diff options
Diffstat (limited to 'arch/arm')
113 files changed, 3482 insertions, 1329 deletions
diff --git a/arch/arm/boot/dts/Makefile b/arch/arm/boot/dts/Makefile index 86217db2937a..992736b5229b 100644 --- a/arch/arm/boot/dts/Makefile +++ b/arch/arm/boot/dts/Makefile @@ -223,7 +223,7 @@ dtb-$(CONFIG_SOC_IMX25) += \ imx25-eukrea-mbimxsd25-baseboard-dvi-vga.dtb \ imx25-karo-tx25.dtb \ imx25-pdk.dtb -dtb-$(CONFIG_SOC_IMX31) += \ +dtb-$(CONFIG_SOC_IMX27) += \ imx27-apf27.dtb \ imx27-apf27dev.dtb \ imx27-eukrea-mbimxsd27-baseboard.dtb \ diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi index c3255e0c90aa..dbb3f4d2bf84 100644 --- a/arch/arm/boot/dts/am335x-bone-common.dtsi +++ b/arch/arm/boot/dts/am335x-bone-common.dtsi @@ -223,6 +223,25 @@ /include/ "tps65217.dtsi" &tps { + /* + * Configure pmic to enter OFF-state instead of SLEEP-state ("RTC-only + * mode") at poweroff. Most BeagleBone versions do not support RTC-only + * mode and risk hardware damage if this mode is entered. + * + * For details, see linux-omap mailing list May 2015 thread + * [PATCH] ARM: dts: am335x-bone* enable pmic-shutdown-controller + * In particular, messages: + * http://www.spinics.net/lists/linux-omap/msg118585.html + * http://www.spinics.net/lists/linux-omap/msg118615.html + * + * You can override this later with + * &tps { /delete-property/ ti,pmic-shutdown-controller; } + * if you want to use RTC-only mode and made sure you are not affected + * by the hardware problems. (Tip: double-check by performing a current + * measurement after shutdown: it should be less than 1 mA.) + */ + ti,pmic-shutdown-controller; + regulators { dcdc1_reg: regulator@0 { regulator-name = "vdds_dpr"; diff --git a/arch/arm/boot/dts/am335x-boneblack.dts b/arch/arm/boot/dts/am335x-boneblack.dts index 5c42d259fa68..901739fcb85a 100644 --- a/arch/arm/boot/dts/am335x-boneblack.dts +++ b/arch/arm/boot/dts/am335x-boneblack.dts @@ -80,7 +80,3 @@ status = "okay"; }; }; - -&rtc { - system-power-controller; -}; diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts index 87fc7a35e802..156d05efcb70 100644 --- a/arch/arm/boot/dts/am335x-evmsk.dts +++ b/arch/arm/boot/dts/am335x-evmsk.dts @@ -654,7 +654,7 @@ wlcore: wlcore@2 { compatible = "ti,wl1271"; reg = <2>; - interrupt-parent = <&gpio1>; + interrupt-parent = <&gpio0>; interrupts = <31 IRQ_TYPE_LEVEL_HIGH>; /* gpio 31 */ ref-clock-frequency = <38400000>; }; diff --git a/arch/arm/boot/dts/am35xx-clocks.dtsi b/arch/arm/boot/dts/am35xx-clocks.dtsi index 518b8fde88b0..18cc826e9db5 100644 --- a/arch/arm/boot/dts/am35xx-clocks.dtsi +++ b/arch/arm/boot/dts/am35xx-clocks.dtsi @@ -12,7 +12,7 @@ #clock-cells = <0>; compatible = "ti,am35xx-gate-clock"; clocks = <&ipss_ick>; - reg = <0x059c>; + reg = <0x032c>; ti,bit-shift = <1>; }; @@ -20,7 +20,7 @@ #clock-cells = <0>; compatible = "ti,gate-clock"; clocks = <&rmii_ck>; - reg = <0x059c>; + reg = <0x032c>; ti,bit-shift = <9>; }; @@ -28,7 +28,7 @@ #clock-cells = <0>; compatible = "ti,am35xx-gate-clock"; clocks = <&ipss_ick>; - reg = <0x059c>; + reg = <0x032c>; ti,bit-shift = <2>; }; @@ -36,7 +36,7 @@ #clock-cells = <0>; compatible = "ti,gate-clock"; clocks = <&pclk_ck>; - reg = <0x059c>; + reg = <0x032c>; ti,bit-shift = <10>; }; @@ -44,7 +44,7 @@ #clock-cells = <0>; compatible = "ti,am35xx-gate-clock"; clocks = <&ipss_ick>; - reg = <0x059c>; + reg = <0x032c>; ti,bit-shift = <0>; }; @@ -52,7 +52,7 @@ #clock-cells = <0>; compatible = "ti,gate-clock"; clocks = <&sys_ck>; - reg = <0x059c>; + reg = <0x032c>; ti,bit-shift = <8>; }; @@ -60,7 +60,7 @@ #clock-cells = <0>; compatible = "ti,am35xx-gate-clock"; clocks = <&sys_ck>; - reg = <0x059c>; + reg = <0x032c>; ti,bit-shift = <3>; }; }; diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts index 8ae29c955c11..c17097d2c167 100644 --- a/arch/arm/boot/dts/am437x-sk-evm.dts +++ b/arch/arm/boot/dts/am437x-sk-evm.dts @@ -49,7 +49,7 @@ pinctrl-0 = <&matrix_keypad_pins>; debounce-delay-ms = <5>; - col-scan-delay-us = <1500>; + col-scan-delay-us = <5>; row-gpios = <&gpio5 5 GPIO_ACTIVE_HIGH /* Bank5, pin5 */ &gpio5 6 GPIO_ACTIVE_HIGH>; /* Bank5, pin6 */ @@ -473,7 +473,7 @@ interrupt-parent = <&gpio0>; interrupts = <31 0>; - wake-gpios = <&gpio1 28 GPIO_ACTIVE_HIGH>; + reset-gpios = <&gpio1 28 GPIO_ACTIVE_LOW>; touchscreen-size-x = <480>; touchscreen-size-y = <272>; diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts index 15f198e4864d..7128fad991ac 100644 --- a/arch/arm/boot/dts/am57xx-beagle-x15.dts +++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts @@ -18,6 +18,7 @@ aliases { rtc0 = &mcp_rtc; rtc1 = &tps659038_rtc; + rtc2 = &rtc; }; memory { @@ -83,7 +84,7 @@ gpio_fan: gpio_fan { /* Based on 5v 500mA AFB02505HHB */ compatible = "gpio-fan"; - gpios = <&tps659038_gpio 1 GPIO_ACTIVE_HIGH>; + gpios = <&tps659038_gpio 2 GPIO_ACTIVE_HIGH>; gpio-fan,speed-map = <0 0>, <13000 1>; #cooling-cells = <2>; @@ -130,8 +131,8 @@ uart3_pins_default: uart3_pins_default { pinctrl-single,pins = < - 0x248 (PIN_INPUT_SLEW | MUX_MODE0) /* uart3_rxd.rxd */ - 0x24c (PIN_INPUT_SLEW | MUX_MODE0) /* uart3_txd.txd */ + 0x3f8 (PIN_INPUT_SLEW | MUX_MODE2) /* uart2_ctsn.uart3_rxd */ + 0x3fc (PIN_INPUT_SLEW | MUX_MODE1) /* uart2_rtsn.uart3_txd */ >; }; @@ -455,7 +456,7 @@ mcp_rtc: rtc@6f { compatible = "microchip,mcp7941x"; reg = <0x6f>; - interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_LOW>; /* IRQ_SYS_1N */ + interrupts = <GIC_SPI 2 IRQ_TYPE_EDGE_RISING>; /* IRQ_SYS_1N */ pinctrl-names = "default"; pinctrl-0 = <&mcp79410_pins_default>; @@ -478,7 +479,7 @@ &uart3 { status = "okay"; interrupts-extended = <&crossbar_mpu GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>, - <&dra7_pmx_core 0x248>; + <&dra7_pmx_core 0x3f8>; pinctrl-names = "default"; pinctrl-0 = <&uart3_pins_default>; diff --git a/arch/arm/boot/dts/armada-375.dtsi b/arch/arm/boot/dts/armada-375.dtsi index c675257f2377..f076ff856d8b 100644 --- a/arch/arm/boot/dts/armada-375.dtsi +++ b/arch/arm/boot/dts/armada-375.dtsi @@ -69,7 +69,7 @@ mainpll: mainpll { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <2000000000>; + clock-frequency = <1000000000>; }; /* 25 MHz reference crystal */ refclk: oscillator { diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi index ed2dd8ba4080..218a2acd36e5 100644 --- a/arch/arm/boot/dts/armada-38x.dtsi +++ b/arch/arm/boot/dts/armada-38x.dtsi @@ -585,7 +585,7 @@ mainpll: mainpll { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <2000000000>; + clock-frequency = <1000000000>; }; /* 25 MHz reference crystal */ diff --git a/arch/arm/boot/dts/armada-39x.dtsi b/arch/arm/boot/dts/armada-39x.dtsi index 0e85fc15ceda..ecd1318109ba 100644 --- a/arch/arm/boot/dts/armada-39x.dtsi +++ b/arch/arm/boot/dts/armada-39x.dtsi @@ -502,7 +502,7 @@ mainpll: mainpll { compatible = "fixed-clock"; #clock-cells = <0>; - clock-frequency = <2000000000>; + clock-frequency = <1000000000>; }; }; }; diff --git a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts index a2cf2154dcdb..fdd187c55aa5 100644 --- a/arch/arm/boot/dts/armada-xp-linksys-mamba.dts +++ b/arch/arm/boot/dts/armada-xp-linksys-mamba.dts @@ -95,6 +95,11 @@ internal-regs { + rtc@10300 { + /* No crystal connected to the internal RTC */ + status = "disabled"; + }; + /* J10: VCC, NC, RX, NC, TX, GND */ serial@12000 { status = "okay"; diff --git a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts index e3b08fb959e5..990e8a2100f0 100644 --- a/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts +++ b/arch/arm/boot/dts/armada-xp-openblocks-ax3-4.dts @@ -105,6 +105,10 @@ }; internal-regs { + rtc@10300 { + /* No crystal connected to the internal RTC */ + status = "disabled"; + }; serial@12000 { status = "okay"; }; diff --git a/arch/arm/boot/dts/dm816x.dtsi b/arch/arm/boot/dts/dm816x.dtsi index de8427be830a..289806adb343 100644 --- a/arch/arm/boot/dts/dm816x.dtsi +++ b/arch/arm/boot/dts/dm816x.dtsi @@ -382,7 +382,7 @@ ti,hwmods = "usb_otg_hs"; usb0: usb@47401000 { - compatible = "ti,musb-am33xx"; + compatible = "ti,musb-dm816"; reg = <0x47401400 0x400 0x47401000 0x200>; reg-names = "mc", "control"; @@ -422,7 +422,7 @@ }; usb1: usb@47401800 { - compatible = "ti,musb-am33xx"; + compatible = "ti,musb-dm816"; reg = <0x47401c00 0x400 0x47401800 0x200>; reg-names = "mc", "control"; diff --git a/arch/arm/boot/dts/dove-cubox.dts b/arch/arm/boot/dts/dove-cubox.dts index aae7efc09b0b..e6fa251e17b9 100644 --- a/arch/arm/boot/dts/dove-cubox.dts +++ b/arch/arm/boot/dts/dove-cubox.dts @@ -87,6 +87,7 @@ /* connect xtal input to 25MHz reference */ clocks = <&ref25>; + clock-names = "xtal"; /* connect xtal input as source of pll0 and pll1 */ silabs,pll-source = <0 0>, <1 0>; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index 5332b57b4950..f03a091cd076 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -911,7 +911,7 @@ ti,clock-cycles = <16>; reg = <0x4ae07ddc 0x4>, <0x4ae07de0 0x4>, - <0x4ae06014 0x4>, <0x4a003b20 0x8>, + <0x4ae06014 0x4>, <0x4a003b20 0xc>, <0x4ae0c158 0x4>; reg-names = "setup-address", "control-address", "int-address", "efuse-address", @@ -944,7 +944,7 @@ ti,clock-cycles = <16>; reg = <0x4ae07e34 0x4>, <0x4ae07e24 0x4>, - <0x4ae06010 0x4>, <0x4a0025cc 0x8>, + <0x4ae06010 0x4>, <0x4a0025cc 0xc>, <0x4a002470 0x4>; reg-names = "setup-address", "control-address", "int-address", "efuse-address", @@ -977,7 +977,7 @@ ti,clock-cycles = <16>; reg = <0x4ae07e30 0x4>, <0x4ae07e20 0x4>, - <0x4ae06010 0x4>, <0x4a0025e0 0x8>, + <0x4ae06010 0x4>, <0x4a0025e0 0xc>, <0x4a00246c 0x4>; reg-names = "setup-address", "control-address", "int-address", "efuse-address", @@ -1010,7 +1010,7 @@ ti,clock-cycles = <16>; reg = <0x4ae07de4 0x4>, <0x4ae07de8 0x4>, - <0x4ae06010 0x4>, <0x4a003b08 0x8>, + <0x4ae06010 0x4>, <0x4a003b08 0xc>, <0x4ae0c154 0x4>; reg-names = "setup-address", "control-address", "int-address", "efuse-address", @@ -1203,7 +1203,7 @@ status = "disabled"; }; - rtc@48838000 { + rtc: rtc@48838000 { compatible = "ti,am3352-rtc"; reg = <0x48838000 0x100>; interrupts = <GIC_SPI 217 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi index 8de12af7c276..d6b49e5b32e9 100644 --- a/arch/arm/boot/dts/exynos4412-odroid-common.dtsi +++ b/arch/arm/boot/dts/exynos4412-odroid-common.dtsi @@ -9,6 +9,7 @@ #include <dt-bindings/sound/samsung-i2s.h> #include <dt-bindings/input/input.h> +#include <dt-bindings/clock/maxim,max77686.h> #include "exynos4412.dtsi" / { @@ -105,6 +106,8 @@ rtc@10070000 { status = "okay"; + clocks = <&clock CLK_RTC>, <&max77686 MAX77686_CLK_AP>; + clock-names = "rtc", "rtc_src"; }; g2d@10800000 { diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts index 173ffa479ad3..792394dd0f2a 100644 --- a/arch/arm/boot/dts/exynos4412-trats2.dts +++ b/arch/arm/boot/dts/exynos4412-trats2.dts @@ -736,7 +736,7 @@ display-timings { timing-0 { - clock-frequency = <0>; + clock-frequency = <57153600>; hactive = <720>; vactive = <1280>; hfront-porch = <5>; diff --git a/arch/arm/boot/dts/exynos5250-snow.dts b/arch/arm/boot/dts/exynos5250-snow.dts index 2657e842e5a5..1eca97ee4bd6 100644 --- a/arch/arm/boot/dts/exynos5250-snow.dts +++ b/arch/arm/boot/dts/exynos5250-snow.dts @@ -567,6 +567,7 @@ num-slots = <1>; broken-cd; cap-sdio-irq; + keep-power-in-suspend; card-detect-delay = <200>; samsung,dw-mshc-ciu-div = <3>; samsung,dw-mshc-sdr-timing = <2 3>; diff --git a/arch/arm/boot/dts/exynos5420-peach-pit.dts b/arch/arm/boot/dts/exynos5420-peach-pit.dts index 0788d08fb43e..146e71118a72 100644 --- a/arch/arm/boot/dts/exynos5420-peach-pit.dts +++ b/arch/arm/boot/dts/exynos5420-peach-pit.dts @@ -711,6 +711,7 @@ num-slots = <1>; broken-cd; cap-sdio-irq; + keep-power-in-suspend; card-detect-delay = <200>; clock-frequency = <400000000>; samsung,dw-mshc-ciu-div = <1>; diff --git a/arch/arm/boot/dts/exynos5420-trip-points.dtsi b/arch/arm/boot/dts/exynos5420-trip-points.dtsi index 5d31fc140823..2180a0152c9b 100644 --- a/arch/arm/boot/dts/exynos5420-trip-points.dtsi +++ b/arch/arm/boot/dts/exynos5420-trip-points.dtsi @@ -28,7 +28,7 @@ trips { type = "active"; }; cpu-crit-0 { - temperature = <1200000>; /* millicelsius */ + temperature = <120000>; /* millicelsius */ hysteresis = <0>; /* millicelsius */ type = "critical"; }; diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi index f67b23f303c3..45317538bbae 100644 --- a/arch/arm/boot/dts/exynos5420.dtsi +++ b/arch/arm/boot/dts/exynos5420.dtsi @@ -536,6 +536,7 @@ clock-names = "dp"; phys = <&dp_phy>; phy-names = "dp"; + power-domains = <&disp_pd>; }; mipi_phy: video-phy@10040714 { diff --git a/arch/arm/boot/dts/exynos5440-trip-points.dtsi b/arch/arm/boot/dts/exynos5440-trip-points.dtsi index 48adfa8f4300..356e963edf11 100644 --- a/arch/arm/boot/dts/exynos5440-trip-points.dtsi +++ b/arch/arm/boot/dts/exynos5440-trip-points.dtsi @@ -18,7 +18,7 @@ trips { type = "active"; }; cpu-crit-0 { - temperature = <1050000>; /* millicelsius */ + temperature = <105000>; /* millicelsius */ hysteresis = <0>; /* millicelsius */ type = "critical"; }; diff --git a/arch/arm/boot/dts/exynos5800-peach-pi.dts b/arch/arm/boot/dts/exynos5800-peach-pi.dts index 412f41d62686..02eb8b15374f 100644 --- a/arch/arm/boot/dts/exynos5800-peach-pi.dts +++ b/arch/arm/boot/dts/exynos5800-peach-pi.dts @@ -674,6 +674,7 @@ num-slots = <1>; broken-cd; cap-sdio-irq; + keep-power-in-suspend; card-detect-delay = <200>; clock-frequency = <400000000>; samsung,dw-mshc-ciu-div = <1>; diff --git a/arch/arm/boot/dts/imx23-olinuxino.dts b/arch/arm/boot/dts/imx23-olinuxino.dts index 7e6eef2488e8..82045398bf1f 100644 --- a/arch/arm/boot/dts/imx23-olinuxino.dts +++ b/arch/arm/boot/dts/imx23-olinuxino.dts @@ -12,6 +12,7 @@ */ /dts-v1/; +#include <dt-bindings/gpio/gpio.h> #include "imx23.dtsi" / { @@ -93,6 +94,7 @@ ahb@80080000 { usb0: usb@80080000 { + dr_mode = "host"; vbus-supply = <®_usb0_vbus>; status = "okay"; }; @@ -122,7 +124,7 @@ user { label = "green"; - gpios = <&gpio2 1 1>; + gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>; }; }; }; diff --git a/arch/arm/boot/dts/imx25.dtsi b/arch/arm/boot/dts/imx25.dtsi index e4d3aecc4ed2..677f81d9dcd5 100644 --- a/arch/arm/boot/dts/imx25.dtsi +++ b/arch/arm/boot/dts/imx25.dtsi @@ -428,6 +428,7 @@ pwm4: pwm@53fc8000 { compatible = "fsl,imx25-pwm", "fsl,imx27-pwm"; + #pwm-cells = <2>; reg = <0x53fc8000 0x4000>; clocks = <&clks 108>, <&clks 52>; clock-names = "ipg", "per"; diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi index 6951b66d1ab7..bc215e4b75fd 100644 --- a/arch/arm/boot/dts/imx27.dtsi +++ b/arch/arm/boot/dts/imx27.dtsi @@ -533,7 +533,7 @@ fec: ethernet@1002b000 { compatible = "fsl,imx27-fec"; - reg = <0x1002b000 0x4000>; + reg = <0x1002b000 0x1000>; interrupts = <50>; clocks = <&clks IMX27_CLK_FEC_IPG_GATE>, <&clks IMX27_CLK_FEC_AHB_GATE>; diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi index 25e25f82fbae..4e073e854742 100644 --- a/arch/arm/boot/dts/imx28.dtsi +++ b/arch/arm/boot/dts/imx28.dtsi @@ -913,7 +913,7 @@ 80 81 68 69 70 71 72 73 74 75 76 77>; - interrupt-names = "auart4-rx", "aurat4-tx", "spdif-tx", "empty", + interrupt-names = "auart4-rx", "auart4-tx", "spdif-tx", "empty", "saif0", "saif1", "i2c0", "i2c1", "auart0-rx", "auart0-tx", "auart1-rx", "auart1-tx", "auart2-rx", "auart2-tx", "auart3-rx", "auart3-tx"; diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi index 19cc269a08d4..1ce6133b67f5 100644 --- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi +++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi @@ -31,6 +31,7 @@ regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; gpio = <&gpio4 15 0>; + enable-active-high; }; reg_usb_h1_vbus: regulator@1 { @@ -40,6 +41,7 @@ regulator-min-microvolt = <5000000>; regulator-max-microvolt = <5000000>; gpio = <&gpio1 0 0>; + enable-active-high; }; }; diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi index 46b2fed7c319..3b24b12651b2 100644 --- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi @@ -185,7 +185,6 @@ &i2c3 { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_i2c3>; - pinctrl-assert-gpios = <&gpio5 4 GPIO_ACTIVE_HIGH>; status = "okay"; max7310_a: gpio@30 { diff --git a/arch/arm/boot/dts/omap3-devkit8000.dts b/arch/arm/boot/dts/omap3-devkit8000.dts index 134d3f27a8ec..921de6605f07 100644 --- a/arch/arm/boot/dts/omap3-devkit8000.dts +++ b/arch/arm/boot/dts/omap3-devkit8000.dts @@ -110,6 +110,8 @@ nand@0,0 { reg = <0 0 4>; /* CS0, offset 0, IO size 4 */ nand-bus-width = <16>; + gpmc,device-width = <2>; + ti,nand-ecc-opt = "sw"; gpmc,sync-clk-ps = <0>; gpmc,cs-on-ns = <0>; diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index a29315833ecd..5f5e0f3d5b64 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -498,6 +498,8 @@ DRVDD-supply = <&vmmc2>; IOVDD-supply = <&vio>; DVDD-supply = <&vio>; + + ai3x-micbias-vg = <1>; }; tlv320aic3x_aux: tlv320aic3x@19 { @@ -509,6 +511,8 @@ DRVDD-supply = <&vmmc2>; IOVDD-supply = <&vio>; DVDD-supply = <&vio>; + + ai3x-micbias-vg = <2>; }; tsl2563: tsl2563@29 { @@ -828,8 +832,8 @@ touchscreen-fuzz-x = <4>; touchscreen-fuzz-y = <7>; touchscreen-fuzz-pressure = <2>; - touchscreen-max-x = <4096>; - touchscreen-max-y = <4096>; + touchscreen-size-x = <4096>; + touchscreen-size-y = <4096>; touchscreen-max-pressure = <2048>; ti,x-plate-ohms = <280>; diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi index d18a90f5eca3..69a40cfc1f29 100644 --- a/arch/arm/boot/dts/omap3.dtsi +++ b/arch/arm/boot/dts/omap3.dtsi @@ -456,6 +456,7 @@ }; mmu_isp: mmu@480bd400 { + #iommu-cells = <0>; compatible = "ti,omap2-iommu"; reg = <0x480bd400 0x80>; interrupts = <24>; @@ -464,6 +465,7 @@ }; mmu_iva: mmu@5d000000 { + #iommu-cells = <0>; compatible = "ti,omap2-iommu"; reg = <0x5d000000 0x80>; interrupts = <28>; diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi index efe5f737f39b..7d24ae0306b5 100644 --- a/arch/arm/boot/dts/omap5.dtsi +++ b/arch/arm/boot/dts/omap5.dtsi @@ -128,7 +128,7 @@ * hierarchy. */ ocp { - compatible = "ti,omap4-l3-noc", "simple-bus"; + compatible = "ti,omap5-l3-noc", "simple-bus"; #address-cells = <1>; #size-cells = <1>; ranges; diff --git a/arch/arm/boot/dts/r8a7791-koelsch.dts b/arch/arm/boot/dts/r8a7791-koelsch.dts index 74c3212f1f11..824ddab9c3ad 100644 --- a/arch/arm/boot/dts/r8a7791-koelsch.dts +++ b/arch/arm/boot/dts/r8a7791-koelsch.dts @@ -545,7 +545,7 @@ compatible = "adi,adv7511w"; reg = <0x39>; interrupt-parent = <&gpio3>; - interrupts = <29 IRQ_TYPE_EDGE_FALLING>; + interrupts = <29 IRQ_TYPE_LEVEL_LOW>; adi,input-depth = <8>; adi,input-colorspace = "rgb"; diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi index bfd3f1c734b8..2201cd5da3bb 100644 --- a/arch/arm/boot/dts/ste-dbx5x0.dtsi +++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi @@ -1017,23 +1017,6 @@ status = "disabled"; }; - vmmci: regulator-gpio { - compatible = "regulator-gpio"; - - regulator-min-microvolt = <1800000>; - regulator-max-microvolt = <2900000>; - regulator-name = "mmci-reg"; - regulator-type = "voltage"; - - startup-delay-us = <100>; - enable-active-high; - - states = <1800000 0x1 - 2900000 0x0>; - - status = "disabled"; - }; - mcde@a0350000 { compatible = "stericsson,mcde"; reg = <0xa0350000 0x1000>, /* MCDE */ diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi index bf8f0eddc2c0..744c1e3a744d 100644 --- a/arch/arm/boot/dts/ste-href.dtsi +++ b/arch/arm/boot/dts/ste-href.dtsi @@ -111,6 +111,21 @@ pinctrl-1 = <&i2c3_sleep_mode>; }; + vmmci: regulator-gpio { + compatible = "regulator-gpio"; + + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <2900000>; + regulator-name = "mmci-reg"; + regulator-type = "voltage"; + + startup-delay-us = <100>; + enable-active-high; + + states = <1800000 0x1 + 2900000 0x0>; + }; + // External Micro SD slot sdi0_per1@80126000 { arm,primecell-periphid = <0x10480180>; diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts index 206826a855c0..1bc84ebdccaa 100644 --- a/arch/arm/boot/dts/ste-snowball.dts +++ b/arch/arm/boot/dts/ste-snowball.dts @@ -146,8 +146,21 @@ }; vmmci: regulator-gpio { + compatible = "regulator-gpio"; + gpios = <&gpio7 4 0x4>; enable-gpio = <&gpio6 25 0x4>; + + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <2900000>; + regulator-name = "mmci-reg"; + regulator-type = "voltage"; + + startup-delay-us = <100>; + enable-active-high; + + states = <1800000 0x1 + 2900000 0x0>; }; // External Micro SD slot diff --git a/arch/arm/boot/dts/tegra124.dtsi b/arch/arm/boot/dts/tegra124.dtsi index cf01c818b8ea..13cc7ca5e031 100644 --- a/arch/arm/boot/dts/tegra124.dtsi +++ b/arch/arm/boot/dts/tegra124.dtsi @@ -826,7 +826,7 @@ <&tegra_car TEGRA124_CLK_PLL_U>, <&tegra_car TEGRA124_CLK_USBD>; clock-names = "reg", "pll_u", "utmi-pads"; - resets = <&tegra_car 59>, <&tegra_car 22>; + resets = <&tegra_car 22>, <&tegra_car 22>; reset-names = "usb", "utmi-pads"; nvidia,hssync-start-delay = <0>; nvidia,idle-wait-delay = <17>; @@ -838,6 +838,7 @@ nvidia,hssquelch-level = <2>; nvidia,hsdiscon-level = <5>; nvidia,xcvr-hsslew = <12>; + nvidia,has-utmi-pad-registers; status = "disabled"; }; @@ -862,7 +863,7 @@ <&tegra_car TEGRA124_CLK_PLL_U>, <&tegra_car TEGRA124_CLK_USBD>; clock-names = "reg", "pll_u", "utmi-pads"; - resets = <&tegra_car 22>, <&tegra_car 22>; + resets = <&tegra_car 58>, <&tegra_car 22>; reset-names = "usb", "utmi-pads"; nvidia,hssync-start-delay = <0>; nvidia,idle-wait-delay = <17>; @@ -874,7 +875,6 @@ nvidia,hssquelch-level = <2>; nvidia,hsdiscon-level = <5>; nvidia,xcvr-hsslew = <12>; - nvidia,has-utmi-pad-registers; status = "disabled"; }; @@ -899,7 +899,7 @@ <&tegra_car TEGRA124_CLK_PLL_U>, <&tegra_car TEGRA124_CLK_USBD>; clock-names = "reg", "pll_u", "utmi-pads"; - resets = <&tegra_car 58>, <&tegra_car 22>; + resets = <&tegra_car 59>, <&tegra_car 22>; reset-names = "usb", "utmi-pads"; nvidia,hssync-start-delay = <0>; nvidia,idle-wait-delay = <17>; diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts index 7a2aeacd62c0..107395c32d82 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts @@ -191,6 +191,7 @@ compatible = "arm,cortex-a15-pmu"; interrupts = <0 68 4>, <0 69 4>; + interrupt-affinity = <&cpu0>, <&cpu1>; }; oscclk6a: oscclk6a { diff --git a/arch/arm/boot/dts/vexpress-v2p-ca9.dts b/arch/arm/boot/dts/vexpress-v2p-ca9.dts index 23662b5a5e9d..d949facba376 100644 --- a/arch/arm/boot/dts/vexpress-v2p-ca9.dts +++ b/arch/arm/boot/dts/vexpress-v2p-ca9.dts @@ -33,28 +33,28 @@ #address-cells = <1>; #size-cells = <0>; - cpu@0 { + A9_0: cpu@0 { device_type = "cpu"; compatible = "arm,cortex-a9"; reg = <0>; next-level-cache = <&L2>; }; - cpu@1 { + A9_1: cpu@1 { device_type = "cpu"; compatible = "arm,cortex-a9"; reg = <1>; next-level-cache = <&L2>; }; - cpu@2 { + A9_2: cpu@2 { device_type = "cpu"; compatible = "arm,cortex-a9"; reg = <2>; next-level-cache = <&L2>; }; - cpu@3 { + A9_3: cpu@3 { device_type = "cpu"; compatible = "arm,cortex-a9"; reg = <3>; @@ -170,6 +170,7 @@ compatible = "arm,pl310-cache"; reg = <0x1e00a000 0x1000>; interrupts = <0 43 4>; + cache-unified; cache-level = <2>; arm,data-latency = <1 1 1>; arm,tag-latency = <1 1 1>; @@ -181,6 +182,8 @@ <0 61 4>, <0 62 4>, <0 63 4>; + interrupt-affinity = <&A9_0>, <&A9_1>, <&A9_2>, <&A9_3>; + }; dcc { diff --git a/arch/arm/boot/dts/zynq-7000.dtsi b/arch/arm/boot/dts/zynq-7000.dtsi index a5cd2eda3edf..9ea54b3dba09 100644 --- a/arch/arm/boot/dts/zynq-7000.dtsi +++ b/arch/arm/boot/dts/zynq-7000.dtsi @@ -193,7 +193,7 @@ }; gem0: ethernet@e000b000 { - compatible = "cdns,gem"; + compatible = "cdns,zynq-gem"; reg = <0xe000b000 0x1000>; status = "disabled"; interrupts = <0 22 4>; @@ -204,7 +204,7 @@ }; gem1: ethernet@e000c000 { - compatible = "cdns,gem"; + compatible = "cdns,zynq-gem"; reg = <0xe000c000 0x1000>; status = "disabled"; interrupts = <0 45 4>; diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c index 5cc779c8e9c6..93ee70dbbdd3 100644 --- a/arch/arm/common/sa1111.c +++ b/arch/arm/common/sa1111.c @@ -501,8 +501,8 @@ static int sa1111_setup_irq(struct sa1111 *sachip, unsigned irq_base) * Register SA1111 interrupt */ irq_set_irq_type(sachip->irq, IRQ_TYPE_EDGE_RISING); - irq_set_handler_data(sachip->irq, sachip); - irq_set_chained_handler(sachip->irq, sa1111_irq_handler); + irq_set_chained_handler_and_data(sachip->irq, sa1111_irq_handler, + sachip); dev_info(sachip->dev, "Providing IRQ%u-%u\n", sachip->irq_base, sachip->irq_base + SA1111_IRQ_NR - 1); @@ -836,8 +836,7 @@ static void __sa1111_remove(struct sa1111 *sachip) clk_unprepare(sachip->clk); if (sachip->irq != NO_IRQ) { - irq_set_chained_handler(sachip->irq, NULL); - irq_set_handler_data(sachip->irq, NULL); + irq_set_chained_handler_and_data(sachip->irq, NULL, NULL); irq_free_descs(sachip->irq_base, SA1111_IRQ_NR); release_mem_region(sachip->phys + SA1111_INTC, 512); diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig index ab86655c1f4b..fbbb1915c6a9 100644 --- a/arch/arm/configs/multi_v7_defconfig +++ b/arch/arm/configs/multi_v7_defconfig @@ -39,11 +39,14 @@ CONFIG_ARCH_HIP04=y CONFIG_ARCH_KEYSTONE=y CONFIG_ARCH_MESON=y CONFIG_ARCH_MXC=y +CONFIG_SOC_IMX50=y CONFIG_SOC_IMX51=y CONFIG_SOC_IMX53=y CONFIG_SOC_IMX6Q=y CONFIG_SOC_IMX6SL=y +CONFIG_SOC_IMX6SX=y CONFIG_SOC_VF610=y +CONFIG_SOC_LS1021A=y CONFIG_ARCH_OMAP3=y CONFIG_ARCH_OMAP4=y CONFIG_SOC_OMAP5=y @@ -426,7 +429,7 @@ CONFIG_USB_EHCI_EXYNOS=y CONFIG_USB_EHCI_TEGRA=y CONFIG_USB_EHCI_HCD_STI=y CONFIG_USB_EHCI_HCD_PLATFORM=y -CONFIG_USB_ISP1760_HCD=y +CONFIG_USB_ISP1760=y CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_STI=y CONFIG_USB_OHCI_HCD_PLATFORM=y diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 9ff7b54b2a83..3743ca221d40 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -393,7 +393,7 @@ CONFIG_TI_EDMA=y CONFIG_DMA_OMAP=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_EXTCON=m -CONFIG_EXTCON_GPIO=m +CONFIG_EXTCON_USB_GPIO=m CONFIG_EXTCON_PALMAS=m CONFIG_TI_EMIF=m CONFIG_PWM=y diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig index 8da2207b0072..27ed1b1cd1d7 100644 --- a/arch/arm/crypto/Kconfig +++ b/arch/arm/crypto/Kconfig @@ -53,20 +53,13 @@ config CRYPTO_SHA256_ARM SHA-256 secure hash standard (DFIPS 180-2) implemented using optimized ARM assembler and NEON, when available. -config CRYPTO_SHA512_ARM_NEON - tristate "SHA384 and SHA512 digest algorithm (ARM NEON)" - depends on KERNEL_MODE_NEON - select CRYPTO_SHA512 +config CRYPTO_SHA512_ARM + tristate "SHA-384/512 digest algorithm (ARM-asm and NEON)" select CRYPTO_HASH + depends on !CPU_V7M help SHA-512 secure hash standard (DFIPS 180-2) implemented - using ARM NEON instructions, when available. - - This version of SHA implements a 512 bit hash with 256 bits of - security against collision attacks. - - This code also includes SHA-384, a 384 bit hash with 192 bits - of security against collision attacks. + using optimized ARM assembler and NEON, when available. config CRYPTO_AES_ARM tristate "AES cipher algorithms (ARM-asm)" diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile index 6ea828241fcb..fc5150702b64 100644 --- a/arch/arm/crypto/Makefile +++ b/arch/arm/crypto/Makefile @@ -7,7 +7,7 @@ obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o -obj-$(CONFIG_CRYPTO_SHA512_ARM_NEON) += sha512-arm-neon.o +obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o @@ -30,7 +30,8 @@ sha1-arm-y := sha1-armv4-large.o sha1_glue.o sha1-arm-neon-y := sha1-armv7-neon.o sha1_neon_glue.o sha256-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha256_neon_glue.o sha256-arm-y := sha256-core.o sha256_glue.o $(sha256-arm-neon-y) -sha512-arm-neon-y := sha512-armv7-neon.o sha512_neon_glue.o +sha512-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha512-neon-glue.o +sha512-arm-y := sha512-core.o sha512-glue.o $(sha512-arm-neon-y) sha1-arm-ce-y := sha1-ce-core.o sha1-ce-glue.o sha2-arm-ce-y := sha2-ce-core.o sha2-ce-glue.o aes-arm-ce-y := aes-ce-core.o aes-ce-glue.o @@ -45,4 +46,7 @@ $(src)/aesbs-core.S_shipped: $(src)/bsaes-armv7.pl $(src)/sha256-core.S_shipped: $(src)/sha256-armv4.pl $(call cmd,perl) -.PRECIOUS: $(obj)/aesbs-core.S $(obj)/sha256-core.S +$(src)/sha512-core.S_shipped: $(src)/sha512-armv4.pl + $(call cmd,perl) + +.PRECIOUS: $(obj)/aesbs-core.S $(obj)/sha256-core.S $(obj)/sha512-core.S diff --git a/arch/arm/crypto/aes-ce-core.S b/arch/arm/crypto/aes-ce-core.S index 8cfa468ee570..987aa632c9f0 100644 --- a/arch/arm/crypto/aes-ce-core.S +++ b/arch/arm/crypto/aes-ce-core.S @@ -101,15 +101,14 @@ \dround q10, q11 blo 0f @ AES-128: 10 rounds vld1.8 {q10-q11}, [ip]! - beq 1f @ AES-192: 12 rounds \dround q12, q13 + beq 1f @ AES-192: 12 rounds vld1.8 {q12-q13}, [ip] \dround q10, q11 0: \fround q12, q13, q14 bx lr -1: \dround q12, q13 - \fround q10, q11, q14 +1: \fround q10, q11, q14 bx lr .endm @@ -122,8 +121,8 @@ * q2 : third in/output block (_3x version only) * q8 : first round key * q9 : secound round key - * ip : address of 3rd round key * q14 : final round key + * r2 : address of round key array * r3 : number of rounds */ .align 6 diff --git a/arch/arm/crypto/sha512-armv4.pl b/arch/arm/crypto/sha512-armv4.pl new file mode 100644 index 000000000000..a2b11a844357 --- /dev/null +++ b/arch/arm/crypto/sha512-armv4.pl @@ -0,0 +1,649 @@ +#!/usr/bin/env perl + +# ==================================================================== +# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL +# project. The module is, however, dual licensed under OpenSSL and +# CRYPTOGAMS licenses depending on where you obtain it. For further +# details see http://www.openssl.org/~appro/cryptogams/. +# +# Permission to use under GPL terms is granted. +# ==================================================================== + +# SHA512 block procedure for ARMv4. September 2007. + +# This code is ~4.5 (four and a half) times faster than code generated +# by gcc 3.4 and it spends ~72 clock cycles per byte [on single-issue +# Xscale PXA250 core]. +# +# July 2010. +# +# Rescheduling for dual-issue pipeline resulted in 6% improvement on +# Cortex A8 core and ~40 cycles per processed byte. + +# February 2011. +# +# Profiler-assisted and platform-specific optimization resulted in 7% +# improvement on Coxtex A8 core and ~38 cycles per byte. + +# March 2011. +# +# Add NEON implementation. On Cortex A8 it was measured to process +# one byte in 23.3 cycles or ~60% faster than integer-only code. + +# August 2012. +# +# Improve NEON performance by 12% on Snapdragon S4. In absolute +# terms it's 22.6 cycles per byte, which is disappointing result. +# Technical writers asserted that 3-way S4 pipeline can sustain +# multiple NEON instructions per cycle, but dual NEON issue could +# not be observed, see http://www.openssl.org/~appro/Snapdragon-S4.html +# for further details. On side note Cortex-A15 processes one byte in +# 16 cycles. + +# Byte order [in]dependence. ========================================= +# +# Originally caller was expected to maintain specific *dword* order in +# h[0-7], namely with most significant dword at *lower* address, which +# was reflected in below two parameters as 0 and 4. Now caller is +# expected to maintain native byte order for whole 64-bit values. +$hi="HI"; +$lo="LO"; +# ==================================================================== + +while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {} +open STDOUT,">$output"; + +$ctx="r0"; # parameter block +$inp="r1"; +$len="r2"; + +$Tlo="r3"; +$Thi="r4"; +$Alo="r5"; +$Ahi="r6"; +$Elo="r7"; +$Ehi="r8"; +$t0="r9"; +$t1="r10"; +$t2="r11"; +$t3="r12"; +############ r13 is stack pointer +$Ktbl="r14"; +############ r15 is program counter + +$Aoff=8*0; +$Boff=8*1; +$Coff=8*2; +$Doff=8*3; +$Eoff=8*4; +$Foff=8*5; +$Goff=8*6; +$Hoff=8*7; +$Xoff=8*8; + +sub BODY_00_15() { +my $magic = shift; +$code.=<<___; + @ Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41)) + @ LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23 + @ HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23 + mov $t0,$Elo,lsr#14 + str $Tlo,[sp,#$Xoff+0] + mov $t1,$Ehi,lsr#14 + str $Thi,[sp,#$Xoff+4] + eor $t0,$t0,$Ehi,lsl#18 + ldr $t2,[sp,#$Hoff+0] @ h.lo + eor $t1,$t1,$Elo,lsl#18 + ldr $t3,[sp,#$Hoff+4] @ h.hi + eor $t0,$t0,$Elo,lsr#18 + eor $t1,$t1,$Ehi,lsr#18 + eor $t0,$t0,$Ehi,lsl#14 + eor $t1,$t1,$Elo,lsl#14 + eor $t0,$t0,$Ehi,lsr#9 + eor $t1,$t1,$Elo,lsr#9 + eor $t0,$t0,$Elo,lsl#23 + eor $t1,$t1,$Ehi,lsl#23 @ Sigma1(e) + adds $Tlo,$Tlo,$t0 + ldr $t0,[sp,#$Foff+0] @ f.lo + adc $Thi,$Thi,$t1 @ T += Sigma1(e) + ldr $t1,[sp,#$Foff+4] @ f.hi + adds $Tlo,$Tlo,$t2 + ldr $t2,[sp,#$Goff+0] @ g.lo + adc $Thi,$Thi,$t3 @ T += h + ldr $t3,[sp,#$Goff+4] @ g.hi + + eor $t0,$t0,$t2 + str $Elo,[sp,#$Eoff+0] + eor $t1,$t1,$t3 + str $Ehi,[sp,#$Eoff+4] + and $t0,$t0,$Elo + str $Alo,[sp,#$Aoff+0] + and $t1,$t1,$Ehi + str $Ahi,[sp,#$Aoff+4] + eor $t0,$t0,$t2 + ldr $t2,[$Ktbl,#$lo] @ K[i].lo + eor $t1,$t1,$t3 @ Ch(e,f,g) + ldr $t3,[$Ktbl,#$hi] @ K[i].hi + + adds $Tlo,$Tlo,$t0 + ldr $Elo,[sp,#$Doff+0] @ d.lo + adc $Thi,$Thi,$t1 @ T += Ch(e,f,g) + ldr $Ehi,[sp,#$Doff+4] @ d.hi + adds $Tlo,$Tlo,$t2 + and $t0,$t2,#0xff + adc $Thi,$Thi,$t3 @ T += K[i] + adds $Elo,$Elo,$Tlo + ldr $t2,[sp,#$Boff+0] @ b.lo + adc $Ehi,$Ehi,$Thi @ d += T + teq $t0,#$magic + + ldr $t3,[sp,#$Coff+0] @ c.lo +#if __ARM_ARCH__>=7 + it eq @ Thumb2 thing, sanity check in ARM +#endif + orreq $Ktbl,$Ktbl,#1 + @ Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39)) + @ LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25 + @ HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25 + mov $t0,$Alo,lsr#28 + mov $t1,$Ahi,lsr#28 + eor $t0,$t0,$Ahi,lsl#4 + eor $t1,$t1,$Alo,lsl#4 + eor $t0,$t0,$Ahi,lsr#2 + eor $t1,$t1,$Alo,lsr#2 + eor $t0,$t0,$Alo,lsl#30 + eor $t1,$t1,$Ahi,lsl#30 + eor $t0,$t0,$Ahi,lsr#7 + eor $t1,$t1,$Alo,lsr#7 + eor $t0,$t0,$Alo,lsl#25 + eor $t1,$t1,$Ahi,lsl#25 @ Sigma0(a) + adds $Tlo,$Tlo,$t0 + and $t0,$Alo,$t2 + adc $Thi,$Thi,$t1 @ T += Sigma0(a) + + ldr $t1,[sp,#$Boff+4] @ b.hi + orr $Alo,$Alo,$t2 + ldr $t2,[sp,#$Coff+4] @ c.hi + and $Alo,$Alo,$t3 + and $t3,$Ahi,$t1 + orr $Ahi,$Ahi,$t1 + orr $Alo,$Alo,$t0 @ Maj(a,b,c).lo + and $Ahi,$Ahi,$t2 + adds $Alo,$Alo,$Tlo + orr $Ahi,$Ahi,$t3 @ Maj(a,b,c).hi + sub sp,sp,#8 + adc $Ahi,$Ahi,$Thi @ h += T + tst $Ktbl,#1 + add $Ktbl,$Ktbl,#8 +___ +} +$code=<<___; +#ifndef __KERNEL__ +# include "arm_arch.h" +# define VFP_ABI_PUSH vstmdb sp!,{d8-d15} +# define VFP_ABI_POP vldmia sp!,{d8-d15} +#else +# define __ARM_ARCH__ __LINUX_ARM_ARCH__ +# define __ARM_MAX_ARCH__ 7 +# define VFP_ABI_PUSH +# define VFP_ABI_POP +#endif + +#ifdef __ARMEL__ +# define LO 0 +# define HI 4 +# define WORD64(hi0,lo0,hi1,lo1) .word lo0,hi0, lo1,hi1 +#else +# define HI 0 +# define LO 4 +# define WORD64(hi0,lo0,hi1,lo1) .word hi0,lo0, hi1,lo1 +#endif + +.text +#if __ARM_ARCH__<7 +.code 32 +#else +.syntax unified +# ifdef __thumb2__ +# define adrl adr +.thumb +# else +.code 32 +# endif +#endif + +.type K512,%object +.align 5 +K512: +WORD64(0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd) +WORD64(0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc) +WORD64(0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019) +WORD64(0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118) +WORD64(0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe) +WORD64(0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2) +WORD64(0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1) +WORD64(0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694) +WORD64(0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3) +WORD64(0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65) +WORD64(0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483) +WORD64(0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5) +WORD64(0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210) +WORD64(0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4) +WORD64(0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725) +WORD64(0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70) +WORD64(0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926) +WORD64(0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df) +WORD64(0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8) +WORD64(0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b) +WORD64(0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001) +WORD64(0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30) +WORD64(0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910) +WORD64(0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8) +WORD64(0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53) +WORD64(0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8) +WORD64(0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb) +WORD64(0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3) +WORD64(0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60) +WORD64(0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec) +WORD64(0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9) +WORD64(0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b) +WORD64(0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207) +WORD64(0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178) +WORD64(0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6) +WORD64(0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b) +WORD64(0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493) +WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c) +WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a) +WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817) +.size K512,.-K512 +#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) +.LOPENSSL_armcap: +.word OPENSSL_armcap_P-sha512_block_data_order +.skip 32-4 +#else +.skip 32 +#endif + +.global sha512_block_data_order +.type sha512_block_data_order,%function +sha512_block_data_order: +#if __ARM_ARCH__<7 + sub r3,pc,#8 @ sha512_block_data_order +#else + adr r3,sha512_block_data_order +#endif +#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) + ldr r12,.LOPENSSL_armcap + ldr r12,[r3,r12] @ OPENSSL_armcap_P + tst r12,#1 + bne .LNEON +#endif + add $len,$inp,$len,lsl#7 @ len to point at the end of inp + stmdb sp!,{r4-r12,lr} + sub $Ktbl,r3,#672 @ K512 + sub sp,sp,#9*8 + + ldr $Elo,[$ctx,#$Eoff+$lo] + ldr $Ehi,[$ctx,#$Eoff+$hi] + ldr $t0, [$ctx,#$Goff+$lo] + ldr $t1, [$ctx,#$Goff+$hi] + ldr $t2, [$ctx,#$Hoff+$lo] + ldr $t3, [$ctx,#$Hoff+$hi] +.Loop: + str $t0, [sp,#$Goff+0] + str $t1, [sp,#$Goff+4] + str $t2, [sp,#$Hoff+0] + str $t3, [sp,#$Hoff+4] + ldr $Alo,[$ctx,#$Aoff+$lo] + ldr $Ahi,[$ctx,#$Aoff+$hi] + ldr $Tlo,[$ctx,#$Boff+$lo] + ldr $Thi,[$ctx,#$Boff+$hi] + ldr $t0, [$ctx,#$Coff+$lo] + ldr $t1, [$ctx,#$Coff+$hi] + ldr $t2, [$ctx,#$Doff+$lo] + ldr $t3, [$ctx,#$Doff+$hi] + str $Tlo,[sp,#$Boff+0] + str $Thi,[sp,#$Boff+4] + str $t0, [sp,#$Coff+0] + str $t1, [sp,#$Coff+4] + str $t2, [sp,#$Doff+0] + str $t3, [sp,#$Doff+4] + ldr $Tlo,[$ctx,#$Foff+$lo] + ldr $Thi,[$ctx,#$Foff+$hi] + str $Tlo,[sp,#$Foff+0] + str $Thi,[sp,#$Foff+4] + +.L00_15: +#if __ARM_ARCH__<7 + ldrb $Tlo,[$inp,#7] + ldrb $t0, [$inp,#6] + ldrb $t1, [$inp,#5] + ldrb $t2, [$inp,#4] + ldrb $Thi,[$inp,#3] + ldrb $t3, [$inp,#2] + orr $Tlo,$Tlo,$t0,lsl#8 + ldrb $t0, [$inp,#1] + orr $Tlo,$Tlo,$t1,lsl#16 + ldrb $t1, [$inp],#8 + orr $Tlo,$Tlo,$t2,lsl#24 + orr $Thi,$Thi,$t3,lsl#8 + orr $Thi,$Thi,$t0,lsl#16 + orr $Thi,$Thi,$t1,lsl#24 +#else + ldr $Tlo,[$inp,#4] + ldr $Thi,[$inp],#8 +#ifdef __ARMEL__ + rev $Tlo,$Tlo + rev $Thi,$Thi +#endif +#endif +___ + &BODY_00_15(0x94); +$code.=<<___; + tst $Ktbl,#1 + beq .L00_15 + ldr $t0,[sp,#`$Xoff+8*(16-1)`+0] + ldr $t1,[sp,#`$Xoff+8*(16-1)`+4] + bic $Ktbl,$Ktbl,#1 +.L16_79: + @ sigma0(x) (ROTR((x),1) ^ ROTR((x),8) ^ ((x)>>7)) + @ LO lo>>1^hi<<31 ^ lo>>8^hi<<24 ^ lo>>7^hi<<25 + @ HI hi>>1^lo<<31 ^ hi>>8^lo<<24 ^ hi>>7 + mov $Tlo,$t0,lsr#1 + ldr $t2,[sp,#`$Xoff+8*(16-14)`+0] + mov $Thi,$t1,lsr#1 + ldr $t3,[sp,#`$Xoff+8*(16-14)`+4] + eor $Tlo,$Tlo,$t1,lsl#31 + eor $Thi,$Thi,$t0,lsl#31 + eor $Tlo,$Tlo,$t0,lsr#8 + eor $Thi,$Thi,$t1,lsr#8 + eor $Tlo,$Tlo,$t1,lsl#24 + eor $Thi,$Thi,$t0,lsl#24 + eor $Tlo,$Tlo,$t0,lsr#7 + eor $Thi,$Thi,$t1,lsr#7 + eor $Tlo,$Tlo,$t1,lsl#25 + + @ sigma1(x) (ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6)) + @ LO lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26 + @ HI hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6 + mov $t0,$t2,lsr#19 + mov $t1,$t3,lsr#19 + eor $t0,$t0,$t3,lsl#13 + eor $t1,$t1,$t2,lsl#13 + eor $t0,$t0,$t3,lsr#29 + eor $t1,$t1,$t2,lsr#29 + eor $t0,$t0,$t2,lsl#3 + eor $t1,$t1,$t3,lsl#3 + eor $t0,$t0,$t2,lsr#6 + eor $t1,$t1,$t3,lsr#6 + ldr $t2,[sp,#`$Xoff+8*(16-9)`+0] + eor $t0,$t0,$t3,lsl#26 + + ldr $t3,[sp,#`$Xoff+8*(16-9)`+4] + adds $Tlo,$Tlo,$t0 + ldr $t0,[sp,#`$Xoff+8*16`+0] + adc $Thi,$Thi,$t1 + + ldr $t1,[sp,#`$Xoff+8*16`+4] + adds $Tlo,$Tlo,$t2 + adc $Thi,$Thi,$t3 + adds $Tlo,$Tlo,$t0 + adc $Thi,$Thi,$t1 +___ + &BODY_00_15(0x17); +$code.=<<___; +#if __ARM_ARCH__>=7 + ittt eq @ Thumb2 thing, sanity check in ARM +#endif + ldreq $t0,[sp,#`$Xoff+8*(16-1)`+0] + ldreq $t1,[sp,#`$Xoff+8*(16-1)`+4] + beq .L16_79 + bic $Ktbl,$Ktbl,#1 + + ldr $Tlo,[sp,#$Boff+0] + ldr $Thi,[sp,#$Boff+4] + ldr $t0, [$ctx,#$Aoff+$lo] + ldr $t1, [$ctx,#$Aoff+$hi] + ldr $t2, [$ctx,#$Boff+$lo] + ldr $t3, [$ctx,#$Boff+$hi] + adds $t0,$Alo,$t0 + str $t0, [$ctx,#$Aoff+$lo] + adc $t1,$Ahi,$t1 + str $t1, [$ctx,#$Aoff+$hi] + adds $t2,$Tlo,$t2 + str $t2, [$ctx,#$Boff+$lo] + adc $t3,$Thi,$t3 + str $t3, [$ctx,#$Boff+$hi] + + ldr $Alo,[sp,#$Coff+0] + ldr $Ahi,[sp,#$Coff+4] + ldr $Tlo,[sp,#$Doff+0] + ldr $Thi,[sp,#$Doff+4] + ldr $t0, [$ctx,#$Coff+$lo] + ldr $t1, [$ctx,#$Coff+$hi] + ldr $t2, [$ctx,#$Doff+$lo] + ldr $t3, [$ctx,#$Doff+$hi] + adds $t0,$Alo,$t0 + str $t0, [$ctx,#$Coff+$lo] + adc $t1,$Ahi,$t1 + str $t1, [$ctx,#$Coff+$hi] + adds $t2,$Tlo,$t2 + str $t2, [$ctx,#$Doff+$lo] + adc $t3,$Thi,$t3 + str $t3, [$ctx,#$Doff+$hi] + + ldr $Tlo,[sp,#$Foff+0] + ldr $Thi,[sp,#$Foff+4] + ldr $t0, [$ctx,#$Eoff+$lo] + ldr $t1, [$ctx,#$Eoff+$hi] + ldr $t2, [$ctx,#$Foff+$lo] + ldr $t3, [$ctx,#$Foff+$hi] + adds $Elo,$Elo,$t0 + str $Elo,[$ctx,#$Eoff+$lo] + adc $Ehi,$Ehi,$t1 + str $Ehi,[$ctx,#$Eoff+$hi] + adds $t2,$Tlo,$t2 + str $t2, [$ctx,#$Foff+$lo] + adc $t3,$Thi,$t3 + str $t3, [$ctx,#$Foff+$hi] + + ldr $Alo,[sp,#$Goff+0] + ldr $Ahi,[sp,#$Goff+4] + ldr $Tlo,[sp,#$Hoff+0] + ldr $Thi,[sp,#$Hoff+4] + ldr $t0, [$ctx,#$Goff+$lo] + ldr $t1, [$ctx,#$Goff+$hi] + ldr $t2, [$ctx,#$Hoff+$lo] + ldr $t3, [$ctx,#$Hoff+$hi] + adds $t0,$Alo,$t0 + str $t0, [$ctx,#$Goff+$lo] + adc $t1,$Ahi,$t1 + str $t1, [$ctx,#$Goff+$hi] + adds $t2,$Tlo,$t2 + str $t2, [$ctx,#$Hoff+$lo] + adc $t3,$Thi,$t3 + str $t3, [$ctx,#$Hoff+$hi] + + add sp,sp,#640 + sub $Ktbl,$Ktbl,#640 + + teq $inp,$len + bne .Loop + + add sp,sp,#8*9 @ destroy frame +#if __ARM_ARCH__>=5 + ldmia sp!,{r4-r12,pc} +#else + ldmia sp!,{r4-r12,lr} + tst lr,#1 + moveq pc,lr @ be binary compatible with V4, yet + bx lr @ interoperable with Thumb ISA:-) +#endif +.size sha512_block_data_order,.-sha512_block_data_order +___ + +{ +my @Sigma0=(28,34,39); +my @Sigma1=(14,18,41); +my @sigma0=(1, 8, 7); +my @sigma1=(19,61,6); + +my $Ktbl="r3"; +my $cnt="r12"; # volatile register known as ip, intra-procedure-call scratch + +my @X=map("d$_",(0..15)); +my @V=($A,$B,$C,$D,$E,$F,$G,$H)=map("d$_",(16..23)); + +sub NEON_00_15() { +my $i=shift; +my ($a,$b,$c,$d,$e,$f,$g,$h)=@_; +my ($t0,$t1,$t2,$T1,$K,$Ch,$Maj)=map("d$_",(24..31)); # temps + +$code.=<<___ if ($i<16 || $i&1); + vshr.u64 $t0,$e,#@Sigma1[0] @ $i +#if $i<16 + vld1.64 {@X[$i%16]},[$inp]! @ handles unaligned +#endif + vshr.u64 $t1,$e,#@Sigma1[1] +#if $i>0 + vadd.i64 $a,$Maj @ h+=Maj from the past +#endif + vshr.u64 $t2,$e,#@Sigma1[2] +___ +$code.=<<___; + vld1.64 {$K},[$Ktbl,:64]! @ K[i++] + vsli.64 $t0,$e,#`64-@Sigma1[0]` + vsli.64 $t1,$e,#`64-@Sigma1[1]` + vmov $Ch,$e + vsli.64 $t2,$e,#`64-@Sigma1[2]` +#if $i<16 && defined(__ARMEL__) + vrev64.8 @X[$i],@X[$i] +#endif + veor $t1,$t0 + vbsl $Ch,$f,$g @ Ch(e,f,g) + vshr.u64 $t0,$a,#@Sigma0[0] + veor $t2,$t1 @ Sigma1(e) + vadd.i64 $T1,$Ch,$h + vshr.u64 $t1,$a,#@Sigma0[1] + vsli.64 $t0,$a,#`64-@Sigma0[0]` + vadd.i64 $T1,$t2 + vshr.u64 $t2,$a,#@Sigma0[2] + vadd.i64 $K,@X[$i%16] + vsli.64 $t1,$a,#`64-@Sigma0[1]` + veor $Maj,$a,$b + vsli.64 $t2,$a,#`64-@Sigma0[2]` + veor $h,$t0,$t1 + vadd.i64 $T1,$K + vbsl $Maj,$c,$b @ Maj(a,b,c) + veor $h,$t2 @ Sigma0(a) + vadd.i64 $d,$T1 + vadd.i64 $Maj,$T1 + @ vadd.i64 $h,$Maj +___ +} + +sub NEON_16_79() { +my $i=shift; + +if ($i&1) { &NEON_00_15($i,@_); return; } + +# 2x-vectorized, therefore runs every 2nd round +my @X=map("q$_",(0..7)); # view @X as 128-bit vector +my ($t0,$t1,$s0,$s1) = map("q$_",(12..15)); # temps +my ($d0,$d1,$d2) = map("d$_",(24..26)); # temps from NEON_00_15 +my $e=@_[4]; # $e from NEON_00_15 +$i /= 2; +$code.=<<___; + vshr.u64 $t0,@X[($i+7)%8],#@sigma1[0] + vshr.u64 $t1,@X[($i+7)%8],#@sigma1[1] + vadd.i64 @_[0],d30 @ h+=Maj from the past + vshr.u64 $s1,@X[($i+7)%8],#@sigma1[2] + vsli.64 $t0,@X[($i+7)%8],#`64-@sigma1[0]` + vext.8 $s0,@X[$i%8],@X[($i+1)%8],#8 @ X[i+1] + vsli.64 $t1,@X[($i+7)%8],#`64-@sigma1[1]` + veor $s1,$t0 + vshr.u64 $t0,$s0,#@sigma0[0] + veor $s1,$t1 @ sigma1(X[i+14]) + vshr.u64 $t1,$s0,#@sigma0[1] + vadd.i64 @X[$i%8],$s1 + vshr.u64 $s1,$s0,#@sigma0[2] + vsli.64 $t0,$s0,#`64-@sigma0[0]` + vsli.64 $t1,$s0,#`64-@sigma0[1]` + vext.8 $s0,@X[($i+4)%8],@X[($i+5)%8],#8 @ X[i+9] + veor $s1,$t0 + vshr.u64 $d0,$e,#@Sigma1[0] @ from NEON_00_15 + vadd.i64 @X[$i%8],$s0 + vshr.u64 $d1,$e,#@Sigma1[1] @ from NEON_00_15 + veor $s1,$t1 @ sigma0(X[i+1]) + vshr.u64 $d2,$e,#@Sigma1[2] @ from NEON_00_15 + vadd.i64 @X[$i%8],$s1 +___ + &NEON_00_15(2*$i,@_); +} + +$code.=<<___; +#if __ARM_MAX_ARCH__>=7 +.arch armv7-a +.fpu neon + +.global sha512_block_data_order_neon +.type sha512_block_data_order_neon,%function +.align 4 +sha512_block_data_order_neon: +.LNEON: + dmb @ errata #451034 on early Cortex A8 + add $len,$inp,$len,lsl#7 @ len to point at the end of inp + VFP_ABI_PUSH + adrl $Ktbl,K512 + vldmia $ctx,{$A-$H} @ load context +.Loop_neon: +___ +for($i=0;$i<16;$i++) { &NEON_00_15($i,@V); unshift(@V,pop(@V)); } +$code.=<<___; + mov $cnt,#4 +.L16_79_neon: + subs $cnt,#1 +___ +for(;$i<32;$i++) { &NEON_16_79($i,@V); unshift(@V,pop(@V)); } +$code.=<<___; + bne .L16_79_neon + + vadd.i64 $A,d30 @ h+=Maj from the past + vldmia $ctx,{d24-d31} @ load context to temp + vadd.i64 q8,q12 @ vectorized accumulate + vadd.i64 q9,q13 + vadd.i64 q10,q14 + vadd.i64 q11,q15 + vstmia $ctx,{$A-$H} @ save context + teq $inp,$len + sub $Ktbl,#640 @ rewind K512 + bne .Loop_neon + + VFP_ABI_POP + ret @ bx lr +.size sha512_block_data_order_neon,.-sha512_block_data_order_neon +#endif +___ +} +$code.=<<___; +.asciz "SHA512 block transform for ARMv4/NEON, CRYPTOGAMS by <appro\@openssl.org>" +.align 2 +#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) +.comm OPENSSL_armcap_P,4,4 +#endif +___ + +$code =~ s/\`([^\`]*)\`/eval $1/gem; +$code =~ s/\bbx\s+lr\b/.word\t0xe12fff1e/gm; # make it possible to compile with -march=armv4 +$code =~ s/\bret\b/bx lr/gm; + +open SELF,$0; +while(<SELF>) { + next if (/^#!/); + last if (!s/^#/@/ and !/^$/); + print; +} +close SELF; + +print $code; +close STDOUT; # enforce flush diff --git a/arch/arm/crypto/sha512-armv7-neon.S b/arch/arm/crypto/sha512-armv7-neon.S deleted file mode 100644 index fe99472e507c..000000000000 --- a/arch/arm/crypto/sha512-armv7-neon.S +++ /dev/null @@ -1,455 +0,0 @@ -/* sha512-armv7-neon.S - ARM/NEON assembly implementation of SHA-512 transform - * - * Copyright © 2013-2014 Jussi Kivilinna <jussi.kivilinna@iki.fi> - * - * 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/linkage.h> - - -.syntax unified -.code 32 -.fpu neon - -.text - -/* structure of SHA512_CONTEXT */ -#define hd_a 0 -#define hd_b ((hd_a) + 8) -#define hd_c ((hd_b) + 8) -#define hd_d ((hd_c) + 8) -#define hd_e ((hd_d) + 8) -#define hd_f ((hd_e) + 8) -#define hd_g ((hd_f) + 8) - -/* register macros */ -#define RK %r2 - -#define RA d0 -#define RB d1 -#define RC d2 -#define RD d3 -#define RE d4 -#define RF d5 -#define RG d6 -#define RH d7 - -#define RT0 d8 -#define RT1 d9 -#define RT2 d10 -#define RT3 d11 -#define RT4 d12 -#define RT5 d13 -#define RT6 d14 -#define RT7 d15 - -#define RT01q q4 -#define RT23q q5 -#define RT45q q6 -#define RT67q q7 - -#define RW0 d16 -#define RW1 d17 -#define RW2 d18 -#define RW3 d19 -#define RW4 d20 -#define RW5 d21 -#define RW6 d22 -#define RW7 d23 -#define RW8 d24 -#define RW9 d25 -#define RW10 d26 -#define RW11 d27 -#define RW12 d28 -#define RW13 d29 -#define RW14 d30 -#define RW15 d31 - -#define RW01q q8 -#define RW23q q9 -#define RW45q q10 -#define RW67q q11 -#define RW89q q12 -#define RW1011q q13 -#define RW1213q q14 -#define RW1415q q15 - -/*********************************************************************** - * ARM assembly implementation of sha512 transform - ***********************************************************************/ -#define rounds2_0_63(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, rw01q, rw2, \ - rw23q, rw1415q, rw9, rw10, interleave_op, arg1) \ - /* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \ - vshr.u64 RT2, re, #14; \ - vshl.u64 RT3, re, #64 - 14; \ - interleave_op(arg1); \ - vshr.u64 RT4, re, #18; \ - vshl.u64 RT5, re, #64 - 18; \ - vld1.64 {RT0}, [RK]!; \ - veor.64 RT23q, RT23q, RT45q; \ - vshr.u64 RT4, re, #41; \ - vshl.u64 RT5, re, #64 - 41; \ - vadd.u64 RT0, RT0, rw0; \ - veor.64 RT23q, RT23q, RT45q; \ - vmov.64 RT7, re; \ - veor.64 RT1, RT2, RT3; \ - vbsl.64 RT7, rf, rg; \ - \ - vadd.u64 RT1, RT1, rh; \ - vshr.u64 RT2, ra, #28; \ - vshl.u64 RT3, ra, #64 - 28; \ - vadd.u64 RT1, RT1, RT0; \ - vshr.u64 RT4, ra, #34; \ - vshl.u64 RT5, ra, #64 - 34; \ - vadd.u64 RT1, RT1, RT7; \ - \ - /* h = Sum0 (a) + Maj (a, b, c); */ \ - veor.64 RT23q, RT23q, RT45q; \ - vshr.u64 RT4, ra, #39; \ - vshl.u64 RT5, ra, #64 - 39; \ - veor.64 RT0, ra, rb; \ - veor.64 RT23q, RT23q, RT45q; \ - vbsl.64 RT0, rc, rb; \ - vadd.u64 rd, rd, RT1; /* d+=t1; */ \ - veor.64 rh, RT2, RT3; \ - \ - /* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \ - vshr.u64 RT2, rd, #14; \ - vshl.u64 RT3, rd, #64 - 14; \ - vadd.u64 rh, rh, RT0; \ - vshr.u64 RT4, rd, #18; \ - vshl.u64 RT5, rd, #64 - 18; \ - vadd.u64 rh, rh, RT1; /* h+=t1; */ \ - vld1.64 {RT0}, [RK]!; \ - veor.64 RT23q, RT23q, RT45q; \ - vshr.u64 RT4, rd, #41; \ - vshl.u64 RT5, rd, #64 - 41; \ - vadd.u64 RT0, RT0, rw1; \ - veor.64 RT23q, RT23q, RT45q; \ - vmov.64 RT7, rd; \ - veor.64 RT1, RT2, RT3; \ - vbsl.64 RT7, re, rf; \ - \ - vadd.u64 RT1, RT1, rg; \ - vshr.u64 RT2, rh, #28; \ - vshl.u64 RT3, rh, #64 - 28; \ - vadd.u64 RT1, RT1, RT0; \ - vshr.u64 RT4, rh, #34; \ - vshl.u64 RT5, rh, #64 - 34; \ - vadd.u64 RT1, RT1, RT7; \ - \ - /* g = Sum0 (h) + Maj (h, a, b); */ \ - veor.64 RT23q, RT23q, RT45q; \ - vshr.u64 RT4, rh, #39; \ - vshl.u64 RT5, rh, #64 - 39; \ - veor.64 RT0, rh, ra; \ - veor.64 RT23q, RT23q, RT45q; \ - vbsl.64 RT0, rb, ra; \ - vadd.u64 rc, rc, RT1; /* c+=t1; */ \ - veor.64 rg, RT2, RT3; \ - \ - /* w[0] += S1 (w[14]) + w[9] + S0 (w[1]); */ \ - /* w[1] += S1 (w[15]) + w[10] + S0 (w[2]); */ \ - \ - /**** S0(w[1:2]) */ \ - \ - /* w[0:1] += w[9:10] */ \ - /* RT23q = rw1:rw2 */ \ - vext.u64 RT23q, rw01q, rw23q, #1; \ - vadd.u64 rw0, rw9; \ - vadd.u64 rg, rg, RT0; \ - vadd.u64 rw1, rw10;\ - vadd.u64 rg, rg, RT1; /* g+=t1; */ \ - \ - vshr.u64 RT45q, RT23q, #1; \ - vshl.u64 RT67q, RT23q, #64 - 1; \ - vshr.u64 RT01q, RT23q, #8; \ - veor.u64 RT45q, RT45q, RT67q; \ - vshl.u64 RT67q, RT23q, #64 - 8; \ - veor.u64 RT45q, RT45q, RT01q; \ - vshr.u64 RT01q, RT23q, #7; \ - veor.u64 RT45q, RT45q, RT67q; \ - \ - /**** S1(w[14:15]) */ \ - vshr.u64 RT23q, rw1415q, #6; \ - veor.u64 RT01q, RT01q, RT45q; \ - vshr.u64 RT45q, rw1415q, #19; \ - vshl.u64 RT67q, rw1415q, #64 - 19; \ - veor.u64 RT23q, RT23q, RT45q; \ - vshr.u64 RT45q, rw1415q, #61; \ - veor.u64 RT23q, RT23q, RT67q; \ - vshl.u64 RT67q, rw1415q, #64 - 61; \ - veor.u64 RT23q, RT23q, RT45q; \ - vadd.u64 rw01q, RT01q; /* w[0:1] += S(w[1:2]) */ \ - veor.u64 RT01q, RT23q, RT67q; -#define vadd_RT01q(rw01q) \ - /* w[0:1] += S(w[14:15]) */ \ - vadd.u64 rw01q, RT01q; - -#define dummy(_) /*_*/ - -#define rounds2_64_79(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, \ - interleave_op1, arg1, interleave_op2, arg2) \ - /* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \ - vshr.u64 RT2, re, #14; \ - vshl.u64 RT3, re, #64 - 14; \ - interleave_op1(arg1); \ - vshr.u64 RT4, re, #18; \ - vshl.u64 RT5, re, #64 - 18; \ - interleave_op2(arg2); \ - vld1.64 {RT0}, [RK]!; \ - veor.64 RT23q, RT23q, RT45q; \ - vshr.u64 RT4, re, #41; \ - vshl.u64 RT5, re, #64 - 41; \ - vadd.u64 RT0, RT0, rw0; \ - veor.64 RT23q, RT23q, RT45q; \ - vmov.64 RT7, re; \ - veor.64 RT1, RT2, RT3; \ - vbsl.64 RT7, rf, rg; \ - \ - vadd.u64 RT1, RT1, rh; \ - vshr.u64 RT2, ra, #28; \ - vshl.u64 RT3, ra, #64 - 28; \ - vadd.u64 RT1, RT1, RT0; \ - vshr.u64 RT4, ra, #34; \ - vshl.u64 RT5, ra, #64 - 34; \ - vadd.u64 RT1, RT1, RT7; \ - \ - /* h = Sum0 (a) + Maj (a, b, c); */ \ - veor.64 RT23q, RT23q, RT45q; \ - vshr.u64 RT4, ra, #39; \ - vshl.u64 RT5, ra, #64 - 39; \ - veor.64 RT0, ra, rb; \ - veor.64 RT23q, RT23q, RT45q; \ - vbsl.64 RT0, rc, rb; \ - vadd.u64 rd, rd, RT1; /* d+=t1; */ \ - veor.64 rh, RT2, RT3; \ - \ - /* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \ - vshr.u64 RT2, rd, #14; \ - vshl.u64 RT3, rd, #64 - 14; \ - vadd.u64 rh, rh, RT0; \ - vshr.u64 RT4, rd, #18; \ - vshl.u64 RT5, rd, #64 - 18; \ - vadd.u64 rh, rh, RT1; /* h+=t1; */ \ - vld1.64 {RT0}, [RK]!; \ - veor.64 RT23q, RT23q, RT45q; \ - vshr.u64 RT4, rd, #41; \ - vshl.u64 RT5, rd, #64 - 41; \ - vadd.u64 RT0, RT0, rw1; \ - veor.64 RT23q, RT23q, RT45q; \ - vmov.64 RT7, rd; \ - veor.64 RT1, RT2, RT3; \ - vbsl.64 RT7, re, rf; \ - \ - vadd.u64 RT1, RT1, rg; \ - vshr.u64 RT2, rh, #28; \ - vshl.u64 RT3, rh, #64 - 28; \ - vadd.u64 RT1, RT1, RT0; \ - vshr.u64 RT4, rh, #34; \ - vshl.u64 RT5, rh, #64 - 34; \ - vadd.u64 RT1, RT1, RT7; \ - \ - /* g = Sum0 (h) + Maj (h, a, b); */ \ - veor.64 RT23q, RT23q, RT45q; \ - vshr.u64 RT4, rh, #39; \ - vshl.u64 RT5, rh, #64 - 39; \ - veor.64 RT0, rh, ra; \ - veor.64 RT23q, RT23q, RT45q; \ - vbsl.64 RT0, rb, ra; \ - vadd.u64 rc, rc, RT1; /* c+=t1; */ \ - veor.64 rg, RT2, RT3; -#define vadd_rg_RT0(rg) \ - vadd.u64 rg, rg, RT0; -#define vadd_rg_RT1(rg) \ - vadd.u64 rg, rg, RT1; /* g+=t1; */ - -.align 3 -ENTRY(sha512_transform_neon) - /* Input: - * %r0: SHA512_CONTEXT - * %r1: data - * %r2: u64 k[] constants - * %r3: nblks - */ - push {%lr}; - - mov %lr, #0; - - /* Load context to d0-d7 */ - vld1.64 {RA-RD}, [%r0]!; - vld1.64 {RE-RH}, [%r0]; - sub %r0, #(4*8); - - /* Load input to w[16], d16-d31 */ - /* NOTE: Assumes that on ARMv7 unaligned accesses are always allowed. */ - vld1.64 {RW0-RW3}, [%r1]!; - vld1.64 {RW4-RW7}, [%r1]!; - vld1.64 {RW8-RW11}, [%r1]!; - vld1.64 {RW12-RW15}, [%r1]!; -#ifdef __ARMEL__ - /* byteswap */ - vrev64.8 RW01q, RW01q; - vrev64.8 RW23q, RW23q; - vrev64.8 RW45q, RW45q; - vrev64.8 RW67q, RW67q; - vrev64.8 RW89q, RW89q; - vrev64.8 RW1011q, RW1011q; - vrev64.8 RW1213q, RW1213q; - vrev64.8 RW1415q, RW1415q; -#endif - - /* EABI says that d8-d15 must be preserved by callee. */ - /*vpush {RT0-RT7};*/ - -.Loop: - rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2, - RW23q, RW1415q, RW9, RW10, dummy, _); - b .Lenter_rounds; - -.Loop_rounds: - rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2, - RW23q, RW1415q, RW9, RW10, vadd_RT01q, RW1415q); -.Lenter_rounds: - rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3, RW23q, RW4, - RW45q, RW01q, RW11, RW12, vadd_RT01q, RW01q); - rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5, RW45q, RW6, - RW67q, RW23q, RW13, RW14, vadd_RT01q, RW23q); - rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7, RW67q, RW8, - RW89q, RW45q, RW15, RW0, vadd_RT01q, RW45q); - rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9, RW89q, RW10, - RW1011q, RW67q, RW1, RW2, vadd_RT01q, RW67q); - rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11, RW1011q, RW12, - RW1213q, RW89q, RW3, RW4, vadd_RT01q, RW89q); - add %lr, #16; - rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13, RW1213q, RW14, - RW1415q, RW1011q, RW5, RW6, vadd_RT01q, RW1011q); - cmp %lr, #64; - rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15, RW1415q, RW0, - RW01q, RW1213q, RW7, RW8, vadd_RT01q, RW1213q); - bne .Loop_rounds; - - subs %r3, #1; - - rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, - vadd_RT01q, RW1415q, dummy, _); - rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3, - vadd_rg_RT0, RG, vadd_rg_RT1, RG); - beq .Lhandle_tail; - vld1.64 {RW0-RW3}, [%r1]!; - rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5, - vadd_rg_RT0, RE, vadd_rg_RT1, RE); - rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7, - vadd_rg_RT0, RC, vadd_rg_RT1, RC); -#ifdef __ARMEL__ - vrev64.8 RW01q, RW01q; - vrev64.8 RW23q, RW23q; -#endif - vld1.64 {RW4-RW7}, [%r1]!; - rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9, - vadd_rg_RT0, RA, vadd_rg_RT1, RA); - rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11, - vadd_rg_RT0, RG, vadd_rg_RT1, RG); -#ifdef __ARMEL__ - vrev64.8 RW45q, RW45q; - vrev64.8 RW67q, RW67q; -#endif - vld1.64 {RW8-RW11}, [%r1]!; - rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13, - vadd_rg_RT0, RE, vadd_rg_RT1, RE); - rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15, - vadd_rg_RT0, RC, vadd_rg_RT1, RC); -#ifdef __ARMEL__ - vrev64.8 RW89q, RW89q; - vrev64.8 RW1011q, RW1011q; -#endif - vld1.64 {RW12-RW15}, [%r1]!; - vadd_rg_RT0(RA); - vadd_rg_RT1(RA); - - /* Load context */ - vld1.64 {RT0-RT3}, [%r0]!; - vld1.64 {RT4-RT7}, [%r0]; - sub %r0, #(4*8); - -#ifdef __ARMEL__ - vrev64.8 RW1213q, RW1213q; - vrev64.8 RW1415q, RW1415q; -#endif - - vadd.u64 RA, RT0; - vadd.u64 RB, RT1; - vadd.u64 RC, RT2; - vadd.u64 RD, RT3; - vadd.u64 RE, RT4; - vadd.u64 RF, RT5; - vadd.u64 RG, RT6; - vadd.u64 RH, RT7; - - /* Store the first half of context */ - vst1.64 {RA-RD}, [%r0]!; - sub RK, $(8*80); - vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */ - mov %lr, #0; - sub %r0, #(4*8); - - b .Loop; - -.Lhandle_tail: - rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5, - vadd_rg_RT0, RE, vadd_rg_RT1, RE); - rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7, - vadd_rg_RT0, RC, vadd_rg_RT1, RC); - rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9, - vadd_rg_RT0, RA, vadd_rg_RT1, RA); - rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11, - vadd_rg_RT0, RG, vadd_rg_RT1, RG); - rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13, - vadd_rg_RT0, RE, vadd_rg_RT1, RE); - rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15, - vadd_rg_RT0, RC, vadd_rg_RT1, RC); - - /* Load context to d16-d23 */ - vld1.64 {RW0-RW3}, [%r0]!; - vadd_rg_RT0(RA); - vld1.64 {RW4-RW7}, [%r0]; - vadd_rg_RT1(RA); - sub %r0, #(4*8); - - vadd.u64 RA, RW0; - vadd.u64 RB, RW1; - vadd.u64 RC, RW2; - vadd.u64 RD, RW3; - vadd.u64 RE, RW4; - vadd.u64 RF, RW5; - vadd.u64 RG, RW6; - vadd.u64 RH, RW7; - - /* Store the first half of context */ - vst1.64 {RA-RD}, [%r0]!; - - /* Clear used registers */ - /* d16-d31 */ - veor.u64 RW01q, RW01q; - veor.u64 RW23q, RW23q; - veor.u64 RW45q, RW45q; - veor.u64 RW67q, RW67q; - vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */ - veor.u64 RW89q, RW89q; - veor.u64 RW1011q, RW1011q; - veor.u64 RW1213q, RW1213q; - veor.u64 RW1415q, RW1415q; - /* d8-d15 */ - /*vpop {RT0-RT7};*/ - /* d0-d7 (q0-q3) */ - veor.u64 %q0, %q0; - veor.u64 %q1, %q1; - veor.u64 %q2, %q2; - veor.u64 %q3, %q3; - - pop {%pc}; -ENDPROC(sha512_transform_neon) diff --git a/arch/arm/crypto/sha512-core.S_shipped b/arch/arm/crypto/sha512-core.S_shipped new file mode 100644 index 000000000000..3694c4d4ca2b --- /dev/null +++ b/arch/arm/crypto/sha512-core.S_shipped @@ -0,0 +1,1861 @@ + +@ ==================================================================== +@ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL +@ project. The module is, however, dual licensed under OpenSSL and +@ CRYPTOGAMS licenses depending on where you obtain it. For further +@ details see http://www.openssl.org/~appro/cryptogams/. +@ +@ Permission to use under GPL terms is granted. +@ ==================================================================== + +@ SHA512 block procedure for ARMv4. September 2007. + +@ This code is ~4.5 (four and a half) times faster than code generated +@ by gcc 3.4 and it spends ~72 clock cycles per byte [on single-issue +@ Xscale PXA250 core]. +@ +@ July 2010. +@ +@ Rescheduling for dual-issue pipeline resulted in 6% improvement on +@ Cortex A8 core and ~40 cycles per processed byte. + +@ February 2011. +@ +@ Profiler-assisted and platform-specific optimization resulted in 7% +@ improvement on Coxtex A8 core and ~38 cycles per byte. + +@ March 2011. +@ +@ Add NEON implementation. On Cortex A8 it was measured to process +@ one byte in 23.3 cycles or ~60% faster than integer-only code. + +@ August 2012. +@ +@ Improve NEON performance by 12% on Snapdragon S4. In absolute +@ terms it's 22.6 cycles per byte, which is disappointing result. +@ Technical writers asserted that 3-way S4 pipeline can sustain +@ multiple NEON instructions per cycle, but dual NEON issue could +@ not be observed, see http://www.openssl.org/~appro/Snapdragon-S4.html +@ for further details. On side note Cortex-A15 processes one byte in +@ 16 cycles. + +@ Byte order [in]dependence. ========================================= +@ +@ Originally caller was expected to maintain specific *dword* order in +@ h[0-7], namely with most significant dword at *lower* address, which +@ was reflected in below two parameters as 0 and 4. Now caller is +@ expected to maintain native byte order for whole 64-bit values. +#ifndef __KERNEL__ +# include "arm_arch.h" +# define VFP_ABI_PUSH vstmdb sp!,{d8-d15} +# define VFP_ABI_POP vldmia sp!,{d8-d15} +#else +# define __ARM_ARCH__ __LINUX_ARM_ARCH__ +# define __ARM_MAX_ARCH__ 7 +# define VFP_ABI_PUSH +# define VFP_ABI_POP +#endif + +#ifdef __ARMEL__ +# define LO 0 +# define HI 4 +# define WORD64(hi0,lo0,hi1,lo1) .word lo0,hi0, lo1,hi1 +#else +# define HI 0 +# define LO 4 +# define WORD64(hi0,lo0,hi1,lo1) .word hi0,lo0, hi1,lo1 +#endif + +.text +#if __ARM_ARCH__<7 +.code 32 +#else +.syntax unified +# ifdef __thumb2__ +# define adrl adr +.thumb +# else +.code 32 +# endif +#endif + +.type K512,%object +.align 5 +K512: +WORD64(0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd) +WORD64(0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc) +WORD64(0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019) +WORD64(0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118) +WORD64(0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe) +WORD64(0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2) +WORD64(0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1) +WORD64(0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694) +WORD64(0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3) +WORD64(0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65) +WORD64(0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483) +WORD64(0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5) +WORD64(0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210) +WORD64(0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4) +WORD64(0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725) +WORD64(0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70) +WORD64(0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926) +WORD64(0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df) +WORD64(0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8) +WORD64(0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b) +WORD64(0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001) +WORD64(0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30) +WORD64(0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910) +WORD64(0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8) +WORD64(0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53) +WORD64(0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8) +WORD64(0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb) +WORD64(0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3) +WORD64(0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60) +WORD64(0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec) +WORD64(0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9) +WORD64(0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b) +WORD64(0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207) +WORD64(0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178) +WORD64(0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6) +WORD64(0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b) +WORD64(0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493) +WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c) +WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a) +WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817) +.size K512,.-K512 +#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) +.LOPENSSL_armcap: +.word OPENSSL_armcap_P-sha512_block_data_order +.skip 32-4 +#else +.skip 32 +#endif + +.global sha512_block_data_order +.type sha512_block_data_order,%function +sha512_block_data_order: +#if __ARM_ARCH__<7 + sub r3,pc,#8 @ sha512_block_data_order +#else + adr r3,sha512_block_data_order +#endif +#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) + ldr r12,.LOPENSSL_armcap + ldr r12,[r3,r12] @ OPENSSL_armcap_P + tst r12,#1 + bne .LNEON +#endif + add r2,r1,r2,lsl#7 @ len to point at the end of inp + stmdb sp!,{r4-r12,lr} + sub r14,r3,#672 @ K512 + sub sp,sp,#9*8 + + ldr r7,[r0,#32+LO] + ldr r8,[r0,#32+HI] + ldr r9, [r0,#48+LO] + ldr r10, [r0,#48+HI] + ldr r11, [r0,#56+LO] + ldr r12, [r0,#56+HI] +.Loop: + str r9, [sp,#48+0] + str r10, [sp,#48+4] + str r11, [sp,#56+0] + str r12, [sp,#56+4] + ldr r5,[r0,#0+LO] + ldr r6,[r0,#0+HI] + ldr r3,[r0,#8+LO] + ldr r4,[r0,#8+HI] + ldr r9, [r0,#16+LO] + ldr r10, [r0,#16+HI] + ldr r11, [r0,#24+LO] + ldr r12, [r0,#24+HI] + str r3,[sp,#8+0] + str r4,[sp,#8+4] + str r9, [sp,#16+0] + str r10, [sp,#16+4] + str r11, [sp,#24+0] + str r12, [sp,#24+4] + ldr r3,[r0,#40+LO] + ldr r4,[r0,#40+HI] + str r3,[sp,#40+0] + str r4,[sp,#40+4] + +.L00_15: +#if __ARM_ARCH__<7 + ldrb r3,[r1,#7] + ldrb r9, [r1,#6] + ldrb r10, [r1,#5] + ldrb r11, [r1,#4] + ldrb r4,[r1,#3] + ldrb r12, [r1,#2] + orr r3,r3,r9,lsl#8 + ldrb r9, [r1,#1] + orr r3,r3,r10,lsl#16 + ldrb r10, [r1],#8 + orr r3,r3,r11,lsl#24 + orr r4,r4,r12,lsl#8 + orr r4,r4,r9,lsl#16 + orr r4,r4,r10,lsl#24 +#else + ldr r3,[r1,#4] + ldr r4,[r1],#8 +#ifdef __ARMEL__ + rev r3,r3 + rev r4,r4 +#endif +#endif + @ Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41)) + @ LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23 + @ HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23 + mov r9,r7,lsr#14 + str r3,[sp,#64+0] + mov r10,r8,lsr#14 + str r4,[sp,#64+4] + eor r9,r9,r8,lsl#18 + ldr r11,[sp,#56+0] @ h.lo + eor r10,r10,r7,lsl#18 + ldr r12,[sp,#56+4] @ h.hi + eor r9,r9,r7,lsr#18 + eor r10,r10,r8,lsr#18 + eor r9,r9,r8,lsl#14 + eor r10,r10,r7,lsl#14 + eor r9,r9,r8,lsr#9 + eor r10,r10,r7,lsr#9 + eor r9,r9,r7,lsl#23 + eor r10,r10,r8,lsl#23 @ Sigma1(e) + adds r3,r3,r9 + ldr r9,[sp,#40+0] @ f.lo + adc r4,r4,r10 @ T += Sigma1(e) + ldr r10,[sp,#40+4] @ f.hi + adds r3,r3,r11 + ldr r11,[sp,#48+0] @ g.lo + adc r4,r4,r12 @ T += h + ldr r12,[sp,#48+4] @ g.hi + + eor r9,r9,r11 + str r7,[sp,#32+0] + eor r10,r10,r12 + str r8,[sp,#32+4] + and r9,r9,r7 + str r5,[sp,#0+0] + and r10,r10,r8 + str r6,[sp,#0+4] + eor r9,r9,r11 + ldr r11,[r14,#LO] @ K[i].lo + eor r10,r10,r12 @ Ch(e,f,g) + ldr r12,[r14,#HI] @ K[i].hi + + adds r3,r3,r9 + ldr r7,[sp,#24+0] @ d.lo + adc r4,r4,r10 @ T += Ch(e,f,g) + ldr r8,[sp,#24+4] @ d.hi + adds r3,r3,r11 + and r9,r11,#0xff + adc r4,r4,r12 @ T += K[i] + adds r7,r7,r3 + ldr r11,[sp,#8+0] @ b.lo + adc r8,r8,r4 @ d += T + teq r9,#148 + + ldr r12,[sp,#16+0] @ c.lo +#if __ARM_ARCH__>=7 + it eq @ Thumb2 thing, sanity check in ARM +#endif + orreq r14,r14,#1 + @ Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39)) + @ LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25 + @ HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25 + mov r9,r5,lsr#28 + mov r10,r6,lsr#28 + eor r9,r9,r6,lsl#4 + eor r10,r10,r5,lsl#4 + eor r9,r9,r6,lsr#2 + eor r10,r10,r5,lsr#2 + eor r9,r9,r5,lsl#30 + eor r10,r10,r6,lsl#30 + eor r9,r9,r6,lsr#7 + eor r10,r10,r5,lsr#7 + eor r9,r9,r5,lsl#25 + eor r10,r10,r6,lsl#25 @ Sigma0(a) + adds r3,r3,r9 + and r9,r5,r11 + adc r4,r4,r10 @ T += Sigma0(a) + + ldr r10,[sp,#8+4] @ b.hi + orr r5,r5,r11 + ldr r11,[sp,#16+4] @ c.hi + and r5,r5,r12 + and r12,r6,r10 + orr r6,r6,r10 + orr r5,r5,r9 @ Maj(a,b,c).lo + and r6,r6,r11 + adds r5,r5,r3 + orr r6,r6,r12 @ Maj(a,b,c).hi + sub sp,sp,#8 + adc r6,r6,r4 @ h += T + tst r14,#1 + add r14,r14,#8 + tst r14,#1 + beq .L00_15 + ldr r9,[sp,#184+0] + ldr r10,[sp,#184+4] + bic r14,r14,#1 +.L16_79: + @ sigma0(x) (ROTR((x),1) ^ ROTR((x),8) ^ ((x)>>7)) + @ LO lo>>1^hi<<31 ^ lo>>8^hi<<24 ^ lo>>7^hi<<25 + @ HI hi>>1^lo<<31 ^ hi>>8^lo<<24 ^ hi>>7 + mov r3,r9,lsr#1 + ldr r11,[sp,#80+0] + mov r4,r10,lsr#1 + ldr r12,[sp,#80+4] + eor r3,r3,r10,lsl#31 + eor r4,r4,r9,lsl#31 + eor r3,r3,r9,lsr#8 + eor r4,r4,r10,lsr#8 + eor r3,r3,r10,lsl#24 + eor r4,r4,r9,lsl#24 + eor r3,r3,r9,lsr#7 + eor r4,r4,r10,lsr#7 + eor r3,r3,r10,lsl#25 + + @ sigma1(x) (ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6)) + @ LO lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26 + @ HI hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6 + mov r9,r11,lsr#19 + mov r10,r12,lsr#19 + eor r9,r9,r12,lsl#13 + eor r10,r10,r11,lsl#13 + eor r9,r9,r12,lsr#29 + eor r10,r10,r11,lsr#29 + eor r9,r9,r11,lsl#3 + eor r10,r10,r12,lsl#3 + eor r9,r9,r11,lsr#6 + eor r10,r10,r12,lsr#6 + ldr r11,[sp,#120+0] + eor r9,r9,r12,lsl#26 + + ldr r12,[sp,#120+4] + adds r3,r3,r9 + ldr r9,[sp,#192+0] + adc r4,r4,r10 + + ldr r10,[sp,#192+4] + adds r3,r3,r11 + adc r4,r4,r12 + adds r3,r3,r9 + adc r4,r4,r10 + @ Sigma1(x) (ROTR((x),14) ^ ROTR((x),18) ^ ROTR((x),41)) + @ LO lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23 + @ HI hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23 + mov r9,r7,lsr#14 + str r3,[sp,#64+0] + mov r10,r8,lsr#14 + str r4,[sp,#64+4] + eor r9,r9,r8,lsl#18 + ldr r11,[sp,#56+0] @ h.lo + eor r10,r10,r7,lsl#18 + ldr r12,[sp,#56+4] @ h.hi + eor r9,r9,r7,lsr#18 + eor r10,r10,r8,lsr#18 + eor r9,r9,r8,lsl#14 + eor r10,r10,r7,lsl#14 + eor r9,r9,r8,lsr#9 + eor r10,r10,r7,lsr#9 + eor r9,r9,r7,lsl#23 + eor r10,r10,r8,lsl#23 @ Sigma1(e) + adds r3,r3,r9 + ldr r9,[sp,#40+0] @ f.lo + adc r4,r4,r10 @ T += Sigma1(e) + ldr r10,[sp,#40+4] @ f.hi + adds r3,r3,r11 + ldr r11,[sp,#48+0] @ g.lo + adc r4,r4,r12 @ T += h + ldr r12,[sp,#48+4] @ g.hi + + eor r9,r9,r11 + str r7,[sp,#32+0] + eor r10,r10,r12 + str r8,[sp,#32+4] + and r9,r9,r7 + str r5,[sp,#0+0] + and r10,r10,r8 + str r6,[sp,#0+4] + eor r9,r9,r11 + ldr r11,[r14,#LO] @ K[i].lo + eor r10,r10,r12 @ Ch(e,f,g) + ldr r12,[r14,#HI] @ K[i].hi + + adds r3,r3,r9 + ldr r7,[sp,#24+0] @ d.lo + adc r4,r4,r10 @ T += Ch(e,f,g) + ldr r8,[sp,#24+4] @ d.hi + adds r3,r3,r11 + and r9,r11,#0xff + adc r4,r4,r12 @ T += K[i] + adds r7,r7,r3 + ldr r11,[sp,#8+0] @ b.lo + adc r8,r8,r4 @ d += T + teq r9,#23 + + ldr r12,[sp,#16+0] @ c.lo +#if __ARM_ARCH__>=7 + it eq @ Thumb2 thing, sanity check in ARM +#endif + orreq r14,r14,#1 + @ Sigma0(x) (ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39)) + @ LO lo>>28^hi<<4 ^ hi>>2^lo<<30 ^ hi>>7^lo<<25 + @ HI hi>>28^lo<<4 ^ lo>>2^hi<<30 ^ lo>>7^hi<<25 + mov r9,r5,lsr#28 + mov r10,r6,lsr#28 + eor r9,r9,r6,lsl#4 + eor r10,r10,r5,lsl#4 + eor r9,r9,r6,lsr#2 + eor r10,r10,r5,lsr#2 + eor r9,r9,r5,lsl#30 + eor r10,r10,r6,lsl#30 + eor r9,r9,r6,lsr#7 + eor r10,r10,r5,lsr#7 + eor r9,r9,r5,lsl#25 + eor r10,r10,r6,lsl#25 @ Sigma0(a) + adds r3,r3,r9 + and r9,r5,r11 + adc r4,r4,r10 @ T += Sigma0(a) + + ldr r10,[sp,#8+4] @ b.hi + orr r5,r5,r11 + ldr r11,[sp,#16+4] @ c.hi + and r5,r5,r12 + and r12,r6,r10 + orr r6,r6,r10 + orr r5,r5,r9 @ Maj(a,b,c).lo + and r6,r6,r11 + adds r5,r5,r3 + orr r6,r6,r12 @ Maj(a,b,c).hi + sub sp,sp,#8 + adc r6,r6,r4 @ h += T + tst r14,#1 + add r14,r14,#8 +#if __ARM_ARCH__>=7 + ittt eq @ Thumb2 thing, sanity check in ARM +#endif + ldreq r9,[sp,#184+0] + ldreq r10,[sp,#184+4] + beq .L16_79 + bic r14,r14,#1 + + ldr r3,[sp,#8+0] + ldr r4,[sp,#8+4] + ldr r9, [r0,#0+LO] + ldr r10, [r0,#0+HI] + ldr r11, [r0,#8+LO] + ldr r12, [r0,#8+HI] + adds r9,r5,r9 + str r9, [r0,#0+LO] + adc r10,r6,r10 + str r10, [r0,#0+HI] + adds r11,r3,r11 + str r11, [r0,#8+LO] + adc r12,r4,r12 + str r12, [r0,#8+HI] + + ldr r5,[sp,#16+0] + ldr r6,[sp,#16+4] + ldr r3,[sp,#24+0] + ldr r4,[sp,#24+4] + ldr r9, [r0,#16+LO] + ldr r10, [r0,#16+HI] + ldr r11, [r0,#24+LO] + ldr r12, [r0,#24+HI] + adds r9,r5,r9 + str r9, [r0,#16+LO] + adc r10,r6,r10 + str r10, [r0,#16+HI] + adds r11,r3,r11 + str r11, [r0,#24+LO] + adc r12,r4,r12 + str r12, [r0,#24+HI] + + ldr r3,[sp,#40+0] + ldr r4,[sp,#40+4] + ldr r9, [r0,#32+LO] + ldr r10, [r0,#32+HI] + ldr r11, [r0,#40+LO] + ldr r12, [r0,#40+HI] + adds r7,r7,r9 + str r7,[r0,#32+LO] + adc r8,r8,r10 + str r8,[r0,#32+HI] + adds r11,r3,r11 + str r11, [r0,#40+LO] + adc r12,r4,r12 + str r12, [r0,#40+HI] + + ldr r5,[sp,#48+0] + ldr r6,[sp,#48+4] + ldr r3,[sp,#56+0] + ldr r4,[sp,#56+4] + ldr r9, [r0,#48+LO] + ldr r10, [r0,#48+HI] + ldr r11, [r0,#56+LO] + ldr r12, [r0,#56+HI] + adds r9,r5,r9 + str r9, [r0,#48+LO] + adc r10,r6,r10 + str r10, [r0,#48+HI] + adds r11,r3,r11 + str r11, [r0,#56+LO] + adc r12,r4,r12 + str r12, [r0,#56+HI] + + add sp,sp,#640 + sub r14,r14,#640 + + teq r1,r2 + bne .Loop + + add sp,sp,#8*9 @ destroy frame +#if __ARM_ARCH__>=5 + ldmia sp!,{r4-r12,pc} +#else + ldmia sp!,{r4-r12,lr} + tst lr,#1 + moveq pc,lr @ be binary compatible with V4, yet + .word 0xe12fff1e @ interoperable with Thumb ISA:-) +#endif +.size sha512_block_data_order,.-sha512_block_data_order +#if __ARM_MAX_ARCH__>=7 +.arch armv7-a +.fpu neon + +.global sha512_block_data_order_neon +.type sha512_block_data_order_neon,%function +.align 4 +sha512_block_data_order_neon: +.LNEON: + dmb @ errata #451034 on early Cortex A8 + add r2,r1,r2,lsl#7 @ len to point at the end of inp + VFP_ABI_PUSH + adrl r3,K512 + vldmia r0,{d16-d23} @ load context +.Loop_neon: + vshr.u64 d24,d20,#14 @ 0 +#if 0<16 + vld1.64 {d0},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d20,#18 +#if 0>0 + vadd.i64 d16,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d20,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d20,#50 + vsli.64 d25,d20,#46 + vmov d29,d20 + vsli.64 d26,d20,#23 +#if 0<16 && defined(__ARMEL__) + vrev64.8 d0,d0 +#endif + veor d25,d24 + vbsl d29,d21,d22 @ Ch(e,f,g) + vshr.u64 d24,d16,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d23 + vshr.u64 d25,d16,#34 + vsli.64 d24,d16,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d16,#39 + vadd.i64 d28,d0 + vsli.64 d25,d16,#30 + veor d30,d16,d17 + vsli.64 d26,d16,#25 + veor d23,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d18,d17 @ Maj(a,b,c) + veor d23,d26 @ Sigma0(a) + vadd.i64 d19,d27 + vadd.i64 d30,d27 + @ vadd.i64 d23,d30 + vshr.u64 d24,d19,#14 @ 1 +#if 1<16 + vld1.64 {d1},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d19,#18 +#if 1>0 + vadd.i64 d23,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d19,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d19,#50 + vsli.64 d25,d19,#46 + vmov d29,d19 + vsli.64 d26,d19,#23 +#if 1<16 && defined(__ARMEL__) + vrev64.8 d1,d1 +#endif + veor d25,d24 + vbsl d29,d20,d21 @ Ch(e,f,g) + vshr.u64 d24,d23,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d22 + vshr.u64 d25,d23,#34 + vsli.64 d24,d23,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d23,#39 + vadd.i64 d28,d1 + vsli.64 d25,d23,#30 + veor d30,d23,d16 + vsli.64 d26,d23,#25 + veor d22,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d17,d16 @ Maj(a,b,c) + veor d22,d26 @ Sigma0(a) + vadd.i64 d18,d27 + vadd.i64 d30,d27 + @ vadd.i64 d22,d30 + vshr.u64 d24,d18,#14 @ 2 +#if 2<16 + vld1.64 {d2},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d18,#18 +#if 2>0 + vadd.i64 d22,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d18,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d18,#50 + vsli.64 d25,d18,#46 + vmov d29,d18 + vsli.64 d26,d18,#23 +#if 2<16 && defined(__ARMEL__) + vrev64.8 d2,d2 +#endif + veor d25,d24 + vbsl d29,d19,d20 @ Ch(e,f,g) + vshr.u64 d24,d22,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d21 + vshr.u64 d25,d22,#34 + vsli.64 d24,d22,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d22,#39 + vadd.i64 d28,d2 + vsli.64 d25,d22,#30 + veor d30,d22,d23 + vsli.64 d26,d22,#25 + veor d21,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d16,d23 @ Maj(a,b,c) + veor d21,d26 @ Sigma0(a) + vadd.i64 d17,d27 + vadd.i64 d30,d27 + @ vadd.i64 d21,d30 + vshr.u64 d24,d17,#14 @ 3 +#if 3<16 + vld1.64 {d3},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d17,#18 +#if 3>0 + vadd.i64 d21,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d17,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d17,#50 + vsli.64 d25,d17,#46 + vmov d29,d17 + vsli.64 d26,d17,#23 +#if 3<16 && defined(__ARMEL__) + vrev64.8 d3,d3 +#endif + veor d25,d24 + vbsl d29,d18,d19 @ Ch(e,f,g) + vshr.u64 d24,d21,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d20 + vshr.u64 d25,d21,#34 + vsli.64 d24,d21,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d21,#39 + vadd.i64 d28,d3 + vsli.64 d25,d21,#30 + veor d30,d21,d22 + vsli.64 d26,d21,#25 + veor d20,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d23,d22 @ Maj(a,b,c) + veor d20,d26 @ Sigma0(a) + vadd.i64 d16,d27 + vadd.i64 d30,d27 + @ vadd.i64 d20,d30 + vshr.u64 d24,d16,#14 @ 4 +#if 4<16 + vld1.64 {d4},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d16,#18 +#if 4>0 + vadd.i64 d20,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d16,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d16,#50 + vsli.64 d25,d16,#46 + vmov d29,d16 + vsli.64 d26,d16,#23 +#if 4<16 && defined(__ARMEL__) + vrev64.8 d4,d4 +#endif + veor d25,d24 + vbsl d29,d17,d18 @ Ch(e,f,g) + vshr.u64 d24,d20,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d19 + vshr.u64 d25,d20,#34 + vsli.64 d24,d20,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d20,#39 + vadd.i64 d28,d4 + vsli.64 d25,d20,#30 + veor d30,d20,d21 + vsli.64 d26,d20,#25 + veor d19,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d22,d21 @ Maj(a,b,c) + veor d19,d26 @ Sigma0(a) + vadd.i64 d23,d27 + vadd.i64 d30,d27 + @ vadd.i64 d19,d30 + vshr.u64 d24,d23,#14 @ 5 +#if 5<16 + vld1.64 {d5},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d23,#18 +#if 5>0 + vadd.i64 d19,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d23,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d23,#50 + vsli.64 d25,d23,#46 + vmov d29,d23 + vsli.64 d26,d23,#23 +#if 5<16 && defined(__ARMEL__) + vrev64.8 d5,d5 +#endif + veor d25,d24 + vbsl d29,d16,d17 @ Ch(e,f,g) + vshr.u64 d24,d19,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d18 + vshr.u64 d25,d19,#34 + vsli.64 d24,d19,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d19,#39 + vadd.i64 d28,d5 + vsli.64 d25,d19,#30 + veor d30,d19,d20 + vsli.64 d26,d19,#25 + veor d18,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d21,d20 @ Maj(a,b,c) + veor d18,d26 @ Sigma0(a) + vadd.i64 d22,d27 + vadd.i64 d30,d27 + @ vadd.i64 d18,d30 + vshr.u64 d24,d22,#14 @ 6 +#if 6<16 + vld1.64 {d6},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d22,#18 +#if 6>0 + vadd.i64 d18,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d22,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d22,#50 + vsli.64 d25,d22,#46 + vmov d29,d22 + vsli.64 d26,d22,#23 +#if 6<16 && defined(__ARMEL__) + vrev64.8 d6,d6 +#endif + veor d25,d24 + vbsl d29,d23,d16 @ Ch(e,f,g) + vshr.u64 d24,d18,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d17 + vshr.u64 d25,d18,#34 + vsli.64 d24,d18,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d18,#39 + vadd.i64 d28,d6 + vsli.64 d25,d18,#30 + veor d30,d18,d19 + vsli.64 d26,d18,#25 + veor d17,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d20,d19 @ Maj(a,b,c) + veor d17,d26 @ Sigma0(a) + vadd.i64 d21,d27 + vadd.i64 d30,d27 + @ vadd.i64 d17,d30 + vshr.u64 d24,d21,#14 @ 7 +#if 7<16 + vld1.64 {d7},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d21,#18 +#if 7>0 + vadd.i64 d17,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d21,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d21,#50 + vsli.64 d25,d21,#46 + vmov d29,d21 + vsli.64 d26,d21,#23 +#if 7<16 && defined(__ARMEL__) + vrev64.8 d7,d7 +#endif + veor d25,d24 + vbsl d29,d22,d23 @ Ch(e,f,g) + vshr.u64 d24,d17,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d16 + vshr.u64 d25,d17,#34 + vsli.64 d24,d17,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d17,#39 + vadd.i64 d28,d7 + vsli.64 d25,d17,#30 + veor d30,d17,d18 + vsli.64 d26,d17,#25 + veor d16,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d19,d18 @ Maj(a,b,c) + veor d16,d26 @ Sigma0(a) + vadd.i64 d20,d27 + vadd.i64 d30,d27 + @ vadd.i64 d16,d30 + vshr.u64 d24,d20,#14 @ 8 +#if 8<16 + vld1.64 {d8},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d20,#18 +#if 8>0 + vadd.i64 d16,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d20,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d20,#50 + vsli.64 d25,d20,#46 + vmov d29,d20 + vsli.64 d26,d20,#23 +#if 8<16 && defined(__ARMEL__) + vrev64.8 d8,d8 +#endif + veor d25,d24 + vbsl d29,d21,d22 @ Ch(e,f,g) + vshr.u64 d24,d16,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d23 + vshr.u64 d25,d16,#34 + vsli.64 d24,d16,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d16,#39 + vadd.i64 d28,d8 + vsli.64 d25,d16,#30 + veor d30,d16,d17 + vsli.64 d26,d16,#25 + veor d23,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d18,d17 @ Maj(a,b,c) + veor d23,d26 @ Sigma0(a) + vadd.i64 d19,d27 + vadd.i64 d30,d27 + @ vadd.i64 d23,d30 + vshr.u64 d24,d19,#14 @ 9 +#if 9<16 + vld1.64 {d9},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d19,#18 +#if 9>0 + vadd.i64 d23,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d19,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d19,#50 + vsli.64 d25,d19,#46 + vmov d29,d19 + vsli.64 d26,d19,#23 +#if 9<16 && defined(__ARMEL__) + vrev64.8 d9,d9 +#endif + veor d25,d24 + vbsl d29,d20,d21 @ Ch(e,f,g) + vshr.u64 d24,d23,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d22 + vshr.u64 d25,d23,#34 + vsli.64 d24,d23,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d23,#39 + vadd.i64 d28,d9 + vsli.64 d25,d23,#30 + veor d30,d23,d16 + vsli.64 d26,d23,#25 + veor d22,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d17,d16 @ Maj(a,b,c) + veor d22,d26 @ Sigma0(a) + vadd.i64 d18,d27 + vadd.i64 d30,d27 + @ vadd.i64 d22,d30 + vshr.u64 d24,d18,#14 @ 10 +#if 10<16 + vld1.64 {d10},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d18,#18 +#if 10>0 + vadd.i64 d22,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d18,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d18,#50 + vsli.64 d25,d18,#46 + vmov d29,d18 + vsli.64 d26,d18,#23 +#if 10<16 && defined(__ARMEL__) + vrev64.8 d10,d10 +#endif + veor d25,d24 + vbsl d29,d19,d20 @ Ch(e,f,g) + vshr.u64 d24,d22,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d21 + vshr.u64 d25,d22,#34 + vsli.64 d24,d22,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d22,#39 + vadd.i64 d28,d10 + vsli.64 d25,d22,#30 + veor d30,d22,d23 + vsli.64 d26,d22,#25 + veor d21,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d16,d23 @ Maj(a,b,c) + veor d21,d26 @ Sigma0(a) + vadd.i64 d17,d27 + vadd.i64 d30,d27 + @ vadd.i64 d21,d30 + vshr.u64 d24,d17,#14 @ 11 +#if 11<16 + vld1.64 {d11},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d17,#18 +#if 11>0 + vadd.i64 d21,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d17,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d17,#50 + vsli.64 d25,d17,#46 + vmov d29,d17 + vsli.64 d26,d17,#23 +#if 11<16 && defined(__ARMEL__) + vrev64.8 d11,d11 +#endif + veor d25,d24 + vbsl d29,d18,d19 @ Ch(e,f,g) + vshr.u64 d24,d21,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d20 + vshr.u64 d25,d21,#34 + vsli.64 d24,d21,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d21,#39 + vadd.i64 d28,d11 + vsli.64 d25,d21,#30 + veor d30,d21,d22 + vsli.64 d26,d21,#25 + veor d20,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d23,d22 @ Maj(a,b,c) + veor d20,d26 @ Sigma0(a) + vadd.i64 d16,d27 + vadd.i64 d30,d27 + @ vadd.i64 d20,d30 + vshr.u64 d24,d16,#14 @ 12 +#if 12<16 + vld1.64 {d12},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d16,#18 +#if 12>0 + vadd.i64 d20,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d16,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d16,#50 + vsli.64 d25,d16,#46 + vmov d29,d16 + vsli.64 d26,d16,#23 +#if 12<16 && defined(__ARMEL__) + vrev64.8 d12,d12 +#endif + veor d25,d24 + vbsl d29,d17,d18 @ Ch(e,f,g) + vshr.u64 d24,d20,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d19 + vshr.u64 d25,d20,#34 + vsli.64 d24,d20,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d20,#39 + vadd.i64 d28,d12 + vsli.64 d25,d20,#30 + veor d30,d20,d21 + vsli.64 d26,d20,#25 + veor d19,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d22,d21 @ Maj(a,b,c) + veor d19,d26 @ Sigma0(a) + vadd.i64 d23,d27 + vadd.i64 d30,d27 + @ vadd.i64 d19,d30 + vshr.u64 d24,d23,#14 @ 13 +#if 13<16 + vld1.64 {d13},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d23,#18 +#if 13>0 + vadd.i64 d19,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d23,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d23,#50 + vsli.64 d25,d23,#46 + vmov d29,d23 + vsli.64 d26,d23,#23 +#if 13<16 && defined(__ARMEL__) + vrev64.8 d13,d13 +#endif + veor d25,d24 + vbsl d29,d16,d17 @ Ch(e,f,g) + vshr.u64 d24,d19,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d18 + vshr.u64 d25,d19,#34 + vsli.64 d24,d19,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d19,#39 + vadd.i64 d28,d13 + vsli.64 d25,d19,#30 + veor d30,d19,d20 + vsli.64 d26,d19,#25 + veor d18,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d21,d20 @ Maj(a,b,c) + veor d18,d26 @ Sigma0(a) + vadd.i64 d22,d27 + vadd.i64 d30,d27 + @ vadd.i64 d18,d30 + vshr.u64 d24,d22,#14 @ 14 +#if 14<16 + vld1.64 {d14},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d22,#18 +#if 14>0 + vadd.i64 d18,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d22,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d22,#50 + vsli.64 d25,d22,#46 + vmov d29,d22 + vsli.64 d26,d22,#23 +#if 14<16 && defined(__ARMEL__) + vrev64.8 d14,d14 +#endif + veor d25,d24 + vbsl d29,d23,d16 @ Ch(e,f,g) + vshr.u64 d24,d18,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d17 + vshr.u64 d25,d18,#34 + vsli.64 d24,d18,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d18,#39 + vadd.i64 d28,d14 + vsli.64 d25,d18,#30 + veor d30,d18,d19 + vsli.64 d26,d18,#25 + veor d17,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d20,d19 @ Maj(a,b,c) + veor d17,d26 @ Sigma0(a) + vadd.i64 d21,d27 + vadd.i64 d30,d27 + @ vadd.i64 d17,d30 + vshr.u64 d24,d21,#14 @ 15 +#if 15<16 + vld1.64 {d15},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d21,#18 +#if 15>0 + vadd.i64 d17,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d21,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d21,#50 + vsli.64 d25,d21,#46 + vmov d29,d21 + vsli.64 d26,d21,#23 +#if 15<16 && defined(__ARMEL__) + vrev64.8 d15,d15 +#endif + veor d25,d24 + vbsl d29,d22,d23 @ Ch(e,f,g) + vshr.u64 d24,d17,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d16 + vshr.u64 d25,d17,#34 + vsli.64 d24,d17,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d17,#39 + vadd.i64 d28,d15 + vsli.64 d25,d17,#30 + veor d30,d17,d18 + vsli.64 d26,d17,#25 + veor d16,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d19,d18 @ Maj(a,b,c) + veor d16,d26 @ Sigma0(a) + vadd.i64 d20,d27 + vadd.i64 d30,d27 + @ vadd.i64 d16,d30 + mov r12,#4 +.L16_79_neon: + subs r12,#1 + vshr.u64 q12,q7,#19 + vshr.u64 q13,q7,#61 + vadd.i64 d16,d30 @ h+=Maj from the past + vshr.u64 q15,q7,#6 + vsli.64 q12,q7,#45 + vext.8 q14,q0,q1,#8 @ X[i+1] + vsli.64 q13,q7,#3 + veor q15,q12 + vshr.u64 q12,q14,#1 + veor q15,q13 @ sigma1(X[i+14]) + vshr.u64 q13,q14,#8 + vadd.i64 q0,q15 + vshr.u64 q15,q14,#7 + vsli.64 q12,q14,#63 + vsli.64 q13,q14,#56 + vext.8 q14,q4,q5,#8 @ X[i+9] + veor q15,q12 + vshr.u64 d24,d20,#14 @ from NEON_00_15 + vadd.i64 q0,q14 + vshr.u64 d25,d20,#18 @ from NEON_00_15 + veor q15,q13 @ sigma0(X[i+1]) + vshr.u64 d26,d20,#41 @ from NEON_00_15 + vadd.i64 q0,q15 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d20,#50 + vsli.64 d25,d20,#46 + vmov d29,d20 + vsli.64 d26,d20,#23 +#if 16<16 && defined(__ARMEL__) + vrev64.8 , +#endif + veor d25,d24 + vbsl d29,d21,d22 @ Ch(e,f,g) + vshr.u64 d24,d16,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d23 + vshr.u64 d25,d16,#34 + vsli.64 d24,d16,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d16,#39 + vadd.i64 d28,d0 + vsli.64 d25,d16,#30 + veor d30,d16,d17 + vsli.64 d26,d16,#25 + veor d23,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d18,d17 @ Maj(a,b,c) + veor d23,d26 @ Sigma0(a) + vadd.i64 d19,d27 + vadd.i64 d30,d27 + @ vadd.i64 d23,d30 + vshr.u64 d24,d19,#14 @ 17 +#if 17<16 + vld1.64 {d1},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d19,#18 +#if 17>0 + vadd.i64 d23,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d19,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d19,#50 + vsli.64 d25,d19,#46 + vmov d29,d19 + vsli.64 d26,d19,#23 +#if 17<16 && defined(__ARMEL__) + vrev64.8 , +#endif + veor d25,d24 + vbsl d29,d20,d21 @ Ch(e,f,g) + vshr.u64 d24,d23,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d22 + vshr.u64 d25,d23,#34 + vsli.64 d24,d23,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d23,#39 + vadd.i64 d28,d1 + vsli.64 d25,d23,#30 + veor d30,d23,d16 + vsli.64 d26,d23,#25 + veor d22,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d17,d16 @ Maj(a,b,c) + veor d22,d26 @ Sigma0(a) + vadd.i64 d18,d27 + vadd.i64 d30,d27 + @ vadd.i64 d22,d30 + vshr.u64 q12,q0,#19 + vshr.u64 q13,q0,#61 + vadd.i64 d22,d30 @ h+=Maj from the past + vshr.u64 q15,q0,#6 + vsli.64 q12,q0,#45 + vext.8 q14,q1,q2,#8 @ X[i+1] + vsli.64 q13,q0,#3 + veor q15,q12 + vshr.u64 q12,q14,#1 + veor q15,q13 @ sigma1(X[i+14]) + vshr.u64 q13,q14,#8 + vadd.i64 q1,q15 + vshr.u64 q15,q14,#7 + vsli.64 q12,q14,#63 + vsli.64 q13,q14,#56 + vext.8 q14,q5,q6,#8 @ X[i+9] + veor q15,q12 + vshr.u64 d24,d18,#14 @ from NEON_00_15 + vadd.i64 q1,q14 + vshr.u64 d25,d18,#18 @ from NEON_00_15 + veor q15,q13 @ sigma0(X[i+1]) + vshr.u64 d26,d18,#41 @ from NEON_00_15 + vadd.i64 q1,q15 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d18,#50 + vsli.64 d25,d18,#46 + vmov d29,d18 + vsli.64 d26,d18,#23 +#if 18<16 && defined(__ARMEL__) + vrev64.8 , +#endif + veor d25,d24 + vbsl d29,d19,d20 @ Ch(e,f,g) + vshr.u64 d24,d22,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d21 + vshr.u64 d25,d22,#34 + vsli.64 d24,d22,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d22,#39 + vadd.i64 d28,d2 + vsli.64 d25,d22,#30 + veor d30,d22,d23 + vsli.64 d26,d22,#25 + veor d21,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d16,d23 @ Maj(a,b,c) + veor d21,d26 @ Sigma0(a) + vadd.i64 d17,d27 + vadd.i64 d30,d27 + @ vadd.i64 d21,d30 + vshr.u64 d24,d17,#14 @ 19 +#if 19<16 + vld1.64 {d3},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d17,#18 +#if 19>0 + vadd.i64 d21,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d17,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d17,#50 + vsli.64 d25,d17,#46 + vmov d29,d17 + vsli.64 d26,d17,#23 +#if 19<16 && defined(__ARMEL__) + vrev64.8 , +#endif + veor d25,d24 + vbsl d29,d18,d19 @ Ch(e,f,g) + vshr.u64 d24,d21,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d20 + vshr.u64 d25,d21,#34 + vsli.64 d24,d21,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d21,#39 + vadd.i64 d28,d3 + vsli.64 d25,d21,#30 + veor d30,d21,d22 + vsli.64 d26,d21,#25 + veor d20,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d23,d22 @ Maj(a,b,c) + veor d20,d26 @ Sigma0(a) + vadd.i64 d16,d27 + vadd.i64 d30,d27 + @ vadd.i64 d20,d30 + vshr.u64 q12,q1,#19 + vshr.u64 q13,q1,#61 + vadd.i64 d20,d30 @ h+=Maj from the past + vshr.u64 q15,q1,#6 + vsli.64 q12,q1,#45 + vext.8 q14,q2,q3,#8 @ X[i+1] + vsli.64 q13,q1,#3 + veor q15,q12 + vshr.u64 q12,q14,#1 + veor q15,q13 @ sigma1(X[i+14]) + vshr.u64 q13,q14,#8 + vadd.i64 q2,q15 + vshr.u64 q15,q14,#7 + vsli.64 q12,q14,#63 + vsli.64 q13,q14,#56 + vext.8 q14,q6,q7,#8 @ X[i+9] + veor q15,q12 + vshr.u64 d24,d16,#14 @ from NEON_00_15 + vadd.i64 q2,q14 + vshr.u64 d25,d16,#18 @ from NEON_00_15 + veor q15,q13 @ sigma0(X[i+1]) + vshr.u64 d26,d16,#41 @ from NEON_00_15 + vadd.i64 q2,q15 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d16,#50 + vsli.64 d25,d16,#46 + vmov d29,d16 + vsli.64 d26,d16,#23 +#if 20<16 && defined(__ARMEL__) + vrev64.8 , +#endif + veor d25,d24 + vbsl d29,d17,d18 @ Ch(e,f,g) + vshr.u64 d24,d20,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d19 + vshr.u64 d25,d20,#34 + vsli.64 d24,d20,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d20,#39 + vadd.i64 d28,d4 + vsli.64 d25,d20,#30 + veor d30,d20,d21 + vsli.64 d26,d20,#25 + veor d19,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d22,d21 @ Maj(a,b,c) + veor d19,d26 @ Sigma0(a) + vadd.i64 d23,d27 + vadd.i64 d30,d27 + @ vadd.i64 d19,d30 + vshr.u64 d24,d23,#14 @ 21 +#if 21<16 + vld1.64 {d5},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d23,#18 +#if 21>0 + vadd.i64 d19,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d23,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d23,#50 + vsli.64 d25,d23,#46 + vmov d29,d23 + vsli.64 d26,d23,#23 +#if 21<16 && defined(__ARMEL__) + vrev64.8 , +#endif + veor d25,d24 + vbsl d29,d16,d17 @ Ch(e,f,g) + vshr.u64 d24,d19,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d18 + vshr.u64 d25,d19,#34 + vsli.64 d24,d19,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d19,#39 + vadd.i64 d28,d5 + vsli.64 d25,d19,#30 + veor d30,d19,d20 + vsli.64 d26,d19,#25 + veor d18,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d21,d20 @ Maj(a,b,c) + veor d18,d26 @ Sigma0(a) + vadd.i64 d22,d27 + vadd.i64 d30,d27 + @ vadd.i64 d18,d30 + vshr.u64 q12,q2,#19 + vshr.u64 q13,q2,#61 + vadd.i64 d18,d30 @ h+=Maj from the past + vshr.u64 q15,q2,#6 + vsli.64 q12,q2,#45 + vext.8 q14,q3,q4,#8 @ X[i+1] + vsli.64 q13,q2,#3 + veor q15,q12 + vshr.u64 q12,q14,#1 + veor q15,q13 @ sigma1(X[i+14]) + vshr.u64 q13,q14,#8 + vadd.i64 q3,q15 + vshr.u64 q15,q14,#7 + vsli.64 q12,q14,#63 + vsli.64 q13,q14,#56 + vext.8 q14,q7,q0,#8 @ X[i+9] + veor q15,q12 + vshr.u64 d24,d22,#14 @ from NEON_00_15 + vadd.i64 q3,q14 + vshr.u64 d25,d22,#18 @ from NEON_00_15 + veor q15,q13 @ sigma0(X[i+1]) + vshr.u64 d26,d22,#41 @ from NEON_00_15 + vadd.i64 q3,q15 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d22,#50 + vsli.64 d25,d22,#46 + vmov d29,d22 + vsli.64 d26,d22,#23 +#if 22<16 && defined(__ARMEL__) + vrev64.8 , +#endif + veor d25,d24 + vbsl d29,d23,d16 @ Ch(e,f,g) + vshr.u64 d24,d18,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d17 + vshr.u64 d25,d18,#34 + vsli.64 d24,d18,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d18,#39 + vadd.i64 d28,d6 + vsli.64 d25,d18,#30 + veor d30,d18,d19 + vsli.64 d26,d18,#25 + veor d17,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d20,d19 @ Maj(a,b,c) + veor d17,d26 @ Sigma0(a) + vadd.i64 d21,d27 + vadd.i64 d30,d27 + @ vadd.i64 d17,d30 + vshr.u64 d24,d21,#14 @ 23 +#if 23<16 + vld1.64 {d7},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d21,#18 +#if 23>0 + vadd.i64 d17,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d21,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d21,#50 + vsli.64 d25,d21,#46 + vmov d29,d21 + vsli.64 d26,d21,#23 +#if 23<16 && defined(__ARMEL__) + vrev64.8 , +#endif + veor d25,d24 + vbsl d29,d22,d23 @ Ch(e,f,g) + vshr.u64 d24,d17,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d16 + vshr.u64 d25,d17,#34 + vsli.64 d24,d17,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d17,#39 + vadd.i64 d28,d7 + vsli.64 d25,d17,#30 + veor d30,d17,d18 + vsli.64 d26,d17,#25 + veor d16,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d19,d18 @ Maj(a,b,c) + veor d16,d26 @ Sigma0(a) + vadd.i64 d20,d27 + vadd.i64 d30,d27 + @ vadd.i64 d16,d30 + vshr.u64 q12,q3,#19 + vshr.u64 q13,q3,#61 + vadd.i64 d16,d30 @ h+=Maj from the past + vshr.u64 q15,q3,#6 + vsli.64 q12,q3,#45 + vext.8 q14,q4,q5,#8 @ X[i+1] + vsli.64 q13,q3,#3 + veor q15,q12 + vshr.u64 q12,q14,#1 + veor q15,q13 @ sigma1(X[i+14]) + vshr.u64 q13,q14,#8 + vadd.i64 q4,q15 + vshr.u64 q15,q14,#7 + vsli.64 q12,q14,#63 + vsli.64 q13,q14,#56 + vext.8 q14,q0,q1,#8 @ X[i+9] + veor q15,q12 + vshr.u64 d24,d20,#14 @ from NEON_00_15 + vadd.i64 q4,q14 + vshr.u64 d25,d20,#18 @ from NEON_00_15 + veor q15,q13 @ sigma0(X[i+1]) + vshr.u64 d26,d20,#41 @ from NEON_00_15 + vadd.i64 q4,q15 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d20,#50 + vsli.64 d25,d20,#46 + vmov d29,d20 + vsli.64 d26,d20,#23 +#if 24<16 && defined(__ARMEL__) + vrev64.8 , +#endif + veor d25,d24 + vbsl d29,d21,d22 @ Ch(e,f,g) + vshr.u64 d24,d16,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d23 + vshr.u64 d25,d16,#34 + vsli.64 d24,d16,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d16,#39 + vadd.i64 d28,d8 + vsli.64 d25,d16,#30 + veor d30,d16,d17 + vsli.64 d26,d16,#25 + veor d23,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d18,d17 @ Maj(a,b,c) + veor d23,d26 @ Sigma0(a) + vadd.i64 d19,d27 + vadd.i64 d30,d27 + @ vadd.i64 d23,d30 + vshr.u64 d24,d19,#14 @ 25 +#if 25<16 + vld1.64 {d9},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d19,#18 +#if 25>0 + vadd.i64 d23,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d19,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d19,#50 + vsli.64 d25,d19,#46 + vmov d29,d19 + vsli.64 d26,d19,#23 +#if 25<16 && defined(__ARMEL__) + vrev64.8 , +#endif + veor d25,d24 + vbsl d29,d20,d21 @ Ch(e,f,g) + vshr.u64 d24,d23,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d22 + vshr.u64 d25,d23,#34 + vsli.64 d24,d23,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d23,#39 + vadd.i64 d28,d9 + vsli.64 d25,d23,#30 + veor d30,d23,d16 + vsli.64 d26,d23,#25 + veor d22,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d17,d16 @ Maj(a,b,c) + veor d22,d26 @ Sigma0(a) + vadd.i64 d18,d27 + vadd.i64 d30,d27 + @ vadd.i64 d22,d30 + vshr.u64 q12,q4,#19 + vshr.u64 q13,q4,#61 + vadd.i64 d22,d30 @ h+=Maj from the past + vshr.u64 q15,q4,#6 + vsli.64 q12,q4,#45 + vext.8 q14,q5,q6,#8 @ X[i+1] + vsli.64 q13,q4,#3 + veor q15,q12 + vshr.u64 q12,q14,#1 + veor q15,q13 @ sigma1(X[i+14]) + vshr.u64 q13,q14,#8 + vadd.i64 q5,q15 + vshr.u64 q15,q14,#7 + vsli.64 q12,q14,#63 + vsli.64 q13,q14,#56 + vext.8 q14,q1,q2,#8 @ X[i+9] + veor q15,q12 + vshr.u64 d24,d18,#14 @ from NEON_00_15 + vadd.i64 q5,q14 + vshr.u64 d25,d18,#18 @ from NEON_00_15 + veor q15,q13 @ sigma0(X[i+1]) + vshr.u64 d26,d18,#41 @ from NEON_00_15 + vadd.i64 q5,q15 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d18,#50 + vsli.64 d25,d18,#46 + vmov d29,d18 + vsli.64 d26,d18,#23 +#if 26<16 && defined(__ARMEL__) + vrev64.8 , +#endif + veor d25,d24 + vbsl d29,d19,d20 @ Ch(e,f,g) + vshr.u64 d24,d22,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d21 + vshr.u64 d25,d22,#34 + vsli.64 d24,d22,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d22,#39 + vadd.i64 d28,d10 + vsli.64 d25,d22,#30 + veor d30,d22,d23 + vsli.64 d26,d22,#25 + veor d21,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d16,d23 @ Maj(a,b,c) + veor d21,d26 @ Sigma0(a) + vadd.i64 d17,d27 + vadd.i64 d30,d27 + @ vadd.i64 d21,d30 + vshr.u64 d24,d17,#14 @ 27 +#if 27<16 + vld1.64 {d11},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d17,#18 +#if 27>0 + vadd.i64 d21,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d17,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d17,#50 + vsli.64 d25,d17,#46 + vmov d29,d17 + vsli.64 d26,d17,#23 +#if 27<16 && defined(__ARMEL__) + vrev64.8 , +#endif + veor d25,d24 + vbsl d29,d18,d19 @ Ch(e,f,g) + vshr.u64 d24,d21,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d20 + vshr.u64 d25,d21,#34 + vsli.64 d24,d21,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d21,#39 + vadd.i64 d28,d11 + vsli.64 d25,d21,#30 + veor d30,d21,d22 + vsli.64 d26,d21,#25 + veor d20,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d23,d22 @ Maj(a,b,c) + veor d20,d26 @ Sigma0(a) + vadd.i64 d16,d27 + vadd.i64 d30,d27 + @ vadd.i64 d20,d30 + vshr.u64 q12,q5,#19 + vshr.u64 q13,q5,#61 + vadd.i64 d20,d30 @ h+=Maj from the past + vshr.u64 q15,q5,#6 + vsli.64 q12,q5,#45 + vext.8 q14,q6,q7,#8 @ X[i+1] + vsli.64 q13,q5,#3 + veor q15,q12 + vshr.u64 q12,q14,#1 + veor q15,q13 @ sigma1(X[i+14]) + vshr.u64 q13,q14,#8 + vadd.i64 q6,q15 + vshr.u64 q15,q14,#7 + vsli.64 q12,q14,#63 + vsli.64 q13,q14,#56 + vext.8 q14,q2,q3,#8 @ X[i+9] + veor q15,q12 + vshr.u64 d24,d16,#14 @ from NEON_00_15 + vadd.i64 q6,q14 + vshr.u64 d25,d16,#18 @ from NEON_00_15 + veor q15,q13 @ sigma0(X[i+1]) + vshr.u64 d26,d16,#41 @ from NEON_00_15 + vadd.i64 q6,q15 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d16,#50 + vsli.64 d25,d16,#46 + vmov d29,d16 + vsli.64 d26,d16,#23 +#if 28<16 && defined(__ARMEL__) + vrev64.8 , +#endif + veor d25,d24 + vbsl d29,d17,d18 @ Ch(e,f,g) + vshr.u64 d24,d20,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d19 + vshr.u64 d25,d20,#34 + vsli.64 d24,d20,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d20,#39 + vadd.i64 d28,d12 + vsli.64 d25,d20,#30 + veor d30,d20,d21 + vsli.64 d26,d20,#25 + veor d19,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d22,d21 @ Maj(a,b,c) + veor d19,d26 @ Sigma0(a) + vadd.i64 d23,d27 + vadd.i64 d30,d27 + @ vadd.i64 d19,d30 + vshr.u64 d24,d23,#14 @ 29 +#if 29<16 + vld1.64 {d13},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d23,#18 +#if 29>0 + vadd.i64 d19,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d23,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d23,#50 + vsli.64 d25,d23,#46 + vmov d29,d23 + vsli.64 d26,d23,#23 +#if 29<16 && defined(__ARMEL__) + vrev64.8 , +#endif + veor d25,d24 + vbsl d29,d16,d17 @ Ch(e,f,g) + vshr.u64 d24,d19,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d18 + vshr.u64 d25,d19,#34 + vsli.64 d24,d19,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d19,#39 + vadd.i64 d28,d13 + vsli.64 d25,d19,#30 + veor d30,d19,d20 + vsli.64 d26,d19,#25 + veor d18,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d21,d20 @ Maj(a,b,c) + veor d18,d26 @ Sigma0(a) + vadd.i64 d22,d27 + vadd.i64 d30,d27 + @ vadd.i64 d18,d30 + vshr.u64 q12,q6,#19 + vshr.u64 q13,q6,#61 + vadd.i64 d18,d30 @ h+=Maj from the past + vshr.u64 q15,q6,#6 + vsli.64 q12,q6,#45 + vext.8 q14,q7,q0,#8 @ X[i+1] + vsli.64 q13,q6,#3 + veor q15,q12 + vshr.u64 q12,q14,#1 + veor q15,q13 @ sigma1(X[i+14]) + vshr.u64 q13,q14,#8 + vadd.i64 q7,q15 + vshr.u64 q15,q14,#7 + vsli.64 q12,q14,#63 + vsli.64 q13,q14,#56 + vext.8 q14,q3,q4,#8 @ X[i+9] + veor q15,q12 + vshr.u64 d24,d22,#14 @ from NEON_00_15 + vadd.i64 q7,q14 + vshr.u64 d25,d22,#18 @ from NEON_00_15 + veor q15,q13 @ sigma0(X[i+1]) + vshr.u64 d26,d22,#41 @ from NEON_00_15 + vadd.i64 q7,q15 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d22,#50 + vsli.64 d25,d22,#46 + vmov d29,d22 + vsli.64 d26,d22,#23 +#if 30<16 && defined(__ARMEL__) + vrev64.8 , +#endif + veor d25,d24 + vbsl d29,d23,d16 @ Ch(e,f,g) + vshr.u64 d24,d18,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d17 + vshr.u64 d25,d18,#34 + vsli.64 d24,d18,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d18,#39 + vadd.i64 d28,d14 + vsli.64 d25,d18,#30 + veor d30,d18,d19 + vsli.64 d26,d18,#25 + veor d17,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d20,d19 @ Maj(a,b,c) + veor d17,d26 @ Sigma0(a) + vadd.i64 d21,d27 + vadd.i64 d30,d27 + @ vadd.i64 d17,d30 + vshr.u64 d24,d21,#14 @ 31 +#if 31<16 + vld1.64 {d15},[r1]! @ handles unaligned +#endif + vshr.u64 d25,d21,#18 +#if 31>0 + vadd.i64 d17,d30 @ h+=Maj from the past +#endif + vshr.u64 d26,d21,#41 + vld1.64 {d28},[r3,:64]! @ K[i++] + vsli.64 d24,d21,#50 + vsli.64 d25,d21,#46 + vmov d29,d21 + vsli.64 d26,d21,#23 +#if 31<16 && defined(__ARMEL__) + vrev64.8 , +#endif + veor d25,d24 + vbsl d29,d22,d23 @ Ch(e,f,g) + vshr.u64 d24,d17,#28 + veor d26,d25 @ Sigma1(e) + vadd.i64 d27,d29,d16 + vshr.u64 d25,d17,#34 + vsli.64 d24,d17,#36 + vadd.i64 d27,d26 + vshr.u64 d26,d17,#39 + vadd.i64 d28,d15 + vsli.64 d25,d17,#30 + veor d30,d17,d18 + vsli.64 d26,d17,#25 + veor d16,d24,d25 + vadd.i64 d27,d28 + vbsl d30,d19,d18 @ Maj(a,b,c) + veor d16,d26 @ Sigma0(a) + vadd.i64 d20,d27 + vadd.i64 d30,d27 + @ vadd.i64 d16,d30 + bne .L16_79_neon + + vadd.i64 d16,d30 @ h+=Maj from the past + vldmia r0,{d24-d31} @ load context to temp + vadd.i64 q8,q12 @ vectorized accumulate + vadd.i64 q9,q13 + vadd.i64 q10,q14 + vadd.i64 q11,q15 + vstmia r0,{d16-d23} @ save context + teq r1,r2 + sub r3,#640 @ rewind K512 + bne .Loop_neon + + VFP_ABI_POP + bx lr @ .word 0xe12fff1e +.size sha512_block_data_order_neon,.-sha512_block_data_order_neon +#endif +.asciz "SHA512 block transform for ARMv4/NEON, CRYPTOGAMS by <appro@openssl.org>" +.align 2 +#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__) +.comm OPENSSL_armcap_P,4,4 +#endif diff --git a/arch/arm/crypto/sha512-glue.c b/arch/arm/crypto/sha512-glue.c new file mode 100644 index 000000000000..269a394e4a53 --- /dev/null +++ b/arch/arm/crypto/sha512-glue.c @@ -0,0 +1,121 @@ +/* + * sha512-glue.c - accelerated SHA-384/512 for ARM + * + * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * 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 <crypto/internal/hash.h> +#include <crypto/sha.h> +#include <crypto/sha512_base.h> +#include <linux/crypto.h> +#include <linux/module.h> + +#include <asm/hwcap.h> +#include <asm/neon.h> + +#include "sha512.h" + +MODULE_DESCRIPTION("Accelerated SHA-384/SHA-512 secure hash for ARM"); +MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>"); +MODULE_LICENSE("GPL v2"); + +MODULE_ALIAS_CRYPTO("sha384"); +MODULE_ALIAS_CRYPTO("sha512"); +MODULE_ALIAS_CRYPTO("sha384-arm"); +MODULE_ALIAS_CRYPTO("sha512-arm"); + +asmlinkage void sha512_block_data_order(u64 *state, u8 const *src, int blocks); + +int sha512_arm_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + return sha512_base_do_update(desc, data, len, + (sha512_block_fn *)sha512_block_data_order); +} + +int sha512_arm_final(struct shash_desc *desc, u8 *out) +{ + sha512_base_do_finalize(desc, + (sha512_block_fn *)sha512_block_data_order); + return sha512_base_finish(desc, out); +} + +int sha512_arm_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + sha512_base_do_update(desc, data, len, + (sha512_block_fn *)sha512_block_data_order); + return sha512_arm_final(desc, out); +} + +static struct shash_alg sha512_arm_algs[] = { { + .init = sha384_base_init, + .update = sha512_arm_update, + .final = sha512_arm_final, + .finup = sha512_arm_finup, + .descsize = sizeof(struct sha512_state), + .digestsize = SHA384_DIGEST_SIZE, + .base = { + .cra_name = "sha384", + .cra_driver_name = "sha384-arm", + .cra_priority = 250, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +}, { + .init = sha512_base_init, + .update = sha512_arm_update, + .final = sha512_arm_final, + .finup = sha512_arm_finup, + .descsize = sizeof(struct sha512_state), + .digestsize = SHA512_DIGEST_SIZE, + .base = { + .cra_name = "sha512", + .cra_driver_name = "sha512-arm", + .cra_priority = 250, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +} }; + +static int __init sha512_arm_mod_init(void) +{ + int err; + + err = crypto_register_shashes(sha512_arm_algs, + ARRAY_SIZE(sha512_arm_algs)); + if (err) + return err; + + if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon()) { + err = crypto_register_shashes(sha512_neon_algs, + ARRAY_SIZE(sha512_neon_algs)); + if (err) + goto err_unregister; + } + return 0; + +err_unregister: + crypto_unregister_shashes(sha512_arm_algs, + ARRAY_SIZE(sha512_arm_algs)); + + return err; +} + +static void __exit sha512_arm_mod_fini(void) +{ + crypto_unregister_shashes(sha512_arm_algs, + ARRAY_SIZE(sha512_arm_algs)); + if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon()) + crypto_unregister_shashes(sha512_neon_algs, + ARRAY_SIZE(sha512_neon_algs)); +} + +module_init(sha512_arm_mod_init); +module_exit(sha512_arm_mod_fini); diff --git a/arch/arm/crypto/sha512-neon-glue.c b/arch/arm/crypto/sha512-neon-glue.c new file mode 100644 index 000000000000..32693684a3ab --- /dev/null +++ b/arch/arm/crypto/sha512-neon-glue.c @@ -0,0 +1,98 @@ +/* + * sha512-neon-glue.c - accelerated SHA-384/512 for ARM NEON + * + * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * 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 <crypto/internal/hash.h> +#include <crypto/sha.h> +#include <crypto/sha512_base.h> +#include <linux/crypto.h> +#include <linux/module.h> + +#include <asm/simd.h> +#include <asm/neon.h> + +#include "sha512.h" + +MODULE_ALIAS_CRYPTO("sha384-neon"); +MODULE_ALIAS_CRYPTO("sha512-neon"); + +asmlinkage void sha512_block_data_order_neon(u64 *state, u8 const *src, + int blocks); + +static int sha512_neon_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + struct sha512_state *sctx = shash_desc_ctx(desc); + + if (!may_use_simd() || + (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE) + return sha512_arm_update(desc, data, len); + + kernel_neon_begin(); + sha512_base_do_update(desc, data, len, + (sha512_block_fn *)sha512_block_data_order_neon); + kernel_neon_end(); + + return 0; +} + +static int sha512_neon_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + if (!may_use_simd()) + return sha512_arm_finup(desc, data, len, out); + + kernel_neon_begin(); + if (len) + sha512_base_do_update(desc, data, len, + (sha512_block_fn *)sha512_block_data_order_neon); + sha512_base_do_finalize(desc, + (sha512_block_fn *)sha512_block_data_order_neon); + kernel_neon_end(); + + return sha512_base_finish(desc, out); +} + +static int sha512_neon_final(struct shash_desc *desc, u8 *out) +{ + return sha512_neon_finup(desc, NULL, 0, out); +} + +struct shash_alg sha512_neon_algs[] = { { + .init = sha384_base_init, + .update = sha512_neon_update, + .final = sha512_neon_final, + .finup = sha512_neon_finup, + .descsize = sizeof(struct sha512_state), + .digestsize = SHA384_DIGEST_SIZE, + .base = { + .cra_name = "sha384", + .cra_driver_name = "sha384-neon", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA384_BLOCK_SIZE, + .cra_module = THIS_MODULE, + + } +}, { + .init = sha512_base_init, + .update = sha512_neon_update, + .final = sha512_neon_final, + .finup = sha512_neon_finup, + .descsize = sizeof(struct sha512_state), + .digestsize = SHA512_DIGEST_SIZE, + .base = { + .cra_name = "sha512", + .cra_driver_name = "sha512-neon", + .cra_priority = 300, + .cra_flags = CRYPTO_ALG_TYPE_SHASH, + .cra_blocksize = SHA512_BLOCK_SIZE, + .cra_module = THIS_MODULE, + } +} }; diff --git a/arch/arm/crypto/sha512.h b/arch/arm/crypto/sha512.h new file mode 100644 index 000000000000..a75d9a82988a --- /dev/null +++ b/arch/arm/crypto/sha512.h @@ -0,0 +1,8 @@ + +int sha512_arm_update(struct shash_desc *desc, const u8 *data, + unsigned int len); + +int sha512_arm_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out); + +extern struct shash_alg sha512_neon_algs[2]; diff --git a/arch/arm/crypto/sha512_neon_glue.c b/arch/arm/crypto/sha512_neon_glue.c deleted file mode 100644 index b124dce838d6..000000000000 --- a/arch/arm/crypto/sha512_neon_glue.c +++ /dev/null @@ -1,305 +0,0 @@ -/* - * Glue code for the SHA512 Secure Hash Algorithm assembly implementation - * using NEON instructions. - * - * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi> - * - * This file is based on sha512_ssse3_glue.c: - * Copyright (C) 2013 Intel Corporation - * Author: Tim Chen <tim.c.chen@linux.intel.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 <crypto/internal/hash.h> -#include <linux/init.h> -#include <linux/module.h> -#include <linux/mm.h> -#include <linux/cryptohash.h> -#include <linux/types.h> -#include <linux/string.h> -#include <crypto/sha.h> -#include <asm/byteorder.h> -#include <asm/simd.h> -#include <asm/neon.h> - - -static const u64 sha512_k[] = { - 0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL, - 0xb5c0fbcfec4d3b2fULL, 0xe9b5dba58189dbbcULL, - 0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL, - 0x923f82a4af194f9bULL, 0xab1c5ed5da6d8118ULL, - 0xd807aa98a3030242ULL, 0x12835b0145706fbeULL, - 0x243185be4ee4b28cULL, 0x550c7dc3d5ffb4e2ULL, - 0x72be5d74f27b896fULL, 0x80deb1fe3b1696b1ULL, - 0x9bdc06a725c71235ULL, 0xc19bf174cf692694ULL, - 0xe49b69c19ef14ad2ULL, 0xefbe4786384f25e3ULL, - 0x0fc19dc68b8cd5b5ULL, 0x240ca1cc77ac9c65ULL, - 0x2de92c6f592b0275ULL, 0x4a7484aa6ea6e483ULL, - 0x5cb0a9dcbd41fbd4ULL, 0x76f988da831153b5ULL, - 0x983e5152ee66dfabULL, 0xa831c66d2db43210ULL, - 0xb00327c898fb213fULL, 0xbf597fc7beef0ee4ULL, - 0xc6e00bf33da88fc2ULL, 0xd5a79147930aa725ULL, - 0x06ca6351e003826fULL, 0x142929670a0e6e70ULL, - 0x27b70a8546d22ffcULL, 0x2e1b21385c26c926ULL, - 0x4d2c6dfc5ac42aedULL, 0x53380d139d95b3dfULL, - 0x650a73548baf63deULL, 0x766a0abb3c77b2a8ULL, - 0x81c2c92e47edaee6ULL, 0x92722c851482353bULL, - 0xa2bfe8a14cf10364ULL, 0xa81a664bbc423001ULL, - 0xc24b8b70d0f89791ULL, 0xc76c51a30654be30ULL, - 0xd192e819d6ef5218ULL, 0xd69906245565a910ULL, - 0xf40e35855771202aULL, 0x106aa07032bbd1b8ULL, - 0x19a4c116b8d2d0c8ULL, 0x1e376c085141ab53ULL, - 0x2748774cdf8eeb99ULL, 0x34b0bcb5e19b48a8ULL, - 0x391c0cb3c5c95a63ULL, 0x4ed8aa4ae3418acbULL, - 0x5b9cca4f7763e373ULL, 0x682e6ff3d6b2b8a3ULL, - 0x748f82ee5defb2fcULL, 0x78a5636f43172f60ULL, - 0x84c87814a1f0ab72ULL, 0x8cc702081a6439ecULL, - 0x90befffa23631e28ULL, 0xa4506cebde82bde9ULL, - 0xbef9a3f7b2c67915ULL, 0xc67178f2e372532bULL, - 0xca273eceea26619cULL, 0xd186b8c721c0c207ULL, - 0xeada7dd6cde0eb1eULL, 0xf57d4f7fee6ed178ULL, - 0x06f067aa72176fbaULL, 0x0a637dc5a2c898a6ULL, - 0x113f9804bef90daeULL, 0x1b710b35131c471bULL, - 0x28db77f523047d84ULL, 0x32caab7b40c72493ULL, - 0x3c9ebe0a15c9bebcULL, 0x431d67c49c100d4cULL, - 0x4cc5d4becb3e42b6ULL, 0x597f299cfc657e2aULL, - 0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL -}; - - -asmlinkage void sha512_transform_neon(u64 *digest, const void *data, - const u64 k[], unsigned int num_blks); - - -static int sha512_neon_init(struct shash_desc *desc) -{ - struct sha512_state *sctx = shash_desc_ctx(desc); - - sctx->state[0] = SHA512_H0; - sctx->state[1] = SHA512_H1; - sctx->state[2] = SHA512_H2; - sctx->state[3] = SHA512_H3; - sctx->state[4] = SHA512_H4; - sctx->state[5] = SHA512_H5; - sctx->state[6] = SHA512_H6; - sctx->state[7] = SHA512_H7; - sctx->count[0] = sctx->count[1] = 0; - - return 0; -} - -static int __sha512_neon_update(struct shash_desc *desc, const u8 *data, - unsigned int len, unsigned int partial) -{ - struct sha512_state *sctx = shash_desc_ctx(desc); - unsigned int done = 0; - - sctx->count[0] += len; - if (sctx->count[0] < len) - sctx->count[1]++; - - if (partial) { - done = SHA512_BLOCK_SIZE - partial; - memcpy(sctx->buf + partial, data, done); - sha512_transform_neon(sctx->state, sctx->buf, sha512_k, 1); - } - - if (len - done >= SHA512_BLOCK_SIZE) { - const unsigned int rounds = (len - done) / SHA512_BLOCK_SIZE; - - sha512_transform_neon(sctx->state, data + done, sha512_k, - rounds); - - done += rounds * SHA512_BLOCK_SIZE; - } - - memcpy(sctx->buf, data + done, len - done); - - return 0; -} - -static int sha512_neon_update(struct shash_desc *desc, const u8 *data, - unsigned int len) -{ - struct sha512_state *sctx = shash_desc_ctx(desc); - unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE; - int res; - - /* Handle the fast case right here */ - if (partial + len < SHA512_BLOCK_SIZE) { - sctx->count[0] += len; - if (sctx->count[0] < len) - sctx->count[1]++; - memcpy(sctx->buf + partial, data, len); - - return 0; - } - - if (!may_use_simd()) { - res = crypto_sha512_update(desc, data, len); - } else { - kernel_neon_begin(); - res = __sha512_neon_update(desc, data, len, partial); - kernel_neon_end(); - } - - return res; -} - - -/* Add padding and return the message digest. */ -static int sha512_neon_final(struct shash_desc *desc, u8 *out) -{ - struct sha512_state *sctx = shash_desc_ctx(desc); - unsigned int i, index, padlen; - __be64 *dst = (__be64 *)out; - __be64 bits[2]; - static const u8 padding[SHA512_BLOCK_SIZE] = { 0x80, }; - - /* save number of bits */ - bits[1] = cpu_to_be64(sctx->count[0] << 3); - bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61); - - /* Pad out to 112 mod 128 and append length */ - index = sctx->count[0] & 0x7f; - padlen = (index < 112) ? (112 - index) : ((128+112) - index); - - if (!may_use_simd()) { - crypto_sha512_update(desc, padding, padlen); - crypto_sha512_update(desc, (const u8 *)&bits, sizeof(bits)); - } else { - kernel_neon_begin(); - /* We need to fill a whole block for __sha512_neon_update() */ - if (padlen <= 112) { - sctx->count[0] += padlen; - if (sctx->count[0] < padlen) - sctx->count[1]++; - memcpy(sctx->buf + index, padding, padlen); - } else { - __sha512_neon_update(desc, padding, padlen, index); - } - __sha512_neon_update(desc, (const u8 *)&bits, - sizeof(bits), 112); - kernel_neon_end(); - } - - /* Store state in digest */ - for (i = 0; i < 8; i++) - dst[i] = cpu_to_be64(sctx->state[i]); - - /* Wipe context */ - memset(sctx, 0, sizeof(*sctx)); - - return 0; -} - -static int sha512_neon_export(struct shash_desc *desc, void *out) -{ - struct sha512_state *sctx = shash_desc_ctx(desc); - - memcpy(out, sctx, sizeof(*sctx)); - - return 0; -} - -static int sha512_neon_import(struct shash_desc *desc, const void *in) -{ - struct sha512_state *sctx = shash_desc_ctx(desc); - - memcpy(sctx, in, sizeof(*sctx)); - - return 0; -} - -static int sha384_neon_init(struct shash_desc *desc) -{ - struct sha512_state *sctx = shash_desc_ctx(desc); - - sctx->state[0] = SHA384_H0; - sctx->state[1] = SHA384_H1; - sctx->state[2] = SHA384_H2; - sctx->state[3] = SHA384_H3; - sctx->state[4] = SHA384_H4; - sctx->state[5] = SHA384_H5; - sctx->state[6] = SHA384_H6; - sctx->state[7] = SHA384_H7; - - sctx->count[0] = sctx->count[1] = 0; - - return 0; -} - -static int sha384_neon_final(struct shash_desc *desc, u8 *hash) -{ - u8 D[SHA512_DIGEST_SIZE]; - - sha512_neon_final(desc, D); - - memcpy(hash, D, SHA384_DIGEST_SIZE); - memzero_explicit(D, SHA512_DIGEST_SIZE); - - return 0; -} - -static struct shash_alg algs[] = { { - .digestsize = SHA512_DIGEST_SIZE, - .init = sha512_neon_init, - .update = sha512_neon_update, - .final = sha512_neon_final, - .export = sha512_neon_export, - .import = sha512_neon_import, - .descsize = sizeof(struct sha512_state), - .statesize = sizeof(struct sha512_state), - .base = { - .cra_name = "sha512", - .cra_driver_name = "sha512-neon", - .cra_priority = 250, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, - .cra_blocksize = SHA512_BLOCK_SIZE, - .cra_module = THIS_MODULE, - } -}, { - .digestsize = SHA384_DIGEST_SIZE, - .init = sha384_neon_init, - .update = sha512_neon_update, - .final = sha384_neon_final, - .export = sha512_neon_export, - .import = sha512_neon_import, - .descsize = sizeof(struct sha512_state), - .statesize = sizeof(struct sha512_state), - .base = { - .cra_name = "sha384", - .cra_driver_name = "sha384-neon", - .cra_priority = 250, - .cra_flags = CRYPTO_ALG_TYPE_SHASH, - .cra_blocksize = SHA384_BLOCK_SIZE, - .cra_module = THIS_MODULE, - } -} }; - -static int __init sha512_neon_mod_init(void) -{ - if (!cpu_has_neon()) - return -ENODEV; - - return crypto_register_shashes(algs, ARRAY_SIZE(algs)); -} - -static void __exit sha512_neon_mod_fini(void) -{ - crypto_unregister_shashes(algs, ARRAY_SIZE(algs)); -} - -module_init(sha512_neon_mod_init); -module_exit(sha512_neon_mod_fini); - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, NEON accelerated"); - -MODULE_ALIAS_CRYPTO("sha512"); -MODULE_ALIAS_CRYPTO("sha384"); diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h index d2f81e6b8c1c..6c2327e1c732 100644 --- a/arch/arm/include/asm/barrier.h +++ b/arch/arm/include/asm/barrier.h @@ -81,7 +81,7 @@ do { \ #define read_barrier_depends() do { } while(0) #define smp_read_barrier_depends() do { } while(0) -#define set_mb(var, value) do { var = value; smp_mb(); } while (0) +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0) #define smp_mb__before_atomic() smp_mb() #define smp_mb__after_atomic() smp_mb() diff --git a/arch/arm/include/asm/dma-iommu.h b/arch/arm/include/asm/dma-iommu.h index 8e3fcb924db6..2ef282f96651 100644 --- a/arch/arm/include/asm/dma-iommu.h +++ b/arch/arm/include/asm/dma-iommu.h @@ -25,7 +25,7 @@ struct dma_iommu_mapping { }; struct dma_iommu_mapping * -arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size); +arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, u64 size); void arm_iommu_release_mapping(struct dma_iommu_mapping *mapping); diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h index 4e78065a16aa..5eed82809d82 100644 --- a/arch/arm/include/asm/futex.h +++ b/arch/arm/include/asm/futex.h @@ -93,6 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; + preempt_disable(); __asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n" "1: " TUSER(ldr) " %1, [%4]\n" " teq %1, %2\n" @@ -104,6 +105,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, : "cc", "memory"); *uval = val; + preempt_enable(); + return ret; } @@ -124,7 +127,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32))) return -EFAULT; - pagefault_disable(); /* implies preempt_disable() */ +#ifndef CONFIG_SMP + preempt_disable(); +#endif + pagefault_disable(); switch (op) { case FUTEX_OP_SET: @@ -146,7 +152,10 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr) ret = -ENOSYS; } - pagefault_enable(); /* subsumes preempt_enable() */ + pagefault_enable(); +#ifndef CONFIG_SMP + preempt_enable(); +#endif if (!ret) { switch (cmp) { diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h index db58deb00aa7..1b7677d1e5e1 100644 --- a/arch/arm/include/asm/io.h +++ b/arch/arm/include/asm/io.h @@ -336,6 +336,7 @@ extern void _memset_io(volatile void __iomem *, int, size_t); #define ioremap_nocache(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE) #define ioremap_cache(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_CACHED) #define ioremap_wc(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE_WC) +#define ioremap_wt(cookie,size) __arm_ioremap((cookie), (size), MT_DEVICE) #define iounmap __arm_iounmap /* diff --git a/arch/arm/include/asm/kvm_asm.h b/arch/arm/include/asm/kvm_asm.h index 25410b2d8bc1..194c91b610ff 100644 --- a/arch/arm/include/asm/kvm_asm.h +++ b/arch/arm/include/asm/kvm_asm.h @@ -23,7 +23,7 @@ #define c0_MPIDR 1 /* MultiProcessor ID Register */ #define c0_CSSELR 2 /* Cache Size Selection Register */ #define c1_SCTLR 3 /* System Control Register */ -#define c1_ACTLR 4 /* Auxilliary Control Register */ +#define c1_ACTLR 4 /* Auxiliary Control Register */ #define c1_CPACR 5 /* Coprocessor Access Control */ #define c2_TTBR0 6 /* Translation Table Base Register 0 */ #define c2_TTBR0_high 7 /* TTBR0 top 32 bits */ diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h index 585dc33a7a24..a5635444ca41 100644 --- a/arch/arm/include/asm/pci.h +++ b/arch/arm/include/asm/pci.h @@ -31,16 +31,6 @@ static inline int pci_proc_domain(struct pci_bus *bus) */ #define PCI_DMA_BUS_IS_PHYS (1) -#ifdef CONFIG_PCI -static inline void pci_dma_burst_advice(struct pci_dev *pdev, - enum pci_dma_burst_strategy *strat, - unsigned long *strategy_parameter) -{ - *strat = PCI_DMA_BURST_INFINITY; - *strategy_parameter = ~0UL; -} -#endif - #define HAVE_PCI_MMAP extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, enum pci_mmap_state mmap_state, int write_combine); diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index 2fe85fff5cca..370f7a732900 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -18,7 +18,7 @@ extern struct cputopo_arm cpu_topology[NR_CPUS]; #define topology_physical_package_id(cpu) (cpu_topology[cpu].socket_id) #define topology_core_id(cpu) (cpu_topology[cpu].core_id) #define topology_core_cpumask(cpu) (&cpu_topology[cpu].core_sibling) -#define topology_thread_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) +#define topology_sibling_cpumask(cpu) (&cpu_topology[cpu].thread_sibling) void init_cpu_topology(void); void store_cpu_topology(unsigned int cpuid); diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h index 2f7e6ff67d51..0b579b2f4e0e 100644 --- a/arch/arm/include/asm/xen/page.h +++ b/arch/arm/include/asm/xen/page.h @@ -110,5 +110,6 @@ static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) bool xen_arch_need_swiotlb(struct device *dev, unsigned long pfn, unsigned long mfn); +unsigned long xen_get_swiotlb_free_pages(unsigned int order); #endif /* _ASM_ARM_XEN_PAGE_H */ diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S index f8ccc21fa032..4e7f40c577e6 100644 --- a/arch/arm/kernel/entry-common.S +++ b/arch/arm/kernel/entry-common.S @@ -33,7 +33,9 @@ ret_fast_syscall: UNWIND(.fnstart ) UNWIND(.cantunwind ) disable_irq @ disable interrupts - ldr r1, [tsk, #TI_FLAGS] + ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing + tst r1, #_TIF_SYSCALL_WORK + bne __sys_trace_return tst r1, #_TIF_WORK_MASK bne fast_work_pending asm_trace_hardirqs_on diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c index 91c7ba182dcd..3b8c2833c537 100644 --- a/arch/arm/kernel/perf_event_cpu.c +++ b/arch/arm/kernel/perf_event_cpu.c @@ -303,9 +303,15 @@ static int probe_current_pmu(struct arm_pmu *pmu) static int of_pmu_irq_cfg(struct platform_device *pdev) { - int i; - int *irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL); + int i, irq; + int *irqs; + /* Don't bother with PPIs; they're already affine */ + irq = platform_get_irq(pdev, 0); + if (irq >= 0 && irq_is_percpu(irq)) + return 0; + + irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL); if (!irqs) return -ENOMEM; @@ -317,7 +323,7 @@ static int of_pmu_irq_cfg(struct platform_device *pdev) i); if (!dn) { pr_warn("Failed to parse %s/interrupt-affinity[%d]\n", - of_node_full_name(dn), i); + of_node_full_name(pdev->dev.of_node), i); break; } diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S index 947567ff67f9..af2267f6a529 100644 --- a/arch/arm/lib/lib1funcs.S +++ b/arch/arm/lib/lib1funcs.S @@ -167,7 +167,7 @@ Boston, MA 02111-1307, USA. */ #endif - @ Perform all needed substractions to keep only the reminder. + @ Perform all needed subtractions to keep only the reminder. @ Do comparisons in batch of 4 first. subs \order, \order, #3 @ yes, 3 is intended here blt 2f @@ -189,7 +189,7 @@ Boston, MA 02111-1307, USA. */ teqne \dividend, #0 beq 5f - @ Either 1, 2 or 3 comparison/substractions are left. + @ Either 1, 2 or 3 comparison/subtractions are left. 2: cmn \order, #2 blt 4f beq 3f diff --git a/arch/arm/mach-davinci/pm_domain.c b/arch/arm/mach-davinci/pm_domain.c index 641edc313938..78eac2c0c146 100644 --- a/arch/arm/mach-davinci/pm_domain.c +++ b/arch/arm/mach-davinci/pm_domain.c @@ -14,39 +14,9 @@ #include <linux/pm_clock.h> #include <linux/platform_device.h> -#ifdef CONFIG_PM -static int davinci_pm_runtime_suspend(struct device *dev) -{ - int ret; - - dev_dbg(dev, "%s\n", __func__); - - ret = pm_generic_runtime_suspend(dev); - if (ret) - return ret; - - ret = pm_clk_suspend(dev); - if (ret) { - pm_generic_runtime_resume(dev); - return ret; - } - - return 0; -} - -static int davinci_pm_runtime_resume(struct device *dev) -{ - dev_dbg(dev, "%s\n", __func__); - - pm_clk_resume(dev); - return pm_generic_runtime_resume(dev); -} -#endif - static struct dev_pm_domain davinci_pm_domain = { .ops = { - SET_RUNTIME_PM_OPS(davinci_pm_runtime_suspend, - davinci_pm_runtime_resume, NULL) + USE_PM_CLK_RUNTIME_OPS USE_PLATFORM_PM_SLEEP_OPS }, }; diff --git a/arch/arm/mach-exynos/common.h b/arch/arm/mach-exynos/common.h index acd5b560b728..5f5cd562c593 100644 --- a/arch/arm/mach-exynos/common.h +++ b/arch/arm/mach-exynos/common.h @@ -159,6 +159,8 @@ extern void exynos_enter_aftr(void); extern struct cpuidle_exynos_data cpuidle_coupled_exynos_data; +extern void exynos_set_delayed_reset_assertion(bool enable); + extern void s5p_init_cpu(void __iomem *cpuid_addr); extern unsigned int samsung_rev(void); extern void __iomem *cpu_boot_reg_base(void); diff --git a/arch/arm/mach-exynos/exynos.c b/arch/arm/mach-exynos/exynos.c index bcde0dd668df..5917a30eee33 100644 --- a/arch/arm/mach-exynos/exynos.c +++ b/arch/arm/mach-exynos/exynos.c @@ -167,6 +167,33 @@ static void __init exynos_init_io(void) } /* + * Set or clear the USE_DELAYED_RESET_ASSERTION option. Used by smp code + * and suspend. + * + * This is necessary only on Exynos4 SoCs. When system is running + * USE_DELAYED_RESET_ASSERTION should be set so the ARM CLK clock down + * feature could properly detect global idle state when secondary CPU is + * powered down. + * + * However this should not be set when such system is going into suspend. + */ +void exynos_set_delayed_reset_assertion(bool enable) +{ + if (of_machine_is_compatible("samsung,exynos4")) { + unsigned int tmp, core_id; + + for (core_id = 0; core_id < num_possible_cpus(); core_id++) { + tmp = pmu_raw_readl(EXYNOS_ARM_CORE_OPTION(core_id)); + if (enable) + tmp |= S5P_USE_DELAYED_RESET_ASSERTION; + else + tmp &= ~(S5P_USE_DELAYED_RESET_ASSERTION); + pmu_raw_writel(tmp, EXYNOS_ARM_CORE_OPTION(core_id)); + } + } +} + +/* * Apparently, these SoCs are not able to wake-up from suspend using * the PMU. Too bad. Should they suddenly become capable of such a * feat, the matches below should be moved to suspend.c. diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c index ebd135bb0995..a825bca2a2b6 100644 --- a/arch/arm/mach-exynos/platsmp.c +++ b/arch/arm/mach-exynos/platsmp.c @@ -34,30 +34,6 @@ extern void exynos4_secondary_startup(void); -/* - * Set or clear the USE_DELAYED_RESET_ASSERTION option, set on Exynos4 SoCs - * during hot-(un)plugging CPUx. - * - * The feature can be cleared safely during first boot of secondary CPU. - * - * Exynos4 SoCs require setting USE_DELAYED_RESET_ASSERTION during powering - * down a CPU so the CPU idle clock down feature could properly detect global - * idle state when CPUx is off. - */ -static void exynos_set_delayed_reset_assertion(u32 core_id, bool enable) -{ - if (soc_is_exynos4()) { - unsigned int tmp; - - tmp = pmu_raw_readl(EXYNOS_ARM_CORE_OPTION(core_id)); - if (enable) - tmp |= S5P_USE_DELAYED_RESET_ASSERTION; - else - tmp &= ~(S5P_USE_DELAYED_RESET_ASSERTION); - pmu_raw_writel(tmp, EXYNOS_ARM_CORE_OPTION(core_id)); - } -} - #ifdef CONFIG_HOTPLUG_CPU static inline void cpu_leave_lowpower(u32 core_id) { @@ -73,8 +49,6 @@ static inline void cpu_leave_lowpower(u32 core_id) : "=&r" (v) : "Ir" (CR_C), "Ir" (0x40) : "cc"); - - exynos_set_delayed_reset_assertion(core_id, false); } static inline void platform_do_lowpower(unsigned int cpu, int *spurious) @@ -87,14 +61,6 @@ static inline void platform_do_lowpower(unsigned int cpu, int *spurious) /* Turn the CPU off on next WFI instruction. */ exynos_cpu_power_down(core_id); - /* - * Exynos4 SoCs require setting - * USE_DELAYED_RESET_ASSERTION so the CPU idle - * clock down feature could properly detect - * global idle state when CPUx is off. - */ - exynos_set_delayed_reset_assertion(core_id, true); - wfi(); if (pen_release == core_id) { @@ -371,9 +337,6 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle) udelay(10); } - /* No harm if this is called during first boot of secondary CPU */ - exynos_set_delayed_reset_assertion(core_id, false); - /* * now the secondary core is starting up let it run its * calibrations, then wait for it to finish @@ -420,6 +383,8 @@ static void __init exynos_smp_prepare_cpus(unsigned int max_cpus) exynos_sysram_init(); + exynos_set_delayed_reset_assertion(true); + if (read_cpuid_part() == ARM_CPU_PART_CORTEX_A9) scu_enable(scu_base_addr()); diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c index cbe56b35aea0..a9686535f9ed 100644 --- a/arch/arm/mach-exynos/pm_domains.c +++ b/arch/arm/mach-exynos/pm_domains.c @@ -188,7 +188,7 @@ no_clk: args.np = np; args.args_count = 0; child_domain = of_genpd_get_from_provider(&args); - if (!child_domain) + if (IS_ERR(child_domain)) continue; if (of_parse_phandle_with_args(np, "power-domains", @@ -196,7 +196,7 @@ no_clk: continue; parent_domain = of_genpd_get_from_provider(&args); - if (!parent_domain) + if (IS_ERR(parent_domain)) continue; if (pm_genpd_add_subdomain(parent_domain, child_domain)) diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c index 3e6aea7f83af..7d23ce04cad5 100644 --- a/arch/arm/mach-exynos/suspend.c +++ b/arch/arm/mach-exynos/suspend.c @@ -87,8 +87,8 @@ static unsigned int exynos_pmu_spare3; static u32 exynos_irqwake_intmask = 0xffffffff; static const struct exynos_wkup_irq exynos3250_wkup_irq[] = { - { 105, BIT(1) }, /* RTC alarm */ - { 106, BIT(2) }, /* RTC tick */ + { 73, BIT(1) }, /* RTC alarm */ + { 74, BIT(2) }, /* RTC tick */ { /* sentinel */ }, }; @@ -342,6 +342,8 @@ static void exynos_pm_enter_sleep_mode(void) static void exynos_pm_prepare(void) { + exynos_set_delayed_reset_assertion(false); + /* Set wake-up mask registers */ exynos_pm_set_wakeup_mask(); @@ -482,6 +484,7 @@ early_wakeup: /* Clear SLEEP mode set in INFORM1 */ pmu_raw_writel(0x0, S5P_INFORM1); + exynos_set_delayed_reset_assertion(true); } static void exynos3250_pm_resume(void) @@ -723,8 +726,10 @@ void __init exynos_pm_init(void) return; } - if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL))) + if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL))) { pr_warn("Outdated DT detected, suspend/resume will NOT work\n"); + return; + } pm_data = (const struct exynos_pm_data *) match->data; diff --git a/arch/arm/mach-gemini/common.h b/arch/arm/mach-gemini/common.h index 38a45260a7c8..dd883698ff7e 100644 --- a/arch/arm/mach-gemini/common.h +++ b/arch/arm/mach-gemini/common.h @@ -12,6 +12,8 @@ #ifndef __GEMINI_COMMON_H__ #define __GEMINI_COMMON_H__ +#include <linux/reboot.h> + struct mtd_partition; extern void gemini_map_io(void); @@ -26,6 +28,6 @@ extern int platform_register_pflash(unsigned int size, struct mtd_partition *parts, unsigned int nr_parts); -extern void gemini_restart(char mode, const char *cmd); +extern void gemini_restart(enum reboot_mode mode, const char *cmd); #endif /* __GEMINI_COMMON_H__ */ diff --git a/arch/arm/mach-gemini/gpio.c b/arch/arm/mach-gemini/gpio.c index f8cb5710d6ee..3292f2e6ed6f 100644 --- a/arch/arm/mach-gemini/gpio.c +++ b/arch/arm/mach-gemini/gpio.c @@ -223,8 +223,8 @@ void __init gemini_gpio_init(void) set_irq_flags(j, IRQF_VALID); } - irq_set_chained_handler(IRQ_GPIO(i), gpio_irq_handler); - irq_set_handler_data(IRQ_GPIO(i), (void *)i); + irq_set_chained_handler_and_data(IRQ_GPIO(i), gpio_irq_handler, + (void *)i); } BUG_ON(gpiochip_add(&gemini_gpio_chip)); diff --git a/arch/arm/mach-gemini/reset.c b/arch/arm/mach-gemini/reset.c index b26659759e27..21a6d6d4f9c4 100644 --- a/arch/arm/mach-gemini/reset.c +++ b/arch/arm/mach-gemini/reset.c @@ -14,7 +14,9 @@ #include <mach/hardware.h> #include <mach/global_reg.h> -void gemini_restart(char mode, const char *cmd) +#include "common.h" + +void gemini_restart(enum reboot_mode mode, const char *cmd) { __raw_writel(RESET_GLOBAL | RESET_CPU1, IO_ADDRESS(GEMINI_GLOBAL_BASE) + GLOBAL_RESET); diff --git a/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c b/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c index fb8d4a2ad48c..a5edd7d60266 100644 --- a/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c +++ b/arch/arm/mach-imx/devices/platform-sdhci-esdhc-imx.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010 Pengutronix, Wolfram Sang <w.sang@pengutronix.de> + * Copyright (C) 2010 Pengutronix, Wolfram Sang <kernel@pengutronix.de> * * This program is free software; you can redistribute it and/or modify it under * the terms of the GNU General Public License version 2 as published by the diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c index 4d60005e9277..6d0893a3828e 100644 --- a/arch/arm/mach-imx/gpc.c +++ b/arch/arm/mach-imx/gpc.c @@ -280,9 +280,15 @@ void __init imx_gpc_check_dt(void) struct device_node *np; np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-gpc"); - if (WARN_ON(!np || - !of_find_property(np, "interrupt-controller", NULL))) - pr_warn("Outdated DT detected, system is about to crash!!!\n"); + if (WARN_ON(!np)) + return; + + if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL))) { + pr_warn("Outdated DT detected, suspend/resume will NOT work\n"); + + /* map GPC, so that at least CPUidle and WARs keep working */ + gpc_base = of_iomap(np, 0); + } } #ifdef CONFIG_PM_GENERIC_DOMAINS @@ -443,6 +449,10 @@ static int imx_gpc_probe(struct platform_device *pdev) struct regulator *pu_reg; int ret; + /* bail out if DT too old and doesn't provide the necessary info */ + if (!of_property_read_bool(pdev->dev.of_node, "#power-domain-cells")) + return 0; + pu_reg = devm_regulator_get_optional(&pdev->dev, "pu"); if (PTR_ERR(pu_reg) == -ENODEV) pu_reg = NULL; diff --git a/arch/arm/mach-keystone/pm_domain.c b/arch/arm/mach-keystone/pm_domain.c index 41bebfd296dc..edea697e8253 100644 --- a/arch/arm/mach-keystone/pm_domain.c +++ b/arch/arm/mach-keystone/pm_domain.c @@ -19,40 +19,9 @@ #include <linux/clk-provider.h> #include <linux/of.h> -#ifdef CONFIG_PM -static int keystone_pm_runtime_suspend(struct device *dev) -{ - int ret; - - dev_dbg(dev, "%s\n", __func__); - - ret = pm_generic_runtime_suspend(dev); - if (ret) - return ret; - - ret = pm_clk_suspend(dev); - if (ret) { - pm_generic_runtime_resume(dev); - return ret; - } - - return 0; -} - -static int keystone_pm_runtime_resume(struct device *dev) -{ - dev_dbg(dev, "%s\n", __func__); - - pm_clk_resume(dev); - - return pm_generic_runtime_resume(dev); -} -#endif - static struct dev_pm_domain keystone_pm_domain = { .ops = { - SET_RUNTIME_PM_OPS(keystone_pm_runtime_suspend, - keystone_pm_runtime_resume, NULL) + USE_PM_CLK_RUNTIME_OPS USE_PLATFORM_PM_SLEEP_OPS }, }; diff --git a/arch/arm/mach-omap1/pm_bus.c b/arch/arm/mach-omap1/pm_bus.c index c40e209de65c..667c1637ff91 100644 --- a/arch/arm/mach-omap1/pm_bus.c +++ b/arch/arm/mach-omap1/pm_bus.c @@ -21,48 +21,15 @@ #include "soc.h" -#ifdef CONFIG_PM -static int omap1_pm_runtime_suspend(struct device *dev) -{ - int ret; - - dev_dbg(dev, "%s\n", __func__); - - ret = pm_generic_runtime_suspend(dev); - if (ret) - return ret; - - ret = pm_clk_suspend(dev); - if (ret) { - pm_generic_runtime_resume(dev); - return ret; - } - - return 0; -} - -static int omap1_pm_runtime_resume(struct device *dev) -{ - dev_dbg(dev, "%s\n", __func__); - - pm_clk_resume(dev); - return pm_generic_runtime_resume(dev); -} - static struct dev_pm_domain default_pm_domain = { .ops = { - .runtime_suspend = omap1_pm_runtime_suspend, - .runtime_resume = omap1_pm_runtime_resume, + USE_PM_CLK_RUNTIME_OPS USE_PLATFORM_PM_SLEEP_OPS }, }; -#define OMAP1_PM_DOMAIN (&default_pm_domain) -#else -#define OMAP1_PM_DOMAIN NULL -#endif /* CONFIG_PM */ static struct pm_clk_notifier_block platform_bus_notifier = { - .pm_domain = OMAP1_PM_DOMAIN, + .pm_domain = &default_pm_domain, .con_ids = { "ick", "fck", NULL, }, }; diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c index 02da3655d288..e417f7fcb2ba 100644 --- a/arch/arm/mach-omap2/omap_device.c +++ b/arch/arm/mach-omap2/omap_device.c @@ -682,11 +682,8 @@ struct dev_pm_domain omap_device_pm_domain = { SET_RUNTIME_PM_OPS(_od_runtime_suspend, _od_runtime_resume, NULL) USE_PLATFORM_PM_SLEEP_OPS - .suspend_noirq = _od_suspend_noirq, - .resume_noirq = _od_resume_noirq, - .freeze_noirq = _od_suspend_noirq, - .thaw_noirq = _od_resume_noirq, - .restore_noirq = _od_resume_noirq, + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(_od_suspend_noirq, + _od_resume_noirq) } }; diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 355b08936871..752969ff9de0 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -171,6 +171,12 @@ */ #define LINKS_PER_OCP_IF 2 +/* + * Address offset (in bytes) between the reset control and the reset + * status registers: 4 bytes on OMAP4 + */ +#define OMAP4_RST_CTRL_ST_OFFSET 4 + /** * struct omap_hwmod_soc_ops - fn ptrs for some SoC-specific operations * @enable_module: function to enable a module (via MODULEMODE) @@ -3016,10 +3022,12 @@ static int _omap4_deassert_hardreset(struct omap_hwmod *oh, if (ohri->st_shift) pr_err("omap_hwmod: %s: %s: hwmod data error: OMAP4 does not support st_shift\n", oh->name, ohri->name); - return omap_prm_deassert_hardreset(ohri->rst_shift, 0, + return omap_prm_deassert_hardreset(ohri->rst_shift, ohri->rst_shift, oh->clkdm->pwrdm.ptr->prcm_partition, oh->clkdm->pwrdm.ptr->prcm_offs, - oh->prcm.omap4.rstctrl_offs, 0); + oh->prcm.omap4.rstctrl_offs, + oh->prcm.omap4.rstctrl_offs + + OMAP4_RST_CTRL_ST_OFFSET); } /** @@ -3048,27 +3056,6 @@ static int _omap4_is_hardreset_asserted(struct omap_hwmod *oh, } /** - * _am33xx_assert_hardreset - call AM33XX PRM hardreset fn with hwmod args - * @oh: struct omap_hwmod * to assert hardreset - * @ohri: hardreset line data - * - * Call am33xx_prminst_assert_hardreset() with parameters extracted - * from the hwmod @oh and the hardreset line data @ohri. Only - * intended for use as an soc_ops function pointer. Passes along the - * return value from am33xx_prminst_assert_hardreset(). XXX This - * function is scheduled for removal when the PRM code is moved into - * drivers/. - */ -static int _am33xx_assert_hardreset(struct omap_hwmod *oh, - struct omap_hwmod_rst_info *ohri) - -{ - return omap_prm_assert_hardreset(ohri->rst_shift, 0, - oh->clkdm->pwrdm.ptr->prcm_offs, - oh->prcm.omap4.rstctrl_offs); -} - -/** * _am33xx_deassert_hardreset - call AM33XX PRM hardreset fn with hwmod args * @oh: struct omap_hwmod * to deassert hardreset * @ohri: hardreset line data @@ -3083,32 +3070,13 @@ static int _am33xx_assert_hardreset(struct omap_hwmod *oh, static int _am33xx_deassert_hardreset(struct omap_hwmod *oh, struct omap_hwmod_rst_info *ohri) { - return omap_prm_deassert_hardreset(ohri->rst_shift, ohri->st_shift, 0, + return omap_prm_deassert_hardreset(ohri->rst_shift, ohri->st_shift, + oh->clkdm->pwrdm.ptr->prcm_partition, oh->clkdm->pwrdm.ptr->prcm_offs, oh->prcm.omap4.rstctrl_offs, oh->prcm.omap4.rstst_offs); } -/** - * _am33xx_is_hardreset_asserted - call AM33XX PRM hardreset fn with hwmod args - * @oh: struct omap_hwmod * to test hardreset - * @ohri: hardreset line data - * - * Call am33xx_prminst_is_hardreset_asserted() with parameters - * extracted from the hwmod @oh and the hardreset line data @ohri. - * Only intended for use as an soc_ops function pointer. Passes along - * the return value from am33xx_prminst_is_hardreset_asserted(). XXX - * This function is scheduled for removal when the PRM code is moved - * into drivers/. - */ -static int _am33xx_is_hardreset_asserted(struct omap_hwmod *oh, - struct omap_hwmod_rst_info *ohri) -{ - return omap_prm_is_hardreset_asserted(ohri->rst_shift, 0, - oh->clkdm->pwrdm.ptr->prcm_offs, - oh->prcm.omap4.rstctrl_offs); -} - /* Public functions */ u32 omap_hwmod_read(struct omap_hwmod *oh, u16 reg_offs) @@ -3908,21 +3876,13 @@ void __init omap_hwmod_init(void) soc_ops.init_clkdm = _init_clkdm; soc_ops.update_context_lost = _omap4_update_context_lost; soc_ops.get_context_lost = _omap4_get_context_lost; - } else if (soc_is_am43xx()) { + } else if (cpu_is_ti816x() || soc_is_am33xx() || soc_is_am43xx()) { soc_ops.enable_module = _omap4_enable_module; soc_ops.disable_module = _omap4_disable_module; soc_ops.wait_target_ready = _omap4_wait_target_ready; soc_ops.assert_hardreset = _omap4_assert_hardreset; - soc_ops.deassert_hardreset = _omap4_deassert_hardreset; - soc_ops.is_hardreset_asserted = _omap4_is_hardreset_asserted; - soc_ops.init_clkdm = _init_clkdm; - } else if (cpu_is_ti816x() || soc_is_am33xx()) { - soc_ops.enable_module = _omap4_enable_module; - soc_ops.disable_module = _omap4_disable_module; - soc_ops.wait_target_ready = _omap4_wait_target_ready; - soc_ops.assert_hardreset = _am33xx_assert_hardreset; soc_ops.deassert_hardreset = _am33xx_deassert_hardreset; - soc_ops.is_hardreset_asserted = _am33xx_is_hardreset_asserted; + soc_ops.is_hardreset_asserted = _omap4_is_hardreset_asserted; soc_ops.init_clkdm = _init_clkdm; } else { WARN(1, "omap_hwmod: unknown SoC type\n"); diff --git a/arch/arm/mach-omap2/omap_hwmod_43xx_data.c b/arch/arm/mach-omap2/omap_hwmod_43xx_data.c index e2223148ba4d..17e8004fc20f 100644 --- a/arch/arm/mach-omap2/omap_hwmod_43xx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_43xx_data.c @@ -544,6 +544,44 @@ static struct omap_hwmod am43xx_hdq1w_hwmod = { }, }; +static struct omap_hwmod_class_sysconfig am43xx_vpfe_sysc = { + .rev_offs = 0x0, + .sysc_offs = 0x104, + .sysc_flags = SYSC_HAS_MIDLEMODE | SYSC_HAS_SIDLEMODE, + .idlemodes = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART | + MSTANDBY_FORCE | MSTANDBY_SMART | MSTANDBY_NO), + .sysc_fields = &omap_hwmod_sysc_type2, +}; + +static struct omap_hwmod_class am43xx_vpfe_hwmod_class = { + .name = "vpfe", + .sysc = &am43xx_vpfe_sysc, +}; + +static struct omap_hwmod am43xx_vpfe0_hwmod = { + .name = "vpfe0", + .class = &am43xx_vpfe_hwmod_class, + .clkdm_name = "l3s_clkdm", + .prcm = { + .omap4 = { + .modulemode = MODULEMODE_SWCTRL, + .clkctrl_offs = AM43XX_CM_PER_VPFE0_CLKCTRL_OFFSET, + }, + }, +}; + +static struct omap_hwmod am43xx_vpfe1_hwmod = { + .name = "vpfe1", + .class = &am43xx_vpfe_hwmod_class, + .clkdm_name = "l3s_clkdm", + .prcm = { + .omap4 = { + .modulemode = MODULEMODE_SWCTRL, + .clkctrl_offs = AM43XX_CM_PER_VPFE1_CLKCTRL_OFFSET, + }, + }, +}; + /* Interfaces */ static struct omap_hwmod_ocp_if am43xx_l3_main__l4_hs = { .master = &am33xx_l3_main_hwmod, @@ -825,6 +863,34 @@ static struct omap_hwmod_ocp_if am43xx_l4_ls__hdq1w = { .user = OCP_USER_MPU | OCP_USER_SDMA, }; +static struct omap_hwmod_ocp_if am43xx_l3__vpfe0 = { + .master = &am43xx_vpfe0_hwmod, + .slave = &am33xx_l3_main_hwmod, + .clk = "l3_gclk", + .user = OCP_USER_MPU | OCP_USER_SDMA, +}; + +static struct omap_hwmod_ocp_if am43xx_l3__vpfe1 = { + .master = &am43xx_vpfe1_hwmod, + .slave = &am33xx_l3_main_hwmod, + .clk = "l3_gclk", + .user = OCP_USER_MPU | OCP_USER_SDMA, +}; + +static struct omap_hwmod_ocp_if am43xx_l4_ls__vpfe0 = { + .master = &am33xx_l4_ls_hwmod, + .slave = &am43xx_vpfe0_hwmod, + .clk = "l4ls_gclk", + .user = OCP_USER_MPU | OCP_USER_SDMA, +}; + +static struct omap_hwmod_ocp_if am43xx_l4_ls__vpfe1 = { + .master = &am33xx_l4_ls_hwmod, + .slave = &am43xx_vpfe1_hwmod, + .clk = "l4ls_gclk", + .user = OCP_USER_MPU | OCP_USER_SDMA, +}; + static struct omap_hwmod_ocp_if *am43xx_hwmod_ocp_ifs[] __initdata = { &am33xx_l4_wkup__synctimer, &am43xx_l4_ls__timer8, @@ -925,6 +991,10 @@ static struct omap_hwmod_ocp_if *am43xx_hwmod_ocp_ifs[] __initdata = { &am43xx_l4_ls__dss_dispc, &am43xx_l4_ls__dss_rfbi, &am43xx_l4_ls__hdq1w, + &am43xx_l3__vpfe0, + &am43xx_l3__vpfe1, + &am43xx_l4_ls__vpfe0, + &am43xx_l4_ls__vpfe1, NULL, }; diff --git a/arch/arm/mach-omap2/prcm43xx.h b/arch/arm/mach-omap2/prcm43xx.h index 48df3b55057e..d0261996db6d 100644 --- a/arch/arm/mach-omap2/prcm43xx.h +++ b/arch/arm/mach-omap2/prcm43xx.h @@ -144,5 +144,6 @@ #define AM43XX_CM_PER_USBPHYOCP2SCP1_CLKCTRL_OFFSET 0x05C0 #define AM43XX_CM_PER_DSS_CLKCTRL_OFFSET 0x0a20 #define AM43XX_CM_PER_HDQ1W_CLKCTRL_OFFSET 0x04a0 - +#define AM43XX_CM_PER_VPFE0_CLKCTRL_OFFSET 0x0068 +#define AM43XX_CM_PER_VPFE1_CLKCTRL_OFFSET 0x0070 #endif diff --git a/arch/arm/mach-omap2/prm-regbits-34xx.h b/arch/arm/mach-omap2/prm-regbits-34xx.h index cbefbd7cfdb5..661d753df584 100644 --- a/arch/arm/mach-omap2/prm-regbits-34xx.h +++ b/arch/arm/mach-omap2/prm-regbits-34xx.h @@ -112,6 +112,7 @@ #define OMAP3430_VC_CMD_ONLP_SHIFT 16 #define OMAP3430_VC_CMD_RET_SHIFT 8 #define OMAP3430_VC_CMD_OFF_SHIFT 0 +#define OMAP3430_SREN_MASK (1 << 4) #define OMAP3430_HSEN_MASK (1 << 3) #define OMAP3430_MCODE_MASK (0x7 << 0) #define OMAP3430_VALID_MASK (1 << 24) diff --git a/arch/arm/mach-omap2/prm-regbits-44xx.h b/arch/arm/mach-omap2/prm-regbits-44xx.h index b1c7a33e00e7..e794828dee55 100644 --- a/arch/arm/mach-omap2/prm-regbits-44xx.h +++ b/arch/arm/mach-omap2/prm-regbits-44xx.h @@ -35,6 +35,7 @@ #define OMAP4430_GLOBAL_WARM_SW_RST_SHIFT 1 #define OMAP4430_GLOBAL_WUEN_MASK (1 << 16) #define OMAP4430_HSMCODE_MASK (0x7 << 0) +#define OMAP4430_SRMODEEN_MASK (1 << 4) #define OMAP4430_HSMODEEN_MASK (1 << 3) #define OMAP4430_HSSCLL_SHIFT 24 #define OMAP4430_ICEPICK_RST_SHIFT 9 diff --git a/arch/arm/mach-omap2/prminst44xx.c b/arch/arm/mach-omap2/prminst44xx.c index c4859c4d3646..d0b15dbafa2e 100644 --- a/arch/arm/mach-omap2/prminst44xx.c +++ b/arch/arm/mach-omap2/prminst44xx.c @@ -87,12 +87,6 @@ u32 omap4_prminst_rmw_inst_reg_bits(u32 mask, u32 bits, u8 part, s16 inst, return v; } -/* - * Address offset (in bytes) between the reset control and the reset - * status registers: 4 bytes on OMAP4 - */ -#define OMAP4_RST_CTRL_ST_OFFSET 4 - /** * omap4_prminst_is_hardreset_asserted - read the HW reset line state of * submodules contained in the hwmod module @@ -141,11 +135,11 @@ int omap4_prminst_assert_hardreset(u8 shift, u8 part, s16 inst, * omap4_prminst_deassert_hardreset - deassert a submodule hardreset line and * wait * @shift: register bit shift corresponding to the reset line to deassert - * @st_shift: status bit offset, not used for OMAP4+ + * @st_shift: status bit offset corresponding to the reset line * @part: PRM partition * @inst: PRM instance offset * @rstctrl_offs: reset register offset - * @st_offs: reset status register offset, not used for OMAP4+ + * @rstst_offs: reset status register offset * * Some IPs like dsp, ipu or iva contain processors that require an HW * reset line to be asserted / deasserted in order to fully enable the @@ -157,11 +151,11 @@ int omap4_prminst_assert_hardreset(u8 shift, u8 part, s16 inst, * of reset, or -EBUSY if the submodule did not exit reset promptly. */ int omap4_prminst_deassert_hardreset(u8 shift, u8 st_shift, u8 part, s16 inst, - u16 rstctrl_offs, u16 st_offs) + u16 rstctrl_offs, u16 rstst_offs) { int c; u32 mask = 1 << shift; - u16 rstst_offs = rstctrl_offs + OMAP4_RST_CTRL_ST_OFFSET; + u32 st_mask = 1 << st_shift; /* Check the current status to avoid de-asserting the line twice */ if (omap4_prminst_is_hardreset_asserted(shift, part, inst, @@ -169,13 +163,13 @@ int omap4_prminst_deassert_hardreset(u8 shift, u8 st_shift, u8 part, s16 inst, return -EEXIST; /* Clear the reset status by writing 1 to the status bit */ - omap4_prminst_rmw_inst_reg_bits(0xffffffff, mask, part, inst, + omap4_prminst_rmw_inst_reg_bits(0xffffffff, st_mask, part, inst, rstst_offs); /* de-assert the reset control line */ omap4_prminst_rmw_inst_reg_bits(mask, 0, part, inst, rstctrl_offs); /* wait the status to be set */ - omap_test_timeout(omap4_prminst_is_hardreset_asserted(shift, part, inst, - rstst_offs), + omap_test_timeout(omap4_prminst_is_hardreset_asserted(st_shift, part, + inst, rstst_offs), MAX_MODULE_HARDRESET_WAIT, c); return (c == MAX_MODULE_HARDRESET_WAIT) ? -EBUSY : 0; diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S index d1dedc8195ed..eafd120b53f1 100644 --- a/arch/arm/mach-omap2/sleep34xx.S +++ b/arch/arm/mach-omap2/sleep34xx.S @@ -203,23 +203,8 @@ save_context_wfi: */ ldr r1, kernel_flush blx r1 - /* - * The kernel doesn't interwork: v7_flush_dcache_all in particluar will - * always return in Thumb state when CONFIG_THUMB2_KERNEL is enabled. - * This sequence switches back to ARM. Note that .align may insert a - * nop: bx pc needs to be word-aligned in order to work. - */ - THUMB( .thumb ) - THUMB( .align ) - THUMB( bx pc ) - THUMB( nop ) - .arm - b omap3_do_wfi - -/* - * Local variables - */ +ENDPROC(omap34xx_cpu_suspend) omap3_do_wfi_sram_addr: .word omap3_do_wfi_sram kernel_flush: @@ -364,10 +349,7 @@ exit_nonoff_modes: * =================================== */ ldmfd sp!, {r4 - r11, pc} @ restore regs and return - -/* - * Local variables - */ +ENDPROC(omap3_do_wfi) sdrc_power: .word SDRC_POWER_V cm_idlest1_core: diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c index cef67af9e9b8..cac46d852da1 100644 --- a/arch/arm/mach-omap2/timer.c +++ b/arch/arm/mach-omap2/timer.c @@ -298,14 +298,11 @@ static int __init omap_dm_timer_init_one(struct omap_dm_timer *timer, if (IS_ERR(src)) return PTR_ERR(src); - if (clk_get_parent(timer->fclk) != src) { - r = clk_set_parent(timer->fclk, src); - if (r < 0) { - pr_warn("%s: %s cannot set source\n", __func__, - oh->name); - clk_put(src); - return r; - } + r = clk_set_parent(timer->fclk, src); + if (r < 0) { + pr_warn("%s: %s cannot set source\n", __func__, oh->name); + clk_put(src); + return r; } clk_put(src); diff --git a/arch/arm/mach-omap2/vc.c b/arch/arm/mach-omap2/vc.c index be9ef834fa81..076fd20d7e5a 100644 --- a/arch/arm/mach-omap2/vc.c +++ b/arch/arm/mach-omap2/vc.c @@ -316,7 +316,8 @@ static void __init omap3_vc_init_pmic_signaling(struct voltagedomain *voltdm) * idle. And we can also scale voltages to zero for off-idle. * Note that no actual voltage scaling during off-idle will * happen unless the board specific twl4030 PMIC scripts are - * loaded. + * loaded. See also omap_vc_i2c_init for comments regarding + * erratum i531. */ val = voltdm->read(OMAP3_PRM_VOLTCTRL_OFFSET); if (!(val & OMAP3430_PRM_VOLTCTRL_SEL_OFF)) { @@ -704,9 +705,16 @@ static void __init omap_vc_i2c_init(struct voltagedomain *voltdm) return; } + /* + * Note that for omap3 OMAP3430_SREN_MASK clears SREN to work around + * erratum i531 "Extra Power Consumed When Repeated Start Operation + * Mode Is Enabled on I2C Interface Dedicated for Smart Reflex (I2C4)". + * Otherwise I2C4 eventually leads into about 23mW extra power being + * consumed even during off idle using VMODE. + */ i2c_high_speed = voltdm->pmic->i2c_high_speed; if (i2c_high_speed) - voltdm->rmw(vc->common->i2c_cfg_hsen_mask, + voltdm->rmw(vc->common->i2c_cfg_clear_mask, vc->common->i2c_cfg_hsen_mask, vc->common->i2c_cfg_reg); diff --git a/arch/arm/mach-omap2/vc.h b/arch/arm/mach-omap2/vc.h index cdbdd78e755e..89b83b7ff3ec 100644 --- a/arch/arm/mach-omap2/vc.h +++ b/arch/arm/mach-omap2/vc.h @@ -34,6 +34,7 @@ struct voltagedomain; * @cmd_ret_shift: RET field shift in PRM_VC_CMD_VAL_* register * @cmd_off_shift: OFF field shift in PRM_VC_CMD_VAL_* register * @i2c_cfg_reg: I2C configuration register offset + * @i2c_cfg_clear_mask: high-speed mode bit clear mask in I2C config register * @i2c_cfg_hsen_mask: high-speed mode bit field mask in I2C config register * @i2c_mcode_mask: MCODE field mask for I2C config register * @@ -52,6 +53,7 @@ struct omap_vc_common { u8 cmd_ret_shift; u8 cmd_off_shift; u8 i2c_cfg_reg; + u8 i2c_cfg_clear_mask; u8 i2c_cfg_hsen_mask; u8 i2c_mcode_mask; }; diff --git a/arch/arm/mach-omap2/vc3xxx_data.c b/arch/arm/mach-omap2/vc3xxx_data.c index 75bc4aa22b3a..71d74c9172c1 100644 --- a/arch/arm/mach-omap2/vc3xxx_data.c +++ b/arch/arm/mach-omap2/vc3xxx_data.c @@ -40,6 +40,7 @@ static struct omap_vc_common omap3_vc_common = { .cmd_onlp_shift = OMAP3430_VC_CMD_ONLP_SHIFT, .cmd_ret_shift = OMAP3430_VC_CMD_RET_SHIFT, .cmd_off_shift = OMAP3430_VC_CMD_OFF_SHIFT, + .i2c_cfg_clear_mask = OMAP3430_SREN_MASK | OMAP3430_HSEN_MASK, .i2c_cfg_hsen_mask = OMAP3430_HSEN_MASK, .i2c_cfg_reg = OMAP3_PRM_VC_I2C_CFG_OFFSET, .i2c_mcode_mask = OMAP3430_MCODE_MASK, diff --git a/arch/arm/mach-omap2/vc44xx_data.c b/arch/arm/mach-omap2/vc44xx_data.c index 085e5d6a04fd..2abd5fa8a697 100644 --- a/arch/arm/mach-omap2/vc44xx_data.c +++ b/arch/arm/mach-omap2/vc44xx_data.c @@ -42,6 +42,7 @@ static const struct omap_vc_common omap4_vc_common = { .cmd_ret_shift = OMAP4430_RET_SHIFT, .cmd_off_shift = OMAP4430_OFF_SHIFT, .i2c_cfg_reg = OMAP4_PRM_VC_CFG_I2C_MODE_OFFSET, + .i2c_cfg_clear_mask = OMAP4430_SRMODEEN_MASK | OMAP4430_HSMODEEN_MASK, .i2c_cfg_hsen_mask = OMAP4430_HSMODEEN_MASK, .i2c_mcode_mask = OMAP4430_HSMCODE_MASK, }; diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig index 8896e71586f5..f09683687963 100644 --- a/arch/arm/mach-pxa/Kconfig +++ b/arch/arm/mach-pxa/Kconfig @@ -691,4 +691,13 @@ config SHARPSL_PM_MAX1111 config PXA310_ULPI bool +config PXA_SYSTEMS_CPLDS + tristate "Motherboard cplds" + default ARCH_LUBBOCK || MACH_MAINSTONE + help + This driver supports the Lubbock and Mainstone multifunction chip + found on the pxa25x development platform system (Lubbock) and pxa27x + development platform system (Mainstone). This IO board supports the + interrupts handling, ethernet controller, flash chips, etc ... + endif diff --git a/arch/arm/mach-pxa/Makefile b/arch/arm/mach-pxa/Makefile index eb0bf7678a99..4087d334ecdf 100644 --- a/arch/arm/mach-pxa/Makefile +++ b/arch/arm/mach-pxa/Makefile @@ -90,4 +90,5 @@ obj-$(CONFIG_MACH_RAUMFELD_CONNECTOR) += raumfeld.o obj-$(CONFIG_MACH_RAUMFELD_SPEAKER) += raumfeld.o obj-$(CONFIG_MACH_ZIPIT2) += z2.o +obj-$(CONFIG_PXA_SYSTEMS_CPLDS) += pxa_cplds_irqs.o obj-$(CONFIG_TOSA_BT) += tosa-bt.o diff --git a/arch/arm/mach-pxa/include/mach/lubbock.h b/arch/arm/mach-pxa/include/mach/lubbock.h index 958cd6af9384..1eecf794acd2 100644 --- a/arch/arm/mach-pxa/include/mach/lubbock.h +++ b/arch/arm/mach-pxa/include/mach/lubbock.h @@ -37,7 +37,9 @@ #define LUB_GP __LUB_REG(LUBBOCK_FPGA_PHYS + 0x100) /* Board specific IRQs */ -#define LUBBOCK_IRQ(x) (IRQ_BOARD_START + (x)) +#define LUBBOCK_NR_IRQS IRQ_BOARD_START + +#define LUBBOCK_IRQ(x) (LUBBOCK_NR_IRQS + (x)) #define LUBBOCK_SD_IRQ LUBBOCK_IRQ(0) #define LUBBOCK_SA1111_IRQ LUBBOCK_IRQ(1) #define LUBBOCK_USB_IRQ LUBBOCK_IRQ(2) /* usb connect */ @@ -47,8 +49,7 @@ #define LUBBOCK_USB_DISC_IRQ LUBBOCK_IRQ(6) /* usb disconnect */ #define LUBBOCK_LAST_IRQ LUBBOCK_IRQ(6) -#define LUBBOCK_SA1111_IRQ_BASE (IRQ_BOARD_START + 16) -#define LUBBOCK_NR_IRQS (IRQ_BOARD_START + 16 + 55) +#define LUBBOCK_SA1111_IRQ_BASE (LUBBOCK_NR_IRQS + 32) #ifndef __ASSEMBLY__ extern void lubbock_set_misc_wr(unsigned int mask, unsigned int set); diff --git a/arch/arm/mach-pxa/include/mach/mainstone.h b/arch/arm/mach-pxa/include/mach/mainstone.h index 1bfc4e822a41..e82a7d31104e 100644 --- a/arch/arm/mach-pxa/include/mach/mainstone.h +++ b/arch/arm/mach-pxa/include/mach/mainstone.h @@ -120,7 +120,9 @@ #define MST_PCMCIA_PWR_VCC_50 0x4 /* voltage VCC = 5.0V */ /* board specific IRQs */ -#define MAINSTONE_IRQ(x) (IRQ_BOARD_START + (x)) +#define MAINSTONE_NR_IRQS IRQ_BOARD_START + +#define MAINSTONE_IRQ(x) (MAINSTONE_NR_IRQS + (x)) #define MAINSTONE_MMC_IRQ MAINSTONE_IRQ(0) #define MAINSTONE_USIM_IRQ MAINSTONE_IRQ(1) #define MAINSTONE_USBC_IRQ MAINSTONE_IRQ(2) @@ -136,6 +138,4 @@ #define MAINSTONE_S1_STSCHG_IRQ MAINSTONE_IRQ(14) #define MAINSTONE_S1_IRQ MAINSTONE_IRQ(15) -#define MAINSTONE_NR_IRQS (IRQ_BOARD_START + 16) - #endif diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c index 235f2d9318c1..7518310c9015 100644 --- a/arch/arm/mach-pxa/lubbock.c +++ b/arch/arm/mach-pxa/lubbock.c @@ -13,6 +13,7 @@ */ #include <linux/clkdev.h> #include <linux/gpio.h> +#include <linux/gpio/machine.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/init.h> @@ -124,84 +125,6 @@ void lubbock_set_misc_wr(unsigned int mask, unsigned int set) } EXPORT_SYMBOL(lubbock_set_misc_wr); -static unsigned long lubbock_irq_enabled; - -static void lubbock_mask_irq(struct irq_data *d) -{ - int lubbock_irq = (d->irq - LUBBOCK_IRQ(0)); - LUB_IRQ_MASK_EN = (lubbock_irq_enabled &= ~(1 << lubbock_irq)); -} - -static void lubbock_unmask_irq(struct irq_data *d) -{ - int lubbock_irq = (d->irq - LUBBOCK_IRQ(0)); - /* the irq can be acknowledged only if deasserted, so it's done here */ - LUB_IRQ_SET_CLR &= ~(1 << lubbock_irq); - LUB_IRQ_MASK_EN = (lubbock_irq_enabled |= (1 << lubbock_irq)); -} - -static struct irq_chip lubbock_irq_chip = { - .name = "FPGA", - .irq_ack = lubbock_mask_irq, - .irq_mask = lubbock_mask_irq, - .irq_unmask = lubbock_unmask_irq, -}; - -static void lubbock_irq_handler(unsigned int irq, struct irq_desc *desc) -{ - unsigned long pending = LUB_IRQ_SET_CLR & lubbock_irq_enabled; - do { - /* clear our parent irq */ - desc->irq_data.chip->irq_ack(&desc->irq_data); - if (likely(pending)) { - irq = LUBBOCK_IRQ(0) + __ffs(pending); - generic_handle_irq(irq); - } - pending = LUB_IRQ_SET_CLR & lubbock_irq_enabled; - } while (pending); -} - -static void __init lubbock_init_irq(void) -{ - int irq; - - pxa25x_init_irq(); - - /* setup extra lubbock irqs */ - for (irq = LUBBOCK_IRQ(0); irq <= LUBBOCK_LAST_IRQ; irq++) { - irq_set_chip_and_handler(irq, &lubbock_irq_chip, - handle_level_irq); - set_irq_flags(irq, IRQF_VALID | IRQF_PROBE); - } - - irq_set_chained_handler(PXA_GPIO_TO_IRQ(0), lubbock_irq_handler); - irq_set_irq_type(PXA_GPIO_TO_IRQ(0), IRQ_TYPE_EDGE_FALLING); -} - -#ifdef CONFIG_PM - -static void lubbock_irq_resume(void) -{ - LUB_IRQ_MASK_EN = lubbock_irq_enabled; -} - -static struct syscore_ops lubbock_irq_syscore_ops = { - .resume = lubbock_irq_resume, -}; - -static int __init lubbock_irq_device_init(void) -{ - if (machine_is_lubbock()) { - register_syscore_ops(&lubbock_irq_syscore_ops); - return 0; - } - return -ENODEV; -} - -device_initcall(lubbock_irq_device_init); - -#endif - static int lubbock_udc_is_connected(void) { return (LUB_MISC_RD & (1 << 9)) == 0; @@ -384,11 +307,38 @@ static struct platform_device lubbock_flash_device[2] = { }, }; +static struct resource lubbock_cplds_resources[] = { + [0] = { + .start = LUBBOCK_FPGA_PHYS + 0xc0, + .end = LUBBOCK_FPGA_PHYS + 0xe0 - 1, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = PXA_GPIO_TO_IRQ(0), + .end = PXA_GPIO_TO_IRQ(0), + .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_LOWEDGE, + }, + [2] = { + .start = LUBBOCK_IRQ(0), + .end = LUBBOCK_IRQ(6), + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device lubbock_cplds_device = { + .name = "pxa_cplds_irqs", + .id = -1, + .resource = &lubbock_cplds_resources[0], + .num_resources = 3, +}; + + static struct platform_device *devices[] __initdata = { &sa1111_device, &smc91x_device, &lubbock_flash_device[0], &lubbock_flash_device[1], + &lubbock_cplds_device, }; static struct pxafb_mode_info sharp_lm8v31_mode = { @@ -649,7 +599,7 @@ MACHINE_START(LUBBOCK, "Intel DBPXA250 Development Platform (aka Lubbock)") /* Maintainer: MontaVista Software Inc. */ .map_io = lubbock_map_io, .nr_irqs = LUBBOCK_NR_IRQS, - .init_irq = lubbock_init_irq, + .init_irq = pxa25x_init_irq, .handle_irq = pxa25x_handle_irq, .init_time = pxa_timer_init, .init_machine = lubbock_init, diff --git a/arch/arm/mach-pxa/mainstone.c b/arch/arm/mach-pxa/mainstone.c index 78b84c0dfc79..2c0658cf6be2 100644 --- a/arch/arm/mach-pxa/mainstone.c +++ b/arch/arm/mach-pxa/mainstone.c @@ -13,6 +13,7 @@ * published by the Free Software Foundation. */ #include <linux/gpio.h> +#include <linux/gpio/machine.h> #include <linux/init.h> #include <linux/platform_device.h> #include <linux/syscore_ops.h> @@ -122,92 +123,6 @@ static unsigned long mainstone_pin_config[] = { GPIO1_GPIO | WAKEUP_ON_EDGE_BOTH, }; -static unsigned long mainstone_irq_enabled; - -static void mainstone_mask_irq(struct irq_data *d) -{ - int mainstone_irq = (d->irq - MAINSTONE_IRQ(0)); - MST_INTMSKENA = (mainstone_irq_enabled &= ~(1 << mainstone_irq)); -} - -static void mainstone_unmask_irq(struct irq_data *d) -{ - int mainstone_irq = (d->irq - MAINSTONE_IRQ(0)); - /* the irq can be acknowledged only if deasserted, so it's done here */ - MST_INTSETCLR &= ~(1 << mainstone_irq); - MST_INTMSKENA = (mainstone_irq_enabled |= (1 << mainstone_irq)); -} - -static struct irq_chip mainstone_irq_chip = { - .name = "FPGA", - .irq_ack = mainstone_mask_irq, - .irq_mask = mainstone_mask_irq, - .irq_unmask = mainstone_unmask_irq, -}; - -static void mainstone_irq_handler(unsigned int irq, struct irq_desc *desc) -{ - unsigned long pending = MST_INTSETCLR & mainstone_irq_enabled; - do { - /* clear useless edge notification */ - desc->irq_data.chip->irq_ack(&desc->irq_data); - if (likely(pending)) { - irq = MAINSTONE_IRQ(0) + __ffs(pending); - generic_handle_irq(irq); - } - pending = MST_INTSETCLR & mainstone_irq_enabled; - } while (pending); -} - -static void __init mainstone_init_irq(void) -{ - int irq; - - pxa27x_init_irq(); - - /* setup extra Mainstone irqs */ - for(irq = MAINSTONE_IRQ(0); irq <= MAINSTONE_IRQ(15); irq++) { - irq_set_chip_and_handler(irq, &mainstone_irq_chip, - handle_level_irq); - if (irq == MAINSTONE_IRQ(10) || irq == MAINSTONE_IRQ(14)) - set_irq_flags(irq, IRQF_VALID | IRQF_PROBE | IRQF_NOAUTOEN); - else - set_irq_flags(irq, IRQF_VALID | IRQF_PROBE); - } - set_irq_flags(MAINSTONE_IRQ(8), 0); - set_irq_flags(MAINSTONE_IRQ(12), 0); - - MST_INTMSKENA = 0; - MST_INTSETCLR = 0; - - irq_set_chained_handler(PXA_GPIO_TO_IRQ(0), mainstone_irq_handler); - irq_set_irq_type(PXA_GPIO_TO_IRQ(0), IRQ_TYPE_EDGE_FALLING); -} - -#ifdef CONFIG_PM - -static void mainstone_irq_resume(void) -{ - MST_INTMSKENA = mainstone_irq_enabled; -} - -static struct syscore_ops mainstone_irq_syscore_ops = { - .resume = mainstone_irq_resume, -}; - -static int __init mainstone_irq_device_init(void) -{ - if (machine_is_mainstone()) - register_syscore_ops(&mainstone_irq_syscore_ops); - - return 0; -} - -device_initcall(mainstone_irq_device_init); - -#endif - - static struct resource smc91x_resources[] = { [0] = { .start = (MST_ETH_PHYS + 0x300), @@ -487,11 +402,37 @@ static struct platform_device mst_gpio_keys_device = { }, }; +static struct resource mst_cplds_resources[] = { + [0] = { + .start = MST_FPGA_PHYS + 0xc0, + .end = MST_FPGA_PHYS + 0xe0 - 1, + .flags = IORESOURCE_MEM, + }, + [1] = { + .start = PXA_GPIO_TO_IRQ(0), + .end = PXA_GPIO_TO_IRQ(0), + .flags = IORESOURCE_IRQ | IORESOURCE_IRQ_LOWEDGE, + }, + [2] = { + .start = MAINSTONE_IRQ(0), + .end = MAINSTONE_IRQ(15), + .flags = IORESOURCE_IRQ, + }, +}; + +static struct platform_device mst_cplds_device = { + .name = "pxa_cplds_irqs", + .id = -1, + .resource = &mst_cplds_resources[0], + .num_resources = 3, +}; + static struct platform_device *platform_devices[] __initdata = { &smc91x_device, &mst_flash_device[0], &mst_flash_device[1], &mst_gpio_keys_device, + &mst_cplds_device, }; static struct pxaohci_platform_data mainstone_ohci_platform_data = { @@ -718,7 +659,7 @@ MACHINE_START(MAINSTONE, "Intel HCDDBBVA0 Development Platform (aka Mainstone)") .atag_offset = 0x100, /* BLOB boot parameter setting */ .map_io = mainstone_map_io, .nr_irqs = MAINSTONE_NR_IRQS, - .init_irq = mainstone_init_irq, + .init_irq = pxa27x_init_irq, .handle_irq = pxa27x_handle_irq, .init_time = pxa_timer_init, .init_machine = mainstone_init, diff --git a/arch/arm/mach-pxa/pxa_cplds_irqs.c b/arch/arm/mach-pxa/pxa_cplds_irqs.c new file mode 100644 index 000000000000..2385052b0ce1 --- /dev/null +++ b/arch/arm/mach-pxa/pxa_cplds_irqs.c @@ -0,0 +1,200 @@ +/* + * Intel Reference Systems cplds + * + * Copyright (C) 2014 Robert Jarzmik + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * Cplds motherboard driver, supporting lubbock and mainstone SoC board. + */ + +#include <linux/bitops.h> +#include <linux/gpio.h> +#include <linux/gpio/consumer.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/mfd/core.h> +#include <linux/module.h> +#include <linux/of_platform.h> + +#define FPGA_IRQ_MASK_EN 0x0 +#define FPGA_IRQ_SET_CLR 0x10 + +#define CPLDS_NB_IRQ 32 + +struct cplds { + void __iomem *base; + int irq; + unsigned int irq_mask; + struct gpio_desc *gpio0; + struct irq_domain *irqdomain; +}; + +static irqreturn_t cplds_irq_handler(int in_irq, void *d) +{ + struct cplds *fpga = d; + unsigned long pending; + unsigned int bit; + + pending = readl(fpga->base + FPGA_IRQ_SET_CLR) & fpga->irq_mask; + for_each_set_bit(bit, &pending, CPLDS_NB_IRQ) + generic_handle_irq(irq_find_mapping(fpga->irqdomain, bit)); + + return IRQ_HANDLED; +} + +static void cplds_irq_mask_ack(struct irq_data *d) +{ + struct cplds *fpga = irq_data_get_irq_chip_data(d); + unsigned int cplds_irq = irqd_to_hwirq(d); + unsigned int set, bit = BIT(cplds_irq); + + fpga->irq_mask &= ~bit; + writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN); + set = readl(fpga->base + FPGA_IRQ_SET_CLR); + writel(set & ~bit, fpga->base + FPGA_IRQ_SET_CLR); +} + +static void cplds_irq_unmask(struct irq_data *d) +{ + struct cplds *fpga = irq_data_get_irq_chip_data(d); + unsigned int cplds_irq = irqd_to_hwirq(d); + unsigned int bit = BIT(cplds_irq); + + fpga->irq_mask |= bit; + writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN); +} + +static struct irq_chip cplds_irq_chip = { + .name = "pxa_cplds", + .irq_mask_ack = cplds_irq_mask_ack, + .irq_unmask = cplds_irq_unmask, + .flags = IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_SKIP_SET_WAKE, +}; + +static int cplds_irq_domain_map(struct irq_domain *d, unsigned int irq, + irq_hw_number_t hwirq) +{ + struct cplds *fpga = d->host_data; + + irq_set_chip_and_handler(irq, &cplds_irq_chip, handle_level_irq); + irq_set_chip_data(irq, fpga); + + return 0; +} + +static const struct irq_domain_ops cplds_irq_domain_ops = { + .xlate = irq_domain_xlate_twocell, + .map = cplds_irq_domain_map, +}; + +static int cplds_resume(struct platform_device *pdev) +{ + struct cplds *fpga = platform_get_drvdata(pdev); + + writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN); + + return 0; +} + +static int cplds_probe(struct platform_device *pdev) +{ + struct resource *res; + struct cplds *fpga; + int ret; + int base_irq; + unsigned long irqflags = 0; + + fpga = devm_kzalloc(&pdev->dev, sizeof(*fpga), GFP_KERNEL); + if (!fpga) + return -ENOMEM; + + res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); + if (res) { + fpga->irq = (unsigned int)res->start; + irqflags = res->flags; + } + if (!fpga->irq) + return -ENODEV; + + base_irq = platform_get_irq(pdev, 1); + if (base_irq < 0) + base_irq = 0; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + fpga->base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(fpga->base)) + return PTR_ERR(fpga->base); + + platform_set_drvdata(pdev, fpga); + + writel(fpga->irq_mask, fpga->base + FPGA_IRQ_MASK_EN); + writel(0, fpga->base + FPGA_IRQ_SET_CLR); + + ret = devm_request_irq(&pdev->dev, fpga->irq, cplds_irq_handler, + irqflags, dev_name(&pdev->dev), fpga); + if (ret == -ENOSYS) + return -EPROBE_DEFER; + + if (ret) { + dev_err(&pdev->dev, "couldn't request main irq%d: %d\n", + fpga->irq, ret); + return ret; + } + + irq_set_irq_wake(fpga->irq, 1); + fpga->irqdomain = irq_domain_add_linear(pdev->dev.of_node, + CPLDS_NB_IRQ, + &cplds_irq_domain_ops, fpga); + if (!fpga->irqdomain) + return -ENODEV; + + if (base_irq) { + ret = irq_create_strict_mappings(fpga->irqdomain, base_irq, 0, + CPLDS_NB_IRQ); + if (ret) { + dev_err(&pdev->dev, "couldn't create the irq mapping %d..%d\n", + base_irq, base_irq + CPLDS_NB_IRQ); + return ret; + } + } + + return 0; +} + +static int cplds_remove(struct platform_device *pdev) +{ + struct cplds *fpga = platform_get_drvdata(pdev); + + irq_set_chip_and_handler(fpga->irq, NULL, NULL); + + return 0; +} + +static const struct of_device_id cplds_id_table[] = { + { .compatible = "intel,lubbock-cplds-irqs", }, + { .compatible = "intel,mainstone-cplds-irqs", }, + { } +}; +MODULE_DEVICE_TABLE(of, cplds_id_table); + +static struct platform_driver cplds_driver = { + .driver = { + .name = "pxa_cplds_irqs", + .of_match_table = of_match_ptr(cplds_id_table), + }, + .probe = cplds_probe, + .remove = cplds_remove, + .resume = cplds_resume, +}; + +module_platform_driver(cplds_driver); + +MODULE_DESCRIPTION("PXA Cplds interrupts driver"); +MODULE_AUTHOR("Robert Jarzmik <robert.jarzmik@free.fr>"); +MODULE_LICENSE("GPL"); diff --git a/arch/arm/mach-rockchip/pm.c b/arch/arm/mach-rockchip/pm.c index b07d88602073..b0dcbe28f78c 100644 --- a/arch/arm/mach-rockchip/pm.c +++ b/arch/arm/mach-rockchip/pm.c @@ -83,6 +83,13 @@ static void rk3288_slp_mode_set(int level) SGRF_PCLK_WDT_GATE | SGRF_FAST_BOOT_EN | SGRF_PCLK_WDT_GATE_WRITE | SGRF_FAST_BOOT_EN_WRITE); + /* + * The dapswjdp can not auto reset before resume, that cause it may + * access some illegal address during resume. Let's disable it before + * suspend, and the MASKROM will enable it back. + */ + regmap_write(sgrf_regmap, RK3288_SGRF_CPU_CON0, SGRF_DAPDEVICEEN_WRITE); + /* booting address of resuming system is from this register value */ regmap_write(sgrf_regmap, RK3288_SGRF_FAST_BOOT_ADDR, rk3288_bootram_phy); diff --git a/arch/arm/mach-rockchip/pm.h b/arch/arm/mach-rockchip/pm.h index 03ff31d8282d..3e8d39c0c3d5 100644 --- a/arch/arm/mach-rockchip/pm.h +++ b/arch/arm/mach-rockchip/pm.h @@ -55,6 +55,10 @@ static inline void rockchip_suspend_init(void) #define SGRF_FAST_BOOT_EN BIT(8) #define SGRF_FAST_BOOT_EN_WRITE BIT(24) +#define RK3288_SGRF_CPU_CON0 (0x40) +#define SGRF_DAPDEVICEEN BIT(0) +#define SGRF_DAPDEVICEEN_WRITE BIT(16) + #define RK3288_CRU_MODE_CON 0x50 #define RK3288_CRU_SEL0_CON 0x60 #define RK3288_CRU_SEL1_CON 0x64 diff --git a/arch/arm/mach-rockchip/rockchip.c b/arch/arm/mach-rockchip/rockchip.c index d360ec044b66..b6cf3b449428 100644 --- a/arch/arm/mach-rockchip/rockchip.c +++ b/arch/arm/mach-rockchip/rockchip.c @@ -30,11 +30,30 @@ #include "pm.h" #define RK3288_GRF_SOC_CON0 0x244 +#define RK3288_TIMER6_7_PHYS 0xff810000 static void __init rockchip_timer_init(void) { if (of_machine_is_compatible("rockchip,rk3288")) { struct regmap *grf; + void __iomem *reg_base; + + /* + * Most/all uboot versions for rk3288 don't enable timer7 + * which is needed for the architected timer to work. + * So make sure it is running during early boot. + */ + reg_base = ioremap(RK3288_TIMER6_7_PHYS, SZ_16K); + if (reg_base) { + writel(0, reg_base + 0x30); + writel(0xffffffff, reg_base + 0x20); + writel(0xffffffff, reg_base + 0x24); + writel(1, reg_base + 0x30); + dsb(); + iounmap(reg_base); + } else { + pr_err("rockchip: could not map timer7 registers\n"); + } /* * Disable auto jtag/sdmmc switching that causes issues diff --git a/arch/arm/mach-sa1100/neponset.c b/arch/arm/mach-sa1100/neponset.c index af868d258e66..99d9a3b1bf34 100644 --- a/arch/arm/mach-sa1100/neponset.c +++ b/arch/arm/mach-sa1100/neponset.c @@ -327,8 +327,7 @@ static int neponset_probe(struct platform_device *dev) irq_set_chip(d->irq_base + NEP_IRQ_SA1111, &nochip); irq_set_irq_type(irq, IRQ_TYPE_EDGE_RISING); - irq_set_handler_data(irq, d); - irq_set_chained_handler(irq, neponset_irq_handler); + irq_set_chained_handler_and_data(irq, neponset_irq_handler, d); /* * We would set IRQ_GPIO25 to be a wake-up IRQ, but unfortunately diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 09c5fe3d30c2..7e7583ddd607 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -1878,7 +1878,7 @@ struct dma_map_ops iommu_coherent_ops = { * arm_iommu_attach_device function. */ struct dma_iommu_mapping * -arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size) +arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, u64 size) { unsigned int bits = size >> PAGE_SHIFT; unsigned int bitmap_size = BITS_TO_LONGS(bits) * sizeof(long); @@ -1886,6 +1886,10 @@ arm_iommu_create_mapping(struct bus_type *bus, dma_addr_t base, size_t size) int extensions = 1; int err = -ENOMEM; + /* currently only 32-bit DMA address space is supported */ + if (size > DMA_BIT_MASK(32) + 1) + return ERR_PTR(-ERANGE); + if (!bitmap_size) return ERR_PTR(-EINVAL); @@ -2057,13 +2061,6 @@ static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size, if (!iommu) return false; - /* - * currently arm_iommu_create_mapping() takes a max of size_t - * for size param. So check this limit for now. - */ - if (size > SIZE_MAX) - return false; - mapping = arm_iommu_create_mapping(dev->bus, dma_base, size); if (IS_ERR(mapping)) { pr_warn("Failed to create %llu-byte IOMMU mapping for device %s\n", diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index 6333d9c17875..0d629b8f973f 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -276,7 +276,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) * If we're in an interrupt or have no user * context, we must not take the fault.. */ - if (in_atomic() || !mm) + if (faulthandler_disabled() || !mm) goto no_context; if (user_mode(regs)) diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c index b98895d9fe57..ee8dfa793989 100644 --- a/arch/arm/mm/highmem.c +++ b/arch/arm/mm/highmem.c @@ -59,6 +59,7 @@ void *kmap_atomic(struct page *page) void *kmap; int type; + preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); @@ -121,6 +122,7 @@ void __kunmap_atomic(void *kvaddr) kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)])); } pagefault_enable(); + preempt_enable(); } EXPORT_SYMBOL(__kunmap_atomic); @@ -130,6 +132,7 @@ void *kmap_atomic_pfn(unsigned long pfn) int idx, type; struct page *page = pfn_to_page(pfn); + preempt_disable(); pagefault_disable(); if (!PageHighMem(page)) return page_address(page); diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 4e6ef896c619..7186382672b5 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -1112,22 +1112,22 @@ void __init sanity_check_meminfo(void) } /* - * Find the first non-section-aligned page, and point + * Find the first non-pmd-aligned page, and point * memblock_limit at it. This relies on rounding the - * limit down to be section-aligned, which happens at - * the end of this function. + * limit down to be pmd-aligned, which happens at the + * end of this function. * * With this algorithm, the start or end of almost any - * bank can be non-section-aligned. The only exception - * is that the start of the bank 0 must be section- + * bank can be non-pmd-aligned. The only exception is + * that the start of the bank 0 must be section- * aligned, since otherwise memory would need to be * allocated when mapping the start of bank 0, which * occurs before any free memory is mapped. */ if (!memblock_limit) { - if (!IS_ALIGNED(block_start, SECTION_SIZE)) + if (!IS_ALIGNED(block_start, PMD_SIZE)) memblock_limit = block_start; - else if (!IS_ALIGNED(block_end, SECTION_SIZE)) + else if (!IS_ALIGNED(block_end, PMD_SIZE)) memblock_limit = arm_lowmem_limit; } @@ -1137,12 +1137,12 @@ void __init sanity_check_meminfo(void) high_memory = __va(arm_lowmem_limit - 1) + 1; /* - * Round the memblock limit down to a section size. This + * Round the memblock limit down to a pmd size. This * helps to ensure that we will allocate memory from the - * last full section, which should be mapped. + * last full pmd, which should be mapped. */ if (memblock_limit) - memblock_limit = round_down(memblock_limit, SECTION_SIZE); + memblock_limit = round_down(memblock_limit, PMD_SIZE); if (!memblock_limit) memblock_limit = arm_lowmem_limit; diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S index aa0519eed698..774ef1323554 100644 --- a/arch/arm/mm/proc-arm1020.S +++ b/arch/arm/mm/proc-arm1020.S @@ -22,8 +22,6 @@ * * These are the low level assembler for performing cache and TLB * functions on the arm1020. - * - * CONFIG_CPU_ARM1020_CPU_IDLE -> nohlt */ #include <linux/linkage.h> #include <linux/init.h> diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S index bff4c7f70fd6..ae3c27b71594 100644 --- a/arch/arm/mm/proc-arm1020e.S +++ b/arch/arm/mm/proc-arm1020e.S @@ -22,8 +22,6 @@ * * These are the low level assembler for performing cache and TLB * functions on the arm1020e. - * - * CONFIG_CPU_ARM1020_CPU_IDLE -> nohlt */ #include <linux/linkage.h> #include <linux/init.h> diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S index ede8c54ab4aa..32a47cc19076 100644 --- a/arch/arm/mm/proc-arm925.S +++ b/arch/arm/mm/proc-arm925.S @@ -441,9 +441,6 @@ ENTRY(cpu_arm925_set_pte_ext) .type __arm925_setup, #function __arm925_setup: mov r0, #0 -#if defined(CONFIG_CPU_ICACHE_STREAMING_DISABLE) - orr r0,r0,#1 << 7 -#endif /* Transparent on, D-cache clean & flush mode. See NOTE2 above */ orr r0,r0,#1 << 1 @ transparent mode on diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S index e494d6d6acbe..92e08bf37aad 100644 --- a/arch/arm/mm/proc-feroceon.S +++ b/arch/arm/mm/proc-feroceon.S @@ -602,7 +602,6 @@ __\name\()_proc_info: PMD_SECT_AP_WRITE | \ PMD_SECT_AP_READ initfn __feroceon_setup, __\name\()_proc_info - .long __feroceon_setup .long cpu_arch_name .long cpu_elf_name .long HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index e1268f905026..e0e23582c8b4 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -54,6 +54,7 @@ #define SEEN_DATA (1 << (BPF_MEMWORDS + 3)) #define FLAG_NEED_X_RESET (1 << 0) +#define FLAG_IMM_OVERFLOW (1 << 1) struct jit_ctx { const struct bpf_prog *skf; @@ -293,6 +294,15 @@ static u16 imm_offset(u32 k, struct jit_ctx *ctx) /* PC in ARM mode == address of the instruction + 8 */ imm = offset - (8 + ctx->idx * 4); + if (imm & ~0xfff) { + /* + * literal pool is too far, signal it into flags. we + * can only detect it on the second pass unfortunately. + */ + ctx->flags |= FLAG_IMM_OVERFLOW; + return 0; + } + return imm; } @@ -449,10 +459,21 @@ static inline void emit_udiv(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx) return; } #endif - if (rm != ARM_R0) - emit(ARM_MOV_R(ARM_R0, rm), ctx); + + /* + * For BPF_ALU | BPF_DIV | BPF_K instructions, rm is ARM_R4 + * (r_A) and rn is ARM_R0 (r_scratch) so load rn first into + * ARM_R1 to avoid accidentally overwriting ARM_R0 with rm + * before using it as a source for ARM_R1. + * + * For BPF_ALU | BPF_DIV | BPF_X rm is ARM_R4 (r_A) and rn is + * ARM_R5 (r_X) so there is no particular register overlap + * issues. + */ if (rn != ARM_R1) emit(ARM_MOV_R(ARM_R1, rn), ctx); + if (rm != ARM_R0) + emit(ARM_MOV_R(ARM_R0, rm), ctx); ctx->seen |= SEEN_CALL; emit_mov_i(ARM_R3, (u32)jit_udiv, ctx); @@ -855,6 +876,14 @@ b_epilogue: default: return -1; } + + if (ctx->flags & FLAG_IMM_OVERFLOW) + /* + * this instruction generated an overflow when + * trying to access the literal pool, so + * delegate this filter to the kernel interpreter. + */ + return -1; } /* compute offsets only during the first pass */ @@ -917,7 +946,14 @@ void bpf_jit_compile(struct bpf_prog *fp) ctx.idx = 0; build_prologue(&ctx); - build_body(&ctx); + if (build_body(&ctx) < 0) { +#if __LINUX_ARM_ARCH__ < 7 + if (ctx.imm_count) + kfree(ctx.imms); +#endif + bpf_jit_binary_free(header); + goto out; + } build_epilogue(&ctx); flush_icache_range((u32)ctx.target, (u32)(ctx.target + ctx.idx)); diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 224081ccc92f..7d0f07020c80 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -272,6 +272,7 @@ void xen_arch_pre_suspend(void) { } void xen_arch_post_suspend(int suspend_cancelled) { } void xen_timer_resume(void) { } void xen_arch_resume(void) { } +void xen_arch_suspend(void) { } /* In the hypervisor.S file. */ diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index 793551d15f1d..498325074a06 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -4,6 +4,7 @@ #include <linux/gfp.h> #include <linux/highmem.h> #include <linux/export.h> +#include <linux/memblock.h> #include <linux/of_address.h> #include <linux/slab.h> #include <linux/types.h> @@ -21,6 +22,20 @@ #include <asm/xen/hypercall.h> #include <asm/xen/interface.h> +unsigned long xen_get_swiotlb_free_pages(unsigned int order) +{ + struct memblock_region *reg; + gfp_t flags = __GFP_NOWARN; + + for_each_memblock(memory, reg) { + if (reg->base < (phys_addr_t)0xffffffff) { + flags |= __GFP_DMA; + break; + } + } + return __get_free_pages(flags, order); +} + enum dma_cache_op { DMA_UNMAP, DMA_MAP, |