diff options
Diffstat (limited to 'arch')
122 files changed, 1878 insertions, 885 deletions
diff --git a/arch/arc/Kconfig.debug b/arch/arc/Kconfig.debug index a7fc0da25650..ff6a4b5ce927 100644 --- a/arch/arc/Kconfig.debug +++ b/arch/arc/Kconfig.debug @@ -2,19 +2,6 @@ menu "Kernel hacking" source "lib/Kconfig.debug" -config EARLY_PRINTK - bool "Early printk" if EMBEDDED - default y - help - Write kernel log output directly into the VGA buffer or to a serial - port. - - This is useful for kernel debugging when your machine crashes very - early before the console code is initialized. For normal operation - it is not recommended because it looks ugly and doesn't cooperate - with klogd/syslogd or the X server. You should normally N here, - unless you want to debug such a crash. - config 16KSTACKS bool "Use 16Kb for kernel stacks instead of 8Kb" help diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 067551b6920a..9917a45fc430 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -99,7 +99,7 @@ static inline void atomic_##op(int i, atomic_t *v) \ atomic_ops_unlock(flags); \ } -#define ATOMIC_OP_RETURN(op, c_op) \ +#define ATOMIC_OP_RETURN(op, c_op, asm_op) \ static inline int atomic_##op##_return(int i, atomic_t *v) \ { \ unsigned long flags; \ diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c index 8c3a3e02ba92..12b2100db073 100644 --- a/arch/arc/mm/cache_arc700.c +++ b/arch/arc/mm/cache_arc700.c @@ -266,7 +266,7 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr, * Machine specific helpers for Entire D-Cache or Per Line ops */ -static unsigned int __before_dc_op(const int op) +static inline unsigned int __before_dc_op(const int op) { unsigned int reg = reg; @@ -284,7 +284,7 @@ static unsigned int __before_dc_op(const int op) return reg; } -static void __after_dc_op(const int op, unsigned int reg) +static inline void __after_dc_op(const int op, unsigned int reg) { if (op & OP_FLUSH) /* flush / flush-n-inv both wait */ while (read_aux_reg(ARC_REG_DC_CTRL) & DC_CTRL_FLUSH_STATUS); diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index 86217db2937a..992736b5229b 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -223,7 +223,7 @@ dtb-$(CONFIG_SOC_IMX25) += \ imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dtb \ imx25-karo-tx25.dtb \ imx25-pdk.dtb -dtb-$(CONFIG_SOC_IMX31) += \ +dtb-$(CONFIG_SOC_IMX27) += \ imx27-apf27.dtb \ imx27-apf27dev.dtb \ imx27-eukrea-mbimxsd27-baseboard.dtb \ diff --git a/arch/arm/boot/dts/armada-375.dtsi b/arch/arm/boot/dts/armada-375.dtsi index c675257f2377..f076ff856d8b 100644 --- a/arch/arm/boot/dts/armada-375.dtsi +++ b/arch/arm/boot/dts/armada-375.dtsi @@ -69,7 +69,7 @@ mainpll: mainpll { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <2000000000>; + clock-frequency = <1000000000>; }; /* 25 MHz reference crystal */ refclk: oscillator { diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi index ed2dd8ba4080..218a2acd36e5 100644 --- a/arch/arm/boot/dts/armada-38x.dtsi +++ b/arch/arm/boot/dts/armada-38x.dtsi @@ -585,7 +585,7 @@ mainpll: mainpll { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <2000000000>; + clock-frequency = <1000000000>; }; /* 25 MHz reference crystal */ diff --git a/arch/arm/boot/dts/armada-39x.dtsi b/arch/arm/boot/dts/armada-39x.dtsi index 0e85fc15ceda..ecd1318109ba 100644 --- a/arch/arm/boot/dts/armada-39x.dtsi +++ b/arch/arm/boot/dts/armada-39x.dtsi @@ -502,7 +502,7 @@ mainpll: mainpll { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <2000000000>; + clock-frequency = <1000000000>; }; }; }; diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts index e3b08fb959e5..990e8a2100f0 100644 --- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts +++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts @@ -105,6 +105,10 @@ }; internal-regs { + rtc@10300 { + /* No crystal connected to the internal RTC */ + status = "disabled"; + }; serial@12000 { status = "okay"; }; diff --git a/arch/arm/boot/dts/dove-cubox.dts b/arch/arm/boot/dts/dove-cubox.dts index aae7efc09b0b..e6fa251e17b9 100644 --- a/arch/arm/boot/dts/dove-cubox.dts +++ b/arch/arm/boot/dts/dove-cubox.dts @@ -87,6 +87,7 @@ /* connect xtal input to 25MHz reference */ clocks = <&ref25>; + clock-names = "xtal"; /* connect xtal input as source of pll0 and pll1 */ silabs,pll-source = <0 0>, <1 0>; diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi index 8de12af7c276..d6b49e5b32e9 100644 --- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi +++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi @@ -9,6 +9,7 @@ #include <dt-bindings/sound/samsung-i2s.h> #include <dt-bindings/input/input.h> +#include <dt-bindings/clock/maxim,max77686.h> #include "exynos4412.dtsi" / { @@ -105,6 +106,8 @@ rtc@10070000 { status = "okay"; + clocks = <&clock CLK_RTC>, <&max77686 MAX77686_CLK_AP>; + clock-names = "rtc", "rtc_src"; }; g2d@10800000 { diff --git a/arch/arm/boot/dts/exynos5250-snow.dts b/arch/arm/boot/dts/exynos5250-snow.dts index 2657e842e5a5..1eca97ee4bd6 100644 --- a/arch/arm/boot/dts/exynos5250-snow.dts +++ b/arch/arm/boot/dts/exynos5250-snow.dts @@ -567,6 +567,7 @@ num-slots = <1>; broken-cd; cap-sdio-irq; + keep-power-in-suspend; card-detect-delay = <200>; samsung,dw-mshc-ciu-div = <3>; samsung,dw-mshc-sdr-timing = <2 3>; diff --git a/arch/arm/boot/dts/exynos5420-peach-pit.dts b/arch/arm/boot/dts/exynos5420-peach-pit.dts index 0788d08fb43e..146e71118a72 100644 --- a/arch/arm/boot/dts/exynos5420-peach-pit.dts +++ b/arch/arm/boot/dts/exynos5420-peach-pit.dts @@ -711,6 +711,7 @@ num-slots = <1>; broken-cd; cap-sdio-irq; + keep-power-in-suspend; card-detect-delay = <200>; clock-frequency = <400000000>; samsung,dw-mshc-ciu-div = <1>; diff --git a/arch/arm/boot/dts/exynos5420-trip-points.dtsi b/arch/arm/boot/dts/exynos5420-trip-points.dtsi index 5d31fc140823..2180a0152c9b 100644 --- a/arch/arm/boot/dts/exynos5420-trip-points.dtsi +++ b/arch/arm/boot/dts/exynos5420-trip-points.dtsi @@ -28,7 +28,7 @@ trips { type = "active"; }; cpu-crit-0 { - temperature = <1200000>; /* millicelsius */ + temperature = <120000>; /* millicelsius */ hysteresis = <0>; /* millicelsius */ type = "critical"; }; diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi index f67b23f303c3..45317538bbae 100644 --- a/arch/arm/boot/dts/exynos5420.dtsi +++ b/arch/arm/boot/dts/exynos5420.dtsi @@ -536,6 +536,7 @@ clock-names = "dp"; phys = <&dp_phy>; phy-names = "dp"; + power-domains = <&disp_pd>; }; mipi_phy: video-phy@10040714 { diff --git a/arch/arm/boot/dts/exynos5440-trip-points.dtsi b/arch/arm/boot/dts/exynos5440-trip-points.dtsi index 48adfa8f4300..356e963edf11 100644 --- a/arch/arm/boot/dts/exynos5440-trip-points.dtsi +++ b/arch/arm/boot/dts/exynos5440-trip-points.dtsi @@ -18,7 +18,7 @@ trips { type = "active"; }; cpu-crit-0 { - temperature = <1050000>; /* millicelsius */ + temperature = <105000>; /* millicelsius */ hysteresis = <0>; /* millicelsius */ type = "critical"; }; diff --git a/arch/arm/boot/dts/exynos5800-peach-pi.dts b/arch/arm/boot/dts/exynos5800-peach-pi.dts index 412f41d62686..02eb8b15374f 100644 --- a/arch/arm/boot/dts/exynos5800-peach-pi.dts +++ b/arch/arm/boot/dts/exynos5800-peach-pi.dts @@ -674,6 +674,7 @@ num-slots = <1>; broken-cd; cap-sdio-irq; + keep-power-in-suspend; card-detect-delay = <200>; clock-frequency = <400000000>; samsung,dw-mshc-ciu-div = <1>; diff --git a/arch/arm/boot/dts/imx23-olinuxino.dts b/arch/arm/boot/dts/imx23-olinuxino.dts index 7e6eef2488e8..82045398bf1f 100644 --- a/arch/arm/boot/dts/imx23-olinuxino.dts +++ b/arch/arm/boot/dts/imx23-olinuxino.dts @@ -12,6 +12,7 @@ */ /dts-v1/; +#include <dt-bindings/gpio/gpio.h> #include "imx23.dtsi" / { @@ -93,6 +94,7 @@ ahb@80080000 { usb0: usb@80080000 { + dr_mode = "host"; vbus-supply = <®_usb0_vbus>; status = "okay"; }; @@ -122,7 +124,7 @@ user { label = "green"; - gpios = <&gpio2 1 1>; + gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>; }; }; }; diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi index e4d3aecc4ed2..677f81d9dcd5 100644 --- a/arch/arm/boot/dts/imx25.dtsi +++ b/arch/arm/boot/dts/imx25.dtsi @@ -428,6 +428,7 @@ pwm4: pwm@53fc8000 { compatible = "fsl,imx25-pwm", "fsl,imx27-pwm"; + #pwm-cells = <2>; reg = <0x53fc8000 0x4000>; clocks = <&clks 108>, <&clks 52>; clock-names = "ipg", "per"; diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi index 6951b66d1ab7..bc215e4b75fd 100644 --- a/arch/arm/boot/dts/imx27.dtsi +++ b/arch/arm/boot/dts/imx27.dtsi @@ -533,7 +533,7 @@ fec: ethernet@1002b000 { compatible = "fsl,imx27-fec"; - reg = <0x1002b000 0x4000>; + reg = <0x1002b000 0x1000>; interrupts = <50>; clocks = <&clks IMX27_CLK_FEC_IPG_GATE>, <&clks IMX27_CLK_FEC_AHB_GATE>; diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi index 25e25f82fbae..4e073e854742 100644 --- a/arch/arm/boot/dts/imx28.dtsi +++ b/arch/arm/boot/dts/imx28.dtsi @@ -913,7 +913,7 @@ 80 81 68 69 70 71 72 73 74 75 76 77>; - interrupt-names = "auart4-rx", "aurat4-tx", "spdif-tx", "empty", + interrupt-names = "auart4-rx", "auart4-tx", "spdif-tx", "empty", "saif0", "saif1", "i2c0", "i2c1", "auart0-rx", "auart0-tx", "auart1-rx", "auart1-tx", "auart2-rx", "auart2-tx", "auart3-rx", "auart3-tx"; diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi index 19cc269a08d4..1ce6133b67f5 100644 --- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi +++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi @@ -31,6 +31,7 @@ regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; gpio = <&gpio4 15 0>; + enable-active-high; }; reg_usb_h1_vbus: regulator@1 { @@ -40,6 +41,7 @@ regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; gpio = <&gpio1 0 0>; + enable-active-high; }; }; diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi index 46b2fed7c319..3b24b12651b2 100644 --- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi @@ -185,7 +185,6 @@ &i2c3 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c3>; - pinctrl-assert-gpios = <&gpio5 4 GPIO_ACTIVE_HIGH>; status = "okay"; max7310_a: gpio@30 { diff --git a/arch/arm/boot/dts/r8a7791-koelsch.dts b/arch/arm/boot/dts/r8a7791-koelsch.dts index 74c3212f1f11..824ddab9c3ad 100644 --- a/arch/arm/boot/dts/r8a7791-koelsch.dts +++ b/arch/arm/boot/dts/r8a7791-koelsch.dts @@ -545,7 +545,7 @@ compatible = "adi,adv7511w"; reg = <0x39>; interrupt-parent = <&gpio3>; - interrupts = <29 IRQ_TYPE_EDGE_FALLING>; + interrupts = <29 IRQ_TYPE_LEVEL_LOW>; adi,input-depth = <8>; adi,input-colorspace = "rgb"; diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi index bfd3f1c734b8..2201cd5da3bb 100644 --- a/arch/arm/boot/dts/ste-dbx5x0.dtsi +++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi @@ -1017,23 +1017,6 @@ status = "disabled"; }; - vmmci: regulator-gpio { - compatible = "regulator-gpio"; - - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <2900000>; - regulator-name = "mmci-reg"; - regulator-type = "voltage"; - - startup-delay-us = <100>; - enable-active-high; - - states = <1800000 0x1 - 2900000 0x0>; - - status = "disabled"; - }; - mcde@a0350000 { compatible = "stericsson,mcde"; reg = <0xa0350000 0x1000>, /* MCDE */ diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi index bf8f0eddc2c0..744c1e3a744d 100644 --- a/arch/arm/boot/dts/ste-href.dtsi +++ b/arch/arm/boot/dts/ste-href.dtsi @@ -111,6 +111,21 @@ pinctrl-1 = <&i2c3_sleep_mode>; }; + vmmci: regulator-gpio { + compatible = "regulator-gpio"; + + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <2900000>; + regulator-name = "mmci-reg"; + regulator-type = "voltage"; + + startup-delay-us = <100>; + enable-active-high; + + states = <1800000 0x1 + 2900000 0x0>; + }; + // External Micro SD slot sdi0_per1@80126000 { arm,primecell-periphid = <0x10480180>; diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts index 206826a855c0..1bc84ebdccaa 100644 --- a/arch/arm/boot/dts/ste-snowball.dts +++ b/arch/arm/boot/dts/ste-snowball.dts @@ -146,8 +146,21 @@ }; vmmci: regulator-gpio { + compatible = "regulator-gpio"; + gpios = <&gpio7 4 0x4>; enable-gpio = <&gpio6 25 0x4>; + + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <2900000>; + regulator-name = "mmci-reg"; + regulator-type = "voltage"; + + startup-delay-us = <100>; + enable-active-high; + + states = <1800000 0x1 + 2900000 0x0>; }; // External Micro SD slot diff --git a/arch/arm/boot/dts/tegra124.dtsi b/arch/arm/boot/dts/tegra124.dtsi index cf01c818b8ea..13cc7ca5e031 100644 --- a/arch/arm/boot/dts/tegra124.dtsi +++ b/arch/arm/boot/dts/tegra124.dtsi @@ -826,7 +826,7 @@ <&tegra_car TEGRA124_CLK_PLL_U>, <&tegra_car TEGRA124_CLK_USBD>; clock-names = "reg", "pll_u", "utmi-pads"; - resets = <&tegra_car 59>, <&tegra_car 22>; + resets = <&tegra_car 22>, <&tegra_car 22>; reset-names = "usb", "utmi-pads"; nvidia,hssync-start-delay = <0>; nvidia,idle-wait-delay = <17>; @@ -838,6 +838,7 @@ nvidia,hssquelch-level = <2>; nvidia,hsdiscon-level = <5>; nvidia,xcvr-hsslew = <12>; + nvidia,has-utmi-pad-registers; status = "disabled"; }; @@ -862,7 +863,7 @@ <&tegra_car TEGRA124_CLK_PLL_U>, <&tegra_car TEGRA124_CLK_USBD>; clock-names = "reg", "pll_u", "utmi-pads"; - resets = <&tegra_car 22>, <&tegra_car 22>; + resets = <&tegra_car 58>, <&tegra_car 22>; reset-names = "usb", "utmi-pads"; nvidia,hssync-start-delay = <0>; nvidia,idle-wait-delay = <17>; @@ -874,7 +875,6 @@ nvidia,hssquelch-level = <2>; nvidia,hsdiscon-level = <5>; nvidia,xcvr-hsslew = <12>; - nvidia,has-utmi-pad-registers; status = "disabled"; }; @@ -899,7 +899,7 @@ <&tegra_car TEGRA124_CLK_PLL_U>, <&tegra_car TEGRA124_CLK_USBD>; clock-names = "reg", "pll_u", "utmi-pads"; - resets = <&tegra_car 58>, <&tegra_car 22>; + resets = <&tegra_car 59>, <&tegra_car 22>; reset-names = "usb", "utmi-pads"; nvidia,hssync-start-delay = <0>; nvidia,idle-wait-delay = <17>; diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts index 7a2aeacd62c0..107395c32d82 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts @@ -191,6 +191,7 @@ compatible = "arm,cortex-a15-pmu"; interrupts = <0 68 4>, <0 69 4>; + interrupt-affinity = <&cpu0>, <&cpu1>; }; oscclk6a: oscclk6a { diff --git a/arch/arm/boot/dts/vexpress-v2p-ca9.dts b/arch/arm/boot/dts/vexpress-v2p-ca9.dts index 23662b5a5e9d..d949facba376 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca9.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca9.dts @@ -33,28 +33,28 @@ #address-cells = <1>; #size-cells = <0>; - cpu@0 { + A9_0: cpu@0 { device_type = "cpu"; compatible = "arm,cortex-a9"; reg = <0>; next-level-cache = <&L2>; }; - cpu@1 { + A9_1: cpu@1 { device_type = "cpu"; compatible = "arm,cortex-a9"; reg = <1>; next-level-cache = <&L2>; }; - cpu@2 { + A9_2: cpu@2 { device_type = "cpu"; compatible = "arm,cortex-a9"; reg = <2>; next-level-cache = <&L2>; }; - cpu@3 { + A9_3: cpu@3 { device_type = "cpu"; compatible = "arm,cortex-a9"; reg = <3>; @@ -170,6 +170,7 @@ compatible = "arm,pl310-cache"; reg = <0x1e00a000 0x1000>; interrupts = <0 43 4>; + cache-unified; cache-level = <2>; arm,data-latency = <1 1 1>; arm,tag-latency = <1 1 1>; @@ -181,6 +182,8 @@ <0 61 4>, <0 62 4>, <0 63 4>; + interrupt-affinity = <&A9_0>, <&A9_1>, <&A9_2>, <&A9_3>; + }; dcc { diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index ab86655c1f4b..0ca4a3eaf65d 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -39,11 +39,14 @@ CONFIG_ARCH_HIP04=y CONFIG_ARCH_KEYSTONE=y CONFIG_ARCH_MESON=y CONFIG_ARCH_MXC=y +CONFIG_SOC_IMX50=y CONFIG_SOC_IMX51=y CONFIG_SOC_IMX53=y CONFIG_SOC_IMX6Q=y CONFIG_SOC_IMX6SL=y +CONFIG_SOC_IMX6SX=y CONFIG_SOC_VF610=y +CONFIG_SOC_LS1021A=y CONFIG_ARCH_OMAP3=y CONFIG_ARCH_OMAP4=y CONFIG_SOC_OMAP5=y diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h index 8e3fcb924db6..2ef282f96651 100644 --- a/arch/arm/include/asm/dma-iommu.h +++ b/arch/arm/include/asm/dma-iommu.h @@ -25,7 +25,7 @@ struct dma_iommu_mapping { }; struct dma_iommu_mapping * -arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size); +arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, u64 size); void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping); diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h index 2f7e6ff67d51..0b579b2f4e0e 100644 --- a/arch/arm/include/asm/xen/page.h +++ b/arch/arm/include/asm/xen/page.h @@ -110,5 +110,6 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) bool xen_arch_need_swiotlb(struct device *dev, unsigned long pfn, unsigned long mfn); +unsigned long xen_get_swiotlb_free_pages(unsigned int order); #endif /* _ASM_ARM_XEN_PAGE_H */ diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c index 91c7ba182dcd..213919ba326f 100644 --- a/arch/arm/kernel/perf_event_cpu.c +++ b/arch/arm/kernel/perf_event_cpu.c @@ -303,12 +303,17 @@ static int probe_current_pmu(struct arm_pmu *pmu) static int of_pmu_irq_cfg(struct platform_device *pdev) { - int i; + int i, irq; int *irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL); if (!irqs) return -ENOMEM; + /* Don't bother with PPIs; they're already affine */ + irq = platform_get_irq(pdev, 0); + if (irq >= 0 && irq_is_percpu(irq)) + return 0; + for (i = 0; i < pdev->num_resources; ++i) { struct device_node *dn; int cpu; @@ -317,7 +322,7 @@ static int of_pmu_irq_cfg(struct platform_device *pdev) i); if (!dn) { pr_warn("Failed to parse %s/interrupt-affinity[%d]\n", - of_node_full_name(dn), i); + of_node_full_name(pdev->dev.of_node), i); break; } diff --git a/arch/arm/mach-exynos/common.h b/arch/arm/mach-exynos/common.h index acd5b560b728..5f5cd562c593 100644 --- a/arch/arm/mach-exynos/common.h +++ b/arch/arm/mach-exynos/common.h @@ -159,6 +159,8 @@ extern void exynos_enter_aftr(void); extern struct cpuidle_exynos_data cpuidle_coupled_exynos_data; +extern void exynos_set_delayed_reset_assertion(bool enable); + extern void s5p_init_cpu(void __iomem *cpuid_addr); extern unsigned int samsung_rev(void); extern void __iomem *cpu_boot_reg_base(void); diff --git a/arch/arm/mach-exynos/exynos.c b/arch/arm/mach-exynos/exynos.c index bcde0dd668df..5917a30eee33 100644 --- a/arch/arm/mach-exynos/exynos.c +++ b/arch/arm/mach-exynos/exynos.c @@ -167,6 +167,33 @@ static void __init exynos_init_io(void) } /* + * Set or clear the USE_DELAYED_RESET_ASSERTION option. Used by smp code + * and suspend. + * + * This is necessary only on Exynos4 SoCs. When system is running + * USE_DELAYED_RESET_ASSERTION should be set so the ARM CLK clock down + * feature could properly detect global idle state when secondary CPU is + * powered down. + * + * However this should not be set when such system is going into suspend. + */ +void exynos_set_delayed_reset_assertion(bool enable) +{ + if (of_machine_is_compatible("samsung,exynos4")) { + unsigned int tmp, core_id; + + for (core_id = 0; core_id < num_possible_cpus(); core_id++) { + tmp = pmu_raw_readl(EXYNOS_ARM_CORE_OPTION(core_id)); + if (enable) + tmp |= S5P_USE_DELAYED_RESET_ASSERTION; + else + tmp &= ~(S5P_USE_DELAYED_RESET_ASSERTION); + pmu_raw_writel(tmp, EXYNOS_ARM_CORE_OPTION(core_id)); + } + } +} + +/* * Apparently, these SoCs are not able to wake-up from suspend using * the PMU. Too bad. Should they suddenly become capable of such a * feat, the matches below should be moved to suspend.c. diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c index ebd135bb0995..a825bca2a2b6 100644 --- a/arch/arm/mach-exynos/platsmp.c +++ b/arch/arm/mach-exynos/platsmp.c @@ -34,30 +34,6 @@ extern void exynos4_secondary_startup(void); -/* - * Set or clear the USE_DELAYED_RESET_ASSERTION option, set on Exynos4 SoCs - * during hot-(un)plugging CPUx. - * - * The feature can be cleared safely during first boot of secondary CPU. - * - * Exynos4 SoCs require setting USE_DELAYED_RESET_ASSERTION during powering - * down a CPU so the CPU idle clock down feature could properly detect global - * idle state when CPUx is off. - */ -static void exynos_set_delayed_reset_assertion(u32 core_id, bool enable) -{ - if (soc_is_exynos4()) { - unsigned int tmp; - - tmp = pmu_raw_readl(EXYNOS_ARM_CORE_OPTION(core_id)); - if (enable) - tmp |= S5P_USE_DELAYED_RESET_ASSERTION; - else - tmp &= ~(S5P_USE_DELAYED_RESET_ASSERTION); - pmu_raw_writel(tmp, EXYNOS_ARM_CORE_OPTION(core_id)); - } -} - #ifdef CONFIG_HOTPLUG_CPU static inline void cpu_leave_lowpower(u32 core_id) { @@ -73,8 +49,6 @@ static inline void cpu_leave_lowpower(u32 core_id) : "=&r" (v) : "Ir" (CR_C), "Ir" (0x40) : "cc"); - - exynos_set_delayed_reset_assertion(core_id, false); } static inline void platform_do_lowpower(unsigned int cpu, int *spurious) @@ -87,14 +61,6 @@ static inline void platform_do_lowpower(unsigned int cpu, int *spurious) /* Turn the CPU off on next WFI instruction. */ exynos_cpu_power_down(core_id); - /* - * Exynos4 SoCs require setting - * USE_DELAYED_RESET_ASSERTION so the CPU idle - * clock down feature could properly detect - * global idle state when CPUx is off. - */ - exynos_set_delayed_reset_assertion(core_id, true); - wfi(); if (pen_release == core_id) { @@ -371,9 +337,6 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle) udelay(10); } - /* No harm if this is called during first boot of secondary CPU */ - exynos_set_delayed_reset_assertion(core_id, false); - /* * now the secondary core is starting up let it run its * calibrations, then wait for it to finish @@ -420,6 +383,8 @@ static void __init exynos_smp_prepare_cpus(unsigned int max_cpus) exynos_sysram_init(); + exynos_set_delayed_reset_assertion(true); + if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9) scu_enable(scu_base_addr()); diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c index cbe56b35aea0..a9686535f9ed 100644 --- a/arch/arm/mach-exynos/pm_domains.c +++ b/arch/arm/mach-exynos/pm_domains.c @@ -188,7 +188,7 @@ no_clk: args.np = np; args.args_count = 0; child_domain = of_genpd_get_from_provider(&args); - if (!child_domain) + if (IS_ERR(child_domain)) continue; if (of_parse_phandle_with_args(np, "power-domains", @@ -196,7 +196,7 @@ no_clk: continue; parent_domain = of_genpd_get_from_provider(&args); - if (!parent_domain) + if (IS_ERR(parent_domain)) continue; if (pm_genpd_add_subdomain(parent_domain, child_domain)) diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c index 3e6aea7f83af..c0b6dccbf7bd 100644 --- a/arch/arm/mach-exynos/suspend.c +++ b/arch/arm/mach-exynos/suspend.c @@ -342,6 +342,8 @@ static void exynos_pm_enter_sleep_mode(void) static void exynos_pm_prepare(void) { + exynos_set_delayed_reset_assertion(false); + /* Set wake-up mask registers */ exynos_pm_set_wakeup_mask(); @@ -482,6 +484,7 @@ early_wakeup: /* Clear SLEEP mode set in INFORM1 */ pmu_raw_writel(0x0, S5P_INFORM1); + exynos_set_delayed_reset_assertion(true); } static void exynos3250_pm_resume(void) @@ -723,8 +726,10 @@ void __init exynos_pm_init(void) return; } - if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL))) + if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL))) { pr_warn("Outdated DT detected, suspend/resume will NOT work\n"); + return; + } pm_data = (const struct exynos_pm_data *) match->data; diff --git a/arch/arm/mach-gemini/common.h b/arch/arm/mach-gemini/common.h index 38a45260a7c8..dd883698ff7e 100644 --- a/arch/arm/mach-gemini/common.h +++ b/arch/arm/mach-gemini/common.h @@ -12,6 +12,8 @@ #ifndef __GEMINI_COMMON_H__ #define __GEMINI_COMMON_H__ +#include <linux/reboot.h> + struct mtd_partition; extern void gemini_map_io(void); @@ -26,6 +28,6 @@ extern int platform_register_pflash(unsigned int size, struct mtd_partition *parts, unsigned int nr_parts); -extern void gemini_restart(char mode, const char *cmd); +extern void gemini_restart(enum reboot_mode mode, const char *cmd); #endif /* __GEMINI_COMMON_H__ */ diff --git a/arch/arm/mach-gemini/reset.c b/arch/arm/mach-gemini/reset.c index b26659759e27..21a6d6d4f9c4 100644 --- a/arch/arm/mach-gemini/reset.c +++ b/arch/arm/mach-gemini/reset.c @@ -14,7 +14,9 @@ #include <mach/hardware.h> #include <mach/global_reg.h> -void gemini_restart(char mode, const char *cmd) +#include "common.h" + +void gemini_restart(enum reboot_mode mode, const char *cmd) { __raw_writel(RESET_GLOBAL | RESET_CPU1, IO_ADDRESS(GEMINI_GLOBAL_BASE) + GLOBAL_RESET); diff --git a/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c b/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c index fb8d4a2ad48c..a5edd7d60266 100644 --- a/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c +++ b/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010 Pengutronix, Wolfram Sang <w.sang@pengutronix.de> + * Copyright (C) 2010 Pengutronix, Wolfram Sang <kernel@pengutronix.de> * * This program is free software; you can redistribute it and/or modify it under * the terms of the GNU General Public License version 2 as published by the diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig index 8896e71586f5..f09683687963 100644 --- a/arch/arm/mach-pxa/Kconfig +++ b/arch/arm/mach-pxa/Kconfig @@ -691,4 +691,13 @@ config SHARPSL_PM_MAX1111 config PXA310_ULPI bool +config PXA_SYSTEMS_CPLDS + tristate "Motherboard cplds" + default ARCH_LUBBOCK || MACH_MAINSTONE + help + This driver supports the Lubbock and Mainstone multifunction chip + found on the pxa25x development platform system (Lubbock) and pxa27x + development platform system (Mainstone). This IO board supports the + interrupts handling, ethernet controller, flash chips, etc ... + endif diff --git a/arch/arm/mach-pxa/Makefile b/arch/arm/mach-pxa/Makefile index eb0bf7678a99..4087d334ecdf 100644 --- a/arch/arm/mach-pxa/Makefile +++ b/arch/arm/mach-pxa/Makefile @@ -90,4 +90,5 @@ obj-$(CONFIG_MACH_RAUMFELD_CONNECTOR) += raumfeld.o obj-$(CONFIG_MACH_RAUMFELD_SPEAKER) += raumfeld.o obj-$(CONFIG_MACH_ZIPIT2) += z2.o +obj-$(CONFIG_PXA_SYSTEMS_CPLDS) += pxa_cplds_irqs.o obj-$(CONFIG_TOSA_BT) += tosa-bt.o diff --git a/arch/arm/mach-pxa/include/mach/lubbock.h b/arch/arm/mach-pxa/include/mach/lubbock.h index 958cd6af9384..1eecf794acd2 100644 --- a/arch/arm/mach-pxa/include/mach/lubbock.h +++ b/arch/arm/mach-pxa/include/mach/lubbock.h @@ -37,7 +37,9 @@ #define LUB_GP __LUB_REG(LUBBOCK_FPGA_PHYS + 0x100) /* Board specific IRQs */ -#define LUBBOCK_IRQ(x) (IRQ_BOARD_START + (x)) +#define LUBBOCK_NR_IRQS IRQ_BOARD_START + +#define LUBBOCK_IRQ(x) (LUBBOCK_NR_IRQS + (x)) #define LUBBOCK_SD_IRQ LUBBOCK_IRQ(0) #define LUBBOCK_SA1111_IRQ LUBBOCK_IRQ(1) #define LUBBOCK_USB_IRQ LUBBOCK_IRQ(2) /* usb connect */ @@ -47,8 +49,7 @@ #define LUBBOCK_USB_DISC_IRQ LUBBOCK_IRQ(6) /* usb disconnect */ #define LUBBOCK_LAST_IRQ LUBBOCK_IRQ(6) -#define LUBBOCK_SA1111_IRQ_BASE (IRQ_BOARD_START + 16) -#define LUBBOCK_NR_IRQS (IRQ_BOARD_START + 16 + 55) +#define LUBBOCK_SA1111_IRQ_BASE (LUBBOCK_NR_IRQS + 32) #ifndef __ASSEMBLY__ extern void lubbock_set_misc_wr(unsigned int mask, unsigned int set); diff --git a/arch/arm/mach-pxa/include/mach/mainstone.h b/arch/arm/mach-pxa/include/mach/mainstone.h index 1bfc4e822a41..e82a7d31104e 100644 --- a/arch/arm/mach-pxa/include/mach/mainstone.h +++ b/arch/arm/mach-pxa/include/mach/mainstone.h @@ -120,7 +120,9 @@ #define MST_PCMCIA_PWR_VCC_50 0x4 /* voltage VCC = 5.0V */ /* board specific IRQs */ -#define MAINSTONE_IRQ(x) (IRQ_BOARD_START + (x)) +#define MAINSTONE_NR_IRQS IRQ_BOARD_START + +#define MAINSTONE_IRQ(x) (MAINSTONE_NR_IRQS + (x)) #define MAINSTONE_MMC_IRQ MAINSTONE_IRQ(0) #define MAINSTONE_USIM_IRQ MAINSTONE_IRQ(1) #define MAINSTONE_USBC_IRQ MAINSTONE_IRQ(2) @@ -136,6 +138,4 @@ #define MAINSTONE_S1_STSCHG_IRQ MAINSTONE_IRQ(14) #define MAINSTONE_S1_IRQ MAINSTONE_IRQ(15) -#define MAINSTONE_NR_IRQS (IRQ_BOARD_START + 16) - #endif diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c index d8a1be619f21..4ac9ab80d24b 100644 --- a/arch/arm/mach-pxa/lubbock.c +++ b/arch/arm/mach-pxa/lubbock.c @@ -12,6 +12,7 @@ * published by the Free Software Foundation. */ #include <linux/gpio.h> +#include <linux/gpio/machine.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/init.h> @@ -123,84 +124,6 @@ void lubbock_set_misc_wr(unsigned int mask, unsigned int set) } EXPORT_SYMBOL(lubbock_set_misc_wr); -static unsigned long lubbock_irq_enabled; - -static void lubbock_mask_irq(struct irq_data *d) -{ - int lubbock_irq = (d->irq - LUBBOCK_IRQ(0)); - LUB_IRQ_MASK_EN = (lubbock_irq_enabled &= ~(1 << lubbock_irq)); -} - -static void lubbock_unmask_irq(struct irq_data *d) -{ - int lubbock_irq = (d->irq - LUBBOCK_IRQ(0)); - /* the irq can be acknowledged only if deasserted, so it's done here */ - LUB_IRQ_SET_CLR &= ~(1 << lubbock_irq); - LUB_IRQ_MASK_EN = (lubbock_irq_enabled |= (1 << lubbock_irq)); -} - -static struct irq_chip lubbock_irq_chip = { - .name = "FPGA", - .irq_ack = lubbock_mask_irq, - .irq_mask = lubbock_mask_irq, - .irq_unmask = lubbock_unmask_irq, -}; - -static void lubbock_irq_handler(unsigned int irq, struct irq_desc *desc) -{ - unsigned long pending = LUB_IRQ_SET_CLR & lubbock_irq_enabled; - do { - /* clear our parent irq */ - desc->irq_data.chip->irq_ack(&desc->irq_data); - if (likely(pending)) { - irq = LUBBOCK_IRQ(0) + __ffs(pending); - generic_handle_irq(irq); - } - pending = LUB_IRQ_SET_CLR & lubbock_irq_enabled; - } while (pending); -} - -static void __init lubbock_init_irq(void) -{ - int irq; - - pxa25x_init_irq(); - - /* setup extra lubbock irqs */ - for (irq = LUBBOCK_IRQ(0); irq <= LUBBOCK_LAST_IRQ; irq++) { - irq_set_chip_and_handler(irq, &lubbock_irq_chip, - handle_level_irq); - set_irq_flags(irq, IRQF_VALID | IRQF_PROBE); - } - - irq_set_chained_handler(PXA_GPIO_TO_IRQ(0), lubbock_irq_handler); - irq_set_irq_type(PXA_GPIO_TO_IRQ(0), IRQ_TYPE_EDGE_FALLING); -} - -#ifdef CONFIG_PM - -static void lubbock_irq_resume(void) -{ - LUB_IRQ_MASK_EN = lubbock_irq_enabled; -} - -static struct syscore_ops lubbock_irq_syscore_ops = { - .resume = lubbock_irq_resume, -}; - -static int __init lubbock_irq_device_init(void) -{ - if (machine_is_lubbock()) { - register_syscore_ops(&lubbock_irq_syscore_ops); - return 0; - } - return -ENODEV; -} - -device_initcall(lubbock_irq_device_init); - -#endif - static int lubbock_udc_is_connected(void) { return (LUB_MISC_RD & (1 << 9)) == 0; @@ -383,11 +306,38 @@ static struct platform_device lubbock_flash_device[2] = { }, }; +static struct resource lubbock_cplds_resources[] = { + [0] = { + .start = LUBBOCK_FPGA_PHYS + 0xc0, + .end = LUBBOCK_FPGA_PHYS + 0xe0 - 1, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = PXA_GPIO_TO_IRQ(0), + .end = PXA_GPIO_TO_IRQ(0), + .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_LOWEDGE, + }, + [2] = { + .start = LUBBOCK_IRQ(0), + .end = LUBBOCK_IRQ(6), + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device lubbock_cplds_device = { + .name = "pxa_cplds_irqs", + .id = -1, + .resource = &lubbock_cplds_resources[0], + .num_resources = 3, +}; + + static struct platform_device *devices[] __initdata = { &sa1111_device, &smc91x_device, &lubbock_flash_device[0], &lubbock_flash_device[1], + &lubbock_cplds_device, }; static struct pxafb_mode_info sharp_lm8v31_mode = { @@ -648,7 +598,7 @@ MACHINE_START(LUBBOCK, "Intel DBPXA250 Development Platform (aka Lubbock)") /* Maintainer: MontaVista Software Inc. */ .map_io = lubbock_map_io, .nr_irqs = LUBBOCK_NR_IRQS, - .init_irq = lubbock_init_irq, + .init_irq = pxa25x_init_irq, .handle_irq = pxa25x_handle_irq, .init_time = pxa_timer_init, .init_machine = lubbock_init, diff --git a/arch/arm/mach-pxa/mainstone.c b/arch/arm/mach-pxa/mainstone.c index 78b84c0dfc79..2c0658cf6be2 100644 --- a/arch/arm/mach-pxa/mainstone.c +++ b/arch/arm/mach-pxa/mainstone.c @@ -13,6 +13,7 @@ * published by the Free Software Foundation. */ #include <linux/gpio.h> +#include <linux/gpio/machine.h> #include <linux/init.h> #include <linux/platform_device.h> #include <linux/syscore_ops.h> @@ -122,92 +123,6 @@ static unsigned long mainstone_pin_config[] = { GPIO1_GPIO | WAKEUP_ON_EDGE_BOTH, }; -static unsigned long mainstone_irq_enabled; - -static void mainstone_mask_irq(struct irq_data *d) -{ - int mainstone_irq = (d->irq - MAINSTONE_IRQ(0)); - MST_INTMSKENA = (mainstone_irq_enabled &= ~(1 << mainstone_irq)); -} - -static void mainstone_unmask_irq(struct irq_data *d) -{ - int mainstone_irq = (d->irq - MAINSTONE_IRQ(0)); - /* the irq can be acknowledged only if deasserted, so it's done here */ - MST_INTSETCLR &= ~(1 << mainstone_irq); - MST_INTMSKENA = (mainstone_irq_enabled |= (1 << mainstone_irq)); -} - -static struct irq_chip mainstone_irq_chip = { - .name = "FPGA", - .irq_ack = mainstone_mask_irq, - .irq_mask = mainstone_mask_irq, - .irq_unmask = mainstone_unmask_irq, -}; - -static void mainstone_irq_handler(unsigned int irq, struct irq_desc *desc) -{ - unsigned long pending = MST_INTSETCLR & mainstone_irq_enabled; - do { - /* clear useless edge notification */ - desc->irq_data.chip->irq_ack(&desc->irq_data); - if (likely(pending)) { - irq = MAINSTONE_IRQ(0) + __ffs(pending); - generic_handle_irq(irq); - } - pending = MST_INTSETCLR & mainstone_irq_enabled; - } while (pending); -} - -static void __init mainstone_init_irq(void) -{ - int irq; - - pxa27x_init_irq(); - - /* setup extra Mainstone irqs */ - for(irq = MAINSTONE_IRQ(0); irq <= MAINSTONE_IRQ(15); irq++) { - irq_set_chip_and_handler(irq, &mainstone_irq_chip, - handle_level_irq); - if (irq == MAINSTONE_IRQ(10) || irq == MAINSTONE_IRQ(14)) - set_irq_flags(irq, IRQF_VALID | IRQF_PROBE | IRQF_NOAUTOEN); - else - set_irq_flags(irq, IRQF_VALID | IRQF_PROBE); - } - set_irq_flags(MAINSTONE_IRQ(8), 0); - set_irq_flags(MAINSTONE_IRQ(12), 0); - - MST_INTMSKENA = 0; - MST_INTSETCLR = 0; - - irq_set_chained_handler(PXA_GPIO_TO_IRQ(0), mainstone_irq_handler); - irq_set_irq_type(PXA_GPIO_TO_IRQ(0), IRQ_TYPE_EDGE_FALLING); -} - -#ifdef CONFIG_PM - -static void mainstone_irq_resume(void) -{ - MST_INTMSKENA = mainstone_irq_enabled; -} - -static struct syscore_ops mainstone_irq_syscore_ops = { - .resume = mainstone_irq_resume, -}; - -static int __init mainstone_irq_device_init(void) -{ - if (machine_is_mainstone()) - register_syscore_ops(&mainstone_irq_syscore_ops); - - return 0; -} - -device_initcall(mainstone_irq_device_init); - -#endif - - static struct resource smc91x_resources[] = { [0] = { .start = (MST_ETH_PHYS + 0x300), @@ -487,11 +402,37 @@ static struct platform_device mst_gpio_keys_device = { }, }; +static struct resource mst_cplds_resources[] = { + [0] = { + .start = MST_FPGA_PHYS + 0xc0, + .end = MST_FPGA_PHYS + 0xe0 - 1, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = PXA_GPIO_TO_IRQ(0), + .end = PXA_GPIO_TO_IRQ(0), + .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_LOWEDGE, + }, + [2] = { + .start = MAINSTONE_IRQ(0), + .end = MAINSTONE_IRQ(15), + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device mst_cplds_device = { + .name = "pxa_cplds_irqs", + .id = -1, + .resource = &mst_cplds_resources[0], + .num_resources = 3, +}; + static struct platform_device *platform_devices[] __initdata = { &smc91x_device, &mst_flash_device[0], &mst_flash_device[1], &mst_gpio_keys_device, + &mst_cplds_device, }; static struct pxaohci_platform_data mainstone_ohci_platform_data = { @@ -718,7 +659,7 @@ MACHINE_START(MAINSTONE, "Intel HCDDBBVA0 Development Platform (aka Mainstone)") .atag_offset = 0x100, /* BLOB boot parameter setting */ .map_io = mainstone_map_io, .nr_irqs = MAINSTONE_NR_IRQS, - .init_irq = mainstone_init_irq, + .init_irq = pxa27x_init_irq, .handle_irq = pxa27x_handle_irq, .init_time = pxa_timer_init, .init_machine = mainstone_init, diff --git a/arch/arm/mach-pxa/pxa_cplds_irqs.c b/arch/arm/mach-pxa/pxa_cplds_irqs.c new file mode 100644 index 000000000000..f1aeb54fabe3 --- /dev/null +++ b/arch/arm/mach-pxa/pxa_cplds_irqs.c @@ -0,0 +1,200 @@ +/* + * Intel Reference Systems cplds + * + * Copyright (C) 2014 Robert Jarzmik + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * Cplds motherboard driver, supporting lubbock and mainstone SoC board. + */ + +#include <linux/bitops.h> +#include <linux/gpio.h> +#include <linux/gpio/consumer.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/mfd/core.h> +#include <linux/module.h> +#include <linux/of_platform.h> + +#define FPGA_IRQ_MASK_EN 0x0 +#define FPGA_IRQ_SET_CLR 0x10 + +#define CPLDS_NB_IRQ 32 + +struct cplds { + void __iomem *base; + int irq; + unsigned int irq_mask; + struct gpio_desc *gpio0; + struct irq_domain *irqdomain; +}; + +static irqreturn_t cplds_irq_handler(int in_irq, void *d) +{ + struct cplds *fpga = d; + unsigned long pending; + unsigned int bit; + + pending = readl(fpga->base + FPGA_IRQ_SET_CLR) & fpga->irq_mask; + for_each_set_bit(bit, &pending, CPLDS_NB_IRQ) + generic_handle_irq(irq_find_mapping(fpga->irqdomain, bit)); + + return IRQ_HANDLED; +} + +static void cplds_irq_mask_ack(struct irq_data *d) +{ + struct cplds *fpga = irq_data_get_irq_chip_data(d); + unsigned int cplds_irq = irqd_to_hwirq(d); + unsigned int set, bit = BIT(cplds_irq); + + fpga->irq_mask &= ~bit; + writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN); + set = readl(fpga->base + FPGA_IRQ_SET_CLR); + writel(set & ~bit, fpga->base + FPGA_IRQ_SET_CLR); +} + +static void cplds_irq_unmask(struct irq_data *d) +{ + struct cplds *fpga = irq_data_get_irq_chip_data(d); + unsigned int cplds_irq = irqd_to_hwirq(d); + unsigned int bit = BIT(cplds_irq); + + fpga->irq_mask |= bit; + writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN); +} + +static struct irq_chip cplds_irq_chip = { + .name = "pxa_cplds", + .irq_mask_ack = cplds_irq_mask_ack, + .irq_unmask = cplds_irq_unmask, + .flags = IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_SKIP_SET_WAKE, +}; + +static int cplds_irq_domain_map(struct irq_domain *d, unsigned int irq, + irq_hw_number_t hwirq) +{ + struct cplds *fpga = d->host_data; + + irq_set_chip_and_handler(irq, &cplds_irq_chip, handle_level_irq); + irq_set_chip_data(irq, fpga); + + return 0; +} + +static const struct irq_domain_ops cplds_irq_domain_ops = { + .xlate = irq_domain_xlate_twocell, + .map = cplds_irq_domain_map, +}; + +static int cplds_resume(struct platform_device *pdev) +{ + struct cplds *fpga = platform_get_drvdata(pdev); + + writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN); + + return 0; +} + +static int cplds_probe(struct platform_device *pdev) +{ + struct resource *res; + struct cplds *fpga; + int ret; + unsigned int base_irq = 0; + unsigned long irqflags = 0; + + fpga = devm_kzalloc(&pdev->dev, sizeof(*fpga), GFP_KERNEL); + if (!fpga) + return -ENOMEM; + + res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + if (res) { + fpga->irq = (unsigned int)res->start; + irqflags = res->flags; + } + if (!fpga->irq) + return -ENODEV; + + base_irq = platform_get_irq(pdev, 1); + if (base_irq < 0) + base_irq = 0; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + fpga->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(fpga->base)) + return PTR_ERR(fpga->base); + + platform_set_drvdata(pdev, fpga); + + writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN); + writel(0, fpga->base + FPGA_IRQ_SET_CLR); + + ret = devm_request_irq(&pdev->dev, fpga->irq, cplds_irq_handler, + irqflags, dev_name(&pdev->dev), fpga); + if (ret == -ENOSYS) + return -EPROBE_DEFER; + + if (ret) { + dev_err(&pdev->dev, "couldn't request main irq%d: %d\n", + fpga->irq, ret); + return ret; + } + + irq_set_irq_wake(fpga->irq, 1); + fpga->irqdomain = irq_domain_add_linear(pdev->dev.of_node, + CPLDS_NB_IRQ, + &cplds_irq_domain_ops, fpga); + if (!fpga->irqdomain) + return -ENODEV; + + if (base_irq) { + ret = irq_create_strict_mappings(fpga->irqdomain, base_irq, 0, + CPLDS_NB_IRQ); + if (ret) { + dev_err(&pdev->dev, "couldn't create the irq mapping %d..%d\n", + base_irq, base_irq + CPLDS_NB_IRQ); + return ret; + } + } + + return 0; +} + +static int cplds_remove(struct platform_device *pdev) +{ + struct cplds *fpga = platform_get_drvdata(pdev); + + irq_set_chip_and_handler(fpga->irq, NULL, NULL); + + return 0; +} + +static const struct of_device_id cplds_id_table[] = { + { .compatible = "intel,lubbock-cplds-irqs", }, + { .compatible = "intel,mainstone-cplds-irqs", }, + { } +}; +MODULE_DEVICE_TABLE(of, cplds_id_table); + +static struct platform_driver cplds_driver = { + .driver = { + .name = "pxa_cplds_irqs", + .of_match_table = of_match_ptr(cplds_id_table), + }, + .probe = cplds_probe, + .remove = cplds_remove, + .resume = cplds_resume, +}; + +module_platform_driver(cplds_driver); + +MODULE_DESCRIPTION("PXA Cplds interrupts driver"); +MODULE_AUTHOR("Robert Jarzmik <robert.jarzmik@free.fr>"); +MODULE_LICENSE("GPL"); diff --git a/arch/arm/mach-rockchip/pm.c b/arch/arm/mach-rockchip/pm.c index b07d88602073..b0dcbe28f78c 100644 --- a/arch/arm/mach-rockchip/pm.c +++ b/arch/arm/mach-rockchip/pm.c @@ -83,6 +83,13 @@ static void rk3288_slp_mode_set(int level) SGRF_PCLK_WDT_GATE | SGRF_FAST_BOOT_EN | SGRF_PCLK_WDT_GATE_WRITE | SGRF_FAST_BOOT_EN_WRITE); + /* + * The dapswjdp can not auto reset before resume, that cause it may + * access some illegal address during resume. Let's disable it before + * suspend, and the MASKROM will enable it back. + */ + regmap_write(sgrf_regmap, RK3288_SGRF_CPU_CON0, SGRF_DAPDEVICEEN_WRITE); + /* booting address of resuming system is from this register value */ regmap_write(sgrf_regmap, RK3288_SGRF_FAST_BOOT_ADDR, rk3288_bootram_phy); diff --git a/arch/arm/mach-rockchip/pm.h b/arch/arm/mach-rockchip/pm.h index 03ff31d8282d..3e8d39c0c3d5 100644 --- a/arch/arm/mach-rockchip/pm.h +++ b/arch/arm/mach-rockchip/pm.h @@ -55,6 +55,10 @@ static inline void rockchip_suspend_init(void) #define SGRF_FAST_BOOT_EN BIT(8) #define SGRF_FAST_BOOT_EN_WRITE BIT(24) +#define RK3288_SGRF_CPU_CON0 (0x40) +#define SGRF_DAPDEVICEEN BIT(0) +#define SGRF_DAPDEVICEEN_WRITE BIT(16) + #define RK3288_CRU_MODE_CON 0x50 #define RK3288_CRU_SEL0_CON 0x60 #define RK3288_CRU_SEL1_CON 0x64 diff --git a/arch/arm/mach-rockchip/rockchip.c b/arch/arm/mach-rockchip/rockchip.c index d360ec044b66..b6cf3b449428 100644 --- a/arch/arm/mach-rockchip/rockchip.c +++ b/arch/arm/mach-rockchip/rockchip.c @@ -30,11 +30,30 @@ #include "pm.h" #define RK3288_GRF_SOC_CON0 0x244 +#define RK3288_TIMER6_7_PHYS 0xff810000 static void __init rockchip_timer_init(void) { if (of_machine_is_compatible("rockchip,rk3288")) { struct regmap *grf; + void __iomem *reg_base; + + /* + * Most/all uboot versions for rk3288 don't enable timer7 + * which is needed for the architected timer to work. + * So make sure it is running during early boot. + */ + reg_base = ioremap(RK3288_TIMER6_7_PHYS, SZ_16K); + if (reg_base) { + writel(0, reg_base + 0x30); + writel(0xffffffff, reg_base + 0x20); + writel(0xffffffff, reg_base + 0x24); + writel(1, reg_base + 0x30); + dsb(); + iounmap(reg_base); + } else { + pr_err("rockchip: could not map timer7 registers\n"); + } /* * Disable auto jtag/sdmmc switching that causes issues diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 09c5fe3d30c2..7e7583ddd607 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -1878,7 +1878,7 @@ struct dma_map_ops iommu_coherent_ops = { * arm_iommu_attach_device function. */ struct dma_iommu_mapping * -arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size) +arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, u64 size) { unsigned int bits = size >> PAGE_SHIFT; unsigned int bitmap_size = BITS_TO_LONGS(bits) * sizeof(long); @@ -1886,6 +1886,10 @@ arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size) int extensions = 1; int err = -ENOMEM; + /* currently only 32-bit DMA address space is supported */ + if (size > DMA_BIT_MASK(32) + 1) + return ERR_PTR(-ERANGE); + if (!bitmap_size) return ERR_PTR(-EINVAL); @@ -2057,13 +2061,6 @@ static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size, if (!iommu) return false; - /* - * currently arm_iommu_create_mapping() takes a max of size_t - * for size param. So check this limit for now. - */ - if (size > SIZE_MAX) - return false; - mapping = arm_iommu_create_mapping(dev->bus, dma_base, size); if (IS_ERR(mapping)) { pr_warn("Failed to create %llu-byte IOMMU mapping for device %s\n", diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S index aa0519eed698..774ef1323554 100644 --- a/arch/arm/mm/proc-arm1020.S +++ b/arch/arm/mm/proc-arm1020.S @@ -22,8 +22,6 @@ * * These are the low level assembler for performing cache and TLB * functions on the arm1020. - * - * CONFIG_CPU_ARM1020_CPU_IDLE -> nohlt */ #include <linux/linkage.h> #include <linux/init.h> diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S index bff4c7f70fd6..ae3c27b71594 100644 --- a/arch/arm/mm/proc-arm1020e.S +++ b/arch/arm/mm/proc-arm1020e.S @@ -22,8 +22,6 @@ * * These are the low level assembler for performing cache and TLB * functions on the arm1020e. - * - * CONFIG_CPU_ARM1020_CPU_IDLE -> nohlt */ #include <linux/linkage.h> #include <linux/init.h> diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S index ede8c54ab4aa..32a47cc19076 100644 --- a/arch/arm/mm/proc-arm925.S +++ b/arch/arm/mm/proc-arm925.S @@ -441,9 +441,6 @@ ENTRY(cpu_arm925_set_pte_ext) .type __arm925_setup, #function __arm925_setup: mov r0, #0 -#if defined(CONFIG_CPU_ICACHE_STREAMING_DISABLE) - orr r0,r0,#1 << 7 -#endif /* Transparent on, D-cache clean & flush mode. See NOTE2 above */ orr r0,r0,#1 << 1 @ transparent mode on diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S index e494d6d6acbe..92e08bf37aad 100644 --- a/arch/arm/mm/proc-feroceon.S +++ b/arch/arm/mm/proc-feroceon.S @@ -602,7 +602,6 @@ __\name\()_proc_info: PMD_SECT_AP_WRITE | \ PMD_SECT_AP_READ initfn __feroceon_setup, __\name\()_proc_info - .long __feroceon_setup .long cpu_arch_name .long cpu_elf_name .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index e1268f905026..e0e23582c8b4 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -54,6 +54,7 @@ #define SEEN_DATA (1 << (BPF_MEMWORDS + 3)) #define FLAG_NEED_X_RESET (1 << 0) +#define FLAG_IMM_OVERFLOW (1 << 1) struct jit_ctx { const struct bpf_prog *skf; @@ -293,6 +294,15 @@ static u16 imm_offset(u32 k, struct jit_ctx *ctx) /* PC in ARM mode == address of the instruction + 8 */ imm = offset - (8 + ctx->idx * 4); + if (imm & ~0xfff) { + /* + * literal pool is too far, signal it into flags. we + * can only detect it on the second pass unfortunately. + */ + ctx->flags |= FLAG_IMM_OVERFLOW; + return 0; + } + return imm; } @@ -449,10 +459,21 @@ static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx) return; } #endif - if (rm != ARM_R0) - emit(ARM_MOV_R(ARM_R0, rm), ctx); + + /* + * For BPF_ALU | BPF_DIV | BPF_K instructions, rm is ARM_R4 + * (r_A) and rn is ARM_R0 (r_scratch) so load rn first into + * ARM_R1 to avoid accidentally overwriting ARM_R0 with rm + * before using it as a source for ARM_R1. + * + * For BPF_ALU | BPF_DIV | BPF_X rm is ARM_R4 (r_A) and rn is + * ARM_R5 (r_X) so there is no particular register overlap + * issues. + */ if (rn != ARM_R1) emit(ARM_MOV_R(ARM_R1, rn), ctx); + if (rm != ARM_R0) + emit(ARM_MOV_R(ARM_R0, rm), ctx); ctx->seen |= SEEN_CALL; emit_mov_i(ARM_R3, (u32)jit_udiv, ctx); @@ -855,6 +876,14 @@ b_epilogue: default: return -1; } + + if (ctx->flags & FLAG_IMM_OVERFLOW) + /* + * this instruction generated an overflow when + * trying to access the literal pool, so + * delegate this filter to the kernel interpreter. + */ + return -1; } /* compute offsets only during the first pass */ @@ -917,7 +946,14 @@ void bpf_jit_compile(struct bpf_prog *fp) ctx.idx = 0; build_prologue(&ctx); - build_body(&ctx); + if (build_body(&ctx) < 0) { +#if __LINUX_ARM_ARCH__ < 7 + if (ctx.imm_count) + kfree(ctx.imms); +#endif + bpf_jit_binary_free(header); + goto out; + } build_epilogue(&ctx); flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx)); diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index 793551d15f1d..498325074a06 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -4,6 +4,7 @@ #include <linux/gfp.h> #include <linux/highmem.h> #include <linux/export.h> +#include <linux/memblock.h> #include <linux/of_address.h> #include <linux/slab.h> #include <linux/types.h> @@ -21,6 +22,20 @@ #include <asm/xen/hypercall.h> #include <asm/xen/interface.h> +unsigned long xen_get_swiotlb_free_pages(unsigned int order) +{ + struct memblock_region *reg; + gfp_t flags = __GFP_NOWARN; + + for_each_memblock(memory, reg) { + if (reg->base < (phys_addr_t)0xffffffff) { + flags |= __GFP_DMA; + break; + } + } + return __get_free_pages(flags, order); +} + enum dma_cache_op { DMA_UNMAP, DMA_MAP, diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 4269dba63cf1..7796af4b1d6f 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -31,6 +31,7 @@ config ARM64 select GENERIC_EARLY_IOREMAP select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW + select GENERIC_IRQ_SHOW_LEVEL select GENERIC_PCI_IOMAP select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD diff --git a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi index c138b95a8356..351c95bda89e 100644 --- a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi +++ b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi @@ -21,6 +21,20 @@ clock-output-names = "juno_mb:clk25mhz"; }; + v2m_refclk1mhz: refclk1mhz { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <1000000>; + clock-output-names = "juno_mb:refclk1mhz"; + }; + + v2m_refclk32khz: refclk32khz { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <32768>; + clock-output-names = "juno_mb:refclk32khz"; + }; + motherboard { compatible = "arm,vexpress,v2p-p1", "simple-bus"; #address-cells = <2>; /* SMB chipselect number and offset */ @@ -66,6 +80,15 @@ #size-cells = <1>; ranges = <0 3 0 0x200000>; + v2m_sysctl: sysctl@020000 { + compatible = "arm,sp810", "arm,primecell"; + reg = <0x020000 0x1000>; + clocks = <&v2m_refclk32khz>, <&v2m_refclk1mhz>, <&mb_clk24mhz>; + clock-names = "refclk", "timclk", "apb_pclk"; + #clock-cells = <1>; + clock-output-names = "timerclken0", "timerclken1", "timerclken2", "timerclken3"; + }; + mmci@050000 { compatible = "arm,pl180", "arm,primecell"; reg = <0x050000 0x1000>; @@ -106,16 +129,16 @@ compatible = "arm,sp804", "arm,primecell"; reg = <0x110000 0x10000>; interrupts = <9>; - clocks = <&mb_clk24mhz>, <&soc_smc50mhz>; - clock-names = "timclken1", "apb_pclk"; + clocks = <&v2m_sysctl 0>, <&v2m_sysctl 1>, <&mb_clk24mhz>; + clock-names = "timclken1", "timclken2", "apb_pclk"; }; v2m_timer23: timer@120000 { compatible = "arm,sp804", "arm,primecell"; reg = <0x120000 0x10000>; interrupts = <9>; - clocks = <&mb_clk24mhz>, <&soc_smc50mhz>; - clock-names = "timclken1", "apb_pclk"; + clocks = <&v2m_sysctl 2>, <&v2m_sysctl 3>, <&mb_clk24mhz>; + clock-names = "timclken1", "timclken2", "apb_pclk"; }; rtc@170000 { diff --git a/arch/arm64/crypto/crc32-arm64.c b/arch/arm64/crypto/crc32-arm64.c index 9499199924ae..6a37c3c6b11d 100644 --- a/arch/arm64/crypto/crc32-arm64.c +++ b/arch/arm64/crypto/crc32-arm64.c @@ -147,13 +147,21 @@ static int chksum_final(struct shash_desc *desc, u8 *out) { struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); + put_unaligned_le32(ctx->crc, out); + return 0; +} + +static int chksumc_final(struct shash_desc *desc, u8 *out) +{ + struct chksum_desc_ctx *ctx = shash_desc_ctx(desc); + put_unaligned_le32(~ctx->crc, out); return 0; } static int __chksum_finup(u32 crc, const u8 *data, unsigned int len, u8 *out) { - put_unaligned_le32(~crc32_arm64_le_hw(crc, data, len), out); + put_unaligned_le32(crc32_arm64_le_hw(crc, data, len), out); return 0; } @@ -199,6 +207,14 @@ static int crc32_cra_init(struct crypto_tfm *tfm) { struct chksum_ctx *mctx = crypto_tfm_ctx(tfm); + mctx->key = 0; + return 0; +} + +static int crc32c_cra_init(struct crypto_tfm *tfm) +{ + struct chksum_ctx *mctx = crypto_tfm_ctx(tfm); + mctx->key = ~0; return 0; } @@ -229,7 +245,7 @@ static struct shash_alg crc32c_alg = { .setkey = chksum_setkey, .init = chksum_init, .update = chksumc_update, - .final = chksum_final, + .final = chksumc_final, .finup = chksumc_finup, .digest = chksumc_digest, .descsize = sizeof(struct chksum_desc_ctx), @@ -241,7 +257,7 @@ static struct shash_alg crc32c_alg = { .cra_alignmask = 0, .cra_ctxsize = sizeof(struct chksum_ctx), .cra_module = THIS_MODULE, - .cra_init = crc32_cra_init, + .cra_init = crc32c_cra_init, } }; diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c index 114e7cc5de8c..aefda9868627 100644 --- a/arch/arm64/crypto/sha1-ce-glue.c +++ b/arch/arm64/crypto/sha1-ce-glue.c @@ -74,6 +74,9 @@ static int sha1_ce_finup(struct shash_desc *desc, const u8 *data, static int sha1_ce_final(struct shash_desc *desc, u8 *out) { + struct sha1_ce_state *sctx = shash_desc_ctx(desc); + + sctx->finalize = 0; kernel_neon_begin_partial(16); sha1_base_do_finalize(desc, (sha1_block_fn *)sha1_ce_transform); kernel_neon_end(); diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c index 1340e44c048b..7cd587564a41 100644 --- a/arch/arm64/crypto/sha2-ce-glue.c +++ b/arch/arm64/crypto/sha2-ce-glue.c @@ -75,6 +75,9 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data, static int sha256_ce_final(struct shash_desc *desc, u8 *out) { + struct sha256_ce_state *sctx = shash_desc_ctx(desc); + + sctx->finalize = 0; kernel_neon_begin_partial(28); sha256_base_do_finalize(desc, (sha256_block_fn *)sha2_ce_transform); kernel_neon_end(); diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index a5abb0062d6e..71f19c4dc0de 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -65,6 +65,14 @@ do { \ do { \ compiletime_assert_atomic_type(*p); \ switch (sizeof(*p)) { \ + case 1: \ + asm volatile ("stlrb %w1, %0" \ + : "=Q" (*p) : "r" (v) : "memory"); \ + break; \ + case 2: \ + asm volatile ("stlrh %w1, %0" \ + : "=Q" (*p) : "r" (v) : "memory"); \ + break; \ case 4: \ asm volatile ("stlr %w1, %0" \ : "=Q" (*p) : "r" (v) : "memory"); \ @@ -81,6 +89,14 @@ do { \ typeof(*p) ___p1; \ compiletime_assert_atomic_type(*p); \ switch (sizeof(*p)) { \ + case 1: \ + asm volatile ("ldarb %w0, %1" \ + : "=r" (___p1) : "Q" (*p) : "memory"); \ + break; \ + case 2: \ + asm volatile ("ldarh %w0, %1" \ + : "=r" (___p1) : "Q" (*p) : "memory"); \ + break; \ case 4: \ asm volatile ("ldar %w0, %1" \ : "=r" (___p1) : "Q" (*p) : "memory"); \ diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index 21033bba9390..28f8365edc4c 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -24,7 +24,6 @@ #include <asm/cacheflush.h> #include <asm/alternative.h> #include <asm/cpufeature.h> -#include <asm/insn.h> #include <linux/stop_machine.h> extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; @@ -34,48 +33,6 @@ struct alt_region { struct alt_instr *end; }; -/* - * Decode the imm field of a b/bl instruction, and return the byte - * offset as a signed value (so it can be used when computing a new - * branch target). - */ -static s32 get_branch_offset(u32 insn) -{ - s32 imm = aarch64_insn_decode_immediate(AARCH64_INSN_IMM_26, insn); - - /* sign-extend the immediate before turning it into a byte offset */ - return (imm << 6) >> 4; -} - -static u32 get_alt_insn(u8 *insnptr, u8 *altinsnptr) -{ - u32 insn; - - aarch64_insn_read(altinsnptr, &insn); - - /* Stop the world on instructions we don't support... */ - BUG_ON(aarch64_insn_is_cbz(insn)); - BUG_ON(aarch64_insn_is_cbnz(insn)); - BUG_ON(aarch64_insn_is_bcond(insn)); - /* ... and there is probably more. */ - - if (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn)) { - enum aarch64_insn_branch_type type; - unsigned long target; - - if (aarch64_insn_is_b(insn)) - type = AARCH64_INSN_BRANCH_NOLINK; - else - type = AARCH64_INSN_BRANCH_LINK; - - target = (unsigned long)altinsnptr + get_branch_offset(insn); - insn = aarch64_insn_gen_branch_imm((unsigned long)insnptr, - target, type); - } - - return insn; -} - static int __apply_alternatives(void *alt_region) { struct alt_instr *alt; @@ -83,9 +40,6 @@ static int __apply_alternatives(void *alt_region) u8 *origptr, *replptr; for (alt = region->begin; alt < region->end; alt++) { - u32 insn; - int i; - if (!cpus_have_cap(alt->cpufeature)) continue; @@ -95,12 +49,7 @@ static int __apply_alternatives(void *alt_region) origptr = (u8 *)&alt->orig_offset + alt->orig_offset; replptr = (u8 *)&alt->alt_offset + alt->alt_offset; - - for (i = 0; i < alt->alt_len; i += sizeof(insn)) { - insn = get_alt_insn(origptr + i, replptr + i); - aarch64_insn_write(origptr + i, insn); - } - + memcpy(origptr, replptr, alt->alt_len); flush_icache_range((uintptr_t)origptr, (uintptr_t)(origptr + alt->alt_len)); } diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 195991dadc37..cce18c85d2e8 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -1310,11 +1310,16 @@ static const struct of_device_id armpmu_of_device_ids[] = { static int armpmu_device_probe(struct platform_device *pdev) { - int i, *irqs; + int i, irq, *irqs; if (!cpu_pmu) return -ENODEV; + /* Don't bother with PPIs; they're already affine */ + irq = platform_get_irq(pdev, 0); + if (irq >= 0 && irq_is_percpu(irq)) + return 0; + irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL); if (!irqs) return -ENOMEM; @@ -1327,7 +1332,7 @@ static int armpmu_device_probe(struct platform_device *pdev) i); if (!dn) { pr_warn("Failed to parse %s/interrupt-affinity[%d]\n", - of_node_full_name(dn), i); + of_node_full_name(pdev->dev.of_node), i); break; } diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index ef7d112f5ce0..b0bd4e5fd5cf 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -67,8 +67,7 @@ static void *__alloc_from_pool(size_t size, struct page **ret_page, gfp_t flags) *ret_page = phys_to_page(phys); ptr = (void *)val; - if (flags & __GFP_ZERO) - memset(ptr, 0, size); + memset(ptr, 0, size); } return ptr; @@ -105,7 +104,6 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, struct page *page; void *addr; - size = PAGE_ALIGN(size); page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT, get_order(size)); if (!page) @@ -113,8 +111,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, *dma_handle = phys_to_dma(dev, page_to_phys(page)); addr = page_address(page); - if (flags & __GFP_ZERO) - memset(addr, 0, size); + memset(addr, 0, size); return addr; } else { return swiotlb_alloc_coherent(dev, size, dma_handle, flags); @@ -195,6 +192,8 @@ static void __dma_free(struct device *dev, size_t size, { void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle)); + size = PAGE_ALIGN(size); + if (!is_device_dma_coherent(dev)) { if (__free_from_pool(vaddr, size)) return; diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index 74c256744b25..f3d6221cd5bd 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -328,10 +328,12 @@ static int ptdump_init(void) for (j = 0; j < pg_level[i].num; j++) pg_level[i].mask |= pg_level[i].bits[j].mask; +#ifdef CONFIG_SPARSEMEM_VMEMMAP address_markers[VMEMMAP_START_NR].start_address = (unsigned long)virt_to_page(PAGE_OFFSET); address_markers[VMEMMAP_END_NR].start_address = (unsigned long)virt_to_page(high_memory); +#endif pe = debugfs_create_file("kernel_page_tables", 0400, NULL, NULL, &ptdump_fops); diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index edba042b2325..dc6a4842683a 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -487,7 +487,7 @@ emit_cond_jmp: return -EINVAL; } - imm64 = (u64)insn1.imm << 32 | imm; + imm64 = (u64)insn1.imm << 32 | (u32)imm; emit_a64_mov_i64(dst, imm64, ctx); return 1; diff --git a/arch/m32r/kernel/smp.c b/arch/m32r/kernel/smp.c index ce7aea34fdf4..c18ddc74ef9a 100644 --- a/arch/m32r/kernel/smp.c +++ b/arch/m32r/kernel/smp.c @@ -45,7 +45,7 @@ static volatile unsigned long flushcache_cpumask = 0; /* * For flush_tlb_others() */ -static volatile cpumask_t flush_cpumask; +static cpumask_t flush_cpumask; static struct mm_struct *flush_mm; static struct vm_area_struct *flush_vma; static volatile unsigned long flush_va; @@ -415,7 +415,7 @@ static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm, */ send_IPI_mask(&cpumask, INVALIDATE_TLB_IPI, 0); - while (!cpumask_empty((cpumask_t*)&flush_cpumask)) { + while (!cpumask_empty(&flush_cpumask)) { /* nothing. lockup detection does not belong here */ mb(); } @@ -468,7 +468,7 @@ void smp_invalidate_interrupt(void) __flush_tlb_page(va); } } - cpumask_clear_cpu(cpu_id, (cpumask_t*)&flush_cpumask); + cpumask_clear_cpu(cpu_id, &flush_cpumask); } /*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*=*/ diff --git a/arch/mips/Makefile b/arch/mips/Makefile index 5200f649dd4e..ae2dd59050f7 100644 --- a/arch/mips/Makefile +++ b/arch/mips/Makefile @@ -277,7 +277,7 @@ LDFLAGS += -m $(ld-emul) ifdef CONFIG_MIPS CHECKFLAGS += $(shell $(CC) $(KBUILD_CFLAGS) -dM -E -x c /dev/null | \ egrep -vw '__GNUC_(|MINOR_|PATCHLEVEL_)_' | \ - sed -e "s/^\#define /-D'/" -e "s/ /'='/" -e "s/$$/'/") + sed -e "s/^\#define /-D'/" -e "s/ /'='/" -e "s/$$/'/" -e 's/\$$/&&/g') ifdef CONFIG_64BIT CHECKFLAGS += -m64 endif diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h index a594d8ed9698..f19e890b99d2 100644 --- a/arch/mips/include/asm/elf.h +++ b/arch/mips/include/asm/elf.h @@ -304,7 +304,7 @@ do { \ \ current->thread.abi = &mips_abi; \ \ - current->thread.fpu.fcr31 = current_cpu_data.fpu_csr31; \ + current->thread.fpu.fcr31 = boot_cpu_data.fpu_csr31; \ } while (0) #endif /* CONFIG_32BIT */ @@ -366,7 +366,7 @@ do { \ else \ current->thread.abi = &mips_abi; \ \ - current->thread.fpu.fcr31 = current_cpu_data.fpu_csr31; \ + current->thread.fpu.fcr31 = boot_cpu_data.fpu_csr31; \ \ p = personality(current->personality); \ if (p != PER_LINUX32 && p != PER_LINUX) \ diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index bb02fac9b4fa..2b25d1ba1ea0 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -45,7 +45,7 @@ extern int __cpu_logical_map[NR_CPUS]; #define SMP_DUMP 0x8 #define SMP_ASK_C0COUNT 0x10 -extern volatile cpumask_t cpu_callin_map; +extern cpumask_t cpu_callin_map; /* Mask of CPUs which are currently definitely operating coherently */ extern cpumask_t cpu_coherent_mask; diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c index be4899f3c393..4a4d9e067c89 100644 --- a/arch/mips/kernel/elf.c +++ b/arch/mips/kernel/elf.c @@ -76,14 +76,6 @@ int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf, /* Lets see if this is an O32 ELF */ if (ehdr32->e_ident[EI_CLASS] == ELFCLASS32) { - /* FR = 1 for N32 */ - if (ehdr32->e_flags & EF_MIPS_ABI2) - state->overall_fp_mode = FP_FR1; - else - /* Set a good default FPU mode for O32 */ - state->overall_fp_mode = cpu_has_mips_r6 ? - FP_FRE : FP_FR0; - if (ehdr32->e_flags & EF_MIPS_FP64) { /* * Set MIPS_ABI_FP_OLD_64 for EF_MIPS_FP64. We will override it @@ -104,9 +96,6 @@ int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf, (char *)&abiflags, sizeof(abiflags)); } else { - /* FR=1 is really the only option for 64-bit */ - state->overall_fp_mode = FP_FR1; - if (phdr64->p_type != PT_MIPS_ABIFLAGS) return 0; if (phdr64->p_filesz < sizeof(abiflags)) @@ -137,6 +126,7 @@ int arch_check_elf(void *_ehdr, bool has_interpreter, struct elf32_hdr *ehdr = _ehdr; struct mode_req prog_req, interp_req; int fp_abi, interp_fp_abi, abi0, abi1, max_abi; + bool is_mips64; if (!config_enabled(CONFIG_MIPS_O32_FP64_SUPPORT)) return 0; @@ -152,10 +142,22 @@ int arch_check_elf(void *_ehdr, bool has_interpreter, abi0 = abi1 = fp_abi; } - /* ABI limits. O32 = FP_64A, N32/N64 = FP_SOFT */ - max_abi = ((ehdr->e_ident[EI_CLASS] == ELFCLASS32) && - (!(ehdr->e_flags & EF_MIPS_ABI2))) ? - MIPS_ABI_FP_64A : MIPS_ABI_FP_SOFT; + is_mips64 = (ehdr->e_ident[EI_CLASS] == ELFCLASS64) || + (ehdr->e_flags & EF_MIPS_ABI2); + + if (is_mips64) { + /* MIPS64 code always uses FR=1, thus the default is easy */ + state->overall_fp_mode = FP_FR1; + + /* Disallow access to the various FPXX & FP64 ABIs */ + max_abi = MIPS_ABI_FP_SOFT; + } else { + /* Default to a mode capable of running code expecting FR=0 */ + state->overall_fp_mode = cpu_has_mips_r6 ? FP_FRE : FP_FR0; + + /* Allow all ABIs we know about */ + max_abi = MIPS_ABI_FP_64A; + } if ((abi0 > max_abi && abi0 != MIPS_ABI_FP_UNKNOWN) || (abi1 > max_abi && abi1 != MIPS_ABI_FP_UNKNOWN)) diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c index d544e774eea6..e933a309f2ea 100644 --- a/arch/mips/kernel/ptrace.c +++ b/arch/mips/kernel/ptrace.c @@ -176,7 +176,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data) __get_user(value, data + 64); fcr31 = child->thread.fpu.fcr31; - mask = current_cpu_data.fpu_msk31; + mask = boot_cpu_data.fpu_msk31; child->thread.fpu.fcr31 = (value & ~mask) | (fcr31 & mask); /* FIR may not be written. */ diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index 7e011f95bb8e..4251d390b5b6 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -92,7 +92,7 @@ static void __init cps_smp_setup(void) #ifdef CONFIG_MIPS_MT_FPAFF /* If we have an FPU, enroll ourselves in the FPU-full mask */ if (cpu_has_fpu) - cpu_set(0, mt_fpu_cpumask); + cpumask_set_cpu(0, &mt_fpu_cpumask); #endif /* CONFIG_MIPS_MT_FPAFF */ } diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 193ace7955fb..faa46ebd9dda 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -43,7 +43,7 @@ #include <asm/time.h> #include <asm/setup.h> -volatile cpumask_t cpu_callin_map; /* Bitmask of started secondaries */ +cpumask_t cpu_callin_map; /* Bitmask of started secondaries */ int __cpu_number_map[NR_CPUS]; /* Map physical to logical */ EXPORT_SYMBOL(__cpu_number_map); @@ -218,8 +218,10 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle) /* * Trust is futile. We should really have timeouts ... */ - while (!cpumask_test_cpu(cpu, &cpu_callin_map)) + while (!cpumask_test_cpu(cpu, &cpu_callin_map)) { udelay(100); + schedule(); + } synchronise_count_master(cpu); return 0; diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index ba32e48d4697..d2d1c1933bc9 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -269,7 +269,6 @@ static void __show_regs(const struct pt_regs *regs) */ printk("epc : %0*lx %pS\n", field, regs->cp0_epc, (void *) regs->cp0_epc); - printk(" %s\n", print_tainted()); printk("ra : %0*lx %pS\n", field, regs->regs[31], (void *) regs->regs[31]); diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 6230f376a44e..4b50c5787e25 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -2389,7 +2389,6 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu, { unsigned long *gpr = &vcpu->arch.gprs[vcpu->arch.io_gpr]; enum emulation_result er = EMULATE_DONE; - unsigned long curr_pc; if (run->mmio.len > sizeof(*gpr)) { kvm_err("Bad MMIO length: %d", run->mmio.len); @@ -2397,11 +2396,6 @@ enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu, goto done; } - /* - * Update PC and hold onto current PC in case there is - * an error and we want to rollback the PC - */ - curr_pc = vcpu->arch.pc; er = update_pc(vcpu, vcpu->arch.pending_load_cause); if (er == EMULATE_FAIL) return er; diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index d31c537ace1d..22b9b2cb9219 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -889,7 +889,7 @@ static inline void cop1_cfc(struct pt_regs *xcp, struct mips_fpu_struct *ctx, break; case FPCREG_RID: - value = current_cpu_data.fpu_id; + value = boot_cpu_data.fpu_id; break; default: @@ -921,7 +921,7 @@ static inline void cop1_ctc(struct pt_regs *xcp, struct mips_fpu_struct *ctx, (void *)xcp->cp0_epc, MIPSInst_RT(ir), value); /* Preserve read-only bits. */ - mask = current_cpu_data.fpu_msk31; + mask = boot_cpu_data.fpu_msk31; fcr31 = (value & ~mask) | (fcr31 & mask); break; diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c index a27a088e6f9f..08318ecb803a 100644 --- a/arch/mips/mm/tlb-r4k.c +++ b/arch/mips/mm/tlb-r4k.c @@ -495,7 +495,7 @@ static void r4k_tlb_configure(void) if (cpu_has_rixi) { /* - * Enable the no read, no exec bits, and enable large virtual + * Enable the no read, no exec bits, and enable large physical * address. */ #ifdef CONFIG_64BIT diff --git a/arch/mips/sgi-ip32/ip32-platform.c b/arch/mips/sgi-ip32/ip32-platform.c index 0134db2ad0a8..5a2a82148d8d 100644 --- a/arch/mips/sgi-ip32/ip32-platform.c +++ b/arch/mips/sgi-ip32/ip32-platform.c @@ -130,9 +130,9 @@ struct platform_device ip32_rtc_device = { .resource = ip32_rtc_resources, }; -+static int __init sgio2_rtc_devinit(void) +static __init int sgio2_rtc_devinit(void) { return platform_device_register(&ip32_rtc_device); } -device_initcall(sgio2_cmos_devinit); +device_initcall(sgio2_rtc_devinit); diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h index 3391d061eccc..78c9fd32c554 100644 --- a/arch/parisc/include/asm/elf.h +++ b/arch/parisc/include/asm/elf.h @@ -348,6 +348,10 @@ struct pt_regs; /* forward declaration... */ #define ELF_HWCAP 0 +#define STACK_RND_MASK (is_32bit_task() ? \ + 0x7ff >> (PAGE_SHIFT - 12) : \ + 0x3ffff >> (PAGE_SHIFT - 12)) + struct mm_struct; extern unsigned long arch_randomize_brk(struct mm_struct *); #define arch_randomize_brk arch_randomize_brk diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c index 8a488c22a99f..809905a811ed 100644 --- a/arch/parisc/kernel/process.c +++ b/arch/parisc/kernel/process.c @@ -181,9 +181,12 @@ int dump_task_fpu (struct task_struct *tsk, elf_fpregset_t *r) return 1; } +/* + * Copy architecture-specific thread state + */ int copy_thread(unsigned long clone_flags, unsigned long usp, - unsigned long arg, struct task_struct *p) + unsigned long kthread_arg, struct task_struct *p) { struct pt_regs *cregs = &(p->thread.regs); void *stack = task_stack_page(p); @@ -195,11 +198,10 @@ copy_thread(unsigned long clone_flags, unsigned long usp, extern void * const child_return; if (unlikely(p->flags & PF_KTHREAD)) { + /* kernel thread */ memset(cregs, 0, sizeof(struct pt_regs)); if (!usp) /* idle thread */ return 0; - - /* kernel thread */ /* Must exit via ret_from_kernel_thread in order * to call schedule_tail() */ @@ -215,7 +217,7 @@ copy_thread(unsigned long clone_flags, unsigned long usp, #else cregs->gr[26] = usp; #endif - cregs->gr[25] = arg; + cregs->gr[25] = kthread_arg; } else { /* user thread */ /* usp must be word aligned. This also prevents users from diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index e1ffea2f9a0b..5aba01ac457f 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -77,6 +77,9 @@ static unsigned long mmap_upper_limit(void) if (stack_base > STACK_SIZE_MAX) stack_base = STACK_SIZE_MAX; + /* Add space for stack randomization. */ + stack_base += (STACK_RND_MASK << PAGE_SHIFT); + return PAGE_ALIGN(STACK_TOP - stack_base); } diff --git a/arch/powerpc/include/uapi/asm/tm.h b/arch/powerpc/include/uapi/asm/tm.h index 5047659815a5..5d836b7c1176 100644 --- a/arch/powerpc/include/uapi/asm/tm.h +++ b/arch/powerpc/include/uapi/asm/tm.h @@ -11,7 +11,7 @@ #define TM_CAUSE_RESCHED 0xde #define TM_CAUSE_TLBI 0xdc #define TM_CAUSE_FAC_UNAV 0xda -#define TM_CAUSE_SYSCALL 0xd8 +#define TM_CAUSE_SYSCALL 0xd8 /* future use */ #define TM_CAUSE_MISC 0xd6 /* future use */ #define TM_CAUSE_SIGNAL 0xd4 #define TM_CAUSE_ALIGNMENT 0xd2 diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c index 44b480e3a5af..9ee61d15653d 100644 --- a/arch/powerpc/kernel/eeh.c +++ b/arch/powerpc/kernel/eeh.c @@ -749,21 +749,24 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat eeh_unfreeze_pe(pe, false); eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); eeh_pe_dev_traverse(pe, eeh_restore_dev_state, dev); + eeh_pe_state_clear(pe, EEH_PE_ISOLATED); break; case pcie_hot_reset: + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE); eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev); eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); eeh_ops->reset(pe, EEH_RESET_HOT); break; case pcie_warm_reset: + eeh_pe_state_mark(pe, EEH_PE_ISOLATED); eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE); eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev); eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED); eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL); break; default: - eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED); + eeh_pe_state_clear(pe, EEH_PE_ISOLATED | EEH_PE_CFG_BLOCKED); return -EINVAL; }; @@ -1058,6 +1061,9 @@ void eeh_add_device_early(struct pci_dn *pdn) if (!edev || !eeh_enabled()) return; + if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE)) + return; + /* USB Bus children of PCI devices will not have BUID's */ phb = edev->phb; if (NULL == phb || @@ -1112,6 +1118,9 @@ void eeh_add_device_late(struct pci_dev *dev) return; } + if (eeh_has_flag(EEH_PROBE_MODE_DEV)) + eeh_ops->probe(pdn, NULL); + /* * The EEH cache might not be removed correctly because of * unbalanced kref to the device during unplug time, which diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index 8ca9434c40e6..afbc20019c2e 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -34,7 +34,6 @@ #include <asm/ftrace.h> #include <asm/hw_irq.h> #include <asm/context_tracking.h> -#include <asm/tm.h> /* * System calls. @@ -146,24 +145,6 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR) andi. r11,r10,_TIF_SYSCALL_DOTRACE bne syscall_dotrace .Lsyscall_dotrace_cont: -#ifdef CONFIG_PPC_TRANSACTIONAL_MEM -BEGIN_FTR_SECTION - b 1f -END_FTR_SECTION_IFCLR(CPU_FTR_TM) - extrdi. r11, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */ - beq+ 1f - - /* Doom the transaction and don't perform the syscall: */ - mfmsr r11 - li r12, 1 - rldimi r11, r12, MSR_TM_LG, 63-MSR_TM_LG - mtmsrd r11, 0 - li r11, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT) - TABORT(R11) - - b .Lsyscall_exit -1: -#endif cmpldi 0,r0,NR_syscalls bge- syscall_enosys diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S index eeaa0d5f69d5..ccde8f084ce4 100644 --- a/arch/powerpc/kernel/idle_power7.S +++ b/arch/powerpc/kernel/idle_power7.S @@ -501,9 +501,11 @@ BEGIN_FTR_SECTION CHECK_HMI_INTERRUPT END_FTR_SECTION_IFSET(CPU_FTR_HVMODE) ld r1,PACAR1(r13) + ld r6,_CCR(r1) ld r4,_MSR(r1) ld r5,_NIP(r1) addi r1,r1,INT_FRAME_SIZE + mtcr r6 mtspr SPRN_SRR1,r4 mtspr SPRN_SRR0,r5 rfid diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index 8f3e6cc54d95..c6ca7db64673 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -12,6 +12,7 @@ #include <linux/err.h> #include <linux/gfp.h> #include <linux/anon_inodes.h> +#include <linux/spinlock.h> #include <asm/uaccess.h> #include <asm/kvm_book3s.h> @@ -20,7 +21,6 @@ #include <asm/xics.h> #include <asm/debug.h> #include <asm/time.h> -#include <asm/spinlock.h> #include <linux/debugfs.h> #include <linux/seq_file.h> diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 920c252d1f49..f8bc950efcae 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -2693,7 +2693,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, hose->last_busno = 0xff; } hose->private_data = phb; - hose->controller_ops = pnv_pci_controller_ops; phb->hub_id = hub_id; phb->opal_id = phb_id; phb->type = ioda_type; @@ -2812,6 +2811,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, pnv_pci_controller_ops.enable_device_hook = pnv_pci_enable_device_hook; pnv_pci_controller_ops.window_alignment = pnv_pci_window_alignment; pnv_pci_controller_ops.reset_secondary_bus = pnv_pci_reset_secondary_bus; + hose->controller_ops = pnv_pci_controller_ops; #ifdef CONFIG_PCI_IOV ppc_md.pcibios_fixup_sriov = pnv_pci_ioda_fixup_iov_resources; diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index b4b11096ea8b..019d34aaf054 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -412,6 +412,10 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count) if (rc) return -EINVAL; + rc = dlpar_acquire_drc(drc_index); + if (rc) + return -EINVAL; + parent = of_find_node_by_path("/cpus"); if (!parent) return -ENODEV; @@ -422,12 +426,6 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count) of_node_put(parent); - rc = dlpar_acquire_drc(drc_index); - if (rc) { - dlpar_free_cc_nodes(dn); - return -EINVAL; - } - rc = dlpar_attach_node(dn); if (rc) { dlpar_release_drc(drc_index); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8e58c614c37d..b06dc3839268 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -115,7 +115,7 @@ config S390 select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_ARCH_TRANSPARENT_HUGEPAGE - select HAVE_BPF_JIT if PACK_STACK && HAVE_MARCH_Z9_109_FEATURES + select HAVE_BPF_JIT if PACK_STACK && HAVE_MARCH_Z196_FEATURES select HAVE_CMPXCHG_DOUBLE select HAVE_CMPXCHG_LOCAL select HAVE_DEBUG_KMEMLEAK diff --git a/arch/s390/crypto/crypt_s390.h b/arch/s390/crypto/crypt_s390.h index ba3b2aefddf5..d9c4c313fbc6 100644 --- a/arch/s390/crypto/crypt_s390.h +++ b/arch/s390/crypto/crypt_s390.h @@ -3,9 +3,10 @@ * * Support for s390 cryptographic instructions. * - * Copyright IBM Corp. 2003, 2007 + * Copyright IBM Corp. 2003, 2015 * Author(s): Thomas Spatzier * Jan Glauber (jan.glauber@de.ibm.com) + * Harald Freudenberger (freude@de.ibm.com) * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the Free @@ -28,15 +29,17 @@ #define CRYPT_S390_MSA 0x1 #define CRYPT_S390_MSA3 0x2 #define CRYPT_S390_MSA4 0x4 +#define CRYPT_S390_MSA5 0x8 /* s390 cryptographic operations */ enum crypt_s390_operations { - CRYPT_S390_KM = 0x0100, - CRYPT_S390_KMC = 0x0200, - CRYPT_S390_KIMD = 0x0300, - CRYPT_S390_KLMD = 0x0400, - CRYPT_S390_KMAC = 0x0500, - CRYPT_S390_KMCTR = 0x0600 + CRYPT_S390_KM = 0x0100, + CRYPT_S390_KMC = 0x0200, + CRYPT_S390_KIMD = 0x0300, + CRYPT_S390_KLMD = 0x0400, + CRYPT_S390_KMAC = 0x0500, + CRYPT_S390_KMCTR = 0x0600, + CRYPT_S390_PPNO = 0x0700 }; /* @@ -138,6 +141,16 @@ enum crypt_s390_kmac_func { KMAC_TDEA_192 = CRYPT_S390_KMAC | 3 }; +/* + * function codes for PPNO (PERFORM PSEUDORANDOM NUMBER + * OPERATION) instruction + */ +enum crypt_s390_ppno_func { + PPNO_QUERY = CRYPT_S390_PPNO | 0, + PPNO_SHA512_DRNG_GEN = CRYPT_S390_PPNO | 3, + PPNO_SHA512_DRNG_SEED = CRYPT_S390_PPNO | 0x83 +}; + /** * crypt_s390_km: * @func: the function code passed to KM; see crypt_s390_km_func @@ -162,11 +175,11 @@ static inline int crypt_s390_km(long func, void *param, int ret; asm volatile( - "0: .insn rre,0xb92e0000,%3,%1 \n" /* KM opcode */ - "1: brc 1,0b \n" /* handle partial completion */ + "0: .insn rre,0xb92e0000,%3,%1\n" /* KM opcode */ + "1: brc 1,0b\n" /* handle partial completion */ " la %0,0\n" "2:\n" - EX_TABLE(0b,2b) EX_TABLE(1b,2b) + EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) : "=d" (ret), "+a" (__src), "+d" (__src_len), "+a" (__dest) : "d" (__func), "a" (__param), "0" (-1) : "cc", "memory"); if (ret < 0) @@ -198,11 +211,11 @@ static inline int crypt_s390_kmc(long func, void *param, int ret; asm volatile( - "0: .insn rre,0xb92f0000,%3,%1 \n" /* KMC opcode */ - "1: brc 1,0b \n" /* handle partial completion */ + "0: .insn rre,0xb92f0000,%3,%1\n" /* KMC opcode */ + "1: brc 1,0b\n" /* handle partial completion */ " la %0,0\n" "2:\n" - EX_TABLE(0b,2b) EX_TABLE(1b,2b) + EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) : "=d" (ret), "+a" (__src), "+d" (__src_len), "+a" (__dest) : "d" (__func), "a" (__param), "0" (-1) : "cc", "memory"); if (ret < 0) @@ -233,11 +246,11 @@ static inline int crypt_s390_kimd(long func, void *param, int ret; asm volatile( - "0: .insn rre,0xb93e0000,%1,%1 \n" /* KIMD opcode */ - "1: brc 1,0b \n" /* handle partial completion */ + "0: .insn rre,0xb93e0000,%1,%1\n" /* KIMD opcode */ + "1: brc 1,0b\n" /* handle partial completion */ " la %0,0\n" "2:\n" - EX_TABLE(0b,2b) EX_TABLE(1b,2b) + EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) : "=d" (ret), "+a" (__src), "+d" (__src_len) : "d" (__func), "a" (__param), "0" (-1) : "cc", "memory"); if (ret < 0) @@ -267,11 +280,11 @@ static inline int crypt_s390_klmd(long func, void *param, int ret; asm volatile( - "0: .insn rre,0xb93f0000,%1,%1 \n" /* KLMD opcode */ - "1: brc 1,0b \n" /* handle partial completion */ + "0: .insn rre,0xb93f0000,%1,%1\n" /* KLMD opcode */ + "1: brc 1,0b\n" /* handle partial completion */ " la %0,0\n" "2:\n" - EX_TABLE(0b,2b) EX_TABLE(1b,2b) + EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) : "=d" (ret), "+a" (__src), "+d" (__src_len) : "d" (__func), "a" (__param), "0" (-1) : "cc", "memory"); if (ret < 0) @@ -302,11 +315,11 @@ static inline int crypt_s390_kmac(long func, void *param, int ret; asm volatile( - "0: .insn rre,0xb91e0000,%1,%1 \n" /* KLAC opcode */ - "1: brc 1,0b \n" /* handle partial completion */ + "0: .insn rre,0xb91e0000,%1,%1\n" /* KLAC opcode */ + "1: brc 1,0b\n" /* handle partial completion */ " la %0,0\n" "2:\n" - EX_TABLE(0b,2b) EX_TABLE(1b,2b) + EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) : "=d" (ret), "+a" (__src), "+d" (__src_len) : "d" (__func), "a" (__param), "0" (-1) : "cc", "memory"); if (ret < 0) @@ -340,11 +353,11 @@ static inline int crypt_s390_kmctr(long func, void *param, u8 *dest, int ret = -1; asm volatile( - "0: .insn rrf,0xb92d0000,%3,%1,%4,0 \n" /* KMCTR opcode */ - "1: brc 1,0b \n" /* handle partial completion */ + "0: .insn rrf,0xb92d0000,%3,%1,%4,0\n" /* KMCTR opcode */ + "1: brc 1,0b\n" /* handle partial completion */ " la %0,0\n" "2:\n" - EX_TABLE(0b,2b) EX_TABLE(1b,2b) + EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) : "+d" (ret), "+a" (__src), "+d" (__src_len), "+a" (__dest), "+a" (__ctr) : "d" (__func), "a" (__param) : "cc", "memory"); @@ -354,6 +367,47 @@ static inline int crypt_s390_kmctr(long func, void *param, u8 *dest, } /** + * crypt_s390_ppno: + * @func: the function code passed to PPNO; see crypt_s390_ppno_func + * @param: address of parameter block; see POP for details on each func + * @dest: address of destination memory area + * @dest_len: size of destination memory area in bytes + * @seed: address of seed data + * @seed_len: size of seed data in bytes + * + * Executes the PPNO (PERFORM PSEUDORANDOM NUMBER OPERATION) + * operation of the CPU. + * + * Returns -1 for failure, 0 for the query func, number of random + * bytes stored in dest buffer for generate function + */ +static inline int crypt_s390_ppno(long func, void *param, + u8 *dest, long dest_len, + const u8 *seed, long seed_len) +{ + register long __func asm("0") = func & CRYPT_S390_FUNC_MASK; + register void *__param asm("1") = param; /* param block (240 bytes) */ + register u8 *__dest asm("2") = dest; /* buf for recv random bytes */ + register long __dest_len asm("3") = dest_len; /* requested random bytes */ + register const u8 *__seed asm("4") = seed; /* buf with seed data */ + register long __seed_len asm("5") = seed_len; /* bytes in seed buf */ + int ret = -1; + + asm volatile ( + "0: .insn rre,0xb93c0000,%1,%5\n" /* PPNO opcode */ + "1: brc 1,0b\n" /* handle partial completion */ + " la %0,0\n" + "2:\n" + EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) + : "+d" (ret), "+a"(__dest), "+d"(__dest_len) + : "d"(__func), "a"(__param), "a"(__seed), "d"(__seed_len) + : "cc", "memory"); + if (ret < 0) + return ret; + return (func & CRYPT_S390_FUNC_MASK) ? dest_len - __dest_len : 0; +} + +/** * crypt_s390_func_available: * @func: the function code of the specific function; 0 if op in general * @@ -373,6 +427,9 @@ static inline int crypt_s390_func_available(int func, return 0; if (facility_mask & CRYPT_S390_MSA4 && !test_facility(77)) return 0; + if (facility_mask & CRYPT_S390_MSA5 && !test_facility(57)) + return 0; + switch (func & CRYPT_S390_OP_MASK) { case CRYPT_S390_KM: ret = crypt_s390_km(KM_QUERY, &status, NULL, NULL, 0); @@ -390,8 +447,12 @@ static inline int crypt_s390_func_available(int func, ret = crypt_s390_kmac(KMAC_QUERY, &status, NULL, 0); break; case CRYPT_S390_KMCTR: - ret = crypt_s390_kmctr(KMCTR_QUERY, &status, NULL, NULL, 0, - NULL); + ret = crypt_s390_kmctr(KMCTR_QUERY, &status, + NULL, NULL, 0, NULL); + break; + case CRYPT_S390_PPNO: + ret = crypt_s390_ppno(PPNO_QUERY, &status, + NULL, 0, NULL, 0); break; default: return 0; @@ -419,15 +480,14 @@ static inline int crypt_s390_pcc(long func, void *param) int ret = -1; asm volatile( - "0: .insn rre,0xb92c0000,0,0 \n" /* PCC opcode */ - "1: brc 1,0b \n" /* handle partial completion */ + "0: .insn rre,0xb92c0000,0,0\n" /* PCC opcode */ + "1: brc 1,0b\n" /* handle partial completion */ " la %0,0\n" "2:\n" - EX_TABLE(0b,2b) EX_TABLE(1b,2b) + EX_TABLE(0b, 2b) EX_TABLE(1b, 2b) : "+d" (ret) : "d" (__func), "a" (__param) : "cc", "memory"); return ret; } - #endif /* _CRYPTO_ARCH_S390_CRYPT_S390_H */ diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c index 94a35a4c1b48..1f374b39a4ec 100644 --- a/arch/s390/crypto/prng.c +++ b/arch/s390/crypto/prng.c @@ -1,106 +1,529 @@ /* - * Copyright IBM Corp. 2006, 2007 + * Copyright IBM Corp. 2006, 2015 * Author(s): Jan Glauber <jan.glauber@de.ibm.com> + * Harald Freudenberger <freude@de.ibm.com> * Driver for the s390 pseudo random number generator */ + +#define KMSG_COMPONENT "prng" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + #include <linux/fs.h> +#include <linux/fips.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/device.h> #include <linux/miscdevice.h> #include <linux/module.h> #include <linux/moduleparam.h> +#include <linux/mutex.h> #include <linux/random.h> #include <linux/slab.h> #include <asm/debug.h> #include <asm/uaccess.h> +#include <asm/timex.h> #include "crypt_s390.h" MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Jan Glauber <jan.glauber@de.ibm.com>"); +MODULE_AUTHOR("IBM Corporation"); MODULE_DESCRIPTION("s390 PRNG interface"); -static int prng_chunk_size = 256; -module_param(prng_chunk_size, int, S_IRUSR | S_IRGRP | S_IROTH); + +#define PRNG_MODE_AUTO 0 +#define PRNG_MODE_TDES 1 +#define PRNG_MODE_SHA512 2 + +static unsigned int prng_mode = PRNG_MODE_AUTO; +module_param_named(mode, prng_mode, int, 0); +MODULE_PARM_DESC(prng_mode, "PRNG mode: 0 - auto, 1 - TDES, 2 - SHA512"); + + +#define PRNG_CHUNKSIZE_TDES_MIN 8 +#define PRNG_CHUNKSIZE_TDES_MAX (64*1024) +#define PRNG_CHUNKSIZE_SHA512_MIN 64 +#define PRNG_CHUNKSIZE_SHA512_MAX (64*1024) + +static unsigned int prng_chunk_size = 256; +module_param_named(chunksize, prng_chunk_size, int, 0); MODULE_PARM_DESC(prng_chunk_size, "PRNG read chunk size in bytes"); -static int prng_entropy_limit = 4096; -module_param(prng_entropy_limit, int, S_IRUSR | S_IRGRP | S_IROTH | S_IWUSR); -MODULE_PARM_DESC(prng_entropy_limit, - "PRNG add entropy after that much bytes were produced"); + +#define PRNG_RESEED_LIMIT_TDES 4096 +#define PRNG_RESEED_LIMIT_TDES_LOWER 4096 +#define PRNG_RESEED_LIMIT_SHA512 100000 +#define PRNG_RESEED_LIMIT_SHA512_LOWER 10000 + +static unsigned int prng_reseed_limit; +module_param_named(reseed_limit, prng_reseed_limit, int, 0); +MODULE_PARM_DESC(prng_reseed_limit, "PRNG reseed limit"); + /* * Any one who considers arithmetical methods of producing random digits is, * of course, in a state of sin. -- John von Neumann */ -struct s390_prng_data { - unsigned long count; /* how many bytes were produced */ - char *buf; +static int prng_errorflag; + +#define PRNG_GEN_ENTROPY_FAILED 1 +#define PRNG_SELFTEST_FAILED 2 +#define PRNG_INSTANTIATE_FAILED 3 +#define PRNG_SEED_FAILED 4 +#define PRNG_RESEED_FAILED 5 +#define PRNG_GEN_FAILED 6 + +struct prng_ws_s { + u8 parm_block[32]; + u32 reseed_counter; + u64 byte_counter; }; -static struct s390_prng_data *p; +struct ppno_ws_s { + u32 res; + u32 reseed_counter; + u64 stream_bytes; + u8 V[112]; + u8 C[112]; +}; -/* copied from libica, use a non-zero initial parameter block */ -static unsigned char parm_block[32] = { -0x0F,0x2B,0x8E,0x63,0x8C,0x8E,0xD2,0x52,0x64,0xB7,0xA0,0x7B,0x75,0x28,0xB8,0xF4, -0x75,0x5F,0xD2,0xA6,0x8D,0x97,0x11,0xFF,0x49,0xD8,0x23,0xF3,0x7E,0x21,0xEC,0xA0, +struct prng_data_s { + struct mutex mutex; + union { + struct prng_ws_s prngws; + struct ppno_ws_s ppnows; + }; + u8 *buf; + u32 rest; + u8 *prev; }; -static int prng_open(struct inode *inode, struct file *file) +static struct prng_data_s *prng_data; + +/* initial parameter block for tdes mode, copied from libica */ +static const u8 initial_parm_block[32] __initconst = { + 0x0F, 0x2B, 0x8E, 0x63, 0x8C, 0x8E, 0xD2, 0x52, + 0x64, 0xB7, 0xA0, 0x7B, 0x75, 0x28, 0xB8, 0xF4, + 0x75, 0x5F, 0xD2, 0xA6, 0x8D, 0x97, 0x11, 0xFF, + 0x49, 0xD8, 0x23, 0xF3, 0x7E, 0x21, 0xEC, 0xA0 }; + + +/*** helper functions ***/ + +static int generate_entropy(u8 *ebuf, size_t nbytes) { - return nonseekable_open(inode, file); + int n, ret = 0; + u8 *pg, *h, hash[32]; + + pg = (u8 *) __get_free_page(GFP_KERNEL); + if (!pg) { + prng_errorflag = PRNG_GEN_ENTROPY_FAILED; + return -ENOMEM; + } + + while (nbytes) { + /* fill page with urandom bytes */ + get_random_bytes(pg, PAGE_SIZE); + /* exor page with stckf values */ + for (n = 0; n < sizeof(PAGE_SIZE/sizeof(u64)); n++) { + u64 *p = ((u64 *)pg) + n; + *p ^= get_tod_clock_fast(); + } + n = (nbytes < sizeof(hash)) ? nbytes : sizeof(hash); + if (n < sizeof(hash)) + h = hash; + else + h = ebuf; + /* generate sha256 from this page */ + if (crypt_s390_kimd(KIMD_SHA_256, h, + pg, PAGE_SIZE) != PAGE_SIZE) { + prng_errorflag = PRNG_GEN_ENTROPY_FAILED; + ret = -EIO; + goto out; + } + if (n < sizeof(hash)) + memcpy(ebuf, hash, n); + ret += n; + ebuf += n; + nbytes -= n; + } + +out: + free_page((unsigned long)pg); + return ret; } -static void prng_add_entropy(void) + +/*** tdes functions ***/ + +static void prng_tdes_add_entropy(void) { __u64 entropy[4]; unsigned int i; int ret; for (i = 0; i < 16; i++) { - ret = crypt_s390_kmc(KMC_PRNG, parm_block, (char *)entropy, - (char *)entropy, sizeof(entropy)); + ret = crypt_s390_kmc(KMC_PRNG, prng_data->prngws.parm_block, + (char *)entropy, (char *)entropy, + sizeof(entropy)); BUG_ON(ret < 0 || ret != sizeof(entropy)); - memcpy(parm_block, entropy, sizeof(entropy)); + memcpy(prng_data->prngws.parm_block, entropy, sizeof(entropy)); } } -static void prng_seed(int nbytes) + +static void prng_tdes_seed(int nbytes) { char buf[16]; int i = 0; - BUG_ON(nbytes > 16); + BUG_ON(nbytes > sizeof(buf)); + get_random_bytes(buf, nbytes); /* Add the entropy */ while (nbytes >= 8) { - *((__u64 *)parm_block) ^= *((__u64 *)(buf+i)); - prng_add_entropy(); + *((__u64 *)prng_data->prngws.parm_block) ^= *((__u64 *)(buf+i)); + prng_tdes_add_entropy(); i += 8; nbytes -= 8; } - prng_add_entropy(); + prng_tdes_add_entropy(); + prng_data->prngws.reseed_counter = 0; +} + + +static int __init prng_tdes_instantiate(void) +{ + int datalen; + + pr_debug("prng runs in TDES mode with " + "chunksize=%d and reseed_limit=%u\n", + prng_chunk_size, prng_reseed_limit); + + /* memory allocation, prng_data struct init, mutex init */ + datalen = sizeof(struct prng_data_s) + prng_chunk_size; + prng_data = kzalloc(datalen, GFP_KERNEL); + if (!prng_data) { + prng_errorflag = PRNG_INSTANTIATE_FAILED; + return -ENOMEM; + } + mutex_init(&prng_data->mutex); + prng_data->buf = ((u8 *)prng_data) + sizeof(struct prng_data_s); + memcpy(prng_data->prngws.parm_block, initial_parm_block, 32); + + /* initialize the PRNG, add 128 bits of entropy */ + prng_tdes_seed(16); + + return 0; } -static ssize_t prng_read(struct file *file, char __user *ubuf, size_t nbytes, - loff_t *ppos) + +static void prng_tdes_deinstantiate(void) +{ + pr_debug("The prng module stopped " + "after running in triple DES mode\n"); + kzfree(prng_data); +} + + +/*** sha512 functions ***/ + +static int __init prng_sha512_selftest(void) { - int chunk, n; + /* NIST DRBG testvector for Hash Drbg, Sha-512, Count #0 */ + static const u8 seed[] __initconst = { + 0x6b, 0x50, 0xa7, 0xd8, 0xf8, 0xa5, 0x5d, 0x7a, + 0x3d, 0xf8, 0xbb, 0x40, 0xbc, 0xc3, 0xb7, 0x22, + 0xd8, 0x70, 0x8d, 0xe6, 0x7f, 0xda, 0x01, 0x0b, + 0x03, 0xc4, 0xc8, 0x4d, 0x72, 0x09, 0x6f, 0x8c, + 0x3e, 0xc6, 0x49, 0xcc, 0x62, 0x56, 0xd9, 0xfa, + 0x31, 0xdb, 0x7a, 0x29, 0x04, 0xaa, 0xf0, 0x25 }; + static const u8 V0[] __initconst = { + 0x00, 0xad, 0xe3, 0x6f, 0x9a, 0x01, 0xc7, 0x76, + 0x61, 0x34, 0x35, 0xf5, 0x4e, 0x24, 0x74, 0x22, + 0x21, 0x9a, 0x29, 0x89, 0xc7, 0x93, 0x2e, 0x60, + 0x1e, 0xe8, 0x14, 0x24, 0x8d, 0xd5, 0x03, 0xf1, + 0x65, 0x5d, 0x08, 0x22, 0x72, 0xd5, 0xad, 0x95, + 0xe1, 0x23, 0x1e, 0x8a, 0xa7, 0x13, 0xd9, 0x2b, + 0x5e, 0xbc, 0xbb, 0x80, 0xab, 0x8d, 0xe5, 0x79, + 0xab, 0x5b, 0x47, 0x4e, 0xdd, 0xee, 0x6b, 0x03, + 0x8f, 0x0f, 0x5c, 0x5e, 0xa9, 0x1a, 0x83, 0xdd, + 0xd3, 0x88, 0xb2, 0x75, 0x4b, 0xce, 0x83, 0x36, + 0x57, 0x4b, 0xf1, 0x5c, 0xca, 0x7e, 0x09, 0xc0, + 0xd3, 0x89, 0xc6, 0xe0, 0xda, 0xc4, 0x81, 0x7e, + 0x5b, 0xf9, 0xe1, 0x01, 0xc1, 0x92, 0x05, 0xea, + 0xf5, 0x2f, 0xc6, 0xc6, 0xc7, 0x8f, 0xbc, 0xf4 }; + static const u8 C0[] __initconst = { + 0x00, 0xf4, 0xa3, 0xe5, 0xa0, 0x72, 0x63, 0x95, + 0xc6, 0x4f, 0x48, 0xd0, 0x8b, 0x5b, 0x5f, 0x8e, + 0x6b, 0x96, 0x1f, 0x16, 0xed, 0xbc, 0x66, 0x94, + 0x45, 0x31, 0xd7, 0x47, 0x73, 0x22, 0xa5, 0x86, + 0xce, 0xc0, 0x4c, 0xac, 0x63, 0xb8, 0x39, 0x50, + 0xbf, 0xe6, 0x59, 0x6c, 0x38, 0x58, 0x99, 0x1f, + 0x27, 0xa7, 0x9d, 0x71, 0x2a, 0xb3, 0x7b, 0xf9, + 0xfb, 0x17, 0x86, 0xaa, 0x99, 0x81, 0xaa, 0x43, + 0xe4, 0x37, 0xd3, 0x1e, 0x6e, 0xe5, 0xe6, 0xee, + 0xc2, 0xed, 0x95, 0x4f, 0x53, 0x0e, 0x46, 0x8a, + 0xcc, 0x45, 0xa5, 0xdb, 0x69, 0x0d, 0x81, 0xc9, + 0x32, 0x92, 0xbc, 0x8f, 0x33, 0xe6, 0xf6, 0x09, + 0x7c, 0x8e, 0x05, 0x19, 0x0d, 0xf1, 0xb6, 0xcc, + 0xf3, 0x02, 0x21, 0x90, 0x25, 0xec, 0xed, 0x0e }; + static const u8 random[] __initconst = { + 0x95, 0xb7, 0xf1, 0x7e, 0x98, 0x02, 0xd3, 0x57, + 0x73, 0x92, 0xc6, 0xa9, 0xc0, 0x80, 0x83, 0xb6, + 0x7d, 0xd1, 0x29, 0x22, 0x65, 0xb5, 0xf4, 0x2d, + 0x23, 0x7f, 0x1c, 0x55, 0xbb, 0x9b, 0x10, 0xbf, + 0xcf, 0xd8, 0x2c, 0x77, 0xa3, 0x78, 0xb8, 0x26, + 0x6a, 0x00, 0x99, 0x14, 0x3b, 0x3c, 0x2d, 0x64, + 0x61, 0x1e, 0xee, 0xb6, 0x9a, 0xcd, 0xc0, 0x55, + 0x95, 0x7c, 0x13, 0x9e, 0x8b, 0x19, 0x0c, 0x7a, + 0x06, 0x95, 0x5f, 0x2c, 0x79, 0x7c, 0x27, 0x78, + 0xde, 0x94, 0x03, 0x96, 0xa5, 0x01, 0xf4, 0x0e, + 0x91, 0x39, 0x6a, 0xcf, 0x8d, 0x7e, 0x45, 0xeb, + 0xdb, 0xb5, 0x3b, 0xbf, 0x8c, 0x97, 0x52, 0x30, + 0xd2, 0xf0, 0xff, 0x91, 0x06, 0xc7, 0x61, 0x19, + 0xae, 0x49, 0x8e, 0x7f, 0xbc, 0x03, 0xd9, 0x0f, + 0x8e, 0x4c, 0x51, 0x62, 0x7a, 0xed, 0x5c, 0x8d, + 0x42, 0x63, 0xd5, 0xd2, 0xb9, 0x78, 0x87, 0x3a, + 0x0d, 0xe5, 0x96, 0xee, 0x6d, 0xc7, 0xf7, 0xc2, + 0x9e, 0x37, 0xee, 0xe8, 0xb3, 0x4c, 0x90, 0xdd, + 0x1c, 0xf6, 0xa9, 0xdd, 0xb2, 0x2b, 0x4c, 0xbd, + 0x08, 0x6b, 0x14, 0xb3, 0x5d, 0xe9, 0x3d, 0xa2, + 0xd5, 0xcb, 0x18, 0x06, 0x69, 0x8c, 0xbd, 0x7b, + 0xbb, 0x67, 0xbf, 0xe3, 0xd3, 0x1f, 0xd2, 0xd1, + 0xdb, 0xd2, 0xa1, 0xe0, 0x58, 0xa3, 0xeb, 0x99, + 0xd7, 0xe5, 0x1f, 0x1a, 0x93, 0x8e, 0xed, 0x5e, + 0x1c, 0x1d, 0xe2, 0x3a, 0x6b, 0x43, 0x45, 0xd3, + 0x19, 0x14, 0x09, 0xf9, 0x2f, 0x39, 0xb3, 0x67, + 0x0d, 0x8d, 0xbf, 0xb6, 0x35, 0xd8, 0xe6, 0xa3, + 0x69, 0x32, 0xd8, 0x10, 0x33, 0xd1, 0x44, 0x8d, + 0x63, 0xb4, 0x03, 0xdd, 0xf8, 0x8e, 0x12, 0x1b, + 0x6e, 0x81, 0x9a, 0xc3, 0x81, 0x22, 0x6c, 0x13, + 0x21, 0xe4, 0xb0, 0x86, 0x44, 0xf6, 0x72, 0x7c, + 0x36, 0x8c, 0x5a, 0x9f, 0x7a, 0x4b, 0x3e, 0xe2 }; + int ret = 0; - int tmp; + u8 buf[sizeof(random)]; + struct ppno_ws_s ws; + + memset(&ws, 0, sizeof(ws)); + + /* initial seed */ + ret = crypt_s390_ppno(PPNO_SHA512_DRNG_SEED, + &ws, NULL, 0, + seed, sizeof(seed)); + if (ret < 0) { + pr_err("The prng self test seed operation for the " + "SHA-512 mode failed with rc=%d\n", ret); + prng_errorflag = PRNG_SELFTEST_FAILED; + return -EIO; + } + + /* check working states V and C */ + if (memcmp(ws.V, V0, sizeof(V0)) != 0 + || memcmp(ws.C, C0, sizeof(C0)) != 0) { + pr_err("The prng self test state test " + "for the SHA-512 mode failed\n"); + prng_errorflag = PRNG_SELFTEST_FAILED; + return -EIO; + } + + /* generate random bytes */ + ret = crypt_s390_ppno(PPNO_SHA512_DRNG_GEN, + &ws, buf, sizeof(buf), + NULL, 0); + if (ret < 0) { + pr_err("The prng self test generate operation for " + "the SHA-512 mode failed with rc=%d\n", ret); + prng_errorflag = PRNG_SELFTEST_FAILED; + return -EIO; + } + ret = crypt_s390_ppno(PPNO_SHA512_DRNG_GEN, + &ws, buf, sizeof(buf), + NULL, 0); + if (ret < 0) { + pr_err("The prng self test generate operation for " + "the SHA-512 mode failed with rc=%d\n", ret); + prng_errorflag = PRNG_SELFTEST_FAILED; + return -EIO; + } + + /* check against expected data */ + if (memcmp(buf, random, sizeof(random)) != 0) { + pr_err("The prng self test data test " + "for the SHA-512 mode failed\n"); + prng_errorflag = PRNG_SELFTEST_FAILED; + return -EIO; + } + + return 0; +} + + +static int __init prng_sha512_instantiate(void) +{ + int ret, datalen; + u8 seed[64]; + + pr_debug("prng runs in SHA-512 mode " + "with chunksize=%d and reseed_limit=%u\n", + prng_chunk_size, prng_reseed_limit); + + /* memory allocation, prng_data struct init, mutex init */ + datalen = sizeof(struct prng_data_s) + prng_chunk_size; + if (fips_enabled) + datalen += prng_chunk_size; + prng_data = kzalloc(datalen, GFP_KERNEL); + if (!prng_data) { + prng_errorflag = PRNG_INSTANTIATE_FAILED; + return -ENOMEM; + } + mutex_init(&prng_data->mutex); + prng_data->buf = ((u8 *)prng_data) + sizeof(struct prng_data_s); + + /* selftest */ + ret = prng_sha512_selftest(); + if (ret) + goto outfree; + + /* generate initial seed bytestring, first 48 bytes of entropy */ + ret = generate_entropy(seed, 48); + if (ret != 48) + goto outfree; + /* followed by 16 bytes of unique nonce */ + get_tod_clock_ext(seed + 48); + + /* initial seed of the ppno drng */ + ret = crypt_s390_ppno(PPNO_SHA512_DRNG_SEED, + &prng_data->ppnows, NULL, 0, + seed, sizeof(seed)); + if (ret < 0) { + prng_errorflag = PRNG_SEED_FAILED; + ret = -EIO; + goto outfree; + } + + /* if fips mode is enabled, generate a first block of random + bytes for the FIPS 140-2 Conditional Self Test */ + if (fips_enabled) { + prng_data->prev = prng_data->buf + prng_chunk_size; + ret = crypt_s390_ppno(PPNO_SHA512_DRNG_GEN, + &prng_data->ppnows, + prng_data->prev, + prng_chunk_size, + NULL, 0); + if (ret < 0 || ret != prng_chunk_size) { + prng_errorflag = PRNG_GEN_FAILED; + ret = -EIO; + goto outfree; + } + } + + return 0; + +outfree: + kfree(prng_data); + return ret; +} + + +static void prng_sha512_deinstantiate(void) +{ + pr_debug("The prng module stopped after running in SHA-512 mode\n"); + kzfree(prng_data); +} + + +static int prng_sha512_reseed(void) +{ + int ret; + u8 seed[32]; + + /* generate 32 bytes of fresh entropy */ + ret = generate_entropy(seed, sizeof(seed)); + if (ret != sizeof(seed)) + return ret; + + /* do a reseed of the ppno drng with this bytestring */ + ret = crypt_s390_ppno(PPNO_SHA512_DRNG_SEED, + &prng_data->ppnows, NULL, 0, + seed, sizeof(seed)); + if (ret) { + prng_errorflag = PRNG_RESEED_FAILED; + return -EIO; + } + + return 0; +} + + +static int prng_sha512_generate(u8 *buf, size_t nbytes) +{ + int ret; + + /* reseed needed ? */ + if (prng_data->ppnows.reseed_counter > prng_reseed_limit) { + ret = prng_sha512_reseed(); + if (ret) + return ret; + } + + /* PPNO generate */ + ret = crypt_s390_ppno(PPNO_SHA512_DRNG_GEN, + &prng_data->ppnows, buf, nbytes, + NULL, 0); + if (ret < 0 || ret != nbytes) { + prng_errorflag = PRNG_GEN_FAILED; + return -EIO; + } + + /* FIPS 140-2 Conditional Self Test */ + if (fips_enabled) { + if (!memcmp(prng_data->prev, buf, nbytes)) { + prng_errorflag = PRNG_GEN_FAILED; + return -EILSEQ; + } + memcpy(prng_data->prev, buf, nbytes); + } + + return ret; +} + + +/*** file io functions ***/ + +static int prng_open(struct inode *inode, struct file *file) +{ + return nonseekable_open(inode, file); +} + + +static ssize_t prng_tdes_read(struct file *file, char __user *ubuf, + size_t nbytes, loff_t *ppos) +{ + int chunk, n, tmp, ret = 0; + + /* lock prng_data struct */ + if (mutex_lock_interruptible(&prng_data->mutex)) + return -ERESTARTSYS; - /* nbytes can be arbitrary length, we split it into chunks */ while (nbytes) { - /* same as in extract_entropy_user in random.c */ if (need_resched()) { if (signal_pending(current)) { if (ret == 0) ret = -ERESTARTSYS; break; } + /* give mutex free before calling schedule() */ + mutex_unlock(&prng_data->mutex); schedule(); + /* occopy mutex again */ + if (mutex_lock_interruptible(&prng_data->mutex)) { + if (ret == 0) + ret = -ERESTARTSYS; + return ret; + } } /* @@ -112,12 +535,11 @@ static ssize_t prng_read(struct file *file, char __user *ubuf, size_t nbytes, /* PRNG only likes multiples of 8 bytes */ n = (chunk + 7) & -8; - if (p->count > prng_entropy_limit) - prng_seed(8); + if (prng_data->prngws.reseed_counter > prng_reseed_limit) + prng_tdes_seed(8); /* if the CPU supports PRNG stckf is present too */ - asm volatile(".insn s,0xb27c0000,%0" - : "=m" (*((unsigned long long *)p->buf)) : : "cc"); + *((unsigned long long *)prng_data->buf) = get_tod_clock_fast(); /* * Beside the STCKF the input for the TDES-EDE is the output @@ -132,35 +554,259 @@ static ssize_t prng_read(struct file *file, char __user *ubuf, size_t nbytes, * Note: you can still get strict X9.17 conformity by setting * prng_chunk_size to 8 bytes. */ - tmp = crypt_s390_kmc(KMC_PRNG, parm_block, p->buf, p->buf, n); - BUG_ON((tmp < 0) || (tmp != n)); + tmp = crypt_s390_kmc(KMC_PRNG, prng_data->prngws.parm_block, + prng_data->buf, prng_data->buf, n); + if (tmp < 0 || tmp != n) { + ret = -EIO; + break; + } - p->count += n; + prng_data->prngws.byte_counter += n; + prng_data->prngws.reseed_counter += n; - if (copy_to_user(ubuf, p->buf, chunk)) + if (copy_to_user(ubuf, prng_data->buf, chunk)) return -EFAULT; nbytes -= chunk; ret += chunk; ubuf += chunk; } + + /* unlock prng_data struct */ + mutex_unlock(&prng_data->mutex); + return ret; } -static const struct file_operations prng_fops = { + +static ssize_t prng_sha512_read(struct file *file, char __user *ubuf, + size_t nbytes, loff_t *ppos) +{ + int n, ret = 0; + u8 *p; + + /* if errorflag is set do nothing and return 'broken pipe' */ + if (prng_errorflag) + return -EPIPE; + + /* lock prng_data struct */ + if (mutex_lock_interruptible(&prng_data->mutex)) + return -ERESTARTSYS; + + while (nbytes) { + if (need_resched()) { + if (signal_pending(current)) { + if (ret == 0) + ret = -ERESTARTSYS; + break; + } + /* give mutex free before calling schedule() */ + mutex_unlock(&prng_data->mutex); + schedule(); + /* occopy mutex again */ + if (mutex_lock_interruptible(&prng_data->mutex)) { + if (ret == 0) + ret = -ERESTARTSYS; + return ret; + } + } + if (prng_data->rest) { + /* push left over random bytes from the previous read */ + p = prng_data->buf + prng_chunk_size - prng_data->rest; + n = (nbytes < prng_data->rest) ? + nbytes : prng_data->rest; + prng_data->rest -= n; + } else { + /* generate one chunk of random bytes into read buf */ + p = prng_data->buf; + n = prng_sha512_generate(p, prng_chunk_size); + if (n < 0) { + ret = n; + break; + } + if (nbytes < prng_chunk_size) { + n = nbytes; + prng_data->rest = prng_chunk_size - n; + } else { + n = prng_chunk_size; + prng_data->rest = 0; + } + } + if (copy_to_user(ubuf, p, n)) { + ret = -EFAULT; + break; + } + ubuf += n; + nbytes -= n; + ret += n; + } + + /* unlock prng_data struct */ + mutex_unlock(&prng_data->mutex); + + return ret; +} + + +/*** sysfs stuff ***/ + +static const struct file_operations prng_sha512_fops = { + .owner = THIS_MODULE, + .open = &prng_open, + .release = NULL, + .read = &prng_sha512_read, + .llseek = noop_llseek, +}; +static const struct file_operations prng_tdes_fops = { .owner = THIS_MODULE, .open = &prng_open, .release = NULL, - .read = &prng_read, + .read = &prng_tdes_read, .llseek = noop_llseek, }; -static struct miscdevice prng_dev = { +static struct miscdevice prng_sha512_dev = { + .name = "prandom", + .minor = MISC_DYNAMIC_MINOR, + .fops = &prng_sha512_fops, +}; +static struct miscdevice prng_tdes_dev = { .name = "prandom", .minor = MISC_DYNAMIC_MINOR, - .fops = &prng_fops, + .fops = &prng_tdes_fops, }; + +/* chunksize attribute (ro) */ +static ssize_t prng_chunksize_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%u\n", prng_chunk_size); +} +static DEVICE_ATTR(chunksize, 0444, prng_chunksize_show, NULL); + +/* counter attribute (ro) */ +static ssize_t prng_counter_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + u64 counter; + + if (mutex_lock_interruptible(&prng_data->mutex)) + return -ERESTARTSYS; + if (prng_mode == PRNG_MODE_SHA512) + counter = prng_data->ppnows.stream_bytes; + else + counter = prng_data->prngws.byte_counter; + mutex_unlock(&prng_data->mutex); + + return snprintf(buf, PAGE_SIZE, "%llu\n", counter); +} +static DEVICE_ATTR(byte_counter, 0444, prng_counter_show, NULL); + +/* errorflag attribute (ro) */ +static ssize_t prng_errorflag_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%d\n", prng_errorflag); +} +static DEVICE_ATTR(errorflag, 0444, prng_errorflag_show, NULL); + +/* mode attribute (ro) */ +static ssize_t prng_mode_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + if (prng_mode == PRNG_MODE_TDES) + return snprintf(buf, PAGE_SIZE, "TDES\n"); + else + return snprintf(buf, PAGE_SIZE, "SHA512\n"); +} +static DEVICE_ATTR(mode, 0444, prng_mode_show, NULL); + +/* reseed attribute (w) */ +static ssize_t prng_reseed_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + if (mutex_lock_interruptible(&prng_data->mutex)) + return -ERESTARTSYS; + prng_sha512_reseed(); + mutex_unlock(&prng_data->mutex); + + return count; +} +static DEVICE_ATTR(reseed, 0200, NULL, prng_reseed_store); + +/* reseed limit attribute (rw) */ +static ssize_t prng_reseed_limit_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%u\n", prng_reseed_limit); +} +static ssize_t prng_reseed_limit_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned limit; + + if (sscanf(buf, "%u\n", &limit) != 1) + return -EINVAL; + + if (prng_mode == PRNG_MODE_SHA512) { + if (limit < PRNG_RESEED_LIMIT_SHA512_LOWER) + return -EINVAL; + } else { + if (limit < PRNG_RESEED_LIMIT_TDES_LOWER) + return -EINVAL; + } + + prng_reseed_limit = limit; + + return count; +} +static DEVICE_ATTR(reseed_limit, 0644, + prng_reseed_limit_show, prng_reseed_limit_store); + +/* strength attribute (ro) */ +static ssize_t prng_strength_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "256\n"); +} +static DEVICE_ATTR(strength, 0444, prng_strength_show, NULL); + +static struct attribute *prng_sha512_dev_attrs[] = { + &dev_attr_errorflag.attr, + &dev_attr_chunksize.attr, + &dev_attr_byte_counter.attr, + &dev_attr_mode.attr, + &dev_attr_reseed.attr, + &dev_attr_reseed_limit.attr, + &dev_attr_strength.attr, + NULL +}; +static struct attribute *prng_tdes_dev_attrs[] = { + &dev_attr_chunksize.attr, + &dev_attr_byte_counter.attr, + &dev_attr_mode.attr, + NULL +}; + +static struct attribute_group prng_sha512_dev_attr_group = { + .attrs = prng_sha512_dev_attrs +}; +static struct attribute_group prng_tdes_dev_attr_group = { + .attrs = prng_tdes_dev_attrs +}; + + +/*** module init and exit ***/ + static int __init prng_init(void) { int ret; @@ -169,43 +815,105 @@ static int __init prng_init(void) if (!crypt_s390_func_available(KMC_PRNG, CRYPT_S390_MSA)) return -EOPNOTSUPP; - if (prng_chunk_size < 8) - return -EINVAL; + /* choose prng mode */ + if (prng_mode != PRNG_MODE_TDES) { + /* check for MSA5 support for PPNO operations */ + if (!crypt_s390_func_available(PPNO_SHA512_DRNG_GEN, + CRYPT_S390_MSA5)) { + if (prng_mode == PRNG_MODE_SHA512) { + pr_err("The prng module cannot " + "start in SHA-512 mode\n"); + return -EOPNOTSUPP; + } + prng_mode = PRNG_MODE_TDES; + } else + prng_mode = PRNG_MODE_SHA512; + } - p = kmalloc(sizeof(struct s390_prng_data), GFP_KERNEL); - if (!p) - return -ENOMEM; - p->count = 0; + if (prng_mode == PRNG_MODE_SHA512) { - p->buf = kmalloc(prng_chunk_size, GFP_KERNEL); - if (!p->buf) { - ret = -ENOMEM; - goto out_free; - } + /* SHA512 mode */ - /* initialize the PRNG, add 128 bits of entropy */ - prng_seed(16); + if (prng_chunk_size < PRNG_CHUNKSIZE_SHA512_MIN + || prng_chunk_size > PRNG_CHUNKSIZE_SHA512_MAX) + return -EINVAL; + prng_chunk_size = (prng_chunk_size + 0x3f) & ~0x3f; - ret = misc_register(&prng_dev); - if (ret) - goto out_buf; - return 0; + if (prng_reseed_limit == 0) + prng_reseed_limit = PRNG_RESEED_LIMIT_SHA512; + else if (prng_reseed_limit < PRNG_RESEED_LIMIT_SHA512_LOWER) + return -EINVAL; + + ret = prng_sha512_instantiate(); + if (ret) + goto out; + + ret = misc_register(&prng_sha512_dev); + if (ret) { + prng_sha512_deinstantiate(); + goto out; + } + ret = sysfs_create_group(&prng_sha512_dev.this_device->kobj, + &prng_sha512_dev_attr_group); + if (ret) { + misc_deregister(&prng_sha512_dev); + prng_sha512_deinstantiate(); + goto out; + } -out_buf: - kfree(p->buf); -out_free: - kfree(p); + } else { + + /* TDES mode */ + + if (prng_chunk_size < PRNG_CHUNKSIZE_TDES_MIN + || prng_chunk_size > PRNG_CHUNKSIZE_TDES_MAX) + return -EINVAL; + prng_chunk_size = (prng_chunk_size + 0x07) & ~0x07; + + if (prng_reseed_limit == 0) + prng_reseed_limit = PRNG_RESEED_LIMIT_TDES; + else if (prng_reseed_limit < PRNG_RESEED_LIMIT_TDES_LOWER) + return -EINVAL; + + ret = prng_tdes_instantiate(); + if (ret) + goto out; + + ret = misc_register(&prng_tdes_dev); + if (ret) { + prng_tdes_deinstantiate(); + goto out; + } + ret = sysfs_create_group(&prng_tdes_dev.this_device->kobj, + &prng_tdes_dev_attr_group); + if (ret) { + misc_deregister(&prng_tdes_dev); + prng_tdes_deinstantiate(); + goto out; + } + + } + +out: return ret; } + static void __exit prng_exit(void) { - /* wipe me */ - kzfree(p->buf); - kfree(p); - - misc_deregister(&prng_dev); + if (prng_mode == PRNG_MODE_SHA512) { + sysfs_remove_group(&prng_sha512_dev.this_device->kobj, + &prng_sha512_dev_attr_group); + misc_deregister(&prng_sha512_dev); + prng_sha512_deinstantiate(); + } else { + sysfs_remove_group(&prng_tdes_dev.this_device->kobj, + &prng_tdes_dev_attr_group); + misc_deregister(&prng_tdes_dev); + prng_tdes_deinstantiate(); + } } + module_init(prng_init); module_exit(prng_exit); diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h index 694bcd6bd927..2f924bc30e35 100644 --- a/arch/s390/include/asm/kexec.h +++ b/arch/s390/include/asm/kexec.h @@ -26,6 +26,9 @@ /* Not more than 2GB */ #define KEXEC_CONTROL_MEMORY_LIMIT (1UL<<31) +/* Allocate control page with GFP_DMA */ +#define KEXEC_CONTROL_MEMORY_GFP GFP_DMA + /* Maximum address we can use for the crash control pages */ #define KEXEC_CRASH_CONTROL_MEMORY_LIMIT (-1UL) diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index a5e656260a70..d29ad9545b41 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -14,7 +14,9 @@ typedef struct { unsigned long asce_bits; unsigned long asce_limit; unsigned long vdso_base; - /* The mmu context has extended page tables. */ + /* The mmu context allocates 4K page tables. */ + unsigned int alloc_pgste:1; + /* The mmu context uses extended page tables. */ unsigned int has_pgste:1; /* The mmu context uses storage keys. */ unsigned int use_skey:1; diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index d25d9ff10ba8..fb1b93ea3e3f 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -20,8 +20,11 @@ static inline int init_new_context(struct task_struct *tsk, mm->context.flush_mm = 0; mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS; mm->context.asce_bits |= _ASCE_TYPE_REGION3; +#ifdef CONFIG_PGSTE + mm->context.alloc_pgste = page_table_allocate_pgste; mm->context.has_pgste = 0; mm->context.use_skey = 0; +#endif mm->context.asce_limit = STACK_TOP_MAX; crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h index 51e7fb634ebc..7b7858f158b4 100644 --- a/arch/s390/include/asm/pgalloc.h +++ b/arch/s390/include/asm/pgalloc.h @@ -21,6 +21,7 @@ void crst_table_free(struct mm_struct *, unsigned long *); unsigned long *page_table_alloc(struct mm_struct *); void page_table_free(struct mm_struct *, unsigned long *); void page_table_free_rcu(struct mmu_gather *, unsigned long *, unsigned long); +extern int page_table_allocate_pgste; int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, unsigned long key, bool nq); diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 989cfae9e202..fc642399b489 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -12,12 +12,9 @@ #define _ASM_S390_PGTABLE_H /* - * The Linux memory management assumes a three-level page table setup. For - * s390 31 bit we "fold" the mid level into the top-level page table, so - * that we physically have the same two-level page table as the s390 mmu - * expects in 31 bit mode. For s390 64 bit we use three of the five levels - * the hardware provides (region first and region second tables are not - * used). + * The Linux memory management assumes a three-level page table setup. + * For s390 64 bit we use up to four of the five levels the hardware + * provides (region first tables are not used). * * The "pgd_xxx()" functions are trivial for a folded two-level * setup: the pgd is never bad, and a pmd always exists (as it's folded @@ -101,8 +98,8 @@ extern unsigned long zero_page_mask; #ifndef __ASSEMBLY__ /* - * The vmalloc and module area will always be on the topmost area of the kernel - * mapping. We reserve 96MB (31bit) / 128GB (64bit) for vmalloc and modules. + * The vmalloc and module area will always be on the topmost area of the + * kernel mapping. We reserve 128GB (64bit) for vmalloc and modules. * On 64 bit kernels we have a 2GB area at the top of the vmalloc area where * modules will reside. That makes sure that inter module branches always * happen without trampolines and in addition the placement within a 2GB frame @@ -131,38 +128,6 @@ static inline int is_module_addr(void *addr) } /* - * A 31 bit pagetable entry of S390 has following format: - * | PFRA | | OS | - * 0 0IP0 - * 00000000001111111111222222222233 - * 01234567890123456789012345678901 - * - * I Page-Invalid Bit: Page is not available for address-translation - * P Page-Protection Bit: Store access not possible for page - * - * A 31 bit segmenttable entry of S390 has following format: - * | P-table origin | |PTL - * 0 IC - * 00000000001111111111222222222233 - * 01234567890123456789012345678901 - * - * I Segment-Invalid Bit: Segment is not available for address-translation - * C Common-Segment Bit: Segment is not private (PoP 3-30) - * PTL Page-Table-Length: Page-table length (PTL+1*16 entries -> up to 256) - * - * The 31 bit segmenttable origin of S390 has following format: - * - * |S-table origin | | STL | - * X **GPS - * 00000000001111111111222222222233 - * 01234567890123456789012345678901 - * - * X Space-Switch event: - * G Segment-Invalid Bit: * - * P Private-Space Bit: Segment is not private (PoP 3-30) - * S Storage-Alteration: - * STL Segment-Table-Length: Segment-table length (STL+1*16 entries -> up to 2048) - * * A 64 bit pagetable entry of S390 has following format: * | PFRA |0IPC| OS | * 0000000000111111111122222222223333333333444444444455555555556666 @@ -220,7 +185,6 @@ static inline int is_module_addr(void *addr) /* Software bits in the page table entry */ #define _PAGE_PRESENT 0x001 /* SW pte present bit */ -#define _PAGE_TYPE 0x002 /* SW pte type bit */ #define _PAGE_YOUNG 0x004 /* SW pte young bit */ #define _PAGE_DIRTY 0x008 /* SW pte dirty bit */ #define _PAGE_READ 0x010 /* SW pte read bit */ @@ -240,31 +204,34 @@ static inline int is_module_addr(void *addr) * table lock held. * * The following table gives the different possible bit combinations for - * the pte hardware and software bits in the last 12 bits of a pte: + * the pte hardware and software bits in the last 12 bits of a pte + * (. unassigned bit, x don't care, t swap type): * * 842100000000 * 000084210000 * 000000008421 - * .IR...wrdytp - * empty .10...000000 - * swap .10...xxxx10 - * file .11...xxxxx0 - * prot-none, clean, old .11...000001 - * prot-none, clean, young .11...000101 - * prot-none, dirty, old .10...001001 - * prot-none, dirty, young .10...001101 - * read-only, clean, old .11...010001 - * read-only, clean, young .01...010101 - * read-only, dirty, old .11...011001 - * read-only, dirty, young .01...011101 - * read-write, clean, old .11...110001 - * read-write, clean, young .01...110101 - * read-write, dirty, old .10...111001 - * read-write, dirty, young .00...111101 + * .IR.uswrdy.p + * empty .10.00000000 + * swap .11..ttttt.0 + * prot-none, clean, old .11.xx0000.1 + * prot-none, clean, young .11.xx0001.1 + * prot-none, dirty, old .10.xx0010.1 + * prot-none, dirty, young .10.xx0011.1 + * read-only, clean, old .11.xx0100.1 + * read-only, clean, young .01.xx0101.1 + * read-only, dirty, old .11.xx0110.1 + * read-only, dirty, young .01.xx0111.1 + * read-write, clean, old .11.xx1100.1 + * read-write, clean, young .01.xx1101.1 + * read-write, dirty, old .10.xx1110.1 + * read-write, dirty, young .00.xx1111.1 + * HW-bits: R read-only, I invalid + * SW-bits: p present, y young, d dirty, r read, w write, s special, + * u unused, l large * - * pte_present is true for the bit pattern .xx...xxxxx1, (pte & 0x001) == 0x001 - * pte_none is true for the bit pattern .10...xxxx00, (pte & 0x603) == 0x400 - * pte_swap is true for the bit pattern .10...xxxx10, (pte & 0x603) == 0x402 + * pte_none is true for the bit pattern .10.00000000, pte == 0x400 + * pte_swap is true for the bit pattern .11..ooooo.0, (pte & 0x201) == 0x200 + * pte_present is true for the bit pattern .xx.xxxxxx.1, (pte & 0x001) == 0x001 */ /* Bits in the segment/region table address-space-control-element */ @@ -335,6 +302,8 @@ static inline int is_module_addr(void *addr) * read-write, dirty, young 11..0...0...11 * The segment table origin is used to distinguish empty (origin==0) from * read-write, old segment table entries (origin!=0) + * HW-bits: R read-only, I invalid + * SW-bits: y young, d dirty, r read, w write */ #define _SEGMENT_ENTRY_SPLIT_BIT 11 /* THP splitting bit number */ @@ -423,6 +392,15 @@ static inline int mm_has_pgste(struct mm_struct *mm) return 0; } +static inline int mm_alloc_pgste(struct mm_struct *mm) +{ +#ifdef CONFIG_PGSTE + if (unlikely(mm->context.alloc_pgste)) + return 1; +#endif + return 0; +} + /* * In the case that a guest uses storage keys * faults should no longer be backed by zero pages @@ -582,10 +560,9 @@ static inline int pte_none(pte_t pte) static inline int pte_swap(pte_t pte) { - /* Bit pattern: (pte & 0x603) == 0x402 */ - return (pte_val(pte) & (_PAGE_INVALID | _PAGE_PROTECT | - _PAGE_TYPE | _PAGE_PRESENT)) - == (_PAGE_INVALID | _PAGE_TYPE); + /* Bit pattern: (pte & 0x201) == 0x200 */ + return (pte_val(pte) & (_PAGE_PROTECT | _PAGE_PRESENT)) + == _PAGE_PROTECT; } static inline int pte_special(pte_t pte) @@ -1586,51 +1563,51 @@ static inline int has_transparent_hugepage(void) #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* - * 31 bit swap entry format: - * A page-table entry has some bits we have to treat in a special way. - * Bits 0, 20 and bit 23 have to be zero, otherwise an specification - * exception will occur instead of a page translation exception. The - * specifiation exception has the bad habit not to store necessary - * information in the lowcore. - * Bits 21, 22, 30 and 31 are used to indicate the page type. - * A swap pte is indicated by bit pattern (pte & 0x603) == 0x402 - * This leaves the bits 1-19 and bits 24-29 to store type and offset. - * We use the 5 bits from 25-29 for the type and the 20 bits from 1-19 - * plus 24 for the offset. - * 0| offset |0110|o|type |00| - * 0 0000000001111111111 2222 2 22222 33 - * 0 1234567890123456789 0123 4 56789 01 - * * 64 bit swap entry format: * A page-table entry has some bits we have to treat in a special way. * Bits 52 and bit 55 have to be zero, otherwise an specification * exception will occur instead of a page translation exception. The * specifiation exception has the bad habit not to store necessary * information in the lowcore. - * Bits 53, 54, 62 and 63 are used to indicate the page type. - * A swap pte is indicated by bit pattern (pte & 0x603) == 0x402 - * This leaves the bits 0-51 and bits 56-61 to store type and offset. - * We use the 5 bits from 57-61 for the type and the 53 bits from 0-51 - * plus 56 for the offset. - * | offset |0110|o|type |00| - * 0000000000111111111122222222223333333333444444444455 5555 5 55566 66 - * 0123456789012345678901234567890123456789012345678901 2345 6 78901 23 + * Bits 54 and 63 are used to indicate the page type. + * A swap pte is indicated by bit pattern (pte & 0x201) == 0x200 + * This leaves the bits 0-51 and bits 56-62 to store type and offset. + * We use the 5 bits from 57-61 for the type and the 52 bits from 0-51 + * for the offset. + * | offset |01100|type |00| + * |0000000000111111111122222222223333333333444444444455|55555|55566|66| + * |0123456789012345678901234567890123456789012345678901|23456|78901|23| */ -#define __SWP_OFFSET_MASK (~0UL >> 11) +#define __SWP_OFFSET_MASK ((1UL << 52) - 1) +#define __SWP_OFFSET_SHIFT 12 +#define __SWP_TYPE_MASK ((1UL << 5) - 1) +#define __SWP_TYPE_SHIFT 2 static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) { pte_t pte; - offset &= __SWP_OFFSET_MASK; - pte_val(pte) = _PAGE_INVALID | _PAGE_TYPE | ((type & 0x1f) << 2) | - ((offset & 1UL) << 7) | ((offset & ~1UL) << 11); + + pte_val(pte) = _PAGE_INVALID | _PAGE_PROTECT; + pte_val(pte) |= (offset & __SWP_OFFSET_MASK) << __SWP_OFFSET_SHIFT; + pte_val(pte) |= (type & __SWP_TYPE_MASK) << __SWP_TYPE_SHIFT; return pte; } -#define __swp_type(entry) (((entry).val >> 2) & 0x1f) -#define __swp_offset(entry) (((entry).val >> 11) | (((entry).val >> 7) & 1)) -#define __swp_entry(type,offset) ((swp_entry_t) { pte_val(mk_swap_pte((type),(offset))) }) +static inline unsigned long __swp_type(swp_entry_t entry) +{ + return (entry.val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK; +} + +static inline unsigned long __swp_offset(swp_entry_t entry) +{ + return (entry.val >> __SWP_OFFSET_SHIFT) & __SWP_OFFSET_MASK; +} + +static inline swp_entry_t __swp_entry(unsigned long type, unsigned long offset) +{ + return (swp_entry_t) { pte_val(mk_swap_pte(type, offset)) }; +} #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(x) ((pte_t) { (x).val }) diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 210ffede0153..e617e74b7be2 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -14,20 +14,23 @@ static inline pmd_t __pte_to_pmd(pte_t pte) /* * Convert encoding pte bits pmd bits - * .IR...wrdytp dy..R...I...wr - * empty .10...000000 -> 00..0...1...00 - * prot-none, clean, old .11...000001 -> 00..1...1...00 - * prot-none, clean, young .11...000101 -> 01..1...1...00 - * prot-none, dirty, old .10...001001 -> 10..1...1...00 - * prot-none, dirty, young .10...001101 -> 11..1...1...00 - * read-only, clean, old .11...010001 -> 00..1...1...01 - * read-only, clean, young .01...010101 -> 01..1...0...01 - * read-only, dirty, old .11...011001 -> 10..1...1...01 - * read-only, dirty, young .01...011101 -> 11..1...0...01 - * read-write, clean, old .11...110001 -> 00..0...1...11 - * read-write, clean, young .01...110101 -> 01..0...0...11 - * read-write, dirty, old .10...111001 -> 10..0...1...11 - * read-write, dirty, young .00...111101 -> 11..0...0...11 + * lIR.uswrdy.p dy..R...I...wr + * empty 010.000000.0 -> 00..0...1...00 + * prot-none, clean, old 111.000000.1 -> 00..1...1...00 + * prot-none, clean, young 111.000001.1 -> 01..1...1...00 + * prot-none, dirty, old 111.000010.1 -> 10..1...1...00 + * prot-none, dirty, young 111.000011.1 -> 11..1...1...00 + * read-only, clean, old 111.000100.1 -> 00..1...1...01 + * read-only, clean, young 101.000101.1 -> 01..1...0...01 + * read-only, dirty, old 111.000110.1 -> 10..1...1...01 + * read-only, dirty, young 101.000111.1 -> 11..1...0...01 + * read-write, clean, old 111.001100.1 -> 00..1...1...11 + * read-write, clean, young 101.001101.1 -> 01..1...0...11 + * read-write, dirty, old 110.001110.1 -> 10..0...1...11 + * read-write, dirty, young 100.001111.1 -> 11..0...0...11 + * HW-bits: R read-only, I invalid + * SW-bits: p present, y young, d dirty, r read, w write, s special, + * u unused, l large */ if (pte_present(pte)) { pmd_val(pmd) = pte_val(pte) & PAGE_MASK; @@ -48,20 +51,23 @@ static inline pte_t __pmd_to_pte(pmd_t pmd) /* * Convert encoding pmd bits pte bits - * dy..R...I...wr .IR...wrdytp - * empty 00..0...1...00 -> .10...001100 - * prot-none, clean, old 00..0...1...00 -> .10...000001 - * prot-none, clean, young 01..0...1...00 -> .10...000101 - * prot-none, dirty, old 10..0...1...00 -> .10...001001 - * prot-none, dirty, young 11..0...1...00 -> .10...001101 - * read-only, clean, old 00..1...1...01 -> .11...010001 - * read-only, clean, young 01..1...1...01 -> .11...010101 - * read-only, dirty, old 10..1...1...01 -> .11...011001 - * read-only, dirty, young 11..1...1...01 -> .11...011101 - * read-write, clean, old 00..0...1...11 -> .10...110001 - * read-write, clean, young 01..0...1...11 -> .10...110101 - * read-write, dirty, old 10..0...1...11 -> .10...111001 - * read-write, dirty, young 11..0...1...11 -> .10...111101 + * dy..R...I...wr lIR.uswrdy.p + * empty 00..0...1...00 -> 010.000000.0 + * prot-none, clean, old 00..1...1...00 -> 111.000000.1 + * prot-none, clean, young 01..1...1...00 -> 111.000001.1 + * prot-none, dirty, old 10..1...1...00 -> 111.000010.1 + * prot-none, dirty, young 11..1...1...00 -> 111.000011.1 + * read-only, clean, old 00..1...1...01 -> 111.000100.1 + * read-only, clean, young 01..1...0...01 -> 101.000101.1 + * read-only, dirty, old 10..1...1...01 -> 111.000110.1 + * read-only, dirty, young 11..1...0...01 -> 101.000111.1 + * read-write, clean, old 00..1...1...11 -> 111.001100.1 + * read-write, clean, young 01..1...0...11 -> 101.001101.1 + * read-write, dirty, old 10..0...1...11 -> 110.001110.1 + * read-write, dirty, young 11..0...0...11 -> 100.001111.1 + * HW-bits: R read-only, I invalid + * SW-bits: p present, y young, d dirty, r read, w write, s special, + * u unused, l large */ if (pmd_present(pmd)) { pte_val(pte) = pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN_LARGE; @@ -70,8 +76,8 @@ static inline pte_t __pmd_to_pte(pmd_t pmd) pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_WRITE) << 4; pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_INVALID) << 5; pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT); - pmd_val(pmd) |= (pte_val(pte) & _PAGE_DIRTY) << 10; - pmd_val(pmd) |= (pte_val(pte) & _PAGE_YOUNG) << 10; + pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_DIRTY) >> 10; + pte_val(pte) |= (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) >> 10; } else pte_val(pte) = _PAGE_INVALID; return pte; diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 33f589459113..b33f66110ca9 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -18,6 +18,7 @@ #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/swapops.h> +#include <linux/sysctl.h> #include <linux/ksm.h> #include <linux/mman.h> @@ -920,6 +921,40 @@ unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr) } EXPORT_SYMBOL(get_guest_storage_key); +static int page_table_allocate_pgste_min = 0; +static int page_table_allocate_pgste_max = 1; +int page_table_allocate_pgste = 0; +EXPORT_SYMBOL(page_table_allocate_pgste); + +static struct ctl_table page_table_sysctl[] = { + { + .procname = "allocate_pgste", + .data = &page_table_allocate_pgste, + .maxlen = sizeof(int), + .mode = S_IRUGO | S_IWUSR, + .proc_handler = proc_dointvec, + .extra1 = &page_table_allocate_pgste_min, + .extra2 = &page_table_allocate_pgste_max, + }, + { } +}; + +static struct ctl_table page_table_sysctl_dir[] = { + { + .procname = "vm", + .maxlen = 0, + .mode = 0555, + .child = page_table_sysctl, + }, + { } +}; + +static int __init page_table_register_sysctl(void) +{ + return register_sysctl_table(page_table_sysctl_dir) ? 0 : -ENOMEM; +} +__initcall(page_table_register_sysctl); + #else /* CONFIG_PGSTE */ static inline int page_table_with_pgste(struct page *page) @@ -963,7 +998,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm) struct page *uninitialized_var(page); unsigned int mask, bit; - if (mm_has_pgste(mm)) + if (mm_alloc_pgste(mm)) return page_table_alloc_pgste(mm); /* Allocate fragments of a 4K page as 1K/2K page table */ spin_lock_bh(&mm->context.list_lock); @@ -1165,116 +1200,25 @@ static inline void thp_split_mm(struct mm_struct *mm) } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ -static unsigned long page_table_realloc_pmd(struct mmu_gather *tlb, - struct mm_struct *mm, pud_t *pud, - unsigned long addr, unsigned long end) -{ - unsigned long next, *table, *new; - struct page *page; - spinlock_t *ptl; - pmd_t *pmd; - - pmd = pmd_offset(pud, addr); - do { - next = pmd_addr_end(addr, end); -again: - if (pmd_none_or_clear_bad(pmd)) - continue; - table = (unsigned long *) pmd_deref(*pmd); - page = pfn_to_page(__pa(table) >> PAGE_SHIFT); - if (page_table_with_pgste(page)) - continue; - /* Allocate new page table with pgstes */ - new = page_table_alloc_pgste(mm); - if (!new) - return -ENOMEM; - - ptl = pmd_lock(mm, pmd); - if (likely((unsigned long *) pmd_deref(*pmd) == table)) { - /* Nuke pmd entry pointing to the "short" page table */ - pmdp_flush_lazy(mm, addr, pmd); - pmd_clear(pmd); - /* Copy ptes from old table to new table */ - memcpy(new, table, PAGE_SIZE/2); - clear_table(table, _PAGE_INVALID, PAGE_SIZE/2); - /* Establish new table */ - pmd_populate(mm, pmd, (pte_t *) new); - /* Free old table with rcu, there might be a walker! */ - page_table_free_rcu(tlb, table, addr); - new = NULL; - } - spin_unlock(ptl); - if (new) { - page_table_free_pgste(new); - goto again; - } - } while (pmd++, addr = next, addr != end); - - return addr; -} - -static unsigned long page_table_realloc_pud(struct mmu_gather *tlb, - struct mm_struct *mm, pgd_t *pgd, - unsigned long addr, unsigned long end) -{ - unsigned long next; - pud_t *pud; - - pud = pud_offset(pgd, addr); - do { - next = pud_addr_end(addr, end); - if (pud_none_or_clear_bad(pud)) - continue; - next = page_table_realloc_pmd(tlb, mm, pud, addr, next); - if (unlikely(IS_ERR_VALUE(next))) - return next; - } while (pud++, addr = next, addr != end); - - return addr; -} - -static unsigned long page_table_realloc(struct mmu_gather *tlb, struct mm_struct *mm, - unsigned long addr, unsigned long end) -{ - unsigned long next; - pgd_t *pgd; - - pgd = pgd_offset(mm, addr); - do { - next = pgd_addr_end(addr, end); - if (pgd_none_or_clear_bad(pgd)) - continue; - next = page_table_realloc_pud(tlb, mm, pgd, addr, next); - if (unlikely(IS_ERR_VALUE(next))) - return next; - } while (pgd++, addr = next, addr != end); - - return 0; -} - /* * switch on pgstes for its userspace process (for kvm) */ int s390_enable_sie(void) { - struct task_struct *tsk = current; - struct mm_struct *mm = tsk->mm; - struct mmu_gather tlb; + struct mm_struct *mm = current->mm; /* Do we have pgstes? if yes, we are done */ - if (mm_has_pgste(tsk->mm)) + if (mm_has_pgste(mm)) return 0; - + /* Fail if the page tables are 2K */ + if (!mm_alloc_pgste(mm)) + return -EINVAL; down_write(&mm->mmap_sem); + mm->context.has_pgste = 1; /* split thp mappings and disable thp for future mappings */ thp_split_mm(mm); - /* Reallocate the page tables with pgstes */ - tlb_gather_mmu(&tlb, mm, 0, TASK_SIZE); - if (!page_table_realloc(&tlb, mm, 0, TASK_SIZE)) - mm->context.has_pgste = 1; - tlb_finish_mmu(&tlb, 0, TASK_SIZE); up_write(&mm->mmap_sem); - return mm->context.has_pgste ? 0 : -ENOMEM; + return 0; } EXPORT_SYMBOL_GPL(s390_enable_sie); diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c index 6873f006f7d0..d366675e4bf8 100644 --- a/arch/tile/kernel/setup.c +++ b/arch/tile/kernel/setup.c @@ -774,7 +774,7 @@ static void __init zone_sizes_init(void) * though, there'll be no lowmem, so we just alloc_bootmem * the memmap. There will be no percpu memory either. */ - if (i != 0 && cpumask_test_cpu(i, &isolnodes)) { + if (i != 0 && node_isset(i, isolnodes)) { node_memmap_pfn[i] = alloc_bootmem_pfn(0, memmap_size, 0); BUG_ON(node_percpu[i] != 0); diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index ef17683484e9..48304b89b601 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -1109,6 +1109,8 @@ struct boot_params *make_boot_params(struct efi_config *c) if (!cmdline_ptr) goto fail; hdr->cmd_line_ptr = (unsigned long)cmdline_ptr; + /* Fill in upper bits of command line address, NOP on 32 bit */ + boot_params->ext_cmd_line_ptr = (u64)(unsigned long)cmdline_ptr >> 32; hdr->ramdisk_image = 0; hdr->ramdisk_size = 0; diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index e42f758a0fbd..055ea9941dd5 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -50,7 +50,7 @@ extern const struct hypervisor_x86 *x86_hyper; /* Recognized hypervisors */ extern const struct hypervisor_x86 x86_hyper_vmware; extern const struct hypervisor_x86 x86_hyper_ms_hyperv; -extern const struct hypervisor_x86 x86_hyper_xen_hvm; +extern const struct hypervisor_x86 x86_hyper_xen; extern const struct hypervisor_x86 x86_hyper_kvm; extern void init_hypervisor(struct cpuinfo_x86 *c); diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 25b1cc07d496..d6b078e9fa28 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -95,7 +95,6 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, struct pvclock_vsyscall_time_info { struct pvclock_vcpu_time_info pvti; - u32 migrate_count; } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index cf87de3fc390..64b611782ef0 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -169,7 +169,7 @@ static inline int arch_spin_is_contended(arch_spinlock_t *lock) struct __raw_tickets tmp = READ_ONCE(lock->tickets); tmp.head &= ~TICKET_SLOWPATH_FLAG; - return (tmp.tail - tmp.head) > TICKET_LOCK_INC; + return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC; } #define arch_spin_is_contended arch_spin_is_contended diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 358dcd338915..c44a5d53e464 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -269,4 +269,9 @@ static inline bool xen_arch_need_swiotlb(struct device *dev, return false; } +static inline unsigned long xen_get_swiotlb_free_pages(unsigned int order) +{ + return __get_free_pages(__GFP_NOWARN, order); +} + #endif /* _ASM_X86_XEN_PAGE_H */ diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index 36ce402a3fa5..d820d8eae96b 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -27,8 +27,8 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] = { -#ifdef CONFIG_XEN_PVHVM - &x86_hyper_xen_hvm, +#ifdef CONFIG_XEN + &x86_hyper_xen, #endif &x86_hyper_vmware, &x86_hyper_ms_hyperv, diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 219d3fb423a1..3998131d1a68 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1134,7 +1134,7 @@ static __initconst const u64 slm_hw_cache_extra_regs [ C(LL ) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = SLM_DMND_READ|SLM_LLC_ACCESS, - [ C(RESULT_MISS) ] = SLM_DMND_READ|SLM_LLC_MISS, + [ C(RESULT_MISS) ] = 0, }, [ C(OP_WRITE) ] = { [ C(RESULT_ACCESS) ] = SLM_DMND_WRITE|SLM_LLC_ACCESS, @@ -1184,8 +1184,7 @@ static __initconst const u64 slm_hw_cache_event_ids [ C(OP_READ) ] = { /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */ [ C(RESULT_ACCESS) ] = 0x01b7, - /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */ - [ C(RESULT_MISS) ] = 0x01b7, + [ C(RESULT_MISS) ] = 0, }, [ C(OP_WRITE) ] = { /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */ @@ -1217,7 +1216,7 @@ static __initconst const u64 slm_hw_cache_event_ids [ C(ITLB) ] = { [ C(OP_READ) ] = { [ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */ - [ C(RESULT_MISS) ] = 0x0282, /* ITLB.MISSES */ + [ C(RESULT_MISS) ] = 0x40205, /* PAGE_WALKS.I_SIDE_WALKS */ }, [ C(OP_WRITE) ] = { [ C(RESULT_ACCESS) ] = -1, @@ -2533,34 +2532,6 @@ ssize_t intel_event_sysfs_show(char *page, u64 config) return x86_event_sysfs_show(page, config, event); } -static __initconst const struct x86_pmu core_pmu = { - .name = "core", - .handle_irq = x86_pmu_handle_irq, - .disable_all = x86_pmu_disable_all, - .enable_all = core_pmu_enable_all, - .enable = core_pmu_enable_event, - .disable = x86_pmu_disable_event, - .hw_config = x86_pmu_hw_config, - .schedule_events = x86_schedule_events, - .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, - .perfctr = MSR_ARCH_PERFMON_PERFCTR0, - .event_map = intel_pmu_event_map, - .max_events = ARRAY_SIZE(intel_perfmon_event_map), - .apic = 1, - /* - * Intel PMCs cannot be accessed sanely above 32 bit width, - * so we install an artificial 1<<31 period regardless of - * the generic event period: - */ - .max_period = (1ULL << 31) - 1, - .get_event_constraints = intel_get_event_constraints, - .put_event_constraints = intel_put_event_constraints, - .event_constraints = intel_core_event_constraints, - .guest_get_msrs = core_guest_get_msrs, - .format_attrs = intel_arch_formats_attr, - .events_sysfs_show = intel_event_sysfs_show, -}; - struct intel_shared_regs *allocate_shared_regs(int cpu) { struct intel_shared_regs *regs; @@ -2743,6 +2714,44 @@ static struct attribute *intel_arch3_formats_attr[] = { NULL, }; +static __initconst const struct x86_pmu core_pmu = { + .name = "core", + .handle_irq = x86_pmu_handle_irq, + .disable_all = x86_pmu_disable_all, + .enable_all = core_pmu_enable_all, + .enable = core_pmu_enable_event, + .disable = x86_pmu_disable_event, + .hw_config = x86_pmu_hw_config, + .schedule_events = x86_schedule_events, + .eventsel = MSR_ARCH_PERFMON_EVENTSEL0, + .perfctr = MSR_ARCH_PERFMON_PERFCTR0, + .event_map = intel_pmu_event_map, + .max_events = ARRAY_SIZE(intel_perfmon_event_map), + .apic = 1, + /* + * Intel PMCs cannot be accessed sanely above 32-bit width, + * so we install an artificial 1<<31 period regardless of + * the generic event period: + */ + .max_period = (1ULL<<31) - 1, + .get_event_constraints = intel_get_event_constraints, + .put_event_constraints = intel_put_event_constraints, + .event_constraints = intel_core_event_constraints, + .guest_get_msrs = core_guest_get_msrs, + .format_attrs = intel_arch_formats_attr, + .events_sysfs_show = intel_event_sysfs_show, + + /* + * Virtual (or funny metal) CPU can define x86_pmu.extra_regs + * together with PMU version 1 and thus be using core_pmu with + * shared_regs. We need following callbacks here to allocate + * it properly. + */ + .cpu_prepare = intel_pmu_cpu_prepare, + .cpu_starting = intel_pmu_cpu_starting, + .cpu_dying = intel_pmu_cpu_dying, +}; + static __initconst const struct x86_pmu intel_pmu = { .name = "Intel", .handle_irq = intel_pmu_handle_irq, diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index 999289b94025..358c54ad20d4 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -722,6 +722,7 @@ static int __init rapl_pmu_init(void) break; case 60: /* Haswell */ case 69: /* Haswell-Celeron */ + case 61: /* Broadwell */ rapl_cntr_mask = RAPL_IDX_HSW; rapl_pmu_events_group.attrs = rapl_events_hsw_attr; break; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c index 3001015b755c..4562e9e22c60 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -1,6 +1,13 @@ /* Nehalem/SandBridge/Haswell uncore support */ #include "perf_event_intel_uncore.h" +/* Uncore IMC PCI IDs */ +#define PCI_DEVICE_ID_INTEL_SNB_IMC 0x0100 +#define PCI_DEVICE_ID_INTEL_IVB_IMC 0x0154 +#define PCI_DEVICE_ID_INTEL_IVB_E3_IMC 0x0150 +#define PCI_DEVICE_ID_INTEL_HSW_IMC 0x0c00 +#define PCI_DEVICE_ID_INTEL_HSW_U_IMC 0x0a04 + /* SNB event control */ #define SNB_UNC_CTL_EV_SEL_MASK 0x000000ff #define SNB_UNC_CTL_UMASK_MASK 0x0000ff00 @@ -472,6 +479,10 @@ static const struct pci_device_id hsw_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC), .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), }, + { /* IMC */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_U_IMC), + .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0), + }, { /* end: all zeroes */ }, }; @@ -502,6 +513,7 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = { IMC_DEV(IVB_IMC, &ivb_uncore_pci_driver), /* 3rd Gen Core processor */ IMC_DEV(IVB_E3_IMC, &ivb_uncore_pci_driver), /* Xeon E3-1200 v2/3rd Gen Core processor */ IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core Processor */ + IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver), /* 4th Gen Core ULT Mobile Processor */ { /* end marker */ } }; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 8213da62b1b7..6e338e3b1dc0 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -57,7 +57,7 @@ __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = { .io_bitmap = { [0 ... IO_BITMAP_LONGS] = ~0 }, #endif }; -EXPORT_PER_CPU_SYMBOL_GPL(cpu_tss); +EXPORT_PER_CPU_SYMBOL(cpu_tss); #ifdef CONFIG_X86_64 static DEFINE_PER_CPU(unsigned char, is_idle); @@ -156,11 +156,13 @@ void flush_thread(void) /* FPU state will be reallocated lazily at the first use. */ drop_fpu(tsk); free_thread_xstate(tsk); - } else if (!used_math()) { - /* kthread execs. TODO: cleanup this horror. */ - if (WARN_ON(init_fpu(tsk))) - force_sig(SIGKILL, tsk); - user_fpu_begin(); + } else { + if (!tsk_used_math(tsk)) { + /* kthread execs. TODO: cleanup this horror. */ + if (WARN_ON(init_fpu(tsk))) + force_sig(SIGKILL, tsk); + user_fpu_begin(); + } restore_init_xstate(); } } diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index e5ecd20e72dd..2f355d229a58 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -141,46 +141,7 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } -static struct pvclock_vsyscall_time_info *pvclock_vdso_info; - -static struct pvclock_vsyscall_time_info * -pvclock_get_vsyscall_user_time_info(int cpu) -{ - if (!pvclock_vdso_info) { - BUG(); - return NULL; - } - - return &pvclock_vdso_info[cpu]; -} - -struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu) -{ - return &pvclock_get_vsyscall_user_time_info(cpu)->pvti; -} - #ifdef CONFIG_X86_64 -static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, - void *v) -{ - struct task_migration_notifier *mn = v; - struct pvclock_vsyscall_time_info *pvti; - - pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu); - - /* this is NULL when pvclock vsyscall is not initialized */ - if (unlikely(pvti == NULL)) - return NOTIFY_DONE; - - pvti->migrate_count++; - - return NOTIFY_DONE; -} - -static struct notifier_block pvclock_migrate = { - .notifier_call = pvclock_task_migrate, -}; - /* * Initialize the generic pvclock vsyscall state. This will allocate * a/some page(s) for the per-vcpu pvclock information, set up a @@ -194,17 +155,12 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); - pvclock_vdso_info = i; - for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, __pa(i) + (idx*PAGE_SIZE), PAGE_KERNEL_VVAR); } - - register_task_migration_notifier(&pvclock_migrate); - return 0; } #endif diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ed31c31b2485..c73efcd03e29 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1669,12 +1669,28 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) &guest_hv_clock, sizeof(guest_hv_clock)))) return 0; - /* - * The interface expects us to write an even number signaling that the - * update is finished. Since the guest won't see the intermediate - * state, we just increase by 2 at the end. + /* This VCPU is paused, but it's legal for a guest to read another + * VCPU's kvmclock, so we really have to follow the specification where + * it says that version is odd if data is being modified, and even after + * it is consistent. + * + * Version field updates must be kept separate. This is because + * kvm_write_guest_cached might use a "rep movs" instruction, and + * writes within a string instruction are weakly ordered. So there + * are three writes overall. + * + * As a small optimization, only write the version field in the first + * and third write. The vcpu->pv_time cache is still valid, because the + * version field is the first in the struct. */ - vcpu->hv_clock.version = guest_hv_clock.version + 2; + BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0); + + vcpu->hv_clock.version = guest_hv_clock.version + 1; + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock.version)); + + smp_wmb(); /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */ pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED); @@ -1695,6 +1711,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) kvm_write_guest_cached(v->kvm, &vcpu->pv_time, &vcpu->hv_clock, sizeof(vcpu->hv_clock)); + + smp_wmb(); + + vcpu->hv_clock.version++; + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock.version)); return 0; } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 5ead4d6cf3a7..70e7444c6835 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -351,18 +351,20 @@ int arch_ioremap_pmd_supported(void) */ void *xlate_dev_mem_ptr(phys_addr_t phys) { - void *addr; - unsigned long start = phys & PAGE_MASK; + unsigned long start = phys & PAGE_MASK; + unsigned long offset = phys & ~PAGE_MASK; + unsigned long vaddr; /* If page is RAM, we can use __va. Otherwise ioremap and unmap. */ if (page_is_ram(start >> PAGE_SHIFT)) return __va(phys); - addr = (void __force *)ioremap_cache(start, PAGE_SIZE); - if (addr) - addr = (void *)((unsigned long)addr | (phys & ~PAGE_MASK)); + vaddr = (unsigned long)ioremap_cache(start, PAGE_SIZE); + /* Only add the offset on success and return NULL if the ioremap() failed: */ + if (vaddr) + vaddr += offset; - return addr; + return (void *)vaddr; } void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 987514396c1e..99f76103c6b7 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -559,6 +559,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, if (is_ereg(dst_reg)) EMIT1(0x41); EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8); + + /* emit 'movzwl eax, ax' */ + if (is_ereg(dst_reg)) + EMIT3(0x45, 0x0F, 0xB7); + else + EMIT2(0x0F, 0xB7); + EMIT1(add_2reg(0xC0, dst_reg, dst_reg)); break; case 32: /* emit 'bswap eax' to swap lower 4 bytes */ @@ -577,6 +584,27 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, break; case BPF_ALU | BPF_END | BPF_FROM_LE: + switch (imm32) { + case 16: + /* emit 'movzwl eax, ax' to zero extend 16-bit + * into 64 bit + */ + if (is_ereg(dst_reg)) + EMIT3(0x45, 0x0F, 0xB7); + else + EMIT2(0x0F, 0xB7); + EMIT1(add_2reg(0xC0, dst_reg, dst_reg)); + break; + case 32: + /* emit 'mov eax, eax' to clear upper 32-bits */ + if (is_ereg(dst_reg)) + EMIT1(0x45); + EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg)); + break; + case 64: + /* nop */ + break; + } break; /* ST: *(u8*)(dst_reg + off) = imm */ diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index e4695985f9de..d93963340c3c 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -325,6 +325,26 @@ static void release_pci_root_info(struct pci_host_bridge *bridge) kfree(info); } +/* + * An IO port or MMIO resource assigned to a PCI host bridge may be + * consumed by the host bridge itself or available to its child + * bus/devices. The ACPI specification defines a bit (Producer/Consumer) + * to tell whether the resource is consumed by the host bridge itself, + * but firmware hasn't used that bit consistently, so we can't rely on it. + * + * On x86 and IA64 platforms, all IO port and MMIO resources are assumed + * to be available to child bus/devices except one special case: + * IO port [0xCF8-0xCFF] is consumed by the host bridge itself + * to access PCI configuration space. + * + * So explicitly filter out PCI CFG IO ports[0xCF8-0xCFF]. + */ +static bool resource_is_pcicfg_ioport(struct resource *res) +{ + return (res->flags & IORESOURCE_IO) && + res->start == 0xCF8 && res->end == 0xCFF; +} + static void probe_pci_root_info(struct pci_root_info *info, struct acpi_device *device, int busnum, int domain, @@ -346,8 +366,8 @@ static void probe_pci_root_info(struct pci_root_info *info, "no IO and memory resources present in _CRS\n"); else resource_list_for_each_entry_safe(entry, tmp, list) { - if ((entry->res->flags & IORESOURCE_WINDOW) == 0 || - (entry->res->flags & IORESOURCE_DISABLED)) + if ((entry->res->flags & IORESOURCE_DISABLED) || + resource_is_pcicfg_ioport(entry->res)) resource_list_destroy_entry(entry); else entry->res->name = info->name; diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index 275a3a8b78af..e97032069f88 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -51,7 +51,7 @@ VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \ $(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE $(call if_changed,vdso) -HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi +HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(srctree)/arch/x86/include/uapi hostprogs-y += vdso2c quiet_cmd_vdso2c = VDSO2C $@ diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 40d2473836c9..9793322751e0 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -82,15 +82,18 @@ static notrace cycle_t vread_pvclock(int *mode) cycle_t ret; u64 last; u32 version; - u32 migrate_count; u8 flags; unsigned cpu, cpu1; /* - * When looping to get a consistent (time-info, tsc) pair, we - * also need to deal with the possibility we can switch vcpus, - * so make sure we always re-fetch time-info for the current vcpu. + * Note: hypervisor must guarantee that: + * 1. cpu ID number maps 1:1 to per-CPU pvclock time info. + * 2. that per-CPU pvclock time info is updated if the + * underlying CPU changes. + * 3. that version is increased whenever underlying CPU + * changes. + * */ do { cpu = __getcpu() & VGETCPU_CPU_MASK; @@ -99,27 +102,20 @@ static notrace cycle_t vread_pvclock(int *mode) * __getcpu() calls (Gleb). */ - /* Make sure migrate_count will change if we leave the VCPU. */ - do { - pvti = get_pvti(cpu); - migrate_count = pvti->migrate_count; - - cpu1 = cpu; - cpu = __getcpu() & VGETCPU_CPU_MASK; - } while (unlikely(cpu != cpu1)); + pvti = get_pvti(cpu); version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); /* * Test we're still on the cpu as well as the version. - * - We must read TSC of pvti's VCPU. - * - KVM doesn't follow the versioning protocol, so data could - * change before version if we left the VCPU. + * We could have been migrated just after the first + * vgetcpu but before fetching the version, so we + * wouldn't notice a version change. */ - smp_rmb(); - } while (unlikely((pvti->pvti.version & 1) || - pvti->pvti.version != version || - pvti->migrate_count != migrate_count)); + cpu1 = __getcpu() & VGETCPU_CPU_MASK; + } while (unlikely(cpu != cpu1 || + (pvti->pvti.version & 1) || + pvti->pvti.version != version)); if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) *mode = VCLOCK_NONE; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 94578efd3067..46957ead3060 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1760,6 +1760,9 @@ static struct notifier_block xen_hvm_cpu_notifier = { static void __init xen_hvm_guest_init(void) { + if (xen_pv_domain()) + return; + init_hvm_pv_info(); xen_hvm_init_shared_info(); @@ -1775,6 +1778,7 @@ static void __init xen_hvm_guest_init(void) xen_hvm_init_time_ops(); xen_hvm_init_mmu_ops(); } +#endif static bool xen_nopv = false; static __init int xen_parse_nopv(char *arg) @@ -1784,14 +1788,11 @@ static __init int xen_parse_nopv(char *arg) } early_param("xen_nopv", xen_parse_nopv); -static uint32_t __init xen_hvm_platform(void) +static uint32_t __init xen_platform(void) { if (xen_nopv) return 0; - if (xen_pv_domain()) - return 0; - return xen_cpuid_base(); } @@ -1809,11 +1810,19 @@ bool xen_hvm_need_lapic(void) } EXPORT_SYMBOL_GPL(xen_hvm_need_lapic); -const struct hypervisor_x86 x86_hyper_xen_hvm __refconst = { - .name = "Xen HVM", - .detect = xen_hvm_platform, +static void xen_set_cpu_features(struct cpuinfo_x86 *c) +{ + if (xen_pv_domain()) + clear_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); +} + +const struct hypervisor_x86 x86_hyper_xen = { + .name = "Xen", + .detect = xen_platform, +#ifdef CONFIG_XEN_PVHVM .init_platform = xen_hvm_guest_init, +#endif .x2apic_available = xen_x2apic_para_available, + .set_cpu_features = xen_set_cpu_features, }; -EXPORT_SYMBOL(x86_hyper_xen_hvm); -#endif +EXPORT_SYMBOL(x86_hyper_xen); diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index d9497698645a..53b4c0811f4f 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -88,7 +88,17 @@ static void xen_vcpu_notify_restore(void *data) tick_resume_local(); } +static void xen_vcpu_notify_suspend(void *data) +{ + tick_suspend_local(); +} + void xen_arch_resume(void) { on_each_cpu(xen_vcpu_notify_restore, NULL, 1); } + +void xen_arch_suspend(void) +{ + on_each_cpu(xen_vcpu_notify_suspend, NULL, 1); +} |