diff options
Diffstat (limited to 'arch')
341 files changed, 7120 insertions, 4552 deletions
diff --git a/arch/arc/lib/strchr-700.S b/arch/arc/lib/strchr-700.S index 99c10475d477..9c548c7cf001 100644 --- a/arch/arc/lib/strchr-700.S +++ b/arch/arc/lib/strchr-700.S @@ -39,9 +39,18 @@ ARC_ENTRY strchr ld.a r2,[r0,4] sub r12,r6,r7 bic r12,r12,r6 +#ifdef __LITTLE_ENDIAN__ and r7,r12,r4 breq r7,0,.Loop ; For speed, we want this branch to be unaligned. b .Lfound_char ; Likewise this one. +#else + and r12,r12,r4 + breq r12,0,.Loop ; For speed, we want this branch to be unaligned. + lsr_s r12,r12,7 + bic r2,r7,r6 + b.d .Lfound_char_b + and_s r2,r2,r12 +#endif ; /* We require this code address to be unaligned for speed... */ .Laligned: ld_s r2,[r0] @@ -95,6 +104,7 @@ ARC_ENTRY strchr lsr r7,r7,7 bic r2,r7,r6 +.Lfound_char_b: norm r2,r2 sub_s r0,r0,4 asr_s r2,r2,3 diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 43594d5116ef..cd5c1c97b043 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -2064,8 +2064,7 @@ config KEXEC It is an ongoing process to be certain the hardware in a machine is properly shutdown, so do not be surprised if this code does not - initially work for you. It may help to enable device hotplugging - support. + initially work for you. config ATAGS_PROC bool "Export atags in procfs" diff --git a/arch/arm/boot/dts/am335x-bone.dts b/arch/arm/boot/dts/am335x-bone.dts index 444b4ede0d60..d318987d44a1 100644 --- a/arch/arm/boot/dts/am335x-bone.dts +++ b/arch/arm/boot/dts/am335x-bone.dts @@ -120,6 +120,35 @@ status = "okay"; }; + musb: usb@47400000 { + status = "okay"; + + control@44e10000 { + status = "okay"; + }; + + usb-phy@47401300 { + status = "okay"; + }; + + usb-phy@47401b00 { + status = "okay"; + }; + + usb@47401000 { + status = "okay"; + }; + + usb@47401800 { + status = "okay"; + dr_mode = "host"; + }; + + dma-controller@07402000 { + status = "okay"; + }; + }; + i2c0: i2c@44e0b000 { pinctrl-names = "default"; pinctrl-0 = <&i2c0_pins>; diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts index 3aee1a43782d..e8ec8756e498 100644 --- a/arch/arm/boot/dts/am335x-evm.dts +++ b/arch/arm/boot/dts/am335x-evm.dts @@ -171,6 +171,35 @@ }; }; + musb: usb@47400000 { + status = "okay"; + + control@44e10000 { + status = "okay"; + }; + + usb-phy@47401300 { + status = "okay"; + }; + + usb-phy@47401b00 { + status = "okay"; + }; + + usb@47401000 { + status = "okay"; + }; + + usb@47401800 { + status = "okay"; + dr_mode = "host"; + }; + + dma-controller@07402000 { + status = "okay"; + }; + }; + i2c1: i2c@4802a000 { pinctrl-names = "default"; pinctrl-0 = <&i2c1_pins>; diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts index 0c8ad173d2b0..4f339fa91c57 100644 --- a/arch/arm/boot/dts/am335x-evmsk.dts +++ b/arch/arm/boot/dts/am335x-evmsk.dts @@ -14,6 +14,7 @@ /dts-v1/; #include "am33xx.dtsi" +#include <dt-bindings/pwm/pwm.h> / { model = "TI AM335x EVM-SK"; @@ -207,6 +208,22 @@ }; }; + musb: usb@47400000 { + status = "okay"; + + control@44e10000 { + status = "okay"; + }; + + usb-phy@47401300 { + status = "okay"; + }; + + usb@47401000 { + status = "okay"; + }; + }; + epwmss2: epwmss@48304000 { status = "okay"; @@ -298,7 +315,7 @@ backlight { compatible = "pwm-backlight"; - pwms = <&ecap2 0 50000 1>; + pwms = <&ecap2 0 50000 PWM_POLARITY_INVERTED>; brightness-levels = <0 58 61 66 75 90 125 170 255>; default-brightness-level = <8>; }; diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi index 38b446ba1ce1..f9c5da9c7fe1 100644 --- a/arch/arm/boot/dts/am33xx.dtsi +++ b/arch/arm/boot/dts/am33xx.dtsi @@ -26,6 +26,10 @@ serial5 = &uart5; d_can0 = &dcan0; d_can1 = &dcan1; + usb0 = &usb0; + usb1 = &usb1; + phy0 = &usb0_phy; + phy1 = &usb1_phy; }; cpus { @@ -333,21 +337,132 @@ status = "disabled"; }; - usb@47400000 { - compatible = "ti,musb-am33xx"; - reg = <0x47400000 0x1000 /* usbss */ - 0x47401000 0x800 /* musb instance 0 */ - 0x47401800 0x800>; /* musb instance 1 */ - interrupts = <17 /* usbss */ - 18 /* musb instance 0 */ - 19>; /* musb instance 1 */ - multipoint = <1>; - num-eps = <16>; - ram-bits = <12>; - port0-mode = <3>; - port1-mode = <3>; - power = <250>; + usb: usb@47400000 { + compatible = "ti,am33xx-usb"; + reg = <0x47400000 0x1000>; + ranges; + #address-cells = <1>; + #size-cells = <1>; ti,hwmods = "usb_otg_hs"; + status = "disabled"; + + ctrl_mod: control@44e10000 { + compatible = "ti,am335x-usb-ctrl-module"; + reg = <0x44e10620 0x10 + 0x44e10648 0x4>; + reg-names = "phy_ctrl", "wakeup"; + status = "disabled"; + }; + + usb0_phy: usb-phy@47401300 { + compatible = "ti,am335x-usb-phy"; + reg = <0x47401300 0x100>; + reg-names = "phy"; + status = "disabled"; + ti,ctrl_mod = <&ctrl_mod>; + }; + + usb0: usb@47401000 { + compatible = "ti,musb-am33xx"; + status = "disabled"; + reg = <0x47401400 0x400 + 0x47401000 0x200>; + reg-names = "mc", "control"; + + interrupts = <18>; + interrupt-names = "mc"; + dr_mode = "otg"; + mentor,multipoint = <1>; + mentor,num-eps = <16>; + mentor,ram-bits = <12>; + mentor,power = <500>; + phys = <&usb0_phy>; + + dmas = <&cppi41dma 0 0 &cppi41dma 1 0 + &cppi41dma 2 0 &cppi41dma 3 0 + &cppi41dma 4 0 &cppi41dma 5 0 + &cppi41dma 6 0 &cppi41dma 7 0 + &cppi41dma 8 0 &cppi41dma 9 0 + &cppi41dma 10 0 &cppi41dma 11 0 + &cppi41dma 12 0 &cppi41dma 13 0 + &cppi41dma 14 0 &cppi41dma 0 1 + &cppi41dma 1 1 &cppi41dma 2 1 + &cppi41dma 3 1 &cppi41dma 4 1 + &cppi41dma 5 1 &cppi41dma 6 1 + &cppi41dma 7 1 &cppi41dma 8 1 + &cppi41dma 9 1 &cppi41dma 10 1 + &cppi41dma 11 1 &cppi41dma 12 1 + &cppi41dma 13 1 &cppi41dma 14 1>; + dma-names = + "rx1", "rx2", "rx3", "rx4", "rx5", "rx6", "rx7", + "rx8", "rx9", "rx10", "rx11", "rx12", "rx13", + "rx14", "rx15", + "tx1", "tx2", "tx3", "tx4", "tx5", "tx6", "tx7", + "tx8", "tx9", "tx10", "tx11", "tx12", "tx13", + "tx14", "tx15"; + }; + + usb1_phy: usb-phy@47401b00 { + compatible = "ti,am335x-usb-phy"; + reg = <0x47401b00 0x100>; + reg-names = "phy"; + status = "disabled"; + ti,ctrl_mod = <&ctrl_mod>; + }; + + usb1: usb@47401800 { + compatible = "ti,musb-am33xx"; + status = "disabled"; + reg = <0x47401c00 0x400 + 0x47401800 0x200>; + reg-names = "mc", "control"; + interrupts = <19>; + interrupt-names = "mc"; + dr_mode = "otg"; + mentor,multipoint = <1>; + mentor,num-eps = <16>; + mentor,ram-bits = <12>; + mentor,power = <500>; + phys = <&usb1_phy>; + + dmas = <&cppi41dma 15 0 &cppi41dma 16 0 + &cppi41dma 17 0 &cppi41dma 18 0 + &cppi41dma 19 0 &cppi41dma 20 0 + &cppi41dma 21 0 &cppi41dma 22 0 + &cppi41dma 23 0 &cppi41dma 24 0 + &cppi41dma 25 0 &cppi41dma 26 0 + &cppi41dma 27 0 &cppi41dma 28 0 + &cppi41dma 29 0 &cppi41dma 15 1 + &cppi41dma 16 1 &cppi41dma 17 1 + &cppi41dma 18 1 &cppi41dma 19 1 + &cppi41dma 20 1 &cppi41dma 21 1 + &cppi41dma 22 1 &cppi41dma 23 1 + &cppi41dma 24 1 &cppi41dma 25 1 + &cppi41dma 26 1 &cppi41dma 27 1 + &cppi41dma 28 1 &cppi41dma 29 1>; + dma-names = + "rx1", "rx2", "rx3", "rx4", "rx5", "rx6", "rx7", + "rx8", "rx9", "rx10", "rx11", "rx12", "rx13", + "rx14", "rx15", + "tx1", "tx2", "tx3", "tx4", "tx5", "tx6", "tx7", + "tx8", "tx9", "tx10", "tx11", "tx12", "tx13", + "tx14", "tx15"; + }; + + cppi41dma: dma-controller@07402000 { + compatible = "ti,am3359-cppi41"; + reg = <0x47400000 0x1000 + 0x47402000 0x1000 + 0x47403000 0x1000 + 0x47404000 0x4000>; + reg-names = "glue", "controller", "scheduler", "queuemgr"; + interrupts = <17>; + interrupt-names = "glue"; + #dma-cells = <2>; + #dma-channels = <30>; + #dma-requests = <256>; + status = "disabled"; + }; }; epwmss0: epwmss@48300000 { diff --git a/arch/arm/boot/dts/at91sam9n12ek.dts b/arch/arm/boot/dts/at91sam9n12ek.dts index d59b70c6a6a0..3d77dbe406f4 100644 --- a/arch/arm/boot/dts/at91sam9n12ek.dts +++ b/arch/arm/boot/dts/at91sam9n12ek.dts @@ -14,11 +14,11 @@ compatible = "atmel,at91sam9n12ek", "atmel,at91sam9n12", "atmel,at91sam9"; chosen { - bootargs = "mem=128M console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2"; + bootargs = "console=ttyS0,115200 root=/dev/mtdblock1 rw rootfstype=jffs2"; }; memory { - reg = <0x20000000 0x10000000>; + reg = <0x20000000 0x8000000>; }; clocks { diff --git a/arch/arm/boot/dts/at91sam9x5ek.dtsi b/arch/arm/boot/dts/at91sam9x5ek.dtsi index b753855b2058..49e3c45818c2 100644 --- a/arch/arm/boot/dts/at91sam9x5ek.dtsi +++ b/arch/arm/boot/dts/at91sam9x5ek.dtsi @@ -94,8 +94,9 @@ usb0: ohci@00600000 { status = "okay"; - num-ports = <2>; - atmel,vbus-gpio = <&pioD 19 GPIO_ACTIVE_LOW + num-ports = <3>; + atmel,vbus-gpio = <0 /* &pioD 18 GPIO_ACTIVE_LOW *//* Activate to have access to port A */ + &pioD 19 GPIO_ACTIVE_LOW &pioD 20 GPIO_ACTIVE_LOW >; }; diff --git a/arch/arm/boot/dts/atlas6.dtsi b/arch/arm/boot/dts/atlas6.dtsi index a0f2721ea583..8678e0c11119 100644 --- a/arch/arm/boot/dts/atlas6.dtsi +++ b/arch/arm/boot/dts/atlas6.dtsi @@ -329,6 +329,12 @@ sirf,function = "uart0"; }; }; + uart0_noflow_pins_a: uart0@1 { + uart { + sirf,pins = "uart0_nostreamctrlgrp"; + sirf,function = "uart0_nostreamctrl"; + }; + }; uart1_pins_a: uart1@0 { uart { sirf,pins = "uart1grp"; diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi index ef57277fc38f..376090f07231 100644 --- a/arch/arm/boot/dts/exynos5250.dtsi +++ b/arch/arm/boot/dts/exynos5250.dtsi @@ -405,7 +405,7 @@ }; i2s0: i2s@03830000 { - compatible = "samsung,i2s-v5"; + compatible = "samsung,s5pv210-i2s"; reg = <0x03830000 0x100>; dmas = <&pdma0 10 &pdma0 9 @@ -415,16 +415,13 @@ <&clock_audss EXYNOS_I2S_BUS>, <&clock_audss EXYNOS_SCLK_I2S>; clock-names = "iis", "i2s_opclk0", "i2s_opclk1"; - samsung,supports-6ch; - samsung,supports-rstclr; - samsung,supports-secdai; samsung,idma-addr = <0x03000000>; pinctrl-names = "default"; pinctrl-0 = <&i2s0_bus>; }; i2s1: i2s@12D60000 { - compatible = "samsung,i2s-v5"; + compatible = "samsung,s3c6410-i2s"; reg = <0x12D60000 0x100>; dmas = <&pdma1 12 &pdma1 11>; @@ -436,7 +433,7 @@ }; i2s2: i2s@12D70000 { - compatible = "samsung,i2s-v5"; + compatible = "samsung,s3c6410-i2s"; reg = <0x12D70000 0x100>; dmas = <&pdma0 12 &pdma0 11>; diff --git a/arch/arm/boot/dts/exynos5440.dtsi b/arch/arm/boot/dts/exynos5440.dtsi index ff7f5d855845..586134e2a382 100644 --- a/arch/arm/boot/dts/exynos5440.dtsi +++ b/arch/arm/boot/dts/exynos5440.dtsi @@ -248,6 +248,7 @@ #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0>; interrupt-map = <0x0 0 &gic 53>; + num-lanes = <4>; }; pcie@2a0000 { @@ -267,5 +268,6 @@ #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0>; interrupt-map = <0x0 0 &gic 56>; + num-lanes = <4>; }; }; diff --git a/arch/arm/boot/dts/imx28-evk.dts b/arch/arm/boot/dts/imx28-evk.dts index e035f4664b97..15715d921d14 100644 --- a/arch/arm/boot/dts/imx28-evk.dts +++ b/arch/arm/boot/dts/imx28-evk.dts @@ -220,6 +220,7 @@ auart0: serial@8006a000 { pinctrl-names = "default"; pinctrl-0 = <&auart0_pins_a>; + fsl,uart-has-rtscts; status = "okay"; }; diff --git a/arch/arm/boot/dts/msm8660-surf.dts b/arch/arm/boot/dts/msm8660-surf.dts index cdc010e0f93e..386d42870215 100644 --- a/arch/arm/boot/dts/msm8660-surf.dts +++ b/arch/arm/boot/dts/msm8660-surf.dts @@ -38,7 +38,7 @@ }; serial@19c40000 { - compatible = "qcom,msm-hsuart", "qcom,msm-uart"; + compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm"; reg = <0x19c40000 0x1000>, <0x19c00000 0x1000>; interrupts = <0 195 0x0>; diff --git a/arch/arm/boot/dts/msm8960-cdp.dts b/arch/arm/boot/dts/msm8960-cdp.dts index 9c1167b0459b..93e9f7e0b7ad 100644 --- a/arch/arm/boot/dts/msm8960-cdp.dts +++ b/arch/arm/boot/dts/msm8960-cdp.dts @@ -38,7 +38,7 @@ }; serial@16440000 { - compatible = "qcom,msm-hsuart", "qcom,msm-uart"; + compatible = "qcom,msm-uartdm-v1.3", "qcom,msm-uartdm"; reg = <0x16440000 0x1000>, <0x16400000 0x1000>; interrupts = <0 154 0x0>; diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi index e643620417a9..07be2cd7b318 100644 --- a/arch/arm/boot/dts/omap5.dtsi +++ b/arch/arm/boot/dts/omap5.dtsi @@ -644,7 +644,7 @@ utmi-mode = <2>; ranges; dwc3@4a030000 { - compatible = "synopsys,dwc3"; + compatible = "snps,dwc3"; reg = <0x4a030000 0x1000>; interrupts = <GIC_SPI 92 IRQ_TYPE_LEVEL_HIGH>; usb-phy = <&usb2_phy>, <&usb3_phy>; diff --git a/arch/arm/boot/dts/tegra20-seaboard.dts b/arch/arm/boot/dts/tegra20-seaboard.dts index 365760b33a26..c8242533268f 100644 --- a/arch/arm/boot/dts/tegra20-seaboard.dts +++ b/arch/arm/boot/dts/tegra20-seaboard.dts @@ -566,7 +566,6 @@ usb@c5000000 { status = "okay"; - nvidia,vbus-gpio = <&gpio TEGRA_GPIO(D, 0) GPIO_ACTIVE_HIGH>; dr_mode = "otg"; }; @@ -830,6 +829,8 @@ regulator-max-microvolt = <5000000>; enable-active-high; gpio = <&gpio 24 0>; /* PD0 */ + regulator-always-on; + regulator-boot-on; }; }; diff --git a/arch/arm/boot/dts/tegra20-trimslice.dts b/arch/arm/boot/dts/tegra20-trimslice.dts index ed4b901b0227..1e9d33adb925 100644 --- a/arch/arm/boot/dts/tegra20-trimslice.dts +++ b/arch/arm/boot/dts/tegra20-trimslice.dts @@ -312,7 +312,6 @@ usb@c5000000 { status = "okay"; - nvidia,vbus-gpio = <&gpio TEGRA_GPIO(V, 2) GPIO_ACTIVE_HIGH>; }; usb-phy@c5000000 { @@ -412,6 +411,8 @@ regulator-max-microvolt = <5000000>; enable-active-high; gpio = <&gpio 170 0>; /* PV2 */ + regulator-always-on; + regulator-boot-on; }; }; diff --git a/arch/arm/boot/dts/tegra20-whistler.dts b/arch/arm/boot/dts/tegra20-whistler.dts index ab67c94db280..c703197dca6e 100644 --- a/arch/arm/boot/dts/tegra20-whistler.dts +++ b/arch/arm/boot/dts/tegra20-whistler.dts @@ -509,7 +509,6 @@ usb@c5000000 { status = "okay"; - nvidia,vbus-gpio = <&tca6416 0 GPIO_ACTIVE_HIGH>; }; usb-phy@c5000000 { @@ -519,7 +518,6 @@ usb@c5008000 { status = "okay"; - nvidia,vbus-gpio = <&tca6416 1 GPIO_ACTIVE_HIGH>; }; usb-phy@c5008000 { @@ -588,6 +586,8 @@ regulator-max-microvolt = <5000000>; enable-active-high; gpio = <&tca6416 0 0>; /* GPIO_PMU0 */ + regulator-always-on; + regulator-boot-on; }; vbus3_reg: regulator@3 { @@ -598,6 +598,8 @@ regulator-max-microvolt = <5000000>; enable-active-high; gpio = <&tca6416 1 0>; /* GPIO_PMU1 */ + regulator-always-on; + regulator-boot-on; }; }; diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi index 9653fd8288d2..e4570834512e 100644 --- a/arch/arm/boot/dts/tegra20.dtsi +++ b/arch/arm/boot/dts/tegra20.dtsi @@ -477,13 +477,13 @@ <&tegra_car TEGRA20_CLK_USBD>; clock-names = "reg", "pll_u", "timer", "utmi-pads"; nvidia,has-legacy-mode; - hssync_start_delay = <9>; - idle_wait_delay = <17>; - elastic_limit = <16>; - term_range_adj = <6>; - xcvr_setup = <9>; - xcvr_lsfslew = <1>; - xcvr_lsrslew = <1>; + nvidia,hssync-start-delay = <9>; + nvidia,idle-wait-delay = <17>; + nvidia,elastic-limit = <16>; + nvidia,term-range-adj = <6>; + nvidia,xcvr-setup = <9>; + nvidia,xcvr-lsfslew = <1>; + nvidia,xcvr-lsrslew = <1>; status = "disabled"; }; @@ -527,13 +527,13 @@ <&tegra_car TEGRA20_CLK_CLK_M>, <&tegra_car TEGRA20_CLK_USBD>; clock-names = "reg", "pll_u", "timer", "utmi-pads"; - hssync_start_delay = <9>; - idle_wait_delay = <17>; - elastic_limit = <16>; - term_range_adj = <6>; - xcvr_setup = <9>; - xcvr_lsfslew = <2>; - xcvr_lsrslew = <2>; + nvidia,hssync-start-delay = <9>; + nvidia,idle-wait-delay = <17>; + nvidia,elastic-limit = <16>; + nvidia,term-range-adj = <6>; + nvidia,xcvr-setup = <9>; + nvidia,xcvr-lsfslew = <2>; + nvidia,xcvr-lsrslew = <2>; status = "disabled"; }; diff --git a/arch/arm/boot/dts/wm8850-w70v2.dts b/arch/arm/boot/dts/wm8850-w70v2.dts index 90e913fb64be..7a563d2523b0 100644 --- a/arch/arm/boot/dts/wm8850-w70v2.dts +++ b/arch/arm/boot/dts/wm8850-w70v2.dts @@ -11,13 +11,14 @@ /dts-v1/; /include/ "wm8850.dtsi" +#include <dt-bindings/pwm/pwm.h> / { model = "Wondermedia WM8850-W70v2 Tablet"; backlight { compatible = "pwm-backlight"; - pwms = <&pwm 0 50000 1>; /* duty inverted */ + pwms = <&pwm 0 50000 PWM_POLARITY_INVERTED>; brightness-levels = <0 40 60 80 100 130 190 255>; default-brightness-level = <5>; diff --git a/arch/arm/configs/keystone_defconfig b/arch/arm/configs/keystone_defconfig index 62e968cac9dc..1f36b823905f 100644 --- a/arch/arm/configs/keystone_defconfig +++ b/arch/arm/configs/keystone_defconfig @@ -104,6 +104,7 @@ CONFIG_IP_SCTP=y CONFIG_VLAN_8021Q=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CMA=y +CONFIG_DMA_CMA=y CONFIG_MTD=y CONFIG_MTD_CMDLINE_PARTS=y CONFIG_MTD_BLOCK=y diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 5339e6a4d639..5465f564fdf3 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -78,6 +78,7 @@ CONFIG_MAC80211_RC_PID=y CONFIG_MAC80211_RC_DEFAULT_PID=y CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_CMA=y +CONFIG_DMA_CMA=y CONFIG_CONNECTOR=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig index 1effb43dab80..92d0a149aeb5 100644 --- a/arch/arm/configs/tegra_defconfig +++ b/arch/arm/configs/tegra_defconfig @@ -79,6 +79,7 @@ CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y # CONFIG_FIRMWARE_IN_KERNEL is not set CONFIG_CMA=y +CONFIG_DMA_CMA=y CONFIG_MTD=y CONFIG_MTD_M25P80=y CONFIG_PROC_DEVICETREE=y diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h index e406d575c94f..5665134bfa3e 100644 --- a/arch/arm/include/asm/arch_timer.h +++ b/arch/arm/include/asm/arch_timer.h @@ -17,7 +17,8 @@ int arch_timer_arch_init(void); * nicely work out which register we want, and chuck away the rest of * the code. At least it does so with a recent GCC (4.6.3). */ -static inline void arch_timer_reg_write(const int access, const int reg, u32 val) +static __always_inline +void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val) { if (access == ARCH_TIMER_PHYS_ACCESS) { switch (reg) { @@ -28,9 +29,7 @@ static inline void arch_timer_reg_write(const int access, const int reg, u32 val asm volatile("mcr p15, 0, %0, c14, c2, 0" : : "r" (val)); break; } - } - - if (access == ARCH_TIMER_VIRT_ACCESS) { + } else if (access == ARCH_TIMER_VIRT_ACCESS) { switch (reg) { case ARCH_TIMER_REG_CTRL: asm volatile("mcr p15, 0, %0, c14, c3, 1" : : "r" (val)); @@ -44,7 +43,8 @@ static inline void arch_timer_reg_write(const int access, const int reg, u32 val isb(); } -static inline u32 arch_timer_reg_read(const int access, const int reg) +static __always_inline +u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg) { u32 val = 0; @@ -57,9 +57,7 @@ static inline u32 arch_timer_reg_read(const int access, const int reg) asm volatile("mrc p15, 0, %0, c14, c2, 0" : "=r" (val)); break; } - } - - if (access == ARCH_TIMER_VIRT_ACCESS) { + } else if (access == ARCH_TIMER_VIRT_ACCESS) { switch (reg) { case ARCH_TIMER_REG_CTRL: asm volatile("mrc p15, 0, %0, c14, c3, 1" : "=r" (val)); diff --git a/arch/arm/include/asm/dma-contiguous.h b/arch/arm/include/asm/dma-contiguous.h index 3ed37b4d93da..e072bb2ba1b1 100644 --- a/arch/arm/include/asm/dma-contiguous.h +++ b/arch/arm/include/asm/dma-contiguous.h @@ -2,7 +2,7 @@ #define ASMARM_DMA_CONTIGUOUS_H #ifdef __KERNEL__ -#ifdef CONFIG_CMA +#ifdef CONFIG_DMA_CMA #include <linux/types.h> #include <asm-generic/dma-contiguous.h> diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 472ac7091003..9b28c41f4ba9 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -64,7 +64,7 @@ void kvm_clear_hyp_idmap(void); static inline void kvm_set_pte(pte_t *pte, pte_t new_pte) { - pte_val(*pte) = new_pte; + *pte = new_pte; /* * flush_pmd_entry just takes a void pointer and cleans the necessary * cache entries, so we can reuse the function for ptes. diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c index 261fcc826169..88e14d74b6de 100644 --- a/arch/arm/kernel/bios32.c +++ b/arch/arm/kernel/bios32.c @@ -525,11 +525,6 @@ void pci_common_init_dev(struct device *parent, struct hw_pci *hw) * Assign resources. */ pci_bus_assign_resources(bus); - - /* - * Enable bridges - */ - pci_enable_bridges(bus); } /* diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c index 5859c8bc727c..2ee8a17d2b01 100644 --- a/arch/arm/kernel/devtree.c +++ b/arch/arm/kernel/devtree.c @@ -169,6 +169,11 @@ void __init arm_dt_init_cpu_maps(void) } } +bool arch_match_cpu_phys_id(int cpu, u64 phys_id) +{ + return (phys_id & MPIDR_HWID_BITMASK) == cpu_logical_map(cpu); +} + /** * setup_machine_fdt - Machine setup when an dtb was passed to the kernel * @dt_phys: physical address of dt blob diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c index fc7920288a3d..918875d96d5d 100644 --- a/arch/arm/kernel/fiq.c +++ b/arch/arm/kernel/fiq.c @@ -89,7 +89,8 @@ void set_fiq_handler(void *start, unsigned int length) memcpy(base + offset, start, length); if (!cache_is_vipt_nonaliasing()) - flush_icache_range(base + offset, offset + length); + flush_icache_range((unsigned long)base + offset, offset + + length); flush_icache_range(0xffff0000 + offset, 0xffff0000 + offset + length); } diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index d7c82df69243..57221e349a7c 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -82,6 +82,7 @@ void machine_crash_nonpanic_core(void *unused) crash_save_cpu(®s, smp_processor_id()); flush_cache_all(); + set_cpu_online(smp_processor_id(), false); atomic_dec(&waiting_for_crash_ipi); while (1) cpu_relax(); diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index c5a59546a256..85a87370f144 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -74,12 +74,8 @@ struct cpu_efficiency table_efficiency[] = { {NULL, }, }; -struct cpu_capacity { - unsigned long hwid; - unsigned long capacity; -}; - -struct cpu_capacity *cpu_capacity; +unsigned long *__cpu_capacity; +#define cpu_capacity(cpu) __cpu_capacity[cpu] unsigned long middle_capacity = 1; @@ -100,15 +96,19 @@ static void __init parse_dt_topology(void) unsigned long capacity = 0; int alloc_size, cpu = 0; - alloc_size = nr_cpu_ids * sizeof(struct cpu_capacity); - cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT); + alloc_size = nr_cpu_ids * sizeof(*__cpu_capacity); + __cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT); - while ((cn = of_find_node_by_type(cn, "cpu"))) { - const u32 *rate, *reg; + for_each_possible_cpu(cpu) { + const u32 *rate; int len; - if (cpu >= num_possible_cpus()) - break; + /* too early to use cpu->of_node */ + cn = of_get_cpu_node(cpu, NULL); + if (!cn) { + pr_err("missing device node for CPU %d\n", cpu); + continue; + } for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++) if (of_device_is_compatible(cn, cpu_eff->compatible)) @@ -124,12 +124,6 @@ static void __init parse_dt_topology(void) continue; } - reg = of_get_property(cn, "reg", &len); - if (!reg || len != 4) { - pr_err("%s missing reg property\n", cn->full_name); - continue; - } - capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency; /* Save min capacity of the system */ @@ -140,13 +134,9 @@ static void __init parse_dt_topology(void) if (capacity > max_capacity) max_capacity = capacity; - cpu_capacity[cpu].capacity = capacity; - cpu_capacity[cpu++].hwid = be32_to_cpup(reg); + cpu_capacity(cpu) = capacity; } - if (cpu < num_possible_cpus()) - cpu_capacity[cpu].hwid = (unsigned long)(-1); - /* If min and max capacities are equals, we bypass the update of the * cpu_scale because all CPUs have the same capacity. Otherwise, we * compute a middle_capacity factor that will ensure that the capacity @@ -154,9 +144,7 @@ static void __init parse_dt_topology(void) * SCHED_POWER_SCALE, which is the default value, but with the * constraint explained near table_efficiency[]. */ - if (min_capacity == max_capacity) - cpu_capacity[0].hwid = (unsigned long)(-1); - else if (4*max_capacity < (3*(max_capacity + min_capacity))) + if (4*max_capacity < (3*(max_capacity + min_capacity))) middle_capacity = (min_capacity + max_capacity) >> (SCHED_POWER_SHIFT+1); else @@ -170,23 +158,12 @@ static void __init parse_dt_topology(void) * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the * function returns directly for SMP system. */ -void update_cpu_power(unsigned int cpu, unsigned long hwid) +void update_cpu_power(unsigned int cpu) { - unsigned int idx = 0; - - /* look for the cpu's hwid in the cpu capacity table */ - for (idx = 0; idx < num_possible_cpus(); idx++) { - if (cpu_capacity[idx].hwid == hwid) - break; - - if (cpu_capacity[idx].hwid == -1) - return; - } - - if (idx == num_possible_cpus()) + if (!cpu_capacity(cpu)) return; - set_power_scale(cpu, cpu_capacity[idx].capacity / middle_capacity); + set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity); printk(KERN_INFO "CPU%u: update cpu_power %lu\n", cpu, arch_scale_freq_power(NULL, cpu)); @@ -194,7 +171,7 @@ void update_cpu_power(unsigned int cpu, unsigned long hwid) #else static inline void parse_dt_topology(void) {} -static inline void update_cpu_power(unsigned int cpuid, unsigned int mpidr) {} +static inline void update_cpu_power(unsigned int cpuid) {} #endif /* @@ -281,7 +258,7 @@ void store_cpu_topology(unsigned int cpuid) update_siblings_masks(cpuid); - update_cpu_power(cpuid, mpidr & MPIDR_HWID_BITMASK); + update_cpu_power(cpuid); printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n", cpuid, cpu_topology[cpuid].thread_id, diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 741f66a2edbd..9c697db2787e 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -219,6 +219,10 @@ long kvm_arch_dev_ioctl(struct file *filp, return -EINVAL; } +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_userspace_memory_region *mem, diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c index 4a5199070430..db9cf692d4dd 100644 --- a/arch/arm/kvm/coproc.c +++ b/arch/arm/kvm/coproc.c @@ -146,7 +146,11 @@ static bool pm_fake(struct kvm_vcpu *vcpu, #define access_pmintenclr pm_fake /* Architected CP15 registers. - * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 + * CRn denotes the primary register number, but is copied to the CRm in the + * user space API for 64-bit register access in line with the terminology used + * in the ARM ARM. + * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit + * registers preceding 32-bit ones. */ static const struct coproc_reg cp15_regs[] = { /* CSSELR: swapped by interrupt.S. */ @@ -154,8 +158,8 @@ static const struct coproc_reg cp15_regs[] = { NULL, reset_unknown, c0_CSSELR }, /* TTBR0/TTBR1: swapped by interrupt.S. */ - { CRm( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 }, - { CRm( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 }, + { CRm64( 2), Op1( 0), is64, NULL, reset_unknown64, c2_TTBR0 }, + { CRm64( 2), Op1( 1), is64, NULL, reset_unknown64, c2_TTBR1 }, /* TTBCR: swapped by interrupt.S. */ { CRn( 2), CRm( 0), Op1( 0), Op2( 2), is32, @@ -182,7 +186,7 @@ static const struct coproc_reg cp15_regs[] = { NULL, reset_unknown, c6_IFAR }, /* PAR swapped by interrupt.S */ - { CRn( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR }, + { CRm64( 7), Op1( 0), is64, NULL, reset_unknown64, c7_PAR }, /* * DC{C,I,CI}SW operations: @@ -399,12 +403,13 @@ static bool index_to_params(u64 id, struct coproc_params *params) | KVM_REG_ARM_OPC1_MASK)) return false; params->is_64bit = true; - params->CRm = ((id & KVM_REG_ARM_CRM_MASK) + /* CRm to CRn: see cp15_to_index for details */ + params->CRn = ((id & KVM_REG_ARM_CRM_MASK) >> KVM_REG_ARM_CRM_SHIFT); params->Op1 = ((id & KVM_REG_ARM_OPC1_MASK) >> KVM_REG_ARM_OPC1_SHIFT); params->Op2 = 0; - params->CRn = 0; + params->CRm = 0; return true; default: return false; @@ -898,7 +903,14 @@ static u64 cp15_to_index(const struct coproc_reg *reg) if (reg->is_64) { val |= KVM_REG_SIZE_U64; val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT); - val |= (reg->CRm << KVM_REG_ARM_CRM_SHIFT); + /* + * CRn always denotes the primary coproc. reg. nr. for the + * in-kernel representation, but the user space API uses the + * CRm for the encoding, because it is modelled after the + * MRRC/MCRR instructions: see the ARM ARM rev. c page + * B3-1445 + */ + val |= (reg->CRn << KVM_REG_ARM_CRM_SHIFT); } else { val |= KVM_REG_SIZE_U32; val |= (reg->Op1 << KVM_REG_ARM_OPC1_SHIFT); diff --git a/arch/arm/kvm/coproc.h b/arch/arm/kvm/coproc.h index b7301d3e4799..0461d5c8d3de 100644 --- a/arch/arm/kvm/coproc.h +++ b/arch/arm/kvm/coproc.h @@ -135,6 +135,8 @@ static inline int cmp_reg(const struct coproc_reg *i1, return -1; if (i1->CRn != i2->CRn) return i1->CRn - i2->CRn; + if (i1->is_64 != i2->is_64) + return i2->is_64 - i1->is_64; if (i1->CRm != i2->CRm) return i1->CRm - i2->CRm; if (i1->Op1 != i2->Op1) @@ -145,6 +147,7 @@ static inline int cmp_reg(const struct coproc_reg *i1, #define CRn(_x) .CRn = _x #define CRm(_x) .CRm = _x +#define CRm64(_x) .CRn = _x, .CRm = 0 #define Op1(_x) .Op1 = _x #define Op2(_x) .Op2 = _x #define is64 .is_64 = true diff --git a/arch/arm/kvm/coproc_a15.c b/arch/arm/kvm/coproc_a15.c index 685063a6d0cf..cf93472b9dd6 100644 --- a/arch/arm/kvm/coproc_a15.c +++ b/arch/arm/kvm/coproc_a15.c @@ -114,7 +114,11 @@ static bool access_l2ectlr(struct kvm_vcpu *vcpu, /* * A15-specific CP15 registers. - * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 + * CRn denotes the primary register number, but is copied to the CRm in the + * user space API for 64-bit register access in line with the terminology used + * in the ARM ARM. + * Important: Must be sorted ascending by CRn, CRM, Op1, Op2 and with 64-bit + * registers preceding 32-bit ones. */ static const struct coproc_reg a15_regs[] = { /* MPIDR: we use VMPIDR for guest access. */ diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S index 16cd4ba5d7fd..85dd84b10687 100644 --- a/arch/arm/kvm/interrupts.S +++ b/arch/arm/kvm/interrupts.S @@ -492,10 +492,10 @@ __kvm_hyp_code_end: .section ".rodata" und_die_str: - .ascii "unexpected undefined exception in Hyp mode at: %#08x" + .ascii "unexpected undefined exception in Hyp mode at: %#08x\n" pabt_die_str: - .ascii "unexpected prefetch abort in Hyp mode at: %#08x" + .ascii "unexpected prefetch abort in Hyp mode at: %#08x\n" dabt_die_str: - .ascii "unexpected data abort in Hyp mode at: %#08x" + .ascii "unexpected data abort in Hyp mode at: %#08x\n" svc_die_str: - .ascii "unexpected HVC/SVC trap in Hyp mode at: %#08x" + .ascii "unexpected HVC/SVC trap in Hyp mode at: %#08x\n" diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index b8e06b7a2833..0c25d9487d53 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -63,7 +63,8 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) static int decode_hsr(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, struct kvm_exit_mmio *mmio) { - unsigned long rt, len; + unsigned long rt; + int len; bool is_write, sign_extend; if (kvm_vcpu_dabt_isextabt(vcpu)) { diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index ca6bea4859b4..0988d9e04dd4 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -85,6 +85,12 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc) return p; } +static bool page_empty(void *ptr) +{ + struct page *ptr_page = virt_to_page(ptr); + return page_count(ptr_page) == 1; +} + static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr) { pmd_t *pmd_table = pmd_offset(pud, 0); @@ -103,12 +109,6 @@ static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr) put_page(virt_to_page(pmd)); } -static bool pmd_empty(pmd_t *pmd) -{ - struct page *pmd_page = virt_to_page(pmd); - return page_count(pmd_page) == 1; -} - static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr) { if (pte_present(*pte)) { @@ -118,12 +118,6 @@ static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr) } } -static bool pte_empty(pte_t *pte) -{ - struct page *pte_page = virt_to_page(pte); - return page_count(pte_page) == 1; -} - static void unmap_range(struct kvm *kvm, pgd_t *pgdp, unsigned long long start, u64 size) { @@ -132,37 +126,37 @@ static void unmap_range(struct kvm *kvm, pgd_t *pgdp, pmd_t *pmd; pte_t *pte; unsigned long long addr = start, end = start + size; - u64 range; + u64 next; while (addr < end) { pgd = pgdp + pgd_index(addr); pud = pud_offset(pgd, addr); if (pud_none(*pud)) { - addr += PUD_SIZE; + addr = pud_addr_end(addr, end); continue; } pmd = pmd_offset(pud, addr); if (pmd_none(*pmd)) { - addr += PMD_SIZE; + addr = pmd_addr_end(addr, end); continue; } pte = pte_offset_kernel(pmd, addr); clear_pte_entry(kvm, pte, addr); - range = PAGE_SIZE; + next = addr + PAGE_SIZE; /* If we emptied the pte, walk back up the ladder */ - if (pte_empty(pte)) { + if (page_empty(pte)) { clear_pmd_entry(kvm, pmd, addr); - range = PMD_SIZE; - if (pmd_empty(pmd)) { + next = pmd_addr_end(addr, end); + if (page_empty(pmd) && !page_empty(pud)) { clear_pud_entry(kvm, pud, addr); - range = PUD_SIZE; + next = pud_addr_end(addr, end); } } - addr += range; + addr = next; } } diff --git a/arch/arm/kvm/reset.c b/arch/arm/kvm/reset.c index b7840e7aa452..71e08baee209 100644 --- a/arch/arm/kvm/reset.c +++ b/arch/arm/kvm/reset.c @@ -40,7 +40,7 @@ static struct kvm_regs a15_regs_reset = { }; static const struct kvm_irq_level a15_vtimer_irq = { - .irq = 27, + { .irq = 27 }, .level = 1, }; diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h index a8e73ed5ad5b..b1d640f78623 100644 --- a/arch/arm/kvm/trace.h +++ b/arch/arm/kvm/trace.h @@ -59,10 +59,9 @@ TRACE_EVENT(kvm_guest_fault, __entry->ipa = ipa; ), - TP_printk("guest fault at PC %#08lx (hxfar %#08lx, " - "ipa %#16llx, hsr %#08lx", - __entry->vcpu_pc, __entry->hxfar, - __entry->ipa, __entry->hsr) + TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx", + __entry->ipa, __entry->hsr, + __entry->hxfar, __entry->vcpu_pc) ); TRACE_EVENT(kvm_irq_line, diff --git a/arch/arm/mach-at91/at91sam9x5.c b/arch/arm/mach-at91/at91sam9x5.c index 2abee6626aac..916e5a142917 100644 --- a/arch/arm/mach-at91/at91sam9x5.c +++ b/arch/arm/mach-at91/at91sam9x5.c @@ -227,6 +227,8 @@ static struct clk_lookup periph_clocks_lookups[] = { CLKDEV_CON_DEV_ID("usart", "f8020000.serial", &usart1_clk), CLKDEV_CON_DEV_ID("usart", "f8024000.serial", &usart2_clk), CLKDEV_CON_DEV_ID("usart", "f8028000.serial", &usart3_clk), + CLKDEV_CON_DEV_ID("usart", "f8040000.serial", &uart0_clk), + CLKDEV_CON_DEV_ID("usart", "f8044000.serial", &uart1_clk), CLKDEV_CON_DEV_ID("t0_clk", "f8008000.timer", &tcb0_clk), CLKDEV_CON_DEV_ID("t0_clk", "f800c000.timer", &tcb0_clk), CLKDEV_CON_DEV_ID("mci_clk", "f0008000.mmc", &mmc0_clk), diff --git a/arch/arm/mach-at91/include/mach/at91_adc.h b/arch/arm/mach-at91/include/mach/at91_adc.h index 8e7ed5c90817..048a57f76bd3 100644 --- a/arch/arm/mach-at91/include/mach/at91_adc.h +++ b/arch/arm/mach-at91/include/mach/at91_adc.h @@ -28,9 +28,12 @@ #define AT91_ADC_TRGSEL_EXTERNAL (6 << 1) #define AT91_ADC_LOWRES (1 << 4) /* Low Resolution */ #define AT91_ADC_SLEEP (1 << 5) /* Sleep Mode */ -#define AT91_ADC_PRESCAL (0x3f << 8) /* Prescalar Rate Selection */ +#define AT91_ADC_PRESCAL_9260 (0x3f << 8) /* Prescalar Rate Selection */ +#define AT91_ADC_PRESCAL_9G45 (0xff << 8) #define AT91_ADC_PRESCAL_(x) ((x) << 8) -#define AT91_ADC_STARTUP (0x1f << 16) /* Startup Up Time */ +#define AT91_ADC_STARTUP_9260 (0x1f << 16) /* Startup Up Time */ +#define AT91_ADC_STARTUP_9G45 (0x7f << 16) +#define AT91_ADC_STARTUP_9X5 (0xf << 16) #define AT91_ADC_STARTUP_(x) ((x) << 16) #define AT91_ADC_SHTIM (0xf << 24) /* Sample & Hold Time */ #define AT91_ADC_SHTIM_(x) ((x) << 24) @@ -48,6 +51,9 @@ #define AT91_ADC_ENDRX (1 << 18) /* End of RX Buffer */ #define AT91_ADC_RXFUFF (1 << 19) /* RX Buffer Full */ +#define AT91_ADC_SR_9X5 0x30 /* Status Register for 9x5 */ +#define AT91_ADC_SR_DRDY_9X5 (1 << 24) /* Data Ready */ + #define AT91_ADC_LCDR 0x20 /* Last Converted Data Register */ #define AT91_ADC_LDATA (0x3ff) @@ -58,4 +64,10 @@ #define AT91_ADC_CHR(n) (0x30 + ((n) * 4)) /* Channel Data Register N */ #define AT91_ADC_DATA (0x3ff) +#define AT91_ADC_CDR0_9X5 (0x50) /* Channel Data Register 0 for 9X5 */ + +#define AT91_ADC_TRGR_9260 AT91_ADC_MR +#define AT91_ADC_TRGR_9G45 0x08 +#define AT91_ADC_TRGR_9X5 0xC0 + #endif diff --git a/arch/arm/mach-davinci/board-dm355-leopard.c b/arch/arm/mach-davinci/board-dm355-leopard.c index dff4ddc5ef81..139e42da25f0 100644 --- a/arch/arm/mach-davinci/board-dm355-leopard.c +++ b/arch/arm/mach-davinci/board-dm355-leopard.c @@ -75,6 +75,7 @@ static struct davinci_nand_pdata davinci_nand_data = { .parts = davinci_nand_partitions, .nr_parts = ARRAY_SIZE(davinci_nand_partitions), .ecc_mode = NAND_ECC_HW_SYNDROME, + .ecc_bits = 4, .bbt_options = NAND_BBT_USE_FLASH, }; diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c index a33686a6fbb2..fa4bfaf952d8 100644 --- a/arch/arm/mach-davinci/board-dm644x-evm.c +++ b/arch/arm/mach-davinci/board-dm644x-evm.c @@ -153,6 +153,7 @@ static struct davinci_nand_pdata davinci_evm_nandflash_data = { .parts = davinci_evm_nandflash_partition, .nr_parts = ARRAY_SIZE(davinci_evm_nandflash_partition), .ecc_mode = NAND_ECC_HW, + .ecc_bits = 1, .bbt_options = NAND_BBT_USE_FLASH, .timing = &davinci_evm_nandflash_timing, }; diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c index fbb8e5ab1dc1..0c005e876cac 100644 --- a/arch/arm/mach-davinci/board-dm646x-evm.c +++ b/arch/arm/mach-davinci/board-dm646x-evm.c @@ -90,6 +90,7 @@ static struct davinci_nand_pdata davinci_nand_data = { .parts = davinci_nand_partitions, .nr_parts = ARRAY_SIZE(davinci_nand_partitions), .ecc_mode = NAND_ECC_HW, + .ecc_bits = 1, .options = 0, }; diff --git a/arch/arm/mach-davinci/board-neuros-osd2.c b/arch/arm/mach-davinci/board-neuros-osd2.c index 2bc112adf565..808233b60e3d 100644 --- a/arch/arm/mach-davinci/board-neuros-osd2.c +++ b/arch/arm/mach-davinci/board-neuros-osd2.c @@ -88,6 +88,7 @@ static struct davinci_nand_pdata davinci_ntosd2_nandflash_data = { .parts = davinci_ntosd2_nandflash_partition, .nr_parts = ARRAY_SIZE(davinci_ntosd2_nandflash_partition), .ecc_mode = NAND_ECC_HW, + .ecc_bits = 1, .bbt_options = NAND_BBT_USE_FLASH, }; diff --git a/arch/arm/mach-davinci/cpuidle.c b/arch/arm/mach-davinci/cpuidle.c index 36aef3a7dedb..f1ac1c94ac0f 100644 --- a/arch/arm/mach-davinci/cpuidle.c +++ b/arch/arm/mach-davinci/cpuidle.c @@ -65,7 +65,7 @@ static struct cpuidle_driver davinci_idle_driver = { .states[1] = { .enter = davinci_enter_idle, .exit_latency = 10, - .target_residency = 100000, + .target_residency = 10000, .flags = CPUIDLE_FLAG_TIME_VALID, .name = "DDR SR", .desc = "WFI and DDR Self Refresh", diff --git a/arch/arm/mach-dove/common.c b/arch/arm/mach-dove/common.c index 00247c771313..304f069ebf50 100644 --- a/arch/arm/mach-dove/common.c +++ b/arch/arm/mach-dove/common.c @@ -108,8 +108,8 @@ static void __init dove_clk_init(void) orion_clkdev_add(NULL, "sdhci-dove.1", sdio1); orion_clkdev_add(NULL, "orion_nand", nand); orion_clkdev_add(NULL, "cafe1000-ccic.0", camera); - orion_clkdev_add(NULL, "kirkwood-i2s.0", i2s0); - orion_clkdev_add(NULL, "kirkwood-i2s.1", i2s1); + orion_clkdev_add(NULL, "mvebu-audio.0", i2s0); + orion_clkdev_add(NULL, "mvebu-audio.1", i2s1); orion_clkdev_add(NULL, "mv_crypto", crypto); orion_clkdev_add(NULL, "dove-ac97", ac97); orion_clkdev_add(NULL, "dove-pdma", pdma); diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c index 7be13f8e69a0..a02f275a198d 100644 --- a/arch/arm/mach-imx/mach-imx6q.c +++ b/arch/arm/mach-imx/mach-imx6q.c @@ -254,13 +254,12 @@ static void __init imx6q_opp_init(struct device *cpu_dev) { struct device_node *np; - np = of_find_node_by_path("/cpus/cpu@0"); + np = of_node_get(cpu_dev->of_node); if (!np) { pr_warn("failed to find cpu0 node\n"); return; } - cpu_dev->of_node = np; if (of_init_opp_table(cpu_dev)) { pr_warn("failed to init OPP table\n"); goto put_node; diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c index e9238b5567ee..1663de090984 100644 --- a/arch/arm/mach-kirkwood/common.c +++ b/arch/arm/mach-kirkwood/common.c @@ -264,7 +264,7 @@ void __init kirkwood_clk_init(void) orion_clkdev_add(NULL, MV_XOR_NAME ".1", xor1); orion_clkdev_add("0", "pcie", pex0); orion_clkdev_add("1", "pcie", pex1); - orion_clkdev_add(NULL, "kirkwood-i2s", audio); + orion_clkdev_add(NULL, "mvebu-audio", audio); orion_clkdev_add(NULL, MV64XXX_I2C_CTLR_NAME ".0", runit); orion_clkdev_add(NULL, MV64XXX_I2C_CTLR_NAME ".1", runit); @@ -560,7 +560,7 @@ void __init kirkwood_timer_init(void) /***************************************************************************** * Audio ****************************************************************************/ -static struct resource kirkwood_i2s_resources[] = { +static struct resource kirkwood_audio_resources[] = { [0] = { .start = AUDIO_PHYS_BASE, .end = AUDIO_PHYS_BASE + SZ_16K - 1, @@ -573,29 +573,23 @@ static struct resource kirkwood_i2s_resources[] = { }, }; -static struct kirkwood_asoc_platform_data kirkwood_i2s_data = { +static struct kirkwood_asoc_platform_data kirkwood_audio_data = { .burst = 128, }; -static struct platform_device kirkwood_i2s_device = { - .name = "kirkwood-i2s", +static struct platform_device kirkwood_audio_device = { + .name = "mvebu-audio", .id = -1, - .num_resources = ARRAY_SIZE(kirkwood_i2s_resources), - .resource = kirkwood_i2s_resources, + .num_resources = ARRAY_SIZE(kirkwood_audio_resources), + .resource = kirkwood_audio_resources, .dev = { - .platform_data = &kirkwood_i2s_data, + .platform_data = &kirkwood_audio_data, }, }; -static struct platform_device kirkwood_pcm_device = { - .name = "kirkwood-pcm-audio", - .id = -1, -}; - void __init kirkwood_audio_init(void) { - platform_device_register(&kirkwood_i2s_device); - platform_device_register(&kirkwood_pcm_device); + platform_device_register(&kirkwood_audio_device); } /***************************************************************************** diff --git a/arch/arm/mach-msm/devices-msm7x00.c b/arch/arm/mach-msm/devices-msm7x00.c index 6d50fb964863..d83404d4b328 100644 --- a/arch/arm/mach-msm/devices-msm7x00.c +++ b/arch/arm/mach-msm/devices-msm7x00.c @@ -456,9 +456,9 @@ static struct clk_pcom_desc msm_clocks_7x01a[] = { CLK_PCOM("tsif_ref_clk", TSIF_REF_CLK, NULL, 0), CLK_PCOM("tv_dac_clk", TV_DAC_CLK, NULL, 0), CLK_PCOM("tv_enc_clk", TV_ENC_CLK, NULL, 0), - CLK_PCOM("uart_clk", UART1_CLK, "msm_serial.0", OFF), - CLK_PCOM("uart_clk", UART2_CLK, "msm_serial.1", 0), - CLK_PCOM("uart_clk", UART3_CLK, "msm_serial.2", OFF), + CLK_PCOM("core", UART1_CLK, "msm_serial.0", OFF), + CLK_PCOM("core", UART2_CLK, "msm_serial.1", 0), + CLK_PCOM("core", UART3_CLK, "msm_serial.2", OFF), CLK_PCOM("uart1dm_clk", UART1DM_CLK, NULL, OFF), CLK_PCOM("uart2dm_clk", UART2DM_CLK, NULL, 0), CLK_PCOM("usb_hs_clk", USB_HS_CLK, "msm_hsusb", OFF), diff --git a/arch/arm/mach-msm/devices-msm7x30.c b/arch/arm/mach-msm/devices-msm7x30.c index d4db75acff56..14e286948f69 100644 --- a/arch/arm/mach-msm/devices-msm7x30.c +++ b/arch/arm/mach-msm/devices-msm7x30.c @@ -211,7 +211,7 @@ static struct clk_pcom_desc msm_clocks_7x30[] = { CLK_PCOM("spi_pclk", SPI_P_CLK, NULL, 0), CLK_PCOM("tv_dac_clk", TV_DAC_CLK, NULL, 0), CLK_PCOM("tv_enc_clk", TV_ENC_CLK, NULL, 0), - CLK_PCOM("uart_clk", UART2_CLK, "msm_serial.1", 0), + CLK_PCOM("core", UART2_CLK, "msm_serial.1", 0), CLK_PCOM("usb_phy_clk", USB_PHY_CLK, NULL, 0), CLK_PCOM("usb_hs_clk", USB_HS_CLK, NULL, OFF), CLK_PCOM("usb_hs_pclk", USB_HS_P_CLK, NULL, OFF), diff --git a/arch/arm/mach-msm/devices-qsd8x50.c b/arch/arm/mach-msm/devices-qsd8x50.c index f5518112284b..2ed89b25d304 100644 --- a/arch/arm/mach-msm/devices-qsd8x50.c +++ b/arch/arm/mach-msm/devices-qsd8x50.c @@ -358,9 +358,9 @@ static struct clk_pcom_desc msm_clocks_8x50[] = { CLK_PCOM("tsif_ref_clk", TSIF_REF_CLK, NULL, 0), CLK_PCOM("tv_dac_clk", TV_DAC_CLK, NULL, 0), CLK_PCOM("tv_enc_clk", TV_ENC_CLK, NULL, 0), - CLK_PCOM("uart_clk", UART1_CLK, NULL, OFF), - CLK_PCOM("uart_clk", UART2_CLK, NULL, 0), - CLK_PCOM("uart_clk", UART3_CLK, "msm_serial.2", OFF), + CLK_PCOM("core", UART1_CLK, NULL, OFF), + CLK_PCOM("core", UART2_CLK, NULL, 0), + CLK_PCOM("core", UART3_CLK, "msm_serial.2", OFF), CLK_PCOM("uartdm_clk", UART1DM_CLK, NULL, OFF), CLK_PCOM("uartdm_clk", UART2DM_CLK, NULL, 0), CLK_PCOM("usb_hs_clk", USB_HS_CLK, NULL, OFF), diff --git a/arch/arm/mach-mvebu/platsmp.c b/arch/arm/mach-mvebu/platsmp.c index ce81d3031405..594b63db4215 100644 --- a/arch/arm/mach-mvebu/platsmp.c +++ b/arch/arm/mach-mvebu/platsmp.c @@ -29,45 +29,40 @@ #include "pmsu.h" #include "coherency.h" +static struct clk *__init get_cpu_clk(int cpu) +{ + struct clk *cpu_clk; + struct device_node *np = of_get_cpu_node(cpu, NULL); + + if (WARN(!np, "missing cpu node\n")) + return NULL; + cpu_clk = of_clk_get(np, 0); + if (WARN_ON(IS_ERR(cpu_clk))) + return NULL; + return cpu_clk; +} + void __init set_secondary_cpus_clock(void) { - int thiscpu; + int thiscpu, cpu; unsigned long rate; - struct clk *cpu_clk = NULL; - struct device_node *np = NULL; + struct clk *cpu_clk; thiscpu = smp_processor_id(); - for_each_node_by_type(np, "cpu") { - int err; - int cpu; - - err = of_property_read_u32(np, "reg", &cpu); - if (WARN_ON(err)) - return; - - if (cpu == thiscpu) { - cpu_clk = of_clk_get(np, 0); - break; - } - } - if (WARN_ON(IS_ERR(cpu_clk))) + cpu_clk = get_cpu_clk(thiscpu); + if (!cpu_clk) return; clk_prepare_enable(cpu_clk); rate = clk_get_rate(cpu_clk); /* set all the other CPU clk to the same rate than the boot CPU */ - for_each_node_by_type(np, "cpu") { - int err; - int cpu; - - err = of_property_read_u32(np, "reg", &cpu); - if (WARN_ON(err)) + for_each_possible_cpu(cpu) { + if (cpu == thiscpu) + continue; + cpu_clk = get_cpu_clk(cpu); + if (!cpu_clk) return; - - if (cpu != thiscpu) { - cpu_clk = of_clk_get(np, 0); - clk_set_rate(cpu_clk, rate); - } + clk_set_rate(cpu_clk, rate); } } diff --git a/arch/arm/mach-omap2/board-n8x0.c b/arch/arm/mach-omap2/board-n8x0.c index f6eeb87e4e95..827d15009a86 100644 --- a/arch/arm/mach-omap2/board-n8x0.c +++ b/arch/arm/mach-omap2/board-n8x0.c @@ -122,11 +122,7 @@ static struct musb_hdrc_config musb_config = { }; static struct musb_hdrc_platform_data tusb_data = { -#ifdef CONFIG_USB_GADGET_MUSB_HDRC .mode = MUSB_OTG, -#else - .mode = MUSB_HOST, -#endif .set_power = tusb_set_power, .min_power = 25, /* x2 = 50 mA drawn from VBUS as peripheral */ .power = 100, /* Max 100 mA VBUS for host mode */ diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c index 04c116555412..1c6ae5f5bae7 100644 --- a/arch/arm/mach-omap2/board-omap3beagle.c +++ b/arch/arm/mach-omap2/board-omap3beagle.c @@ -33,7 +33,7 @@ #include <linux/mtd/nand.h> #include <linux/mmc/host.h> #include <linux/usb/phy.h> -#include <linux/usb/nop-usb-xceiv.h> +#include <linux/usb/usb_phy_gen_xceiv.h> #include <linux/regulator/machine.h> #include <linux/i2c/twl.h> @@ -279,7 +279,7 @@ static struct regulator_consumer_supply beagle_vsim_supply[] = { static struct gpio_led gpio_leds[]; /* PHY's VCC regulator might be added later, so flag that we need it */ -static struct nop_usb_xceiv_platform_data hsusb2_phy_data = { +static struct usb_phy_gen_xceiv_platform_data hsusb2_phy_data = { .needs_vcc = true, }; diff --git a/arch/arm/mach-omap2/board-omap3evm.c b/arch/arm/mach-omap2/board-omap3evm.c index 8c026269baca..52bdddd41e0e 100644 --- a/arch/arm/mach-omap2/board-omap3evm.c +++ b/arch/arm/mach-omap2/board-omap3evm.c @@ -33,7 +33,7 @@ #include <linux/i2c/twl.h> #include <linux/usb/otg.h> #include <linux/usb/musb.h> -#include <linux/usb/nop-usb-xceiv.h> +#include <linux/usb/usb_phy_gen_xceiv.h> #include <linux/smsc911x.h> #include <linux/wl12xx.h> @@ -468,7 +468,7 @@ struct wl12xx_platform_data omap3evm_wlan_data __initdata = { static struct regulator_consumer_supply omap3evm_vaux2_supplies[] = { REGULATOR_SUPPLY("VDD_CSIPHY1", "omap3isp"), /* OMAP ISP */ REGULATOR_SUPPLY("VDD_CSIPHY2", "omap3isp"), /* OMAP ISP */ - REGULATOR_SUPPLY("vcc", "nop_usb_xceiv.2"), /* hsusb port 2 */ + REGULATOR_SUPPLY("vcc", "usb_phy_gen_xceiv.2"), /* hsusb port 2 */ REGULATOR_SUPPLY("vaux2", NULL), }; diff --git a/arch/arm/mach-omap2/board-omap3pandora.c b/arch/arm/mach-omap2/board-omap3pandora.c index b1547a0edfcd..d2b455e70486 100644 --- a/arch/arm/mach-omap2/board-omap3pandora.c +++ b/arch/arm/mach-omap2/board-omap3pandora.c @@ -352,7 +352,7 @@ static struct regulator_consumer_supply pandora_vcc_lcd_supply[] = { }; static struct regulator_consumer_supply pandora_usb_phy_supply[] = { - REGULATOR_SUPPLY("vcc", "nop_usb_xceiv.2"), /* hsusb port 2 */ + REGULATOR_SUPPLY("vcc", "usb_phy_gen_xceiv.2"), /* hsusb port 2 */ }; /* ads7846 on SPI and 2 nub controllers on I2C */ diff --git a/arch/arm/mach-omap2/board-rx51.c b/arch/arm/mach-omap2/board-rx51.c index d2ea68ea678a..7735105561d8 100644 --- a/arch/arm/mach-omap2/board-rx51.c +++ b/arch/arm/mach-omap2/board-rx51.c @@ -85,7 +85,7 @@ static struct omap_board_mux board_mux[] __initdata = { static struct omap_musb_board_data musb_board_data = { .interface_type = MUSB_INTERFACE_ULPI, - .mode = MUSB_PERIPHERAL, + .mode = MUSB_OTG, .power = 0, }; diff --git a/arch/arm/mach-omap2/i2c.c b/arch/arm/mach-omap2/i2c.c index d940e53dd9f2..b456b4471f35 100644 --- a/arch/arm/mach-omap2/i2c.c +++ b/arch/arm/mach-omap2/i2c.c @@ -181,7 +181,7 @@ int __init omap_i2c_add_bus(struct omap_i2c_bus_platform_data *i2c_pdata, sizeof(struct omap_i2c_bus_platform_data)); WARN(IS_ERR(pdev), "Could not build omap_device for %s\n", name); - return PTR_RET(pdev); + return PTR_ERR_OR_ZERO(pdev); } static int __init omap_i2c_cmdline(void) diff --git a/arch/arm/mach-omap2/usb-host.c b/arch/arm/mach-omap2/usb-host.c index 2eb19d4d0aa1..e83a6a4b184a 100644 --- a/arch/arm/mach-omap2/usb-host.c +++ b/arch/arm/mach-omap2/usb-host.c @@ -28,7 +28,7 @@ #include <linux/io.h> #include <linux/gpio.h> #include <linux/usb/phy.h> -#include <linux/usb/nop-usb-xceiv.h> +#include <linux/usb/usb_phy_gen_xceiv.h> #include "soc.h" #include "omap_device.h" @@ -349,7 +349,7 @@ static struct fixed_voltage_config hsusb_reg_config = { /* .init_data filled later */ }; -static const char *nop_name = "nop_usb_xceiv"; /* NOP PHY driver */ +static const char *nop_name = "usb_phy_gen_xceiv"; /* NOP PHY driver */ static const char *reg_name = "reg-fixed-voltage"; /* Regulator driver */ /** @@ -460,9 +460,9 @@ int usbhs_init_phys(struct usbhs_phy_data *phy, int num_phys) pdevinfo.name = nop_name; pdevinfo.id = phy->port; pdevinfo.data = phy->platform_data; - pdevinfo.size_data = sizeof(struct nop_usb_xceiv_platform_data); - - scnprintf(phy_id, MAX_STR, "nop_usb_xceiv.%d", + pdevinfo.size_data = + sizeof(struct usb_phy_gen_xceiv_platform_data); + scnprintf(phy_id, MAX_STR, "usb_phy_gen_xceiv.%d", phy->port); pdev = platform_device_register_full(&pdevinfo); if (IS_ERR(pdev)) { diff --git a/arch/arm/mach-omap2/usb-musb.c b/arch/arm/mach-omap2/usb-musb.c index 8c4de2708cf2..bc897231bd10 100644 --- a/arch/arm/mach-omap2/usb-musb.c +++ b/arch/arm/mach-omap2/usb-musb.c @@ -38,11 +38,8 @@ static struct musb_hdrc_config musb_config = { }; static struct musb_hdrc_platform_data musb_plat = { -#ifdef CONFIG_USB_GADGET_MUSB_HDRC .mode = MUSB_OTG, -#else - .mode = MUSB_HOST, -#endif + /* .clock is set dynamically */ .config = &musb_config, diff --git a/arch/arm/mach-prima2/common.c b/arch/arm/mach-prima2/common.c index 2c70f74fed5d..e110b6d4ae8c 100644 --- a/arch/arm/mach-prima2/common.c +++ b/arch/arm/mach-prima2/common.c @@ -42,7 +42,6 @@ static const char *atlas6_dt_match[] __initdata = { DT_MACHINE_START(ATLAS6_DT, "Generic ATLAS6 (Flattened Device Tree)") /* Maintainer: Barry Song <baohua.song@csr.com> */ - .nr_irqs = 128, .map_io = sirfsoc_map_io, .init_time = sirfsoc_init_time, .init_late = sirfsoc_init_late, @@ -59,7 +58,6 @@ static const char *prima2_dt_match[] __initdata = { DT_MACHINE_START(PRIMA2_DT, "Generic PRIMA2 (Flattened Device Tree)") /* Maintainer: Barry Song <baohua.song@csr.com> */ - .nr_irqs = 128, .map_io = sirfsoc_map_io, .init_time = sirfsoc_init_time, .dma_zone_size = SZ_256M, diff --git a/arch/arm/mach-tegra/tegra.c b/arch/arm/mach-tegra/tegra.c index 0d1e4128d460..fc97cfd52769 100644 --- a/arch/arm/mach-tegra/tegra.c +++ b/arch/arm/mach-tegra/tegra.c @@ -29,7 +29,6 @@ #include <linux/of_fdt.h> #include <linux/of_platform.h> #include <linux/pda_power.h> -#include <linux/platform_data/tegra_usb.h> #include <linux/io.h> #include <linux/slab.h> #include <linux/sys_soc.h> @@ -46,40 +45,6 @@ #include "fuse.h" #include "iomap.h" -static struct tegra_ehci_platform_data tegra_ehci1_pdata = { - .operating_mode = TEGRA_USB_OTG, - .power_down_on_bus_suspend = 1, - .vbus_gpio = -1, -}; - -static struct tegra_ulpi_config tegra_ehci2_ulpi_phy_config = { - .reset_gpio = -1, - .clk = "cdev2", -}; - -static struct tegra_ehci_platform_data tegra_ehci2_pdata = { - .phy_config = &tegra_ehci2_ulpi_phy_config, - .operating_mode = TEGRA_USB_HOST, - .power_down_on_bus_suspend = 1, - .vbus_gpio = -1, -}; - -static struct tegra_ehci_platform_data tegra_ehci3_pdata = { - .operating_mode = TEGRA_USB_HOST, - .power_down_on_bus_suspend = 1, - .vbus_gpio = -1, -}; - -static struct of_dev_auxdata tegra20_auxdata_lookup[] __initdata = { - OF_DEV_AUXDATA("nvidia,tegra20-ehci", 0xC5000000, "tegra-ehci.0", - &tegra_ehci1_pdata), - OF_DEV_AUXDATA("nvidia,tegra20-ehci", 0xC5004000, "tegra-ehci.1", - &tegra_ehci2_pdata), - OF_DEV_AUXDATA("nvidia,tegra20-ehci", 0xC5008000, "tegra-ehci.2", - &tegra_ehci3_pdata), - {} -}; - static void __init tegra_dt_init(void) { struct soc_device_attribute *soc_dev_attr; @@ -112,8 +77,7 @@ static void __init tegra_dt_init(void) * devices */ out: - of_platform_populate(NULL, of_default_bus_match_table, - tegra20_auxdata_lookup, parent); + of_platform_populate(NULL, of_default_bus_match_table, NULL, parent); } static void __init trimslice_init(void) diff --git a/arch/arm/mach-ux500/Makefile b/arch/arm/mach-ux500/Makefile index bf9b6be5b180..fe1f3e26b88b 100644 --- a/arch/arm/mach-ux500/Makefile +++ b/arch/arm/mach-ux500/Makefile @@ -4,7 +4,6 @@ obj-y := cpu.o devices.o devices-common.o \ id.o usb.o timer.o pm.o -obj-$(CONFIG_CPU_IDLE) += cpuidle.o obj-$(CONFIG_CACHE_L2X0) += cache-l2x0.o obj-$(CONFIG_UX500_SOC_DB8500) += cpu-db8500.o devices-db8500.o obj-$(CONFIG_MACH_MOP500) += board-mop500.o board-mop500-sdi.o \ diff --git a/arch/arm/mach-ux500/cpuidle.c b/arch/arm/mach-ux500/cpuidle.c deleted file mode 100644 index a45dd09daed9..000000000000 --- a/arch/arm/mach-ux500/cpuidle.c +++ /dev/null @@ -1,128 +0,0 @@ -/* - * Copyright (c) 2012 Linaro : Daniel Lezcano <daniel.lezcano@linaro.org> (IBM) - * - * Based on the work of Rickard Andersson <rickard.andersson@stericsson.com> - * and Jonas Aaberg <jonas.aberg@stericsson.com>. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ - -#include <linux/module.h> -#include <linux/cpuidle.h> -#include <linux/spinlock.h> -#include <linux/atomic.h> -#include <linux/smp.h> -#include <linux/mfd/dbx500-prcmu.h> -#include <linux/platform_data/arm-ux500-pm.h> - -#include <asm/cpuidle.h> -#include <asm/proc-fns.h> - -#include "db8500-regs.h" -#include "id.h" - -static atomic_t master = ATOMIC_INIT(0); -static DEFINE_SPINLOCK(master_lock); - -static inline int ux500_enter_idle(struct cpuidle_device *dev, - struct cpuidle_driver *drv, int index) -{ - int this_cpu = smp_processor_id(); - bool recouple = false; - - if (atomic_inc_return(&master) == num_online_cpus()) { - - /* With this lock, we prevent the other cpu to exit and enter - * this function again and become the master */ - if (!spin_trylock(&master_lock)) - goto wfi; - - /* decouple the gic from the A9 cores */ - if (prcmu_gic_decouple()) { - spin_unlock(&master_lock); - goto out; - } - - /* If an error occur, we will have to recouple the gic - * manually */ - recouple = true; - - /* At this state, as the gic is decoupled, if the other - * cpu is in WFI, we have the guarantee it won't be wake - * up, so we can safely go to retention */ - if (!prcmu_is_cpu_in_wfi(this_cpu ? 0 : 1)) - goto out; - - /* The prcmu will be in charge of watching the interrupts - * and wake up the cpus */ - if (prcmu_copy_gic_settings()) - goto out; - - /* Check in the meantime an interrupt did - * not occur on the gic ... */ - if (prcmu_gic_pending_irq()) - goto out; - - /* ... and the prcmu */ - if (prcmu_pending_irq()) - goto out; - - /* Go to the retention state, the prcmu will wait for the - * cpu to go WFI and this is what happens after exiting this - * 'master' critical section */ - if (prcmu_set_power_state(PRCMU_AP_IDLE, true, true)) - goto out; - - /* When we switch to retention, the prcmu is in charge - * of recoupling the gic automatically */ - recouple = false; - - spin_unlock(&master_lock); - } -wfi: - cpu_do_idle(); -out: - atomic_dec(&master); - - if (recouple) { - prcmu_gic_recouple(); - spin_unlock(&master_lock); - } - - return index; -} - -static struct cpuidle_driver ux500_idle_driver = { - .name = "ux500_idle", - .owner = THIS_MODULE, - .states = { - ARM_CPUIDLE_WFI_STATE, - { - .enter = ux500_enter_idle, - .exit_latency = 70, - .target_residency = 260, - .flags = CPUIDLE_FLAG_TIME_VALID | - CPUIDLE_FLAG_TIMER_STOP, - .name = "ApIdle", - .desc = "ARM Retention", - }, - }, - .safe_state_index = 0, - .state_count = 2, -}; - -int __init ux500_idle_init(void) -{ - if (!(cpu_is_u8500_family() || cpu_is_ux540_family())) - return -ENODEV; - - /* Configure wake up reasons */ - prcmu_enable_wakeups(PRCMU_WAKEUP(ARM) | PRCMU_WAKEUP(RTC) | - PRCMU_WAKEUP(ABB)); - - return cpuidle_register(&ux500_idle_driver, NULL); -} - -device_initcall(ux500_idle_init); diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index db5c2cab8fda..cd2c88e7a8f7 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -809,15 +809,18 @@ config KUSER_HELPERS the CPU type fitted to the system. This permits binaries to be run on ARMv4 through to ARMv7 without modification. + See Documentation/arm/kernel_user_helpers.txt for details. + However, the fixed address nature of these helpers can be used by ROP (return orientated programming) authors when creating exploits. If all of the binaries and libraries which run on your platform are built specifically for your platform, and make no use of - these helpers, then you can turn this option off. However, - when such an binary or library is run, it will receive a SIGILL - signal, which will terminate the program. + these helpers, then you can turn this option off to hinder + such exploits. However, in that case, if a binary or library + relying on those helpers is run, it will receive a SIGILL signal, + which will terminate the program. Say N here only if you are absolutely certain that you do not need these helpers; otherwise, the safe option is to say Y. diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 7f9b1798c6cf..dbddc07a3bbd 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -358,7 +358,7 @@ static int __init atomic_pool_init(void) if (!pages) goto no_pages; - if (IS_ENABLED(CONFIG_CMA)) + if (IS_ENABLED(CONFIG_DMA_CMA)) ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page, atomic_pool_init); else @@ -670,7 +670,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, addr = __alloc_simple_buffer(dev, size, gfp, &page); else if (!(gfp & __GFP_WAIT)) addr = __alloc_from_pool(size, &page); - else if (!IS_ENABLED(CONFIG_CMA)) + else if (!IS_ENABLED(CONFIG_DMA_CMA)) addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller); else addr = __alloc_from_contiguous(dev, size, prot, &page, caller); @@ -759,7 +759,7 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr, __dma_free_buffer(page, size); } else if (__free_from_pool(cpu_addr, size)) { return; - } else if (!IS_ENABLED(CONFIG_CMA)) { + } else if (!IS_ENABLED(CONFIG_DMA_CMA)) { __dma_free_remap(cpu_addr, size); __dma_free_buffer(page, size); } else { diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c index 8e11e96eab5e..c83f27b6bdda 100644 --- a/arch/arm/plat-pxa/ssp.c +++ b/arch/arm/plat-pxa/ssp.c @@ -30,6 +30,8 @@ #include <linux/platform_device.h> #include <linux/spi/pxa2xx_spi.h> #include <linux/io.h> +#include <linux/of.h> +#include <linux/of_device.h> #include <asm/irq.h> #include <mach/hardware.h> @@ -60,6 +62,30 @@ struct ssp_device *pxa_ssp_request(int port, const char *label) } EXPORT_SYMBOL(pxa_ssp_request); +struct ssp_device *pxa_ssp_request_of(const struct device_node *of_node, + const char *label) +{ + struct ssp_device *ssp = NULL; + + mutex_lock(&ssp_lock); + + list_for_each_entry(ssp, &ssp_list, node) { + if (ssp->of_node == of_node && ssp->use_count == 0) { + ssp->use_count++; + ssp->label = label; + break; + } + } + + mutex_unlock(&ssp_lock); + + if (&ssp->node == &ssp_list) + return NULL; + + return ssp; +} +EXPORT_SYMBOL(pxa_ssp_request_of); + void pxa_ssp_free(struct ssp_device *ssp) { mutex_lock(&ssp_lock); @@ -72,96 +98,126 @@ void pxa_ssp_free(struct ssp_device *ssp) } EXPORT_SYMBOL(pxa_ssp_free); +#ifdef CONFIG_OF +static const struct of_device_id pxa_ssp_of_ids[] = { + { .compatible = "mrvl,pxa25x-ssp", .data = (void *) PXA25x_SSP }, + { .compatible = "mvrl,pxa25x-nssp", .data = (void *) PXA25x_NSSP }, + { .compatible = "mrvl,pxa27x-ssp", .data = (void *) PXA27x_SSP }, + { .compatible = "mrvl,pxa3xx-ssp", .data = (void *) PXA3xx_SSP }, + { .compatible = "mvrl,pxa168-ssp", .data = (void *) PXA168_SSP }, + { .compatible = "mrvl,pxa910-ssp", .data = (void *) PXA910_SSP }, + { .compatible = "mrvl,ce4100-ssp", .data = (void *) CE4100_SSP }, + { .compatible = "mrvl,lpss-ssp", .data = (void *) LPSS_SSP }, + { }, +}; +MODULE_DEVICE_TABLE(of, pxa_ssp_of_ids); +#endif + static int pxa_ssp_probe(struct platform_device *pdev) { - const struct platform_device_id *id = platform_get_device_id(pdev); struct resource *res; struct ssp_device *ssp; - int ret = 0; + struct device *dev = &pdev->dev; - ssp = kzalloc(sizeof(struct ssp_device), GFP_KERNEL); - if (ssp == NULL) { - dev_err(&pdev->dev, "failed to allocate memory"); + ssp = devm_kzalloc(dev, sizeof(struct ssp_device), GFP_KERNEL); + if (ssp == NULL) return -ENOMEM; - } - ssp->pdev = pdev; - ssp->clk = clk_get(&pdev->dev, NULL); - if (IS_ERR(ssp->clk)) { - ret = PTR_ERR(ssp->clk); - goto err_free; - } + ssp->pdev = pdev; - res = platform_get_resource(pdev, IORESOURCE_DMA, 0); - if (res == NULL) { - dev_err(&pdev->dev, "no SSP RX DRCMR defined\n"); - ret = -ENODEV; - goto err_free_clk; - } - ssp->drcmr_rx = res->start; + ssp->clk = devm_clk_get(dev, NULL); + if (IS_ERR(ssp->clk)) + return PTR_ERR(ssp->clk); + + if (dev->of_node) { + struct of_phandle_args dma_spec; + struct device_node *np = dev->of_node; + + /* + * FIXME: we should allocate the DMA channel from this + * context and pass the channel down to the ssp users. + * For now, we lookup the rx and tx indices manually + */ + + /* rx */ + of_parse_phandle_with_args(np, "dmas", "#dma-cells", + 0, &dma_spec); + ssp->drcmr_rx = dma_spec.args[0]; + of_node_put(dma_spec.np); + + /* tx */ + of_parse_phandle_with_args(np, "dmas", "#dma-cells", + 1, &dma_spec); + ssp->drcmr_tx = dma_spec.args[0]; + of_node_put(dma_spec.np); + } else { + res = platform_get_resource(pdev, IORESOURCE_DMA, 0); + if (res == NULL) { + dev_err(dev, "no SSP RX DRCMR defined\n"); + return -ENODEV; + } + ssp->drcmr_rx = res->start; - res = platform_get_resource(pdev, IORESOURCE_DMA, 1); - if (res == NULL) { - dev_err(&pdev->dev, "no SSP TX DRCMR defined\n"); - ret = -ENODEV; - goto err_free_clk; + res = platform_get_resource(pdev, IORESOURCE_DMA, 1); + if (res == NULL) { + dev_err(dev, "no SSP TX DRCMR defined\n"); + return -ENODEV; + } + ssp->drcmr_tx = res->start; } - ssp->drcmr_tx = res->start; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (res == NULL) { - dev_err(&pdev->dev, "no memory resource defined\n"); - ret = -ENODEV; - goto err_free_clk; + dev_err(dev, "no memory resource defined\n"); + return -ENODEV; } - res = request_mem_region(res->start, resource_size(res), - pdev->name); + res = devm_request_mem_region(dev, res->start, resource_size(res), + pdev->name); if (res == NULL) { - dev_err(&pdev->dev, "failed to request memory resource\n"); - ret = -EBUSY; - goto err_free_clk; + dev_err(dev, "failed to request memory resource\n"); + return -EBUSY; } ssp->phys_base = res->start; - ssp->mmio_base = ioremap(res->start, resource_size(res)); + ssp->mmio_base = devm_ioremap(dev, res->start, resource_size(res)); if (ssp->mmio_base == NULL) { - dev_err(&pdev->dev, "failed to ioremap() registers\n"); - ret = -ENODEV; - goto err_free_mem; + dev_err(dev, "failed to ioremap() registers\n"); + return -ENODEV; } ssp->irq = platform_get_irq(pdev, 0); if (ssp->irq < 0) { - dev_err(&pdev->dev, "no IRQ resource defined\n"); - ret = -ENODEV; - goto err_free_io; + dev_err(dev, "no IRQ resource defined\n"); + return -ENODEV; + } + + if (dev->of_node) { + const struct of_device_id *id = + of_match_device(of_match_ptr(pxa_ssp_of_ids), dev); + ssp->type = (int) id->data; + } else { + const struct platform_device_id *id = + platform_get_device_id(pdev); + ssp->type = (int) id->driver_data; + + /* PXA2xx/3xx SSP ports starts from 1 and the internal pdev->id + * starts from 0, do a translation here + */ + ssp->port_id = pdev->id + 1; } - /* PXA2xx/3xx SSP ports starts from 1 and the internal pdev->id - * starts from 0, do a translation here - */ - ssp->port_id = pdev->id + 1; ssp->use_count = 0; - ssp->type = (int)id->driver_data; + ssp->of_node = dev->of_node; mutex_lock(&ssp_lock); list_add(&ssp->node, &ssp_list); mutex_unlock(&ssp_lock); platform_set_drvdata(pdev, ssp); - return 0; -err_free_io: - iounmap(ssp->mmio_base); -err_free_mem: - release_mem_region(res->start, resource_size(res)); -err_free_clk: - clk_put(ssp->clk); -err_free: - kfree(ssp); - return ret; + return 0; } static int pxa_ssp_remove(struct platform_device *pdev) @@ -201,8 +257,9 @@ static struct platform_driver pxa_ssp_driver = { .probe = pxa_ssp_probe, .remove = pxa_ssp_remove, .driver = { - .owner = THIS_MODULE, - .name = "pxa2xx-ssp", + .owner = THIS_MODULE, + .name = "pxa2xx-ssp", + .of_match_table = of_match_ptr(pxa_ssp_of_ids), }, .id_table = ssp_id_table, }; diff --git a/arch/arm/plat-samsung/init.c b/arch/arm/plat-samsung/init.c index 3e5c4619caa5..50a3ea0037db 100644 --- a/arch/arm/plat-samsung/init.c +++ b/arch/arm/plat-samsung/init.c @@ -55,12 +55,13 @@ void __init s3c_init_cpu(unsigned long idcode, printk("CPU %s (id 0x%08lx)\n", cpu->name, idcode); - if (cpu->map_io == NULL || cpu->init == NULL) { + if (cpu->init == NULL) { printk(KERN_ERR "CPU %s support not enabled\n", cpu->name); panic("Unsupported Samsung CPU"); } - cpu->map_io(); + if (cpu->map_io) + cpu->map_io(); } /* s3c24xx_init_clocks diff --git a/arch/arm/plat-samsung/s3c-dma-ops.c b/arch/arm/plat-samsung/s3c-dma-ops.c index 0cc40aea3f5a..98b10ba67dc7 100644 --- a/arch/arm/plat-samsung/s3c-dma-ops.c +++ b/arch/arm/plat-samsung/s3c-dma-ops.c @@ -82,7 +82,8 @@ static int s3c_dma_config(unsigned ch, struct samsung_dma_config *param) static int s3c_dma_prepare(unsigned ch, struct samsung_dma_prep *param) { struct cb_data *data; - int len = (param->cap == DMA_CYCLIC) ? param->period : param->len; + dma_addr_t pos = param->buf; + dma_addr_t end = param->buf + param->len; list_for_each_entry(data, &dma_list, node) if (data->ch == ch) @@ -94,7 +95,15 @@ static int s3c_dma_prepare(unsigned ch, struct samsung_dma_prep *param) data->fp_param = param->fp_param; } - s3c2410_dma_enqueue(ch, (void *)data, param->buf, len); + if (param->cap != DMA_CYCLIC) { + s3c2410_dma_enqueue(ch, (void *)data, param->buf, param->len); + return 0; + } + + while (pos < end) { + s3c2410_dma_enqueue(ch, (void *)data, pos, param->period); + pos += param->period; + } return 0; } diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index c9770ba5c7df..8a6295c86209 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -170,6 +170,7 @@ static void __init xen_percpu_init(void *unused) per_cpu(xen_vcpu, cpu) = vcpup; enable_percpu_irq(xen_events_irq, 0); + put_cpu(); } static void xen_restart(enum reboot_mode reboot_mode, const char *cmd) diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h index 98abd476992d..c9f1d2816c2b 100644 --- a/arch/arm64/include/asm/arch_timer.h +++ b/arch/arm64/include/asm/arch_timer.h @@ -26,7 +26,13 @@ #include <clocksource/arm_arch_timer.h> -static inline void arch_timer_reg_write(int access, int reg, u32 val) +/* + * These register accessors are marked inline so the compiler can + * nicely work out which register we want, and chuck away the rest of + * the code. + */ +static __always_inline +void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val) { if (access == ARCH_TIMER_PHYS_ACCESS) { switch (reg) { @@ -36,8 +42,6 @@ static inline void arch_timer_reg_write(int access, int reg, u32 val) case ARCH_TIMER_REG_TVAL: asm volatile("msr cntp_tval_el0, %0" : : "r" (val)); break; - default: - BUILD_BUG(); } } else if (access == ARCH_TIMER_VIRT_ACCESS) { switch (reg) { @@ -47,17 +51,14 @@ static inline void arch_timer_reg_write(int access, int reg, u32 val) case ARCH_TIMER_REG_TVAL: asm volatile("msr cntv_tval_el0, %0" : : "r" (val)); break; - default: - BUILD_BUG(); } - } else { - BUILD_BUG(); } isb(); } -static inline u32 arch_timer_reg_read(int access, int reg) +static __always_inline +u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg) { u32 val; @@ -69,8 +70,6 @@ static inline u32 arch_timer_reg_read(int access, int reg) case ARCH_TIMER_REG_TVAL: asm volatile("mrs %0, cntp_tval_el0" : "=r" (val)); break; - default: - BUILD_BUG(); } } else if (access == ARCH_TIMER_VIRT_ACCESS) { switch (reg) { @@ -80,11 +79,7 @@ static inline u32 arch_timer_reg_read(int access, int reg) case ARCH_TIMER_REG_TVAL: asm volatile("mrs %0, cntv_tval_el0" : "=r" (val)); break; - default: - BUILD_BUG(); } - } else { - BUILD_BUG(); } return val; diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index c92de4163eba..b25763bc0ec4 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -42,14 +42,15 @@ #define TPIDR_EL1 18 /* Thread ID, Privileged */ #define AMAIR_EL1 19 /* Aux Memory Attribute Indirection Register */ #define CNTKCTL_EL1 20 /* Timer Control Register (EL1) */ +#define PAR_EL1 21 /* Physical Address Register */ /* 32bit specific registers. Keep them at the end of the range */ -#define DACR32_EL2 21 /* Domain Access Control Register */ -#define IFSR32_EL2 22 /* Instruction Fault Status Register */ -#define FPEXC32_EL2 23 /* Floating-Point Exception Control Register */ -#define DBGVCR32_EL2 24 /* Debug Vector Catch Register */ -#define TEECR32_EL1 25 /* ThumbEE Configuration Register */ -#define TEEHBR32_EL1 26 /* ThumbEE Handler Base Register */ -#define NR_SYS_REGS 27 +#define DACR32_EL2 22 /* Domain Access Control Register */ +#define IFSR32_EL2 23 /* Instruction Fault Status Register */ +#define FPEXC32_EL2 24 /* Floating-Point Exception Control Register */ +#define DBGVCR32_EL2 25 /* Debug Vector Catch Register */ +#define TEECR32_EL1 26 /* ThumbEE Configuration Register */ +#define TEEHBR32_EL1 27 /* ThumbEE Handler Base Register */ +#define NR_SYS_REGS 28 /* 32bit mapping */ #define c0_MPIDR (MPIDR_EL1 * 2) /* MultiProcessor ID Register */ @@ -69,6 +70,8 @@ #define c5_AIFSR (AFSR1_EL1 * 2) /* Auxiliary Instr Fault Status R */ #define c6_DFAR (FAR_EL1 * 2) /* Data Fault Address Register */ #define c6_IFAR (c6_DFAR + 1) /* Instruction Fault Address Register */ +#define c7_PAR (PAR_EL1 * 2) /* Physical Address Register */ +#define c7_PAR_high (c7_PAR + 1) /* PAR top 32 bits */ #define c10_PRRR (MAIR_EL1 * 2) /* Primary Region Remap Register */ #define c10_NMRR (c10_PRRR + 1) /* Normal Memory Remap Register */ #define c12_VBAR (VBAR_EL1 * 2) /* Vector Base Address Register */ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 644d73956864..0859a4ddd1e7 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -129,7 +129,7 @@ struct kvm_vcpu_arch { struct kvm_mmu_memory_cache mmu_page_cache; /* Target CPU and feature flags */ - u32 target; + int target; DECLARE_BITMAP(features, KVM_VCPU_MAX_FEATURES); /* Detect first run of a vcpu */ diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 9ba33c40cdf8..12e6ccb88691 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -107,7 +107,12 @@ armpmu_map_cache_event(const unsigned (*cache_map) static int armpmu_map_event(const unsigned (*event_map)[PERF_COUNT_HW_MAX], u64 config) { - int mapping = (*event_map)[config]; + int mapping; + + if (config >= PERF_COUNT_HW_MAX) + return -EINVAL; + + mapping = (*event_map)[config]; return mapping == HW_OP_UNSUPPORTED ? -ENOENT : mapping; } @@ -317,6 +322,9 @@ validate_event(struct pmu_hw_events *hw_events, struct hw_perf_event fake_event = event->hw; struct pmu *leader_pmu = event->group_leader->pmu; + if (is_software_event(event)) + return 1; + if (event->pmu != leader_pmu || event->state <= PERF_EVENT_STATE_OFF) return 1; diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index ff985e3d8b72..1ac0bbbdddb2 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -214,6 +214,7 @@ __kvm_hyp_code_start: mrs x21, tpidr_el1 mrs x22, amair_el1 mrs x23, cntkctl_el1 + mrs x24, par_el1 stp x4, x5, [x3] stp x6, x7, [x3, #16] @@ -225,6 +226,7 @@ __kvm_hyp_code_start: stp x18, x19, [x3, #112] stp x20, x21, [x3, #128] stp x22, x23, [x3, #144] + str x24, [x3, #160] .endm .macro restore_sysregs @@ -243,6 +245,7 @@ __kvm_hyp_code_start: ldp x18, x19, [x3, #112] ldp x20, x21, [x3, #128] ldp x22, x23, [x3, #144] + ldr x24, [x3, #160] msr vmpidr_el2, x4 msr csselr_el1, x5 @@ -264,6 +267,7 @@ __kvm_hyp_code_start: msr tpidr_el1, x21 msr amair_el1, x22 msr cntkctl_el1, x23 + msr par_el1, x24 .endm .macro skip_32bit_state tmp, target @@ -600,6 +604,8 @@ END(__kvm_vcpu_run) // void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); ENTRY(__kvm_tlb_flush_vmid_ipa) + dsb ishst + kern_hyp_va x0 ldr x2, [x0, #KVM_VTTBR] msr vttbr_el2, x2 @@ -621,6 +627,7 @@ ENTRY(__kvm_tlb_flush_vmid_ipa) ENDPROC(__kvm_tlb_flush_vmid_ipa) ENTRY(__kvm_flush_vm_context) + dsb ishst tlbi alle1is ic ialluis dsb sy @@ -753,6 +760,10 @@ el1_trap: */ tbnz x1, #7, 1f // S1PTW is set + /* Preserve PAR_EL1 */ + mrs x3, par_el1 + push x3, xzr + /* * Permission fault, HPFAR_EL2 is invalid. * Resolve the IPA the hard way using the guest VA. @@ -766,6 +777,8 @@ el1_trap: /* Read result */ mrs x3, par_el1 + pop x0, xzr // Restore PAR_EL1 from the stack + msr par_el1, x0 tbnz x3, #0, 3f // Bail out if we failed the translation ubfx x3, x3, #12, #36 // Extract IPA lsl x3, x3, #4 // and present it like HPFAR diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 94923609753b..02e9d09e1d80 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -211,6 +211,9 @@ static const struct sys_reg_desc sys_reg_descs[] = { /* FAR_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b0110), CRm(0b0000), Op2(0b000), NULL, reset_unknown, FAR_EL1 }, + /* PAR_EL1 */ + { Op0(0b11), Op1(0b000), CRn(0b0111), CRm(0b0100), Op2(0b000), + NULL, reset_unknown, PAR_EL1 }, /* PMINTENSET_EL1 */ { Op0(0b11), Op1(0b000), CRn(0b1001), CRm(0b1110), Op2(0b001), diff --git a/arch/frv/mb93090-mb00/pci-vdk.c b/arch/frv/mb93090-mb00/pci-vdk.c index 0aa35f0eb0db..deb67843693c 100644 --- a/arch/frv/mb93090-mb00/pci-vdk.c +++ b/arch/frv/mb93090-mb00/pci-vdk.c @@ -320,7 +320,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pci_fixup_ide_bases); * are examined. */ -void __init pcibios_fixup_bus(struct pci_bus *bus) +void pcibios_fixup_bus(struct pci_bus *bus) { #if 0 printk("### PCIBIOS_FIXUP_BUS(%d)\n",bus->number); diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 5a768ad8e893..566642266324 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -43,6 +43,7 @@ config IA64 select SYSCTL_ARCH_UNALIGN_NO_WARN select HAVE_MOD_ARCH_SPECIFIC select MODULES_USE_ELF_RELA + select ARCH_USE_CMPXCHG_LOCKREF default y help The Itanium Processor Family is Intel's 64-bit successor to @@ -565,9 +566,9 @@ config KEXEC It is an ongoing process to be certain the hardware in a machine is properly shutdown, so do not be surprised if this code does not - initially work for you. It may help to enable device hotplugging - support. As of this writing the exact hardware interface is - strongly in flux, so no good recommendation can be made. + initially work for you. As of this writing the exact hardware + interface is strongly in flux, so no good recommendation can be + made. config CRASH_DUMP bool "kernel crash dumps" diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild index 05b03ecd7933..a3456f34f672 100644 --- a/arch/ia64/include/asm/Kbuild +++ b/arch/ia64/include/asm/Kbuild @@ -3,3 +3,4 @@ generic-y += clkdev.h generic-y += exec.h generic-y += kvm_para.h generic-y += trace_clock.h +generic-y += vtime.h
\ No newline at end of file diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h index 54ff557d474e..45698cd15b7b 100644 --- a/arch/ia64/include/asm/spinlock.h +++ b/arch/ia64/include/asm/spinlock.h @@ -102,6 +102,11 @@ static inline int __ticket_spin_is_contended(arch_spinlock_t *lock) return ((tmp - (tmp >> TICKET_SHIFT)) & TICKET_MASK) > 1; } +static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) +{ + return !(((lock.lock >> TICKET_SHIFT) ^ lock.lock) & TICKET_MASK); +} + static inline int arch_spin_is_locked(arch_spinlock_t *lock) { return __ticket_spin_is_locked(lock); diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index 5b2dc0d10c8f..bdfd8789b376 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1560,6 +1560,10 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) return 0; } +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_userspace_memory_region *mem, diff --git a/arch/m68k/amiga/platform.c b/arch/m68k/amiga/platform.c index 6083088c0cca..dacd9f911f71 100644 --- a/arch/m68k/amiga/platform.c +++ b/arch/m68k/amiga/platform.c @@ -56,7 +56,7 @@ static int __init amiga_init_bus(void) n = AMIGAHW_PRESENT(ZORRO3) ? 4 : 2; pdev = platform_device_register_simple("amiga-zorro", -1, zorro_resources, n); - return PTR_RET(pdev); + return PTR_ERR_OR_ZERO(pdev); } subsys_initcall(amiga_init_bus); diff --git a/arch/m68k/emu/natfeat.c b/arch/m68k/emu/natfeat.c index fa277aecfb78..121a6660ad4e 100644 --- a/arch/m68k/emu/natfeat.c +++ b/arch/m68k/emu/natfeat.c @@ -18,11 +18,11 @@ #include <asm/machdep.h> #include <asm/natfeat.h> -extern long nf_get_id2(const char *feature_name); +extern long nf_get_id_phys(unsigned long feature_name); asm("\n" -" .global nf_get_id2,nf_call\n" -"nf_get_id2:\n" +" .global nf_get_id_phys,nf_call\n" +"nf_get_id_phys:\n" " .short 0x7300\n" " rts\n" "nf_call:\n" @@ -31,7 +31,7 @@ asm("\n" "1: moveq.l #0,%d0\n" " rts\n" " .section __ex_table,\"a\"\n" -" .long nf_get_id2,1b\n" +" .long nf_get_id_phys,1b\n" " .long nf_call,1b\n" " .previous"); EXPORT_SYMBOL_GPL(nf_call); @@ -46,7 +46,7 @@ long nf_get_id(const char *feature_name) if (n >= sizeof(name_copy)) return 0; - return nf_get_id2(name_copy); + return nf_get_id_phys(virt_to_phys(name_copy)); } EXPORT_SYMBOL_GPL(nf_get_id); @@ -58,7 +58,7 @@ void nfprint(const char *fmt, ...) va_start(ap, fmt); n = vsnprintf(buf, 256, fmt, ap); - nf_call(nf_get_id("NF_STDERR"), buf); + nf_call(nf_get_id("NF_STDERR"), virt_to_phys(buf)); va_end(ap); } @@ -83,7 +83,7 @@ void nf_init(void) id = nf_get_id("NF_NAME"); if (!id) return; - nf_call(id, buf, 256); + nf_call(id, virt_to_phys(buf), 256); buf[255] = 0; pr_info("NatFeats found (%s, %lu.%lu)\n", buf, version >> 16, diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c index e3011338ab40..0721858fbd1e 100644 --- a/arch/m68k/emu/nfblock.c +++ b/arch/m68k/emu/nfblock.c @@ -41,8 +41,8 @@ static inline s32 nfhd_read_write(u32 major, u32 minor, u32 rwflag, u32 recno, static inline s32 nfhd_get_capacity(u32 major, u32 minor, u32 *blocks, u32 *blocksize) { - return nf_call(nfhd_id + NFHD_GET_CAPACITY, major, minor, blocks, - blocksize); + return nf_call(nfhd_id + NFHD_GET_CAPACITY, major, minor, + virt_to_phys(blocks), virt_to_phys(blocksize)); } static LIST_HEAD(nfhd_list); diff --git a/arch/m68k/emu/nfcon.c b/arch/m68k/emu/nfcon.c index 6685bf45c2c3..57e8c8fb5eba 100644 --- a/arch/m68k/emu/nfcon.c +++ b/arch/m68k/emu/nfcon.c @@ -15,6 +15,7 @@ #include <linux/slab.h> #include <linux/err.h> #include <linux/uaccess.h> +#include <linux/io.h> #include <asm/natfeat.h> @@ -25,17 +26,18 @@ static struct tty_driver *nfcon_tty_driver; static void nfputs(const char *str, unsigned int count) { char buf[68]; + unsigned long phys = virt_to_phys(buf); buf[64] = 0; while (count > 64) { memcpy(buf, str, 64); - nf_call(stderr_id, buf); + nf_call(stderr_id, phys); str += 64; count -= 64; } memcpy(buf, str, count); buf[count] = 0; - nf_call(stderr_id, buf); + nf_call(stderr_id, phys); } static void nfcon_write(struct console *con, const char *str, @@ -79,7 +81,7 @@ static int nfcon_tty_put_char(struct tty_struct *tty, unsigned char ch) { char temp[2] = { ch, 0 }; - nf_call(stderr_id, temp); + nf_call(stderr_id, virt_to_phys(temp)); return 1; } diff --git a/arch/m68k/emu/nfeth.c b/arch/m68k/emu/nfeth.c index 695cd737a42e..a0985fd088d1 100644 --- a/arch/m68k/emu/nfeth.c +++ b/arch/m68k/emu/nfeth.c @@ -195,7 +195,8 @@ static struct net_device * __init nfeth_probe(int unit) char mac[ETH_ALEN], host_ip[32], local_ip[32]; int err; - if (!nf_call(nfEtherID + XIF_GET_MAC, unit, mac, ETH_ALEN)) + if (!nf_call(nfEtherID + XIF_GET_MAC, unit, virt_to_phys(mac), + ETH_ALEN)) return NULL; dev = alloc_etherdev(sizeof(struct nfeth_private)); @@ -217,9 +218,9 @@ static struct net_device * __init nfeth_probe(int unit) } nf_call(nfEtherID + XIF_GET_IPHOST, unit, - host_ip, sizeof(host_ip)); + virt_to_phys(host_ip), sizeof(host_ip)); nf_call(nfEtherID + XIF_GET_IPATARI, unit, - local_ip, sizeof(local_ip)); + virt_to_phys(local_ip), sizeof(local_ip)); netdev_info(dev, KBUILD_MODNAME " addr:%s (%s) HWaddr:%pM\n", host_ip, local_ip, mac); diff --git a/arch/m68k/include/asm/irqflags.h b/arch/m68k/include/asm/irqflags.h index 7ef4115b8c4a..a823cd73dc09 100644 --- a/arch/m68k/include/asm/irqflags.h +++ b/arch/m68k/include/asm/irqflags.h @@ -3,7 +3,7 @@ #include <linux/types.h> #ifdef CONFIG_MMU -#include <linux/hardirq.h> +#include <linux/preempt_mask.h> #endif #include <linux/preempt.h> #include <asm/thread_info.h> @@ -67,6 +67,10 @@ static inline void arch_local_irq_restore(unsigned long flags) static inline bool arch_irqs_disabled_flags(unsigned long flags) { + if (MACH_IS_ATARI) { + /* Ignore HSYNC = ipl 2 on Atari */ + return (flags & ~(ALLOWINT | 0x200)) != 0; + } return (flags & ~ALLOWINT) != 0; } diff --git a/arch/m68k/kernel/time.c b/arch/m68k/kernel/time.c index bea6bcf8f9b8..7eb9792009f8 100644 --- a/arch/m68k/kernel/time.c +++ b/arch/m68k/kernel/time.c @@ -90,7 +90,7 @@ static int __init rtc_init(void) return -ENODEV; pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0); - return PTR_RET(pdev); + return PTR_ERR_OR_ZERO(pdev); } module_init(rtc_init); diff --git a/arch/m68k/platform/coldfire/pci.c b/arch/m68k/platform/coldfire/pci.c index b33f97a13e6d..df9679238b6d 100644 --- a/arch/m68k/platform/coldfire/pci.c +++ b/arch/m68k/platform/coldfire/pci.c @@ -319,7 +319,6 @@ static int __init mcf_pci_init(void) pci_fixup_irqs(pci_common_swizzle, mcf_pci_map_irq); pci_bus_size_bridges(rootbus); pci_bus_assign_resources(rootbus); - pci_enable_bridges(rootbus); return 0; } diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c index 658542b914fc..078bb744b5fe 100644 --- a/arch/m68k/q40/config.c +++ b/arch/m68k/q40/config.c @@ -338,6 +338,6 @@ static __init int q40_add_kbd_device(void) return -ENODEV; pdev = platform_device_register_simple("q40kbd", -1, NULL, 0); - return PTR_RET(pdev); + return PTR_ERR_OR_ZERO(pdev); } arch_initcall(q40_add_kbd_device); diff --git a/arch/microblaze/include/asm/prom.h b/arch/microblaze/include/asm/prom.h index 20c5e8e5121b..9977816c5ad3 100644 --- a/arch/microblaze/include/asm/prom.h +++ b/arch/microblaze/include/asm/prom.h @@ -50,9 +50,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop, extern void kdump_move_device_tree(void); -/* CPU OF node matching */ -struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); - #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index e12764c2a9d0..dccd7cec442d 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -2305,9 +2305,9 @@ config KEXEC It is an ongoing process to be certain the hardware in a machine is properly shutdown, so do not be surprised if this code does not - initially work for you. It may help to enable device hotplugging - support. As of this writing the exact hardware interface is - strongly in flux, so no good recommendation can be made. + initially work for you. As of this writing the exact hardware + interface is strongly in flux, so no good recommendation can be + made. config CRASH_DUMP bool "Kernel crash dumps" diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 1765bab000a0..faf84c5f2629 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -1335,8 +1335,9 @@ static ssize_t store_kill(struct device *dev, struct device_attribute *attr, return len; } +static DEVICE_ATTR(kill, S_IWUSR, NULL, store_kill); -static ssize_t show_ntcs(struct device *cd, struct device_attribute *attr, +static ssize_t ntcs_show(struct device *cd, struct device_attribute *attr, char *buf) { struct vpe *vpe = get_vpe(tclimit); @@ -1344,7 +1345,7 @@ static ssize_t show_ntcs(struct device *cd, struct device_attribute *attr, return sprintf(buf, "%d\n", vpe->ntcs); } -static ssize_t store_ntcs(struct device *dev, struct device_attribute *attr, +static ssize_t ntcs_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct vpe *vpe = get_vpe(tclimit); @@ -1365,12 +1366,14 @@ static ssize_t store_ntcs(struct device *dev, struct device_attribute *attr, out_einval: return -EINVAL; } +static DEVICE_ATTR_RW(ntcs); -static struct device_attribute vpe_class_attributes[] = { - __ATTR(kill, S_IWUSR, NULL, store_kill), - __ATTR(ntcs, S_IRUGO | S_IWUSR, show_ntcs, store_ntcs), - {} +static struct attribute vpe_attrs[] = { + &dev_attr_kill.attr, + &dev_attr_ntcs.attr, + NULL, }; +ATTRIBUTE_GROUPS(vpe); static void vpe_device_release(struct device *cd) { @@ -1381,7 +1384,7 @@ struct class vpe_class = { .name = "vpe", .owner = THIS_MODULE, .dev_release = vpe_device_release, - .dev_attrs = vpe_class_attributes, + .dev_groups = vpe_groups, }; struct device vpe_device; diff --git a/arch/mips/kvm/kvm_locore.S b/arch/mips/kvm/kvm_locore.S index dca2aa665993..bbace092ad0a 100644 --- a/arch/mips/kvm/kvm_locore.S +++ b/arch/mips/kvm/kvm_locore.S @@ -1,13 +1,13 @@ /* -* This file is subject to the terms and conditions of the GNU General Public -* License. See the file "COPYING" in the main directory of this archive -* for more details. -* -* Main entry point for the guest, exception handling. -* -* Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved. -* Authors: Sanjay Lal <sanjayl@kymasys.com> -*/ + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * Main entry point for the guest, exception handling. + * + * Copyright (C) 2012 MIPS Technologies, Inc. All rights reserved. + * Authors: Sanjay Lal <sanjayl@kymasys.com> + */ #include <asm/asm.h> #include <asm/asmmacro.h> @@ -55,195 +55,193 @@ * a0: run * a1: vcpu */ + .set noreorder + .set noat FEXPORT(__kvm_mips_vcpu_run) - .set push - .set noreorder - .set noat - - /* k0/k1 not being used in host kernel context */ - addiu k1,sp, -PT_SIZE - LONG_S $0, PT_R0(k1) - LONG_S $1, PT_R1(k1) - LONG_S $2, PT_R2(k1) - LONG_S $3, PT_R3(k1) - - LONG_S $4, PT_R4(k1) - LONG_S $5, PT_R5(k1) - LONG_S $6, PT_R6(k1) - LONG_S $7, PT_R7(k1) - - LONG_S $8, PT_R8(k1) - LONG_S $9, PT_R9(k1) - LONG_S $10, PT_R10(k1) - LONG_S $11, PT_R11(k1) - LONG_S $12, PT_R12(k1) - LONG_S $13, PT_R13(k1) - LONG_S $14, PT_R14(k1) - LONG_S $15, PT_R15(k1) - LONG_S $16, PT_R16(k1) - LONG_S $17, PT_R17(k1) - - LONG_S $18, PT_R18(k1) - LONG_S $19, PT_R19(k1) - LONG_S $20, PT_R20(k1) - LONG_S $21, PT_R21(k1) - LONG_S $22, PT_R22(k1) - LONG_S $23, PT_R23(k1) - LONG_S $24, PT_R24(k1) - LONG_S $25, PT_R25(k1) + /* k0/k1 not being used in host kernel context */ + INT_ADDIU k1, sp, -PT_SIZE + LONG_S $0, PT_R0(k1) + LONG_S $1, PT_R1(k1) + LONG_S $2, PT_R2(k1) + LONG_S $3, PT_R3(k1) + + LONG_S $4, PT_R4(k1) + LONG_S $5, PT_R5(k1) + LONG_S $6, PT_R6(k1) + LONG_S $7, PT_R7(k1) + + LONG_S $8, PT_R8(k1) + LONG_S $9, PT_R9(k1) + LONG_S $10, PT_R10(k1) + LONG_S $11, PT_R11(k1) + LONG_S $12, PT_R12(k1) + LONG_S $13, PT_R13(k1) + LONG_S $14, PT_R14(k1) + LONG_S $15, PT_R15(k1) + LONG_S $16, PT_R16(k1) + LONG_S $17, PT_R17(k1) + + LONG_S $18, PT_R18(k1) + LONG_S $19, PT_R19(k1) + LONG_S $20, PT_R20(k1) + LONG_S $21, PT_R21(k1) + LONG_S $22, PT_R22(k1) + LONG_S $23, PT_R23(k1) + LONG_S $24, PT_R24(k1) + LONG_S $25, PT_R25(k1) /* XXXKYMA k0/k1 not saved, not being used if we got here through an ioctl() */ - LONG_S $28, PT_R28(k1) - LONG_S $29, PT_R29(k1) - LONG_S $30, PT_R30(k1) - LONG_S $31, PT_R31(k1) + LONG_S $28, PT_R28(k1) + LONG_S $29, PT_R29(k1) + LONG_S $30, PT_R30(k1) + LONG_S $31, PT_R31(k1) - /* Save hi/lo */ - mflo v0 - LONG_S v0, PT_LO(k1) - mfhi v1 - LONG_S v1, PT_HI(k1) + /* Save hi/lo */ + mflo v0 + LONG_S v0, PT_LO(k1) + mfhi v1 + LONG_S v1, PT_HI(k1) /* Save host status */ - mfc0 v0, CP0_STATUS - LONG_S v0, PT_STATUS(k1) + mfc0 v0, CP0_STATUS + LONG_S v0, PT_STATUS(k1) /* Save host ASID, shove it into the BVADDR location */ - mfc0 v1,CP0_ENTRYHI - andi v1, 0xff - LONG_S v1, PT_HOST_ASID(k1) + mfc0 v1, CP0_ENTRYHI + andi v1, 0xff + LONG_S v1, PT_HOST_ASID(k1) - /* Save DDATA_LO, will be used to store pointer to vcpu */ - mfc0 v1, CP0_DDATA_LO - LONG_S v1, PT_HOST_USERLOCAL(k1) + /* Save DDATA_LO, will be used to store pointer to vcpu */ + mfc0 v1, CP0_DDATA_LO + LONG_S v1, PT_HOST_USERLOCAL(k1) - /* DDATA_LO has pointer to vcpu */ - mtc0 a1,CP0_DDATA_LO + /* DDATA_LO has pointer to vcpu */ + mtc0 a1, CP0_DDATA_LO - /* Offset into vcpu->arch */ - addiu k1, a1, VCPU_HOST_ARCH + /* Offset into vcpu->arch */ + INT_ADDIU k1, a1, VCPU_HOST_ARCH - /* Save the host stack to VCPU, used for exception processing when we exit from the Guest */ - LONG_S sp, VCPU_HOST_STACK(k1) + /* + * Save the host stack to VCPU, used for exception processing + * when we exit from the Guest + */ + LONG_S sp, VCPU_HOST_STACK(k1) - /* Save the kernel gp as well */ - LONG_S gp, VCPU_HOST_GP(k1) + /* Save the kernel gp as well */ + LONG_S gp, VCPU_HOST_GP(k1) /* Setup status register for running the guest in UM, interrupts are disabled */ - li k0,(ST0_EXL | KSU_USER| ST0_BEV) - mtc0 k0,CP0_STATUS - ehb - - /* load up the new EBASE */ - LONG_L k0, VCPU_GUEST_EBASE(k1) - mtc0 k0,CP0_EBASE - - /* Now that the new EBASE has been loaded, unset BEV, set interrupt mask as it was - * but make sure that timer interrupts are enabled - */ - li k0,(ST0_EXL | KSU_USER | ST0_IE) - andi v0, v0, ST0_IM - or k0, k0, v0 - mtc0 k0,CP0_STATUS - ehb + li k0, (ST0_EXL | KSU_USER | ST0_BEV) + mtc0 k0, CP0_STATUS + ehb + + /* load up the new EBASE */ + LONG_L k0, VCPU_GUEST_EBASE(k1) + mtc0 k0, CP0_EBASE + + /* + * Now that the new EBASE has been loaded, unset BEV, set + * interrupt mask as it was but make sure that timer interrupts + * are enabled + */ + li k0, (ST0_EXL | KSU_USER | ST0_IE) + andi v0, v0, ST0_IM + or k0, k0, v0 + mtc0 k0, CP0_STATUS + ehb /* Set Guest EPC */ - LONG_L t0, VCPU_PC(k1) - mtc0 t0, CP0_EPC + LONG_L t0, VCPU_PC(k1) + mtc0 t0, CP0_EPC FEXPORT(__kvm_mips_load_asid) - /* Set the ASID for the Guest Kernel */ - sll t0, t0, 1 /* with kseg0 @ 0x40000000, kernel */ - /* addresses shift to 0x80000000 */ - bltz t0, 1f /* If kernel */ - addiu t1, k1, VCPU_GUEST_KERNEL_ASID /* (BD) */ - addiu t1, k1, VCPU_GUEST_USER_ASID /* else user */ + /* Set the ASID for the Guest Kernel */ + INT_SLL t0, t0, 1 /* with kseg0 @ 0x40000000, kernel */ + /* addresses shift to 0x80000000 */ + bltz t0, 1f /* If kernel */ + INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID /* (BD) */ + INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID /* else user */ 1: - /* t1: contains the base of the ASID array, need to get the cpu id */ - LONG_L t2, TI_CPU($28) /* smp_processor_id */ - sll t2, t2, 2 /* x4 */ - addu t3, t1, t2 - LONG_L k0, (t3) - andi k0, k0, 0xff - mtc0 k0,CP0_ENTRYHI - ehb - - /* Disable RDHWR access */ - mtc0 zero, CP0_HWRENA - - /* Now load up the Guest Context from VCPU */ - LONG_L $1, VCPU_R1(k1) - LONG_L $2, VCPU_R2(k1) - LONG_L $3, VCPU_R3(k1) - - LONG_L $4, VCPU_R4(k1) - LONG_L $5, VCPU_R5(k1) - LONG_L $6, VCPU_R6(k1) - LONG_L $7, VCPU_R7(k1) - - LONG_L $8, VCPU_R8(k1) - LONG_L $9, VCPU_R9(k1) - LONG_L $10, VCPU_R10(k1) - LONG_L $11, VCPU_R11(k1) - LONG_L $12, VCPU_R12(k1) - LONG_L $13, VCPU_R13(k1) - LONG_L $14, VCPU_R14(k1) - LONG_L $15, VCPU_R15(k1) - LONG_L $16, VCPU_R16(k1) - LONG_L $17, VCPU_R17(k1) - LONG_L $18, VCPU_R18(k1) - LONG_L $19, VCPU_R19(k1) - LONG_L $20, VCPU_R20(k1) - LONG_L $21, VCPU_R21(k1) - LONG_L $22, VCPU_R22(k1) - LONG_L $23, VCPU_R23(k1) - LONG_L $24, VCPU_R24(k1) - LONG_L $25, VCPU_R25(k1) - - /* k0/k1 loaded up later */ - - LONG_L $28, VCPU_R28(k1) - LONG_L $29, VCPU_R29(k1) - LONG_L $30, VCPU_R30(k1) - LONG_L $31, VCPU_R31(k1) - - /* Restore hi/lo */ - LONG_L k0, VCPU_LO(k1) - mtlo k0 - - LONG_L k0, VCPU_HI(k1) - mthi k0 + /* t1: contains the base of the ASID array, need to get the cpu id */ + LONG_L t2, TI_CPU($28) /* smp_processor_id */ + INT_SLL t2, t2, 2 /* x4 */ + REG_ADDU t3, t1, t2 + LONG_L k0, (t3) + andi k0, k0, 0xff + mtc0 k0, CP0_ENTRYHI + ehb + + /* Disable RDHWR access */ + mtc0 zero, CP0_HWRENA + + /* Now load up the Guest Context from VCPU */ + LONG_L $1, VCPU_R1(k1) + LONG_L $2, VCPU_R2(k1) + LONG_L $3, VCPU_R3(k1) + + LONG_L $4, VCPU_R4(k1) + LONG_L $5, VCPU_R5(k1) + LONG_L $6, VCPU_R6(k1) + LONG_L $7, VCPU_R7(k1) + + LONG_L $8, VCPU_R8(k1) + LONG_L $9, VCPU_R9(k1) + LONG_L $10, VCPU_R10(k1) + LONG_L $11, VCPU_R11(k1) + LONG_L $12, VCPU_R12(k1) + LONG_L $13, VCPU_R13(k1) + LONG_L $14, VCPU_R14(k1) + LONG_L $15, VCPU_R15(k1) + LONG_L $16, VCPU_R16(k1) + LONG_L $17, VCPU_R17(k1) + LONG_L $18, VCPU_R18(k1) + LONG_L $19, VCPU_R19(k1) + LONG_L $20, VCPU_R20(k1) + LONG_L $21, VCPU_R21(k1) + LONG_L $22, VCPU_R22(k1) + LONG_L $23, VCPU_R23(k1) + LONG_L $24, VCPU_R24(k1) + LONG_L $25, VCPU_R25(k1) + + /* k0/k1 loaded up later */ + + LONG_L $28, VCPU_R28(k1) + LONG_L $29, VCPU_R29(k1) + LONG_L $30, VCPU_R30(k1) + LONG_L $31, VCPU_R31(k1) + + /* Restore hi/lo */ + LONG_L k0, VCPU_LO(k1) + mtlo k0 + + LONG_L k0, VCPU_HI(k1) + mthi k0 FEXPORT(__kvm_mips_load_k0k1) /* Restore the guest's k0/k1 registers */ - LONG_L k0, VCPU_R26(k1) - LONG_L k1, VCPU_R27(k1) + LONG_L k0, VCPU_R26(k1) + LONG_L k1, VCPU_R27(k1) - /* Jump to guest */ + /* Jump to guest */ eret - .set pop VECTOR(MIPSX(exception), unknown) /* * Find out what mode we came from and jump to the proper handler. */ - .set push - .set noat - .set noreorder - mtc0 k0, CP0_ERROREPC #01: Save guest k0 - ehb #02: - - mfc0 k0, CP0_EBASE #02: Get EBASE - srl k0, k0, 10 #03: Get rid of CPUNum - sll k0, k0, 10 #04 - LONG_S k1, 0x3000(k0) #05: Save k1 @ offset 0x3000 - addiu k0, k0, 0x2000 #06: Exception handler is installed @ offset 0x2000 - j k0 #07: jump to the function - nop #08: branch delay slot - .set push + mtc0 k0, CP0_ERROREPC #01: Save guest k0 + ehb #02: + + mfc0 k0, CP0_EBASE #02: Get EBASE + INT_SRL k0, k0, 10 #03: Get rid of CPUNum + INT_SLL k0, k0, 10 #04 + LONG_S k1, 0x3000(k0) #05: Save k1 @ offset 0x3000 + INT_ADDIU k0, k0, 0x2000 #06: Exception handler is installed @ offset 0x2000 + j k0 #07: jump to the function + nop #08: branch delay slot VECTOR_END(MIPSX(exceptionEnd)) .end MIPSX(exception) @@ -253,329 +251,327 @@ VECTOR_END(MIPSX(exceptionEnd)) * */ NESTED (MIPSX(GuestException), CALLFRAME_SIZ, ra) - .set push - .set noat - .set noreorder - - /* Get the VCPU pointer from DDTATA_LO */ - mfc0 k1, CP0_DDATA_LO - addiu k1, k1, VCPU_HOST_ARCH - - /* Start saving Guest context to VCPU */ - LONG_S $0, VCPU_R0(k1) - LONG_S $1, VCPU_R1(k1) - LONG_S $2, VCPU_R2(k1) - LONG_S $3, VCPU_R3(k1) - LONG_S $4, VCPU_R4(k1) - LONG_S $5, VCPU_R5(k1) - LONG_S $6, VCPU_R6(k1) - LONG_S $7, VCPU_R7(k1) - LONG_S $8, VCPU_R8(k1) - LONG_S $9, VCPU_R9(k1) - LONG_S $10, VCPU_R10(k1) - LONG_S $11, VCPU_R11(k1) - LONG_S $12, VCPU_R12(k1) - LONG_S $13, VCPU_R13(k1) - LONG_S $14, VCPU_R14(k1) - LONG_S $15, VCPU_R15(k1) - LONG_S $16, VCPU_R16(k1) - LONG_S $17,VCPU_R17(k1) - LONG_S $18, VCPU_R18(k1) - LONG_S $19, VCPU_R19(k1) - LONG_S $20, VCPU_R20(k1) - LONG_S $21, VCPU_R21(k1) - LONG_S $22, VCPU_R22(k1) - LONG_S $23, VCPU_R23(k1) - LONG_S $24, VCPU_R24(k1) - LONG_S $25, VCPU_R25(k1) - - /* Guest k0/k1 saved later */ - - LONG_S $28, VCPU_R28(k1) - LONG_S $29, VCPU_R29(k1) - LONG_S $30, VCPU_R30(k1) - LONG_S $31, VCPU_R31(k1) - - /* We need to save hi/lo and restore them on - * the way out - */ - mfhi t0 - LONG_S t0, VCPU_HI(k1) - - mflo t0 - LONG_S t0, VCPU_LO(k1) - - /* Finally save guest k0/k1 to VCPU */ - mfc0 t0, CP0_ERROREPC - LONG_S t0, VCPU_R26(k1) - - /* Get GUEST k1 and save it in VCPU */ - la t1, ~0x2ff - mfc0 t0, CP0_EBASE - and t0, t0, t1 - LONG_L t0, 0x3000(t0) - LONG_S t0, VCPU_R27(k1) - - /* Now that context has been saved, we can use other registers */ - - /* Restore vcpu */ - mfc0 a1, CP0_DDATA_LO - move s1, a1 - - /* Restore run (vcpu->run) */ - LONG_L a0, VCPU_RUN(a1) - /* Save pointer to run in s0, will be saved by the compiler */ - move s0, a0 - - - /* Save Host level EPC, BadVaddr and Cause to VCPU, useful to process the exception */ - mfc0 k0,CP0_EPC - LONG_S k0, VCPU_PC(k1) - - mfc0 k0, CP0_BADVADDR - LONG_S k0, VCPU_HOST_CP0_BADVADDR(k1) - - mfc0 k0, CP0_CAUSE - LONG_S k0, VCPU_HOST_CP0_CAUSE(k1) - - mfc0 k0, CP0_ENTRYHI - LONG_S k0, VCPU_HOST_ENTRYHI(k1) - - /* Now restore the host state just enough to run the handlers */ - - /* Swtich EBASE to the one used by Linux */ - /* load up the host EBASE */ - mfc0 v0, CP0_STATUS - - .set at - or k0, v0, ST0_BEV - .set noat - - mtc0 k0, CP0_STATUS - ehb - - LONG_L k0, VCPU_HOST_EBASE(k1) - mtc0 k0,CP0_EBASE - - - /* Now that the new EBASE has been loaded, unset BEV and KSU_USER */ - .set at - and v0, v0, ~(ST0_EXL | KSU_USER | ST0_IE) - or v0, v0, ST0_CU0 - .set noat - mtc0 v0, CP0_STATUS - ehb - - /* Load up host GP */ - LONG_L gp, VCPU_HOST_GP(k1) - - /* Need a stack before we can jump to "C" */ - LONG_L sp, VCPU_HOST_STACK(k1) - - /* Saved host state */ - addiu sp,sp, -PT_SIZE + /* Get the VCPU pointer from DDTATA_LO */ + mfc0 k1, CP0_DDATA_LO + INT_ADDIU k1, k1, VCPU_HOST_ARCH + + /* Start saving Guest context to VCPU */ + LONG_S $0, VCPU_R0(k1) + LONG_S $1, VCPU_R1(k1) + LONG_S $2, VCPU_R2(k1) + LONG_S $3, VCPU_R3(k1) + LONG_S $4, VCPU_R4(k1) + LONG_S $5, VCPU_R5(k1) + LONG_S $6, VCPU_R6(k1) + LONG_S $7, VCPU_R7(k1) + LONG_S $8, VCPU_R8(k1) + LONG_S $9, VCPU_R9(k1) + LONG_S $10, VCPU_R10(k1) + LONG_S $11, VCPU_R11(k1) + LONG_S $12, VCPU_R12(k1) + LONG_S $13, VCPU_R13(k1) + LONG_S $14, VCPU_R14(k1) + LONG_S $15, VCPU_R15(k1) + LONG_S $16, VCPU_R16(k1) + LONG_S $17, VCPU_R17(k1) + LONG_S $18, VCPU_R18(k1) + LONG_S $19, VCPU_R19(k1) + LONG_S $20, VCPU_R20(k1) + LONG_S $21, VCPU_R21(k1) + LONG_S $22, VCPU_R22(k1) + LONG_S $23, VCPU_R23(k1) + LONG_S $24, VCPU_R24(k1) + LONG_S $25, VCPU_R25(k1) + + /* Guest k0/k1 saved later */ + + LONG_S $28, VCPU_R28(k1) + LONG_S $29, VCPU_R29(k1) + LONG_S $30, VCPU_R30(k1) + LONG_S $31, VCPU_R31(k1) + + /* We need to save hi/lo and restore them on + * the way out + */ + mfhi t0 + LONG_S t0, VCPU_HI(k1) + + mflo t0 + LONG_S t0, VCPU_LO(k1) + + /* Finally save guest k0/k1 to VCPU */ + mfc0 t0, CP0_ERROREPC + LONG_S t0, VCPU_R26(k1) + + /* Get GUEST k1 and save it in VCPU */ + PTR_LI t1, ~0x2ff + mfc0 t0, CP0_EBASE + and t0, t0, t1 + LONG_L t0, 0x3000(t0) + LONG_S t0, VCPU_R27(k1) + + /* Now that context has been saved, we can use other registers */ + + /* Restore vcpu */ + mfc0 a1, CP0_DDATA_LO + move s1, a1 + + /* Restore run (vcpu->run) */ + LONG_L a0, VCPU_RUN(a1) + /* Save pointer to run in s0, will be saved by the compiler */ + move s0, a0 + + /* Save Host level EPC, BadVaddr and Cause to VCPU, useful to + * process the exception */ + mfc0 k0,CP0_EPC + LONG_S k0, VCPU_PC(k1) + + mfc0 k0, CP0_BADVADDR + LONG_S k0, VCPU_HOST_CP0_BADVADDR(k1) + + mfc0 k0, CP0_CAUSE + LONG_S k0, VCPU_HOST_CP0_CAUSE(k1) + + mfc0 k0, CP0_ENTRYHI + LONG_S k0, VCPU_HOST_ENTRYHI(k1) + + /* Now restore the host state just enough to run the handlers */ + + /* Swtich EBASE to the one used by Linux */ + /* load up the host EBASE */ + mfc0 v0, CP0_STATUS + + .set at + or k0, v0, ST0_BEV + .set noat + + mtc0 k0, CP0_STATUS + ehb + + LONG_L k0, VCPU_HOST_EBASE(k1) + mtc0 k0,CP0_EBASE + - /* XXXKYMA do we need to load the host ASID, maybe not because the - * kernel entries are marked GLOBAL, need to verify - */ + /* Now that the new EBASE has been loaded, unset BEV and KSU_USER */ + .set at + and v0, v0, ~(ST0_EXL | KSU_USER | ST0_IE) + or v0, v0, ST0_CU0 + .set noat + mtc0 v0, CP0_STATUS + ehb + + /* Load up host GP */ + LONG_L gp, VCPU_HOST_GP(k1) + + /* Need a stack before we can jump to "C" */ + LONG_L sp, VCPU_HOST_STACK(k1) + + /* Saved host state */ + INT_ADDIU sp, sp, -PT_SIZE - /* Restore host DDATA_LO */ - LONG_L k0, PT_HOST_USERLOCAL(sp) - mtc0 k0, CP0_DDATA_LO + /* XXXKYMA do we need to load the host ASID, maybe not because the + * kernel entries are marked GLOBAL, need to verify + */ - /* Restore RDHWR access */ - la k0, 0x2000000F - mtc0 k0, CP0_HWRENA + /* Restore host DDATA_LO */ + LONG_L k0, PT_HOST_USERLOCAL(sp) + mtc0 k0, CP0_DDATA_LO - /* Jump to handler */ + /* Restore RDHWR access */ + PTR_LI k0, 0x2000000F + mtc0 k0, CP0_HWRENA + + /* Jump to handler */ FEXPORT(__kvm_mips_jump_to_handler) - /* XXXKYMA: not sure if this is safe, how large is the stack?? */ - /* Now jump to the kvm_mips_handle_exit() to see if we can deal with this in the kernel */ - la t9,kvm_mips_handle_exit - jalr.hb t9 - addiu sp,sp, -CALLFRAME_SIZ /* BD Slot */ - - /* Return from handler Make sure interrupts are disabled */ - di - ehb - - /* XXXKYMA: k0/k1 could have been blown away if we processed an exception - * while we were handling the exception from the guest, reload k1 - */ - move k1, s1 - addiu k1, k1, VCPU_HOST_ARCH - - /* Check return value, should tell us if we are returning to the host (handle I/O etc) - * or resuming the guest - */ - andi t0, v0, RESUME_HOST - bnez t0, __kvm_mips_return_to_host - nop + /* XXXKYMA: not sure if this is safe, how large is the stack?? + * Now jump to the kvm_mips_handle_exit() to see if we can deal + * with this in the kernel */ + PTR_LA t9, kvm_mips_handle_exit + jalr.hb t9 + INT_ADDIU sp, sp, -CALLFRAME_SIZ /* BD Slot */ + + /* Return from handler Make sure interrupts are disabled */ + di + ehb + + /* XXXKYMA: k0/k1 could have been blown away if we processed + * an exception while we were handling the exception from the + * guest, reload k1 + */ + + move k1, s1 + INT_ADDIU k1, k1, VCPU_HOST_ARCH + + /* Check return value, should tell us if we are returning to the + * host (handle I/O etc)or resuming the guest + */ + andi t0, v0, RESUME_HOST + bnez t0, __kvm_mips_return_to_host + nop __kvm_mips_return_to_guest: - /* Put the saved pointer to vcpu (s1) back into the DDATA_LO Register */ - mtc0 s1, CP0_DDATA_LO - - /* Load up the Guest EBASE to minimize the window where BEV is set */ - LONG_L t0, VCPU_GUEST_EBASE(k1) - - /* Switch EBASE back to the one used by KVM */ - mfc0 v1, CP0_STATUS - .set at - or k0, v1, ST0_BEV - .set noat - mtc0 k0, CP0_STATUS - ehb - mtc0 t0,CP0_EBASE - - /* Setup status register for running guest in UM */ - .set at - or v1, v1, (ST0_EXL | KSU_USER | ST0_IE) - and v1, v1, ~ST0_CU0 - .set noat - mtc0 v1, CP0_STATUS - ehb + /* Put the saved pointer to vcpu (s1) back into the DDATA_LO Register */ + mtc0 s1, CP0_DDATA_LO + /* Load up the Guest EBASE to minimize the window where BEV is set */ + LONG_L t0, VCPU_GUEST_EBASE(k1) + + /* Switch EBASE back to the one used by KVM */ + mfc0 v1, CP0_STATUS + .set at + or k0, v1, ST0_BEV + .set noat + mtc0 k0, CP0_STATUS + ehb + mtc0 t0, CP0_EBASE + + /* Setup status register for running guest in UM */ + .set at + or v1, v1, (ST0_EXL | KSU_USER | ST0_IE) + and v1, v1, ~ST0_CU0 + .set noat + mtc0 v1, CP0_STATUS + ehb /* Set Guest EPC */ - LONG_L t0, VCPU_PC(k1) - mtc0 t0, CP0_EPC - - /* Set the ASID for the Guest Kernel */ - sll t0, t0, 1 /* with kseg0 @ 0x40000000, kernel */ - /* addresses shift to 0x80000000 */ - bltz t0, 1f /* If kernel */ - addiu t1, k1, VCPU_GUEST_KERNEL_ASID /* (BD) */ - addiu t1, k1, VCPU_GUEST_USER_ASID /* else user */ + LONG_L t0, VCPU_PC(k1) + mtc0 t0, CP0_EPC + + /* Set the ASID for the Guest Kernel */ + INT_SLL t0, t0, 1 /* with kseg0 @ 0x40000000, kernel */ + /* addresses shift to 0x80000000 */ + bltz t0, 1f /* If kernel */ + INT_ADDIU t1, k1, VCPU_GUEST_KERNEL_ASID /* (BD) */ + INT_ADDIU t1, k1, VCPU_GUEST_USER_ASID /* else user */ 1: - /* t1: contains the base of the ASID array, need to get the cpu id */ - LONG_L t2, TI_CPU($28) /* smp_processor_id */ - sll t2, t2, 2 /* x4 */ - addu t3, t1, t2 - LONG_L k0, (t3) - andi k0, k0, 0xff - mtc0 k0,CP0_ENTRYHI - ehb - - /* Disable RDHWR access */ - mtc0 zero, CP0_HWRENA - - /* load the guest context from VCPU and return */ - LONG_L $0, VCPU_R0(k1) - LONG_L $1, VCPU_R1(k1) - LONG_L $2, VCPU_R2(k1) - LONG_L $3, VCPU_R3(k1) - LONG_L $4, VCPU_R4(k1) - LONG_L $5, VCPU_R5(k1) - LONG_L $6, VCPU_R6(k1) - LONG_L $7, VCPU_R7(k1) - LONG_L $8, VCPU_R8(k1) - LONG_L $9, VCPU_R9(k1) - LONG_L $10, VCPU_R10(k1) - LONG_L $11, VCPU_R11(k1) - LONG_L $12, VCPU_R12(k1) - LONG_L $13, VCPU_R13(k1) - LONG_L $14, VCPU_R14(k1) - LONG_L $15, VCPU_R15(k1) - LONG_L $16, VCPU_R16(k1) - LONG_L $17, VCPU_R17(k1) - LONG_L $18, VCPU_R18(k1) - LONG_L $19, VCPU_R19(k1) - LONG_L $20, VCPU_R20(k1) - LONG_L $21, VCPU_R21(k1) - LONG_L $22, VCPU_R22(k1) - LONG_L $23, VCPU_R23(k1) - LONG_L $24, VCPU_R24(k1) - LONG_L $25, VCPU_R25(k1) - - /* $/k1 loaded later */ - LONG_L $28, VCPU_R28(k1) - LONG_L $29, VCPU_R29(k1) - LONG_L $30, VCPU_R30(k1) - LONG_L $31, VCPU_R31(k1) + /* t1: contains the base of the ASID array, need to get the cpu id */ + LONG_L t2, TI_CPU($28) /* smp_processor_id */ + INT_SLL t2, t2, 2 /* x4 */ + REG_ADDU t3, t1, t2 + LONG_L k0, (t3) + andi k0, k0, 0xff + mtc0 k0,CP0_ENTRYHI + ehb + + /* Disable RDHWR access */ + mtc0 zero, CP0_HWRENA + + /* load the guest context from VCPU and return */ + LONG_L $0, VCPU_R0(k1) + LONG_L $1, VCPU_R1(k1) + LONG_L $2, VCPU_R2(k1) + LONG_L $3, VCPU_R3(k1) + LONG_L $4, VCPU_R4(k1) + LONG_L $5, VCPU_R5(k1) + LONG_L $6, VCPU_R6(k1) + LONG_L $7, VCPU_R7(k1) + LONG_L $8, VCPU_R8(k1) + LONG_L $9, VCPU_R9(k1) + LONG_L $10, VCPU_R10(k1) + LONG_L $11, VCPU_R11(k1) + LONG_L $12, VCPU_R12(k1) + LONG_L $13, VCPU_R13(k1) + LONG_L $14, VCPU_R14(k1) + LONG_L $15, VCPU_R15(k1) + LONG_L $16, VCPU_R16(k1) + LONG_L $17, VCPU_R17(k1) + LONG_L $18, VCPU_R18(k1) + LONG_L $19, VCPU_R19(k1) + LONG_L $20, VCPU_R20(k1) + LONG_L $21, VCPU_R21(k1) + LONG_L $22, VCPU_R22(k1) + LONG_L $23, VCPU_R23(k1) + LONG_L $24, VCPU_R24(k1) + LONG_L $25, VCPU_R25(k1) + + /* $/k1 loaded later */ + LONG_L $28, VCPU_R28(k1) + LONG_L $29, VCPU_R29(k1) + LONG_L $30, VCPU_R30(k1) + LONG_L $31, VCPU_R31(k1) FEXPORT(__kvm_mips_skip_guest_restore) - LONG_L k0, VCPU_HI(k1) - mthi k0 + LONG_L k0, VCPU_HI(k1) + mthi k0 - LONG_L k0, VCPU_LO(k1) - mtlo k0 + LONG_L k0, VCPU_LO(k1) + mtlo k0 - LONG_L k0, VCPU_R26(k1) - LONG_L k1, VCPU_R27(k1) + LONG_L k0, VCPU_R26(k1) + LONG_L k1, VCPU_R27(k1) - eret + eret __kvm_mips_return_to_host: - /* EBASE is already pointing to Linux */ - LONG_L k1, VCPU_HOST_STACK(k1) - addiu k1,k1, -PT_SIZE - - /* Restore host DDATA_LO */ - LONG_L k0, PT_HOST_USERLOCAL(k1) - mtc0 k0, CP0_DDATA_LO - - /* Restore host ASID */ - LONG_L k0, PT_HOST_ASID(sp) - andi k0, 0xff - mtc0 k0,CP0_ENTRYHI - ehb - - /* Load context saved on the host stack */ - LONG_L $0, PT_R0(k1) - LONG_L $1, PT_R1(k1) - - /* r2/v0 is the return code, shift it down by 2 (arithmetic) to recover the err code */ - sra k0, v0, 2 - move $2, k0 - - LONG_L $3, PT_R3(k1) - LONG_L $4, PT_R4(k1) - LONG_L $5, PT_R5(k1) - LONG_L $6, PT_R6(k1) - LONG_L $7, PT_R7(k1) - LONG_L $8, PT_R8(k1) - LONG_L $9, PT_R9(k1) - LONG_L $10, PT_R10(k1) - LONG_L $11, PT_R11(k1) - LONG_L $12, PT_R12(k1) - LONG_L $13, PT_R13(k1) - LONG_L $14, PT_R14(k1) - LONG_L $15, PT_R15(k1) - LONG_L $16, PT_R16(k1) - LONG_L $17, PT_R17(k1) - LONG_L $18, PT_R18(k1) - LONG_L $19, PT_R19(k1) - LONG_L $20, PT_R20(k1) - LONG_L $21, PT_R21(k1) - LONG_L $22, PT_R22(k1) - LONG_L $23, PT_R23(k1) - LONG_L $24, PT_R24(k1) - LONG_L $25, PT_R25(k1) - - /* Host k0/k1 were not saved */ - - LONG_L $28, PT_R28(k1) - LONG_L $29, PT_R29(k1) - LONG_L $30, PT_R30(k1) - - LONG_L k0, PT_HI(k1) - mthi k0 - - LONG_L k0, PT_LO(k1) - mtlo k0 - - /* Restore RDHWR access */ - la k0, 0x2000000F - mtc0 k0, CP0_HWRENA - - - /* Restore RA, which is the address we will return to */ - LONG_L ra, PT_R31(k1) - j ra - nop - - .set pop + /* EBASE is already pointing to Linux */ + LONG_L k1, VCPU_HOST_STACK(k1) + INT_ADDIU k1,k1, -PT_SIZE + + /* Restore host DDATA_LO */ + LONG_L k0, PT_HOST_USERLOCAL(k1) + mtc0 k0, CP0_DDATA_LO + + /* Restore host ASID */ + LONG_L k0, PT_HOST_ASID(sp) + andi k0, 0xff + mtc0 k0,CP0_ENTRYHI + ehb + + /* Load context saved on the host stack */ + LONG_L $0, PT_R0(k1) + LONG_L $1, PT_R1(k1) + + /* r2/v0 is the return code, shift it down by 2 (arithmetic) + * to recover the err code */ + INT_SRA k0, v0, 2 + move $2, k0 + + LONG_L $3, PT_R3(k1) + LONG_L $4, PT_R4(k1) + LONG_L $5, PT_R5(k1) + LONG_L $6, PT_R6(k1) + LONG_L $7, PT_R7(k1) + LONG_L $8, PT_R8(k1) + LONG_L $9, PT_R9(k1) + LONG_L $10, PT_R10(k1) + LONG_L $11, PT_R11(k1) + LONG_L $12, PT_R12(k1) + LONG_L $13, PT_R13(k1) + LONG_L $14, PT_R14(k1) + LONG_L $15, PT_R15(k1) + LONG_L $16, PT_R16(k1) + LONG_L $17, PT_R17(k1) + LONG_L $18, PT_R18(k1) + LONG_L $19, PT_R19(k1) + LONG_L $20, PT_R20(k1) + LONG_L $21, PT_R21(k1) + LONG_L $22, PT_R22(k1) + LONG_L $23, PT_R23(k1) + LONG_L $24, PT_R24(k1) + LONG_L $25, PT_R25(k1) + + /* Host k0/k1 were not saved */ + + LONG_L $28, PT_R28(k1) + LONG_L $29, PT_R29(k1) + LONG_L $30, PT_R30(k1) + + LONG_L k0, PT_HI(k1) + mthi k0 + + LONG_L k0, PT_LO(k1) + mtlo k0 + + /* Restore RDHWR access */ + PTR_LI k0, 0x2000000F + mtc0 k0, CP0_HWRENA + + + /* Restore RA, which is the address we will return to */ + LONG_L ra, PT_R31(k1) + j ra + nop + VECTOR_END(MIPSX(GuestExceptionEnd)) .end MIPSX(GuestException) @@ -627,24 +623,23 @@ MIPSX(exceptions): #define HW_SYNCI_Step $1 LEAF(MIPSX(SyncICache)) - .set push + .set push .set mips32r2 - beq a1, zero, 20f - nop - addu a1, a0, a1 - rdhwr v0, HW_SYNCI_Step - beq v0, zero, 20f - nop - + beq a1, zero, 20f + nop + REG_ADDU a1, a0, a1 + rdhwr v0, HW_SYNCI_Step + beq v0, zero, 20f + nop 10: - synci 0(a0) - addu a0, a0, v0 - sltu v1, a0, a1 - bne v1, zero, 10b - nop - sync + synci 0(a0) + REG_ADDU a0, a0, v0 + sltu v1, a0, a1 + bne v1, zero, 10b + nop + sync 20: - jr.hb ra - nop - .set pop + jr.hb ra + nop + .set pop END(MIPSX(SyncICache)) diff --git a/arch/mips/kvm/kvm_mips.c b/arch/mips/kvm/kvm_mips.c index dd203e59e6fd..a7b044536de4 100644 --- a/arch/mips/kvm/kvm_mips.c +++ b/arch/mips/kvm/kvm_mips.c @@ -208,6 +208,10 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) return 0; } +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_userspace_memory_region *mem, diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c index e773659ccf9f..46048d24328c 100644 --- a/arch/mips/math-emu/cp1emu.c +++ b/arch/mips/math-emu/cp1emu.c @@ -803,6 +803,32 @@ static int isBranchInstr(struct pt_regs *regs, struct mm_decoded_insn dec_insn, dec_insn.next_pc_inc; return 1; break; +#ifdef CONFIG_CPU_CAVIUM_OCTEON + case lwc2_op: /* This is bbit0 on Octeon */ + if ((regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt)) == 0) + *contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2); + else + *contpc = regs->cp0_epc + 8; + return 1; + case ldc2_op: /* This is bbit032 on Octeon */ + if ((regs->regs[insn.i_format.rs] & (1ull<<(insn.i_format.rt + 32))) == 0) + *contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2); + else + *contpc = regs->cp0_epc + 8; + return 1; + case swc2_op: /* This is bbit1 on Octeon */ + if (regs->regs[insn.i_format.rs] & (1ull<<insn.i_format.rt)) + *contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2); + else + *contpc = regs->cp0_epc + 8; + return 1; + case sdc2_op: /* This is bbit132 on Octeon */ + if (regs->regs[insn.i_format.rs] & (1ull<<(insn.i_format.rt + 32))) + *contpc = regs->cp0_epc + 4 + (insn.i_format.simmediate << 2); + else + *contpc = regs->cp0_epc + 8; + return 1; +#endif case cop0_op: case cop1_op: case cop2_op: diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c index 594e60d6a43b..33e7aa52d9c4 100644 --- a/arch/mips/pci/pci.c +++ b/arch/mips/pci/pci.c @@ -113,7 +113,6 @@ static void pcibios_scanbus(struct pci_controller *hose) if (!pci_has_flag(PCI_PROBE_ONLY)) { pci_bus_size_bridges(bus); pci_bus_assign_resources(bus); - pci_enable_bridges(bus); } } } diff --git a/arch/mips/sni/a20r.c b/arch/mips/sni/a20r.c index dd0ab982d77e..f9407e170476 100644 --- a/arch/mips/sni/a20r.c +++ b/arch/mips/sni/a20r.c @@ -122,7 +122,6 @@ static struct resource sc26xx_rsrc[] = { static struct sccnxp_pdata sccnxp_data = { .reg_shift = 2, - .frequency = 3686400, .mctrl_cfg[0] = MCTRL_SIG(DTR_OP, LINE_OP7) | MCTRL_SIG(RTS_OP, LINE_OP3) | MCTRL_SIG(DSR_IP, LINE_IP5) | diff --git a/arch/openrisc/include/asm/prom.h b/arch/openrisc/include/asm/prom.h index bbb34e5343a2..eb59bfe23e85 100644 --- a/arch/openrisc/include/asm/prom.h +++ b/arch/openrisc/include/asm/prom.h @@ -44,9 +44,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop, extern void kdump_move_device_tree(void); -/* CPU OF node matching */ -struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); - /* Get the MAC address */ extern const void *of_get_mac_address(struct device_node *np); diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index dbd9d3c991e8..5aecda05e0da 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -369,9 +369,9 @@ config KEXEC It is an ongoing process to be certain the hardware in a machine is properly shutdown, so do not be surprised if this code does not - initially work for you. It may help to enable device hotplugging - support. As of this writing the exact hardware interface is - strongly in flux, so no good recommendation can be made. + initially work for you. As of this writing the exact hardware + interface is strongly in flux, so no good recommendation can be + made. config CRASH_DUMP bool "Build a kdump crash kernel" @@ -979,6 +979,7 @@ config RELOCATABLE must live at a different physical address than the primary kernel. +# This value must have zeroes in the bottom 60 bits otherwise lots will break config PAGE_OFFSET hex default "0xc000000000000000" diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index 650757c300db..704e6f10ae80 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -2,3 +2,4 @@ generic-y += clkdev.h generic-y += rwsem.h generic-y += trace_clock.h +generic-y += vtime.h
\ No newline at end of file diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 08891d07aeb6..fa19e2f1a874 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -334,6 +334,27 @@ static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu) return r; } +/* + * Like kvmppc_get_last_inst(), but for fetching a sc instruction. + * Because the sc instruction sets SRR0 to point to the following + * instruction, we have to fetch from pc - 4. + */ +static inline u32 kvmppc_get_last_sc(struct kvm_vcpu *vcpu) +{ + ulong pc = kvmppc_get_pc(vcpu) - 4; + struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); + u32 r; + + /* Load the instruction manually if it failed to do so in the + * exit path */ + if (svcpu->last_inst == KVM_INST_FETCH_FAILED) + kvmppc_ld(vcpu, &pc, sizeof(u32), &svcpu->last_inst, false); + + r = svcpu->last_inst; + svcpu_put(svcpu); + return r; +} + static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) { struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu); @@ -446,6 +467,23 @@ static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu) return vcpu->arch.last_inst; } +/* + * Like kvmppc_get_last_inst(), but for fetching a sc instruction. + * Because the sc instruction sets SRR0 to point to the following + * instruction, we have to fetch from pc - 4. + */ +static inline u32 kvmppc_get_last_sc(struct kvm_vcpu *vcpu) +{ + ulong pc = kvmppc_get_pc(vcpu) - 4; + + /* Load the instruction manually if it failed to do so in the + * exit path */ + if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED) + kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false); + + return vcpu->arch.last_inst; +} + static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu) { return vcpu->arch.fault_dar; diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index a1ecb14e4442..86d638a3b359 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -37,7 +37,7 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu) #ifdef CONFIG_KVM_BOOK3S_64_HV #define KVM_DEFAULT_HPT_ORDER 24 /* 16MB HPT by default */ -extern int kvm_hpt_order; /* order of preallocated HPTs */ +extern unsigned long kvm_rma_pages; #endif #define VRMA_VSID 0x1ffffffUL /* 1TB VSID reserved for VRMA */ @@ -100,7 +100,7 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, /* (masks depend on page size) */ rb |= 0x1000; /* page encoding in LP field */ rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */ - rb |= (va_low & 0xfe); /* AVAL field (P7 doesn't seem to care) */ + rb |= ((va_low << 4) & 0xf0); /* AVAL field (P7 doesn't seem to care) */ } } else { /* 4kB page */ diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index af326cde7cb6..33283532e9d8 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -183,13 +183,9 @@ struct kvmppc_spapr_tce_table { struct page *pages[0]; }; -struct kvmppc_linear_info { - void *base_virt; - unsigned long base_pfn; - unsigned long npages; - struct list_head list; - atomic_t use_count; - int type; +struct kvm_rma_info { + atomic_t use_count; + unsigned long base_pfn; }; /* XICS components, defined in book3s_xics.c */ @@ -246,7 +242,7 @@ struct kvm_arch { int tlbie_lock; unsigned long lpcr; unsigned long rmor; - struct kvmppc_linear_info *rma; + struct kvm_rma_info *rma; unsigned long vrma_slb_v; int rma_setup_done; int using_mmu_notifiers; @@ -259,7 +255,7 @@ struct kvm_arch { spinlock_t slot_phys_lock; cpumask_t need_tlb_flush; struct kvmppc_vcore *vcores[KVM_MAX_VCORES]; - struct kvmppc_linear_info *hpt_li; + int hpt_cma_alloc; #endif /* CONFIG_KVM_BOOK3S_64_HV */ #ifdef CONFIG_PPC_BOOK3S_64 struct list_head spapr_tce_tables; diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h index a5287fe03d77..b15554a26c20 100644 --- a/arch/powerpc/include/asm/kvm_ppc.h +++ b/arch/powerpc/include/asm/kvm_ppc.h @@ -137,10 +137,10 @@ extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn, unsigned long ioba, unsigned long tce); extern long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *rma); -extern struct kvmppc_linear_info *kvm_alloc_rma(void); -extern void kvm_release_rma(struct kvmppc_linear_info *ri); -extern struct kvmppc_linear_info *kvm_alloc_hpt(void); -extern void kvm_release_hpt(struct kvmppc_linear_info *li); +extern struct kvm_rma_info *kvm_alloc_rma(void); +extern void kvm_release_rma(struct kvm_rma_info *ri); +extern struct page *kvm_alloc_hpt(unsigned long nr_pages); +extern void kvm_release_hpt(struct page *page, unsigned long nr_pages); extern int kvmppc_core_init_vm(struct kvm *kvm); extern void kvmppc_core_destroy_vm(struct kvm *kvm); extern void kvmppc_core_free_memslot(struct kvm_memory_slot *free, @@ -261,6 +261,7 @@ void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid); struct openpic; #ifdef CONFIG_KVM_BOOK3S_64_HV +extern void kvm_cma_reserve(void) __init; static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr) { paca[cpu].kvm_hstate.xics_phys = addr; @@ -281,13 +282,12 @@ static inline void kvmppc_set_host_ipi(int cpu, u8 host_ipi) } extern void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu); -extern void kvm_linear_init(void); #else -static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr) +static inline void __init kvm_cma_reserve(void) {} -static inline void kvm_linear_init(void) +static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr) {} static inline u32 kvmppc_get_xics_latch(void) @@ -394,10 +394,15 @@ static inline void kvmppc_mmu_flush_icache(pfn_t pfn) } } -/* Please call after prepare_to_enter. This function puts the lazy ee state - back to normal mode, without actually enabling interrupts. */ -static inline void kvmppc_lazy_ee_enable(void) +/* + * Please call after prepare_to_enter. This function puts the lazy ee and irq + * disabled tracking state back to normal mode, without actually enabling + * interrupts. + */ +static inline void kvmppc_fix_ee_before_entry(void) { + trace_hardirqs_on(); + #ifdef CONFIG_PPC64 /* Only need to enable IRQs by hard enabling them after this */ local_paca->irq_happened = 0; diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h index 988c812aab5b..b9f426212d3a 100644 --- a/arch/powerpc/include/asm/page.h +++ b/arch/powerpc/include/asm/page.h @@ -211,9 +211,19 @@ extern long long virt_phys_offset; #define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + VIRT_PHYS_OFFSET)) #define __pa(x) ((unsigned long)(x) - VIRT_PHYS_OFFSET) #else +#ifdef CONFIG_PPC64 +/* + * gcc miscompiles (unsigned long)(&static_var) - PAGE_OFFSET + * with -mcmodel=medium, so we use & and | instead of - and + on 64-bit. + */ +#define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) | PAGE_OFFSET)) +#define __pa(x) ((unsigned long)(x) & 0x0fffffffffffffffUL) + +#else /* 32-bit, non book E */ #define __va(x) ((void *)(unsigned long)((phys_addr_t)(x) + PAGE_OFFSET - MEMORY_START)) #define __pa(x) ((unsigned long)(x) - PAGE_OFFSET + MEMORY_START) #endif +#endif /* * Unfortunately the PLT is in the BSS in the PPC32 ELF ABI, diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h index 8b2492644754..3fd2f1b6f906 100644 --- a/arch/powerpc/include/asm/perf_event_server.h +++ b/arch/powerpc/include/asm/perf_event_server.h @@ -138,11 +138,11 @@ extern ssize_t power_events_sysfs_show(struct device *dev, #define EVENT_PTR(_id, _suffix) &EVENT_VAR(_id, _suffix).attr.attr #define EVENT_ATTR(_name, _id, _suffix) \ - PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), PME_PM_##_id, \ + PMU_EVENT_ATTR(_name, EVENT_VAR(_id, _suffix), PME_##_id, \ power_events_sysfs_show) #define GENERIC_EVENT_ATTR(_name, _id) EVENT_ATTR(_name, _id, _g) #define GENERIC_EVENT_PTR(_id) EVENT_PTR(_id, _g) -#define POWER_EVENT_ATTR(_name, _id) EVENT_ATTR(PM_##_name, _id, _p) +#define POWER_EVENT_ATTR(_name, _id) EVENT_ATTR(_name, _id, _p) #define POWER_EVENT_PTR(_id) EVENT_PTR(_id, _p) diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h index bc2da154f68b..ac204e022922 100644 --- a/arch/powerpc/include/asm/prom.h +++ b/arch/powerpc/include/asm/prom.h @@ -43,9 +43,6 @@ void of_parse_dma_window(struct device_node *dn, const void *dma_window_prop, extern void kdump_move_device_tree(void); -/* CPU OF node matching */ -struct device_node *of_get_cpu_node(int cpu, unsigned int *thread); - /* cache lookup */ struct device_node *of_find_next_cache_node(struct device_node *np); diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 8207459efe56..d8958be5f31a 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -454,6 +454,7 @@ int main(void) DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2)); DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3)); #endif + DEFINE(VCPU_SHARED_SPRG3, offsetof(struct kvm_vcpu_arch_shared, sprg3)); DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4)); DEFINE(VCPU_SHARED_SPRG5, offsetof(struct kvm_vcpu_arch_shared, sprg5)); DEFINE(VCPU_SHARED_SPRG6, offsetof(struct kvm_vcpu_arch_shared, sprg6)); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index b20ff173a671..0adab06ce5c0 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -105,7 +105,7 @@ static int __init fail_iommu_debugfs(void) struct dentry *dir = fault_create_debugfs_attr("fail_iommu", NULL, &fail_iommu); - return PTR_RET(dir); + return PTR_ERR_OR_ZERO(dir); } late_initcall(fail_iommu_debugfs); diff --git a/arch/powerpc/kernel/lparcfg.c b/arch/powerpc/kernel/lparcfg.c index d92f3871e9cf..e2a0a162299b 100644 --- a/arch/powerpc/kernel/lparcfg.c +++ b/arch/powerpc/kernel/lparcfg.c @@ -35,7 +35,13 @@ #include <asm/vdso_datapage.h> #include <asm/vio.h> #include <asm/mmu.h> +#include <asm/machdep.h> + +/* + * This isn't a module but we expose that to userspace + * via /proc so leave the definitions here + */ #define MODULE_VERS "1.9" #define MODULE_NAME "lparcfg" @@ -418,7 +424,8 @@ static void parse_em_data(struct seq_file *m) { unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; - if (plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS) + if (firmware_has_feature(FW_FEATURE_LPAR) && + plpar_hcall(H_GET_EM_PARMS, retbuf) == H_SUCCESS) seq_printf(m, "power_mode_data=%016lx\n", retbuf[0]); } @@ -677,7 +684,6 @@ static int lparcfg_open(struct inode *inode, struct file *file) } static const struct file_operations lparcfg_fops = { - .owner = THIS_MODULE, .read = seq_read, .write = lparcfg_write, .open = lparcfg_open, @@ -699,14 +705,4 @@ static int __init lparcfg_init(void) } return 0; } - -static void __exit lparcfg_cleanup(void) -{ - remove_proc_subtree("powerpc/lparcfg", NULL); -} - -module_init(lparcfg_init); -module_exit(lparcfg_cleanup); -MODULE_DESCRIPTION("Interface for LPAR configuration data"); -MODULE_AUTHOR("Dave Engebretsen"); -MODULE_LICENSE("GPL"); +machine_device_initcall(pseries, lparcfg_init); diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c index 7d22a675fe1a..2b4a9a4db7d9 100644 --- a/arch/powerpc/kernel/pci-common.c +++ b/arch/powerpc/kernel/pci-common.c @@ -1674,12 +1674,8 @@ void pcibios_scan_phb(struct pci_controller *hose) /* Configure PCI Express settings */ if (bus && !pci_has_flag(PCI_PROBE_ONLY)) { struct pci_bus *child; - list_for_each_entry(child, &bus->children, node) { - struct pci_dev *self = child->self; - if (!self) - continue; - pcie_bus_configure_settings(child, self->pcie_mpss); - } + list_for_each_entry(child, &bus->children, node) + pcie_bus_configure_settings(child); } } diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index eb23ac92abb9..1c14cd4a5e05 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -865,49 +865,10 @@ static int __init prom_reconfig_setup(void) __initcall(prom_reconfig_setup); #endif -/* Find the device node for a given logical cpu number, also returns the cpu - * local thread number (index in ibm,interrupt-server#s) if relevant and - * asked for (non NULL) - */ -struct device_node *of_get_cpu_node(int cpu, unsigned int *thread) +bool arch_match_cpu_phys_id(int cpu, u64 phys_id) { - int hardid; - struct device_node *np; - - hardid = get_hard_smp_processor_id(cpu); - - for_each_node_by_type(np, "cpu") { - const u32 *intserv; - unsigned int plen, t; - - /* Check for ibm,ppc-interrupt-server#s. If it doesn't exist - * fallback to "reg" property and assume no threads - */ - intserv = of_get_property(np, "ibm,ppc-interrupt-server#s", - &plen); - if (intserv == NULL) { - const u32 *reg = of_get_property(np, "reg", NULL); - if (reg == NULL) - continue; - if (*reg == hardid) { - if (thread) - *thread = 0; - return np; - } - } else { - plen /= sizeof(u32); - for (t = 0; t < plen; t++) { - if (hardid == intserv[t]) { - if (thread) - *thread = t; - return np; - } - } - } - } - return NULL; + return (int)phys_id == get_hard_smp_processor_id(cpu); } -EXPORT_SYMBOL(of_get_cpu_node); #if defined(CONFIG_DEBUG_FS) && defined(DEBUG) static struct debugfs_blob_wrapper flat_dt_blob; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 389fb8077cc9..fe6a58c9f0b7 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -229,6 +229,8 @@ void __init early_setup(unsigned long dt_ptr) /* Initialize the hash table or TLB handling */ early_init_mmu(); + kvm_cma_reserve(); + /* * Reserve any gigantic pages requested on the command line. * memblock needs to have been initialized by the time this is @@ -609,8 +611,6 @@ void __init setup_arch(char **cmdline_p) /* Initialize the MMU context management stuff */ mmu_context_init(); - kvm_linear_init(); - /* Interrupt code needs to be 64K-aligned */ if ((unsigned long)_stext & 0xffff) panic("Kernelbase not 64K-aligned (0x%lx)!\n", diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index 65ab9e909377..cdcc156865ef 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -1049,7 +1049,7 @@ static int __init rtc_init(void) pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0); - return PTR_RET(pdev); + return PTR_ERR_OR_ZERO(pdev); } module_init(rtc_init); diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig index eb643f862579..ffaef2cb101a 100644 --- a/arch/powerpc/kvm/Kconfig +++ b/arch/powerpc/kvm/Kconfig @@ -72,6 +72,7 @@ config KVM_BOOK3S_64_HV bool "KVM support for POWER7 and PPC970 using hypervisor mode in host" depends on KVM_BOOK3S_64 select MMU_NOTIFIER + select CMA ---help--- Support running unmodified book3s_64 guest kernels in virtual machines on POWER7 and PPC970 processors that have diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile index 008cd856c5b5..6646c952c5e3 100644 --- a/arch/powerpc/kvm/Makefile +++ b/arch/powerpc/kvm/Makefile @@ -81,6 +81,7 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \ book3s_64_vio_hv.o \ book3s_hv_ras.o \ book3s_hv_builtin.o \ + book3s_hv_cma.o \ $(kvm-book3s_64-builtin-xics-objs-y) kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \ diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c index 739bfbadb85e..7e345e00661a 100644 --- a/arch/powerpc/kvm/book3s_64_mmu.c +++ b/arch/powerpc/kvm/book3s_64_mmu.c @@ -182,10 +182,13 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, hva_t ptegp; u64 pteg[16]; u64 avpn = 0; + u64 v, r; + u64 v_val, v_mask; + u64 eaddr_mask; int i; - u8 key = 0; + u8 pp, key = 0; bool found = false; - int second = 0; + bool second = false; ulong mp_ea = vcpu->arch.magic_page_ea; /* Magic page override */ @@ -208,8 +211,16 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, goto no_seg_found; avpn = kvmppc_mmu_book3s_64_get_avpn(slbe, eaddr); + v_val = avpn & HPTE_V_AVPN; + if (slbe->tb) - avpn |= SLB_VSID_B_1T; + v_val |= SLB_VSID_B_1T; + if (slbe->large) + v_val |= HPTE_V_LARGE; + v_val |= HPTE_V_VALID; + + v_mask = SLB_VSID_B | HPTE_V_AVPN | HPTE_V_LARGE | HPTE_V_VALID | + HPTE_V_SECONDARY; do_second: ptegp = kvmppc_mmu_book3s_64_get_pteg(vcpu_book3s, slbe, eaddr, second); @@ -227,91 +238,74 @@ do_second: key = 4; for (i=0; i<16; i+=2) { - u64 v = pteg[i]; - u64 r = pteg[i+1]; - - /* Valid check */ - if (!(v & HPTE_V_VALID)) - continue; - /* Hash check */ - if ((v & HPTE_V_SECONDARY) != second) - continue; - - /* AVPN compare */ - if (HPTE_V_COMPARE(avpn, v)) { - u8 pp = (r & HPTE_R_PP) | key; - int eaddr_mask = 0xFFF; - - gpte->eaddr = eaddr; - gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu, - eaddr, - data); - if (slbe->large) - eaddr_mask = 0xFFFFFF; - gpte->raddr = (r & HPTE_R_RPN) | (eaddr & eaddr_mask); - gpte->may_execute = ((r & HPTE_R_N) ? false : true); - gpte->may_read = false; - gpte->may_write = false; - - switch (pp) { - case 0: - case 1: - case 2: - case 6: - gpte->may_write = true; - /* fall through */ - case 3: - case 5: - case 7: - gpte->may_read = true; - break; - } - - dprintk("KVM MMU: Translated 0x%lx [0x%llx] -> 0x%llx " - "-> 0x%lx\n", - eaddr, avpn, gpte->vpage, gpte->raddr); + /* Check all relevant fields of 1st dword */ + if ((pteg[i] & v_mask) == v_val) { found = true; break; } } - /* Update PTE R and C bits, so the guest's swapper knows we used the - * page */ - if (found) { - u32 oldr = pteg[i+1]; + if (!found) { + if (second) + goto no_page_found; + v_val |= HPTE_V_SECONDARY; + second = true; + goto do_second; + } - if (gpte->may_read) { - /* Set the accessed flag */ - pteg[i+1] |= HPTE_R_R; - } - if (gpte->may_write) { - /* Set the dirty flag */ - pteg[i+1] |= HPTE_R_C; - } else { - dprintk("KVM: Mapping read-only page!\n"); - } + v = pteg[i]; + r = pteg[i+1]; + pp = (r & HPTE_R_PP) | key; + eaddr_mask = 0xFFF; + + gpte->eaddr = eaddr; + gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu, eaddr, data); + if (slbe->large) + eaddr_mask = 0xFFFFFF; + gpte->raddr = (r & HPTE_R_RPN & ~eaddr_mask) | (eaddr & eaddr_mask); + gpte->may_execute = ((r & HPTE_R_N) ? false : true); + gpte->may_read = false; + gpte->may_write = false; + + switch (pp) { + case 0: + case 1: + case 2: + case 6: + gpte->may_write = true; + /* fall through */ + case 3: + case 5: + case 7: + gpte->may_read = true; + break; + } - /* Write back into the PTEG */ - if (pteg[i+1] != oldr) - copy_to_user((void __user *)ptegp, pteg, sizeof(pteg)); + dprintk("KVM MMU: Translated 0x%lx [0x%llx] -> 0x%llx " + "-> 0x%lx\n", + eaddr, avpn, gpte->vpage, gpte->raddr); - if (!gpte->may_read) - return -EPERM; - return 0; - } else { - dprintk("KVM MMU: No PTE found (ea=0x%lx sdr1=0x%llx " - "ptegp=0x%lx)\n", - eaddr, to_book3s(vcpu)->sdr1, ptegp); - for (i = 0; i < 16; i += 2) - dprintk(" %02d: 0x%llx - 0x%llx (0x%llx)\n", - i, pteg[i], pteg[i+1], avpn); - - if (!second) { - second = HPTE_V_SECONDARY; - goto do_second; - } + /* Update PTE R and C bits, so the guest's swapper knows we used the + * page */ + if (gpte->may_read) { + /* Set the accessed flag */ + r |= HPTE_R_R; + } + if (data && gpte->may_write) { + /* Set the dirty flag -- XXX even if not writing */ + r |= HPTE_R_C; + } + + /* Write back into the PTEG */ + if (pteg[i+1] != r) { + pteg[i+1] = r; + copy_to_user((void __user *)ptegp, pteg, sizeof(pteg)); } + if (!gpte->may_read) + return -EPERM; + return 0; + no_page_found: return -ENOENT; diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 710d31317d81..043eec8461e7 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -37,6 +37,8 @@ #include <asm/ppc-opcode.h> #include <asm/cputable.h> +#include "book3s_hv_cma.h" + /* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */ #define MAX_LPID_970 63 @@ -52,8 +54,8 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp) { unsigned long hpt; struct revmap_entry *rev; - struct kvmppc_linear_info *li; - long order = kvm_hpt_order; + struct page *page = NULL; + long order = KVM_DEFAULT_HPT_ORDER; if (htab_orderp) { order = *htab_orderp; @@ -61,26 +63,23 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp) order = PPC_MIN_HPT_ORDER; } + kvm->arch.hpt_cma_alloc = 0; /* - * If the user wants a different size from default, * try first to allocate it from the kernel page allocator. + * We keep the CMA reserved for failed allocation. */ - hpt = 0; - if (order != kvm_hpt_order) { - hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT| - __GFP_NOWARN, order - PAGE_SHIFT); - if (!hpt) - --order; - } + hpt = __get_free_pages(GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT | + __GFP_NOWARN, order - PAGE_SHIFT); /* Next try to allocate from the preallocated pool */ if (!hpt) { - li = kvm_alloc_hpt(); - if (li) { - hpt = (ulong)li->base_virt; - kvm->arch.hpt_li = li; - order = kvm_hpt_order; - } + VM_BUG_ON(order < KVM_CMA_CHUNK_ORDER); + page = kvm_alloc_hpt(1 << (order - PAGE_SHIFT)); + if (page) { + hpt = (unsigned long)pfn_to_kaddr(page_to_pfn(page)); + kvm->arch.hpt_cma_alloc = 1; + } else + --order; } /* Lastly try successively smaller sizes from the page allocator */ @@ -118,8 +117,8 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp) return 0; out_freehpt: - if (kvm->arch.hpt_li) - kvm_release_hpt(kvm->arch.hpt_li); + if (kvm->arch.hpt_cma_alloc) + kvm_release_hpt(page, 1 << (order - PAGE_SHIFT)); else free_pages(hpt, order - PAGE_SHIFT); return -ENOMEM; @@ -165,8 +164,9 @@ void kvmppc_free_hpt(struct kvm *kvm) { kvmppc_free_lpid(kvm->arch.lpid); vfree(kvm->arch.revmap); - if (kvm->arch.hpt_li) - kvm_release_hpt(kvm->arch.hpt_li); + if (kvm->arch.hpt_cma_alloc) + kvm_release_hpt(virt_to_page(kvm->arch.hpt_virt), + 1 << (kvm->arch.hpt_order - PAGE_SHIFT)); else free_pages(kvm->arch.hpt_virt, kvm->arch.hpt_order - PAGE_SHIFT); @@ -1579,7 +1579,7 @@ int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *ghf) ctx->first_pass = 1; rwflag = (ghf->flags & KVM_GET_HTAB_WRITE) ? O_WRONLY : O_RDONLY; - ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag); + ret = anon_inode_getfd("kvm-htab", &kvm_htab_fops, ctx, rwflag | O_CLOEXEC); if (ret < 0) { kvm_put_kvm(kvm); return ret; diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index b2d3f3b2de72..54cf9bc94dad 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -136,7 +136,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm, mutex_unlock(&kvm->lock); return anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops, - stt, O_RDWR); + stt, O_RDWR | O_CLOEXEC); fail: if (stt) { diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c index 1f6344c4408d..360ce68c9809 100644 --- a/arch/powerpc/kvm/book3s_emulate.c +++ b/arch/powerpc/kvm/book3s_emulate.c @@ -458,6 +458,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val) case SPRN_PMC4_GEKKO: case SPRN_WPAR_GEKKO: case SPRN_MSSSR0: + case SPRN_DABR: break; unprivileged: default: @@ -555,6 +556,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val) case SPRN_PMC4_GEKKO: case SPRN_WPAR_GEKKO: case SPRN_MSSSR0: + case SPRN_DABR: *spr_val = 0; break; default: diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 7629cd3eb91a..b0ee3bc9ca76 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -680,13 +680,12 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, } int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) + struct kvm_sregs *sregs) { int i; - sregs->pvr = vcpu->arch.pvr; - memset(sregs, 0, sizeof(struct kvm_sregs)); + sregs->pvr = vcpu->arch.pvr; for (i = 0; i < vcpu->arch.slb_max; i++) { sregs->u.s.ppc64.slb[i].slbe = vcpu->arch.slb[i].orige; sregs->u.s.ppc64.slb[i].slbv = vcpu->arch.slb[i].origv; @@ -696,7 +695,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, } int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, - struct kvm_sregs *sregs) + struct kvm_sregs *sregs) { int i, j; @@ -1511,10 +1510,10 @@ static inline int lpcr_rmls(unsigned long rma_size) static int kvm_rma_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { - struct kvmppc_linear_info *ri = vma->vm_file->private_data; struct page *page; + struct kvm_rma_info *ri = vma->vm_file->private_data; - if (vmf->pgoff >= ri->npages) + if (vmf->pgoff >= kvm_rma_pages) return VM_FAULT_SIGBUS; page = pfn_to_page(ri->base_pfn + vmf->pgoff); @@ -1536,7 +1535,7 @@ static int kvm_rma_mmap(struct file *file, struct vm_area_struct *vma) static int kvm_rma_release(struct inode *inode, struct file *filp) { - struct kvmppc_linear_info *ri = filp->private_data; + struct kvm_rma_info *ri = filp->private_data; kvm_release_rma(ri); return 0; @@ -1549,18 +1548,27 @@ static const struct file_operations kvm_rma_fops = { long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret) { - struct kvmppc_linear_info *ri; long fd; + struct kvm_rma_info *ri; + /* + * Only do this on PPC970 in HV mode + */ + if (!cpu_has_feature(CPU_FTR_HVMODE) || + !cpu_has_feature(CPU_FTR_ARCH_201)) + return -EINVAL; + + if (!kvm_rma_pages) + return -EINVAL; ri = kvm_alloc_rma(); if (!ri) return -ENOMEM; - fd = anon_inode_getfd("kvm-rma", &kvm_rma_fops, ri, O_RDWR); + fd = anon_inode_getfd("kvm-rma", &kvm_rma_fops, ri, O_RDWR | O_CLOEXEC); if (fd < 0) kvm_release_rma(ri); - ret->rma_size = ri->npages << PAGE_SHIFT; + ret->rma_size = kvm_rma_pages << PAGE_SHIFT; return fd; } @@ -1725,7 +1733,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) { int err = 0; struct kvm *kvm = vcpu->kvm; - struct kvmppc_linear_info *ri = NULL; + struct kvm_rma_info *ri = NULL; unsigned long hva; struct kvm_memory_slot *memslot; struct vm_area_struct *vma; @@ -1803,7 +1811,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) } else { /* Set up to use an RMO region */ - rma_size = ri->npages; + rma_size = kvm_rma_pages; if (rma_size > memslot->npages) rma_size = memslot->npages; rma_size <<= PAGE_SHIFT; @@ -1831,14 +1839,14 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu) /* POWER7 */ lpcr &= ~(LPCR_VPM0 | LPCR_VRMA_L); lpcr |= rmls << LPCR_RMLS_SH; - kvm->arch.rmor = kvm->arch.rma->base_pfn << PAGE_SHIFT; + kvm->arch.rmor = ri->base_pfn << PAGE_SHIFT; } kvm->arch.lpcr = lpcr; pr_info("KVM: Using RMO at %lx size %lx (LPCR = %lx)\n", ri->base_pfn << PAGE_SHIFT, rma_size, lpcr); /* Initialize phys addrs of pages in RMO */ - npages = ri->npages; + npages = kvm_rma_pages; porder = __ilog2(npages); physp = memslot->arch.slot_phys; if (physp) { diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c index ec0a9e5de100..8cd0daebb82d 100644 --- a/arch/powerpc/kvm/book3s_hv_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_builtin.c @@ -13,33 +13,34 @@ #include <linux/spinlock.h> #include <linux/bootmem.h> #include <linux/init.h> +#include <linux/memblock.h> +#include <linux/sizes.h> #include <asm/cputable.h> #include <asm/kvm_ppc.h> #include <asm/kvm_book3s.h> -#define KVM_LINEAR_RMA 0 -#define KVM_LINEAR_HPT 1 - -static void __init kvm_linear_init_one(ulong size, int count, int type); -static struct kvmppc_linear_info *kvm_alloc_linear(int type); -static void kvm_release_linear(struct kvmppc_linear_info *ri); - -int kvm_hpt_order = KVM_DEFAULT_HPT_ORDER; -EXPORT_SYMBOL_GPL(kvm_hpt_order); - -/*************** RMA *************/ - +#include "book3s_hv_cma.h" +/* + * Hash page table alignment on newer cpus(CPU_FTR_ARCH_206) + * should be power of 2. + */ +#define HPT_ALIGN_PAGES ((1 << 18) >> PAGE_SHIFT) /* 256k */ +/* + * By default we reserve 5% of memory for hash pagetable allocation. + */ +static unsigned long kvm_cma_resv_ratio = 5; /* - * This maintains a list of RMAs (real mode areas) for KVM guests to use. + * We allocate RMAs (real mode areas) for KVM guests from the KVM CMA area. * Each RMA has to be physically contiguous and of a size that the * hardware supports. PPC970 and POWER7 support 64MB, 128MB and 256MB, * and other larger sizes. Since we are unlikely to be allocate that * much physically contiguous memory after the system is up and running, - * we preallocate a set of RMAs in early boot for KVM to use. + * we preallocate a set of RMAs in early boot using CMA. + * should be power of 2. */ -static unsigned long kvm_rma_size = 64 << 20; /* 64MB */ -static unsigned long kvm_rma_count; +unsigned long kvm_rma_pages = (1 << 27) >> PAGE_SHIFT; /* 128MB */ +EXPORT_SYMBOL_GPL(kvm_rma_pages); /* Work out RMLS (real mode limit selector) field value for a given RMA size. Assumes POWER7 or PPC970. */ @@ -69,165 +70,114 @@ static inline int lpcr_rmls(unsigned long rma_size) static int __init early_parse_rma_size(char *p) { - if (!p) - return 1; + unsigned long kvm_rma_size; + pr_debug("%s(%s)\n", __func__, p); + if (!p) + return -EINVAL; kvm_rma_size = memparse(p, &p); - + /* + * Check that the requested size is one supported in hardware + */ + if (lpcr_rmls(kvm_rma_size) < 0) { + pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size); + return -EINVAL; + } + kvm_rma_pages = kvm_rma_size >> PAGE_SHIFT; return 0; } early_param("kvm_rma_size", early_parse_rma_size); -static int __init early_parse_rma_count(char *p) +struct kvm_rma_info *kvm_alloc_rma() { - if (!p) - return 1; - - kvm_rma_count = simple_strtoul(p, NULL, 0); - - return 0; -} -early_param("kvm_rma_count", early_parse_rma_count); - -struct kvmppc_linear_info *kvm_alloc_rma(void) -{ - return kvm_alloc_linear(KVM_LINEAR_RMA); + struct page *page; + struct kvm_rma_info *ri; + + ri = kmalloc(sizeof(struct kvm_rma_info), GFP_KERNEL); + if (!ri) + return NULL; + page = kvm_alloc_cma(kvm_rma_pages, kvm_rma_pages); + if (!page) + goto err_out; + atomic_set(&ri->use_count, 1); + ri->base_pfn = page_to_pfn(page); + return ri; +err_out: + kfree(ri); + return NULL; } EXPORT_SYMBOL_GPL(kvm_alloc_rma); -void kvm_release_rma(struct kvmppc_linear_info *ri) +void kvm_release_rma(struct kvm_rma_info *ri) { - kvm_release_linear(ri); + if (atomic_dec_and_test(&ri->use_count)) { + kvm_release_cma(pfn_to_page(ri->base_pfn), kvm_rma_pages); + kfree(ri); + } } EXPORT_SYMBOL_GPL(kvm_release_rma); -/*************** HPT *************/ - -/* - * This maintains a list of big linear HPT tables that contain the GVA->HPA - * memory mappings. If we don't reserve those early on, we might not be able - * to get a big (usually 16MB) linear memory region from the kernel anymore. - */ - -static unsigned long kvm_hpt_count; - -static int __init early_parse_hpt_count(char *p) +static int __init early_parse_kvm_cma_resv(char *p) { + pr_debug("%s(%s)\n", __func__, p); if (!p) - return 1; - - kvm_hpt_count = simple_strtoul(p, NULL, 0); - - return 0; + return -EINVAL; + return kstrtoul(p, 0, &kvm_cma_resv_ratio); } -early_param("kvm_hpt_count", early_parse_hpt_count); +early_param("kvm_cma_resv_ratio", early_parse_kvm_cma_resv); -struct kvmppc_linear_info *kvm_alloc_hpt(void) +struct page *kvm_alloc_hpt(unsigned long nr_pages) { - return kvm_alloc_linear(KVM_LINEAR_HPT); + unsigned long align_pages = HPT_ALIGN_PAGES; + + /* Old CPUs require HPT aligned on a multiple of its size */ + if (!cpu_has_feature(CPU_FTR_ARCH_206)) + align_pages = nr_pages; + return kvm_alloc_cma(nr_pages, align_pages); } EXPORT_SYMBOL_GPL(kvm_alloc_hpt); -void kvm_release_hpt(struct kvmppc_linear_info *li) +void kvm_release_hpt(struct page *page, unsigned long nr_pages) { - kvm_release_linear(li); + kvm_release_cma(page, nr_pages); } EXPORT_SYMBOL_GPL(kvm_release_hpt); -/*************** generic *************/ - -static LIST_HEAD(free_linears); -static DEFINE_SPINLOCK(linear_lock); - -static void __init kvm_linear_init_one(ulong size, int count, int type) -{ - unsigned long i; - unsigned long j, npages; - void *linear; - struct page *pg; - const char *typestr; - struct kvmppc_linear_info *linear_info; - - if (!count) - return; - - typestr = (type == KVM_LINEAR_RMA) ? "RMA" : "HPT"; - - npages = size >> PAGE_SHIFT; - linear_info = alloc_bootmem(count * sizeof(struct kvmppc_linear_info)); - for (i = 0; i < count; ++i) { - linear = alloc_bootmem_align(size, size); - pr_debug("Allocated KVM %s at %p (%ld MB)\n", typestr, linear, - size >> 20); - linear_info[i].base_virt = linear; - linear_info[i].base_pfn = __pa(linear) >> PAGE_SHIFT; - linear_info[i].npages = npages; - linear_info[i].type = type; - list_add_tail(&linear_info[i].list, &free_linears); - atomic_set(&linear_info[i].use_count, 0); - - pg = pfn_to_page(linear_info[i].base_pfn); - for (j = 0; j < npages; ++j) { - atomic_inc(&pg->_count); - ++pg; - } - } -} - -static struct kvmppc_linear_info *kvm_alloc_linear(int type) -{ - struct kvmppc_linear_info *ri, *ret; - - ret = NULL; - spin_lock(&linear_lock); - list_for_each_entry(ri, &free_linears, list) { - if (ri->type != type) - continue; - - list_del(&ri->list); - atomic_inc(&ri->use_count); - memset(ri->base_virt, 0, ri->npages << PAGE_SHIFT); - ret = ri; - break; - } - spin_unlock(&linear_lock); - return ret; -} - -static void kvm_release_linear(struct kvmppc_linear_info *ri) -{ - if (atomic_dec_and_test(&ri->use_count)) { - spin_lock(&linear_lock); - list_add_tail(&ri->list, &free_linears); - spin_unlock(&linear_lock); - - } -} - -/* - * Called at boot time while the bootmem allocator is active, - * to allocate contiguous physical memory for the hash page - * tables for guests. +/** + * kvm_cma_reserve() - reserve area for kvm hash pagetable + * + * This function reserves memory from early allocator. It should be + * called by arch specific code once the early allocator (memblock or bootmem) + * has been activated and all other subsystems have already allocated/reserved + * memory. */ -void __init kvm_linear_init(void) +void __init kvm_cma_reserve(void) { - /* HPT */ - kvm_linear_init_one(1 << kvm_hpt_order, kvm_hpt_count, KVM_LINEAR_HPT); - - /* RMA */ - /* Only do this on PPC970 in HV mode */ - if (!cpu_has_feature(CPU_FTR_HVMODE) || - !cpu_has_feature(CPU_FTR_ARCH_201)) - return; - - if (!kvm_rma_size || !kvm_rma_count) - return; - - /* Check that the requested size is one supported in hardware */ - if (lpcr_rmls(kvm_rma_size) < 0) { - pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size); - return; + unsigned long align_size; + struct memblock_region *reg; + phys_addr_t selected_size = 0; + /* + * We cannot use memblock_phys_mem_size() here, because + * memblock_analyze() has not been called yet. + */ + for_each_memblock(memory, reg) + selected_size += memblock_region_memory_end_pfn(reg) - + memblock_region_memory_base_pfn(reg); + + selected_size = (selected_size * kvm_cma_resv_ratio / 100) << PAGE_SHIFT; + if (selected_size) { + pr_debug("%s: reserving %ld MiB for global area\n", __func__, + (unsigned long)selected_size / SZ_1M); + /* + * Old CPUs require HPT aligned on a multiple of its size. So for them + * make the alignment as max size we could request. + */ + if (!cpu_has_feature(CPU_FTR_ARCH_206)) + align_size = __rounddown_pow_of_two(selected_size); + else + align_size = HPT_ALIGN_PAGES << PAGE_SHIFT; + + align_size = max(kvm_rma_pages << PAGE_SHIFT, align_size); + kvm_cma_declare_contiguous(selected_size, align_size); } - - kvm_linear_init_one(kvm_rma_size, kvm_rma_count, KVM_LINEAR_RMA); } diff --git a/arch/powerpc/kvm/book3s_hv_cma.c b/arch/powerpc/kvm/book3s_hv_cma.c new file mode 100644 index 000000000000..d9d3d8553d51 --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv_cma.c @@ -0,0 +1,240 @@ +/* + * Contiguous Memory Allocator for ppc KVM hash pagetable based on CMA + * for DMA mapping framework + * + * Copyright IBM Corporation, 2013 + * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.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 Software Foundation; either version 2 of the + * License or (at your optional) any later version of the license. + * + */ +#define pr_fmt(fmt) "kvm_cma: " fmt + +#ifdef CONFIG_CMA_DEBUG +#ifndef DEBUG +# define DEBUG +#endif +#endif + +#include <linux/memblock.h> +#include <linux/mutex.h> +#include <linux/sizes.h> +#include <linux/slab.h> + +#include "book3s_hv_cma.h" + +struct kvm_cma { + unsigned long base_pfn; + unsigned long count; + unsigned long *bitmap; +}; + +static DEFINE_MUTEX(kvm_cma_mutex); +static struct kvm_cma kvm_cma_area; + +/** + * kvm_cma_declare_contiguous() - reserve area for contiguous memory handling + * for kvm hash pagetable + * @size: Size of the reserved memory. + * @alignment: Alignment for the contiguous memory area + * + * This function reserves memory for kvm cma area. It should be + * called by arch code when early allocator (memblock or bootmem) + * is still activate. + */ +long __init kvm_cma_declare_contiguous(phys_addr_t size, phys_addr_t alignment) +{ + long base_pfn; + phys_addr_t addr; + struct kvm_cma *cma = &kvm_cma_area; + + pr_debug("%s(size %lx)\n", __func__, (unsigned long)size); + + if (!size) + return -EINVAL; + /* + * Sanitise input arguments. + * We should be pageblock aligned for CMA. + */ + alignment = max(alignment, (phys_addr_t)(PAGE_SIZE << pageblock_order)); + size = ALIGN(size, alignment); + /* + * Reserve memory + * Use __memblock_alloc_base() since + * memblock_alloc_base() panic()s. + */ + addr = __memblock_alloc_base(size, alignment, 0); + if (!addr) { + base_pfn = -ENOMEM; + goto err; + } else + base_pfn = PFN_DOWN(addr); + + /* + * Each reserved area must be initialised later, when more kernel + * subsystems (like slab allocator) are available. + */ + cma->base_pfn = base_pfn; + cma->count = size >> PAGE_SHIFT; + pr_info("CMA: reserved %ld MiB\n", (unsigned long)size / SZ_1M); + return 0; +err: + pr_err("CMA: failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M); + return base_pfn; +} + +/** + * kvm_alloc_cma() - allocate pages from contiguous area + * @nr_pages: Requested number of pages. + * @align_pages: Requested alignment in number of pages + * + * This function allocates memory buffer for hash pagetable. + */ +struct page *kvm_alloc_cma(unsigned long nr_pages, unsigned long align_pages) +{ + int ret; + struct page *page = NULL; + struct kvm_cma *cma = &kvm_cma_area; + unsigned long chunk_count, nr_chunk; + unsigned long mask, pfn, pageno, start = 0; + + + if (!cma || !cma->count) + return NULL; + + pr_debug("%s(cma %p, count %lu, align pages %lu)\n", __func__, + (void *)cma, nr_pages, align_pages); + + if (!nr_pages) + return NULL; + /* + * align mask with chunk size. The bit tracks pages in chunk size + */ + VM_BUG_ON(!is_power_of_2(align_pages)); + mask = (align_pages >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT)) - 1; + BUILD_BUG_ON(PAGE_SHIFT > KVM_CMA_CHUNK_ORDER); + + chunk_count = cma->count >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT); + nr_chunk = nr_pages >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT); + + mutex_lock(&kvm_cma_mutex); + for (;;) { + pageno = bitmap_find_next_zero_area(cma->bitmap, chunk_count, + start, nr_chunk, mask); + if (pageno >= chunk_count) + break; + + pfn = cma->base_pfn + (pageno << (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT)); + ret = alloc_contig_range(pfn, pfn + nr_pages, MIGRATE_CMA); + if (ret == 0) { + bitmap_set(cma->bitmap, pageno, nr_chunk); + page = pfn_to_page(pfn); + memset(pfn_to_kaddr(pfn), 0, nr_pages << PAGE_SHIFT); + break; + } else if (ret != -EBUSY) { + break; + } + pr_debug("%s(): memory range at %p is busy, retrying\n", + __func__, pfn_to_page(pfn)); + /* try again with a bit different memory target */ + start = pageno + mask + 1; + } + mutex_unlock(&kvm_cma_mutex); + pr_debug("%s(): returned %p\n", __func__, page); + return page; +} + +/** + * kvm_release_cma() - release allocated pages for hash pagetable + * @pages: Allocated pages. + * @nr_pages: Number of allocated pages. + * + * This function releases memory allocated by kvm_alloc_cma(). + * It returns false when provided pages do not belong to contiguous area and + * true otherwise. + */ +bool kvm_release_cma(struct page *pages, unsigned long nr_pages) +{ + unsigned long pfn; + unsigned long nr_chunk; + struct kvm_cma *cma = &kvm_cma_area; + + if (!cma || !pages) + return false; + + pr_debug("%s(page %p count %lu)\n", __func__, (void *)pages, nr_pages); + + pfn = page_to_pfn(pages); + + if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count) + return false; + + VM_BUG_ON(pfn + nr_pages > cma->base_pfn + cma->count); + nr_chunk = nr_pages >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT); + + mutex_lock(&kvm_cma_mutex); + bitmap_clear(cma->bitmap, + (pfn - cma->base_pfn) >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT), + nr_chunk); + free_contig_range(pfn, nr_pages); + mutex_unlock(&kvm_cma_mutex); + + return true; +} + +static int __init kvm_cma_activate_area(unsigned long base_pfn, + unsigned long count) +{ + unsigned long pfn = base_pfn; + unsigned i = count >> pageblock_order; + struct zone *zone; + + WARN_ON_ONCE(!pfn_valid(pfn)); + zone = page_zone(pfn_to_page(pfn)); + do { + unsigned j; + base_pfn = pfn; + for (j = pageblock_nr_pages; j; --j, pfn++) { + WARN_ON_ONCE(!pfn_valid(pfn)); + /* + * alloc_contig_range requires the pfn range + * specified to be in the same zone. Make this + * simple by forcing the entire CMA resv range + * to be in the same zone. + */ + if (page_zone(pfn_to_page(pfn)) != zone) + return -EINVAL; + } + init_cma_reserved_pageblock(pfn_to_page(base_pfn)); + } while (--i); + return 0; +} + +static int __init kvm_cma_init_reserved_areas(void) +{ + int bitmap_size, ret; + unsigned long chunk_count; + struct kvm_cma *cma = &kvm_cma_area; + + pr_debug("%s()\n", __func__); + if (!cma->count) + return 0; + chunk_count = cma->count >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT); + bitmap_size = BITS_TO_LONGS(chunk_count) * sizeof(long); + cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL); + if (!cma->bitmap) + return -ENOMEM; + + ret = kvm_cma_activate_area(cma->base_pfn, cma->count); + if (ret) + goto error; + return 0; + +error: + kfree(cma->bitmap); + return ret; +} +core_initcall(kvm_cma_init_reserved_areas); diff --git a/arch/powerpc/kvm/book3s_hv_cma.h b/arch/powerpc/kvm/book3s_hv_cma.h new file mode 100644 index 000000000000..655144f75fa5 --- /dev/null +++ b/arch/powerpc/kvm/book3s_hv_cma.h @@ -0,0 +1,27 @@ +/* + * Contiguous Memory Allocator for ppc KVM hash pagetable based on CMA + * for DMA mapping framework + * + * Copyright IBM Corporation, 2013 + * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.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 Software Foundation; either version 2 of the + * License or (at your optional) any later version of the license. + * + */ + +#ifndef __POWERPC_KVM_CMA_ALLOC_H__ +#define __POWERPC_KVM_CMA_ALLOC_H__ +/* + * Both RMA and Hash page allocation will be multiple of 256K. + */ +#define KVM_CMA_CHUNK_ORDER 18 + +extern struct page *kvm_alloc_cma(unsigned long nr_pages, + unsigned long align_pages); +extern bool kvm_release_cma(struct page *pages, unsigned long nr_pages); +extern long kvm_cma_declare_contiguous(phys_addr_t size, + phys_addr_t alignment) __init; +#endif diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c index fc25689a9f35..45e30d6e462b 100644 --- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c +++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c @@ -383,6 +383,80 @@ static inline int try_lock_tlbie(unsigned int *lock) return old == 0; } +/* + * tlbie/tlbiel is a bit different on the PPC970 compared to later + * processors such as POWER7; the large page bit is in the instruction + * not RB, and the top 16 bits and the bottom 12 bits of the VA + * in RB must be 0. + */ +static void do_tlbies_970(struct kvm *kvm, unsigned long *rbvalues, + long npages, int global, bool need_sync) +{ + long i; + + if (global) { + while (!try_lock_tlbie(&kvm->arch.tlbie_lock)) + cpu_relax(); + if (need_sync) + asm volatile("ptesync" : : : "memory"); + for (i = 0; i < npages; ++i) { + unsigned long rb = rbvalues[i]; + + if (rb & 1) /* large page */ + asm volatile("tlbie %0,1" : : + "r" (rb & 0x0000fffffffff000ul)); + else + asm volatile("tlbie %0,0" : : + "r" (rb & 0x0000fffffffff000ul)); + } + asm volatile("eieio; tlbsync; ptesync" : : : "memory"); + kvm->arch.tlbie_lock = 0; + } else { + if (need_sync) + asm volatile("ptesync" : : : "memory"); + for (i = 0; i < npages; ++i) { + unsigned long rb = rbvalues[i]; + + if (rb & 1) /* large page */ + asm volatile("tlbiel %0,1" : : + "r" (rb & 0x0000fffffffff000ul)); + else + asm volatile("tlbiel %0,0" : : + "r" (rb & 0x0000fffffffff000ul)); + } + asm volatile("ptesync" : : : "memory"); + } +} + +static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues, + long npages, int global, bool need_sync) +{ + long i; + + if (cpu_has_feature(CPU_FTR_ARCH_201)) { + /* PPC970 tlbie instruction is a bit different */ + do_tlbies_970(kvm, rbvalues, npages, global, need_sync); + return; + } + if (global) { + while (!try_lock_tlbie(&kvm->arch.tlbie_lock)) + cpu_relax(); + if (need_sync) + asm volatile("ptesync" : : : "memory"); + for (i = 0; i < npages; ++i) + asm volatile(PPC_TLBIE(%1,%0) : : + "r" (rbvalues[i]), "r" (kvm->arch.lpid)); + asm volatile("eieio; tlbsync; ptesync" : : : "memory"); + kvm->arch.tlbie_lock = 0; + } else { + if (need_sync) + asm volatile("ptesync" : : : "memory"); + for (i = 0; i < npages; ++i) + asm volatile("tlbiel %0" : : "r" (rbvalues[i])); + asm volatile("ptesync" : : : "memory"); + } +} + long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags, unsigned long pte_index, unsigned long avpn, unsigned long *hpret) @@ -408,19 +482,7 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags, if (v & HPTE_V_VALID) { hpte[0] &= ~HPTE_V_VALID; rb = compute_tlbie_rb(v, hpte[1], pte_index); - if (global_invalidates(kvm, flags)) { - while (!try_lock_tlbie(&kvm->arch.tlbie_lock)) - cpu_relax(); - asm volatile("ptesync" : : : "memory"); - asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync" - : : "r" (rb), "r" (kvm->arch.lpid)); - asm volatile("ptesync" : : : "memory"); - kvm->arch.tlbie_lock = 0; - } else { - asm volatile("ptesync" : : : "memory"); - asm volatile("tlbiel %0" : : "r" (rb)); - asm volatile("ptesync" : : : "memory"); - } + do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true); /* Read PTE low word after tlbie to get final R/C values */ remove_revmap_chain(kvm, pte_index, rev, v, hpte[1]); } @@ -448,12 +510,11 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) unsigned long *hp, *hptes[4], tlbrb[4]; long int i, j, k, n, found, indexes[4]; unsigned long flags, req, pte_index, rcbits; - long int local = 0; + int global; long int ret = H_SUCCESS; struct revmap_entry *rev, *revs[4]; - if (atomic_read(&kvm->online_vcpus) == 1) - local = 1; + global = global_invalidates(kvm, 0); for (i = 0; i < 4 && ret == H_SUCCESS; ) { n = 0; for (; i < 4; ++i) { @@ -529,22 +590,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu) break; /* Now that we've collected a batch, do the tlbies */ - if (!local) { - while(!try_lock_tlbie(&kvm->arch.tlbie_lock)) - cpu_relax(); - asm volatile("ptesync" : : : "memory"); - for (k = 0; k < n; ++k) - asm volatile(PPC_TLBIE(%1,%0) : : - "r" (tlbrb[k]), - "r" (kvm->arch.lpid)); - asm volatile("eieio; tlbsync; ptesync" : : : "memory"); - kvm->arch.tlbie_lock = 0; - } else { - asm volatile("ptesync" : : : "memory"); - for (k = 0; k < n; ++k) - asm volatile("tlbiel %0" : : "r" (tlbrb[k])); - asm volatile("ptesync" : : : "memory"); - } + do_tlbies(kvm, tlbrb, n, global, true); /* Read PTE low words after tlbie to get final R/C values */ for (k = 0; k < n; ++k) { @@ -603,19 +649,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags, if (v & HPTE_V_VALID) { rb = compute_tlbie_rb(v, r, pte_index); hpte[0] = v & ~HPTE_V_VALID; - if (global_invalidates(kvm, flags)) { - while(!try_lock_tlbie(&kvm->arch.tlbie_lock)) - cpu_relax(); - asm volatile("ptesync" : : : "memory"); - asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync" - : : "r" (rb), "r" (kvm->arch.lpid)); - asm volatile("ptesync" : : : "memory"); - kvm->arch.tlbie_lock = 0; - } else { - asm volatile("ptesync" : : : "memory"); - asm volatile("tlbiel %0" : : "r" (rb)); - asm volatile("ptesync" : : : "memory"); - } + do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true); /* * If the host has this page as readonly but the guest * wants to make it read/write, reduce the permissions. @@ -686,13 +720,7 @@ void kvmppc_invalidate_hpte(struct kvm *kvm, unsigned long *hptep, hptep[0] &= ~HPTE_V_VALID; rb = compute_tlbie_rb(hptep[0], hptep[1], pte_index); - while (!try_lock_tlbie(&kvm->arch.tlbie_lock)) - cpu_relax(); - asm volatile("ptesync" : : : "memory"); - asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync" - : : "r" (rb), "r" (kvm->arch.lpid)); - asm volatile("ptesync" : : : "memory"); - kvm->arch.tlbie_lock = 0; + do_tlbies(kvm, &rb, 1, 1, true); } EXPORT_SYMBOL_GPL(kvmppc_invalidate_hpte); @@ -706,12 +734,7 @@ void kvmppc_clear_ref_hpte(struct kvm *kvm, unsigned long *hptep, rbyte = (hptep[1] & ~HPTE_R_R) >> 8; /* modify only the second-last byte, which contains the ref bit */ *((char *)hptep + 14) = rbyte; - while (!try_lock_tlbie(&kvm->arch.tlbie_lock)) - cpu_relax(); - asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync" - : : "r" (rb), "r" (kvm->arch.lpid)); - asm volatile("ptesync" : : : "memory"); - kvm->arch.tlbie_lock = 0; + do_tlbies(kvm, &rb, 1, 1, false); } EXPORT_SYMBOL_GPL(kvmppc_clear_ref_hpte); diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index b02f91e4c70d..60dce5bfab3f 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -1381,7 +1381,7 @@ hcall_try_real_mode: cmpldi r3,hcall_real_table_end - hcall_real_table bge guest_exit_cont LOAD_REG_ADDR(r4, hcall_real_table) - lwzx r3,r3,r4 + lwax r3,r3,r4 cmpwi r3,0 beq guest_exit_cont add r3,r3,r4 diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S index 48cbbf862958..17cfae5497a3 100644 --- a/arch/powerpc/kvm/book3s_interrupts.S +++ b/arch/powerpc/kvm/book3s_interrupts.S @@ -92,6 +92,11 @@ kvm_start_lightweight: PPC_LL r3, VCPU_HFLAGS(r4) rldicl r3, r3, 0, 63 /* r3 &= 1 */ stb r3, HSTATE_RESTORE_HID5(r13) + + /* Load up guest SPRG3 value, since it's user readable */ + ld r3, VCPU_SHARED(r4) + ld r3, VCPU_SHARED_SPRG3(r3) + mtspr SPRN_SPRG3, r3 #endif /* CONFIG_PPC_BOOK3S_64 */ PPC_LL r4, VCPU_SHADOW_MSR(r4) /* get shadow_msr */ @@ -123,6 +128,15 @@ kvmppc_handler_highmem: /* R7 = vcpu */ PPC_LL r7, GPR4(r1) +#ifdef CONFIG_PPC_BOOK3S_64 + /* + * Reload kernel SPRG3 value. + * No need to save guest value as usermode can't modify SPRG3. + */ + ld r3, PACA_SPRG3(r13) + mtspr SPRN_SPRG3, r3 +#endif /* CONFIG_PPC_BOOK3S_64 */ + PPC_STL r14, VCPU_GPR(R14)(r7) PPC_STL r15, VCPU_GPR(R15)(r7) PPC_STL r16, VCPU_GPR(R16)(r7) diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index c6e13d9a9e15..27db1e665959 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -468,7 +468,8 @@ void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr) * both the traditional FP registers and the added VSX * registers into thread.fpr[]. */ - giveup_fpu(current); + if (current->thread.regs->msr & MSR_FP) + giveup_fpu(current); for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) vcpu_fpr[i] = thread_fpr[get_fpr_index(i)]; @@ -483,7 +484,8 @@ void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr) #ifdef CONFIG_ALTIVEC if (msr & MSR_VEC) { - giveup_altivec(current); + if (current->thread.regs->msr & MSR_VEC) + giveup_altivec(current); memcpy(vcpu->arch.vr, t->vr, sizeof(vcpu->arch.vr)); vcpu->arch.vscr = t->vscr; } @@ -575,8 +577,6 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr, printk(KERN_INFO "Loading up ext 0x%lx\n", msr); #endif - current->thread.regs->msr |= msr; - if (msr & MSR_FP) { for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++) thread_fpr[get_fpr_index(i)] = vcpu_fpr[i]; @@ -598,12 +598,32 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr, #endif } + current->thread.regs->msr |= msr; vcpu->arch.guest_owned_ext |= msr; kvmppc_recalc_shadow_msr(vcpu); return RESUME_GUEST; } +/* + * Kernel code using FP or VMX could have flushed guest state to + * the thread_struct; if so, get it back now. + */ +static void kvmppc_handle_lost_ext(struct kvm_vcpu *vcpu) +{ + unsigned long lost_ext; + + lost_ext = vcpu->arch.guest_owned_ext & ~current->thread.regs->msr; + if (!lost_ext) + return; + + if (lost_ext & MSR_FP) + kvmppc_load_up_fpu(); + if (lost_ext & MSR_VEC) + kvmppc_load_up_altivec(); + current->thread.regs->msr |= lost_ext; +} + int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, unsigned int exit_nr) { @@ -772,7 +792,7 @@ program_interrupt: } case BOOK3S_INTERRUPT_SYSCALL: if (vcpu->arch.papr_enabled && - (kvmppc_get_last_inst(vcpu) == 0x44000022) && + (kvmppc_get_last_sc(vcpu) == 0x44000022) && !(vcpu->arch.shared->msr & MSR_PR)) { /* SC 1 papr hypercalls */ ulong cmd = kvmppc_get_gpr(vcpu, 3); @@ -890,8 +910,9 @@ program_interrupt: local_irq_enable(); r = s; } else { - kvmppc_lazy_ee_enable(); + kvmppc_fix_ee_before_entry(); } + kvmppc_handle_lost_ext(vcpu); } trace_kvm_book3s_reenter(r, vcpu); @@ -1162,7 +1183,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) if (vcpu->arch.shared->msr & MSR_FP) kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP); - kvmppc_lazy_ee_enable(); + kvmppc_fix_ee_before_entry(); ret = __kvmppc_vcpu_run(kvm_run, vcpu); diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c index 94c1dd46b83d..a3a5cb8ee7ea 100644 --- a/arch/powerpc/kvm/book3s_xics.c +++ b/arch/powerpc/kvm/book3s_xics.c @@ -19,6 +19,7 @@ #include <asm/hvcall.h> #include <asm/xics.h> #include <asm/debug.h> +#include <asm/time.h> #include <linux/debugfs.h> #include <linux/seq_file.h> diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c index dcc94f016007..17722d82f1d1 100644 --- a/arch/powerpc/kvm/booke.c +++ b/arch/powerpc/kvm/booke.c @@ -674,8 +674,6 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) goto out; } - kvm_guest_enter(); - #ifdef CONFIG_PPC_FPU /* Save userspace FPU state in stack */ enable_kernel_fp(); @@ -698,7 +696,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) kvmppc_load_guest_fp(vcpu); #endif - kvmppc_lazy_ee_enable(); + kvmppc_fix_ee_before_entry(); ret = __kvmppc_vcpu_run(kvm_run, vcpu); @@ -1168,7 +1166,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu, local_irq_enable(); r = (s << 2) | RESUME_HOST | (r & RESUME_FLAG_NV); } else { - kvmppc_lazy_ee_enable(); + kvmppc_fix_ee_before_entry(); } } diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index aca2e8f2e33f..07c0106fab76 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -117,8 +117,6 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu) kvm_guest_exit(); continue; } - - trace_hardirqs_on(); #endif kvm_guest_enter(); @@ -420,6 +418,10 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) return kvmppc_core_create_memslot(slot, npages); } +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_userspace_memory_region *mem, diff --git a/arch/powerpc/perf/power7-events-list.h b/arch/powerpc/perf/power7-events-list.h new file mode 100644 index 000000000000..687790a2c0b8 --- /dev/null +++ b/arch/powerpc/perf/power7-events-list.h @@ -0,0 +1,548 @@ +/* + * Performance counter support for POWER7 processors. + * + * Copyright 2013 Runzhen Wang, IBM Corporation. + * + * 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. + */ + +EVENT(PM_IC_DEMAND_L2_BR_ALL, 0x04898) +EVENT(PM_GCT_UTIL_7_TO_10_SLOTS, 0x020a0) +EVENT(PM_PMC2_SAVED, 0x10022) +EVENT(PM_CMPLU_STALL_DFU, 0x2003c) +EVENT(PM_VSU0_16FLOP, 0x0a0a4) +EVENT(PM_MRK_LSU_DERAT_MISS, 0x3d05a) +EVENT(PM_MRK_ST_CMPL, 0x10034) +EVENT(PM_NEST_PAIR3_ADD, 0x40881) +EVENT(PM_L2_ST_DISP, 0x46180) +EVENT(PM_L2_CASTOUT_MOD, 0x16180) +EVENT(PM_ISEG, 0x020a4) +EVENT(PM_MRK_INST_TIMEO, 0x40034) +EVENT(PM_L2_RCST_DISP_FAIL_ADDR, 0x36282) +EVENT(PM_LSU1_DC_PREF_STREAM_CONFIRM, 0x0d0b6) +EVENT(PM_IERAT_WR_64K, 0x040be) +EVENT(PM_MRK_DTLB_MISS_16M, 0x4d05e) +EVENT(PM_IERAT_MISS, 0x100f6) +EVENT(PM_MRK_PTEG_FROM_LMEM, 0x4d052) +EVENT(PM_FLOP, 0x100f4) +EVENT(PM_THRD_PRIO_4_5_CYC, 0x040b4) +EVENT(PM_BR_PRED_TA, 0x040aa) +EVENT(PM_CMPLU_STALL_FXU, 0x20014) +EVENT(PM_EXT_INT, 0x200f8) +EVENT(PM_VSU_FSQRT_FDIV, 0x0a888) +EVENT(PM_MRK_LD_MISS_EXPOSED_CYC, 0x1003e) +EVENT(PM_LSU1_LDF, 0x0c086) +EVENT(PM_IC_WRITE_ALL, 0x0488c) +EVENT(PM_LSU0_SRQ_STFWD, 0x0c0a0) +EVENT(PM_PTEG_FROM_RL2L3_MOD, 0x1c052) +EVENT(PM_MRK_DATA_FROM_L31_SHR, 0x1d04e) +EVENT(PM_DATA_FROM_L21_MOD, 0x3c046) +EVENT(PM_VSU1_SCAL_DOUBLE_ISSUED, 0x0b08a) +EVENT(PM_VSU0_8FLOP, 0x0a0a0) +EVENT(PM_POWER_EVENT1, 0x1006e) +EVENT(PM_DISP_CLB_HELD_BAL, 0x02092) +EVENT(PM_VSU1_2FLOP, 0x0a09a) +EVENT(PM_LWSYNC_HELD, 0x0209a) +EVENT(PM_PTEG_FROM_DL2L3_SHR, 0x3c054) +EVENT(PM_INST_FROM_L21_MOD, 0x34046) +EVENT(PM_IERAT_XLATE_WR_16MPLUS, 0x040bc) +EVENT(PM_IC_REQ_ALL, 0x04888) +EVENT(PM_DSLB_MISS, 0x0d090) +EVENT(PM_L3_MISS, 0x1f082) +EVENT(PM_LSU0_L1_PREF, 0x0d0b8) +EVENT(PM_VSU_SCALAR_SINGLE_ISSUED, 0x0b884) +EVENT(PM_LSU1_DC_PREF_STREAM_CONFIRM_STRIDE, 0x0d0be) +EVENT(PM_L2_INST, 0x36080) +EVENT(PM_VSU0_FRSP, 0x0a0b4) +EVENT(PM_FLUSH_DISP, 0x02082) +EVENT(PM_PTEG_FROM_L2MISS, 0x4c058) +EVENT(PM_VSU1_DQ_ISSUED, 0x0b09a) +EVENT(PM_CMPLU_STALL_LSU, 0x20012) +EVENT(PM_MRK_DATA_FROM_DMEM, 0x1d04a) +EVENT(PM_LSU_FLUSH_ULD, 0x0c8b0) +EVENT(PM_PTEG_FROM_LMEM, 0x4c052) +EVENT(PM_MRK_DERAT_MISS_16M, 0x3d05c) +EVENT(PM_THRD_ALL_RUN_CYC, 0x2000c) +EVENT(PM_MEM0_PREFETCH_DISP, 0x20083) +EVENT(PM_MRK_STALL_CMPLU_CYC_COUNT, 0x3003f) +EVENT(PM_DATA_FROM_DL2L3_MOD, 0x3c04c) +EVENT(PM_VSU_FRSP, 0x0a8b4) +EVENT(PM_MRK_DATA_FROM_L21_MOD, 0x3d046) +EVENT(PM_PMC1_OVERFLOW, 0x20010) +EVENT(PM_VSU0_SINGLE, 0x0a0a8) +EVENT(PM_MRK_PTEG_FROM_L3MISS, 0x2d058) +EVENT(PM_MRK_PTEG_FROM_L31_SHR, 0x2d056) +EVENT(PM_VSU0_VECTOR_SP_ISSUED, 0x0b090) +EVENT(PM_VSU1_FEST, 0x0a0ba) +EVENT(PM_MRK_INST_DISP, 0x20030) +EVENT(PM_VSU0_COMPLEX_ISSUED, 0x0b096) +EVENT(PM_LSU1_FLUSH_UST, 0x0c0b6) +EVENT(PM_INST_CMPL, 0x00002) +EVENT(PM_FXU_IDLE, 0x1000e) +EVENT(PM_LSU0_FLUSH_ULD, 0x0c0b0) +EVENT(PM_MRK_DATA_FROM_DL2L3_MOD, 0x3d04c) +EVENT(PM_LSU_LMQ_SRQ_EMPTY_ALL_CYC, 0x3001c) +EVENT(PM_LSU1_REJECT_LMQ_FULL, 0x0c0a6) +EVENT(PM_INST_PTEG_FROM_L21_MOD, 0x3e056) +EVENT(PM_INST_FROM_RL2L3_MOD, 0x14042) +EVENT(PM_SHL_CREATED, 0x05082) +EVENT(PM_L2_ST_HIT, 0x46182) +EVENT(PM_DATA_FROM_DMEM, 0x1c04a) +EVENT(PM_L3_LD_MISS, 0x2f082) +EVENT(PM_FXU1_BUSY_FXU0_IDLE, 0x4000e) +EVENT(PM_DISP_CLB_HELD_RES, 0x02094) +EVENT(PM_L2_SN_SX_I_DONE, 0x36382) +EVENT(PM_GRP_CMPL, 0x30004) +EVENT(PM_STCX_CMPL, 0x0c098) +EVENT(PM_VSU0_2FLOP, 0x0a098) +EVENT(PM_L3_PREF_MISS, 0x3f082) +EVENT(PM_LSU_SRQ_SYNC_CYC, 0x0d096) +EVENT(PM_LSU_REJECT_ERAT_MISS, 0x20064) +EVENT(PM_L1_ICACHE_MISS, 0x200fc) +EVENT(PM_LSU1_FLUSH_SRQ, 0x0c0be) +EVENT(PM_LD_REF_L1_LSU0, 0x0c080) +EVENT(PM_VSU0_FEST, 0x0a0b8) +EVENT(PM_VSU_VECTOR_SINGLE_ISSUED, 0x0b890) +EVENT(PM_FREQ_UP, 0x4000c) +EVENT(PM_DATA_FROM_LMEM, 0x3c04a) +EVENT(PM_LSU1_LDX, 0x0c08a) +EVENT(PM_PMC3_OVERFLOW, 0x40010) +EVENT(PM_MRK_BR_MPRED, 0x30036) +EVENT(PM_SHL_MATCH, 0x05086) +EVENT(PM_MRK_BR_TAKEN, 0x10036) +EVENT(PM_CMPLU_STALL_BRU, 0x4004e) +EVENT(PM_ISLB_MISS, 0x0d092) +EVENT(PM_CYC, 0x0001e) +EVENT(PM_DISP_HELD_THERMAL, 0x30006) +EVENT(PM_INST_PTEG_FROM_RL2L3_SHR, 0x2e054) +EVENT(PM_LSU1_SRQ_STFWD, 0x0c0a2) +EVENT(PM_GCT_NOSLOT_BR_MPRED, 0x4001a) +EVENT(PM_1PLUS_PPC_CMPL, 0x100f2) +EVENT(PM_PTEG_FROM_DMEM, 0x2c052) +EVENT(PM_VSU_2FLOP, 0x0a898) +EVENT(PM_GCT_FULL_CYC, 0x04086) +EVENT(PM_MRK_DATA_FROM_L3_CYC, 0x40020) +EVENT(PM_LSU_SRQ_S0_ALLOC, 0x0d09d) +EVENT(PM_MRK_DERAT_MISS_4K, 0x1d05c) +EVENT(PM_BR_MPRED_TA, 0x040ae) +EVENT(PM_INST_PTEG_FROM_L2MISS, 0x4e058) +EVENT(PM_DPU_HELD_POWER, 0x20006) +EVENT(PM_RUN_INST_CMPL, 0x400fa) +EVENT(PM_MRK_VSU_FIN, 0x30032) +EVENT(PM_LSU_SRQ_S0_VALID, 0x0d09c) +EVENT(PM_GCT_EMPTY_CYC, 0x20008) +EVENT(PM_IOPS_DISP, 0x30014) +EVENT(PM_RUN_SPURR, 0x10008) +EVENT(PM_PTEG_FROM_L21_MOD, 0x3c056) +EVENT(PM_VSU0_1FLOP, 0x0a080) +EVENT(PM_SNOOP_TLBIE, 0x0d0b2) +EVENT(PM_DATA_FROM_L3MISS, 0x2c048) +EVENT(PM_VSU_SINGLE, 0x0a8a8) +EVENT(PM_DTLB_MISS_16G, 0x1c05e) +EVENT(PM_CMPLU_STALL_VECTOR, 0x2001c) +EVENT(PM_FLUSH, 0x400f8) +EVENT(PM_L2_LD_HIT, 0x36182) +EVENT(PM_NEST_PAIR2_AND, 0x30883) +EVENT(PM_VSU1_1FLOP, 0x0a082) +EVENT(PM_IC_PREF_REQ, 0x0408a) +EVENT(PM_L3_LD_HIT, 0x2f080) +EVENT(PM_GCT_NOSLOT_IC_MISS, 0x2001a) +EVENT(PM_DISP_HELD, 0x10006) +EVENT(PM_L2_LD, 0x16080) +EVENT(PM_LSU_FLUSH_SRQ, 0x0c8bc) +EVENT(PM_BC_PLUS_8_CONV, 0x040b8) +EVENT(PM_MRK_DATA_FROM_L31_MOD_CYC, 0x40026) +EVENT(PM_CMPLU_STALL_VECTOR_LONG, 0x4004a) +EVENT(PM_L2_RCST_BUSY_RC_FULL, 0x26282) +EVENT(PM_TB_BIT_TRANS, 0x300f8) +EVENT(PM_THERMAL_MAX, 0x40006) +EVENT(PM_LSU1_FLUSH_ULD, 0x0c0b2) +EVENT(PM_LSU1_REJECT_LHS, 0x0c0ae) +EVENT(PM_LSU_LRQ_S0_ALLOC, 0x0d09f) +EVENT(PM_L3_CO_L31, 0x4f080) +EVENT(PM_POWER_EVENT4, 0x4006e) +EVENT(PM_DATA_FROM_L31_SHR, 0x1c04e) +EVENT(PM_BR_UNCOND, 0x0409e) +EVENT(PM_LSU1_DC_PREF_STREAM_ALLOC, 0x0d0aa) +EVENT(PM_PMC4_REWIND, 0x10020) +EVENT(PM_L2_RCLD_DISP, 0x16280) +EVENT(PM_THRD_PRIO_2_3_CYC, 0x040b2) +EVENT(PM_MRK_PTEG_FROM_L2MISS, 0x4d058) +EVENT(PM_IC_DEMAND_L2_BHT_REDIRECT, 0x04098) +EVENT(PM_LSU_DERAT_MISS, 0x200f6) +EVENT(PM_IC_PREF_CANCEL_L2, 0x04094) +EVENT(PM_MRK_FIN_STALL_CYC_COUNT, 0x1003d) +EVENT(PM_BR_PRED_CCACHE, 0x040a0) +EVENT(PM_GCT_UTIL_1_TO_2_SLOTS, 0x0209c) +EVENT(PM_MRK_ST_CMPL_INT, 0x30034) +EVENT(PM_LSU_TWO_TABLEWALK_CYC, 0x0d0a6) +EVENT(PM_MRK_DATA_FROM_L3MISS, 0x2d048) +EVENT(PM_GCT_NOSLOT_CYC, 0x100f8) +EVENT(PM_LSU_SET_MPRED, 0x0c0a8) +EVENT(PM_FLUSH_DISP_TLBIE, 0x0208a) +EVENT(PM_VSU1_FCONV, 0x0a0b2) +EVENT(PM_DERAT_MISS_16G, 0x4c05c) +EVENT(PM_INST_FROM_LMEM, 0x3404a) +EVENT(PM_IC_DEMAND_L2_BR_REDIRECT, 0x0409a) +EVENT(PM_CMPLU_STALL_SCALAR_LONG, 0x20018) +EVENT(PM_INST_PTEG_FROM_L2, 0x1e050) +EVENT(PM_PTEG_FROM_L2, 0x1c050) +EVENT(PM_MRK_DATA_FROM_L21_SHR_CYC, 0x20024) +EVENT(PM_MRK_DTLB_MISS_4K, 0x2d05a) +EVENT(PM_VSU0_FPSCR, 0x0b09c) +EVENT(PM_VSU1_VECT_DOUBLE_ISSUED, 0x0b082) +EVENT(PM_MRK_PTEG_FROM_RL2L3_MOD, 0x1d052) +EVENT(PM_MEM0_RQ_DISP, 0x10083) +EVENT(PM_L2_LD_MISS, 0x26080) +EVENT(PM_VMX_RESULT_SAT_1, 0x0b0a0) +EVENT(PM_L1_PREF, 0x0d8b8) +EVENT(PM_MRK_DATA_FROM_LMEM_CYC, 0x2002c) +EVENT(PM_GRP_IC_MISS_NONSPEC, 0x1000c) +EVENT(PM_PB_NODE_PUMP, 0x10081) +EVENT(PM_SHL_MERGED, 0x05084) +EVENT(PM_NEST_PAIR1_ADD, 0x20881) +EVENT(PM_DATA_FROM_L3, 0x1c048) +EVENT(PM_LSU_FLUSH, 0x0208e) +EVENT(PM_LSU_SRQ_SYNC_COUNT, 0x0d097) +EVENT(PM_PMC2_OVERFLOW, 0x30010) +EVENT(PM_LSU_LDF, 0x0c884) +EVENT(PM_POWER_EVENT3, 0x3006e) +EVENT(PM_DISP_WT, 0x30008) +EVENT(PM_CMPLU_STALL_REJECT, 0x40016) +EVENT(PM_IC_BANK_CONFLICT, 0x04082) +EVENT(PM_BR_MPRED_CR_TA, 0x048ae) +EVENT(PM_L2_INST_MISS, 0x36082) +EVENT(PM_CMPLU_STALL_ERAT_MISS, 0x40018) +EVENT(PM_NEST_PAIR2_ADD, 0x30881) +EVENT(PM_MRK_LSU_FLUSH, 0x0d08c) +EVENT(PM_L2_LDST, 0x16880) +EVENT(PM_INST_FROM_L31_SHR, 0x1404e) +EVENT(PM_VSU0_FIN, 0x0a0bc) +EVENT(PM_LARX_LSU, 0x0c894) +EVENT(PM_INST_FROM_RMEM, 0x34042) +EVENT(PM_DISP_CLB_HELD_TLBIE, 0x02096) +EVENT(PM_MRK_DATA_FROM_DMEM_CYC, 0x2002e) +EVENT(PM_BR_PRED_CR, 0x040a8) +EVENT(PM_LSU_REJECT, 0x10064) +EVENT(PM_GCT_UTIL_3_TO_6_SLOTS, 0x0209e) +EVENT(PM_CMPLU_STALL_END_GCT_NOSLOT, 0x10028) +EVENT(PM_LSU0_REJECT_LMQ_FULL, 0x0c0a4) +EVENT(PM_VSU_FEST, 0x0a8b8) +EVENT(PM_NEST_PAIR0_AND, 0x10883) +EVENT(PM_PTEG_FROM_L3, 0x2c050) +EVENT(PM_POWER_EVENT2, 0x2006e) +EVENT(PM_IC_PREF_CANCEL_PAGE, 0x04090) +EVENT(PM_VSU0_FSQRT_FDIV, 0x0a088) +EVENT(PM_MRK_GRP_CMPL, 0x40030) +EVENT(PM_VSU0_SCAL_DOUBLE_ISSUED, 0x0b088) +EVENT(PM_GRP_DISP, 0x3000a) +EVENT(PM_LSU0_LDX, 0x0c088) +EVENT(PM_DATA_FROM_L2, 0x1c040) +EVENT(PM_MRK_DATA_FROM_RL2L3_MOD, 0x1d042) +EVENT(PM_LD_REF_L1, 0x0c880) +EVENT(PM_VSU0_VECT_DOUBLE_ISSUED, 0x0b080) +EVENT(PM_VSU1_2FLOP_DOUBLE, 0x0a08e) +EVENT(PM_THRD_PRIO_6_7_CYC, 0x040b6) +EVENT(PM_BC_PLUS_8_RSLV_TAKEN, 0x040ba) +EVENT(PM_BR_MPRED_CR, 0x040ac) +EVENT(PM_L3_CO_MEM, 0x4f082) +EVENT(PM_LD_MISS_L1, 0x400f0) +EVENT(PM_DATA_FROM_RL2L3_MOD, 0x1c042) +EVENT(PM_LSU_SRQ_FULL_CYC, 0x1001a) +EVENT(PM_TABLEWALK_CYC, 0x10026) +EVENT(PM_MRK_PTEG_FROM_RMEM, 0x3d052) +EVENT(PM_LSU_SRQ_STFWD, 0x0c8a0) +EVENT(PM_INST_PTEG_FROM_RMEM, 0x3e052) +EVENT(PM_FXU0_FIN, 0x10004) +EVENT(PM_LSU1_L1_SW_PREF, 0x0c09e) +EVENT(PM_PTEG_FROM_L31_MOD, 0x1c054) +EVENT(PM_PMC5_OVERFLOW, 0x10024) +EVENT(PM_LD_REF_L1_LSU1, 0x0c082) +EVENT(PM_INST_PTEG_FROM_L21_SHR, 0x4e056) +EVENT(PM_CMPLU_STALL_THRD, 0x1001c) +EVENT(PM_DATA_FROM_RMEM, 0x3c042) +EVENT(PM_VSU0_SCAL_SINGLE_ISSUED, 0x0b084) +EVENT(PM_BR_MPRED_LSTACK, 0x040a6) +EVENT(PM_MRK_DATA_FROM_RL2L3_MOD_CYC, 0x40028) +EVENT(PM_LSU0_FLUSH_UST, 0x0c0b4) +EVENT(PM_LSU_NCST, 0x0c090) +EVENT(PM_BR_TAKEN, 0x20004) +EVENT(PM_INST_PTEG_FROM_LMEM, 0x4e052) +EVENT(PM_GCT_NOSLOT_BR_MPRED_IC_MISS, 0x4001c) +EVENT(PM_DTLB_MISS_4K, 0x2c05a) +EVENT(PM_PMC4_SAVED, 0x30022) +EVENT(PM_VSU1_PERMUTE_ISSUED, 0x0b092) +EVENT(PM_SLB_MISS, 0x0d890) +EVENT(PM_LSU1_FLUSH_LRQ, 0x0c0ba) +EVENT(PM_DTLB_MISS, 0x300fc) +EVENT(PM_VSU1_FRSP, 0x0a0b6) +EVENT(PM_VSU_VECTOR_DOUBLE_ISSUED, 0x0b880) +EVENT(PM_L2_CASTOUT_SHR, 0x16182) +EVENT(PM_DATA_FROM_DL2L3_SHR, 0x3c044) +EVENT(PM_VSU1_STF, 0x0b08e) +EVENT(PM_ST_FIN, 0x200f0) +EVENT(PM_PTEG_FROM_L21_SHR, 0x4c056) +EVENT(PM_L2_LOC_GUESS_WRONG, 0x26480) +EVENT(PM_MRK_STCX_FAIL, 0x0d08e) +EVENT(PM_LSU0_REJECT_LHS, 0x0c0ac) +EVENT(PM_IC_PREF_CANCEL_HIT, 0x04092) +EVENT(PM_L3_PREF_BUSY, 0x4f080) +EVENT(PM_MRK_BRU_FIN, 0x2003a) +EVENT(PM_LSU1_NCLD, 0x0c08e) +EVENT(PM_INST_PTEG_FROM_L31_MOD, 0x1e054) +EVENT(PM_LSU_NCLD, 0x0c88c) +EVENT(PM_LSU_LDX, 0x0c888) +EVENT(PM_L2_LOC_GUESS_CORRECT, 0x16480) +EVENT(PM_THRESH_TIMEO, 0x10038) +EVENT(PM_L3_PREF_ST, 0x0d0ae) +EVENT(PM_DISP_CLB_HELD_SYNC, 0x02098) +EVENT(PM_VSU_SIMPLE_ISSUED, 0x0b894) +EVENT(PM_VSU1_SINGLE, 0x0a0aa) +EVENT(PM_DATA_TABLEWALK_CYC, 0x3001a) +EVENT(PM_L2_RC_ST_DONE, 0x36380) +EVENT(PM_MRK_PTEG_FROM_L21_MOD, 0x3d056) +EVENT(PM_LARX_LSU1, 0x0c096) +EVENT(PM_MRK_DATA_FROM_RMEM, 0x3d042) +EVENT(PM_DISP_CLB_HELD, 0x02090) +EVENT(PM_DERAT_MISS_4K, 0x1c05c) +EVENT(PM_L2_RCLD_DISP_FAIL_ADDR, 0x16282) +EVENT(PM_SEG_EXCEPTION, 0x028a4) +EVENT(PM_FLUSH_DISP_SB, 0x0208c) +EVENT(PM_L2_DC_INV, 0x26182) +EVENT(PM_PTEG_FROM_DL2L3_MOD, 0x4c054) +EVENT(PM_DSEG, 0x020a6) +EVENT(PM_BR_PRED_LSTACK, 0x040a2) +EVENT(PM_VSU0_STF, 0x0b08c) +EVENT(PM_LSU_FX_FIN, 0x10066) +EVENT(PM_DERAT_MISS_16M, 0x3c05c) +EVENT(PM_MRK_PTEG_FROM_DL2L3_MOD, 0x4d054) +EVENT(PM_GCT_UTIL_11_PLUS_SLOTS, 0x020a2) +EVENT(PM_INST_FROM_L3, 0x14048) +EVENT(PM_MRK_IFU_FIN, 0x3003a) +EVENT(PM_ITLB_MISS, 0x400fc) +EVENT(PM_VSU_STF, 0x0b88c) +EVENT(PM_LSU_FLUSH_UST, 0x0c8b4) +EVENT(PM_L2_LDST_MISS, 0x26880) +EVENT(PM_FXU1_FIN, 0x40004) +EVENT(PM_SHL_DEALLOCATED, 0x05080) +EVENT(PM_L2_SN_M_WR_DONE, 0x46382) +EVENT(PM_LSU_REJECT_SET_MPRED, 0x0c8a8) +EVENT(PM_L3_PREF_LD, 0x0d0ac) +EVENT(PM_L2_SN_M_RD_DONE, 0x46380) +EVENT(PM_MRK_DERAT_MISS_16G, 0x4d05c) +EVENT(PM_VSU_FCONV, 0x0a8b0) +EVENT(PM_ANY_THRD_RUN_CYC, 0x100fa) +EVENT(PM_LSU_LMQ_FULL_CYC, 0x0d0a4) +EVENT(PM_MRK_LSU_REJECT_LHS, 0x0d082) +EVENT(PM_MRK_LD_MISS_L1_CYC, 0x4003e) +EVENT(PM_MRK_DATA_FROM_L2_CYC, 0x20020) +EVENT(PM_INST_IMC_MATCH_DISP, 0x30016) +EVENT(PM_MRK_DATA_FROM_RMEM_CYC, 0x4002c) +EVENT(PM_VSU0_SIMPLE_ISSUED, 0x0b094) +EVENT(PM_CMPLU_STALL_DIV, 0x40014) +EVENT(PM_MRK_PTEG_FROM_RL2L3_SHR, 0x2d054) +EVENT(PM_VSU_FMA_DOUBLE, 0x0a890) +EVENT(PM_VSU_4FLOP, 0x0a89c) +EVENT(PM_VSU1_FIN, 0x0a0be) +EVENT(PM_NEST_PAIR1_AND, 0x20883) +EVENT(PM_INST_PTEG_FROM_RL2L3_MOD, 0x1e052) +EVENT(PM_RUN_CYC, 0x200f4) +EVENT(PM_PTEG_FROM_RMEM, 0x3c052) +EVENT(PM_LSU_LRQ_S0_VALID, 0x0d09e) +EVENT(PM_LSU0_LDF, 0x0c084) +EVENT(PM_FLUSH_COMPLETION, 0x30012) +EVENT(PM_ST_MISS_L1, 0x300f0) +EVENT(PM_L2_NODE_PUMP, 0x36480) +EVENT(PM_INST_FROM_DL2L3_SHR, 0x34044) +EVENT(PM_MRK_STALL_CMPLU_CYC, 0x3003e) +EVENT(PM_VSU1_DENORM, 0x0a0ae) +EVENT(PM_MRK_DATA_FROM_L31_SHR_CYC, 0x20026) +EVENT(PM_NEST_PAIR0_ADD, 0x10881) +EVENT(PM_INST_FROM_L3MISS, 0x24048) +EVENT(PM_EE_OFF_EXT_INT, 0x02080) +EVENT(PM_INST_PTEG_FROM_DMEM, 0x2e052) +EVENT(PM_INST_FROM_DL2L3_MOD, 0x3404c) +EVENT(PM_PMC6_OVERFLOW, 0x30024) +EVENT(PM_VSU_2FLOP_DOUBLE, 0x0a88c) +EVENT(PM_TLB_MISS, 0x20066) +EVENT(PM_FXU_BUSY, 0x2000e) +EVENT(PM_L2_RCLD_DISP_FAIL_OTHER, 0x26280) +EVENT(PM_LSU_REJECT_LMQ_FULL, 0x0c8a4) +EVENT(PM_IC_RELOAD_SHR, 0x04096) +EVENT(PM_GRP_MRK, 0x10031) +EVENT(PM_MRK_ST_NEST, 0x20034) +EVENT(PM_VSU1_FSQRT_FDIV, 0x0a08a) +EVENT(PM_LSU0_FLUSH_LRQ, 0x0c0b8) +EVENT(PM_LARX_LSU0, 0x0c094) +EVENT(PM_IBUF_FULL_CYC, 0x04084) +EVENT(PM_MRK_DATA_FROM_DL2L3_SHR_CYC, 0x2002a) +EVENT(PM_LSU_DC_PREF_STREAM_ALLOC, 0x0d8a8) +EVENT(PM_GRP_MRK_CYC, 0x10030) +EVENT(PM_MRK_DATA_FROM_RL2L3_SHR_CYC, 0x20028) +EVENT(PM_L2_GLOB_GUESS_CORRECT, 0x16482) +EVENT(PM_LSU_REJECT_LHS, 0x0c8ac) +EVENT(PM_MRK_DATA_FROM_LMEM, 0x3d04a) +EVENT(PM_INST_PTEG_FROM_L3, 0x2e050) +EVENT(PM_FREQ_DOWN, 0x3000c) +EVENT(PM_PB_RETRY_NODE_PUMP, 0x30081) +EVENT(PM_INST_FROM_RL2L3_SHR, 0x1404c) +EVENT(PM_MRK_INST_ISSUED, 0x10032) +EVENT(PM_PTEG_FROM_L3MISS, 0x2c058) +EVENT(PM_RUN_PURR, 0x400f4) +EVENT(PM_MRK_GRP_IC_MISS, 0x40038) +EVENT(PM_MRK_DATA_FROM_L3, 0x1d048) +EVENT(PM_CMPLU_STALL_DCACHE_MISS, 0x20016) +EVENT(PM_PTEG_FROM_RL2L3_SHR, 0x2c054) +EVENT(PM_LSU_FLUSH_LRQ, 0x0c8b8) +EVENT(PM_MRK_DERAT_MISS_64K, 0x2d05c) +EVENT(PM_INST_PTEG_FROM_DL2L3_MOD, 0x4e054) +EVENT(PM_L2_ST_MISS, 0x26082) +EVENT(PM_MRK_PTEG_FROM_L21_SHR, 0x4d056) +EVENT(PM_LWSYNC, 0x0d094) +EVENT(PM_LSU0_DC_PREF_STREAM_CONFIRM_STRIDE, 0x0d0bc) +EVENT(PM_MRK_LSU_FLUSH_LRQ, 0x0d088) +EVENT(PM_INST_IMC_MATCH_CMPL, 0x100f0) +EVENT(PM_NEST_PAIR3_AND, 0x40883) +EVENT(PM_PB_RETRY_SYS_PUMP, 0x40081) +EVENT(PM_MRK_INST_FIN, 0x30030) +EVENT(PM_MRK_PTEG_FROM_DL2L3_SHR, 0x3d054) +EVENT(PM_INST_FROM_L31_MOD, 0x14044) +EVENT(PM_MRK_DTLB_MISS_64K, 0x3d05e) +EVENT(PM_LSU_FIN, 0x30066) +EVENT(PM_MRK_LSU_REJECT, 0x40064) +EVENT(PM_L2_CO_FAIL_BUSY, 0x16382) +EVENT(PM_MEM0_WQ_DISP, 0x40083) +EVENT(PM_DATA_FROM_L31_MOD, 0x1c044) +EVENT(PM_THERMAL_WARN, 0x10016) +EVENT(PM_VSU0_4FLOP, 0x0a09c) +EVENT(PM_BR_MPRED_CCACHE, 0x040a4) +EVENT(PM_CMPLU_STALL_IFU, 0x4004c) +EVENT(PM_L1_DEMAND_WRITE, 0x0408c) +EVENT(PM_FLUSH_BR_MPRED, 0x02084) +EVENT(PM_MRK_DTLB_MISS_16G, 0x1d05e) +EVENT(PM_MRK_PTEG_FROM_DMEM, 0x2d052) +EVENT(PM_L2_RCST_DISP, 0x36280) +EVENT(PM_CMPLU_STALL, 0x4000a) +EVENT(PM_LSU_PARTIAL_CDF, 0x0c0aa) +EVENT(PM_DISP_CLB_HELD_SB, 0x020a8) +EVENT(PM_VSU0_FMA_DOUBLE, 0x0a090) +EVENT(PM_FXU0_BUSY_FXU1_IDLE, 0x3000e) +EVENT(PM_IC_DEMAND_CYC, 0x10018) +EVENT(PM_MRK_DATA_FROM_L21_SHR, 0x3d04e) +EVENT(PM_MRK_LSU_FLUSH_UST, 0x0d086) +EVENT(PM_INST_PTEG_FROM_L3MISS, 0x2e058) +EVENT(PM_VSU_DENORM, 0x0a8ac) +EVENT(PM_MRK_LSU_PARTIAL_CDF, 0x0d080) +EVENT(PM_INST_FROM_L21_SHR, 0x3404e) +EVENT(PM_IC_PREF_WRITE, 0x0408e) +EVENT(PM_BR_PRED, 0x0409c) +EVENT(PM_INST_FROM_DMEM, 0x1404a) +EVENT(PM_IC_PREF_CANCEL_ALL, 0x04890) +EVENT(PM_LSU_DC_PREF_STREAM_CONFIRM, 0x0d8b4) +EVENT(PM_MRK_LSU_FLUSH_SRQ, 0x0d08a) +EVENT(PM_MRK_FIN_STALL_CYC, 0x1003c) +EVENT(PM_L2_RCST_DISP_FAIL_OTHER, 0x46280) +EVENT(PM_VSU1_DD_ISSUED, 0x0b098) +EVENT(PM_PTEG_FROM_L31_SHR, 0x2c056) +EVENT(PM_DATA_FROM_L21_SHR, 0x3c04e) +EVENT(PM_LSU0_NCLD, 0x0c08c) +EVENT(PM_VSU1_4FLOP, 0x0a09e) +EVENT(PM_VSU1_8FLOP, 0x0a0a2) +EVENT(PM_VSU_8FLOP, 0x0a8a0) +EVENT(PM_LSU_LMQ_SRQ_EMPTY_CYC, 0x2003e) +EVENT(PM_DTLB_MISS_64K, 0x3c05e) +EVENT(PM_THRD_CONC_RUN_INST, 0x300f4) +EVENT(PM_MRK_PTEG_FROM_L2, 0x1d050) +EVENT(PM_PB_SYS_PUMP, 0x20081) +EVENT(PM_VSU_FIN, 0x0a8bc) +EVENT(PM_MRK_DATA_FROM_L31_MOD, 0x1d044) +EVENT(PM_THRD_PRIO_0_1_CYC, 0x040b0) +EVENT(PM_DERAT_MISS_64K, 0x2c05c) +EVENT(PM_PMC2_REWIND, 0x30020) +EVENT(PM_INST_FROM_L2, 0x14040) +EVENT(PM_GRP_BR_MPRED_NONSPEC, 0x1000a) +EVENT(PM_INST_DISP, 0x200f2) +EVENT(PM_MEM0_RD_CANCEL_TOTAL, 0x30083) +EVENT(PM_LSU0_DC_PREF_STREAM_CONFIRM, 0x0d0b4) +EVENT(PM_L1_DCACHE_RELOAD_VALID, 0x300f6) +EVENT(PM_VSU_SCALAR_DOUBLE_ISSUED, 0x0b888) +EVENT(PM_L3_PREF_HIT, 0x3f080) +EVENT(PM_MRK_PTEG_FROM_L31_MOD, 0x1d054) +EVENT(PM_CMPLU_STALL_STORE, 0x2004a) +EVENT(PM_MRK_FXU_FIN, 0x20038) +EVENT(PM_PMC4_OVERFLOW, 0x10010) +EVENT(PM_MRK_PTEG_FROM_L3, 0x2d050) +EVENT(PM_LSU0_LMQ_LHR_MERGE, 0x0d098) +EVENT(PM_BTAC_HIT, 0x0508a) +EVENT(PM_L3_RD_BUSY, 0x4f082) +EVENT(PM_LSU0_L1_SW_PREF, 0x0c09c) +EVENT(PM_INST_FROM_L2MISS, 0x44048) +EVENT(PM_LSU0_DC_PREF_STREAM_ALLOC, 0x0d0a8) +EVENT(PM_L2_ST, 0x16082) +EVENT(PM_VSU0_DENORM, 0x0a0ac) +EVENT(PM_MRK_DATA_FROM_DL2L3_SHR, 0x3d044) +EVENT(PM_BR_PRED_CR_TA, 0x048aa) +EVENT(PM_VSU0_FCONV, 0x0a0b0) +EVENT(PM_MRK_LSU_FLUSH_ULD, 0x0d084) +EVENT(PM_BTAC_MISS, 0x05088) +EVENT(PM_MRK_LD_MISS_EXPOSED_CYC_COUNT, 0x1003f) +EVENT(PM_MRK_DATA_FROM_L2, 0x1d040) +EVENT(PM_LSU_DCACHE_RELOAD_VALID, 0x0d0a2) +EVENT(PM_VSU_FMA, 0x0a884) +EVENT(PM_LSU0_FLUSH_SRQ, 0x0c0bc) +EVENT(PM_LSU1_L1_PREF, 0x0d0ba) +EVENT(PM_IOPS_CMPL, 0x10014) +EVENT(PM_L2_SYS_PUMP, 0x36482) +EVENT(PM_L2_RCLD_BUSY_RC_FULL, 0x46282) +EVENT(PM_LSU_LMQ_S0_ALLOC, 0x0d0a1) +EVENT(PM_FLUSH_DISP_SYNC, 0x02088) +EVENT(PM_MRK_DATA_FROM_DL2L3_MOD_CYC, 0x4002a) +EVENT(PM_L2_IC_INV, 0x26180) +EVENT(PM_MRK_DATA_FROM_L21_MOD_CYC, 0x40024) +EVENT(PM_L3_PREF_LDST, 0x0d8ac) +EVENT(PM_LSU_SRQ_EMPTY_CYC, 0x40008) +EVENT(PM_LSU_LMQ_S0_VALID, 0x0d0a0) +EVENT(PM_FLUSH_PARTIAL, 0x02086) +EVENT(PM_VSU1_FMA_DOUBLE, 0x0a092) +EVENT(PM_1PLUS_PPC_DISP, 0x400f2) +EVENT(PM_DATA_FROM_L2MISS, 0x200fe) +EVENT(PM_SUSPENDED, 0x00000) +EVENT(PM_VSU0_FMA, 0x0a084) +EVENT(PM_CMPLU_STALL_SCALAR, 0x40012) +EVENT(PM_STCX_FAIL, 0x0c09a) +EVENT(PM_VSU0_FSQRT_FDIV_DOUBLE, 0x0a094) +EVENT(PM_DC_PREF_DST, 0x0d0b0) +EVENT(PM_VSU1_SCAL_SINGLE_ISSUED, 0x0b086) +EVENT(PM_L3_HIT, 0x1f080) +EVENT(PM_L2_GLOB_GUESS_WRONG, 0x26482) +EVENT(PM_MRK_DFU_FIN, 0x20032) +EVENT(PM_INST_FROM_L1, 0x04080) +EVENT(PM_BRU_FIN, 0x10068) +EVENT(PM_IC_DEMAND_REQ, 0x04088) +EVENT(PM_VSU1_FSQRT_FDIV_DOUBLE, 0x0a096) +EVENT(PM_VSU1_FMA, 0x0a086) +EVENT(PM_MRK_LD_MISS_L1, 0x20036) +EVENT(PM_VSU0_2FLOP_DOUBLE, 0x0a08c) +EVENT(PM_LSU_DC_PREF_STRIDED_STREAM_CONFIRM, 0x0d8bc) +EVENT(PM_INST_PTEG_FROM_L31_SHR, 0x2e056) +EVENT(PM_MRK_LSU_REJECT_ERAT_MISS, 0x30064) +EVENT(PM_MRK_DATA_FROM_L2MISS, 0x4d048) +EVENT(PM_DATA_FROM_RL2L3_SHR, 0x1c04c) +EVENT(PM_INST_FROM_PREF, 0x14046) +EVENT(PM_VSU1_SQ, 0x0b09e) +EVENT(PM_L2_LD_DISP, 0x36180) +EVENT(PM_L2_DISP_ALL, 0x46080) +EVENT(PM_THRD_GRP_CMPL_BOTH_CYC, 0x10012) +EVENT(PM_VSU_FSQRT_FDIV_DOUBLE, 0x0a894) +EVENT(PM_BR_MPRED, 0x400f6) +EVENT(PM_INST_PTEG_FROM_DL2L3_SHR, 0x3e054) +EVENT(PM_VSU_1FLOP, 0x0a880) +EVENT(PM_HV_CYC, 0x2000a) +EVENT(PM_MRK_LSU_FIN, 0x40032) +EVENT(PM_MRK_DATA_FROM_RL2L3_SHR, 0x1d04c) +EVENT(PM_DTLB_MISS_16M, 0x4c05e) +EVENT(PM_LSU1_LMQ_LHR_MERGE, 0x0d09a) +EVENT(PM_IFU_FIN, 0x40066) diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c index d1821b8bbc4c..56c67bca2f75 100644 --- a/arch/powerpc/perf/power7-pmu.c +++ b/arch/powerpc/perf/power7-pmu.c @@ -53,37 +53,13 @@ /* * Power7 event codes. */ -#define PME_PM_CYC 0x1e -#define PME_PM_GCT_NOSLOT_CYC 0x100f8 -#define PME_PM_CMPLU_STALL 0x4000a -#define PME_PM_INST_CMPL 0x2 -#define PME_PM_LD_REF_L1 0xc880 -#define PME_PM_LD_MISS_L1 0x400f0 -#define PME_PM_BRU_FIN 0x10068 -#define PME_PM_BR_MPRED 0x400f6 - -#define PME_PM_CMPLU_STALL_FXU 0x20014 -#define PME_PM_CMPLU_STALL_DIV 0x40014 -#define PME_PM_CMPLU_STALL_SCALAR 0x40012 -#define PME_PM_CMPLU_STALL_SCALAR_LONG 0x20018 -#define PME_PM_CMPLU_STALL_VECTOR 0x2001c -#define PME_PM_CMPLU_STALL_VECTOR_LONG 0x4004a -#define PME_PM_CMPLU_STALL_LSU 0x20012 -#define PME_PM_CMPLU_STALL_REJECT 0x40016 -#define PME_PM_CMPLU_STALL_ERAT_MISS 0x40018 -#define PME_PM_CMPLU_STALL_DCACHE_MISS 0x20016 -#define PME_PM_CMPLU_STALL_STORE 0x2004a -#define PME_PM_CMPLU_STALL_THRD 0x1001c -#define PME_PM_CMPLU_STALL_IFU 0x4004c -#define PME_PM_CMPLU_STALL_BRU 0x4004e -#define PME_PM_GCT_NOSLOT_IC_MISS 0x2001a -#define PME_PM_GCT_NOSLOT_BR_MPRED 0x4001a -#define PME_PM_GCT_NOSLOT_BR_MPRED_IC_MISS 0x4001c -#define PME_PM_GRP_CMPL 0x30004 -#define PME_PM_1PLUS_PPC_CMPL 0x100f2 -#define PME_PM_CMPLU_STALL_DFU 0x2003c -#define PME_PM_RUN_CYC 0x200f4 -#define PME_PM_RUN_INST_CMPL 0x400fa +#define EVENT(_name, _code) \ + PME_##_name = _code, + +enum { +#include "power7-events-list.h" +}; +#undef EVENT /* * Layout of constraint bits: @@ -398,96 +374,36 @@ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = { }; -GENERIC_EVENT_ATTR(cpu-cycles, CYC); -GENERIC_EVENT_ATTR(stalled-cycles-frontend, GCT_NOSLOT_CYC); -GENERIC_EVENT_ATTR(stalled-cycles-backend, CMPLU_STALL); -GENERIC_EVENT_ATTR(instructions, INST_CMPL); -GENERIC_EVENT_ATTR(cache-references, LD_REF_L1); -GENERIC_EVENT_ATTR(cache-misses, LD_MISS_L1); -GENERIC_EVENT_ATTR(branch-instructions, BRU_FIN); -GENERIC_EVENT_ATTR(branch-misses, BR_MPRED); - -POWER_EVENT_ATTR(CYC, CYC); -POWER_EVENT_ATTR(GCT_NOSLOT_CYC, GCT_NOSLOT_CYC); -POWER_EVENT_ATTR(CMPLU_STALL, CMPLU_STALL); -POWER_EVENT_ATTR(INST_CMPL, INST_CMPL); -POWER_EVENT_ATTR(LD_REF_L1, LD_REF_L1); -POWER_EVENT_ATTR(LD_MISS_L1, LD_MISS_L1); -POWER_EVENT_ATTR(BRU_FIN, BRU_FIN) -POWER_EVENT_ATTR(BR_MPRED, BR_MPRED); - -POWER_EVENT_ATTR(CMPLU_STALL_FXU, CMPLU_STALL_FXU); -POWER_EVENT_ATTR(CMPLU_STALL_DIV, CMPLU_STALL_DIV); -POWER_EVENT_ATTR(CMPLU_STALL_SCALAR, CMPLU_STALL_SCALAR); -POWER_EVENT_ATTR(CMPLU_STALL_SCALAR_LONG, CMPLU_STALL_SCALAR_LONG); -POWER_EVENT_ATTR(CMPLU_STALL_VECTOR, CMPLU_STALL_VECTOR); -POWER_EVENT_ATTR(CMPLU_STALL_VECTOR_LONG, CMPLU_STALL_VECTOR_LONG); -POWER_EVENT_ATTR(CMPLU_STALL_LSU, CMPLU_STALL_LSU); -POWER_EVENT_ATTR(CMPLU_STALL_REJECT, CMPLU_STALL_REJECT); - -POWER_EVENT_ATTR(CMPLU_STALL_ERAT_MISS, CMPLU_STALL_ERAT_MISS); -POWER_EVENT_ATTR(CMPLU_STALL_DCACHE_MISS, CMPLU_STALL_DCACHE_MISS); -POWER_EVENT_ATTR(CMPLU_STALL_STORE, CMPLU_STALL_STORE); -POWER_EVENT_ATTR(CMPLU_STALL_THRD, CMPLU_STALL_THRD); -POWER_EVENT_ATTR(CMPLU_STALL_IFU, CMPLU_STALL_IFU); -POWER_EVENT_ATTR(CMPLU_STALL_BRU, CMPLU_STALL_BRU); -POWER_EVENT_ATTR(GCT_NOSLOT_IC_MISS, GCT_NOSLOT_IC_MISS); - -POWER_EVENT_ATTR(GCT_NOSLOT_BR_MPRED, GCT_NOSLOT_BR_MPRED); -POWER_EVENT_ATTR(GCT_NOSLOT_BR_MPRED_IC_MISS, GCT_NOSLOT_BR_MPRED_IC_MISS); -POWER_EVENT_ATTR(GRP_CMPL, GRP_CMPL); -POWER_EVENT_ATTR(1PLUS_PPC_CMPL, 1PLUS_PPC_CMPL); -POWER_EVENT_ATTR(CMPLU_STALL_DFU, CMPLU_STALL_DFU); -POWER_EVENT_ATTR(RUN_CYC, RUN_CYC); -POWER_EVENT_ATTR(RUN_INST_CMPL, RUN_INST_CMPL); +GENERIC_EVENT_ATTR(cpu-cycles, PM_CYC); +GENERIC_EVENT_ATTR(stalled-cycles-frontend, PM_GCT_NOSLOT_CYC); +GENERIC_EVENT_ATTR(stalled-cycles-backend, PM_CMPLU_STALL); +GENERIC_EVENT_ATTR(instructions, PM_INST_CMPL); +GENERIC_EVENT_ATTR(cache-references, PM_LD_REF_L1); +GENERIC_EVENT_ATTR(cache-misses, PM_LD_MISS_L1); +GENERIC_EVENT_ATTR(branch-instructions, PM_BRU_FIN); +GENERIC_EVENT_ATTR(branch-misses, PM_BR_MPRED); + +#define EVENT(_name, _code) POWER_EVENT_ATTR(_name, _name); +#include "power7-events-list.h" +#undef EVENT + +#define EVENT(_name, _code) POWER_EVENT_PTR(_name), static struct attribute *power7_events_attr[] = { - GENERIC_EVENT_PTR(CYC), - GENERIC_EVENT_PTR(GCT_NOSLOT_CYC), - GENERIC_EVENT_PTR(CMPLU_STALL), - GENERIC_EVENT_PTR(INST_CMPL), - GENERIC_EVENT_PTR(LD_REF_L1), - GENERIC_EVENT_PTR(LD_MISS_L1), - GENERIC_EVENT_PTR(BRU_FIN), - GENERIC_EVENT_PTR(BR_MPRED), - - POWER_EVENT_PTR(CYC), - POWER_EVENT_PTR(GCT_NOSLOT_CYC), - POWER_EVENT_PTR(CMPLU_STALL), - POWER_EVENT_PTR(INST_CMPL), - POWER_EVENT_PTR(LD_REF_L1), - POWER_EVENT_PTR(LD_MISS_L1), - POWER_EVENT_PTR(BRU_FIN), - POWER_EVENT_PTR(BR_MPRED), - - POWER_EVENT_PTR(CMPLU_STALL_FXU), - POWER_EVENT_PTR(CMPLU_STALL_DIV), - POWER_EVENT_PTR(CMPLU_STALL_SCALAR), - POWER_EVENT_PTR(CMPLU_STALL_SCALAR_LONG), - POWER_EVENT_PTR(CMPLU_STALL_VECTOR), - POWER_EVENT_PTR(CMPLU_STALL_VECTOR_LONG), - POWER_EVENT_PTR(CMPLU_STALL_LSU), - POWER_EVENT_PTR(CMPLU_STALL_REJECT), - - POWER_EVENT_PTR(CMPLU_STALL_ERAT_MISS), - POWER_EVENT_PTR(CMPLU_STALL_DCACHE_MISS), - POWER_EVENT_PTR(CMPLU_STALL_STORE), - POWER_EVENT_PTR(CMPLU_STALL_THRD), - POWER_EVENT_PTR(CMPLU_STALL_IFU), - POWER_EVENT_PTR(CMPLU_STALL_BRU), - POWER_EVENT_PTR(GCT_NOSLOT_IC_MISS), - POWER_EVENT_PTR(GCT_NOSLOT_BR_MPRED), - - POWER_EVENT_PTR(GCT_NOSLOT_BR_MPRED_IC_MISS), - POWER_EVENT_PTR(GRP_CMPL), - POWER_EVENT_PTR(1PLUS_PPC_CMPL), - POWER_EVENT_PTR(CMPLU_STALL_DFU), - POWER_EVENT_PTR(RUN_CYC), - POWER_EVENT_PTR(RUN_INST_CMPL), + GENERIC_EVENT_PTR(PM_CYC), + GENERIC_EVENT_PTR(PM_GCT_NOSLOT_CYC), + GENERIC_EVENT_PTR(PM_CMPLU_STALL), + GENERIC_EVENT_PTR(PM_INST_CMPL), + GENERIC_EVENT_PTR(PM_LD_REF_L1), + GENERIC_EVENT_PTR(PM_LD_MISS_L1), + GENERIC_EVENT_PTR(PM_BRU_FIN), + GENERIC_EVENT_PTR(PM_BR_MPRED), + + #include "power7-events-list.h" + #undef EVENT NULL }; - static struct attribute_group power7_pmu_events_group = { .name = "events", .attrs = power7_events_attr, diff --git a/arch/powerpc/platforms/ps3/time.c b/arch/powerpc/platforms/ps3/time.c index cba1e6be68e5..ce73ce865613 100644 --- a/arch/powerpc/platforms/ps3/time.c +++ b/arch/powerpc/platforms/ps3/time.c @@ -90,7 +90,7 @@ static int __init ps3_rtc_init(void) pdev = platform_device_register_simple("rtc-ps3", -1, NULL, 0); - return PTR_RET(pdev); + return PTR_ERR_OR_ZERO(pdev); } module_init(ps3_rtc_init); diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c index 6a5f2b1f32ca..d276cd3edd8f 100644 --- a/arch/powerpc/platforms/pseries/nvram.c +++ b/arch/powerpc/platforms/pseries/nvram.c @@ -539,36 +539,6 @@ static int zip_oops(size_t text_len) } #ifdef CONFIG_PSTORE -/* Derived from logfs_uncompress */ -int nvram_decompress(void *in, void *out, size_t inlen, size_t outlen) -{ - int err, ret; - - ret = -EIO; - err = zlib_inflateInit(&stream); - if (err != Z_OK) - goto error; - - stream.next_in = in; - stream.avail_in = inlen; - stream.total_in = 0; - stream.next_out = out; - stream.avail_out = outlen; - stream.total_out = 0; - - err = zlib_inflate(&stream, Z_FINISH); - if (err != Z_STREAM_END) - goto error; - - err = zlib_inflateEnd(&stream); - if (err != Z_OK) - goto error; - - ret = stream.total_out; -error: - return ret; -} - static int nvram_pstore_open(struct pstore_info *psi) { /* Reset the iterator to start reading partitions again */ @@ -584,7 +554,7 @@ static int nvram_pstore_open(struct pstore_info *psi) * @part: pstore writes data to registered buffer in parts, * part number will indicate the same. * @count: Indicates oops count - * @hsize: Size of header added by pstore + * @compressed: Flag to indicate the log is compressed * @size: number of bytes written to the registered buffer * @psi: registered pstore_info structure * @@ -595,7 +565,7 @@ static int nvram_pstore_open(struct pstore_info *psi) static int nvram_pstore_write(enum pstore_type_id type, enum kmsg_dump_reason reason, u64 *id, unsigned int part, int count, - size_t hsize, size_t size, + bool compressed, size_t size, struct pstore_info *psi) { int rc; @@ -611,30 +581,11 @@ static int nvram_pstore_write(enum pstore_type_id type, oops_hdr->report_length = (u16) size; oops_hdr->timestamp = get_seconds(); - if (big_oops_buf) { - rc = zip_oops(size); - /* - * If compression fails copy recent log messages from - * big_oops_buf to oops_data. - */ - if (rc != 0) { - size_t diff = size - oops_data_sz + hsize; - - if (size > oops_data_sz) { - memcpy(oops_data, big_oops_buf, hsize); - memcpy(oops_data + hsize, big_oops_buf + diff, - oops_data_sz - hsize); - - oops_hdr->report_length = (u16) oops_data_sz; - } else - memcpy(oops_data, big_oops_buf, size); - } else - err_type = ERR_TYPE_KERNEL_PANIC_GZ; - } + if (compressed) + err_type = ERR_TYPE_KERNEL_PANIC_GZ; rc = nvram_write_os_partition(&oops_log_partition, oops_buf, - (int) (sizeof(*oops_hdr) + oops_hdr->report_length), err_type, - count); + (int) (sizeof(*oops_hdr) + size), err_type, count); if (rc != 0) return rc; @@ -650,12 +601,12 @@ static int nvram_pstore_write(enum pstore_type_id type, */ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, int *count, struct timespec *time, char **buf, - struct pstore_info *psi) + bool *compressed, struct pstore_info *psi) { struct oops_log_info *oops_hdr; unsigned int err_type, id_no, size = 0; struct nvram_os_partition *part = NULL; - char *buff = NULL, *big_buff = NULL; + char *buff = NULL; int sig = 0; loff_t p; @@ -719,8 +670,7 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, *id = id_no; if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) { - int length, unzipped_len; - size_t hdr_size; + size_t length, hdr_size; oops_hdr = (struct oops_log_info *)buff; if (oops_hdr->version < OOPS_HDR_VERSION) { @@ -741,23 +691,10 @@ static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type, memcpy(*buf, buff + hdr_size, length); kfree(buff); - if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) { - big_buff = kmalloc(big_oops_buf_sz, GFP_KERNEL); - if (!big_buff) - return -ENOMEM; - - unzipped_len = nvram_decompress(*buf, big_buff, - length, big_oops_buf_sz); - - if (unzipped_len < 0) { - pr_err("nvram: decompression failed, returned " - "rc %d\n", unzipped_len); - kfree(big_buff); - } else { - *buf = big_buff; - length = unzipped_len; - } - } + if (err_type == ERR_TYPE_KERNEL_PANIC_GZ) + *compressed = true; + else + *compressed = false; return length; } @@ -777,13 +714,8 @@ static int nvram_pstore_init(void) { int rc = 0; - if (big_oops_buf) { - nvram_pstore_info.buf = big_oops_buf; - nvram_pstore_info.bufsize = big_oops_buf_sz; - } else { - nvram_pstore_info.buf = oops_data; - nvram_pstore_info.bufsize = oops_data_sz; - } + nvram_pstore_info.buf = oops_data; + nvram_pstore_info.bufsize = oops_data_sz; rc = pstore_register(&nvram_pstore_info); if (rc != 0) @@ -802,7 +734,6 @@ static int nvram_pstore_init(void) static void __init nvram_init_oops_partition(int rtas_partition_exists) { int rc; - size_t size; rc = pseries_nvram_init_os_partition(&oops_log_partition); if (rc != 0) { @@ -823,6 +754,11 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists) oops_data = oops_buf + sizeof(struct oops_log_info); oops_data_sz = oops_log_partition.size - sizeof(struct oops_log_info); + rc = nvram_pstore_init(); + + if (!rc) + return; + /* * Figure compression (preceded by elimination of each line's <n> * severity prefix) will reduce the oops/panic report to at most @@ -831,9 +767,8 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists) big_oops_buf_sz = (oops_data_sz * 100) / 45; big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL); if (big_oops_buf) { - size = max(zlib_deflate_workspacesize(WINDOW_BITS, MEM_LEVEL), - zlib_inflate_workspacesize()); - stream.workspace = kmalloc(size, GFP_KERNEL); + stream.workspace = kmalloc(zlib_deflate_workspacesize( + WINDOW_BITS, MEM_LEVEL), GFP_KERNEL); if (!stream.workspace) { pr_err("nvram: No memory for compression workspace; " "skipping compression of %s partition data\n", @@ -847,11 +782,6 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists) stream.workspace = NULL; } - rc = nvram_pstore_init(); - - if (!rc) - return; - rc = kmsg_dump_register(&nvram_kmsg_dumper); if (rc != 0) { pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc); diff --git a/arch/powerpc/sysdev/rtc_cmos_setup.c b/arch/powerpc/sysdev/rtc_cmos_setup.c index af79e1ea74b6..af0f9beddca9 100644 --- a/arch/powerpc/sysdev/rtc_cmos_setup.c +++ b/arch/powerpc/sysdev/rtc_cmos_setup.c @@ -62,7 +62,7 @@ static int __init add_rtc(void) pd = platform_device_register_simple("rtc_cmos", -1, &res[0], num_res); - return PTR_RET(pd); + return PTR_ERR_OR_ZERO(pd); } fs_initcall(add_rtc); diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8a4cae78f03c..8b7892bf6d8b 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -116,6 +116,7 @@ config S390 select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_TRACE_MCOUNT_TEST + select HAVE_GENERIC_HARDIRQS select HAVE_KERNEL_BZIP2 select HAVE_KERNEL_GZIP select HAVE_KERNEL_LZ4 @@ -445,6 +446,16 @@ config PCI_NR_FUNCTIONS This allows you to specify the maximum number of PCI functions which this kernel will support. +config PCI_NR_MSI + int "Maximum number of MSI interrupts (64-32768)" + range 64 32768 + default "256" + help + This defines the number of virtual interrupts the kernel will + provide for MSI interrupts. If you configure your system to have + too few drivers will fail to allocate MSI interrupts for all + PCI devices. + source "drivers/pci/Kconfig" source "drivers/pci/pcie/Kconfig" source "drivers/pci/hotplug/Kconfig" diff --git a/arch/s390/hypfs/hypfs_dbfs.c b/arch/s390/hypfs/hypfs_dbfs.c index bb5dd496614f..17ab8b7b53cc 100644 --- a/arch/s390/hypfs/hypfs_dbfs.c +++ b/arch/s390/hypfs/hypfs_dbfs.c @@ -105,7 +105,7 @@ void hypfs_dbfs_remove_file(struct hypfs_dbfs_file *df) int hypfs_dbfs_init(void) { dbfs_dir = debugfs_create_dir("s390_hypfs", NULL); - return PTR_RET(dbfs_dir); + return PTR_ERR_OR_ZERO(dbfs_dir); } void hypfs_dbfs_exit(void) diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h index 4066cee0c2d2..4bbb5957ed1b 100644 --- a/arch/s390/include/asm/airq.h +++ b/arch/s390/include/asm/airq.h @@ -9,6 +9,8 @@ #ifndef _ASM_S390_AIRQ_H #define _ASM_S390_AIRQ_H +#include <linux/bit_spinlock.h> + struct airq_struct { struct hlist_node list; /* Handler queueing. */ void (*handler)(struct airq_struct *); /* Thin-interrupt handler */ @@ -23,4 +25,69 @@ struct airq_struct { int register_adapter_interrupt(struct airq_struct *airq); void unregister_adapter_interrupt(struct airq_struct *airq); +/* Adapter interrupt bit vector */ +struct airq_iv { + unsigned long *vector; /* Adapter interrupt bit vector */ + unsigned long *avail; /* Allocation bit mask for the bit vector */ + unsigned long *bitlock; /* Lock bit mask for the bit vector */ + unsigned long *ptr; /* Pointer associated with each bit */ + unsigned int *data; /* 32 bit value associated with each bit */ + unsigned long bits; /* Number of bits in the vector */ + unsigned long end; /* Number of highest allocated bit + 1 */ + spinlock_t lock; /* Lock to protect alloc & free */ +}; + +#define AIRQ_IV_ALLOC 1 /* Use an allocation bit mask */ +#define AIRQ_IV_BITLOCK 2 /* Allocate the lock bit mask */ +#define AIRQ_IV_PTR 4 /* Allocate the ptr array */ +#define AIRQ_IV_DATA 8 /* Allocate the data array */ + +struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags); +void airq_iv_release(struct airq_iv *iv); +unsigned long airq_iv_alloc_bit(struct airq_iv *iv); +void airq_iv_free_bit(struct airq_iv *iv, unsigned long bit); +unsigned long airq_iv_scan(struct airq_iv *iv, unsigned long start, + unsigned long end); + +static inline unsigned long airq_iv_end(struct airq_iv *iv) +{ + return iv->end; +} + +static inline void airq_iv_lock(struct airq_iv *iv, unsigned long bit) +{ + const unsigned long be_to_le = BITS_PER_LONG - 1; + bit_spin_lock(bit ^ be_to_le, iv->bitlock); +} + +static inline void airq_iv_unlock(struct airq_iv *iv, unsigned long bit) +{ + const unsigned long be_to_le = BITS_PER_LONG - 1; + bit_spin_unlock(bit ^ be_to_le, iv->bitlock); +} + +static inline void airq_iv_set_data(struct airq_iv *iv, unsigned long bit, + unsigned int data) +{ + iv->data[bit] = data; +} + +static inline unsigned int airq_iv_get_data(struct airq_iv *iv, + unsigned long bit) +{ + return iv->data[bit]; +} + +static inline void airq_iv_set_ptr(struct airq_iv *iv, unsigned long bit, + unsigned long ptr) +{ + iv->ptr[bit] = ptr; +} + +static inline unsigned long airq_iv_get_ptr(struct airq_iv *iv, + unsigned long bit) +{ + return iv->ptr[bit]; +} + #endif /* _ASM_S390_AIRQ_H */ diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 7d4676758733..10135a38673c 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -216,7 +216,7 @@ static inline void __set_bit(unsigned long nr, volatile unsigned long *ptr) addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); asm volatile( " oc %O0(1,%R0),%1" - : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc" ); + : "+Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc"); } static inline void @@ -244,7 +244,7 @@ __clear_bit(unsigned long nr, volatile unsigned long *ptr) addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); asm volatile( " nc %O0(1,%R0),%1" - : "=Q" (*(char *) addr) : "Q" (_ni_bitmap[nr & 7]) : "cc" ); + : "+Q" (*(char *) addr) : "Q" (_ni_bitmap[nr & 7]) : "cc"); } static inline void @@ -271,7 +271,7 @@ static inline void __change_bit(unsigned long nr, volatile unsigned long *ptr) addr = (unsigned long) ptr + ((nr ^ (BITS_PER_LONG - 8)) >> 3); asm volatile( " xc %O0(1,%R0),%1" - : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc" ); + : "+Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc"); } static inline void @@ -301,7 +301,7 @@ test_and_set_bit_simple(unsigned long nr, volatile unsigned long *ptr) ch = *(unsigned char *) addr; asm volatile( " oc %O0(1,%R0),%1" - : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) + : "+Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc", "memory"); return (ch >> (nr & 7)) & 1; } @@ -320,7 +320,7 @@ test_and_clear_bit_simple(unsigned long nr, volatile unsigned long *ptr) ch = *(unsigned char *) addr; asm volatile( " nc %O0(1,%R0),%1" - : "=Q" (*(char *) addr) : "Q" (_ni_bitmap[nr & 7]) + : "+Q" (*(char *) addr) : "Q" (_ni_bitmap[nr & 7]) : "cc", "memory"); return (ch >> (nr & 7)) & 1; } @@ -339,7 +339,7 @@ test_and_change_bit_simple(unsigned long nr, volatile unsigned long *ptr) ch = *(unsigned char *) addr; asm volatile( " xc %O0(1,%R0),%1" - : "=Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) + : "+Q" (*(char *) addr) : "Q" (_oi_bitmap[nr & 7]) : "cc", "memory"); return (ch >> (nr & 7)) & 1; } diff --git a/arch/s390/include/asm/cio.h b/arch/s390/include/asm/cio.h index ffb898961c8d..d42625053c37 100644 --- a/arch/s390/include/asm/cio.h +++ b/arch/s390/include/asm/cio.h @@ -296,6 +296,7 @@ static inline int ccw_dev_id_is_equal(struct ccw_dev_id *dev_id1, return 0; } +void channel_subsystem_reinit(void); extern void css_schedule_reprobe(void); extern void reipl_ccw_dev(struct ccw_dev_id *id); diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h index d2ff41370c0c..f65bd3634519 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -13,9 +13,6 @@ #include <asm/div64.h> -#define __ARCH_HAS_VTIME_ACCOUNT -#define __ARCH_HAS_VTIME_TASK_SWITCH - /* We want to use full resolution of the CPU timer: 2**-12 micro-seconds. */ typedef unsigned long long __nocast cputime_t; diff --git a/arch/s390/include/asm/hardirq.h b/arch/s390/include/asm/hardirq.h index 0c82ba86e997..a908d2941c5d 100644 --- a/arch/s390/include/asm/hardirq.h +++ b/arch/s390/include/asm/hardirq.h @@ -20,4 +20,9 @@ #define HARDIRQ_BITS 8 +static inline void ack_bad_irq(unsigned int irq) +{ + printk(KERN_CRIT "unexpected IRQ trap at vector %02x\n", irq); +} + #endif /* __ASM_HARDIRQ_H */ diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index bd90359d6d22..11eae5f55b70 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -17,6 +17,9 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); +pte_t huge_ptep_get(pte_t *ptep); +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); /* * If the arch doesn't supply something else, assume that hugepage @@ -38,147 +41,75 @@ static inline int prepare_hugepage_range(struct file *file, int arch_prepare_hugepage(struct page *page); void arch_release_hugepage(struct page *page); -static inline pte_t huge_pte_wrprotect(pte_t pte) +static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) { - pte_val(pte) |= _PAGE_RO; - return pte; + pte_val(*ptep) = _SEGMENT_ENTRY_EMPTY; } -static inline int huge_pte_none(pte_t pte) +static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) { - return (pte_val(pte) & _SEGMENT_ENTRY_INV) && - !(pte_val(pte) & _SEGMENT_ENTRY_RO); + huge_ptep_get_and_clear(vma->vm_mm, address, ptep); } -static inline pte_t huge_ptep_get(pte_t *ptep) +static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) { - pte_t pte = *ptep; - unsigned long mask; - - if (!MACHINE_HAS_HPAGE) { - ptep = (pte_t *) (pte_val(pte) & _SEGMENT_ENTRY_ORIGIN); - if (ptep) { - mask = pte_val(pte) & - (_SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO); - pte = pte_mkhuge(*ptep); - pte_val(pte) |= mask; - } + int changed = !pte_same(huge_ptep_get(ptep), pte); + if (changed) { + huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); } - return pte; + return changed; } -static inline void __pmd_csp(pmd_t *pmdp) +static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) { - register unsigned long reg2 asm("2") = pmd_val(*pmdp); - register unsigned long reg3 asm("3") = pmd_val(*pmdp) | - _SEGMENT_ENTRY_INV; - register unsigned long reg4 asm("4") = ((unsigned long) pmdp) + 5; - - asm volatile( - " csp %1,%3" - : "=m" (*pmdp) - : "d" (reg2), "d" (reg3), "d" (reg4), "m" (*pmdp) : "cc"); + pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep); + set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte)); } -static inline void huge_ptep_invalidate(struct mm_struct *mm, - unsigned long address, pte_t *ptep) -{ - pmd_t *pmdp = (pmd_t *) ptep; - - if (MACHINE_HAS_IDTE) - __pmd_idte(address, pmdp); - else - __pmd_csp(pmdp); - pmd_val(*pmdp) = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY; -} - -static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - pte_t pte = huge_ptep_get(ptep); - - huge_ptep_invalidate(mm, addr, ptep); - return pte; -} - -#define huge_ptep_set_access_flags(__vma, __addr, __ptep, __entry, __dirty) \ -({ \ - int __changed = !pte_same(huge_ptep_get(__ptep), __entry); \ - if (__changed) { \ - huge_ptep_invalidate((__vma)->vm_mm, __addr, __ptep); \ - set_huge_pte_at((__vma)->vm_mm, __addr, __ptep, __entry); \ - } \ - __changed; \ -}) - -#define huge_ptep_set_wrprotect(__mm, __addr, __ptep) \ -({ \ - pte_t __pte = huge_ptep_get(__ptep); \ - if (huge_pte_write(__pte)) { \ - huge_ptep_invalidate(__mm, __addr, __ptep); \ - set_huge_pte_at(__mm, __addr, __ptep, \ - huge_pte_wrprotect(__pte)); \ - } \ -}) - -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long address, pte_t *ptep) +static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot) { - huge_ptep_invalidate(vma->vm_mm, address, ptep); + return mk_pte(page, pgprot); } -static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot) +static inline int huge_pte_none(pte_t pte) { - pte_t pte; - pmd_t pmd; - - pmd = mk_pmd_phys(page_to_phys(page), pgprot); - pte_val(pte) = pmd_val(pmd); - return pte; + return pte_none(pte); } static inline int huge_pte_write(pte_t pte) { - pmd_t pmd; - - pmd_val(pmd) = pte_val(pte); - return pmd_write(pmd); + return pte_write(pte); } static inline int huge_pte_dirty(pte_t pte) { - /* No dirty bit in the segment table entry. */ - return 0; + return pte_dirty(pte); } static inline pte_t huge_pte_mkwrite(pte_t pte) { - pmd_t pmd; - - pmd_val(pmd) = pte_val(pte); - pte_val(pte) = pmd_val(pmd_mkwrite(pmd)); - return pte; + return pte_mkwrite(pte); } static inline pte_t huge_pte_mkdirty(pte_t pte) { - /* No dirty bit in the segment table entry. */ - return pte; + return pte_mkdirty(pte); } -static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot) +static inline pte_t huge_pte_wrprotect(pte_t pte) { - pmd_t pmd; - - pmd_val(pmd) = pte_val(pte); - pte_val(pte) = pmd_val(pmd_modify(pmd, newprot)); - return pte; + return pte_wrprotect(pte); } -static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) +static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot) { - pmd_clear((pmd_t *) ptep); + return pte_modify(pte, newprot); } #endif /* _ASM_S390_HUGETLB_H */ diff --git a/arch/s390/include/asm/hw_irq.h b/arch/s390/include/asm/hw_irq.h index 7e3d2586c1ff..ee96a8b697f9 100644 --- a/arch/s390/include/asm/hw_irq.h +++ b/arch/s390/include/asm/hw_irq.h @@ -4,19 +4,8 @@ #include <linux/msi.h> #include <linux/pci.h> -static inline struct msi_desc *irq_get_msi_desc(unsigned int irq) -{ - return __irq_get_msi_desc(irq); -} - -/* Must be called with msi map lock held */ -static inline int irq_set_msi_desc(unsigned int irq, struct msi_desc *msi) -{ - if (!msi) - return -EINVAL; - - msi->irq = irq; - return 0; -} +void __init init_airq_interrupts(void); +void __init init_cio_interrupts(void); +void __init init_ext_interrupts(void); #endif diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h index 87c17bfb2968..1eaa3625803c 100644 --- a/arch/s390/include/asm/irq.h +++ b/arch/s390/include/asm/irq.h @@ -1,17 +1,28 @@ #ifndef _ASM_IRQ_H #define _ASM_IRQ_H +#define EXT_INTERRUPT 1 +#define IO_INTERRUPT 2 +#define THIN_INTERRUPT 3 + +#define NR_IRQS_BASE 4 + +#ifdef CONFIG_PCI_NR_MSI +# define NR_IRQS (NR_IRQS_BASE + CONFIG_PCI_NR_MSI) +#else +# define NR_IRQS NR_IRQS_BASE +#endif + +/* This number is used when no interrupt has been assigned */ +#define NO_IRQ 0 + +#ifndef __ASSEMBLY__ + #include <linux/hardirq.h> #include <linux/percpu.h> #include <linux/cache.h> #include <linux/types.h> -enum interruption_main_class { - EXTERNAL_INTERRUPT, - IO_INTERRUPT, - NR_IRQS -}; - enum interruption_class { IRQEXT_CLK, IRQEXT_EXC, @@ -72,14 +83,8 @@ void service_subclass_irq_unregister(void); void measurement_alert_subclass_register(void); void measurement_alert_subclass_unregister(void); -#ifdef CONFIG_LOCKDEP -# define disable_irq_nosync_lockdep(irq) disable_irq_nosync(irq) -# define disable_irq_nosync_lockdep_irqsave(irq, flags) \ - disable_irq_nosync(irq) -# define disable_irq_lockdep(irq) disable_irq(irq) -# define enable_irq_lockdep(irq) enable_irq(irq) -# define enable_irq_lockdep_irqrestore(irq, flags) \ - enable_irq(irq) -#endif +#define irq_canonicalize(irq) (irq) + +#endif /* __ASSEMBLY__ */ #endif /* _ASM_IRQ_H */ diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 3238d4004e84..e87ecaa2c569 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -274,6 +274,14 @@ struct kvm_arch{ int css_support; }; +#define KVM_HVA_ERR_BAD (-1UL) +#define KVM_HVA_ERR_RO_BAD (-2UL) + +static inline bool kvm_is_error_hva(unsigned long addr) +{ + return IS_ERR_VALUE(addr); +} + extern int sie64a(struct kvm_s390_sie_block *, u64 *); extern char sie_exit; #endif diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index 6340178748bf..ff132ac64ddd 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -12,8 +12,6 @@ typedef struct { unsigned long asce_bits; unsigned long asce_limit; unsigned long vdso_base; - /* Cloned contexts will be created with extended page tables. */ - unsigned int alloc_pgste:1; /* The mmu context has extended page tables. */ unsigned int has_pgste:1; } mm_context_t; diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h index 084e7755ed9b..9f973d8de90e 100644 --- a/arch/s390/include/asm/mmu_context.h +++ b/arch/s390/include/asm/mmu_context.h @@ -21,24 +21,7 @@ static inline int init_new_context(struct task_struct *tsk, #ifdef CONFIG_64BIT mm->context.asce_bits |= _ASCE_TYPE_REGION3; #endif - if (current->mm && current->mm->context.alloc_pgste) { - /* - * alloc_pgste indicates, that any NEW context will be created - * with extended page tables. The old context is unchanged. The - * page table allocation and the page table operations will - * look at has_pgste to distinguish normal and extended page - * tables. The only way to create extended page tables is to - * set alloc_pgste and then create a new context (e.g. dup_mm). - * The page table allocation is called after init_new_context - * and if has_pgste is set, it will create extended page - * tables. - */ - mm->context.has_pgste = 1; - mm->context.alloc_pgste = 1; - } else { - mm->context.has_pgste = 0; - mm->context.alloc_pgste = 0; - } + mm->context.has_pgste = 0; mm->context.asce_limit = STACK_TOP_MAX; crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm)); return 0; @@ -77,8 +60,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, WARN_ON(atomic_read(&prev->context.attach_count) < 0); atomic_inc(&next->context.attach_count); /* Check for TLBs not flushed yet */ - if (next->context.flush_mm) - __tlb_flush_mm(next); + __tlb_flush_mm_lazy(next); } #define enter_lazy_tlb(mm,tsk) do { } while (0) diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h index 5d64fb7619cc..1e51f2915b2e 100644 --- a/arch/s390/include/asm/page.h +++ b/arch/s390/include/asm/page.h @@ -32,16 +32,6 @@ void storage_key_init_range(unsigned long start, unsigned long end); -static inline unsigned long pfmf(unsigned long function, unsigned long address) -{ - asm volatile( - " .insn rre,0xb9af0000,%[function],%[address]" - : [address] "+a" (address) - : [function] "d" (function) - : "memory"); - return address; -} - static inline void clear_page(void *page) { register unsigned long reg1 asm ("1") = 0; @@ -150,15 +140,6 @@ static inline int page_reset_referenced(unsigned long addr) #define _PAGE_FP_BIT 0x08 /* HW fetch protection bit */ #define _PAGE_ACC_BITS 0xf0 /* HW access control bits */ -/* - * Test and clear referenced bit in storage key. - */ -#define __HAVE_ARCH_PAGE_TEST_AND_CLEAR_YOUNG -static inline int page_test_and_clear_young(unsigned long pfn) -{ - return page_reset_referenced(pfn << PAGE_SHIFT); -} - struct page; void arch_free_page(struct page *page, int order); void arch_alloc_page(struct page *page, int order); diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h index 6e577ba0e5da..c290f13d1c47 100644 --- a/arch/s390/include/asm/pci.h +++ b/arch/s390/include/asm/pci.h @@ -6,6 +6,7 @@ /* must be set before including pci_clp.h */ #define PCI_BAR_COUNT 6 +#include <linux/pci.h> #include <asm-generic/pci.h> #include <asm-generic/pci-dma-compat.h> #include <asm/pci_clp.h> @@ -53,14 +54,9 @@ struct zpci_fmb { atomic64_t unmapped_pages; } __packed __aligned(16); -struct msi_map { - unsigned long irq; - struct msi_desc *msi; - struct hlist_node msi_chain; -}; - -#define ZPCI_NR_MSI_VECS 64 -#define ZPCI_MSI_MASK (ZPCI_NR_MSI_VECS - 1) +#define ZPCI_MSI_VEC_BITS 11 +#define ZPCI_MSI_VEC_MAX (1 << ZPCI_MSI_VEC_BITS) +#define ZPCI_MSI_VEC_MASK (ZPCI_MSI_VEC_MAX - 1) enum zpci_state { ZPCI_FN_STATE_RESERVED, @@ -91,8 +87,7 @@ struct zpci_dev { /* IRQ stuff */ u64 msi_addr; /* MSI address */ - struct zdev_irq_map *irq_map; - struct msi_map *msi_map[ZPCI_NR_MSI_VECS]; + struct airq_iv *aibv; /* adapter interrupt bit vector */ unsigned int aisb; /* number of the summary bit */ /* DMA stuff */ @@ -122,11 +117,6 @@ struct zpci_dev { struct dentry *debugfs_perf; }; -struct pci_hp_callback_ops { - int (*create_slot) (struct zpci_dev *zdev); - void (*remove_slot) (struct zpci_dev *zdev); -}; - static inline bool zdev_enabled(struct zpci_dev *zdev) { return (zdev->fh & (1UL << 31)) ? true : false; @@ -146,32 +136,38 @@ int zpci_register_ioat(struct zpci_dev *, u8, u64, u64, u64); int zpci_unregister_ioat(struct zpci_dev *, u8); /* CLP */ -int clp_find_pci_devices(void); +int clp_scan_pci_devices(void); +int clp_rescan_pci_devices(void); +int clp_rescan_pci_devices_simple(void); int clp_add_pci_device(u32, u32, int); int clp_enable_fh(struct zpci_dev *, u8); int clp_disable_fh(struct zpci_dev *); -/* MSI */ -struct msi_desc *__irq_get_msi_desc(unsigned int); -int zpci_msi_set_mask_bits(struct msi_desc *, u32, u32); -int zpci_setup_msi_irq(struct zpci_dev *, struct msi_desc *, unsigned int, int); -void zpci_teardown_msi_irq(struct zpci_dev *, struct msi_desc *); -int zpci_msihash_init(void); -void zpci_msihash_exit(void); - #ifdef CONFIG_PCI /* Error handling and recovery */ void zpci_event_error(void *); void zpci_event_availability(void *); +void zpci_rescan(void); #else /* CONFIG_PCI */ static inline void zpci_event_error(void *e) {} static inline void zpci_event_availability(void *e) {} +static inline void zpci_rescan(void) {} #endif /* CONFIG_PCI */ +#ifdef CONFIG_HOTPLUG_PCI_S390 +int zpci_init_slot(struct zpci_dev *); +void zpci_exit_slot(struct zpci_dev *); +#else /* CONFIG_HOTPLUG_PCI_S390 */ +static inline int zpci_init_slot(struct zpci_dev *zdev) +{ + return 0; +} +static inline void zpci_exit_slot(struct zpci_dev *zdev) {} +#endif /* CONFIG_HOTPLUG_PCI_S390 */ + /* Helpers */ struct zpci_dev *get_zdev(struct pci_dev *); struct zpci_dev *get_zdev_by_fid(u32); -bool zpci_fid_present(u32); /* sysfs */ int zpci_sysfs_add_device(struct device *); @@ -181,14 +177,6 @@ void zpci_sysfs_remove_device(struct device *); int zpci_dma_init(void); void zpci_dma_exit(void); -/* Hotplug */ -extern struct mutex zpci_list_lock; -extern struct list_head zpci_list; -extern unsigned int s390_pci_probe; - -void zpci_register_hp_ops(struct pci_hp_callback_ops *); -void zpci_deregister_hp_ops(void); - /* FMB */ int zpci_fmb_enable_device(struct zpci_dev *); int zpci_fmb_disable_device(struct zpci_dev *); diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h index e6a2bdd4d705..df6eac9f0cb4 100644 --- a/arch/s390/include/asm/pci_insn.h +++ b/arch/s390/include/asm/pci_insn.h @@ -79,11 +79,11 @@ struct zpci_fib { } __packed; -int s390pci_mod_fc(u64 req, struct zpci_fib *fib); -int s390pci_refresh_trans(u64 fn, u64 addr, u64 range); -int s390pci_load(u64 *data, u64 req, u64 offset); -int s390pci_store(u64 data, u64 req, u64 offset); -int s390pci_store_block(const u64 *data, u64 req, u64 offset); -void set_irq_ctrl(u16 ctl, char *unused, u8 isc); +int zpci_mod_fc(u64 req, struct zpci_fib *fib); +int zpci_refresh_trans(u64 fn, u64 addr, u64 range); +int zpci_load(u64 *data, u64 req, u64 offset); +int zpci_store(u64 data, u64 req, u64 offset); +int zpci_store_block(const u64 *data, u64 req, u64 offset); +void zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc); #endif diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h index 83a9caa6ae53..d194d544d694 100644 --- a/arch/s390/include/asm/pci_io.h +++ b/arch/s390/include/asm/pci_io.h @@ -36,7 +36,7 @@ static inline RETTYPE zpci_read_##RETTYPE(const volatile void __iomem *addr) \ u64 data; \ int rc; \ \ - rc = s390pci_load(&data, req, ZPCI_OFFSET(addr)); \ + rc = zpci_load(&data, req, ZPCI_OFFSET(addr)); \ if (rc) \ data = -1ULL; \ return (RETTYPE) data; \ @@ -50,7 +50,7 @@ static inline void zpci_write_##VALTYPE(VALTYPE val, \ u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH); \ u64 data = (VALTYPE) val; \ \ - s390pci_store(data, req, ZPCI_OFFSET(addr)); \ + zpci_store(data, req, ZPCI_OFFSET(addr)); \ } zpci_read(8, u64) @@ -83,7 +83,7 @@ static inline int zpci_write_single(u64 req, const u64 *data, u64 offset, u8 len val = 0; /* let FW report error */ break; } - return s390pci_store(val, req, offset); + return zpci_store(val, req, offset); } static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len) @@ -91,7 +91,7 @@ static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len) u64 data; int cc; - cc = s390pci_load(&data, req, offset); + cc = zpci_load(&data, req, offset); if (cc) goto out; @@ -115,7 +115,7 @@ out: static inline int zpci_write_block(u64 req, const u64 *data, u64 offset) { - return s390pci_store_block(data, req, offset); + return zpci_store_block(data, req, offset); } static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max) diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 75fb726de91f..9b60a36c348d 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -217,63 +217,57 @@ extern unsigned long MODULES_END; /* Hardware bits in the page table entry */ #define _PAGE_CO 0x100 /* HW Change-bit override */ -#define _PAGE_RO 0x200 /* HW read-only bit */ +#define _PAGE_PROTECT 0x200 /* HW read-only bit */ #define _PAGE_INVALID 0x400 /* HW invalid bit */ +#define _PAGE_LARGE 0x800 /* Bit to mark a large pte */ /* Software bits in the page table entry */ -#define _PAGE_SWT 0x001 /* SW pte type bit t */ -#define _PAGE_SWX 0x002 /* SW pte type bit x */ -#define _PAGE_SWC 0x004 /* SW pte changed bit */ -#define _PAGE_SWR 0x008 /* SW pte referenced bit */ -#define _PAGE_SWW 0x010 /* SW pte write bit */ -#define _PAGE_SPECIAL 0x020 /* SW associated with special page */ +#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 */ +#define _PAGE_WRITE 0x020 /* SW pte write bit */ +#define _PAGE_SPECIAL 0x040 /* SW associated with special page */ #define __HAVE_ARCH_PTE_SPECIAL /* Set of bits not changed in pte_modify */ #define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_SPECIAL | _PAGE_CO | \ - _PAGE_SWC | _PAGE_SWR) - -/* Six different types of pages. */ -#define _PAGE_TYPE_EMPTY 0x400 -#define _PAGE_TYPE_NONE 0x401 -#define _PAGE_TYPE_SWAP 0x403 -#define _PAGE_TYPE_FILE 0x601 /* bit 0x002 is used for offset !! */ -#define _PAGE_TYPE_RO 0x200 -#define _PAGE_TYPE_RW 0x000 - -/* - * Only four types for huge pages, using the invalid bit and protection bit - * of a segment table entry. - */ -#define _HPAGE_TYPE_EMPTY 0x020 /* _SEGMENT_ENTRY_INV */ -#define _HPAGE_TYPE_NONE 0x220 -#define _HPAGE_TYPE_RO 0x200 /* _SEGMENT_ENTRY_RO */ -#define _HPAGE_TYPE_RW 0x000 + _PAGE_DIRTY | _PAGE_YOUNG) /* - * PTE type bits are rather complicated. handle_pte_fault uses pte_present, - * pte_none and pte_file to find out the pte type WITHOUT holding the page - * table lock. ptep_clear_flush on the other hand uses ptep_clear_flush to - * invalidate a given pte. ipte sets the hw invalid bit and clears all tlbs - * for the page. The page table entry is set to _PAGE_TYPE_EMPTY afterwards. - * This change is done while holding the lock, but the intermediate step - * of a previously valid pte with the hw invalid bit set can be observed by - * handle_pte_fault. That makes it necessary that all valid pte types with - * the hw invalid bit set must be distinguishable from the four pte types - * empty, none, swap and file. + * handle_pte_fault uses pte_present, pte_none and pte_file to find out the + * pte type WITHOUT holding the page table lock. The _PAGE_PRESENT bit + * is used to distinguish present from not-present ptes. It is changed only + * with the page 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: * - * irxt ipte irxt - * _PAGE_TYPE_EMPTY 1000 -> 1000 - * _PAGE_TYPE_NONE 1001 -> 1001 - * _PAGE_TYPE_SWAP 1011 -> 1011 - * _PAGE_TYPE_FILE 11?1 -> 11?1 - * _PAGE_TYPE_RO 0100 -> 1100 - * _PAGE_TYPE_RW 0000 -> 1000 + * 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 * - * pte_none is true for bits combinations 1000, 1010, 1100, 1110 - * pte_present is true for bits combinations 0000, 0010, 0100, 0110, 1001 - * pte_file is true for bits combinations 1101, 1111 - * swap pte is 1011 and 0001, 0011, 0101, 0111 are invalid. + * 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_file is true for the bit pattern .11...xxxxx0, (pte & 0x601) == 0x600 + * pte_swap is true for the bit pattern .10...xxxx10, (pte & 0x603) == 0x402 */ #ifndef CONFIG_64BIT @@ -286,14 +280,25 @@ extern unsigned long MODULES_END; #define _ASCE_TABLE_LENGTH 0x7f /* 128 x 64 entries = 8k */ /* Bits in the segment table entry */ +#define _SEGMENT_ENTRY_BITS 0x7fffffffUL /* Valid segment table bits */ #define _SEGMENT_ENTRY_ORIGIN 0x7fffffc0UL /* page table origin */ -#define _SEGMENT_ENTRY_RO 0x200 /* page protection bit */ -#define _SEGMENT_ENTRY_INV 0x20 /* invalid segment table entry */ +#define _SEGMENT_ENTRY_PROTECT 0x200 /* page protection bit */ +#define _SEGMENT_ENTRY_INVALID 0x20 /* invalid segment table entry */ #define _SEGMENT_ENTRY_COMMON 0x10 /* common segment bit */ #define _SEGMENT_ENTRY_PTL 0x0f /* page table length */ +#define _SEGMENT_ENTRY_NONE _SEGMENT_ENTRY_PROTECT #define _SEGMENT_ENTRY (_SEGMENT_ENTRY_PTL) -#define _SEGMENT_ENTRY_EMPTY (_SEGMENT_ENTRY_INV) +#define _SEGMENT_ENTRY_EMPTY (_SEGMENT_ENTRY_INVALID) + +/* + * Segment table entry encoding (I = invalid, R = read-only bit): + * ..R...I..... + * prot-none ..1...1..... + * read-only ..1...0..... + * read-write ..0...0..... + * empty ..0...1..... + */ /* Page status table bits for virtualization */ #define PGSTE_ACC_BITS 0xf0000000UL @@ -303,9 +308,7 @@ extern unsigned long MODULES_END; #define PGSTE_HC_BIT 0x00200000UL #define PGSTE_GR_BIT 0x00040000UL #define PGSTE_GC_BIT 0x00020000UL -#define PGSTE_UR_BIT 0x00008000UL -#define PGSTE_UC_BIT 0x00004000UL /* user dirty (migration) */ -#define PGSTE_IN_BIT 0x00002000UL /* IPTE notify bit */ +#define PGSTE_IN_BIT 0x00008000UL /* IPTE notify bit */ #else /* CONFIG_64BIT */ @@ -324,8 +327,8 @@ extern unsigned long MODULES_END; /* Bits in the region table entry */ #define _REGION_ENTRY_ORIGIN ~0xfffUL/* region/segment table origin */ -#define _REGION_ENTRY_RO 0x200 /* region protection bit */ -#define _REGION_ENTRY_INV 0x20 /* invalid region table entry */ +#define _REGION_ENTRY_PROTECT 0x200 /* region protection bit */ +#define _REGION_ENTRY_INVALID 0x20 /* invalid region table entry */ #define _REGION_ENTRY_TYPE_MASK 0x0c /* region/segment table type mask */ #define _REGION_ENTRY_TYPE_R1 0x0c /* region first table type */ #define _REGION_ENTRY_TYPE_R2 0x08 /* region second table type */ @@ -333,29 +336,47 @@ extern unsigned long MODULES_END; #define _REGION_ENTRY_LENGTH 0x03 /* region third length */ #define _REGION1_ENTRY (_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_LENGTH) -#define _REGION1_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INV) +#define _REGION1_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INVALID) #define _REGION2_ENTRY (_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_LENGTH) -#define _REGION2_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INV) +#define _REGION2_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INVALID) #define _REGION3_ENTRY (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_LENGTH) -#define _REGION3_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INV) +#define _REGION3_ENTRY_EMPTY (_REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID) #define _REGION3_ENTRY_LARGE 0x400 /* RTTE-format control, large page */ #define _REGION3_ENTRY_RO 0x200 /* page protection bit */ #define _REGION3_ENTRY_CO 0x100 /* change-recording override */ /* Bits in the segment table entry */ +#define _SEGMENT_ENTRY_BITS 0xfffffffffffffe33UL +#define _SEGMENT_ENTRY_BITS_LARGE 0xfffffffffff1ff33UL #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address */ #define _SEGMENT_ENTRY_ORIGIN ~0x7ffUL/* segment table origin */ -#define _SEGMENT_ENTRY_RO 0x200 /* page protection bit */ -#define _SEGMENT_ENTRY_INV 0x20 /* invalid segment table entry */ +#define _SEGMENT_ENTRY_PROTECT 0x200 /* page protection bit */ +#define _SEGMENT_ENTRY_INVALID 0x20 /* invalid segment table entry */ #define _SEGMENT_ENTRY (0) -#define _SEGMENT_ENTRY_EMPTY (_SEGMENT_ENTRY_INV) +#define _SEGMENT_ENTRY_EMPTY (_SEGMENT_ENTRY_INVALID) #define _SEGMENT_ENTRY_LARGE 0x400 /* STE-format control, large page */ #define _SEGMENT_ENTRY_CO 0x100 /* change-recording override */ +#define _SEGMENT_ENTRY_SPLIT 0x001 /* THP splitting bit */ +#define _SEGMENT_ENTRY_YOUNG 0x002 /* SW segment young bit */ +#define _SEGMENT_ENTRY_NONE _SEGMENT_ENTRY_YOUNG + +/* + * Segment table entry encoding (R = read-only, I = invalid, y = young bit): + * ..R...I...y. + * prot-none, old ..0...1...1. + * prot-none, young ..1...1...1. + * read-only, old ..1...1...0. + * read-only, young ..1...0...1. + * read-write, old ..0...1...0. + * read-write, young ..0...0...1. + * The segment table origin is used to distinguish empty (origin==0) from + * read-write, old segment table entries (origin!=0) + */ + #define _SEGMENT_ENTRY_SPLIT_BIT 0 /* THP splitting bit number */ -#define _SEGMENT_ENTRY_SPLIT (1UL << _SEGMENT_ENTRY_SPLIT_BIT) /* Set of bits not changed in pmd_modify */ #define _SEGMENT_CHG_MASK (_SEGMENT_ENTRY_ORIGIN | _SEGMENT_ENTRY_LARGE \ @@ -369,9 +390,7 @@ extern unsigned long MODULES_END; #define PGSTE_HC_BIT 0x0020000000000000UL #define PGSTE_GR_BIT 0x0004000000000000UL #define PGSTE_GC_BIT 0x0002000000000000UL -#define PGSTE_UR_BIT 0x0000800000000000UL -#define PGSTE_UC_BIT 0x0000400000000000UL /* user dirty (migration) */ -#define PGSTE_IN_BIT 0x0000200000000000UL /* IPTE notify bit */ +#define PGSTE_IN_BIT 0x0000800000000000UL /* IPTE notify bit */ #endif /* CONFIG_64BIT */ @@ -386,14 +405,18 @@ extern unsigned long MODULES_END; /* * Page protection definitions. */ -#define PAGE_NONE __pgprot(_PAGE_TYPE_NONE) -#define PAGE_RO __pgprot(_PAGE_TYPE_RO) -#define PAGE_RW __pgprot(_PAGE_TYPE_RO | _PAGE_SWW) -#define PAGE_RWC __pgprot(_PAGE_TYPE_RW | _PAGE_SWW | _PAGE_SWC) - -#define PAGE_KERNEL PAGE_RWC -#define PAGE_SHARED PAGE_KERNEL -#define PAGE_COPY PAGE_RO +#define PAGE_NONE __pgprot(_PAGE_PRESENT | _PAGE_INVALID) +#define PAGE_READ __pgprot(_PAGE_PRESENT | _PAGE_READ | \ + _PAGE_INVALID | _PAGE_PROTECT) +#define PAGE_WRITE __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ + _PAGE_INVALID | _PAGE_PROTECT) + +#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ + _PAGE_YOUNG | _PAGE_DIRTY) +#define PAGE_KERNEL __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ + _PAGE_YOUNG | _PAGE_DIRTY) +#define PAGE_KERNEL_RO __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_YOUNG | \ + _PAGE_PROTECT) /* * On s390 the page table entry has an invalid bit and a read-only bit. @@ -402,35 +425,31 @@ extern unsigned long MODULES_END; */ /*xwr*/ #define __P000 PAGE_NONE -#define __P001 PAGE_RO -#define __P010 PAGE_RO -#define __P011 PAGE_RO -#define __P100 PAGE_RO -#define __P101 PAGE_RO -#define __P110 PAGE_RO -#define __P111 PAGE_RO +#define __P001 PAGE_READ +#define __P010 PAGE_READ +#define __P011 PAGE_READ +#define __P100 PAGE_READ +#define __P101 PAGE_READ +#define __P110 PAGE_READ +#define __P111 PAGE_READ #define __S000 PAGE_NONE -#define __S001 PAGE_RO -#define __S010 PAGE_RW -#define __S011 PAGE_RW -#define __S100 PAGE_RO -#define __S101 PAGE_RO -#define __S110 PAGE_RW -#define __S111 PAGE_RW +#define __S001 PAGE_READ +#define __S010 PAGE_WRITE +#define __S011 PAGE_WRITE +#define __S100 PAGE_READ +#define __S101 PAGE_READ +#define __S110 PAGE_WRITE +#define __S111 PAGE_WRITE /* * Segment entry (large page) protection definitions. */ -#define SEGMENT_NONE __pgprot(_HPAGE_TYPE_NONE) -#define SEGMENT_RO __pgprot(_HPAGE_TYPE_RO) -#define SEGMENT_RW __pgprot(_HPAGE_TYPE_RW) - -static inline int mm_exclusive(struct mm_struct *mm) -{ - return likely(mm == current->active_mm && - atomic_read(&mm->context.attach_count) <= 1); -} +#define SEGMENT_NONE __pgprot(_SEGMENT_ENTRY_INVALID | \ + _SEGMENT_ENTRY_NONE) +#define SEGMENT_READ __pgprot(_SEGMENT_ENTRY_INVALID | \ + _SEGMENT_ENTRY_PROTECT) +#define SEGMENT_WRITE __pgprot(_SEGMENT_ENTRY_INVALID) static inline int mm_has_pgste(struct mm_struct *mm) { @@ -467,7 +486,7 @@ static inline int pgd_none(pgd_t pgd) { if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2) return 0; - return (pgd_val(pgd) & _REGION_ENTRY_INV) != 0UL; + return (pgd_val(pgd) & _REGION_ENTRY_INVALID) != 0UL; } static inline int pgd_bad(pgd_t pgd) @@ -478,7 +497,7 @@ static inline int pgd_bad(pgd_t pgd) * invalid for either table entry. */ unsigned long mask = - ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INV & + ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INVALID & ~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH; return (pgd_val(pgd) & mask) != 0; } @@ -494,7 +513,7 @@ static inline int pud_none(pud_t pud) { if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3) return 0; - return (pud_val(pud) & _REGION_ENTRY_INV) != 0UL; + return (pud_val(pud) & _REGION_ENTRY_INVALID) != 0UL; } static inline int pud_large(pud_t pud) @@ -512,7 +531,7 @@ static inline int pud_bad(pud_t pud) * invalid for either table entry. */ unsigned long mask = - ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INV & + ~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INVALID & ~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH; return (pud_val(pud) & mask) != 0; } @@ -521,30 +540,36 @@ static inline int pud_bad(pud_t pud) static inline int pmd_present(pmd_t pmd) { - unsigned long mask = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO; - return (pmd_val(pmd) & mask) == _HPAGE_TYPE_NONE || - !(pmd_val(pmd) & _SEGMENT_ENTRY_INV); + return pmd_val(pmd) != _SEGMENT_ENTRY_INVALID; } static inline int pmd_none(pmd_t pmd) { - return (pmd_val(pmd) & _SEGMENT_ENTRY_INV) && - !(pmd_val(pmd) & _SEGMENT_ENTRY_RO); + return pmd_val(pmd) == _SEGMENT_ENTRY_INVALID; } static inline int pmd_large(pmd_t pmd) { #ifdef CONFIG_64BIT - return !!(pmd_val(pmd) & _SEGMENT_ENTRY_LARGE); + return (pmd_val(pmd) & _SEGMENT_ENTRY_LARGE) != 0; #else return 0; #endif } +static inline int pmd_prot_none(pmd_t pmd) +{ + return (pmd_val(pmd) & _SEGMENT_ENTRY_INVALID) && + (pmd_val(pmd) & _SEGMENT_ENTRY_NONE); +} + static inline int pmd_bad(pmd_t pmd) { - unsigned long mask = ~_SEGMENT_ENTRY_ORIGIN & ~_SEGMENT_ENTRY_INV; - return (pmd_val(pmd) & mask) != _SEGMENT_ENTRY; +#ifdef CONFIG_64BIT + if (pmd_large(pmd)) + return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0; +#endif + return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0; } #define __HAVE_ARCH_PMDP_SPLITTING_FLUSH @@ -563,31 +588,40 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma, #define __HAVE_ARCH_PMD_WRITE static inline int pmd_write(pmd_t pmd) { - return (pmd_val(pmd) & _SEGMENT_ENTRY_RO) == 0; + if (pmd_prot_none(pmd)) + return 0; + return (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT) == 0; } static inline int pmd_young(pmd_t pmd) { - return 0; + int young = 0; +#ifdef CONFIG_64BIT + if (pmd_prot_none(pmd)) + young = (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT) != 0; + else + young = (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) != 0; +#endif + return young; } -static inline int pte_none(pte_t pte) +static inline int pte_present(pte_t pte) { - return (pte_val(pte) & _PAGE_INVALID) && !(pte_val(pte) & _PAGE_SWT); + /* Bit pattern: (pte & 0x001) == 0x001 */ + return (pte_val(pte) & _PAGE_PRESENT) != 0; } -static inline int pte_present(pte_t pte) +static inline int pte_none(pte_t pte) { - unsigned long mask = _PAGE_RO | _PAGE_INVALID | _PAGE_SWT | _PAGE_SWX; - return (pte_val(pte) & mask) == _PAGE_TYPE_NONE || - (!(pte_val(pte) & _PAGE_INVALID) && - !(pte_val(pte) & _PAGE_SWT)); + /* Bit pattern: pte == 0x400 */ + return pte_val(pte) == _PAGE_INVALID; } static inline int pte_file(pte_t pte) { - unsigned long mask = _PAGE_RO | _PAGE_INVALID | _PAGE_SWT; - return (pte_val(pte) & mask) == _PAGE_TYPE_FILE; + /* Bit pattern: (pte & 0x601) == 0x600 */ + return (pte_val(pte) & (_PAGE_INVALID | _PAGE_PROTECT | _PAGE_PRESENT)) + == (_PAGE_INVALID | _PAGE_PROTECT); } static inline int pte_special(pte_t pte) @@ -634,6 +668,15 @@ static inline void pgste_set_unlock(pte_t *ptep, pgste_t pgste) #endif } +static inline pgste_t pgste_get(pte_t *ptep) +{ + unsigned long pgste = 0; +#ifdef CONFIG_PGSTE + pgste = *(unsigned long *)(ptep + PTRS_PER_PTE); +#endif + return __pgste(pgste); +} + static inline void pgste_set(pte_t *ptep, pgste_t pgste) { #ifdef CONFIG_PGSTE @@ -644,33 +687,28 @@ static inline void pgste_set(pte_t *ptep, pgste_t pgste) static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste) { #ifdef CONFIG_PGSTE - unsigned long address, bits; - unsigned char skey; + unsigned long address, bits, skey; if (pte_val(*ptep) & _PAGE_INVALID) return pgste; address = pte_val(*ptep) & PAGE_MASK; - skey = page_get_storage_key(address); + skey = (unsigned long) page_get_storage_key(address); bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED); - /* Clear page changed & referenced bit in the storage key */ - if (bits & _PAGE_CHANGED) + if (!(pgste_val(pgste) & PGSTE_HC_BIT) && (bits & _PAGE_CHANGED)) { + /* Transfer dirty + referenced bit to host bits in pgste */ + pgste_val(pgste) |= bits << 52; page_set_storage_key(address, skey ^ bits, 0); - else if (bits) + } else if (!(pgste_val(pgste) & PGSTE_HR_BIT) && + (bits & _PAGE_REFERENCED)) { + /* Transfer referenced bit to host bit in pgste */ + pgste_val(pgste) |= PGSTE_HR_BIT; page_reset_referenced(address); + } /* Transfer page changed & referenced bit to guest bits in pgste */ pgste_val(pgste) |= bits << 48; /* GR bit & GC bit */ - /* Get host changed & referenced bits from pgste */ - bits |= (pgste_val(pgste) & (PGSTE_HR_BIT | PGSTE_HC_BIT)) >> 52; - /* Transfer page changed & referenced bit to kvm user bits */ - pgste_val(pgste) |= bits << 45; /* PGSTE_UR_BIT & PGSTE_UC_BIT */ - /* Clear relevant host bits in pgste. */ - pgste_val(pgste) &= ~(PGSTE_HR_BIT | PGSTE_HC_BIT); - pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT); /* Copy page access key and fetch protection bit to pgste */ - pgste_val(pgste) |= - (unsigned long) (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56; - /* Transfer referenced bit to pte */ - pte_val(*ptep) |= (bits & _PAGE_REFERENCED) << 1; + pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT); + pgste_val(pgste) |= (skey & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56; #endif return pgste; @@ -679,24 +717,11 @@ static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste) static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste) { #ifdef CONFIG_PGSTE - int young; - if (pte_val(*ptep) & _PAGE_INVALID) return pgste; /* Get referenced bit from storage key */ - young = page_reset_referenced(pte_val(*ptep) & PAGE_MASK); - if (young) - pgste_val(pgste) |= PGSTE_GR_BIT; - /* Get host referenced bit from pgste */ - if (pgste_val(pgste) & PGSTE_HR_BIT) { - pgste_val(pgste) &= ~PGSTE_HR_BIT; - young = 1; - } - /* Transfer referenced bit to kvm user bits and pte */ - if (young) { - pgste_val(pgste) |= PGSTE_UR_BIT; - pte_val(*ptep) |= _PAGE_SWR; - } + if (page_reset_referenced(pte_val(*ptep) & PAGE_MASK)) + pgste_val(pgste) |= PGSTE_HR_BIT | PGSTE_GR_BIT; #endif return pgste; } @@ -723,13 +748,13 @@ static inline void pgste_set_key(pte_t *ptep, pgste_t pgste, pte_t entry) static inline void pgste_set_pte(pte_t *ptep, pte_t entry) { - if (!MACHINE_HAS_ESOP && (pte_val(entry) & _PAGE_SWW)) { + if (!MACHINE_HAS_ESOP && (pte_val(entry) & _PAGE_WRITE)) { /* * Without enhanced suppression-on-protection force * the dirty bit on for all writable ptes. */ - pte_val(entry) |= _PAGE_SWC; - pte_val(entry) &= ~_PAGE_RO; + pte_val(entry) |= _PAGE_DIRTY; + pte_val(entry) &= ~_PAGE_PROTECT; } *ptep = entry; } @@ -841,21 +866,17 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, */ static inline int pte_write(pte_t pte) { - return (pte_val(pte) & _PAGE_SWW) != 0; + return (pte_val(pte) & _PAGE_WRITE) != 0; } static inline int pte_dirty(pte_t pte) { - return (pte_val(pte) & _PAGE_SWC) != 0; + return (pte_val(pte) & _PAGE_DIRTY) != 0; } static inline int pte_young(pte_t pte) { -#ifdef CONFIG_PGSTE - if (pte_val(pte) & _PAGE_SWR) - return 1; -#endif - return 0; + return (pte_val(pte) & _PAGE_YOUNG) != 0; } /* @@ -880,12 +901,12 @@ static inline void pud_clear(pud_t *pud) static inline void pmd_clear(pmd_t *pmdp) { - pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY; + pmd_val(*pmdp) = _SEGMENT_ENTRY_INVALID; } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { - pte_val(*ptep) = _PAGE_TYPE_EMPTY; + pte_val(*ptep) = _PAGE_INVALID; } /* @@ -896,55 +917,63 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { pte_val(pte) &= _PAGE_CHG_MASK; pte_val(pte) |= pgprot_val(newprot); - if ((pte_val(pte) & _PAGE_SWC) && (pte_val(pte) & _PAGE_SWW)) - pte_val(pte) &= ~_PAGE_RO; + /* + * newprot for PAGE_NONE, PAGE_READ and PAGE_WRITE has the + * invalid bit set, clear it again for readable, young pages + */ + if ((pte_val(pte) & _PAGE_YOUNG) && (pte_val(pte) & _PAGE_READ)) + pte_val(pte) &= ~_PAGE_INVALID; + /* + * newprot for PAGE_READ and PAGE_WRITE has the page protection + * bit set, clear it again for writable, dirty pages + */ + if ((pte_val(pte) & _PAGE_DIRTY) && (pte_val(pte) & _PAGE_WRITE)) + pte_val(pte) &= ~_PAGE_PROTECT; return pte; } static inline pte_t pte_wrprotect(pte_t pte) { - pte_val(pte) &= ~_PAGE_SWW; - /* Do not clobber _PAGE_TYPE_NONE pages! */ - if (!(pte_val(pte) & _PAGE_INVALID)) - pte_val(pte) |= _PAGE_RO; + pte_val(pte) &= ~_PAGE_WRITE; + pte_val(pte) |= _PAGE_PROTECT; return pte; } static inline pte_t pte_mkwrite(pte_t pte) { - pte_val(pte) |= _PAGE_SWW; - if (pte_val(pte) & _PAGE_SWC) - pte_val(pte) &= ~_PAGE_RO; + pte_val(pte) |= _PAGE_WRITE; + if (pte_val(pte) & _PAGE_DIRTY) + pte_val(pte) &= ~_PAGE_PROTECT; return pte; } static inline pte_t pte_mkclean(pte_t pte) { - pte_val(pte) &= ~_PAGE_SWC; - /* Do not clobber _PAGE_TYPE_NONE pages! */ - if (!(pte_val(pte) & _PAGE_INVALID)) - pte_val(pte) |= _PAGE_RO; + pte_val(pte) &= ~_PAGE_DIRTY; + pte_val(pte) |= _PAGE_PROTECT; return pte; } static inline pte_t pte_mkdirty(pte_t pte) { - pte_val(pte) |= _PAGE_SWC; - if (pte_val(pte) & _PAGE_SWW) - pte_val(pte) &= ~_PAGE_RO; + pte_val(pte) |= _PAGE_DIRTY; + if (pte_val(pte) & _PAGE_WRITE) + pte_val(pte) &= ~_PAGE_PROTECT; return pte; } static inline pte_t pte_mkold(pte_t pte) { -#ifdef CONFIG_PGSTE - pte_val(pte) &= ~_PAGE_SWR; -#endif + pte_val(pte) &= ~_PAGE_YOUNG; + pte_val(pte) |= _PAGE_INVALID; return pte; } static inline pte_t pte_mkyoung(pte_t pte) { + pte_val(pte) |= _PAGE_YOUNG; + if (pte_val(pte) & _PAGE_READ) + pte_val(pte) &= ~_PAGE_INVALID; return pte; } @@ -957,7 +986,7 @@ static inline pte_t pte_mkspecial(pte_t pte) #ifdef CONFIG_HUGETLB_PAGE static inline pte_t pte_mkhuge(pte_t pte) { - pte_val(pte) |= (_SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_CO); + pte_val(pte) |= _PAGE_LARGE; return pte; } #endif @@ -974,8 +1003,8 @@ static inline int ptep_test_and_clear_user_dirty(struct mm_struct *mm, if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); pgste = pgste_update_all(ptep, pgste); - dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT); - pgste_val(pgste) &= ~PGSTE_UC_BIT; + dirty = !!(pgste_val(pgste) & PGSTE_HC_BIT); + pgste_val(pgste) &= ~PGSTE_HC_BIT; pgste_set_unlock(ptep, pgste); return dirty; } @@ -994,59 +1023,75 @@ static inline int ptep_test_and_clear_user_young(struct mm_struct *mm, if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); pgste = pgste_update_young(ptep, pgste); - young = !!(pgste_val(pgste) & PGSTE_UR_BIT); - pgste_val(pgste) &= ~PGSTE_UR_BIT; + young = !!(pgste_val(pgste) & PGSTE_HR_BIT); + pgste_val(pgste) &= ~PGSTE_HR_BIT; pgste_set_unlock(ptep, pgste); } return young; } +static inline void __ptep_ipte(unsigned long address, pte_t *ptep) +{ + if (!(pte_val(*ptep) & _PAGE_INVALID)) { +#ifndef CONFIG_64BIT + /* pto must point to the start of the segment table */ + pte_t *pto = (pte_t *) (((unsigned long) ptep) & 0x7ffffc00); +#else + /* ipte in zarch mode can do the math */ + pte_t *pto = ptep; +#endif + asm volatile( + " ipte %2,%3" + : "=m" (*ptep) : "m" (*ptep), + "a" (pto), "a" (address)); + } +} + +static inline void ptep_flush_lazy(struct mm_struct *mm, + unsigned long address, pte_t *ptep) +{ + int active = (mm == current->active_mm) ? 1 : 0; + + if (atomic_read(&mm->context.attach_count) > active) + __ptep_ipte(address, ptep); + else + mm->context.flush_mm = 1; +} + #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pgste_t pgste; pte_t pte; + int young; if (mm_has_pgste(vma->vm_mm)) { pgste = pgste_get_lock(ptep); - pgste = pgste_update_young(ptep, pgste); - pte = *ptep; - *ptep = pte_mkold(pte); - pgste_set_unlock(ptep, pgste); - return pte_young(pte); + pgste = pgste_ipte_notify(vma->vm_mm, addr, ptep, pgste); } - return 0; + + pte = *ptep; + __ptep_ipte(addr, ptep); + young = pte_young(pte); + pte = pte_mkold(pte); + + if (mm_has_pgste(vma->vm_mm)) { + pgste_set_pte(ptep, pte); + pgste_set_unlock(ptep, pgste); + } else + *ptep = pte; + + return young; } #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH static inline int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { - /* No need to flush TLB - * On s390 reference bits are in storage key and never in TLB - * With virtualization we handle the reference bit, without we - * we can simply return */ return ptep_test_and_clear_young(vma, address, ptep); } -static inline void __ptep_ipte(unsigned long address, pte_t *ptep) -{ - if (!(pte_val(*ptep) & _PAGE_INVALID)) { -#ifndef CONFIG_64BIT - /* pto must point to the start of the segment table */ - pte_t *pto = (pte_t *) (((unsigned long) ptep) & 0x7ffffc00); -#else - /* ipte in zarch mode can do the math */ - pte_t *pto = ptep; -#endif - asm volatile( - " ipte %2,%3" - : "=m" (*ptep) : "m" (*ptep), - "a" (pto), "a" (address)); - } -} - /* * This is hard to understand. ptep_get_and_clear and ptep_clear_flush * both clear the TLB for the unmapped pte. The reason is that @@ -1067,16 +1112,14 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, pgste_t pgste; pte_t pte; - mm->context.flush_mm = 1; if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); pgste = pgste_ipte_notify(mm, address, ptep, pgste); } pte = *ptep; - if (!mm_exclusive(mm)) - __ptep_ipte(address, ptep); - pte_val(*ptep) = _PAGE_TYPE_EMPTY; + ptep_flush_lazy(mm, address, ptep); + pte_val(*ptep) = _PAGE_INVALID; if (mm_has_pgste(mm)) { pgste = pgste_update_all(&pte, pgste); @@ -1093,15 +1136,14 @@ static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, pgste_t pgste; pte_t pte; - mm->context.flush_mm = 1; if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); pgste_ipte_notify(mm, address, ptep, pgste); } pte = *ptep; - if (!mm_exclusive(mm)) - __ptep_ipte(address, ptep); + ptep_flush_lazy(mm, address, ptep); + pte_val(*ptep) |= _PAGE_INVALID; if (mm_has_pgste(mm)) { pgste = pgste_update_all(&pte, pgste); @@ -1117,7 +1159,7 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm, pgste_t pgste; if (mm_has_pgste(mm)) { - pgste = *(pgste_t *)(ptep + PTRS_PER_PTE); + pgste = pgste_get(ptep); pgste_set_key(ptep, pgste, pte); pgste_set_pte(ptep, pte); pgste_set_unlock(ptep, pgste); @@ -1139,7 +1181,7 @@ static inline pte_t ptep_clear_flush(struct vm_area_struct *vma, pte = *ptep; __ptep_ipte(address, ptep); - pte_val(*ptep) = _PAGE_TYPE_EMPTY; + pte_val(*ptep) = _PAGE_INVALID; if (mm_has_pgste(vma->vm_mm)) { pgste = pgste_update_all(&pte, pgste); @@ -1163,18 +1205,17 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, pgste_t pgste; pte_t pte; - if (mm_has_pgste(mm)) { + if (!full && mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); - if (!full) - pgste = pgste_ipte_notify(mm, address, ptep, pgste); + pgste = pgste_ipte_notify(mm, address, ptep, pgste); } pte = *ptep; if (!full) - __ptep_ipte(address, ptep); - pte_val(*ptep) = _PAGE_TYPE_EMPTY; + ptep_flush_lazy(mm, address, ptep); + pte_val(*ptep) = _PAGE_INVALID; - if (mm_has_pgste(mm)) { + if (!full && mm_has_pgste(mm)) { pgste = pgste_update_all(&pte, pgste); pgste_set_unlock(ptep, pgste); } @@ -1189,14 +1230,12 @@ static inline pte_t ptep_set_wrprotect(struct mm_struct *mm, pte_t pte = *ptep; if (pte_write(pte)) { - mm->context.flush_mm = 1; if (mm_has_pgste(mm)) { pgste = pgste_get_lock(ptep); pgste = pgste_ipte_notify(mm, address, ptep, pgste); } - if (!mm_exclusive(mm)) - __ptep_ipte(address, ptep); + ptep_flush_lazy(mm, address, ptep); pte = pte_wrprotect(pte); if (mm_has_pgste(mm)) { @@ -1240,7 +1279,7 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot) { pte_t __pte; pte_val(__pte) = physpage + pgprot_val(pgprot); - return __pte; + return pte_mkyoung(__pte); } static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) @@ -1248,10 +1287,8 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot) unsigned long physpage = page_to_phys(page); pte_t __pte = mk_pte_phys(physpage, pgprot); - if ((pte_val(__pte) & _PAGE_SWW) && PageDirty(page)) { - pte_val(__pte) |= _PAGE_SWC; - pte_val(__pte) &= ~_PAGE_RO; - } + if (pte_write(__pte) && PageDirty(page)) + __pte = pte_mkdirty(__pte); return __pte; } @@ -1313,7 +1350,7 @@ static inline void __pmd_idte(unsigned long address, pmd_t *pmdp) unsigned long sto = (unsigned long) pmdp - pmd_index(address) * sizeof(pmd_t); - if (!(pmd_val(*pmdp) & _SEGMENT_ENTRY_INV)) { + if (!(pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)) { asm volatile( " .insn rrf,0xb98e0000,%2,%3,0,0" : "=m" (*pmdp) @@ -1324,24 +1361,68 @@ static inline void __pmd_idte(unsigned long address, pmd_t *pmdp) } } +static inline void __pmd_csp(pmd_t *pmdp) +{ + register unsigned long reg2 asm("2") = pmd_val(*pmdp); + register unsigned long reg3 asm("3") = pmd_val(*pmdp) | + _SEGMENT_ENTRY_INVALID; + register unsigned long reg4 asm("4") = ((unsigned long) pmdp) + 5; + + asm volatile( + " csp %1,%3" + : "=m" (*pmdp) + : "d" (reg2), "d" (reg3), "d" (reg4), "m" (*pmdp) : "cc"); +} + #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE) static inline unsigned long massage_pgprot_pmd(pgprot_t pgprot) { /* - * pgprot is PAGE_NONE, PAGE_RO, or PAGE_RW (see __Pxxx / __Sxxx) + * pgprot is PAGE_NONE, PAGE_READ, or PAGE_WRITE (see __Pxxx / __Sxxx) * Convert to segment table entry format. */ if (pgprot_val(pgprot) == pgprot_val(PAGE_NONE)) return pgprot_val(SEGMENT_NONE); - if (pgprot_val(pgprot) == pgprot_val(PAGE_RO)) - return pgprot_val(SEGMENT_RO); - return pgprot_val(SEGMENT_RW); + if (pgprot_val(pgprot) == pgprot_val(PAGE_READ)) + return pgprot_val(SEGMENT_READ); + return pgprot_val(SEGMENT_WRITE); +} + +static inline pmd_t pmd_mkyoung(pmd_t pmd) +{ +#ifdef CONFIG_64BIT + if (pmd_prot_none(pmd)) { + pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; + } else { + pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG; + pmd_val(pmd) &= ~_SEGMENT_ENTRY_INVALID; + } +#endif + return pmd; +} + +static inline pmd_t pmd_mkold(pmd_t pmd) +{ +#ifdef CONFIG_64BIT + if (pmd_prot_none(pmd)) { + pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; + } else { + pmd_val(pmd) &= ~_SEGMENT_ENTRY_YOUNG; + pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; + } +#endif + return pmd; } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { + int young; + + young = pmd_young(pmd); pmd_val(pmd) &= _SEGMENT_CHG_MASK; pmd_val(pmd) |= massage_pgprot_pmd(newprot); + if (young) + pmd = pmd_mkyoung(pmd); return pmd; } @@ -1349,18 +1430,29 @@ static inline pmd_t mk_pmd_phys(unsigned long physpage, pgprot_t pgprot) { pmd_t __pmd; pmd_val(__pmd) = physpage + massage_pgprot_pmd(pgprot); - return __pmd; + return pmd_mkyoung(__pmd); } static inline pmd_t pmd_mkwrite(pmd_t pmd) { - /* Do not clobber _HPAGE_TYPE_NONE pages! */ - if (!(pmd_val(pmd) & _SEGMENT_ENTRY_INV)) - pmd_val(pmd) &= ~_SEGMENT_ENTRY_RO; + /* Do not clobber PROT_NONE segments! */ + if (!pmd_prot_none(pmd)) + pmd_val(pmd) &= ~_SEGMENT_ENTRY_PROTECT; return pmd; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLB_PAGE */ +static inline void pmdp_flush_lazy(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + int active = (mm == current->active_mm) ? 1 : 0; + + if ((atomic_read(&mm->context.attach_count) & 0xffff) > active) + __pmd_idte(address, pmdp); + else + mm->context.flush_mm = 1; +} + #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PGTABLE_DEPOSIT @@ -1378,7 +1470,7 @@ static inline int pmd_trans_splitting(pmd_t pmd) static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t entry) { - if (!(pmd_val(entry) & _SEGMENT_ENTRY_INV) && MACHINE_HAS_EDAT1) + if (!(pmd_val(entry) & _SEGMENT_ENTRY_INVALID) && MACHINE_HAS_EDAT1) pmd_val(entry) |= _SEGMENT_ENTRY_CO; *pmdp = entry; } @@ -1391,7 +1483,9 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd) static inline pmd_t pmd_wrprotect(pmd_t pmd) { - pmd_val(pmd) |= _SEGMENT_ENTRY_RO; + /* Do not clobber PROT_NONE segments! */ + if (!pmd_prot_none(pmd)) + pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; return pmd; } @@ -1401,50 +1495,16 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd) return pmd; } -static inline pmd_t pmd_mkold(pmd_t pmd) -{ - /* No referenced bit in the segment table entry. */ - return pmd; -} - -static inline pmd_t pmd_mkyoung(pmd_t pmd) -{ - /* No referenced bit in the segment table entry. */ - return pmd; -} - #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { - unsigned long pmd_addr = pmd_val(*pmdp) & HPAGE_MASK; - long tmp, rc; - int counter; + pmd_t pmd; - rc = 0; - if (MACHINE_HAS_RRBM) { - counter = PTRS_PER_PTE >> 6; - asm volatile( - "0: .insn rre,0xb9ae0000,%0,%3\n" /* rrbm */ - " ogr %1,%0\n" - " la %3,0(%4,%3)\n" - " brct %2,0b\n" - : "=&d" (tmp), "+&d" (rc), "+d" (counter), - "+a" (pmd_addr) - : "a" (64 * 4096UL) : "cc"); - rc = !!rc; - } else { - counter = PTRS_PER_PTE; - asm volatile( - "0: rrbe 0,%2\n" - " la %2,0(%3,%2)\n" - " brc 12,1f\n" - " lhi %0,1\n" - "1: brct %1,0b\n" - : "+d" (rc), "+d" (counter), "+a" (pmd_addr) - : "a" (4096UL) : "cc"); - } - return rc; + pmd = *pmdp; + __pmd_idte(address, pmdp); + *pmdp = pmd_mkold(pmd); + return pmd_young(pmd); } #define __HAVE_ARCH_PMDP_GET_AND_CLEAR @@ -1510,10 +1570,8 @@ static inline unsigned long pmd_pfn(pmd_t pmd) * exception will occur instead of a page translation exception. The * specifiation exception has the bad habit not to store necessary * information in the lowcore. - * Bit 21 and bit 22 are the page invalid bit and the page protection - * bit. We set both to indicate a swapped page. - * Bit 30 and 31 are used to distinguish the different page types. For - * a swapped page these bits need to be zero. + * 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. @@ -1527,10 +1585,8 @@ static inline unsigned long pmd_pfn(pmd_t pmd) * exception will occur instead of a page translation exception. The * specifiation exception has the bad habit not to store necessary * information in the lowcore. - * Bit 53 and bit 54 are the page invalid bit and the page protection - * bit. We set both to indicate a swapped page. - * Bit 62 and 63 are used to distinguish the different page types. For - * a swapped page these bits need to be zero. + * 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. @@ -1547,7 +1603,7 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) { pte_t pte; offset &= __SWP_OFFSET_MASK; - pte_val(pte) = _PAGE_TYPE_SWAP | ((type & 0x1f) << 2) | + pte_val(pte) = _PAGE_INVALID | _PAGE_TYPE | ((type & 0x1f) << 2) | ((offset & 1UL) << 7) | ((offset & ~1UL) << 11); return pte; } @@ -1570,7 +1626,7 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset) #define pgoff_to_pte(__off) \ ((pte_t) { ((((__off) & 0x7f) << 1) + (((__off) >> 7) << 12)) \ - | _PAGE_TYPE_FILE }) + | _PAGE_INVALID | _PAGE_PROTECT }) #endif /* !__ASSEMBLY__ */ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index b0e6435b2f02..0eb37505cab1 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -43,6 +43,7 @@ extern void execve_tail(void); #ifndef CONFIG_64BIT #define TASK_SIZE (1UL << 31) +#define TASK_MAX_SIZE (1UL << 31) #define TASK_UNMAPPED_BASE (1UL << 30) #else /* CONFIG_64BIT */ @@ -51,6 +52,7 @@ extern void execve_tail(void); #define TASK_UNMAPPED_BASE (test_thread_flag(TIF_31BIT) ? \ (1UL << 30) : (1UL << 41)) #define TASK_SIZE TASK_SIZE_OF(current) +#define TASK_MAX_SIZE (1UL << 53) #endif /* CONFIG_64BIT */ diff --git a/arch/s390/include/asm/serial.h b/arch/s390/include/asm/serial.h new file mode 100644 index 000000000000..5b3e48ef534b --- /dev/null +++ b/arch/s390/include/asm/serial.h @@ -0,0 +1,6 @@ +#ifndef _ASM_S390_SERIAL_H +#define _ASM_S390_SERIAL_H + +#define BASE_BAUD 0 + +#endif /* _ASM_S390_SERIAL_H */ diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h index 80b6f11263c4..6dbd559763c9 100644 --- a/arch/s390/include/asm/switch_to.h +++ b/arch/s390/include/asm/switch_to.h @@ -8,6 +8,7 @@ #define __ASM_SWITCH_TO_H #include <linux/thread_info.h> +#include <asm/ptrace.h> extern struct task_struct *__switch_to(void *, void *); extern void update_cr_regs(struct task_struct *task); @@ -68,12 +69,16 @@ static inline void restore_fp_regs(s390_fp_regs *fpregs) static inline void save_access_regs(unsigned int *acrs) { - asm volatile("stam 0,15,%0" : "=Q" (*acrs)); + typedef struct { int _[NUM_ACRS]; } acrstype; + + asm volatile("stam 0,15,%0" : "=Q" (*(acrstype *)acrs)); } static inline void restore_access_regs(unsigned int *acrs) { - asm volatile("lam 0,15,%0" : : "Q" (*acrs)); + typedef struct { int _[NUM_ACRS]; } acrstype; + + asm volatile("lam 0,15,%0" : : "Q" (*(acrstype *)acrs)); } #define switch_to(prev,next,last) do { \ diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index 6d6d92b4ea11..2cb846c4b37f 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -63,13 +63,14 @@ static inline void tlb_gather_mmu(struct mmu_gather *tlb, static inline void tlb_flush_mmu(struct mmu_gather *tlb) { + __tlb_flush_mm_lazy(tlb->mm); tlb_table_flush(tlb); } static inline void tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end) { - tlb_table_flush(tlb); + tlb_flush_mmu(tlb); } /* diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h index 6b32af30878c..f9fef0425fee 100644 --- a/arch/s390/include/asm/tlbflush.h +++ b/arch/s390/include/asm/tlbflush.h @@ -86,7 +86,7 @@ static inline void __tlb_flush_mm(struct mm_struct * mm) __tlb_flush_full(mm); } -static inline void __tlb_flush_mm_cond(struct mm_struct * mm) +static inline void __tlb_flush_mm_lazy(struct mm_struct * mm) { if (mm->context.flush_mm) { __tlb_flush_mm(mm); @@ -118,13 +118,13 @@ static inline void __tlb_flush_mm_cond(struct mm_struct * mm) static inline void flush_tlb_mm(struct mm_struct *mm) { - __tlb_flush_mm_cond(mm); + __tlb_flush_mm_lazy(mm); } static inline void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - __tlb_flush_mm_cond(vma->vm_mm); + __tlb_flush_mm_lazy(vma->vm_mm); } static inline void flush_tlb_kernel_range(unsigned long start, diff --git a/arch/s390/include/asm/vtime.h b/arch/s390/include/asm/vtime.h new file mode 100644 index 000000000000..af9896c53eb3 --- /dev/null +++ b/arch/s390/include/asm/vtime.h @@ -0,0 +1,7 @@ +#ifndef _S390_VTIME_H +#define _S390_VTIME_H + +#define __ARCH_HAS_VTIME_ACCOUNT +#define __ARCH_HAS_VTIME_TASK_SWITCH + +#endif /* _S390_VTIME_H */ diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index be7a408be7a1..cc30d1fb000c 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -18,6 +18,7 @@ #include <asm/unistd.h> #include <asm/page.h> #include <asm/sigp.h> +#include <asm/irq.h> __PT_R0 = __PT_GPRS __PT_R1 = __PT_GPRS + 4 @@ -435,6 +436,11 @@ io_skip: io_loop: l %r1,BASED(.Ldo_IRQ) lr %r2,%r11 # pass pointer to pt_regs + lhi %r3,IO_INTERRUPT + tm __PT_INT_CODE+8(%r11),0x80 # adapter interrupt ? + jz io_call + lhi %r3,THIN_INTERRUPT +io_call: basr %r14,%r1 # call do_IRQ tm __LC_MACHINE_FLAGS+2,0x10 # MACHINE_FLAG_LPAR jz io_return @@ -584,9 +590,10 @@ ext_skip: mvc __PT_INT_CODE(4,%r11),__LC_EXT_CPU_ADDR mvc __PT_INT_PARM(4,%r11),__LC_EXT_PARAMS TRACE_IRQS_OFF + l %r1,BASED(.Ldo_IRQ) lr %r2,%r11 # pass pointer to pt_regs - l %r1,BASED(.Ldo_extint) - basr %r14,%r1 # call do_extint + lhi %r3,EXT_INTERRUPT + basr %r14,%r1 # call do_IRQ j io_return /* @@ -879,13 +886,13 @@ cleanup_idle: stm %r9,%r10,__LC_SYSTEM_TIMER mvc __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2) # prepare return psw - n %r8,BASED(cleanup_idle_wait) # clear wait state bit + n %r8,BASED(cleanup_idle_wait) # clear irq & wait state bits l %r9,24(%r11) # return from psw_idle br %r14 cleanup_idle_insn: .long psw_idle_lpsw + 0x80000000 cleanup_idle_wait: - .long 0xfffdffff + .long 0xfcfdffff /* * Integer constants @@ -902,7 +909,6 @@ cleanup_idle_wait: .Ldo_machine_check: .long s390_do_machine_check .Lhandle_mcck: .long s390_handle_mcck .Ldo_IRQ: .long do_IRQ -.Ldo_extint: .long do_extint .Ldo_signal: .long do_signal .Ldo_notify_resume: .long do_notify_resume .Ldo_per_trap: .long do_per_trap diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S index 1c039d0c24c7..2b2188b97c6a 100644 --- a/arch/s390/kernel/entry64.S +++ b/arch/s390/kernel/entry64.S @@ -19,6 +19,7 @@ #include <asm/unistd.h> #include <asm/page.h> #include <asm/sigp.h> +#include <asm/irq.h> __PT_R0 = __PT_GPRS __PT_R1 = __PT_GPRS + 8 @@ -468,6 +469,11 @@ io_skip: xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) io_loop: lgr %r2,%r11 # pass pointer to pt_regs + lghi %r3,IO_INTERRUPT + tm __PT_INT_CODE+8(%r11),0x80 # adapter interrupt ? + jz io_call + lghi %r3,THIN_INTERRUPT +io_call: brasl %r14,do_IRQ tm __LC_MACHINE_FLAGS+6,0x10 # MACHINE_FLAG_LPAR jz io_return @@ -623,7 +629,8 @@ ext_skip: TRACE_IRQS_OFF xc __SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15) lgr %r2,%r11 # pass pointer to pt_regs - brasl %r14,do_extint + lghi %r3,EXT_INTERRUPT + brasl %r14,do_IRQ j io_return /* @@ -922,7 +929,7 @@ cleanup_idle: stg %r9,__LC_SYSTEM_TIMER mvc __LC_LAST_UPDATE_TIMER(8),__TIMER_IDLE_EXIT(%r2) # prepare return psw - nihh %r8,0xfffd # clear wait state bit + nihh %r8,0xfcfd # clear irq & wait state bits lg %r9,48(%r11) # return from psw_idle br %r14 cleanup_idle_insn: diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 54b0995514e8..b34ba0ea96a9 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -22,6 +22,7 @@ #include <asm/cputime.h> #include <asm/lowcore.h> #include <asm/irq.h> +#include <asm/hw_irq.h> #include "entry.h" DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_stat, irq_stat); @@ -42,9 +43,10 @@ struct irq_class { * Since the external and I/O interrupt fields are already sums we would end * up with having a sum which accounts each interrupt twice. */ -static const struct irq_class irqclass_main_desc[NR_IRQS] = { - [EXTERNAL_INTERRUPT] = {.name = "EXT"}, - [IO_INTERRUPT] = {.name = "I/O"} +static const struct irq_class irqclass_main_desc[NR_IRQS_BASE] = { + [EXT_INTERRUPT] = {.name = "EXT"}, + [IO_INTERRUPT] = {.name = "I/O"}, + [THIN_INTERRUPT] = {.name = "AIO"}, }; /* @@ -86,6 +88,28 @@ static const struct irq_class irqclass_sub_desc[NR_ARCH_IRQS] = { [CPU_RST] = {.name = "RST", .desc = "[CPU] CPU Restart"}, }; +void __init init_IRQ(void) +{ + irq_reserve_irqs(0, THIN_INTERRUPT); + init_cio_interrupts(); + init_airq_interrupts(); + init_ext_interrupts(); +} + +void do_IRQ(struct pt_regs *regs, int irq) +{ + struct pt_regs *old_regs; + + old_regs = set_irq_regs(regs); + irq_enter(); + if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator) + /* Serve timer interrupts first. */ + clock_comparator_work(); + generic_handle_irq(irq); + irq_exit(); + set_irq_regs(old_regs); +} + /* * show_interrupts is needed by /proc/interrupts. */ @@ -100,27 +124,36 @@ int show_interrupts(struct seq_file *p, void *v) for_each_online_cpu(cpu) seq_printf(p, "CPU%d ", cpu); seq_putc(p, '\n'); + goto out; } if (irq < NR_IRQS) { + if (irq >= NR_IRQS_BASE) + goto out; seq_printf(p, "%s: ", irqclass_main_desc[irq].name); for_each_online_cpu(cpu) - seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[irq]); + seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu)); seq_putc(p, '\n'); - goto skip_arch_irqs; + goto out; } for (irq = 0; irq < NR_ARCH_IRQS; irq++) { seq_printf(p, "%s: ", irqclass_sub_desc[irq].name); for_each_online_cpu(cpu) - seq_printf(p, "%10u ", per_cpu(irq_stat, cpu).irqs[irq]); + seq_printf(p, "%10u ", + per_cpu(irq_stat, cpu).irqs[irq]); if (irqclass_sub_desc[irq].desc) seq_printf(p, " %s", irqclass_sub_desc[irq].desc); seq_putc(p, '\n'); } -skip_arch_irqs: +out: put_online_cpus(); return 0; } +int arch_show_interrupts(struct seq_file *p, int prec) +{ + return 0; +} + /* * Switch to the asynchronous interrupt stack for softirq execution. */ @@ -159,14 +192,6 @@ asmlinkage void do_softirq(void) local_irq_restore(flags); } -#ifdef CONFIG_PROC_FS -void init_irq_proc(void) -{ - if (proc_mkdir("irq", NULL)) - create_prof_cpu_mask(); -} -#endif - /* * ext_int_hash[index] is the list head for all external interrupts that hash * to this index. @@ -183,14 +208,6 @@ struct ext_int_info { /* ext_int_hash_lock protects the handler lists for external interrupts */ DEFINE_SPINLOCK(ext_int_hash_lock); -static void __init init_external_interrupts(void) -{ - int idx; - - for (idx = 0; idx < ARRAY_SIZE(ext_int_hash); idx++) - INIT_LIST_HEAD(&ext_int_hash[idx]); -} - static inline int ext_hash(u16 code) { return (code + (code >> 9)) & 0xff; @@ -234,20 +251,13 @@ int unregister_external_interrupt(u16 code, ext_int_handler_t handler) } EXPORT_SYMBOL(unregister_external_interrupt); -void __irq_entry do_extint(struct pt_regs *regs) +static irqreturn_t do_ext_interrupt(int irq, void *dummy) { + struct pt_regs *regs = get_irq_regs(); struct ext_code ext_code; - struct pt_regs *old_regs; struct ext_int_info *p; int index; - old_regs = set_irq_regs(regs); - irq_enter(); - if (S390_lowcore.int_clock >= S390_lowcore.clock_comparator) { - /* Serve timer interrupts first. */ - clock_comparator_work(); - } - kstat_incr_irqs_this_cpu(EXTERNAL_INTERRUPT, NULL); ext_code = *(struct ext_code *) ®s->int_code; if (ext_code.code != 0x1004) __get_cpu_var(s390_idle).nohz_delay = 1; @@ -259,13 +269,25 @@ void __irq_entry do_extint(struct pt_regs *regs) p->handler(ext_code, regs->int_parm, regs->int_parm_long); rcu_read_unlock(); - irq_exit(); - set_irq_regs(old_regs); + + return IRQ_HANDLED; } -void __init init_IRQ(void) +static struct irqaction external_interrupt = { + .name = "EXT", + .handler = do_ext_interrupt, +}; + +void __init init_ext_interrupts(void) { - init_external_interrupts(); + int idx; + + for (idx = 0; idx < ARRAY_SIZE(ext_int_hash); idx++) + INIT_LIST_HEAD(&ext_int_hash[idx]); + + irq_set_chip_and_handler(EXT_INTERRUPT, + &dummy_irq_chip, handle_percpu_irq); + setup_irq(EXT_INTERRUPT, &external_interrupt); } static DEFINE_SPINLOCK(sc_irq_lock); @@ -313,69 +335,3 @@ void measurement_alert_subclass_unregister(void) spin_unlock(&ma_subclass_lock); } EXPORT_SYMBOL(measurement_alert_subclass_unregister); - -#ifdef CONFIG_SMP -void synchronize_irq(unsigned int irq) -{ - /* - * Not needed, the handler is protected by a lock and IRQs that occur - * after the handler is deleted are just NOPs. - */ -} -EXPORT_SYMBOL_GPL(synchronize_irq); -#endif - -#ifndef CONFIG_PCI - -/* Only PCI devices have dynamically-defined IRQ handlers */ - -int request_irq(unsigned int irq, irq_handler_t handler, - unsigned long irqflags, const char *devname, void *dev_id) -{ - return -EINVAL; -} -EXPORT_SYMBOL_GPL(request_irq); - -void free_irq(unsigned int irq, void *dev_id) -{ - WARN_ON(1); -} -EXPORT_SYMBOL_GPL(free_irq); - -void enable_irq(unsigned int irq) -{ - WARN_ON(1); -} -EXPORT_SYMBOL_GPL(enable_irq); - -void disable_irq(unsigned int irq) -{ - WARN_ON(1); -} -EXPORT_SYMBOL_GPL(disable_irq); - -#endif /* !CONFIG_PCI */ - -void disable_irq_nosync(unsigned int irq) -{ - disable_irq(irq); -} -EXPORT_SYMBOL_GPL(disable_irq_nosync); - -unsigned long probe_irq_on(void) -{ - return 0; -} -EXPORT_SYMBOL_GPL(probe_irq_on); - -int probe_irq_off(unsigned long val) -{ - return 0; -} -EXPORT_SYMBOL_GPL(probe_irq_off); - -unsigned int probe_irq_mask(unsigned long val) -{ - return val; -} -EXPORT_SYMBOL_GPL(probe_irq_mask); diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c index 3388b2b2a07d..adbbe7f1cb0d 100644 --- a/arch/s390/kernel/kprobes.c +++ b/arch/s390/kernel/kprobes.c @@ -105,14 +105,31 @@ static int __kprobes get_fixup_type(kprobe_opcode_t *insn) fixup |= FIXUP_RETURN_REGISTER; break; case 0xeb: - if ((insn[2] & 0xff) == 0x44 || /* bxhg */ - (insn[2] & 0xff) == 0x45) /* bxleg */ + switch (insn[2] & 0xff) { + case 0x44: /* bxhg */ + case 0x45: /* bxleg */ fixup = FIXUP_BRANCH_NOT_TAKEN; + break; + } break; case 0xe3: /* bctg */ if ((insn[2] & 0xff) == 0x46) fixup = FIXUP_BRANCH_NOT_TAKEN; break; + case 0xec: + switch (insn[2] & 0xff) { + case 0xe5: /* clgrb */ + case 0xe6: /* cgrb */ + case 0xf6: /* crb */ + case 0xf7: /* clrb */ + case 0xfc: /* cgib */ + case 0xfd: /* cglib */ + case 0xfe: /* cib */ + case 0xff: /* clib */ + fixup = FIXUP_BRANCH_NOT_TAKEN; + break; + } + break; } return fixup; } diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c index 504175ebf8b0..c4c033819879 100644 --- a/arch/s390/kernel/nmi.c +++ b/arch/s390/kernel/nmi.c @@ -214,10 +214,7 @@ static int notrace s390_revalidate_registers(struct mci *mci) : "0", "cc"); #endif /* Revalidate clock comparator register */ - if (S390_lowcore.clock_comparator == -1) - set_clock_comparator(S390_lowcore.mcck_clock); - else - set_clock_comparator(S390_lowcore.clock_comparator); + set_clock_comparator(S390_lowcore.clock_comparator); /* Check if old PSW is valid */ if (!mci->wp) /* diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 2bc3eddae34a..c5dbb335716d 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -71,6 +71,7 @@ void arch_cpu_idle(void) } /* Halt the cpu and keep track of cpu time accounting. */ vtime_stop_cpu(); + local_irq_enable(); } void arch_cpu_idle_exit(void) diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c index e9fadb04e3c6..9556905bd3ce 100644 --- a/arch/s390/kernel/ptrace.c +++ b/arch/s390/kernel/ptrace.c @@ -60,11 +60,11 @@ void update_cr_regs(struct task_struct *task) __ctl_store(cr, 0, 2); cr_new[1] = cr[1]; - /* Set or clear transaction execution TXC/PIFO bits 8 and 9. */ + /* Set or clear transaction execution TXC bit 8. */ if (task->thread.per_flags & PER_FLAG_NO_TE) - cr_new[0] = cr[0] & ~(3UL << 54); + cr_new[0] = cr[0] & ~(1UL << 55); else - cr_new[0] = cr[0] | (3UL << 54); + cr_new[0] = cr[0] | (1UL << 55); /* Set or clear transaction execution TDC bits 62 and 63. */ cr_new[2] = cr[2] & ~3UL; if (task->thread.per_flags & PER_FLAG_TE_ABORT_RAND) { @@ -1299,7 +1299,7 @@ int regs_query_register_offset(const char *name) if (!name || *name != 'r') return -EINVAL; - if (strict_strtoul(name + 1, 10, &offset)) + if (kstrtoul(name + 1, 10, &offset)) return -EINVAL; if (offset >= NUM_GPRS) return -EINVAL; diff --git a/arch/s390/kernel/suspend.c b/arch/s390/kernel/suspend.c index c479d2f9605b..737bff38e3ee 100644 --- a/arch/s390/kernel/suspend.c +++ b/arch/s390/kernel/suspend.c @@ -10,6 +10,9 @@ #include <linux/suspend.h> #include <linux/mm.h> #include <asm/ctl_reg.h> +#include <asm/ipl.h> +#include <asm/cio.h> +#include <asm/pci.h> /* * References to section boundaries @@ -211,3 +214,11 @@ void restore_processor_state(void) __ctl_set_bit(0,28); local_mcck_enable(); } + +/* Called at the end of swsusp_arch_resume */ +void s390_early_resume(void) +{ + lgr_info_log(); + channel_subsystem_reinit(); + zpci_rescan(); +} diff --git a/arch/s390/kernel/swsusp_asm64.S b/arch/s390/kernel/swsusp_asm64.S index c487be4cfc81..6b09fdffbd2f 100644 --- a/arch/s390/kernel/swsusp_asm64.S +++ b/arch/s390/kernel/swsusp_asm64.S @@ -281,11 +281,8 @@ restore_registers: lghi %r2,0 brasl %r14,arch_set_page_states - /* Log potential guest relocation */ - brasl %r14,lgr_info_log - - /* Reinitialize the channel subsystem */ - brasl %r14,channel_subsystem_reinit + /* Call arch specific early resume code */ + brasl %r14,s390_early_resume /* Return 0 */ lmg %r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15) diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c index 876546b9cfa1..064c3082ab33 100644 --- a/arch/s390/kernel/time.c +++ b/arch/s390/kernel/time.c @@ -92,7 +92,6 @@ void clock_comparator_work(void) struct clock_event_device *cd; S390_lowcore.clock_comparator = -1ULL; - set_clock_comparator(S390_lowcore.clock_comparator); cd = &__get_cpu_var(comparators); cd->event_handler(cd); } diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index d7776281cb60..05d75c413137 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -63,7 +63,7 @@ static int __init vdso_setup(char *s) else if (strncmp(s, "off", 4) == 0) vdso_enabled = 0; else { - rc = strict_strtoul(s, 0, &val); + rc = kstrtoul(s, 0, &val); vdso_enabled = rc ? 0 : !!val; } return !rc; @@ -113,11 +113,11 @@ int vdso_alloc_per_cpu(struct _lowcore *lowcore) clear_table((unsigned long *) segment_table, _SEGMENT_ENTRY_EMPTY, PAGE_SIZE << SEGMENT_ORDER); - clear_table((unsigned long *) page_table, _PAGE_TYPE_EMPTY, + clear_table((unsigned long *) page_table, _PAGE_INVALID, 256*sizeof(unsigned long)); *(unsigned long *) segment_table = _SEGMENT_ENTRY + page_table; - *(unsigned long *) page_table = _PAGE_RO + page_frame; + *(unsigned long *) page_table = _PAGE_PROTECT + page_frame; psal = (u32 *) (page_table + 256*sizeof(unsigned long)); aste = psal + 32; diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c index 9b9c1b78ec67..abcfab55f99b 100644 --- a/arch/s390/kernel/vtime.c +++ b/arch/s390/kernel/vtime.c @@ -19,6 +19,7 @@ #include <asm/irq_regs.h> #include <asm/cputime.h> #include <asm/vtimer.h> +#include <asm/vtime.h> #include <asm/irq.h> #include "entry.h" diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 3074475c8ae0..3a74d8af0d69 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -119,12 +119,21 @@ static int __diag_virtio_hypercall(struct kvm_vcpu *vcpu) * The layout is as follows: * - gpr 2 contains the subchannel id (passed as addr) * - gpr 3 contains the virtqueue index (passed as datamatch) + * - gpr 4 contains the index on the bus (optionally) */ - ret = kvm_io_bus_write(vcpu->kvm, KVM_VIRTIO_CCW_NOTIFY_BUS, - vcpu->run->s.regs.gprs[2], - 8, &vcpu->run->s.regs.gprs[3]); + ret = kvm_io_bus_write_cookie(vcpu->kvm, KVM_VIRTIO_CCW_NOTIFY_BUS, + vcpu->run->s.regs.gprs[2], + 8, &vcpu->run->s.regs.gprs[3], + vcpu->run->s.regs.gprs[4]); srcu_read_unlock(&vcpu->kvm->srcu, idx); - /* kvm_io_bus_write returns -EOPNOTSUPP if it found no match. */ + + /* + * Return cookie in gpr 2, but don't overwrite the register if the + * diagnose will be handled by userspace. + */ + if (ret != -EOPNOTSUPP) + vcpu->run->s.regs.gprs[2] = ret; + /* kvm_io_bus_write_cookie returns -EOPNOTSUPP if it found no match. */ return ret < 0 ? ret : 0; } diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 302e0e52b009..99d789e8a018 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -42,9 +42,11 @@ static inline void __user *__gptr_to_uptr(struct kvm_vcpu *vcpu, ({ \ __typeof__(gptr) __uptr = __gptr_to_uptr(vcpu, gptr, 1);\ int __mask = sizeof(__typeof__(*(gptr))) - 1; \ - int __ret = PTR_RET((void __force *)__uptr); \ + int __ret; \ \ - if (!__ret) { \ + if (IS_ERR((void __force *)__uptr)) { \ + __ret = PTR_ERR((void __force *)__uptr); \ + } else { \ BUG_ON((unsigned long)__uptr & __mask); \ __ret = get_user(x, __uptr); \ } \ @@ -55,9 +57,11 @@ static inline void __user *__gptr_to_uptr(struct kvm_vcpu *vcpu, ({ \ __typeof__(gptr) __uptr = __gptr_to_uptr(vcpu, gptr, 1);\ int __mask = sizeof(__typeof__(*(gptr))) - 1; \ - int __ret = PTR_RET((void __force *)__uptr); \ + int __ret; \ \ - if (!__ret) { \ + if (IS_ERR((void __force *)__uptr)) { \ + __ret = PTR_ERR((void __force *)__uptr); \ + } else { \ BUG_ON((unsigned long)__uptr & __mask); \ __ret = put_user(x, __uptr); \ } \ diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 34c1c9a90be2..776dafe918db 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -28,6 +28,7 @@ #include <asm/pgtable.h> #include <asm/nmi.h> #include <asm/switch_to.h> +#include <asm/facility.h> #include <asm/sclp.h> #include "kvm-s390.h" #include "gaccess.h" @@ -84,9 +85,15 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; -static unsigned long long *facilities; +unsigned long *vfacilities; static struct gmap_notifier gmap_notifier; +/* test availability of vfacility */ +static inline int test_vfacility(unsigned long nr) +{ + return __test_facility(nr, (void *) vfacilities); +} + /* Section: not file related */ int kvm_arch_hardware_enable(void *garbage) { @@ -387,7 +394,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->ecb = 6; vcpu->arch.sie_block->ecb2 = 8; vcpu->arch.sie_block->eca = 0xC1002001U; - vcpu->arch.sie_block->fac = (int) (long) facilities; + vcpu->arch.sie_block->fac = (int) (long) vfacilities; hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet, (unsigned long) vcpu); @@ -1063,6 +1070,10 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages) return 0; } +void kvm_arch_memslots_updated(struct kvm *kvm) +{ +} + /* Section: memory related */ int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, @@ -1129,20 +1140,20 @@ static int __init kvm_s390_init(void) * to hold the maximum amount of facilities. On the other hand, we * only set facilities that are known to work in KVM. */ - facilities = (unsigned long long *) get_zeroed_page(GFP_KERNEL|GFP_DMA); - if (!facilities) { + vfacilities = (unsigned long *) get_zeroed_page(GFP_KERNEL|GFP_DMA); + if (!vfacilities) { kvm_exit(); return -ENOMEM; } - memcpy(facilities, S390_lowcore.stfle_fac_list, 16); - facilities[0] &= 0xff82fff3f47c0000ULL; - facilities[1] &= 0x001c000000000000ULL; + memcpy(vfacilities, S390_lowcore.stfle_fac_list, 16); + vfacilities[0] &= 0xff82fff3f47c0000UL; + vfacilities[1] &= 0x001c000000000000UL; return 0; } static void __exit kvm_s390_exit(void) { - free_page((unsigned long) facilities); + free_page((unsigned long) vfacilities); kvm_exit(); } diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 028ca9fd2158..dc99f1ca4267 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -24,6 +24,9 @@ typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu); +/* declare vfacilities extern */ +extern unsigned long *vfacilities; + /* negativ values are error codes, positive values for internal conditions */ #define SIE_INTERCEPT_RERUNVCPU (1<<0) #define SIE_INTERCEPT_UCONTROL (1<<1) @@ -112,6 +115,13 @@ static inline u64 kvm_s390_get_base_disp_rs(struct kvm_vcpu *vcpu) return (base2 ? vcpu->run->s.regs.gprs[base2] : 0) + disp2; } +/* Set the condition code in the guest program status word */ +static inline void kvm_s390_set_psw_cc(struct kvm_vcpu *vcpu, unsigned long cc) +{ + vcpu->arch.sie_block->gpsw.mask &= ~(3UL << 44); + vcpu->arch.sie_block->gpsw.mask |= cc << 44; +} + int kvm_s390_handle_wait(struct kvm_vcpu *vcpu); enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer); void kvm_s390_tasklet(unsigned long parm); diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index 4cdc54e63ebc..59200ee275e5 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -164,8 +164,7 @@ static int handle_tpi(struct kvm_vcpu *vcpu) kfree(inti); no_interrupt: /* Set condition code and we're done. */ - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); - vcpu->arch.sie_block->gpsw.mask |= (cc & 3ul) << 44; + kvm_s390_set_psw_cc(vcpu, cc); return 0; } @@ -220,15 +219,13 @@ static int handle_io_inst(struct kvm_vcpu *vcpu) * Set condition code 3 to stop the guest from issueing channel * I/O instructions. */ - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); - vcpu->arch.sie_block->gpsw.mask |= (3 & 3ul) << 44; + kvm_s390_set_psw_cc(vcpu, 3); return 0; } } static int handle_stfl(struct kvm_vcpu *vcpu) { - unsigned int facility_list; int rc; vcpu->stat.instruction_stfl++; @@ -236,15 +233,13 @@ static int handle_stfl(struct kvm_vcpu *vcpu) if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - /* only pass the facility bits, which we can handle */ - facility_list = S390_lowcore.stfl_fac_list & 0xff82fff3; - rc = copy_to_guest(vcpu, offsetof(struct _lowcore, stfl_fac_list), - &facility_list, sizeof(facility_list)); + vfacilities, 4); if (rc) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - VCPU_EVENT(vcpu, 5, "store facility list value %x", facility_list); - trace_kvm_s390_handle_stfl(vcpu, facility_list); + VCPU_EVENT(vcpu, 5, "store facility list value %x", + *(unsigned int *) vfacilities); + trace_kvm_s390_handle_stfl(vcpu, *(unsigned int *) vfacilities); return 0; } @@ -387,7 +382,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); if (fc > 3) { - vcpu->arch.sie_block->gpsw.mask |= 3ul << 44; /* cc 3 */ + kvm_s390_set_psw_cc(vcpu, 3); return 0; } @@ -397,7 +392,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu) if (fc == 0) { vcpu->run->s.regs.gprs[0] = 3 << 28; - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); /* cc 0 */ + kvm_s390_set_psw_cc(vcpu, 0); return 0; } @@ -431,12 +426,11 @@ static int handle_stsi(struct kvm_vcpu *vcpu) } trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2); free_page(mem); - vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44); + kvm_s390_set_psw_cc(vcpu, 0); vcpu->run->s.regs.gprs[0] = 0; return 0; out_no_data: - /* condition code 3 */ - vcpu->arch.sie_block->gpsw.mask |= 3ul << 44; + kvm_s390_set_psw_cc(vcpu, 3); out_exception: free_page(mem); return rc; @@ -494,12 +488,12 @@ static int handle_epsw(struct kvm_vcpu *vcpu) kvm_s390_get_regs_rre(vcpu, ®1, ®2); /* This basically extracts the mask half of the psw. */ - vcpu->run->s.regs.gprs[reg1] &= 0xffffffff00000000; + vcpu->run->s.regs.gprs[reg1] &= 0xffffffff00000000UL; vcpu->run->s.regs.gprs[reg1] |= vcpu->arch.sie_block->gpsw.mask >> 32; if (reg2) { - vcpu->run->s.regs.gprs[reg2] &= 0xffffffff00000000; + vcpu->run->s.regs.gprs[reg2] &= 0xffffffff00000000UL; vcpu->run->s.regs.gprs[reg2] |= - vcpu->arch.sie_block->gpsw.mask & 0x00000000ffffffff; + vcpu->arch.sie_block->gpsw.mask & 0x00000000ffffffffUL; } return 0; } diff --git a/arch/s390/lib/delay.c b/arch/s390/lib/delay.c index c61b9fad43cc..57c87d7d7ede 100644 --- a/arch/s390/lib/delay.c +++ b/arch/s390/lib/delay.c @@ -44,7 +44,6 @@ static void __udelay_disabled(unsigned long long usecs) do { set_clock_comparator(end); vtime_stop_cpu(); - local_irq_disable(); } while (get_tod_clock() < end); lockdep_on(); __ctl_load(cr0, 0, 0); @@ -64,7 +63,6 @@ static void __udelay_enabled(unsigned long long usecs) set_clock_comparator(end); } vtime_stop_cpu(); - local_irq_disable(); if (clock_saved) local_tick_enable(clock_saved); } while (get_tod_clock() < end); diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c index 50ea137a2d3c..1694d738b175 100644 --- a/arch/s390/lib/uaccess_pt.c +++ b/arch/s390/lib/uaccess_pt.c @@ -86,28 +86,28 @@ static unsigned long follow_table(struct mm_struct *mm, switch (mm->context.asce_bits & _ASCE_TYPE_MASK) { case _ASCE_TYPE_REGION1: table = table + ((address >> 53) & 0x7ff); - if (unlikely(*table & _REGION_ENTRY_INV)) + if (unlikely(*table & _REGION_ENTRY_INVALID)) return -0x39UL; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); /* fallthrough */ case _ASCE_TYPE_REGION2: table = table + ((address >> 42) & 0x7ff); - if (unlikely(*table & _REGION_ENTRY_INV)) + if (unlikely(*table & _REGION_ENTRY_INVALID)) return -0x3aUL; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); /* fallthrough */ case _ASCE_TYPE_REGION3: table = table + ((address >> 31) & 0x7ff); - if (unlikely(*table & _REGION_ENTRY_INV)) + if (unlikely(*table & _REGION_ENTRY_INVALID)) return -0x3bUL; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); /* fallthrough */ case _ASCE_TYPE_SEGMENT: table = table + ((address >> 20) & 0x7ff); - if (unlikely(*table & _SEGMENT_ENTRY_INV)) + if (unlikely(*table & _SEGMENT_ENTRY_INVALID)) return -0x10UL; if (unlikely(*table & _SEGMENT_ENTRY_LARGE)) { - if (write && (*table & _SEGMENT_ENTRY_RO)) + if (write && (*table & _SEGMENT_ENTRY_PROTECT)) return -0x04UL; return (*table & _SEGMENT_ENTRY_ORIGIN_LARGE) + (address & ~_SEGMENT_ENTRY_ORIGIN_LARGE); @@ -117,7 +117,7 @@ static unsigned long follow_table(struct mm_struct *mm, table = table + ((address >> 12) & 0xff); if (unlikely(*table & _PAGE_INVALID)) return -0x11UL; - if (write && (*table & _PAGE_RO)) + if (write && (*table & _PAGE_PROTECT)) return -0x04UL; return (*table & PAGE_MASK) + (address & ~PAGE_MASK); } @@ -130,13 +130,13 @@ static unsigned long follow_table(struct mm_struct *mm, unsigned long *table = (unsigned long *)__pa(mm->pgd); table = table + ((address >> 20) & 0x7ff); - if (unlikely(*table & _SEGMENT_ENTRY_INV)) + if (unlikely(*table & _SEGMENT_ENTRY_INVALID)) return -0x10UL; table = (unsigned long *)(*table & _SEGMENT_ENTRY_ORIGIN); table = table + ((address >> 12) & 0xff); if (unlikely(*table & _PAGE_INVALID)) return -0x11UL; - if (write && (*table & _PAGE_RO)) + if (write && (*table & _PAGE_PROTECT)) return -0x04UL; return (*table & PAGE_MASK) + (address & ~PAGE_MASK); } diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c index 3ad65b04ac15..46d517c3c763 100644 --- a/arch/s390/mm/dump_pagetables.c +++ b/arch/s390/mm/dump_pagetables.c @@ -53,7 +53,7 @@ static void print_prot(struct seq_file *m, unsigned int pr, int level) seq_printf(m, "I\n"); return; } - seq_printf(m, "%s", pr & _PAGE_RO ? "RO " : "RW "); + seq_printf(m, "%s", pr & _PAGE_PROTECT ? "RO " : "RW "); seq_printf(m, "%s", pr & _PAGE_CO ? "CO " : " "); seq_putc(m, '\n'); } @@ -105,12 +105,12 @@ static void note_page(struct seq_file *m, struct pg_state *st, } /* - * The actual page table walker functions. In order to keep the implementation - * of print_prot() short, we only check and pass _PAGE_INVALID and _PAGE_RO - * flags to note_page() if a region, segment or page table entry is invalid or - * read-only. - * After all it's just a hint that the current level being walked contains an - * invalid or read-only entry. + * The actual page table walker functions. In order to keep the + * implementation of print_prot() short, we only check and pass + * _PAGE_INVALID and _PAGE_PROTECT flags to note_page() if a region, + * segment or page table entry is invalid or read-only. + * After all it's just a hint that the current level being walked + * contains an invalid or read-only entry. */ static void walk_pte_level(struct seq_file *m, struct pg_state *st, pmd_t *pmd, unsigned long addr) @@ -122,14 +122,14 @@ static void walk_pte_level(struct seq_file *m, struct pg_state *st, for (i = 0; i < PTRS_PER_PTE && addr < max_addr; i++) { st->current_address = addr; pte = pte_offset_kernel(pmd, addr); - prot = pte_val(*pte) & (_PAGE_RO | _PAGE_INVALID); + prot = pte_val(*pte) & (_PAGE_PROTECT | _PAGE_INVALID); note_page(m, st, prot, 4); addr += PAGE_SIZE; } } #ifdef CONFIG_64BIT -#define _PMD_PROT_MASK (_SEGMENT_ENTRY_RO | _SEGMENT_ENTRY_CO) +#define _PMD_PROT_MASK (_SEGMENT_ENTRY_PROTECT | _SEGMENT_ENTRY_CO) #else #define _PMD_PROT_MASK 0 #endif diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c index 1f5315d1215c..5d758db27bdc 100644 --- a/arch/s390/mm/gup.c +++ b/arch/s390/mm/gup.c @@ -24,7 +24,7 @@ static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr, pte_t *ptep, pte; struct page *page; - mask = (write ? _PAGE_RO : 0) | _PAGE_INVALID | _PAGE_SPECIAL; + mask = (write ? _PAGE_PROTECT : 0) | _PAGE_INVALID | _PAGE_SPECIAL; ptep = ((pte_t *) pmd_deref(pmd)) + pte_index(addr); do { @@ -55,8 +55,8 @@ static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr, struct page *head, *page, *tail; int refs; - result = write ? 0 : _SEGMENT_ENTRY_RO; - mask = result | _SEGMENT_ENTRY_INV; + result = write ? 0 : _SEGMENT_ENTRY_PROTECT; + mask = result | _SEGMENT_ENTRY_INVALID; if ((pmd_val(pmd) & mask) != result) return 0; VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT)); diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c index 121089d57802..248445f92604 100644 --- a/arch/s390/mm/hugetlbpage.c +++ b/arch/s390/mm/hugetlbpage.c @@ -8,21 +8,127 @@ #include <linux/mm.h> #include <linux/hugetlb.h> +static inline pmd_t __pte_to_pmd(pte_t pte) +{ + int none, young, prot; + pmd_t pmd; + + /* + * Convert encoding pte bits pmd bits + * .IR...wrdytp ..R...I...y. + * empty .10...000000 -> ..0...1...0. + * prot-none, clean, old .11...000001 -> ..0...1...1. + * prot-none, clean, young .11...000101 -> ..1...1...1. + * prot-none, dirty, old .10...001001 -> ..0...1...1. + * prot-none, dirty, young .10...001101 -> ..1...1...1. + * read-only, clean, old .11...010001 -> ..1...1...0. + * read-only, clean, young .01...010101 -> ..1...0...1. + * read-only, dirty, old .11...011001 -> ..1...1...0. + * read-only, dirty, young .01...011101 -> ..1...0...1. + * read-write, clean, old .11...110001 -> ..0...1...0. + * read-write, clean, young .01...110101 -> ..0...0...1. + * read-write, dirty, old .10...111001 -> ..0...1...0. + * read-write, dirty, young .00...111101 -> ..0...0...1. + * Huge ptes are dirty by definition, a clean pte is made dirty + * by the conversion. + */ + if (pte_present(pte)) { + pmd_val(pmd) = pte_val(pte) & PAGE_MASK; + if (pte_val(pte) & _PAGE_INVALID) + pmd_val(pmd) |= _SEGMENT_ENTRY_INVALID; + none = (pte_val(pte) & _PAGE_PRESENT) && + !(pte_val(pte) & _PAGE_READ) && + !(pte_val(pte) & _PAGE_WRITE); + prot = (pte_val(pte) & _PAGE_PROTECT) && + !(pte_val(pte) & _PAGE_WRITE); + young = pte_val(pte) & _PAGE_YOUNG; + if (none || young) + pmd_val(pmd) |= _SEGMENT_ENTRY_YOUNG; + if (prot || (none && young)) + pmd_val(pmd) |= _SEGMENT_ENTRY_PROTECT; + } else + pmd_val(pmd) = _SEGMENT_ENTRY_INVALID; + return pmd; +} + +static inline pte_t __pmd_to_pte(pmd_t pmd) +{ + pte_t pte; + + /* + * Convert encoding pmd bits pte bits + * ..R...I...y. .IR...wrdytp + * empty ..0...1...0. -> .10...000000 + * prot-none, old ..0...1...1. -> .10...001001 + * prot-none, young ..1...1...1. -> .10...001101 + * read-only, old ..1...1...0. -> .11...011001 + * read-only, young ..1...0...1. -> .01...011101 + * read-write, old ..0...1...0. -> .10...111001 + * read-write, young ..0...0...1. -> .00...111101 + * Huge ptes are dirty by definition + */ + if (pmd_present(pmd)) { + pte_val(pte) = _PAGE_PRESENT | _PAGE_LARGE | _PAGE_DIRTY | + (pmd_val(pmd) & PAGE_MASK); + if (pmd_val(pmd) & _SEGMENT_ENTRY_INVALID) + pte_val(pte) |= _PAGE_INVALID; + if (pmd_prot_none(pmd)) { + if (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT) + pte_val(pte) |= _PAGE_YOUNG; + } else { + pte_val(pte) |= _PAGE_READ; + if (pmd_val(pmd) & _SEGMENT_ENTRY_PROTECT) + pte_val(pte) |= _PAGE_PROTECT; + else + pte_val(pte) |= _PAGE_WRITE; + if (pmd_val(pmd) & _SEGMENT_ENTRY_YOUNG) + pte_val(pte) |= _PAGE_YOUNG; + } + } else + pte_val(pte) = _PAGE_INVALID; + return pte; +} void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *pteptr, pte_t pteval) + pte_t *ptep, pte_t pte) { - pmd_t *pmdp = (pmd_t *) pteptr; - unsigned long mask; + pmd_t pmd; + pmd = __pte_to_pmd(pte); if (!MACHINE_HAS_HPAGE) { - pteptr = (pte_t *) pte_page(pteval)[1].index; - mask = pte_val(pteval) & - (_SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO); - pte_val(pteval) = (_SEGMENT_ENTRY + __pa(pteptr)) | mask; + pmd_val(pmd) &= ~_SEGMENT_ENTRY_ORIGIN; + pmd_val(pmd) |= pte_page(pte)[1].index; + } else + pmd_val(pmd) |= _SEGMENT_ENTRY_LARGE | _SEGMENT_ENTRY_CO; + *(pmd_t *) ptep = pmd; +} + +pte_t huge_ptep_get(pte_t *ptep) +{ + unsigned long origin; + pmd_t pmd; + + pmd = *(pmd_t *) ptep; + if (!MACHINE_HAS_HPAGE && pmd_present(pmd)) { + origin = pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN; + pmd_val(pmd) &= ~_SEGMENT_ENTRY_ORIGIN; + pmd_val(pmd) |= *(unsigned long *) origin; } + return __pmd_to_pte(pmd); +} - pmd_val(*pmdp) = pte_val(pteval); +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + pmd_t *pmdp = (pmd_t *) ptep; + pte_t pte = huge_ptep_get(ptep); + + if (MACHINE_HAS_IDTE) + __pmd_idte(addr, pmdp); + else + __pmd_csp(pmdp); + pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY; + return pte; } int arch_prepare_hugepage(struct page *page) @@ -58,7 +164,7 @@ void arch_release_hugepage(struct page *page) ptep = (pte_t *) page[1].index; if (!ptep) return; - clear_table((unsigned long *) ptep, _PAGE_TYPE_EMPTY, + clear_table((unsigned long *) ptep, _PAGE_INVALID, PTRS_PER_PTE * sizeof(pte_t)); page_table_free(&init_mm, (unsigned long *) ptep); page[1].index = 0; diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 80adfbf75065..990397420e6b 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -118,7 +118,7 @@ void kernel_map_pages(struct page *page, int numpages, int enable) pte = pte_offset_kernel(pmd, address); if (!enable) { __ptep_ipte(address, pte); - pte_val(*pte) = _PAGE_TYPE_EMPTY; + pte_val(*pte) = _PAGE_INVALID; continue; } pte_val(*pte) = __pa(address); diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index a8154a1a2c94..bf7c0dc64a76 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -161,7 +161,7 @@ static int gmap_unlink_segment(struct gmap *gmap, unsigned long *table) struct gmap_rmap *rmap; struct page *page; - if (*table & _SEGMENT_ENTRY_INV) + if (*table & _SEGMENT_ENTRY_INVALID) return 0; page = pfn_to_page(*table >> PAGE_SHIFT); mp = (struct gmap_pgtable *) page->index; @@ -172,7 +172,7 @@ static int gmap_unlink_segment(struct gmap *gmap, unsigned long *table) kfree(rmap); break; } - *table = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr; + *table = mp->vmaddr | _SEGMENT_ENTRY_INVALID | _SEGMENT_ENTRY_PROTECT; return 1; } @@ -258,7 +258,7 @@ static int gmap_alloc_table(struct gmap *gmap, return -ENOMEM; new = (unsigned long *) page_to_phys(page); crst_table_init(new, init); - if (*table & _REGION_ENTRY_INV) { + if (*table & _REGION_ENTRY_INVALID) { list_add(&page->lru, &gmap->crst_list); *table = (unsigned long) new | _REGION_ENTRY_LENGTH | (*table & _REGION_ENTRY_TYPE_MASK); @@ -292,22 +292,22 @@ int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len) for (off = 0; off < len; off += PMD_SIZE) { /* Walk the guest addr space page table */ table = gmap->table + (((to + off) >> 53) & 0x7ff); - if (*table & _REGION_ENTRY_INV) + if (*table & _REGION_ENTRY_INVALID) goto out; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + (((to + off) >> 42) & 0x7ff); - if (*table & _REGION_ENTRY_INV) + if (*table & _REGION_ENTRY_INVALID) goto out; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + (((to + off) >> 31) & 0x7ff); - if (*table & _REGION_ENTRY_INV) + if (*table & _REGION_ENTRY_INVALID) goto out; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + (((to + off) >> 20) & 0x7ff); /* Clear segment table entry in guest address space. */ flush |= gmap_unlink_segment(gmap, table); - *table = _SEGMENT_ENTRY_INV; + *table = _SEGMENT_ENTRY_INVALID; } out: spin_unlock(&gmap->mm->page_table_lock); @@ -335,7 +335,7 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from, if ((from | to | len) & (PMD_SIZE - 1)) return -EINVAL; - if (len == 0 || from + len > PGDIR_SIZE || + if (len == 0 || from + len > TASK_MAX_SIZE || from + len < from || to + len < to) return -EINVAL; @@ -345,17 +345,17 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from, for (off = 0; off < len; off += PMD_SIZE) { /* Walk the gmap address space page table */ table = gmap->table + (((to + off) >> 53) & 0x7ff); - if ((*table & _REGION_ENTRY_INV) && + if ((*table & _REGION_ENTRY_INVALID) && gmap_alloc_table(gmap, table, _REGION2_ENTRY_EMPTY)) goto out_unmap; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + (((to + off) >> 42) & 0x7ff); - if ((*table & _REGION_ENTRY_INV) && + if ((*table & _REGION_ENTRY_INVALID) && gmap_alloc_table(gmap, table, _REGION3_ENTRY_EMPTY)) goto out_unmap; table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + (((to + off) >> 31) & 0x7ff); - if ((*table & _REGION_ENTRY_INV) && + if ((*table & _REGION_ENTRY_INVALID) && gmap_alloc_table(gmap, table, _SEGMENT_ENTRY_EMPTY)) goto out_unmap; table = (unsigned long *) (*table & _REGION_ENTRY_ORIGIN); @@ -363,7 +363,8 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from, /* Store 'from' address in an invalid segment table entry. */ flush |= gmap_unlink_segment(gmap, table); - *table = _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | (from + off); + *table = (from + off) | (_SEGMENT_ENTRY_INVALID | + _SEGMENT_ENTRY_PROTECT); } spin_unlock(&gmap->mm->page_table_lock); up_read(&gmap->mm->mmap_sem); @@ -384,15 +385,15 @@ static unsigned long *gmap_table_walk(unsigned long address, struct gmap *gmap) unsigned long *table; table = gmap->table + ((address >> 53) & 0x7ff); - if (unlikely(*table & _REGION_ENTRY_INV)) + if (unlikely(*table & _REGION_ENTRY_INVALID)) return ERR_PTR(-EFAULT); table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 42) & 0x7ff); - if (unlikely(*table & _REGION_ENTRY_INV)) + if (unlikely(*table & _REGION_ENTRY_INVALID)) return ERR_PTR(-EFAULT); table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 31) & 0x7ff); - if (unlikely(*table & _REGION_ENTRY_INV)) + if (unlikely(*table & _REGION_ENTRY_INVALID)) return ERR_PTR(-EFAULT); table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 20) & 0x7ff); @@ -422,11 +423,11 @@ unsigned long __gmap_translate(unsigned long address, struct gmap *gmap) return PTR_ERR(segment_ptr); /* Convert the gmap address to an mm address. */ segment = *segment_ptr; - if (!(segment & _SEGMENT_ENTRY_INV)) { + if (!(segment & _SEGMENT_ENTRY_INVALID)) { page = pfn_to_page(segment >> PAGE_SHIFT); mp = (struct gmap_pgtable *) page->index; return mp->vmaddr | (address & ~PMD_MASK); - } else if (segment & _SEGMENT_ENTRY_RO) { + } else if (segment & _SEGMENT_ENTRY_PROTECT) { vmaddr = segment & _SEGMENT_ENTRY_ORIGIN; return vmaddr | (address & ~PMD_MASK); } @@ -517,8 +518,8 @@ static void gmap_disconnect_pgtable(struct mm_struct *mm, unsigned long *table) page = pfn_to_page(__pa(table) >> PAGE_SHIFT); mp = (struct gmap_pgtable *) page->index; list_for_each_entry_safe(rmap, next, &mp->mapper, list) { - *rmap->entry = - _SEGMENT_ENTRY_INV | _SEGMENT_ENTRY_RO | mp->vmaddr; + *rmap->entry = mp->vmaddr | (_SEGMENT_ENTRY_INVALID | + _SEGMENT_ENTRY_PROTECT); list_del(&rmap->list); kfree(rmap); flush = 1; @@ -545,13 +546,13 @@ unsigned long __gmap_fault(unsigned long address, struct gmap *gmap) /* Convert the gmap address to an mm address. */ while (1) { segment = *segment_ptr; - if (!(segment & _SEGMENT_ENTRY_INV)) { + if (!(segment & _SEGMENT_ENTRY_INVALID)) { /* Page table is present */ page = pfn_to_page(segment >> PAGE_SHIFT); mp = (struct gmap_pgtable *) page->index; return mp->vmaddr | (address & ~PMD_MASK); } - if (!(segment & _SEGMENT_ENTRY_RO)) + if (!(segment & _SEGMENT_ENTRY_PROTECT)) /* Nothing mapped in the gmap address space. */ break; rc = gmap_connect_pgtable(address, segment, segment_ptr, gmap); @@ -586,25 +587,25 @@ void gmap_discard(unsigned long from, unsigned long to, struct gmap *gmap) while (address < to) { /* Walk the gmap address space page table */ table = gmap->table + ((address >> 53) & 0x7ff); - if (unlikely(*table & _REGION_ENTRY_INV)) { + if (unlikely(*table & _REGION_ENTRY_INVALID)) { address = (address + PMD_SIZE) & PMD_MASK; continue; } table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 42) & 0x7ff); - if (unlikely(*table & _REGION_ENTRY_INV)) { + if (unlikely(*table & _REGION_ENTRY_INVALID)) { address = (address + PMD_SIZE) & PMD_MASK; continue; } table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 31) & 0x7ff); - if (unlikely(*table & _REGION_ENTRY_INV)) { + if (unlikely(*table & _REGION_ENTRY_INVALID)) { address = (address + PMD_SIZE) & PMD_MASK; continue; } table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN); table = table + ((address >> 20) & 0x7ff); - if (unlikely(*table & _SEGMENT_ENTRY_INV)) { + if (unlikely(*table & _SEGMENT_ENTRY_INVALID)) { address = (address + PMD_SIZE) & PMD_MASK; continue; } @@ -687,7 +688,7 @@ int gmap_ipte_notify(struct gmap *gmap, unsigned long start, unsigned long len) continue; /* Set notification bit in the pgste of the pte */ entry = *ptep; - if ((pte_val(entry) & (_PAGE_INVALID | _PAGE_RO)) == 0) { + if ((pte_val(entry) & (_PAGE_INVALID | _PAGE_PROTECT)) == 0) { pgste = pgste_get_lock(ptep); pgste_val(pgste) |= PGSTE_IN_BIT; pgste_set_unlock(ptep, pgste); @@ -731,6 +732,11 @@ void gmap_do_ipte_notify(struct mm_struct *mm, unsigned long addr, pte_t *pte) spin_unlock(&gmap_notifier_lock); } +static inline int page_table_with_pgste(struct page *page) +{ + return atomic_read(&page->_mapcount) == 0; +} + static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, unsigned long vmaddr) { @@ -750,10 +756,11 @@ static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, mp->vmaddr = vmaddr & PMD_MASK; INIT_LIST_HEAD(&mp->mapper); page->index = (unsigned long) mp; - atomic_set(&page->_mapcount, 3); + atomic_set(&page->_mapcount, 0); table = (unsigned long *) page_to_phys(page); - clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/2); - clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2); + clear_table(table, _PAGE_INVALID, PAGE_SIZE/2); + clear_table(table + PTRS_PER_PTE, PGSTE_HR_BIT | PGSTE_HC_BIT, + PAGE_SIZE/2); return table; } @@ -791,26 +798,21 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr, pgste_val(new) |= (key & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48; pgste_val(new) |= (key & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56; if (!(pte_val(*ptep) & _PAGE_INVALID)) { - unsigned long address, bits; - unsigned char skey; + unsigned long address, bits, skey; address = pte_val(*ptep) & PAGE_MASK; - skey = page_get_storage_key(address); + skey = (unsigned long) page_get_storage_key(address); bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED); + skey = key & (_PAGE_ACC_BITS | _PAGE_FP_BIT); /* Set storage key ACC and FP */ - page_set_storage_key(address, - (key & (_PAGE_ACC_BITS | _PAGE_FP_BIT)), - !nq); - + page_set_storage_key(address, skey, !nq); /* Merge host changed & referenced into pgste */ pgste_val(new) |= bits << 52; - /* Transfer skey changed & referenced bit to kvm user bits */ - pgste_val(new) |= bits << 45; /* PGSTE_UR_BIT & PGSTE_UC_BIT */ } /* changing the guest storage key is considered a change of the page */ if ((pgste_val(new) ^ pgste_val(old)) & (PGSTE_ACC_BITS | PGSTE_FP_BIT | PGSTE_GR_BIT | PGSTE_GC_BIT)) - pgste_val(new) |= PGSTE_UC_BIT; + pgste_val(new) |= PGSTE_HC_BIT; pgste_set_unlock(ptep, new); pte_unmap_unlock(*ptep, ptl); @@ -821,6 +823,11 @@ EXPORT_SYMBOL(set_guest_storage_key); #else /* CONFIG_PGSTE */ +static inline int page_table_with_pgste(struct page *page) +{ + return 0; +} + static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm, unsigned long vmaddr) { @@ -878,7 +885,7 @@ unsigned long *page_table_alloc(struct mm_struct *mm, unsigned long vmaddr) pgtable_page_ctor(page); atomic_set(&page->_mapcount, 1); table = (unsigned long *) page_to_phys(page); - clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE); + clear_table(table, _PAGE_INVALID, PAGE_SIZE); spin_lock_bh(&mm->context.list_lock); list_add(&page->lru, &mm->context.pgtable_list); } else { @@ -897,12 +904,12 @@ void page_table_free(struct mm_struct *mm, unsigned long *table) struct page *page; unsigned int bit, mask; - if (mm_has_pgste(mm)) { + page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + if (page_table_with_pgste(page)) { gmap_disconnect_pgtable(mm, table); return page_table_free_pgste(table); } /* Free 1K/2K page table fragment of a 4K page */ - page = pfn_to_page(__pa(table) >> PAGE_SHIFT); bit = 1 << ((__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t))); spin_lock_bh(&mm->context.list_lock); if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK) @@ -940,14 +947,14 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table) unsigned int bit, mask; mm = tlb->mm; - if (mm_has_pgste(mm)) { + page = pfn_to_page(__pa(table) >> PAGE_SHIFT); + if (page_table_with_pgste(page)) { gmap_disconnect_pgtable(mm, table); table = (unsigned long *) (__pa(table) | FRAG_MASK); tlb_remove_table(tlb, table); return; } bit = 1 << ((__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t))); - page = pfn_to_page(__pa(table) >> PAGE_SHIFT); spin_lock_bh(&mm->context.list_lock); if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK) list_del(&page->lru); @@ -1007,7 +1014,6 @@ void tlb_table_flush(struct mmu_gather *tlb) struct mmu_table_batch **batch = &tlb->batch; if (*batch) { - __tlb_flush_mm(tlb->mm); call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu); *batch = NULL; } @@ -1017,11 +1023,12 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) { struct mmu_table_batch **batch = &tlb->batch; + tlb->mm->context.flush_mm = 1; if (*batch == NULL) { *batch = (struct mmu_table_batch *) __get_free_page(GFP_NOWAIT | __GFP_NOWARN); if (*batch == NULL) { - __tlb_flush_mm(tlb->mm); + __tlb_flush_mm_lazy(tlb->mm); tlb_remove_table_one(table); return; } @@ -1029,40 +1036,124 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table) } (*batch)->tables[(*batch)->nr++] = table; if ((*batch)->nr == MAX_TABLE_BATCH) - tlb_table_flush(tlb); + tlb_flush_mmu(tlb); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -void thp_split_vma(struct vm_area_struct *vma) +static inline void thp_split_vma(struct vm_area_struct *vma) { unsigned long addr; - struct page *page; - for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) { - page = follow_page(vma, addr, FOLL_SPLIT); - } + for (addr = vma->vm_start; addr < vma->vm_end; addr += PAGE_SIZE) + follow_page(vma, addr, FOLL_SPLIT); } -void thp_split_mm(struct mm_struct *mm) +static inline void thp_split_mm(struct mm_struct *mm) { - struct vm_area_struct *vma = mm->mmap; + struct vm_area_struct *vma; - while (vma != NULL) { + for (vma = mm->mmap; vma != NULL; vma = vma->vm_next) { thp_split_vma(vma); vma->vm_flags &= ~VM_HUGEPAGE; vma->vm_flags |= VM_NOHUGEPAGE; - vma = vma->vm_next; } + mm->def_flags |= VM_NOHUGEPAGE; +} +#else +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; + 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, addr); + if (!new) { + mm->context.has_pgste = 0; + continue; + } + spin_lock(&mm->page_table_lock); + 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); + new = NULL; + } + spin_unlock(&mm->page_table_lock); + 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); + } while (pud++, addr = next, addr != end); + + return addr; +} + +static void 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); + } while (pgd++, addr = next, addr != end); +} + /* * switch on pgstes for its userspace process (for kvm) */ int s390_enable_sie(void) { struct task_struct *tsk = current; - struct mm_struct *mm, *old_mm; + struct mm_struct *mm = tsk->mm; + struct mmu_gather tlb; /* Do we have switched amode? If no, we cannot do sie */ if (s390_user_mode == HOME_SPACE_MODE) @@ -1072,57 +1163,16 @@ int s390_enable_sie(void) if (mm_has_pgste(tsk->mm)) return 0; - /* lets check if we are allowed to replace the mm */ - task_lock(tsk); - if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 || -#ifdef CONFIG_AIO - !hlist_empty(&tsk->mm->ioctx_list) || -#endif - tsk->mm != tsk->active_mm) { - task_unlock(tsk); - return -EINVAL; - } - task_unlock(tsk); - - /* we copy the mm and let dup_mm create the page tables with_pgstes */ - tsk->mm->context.alloc_pgste = 1; - /* make sure that both mms have a correct rss state */ - sync_mm_rss(tsk->mm); - mm = dup_mm(tsk); - tsk->mm->context.alloc_pgste = 0; - if (!mm) - return -ENOMEM; - -#ifdef CONFIG_TRANSPARENT_HUGEPAGE + down_write(&mm->mmap_sem); /* split thp mappings and disable thp for future mappings */ thp_split_mm(mm); - mm->def_flags |= VM_NOHUGEPAGE; -#endif - - /* Now lets check again if something happened */ - task_lock(tsk); - if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 || -#ifdef CONFIG_AIO - !hlist_empty(&tsk->mm->ioctx_list) || -#endif - tsk->mm != tsk->active_mm) { - mmput(mm); - task_unlock(tsk); - return -EINVAL; - } - - /* ok, we are alone. No ptrace, no threads, etc. */ - old_mm = tsk->mm; - tsk->mm = tsk->active_mm = mm; - preempt_disable(); - update_mm(mm, tsk); - atomic_inc(&mm->context.attach_count); - atomic_dec(&old_mm->context.attach_count); - cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm)); - preempt_enable(); - task_unlock(tsk); - mmput(old_mm); - return 0; + /* Reallocate the page tables with pgstes */ + mm->context.has_pgste = 1; + tlb_gather_mmu(&tlb, mm, 0, TASK_SIZE); + page_table_realloc(&tlb, mm, 0, TASK_SIZE); + tlb_finish_mmu(&tlb, 0, TASK_SIZE); + up_write(&mm->mmap_sem); + return mm->context.has_pgste ? 0 : -ENOMEM; } EXPORT_SYMBOL_GPL(s390_enable_sie); @@ -1198,9 +1248,9 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) list_del(lh); } ptep = (pte_t *) pgtable; - pte_val(*ptep) = _PAGE_TYPE_EMPTY; + pte_val(*ptep) = _PAGE_INVALID; ptep++; - pte_val(*ptep) = _PAGE_TYPE_EMPTY; + pte_val(*ptep) = _PAGE_INVALID; return pgtable; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 8b268fcc4612..bcfb70b60be6 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -69,7 +69,7 @@ static pte_t __ref *vmem_pte_alloc(unsigned long address) pte = alloc_bootmem(PTRS_PER_PTE * sizeof(pte_t)); if (!pte) return NULL; - clear_table((unsigned long *) pte, _PAGE_TYPE_EMPTY, + clear_table((unsigned long *) pte, _PAGE_INVALID, PTRS_PER_PTE * sizeof(pte_t)); return pte; } @@ -101,7 +101,7 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro) !(address & ~PUD_MASK) && (address + PUD_SIZE <= end)) { pud_val(*pu_dir) = __pa(address) | _REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE | - (ro ? _REGION_ENTRY_RO : 0); + (ro ? _REGION_ENTRY_PROTECT : 0); address += PUD_SIZE; continue; } @@ -118,7 +118,8 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro) !(address & ~PMD_MASK) && (address + PMD_SIZE <= end)) { pmd_val(*pm_dir) = __pa(address) | _SEGMENT_ENTRY | _SEGMENT_ENTRY_LARGE | - (ro ? _SEGMENT_ENTRY_RO : 0); + _SEGMENT_ENTRY_YOUNG | + (ro ? _SEGMENT_ENTRY_PROTECT : 0); address += PMD_SIZE; continue; } @@ -131,7 +132,8 @@ static int vmem_add_mem(unsigned long start, unsigned long size, int ro) } pt_dir = pte_offset_kernel(pm_dir, address); - pte_val(*pt_dir) = __pa(address) | (ro ? _PAGE_RO : 0); + pte_val(*pt_dir) = __pa(address) | + pgprot_val(ro ? PAGE_KERNEL_RO : PAGE_KERNEL); address += PAGE_SIZE; } ret = 0; @@ -154,7 +156,7 @@ static void vmem_remove_range(unsigned long start, unsigned long size) pte_t *pt_dir; pte_t pte; - pte_val(pte) = _PAGE_TYPE_EMPTY; + pte_val(pte) = _PAGE_INVALID; while (address < end) { pg_dir = pgd_offset_k(address); if (pgd_none(*pg_dir)) { @@ -255,7 +257,8 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node) new_page =__pa(vmem_alloc_pages(0)); if (!new_page) goto out; - pte_val(*pt_dir) = __pa(new_page); + pte_val(*pt_dir) = + __pa(new_page) | pgprot_val(PAGE_KERNEL); } address += PAGE_SIZE; } diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile index 086a2e37935d..a9e1dc4ae442 100644 --- a/arch/s390/pci/Makefile +++ b/arch/s390/pci/Makefile @@ -2,5 +2,5 @@ # Makefile for the s390 PCI subsystem. # -obj-$(CONFIG_PCI) += pci.o pci_dma.o pci_clp.o pci_msi.o pci_sysfs.o \ +obj-$(CONFIG_PCI) += pci.o pci_dma.o pci_clp.o pci_sysfs.o \ pci_event.o pci_debug.o pci_insn.o diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index e2956ad39a4f..f17a8343e360 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -42,45 +42,26 @@ #define SIC_IRQ_MODE_SINGLE 1 #define ZPCI_NR_DMA_SPACES 1 -#define ZPCI_MSI_VEC_BITS 6 #define ZPCI_NR_DEVICES CONFIG_PCI_NR_FUNCTIONS /* list of all detected zpci devices */ -LIST_HEAD(zpci_list); -EXPORT_SYMBOL_GPL(zpci_list); -DEFINE_MUTEX(zpci_list_lock); -EXPORT_SYMBOL_GPL(zpci_list_lock); +static LIST_HEAD(zpci_list); +static DEFINE_SPINLOCK(zpci_list_lock); -static struct pci_hp_callback_ops *hotplug_ops; +static void zpci_enable_irq(struct irq_data *data); +static void zpci_disable_irq(struct irq_data *data); -static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES); -static DEFINE_SPINLOCK(zpci_domain_lock); - -struct callback { - irq_handler_t handler; - void *data; +static struct irq_chip zpci_irq_chip = { + .name = "zPCI", + .irq_unmask = zpci_enable_irq, + .irq_mask = zpci_disable_irq, }; -struct zdev_irq_map { - unsigned long aibv; /* AI bit vector */ - int msi_vecs; /* consecutive MSI-vectors used */ - int __unused; - struct callback cb[ZPCI_NR_MSI_VECS]; /* callback handler array */ - spinlock_t lock; /* protect callbacks against de-reg */ -}; - -struct intr_bucket { - /* amap of adapters, one bit per dev, corresponds to one irq nr */ - unsigned long *alloc; - /* AI summary bit, global page for all devices */ - unsigned long *aisb; - /* pointer to aibv and callback data in zdev */ - struct zdev_irq_map *imap[ZPCI_NR_DEVICES]; - /* protects the whole bucket struct */ - spinlock_t lock; -}; +static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES); +static DEFINE_SPINLOCK(zpci_domain_lock); -static struct intr_bucket *bucket; +static struct airq_iv *zpci_aisb_iv; +static struct airq_iv *zpci_aibv[ZPCI_NR_DEVICES]; /* Adapter interrupt definitions */ static void zpci_irq_handler(struct airq_struct *airq); @@ -96,27 +77,8 @@ static DECLARE_BITMAP(zpci_iomap, ZPCI_IOMAP_MAX_ENTRIES); struct zpci_iomap_entry *zpci_iomap_start; EXPORT_SYMBOL_GPL(zpci_iomap_start); -/* highest irq summary bit */ -static int __read_mostly aisb_max; - -static struct kmem_cache *zdev_irq_cache; static struct kmem_cache *zdev_fmb_cache; -static inline int irq_to_msi_nr(unsigned int irq) -{ - return irq & ZPCI_MSI_MASK; -} - -static inline int irq_to_dev_nr(unsigned int irq) -{ - return irq >> ZPCI_MSI_VEC_BITS; -} - -static inline struct zdev_irq_map *get_imap(unsigned int irq) -{ - return bucket->imap[irq_to_dev_nr(irq)]; -} - struct zpci_dev *get_zdev(struct pci_dev *pdev) { return (struct zpci_dev *) pdev->sysdata; @@ -126,22 +88,17 @@ struct zpci_dev *get_zdev_by_fid(u32 fid) { struct zpci_dev *tmp, *zdev = NULL; - mutex_lock(&zpci_list_lock); + spin_lock(&zpci_list_lock); list_for_each_entry(tmp, &zpci_list, entry) { if (tmp->fid == fid) { zdev = tmp; break; } } - mutex_unlock(&zpci_list_lock); + spin_unlock(&zpci_list_lock); return zdev; } -bool zpci_fid_present(u32 fid) -{ - return (get_zdev_by_fid(fid) != NULL) ? true : false; -} - static struct zpci_dev *get_zdev_by_bus(struct pci_bus *bus) { return (bus && bus->sysdata) ? (struct zpci_dev *) bus->sysdata : NULL; @@ -160,8 +117,7 @@ int pci_proc_domain(struct pci_bus *bus) EXPORT_SYMBOL_GPL(pci_proc_domain); /* Modify PCI: Register adapter interruptions */ -static int zpci_register_airq(struct zpci_dev *zdev, unsigned int aisb, - u64 aibv) +static int zpci_set_airq(struct zpci_dev *zdev) { u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT); struct zpci_fib *fib; @@ -172,14 +128,14 @@ static int zpci_register_airq(struct zpci_dev *zdev, unsigned int aisb, return -ENOMEM; fib->isc = PCI_ISC; - fib->noi = zdev->irq_map->msi_vecs; fib->sum = 1; /* enable summary notifications */ - fib->aibv = aibv; - fib->aibvo = 0; /* every function has its own page */ - fib->aisb = (u64) bucket->aisb + aisb / 8; - fib->aisbo = aisb & ZPCI_MSI_MASK; + fib->noi = airq_iv_end(zdev->aibv); + fib->aibv = (unsigned long) zdev->aibv->vector; + fib->aibvo = 0; /* each zdev has its own interrupt vector */ + fib->aisb = (unsigned long) zpci_aisb_iv->vector + (zdev->aisb/64)*8; + fib->aisbo = zdev->aisb & 63; - rc = s390pci_mod_fc(req, fib); + rc = zpci_mod_fc(req, fib); pr_debug("%s mpcifc returned noi: %d\n", __func__, fib->noi); free_page((unsigned long) fib); @@ -209,7 +165,7 @@ static int mod_pci(struct zpci_dev *zdev, int fn, u8 dmaas, struct mod_pci_args fib->iota = args->iota; fib->fmb_addr = args->fmb_addr; - rc = s390pci_mod_fc(req, fib); + rc = zpci_mod_fc(req, fib); free_page((unsigned long) fib); return rc; } @@ -234,7 +190,7 @@ int zpci_unregister_ioat(struct zpci_dev *zdev, u8 dmaas) } /* Modify PCI: Unregister adapter interruptions */ -static int zpci_unregister_airq(struct zpci_dev *zdev) +static int zpci_clear_airq(struct zpci_dev *zdev) { struct mod_pci_args args = { 0, 0, 0, 0 }; @@ -283,7 +239,7 @@ static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len) u64 data; int rc; - rc = s390pci_load(&data, req, offset); + rc = zpci_load(&data, req, offset); if (!rc) { data = data << ((8 - len) * 8); data = le64_to_cpu(data); @@ -301,25 +257,46 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len) data = cpu_to_le64(data); data = data >> ((8 - len) * 8); - rc = s390pci_store(data, req, offset); + rc = zpci_store(data, req, offset); return rc; } -void enable_irq(unsigned int irq) +static int zpci_msi_set_mask_bits(struct msi_desc *msi, u32 mask, u32 flag) +{ + int offset, pos; + u32 mask_bits; + + if (msi->msi_attrib.is_msix) { + offset = msi->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE + + PCI_MSIX_ENTRY_VECTOR_CTRL; + msi->masked = readl(msi->mask_base + offset); + writel(flag, msi->mask_base + offset); + } else if (msi->msi_attrib.maskbit) { + pos = (long) msi->mask_base; + pci_read_config_dword(msi->dev, pos, &mask_bits); + mask_bits &= ~(mask); + mask_bits |= flag & mask; + pci_write_config_dword(msi->dev, pos, mask_bits); + } else + return 0; + + msi->msi_attrib.maskbit = !!flag; + return 1; +} + +static void zpci_enable_irq(struct irq_data *data) { - struct msi_desc *msi = irq_get_msi_desc(irq); + struct msi_desc *msi = irq_get_msi_desc(data->irq); zpci_msi_set_mask_bits(msi, 1, 0); } -EXPORT_SYMBOL_GPL(enable_irq); -void disable_irq(unsigned int irq) +static void zpci_disable_irq(struct irq_data *data) { - struct msi_desc *msi = irq_get_msi_desc(irq); + struct msi_desc *msi = irq_get_msi_desc(data->irq); zpci_msi_set_mask_bits(msi, 1, 1); } -EXPORT_SYMBOL_GPL(disable_irq); void pcibios_fixup_bus(struct pci_bus *bus) { @@ -404,152 +381,147 @@ static struct pci_ops pci_root_ops = { .write = pci_write, }; -/* store the last handled bit to implement fair scheduling of devices */ -static DEFINE_PER_CPU(unsigned long, next_sbit); - static void zpci_irq_handler(struct airq_struct *airq) { - unsigned long sbit, mbit, last = 0, start = __get_cpu_var(next_sbit); - int rescan = 0, max = aisb_max; - struct zdev_irq_map *imap; + unsigned long si, ai; + struct airq_iv *aibv; + int irqs_on = 0; inc_irq_stat(IRQIO_PCI); - sbit = start; - -scan: - /* find summary_bit */ - for_each_set_bit_left_cont(sbit, bucket->aisb, max) { - clear_bit(63 - (sbit & 63), bucket->aisb + (sbit >> 6)); - last = sbit; + for (si = 0;;) { + /* Scan adapter summary indicator bit vector */ + si = airq_iv_scan(zpci_aisb_iv, si, airq_iv_end(zpci_aisb_iv)); + if (si == -1UL) { + if (irqs_on++) + /* End of second scan with interrupts on. */ + break; + /* First scan complete, reenable interrupts. */ + zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); + si = 0; + continue; + } - /* find vector bit */ - imap = bucket->imap[sbit]; - for_each_set_bit_left(mbit, &imap->aibv, imap->msi_vecs) { + /* Scan the adapter interrupt vector for this device. */ + aibv = zpci_aibv[si]; + for (ai = 0;;) { + ai = airq_iv_scan(aibv, ai, airq_iv_end(aibv)); + if (ai == -1UL) + break; inc_irq_stat(IRQIO_MSI); - clear_bit(63 - mbit, &imap->aibv); - - spin_lock(&imap->lock); - if (imap->cb[mbit].handler) - imap->cb[mbit].handler(mbit, - imap->cb[mbit].data); - spin_unlock(&imap->lock); + airq_iv_lock(aibv, ai); + generic_handle_irq(airq_iv_get_data(aibv, ai)); + airq_iv_unlock(aibv, ai); } } - - if (rescan) - goto out; - - /* scan the skipped bits */ - if (start > 0) { - sbit = 0; - max = start; - start = 0; - goto scan; - } - - /* enable interrupts again */ - set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); - - /* check again to not lose initiative */ - rmb(); - max = aisb_max; - sbit = find_first_bit_left(bucket->aisb, max); - if (sbit != max) { - rescan++; - goto scan; - } -out: - /* store next device bit to scan */ - __get_cpu_var(next_sbit) = (++last >= aisb_max) ? 0 : last; } -/* msi_vecs - number of requested interrupts, 0 place function to error state */ -static int zpci_setup_msi(struct pci_dev *pdev, int msi_vecs) +int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) { struct zpci_dev *zdev = get_zdev(pdev); - unsigned int aisb, msi_nr; + unsigned int hwirq, irq, msi_vecs; + unsigned long aisb; struct msi_desc *msi; + struct msi_msg msg; int rc; - /* store the number of used MSI vectors */ - zdev->irq_map->msi_vecs = min(msi_vecs, ZPCI_NR_MSI_VECS); - - spin_lock(&bucket->lock); - aisb = find_first_zero_bit(bucket->alloc, PAGE_SIZE); - /* alloc map exhausted? */ - if (aisb == PAGE_SIZE) { - spin_unlock(&bucket->lock); - return -EIO; - } - set_bit(aisb, bucket->alloc); - spin_unlock(&bucket->lock); + pr_debug("%s: requesting %d MSI-X interrupts...", __func__, nvec); + if (type != PCI_CAP_ID_MSIX && type != PCI_CAP_ID_MSI) + return -EINVAL; + msi_vecs = min(nvec, ZPCI_MSI_VEC_MAX); + msi_vecs = min_t(unsigned int, msi_vecs, CONFIG_PCI_NR_MSI); + /* Allocate adapter summary indicator bit */ + rc = -EIO; + aisb = airq_iv_alloc_bit(zpci_aisb_iv); + if (aisb == -1UL) + goto out; zdev->aisb = aisb; - if (aisb + 1 > aisb_max) - aisb_max = aisb + 1; - /* wire up IRQ shortcut pointer */ - bucket->imap[zdev->aisb] = zdev->irq_map; - pr_debug("%s: imap[%u] linked to %p\n", __func__, zdev->aisb, zdev->irq_map); + /* Create adapter interrupt vector */ + rc = -ENOMEM; + zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK); + if (!zdev->aibv) + goto out_si; - /* TODO: irq number 0 wont be found if we return less than requested MSIs. - * ignore it for now and fix in common code. - */ - msi_nr = aisb << ZPCI_MSI_VEC_BITS; + /* Wire up shortcut pointer */ + zpci_aibv[aisb] = zdev->aibv; + /* Request MSI interrupts */ + hwirq = 0; list_for_each_entry(msi, &pdev->msi_list, list) { - rc = zpci_setup_msi_irq(zdev, msi, msi_nr, - aisb << ZPCI_MSI_VEC_BITS); + rc = -EIO; + irq = irq_alloc_desc(0); /* Alloc irq on node 0 */ + if (irq == NO_IRQ) + goto out_msi; + rc = irq_set_msi_desc(irq, msi); if (rc) - return rc; - msi_nr++; + goto out_msi; + irq_set_chip_and_handler(irq, &zpci_irq_chip, + handle_simple_irq); + msg.data = hwirq; + msg.address_lo = zdev->msi_addr & 0xffffffff; + msg.address_hi = zdev->msi_addr >> 32; + write_msi_msg(irq, &msg); + airq_iv_set_data(zdev->aibv, hwirq, irq); + hwirq++; } - rc = zpci_register_airq(zdev, aisb, (u64) &zdev->irq_map->aibv); - if (rc) { - clear_bit(aisb, bucket->alloc); - dev_err(&pdev->dev, "register MSI failed with: %d\n", rc); - return rc; + /* Enable adapter interrupts */ + rc = zpci_set_airq(zdev); + if (rc) + goto out_msi; + + return (msi_vecs == nvec) ? 0 : msi_vecs; + +out_msi: + list_for_each_entry(msi, &pdev->msi_list, list) { + if (hwirq-- == 0) + break; + irq_set_msi_desc(msi->irq, NULL); + irq_free_desc(msi->irq); + msi->msg.address_lo = 0; + msi->msg.address_hi = 0; + msi->msg.data = 0; + msi->irq = 0; } - return (zdev->irq_map->msi_vecs == msi_vecs) ? - 0 : zdev->irq_map->msi_vecs; + zpci_aibv[aisb] = NULL; + airq_iv_release(zdev->aibv); +out_si: + airq_iv_free_bit(zpci_aisb_iv, aisb); +out: + dev_err(&pdev->dev, "register MSI failed with: %d\n", rc); + return rc; } -static void zpci_teardown_msi(struct pci_dev *pdev) +void arch_teardown_msi_irqs(struct pci_dev *pdev) { struct zpci_dev *zdev = get_zdev(pdev); struct msi_desc *msi; - int aisb, rc; + int rc; - rc = zpci_unregister_airq(zdev); + pr_info("%s: on pdev: %p\n", __func__, pdev); + + /* Disable adapter interrupts */ + rc = zpci_clear_airq(zdev); if (rc) { dev_err(&pdev->dev, "deregister MSI failed with: %d\n", rc); return; } - msi = list_first_entry(&pdev->msi_list, struct msi_desc, list); - aisb = irq_to_dev_nr(msi->irq); - - list_for_each_entry(msi, &pdev->msi_list, list) - zpci_teardown_msi_irq(zdev, msi); - - clear_bit(aisb, bucket->alloc); - if (aisb + 1 == aisb_max) - aisb_max--; -} - -int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) -{ - pr_debug("%s: requesting %d MSI-X interrupts...", __func__, nvec); - if (type != PCI_CAP_ID_MSIX && type != PCI_CAP_ID_MSI) - return -EINVAL; - return zpci_setup_msi(pdev, nvec); -} + /* Release MSI interrupts */ + list_for_each_entry(msi, &pdev->msi_list, list) { + zpci_msi_set_mask_bits(msi, 1, 1); + irq_set_msi_desc(msi->irq, NULL); + irq_free_desc(msi->irq); + msi->msg.address_lo = 0; + msi->msg.address_hi = 0; + msi->msg.data = 0; + msi->irq = 0; + } -void arch_teardown_msi_irqs(struct pci_dev *pdev) -{ - pr_info("%s: on pdev: %p\n", __func__, pdev); - zpci_teardown_msi(pdev); + zpci_aibv[zdev->aisb] = NULL; + airq_iv_release(zdev->aibv); + airq_iv_free_bit(zpci_aisb_iv, zdev->aisb); } static void zpci_map_resources(struct zpci_dev *zdev) @@ -564,8 +536,6 @@ static void zpci_map_resources(struct zpci_dev *zdev) continue; pdev->resource[i].start = (resource_size_t) pci_iomap(pdev, i, 0); pdev->resource[i].end = pdev->resource[i].start + len - 1; - pr_debug("BAR%i: -> start: %Lx end: %Lx\n", - i, pdev->resource[i].start, pdev->resource[i].end); } } @@ -589,162 +559,47 @@ struct zpci_dev *zpci_alloc_device(void) /* Alloc memory for our private pci device data */ zdev = kzalloc(sizeof(*zdev), GFP_KERNEL); - if (!zdev) - return ERR_PTR(-ENOMEM); - - /* Alloc aibv & callback space */ - zdev->irq_map = kmem_cache_zalloc(zdev_irq_cache, GFP_KERNEL); - if (!zdev->irq_map) - goto error; - WARN_ON((u64) zdev->irq_map & 0xff); - return zdev; - -error: - kfree(zdev); - return ERR_PTR(-ENOMEM); + return zdev ? : ERR_PTR(-ENOMEM); } void zpci_free_device(struct zpci_dev *zdev) { - kmem_cache_free(zdev_irq_cache, zdev->irq_map); kfree(zdev); } -/* - * Too late for any s390 specific setup, since interrupts must be set up - * already which requires DMA setup too and the pci scan will access the - * config space, which only works if the function handle is enabled. - */ -int pcibios_enable_device(struct pci_dev *pdev, int mask) -{ - struct resource *res; - u16 cmd; - int i; - - pci_read_config_word(pdev, PCI_COMMAND, &cmd); - - for (i = 0; i < PCI_BAR_COUNT; i++) { - res = &pdev->resource[i]; - - if (res->flags & IORESOURCE_IO) - return -EINVAL; - - if (res->flags & IORESOURCE_MEM) - cmd |= PCI_COMMAND_MEMORY; - } - pci_write_config_word(pdev, PCI_COMMAND, cmd); - return 0; -} - int pcibios_add_platform_entries(struct pci_dev *pdev) { return zpci_sysfs_add_device(&pdev->dev); } -int zpci_request_irq(unsigned int irq, irq_handler_t handler, void *data) -{ - int msi_nr = irq_to_msi_nr(irq); - struct zdev_irq_map *imap; - struct msi_desc *msi; - - msi = irq_get_msi_desc(irq); - if (!msi) - return -EIO; - - imap = get_imap(irq); - spin_lock_init(&imap->lock); - - pr_debug("%s: register handler for IRQ:MSI %d:%d\n", __func__, irq >> 6, msi_nr); - imap->cb[msi_nr].handler = handler; - imap->cb[msi_nr].data = data; - - /* - * The generic MSI code returns with the interrupt disabled on the - * card, using the MSI mask bits. Firmware doesn't appear to unmask - * at that level, so we do it here by hand. - */ - zpci_msi_set_mask_bits(msi, 1, 0); - return 0; -} - -void zpci_free_irq(unsigned int irq) -{ - struct zdev_irq_map *imap = get_imap(irq); - int msi_nr = irq_to_msi_nr(irq); - unsigned long flags; - - pr_debug("%s: for irq: %d\n", __func__, irq); - - spin_lock_irqsave(&imap->lock, flags); - imap->cb[msi_nr].handler = NULL; - imap->cb[msi_nr].data = NULL; - spin_unlock_irqrestore(&imap->lock, flags); -} - -int request_irq(unsigned int irq, irq_handler_t handler, - unsigned long irqflags, const char *devname, void *dev_id) -{ - pr_debug("%s: irq: %d handler: %p flags: %lx dev: %s\n", - __func__, irq, handler, irqflags, devname); - - return zpci_request_irq(irq, handler, dev_id); -} -EXPORT_SYMBOL_GPL(request_irq); - -void free_irq(unsigned int irq, void *dev_id) -{ - zpci_free_irq(irq); -} -EXPORT_SYMBOL_GPL(free_irq); - static int __init zpci_irq_init(void) { - int cpu, rc; - - bucket = kzalloc(sizeof(*bucket), GFP_KERNEL); - if (!bucket) - return -ENOMEM; - - bucket->aisb = (unsigned long *) get_zeroed_page(GFP_KERNEL); - if (!bucket->aisb) { - rc = -ENOMEM; - goto out_aisb; - } - - bucket->alloc = (unsigned long *) get_zeroed_page(GFP_KERNEL); - if (!bucket->alloc) { - rc = -ENOMEM; - goto out_alloc; - } + int rc; rc = register_adapter_interrupt(&zpci_airq); if (rc) - goto out_ai; + goto out; /* Set summary to 1 to be called every time for the ISC. */ *zpci_airq.lsi_ptr = 1; - for_each_online_cpu(cpu) - per_cpu(next_sbit, cpu) = 0; + rc = -ENOMEM; + zpci_aisb_iv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC); + if (!zpci_aisb_iv) + goto out_airq; - spin_lock_init(&bucket->lock); - set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); + zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC); return 0; -out_ai: - free_page((unsigned long) bucket->alloc); -out_alloc: - free_page((unsigned long) bucket->aisb); -out_aisb: - kfree(bucket); +out_airq: + unregister_adapter_interrupt(&zpci_airq); +out: return rc; } static void zpci_irq_exit(void) { - free_page((unsigned long) bucket->alloc); - free_page((unsigned long) bucket->aisb); + airq_iv_release(zpci_aisb_iv); unregister_adapter_interrupt(&zpci_airq); - kfree(bucket); } static struct resource *zpci_alloc_bus_resource(unsigned long start, unsigned long size, @@ -801,16 +656,49 @@ static void zpci_free_iomap(struct zpci_dev *zdev, int entry) int pcibios_add_device(struct pci_dev *pdev) { struct zpci_dev *zdev = get_zdev(pdev); + struct resource *res; + int i; + + zdev->pdev = pdev; + zpci_map_resources(zdev); + + for (i = 0; i < PCI_BAR_COUNT; i++) { + res = &pdev->resource[i]; + if (res->parent || !res->flags) + continue; + pci_claim_resource(pdev, i); + } + + return 0; +} + +int pcibios_enable_device(struct pci_dev *pdev, int mask) +{ + struct zpci_dev *zdev = get_zdev(pdev); + struct resource *res; + u16 cmd; + int i; zdev->pdev = pdev; zpci_debug_init_device(zdev); zpci_fmb_enable_device(zdev); zpci_map_resources(zdev); + pci_read_config_word(pdev, PCI_COMMAND, &cmd); + for (i = 0; i < PCI_BAR_COUNT; i++) { + res = &pdev->resource[i]; + + if (res->flags & IORESOURCE_IO) + return -EINVAL; + + if (res->flags & IORESOURCE_MEM) + cmd |= PCI_COMMAND_MEMORY; + } + pci_write_config_word(pdev, PCI_COMMAND, cmd); return 0; } -void pcibios_release_device(struct pci_dev *pdev) +void pcibios_disable_device(struct pci_dev *pdev) { struct zpci_dev *zdev = get_zdev(pdev); @@ -898,6 +786,8 @@ int zpci_enable_device(struct zpci_dev *zdev) rc = zpci_dma_init_device(zdev); if (rc) goto out_dma; + + zdev->state = ZPCI_FN_STATE_ONLINE; return 0; out_dma: @@ -926,18 +816,16 @@ int zpci_create_device(struct zpci_dev *zdev) rc = zpci_enable_device(zdev); if (rc) goto out_free; - - zdev->state = ZPCI_FN_STATE_ONLINE; } rc = zpci_scan_bus(zdev); if (rc) goto out_disable; - mutex_lock(&zpci_list_lock); + spin_lock(&zpci_list_lock); list_add_tail(&zdev->entry, &zpci_list); - if (hotplug_ops) - hotplug_ops->create_slot(zdev); - mutex_unlock(&zpci_list_lock); + spin_unlock(&zpci_list_lock); + + zpci_init_slot(zdev); return 0; @@ -967,15 +855,10 @@ static inline int barsize(u8 size) static int zpci_mem_init(void) { - zdev_irq_cache = kmem_cache_create("PCI_IRQ_cache", sizeof(struct zdev_irq_map), - L1_CACHE_BYTES, SLAB_HWCACHE_ALIGN, NULL); - if (!zdev_irq_cache) - goto error_zdev; - zdev_fmb_cache = kmem_cache_create("PCI_FMB_cache", sizeof(struct zpci_fmb), 16, 0, NULL); if (!zdev_fmb_cache) - goto error_fmb; + goto error_zdev; /* TODO: use realloc */ zpci_iomap_start = kzalloc(ZPCI_IOMAP_MAX_ENTRIES * sizeof(*zpci_iomap_start), @@ -986,8 +869,6 @@ static int zpci_mem_init(void) error_iomap: kmem_cache_destroy(zdev_fmb_cache); -error_fmb: - kmem_cache_destroy(zdev_irq_cache); error_zdev: return -ENOMEM; } @@ -995,28 +876,10 @@ error_zdev: static void zpci_mem_exit(void) { kfree(zpci_iomap_start); - kmem_cache_destroy(zdev_irq_cache); kmem_cache_destroy(zdev_fmb_cache); } -void zpci_register_hp_ops(struct pci_hp_callback_ops *ops) -{ - mutex_lock(&zpci_list_lock); - hotplug_ops = ops; - mutex_unlock(&zpci_list_lock); -} -EXPORT_SYMBOL_GPL(zpci_register_hp_ops); - -void zpci_deregister_hp_ops(void) -{ - mutex_lock(&zpci_list_lock); - hotplug_ops = NULL; - mutex_unlock(&zpci_list_lock); -} -EXPORT_SYMBOL_GPL(zpci_deregister_hp_ops); - -unsigned int s390_pci_probe; -EXPORT_SYMBOL_GPL(s390_pci_probe); +static unsigned int s390_pci_probe; char * __init pcibios_setup(char *str) { @@ -1044,16 +907,12 @@ static int __init pci_base_init(void) rc = zpci_debug_init(); if (rc) - return rc; + goto out; rc = zpci_mem_init(); if (rc) goto out_mem; - rc = zpci_msihash_init(); - if (rc) - goto out_hash; - rc = zpci_irq_init(); if (rc) goto out_irq; @@ -1062,7 +921,7 @@ static int __init pci_base_init(void) if (rc) goto out_dma; - rc = clp_find_pci_devices(); + rc = clp_scan_pci_devices(); if (rc) goto out_find; @@ -1073,11 +932,15 @@ out_find: out_dma: zpci_irq_exit(); out_irq: - zpci_msihash_exit(); -out_hash: zpci_mem_exit(); out_mem: zpci_debug_exit(); +out: return rc; } -subsys_initcall(pci_base_init); +subsys_initcall_sync(pci_base_init); + +void zpci_rescan(void) +{ + clp_rescan_pci_devices_simple(); +} diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c index 2e9539625d93..475563c3d1e4 100644 --- a/arch/s390/pci/pci_clp.c +++ b/arch/s390/pci/pci_clp.c @@ -36,9 +36,9 @@ static inline u8 clp_instr(void *data) return cc; } -static void *clp_alloc_block(void) +static void *clp_alloc_block(gfp_t gfp_mask) { - return (void *) __get_free_pages(GFP_KERNEL, get_order(CLP_BLK_SIZE)); + return (void *) __get_free_pages(gfp_mask, get_order(CLP_BLK_SIZE)); } static void clp_free_block(void *ptr) @@ -70,7 +70,7 @@ static int clp_query_pci_fngrp(struct zpci_dev *zdev, u8 pfgid) struct clp_req_rsp_query_pci_grp *rrb; int rc; - rrb = clp_alloc_block(); + rrb = clp_alloc_block(GFP_KERNEL); if (!rrb) return -ENOMEM; @@ -113,7 +113,7 @@ static int clp_query_pci_fn(struct zpci_dev *zdev, u32 fh) struct clp_req_rsp_query_pci *rrb; int rc; - rrb = clp_alloc_block(); + rrb = clp_alloc_block(GFP_KERNEL); if (!rrb) return -ENOMEM; @@ -179,9 +179,9 @@ error: static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command) { struct clp_req_rsp_set_pci *rrb; - int rc, retries = 1000; + int rc, retries = 100; - rrb = clp_alloc_block(); + rrb = clp_alloc_block(GFP_KERNEL); if (!rrb) return -ENOMEM; @@ -199,7 +199,7 @@ static int clp_set_pci_fn(u32 *fh, u8 nr_dma_as, u8 command) retries--; if (retries < 0) break; - msleep(1); + msleep(20); } } while (rrb->response.hdr.rsp == CLP_RC_SETPCIFN_BUSY); @@ -245,49 +245,12 @@ int clp_disable_fh(struct zpci_dev *zdev) return rc; } -static void clp_check_pcifn_entry(struct clp_fh_list_entry *entry) +static int clp_list_pci(struct clp_req_rsp_list_pci *rrb, + void (*cb)(struct clp_fh_list_entry *entry)) { - int present, rc; - - if (!entry->vendor_id) - return; - - /* TODO: be a little bit more scalable */ - present = zpci_fid_present(entry->fid); - - if (present) - pr_debug("%s: device %x already present\n", __func__, entry->fid); - - /* skip already used functions */ - if (present && entry->config_state) - return; - - /* aev 306: function moved to stand-by state */ - if (present && !entry->config_state) { - /* - * The handle is already disabled, that means no iota/irq freeing via - * the firmware interfaces anymore. Need to free resources manually - * (DMA memory, debug, sysfs)... - */ - zpci_stop_device(get_zdev_by_fid(entry->fid)); - return; - } - - rc = clp_add_pci_device(entry->fid, entry->fh, entry->config_state); - if (rc) - pr_err("Failed to add fid: 0x%x\n", entry->fid); -} - -int clp_find_pci_devices(void) -{ - struct clp_req_rsp_list_pci *rrb; u64 resume_token = 0; int entries, i, rc; - rrb = clp_alloc_block(); - if (!rrb) - return -ENOMEM; - do { memset(rrb, 0, sizeof(*rrb)); rrb->request.hdr.len = sizeof(rrb->request); @@ -316,12 +279,101 @@ int clp_find_pci_devices(void) resume_token = rrb->response.resume_token; for (i = 0; i < entries; i++) - clp_check_pcifn_entry(&rrb->response.fh_list[i]); + cb(&rrb->response.fh_list[i]); } while (resume_token); pr_debug("Maximum number of supported PCI functions: %u\n", rrb->response.max_fn); out: + return rc; +} + +static void __clp_add(struct clp_fh_list_entry *entry) +{ + if (!entry->vendor_id) + return; + + clp_add_pci_device(entry->fid, entry->fh, entry->config_state); +} + +static void __clp_rescan(struct clp_fh_list_entry *entry) +{ + struct zpci_dev *zdev; + + if (!entry->vendor_id) + return; + + zdev = get_zdev_by_fid(entry->fid); + if (!zdev) { + clp_add_pci_device(entry->fid, entry->fh, entry->config_state); + return; + } + + if (!entry->config_state) { + /* + * The handle is already disabled, that means no iota/irq freeing via + * the firmware interfaces anymore. Need to free resources manually + * (DMA memory, debug, sysfs)... + */ + zpci_stop_device(zdev); + } +} + +static void __clp_update(struct clp_fh_list_entry *entry) +{ + struct zpci_dev *zdev; + + if (!entry->vendor_id) + return; + + zdev = get_zdev_by_fid(entry->fid); + if (!zdev) + return; + + zdev->fh = entry->fh; +} + +int clp_scan_pci_devices(void) +{ + struct clp_req_rsp_list_pci *rrb; + int rc; + + rrb = clp_alloc_block(GFP_KERNEL); + if (!rrb) + return -ENOMEM; + + rc = clp_list_pci(rrb, __clp_add); + + clp_free_block(rrb); + return rc; +} + +int clp_rescan_pci_devices(void) +{ + struct clp_req_rsp_list_pci *rrb; + int rc; + + rrb = clp_alloc_block(GFP_KERNEL); + if (!rrb) + return -ENOMEM; + + rc = clp_list_pci(rrb, __clp_rescan); + + clp_free_block(rrb); + return rc; +} + +int clp_rescan_pci_devices_simple(void) +{ + struct clp_req_rsp_list_pci *rrb; + int rc; + + rrb = clp_alloc_block(GFP_NOWAIT); + if (!rrb) + return -ENOMEM; + + rc = clp_list_pci(rrb, __clp_update); + clp_free_block(rrb); return rc; } diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index a2343c1f6e04..7e5573acb063 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -10,6 +10,7 @@ #include <linux/export.h> #include <linux/iommu-helper.h> #include <linux/dma-mapping.h> +#include <linux/vmalloc.h> #include <linux/pci.h> #include <asm/pci_dma.h> @@ -170,8 +171,8 @@ static int dma_update_trans(struct zpci_dev *zdev, unsigned long pa, */ goto no_refresh; - rc = s390pci_refresh_trans((u64) zdev->fh << 32, start_dma_addr, - nr_pages * PAGE_SIZE); + rc = zpci_refresh_trans((u64) zdev->fh << 32, start_dma_addr, + nr_pages * PAGE_SIZE); no_refresh: spin_unlock_irqrestore(&zdev->dma_table_lock, irq_flags); @@ -407,7 +408,6 @@ static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int zpci_dma_init_device(struct zpci_dev *zdev) { - unsigned int bitmap_order; int rc; spin_lock_init(&zdev->iommu_bitmap_lock); @@ -421,12 +421,7 @@ int zpci_dma_init_device(struct zpci_dev *zdev) zdev->iommu_size = (unsigned long) high_memory - PAGE_OFFSET; zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT; - bitmap_order = get_order(zdev->iommu_pages / 8); - pr_info("iommu_size: 0x%lx iommu_pages: 0x%lx bitmap_order: %i\n", - zdev->iommu_size, zdev->iommu_pages, bitmap_order); - - zdev->iommu_bitmap = (void *) __get_free_pages(GFP_KERNEL | __GFP_ZERO, - bitmap_order); + zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8); if (!zdev->iommu_bitmap) { rc = -ENOMEM; goto out_reg; @@ -451,8 +446,7 @@ void zpci_dma_exit_device(struct zpci_dev *zdev) { zpci_unregister_ioat(zdev, 0); dma_cleanup_tables(zdev); - free_pages((unsigned long) zdev->iommu_bitmap, - get_order(zdev->iommu_pages / 8)); + vfree(zdev->iommu_bitmap); zdev->iommu_bitmap = NULL; zdev->next_bit = 0; } diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index ec62e3a0dc09..0aecaf954845 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -69,7 +69,7 @@ static void zpci_event_log_avail(struct zpci_ccdf_avail *ccdf) clp_add_pci_device(ccdf->fid, ccdf->fh, 0); break; case 0x0306: - clp_find_pci_devices(); + clp_rescan_pci_devices(); break; default: break; diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c index 22eeb9d7ffeb..85267c058af8 100644 --- a/arch/s390/pci/pci_insn.c +++ b/arch/s390/pci/pci_insn.c @@ -27,7 +27,7 @@ static inline u8 __mpcifc(u64 req, struct zpci_fib *fib, u8 *status) return cc; } -int s390pci_mod_fc(u64 req, struct zpci_fib *fib) +int zpci_mod_fc(u64 req, struct zpci_fib *fib) { u8 cc, status; @@ -61,7 +61,7 @@ static inline u8 __rpcit(u64 fn, u64 addr, u64 range, u8 *status) return cc; } -int s390pci_refresh_trans(u64 fn, u64 addr, u64 range) +int zpci_refresh_trans(u64 fn, u64 addr, u64 range) { u8 cc, status; @@ -78,7 +78,7 @@ int s390pci_refresh_trans(u64 fn, u64 addr, u64 range) } /* Set Interruption Controls */ -void set_irq_ctrl(u16 ctl, char *unused, u8 isc) +void zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc) { asm volatile ( " .insn rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n" @@ -109,7 +109,7 @@ static inline int __pcilg(u64 *data, u64 req, u64 offset, u8 *status) return cc; } -int s390pci_load(u64 *data, u64 req, u64 offset) +int zpci_load(u64 *data, u64 req, u64 offset) { u8 status; int cc; @@ -125,7 +125,7 @@ int s390pci_load(u64 *data, u64 req, u64 offset) __func__, cc, status, req, offset); return (cc > 0) ? -EIO : cc; } -EXPORT_SYMBOL_GPL(s390pci_load); +EXPORT_SYMBOL_GPL(zpci_load); /* PCI Store */ static inline int __pcistg(u64 data, u64 req, u64 offset, u8 *status) @@ -147,7 +147,7 @@ static inline int __pcistg(u64 data, u64 req, u64 offset, u8 *status) return cc; } -int s390pci_store(u64 data, u64 req, u64 offset) +int zpci_store(u64 data, u64 req, u64 offset) { u8 status; int cc; @@ -163,7 +163,7 @@ int s390pci_store(u64 data, u64 req, u64 offset) __func__, cc, status, req, offset); return (cc > 0) ? -EIO : cc; } -EXPORT_SYMBOL_GPL(s390pci_store); +EXPORT_SYMBOL_GPL(zpci_store); /* PCI Store Block */ static inline int __pcistb(const u64 *data, u64 req, u64 offset, u8 *status) @@ -183,7 +183,7 @@ static inline int __pcistb(const u64 *data, u64 req, u64 offset, u8 *status) return cc; } -int s390pci_store_block(const u64 *data, u64 req, u64 offset) +int zpci_store_block(const u64 *data, u64 req, u64 offset) { u8 status; int cc; @@ -199,4 +199,4 @@ int s390pci_store_block(const u64 *data, u64 req, u64 offset) __func__, cc, status, req, offset); return (cc > 0) ? -EIO : cc; } -EXPORT_SYMBOL_GPL(s390pci_store_block); +EXPORT_SYMBOL_GPL(zpci_store_block); diff --git a/arch/s390/pci/pci_msi.c b/arch/s390/pci/pci_msi.c deleted file mode 100644 index b097aed05a9b..000000000000 --- a/arch/s390/pci/pci_msi.c +++ /dev/null @@ -1,142 +0,0 @@ -/* - * Copyright IBM Corp. 2012 - * - * Author(s): - * Jan Glauber <jang@linux.vnet.ibm.com> - */ - -#define COMPONENT "zPCI" -#define pr_fmt(fmt) COMPONENT ": " fmt - -#include <linux/kernel.h> -#include <linux/err.h> -#include <linux/rculist.h> -#include <linux/hash.h> -#include <linux/pci.h> -#include <linux/msi.h> -#include <asm/hw_irq.h> - -/* mapping of irq numbers to msi_desc */ -static struct hlist_head *msi_hash; -static const unsigned int msi_hash_bits = 8; -#define MSI_HASH_BUCKETS (1U << msi_hash_bits) -#define msi_hashfn(nr) hash_long(nr, msi_hash_bits) - -static DEFINE_SPINLOCK(msi_map_lock); - -struct msi_desc *__irq_get_msi_desc(unsigned int irq) -{ - struct msi_map *map; - - hlist_for_each_entry_rcu(map, - &msi_hash[msi_hashfn(irq)], msi_chain) - if (map->irq == irq) - return map->msi; - return NULL; -} - -int zpci_msi_set_mask_bits(struct msi_desc *msi, u32 mask, u32 flag) -{ - if (msi->msi_attrib.is_msix) { - int offset = msi->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE + - PCI_MSIX_ENTRY_VECTOR_CTRL; - msi->masked = readl(msi->mask_base + offset); - writel(flag, msi->mask_base + offset); - } else { - if (msi->msi_attrib.maskbit) { - int pos; - u32 mask_bits; - - pos = (long) msi->mask_base; - pci_read_config_dword(msi->dev, pos, &mask_bits); - mask_bits &= ~(mask); - mask_bits |= flag & mask; - pci_write_config_dword(msi->dev, pos, mask_bits); - } else { - return 0; - } - } - - msi->msi_attrib.maskbit = !!flag; - return 1; -} - -int zpci_setup_msi_irq(struct zpci_dev *zdev, struct msi_desc *msi, - unsigned int nr, int offset) -{ - struct msi_map *map; - struct msi_msg msg; - int rc; - - map = kmalloc(sizeof(*map), GFP_KERNEL); - if (map == NULL) - return -ENOMEM; - - map->irq = nr; - map->msi = msi; - zdev->msi_map[nr & ZPCI_MSI_MASK] = map; - INIT_HLIST_NODE(&map->msi_chain); - - pr_debug("%s hashing irq: %u to bucket nr: %llu\n", - __func__, nr, msi_hashfn(nr)); - hlist_add_head_rcu(&map->msi_chain, &msi_hash[msi_hashfn(nr)]); - - spin_lock(&msi_map_lock); - rc = irq_set_msi_desc(nr, msi); - if (rc) { - spin_unlock(&msi_map_lock); - hlist_del_rcu(&map->msi_chain); - kfree(map); - zdev->msi_map[nr & ZPCI_MSI_MASK] = NULL; - return rc; - } - spin_unlock(&msi_map_lock); - - msg.data = nr - offset; - msg.address_lo = zdev->msi_addr & 0xffffffff; - msg.address_hi = zdev->msi_addr >> 32; - write_msi_msg(nr, &msg); - return 0; -} - -void zpci_teardown_msi_irq(struct zpci_dev *zdev, struct msi_desc *msi) -{ - int irq = msi->irq & ZPCI_MSI_MASK; - struct msi_map *map; - - msi->msg.address_lo = 0; - msi->msg.address_hi = 0; - msi->msg.data = 0; - msi->irq = 0; - zpci_msi_set_mask_bits(msi, 1, 1); - - spin_lock(&msi_map_lock); - map = zdev->msi_map[irq]; - hlist_del_rcu(&map->msi_chain); - kfree(map); - zdev->msi_map[irq] = NULL; - spin_unlock(&msi_map_lock); -} - -/* - * The msi hash table has 256 entries which is good for 4..20 - * devices (a typical device allocates 10 + CPUs MSI's). Maybe make - * the hash table size adjustable later. - */ -int __init zpci_msihash_init(void) -{ - unsigned int i; - - msi_hash = kmalloc(MSI_HASH_BUCKETS * sizeof(*msi_hash), GFP_KERNEL); - if (!msi_hash) - return -ENOMEM; - - for (i = 0; i < MSI_HASH_BUCKETS; i++) - INIT_HLIST_HEAD(&msi_hash[i]); - return 0; -} - -void __init zpci_msihash_exit(void) -{ - kfree(msi_hash); -} diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c index e99a2557f186..cf8a12ff733b 100644 --- a/arch/s390/pci/pci_sysfs.c +++ b/arch/s390/pci/pci_sysfs.c @@ -48,11 +48,38 @@ static ssize_t show_pfgid(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR(pfgid, S_IRUGO, show_pfgid, NULL); +static void recover_callback(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct zpci_dev *zdev = get_zdev(pdev); + int ret; + + pci_stop_and_remove_bus_device(pdev); + ret = zpci_disable_device(zdev); + if (ret) + return; + + ret = zpci_enable_device(zdev); + if (ret) + return; + + pci_rescan_bus(zdev->bus); +} + +static ssize_t store_recover(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + int rc = device_schedule_callback(dev, recover_callback); + return rc ? rc : count; +} +static DEVICE_ATTR(recover, S_IWUSR, NULL, store_recover); + static struct device_attribute *zpci_dev_attrs[] = { &dev_attr_function_id, &dev_attr_function_handle, &dev_attr_pchid, &dev_attr_pfgid, + &dev_attr_recover, NULL, }; diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 1020dd85431a..1018ed3a3ca5 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -643,9 +643,9 @@ config KEXEC It is an ongoing process to be certain the hardware in a machine is properly shutdown, so do not be surprised if this code does not - initially work for you. It may help to enable device hotplugging - support. As of this writing the exact hardware interface is - strongly in flux, so no good recommendation can be made. + initially work for you. As of this writing the exact hardware + interface is strongly in flux, so no good recommendation can be + made. config CRASH_DUMP bool "kernel crash dumps (EXPERIMENTAL)" diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c index 102f5d58b037..60ed3e1c4b75 100644 --- a/arch/sh/drivers/pci/pci.c +++ b/arch/sh/drivers/pci/pci.c @@ -69,7 +69,6 @@ static void pcibios_scanbus(struct pci_channel *hose) pci_bus_size_bridges(bus); pci_bus_assign_resources(bus); - pci_enable_bridges(bus); } else { pci_free_resource_list(&resources); } diff --git a/arch/sh/kernel/cpu/shmobile/cpuidle.c b/arch/sh/kernel/cpu/shmobile/cpuidle.c index d30622592116..e3abfd4277e2 100644 --- a/arch/sh/kernel/cpu/shmobile/cpuidle.c +++ b/arch/sh/kernel/cpu/shmobile/cpuidle.c @@ -91,13 +91,11 @@ static struct cpuidle_driver cpuidle_driver = { int __init sh_mobile_setup_cpuidle(void) { - int ret; - if (sh_mobile_sleep_supported & SUSP_SH_SF) cpuidle_driver.states[1].disabled = false; if (sh_mobile_sleep_supported & SUSP_SH_STANDBY) cpuidle_driver.states[2].disabled = false; - return cpuidle_register(&cpuidle_driver); + return cpuidle_register(&cpuidle_driver, NULL); } diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h index d5e86c9f74fd..d15c0d8d550f 100644 --- a/arch/tile/include/asm/topology.h +++ b/arch/tile/include/asm/topology.h @@ -89,9 +89,6 @@ static inline const struct cpumask *cpumask_of_node(int node) #define topology_core_id(cpu) (cpu) #define topology_core_cpumask(cpu) ((void)(cpu), cpu_online_mask) #define topology_thread_cpumask(cpu) cpumask_of(cpu) - -/* indicates that pointers to the topology struct cpumask maps are valid */ -#define arch_provides_topology_pointers yes #endif #endif /* _ASM_TILE_TOPOLOGY_H */ diff --git a/arch/tile/kernel/pci_gx.c b/arch/tile/kernel/pci_gx.c index 11425633b2d7..6640e7bbeaa2 100644 --- a/arch/tile/kernel/pci_gx.c +++ b/arch/tile/kernel/pci_gx.c @@ -508,13 +508,8 @@ static void fixup_read_and_payload_sizes(struct pci_controller *controller) rc_dev_cap.word); /* Configure PCI Express MPS setting. */ - list_for_each_entry(child, &root_bus->children, node) { - struct pci_dev *self = child->self; - if (!self) - continue; - - pcie_bus_configure_settings(child, self->pcie_mpss); - } + list_for_each_entry(child, &root_bus->children, node) + pcie_bus_configure_settings(child); /* * Set the mac_config register in trio based on the MPS/MRS of the link. diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index b32ebf92b0ce..5c0ed72c02a2 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -16,6 +16,7 @@ config X86_64 def_bool y depends on 64BIT select X86_DEV_DMA_OPS + select ARCH_USE_CMPXCHG_LOCKREF ### Arch settings config X86 @@ -81,7 +82,6 @@ config X86 select HAVE_USER_RETURN_NOTIFIER select ARCH_BINFMT_ELF_RANDOMIZE_PIE select HAVE_ARCH_JUMP_LABEL - select HAVE_TEXT_POKE_SMP select HAVE_GENERIC_HARDIRQS select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE select SPARSE_IRQ @@ -632,6 +632,7 @@ config PARAVIRT_DEBUG config PARAVIRT_SPINLOCKS bool "Paravirtualization layer for spinlocks" depends on PARAVIRT && SMP + select UNINLINE_SPIN_UNLOCK ---help--- Paravirtualized spinlocks allow a pvops backend to replace the spinlock implementation with something virtualization-friendly @@ -656,6 +657,15 @@ config KVM_GUEST underlying device model, the host provides the guest with timing infrastructure such as time of day, and system time +config KVM_DEBUG_FS + bool "Enable debug information for KVM Guests in debugfs" + depends on KVM_GUEST && DEBUG_FS + default n + ---help--- + This option enables collection of various statistics for KVM guest. + Statistics are displayed in debugfs filesystem. Enabling this option + may incur significant overhead. + source "arch/x86/lguest/Kconfig" config PARAVIRT_TIME_ACCOUNTING @@ -1344,8 +1354,12 @@ config ARCH_SELECT_MEMORY_MODEL depends on ARCH_SPARSEMEM_ENABLE config ARCH_MEMORY_PROBE - def_bool y + bool "Enable sysfs memory/probe interface" depends on X86_64 && MEMORY_HOTPLUG + help + This option enables a sysfs memory/probe interface for testing. + See Documentation/memory-hotplug.txt for more information. + If you are unsure how to answer this question, answer N. config ARCH_PROC_KCORE_TEXT def_bool y @@ -1627,9 +1641,9 @@ config KEXEC It is an ongoing process to be certain the hardware in a machine is properly shutdown, so do not be surprised if this code does not - initially work for you. It may help to enable device hotplugging - support. As of this writing the exact hardware interface is - strongly in flux, so no good recommendation can be made. + initially work for you. As of this writing the exact hardware + interface is strongly in flux, so no good recommendation can be + made. config CRASH_DUMP bool "kernel crash dumps" @@ -1716,9 +1730,10 @@ config X86_NEED_RELOCS depends on X86_32 && RELOCATABLE config PHYSICAL_ALIGN - hex "Alignment value to which kernel should be aligned" if X86_32 + hex "Alignment value to which kernel should be aligned" default "0x1000000" - range 0x2000 0x1000000 + range 0x2000 0x1000000 if X86_32 + range 0x200000 0x1000000 if X86_64 ---help--- This value puts the alignment restrictions on physical address where kernel is loaded and run from. Kernel is compiled for an @@ -1736,6 +1751,9 @@ config PHYSICAL_ALIGN end result is that kernel runs from a physical address meeting above alignment restrictions. + On 32-bit this value must be a multiple of 0x2000. On 64-bit + this value must be a multiple of 0x200000. + Don't change this unless you know what you are doing. config HOTPLUG_CPU @@ -2270,6 +2288,32 @@ config RAPIDIO source "drivers/rapidio/Kconfig" +config X86_SYSFB + bool "Mark VGA/VBE/EFI FB as generic system framebuffer" + help + Firmwares often provide initial graphics framebuffers so the BIOS, + bootloader or kernel can show basic video-output during boot for + user-guidance and debugging. Historically, x86 used the VESA BIOS + Extensions and EFI-framebuffers for this, which are mostly limited + to x86. + This option, if enabled, marks VGA/VBE/EFI framebuffers as generic + framebuffers so the new generic system-framebuffer drivers can be + used on x86. If the framebuffer is not compatible with the generic + modes, it is adverticed as fallback platform framebuffer so legacy + drivers like efifb, vesafb and uvesafb can pick it up. + If this option is not selected, all system framebuffers are always + marked as fallback platform framebuffers as usual. + + Note: Legacy fbdev drivers, including vesafb, efifb, uvesafb, will + not be able to pick up generic system framebuffers if this option + is selected. You are highly encouraged to enable simplefb as + replacement if you select this option. simplefb can correctly deal + with generic system framebuffers. But you should still keep vesafb + and others enabled as fallback if a system framebuffer is + incompatible with simplefb. + + If unsure, say Y. + endmenu @@ -2332,10 +2376,6 @@ config HAVE_ATOMIC_IOMAP def_bool y depends on X86_32 -config HAVE_TEXT_POKE_SMP - bool - select STOP_MACHINE if SMP - config X86_DEV_DMA_OPS bool depends on X86_64 || STA2X11 diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 07639c656fcd..41250fb33985 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -16,6 +16,10 @@ endif # e.g.: obj-y += foo_$(BITS).o export BITS +ifdef CONFIG_X86_NEED_RELOCS + LDFLAGS_vmlinux := --emit-relocs +endif + ifeq ($(CONFIG_X86_32),y) BITS := 32 UTS_MACHINE := i386 @@ -25,10 +29,6 @@ ifeq ($(CONFIG_X86_32),y) KBUILD_AFLAGS += $(biarch) KBUILD_CFLAGS += $(biarch) - ifdef CONFIG_RELOCATABLE - LDFLAGS_vmlinux := --emit-relocs - endif - KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return # Never want PIC in a 32-bit kernel, prevent breakage with GCC built diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index 5b7531966b84..ef72baeff484 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -355,6 +355,7 @@ int strncmp(const char *cs, const char *ct, size_t count); size_t strnlen(const char *s, size_t maxlen); unsigned int atou(const char *s); unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base); +size_t strlen(const char *s); /* tty.c */ void puts(const char *); diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 1e3184f6072f..5d6f6891b188 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -181,8 +181,9 @@ relocated: /* * Do the decompression, and jump to the new kernel.. */ - leal z_extract_offset_negative(%ebx), %ebp /* push arguments for decompress_kernel: */ + pushl $z_output_len /* decompressed length */ + leal z_extract_offset_negative(%ebx), %ebp pushl %ebp /* output address */ pushl $z_input_len /* input_len */ leal input_data(%ebx), %eax @@ -191,33 +192,7 @@ relocated: pushl %eax /* heap area */ pushl %esi /* real mode pointer */ call decompress_kernel - addl $20, %esp - -#if CONFIG_RELOCATABLE -/* - * Find the address of the relocations. - */ - leal z_output_len(%ebp), %edi - -/* - * Calculate the delta between where vmlinux was compiled to run - * and where it was actually loaded. - */ - movl %ebp, %ebx - subl $LOAD_PHYSICAL_ADDR, %ebx - jz 2f /* Nothing to be done if loaded at compiled addr. */ -/* - * Process relocations. - */ - -1: subl $4, %edi - movl (%edi), %ecx - testl %ecx, %ecx - jz 2f - addl %ebx, -__PAGE_OFFSET(%ebx, %ecx) - jmp 1b -2: -#endif + addl $24, %esp /* * Jump to the decompressed kernel. diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 06e71c2c16bf..c337422b575d 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -338,6 +338,7 @@ relocated: leaq input_data(%rip), %rdx /* input_data */ movl $z_input_len, %ecx /* input_len */ movq %rbp, %r8 /* output target address */ + movq $z_output_len, %r9 /* decompressed length */ call decompress_kernel popq %rsi diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index 0319c88290a5..434f077d2c4d 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -271,6 +271,79 @@ static void error(char *x) asm("hlt"); } +#if CONFIG_X86_NEED_RELOCS +static void handle_relocations(void *output, unsigned long output_len) +{ + int *reloc; + unsigned long delta, map, ptr; + unsigned long min_addr = (unsigned long)output; + unsigned long max_addr = min_addr + output_len; + + /* + * Calculate the delta between where vmlinux was linked to load + * and where it was actually loaded. + */ + delta = min_addr - LOAD_PHYSICAL_ADDR; + if (!delta) { + debug_putstr("No relocation needed... "); + return; + } + debug_putstr("Performing relocations... "); + + /* + * The kernel contains a table of relocation addresses. Those + * addresses have the final load address of the kernel in virtual + * memory. We are currently working in the self map. So we need to + * create an adjustment for kernel memory addresses to the self map. + * This will involve subtracting out the base address of the kernel. + */ + map = delta - __START_KERNEL_map; + + /* + * Process relocations: 32 bit relocations first then 64 bit after. + * Two sets of binary relocations are added to the end of the kernel + * before compression. Each relocation table entry is the kernel + * address of the location which needs to be updated stored as a + * 32-bit value which is sign extended to 64 bits. + * + * Format is: + * + * kernel bits... + * 0 - zero terminator for 64 bit relocations + * 64 bit relocation repeated + * 0 - zero terminator for 32 bit relocations + * 32 bit relocation repeated + * + * So we work backwards from the end of the decompressed image. + */ + for (reloc = output + output_len - sizeof(*reloc); *reloc; reloc--) { + int extended = *reloc; + extended += map; + + ptr = (unsigned long)extended; + if (ptr < min_addr || ptr > max_addr) + error("32-bit relocation outside of kernel!\n"); + + *(uint32_t *)ptr += delta; + } +#ifdef CONFIG_X86_64 + for (reloc--; *reloc; reloc--) { + long extended = *reloc; + extended += map; + + ptr = (unsigned long)extended; + if (ptr < min_addr || ptr > max_addr) + error("64-bit relocation outside of kernel!\n"); + + *(uint64_t *)ptr += delta; + } +#endif +} +#else +static inline void handle_relocations(void *output, unsigned long output_len) +{ } +#endif + static void parse_elf(void *output) { #ifdef CONFIG_X86_64 @@ -325,7 +398,8 @@ static void parse_elf(void *output) asmlinkage void decompress_kernel(void *rmode, memptr heap, unsigned char *input_data, unsigned long input_len, - unsigned char *output) + unsigned char *output, + unsigned long output_len) { real_mode = rmode; @@ -365,6 +439,7 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap, debug_putstr("\nDecompressing Linux... "); decompress(input_data, input_len, NULL, NULL, output, NULL, error); parse_elf(output); + handle_relocations(output, output_len); debug_putstr("done.\nBooting the kernel.\n"); return; } diff --git a/arch/x86/boot/printf.c b/arch/x86/boot/printf.c index cdac91ca55d3..565083c16e5c 100644 --- a/arch/x86/boot/printf.c +++ b/arch/x86/boot/printf.c @@ -55,7 +55,7 @@ static char *number(char *str, long num, int base, int size, int precision, locase = (type & SMALL); if (type & LEFT) type &= ~ZEROPAD; - if (base < 2 || base > 36) + if (base < 2 || base > 16) return NULL; c = (type & ZEROPAD) ? '0' : ' '; sign = 0; diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index bccfca68430e..665a730307f2 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -457,7 +457,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp); + compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp); if (ksig->ka.sa.sa_flags & SA_RESTORER) restorer = ksig->ka.sa.sa_restorer; diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S index 474dc1b59f72..4299eb05023c 100644 --- a/arch/x86/ia32/ia32entry.S +++ b/arch/x86/ia32/ia32entry.S @@ -452,7 +452,7 @@ ia32_badsys: CFI_ENDPROC - .macro PTREGSCALL label, func, arg + .macro PTREGSCALL label, func ALIGN GLOBAL(\label) leaq \func(%rip),%rax diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 2dfac58f3b11..b1977bad5435 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -86,6 +86,7 @@ extern int acpi_pci_disabled; extern int acpi_skip_timer_override; extern int acpi_use_timer_override; extern int acpi_fix_pin2_polarity; +extern int acpi_disable_cmcff; extern u8 acpi_sci_flags; extern int acpi_sci_override_gsi; @@ -168,6 +169,7 @@ static inline void arch_acpi_set_pdc_bits(u32 *buf) #define acpi_lapic 0 #define acpi_ioapic 0 +#define acpi_disable_cmcff 0 static inline void acpi_noirq_set(void) { } static inline void acpi_disable_pci(void) { } static inline void disable_acpi(void) { } diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 58ed6d96a6ac..0a3f9c9f98d5 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -5,6 +5,7 @@ #include <linux/stddef.h> #include <linux/stringify.h> #include <asm/asm.h> +#include <asm/ptrace.h> /* * Alternative inline assembly for SMP. @@ -220,20 +221,11 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len); * no thread can be preempted in the instructions being modified (no iret to an * invalid instruction possible) or if the instructions are changed from a * consistent state to another consistent state atomically. - * More care must be taken when modifying code in the SMP case because of - * Intel's errata. text_poke_smp() takes care that errata, but still - * doesn't support NMI/MCE handler code modifying. * On the local CPU you need to be protected again NMI or MCE handlers seeing an * inconsistent instruction while you patch. */ -struct text_poke_param { - void *addr; - const void *opcode; - size_t len; -}; - extern void *text_poke(void *addr, const void *opcode, size_t len); -extern void *text_poke_smp(void *addr, const void *opcode, size_t len); -extern void text_poke_smp_batch(struct text_poke_param *params, int n); +extern int poke_int3_handler(struct pt_regs *regs); +extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler); #endif /* _ASM_X86_ALTERNATIVE_H */ diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index f8119b582c3c..1d2091a226bc 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -715,4 +715,6 @@ static inline void exiting_ack_irq(void) ack_APIC_irq(); } +extern void ioapic_zap_locks(void); + #endif /* _ASM_X86_APIC_H */ diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 1c2d247f65ce..4582e8e1cd1a 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -3,21 +3,25 @@ #ifdef __ASSEMBLY__ # define __ASM_FORM(x) x +# define __ASM_FORM_RAW(x) x # define __ASM_FORM_COMMA(x) x, #else # define __ASM_FORM(x) " " #x " " +# define __ASM_FORM_RAW(x) #x # define __ASM_FORM_COMMA(x) " " #x "," #endif #ifdef CONFIG_X86_32 # define __ASM_SEL(a,b) __ASM_FORM(a) +# define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a) #else # define __ASM_SEL(a,b) __ASM_FORM(b) +# define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b) #endif #define __ASM_SIZE(inst, ...) __ASM_SEL(inst##l##__VA_ARGS__, \ inst##q##__VA_ARGS__) -#define __ASM_REG(reg) __ASM_SEL(e##reg, r##reg) +#define __ASM_REG(reg) __ASM_SEL_RAW(e##reg, r##reg) #define _ASM_PTR __ASM_SEL(.long, .quad) #define _ASM_ALIGN __ASM_SEL(.balign 4, .balign 8) diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 6dfd0195bb55..41639ce8fd63 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -15,6 +15,14 @@ #include <linux/compiler.h> #include <asm/alternative.h> +#if BITS_PER_LONG == 32 +# define _BITOPS_LONG_SHIFT 5 +#elif BITS_PER_LONG == 64 +# define _BITOPS_LONG_SHIFT 6 +#else +# error "Unexpected BITS_PER_LONG" +#endif + #define BIT_64(n) (U64_C(1) << (n)) /* @@ -59,7 +67,7 @@ * restricted to acting on a single-word quantity. */ static __always_inline void -set_bit(unsigned int nr, volatile unsigned long *addr) +set_bit(long nr, volatile unsigned long *addr) { if (IS_IMMEDIATE(nr)) { asm volatile(LOCK_PREFIX "orb %1,%0" @@ -81,7 +89,7 @@ set_bit(unsigned int nr, volatile unsigned long *addr) * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ -static inline void __set_bit(int nr, volatile unsigned long *addr) +static inline void __set_bit(long nr, volatile unsigned long *addr) { asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory"); } @@ -97,7 +105,7 @@ static inline void __set_bit(int nr, volatile unsigned long *addr) * in order to ensure changes are visible on other processors. */ static __always_inline void -clear_bit(int nr, volatile unsigned long *addr) +clear_bit(long nr, volatile unsigned long *addr) { if (IS_IMMEDIATE(nr)) { asm volatile(LOCK_PREFIX "andb %1,%0" @@ -118,13 +126,13 @@ clear_bit(int nr, volatile unsigned long *addr) * clear_bit() is atomic and implies release semantics before the memory * operation. It can be used for an unlock. */ -static inline void clear_bit_unlock(unsigned nr, volatile unsigned long *addr) +static inline void clear_bit_unlock(long nr, volatile unsigned long *addr) { barrier(); clear_bit(nr, addr); } -static inline void __clear_bit(int nr, volatile unsigned long *addr) +static inline void __clear_bit(long nr, volatile unsigned long *addr) { asm volatile("btr %1,%0" : ADDR : "Ir" (nr)); } @@ -141,7 +149,7 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr) * No memory barrier is required here, because x86 cannot reorder stores past * older loads. Same principle as spin_unlock. */ -static inline void __clear_bit_unlock(unsigned nr, volatile unsigned long *addr) +static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr) { barrier(); __clear_bit(nr, addr); @@ -159,7 +167,7 @@ static inline void __clear_bit_unlock(unsigned nr, volatile unsigned long *addr) * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ -static inline void __change_bit(int nr, volatile unsigned long *addr) +static inline void __change_bit(long nr, volatile unsigned long *addr) { asm volatile("btc %1,%0" : ADDR : "Ir" (nr)); } @@ -173,7 +181,7 @@ static inline void __change_bit(int nr, volatile unsigned long *addr) * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ -static inline void change_bit(int nr, volatile unsigned long *addr) +static inline void change_bit(long nr, volatile unsigned long *addr) { if (IS_IMMEDIATE(nr)) { asm volatile(LOCK_PREFIX "xorb %1,%0" @@ -194,7 +202,7 @@ static inline void change_bit(int nr, volatile unsigned long *addr) * This operation is atomic and cannot be reordered. * It also implies a memory barrier. */ -static inline int test_and_set_bit(int nr, volatile unsigned long *addr) +static inline int test_and_set_bit(long nr, volatile unsigned long *addr) { int oldbit; @@ -212,7 +220,7 @@ static inline int test_and_set_bit(int nr, volatile unsigned long *addr) * This is the same as test_and_set_bit on x86. */ static __always_inline int -test_and_set_bit_lock(int nr, volatile unsigned long *addr) +test_and_set_bit_lock(long nr, volatile unsigned long *addr) { return test_and_set_bit(nr, addr); } @@ -226,7 +234,7 @@ test_and_set_bit_lock(int nr, volatile unsigned long *addr) * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ -static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) +static inline int __test_and_set_bit(long nr, volatile unsigned long *addr) { int oldbit; @@ -245,7 +253,7 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) * This operation is atomic and cannot be reordered. * It also implies a memory barrier. */ -static inline int test_and_clear_bit(int nr, volatile unsigned long *addr) +static inline int test_and_clear_bit(long nr, volatile unsigned long *addr) { int oldbit; @@ -272,7 +280,7 @@ static inline int test_and_clear_bit(int nr, volatile unsigned long *addr) * accessed from a hypervisor on the same CPU if running in a VM: don't change * this without also updating arch/x86/kernel/kvm.c */ -static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) +static inline int __test_and_clear_bit(long nr, volatile unsigned long *addr) { int oldbit; @@ -284,7 +292,7 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) } /* WARNING: non atomic and it can be reordered! */ -static inline int __test_and_change_bit(int nr, volatile unsigned long *addr) +static inline int __test_and_change_bit(long nr, volatile unsigned long *addr) { int oldbit; @@ -304,7 +312,7 @@ static inline int __test_and_change_bit(int nr, volatile unsigned long *addr) * This operation is atomic and cannot be reordered. * It also implies a memory barrier. */ -static inline int test_and_change_bit(int nr, volatile unsigned long *addr) +static inline int test_and_change_bit(long nr, volatile unsigned long *addr) { int oldbit; @@ -315,13 +323,13 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr) return oldbit; } -static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr) +static __always_inline int constant_test_bit(long nr, const volatile unsigned long *addr) { - return ((1UL << (nr % BITS_PER_LONG)) & - (addr[nr / BITS_PER_LONG])) != 0; + return ((1UL << (nr & (BITS_PER_LONG-1))) & + (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; } -static inline int variable_test_bit(int nr, volatile const unsigned long *addr) +static inline int variable_test_bit(long nr, volatile const unsigned long *addr) { int oldbit; diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h index 653668d140f9..4a8cb8d7cbd5 100644 --- a/arch/x86/include/asm/bootparam_utils.h +++ b/arch/x86/include/asm/bootparam_utils.h @@ -35,9 +35,9 @@ static void sanitize_boot_params(struct boot_params *boot_params) */ if (boot_params->sentinel) { /* fields in boot_params are left uninitialized, clear them */ - memset(&boot_params->olpc_ofw_header, 0, + memset(&boot_params->ext_ramdisk_image, 0, (char *)&boot_params->efi_info - - (char *)&boot_params->olpc_ofw_header); + (char *)&boot_params->ext_ramdisk_image); memset(&boot_params->kbd_status, 0, (char *)&boot_params->hdr - (char *)&boot_params->kbd_status); diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h index 46fc474fd819..f50de6951738 100644 --- a/arch/x86/include/asm/checksum_32.h +++ b/arch/x86/include/asm/checksum_32.h @@ -49,9 +49,15 @@ static inline __wsum csum_partial_copy_from_user(const void __user *src, int len, __wsum sum, int *err_ptr) { + __wsum ret; + might_sleep(); - return csum_partial_copy_generic((__force void *)src, dst, - len, sum, err_ptr, NULL); + stac(); + ret = csum_partial_copy_generic((__force void *)src, dst, + len, sum, err_ptr, NULL); + clac(); + + return ret; } /* @@ -176,10 +182,16 @@ static inline __wsum csum_and_copy_to_user(const void *src, int len, __wsum sum, int *err_ptr) { + __wsum ret; + might_sleep(); - if (access_ok(VERIFY_WRITE, dst, len)) - return csum_partial_copy_generic(src, (__force void *)dst, - len, sum, NULL, err_ptr); + if (access_ok(VERIFY_WRITE, dst, len)) { + stac(); + ret = csum_partial_copy_generic(src, (__force void *)dst, + len, sum, NULL, err_ptr); + clac(); + return ret; + } if (len) *err_ptr = -EFAULT; diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h index 9bfdc41629ec..e6fd8a026c7b 100644 --- a/arch/x86/include/asm/checksum_64.h +++ b/arch/x86/include/asm/checksum_64.h @@ -133,7 +133,7 @@ extern __wsum csum_partial(const void *buff, int len, __wsum sum); /* Do not call this directly. Use the wrappers below */ -extern __wsum csum_partial_copy_generic(const void *src, const void *dst, +extern __visible __wsum csum_partial_copy_generic(const void *src, const void *dst, int len, __wsum sum, int *src_err_ptr, int *dst_err_ptr); diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 47538a61c91b..d3f5c63078d8 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -366,9 +366,10 @@ extern bool __static_cpu_has_safe(u16 bit); */ static __always_inline __pure bool __static_cpu_has(u16 bit) { -#if __GNUC__ > 4 || __GNUC_MINOR__ >= 5 +#ifdef CC_HAVE_ASM_GOTO #ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS + /* * Catch too early usage of this before alternatives * have run. @@ -384,6 +385,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) ".previous\n" /* skipping size check since replacement size = 0 */ : : "i" (X86_FEATURE_ALWAYS) : : t_warn); + #endif asm goto("1: jmp %l[t_no]\n" @@ -406,7 +408,9 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) warn_pre_alternatives(); return false; #endif -#else /* GCC_VERSION >= 40500 */ + +#else /* CC_HAVE_ASM_GOTO */ + u8 flag; /* Open-coded due to __stringify() in ALTERNATIVE() */ asm volatile("1: movb $0,%0\n" @@ -427,7 +431,8 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) ".previous\n" : "=qm" (flag) : "i" (bit)); return flag; -#endif + +#endif /* CC_HAVE_ASM_GOTO */ } #define static_cpu_has(bit) \ @@ -441,7 +446,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit) static __always_inline __pure bool _static_cpu_has_safe(u16 bit) { -#if __GNUC__ > 4 || __GNUC_MINOR__ >= 5 +#ifdef CC_HAVE_ASM_GOTO /* * We need to spell the jumps to the compiler because, depending on the offset, * the replacement jump can be bigger than the original jump, and this we cannot @@ -475,7 +480,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit) return false; t_dynamic: return __static_cpu_has_safe(bit); -#else /* GCC_VERSION >= 40500 */ +#else u8 flag; /* Open-coded due to __stringify() in ALTERNATIVE() */ asm volatile("1: movb $2,%0\n" @@ -511,7 +516,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit) : "=qm" (flag) : "i" (bit), "i" (X86_FEATURE_ALWAYS)); return (flag == 2 ? __static_cpu_has_safe(bit) : flag); -#endif +#endif /* CC_HAVE_ASM_GOTO */ } #define static_cpu_has_safe(bit) \ diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index cccd07fa5e3a..779c2efe2e97 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -29,7 +29,7 @@ extern void e820_setup_gap(void); extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize, unsigned long start_addr, unsigned long long end_addr); struct setup_data; -extern void parse_e820_ext(struct setup_data *data); +extern void parse_e820_ext(u64 phys_addr, u32 data_len); #if defined(CONFIG_X86_64) || \ (defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION)) diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index e4ac559c4a24..92b3bae08b74 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -26,56 +26,56 @@ #include <asm/sections.h> /* Interrupt handlers registered during init_IRQ */ -extern void apic_timer_interrupt(void); -extern void x86_platform_ipi(void); -extern void kvm_posted_intr_ipi(void); -extern void error_interrupt(void); -extern void irq_work_interrupt(void); - -extern void spurious_interrupt(void); -extern void thermal_interrupt(void); -extern void reschedule_interrupt(void); - -extern void invalidate_interrupt(void); -extern void invalidate_interrupt0(void); -extern void invalidate_interrupt1(void); -extern void invalidate_interrupt2(void); -extern void invalidate_interrupt3(void); -extern void invalidate_interrupt4(void); -extern void invalidate_interrupt5(void); -extern void invalidate_interrupt6(void); -extern void invalidate_interrupt7(void); -extern void invalidate_interrupt8(void); -extern void invalidate_interrupt9(void); -extern void invalidate_interrupt10(void); -extern void invalidate_interrupt11(void); -extern void invalidate_interrupt12(void); -extern void invalidate_interrupt13(void); -extern void invalidate_interrupt14(void); -extern void invalidate_interrupt15(void); -extern void invalidate_interrupt16(void); -extern void invalidate_interrupt17(void); -extern void invalidate_interrupt18(void); -extern void invalidate_interrupt19(void); -extern void invalidate_interrupt20(void); -extern void invalidate_interrupt21(void); -extern void invalidate_interrupt22(void); -extern void invalidate_interrupt23(void); -extern void invalidate_interrupt24(void); -extern void invalidate_interrupt25(void); -extern void invalidate_interrupt26(void); -extern void invalidate_interrupt27(void); -extern void invalidate_interrupt28(void); -extern void invalidate_interrupt29(void); -extern void invalidate_interrupt30(void); -extern void invalidate_interrupt31(void); - -extern void irq_move_cleanup_interrupt(void); -extern void reboot_interrupt(void); -extern void threshold_interrupt(void); - -extern void call_function_interrupt(void); -extern void call_function_single_interrupt(void); +extern asmlinkage void apic_timer_interrupt(void); +extern asmlinkage void x86_platform_ipi(void); +extern asmlinkage void kvm_posted_intr_ipi(void); +extern asmlinkage void error_interrupt(void); +extern asmlinkage void irq_work_interrupt(void); + +extern asmlinkage void spurious_interrupt(void); +extern asmlinkage void thermal_interrupt(void); +extern asmlinkage void reschedule_interrupt(void); + +extern asmlinkage void invalidate_interrupt(void); +extern asmlinkage void invalidate_interrupt0(void); +extern asmlinkage void invalidate_interrupt1(void); +extern asmlinkage void invalidate_interrupt2(void); +extern asmlinkage void invalidate_interrupt3(void); +extern asmlinkage void invalidate_interrupt4(void); +extern asmlinkage void invalidate_interrupt5(void); +extern asmlinkage void invalidate_interrupt6(void); +extern asmlinkage void invalidate_interrupt7(void); +extern asmlinkage void invalidate_interrupt8(void); +extern asmlinkage void invalidate_interrupt9(void); +extern asmlinkage void invalidate_interrupt10(void); +extern asmlinkage void invalidate_interrupt11(void); +extern asmlinkage void invalidate_interrupt12(void); +extern asmlinkage void invalidate_interrupt13(void); +extern asmlinkage void invalidate_interrupt14(void); +extern asmlinkage void invalidate_interrupt15(void); +extern asmlinkage void invalidate_interrupt16(void); +extern asmlinkage void invalidate_interrupt17(void); +extern asmlinkage void invalidate_interrupt18(void); +extern asmlinkage void invalidate_interrupt19(void); +extern asmlinkage void invalidate_interrupt20(void); +extern asmlinkage void invalidate_interrupt21(void); +extern asmlinkage void invalidate_interrupt22(void); +extern asmlinkage void invalidate_interrupt23(void); +extern asmlinkage void invalidate_interrupt24(void); +extern asmlinkage void invalidate_interrupt25(void); +extern asmlinkage void invalidate_interrupt26(void); +extern asmlinkage void invalidate_interrupt27(void); +extern asmlinkage void invalidate_interrupt28(void); +extern asmlinkage void invalidate_interrupt29(void); +extern asmlinkage void invalidate_interrupt30(void); +extern asmlinkage void invalidate_interrupt31(void); + +extern asmlinkage void irq_move_cleanup_interrupt(void); +extern asmlinkage void reboot_interrupt(void); +extern asmlinkage void threshold_interrupt(void); + +extern asmlinkage void call_function_interrupt(void); +extern asmlinkage void call_function_single_interrupt(void); #ifdef CONFIG_TRACING /* Interrupt handlers registered during init_IRQ */ @@ -172,22 +172,18 @@ extern atomic_t irq_mis_count; extern void eisa_set_level_irq(unsigned int irq); /* SMP */ -extern void smp_apic_timer_interrupt(struct pt_regs *); -extern void smp_spurious_interrupt(struct pt_regs *); -extern void smp_x86_platform_ipi(struct pt_regs *); -extern void smp_error_interrupt(struct pt_regs *); +extern __visible void smp_apic_timer_interrupt(struct pt_regs *); +extern __visible void smp_spurious_interrupt(struct pt_regs *); +extern __visible void smp_x86_platform_ipi(struct pt_regs *); +extern __visible void smp_error_interrupt(struct pt_regs *); #ifdef CONFIG_X86_IO_APIC extern asmlinkage void smp_irq_move_cleanup_interrupt(void); #endif #ifdef CONFIG_SMP -extern void smp_reschedule_interrupt(struct pt_regs *); -extern void smp_call_function_interrupt(struct pt_regs *); -extern void smp_call_function_single_interrupt(struct pt_regs *); -#ifdef CONFIG_X86_32 -extern void smp_invalidate_interrupt(struct pt_regs *); -#else -extern asmlinkage void smp_invalidate_interrupt(struct pt_regs *); -#endif +extern __visible void smp_reschedule_interrupt(struct pt_regs *); +extern __visible void smp_call_function_interrupt(struct pt_regs *); +extern __visible void smp_call_function_single_interrupt(struct pt_regs *); +extern __visible void smp_invalidate_interrupt(struct pt_regs *); #endif extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void); diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 2d4b5e6107cd..e42f758a0fbd 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -33,7 +33,7 @@ struct hypervisor_x86 { const char *name; /* Detection routine */ - bool (*detect)(void); + uint32_t (*detect)(void); /* Adjust CPU feature bits (run once per CPU) */ void (*set_cpu_features)(struct cpuinfo_x86 *); diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 57873beb3292..0ea10f27d613 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -33,7 +33,7 @@ extern void (*x86_platform_ipi_callback)(void); extern void native_init_IRQ(void); extern bool handle_irq(unsigned irq, struct pt_regs *regs); -extern unsigned int do_IRQ(struct pt_regs *regs); +extern __visible unsigned int do_IRQ(struct pt_regs *regs); /* Interrupt vector management */ extern DECLARE_BITMAP(used_vectors, NR_VECTORS); diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 5a6d2873f80e..9454c167629f 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -49,10 +49,10 @@ typedef u8 kprobe_opcode_t; #define flush_insn_slot(p) do { } while (0) /* optinsn template addresses */ -extern kprobe_opcode_t optprobe_template_entry; -extern kprobe_opcode_t optprobe_template_val; -extern kprobe_opcode_t optprobe_template_call; -extern kprobe_opcode_t optprobe_template_end; +extern __visible kprobe_opcode_t optprobe_template_entry; +extern __visible kprobe_opcode_t optprobe_template_val; +extern __visible kprobe_opcode_t optprobe_template_call; +extern __visible kprobe_opcode_t optprobe_template_end; #define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE) #define MAX_OPTINSN_SIZE \ (((unsigned long)&optprobe_template_end - \ @@ -62,7 +62,7 @@ extern kprobe_opcode_t optprobe_template_end; extern const int kretprobe_blacklist_size; void arch_remove_kprobe(struct kprobe *p); -void kretprobe_trampoline(void); +asmlinkage void kretprobe_trampoline(void); /* Architecture specific copy of original instruction*/ struct arch_specific_insn { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f87f7fcefa0a..c76ff74a98f2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -286,6 +286,7 @@ struct kvm_mmu { u64 *pae_root; u64 *lm_root; u64 rsvd_bits_mask[2][4]; + u64 bad_mt_xwr; /* * Bitmap: bit set = last pte in walk @@ -323,6 +324,7 @@ struct kvm_pmu { u64 global_ovf_ctrl; u64 counter_bitmask[2]; u64 global_ctrl_mask; + u64 reserved_bits; u8 version; struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC]; struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED]; @@ -511,6 +513,14 @@ struct kvm_vcpu_arch { * instruction. */ bool write_fault_to_shadow_pgtable; + + /* set at EPT violation at this point */ + unsigned long exit_qualification; + + /* pv related host specific info */ + struct { + bool pv_unhalted; + } pv; }; struct kvm_lpage_info { @@ -802,8 +812,8 @@ extern u32 kvm_min_guest_tsc_khz; extern u32 kvm_max_guest_tsc_khz; enum emulation_result { - EMULATE_DONE, /* no further processing */ - EMULATE_DO_MMIO, /* kvm_run filled with mmio request */ + EMULATE_DONE, /* no further processing */ + EMULATE_USER_EXIT, /* kvm_run ready for userspace exit */ EMULATE_FAIL, /* can't emulate this instruction */ }; diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 695399f2d5eb..1df115909758 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -85,26 +85,20 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, return ret; } -static inline bool kvm_para_available(void) +static inline uint32_t kvm_cpuid_base(void) { - unsigned int eax, ebx, ecx, edx; - char signature[13]; - if (boot_cpu_data.cpuid_level < 0) - return false; /* So we don't blow up on old processors */ + return 0; /* So we don't blow up on old processors */ - if (cpu_has_hypervisor) { - cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx); - memcpy(signature + 0, &ebx, 4); - memcpy(signature + 4, &ecx, 4); - memcpy(signature + 8, &edx, 4); - signature[12] = 0; + if (cpu_has_hypervisor) + return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0); - if (strcmp(signature, "KVMKVMKVM") == 0) - return true; - } + return 0; +} - return false; +static inline bool kvm_para_available(void) +{ + return kvm_cpuid_base() != 0; } static inline unsigned int kvm_arch_para_features(void) @@ -118,10 +112,20 @@ void kvm_async_pf_task_wait(u32 token); void kvm_async_pf_task_wake(u32 token); u32 kvm_read_and_reset_pf_reason(void); extern void kvm_disable_steal_time(void); -#else -#define kvm_guest_init() do { } while (0) + +#ifdef CONFIG_PARAVIRT_SPINLOCKS +void __init kvm_spinlock_init(void); +#else /* !CONFIG_PARAVIRT_SPINLOCKS */ +static inline void kvm_spinlock_init(void) +{ +} +#endif /* CONFIG_PARAVIRT_SPINLOCKS */ + +#else /* CONFIG_KVM_GUEST */ +#define kvm_guest_init() do {} while (0) #define kvm_async_pf_task_wait(T) do {} while(0) #define kvm_async_pf_task_wake(T) do {} while(0) + static inline u32 kvm_read_and_reset_pf_reason(void) { return 0; diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 29e3093bbd21..cbe6b9e404ce 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -32,11 +32,20 @@ #define MCI_STATUS_PCC (1ULL<<57) /* processor context corrupt */ #define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */ #define MCI_STATUS_AR (1ULL<<55) /* Action required */ -#define MCACOD 0xffff /* MCA Error Code */ + +/* + * Note that the full MCACOD field of IA32_MCi_STATUS MSR is + * bits 15:0. But bit 12 is the 'F' bit, defined for corrected + * errors to indicate that errors are being filtered by hardware. + * We should mask out bit 12 when looking for specific signatures + * of uncorrected errors - so the F bit is deliberately skipped + * in this #define. + */ +#define MCACOD 0xefff /* MCA Error Code */ /* Architecturally defined codes from SDM Vol. 3B Chapter 15 */ #define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */ -#define MCACOD_SCRUBMSK 0xfff0 +#define MCACOD_SCRUBMSK 0xeff0 /* Skip bit 12 ('F' bit) */ #define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */ #define MCACOD_DATA 0x0134 /* Data Load */ #define MCACOD_INSTR 0x0150 /* Instruction Fetch */ @@ -188,6 +197,9 @@ extern void register_mce_write_callback(ssize_t (*)(struct file *filp, const char __user *ubuf, size_t usize, loff_t *off)); +/* Disable CMCI/polling for MCA bank claimed by firmware */ +extern void mce_disable_bank(int bank); + /* * Exception handler */ diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h index 50e5c58ced23..4c019179a57d 100644 --- a/arch/x86/include/asm/microcode_amd.h +++ b/arch/x86/include/asm/microcode_amd.h @@ -59,7 +59,7 @@ static inline u16 find_equiv_id(struct equiv_cpu_entry *equiv_cpu_table, extern int __apply_microcode_amd(struct microcode_amd *mc_amd); extern int apply_microcode_amd(int cpu); -extern enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size); +extern enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size); #ifdef CONFIG_MICROCODE_AMD_EARLY #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index cdbf36776106..be12c534fd59 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -45,22 +45,28 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, /* Re-load page tables */ load_cr3(next->pgd); - /* stop flush ipis for the previous mm */ + /* Stop flush ipis for the previous mm */ cpumask_clear_cpu(cpu, mm_cpumask(prev)); - /* - * load the LDT, if the LDT is different: - */ + /* Load the LDT, if the LDT is different: */ if (unlikely(prev->context.ldt != next->context.ldt)) load_LDT_nolock(&next->context); } #ifdef CONFIG_SMP - else { + else { this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK); BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next); - if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) { - /* We were in lazy tlb mode and leave_mm disabled + if (!cpumask_test_cpu(cpu, mm_cpumask(next))) { + /* + * On established mms, the mm_cpumask is only changed + * from irq context, from ptep_clear_flush() while in + * lazy tlb mode, and here. Irqs are blocked during + * schedule, protecting us from simultaneous changes. + */ + cpumask_set_cpu(cpu, mm_cpumask(next)); + /* + * We were in lazy tlb mode and leave_mm disabled * tlb flush IPI delivery. We must reload CR3 * to make sure to use no freed page tables. */ diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h index 2c543fff241b..e7e6751648ed 100644 --- a/arch/x86/include/asm/mutex_64.h +++ b/arch/x86/include/asm/mutex_64.h @@ -16,6 +16,20 @@ * * Atomically decrements @v and calls <fail_fn> if the result is negative. */ +#ifdef CC_HAVE_ASM_GOTO +static inline void __mutex_fastpath_lock(atomic_t *v, + void (*fail_fn)(atomic_t *)) +{ + asm volatile goto(LOCK_PREFIX " decl %0\n" + " jns %l[exit]\n" + : : "m" (v->counter) + : "memory", "cc" + : exit); + fail_fn(v); +exit: + return; +} +#else #define __mutex_fastpath_lock(v, fail_fn) \ do { \ unsigned long dummy; \ @@ -32,6 +46,7 @@ do { \ : "rax", "rsi", "rdx", "rcx", \ "r8", "r9", "r10", "r11", "memory"); \ } while (0) +#endif /** * __mutex_fastpath_lock_retval - try to take the lock by moving the count @@ -56,6 +71,20 @@ static inline int __mutex_fastpath_lock_retval(atomic_t *count) * * Atomically increments @v and calls <fail_fn> if the result is nonpositive. */ +#ifdef CC_HAVE_ASM_GOTO +static inline void __mutex_fastpath_unlock(atomic_t *v, + void (*fail_fn)(atomic_t *)) +{ + asm volatile goto(LOCK_PREFIX " incl %0\n" + " jg %l[exit]\n" + : : "m" (v->counter) + : "memory", "cc" + : exit); + fail_fn(v); +exit: + return; +} +#else #define __mutex_fastpath_unlock(v, fail_fn) \ do { \ unsigned long dummy; \ @@ -72,6 +101,7 @@ do { \ : "rax", "rsi", "rdx", "rcx", \ "r8", "r9", "r10", "r11", "memory"); \ } while (0) +#endif #define __mutex_slowpath_needs_to_unlock() 1 diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h index ef17af013475..f48b17df4224 100644 --- a/arch/x86/include/asm/page_32_types.h +++ b/arch/x86/include/asm/page_32_types.h @@ -15,6 +15,8 @@ */ #define __PAGE_OFFSET _AC(CONFIG_PAGE_OFFSET, UL) +#define __START_KERNEL_map __PAGE_OFFSET + #define THREAD_SIZE_ORDER 1 #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 6c896fbe21db..43dcd804ebd5 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -32,11 +32,6 @@ */ #define __PAGE_OFFSET _AC(0xffff880000000000, UL) -#define __PHYSICAL_START ((CONFIG_PHYSICAL_START + \ - (CONFIG_PHYSICAL_ALIGN - 1)) & \ - ~(CONFIG_PHYSICAL_ALIGN - 1)) - -#define __START_KERNEL (__START_KERNEL_map + __PHYSICAL_START) #define __START_KERNEL_map _AC(0xffffffff80000000, UL) /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */ diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index 54c97879195e..f97fbe3abb67 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -33,6 +33,11 @@ (((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \ VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) +#define __PHYSICAL_START ALIGN(CONFIG_PHYSICAL_START, \ + CONFIG_PHYSICAL_ALIGN) + +#define __START_KERNEL (__START_KERNEL_map + __PHYSICAL_START) + #ifdef CONFIG_X86_64 #include <asm/page_64_types.h> #else diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index cfdc9ee4c900..401f350ef71b 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -712,36 +712,16 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS) -static inline int arch_spin_is_locked(struct arch_spinlock *lock) +static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, + __ticket_t ticket) { - return PVOP_CALL1(int, pv_lock_ops.spin_is_locked, lock); + PVOP_VCALLEE2(pv_lock_ops.lock_spinning, lock, ticket); } -static inline int arch_spin_is_contended(struct arch_spinlock *lock) +static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock, + __ticket_t ticket) { - return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock); -} -#define arch_spin_is_contended arch_spin_is_contended - -static __always_inline void arch_spin_lock(struct arch_spinlock *lock) -{ - PVOP_VCALL1(pv_lock_ops.spin_lock, lock); -} - -static __always_inline void arch_spin_lock_flags(struct arch_spinlock *lock, - unsigned long flags) -{ - PVOP_VCALL2(pv_lock_ops.spin_lock_flags, lock, flags); -} - -static __always_inline int arch_spin_trylock(struct arch_spinlock *lock) -{ - return PVOP_CALL1(int, pv_lock_ops.spin_trylock, lock); -} - -static __always_inline void arch_spin_unlock(struct arch_spinlock *lock) -{ - PVOP_VCALL1(pv_lock_ops.spin_unlock, lock); + PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket); } #endif diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 0db1fcac668c..aab8f671b523 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -327,13 +327,15 @@ struct pv_mmu_ops { }; struct arch_spinlock; +#ifdef CONFIG_SMP +#include <asm/spinlock_types.h> +#else +typedef u16 __ticket_t; +#endif + struct pv_lock_ops { - int (*spin_is_locked)(struct arch_spinlock *lock); - int (*spin_is_contended)(struct arch_spinlock *lock); - void (*spin_lock)(struct arch_spinlock *lock); - void (*spin_lock_flags)(struct arch_spinlock *lock, unsigned long flags); - int (*spin_trylock)(struct arch_spinlock *lock); - void (*spin_unlock)(struct arch_spinlock *lock); + struct paravirt_callee_save lock_spinning; + void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket); }; /* This contains all the paravirt structures: we get a convenient @@ -387,7 +389,8 @@ extern struct pv_lock_ops pv_lock_ops; /* Simple instruction patching code. */ #define DEF_NATIVE(ops, name, code) \ - extern const char start_##ops##_##name[], end_##ops##_##name[]; \ + extern const char start_##ops##_##name[] __visible, \ + end_##ops##_##name[] __visible; \ asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":") unsigned paravirt_patch_nop(void); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 1c00631164c2..8d16befdec88 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -22,7 +22,8 @@ * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. */ -extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; +extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] + __visible; #define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) extern spinlock_t pgd_lock; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 24cf5aefb704..987c75ecc334 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -412,7 +412,7 @@ union irq_stack_union { }; }; -DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union); +DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __visible; DECLARE_INIT_PER_CPU(irq_stack_union); DECLARE_PER_CPU(char *, irq_stack_ptr); @@ -942,33 +942,19 @@ extern int set_tsc_mode(unsigned int val); extern u16 amd_get_nb_id(int cpu); -struct aperfmperf { - u64 aperf, mperf; -}; - -static inline void get_aperfmperf(struct aperfmperf *am) +static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) { - WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_APERFMPERF)); - - rdmsrl(MSR_IA32_APERF, am->aperf); - rdmsrl(MSR_IA32_MPERF, am->mperf); -} + uint32_t base, eax, signature[3]; -#define APERFMPERF_SHIFT 10 + for (base = 0x40000000; base < 0x40010000; base += 0x100) { + cpuid(base, &eax, &signature[0], &signature[1], &signature[2]); -static inline -unsigned long calc_aperfmperf_ratio(struct aperfmperf *old, - struct aperfmperf *new) -{ - u64 aperf = new->aperf - old->aperf; - u64 mperf = new->mperf - old->mperf; - unsigned long ratio = aperf; - - mperf >>= APERFMPERF_SHIFT; - if (mperf) - ratio = div64_u64(aperf, mperf); + if (!memcmp(sig, signature, 12) && + (leaves == 0 || ((eax - base) >= leaves))) + return base; + } - return ratio; + return 0; } extern unsigned long arch_align_stack(unsigned long sp); diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 109a9dd5d454..be8269b00e2a 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -93,7 +93,6 @@ 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/setup.h b/arch/x86/include/asm/setup.h index b7bf3505e1ec..347555492dad 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -6,6 +6,8 @@ #define COMMAND_LINE_SIZE 2048 +#include <linux/linkage.h> + #ifdef __i386__ #include <linux/pfn.h> @@ -108,11 +110,11 @@ void *extend_brk(size_t size, size_t align); extern void probe_roms(void); #ifdef __i386__ -void __init i386_start_kernel(void); +asmlinkage void __init i386_start_kernel(void); #else -void __init x86_64_start_kernel(char *real_mode); -void __init x86_64_start_reservations(char *real_mode_data); +asmlinkage void __init x86_64_start_kernel(char *real_mode); +asmlinkage void __init x86_64_start_reservations(char *real_mode_data); #endif /* __i386__ */ #endif /* _SETUP */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 2f4d924fe6c9..645cad2c95ff 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -101,7 +101,7 @@ static inline void native_wbinvd(void) asm volatile("wbinvd": : :"memory"); } -extern void native_load_gs_index(unsigned); +extern asmlinkage void native_load_gs_index(unsigned); #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index e3ddd7db723f..bf156ded74b5 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -1,11 +1,14 @@ #ifndef _ASM_X86_SPINLOCK_H #define _ASM_X86_SPINLOCK_H +#include <linux/jump_label.h> #include <linux/atomic.h> #include <asm/page.h> #include <asm/processor.h> #include <linux/compiler.h> #include <asm/paravirt.h> +#include <asm/bitops.h> + /* * Your basic SMP spinlocks, allowing only a single CPU anywhere * @@ -34,6 +37,36 @@ # define UNLOCK_LOCK_PREFIX #endif +/* How long a lock should spin before we consider blocking */ +#define SPIN_THRESHOLD (1 << 15) + +extern struct static_key paravirt_ticketlocks_enabled; +static __always_inline bool static_key_false(struct static_key *key); + +#ifdef CONFIG_PARAVIRT_SPINLOCKS + +static inline void __ticket_enter_slowpath(arch_spinlock_t *lock) +{ + set_bit(0, (volatile unsigned long *)&lock->tickets.tail); +} + +#else /* !CONFIG_PARAVIRT_SPINLOCKS */ +static __always_inline void __ticket_lock_spinning(arch_spinlock_t *lock, + __ticket_t ticket) +{ +} +static inline void __ticket_unlock_kick(arch_spinlock_t *lock, + __ticket_t ticket) +{ +} + +#endif /* CONFIG_PARAVIRT_SPINLOCKS */ + +static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) +{ + return lock.tickets.head == lock.tickets.tail; +} + /* * Ticket locks are conceptually two parts, one indicating the current head of * the queue, and the other indicating the current tail. The lock is acquired @@ -47,81 +80,101 @@ * in the high part, because a wide xadd increment of the low part would carry * up and contaminate the high part. */ -static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock) +static __always_inline void arch_spin_lock(arch_spinlock_t *lock) { - register struct __raw_tickets inc = { .tail = 1 }; + register struct __raw_tickets inc = { .tail = TICKET_LOCK_INC }; inc = xadd(&lock->tickets, inc); + if (likely(inc.head == inc.tail)) + goto out; + inc.tail &= ~TICKET_SLOWPATH_FLAG; for (;;) { - if (inc.head == inc.tail) - break; - cpu_relax(); - inc.head = ACCESS_ONCE(lock->tickets.head); + unsigned count = SPIN_THRESHOLD; + + do { + if (ACCESS_ONCE(lock->tickets.head) == inc.tail) + goto out; + cpu_relax(); + } while (--count); + __ticket_lock_spinning(lock, inc.tail); } - barrier(); /* make sure nothing creeps before the lock is taken */ +out: barrier(); /* make sure nothing creeps before the lock is taken */ } -static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock) +static __always_inline int arch_spin_trylock(arch_spinlock_t *lock) { arch_spinlock_t old, new; old.tickets = ACCESS_ONCE(lock->tickets); - if (old.tickets.head != old.tickets.tail) + if (old.tickets.head != (old.tickets.tail & ~TICKET_SLOWPATH_FLAG)) return 0; - new.head_tail = old.head_tail + (1 << TICKET_SHIFT); + new.head_tail = old.head_tail + (TICKET_LOCK_INC << TICKET_SHIFT); /* cmpxchg is a full barrier, so nothing can move before it */ return cmpxchg(&lock->head_tail, old.head_tail, new.head_tail) == old.head_tail; } -static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock) +static inline void __ticket_unlock_slowpath(arch_spinlock_t *lock, + arch_spinlock_t old) { - __add(&lock->tickets.head, 1, UNLOCK_LOCK_PREFIX); + arch_spinlock_t new; + + BUILD_BUG_ON(((__ticket_t)NR_CPUS) != NR_CPUS); + + /* Perform the unlock on the "before" copy */ + old.tickets.head += TICKET_LOCK_INC; + + /* Clear the slowpath flag */ + new.head_tail = old.head_tail & ~(TICKET_SLOWPATH_FLAG << TICKET_SHIFT); + + /* + * If the lock is uncontended, clear the flag - use cmpxchg in + * case it changes behind our back though. + */ + if (new.tickets.head != new.tickets.tail || + cmpxchg(&lock->head_tail, old.head_tail, + new.head_tail) != old.head_tail) { + /* + * Lock still has someone queued for it, so wake up an + * appropriate waiter. + */ + __ticket_unlock_kick(lock, old.tickets.head); + } } -static inline int __ticket_spin_is_locked(arch_spinlock_t *lock) +static __always_inline void arch_spin_unlock(arch_spinlock_t *lock) { - struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); + if (TICKET_SLOWPATH_FLAG && + static_key_false(¶virt_ticketlocks_enabled)) { + arch_spinlock_t prev; - return tmp.tail != tmp.head; -} + prev = *lock; + add_smp(&lock->tickets.head, TICKET_LOCK_INC); -static inline int __ticket_spin_is_contended(arch_spinlock_t *lock) -{ - struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); + /* add_smp() is a full mb() */ - return (__ticket_t)(tmp.tail - tmp.head) > 1; + if (unlikely(lock->tickets.tail & TICKET_SLOWPATH_FLAG)) + __ticket_unlock_slowpath(lock, prev); + } else + __add(&lock->tickets.head, TICKET_LOCK_INC, UNLOCK_LOCK_PREFIX); } -#ifndef CONFIG_PARAVIRT_SPINLOCKS - static inline int arch_spin_is_locked(arch_spinlock_t *lock) { - return __ticket_spin_is_locked(lock); -} - -static inline int arch_spin_is_contended(arch_spinlock_t *lock) -{ - return __ticket_spin_is_contended(lock); -} -#define arch_spin_is_contended arch_spin_is_contended + struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); -static __always_inline void arch_spin_lock(arch_spinlock_t *lock) -{ - __ticket_spin_lock(lock); + return tmp.tail != tmp.head; } -static __always_inline int arch_spin_trylock(arch_spinlock_t *lock) +static inline int arch_spin_is_contended(arch_spinlock_t *lock) { - return __ticket_spin_trylock(lock); -} + struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets); -static __always_inline void arch_spin_unlock(arch_spinlock_t *lock) -{ - __ticket_spin_unlock(lock); + return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC; } +#define arch_spin_is_contended arch_spin_is_contended static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) @@ -129,8 +182,6 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock, arch_spin_lock(lock); } -#endif /* CONFIG_PARAVIRT_SPINLOCKS */ - static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) { while (arch_spin_is_locked(lock)) diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h index ad0ad07fc006..4f1bea19945b 100644 --- a/arch/x86/include/asm/spinlock_types.h +++ b/arch/x86/include/asm/spinlock_types.h @@ -1,13 +1,17 @@ #ifndef _ASM_X86_SPINLOCK_TYPES_H #define _ASM_X86_SPINLOCK_TYPES_H -#ifndef __LINUX_SPINLOCK_TYPES_H -# error "please don't include this file directly" -#endif - #include <linux/types.h> -#if (CONFIG_NR_CPUS < 256) +#ifdef CONFIG_PARAVIRT_SPINLOCKS +#define __TICKET_LOCK_INC 2 +#define TICKET_SLOWPATH_FLAG ((__ticket_t)1) +#else +#define __TICKET_LOCK_INC 1 +#define TICKET_SLOWPATH_FLAG ((__ticket_t)0) +#endif + +#if (CONFIG_NR_CPUS < (256 / __TICKET_LOCK_INC)) typedef u8 __ticket_t; typedef u16 __ticketpair_t; #else @@ -15,6 +19,8 @@ typedef u16 __ticket_t; typedef u32 __ticketpair_t; #endif +#define TICKET_LOCK_INC ((__ticket_t)__TICKET_LOCK_INC) + #define TICKET_SHIFT (sizeof(__ticket_t) * 8) typedef struct arch_spinlock { diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 4ec45b3abba1..d7f3b3b78ac3 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -2,8 +2,8 @@ #define _ASM_X86_SWITCH_TO_H struct task_struct; /* one of the stranger aspects of C forward declarations */ -struct task_struct *__switch_to(struct task_struct *prev, - struct task_struct *next); +__visible struct task_struct *__switch_to(struct task_struct *prev, + struct task_struct *next); struct tss_struct; void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p, struct tss_struct *tss); diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h index 9d09b4073b60..05af3b31d522 100644 --- a/arch/x86/include/asm/sync_bitops.h +++ b/arch/x86/include/asm/sync_bitops.h @@ -26,9 +26,9 @@ * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ -static inline void sync_set_bit(int nr, volatile unsigned long *addr) +static inline void sync_set_bit(long nr, volatile unsigned long *addr) { - asm volatile("lock; btsl %1,%0" + asm volatile("lock; bts %1,%0" : "+m" (ADDR) : "Ir" (nr) : "memory"); @@ -44,9 +44,9 @@ static inline void sync_set_bit(int nr, volatile unsigned long *addr) * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit() * in order to ensure changes are visible on other processors. */ -static inline void sync_clear_bit(int nr, volatile unsigned long *addr) +static inline void sync_clear_bit(long nr, volatile unsigned long *addr) { - asm volatile("lock; btrl %1,%0" + asm volatile("lock; btr %1,%0" : "+m" (ADDR) : "Ir" (nr) : "memory"); @@ -61,9 +61,9 @@ static inline void sync_clear_bit(int nr, volatile unsigned long *addr) * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ -static inline void sync_change_bit(int nr, volatile unsigned long *addr) +static inline void sync_change_bit(long nr, volatile unsigned long *addr) { - asm volatile("lock; btcl %1,%0" + asm volatile("lock; btc %1,%0" : "+m" (ADDR) : "Ir" (nr) : "memory"); @@ -77,11 +77,11 @@ static inline void sync_change_bit(int nr, volatile unsigned long *addr) * This operation is atomic and cannot be reordered. * It also implies a memory barrier. */ -static inline int sync_test_and_set_bit(int nr, volatile unsigned long *addr) +static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr) { int oldbit; - asm volatile("lock; btsl %2,%1\n\tsbbl %0,%0" + asm volatile("lock; bts %2,%1\n\tsbbl %0,%0" : "=r" (oldbit), "+m" (ADDR) : "Ir" (nr) : "memory"); return oldbit; @@ -95,11 +95,11 @@ static inline int sync_test_and_set_bit(int nr, volatile unsigned long *addr) * This operation is atomic and cannot be reordered. * It also implies a memory barrier. */ -static inline int sync_test_and_clear_bit(int nr, volatile unsigned long *addr) +static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr) { int oldbit; - asm volatile("lock; btrl %2,%1\n\tsbbl %0,%0" + asm volatile("lock; btr %2,%1\n\tsbbl %0,%0" : "=r" (oldbit), "+m" (ADDR) : "Ir" (nr) : "memory"); return oldbit; @@ -113,11 +113,11 @@ static inline int sync_test_and_clear_bit(int nr, volatile unsigned long *addr) * This operation is atomic and cannot be reordered. * It also implies a memory barrier. */ -static inline int sync_test_and_change_bit(int nr, volatile unsigned long *addr) +static inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr) { int oldbit; - asm volatile("lock; btcl %2,%1\n\tsbbl %0,%0" + asm volatile("lock; btc %2,%1\n\tsbbl %0,%0" : "=r" (oldbit), "+m" (ADDR) : "Ir" (nr) : "memory"); return oldbit; diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 2e188d68397c..aea284b41312 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -20,7 +20,8 @@ #include <asm/thread_info.h> /* for TS_COMPAT */ #include <asm/unistd.h> -extern const unsigned long sys_call_table[]; +typedef void (*sys_call_ptr_t)(void); +extern const sys_call_ptr_t sys_call_table[]; /* * Only the low 32 bits of orig_ax are meaningful, so we return int. diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 2917a6452c49..592a6a672e07 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -24,7 +24,7 @@ asmlinkage long sys_iopl(unsigned int); asmlinkage int sys_modify_ldt(int, void __user *, unsigned long); /* kernel/signal.c */ -long sys_rt_sigreturn(void); +asmlinkage long sys_rt_sigreturn(void); /* kernel/tls.c */ asmlinkage long sys_set_thread_area(struct user_desc __user *); @@ -34,7 +34,7 @@ asmlinkage long sys_get_thread_area(struct user_desc __user *); #ifdef CONFIG_X86_32 /* kernel/signal.c */ -unsigned long sys_sigreturn(void); +asmlinkage unsigned long sys_sigreturn(void); /* kernel/vm86_32.c */ asmlinkage long sys_vm86old(struct vm86_struct __user *); @@ -44,7 +44,7 @@ asmlinkage long sys_vm86(unsigned long, unsigned long); /* X86_64 only */ /* kernel/process_64.c */ -long sys_arch_prctl(int, unsigned long); +asmlinkage long sys_arch_prctl(int, unsigned long); /* kernel/sys_x86_64.c */ asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long, diff --git a/arch/x86/include/asm/sysfb.h b/arch/x86/include/asm/sysfb.h new file mode 100644 index 000000000000..2aeb3e25579c --- /dev/null +++ b/arch/x86/include/asm/sysfb.h @@ -0,0 +1,98 @@ +#ifndef _ARCH_X86_KERNEL_SYSFB_H +#define _ARCH_X86_KERNEL_SYSFB_H + +/* + * Generic System Framebuffers on x86 + * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.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 + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + */ + +#include <linux/kernel.h> +#include <linux/platform_data/simplefb.h> +#include <linux/screen_info.h> + +enum { + M_I17, /* 17-Inch iMac */ + M_I20, /* 20-Inch iMac */ + M_I20_SR, /* 20-Inch iMac (Santa Rosa) */ + M_I24, /* 24-Inch iMac */ + M_I24_8_1, /* 24-Inch iMac, 8,1th gen */ + M_I24_10_1, /* 24-Inch iMac, 10,1th gen */ + M_I27_11_1, /* 27-Inch iMac, 11,1th gen */ + M_MINI, /* Mac Mini */ + M_MINI_3_1, /* Mac Mini, 3,1th gen */ + M_MINI_4_1, /* Mac Mini, 4,1th gen */ + M_MB, /* MacBook */ + M_MB_2, /* MacBook, 2nd rev. */ + M_MB_3, /* MacBook, 3rd rev. */ + M_MB_5_1, /* MacBook, 5th rev. */ + M_MB_6_1, /* MacBook, 6th rev. */ + M_MB_7_1, /* MacBook, 7th rev. */ + M_MB_SR, /* MacBook, 2nd gen, (Santa Rosa) */ + M_MBA, /* MacBook Air */ + M_MBA_3, /* Macbook Air, 3rd rev */ + M_MBP, /* MacBook Pro */ + M_MBP_2, /* MacBook Pro 2nd gen */ + M_MBP_2_2, /* MacBook Pro 2,2nd gen */ + M_MBP_SR, /* MacBook Pro (Santa Rosa) */ + M_MBP_4, /* MacBook Pro, 4th gen */ + M_MBP_5_1, /* MacBook Pro, 5,1th gen */ + M_MBP_5_2, /* MacBook Pro, 5,2th gen */ + M_MBP_5_3, /* MacBook Pro, 5,3rd gen */ + M_MBP_6_1, /* MacBook Pro, 6,1th gen */ + M_MBP_6_2, /* MacBook Pro, 6,2th gen */ + M_MBP_7_1, /* MacBook Pro, 7,1th gen */ + M_MBP_8_2, /* MacBook Pro, 8,2nd gen */ + M_UNKNOWN /* placeholder */ +}; + +struct efifb_dmi_info { + char *optname; + unsigned long base; + int stride; + int width; + int height; + int flags; +}; + +#ifdef CONFIG_EFI + +extern struct efifb_dmi_info efifb_dmi_list[]; +void sysfb_apply_efi_quirks(void); + +#else /* CONFIG_EFI */ + +static inline void sysfb_apply_efi_quirks(void) +{ +} + +#endif /* CONFIG_EFI */ + +#ifdef CONFIG_X86_SYSFB + +bool parse_mode(const struct screen_info *si, + struct simplefb_platform_data *mode); +int create_simplefb(const struct screen_info *si, + const struct simplefb_platform_data *mode); + +#else /* CONFIG_X86_SYSFB */ + +static inline bool parse_mode(const struct screen_info *si, + struct simplefb_platform_data *mode) +{ + return false; +} + +static inline int create_simplefb(const struct screen_info *si, + const struct simplefb_platform_data *mode) +{ + return -EINVAL; +} + +#endif /* CONFIG_X86_SYSFB */ + +#endif /* _ARCH_X86_KERNEL_SYSFB_H */ diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 095b21507b6a..d35f24e231cd 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -124,9 +124,6 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); #define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id) #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) #define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) - -/* indicates that pointers to the topology cpumask_t maps are valid */ -#define arch_provides_topology_pointers yes #endif static inline void arch_fix_phys_package_id(int num, u32 slot) diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 88eae2aec619..7036cb60cd87 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -6,11 +6,7 @@ #include <asm/debugreg.h> #include <asm/siginfo.h> /* TRAP_TRACE, ... */ -#ifdef CONFIG_X86_32 -#define dotraplinkage -#else -#define dotraplinkage asmlinkage -#endif +#define dotraplinkage __visible asmlinkage void divide_error(void); asmlinkage void debug(void); diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index c91e8b9d588b..235be70d5bb4 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -49,6 +49,7 @@ extern void tsc_init(void); extern void mark_tsc_unstable(char *reason); extern int unsynchronized_tsc(void); extern int check_tsc_unstable(void); +extern int check_tsc_disabled(void); extern unsigned long native_calibrate_tsc(void); extern int tsc_clocksource_reliable; diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 5ee26875baea..5838fa911aa0 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -153,16 +153,19 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) * Careful: we have to cast the result to the type of the pointer * for sign reasons. * - * The use of %edx as the register specifier is a bit of a + * The use of _ASM_DX as the register specifier is a bit of a * simplification, as gcc only cares about it as the starting point * and not size: for a 64-bit value it will use %ecx:%edx on 32 bits * (%ecx being the next register in gcc's x86 register sequence), and * %rdx on 64 bits. + * + * Clang/LLVM cares about the size of the register, but still wants + * the base register for something that ends up being a pair. */ #define get_user(x, ptr) \ ({ \ int __ret_gu; \ - register __inttype(*(ptr)) __val_gu asm("%edx"); \ + register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ __chk_user_ptr(ptr); \ might_fault(); \ asm volatile("call __get_user_%P3" \ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index f3e01a2cbaa1..966502d4682e 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -387,6 +387,7 @@ enum vmcs_field { #define VMX_EPT_EXTENT_INDIVIDUAL_ADDR 0 #define VMX_EPT_EXTENT_CONTEXT 1 #define VMX_EPT_EXTENT_GLOBAL 2 +#define VMX_EPT_EXTENT_SHIFT 24 #define VMX_EPT_EXECUTE_ONLY_BIT (1ull) #define VMX_EPT_PAGE_WALK_4_BIT (1ull << 6) @@ -394,6 +395,7 @@ enum vmcs_field { #define VMX_EPTP_WB_BIT (1ull << 14) #define VMX_EPT_2MB_PAGE_BIT (1ull << 16) #define VMX_EPT_1GB_PAGE_BIT (1ull << 17) +#define VMX_EPT_INVEPT_BIT (1ull << 20) #define VMX_EPT_AD_BIT (1ull << 21) #define VMX_EPT_EXTENT_CONTEXT_BIT (1ull << 25) #define VMX_EPT_EXTENT_GLOBAL_BIT (1ull << 26) diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h index de656ac2af41..d76ac40da206 100644 --- a/arch/x86/include/asm/vvar.h +++ b/arch/x86/include/asm/vvar.h @@ -35,7 +35,7 @@ #define DEFINE_VVAR(type, name) \ type name \ - __attribute__((section(".vvar_" #name), aligned(16))) + __attribute__((section(".vvar_" #name), aligned(16))) __visible #define VVAR(name) (*vvaraddr_ ## name) diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h index ca842f2769ef..608a79d5a466 100644 --- a/arch/x86/include/asm/xen/events.h +++ b/arch/x86/include/asm/xen/events.h @@ -7,6 +7,7 @@ enum ipi_vector { XEN_CALL_FUNCTION_SINGLE_VECTOR, XEN_SPIN_UNLOCK_VECTOR, XEN_IRQ_WORK_VECTOR, + XEN_NMI_VECTOR, XEN_NR_IPIS, }; diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index 125f344f06a9..d866959e5685 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -40,21 +40,7 @@ extern struct start_info *xen_start_info; static inline uint32_t xen_cpuid_base(void) { - uint32_t base, eax, ebx, ecx, edx; - char signature[13]; - - for (base = 0x40000000; base < 0x40010000; base += 0x100) { - cpuid(base, &eax, &ebx, &ecx, &edx); - *(uint32_t *)(signature + 0) = ebx; - *(uint32_t *)(signature + 4) = ecx; - *(uint32_t *)(signature + 8) = edx; - signature[12] = 0; - - if (!strcmp("XenVMMXenVMM", signature) && ((eax - base) >= 2)) - return base; - } - - return 0; + return hypervisor_cpuid_base("XenVMMXenVMM", 2); } #ifdef CONFIG_XEN diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 06fdbd987e97..94dc8ca434e0 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -23,6 +23,7 @@ #define KVM_FEATURE_ASYNC_PF 4 #define KVM_FEATURE_STEAL_TIME 5 #define KVM_FEATURE_PV_EOI 6 +#define KVM_FEATURE_PV_UNHALT 7 /* The last 8 bits are used to indicate how to interpret the flags field * in pvclock structure. If no bits are set, all flags are ignored. diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index d651082c7cf7..0e79420376eb 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -65,6 +65,7 @@ #define EXIT_REASON_EOI_INDUCED 45 #define EXIT_REASON_EPT_VIOLATION 48 #define EXIT_REASON_EPT_MISCONFIG 49 +#define EXIT_REASON_INVEPT 50 #define EXIT_REASON_PREEMPTION_TIMER 52 #define EXIT_REASON_WBINVD 54 #define EXIT_REASON_XSETBV 55 @@ -106,12 +107,13 @@ { EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \ { EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \ { EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \ + { EXIT_REASON_INVEPT, "INVEPT" }, \ + { EXIT_REASON_PREEMPTION_TIMER, "PREEMPTION_TIMER" }, \ { EXIT_REASON_WBINVD, "WBINVD" }, \ { EXIT_REASON_APIC_WRITE, "APIC_WRITE" }, \ { EXIT_REASON_EOI_INDUCED, "EOI_INDUCED" }, \ { EXIT_REASON_INVALID_STATE, "INVALID_STATE" }, \ { EXIT_REASON_INVD, "INVD" }, \ - { EXIT_REASON_INVPCID, "INVPCID" }, \ - { EXIT_REASON_PREEMPTION_TIMER, "PREEMPTION_TIMER" } + { EXIT_REASON_INVPCID, "INVPCID" } #endif /* _UAPIVMX_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 88d99ea77723..a5408b965c9d 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -103,6 +103,9 @@ obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o obj-$(CONFIG_OF) += devicetree.o obj-$(CONFIG_UPROBES) += uprobes.o +obj-y += sysfb.o +obj-$(CONFIG_X86_SYSFB) += sysfb_simplefb.o +obj-$(CONFIG_EFI) += sysfb_efi.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o obj-$(CONFIG_TRACING) += tracepoint.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 2627a81253ee..40c76604199f 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -67,6 +67,7 @@ EXPORT_SYMBOL(acpi_pci_disabled); int acpi_lapic; int acpi_ioapic; int acpi_strict; +int acpi_disable_cmcff; u8 acpi_sci_flags __initdata; int acpi_sci_override_gsi __initdata; @@ -141,16 +142,8 @@ static u32 irq_to_gsi(int irq) } /* - * Temporarily use the virtual area starting from FIX_IO_APIC_BASE_END, - * to map the target physical address. The problem is that set_fixmap() - * provides a single page, and it is possible that the page is not - * sufficient. - * By using this area, we can map up to MAX_IO_APICS pages temporarily, - * i.e. until the next __va_range() call. - * - * Important Safety Note: The fixed I/O APIC page numbers are *subtracted* - * from the fixed base. That's why we start at FIX_IO_APIC_BASE_END and - * count idx down while incrementing the phys address. + * This is just a simple wrapper around early_ioremap(), + * with sanity checks for phys == 0 and size == 0. */ char *__init __acpi_map_table(unsigned long phys, unsigned long size) { @@ -160,6 +153,7 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size) return early_ioremap(phys, size); } + void __init __acpi_unmap_table(char *map, unsigned long size) { if (!map || !size) @@ -199,7 +193,7 @@ static void acpi_register_lapic(int id, u8 enabled) { unsigned int ver = 0; - if (id >= (MAX_LOCAL_APIC-1)) { + if (id >= MAX_LOCAL_APIC) { printk(KERN_INFO PREFIX "skipped apicid that is too big\n"); return; } @@ -1120,6 +1114,7 @@ int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) int ioapic; int ioapic_pin; struct io_apic_irq_attr irq_attr; + int ret; if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC) return gsi; @@ -1149,7 +1144,9 @@ int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) set_io_apic_irq_attr(&irq_attr, ioapic, ioapic_pin, trigger == ACPI_EDGE_SENSITIVE ? 0 : 1, polarity == ACPI_ACTIVE_HIGH ? 0 : 1); - io_apic_set_pci_routing(dev, gsi_to_irq(gsi), &irq_attr); + ret = io_apic_set_pci_routing(dev, gsi_to_irq(gsi), &irq_attr); + if (ret < 0) + gsi = INT_MIN; return gsi; } @@ -1626,6 +1623,10 @@ static int __init parse_acpi(char *arg) /* "acpi=copy_dsdt" copys DSDT */ else if (strcmp(arg, "copy_dsdt") == 0) { acpi_gbl_copy_dsdt_locally = 1; + } + /* "acpi=nocmcff" disables FF mode for corrected errors */ + else if (strcmp(arg, "nocmcff") == 0) { + acpi_disable_cmcff = 1; } else { /* Core will printk when we return error. */ return -EINVAL; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index c15cf9a25e27..15e8563e5c24 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -11,6 +11,7 @@ #include <linux/memory.h> #include <linux/stop_machine.h> #include <linux/slab.h> +#include <linux/kdebug.h> #include <asm/alternative.h> #include <asm/sections.h> #include <asm/pgtable.h> @@ -596,97 +597,93 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len) return addr; } -/* - * Cross-modifying kernel text with stop_machine(). - * This code originally comes from immediate value. - */ -static atomic_t stop_machine_first; -static int wrote_text; +static void do_sync_core(void *info) +{ + sync_core(); +} -struct text_poke_params { - struct text_poke_param *params; - int nparams; -}; +static bool bp_patching_in_progress; +static void *bp_int3_handler, *bp_int3_addr; -static int __kprobes stop_machine_text_poke(void *data) +int poke_int3_handler(struct pt_regs *regs) { - struct text_poke_params *tpp = data; - struct text_poke_param *p; - int i; + /* bp_patching_in_progress */ + smp_rmb(); - if (atomic_xchg(&stop_machine_first, 0)) { - for (i = 0; i < tpp->nparams; i++) { - p = &tpp->params[i]; - text_poke(p->addr, p->opcode, p->len); - } - smp_wmb(); /* Make sure other cpus see that this has run */ - wrote_text = 1; - } else { - while (!wrote_text) - cpu_relax(); - smp_mb(); /* Load wrote_text before following execution */ - } + if (likely(!bp_patching_in_progress)) + return 0; - for (i = 0; i < tpp->nparams; i++) { - p = &tpp->params[i]; - flush_icache_range((unsigned long)p->addr, - (unsigned long)p->addr + p->len); - } - /* - * Intel Archiecture Software Developer's Manual section 7.1.3 specifies - * that a core serializing instruction such as "cpuid" should be - * executed on _each_ core before the new instruction is made visible. - */ - sync_core(); - return 0; -} + if (user_mode_vm(regs) || regs->ip != (unsigned long)bp_int3_addr) + return 0; + + /* set up the specified breakpoint handler */ + regs->ip = (unsigned long) bp_int3_handler; + + return 1; -/** - * text_poke_smp - Update instructions on a live kernel on SMP - * @addr: address to modify - * @opcode: source of the copy - * @len: length to copy - * - * Modify multi-byte instruction by using stop_machine() on SMP. This allows - * user to poke/set multi-byte text on SMP. Only non-NMI/MCE code modifying - * should be allowed, since stop_machine() does _not_ protect code against - * NMI and MCE. - * - * Note: Must be called under get_online_cpus() and text_mutex. - */ -void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len) -{ - struct text_poke_params tpp; - struct text_poke_param p; - - p.addr = addr; - p.opcode = opcode; - p.len = len; - tpp.params = &p; - tpp.nparams = 1; - atomic_set(&stop_machine_first, 1); - wrote_text = 0; - /* Use __stop_machine() because the caller already got online_cpus. */ - __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask); - return addr; } /** - * text_poke_smp_batch - Update instructions on a live kernel on SMP - * @params: an array of text_poke parameters - * @n: the number of elements in params. + * text_poke_bp() -- update instructions on live kernel on SMP + * @addr: address to patch + * @opcode: opcode of new instruction + * @len: length to copy + * @handler: address to jump to when the temporary breakpoint is hit * - * Modify multi-byte instruction by using stop_machine() on SMP. Since the - * stop_machine() is heavy task, it is better to aggregate text_poke requests - * and do it once if possible. + * Modify multi-byte instruction by using int3 breakpoint on SMP. + * We completely avoid stop_machine() here, and achieve the + * synchronization using int3 breakpoint. * - * Note: Must be called under get_online_cpus() and text_mutex. + * The way it is done: + * - add a int3 trap to the address that will be patched + * - sync cores + * - update all but the first byte of the patched range + * - sync cores + * - replace the first byte (int3) by the first byte of + * replacing opcode + * - sync cores + * + * Note: must be called under text_mutex. */ -void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n) +void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler) { - struct text_poke_params tpp = {.params = params, .nparams = n}; + unsigned char int3 = 0xcc; + + bp_int3_handler = handler; + bp_int3_addr = (u8 *)addr + sizeof(int3); + bp_patching_in_progress = true; + /* + * Corresponding read barrier in int3 notifier for + * making sure the in_progress flags is correctly ordered wrt. + * patching + */ + smp_wmb(); + + text_poke(addr, &int3, sizeof(int3)); - atomic_set(&stop_machine_first, 1); - wrote_text = 0; - __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask); + on_each_cpu(do_sync_core, NULL, 1); + + if (len - sizeof(int3) > 0) { + /* patch all but the first byte */ + text_poke((char *)addr + sizeof(int3), + (const char *) opcode + sizeof(int3), + len - sizeof(int3)); + /* + * According to Intel, this core syncing is very likely + * not necessary and we'd be safe even without it. But + * better safe than sorry (plus there's not only Intel). + */ + on_each_cpu(do_sync_core, NULL, 1); + } + + /* patch the first byte */ + text_poke(addr, opcode, sizeof(int3)); + + on_each_cpu(do_sync_core, NULL, 1); + + bp_patching_in_progress = false; + smp_wmb(); + + return addr; } + diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 3048ded1b598..59554dca96ec 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -20,6 +20,7 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, {} }; @@ -27,6 +28,7 @@ EXPORT_SYMBOL(amd_nb_misc_ids); static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, {} }; @@ -81,13 +83,20 @@ int amd_cache_northbridges(void) next_northbridge(misc, amd_nb_misc_ids); node_to_amd_nb(i)->link = link = next_northbridge(link, amd_nb_link_ids); - } + } + /* GART present only on Fam15h upto model 0fh */ if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || - boot_cpu_data.x86 == 0x15) + (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) amd_northbridges.flags |= AMD_NB_GART; /* + * Check for L3 cache presence. + */ + if (!cpuid_edx(0x80000006)) + return 0; + + /* * Some CPU families support L3 Cache Index Disable. There are some * limitations because of E382 and E388 on family 0x10. */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index eca89c53a7f5..a7eb82d9b012 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -913,7 +913,7 @@ static void local_apic_timer_interrupt(void) * [ if a single-CPU system runs an SMP kernel then we call the local * interrupt as well. Thus we cannot inline the local irq ... ] */ -void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -932,7 +932,7 @@ void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs) set_irq_regs(old_regs); } -void __irq_entry smp_trace_apic_timer_interrupt(struct pt_regs *regs) +__visible void __irq_entry smp_trace_apic_timer_interrupt(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -1946,14 +1946,14 @@ static inline void __smp_spurious_interrupt(void) "should never happen.\n", smp_processor_id()); } -void smp_spurious_interrupt(struct pt_regs *regs) +__visible void smp_spurious_interrupt(struct pt_regs *regs) { entering_irq(); __smp_spurious_interrupt(); exiting_irq(); } -void smp_trace_spurious_interrupt(struct pt_regs *regs) +__visible void smp_trace_spurious_interrupt(struct pt_regs *regs) { entering_irq(); trace_spurious_apic_entry(SPURIOUS_APIC_VECTOR); @@ -2002,14 +2002,14 @@ static inline void __smp_error_interrupt(struct pt_regs *regs) } -void smp_error_interrupt(struct pt_regs *regs) +__visible void smp_error_interrupt(struct pt_regs *regs) { entering_irq(); __smp_error_interrupt(regs); exiting_irq(); } -void smp_trace_error_interrupt(struct pt_regs *regs) +__visible void smp_trace_error_interrupt(struct pt_regs *regs) { entering_irq(); trace_error_apic_entry(ERROR_APIC_VECTOR); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 9ed796ccc32c..e63a5bd2a78f 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1534,6 +1534,11 @@ void intel_ir_io_apic_print_entries(unsigned int apic, } } +void ioapic_zap_locks(void) +{ + raw_spin_lock_init(&ioapic_lock); +} + __apicdebuginit(void) print_IO_APIC(int ioapic_idx) { union IO_APIC_reg_00 reg_00; @@ -3375,12 +3380,15 @@ int io_apic_setup_irq_pin_once(unsigned int irq, int node, { unsigned int ioapic_idx = attr->ioapic, pin = attr->ioapic_pin; int ret; + struct IO_APIC_route_entry orig_entry; /* Avoid redundant programming */ if (test_bit(pin, ioapics[ioapic_idx].pin_programmed)) { - pr_debug("Pin %d-%d already programmed\n", - mpc_ioapic_id(ioapic_idx), pin); - return 0; + pr_debug("Pin %d-%d already programmed\n", mpc_ioapic_id(ioapic_idx), pin); + orig_entry = ioapic_read_entry(attr->ioapic, pin); + if (attr->trigger == orig_entry.trigger && attr->polarity == orig_entry.polarity) + return 0; + return -EBUSY; } ret = io_apic_setup_irq_pin(irq, node, attr); if (!ret) diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 53a4e2744846..3ab03430211d 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -392,7 +392,7 @@ static struct cpuidle_device apm_cpuidle_device; /* * Local variables */ -static struct { +__visible struct { unsigned long offset; unsigned short segment; } apm_bios_entry; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f654ecefea5b..903a264af981 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -66,8 +66,8 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val) * performance at the same time.. */ -extern void vide(void); -__asm__(".align 4\nvide: ret"); +extern __visible void vide(void); +__asm__(".globl vide\n\t.align 4\nvide: ret"); static void init_amd_k5(struct cpuinfo_x86 *c) { @@ -512,7 +512,7 @@ static void early_init_amd(struct cpuinfo_x86 *c) static const int amd_erratum_383[]; static const int amd_erratum_400[]; -static bool cpu_has_amd_erratum(const int *erratum); +static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum); static void init_amd(struct cpuinfo_x86 *c) { @@ -729,11 +729,11 @@ static void init_amd(struct cpuinfo_x86 *c) value &= ~(1ULL << 24); wrmsrl_safe(MSR_AMD64_BU_CFG2, value); - if (cpu_has_amd_erratum(amd_erratum_383)) + if (cpu_has_amd_erratum(c, amd_erratum_383)) set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); } - if (cpu_has_amd_erratum(amd_erratum_400)) + if (cpu_has_amd_erratum(c, amd_erratum_400)) set_cpu_bug(c, X86_BUG_AMD_APIC_C1E); rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); @@ -878,23 +878,13 @@ static const int amd_erratum_400[] = static const int amd_erratum_383[] = AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); -static bool cpu_has_amd_erratum(const int *erratum) + +static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { - struct cpuinfo_x86 *cpu = __this_cpu_ptr(&cpu_info); int osvw_id = *erratum++; u32 range; u32 ms; - /* - * If called early enough that current_cpu_data hasn't been initialized - * yet, fall back to boot_cpu_data. - */ - if (cpu->x86 == 0) - cpu = &boot_cpu_data; - - if (cpu->x86_vendor != X86_VENDOR_AMD) - return false; - if (osvw_id >= 0 && osvw_id < 65536 && cpu_has(cpu, X86_FEATURE_OSVW)) { u64 osvw_len; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 25eb2747b063..2793d1f095a2 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1076,7 +1076,7 @@ struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) debug_idt_table }; DEFINE_PER_CPU_FIRST(union irq_stack_union, - irq_stack_union) __aligned(PAGE_SIZE); + irq_stack_union) __aligned(PAGE_SIZE) __visible; /* * The following four percpu variables are hot. Align current_task to @@ -1093,7 +1093,7 @@ EXPORT_PER_CPU_SYMBOL(kernel_stack); DEFINE_PER_CPU(char *, irq_stack_ptr) = init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64; -DEFINE_PER_CPU(unsigned int, irq_count) = -1; +DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1; DEFINE_PER_CPU(struct task_struct *, fpu_owner_task); diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c index 87279212d318..36ce402a3fa5 100644 --- a/arch/x86/kernel/cpu/hypervisor.c +++ b/arch/x86/kernel/cpu/hypervisor.c @@ -25,11 +25,6 @@ #include <asm/processor.h> #include <asm/hypervisor.h> -/* - * Hypervisor detect order. This is specified explicitly here because - * some hypervisors might implement compatibility modes for other - * hypervisors and therefore need to be detected in specific sequence. - */ static const __initconst struct hypervisor_x86 * const hypervisors[] = { #ifdef CONFIG_XEN_PVHVM @@ -49,15 +44,19 @@ static inline void __init detect_hypervisor_vendor(void) { const struct hypervisor_x86 *h, * const *p; + uint32_t pri, max_pri = 0; for (p = hypervisors; p < hypervisors + ARRAY_SIZE(hypervisors); p++) { h = *p; - if (h->detect()) { + pri = h->detect(); + if (pri != 0 && pri > max_pri) { + max_pri = pri; x86_hyper = h; - printk(KERN_INFO "Hypervisor detected: %s\n", h->name); - break; } } + + if (max_pri) + printk(KERN_INFO "Hypervisor detected: %s\n", x86_hyper->name); } void init_hypervisor(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h index 5b7d4fa5d3b7..09edd0b65fef 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-internal.h +++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h @@ -25,15 +25,18 @@ int mce_severity(struct mce *a, int tolerant, char **msg); struct dentry *mce_get_debugfs_dir(void); extern struct mce_bank *mce_banks; +extern mce_banks_t mce_banks_ce_disabled; #ifdef CONFIG_X86_MCE_INTEL unsigned long mce_intel_adjust_timer(unsigned long interval); void mce_intel_cmci_poll(void); void mce_intel_hcpu_update(unsigned long cpu); +void cmci_disable_bank(int bank); #else # define mce_intel_adjust_timer mce_adjust_timer_default static inline void mce_intel_cmci_poll(void) { } static inline void mce_intel_hcpu_update(unsigned long cpu) { } +static inline void cmci_disable_bank(int bank) { } #endif void mce_timer_kick(unsigned long interval); diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 87a65c939bcd..b3218cdee95f 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -97,6 +97,15 @@ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = { [0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL }; +/* + * MCA banks controlled through firmware first for corrected errors. + * This is a global list of banks for which we won't enable CMCI and we + * won't poll. Firmware controls these banks and is responsible for + * reporting corrected errors through GHES. Uncorrected/recoverable + * errors are still notified through a machine check. + */ +mce_banks_t mce_banks_ce_disabled; + static DEFINE_PER_CPU(struct work_struct, mce_work); static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); @@ -1935,6 +1944,25 @@ static struct miscdevice mce_chrdev_device = { &mce_chrdev_ops, }; +static void __mce_disable_bank(void *arg) +{ + int bank = *((int *)arg); + __clear_bit(bank, __get_cpu_var(mce_poll_banks)); + cmci_disable_bank(bank); +} + +void mce_disable_bank(int bank) +{ + if (bank >= mca_cfg.banks) { + pr_warn(FW_BUG + "Ignoring request to disable invalid MCA bank %d.\n", + bank); + return; + } + set_bit(bank, mce_banks_ce_disabled); + on_each_cpu(__mce_disable_bank, &bank, 1); +} + /* * mce=off Disables machine check * mce=no_cmci Disables CMCI diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index d56405309dc1..4cfe0458ca66 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -203,6 +203,10 @@ static void cmci_discover(int banks) if (test_bit(i, owned)) continue; + /* Skip banks in firmware first mode */ + if (test_bit(i, mce_banks_ce_disabled)) + continue; + rdmsrl(MSR_IA32_MCx_CTL2(i), val); /* Already owned by someone else? */ @@ -271,6 +275,19 @@ void cmci_recheck(void) local_irq_restore(flags); } +/* Caller must hold the lock on cmci_discover_lock */ +static void __cmci_disable_bank(int bank) +{ + u64 val; + + if (!test_bit(bank, __get_cpu_var(mce_banks_owned))) + return; + rdmsrl(MSR_IA32_MCx_CTL2(bank), val); + val &= ~MCI_CTL2_CMCI_EN; + wrmsrl(MSR_IA32_MCx_CTL2(bank), val); + __clear_bit(bank, __get_cpu_var(mce_banks_owned)); +} + /* * Disable CMCI on this CPU for all banks it owns when it goes down. * This allows other CPUs to claim the banks on rediscovery. @@ -280,20 +297,12 @@ void cmci_clear(void) unsigned long flags; int i; int banks; - u64 val; if (!cmci_supported(&banks)) return; raw_spin_lock_irqsave(&cmci_discover_lock, flags); - for (i = 0; i < banks; i++) { - if (!test_bit(i, __get_cpu_var(mce_banks_owned))) - continue; - /* Disable CMCI */ - rdmsrl(MSR_IA32_MCx_CTL2(i), val); - val &= ~MCI_CTL2_CMCI_EN; - wrmsrl(MSR_IA32_MCx_CTL2(i), val); - __clear_bit(i, __get_cpu_var(mce_banks_owned)); - } + for (i = 0; i < banks; i++) + __cmci_disable_bank(i); raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); } @@ -327,6 +336,19 @@ void cmci_reenable(void) cmci_discover(banks); } +void cmci_disable_bank(int bank) +{ + int banks; + unsigned long flags; + + if (!cmci_supported(&banks)) + return; + + raw_spin_lock_irqsave(&cmci_discover_lock, flags); + __cmci_disable_bank(bank); + raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); +} + static void intel_init_cmci(void) { int banks; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 8f4be53ea04b..71a39f3621ba 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -27,20 +27,23 @@ struct ms_hyperv_info ms_hyperv; EXPORT_SYMBOL_GPL(ms_hyperv); -static bool __init ms_hyperv_platform(void) +static uint32_t __init ms_hyperv_platform(void) { u32 eax; u32 hyp_signature[3]; if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) - return false; + return 0; cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS, &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]); - return eax >= HYPERV_CPUID_MIN && - eax <= HYPERV_CPUID_MAX && - !memcmp("Microsoft Hv", hyp_signature, 12); + if (eax >= HYPERV_CPUID_MIN && + eax <= HYPERV_CPUID_MAX && + !memcmp("Microsoft Hv", hyp_signature, 12)) + return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS; + + return 0; } static cycle_t read_hv_clock(struct clocksource *arg) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index a7c7305030cc..8355c84b9729 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1884,6 +1884,7 @@ static struct pmu pmu = { void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) { userpg->cap_usr_time = 0; + userpg->cap_usr_time_zero = 0; userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc; userpg->pmc_width = x86_pmu.cntval_bits; @@ -1897,6 +1898,11 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now) userpg->time_mult = this_cpu_read(cyc2ns); userpg->time_shift = CYC2NS_SCALE_FACTOR; userpg->time_offset = this_cpu_read(cyc2ns_offset) - now; + + if (sched_clock_stable && !check_tsc_disabled()) { + userpg->cap_usr_time_zero = 1; + userpg->time_zero = this_cpu_read(cyc2ns_offset); + } } /* diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 97e557bc4c91..cc16faae0538 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -641,6 +641,8 @@ extern struct event_constraint intel_core2_pebs_event_constraints[]; extern struct event_constraint intel_atom_pebs_event_constraints[]; +extern struct event_constraint intel_slm_pebs_event_constraints[]; + extern struct event_constraint intel_nehalem_pebs_event_constraints[]; extern struct event_constraint intel_westmere_pebs_event_constraints[]; diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 4cbe03287b08..beeb7cc07044 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -347,8 +347,7 @@ static struct amd_nb *amd_alloc_nb(int cpu) struct amd_nb *nb; int i; - nb = kmalloc_node(sizeof(struct amd_nb), GFP_KERNEL | __GFP_ZERO, - cpu_to_node(cpu)); + nb = kzalloc_node(sizeof(struct amd_nb), GFP_KERNEL, cpu_to_node(cpu)); if (!nb) return NULL; diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index a45d8d4ace10..0abf6742a8b0 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -81,7 +81,8 @@ static struct event_constraint intel_nehalem_event_constraints[] __read_mostly = static struct extra_reg intel_nehalem_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b), EVENT_EXTRA_END }; @@ -143,8 +144,9 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly = static struct extra_reg intel_westmere_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1), + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b), EVENT_EXTRA_END }; @@ -162,16 +164,27 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly = EVENT_CONSTRAINT_END }; +static struct event_constraint intel_slm_event_constraints[] __read_mostly = +{ + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */ + EVENT_CONSTRAINT_END +}; + static struct extra_reg intel_snb_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1), + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), EVENT_EXTRA_END }; static struct extra_reg intel_snbep_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), EVENT_EXTRA_END }; @@ -882,6 +895,140 @@ static __initconst const u64 atom_hw_cache_event_ids }, }; +static struct extra_reg intel_slm_extra_regs[] __read_mostly = +{ + /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ + INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x768005ffff, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x768005ffff, RSP_1), + EVENT_EXTRA_END +}; + +#define SLM_DMND_READ SNB_DMND_DATA_RD +#define SLM_DMND_WRITE SNB_DMND_RFO +#define SLM_DMND_PREFETCH (SNB_PF_DATA_RD|SNB_PF_RFO) + +#define SLM_SNP_ANY (SNB_SNP_NONE|SNB_SNP_MISS|SNB_NO_FWD|SNB_HITM) +#define SLM_LLC_ACCESS SNB_RESP_ANY +#define SLM_LLC_MISS (SLM_SNP_ANY|SNB_NON_DRAM) + +static __initconst const u64 slm_hw_cache_extra_regs + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(LL ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = SLM_DMND_READ|SLM_LLC_ACCESS, + [ C(RESULT_MISS) ] = SLM_DMND_READ|SLM_LLC_MISS, + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = SLM_DMND_WRITE|SLM_LLC_ACCESS, + [ C(RESULT_MISS) ] = SLM_DMND_WRITE|SLM_LLC_MISS, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = SLM_DMND_PREFETCH|SLM_LLC_ACCESS, + [ C(RESULT_MISS) ] = SLM_DMND_PREFETCH|SLM_LLC_MISS, + }, + }, +}; + +static __initconst const u64 slm_hw_cache_event_ids + [PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = +{ + [ C(L1D) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0x0104, /* LD_DCU_MISS */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(L1I ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x0380, /* ICACHE.ACCESSES */ + [ C(RESULT_MISS) ] = 0x0280, /* ICACGE.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(LL ) ] = { + [ 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(OP_WRITE) ] = { + /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, + }, + [ C(OP_PREFETCH) ] = { + /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */ + [ C(RESULT_ACCESS) ] = 0x01b7, + /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */ + [ C(RESULT_MISS) ] = 0x01b7, + }, + }, + [ C(DTLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0x0804, /* LD_DTLB_MISS */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = 0, + [ C(RESULT_MISS) ] = 0, + }, + }, + [ C(ITLB) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */ + [ C(RESULT_MISS) ] = 0x0282, /* ITLB.MISSES */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, + [ C(BPU ) ] = { + [ C(OP_READ) ] = { + [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY */ + [ C(RESULT_MISS) ] = 0x00c5, /* BP_INST_RETIRED.MISPRED */ + }, + [ C(OP_WRITE) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + [ C(OP_PREFETCH) ] = { + [ C(RESULT_ACCESS) ] = -1, + [ C(RESULT_MISS) ] = -1, + }, + }, +}; + static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event) { /* user explicitly requested branch sampling */ @@ -1301,11 +1448,11 @@ static void intel_fixup_er(struct perf_event *event, int idx) if (idx == EXTRA_REG_RSP_0) { event->hw.config &= ~INTEL_ARCH_EVENT_MASK; - event->hw.config |= 0x01b7; + event->hw.config |= x86_pmu.extra_regs[EXTRA_REG_RSP_0].event; event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0; } else if (idx == EXTRA_REG_RSP_1) { event->hw.config &= ~INTEL_ARCH_EVENT_MASK; - event->hw.config |= 0x01bb; + event->hw.config |= x86_pmu.extra_regs[EXTRA_REG_RSP_1].event; event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1; } } @@ -2176,6 +2323,21 @@ __init int intel_pmu_init(void) pr_cont("Atom events, "); break; + case 55: /* Atom 22nm "Silvermont" */ + memcpy(hw_cache_event_ids, slm_hw_cache_event_ids, + sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs, + sizeof(hw_cache_extra_regs)); + + intel_pmu_lbr_init_atom(); + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints; + x86_pmu.extra_regs = intel_slm_extra_regs; + x86_pmu.er_flags |= ERF_HAS_RSP_1; + pr_cont("Silvermont events, "); + break; + case 37: /* 32 nm nehalem, "Clarkdale" */ case 44: /* 32 nm nehalem, "Gulftown" */ case 47: /* 32 nm Xeon E7 */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 3065c57a63c1..63438aad177f 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -224,7 +224,7 @@ static int alloc_pebs_buffer(int cpu) if (!x86_pmu.pebs) return 0; - buffer = kmalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node); + buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node); if (unlikely(!buffer)) return -ENOMEM; @@ -262,7 +262,7 @@ static int alloc_bts_buffer(int cpu) if (!x86_pmu.bts) return 0; - buffer = kmalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node); + buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL, node); if (unlikely(!buffer)) return -ENOMEM; @@ -295,7 +295,7 @@ static int alloc_ds_buffer(int cpu) int node = cpu_to_node(cpu); struct debug_store *ds; - ds = kmalloc_node(sizeof(*ds), GFP_KERNEL | __GFP_ZERO, node); + ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node); if (unlikely(!ds)) return -ENOMEM; @@ -517,6 +517,32 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; +struct event_constraint intel_slm_pebs_event_constraints[] = { + INTEL_UEVENT_CONSTRAINT(0x0103, 0x1), /* REHABQ.LD_BLOCK_ST_FORWARD_PS */ + INTEL_UEVENT_CONSTRAINT(0x0803, 0x1), /* REHABQ.LD_SPLITS_PS */ + INTEL_UEVENT_CONSTRAINT(0x0204, 0x1), /* MEM_UOPS_RETIRED.L2_HIT_LOADS_PS */ + INTEL_UEVENT_CONSTRAINT(0x0404, 0x1), /* MEM_UOPS_RETIRED.L2_MISS_LOADS_PS */ + INTEL_UEVENT_CONSTRAINT(0x0804, 0x1), /* MEM_UOPS_RETIRED.DTLB_MISS_LOADS_PS */ + INTEL_UEVENT_CONSTRAINT(0x2004, 0x1), /* MEM_UOPS_RETIRED.HITM_PS */ + INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY_PS */ + INTEL_UEVENT_CONSTRAINT(0x00c4, 0x1), /* BR_INST_RETIRED.ALL_BRANCHES_PS */ + INTEL_UEVENT_CONSTRAINT(0x7ec4, 0x1), /* BR_INST_RETIRED.JCC_PS */ + INTEL_UEVENT_CONSTRAINT(0xbfc4, 0x1), /* BR_INST_RETIRED.FAR_BRANCH_PS */ + INTEL_UEVENT_CONSTRAINT(0xebc4, 0x1), /* BR_INST_RETIRED.NON_RETURN_IND_PS */ + INTEL_UEVENT_CONSTRAINT(0xf7c4, 0x1), /* BR_INST_RETIRED.RETURN_PS */ + INTEL_UEVENT_CONSTRAINT(0xf9c4, 0x1), /* BR_INST_RETIRED.CALL_PS */ + INTEL_UEVENT_CONSTRAINT(0xfbc4, 0x1), /* BR_INST_RETIRED.IND_CALL_PS */ + INTEL_UEVENT_CONSTRAINT(0xfdc4, 0x1), /* BR_INST_RETIRED.REL_CALL_PS */ + INTEL_UEVENT_CONSTRAINT(0xfec4, 0x1), /* BR_INST_RETIRED.TAKEN_JCC_PS */ + INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_MISP_RETIRED.ALL_BRANCHES_PS */ + INTEL_UEVENT_CONSTRAINT(0x7ec5, 0x1), /* BR_INST_MISP_RETIRED.JCC_PS */ + INTEL_UEVENT_CONSTRAINT(0xebc5, 0x1), /* BR_INST_MISP_RETIRED.NON_RETURN_IND_PS */ + INTEL_UEVENT_CONSTRAINT(0xf7c5, 0x1), /* BR_INST_MISP_RETIRED.RETURN_PS */ + INTEL_UEVENT_CONSTRAINT(0xfbc5, 0x1), /* BR_INST_MISP_RETIRED.IND_CALL_PS */ + INTEL_UEVENT_CONSTRAINT(0xfec5, 0x1), /* BR_INST_MISP_RETIRED.TAKEN_JCC_PS */ + EVENT_CONSTRAINT_END +}; + struct event_constraint intel_nehalem_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 1fb6c72717bd..fd8011ed4dcd 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -6,6 +6,8 @@ static struct intel_uncore_type **pci_uncores = empty_uncore; /* pci bus to socket mapping */ static int pcibus_to_physid[256] = { [0 ... 255] = -1, }; +static struct pci_dev *extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX]; + static DEFINE_RAW_SPINLOCK(uncore_box_lock); /* mask of cpus that collect uncore events */ @@ -45,6 +47,24 @@ DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7"); DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15"); DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23"); DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51"); +DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35"); +DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31"); +DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17"); +DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12"); +DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8"); +DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4"); +DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35"); +DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31"); +DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17"); +DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12"); +DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8"); +DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4"); +DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31"); +DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63"); static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event) { @@ -281,7 +301,7 @@ static struct attribute *snbep_uncore_cbox_formats_attr[] = { }; static struct attribute *snbep_uncore_pcu_formats_attr[] = { - &format_attr_event.attr, + &format_attr_event_ext.attr, &format_attr_occ_sel.attr, &format_attr_edge.attr, &format_attr_inv.attr, @@ -301,6 +321,24 @@ static struct attribute *snbep_uncore_qpi_formats_attr[] = { &format_attr_edge.attr, &format_attr_inv.attr, &format_attr_thresh8.attr, + &format_attr_match_rds.attr, + &format_attr_match_rnid30.attr, + &format_attr_match_rnid4.attr, + &format_attr_match_dnid.attr, + &format_attr_match_mc.attr, + &format_attr_match_opc.attr, + &format_attr_match_vnw.attr, + &format_attr_match0.attr, + &format_attr_match1.attr, + &format_attr_mask_rds.attr, + &format_attr_mask_rnid30.attr, + &format_attr_mask_rnid4.attr, + &format_attr_mask_dnid.attr, + &format_attr_mask_mc.attr, + &format_attr_mask_opc.attr, + &format_attr_mask_vnw.attr, + &format_attr_mask0.attr, + &format_attr_mask1.attr, NULL, }; @@ -356,13 +394,16 @@ static struct intel_uncore_ops snbep_uncore_msr_ops = { SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), }; +#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT() \ + .init_box = snbep_uncore_pci_init_box, \ + .disable_box = snbep_uncore_pci_disable_box, \ + .enable_box = snbep_uncore_pci_enable_box, \ + .disable_event = snbep_uncore_pci_disable_event, \ + .read_counter = snbep_uncore_pci_read_counter + static struct intel_uncore_ops snbep_uncore_pci_ops = { - .init_box = snbep_uncore_pci_init_box, - .disable_box = snbep_uncore_pci_disable_box, - .enable_box = snbep_uncore_pci_enable_box, - .disable_event = snbep_uncore_pci_disable_event, - .enable_event = snbep_uncore_pci_enable_event, - .read_counter = snbep_uncore_pci_read_counter, + SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), + .enable_event = snbep_uncore_pci_enable_event, \ }; static struct event_constraint snbep_uncore_cbox_constraints[] = { @@ -726,6 +767,61 @@ static struct intel_uncore_type *snbep_msr_uncores[] = { NULL, }; +enum { + SNBEP_PCI_QPI_PORT0_FILTER, + SNBEP_PCI_QPI_PORT1_FILTER, +}; + +static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) { + reg1->idx = 0; + reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0; + reg1->config = event->attr.config1; + reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0; + reg2->config = event->attr.config2; + } + return 0; +} + +static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct pci_dev *pdev = box->pci_dev; + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + struct hw_perf_event_extra *reg2 = &hwc->branch_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER; + struct pci_dev *filter_pdev = extra_pci_dev[box->phys_id][idx]; + WARN_ON_ONCE(!filter_pdev); + if (filter_pdev) { + pci_write_config_dword(filter_pdev, reg1->reg, + (u32)reg1->config); + pci_write_config_dword(filter_pdev, reg1->reg + 4, + (u32)(reg1->config >> 32)); + pci_write_config_dword(filter_pdev, reg2->reg, + (u32)reg2->config); + pci_write_config_dword(filter_pdev, reg2->reg + 4, + (u32)(reg2->config >> 32)); + } + } + + pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops snbep_uncore_qpi_ops = { + SNBEP_UNCORE_PCI_OPS_COMMON_INIT(), + .enable_event = snbep_qpi_enable_event, + .hw_config = snbep_qpi_hw_config, + .get_constraint = uncore_get_constraint, + .put_constraint = uncore_put_constraint, +}; + #define SNBEP_UNCORE_PCI_COMMON_INIT() \ .perf_ctr = SNBEP_PCI_PMON_CTR0, \ .event_ctl = SNBEP_PCI_PMON_CTL0, \ @@ -755,17 +851,18 @@ static struct intel_uncore_type snbep_uncore_imc = { }; static struct intel_uncore_type snbep_uncore_qpi = { - .name = "qpi", - .num_counters = 4, - .num_boxes = 2, - .perf_ctr_bits = 48, - .perf_ctr = SNBEP_PCI_PMON_CTR0, - .event_ctl = SNBEP_PCI_PMON_CTL0, - .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, - .box_ctl = SNBEP_PCI_PMON_BOX_CTL, - .ops = &snbep_uncore_pci_ops, - .event_descs = snbep_uncore_qpi_events, - .format_group = &snbep_uncore_qpi_format_group, + .name = "qpi", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_qpi_ops, + .event_descs = snbep_uncore_qpi_events, + .format_group = &snbep_uncore_qpi_format_group, }; @@ -807,43 +904,53 @@ static struct intel_uncore_type *snbep_pci_uncores[] = { static DEFINE_PCI_DEVICE_TABLE(snbep_uncore_pci_ids) = { { /* Home Agent */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA), - .driver_data = SNBEP_PCI_UNCORE_HA, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0), }, { /* MC Channel 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0), - .driver_data = SNBEP_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0), }, { /* MC Channel 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1), - .driver_data = SNBEP_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1), }, { /* MC Channel 2 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2), - .driver_data = SNBEP_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2), }, { /* MC Channel 3 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3), - .driver_data = SNBEP_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3), }, { /* QPI Port 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0), - .driver_data = SNBEP_PCI_UNCORE_QPI, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0), }, { /* QPI Port 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1), - .driver_data = SNBEP_PCI_UNCORE_QPI, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1), }, { /* R2PCIe */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE), - .driver_data = SNBEP_PCI_UNCORE_R2PCIE, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0), }, { /* R3QPI Link 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0), - .driver_data = SNBEP_PCI_UNCORE_R3QPI, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0), }, { /* R3QPI Link 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1), - .driver_data = SNBEP_PCI_UNCORE_R3QPI, + .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT0_FILTER), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, + SNBEP_PCI_QPI_PORT1_FILTER), }, { /* end: all zeroes */ } }; @@ -1256,71 +1363,71 @@ static struct intel_uncore_type *ivt_pci_uncores[] = { static DEFINE_PCI_DEVICE_TABLE(ivt_uncore_pci_ids) = { { /* Home Agent 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30), - .driver_data = IVT_PCI_UNCORE_HA, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 0), }, { /* Home Agent 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38), - .driver_data = IVT_PCI_UNCORE_HA, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 1), }, { /* MC0 Channel 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 0), }, { /* MC0 Channel 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 1), }, { /* MC0 Channel 3 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 2), }, { /* MC0 Channel 4 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 3), }, { /* MC1 Channel 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 4), }, { /* MC1 Channel 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 5), }, { /* MC1 Channel 3 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 6), }, { /* MC1 Channel 4 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1), - .driver_data = IVT_PCI_UNCORE_IMC, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 7), }, { /* QPI0 Port 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32), - .driver_data = IVT_PCI_UNCORE_QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 0), }, { /* QPI0 Port 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33), - .driver_data = IVT_PCI_UNCORE_QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 1), }, { /* QPI1 Port 2 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a), - .driver_data = IVT_PCI_UNCORE_QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 2), }, { /* R2PCIe */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34), - .driver_data = IVT_PCI_UNCORE_R2PCIE, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R2PCIE, 0), }, { /* R3QPI0 Link 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36), - .driver_data = IVT_PCI_UNCORE_R3QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 0), }, { /* R3QPI0 Link 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37), - .driver_data = IVT_PCI_UNCORE_R3QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 1), }, { /* R3QPI1 Link 2 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e), - .driver_data = IVT_PCI_UNCORE_R3QPI, + .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 2), }, { /* end: all zeroes */ } }; @@ -2606,7 +2713,7 @@ struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cp size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg); - box = kmalloc_node(size, GFP_KERNEL | __GFP_ZERO, cpu_to_node(cpu)); + box = kzalloc_node(size, GFP_KERNEL, cpu_to_node(cpu)); if (!box) return NULL; @@ -3167,16 +3274,24 @@ static bool pcidrv_registered; /* * add a pci uncore device */ -static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev) +static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct intel_uncore_pmu *pmu; struct intel_uncore_box *box; - int i, phys_id; + struct intel_uncore_type *type; + int phys_id; phys_id = pcibus_to_physid[pdev->bus->number]; if (phys_id < 0) return -ENODEV; + if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) { + extra_pci_dev[phys_id][UNCORE_PCI_DEV_IDX(id->driver_data)] = pdev; + pci_set_drvdata(pdev, NULL); + return 0; + } + + type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)]; box = uncore_alloc_box(type, 0); if (!box) return -ENOMEM; @@ -3185,21 +3300,11 @@ static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev) * for performance monitoring unit with multiple boxes, * each box has a different function id. */ - for (i = 0; i < type->num_boxes; i++) { - pmu = &type->pmus[i]; - if (pmu->func_id == pdev->devfn) - break; - if (pmu->func_id < 0) { - pmu->func_id = pdev->devfn; - break; - } - pmu = NULL; - } - - if (!pmu) { - kfree(box); - return -EINVAL; - } + pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)]; + if (pmu->func_id < 0) + pmu->func_id = pdev->devfn; + else + WARN_ON_ONCE(pmu->func_id != pdev->devfn); box->phys_id = phys_id; box->pci_dev = pdev; @@ -3217,9 +3322,22 @@ static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev) static void uncore_pci_remove(struct pci_dev *pdev) { struct intel_uncore_box *box = pci_get_drvdata(pdev); - struct intel_uncore_pmu *pmu = box->pmu; - int cpu, phys_id = pcibus_to_physid[pdev->bus->number]; + struct intel_uncore_pmu *pmu; + int i, cpu, phys_id = pcibus_to_physid[pdev->bus->number]; + box = pci_get_drvdata(pdev); + if (!box) { + for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) { + if (extra_pci_dev[phys_id][i] == pdev) { + extra_pci_dev[phys_id][i] = NULL; + break; + } + } + WARN_ON_ONCE(i >= UNCORE_EXTRA_PCI_DEV_MAX); + return; + } + + pmu = box->pmu; if (WARN_ON_ONCE(phys_id != box->phys_id)) return; @@ -3240,12 +3358,6 @@ static void uncore_pci_remove(struct pci_dev *pdev) kfree(box); } -static int uncore_pci_probe(struct pci_dev *pdev, - const struct pci_device_id *id) -{ - return uncore_pci_add(pci_uncores[id->driver_data], pdev); -} - static int __init uncore_pci_init(void) { int ret; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 47b3d00c9d89..a80ab71a883d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -12,6 +12,15 @@ #define UNCORE_PMC_IDX_FIXED UNCORE_PMC_IDX_MAX_GENERIC #define UNCORE_PMC_IDX_MAX (UNCORE_PMC_IDX_FIXED + 1) +#define UNCORE_PCI_DEV_DATA(type, idx) ((type << 8) | idx) +#define UNCORE_PCI_DEV_TYPE(data) ((data >> 8) & 0xff) +#define UNCORE_PCI_DEV_IDX(data) (data & 0xff) +#define UNCORE_EXTRA_PCI_DEV 0xff +#define UNCORE_EXTRA_PCI_DEV_MAX 2 + +/* support up to 8 sockets */ +#define UNCORE_SOCKET_MAX 8 + #define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff) /* SNB event control */ @@ -108,6 +117,7 @@ (SNBEP_PMON_CTL_EV_SEL_MASK | \ SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_EV_SEL_EXT | \ SNBEP_PMON_CTL_INVERT | \ SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 7076878404ec..628a059a9a06 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -93,7 +93,7 @@ static void __init vmware_platform_setup(void) * serial key should be enough, as this will always have a VMware * specific string when running under VMware hypervisor. */ -static bool __init vmware_platform(void) +static uint32_t __init vmware_platform(void) { if (cpu_has_hypervisor) { unsigned int eax; @@ -102,12 +102,12 @@ static bool __init vmware_platform(void) cpuid(CPUID_VMWARE_INFO_LEAF, &eax, &hyper_vendor_id[0], &hyper_vendor_id[1], &hyper_vendor_id[2]); if (!memcmp(hyper_vendor_id, "VMwareVMware", 12)) - return true; + return CPUID_VMWARE_INFO_LEAF; } else if (dmi_available && dmi_name_in_serial("VMware") && __vmware_platform()) - return true; + return 1; - return false; + return 0; } /* diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 74467feb4dc5..e0e0841eef45 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -128,7 +128,9 @@ void native_machine_crash_shutdown(struct pt_regs *regs) cpu_emergency_svm_disable(); lapic_shutdown(); -#if defined(CONFIG_X86_IO_APIC) +#ifdef CONFIG_X86_IO_APIC + /* Prevent crash_kexec() from deadlocking on ioapic_lock. */ + ioapic_zap_locks(); disable_IO_APIC(); #endif #ifdef CONFIG_HPET_TIMER diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index d32abeabbda5..174da5fc5a7b 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -658,15 +658,18 @@ __init void e820_setup_gap(void) * boot_params.e820_map, others are passed via SETUP_E820_EXT node of * linked list of struct setup_data, which is parsed here. */ -void __init parse_e820_ext(struct setup_data *sdata) +void __init parse_e820_ext(u64 phys_addr, u32 data_len) { int entries; struct e820entry *extmap; + struct setup_data *sdata; + sdata = early_memremap(phys_addr, data_len); entries = sdata->len / sizeof(struct e820entry); extmap = (struct e820entry *)(sdata->data); __append_e820_map(extmap, entries); sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); + early_iounmap(sdata, data_len); printk(KERN_INFO "e820: extended physical RAM map:\n"); e820_print_map("extended"); } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 138463a24877..06f87bece92a 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -29,7 +29,7 @@ static void __init i386_default_early_setup(void) reserve_ebda_region(); } -void __init i386_start_kernel(void) +asmlinkage void __init i386_start_kernel(void) { sanitize_boot_params(&boot_params); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 55b67614ed94..1be8e43b669e 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -137,7 +137,7 @@ static void __init copy_bootdata(char *real_mode_data) } } -void __init x86_64_start_kernel(char * real_mode_data) +asmlinkage void __init x86_64_start_kernel(char * real_mode_data) { int i; diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 5dd87a89f011..81ba27679f18 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -409,6 +409,7 @@ enable_paging: /* * Check if it is 486 */ + movb $4,X86 # at least 486 cmpl $-1,X86_CPUID je is486 @@ -436,7 +437,6 @@ enable_paging: movl %edx,X86_CAPABILITY is486: - movb $4,X86 movl $0x50022,%ecx # set AM, WP, NE and MP movl %cr0,%eax andl $0x80000011,%eax # Save PG,PE,ET diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 3a8185c042a2..22d0687e7fda 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -177,7 +177,7 @@ u64 arch_irq_stat(void) * SMP cross-CPU interrupts have their own specific * handlers). */ -unsigned int __irq_entry do_IRQ(struct pt_regs *regs) +__visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -215,7 +215,7 @@ void __smp_x86_platform_ipi(void) x86_platform_ipi_callback(); } -void smp_x86_platform_ipi(struct pt_regs *regs) +__visible void smp_x86_platform_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -229,7 +229,7 @@ void smp_x86_platform_ipi(struct pt_regs *regs) /* * Handler for POSTED_INTERRUPT_VECTOR. */ -void smp_kvm_posted_intr_ipi(struct pt_regs *regs) +__visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); @@ -247,7 +247,7 @@ void smp_kvm_posted_intr_ipi(struct pt_regs *regs) } #endif -void smp_trace_x86_platform_ipi(struct pt_regs *regs) +__visible void smp_trace_x86_platform_ipi(struct pt_regs *regs) { struct pt_regs *old_regs = set_irq_regs(regs); diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index 636a55e4a13c..1de84e3ab4e0 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -22,14 +22,14 @@ static inline void __smp_irq_work_interrupt(void) irq_work_run(); } -void smp_irq_work_interrupt(struct pt_regs *regs) +__visible void smp_irq_work_interrupt(struct pt_regs *regs) { irq_work_entering_irq(); __smp_irq_work_interrupt(); exiting_irq(); } -void smp_trace_irq_work_interrupt(struct pt_regs *regs) +__visible void smp_trace_irq_work_interrupt(struct pt_regs *regs) { irq_work_entering_irq(); trace_irq_work_entry(IRQ_WORK_VECTOR); diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c index 2889b3d43882..460f5d9ceebb 100644 --- a/arch/x86/kernel/jump_label.c +++ b/arch/x86/kernel/jump_label.c @@ -37,7 +37,19 @@ static void __jump_label_transform(struct jump_entry *entry, } else memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE); - (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE); + /* + * Make text_poke_bp() a default fallback poker. + * + * At the time the change is being done, just ignore whether we + * are doing nop -> jump or jump -> nop transition, and assume + * always nop being the 'currently valid' instruction + * + */ + if (poker) + (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE); + else + text_poke_bp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE, + (void *)entry->code + JUMP_LABEL_NOP_SIZE); } void arch_jump_label_transform(struct jump_entry *entry, @@ -45,7 +57,7 @@ void arch_jump_label_transform(struct jump_entry *entry, { get_online_cpus(); mutex_lock(&text_mutex); - __jump_label_transform(entry, type, text_poke_smp); + __jump_label_transform(entry, type, NULL); mutex_unlock(&text_mutex); put_online_cpus(); } diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index 2e9d4b5af036..c6ee63f927ab 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -82,14 +82,9 @@ extern void synthesize_reljump(void *from, void *to); extern void synthesize_relcall(void *from, void *to); #ifdef CONFIG_OPTPROBES -extern int arch_init_optprobes(void); extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter); extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr); #else /* !CONFIG_OPTPROBES */ -static inline int arch_init_optprobes(void) -{ - return 0; -} static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) { return 0; diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 211bce445522..79a3f9682871 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -661,7 +661,7 @@ static void __used __kprobes kretprobe_trampoline_holder(void) /* * Called from kretprobe_trampoline */ -static __used __kprobes void *trampoline_handler(struct pt_regs *regs) +__visible __used __kprobes void *trampoline_handler(struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; @@ -1068,7 +1068,7 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) int __init arch_init_kprobes(void) { - return arch_init_optprobes(); + return 0; } int __kprobes arch_trampoline_kprobe(struct kprobe *p) diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 76dc6f095724..898160b42e43 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -88,9 +88,7 @@ static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long v *(unsigned long *)addr = val; } -static void __used __kprobes kprobes_optinsn_template_holder(void) -{ - asm volatile ( +asm ( ".global optprobe_template_entry\n" "optprobe_template_entry:\n" #ifdef CONFIG_X86_64 @@ -129,7 +127,6 @@ static void __used __kprobes kprobes_optinsn_template_holder(void) #endif ".global optprobe_template_end\n" "optprobe_template_end:\n"); -} #define TMPL_MOVE_IDX \ ((long)&optprobe_template_val - (long)&optprobe_template_entry) @@ -371,31 +368,6 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) return 0; } -#define MAX_OPTIMIZE_PROBES 256 -static struct text_poke_param *jump_poke_params; -static struct jump_poke_buffer { - u8 buf[RELATIVEJUMP_SIZE]; -} *jump_poke_bufs; - -static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, - u8 *insn_buf, - struct optimized_kprobe *op) -{ - s32 rel = (s32)((long)op->optinsn.insn - - ((long)op->kp.addr + RELATIVEJUMP_SIZE)); - - /* Backup instructions which will be replaced by jump address */ - memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, - RELATIVE_ADDR_SIZE); - - insn_buf[0] = RELATIVEJUMP_OPCODE; - *(s32 *)(&insn_buf[1]) = rel; - - tprm->addr = op->kp.addr; - tprm->opcode = insn_buf; - tprm->len = RELATIVEJUMP_SIZE; -} - /* * Replace breakpoints (int3) with relative jumps. * Caller must call with locking kprobe_mutex and text_mutex. @@ -403,37 +375,38 @@ static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm, void __kprobes arch_optimize_kprobes(struct list_head *oplist) { struct optimized_kprobe *op, *tmp; - int c = 0; + u8 insn_buf[RELATIVEJUMP_SIZE]; list_for_each_entry_safe(op, tmp, oplist, list) { + s32 rel = (s32)((long)op->optinsn.insn - + ((long)op->kp.addr + RELATIVEJUMP_SIZE)); + WARN_ON(kprobe_disabled(&op->kp)); - /* Setup param */ - setup_optimize_kprobe(&jump_poke_params[c], - jump_poke_bufs[c].buf, op); + + /* Backup instructions which will be replaced by jump address */ + memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE, + RELATIVE_ADDR_SIZE); + + insn_buf[0] = RELATIVEJUMP_OPCODE; + *(s32 *)(&insn_buf[1]) = rel; + + text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE, + op->optinsn.insn); + list_del_init(&op->list); - if (++c >= MAX_OPTIMIZE_PROBES) - break; } - - /* - * text_poke_smp doesn't support NMI/MCE code modifying. - * However, since kprobes itself also doesn't support NMI/MCE - * code probing, it's not a problem. - */ - text_poke_smp_batch(jump_poke_params, c); } -static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm, - u8 *insn_buf, - struct optimized_kprobe *op) +/* Replace a relative jump with a breakpoint (int3). */ +void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) { + u8 insn_buf[RELATIVEJUMP_SIZE]; + /* Set int3 to first byte for kprobes */ insn_buf[0] = BREAKPOINT_INSTRUCTION; memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - - tprm->addr = op->kp.addr; - tprm->opcode = insn_buf; - tprm->len = RELATIVEJUMP_SIZE; + text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE, + op->optinsn.insn); } /* @@ -444,34 +417,11 @@ extern void arch_unoptimize_kprobes(struct list_head *oplist, struct list_head *done_list) { struct optimized_kprobe *op, *tmp; - int c = 0; list_for_each_entry_safe(op, tmp, oplist, list) { - /* Setup param */ - setup_unoptimize_kprobe(&jump_poke_params[c], - jump_poke_bufs[c].buf, op); + arch_unoptimize_kprobe(op); list_move(&op->list, done_list); - if (++c >= MAX_OPTIMIZE_PROBES) - break; } - - /* - * text_poke_smp doesn't support NMI/MCE code modifying. - * However, since kprobes itself also doesn't support NMI/MCE - * code probing, it's not a problem. - */ - text_poke_smp_batch(jump_poke_params, c); -} - -/* Replace a relative jump with a breakpoint (int3). */ -void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) -{ - u8 buf[RELATIVEJUMP_SIZE]; - - /* Set int3 to first byte for kprobes */ - buf[0] = BREAKPOINT_INSTRUCTION; - memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE); - text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE); } int __kprobes @@ -491,22 +441,3 @@ setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) } return 0; } - -int __kprobes arch_init_optprobes(void) -{ - /* Allocate code buffer and parameter array */ - jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) * - MAX_OPTIMIZE_PROBES, GFP_KERNEL); - if (!jump_poke_bufs) - return -ENOMEM; - - jump_poke_params = kmalloc(sizeof(struct text_poke_param) * - MAX_OPTIMIZE_PROBES, GFP_KERNEL); - if (!jump_poke_params) { - kfree(jump_poke_bufs); - jump_poke_bufs = NULL; - return -ENOMEM; - } - - return 0; -} diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index a96d32cc55b8..697b93af02dd 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -34,6 +34,7 @@ #include <linux/sched.h> #include <linux/slab.h> #include <linux/kprobes.h> +#include <linux/debugfs.h> #include <asm/timer.h> #include <asm/cpu.h> #include <asm/traps.h> @@ -419,6 +420,7 @@ static void __init kvm_smp_prepare_boot_cpu(void) WARN_ON(kvm_register_clock("primary cpu clock")); kvm_guest_cpu_init(); native_smp_prepare_boot_cpu(); + kvm_spinlock_init(); } static void kvm_guest_cpu_online(void *dummy) @@ -498,11 +500,9 @@ void __init kvm_guest_init(void) #endif } -static bool __init kvm_detect(void) +static uint32_t __init kvm_detect(void) { - if (!kvm_para_available()) - return false; - return true; + return kvm_cpuid_base(); } const struct hypervisor_x86 x86_hyper_kvm __refconst = { @@ -523,3 +523,263 @@ static __init int activate_jump_labels(void) return 0; } arch_initcall(activate_jump_labels); + +#ifdef CONFIG_PARAVIRT_SPINLOCKS + +/* Kick a cpu by its apicid. Used to wake up a halted vcpu */ +static void kvm_kick_cpu(int cpu) +{ + int apicid; + unsigned long flags = 0; + + apicid = per_cpu(x86_cpu_to_apicid, cpu); + kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid); +} + +enum kvm_contention_stat { + TAKEN_SLOW, + TAKEN_SLOW_PICKUP, + RELEASED_SLOW, + RELEASED_SLOW_KICKED, + NR_CONTENTION_STATS +}; + +#ifdef CONFIG_KVM_DEBUG_FS +#define HISTO_BUCKETS 30 + +static struct kvm_spinlock_stats +{ + u32 contention_stats[NR_CONTENTION_STATS]; + u32 histo_spin_blocked[HISTO_BUCKETS+1]; + u64 time_blocked; +} spinlock_stats; + +static u8 zero_stats; + +static inline void check_zero(void) +{ + u8 ret; + u8 old; + + old = ACCESS_ONCE(zero_stats); + if (unlikely(old)) { + ret = cmpxchg(&zero_stats, old, 0); + /* This ensures only one fellow resets the stat */ + if (ret == old) + memset(&spinlock_stats, 0, sizeof(spinlock_stats)); + } +} + +static inline void add_stats(enum kvm_contention_stat var, u32 val) +{ + check_zero(); + spinlock_stats.contention_stats[var] += val; +} + + +static inline u64 spin_time_start(void) +{ + return sched_clock(); +} + +static void __spin_time_accum(u64 delta, u32 *array) +{ + unsigned index; + + index = ilog2(delta); + check_zero(); + + if (index < HISTO_BUCKETS) + array[index]++; + else + array[HISTO_BUCKETS]++; +} + +static inline void spin_time_accum_blocked(u64 start) +{ + u32 delta; + + delta = sched_clock() - start; + __spin_time_accum(delta, spinlock_stats.histo_spin_blocked); + spinlock_stats.time_blocked += delta; +} + +static struct dentry *d_spin_debug; +static struct dentry *d_kvm_debug; + +struct dentry *kvm_init_debugfs(void) +{ + d_kvm_debug = debugfs_create_dir("kvm", NULL); + if (!d_kvm_debug) + printk(KERN_WARNING "Could not create 'kvm' debugfs directory\n"); + + return d_kvm_debug; +} + +static int __init kvm_spinlock_debugfs(void) +{ + struct dentry *d_kvm; + + d_kvm = kvm_init_debugfs(); + if (d_kvm == NULL) + return -ENOMEM; + + d_spin_debug = debugfs_create_dir("spinlocks", d_kvm); + + debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats); + + debugfs_create_u32("taken_slow", 0444, d_spin_debug, + &spinlock_stats.contention_stats[TAKEN_SLOW]); + debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug, + &spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]); + + debugfs_create_u32("released_slow", 0444, d_spin_debug, + &spinlock_stats.contention_stats[RELEASED_SLOW]); + debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug, + &spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]); + + debugfs_create_u64("time_blocked", 0444, d_spin_debug, + &spinlock_stats.time_blocked); + + debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug, + spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1); + + return 0; +} +fs_initcall(kvm_spinlock_debugfs); +#else /* !CONFIG_KVM_DEBUG_FS */ +static inline void add_stats(enum kvm_contention_stat var, u32 val) +{ +} + +static inline u64 spin_time_start(void) +{ + return 0; +} + +static inline void spin_time_accum_blocked(u64 start) +{ +} +#endif /* CONFIG_KVM_DEBUG_FS */ + +struct kvm_lock_waiting { + struct arch_spinlock *lock; + __ticket_t want; +}; + +/* cpus 'waiting' on a spinlock to become available */ +static cpumask_t waiting_cpus; + +/* Track spinlock on which a cpu is waiting */ +static DEFINE_PER_CPU(struct kvm_lock_waiting, klock_waiting); + +static void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want) +{ + struct kvm_lock_waiting *w; + int cpu; + u64 start; + unsigned long flags; + + if (in_nmi()) + return; + + w = &__get_cpu_var(klock_waiting); + cpu = smp_processor_id(); + start = spin_time_start(); + + /* + * Make sure an interrupt handler can't upset things in a + * partially setup state. + */ + local_irq_save(flags); + + /* + * The ordering protocol on this is that the "lock" pointer + * may only be set non-NULL if the "want" ticket is correct. + * If we're updating "want", we must first clear "lock". + */ + w->lock = NULL; + smp_wmb(); + w->want = want; + smp_wmb(); + w->lock = lock; + + add_stats(TAKEN_SLOW, 1); + + /* + * This uses set_bit, which is atomic but we should not rely on its + * reordering gurantees. So barrier is needed after this call. + */ + cpumask_set_cpu(cpu, &waiting_cpus); + + barrier(); + + /* + * Mark entry to slowpath before doing the pickup test to make + * sure we don't deadlock with an unlocker. + */ + __ticket_enter_slowpath(lock); + + /* + * check again make sure it didn't become free while + * we weren't looking. + */ + if (ACCESS_ONCE(lock->tickets.head) == want) { + add_stats(TAKEN_SLOW_PICKUP, 1); + goto out; + } + + /* + * halt until it's our turn and kicked. Note that we do safe halt + * for irq enabled case to avoid hang when lock info is overwritten + * in irq spinlock slowpath and no spurious interrupt occur to save us. + */ + if (arch_irqs_disabled_flags(flags)) + halt(); + else + safe_halt(); + +out: + cpumask_clear_cpu(cpu, &waiting_cpus); + w->lock = NULL; + local_irq_restore(flags); + spin_time_accum_blocked(start); +} +PV_CALLEE_SAVE_REGS_THUNK(kvm_lock_spinning); + +/* Kick vcpu waiting on @lock->head to reach value @ticket */ +static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket) +{ + int cpu; + + add_stats(RELEASED_SLOW, 1); + for_each_cpu(cpu, &waiting_cpus) { + const struct kvm_lock_waiting *w = &per_cpu(klock_waiting, cpu); + if (ACCESS_ONCE(w->lock) == lock && + ACCESS_ONCE(w->want) == ticket) { + add_stats(RELEASED_SLOW_KICKED, 1); + kvm_kick_cpu(cpu); + break; + } + } +} + +/* + * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present. + */ +void __init kvm_spinlock_init(void) +{ + if (!kvm_para_available()) + return; + /* Does host kernel support KVM_FEATURE_PV_UNHALT? */ + if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT)) + return; + + printk(KERN_INFO "KVM setup paravirtual spinlock\n"); + + static_key_slow_inc(¶virt_ticketlocks_enabled); + + pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning); + pv_lock_ops.unlock_kick = kvm_unlock_kick; +} +#endif /* CONFIG_PARAVIRT_SPINLOCKS */ diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c index 7a0adb7ee433..7123b5df479d 100644 --- a/arch/x86/kernel/microcode_amd.c +++ b/arch/x86/kernel/microcode_amd.c @@ -145,10 +145,9 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig) return 0; } -static unsigned int verify_patch_size(int cpu, u32 patch_size, +static unsigned int verify_patch_size(u8 family, u32 patch_size, unsigned int size) { - struct cpuinfo_x86 *c = &cpu_data(cpu); u32 max_size; #define F1XH_MPB_MAX_SIZE 2048 @@ -156,7 +155,7 @@ static unsigned int verify_patch_size(int cpu, u32 patch_size, #define F15H_MPB_MAX_SIZE 4096 #define F16H_MPB_MAX_SIZE 3458 - switch (c->x86) { + switch (family) { case 0x14: max_size = F14H_MPB_MAX_SIZE; break; @@ -277,9 +276,8 @@ static void cleanup(void) * driver cannot continue functioning normally. In such cases, we tear * down everything we've used up so far and exit. */ -static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover) +static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover) { - struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_header_amd *mc_hdr; struct ucode_patch *patch; unsigned int patch_size, crnt_size, ret; @@ -299,7 +297,7 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover) /* check if patch is for the current family */ proc_fam = ((proc_fam >> 8) & 0xf) + ((proc_fam >> 20) & 0xff); - if (proc_fam != c->x86) + if (proc_fam != family) return crnt_size; if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) { @@ -308,7 +306,7 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover) return crnt_size; } - ret = verify_patch_size(cpu, patch_size, leftover); + ret = verify_patch_size(family, patch_size, leftover); if (!ret) { pr_err("Patch-ID 0x%08x: size mismatch.\n", mc_hdr->patch_id); return crnt_size; @@ -339,7 +337,8 @@ static int verify_and_add_patch(unsigned int cpu, u8 *fw, unsigned int leftover) return crnt_size; } -static enum ucode_state __load_microcode_amd(int cpu, const u8 *data, size_t size) +static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, + size_t size) { enum ucode_state ret = UCODE_ERROR; unsigned int leftover; @@ -362,7 +361,7 @@ static enum ucode_state __load_microcode_amd(int cpu, const u8 *data, size_t siz } while (leftover) { - crnt_size = verify_and_add_patch(cpu, fw, leftover); + crnt_size = verify_and_add_patch(family, fw, leftover); if (crnt_size < 0) return ret; @@ -373,22 +372,22 @@ static enum ucode_state __load_microcode_amd(int cpu, const u8 *data, size_t siz return UCODE_OK; } -enum ucode_state load_microcode_amd(int cpu, const u8 *data, size_t size) +enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size) { enum ucode_state ret; /* free old equiv table */ free_equiv_cpu_table(); - ret = __load_microcode_amd(cpu, data, size); + ret = __load_microcode_amd(family, data, size); if (ret != UCODE_OK) cleanup(); #if defined(CONFIG_MICROCODE_AMD_EARLY) && defined(CONFIG_X86_32) /* save BSP's matching patch for early load */ - if (cpu_data(cpu).cpu_index == boot_cpu_data.cpu_index) { - struct ucode_patch *p = find_patch(cpu); + if (cpu_data(smp_processor_id()).cpu_index == boot_cpu_data.cpu_index) { + struct ucode_patch *p = find_patch(smp_processor_id()); if (p) { memset(amd_bsp_mpb, 0, MPB_MAX_SIZE); memcpy(amd_bsp_mpb, p->data, min_t(u32, ksize(p->data), @@ -441,7 +440,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, goto fw_release; } - ret = load_microcode_amd(cpu, fw->data, fw->size); + ret = load_microcode_amd(c->x86, fw->data, fw->size); fw_release: release_firmware(fw); diff --git a/arch/x86/kernel/microcode_amd_early.c b/arch/x86/kernel/microcode_amd_early.c index 1d14ffee5749..6073104ccaa3 100644 --- a/arch/x86/kernel/microcode_amd_early.c +++ b/arch/x86/kernel/microcode_amd_early.c @@ -238,25 +238,17 @@ static void __init collect_cpu_sig_on_bsp(void *arg) uci->cpu_sig.sig = cpuid_eax(0x00000001); } #else -static void collect_cpu_info_amd_early(struct cpuinfo_x86 *c, - struct ucode_cpu_info *uci) +void load_ucode_amd_ap(void) { + unsigned int cpu = smp_processor_id(); + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; u32 rev, eax; rdmsr(MSR_AMD64_PATCH_LEVEL, rev, eax); eax = cpuid_eax(0x00000001); - uci->cpu_sig.sig = eax; uci->cpu_sig.rev = rev; - c->microcode = rev; - c->x86 = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); -} - -void load_ucode_amd_ap(void) -{ - unsigned int cpu = smp_processor_id(); - - collect_cpu_info_amd_early(&cpu_data(cpu), ucode_cpu_info + cpu); + uci->cpu_sig.sig = eax; if (cpu && !ucode_loaded) { void *ucode; @@ -265,8 +257,10 @@ void load_ucode_amd_ap(void) return; ucode = (void *)(initrd_start + ucode_offset); - if (load_microcode_amd(0, ucode, ucode_size) != UCODE_OK) + eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); + if (load_microcode_amd(eax, ucode, ucode_size) != UCODE_OK) return; + ucode_loaded = true; } @@ -278,6 +272,8 @@ int __init save_microcode_in_initrd_amd(void) { enum ucode_state ret; void *ucode; + u32 eax; + #ifdef CONFIG_X86_32 unsigned int bsp = boot_cpu_data.cpu_index; struct ucode_cpu_info *uci = ucode_cpu_info + bsp; @@ -293,7 +289,10 @@ int __init save_microcode_in_initrd_amd(void) return 0; ucode = (void *)(initrd_start + ucode_offset); - ret = load_microcode_amd(0, ucode, ucode_size); + eax = cpuid_eax(0x00000001); + eax = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff); + + ret = load_microcode_amd(eax, ucode, ucode_size); if (ret != UCODE_OK) return -EINVAL; diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c index 676b8c77a976..bbb6c7316341 100644 --- a/arch/x86/kernel/paravirt-spinlocks.c +++ b/arch/x86/kernel/paravirt-spinlocks.c @@ -4,25 +4,17 @@ */ #include <linux/spinlock.h> #include <linux/module.h> +#include <linux/jump_label.h> #include <asm/paravirt.h> -static inline void -default_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags) -{ - arch_spin_lock(lock); -} - struct pv_lock_ops pv_lock_ops = { #ifdef CONFIG_SMP - .spin_is_locked = __ticket_spin_is_locked, - .spin_is_contended = __ticket_spin_is_contended, - - .spin_lock = __ticket_spin_lock, - .spin_lock_flags = default_spin_lock_flags, - .spin_trylock = __ticket_spin_trylock, - .spin_unlock = __ticket_spin_unlock, + .lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop), + .unlock_kick = paravirt_nop, #endif }; EXPORT_SYMBOL(pv_lock_ops); +struct static_key paravirt_ticketlocks_enabled = STATIC_KEY_INIT_FALSE; +EXPORT_SYMBOL(paravirt_ticketlocks_enabled); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index cd6de64cc480..884aa4053313 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -324,7 +324,7 @@ struct pv_time_ops pv_time_ops = { .steal_clock = native_steal_clock, }; -struct pv_irq_ops pv_irq_ops = { +__visible struct pv_irq_ops pv_irq_ops = { .save_fl = __PV_IS_CALLEE_SAVE(native_save_fl), .restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl), .irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable), @@ -336,7 +336,7 @@ struct pv_irq_ops pv_irq_ops = { #endif }; -struct pv_cpu_ops pv_cpu_ops = { +__visible struct pv_cpu_ops pv_cpu_ops = { .cpuid = native_cpuid, .get_debugreg = native_get_debugreg, .set_debugreg = native_set_debugreg, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 83369e5a1d27..c83516be1052 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -36,7 +36,7 @@ * section. Since TSS's are completely CPU-local, we want them * on exact cacheline boundaries, to eliminate cacheline ping-pong. */ -DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS; +__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS; #ifdef CONFIG_X86_64 static DEFINE_PER_CPU(unsigned char, is_idle); diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index f8adefca71dc..884f98f69354 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -247,7 +247,7 @@ EXPORT_SYMBOL_GPL(start_thread); * the task-switch, and shows up in ret_from_fork in entry.S, * for example. */ -__notrace_funcgraph struct task_struct * +__visible __notrace_funcgraph struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread, diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 05646bab4ca6..bb1dc51bab05 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -52,7 +52,7 @@ asmlinkage extern void ret_from_fork(void); -DEFINE_PER_CPU(unsigned long, old_rsp); +asmlinkage DEFINE_PER_CPU(unsigned long, old_rsp); /* Prints also some state that isn't saved in the pt_regs */ void __show_regs(struct pt_regs *regs, int all) @@ -274,7 +274,7 @@ void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp) * Kprobes not supported here. Set the probe on schedule instead. * Function graph tracer not supported too. */ -__notrace_funcgraph struct task_struct * +__visible __notrace_funcgraph struct task_struct * __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread; diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 2cb9470ea85b..a16bae3f83b3 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -128,46 +128,7 @@ 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 @@ -181,17 +142,12 @@ 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/kernel/setup.c b/arch/x86/kernel/setup.c index f8ec57815c05..f0de6294b955 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -206,9 +206,9 @@ EXPORT_SYMBOL(boot_cpu_data); #if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64) -unsigned long mmu_cr4_features; +__visible unsigned long mmu_cr4_features; #else -unsigned long mmu_cr4_features = X86_CR4_PAE; +__visible unsigned long mmu_cr4_features = X86_CR4_PAE; #endif /* Boot loader ID and version as integers, for the benefit of proc_dointvec */ @@ -426,25 +426,23 @@ static void __init reserve_initrd(void) static void __init parse_setup_data(void) { struct setup_data *data; - u64 pa_data; + u64 pa_data, pa_next; pa_data = boot_params.hdr.setup_data; while (pa_data) { - u32 data_len, map_len; + u32 data_len, map_len, data_type; map_len = max(PAGE_SIZE - (pa_data & ~PAGE_MASK), (u64)sizeof(struct setup_data)); data = early_memremap(pa_data, map_len); data_len = data->len + sizeof(struct setup_data); - if (data_len > map_len) { - early_iounmap(data, map_len); - data = early_memremap(pa_data, data_len); - map_len = data_len; - } + data_type = data->type; + pa_next = data->next; + early_iounmap(data, map_len); - switch (data->type) { + switch (data_type) { case SETUP_E820_EXT: - parse_e820_ext(data); + parse_e820_ext(pa_data, data_len); break; case SETUP_DTB: add_dtb(pa_data); @@ -452,8 +450,7 @@ static void __init parse_setup_data(void) default: break; } - pa_data = data->next; - early_iounmap(data, map_len); + pa_data = pa_next; } } @@ -1070,7 +1067,7 @@ void __init setup_arch(char **cmdline_p) cleanup_highmap(); - memblock.current_limit = ISA_END_ADDRESS; + memblock_set_current_limit(ISA_END_ADDRESS); memblock_x86_fill(); /* @@ -1103,7 +1100,7 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); - memblock.current_limit = get_max_mapped(); + memblock_set_current_limit(get_max_mapped()); dma_contiguous_reserve(0); /* diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index cf913587d4dd..9e5de6813e1f 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -358,7 +358,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __save_altstack(&frame->uc.uc_stack, regs->sp); + save_altstack_ex(&frame->uc.uc_stack, regs->sp); /* Set up to return from userspace. */ restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn); @@ -423,7 +423,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __save_altstack(&frame->uc.uc_stack, regs->sp); + save_altstack_ex(&frame->uc.uc_stack, regs->sp); /* Set up to return from userspace. If provided, use a stub already in userspace. */ @@ -490,7 +490,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig, else put_user_ex(0, &frame->uc.uc_flags); put_user_ex(0, &frame->uc.uc_link); - err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp); + compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp); put_user_ex(0, &frame->uc.uc__pad0); if (ksig->ka.sa.sa_flags & SA_RESTORER) { @@ -533,7 +533,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig, * Do a signal return; undo the signal stack. */ #ifdef CONFIG_X86_32 -unsigned long sys_sigreturn(void) +asmlinkage unsigned long sys_sigreturn(void) { struct pt_regs *regs = current_pt_regs(); struct sigframe __user *frame; @@ -562,7 +562,7 @@ badframe: } #endif /* CONFIG_X86_32 */ -long sys_rt_sigreturn(void) +asmlinkage long sys_rt_sigreturn(void) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe __user *frame; @@ -728,7 +728,7 @@ static void do_signal(struct pt_regs *regs) * notification of userspace execution resumption * - triggered by the TIF_WORK_MASK flags */ -void +__visible void do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags) { user_exit(); diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index cdaa347dfcad..7c3a5a61f2e4 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -256,7 +256,7 @@ static inline void __smp_reschedule_interrupt(void) scheduler_ipi(); } -void smp_reschedule_interrupt(struct pt_regs *regs) +__visible void smp_reschedule_interrupt(struct pt_regs *regs) { ack_APIC_irq(); __smp_reschedule_interrupt(); @@ -271,7 +271,7 @@ static inline void smp_entering_irq(void) irq_enter(); } -void smp_trace_reschedule_interrupt(struct pt_regs *regs) +__visible void smp_trace_reschedule_interrupt(struct pt_regs *regs) { /* * Need to call irq_enter() before calling the trace point. @@ -295,14 +295,14 @@ static inline void __smp_call_function_interrupt(void) inc_irq_stat(irq_call_count); } -void smp_call_function_interrupt(struct pt_regs *regs) +__visible void smp_call_function_interrupt(struct pt_regs *regs) { smp_entering_irq(); __smp_call_function_interrupt(); exiting_irq(); } -void smp_trace_call_function_interrupt(struct pt_regs *regs) +__visible void smp_trace_call_function_interrupt(struct pt_regs *regs) { smp_entering_irq(); trace_call_function_entry(CALL_FUNCTION_VECTOR); @@ -317,14 +317,14 @@ static inline void __smp_call_function_single_interrupt(void) inc_irq_stat(irq_call_count); } -void smp_call_function_single_interrupt(struct pt_regs *regs) +__visible void smp_call_function_single_interrupt(struct pt_regs *regs) { smp_entering_irq(); __smp_call_function_single_interrupt(); exiting_irq(); } -void smp_trace_call_function_single_interrupt(struct pt_regs *regs) +__visible void smp_trace_call_function_single_interrupt(struct pt_regs *regs) { smp_entering_irq(); trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR); diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index 48f8375e4c6b..30277e27431a 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -101,7 +101,7 @@ static void find_start_end(unsigned long flags, unsigned long *begin, *begin = new_begin; } } else { - *begin = mmap_legacy_base(); + *begin = current->mm->mmap_legacy_base; *end = TASK_SIZE; } } diff --git a/arch/x86/kernel/syscall_32.c b/arch/x86/kernel/syscall_32.c index 147fcd4941c4..e9bcd57d8a9e 100644 --- a/arch/x86/kernel/syscall_32.c +++ b/arch/x86/kernel/syscall_32.c @@ -15,7 +15,7 @@ typedef asmlinkage void (*sys_call_ptr_t)(void); extern asmlinkage void sys_ni_syscall(void); -const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { +__visible const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c index 5c7f8c20da74..4ac730b37f0b 100644 --- a/arch/x86/kernel/syscall_64.c +++ b/arch/x86/kernel/syscall_64.c @@ -4,6 +4,7 @@ #include <linux/sys.h> #include <linux/cache.h> #include <asm/asm-offsets.h> +#include <asm/syscall.h> #define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat) @@ -19,11 +20,9 @@ #define __SYSCALL_64(nr, sym, compat) [nr] = sym, -typedef void (*sys_call_ptr_t)(void); - extern void sys_ni_syscall(void); -const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { +asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = { /* * Smells like a compiler bug -- it doesn't work * when the & below is removed. diff --git a/arch/x86/kernel/sysfb.c b/arch/x86/kernel/sysfb.c new file mode 100644 index 000000000000..193ec2ce46c7 --- /dev/null +++ b/arch/x86/kernel/sysfb.c @@ -0,0 +1,74 @@ +/* + * Generic System Framebuffers on x86 + * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.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 + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + */ + +/* + * Simple-Framebuffer support for x86 systems + * Create a platform-device for any available boot framebuffer. The + * simple-framebuffer platform device is already available on DT systems, so + * this module parses the global "screen_info" object and creates a suitable + * platform device compatible with the "simple-framebuffer" DT object. If + * the framebuffer is incompatible, we instead create a legacy + * "vesa-framebuffer", "efi-framebuffer" or "platform-framebuffer" device and + * pass the screen_info as platform_data. This allows legacy drivers + * to pick these devices up without messing with simple-framebuffer drivers. + * The global "screen_info" is still valid at all times. + * + * If CONFIG_X86_SYSFB is not selected, we never register "simple-framebuffer" + * platform devices, but only use legacy framebuffer devices for + * backwards compatibility. + * + * TODO: We set the dev_id field of all platform-devices to 0. This allows + * other x86 OF/DT parsers to create such devices, too. However, they must + * start at offset 1 for this to work. + */ + +#include <linux/err.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/platform_data/simplefb.h> +#include <linux/platform_device.h> +#include <linux/screen_info.h> +#include <asm/sysfb.h> + +static __init int sysfb_init(void) +{ + struct screen_info *si = &screen_info; + struct simplefb_platform_data mode; + struct platform_device *pd; + const char *name; + bool compatible; + int ret; + + sysfb_apply_efi_quirks(); + + /* try to create a simple-framebuffer device */ + compatible = parse_mode(si, &mode); + if (compatible) { + ret = create_simplefb(si, &mode); + if (!ret) + return 0; + } + + /* if the FB is incompatible, create a legacy framebuffer device */ + if (si->orig_video_isVGA == VIDEO_TYPE_EFI) + name = "efi-framebuffer"; + else if (si->orig_video_isVGA == VIDEO_TYPE_VLFB) + name = "vesa-framebuffer"; + else + name = "platform-framebuffer"; + + pd = platform_device_register_resndata(NULL, name, 0, + NULL, 0, si, sizeof(*si)); + return IS_ERR(pd) ? PTR_ERR(pd) : 0; +} + +/* must execute after PCI subsystem for EFI quirks */ +device_initcall(sysfb_init); diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c new file mode 100644 index 000000000000..b285d4e8c68e --- /dev/null +++ b/arch/x86/kernel/sysfb_efi.c @@ -0,0 +1,214 @@ +/* + * Generic System Framebuffers on x86 + * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com> + * + * EFI Quirks Copyright (c) 2006 Edgar Hucek <gimli@dark-green.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 + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + */ + +/* + * EFI Quirks + * Several EFI systems do not correctly advertise their boot framebuffers. + * Hence, we use this static table of known broken machines and fix up the + * information so framebuffer drivers can load corectly. + */ + +#include <linux/dmi.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/pci.h> +#include <linux/screen_info.h> +#include <video/vga.h> +#include <asm/sysfb.h> + +enum { + OVERRIDE_NONE = 0x0, + OVERRIDE_BASE = 0x1, + OVERRIDE_STRIDE = 0x2, + OVERRIDE_HEIGHT = 0x4, + OVERRIDE_WIDTH = 0x8, +}; + +struct efifb_dmi_info efifb_dmi_list[] = { + [M_I17] = { "i17", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE }, + [M_I20] = { "i20", 0x80010000, 1728 * 4, 1680, 1050, OVERRIDE_NONE }, /* guess */ + [M_I20_SR] = { "imac7", 0x40010000, 1728 * 4, 1680, 1050, OVERRIDE_NONE }, + [M_I24] = { "i24", 0x80010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, /* guess */ + [M_I24_8_1] = { "imac8", 0xc0060000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, + [M_I24_10_1] = { "imac10", 0xc0010000, 2048 * 4, 1920, 1080, OVERRIDE_NONE }, + [M_I27_11_1] = { "imac11", 0xc0010000, 2560 * 4, 2560, 1440, OVERRIDE_NONE }, + [M_MINI]= { "mini", 0x80000000, 2048 * 4, 1024, 768, OVERRIDE_NONE }, + [M_MINI_3_1] = { "mini31", 0x40010000, 1024 * 4, 1024, 768, OVERRIDE_NONE }, + [M_MINI_4_1] = { "mini41", 0xc0010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, + [M_MB] = { "macbook", 0x80000000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, + [M_MB_5_1] = { "macbook51", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, + [M_MB_6_1] = { "macbook61", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, + [M_MB_7_1] = { "macbook71", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, + [M_MBA] = { "mba", 0x80000000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, + /* 11" Macbook Air 3,1 passes the wrong stride */ + [M_MBA_3] = { "mba3", 0, 2048 * 4, 0, 0, OVERRIDE_STRIDE }, + [M_MBP] = { "mbp", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE }, + [M_MBP_2] = { "mbp2", 0, 0, 0, 0, OVERRIDE_NONE }, /* placeholder */ + [M_MBP_2_2] = { "mbp22", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE }, + [M_MBP_SR] = { "mbp3", 0x80030000, 2048 * 4, 1440, 900, OVERRIDE_NONE }, + [M_MBP_4] = { "mbp4", 0xc0060000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, + [M_MBP_5_1] = { "mbp51", 0xc0010000, 2048 * 4, 1440, 900, OVERRIDE_NONE }, + [M_MBP_5_2] = { "mbp52", 0xc0010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, + [M_MBP_5_3] = { "mbp53", 0xd0010000, 2048 * 4, 1440, 900, OVERRIDE_NONE }, + [M_MBP_6_1] = { "mbp61", 0x90030000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, + [M_MBP_6_2] = { "mbp62", 0x90030000, 2048 * 4, 1680, 1050, OVERRIDE_NONE }, + [M_MBP_7_1] = { "mbp71", 0xc0010000, 2048 * 4, 1280, 800, OVERRIDE_NONE }, + [M_MBP_8_2] = { "mbp82", 0x90010000, 1472 * 4, 1440, 900, OVERRIDE_NONE }, + [M_UNKNOWN] = { NULL, 0, 0, 0, 0, OVERRIDE_NONE } +}; + +#define choose_value(dmivalue, fwvalue, field, flags) ({ \ + typeof(fwvalue) _ret_ = fwvalue; \ + if ((flags) & (field)) \ + _ret_ = dmivalue; \ + else if ((fwvalue) == 0) \ + _ret_ = dmivalue; \ + _ret_; \ + }) + +static int __init efifb_set_system(const struct dmi_system_id *id) +{ + struct efifb_dmi_info *info = id->driver_data; + + if (info->base == 0 && info->height == 0 && info->width == 0 && + info->stride == 0) + return 0; + + /* Trust the bootloader over the DMI tables */ + if (screen_info.lfb_base == 0) { +#if defined(CONFIG_PCI) + struct pci_dev *dev = NULL; + int found_bar = 0; +#endif + if (info->base) { + screen_info.lfb_base = choose_value(info->base, + screen_info.lfb_base, OVERRIDE_BASE, + info->flags); + +#if defined(CONFIG_PCI) + /* make sure that the address in the table is actually + * on a VGA device's PCI BAR */ + + for_each_pci_dev(dev) { + int i; + if ((dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) + continue; + for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) { + resource_size_t start, end; + + start = pci_resource_start(dev, i); + if (start == 0) + break; + end = pci_resource_end(dev, i); + if (screen_info.lfb_base >= start && + screen_info.lfb_base < end) { + found_bar = 1; + } + } + } + if (!found_bar) + screen_info.lfb_base = 0; +#endif + } + } + if (screen_info.lfb_base) { + screen_info.lfb_linelength = choose_value(info->stride, + screen_info.lfb_linelength, OVERRIDE_STRIDE, + info->flags); + screen_info.lfb_width = choose_value(info->width, + screen_info.lfb_width, OVERRIDE_WIDTH, + info->flags); + screen_info.lfb_height = choose_value(info->height, + screen_info.lfb_height, OVERRIDE_HEIGHT, + info->flags); + if (screen_info.orig_video_isVGA == 0) + screen_info.orig_video_isVGA = VIDEO_TYPE_EFI; + } else { + screen_info.lfb_linelength = 0; + screen_info.lfb_width = 0; + screen_info.lfb_height = 0; + screen_info.orig_video_isVGA = 0; + return 0; + } + + printk(KERN_INFO "efifb: dmi detected %s - framebuffer at 0x%08x " + "(%dx%d, stride %d)\n", id->ident, + screen_info.lfb_base, screen_info.lfb_width, + screen_info.lfb_height, screen_info.lfb_linelength); + + return 1; +} + +#define EFIFB_DMI_SYSTEM_ID(vendor, name, enumid) \ + { \ + efifb_set_system, \ + name, \ + { \ + DMI_MATCH(DMI_BIOS_VENDOR, vendor), \ + DMI_MATCH(DMI_PRODUCT_NAME, name) \ + }, \ + &efifb_dmi_list[enumid] \ + } + +static const struct dmi_system_id efifb_dmi_system_table[] __initconst = { + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac4,1", M_I17), + /* At least one of these two will be right; maybe both? */ + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac5,1", M_I20), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac5,1", M_I20), + /* At least one of these two will be right; maybe both? */ + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac6,1", M_I24), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac6,1", M_I24), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac7,1", M_I20_SR), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac8,1", M_I24_8_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac10,1", M_I24_10_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac11,1", M_I27_11_1), + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "Macmini1,1", M_MINI), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "Macmini3,1", M_MINI_3_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "Macmini4,1", M_MINI_4_1), + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook1,1", M_MB), + /* At least one of these two will be right; maybe both? */ + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook2,1", M_MB), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook2,1", M_MB), + /* At least one of these two will be right; maybe both? */ + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook3,1", M_MB), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook3,1", M_MB), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook4,1", M_MB), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook5,1", M_MB_5_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook6,1", M_MB_6_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook7,1", M_MB_7_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookAir1,1", M_MBA), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookAir3,1", M_MBA_3), + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro1,1", M_MBP), + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro2,1", M_MBP_2), + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro2,2", M_MBP_2_2), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro2,1", M_MBP_2), + EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro3,1", M_MBP_SR), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro3,1", M_MBP_SR), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro4,1", M_MBP_4), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,1", M_MBP_5_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,2", M_MBP_5_2), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,3", M_MBP_5_3), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro6,1", M_MBP_6_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro6,2", M_MBP_6_2), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro7,1", M_MBP_7_1), + EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro8,2", M_MBP_8_2), + {}, +}; + +__init void sysfb_apply_efi_quirks(void) +{ + if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || + !(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS)) + dmi_check_system(efifb_dmi_system_table); +} diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c new file mode 100644 index 000000000000..22513e96b012 --- /dev/null +++ b/arch/x86/kernel/sysfb_simplefb.c @@ -0,0 +1,95 @@ +/* + * Generic System Framebuffers on x86 + * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.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 + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + */ + +/* + * simple-framebuffer probing + * Try to convert "screen_info" into a "simple-framebuffer" compatible mode. + * If the mode is incompatible, we return "false" and let the caller create + * legacy nodes instead. + */ + +#include <linux/err.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/platform_data/simplefb.h> +#include <linux/platform_device.h> +#include <linux/screen_info.h> +#include <asm/sysfb.h> + +static const char simplefb_resname[] = "BOOTFB"; +static const struct simplefb_format formats[] = SIMPLEFB_FORMATS; + +/* try parsing x86 screen_info into a simple-framebuffer mode struct */ +__init bool parse_mode(const struct screen_info *si, + struct simplefb_platform_data *mode) +{ + const struct simplefb_format *f; + __u8 type; + unsigned int i; + + type = si->orig_video_isVGA; + if (type != VIDEO_TYPE_VLFB && type != VIDEO_TYPE_EFI) + return false; + + for (i = 0; i < ARRAY_SIZE(formats); ++i) { + f = &formats[i]; + if (si->lfb_depth == f->bits_per_pixel && + si->red_size == f->red.length && + si->red_pos == f->red.offset && + si->green_size == f->green.length && + si->green_pos == f->green.offset && + si->blue_size == f->blue.length && + si->blue_pos == f->blue.offset && + si->rsvd_size == f->transp.length && + si->rsvd_pos == f->transp.offset) { + mode->format = f->name; + mode->width = si->lfb_width; + mode->height = si->lfb_height; + mode->stride = si->lfb_linelength; + return true; + } + } + + return false; +} + +__init int create_simplefb(const struct screen_info *si, + const struct simplefb_platform_data *mode) +{ + struct platform_device *pd; + struct resource res; + unsigned long len; + + /* don't use lfb_size as it may contain the whole VMEM instead of only + * the part that is occupied by the framebuffer */ + len = mode->height * mode->stride; + len = PAGE_ALIGN(len); + if (len > si->lfb_size << 16) { + printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n"); + return -EINVAL; + } + + /* setup IORESOURCE_MEM as framebuffer memory */ + memset(&res, 0, sizeof(res)); + res.flags = IORESOURCE_MEM; + res.name = simplefb_resname; + res.start = si->lfb_base; + res.end = si->lfb_base + len - 1; + if (res.end <= res.start) + return -EINVAL; + + pd = platform_device_register_resndata(NULL, "simple-framebuffer", 0, + &res, 1, mode, sizeof(*mode)); + if (IS_ERR(pd)) + return PTR_ERR(pd); + + return 0; +} diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index addf7b58f4e8..91a4496db434 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -301,6 +301,15 @@ static int tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control) return 0; } +static int tboot_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b) +{ + if (!tboot_enabled()) + return 0; + + pr_warning("tboot is not able to suspend on platforms with reduced hardware sleep (ACPIv5)"); + return -ENODEV; +} + static atomic_t ap_wfs_count; static int tboot_wait_for_aps(int num_aps) @@ -422,6 +431,7 @@ static __init int tboot_late_init(void) #endif acpi_os_set_prepare_sleep(&tboot_sleep); + acpi_os_set_prepare_extended_sleep(&tboot_extended_sleep); return 0; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 1b23a1c92746..8c8093b146ca 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -58,6 +58,7 @@ #include <asm/mce.h> #include <asm/fixmap.h> #include <asm/mach_traps.h> +#include <asm/alternative.h> #ifdef CONFIG_X86_64 #include <asm/x86_init.h> @@ -327,6 +328,9 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co ftrace_int3_handler(regs)) return; #endif + if (poke_int3_handler(regs)) + return; + prev_state = exception_enter(); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 6ff49247edf8..930e5d48f560 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -89,6 +89,12 @@ int check_tsc_unstable(void) } EXPORT_SYMBOL_GPL(check_tsc_unstable); +int check_tsc_disabled(void) +{ + return tsc_disabled; +} +EXPORT_SYMBOL_GPL(check_tsc_disabled); + #ifdef CONFIG_X86_TSC int __init notsc_setup(char *str) { diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index a20ecb5b6cbf..b110fe6c03d4 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -413,7 +413,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, (1 << KVM_FEATURE_CLOCKSOURCE2) | (1 << KVM_FEATURE_ASYNC_PF) | (1 << KVM_FEATURE_PV_EOI) | - (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT); + (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) | + (1 << KVM_FEATURE_PV_UNHALT); if (sched_info_on()) entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index afc11245827c..5439117d5c4c 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -79,16 +79,6 @@ static inline void apic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val) *((u32 *) (apic->regs + reg_off)) = val; } -static inline int apic_test_and_set_vector(int vec, void *bitmap) -{ - return test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); -} - -static inline int apic_test_and_clear_vector(int vec, void *bitmap) -{ - return test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); -} - static inline int apic_test_vector(int vec, void *bitmap) { return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); @@ -331,10 +321,10 @@ void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir) } EXPORT_SYMBOL_GPL(kvm_apic_update_irr); -static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic) +static inline void apic_set_irr(int vec, struct kvm_lapic *apic) { apic->irr_pending = true; - return apic_test_and_set_vector(vec, apic->regs + APIC_IRR); + apic_set_vector(vec, apic->regs + APIC_IRR); } static inline int apic_search_irr(struct kvm_lapic *apic) @@ -681,32 +671,28 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, if (unlikely(!apic_enabled(apic))) break; + result = 1; + if (dest_map) __set_bit(vcpu->vcpu_id, dest_map); - if (kvm_x86_ops->deliver_posted_interrupt) { - result = 1; + if (kvm_x86_ops->deliver_posted_interrupt) kvm_x86_ops->deliver_posted_interrupt(vcpu, vector); - } else { - result = !apic_test_and_set_irr(vector, apic); - - if (!result) { - if (trig_mode) - apic_debug("level trig mode repeatedly " - "for vector %d", vector); - goto out; - } + else { + apic_set_irr(vector, apic); kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } -out: trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode, - trig_mode, vector, !result); + trig_mode, vector, false); break; case APIC_DM_REMRD: - apic_debug("Ignoring delivery mode 3\n"); + result = 1; + vcpu->arch.pv.pv_unhalted = 1; + kvm_make_request(KVM_REQ_EVENT, vcpu); + kvm_vcpu_kick(vcpu); break; case APIC_DM_SMI: diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 9e9285ae9b94..6e2d2c8f230b 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -132,8 +132,8 @@ module_param(dbg, bool, 0644); (PAGE_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \ * PT32_LEVEL_BITS))) - 1)) -#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK \ - | PT64_NX_MASK) +#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \ + | shadow_x_mask | shadow_nx_mask) #define ACC_EXEC_MASK 1 #define ACC_WRITE_MASK PT_WRITABLE_MASK @@ -331,11 +331,6 @@ static int is_large_pte(u64 pte) return pte & PT_PAGE_SIZE_MASK; } -static int is_dirty_gpte(unsigned long pte) -{ - return pte & PT_DIRTY_MASK; -} - static int is_rmap_spte(u64 pte) { return is_shadow_present_pte(pte); @@ -2052,12 +2047,18 @@ static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator) return __shadow_walk_next(iterator, *iterator->sptep); } -static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp) +static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp, bool accessed) { u64 spte; + BUILD_BUG_ON(VMX_EPT_READABLE_MASK != PT_PRESENT_MASK || + VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK); + spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK | - shadow_user_mask | shadow_x_mask | shadow_accessed_mask; + shadow_user_mask | shadow_x_mask; + + if (accessed) + spte |= shadow_accessed_mask; mmu_spte_set(sptep, spte); } @@ -2574,14 +2575,6 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) mmu_free_roots(vcpu); } -static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level) -{ - int bit7; - - bit7 = (gpte >> 7) & 1; - return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) != 0; -} - static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, bool no_dirty_log) { @@ -2594,26 +2587,6 @@ static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, return gfn_to_pfn_memslot_atomic(slot, gfn); } -static bool prefetch_invalid_gpte(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp, u64 *spte, - u64 gpte) -{ - if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) - goto no_present; - - if (!is_present_gpte(gpte)) - goto no_present; - - if (!(gpte & PT_ACCESSED_MASK)) - goto no_present; - - return false; - -no_present: - drop_spte(vcpu->kvm, spte); - return true; -} - static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *start, u64 *end) @@ -2710,7 +2683,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, iterator.level - 1, 1, ACC_ALL, iterator.sptep); - link_shadow_page(iterator.sptep, sp); + link_shadow_page(iterator.sptep, sp, true); } } return emulate; @@ -2808,7 +2781,7 @@ exit: return ret; } -static bool page_fault_can_be_fast(struct kvm_vcpu *vcpu, u32 error_code) +static bool page_fault_can_be_fast(u32 error_code) { /* * Do not fix the mmio spte with invalid generation number which @@ -2861,7 +2834,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, bool ret = false; u64 spte = 0ull; - if (!page_fault_can_be_fast(vcpu, error_code)) + if (!page_fault_can_be_fast(error_code)) return false; walk_shadow_page_lockless_begin(vcpu); @@ -3209,6 +3182,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) mmu_sync_roots(vcpu); spin_unlock(&vcpu->kvm->mmu_lock); } +EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots); static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, struct x86_exception *exception) @@ -3478,6 +3452,7 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu) ++vcpu->stat.tlb_flush; kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } +EXPORT_SYMBOL_GPL(kvm_mmu_flush_tlb); static void paging_new_cr3(struct kvm_vcpu *vcpu) { @@ -3501,18 +3476,6 @@ static void paging_free(struct kvm_vcpu *vcpu) nonpaging_free(vcpu); } -static inline void protect_clean_gpte(unsigned *access, unsigned gpte) -{ - unsigned mask; - - BUILD_BUG_ON(PT_WRITABLE_MASK != ACC_WRITE_MASK); - - mask = (unsigned)~ACC_WRITE_MASK; - /* Allow write access to dirty gptes */ - mask |= (gpte >> (PT_DIRTY_SHIFT - PT_WRITABLE_SHIFT)) & PT_WRITABLE_MASK; - *access &= mask; -} - static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, unsigned access, int *nr_present) { @@ -3530,16 +3493,6 @@ static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn, return false; } -static inline unsigned gpte_access(struct kvm_vcpu *vcpu, u64 gpte) -{ - unsigned access; - - access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK; - access &= ~(gpte >> PT64_NX_SHIFT); - - return access; -} - static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gpte) { unsigned index; @@ -3549,6 +3502,11 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gp return mmu->last_pte_bitmap & (1 << index); } +#define PTTYPE_EPT 18 /* arbitrary */ +#define PTTYPE PTTYPE_EPT +#include "paging_tmpl.h" +#undef PTTYPE + #define PTTYPE 64 #include "paging_tmpl.h" #undef PTTYPE @@ -3563,6 +3521,8 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, int maxphyaddr = cpuid_maxphyaddr(vcpu); u64 exb_bit_rsvd = 0; + context->bad_mt_xwr = 0; + if (!context->nx) exb_bit_rsvd = rsvd_bits(63, 63); switch (context->root_level) { @@ -3618,7 +3578,40 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, } } -static void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) +static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, + struct kvm_mmu *context, bool execonly) +{ + int maxphyaddr = cpuid_maxphyaddr(vcpu); + int pte; + + context->rsvd_bits_mask[0][3] = + rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7); + context->rsvd_bits_mask[0][2] = + rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6); + context->rsvd_bits_mask[0][1] = + rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6); + context->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51); + + /* large page */ + context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3]; + context->rsvd_bits_mask[1][2] = + rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29); + context->rsvd_bits_mask[1][1] = + rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20); + context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0]; + + for (pte = 0; pte < 64; pte++) { + int rwx_bits = pte & 7; + int mt = pte >> 3; + if (mt == 0x2 || mt == 0x3 || mt == 0x7 || + rwx_bits == 0x2 || rwx_bits == 0x6 || + (rwx_bits == 0x4 && !execonly)) + context->bad_mt_xwr |= (1ull << pte); + } +} + +static void update_permission_bitmask(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu, bool ept) { unsigned bit, byte, pfec; u8 map; @@ -3636,12 +3629,16 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu w = bit & ACC_WRITE_MASK; u = bit & ACC_USER_MASK; - /* Not really needed: !nx will cause pte.nx to fault */ - x |= !mmu->nx; - /* Allow supervisor writes if !cr0.wp */ - w |= !is_write_protection(vcpu) && !uf; - /* Disallow supervisor fetches of user code if cr4.smep */ - x &= !(smep && u && !uf); + if (!ept) { + /* Not really needed: !nx will cause pte.nx to fault */ + x |= !mmu->nx; + /* Allow supervisor writes if !cr0.wp */ + w |= !is_write_protection(vcpu) && !uf; + /* Disallow supervisor fetches of user code if cr4.smep */ + x &= !(smep && u && !uf); + } else + /* Not really needed: no U/S accesses on ept */ + u = 1; fault = (ff && !x) || (uf && !u) || (wf && !w); map |= fault << bit; @@ -3676,7 +3673,7 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu, context->root_level = level; reset_rsvds_bits_mask(vcpu, context); - update_permission_bitmask(vcpu, context); + update_permission_bitmask(vcpu, context, false); update_last_pte_bitmap(vcpu, context); ASSERT(is_pae(vcpu)); @@ -3706,7 +3703,7 @@ static int paging32_init_context(struct kvm_vcpu *vcpu, context->root_level = PT32_ROOT_LEVEL; reset_rsvds_bits_mask(vcpu, context); - update_permission_bitmask(vcpu, context); + update_permission_bitmask(vcpu, context, false); update_last_pte_bitmap(vcpu, context); context->new_cr3 = paging_new_cr3; @@ -3768,7 +3765,7 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->gva_to_gpa = paging32_gva_to_gpa; } - update_permission_bitmask(vcpu, context); + update_permission_bitmask(vcpu, context, false); update_last_pte_bitmap(vcpu, context); return 0; @@ -3800,6 +3797,33 @@ int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context) } EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu); +int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context, + bool execonly) +{ + ASSERT(vcpu); + ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); + + context->shadow_root_level = kvm_x86_ops->get_tdp_level(); + + context->nx = true; + context->new_cr3 = paging_new_cr3; + context->page_fault = ept_page_fault; + context->gva_to_gpa = ept_gva_to_gpa; + context->sync_page = ept_sync_page; + context->invlpg = ept_invlpg; + context->update_pte = ept_update_pte; + context->free = paging_free; + context->root_level = context->shadow_root_level; + context->root_hpa = INVALID_PAGE; + context->direct_map = false; + + update_permission_bitmask(vcpu, context, true); + reset_rsvds_bits_mask_ept(vcpu, context, execonly); + + return 0; +} +EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu); + static int init_kvm_softmmu(struct kvm_vcpu *vcpu) { int r = kvm_init_shadow_mmu(vcpu, vcpu->arch.walk_mmu); @@ -3847,7 +3871,7 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu) g_context->gva_to_gpa = paging32_gva_to_gpa_nested; } - update_permission_bitmask(vcpu, g_context); + update_permission_bitmask(vcpu, g_context, false); update_last_pte_bitmap(vcpu, g_context); return 0; @@ -3923,8 +3947,8 @@ static bool need_remote_flush(u64 old, u64 new) return true; if ((old ^ new) & PT64_BASE_ADDR_MASK) return true; - old ^= PT64_NX_MASK; - new ^= PT64_NX_MASK; + old ^= shadow_nx_mask; + new ^= shadow_nx_mask; return (old & ~new & PT64_PERM_MASK) != 0; } @@ -4182,7 +4206,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code, switch (er) { case EMULATE_DONE: return 1; - case EMULATE_DO_MMIO: + case EMULATE_USER_EXIT: ++vcpu->stat.mmio_exits; /* fall through */ case EMULATE_FAIL: @@ -4390,11 +4414,8 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm) /* * The very rare case: if the generation-number is round, * zap all shadow pages. - * - * The max value is MMIO_MAX_GEN - 1 since it is not called - * when mark memslot invalid. */ - if (unlikely(kvm_current_mmio_generation(kvm) >= (MMIO_MAX_GEN - 1))) { + if (unlikely(kvm_current_mmio_generation(kvm) >= MMIO_MAX_GEN)) { printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n"); kvm_mmu_invalidate_zap_all_pages(kvm); } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 5b59c573aba7..77e044a0f5f7 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -71,6 +71,8 @@ enum { int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct); int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context); +int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context, + bool execonly); static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm) { diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 7769699d48a8..043330159179 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -23,6 +23,13 @@ * so the code in this file is compiled twice, once per pte size. */ +/* + * This is used to catch non optimized PT_GUEST_(DIRTY|ACCESS)_SHIFT macro + * uses for EPT without A/D paging type. + */ +extern u64 __pure __using_nonexistent_pte_bit(void) + __compiletime_error("wrong use of PT_GUEST_(DIRTY|ACCESS)_SHIFT"); + #if PTTYPE == 64 #define pt_element_t u64 #define guest_walker guest_walker64 @@ -32,6 +39,10 @@ #define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl) #define PT_INDEX(addr, level) PT64_INDEX(addr, level) #define PT_LEVEL_BITS PT64_LEVEL_BITS + #define PT_GUEST_ACCESSED_MASK PT_ACCESSED_MASK + #define PT_GUEST_DIRTY_MASK PT_DIRTY_MASK + #define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT + #define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT #ifdef CONFIG_X86_64 #define PT_MAX_FULL_LEVELS 4 #define CMPXCHG cmpxchg @@ -49,7 +60,26 @@ #define PT_INDEX(addr, level) PT32_INDEX(addr, level) #define PT_LEVEL_BITS PT32_LEVEL_BITS #define PT_MAX_FULL_LEVELS 2 + #define PT_GUEST_ACCESSED_MASK PT_ACCESSED_MASK + #define PT_GUEST_DIRTY_MASK PT_DIRTY_MASK + #define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT + #define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT #define CMPXCHG cmpxchg +#elif PTTYPE == PTTYPE_EPT + #define pt_element_t u64 + #define guest_walker guest_walkerEPT + #define FNAME(name) ept_##name + #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK + #define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl) + #define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl) + #define PT_INDEX(addr, level) PT64_INDEX(addr, level) + #define PT_LEVEL_BITS PT64_LEVEL_BITS + #define PT_GUEST_ACCESSED_MASK 0 + #define PT_GUEST_DIRTY_MASK 0 + #define PT_GUEST_DIRTY_SHIFT __using_nonexistent_pte_bit() + #define PT_GUEST_ACCESSED_SHIFT __using_nonexistent_pte_bit() + #define CMPXCHG cmpxchg64 + #define PT_MAX_FULL_LEVELS 4 #else #error Invalid PTTYPE value #endif @@ -80,6 +110,40 @@ static gfn_t gpte_to_gfn_lvl(pt_element_t gpte, int lvl) return (gpte & PT_LVL_ADDR_MASK(lvl)) >> PAGE_SHIFT; } +static inline void FNAME(protect_clean_gpte)(unsigned *access, unsigned gpte) +{ + unsigned mask; + + /* dirty bit is not supported, so no need to track it */ + if (!PT_GUEST_DIRTY_MASK) + return; + + BUILD_BUG_ON(PT_WRITABLE_MASK != ACC_WRITE_MASK); + + mask = (unsigned)~ACC_WRITE_MASK; + /* Allow write access to dirty gptes */ + mask |= (gpte >> (PT_GUEST_DIRTY_SHIFT - PT_WRITABLE_SHIFT)) & + PT_WRITABLE_MASK; + *access &= mask; +} + +static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level) +{ + int bit7 = (gpte >> 7) & 1, low6 = gpte & 0x3f; + + return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) | + ((mmu->bad_mt_xwr & (1ull << low6)) != 0); +} + +static inline int FNAME(is_present_gpte)(unsigned long pte) +{ +#if PTTYPE != PTTYPE_EPT + return is_present_gpte(pte); +#else + return pte & 7; +#endif +} + static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, pt_element_t __user *ptep_user, unsigned index, pt_element_t orig_pte, pt_element_t new_pte) @@ -103,6 +167,42 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, return (ret != orig_pte); } +static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp, u64 *spte, + u64 gpte) +{ + if (FNAME(is_rsvd_bits_set)(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL)) + goto no_present; + + if (!FNAME(is_present_gpte)(gpte)) + goto no_present; + + /* if accessed bit is not supported prefetch non accessed gpte */ + if (PT_GUEST_ACCESSED_MASK && !(gpte & PT_GUEST_ACCESSED_MASK)) + goto no_present; + + return false; + +no_present: + drop_spte(vcpu->kvm, spte); + return true; +} + +static inline unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, u64 gpte) +{ + unsigned access; +#if PTTYPE == PTTYPE_EPT + access = ((gpte & VMX_EPT_WRITABLE_MASK) ? ACC_WRITE_MASK : 0) | + ((gpte & VMX_EPT_EXECUTABLE_MASK) ? ACC_EXEC_MASK : 0) | + ACC_USER_MASK; +#else + access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK; + access &= ~(gpte >> PT64_NX_SHIFT); +#endif + + return access; +} + static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, struct guest_walker *walker, @@ -114,18 +214,23 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, gfn_t table_gfn; int ret; + /* dirty/accessed bits are not supported, so no need to update them */ + if (!PT_GUEST_DIRTY_MASK) + return 0; + for (level = walker->max_level; level >= walker->level; --level) { pte = orig_pte = walker->ptes[level - 1]; table_gfn = walker->table_gfn[level - 1]; ptep_user = walker->ptep_user[level - 1]; index = offset_in_page(ptep_user) / sizeof(pt_element_t); - if (!(pte & PT_ACCESSED_MASK)) { + if (!(pte & PT_GUEST_ACCESSED_MASK)) { trace_kvm_mmu_set_accessed_bit(table_gfn, index, sizeof(pte)); - pte |= PT_ACCESSED_MASK; + pte |= PT_GUEST_ACCESSED_MASK; } - if (level == walker->level && write_fault && !is_dirty_gpte(pte)) { + if (level == walker->level && write_fault && + !(pte & PT_GUEST_DIRTY_MASK)) { trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte)); - pte |= PT_DIRTY_MASK; + pte |= PT_GUEST_DIRTY_MASK; } if (pte == orig_pte) continue; @@ -170,7 +275,7 @@ retry_walk: if (walker->level == PT32E_ROOT_LEVEL) { pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3); trace_kvm_mmu_paging_element(pte, walker->level); - if (!is_present_gpte(pte)) + if (!FNAME(is_present_gpte)(pte)) goto error; --walker->level; } @@ -179,7 +284,7 @@ retry_walk: ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) || (mmu->get_cr3(vcpu) & CR3_NONPAE_RESERVED_BITS) == 0); - accessed_dirty = PT_ACCESSED_MASK; + accessed_dirty = PT_GUEST_ACCESSED_MASK; pt_access = pte_access = ACC_ALL; ++walker->level; @@ -215,17 +320,17 @@ retry_walk: trace_kvm_mmu_paging_element(pte, walker->level); - if (unlikely(!is_present_gpte(pte))) + if (unlikely(!FNAME(is_present_gpte)(pte))) goto error; - if (unlikely(is_rsvd_bits_set(&vcpu->arch.mmu, pte, - walker->level))) { + if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte, + walker->level))) { errcode |= PFERR_RSVD_MASK | PFERR_PRESENT_MASK; goto error; } accessed_dirty &= pte; - pte_access = pt_access & gpte_access(vcpu, pte); + pte_access = pt_access & FNAME(gpte_access)(vcpu, pte); walker->ptes[walker->level - 1] = pte; } while (!is_last_gpte(mmu, walker->level, pte)); @@ -248,13 +353,15 @@ retry_walk: walker->gfn = real_gpa >> PAGE_SHIFT; if (!write_fault) - protect_clean_gpte(&pte_access, pte); + FNAME(protect_clean_gpte)(&pte_access, pte); else /* - * On a write fault, fold the dirty bit into accessed_dirty by - * shifting it one place right. + * On a write fault, fold the dirty bit into accessed_dirty. + * For modes without A/D bits support accessed_dirty will be + * always clear. */ - accessed_dirty &= pte >> (PT_DIRTY_SHIFT - PT_ACCESSED_SHIFT); + accessed_dirty &= pte >> + (PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT); if (unlikely(!accessed_dirty)) { ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault); @@ -279,6 +386,25 @@ error: walker->fault.vector = PF_VECTOR; walker->fault.error_code_valid = true; walker->fault.error_code = errcode; + +#if PTTYPE == PTTYPE_EPT + /* + * Use PFERR_RSVD_MASK in error_code to to tell if EPT + * misconfiguration requires to be injected. The detection is + * done by is_rsvd_bits_set() above. + * + * We set up the value of exit_qualification to inject: + * [2:0] - Derive from [2:0] of real exit_qualification at EPT violation + * [5:3] - Calculated by the page walk of the guest EPT page tables + * [7:8] - Derived from [7:8] of real exit_qualification + * + * The other bits are set to 0. + */ + if (!(errcode & PFERR_RSVD_MASK)) { + vcpu->arch.exit_qualification &= 0x187; + vcpu->arch.exit_qualification |= ((pt_access & pte) & 0x7) << 3; + } +#endif walker->fault.address = addr; walker->fault.nested_page_fault = mmu != vcpu->arch.walk_mmu; @@ -293,6 +419,7 @@ static int FNAME(walk_addr)(struct guest_walker *walker, access); } +#if PTTYPE != PTTYPE_EPT static int FNAME(walk_addr_nested)(struct guest_walker *walker, struct kvm_vcpu *vcpu, gva_t addr, u32 access) @@ -300,6 +427,7 @@ static int FNAME(walk_addr_nested)(struct guest_walker *walker, return FNAME(walk_addr_generic)(walker, vcpu, &vcpu->arch.nested_mmu, addr, access); } +#endif static bool FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, @@ -309,14 +437,14 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, gfn_t gfn; pfn_t pfn; - if (prefetch_invalid_gpte(vcpu, sp, spte, gpte)) + if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte)) return false; pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte); gfn = gpte_to_gfn(gpte); - pte_access = sp->role.access & gpte_access(vcpu, gpte); - protect_clean_gpte(&pte_access, gpte); + pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte); + FNAME(protect_clean_gpte)(&pte_access, gpte); pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn, no_dirty_log && (pte_access & ACC_WRITE_MASK)); if (is_error_pfn(pfn)) @@ -446,7 +574,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, goto out_gpte_changed; if (sp) - link_shadow_page(it.sptep, sp); + link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK); } for (; @@ -466,7 +594,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1, true, direct_access, it.sptep); - link_shadow_page(it.sptep, sp); + link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK); } clear_sp_write_flooding_count(it.sptep); @@ -727,6 +855,7 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, return gpa; } +#if PTTYPE != PTTYPE_EPT static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, struct x86_exception *exception) @@ -745,6 +874,7 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, return gpa; } +#endif /* * Using the cached information from sp->gfns is safe because: @@ -785,15 +915,15 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) sizeof(pt_element_t))) return -EINVAL; - if (prefetch_invalid_gpte(vcpu, sp, &sp->spt[i], gpte)) { + if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) { vcpu->kvm->tlbs_dirty++; continue; } gfn = gpte_to_gfn(gpte); pte_access = sp->role.access; - pte_access &= gpte_access(vcpu, gpte); - protect_clean_gpte(&pte_access, gpte); + pte_access &= FNAME(gpte_access)(vcpu, gpte); + FNAME(protect_clean_gpte)(&pte_access, gpte); if (sync_mmio_spte(vcpu->kvm, &sp->spt[i], gfn, pte_access, &nr_present)) @@ -830,3 +960,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) #undef gpte_to_gfn #undef gpte_to_gfn_lvl #undef CMPXCHG +#undef PT_GUEST_ACCESSED_MASK +#undef PT_GUEST_DIRTY_MASK +#undef PT_GUEST_DIRTY_SHIFT +#undef PT_GUEST_ACCESSED_SHIFT diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index c53e797e7369..5c4f63151b4d 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -160,7 +160,7 @@ static void stop_counter(struct kvm_pmc *pmc) static void reprogram_counter(struct kvm_pmc *pmc, u32 type, unsigned config, bool exclude_user, bool exclude_kernel, - bool intr) + bool intr, bool in_tx, bool in_tx_cp) { struct perf_event *event; struct perf_event_attr attr = { @@ -173,6 +173,10 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type, .exclude_kernel = exclude_kernel, .config = config, }; + if (in_tx) + attr.config |= HSW_IN_TX; + if (in_tx_cp) + attr.config |= HSW_IN_TX_CHECKPOINTED; attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc); @@ -226,7 +230,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE | ARCH_PERFMON_EVENTSEL_INV | - ARCH_PERFMON_EVENTSEL_CMASK))) { + ARCH_PERFMON_EVENTSEL_CMASK | + HSW_IN_TX | + HSW_IN_TX_CHECKPOINTED))) { config = find_arch_event(&pmc->vcpu->arch.pmu, event_select, unit_mask); if (config != PERF_COUNT_HW_MAX) @@ -239,7 +245,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) reprogram_counter(pmc, type, config, !(eventsel & ARCH_PERFMON_EVENTSEL_USR), !(eventsel & ARCH_PERFMON_EVENTSEL_OS), - eventsel & ARCH_PERFMON_EVENTSEL_INT); + eventsel & ARCH_PERFMON_EVENTSEL_INT, + (eventsel & HSW_IN_TX), + (eventsel & HSW_IN_TX_CHECKPOINTED)); } static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx) @@ -256,7 +264,7 @@ static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx) arch_events[fixed_pmc_events[idx]].event_type, !(en & 0x2), /* exclude user */ !(en & 0x1), /* exclude kernel */ - pmi); + pmi, false, false); } static inline u8 fixed_en_pmi(u64 ctrl, int idx) @@ -408,7 +416,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) { if (data == pmc->eventsel) return 0; - if (!(data & 0xffffffff00200000ull)) { + if (!(data & pmu->reserved_bits)) { reprogram_gp_counter(pmc, data); return 0; } @@ -450,6 +458,7 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu) pmu->counter_bitmask[KVM_PMC_GP] = 0; pmu->counter_bitmask[KVM_PMC_FIXED] = 0; pmu->version = 0; + pmu->reserved_bits = 0xffffffff00200000ull; entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); if (!entry) @@ -478,6 +487,12 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu) pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) | (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED); pmu->global_ctrl_mask = ~pmu->global_ctrl; + + entry = kvm_find_cpuid_entry(vcpu, 7, 0); + if (entry && + (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) && + (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) + pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED; } void kvm_pmu_init(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 064d0be67ecc..1f1da43ff2a2 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -373,6 +373,7 @@ struct nested_vmx { * we must keep them pinned while L2 runs. */ struct page *apic_access_page; + u64 msr_ia32_feature_control; }; #define POSTED_INTR_ON 0 @@ -711,10 +712,10 @@ static void nested_release_page_clean(struct page *page) kvm_release_page_clean(page); } +static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu); static u64 construct_eptp(unsigned long root_hpa); static void kvm_cpu_vmxon(u64 addr); static void kvm_cpu_vmxoff(void); -static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); static void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); @@ -1039,12 +1040,16 @@ static inline bool nested_cpu_has2(struct vmcs12 *vmcs12, u32 bit) (vmcs12->secondary_vm_exec_control & bit); } -static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12, - struct kvm_vcpu *vcpu) +static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12) { return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS; } +static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12) +{ + return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT); +} + static inline bool is_exception(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) @@ -2155,6 +2160,7 @@ static u32 nested_vmx_pinbased_ctls_low, nested_vmx_pinbased_ctls_high; static u32 nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high; static u32 nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high; static u32 nested_vmx_misc_low, nested_vmx_misc_high; +static u32 nested_vmx_ept_caps; static __init void nested_vmx_setup_ctls_msrs(void) { /* @@ -2190,14 +2196,17 @@ static __init void nested_vmx_setup_ctls_msrs(void) * If bit 55 of VMX_BASIC is off, bits 0-8 and 10, 11, 13, 14, 16 and * 17 must be 1. */ + rdmsr(MSR_IA32_VMX_EXIT_CTLS, + nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high); nested_vmx_exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; /* Note that guest use of VM_EXIT_ACK_INTR_ON_EXIT is not supported. */ + nested_vmx_exit_ctls_high &= #ifdef CONFIG_X86_64 - nested_vmx_exit_ctls_high = VM_EXIT_HOST_ADDR_SPACE_SIZE; -#else - nested_vmx_exit_ctls_high = 0; + VM_EXIT_HOST_ADDR_SPACE_SIZE | #endif - nested_vmx_exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; + VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT; + nested_vmx_exit_ctls_high |= (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | + VM_EXIT_LOAD_IA32_EFER); /* entry controls */ rdmsr(MSR_IA32_VMX_ENTRY_CTLS, @@ -2205,8 +2214,12 @@ static __init void nested_vmx_setup_ctls_msrs(void) /* If bit 55 of VMX_BASIC is off, bits 0-8 and 12 must be 1. */ nested_vmx_entry_ctls_low = VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR; nested_vmx_entry_ctls_high &= - VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_IA32E_MODE; - nested_vmx_entry_ctls_high |= VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR; +#ifdef CONFIG_X86_64 + VM_ENTRY_IA32E_MODE | +#endif + VM_ENTRY_LOAD_IA32_PAT; + nested_vmx_entry_ctls_high |= (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | + VM_ENTRY_LOAD_IA32_EFER); /* cpu-based controls */ rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, @@ -2241,6 +2254,22 @@ static __init void nested_vmx_setup_ctls_msrs(void) SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | SECONDARY_EXEC_WBINVD_EXITING; + if (enable_ept) { + /* nested EPT: emulate EPT also to L1 */ + nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT; + nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT | + VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT; + nested_vmx_ept_caps &= vmx_capability.ept; + /* + * Since invept is completely emulated we support both global + * and context invalidation independent of what host cpu + * supports + */ + nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT | + VMX_EPT_EXTENT_CONTEXT_BIT; + } else + nested_vmx_ept_caps = 0; + /* miscellaneous data */ rdmsr(MSR_IA32_VMX_MISC, nested_vmx_misc_low, nested_vmx_misc_high); nested_vmx_misc_low &= VMX_MISC_PREEMPTION_TIMER_RATE_MASK | @@ -2282,8 +2311,11 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) switch (msr_index) { case MSR_IA32_FEATURE_CONTROL: - *pdata = 0; - break; + if (nested_vmx_allowed(vcpu)) { + *pdata = to_vmx(vcpu)->nested.msr_ia32_feature_control; + break; + } + return 0; case MSR_IA32_VMX_BASIC: /* * This MSR reports some information about VMX support. We @@ -2346,8 +2378,8 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) nested_vmx_secondary_ctls_high); break; case MSR_IA32_VMX_EPT_VPID_CAP: - /* Currently, no nested ept or nested vpid */ - *pdata = 0; + /* Currently, no nested vpid support */ + *pdata = nested_vmx_ept_caps; break; default: return 0; @@ -2356,14 +2388,24 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) return 1; } -static int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) +static int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { + u32 msr_index = msr_info->index; + u64 data = msr_info->data; + bool host_initialized = msr_info->host_initiated; + if (!nested_vmx_allowed(vcpu)) return 0; - if (msr_index == MSR_IA32_FEATURE_CONTROL) - /* TODO: the right thing. */ + if (msr_index == MSR_IA32_FEATURE_CONTROL) { + if (!host_initialized && + to_vmx(vcpu)->nested.msr_ia32_feature_control + & FEATURE_CONTROL_LOCKED) + return 0; + to_vmx(vcpu)->nested.msr_ia32_feature_control = data; return 1; + } + /* * No need to treat VMX capability MSRs specially: If we don't handle * them, handle_wrmsr will #GP(0), which is correct (they are readonly) @@ -2494,7 +2536,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; /* Otherwise falls through */ default: - if (vmx_set_vmx_msr(vcpu, msr_index, data)) + if (vmx_set_vmx_msr(vcpu, msr_info)) break; msr = find_msr_entry(vmx, msr_index); if (msr) { @@ -5302,9 +5344,13 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) /* It is a write fault? */ error_code = exit_qualification & (1U << 1); + /* It is a fetch fault? */ + error_code |= (exit_qualification & (1U << 2)) << 2; /* ept page table is present? */ error_code |= (exit_qualification >> 3) & 0x1; + vcpu->arch.exit_qualification = exit_qualification; + return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); } @@ -5438,7 +5484,8 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE); - if (err == EMULATE_DO_MMIO) { + if (err == EMULATE_USER_EXIT) { + ++vcpu->stat.mmio_exits; ret = 0; goto out; } @@ -5567,8 +5614,47 @@ static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx) free_loaded_vmcs(&vmx->vmcs01); } +/* + * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(), + * set the success or error code of an emulated VMX instruction, as specified + * by Vol 2B, VMX Instruction Reference, "Conventions". + */ +static void nested_vmx_succeed(struct kvm_vcpu *vcpu) +{ + vmx_set_rflags(vcpu, vmx_get_rflags(vcpu) + & ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | + X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF)); +} + +static void nested_vmx_failInvalid(struct kvm_vcpu *vcpu) +{ + vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu) + & ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF | + X86_EFLAGS_SF | X86_EFLAGS_OF)) + | X86_EFLAGS_CF); +} + static void nested_vmx_failValid(struct kvm_vcpu *vcpu, - u32 vm_instruction_error); + u32 vm_instruction_error) +{ + if (to_vmx(vcpu)->nested.current_vmptr == -1ull) { + /* + * failValid writes the error number to the current VMCS, which + * can't be done there isn't a current VMCS. + */ + nested_vmx_failInvalid(vcpu); + return; + } + vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu) + & ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | + X86_EFLAGS_SF | X86_EFLAGS_OF)) + | X86_EFLAGS_ZF); + get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error; + /* + * We don't need to force a shadow sync because + * VM_INSTRUCTION_ERROR is not shadowed + */ +} /* * Emulate the VMXON instruction. @@ -5583,6 +5669,8 @@ static int handle_vmon(struct kvm_vcpu *vcpu) struct kvm_segment cs; struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs *shadow_vmcs; + const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED + | FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX; /* The Intel VMX Instruction Reference lists a bunch of bits that * are prerequisite to running VMXON, most notably cr4.VMXE must be @@ -5611,6 +5699,13 @@ static int handle_vmon(struct kvm_vcpu *vcpu) skip_emulated_instruction(vcpu); return 1; } + + if ((vmx->nested.msr_ia32_feature_control & VMXON_NEEDED_FEATURES) + != VMXON_NEEDED_FEATURES) { + kvm_inject_gp(vcpu, 0); + return 1; + } + if (enable_shadow_vmcs) { shadow_vmcs = alloc_vmcs(); if (!shadow_vmcs) @@ -5628,6 +5723,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu) vmx->nested.vmxon = true; skip_emulated_instruction(vcpu); + nested_vmx_succeed(vcpu); return 1; } @@ -5712,6 +5808,7 @@ static int handle_vmoff(struct kvm_vcpu *vcpu) return 1; free_nested(to_vmx(vcpu)); skip_emulated_instruction(vcpu); + nested_vmx_succeed(vcpu); return 1; } @@ -5768,48 +5865,6 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, return 0; } -/* - * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(), - * set the success or error code of an emulated VMX instruction, as specified - * by Vol 2B, VMX Instruction Reference, "Conventions". - */ -static void nested_vmx_succeed(struct kvm_vcpu *vcpu) -{ - vmx_set_rflags(vcpu, vmx_get_rflags(vcpu) - & ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | - X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF)); -} - -static void nested_vmx_failInvalid(struct kvm_vcpu *vcpu) -{ - vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu) - & ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF | - X86_EFLAGS_SF | X86_EFLAGS_OF)) - | X86_EFLAGS_CF); -} - -static void nested_vmx_failValid(struct kvm_vcpu *vcpu, - u32 vm_instruction_error) -{ - if (to_vmx(vcpu)->nested.current_vmptr == -1ull) { - /* - * failValid writes the error number to the current VMCS, which - * can't be done there isn't a current VMCS. - */ - nested_vmx_failInvalid(vcpu); - return; - } - vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu) - & ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF | - X86_EFLAGS_SF | X86_EFLAGS_OF)) - | X86_EFLAGS_ZF); - get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error; - /* - * We don't need to force a shadow sync because - * VM_INSTRUCTION_ERROR is not shadowed - */ -} - /* Emulate the VMCLEAR instruction */ static int handle_vmclear(struct kvm_vcpu *vcpu) { @@ -5972,8 +6027,8 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx) unsigned long field; u64 field_value; struct vmcs *shadow_vmcs = vmx->nested.current_shadow_vmcs; - unsigned long *fields = (unsigned long *)shadow_read_write_fields; - int num_fields = max_shadow_read_write_fields; + const unsigned long *fields = shadow_read_write_fields; + const int num_fields = max_shadow_read_write_fields; vmcs_load(shadow_vmcs); @@ -6002,12 +6057,11 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx) static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) { - unsigned long *fields[] = { - (unsigned long *)shadow_read_write_fields, - (unsigned long *)shadow_read_only_fields + const unsigned long *fields[] = { + shadow_read_write_fields, + shadow_read_only_fields }; - int num_lists = ARRAY_SIZE(fields); - int max_fields[] = { + const int max_fields[] = { max_shadow_read_write_fields, max_shadow_read_only_fields }; @@ -6018,7 +6072,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) vmcs_load(shadow_vmcs); - for (q = 0; q < num_lists; q++) { + for (q = 0; q < ARRAY_SIZE(fields); q++) { for (i = 0; i < max_fields[q]; i++) { field = fields[q][i]; vmcs12_read_any(&vmx->vcpu, field, &field_value); @@ -6248,6 +6302,74 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) return 1; } +/* Emulate the INVEPT instruction */ +static int handle_invept(struct kvm_vcpu *vcpu) +{ + u32 vmx_instruction_info, types; + unsigned long type; + gva_t gva; + struct x86_exception e; + struct { + u64 eptp, gpa; + } operand; + u64 eptp_mask = ((1ull << 51) - 1) & PAGE_MASK; + + if (!(nested_vmx_secondary_ctls_high & SECONDARY_EXEC_ENABLE_EPT) || + !(nested_vmx_ept_caps & VMX_EPT_INVEPT_BIT)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + if (!nested_vmx_check_permission(vcpu)) + return 1; + + if (!kvm_read_cr0_bits(vcpu, X86_CR0_PE)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO); + type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf); + + types = (nested_vmx_ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6; + + if (!(types & (1UL << type))) { + nested_vmx_failValid(vcpu, + VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + return 1; + } + + /* According to the Intel VMX instruction reference, the memory + * operand is read even if it isn't needed (e.g., for type==global) + */ + if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), + vmx_instruction_info, &gva)) + return 1; + if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand, + sizeof(operand), &e)) { + kvm_inject_page_fault(vcpu, &e); + return 1; + } + + switch (type) { + case VMX_EPT_EXTENT_CONTEXT: + if ((operand.eptp & eptp_mask) != + (nested_ept_get_cr3(vcpu) & eptp_mask)) + break; + case VMX_EPT_EXTENT_GLOBAL: + kvm_mmu_sync_roots(vcpu); + kvm_mmu_flush_tlb(vcpu); + nested_vmx_succeed(vcpu); + break; + default: + BUG_ON(1); + break; + } + + skip_emulated_instruction(vcpu); + return 1; +} + /* * The exit handlers return 1 if the exit was handled fully and guest execution * may resume. Otherwise they set the kvm_run parameter to indicate what needs @@ -6292,6 +6414,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, [EXIT_REASON_MWAIT_INSTRUCTION] = handle_invalid_op, [EXIT_REASON_MONITOR_INSTRUCTION] = handle_invalid_op, + [EXIT_REASON_INVEPT] = handle_invept, }; static const int kvm_vmx_max_exit_handlers = @@ -6518,6 +6641,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD: case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE: case EXIT_REASON_VMOFF: case EXIT_REASON_VMON: + case EXIT_REASON_INVEPT: /* * VMX instructions trap unconditionally. This allows L1 to * emulate them for its L2 guest, i.e., allows 3-level nesting! @@ -6550,7 +6674,20 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) return nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES); case EXIT_REASON_EPT_VIOLATION: + /* + * L0 always deals with the EPT violation. If nested EPT is + * used, and the nested mmu code discovers that the address is + * missing in the guest EPT table (EPT12), the EPT violation + * will be injected with nested_ept_inject_page_fault() + */ + return 0; case EXIT_REASON_EPT_MISCONFIG: + /* + * L2 never uses directly L1's EPT, but rather L0's own EPT + * table (shadow on EPT) or a merged EPT table that L0 built + * (EPT on EPT). So any problems with the structure of the + * table is L0's fault. + */ return 0; case EXIT_REASON_PREEMPTION_TIMER: return vmcs12->pin_based_vm_exec_control & @@ -6638,7 +6775,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked && !(is_guest_mode(vcpu) && nested_cpu_has_virtual_nmis( - get_vmcs12(vcpu), vcpu)))) { + get_vmcs12(vcpu))))) { if (vmx_interrupt_allowed(vcpu)) { vmx->soft_vnmi_blocked = 0; } else if (vmx->vnmi_blocked_time > 1000000000LL && @@ -7326,6 +7463,48 @@ static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) entry->ecx |= bit(X86_FEATURE_VMX); } +static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, + struct x86_exception *fault) +{ + struct vmcs12 *vmcs12; + nested_vmx_vmexit(vcpu); + vmcs12 = get_vmcs12(vcpu); + + if (fault->error_code & PFERR_RSVD_MASK) + vmcs12->vm_exit_reason = EXIT_REASON_EPT_MISCONFIG; + else + vmcs12->vm_exit_reason = EXIT_REASON_EPT_VIOLATION; + vmcs12->exit_qualification = vcpu->arch.exit_qualification; + vmcs12->guest_physical_address = fault->address; +} + +/* Callbacks for nested_ept_init_mmu_context: */ + +static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu) +{ + /* return the page table to be shadowed - in our case, EPT12 */ + return get_vmcs12(vcpu)->ept_pointer; +} + +static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu) +{ + int r = kvm_init_shadow_ept_mmu(vcpu, &vcpu->arch.mmu, + nested_vmx_ept_caps & VMX_EPT_EXECUTE_ONLY_BIT); + + vcpu->arch.mmu.set_cr3 = vmx_set_cr3; + vcpu->arch.mmu.get_cr3 = nested_ept_get_cr3; + vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault; + + vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; + + return r; +} + +static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu) +{ + vcpu->arch.walk_mmu = &vcpu->arch.mmu; +} + /* * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it @@ -7388,7 +7567,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_interruptibility_info); vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs); kvm_set_dr(vcpu, 7, vmcs12->guest_dr7); - vmcs_writel(GUEST_RFLAGS, vmcs12->guest_rflags); + vmx_set_rflags(vcpu, vmcs12->guest_rflags); vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, vmcs12->guest_pending_dbg_exceptions); vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp); @@ -7508,15 +7687,24 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vcpu->arch.cr0_guest_owned_bits &= ~vmcs12->cr0_guest_host_mask; vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits); - /* Note: IA32_MODE, LOAD_IA32_EFER are modified by vmx_set_efer below */ - vmcs_write32(VM_EXIT_CONTROLS, - vmcs12->vm_exit_controls | vmcs_config.vmexit_ctrl); - vmcs_write32(VM_ENTRY_CONTROLS, vmcs12->vm_entry_controls | + /* L2->L1 exit controls are emulated - the hardware exit is to L0 so + * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER + * bits are further modified by vmx_set_efer() below. + */ + vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl); + + /* vmcs12's VM_ENTRY_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE are + * emulated by vmx_set_efer(), below. + */ + vmcs_write32(VM_ENTRY_CONTROLS, + (vmcs12->vm_entry_controls & ~VM_ENTRY_LOAD_IA32_EFER & + ~VM_ENTRY_IA32E_MODE) | (vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE)); - if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) + if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) { vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat); - else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) + vcpu->arch.pat = vmcs12->guest_ia32_pat; + } else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat); @@ -7538,6 +7726,11 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmx_flush_tlb(vcpu); } + if (nested_cpu_has_ept(vmcs12)) { + kvm_mmu_unload(vcpu); + nested_ept_init_mmu_context(vcpu); + } + if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER) vcpu->arch.efer = vmcs12->guest_ia32_efer; else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) @@ -7565,6 +7758,16 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) kvm_set_cr3(vcpu, vmcs12->guest_cr3); kvm_mmu_reset_context(vcpu); + /* + * L1 may access the L2's PDPTR, so save them to construct vmcs12 + */ + if (enable_ept) { + vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0); + vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1); + vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2); + vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3); + } + kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp); kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->guest_rip); } @@ -7887,6 +8090,22 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) vmcs12->guest_pending_dbg_exceptions = vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS); + /* + * In some cases (usually, nested EPT), L2 is allowed to change its + * own CR3 without exiting. If it has changed it, we must keep it. + * Of course, if L0 is using shadow page tables, GUEST_CR3 was defined + * by L0, not L1 or L2, so we mustn't unconditionally copy it to vmcs12. + * + * Additionally, restore L2's PDPTR to vmcs12. + */ + if (enable_ept) { + vmcs12->guest_cr3 = vmcs_read64(GUEST_CR3); + vmcs12->guest_pdptr0 = vmcs_read64(GUEST_PDPTR0); + vmcs12->guest_pdptr1 = vmcs_read64(GUEST_PDPTR1); + vmcs12->guest_pdptr2 = vmcs_read64(GUEST_PDPTR2); + vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3); + } + vmcs12->vm_entry_controls = (vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) | (vmcs_read32(VM_ENTRY_CONTROLS) & VM_ENTRY_IA32E_MODE); @@ -7948,6 +8167,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { + struct kvm_segment seg; + if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) vcpu->arch.efer = vmcs12->host_ia32_efer; else if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) @@ -7982,7 +8203,9 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); kvm_set_cr4(vcpu, vmcs12->host_cr4); - /* shadow page tables on either EPT or shadow page tables */ + if (nested_cpu_has_ept(vmcs12)) + nested_ept_uninit_mmu_context(vcpu); + kvm_set_cr3(vcpu, vmcs12->host_cr3); kvm_mmu_reset_context(vcpu); @@ -8001,23 +8224,61 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->host_ia32_sysenter_eip); vmcs_writel(GUEST_IDTR_BASE, vmcs12->host_idtr_base); vmcs_writel(GUEST_GDTR_BASE, vmcs12->host_gdtr_base); - vmcs_writel(GUEST_TR_BASE, vmcs12->host_tr_base); - vmcs_writel(GUEST_GS_BASE, vmcs12->host_gs_base); - vmcs_writel(GUEST_FS_BASE, vmcs12->host_fs_base); - vmcs_write16(GUEST_ES_SELECTOR, vmcs12->host_es_selector); - vmcs_write16(GUEST_CS_SELECTOR, vmcs12->host_cs_selector); - vmcs_write16(GUEST_SS_SELECTOR, vmcs12->host_ss_selector); - vmcs_write16(GUEST_DS_SELECTOR, vmcs12->host_ds_selector); - vmcs_write16(GUEST_FS_SELECTOR, vmcs12->host_fs_selector); - vmcs_write16(GUEST_GS_SELECTOR, vmcs12->host_gs_selector); - vmcs_write16(GUEST_TR_SELECTOR, vmcs12->host_tr_selector); - - if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) + + if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) { vmcs_write64(GUEST_IA32_PAT, vmcs12->host_ia32_pat); + vcpu->arch.pat = vmcs12->host_ia32_pat; + } if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL, vmcs12->host_ia32_perf_global_ctrl); + /* Set L1 segment info according to Intel SDM + 27.5.2 Loading Host Segment and Descriptor-Table Registers */ + seg = (struct kvm_segment) { + .base = 0, + .limit = 0xFFFFFFFF, + .selector = vmcs12->host_cs_selector, + .type = 11, + .present = 1, + .s = 1, + .g = 1 + }; + if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) + seg.l = 1; + else + seg.db = 1; + vmx_set_segment(vcpu, &seg, VCPU_SREG_CS); + seg = (struct kvm_segment) { + .base = 0, + .limit = 0xFFFFFFFF, + .type = 3, + .present = 1, + .s = 1, + .db = 1, + .g = 1 + }; + seg.selector = vmcs12->host_ds_selector; + vmx_set_segment(vcpu, &seg, VCPU_SREG_DS); + seg.selector = vmcs12->host_es_selector; + vmx_set_segment(vcpu, &seg, VCPU_SREG_ES); + seg.selector = vmcs12->host_ss_selector; + vmx_set_segment(vcpu, &seg, VCPU_SREG_SS); + seg.selector = vmcs12->host_fs_selector; + seg.base = vmcs12->host_fs_base; + vmx_set_segment(vcpu, &seg, VCPU_SREG_FS); + seg.selector = vmcs12->host_gs_selector; + seg.base = vmcs12->host_gs_base; + vmx_set_segment(vcpu, &seg, VCPU_SREG_GS); + seg = (struct kvm_segment) { + .base = vmcs12->host_tr_base, + .limit = 0x67, + .selector = vmcs12->host_tr_selector, + .type = 11, + .present = 1 + }; + vmx_set_segment(vcpu, &seg, VCPU_SREG_TR); + kvm_set_dr(vcpu, 7, 0x400); vmcs_write64(GUEST_IA32_DEBUGCTL, 0); } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index d21bce505315..e5ca72a5cdb6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -682,17 +682,6 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) */ } - /* - * Does the new cr3 value map to physical memory? (Note, we - * catch an invalid cr3 even in real-mode, because it would - * cause trouble later on when we turn on paging anyway.) - * - * A real CPU would silently accept an invalid cr3 and would - * attempt to use it - with largely undefined (and often hard - * to debug) behavior on the guest side. - */ - if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT))) - return 1; vcpu->arch.cr3 = cr3; __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); vcpu->arch.mmu.new_cr3(vcpu); @@ -850,7 +839,8 @@ static u32 msrs_to_save[] = { #ifdef CONFIG_X86_64 MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif - MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA + MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA, + MSR_IA32_FEATURE_CONTROL }; static unsigned num_msrs_to_save; @@ -1457,6 +1447,29 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) #endif } +static void kvm_gen_update_masterclock(struct kvm *kvm) +{ +#ifdef CONFIG_X86_64 + int i; + struct kvm_vcpu *vcpu; + struct kvm_arch *ka = &kvm->arch; + + spin_lock(&ka->pvclock_gtod_sync_lock); + kvm_make_mclock_inprogress_request(kvm); + /* no guest entries from this point */ + pvclock_update_vm_gtod_copy(kvm); + + kvm_for_each_vcpu(i, vcpu, kvm) + set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests); + + /* guest entries allowed */ + kvm_for_each_vcpu(i, vcpu, kvm) + clear_bit(KVM_REQ_MCLOCK_INPROGRESS, &vcpu->requests); + + spin_unlock(&ka->pvclock_gtod_sync_lock); +#endif +} + static int kvm_guest_time_update(struct kvm_vcpu *v) { unsigned long flags, this_tsc_khz; @@ -3806,6 +3819,7 @@ long kvm_arch_vm_ioctl(struct file *filp, delta = user_ns.clock - now_ns; local_irq_enable(); kvm->arch.kvmclock_offset = delta; + kvm_gen_update_masterclock(kvm); break; } case KVM_GET_CLOCK: { @@ -4955,6 +4969,97 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, static int complete_emulated_mmio(struct kvm_vcpu *vcpu); static int complete_emulated_pio(struct kvm_vcpu *vcpu); +static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, + unsigned long *db) +{ + u32 dr6 = 0; + int i; + u32 enable, rwlen; + + enable = dr7; + rwlen = dr7 >> 16; + for (i = 0; i < 4; i++, enable >>= 2, rwlen >>= 4) + if ((enable & 3) && (rwlen & 15) == type && db[i] == addr) + dr6 |= (1 << i); + return dr6; +} + +static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, int *r) +{ + struct kvm_run *kvm_run = vcpu->run; + + /* + * Use the "raw" value to see if TF was passed to the processor. + * Note that the new value of the flags has not been saved yet. + * + * This is correct even for TF set by the guest, because "the + * processor will not generate this exception after the instruction + * that sets the TF flag". + */ + unsigned long rflags = kvm_x86_ops->get_rflags(vcpu); + + if (unlikely(rflags & X86_EFLAGS_TF)) { + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { + kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1; + kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip; + kvm_run->debug.arch.exception = DB_VECTOR; + kvm_run->exit_reason = KVM_EXIT_DEBUG; + *r = EMULATE_USER_EXIT; + } else { + vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF; + /* + * "Certain debug exceptions may clear bit 0-3. The + * remaining contents of the DR6 register are never + * cleared by the processor". + */ + vcpu->arch.dr6 &= ~15; + vcpu->arch.dr6 |= DR6_BS; + kvm_queue_exception(vcpu, DB_VECTOR); + } + } +} + +static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) +{ + struct kvm_run *kvm_run = vcpu->run; + unsigned long eip = vcpu->arch.emulate_ctxt.eip; + u32 dr6 = 0; + + if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) && + (vcpu->arch.guest_debug_dr7 & DR7_BP_EN_MASK)) { + dr6 = kvm_vcpu_check_hw_bp(eip, 0, + vcpu->arch.guest_debug_dr7, + vcpu->arch.eff_db); + + if (dr6 != 0) { + kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1; + kvm_run->debug.arch.pc = kvm_rip_read(vcpu) + + get_segment_base(vcpu, VCPU_SREG_CS); + + kvm_run->debug.arch.exception = DB_VECTOR; + kvm_run->exit_reason = KVM_EXIT_DEBUG; + *r = EMULATE_USER_EXIT; + return true; + } + } + + if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK)) { + dr6 = kvm_vcpu_check_hw_bp(eip, 0, + vcpu->arch.dr7, + vcpu->arch.db); + + if (dr6 != 0) { + vcpu->arch.dr6 &= ~15; + vcpu->arch.dr6 |= dr6; + kvm_queue_exception(vcpu, DB_VECTOR); + *r = EMULATE_DONE; + return true; + } + } + + return false; +} + int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, int emulation_type, @@ -4975,6 +5080,16 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, if (!(emulation_type & EMULTYPE_NO_DECODE)) { init_emulate_ctxt(vcpu); + + /* + * We will reenter on the same instruction since + * we do not set complete_userspace_io. This does not + * handle watchpoints yet, those would be handled in + * the emulate_ops. + */ + if (kvm_vcpu_check_breakpoint(vcpu, &r)) + return r; + ctxt->interruptibility = 0; ctxt->have_exception = false; ctxt->perm_ok = false; @@ -5031,17 +5146,18 @@ restart: inject_emulated_exception(vcpu); r = EMULATE_DONE; } else if (vcpu->arch.pio.count) { - if (!vcpu->arch.pio.in) + if (!vcpu->arch.pio.in) { + /* FIXME: return into emulator if single-stepping. */ vcpu->arch.pio.count = 0; - else { + } else { writeback = false; vcpu->arch.complete_userspace_io = complete_emulated_pio; } - r = EMULATE_DO_MMIO; + r = EMULATE_USER_EXIT; } else if (vcpu->mmio_needed) { if (!vcpu->mmio_is_write) writeback = false; - r = EMULATE_DO_MMIO; + r = EMULATE_USER_EXIT; vcpu->arch.complete_userspace_io = complete_emulated_mmio; } else if (r == EMULATION_RESTART) goto restart; @@ -5050,10 +5166,12 @@ restart: if (writeback) { toggle_interruptibility(vcpu, ctxt->interruptibility); - kvm_set_rflags(vcpu, ctxt->eflags); kvm_make_request(KVM_REQ_EVENT, vcpu); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; kvm_rip_write(vcpu, ctxt->eip); + if (r == EMULATE_DONE) + kvm_vcpu_check_singlestep(vcpu, &r); + kvm_set_rflags(vcpu, ctxt->eflags); } else vcpu->arch.emulate_regs_need_sync_to_vcpu = true; @@ -5347,7 +5465,7 @@ static struct notifier_block pvclock_gtod_notifier = { int kvm_arch_init(void *opaque) { int r; - struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque; + struct kvm_x86_ops *ops = opaque; if (kvm_x86_ops) { printk(KERN_ERR "kvm: already loaded the other module\n"); @@ -5495,6 +5613,23 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) return 1; } +/* + * kvm_pv_kick_cpu_op: Kick a vcpu. + * + * @apicid - apicid of vcpu to be kicked. + */ +static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) +{ + struct kvm_lapic_irq lapic_irq; + + lapic_irq.shorthand = 0; + lapic_irq.dest_mode = 0; + lapic_irq.dest_id = apicid; + + lapic_irq.delivery_mode = APIC_DM_REMRD; + kvm_irq_delivery_to_apic(kvm, 0, &lapic_irq, NULL); +} + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; @@ -5528,6 +5663,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) case KVM_HC_VAPIC_POLL_IRQ: ret = 0; break; + case KVM_HC_KICK_CPU: + kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1); + ret = 0; + break; default: ret = -KVM_ENOSYS; break; @@ -5689,29 +5828,6 @@ static void process_nmi(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); } -static void kvm_gen_update_masterclock(struct kvm *kvm) -{ -#ifdef CONFIG_X86_64 - int i; - struct kvm_vcpu *vcpu; - struct kvm_arch *ka = &kvm->arch; - - spin_lock(&ka->pvclock_gtod_sync_lock); - kvm_make_mclock_inprogress_request(kvm); - /* no guest entries from this point */ - pvclock_update_vm_gtod_copy(kvm); - - kvm_for_each_vcpu(i, vcpu, kvm) - set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests); - - /* guest entries allowed */ - kvm_for_each_vcpu(i, vcpu, kvm) - clear_bit(KVM_REQ_MCLOCK_INPROGRESS, &vcpu->requests); - - spin_unlock(&ka->pvclock_gtod_sync_lock); -#endif -} - static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { u64 eoi_exit_bitmap[4]; @@ -5950,6 +6066,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) kvm_apic_accept_events(vcpu); switch(vcpu->arch.mp_state) { case KVM_MP_STATE_HALTED: + vcpu->arch.pv.pv_unhalted = false; vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; case KVM_MP_STATE_RUNNABLE: @@ -6061,6 +6178,8 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu) if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) { vcpu->mmio_needed = 0; + + /* FIXME: return into emulator if single-stepping. */ if (vcpu->mmio_is_write) return 1; vcpu->mmio_read_completed = 1; @@ -6249,7 +6368,12 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { kvm_apic_accept_events(vcpu); - mp_state->mp_state = vcpu->arch.mp_state; + if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED && + vcpu->arch.pv.pv_unhalted) + mp_state->mp_state = KVM_MP_STATE_RUNNABLE; + else + mp_state->mp_state = vcpu->arch.mp_state; + return 0; } @@ -6770,6 +6894,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) BUG_ON(vcpu->kvm == NULL); kvm = vcpu->kvm; + vcpu->arch.pv.pv_unhalted = false; vcpu->arch.emulate_ctxt.ops = &emulate_ops; if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -7019,6 +7144,15 @@ out_free: return -ENOMEM; } +void kvm_arch_memslots_updated(struct kvm *kvm) +{ + /* + * memslots->generation has been incremented. + * mmio generation may have reached its maximum value. + */ + kvm_mmu_invalidate_mmio_sptes(kvm); +} + int kvm_arch_prepare_memory_region(struct kvm *kvm, struct kvm_memory_slot *memslot, struct kvm_userspace_memory_region *mem, @@ -7079,11 +7213,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, */ if ((change != KVM_MR_DELETE) && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES)) kvm_mmu_slot_remove_write_access(kvm, mem->slot); - /* - * If memory slot is created, or moved, we need to clear all - * mmio sptes. - */ - kvm_mmu_invalidate_mmio_sptes(kvm); } void kvm_arch_flush_shadow_all(struct kvm *kvm) @@ -7103,6 +7232,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) !vcpu->arch.apf.halted) || !list_empty_careful(&vcpu->async_pf.done) || kvm_apic_has_events(vcpu) + || vcpu->arch.pv.pv_unhalted || atomic_read(&vcpu->arch.nmi_queued) || (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu)); diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c index 25b7ae8d058a..7609e0e421ec 100644 --- a/arch/x86/lib/csum-wrappers_64.c +++ b/arch/x86/lib/csum-wrappers_64.c @@ -6,6 +6,7 @@ */ #include <asm/checksum.h> #include <linux/module.h> +#include <asm/smap.h> /** * csum_partial_copy_from_user - Copy and checksum from user space. @@ -52,8 +53,10 @@ csum_partial_copy_from_user(const void __user *src, void *dst, len -= 2; } } + stac(); isum = csum_partial_copy_generic((__force const void *)src, dst, len, isum, errp, NULL); + clac(); if (unlikely(*errp)) goto out_err; @@ -82,6 +85,8 @@ __wsum csum_partial_copy_to_user(const void *src, void __user *dst, int len, __wsum isum, int *errp) { + __wsum ret; + might_sleep(); if (unlikely(!access_ok(VERIFY_WRITE, dst, len))) { @@ -105,8 +110,11 @@ csum_partial_copy_to_user(const void *src, void __user *dst, } *errp = 0; - return csum_partial_copy_generic(src, (void __force *)dst, - len, isum, NULL, errp); + stac(); + ret = csum_partial_copy_generic(src, (void __force *)dst, + len, isum, NULL, errp); + clac(); + return ret; } EXPORT_SYMBOL(csum_partial_copy_to_user); diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 906fea315791..c905e89e19fe 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -68,7 +68,7 @@ EXPORT_SYMBOL(copy_in_user); * Since protection fault in copy_from/to_user is not a normal situation, * it is not necessary to optimize tail handling. */ -unsigned long +__visible unsigned long copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest) { char c; diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index 5d7e51f3fd28..533a85e3a07e 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -1,10 +1,8 @@ # x86 Opcode Maps # # This is (mostly) based on following documentations. -# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2 -# (#325383-040US, October 2011) -# - Intel(R) Advanced Vector Extensions Programming Reference -# (#319433-011,JUNE 2011). +# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2C +# (#326018-047US, June 2013) # #<Opcode maps> # Table: table-name @@ -29,6 +27,7 @@ # - (F3): the last prefix is 0xF3 # - (F2): the last prefix is 0xF2 # - (!F3) : the last prefix is not 0xF3 (including non-last prefix case) +# - (66&F2): Both 0x66 and 0xF2 prefixes are specified. Table: one byte opcode Referrer: @@ -246,8 +245,8 @@ c2: RETN Iw (f64) c3: RETN c4: LES Gz,Mp (i64) | VEX+2byte (Prefix) c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix) -c6: Grp11 Eb,Ib (1A) -c7: Grp11 Ev,Iz (1A) +c6: Grp11A Eb,Ib (1A) +c7: Grp11B Ev,Iz (1A) c8: ENTER Iw,Ib c9: LEAVE (d64) ca: RETF Iw @@ -293,8 +292,8 @@ ef: OUT DX,eAX # 0xf0 - 0xff f0: LOCK (Prefix) f1: -f2: REPNE (Prefix) -f3: REP/REPE (Prefix) +f2: REPNE (Prefix) | XACQUIRE (Prefix) +f3: REP/REPE (Prefix) | XRELEASE (Prefix) f4: HLT f5: CMC f6: Grp3_1 Eb (1A) @@ -326,7 +325,8 @@ AVXcode: 1 0a: 0b: UD2 (1B) 0c: -0d: NOP Ev | GrpP +# AMD's prefetch group. Intel supports prefetchw(/1) only. +0d: GrpP 0e: FEMMS # 3DNow! uses the last imm byte as opcode extension. 0f: 3DNow! Pq,Qq,Ib @@ -729,12 +729,12 @@ dc: VAESENC Vdq,Hdq,Wdq (66),(v1) dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1) de: VAESDEC Vdq,Hdq,Wdq (66),(v1) df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1) -f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) -f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) +f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2) +f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2) f2: ANDN Gy,By,Ey (v) f3: Grp17 (1A) f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v) -f6: MULX By,Gy,rDX,Ey (F2),(v) +f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v) f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v) EndTable @@ -861,8 +861,8 @@ EndTable GrpTable: Grp7 0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) -1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001) -2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) +1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) +2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) 3: LIDT Ms 4: SMSW Mw/Rv 5: @@ -880,15 +880,21 @@ EndTable GrpTable: Grp9 1: CMPXCHG8B/16B Mq/Mdq 6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B) -7: VMPTRST Mq | VMPTRST Mq (F3) +7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B) EndTable GrpTable: Grp10 EndTable -GrpTable: Grp11 -# Note: the operands are given by group opcode -0: MOV +# Grp11A and Grp11B are expressed as Grp11 in Intel SDM +GrpTable: Grp11A +0: MOV Eb,Ib +7: XABORT Ib (000),(11B) +EndTable + +GrpTable: Grp11B +0: MOV Eb,Iz +7: XBEGIN Jz (000),(11B) EndTable GrpTable: Grp12 diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 2ec29ac78ae6..04664cdb7fda 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -78,8 +78,8 @@ __ref void *alloc_low_pages(unsigned int num) return __va(pfn << PAGE_SHIFT); } -/* need 4 4k for initial PMD_SIZE, 4k for 0-ISA_END_ADDRESS */ -#define INIT_PGT_BUF_SIZE (5 * PAGE_SIZE) +/* need 3 4k for initial PMD_SIZE, 3 4k for 0-ISA_END_ADDRESS */ +#define INIT_PGT_BUF_SIZE (6 * PAGE_SIZE) RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE); void __init early_alloc_pgt_buf(void) { diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 0215e2c563ef..799580cabc78 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -487,7 +487,7 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot) unsigned long offset; resource_size_t last_addr; unsigned int nrpages; - enum fixed_addresses idx0, idx; + enum fixed_addresses idx; int i, slot; WARN_ON(system_state != SYSTEM_BOOTING); @@ -540,8 +540,7 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot) /* * Ok, go for it.. */ - idx0 = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; - idx = idx0; + idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot; while (nrpages > 0) { early_set_fixmap(idx, phys_addr, prot); phys_addr += PAGE_SIZE; diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index f63778cb2363..25e7e1372bb2 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -98,7 +98,7 @@ static unsigned long mmap_base(void) * Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64 * does, but not when emulating X86_32 */ -unsigned long mmap_legacy_base(void) +static unsigned long mmap_legacy_base(void) { if (mmap_is_ia32()) return TASK_UNMAPPED_BASE; @@ -112,11 +112,13 @@ unsigned long mmap_legacy_base(void) */ void arch_pick_mmap_layout(struct mm_struct *mm) { + mm->mmap_legacy_base = mmap_legacy_base(); + mm->mmap_base = mmap_base(); + if (mmap_is_legacy()) { - mm->mmap_base = mmap_legacy_base(); + mm->mmap_base = mm->mmap_legacy_base; mm->get_unmapped_area = arch_get_unmapped_area; } else { - mm->mmap_base = mmap_base(); mm->get_unmapped_area = arch_get_unmapped_area_topdown; } } diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index cdd0da9dd530..266ca912f62e 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -146,6 +146,7 @@ int __init acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) { u64 start, end; + u32 hotpluggable; int node, pxm; if (srat_disabled()) @@ -154,7 +155,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) goto out_err_bad_srat; if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0) goto out_err; - if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info()) + hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE; + if (hotpluggable && !save_add_info()) goto out_err; start = ma->base_address; @@ -174,9 +176,10 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) node_set(node, numa_nodes_parsed); - printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n", - node, pxm, - (unsigned long long) start, (unsigned long long) end - 1); + pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s\n", + node, pxm, + (unsigned long long) start, (unsigned long long) end - 1, + hotpluggable ? " hotplug" : ""); return 0; out_err_bad_srat: diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index d641897a1f4e..b30e937689d6 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -568,13 +568,8 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) */ if (bus) { struct pci_bus *child; - list_for_each_entry(child, &bus->children, node) { - struct pci_dev *self = child->self; - if (!self) - continue; - - pcie_bus_configure_settings(child, self->pcie_mpss); - } + list_for_each_entry(child, &bus->children, node) + pcie_bus_configure_settings(child); } if (bus && node != -1) { diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 94919e307f8e..db6b1ab43255 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -210,6 +210,8 @@ static void pcibios_allocate_bridge_resources(struct pci_dev *dev) r = &dev->resource[idx]; if (!r->flags) continue; + if (r->parent) /* Already allocated */ + continue; if (!r->start || pci_claim_resource(dev, idx) < 0) { /* * Something is wrong with the region. @@ -318,6 +320,8 @@ static void pcibios_allocate_dev_rom_resource(struct pci_dev *dev) r = &dev->resource[PCI_ROM_RESOURCE]; if (!r->flags || !r->start) return; + if (r->parent) /* Already allocated */ + return; if (pci_claim_resource(dev, PCI_ROM_RESOURCE) < 0) { r->end -= r->start; diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 082e88129712..5596c7bdd327 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -700,7 +700,7 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, if (!(pci_probe & PCI_PROBE_MMCONF) || pci_mmcfg_arch_init_failed) return -ENODEV; - if (start > end) + if (start > end || !addr) return -EINVAL; mutex_lock(&pci_mmcfg_lock); @@ -716,11 +716,6 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, return -EEXIST; } - if (!addr) { - mutex_unlock(&pci_mmcfg_lock); - return -EINVAL; - } - rc = -EBUSY; cfg = pci_mmconfig_alloc(seg, start, end, addr); if (cfg == NULL) { diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/mrst.c index 6eb18c42a28a..903fded50786 100644 --- a/arch/x86/pci/mrst.c +++ b/arch/x86/pci/mrst.c @@ -23,11 +23,11 @@ #include <linux/ioport.h> #include <linux/init.h> #include <linux/dmi.h> +#include <linux/acpi.h> +#include <linux/io.h> +#include <linux/smp.h> -#include <asm/acpi.h> #include <asm/segment.h> -#include <asm/io.h> -#include <asm/smp.h> #include <asm/pci_x86.h> #include <asm/hw_irq.h> #include <asm/io_apic.h> @@ -43,7 +43,7 @@ #define PCI_FIXED_BAR_4_SIZE 0x14 #define PCI_FIXED_BAR_5_SIZE 0x1c -static int pci_soc_mode = 0; +static int pci_soc_mode; /** * fixed_bar_cap - return the offset of the fixed BAR cap if found @@ -141,7 +141,8 @@ static int pci_device_update_fixed(struct pci_bus *bus, unsigned int devfn, */ static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg) { - /* This is a workaround for A0 LNC bug where PCI status register does + /* + * This is a workaround for A0 LNC bug where PCI status register does * not have new CAP bit set. can not be written by SW either. * * PCI header type in real LNC indicates a single function device, this @@ -154,7 +155,7 @@ static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg) || devfn == PCI_DEVFN(0, 0) || devfn == PCI_DEVFN(3, 0))) return 1; - return 0; /* langwell on others */ + return 0; /* Langwell on others */ } static int pci_read(struct pci_bus *bus, unsigned int devfn, int where, @@ -172,7 +173,8 @@ static int pci_write(struct pci_bus *bus, unsigned int devfn, int where, { int offset; - /* On MRST, there is no PCI ROM BAR, this will cause a subsequent read + /* + * On MRST, there is no PCI ROM BAR, this will cause a subsequent read * to ROM BAR return 0 then being ignored. */ if (where == PCI_ROM_ADDRESS) @@ -210,7 +212,8 @@ static int mrst_pci_irq_enable(struct pci_dev *dev) pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); - /* MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to + /* + * MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to * IOAPIC RTE entries, so we just enable RTE for the device. */ irq_attr.ioapic = mp_find_ioapic(dev->irq); @@ -235,7 +238,7 @@ struct pci_ops pci_mrst_ops = { */ int __init pci_mrst_init(void) { - printk(KERN_INFO "Intel MID platform detected, using MID PCI ops\n"); + pr_info("Intel MID platform detected, using MID PCI ops\n"); pci_mmcfg_late_init(); pcibios_enable_irq = mrst_pci_irq_enable; pci_root_ops = pci_mrst_ops; @@ -244,17 +247,21 @@ int __init pci_mrst_init(void) return 1; } -/* Langwell devices are not true pci devices, they are not subject to 10 ms - * d3 to d0 delay required by pci spec. +/* + * Langwell devices are not true PCI devices; they are not subject to 10 ms + * d3 to d0 delay required by PCI spec. */ static void pci_d3delay_fixup(struct pci_dev *dev) { - /* PCI fixups are effectively decided compile time. If we have a dual - SoC/non-SoC kernel we don't want to mangle d3 on non SoC devices */ - if (!pci_soc_mode) - return; - /* true pci devices in lincroft should allow type 1 access, the rest - * are langwell fake pci devices. + /* + * PCI fixups are effectively decided compile time. If we have a dual + * SoC/non-SoC kernel we don't want to mangle d3 on non-SoC devices. + */ + if (!pci_soc_mode) + return; + /* + * True PCI devices in Lincroft should allow type 1 access, the rest + * are Langwell fake PCI devices. */ if (type1_access_ok(dev->bus->number, dev->devfn, PCI_DEVICE_ID)) return; diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 1cf5b300305e..424f4c97a44d 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -25,10 +25,10 @@ #include <asm/cpu.h> #ifdef CONFIG_X86_32 -unsigned long saved_context_ebx; -unsigned long saved_context_esp, saved_context_ebp; -unsigned long saved_context_esi, saved_context_edi; -unsigned long saved_context_eflags; +__visible unsigned long saved_context_ebx; +__visible unsigned long saved_context_esp, saved_context_ebp; +__visible unsigned long saved_context_esi, saved_context_edi; +__visible unsigned long saved_context_eflags; #endif struct saved_context saved_context; diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index a0fde91c16cf..304fca20d96e 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -20,26 +20,26 @@ #include <asm/suspend.h> /* References to section boundaries */ -extern const void __nosave_begin, __nosave_end; +extern __visible const void __nosave_begin, __nosave_end; /* Defined in hibernate_asm_64.S */ -extern int restore_image(void); +extern asmlinkage int restore_image(void); /* * Address to jump to in the last phase of restore in order to get to the image * kernel's text (this value is passed in the image header). */ -unsigned long restore_jump_address; +unsigned long restore_jump_address __visible; /* * Value of the cr3 register from before the hibernation (this value is passed * in the image header). */ -unsigned long restore_cr3; +unsigned long restore_cr3 __visible; -pgd_t *temp_level4_pgt; +pgd_t *temp_level4_pgt __visible; -void *relocated_restore_code; +void *relocated_restore_code __visible; static void *alloc_pgt_page(void *context) { diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk index e6773dc8ac41..093a892026f9 100644 --- a/arch/x86/tools/gen-insn-attr-x86.awk +++ b/arch/x86/tools/gen-insn-attr-x86.awk @@ -68,7 +68,7 @@ BEGIN { lprefix1_expr = "\\((66|!F3)\\)" lprefix2_expr = "\\(F3\\)" - lprefix3_expr = "\\((F2|!F3)\\)" + lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)" lprefix_expr = "\\((66|F2|F3)\\)" max_lprefix = 4 @@ -83,6 +83,8 @@ BEGIN { prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ" prefix_num["REPNE"] = "INAT_PFX_REPNE" prefix_num["REP/REPE"] = "INAT_PFX_REPE" + prefix_num["XACQUIRE"] = "INAT_PFX_REPNE" + prefix_num["XRELEASE"] = "INAT_PFX_REPE" prefix_num["LOCK"] = "INAT_PFX_LOCK" prefix_num["SEG=CS"] = "INAT_PFX_CS" prefix_num["SEG=DS"] = "INAT_PFX_DS" diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index c74436e687bf..72074d528400 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -85,15 +85,18 @@ 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; @@ -104,8 +107,6 @@ static notrace cycle_t vread_pvclock(int *mode) pvti = get_pvti(cpu); - migrate_count = pvti->migrate_count; - version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); /* @@ -117,8 +118,7 @@ static notrace cycle_t vread_pvclock(int *mode) cpu1 = __getcpu() & VGETCPU_CPU_MASK; } while (unlikely(cpu != cpu1 || (pvti->pvti.version & 1) || - pvti->pvti.version != version || - pvti->migrate_count != migrate_count)); + 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 193097ef3d7d..2fc216dfbd9c 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -427,8 +427,7 @@ static void __init xen_init_cpuid_mask(void) if (!xen_initial_domain()) cpuid_leaf1_edx_mask &= - ~((1 << X86_FEATURE_APIC) | /* disable local APIC */ - (1 << X86_FEATURE_ACPI)); /* disable ACPI */ + ~((1 << X86_FEATURE_ACPI)); /* disable ACPI */ cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_X2APIC % 32)); @@ -735,8 +734,7 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val, addr = (unsigned long)xen_int3; else if (addr == (unsigned long)stack_segment) addr = (unsigned long)xen_stack_segment; - else if (addr == (unsigned long)double_fault || - addr == (unsigned long)nmi) { + else if (addr == (unsigned long)double_fault) { /* Don't need to handle these */ return 0; #ifdef CONFIG_X86_MCE @@ -747,7 +745,12 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val, */ ; #endif - } else { + } else if (addr == (unsigned long)nmi) + /* + * Use the native version as well. + */ + ; + else { /* Some other trap using IST? */ if (WARN_ON(val->ist != 0)) return 0; @@ -1710,6 +1713,8 @@ static void __init xen_hvm_guest_init(void) xen_hvm_init_shared_info(); + xen_panic_handler_init(); + if (xen_feature(XENFEAT_hvm_callback_vector)) xen_have_vector_callback = 1; xen_hvm_smp_init(); @@ -1720,15 +1725,12 @@ static void __init xen_hvm_guest_init(void) xen_hvm_init_mmu_ops(); } -static bool __init xen_hvm_platform(void) +static uint32_t __init xen_hvm_platform(void) { if (xen_pv_domain()) - return false; - - if (!xen_cpuid_base()) - return false; + return 0; - return true; + return xen_cpuid_base(); } bool xen_hvm_need_lapic(void) diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index 01a4dc015ae1..0da7f863056f 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -47,23 +47,18 @@ static void xen_restore_fl(unsigned long flags) /* convert from IF type flag */ flags = !(flags & X86_EFLAGS_IF); - /* There's a one instruction preempt window here. We need to - make sure we're don't switch CPUs between getting the vcpu - pointer and updating the mask. */ + /* See xen_irq_enable() for why preemption must be disabled. */ preempt_disable(); vcpu = this_cpu_read(xen_vcpu); vcpu->evtchn_upcall_mask = flags; - preempt_enable_no_resched(); - - /* Doesn't matter if we get preempted here, because any - pending event will get dealt with anyway. */ if (flags == 0) { - preempt_check_resched(); barrier(); /* unmask then check (avoid races) */ if (unlikely(vcpu->evtchn_upcall_pending)) xen_force_evtchn_callback(); - } + preempt_enable(); + } else + preempt_enable_no_resched(); } PV_CALLEE_SAVE_REGS_THUNK(xen_restore_fl); @@ -82,10 +77,12 @@ static void xen_irq_enable(void) { struct vcpu_info *vcpu; - /* We don't need to worry about being preempted here, since - either a) interrupts are disabled, so no preemption, or b) - the caller is confused and is trying to re-enable interrupts - on an indeterminate processor. */ + /* + * We may be preempted as soon as vcpu->evtchn_upcall_mask is + * cleared, so disable preemption to ensure we check for + * events on the VCPU we are still running on. + */ + preempt_disable(); vcpu = this_cpu_read(xen_vcpu); vcpu->evtchn_upcall_mask = 0; @@ -96,6 +93,8 @@ static void xen_irq_enable(void) barrier(); /* unmask then check (avoid races) */ if (unlikely(vcpu->evtchn_upcall_pending)) xen_force_evtchn_callback(); + + preempt_enable(); } PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable); diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 95fb2aa5927e..0d4ec35895d4 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -161,6 +161,7 @@ #include <asm/xen/page.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> +#include <xen/balloon.h> #include <xen/grant_table.h> #include "multicalls.h" @@ -967,7 +968,10 @@ int m2p_remove_override(struct page *page, if (kmap_op != NULL) { if (!PageHighMem(page)) { struct multicall_space mcs; - struct gnttab_unmap_grant_ref *unmap_op; + struct gnttab_unmap_and_replace *unmap_op; + struct page *scratch_page = get_balloon_scratch_page(); + unsigned long scratch_page_address = (unsigned long) + __va(page_to_pfn(scratch_page) << PAGE_SHIFT); /* * It might be that we queued all the m2p grant table @@ -990,21 +994,25 @@ int m2p_remove_override(struct page *page, } mcs = xen_mc_entry( - sizeof(struct gnttab_unmap_grant_ref)); + sizeof(struct gnttab_unmap_and_replace)); unmap_op = mcs.args; unmap_op->host_addr = kmap_op->host_addr; + unmap_op->new_addr = scratch_page_address; unmap_op->handle = kmap_op->handle; - unmap_op->dev_bus_addr = 0; MULTI_grant_table_op(mcs.mc, - GNTTABOP_unmap_grant_ref, unmap_op, 1); + GNTTABOP_unmap_and_replace, unmap_op, 1); xen_mc_issue(PARAVIRT_LAZY_MMU); - set_pte_at(&init_mm, address, ptep, - pfn_pte(pfn, PAGE_KERNEL)); - __flush_tlb_single(address); + mcs = __xen_mc_entry(0); + MULTI_update_va_mapping(mcs.mc, scratch_page_address, + pfn_pte(page_to_pfn(get_balloon_scratch_page()), + PAGE_KERNEL_RO), 0); + xen_mc_issue(PARAVIRT_LAZY_MMU); + kmap_op->host_addr = 0; + put_balloon_scratch_page(); } } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 056d11faef21..09f3059cb00b 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -33,6 +33,9 @@ /* These are code, but not functions. Defined in entry.S */ extern const char xen_hypervisor_callback[]; extern const char xen_failsafe_callback[]; +#ifdef CONFIG_X86_64 +extern const char nmi[]; +#endif extern void xen_sysenter_target(void); extern void xen_syscall_target(void); extern void xen_syscall32_target(void); @@ -215,13 +218,19 @@ static void __init xen_set_identity_and_release_chunk( unsigned long pfn; /* - * If the PFNs are currently mapped, the VA mapping also needs - * to be updated to be 1:1. + * If the PFNs are currently mapped, clear the mappings + * (except for the ISA region which must be 1:1 mapped) to + * release the refcounts (in Xen) on the original frames. */ - for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) + for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) { + pte_t pte = __pte_ma(0); + + if (pfn < PFN_UP(ISA_END_ADDRESS)) + pte = mfn_pte(pfn, PAGE_KERNEL_IO); + (void)HYPERVISOR_update_va_mapping( - (unsigned long)__va(pfn << PAGE_SHIFT), - mfn_pte(pfn, PAGE_KERNEL_IO), 0); + (unsigned long)__va(pfn << PAGE_SHIFT), pte, 0); + } if (start_pfn < nr_pages) *released += xen_release_chunk( @@ -313,6 +322,17 @@ static void xen_align_and_add_e820_region(u64 start, u64 size, int type) e820_add_region(start, end - start, type); } +void xen_ignore_unusable(struct e820entry *list, size_t map_size) +{ + struct e820entry *entry; + unsigned int i; + + for (i = 0, entry = list; i < map_size; i++, entry++) { + if (entry->type == E820_UNUSABLE) + entry->type = E820_RAM; + } +} + /** * machine_specific_memory_setup - Hook for machine specific memory setup. **/ @@ -353,6 +373,17 @@ char * __init xen_memory_setup(void) } BUG_ON(rc); + /* + * Xen won't allow a 1:1 mapping to be created to UNUSABLE + * regions, so if we're using the machine memory map leave the + * region as RAM as it is in the pseudo-physical map. + * + * UNUSABLE regions in domUs are not handled and will need + * a patch in the future. + */ + if (xen_initial_domain()) + xen_ignore_unusable(map, memmap.nr_entries); + /* Make sure the Xen-supplied memory map is well-ordered. */ sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries); @@ -525,7 +556,13 @@ void xen_enable_syscall(void) } #endif /* CONFIG_X86_64 */ } - +void __cpuinit xen_enable_nmi(void) +{ +#ifdef CONFIG_X86_64 + if (register_callback(CALLBACKTYPE_nmi, nmi)) + BUG(); +#endif +} void __init xen_arch_setup(void) { xen_panic_handler_init(); @@ -543,7 +580,7 @@ void __init xen_arch_setup(void) xen_enable_sysenter(); xen_enable_syscall(); - + xen_enable_nmi(); #ifdef CONFIG_ACPI if (!(xen_start_info->flags & SIF_INITDOMAIN)) { printk(KERN_INFO "ACPI in unprivileged domain disabled\n"); diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index ca92754eb846..9235842cd76a 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -279,6 +279,7 @@ static void __init xen_smp_prepare_boot_cpu(void) xen_filter_cpu_maps(); xen_setup_vcpu_info_placement(); + xen_init_spinlocks(); } static void __init xen_smp_prepare_cpus(unsigned int max_cpus) @@ -572,6 +573,12 @@ static inline int xen_map_vector(int vector) case IRQ_WORK_VECTOR: xen_vector = XEN_IRQ_WORK_VECTOR; break; +#ifdef CONFIG_X86_64 + case NMI_VECTOR: + case APIC_DM_NMI: /* Some use that instead of NMI_VECTOR */ + xen_vector = XEN_NMI_VECTOR; + break; +#endif default: xen_vector = -1; printk(KERN_ERR "xen: vector 0x%x is not implemented\n", @@ -680,7 +687,6 @@ void __init xen_smp_init(void) { smp_ops = xen_smp_ops; xen_fill_possible_map(); - xen_init_spinlocks(); } static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) @@ -694,8 +700,15 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle) { int rc; - rc = native_cpu_up(cpu, tidle); - WARN_ON (xen_smp_intr_init(cpu)); + /* + * xen_smp_intr_init() needs to run before native_cpu_up() + * so that IPI vectors are set up on the booting CPU before + * it is marked online in native_cpu_up(). + */ + rc = xen_smp_intr_init(cpu); + WARN_ON(rc); + if (!rc) + rc = native_cpu_up(cpu, tidle); return rc; } diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index cf3caee356b3..0438b9324a72 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -17,45 +17,44 @@ #include "xen-ops.h" #include "debugfs.h" -#ifdef CONFIG_XEN_DEBUG_FS -static struct xen_spinlock_stats -{ - u64 taken; - u32 taken_slow; - u32 taken_slow_nested; - u32 taken_slow_pickup; - u32 taken_slow_spurious; - u32 taken_slow_irqenable; +enum xen_contention_stat { + TAKEN_SLOW, + TAKEN_SLOW_PICKUP, + TAKEN_SLOW_SPURIOUS, + RELEASED_SLOW, + RELEASED_SLOW_KICKED, + NR_CONTENTION_STATS +}; - u64 released; - u32 released_slow; - u32 released_slow_kicked; +#ifdef CONFIG_XEN_DEBUG_FS #define HISTO_BUCKETS 30 - u32 histo_spin_total[HISTO_BUCKETS+1]; - u32 histo_spin_spinning[HISTO_BUCKETS+1]; +static struct xen_spinlock_stats +{ + u32 contention_stats[NR_CONTENTION_STATS]; u32 histo_spin_blocked[HISTO_BUCKETS+1]; - - u64 time_total; - u64 time_spinning; u64 time_blocked; } spinlock_stats; static u8 zero_stats; -static unsigned lock_timeout = 1 << 10; -#define TIMEOUT lock_timeout - static inline void check_zero(void) { - if (unlikely(zero_stats)) { - memset(&spinlock_stats, 0, sizeof(spinlock_stats)); - zero_stats = 0; + u8 ret; + u8 old = ACCESS_ONCE(zero_stats); + if (unlikely(old)) { + ret = cmpxchg(&zero_stats, old, 0); + /* This ensures only one fellow resets the stat */ + if (ret == old) + memset(&spinlock_stats, 0, sizeof(spinlock_stats)); } } -#define ADD_STATS(elem, val) \ - do { check_zero(); spinlock_stats.elem += (val); } while(0) +static inline void add_stats(enum xen_contention_stat var, u32 val) +{ + check_zero(); + spinlock_stats.contention_stats[var] += val; +} static inline u64 spin_time_start(void) { @@ -74,22 +73,6 @@ static void __spin_time_accum(u64 delta, u32 *array) array[HISTO_BUCKETS]++; } -static inline void spin_time_accum_spinning(u64 start) -{ - u32 delta = xen_clocksource_read() - start; - - __spin_time_accum(delta, spinlock_stats.histo_spin_spinning); - spinlock_stats.time_spinning += delta; -} - -static inline void spin_time_accum_total(u64 start) -{ - u32 delta = xen_clocksource_read() - start; - - __spin_time_accum(delta, spinlock_stats.histo_spin_total); - spinlock_stats.time_total += delta; -} - static inline void spin_time_accum_blocked(u64 start) { u32 delta = xen_clocksource_read() - start; @@ -99,19 +82,15 @@ static inline void spin_time_accum_blocked(u64 start) } #else /* !CONFIG_XEN_DEBUG_FS */ #define TIMEOUT (1 << 10) -#define ADD_STATS(elem, val) do { (void)(val); } while(0) +static inline void add_stats(enum xen_contention_stat var, u32 val) +{ +} static inline u64 spin_time_start(void) { return 0; } -static inline void spin_time_accum_total(u64 start) -{ -} -static inline void spin_time_accum_spinning(u64 start) -{ -} static inline void spin_time_accum_blocked(u64 start) { } @@ -134,227 +113,123 @@ typedef u16 xen_spinners_t; asm(LOCK_PREFIX " decw %0" : "+m" ((xl)->spinners) : : "memory"); #endif -struct xen_spinlock { - unsigned char lock; /* 0 -> free; 1 -> locked */ - xen_spinners_t spinners; /* count of waiting cpus */ +struct xen_lock_waiting { + struct arch_spinlock *lock; + __ticket_t want; }; -static int xen_spin_is_locked(struct arch_spinlock *lock) -{ - struct xen_spinlock *xl = (struct xen_spinlock *)lock; - - return xl->lock != 0; -} - -static int xen_spin_is_contended(struct arch_spinlock *lock) -{ - struct xen_spinlock *xl = (struct xen_spinlock *)lock; - - /* Not strictly true; this is only the count of contended - lock-takers entering the slow path. */ - return xl->spinners != 0; -} - -static int xen_spin_trylock(struct arch_spinlock *lock) -{ - struct xen_spinlock *xl = (struct xen_spinlock *)lock; - u8 old = 1; - - asm("xchgb %b0,%1" - : "+q" (old), "+m" (xl->lock) : : "memory"); - - return old == 0; -} - -static DEFINE_PER_CPU(char *, irq_name); static DEFINE_PER_CPU(int, lock_kicker_irq) = -1; -static DEFINE_PER_CPU(struct xen_spinlock *, lock_spinners); - -/* - * Mark a cpu as interested in a lock. Returns the CPU's previous - * lock of interest, in case we got preempted by an interrupt. - */ -static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl) -{ - struct xen_spinlock *prev; - - prev = __this_cpu_read(lock_spinners); - __this_cpu_write(lock_spinners, xl); - - wmb(); /* set lock of interest before count */ - - inc_spinners(xl); - - return prev; -} - -/* - * Mark a cpu as no longer interested in a lock. Restores previous - * lock of interest (NULL for none). - */ -static inline void unspinning_lock(struct xen_spinlock *xl, struct xen_spinlock *prev) -{ - dec_spinners(xl); - wmb(); /* decrement count before restoring lock */ - __this_cpu_write(lock_spinners, prev); -} +static DEFINE_PER_CPU(char *, irq_name); +static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting); +static cpumask_t waiting_cpus; -static noinline int xen_spin_lock_slow(struct arch_spinlock *lock, bool irq_enable) +static void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want) { - struct xen_spinlock *xl = (struct xen_spinlock *)lock; - struct xen_spinlock *prev; int irq = __this_cpu_read(lock_kicker_irq); - int ret; + struct xen_lock_waiting *w = &__get_cpu_var(lock_waiting); + int cpu = smp_processor_id(); u64 start; + unsigned long flags; /* If kicker interrupts not initialized yet, just spin */ if (irq == -1) - return 0; + return; start = spin_time_start(); - /* announce we're spinning */ - prev = spinning_lock(xl); + /* + * Make sure an interrupt handler can't upset things in a + * partially setup state. + */ + local_irq_save(flags); + /* + * We don't really care if we're overwriting some other + * (lock,want) pair, as that would mean that we're currently + * in an interrupt context, and the outer context had + * interrupts enabled. That has already kicked the VCPU out + * of xen_poll_irq(), so it will just return spuriously and + * retry with newly setup (lock,want). + * + * The ordering protocol on this is that the "lock" pointer + * may only be set non-NULL if the "want" ticket is correct. + * If we're updating "want", we must first clear "lock". + */ + w->lock = NULL; + smp_wmb(); + w->want = want; + smp_wmb(); + w->lock = lock; - ADD_STATS(taken_slow, 1); - ADD_STATS(taken_slow_nested, prev != NULL); + /* This uses set_bit, which atomic and therefore a barrier */ + cpumask_set_cpu(cpu, &waiting_cpus); + add_stats(TAKEN_SLOW, 1); - do { - unsigned long flags; + /* clear pending */ + xen_clear_irq_pending(irq); - /* clear pending */ - xen_clear_irq_pending(irq); + /* Only check lock once pending cleared */ + barrier(); - /* check again make sure it didn't become free while - we weren't looking */ - ret = xen_spin_trylock(lock); - if (ret) { - ADD_STATS(taken_slow_pickup, 1); + /* + * Mark entry to slowpath before doing the pickup test to make + * sure we don't deadlock with an unlocker. + */ + __ticket_enter_slowpath(lock); - /* - * If we interrupted another spinlock while it - * was blocking, make sure it doesn't block - * without rechecking the lock. - */ - if (prev != NULL) - xen_set_irq_pending(irq); - goto out; - } + /* + * check again make sure it didn't become free while + * we weren't looking + */ + if (ACCESS_ONCE(lock->tickets.head) == want) { + add_stats(TAKEN_SLOW_PICKUP, 1); + goto out; + } - flags = arch_local_save_flags(); - if (irq_enable) { - ADD_STATS(taken_slow_irqenable, 1); - raw_local_irq_enable(); - } + /* Allow interrupts while blocked */ + local_irq_restore(flags); - /* - * Block until irq becomes pending. If we're - * interrupted at this point (after the trylock but - * before entering the block), then the nested lock - * handler guarantees that the irq will be left - * pending if there's any chance the lock became free; - * xen_poll_irq() returns immediately if the irq is - * pending. - */ - xen_poll_irq(irq); + /* + * If an interrupt happens here, it will leave the wakeup irq + * pending, which will cause xen_poll_irq() to return + * immediately. + */ - raw_local_irq_restore(flags); + /* Block until irq becomes pending (or perhaps a spurious wakeup) */ + xen_poll_irq(irq); + add_stats(TAKEN_SLOW_SPURIOUS, !xen_test_irq_pending(irq)); - ADD_STATS(taken_slow_spurious, !xen_test_irq_pending(irq)); - } while (!xen_test_irq_pending(irq)); /* check for spurious wakeups */ + local_irq_save(flags); kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); - out: - unspinning_lock(xl, prev); - spin_time_accum_blocked(start); - - return ret; -} - -static inline void __xen_spin_lock(struct arch_spinlock *lock, bool irq_enable) -{ - struct xen_spinlock *xl = (struct xen_spinlock *)lock; - unsigned timeout; - u8 oldval; - u64 start_spin; - - ADD_STATS(taken, 1); - - start_spin = spin_time_start(); - - do { - u64 start_spin_fast = spin_time_start(); - - timeout = TIMEOUT; - - asm("1: xchgb %1,%0\n" - " testb %1,%1\n" - " jz 3f\n" - "2: rep;nop\n" - " cmpb $0,%0\n" - " je 1b\n" - " dec %2\n" - " jnz 2b\n" - "3:\n" - : "+m" (xl->lock), "=q" (oldval), "+r" (timeout) - : "1" (1) - : "memory"); + cpumask_clear_cpu(cpu, &waiting_cpus); + w->lock = NULL; - spin_time_accum_spinning(start_spin_fast); + local_irq_restore(flags); - } while (unlikely(oldval != 0 && - (TIMEOUT == ~0 || !xen_spin_lock_slow(lock, irq_enable)))); - - spin_time_accum_total(start_spin); -} - -static void xen_spin_lock(struct arch_spinlock *lock) -{ - __xen_spin_lock(lock, false); -} - -static void xen_spin_lock_flags(struct arch_spinlock *lock, unsigned long flags) -{ - __xen_spin_lock(lock, !raw_irqs_disabled_flags(flags)); + spin_time_accum_blocked(start); } +PV_CALLEE_SAVE_REGS_THUNK(xen_lock_spinning); -static noinline void xen_spin_unlock_slow(struct xen_spinlock *xl) +static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next) { int cpu; - ADD_STATS(released_slow, 1); + add_stats(RELEASED_SLOW, 1); + + for_each_cpu(cpu, &waiting_cpus) { + const struct xen_lock_waiting *w = &per_cpu(lock_waiting, cpu); - for_each_online_cpu(cpu) { - /* XXX should mix up next cpu selection */ - if (per_cpu(lock_spinners, cpu) == xl) { - ADD_STATS(released_slow_kicked, 1); + /* Make sure we read lock before want */ + if (ACCESS_ONCE(w->lock) == lock && + ACCESS_ONCE(w->want) == next) { + add_stats(RELEASED_SLOW_KICKED, 1); xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR); + break; } } } -static void xen_spin_unlock(struct arch_spinlock *lock) -{ - struct xen_spinlock *xl = (struct xen_spinlock *)lock; - - ADD_STATS(released, 1); - - smp_wmb(); /* make sure no writes get moved after unlock */ - xl->lock = 0; /* release lock */ - - /* - * Make sure unlock happens before checking for waiting - * spinners. We need a strong barrier to enforce the - * write-read ordering to different memory locations, as the - * CPU makes no implied guarantees about their ordering. - */ - mb(); - - if (unlikely(xl->spinners)) - xen_spin_unlock_slow(xl); -} - static irqreturn_t dummy_handler(int irq, void *dev_id) { BUG(); @@ -408,6 +283,8 @@ void xen_uninit_lock_cpu(int cpu) per_cpu(irq_name, cpu) = NULL; } +static bool xen_pvspin __initdata = true; + void __init xen_init_spinlocks(void) { /* @@ -417,15 +294,23 @@ void __init xen_init_spinlocks(void) if (xen_hvm_domain()) return; - BUILD_BUG_ON(sizeof(struct xen_spinlock) > sizeof(arch_spinlock_t)); + if (!xen_pvspin) { + printk(KERN_DEBUG "xen: PV spinlocks disabled\n"); + return; + } - pv_lock_ops.spin_is_locked = xen_spin_is_locked; - pv_lock_ops.spin_is_contended = xen_spin_is_contended; - pv_lock_ops.spin_lock = xen_spin_lock; - pv_lock_ops.spin_lock_flags = xen_spin_lock_flags; - pv_lock_ops.spin_trylock = xen_spin_trylock; - pv_lock_ops.spin_unlock = xen_spin_unlock; + static_key_slow_inc(¶virt_ticketlocks_enabled); + + pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning); + pv_lock_ops.unlock_kick = xen_unlock_kick; +} + +static __init int xen_parse_nopvspin(char *arg) +{ + xen_pvspin = false; + return 0; } +early_param("xen_nopvspin", xen_parse_nopvspin); #ifdef CONFIG_XEN_DEBUG_FS @@ -442,37 +327,21 @@ static int __init xen_spinlock_debugfs(void) debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats); - debugfs_create_u32("timeout", 0644, d_spin_debug, &lock_timeout); - - debugfs_create_u64("taken", 0444, d_spin_debug, &spinlock_stats.taken); debugfs_create_u32("taken_slow", 0444, d_spin_debug, - &spinlock_stats.taken_slow); - debugfs_create_u32("taken_slow_nested", 0444, d_spin_debug, - &spinlock_stats.taken_slow_nested); + &spinlock_stats.contention_stats[TAKEN_SLOW]); debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug, - &spinlock_stats.taken_slow_pickup); + &spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]); debugfs_create_u32("taken_slow_spurious", 0444, d_spin_debug, - &spinlock_stats.taken_slow_spurious); - debugfs_create_u32("taken_slow_irqenable", 0444, d_spin_debug, - &spinlock_stats.taken_slow_irqenable); + &spinlock_stats.contention_stats[TAKEN_SLOW_SPURIOUS]); - debugfs_create_u64("released", 0444, d_spin_debug, &spinlock_stats.released); debugfs_create_u32("released_slow", 0444, d_spin_debug, - &spinlock_stats.released_slow); + &spinlock_stats.contention_stats[RELEASED_SLOW]); debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug, - &spinlock_stats.released_slow_kicked); + &spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]); - debugfs_create_u64("time_spinning", 0444, d_spin_debug, - &spinlock_stats.time_spinning); debugfs_create_u64("time_blocked", 0444, d_spin_debug, &spinlock_stats.time_blocked); - debugfs_create_u64("time_total", 0444, d_spin_debug, - &spinlock_stats.time_total); - debugfs_create_u32_array("histo_total", 0444, d_spin_debug, - spinlock_stats.histo_spin_total, HISTO_BUCKETS + 1); - debugfs_create_u32_array("histo_spinning", 0444, d_spin_debug, - spinlock_stats.histo_spin_spinning, HISTO_BUCKETS + 1); debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug, spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1); diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 86782c5d7e2a..95f8c6142328 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -105,9 +105,9 @@ static inline void __init xen_init_apic(void) /* Declare an asm function, along with symbols needed to make it inlineable */ #define DECL_ASM(ret, name, ...) \ - ret name(__VA_ARGS__); \ - extern char name##_end[]; \ - extern char name##_reloc[] \ + __visible ret name(__VA_ARGS__); \ + extern char name##_end[] __visible; \ + extern char name##_reloc[] __visible DECL_ASM(void, xen_irq_enable_direct, void); DECL_ASM(void, xen_irq_disable_direct, void); @@ -115,11 +115,11 @@ DECL_ASM(unsigned long, xen_save_fl_direct, void); DECL_ASM(void, xen_restore_fl_direct, unsigned long); /* These are not functions, and cannot be called normally */ -void xen_iret(void); -void xen_sysexit(void); -void xen_sysret32(void); -void xen_sysret64(void); -void xen_adjust_exception_frame(void); +__visible void xen_iret(void); +__visible void xen_sysexit(void); +__visible void xen_sysret32(void); +__visible void xen_sysret64(void); +__visible void xen_adjust_exception_frame(void); extern int xen_panic_handler_init(void); |