diff options
193 files changed, 3218 insertions, 977 deletions
diff --git a/Documentation/ABI/testing/sysfs-power b/Documentation/ABI/testing/sysfs-power index 18b7dc929234..3c5130355011 100644 --- a/Documentation/ABI/testing/sysfs-power +++ b/Documentation/ABI/testing/sysfs-power @@ -300,4 +300,4 @@ Description: attempt. Using this sysfs file will override any values that were - set using the kernel command line for disk offset.
\ No newline at end of file + set using the kernel command line for disk offset. diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml index 27f02ec4bb45..f97a4ecd7b91 100644 --- a/Documentation/devicetree/bindings/riscv/cpus.yaml +++ b/Documentation/devicetree/bindings/riscv/cpus.yaml @@ -152,17 +152,19 @@ examples: - | // Example 2: Spike ISA Simulator with 1 Hart cpus { - cpu@0 { - device_type = "cpu"; - reg = <0>; - compatible = "riscv"; - riscv,isa = "rv64imafdc"; - mmu-type = "riscv,sv48"; - interrupt-controller { - #interrupt-cells = <1>; - interrupt-controller; - compatible = "riscv,cpu-intc"; - }; - }; + #address-cells = <1>; + #size-cells = <0>; + cpu@0 { + device_type = "cpu"; + reg = <0>; + compatible = "riscv"; + riscv,isa = "rv64imafdc"; + mmu-type = "riscv,sv48"; + interrupt-controller { + #interrupt-cells = <1>; + interrupt-controller; + compatible = "riscv,cpu-intc"; + }; + }; }; ... diff --git a/MAINTAINERS b/MAINTAINERS index d0ed735994a5..01a52fc964da 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3122,6 +3122,7 @@ F: arch/arm/mach-bcm/ BROADCOM BCM2835 ARM ARCHITECTURE M: Eric Anholt <eric@anholt.net> M: Stefan Wahren <wahrenst@gmx.net> +L: bcm-kernel-feedback-list@broadcom.com L: linux-rpi-kernel@lists.infradead.org (moderated for non-subscribers) L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) T: git git://github.com/anholt/linux @@ -3151,6 +3152,7 @@ F: arch/arm/boot/dts/bcm953012* BROADCOM BCM53573 ARM ARCHITECTURE M: RafaÅ‚ MiÅ‚ecki <rafal@milecki.pl> +L: bcm-kernel-feedback-list@broadcom.com L: linux-arm-kernel@lists.infradead.org S: Maintained F: arch/arm/boot/dts/bcm53573* @@ -3940,6 +3942,14 @@ M: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com> S: Maintained F: .clang-format +CLANG/LLVM BUILD SUPPORT +L: clang-built-linux@googlegroups.com +W: https://clangbuiltlinux.github.io/ +B: https://github.com/ClangBuiltLinux/linux/issues +C: irc://chat.freenode.net/clangbuiltlinux +S: Supported +K: \b(?i:clang|llvm)\b + CLEANCACHE API M: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> L: linux-kernel@vger.kernel.org @@ -2,8 +2,8 @@ VERSION = 5 PATCHLEVEL = 2 SUBLEVEL = 0 -EXTRAVERSION = -rc6 -NAME = Golden Lions +EXTRAVERSION = -rc7 +NAME = Bobtail Squid # *DOCUMENTATION* # To see a list of typical targets execute "make help" diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 480af1af9e63..03a0b19c92cd 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -5,6 +5,10 @@ KBUILD_DEFCONFIG := nsim_hs_defconfig +ifeq ($(CROSS_COMPILE),) +CROSS_COMPILE := $(call cc-cross-prefix, arc-linux- arceb-linux-) +endif + cflags-y += -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__ cflags-$(CONFIG_ISA_ARCOMPACT) += -mA7 cflags-$(CONFIG_ISA_ARCV2) += -mcpu=hs38 diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c index 6a91a742ab3d..7dd2dd335cf6 100644 --- a/arch/arc/plat-hsdk/platform.c +++ b/arch/arc/plat-hsdk/platform.c @@ -32,8 +32,6 @@ static void __init hsdk_init_per_cpu(unsigned int cpu) #define ARC_PERIPHERAL_BASE 0xf0000000 #define CREG_BASE (ARC_PERIPHERAL_BASE + 0x1000) -#define CREG_PAE (CREG_BASE + 0x180) -#define CREG_PAE_UPDATE (CREG_BASE + 0x194) #define SDIO_BASE (ARC_PERIPHERAL_BASE + 0xA000) #define SDIO_UHS_REG_EXT (SDIO_BASE + 0x108) @@ -99,20 +97,167 @@ static void __init hsdk_enable_gpio_intc_wire(void) iowrite32(GPIO_INT_CONNECTED_MASK, (void __iomem *) GPIO_INTEN); } -static void __init hsdk_init_early(void) +enum hsdk_axi_masters { + M_HS_CORE = 0, + M_HS_RTT, + M_AXI_TUN, + M_HDMI_VIDEO, + M_HDMI_AUDIO, + M_USB_HOST, + M_ETHERNET, + M_SDIO, + M_GPU, + M_DMAC_0, + M_DMAC_1, + M_DVFS +}; + +#define UPDATE_VAL 1 + +/* + * This is modified configuration of AXI bridge. Default settings + * are specified in "Table 111 CREG Address Decoder register reset values". + * + * AXI_M_m_SLV{0|1} - Slave Select register for master 'm'. + * Possible slaves are: + * - 0 => no slave selected + * - 1 => DDR controller port #1 + * - 2 => SRAM controller + * - 3 => AXI tunnel + * - 4 => EBI controller + * - 5 => ROM controller + * - 6 => AXI2APB bridge + * - 7 => DDR controller port #2 + * - 8 => DDR controller port #3 + * - 9 => HS38x4 IOC + * - 10 => HS38x4 DMI + * AXI_M_m_OFFSET{0|1} - Addr Offset register for master 'm' + * + * Please read ARC HS Development IC Specification, section 17.2 for more + * information about apertures configuration. + * + * m master AXI_M_m_SLV0 AXI_M_m_SLV1 AXI_M_m_OFFSET0 AXI_M_m_OFFSET1 + * 0 HS (CBU) 0x11111111 0x63111111 0xFEDCBA98 0x0E543210 + * 1 HS (RTT) 0x77777777 0x77777777 0xFEDCBA98 0x76543210 + * 2 AXI Tunnel 0x88888888 0x88888888 0xFEDCBA98 0x76543210 + * 3 HDMI-VIDEO 0x77777777 0x77777777 0xFEDCBA98 0x76543210 + * 4 HDMI-ADUIO 0x77777777 0x77777777 0xFEDCBA98 0x76543210 + * 5 USB-HOST 0x77777777 0x77999999 0xFEDCBA98 0x76DCBA98 + * 6 ETHERNET 0x77777777 0x77999999 0xFEDCBA98 0x76DCBA98 + * 7 SDIO 0x77777777 0x77999999 0xFEDCBA98 0x76DCBA98 + * 8 GPU 0x77777777 0x77777777 0xFEDCBA98 0x76543210 + * 9 DMAC (port #1) 0x77777777 0x77777777 0xFEDCBA98 0x76543210 + * 10 DMAC (port #2) 0x77777777 0x77777777 0xFEDCBA98 0x76543210 + * 11 DVFS 0x00000000 0x60000000 0x00000000 0x00000000 + */ + +#define CREG_AXI_M_SLV0(m) ((void __iomem *)(CREG_BASE + 0x20 * (m))) +#define CREG_AXI_M_SLV1(m) ((void __iomem *)(CREG_BASE + 0x20 * (m) + 0x04)) +#define CREG_AXI_M_OFT0(m) ((void __iomem *)(CREG_BASE + 0x20 * (m) + 0x08)) +#define CREG_AXI_M_OFT1(m) ((void __iomem *)(CREG_BASE + 0x20 * (m) + 0x0C)) +#define CREG_AXI_M_UPDT(m) ((void __iomem *)(CREG_BASE + 0x20 * (m) + 0x14)) + +#define CREG_AXI_M_HS_CORE_BOOT ((void __iomem *)(CREG_BASE + 0x010)) + +#define CREG_PAE ((void __iomem *)(CREG_BASE + 0x180)) +#define CREG_PAE_UPDT ((void __iomem *)(CREG_BASE + 0x194)) + +static void __init hsdk_init_memory_bridge(void) { + u32 reg; + + /* + * M_HS_CORE has one unique register - BOOT. + * We need to clean boot mirror (BOOT[1:0]) bits in them to avoid first + * aperture to be masked by 'boot mirror'. + */ + reg = readl(CREG_AXI_M_HS_CORE_BOOT) & (~0x3); + writel(reg, CREG_AXI_M_HS_CORE_BOOT); + writel(0x11111111, CREG_AXI_M_SLV0(M_HS_CORE)); + writel(0x63111111, CREG_AXI_M_SLV1(M_HS_CORE)); + writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_HS_CORE)); + writel(0x0E543210, CREG_AXI_M_OFT1(M_HS_CORE)); + writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_HS_CORE)); + + writel(0x77777777, CREG_AXI_M_SLV0(M_HS_RTT)); + writel(0x77777777, CREG_AXI_M_SLV1(M_HS_RTT)); + writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_HS_RTT)); + writel(0x76543210, CREG_AXI_M_OFT1(M_HS_RTT)); + writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_HS_RTT)); + + writel(0x88888888, CREG_AXI_M_SLV0(M_AXI_TUN)); + writel(0x88888888, CREG_AXI_M_SLV1(M_AXI_TUN)); + writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_AXI_TUN)); + writel(0x76543210, CREG_AXI_M_OFT1(M_AXI_TUN)); + writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_AXI_TUN)); + + writel(0x77777777, CREG_AXI_M_SLV0(M_HDMI_VIDEO)); + writel(0x77777777, CREG_AXI_M_SLV1(M_HDMI_VIDEO)); + writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_HDMI_VIDEO)); + writel(0x76543210, CREG_AXI_M_OFT1(M_HDMI_VIDEO)); + writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_HDMI_VIDEO)); + + writel(0x77777777, CREG_AXI_M_SLV0(M_HDMI_AUDIO)); + writel(0x77777777, CREG_AXI_M_SLV1(M_HDMI_AUDIO)); + writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_HDMI_AUDIO)); + writel(0x76543210, CREG_AXI_M_OFT1(M_HDMI_AUDIO)); + writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_HDMI_AUDIO)); + + writel(0x77777777, CREG_AXI_M_SLV0(M_USB_HOST)); + writel(0x77999999, CREG_AXI_M_SLV1(M_USB_HOST)); + writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_USB_HOST)); + writel(0x76DCBA98, CREG_AXI_M_OFT1(M_USB_HOST)); + writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_USB_HOST)); + + writel(0x77777777, CREG_AXI_M_SLV0(M_ETHERNET)); + writel(0x77999999, CREG_AXI_M_SLV1(M_ETHERNET)); + writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_ETHERNET)); + writel(0x76DCBA98, CREG_AXI_M_OFT1(M_ETHERNET)); + writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_ETHERNET)); + + writel(0x77777777, CREG_AXI_M_SLV0(M_SDIO)); + writel(0x77999999, CREG_AXI_M_SLV1(M_SDIO)); + writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_SDIO)); + writel(0x76DCBA98, CREG_AXI_M_OFT1(M_SDIO)); + writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_SDIO)); + + writel(0x77777777, CREG_AXI_M_SLV0(M_GPU)); + writel(0x77777777, CREG_AXI_M_SLV1(M_GPU)); + writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_GPU)); + writel(0x76543210, CREG_AXI_M_OFT1(M_GPU)); + writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_GPU)); + + writel(0x77777777, CREG_AXI_M_SLV0(M_DMAC_0)); + writel(0x77777777, CREG_AXI_M_SLV1(M_DMAC_0)); + writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_DMAC_0)); + writel(0x76543210, CREG_AXI_M_OFT1(M_DMAC_0)); + writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_DMAC_0)); + + writel(0x77777777, CREG_AXI_M_SLV0(M_DMAC_1)); + writel(0x77777777, CREG_AXI_M_SLV1(M_DMAC_1)); + writel(0xFEDCBA98, CREG_AXI_M_OFT0(M_DMAC_1)); + writel(0x76543210, CREG_AXI_M_OFT1(M_DMAC_1)); + writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_DMAC_1)); + + writel(0x00000000, CREG_AXI_M_SLV0(M_DVFS)); + writel(0x60000000, CREG_AXI_M_SLV1(M_DVFS)); + writel(0x00000000, CREG_AXI_M_OFT0(M_DVFS)); + writel(0x00000000, CREG_AXI_M_OFT1(M_DVFS)); + writel(UPDATE_VAL, CREG_AXI_M_UPDT(M_DVFS)); + /* * PAE remapping for DMA clients does not work due to an RTL bug, so * CREG_PAE register must be programmed to all zeroes, otherwise it * will cause problems with DMA to/from peripherals even if PAE40 is * not used. */ + writel(0x00000000, CREG_PAE); + writel(UPDATE_VAL, CREG_PAE_UPDT); +} - /* Default is 1, which means "PAE offset = 4GByte" */ - writel_relaxed(0, (void __iomem *) CREG_PAE); - - /* Really apply settings made above */ - writel(1, (void __iomem *) CREG_PAE_UPDATE); +static void __init hsdk_init_early(void) +{ + hsdk_init_memory_bridge(); /* * Switch SDIO external ciu clock divider from default div-by-8 to diff --git a/arch/arm/boot/dts/gemini-dlink-dir-685.dts b/arch/arm/boot/dts/gemini-dlink-dir-685.dts index cfbfbc91a1e1..3613f05f8a80 100644 --- a/arch/arm/boot/dts/gemini-dlink-dir-685.dts +++ b/arch/arm/boot/dts/gemini-dlink-dir-685.dts @@ -20,7 +20,7 @@ }; chosen { - bootargs = "console=ttyS0,19200n8 root=/dev/sda1 rw rootwait"; + bootargs = "console=ttyS0,19200n8 root=/dev/sda1 rw rootwait consoleblank=300"; stdout-path = "uart0:19200n8"; }; diff --git a/arch/arm/boot/dts/gemini-dlink-dns-313.dts b/arch/arm/boot/dts/gemini-dlink-dns-313.dts index b12504e10f0b..360642a02a48 100644 --- a/arch/arm/boot/dts/gemini-dlink-dns-313.dts +++ b/arch/arm/boot/dts/gemini-dlink-dns-313.dts @@ -11,7 +11,7 @@ / { model = "D-Link DNS-313 1-Bay Network Storage Enclosure"; - compatible = "dlink,dir-313", "cortina,gemini"; + compatible = "dlink,dns-313", "cortina,gemini"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm/boot/dts/imx6ul.dtsi b/arch/arm/boot/dts/imx6ul.dtsi index bbf010c73336..a7f6d1d58e20 100644 --- a/arch/arm/boot/dts/imx6ul.dtsi +++ b/arch/arm/boot/dts/imx6ul.dtsi @@ -358,7 +358,7 @@ pwm1: pwm@2080000 { compatible = "fsl,imx6ul-pwm", "fsl,imx27-pwm"; reg = <0x02080000 0x4000>; - interrupts = <GIC_SPI 115 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6UL_CLK_PWM1>, <&clks IMX6UL_CLK_PWM1>; clock-names = "ipg", "per"; @@ -369,7 +369,7 @@ pwm2: pwm@2084000 { compatible = "fsl,imx6ul-pwm", "fsl,imx27-pwm"; reg = <0x02084000 0x4000>; - interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 84 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6UL_CLK_PWM2>, <&clks IMX6UL_CLK_PWM2>; clock-names = "ipg", "per"; @@ -380,7 +380,7 @@ pwm3: pwm@2088000 { compatible = "fsl,imx6ul-pwm", "fsl,imx27-pwm"; reg = <0x02088000 0x4000>; - interrupts = <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 85 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6UL_CLK_PWM3>, <&clks IMX6UL_CLK_PWM3>; clock-names = "ipg", "per"; @@ -391,7 +391,7 @@ pwm4: pwm@208c000 { compatible = "fsl,imx6ul-pwm", "fsl,imx27-pwm"; reg = <0x0208c000 0x4000>; - interrupts = <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6UL_CLK_PWM4>, <&clks IMX6UL_CLK_PWM4>; clock-names = "ipg", "per"; diff --git a/arch/arm/boot/dts/meson8.dtsi b/arch/arm/boot/dts/meson8.dtsi index 7ef442462ea4..40c11b6b217a 100644 --- a/arch/arm/boot/dts/meson8.dtsi +++ b/arch/arm/boot/dts/meson8.dtsi @@ -248,8 +248,8 @@ <GIC_SPI 167 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 169 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 172 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 173 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 170 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 172 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 173 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 174 IRQ_TYPE_LEVEL_HIGH>, @@ -264,7 +264,6 @@ clocks = <&clkc CLKID_CLK81>, <&clkc CLKID_MALI>; clock-names = "bus", "core"; operating-points-v2 = <&gpu_opp_table>; - switch-delay = <0xffff>; }; }; }; /* end of / */ diff --git a/arch/arm/boot/dts/meson8b.dtsi b/arch/arm/boot/dts/meson8b.dtsi index 800cd65fc50a..ec67f49116d9 100644 --- a/arch/arm/boot/dts/meson8b.dtsi +++ b/arch/arm/boot/dts/meson8b.dtsi @@ -163,23 +163,23 @@ opp-255000000 { opp-hz = /bits/ 64 <255000000>; - opp-microvolt = <1150000>; + opp-microvolt = <1100000>; }; opp-364300000 { opp-hz = /bits/ 64 <364300000>; - opp-microvolt = <1150000>; + opp-microvolt = <1100000>; }; opp-425000000 { opp-hz = /bits/ 64 <425000000>; - opp-microvolt = <1150000>; + opp-microvolt = <1100000>; }; opp-510000000 { opp-hz = /bits/ 64 <510000000>; - opp-microvolt = <1150000>; + opp-microvolt = <1100000>; }; opp-637500000 { opp-hz = /bits/ 64 <637500000>; - opp-microvolt = <1150000>; + opp-microvolt = <1100000>; turbo-mode; }; }; @@ -229,7 +229,6 @@ clocks = <&clkc CLKID_CLK81>, <&clkc CLKID_MALI>; clock-names = "bus", "core"; operating-points-v2 = <&gpu_opp_table>; - switch-delay = <0xffff>; }; }; }; /* end of / */ diff --git a/arch/arm/mach-omap2/prm3xxx.c b/arch/arm/mach-omap2/prm3xxx.c index fd4a3bf27993..1b442b128569 100644 --- a/arch/arm/mach-omap2/prm3xxx.c +++ b/arch/arm/mach-omap2/prm3xxx.c @@ -430,7 +430,7 @@ static void omap3_prm_reconfigure_io_chain(void) * registers, and omap3xxx_prm_reconfigure_io_chain() must be called. * No return value. */ -static void __init omap3xxx_prm_enable_io_wakeup(void) +static void omap3xxx_prm_enable_io_wakeup(void) { if (prm_features & PRM_HAS_IO_WAKEUP) omap2_prm_set_mod_reg_bits(OMAP3430_EN_IO_MASK, WKUP_MOD, diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index b04581249f0b..bf7f845447ed 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -28,7 +28,7 @@ enable-method = "psci"; clocks = <&clockgen 1 0>; next-level-cache = <&l2>; - cpu-idle-states = <&CPU_PH20>; + cpu-idle-states = <&CPU_PW20>; }; cpu1: cpu@1 { @@ -38,7 +38,7 @@ enable-method = "psci"; clocks = <&clockgen 1 0>; next-level-cache = <&l2>; - cpu-idle-states = <&CPU_PH20>; + cpu-idle-states = <&CPU_PW20>; }; l2: l2-cache { @@ -53,13 +53,13 @@ */ entry-method = "arm,psci"; - CPU_PH20: cpu-ph20 { - compatible = "arm,idle-state"; - idle-state-name = "PH20"; - arm,psci-suspend-param = <0x00010000>; - entry-latency-us = <1000>; - exit-latency-us = <1000>; - min-residency-us = <3000>; + CPU_PW20: cpu-pw20 { + compatible = "arm,idle-state"; + idle-state-name = "PW20"; + arm,psci-suspend-param = <0x0>; + entry-latency-us = <2000>; + exit-latency-us = <2000>; + min-residency-us = <6000>; }; }; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 4d583514258c..6bca5b082ea4 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -613,6 +613,7 @@ CONFIG_RTC_DRV_TEGRA=y CONFIG_RTC_DRV_IMX_SC=m CONFIG_RTC_DRV_XGENE=y CONFIG_DMADEVICES=y +CONFIG_FSL_EDMA=y CONFIG_DMA_BCM2835=m CONFIG_K3_DMA=y CONFIG_MV_XOR=y diff --git a/arch/csky/kernel/signal.c b/arch/csky/kernel/signal.c index 04a43cfd4e09..d47a3381aad8 100644 --- a/arch/csky/kernel/signal.c +++ b/arch/csky/kernel/signal.c @@ -39,6 +39,11 @@ static int save_fpu_state(struct sigcontext __user *sc) #endif struct rt_sigframe { + /* + * pad[3] is compatible with the same struct defined in + * gcc/libgcc/config/csky/linux-unwind.h + */ + int pad[3]; struct siginfo info; struct ucontext uc; }; diff --git a/arch/mips/include/asm/mips-gic.h b/arch/mips/include/asm/mips-gic.h index 75a1cdee1331..084cac1c5ea2 100644 --- a/arch/mips/include/asm/mips-gic.h +++ b/arch/mips/include/asm/mips-gic.h @@ -311,6 +311,36 @@ static inline bool mips_gic_present(void) } /** + * mips_gic_vx_map_reg() - Return GIC_Vx_<intr>_MAP register offset + * @intr: A GIC local interrupt + * + * Determine the index of the GIC_VL_<intr>_MAP or GIC_VO_<intr>_MAP register + * within the block of GIC map registers. This is almost the same as the order + * of interrupts in the pending & mask registers, as used by enum + * mips_gic_local_interrupt, but moves the FDC interrupt & thus offsets the + * interrupts after it... + * + * Return: The map register index corresponding to @intr. + * + * The return value is suitable for use with the (read|write)_gic_v[lo]_map + * accessor functions. + */ +static inline unsigned int +mips_gic_vx_map_reg(enum mips_gic_local_interrupt intr) +{ + /* WD, Compare & Timer are 1:1 */ + if (intr <= GIC_LOCAL_INT_TIMER) + return intr; + + /* FDC moves to after Timer... */ + if (intr == GIC_LOCAL_INT_FDC) + return GIC_LOCAL_INT_TIMER + 1; + + /* As a result everything else is offset by 1 */ + return intr + 1; +} + +/** * gic_get_c0_compare_int() - Return cp0 count/compare interrupt virq * * Determine the virq number to use for the coprocessor 0 count/compare diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c index f241ded9239b..1f0f29a289d3 100644 --- a/arch/parisc/kernel/module.c +++ b/arch/parisc/kernel/module.c @@ -786,6 +786,10 @@ int apply_relocate_add(Elf_Shdr *sechdrs, /* 32-bit PC relative address */ *loc = val - dot - 8 + addend; break; + case R_PARISC_PCREL64: + /* 64-bit PC relative address */ + *loc64 = val - dot - 8 + addend; + break; case R_PARISC_DIR64: /* 64-bit effective address */ *loc64 = val + addend; diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 6b86055e5251..73ba246ca11d 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -315,7 +315,7 @@ TRAMP_REAL_BEGIN(machine_check_common_early) mfspr r11,SPRN_DSISR /* Save DSISR */ std r11,_DSISR(r1) std r9,_CCR(r1) /* Save CR in stackframe */ - kuap_save_amr_and_lock r9, r10, cr1 + /* We don't touch AMR here, we never go to virtual mode */ /* Save r9 through r13 from EXMC save area to stack frame. */ EXCEPTION_PROLOG_COMMON_2(PACA_EXMC) mfmsr r11 /* get MSR value */ diff --git a/arch/powerpc/kernel/suspend.c b/arch/powerpc/kernel/suspend.c index c612d50c9d18..b84992c10854 100644 --- a/arch/powerpc/kernel/suspend.c +++ b/arch/powerpc/kernel/suspend.c @@ -7,6 +7,7 @@ */ #include <linux/mm.h> +#include <linux/suspend.h> #include <asm/page.h> #include <asm/sections.h> diff --git a/arch/powerpc/mm/book3s64/mmu_context.c b/arch/powerpc/mm/book3s64/mmu_context.c index bb70391401f7..794404d50a85 100644 --- a/arch/powerpc/mm/book3s64/mmu_context.c +++ b/arch/powerpc/mm/book3s64/mmu_context.c @@ -50,20 +50,52 @@ EXPORT_SYMBOL_GPL(hash__alloc_context_id); void slb_setup_new_exec(void); +static int realloc_context_ids(mm_context_t *ctx) +{ + int i, id; + + /* + * id 0 (aka. ctx->id) is special, we always allocate a new one, even if + * there wasn't one allocated previously (which happens in the exec + * case where ctx is newly allocated). + * + * We have to be a bit careful here. We must keep the existing ids in + * the array, so that we can test if they're non-zero to decide if we + * need to allocate a new one. However in case of error we must free the + * ids we've allocated but *not* any of the existing ones (or risk a + * UAF). That's why we decrement i at the start of the error handling + * loop, to skip the id that we just tested but couldn't reallocate. + */ + for (i = 0; i < ARRAY_SIZE(ctx->extended_id); i++) { + if (i == 0 || ctx->extended_id[i]) { + id = hash__alloc_context_id(); + if (id < 0) + goto error; + + ctx->extended_id[i] = id; + } + } + + /* The caller expects us to return id */ + return ctx->id; + +error: + for (i--; i >= 0; i--) { + if (ctx->extended_id[i]) + ida_free(&mmu_context_ida, ctx->extended_id[i]); + } + + return id; +} + static int hash__init_new_context(struct mm_struct *mm) { int index; - index = hash__alloc_context_id(); - if (index < 0) - return index; - mm->context.hash_context = kmalloc(sizeof(struct hash_mm_context), GFP_KERNEL); - if (!mm->context.hash_context) { - ida_free(&mmu_context_ida, index); + if (!mm->context.hash_context) return -ENOMEM; - } /* * The old code would re-promote on fork, we don't do that when using @@ -91,13 +123,20 @@ static int hash__init_new_context(struct mm_struct *mm) mm->context.hash_context->spt = kmalloc(sizeof(struct subpage_prot_table), GFP_KERNEL); if (!mm->context.hash_context->spt) { - ida_free(&mmu_context_ida, index); kfree(mm->context.hash_context); return -ENOMEM; } } #endif + } + index = realloc_context_ids(&mm->context); + if (index < 0) { +#ifdef CONFIG_PPC_SUBPAGE_PROT + kfree(mm->context.hash_context->spt); +#endif + kfree(mm->context.hash_context); + return index; } pkey_mm_init(mm); diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi index 3c06ee4b2b29..40983491b95f 100644 --- a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi +++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi @@ -163,6 +163,7 @@ interrupt-parent = <&plic0>; interrupts = <4>; clocks = <&prci PRCI_CLK_TLCLK>; + status = "disabled"; }; uart1: serial@10011000 { compatible = "sifive,fu540-c000-uart", "sifive,uart0"; @@ -170,6 +171,7 @@ interrupt-parent = <&plic0>; interrupts = <5>; clocks = <&prci PRCI_CLK_TLCLK>; + status = "disabled"; }; i2c0: i2c@10030000 { compatible = "sifive,fu540-c000-i2c", "sifive,i2c0"; @@ -181,6 +183,7 @@ reg-io-width = <1>; #address-cells = <1>; #size-cells = <0>; + status = "disabled"; }; qspi0: spi@10040000 { compatible = "sifive,fu540-c000-spi", "sifive,spi0"; @@ -191,6 +194,7 @@ clocks = <&prci PRCI_CLK_TLCLK>; #address-cells = <1>; #size-cells = <0>; + status = "disabled"; }; qspi1: spi@10041000 { compatible = "sifive,fu540-c000-spi", "sifive,spi0"; @@ -201,6 +205,7 @@ clocks = <&prci PRCI_CLK_TLCLK>; #address-cells = <1>; #size-cells = <0>; + status = "disabled"; }; qspi2: spi@10050000 { compatible = "sifive,fu540-c000-spi", "sifive,spi0"; @@ -210,6 +215,7 @@ clocks = <&prci PRCI_CLK_TLCLK>; #address-cells = <1>; #size-cells = <0>; + status = "disabled"; }; }; }; diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 4da88707e28f..0b55c53c08c7 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -42,7 +42,20 @@ }; }; +&uart0 { + status = "okay"; +}; + +&uart1 { + status = "okay"; +}; + +&i2c0 { + status = "okay"; +}; + &qspi0 { + status = "okay"; flash@0 { compatible = "issi,is25wp256", "jedec,spi-nor"; reg = <0>; diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 4f02967e55de..04944fb4fa7a 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -69,6 +69,7 @@ CONFIG_VIRTIO_MMIO=y CONFIG_CLK_SIFIVE=y CONFIG_CLK_SIFIVE_FU540_PRCI=y CONFIG_SIFIVE_PLIC=y +CONFIG_SPI_SIFIVE=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_AUTOFS4_FS=y @@ -84,4 +85,8 @@ CONFIG_ROOT_NFS=y CONFIG_CRYPTO_USER_API_HASH=y CONFIG_CRYPTO_DEV_VIRTIO=y CONFIG_PRINTK_TIME=y +CONFIG_SPI=y +CONFIG_MMC_SPI=y +CONFIG_MMC=y +CONFIG_DEVTMPFS_MOUNT=y # CONFIG_RCU_TRACE is not set diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 3e2708c626a8..f960c3f4ce47 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -272,9 +272,6 @@ vmalloc_fault: * entries, but in RISC-V, SFENCE.VMA specifies an * ordering constraint, not a cache flush; it is * necessary even after writing invalid entries. - * Relying on flush_tlb_fix_spurious_fault would - * suffice, but the extra traps reduce - * performance. So, eagerly SFENCE.VMA. */ local_flush_tlb_page(addr); diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 20420c2b8a14..b2956d49b6ad 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -63,7 +63,6 @@ void __init startup_init(void); void die(struct pt_regs *regs, const char *str); int setup_profiling_timer(unsigned int multiplier); void __init time_init(void); -int pfn_is_nosave(unsigned long); void s390_early_resume(void); unsigned long prepare_ftrace_return(unsigned long parent, unsigned long sp, unsigned long ip); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index f315425d8468..3cd94a21bd53 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -561,14 +561,14 @@ int x86_pmu_hw_config(struct perf_event *event) } /* sample_regs_user never support XMM registers */ - if (unlikely(event->attr.sample_regs_user & PEBS_XMM_REGS)) + if (unlikely(event->attr.sample_regs_user & PERF_REG_EXTENDED_MASK)) return -EINVAL; /* * Besides the general purpose registers, XMM registers may * be collected in PEBS on some platforms, e.g. Icelake */ - if (unlikely(event->attr.sample_regs_intr & PEBS_XMM_REGS)) { - if (x86_pmu.pebs_no_xmm_regs) + if (unlikely(event->attr.sample_regs_intr & PERF_REG_EXTENDED_MASK)) { + if (!(event->pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS)) return -EINVAL; if (!event->attr.precise_ip) @@ -2402,13 +2402,13 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re return; } - if (perf_hw_regs(regs)) { - if (perf_callchain_store(entry, regs->ip)) - return; + if (perf_callchain_store(entry, regs->ip)) + return; + + if (perf_hw_regs(regs)) unwind_start(&state, current, regs, NULL); - } else { + else unwind_start(&state, current, NULL, (void *)regs->sp); - } for (; !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 7acc526b4ad2..505c73dc6a73 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -987,7 +987,7 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event) pebs_data_cfg |= PEBS_DATACFG_GP; if ((sample_type & PERF_SAMPLE_REGS_INTR) && - (attr->sample_regs_intr & PEBS_XMM_REGS)) + (attr->sample_regs_intr & PERF_REG_EXTENDED_MASK)) pebs_data_cfg |= PEBS_DATACFG_XMMS; if (sample_type & PERF_SAMPLE_BRANCH_STACK) { @@ -1964,10 +1964,9 @@ void __init intel_ds_init(void) x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS); x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS); x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE; - if (x86_pmu.version <= 4) { + if (x86_pmu.version <= 4) x86_pmu.pebs_no_isolation = 1; - x86_pmu.pebs_no_xmm_regs = 1; - } + if (x86_pmu.pebs) { char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-'; char *pebs_qual = ""; @@ -2020,9 +2019,9 @@ void __init intel_ds_init(void) PERF_SAMPLE_TIME; x86_pmu.flags |= PMU_FL_PEBS_ALL; pebs_qual = "-baseline"; + x86_get_pmu()->capabilities |= PERF_PMU_CAP_EXTENDED_REGS; } else { /* Only basic record supported */ - x86_pmu.pebs_no_xmm_regs = 1; x86_pmu.large_pebs_flags &= ~(PERF_SAMPLE_ADDR | PERF_SAMPLE_TIME | diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index a6ac2f4f76fc..4e346856ee19 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -121,24 +121,6 @@ struct amd_nb { (1ULL << PERF_REG_X86_R14) | \ (1ULL << PERF_REG_X86_R15)) -#define PEBS_XMM_REGS \ - ((1ULL << PERF_REG_X86_XMM0) | \ - (1ULL << PERF_REG_X86_XMM1) | \ - (1ULL << PERF_REG_X86_XMM2) | \ - (1ULL << PERF_REG_X86_XMM3) | \ - (1ULL << PERF_REG_X86_XMM4) | \ - (1ULL << PERF_REG_X86_XMM5) | \ - (1ULL << PERF_REG_X86_XMM6) | \ - (1ULL << PERF_REG_X86_XMM7) | \ - (1ULL << PERF_REG_X86_XMM8) | \ - (1ULL << PERF_REG_X86_XMM9) | \ - (1ULL << PERF_REG_X86_XMM10) | \ - (1ULL << PERF_REG_X86_XMM11) | \ - (1ULL << PERF_REG_X86_XMM12) | \ - (1ULL << PERF_REG_X86_XMM13) | \ - (1ULL << PERF_REG_X86_XMM14) | \ - (1ULL << PERF_REG_X86_XMM15)) - /* * Per register state. */ @@ -668,8 +650,7 @@ struct x86_pmu { pebs_broken :1, pebs_prec_dist :1, pebs_no_tlb :1, - pebs_no_isolation :1, - pebs_no_xmm_regs :1; + pebs_no_isolation :1; int pebs_record_size; int pebs_buffer_size; int max_pebs_events; diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h index ac67bbea10ca..7c9d2bb3833b 100644 --- a/arch/x86/include/uapi/asm/perf_regs.h +++ b/arch/x86/include/uapi/asm/perf_regs.h @@ -52,4 +52,7 @@ enum perf_event_x86_regs { /* These include both GPRs and XMMX registers */ PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2, }; + +#define PERF_REG_EXTENDED_MASK (~((1ULL << PERF_REG_X86_XMM0) - 1)) + #endif /* _ASM_X86_PERF_REGS_H */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 177aa8ef2afa..85be316665b4 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1464,7 +1464,8 @@ static void apic_pending_intr_clear(void) if (queued) { if (boot_cpu_has(X86_FEATURE_TSC) && cpu_khz) { ntsc = rdtsc(); - max_loops = (cpu_khz << 10) - (ntsc - tsc); + max_loops = (long long)cpu_khz << 10; + max_loops -= ntsc - tsc; } else { max_loops--; } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 03b4cc0ec3a7..66ca906aa790 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -836,6 +836,16 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) } /* + * If SSBD is controlled by the SPEC_CTRL MSR, then set the proper + * bit in the mask to allow guests to use the mitigation even in the + * case where the host does not enable it. + */ + if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || + static_cpu_has(X86_FEATURE_AMD_SSBD)) { + x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; + } + + /* * We have three CPU feature flags that are in play here: * - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible. * - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass @@ -852,7 +862,6 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) x86_amd_ssb_disable(); } else { x86_spec_ctrl_base |= SPEC_CTRL_SSBD; - x86_spec_ctrl_mask |= SPEC_CTRL_SSBD; wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); } } diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index a813987b5552..cb0fdcaf1415 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -789,13 +789,16 @@ static struct syscore_ops mc_syscore_ops = { .resume = mc_bp_resume, }; -static int mc_cpu_online(unsigned int cpu) +static int mc_cpu_starting(unsigned int cpu) { - struct device *dev; - - dev = get_cpu_device(cpu); microcode_update_cpu(cpu); pr_debug("CPU%d added\n", cpu); + return 0; +} + +static int mc_cpu_online(unsigned int cpu) +{ + struct device *dev = get_cpu_device(cpu); if (sysfs_create_group(&dev->kobj, &mc_attr_group)) pr_err("Failed to create group for CPU%d\n", cpu); @@ -872,7 +875,9 @@ int __init microcode_init(void) goto out_ucode_group; register_syscore_ops(&mc_syscore_ops); - cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:online", + cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:starting", + mc_cpu_starting, NULL); + cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/microcode:online", mc_cpu_online, mc_cpu_down_prep); pr_info("Microcode Update Driver: v%s.", DRIVER_VERSION); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 2131b8bbaad7..2f4824793798 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -796,8 +796,12 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, struct seq_file *seq, void *v) { struct rdt_resource *r = of->kn->parent->priv; - u32 sw_shareable = 0, hw_shareable = 0; - u32 exclusive = 0, pseudo_locked = 0; + /* + * Use unsigned long even though only 32 bits are used to ensure + * test_bit() is used safely. + */ + unsigned long sw_shareable = 0, hw_shareable = 0; + unsigned long exclusive = 0, pseudo_locked = 0; struct rdt_domain *dom; int i, hwb, swb, excl, psl; enum rdtgrp_mode mode; @@ -842,10 +846,10 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, } for (i = r->cache.cbm_len - 1; i >= 0; i--) { pseudo_locked = dom->plr ? dom->plr->cbm : 0; - hwb = test_bit(i, (unsigned long *)&hw_shareable); - swb = test_bit(i, (unsigned long *)&sw_shareable); - excl = test_bit(i, (unsigned long *)&exclusive); - psl = test_bit(i, (unsigned long *)&pseudo_locked); + hwb = test_bit(i, &hw_shareable); + swb = test_bit(i, &sw_shareable); + excl = test_bit(i, &exclusive); + psl = test_bit(i, &pseudo_locked); if (hwb && swb) seq_putc(seq, 'X'); else if (hwb && !swb) @@ -2486,26 +2490,19 @@ out_destroy: */ static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r) { - /* - * Convert the u32 _val to an unsigned long required by all the bit - * operations within this function. No more than 32 bits of this - * converted value can be accessed because all bit operations are - * additionally provided with cbm_len that is initialized during - * hardware enumeration using five bits from the EAX register and - * thus never can exceed 32 bits. - */ - unsigned long *val = (unsigned long *)_val; + unsigned long val = *_val; unsigned int cbm_len = r->cache.cbm_len; unsigned long first_bit, zero_bit; - if (*val == 0) + if (val == 0) return; - first_bit = find_first_bit(val, cbm_len); - zero_bit = find_next_zero_bit(val, cbm_len, first_bit); + first_bit = find_first_bit(&val, cbm_len); + zero_bit = find_next_zero_bit(&val, cbm_len, first_bit); /* Clear any remaining bits to ensure contiguous region */ - bitmap_clear(val, zero_bit, cbm_len - zero_bit); + bitmap_clear(&val, zero_bit, cbm_len - zero_bit); + *_val = (u32)val; } /* diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 16b1cbd3a61e..29ffa495bd1c 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -184,24 +184,25 @@ unsigned long __head __startup_64(unsigned long physaddr, pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask(); if (la57) { - p4d = fixup_pointer(early_dynamic_pgts[next_early_pgt++], physaddr); + p4d = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], + physaddr); i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; pgd[i + 0] = (pgdval_t)p4d + pgtable_flags; pgd[i + 1] = (pgdval_t)p4d + pgtable_flags; - i = (physaddr >> P4D_SHIFT) % PTRS_PER_P4D; - p4d[i + 0] = (pgdval_t)pud + pgtable_flags; - p4d[i + 1] = (pgdval_t)pud + pgtable_flags; + i = physaddr >> P4D_SHIFT; + p4d[(i + 0) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags; + p4d[(i + 1) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags; } else { i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; pgd[i + 0] = (pgdval_t)pud + pgtable_flags; pgd[i + 1] = (pgdval_t)pud + pgtable_flags; } - i = (physaddr >> PUD_SHIFT) % PTRS_PER_PUD; - pud[i + 0] = (pudval_t)pmd + pgtable_flags; - pud[i + 1] = (pudval_t)pmd + pgtable_flags; + i = physaddr >> PUD_SHIFT; + pud[(i + 0) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags; + pud[(i + 1) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags; pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL; /* Filter out unsupported __PAGE_KERNEL_* bits: */ @@ -211,8 +212,9 @@ unsigned long __head __startup_64(unsigned long physaddr, pmd_entry += physaddr; for (i = 0; i < DIV_ROUND_UP(_end - _text, PMD_SIZE); i++) { - int idx = i + (physaddr >> PMD_SHIFT) % PTRS_PER_PMD; - pmd[idx] = pmd_entry + i * PMD_SIZE; + int idx = i + (physaddr >> PMD_SHIFT); + + pmd[idx % PTRS_PER_PMD] = pmd_entry + i * PMD_SIZE; } /* diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c index 07c30ee17425..bb7e1132290b 100644 --- a/arch/x86/kernel/perf_regs.c +++ b/arch/x86/kernel/perf_regs.c @@ -74,6 +74,9 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) return regs_get_register(regs, pt_regs_offset[idx]); } +#define PERF_REG_X86_RESERVED (((1ULL << PERF_REG_X86_XMM0) - 1) & \ + ~((1ULL << PERF_REG_X86_MAX) - 1)) + #ifdef CONFIG_X86_32 #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_R8) | \ (1ULL << PERF_REG_X86_R9) | \ @@ -86,7 +89,7 @@ u64 perf_reg_value(struct pt_regs *regs, int idx) int perf_reg_validate(u64 mask) { - if (!mask || (mask & REG_NOSUPPORT)) + if (!mask || (mask & (REG_NOSUPPORT | PERF_REG_X86_RESERVED))) return -EINVAL; return 0; @@ -112,7 +115,7 @@ void perf_get_regs_user(struct perf_regs *regs_user, int perf_reg_validate(u64 mask) { - if (!mask || (mask & REG_NOSUPPORT)) + if (!mask || (mask & (REG_NOSUPPORT | PERF_REG_X86_RESERVED))) return -EINVAL; return 0; diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 33b66b5c5aec..72b997eaa1fc 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -82,9 +82,9 @@ static struct orc_entry *orc_find(unsigned long ip); * But they are copies of the ftrace entries that are static and * defined in ftrace_*.S, which do have orc entries. * - * If the undwinder comes across a ftrace trampoline, then find the + * If the unwinder comes across a ftrace trampoline, then find the * ftrace function that was used to create it, and use that ftrace - * function's orc entrie, as the placement of the return code in + * function's orc entry, as the placement of the return code in * the stack will be identical. */ static struct orc_entry *orc_ftrace_find(unsigned long ip) @@ -128,6 +128,16 @@ static struct orc_entry null_orc_entry = { .type = ORC_TYPE_CALL }; +/* Fake frame pointer entry -- used as a fallback for generated code */ +static struct orc_entry orc_fp_entry = { + .type = ORC_TYPE_CALL, + .sp_reg = ORC_REG_BP, + .sp_offset = 16, + .bp_reg = ORC_REG_PREV_SP, + .bp_offset = -16, + .end = 0, +}; + static struct orc_entry *orc_find(unsigned long ip) { static struct orc_entry *orc; @@ -392,8 +402,16 @@ bool unwind_next_frame(struct unwind_state *state) * calls and calls to noreturn functions. */ orc = orc_find(state->signal ? state->ip : state->ip - 1); - if (!orc) - goto err; + if (!orc) { + /* + * As a fallback, try to assume this code uses a frame pointer. + * This is useful for generated code, like BPF, which ORC + * doesn't know about. This is just a guess, so the rest of + * the unwind is no longer considered reliable. + */ + orc = &orc_fp_entry; + state->error = true; + } /* End-of-stack check for kernel threads: */ if (orc->sp_reg == ORC_REG_UNDEFINED) { diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 693aaf28d5fe..0f01c7b1d217 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -671,23 +671,25 @@ static unsigned long __meminit phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end, unsigned long page_size_mask, bool init) { - unsigned long paddr_next, paddr_last = paddr_end; - unsigned long vaddr = (unsigned long)__va(paddr); - int i = p4d_index(vaddr); + unsigned long vaddr, vaddr_end, vaddr_next, paddr_next, paddr_last; + + paddr_last = paddr_end; + vaddr = (unsigned long)__va(paddr); + vaddr_end = (unsigned long)__va(paddr_end); if (!pgtable_l5_enabled()) return phys_pud_init((pud_t *) p4d_page, paddr, paddr_end, page_size_mask, init); - for (; i < PTRS_PER_P4D; i++, paddr = paddr_next) { - p4d_t *p4d; + for (; vaddr < vaddr_end; vaddr = vaddr_next) { + p4d_t *p4d = p4d_page + p4d_index(vaddr); pud_t *pud; - vaddr = (unsigned long)__va(paddr); - p4d = p4d_page + p4d_index(vaddr); - paddr_next = (paddr & P4D_MASK) + P4D_SIZE; + vaddr_next = (vaddr & P4D_MASK) + P4D_SIZE; + paddr = __pa(vaddr); if (paddr >= paddr_end) { + paddr_next = __pa(vaddr_next); if (!after_bootmem && !e820__mapped_any(paddr & P4D_MASK, paddr_next, E820_TYPE_RAM) && @@ -699,13 +701,13 @@ phys_p4d_init(p4d_t *p4d_page, unsigned long paddr, unsigned long paddr_end, if (!p4d_none(*p4d)) { pud = pud_offset(p4d, 0); - paddr_last = phys_pud_init(pud, paddr, paddr_end, - page_size_mask, init); + paddr_last = phys_pud_init(pud, paddr, __pa(vaddr_end), + page_size_mask, init); continue; } pud = alloc_low_page(); - paddr_last = phys_pud_init(pud, paddr, paddr_end, + paddr_last = phys_pud_init(pud, paddr, __pa(vaddr_end), page_size_mask, init); spin_lock(&init_mm.page_table_lock); diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 632b83885867..3b9fd679cea9 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -728,7 +728,7 @@ void efi_recover_from_page_fault(unsigned long phys_addr) * Address range 0x0000 - 0x0fff is always mapped in the efi_pgd, so * page faulting on these addresses isn't expected. */ - if (phys_addr >= 0x0000 && phys_addr <= 0x0fff) + if (phys_addr <= 0x0fff) return; /* diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index f8d430f88d25..f9269ae6da9c 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -240,7 +240,7 @@ static struct kmem_cache *bfq_pool; * containing only random (seeky) I/O are prevented from being tagged * as soft real-time. */ -#define BFQQ_TOTALLY_SEEKY(bfqq) (bfqq->seek_history & -1) +#define BFQQ_TOTALLY_SEEKY(bfqq) (bfqq->seek_history == -1) /* Min number of samples required to perform peak-rate update */ #define BFQ_RATE_MIN_SAMPLES 32 diff --git a/drivers/acpi/acpi_lpit.c b/drivers/acpi/acpi_lpit.c index 6116b0fb86d4..433376e819bb 100644 --- a/drivers/acpi/acpi_lpit.c +++ b/drivers/acpi/acpi_lpit.c @@ -129,7 +129,7 @@ static void lpit_update_residency(struct lpit_residency_info *info, static void lpit_process(u64 begin, u64 end) { - while (begin + sizeof(struct acpi_lpit_native) < end) { + while (begin + sizeof(struct acpi_lpit_native) <= end) { struct acpi_lpit_native *lpit_native = (struct acpi_lpit_native *)begin; if (!lpit_native->header.type && !lpit_native->header.flags) { @@ -148,7 +148,6 @@ static void lpit_process(u64 begin, u64 end) void acpi_init_lpit(void) { acpi_status status; - u64 lpit_begin; struct acpi_table_lpit *lpit; status = acpi_get_table(ACPI_SIG_LPIT, 0, (struct acpi_table_header **)&lpit); @@ -156,6 +155,6 @@ void acpi_init_lpit(void) if (ACPI_FAILURE(status)) return; - lpit_begin = (u64)lpit + sizeof(*lpit); - lpit_process(lpit_begin, lpit_begin + lpit->header.length); + lpit_process((u64)lpit + sizeof(*lpit), + (u64)lpit + lpit->header.length); } diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index 23484aa877b6..398451839178 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -1061,6 +1061,13 @@ static int acpi_lpss_suspend_noirq(struct device *dev) int ret; if (pdata->dev_desc->resume_from_noirq) { + /* + * The driver's ->suspend_late callback will be invoked by + * acpi_lpss_do_suspend_late(), with the assumption that the + * driver really wanted to run that code in ->suspend_noirq, but + * it could not run after acpi_dev_suspend() and the driver + * expected the latter to be called in the "late" phase. + */ ret = acpi_lpss_do_suspend_late(dev); if (ret) return ret; @@ -1091,16 +1098,99 @@ static int acpi_lpss_resume_noirq(struct device *dev) struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); int ret; - ret = acpi_subsys_resume_noirq(dev); + /* Follow acpi_subsys_resume_noirq(). */ + if (dev_pm_may_skip_resume(dev)) + return 0; + + if (dev_pm_smart_suspend_and_suspended(dev)) + pm_runtime_set_active(dev); + + ret = pm_generic_resume_noirq(dev); if (ret) return ret; - if (!dev_pm_may_skip_resume(dev) && pdata->dev_desc->resume_from_noirq) - ret = acpi_lpss_do_resume_early(dev); + if (!pdata->dev_desc->resume_from_noirq) + return 0; - return ret; + /* + * The driver's ->resume_early callback will be invoked by + * acpi_lpss_do_resume_early(), with the assumption that the driver + * really wanted to run that code in ->resume_noirq, but it could not + * run before acpi_dev_resume() and the driver expected the latter to be + * called in the "early" phase. + */ + return acpi_lpss_do_resume_early(dev); +} + +static int acpi_lpss_do_restore_early(struct device *dev) +{ + int ret = acpi_lpss_resume(dev); + + return ret ? ret : pm_generic_restore_early(dev); } +static int acpi_lpss_restore_early(struct device *dev) +{ + struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); + + if (pdata->dev_desc->resume_from_noirq) + return 0; + + return acpi_lpss_do_restore_early(dev); +} + +static int acpi_lpss_restore_noirq(struct device *dev) +{ + struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); + int ret; + + ret = pm_generic_restore_noirq(dev); + if (ret) + return ret; + + if (!pdata->dev_desc->resume_from_noirq) + return 0; + + /* This is analogous to what happens in acpi_lpss_resume_noirq(). */ + return acpi_lpss_do_restore_early(dev); +} + +static int acpi_lpss_do_poweroff_late(struct device *dev) +{ + int ret = pm_generic_poweroff_late(dev); + + return ret ? ret : acpi_lpss_suspend(dev, device_may_wakeup(dev)); +} + +static int acpi_lpss_poweroff_late(struct device *dev) +{ + struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); + + if (dev_pm_smart_suspend_and_suspended(dev)) + return 0; + + if (pdata->dev_desc->resume_from_noirq) + return 0; + + return acpi_lpss_do_poweroff_late(dev); +} + +static int acpi_lpss_poweroff_noirq(struct device *dev) +{ + struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev)); + + if (dev_pm_smart_suspend_and_suspended(dev)) + return 0; + + if (pdata->dev_desc->resume_from_noirq) { + /* This is analogous to the acpi_lpss_suspend_noirq() case. */ + int ret = acpi_lpss_do_poweroff_late(dev); + if (ret) + return ret; + } + + return pm_generic_poweroff_noirq(dev); +} #endif /* CONFIG_PM_SLEEP */ static int acpi_lpss_runtime_suspend(struct device *dev) @@ -1134,14 +1224,11 @@ static struct dev_pm_domain acpi_lpss_pm_domain = { .resume_noirq = acpi_lpss_resume_noirq, .resume_early = acpi_lpss_resume_early, .freeze = acpi_subsys_freeze, - .freeze_late = acpi_subsys_freeze_late, - .freeze_noirq = acpi_subsys_freeze_noirq, - .thaw_noirq = acpi_subsys_thaw_noirq, - .poweroff = acpi_subsys_suspend, - .poweroff_late = acpi_lpss_suspend_late, - .poweroff_noirq = acpi_lpss_suspend_noirq, - .restore_noirq = acpi_lpss_resume_noirq, - .restore_early = acpi_lpss_resume_early, + .poweroff = acpi_subsys_poweroff, + .poweroff_late = acpi_lpss_poweroff_late, + .poweroff_noirq = acpi_lpss_poweroff_noirq, + .restore_noirq = acpi_lpss_restore_noirq, + .restore_early = acpi_lpss_restore_early, #endif .runtime_suspend = acpi_lpss_runtime_suspend, .runtime_resume = acpi_lpss_runtime_resume, diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c index e54956ae93d3..28cffaaf9d82 100644 --- a/drivers/acpi/device_pm.c +++ b/drivers/acpi/device_pm.c @@ -45,6 +45,19 @@ const char *acpi_power_state_string(int state) } } +static int acpi_dev_pm_explicit_get(struct acpi_device *device, int *state) +{ + unsigned long long psc; + acpi_status status; + + status = acpi_evaluate_integer(device->handle, "_PSC", NULL, &psc); + if (ACPI_FAILURE(status)) + return -ENODEV; + + *state = psc; + return 0; +} + /** * acpi_device_get_power - Get power state of an ACPI device. * @device: Device to get the power state of. @@ -53,10 +66,16 @@ const char *acpi_power_state_string(int state) * This function does not update the device's power.state field, but it may * update its parent's power.state field (when the parent's power state is * unknown and the device's power state turns out to be D0). + * + * Also, it does not update power resource reference counters to ensure that + * the power state returned by it will be persistent and it may return a power + * state shallower than previously set by acpi_device_set_power() for @device + * (if that power state depends on any power resources). */ int acpi_device_get_power(struct acpi_device *device, int *state) { int result = ACPI_STATE_UNKNOWN; + int error; if (!device || !state) return -EINVAL; @@ -73,18 +92,16 @@ int acpi_device_get_power(struct acpi_device *device, int *state) * if available. */ if (device->power.flags.power_resources) { - int error = acpi_power_get_inferred_state(device, &result); + error = acpi_power_get_inferred_state(device, &result); if (error) return error; } if (device->power.flags.explicit_get) { - acpi_handle handle = device->handle; - unsigned long long psc; - acpi_status status; + int psc; - status = acpi_evaluate_integer(handle, "_PSC", NULL, &psc); - if (ACPI_FAILURE(status)) - return -ENODEV; + error = acpi_dev_pm_explicit_get(device, &psc); + if (error) + return error; /* * The power resources settings may indicate a power state @@ -118,7 +135,6 @@ int acpi_device_get_power(struct acpi_device *device, int *state) return 0; } -EXPORT_SYMBOL(acpi_device_get_power); static int acpi_dev_pm_explicit_set(struct acpi_device *adev, int state) { @@ -152,7 +168,8 @@ int acpi_device_set_power(struct acpi_device *device, int state) /* Make sure this is a valid target state */ - if (state == device->power.state) { + /* There is a special case for D0 addressed below. */ + if (state > ACPI_STATE_D0 && state == device->power.state) { ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device [%s] already in %s\n", device->pnp.bus_id, acpi_power_state_string(state))); @@ -202,9 +219,15 @@ int acpi_device_set_power(struct acpi_device *device, int state) return -ENODEV; } - result = acpi_dev_pm_explicit_set(device, state); - if (result) - goto end; + /* + * If the device goes from D3hot to D3cold, _PS3 has been + * evaluated for it already, so skip it in that case. + */ + if (device->power.state < ACPI_STATE_D3_HOT) { + result = acpi_dev_pm_explicit_set(device, state); + if (result) + goto end; + } if (device->power.flags.power_resources) result = acpi_power_transition(device, target_state); @@ -214,6 +237,30 @@ int acpi_device_set_power(struct acpi_device *device, int state) if (result) goto end; } + + if (device->power.state == ACPI_STATE_D0) { + int psc; + + /* Nothing to do here if _PSC is not present. */ + if (!device->power.flags.explicit_get) + return 0; + + /* + * The power state of the device was set to D0 last + * time, but that might have happened before a + * system-wide transition involving the platform + * firmware, so it may be necessary to evaluate _PS0 + * for the device here. However, use extra care here + * and evaluate _PSC to check the device's current power + * state, and only invoke _PS0 if the evaluation of _PSC + * is successful and it returns a power state different + * from D0. + */ + result = acpi_dev_pm_explicit_get(device, &psc); + if (result || psc == ACPI_STATE_D0) + return 0; + } + result = acpi_dev_pm_explicit_set(device, ACPI_STATE_D0); } @@ -1073,7 +1120,7 @@ EXPORT_SYMBOL_GPL(acpi_subsys_suspend_noirq); * acpi_subsys_resume_noirq - Run the device driver's "noirq" resume callback. * @dev: Device to handle. */ -int acpi_subsys_resume_noirq(struct device *dev) +static int acpi_subsys_resume_noirq(struct device *dev) { if (dev_pm_may_skip_resume(dev)) return 0; @@ -1088,7 +1135,6 @@ int acpi_subsys_resume_noirq(struct device *dev) return pm_generic_resume_noirq(dev); } -EXPORT_SYMBOL_GPL(acpi_subsys_resume_noirq); /** * acpi_subsys_resume_early - Resume device using ACPI. @@ -1098,12 +1144,11 @@ EXPORT_SYMBOL_GPL(acpi_subsys_resume_noirq); * generic early resume procedure for it during system transition into the * working state. */ -int acpi_subsys_resume_early(struct device *dev) +static int acpi_subsys_resume_early(struct device *dev) { int ret = acpi_dev_resume(dev); return ret ? ret : pm_generic_resume_early(dev); } -EXPORT_SYMBOL_GPL(acpi_subsys_resume_early); /** * acpi_subsys_freeze - Run the device driver's freeze callback. @@ -1112,65 +1157,81 @@ EXPORT_SYMBOL_GPL(acpi_subsys_resume_early); int acpi_subsys_freeze(struct device *dev) { /* - * This used to be done in acpi_subsys_prepare() for all devices and - * some drivers may depend on it, so do it here. Ideally, however, - * runtime-suspended devices should not be touched during freeze/thaw - * transitions. + * Resume all runtime-suspended devices before creating a snapshot + * image of system memory, because the restore kernel generally cannot + * be expected to always handle them consistently and they need to be + * put into the runtime-active metastate during system resume anyway, + * so it is better to ensure that the state saved in the image will be + * always consistent with that. */ - if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND)) - pm_runtime_resume(dev); + pm_runtime_resume(dev); return pm_generic_freeze(dev); } EXPORT_SYMBOL_GPL(acpi_subsys_freeze); /** - * acpi_subsys_freeze_late - Run the device driver's "late" freeze callback. - * @dev: Device to handle. + * acpi_subsys_restore_early - Restore device using ACPI. + * @dev: Device to restore. */ -int acpi_subsys_freeze_late(struct device *dev) +int acpi_subsys_restore_early(struct device *dev) { + int ret = acpi_dev_resume(dev); + return ret ? ret : pm_generic_restore_early(dev); +} +EXPORT_SYMBOL_GPL(acpi_subsys_restore_early); - if (dev_pm_smart_suspend_and_suspended(dev)) - return 0; +/** + * acpi_subsys_poweroff - Run the device driver's poweroff callback. + * @dev: Device to handle. + * + * Follow PCI and resume devices from runtime suspend before running their + * system poweroff callbacks, unless the driver can cope with runtime-suspended + * devices during system suspend and there are no ACPI-specific reasons for + * resuming them. + */ +int acpi_subsys_poweroff(struct device *dev) +{ + if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) || + acpi_dev_needs_resume(dev, ACPI_COMPANION(dev))) + pm_runtime_resume(dev); - return pm_generic_freeze_late(dev); + return pm_generic_poweroff(dev); } -EXPORT_SYMBOL_GPL(acpi_subsys_freeze_late); +EXPORT_SYMBOL_GPL(acpi_subsys_poweroff); /** - * acpi_subsys_freeze_noirq - Run the device driver's "noirq" freeze callback. + * acpi_subsys_poweroff_late - Run the device driver's poweroff callback. * @dev: Device to handle. + * + * Carry out the generic late poweroff procedure for @dev and use ACPI to put + * it into a low-power state during system transition into a sleep state. */ -int acpi_subsys_freeze_noirq(struct device *dev) +static int acpi_subsys_poweroff_late(struct device *dev) { + int ret; if (dev_pm_smart_suspend_and_suspended(dev)) return 0; - return pm_generic_freeze_noirq(dev); + ret = pm_generic_poweroff_late(dev); + if (ret) + return ret; + + return acpi_dev_suspend(dev, device_may_wakeup(dev)); } -EXPORT_SYMBOL_GPL(acpi_subsys_freeze_noirq); /** - * acpi_subsys_thaw_noirq - Run the device driver's "noirq" thaw callback. - * @dev: Device to handle. + * acpi_subsys_poweroff_noirq - Run the driver's "noirq" poweroff callback. + * @dev: Device to suspend. */ -int acpi_subsys_thaw_noirq(struct device *dev) +static int acpi_subsys_poweroff_noirq(struct device *dev) { - /* - * If the device is in runtime suspend, the "thaw" code may not work - * correctly with it, so skip the driver callback and make the PM core - * skip all of the subsequent "thaw" callbacks for the device. - */ - if (dev_pm_smart_suspend_and_suspended(dev)) { - dev_pm_skip_next_resume_phases(dev); + if (dev_pm_smart_suspend_and_suspended(dev)) return 0; - } - return pm_generic_thaw_noirq(dev); + return pm_generic_poweroff_noirq(dev); } -EXPORT_SYMBOL_GPL(acpi_subsys_thaw_noirq); #endif /* CONFIG_PM_SLEEP */ static struct dev_pm_domain acpi_general_pm_domain = { @@ -1186,14 +1247,10 @@ static struct dev_pm_domain acpi_general_pm_domain = { .resume_noirq = acpi_subsys_resume_noirq, .resume_early = acpi_subsys_resume_early, .freeze = acpi_subsys_freeze, - .freeze_late = acpi_subsys_freeze_late, - .freeze_noirq = acpi_subsys_freeze_noirq, - .thaw_noirq = acpi_subsys_thaw_noirq, - .poweroff = acpi_subsys_suspend, - .poweroff_late = acpi_subsys_suspend_late, - .poweroff_noirq = acpi_subsys_suspend_noirq, - .restore_noirq = acpi_subsys_resume_noirq, - .restore_early = acpi_subsys_resume_early, + .poweroff = acpi_subsys_poweroff, + .poweroff_late = acpi_subsys_poweroff_late, + .poweroff_noirq = acpi_subsys_poweroff_noirq, + .restore_early = acpi_subsys_restore_early, #endif }, }; diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index f6157d4d637a..f4c2fe6be4f2 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -139,8 +139,15 @@ int acpi_power_get_inferred_state(struct acpi_device *device, int *state); int acpi_power_on_resources(struct acpi_device *device, int state); int acpi_power_transition(struct acpi_device *device, int state); +/* -------------------------------------------------------------------------- + Device Power Management + -------------------------------------------------------------------------- */ +int acpi_device_get_power(struct acpi_device *device, int *state); int acpi_wakeup_device_init(void); +/* -------------------------------------------------------------------------- + Processor + -------------------------------------------------------------------------- */ #ifdef CONFIG_ARCH_MIGHT_HAVE_ACPI_PDC void acpi_early_processor_set_pdc(void); #else diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c index a916417b9e70..fe1e7bc91a5e 100644 --- a/drivers/acpi/power.c +++ b/drivers/acpi/power.c @@ -42,6 +42,11 @@ ACPI_MODULE_NAME("power"); #define ACPI_POWER_RESOURCE_STATE_ON 0x01 #define ACPI_POWER_RESOURCE_STATE_UNKNOWN 0xFF +struct acpi_power_dependent_device { + struct device *dev; + struct list_head node; +}; + struct acpi_power_resource { struct acpi_device device; struct list_head list_node; @@ -51,6 +56,7 @@ struct acpi_power_resource { unsigned int ref_count; bool wakeup_enabled; struct mutex resource_lock; + struct list_head dependents; }; struct acpi_power_resource_entry { @@ -232,8 +238,121 @@ static int acpi_power_get_list_state(struct list_head *list, int *state) return 0; } +static int +acpi_power_resource_add_dependent(struct acpi_power_resource *resource, + struct device *dev) +{ + struct acpi_power_dependent_device *dep; + int ret = 0; + + mutex_lock(&resource->resource_lock); + list_for_each_entry(dep, &resource->dependents, node) { + /* Only add it once */ + if (dep->dev == dev) + goto unlock; + } + + dep = kzalloc(sizeof(*dep), GFP_KERNEL); + if (!dep) { + ret = -ENOMEM; + goto unlock; + } + + dep->dev = dev; + list_add_tail(&dep->node, &resource->dependents); + dev_dbg(dev, "added power dependency to [%s]\n", resource->name); + +unlock: + mutex_unlock(&resource->resource_lock); + return ret; +} + +static void +acpi_power_resource_remove_dependent(struct acpi_power_resource *resource, + struct device *dev) +{ + struct acpi_power_dependent_device *dep; + + mutex_lock(&resource->resource_lock); + list_for_each_entry(dep, &resource->dependents, node) { + if (dep->dev == dev) { + list_del(&dep->node); + kfree(dep); + dev_dbg(dev, "removed power dependency to [%s]\n", + resource->name); + break; + } + } + mutex_unlock(&resource->resource_lock); +} + +/** + * acpi_device_power_add_dependent - Add dependent device of this ACPI device + * @adev: ACPI device pointer + * @dev: Dependent device + * + * If @adev has non-empty _PR0 the @dev is added as dependent device to all + * power resources returned by it. This means that whenever these power + * resources are turned _ON the dependent devices get runtime resumed. This + * is needed for devices such as PCI to allow its driver to re-initialize + * it after it went to D0uninitialized. + * + * If @adev does not have _PR0 this does nothing. + * + * Returns %0 in case of success and negative errno otherwise. + */ +int acpi_device_power_add_dependent(struct acpi_device *adev, + struct device *dev) +{ + struct acpi_power_resource_entry *entry; + struct list_head *resources; + int ret; + + if (!adev->flags.power_manageable) + return 0; + + resources = &adev->power.states[ACPI_STATE_D0].resources; + list_for_each_entry(entry, resources, node) { + ret = acpi_power_resource_add_dependent(entry->resource, dev); + if (ret) + goto err; + } + + return 0; + +err: + list_for_each_entry(entry, resources, node) + acpi_power_resource_remove_dependent(entry->resource, dev); + + return ret; +} + +/** + * acpi_device_power_remove_dependent - Remove dependent device + * @adev: ACPI device pointer + * @dev: Dependent device + * + * Does the opposite of acpi_device_power_add_dependent() and removes the + * dependent device if it is found. Can be called to @adev that does not + * have _PR0 as well. + */ +void acpi_device_power_remove_dependent(struct acpi_device *adev, + struct device *dev) +{ + struct acpi_power_resource_entry *entry; + struct list_head *resources; + + if (!adev->flags.power_manageable) + return; + + resources = &adev->power.states[ACPI_STATE_D0].resources; + list_for_each_entry_reverse(entry, resources, node) + acpi_power_resource_remove_dependent(entry->resource, dev); +} + static int __acpi_power_on(struct acpi_power_resource *resource) { + struct acpi_power_dependent_device *dep; acpi_status status = AE_OK; status = acpi_evaluate_object(resource->device.handle, "_ON", NULL, NULL); @@ -243,6 +362,21 @@ static int __acpi_power_on(struct acpi_power_resource *resource) ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Power resource [%s] turned on\n", resource->name)); + /* + * If there are other dependents on this power resource we need to + * resume them now so that their drivers can re-initialize the + * hardware properly after it went back to D0. + */ + if (list_empty(&resource->dependents) || + list_is_singular(&resource->dependents)) + return 0; + + list_for_each_entry(dep, &resource->dependents, node) { + dev_dbg(dep->dev, "runtime resuming because [%s] turned on\n", + resource->name); + pm_request_resume(dep->dev); + } + return 0; } @@ -810,6 +944,7 @@ int acpi_add_power_resource(acpi_handle handle) ACPI_STA_DEFAULT); mutex_init(&resource->resource_lock); INIT_LIST_HEAD(&resource->list_node); + INIT_LIST_HEAD(&resource->dependents); resource->name = device->pnp.bus_id; strcpy(acpi_device_name(device), ACPI_POWER_DEVICE_NAME); strcpy(acpi_device_class(device), ACPI_POWER_CLASS); diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 8ff08e531443..f0fe7c15d657 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -77,7 +77,7 @@ static int acpi_sleep_prepare(u32 acpi_state) return 0; } -static bool acpi_sleep_state_supported(u8 sleep_state) +bool acpi_sleep_state_supported(u8 sleep_state) { acpi_status status; u8 type_a, type_b; @@ -452,14 +452,6 @@ static int acpi_pm_prepare(void) return error; } -static int find_powerf_dev(struct device *dev, void *data) -{ - struct acpi_device *device = to_acpi_device(dev); - const char *hid = acpi_device_hid(device); - - return !strcmp(hid, ACPI_BUTTON_HID_POWERF); -} - /** * acpi_pm_finish - Instruct the platform to leave a sleep state. * @@ -468,7 +460,7 @@ static int find_powerf_dev(struct device *dev, void *data) */ static void acpi_pm_finish(void) { - struct device *pwr_btn_dev; + struct acpi_device *pwr_btn_adev; u32 acpi_state = acpi_target_sleep_state; acpi_ec_unblock_transactions(); @@ -499,11 +491,11 @@ static void acpi_pm_finish(void) return; pwr_btn_event_pending = false; - pwr_btn_dev = bus_find_device(&acpi_bus_type, NULL, NULL, - find_powerf_dev); - if (pwr_btn_dev) { - pm_wakeup_event(pwr_btn_dev, 0); - put_device(pwr_btn_dev); + pwr_btn_adev = acpi_dev_get_first_match_dev(ACPI_BUTTON_HID_POWERF, + NULL, -1); + if (pwr_btn_adev) { + pm_wakeup_event(&pwr_btn_adev->dev, 0); + acpi_dev_put(pwr_btn_adev); } } diff --git a/drivers/auxdisplay/cfag12864bfb.c b/drivers/auxdisplay/cfag12864bfb.c index 40c8a552a478..4074886b7bc8 100644 --- a/drivers/auxdisplay/cfag12864bfb.c +++ b/drivers/auxdisplay/cfag12864bfb.c @@ -52,8 +52,9 @@ static const struct fb_var_screeninfo cfag12864bfb_var = { static int cfag12864bfb_mmap(struct fb_info *info, struct vm_area_struct *vma) { - return vm_insert_page(vma, vma->vm_start, - virt_to_page(cfag12864b_buffer)); + struct page *pages = virt_to_page(cfag12864b_buffer); + + return vm_map_pages_zero(vma, &pages, 1); } static struct fb_ops cfag12864bfb_ops = { diff --git a/drivers/auxdisplay/ht16k33.c b/drivers/auxdisplay/ht16k33.c index 21393ec3b9a4..9c0bb771751d 100644 --- a/drivers/auxdisplay/ht16k33.c +++ b/drivers/auxdisplay/ht16k33.c @@ -223,9 +223,9 @@ static const struct backlight_ops ht16k33_bl_ops = { static int ht16k33_mmap(struct fb_info *info, struct vm_area_struct *vma) { struct ht16k33_priv *priv = info->par; + struct page *pages = virt_to_page(priv->fbdev.buffer); - return vm_insert_page(vma, vma->vm_start, - virt_to_page(priv->fbdev.buffer)); + return vm_map_pages_zero(vma, &pages, 1); } static struct fb_ops ht16k33_fb_ops = { diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c index 59d19dd64928..ced6863a16a5 100644 --- a/drivers/base/power/clock_ops.c +++ b/drivers/base/power/clock_ops.c @@ -12,6 +12,7 @@ #include <linux/pm_clock.h> #include <linux/clk.h> #include <linux/clkdev.h> +#include <linux/of_clk.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/pm_domain.h> @@ -92,8 +93,6 @@ static int __pm_clk_add(struct device *dev, const char *con_id, if (con_id) { ce->con_id = kstrdup(con_id, GFP_KERNEL); if (!ce->con_id) { - dev_err(dev, - "Not enough memory for clock connection ID.\n"); kfree(ce); return -ENOMEM; } @@ -195,8 +194,7 @@ int of_pm_clk_add_clks(struct device *dev) if (!dev || !dev->of_node) return -EINVAL; - count = of_count_phandle_with_args(dev->of_node, "clocks", - "#clock-cells"); + count = of_clk_get_parent_count(dev->of_node); if (count <= 0) return -ENODEV; diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index dcfc0a36c8f7..7fb2c39bc725 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -530,21 +530,6 @@ static void dpm_watchdog_clear(struct dpm_watchdog *wd) /*------------------------- Resume routines -------------------------*/ /** - * dev_pm_skip_next_resume_phases - Skip next system resume phases for device. - * @dev: Target device. - * - * Make the core skip the "early resume" and "resume" phases for @dev. - * - * This function can be called by middle-layer code during the "noirq" phase of - * system resume if necessary, but not by device drivers. - */ -void dev_pm_skip_next_resume_phases(struct device *dev) -{ - dev->power.is_late_suspended = false; - dev->power.is_suspended = false; -} - -/** * suspend_event - Return a "suspend" message for given "resume" one. * @resume_msg: PM message representing a system-wide resume transition. */ @@ -681,6 +666,9 @@ Skip: dev->power.is_noirq_suspended = false; if (skip_resume) { + /* Make the next phases of resume skip the device. */ + dev->power.is_late_suspended = false; + dev->power.is_suspended = false; /* * The device is going to be left in suspend, but it might not * have been in runtime suspend before the system suspended, so @@ -689,7 +677,6 @@ Skip: * device again. */ pm_runtime_set_suspended(dev); - dev_pm_skip_next_resume_phases(dev); } Out: @@ -1631,17 +1618,20 @@ int dpm_suspend_late(pm_message_t state) */ int dpm_suspend_end(pm_message_t state) { - int error = dpm_suspend_late(state); + ktime_t starttime = ktime_get(); + int error; + + error = dpm_suspend_late(state); if (error) - return error; + goto out; error = dpm_suspend_noirq(state); - if (error) { + if (error) dpm_resume_early(resume_event(state)); - return error; - } - return 0; +out: + dpm_show_time(starttime, state, error, "end"); + return error; } EXPORT_SYMBOL_GPL(dpm_suspend_end); @@ -2034,6 +2024,7 @@ int dpm_prepare(pm_message_t state) */ int dpm_suspend_start(pm_message_t state) { + ktime_t starttime = ktime_get(); int error; error = dpm_prepare(state); @@ -2042,6 +2033,7 @@ int dpm_suspend_start(pm_message_t state) dpm_save_failed_step(SUSPEND_PREPARE); } else error = dpm_suspend(state); + dpm_show_time(starttime, state, error, "start"); return error; } EXPORT_SYMBOL_GPL(dpm_suspend_start); diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c index 5b2b6a05a4f3..ee31d4f8d856 100644 --- a/drivers/base/power/wakeup.c +++ b/drivers/base/power/wakeup.c @@ -968,8 +968,6 @@ void pm_wakep_autosleep_enabled(bool set) } #endif /* CONFIG_PM_AUTOSLEEP */ -static struct dentry *wakeup_sources_stats_dentry; - /** * print_wakeup_source_stats - Print wakeup source statistics information. * @m: seq_file to print the statistics into. @@ -1099,8 +1097,8 @@ static const struct file_operations wakeup_sources_stats_fops = { static int __init wakeup_sources_debugfs_init(void) { - wakeup_sources_stats_dentry = debugfs_create_file("wakeup_sources", - S_IRUGO, NULL, NULL, &wakeup_sources_stats_fops); + debugfs_create_file("wakeup_sources", S_IRUGO, NULL, NULL, + &wakeup_sources_stats_fops); return 0; } diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index aa51756fd4d6..87b410d6e51d 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -368,7 +368,7 @@ static struct clk_core *clk_core_get(struct clk_core *core, u8 p_index) const char *dev_id = dev ? dev_name(dev) : NULL; struct device_node *np = core->of_node; - if (np && index >= 0) + if (np && (name || index >= 0)) hw = of_clk_get_hw(np, index, name); /* diff --git a/drivers/clk/meson/g12a.c b/drivers/clk/meson/g12a.c index 739f64fdf1e3..206fafd299ea 100644 --- a/drivers/clk/meson/g12a.c +++ b/drivers/clk/meson/g12a.c @@ -2734,8 +2734,8 @@ static struct clk_hw_onecell_data g12a_hw_onecell_data = { [CLKID_MALI_1_DIV] = &g12a_mali_1_div.hw, [CLKID_MALI_1] = &g12a_mali_1.hw, [CLKID_MALI] = &g12a_mali.hw, - [CLKID_MPLL_5OM_DIV] = &g12a_mpll_50m_div.hw, - [CLKID_MPLL_5OM] = &g12a_mpll_50m.hw, + [CLKID_MPLL_50M_DIV] = &g12a_mpll_50m_div.hw, + [CLKID_MPLL_50M] = &g12a_mpll_50m.hw, [CLKID_SYS_PLL_DIV16_EN] = &g12a_sys_pll_div16_en.hw, [CLKID_SYS_PLL_DIV16] = &g12a_sys_pll_div16.hw, [CLKID_CPU_CLK_DYN0_SEL] = &g12a_cpu_clk_premux0.hw, diff --git a/drivers/clk/meson/g12a.h b/drivers/clk/meson/g12a.h index 39c41af70804..bcc05cd9882f 100644 --- a/drivers/clk/meson/g12a.h +++ b/drivers/clk/meson/g12a.h @@ -166,7 +166,7 @@ #define CLKID_HDMI_DIV 167 #define CLKID_MALI_0_DIV 170 #define CLKID_MALI_1_DIV 173 -#define CLKID_MPLL_5OM_DIV 176 +#define CLKID_MPLL_50M_DIV 176 #define CLKID_SYS_PLL_DIV16_EN 178 #define CLKID_SYS_PLL_DIV16 179 #define CLKID_CPU_CLK_DYN0_SEL 180 diff --git a/drivers/clk/meson/meson8b.c b/drivers/clk/meson/meson8b.c index 37cf0f01bb5d..62cd3a7f1f65 100644 --- a/drivers/clk/meson/meson8b.c +++ b/drivers/clk/meson/meson8b.c @@ -1761,7 +1761,7 @@ static struct clk_regmap meson8m2_gp_pll = { }, }; -static const char * const mmeson8b_vpu_0_1_parent_names[] = { +static const char * const meson8b_vpu_0_1_parent_names[] = { "fclk_div4", "fclk_div3", "fclk_div5", "fclk_div7" }; @@ -1778,8 +1778,8 @@ static struct clk_regmap meson8b_vpu_0_sel = { .hw.init = &(struct clk_init_data){ .name = "vpu_0_sel", .ops = &clk_regmap_mux_ops, - .parent_names = mmeson8b_vpu_0_1_parent_names, - .num_parents = ARRAY_SIZE(mmeson8b_vpu_0_1_parent_names), + .parent_names = meson8b_vpu_0_1_parent_names, + .num_parents = ARRAY_SIZE(meson8b_vpu_0_1_parent_names), .flags = CLK_SET_RATE_PARENT, }, }; @@ -1837,8 +1837,8 @@ static struct clk_regmap meson8b_vpu_1_sel = { .hw.init = &(struct clk_init_data){ .name = "vpu_1_sel", .ops = &clk_regmap_mux_ops, - .parent_names = mmeson8b_vpu_0_1_parent_names, - .num_parents = ARRAY_SIZE(mmeson8b_vpu_0_1_parent_names), + .parent_names = meson8b_vpu_0_1_parent_names, + .num_parents = ARRAY_SIZE(meson8b_vpu_0_1_parent_names), .flags = CLK_SET_RATE_PARENT, }, }; diff --git a/drivers/clk/socfpga/clk-s10.c b/drivers/clk/socfpga/clk-s10.c index 8281dfbf38c2..5bed36e12951 100644 --- a/drivers/clk/socfpga/clk-s10.c +++ b/drivers/clk/socfpga/clk-s10.c @@ -103,9 +103,9 @@ static const struct stratix10_perip_cnt_clock s10_main_perip_cnt_clks[] = { { STRATIX10_NOC_CLK, "noc_clk", NULL, noc_mux, ARRAY_SIZE(noc_mux), 0, 0, 0, 0x3C, 1}, { STRATIX10_EMAC_A_FREE_CLK, "emaca_free_clk", NULL, emaca_free_mux, ARRAY_SIZE(emaca_free_mux), - 0, 0, 4, 0xB0, 0}, + 0, 0, 2, 0xB0, 0}, { STRATIX10_EMAC_B_FREE_CLK, "emacb_free_clk", NULL, emacb_free_mux, ARRAY_SIZE(emacb_free_mux), - 0, 0, 4, 0xB0, 1}, + 0, 0, 2, 0xB0, 1}, { STRATIX10_EMAC_PTP_FREE_CLK, "emac_ptp_free_clk", NULL, emac_ptp_free_mux, ARRAY_SIZE(emac_ptp_free_mux), 0, 0, 4, 0xB0, 2}, { STRATIX10_GPIO_DB_FREE_CLK, "gpio_db_free_clk", NULL, gpio_db_free_mux, diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c index e1ba62d2b1a0..ac1d27a8c650 100644 --- a/drivers/clk/tegra/clk-tegra210.c +++ b/drivers/clk/tegra/clk-tegra210.c @@ -3366,6 +3366,8 @@ static struct tegra_clk_init_table init_table[] __initdata = { { TEGRA210_CLK_I2S3_SYNC, TEGRA210_CLK_CLK_MAX, 24576000, 0 }, { TEGRA210_CLK_I2S4_SYNC, TEGRA210_CLK_CLK_MAX, 24576000, 0 }, { TEGRA210_CLK_VIMCLK_SYNC, TEGRA210_CLK_CLK_MAX, 24576000, 0 }, + { TEGRA210_CLK_HDA, TEGRA210_CLK_PLL_P, 51000000, 0 }, + { TEGRA210_CLK_HDA2CODEC_2X, TEGRA210_CLK_PLL_P, 48000000, 0 }, /* This MUST be the last entry. */ { TEGRA210_CLK_CLK_MAX, TEGRA210_CLK_CLK_MAX, 0, 0 }, }; diff --git a/drivers/clk/ti/clkctrl.c b/drivers/clk/ti/clkctrl.c index 8e834317c97d..975995eea15c 100644 --- a/drivers/clk/ti/clkctrl.c +++ b/drivers/clk/ti/clkctrl.c @@ -229,6 +229,7 @@ static struct clk_hw *_ti_omap4_clkctrl_xlate(struct of_phandle_args *clkspec, { struct omap_clkctrl_provider *provider = data; struct omap_clkctrl_clk *entry; + bool found = false; if (clkspec->args_count != 2) return ERR_PTR(-EINVAL); @@ -238,11 +239,13 @@ static struct clk_hw *_ti_omap4_clkctrl_xlate(struct of_phandle_args *clkspec, list_for_each_entry(entry, &provider->clocks, node) { if (entry->reg_offset == clkspec->args[0] && - entry->bit_offset == clkspec->args[1]) + entry->bit_offset == clkspec->args[1]) { + found = true; break; + } } - if (!entry) + if (!found) return ERR_PTR(-EINVAL); return entry->clk; diff --git a/drivers/firmware/efi/efi-bgrt.c b/drivers/firmware/efi/efi-bgrt.c index a2384184a7de..b07c17643210 100644 --- a/drivers/firmware/efi/efi-bgrt.c +++ b/drivers/firmware/efi/efi-bgrt.c @@ -47,11 +47,6 @@ void __init efi_bgrt_init(struct acpi_table_header *table) bgrt->version); goto out; } - if (bgrt->status & 0xfe) { - pr_notice("Ignoring BGRT: reserved status bits are non-zero %u\n", - bgrt->status); - goto out; - } if (bgrt->image_type != 0) { pr_notice("Ignoring BGRT: invalid image type %u (expected 0)\n", bgrt->image_type); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index 16b2137d117c..4b7cf7bc0ded 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -1009,14 +1009,16 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) /* first try to find a slot in an existing linked list entry */ for (prsv = efi_memreserve_root->next; prsv; prsv = rsv->next) { - rsv = __va(prsv); + rsv = memremap(prsv, sizeof(*rsv), MEMREMAP_WB); index = atomic_fetch_add_unless(&rsv->count, 1, rsv->size); if (index < rsv->size) { rsv->entry[index].base = addr; rsv->entry[index].size = size; + memunmap(rsv); return 0; } + memunmap(rsv); } /* no slot found - allocate a new linked list entry */ @@ -1024,7 +1026,13 @@ int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size) if (!rsv) return -ENOMEM; - rsv->size = EFI_MEMRESERVE_COUNT(PAGE_SIZE); + /* + * The memremap() call above assumes that a linux_efi_memreserve entry + * never crosses a page boundary, so let's ensure that this remains true + * even when kexec'ing a 4k pages kernel from a >4k pages kernel, by + * using SZ_4K explicitly in the size calculation below. + */ + rsv->size = EFI_MEMRESERVE_COUNT(SZ_4K); atomic_set(&rsv->count, 1); rsv->entry[0].base = addr; rsv->entry[0].size = size; diff --git a/drivers/firmware/efi/efibc.c b/drivers/firmware/efi/efibc.c index 61e099826cbb..35dccc88ac0a 100644 --- a/drivers/firmware/efi/efibc.c +++ b/drivers/firmware/efi/efibc.c @@ -43,11 +43,13 @@ static int efibc_set_variable(const char *name, const char *value) efibc_str_to_str16(value, (efi_char16_t *)entry->var.Data); memcpy(&entry->var.VendorGuid, &guid, sizeof(guid)); - ret = efivar_entry_set(entry, - EFI_VARIABLE_NON_VOLATILE - | EFI_VARIABLE_BOOTSERVICE_ACCESS - | EFI_VARIABLE_RUNTIME_ACCESS, - size, entry->var.Data, NULL); + ret = efivar_entry_set_safe(entry->var.VariableName, + entry->var.VendorGuid, + EFI_VARIABLE_NON_VOLATILE + | EFI_VARIABLE_BOOTSERVICE_ACCESS + | EFI_VARIABLE_RUNTIME_ACCESS, + false, size, entry->var.Data); + if (ret) pr_err("failed to set %s EFI variable: 0x%x\n", name, ret); diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index eac0c54c5970..b032d3899fa3 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -80,6 +80,7 @@ #define HID_DEVICE_ID_ALPS_U1_DUAL_3BTN_PTP 0x1220 #define HID_DEVICE_ID_ALPS_U1 0x1215 #define HID_DEVICE_ID_ALPS_T4_BTNLESS 0x120C +#define HID_DEVICE_ID_ALPS_1222 0x1222 #define USB_VENDOR_ID_AMI 0x046b @@ -269,6 +270,7 @@ #define USB_DEVICE_ID_CHICONY_MULTI_TOUCH 0xb19d #define USB_DEVICE_ID_CHICONY_WIRELESS 0x0618 #define USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE 0x1053 +#define USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE2 0x0939 #define USB_DEVICE_ID_CHICONY_WIRELESS2 0x1123 #define USB_DEVICE_ID_ASUS_AK1D 0x1125 #define USB_DEVICE_ID_CHICONY_TOSHIBA_WT10A 0x1408 @@ -569,6 +571,7 @@ #define USB_VENDOR_ID_HUION 0x256c #define USB_DEVICE_ID_HUION_TABLET 0x006e +#define USB_DEVICE_ID_HUION_HS64 0x006d #define USB_VENDOR_ID_IBM 0x04b3 #define USB_DEVICE_ID_IBM_SCROLLPOINT_III 0x3100 diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c index e564bff86515..bfcf2ee58d14 100644 --- a/drivers/hid/hid-logitech-dj.c +++ b/drivers/hid/hid-logitech-dj.c @@ -30,6 +30,7 @@ #define REPORT_ID_HIDPP_SHORT 0x10 #define REPORT_ID_HIDPP_LONG 0x11 +#define REPORT_ID_HIDPP_VERY_LONG 0x12 #define HIDPP_REPORT_SHORT_LENGTH 7 #define HIDPP_REPORT_LONG_LENGTH 20 @@ -1242,7 +1243,8 @@ static int logi_dj_ll_raw_request(struct hid_device *hid, int ret; if ((buf[0] == REPORT_ID_HIDPP_SHORT) || - (buf[0] == REPORT_ID_HIDPP_LONG)) { + (buf[0] == REPORT_ID_HIDPP_LONG) || + (buf[0] == REPORT_ID_HIDPP_VERY_LONG)) { if (count < 2) return -EINVAL; diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 5df5dd56ecc8..b603c14d043b 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1776,6 +1776,10 @@ static const struct hid_device_id mt_devices[] = { HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, USB_VENDOR_ID_ALPS_JP, HID_DEVICE_ID_ALPS_U1_DUAL_3BTN_PTP) }, + { .driver_data = MT_CLS_WIN_8_DUAL, + HID_DEVICE(BUS_I2C, HID_GROUP_MULTITOUCH_WIN_8, + USB_VENDOR_ID_ALPS_JP, + HID_DEVICE_ID_ALPS_1222) }, /* Lenovo X1 TAB Gen 2 */ { .driver_data = MT_CLS_WIN_8_DUAL, diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index e5ca6fe2ca57..671a285724f9 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -42,6 +42,7 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ATEN, USB_DEVICE_ID_ATEN_UC100KM), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_MULTI_TOUCH), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE), HID_QUIRK_ALWAYS_POLL }, + { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_PIXART_USB_OPTICAL_MOUSE2), HID_QUIRK_ALWAYS_POLL }, { HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_WIRELESS), HID_QUIRK_MULTI_INPUT }, { HID_USB_DEVICE(USB_VENDOR_ID_CHIC, USB_DEVICE_ID_CHIC_GAMEPAD), HID_QUIRK_BADPAD }, { HID_USB_DEVICE(USB_VENDOR_ID_CH, USB_DEVICE_ID_CH_3AXIS_5BUTTON_STICK), HID_QUIRK_NOGET }, diff --git a/drivers/hid/hid-uclogic-core.c b/drivers/hid/hid-uclogic-core.c index 8fe02d81265d..914fb527ae7a 100644 --- a/drivers/hid/hid-uclogic-core.c +++ b/drivers/hid/hid-uclogic-core.c @@ -369,6 +369,8 @@ static const struct hid_device_id uclogic_devices[] = { USB_DEVICE_ID_UCLOGIC_TABLET_TWHA60) }, { HID_USB_DEVICE(USB_VENDOR_ID_HUION, USB_DEVICE_ID_HUION_TABLET) }, + { HID_USB_DEVICE(USB_VENDOR_ID_HUION, + USB_DEVICE_ID_HUION_HS64) }, { HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_HUION_TABLET) }, { HID_USB_DEVICE(USB_VENDOR_ID_UCLOGIC, diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c index 0187c9f8fc22..273d784fff66 100644 --- a/drivers/hid/hid-uclogic-params.c +++ b/drivers/hid/hid-uclogic-params.c @@ -977,6 +977,8 @@ int uclogic_params_init(struct uclogic_params *params, /* FALL THROUGH */ case VID_PID(USB_VENDOR_ID_HUION, USB_DEVICE_ID_HUION_TABLET): + case VID_PID(USB_VENDOR_ID_HUION, + USB_DEVICE_ID_HUION_HS64): case VID_PID(USB_VENDOR_ID_UCLOGIC, USB_DEVICE_ID_HUION_TABLET): case VID_PID(USB_VENDOR_ID_UCLOGIC, diff --git a/drivers/hid/intel-ish-hid/ishtp-fw-loader.c b/drivers/hid/intel-ish-hid/ishtp-fw-loader.c index 22ba21457035..aa2dbed30fc3 100644 --- a/drivers/hid/intel-ish-hid/ishtp-fw-loader.c +++ b/drivers/hid/intel-ish-hid/ishtp-fw-loader.c @@ -816,9 +816,9 @@ static int load_fw_from_host(struct ishtp_cl_data *client_data) goto end_err_fw_release; release_firmware(fw); - kfree(filename); dev_info(cl_data_to_dev(client_data), "ISH firmware %s loaded\n", filename); + kfree(filename); return 0; end_err_fw_release: diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c index c0487b34d2cf..6ba944b40fdb 100644 --- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c +++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c @@ -891,7 +891,7 @@ static int hid_ishtp_cl_reset(struct ishtp_cl_device *cl_device) */ static int hid_ishtp_cl_suspend(struct device *device) { - struct ishtp_cl_device *cl_device = dev_get_drvdata(device); + struct ishtp_cl_device *cl_device = ishtp_dev_to_cl_device(device); struct ishtp_cl *hid_ishtp_cl = ishtp_get_drvdata(cl_device); struct ishtp_cl_data *client_data = ishtp_get_client_data(hid_ishtp_cl); @@ -912,7 +912,7 @@ static int hid_ishtp_cl_suspend(struct device *device) */ static int hid_ishtp_cl_resume(struct device *device) { - struct ishtp_cl_device *cl_device = dev_get_drvdata(device); + struct ishtp_cl_device *cl_device = ishtp_dev_to_cl_device(device); struct ishtp_cl *hid_ishtp_cl = ishtp_get_drvdata(cl_device); struct ishtp_cl_data *client_data = ishtp_get_client_data(hid_ishtp_cl); diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c index 794e700d65f7..c47c3328a0f4 100644 --- a/drivers/hid/intel-ish-hid/ishtp/bus.c +++ b/drivers/hid/intel-ish-hid/ishtp/bus.c @@ -471,7 +471,6 @@ static struct ishtp_cl_device *ishtp_bus_add_device(struct ishtp_device *dev, } ishtp_device_ready = true; - dev_set_drvdata(&device->dev, device); return device; } @@ -640,6 +639,20 @@ void *ishtp_get_drvdata(struct ishtp_cl_device *cl_device) EXPORT_SYMBOL(ishtp_get_drvdata); /** + * ishtp_dev_to_cl_device() - get ishtp_cl_device instance from device instance + * @device: device instance + * + * Get ish_cl_device instance which embeds device instance in it. + * + * Return: pointer to ishtp_cl_device instance + */ +struct ishtp_cl_device *ishtp_dev_to_cl_device(struct device *device) +{ + return to_ishtp_cl_device(device); +} +EXPORT_SYMBOL(ishtp_dev_to_cl_device); + +/** * ishtp_bus_new_client() - Create a new client * @dev: ISHTP device instance * diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c index e4352741c467..b695094290ab 100644 --- a/drivers/input/serio/i8042.c +++ b/drivers/input/serio/i8042.c @@ -1406,7 +1406,7 @@ static void __init i8042_register_ports(void) * behavior on many platforms using suspend-to-RAM (ACPI S3) * by default. */ - if (pm_suspend_via_s2idle() && i == I8042_KBD_PORT_NO) + if (pm_suspend_default_s2idle() && i == I8042_KBD_PORT_NO) device_set_wakeup_enable(&serio->dev, true); } } diff --git a/drivers/irqchip/irq-csky-mpintc.c b/drivers/irqchip/irq-csky-mpintc.c index c67c961ab6cc..a4c1aacba1ff 100644 --- a/drivers/irqchip/irq-csky-mpintc.c +++ b/drivers/irqchip/irq-csky-mpintc.c @@ -89,8 +89,19 @@ static int csky_irq_set_affinity(struct irq_data *d, if (cpu >= nr_cpu_ids) return -EINVAL; - /* Enable interrupt destination */ - cpu |= BIT(31); + /* + * The csky,mpintc could support auto irq deliver, but it only + * could deliver external irq to one cpu or all cpus. So it + * doesn't support deliver external irq to a group of cpus + * with cpu_mask. + * SO we only use auto deliver mode when affinity mask_val is + * equal to cpu_present_mask. + * + */ + if (cpumask_equal(mask_val, cpu_present_mask)) + cpu = 0; + else + cpu |= BIT(31); writel_relaxed(cpu, INTCG_base + INTCG_CIDSTR + offset); diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index d29b44b677e4..35500801dc2b 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -733,32 +733,43 @@ static void its_flush_cmd(struct its_node *its, struct its_cmd_block *cmd) } static int its_wait_for_range_completion(struct its_node *its, - struct its_cmd_block *from, + u64 prev_idx, struct its_cmd_block *to) { - u64 rd_idx, from_idx, to_idx; + u64 rd_idx, to_idx, linear_idx; u32 count = 1000000; /* 1s! */ - from_idx = its_cmd_ptr_to_offset(its, from); + /* Linearize to_idx if the command set has wrapped around */ to_idx = its_cmd_ptr_to_offset(its, to); + if (to_idx < prev_idx) + to_idx += ITS_CMD_QUEUE_SZ; + + linear_idx = prev_idx; while (1) { + s64 delta; + rd_idx = readl_relaxed(its->base + GITS_CREADR); - /* Direct case */ - if (from_idx < to_idx && rd_idx >= to_idx) - break; + /* + * Compute the read pointer progress, taking the + * potential wrap-around into account. + */ + delta = rd_idx - prev_idx; + if (rd_idx < prev_idx) + delta += ITS_CMD_QUEUE_SZ; - /* Wrapped case */ - if (from_idx >= to_idx && rd_idx >= to_idx && rd_idx < from_idx) + linear_idx += delta; + if (linear_idx >= to_idx) break; count--; if (!count) { - pr_err_ratelimited("ITS queue timeout (%llu %llu %llu)\n", - from_idx, to_idx, rd_idx); + pr_err_ratelimited("ITS queue timeout (%llu %llu)\n", + to_idx, linear_idx); return -1; } + prev_idx = rd_idx; cpu_relax(); udelay(1); } @@ -775,6 +786,7 @@ void name(struct its_node *its, \ struct its_cmd_block *cmd, *sync_cmd, *next_cmd; \ synctype *sync_obj; \ unsigned long flags; \ + u64 rd_idx; \ \ raw_spin_lock_irqsave(&its->lock, flags); \ \ @@ -796,10 +808,11 @@ void name(struct its_node *its, \ } \ \ post: \ + rd_idx = readl_relaxed(its->base + GITS_CREADR); \ next_cmd = its_post_commands(its); \ raw_spin_unlock_irqrestore(&its->lock, flags); \ \ - if (its_wait_for_range_completion(its, cmd, next_cmd)) \ + if (its_wait_for_range_completion(its, rd_idx, next_cmd)) \ pr_err_ratelimited("ITS cmd %ps failed\n", builder); \ } diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c index d32268cc1174..f3985469c221 100644 --- a/drivers/irqchip/irq-mips-gic.c +++ b/drivers/irqchip/irq-mips-gic.c @@ -388,7 +388,7 @@ static void gic_all_vpes_irq_cpu_online(struct irq_data *d) intr = GIC_HWIRQ_TO_LOCAL(d->hwirq); cd = irq_data_get_irq_chip_data(d); - write_gic_vl_map(intr, cd->map); + write_gic_vl_map(mips_gic_vx_map_reg(intr), cd->map); if (cd->mask) write_gic_vl_smask(BIT(intr)); } @@ -517,7 +517,7 @@ static int gic_irq_domain_map(struct irq_domain *d, unsigned int virq, spin_lock_irqsave(&gic_lock, flags); for_each_online_cpu(cpu) { write_gic_vl_other(mips_cm_vp_id(cpu)); - write_gic_vo_map(intr, map); + write_gic_vo_map(mips_gic_vx_map_reg(intr), map); } spin_unlock_irqrestore(&gic_lock, flags); diff --git a/drivers/irqchip/irq-ti-sci-inta.c b/drivers/irqchip/irq-ti-sci-inta.c index 011b60a49e3f..ef4d625d2d80 100644 --- a/drivers/irqchip/irq-ti-sci-inta.c +++ b/drivers/irqchip/irq-ti-sci-inta.c @@ -159,9 +159,9 @@ static struct ti_sci_inta_vint_desc *ti_sci_inta_alloc_parent_irq(struct irq_dom parent_fwspec.param[1] = vint_desc->vint_id; parent_virq = irq_create_fwspec_mapping(&parent_fwspec); - if (parent_virq <= 0) { + if (parent_virq == 0) { kfree(vint_desc); - return ERR_PTR(parent_virq); + return ERR_PTR(-EINVAL); } vint_desc->parent_virq = parent_virq; diff --git a/drivers/md/dm-init.c b/drivers/md/dm-init.c index 352e803f566e..728733a514c7 100644 --- a/drivers/md/dm-init.c +++ b/drivers/md/dm-init.c @@ -140,8 +140,8 @@ static char __init *dm_parse_table_entry(struct dm_device *dev, char *str) return ERR_PTR(-EINVAL); } /* target_args */ - dev->target_args_array[n] = kstrndup(field[3], GFP_KERNEL, - DM_MAX_STR_SIZE); + dev->target_args_array[n] = kstrndup(field[3], DM_MAX_STR_SIZE, + GFP_KERNEL); if (!dev->target_args_array[n]) return ERR_PTR(-ENOMEM); @@ -272,10 +272,10 @@ static int __init dm_init_init(void) return 0; if (strlen(create) >= DM_MAX_STR_SIZE) { - DMERR("Argument is too big. Limit is %d\n", DM_MAX_STR_SIZE); + DMERR("Argument is too big. Limit is %d", DM_MAX_STR_SIZE); return -EINVAL; } - str = kstrndup(create, GFP_KERNEL, DM_MAX_STR_SIZE); + str = kstrndup(create, DM_MAX_STR_SIZE, GFP_KERNEL); if (!str) return -ENOMEM; @@ -283,7 +283,7 @@ static int __init dm_init_init(void) if (r) goto out; - DMINFO("waiting for all devices to be available before creating mapped devices\n"); + DMINFO("waiting for all devices to be available before creating mapped devices"); wait_for_device_probe(); list_for_each_entry(dev, &devices, list) { diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index 9ea2b0291f20..e549392e0ea5 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -60,6 +60,7 @@ #define WRITE_LOG_VERSION 1ULL #define WRITE_LOG_MAGIC 0x6a736677736872ULL +#define WRITE_LOG_SUPER_SECTOR 0 /* * The disk format for this is braindead simple. @@ -115,6 +116,7 @@ struct log_writes_c { struct list_head logging_blocks; wait_queue_head_t wait; struct task_struct *log_kthread; + struct completion super_done; }; struct pending_block { @@ -180,6 +182,14 @@ static void log_end_io(struct bio *bio) bio_put(bio); } +static void log_end_super(struct bio *bio) +{ + struct log_writes_c *lc = bio->bi_private; + + complete(&lc->super_done); + log_end_io(bio); +} + /* * Meant to be called if there is an error, it will free all the pages * associated with the block. @@ -215,7 +225,8 @@ static int write_metadata(struct log_writes_c *lc, void *entry, bio->bi_iter.bi_size = 0; bio->bi_iter.bi_sector = sector; bio_set_dev(bio, lc->logdev->bdev); - bio->bi_end_io = log_end_io; + bio->bi_end_io = (sector == WRITE_LOG_SUPER_SECTOR) ? + log_end_super : log_end_io; bio->bi_private = lc; bio_set_op_attrs(bio, REQ_OP_WRITE, 0); @@ -418,11 +429,18 @@ static int log_super(struct log_writes_c *lc) super.nr_entries = cpu_to_le64(lc->logged_entries); super.sectorsize = cpu_to_le32(lc->sectorsize); - if (write_metadata(lc, &super, sizeof(super), NULL, 0, 0)) { + if (write_metadata(lc, &super, sizeof(super), NULL, 0, + WRITE_LOG_SUPER_SECTOR)) { DMERR("Couldn't write super"); return -1; } + /* + * Super sector should be writen in-order, otherwise the + * nr_entries could be rewritten incorrectly by an old bio. + */ + wait_for_completion_io(&lc->super_done); + return 0; } @@ -531,6 +549,7 @@ static int log_writes_ctr(struct dm_target *ti, unsigned int argc, char **argv) INIT_LIST_HEAD(&lc->unflushed_blocks); INIT_LIST_HEAD(&lc->logging_blocks); init_waitqueue_head(&lc->wait); + init_completion(&lc->super_done); atomic_set(&lc->io_blocks, 0); atomic_set(&lc->pending_blocks, 0); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 350cf0451456..ec8b27e20de3 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -561,7 +561,7 @@ static char **realloc_argv(unsigned *size, char **old_argv) gfp = GFP_NOIO; } argv = kmalloc_array(new_size, sizeof(*argv), gfp); - if (argv) { + if (argv && old_argv) { memcpy(argv, old_argv, *size * sizeof(*argv)); *size = new_size; } diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 720d06531aa3..ea24ff0612e3 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -235,8 +235,8 @@ static int verity_handle_err(struct dm_verity *v, enum verity_block_type type, BUG(); } - DMERR("%s: %s block %llu is corrupted", v->data_dev->name, type_str, - block); + DMERR_LIMIT("%s: %s block %llu is corrupted", v->data_dev->name, + type_str, block); if (v->corrupted_errs == DM_VERITY_MAX_CORRUPTED_ERRS) DMERR("%s: reached maximum errors", v->data_dev->name); diff --git a/drivers/mfd/stmfx.c b/drivers/mfd/stmfx.c index fe8efba2d45f..857991cb3cbb 100644 --- a/drivers/mfd/stmfx.c +++ b/drivers/mfd/stmfx.c @@ -204,12 +204,11 @@ static struct irq_chip stmfx_irq_chip = { static irqreturn_t stmfx_irq_handler(int irq, void *data) { struct stmfx *stmfx = data; - unsigned long n, pending; - u32 ack; - int ret; + unsigned long bits; + u32 pending, ack; + int n, ret; - ret = regmap_read(stmfx->map, STMFX_REG_IRQ_PENDING, - (u32 *)&pending); + ret = regmap_read(stmfx->map, STMFX_REG_IRQ_PENDING, &pending); if (ret) return IRQ_NONE; @@ -224,7 +223,8 @@ static irqreturn_t stmfx_irq_handler(int irq, void *data) return IRQ_NONE; } - for_each_set_bit(n, &pending, STMFX_REG_IRQ_SRC_MAX) + bits = pending; + for_each_set_bit(n, &bits, STMFX_REG_IRQ_SRC_MAX) handle_nested_irq(irq_find_mapping(stmfx->irq_domain, n)); return IRQ_HANDLED; diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index b5b68aa16eb3..6eb131292eb2 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -4662,7 +4662,6 @@ static int nand_detect(struct nand_chip *chip, struct nand_flash_dev *type) memorg = nanddev_get_memorg(&chip->base); memorg->planes_per_lun = 1; memorg->luns_per_target = 1; - memorg->ntargets = 1; /* * Reset the chip, required by some chips (e.g. Micron MT29FxGxxxxx) @@ -5027,6 +5026,8 @@ static int nand_scan_ident(struct nand_chip *chip, unsigned int maxchips, if (ret) return ret; + memorg->ntargets = maxchips; + /* Read the flash type */ ret = nand_detect(chip, table); if (ret) { diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c index 73172d7f512b..0c2ec1c21434 100644 --- a/drivers/mtd/spi-nor/spi-nor.c +++ b/drivers/mtd/spi-nor/spi-nor.c @@ -1636,6 +1636,95 @@ static int sr2_bit7_quad_enable(struct spi_nor *nor) return 0; } +/** + * spi_nor_clear_sr_bp() - clear the Status Register Block Protection bits. + * @nor: pointer to a 'struct spi_nor' + * + * Read-modify-write function that clears the Block Protection bits from the + * Status Register without affecting other bits. + * + * Return: 0 on success, -errno otherwise. + */ +static int spi_nor_clear_sr_bp(struct spi_nor *nor) +{ + int ret; + u8 mask = SR_BP2 | SR_BP1 | SR_BP0; + + ret = read_sr(nor); + if (ret < 0) { + dev_err(nor->dev, "error while reading status register\n"); + return ret; + } + + write_enable(nor); + + ret = write_sr(nor, ret & ~mask); + if (ret) { + dev_err(nor->dev, "write to status register failed\n"); + return ret; + } + + ret = spi_nor_wait_till_ready(nor); + if (ret) + dev_err(nor->dev, "timeout while writing status register\n"); + return ret; +} + +/** + * spi_nor_spansion_clear_sr_bp() - clear the Status Register Block Protection + * bits on spansion flashes. + * @nor: pointer to a 'struct spi_nor' + * + * Read-modify-write function that clears the Block Protection bits from the + * Status Register without affecting other bits. The function is tightly + * coupled with the spansion_quad_enable() function. Both assume that the Write + * Register with 16 bits, together with the Read Configuration Register (35h) + * instructions are supported. + * + * Return: 0 on success, -errno otherwise. + */ +static int spi_nor_spansion_clear_sr_bp(struct spi_nor *nor) +{ + int ret; + u8 mask = SR_BP2 | SR_BP1 | SR_BP0; + u8 sr_cr[2] = {0}; + + /* Check current Quad Enable bit value. */ + ret = read_cr(nor); + if (ret < 0) { + dev_err(nor->dev, + "error while reading configuration register\n"); + return ret; + } + + /* + * When the configuration register Quad Enable bit is one, only the + * Write Status (01h) command with two data bytes may be used. + */ + if (ret & CR_QUAD_EN_SPAN) { + sr_cr[1] = ret; + + ret = read_sr(nor); + if (ret < 0) { + dev_err(nor->dev, + "error while reading status register\n"); + return ret; + } + sr_cr[0] = ret & ~mask; + + ret = write_sr_cr(nor, sr_cr); + if (ret) + dev_err(nor->dev, "16-bit write register failed\n"); + return ret; + } + + /* + * If the Quad Enable bit is zero, use the Write Status (01h) command + * with one data byte. + */ + return spi_nor_clear_sr_bp(nor); +} + /* Used when the "_ext_id" is two bytes at most */ #define INFO(_jedec_id, _ext_id, _sector_size, _n_sectors, _flags) \ .id = { \ @@ -3660,6 +3749,8 @@ static int spi_nor_init_params(struct spi_nor *nor, default: /* Kept only for backward compatibility purpose. */ params->quad_enable = spansion_quad_enable; + if (nor->clear_sr_bp) + nor->clear_sr_bp = spi_nor_spansion_clear_sr_bp; break; } @@ -3912,17 +4003,13 @@ static int spi_nor_init(struct spi_nor *nor) { int err; - /* - * Atmel, SST, Intel/Numonyx, and others serial NOR tend to power up - * with the software protection bits set - */ - if (JEDEC_MFR(nor->info) == SNOR_MFR_ATMEL || - JEDEC_MFR(nor->info) == SNOR_MFR_INTEL || - JEDEC_MFR(nor->info) == SNOR_MFR_SST || - nor->info->flags & SPI_NOR_HAS_LOCK) { - write_enable(nor); - write_sr(nor, 0); - spi_nor_wait_till_ready(nor); + if (nor->clear_sr_bp) { + err = nor->clear_sr_bp(nor); + if (err) { + dev_err(nor->dev, + "fail to clear block protection bits\n"); + return err; + } } if (nor->quad_enable) { @@ -4047,6 +4134,16 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, if (info->flags & SPI_S3AN) nor->flags |= SNOR_F_READY_XSR_RDY; + /* + * Atmel, SST, Intel/Numonyx, and others serial NOR tend to power up + * with the software protection bits set. + */ + if (JEDEC_MFR(nor->info) == SNOR_MFR_ATMEL || + JEDEC_MFR(nor->info) == SNOR_MFR_INTEL || + JEDEC_MFR(nor->info) == SNOR_MFR_SST || + nor->info->flags & SPI_NOR_HAS_LOCK) + nor->clear_sr_bp = spi_nor_clear_sr_bp; + /* Parse the Serial Flash Discoverable Parameters table. */ ret = spi_nor_init_params(nor, ¶ms); if (ret) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 407f4095a37a..799fc38c5c34 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4320,12 +4320,12 @@ void bond_setup(struct net_device *bond_dev) bond_dev->features |= NETIF_F_NETNS_LOCAL; bond_dev->hw_features = BOND_VLAN_FEATURES | - NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL | NETIF_F_GSO_UDP_L4; bond_dev->features |= bond_dev->hw_features; + bond_dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; } /* Destroy a bonding device. diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index f46086fa9064..db91b213eae1 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -436,9 +436,9 @@ int ksz_switch_register(struct ksz_device *dev, return PTR_ERR(dev->reset_gpio); if (dev->reset_gpio) { - gpiod_set_value(dev->reset_gpio, 1); + gpiod_set_value_cansleep(dev->reset_gpio, 1); mdelay(10); - gpiod_set_value(dev->reset_gpio, 0); + gpiod_set_value_cansleep(dev->reset_gpio, 0); } mutex_init(&dev->dev_mutex); @@ -487,7 +487,7 @@ void ksz_switch_remove(struct ksz_device *dev) dsa_unregister_switch(dev->ds); if (dev->reset_gpio) - gpiod_set_value(dev->reset_gpio, 1); + gpiod_set_value_cansleep(dev->reset_gpio, 1); } EXPORT_SYMBOL(ksz_switch_remove); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c index 18bc035da850..1fff462a4175 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c @@ -843,9 +843,14 @@ int aq_filters_vlans_update(struct aq_nic_s *aq_nic) return err; if (aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) { - if (hweight < AQ_VLAN_MAX_FILTERS) - err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw, true); + if (hweight < AQ_VLAN_MAX_FILTERS && hweight > 0) { + err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw, + !(aq_nic->packet_filter & IFF_PROMISC)); + aq_nic->aq_nic_cfg.is_vlan_force_promisc = false; + } else { /* otherwise left in promiscue mode */ + aq_nic->aq_nic_cfg.is_vlan_force_promisc = true; + } } return err; @@ -866,6 +871,7 @@ int aq_filters_vlan_offload_off(struct aq_nic_s *aq_nic) if (unlikely(!aq_hw_ops->hw_filter_vlan_ctrl)) return -EOPNOTSUPP; + aq_nic->aq_nic_cfg.is_vlan_force_promisc = true; err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw, false); if (err) return err; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 0da5e161ec5d..41172fbebddd 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -126,6 +126,7 @@ void aq_nic_cfg_start(struct aq_nic_s *self) cfg->link_speed_msk &= cfg->aq_hw_caps->link_speed_msk; cfg->features = cfg->aq_hw_caps->hw_features; + cfg->is_vlan_force_promisc = true; } static int aq_nic_update_link_status(struct aq_nic_s *self) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h index eb2e3c7c36f9..0f22f5d5691b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -35,6 +35,7 @@ struct aq_nic_cfg_s { u32 flow_control; u32 link_speed_msk; u32 wol; + bool is_vlan_force_promisc; u16 is_mc_list_enabled; u16 mc_list_count; bool is_autoneg; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 1c7593d54035..13ac2661a473 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -778,8 +778,15 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self, unsigned int packet_filter) { unsigned int i = 0U; + struct aq_nic_cfg_s *cfg = self->aq_nic_cfg; + + hw_atl_rpfl2promiscuous_mode_en_set(self, + IS_FILTER_ENABLED(IFF_PROMISC)); + + hw_atl_rpf_vlan_prom_mode_en_set(self, + IS_FILTER_ENABLED(IFF_PROMISC) || + cfg->is_vlan_force_promisc); - hw_atl_rpfl2promiscuous_mode_en_set(self, IS_FILTER_ENABLED(IFF_PROMISC)); hw_atl_rpfl2multicast_flr_en_set(self, IS_FILTER_ENABLED(IFF_ALLMULTI), 0); @@ -788,13 +795,13 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self, hw_atl_rpfl2broadcast_en_set(self, IS_FILTER_ENABLED(IFF_BROADCAST)); - self->aq_nic_cfg->is_mc_list_enabled = IS_FILTER_ENABLED(IFF_MULTICAST); + cfg->is_mc_list_enabled = IS_FILTER_ENABLED(IFF_MULTICAST); for (i = HW_ATL_B0_MAC_MIN; i < HW_ATL_B0_MAC_MAX; ++i) hw_atl_rpfl2_uc_flr_en_set(self, - (self->aq_nic_cfg->is_mc_list_enabled && - (i <= self->aq_nic_cfg->mc_list_count)) ? - 1U : 0U, i); + (cfg->is_mc_list_enabled && + (i <= cfg->mc_list_count)) ? + 1U : 0U, i); return aq_hw_err_from_flags(self); } @@ -1086,7 +1093,7 @@ static int hw_atl_b0_hw_vlan_set(struct aq_hw_s *self, static int hw_atl_b0_hw_vlan_ctrl(struct aq_hw_s *self, bool enable) { /* set promisc in case of disabing the vland filter */ - hw_atl_rpf_vlan_prom_mode_en_set(self, !!!enable); + hw_atl_rpf_vlan_prom_mode_en_set(self, !enable); return aq_hw_err_from_flags(self); } diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 2375a13bb446..262a28ff81fc 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -4180,7 +4180,7 @@ static int macb_probe(struct platform_device *pdev) if (PTR_ERR(mac) == -EPROBE_DEFER) { err = -EPROBE_DEFER; goto err_out_free_netdev; - } else if (!IS_ERR(mac)) { + } else if (!IS_ERR_OR_NULL(mac)) { ether_addr_copy(bp->dev->dev_addr, mac); } else { macb_get_hwaddr(bp); diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index 8a6785173228..492f8769ac12 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -891,7 +891,7 @@ static void be_self_test(struct net_device *netdev, struct ethtool_test *test, u64 *data) { struct be_adapter *adapter = netdev_priv(netdev); - int status; + int status, cnt; u8 link_status = 0; if (adapter->function_caps & BE_FUNCTION_CAPS_SUPER_NIC) { @@ -902,6 +902,9 @@ static void be_self_test(struct net_device *netdev, struct ethtool_test *test, memset(data, 0, sizeof(u64) * ETHTOOL_TESTS_NUM); + /* check link status before offline tests */ + link_status = netif_carrier_ok(netdev); + if (test->flags & ETH_TEST_FL_OFFLINE) { if (be_loopback_test(adapter, BE_MAC_LOOPBACK, &data[0]) != 0) test->flags |= ETH_TEST_FL_FAILED; @@ -922,13 +925,26 @@ static void be_self_test(struct net_device *netdev, struct ethtool_test *test, test->flags |= ETH_TEST_FL_FAILED; } - status = be_cmd_link_status_query(adapter, NULL, &link_status, 0); - if (status) { - test->flags |= ETH_TEST_FL_FAILED; - data[4] = -1; - } else if (!link_status) { + /* link status was down prior to test */ + if (!link_status) { test->flags |= ETH_TEST_FL_FAILED; data[4] = 1; + return; + } + + for (cnt = 10; cnt; cnt--) { + status = be_cmd_link_status_query(adapter, NULL, &link_status, + 0); + if (status) { + test->flags |= ETH_TEST_FL_FAILED; + data[4] = -1; + break; + } + + if (link_status) + break; + + msleep_interruptible(500); } } diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index 67f9bb6e941b..9b036c857b1d 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -1057,7 +1057,7 @@ sis900_open(struct net_device *net_dev) sis900_set_mode(sis_priv, HW_SPEED_10_MBPS, FDX_CAPABLE_HALF_SELECTED); /* Enable all known interrupts by setting the interrupt mask. */ - sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxIDLE); + sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxIDLE | TxDESC); sw32(cr, RxENA | sr32(cr)); sw32(ier, IE); @@ -1578,7 +1578,7 @@ static void sis900_tx_timeout(struct net_device *net_dev) sw32(txdp, sis_priv->tx_ring_dma); /* Enable all known interrupts by setting the interrupt mask. */ - sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxIDLE); + sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxIDLE | TxDESC); } /** @@ -1618,7 +1618,7 @@ sis900_start_xmit(struct sk_buff *skb, struct net_device *net_dev) spin_unlock_irqrestore(&sis_priv->lock, flags); return NETDEV_TX_OK; } - sis_priv->tx_ring[entry].cmdsts = (OWN | skb->len); + sis_priv->tx_ring[entry].cmdsts = (OWN | INTR | skb->len); sw32(cr, TxENA | sr32(cr)); sis_priv->cur_tx ++; @@ -1674,7 +1674,7 @@ static irqreturn_t sis900_interrupt(int irq, void *dev_instance) do { status = sr32(isr); - if ((status & (HIBERR|TxURN|TxERR|TxIDLE|RxORN|RxERR|RxOK)) == 0) + if ((status & (HIBERR|TxURN|TxERR|TxIDLE|TxDESC|RxORN|RxERR|RxOK)) == 0) /* nothing intresting happened */ break; handled = 1; @@ -1684,7 +1684,7 @@ static irqreturn_t sis900_interrupt(int irq, void *dev_instance) /* Rx interrupt */ sis900_rx(net_dev); - if (status & (TxURN | TxERR | TxIDLE)) + if (status & (TxURN | TxERR | TxIDLE | TxDESC)) /* Tx interrupt */ sis900_finish_xmit(net_dev); @@ -1896,8 +1896,8 @@ static void sis900_finish_xmit (struct net_device *net_dev) if (tx_status & OWN) { /* The packet is not transmitted yet (owned by hardware) ! - * Note: the interrupt is generated only when Tx Machine - * is idle, so this is an almost impossible case */ + * Note: this is an almost impossible condition + * in case of TxDESC ('descriptor interrupt') */ break; } @@ -2473,7 +2473,7 @@ static int sis900_resume(struct pci_dev *pci_dev) sis900_set_mode(sis_priv, HW_SPEED_10_MBPS, FDX_CAPABLE_HALF_SELECTED); /* Enable all known interrupts by setting the interrupt mask. */ - sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxIDLE); + sw32(imr, RxSOVR | RxORN | RxERR | RxOK | TxURN | TxERR | TxIDLE | TxDESC); sw32(cr, RxENA | sr32(cr)); sw32(ier, IE); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 2dcdf761d525..020159622559 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -112,7 +112,7 @@ static int adjust_systime(void __iomem *ioaddr, u32 sec, u32 nsec, * programmed with (2^32 – <new_sec_value>) */ if (gmac4) - sec = (100000000ULL - sec); + sec = -sec; value = readl(ioaddr + PTP_TCR); if (value & PTP_TCR_TSCTRLSSR) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 06dd51f47cfd..06358fe5b245 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -2947,12 +2947,15 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) /* Manage tx mitigation */ tx_q->tx_count_frames += nfrags + 1; - if (priv->tx_coal_frames <= tx_q->tx_count_frames) { + if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) && + !(priv->synopsys_id >= DWMAC_CORE_4_00 && + (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + priv->hwts_tx_en)) { + stmmac_tx_timer_arm(priv, queue); + } else { + tx_q->tx_count_frames = 0; stmmac_set_tx_ic(priv, desc); priv->xstats.tx_set_ic_bit++; - tx_q->tx_count_frames = 0; - } else { - stmmac_tx_timer_arm(priv, queue); } skb_tx_timestamp(skb); @@ -3166,12 +3169,15 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) * element in case of no SG. */ tx_q->tx_count_frames += nfrags + 1; - if (priv->tx_coal_frames <= tx_q->tx_count_frames) { + if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) && + !(priv->synopsys_id >= DWMAC_CORE_4_00 && + (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + priv->hwts_tx_en)) { + stmmac_tx_timer_arm(priv, queue); + } else { + tx_q->tx_count_frames = 0; stmmac_set_tx_ic(priv, desc); priv->xstats.tx_set_ic_bit++; - tx_q->tx_count_frames = 0; - } else { - stmmac_tx_timer_arm(priv, queue); } skb_tx_timestamp(skb); diff --git a/drivers/net/ppp/ppp_mppe.c b/drivers/net/ppp/ppp_mppe.c index ff61dd8748de..66c8e65f6872 100644 --- a/drivers/net/ppp/ppp_mppe.c +++ b/drivers/net/ppp/ppp_mppe.c @@ -63,6 +63,7 @@ MODULE_AUTHOR("Frank Cusack <fcusack@fcusack.com>"); MODULE_DESCRIPTION("Point-to-Point Protocol Microsoft Point-to-Point Encryption support"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_ALIAS("ppp-compress-" __stringify(CI_MPPE)); +MODULE_SOFTDEP("pre: arc4"); MODULE_VERSION("1.0.2"); static unsigned int diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index b48006e7fa2f..36916bf51ee6 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2128,12 +2128,12 @@ static void team_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; dev->hw_features = TEAM_VLAN_FEATURES | - NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; dev->hw_features |= NETIF_F_GSO_ENCAP_ALL | NETIF_F_GSO_UDP_L4; dev->features |= dev->hw_features; + dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; } static int team_newlink(struct net *src_net, struct net_device *dev, diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index d080f8048e52..8b4ad10cf940 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1482,7 +1482,7 @@ static int qmi_wwan_probe(struct usb_interface *intf, * different. Ignore the current interface if the number of endpoints * equals the number for the diag interface (two). */ - info = (void *)&id->driver_info; + info = (void *)id->driver_info; if (info->data & QMI_WWAN_QUIRK_QUECTEL_DYNCFG) { if (desc->bNumEndpoints == 2) diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 11b9525dff27..311b0cc6eb98 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -350,8 +350,8 @@ static int vrf_finish_output6(struct net *net, struct sock *sk, { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; + const struct in6_addr *nexthop; struct neighbour *neigh; - struct in6_addr *nexthop; int ret; nf_reset(skb); diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index 1897847ceb0c..45049f558860 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -685,12 +685,21 @@ static pci_power_t acpi_pci_get_power_state(struct pci_dev *dev) if (!adev || !acpi_device_power_manageable(adev)) return PCI_UNKNOWN; - if (acpi_device_get_power(adev, &state) || state == ACPI_STATE_UNKNOWN) + state = adev->power.state; + if (state == ACPI_STATE_UNKNOWN) return PCI_UNKNOWN; return state_conv[state]; } +static void acpi_pci_refresh_power_state(struct pci_dev *dev) +{ + struct acpi_device *adev = ACPI_COMPANION(&dev->dev); + + if (adev && acpi_device_power_manageable(adev)) + acpi_device_update_power(adev, NULL); +} + static int acpi_pci_propagate_wakeup(struct pci_bus *bus, bool enable) { while (bus->parent) { @@ -748,6 +757,7 @@ static const struct pci_platform_pm_ops acpi_pci_platform_pm = { .is_manageable = acpi_pci_power_manageable, .set_state = acpi_pci_set_power_state, .get_state = acpi_pci_get_power_state, + .refresh_state = acpi_pci_refresh_power_state, .choose_state = acpi_pci_choose_state, .set_wakeup = acpi_pci_wakeup, .need_resume = acpi_pci_need_resume, @@ -901,6 +911,7 @@ static void pci_acpi_setup(struct device *dev) device_wakeup_enable(dev); acpi_pci_wakeup(pci_dev, false); + acpi_device_power_add_dependent(adev, dev); } static void pci_acpi_cleanup(struct device *dev) @@ -913,6 +924,7 @@ static void pci_acpi_cleanup(struct device *dev) pci_acpi_remove_pm_notifier(adev); if (adev->wakeup.flags.valid) { + acpi_device_power_remove_dependent(adev, dev); if (pci_dev->bridge_d3) device_wakeup_disable(dev); diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index 98af9ecd4a90..36dbe960306b 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -678,6 +678,7 @@ static bool pci_has_legacy_pm_support(struct pci_dev *pci_dev) static int pci_pm_prepare(struct device *dev) { struct device_driver *drv = dev->driver; + struct pci_dev *pci_dev = to_pci_dev(dev); if (drv && drv->pm && drv->pm->prepare) { int error = drv->pm->prepare(dev); @@ -687,7 +688,15 @@ static int pci_pm_prepare(struct device *dev) if (!error && dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_PREPARE)) return 0; } - return pci_dev_keep_suspended(to_pci_dev(dev)); + if (pci_dev_need_resume(pci_dev)) + return 0; + + /* + * The PME setting needs to be adjusted here in case the direct-complete + * optimization is used with respect to this device. + */ + pci_dev_adjust_pme(pci_dev); + return 1; } static void pci_pm_complete(struct device *dev) @@ -701,7 +710,14 @@ static void pci_pm_complete(struct device *dev) if (pm_runtime_suspended(dev) && pm_resume_via_firmware()) { pci_power_t pre_sleep_state = pci_dev->current_state; - pci_update_current_state(pci_dev, pci_dev->current_state); + pci_refresh_power_state(pci_dev); + /* + * On platforms with ACPI this check may also trigger for + * devices sharing power resources if one of those power + * resources has been activated as a result of a change of the + * power state of another device sharing it. However, in that + * case it is also better to resume the device, in general. + */ if (pci_dev->current_state < pre_sleep_state) pm_request_resume(dev); } @@ -757,9 +773,11 @@ static int pci_pm_suspend(struct device *dev) * better to resume the device from runtime suspend here. */ if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) || - !pci_dev_keep_suspended(pci_dev)) { + pci_dev_need_resume(pci_dev)) { pm_runtime_resume(dev); pci_dev->state_saved = false; + } else { + pci_dev_adjust_pme(pci_dev); } if (pm->suspend) { @@ -859,7 +877,7 @@ static int pci_pm_suspend_noirq(struct device *dev) pci_dev->bus->self->skip_bus_pm = true; } - if (pci_dev->skip_bus_pm && !pm_suspend_via_firmware()) { + if (pci_dev->skip_bus_pm && pm_suspend_no_platform()) { dev_dbg(dev, "PCI PM: Skipped\n"); goto Fixup; } @@ -914,10 +932,10 @@ static int pci_pm_resume_noirq(struct device *dev) /* * In the suspend-to-idle case, devices left in D0 during suspend will * stay in D0, so it is not necessary to restore or update their - * configuration here and attempting to put them into D0 again may - * confuse some firmware, so avoid doing that. + * configuration here and attempting to put them into D0 again is + * pointless, so avoid doing that. */ - if (!pci_dev->skip_bus_pm || pm_suspend_via_firmware()) + if (!(pci_dev->skip_bus_pm && pm_suspend_no_platform())) pci_pm_default_resume_early(pci_dev); pci_fixup_device(pci_fixup_resume_early, pci_dev); @@ -994,15 +1012,15 @@ static int pci_pm_freeze(struct device *dev) } /* - * This used to be done in pci_pm_prepare() for all devices and some - * drivers may depend on it, so do it here. Ideally, runtime-suspended - * devices should not be touched during freeze/thaw transitions, - * however. + * Resume all runtime-suspended devices before creating a snapshot + * image of system memory, because the restore kernel generally cannot + * be expected to always handle them consistently and they need to be + * put into the runtime-active metastate during system resume anyway, + * so it is better to ensure that the state saved in the image will be + * always consistent with that. */ - if (!dev_pm_smart_suspend_and_suspended(dev)) { - pm_runtime_resume(dev); - pci_dev->state_saved = false; - } + pm_runtime_resume(dev); + pci_dev->state_saved = false; if (pm->freeze) { int error; @@ -1016,22 +1034,11 @@ static int pci_pm_freeze(struct device *dev) return 0; } -static int pci_pm_freeze_late(struct device *dev) -{ - if (dev_pm_smart_suspend_and_suspended(dev)) - return 0; - - return pm_generic_freeze_late(dev); -} - static int pci_pm_freeze_noirq(struct device *dev) { struct pci_dev *pci_dev = to_pci_dev(dev); struct device_driver *drv = dev->driver; - if (dev_pm_smart_suspend_and_suspended(dev)) - return 0; - if (pci_has_legacy_pm_support(pci_dev)) return pci_legacy_suspend_late(dev, PMSG_FREEZE); @@ -1061,16 +1068,6 @@ static int pci_pm_thaw_noirq(struct device *dev) struct device_driver *drv = dev->driver; int error = 0; - /* - * If the device is in runtime suspend, the code below may not work - * correctly with it, so skip that code and make the PM core skip all of - * the subsequent "thaw" callbacks for the device. - */ - if (dev_pm_smart_suspend_and_suspended(dev)) { - dev_pm_skip_next_resume_phases(dev); - return 0; - } - if (pcibios_pm_ops.thaw_noirq) { error = pcibios_pm_ops.thaw_noirq(dev); if (error) @@ -1130,10 +1127,13 @@ static int pci_pm_poweroff(struct device *dev) /* The reason to do that is the same as in pci_pm_suspend(). */ if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) || - !pci_dev_keep_suspended(pci_dev)) + pci_dev_need_resume(pci_dev)) { pm_runtime_resume(dev); + pci_dev->state_saved = false; + } else { + pci_dev_adjust_pme(pci_dev); + } - pci_dev->state_saved = false; if (pm->poweroff) { int error; @@ -1205,10 +1205,6 @@ static int pci_pm_restore_noirq(struct device *dev) struct device_driver *drv = dev->driver; int error = 0; - /* This is analogous to the pci_pm_resume_noirq() case. */ - if (dev_pm_smart_suspend_and_suspended(dev)) - pm_runtime_set_active(dev); - if (pcibios_pm_ops.restore_noirq) { error = pcibios_pm_ops.restore_noirq(dev); if (error) @@ -1258,7 +1254,6 @@ static int pci_pm_restore(struct device *dev) #else /* !CONFIG_HIBERNATE_CALLBACKS */ #define pci_pm_freeze NULL -#define pci_pm_freeze_late NULL #define pci_pm_freeze_noirq NULL #define pci_pm_thaw NULL #define pci_pm_thaw_noirq NULL @@ -1384,7 +1379,6 @@ static const struct dev_pm_ops pci_dev_pm_ops = { .suspend_late = pci_pm_suspend_late, .resume = pci_pm_resume, .freeze = pci_pm_freeze, - .freeze_late = pci_pm_freeze_late, .thaw = pci_pm_thaw, .poweroff = pci_pm_poweroff, .poweroff_late = pci_pm_poweroff_late, diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 8abc843b1615..b1f563916036 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -777,6 +777,12 @@ static inline pci_power_t platform_pci_get_power_state(struct pci_dev *dev) return pci_platform_pm ? pci_platform_pm->get_state(dev) : PCI_UNKNOWN; } +static inline void platform_pci_refresh_power_state(struct pci_dev *dev) +{ + if (pci_platform_pm && pci_platform_pm->refresh_state) + pci_platform_pm->refresh_state(dev); +} + static inline pci_power_t platform_pci_choose_state(struct pci_dev *dev) { return pci_platform_pm ? @@ -938,6 +944,21 @@ void pci_update_current_state(struct pci_dev *dev, pci_power_t state) } /** + * pci_refresh_power_state - Refresh the given device's power state data + * @dev: Target PCI device. + * + * Ask the platform to refresh the devices power state information and invoke + * pci_update_current_state() to update its current PCI power state. + */ +void pci_refresh_power_state(struct pci_dev *dev) +{ + if (platform_pci_power_manageable(dev)) + platform_pci_refresh_power_state(dev); + + pci_update_current_state(dev, dev->current_state); +} + +/** * pci_power_up - Put the given device into D0 forcibly * @dev: PCI device to power up */ @@ -1004,15 +1025,10 @@ static void __pci_start_power_transition(struct pci_dev *dev, pci_power_t state) if (state == PCI_D0) { pci_platform_power_transition(dev, PCI_D0); /* - * Mandatory power management transition delays, see - * PCI Express Base Specification Revision 2.0 Section - * 6.6.1: Conventional Reset. Do not delay for - * devices powered on/off by corresponding bridge, - * because have already delayed for the bridge. + * Mandatory power management transition delays are + * handled in the PCIe portdrv resume hooks. */ if (dev->runtime_d3cold) { - if (dev->d3cold_delay && !dev->imm_ready) - msleep(dev->d3cold_delay); /* * When powering on a bridge from D3cold, the * whole hierarchy may be powered on into @@ -2065,6 +2081,13 @@ static void pci_pme_list_scan(struct work_struct *work) */ if (bridge && bridge->current_state != PCI_D0) continue; + /* + * If the device is in D3cold it should not be + * polled either. + */ + if (pme_dev->dev->current_state == PCI_D3cold) + continue; + pci_pme_wakeup(pme_dev->dev, NULL); } else { list_del(&pme_dev->list); @@ -2459,45 +2482,56 @@ bool pci_dev_run_wake(struct pci_dev *dev) EXPORT_SYMBOL_GPL(pci_dev_run_wake); /** - * pci_dev_keep_suspended - Check if the device can stay in the suspended state. + * pci_dev_need_resume - Check if it is necessary to resume the device. * @pci_dev: Device to check. * - * Return 'true' if the device is runtime-suspended, it doesn't have to be + * Return 'true' if the device is not runtime-suspended or it has to be * reconfigured due to wakeup settings difference between system and runtime - * suspend and the current power state of it is suitable for the upcoming - * (system) transition. - * - * If the device is not configured for system wakeup, disable PME for it before - * returning 'true' to prevent it from waking up the system unnecessarily. + * suspend, or the current power state of it is not suitable for the upcoming + * (system-wide) transition. */ -bool pci_dev_keep_suspended(struct pci_dev *pci_dev) +bool pci_dev_need_resume(struct pci_dev *pci_dev) { struct device *dev = &pci_dev->dev; - bool wakeup = device_may_wakeup(dev); + pci_power_t target_state; - if (!pm_runtime_suspended(dev) - || pci_target_state(pci_dev, wakeup) != pci_dev->current_state - || platform_pci_need_resume(pci_dev)) - return false; + if (!pm_runtime_suspended(dev) || platform_pci_need_resume(pci_dev)) + return true; + + target_state = pci_target_state(pci_dev, device_may_wakeup(dev)); /* - * At this point the device is good to go unless it's been configured - * to generate PME at the runtime suspend time, but it is not supposed - * to wake up the system. In that case, simply disable PME for it - * (it will have to be re-enabled on exit from system resume). - * - * If the device's power state is D3cold and the platform check above - * hasn't triggered, the device's configuration is suitable and we don't - * need to manipulate it at all. + * If the earlier platform check has not triggered, D3cold is just power + * removal on top of D3hot, so no need to resume the device in that + * case. */ + return target_state != pci_dev->current_state && + target_state != PCI_D3cold && + pci_dev->current_state != PCI_D3hot; +} + +/** + * pci_dev_adjust_pme - Adjust PME setting for a suspended device. + * @pci_dev: Device to check. + * + * If the device is suspended and it is not configured for system wakeup, + * disable PME for it to prevent it from waking up the system unnecessarily. + * + * Note that if the device's power state is D3cold and the platform check in + * pci_dev_need_resume() has not triggered, the device's configuration need not + * be changed. + */ +void pci_dev_adjust_pme(struct pci_dev *pci_dev) +{ + struct device *dev = &pci_dev->dev; + spin_lock_irq(&dev->power.lock); - if (pm_runtime_suspended(dev) && pci_dev->current_state < PCI_D3cold && - !wakeup) + if (pm_runtime_suspended(dev) && !device_may_wakeup(dev) && + pci_dev->current_state < PCI_D3cold) __pci_pme_active(pci_dev, false); spin_unlock_irq(&dev->power.lock); - return true; } /** @@ -4568,14 +4602,16 @@ static int pci_pm_reset(struct pci_dev *dev, int probe) return pci_dev_wait(dev, "PM D3->D0", PCIE_RESET_READY_POLL_MS); } + /** - * pcie_wait_for_link - Wait until link is active or inactive + * pcie_wait_for_link_delay - Wait until link is active or inactive * @pdev: Bridge device * @active: waiting for active or inactive? + * @delay: Delay to wait after link has become active (in ms) * * Use this to wait till link becomes active or inactive. */ -bool pcie_wait_for_link(struct pci_dev *pdev, bool active) +bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, int delay) { int timeout = 1000; bool ret; @@ -4612,13 +4648,25 @@ bool pcie_wait_for_link(struct pci_dev *pdev, bool active) timeout -= 10; } if (active && ret) - msleep(100); + msleep(delay); else if (ret != active) pci_info(pdev, "Data Link Layer Link Active not %s in 1000 msec\n", active ? "set" : "cleared"); return ret == active; } +/** + * pcie_wait_for_link - Wait until link is active or inactive + * @pdev: Bridge device + * @active: waiting for active or inactive? + * + * Use this to wait till link becomes active or inactive. + */ +bool pcie_wait_for_link(struct pci_dev *pdev, bool active) +{ + return pcie_wait_for_link_delay(pdev, active, 100); +} + void pci_reset_secondary_bus(struct pci_dev *dev) { u16 ctrl; diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index 9cb99380c61e..5db6f985f16d 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -51,6 +51,8 @@ int pci_bus_error_reset(struct pci_dev *dev); * * @get_state: queries the platform firmware for a device's current power state * + * @refresh_state: asks the platform to refresh the device's power state data + * * @choose_state: returns PCI power state of given device preferred by the * platform; to be used during system-wide transitions from a * sleeping state to the working state and vice versa @@ -69,6 +71,7 @@ struct pci_platform_pm_ops { bool (*is_manageable)(struct pci_dev *dev); int (*set_state)(struct pci_dev *dev, pci_power_t state); pci_power_t (*get_state)(struct pci_dev *dev); + void (*refresh_state)(struct pci_dev *dev); pci_power_t (*choose_state)(struct pci_dev *dev); int (*set_wakeup)(struct pci_dev *dev, bool enable); bool (*need_resume)(struct pci_dev *dev); @@ -76,13 +79,15 @@ struct pci_platform_pm_ops { int pci_set_platform_pm(const struct pci_platform_pm_ops *ops); void pci_update_current_state(struct pci_dev *dev, pci_power_t state); +void pci_refresh_power_state(struct pci_dev *dev); void pci_power_up(struct pci_dev *dev); void pci_disable_enabled_device(struct pci_dev *dev); int pci_finish_runtime_suspend(struct pci_dev *dev); void pcie_clear_root_pme_status(struct pci_dev *dev); int __pci_pme_wakeup(struct pci_dev *dev, void *ign); void pci_pme_restore(struct pci_dev *dev); -bool pci_dev_keep_suspended(struct pci_dev *dev); +bool pci_dev_need_resume(struct pci_dev *dev); +void pci_dev_adjust_pme(struct pci_dev *dev); void pci_dev_complete_resume(struct pci_dev *pci_dev); void pci_config_pm_runtime_get(struct pci_dev *dev); void pci_config_pm_runtime_put(struct pci_dev *dev); @@ -493,6 +498,7 @@ static inline int pci_dev_specific_disable_acs_redir(struct pci_dev *dev) void pcie_do_recovery(struct pci_dev *dev, enum pci_channel_state state, u32 service); +bool pcie_wait_for_link_delay(struct pci_dev *pdev, bool active, int delay); bool pcie_wait_for_link(struct pci_dev *pdev, bool active); #ifdef CONFIG_PCIEASPM void pcie_aspm_init_link_state(struct pci_dev *pdev); diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c index 1b330129089f..308c3e0c4a34 100644 --- a/drivers/pci/pcie/portdrv_core.c +++ b/drivers/pci/pcie/portdrv_core.c @@ -9,6 +9,7 @@ #include <linux/module.h> #include <linux/pci.h> #include <linux/kernel.h> +#include <linux/delay.h> #include <linux/errno.h> #include <linux/pm.h> #include <linux/pm_runtime.h> @@ -378,6 +379,67 @@ static int pm_iter(struct device *dev, void *data) return 0; } +static int get_downstream_delay(struct pci_bus *bus) +{ + struct pci_dev *pdev; + int min_delay = 100; + int max_delay = 0; + + list_for_each_entry(pdev, &bus->devices, bus_list) { + if (!pdev->imm_ready) + min_delay = 0; + else if (pdev->d3cold_delay < min_delay) + min_delay = pdev->d3cold_delay; + if (pdev->d3cold_delay > max_delay) + max_delay = pdev->d3cold_delay; + } + + return max(min_delay, max_delay); +} + +/* + * wait_for_downstream_link - Wait for downstream link to establish + * @pdev: PCIe port whose downstream link is waited + * + * Handle delays according to PCIe 4.0 section 6.6.1 before configuration + * access to the downstream component is permitted. + * + * This blocks PCI core resume of the hierarchy below this port until the + * link is trained. Should be called before resuming port services to + * prevent pciehp from starting to tear-down the hierarchy too soon. + */ +static void wait_for_downstream_link(struct pci_dev *pdev) +{ + int delay; + + if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT && + pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM) + return; + + if (pci_dev_is_disconnected(pdev)) + return; + + if (!pdev->subordinate || list_empty(&pdev->subordinate->devices) || + !pdev->bridge_d3) + return; + + delay = get_downstream_delay(pdev->subordinate); + if (!delay) + return; + + dev_dbg(&pdev->dev, "waiting downstream link for %d ms\n", delay); + + /* + * If downstream port does not support speeds greater than 5 GT/s + * need to wait 100ms. For higher speeds (gen3) we need to wait + * first for the data link layer to become active. + */ + if (pcie_get_speed_cap(pdev) <= PCIE_SPEED_5_0GT) + msleep(delay); + else + pcie_wait_for_link_delay(pdev, true, delay); +} + /** * pcie_port_device_suspend - suspend port services associated with a PCIe port * @dev: PCI Express port to handle @@ -391,6 +453,8 @@ int pcie_port_device_suspend(struct device *dev) int pcie_port_device_resume_noirq(struct device *dev) { size_t off = offsetof(struct pcie_port_service_driver, resume_noirq); + + wait_for_downstream_link(to_pci_dev(dev)); return device_for_each_child(dev, &off, pm_iter); } @@ -421,6 +485,8 @@ int pcie_port_device_runtime_suspend(struct device *dev) int pcie_port_device_runtime_resume(struct device *dev) { size_t off = offsetof(struct pcie_port_service_driver, runtime_resume); + + wait_for_downstream_link(to_pci_dev(dev)); return device_for_each_child(dev, &off, pm_iter); } #endif /* PM */ diff --git a/drivers/pinctrl/mediatek/mtk-eint.c b/drivers/pinctrl/mediatek/mtk-eint.c index f464f8cd274b..7e526bcf5e0b 100644 --- a/drivers/pinctrl/mediatek/mtk-eint.c +++ b/drivers/pinctrl/mediatek/mtk-eint.c @@ -113,6 +113,8 @@ static void mtk_eint_mask(struct irq_data *d) void __iomem *reg = mtk_eint_get_offset(eint, d->hwirq, eint->regs->mask_set); + eint->cur_mask[d->hwirq >> 5] &= ~mask; + writel(mask, reg); } @@ -123,6 +125,8 @@ static void mtk_eint_unmask(struct irq_data *d) void __iomem *reg = mtk_eint_get_offset(eint, d->hwirq, eint->regs->mask_clr); + eint->cur_mask[d->hwirq >> 5] |= mask; + writel(mask, reg); if (eint->dual_edge[d->hwirq]) @@ -217,19 +221,6 @@ static void mtk_eint_chip_write_mask(const struct mtk_eint *eint, } } -static void mtk_eint_chip_read_mask(const struct mtk_eint *eint, - void __iomem *base, u32 *buf) -{ - int port; - void __iomem *reg; - - for (port = 0; port < eint->hw->ports; port++) { - reg = base + eint->regs->mask + (port << 2); - buf[port] = ~readl_relaxed(reg); - /* Mask is 0 when irq is enabled, and 1 when disabled. */ - } -} - static int mtk_eint_irq_request_resources(struct irq_data *d) { struct mtk_eint *eint = irq_data_get_irq_chip_data(d); @@ -318,7 +309,7 @@ static void mtk_eint_irq_handler(struct irq_desc *desc) struct irq_chip *chip = irq_desc_get_chip(desc); struct mtk_eint *eint = irq_desc_get_handler_data(desc); unsigned int status, eint_num; - int offset, index, virq; + int offset, mask_offset, index, virq; void __iomem *reg = mtk_eint_get_offset(eint, 0, eint->regs->stat); int dual_edge, start_level, curr_level; @@ -328,10 +319,24 @@ static void mtk_eint_irq_handler(struct irq_desc *desc) status = readl(reg); while (status) { offset = __ffs(status); + mask_offset = eint_num >> 5; index = eint_num + offset; virq = irq_find_mapping(eint->domain, index); status &= ~BIT(offset); + /* + * If we get an interrupt on pin that was only required + * for wake (but no real interrupt requested), mask the + * interrupt (as would mtk_eint_resume do anyway later + * in the resume sequence). + */ + if (eint->wake_mask[mask_offset] & BIT(offset) && + !(eint->cur_mask[mask_offset] & BIT(offset))) { + writel_relaxed(BIT(offset), reg - + eint->regs->stat + + eint->regs->mask_set); + } + dual_edge = eint->dual_edge[index]; if (dual_edge) { /* @@ -370,7 +375,6 @@ static void mtk_eint_irq_handler(struct irq_desc *desc) int mtk_eint_do_suspend(struct mtk_eint *eint) { - mtk_eint_chip_read_mask(eint, eint->base, eint->cur_mask); mtk_eint_chip_write_mask(eint, eint->base, eint->wake_mask); return 0; diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c index 568ca96cdb6d..3a235487e38d 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08.c +++ b/drivers/pinctrl/pinctrl-mcp23s08.c @@ -771,6 +771,10 @@ static int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev, if (ret < 0) goto fail; + ret = devm_gpiochip_add_data(dev, &mcp->chip, mcp); + if (ret < 0) + goto fail; + mcp->irq_controller = device_property_read_bool(dev, "interrupt-controller"); if (mcp->irq && mcp->irq_controller) { @@ -812,10 +816,6 @@ static int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev, goto fail; } - ret = devm_gpiochip_add_data(dev, &mcp->chip, mcp); - if (ret < 0) - goto fail; - if (one_regmap_config) { mcp->pinctrl_desc.name = devm_kasprintf(dev, GFP_KERNEL, "mcp23xxx-pinctrl.%d", raw_chip_address); diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c index 3b4ca52d2456..fb76fb2e9ea5 100644 --- a/drivers/pinctrl/pinctrl-ocelot.c +++ b/drivers/pinctrl/pinctrl-ocelot.c @@ -396,7 +396,7 @@ static int ocelot_pin_function_idx(struct ocelot_pinctrl *info, return -1; } -#define REG(r, info, p) ((r) * (info)->stride + (4 * ((p) / 32))) +#define REG_ALT(msb, info, p) (OCELOT_GPIO_ALT0 * (info)->stride + 4 * ((msb) + ((info)->stride * ((p) / 32)))) static int ocelot_pinmux_set_mux(struct pinctrl_dev *pctldev, unsigned int selector, unsigned int group) @@ -412,19 +412,21 @@ static int ocelot_pinmux_set_mux(struct pinctrl_dev *pctldev, /* * f is encoded on two bits. - * bit 0 of f goes in BIT(pin) of ALT0, bit 1 of f goes in BIT(pin) of - * ALT1 + * bit 0 of f goes in BIT(pin) of ALT[0], bit 1 of f goes in BIT(pin) of + * ALT[1] * This is racy because both registers can't be updated at the same time * but it doesn't matter much for now. */ - regmap_update_bits(info->map, REG(OCELOT_GPIO_ALT0, info, pin->pin), + regmap_update_bits(info->map, REG_ALT(0, info, pin->pin), BIT(p), f << p); - regmap_update_bits(info->map, REG(OCELOT_GPIO_ALT1, info, pin->pin), + regmap_update_bits(info->map, REG_ALT(1, info, pin->pin), BIT(p), f << (p - 1)); return 0; } +#define REG(r, info, p) ((r) * (info)->stride + (4 * ((p) / 32))) + static int ocelot_gpio_set_direction(struct pinctrl_dev *pctldev, struct pinctrl_gpio_range *range, unsigned int pin, bool input) @@ -432,7 +434,7 @@ static int ocelot_gpio_set_direction(struct pinctrl_dev *pctldev, struct ocelot_pinctrl *info = pinctrl_dev_get_drvdata(pctldev); unsigned int p = pin % 32; - regmap_update_bits(info->map, REG(OCELOT_GPIO_OE, info, p), BIT(p), + regmap_update_bits(info->map, REG(OCELOT_GPIO_OE, info, pin), BIT(p), input ? 0 : BIT(p)); return 0; @@ -445,9 +447,9 @@ static int ocelot_gpio_request_enable(struct pinctrl_dev *pctldev, struct ocelot_pinctrl *info = pinctrl_dev_get_drvdata(pctldev); unsigned int p = offset % 32; - regmap_update_bits(info->map, REG(OCELOT_GPIO_ALT0, info, offset), + regmap_update_bits(info->map, REG_ALT(0, info, offset), BIT(p), 0); - regmap_update_bits(info->map, REG(OCELOT_GPIO_ALT1, info, offset), + regmap_update_bits(info->map, REG_ALT(1, info, offset), BIT(p), 0); return 0; diff --git a/drivers/power/avs/smartreflex.c b/drivers/power/avs/smartreflex.c index c96c01e09740..4684e7df833a 100644 --- a/drivers/power/avs/smartreflex.c +++ b/drivers/power/avs/smartreflex.c @@ -899,38 +899,19 @@ static int omap_sr_probe(struct platform_device *pdev) } dev_info(&pdev->dev, "%s: SmartReflex driver initialized\n", __func__); - if (!sr_dbg_dir) { + if (!sr_dbg_dir) sr_dbg_dir = debugfs_create_dir("smartreflex", NULL); - if (IS_ERR_OR_NULL(sr_dbg_dir)) { - ret = PTR_ERR(sr_dbg_dir); - pr_err("%s:sr debugfs dir creation failed(%d)\n", - __func__, ret); - goto err_list_del; - } - } sr_info->dbg_dir = debugfs_create_dir(sr_info->name, sr_dbg_dir); - if (IS_ERR_OR_NULL(sr_info->dbg_dir)) { - dev_err(&pdev->dev, "%s: Unable to create debugfs directory\n", - __func__); - ret = PTR_ERR(sr_info->dbg_dir); - goto err_debugfs; - } - (void) debugfs_create_file("autocomp", S_IRUGO | S_IWUSR, - sr_info->dbg_dir, (void *)sr_info, &pm_sr_fops); - (void) debugfs_create_x32("errweight", S_IRUGO, sr_info->dbg_dir, - &sr_info->err_weight); - (void) debugfs_create_x32("errmaxlimit", S_IRUGO, sr_info->dbg_dir, - &sr_info->err_maxlimit); + debugfs_create_file("autocomp", S_IRUGO | S_IWUSR, sr_info->dbg_dir, + (void *)sr_info, &pm_sr_fops); + debugfs_create_x32("errweight", S_IRUGO, sr_info->dbg_dir, + &sr_info->err_weight); + debugfs_create_x32("errmaxlimit", S_IRUGO, sr_info->dbg_dir, + &sr_info->err_maxlimit); nvalue_dir = debugfs_create_dir("nvalue", sr_info->dbg_dir); - if (IS_ERR_OR_NULL(nvalue_dir)) { - dev_err(&pdev->dev, "%s: Unable to create debugfs directory for n-values\n", - __func__); - ret = PTR_ERR(nvalue_dir); - goto err_debugfs; - } if (sr_info->nvalue_count == 0 || !sr_info->nvalue_table) { dev_warn(&pdev->dev, "%s: %s: No Voltage table for the corresponding vdd. Cannot create debugfs entries for n-values\n", @@ -945,12 +926,12 @@ static int omap_sr_probe(struct platform_device *pdev) snprintf(name, sizeof(name), "volt_%lu", sr_info->nvalue_table[i].volt_nominal); - (void) debugfs_create_x32(name, S_IRUGO | S_IWUSR, nvalue_dir, - &(sr_info->nvalue_table[i].nvalue)); + debugfs_create_x32(name, S_IRUGO | S_IWUSR, nvalue_dir, + &(sr_info->nvalue_table[i].nvalue)); snprintf(name, sizeof(name), "errminlimit_%lu", sr_info->nvalue_table[i].volt_nominal); - (void) debugfs_create_x32(name, S_IRUGO | S_IWUSR, nvalue_dir, - &(sr_info->nvalue_table[i].errminlimit)); + debugfs_create_x32(name, S_IRUGO | S_IWUSR, nvalue_dir, + &(sr_info->nvalue_table[i].errminlimit)); } diff --git a/drivers/scsi/vmw_pvscsi.c b/drivers/scsi/vmw_pvscsi.c index ecee4b3ff073..377b07b2feeb 100644 --- a/drivers/scsi/vmw_pvscsi.c +++ b/drivers/scsi/vmw_pvscsi.c @@ -763,6 +763,7 @@ static int pvscsi_queue_lck(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd struct pvscsi_adapter *adapter = shost_priv(host); struct pvscsi_ctx *ctx; unsigned long flags; + unsigned char op; spin_lock_irqsave(&adapter->hw_lock, flags); @@ -775,13 +776,14 @@ static int pvscsi_queue_lck(struct scsi_cmnd *cmd, void (*done)(struct scsi_cmnd } cmd->scsi_done = done; + op = cmd->cmnd[0]; dev_dbg(&cmd->device->sdev_gendev, - "queued cmd %p, ctx %p, op=%x\n", cmd, ctx, cmd->cmnd[0]); + "queued cmd %p, ctx %p, op=%x\n", cmd, ctx, op); spin_unlock_irqrestore(&adapter->hw_lock, flags); - pvscsi_kick_io(adapter, cmd->cmnd[0]); + pvscsi_kick_io(adapter, op); return 0; } diff --git a/fs/afs/callback.c b/fs/afs/callback.c index d441bef72163..915010464572 100644 --- a/fs/afs/callback.c +++ b/fs/afs/callback.c @@ -275,9 +275,9 @@ static void afs_break_one_callback(struct afs_server *server, struct afs_super_info *as = AFS_FS_S(cbi->sb); struct afs_volume *volume = as->volume; - write_lock(&volume->cb_break_lock); + write_lock(&volume->cb_v_break_lock); volume->cb_v_break++; - write_unlock(&volume->cb_break_lock); + write_unlock(&volume->cb_v_break_lock); } else { data.volume = NULL; data.fid = *fid; diff --git a/fs/afs/inode.c b/fs/afs/inode.c index b42d9d09669c..18a50d4febcf 100644 --- a/fs/afs/inode.c +++ b/fs/afs/inode.c @@ -56,6 +56,16 @@ static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *paren } /* + * Set the file size and block count. Estimate the number of 512 bytes blocks + * used, rounded up to nearest 1K for consistency with other AFS clients. + */ +static void afs_set_i_size(struct afs_vnode *vnode, u64 size) +{ + i_size_write(&vnode->vfs_inode, size); + vnode->vfs_inode.i_blocks = ((size + 1023) >> 10) << 1; +} + +/* * Initialise an inode from the vnode status. */ static int afs_inode_init_from_status(struct afs_vnode *vnode, struct key *key, @@ -124,12 +134,7 @@ static int afs_inode_init_from_status(struct afs_vnode *vnode, struct key *key, return afs_protocol_error(NULL, -EBADMSG, afs_eproto_file_type); } - /* - * Estimate 512 bytes blocks used, rounded up to nearest 1K - * for consistency with other AFS clients. - */ - inode->i_blocks = ((i_size_read(inode) + 1023) >> 10) << 1; - i_size_write(&vnode->vfs_inode, status->size); + afs_set_i_size(vnode, status->size); vnode->invalid_before = status->data_version; inode_set_iversion_raw(&vnode->vfs_inode, status->data_version); @@ -207,11 +212,13 @@ static void afs_apply_status(struct afs_fs_cursor *fc, if (expected_version && *expected_version != status->data_version) { - kdebug("vnode modified %llx on {%llx:%llu} [exp %llx] %s", - (unsigned long long) status->data_version, - vnode->fid.vid, vnode->fid.vnode, - (unsigned long long) *expected_version, - fc->type ? fc->type->name : "???"); + if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) + pr_warn("kAFS: vnode modified {%llx:%llu} %llx->%llx %s\n", + vnode->fid.vid, vnode->fid.vnode, + (unsigned long long)*expected_version, + (unsigned long long)status->data_version, + fc->type ? fc->type->name : "???"); + vnode->invalid_before = status->data_version; if (vnode->status.type == AFS_FTYPE_DIR) { if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags)) @@ -230,7 +237,7 @@ static void afs_apply_status(struct afs_fs_cursor *fc, if (data_changed) { inode_set_iversion_raw(&vnode->vfs_inode, status->data_version); - i_size_write(&vnode->vfs_inode, status->size); + afs_set_i_size(vnode, status->size); } } diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 8a67bf741880..7ee63526c6a2 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -109,10 +109,8 @@ struct afs_call { struct rxrpc_call *rxcall; /* RxRPC call handle */ struct key *key; /* security for this call */ struct afs_net *net; /* The network namespace */ - union { - struct afs_server *server; - struct afs_vlserver *vlserver; - }; + struct afs_server *server; /* The fileserver record if fs op (pins ref) */ + struct afs_vlserver *vlserver; /* The vlserver record if vl op */ struct afs_cb_interest *cbi; /* Callback interest for server used */ struct afs_vnode *lvnode; /* vnode being locked */ void *request; /* request data (first part) */ @@ -616,7 +614,7 @@ struct afs_volume { unsigned int servers_seq; /* Incremented each time ->servers changes */ unsigned cb_v_break; /* Break-everything counter. */ - rwlock_t cb_break_lock; + rwlock_t cb_v_break_lock; afs_voltype_t type; /* type of volume */ short error; diff --git a/fs/afs/volume.c b/fs/afs/volume.c index 08fdb3951c49..1a414300b654 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -43,6 +43,7 @@ static struct afs_volume *afs_alloc_volume(struct afs_fs_context *params, atomic_set(&volume->usage, 1); INIT_LIST_HEAD(&volume->proc_link); rwlock_init(&volume->servers_lock); + rwlock_init(&volume->cb_v_break_lock); memcpy(volume->name, vldb->name, vldb->name_len + 1); slist = afs_alloc_server_list(params->cell, params->key, vldb, type_mask); @@ -2095,6 +2095,7 @@ SYSCALL_DEFINE6(io_pgetevents, struct __aio_sigset ksig = { NULL, }; sigset_t ksigmask, sigsaved; struct timespec64 ts; + bool interrupted; int ret; if (timeout && unlikely(get_timespec64(&ts, timeout))) @@ -2108,8 +2109,10 @@ SYSCALL_DEFINE6(io_pgetevents, return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL); - restore_user_sigmask(ksig.sigmask, &sigsaved); - if (signal_pending(current) && !ret) + + interrupted = signal_pending(current); + restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted); + if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; @@ -2128,6 +2131,7 @@ SYSCALL_DEFINE6(io_pgetevents_time32, struct __aio_sigset ksig = { NULL, }; sigset_t ksigmask, sigsaved; struct timespec64 ts; + bool interrupted; int ret; if (timeout && unlikely(get_old_timespec32(&ts, timeout))) @@ -2142,8 +2146,10 @@ SYSCALL_DEFINE6(io_pgetevents_time32, return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL); - restore_user_sigmask(ksig.sigmask, &sigsaved); - if (signal_pending(current) && !ret) + + interrupted = signal_pending(current); + restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted); + if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; @@ -2193,6 +2199,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents, struct __compat_aio_sigset ksig = { NULL, }; sigset_t ksigmask, sigsaved; struct timespec64 t; + bool interrupted; int ret; if (timeout && get_old_timespec32(&t, timeout)) @@ -2206,8 +2213,10 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents, return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL); - restore_user_sigmask(ksig.sigmask, &sigsaved); - if (signal_pending(current) && !ret) + + interrupted = signal_pending(current); + restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted); + if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; @@ -2226,6 +2235,7 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64, struct __compat_aio_sigset ksig = { NULL, }; sigset_t ksigmask, sigsaved; struct timespec64 t; + bool interrupted; int ret; if (timeout && get_timespec64(&t, timeout)) @@ -2239,8 +2249,10 @@ COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64, return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL); - restore_user_sigmask(ksig.sigmask, &sigsaved); - if (signal_pending(current) && !ret) + + interrupted = signal_pending(current); + restore_user_sigmask(ksig.sigmask, &sigsaved, interrupted); + if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 82a48e830018..e4b59e76afb0 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -856,9 +856,14 @@ err: static int load_flat_shared_library(int id, struct lib_info *libs) { + /* + * This is a fake bprm struct; only the members "buf", "file" and + * "filename" are actually used. + */ struct linux_binprm bprm; int res; char buf[16]; + loff_t pos = 0; memset(&bprm, 0, sizeof(bprm)); @@ -872,25 +877,11 @@ static int load_flat_shared_library(int id, struct lib_info *libs) if (IS_ERR(bprm.file)) return res; - bprm.cred = prepare_exec_creds(); - res = -ENOMEM; - if (!bprm.cred) - goto out; - - /* We don't really care about recalculating credentials at this point - * as we're past the point of no return and are dealing with shared - * libraries. - */ - bprm.called_set_creds = 1; + res = kernel_read(bprm.file, bprm.buf, BINPRM_BUF_SIZE, &pos); - res = prepare_binprm(&bprm); - - if (!res) + if (res >= 0) res = load_flat_file(&bprm, libs, id, NULL); - abort_creds(bprm.cred); - -out: allow_write_access(bprm.file); fput(bprm.file); diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 6af2d0d4a87a..c8a9b89b922d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2121,9 +2121,10 @@ retry: if (inode && ceph_snap(inode) == CEPH_SNAPDIR) { dout("build_path path+%d: %p SNAPDIR\n", pos, temp); - } else if (stop_on_nosnap && inode && + } else if (stop_on_nosnap && inode && dentry != temp && ceph_snap(inode) == CEPH_NOSNAP) { spin_unlock(&temp->d_lock); + pos++; /* get rid of any prepended '/' */ break; } else { pos -= temp->d_name.len; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index c6f513100cc9..4c74c768ae43 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -2325,7 +2325,7 @@ SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, error = do_epoll_wait(epfd, events, maxevents, timeout); - restore_user_sigmask(sigmask, &sigsaved); + restore_user_sigmask(sigmask, &sigsaved, error == -EINTR); return error; } @@ -2350,7 +2350,7 @@ COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, err = do_epoll_wait(epfd, events, maxevents, timeout); - restore_user_sigmask(sigmask, &sigsaved); + restore_user_sigmask(sigmask, &sigsaved, err == -EINTR); return err; } diff --git a/fs/inode.c b/fs/inode.c index df6542ec3b88..2bf21e2c90fc 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -362,7 +362,7 @@ EXPORT_SYMBOL(inc_nlink); static void __address_space_init_once(struct address_space *mapping) { - xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ); + xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT); init_rwsem(&mapping->i_mmap_rwsem); INIT_LIST_HEAD(&mapping->private_list); spin_lock_init(&mapping->private_lock); diff --git a/fs/io_uring.c b/fs/io_uring.c index 86a2bd721900..4ef62a45045d 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -579,6 +579,7 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx, state->cur_req++; } + req->file = NULL; req->ctx = ctx; req->flags = 0; /* one is dropped after submission, the other at completion */ @@ -1801,10 +1802,8 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s, req->sequence = ctx->cached_sq_head - 1; } - if (!io_op_needs_file(s->sqe)) { - req->file = NULL; + if (!io_op_needs_file(s->sqe)) return 0; - } if (flags & IOSQE_FIXED_FILE) { if (unlikely(!ctx->user_files || @@ -2201,11 +2200,12 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events, } ret = wait_event_interruptible(ctx->wait, io_cqring_events(ring) >= min_events); - if (ret == -ERESTARTSYS) - ret = -EINTR; if (sig) - restore_user_sigmask(sig, &sigsaved); + restore_user_sigmask(sig, &sigsaved, ret == -ERESTARTSYS); + + if (ret == -ERESTARTSYS) + ret = -EINTR; return READ_ONCE(ring->r.head) == READ_ONCE(ring->r.tail) ? ret : 0; } diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index a809989807d6..19f856f45689 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -18,7 +18,7 @@ #define NFSDBG_FACILITY NFSDBG_PNFS_LD -static unsigned int dataserver_timeo = NFS_DEF_TCP_RETRANS; +static unsigned int dataserver_timeo = NFS_DEF_TCP_TIMEO; static unsigned int dataserver_retrans; static bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg); diff --git a/fs/proc/array.c b/fs/proc/array.c index 2edbb657f859..55180501b915 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -462,7 +462,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, * a program is not able to use ptrace(2) in that case. It is * safe because the task has stopped executing permanently. */ - if (permitted && (task->flags & PF_DUMPCORE)) { + if (permitted && (task->flags & (PF_EXITING|PF_DUMPCORE))) { if (try_get_task_stack(task)) { eip = KSTK_EIP(task); esp = KSTK_ESP(task); diff --git a/fs/proc/base.c b/fs/proc/base.c index 9c8ca6cd3ce4..255f6754c70d 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -3077,8 +3077,7 @@ static const struct file_operations proc_tgid_base_operations = { struct pid *tgid_pidfd_to_pid(const struct file *file) { - if (!d_is_dir(file->f_path.dentry) || - (file->f_op != &proc_tgid_base_operations)) + if (file->f_op != &proc_tgid_base_operations) return ERR_PTR(-EBADF); return proc_pid(file_inode(file)); diff --git a/fs/select.c b/fs/select.c index 6cbc9ff56ba0..a4d8f6e8b63c 100644 --- a/fs/select.c +++ b/fs/select.c @@ -758,10 +758,9 @@ static long do_pselect(int n, fd_set __user *inp, fd_set __user *outp, return ret; ret = core_sys_select(n, inp, outp, exp, to); + restore_user_sigmask(sigmask, &sigsaved, ret == -ERESTARTNOHAND); ret = poll_select_copy_remaining(&end_time, tsp, type, ret); - restore_user_sigmask(sigmask, &sigsaved); - return ret; } @@ -1106,8 +1105,7 @@ SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds, ret = do_sys_poll(ufds, nfds, to); - restore_user_sigmask(sigmask, &sigsaved); - + restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR); /* We can restart this syscall, usually */ if (ret == -EINTR) ret = -ERESTARTNOHAND; @@ -1142,8 +1140,7 @@ SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, unsigned int, nfds, ret = do_sys_poll(ufds, nfds, to); - restore_user_sigmask(sigmask, &sigsaved); - + restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR); /* We can restart this syscall, usually */ if (ret == -EINTR) ret = -ERESTARTNOHAND; @@ -1350,10 +1347,9 @@ static long do_compat_pselect(int n, compat_ulong_t __user *inp, return ret; ret = compat_core_sys_select(n, inp, outp, exp, to); + restore_user_sigmask(sigmask, &sigsaved, ret == -ERESTARTNOHAND); ret = poll_select_copy_remaining(&end_time, tsp, type, ret); - restore_user_sigmask(sigmask, &sigsaved); - return ret; } @@ -1425,8 +1421,7 @@ COMPAT_SYSCALL_DEFINE5(ppoll_time32, struct pollfd __user *, ufds, ret = do_sys_poll(ufds, nfds, to); - restore_user_sigmask(sigmask, &sigsaved); - + restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR); /* We can restart this syscall, usually */ if (ret == -EINTR) ret = -ERESTARTNOHAND; @@ -1461,8 +1456,7 @@ COMPAT_SYSCALL_DEFINE5(ppoll_time64, struct pollfd __user *, ufds, ret = do_sys_poll(ufds, nfds, to); - restore_user_sigmask(sigmask, &sigsaved); - + restore_user_sigmask(sigmask, &sigsaved, ret == -EINTR); /* We can restart this syscall, usually */ if (ret == -EINTR) ret = -ERESTARTNOHAND; diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 31b6c87d6240..175f7b40c585 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -506,13 +506,16 @@ int acpi_bus_get_status(struct acpi_device *device); int acpi_bus_set_power(acpi_handle handle, int state); const char *acpi_power_state_string(int state); -int acpi_device_get_power(struct acpi_device *device, int *state); int acpi_device_set_power(struct acpi_device *device, int state); int acpi_bus_init_power(struct acpi_device *device); int acpi_device_fix_up_power(struct acpi_device *device); int acpi_bus_update_power(acpi_handle handle, int *state_p); int acpi_device_update_power(struct acpi_device *device, int *state_p); bool acpi_bus_power_manageable(acpi_handle handle); +int acpi_device_power_add_dependent(struct acpi_device *adev, + struct device *dev); +void acpi_device_power_remove_dependent(struct acpi_device *adev, + struct device *dev); #ifdef CONFIG_PM bool acpi_bus_can_wakeup(acpi_handle handle); @@ -651,6 +654,12 @@ static inline int acpi_pm_set_bridge_wakeup(struct device *dev, bool enable) } #endif +#ifdef CONFIG_ACPI_SYSTEM_POWER_STATES_SUPPORT +bool acpi_sleep_state_supported(u8 sleep_state); +#else +static inline bool acpi_sleep_state_supported(u8 sleep_state) { return false; } +#endif + #ifdef CONFIG_ACPI_SLEEP u32 acpi_target_system_state(void); #else diff --git a/include/dt-bindings/clock/g12a-clkc.h b/include/dt-bindings/clock/g12a-clkc.h index 82c9e0c020b2..e10470ed7c4f 100644 --- a/include/dt-bindings/clock/g12a-clkc.h +++ b/include/dt-bindings/clock/g12a-clkc.h @@ -130,7 +130,7 @@ #define CLKID_MALI_1_SEL 172 #define CLKID_MALI_1 174 #define CLKID_MALI 175 -#define CLKID_MPLL_5OM 177 +#define CLKID_MPLL_50M 177 #define CLKID_CPU_CLK 187 #define CLKID_PCIE_PLL 201 #define CLKID_VDEC_1 204 diff --git a/include/dt-bindings/clock/sifive-fu540-prci.h b/include/dt-bindings/clock/sifive-fu540-prci.h index 6a0b70a37d78..3b21d0522c91 100644 --- a/include/dt-bindings/clock/sifive-fu540-prci.h +++ b/include/dt-bindings/clock/sifive-fu540-prci.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: GPL-2.0 */ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ /* * Copyright (C) 2018-2019 SiFive, Inc. * Wesley Terpstra diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d315d86844e4..cbbe45e408d9 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -913,31 +913,21 @@ static inline int acpi_dev_pm_attach(struct device *dev, bool power_on) #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM_SLEEP) -int acpi_dev_suspend_late(struct device *dev); int acpi_subsys_prepare(struct device *dev); void acpi_subsys_complete(struct device *dev); int acpi_subsys_suspend_late(struct device *dev); int acpi_subsys_suspend_noirq(struct device *dev); -int acpi_subsys_resume_noirq(struct device *dev); -int acpi_subsys_resume_early(struct device *dev); int acpi_subsys_suspend(struct device *dev); int acpi_subsys_freeze(struct device *dev); -int acpi_subsys_freeze_late(struct device *dev); -int acpi_subsys_freeze_noirq(struct device *dev); -int acpi_subsys_thaw_noirq(struct device *dev); +int acpi_subsys_poweroff(struct device *dev); #else -static inline int acpi_dev_resume_early(struct device *dev) { return 0; } static inline int acpi_subsys_prepare(struct device *dev) { return 0; } static inline void acpi_subsys_complete(struct device *dev) {} static inline int acpi_subsys_suspend_late(struct device *dev) { return 0; } static inline int acpi_subsys_suspend_noirq(struct device *dev) { return 0; } -static inline int acpi_subsys_resume_noirq(struct device *dev) { return 0; } -static inline int acpi_subsys_resume_early(struct device *dev) { return 0; } static inline int acpi_subsys_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_freeze(struct device *dev) { return 0; } -static inline int acpi_subsys_freeze_late(struct device *dev) { return 0; } -static inline int acpi_subsys_freeze_noirq(struct device *dev) { return 0; } -static inline int acpi_subsys_thaw_noirq(struct device *dev) { return 0; } +static inline int acpi_subsys_poweroff(struct device *dev) { return 0; } #endif #ifdef CONFIG_ACPI diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h index 16255c2ca2f4..0d6b4bc191c5 100644 --- a/include/linux/intel-ish-client-if.h +++ b/include/linux/intel-ish-client-if.h @@ -103,6 +103,7 @@ void ishtp_put_device(struct ishtp_cl_device *cl_dev); void ishtp_get_device(struct ishtp_cl_device *cl_dev); void ishtp_set_drvdata(struct ishtp_cl_device *cl_device, void *data); void *ishtp_get_drvdata(struct ishtp_cl_device *cl_device); +struct ishtp_cl_device *ishtp_dev_to_cl_device(struct device *dev); int ishtp_register_event_cb(struct ishtp_cl_device *device, void (*read_cb)(struct ishtp_cl_device *)); struct ishtp_fw_client *ishtp_fw_cl_get_client(struct ishtp_device *dev, diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 74b1ee9027f5..0c9bc231107f 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -93,7 +93,8 @@ #define DIV_ROUND_DOWN_ULL(ll, d) \ ({ unsigned long long _tmp = (ll); do_div(_tmp, d); _tmp; }) -#define DIV_ROUND_UP_ULL(ll, d) DIV_ROUND_DOWN_ULL((ll) + (d) - 1, (d)) +#define DIV_ROUND_UP_ULL(ll, d) \ + DIV_ROUND_DOWN_ULL((unsigned long long)(ll) + (d) - 1, (d)) #if BITS_PER_LONG == 32 # define DIV_ROUND_UP_SECTOR_T(ll,d) DIV_ROUND_UP_ULL(ll, d) diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h index b3d360b0ee3d..9f57cdfcc93d 100644 --- a/include/linux/mtd/spi-nor.h +++ b/include/linux/mtd/spi-nor.h @@ -373,6 +373,8 @@ struct flash_info; * @flash_unlock: [FLASH-SPECIFIC] unlock a region of the SPI NOR * @flash_is_locked: [FLASH-SPECIFIC] check if a region of the SPI NOR is * @quad_enable: [FLASH-SPECIFIC] enables SPI NOR quad mode + * @clear_sr_bp: [FLASH-SPECIFIC] clears the Block Protection Bits from + * the SPI NOR Status Register. * completely locked * @priv: the private data */ @@ -410,6 +412,7 @@ struct spi_nor { int (*flash_unlock)(struct spi_nor *nor, loff_t ofs, uint64_t len); int (*flash_is_locked)(struct spi_nor *nor, loff_t ofs, uint64_t len); int (*quad_enable)(struct spi_nor *nor); + int (*clear_sr_bp)(struct spi_nor *nor); void *priv; }; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 0ab99c7b652d..2bca72f3028b 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -241,6 +241,7 @@ struct perf_event; #define PERF_PMU_CAP_NO_INTERRUPT 0x01 #define PERF_PMU_CAP_NO_NMI 0x02 #define PERF_PMU_CAP_AUX_NO_SG 0x04 +#define PERF_PMU_CAP_EXTENDED_REGS 0x08 #define PERF_PMU_CAP_EXCLUSIVE 0x10 #define PERF_PMU_CAP_ITRACE 0x20 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x40 diff --git a/include/linux/perf_regs.h b/include/linux/perf_regs.h index 476747456bca..2d12e97d5e7b 100644 --- a/include/linux/perf_regs.h +++ b/include/linux/perf_regs.h @@ -11,6 +11,11 @@ struct perf_regs { #ifdef CONFIG_HAVE_PERF_REGS #include <asm/perf_regs.h> + +#ifndef PERF_REG_EXTENDED_MASK +#define PERF_REG_EXTENDED_MASK 0 +#endif + u64 perf_reg_value(struct pt_regs *regs, int idx); int perf_reg_validate(u64 mask); u64 perf_reg_abi(struct task_struct *task); @@ -18,6 +23,9 @@ void perf_get_regs_user(struct perf_regs *regs_user, struct pt_regs *regs, struct pt_regs *regs_user_copy); #else + +#define PERF_REG_EXTENDED_MASK 0 + static inline u64 perf_reg_value(struct pt_regs *regs, int idx) { return 0; diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h index 7bb77850c65a..3c202a11a79e 100644 --- a/include/linux/pfn_t.h +++ b/include/linux/pfn_t.h @@ -68,7 +68,7 @@ static inline phys_addr_t pfn_t_to_phys(pfn_t pfn) static inline void *pfn_t_to_virt(pfn_t pfn) { - if (pfn_t_has_page(pfn)) + if (pfn_t_has_page(pfn) && !is_device_private_page(pfn_t_to_page(pfn))) return __va(pfn_t_to_phys(pfn)); return NULL; } diff --git a/include/linux/pm.h b/include/linux/pm.h index 345d74a727e3..283fb3defe56 100644 --- a/include/linux/pm.h +++ b/include/linux/pm.h @@ -760,7 +760,6 @@ extern int pm_generic_poweroff_late(struct device *dev); extern int pm_generic_poweroff(struct device *dev); extern void pm_generic_complete(struct device *dev); -extern void dev_pm_skip_next_resume_phases(struct device *dev); extern bool dev_pm_may_skip_resume(struct device *dev); extern bool dev_pm_smart_suspend_and_suspended(struct device *dev); diff --git a/include/linux/pm_wakeup.h b/include/linux/pm_wakeup.h index ce57771fab9b..91027602d137 100644 --- a/include/linux/pm_wakeup.h +++ b/include/linux/pm_wakeup.h @@ -36,7 +36,7 @@ struct wake_irq; * @expire_count: Number of times the wakeup source's timeout has expired. * @wakeup_count: Number of times the wakeup source might abort suspend. * @active: Status of the wakeup source. - * @has_timeout: The wakeup source has been activated with a timeout. + * @autosleep_enabled: Autosleep is active, so update @prevent_sleep_time. */ struct wakeup_source { const char *name; diff --git a/include/linux/signal.h b/include/linux/signal.h index 9702016734b1..78c2bb376954 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -276,7 +276,7 @@ extern int sigprocmask(int, sigset_t *, sigset_t *); extern int set_user_sigmask(const sigset_t __user *usigmask, sigset_t *set, sigset_t *oldset, size_t sigsetsize); extern void restore_user_sigmask(const void __user *usigmask, - sigset_t *sigsaved); + sigset_t *sigsaved, bool interrupted); extern void set_current_blocked(sigset_t *); extern void __set_current_blocked(const sigset_t *); extern int show_unhandled_signals; diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 8594001e8be8..9c0ad1a3a727 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -209,8 +209,9 @@ extern int suspend_valid_only_mem(suspend_state_t state); extern unsigned int pm_suspend_global_flags; -#define PM_SUSPEND_FLAG_FW_SUSPEND (1 << 0) -#define PM_SUSPEND_FLAG_FW_RESUME (1 << 1) +#define PM_SUSPEND_FLAG_FW_SUSPEND BIT(0) +#define PM_SUSPEND_FLAG_FW_RESUME BIT(1) +#define PM_SUSPEND_FLAG_NO_PLATFORM BIT(2) static inline void pm_suspend_clear_flags(void) { @@ -227,6 +228,11 @@ static inline void pm_set_resume_via_firmware(void) pm_suspend_global_flags |= PM_SUSPEND_FLAG_FW_RESUME; } +static inline void pm_set_suspend_no_platform(void) +{ + pm_suspend_global_flags |= PM_SUSPEND_FLAG_NO_PLATFORM; +} + /** * pm_suspend_via_firmware - Check if platform firmware will suspend the system. * @@ -268,6 +274,22 @@ static inline bool pm_resume_via_firmware(void) return !!(pm_suspend_global_flags & PM_SUSPEND_FLAG_FW_RESUME); } +/** + * pm_suspend_no_platform - Check if platform may change device power states. + * + * To be called during system-wide power management transitions to sleep states + * or during the subsequent system-wide transitions back to the working state. + * + * Return 'true' if the power states of devices remain under full control of the + * kernel throughout the system-wide suspend and resume cycle in progress (that + * is, if a device is put into a certain power state during suspend, it can be + * expected to remain in that state during resume). + */ +static inline bool pm_suspend_no_platform(void) +{ + return !!(pm_suspend_global_flags & PM_SUSPEND_FLAG_NO_PLATFORM); +} + /* Suspend-to-idle state machnine. */ enum s2idle_states { S2IDLE_STATE_NONE, /* Not suspended/suspending. */ @@ -282,7 +304,7 @@ static inline bool idle_should_enter_s2idle(void) return unlikely(s2idle_state == S2IDLE_STATE_ENTER); } -extern bool pm_suspend_via_s2idle(void); +extern bool pm_suspend_default_s2idle(void); extern void __init pm_states_init(void); extern void s2idle_set_ops(const struct platform_s2idle_ops *ops); extern void s2idle_wake(void); @@ -314,7 +336,7 @@ static inline void pm_set_suspend_via_firmware(void) {} static inline void pm_set_resume_via_firmware(void) {} static inline bool pm_suspend_via_firmware(void) { return false; } static inline bool pm_resume_via_firmware(void) { return false; } -static inline bool pm_suspend_via_s2idle(void) { return false; } +static inline bool pm_suspend_default_s2idle(void) { return false; } static inline void suspend_set_ops(const struct platform_suspend_ops *ops) {} static inline int pm_suspend(suspend_state_t state) { return -ENOSYS; } @@ -426,6 +448,7 @@ extern bool system_entering_hibernation(void); extern bool hibernation_available(void); asmlinkage int swsusp_save(void); extern struct pbe *restore_pblist; +int pfn_is_nosave(unsigned long pfn); #else /* CONFIG_HIBERNATION */ static inline void register_nosave_region(unsigned long b, unsigned long e) {} static inline void register_nosave_region_late(unsigned long b, unsigned long e) {} diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 0e01e6129145..5921599b6dc4 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -265,6 +265,7 @@ enum xa_lock_type { #define XA_FLAGS_TRACK_FREE ((__force gfp_t)4U) #define XA_FLAGS_ZERO_BUSY ((__force gfp_t)8U) #define XA_FLAGS_ALLOC_WRAPPED ((__force gfp_t)16U) +#define XA_FLAGS_ACCOUNT ((__force gfp_t)32U) #define XA_FLAGS_MARK(mark) ((__force gfp_t)((1U << __GFP_BITS_SHIFT) << \ (__force unsigned)(mark))) diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 4790beaa86e0..ee7405e759ba 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -262,8 +262,8 @@ static inline bool ip6_sk_ignore_df(const struct sock *sk) inet6_sk(sk)->pmtudisc == IPV6_PMTUDISC_OMIT; } -static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt, - struct in6_addr *daddr) +static inline const struct in6_addr *rt6_nexthop(const struct rt6_info *rt, + const struct in6_addr *daddr) { if (rt->rt6i_flags & RTF_GATEWAY) return &rt->rt6i_gateway; diff --git a/include/net/route.h b/include/net/route.h index 065b47754f05..55ff71ffb796 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -221,6 +221,7 @@ void ip_rt_get_source(u8 *src, struct sk_buff *skb, struct rtable *rt); struct rtable *rt_dst_alloc(struct net_device *dev, unsigned int flags, u16 type, bool nopolicy, bool noxfrm, bool will_cache); +struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt); struct in_ifaddr; void fib_add_ifaddr(struct in_ifaddr *); diff --git a/include/net/tls.h b/include/net/tls.h index 4a55ce6a303f..53d96bca220d 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -373,21 +373,6 @@ static inline bool tls_is_partially_sent_record(struct tls_context *ctx) return !!ctx->partially_sent_record; } -static inline int tls_complete_pending_work(struct sock *sk, - struct tls_context *ctx, - int flags, long *timeo) -{ - int rc = 0; - - if (unlikely(sk->sk_write_pending)) - rc = wait_on_pending_writer(sk, timeo); - - if (!rc && tls_is_partially_sent_record(ctx)) - rc = tls_push_partial_record(sk, ctx, flags); - - return rc; -} - static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx) { return tls_ctx->pending_open_record_frags; diff --git a/init/initramfs.c b/init/initramfs.c index 178130fd61c2..c47dad0884f7 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -617,7 +617,7 @@ static inline void clean_rootfs(void) #endif /* CONFIG_BLK_DEV_RAM */ #ifdef CONFIG_BLK_DEV_RAM -static void populate_initrd_image(char *err) +static void __init populate_initrd_image(char *err) { ssize_t written; int fd; @@ -637,7 +637,7 @@ static void populate_initrd_image(char *err) ksys_close(fd); } #else -static void populate_initrd_image(char *err) +static void __init populate_initrd_image(char *err) { printk(KERN_EMERG "Initramfs unpacking failed: %s\n", err); } diff --git a/kernel/cpu.c b/kernel/cpu.c index 077fde6fb953..ef1c565edc5d 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1964,6 +1964,9 @@ static ssize_t write_cpuhp_fail(struct device *dev, if (ret) return ret; + if (fail < CPUHP_OFFLINE || fail > CPUHP_ONLINE) + return -EINVAL; + /* * Cannot fail STARTING/DYING callbacks. */ @@ -2339,6 +2342,9 @@ static int __init mitigations_parse_cmdline(char *arg) cpu_mitigations = CPU_MITIGATIONS_AUTO; else if (!strcmp(arg, "auto,nosmt")) cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT; + else + pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n", + arg); return 0; } diff --git a/kernel/events/core.c b/kernel/events/core.c index abbd4b3b96c2..f85929ce13be 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5005,6 +5005,9 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg) if (perf_event_check_period(event, value)) return -EINVAL; + if (!event->attr.freq && (value & (1ULL << 63))) + return -EINVAL; + event_function_call(event, __perf_event_period, &value); return 0; @@ -5923,7 +5926,7 @@ static void perf_sample_regs_user(struct perf_regs *regs_user, if (user_mode(regs)) { regs_user->abi = perf_reg_abi(current); regs_user->regs = regs; - } else if (current->mm) { + } else if (!(current->flags & PF_KTHREAD)) { perf_get_regs_user(regs_user, regs, regs_user_copy); } else { regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE; @@ -10033,6 +10036,12 @@ void perf_pmu_unregister(struct pmu *pmu) } EXPORT_SYMBOL_GPL(perf_pmu_unregister); +static inline bool has_extended_regs(struct perf_event *event) +{ + return (event->attr.sample_regs_user & PERF_REG_EXTENDED_MASK) || + (event->attr.sample_regs_intr & PERF_REG_EXTENDED_MASK); +} + static int perf_try_init_event(struct pmu *pmu, struct perf_event *event) { struct perf_event_context *ctx = NULL; @@ -10064,12 +10073,16 @@ static int perf_try_init_event(struct pmu *pmu, struct perf_event *event) perf_event_ctx_unlock(event->group_leader, ctx); if (!ret) { + if (!(pmu->capabilities & PERF_PMU_CAP_EXTENDED_REGS) && + has_extended_regs(event)) + ret = -EOPNOTSUPP; + if (pmu->capabilities & PERF_PMU_CAP_NO_EXCLUDE && - event_has_any_exclude_flag(event)) { - if (event->destroy) - event->destroy(event); + event_has_any_exclude_flag(event)) ret = -EINVAL; - } + + if (ret && event->destroy) + event->destroy(event); } if (ret) diff --git a/kernel/fork.c b/kernel/fork.c index 75675b9bf6df..61667909ce83 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -248,7 +248,11 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); - return page ? page_address(page) : NULL; + if (likely(page)) { + tsk->stack = page_address(page); + return tsk->stack; + } + return NULL; #endif } @@ -1712,31 +1716,6 @@ const struct file_operations pidfd_fops = { #endif }; -/** - * pidfd_create() - Create a new pid file descriptor. - * - * @pid: struct pid that the pidfd will reference - * - * This creates a new pid file descriptor with the O_CLOEXEC flag set. - * - * Note, that this function can only be called after the fd table has - * been unshared to avoid leaking the pidfd to the new process. - * - * Return: On success, a cloexec pidfd is returned. - * On error, a negative errno number will be returned. - */ -static int pidfd_create(struct pid *pid) -{ - int fd; - - fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid), - O_RDWR | O_CLOEXEC); - if (fd < 0) - put_pid(pid); - - return fd; -} - static void __delayed_free_task(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); @@ -1774,6 +1753,7 @@ static __latent_entropy struct task_struct *copy_process( int pidfd = -1, retval; struct task_struct *p; struct multiprocess_signals delayed; + struct file *pidfile = NULL; /* * Don't allow sharing the root directory with processes in a different @@ -1822,8 +1802,6 @@ static __latent_entropy struct task_struct *copy_process( } if (clone_flags & CLONE_PIDFD) { - int reserved; - /* * - CLONE_PARENT_SETTID is useless for pidfds and also * parent_tidptr is used to return pidfds. @@ -1834,16 +1812,6 @@ static __latent_entropy struct task_struct *copy_process( if (clone_flags & (CLONE_DETACHED | CLONE_PARENT_SETTID | CLONE_THREAD)) return ERR_PTR(-EINVAL); - - /* - * Verify that parent_tidptr is sane so we can potentially - * reuse it later. - */ - if (get_user(reserved, parent_tidptr)) - return ERR_PTR(-EFAULT); - - if (reserved != 0) - return ERR_PTR(-EINVAL); } /* @@ -2058,11 +2026,20 @@ static __latent_entropy struct task_struct *copy_process( * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { - retval = pidfd_create(pid); + retval = get_unused_fd_flags(O_RDWR | O_CLOEXEC); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; + + pidfile = anon_inode_getfile("[pidfd]", &pidfd_fops, pid, + O_RDWR | O_CLOEXEC); + if (IS_ERR(pidfile)) { + put_unused_fd(pidfd); + goto bad_fork_free_pid; + } + get_pid(pid); /* held by pidfile now */ + retval = put_user(pidfd, parent_tidptr); if (retval) goto bad_fork_put_pidfd; @@ -2180,6 +2157,9 @@ static __latent_entropy struct task_struct *copy_process( goto bad_fork_cancel_cgroup; } + /* past the last point of failure */ + if (pidfile) + fd_install(pidfd, pidfile); init_task_pid_links(p); if (likely(p->pid)) { @@ -2246,8 +2226,10 @@ bad_fork_cancel_cgroup: bad_fork_cgroup_threadgroup_change_end: cgroup_threadgroup_change_end(current); bad_fork_put_pidfd: - if (clone_flags & CLONE_PIDFD) - ksys_close(pidfd); + if (clone_flags & CLONE_PIDFD) { + fput(pidfile); + put_unused_fd(pidfd); + } bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); diff --git a/kernel/power/power.h b/kernel/power/power.h index 9e58bdc8a562..44bee462ff57 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -75,8 +75,6 @@ static inline void hibernate_reserved_size_init(void) {} static inline void hibernate_image_size_init(void) {} #endif /* !CONFIG_HIBERNATION */ -extern int pfn_is_nosave(unsigned long); - #define power_attr(_name) \ static struct kobj_attribute _name##_attr = { \ .attr = { \ diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 9505101ed2bc..c874a7026e24 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -62,16 +62,16 @@ enum s2idle_states __read_mostly s2idle_state; static DEFINE_RAW_SPINLOCK(s2idle_lock); /** - * pm_suspend_via_s2idle - Check if suspend-to-idle is the default suspend. + * pm_suspend_default_s2idle - Check if suspend-to-idle is the default suspend. * * Return 'true' if suspend-to-idle has been selected as the default system * suspend method. */ -bool pm_suspend_via_s2idle(void) +bool pm_suspend_default_s2idle(void) { return mem_sleep_current == PM_SUSPEND_TO_IDLE; } -EXPORT_SYMBOL_GPL(pm_suspend_via_s2idle); +EXPORT_SYMBOL_GPL(pm_suspend_default_s2idle); void s2idle_set_ops(const struct platform_s2idle_ops *ops) { @@ -493,6 +493,9 @@ int suspend_devices_and_enter(suspend_state_t state) pm_suspend_target_state = state; + if (state == PM_SUSPEND_TO_IDLE) + pm_set_suspend_no_platform(); + error = platform_suspend_begin(state); if (error) goto Close; diff --git a/kernel/power/swap.c b/kernel/power/swap.c index e1912ad13bdc..ca0fcb5ced71 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -974,12 +974,11 @@ static int get_swap_reader(struct swap_map_handle *handle, last = handle->maps = NULL; offset = swsusp_header->image; while (offset) { - tmp = kmalloc(sizeof(*handle->maps), GFP_KERNEL); + tmp = kzalloc(sizeof(*handle->maps), GFP_KERNEL); if (!tmp) { release_swap_reader(handle); return -ENOMEM; } - memset(tmp, 0, sizeof(*tmp)); if (!handle->maps) handle->maps = tmp; if (last) diff --git a/kernel/signal.c b/kernel/signal.c index d622eac9d169..edf8915ddd54 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2912,7 +2912,8 @@ EXPORT_SYMBOL(set_compat_user_sigmask); * This is useful for syscalls such as ppoll, pselect, io_pgetevents and * epoll_pwait where a new sigmask is passed in from userland for the syscalls. */ -void restore_user_sigmask(const void __user *usigmask, sigset_t *sigsaved) +void restore_user_sigmask(const void __user *usigmask, sigset_t *sigsaved, + bool interrupted) { if (!usigmask) @@ -2922,7 +2923,7 @@ void restore_user_sigmask(const void __user *usigmask, sigset_t *sigsaved) * Restoring sigmask here can lead to delivering signals that the above * syscalls are intended to block because of the sigmask passed in. */ - if (signal_pending(current)) { + if (interrupted) { current->saved_sigmask = *sigsaved; set_restore_sigmask(); return; diff --git a/lib/idr.c b/lib/idr.c index c34e256d2f01..66a374892482 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -228,11 +228,21 @@ void *idr_get_next(struct idr *idr, int *nextid) { struct radix_tree_iter iter; void __rcu **slot; + void *entry = NULL; unsigned long base = idr->idr_base; unsigned long id = *nextid; id = (id < base) ? 0 : id - base; - slot = radix_tree_iter_find(&idr->idr_rt, &iter, id); + radix_tree_for_each_slot(slot, &idr->idr_rt, &iter, id) { + entry = rcu_dereference_raw(*slot); + if (!entry) + continue; + if (!xa_is_internal(entry)) + break; + if (slot != &idr->idr_rt.xa_head && !xa_is_retry(entry)) + break; + slot = radix_tree_iter_retry(&iter); + } if (!slot) return NULL; id = iter.index + base; @@ -241,7 +251,7 @@ void *idr_get_next(struct idr *idr, int *nextid) return NULL; *nextid = id; - return rcu_dereference_raw(*slot); + return entry; } EXPORT_SYMBOL(idr_get_next); diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 5d4bad8bd96a..9d631a7b6a70 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -38,6 +38,12 @@ static void *xa_store_index(struct xarray *xa, unsigned long index, gfp_t gfp) return xa_store(xa, index, xa_mk_index(index), gfp); } +static void xa_insert_index(struct xarray *xa, unsigned long index) +{ + XA_BUG_ON(xa, xa_insert(xa, index, xa_mk_index(index), + GFP_KERNEL) != 0); +} + static void xa_alloc_index(struct xarray *xa, unsigned long index, gfp_t gfp) { u32 id; @@ -338,6 +344,37 @@ static noinline void check_xa_shrink(struct xarray *xa) } } +static noinline void check_insert(struct xarray *xa) +{ + unsigned long i; + + for (i = 0; i < 1024; i++) { + xa_insert_index(xa, i); + XA_BUG_ON(xa, xa_load(xa, i - 1) != NULL); + XA_BUG_ON(xa, xa_load(xa, i + 1) != NULL); + xa_erase_index(xa, i); + } + + for (i = 10; i < BITS_PER_LONG; i++) { + xa_insert_index(xa, 1UL << i); + XA_BUG_ON(xa, xa_load(xa, (1UL << i) - 1) != NULL); + XA_BUG_ON(xa, xa_load(xa, (1UL << i) + 1) != NULL); + xa_erase_index(xa, 1UL << i); + + xa_insert_index(xa, (1UL << i) - 1); + XA_BUG_ON(xa, xa_load(xa, (1UL << i) - 2) != NULL); + XA_BUG_ON(xa, xa_load(xa, 1UL << i) != NULL); + xa_erase_index(xa, (1UL << i) - 1); + } + + xa_insert_index(xa, ~0UL); + XA_BUG_ON(xa, xa_load(xa, 0UL) != NULL); + XA_BUG_ON(xa, xa_load(xa, ~1UL) != NULL); + xa_erase_index(xa, ~0UL); + + XA_BUG_ON(xa, !xa_empty(xa)); +} + static noinline void check_cmpxchg(struct xarray *xa) { void *FIVE = xa_mk_value(5); @@ -1527,6 +1564,7 @@ static int xarray_checks(void) check_xa_mark(&array); check_xa_shrink(&array); check_xas_erase(&array); + check_insert(&array); check_cmpxchg(&array); check_reserve(&array); check_reserve(&xa0); diff --git a/lib/xarray.c b/lib/xarray.c index 6be3acbb861f..446b956c9188 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -298,6 +298,8 @@ bool xas_nomem(struct xa_state *xas, gfp_t gfp) xas_destroy(xas); return false; } + if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) + gfp |= __GFP_ACCOUNT; xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); if (!xas->xa_alloc) return false; @@ -325,6 +327,8 @@ static bool __xas_nomem(struct xa_state *xas, gfp_t gfp) xas_destroy(xas); return false; } + if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) + gfp |= __GFP_ACCOUNT; if (gfpflags_allow_blocking(gfp)) { xas_unlock_type(xas, lock_type); xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); @@ -358,8 +362,12 @@ static void *xas_alloc(struct xa_state *xas, unsigned int shift) if (node) { xas->xa_alloc = NULL; } else { - node = kmem_cache_alloc(radix_tree_node_cachep, - GFP_NOWAIT | __GFP_NOWARN); + gfp_t gfp = GFP_NOWAIT | __GFP_NOWARN; + + if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) + gfp |= __GFP_ACCOUNT; + + node = kmem_cache_alloc(radix_tree_node_cachep, gfp); if (!node) { xas_set_err(xas, -ENOMEM); return NULL; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ac843d32b019..ede7e7f5d1ab 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1510,16 +1510,29 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, /* * Dissolve a given free hugepage into free buddy pages. This function does - * nothing for in-use (including surplus) hugepages. Returns -EBUSY if the - * dissolution fails because a give page is not a free hugepage, or because - * free hugepages are fully reserved. + * nothing for in-use hugepages and non-hugepages. + * This function returns values like below: + * + * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use + * (allocated or reserved.) + * 0: successfully dissolved free hugepages or the page is not a + * hugepage (considered as already dissolved) */ int dissolve_free_huge_page(struct page *page) { int rc = -EBUSY; + /* Not to disrupt normal path by vainly holding hugetlb_lock */ + if (!PageHuge(page)) + return 0; + spin_lock(&hugetlb_lock); - if (PageHuge(page) && !page_count(page)) { + if (!PageHuge(page)) { + rc = 0; + goto out; + } + + if (!page_count(page)) { struct page *head = compound_head(page); struct hstate *h = page_hstate(head); int nid = page_to_nid(head); @@ -1564,11 +1577,9 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) { page = pfn_to_page(pfn); - if (PageHuge(page) && !page_count(page)) { - rc = dissolve_free_huge_page(page); - if (rc) - break; - } + rc = dissolve_free_huge_page(page); + if (rc) + break; } return rc; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 8da0334b9ca0..d9cc6606f409 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1730,6 +1730,8 @@ static int soft_offline_huge_page(struct page *page, int flags) if (!ret) { if (set_hwpoison_free_buddy_page(page)) num_poisoned_pages_inc(); + else + ret = -EBUSY; } } return ret; @@ -1854,11 +1856,8 @@ static int soft_offline_in_use_page(struct page *page, int flags) static int soft_offline_free_page(struct page *page) { - int rc = 0; - struct page *head = compound_head(page); + int rc = dissolve_free_huge_page(page); - if (PageHuge(head)) - rc = dissolve_free_huge_page(page); if (!rc) { if (set_hwpoison_free_buddy_page(page)) num_poisoned_pages_inc(); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 01600d80ae01..fdcb73536319 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -306,7 +306,7 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) else { nodes_remap(tmp, pol->v.nodes,pol->w.cpuset_mems_allowed, *nodes); - pol->w.cpuset_mems_allowed = tmp; + pol->w.cpuset_mems_allowed = *nodes; } if (nodes_empty(tmp)) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 5a58778c91d4..f719b64741d6 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -987,8 +987,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) /* * Determines whether the kernel must panic because of the panic_on_oom sysctl. */ -static void check_panic_on_oom(struct oom_control *oc, - enum oom_constraint constraint) +static void check_panic_on_oom(struct oom_control *oc) { if (likely(!sysctl_panic_on_oom)) return; @@ -998,7 +997,7 @@ static void check_panic_on_oom(struct oom_control *oc, * does not panic for cpuset, mempolicy, or memcg allocation * failures. */ - if (constraint != CONSTRAINT_NONE) + if (oc->constraint != CONSTRAINT_NONE) return; } /* Do not panic for oom kills triggered by sysrq */ @@ -1035,7 +1034,6 @@ EXPORT_SYMBOL_GPL(unregister_oom_notifier); bool out_of_memory(struct oom_control *oc) { unsigned long freed = 0; - enum oom_constraint constraint = CONSTRAINT_NONE; if (oom_killer_disabled) return false; @@ -1071,10 +1069,10 @@ bool out_of_memory(struct oom_control *oc) * Check if there were limitations on the allocation (only relevant for * NUMA and memcg) that may require different handling. */ - constraint = constrained_alloc(oc); - if (constraint != CONSTRAINT_MEMORY_POLICY) + oc->constraint = constrained_alloc(oc); + if (oc->constraint != CONSTRAINT_MEMORY_POLICY) oc->nodemask = NULL; - check_panic_on_oom(oc, constraint); + check_panic_on_oom(oc); if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task && current->mm && !oom_unkillable_task(current, NULL, oc->nodemask) && diff --git a/mm/page_idle.c b/mm/page_idle.c index 0b39ec0c945c..295512465065 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -136,7 +136,7 @@ static ssize_t page_idle_bitmap_read(struct file *file, struct kobject *kobj, end_pfn = pfn + count * BITS_PER_BYTE; if (end_pfn > max_pfn) - end_pfn = ALIGN(max_pfn, BITMAP_CHUNK_BITS); + end_pfn = max_pfn; for (; pfn < end_pfn; pfn++) { bit = pfn % BITMAP_CHUNK_BITS; @@ -181,7 +181,7 @@ static ssize_t page_idle_bitmap_write(struct file *file, struct kobject *kobj, end_pfn = pfn + count * BITS_PER_BYTE; if (end_pfn > max_pfn) - end_pfn = ALIGN(max_pfn, BITMAP_CHUNK_BITS); + end_pfn = max_pfn; for (; pfn < end_pfn; pfn++) { bit = pfn % BITMAP_CHUNK_BITS; diff --git a/mm/page_io.c b/mm/page_io.c index 2e8019d0e048..189415852077 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -29,10 +29,9 @@ static struct bio *get_swap_bio(gfp_t gfp_flags, struct page *page, bio_end_io_t end_io) { - int i, nr = hpage_nr_pages(page); struct bio *bio; - bio = bio_alloc(gfp_flags, nr); + bio = bio_alloc(gfp_flags, 1); if (bio) { struct block_device *bdev; @@ -41,9 +40,7 @@ static struct bio *get_swap_bio(gfp_t gfp_flags, bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9; bio->bi_end_io = end_io; - for (i = 0; i < nr; i++) - bio_add_page(bio, page + i, PAGE_SIZE, 0); - VM_BUG_ON(bio->bi_iter.bi_size != PAGE_SIZE * nr); + bio_add_page(bio, page, PAGE_SIZE * hpage_nr_pages(page), 0); } return bio; } diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 4c9e150e5ad3..0f76cca32a1c 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -913,7 +913,7 @@ adjust_va_to_fit_type(struct vmap_area *va, unsigned long nva_start_addr, unsigned long size, enum fit_type type) { - struct vmap_area *lva; + struct vmap_area *lva = NULL; if (type == FL_FIT_TYPE) { /* @@ -972,7 +972,7 @@ adjust_va_to_fit_type(struct vmap_area *va, if (type != FL_FIT_TYPE) { augment_tree_propagate_from(va); - if (type == NE_FIT_TYPE) + if (lva) /* type == NE_FIT_TYPE */ insert_vmap_area_augment(lva, &va->rb_node, &free_vmap_area_root, &free_vmap_area_list); } diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 19d27bee285e..1555b0c6f7ec 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -160,10 +160,10 @@ static inline struct lowpan_peer *peer_lookup_dst(struct lowpan_btle_dev *dev, struct in6_addr *daddr, struct sk_buff *skb) { - struct lowpan_peer *peer; - struct in6_addr *nexthop; struct rt6_info *rt = (struct rt6_info *)skb_dst(skb); int count = atomic_read(&dev->peer_count); + const struct in6_addr *nexthop; + struct lowpan_peer *peer; BT_DBG("peers %d addr %pI6c rt %p", count, daddr, rt); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 16f9159234a2..8c2ec35b6512 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -318,6 +318,7 @@ static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *sk static int ip_mc_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { + struct rtable *new_rt; int ret; ret = BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb); @@ -326,6 +327,17 @@ static int ip_mc_finish_output(struct net *net, struct sock *sk, return ret; } + /* Reset rt_iif so that inet_iif() will return skb->skb_iif. Setting + * this to non-zero causes ipi_ifindex in in_pktinfo to be overwritten, + * see ipv4_pktinfo_prepare(). + */ + new_rt = rt_dst_clone(net->loopback_dev, skb_rtable(skb)); + if (new_rt) { + new_rt->rt_iif = 0; + skb_dst_drop(skb); + skb_dst_set(skb, &new_rt->dst); + } + return dev_loopback_xmit(net, sk, skb); } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 0b8e06ca75d6..40a6abbc9cf6 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -197,7 +197,7 @@ static int raw_v4_input(struct sk_buff *skb, const struct iphdr *iph, int hash) } sk = __raw_v4_lookup(net, sk_next(sk), iph->protocol, iph->saddr, iph->daddr, - skb->dev->ifindex, sdif); + dif, sdif); } out: read_unlock(&raw_v4_hashinfo.lock); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 6cb7cff22db9..8ea0735a6754 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1647,6 +1647,39 @@ struct rtable *rt_dst_alloc(struct net_device *dev, } EXPORT_SYMBOL(rt_dst_alloc); +struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt) +{ + struct rtable *new_rt; + + new_rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, + rt->dst.flags); + + if (new_rt) { + new_rt->rt_genid = rt_genid_ipv4(dev_net(dev)); + new_rt->rt_flags = rt->rt_flags; + new_rt->rt_type = rt->rt_type; + new_rt->rt_is_input = rt->rt_is_input; + new_rt->rt_iif = rt->rt_iif; + new_rt->rt_pmtu = rt->rt_pmtu; + new_rt->rt_mtu_locked = rt->rt_mtu_locked; + new_rt->rt_gw_family = rt->rt_gw_family; + if (rt->rt_gw_family == AF_INET) + new_rt->rt_gw4 = rt->rt_gw4; + else if (rt->rt_gw_family == AF_INET6) + new_rt->rt_gw6 = rt->rt_gw6; + INIT_LIST_HEAD(&new_rt->rt_uncached); + + new_rt->dst.flags |= DST_HOST; + new_rt->dst.input = rt->dst.input; + new_rt->dst.output = rt->dst.output; + new_rt->dst.error = rt->dst.error; + new_rt->dst.lastuse = jiffies; + new_rt->dst.lwtstate = lwtstate_get(rt->dst.lwtstate); + } + return new_rt; +} +EXPORT_SYMBOL(rt_dst_clone); + /* called in rcu_read_lock() section */ int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 834475717110..21efcd02f337 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -59,8 +59,8 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; + const struct in6_addr *nexthop; struct neighbour *neigh; - struct in6_addr *nexthop; int ret; if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 11ad62effd56..97a843cf164c 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -218,7 +218,8 @@ static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst, { const struct rt6_info *rt = container_of(dst, struct rt6_info, dst); - return ip6_neigh_lookup(&rt->rt6i_gateway, dst->dev, skb, daddr); + return ip6_neigh_lookup(rt6_nexthop(rt, &in6addr_any), + dst->dev, skb, daddr); } static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr) @@ -5281,7 +5282,7 @@ static struct ctl_table ipv6_route_table_template[] = { .data = &init_net.ipv6.sysctl.skip_notify_on_dev_down, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero, .extra2 = &one, }, diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index 241317473114..cdfc33517e85 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -439,9 +439,9 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, struct nf_flowtable *flow_table = priv; struct flow_offload_tuple tuple = {}; enum flow_offload_tuple_dir dir; + const struct in6_addr *nexthop; struct flow_offload *flow; struct net_device *outdev; - struct in6_addr *nexthop; struct ipv6hdr *ip6h; struct rt6_info *rt; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a29d66da7394..5f78df080573 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2401,6 +2401,9 @@ static void tpacket_destruct_skb(struct sk_buff *skb) ts = __packet_set_timestamp(po, ph, skb); __packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts); + + if (!packet_read_pending(&po->tx_ring)) + complete(&po->skb_completion); } sock_wfree(skb); @@ -2585,7 +2588,7 @@ static int tpacket_parse_header(struct packet_sock *po, void *frame, static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) { - struct sk_buff *skb; + struct sk_buff *skb = NULL; struct net_device *dev; struct virtio_net_hdr *vnet_hdr = NULL; struct sockcm_cookie sockc; @@ -2600,6 +2603,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) int len_sum = 0; int status = TP_STATUS_AVAILABLE; int hlen, tlen, copylen = 0; + long timeo = 0; mutex_lock(&po->pg_vec_lock); @@ -2646,12 +2650,21 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if ((size_max > dev->mtu + reserve + VLAN_HLEN) && !po->has_vnet_hdr) size_max = dev->mtu + reserve + VLAN_HLEN; + reinit_completion(&po->skb_completion); + do { ph = packet_current_frame(po, &po->tx_ring, TP_STATUS_SEND_REQUEST); if (unlikely(ph == NULL)) { - if (need_wait && need_resched()) - schedule(); + if (need_wait && skb) { + timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT); + timeo = wait_for_completion_interruptible_timeout(&po->skb_completion, timeo); + if (timeo <= 0) { + err = !timeo ? -ETIMEDOUT : -ERESTARTSYS; + goto out_put; + } + } + /* check for additional frames */ continue; } @@ -3207,6 +3220,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, sock_init_data(sock, sk); po = pkt_sk(sk); + init_completion(&po->skb_completion); sk->sk_family = PF_PACKET; po->num = proto; po->xmit = dev_queue_xmit; @@ -4314,7 +4328,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, req3->tp_sizeof_priv || req3->tp_feature_req_word) { err = -EINVAL; - goto out; + goto out_free_pg_vec; } } break; @@ -4378,6 +4392,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, prb_shutdown_retire_blk_timer(po, rb_queue); } +out_free_pg_vec: if (pg_vec) free_pg_vec(pg_vec, order, req->tp_block_nr); out: diff --git a/net/packet/internal.h b/net/packet/internal.h index 3bb7c5fb3bff..c70a2794456f 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -128,6 +128,7 @@ struct packet_sock { unsigned int tp_hdrlen; unsigned int tp_reserve; unsigned int tp_tstamp; + struct completion skb_completion; struct net_device __rcu *cached_dev; int (*xmit)(struct sk_buff *skb); struct packet_type prot_hook ____cacheline_aligned_in_smp; diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index e16a3d37d2bc..732e109c3055 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -549,12 +549,17 @@ static struct notifier_block cbs_device_notifier = { static int __init cbs_module_init(void) { - int err = register_netdevice_notifier(&cbs_device_notifier); + int err; + err = register_netdevice_notifier(&cbs_device_notifier); if (err) return err; - return register_qdisc(&cbs_qdisc_ops); + err = register_qdisc(&cbs_qdisc_ops); + if (err) + unregister_netdevice_notifier(&cbs_device_notifier); + + return err; } static void __exit cbs_module_exit(void) diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index e358437ba29b..69cebb2c998b 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -118,10 +118,6 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, /* Initialize the bind addr area */ sctp_bind_addr_init(&ep->base.bind_addr, 0); - /* Remember who we are attached to. */ - ep->base.sk = sk; - sock_hold(ep->base.sk); - /* Create the lists of associations. */ INIT_LIST_HEAD(&ep->asocs); @@ -154,6 +150,10 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, ep->prsctp_enable = net->sctp.prsctp_enable; ep->reconf_enable = net->sctp.reconf_enable; + /* Remember who we are attached to. */ + ep->base.sk = sk; + sock_hold(ep->base.sk); + return ep; nomem_shkey: diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 0c874e996f85..7621ec2f539c 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2029,7 +2029,7 @@ static int __init smc_init(void) rc = smc_pnet_init(); if (rc) - return rc; + goto out_pernet_subsys; rc = smc_llc_init(); if (rc) { @@ -2080,6 +2080,9 @@ out_proto: proto_unregister(&smc_proto); out_pnet: smc_pnet_exit(); +out_pernet_subsys: + unregister_pernet_subsys(&smc_net_ops); + return rc; } diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 2d2850adc2a3..4ca50ddf8d16 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -652,7 +652,10 @@ create: rc = smc_lgr_create(smc, ini); if (rc) goto out; + lgr = conn->lgr; + write_lock_bh(&lgr->conns_lock); smc_lgr_register_conn(conn); /* add smc conn to lgr */ + write_unlock_bh(&lgr->conns_lock); } conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE; conn->local_tx_ctrl.len = SMC_WR_TX_SIZE; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index c69951ed2ebc..36652352a38c 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -950,6 +950,8 @@ static int xs_local_send_request(struct rpc_rqst *req) struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct xdr_buf *xdr = &req->rq_snd_buf; + rpc_fraghdr rm = xs_stream_record_marker(xdr); + unsigned int msglen = rm ? req->rq_slen + sizeof(rm) : req->rq_slen; int status; int sent = 0; @@ -964,9 +966,7 @@ static int xs_local_send_request(struct rpc_rqst *req) req->rq_xtime = ktime_get(); status = xs_sendpages(transport->sock, NULL, 0, xdr, - transport->xmit.offset, - xs_stream_record_marker(xdr), - &sent); + transport->xmit.offset, rm, &sent); dprintk("RPC: %s(%u) = %d\n", __func__, xdr->len - transport->xmit.offset, status); @@ -976,7 +976,7 @@ static int xs_local_send_request(struct rpc_rqst *req) if (likely(sent > 0) || status == 0) { transport->xmit.offset += sent; req->rq_bytes_sent = transport->xmit.offset; - if (likely(req->rq_bytes_sent >= req->rq_slen)) { + if (likely(req->rq_bytes_sent >= msglen)) { req->rq_xmit_bytes_sent += transport->xmit.offset; transport->xmit.offset = 0; return 0; @@ -1097,6 +1097,8 @@ static int xs_tcp_send_request(struct rpc_rqst *req) struct rpc_xprt *xprt = req->rq_xprt; struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt); struct xdr_buf *xdr = &req->rq_snd_buf; + rpc_fraghdr rm = xs_stream_record_marker(xdr); + unsigned int msglen = rm ? req->rq_slen + sizeof(rm) : req->rq_slen; bool vm_wait = false; int status; int sent; @@ -1122,9 +1124,7 @@ static int xs_tcp_send_request(struct rpc_rqst *req) while (1) { sent = 0; status = xs_sendpages(transport->sock, NULL, 0, xdr, - transport->xmit.offset, - xs_stream_record_marker(xdr), - &sent); + transport->xmit.offset, rm, &sent); dprintk("RPC: xs_tcp_send_request(%u) = %d\n", xdr->len - transport->xmit.offset, status); @@ -1133,7 +1133,7 @@ static int xs_tcp_send_request(struct rpc_rqst *req) * reset the count of bytes sent. */ transport->xmit.offset += sent; req->rq_bytes_sent = transport->xmit.offset; - if (likely(req->rq_bytes_sent >= req->rq_slen)) { + if (likely(req->rq_bytes_sent >= msglen)) { req->rq_xmit_bytes_sent += transport->xmit.offset; transport->xmit.offset = 0; return 0; diff --git a/net/tipc/core.c b/net/tipc/core.c index ed536c05252a..c8370722f0bb 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -134,7 +134,7 @@ static int __init tipc_init(void) if (err) goto out_sysctl; - err = register_pernet_subsys(&tipc_net_ops); + err = register_pernet_device(&tipc_net_ops); if (err) goto out_pernet; @@ -142,7 +142,7 @@ static int __init tipc_init(void) if (err) goto out_socket; - err = register_pernet_subsys(&tipc_topsrv_net_ops); + err = register_pernet_device(&tipc_topsrv_net_ops); if (err) goto out_pernet_topsrv; @@ -153,11 +153,11 @@ static int __init tipc_init(void) pr_info("Started in single node mode\n"); return 0; out_bearer: - unregister_pernet_subsys(&tipc_topsrv_net_ops); + unregister_pernet_device(&tipc_topsrv_net_ops); out_pernet_topsrv: tipc_socket_stop(); out_socket: - unregister_pernet_subsys(&tipc_net_ops); + unregister_pernet_device(&tipc_net_ops); out_pernet: tipc_unregister_sysctl(); out_sysctl: @@ -172,9 +172,9 @@ out_netlink: static void __exit tipc_exit(void) { tipc_bearer_cleanup(); - unregister_pernet_subsys(&tipc_topsrv_net_ops); + unregister_pernet_device(&tipc_topsrv_net_ops); tipc_socket_stop(); - unregister_pernet_subsys(&tipc_net_ops); + unregister_pernet_device(&tipc_net_ops); tipc_netlink_stop(); tipc_netlink_compat_stop(); tipc_unregister_sysctl(); diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index c6a04c09d075..cf155061c472 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -445,7 +445,11 @@ static int tipc_nl_compat_bearer_disable(struct tipc_nl_compat_cmd_doit *cmd, if (!bearer) return -EMSGSIZE; - len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME); + len = TLV_GET_DATA_LEN(msg->req); + if (len <= 0) + return -EINVAL; + + len = min_t(int, len, TIPC_MAX_BEARER_NAME); if (!string_is_valid(name, len)) return -EINVAL; @@ -539,7 +543,11 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg, name = (char *)TLV_DATA(msg->req); - len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); + len = TLV_GET_DATA_LEN(msg->req); + if (len <= 0) + return -EINVAL; + + len = min_t(int, len, TIPC_MAX_BEARER_NAME); if (!string_is_valid(name, len)) return -EINVAL; @@ -817,7 +825,11 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd, if (!link) return -EMSGSIZE; - len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME); + len = TLV_GET_DATA_LEN(msg->req); + if (len <= 0) + return -EINVAL; + + len = min_t(int, len, TIPC_MAX_BEARER_NAME); if (!string_is_valid(name, len)) return -EINVAL; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index fc81ae18cc44..e2b69e805d46 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -279,7 +279,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) goto skip_tx_cleanup; } - if (!tls_complete_pending_work(sk, ctx, 0, &timeo)) + if (unlikely(sk->sk_write_pending) && + !wait_on_pending_writer(sk, &timeo)) tls_handle_open_record(sk, 0); /* We need these for tls_sw_fallback handling of other packets */ diff --git a/samples/pidfd/pidfd-metadata.c b/samples/pidfd/pidfd-metadata.c index 14b454448429..c459155daf9a 100644 --- a/samples/pidfd/pidfd-metadata.c +++ b/samples/pidfd/pidfd-metadata.c @@ -83,7 +83,7 @@ static int pidfd_metadata_fd(pid_t pid, int pidfd) int main(int argc, char *argv[]) { - int pidfd = 0, ret = EXIT_FAILURE; + int pidfd = -1, ret = EXIT_FAILURE; char buf[4096] = { 0 }; pid_t pid; int procfd, statusfd; @@ -91,7 +91,11 @@ int main(int argc, char *argv[]) pid = pidfd_clone(CLONE_PIDFD, &pidfd); if (pid < 0) - exit(ret); + err(ret, "CLONE_PIDFD"); + if (pidfd == -1) { + warnx("CLONE_PIDFD is not supported by the kernel"); + goto out; + } procfd = pidfd_metadata_fd(pid, pidfd); close(pidfd); diff --git a/tools/arch/x86/include/uapi/asm/perf_regs.h b/tools/arch/x86/include/uapi/asm/perf_regs.h index ac67bbea10ca..7c9d2bb3833b 100644 --- a/tools/arch/x86/include/uapi/asm/perf_regs.h +++ b/tools/arch/x86/include/uapi/asm/perf_regs.h @@ -52,4 +52,7 @@ enum perf_event_x86_regs { /* These include both GPRs and XMMX registers */ PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2, }; + +#define PERF_REG_EXTENDED_MASK (~((1ULL << PERF_REG_X86_XMM0) - 1)) + #endif /* _ASM_X86_PERF_REGS_H */ diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h index b7cd91a9014f..b7321337d100 100644 --- a/tools/perf/arch/x86/include/perf_regs.h +++ b/tools/perf/arch/x86/include/perf_regs.h @@ -9,7 +9,6 @@ void perf_regs_load(u64 *regs); #define PERF_REGS_MAX PERF_REG_X86_XMM_MAX -#define PERF_XMM_REGS_MASK (~((1ULL << PERF_REG_X86_XMM0) - 1)) #ifndef HAVE_ARCH_X86_64_SUPPORT #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1) #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32 diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c index 7886ca5263e3..3666c0076df9 100644 --- a/tools/perf/arch/x86/util/perf_regs.c +++ b/tools/perf/arch/x86/util/perf_regs.c @@ -277,7 +277,7 @@ uint64_t arch__intr_reg_mask(void) .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES, .sample_type = PERF_SAMPLE_REGS_INTR, - .sample_regs_intr = PERF_XMM_REGS_MASK, + .sample_regs_intr = PERF_REG_EXTENDED_MASK, .precise_ip = 1, .disabled = 1, .exclude_kernel = 1, @@ -293,7 +293,7 @@ uint64_t arch__intr_reg_mask(void) fd = sys_perf_event_open(&attr, 0, -1, -1, 0); if (fd != -1) { close(fd); - return (PERF_XMM_REGS_MASK | PERF_REGS_MASK); + return (PERF_REG_EXTENDED_MASK | PERF_REGS_MASK); } return PERF_REGS_MASK; diff --git a/tools/power/cpupower/man/cpupower-monitor.1 b/tools/power/cpupower/man/cpupower-monitor.1 index 914cbb9d9cd0..70a56476f4b0 100644 --- a/tools/power/cpupower/man/cpupower-monitor.1 +++ b/tools/power/cpupower/man/cpupower-monitor.1 @@ -61,7 +61,7 @@ Only display specific monitors. Use the monitor string(s) provided by \-l option .PP \-i seconds .RS 4 -Measure intervall. +Measure interval. .RE .PP \-c diff --git a/tools/power/cpupower/po/cs.po b/tools/power/cpupower/po/cs.po index cb22c45c5069..bfc7e1702ec9 100644 --- a/tools/power/cpupower/po/cs.po +++ b/tools/power/cpupower/po/cs.po @@ -98,7 +98,7 @@ msgstr "" #: utils/idle_monitor/cpupower-monitor.c:74 #, c-format -msgid "\t -i: time intervall to measure for in seconds (default 1)\n" +msgid "\t -i: time interval to measure for in seconds (default 1)\n" msgstr "" #: utils/idle_monitor/cpupower-monitor.c:75 diff --git a/tools/power/cpupower/po/de.po b/tools/power/cpupower/po/de.po index 840c17cc450a..70887bb8ba95 100644 --- a/tools/power/cpupower/po/de.po +++ b/tools/power/cpupower/po/de.po @@ -95,7 +95,7 @@ msgstr "" #: utils/idle_monitor/cpupower-monitor.c:74 #, c-format -msgid "\t -i: time intervall to measure for in seconds (default 1)\n" +msgid "\t -i: time interval to measure for in seconds (default 1)\n" msgstr "" #: utils/idle_monitor/cpupower-monitor.c:75 diff --git a/tools/power/cpupower/po/fr.po b/tools/power/cpupower/po/fr.po index b46ca2548f86..b6e505b34e4a 100644 --- a/tools/power/cpupower/po/fr.po +++ b/tools/power/cpupower/po/fr.po @@ -95,7 +95,7 @@ msgstr "" #: utils/idle_monitor/cpupower-monitor.c:74 #, c-format -msgid "\t -i: time intervall to measure for in seconds (default 1)\n" +msgid "\t -i: time interval to measure for in seconds (default 1)\n" msgstr "" #: utils/idle_monitor/cpupower-monitor.c:75 diff --git a/tools/power/cpupower/po/it.po b/tools/power/cpupower/po/it.po index f80c4ddb9bda..a1deeb52c9e0 100644 --- a/tools/power/cpupower/po/it.po +++ b/tools/power/cpupower/po/it.po @@ -95,7 +95,7 @@ msgstr "" #: utils/idle_monitor/cpupower-monitor.c:74 #, c-format -msgid "\t -i: time intervall to measure for in seconds (default 1)\n" +msgid "\t -i: time interval to measure for in seconds (default 1)\n" msgstr "" #: utils/idle_monitor/cpupower-monitor.c:75 diff --git a/tools/power/cpupower/po/pt.po b/tools/power/cpupower/po/pt.po index 990f5267ffe8..902186585bb9 100644 --- a/tools/power/cpupower/po/pt.po +++ b/tools/power/cpupower/po/pt.po @@ -93,7 +93,7 @@ msgstr "" #: utils/idle_monitor/cpupower-monitor.c:74 #, c-format -msgid "\t -i: time intervall to measure for in seconds (default 1)\n" +msgid "\t -i: time interval to measure for in seconds (default 1)\n" msgstr "" #: utils/idle_monitor/cpupower-monitor.c:75 diff --git a/tools/power/cpupower/utils/cpufreq-set.c b/tools/power/cpupower/utils/cpufreq-set.c index f49bc4aa2a08..6ed82fba5aaa 100644 --- a/tools/power/cpupower/utils/cpufreq-set.c +++ b/tools/power/cpupower/utils/cpufreq-set.c @@ -305,6 +305,8 @@ int cmd_freq_set(int argc, char **argv) bitmask_setbit(cpus_chosen, cpus->cpu); cpus = cpus->next; } + /* Set the last cpu in related cpus list */ + bitmask_setbit(cpus_chosen, cpus->cpu); cpufreq_put_related_cpus(cpus); } } diff --git a/tools/power/pm-graph/README b/tools/power/pm-graph/README new file mode 100644 index 000000000000..58a5591e3951 --- /dev/null +++ b/tools/power/pm-graph/README @@ -0,0 +1,552 @@ + p m - g r a p h + + pm-graph: suspend/resume/boot timing analysis tools + Version: 5.4 + Author: Todd Brandt <todd.e.brandt@intel.com> + Home Page: https://01.org/pm-graph + + Report bugs/issues at bugzilla.kernel.org Tools/pm-graph + - https://bugzilla.kernel.org/buglist.cgi?component=pm-graph&product=Tools + + Full documentation available online & in man pages + - Getting Started: + https://01.org/pm-graph/documentation/getting-started + + - Config File Format: + https://01.org/pm-graph/documentation/3-config-file-format + + - upstream version in git: + https://github.com/intel/pm-graph/ + + Table of Contents + - Overview + - Setup + - Usage + - Basic Usage + - Dev Mode Usage + - Proc Mode Usage + - Configuration Files + - Usage Examples + - Config File Options + - Custom Timeline Entries + - Adding/Editing Timeline Functions + - Adding/Editing Dev Timeline Source Functions + - Verifying your Custom Functions + - Testing on consumer linux Operating Systems + - Android + +------------------------------------------------------------------ +| OVERVIEW | +------------------------------------------------------------------ + + This tool suite is designed to assist kernel and OS developers in optimizing + their linux stack's suspend/resume & boot time. Using a kernel image built + with a few extra options enabled, the tools will execute a suspend or boot, + and will capture dmesg and ftrace data. This data is transformed into a set of + timelines and a callgraph to give a quick and detailed view of which devices + and kernel processes are taking the most time in suspend/resume & boot. + +------------------------------------------------------------------ +| SETUP | +------------------------------------------------------------------ + + These packages are required to execute the scripts + - python + - python-requests + + Ubuntu: + sudo apt-get install python python-requests + + Fedora: + sudo dnf install python python-requests + + The tools can most easily be installed via git clone and make install + + $> git clone http://github.com/intel/pm-graph.git + $> cd pm-graph + $> sudo make install + $> man sleepgraph ; man bootgraph + + Setup involves some minor kernel configuration + + The following kernel build options are required for all kernels: + CONFIG_DEVMEM=y + CONFIG_PM_DEBUG=y + CONFIG_PM_SLEEP_DEBUG=y + CONFIG_FTRACE=y + CONFIG_FUNCTION_TRACER=y + CONFIG_FUNCTION_GRAPH_TRACER=y + CONFIG_KPROBES=y + CONFIG_KPROBES_ON_FTRACE=y + + In kernel 3.15.0, two patches were upstreamed which enable the + v3.0 behavior. These patches allow the tool to read all the + data from trace events instead of from dmesg. You can enable + this behavior on earlier kernels with these patches: + + (kernel/pre-3.15/enable_trace_events_suspend_resume.patch) + (kernel/pre-3.15/enable_trace_events_device_pm_callback.patch) + + If you're using a kernel older than 3.15.0, the following + additional kernel parameters are required: + (e.g. in file /etc/default/grub) + GRUB_CMDLINE_LINUX_DEFAULT="... initcall_debug log_buf_len=32M ..." + + If you're using a kernel older than 3.11-rc2, the following simple + patch must be applied to enable ftrace data: + in file: kernel/power/suspend.c + in function: int suspend_devices_and_enter(suspend_state_t state) + remove call to "ftrace_stop();" + remove call to "ftrace_start();" + + There is a patch which does this for kernel v3.8.0: + (kernel/pre-3.11-rc2/enable_ftrace_in_suspendresume.patch) + + + +------------------------------------------------------------------ +| USAGE | +------------------------------------------------------------------ + +Basic Usage +___________ + + 1) First configure a kernel using the instructions from the previous sections. + Then build, install, and boot with it. + 2) Open up a terminal window and execute the mode list command: + + %> sudo ./sleepgraph.py -modes + ['freeze', 'mem', 'disk'] + + Execute a test using one of the available power modes, e.g. mem (S3): + + %> sudo ./sleepgraph.py -m mem -rtcwake 15 + + or with a config file + + %> sudo ./sleepgraph.py -config config/suspend.cfg + + When the system comes back you'll see the script finishing up and + creating the output files in the test subdir. It generates output + files in subdirectory: suspend-mmddyy-HHMMSS. The ftrace file can + be used to regenerate the html timeline with different options + + HTML output: <hostname>_<mode>.html + raw dmesg output: <hostname>_<mode>_dmesg.txt + raw ftrace output: <hostname>_<mode>_ftrace.txt + + View the html in firefox or chrome. + + +Dev Mode Usage +______________ + + Developer mode adds information on low level source calls to the timeline. + The tool sets kprobes on all delay and mutex calls to see which devices + are waiting for something and when. It also sets a suite of kprobes on + subsystem dependent calls to better fill out the timeline. + + The tool will also expose kernel threads that don't normally show up in the + timeline. This is useful in discovering dependent threads to get a better + idea of what each device is waiting for. For instance, the scsi_eh thread, + a.k.a. scsi resume error handler, is what each SATA disk device waits for + before it can continue resume. + + The timeline will be much larger if run with dev mode, so it can be useful + to set the -mindev option to clip out any device blocks that are too small + to see easily. The following command will give a nice dev mode run: + + %> sudo ./sleepgraph.py -m mem -rtcwake 15 -mindev 1 -dev + + or with a config file + + %> sudo ./sleepgraph.py -config config/suspend-dev.cfg + + +Proc Mode Usage +_______________ + + Proc mode adds user process info to the timeline. This is done in a manner + similar to the bootchart utility, which graphs init processes and their + execution as the system boots. This tool option does the same thing but for + the period before and after suspend/resume. + + In order to see any process info, there needs to be some delay before or + after resume since processes are frozen in suspend_prepare and thawed in + resume_complete. The predelay and postdelay args allow you to do this. It + can also be useful to run in x2 mode with an x2 delay, this way you can + see process activity before and after resume, and in between two + successive suspend/resumes. + + The command can be run like this: + + %> sudo ./sleepgraph.py -m mem -rtcwake 15 -x2 -x2delay 1000 -predelay 1000 -postdelay 1000 -proc + + or with a config file + + %> sudo ./sleepgraph.py -config config/suspend-proc.cfg + + +------------------------------------------------------------------ +| CONFIGURATION FILES | +------------------------------------------------------------------ + + Since 4.0 we've moved to using config files in lieu of command line options. + The config folder contains a collection of typical use cases. + There are corresponding configs for other power modes: + + Simple suspend/resume with basic timeline (mem/freeze/standby) + config/suspend.cfg + config/freeze.cfg + config/standby.cfg + + Dev mode suspend/resume with dev timeline (mem/freeze/standby) + config/suspend-dev.cfg + config/freeze-dev.cfg + config/standby-dev.cfg + + Simple suspend/resume with timeline and callgraph (mem/freeze/standby) + config/suspend-callgraph.cfg + config/freeze-callgraph.cfg + config/standby-callgraph.cfg + + Sample proc mode x2 run using mem suspend + config/suspend-x2-proc.cfg + + Sample for editing timeline funcs (moves internal functions into config) + config/custom-timeline-functions.cfg + + Sample debug config for serio subsystem + config/debug-serio-suspend.cfg + + +Usage Examples +______________ + + Run a simple mem suspend: + %> sudo ./sleepgraph.py -config config/suspend.cfg + + Run a mem suspend with callgraph data: + %> sudo ./sleepgraph.py -config config/suspend-callgraph.cfg + + Run a mem suspend with dev mode detail: + %> sudo ./sleepgraph.py -config config/suspend-dev.cfg + + +Config File Options +___________________ + + [Settings] + + # Verbosity: print verbose messages (def: false) + verbose: false + + # Suspend Mode: e.g. standby, mem, freeze, disk (def: mem) + mode: mem + + # Output Directory Format: {hostname}, {date}, {time} give current values + output-dir: suspend-{hostname}-{date}-{time} + + # Automatic Wakeup: use rtcwake to wakeup after X seconds (def: infinity) + rtcwake: 15 + + # Add Logs: add the dmesg and ftrace log to the html output (def: false) + addlogs: false + + # Sus/Res Gap: insert a gap between sus & res in the timeline (def: false) + srgap: false + + # Custom Command: Command to execute in lieu of suspend (def: "") + command: echo mem > /sys/power/state + + # Proc mode: graph user processes and cpu usage in the timeline (def: false) + proc: false + + # Dev mode: graph source functions in the timeline (def: false) + dev: false + + # Suspend/Resume x2: run 2 suspend/resumes back to back (def: false) + x2: false + + # x2 Suspend Delay: time delay between the two test runs in ms (def: 0 ms) + x2delay: 0 + + # Pre Suspend Delay: nclude an N ms delay before (1st) suspend (def: 0 ms) + predelay: 0 + + # Post Resume Delay: include an N ms delay after (last) resume (def: 0 ms) + postdelay: 0 + + # Min Device Length: graph only dev callbacks longer than min (def: 0.001 ms) + mindev: 0.001 + + # Callgraph: gather ftrace callgraph data on all timeline events (def: false) + callgraph: false + + # Expand Callgraph: pre-expand the callgraph treeviews in html (def: false) + expandcg: false + + # Min Callgraph Length: show callgraphs only if longer than min (def: 1 ms) + mincg: 1 + + # Timestamp Precision: number of sig digits in timestamps (0:S, [3:ms], 6:us) + timeprec: 3 + + # Device Filter: show only devs whose name/driver includes one of these strings + devicefilter: _cpu_up,_cpu_down,i915,usb + + # Override default timeline entries: + # Do not use the internal default functions for timeline entries (def: false) + # Set this to true if you intend to only use the ones defined in the config + override-timeline-functions: true + + # Override default dev timeline entries: + # Do not use the internal default functions for dev timeline entries (def: false) + # Set this to true if you intend to only use the ones defined in the config + override-dev-timeline-functions: true + + # Call Loop Max Gap (dev mode only) + # merge loops of the same call if each is less than maxgap apart (def: 100us) + callloop-maxgap: 0.0001 + + # Call Loop Max Length (dev mode only) + # merge loops of the same call if each is less than maxlen in length (def: 5ms) + callloop-maxlen: 0.005 + +------------------------------------------------------------------ +| CUSTOM TIMELINE ENTRIES | +------------------------------------------------------------------ + +Adding or Editing Timeline Functions +____________________________________ + + The tool uses an array of function names to fill out empty spaces in the + timeline where device callbacks don't appear. For instance, in suspend_prepare + the tool adds the sys_sync and freeze_processes calls as virtual device blocks + in the timeline to show you where the time is going. These calls should fill + the timeline with contiguous data so that most kernel execution is covered. + + It is possible to add new function calls to the timeline by adding them to + the config. It's also possible to copy the internal timeline functions into + the config so that you can override and edit them. Place them in the + timeline_functions_ARCH section with the name of your architecture appended. + i.e. for x86_64: [timeline_functions_x86_64] + + Use the override-timeline-functions option if you only want to use your + custom calls, or leave it false to append them to the internal ones. + + This section includes a list of functions (set using kprobes) which use both + symbol data and function arg data. The args are pulled directly from the + stack using this architecture's registers and stack formatting. Each entry + can include up to four pieces of info: The function name, a format string, + an argument list, and a color. But only a function name is required. + + For a full example config, see config/custom-timeline-functions.cfg. It pulls + all the internal timeline functions into the config and allows you to edit + them. + + Entry format: + + function: format{fn_arg1}_{fn_arg2} fn_arg1 fn_arg2 ... [color=purple] + + Required Arguments: + + function: The symbol name for the function you want probed, this is the + minimum required for an entry, it will show up as the function + name with no arguments. + + example: _cpu_up: + + Optional Arguments: + + format: The format to display the data on the timeline in. Use braces to + enclose the arg names. + + example: CPU_ON[{cpu}] + + color: The color of the entry block in the timeline. The default color is + transparent, so the entry shares the phase color. The color is an + html color string, either a word, or an RGB. + + example: [color=#CC00CC] + + arglist: A list of arguments from registers/stack addresses. See URL: + https://www.kernel.org/doc/Documentation/trace/kprobetrace.txt + + example: cpu=%di:s32 + + Here is a full example entry. It displays cpu resume calls in the timeline + in orange. They will appear as CPU_ON[0], CPU_ON[1], etc. + + [timeline_functions_x86_64] + _cpu_up: CPU_ON[{cpu}] cpu=%di:s32 [color=orange] + + +Adding or Editing Dev Mode Timeline Source Functions +____________________________________________________ + + In dev mode, the tool uses an array of function names to monitor source + execution within the timeline entries. + + The function calls are displayed inside the main device/call blocks in the + timeline. However, if a function call is not within a main timeline event, + it will spawn an entirely new event named after the caller's kernel thread. + These asynchronous kernel threads will populate in a separate section + beneath the main device/call section. + + The tool has a set of hard coded calls which focus on the most common use + cases: msleep, udelay, schedule_timeout, mutex_lock_slowpath, etc. These are + the functions that add a hardcoded time delay to the suspend/resume path. + The tool also includes some common functions native to important + subsystems: ata, i915, and ACPI, etc. + + It is possible to add new function calls to the dev timeline by adding them + to the config. It's also possible to copy the internal dev timeline + functions into the config so that you can override and edit them. Place them + in the dev_timeline_functions_ARCH section with the name of your architecture + appended. i.e. for x86_64: [dev_timeline_functions_x86_64] + + Use the override-dev-timeline-functions option if you only want to use your + custom calls, or leave it false to append them to the internal ones. + + The format is the same as the timeline_functions_x86_64 section. It's a + list of functions (set using kprobes) which use both symbol data and function + arg data. The args are pulled directly from the stack using this + architecture's registers and stack formatting. Each entry can include up + to four pieces of info: The function name, a format string, an argument list, + and a color. But only the function name is required. + + For a full example config, see config/custom-timeline-functions.cfg. It pulls + all the internal dev timeline functions into the config and allows you to edit + them. + + Here is a full example entry. It displays the ATA port reset calls as + ataN_port_reset in the timeline. This is where most of the SATA disk resume + time goes, so it can be helpful to see the low level call. + + [dev_timeline_functions_x86_64] + ata_eh_recover: ata{port}_port_reset port=+36(%di):s32 [color=#CC00CC] + + +Verifying your custom functions +_______________________________ + + Once you have a set of functions (kprobes) defined, it can be useful to + perform a quick check to see if you formatted them correctly and if the system + actually supports them. To do this, run the tool with your config file + and the -status option. The tool will go through all the kprobes (both + custom and internal if you haven't overridden them) and actually attempts + to set them in ftrace. It will then print out success or fail for you. + + Note that kprobes which don't actually exist in the kernel won't stop the + tool, they just wont show up. + + For example: + + sudo ./sleepgraph.py -config config/custom-timeline-functions.cfg -status + Checking this system (myhostname)... + have root access: YES + is sysfs mounted: YES + is "mem" a valid power mode: YES + is ftrace supported: YES + are kprobes supported: YES + timeline data source: FTRACE (all trace events found) + is rtcwake supported: YES + verifying timeline kprobes work: + _cpu_down: YES + _cpu_up: YES + acpi_pm_finish: YES + acpi_pm_prepare: YES + freeze_kernel_threads: YES + freeze_processes: YES + sys_sync: YES + thaw_processes: YES + verifying dev kprobes work: + __const_udelay: YES + __mutex_lock_slowpath: YES + acpi_os_stall: YES + acpi_ps_parse_aml: YES + intel_opregion_init: NO + intel_opregion_register: NO + intel_opregion_setup: NO + msleep: YES + schedule_timeout: YES + schedule_timeout_uninterruptible: YES + usleep_range: YES + + +------------------------------------------------------------------ +| TESTING ON CONSUMER LINUX OPERATING SYSTEMS | +------------------------------------------------------------------ + +Android +_______ + + The easiest way to execute on an android device is to run the android.sh + script on the device, then pull the ftrace log back to the host and run + sleepgraph.py on it. + + Here are the steps: + + [download and install the tool on the device] + + host%> wget https://raw.githubusercontent.com/intel/pm-graph/master/tools/android.sh + host%> adb connect 192.168.1.6 + host%> adb root + # push the script to a writeable location + host%> adb push android.sh /sdcard/ + + [check whether the tool will run on your device] + + host%> adb shell + dev%> cd /sdcard + dev%> sh android.sh status + host : asus_t100 + kernel : 3.14.0-i386-dirty + modes : freeze mem + rtcwake : supported + ftrace : supported + trace events { + suspend_resume: found + device_pm_callback_end: found + device_pm_callback_start: found + } + # the above is what you see on a system that's properly patched + + [execute the suspend] + + # NOTE: The suspend will only work if the screen isn't timed out, + # so you have to press some keys first to wake it up b4 suspend) + dev%> sh android.sh suspend mem + ------------------------------------ + Suspend/Resume timing test initiated + ------------------------------------ + hostname : asus_t100 + kernel : 3.14.0-i386-dirty + mode : mem + ftrace out : /mnt/shell/emulated/0/ftrace.txt + dmesg out : /mnt/shell/emulated/0/dmesg.txt + log file : /mnt/shell/emulated/0/log.txt + ------------------------------------ + INITIALIZING FTRACE........DONE + STARTING FTRACE + SUSPEND START @ 21:24:02 (rtcwake in 10 seconds) + <adb connection will now terminate> + + [retrieve the data from the device] + + # I find that you have to actually kill the adb process and + # reconnect sometimes in order for the connection to work post-suspend + host%> adb connect 192.168.1.6 + # (required) get the ftrace data, this is the most important piece + host%> adb pull /sdcard/ftrace.txt + # (optional) get the dmesg data, this is for debugging + host%> adb pull /sdcard/dmesg.txt + # (optional) get the log, which just lists some test times for comparison + host%> adb pull /sdcard/log.txt + + [create an output html file using sleepgraph.py] + + host%> sleepgraph.py -ftrace ftrace.txt + + You should now have an output.html with the android data, enjoy! diff --git a/tools/power/pm-graph/bootgraph.py b/tools/power/pm-graph/bootgraph.py index 3d899dd8147a..666bcbda648d 100755 --- a/tools/power/pm-graph/bootgraph.py +++ b/tools/power/pm-graph/bootgraph.py @@ -325,9 +325,9 @@ def parseKernelLog(): if(not sysvals.stamp['kernel']): sysvals.stamp['kernel'] = sysvals.kernelVersion(msg) continue - m = re.match('.* setting system clock to (?P<t>.*) UTC.*', msg) + m = re.match('.* setting system clock to (?P<d>[0-9\-]*)[ A-Z](?P<t>[0-9:]*) UTC.*', msg) if(m): - bt = datetime.strptime(m.group('t'), '%Y-%m-%d %H:%M:%S') + bt = datetime.strptime(m.group('d')+' '+m.group('t'), '%Y-%m-%d %H:%M:%S') bt = bt - timedelta(seconds=int(ktime)) data.boottime = bt.strftime('%Y-%m-%d_%H:%M:%S') sysvals.stamp['time'] = bt.strftime('%B %d %Y, %I:%M:%S %p') @@ -348,7 +348,7 @@ def parseKernelLog(): data.newAction(phase, f, pid, start, ktime, int(r), int(t)) del devtemp[f] continue - if(re.match('^Freeing unused kernel memory.*', msg)): + if(re.match('^Freeing unused kernel .*', msg)): data.tUserMode = ktime data.dmesg['kernel']['end'] = ktime data.dmesg['user']['start'] = ktime @@ -1008,7 +1008,7 @@ if __name__ == '__main__': updateKernelParams() elif cmd == 'flistall': for f in sysvals.getBootFtraceFilterFunctions(): - print f + print(f) elif cmd == 'checkbl': sysvals.getBootLoader() pprint('Boot Loader: %s\n%s' % (sysvals.bootloader, sysvals.blexec)) diff --git a/tools/power/pm-graph/config/example.cfg b/tools/power/pm-graph/config/example.cfg index 05b2efb9bb54..1ef3eb9383fa 100644 --- a/tools/power/pm-graph/config/example.cfg +++ b/tools/power/pm-graph/config/example.cfg @@ -98,12 +98,34 @@ postdelay: 0 # graph only devices longer than min in the timeline (default: 0.001 ms) mindev: 0.001 +# Call Loop Max Gap (dev mode only) +# merge loops of the same call if each is less than maxgap apart (def: 100us) +callloop-maxgap: 0.0001 + +# Call Loop Max Length (dev mode only) +# merge loops of the same call if each is less than maxlen in length (def: 5ms) +callloop-maxlen: 0.005 + +# Override default timeline entries: +# Do not use the internal default functions for timeline entries (def: false) +# Set this to true if you intend to only use the ones defined in the config +override-timeline-functions: true + +# Override default dev timeline entries: +# Do not use the internal default functions for dev timeline entries (def: false) +# Set this to true if you intend to only use the ones defined in the config +override-dev-timeline-functions: true + # ---- Debug Options ---- # Callgraph # gather detailed ftrace callgraph data on all timeline events (default: false) callgraph: false +# Max graph depth +# limit the callgraph trace to this depth (default: 0 = all) +maxdepth: 2 + # Callgraph phase filter # Only enable callgraphs for one phase, i.e. resume_noirq (default: all) cgphase: suspend @@ -131,3 +153,7 @@ timeprec: 6 # Add kprobe functions to the timeline # Add functions to the timeline from a text file (default: no-action) # fadd: file.txt + +# Ftrace buffer size +# Set trace buffer size to N kilo-bytes (default: all of free memory up to 3GB) +# bufsize: 1000 diff --git a/tools/power/pm-graph/sleepgraph.8 b/tools/power/pm-graph/sleepgraph.8 index 24a2e7d0ae63..9648be644d5f 100644 --- a/tools/power/pm-graph/sleepgraph.8 +++ b/tools/power/pm-graph/sleepgraph.8 @@ -53,6 +53,11 @@ disable rtcwake and require a user keypress to resume. Add the dmesg and ftrace logs to the html output. They will be viewable by clicking buttons in the timeline. .TP +\fB-turbostat\fR +Use turbostat to execute the command in freeze mode (default: disabled). This +will provide turbostat output in the log which will tell you which actual +power modes were entered. +.TP \fB-result \fIfile\fR Export a results table to a text file for parsing. .TP @@ -121,6 +126,10 @@ be created in a new subdirectory with a summary page: suspend-xN-{date}-{time}. Use ftrace to create device callgraphs (default: disabled). This can produce very large outputs, i.e. 10MB - 100MB. .TP +\fB-ftop\fR +Use ftrace on the top level call: "suspend_devices_and_enter" only (default: disabled). +This option implies -f and creates a single callgraph covering all of suspend/resume. +.TP \fB-maxdepth \fIlevel\fR limit the callgraph trace depth to \fIlevel\fR (default: 0=all). This is the best way to limit the output size when using callgraphs via -f. @@ -138,8 +147,8 @@ which are barely visible in the timeline. The value is a float: e.g. 0.001 represents 1 us. .TP \fB-cgfilter \fI"func1,func2,..."\fR -Reduce callgraph output in the timeline by limiting it to a list of calls. The -argument can be a single function name or a comma delimited list. +Reduce callgraph output in the timeline by limiting it certain devices. The +argument can be a single device name or a comma delimited list. (default: none) .TP \fB-cgskip \fIfile\fR @@ -183,6 +192,9 @@ Print out the contents of the ACPI Firmware Performance Data Table. \fB-battery\fR Print out battery status and current charge. .TP +\fB-wifi\fR +Print out wifi status and connection details. +.TP \fB-xon/-xoff/-xstandby/-xsuspend\fR Test xset by attempting to switch the display to the given mode. This is the same command which will be issued by \fB-display \fImode\fR. diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py index d1a88d05e976..4f46a7a1feb6 100755 --- a/tools/power/pm-graph/sleepgraph.py +++ b/tools/power/pm-graph/sleepgraph.py @@ -9,9 +9,9 @@ # # Links: # Home Page -# https://01.org/suspendresume +# https://01.org/pm-graph # Source repo -# git@github.com:01org/pm-graph +# git@github.com:intel/pm-graph # # Description: # This tool is designed to assist kernel and OS developers in optimizing @@ -24,6 +24,7 @@ # viewed in firefox or chrome. # # The following kernel build options are required: +# CONFIG_DEVMEM=y # CONFIG_PM_DEBUG=y # CONFIG_PM_SLEEP_DEBUG=y # CONFIG_FTRACE=y @@ -53,6 +54,7 @@ import ConfigParser import gzip from threading import Thread from subprocess import call, Popen, PIPE +import base64 def pprint(msg): print(msg) @@ -66,7 +68,7 @@ def pprint(msg): # store system values and test parameters class SystemValues: title = 'SleepGraph' - version = '5.2' + version = '5.4' ansi = False rs = 0 display = '' @@ -74,8 +76,9 @@ class SystemValues: sync = False verbose = False testlog = True - dmesglog = False + dmesglog = True ftracelog = False + tstat = False mindevlen = 0.0 mincglen = 0.0 cgphase = '' @@ -99,6 +102,8 @@ class SystemValues: pmdpath = '/sys/power/pm_debug_messages' traceevents = [ 'suspend_resume', + 'wakeup_source_activate', + 'wakeup_source_deactivate', 'device_pm_callback_end', 'device_pm_callback_start' ] @@ -130,6 +135,8 @@ class SystemValues: x2delay = 0 skiphtml = False usecallgraph = False + ftopfunc = 'suspend_devices_and_enter' + ftop = False usetraceevents = False usetracemarkers = True usekprobes = True @@ -158,6 +165,13 @@ class SystemValues: 'acpi_hibernation_leave': {}, 'acpi_pm_freeze': {}, 'acpi_pm_thaw': {}, + 'acpi_s2idle_end': {}, + 'acpi_s2idle_sync': {}, + 'acpi_s2idle_begin': {}, + 'acpi_s2idle_prepare': {}, + 'acpi_s2idle_wake': {}, + 'acpi_s2idle_wakeup': {}, + 'acpi_s2idle_restore': {}, 'hibernate_preallocate_memory': {}, 'create_basic_memory_bitmaps': {}, 'swsusp_write': {}, @@ -191,9 +205,14 @@ class SystemValues: 'usleep_range': { 'args_x86_64': {'min':'%di:s32', 'max':'%si:s32'}, 'ub': 1 }, 'mutex_lock_slowpath': { 'func':'__mutex_lock_slowpath', 'ub': 1 }, 'acpi_os_stall': {'ub': 1}, + 'rt_mutex_slowlock': {'ub': 1}, # ACPI 'acpi_resume_power_resources': {}, - 'acpi_ps_parse_aml': {}, + 'acpi_ps_execute_method': { 'args_x86_64': { + 'fullpath':'+0(+40(%di)):string', + }}, + # mei_me + 'mei_reset': {}, # filesystem 'ext4_sync_fs': {}, # 80211 @@ -242,6 +261,7 @@ class SystemValues: timeformat = '%.3f' cmdline = '%s %s' % \ (os.path.basename(sys.argv[0]), ' '.join(sys.argv[1:])) + kparams = '' sudouser = '' def __init__(self): self.archargs = 'args_'+platform.machine() @@ -320,6 +340,7 @@ class SystemValues: args['date'] = n.strftime('%y%m%d') args['time'] = n.strftime('%H%M%S') args['hostname'] = args['host'] = self.hostname + args['mode'] = self.suspendmode return value.format(**args) def setOutputFile(self): if self.dmesgfile != '': @@ -331,21 +352,28 @@ class SystemValues: if(m): self.htmlfile = m.group('name')+'.html' def systemInfo(self, info): - p = c = m = b = '' + p = m = '' if 'baseboard-manufacturer' in info: m = info['baseboard-manufacturer'] elif 'system-manufacturer' in info: m = info['system-manufacturer'] - if 'baseboard-product-name' in info: - p = info['baseboard-product-name'] - elif 'system-product-name' in info: + if 'system-product-name' in info: p = info['system-product-name'] - if 'processor-version' in info: - c = info['processor-version'] - if 'bios-version' in info: - b = info['bios-version'] - self.sysstamp = '# sysinfo | man:%s | plat:%s | cpu:%s | bios:%s | numcpu:%d | memsz:%d | memfr:%d' % \ - (m, p, c, b, self.cpucount, self.memtotal, self.memfree) + elif 'baseboard-product-name' in info: + p = info['baseboard-product-name'] + if m[:5].lower() == 'intel' and 'baseboard-product-name' in info: + p = info['baseboard-product-name'] + c = info['processor-version'] if 'processor-version' in info else '' + b = info['bios-version'] if 'bios-version' in info else '' + r = info['bios-release-date'] if 'bios-release-date' in info else '' + self.sysstamp = '# sysinfo | man:%s | plat:%s | cpu:%s | bios:%s | biosdate:%s | numcpu:%d | memsz:%d | memfr:%d' % \ + (m, p, c, b, r, self.cpucount, self.memtotal, self.memfree) + try: + kcmd = open('/proc/cmdline', 'r').read().strip() + except: + kcmd = '' + if kcmd: + self.sysstamp += '\n# kparams | %s' % kcmd def printSystemInfo(self, fatal=False): self.rootCheck(True) out = dmidecode(self.mempath, fatal) @@ -353,10 +381,10 @@ class SystemValues: return fmt = '%-24s: %s' for name in sorted(out): - print fmt % (name, out[name]) - print fmt % ('cpucount', ('%d' % self.cpucount)) - print fmt % ('memtotal', ('%d kB' % self.memtotal)) - print fmt % ('memfree', ('%d kB' % self.memfree)) + print(fmt % (name, out[name])) + print(fmt % ('cpucount', ('%d' % self.cpucount))) + print(fmt % ('memtotal', ('%d kB' % self.memtotal))) + print(fmt % ('memfree', ('%d kB' % self.memfree))) def cpuInfo(self): self.cpucount = 0 fp = open('/proc/cpuinfo', 'r') @@ -376,7 +404,7 @@ class SystemValues: def initTestOutput(self, name): self.prefix = self.hostname v = open('/proc/version', 'r').read().strip() - kver = string.split(v)[2] + kver = v.split()[2] fmt = name+'-%m%d%y-%H%M%S' testtime = datetime.now().strftime(fmt) self.teststamp = \ @@ -391,7 +419,7 @@ class SystemValues: self.htmlfile = \ self.testdir+'/'+self.prefix+'_'+self.suspendmode+'.html' if not os.path.isdir(self.testdir): - os.mkdir(self.testdir) + os.makedirs(self.testdir) def getValueList(self, value): out = [] for i in value.split(','): @@ -402,6 +430,12 @@ class SystemValues: self.devicefilter = self.getValueList(value) def setCallgraphFilter(self, value): self.cgfilter = self.getValueList(value) + def skipKprobes(self, value): + for k in self.getValueList(value): + if k in self.tracefuncs: + del self.tracefuncs[k] + if k in self.dev_tracefuncs: + del self.dev_tracefuncs[k] def setCallgraphBlacklist(self, file): self.cgblacklist = self.listFromFile(file) def rtcWakeAlarmOn(self): @@ -471,9 +505,9 @@ class SystemValues: if 'func' in self.tracefuncs[i]: i = self.tracefuncs[i]['func'] if i in master: - print i + print(i) else: - print self.colorText(i) + print(self.colorText(i)) def setFtraceFilterFunctions(self, list): master = self.listFromFile(self.tpath+'available_filter_functions') flist = '' @@ -680,7 +714,8 @@ class SystemValues: if self.bufsize > 0: tgtsize = self.bufsize elif self.usecallgraph or self.usedevsrc: - bmax = (1*1024*1024) if self.suspendmode == 'disk' else (3*1024*1024) + bmax = (1*1024*1024) if self.suspendmode in ['disk', 'command'] \ + else (3*1024*1024) tgtsize = min(self.memfree, bmax) else: tgtsize = 65536 @@ -715,7 +750,10 @@ class SystemValues: cf.append(self.tracefuncs[fn]['func']) else: cf.append(fn) - self.setFtraceFilterFunctions(cf) + if self.ftop: + self.setFtraceFilterFunctions([self.ftopfunc]) + else: + self.setFtraceFilterFunctions(cf) # initialize the kprobe trace elif self.usekprobes: for name in self.tracefuncs: @@ -768,9 +806,21 @@ class SystemValues: fw = test['fw'] if(fw): fp.write('# fwsuspend %u fwresume %u\n' % (fw[0], fw[1])) + if 'mcelog' in test: + fp.write('# mcelog %s\n' % test['mcelog']) + if 'turbo' in test: + fp.write('# turbostat %s\n' % test['turbo']) if 'bat' in test: (a1, c1), (a2, c2) = test['bat'] fp.write('# battery %s %d %s %d\n' % (a1, c1, a2, c2)) + if 'wifi' in test: + wstr = [] + for wifi in test['wifi']: + tmp = [] + for key in sorted(wifi): + tmp.append('%s:%s' % (key, wifi[key])) + wstr.append('|'.join(tmp)) + fp.write('# wifi %s\n' % (','.join(wstr))) if test['error'] or len(testdata) > 1: fp.write('# enter_sleep_error %s\n' % test['error']) return fp @@ -821,6 +871,106 @@ class SystemValues: if isgz: return gzip.open(filename, mode+'b') return open(filename, mode) + def mcelog(self, clear=False): + cmd = self.getExec('mcelog') + if not cmd: + return '' + if clear: + call(cmd+' > /dev/null 2>&1', shell=True) + return '' + fp = Popen([cmd], stdout=PIPE, stderr=PIPE).stdout + out = fp.read().strip() + fp.close() + if not out: + return '' + return base64.b64encode(out.encode('zlib')) + def haveTurbostat(self): + if not self.tstat: + return False + cmd = self.getExec('turbostat') + if not cmd: + return False + fp = Popen([cmd, '-v'], stdout=PIPE, stderr=PIPE).stderr + out = fp.read().strip() + fp.close() + return re.match('turbostat version [0-9\.]* .*', out) + def turbostat(self): + cmd = self.getExec('turbostat') + if not cmd: + return 'missing turbostat executable' + text = [] + fullcmd = '%s -q -S echo freeze > %s' % (cmd, self.powerfile) + fp = Popen(['sh', '-c', fullcmd], stdout=PIPE, stderr=PIPE).stderr + for line in fp: + if re.match('[0-9.]* sec', line): + continue + text.append(line.split()) + fp.close() + if len(text) < 2: + return 'turbostat output format error' + out = [] + for key in text[0]: + values = [] + idx = text[0].index(key) + for line in text[1:]: + if len(line) > idx: + values.append(line[idx]) + out.append('%s=%s' % (key, ','.join(values))) + return '|'.join(out) + def checkWifi(self): + out = dict() + iwcmd, ifcmd = self.getExec('iwconfig'), self.getExec('ifconfig') + if not iwcmd or not ifcmd: + return out + fp = Popen(iwcmd, stdout=PIPE, stderr=PIPE).stdout + for line in fp: + m = re.match('(?P<dev>\S*) .* ESSID:(?P<ess>\S*)', line) + if not m: + continue + out['device'] = m.group('dev') + if '"' in m.group('ess'): + out['essid'] = m.group('ess').strip('"') + break + fp.close() + if 'device' in out: + fp = Popen([ifcmd, out['device']], stdout=PIPE, stderr=PIPE).stdout + for line in fp: + m = re.match('.* inet (?P<ip>[0-9\.]*)', line) + if m: + out['ip'] = m.group('ip') + break + fp.close() + return out + def errorSummary(self, errinfo, msg): + found = False + for entry in errinfo: + if re.match(entry['match'], msg): + entry['count'] += 1 + if self.hostname not in entry['urls']: + entry['urls'][self.hostname] = [self.htmlfile] + elif self.htmlfile not in entry['urls'][self.hostname]: + entry['urls'][self.hostname].append(self.htmlfile) + found = True + break + if found: + return + arr = msg.split() + for j in range(len(arr)): + if re.match('^[0-9,\-\.]*$', arr[j]): + arr[j] = '[0-9,\-\.]*' + else: + arr[j] = arr[j]\ + .replace('\\', '\\\\').replace(']', '\]').replace('[', '\[')\ + .replace('.', '\.').replace('+', '\+').replace('*', '\*')\ + .replace('(', '\(').replace(')', '\)') + mstr = ' '.join(arr) + entry = { + 'line': msg, + 'match': mstr, + 'count': 1, + 'urls': {self.hostname: [self.htmlfile]} + } + errinfo.append(entry) sysvals = SystemValues() switchvalues = ['enable', 'disable', 'on', 'off', 'true', 'false', '1', '0'] @@ -915,7 +1065,14 @@ class Data: 'ERROR' : '.*ERROR.*', 'WARNING' : '.*WARNING.*', 'IRQ' : '.*genirq: .*', - 'TASKFAIL': '.*Freezing of tasks failed.*', + 'TASKFAIL': '.*Freezing of tasks *.*', + 'ACPI' : '.*ACPI *(?P<b>[A-Za-z]*) *Error[: ].*', + 'DEVFAIL' : '.* failed to (?P<b>[a-z]*) async: .*', + 'DISKFULL': '.*No space left on device.*', + 'USBERR' : '.*usb .*device .*, error [0-9-]*', + 'ATAERR' : ' *ata[0-9\.]*: .*failed.*', + 'MEIERR' : ' *mei.*: .*failed.*', + 'TPMERR' : '(?i) *tpm *tpm[0-9]*: .*error.*', } def __init__(self, num): idchar = 'abcdefghij' @@ -933,6 +1090,9 @@ class Data: self.outfile = '' self.kerror = False self.battery = 0 + self.wifi = 0 + self.turbostat = 0 + self.mcelog = 0 self.enterfail = '' self.currphase = '' self.pstl = dict() # process timeline @@ -967,8 +1127,24 @@ class Data: if len(plist) < 1: return '' return plist[-1] + def turbostatInfo(self): + tp = TestProps() + out = {'syslpi':'N/A','pkgpc10':'N/A'} + for line in self.dmesgtext: + m = re.match(tp.tstatfmt, line) + if not m: + continue + for i in m.group('t').split('|'): + if 'SYS%LPI' in i: + out['syslpi'] = i.split('=')[-1]+'%' + elif 'pc10' in i: + out['pkgpc10'] = i.split('=')[-1]+'%' + break + return out def extractErrorInfo(self): - lf = sysvals.openlog(sysvals.dmesgfile, 'r') + lf = self.dmesgtext + if len(self.dmesgtext) < 1 and sysvals.dmesgfile: + lf = sysvals.openlog(sysvals.dmesgfile, 'r') i = 0 list = [] for line in lf: @@ -983,16 +1159,19 @@ class Data: msg = m.group('msg') for err in self.errlist: if re.match(self.errlist[err], msg): - list.append((err, dir, t, i, i)) + list.append((msg, err, dir, t, i, i)) self.kerror = True break - for e in list: - type, dir, t, idx1, idx2 = e + msglist = [] + for msg, type, dir, t, idx1, idx2 in list: + msglist.append(msg) sysvals.vprint('kernel %s found in %s at %f' % (type, dir, t)) self.errorinfo[dir].append((type, t, idx1, idx2)) if self.kerror: sysvals.dmesglog = True - lf.close() + if len(self.dmesgtext) < 1 and sysvals.dmesgfile: + lf.close() + return msglist def setStart(self, time): self.start = time def setEnd(self, time): @@ -2045,7 +2224,7 @@ class FTraceCallGraph: if(data.dmesg[p]['start'] <= self.start and self.start <= data.dmesg[p]['end']): list = data.dmesg[p]['list'] - for devname in list: + for devname in sorted(list, key=lambda k:list[k]['start']): dev = list[devname] if(pid == dev['pid'] and self.start <= dev['start'] and @@ -2350,6 +2529,9 @@ class TestProps: '(?P<H>[0-9]{2})(?P<M>[0-9]{2})(?P<S>[0-9]{2})'+\ ' (?P<host>.*) (?P<mode>.*) (?P<kernel>.*)$' batteryfmt = '^# battery (?P<a1>\w*) (?P<c1>\d*) (?P<a2>\w*) (?P<c2>\d*)' + wififmt = '^# wifi (?P<w>.*)' + tstatfmt = '^# turbostat (?P<t>\S*)' + mcelogfmt = '^# mcelog (?P<m>\S*)' testerrfmt = '^# enter_sleep_error (?P<e>.*)' sysinfofmt = '^# sysinfo .*' cmdlinefmt = '^# command \| (?P<cmd>.*)' @@ -2372,7 +2554,10 @@ class TestProps: self.cmdline = '' self.kparams = '' self.testerror = [] + self.mcelog = [] + self.turbostat = [] self.battery = [] + self.wifi = [] self.fwdata = [] self.ftrace_line_fmt = self.ftrace_line_fmt_nop self.cgformat = False @@ -2386,6 +2571,44 @@ class TestProps: self.ftrace_line_fmt = self.ftrace_line_fmt_nop else: doError('Invalid tracer format: [%s]' % tracer) + def decode(self, data): + try: + out = base64.b64decode(data).decode('zlib') + except: + out = data + return out + def stampInfo(self, line): + if re.match(self.stampfmt, line): + self.stamp = line + return True + elif re.match(self.sysinfofmt, line): + self.sysinfo = line + return True + elif re.match(self.kparamsfmt, line): + self.kparams = line + return True + elif re.match(self.cmdlinefmt, line): + self.cmdline = line + return True + elif re.match(self.mcelogfmt, line): + self.mcelog.append(line) + return True + elif re.match(self.tstatfmt, line): + self.turbostat.append(line) + return True + elif re.match(self.batteryfmt, line): + self.battery.append(line) + return True + elif re.match(self.wififmt, line): + self.wifi.append(line) + return True + elif re.match(self.testerrfmt, line): + self.testerror.append(line) + return True + elif re.match(self.firmwarefmt, line): + self.fwdata.append(line) + return True + return False def parseStamp(self, data, sv): # global test data m = re.match(self.stampfmt, self.stamp) @@ -2428,14 +2651,31 @@ class TestProps: sv.stamp = data.stamp # firmware data if sv.suspendmode == 'mem' and len(self.fwdata) > data.testnumber: - data.fwSuspend, data.fwResume = self.fwdata[data.testnumber] - if(data.fwSuspend > 0 or data.fwResume > 0): - data.fwValid = True + m = re.match(self.firmwarefmt, self.fwdata[data.testnumber]) + if m: + data.fwSuspend, data.fwResume = int(m.group('s')), int(m.group('r')) + if(data.fwSuspend > 0 or data.fwResume > 0): + data.fwValid = True + # mcelog data + if len(self.mcelog) > data.testnumber: + m = re.match(self.mcelogfmt, self.mcelog[data.testnumber]) + if m: + data.mcelog = self.decode(m.group('m')) + # turbostat data + if len(self.turbostat) > data.testnumber: + m = re.match(self.tstatfmt, self.turbostat[data.testnumber]) + if m: + data.turbostat = m.group('t') # battery data if len(self.battery) > data.testnumber: m = re.match(self.batteryfmt, self.battery[data.testnumber]) if m: data.battery = m.groups() + # wifi data + if len(self.wifi) > data.testnumber: + m = re.match(self.wififmt, self.wifi[data.testnumber]) + if m: + data.wifi = m.group('w') # sleep mode enter errors if len(self.testerror) > data.testnumber: m = re.match(self.testerrfmt, self.testerror[data.testnumber]) @@ -2505,9 +2745,9 @@ class ProcessMonitor: # Quickly determine if the ftrace log has all of the trace events, # markers, and/or kprobes required for primary parsing. def doesTraceLogHaveTraceEvents(): - kpcheck = ['_cal: (', '_cpu_down()'] + kpcheck = ['_cal: (', '_ret: ('] techeck = ['suspend_resume', 'device_pm_callback'] - tmcheck = ['tracing_mark_write'] + tmcheck = ['SUSPEND START', 'RESUME COMPLETE'] sysvals.usekprobes = False fp = sysvals.openlog(sysvals.ftracefile, 'r') for line in fp: @@ -2556,21 +2796,7 @@ def appendIncompleteTraceLog(testruns): for line in tf: # remove any latent carriage returns line = line.replace('\r\n', '') - # grab the stamp and sysinfo - if re.match(tp.stampfmt, line): - tp.stamp = line - continue - elif re.match(tp.sysinfofmt, line): - tp.sysinfo = line - continue - elif re.match(tp.cmdlinefmt, line): - tp.cmdline = line - continue - elif re.match(tp.batteryfmt, line): - tp.battery.append(line) - continue - elif re.match(tp.testerrfmt, line): - tp.testerror.append(line) + if tp.stampInfo(line): continue # determine the trace data type (required for further parsing) m = re.match(tp.tracertypefmt, line) @@ -2693,26 +2919,7 @@ def parseTraceLog(live=False): for line in tf: # remove any latent carriage returns line = line.replace('\r\n', '') - # stamp and sysinfo lines - if re.match(tp.stampfmt, line): - tp.stamp = line - continue - elif re.match(tp.sysinfofmt, line): - tp.sysinfo = line - continue - elif re.match(tp.cmdlinefmt, line): - tp.cmdline = line - continue - elif re.match(tp.batteryfmt, line): - tp.battery.append(line) - continue - elif re.match(tp.testerrfmt, line): - tp.testerror.append(line) - continue - # firmware line: pull out any firmware data - m = re.match(tp.firmwarefmt, line) - if(m): - tp.fwdata.append((int(m.group('s')), int(m.group('r')))) + if tp.stampInfo(line): continue # tracer type line: determine the trace data type m = re.match(tp.tracertypefmt, line) @@ -2925,7 +3132,7 @@ def parseTraceLog(live=False): tp.ktemp[key].append({ 'pid': pid, 'begin': t.time, - 'end': t.time, + 'end': -1, 'name': displayname, 'cdata': kprobedata, 'proc': m_proc, @@ -2936,12 +3143,11 @@ def parseTraceLog(live=False): elif(t.freturn): if(key not in tp.ktemp) or len(tp.ktemp[key]) < 1: continue - e = tp.ktemp[key][-1] - if e['begin'] < 0.0 or t.time - e['begin'] < 0.000001: - tp.ktemp[key].pop() - else: - e['end'] = t.time - e['rdata'] = kprobedata + e = next((x for x in reversed(tp.ktemp[key]) if x['end'] < 0), 0) + if not e: + continue + e['end'] = t.time + e['rdata'] = kprobedata # end of kernel resume if(phase != 'suspend_prepare' and kprobename in krescalls): if phase in data.dmesg: @@ -2963,8 +3169,10 @@ def parseTraceLog(live=False): if(res == -1): testrun.ftemp[key][-1].addLine(t) tf.close() + if len(testdata) < 1: + sysvals.vprint('WARNING: ftrace start marker is missing') if data and not data.devicegroups: - sysvals.vprint('WARNING: end marker is missing') + sysvals.vprint('WARNING: ftrace end marker is missing') data.handleEndMarker(t.time) if sysvals.suspendmode == 'command': @@ -3013,9 +3221,11 @@ def parseTraceLog(live=False): name, pid = key if name not in sysvals.tracefuncs: continue + if pid not in data.devpids: + data.devpids.append(pid) for e in tp.ktemp[key]: kb, ke = e['begin'], e['end'] - if kb == ke or tlb > kb or tle <= kb: + if ke - kb < 0.000001 or tlb > kb or tle <= kb: continue color = sysvals.kprobeColor(name) data.newActionGlobal(e['name'], kb, ke, pid, color) @@ -3027,7 +3237,7 @@ def parseTraceLog(live=False): continue for e in tp.ktemp[key]: kb, ke = e['begin'], e['end'] - if kb == ke or tlb > kb or tle <= kb: + if ke - kb < 0.000001 or tlb > kb or tle <= kb: continue data.addDeviceFunctionCall(e['name'], name, e['proc'], pid, kb, ke, e['cdata'], e['rdata']) @@ -3051,7 +3261,7 @@ def parseTraceLog(live=False): if not devname: sortkey = '%f%f%d' % (cg.start, cg.end, pid) sortlist[sortkey] = cg - elif len(cg.list) > 1000000: + elif len(cg.list) > 1000000 and cg.name != sysvals.ftopfunc: sysvals.vprint('WARNING: the callgraph for %s is massive (%d lines)' %\ (devname, len(cg.list))) # create blocks for orphan cg data @@ -3133,25 +3343,7 @@ def loadKernelLog(): idx = line.find('[') if idx > 1: line = line[idx:] - # grab the stamp and sysinfo - if re.match(tp.stampfmt, line): - tp.stamp = line - continue - elif re.match(tp.sysinfofmt, line): - tp.sysinfo = line - continue - elif re.match(tp.cmdlinefmt, line): - tp.cmdline = line - continue - elif re.match(tp.batteryfmt, line): - tp.battery.append(line) - continue - elif re.match(tp.testerrfmt, line): - tp.testerror.append(line) - continue - m = re.match(tp.firmwarefmt, line) - if(m): - tp.fwdata.append((int(m.group('s')), int(m.group('r')))) + if tp.stampInfo(line): continue m = re.match('[ \t]*(\[ *)(?P<ktime>[0-9\.]*)(\]) (?P<msg>.*)', line) if(not m): @@ -3176,7 +3368,7 @@ def loadKernelLog(): if data: testruns.append(data) if len(testruns) < 1: - pprint('ERROR: dmesg log has no suspend/resume data: %s' \ + doError('dmesg log has no suspend/resume data: %s' \ % sysvals.dmesgfile) # fix lines with same timestamp/function with the call and return swapped @@ -3515,6 +3707,8 @@ def addCallgraphs(sv, hf, data): name += ' '+p if('ftrace' in dev): cg = dev['ftrace'] + if cg.name == sv.ftopfunc: + name = 'top level suspend/resume call' num = callgraphHTML(sv, hf, num, cg, name, color, dev['id']) if('ftraces' in dev): @@ -3523,22 +3717,16 @@ def addCallgraphs(sv, hf, data): name+' → '+cg.name, color, dev['id']) hf.write('\n\n </section>\n') -# Function: createHTMLSummarySimple -# Description: -# Create summary html file for a series of tests -# Arguments: -# testruns: array of Data objects from parseTraceLog -def createHTMLSummarySimple(testruns, htmlfile, title): - # write the html header first (html head, css code, up to body start) - html = '<!DOCTYPE html>\n<html>\n<head>\n\ +def summaryCSS(title, center=True): + tdcenter = 'text-align:center;' if center else '' + out = '<!DOCTYPE html>\n<html>\n<head>\n\ <meta http-equiv="content-type" content="text/html; charset=UTF-8">\n\ - <title>SleepGraph Summary</title>\n\ + <title>'+title+'</title>\n\ <style type=\'text/css\'>\n\ .stamp {width: 100%;text-align:center;background:#888;line-height:30px;color:white;font: 25px Arial;}\n\ - table {width:100%;border-collapse: collapse;}\n\ - .summary {border:1px solid;}\n\ + table {width:100%;border-collapse: collapse;border:1px solid;}\n\ th {border: 1px solid black;background:#222;color:white;}\n\ - td {font: 14px "Times New Roman";text-align: center;}\n\ + td {font: 14px "Times New Roman";'+tdcenter+'}\n\ tr.head td {border: 1px solid black;background:#aaa;}\n\ tr.alt {background-color:#ddd;}\n\ tr.notice {color:red;}\n\ @@ -3547,12 +3735,23 @@ def createHTMLSummarySimple(testruns, htmlfile, title): .maxval {background-color:#FFBBBB;}\n\ .head a {color:#000;text-decoration: none;}\n\ </style>\n</head>\n<body>\n' + return out + +# Function: createHTMLSummarySimple +# Description: +# Create summary html file for a series of tests +# Arguments: +# testruns: array of Data objects from parseTraceLog +def createHTMLSummarySimple(testruns, htmlfile, title): + # write the html header first (html head, css code, up to body start) + html = summaryCSS('Summary - SleepGraph') # extract the test data into list list = dict() - tAvg, tMin, tMax, tMed = [0.0, 0.0], [0.0, 0.0], [0.0, 0.0], [[], []] + tAvg, tMin, tMax, tMed = [0.0, 0.0], [0.0, 0.0], [0.0, 0.0], [dict(), dict()] iMin, iMed, iMax = [0, 0], [0, 0], [0, 0] num = 0 + useturbo = False lastmode = '' cnt = dict() for data in sorted(testruns, key=lambda v:(v['mode'], v['host'], v['kernel'], v['time'])): @@ -3563,27 +3762,35 @@ def createHTMLSummarySimple(testruns, htmlfile, title): for i in range(2): s = sorted(tMed[i]) list[lastmode]['med'][i] = s[int(len(s)/2)] - iMed[i] = tMed[i].index(list[lastmode]['med'][i]) + iMed[i] = tMed[i][list[lastmode]['med'][i]] list[lastmode]['avg'] = [tAvg[0] / num, tAvg[1] / num] list[lastmode]['min'] = tMin list[lastmode]['max'] = tMax list[lastmode]['idx'] = (iMin, iMed, iMax) - tAvg, tMin, tMax, tMed = [0.0, 0.0], [0.0, 0.0], [0.0, 0.0], [[], []] + tAvg, tMin, tMax, tMed = [0.0, 0.0], [0.0, 0.0], [0.0, 0.0], [dict(), dict()] iMin, iMed, iMax = [0, 0], [0, 0], [0, 0] num = 0 + pkgpc10 = syslpi = '' + if 'pkgpc10' in data and 'syslpi' in data: + pkgpc10 = data['pkgpc10'] + syslpi = data['syslpi'] + useturbo = True + res = data['result'] tVal = [float(data['suspend']), float(data['resume'])] list[mode]['data'].append([data['host'], data['kernel'], - data['time'], tVal[0], tVal[1], data['url'], data['result'], + data['time'], tVal[0], tVal[1], data['url'], res, data['issues'], data['sus_worst'], data['sus_worsttime'], - data['res_worst'], data['res_worsttime']]) + data['res_worst'], data['res_worsttime'], pkgpc10, syslpi]) idx = len(list[mode]['data']) - 1 - if data['result'] not in cnt: - cnt[data['result']] = 1 + if res.startswith('fail in'): + res = 'fail' + if res not in cnt: + cnt[res] = 1 else: - cnt[data['result']] += 1 - if data['result'] == 'pass': + cnt[res] += 1 + if res == 'pass': for i in range(2): - tMed[i].append(tVal[i]) + tMed[i][tVal[i]] = idx tAvg[i] += tVal[i] if tMin[i] == 0 or tVal[i] < tMin[i]: iMin[i] = idx @@ -3597,7 +3804,7 @@ def createHTMLSummarySimple(testruns, htmlfile, title): for i in range(2): s = sorted(tMed[i]) list[lastmode]['med'][i] = s[int(len(s)/2)] - iMed[i] = tMed[i].index(list[lastmode]['med'][i]) + iMed[i] = tMed[i][list[lastmode]['med'][i]] list[lastmode]['avg'] = [tAvg[0] / num, tAvg[1] / num] list[lastmode]['min'] = tMin list[lastmode]['max'] = tMax @@ -3613,19 +3820,21 @@ def createHTMLSummarySimple(testruns, htmlfile, title): td = '\t<td>{0}</td>\n' tdh = '\t<td{1}>{0}</td>\n' tdlink = '\t<td><a href="{0}">html</a></td>\n' + colspan = '14' if useturbo else '12' # table header - html += '<table class="summary">\n<tr>\n' + th.format('#') +\ + html += '<table>\n<tr>\n' + th.format('#') +\ th.format('Mode') + th.format('Host') + th.format('Kernel') +\ th.format('Test Time') + th.format('Result') + th.format('Issues') +\ th.format('Suspend') + th.format('Resume') +\ th.format('Worst Suspend Device') + th.format('SD Time') +\ - th.format('Worst Resume Device') + th.format('RD Time') +\ - th.format('Detail') + '</tr>\n' - + th.format('Worst Resume Device') + th.format('RD Time') + if useturbo: + html += th.format('PkgPC10') + th.format('SysLPI') + html += th.format('Detail')+'</tr>\n' # export list into html head = '<tr class="head"><td>{0}</td><td>{1}</td>'+\ - '<td colspan=12 class="sus">Suspend Avg={2} '+\ + '<td colspan='+colspan+' class="sus">Suspend Avg={2} '+\ '<span class=minval><a href="#s{10}min">Min={3}</a></span> '+\ '<span class=medval><a href="#s{10}med">Med={4}</a></span> '+\ '<span class=maxval><a href="#s{10}max">Max={5}</a></span> '+\ @@ -3634,7 +3843,8 @@ def createHTMLSummarySimple(testruns, htmlfile, title): '<span class=medval><a href="#r{10}med">Med={8}</a></span> '+\ '<span class=maxval><a href="#r{10}max">Max={9}</a></span></td>'+\ '</tr>\n' - headnone = '<tr class="head"><td>{0}</td><td>{1}</td><td colspan=12></td></tr>\n' + headnone = '<tr class="head"><td>{0}</td><td>{1}</td><td colspan='+\ + colspan+'></td></tr>\n' for mode in list: # header line for each suspend mode num = 0 @@ -3681,6 +3891,9 @@ def createHTMLSummarySimple(testruns, htmlfile, title): html += td.format('%.3f ms' % d[9]) if d[9] else td.format('') # sus_worst time html += td.format(d[10]) # res_worst html += td.format('%.3f ms' % d[11]) if d[11] else td.format('') # res_worst time + if useturbo: + html += td.format(d[12]) # pkg_pc10 + html += td.format(d[13]) # syslpi html += tdlink.format(d[5]) if d[5] else td.format('') # url html += '</tr>\n' num += 1 @@ -3690,6 +3903,115 @@ def createHTMLSummarySimple(testruns, htmlfile, title): hf.write(html+'</table>\n</body>\n</html>\n') hf.close() +def createHTMLDeviceSummary(testruns, htmlfile, title): + html = summaryCSS('Device Summary - SleepGraph', False) + + # create global device list from all tests + devall = dict() + for data in testruns: + host, url, devlist = data['host'], data['url'], data['devlist'] + for type in devlist: + if type not in devall: + devall[type] = dict() + mdevlist, devlist = devall[type], data['devlist'][type] + for name in devlist: + length = devlist[name] + if name not in mdevlist: + mdevlist[name] = {'name': name, 'host': host, + 'worst': length, 'total': length, 'count': 1, + 'url': url} + else: + if length > mdevlist[name]['worst']: + mdevlist[name]['worst'] = length + mdevlist[name]['url'] = url + mdevlist[name]['host'] = host + mdevlist[name]['total'] += length + mdevlist[name]['count'] += 1 + + # generate the html + th = '\t<th>{0}</th>\n' + td = '\t<td align=center>{0}</td>\n' + tdr = '\t<td align=right>{0}</td>\n' + tdlink = '\t<td align=center><a href="{0}">html</a></td>\n' + limit = 1 + for type in sorted(devall, reverse=True): + num = 0 + devlist = devall[type] + # table header + html += '<div class="stamp">%s (%s devices > %d ms)</div><table>\n' % \ + (title, type.upper(), limit) + html += '<tr>\n' + '<th align=right>Device Name</th>' +\ + th.format('Average Time') + th.format('Count') +\ + th.format('Worst Time') + th.format('Host (worst time)') +\ + th.format('Link (worst time)') + '</tr>\n' + for name in sorted(devlist, key=lambda k:devlist[k]['worst'], reverse=True): + data = devall[type][name] + data['average'] = data['total'] / data['count'] + if data['average'] < limit: + continue + # row classes - alternate row color + rcls = ['alt'] if num % 2 == 1 else [] + html += '<tr class="'+(' '.join(rcls))+'">\n' if len(rcls) > 0 else '<tr>\n' + html += tdr.format(data['name']) # name + html += td.format('%.3f ms' % data['average']) # average + html += td.format(data['count']) # count + html += td.format('%.3f ms' % data['worst']) # worst + html += td.format(data['host']) # host + html += tdlink.format(data['url']) # url + html += '</tr>\n' + num += 1 + html += '</table>\n' + + # flush the data to file + hf = open(htmlfile, 'w') + hf.write(html+'</body>\n</html>\n') + hf.close() + return devall + +def createHTMLIssuesSummary(testruns, issues, htmlfile, title, extra=''): + multihost = len([e for e in issues if len(e['urls']) > 1]) > 0 + html = summaryCSS('Issues Summary - SleepGraph', False) + total = len(testruns) + + # generate the html + th = '\t<th>{0}</th>\n' + td = '\t<td align={0}>{1}</td>\n' + tdlink = '<a href="{1}">{0}</a>' + subtitle = '%d issues' % len(issues) if len(issues) > 0 else 'no issues' + html += '<div class="stamp">%s (%s)</div><table>\n' % (title, subtitle) + html += '<tr>\n' + th.format('Issue') + th.format('Count') + if multihost: + html += th.format('Hosts') + html += th.format('Tests') + th.format('Fail Rate') +\ + th.format('First Instance') + '</tr>\n' + + num = 0 + for e in sorted(issues, key=lambda v:v['count'], reverse=True): + testtotal = 0 + links = [] + for host in sorted(e['urls']): + links.append(tdlink.format(host, e['urls'][host][0])) + testtotal += len(e['urls'][host]) + rate = '%d/%d (%.2f%%)' % (testtotal, total, 100*float(testtotal)/float(total)) + # row classes - alternate row color + rcls = ['alt'] if num % 2 == 1 else [] + html += '<tr class="'+(' '.join(rcls))+'">\n' if len(rcls) > 0 else '<tr>\n' + html += td.format('left', e['line']) # issue + html += td.format('center', e['count']) # count + if multihost: + html += td.format('center', len(e['urls'])) # hosts + html += td.format('center', testtotal) # test count + html += td.format('center', rate) # test rate + html += td.format('center nowrap', '<br>'.join(links)) # links + html += '</tr>\n' + num += 1 + + # flush the data to file + hf = open(htmlfile, 'w') + hf.write(html+'</table>\n'+extra+'</body>\n</html>\n') + hf.close() + return issues + def ordinal(value): suffix = 'th' if value < 10 or value > 19: @@ -3991,7 +4313,7 @@ def createHTML(testruns, testfail): for word in phase.split('_'): id += word[0] order = '%.2f' % ((p['order'] * pdelta) + pmargin) - name = string.replace(phase, '_', ' ') + name = phase.replace('_', ' ') devtl.html += devtl.html_legend.format(order, p['color'], name, id) devtl.html += '</div>\n' @@ -4580,6 +4902,7 @@ def setRuntimeSuspend(before=True): def executeSuspend(): pm = ProcessMonitor() tp = sysvals.tpath + wifi = sysvals.checkWifi() testdata = [] battery = True if getBattery() else False # run these commands to prepare the system for suspend @@ -4613,6 +4936,7 @@ def executeSuspend(): pprint('SUSPEND START') else: pprint('SUSPEND START (press a key to resume)') + sysvals.mcelog(True) bat1 = getBattery() if battery else False # set rtcwake if(sysvals.rtcwake): @@ -4644,13 +4968,23 @@ def executeSuspend(): pf = open(sysvals.diskpowerfile, 'w') pf.write(sysvals.diskmode) pf.close() - pf = open(sysvals.powerfile, 'w') - pf.write(mode) - # execution will pause here - try: - pf.close() - except Exception as e: - tdata['error'] = str(e) + if mode == 'freeze' and sysvals.haveTurbostat(): + # execution will pause here + turbo = sysvals.turbostat() + if '|' in turbo: + tdata['turbo'] = turbo + else: + tdata['error'] = turbo + else: + if sysvals.haveTurbostat(): + sysvals.vprint('WARNING: ignoring turbostat in mode "%s"' % mode) + pf = open(sysvals.powerfile, 'w') + pf.write(mode) + # execution will pause here + try: + pf.close() + except Exception as e: + tdata['error'] = str(e) if(sysvals.rtcwake): sysvals.rtcWakeAlarmOff() # postdelay delay @@ -4664,9 +4998,14 @@ def executeSuspend(): sysvals.fsetVal('RESUME COMPLETE', 'trace_marker') if(sysvals.suspendmode == 'mem' or sysvals.suspendmode == 'command'): tdata['fw'] = getFPDT(False) + mcelog = sysvals.mcelog() + if mcelog: + tdata['mcelog'] = mcelog bat2 = getBattery() if battery else False if battery and bat1 and bat2: tdata['bat'] = (bat1, bat2) + if 'device' in wifi and 'ip' in wifi: + tdata['wifi'] = (wifi, sysvals.checkWifi()) testdata.append(tdata) # stop ftrace if(sysvals.usecallgraph or sysvals.usetraceevents): @@ -4686,6 +5025,7 @@ def executeSuspend(): op.close() sysvals.fsetVal('', 'trace') devProps() + return testdata def readFile(file): if os.path.islink(file): @@ -4772,7 +5112,7 @@ def deviceInfo(output=''): ms2nice(power['runtime_active_time']), \ ms2nice(power['runtime_suspended_time'])) for i in sorted(lines): - print lines[i] + print(lines[i]) return res # Function: devProps @@ -4905,12 +5245,12 @@ def getModes(): modes = [] if(os.path.exists(sysvals.powerfile)): fp = open(sysvals.powerfile, 'r') - modes = string.split(fp.read()) + modes = fp.read().split() fp.close() if(os.path.exists(sysvals.mempowerfile)): deep = False fp = open(sysvals.mempowerfile, 'r') - for m in string.split(fp.read()): + for m in fp.read().split(): memmode = m.strip('[]') if memmode == 'deep': deep = True @@ -4921,7 +5261,7 @@ def getModes(): modes.remove('mem') if('disk' in modes and os.path.exists(sysvals.diskpowerfile)): fp = open(sysvals.diskpowerfile, 'r') - for m in string.split(fp.read()): + for m in fp.read().split(): modes.append('disk-%s' % m.strip('[]')) fp.close() return modes @@ -4984,14 +5324,15 @@ def dmidecode(mempath, fatal=False): continue # read in the memory for scanning - fp = open(mempath, 'rb') try: + fp = open(mempath, 'rb') fp.seek(memaddr) buf = fp.read(memsize) except: if(fatal): doError('DMI table is unreachable, sorry') else: + pprint('WARNING: /dev/mem is not readable, ignoring DMI data') return out fp.close() @@ -5014,14 +5355,15 @@ def dmidecode(mempath, fatal=False): return out # read in the SM or DMI table - fp = open(mempath, 'rb') try: + fp = open(mempath, 'rb') fp.seek(base) buf = fp.read(length) except: if(fatal): doError('DMI table is unreachable, sorry') else: + pprint('WARNING: /dev/mem is not readable, ignoring DMI data') return out fp.close() @@ -5165,7 +5507,11 @@ def getFPDT(output): i = 0 fwData = [0, 0] records = buf[36:] - fp = open(sysvals.mempath, 'rb') + try: + fp = open(sysvals.mempath, 'rb') + except: + pprint('WARNING: /dev/mem is not readable, ignoring the FPDT data') + return False while(i < len(records)): header = struct.unpack('HBB', records[i:i+4]) if(header[0] not in rectype): @@ -5282,13 +5628,14 @@ def statusCheck(probecheck=False): pprint(' is ftrace supported: %s' % res) # check if kprobes are available - res = sysvals.colorText('NO') - sysvals.usekprobes = sysvals.verifyKprobes() - if(sysvals.usekprobes): - res = 'YES' - else: - sysvals.usedevsrc = False - pprint(' are kprobes supported: %s' % res) + if sysvals.usekprobes: + res = sysvals.colorText('NO') + sysvals.usekprobes = sysvals.verifyKprobes() + if(sysvals.usekprobes): + res = 'YES' + else: + sysvals.usedevsrc = False + pprint(' are kprobes supported: %s' % res) # what data source are we using res = 'DMESG' @@ -5376,6 +5723,8 @@ def getArgFloat(name, args, min, max, main=True): def processData(live=False): pprint('PROCESSING DATA') + sysvals.vprint('usetraceevents=%s, usetracemarkers=%s, usekprobes=%s' % \ + (sysvals.usetraceevents, sysvals.usetracemarkers, sysvals.usekprobes)) error = '' if(sysvals.usetraceevents): testruns, error = parseTraceLog(live) @@ -5388,13 +5737,36 @@ def processData(live=False): parseKernelLog(data) if(sysvals.ftracefile and (sysvals.usecallgraph or sysvals.usetraceevents)): appendIncompleteTraceLog(testruns) + sysvals.vprint('System Info:') + for key in sorted(sysvals.stamp): + sysvals.vprint(' %-8s : %s' % (key.upper(), sysvals.stamp[key])) + if sysvals.kparams: + sysvals.vprint('Kparams:\n %s' % sysvals.kparams) sysvals.vprint('Command:\n %s' % sysvals.cmdline) for data in testruns: + if data.mcelog: + sysvals.vprint('MCELOG Data:') + for line in data.mcelog.split('\n'): + sysvals.vprint(' %s' % line) + if data.turbostat: + idx, s = 0, 'Turbostat:\n ' + for val in data.turbostat.split('|'): + idx += len(val) + 1 + if idx >= 80: + idx = 0 + s += '\n ' + s += val + ' ' + sysvals.vprint(s) if data.battery: a1, c1, a2, c2 = data.battery s = 'Battery:\n Before - AC: %s, Charge: %d\n After - AC: %s, Charge: %d' % \ (a1, int(c1), a2, int(c2)) sysvals.vprint(s) + if data.wifi: + w = data.wifi.replace('|', ' ').split(',') + s = 'Wifi:\n Before %s\n After %s' % \ + (w[0], w[1]) + sysvals.vprint(s) data.printDetails() if sysvals.cgdump: for data in testruns: @@ -5418,12 +5790,15 @@ def processData(live=False): # Function: rerunTest # Description: # generate an output from an existing set of ftrace/dmesg logs -def rerunTest(): +def rerunTest(htmlfile=''): if sysvals.ftracefile: doesTraceLogHaveTraceEvents() if not sysvals.dmesgfile and not sysvals.usetraceevents: doError('recreating this html output requires a dmesg file') - sysvals.setOutputFile() + if htmlfile: + sysvals.htmlfile = htmlfile + else: + sysvals.setOutputFile() if os.path.exists(sysvals.htmlfile): if not os.path.isfile(sysvals.htmlfile): doError('a directory already exists with this name: %s' % sysvals.htmlfile) @@ -5442,14 +5817,18 @@ def runTest(n=0): sysvals.initTestOutput('suspend') # execute the test - executeSuspend() + testdata = executeSuspend() sysvals.cleanupFtrace() if sysvals.skiphtml: sysvals.sudoUserchown(sysvals.testdir) return - testruns, stamp = processData(True) - for data in testruns: - del data + if not testdata[0]['error']: + testruns, stamp = processData(True) + for data in testruns: + del data + else: + stamp = testdata[0] + sysvals.sudoUserchown(sysvals.testdir) sysvals.outputResult(stamp, n) if 'error' in stamp: @@ -5479,10 +5858,13 @@ def find_in_html(html, start, end, firstonly=True): return '' return out -def data_from_html(file, outpath, devlist=False): +def data_from_html(file, outpath, issues, fulldetail=False): html = open(file, 'r').read() + sysvals.htmlfile = os.path.relpath(file, outpath) + # extract general info suspend = find_in_html(html, 'Kernel Suspend', 'ms') resume = find_in_html(html, 'Kernel Resume', 'ms') + sysinfo = find_in_html(html, '<div class="stamp sysinfo">', '</div>') line = find_in_html(html, '<div class="stamp">', '</div>') stmp = line.split() if not suspend or not resume or len(stmp) != 8: @@ -5491,6 +5873,7 @@ def data_from_html(file, outpath, devlist=False): dt = datetime.strptime(' '.join(stmp[3:]), '%B %d %Y, %I:%M:%S %p') except: return False + sysvals.hostname = stmp[0] tstr = dt.strftime('%Y/%m/%d %H:%M:%S') error = find_in_html(html, '<table class="testfail"><tr><td>', '</td>') if error: @@ -5501,13 +5884,45 @@ def data_from_html(file, outpath, devlist=False): result = 'fail' else: result = 'pass' + # extract error info ilist = [] - e = find_in_html(html, 'class="err"[\w=":;\.%\- ]*>', '→</div>', False) - for i in list(set(e)): - ilist.append('%sx%d' % (i, e.count(i)) if e.count(i) > 1 else i) + extra = dict() + log = find_in_html(html, '<div id="dmesglog" style="display:none;">', + '</div>').strip() + if log: + d = Data(0) + d.end = 999999999 + d.dmesgtext = log.split('\n') + msglist = d.extractErrorInfo() + for msg in msglist: + sysvals.errorSummary(issues, msg) + if stmp[2] == 'freeze': + extra = d.turbostatInfo() + elist = dict() + for dir in d.errorinfo: + for err in d.errorinfo[dir]: + if err[0] not in elist: + elist[err[0]] = 0 + elist[err[0]] += 1 + for i in elist: + ilist.append('%sx%d' % (i, elist[i]) if elist[i] > 1 else i) low = find_in_html(html, 'freeze time: <b>', ' ms</b>') if low and '|' in low: - ilist.append('FREEZEx%d' % len(low.split('|'))) + issue = 'FREEZEx%d' % len(low.split('|')) + match = [i for i in issues if i['match'] == issue] + if len(match) > 0: + match[0]['count'] += 1 + if sysvals.hostname not in match[0]['urls']: + match[0]['urls'][sysvals.hostname] = [sysvals.htmlfile] + elif sysvals.htmlfile not in match[0]['urls'][sysvals.hostname]: + match[0]['urls'][sysvals.hostname].append(sysvals.htmlfile) + else: + issues.append({ + 'match': issue, 'count': 1, 'line': issue, + 'urls': {sysvals.hostname: [sysvals.htmlfile]}, + }) + ilist.append(issue) + # extract device info devices = dict() for line in html.split('\n'): m = re.match(' *<div id=\"[a,0-9]*\" *title=\"(?P<title>.*)\" class=\"thread.*', line) @@ -5519,82 +5934,98 @@ def data_from_html(file, outpath, devlist=False): name, time, phase = m.group('n'), m.group('t'), m.group('p') if ' async' in name or ' sync' in name: name = ' '.join(name.split(' ')[:-1]) - d = phase.split('_')[0] + if phase.startswith('suspend'): + d = 'suspend' + elif phase.startswith('resume'): + d = 'resume' + else: + continue if d not in devices: devices[d] = dict() if name not in devices[d]: devices[d][name] = 0.0 devices[d][name] += float(time) - worst = {'suspend': {'name':'', 'time': 0.0}, - 'resume': {'name':'', 'time': 0.0}} - for d in devices: - if d not in worst: - worst[d] = dict() - dev = devices[d] - if len(dev.keys()) > 0: + # create worst device info + worst = dict() + for d in ['suspend', 'resume']: + worst[d] = {'name':'', 'time': 0.0} + dev = devices[d] if d in devices else 0 + if dev and len(dev.keys()) > 0: n = sorted(dev, key=dev.get, reverse=True)[0] worst[d]['name'], worst[d]['time'] = n, dev[n] data = { 'mode': stmp[2], 'host': stmp[0], 'kernel': stmp[1], + 'sysinfo': sysinfo, 'time': tstr, 'result': result, 'issues': ' '.join(ilist), 'suspend': suspend, 'resume': resume, + 'devlist': devices, 'sus_worst': worst['suspend']['name'], 'sus_worsttime': worst['suspend']['time'], 'res_worst': worst['resume']['name'], 'res_worsttime': worst['resume']['time'], - 'url': os.path.relpath(file, outpath), + 'url': sysvals.htmlfile, } - if devlist: - data['devlist'] = devices + for key in extra: + data[key] = extra[key] + if fulldetail: + data['funclist'] = find_in_html(html, '<div title="', '" class="traceevent"', False) return data +def genHtml(subdir): + for dirname, dirnames, filenames in os.walk(subdir): + sysvals.dmesgfile = sysvals.ftracefile = sysvals.htmlfile = '' + for filename in filenames: + if(re.match('.*_dmesg.txt', filename)): + sysvals.dmesgfile = os.path.join(dirname, filename) + elif(re.match('.*_ftrace.txt', filename)): + sysvals.ftracefile = os.path.join(dirname, filename) + sysvals.setOutputFile() + if sysvals.ftracefile and sysvals.htmlfile and \ + not os.path.exists(sysvals.htmlfile): + pprint('FTRACE: %s' % sysvals.ftracefile) + if sysvals.dmesgfile: + pprint('DMESG : %s' % sysvals.dmesgfile) + rerunTest() + # Function: runSummary # Description: # create a summary of tests in a sub-directory def runSummary(subdir, local=True, genhtml=False): inpath = os.path.abspath(subdir) outpath = os.path.abspath('.') if local else inpath - pprint('Generating a summary of folder "%s"' % inpath) + pprint('Generating a summary of folder:\n %s' % inpath) if genhtml: - for dirname, dirnames, filenames in os.walk(subdir): - sysvals.dmesgfile = sysvals.ftracefile = sysvals.htmlfile = '' - for filename in filenames: - if(re.match('.*_dmesg.txt', filename)): - sysvals.dmesgfile = os.path.join(dirname, filename) - elif(re.match('.*_ftrace.txt', filename)): - sysvals.ftracefile = os.path.join(dirname, filename) - sysvals.setOutputFile() - if sysvals.ftracefile and sysvals.htmlfile and \ - not os.path.exists(sysvals.htmlfile): - pprint('FTRACE: %s' % sysvals.ftracefile) - if sysvals.dmesgfile: - pprint('DMESG : %s' % sysvals.dmesgfile) - rerunTest() + genHtml(subdir) + issues = [] testruns = [] desc = {'host':[],'mode':[],'kernel':[]} for dirname, dirnames, filenames in os.walk(subdir): for filename in filenames: if(not re.match('.*.html', filename)): continue - data = data_from_html(os.path.join(dirname, filename), outpath) + data = data_from_html(os.path.join(dirname, filename), outpath, issues) if(not data): continue testruns.append(data) for key in desc: if data[key] not in desc[key]: desc[key].append(data[key]) - outfile = os.path.join(outpath, 'summary.html') - pprint('Summary file: %s' % outfile) + pprint('Summary files:') if len(desc['host']) == len(desc['mode']) == len(desc['kernel']) == 1: title = '%s %s %s' % (desc['host'][0], desc['kernel'][0], desc['mode'][0]) else: title = inpath - createHTMLSummarySimple(testruns, outfile, title) + createHTMLSummarySimple(testruns, os.path.join(outpath, 'summary.html'), title) + pprint(' summary.html - tabular list of test data found') + createHTMLDeviceSummary(testruns, os.path.join(outpath, 'summary-devices.html'), title) + pprint(' summary-devices.html - kernel device list sorted by total execution time') + createHTMLIssuesSummary(testruns, issues, os.path.join(outpath, 'summary-issues.html'), title) + pprint(' summary-issues.html - kernel issues found sorted by frequency') # Function: checkArgBool # Description: @@ -5839,6 +6270,7 @@ def printHelp(): ' default: suspend-{date}-{time}\n'\ ' -rtcwake t Wakeup t seconds after suspend, set t to "off" to disable (default: 15)\n'\ ' -addlogs Add the dmesg and ftrace logs to the html output\n'\ + ' -turbostat Use turbostat to execute the command in freeze mode (default: disabled)\n'\ ' -srgap Add a visible gap in the timeline between sus/res (default: disabled)\n'\ ' -skiphtml Run the test and capture the trace logs, but skip the timeline (default: disabled)\n'\ ' -result fn Export a results table to a text file for parsing.\n'\ @@ -5860,6 +6292,7 @@ def printHelp(): ' be created in a new subdirectory with a summary page.\n'\ ' [debug]\n'\ ' -f Use ftrace to create device callgraphs (default: disabled)\n'\ + ' -ftop Use ftrace on the top level call: "%s" (default: disabled)\n'\ ' -maxdepth N limit the callgraph data to N call levels (default: 0=all)\n'\ ' -expandcg pre-expand the callgraph data in the html output (default: disabled)\n'\ ' -fadd file Add functions to be graphed in the timeline from a list in a text file\n'\ @@ -5879,6 +6312,7 @@ def printHelp(): ' -status Test to see if the system is enabled to run this tool\n'\ ' -fpdt Print out the contents of the ACPI Firmware Performance Data Table\n'\ ' -battery Print out battery info (if available)\n'\ + ' -wifi Print out wifi connection info (if wireless-tools and device exists)\n'\ ' -x<mode> Test xset by toggling the given mode (on/off/standby/suspend)\n'\ ' -sysinfo Print out system info extracted from BIOS\n'\ ' -devinfo Print out the pm settings of all devices which support runtime suspend\n'\ @@ -5888,7 +6322,7 @@ def printHelp(): ' [redo]\n'\ ' -ftrace ftracefile Create HTML output using ftrace input (used with -dmesg)\n'\ ' -dmesg dmesgfile Create HTML output using dmesg (used with -ftrace)\n'\ - '' % (sysvals.title, sysvals.version, sysvals.suspendmode)) + '' % (sysvals.title, sysvals.version, sysvals.suspendmode, sysvals.ftopfunc)) return True # ----------------- MAIN -------------------- @@ -5898,7 +6332,7 @@ if __name__ == '__main__': cmd = '' simplecmds = ['-sysinfo', '-modes', '-fpdt', '-flist', '-flistall', '-devinfo', '-status', '-battery', '-xon', '-xoff', '-xstandby', - '-xsuspend', '-xinit', '-xreset', '-xstat'] + '-xsuspend', '-xinit', '-xreset', '-xstat', '-wifi'] if '-f' in sys.argv: sysvals.cgskip = sysvals.configFile('cgskip.txt') # loop through the command line arguments @@ -5930,6 +6364,10 @@ if __name__ == '__main__': sysvals.postdelay = getArgInt('-postdelay', args, 0, 60000) elif(arg == '-f'): sysvals.usecallgraph = True + elif(arg == '-ftop'): + sysvals.usecallgraph = True + sysvals.ftop = True + sysvals.usekprobes = False elif(arg == '-skiphtml'): sysvals.skiphtml = True elif(arg == '-cgdump'): @@ -5940,10 +6378,16 @@ if __name__ == '__main__': genhtml = True elif(arg == '-addlogs'): sysvals.dmesglog = sysvals.ftracelog = True + elif(arg == '-nologs'): + sysvals.dmesglog = sysvals.ftracelog = False elif(arg == '-addlogdmesg'): sysvals.dmesglog = True elif(arg == '-addlogftrace'): sysvals.ftracelog = True + elif(arg == '-turbostat'): + sysvals.tstat = True + if not sysvals.haveTurbostat(): + doError('Turbostat command not found') elif(arg == '-verbose'): sysvals.verbose = True elif(arg == '-proc'): @@ -6013,6 +6457,12 @@ if __name__ == '__main__': except: doError('No callgraph functions supplied', True) sysvals.setCallgraphFilter(val) + elif(arg == '-skipkprobe'): + try: + val = args.next() + except: + doError('No kprobe functions supplied', True) + sysvals.skipKprobes(val) elif(arg == '-cgskip'): try: val = args.next() @@ -6151,7 +6601,7 @@ if __name__ == '__main__': elif(cmd == 'devinfo'): deviceInfo() elif(cmd == 'modes'): - print getModes() + pprint(getModes()) elif(cmd == 'flist'): sysvals.getFtraceFilterFunctions(True) elif(cmd == 'flistall'): @@ -6163,11 +6613,18 @@ if __name__ == '__main__': ret = displayControl(cmd[1:]) elif(cmd == 'xstat'): pprint('Display Status: %s' % displayControl('stat').upper()) + elif(cmd == 'wifi'): + out = sysvals.checkWifi() + if 'device' not in out: + pprint('WIFI interface not found') + else: + for key in sorted(out): + pprint('%6s: %s' % (key.upper(), out[key])) sys.exit(ret) # if instructed, re-analyze existing data files if(sysvals.notestrun): - stamp = rerunTest() + stamp = rerunTest(sysvals.outdir) sysvals.outputResult(stamp) sys.exit(0) @@ -6204,7 +6661,7 @@ if __name__ == '__main__': s = 'suspend-x%d' % sysvals.multitest['count'] sysvals.outdir = datetime.now().strftime(s+'-%y%m%d-%H%M%S') if not os.path.isdir(sysvals.outdir): - os.mkdir(sysvals.outdir) + os.makedirs(sysvals.outdir) for i in range(sysvals.multitest['count']): if(i != 0): pprint('Waiting %d seconds...' % (sysvals.multitest['delay'])) diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c index 698c08f851b8..8995092d541e 100644 --- a/tools/testing/radix-tree/idr-test.c +++ b/tools/testing/radix-tree/idr-test.c @@ -279,6 +279,51 @@ static void idr_align_test(struct idr *idr) } } +DEFINE_IDR(find_idr); + +static void *idr_throbber(void *arg) +{ + time_t start = time(NULL); + int id = *(int *)arg; + + rcu_register_thread(); + do { + idr_alloc(&find_idr, xa_mk_value(id), id, id + 1, GFP_KERNEL); + idr_remove(&find_idr, id); + } while (time(NULL) < start + 10); + rcu_unregister_thread(); + + return NULL; +} + +void idr_find_test_1(int anchor_id, int throbber_id) +{ + pthread_t throbber; + time_t start = time(NULL); + + pthread_create(&throbber, NULL, idr_throbber, &throbber_id); + + BUG_ON(idr_alloc(&find_idr, xa_mk_value(anchor_id), anchor_id, + anchor_id + 1, GFP_KERNEL) != anchor_id); + + do { + int id = 0; + void *entry = idr_get_next(&find_idr, &id); + BUG_ON(entry != xa_mk_value(id)); + } while (time(NULL) < start + 11); + + pthread_join(throbber, NULL); + + idr_remove(&find_idr, anchor_id); + BUG_ON(!idr_is_empty(&find_idr)); +} + +void idr_find_test(void) +{ + idr_find_test_1(100000, 0); + idr_find_test_1(0, 100000); +} + void idr_checks(void) { unsigned long i; @@ -360,6 +405,7 @@ void idr_checks(void) idr_u32_test(1); idr_u32_test(0); idr_align_test(&idr); + idr_find_test(); } #define module_init(x) diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore index ba919308fe30..d503b8764a8e 100644 --- a/tools/testing/selftests/powerpc/mm/.gitignore +++ b/tools/testing/selftests/powerpc/mm/.gitignore @@ -3,4 +3,5 @@ subpage_prot tempfile prot_sao segv_errors -wild_bctr
\ No newline at end of file +wild_bctr +large_vm_fork_separation
\ No newline at end of file diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile index 43d68420e363..f1fbc15800c4 100644 --- a/tools/testing/selftests/powerpc/mm/Makefile +++ b/tools/testing/selftests/powerpc/mm/Makefile @@ -2,7 +2,8 @@ noarg: $(MAKE) -C ../ -TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr +TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr \ + large_vm_fork_separation TEST_GEN_FILES := tempfile top_srcdir = ../../../../.. @@ -13,6 +14,7 @@ $(TEST_GEN_PROGS): ../harness.c $(OUTPUT)/prot_sao: ../utils.c $(OUTPUT)/wild_bctr: CFLAGS += -m64 +$(OUTPUT)/large_vm_fork_separation: CFLAGS += -m64 $(OUTPUT)/tempfile: dd if=/dev/zero of=$@ bs=64k count=1 diff --git a/tools/testing/selftests/powerpc/mm/large_vm_fork_separation.c b/tools/testing/selftests/powerpc/mm/large_vm_fork_separation.c new file mode 100644 index 000000000000..2363a7f3ab0d --- /dev/null +++ b/tools/testing/selftests/powerpc/mm/large_vm_fork_separation.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0+ +// +// Copyright 2019, Michael Ellerman, IBM Corp. +// +// Test that allocating memory beyond the memory limit and then forking is +// handled correctly, ie. the child is able to access the mappings beyond the +// memory limit and the child's writes are not visible to the parent. + +#include <stdio.h> +#include <stdlib.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "utils.h" + + +#ifndef MAP_FIXED_NOREPLACE +#define MAP_FIXED_NOREPLACE MAP_FIXED // "Should be safe" above 512TB +#endif + + +static int test(void) +{ + int p2c[2], c2p[2], rc, status, c, *p; + unsigned long page_size; + pid_t pid; + + page_size = sysconf(_SC_PAGESIZE); + SKIP_IF(page_size != 65536); + + // Create a mapping at 512TB to allocate an extended_id + p = mmap((void *)(512ul << 40), page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED_NOREPLACE, -1, 0); + if (p == MAP_FAILED) { + perror("mmap"); + printf("Error: couldn't mmap(), confirm kernel has 4TB support?\n"); + return 1; + } + + printf("parent writing %p = 1\n", p); + *p = 1; + + FAIL_IF(pipe(p2c) == -1 || pipe(c2p) == -1); + + pid = fork(); + if (pid == 0) { + FAIL_IF(read(p2c[0], &c, 1) != 1); + + pid = getpid(); + printf("child writing %p = %d\n", p, pid); + *p = pid; + + FAIL_IF(write(c2p[1], &c, 1) != 1); + FAIL_IF(read(p2c[0], &c, 1) != 1); + exit(0); + } + + c = 0; + FAIL_IF(write(p2c[1], &c, 1) != 1); + FAIL_IF(read(c2p[0], &c, 1) != 1); + + // Prevent compiler optimisation + barrier(); + + rc = 0; + printf("parent reading %p = %d\n", p, *p); + if (*p != 1) { + printf("Error: BUG! parent saw child's write! *p = %d\n", *p); + rc = 1; + } + + FAIL_IF(write(p2c[1], &c, 1) != 1); + FAIL_IF(waitpid(pid, &status, 0) == -1); + FAIL_IF(!WIFEXITED(status) || WEXITSTATUS(status)); + + if (rc == 0) + printf("success: test completed OK\n"); + + return rc; +} + +int main(void) +{ + return test_harness(test, "large_vm_fork_separation"); +} |