diff options
Diffstat (limited to 'arch')
243 files changed, 1687 insertions, 1145 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 78c6f05b10f9..24862d15f3a3 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1105,6 +1105,12 @@ config HAVE_ARCH_PFN_VALID config ARCH_SUPPORTS_DEBUG_PAGEALLOC bool +config ARCH_SPLIT_ARG64 + bool + help + If a 32-bit architecture requires 64-bit arguments to be split into + pairs of 32-bit arguments, select this option. + source "kernel/gcov/Kconfig" source "scripts/gcc-plugins/Kconfig" diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 0c6bf0d1df7a..578bdbbb0fa7 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -102,16 +102,22 @@ libs-y += arch/arc/lib/ $(LIBGCC) boot := arch/arc/boot -#default target for make without any arguments. -KBUILD_IMAGE := $(boot)/bootpImage - -all: bootpImage -bootpImage: vmlinux - -boot_targets += uImage uImage.bin uImage.gz +boot_targets := uImage.bin uImage.gz uImage.lzma +PHONY += $(boot_targets) $(boot_targets): vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ +uimage-default-y := uImage.bin +uimage-default-$(CONFIG_KERNEL_GZIP) := uImage.gz +uimage-default-$(CONFIG_KERNEL_LZMA) := uImage.lzma + +PHONY += uImage +uImage: $(uimage-default-y) + @ln -sf $< $(boot)/uImage + @$(kecho) ' Image $(boot)/uImage is ready' + +CLEAN_FILES += $(boot)/uImage + archclean: $(Q)$(MAKE) $(clean)=$(boot) diff --git a/arch/arc/boot/Makefile b/arch/arc/boot/Makefile index 538b92f4dd25..5648748c285f 100644 --- a/arch/arc/boot/Makefile +++ b/arch/arc/boot/Makefile @@ -1,5 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -targets := vmlinux.bin vmlinux.bin.gz uImage # uImage build relies on mkimage being availble on your host for ARC target # You will need to build u-boot for ARC, rename mkimage to arc-elf32-mkimage @@ -7,23 +6,18 @@ targets := vmlinux.bin vmlinux.bin.gz uImage OBJCOPYFLAGS= -O binary -R .note -R .note.gnu.build-id -R .comment -S -LINUX_START_TEXT = $$(readelf -h vmlinux | \ +LINUX_START_TEXT = $$($(READELF) -h vmlinux | \ grep "Entry point address" | grep -o 0x.*) UIMAGE_LOADADDR = $(CONFIG_LINUX_LINK_BASE) UIMAGE_ENTRYADDR = $(LINUX_START_TEXT) -suffix-y := bin -suffix-$(CONFIG_KERNEL_GZIP) := gz -suffix-$(CONFIG_KERNEL_LZMA) := lzma - -targets += uImage +targets += vmlinux.bin +targets += vmlinux.bin.gz +targets += vmlinux.bin.lzma targets += uImage.bin targets += uImage.gz targets += uImage.lzma -extra-y += vmlinux.bin -extra-y += vmlinux.bin.gz -extra-y += vmlinux.bin.lzma $(obj)/vmlinux.bin: vmlinux FORCE $(call if_changed,objcopy) @@ -42,7 +36,3 @@ $(obj)/uImage.gz: $(obj)/vmlinux.bin.gz FORCE $(obj)/uImage.lzma: $(obj)/vmlinux.bin.lzma FORCE $(call if_changed,uimage,lzma) - -$(obj)/uImage: $(obj)/uImage.$(suffix-y) - @ln -sf $(notdir $<) $@ - @echo ' Image $@ is ready' diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h index 23e41e890eda..ad9b7fe4dba3 100644 --- a/arch/arc/include/asm/page.h +++ b/arch/arc/include/asm/page.h @@ -10,6 +10,7 @@ #ifndef __ASSEMBLY__ #define clear_page(paddr) memset((paddr), 0, PAGE_SIZE) +#define copy_user_page(to, from, vaddr, pg) copy_page(to, from) #define copy_page(to, from) memcpy((to), (from), PAGE_SIZE) struct vm_area_struct; diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S index 1f5308abf36d..1743506081da 100644 --- a/arch/arc/kernel/entry.S +++ b/arch/arc/kernel/entry.S @@ -307,7 +307,7 @@ resume_user_mode_begin: mov r0, sp ; pt_regs for arg to do_signal()/do_notify_resume() GET_CURR_THR_INFO_FLAGS r9 - and.f 0, r9, TIF_SIGPENDING|TIF_NOTIFY_SIGNAL + and.f 0, r9, _TIF_SIGPENDING|_TIF_NOTIFY_SIGNAL bz .Lchk_notify_resume ; Normal Trap/IRQ entry only saves Scratch (caller-saved) regs diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig index 6b5c54576f54..a2d10c29fbcc 100644 --- a/arch/arc/plat-hsdk/Kconfig +++ b/arch/arc/plat-hsdk/Kconfig @@ -7,6 +7,7 @@ menuconfig ARC_SOC_HSDK depends on ISA_ARCV2 select ARC_HAS_ACCL_REGS select ARC_IRQ_NO_AUTOSAVE + select ARC_FPU_SAVE_RESTORE select CLK_HSDK select RESET_CONTROLLER select RESET_HSDK diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c index 8452753efebe..31927d2fe297 100644 --- a/arch/arm/boot/compressed/atags_to_fdt.c +++ b/arch/arm/boot/compressed/atags_to_fdt.c @@ -15,7 +15,8 @@ static int node_offset(void *fdt, const char *node_path) { int offset = fdt_path_offset(fdt, node_path); if (offset == -FDT_ERR_NOTFOUND) - offset = fdt_add_subnode(fdt, 0, node_path); + /* Add the node to root if not found, dropping the leading '/' */ + offset = fdt_add_subnode(fdt, 0, node_path + 1); return offset; } diff --git a/arch/arm/boot/dts/imx6q-tbs2910.dts b/arch/arm/boot/dts/imx6q-tbs2910.dts index 861e05d53157..343364d3e4f7 100644 --- a/arch/arm/boot/dts/imx6q-tbs2910.dts +++ b/arch/arm/boot/dts/imx6q-tbs2910.dts @@ -16,6 +16,13 @@ stdout-path = &uart1; }; + aliases { + mmc0 = &usdhc2; + mmc1 = &usdhc3; + mmc2 = &usdhc4; + /delete-property/ mmc3; + }; + memory@10000000 { device_type = "memory"; reg = <0x10000000 0x80000000>; diff --git a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi index 736074f1c3ef..959d8ac2e393 100644 --- a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi +++ b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi @@ -418,7 +418,7 @@ /* VDD_AUD_1P8: Audio codec */ reg_aud_1p8v: ldo3 { - regulator-name = "vdd1p8"; + regulator-name = "vdd1p8a"; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; regulator-boot-on; diff --git a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi index d6df598bd1c2..b167b33bd108 100644 --- a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi @@ -137,7 +137,7 @@ lcd_backlight: lcd-backlight { compatible = "pwm-backlight"; - pwms = <&pwm4 0 5000000>; + pwms = <&pwm4 0 5000000 0>; pwm-names = "LCD_BKLT_PWM"; brightness-levels = <0 10 20 30 40 50 60 70 80 90 100>; @@ -167,7 +167,7 @@ i2c-gpio,delay-us = <2>; /* ~100 kHz */ #address-cells = <1>; #size-cells = <0>; - status = "disabld"; + status = "disabled"; }; i2c_cam: i2c-gpio-cam { @@ -179,7 +179,7 @@ i2c-gpio,delay-us = <2>; /* ~100 kHz */ #address-cells = <1>; #size-cells = <0>; - status = "disabld"; + status = "disabled"; }; }; diff --git a/arch/arm/boot/dts/imx6qdl-sr-som.dtsi b/arch/arm/boot/dts/imx6qdl-sr-som.dtsi index b06577808ff4..7e4e5fd0143a 100644 --- a/arch/arm/boot/dts/imx6qdl-sr-som.dtsi +++ b/arch/arm/boot/dts/imx6qdl-sr-som.dtsi @@ -53,7 +53,6 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_microsom_enet_ar8035>; - phy-handle = <&phy>; phy-mode = "rgmii-id"; phy-reset-duration = <2>; phy-reset-gpios = <&gpio4 15 GPIO_ACTIVE_LOW>; @@ -63,10 +62,19 @@ #address-cells = <1>; #size-cells = <0>; - phy: ethernet-phy@0 { + /* + * The PHY can appear at either address 0 or 4 due to the + * configuration (LED) pin not being pulled sufficiently. + */ + ethernet-phy@0 { reg = <0>; qca,clk-out-frequency = <125000000>; }; + + ethernet-phy@4 { + reg = <4>; + qca,clk-out-frequency = <125000000>; + }; }; }; diff --git a/arch/arm/boot/dts/imx7d-flex-concentrator.dts b/arch/arm/boot/dts/imx7d-flex-concentrator.dts index 84b095279e65..bd6b5285aa8d 100644 --- a/arch/arm/boot/dts/imx7d-flex-concentrator.dts +++ b/arch/arm/boot/dts/imx7d-flex-concentrator.dts @@ -115,6 +115,7 @@ compatible = "nxp,pcf2127"; reg = <0>; spi-max-frequency = <2000000>; + reset-source; }; }; diff --git a/arch/arm/boot/dts/lpc32xx.dtsi b/arch/arm/boot/dts/lpc32xx.dtsi index 3a5cfb0ddb20..c87066d6c995 100644 --- a/arch/arm/boot/dts/lpc32xx.dtsi +++ b/arch/arm/boot/dts/lpc32xx.dtsi @@ -326,9 +326,6 @@ clocks = <&xtal_32k>, <&xtal>; clock-names = "xtal_32k", "xtal"; - - assigned-clocks = <&clk LPC32XX_CLK_HCLK_PLL>; - assigned-clock-rates = <208000000>; }; }; diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index c8745bc800f7..7b8c18e6605e 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -114,7 +114,7 @@ gpio-sck = <&gpio1 12 GPIO_ACTIVE_HIGH>; gpio-miso = <&gpio1 18 GPIO_ACTIVE_HIGH>; gpio-mosi = <&gpio1 20 GPIO_ACTIVE_HIGH>; - cs-gpios = <&gpio1 19 GPIO_ACTIVE_HIGH>; + cs-gpios = <&gpio1 19 GPIO_ACTIVE_LOW>; num-chipselects = <1>; /* lcd panel */ @@ -124,7 +124,6 @@ spi-max-frequency = <100000>; spi-cpol; spi-cpha; - spi-cs-high; backlight= <&backlight>; label = "lcd"; diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi index 11d41e86f814..7dde9fbb06d3 100644 --- a/arch/arm/boot/dts/omap3-n950-n9.dtsi +++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi @@ -494,3 +494,11 @@ clock-names = "sysclk"; }; }; + +&aes1_target { + status = "disabled"; +}; + +&aes2_target { + status = "disabled"; +}; diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts index 3ea4c5b9fd31..e833c21f1c01 100644 --- a/arch/arm/boot/dts/omap4-droid4-xt894.dts +++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts @@ -16,8 +16,13 @@ debounce-interval = <10>; }; + /* + * We use pad 0x4a100116 abe_dmic_din3.gpio_122 as the irq instead + * of the gpio interrupt to avoid lost events in deeper idle states. + */ slider { label = "Keypad Slide"; + interrupts-extended = <&omap4_pmx_core 0xd6>; gpios = <&gpio4 26 GPIO_ACTIVE_HIGH>; /* gpio122 */ linux,input-type = <EV_SW>; linux,code = <SW_KEYPAD_SLIDE>; diff --git a/arch/arm/boot/dts/picoxcell-pc3x2.dtsi b/arch/arm/boot/dts/picoxcell-pc3x2.dtsi index c4c6c7e9e37b..5898879a3038 100644 --- a/arch/arm/boot/dts/picoxcell-pc3x2.dtsi +++ b/arch/arm/boot/dts/picoxcell-pc3x2.dtsi @@ -45,18 +45,21 @@ emac: gem@30000 { compatible = "cadence,gem"; reg = <0x30000 0x10000>; + interrupt-parent = <&vic0>; interrupts = <31>; }; dmac1: dmac@40000 { compatible = "snps,dw-dmac"; reg = <0x40000 0x10000>; + interrupt-parent = <&vic0>; interrupts = <25>; }; dmac2: dmac@50000 { compatible = "snps,dw-dmac"; reg = <0x50000 0x10000>; + interrupt-parent = <&vic0>; interrupts = <26>; }; @@ -233,6 +236,7 @@ axi2pico@c0000000 { compatible = "picochip,axi2pico-pc3x2"; reg = <0xc0000000 0x10000>; + interrupt-parent = <&vic0>; interrupts = <13 14 15 16 17 18 19 20 21>; }; }; diff --git a/arch/arm/boot/dts/ste-db8500.dtsi b/arch/arm/boot/dts/ste-db8500.dtsi index d309fad32229..344d29853bf7 100644 --- a/arch/arm/boot/dts/ste-db8500.dtsi +++ b/arch/arm/boot/dts/ste-db8500.dtsi @@ -12,4 +12,42 @@ 200000 0>; }; }; + + reserved-memory { + #address-cells = <1>; + #size-cells = <1>; + ranges; + + /* Modem trace memory */ + ram@06000000 { + reg = <0x06000000 0x00f00000>; + no-map; + }; + + /* Modem shared memory */ + ram@06f00000 { + reg = <0x06f00000 0x00100000>; + no-map; + }; + + /* Modem private memory */ + ram@07000000 { + reg = <0x07000000 0x01000000>; + no-map; + }; + + /* + * Initial Secure Software ISSW memory + * + * This is probably only used if the kernel tries + * to actually call into trustzone to run secure + * applications, which the mainline kernel probably + * will not do on this old chipset. But you can never + * be too careful, so reserve this memory anyway. + */ + ram@17f00000 { + reg = <0x17f00000 0x00100000>; + no-map; + }; + }; }; diff --git a/arch/arm/boot/dts/ste-db8520.dtsi b/arch/arm/boot/dts/ste-db8520.dtsi index 48bd8728ae27..287804e9e183 100644 --- a/arch/arm/boot/dts/ste-db8520.dtsi +++ b/arch/arm/boot/dts/ste-db8520.dtsi @@ -12,4 +12,42 @@ 200000 0>; }; }; + + reserved-memory { + #address-cells = <1>; + #size-cells = <1>; + ranges; + + /* Modem trace memory */ + ram@06000000 { + reg = <0x06000000 0x00f00000>; + no-map; + }; + + /* Modem shared memory */ + ram@06f00000 { + reg = <0x06f00000 0x00100000>; + no-map; + }; + + /* Modem private memory */ + ram@07000000 { + reg = <0x07000000 0x01000000>; + no-map; + }; + + /* + * Initial Secure Software ISSW memory + * + * This is probably only used if the kernel tries + * to actually call into trustzone to run secure + * applications, which the mainline kernel probably + * will not do on this old chipset. But you can never + * be too careful, so reserve this memory anyway. + */ + ram@17f00000 { + reg = <0x17f00000 0x00100000>; + no-map; + }; + }; }; diff --git a/arch/arm/boot/dts/ste-db9500.dtsi b/arch/arm/boot/dts/ste-db9500.dtsi new file mode 100644 index 000000000000..0afff703191c --- /dev/null +++ b/arch/arm/boot/dts/ste-db9500.dtsi @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include "ste-dbx5x0.dtsi" + +/ { + cpus { + cpu@300 { + /* cpufreq controls */ + operating-points = <1152000 0 + 800000 0 + 400000 0 + 200000 0>; + }; + }; + + reserved-memory { + #address-cells = <1>; + #size-cells = <1>; + ranges; + + /* + * Initial Secure Software ISSW memory + * + * This is probably only used if the kernel tries + * to actually call into trustzone to run secure + * applications, which the mainline kernel probably + * will not do on this old chipset. But you can never + * be too careful, so reserve this memory anyway. + */ + ram@17f00000 { + reg = <0x17f00000 0x00100000>; + no-map; + }; + }; +}; diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts index be90e73c923e..27d8a07718a0 100644 --- a/arch/arm/boot/dts/ste-snowball.dts +++ b/arch/arm/boot/dts/ste-snowball.dts @@ -4,7 +4,7 @@ */ /dts-v1/; -#include "ste-db8500.dtsi" +#include "ste-db9500.dtsi" #include "ste-href-ab8500.dtsi" #include "ste-href-family-pinctrl.dtsi" diff --git a/arch/arm/boot/dts/ste-ux500-samsung-golden.dts b/arch/arm/boot/dts/ste-ux500-samsung-golden.dts index 496f9d3ba7b7..60fe6189e728 100644 --- a/arch/arm/boot/dts/ste-ux500-samsung-golden.dts +++ b/arch/arm/boot/dts/ste-ux500-samsung-golden.dts @@ -329,6 +329,7 @@ panel@0 { compatible = "samsung,s6e63m0"; reg = <0>; + max-brightness = <15>; vdd3-supply = <&panel_reg_3v0>; vci-supply = <&panel_reg_1v8>; reset-gpios = <&gpio4 11 GPIO_ACTIVE_LOW>; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-drc02.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-drc02.dtsi index 62ab23824a3e..5088dd3a301b 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-drc02.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-drc02.dtsi @@ -33,9 +33,9 @@ * during TX anyway and that it only controls drive enable DE * line. Hence, the RX is always enabled here. */ - rs485-rx-en { + rs485-rx-en-hog { gpio-hog; - gpios = <8 GPIO_ACTIVE_HIGH>; + gpios = <8 0>; output-low; line-name = "rs485-rx-en"; }; @@ -61,9 +61,9 @@ * order to reset the Hub when USB bus is powered down, but * so far there is no such functionality. */ - usb-hub { + usb-hub-hog { gpio-hog; - gpios = <2 GPIO_ACTIVE_HIGH>; + gpios = <2 0>; output-high; line-name = "usb-hub-reset"; }; @@ -87,6 +87,12 @@ }; }; +&i2c4 { + touchscreen@49 { + status = "disabled"; + }; +}; + &i2c5 { /* TP7/TP8 */ pinctrl-names = "default"; pinctrl-0 = <&i2c5_pins_a>; @@ -104,7 +110,7 @@ * are used for on-board microSD slot instead. */ /delete-property/broken-cd; - cd-gpios = <&gpioi 10 (GPIO_ACTIVE_LOW | GPIO_PULL_UP)>; + cd-gpios = <&gpioi 10 GPIO_ACTIVE_HIGH>; disable-wp; }; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-picoitx.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-picoitx.dtsi index 356150d28c42..32700cca24c8 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-picoitx.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-picoitx.dtsi @@ -43,9 +43,9 @@ * in order to turn on port power when USB bus is powered up, but so * far there is no such functionality. */ - usb-port-power { + usb-port-power-hog { gpio-hog; - gpios = <13 GPIO_ACTIVE_LOW>; + gpios = <13 0>; output-low; line-name = "usb-port-power"; }; diff --git a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi index ac46ab363e1b..daff5318f301 100644 --- a/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi +++ b/arch/arm/boot/dts/stm32mp15xx-dhcom-som.dtsi @@ -390,7 +390,8 @@ pinctrl-0 = <&sdmmc1_b4_pins_a &sdmmc1_dir_pins_a>; pinctrl-1 = <&sdmmc1_b4_od_pins_a &sdmmc1_dir_pins_a>; pinctrl-2 = <&sdmmc1_b4_sleep_pins_a &sdmmc1_dir_sleep_pins_a>; - broken-cd; + cd-gpios = <&gpiog 1 (GPIO_ACTIVE_LOW | GPIO_PULL_UP)>; + disable-wp; st,sig-dir; st,neg-edge; st,use-ckin; diff --git a/arch/arm/boot/dts/sun7i-a20-bananapro.dts b/arch/arm/boot/dts/sun7i-a20-bananapro.dts index 01ccff756996..5740f9442705 100644 --- a/arch/arm/boot/dts/sun7i-a20-bananapro.dts +++ b/arch/arm/boot/dts/sun7i-a20-bananapro.dts @@ -110,7 +110,7 @@ pinctrl-names = "default"; pinctrl-0 = <&gmac_rgmii_pins>; phy-handle = <&phy1>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-supply = <®_gmac_3v3>; status = "okay"; }; diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index 1c11d1557779..b515c31f0ab7 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -279,6 +279,7 @@ CONFIG_SERIAL_OMAP_CONSOLE=y CONFIG_SERIAL_DEV_BUS=y CONFIG_I2C_CHARDEV=y CONFIG_SPI=y +CONFIG_SPI_GPIO=m CONFIG_SPI_OMAP24XX=y CONFIG_SPI_TI_QSPI=m CONFIG_HSI=m @@ -296,7 +297,6 @@ CONFIG_GPIO_TWL4030=y CONFIG_W1=m CONFIG_HDQ_MASTER_OMAP=m CONFIG_W1_SLAVE_DS250X=m -CONFIG_POWER_AVS=y CONFIG_POWER_RESET=y CONFIG_POWER_RESET_GPIO=y CONFIG_BATTERY_BQ27XXX=m diff --git a/arch/arm/crypto/chacha-glue.c b/arch/arm/crypto/chacha-glue.c index 7b5cf8430c6d..cdde8fd01f8f 100644 --- a/arch/arm/crypto/chacha-glue.c +++ b/arch/arm/crypto/chacha-glue.c @@ -60,6 +60,7 @@ static void chacha_doneon(u32 *state, u8 *dst, const u8 *src, chacha_block_xor_neon(state, d, s, nrounds); if (d != dst) memcpy(dst, buf, bytes); + state[12]++; } } diff --git a/arch/arm/include/asm/kexec-internal.h b/arch/arm/include/asm/kexec-internal.h new file mode 100644 index 000000000000..ecc2322db7aa --- /dev/null +++ b/arch/arm/include/asm/kexec-internal.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ARM_KEXEC_INTERNAL_H +#define _ARM_KEXEC_INTERNAL_H + +struct kexec_relocate_data { + unsigned long kexec_start_address; + unsigned long kexec_indirection_page; + unsigned long kexec_mach_type; + unsigned long kexec_r2; +}; + +#endif diff --git a/arch/arm/include/debug/tegra.S b/arch/arm/include/debug/tegra.S index 98daa7f48314..7454480d084b 100644 --- a/arch/arm/include/debug/tegra.S +++ b/arch/arm/include/debug/tegra.S @@ -149,7 +149,34 @@ .align 99: .word . +#if defined(ZIMAGE) + .word . + 4 +/* + * Storage for the state maintained by the macro. + * + * In the kernel proper, this data is located in arch/arm/mach-tegra/tegra.c. + * That's because this header is included from multiple files, and we only + * want a single copy of the data. In particular, the UART probing code above + * assumes it's running using physical addresses. This is true when this file + * is included from head.o, but not when included from debug.o. So we need + * to share the probe results between the two copies, rather than having + * to re-run the probing again later. + * + * In the decompressor, we put the storage right here, since common.c + * isn't included in the decompressor build. This storage data gets put in + * .text even though it's really data, since .data is discarded from the + * decompressor. Luckily, .text is writeable in the decompressor, unless + * CONFIG_ZBOOT_ROM. That dependency is handled in arch/arm/Kconfig.debug. + */ + /* Debug UART initialization required */ + .word 1 + /* Debug UART physical address */ + .word 0 + /* Debug UART virtual address */ + .word 0 +#else .word tegra_uart_config +#endif .ltorg /* Load previously selected UART address */ @@ -189,30 +216,3 @@ .macro waituarttxrdy,rd,rx .endm - -/* - * Storage for the state maintained by the macros above. - * - * In the kernel proper, this data is located in arch/arm/mach-tegra/tegra.c. - * That's because this header is included from multiple files, and we only - * want a single copy of the data. In particular, the UART probing code above - * assumes it's running using physical addresses. This is true when this file - * is included from head.o, but not when included from debug.o. So we need - * to share the probe results between the two copies, rather than having - * to re-run the probing again later. - * - * In the decompressor, we put the symbol/storage right here, since common.c - * isn't included in the decompressor build. This symbol gets put in .text - * even though it's really data, since .data is discarded from the - * decompressor. Luckily, .text is writeable in the decompressor, unless - * CONFIG_ZBOOT_ROM. That dependency is handled in arch/arm/Kconfig.debug. - */ -#if defined(ZIMAGE) -tegra_uart_config: - /* Debug UART initialization required */ - .word 1 - /* Debug UART physical address */ - .word 0 - /* Debug UART virtual address */ - .word 0 -#endif diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c index a1570c8bab25..be8050b0c3df 100644 --- a/arch/arm/kernel/asm-offsets.c +++ b/arch/arm/kernel/asm-offsets.c @@ -12,6 +12,7 @@ #include <linux/mm.h> #include <linux/dma-mapping.h> #include <asm/cacheflush.h> +#include <asm/kexec-internal.h> #include <asm/glue-df.h> #include <asm/glue-pf.h> #include <asm/mach/arch.h> @@ -170,5 +171,9 @@ int main(void) DEFINE(MPU_RGN_PRBAR, offsetof(struct mpu_rgn, prbar)); DEFINE(MPU_RGN_PRLAR, offsetof(struct mpu_rgn, prlar)); #endif + DEFINE(KEXEC_START_ADDR, offsetof(struct kexec_relocate_data, kexec_start_address)); + DEFINE(KEXEC_INDIR_PAGE, offsetof(struct kexec_relocate_data, kexec_indirection_page)); + DEFINE(KEXEC_MACH_TYPE, offsetof(struct kexec_relocate_data, kexec_mach_type)); + DEFINE(KEXEC_R2, offsetof(struct kexec_relocate_data, kexec_r2)); return 0; } diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index 5d84ad333f05..2b09dad7935e 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -13,6 +13,7 @@ #include <linux/of_fdt.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> +#include <asm/kexec-internal.h> #include <asm/fncpy.h> #include <asm/mach-types.h> #include <asm/smp_plat.h> @@ -22,11 +23,6 @@ extern void relocate_new_kernel(void); extern const unsigned int relocate_new_kernel_size; -extern unsigned long kexec_start_address; -extern unsigned long kexec_indirection_page; -extern unsigned long kexec_mach_type; -extern unsigned long kexec_boot_atags; - static atomic_t waiting_for_crash_ipi; /* @@ -159,6 +155,7 @@ void (*kexec_reinit)(void); void machine_kexec(struct kimage *image) { unsigned long page_list, reboot_entry_phys; + struct kexec_relocate_data *data; void (*reboot_entry)(void); void *reboot_code_buffer; @@ -174,18 +171,17 @@ void machine_kexec(struct kimage *image) reboot_code_buffer = page_address(image->control_code_page); - /* Prepare parameters for reboot_code_buffer*/ - set_kernel_text_rw(); - kexec_start_address = image->start; - kexec_indirection_page = page_list; - kexec_mach_type = machine_arch_type; - kexec_boot_atags = image->arch.kernel_r2; - /* copy our kernel relocation code to the control code page */ reboot_entry = fncpy(reboot_code_buffer, &relocate_new_kernel, relocate_new_kernel_size); + data = reboot_code_buffer + relocate_new_kernel_size; + data->kexec_start_address = image->start; + data->kexec_indirection_page = page_list; + data->kexec_mach_type = machine_arch_type; + data->kexec_r2 = image->arch.kernel_r2; + /* get the identity mapping physical address for the reboot code */ reboot_entry_phys = virt_to_idmap(reboot_entry); diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S index 72a08786e16e..218d524360fc 100644 --- a/arch/arm/kernel/relocate_kernel.S +++ b/arch/arm/kernel/relocate_kernel.S @@ -5,14 +5,16 @@ #include <linux/linkage.h> #include <asm/assembler.h> +#include <asm/asm-offsets.h> #include <asm/kexec.h> .align 3 /* not needed for this code, but keeps fncpy() happy */ ENTRY(relocate_new_kernel) - ldr r0,kexec_indirection_page - ldr r1,kexec_start_address + adr r7, relocate_new_kernel_end + ldr r0, [r7, #KEXEC_INDIR_PAGE] + ldr r1, [r7, #KEXEC_START_ADDR] /* * If there is no indirection page (we are doing crashdumps) @@ -57,34 +59,16 @@ ENTRY(relocate_new_kernel) 2: /* Jump to relocated kernel */ - mov lr,r1 - mov r0,#0 - ldr r1,kexec_mach_type - ldr r2,kexec_boot_atags - ARM( ret lr ) - THUMB( bx lr ) - - .align - - .globl kexec_start_address -kexec_start_address: - .long 0x0 - - .globl kexec_indirection_page -kexec_indirection_page: - .long 0x0 - - .globl kexec_mach_type -kexec_mach_type: - .long 0x0 - - /* phy addr of the atags for the new kernel */ - .globl kexec_boot_atags -kexec_boot_atags: - .long 0x0 + mov lr, r1 + mov r0, #0 + ldr r1, [r7, #KEXEC_MACH_TYPE] + ldr r2, [r7, #KEXEC_R2] + ARM( ret lr ) + THUMB( bx lr ) ENDPROC(relocate_new_kernel) + .align 3 relocate_new_kernel_end: .globl relocate_new_kernel_size diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c index 9d2e916121be..a3a38d0a4c85 100644 --- a/arch/arm/kernel/signal.c +++ b/arch/arm/kernel/signal.c @@ -693,18 +693,20 @@ struct page *get_signal_page(void) addr = page_address(page); + /* Poison the entire page */ + memset32(addr, __opcode_to_mem_arm(0xe7fddef1), + PAGE_SIZE / sizeof(u32)); + /* Give the signal return code some randomness */ offset = 0x200 + (get_random_int() & 0x7fc); signal_return_offset = offset; - /* - * Copy signal return handlers into the vector page, and - * set sigreturn to be a pointer to these. - */ + /* Copy signal return handlers into the page */ memcpy(addr + offset, sigreturn_codes, sizeof(sigreturn_codes)); - ptr = (unsigned long)addr + offset; - flush_icache_range(ptr, ptr + sizeof(sigreturn_codes)); + /* Flush out all instructions in this page */ + ptr = (unsigned long)addr; + flush_icache_range(ptr, ptr + PAGE_SIZE); return page; } diff --git a/arch/arm/mach-footbridge/dc21285.c b/arch/arm/mach-footbridge/dc21285.c index 416462e3f5d6..f9713dc561cf 100644 --- a/arch/arm/mach-footbridge/dc21285.c +++ b/arch/arm/mach-footbridge/dc21285.c @@ -65,15 +65,15 @@ dc21285_read_config(struct pci_bus *bus, unsigned int devfn, int where, if (addr) switch (size) { case 1: - asm("ldrb %0, [%1, %2]" + asm volatile("ldrb %0, [%1, %2]" : "=r" (v) : "r" (addr), "r" (where) : "cc"); break; case 2: - asm("ldrh %0, [%1, %2]" + asm volatile("ldrh %0, [%1, %2]" : "=r" (v) : "r" (addr), "r" (where) : "cc"); break; case 4: - asm("ldr %0, [%1, %2]" + asm volatile("ldr %0, [%1, %2]" : "=r" (v) : "r" (addr), "r" (where) : "cc"); break; } @@ -99,17 +99,17 @@ dc21285_write_config(struct pci_bus *bus, unsigned int devfn, int where, if (addr) switch (size) { case 1: - asm("strb %0, [%1, %2]" + asm volatile("strb %0, [%1, %2]" : : "r" (value), "r" (addr), "r" (where) : "cc"); break; case 2: - asm("strh %0, [%1, %2]" + asm volatile("strh %0, [%1, %2]" : : "r" (value), "r" (addr), "r" (where) : "cc"); break; case 4: - asm("str %0, [%1, %2]" + asm volatile("str %0, [%1, %2]" : : "r" (value), "r" (addr), "r" (where) : "cc"); break; diff --git a/arch/arm/mach-imx/suspend-imx6.S b/arch/arm/mach-imx/suspend-imx6.S index 1eabf2d2834b..e06f946b75b9 100644 --- a/arch/arm/mach-imx/suspend-imx6.S +++ b/arch/arm/mach-imx/suspend-imx6.S @@ -67,6 +67,7 @@ #define MX6Q_CCM_CCR 0x0 .align 3 + .arm .macro sync_l2_cache diff --git a/arch/arm/mach-omap1/board-osk.c b/arch/arm/mach-omap1/board-osk.c index a720259099ed..0a4c9b0b13b0 100644 --- a/arch/arm/mach-omap1/board-osk.c +++ b/arch/arm/mach-omap1/board-osk.c @@ -203,6 +203,8 @@ static int osk_tps_setup(struct i2c_client *client, void *context) */ gpio_request(OSK_TPS_GPIO_USB_PWR_EN, "n_vbus_en"); gpio_direction_output(OSK_TPS_GPIO_USB_PWR_EN, 1); + /* Free the GPIO again as the driver will request it */ + gpio_free(OSK_TPS_GPIO_USB_PWR_EN); /* Set GPIO 2 high so LED D3 is off by default */ tps65010_set_gpio_out_value(GPIO2, HIGH); diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig index 4a59c169a113..4178c0ee46eb 100644 --- a/arch/arm/mach-omap2/Kconfig +++ b/arch/arm/mach-omap2/Kconfig @@ -17,11 +17,10 @@ config ARCH_OMAP3 bool "TI OMAP3" depends on ARCH_MULTI_V7 select ARCH_OMAP2PLUS - select ARM_CPU_SUSPEND if PM + select ARM_CPU_SUSPEND select OMAP_HWMOD select OMAP_INTERCONNECT - select PM_OPP if PM - select PM if CPU_IDLE + select PM_OPP select SOC_HAS_OMAP2_SDRC select ARM_ERRATA_430973 @@ -30,7 +29,7 @@ config ARCH_OMAP4 depends on ARCH_MULTI_V7 select ARCH_OMAP2PLUS select ARCH_NEEDS_CPU_IDLE_COUPLED if SMP - select ARM_CPU_SUSPEND if PM + select ARM_CPU_SUSPEND select ARM_ERRATA_720789 select ARM_GIC select HAVE_ARM_SCU if SMP @@ -40,7 +39,7 @@ config ARCH_OMAP4 select OMAP_INTERCONNECT_BARRIER select PL310_ERRATA_588369 if CACHE_L2X0 select PL310_ERRATA_727915 if CACHE_L2X0 - select PM_OPP if PM + select PM_OPP select PM if CPU_IDLE select ARM_ERRATA_754322 select ARM_ERRATA_775420 @@ -50,7 +49,7 @@ config SOC_OMAP5 bool "TI OMAP5" depends on ARCH_MULTI_V7 select ARCH_OMAP2PLUS - select ARM_CPU_SUSPEND if PM + select ARM_CPU_SUSPEND select ARM_GIC select HAVE_ARM_SCU if SMP select HAVE_ARM_ARCH_TIMER @@ -58,14 +57,14 @@ config SOC_OMAP5 select OMAP_HWMOD select OMAP_INTERCONNECT select OMAP_INTERCONNECT_BARRIER - select PM_OPP if PM + select PM_OPP select ZONE_DMA if ARM_LPAE config SOC_AM33XX bool "TI AM33XX" depends on ARCH_MULTI_V7 select ARCH_OMAP2PLUS - select ARM_CPU_SUSPEND if PM + select ARM_CPU_SUSPEND config SOC_AM43XX bool "TI AM43x" @@ -79,13 +78,13 @@ config SOC_AM43XX select ARM_ERRATA_754322 select ARM_ERRATA_775420 select OMAP_INTERCONNECT - select ARM_CPU_SUSPEND if PM + select ARM_CPU_SUSPEND config SOC_DRA7XX bool "TI DRA7XX" depends on ARCH_MULTI_V7 select ARCH_OMAP2PLUS - select ARM_CPU_SUSPEND if PM + select ARM_CPU_SUSPEND select ARM_GIC select HAVE_ARM_SCU if SMP select HAVE_ARM_ARCH_TIMER @@ -94,7 +93,7 @@ config SOC_DRA7XX select OMAP_HWMOD select OMAP_INTERCONNECT select OMAP_INTERCONNECT_BARRIER - select PM_OPP if PM + select PM_OPP select ZONE_DMA if ARM_LPAE select PINCTRL_TI_IODELAY if OF && PINCTRL @@ -112,9 +111,11 @@ config ARCH_OMAP2PLUS select OMAP_DM_TIMER select OMAP_GPMC select PINCTRL - select PM_GENERIC_DOMAINS if PM - select PM_GENERIC_DOMAINS_OF if PM + select PM + select PM_GENERIC_DOMAINS + select PM_GENERIC_DOMAINS_OF select RESET_CONTROLLER + select SIMPLE_PM_BUS select SOC_BUS select TI_SYSC select OMAP_IRQCHIP @@ -140,7 +141,6 @@ config ARCH_OMAP2PLUS_TYPICAL select I2C_OMAP select MENELAUS if ARCH_OMAP2 select NEON if CPU_V7 - select PM select REGULATOR select REGULATOR_FIXED_VOLTAGE select TWL4030_CORE if ARCH_OMAP3 || ARCH_OMAP4 diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c index c8d317fafe2e..de37027ad758 100644 --- a/arch/arm/mach-omap2/cpuidle44xx.c +++ b/arch/arm/mach-omap2/cpuidle44xx.c @@ -151,10 +151,10 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, (cx->mpu_logic_state == PWRDM_POWER_OFF); /* Enter broadcast mode for periodic timers */ - tick_broadcast_enable(); + RCU_NONIDLE(tick_broadcast_enable()); /* Enter broadcast mode for one-shot timers */ - tick_broadcast_enter(); + RCU_NONIDLE(tick_broadcast_enter()); /* * Call idle CPU PM enter notifier chain so that @@ -166,7 +166,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, if (dev->cpu == 0) { pwrdm_set_logic_retst(mpu_pd, cx->mpu_logic_state); - omap_set_pwrdm_state(mpu_pd, cx->mpu_state); + RCU_NONIDLE(omap_set_pwrdm_state(mpu_pd, cx->mpu_state)); /* * Call idle CPU cluster PM enter notifier chain @@ -178,7 +178,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, index = 0; cx = state_ptr + index; pwrdm_set_logic_retst(mpu_pd, cx->mpu_logic_state); - omap_set_pwrdm_state(mpu_pd, cx->mpu_state); + RCU_NONIDLE(omap_set_pwrdm_state(mpu_pd, cx->mpu_state)); mpuss_can_lose_context = 0; } } @@ -194,9 +194,9 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, mpuss_can_lose_context) gic_dist_disable(); - clkdm_deny_idle(cpu_clkdm[1]); - omap_set_pwrdm_state(cpu_pd[1], PWRDM_POWER_ON); - clkdm_allow_idle(cpu_clkdm[1]); + RCU_NONIDLE(clkdm_deny_idle(cpu_clkdm[1])); + RCU_NONIDLE(omap_set_pwrdm_state(cpu_pd[1], PWRDM_POWER_ON)); + RCU_NONIDLE(clkdm_allow_idle(cpu_clkdm[1])); if (IS_PM44XX_ERRATUM(PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD) && mpuss_can_lose_context) { @@ -222,7 +222,7 @@ static int omap_enter_idle_coupled(struct cpuidle_device *dev, cpu_pm_exit(); cpu_pm_out: - tick_broadcast_exit(); + RCU_NONIDLE(tick_broadcast_exit()); fail: cpuidle_coupled_parallel_barrier(dev, &abort_barrier); diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c index f3191704cab9..56d6814bec26 100644 --- a/arch/arm/mach-omap2/omap_device.c +++ b/arch/arm/mach-omap2/omap_device.c @@ -230,10 +230,12 @@ static int _omap_device_notifier_call(struct notifier_block *nb, break; case BUS_NOTIFY_BIND_DRIVER: od = to_omap_device(pdev); - if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED) && - pm_runtime_status_suspended(dev)) { + if (od) { od->_driver_status = BUS_NOTIFY_BIND_DRIVER; - pm_runtime_set_active(dev); + if (od->_state == OMAP_DEVICE_STATE_ENABLED && + pm_runtime_status_suspended(dev)) { + pm_runtime_set_active(dev); + } } break; case BUS_NOTIFY_ADD_DEVICE: diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c index cd38bf07c094..2e3a10914c40 100644 --- a/arch/arm/mach-omap2/pdata-quirks.c +++ b/arch/arm/mach-omap2/pdata-quirks.c @@ -522,6 +522,7 @@ static struct of_dev_auxdata omap_auxdata_lookup[] = { &dra7_ipu1_dsp_iommu_pdata), #endif /* Common auxdata */ + OF_DEV_AUXDATA("simple-pm-bus", 0, NULL, omap_auxdata_lookup), OF_DEV_AUXDATA("ti,sysc", 0, NULL, &ti_sysc_pdata), OF_DEV_AUXDATA("pinctrl-single", 0, NULL, &pcs_pdata), OF_DEV_AUXDATA("ti,omap-prm-inst", 0, NULL, &ti_prm_pdata), diff --git a/arch/arm/mach-omap2/pmic-cpcap.c b/arch/arm/mach-omap2/pmic-cpcap.c index eab281a5fc9f..09076ad0576d 100644 --- a/arch/arm/mach-omap2/pmic-cpcap.c +++ b/arch/arm/mach-omap2/pmic-cpcap.c @@ -71,7 +71,7 @@ static struct omap_voltdm_pmic omap_cpcap_iva = { .vp_vstepmin = OMAP4_VP_VSTEPMIN_VSTEPMIN, .vp_vstepmax = OMAP4_VP_VSTEPMAX_VSTEPMAX, .vddmin = 900000, - .vddmax = 1350000, + .vddmax = 1375000, .vp_timeout_us = OMAP4_VP_VLIMITTO_TIMEOUT_US, .i2c_slave_addr = 0x44, .volt_reg_addr = 0x0, diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index 60e901cd0de6..8ad576ecd0f1 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -370,8 +370,6 @@ static int __init xen_guest_init(void) return -ENOMEM; } gnttab_init(); - if (!xen_initial_domain()) - xenbus_probe(NULL); /* * Making sure board specific code will not set up ops for diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 05e17351e4f3..f39568b28ec1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -174,8 +174,6 @@ config ARM64 select HAVE_NMI select HAVE_PATA_PLATFORM select HAVE_PERF_EVENTS - select HAVE_PERF_EVENTS_NMI if ARM64_PSEUDO_NMI && HW_PERF_EVENTS - select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP select HAVE_REGS_AND_STACK_ACCESS_API diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 6be9b3750250..90309208bb28 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -10,7 +10,7 @@ # # Copyright (C) 1995-2001 by Russell King -LDFLAGS_vmlinux :=--no-undefined -X -z norelro +LDFLAGS_vmlinux :=--no-undefined -X ifeq ($(CONFIG_RELOCATABLE), y) # Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour @@ -115,16 +115,20 @@ KBUILD_CPPFLAGS += -mbig-endian CHECKFLAGS += -D__AARCH64EB__ # Prefer the baremetal ELF build target, but not all toolchains include # it so fall back to the standard linux version if needed. -KBUILD_LDFLAGS += -EB $(call ld-option, -maarch64elfb, -maarch64linuxb) +KBUILD_LDFLAGS += -EB $(call ld-option, -maarch64elfb, -maarch64linuxb -z norelro) UTS_MACHINE := aarch64_be else KBUILD_CPPFLAGS += -mlittle-endian CHECKFLAGS += -D__AARCH64EL__ # Same as above, prefer ELF but fall back to linux target if needed. -KBUILD_LDFLAGS += -EL $(call ld-option, -maarch64elf, -maarch64linux) +KBUILD_LDFLAGS += -EL $(call ld-option, -maarch64elf, -maarch64linux -z norelro) UTS_MACHINE := aarch64 endif +ifeq ($(CONFIG_LD_IS_LLD), y) +KBUILD_LDFLAGS += -z norelro +endif + CHECKFLAGS += -D__aarch64__ ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS),y) diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi index ba1c6dfdc4b6..d945c84ab697 100644 --- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi @@ -280,8 +280,6 @@ "timing-adjustment"; rx-fifo-depth = <4096>; tx-fifo-depth = <2048>; - resets = <&reset RESET_ETHERNET>; - reset-names = "stmmaceth"; power-domains = <&pwrc PWRC_AXG_ETHERNET_MEM_ID>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi index 9c90d562ada1..b858c5e43cc8 100644 --- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi @@ -224,8 +224,6 @@ "timing-adjustment"; rx-fifo-depth = <4096>; tx-fifo-depth = <2048>; - resets = <&reset RESET_ETHERNET>; - reset-names = "stmmaceth"; status = "disabled"; mdio0: mdio { @@ -2390,7 +2388,7 @@ interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>; dr_mode = "host"; snps,dis_u2_susphy_quirk; - snps,quirk-frame-length-adjustment; + snps,quirk-frame-length-adjustment = <0x20>; snps,parkmode-disable-ss-quirk; }; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi index 726b91d3a905..0edd137151f8 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi @@ -13,7 +13,6 @@ #include <dt-bindings/interrupt-controller/irq.h> #include <dt-bindings/interrupt-controller/arm-gic.h> #include <dt-bindings/power/meson-gxbb-power.h> -#include <dt-bindings/reset/amlogic,meson-gxbb-reset.h> #include <dt-bindings/thermal/thermal.h> / { @@ -576,8 +575,6 @@ interrupt-names = "macirq"; rx-fifo-depth = <4096>; tx-fifo-depth = <2048>; - resets = <&reset RESET_ETHERNET>; - reset-names = "stmmaceth"; power-domains = <&pwrc PWRC_GXBB_ETHERNET_MEM_ID>; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-c4.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-c4.dts index cf5a98f0e47c..a712273c905a 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-c4.dts +++ b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-c4.dts @@ -52,7 +52,7 @@ regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; - gpio = <&gpio_ao GPIOAO_3 GPIO_ACTIVE_HIGH>; + gpio = <&gpio_ao GPIOAO_3 GPIO_OPEN_DRAIN>; enable-active-high; regulator-always-on; }; diff --git a/arch/arm64/boot/dts/bitmain/bm1880.dtsi b/arch/arm64/boot/dts/bitmain/bm1880.dtsi index fa6e6905f588..53a9b76057aa 100644 --- a/arch/arm64/boot/dts/bitmain/bm1880.dtsi +++ b/arch/arm64/boot/dts/bitmain/bm1880.dtsi @@ -127,7 +127,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <32>; + ngpios = <32>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; @@ -145,7 +145,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <32>; + ngpios = <32>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; @@ -163,7 +163,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <8>; + ngpios = <8>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi index aef8f2b00778..5401a646c840 100644 --- a/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi +++ b/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi @@ -4,11 +4,16 @@ */ usb { compatible = "simple-bus"; - dma-ranges; #address-cells = <2>; #size-cells = <2>; ranges = <0x0 0x0 0x0 0x68500000 0x0 0x00400000>; + /* + * Internally, USB bus to the interconnect can only address up + * to 40-bit + */ + dma-ranges = <0 0 0 0 0x100 0x0>; + usbphy0: usb-phy@0 { compatible = "brcm,sr-usb-combo-phy"; reg = <0x0 0x00000000 0x0 0x100>; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index 60ff19fa53b4..6c8a61c2cc74 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@ -101,7 +101,7 @@ reboot { compatible ="syscon-reboot"; regmap = <&rst>; - offset = <0xb0>; + offset = <0>; mask = <0x02>; }; diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi index 025e1f587662..565934cbfa28 100644 --- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi @@ -385,7 +385,7 @@ dcfg: dcfg@1ee0000 { compatible = "fsl,ls1046a-dcfg", "syscon"; - reg = <0x0 0x1ee0000 0x0 0x10000>; + reg = <0x0 0x1ee0000 0x0 0x1000>; big-endian; }; diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi index ee1790230490..2a79e89f821e 100644 --- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi @@ -253,7 +253,7 @@ #size-cells = <1>; ranges; - spba: bus@30000000 { + spba: spba-bus@30000000 { compatible = "fsl,spba-bus", "simple-bus"; #address-cells = <1>; #size-cells = <1>; diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi index ecccfbb4f5ad..23f5a5e37167 100644 --- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi @@ -266,7 +266,7 @@ #gpio-cells = <2>; interrupt-controller; #interrupt-cells = <2>; - gpio-ranges = <&iomuxc 0 56 26>, <&iomuxc 0 144 4>; + gpio-ranges = <&iomuxc 0 56 26>, <&iomuxc 26 144 4>; }; gpio4: gpio@30230000 { diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts index 7cc236575ee2..c0b93813ea9a 100644 --- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts +++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts @@ -415,7 +415,9 @@ &gcc { protected-clocks = <GCC_QSPI_CORE_CLK>, <GCC_QSPI_CORE_CLK_SRC>, - <GCC_QSPI_CNOC_PERIPH_AHB_CLK>; + <GCC_QSPI_CNOC_PERIPH_AHB_CLK>, + <GCC_LPASS_Q6_AXI_CLK>, + <GCC_LPASS_SWAY_CLK>; }; &gpu { diff --git a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts index 13fdd02cffe6..8b40f96e9780 100644 --- a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts +++ b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts @@ -302,7 +302,9 @@ &gcc { protected-clocks = <GCC_QSPI_CORE_CLK>, <GCC_QSPI_CORE_CLK_SRC>, - <GCC_QSPI_CNOC_PERIPH_AHB_CLK>; + <GCC_QSPI_CNOC_PERIPH_AHB_CLK>, + <GCC_LPASS_Q6_AXI_CLK>, + <GCC_LPASS_SWAY_CLK>; }; &gpu { @@ -320,6 +322,8 @@ &i2c3 { status = "okay"; clock-frequency = <400000>; + /* Overwrite pinctrl-0 from sdm845.dtsi */ + pinctrl-0 = <&qup_i2c3_default &i2c3_hid_active>; tsel: hid@15 { compatible = "hid-over-i2c"; @@ -327,9 +331,6 @@ hid-descr-addr = <0x1>; interrupts-extended = <&tlmm 37 IRQ_TYPE_LEVEL_HIGH>; - - pinctrl-names = "default"; - pinctrl-0 = <&i2c3_hid_active>; }; tsc2: hid@2c { @@ -338,11 +339,6 @@ hid-descr-addr = <0x20>; interrupts-extended = <&tlmm 37 IRQ_TYPE_LEVEL_HIGH>; - - pinctrl-names = "default"; - pinctrl-0 = <&i2c3_hid_active>; - - status = "disabled"; }; }; diff --git a/arch/arm64/boot/dts/rockchip/px30.dtsi b/arch/arm64/boot/dts/rockchip/px30.dtsi index 2695ea8cda14..64193292d26c 100644 --- a/arch/arm64/boot/dts/rockchip/px30.dtsi +++ b/arch/arm64/boot/dts/rockchip/px30.dtsi @@ -1097,7 +1097,7 @@ vopl_mmu: iommu@ff470f00 { compatible = "rockchip,iommu"; reg = <0x0 0xff470f00 0x0 0x100>; - interrupts = <GIC_SPI 79 IRQ_TYPE_LEVEL_HIGH>; + interrupts = <GIC_SPI 78 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "vopl_mmu"; clocks = <&cru ACLK_VOPL>, <&cru HCLK_VOPL>; clock-names = "aclk", "iface"; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts index 2ee07d15a6e3..1eecad724f04 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts @@ -114,6 +114,10 @@ cpu-supply = <&vdd_arm>; }; +&display_subsystem { + status = "disabled"; +}; + &gmac2io { assigned-clocks = <&cru SCLK_MAC2IO>, <&cru SCLK_MAC2IO_EXT>; assigned-clock-parents = <&gmac_clk>, <&gmac_clk>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts index 06d48338c836..219b7507a10f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts @@ -790,7 +790,6 @@ &pcie0 { bus-scan-delay-ms = <1000>; ep-gpios = <&gpio2 RK_PD4 GPIO_ACTIVE_HIGH>; - max-link-speed = <2>; num-lanes = <4>; pinctrl-names = "default"; pinctrl-0 = <&pcie_clkreqn_cpm>; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index f5dee5f447bb..2551b238b97c 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -234,6 +234,7 @@ reg = <0x0 0xf8000000 0x0 0x2000000>, <0x0 0xfd000000 0x0 0x1000000>; reg-names = "axi-base", "apb-base"; + device_type = "pci"; #address-cells = <3>; #size-cells = <2>; #interrupt-cells = <1>; @@ -252,7 +253,6 @@ <0 0 0 2 &pcie0_intc 1>, <0 0 0 3 &pcie0_intc 2>, <0 0 0 4 &pcie0_intc 3>; - linux,pci-domain = <0>; max-link-speed = <1>; msi-map = <0x0 &its 0x0 0x1000>; phys = <&pcie_phy 0>, <&pcie_phy 1>, @@ -1278,7 +1278,6 @@ compatible = "rockchip,rk3399-vdec"; reg = <0x0 0xff660000 0x0 0x400>; interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH 0>; - interrupt-names = "vdpu"; clocks = <&cru ACLK_VDU>, <&cru HCLK_VDU>, <&cru SCLK_VDU_CA>, <&cru SCLK_VDU_CORE>; clock-names = "axi", "ahb", "cabac", "core"; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index 838301650a79..01aa3eee90e8 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -991,8 +991,6 @@ CONFIG_ARCH_TEGRA_210_SOC=y CONFIG_ARCH_TEGRA_186_SOC=y CONFIG_ARCH_TEGRA_194_SOC=y CONFIG_ARCH_TEGRA_234_SOC=y -CONFIG_ARCH_K3_AM6_SOC=y -CONFIG_ARCH_K3_J721E_SOC=y CONFIG_TI_SCI_PM_DOMAINS=y CONFIG_EXTCON_PTN5150=m CONFIG_EXTCON_USB_GPIO=y @@ -1078,7 +1076,7 @@ CONFIG_INTERCONNECT=y CONFIG_INTERCONNECT_QCOM=y CONFIG_INTERCONNECT_QCOM_MSM8916=m CONFIG_INTERCONNECT_QCOM_OSM_L3=m -CONFIG_INTERCONNECT_QCOM_SDM845=m +CONFIG_INTERCONNECT_QCOM_SDM845=y CONFIG_INTERCONNECT_QCOM_SM8150=m CONFIG_INTERCONNECT_QCOM_SM8250=m CONFIG_EXT2_FS=y diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h index 015ddffaf6ca..b56a4b2bc248 100644 --- a/arch/arm64/include/asm/atomic.h +++ b/arch/arm64/include/asm/atomic.h @@ -17,7 +17,7 @@ #include <asm/lse.h> #define ATOMIC_OP(op) \ -static inline void arch_##op(int i, atomic_t *v) \ +static __always_inline void arch_##op(int i, atomic_t *v) \ { \ __lse_ll_sc_body(op, i, v); \ } @@ -32,7 +32,7 @@ ATOMIC_OP(atomic_sub) #undef ATOMIC_OP #define ATOMIC_FETCH_OP(name, op) \ -static inline int arch_##op##name(int i, atomic_t *v) \ +static __always_inline int arch_##op##name(int i, atomic_t *v) \ { \ return __lse_ll_sc_body(op##name, i, v); \ } @@ -56,7 +56,7 @@ ATOMIC_FETCH_OPS(atomic_sub_return) #undef ATOMIC_FETCH_OPS #define ATOMIC64_OP(op) \ -static inline void arch_##op(long i, atomic64_t *v) \ +static __always_inline void arch_##op(long i, atomic64_t *v) \ { \ __lse_ll_sc_body(op, i, v); \ } @@ -71,7 +71,7 @@ ATOMIC64_OP(atomic64_sub) #undef ATOMIC64_OP #define ATOMIC64_FETCH_OP(name, op) \ -static inline long arch_##op##name(long i, atomic64_t *v) \ +static __always_inline long arch_##op##name(long i, atomic64_t *v) \ { \ return __lse_ll_sc_body(op##name, i, v); \ } @@ -94,7 +94,7 @@ ATOMIC64_FETCH_OPS(atomic64_sub_return) #undef ATOMIC64_FETCH_OP #undef ATOMIC64_FETCH_OPS -static inline long arch_atomic64_dec_if_positive(atomic64_t *v) +static __always_inline long arch_atomic64_dec_if_positive(atomic64_t *v) { return __lse_ll_sc_body(atomic64_dec_if_positive, v); } diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 11beda85ee7e..8fcfab0c2567 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -17,6 +17,7 @@ #include <linux/jump_label.h> #include <linux/kvm_types.h> #include <linux/percpu.h> +#include <linux/psci.h> #include <asm/arch_gicv3.h> #include <asm/barrier.h> #include <asm/cpufeature.h> @@ -240,6 +241,28 @@ struct kvm_host_data { struct kvm_pmu_events pmu_events; }; +struct kvm_host_psci_config { + /* PSCI version used by host. */ + u32 version; + + /* Function IDs used by host if version is v0.1. */ + struct psci_0_1_function_ids function_ids_0_1; + + bool psci_0_1_cpu_suspend_implemented; + bool psci_0_1_cpu_on_implemented; + bool psci_0_1_cpu_off_implemented; + bool psci_0_1_migrate_implemented; +}; + +extern struct kvm_host_psci_config kvm_nvhe_sym(kvm_host_psci_config); +#define kvm_host_psci_config CHOOSE_NVHE_SYM(kvm_host_psci_config) + +extern s64 kvm_nvhe_sym(hyp_physvirt_offset); +#define hyp_physvirt_offset CHOOSE_NVHE_SYM(hyp_physvirt_offset) + +extern u64 kvm_nvhe_sym(hyp_cpu_logical_map)[NR_CPUS]; +#define hyp_cpu_logical_map CHOOSE_NVHE_SYM(hyp_cpu_logical_map) + struct vcpu_reset_state { unsigned long pc; unsigned long r0; diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 18fce223b67b..ff4732785c32 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -247,11 +247,13 @@ static inline const void *__tag_set(const void *addr, u8 tag) /* - * The linear kernel range starts at the bottom of the virtual address space. + * Check whether an arbitrary address is within the linear map, which + * lives in the [PAGE_OFFSET, PAGE_END) interval at the bottom of the + * kernel's TTBR1 address range. */ -#define __is_lm_address(addr) (((u64)(addr) & ~PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET)) +#define __is_lm_address(addr) (((u64)(addr) - PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET)) -#define __lm_to_phys(addr) (((addr) & ~PAGE_OFFSET) + PHYS_OFFSET) +#define __lm_to_phys(addr) (((addr) - PAGE_OFFSET) + PHYS_OFFSET) #define __kimg_to_phys(addr) ((addr) - kimage_voffset) #define __virt_to_phys_nodebug(x) ({ \ @@ -330,7 +332,7 @@ static inline void *phys_to_virt(phys_addr_t x) #endif /* !CONFIG_SPARSEMEM_VMEMMAP || CONFIG_DEBUG_VIRTUAL */ #define virt_addr_valid(addr) ({ \ - __typeof__(addr) __addr = addr; \ + __typeof__(addr) __addr = __tag_reset(addr); \ __is_lm_address(__addr) && pfn_valid(virt_to_pfn(__addr)); \ }) diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h index 6f986e09a781..f0fe0cc6abe0 100644 --- a/arch/arm64/include/asm/uaccess.h +++ b/arch/arm64/include/asm/uaccess.h @@ -176,10 +176,21 @@ static inline void __uaccess_enable_hw_pan(void) * The Tag check override (TCO) bit disables temporarily the tag checking * preventing the issue. */ -static inline void uaccess_disable_privileged(void) +static inline void __uaccess_disable_tco(void) { asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(0), ARM64_MTE, CONFIG_KASAN_HW_TAGS)); +} + +static inline void __uaccess_enable_tco(void) +{ + asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(1), + ARM64_MTE, CONFIG_KASAN_HW_TAGS)); +} + +static inline void uaccess_disable_privileged(void) +{ + __uaccess_disable_tco(); if (uaccess_ttbr0_disable()) return; @@ -189,8 +200,7 @@ static inline void uaccess_disable_privileged(void) static inline void uaccess_enable_privileged(void) { - asm volatile(ALTERNATIVE("nop", SET_PSTATE_TCO(1), - ARM64_MTE, CONFIG_KASAN_HW_TAGS)); + __uaccess_enable_tco(); if (uaccess_ttbr0_enable()) return; diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index f42fd9e33981..301784463587 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -75,7 +75,7 @@ int main(void) DEFINE(S_SDEI_TTBR1, offsetof(struct pt_regs, sdei_ttbr1)); DEFINE(S_PMR_SAVE, offsetof(struct pt_regs, pmr_save)); DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe)); - DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs)); + DEFINE(PT_REGS_SIZE, sizeof(struct pt_regs)); BLANK(); #ifdef CONFIG_COMPAT DEFINE(COMPAT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0)); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 7ffb5f1d8b68..3e6331b64932 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1701,16 +1701,12 @@ static void bti_enable(const struct arm64_cpu_capabilities *__unused) #ifdef CONFIG_ARM64_MTE static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap) { - static bool cleared_zero_page = false; - /* * Clear the tags in the zero page. This needs to be done via the * linear map which has the Tagged attribute. */ - if (!cleared_zero_page) { - cleared_zero_page = true; + if (!test_and_set_bit(PG_mte_tagged, &ZERO_PAGE(0)->flags)) mte_clear_page_tags(lm_alias(empty_zero_page)); - } kasan_init_hw_tags_cpu(); } @@ -2568,7 +2564,7 @@ static void verify_hyp_capabilities(void) int parange, ipa_max; unsigned int safe_vmid_bits, vmid_bits; - if (!IS_ENABLED(CONFIG_KVM) || !IS_ENABLED(CONFIG_KVM_ARM_HOST)) + if (!IS_ENABLED(CONFIG_KVM)) return; safe_mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index a338f40e64d3..b3e4f9a088b1 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -35,7 +35,7 @@ */ .macro ftrace_regs_entry, allregs=0 /* Make room for pt_regs, plus a callee frame */ - sub sp, sp, #(S_FRAME_SIZE + 16) + sub sp, sp, #(PT_REGS_SIZE + 16) /* Save function arguments (and x9 for simplicity) */ stp x0, x1, [sp, #S_X0] @@ -61,15 +61,15 @@ .endif /* Save the callsite's SP and LR */ - add x10, sp, #(S_FRAME_SIZE + 16) + add x10, sp, #(PT_REGS_SIZE + 16) stp x9, x10, [sp, #S_LR] /* Save the PC after the ftrace callsite */ str x30, [sp, #S_PC] /* Create a frame record for the callsite above pt_regs */ - stp x29, x9, [sp, #S_FRAME_SIZE] - add x29, sp, #S_FRAME_SIZE + stp x29, x9, [sp, #PT_REGS_SIZE] + add x29, sp, #PT_REGS_SIZE /* Create our frame record within pt_regs. */ stp x29, x30, [sp, #S_STACKFRAME] @@ -120,7 +120,7 @@ ftrace_common_return: ldr x9, [sp, #S_PC] /* Restore the callsite's SP */ - add sp, sp, #S_FRAME_SIZE + 16 + add sp, sp, #PT_REGS_SIZE + 16 ret x9 SYM_CODE_END(ftrace_common) @@ -130,7 +130,7 @@ SYM_CODE_START(ftrace_graph_caller) ldr x0, [sp, #S_PC] sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn) add x1, sp, #S_LR // parent_ip (callsite's LR) - ldr x2, [sp, #S_FRAME_SIZE] // parent fp (callsite's FP) + ldr x2, [sp, #PT_REGS_SIZE] // parent fp (callsite's FP) bl prepare_ftrace_return b ftrace_common_return SYM_CODE_END(ftrace_graph_caller) diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 2a93fa5f4e49..c9bae73f2621 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -75,7 +75,7 @@ alternative_else_nop_endif .endif #endif - sub sp, sp, #S_FRAME_SIZE + sub sp, sp, #PT_REGS_SIZE #ifdef CONFIG_VMAP_STACK /* * Test whether the SP has overflowed, without corrupting a GPR. @@ -96,7 +96,7 @@ alternative_else_nop_endif * userspace, and can clobber EL0 registers to free up GPRs. */ - /* Stash the original SP (minus S_FRAME_SIZE) in tpidr_el0. */ + /* Stash the original SP (minus PT_REGS_SIZE) in tpidr_el0. */ msr tpidr_el0, x0 /* Recover the original x0 value and stash it in tpidrro_el0 */ @@ -182,7 +182,6 @@ alternative_else_nop_endif mrs_s \tmp2, SYS_GCR_EL1 bfi \tmp2, \tmp, #0, #16 msr_s SYS_GCR_EL1, \tmp2 - isb #endif .endm @@ -194,6 +193,7 @@ alternative_else_nop_endif ldr_l \tmp, gcr_kernel_excl mte_set_gcr \tmp, \tmp2 + isb 1: #endif .endm @@ -253,7 +253,7 @@ alternative_else_nop_endif scs_load tsk, x20 .else - add x21, sp, #S_FRAME_SIZE + add x21, sp, #PT_REGS_SIZE get_current_task tsk .endif /* \el == 0 */ mrs x22, elr_el1 @@ -377,7 +377,7 @@ alternative_else_nop_endif ldp x26, x27, [sp, #16 * 13] ldp x28, x29, [sp, #16 * 14] ldr lr, [sp, #S_LR] - add sp, sp, #S_FRAME_SIZE // restore sp + add sp, sp, #PT_REGS_SIZE // restore sp .if \el == 0 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0 @@ -580,12 +580,12 @@ __bad_stack: /* * Store the original GPRs to the new stack. The orginal SP (minus - * S_FRAME_SIZE) was stashed in tpidr_el0 by kernel_ventry. + * PT_REGS_SIZE) was stashed in tpidr_el0 by kernel_ventry. */ - sub sp, sp, #S_FRAME_SIZE + sub sp, sp, #PT_REGS_SIZE kernel_entry 1 mrs x0, tpidr_el0 - add x0, x0, #S_FRAME_SIZE + add x0, x0, #PT_REGS_SIZE str x0, [sp, #S_SP] /* Stash the regs for handle_bad_stack */ diff --git a/arch/arm64/kernel/mte.c b/arch/arm64/kernel/mte.c index dc9ada64feed..80b62fe49dcf 100644 --- a/arch/arm64/kernel/mte.c +++ b/arch/arm64/kernel/mte.c @@ -329,11 +329,12 @@ static int __access_remote_tags(struct mm_struct *mm, unsigned long addr, * would cause the existing tags to be cleared if the page * was never mapped with PROT_MTE. */ - if (!test_bit(PG_mte_tagged, &page->flags)) { + if (!(vma->vm_flags & VM_MTE)) { ret = -EOPNOTSUPP; put_page(page); break; } + WARN_ON_ONCE(!test_bit(PG_mte_tagged, &page->flags)); /* limit access to the end of the page */ offset = offset_in_page(addr); diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 38bb07eff872..3605f77ad4df 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -23,8 +23,6 @@ #include <linux/platform_device.h> #include <linux/sched_clock.h> #include <linux/smp.h> -#include <linux/nmi.h> -#include <linux/cpufreq.h> /* ARMv8 Cortex-A53 specific event types. */ #define ARMV8_A53_PERFCTR_PREF_LINEFILL 0xC2 @@ -1250,21 +1248,10 @@ static struct platform_driver armv8_pmu_driver = { static int __init armv8_pmu_driver_init(void) { - int ret; - if (acpi_disabled) - ret = platform_driver_register(&armv8_pmu_driver); + return platform_driver_register(&armv8_pmu_driver); else - ret = arm_pmu_acpi_probe(armv8_pmuv3_init); - - /* - * Try to re-initialize lockup detector after PMU init in - * case PMU events are triggered via NMIs. - */ - if (ret == 0 && arm_pmu_irq_is_nmi()) - lockup_detector_init(); - - return ret; + return arm_pmu_acpi_probe(armv8_pmuv3_init); } device_initcall(armv8_pmu_driver_init) @@ -1322,27 +1309,3 @@ void arch_perf_update_userpage(struct perf_event *event, userpg->cap_user_time_zero = 1; userpg->cap_user_time_short = 1; } - -#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF -/* - * Safe maximum CPU frequency in case a particular platform doesn't implement - * cpufreq driver. Although, architecture doesn't put any restrictions on - * maximum frequency but 5 GHz seems to be safe maximum given the available - * Arm CPUs in the market which are clocked much less than 5 GHz. On the other - * hand, we can't make it much higher as it would lead to a large hard-lockup - * detection timeout on parts which are running slower (eg. 1GHz on - * Developerbox) and doesn't possess a cpufreq driver. - */ -#define SAFE_MAX_CPU_FREQ 5000000000UL // 5 GHz -u64 hw_nmi_get_sample_period(int watchdog_thresh) -{ - unsigned int cpu = smp_processor_id(); - unsigned long max_cpu_freq; - - max_cpu_freq = cpufreq_get_hw_max_freq(cpu) * 1000UL; - if (!max_cpu_freq) - max_cpu_freq = SAFE_MAX_CPU_FREQ; - - return (u64)max_cpu_freq * watchdog_thresh; -} -#endif diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 89c64ada8732..66aac2881ba8 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -352,8 +352,8 @@ kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned int esr) unsigned long addr = instruction_pointer(regs); struct kprobe *cur = kprobe_running(); - if (cur && (kcb->kprobe_status == KPROBE_HIT_SS) - && ((unsigned long)&cur->ainsn.api.insn[1] == addr)) { + if (cur && (kcb->kprobe_status & (KPROBE_HIT_SS | KPROBE_REENTER)) && + ((unsigned long)&cur->ainsn.api.insn[1] == addr)) { kprobes_restore_local_irqflag(kcb, regs); post_kprobe_handler(cur, kcb, regs); diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S index 890ca72c5a51..288a84e253cc 100644 --- a/arch/arm64/kernel/probes/kprobes_trampoline.S +++ b/arch/arm64/kernel/probes/kprobes_trampoline.S @@ -25,7 +25,7 @@ stp x24, x25, [sp, #S_X24] stp x26, x27, [sp, #S_X26] stp x28, x29, [sp, #S_X28] - add x0, sp, #S_FRAME_SIZE + add x0, sp, #PT_REGS_SIZE stp lr, x0, [sp, #S_LR] /* * Construct a useful saved PSTATE @@ -62,7 +62,7 @@ .endm SYM_CODE_START(kretprobe_trampoline) - sub sp, sp, #S_FRAME_SIZE + sub sp, sp, #PT_REGS_SIZE save_all_base_regs @@ -76,7 +76,7 @@ SYM_CODE_START(kretprobe_trampoline) restore_all_base_regs - add sp, sp, #S_FRAME_SIZE + add sp, sp, #PT_REGS_SIZE ret SYM_CODE_END(kretprobe_trampoline) diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index f71d6ce4673f..6237486ff6bb 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -914,13 +914,6 @@ static void do_signal(struct pt_regs *regs) asmlinkage void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) { - /* - * The assembly code enters us with IRQs off, but it hasn't - * informed the tracing code of that for efficiency reasons. - * Update the trace code with the current status. - */ - trace_hardirqs_off(); - do { if (thread_flags & _TIF_NEED_RESCHED) { /* Unmask Debug and SError for the next task */ diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 6bc3a3698c3d..ad00f99ee9b0 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -434,7 +434,7 @@ static void __init hyp_mode_check(void) "CPU: CPUs started in inconsistent modes"); else pr_info("CPU: All CPU(s) started at EL1\n"); - if (IS_ENABLED(CONFIG_KVM)) + if (IS_ENABLED(CONFIG_KVM) && !is_kernel_in_hyp_mode()) kvm_compute_layout(); } @@ -807,7 +807,6 @@ int arch_show_interrupts(struct seq_file *p, int prec) unsigned int cpu, i; for (i = 0; i < NR_IPI; i++) { - unsigned int irq = irq_desc_get_irq(ipi_desc[i]); seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i, prec >= 4 ? " " : ""); for_each_online_cpu(cpu) diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index f61e9d8cc55a..c2877c332f2d 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -9,6 +9,7 @@ #include <asm/daifflags.h> #include <asm/debug-monitors.h> +#include <asm/exception.h> #include <asm/fpsimd.h> #include <asm/syscall.h> #include <asm/thread_info.h> @@ -165,15 +166,8 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr, if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) { local_daif_mask(); flags = current_thread_info()->flags; - if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) { - /* - * We're off to userspace, where interrupts are - * always enabled after we restore the flags from - * the SPSR. - */ - trace_hardirqs_on(); + if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) return; - } local_daif_restore(DAIF_PROCCTX); } diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 08156be75569..6895ce777e7f 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -42,7 +42,6 @@ #include <asm/smp.h> #include <asm/stack_pointer.h> #include <asm/stacktrace.h> -#include <asm/exception.h> #include <asm/system_misc.h> #include <asm/sysreg.h> diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index a8f8e409e2bf..cd9c3fa25902 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -24,8 +24,7 @@ btildflags-$(CONFIG_ARM64_BTI_KERNEL) += -z force-bti # routines, as x86 does (see 6f121e548f83 ("x86, vdso: Reimplement vdso.so # preparation in build-time C")). ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv \ - -Bsymbolic $(call ld-option, --no-eh-frame-hdr) --build-id=sha1 -n \ - $(btildflags-y) -T + -Bsymbolic --build-id=sha1 -n $(btildflags-y) -T ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18 ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S index d808ad31e01f..61dbb4c838ef 100644 --- a/arch/arm64/kernel/vdso/vdso.lds.S +++ b/arch/arm64/kernel/vdso/vdso.lds.S @@ -40,9 +40,6 @@ SECTIONS PROVIDE (_etext = .); PROVIDE (etext = .); - .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr - .eh_frame : { KEEP (*(.eh_frame)) } :text - .dynamic : { *(.dynamic) } :text :dynamic .rodata : { *(.rodata*) } :text @@ -54,6 +51,7 @@ SECTIONS *(.note.GNU-stack) *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) + *(.eh_frame .eh_frame_hdr) } } @@ -66,7 +64,6 @@ PHDRS text PT_LOAD FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */ dynamic PT_DYNAMIC FLAGS(4); /* PF_R */ note PT_NOTE FLAGS(4); /* PF_R */ - eh_frame_hdr PT_GNU_EH_FRAME; } /* diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 043756db8f6e..3964acf5451e 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -49,14 +49,6 @@ if KVM source "virt/kvm/Kconfig" -config KVM_ARM_PMU - bool "Virtual Performance Monitoring Unit (PMU) support" - depends on HW_PERF_EVENTS - default y - help - Adds support for a virtual Performance Monitoring Unit (PMU) in - virtual machines. - endif # KVM endif # VIRTUALIZATION diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 60fd181df624..13b017284bf9 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -24,4 +24,4 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \ vgic/vgic-mmio-v3.o vgic/vgic-kvm-device.o \ vgic/vgic-its.o vgic/vgic-debug.o -kvm-$(CONFIG_KVM_ARM_PMU) += pmu-emul.o +kvm-$(CONFIG_HW_PERF_EVENTS) += pmu-emul.o diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 32ba6fbc3814..74e0699661e9 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -1129,9 +1129,10 @@ int kvm_timer_enable(struct kvm_vcpu *vcpu) if (!irqchip_in_kernel(vcpu->kvm)) goto no_vgic; - if (!vgic_initialized(vcpu->kvm)) - return -ENODEV; - + /* + * At this stage, we have the guarantee that the vgic is both + * available and initialized. + */ if (!timer_irqs_are_valid(vcpu)) { kvm_debug("incorrectly configured timer irqs\n"); return -EINVAL; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 6e637d2b4cfb..fe60d25c000e 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -65,10 +65,6 @@ static bool vgic_present; static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled); DEFINE_STATIC_KEY_FALSE(userspace_irqchip_in_use); -extern u64 kvm_nvhe_sym(__cpu_logical_map)[NR_CPUS]; -extern u32 kvm_nvhe_sym(kvm_host_psci_version); -extern struct psci_0_1_function_ids kvm_nvhe_sym(kvm_host_psci_0_1_function_ids); - int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) { return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; @@ -584,11 +580,9 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) * Map the VGIC hardware resources before running a vcpu the * first time on this VM. */ - if (unlikely(!vgic_ready(kvm))) { - ret = kvm_vgic_map_resources(kvm); - if (ret) - return ret; - } + ret = kvm_vgic_map_resources(kvm); + if (ret) + return ret; } else { /* * Tell the rest of the code that there are userspace irqchip @@ -1402,8 +1396,9 @@ static void cpu_init_hyp_mode(void) * Calculate the raw per-cpu offset without a translation from the * kernel's mapping to the linear mapping, and store it in tpidr_el2 * so that we can use adr_l to access per-cpu variables in EL2. + * Also drop the KASAN tag which gets in the way... */ - params->tpidr_el2 = (unsigned long)this_cpu_ptr_nvhe_sym(__per_cpu_start) - + params->tpidr_el2 = (unsigned long)kasan_reset_tag(this_cpu_ptr_nvhe_sym(__per_cpu_start)) - (unsigned long)kvm_ksym_ref(CHOOSE_NVHE_SYM(__per_cpu_start)); params->mair_el2 = read_sysreg(mair_el1); @@ -1574,12 +1569,12 @@ static struct notifier_block hyp_init_cpu_pm_nb = { .notifier_call = hyp_init_cpu_pm_notifier, }; -static void __init hyp_cpu_pm_init(void) +static void hyp_cpu_pm_init(void) { if (!is_protected_kvm_enabled()) cpu_pm_register_notifier(&hyp_init_cpu_pm_nb); } -static void __init hyp_cpu_pm_exit(void) +static void hyp_cpu_pm_exit(void) { if (!is_protected_kvm_enabled()) cpu_pm_unregister_notifier(&hyp_init_cpu_pm_nb); @@ -1604,9 +1599,12 @@ static void init_cpu_logical_map(void) * allow any other CPUs from the `possible` set to boot. */ for_each_online_cpu(cpu) - kvm_nvhe_sym(__cpu_logical_map)[cpu] = cpu_logical_map(cpu); + hyp_cpu_logical_map[cpu] = cpu_logical_map(cpu); } +#define init_psci_0_1_impl_state(config, what) \ + config.psci_0_1_ ## what ## _implemented = psci_ops.what + static bool init_psci_relay(void) { /* @@ -1618,8 +1616,15 @@ static bool init_psci_relay(void) return false; } - kvm_nvhe_sym(kvm_host_psci_version) = psci_ops.get_version(); - kvm_nvhe_sym(kvm_host_psci_0_1_function_ids) = get_psci_0_1_function_ids(); + kvm_host_psci_config.version = psci_ops.get_version(); + + if (kvm_host_psci_config.version == PSCI_VERSION(0, 1)) { + kvm_host_psci_config.function_ids_0_1 = get_psci_0_1_function_ids(); + init_psci_0_1_impl_state(kvm_host_psci_config, cpu_suspend); + init_psci_0_1_impl_state(kvm_host_psci_config, cpu_on); + init_psci_0_1_impl_state(kvm_host_psci_config, cpu_off); + init_psci_0_1_impl_state(kvm_host_psci_config, migrate); + } return true; } diff --git a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h index b1f60923a8fe..61716359035d 100644 --- a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h +++ b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h @@ -59,4 +59,13 @@ static inline void __adjust_pc(struct kvm_vcpu *vcpu) } } +/* + * Skip an instruction while host sysregs are live. + * Assumes host is always 64-bit. + */ +static inline void kvm_skip_host_instr(void) +{ + write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR); +} + #endif diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S index 31b060a44045..b17bf19217f1 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S +++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S @@ -47,6 +47,8 @@ __invalid: b . /* + * Only uses x0..x3 so as to not clobber callee-saved SMCCC registers. + * * x0: SMCCC function ID * x1: struct kvm_nvhe_init_params PA */ @@ -70,9 +72,9 @@ __do_hyp_init: eret 1: mov x0, x1 - mov x4, lr - bl ___kvm_hyp_init - mov lr, x4 + mov x3, lr + bl ___kvm_hyp_init // Clobbers x0..x2 + mov lr, x3 /* Hello, World! */ mov x0, #SMCCC_RET_SUCCESS @@ -82,8 +84,8 @@ SYM_CODE_END(__kvm_hyp_init) /* * Initialize the hypervisor in EL2. * - * Only uses x0..x3 so as to not clobber callee-saved SMCCC registers - * and leave x4 for the caller. + * Only uses x0..x2 so as to not clobber callee-saved SMCCC registers + * and leave x3 for the caller. * * x0: struct kvm_nvhe_init_params PA */ @@ -112,9 +114,9 @@ alternative_else_nop_endif /* * Set the PS bits in TCR_EL2. */ - ldr x1, [x0, #NVHE_INIT_TCR_EL2] - tcr_compute_pa_size x1, #TCR_EL2_PS_SHIFT, x2, x3 - msr tcr_el2, x1 + ldr x0, [x0, #NVHE_INIT_TCR_EL2] + tcr_compute_pa_size x0, #TCR_EL2_PS_SHIFT, x1, x2 + msr tcr_el2, x0 isb @@ -193,7 +195,7 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu) /* Enable MMU, set vectors and stack. */ mov x0, x28 - bl ___kvm_hyp_init // Clobbers x0..x3 + bl ___kvm_hyp_init // Clobbers x0..x2 /* Leave idmap. */ mov x0, x29 diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index bde658d51404..a906f9e2ff34 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -157,11 +157,6 @@ static void default_host_smc_handler(struct kvm_cpu_context *host_ctxt) __kvm_hyp_host_forward_smc(host_ctxt); } -static void skip_host_instruction(void) -{ - write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR); -} - static void handle_host_smc(struct kvm_cpu_context *host_ctxt) { bool handled; @@ -170,11 +165,8 @@ static void handle_host_smc(struct kvm_cpu_context *host_ctxt) if (!handled) default_host_smc_handler(host_ctxt); - /* - * Unlike HVC, the return address of an SMC is the instruction's PC. - * Move the return address past the instruction. - */ - skip_host_instruction(); + /* SMC was trapped, move ELR past the current PC. */ + kvm_skip_host_instr(); } void handle_trap(struct kvm_cpu_context *host_ctxt) diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-smp.c b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c index cbab0c6246e2..2997aa156d8e 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-smp.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c @@ -14,14 +14,14 @@ * Other CPUs should not be allowed to boot because their features were * not checked against the finalized system capabilities. */ -u64 __ro_after_init __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID }; +u64 __ro_after_init hyp_cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID }; u64 cpu_logical_map(unsigned int cpu) { - if (cpu >= ARRAY_SIZE(__cpu_logical_map)) + if (cpu >= ARRAY_SIZE(hyp_cpu_logical_map)) hyp_panic(); - return __cpu_logical_map[cpu]; + return hyp_cpu_logical_map[cpu]; } unsigned long __hyp_per_cpu_offset(unsigned int cpu) diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c index 08dc9de69314..8e7128cb7667 100644 --- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c +++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c @@ -7,11 +7,8 @@ #include <asm/kvm_asm.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> -#include <kvm/arm_hypercalls.h> #include <linux/arm-smccc.h> #include <linux/kvm_host.h> -#include <linux/psci.h> -#include <kvm/arm_psci.h> #include <uapi/linux/psci.h> #include <nvhe/trap_handler.h> @@ -22,9 +19,8 @@ void kvm_hyp_cpu_resume(unsigned long r0); void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt); /* Config options set by the host. */ -__ro_after_init u32 kvm_host_psci_version; -__ro_after_init struct psci_0_1_function_ids kvm_host_psci_0_1_function_ids; -__ro_after_init s64 hyp_physvirt_offset; +struct kvm_host_psci_config __ro_after_init kvm_host_psci_config; +s64 __ro_after_init hyp_physvirt_offset; #define __hyp_pa(x) ((phys_addr_t)((x)) + hyp_physvirt_offset) @@ -47,19 +43,16 @@ struct psci_boot_args { static DEFINE_PER_CPU(struct psci_boot_args, cpu_on_args) = PSCI_BOOT_ARGS_INIT; static DEFINE_PER_CPU(struct psci_boot_args, suspend_args) = PSCI_BOOT_ARGS_INIT; -static u64 get_psci_func_id(struct kvm_cpu_context *host_ctxt) -{ - DECLARE_REG(u64, func_id, host_ctxt, 0); - - return func_id; -} +#define is_psci_0_1(what, func_id) \ + (kvm_host_psci_config.psci_0_1_ ## what ## _implemented && \ + (func_id) == kvm_host_psci_config.function_ids_0_1.what) static bool is_psci_0_1_call(u64 func_id) { - return (func_id == kvm_host_psci_0_1_function_ids.cpu_suspend) || - (func_id == kvm_host_psci_0_1_function_ids.cpu_on) || - (func_id == kvm_host_psci_0_1_function_ids.cpu_off) || - (func_id == kvm_host_psci_0_1_function_ids.migrate); + return (is_psci_0_1(cpu_suspend, func_id) || + is_psci_0_1(cpu_on, func_id) || + is_psci_0_1(cpu_off, func_id) || + is_psci_0_1(migrate, func_id)); } static bool is_psci_0_2_call(u64 func_id) @@ -69,16 +62,6 @@ static bool is_psci_0_2_call(u64 func_id) (PSCI_0_2_FN64(0) <= func_id && func_id <= PSCI_0_2_FN64(31)); } -static bool is_psci_call(u64 func_id) -{ - switch (kvm_host_psci_version) { - case PSCI_VERSION(0, 1): - return is_psci_0_1_call(func_id); - default: - return is_psci_0_2_call(func_id); - } -} - static unsigned long psci_call(unsigned long fn, unsigned long arg0, unsigned long arg1, unsigned long arg2) { @@ -94,12 +77,6 @@ static unsigned long psci_forward(struct kvm_cpu_context *host_ctxt) cpu_reg(host_ctxt, 2), cpu_reg(host_ctxt, 3)); } -static __noreturn unsigned long psci_forward_noreturn(struct kvm_cpu_context *host_ctxt) -{ - psci_forward(host_ctxt); - hyp_panic(); /* unreachable */ -} - static unsigned int find_cpu_id(u64 mpidr) { unsigned int i; @@ -248,15 +225,14 @@ asmlinkage void __noreturn kvm_host_psci_cpu_entry(bool is_cpu_on) static unsigned long psci_0_1_handler(u64 func_id, struct kvm_cpu_context *host_ctxt) { - if ((func_id == kvm_host_psci_0_1_function_ids.cpu_off) || - (func_id == kvm_host_psci_0_1_function_ids.migrate)) + if (is_psci_0_1(cpu_off, func_id) || is_psci_0_1(migrate, func_id)) return psci_forward(host_ctxt); - else if (func_id == kvm_host_psci_0_1_function_ids.cpu_on) + if (is_psci_0_1(cpu_on, func_id)) return psci_cpu_on(func_id, host_ctxt); - else if (func_id == kvm_host_psci_0_1_function_ids.cpu_suspend) + if (is_psci_0_1(cpu_suspend, func_id)) return psci_cpu_suspend(func_id, host_ctxt); - else - return PSCI_RET_NOT_SUPPORTED; + + return PSCI_RET_NOT_SUPPORTED; } static unsigned long psci_0_2_handler(u64 func_id, struct kvm_cpu_context *host_ctxt) @@ -269,10 +245,13 @@ static unsigned long psci_0_2_handler(u64 func_id, struct kvm_cpu_context *host_ case PSCI_0_2_FN_MIGRATE_INFO_TYPE: case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU: return psci_forward(host_ctxt); + /* + * SYSTEM_OFF/RESET should not return according to the spec. + * Allow it so as to stay robust to broken firmware. + */ case PSCI_0_2_FN_SYSTEM_OFF: case PSCI_0_2_FN_SYSTEM_RESET: - psci_forward_noreturn(host_ctxt); - unreachable(); + return psci_forward(host_ctxt); case PSCI_0_2_FN64_CPU_SUSPEND: return psci_cpu_suspend(func_id, host_ctxt); case PSCI_0_2_FN64_CPU_ON: @@ -298,20 +277,23 @@ static unsigned long psci_1_0_handler(u64 func_id, struct kvm_cpu_context *host_ bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt) { - u64 func_id = get_psci_func_id(host_ctxt); + DECLARE_REG(u64, func_id, host_ctxt, 0); unsigned long ret; - if (!is_psci_call(func_id)) - return false; - - switch (kvm_host_psci_version) { + switch (kvm_host_psci_config.version) { case PSCI_VERSION(0, 1): + if (!is_psci_0_1_call(func_id)) + return false; ret = psci_0_1_handler(func_id, host_ctxt); break; case PSCI_VERSION(0, 2): + if (!is_psci_0_2_call(func_id)) + return false; ret = psci_0_2_handler(func_id, host_ctxt); break; default: + if (!is_psci_0_2_call(func_id)) + return false; ret = psci_1_0_handler(func_id, host_ctxt); break; } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 398f6df1bbe4..247422ac78a9 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -788,7 +788,7 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) { unsigned long *bmap = vcpu->kvm->arch.pmu_filter; u64 val, mask = 0; - int base, i; + int base, i, nr_events; if (!pmceid1) { val = read_sysreg(pmceid0_el0); @@ -801,13 +801,17 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1) if (!bmap) return val; + nr_events = kvm_pmu_event_mask(vcpu->kvm) + 1; + for (i = 0; i < 32; i += 8) { u64 byte; byte = bitmap_get_value8(bmap, base + i); mask |= byte << i; - byte = bitmap_get_value8(bmap, 0x4000 + base + i); - mask |= byte << (32 + i); + if (nr_events >= (0x4000 + base + 32)) { + byte = bitmap_get_value8(bmap, 0x4000 + base + i); + mask |= byte << (32 + i); + } } return val & mask; @@ -850,8 +854,6 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) return -EINVAL; } - kvm_pmu_vcpu_reset(vcpu); - return 0; } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 3313dedfa505..7c4f79532406 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -43,6 +43,10 @@ * 64bit interface. */ +#define reg_to_encoding(x) \ + sys_reg((u32)(x)->Op0, (u32)(x)->Op1, \ + (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2) + static bool read_from_write_only(struct kvm_vcpu *vcpu, struct sys_reg_params *params, const struct sys_reg_desc *r) @@ -273,8 +277,7 @@ static bool trap_loregion(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 val = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); - u32 sr = sys_reg((u32)r->Op0, (u32)r->Op1, - (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); + u32 sr = reg_to_encoding(r); if (!(val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT))) { kvm_inject_undefined(vcpu); @@ -590,10 +593,23 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) vcpu_write_sys_reg(vcpu, (1ULL << 31) | mpidr, MPIDR_EL1); } +static unsigned int pmu_visibility(const struct kvm_vcpu *vcpu, + const struct sys_reg_desc *r) +{ + if (kvm_vcpu_has_pmu(vcpu)) + return 0; + + return REG_HIDDEN; +} + static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { u64 pmcr, val; + /* No PMU available, PMCR_EL0 may UNDEF... */ + if (!kvm_arm_support_pmu_v3()) + return; + pmcr = read_sysreg(pmcr_el0); /* * Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) are reset to UNKNOWN @@ -609,9 +625,8 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags) { u64 reg = __vcpu_sys_reg(vcpu, PMUSERENR_EL0); - bool enabled = kvm_vcpu_has_pmu(vcpu); + bool enabled = (reg & flags) || vcpu_mode_priv(vcpu); - enabled &= (reg & flags) || vcpu_mode_priv(vcpu); if (!enabled) kvm_inject_undefined(vcpu); @@ -896,11 +911,6 @@ static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p, static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) { - if (!kvm_vcpu_has_pmu(vcpu)) { - kvm_inject_undefined(vcpu); - return false; - } - if (p->is_write) { if (!vcpu_mode_priv(vcpu)) { kvm_inject_undefined(vcpu); @@ -917,10 +927,6 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, return true; } -#define reg_to_encoding(x) \ - sys_reg((u32)(x)->Op0, (u32)(x)->Op1, \ - (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2); - /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */ #define DBG_BCR_BVR_WCR_WVR_EL1(n) \ { SYS_DESC(SYS_DBGBVRn_EL1(n)), \ @@ -932,15 +938,18 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, { SYS_DESC(SYS_DBGWCRn_EL1(n)), \ trap_wcr, reset_wcr, 0, 0, get_wcr, set_wcr } +#define PMU_SYS_REG(r) \ + SYS_DESC(r), .reset = reset_unknown, .visibility = pmu_visibility + /* Macro to expand the PMEVCNTRn_EL0 register */ #define PMU_PMEVCNTR_EL0(n) \ - { SYS_DESC(SYS_PMEVCNTRn_EL0(n)), \ - access_pmu_evcntr, reset_unknown, (PMEVCNTR0_EL0 + n), } + { PMU_SYS_REG(SYS_PMEVCNTRn_EL0(n)), \ + .access = access_pmu_evcntr, .reg = (PMEVCNTR0_EL0 + n), } /* Macro to expand the PMEVTYPERn_EL0 register */ #define PMU_PMEVTYPER_EL0(n) \ - { SYS_DESC(SYS_PMEVTYPERn_EL0(n)), \ - access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), } + { PMU_SYS_REG(SYS_PMEVTYPERn_EL0(n)), \ + .access = access_pmu_evtyper, .reg = (PMEVTYPER0_EL0 + n), } static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *r) @@ -1016,8 +1025,7 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu, static u64 read_id_reg(const struct kvm_vcpu *vcpu, struct sys_reg_desc const *r, bool raz) { - u32 id = sys_reg((u32)r->Op0, (u32)r->Op1, - (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); + u32 id = reg_to_encoding(r); u64 val = raz ? 0 : read_sanitised_ftr_reg(id); if (id == SYS_ID_AA64PFR0_EL1) { @@ -1058,8 +1066,7 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, static unsigned int id_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { - u32 id = sys_reg((u32)r->Op0, (u32)r->Op1, - (u32)r->CRn, (u32)r->CRm, (u32)r->Op2); + u32 id = reg_to_encoding(r); switch (id) { case SYS_ID_AA64ZFR0_EL1: @@ -1482,8 +1489,10 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 }, { SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 }, - { SYS_DESC(SYS_PMINTENSET_EL1), access_pminten, reset_unknown, PMINTENSET_EL1 }, - { SYS_DESC(SYS_PMINTENCLR_EL1), access_pminten, reset_unknown, PMINTENSET_EL1 }, + { PMU_SYS_REG(SYS_PMINTENSET_EL1), + .access = access_pminten, .reg = PMINTENSET_EL1 }, + { PMU_SYS_REG(SYS_PMINTENCLR_EL1), + .access = access_pminten, .reg = PMINTENSET_EL1 }, { SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 }, { SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 }, @@ -1522,23 +1531,36 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 }, { SYS_DESC(SYS_CTR_EL0), access_ctr }, - { SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, PMCR_EL0 }, - { SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 }, - { SYS_DESC(SYS_PMCNTENCLR_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 }, - { SYS_DESC(SYS_PMOVSCLR_EL0), access_pmovs, reset_unknown, PMOVSSET_EL0 }, - { SYS_DESC(SYS_PMSWINC_EL0), access_pmswinc, reset_unknown, PMSWINC_EL0 }, - { SYS_DESC(SYS_PMSELR_EL0), access_pmselr, reset_unknown, PMSELR_EL0 }, - { SYS_DESC(SYS_PMCEID0_EL0), access_pmceid }, - { SYS_DESC(SYS_PMCEID1_EL0), access_pmceid }, - { SYS_DESC(SYS_PMCCNTR_EL0), access_pmu_evcntr, reset_unknown, PMCCNTR_EL0 }, - { SYS_DESC(SYS_PMXEVTYPER_EL0), access_pmu_evtyper }, - { SYS_DESC(SYS_PMXEVCNTR_EL0), access_pmu_evcntr }, + { PMU_SYS_REG(SYS_PMCR_EL0), .access = access_pmcr, + .reset = reset_pmcr, .reg = PMCR_EL0 }, + { PMU_SYS_REG(SYS_PMCNTENSET_EL0), + .access = access_pmcnten, .reg = PMCNTENSET_EL0 }, + { PMU_SYS_REG(SYS_PMCNTENCLR_EL0), + .access = access_pmcnten, .reg = PMCNTENSET_EL0 }, + { PMU_SYS_REG(SYS_PMOVSCLR_EL0), + .access = access_pmovs, .reg = PMOVSSET_EL0 }, + { PMU_SYS_REG(SYS_PMSWINC_EL0), + .access = access_pmswinc, .reg = PMSWINC_EL0 }, + { PMU_SYS_REG(SYS_PMSELR_EL0), + .access = access_pmselr, .reg = PMSELR_EL0 }, + { PMU_SYS_REG(SYS_PMCEID0_EL0), + .access = access_pmceid, .reset = NULL }, + { PMU_SYS_REG(SYS_PMCEID1_EL0), + .access = access_pmceid, .reset = NULL }, + { PMU_SYS_REG(SYS_PMCCNTR_EL0), + .access = access_pmu_evcntr, .reg = PMCCNTR_EL0 }, + { PMU_SYS_REG(SYS_PMXEVTYPER_EL0), + .access = access_pmu_evtyper, .reset = NULL }, + { PMU_SYS_REG(SYS_PMXEVCNTR_EL0), + .access = access_pmu_evcntr, .reset = NULL }, /* * PMUSERENR_EL0 resets as unknown in 64bit mode while it resets as zero * in 32bit mode. Here we choose to reset it as zero for consistency. */ - { SYS_DESC(SYS_PMUSERENR_EL0), access_pmuserenr, reset_val, PMUSERENR_EL0, 0 }, - { SYS_DESC(SYS_PMOVSSET_EL0), access_pmovs, reset_unknown, PMOVSSET_EL0 }, + { PMU_SYS_REG(SYS_PMUSERENR_EL0), .access = access_pmuserenr, + .reset = reset_val, .reg = PMUSERENR_EL0, .val = 0 }, + { PMU_SYS_REG(SYS_PMOVSSET_EL0), + .access = access_pmovs, .reg = PMOVSSET_EL0 }, { SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 }, { SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 }, @@ -1690,7 +1712,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { * PMCCFILTR_EL0 resets as unknown in 64bit mode while it resets as zero * in 32bit mode. Here we choose to reset it as zero for consistency. */ - { SYS_DESC(SYS_PMCCFILTR_EL0), access_pmu_evtyper, reset_val, PMCCFILTR_EL0, 0 }, + { PMU_SYS_REG(SYS_PMCCFILTR_EL0), .access = access_pmu_evtyper, + .reset = reset_val, .reg = PMCCFILTR_EL0, .val = 0 }, { SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 }, { SYS_DESC(SYS_IFSR32_EL2), NULL, reset_unknown, IFSR32_EL2 }, diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c index d8cc51bd60bf..70fcd6a12fe1 100644 --- a/arch/arm64/kvm/va_layout.c +++ b/arch/arm64/kvm/va_layout.c @@ -34,17 +34,16 @@ static u64 __early_kern_hyp_va(u64 addr) } /* - * Store a hyp VA <-> PA offset into a hyp-owned variable. + * Store a hyp VA <-> PA offset into a EL2-owned variable. */ static void init_hyp_physvirt_offset(void) { - extern s64 kvm_nvhe_sym(hyp_physvirt_offset); u64 kern_va, hyp_va; /* Compute the offset from the hyp VA and PA of a random symbol. */ - kern_va = (u64)kvm_ksym_ref(__hyp_text_start); + kern_va = (u64)lm_alias(__hyp_text_start); hyp_va = __early_kern_hyp_va(kern_va); - CHOOSE_NVHE_SYM(hyp_physvirt_offset) = (s64)__pa(kern_va) - (s64)hyp_va; + hyp_physvirt_offset = (s64)__pa(kern_va) - (s64)hyp_va; } /* diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 32e32d67a127..052917deb149 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -419,7 +419,8 @@ int vgic_lazy_init(struct kvm *kvm) * Map the MMIO regions depending on the VGIC model exposed to the guest * called on the first VCPU run. * Also map the virtual CPU interface into the VM. - * v2/v3 derivatives call vgic_init if not already done. + * v2 calls vgic_init() if not already done. + * v3 and derivatives return an error if the VGIC is not initialized. * vgic_ready() returns true if this function has succeeded. * @kvm: kvm struct pointer */ @@ -428,7 +429,13 @@ int kvm_vgic_map_resources(struct kvm *kvm) struct vgic_dist *dist = &kvm->arch.vgic; int ret = 0; + if (likely(vgic_ready(kvm))) + return 0; + mutex_lock(&kvm->lock); + if (vgic_ready(kvm)) + goto out; + if (!irqchip_in_kernel(kvm)) goto out; @@ -439,6 +446,8 @@ int kvm_vgic_map_resources(struct kvm *kvm) if (ret) __kvm_vgic_destroy(kvm); + else + dist->ready = true; out: mutex_unlock(&kvm->lock); diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c index ebf53a4e1296..11934c2af2f4 100644 --- a/arch/arm64/kvm/vgic/vgic-v2.c +++ b/arch/arm64/kvm/vgic/vgic-v2.c @@ -306,20 +306,15 @@ int vgic_v2_map_resources(struct kvm *kvm) struct vgic_dist *dist = &kvm->arch.vgic; int ret = 0; - if (vgic_ready(kvm)) - goto out; - if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base) || IS_VGIC_ADDR_UNDEF(dist->vgic_cpu_base)) { kvm_err("Need to set vgic cpu and dist addresses first\n"); - ret = -ENXIO; - goto out; + return -ENXIO; } if (!vgic_v2_check_base(dist->vgic_dist_base, dist->vgic_cpu_base)) { kvm_err("VGIC CPU and dist frames overlap\n"); - ret = -EINVAL; - goto out; + return -EINVAL; } /* @@ -329,13 +324,13 @@ int vgic_v2_map_resources(struct kvm *kvm) ret = vgic_init(kvm); if (ret) { kvm_err("Unable to initialize VGIC dynamic data structures\n"); - goto out; + return ret; } ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V2); if (ret) { kvm_err("Unable to register VGIC MMIO regions\n"); - goto out; + return ret; } if (!static_branch_unlikely(&vgic_v2_cpuif_trap)) { @@ -344,14 +339,11 @@ int vgic_v2_map_resources(struct kvm *kvm) KVM_VGIC_V2_CPU_SIZE, true); if (ret) { kvm_err("Unable to remap VGIC CPU to VCPU\n"); - goto out; + return ret; } } - dist->ready = true; - -out: - return ret; + return 0; } DEFINE_STATIC_KEY_FALSE(vgic_v2_cpuif_trap); diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 9cdf39a94a63..52915b342351 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -500,29 +500,23 @@ int vgic_v3_map_resources(struct kvm *kvm) int ret = 0; int c; - if (vgic_ready(kvm)) - goto out; - kvm_for_each_vcpu(c, vcpu, kvm) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) { kvm_debug("vcpu %d redistributor base not set\n", c); - ret = -ENXIO; - goto out; + return -ENXIO; } } if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) { kvm_err("Need to set vgic distributor addresses first\n"); - ret = -ENXIO; - goto out; + return -ENXIO; } if (!vgic_v3_check_base(kvm)) { kvm_err("VGIC redist and dist frames overlap\n"); - ret = -EINVAL; - goto out; + return -EINVAL; } /* @@ -530,22 +524,19 @@ int vgic_v3_map_resources(struct kvm *kvm) * the VGIC before we need to use it. */ if (!vgic_initialized(kvm)) { - ret = -EBUSY; - goto out; + return -EBUSY; } ret = vgic_register_dist_iodev(kvm, dist->vgic_dist_base, VGIC_V3); if (ret) { kvm_err("Unable to register VGICv3 dist MMIO regions\n"); - goto out; + return ret; } if (kvm_vgic_global_state.has_gicv4_1) vgic_v4_configure_vsgis(kvm); - dist->ready = true; -out: - return ret; + return 0; } DEFINE_STATIC_KEY_FALSE(vgic_v3_cpuif_trap); diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 3c40da479899..35d75c60e2b8 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -709,10 +709,11 @@ static int do_tag_check_fault(unsigned long far, unsigned int esr, struct pt_regs *regs) { /* - * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN for tag - * check faults. Mask them out now so that userspace doesn't see them. + * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN + * for tag check faults. Set them to corresponding bits in the untagged + * address. */ - far &= (1UL << 60) - 1; + far = (__untagged_addr(far) & ~MTE_TAG_MASK) | (far & MTE_TAG_MASK); do_bad_area(far, esr, regs); return 0; } diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 75addb36354a..709d98fea90c 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -53,13 +53,13 @@ s64 memstart_addr __ro_after_init = -1; EXPORT_SYMBOL(memstart_addr); /* - * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of - * memory as some devices, namely the Raspberry Pi 4, have peripherals with - * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32 - * bit addressable memory area. + * If the corresponding config options are enabled, we create both ZONE_DMA + * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory + * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4). + * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory, + * otherwise it is empty. */ phys_addr_t arm64_dma_phys_limit __ro_after_init; -static phys_addr_t arm64_dma32_phys_limit __ro_after_init; #ifdef CONFIG_KEXEC_CORE /* @@ -84,7 +84,7 @@ static void __init reserve_crashkernel(void) if (crash_base == 0) { /* Current arm64 boot protocol requires 2MB alignment */ - crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit, + crash_base = memblock_find_in_range(0, arm64_dma_phys_limit, crash_size, SZ_2M); if (crash_base == 0) { pr_warn("cannot allocate crashkernel (size:0x%llx)\n", @@ -196,6 +196,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) unsigned long max_zone_pfns[MAX_NR_ZONES] = {0}; unsigned int __maybe_unused acpi_zone_dma_bits; unsigned int __maybe_unused dt_zone_dma_bits; + phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32); #ifdef CONFIG_ZONE_DMA acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address()); @@ -205,8 +206,12 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit); #endif #ifdef CONFIG_ZONE_DMA32 - max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit); + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit); + if (!arm64_dma_phys_limit) + arm64_dma_phys_limit = dma32_phys_limit; #endif + if (!arm64_dma_phys_limit) + arm64_dma_phys_limit = PHYS_MASK + 1; max_zone_pfns[ZONE_NORMAL] = max; free_area_init(max_zone_pfns); @@ -394,16 +399,9 @@ void __init arm64_memblock_init(void) early_init_fdt_scan_reserved_mem(); - if (IS_ENABLED(CONFIG_ZONE_DMA32)) - arm64_dma32_phys_limit = max_zone_phys(32); - else - arm64_dma32_phys_limit = PHYS_MASK + 1; - reserve_elfcorehdr(); high_memory = __va(memblock_end_of_DRAM() - 1) + 1; - - dma_contiguous_reserve(arm64_dma32_phys_limit); } void __init bootmem_init(void) @@ -439,6 +437,11 @@ void __init bootmem_init(void) zone_sizes_init(min, max); /* + * Reserve the CMA area after arm64_dma_phys_limit was initialised. + */ + dma_contiguous_reserve(arm64_dma_phys_limit); + + /* * request_standard_resources() depends on crashkernel's memory being * reserved, so do it here. */ @@ -455,7 +458,7 @@ void __init bootmem_init(void) void __init mem_init(void) { if (swiotlb_force == SWIOTLB_FORCE || - max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit)) + max_pfn > PFN_DOWN(arm64_dma_phys_limit)) swiotlb_init(1); else swiotlb_force = SWIOTLB_NO_FORCE; diff --git a/arch/arm64/mm/physaddr.c b/arch/arm64/mm/physaddr.c index 67a9ba9eaa96..cde44c13dda1 100644 --- a/arch/arm64/mm/physaddr.c +++ b/arch/arm64/mm/physaddr.c @@ -9,7 +9,7 @@ phys_addr_t __virt_to_phys(unsigned long x) { - WARN(!__is_lm_address(x), + WARN(!__is_lm_address(__tag_reset(x)), "virt_to_phys used for non-linear address: %pK (%pS)\n", (void *)x, (void *)x); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 37a54b57178a..1f7ee8c8b7b8 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -46,7 +46,7 @@ #endif #ifdef CONFIG_KASAN_HW_TAGS -#define TCR_KASAN_HW_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1 +#define TCR_KASAN_HW_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1 | TCR_TBID1 #else #define TCR_KASAN_HW_FLAGS 0 #endif diff --git a/arch/h8300/kernel/asm-offsets.c b/arch/h8300/kernel/asm-offsets.c index 85e60509f0a8..d4b53af657c8 100644 --- a/arch/h8300/kernel/asm-offsets.c +++ b/arch/h8300/kernel/asm-offsets.c @@ -63,6 +63,9 @@ int main(void) OFFSET(TI_FLAGS, thread_info, flags); OFFSET(TI_CPU, thread_info, cpu); OFFSET(TI_PRE, thread_info, preempt_count); +#ifdef CONFIG_PREEMPTION + DEFINE(TI_PRE_COUNT, offsetof(struct thread_info, preempt_count)); +#endif return 0; } diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile index 703b1c4f6d12..45d5368d6a99 100644 --- a/arch/ia64/Makefile +++ b/arch/ia64/Makefile @@ -69,7 +69,7 @@ vmlinux.bin: vmlinux FORCE $(call if_changed,objcopy) unwcheck: vmlinux - -$(Q)READELF=$(READELF) $(PYTHON) $(srctree)/arch/ia64/scripts/unwcheck.py $< + -$(Q)READELF=$(READELF) $(PYTHON3) $(srctree)/arch/ia64/scripts/unwcheck.py $< archclean: diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h index dd8c166ffd7b..42ed5248fae9 100644 --- a/arch/ia64/include/asm/sparsemem.h +++ b/arch/ia64/include/asm/sparsemem.h @@ -3,6 +3,7 @@ #define _ASM_IA64_SPARSEMEM_H #ifdef CONFIG_SPARSEMEM +#include <asm/page.h> /* * SECTION_SIZE_BITS 2^N: how big each section will be * MAX_PHYSMEM_BITS 2^N: how much memory we can have in that space diff --git a/arch/ia64/include/uapi/asm/cmpxchg.h b/arch/ia64/include/uapi/asm/cmpxchg.h index d69c979936d4..5d90307fd6e0 100644 --- a/arch/ia64/include/uapi/asm/cmpxchg.h +++ b/arch/ia64/include/uapi/asm/cmpxchg.h @@ -54,7 +54,7 @@ extern void ia64_xchg_called_with_bad_pointer(void); }) #define xchg(ptr, x) \ -((__typeof__(*(ptr))) __xchg((unsigned long) (x), (ptr), sizeof(*(ptr)))) +({(__typeof__(*(ptr))) __xchg((unsigned long) (x), (ptr), sizeof(*(ptr)));}) /* * Atomic compare and exchange. Compare OLD with MEM, if identical, diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c index ed9fc3d057a6..43e8050145be 100644 --- a/arch/ia64/kernel/time.c +++ b/arch/ia64/kernel/time.c @@ -171,29 +171,34 @@ void vtime_account_hardirq(struct task_struct *tsk) static irqreturn_t timer_interrupt (int irq, void *dev_id) { - unsigned long cur_itm, new_itm, ticks; + unsigned long new_itm; if (cpu_is_offline(smp_processor_id())) { return IRQ_HANDLED; } new_itm = local_cpu_data->itm_next; - cur_itm = ia64_get_itc(); - if (!time_after(cur_itm, new_itm)) { + if (!time_after(ia64_get_itc(), new_itm)) printk(KERN_ERR "Oops: timer tick before it's due (itc=%lx,itm=%lx)\n", - cur_itm, new_itm); - ticks = 1; - } else { - ticks = DIV_ROUND_UP(cur_itm - new_itm, - local_cpu_data->itm_delta); - new_itm += ticks * local_cpu_data->itm_delta; - } + ia64_get_itc(), new_itm); + + while (1) { + new_itm += local_cpu_data->itm_delta; + + legacy_timer_tick(smp_processor_id() == time_keeper_id); - if (smp_processor_id() != time_keeper_id) - ticks = 0; + local_cpu_data->itm_next = new_itm; - legacy_timer_tick(ticks); + if (time_after(new_itm, ia64_get_itc())) + break; + + /* + * Allow IPIs to interrupt the timer loop. + */ + local_irq_enable(); + local_irq_disable(); + } do { /* diff --git a/arch/ia64/scripts/unwcheck.py b/arch/ia64/scripts/unwcheck.py index bfd1b671e35f..9581742f0db2 100644 --- a/arch/ia64/scripts/unwcheck.py +++ b/arch/ia64/scripts/unwcheck.py @@ -1,4 +1,4 @@ -#!/usr/bin/env python +#!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 # # Usage: unwcheck.py FILE diff --git a/arch/m68k/include/asm/page.h b/arch/m68k/include/asm/page.h index 6116d7094292..97087dd3ca6d 100644 --- a/arch/m68k/include/asm/page.h +++ b/arch/m68k/include/asm/page.h @@ -62,7 +62,7 @@ extern unsigned long _ramend; #include <asm/page_no.h> #endif -#ifdef CONFIG_DISCONTIGMEM +#if !defined(CONFIG_MMU) || defined(CONFIG_DISCONTIGMEM) #define __phys_to_pfn(paddr) ((unsigned long)((paddr) >> PAGE_SHIFT)) #define __pfn_to_phys(pfn) PFN_PHYS(pfn) #endif diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c index c61c641674e6..e3946b06e840 100644 --- a/arch/mips/boot/compressed/decompress.c +++ b/arch/mips/boot/compressed/decompress.c @@ -13,6 +13,7 @@ #include <linux/libfdt.h> #include <asm/addrspace.h> +#include <asm/unaligned.h> /* * These two variables specify the free mem region @@ -117,7 +118,7 @@ void decompress_kernel(unsigned long boot_heap_start) dtb_size = fdt_totalsize((void *)&__appended_dtb); /* last four bytes is always image size in little endian */ - image_size = le32_to_cpup((void *)&__image_end - 4); + image_size = get_unaligned_le32((void *)&__image_end - 4); /* copy dtb to where the booted kernel will expect it */ memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size, diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c index bd47e15d02c7..be5d4afcd30f 100644 --- a/arch/mips/cavium-octeon/octeon-irq.c +++ b/arch/mips/cavium-octeon/octeon-irq.c @@ -1444,7 +1444,7 @@ static void octeon_irq_setup_secondary_ciu2(void) static int __init octeon_irq_init_ciu( struct device_node *ciu_node, struct device_node *parent) { - unsigned int i, r; + int i, r; struct irq_chip *chip; struct irq_chip *chip_edge; struct irq_chip *chip_mbox; diff --git a/arch/mips/include/asm/highmem.h b/arch/mips/include/asm/highmem.h index 19edf8e69971..292d0425717f 100644 --- a/arch/mips/include/asm/highmem.h +++ b/arch/mips/include/asm/highmem.h @@ -51,6 +51,7 @@ extern void kmap_flush_tlb(unsigned long addr); #define flush_cache_kmaps() BUG_ON(cpu_has_dc_aliases) +#define arch_kmap_local_set_pte(mm, vaddr, ptep, ptev) set_pte(ptep, ptev) #define arch_kmap_local_post_map(vaddr, pteval) local_flush_tlb_one(vaddr) #define arch_kmap_local_post_unmap(vaddr) local_flush_tlb_one(vaddr) diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c index 6ee3f7218c67..c4441416e96b 100644 --- a/arch/mips/kernel/binfmt_elfn32.c +++ b/arch/mips/kernel/binfmt_elfn32.c @@ -103,4 +103,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value) #undef ns_to_kernel_old_timeval #define ns_to_kernel_old_timeval ns_to_old_timeval32 +/* + * Some data types as stored in coredump. + */ +#define user_long_t compat_long_t +#define user_siginfo_t compat_siginfo_t +#define copy_siginfo_to_external copy_siginfo_to_external32 + #include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c index 6dd103d3cebb..7b2a23f48c1a 100644 --- a/arch/mips/kernel/binfmt_elfo32.c +++ b/arch/mips/kernel/binfmt_elfo32.c @@ -106,4 +106,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value) #undef ns_to_kernel_old_timeval #define ns_to_kernel_old_timeval ns_to_old_timeval32 +/* + * Some data types as stored in coredump. + */ +#define user_long_t compat_long_t +#define user_siginfo_t compat_siginfo_t +#define copy_siginfo_to_external copy_siginfo_to_external32 + #include "../../../fs/binfmt_elf.c" diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c index 47aeb3350a76..0e365b7c742d 100644 --- a/arch/mips/kernel/relocate.c +++ b/arch/mips/kernel/relocate.c @@ -187,8 +187,14 @@ static int __init relocate_exception_table(long offset) static inline __init unsigned long rotate_xor(unsigned long hash, const void *area, size_t size) { - size_t i; - unsigned long *ptr = (unsigned long *)area; + const typeof(hash) *ptr = PTR_ALIGN(area, sizeof(hash)); + size_t diff, i; + + diff = (void *)ptr - area; + if (unlikely(size < diff + sizeof(hash))) + return hash; + + size = ALIGN_DOWN(size - diff, sizeof(hash)); for (i = 0; i < size / sizeof(hash); i++) { /* Rotate by odd number of bits and XOR. */ diff --git a/arch/openrisc/include/asm/io.h b/arch/openrisc/include/asm/io.h index 7d6b4a77b379..c298061c70a7 100644 --- a/arch/openrisc/include/asm/io.h +++ b/arch/openrisc/include/asm/io.h @@ -31,7 +31,7 @@ void __iomem *ioremap(phys_addr_t offset, unsigned long size); #define iounmap iounmap -extern void iounmap(void *addr); +extern void iounmap(void __iomem *addr); #include <asm-generic/io.h> diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c index 5aed97a18bac..daae13a76743 100644 --- a/arch/openrisc/mm/ioremap.c +++ b/arch/openrisc/mm/ioremap.c @@ -77,7 +77,7 @@ void __iomem *__ref ioremap(phys_addr_t addr, unsigned long size) } EXPORT_SYMBOL(ioremap); -void iounmap(void *addr) +void iounmap(void __iomem *addr) { /* If the page is from the fixmap pool then we just clear out * the fixmap mapping. diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 78b17621ee4a..278462186ac4 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -202,9 +202,8 @@ config PREFETCH depends on PA8X00 || PA7200 config MLONGCALLS - bool "Enable the -mlong-calls compiler option for big kernels" - default y if !MODULES || UBSAN || FTRACE - default n + def_bool y if !MODULES || UBSAN || FTRACE + bool "Enable the -mlong-calls compiler option for big kernels" if MODULES && !UBSAN && !FTRACE depends on PA8X00 help If you configure the kernel to include many drivers built-in instead diff --git a/arch/parisc/include/asm/irq.h b/arch/parisc/include/asm/irq.h index 959e79cd2c14..378f63c4015b 100644 --- a/arch/parisc/include/asm/irq.h +++ b/arch/parisc/include/asm/irq.h @@ -47,7 +47,4 @@ extern unsigned long txn_affinity_addr(unsigned int irq, int cpu); extern int cpu_claim_irq(unsigned int irq, struct irq_chip *, void *); extern int cpu_check_affinity(struct irq_data *d, const struct cpumask *dest); -/* soft power switch support (power.c) */ -extern struct tasklet_struct power_tasklet; - #endif /* _ASM_PARISC_IRQ_H */ diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index beba9816cc6c..4d37cc9cba37 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -997,10 +997,17 @@ intr_do_preempt: bb,<,n %r20, 31 - PSW_SM_I, intr_restore nop + /* ssm PSW_SM_I done later in intr_restore */ +#ifdef CONFIG_MLONGCALLS + ldil L%intr_restore, %r2 + load32 preempt_schedule_irq, %r1 + bv %r0(%r1) + ldo R%intr_restore(%r2), %r2 +#else + ldil L%intr_restore, %r1 BL preempt_schedule_irq, %r2 - nop - - b,n intr_restore /* ssm PSW_SM_I done by intr_restore */ + ldo R%intr_restore(%r1), %r2 +#endif #endif /* CONFIG_PREEMPTION */ /* diff --git a/arch/powerpc/include/asm/book3s/64/kup.h b/arch/powerpc/include/asm/book3s/64/kup.h index f50f72e535aa..7d1ef7b9754e 100644 --- a/arch/powerpc/include/asm/book3s/64/kup.h +++ b/arch/powerpc/include/asm/book3s/64/kup.h @@ -199,25 +199,31 @@ DECLARE_STATIC_KEY_FALSE(uaccess_flush_key); #ifdef CONFIG_PPC_PKEY +extern u64 __ro_after_init default_uamor; +extern u64 __ro_after_init default_amr; +extern u64 __ro_after_init default_iamr; + #include <asm/mmu.h> #include <asm/ptrace.h> -/* - * For kernel thread that doesn't have thread.regs return - * default AMR/IAMR values. +/* usage of kthread_use_mm() should inherit the + * AMR value of the operating address space. But, the AMR value is + * thread-specific and we inherit the address space and not thread + * access restrictions. Because of this ignore AMR value when accessing + * userspace via kernel thread. */ static inline u64 current_thread_amr(void) { if (current->thread.regs) return current->thread.regs->amr; - return AMR_KUAP_BLOCKED; + return default_amr; } static inline u64 current_thread_iamr(void) { if (current->thread.regs) return current->thread.regs->iamr; - return AMR_KUEP_BLOCKED; + return default_iamr; } #endif /* CONFIG_PPC_PKEY */ diff --git a/arch/powerpc/include/asm/book3s/64/pkeys.h b/arch/powerpc/include/asm/book3s/64/pkeys.h index 3b8640498f5b..5b178139f3c0 100644 --- a/arch/powerpc/include/asm/book3s/64/pkeys.h +++ b/arch/powerpc/include/asm/book3s/64/pkeys.h @@ -5,10 +5,6 @@ #include <asm/book3s/64/hash-pkey.h> -extern u64 __ro_after_init default_uamor; -extern u64 __ro_after_init default_amr; -extern u64 __ro_after_init default_iamr; - static inline u64 vmflag_to_pte_pkey_bits(u64 vm_flags) { if (!mmu_has_feature(MMU_FTR_PKEY)) diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h index 1d32b174ab6a..c1a8aac01cf9 100644 --- a/arch/powerpc/include/asm/exception-64s.h +++ b/arch/powerpc/include/asm/exception-64s.h @@ -63,6 +63,12 @@ nop; \ nop; +#define SCV_ENTRY_FLUSH_SLOT \ + SCV_ENTRY_FLUSH_FIXUP_SECTION; \ + nop; \ + nop; \ + nop; + /* * r10 must be free to use, r13 must be paca */ @@ -71,6 +77,13 @@ ENTRY_FLUSH_SLOT /* + * r10, ctr must be free to use, r13 must be paca + */ +#define SCV_INTERRUPT_TO_KERNEL \ + STF_ENTRY_BARRIER_SLOT; \ + SCV_ENTRY_FLUSH_SLOT + +/* * Macros for annotating the expected destination of (h)rfid * * The nop instructions allow us to insert one or more instructions to flush the diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h index f6d2acb57425..ac605fc369c4 100644 --- a/arch/powerpc/include/asm/feature-fixups.h +++ b/arch/powerpc/include/asm/feature-fixups.h @@ -240,6 +240,14 @@ label##3: \ FTR_ENTRY_OFFSET 957b-958b; \ .popsection; +#define SCV_ENTRY_FLUSH_FIXUP_SECTION \ +957: \ + .pushsection __scv_entry_flush_fixup,"a"; \ + .align 2; \ +958: \ + FTR_ENTRY_OFFSET 957b-958b; \ + .popsection; + #define RFI_FLUSH_FIXUP_SECTION \ 951: \ .pushsection __rfi_flush_fixup,"a"; \ @@ -273,10 +281,12 @@ label##3: \ extern long stf_barrier_fallback; extern long entry_flush_fallback; +extern long scv_entry_flush_fallback; extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup; extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup; extern long __start___uaccess_flush_fixup, __stop___uaccess_flush_fixup; extern long __start___entry_flush_fixup, __stop___entry_flush_fixup; +extern long __start___scv_entry_flush_fixup, __stop___scv_entry_flush_fixup; extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup; extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup; extern long __start__btb_flush_fixup, __stop__btb_flush_fixup; diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h index 80a5ae771c65..c0fcd1bbdba9 100644 --- a/arch/powerpc/include/asm/highmem.h +++ b/arch/powerpc/include/asm/highmem.h @@ -58,6 +58,8 @@ extern pte_t *pkmap_page_table; #define flush_cache_kmaps() flush_cache_all() +#define arch_kmap_local_set_pte(mm, vaddr, ptep, ptev) \ + __set_pte_at(mm, vaddr, ptep, ptev, 1) #define arch_kmap_local_post_map(vaddr, pteval) \ local_flush_tlb_page(NULL, vaddr) #define arch_kmap_local_post_unmap(vaddr) \ diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h index 81671aa365b3..77c635c2c90d 100644 --- a/arch/powerpc/include/asm/vdso/gettimeofday.h +++ b/arch/powerpc/include/asm/vdso/gettimeofday.h @@ -103,6 +103,8 @@ int gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz return do_syscall_2(__NR_gettimeofday, (unsigned long)_tv, (unsigned long)_tz); } +#ifdef __powerpc64__ + static __always_inline int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) { @@ -115,11 +117,23 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts); } -#ifdef CONFIG_VDSO32 +#else #define BUILD_VDSO32 1 static __always_inline +int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_gettime64, _clkid, (unsigned long)_ts); +} + +static __always_inline +int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return do_syscall_2(__NR_clock_getres_time64, _clkid, (unsigned long)_ts); +} + +static __always_inline int clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) { return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts); diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index fe2ef598e2ea..79ee7750937d 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -51,7 +51,7 @@ obj-y += ptrace/ obj-$(CONFIG_PPC64) += setup_64.o \ paca.o nvram_64.o note.o syscall_64.o obj-$(CONFIG_COMPAT) += sys_ppc32.o signal_32.o -obj-$(CONFIG_VDSO32) += vdso32/ +obj-$(CONFIG_VDSO32) += vdso32_wrapper.o obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_PPC_DAWR) += dawr.o @@ -60,7 +60,7 @@ obj-$(CONFIG_PPC_BOOK3S_64) += cpu_setup_power.o obj-$(CONFIG_PPC_BOOK3S_64) += mce.o mce_power.o obj-$(CONFIG_PPC_BOOK3E_64) += exceptions-64e.o idle_book3e.o obj-$(CONFIG_PPC_BARRIER_NOSPEC) += security.o -obj-$(CONFIG_PPC64) += vdso64/ +obj-$(CONFIG_PPC64) += vdso64_wrapper.o obj-$(CONFIG_ALTIVEC) += vecemu.o obj-$(CONFIG_PPC_BOOK3S_IDLE) += idle_book3s.o procfs-y := proc_powerpc.o diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S index aa1af139d947..33ddfeef4fe9 100644 --- a/arch/powerpc/kernel/entry_64.S +++ b/arch/powerpc/kernel/entry_64.S @@ -75,7 +75,7 @@ BEGIN_FTR_SECTION bne .Ltabort_syscall END_FTR_SECTION_IFSET(CPU_FTR_TM) #endif - INTERRUPT_TO_KERNEL + SCV_INTERRUPT_TO_KERNEL mr r10,r1 ld r1,PACAKSAVE(r13) std r10,0(r1) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index e02ad6fefa46..6e53f7638737 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -2993,6 +2993,25 @@ TRAMP_REAL_BEGIN(entry_flush_fallback) ld r11,PACA_EXRFI+EX_R11(r13) blr +/* + * The SCV entry flush happens with interrupts enabled, so it must disable + * to prevent EXRFI being clobbered by NMIs (e.g., soft_nmi_common). r10 + * (containing LR) does not need to be preserved here because scv entry + * puts 0 in the pt_regs, CTR can be clobbered for the same reason. + */ +TRAMP_REAL_BEGIN(scv_entry_flush_fallback) + li r10,0 + mtmsrd r10,1 + lbz r10,PACAIRQHAPPENED(r13) + ori r10,r10,PACA_IRQ_HARD_DIS + stb r10,PACAIRQHAPPENED(r13) + std r11,PACA_EXRFI+EX_R11(r13) + L1D_DISPLACEMENT_FLUSH + ld r11,PACA_EXRFI+EX_R11(r13) + li r10,MSR_RI + mtmsrd r10,1 + blr + TRAMP_REAL_BEGIN(rfi_flush_fallback) SET_SCRATCH0(r13); GET_PACA(r13); diff --git a/arch/powerpc/kernel/head_book3s_32.S b/arch/powerpc/kernel/head_book3s_32.S index 349bf3f0c3af..858fbc8b19f3 100644 --- a/arch/powerpc/kernel/head_book3s_32.S +++ b/arch/powerpc/kernel/head_book3s_32.S @@ -260,10 +260,19 @@ __secondary_hold_acknowledge: MachineCheck: EXCEPTION_PROLOG_0 #ifdef CONFIG_PPC_CHRP +#ifdef CONFIG_VMAP_STACK + mtspr SPRN_SPRG_SCRATCH2,r1 + mfspr r1, SPRN_SPRG_THREAD + lwz r1, RTAS_SP(r1) + cmpwi cr1, r1, 0 + bne cr1, 7f + mfspr r1, SPRN_SPRG_SCRATCH2 +#else mfspr r11, SPRN_SPRG_THREAD lwz r11, RTAS_SP(r11) cmpwi cr1, r11, 0 bne cr1, 7f +#endif #endif /* CONFIG_PPC_CHRP */ EXCEPTION_PROLOG_1 for_rtas=1 7: EXCEPTION_PROLOG_2 diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c index 6b1eca53e36c..cc7a6271b6b4 100644 --- a/arch/powerpc/kernel/irq.c +++ b/arch/powerpc/kernel/irq.c @@ -180,13 +180,18 @@ void notrace restore_interrupts(void) void replay_soft_interrupts(void) { + struct pt_regs regs; + /* - * We use local_paca rather than get_paca() to avoid all - * the debug_smp_processor_id() business in this low level - * function + * Be careful here, calling these interrupt handlers can cause + * softirqs to be raised, which they may run when calling irq_exit, + * which will cause local_irq_enable() to be run, which can then + * recurse into this function. Don't keep any state across + * interrupt handler calls which may change underneath us. + * + * We use local_paca rather than get_paca() to avoid all the + * debug_smp_processor_id() business in this low level function. */ - unsigned char happened = local_paca->irq_happened; - struct pt_regs regs; ppc_save_regs(®s); regs.softe = IRQS_ENABLED; @@ -209,7 +214,7 @@ again: * This is a higher priority interrupt than the others, so * replay it first. */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (happened & PACA_IRQ_HMI)) { + if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_HMI)) { local_paca->irq_happened &= ~PACA_IRQ_HMI; regs.trap = 0xe60; handle_hmi_exception(®s); @@ -217,7 +222,7 @@ again: hard_irq_disable(); } - if (happened & PACA_IRQ_DEC) { + if (local_paca->irq_happened & PACA_IRQ_DEC) { local_paca->irq_happened &= ~PACA_IRQ_DEC; regs.trap = 0x900; timer_interrupt(®s); @@ -225,7 +230,7 @@ again: hard_irq_disable(); } - if (happened & PACA_IRQ_EE) { + if (local_paca->irq_happened & PACA_IRQ_EE) { local_paca->irq_happened &= ~PACA_IRQ_EE; regs.trap = 0x500; do_IRQ(®s); @@ -233,7 +238,7 @@ again: hard_irq_disable(); } - if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (happened & PACA_IRQ_DBELL)) { + if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (local_paca->irq_happened & PACA_IRQ_DBELL)) { local_paca->irq_happened &= ~PACA_IRQ_DBELL; if (IS_ENABLED(CONFIG_PPC_BOOK3E)) regs.trap = 0x280; @@ -245,7 +250,7 @@ again: } /* Book3E does not support soft-masking PMI interrupts */ - if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (happened & PACA_IRQ_PMI)) { + if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (local_paca->irq_happened & PACA_IRQ_PMI)) { local_paca->irq_happened &= ~PACA_IRQ_PMI; regs.trap = 0xf00; performance_monitor_exception(®s); @@ -253,8 +258,7 @@ again: hard_irq_disable(); } - happened = local_paca->irq_happened; - if (happened & ~PACA_IRQ_HARD_DIS) { + if (local_paca->irq_happened & ~PACA_IRQ_HARD_DIS) { /* * We are responding to the next interrupt, so interrupt-off * latencies should be reset here. diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile index 9cb6f524854b..7d9a6fee0e3d 100644 --- a/arch/powerpc/kernel/vdso32/Makefile +++ b/arch/powerpc/kernel/vdso32/Makefile @@ -30,7 +30,7 @@ CC32FLAGS += -m32 KBUILD_CFLAGS := $(filter-out -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc,$(KBUILD_CFLAGS)) endif -targets := $(obj-vdso32) vdso32.so.dbg +targets := $(obj-vdso32) vdso32.so.dbg vgettimeofday.o obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32)) GCOV_PROFILE := n @@ -46,9 +46,6 @@ obj-y += vdso32_wrapper.o targets += vdso32.lds CPPFLAGS_vdso32.lds += -P -C -Upowerpc -# Force dependency (incbin is bad) -$(obj)/vdso32_wrapper.o : $(obj)/vdso32.so.dbg - # link rule for the .so file, .lds has to be first $(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32) $(obj)/vgettimeofday.o FORCE $(call if_changed,vdso32ld_and_check) diff --git a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32_wrapper.S index 3f5ef035b0a9..3f5ef035b0a9 100644 --- a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S +++ b/arch/powerpc/kernel/vdso32_wrapper.S diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile index bf363ff37152..2813e3f98db6 100644 --- a/arch/powerpc/kernel/vdso64/Makefile +++ b/arch/powerpc/kernel/vdso64/Makefile @@ -17,7 +17,7 @@ endif # Build rules -targets := $(obj-vdso64) vdso64.so.dbg +targets := $(obj-vdso64) vdso64.so.dbg vgettimeofday.o obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64)) GCOV_PROFILE := n @@ -29,15 +29,9 @@ ccflags-y := -shared -fno-common -fno-builtin -nostdlib \ -Wl,-soname=linux-vdso64.so.1 -Wl,--hash-style=both asflags-y := -D__VDSO64__ -s -obj-y += vdso64_wrapper.o targets += vdso64.lds CPPFLAGS_vdso64.lds += -P -C -U$(ARCH) -$(obj)/vgettimeofday.o: %.o: %.c FORCE - -# Force dependency (incbin is bad) -$(obj)/vdso64_wrapper.o : $(obj)/vdso64.so.dbg - # link rule for the .so file, .lds has to be first $(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64) $(obj)/vgettimeofday.o FORCE $(call if_changed,vdso64ld_and_check) diff --git a/arch/powerpc/kernel/vdso64/sigtramp.S b/arch/powerpc/kernel/vdso64/sigtramp.S index bbf68cd01088..2d4067561293 100644 --- a/arch/powerpc/kernel/vdso64/sigtramp.S +++ b/arch/powerpc/kernel/vdso64/sigtramp.S @@ -15,11 +15,20 @@ .text +/* + * __kernel_start_sigtramp_rt64 and __kernel_sigtramp_rt64 together + * are one function split in two parts. The kernel jumps to the former + * and the signal handler indirectly (by blr) returns to the latter. + * __kernel_sigtramp_rt64 needs to point to the return address so + * glibc can correctly identify the trampoline stack frame. + */ .balign 8 .balign IFETCH_ALIGN_BYTES -V_FUNCTION_BEGIN(__kernel_sigtramp_rt64) +V_FUNCTION_BEGIN(__kernel_start_sigtramp_rt64) .Lsigrt_start: bctrl /* call the handler */ +V_FUNCTION_END(__kernel_start_sigtramp_rt64) +V_FUNCTION_BEGIN(__kernel_sigtramp_rt64) addi r1, r1, __SIGNAL_FRAMESIZE li r0,__NR_rt_sigreturn sc diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S index 6164d1a1ba11..2f3c359cacd3 100644 --- a/arch/powerpc/kernel/vdso64/vdso64.lds.S +++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S @@ -131,4 +131,4 @@ VERSION /* * Make the sigreturn code visible to the kernel. */ -VDSO_sigtramp_rt64 = __kernel_sigtramp_rt64; +VDSO_sigtramp_rt64 = __kernel_start_sigtramp_rt64; diff --git a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64_wrapper.S index 1d56d81fe3b3..1d56d81fe3b3 100644 --- a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S +++ b/arch/powerpc/kernel/vdso64_wrapper.S diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S index 0318ba436f34..72fa3c00229a 100644 --- a/arch/powerpc/kernel/vmlinux.lds.S +++ b/arch/powerpc/kernel/vmlinux.lds.S @@ -85,7 +85,7 @@ SECTIONS ALIGN_FUNCTION(); #endif /* careful! __ftr_alt_* sections need to be close to .text */ - *(.text.hot TEXT_MAIN .text.fixup .text.unlikely .fixup __ftr_alt_* .ref.text); + *(.text.hot .text.hot.* TEXT_MAIN .text.fixup .text.unlikely .text.unlikely.* .fixup __ftr_alt_* .ref.text); #ifdef CONFIG_PPC64 *(.tramp.ftrace.text); #endif @@ -146,6 +146,13 @@ SECTIONS } . = ALIGN(8); + __scv_entry_flush_fixup : AT(ADDR(__scv_entry_flush_fixup) - LOAD_OFFSET) { + __start___scv_entry_flush_fixup = .; + *(__scv_entry_flush_fixup) + __stop___scv_entry_flush_fixup = .; + } + + . = ALIGN(8); __stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) { __start___stf_exit_barrier_fixup = .; *(__stf_exit_barrier_fixup) @@ -187,6 +194,12 @@ SECTIONS .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) { _sinittext = .; INIT_TEXT + + /* + *.init.text might be RO so we must ensure this section ends on + * a page boundary. + */ + . = ALIGN(PAGE_SIZE); _einittext = .; #ifdef CONFIG_PPC64 *(.tramp.ftrace.init); @@ -200,6 +213,8 @@ SECTIONS EXIT_TEXT } + . = ALIGN(PAGE_SIZE); + INIT_DATA_SECTION(16) . = ALIGN(8); diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c index 47821055b94c..1fd31b4b0e13 100644 --- a/arch/powerpc/lib/feature-fixups.c +++ b/arch/powerpc/lib/feature-fixups.c @@ -290,9 +290,6 @@ void do_entry_flush_fixups(enum l1d_flush_type types) long *start, *end; int i; - start = PTRRELOC(&__start___entry_flush_fixup); - end = PTRRELOC(&__stop___entry_flush_fixup); - instrs[0] = 0x60000000; /* nop */ instrs[1] = 0x60000000; /* nop */ instrs[2] = 0x60000000; /* nop */ @@ -312,6 +309,8 @@ void do_entry_flush_fixups(enum l1d_flush_type types) if (types & L1D_FLUSH_MTTRIG) instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */ + start = PTRRELOC(&__start___entry_flush_fixup); + end = PTRRELOC(&__stop___entry_flush_fixup); for (i = 0; start < end; start++, i++) { dest = (void *)start + *start; @@ -328,6 +327,25 @@ void do_entry_flush_fixups(enum l1d_flush_type types) patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); } + start = PTRRELOC(&__start___scv_entry_flush_fixup); + end = PTRRELOC(&__stop___scv_entry_flush_fixup); + for (; start < end; start++, i++) { + dest = (void *)start + *start; + + pr_devel("patching dest %lx\n", (unsigned long)dest); + + patch_instruction((struct ppc_inst *)dest, ppc_inst(instrs[0])); + + if (types == L1D_FLUSH_FALLBACK) + patch_branch((struct ppc_inst *)(dest + 1), (unsigned long)&scv_entry_flush_fallback, + BRANCH_SET_LINK); + else + patch_instruction((struct ppc_inst *)(dest + 1), ppc_inst(instrs[1])); + + patch_instruction((struct ppc_inst *)(dest + 2), ppc_inst(instrs[2])); + } + + printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i, (types == L1D_FLUSH_NONE) ? "no" : (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" : diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c index bf7a7d62ae8b..ede093e96234 100644 --- a/arch/powerpc/lib/sstep.c +++ b/arch/powerpc/lib/sstep.c @@ -818,13 +818,15 @@ void emulate_vsx_store(struct instruction_op *op, const union vsx_reg *reg, break; if (rev) { /* reverse 32 bytes */ - buf.d[0] = byterev_8(reg->d[3]); - buf.d[1] = byterev_8(reg->d[2]); - buf.d[2] = byterev_8(reg->d[1]); - buf.d[3] = byterev_8(reg->d[0]); - reg = &buf; + union vsx_reg buf32[2]; + buf32[0].d[0] = byterev_8(reg[1].d[1]); + buf32[0].d[1] = byterev_8(reg[1].d[0]); + buf32[1].d[0] = byterev_8(reg[0].d[1]); + buf32[1].d[1] = byterev_8(reg[0].d[0]); + memcpy(mem, buf32, size); + } else { + memcpy(mem, reg, size); } - memcpy(mem, reg, size); break; case 16: /* stxv, stxvx, stxvl, stxvll */ diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c index f1c6f264ed91..15dcc5ad91c5 100644 --- a/arch/powerpc/mm/book3s64/pkeys.c +++ b/arch/powerpc/mm/book3s64/pkeys.c @@ -31,6 +31,7 @@ static u32 initial_allocation_mask __ro_after_init; u64 default_amr __ro_after_init = ~0x0UL; u64 default_iamr __ro_after_init = 0x5555555555555555UL; u64 default_uamor __ro_after_init; +EXPORT_SYMBOL(default_amr); /* * Key used to implement PROT_EXEC mmap. Denies READ/WRITE * We pick key 2 because 0 is special key and 1 is reserved as per ISA. diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index 81b76d44725d..e0a34eb5ed3b 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -137,7 +137,7 @@ config PA_BITS config PAGE_OFFSET hex - default 0xC0000000 if 32BIT && MAXPHYSMEM_2GB + default 0xC0000000 if 32BIT && MAXPHYSMEM_1GB default 0x80000000 if 64BIT && !MMU default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB @@ -247,11 +247,15 @@ config MODULE_SECTIONS choice prompt "Maximum Physical Memory" - default MAXPHYSMEM_2GB if 32BIT + default MAXPHYSMEM_1GB if 32BIT default MAXPHYSMEM_2GB if 64BIT && CMODEL_MEDLOW default MAXPHYSMEM_128GB if 64BIT && CMODEL_MEDANY + config MAXPHYSMEM_1GB + depends on 32BIT + bool "1GiB" config MAXPHYSMEM_2GB + depends on 64BIT && CMODEL_MEDLOW bool "2GiB" config MAXPHYSMEM_128GB depends on 64BIT && CMODEL_MEDANY diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts index 4a2729f5ca3f..60846e88ae4b 100644 --- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -88,6 +88,7 @@ phy-mode = "gmii"; phy-handle = <&phy0>; phy0: ethernet-phy@0 { + compatible = "ethernet-phy-id0007.0771"; reg = <0>; }; }; diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index d222d353d86d..8c3d1e451703 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -64,6 +64,8 @@ CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=y CONFIG_SPI=y CONFIG_SPI_SIFIVE=y +CONFIG_GPIOLIB=y +CONFIG_GPIO_SIFIVE=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_POWER_RESET=y CONFIG_DRM=y diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 2d50f76efe48..64a675c5c30a 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -135,7 +135,10 @@ extern phys_addr_t __phys_addr_symbol(unsigned long x); #endif /* __ASSEMBLY__ */ -#define virt_addr_valid(vaddr) (pfn_valid(virt_to_pfn(vaddr))) +#define virt_addr_valid(vaddr) ({ \ + unsigned long _addr = (unsigned long)vaddr; \ + (unsigned long)(_addr) >= PAGE_OFFSET && pfn_valid(virt_to_pfn(_addr)); \ +}) #define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_NON_EXEC diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 41a72861987c..251e1db088fa 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -99,7 +99,6 @@ | _PAGE_DIRTY) #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) -#define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC) #define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC) #define PAGE_KERNEL_READ_EXEC __pgprot((_PAGE_KERNEL & ~_PAGE_WRITE) \ diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h index 211eb8244a45..8b80c80c7f1a 100644 --- a/arch/riscv/include/asm/set_memory.h +++ b/arch/riscv/include/asm/set_memory.h @@ -32,14 +32,14 @@ bool kernel_page_present(struct page *page); #endif /* __ASSEMBLY__ */ -#ifdef CONFIG_ARCH_HAS_STRICT_KERNEL_RWX +#ifdef CONFIG_STRICT_KERNEL_RWX #ifdef CONFIG_64BIT #define SECTION_ALIGN (1 << 21) #else #define SECTION_ALIGN (1 << 22) #endif -#else /* !CONFIG_ARCH_HAS_STRICT_KERNEL_RWX */ +#else /* !CONFIG_STRICT_KERNEL_RWX */ #define SECTION_ALIGN L1_CACHE_BYTES -#endif /* CONFIG_ARCH_HAS_STRICT_KERNEL_RWX */ +#endif /* CONFIG_STRICT_KERNEL_RWX */ #endif /* _ASM_RISCV_SET_MEMORY_H */ diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h index 8454f746bbfd..1453a2f563bc 100644 --- a/arch/riscv/include/asm/vdso.h +++ b/arch/riscv/include/asm/vdso.h @@ -10,7 +10,7 @@ #include <linux/types.h> -#ifndef GENERIC_TIME_VSYSCALL +#ifndef CONFIG_GENERIC_TIME_VSYSCALL struct vdso_data { }; #endif diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c index de59dd457b41..d86781357044 100644 --- a/arch/riscv/kernel/cacheinfo.c +++ b/arch/riscv/kernel/cacheinfo.c @@ -26,7 +26,16 @@ cache_get_priv_group(struct cacheinfo *this_leaf) static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type) { - struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(smp_processor_id()); + /* + * Using raw_smp_processor_id() elides a preemptability check, but this + * is really indicative of a larger problem: the cacheinfo UABI assumes + * that cores have a homonogenous view of the cache hierarchy. That + * happens to be the case for the current set of RISC-V systems, but + * likely won't be true in general. Since there's no way to provide + * correct information for these systems via the current UABI we're + * just eliding the check for now. + */ + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(raw_smp_processor_id()); struct cacheinfo *this_leaf; int index; diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 524d918f3601..744f3209c48d 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -124,15 +124,15 @@ skip_context_tracking: REG_L a1, (a1) jr a1 1: -#ifdef CONFIG_TRACE_IRQFLAGS - call trace_hardirqs_on -#endif /* * Exceptions run with interrupts enabled or disabled depending on the * state of SR_PIE in m/sstatus. */ andi t0, s1, SR_PIE beqz t0, 1f +#ifdef CONFIG_TRACE_IRQFLAGS + call trace_hardirqs_on +#endif csrs CSR_STATUS, SR_IE 1: @@ -155,6 +155,15 @@ skip_context_tracking: tail do_trap_unknown handle_syscall: +#ifdef CONFIG_RISCV_M_MODE + /* + * When running is M-Mode (no MMU config), MPIE does not get set. + * As a result, we need to force enable interrupts here because + * handle_exception did not do set SR_IE as it always sees SR_PIE + * being cleared. + */ + csrs CSR_STATUS, SR_IE +#endif #if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING) /* Recover a0 - a7 for system calls */ REG_L a0, PT_A0(sp) @@ -186,14 +195,7 @@ check_syscall_nr: * Syscall number held in a7. * If syscall number is above allowed value, redirect to ni_syscall. */ - bge a7, t0, 1f - /* - * Check if syscall is rejected by tracer, i.e., a7 == -1. - * If yes, we pretend it was executed. - */ - li t1, -1 - beq a7, t1, ret_from_syscall_rejected - blt a7, t1, 1f + bgeu a7, t0, 1f /* Call syscall */ la s0, sys_call_table slli t0, a7, RISCV_LGPTR diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 1d85e9bf783c..c7c0655dd45b 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -127,7 +127,9 @@ static void __init init_resources(void) { struct memblock_region *region = NULL; struct resource *res = NULL; - int ret = 0; + struct resource *mem_res = NULL; + size_t mem_res_sz = 0; + int ret = 0, i = 0; code_res.start = __pa_symbol(_text); code_res.end = __pa_symbol(_etext) - 1; @@ -145,16 +147,17 @@ static void __init init_resources(void) bss_res.end = __pa_symbol(__bss_stop) - 1; bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt) * sizeof(*mem_res); + mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES); + if (!mem_res) + panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz); /* * Start by adding the reserved regions, if they overlap * with /memory regions, insert_resource later on will take * care of it. */ for_each_reserved_mem_region(region) { - res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct resource)); + res = &mem_res[i++]; res->name = "Reserved"; res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; @@ -171,8 +174,10 @@ static void __init init_resources(void) * Ignore any other reserved regions within * system memory. */ - if (memblock_is_memory(res->start)) + if (memblock_is_memory(res->start)) { + memblock_free((phys_addr_t) res, sizeof(struct resource)); continue; + } ret = add_resource(&iomem_resource, res); if (ret < 0) @@ -181,10 +186,7 @@ static void __init init_resources(void) /* Add /memory regions to the resource tree */ for_each_mem_region(region) { - res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); - if (!res) - panic("%s: Failed to allocate %zu bytes\n", __func__, - sizeof(struct resource)); + res = &mem_res[i++]; if (unlikely(memblock_is_nomap(region))) { res->name = "Reserved"; @@ -205,9 +207,9 @@ static void __init init_resources(void) return; error: - memblock_free((phys_addr_t) res, sizeof(struct resource)); /* Better an empty resource tree than an inconsistent one */ release_child_resources(&iomem_resource); + memblock_free((phys_addr_t) mem_res, mem_res_sz); } @@ -291,6 +293,8 @@ void free_initmem(void) unsigned long init_begin = (unsigned long)__init_begin; unsigned long init_end = (unsigned long)__init_end; - set_memory_rw_nx(init_begin, (init_end - init_begin) >> PAGE_SHIFT); + if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) + set_memory_rw_nx(init_begin, (init_end - init_begin) >> PAGE_SHIFT); + free_initmem_default(POISON_FREE_INITMEM); } diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 48b870a685b3..df5d2da7c40b 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -14,7 +14,7 @@ #include <asm/stacktrace.h> -register unsigned long sp_in_global __asm__("sp"); +register const unsigned long sp_in_global __asm__("sp"); #ifdef CONFIG_FRAME_POINTER @@ -28,9 +28,8 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, sp = user_stack_pointer(regs); pc = instruction_pointer(regs); } else if (task == NULL || task == current) { - const register unsigned long current_sp = sp_in_global; fp = (unsigned long)__builtin_frame_address(0); - sp = current_sp; + sp = sp_in_global; pc = (unsigned long)walk_stackframe; } else { /* task blocked in __switch_to */ diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c index 4d3a1048ad8b..8a5cf99c0776 100644 --- a/arch/riscv/kernel/time.c +++ b/arch/riscv/kernel/time.c @@ -4,6 +4,7 @@ * Copyright (C) 2017 SiFive */ +#include <linux/of_clk.h> #include <linux/clocksource.h> #include <linux/delay.h> #include <asm/sbi.h> @@ -24,6 +25,8 @@ void __init time_init(void) riscv_timebase = prop; lpj_fine = riscv_timebase / HZ; + + of_clk_init(NULL); timer_probe(); } diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c index 678204231700..3f1d35e7c98a 100644 --- a/arch/riscv/kernel/vdso.c +++ b/arch/riscv/kernel/vdso.c @@ -12,7 +12,7 @@ #include <linux/binfmts.h> #include <linux/err.h> #include <asm/page.h> -#ifdef GENERIC_TIME_VSYSCALL +#ifdef CONFIG_GENERIC_TIME_VSYSCALL #include <vdso/datapage.h> #else #include <asm/vdso.h> diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index bf5379135e39..f9f9568d689e 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -157,9 +157,10 @@ disable: void __init setup_bootmem(void) { phys_addr_t mem_start = 0; - phys_addr_t start, end = 0; + phys_addr_t start, dram_end, end = 0; phys_addr_t vmlinux_end = __pa_symbol(&_end); phys_addr_t vmlinux_start = __pa_symbol(&_start); + phys_addr_t max_mapped_addr = __pa(~(ulong)0); u64 i; /* Find the memory region containing the kernel */ @@ -181,10 +182,21 @@ void __init setup_bootmem(void) /* Reserve from the start of the kernel to the end of the kernel */ memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); - max_pfn = PFN_DOWN(memblock_end_of_DRAM()); + dram_end = memblock_end_of_DRAM(); + + /* + * memblock allocator is not aware of the fact that last 4K bytes of + * the addressable memory can not be mapped because of IS_ERR_VALUE + * macro. Make sure that last 4k bytes are not usable by memblock + * if end of dram is equal to maximum addressable memory. + */ + if (max_mapped_addr == (dram_end - 1)) + memblock_set_current_limit(max_mapped_addr - 4096); + + max_pfn = PFN_DOWN(dram_end); max_low_pfn = max_pfn; dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); - set_max_mapnr(max_low_pfn); + set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET); #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c index 12ddd1f6bf70..a8a2ffd9114a 100644 --- a/arch/riscv/mm/kasan_init.c +++ b/arch/riscv/mm/kasan_init.c @@ -93,8 +93,8 @@ void __init kasan_init(void) VMALLOC_END)); for_each_mem_range(i, &_start, &_end) { - void *start = (void *)_start; - void *end = (void *)_end; + void *start = (void *)__va(_start); + void *end = (void *)__va(_end); if (start >= end) break; diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c index a15c033f53ca..87641dd65ccf 100644 --- a/arch/s390/boot/uv.c +++ b/arch/s390/boot/uv.c @@ -35,7 +35,7 @@ void uv_query_info(void) uv_info.guest_cpu_stor_len = uvcb.cpu_stor_len; uv_info.max_sec_stor_addr = ALIGN(uvcb.max_guest_stor_addr, PAGE_SIZE); uv_info.max_num_sec_conf = uvcb.max_num_sec_conf; - uv_info.max_guest_cpus = uvcb.max_guest_cpus; + uv_info.max_guest_cpu_id = uvcb.max_guest_cpu_id; } #ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index 0325fc0469b7..7b98d4caee77 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -96,7 +96,7 @@ struct uv_cb_qui { u32 max_num_sec_conf; u64 max_guest_stor_addr; u8 reserved88[158 - 136]; - u16 max_guest_cpus; + u16 max_guest_cpu_id; u8 reserveda0[200 - 160]; } __packed __aligned(8); @@ -273,7 +273,7 @@ struct uv_info { unsigned long guest_cpu_stor_len; unsigned long max_sec_stor_addr; unsigned int max_num_sec_conf; - unsigned short max_guest_cpus; + unsigned short max_guest_cpu_id; }; extern struct uv_info uv_info; diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 883bfed9f5c2..b2d2ad153067 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -368,7 +368,7 @@ static ssize_t uv_query_max_guest_cpus(struct kobject *kobj, struct kobj_attribute *attr, char *page) { return scnprintf(page, PAGE_SIZE, "%d\n", - uv_info.max_guest_cpus); + uv_info.max_guest_cpu_id + 1); } static struct kobj_attribute uv_query_max_guest_cpus_attr = diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 5fa580219a86..52646f52f130 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -29,7 +29,6 @@ config SUPERH select HAVE_ARCH_KGDB select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK - select HAVE_COPY_THREAD_TLS select HAVE_DEBUG_BUGVERBOSE select HAVE_DEBUG_KMEMLEAK select HAVE_DYNAMIC_FTRACE diff --git a/arch/sh/boards/mach-sh03/rtc.c b/arch/sh/boards/mach-sh03/rtc.c index 8b23ed7c201c..7fb474844a2d 100644 --- a/arch/sh/boards/mach-sh03/rtc.c +++ b/arch/sh/boards/mach-sh03/rtc.c @@ -11,7 +11,6 @@ #include <linux/sched.h> #include <linux/time.h> #include <linux/bcd.h> -#include <linux/rtc.h> #include <linux/spinlock.h> #include <linux/io.h> #include <linux/rtc.h> diff --git a/arch/sh/configs/landisk_defconfig b/arch/sh/configs/landisk_defconfig index ba6ec042606f..e6c5ddf070c0 100644 --- a/arch/sh/configs/landisk_defconfig +++ b/arch/sh/configs/landisk_defconfig @@ -27,13 +27,12 @@ CONFIG_NETFILTER=y CONFIG_ATALK=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y -CONFIG_BLK_DEV_OFFBOARD=y -CONFIG_BLK_DEV_GENERIC=y -CONFIG_BLK_DEV_AEC62XX=y +CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_ATP867X=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y +CONFIG_BLK_DEV_SR=y CONFIG_SCSI_MULTI_LUN=y CONFIG_MD=y CONFIG_BLK_DEV_MD=m diff --git a/arch/sh/configs/microdev_defconfig b/arch/sh/configs/microdev_defconfig index c65667d00313..e9825196dd66 100644 --- a/arch/sh/configs/microdev_defconfig +++ b/arch/sh/configs/microdev_defconfig @@ -20,8 +20,6 @@ CONFIG_IP_PNP=y # CONFIG_IPV6 is not set # CONFIG_FW_LOADER is not set CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y CONFIG_SMC91X=y diff --git a/arch/sh/configs/sdk7780_defconfig b/arch/sh/configs/sdk7780_defconfig index d10a0414123a..d00376eb044f 100644 --- a/arch/sh/configs/sdk7780_defconfig +++ b/arch/sh/configs/sdk7780_defconfig @@ -44,16 +44,14 @@ CONFIG_NET_SCHED=y CONFIG_PARPORT=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y -CONFIG_BLK_DEV_PLATFORM=y -CONFIG_BLK_DEV_GENERIC=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y CONFIG_CHR_DEV_SG=y CONFIG_SCSI_SPI_ATTRS=y CONFIG_SCSI_FC_ATTRS=y CONFIG_ATA=y +CONFIG_ATA_GENERIC=y +CONFIG_PATA_PLATFORM=y CONFIG_MD=y CONFIG_BLK_DEV_DM=y CONFIG_NETDEVICES=y diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig index 61bec46ebd66..4a44cac640bc 100644 --- a/arch/sh/configs/sdk7786_defconfig +++ b/arch/sh/configs/sdk7786_defconfig @@ -116,9 +116,6 @@ CONFIG_MTD_UBI_GLUEBI=m CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_CRYPTOLOOP=y CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=y -CONFIG_BLK_DEV_PLATFORM=y CONFIG_BLK_DEV_SD=y CONFIG_BLK_DEV_SR=y CONFIG_SCSI_MULTI_LUN=y diff --git a/arch/sh/configs/se7750_defconfig b/arch/sh/configs/se7750_defconfig index 3f1c13799d79..4defc7628a49 100644 --- a/arch/sh/configs/se7750_defconfig +++ b/arch/sh/configs/se7750_defconfig @@ -29,7 +29,6 @@ CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y CONFIG_MTD_CFI_AMDSTD=y CONFIG_MTD_ROM=y -CONFIG_IDE=y CONFIG_SCSI=y CONFIG_NETDEVICES=y CONFIG_NET_ETHERNET=y diff --git a/arch/sh/configs/sh03_defconfig b/arch/sh/configs/sh03_defconfig index f0073ed39947..48b457d59e79 100644 --- a/arch/sh/configs/sh03_defconfig +++ b/arch/sh/configs/sh03_defconfig @@ -39,9 +39,6 @@ CONFIG_IP_PNP_RARP=y CONFIG_BLK_DEV_LOOP=y CONFIG_BLK_DEV_NBD=y CONFIG_BLK_DEV_RAM=y -CONFIG_IDE=y -CONFIG_BLK_DEV_IDECD=m -CONFIG_BLK_DEV_IDETAPE=m CONFIG_SCSI=m CONFIG_BLK_DEV_SD=m CONFIG_BLK_DEV_SR=m diff --git a/arch/sh/drivers/dma/Kconfig b/arch/sh/drivers/dma/Kconfig index d0de378beefe..7d54f284ce10 100644 --- a/arch/sh/drivers/dma/Kconfig +++ b/arch/sh/drivers/dma/Kconfig @@ -63,8 +63,7 @@ config PVR2_DMA config G2_DMA tristate "G2 Bus DMA support" - depends on SH_DREAMCAST - select SH_DMA_API + depends on SH_DREAMCAST && SH_DMA_API help This enables support for the DMA controller for the Dreamcast's G2 bus. Drivers that want this will generally enable this on diff --git a/arch/sh/include/asm/gpio.h b/arch/sh/include/asm/gpio.h index 351918894e86..d643250f0a0f 100644 --- a/arch/sh/include/asm/gpio.h +++ b/arch/sh/include/asm/gpio.h @@ -16,7 +16,6 @@ #include <cpu/gpio.h> #endif -#define ARCH_NR_GPIOS 512 #include <asm-generic/gpio.h> #ifdef CONFIG_GPIOLIB diff --git a/arch/sh/kernel/cpu/sh3/entry.S b/arch/sh/kernel/cpu/sh3/entry.S index 25eb80905416..e48b3dd996f5 100644 --- a/arch/sh/kernel/cpu/sh3/entry.S +++ b/arch/sh/kernel/cpu/sh3/entry.S @@ -14,7 +14,6 @@ #include <cpu/mmu_context.h> #include <asm/page.h> #include <asm/cache.h> -#include <asm/thread_info.h> ! NOTE: ! GNU as (as of 2.9.1) changes bf/s into bt/s and bra, when the address diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig index 703d3069997c..77aa2f802d8d 100644 --- a/arch/sh/mm/Kconfig +++ b/arch/sh/mm/Kconfig @@ -105,7 +105,7 @@ config VSYSCALL (the default value) say Y. config NUMA - bool "Non Uniform Memory Access (NUMA) Support" + bool "Non-Uniform Memory Access (NUMA) Support" depends on MMU && SYS_SUPPORTS_NUMA select ARCH_WANT_NUMA_VARIABLE_LOCALITY default n diff --git a/arch/sh/mm/asids-debugfs.c b/arch/sh/mm/asids-debugfs.c index 4c1ca197e9c5..d16d6f5ec774 100644 --- a/arch/sh/mm/asids-debugfs.c +++ b/arch/sh/mm/asids-debugfs.c @@ -26,7 +26,7 @@ #include <asm/processor.h> #include <asm/mmu_context.h> -static int asids_seq_show(struct seq_file *file, void *iter) +static int asids_debugfs_show(struct seq_file *file, void *iter) { struct task_struct *p; @@ -48,18 +48,7 @@ static int asids_seq_show(struct seq_file *file, void *iter) return 0; } -static int asids_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, asids_seq_show, inode->i_private); -} - -static const struct file_operations asids_debugfs_fops = { - .owner = THIS_MODULE, - .open = asids_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(asids_debugfs); static int __init asids_debugfs_init(void) { diff --git a/arch/sh/mm/cache-debugfs.c b/arch/sh/mm/cache-debugfs.c index 17d780794497..b0f185169dfa 100644 --- a/arch/sh/mm/cache-debugfs.c +++ b/arch/sh/mm/cache-debugfs.c @@ -22,7 +22,7 @@ enum cache_type { CACHE_TYPE_UNIFIED, }; -static int cache_seq_show(struct seq_file *file, void *iter) +static int cache_debugfs_show(struct seq_file *file, void *iter) { unsigned int cache_type = (unsigned int)file->private; struct cache_info *cache; @@ -94,18 +94,7 @@ static int cache_seq_show(struct seq_file *file, void *iter) return 0; } -static int cache_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, cache_seq_show, inode->i_private); -} - -static const struct file_operations cache_debugfs_fops = { - .owner = THIS_MODULE, - .open = cache_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(cache_debugfs); static int __init cache_debugfs_init(void) { diff --git a/arch/sh/mm/pmb.c b/arch/sh/mm/pmb.c index b20aba6e1b37..68eb7cc6e564 100644 --- a/arch/sh/mm/pmb.c +++ b/arch/sh/mm/pmb.c @@ -812,7 +812,7 @@ bool __in_29bit_mode(void) return (__raw_readl(PMB_PASCR) & PASCR_SE) == 0; } -static int pmb_seq_show(struct seq_file *file, void *iter) +static int pmb_debugfs_show(struct seq_file *file, void *iter) { int i; @@ -846,18 +846,7 @@ static int pmb_seq_show(struct seq_file *file, void *iter) return 0; } -static int pmb_debugfs_open(struct inode *inode, struct file *file) -{ - return single_open(file, pmb_seq_show, NULL); -} - -static const struct file_operations pmb_debugfs_fops = { - .owner = THIS_MODULE, - .open = pmb_debugfs_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(pmb_debugfs); static int __init pmb_debugfs_init(void) { diff --git a/arch/sparc/include/asm/highmem.h b/arch/sparc/include/asm/highmem.h index 875116209ec1..c7b2e208328b 100644 --- a/arch/sparc/include/asm/highmem.h +++ b/arch/sparc/include/asm/highmem.h @@ -50,10 +50,11 @@ extern pte_t *pkmap_page_table; #define flush_cache_kmaps() flush_cache_all() -/* FIXME: Use __flush_tlb_one(vaddr) instead of flush_cache_all() -- Anton */ -#define arch_kmap_local_post_map(vaddr, pteval) flush_cache_all() -#define arch_kmap_local_post_unmap(vaddr) flush_cache_all() - +/* FIXME: Use __flush_*_one(vaddr) instead of flush_*_all() -- Anton */ +#define arch_kmap_local_pre_map(vaddr, pteval) flush_cache_all() +#define arch_kmap_local_pre_unmap(vaddr) flush_cache_all() +#define arch_kmap_local_post_map(vaddr, pteval) flush_tlb_all() +#define arch_kmap_local_post_unmap(vaddr) flush_tlb_all() #endif /* __KERNEL__ */ diff --git a/arch/um/Kconfig b/arch/um/Kconfig index 34d302d1a07f..c3030db3325f 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -15,7 +15,6 @@ config UML select HAVE_DEBUG_KMEMLEAK select HAVE_DEBUG_BUGVERBOSE select NO_DMA - select ARCH_HAS_SET_MEMORY select GENERIC_IRQ_SHOW select GENERIC_CPU_DEVICES select HAVE_GCC_PLUGINS diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 13b1fe694b90..8e0b43cf089f 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -375,11 +375,11 @@ break_loop: file = NULL; backing_file = strsep(&str, ",:"); - if (*backing_file == '\0') + if (backing_file && *backing_file == '\0') backing_file = NULL; serial = strsep(&str, ",:"); - if (*serial == '\0') + if (serial && *serial == '\0') serial = NULL; if (backing_file && ubd_dev->no_cow) { @@ -1241,7 +1241,7 @@ static int __init ubd_driver_init(void){ /* Letting ubd=sync be like using ubd#s= instead of ubd#= is * enough. So use anyway the io thread. */ } - stack = alloc_stack(0); + stack = alloc_stack(0, 0); io_pid = start_io_thread(stack + PAGE_SIZE - sizeof(void *), &thread_fd); if(io_pid < 0){ diff --git a/arch/um/drivers/virtio_uml.c b/arch/um/drivers/virtio_uml.c index 27e92d3881ff..5d957b7e7fd5 100644 --- a/arch/um/drivers/virtio_uml.c +++ b/arch/um/drivers/virtio_uml.c @@ -1084,6 +1084,7 @@ static void virtio_uml_release_dev(struct device *d) } os_close_file(vu_dev->sock); + kfree(vu_dev); } /* Platform device */ @@ -1097,7 +1098,7 @@ static int virtio_uml_probe(struct platform_device *pdev) if (!pdata) return -EINVAL; - vu_dev = devm_kzalloc(&pdev->dev, sizeof(*vu_dev), GFP_KERNEL); + vu_dev = kzalloc(sizeof(*vu_dev), GFP_KERNEL); if (!vu_dev) return -ENOMEM; diff --git a/arch/um/include/asm/io.h b/arch/um/include/asm/io.h index 96f77b5232aa..cef03e3aa0f9 100644 --- a/arch/um/include/asm/io.h +++ b/arch/um/include/asm/io.h @@ -5,7 +5,7 @@ #define ioremap ioremap static inline void __iomem *ioremap(phys_addr_t offset, size_t size) { - return (void __iomem *)(unsigned long)offset; + return NULL; } #define iounmap iounmap diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h index 39376bb63abf..def376194dce 100644 --- a/arch/um/include/asm/pgtable.h +++ b/arch/um/include/asm/pgtable.h @@ -55,15 +55,12 @@ extern unsigned long end_iomem; #define _PAGE_CHG_MASK (PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY) #define __PAGE_KERNEL_EXEC \ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED) -#define __PAGE_KERNEL_RO \ - (_PAGE_PRESENT | _PAGE_DIRTY | _PAGE_ACCESSED) #define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED) #define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED) #define PAGE_COPY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED) #define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED) #define PAGE_KERNEL __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED) #define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC) -#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO) /* * The i386 can't do page protection for execute, and considers that the same diff --git a/arch/um/include/asm/set_memory.h b/arch/um/include/asm/set_memory.h deleted file mode 100644 index 24266c63720d..000000000000 --- a/arch/um/include/asm/set_memory.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/set_memory.h> diff --git a/arch/um/include/shared/kern_util.h b/arch/um/include/shared/kern_util.h index d8c279e3312f..2888ec812f6e 100644 --- a/arch/um/include/shared/kern_util.h +++ b/arch/um/include/shared/kern_util.h @@ -19,7 +19,7 @@ extern int kmalloc_ok; #define UML_ROUND_UP(addr) \ ((((unsigned long) addr) + PAGE_SIZE - 1) & PAGE_MASK) -extern unsigned long alloc_stack(int atomic); +extern unsigned long alloc_stack(int order, int atomic); extern void free_stack(unsigned long stack, int order); struct pt_regs; diff --git a/arch/um/kernel/kmsg_dump.c b/arch/um/kernel/kmsg_dump.c index e4abac6c9727..6516ef1f8274 100644 --- a/arch/um/kernel/kmsg_dump.c +++ b/arch/um/kernel/kmsg_dump.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/kmsg_dump.h> #include <linux/console.h> +#include <linux/string.h> #include <shared/init.h> #include <shared/kern.h> #include <os.h> @@ -16,8 +17,12 @@ static void kmsg_dumper_stdout(struct kmsg_dumper *dumper, if (!console_trylock()) return; - for_each_console(con) - break; + for_each_console(con) { + if(strcmp(con->name, "tty") == 0 && + (con->flags & (CON_ENABLED | CON_CONSDEV)) != 0) { + break; + } + } console_unlock(); diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index 2a986ece5478..81d508daf67c 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -32,7 +32,6 @@ #include <os.h> #include <skas.h> #include <linux/time-internal.h> -#include <asm/set_memory.h> /* * This is a per-cpu array. A processor only modifies its entry and it only @@ -63,18 +62,16 @@ void free_stack(unsigned long stack, int order) free_pages(stack, order); } -unsigned long alloc_stack(int atomic) +unsigned long alloc_stack(int order, int atomic) { - unsigned long addr; + unsigned long page; gfp_t flags = GFP_KERNEL; if (atomic) flags = GFP_ATOMIC; - addr = __get_free_pages(flags, 1); + page = __get_free_pages(flags, order); - set_memory_ro(addr, 1); - - return addr + PAGE_SIZE; + return page; } static inline void set_current(struct task_struct *task) diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index f4db89b5b5a6..315248b03941 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -535,6 +535,31 @@ invalid_number: return 1; } + +static void time_travel_set_start(void) +{ + if (time_travel_start_set) + return; + + switch (time_travel_mode) { + case TT_MODE_EXTERNAL: + time_travel_start = time_travel_ext_req(UM_TIMETRAVEL_GET_TOD, -1); + /* controller gave us the *current* time, so adjust by that */ + time_travel_ext_get_time(); + time_travel_start -= time_travel_time; + break; + case TT_MODE_INFCPU: + case TT_MODE_BASIC: + if (!time_travel_start_set) + time_travel_start = os_persistent_clock_emulation(); + break; + case TT_MODE_OFF: + /* we just read the host clock with os_persistent_clock_emulation() */ + break; + } + + time_travel_start_set = true; +} #else /* CONFIG_UML_TIME_TRAVEL_SUPPORT */ #define time_travel_start_set 0 #define time_travel_start 0 @@ -553,6 +578,10 @@ static void time_travel_set_interval(unsigned long long interval) { } +static inline void time_travel_set_start(void) +{ +} + /* fail link if this actually gets used */ extern u64 time_travel_ext_req(u32 op, u64 time); @@ -731,6 +760,8 @@ void read_persistent_clock64(struct timespec64 *ts) { long long nsecs; + time_travel_set_start(); + if (time_travel_mode != TT_MODE_OFF) nsecs = time_travel_start + time_travel_time; else @@ -742,25 +773,6 @@ void read_persistent_clock64(struct timespec64 *ts) void __init time_init(void) { -#ifdef CONFIG_UML_TIME_TRAVEL_SUPPORT - switch (time_travel_mode) { - case TT_MODE_EXTERNAL: - time_travel_start = time_travel_ext_req(UM_TIMETRAVEL_GET_TOD, -1); - /* controller gave us the *current* time, so adjust by that */ - time_travel_ext_get_time(); - time_travel_start -= time_travel_time; - break; - case TT_MODE_INFCPU: - case TT_MODE_BASIC: - if (!time_travel_start_set) - time_travel_start = os_persistent_clock_emulation(); - break; - case TT_MODE_OFF: - /* we just read the host clock with os_persistent_clock_emulation() */ - break; - } -#endif - timer_set_signal_handler(); late_time_init = um_timer_setup; } diff --git a/arch/um/kernel/tlb.c b/arch/um/kernel/tlb.c index 437d1f1cc5ec..61776790cd67 100644 --- a/arch/um/kernel/tlb.c +++ b/arch/um/kernel/tlb.c @@ -608,57 +608,3 @@ void force_flush_all(void) vma = vma->vm_next; } } - -struct page_change_data { - unsigned int set_mask, clear_mask; -}; - -static int change_page_range(pte_t *ptep, unsigned long addr, void *data) -{ - struct page_change_data *cdata = data; - pte_t pte = READ_ONCE(*ptep); - - pte_clear_bits(pte, cdata->clear_mask); - pte_set_bits(pte, cdata->set_mask); - - set_pte(ptep, pte); - return 0; -} - -static int change_memory(unsigned long start, unsigned long pages, - unsigned int set_mask, unsigned int clear_mask) -{ - unsigned long size = pages * PAGE_SIZE; - struct page_change_data data; - int ret; - - data.set_mask = set_mask; - data.clear_mask = clear_mask; - - ret = apply_to_page_range(&init_mm, start, size, change_page_range, - &data); - - flush_tlb_kernel_range(start, start + size); - - return ret; -} - -int set_memory_ro(unsigned long addr, int numpages) -{ - return change_memory(addr, numpages, 0, _PAGE_RW); -} - -int set_memory_rw(unsigned long addr, int numpages) -{ - return change_memory(addr, numpages, _PAGE_RW, 0); -} - -int set_memory_nx(unsigned long addr, int numpages) -{ - return -EOPNOTSUPP; -} - -int set_memory_x(unsigned long addr, int numpages) -{ - return -EOPNOTSUPP; -} diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 31d356b1ffd8..80e2660782a0 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -26,7 +26,8 @@ #include <mem_user.h> #include <os.h> -#define DEFAULT_COMMAND_LINE "root=98:0" +#define DEFAULT_COMMAND_LINE_ROOT "root=98:0" +#define DEFAULT_COMMAND_LINE_CONSOLE "console=tty" /* Changed in add_arg and setup_arch, which run before SMP is started */ static char __initdata command_line[COMMAND_LINE_SIZE] = { 0 }; @@ -109,7 +110,8 @@ unsigned long end_vm; int ncpus = 1; /* Set in early boot */ -static int have_root __initdata = 0; +static int have_root __initdata; +static int have_console __initdata; /* Set in uml_mem_setup and modified in linux_main */ long long physmem_size = 32 * 1024 * 1024; @@ -161,6 +163,17 @@ __uml_setup("debug", no_skas_debug_setup, " this flag is not needed to run gdb on UML in skas mode\n\n" ); +static int __init uml_console_setup(char *line, int *add) +{ + have_console = 1; + return 0; +} + +__uml_setup("console=", uml_console_setup, +"console=<preferred console>\n" +" Specify the preferred console output driver\n\n" +); + static int __init Usage(char *line, int *add) { const char **p; @@ -264,7 +277,10 @@ int __init linux_main(int argc, char **argv) add_arg(argv[i]); } if (have_root == 0) - add_arg(DEFAULT_COMMAND_LINE); + add_arg(DEFAULT_COMMAND_LINE_ROOT); + + if (have_console == 0) + add_arg(DEFAULT_COMMAND_LINE_CONSOLE); host_task_size = os_get_top_address(); /* diff --git a/arch/um/os-Linux/helper.c b/arch/um/os-Linux/helper.c index feb48d796e00..9fa6e4187d4f 100644 --- a/arch/um/os-Linux/helper.c +++ b/arch/um/os-Linux/helper.c @@ -45,7 +45,7 @@ int run_helper(void (*pre_exec)(void *), void *pre_data, char **argv) unsigned long stack, sp; int pid, fds[2], ret, n; - stack = alloc_stack(__cant_sleep()); + stack = alloc_stack(0, __cant_sleep()); if (stack == 0) return -ENOMEM; @@ -116,7 +116,7 @@ int run_helper_thread(int (*proc)(void *), void *arg, unsigned int flags, unsigned long stack, sp; int pid, status, err; - stack = alloc_stack(__cant_sleep()); + stack = alloc_stack(0, __cant_sleep()); if (stack == 0) return -ENOMEM; diff --git a/arch/um/os-Linux/time.c b/arch/um/os-Linux/time.c index a61cbf73a179..6c5041c5560b 100644 --- a/arch/um/os-Linux/time.c +++ b/arch/um/os-Linux/time.c @@ -104,5 +104,18 @@ long long os_nsecs(void) */ void os_idle_sleep(void) { - pause(); + struct itimerspec its; + sigset_t set, old; + + /* block SIGALRM while we analyze the timer state */ + sigemptyset(&set); + sigaddset(&set, SIGALRM); + sigprocmask(SIG_BLOCK, &set, &old); + + /* check the timer, and if it'll fire then wait for it */ + timer_gettime(event_high_res_timer, &its); + if (its.it_value.tv_sec || its.it_value.tv_nsec) + sigsuspend(&old); + /* either way, restore the signal mask */ + sigprocmask(SIG_UNBLOCK, &set, NULL); } diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7b6dd10b162a..21f851179ff0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -19,6 +19,7 @@ config X86_32 select KMAP_LOCAL select MODULES_USE_ELF_REL select OLD_SIGACTION + select ARCH_SPLIT_ARG64 config X86_64 def_bool y diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 7116da3980be..5857917f83ee 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -120,6 +120,9 @@ else KBUILD_CFLAGS += -mno-red-zone KBUILD_CFLAGS += -mcmodel=kernel + + # Intel CET isn't enabled in the kernel + KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none) endif ifdef CONFIG_X86_X32 diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 18d8f17f755c..0904f5676e4d 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -73,10 +73,8 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, unsigned int nr) { if (likely(nr < IA32_NR_syscalls)) { - instrumentation_begin(); nr = array_index_nospec(nr, IA32_NR_syscalls); regs->ax = ia32_sys_call_table[nr](regs); - instrumentation_end(); } } @@ -91,8 +89,11 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) * or may not be necessary, but it matches the old asm behavior. */ nr = (unsigned int)syscall_enter_from_user_mode(regs, nr); + instrumentation_begin(); do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); syscall_exit_to_user_mode(regs); } @@ -121,11 +122,12 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) res = get_user(*(u32 *)®s->bp, (u32 __user __force *)(unsigned long)(u32)regs->sp); } - instrumentation_end(); if (res) { /* User code screwed up. */ regs->ax = -EFAULT; + + instrumentation_end(); syscall_exit_to_user_mode(regs); return false; } @@ -135,6 +137,8 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) /* Now this is just like a normal syscall. */ do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); syscall_exit_to_user_mode(regs); return true; } diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S index ccd32877a3c4..496b11ec469d 100644 --- a/arch/x86/entry/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -10,7 +10,7 @@ #include <asm/export.h> /* rdi: arg1 ... normal C conventions. rax is saved/restored. */ - .macro THUNK name, func, put_ret_addr_in_rdi=0 + .macro THUNK name, func SYM_FUNC_START_NOALIGN(\name) pushq %rbp movq %rsp, %rbp @@ -25,13 +25,8 @@ SYM_FUNC_START_NOALIGN(\name) pushq %r10 pushq %r11 - .if \put_ret_addr_in_rdi - /* 8(%rbp) is return addr on stack */ - movq 8(%rbp), %rdi - .endif - call \func - jmp .L_restore + jmp __thunk_restore SYM_FUNC_END(\name) _ASM_NOKPROBE(\name) .endm @@ -44,7 +39,7 @@ SYM_FUNC_END(\name) #endif #ifdef CONFIG_PREEMPTION -SYM_CODE_START_LOCAL_NOALIGN(.L_restore) +SYM_CODE_START_LOCAL_NOALIGN(__thunk_restore) popq %r11 popq %r10 popq %r9 @@ -56,6 +51,6 @@ SYM_CODE_START_LOCAL_NOALIGN(.L_restore) popq %rdi popq %rbp ret - _ASM_NOKPROBE(.L_restore) -SYM_CODE_END(.L_restore) + _ASM_NOKPROBE(__thunk_restore) +SYM_CODE_END(__thunk_restore) #endif diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index e04d90af4c27..6375967a8244 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -16,6 +16,7 @@ #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> #include <asm/idtentry.h> +#include <linux/kexec.h> #include <linux/version.h> #include <linux/vmalloc.h> #include <linux/mm.h> @@ -26,6 +27,8 @@ #include <linux/syscore_ops.h> #include <clocksource/hyperv_timer.h> +int hyperv_init_cpuhp; + void *hv_hypercall_pg; EXPORT_SYMBOL_GPL(hv_hypercall_pg); @@ -312,6 +315,25 @@ static struct syscore_ops hv_syscore_ops = { .resume = hv_resume, }; +static void (* __initdata old_setup_percpu_clockev)(void); + +static void __init hv_stimer_setup_percpu_clockev(void) +{ + /* + * Ignore any errors in setting up stimer clockevents + * as we can run with the LAPIC timer as a fallback. + */ + (void)hv_stimer_alloc(); + + /* + * Still register the LAPIC timer, because the direct-mode STIMER is + * not supported by old versions of Hyper-V. This also allows users + * to switch to LAPIC timer via /sys, if they want to. + */ + if (old_setup_percpu_clockev) + old_setup_percpu_clockev(); +} + /* * This function is to be invoked early in the boot sequence after the * hypervisor has been detected. @@ -390,10 +412,14 @@ void __init hyperv_init(void) wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); /* - * Ignore any errors in setting up stimer clockevents - * as we can run with the LAPIC timer as a fallback. + * hyperv_init() is called before LAPIC is initialized: see + * apic_intr_mode_init() -> x86_platform.apic_post_init() and + * apic_bsp_setup() -> setup_local_APIC(). The direct-mode STIMER + * depends on LAPIC, so hv_stimer_alloc() should be called from + * x86_init.timers.setup_percpu_clockev. */ - (void)hv_stimer_alloc(); + old_setup_percpu_clockev = x86_init.timers.setup_percpu_clockev; + x86_init.timers.setup_percpu_clockev = hv_stimer_setup_percpu_clockev; hv_apic_init(); @@ -401,6 +427,7 @@ void __init hyperv_init(void) register_syscore_ops(&hv_syscore_ops); + hyperv_init_cpuhp = cpuhp; return; remove_cpuhp_state: diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c index 5208ba49c89a..2c87350c1fb0 100644 --- a/arch/x86/hyperv/mmu.c +++ b/arch/x86/hyperv/mmu.c @@ -66,11 +66,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus, if (!hv_hypercall_pg) goto do_native; - if (cpumask_empty(cpus)) - return; - local_irq_save(flags); + /* + * Only check the mask _after_ interrupt has been disabled to avoid the + * mask changing under our feet. + */ + if (cpumask_empty(cpus)) { + local_irq_restore(flags); + return; + } + flush_pcpu = (struct hv_tlb_flush **) this_cpu_ptr(hyperv_pcpu_input_arg); diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 34cb3c159481..412b51e059c8 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -197,16 +197,6 @@ static inline bool apic_needs_pit(void) { return true; } #endif /* !CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_X2APIC -/* - * Make previous memory operations globally visible before - * sending the IPI through x2apic wrmsr. We need a serializing instruction or - * mfence for this. - */ -static inline void x2apic_wrmsr_fence(void) -{ - asm volatile("mfence" : : : "memory"); -} - static inline void native_apic_msr_write(u32 reg, u32 v) { if (reg == APIC_DFR || reg == APIC_ID || reg == APIC_LDR || diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 7f828fe49797..4819d5e5a335 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -84,4 +84,22 @@ do { \ #include <asm-generic/barrier.h> +/* + * Make previous memory operations globally visible before + * a WRMSR. + * + * MFENCE makes writes visible, but only affects load/store + * instructions. WRMSR is unfortunately not a load/store + * instruction and is unaffected by MFENCE. The LFENCE ensures + * that the WRMSR is not reordered. + * + * Most WRMSRs are full serializing instructions themselves and + * do not require this barrier. This is only required for the + * IA32_TSC_DEADLINE and X2APIC MSRs. + */ +static inline void weak_wrmsr_fence(void) +{ + asm volatile("mfence; lfence" : : : "memory"); +} + #endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index 6fe54b2813c1..2b87b191b3b8 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -43,8 +43,6 @@ static __always_inline void arch_check_user_regs(struct pt_regs *regs) } #define arch_check_user_regs arch_check_user_regs -#define ARCH_SYSCALL_EXIT_WORK (_TIF_SINGLESTEP) - static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, unsigned long ti_work) { diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index a5aba4ab0224..67a4f1cb2aac 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -16,14 +16,25 @@ * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It * disables preemption so be careful if you intend to use it for long periods * of time. - * If you intend to use the FPU in softirq you need to check first with + * If you intend to use the FPU in irq/softirq you need to check first with * irq_fpu_usable() if it is possible. */ -extern void kernel_fpu_begin(void); + +/* Kernel FPU states to initialize in kernel_fpu_begin_mask() */ +#define KFPU_387 _BITUL(0) /* 387 state will be initialized */ +#define KFPU_MXCSR _BITUL(1) /* MXCSR will be initialized */ + +extern void kernel_fpu_begin_mask(unsigned int kfpu_mask); extern void kernel_fpu_end(void); extern bool irq_fpu_usable(void); extern void fpregs_mark_activate(void); +/* Code that is unaware of kernel_fpu_begin_mask() can use this */ +static inline void kernel_fpu_begin(void) +{ + kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR); +} + /* * Use fpregs_lock() while editing CPU's FPU registers or fpu->state. * A context switch will (and softirq might) save CPU's FPU registers to diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 247a60a47331..f656aabd1545 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -613,6 +613,7 @@ DECLARE_IDTENTRY_VC(X86_TRAP_VC, exc_vmm_communication); #ifdef CONFIG_XEN_PV DECLARE_IDTENTRY_XENCB(X86_TRAP_OTHER, exc_xen_hypervisor_callback); +DECLARE_IDTENTRY_RAW(X86_TRAP_OTHER, exc_xen_unknown_trap); #endif /* Device interrupts common/spurious */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 5e658ba2654a..9abe842dbd84 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -97,6 +97,7 @@ #define INTEL_FAM6_LAKEFIELD 0x8A #define INTEL_FAM6_ALDERLAKE 0x97 +#define INTEL_FAM6_ALDERLAKE_L 0x9A /* "Small Core" Processors (Atom) */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 3ab7b46087b7..3d6616f6f6ef 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1010,9 +1010,21 @@ struct kvm_arch { */ bool tdp_mmu_enabled; - /* List of struct tdp_mmu_pages being used as roots */ + /* + * List of struct kvmp_mmu_pages being used as roots. + * All struct kvm_mmu_pages in the list should have + * tdp_mmu_page set. + * All struct kvm_mmu_pages in the list should have a positive + * root_count except when a thread holds the MMU lock and is removing + * an entry from the list. + */ struct list_head tdp_mmu_roots; - /* List of struct tdp_mmu_pages not being used as roots */ + + /* + * List of struct kvmp_mmu_pages not being used as roots. + * All struct kvm_mmu_pages in the list should have + * tdp_mmu_page set and a root_count of 0. + */ struct list_head tdp_mmu_pages; }; @@ -1287,6 +1299,8 @@ struct kvm_x86_ops { void (*migrate_timers)(struct kvm_vcpu *vcpu); void (*msr_filter_changed)(struct kvm_vcpu *vcpu); int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err); + + void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector); }; struct kvm_x86_nested_ops { @@ -1468,6 +1482,7 @@ int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in); int kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); int kvm_vcpu_halt(struct kvm_vcpu *vcpu); +int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index ffc289992d1b..30f76b966857 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -74,6 +74,8 @@ static inline void hv_disable_stimer0_percpu_irq(int irq) {} #if IS_ENABLED(CONFIG_HYPERV) +extern int hyperv_init_cpuhp; + extern void *hv_hypercall_pg; extern void __percpu **hyperv_pcpu_input_arg; diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 0b4920a7238e..e16cccdd0420 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -86,7 +86,7 @@ static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {} * think of extending them - you will be slapped with a stinking trout or a frozen * shark will reach you, wherever you are! You've been warned. */ -static inline unsigned long long notrace __rdmsr(unsigned int msr) +static __always_inline unsigned long long __rdmsr(unsigned int msr) { DECLARE_ARGS(val, low, high); @@ -98,7 +98,7 @@ static inline unsigned long long notrace __rdmsr(unsigned int msr) return EAX_EDX_VAL(val, low, high); } -static inline void notrace __wrmsr(unsigned int msr, u32 low, u32 high) +static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high) { asm volatile("1: wrmsr\n" "2:\n" diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 488a8e848754..9239399e5491 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -110,6 +110,8 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); #define topology_die_id(cpu) (cpu_data(cpu).cpu_die_id) #define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id) +extern unsigned int __max_die_per_package; + #ifdef CONFIG_SMP #define topology_die_cpumask(cpu) (per_cpu(cpu_die_map, cpu)) #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) @@ -118,8 +120,6 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu); extern unsigned int __max_logical_packages; #define topology_max_packages() (__max_logical_packages) -extern unsigned int __max_die_per_package; - static inline int topology_max_die_per_package(void) { return __max_die_per_package; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 6bd20c0de8bc..7f4c081f59f0 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -41,6 +41,7 @@ #include <asm/perf_event.h> #include <asm/x86_init.h> #include <linux/atomic.h> +#include <asm/barrier.h> #include <asm/mpspec.h> #include <asm/i8259.h> #include <asm/proto.h> @@ -477,6 +478,9 @@ static int lapic_next_deadline(unsigned long delta, { u64 tsc; + /* This MSR is special and need a special fence: */ + weak_wrmsr_fence(); + tsc = rdtsc(); wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR)); return 0; diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index df6adc5674c9..f4da9bb69a88 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -29,7 +29,8 @@ static void x2apic_send_IPI(int cpu, int vector) { u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu); - x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence(); __x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL); } @@ -41,7 +42,8 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) unsigned long flags; u32 dest; - x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence(); local_irq_save(flags); tmpmsk = this_cpu_cpumask_var_ptr(ipi_mask); diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 0e4e81971567..6bde05a86b4e 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -43,7 +43,8 @@ static void x2apic_send_IPI(int cpu, int vector) { u32 dest = per_cpu(x86_cpu_to_apicid, cpu); - x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence(); __x2apic_send_IPI_dest(dest, vector, APIC_DEST_PHYSICAL); } @@ -54,7 +55,8 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) unsigned long this_cpu; unsigned long flags; - x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence(); local_irq_save(flags); @@ -125,7 +127,8 @@ void __x2apic_send_IPI_shorthand(int vector, u32 which) { unsigned long cfg = __prepare_ICR(which, vector, 0); - x2apic_wrmsr_fence(); + /* x2apic MSRs are special and need a special fence: */ + weak_wrmsr_fence(); native_x2apic_icr_write(cfg, 0); } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index f8ca66f3d861..347a956f71ca 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -542,12 +542,12 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) u32 ecx; ecx = cpuid_ecx(0x8000001e); - nodes_per_socket = ((ecx >> 8) & 7) + 1; + __max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1; } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - nodes_per_socket = ((value >> 3) & 7) + 1; + __max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1; } if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 59a1e3ce3f14..816fdbec795a 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -1159,6 +1159,7 @@ static const struct x86_cpu_id split_lock_cpu_ids[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, 1), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, 1), X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, 1), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, 1), {} }; diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 13d3f1cbda17..e133ce1e562b 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1992,10 +1992,9 @@ static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) * that out because it's an indirect call. Annotate it. */ instrumentation_begin(); - trace_hardirqs_off_finish(); + machine_check_vector(regs); - if (regs->flags & X86_EFLAGS_IF) - trace_hardirqs_on_prepare(); + instrumentation_end(); irqentry_nmi_exit(regs, irq_state); } @@ -2004,7 +2003,9 @@ static __always_inline void exc_machine_check_user(struct pt_regs *regs) { irqentry_enter_from_user_mode(regs); instrumentation_begin(); + machine_check_vector(regs); + instrumentation_end(); irqentry_exit_to_user_mode(regs); } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index f628e3dc150f..43b54bef5448 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -135,14 +135,32 @@ static void hv_machine_shutdown(void) { if (kexec_in_progress && hv_kexec_handler) hv_kexec_handler(); + + /* + * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor + * corrupts the old VP Assist Pages and can crash the kexec kernel. + */ + if (kexec_in_progress && hyperv_init_cpuhp > 0) + cpuhp_remove_state(hyperv_init_cpuhp); + + /* The function calls stop_other_cpus(). */ native_machine_shutdown(); + + /* Disable the hypercall page when there is only 1 active CPU. */ + if (kexec_in_progress) + hyperv_cleanup(); } static void hv_machine_crash_shutdown(struct pt_regs *regs) { if (hv_crash_handler) hv_crash_handler(regs); + + /* The function calls crash_smp_send_stop(). */ native_machine_crash_shutdown(regs); + + /* Disable the hypercall page when there is only 1 active CPU. */ + hyperv_cleanup(); } #endif /* CONFIG_KEXEC_CORE */ #endif /* CONFIG_HYPERV */ diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 23ad8e953dfb..a29997e6cf9e 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -167,9 +167,6 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end, *repeat = 0; *uniform = 1; - /* Make end inclusive instead of exclusive */ - end--; - prev_match = MTRR_TYPE_INVALID; for (i = 0; i < num_var_ranges; ++i) { unsigned short start_state, end_state, inclusive; @@ -261,6 +258,9 @@ u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform) int repeat; u64 partial_end; + /* Make end inclusive instead of exclusive */ + end--; + if (!mtrr_state_set) return MTRR_TYPE_INVALID; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 29ffb95b25ff..460f3e0df106 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -525,89 +525,70 @@ static void rdtgroup_remove(struct rdtgroup *rdtgrp) kfree(rdtgrp); } -struct task_move_callback { - struct callback_head work; - struct rdtgroup *rdtgrp; -}; - -static void move_myself(struct callback_head *head) +static void _update_task_closid_rmid(void *task) { - struct task_move_callback *callback; - struct rdtgroup *rdtgrp; - - callback = container_of(head, struct task_move_callback, work); - rdtgrp = callback->rdtgrp; - /* - * If resource group was deleted before this task work callback - * was invoked, then assign the task to root group and free the - * resource group. + * If the task is still current on this CPU, update PQR_ASSOC MSR. + * Otherwise, the MSR is updated when the task is scheduled in. */ - if (atomic_dec_and_test(&rdtgrp->waitcount) && - (rdtgrp->flags & RDT_DELETED)) { - current->closid = 0; - current->rmid = 0; - rdtgroup_remove(rdtgrp); - } - - if (unlikely(current->flags & PF_EXITING)) - goto out; - - preempt_disable(); - /* update PQR_ASSOC MSR to make resource group go into effect */ - resctrl_sched_in(); - preempt_enable(); + if (task == current) + resctrl_sched_in(); +} -out: - kfree(callback); +static void update_task_closid_rmid(struct task_struct *t) +{ + if (IS_ENABLED(CONFIG_SMP) && task_curr(t)) + smp_call_function_single(task_cpu(t), _update_task_closid_rmid, t, 1); + else + _update_task_closid_rmid(t); } static int __rdtgroup_move_task(struct task_struct *tsk, struct rdtgroup *rdtgrp) { - struct task_move_callback *callback; - int ret; - - callback = kzalloc(sizeof(*callback), GFP_KERNEL); - if (!callback) - return -ENOMEM; - callback->work.func = move_myself; - callback->rdtgrp = rdtgrp; + /* If the task is already in rdtgrp, no need to move the task. */ + if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid && + tsk->rmid == rdtgrp->mon.rmid) || + (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid && + tsk->closid == rdtgrp->mon.parent->closid)) + return 0; /* - * Take a refcount, so rdtgrp cannot be freed before the - * callback has been invoked. + * Set the task's closid/rmid before the PQR_ASSOC MSR can be + * updated by them. + * + * For ctrl_mon groups, move both closid and rmid. + * For monitor groups, can move the tasks only from + * their parent CTRL group. */ - atomic_inc(&rdtgrp->waitcount); - ret = task_work_add(tsk, &callback->work, TWA_RESUME); - if (ret) { - /* - * Task is exiting. Drop the refcount and free the callback. - * No need to check the refcount as the group cannot be - * deleted before the write function unlocks rdtgroup_mutex. - */ - atomic_dec(&rdtgrp->waitcount); - kfree(callback); - rdt_last_cmd_puts("Task exited\n"); - } else { - /* - * For ctrl_mon groups move both closid and rmid. - * For monitor groups, can move the tasks only from - * their parent CTRL group. - */ - if (rdtgrp->type == RDTCTRL_GROUP) { - tsk->closid = rdtgrp->closid; + + if (rdtgrp->type == RDTCTRL_GROUP) { + tsk->closid = rdtgrp->closid; + tsk->rmid = rdtgrp->mon.rmid; + } else if (rdtgrp->type == RDTMON_GROUP) { + if (rdtgrp->mon.parent->closid == tsk->closid) { tsk->rmid = rdtgrp->mon.rmid; - } else if (rdtgrp->type == RDTMON_GROUP) { - if (rdtgrp->mon.parent->closid == tsk->closid) { - tsk->rmid = rdtgrp->mon.rmid; - } else { - rdt_last_cmd_puts("Can't move task to different control group\n"); - ret = -EINVAL; - } + } else { + rdt_last_cmd_puts("Can't move task to different control group\n"); + return -EINVAL; } } - return ret; + + /* + * Ensure the task's closid and rmid are written before determining if + * the task is current that will decide if it will be interrupted. + */ + barrier(); + + /* + * By now, the task's closid and rmid are set. If the task is current + * on a CPU, the PQR_ASSOC MSR needs to be updated to make the resource + * group go into effect. If the task is not current, the MSR will be + * updated when the task is scheduled in. + */ + update_task_closid_rmid(tsk); + + return 0; } static bool is_closid_match(struct task_struct *t, struct rdtgroup *r) diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 1068002c8532..8678864ce712 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -25,10 +25,10 @@ #define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f) #define LEVEL_MAX_SIBLINGS(ebx) ((ebx) & 0xffff) -#ifdef CONFIG_SMP unsigned int __max_die_per_package __read_mostly = 1; EXPORT_SYMBOL(__max_die_per_package); +#ifdef CONFIG_SMP /* * Check if given CPUID extended toplogy "leaf" is implemented */ diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index eb86a2b831b1..571220ac8bea 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -121,7 +121,7 @@ int copy_fpregs_to_fpstate(struct fpu *fpu) } EXPORT_SYMBOL(copy_fpregs_to_fpstate); -void kernel_fpu_begin(void) +void kernel_fpu_begin_mask(unsigned int kfpu_mask) { preempt_disable(); @@ -141,13 +141,14 @@ void kernel_fpu_begin(void) } __cpu_invalidate_fpregs_state(); - if (boot_cpu_has(X86_FEATURE_XMM)) + /* Put sane initial values into the control registers. */ + if (likely(kfpu_mask & KFPU_MXCSR) && boot_cpu_has(X86_FEATURE_XMM)) ldmxcsr(MXCSR_DEFAULT); - if (boot_cpu_has(X86_FEATURE_FPU)) + if (unlikely(kfpu_mask & KFPU_387) && boot_cpu_has(X86_FEATURE_FPU)) asm volatile ("fninit"); } -EXPORT_SYMBOL_GPL(kernel_fpu_begin); +EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask); void kernel_fpu_end(void) { diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 03aa33b58165..668a4a6533d9 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -269,6 +269,20 @@ static inline bool within_cpu_entry(unsigned long addr, unsigned long end) CPU_ENTRY_AREA_TOTAL_SIZE)) return true; + /* + * When FSGSBASE is enabled, paranoid_entry() fetches the per-CPU + * GSBASE value via __per_cpu_offset or pcpu_unit_offsets. + */ +#ifdef CONFIG_SMP + if (within_area(addr, end, (unsigned long)__per_cpu_offset, + sizeof(unsigned long) * nr_cpu_ids)) + return true; +#else + if (within_area(addr, end, (unsigned long)&pcpu_unit_offsets, + sizeof(pcpu_unit_offsets))) + return true; +#endif + for_each_possible_cpu(cpu) { /* The original rw GDT is being used after load_direct_gdt() */ if (within_area(addr, end, (unsigned long)get_cpu_gdt_rw(cpu), @@ -293,6 +307,14 @@ static inline bool within_cpu_entry(unsigned long addr, unsigned long end) (unsigned long)&per_cpu(cpu_tlbstate, cpu), sizeof(struct tlb_state))) return true; + + /* + * When in guest (X86_FEATURE_HYPERVISOR), local_db_save() + * will read per-cpu cpu_dr7 before clear dr7 register. + */ + if (within_area(addr, end, (unsigned long)&per_cpu(cpu_dr7, cpu), + sizeof(cpu_dr7))) + return true; } return false; @@ -491,15 +513,12 @@ static int hw_breakpoint_handler(struct die_args *args) struct perf_event *bp; unsigned long *dr6_p; unsigned long dr6; + bool bpx; /* The DR6 value is pointed by args->err */ dr6_p = (unsigned long *)ERR_PTR(args->err); dr6 = *dr6_p; - /* If it's a single step, TRAP bits are random */ - if (dr6 & DR_STEP) - return NOTIFY_DONE; - /* Do an early return if no trap bits are set in DR6 */ if ((dr6 & DR_TRAP_BITS) == 0) return NOTIFY_DONE; @@ -509,28 +528,29 @@ static int hw_breakpoint_handler(struct die_args *args) if (likely(!(dr6 & (DR_TRAP0 << i)))) continue; + bp = this_cpu_read(bp_per_reg[i]); + if (!bp) + continue; + + bpx = bp->hw.info.type == X86_BREAKPOINT_EXECUTE; + /* - * The counter may be concurrently released but that can only - * occur from a call_rcu() path. We can then safely fetch - * the breakpoint, use its callback, touch its counter - * while we are in an rcu_read_lock() path. + * TF and data breakpoints are traps and can be merged, however + * instruction breakpoints are faults and will be raised + * separately. + * + * However DR6 can indicate both TF and instruction + * breakpoints. In that case take TF as that has precedence and + * delay the instruction breakpoint for the next exception. */ - rcu_read_lock(); + if (bpx && (dr6 & DR_STEP)) + continue; - bp = this_cpu_read(bp_per_reg[i]); /* * Reset the 'i'th TRAP bit in dr6 to denote completion of * exception handling */ (*dr6_p) &= ~(DR_TRAP0 << i); - /* - * bp can be NULL due to lazy debug register switching - * or due to concurrent perf counter removing. - */ - if (!bp) { - rcu_read_unlock(); - break; - } perf_bp_event(bp, args->regs); @@ -538,11 +558,10 @@ static int hw_breakpoint_handler(struct die_args *args) * Set up resume flag to avoid breakpoint recursion when * returning back to origin. */ - if (bp->hw.info.type == X86_BREAKPOINT_EXECUTE) + if (bpx) args->regs->flags |= X86_EFLAGS_RF; - - rcu_read_unlock(); } + /* * Further processing in do_debug() is needed for a) user-space * breakpoints (to generate signals) and b) when the system has diff --git a/arch/x86/kernel/sev-es-shared.c b/arch/x86/kernel/sev-es-shared.c index 7d04b356d44d..cdc04d091242 100644 --- a/arch/x86/kernel/sev-es-shared.c +++ b/arch/x86/kernel/sev-es-shared.c @@ -305,14 +305,14 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) case 0xe4: case 0xe5: *exitinfo |= IOIO_TYPE_IN; - *exitinfo |= (u64)insn->immediate.value << 16; + *exitinfo |= (u8)insn->immediate.value << 16; break; /* OUT immediate opcodes */ case 0xe6: case 0xe7: *exitinfo |= IOIO_TYPE_OUT; - *exitinfo |= (u64)insn->immediate.value << 16; + *exitinfo |= (u8)insn->immediate.value << 16; break; /* IN register opcodes */ diff --git a/arch/x86/kernel/sev-es.c b/arch/x86/kernel/sev-es.c index 0bd1a0fc587e..84c1821819af 100644 --- a/arch/x86/kernel/sev-es.c +++ b/arch/x86/kernel/sev-es.c @@ -225,7 +225,7 @@ static inline u64 sev_es_rd_ghcb_msr(void) return __rdmsr(MSR_AMD64_SEV_ES_GHCB); } -static inline void sev_es_wr_ghcb_msr(u64 val) +static __always_inline void sev_es_wr_ghcb_msr(u64 val) { u32 low, high; @@ -286,6 +286,12 @@ static enum es_result vc_write_mem(struct es_em_ctxt *ctxt, u16 d2; u8 d1; + /* If instruction ran in kernel mode and the I/O buffer is in kernel space */ + if (!user_mode(ctxt->regs) && !access_ok(target, size)) { + memcpy(dst, buf, size); + return ES_OK; + } + switch (size) { case 1: memcpy(&d1, buf, 1); @@ -335,6 +341,12 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, u16 d2; u8 d1; + /* If instruction ran in kernel mode and the I/O buffer is in kernel space */ + if (!user_mode(ctxt->regs) && !access_ok(s, size)) { + memcpy(buf, src, size); + return ES_OK; + } + switch (size) { case 1: if (get_user(d1, s)) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 8ca66af96a54..02813a7f3a7c 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -56,6 +56,7 @@ #include <linux/numa.h> #include <linux/pgtable.h> #include <linux/overflow.h> +#include <linux/syscore_ops.h> #include <asm/acpi.h> #include <asm/desc.h> @@ -1832,6 +1833,7 @@ void arch_set_max_freq_ratio(bool turbo_disabled) arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE : arch_turbo_freq_ratio; } +EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio); static bool turbo_disabled(void) { @@ -2083,6 +2085,23 @@ static void init_counter_refs(void) this_cpu_write(arch_prev_mperf, mperf); } +#ifdef CONFIG_PM_SLEEP +static struct syscore_ops freq_invariance_syscore_ops = { + .resume = init_counter_refs, +}; + +static void register_freq_invariance_syscore_ops(void) +{ + /* Bail out if registered already. */ + if (freq_invariance_syscore_ops.node.prev) + return; + + register_syscore_ops(&freq_invariance_syscore_ops); +} +#else +static inline void register_freq_invariance_syscore_ops(void) {} +#endif + static void init_freq_invariance(bool secondary, bool cppc_ready) { bool ret = false; @@ -2109,6 +2128,7 @@ static void init_freq_invariance(bool secondary, bool cppc_ready) if (ret) { init_counter_refs(); static_branch_enable(&arch_scale_freq_key); + register_freq_invariance_syscore_ops(); pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); } else { pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n"); diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 60d2c3798ba2..0f3c307b37b3 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -127,12 +127,17 @@ static int enable_single_step(struct task_struct *child) regs->flags |= X86_EFLAGS_TF; /* - * Always set TIF_SINGLESTEP - this guarantees that - * we single-step system calls etc.. This will also + * Always set TIF_SINGLESTEP. This will also * cause us to set TF when returning to user mode. */ set_tsk_thread_flag(child, TIF_SINGLESTEP); + /* + * Ensure that a trap is triggered once stepping out of a system + * call prior to executing any user instruction. + */ + set_task_syscall_work(child, SYSCALL_EXIT_TRAP); + oflags = regs->flags; /* Set TF on the kernel stack.. */ @@ -230,6 +235,7 @@ void user_disable_single_step(struct task_struct *child) /* Always clear TIF_SINGLESTEP... */ clear_tsk_thread_flag(child, TIF_SINGLESTEP); + clear_task_syscall_work(child, SYSCALL_EXIT_TRAP); /* But touch TF only if it was set by us.. */ if (test_and_clear_tsk_thread_flag(child, TIF_FORCED_TF)) diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 13036cf0b912..38172ca627d3 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -321,7 +321,7 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, if (cpuid->nent < vcpu->arch.cpuid_nent) goto out; r = -EFAULT; - if (copy_to_user(entries, &vcpu->arch.cpuid_entries, + if (copy_to_user(entries, vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2))) goto out; return 0; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 56cae1ff9e3f..66a08322988f 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -2879,6 +2879,8 @@ static int em_sysenter(struct x86_emulate_ctxt *ctxt) ops->get_msr(ctxt, MSR_IA32_SYSENTER_ESP, &msr_data); *reg_write(ctxt, VCPU_REGS_RSP) = (efer & EFER_LMA) ? msr_data : (u32)msr_data; + if (efer & EFER_LMA) + ctxt->mode = X86EMUL_MODE_PROT64; return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index f15bc16de07c..a889563ad02d 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -9,31 +9,6 @@ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE) -static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); -} - -static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); -} - -static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); -} - -static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, - enum kvm_reg reg) -{ - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); - __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); -} - #define BUILD_KVM_GPR_ACCESSORS(lname, uname) \ static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\ { \ @@ -43,7 +18,6 @@ static __always_inline void kvm_##lname##_write(struct kvm_vcpu *vcpu, \ unsigned long val) \ { \ vcpu->arch.regs[VCPU_REGS_##uname] = val; \ - kvm_register_mark_dirty(vcpu, VCPU_REGS_##uname); \ } BUILD_KVM_GPR_ACCESSORS(rax, RAX) BUILD_KVM_GPR_ACCESSORS(rbx, RBX) @@ -63,6 +37,31 @@ BUILD_KVM_GPR_ACCESSORS(r14, R14) BUILD_KVM_GPR_ACCESSORS(r15, R15) #endif +static inline bool kvm_register_is_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + return test_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +static inline bool kvm_register_is_dirty(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + return test_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); +} + +static inline void kvm_register_mark_available(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); +} + +static inline void kvm_register_mark_dirty(struct kvm_vcpu *vcpu, + enum kvm_reg reg) +{ + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_avail); + __set_bit(reg, (unsigned long *)&vcpu->arch.regs_dirty); +} + static inline unsigned long kvm_register_read(struct kvm_vcpu *vcpu, int reg) { if (WARN_ON_ONCE((unsigned int)reg >= NR_VCPU_REGS)) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 3136e05831cf..43cceadd073e 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -674,7 +674,7 @@ static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu) (unsigned long long)vcpu->arch.pv_eoi.msr_val); return false; } - return val & 0x1; + return val & KVM_PV_EOI_ENABLED; } static void pv_eoi_set_pending(struct kvm_vcpu *vcpu) @@ -2898,7 +2898,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu) /* evaluate pending_events before reading the vector */ smp_rmb(); sipi_vector = apic->sipi_vector; - kvm_vcpu_deliver_sipi_vector(vcpu, sipi_vector); + kvm_x86_ops.vcpu_deliver_sipi_vector(vcpu, sipi_vector); vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; } } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 9c4a9c8e43d9..261be1d2032b 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -44,12 +44,19 @@ #define PT32_ROOT_LEVEL 2 #define PT32E_ROOT_LEVEL 3 -static inline u64 rsvd_bits(int s, int e) +static __always_inline u64 rsvd_bits(int s, int e) { + BUILD_BUG_ON(__builtin_constant_p(e) && __builtin_constant_p(s) && e < s); + + if (__builtin_constant_p(e)) + BUILD_BUG_ON(e > 63); + else + e &= 63; + if (e < s) return 0; - return ((1ULL << (e - s + 1)) - 1) << s; + return ((2ULL << (e - s)) - 1) << s; } void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 access_mask); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index c478904af518..6d16481aa29d 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3493,26 +3493,25 @@ static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) * Return the level of the lowest level SPTE added to sptes. * That SPTE may be non-present. */ -static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes) +static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level) { struct kvm_shadow_walk_iterator iterator; - int leaf = vcpu->arch.mmu->root_level; + int leaf = -1; u64 spte; - walk_shadow_page_lockless_begin(vcpu); - for (shadow_walk_init(&iterator, vcpu, addr); + for (shadow_walk_init(&iterator, vcpu, addr), + *root_level = iterator.level; shadow_walk_okay(&iterator); __shadow_walk_next(&iterator, spte)) { leaf = iterator.level; spte = mmu_spte_get_lockless(iterator.sptep); - sptes[leaf - 1] = spte; + sptes[leaf] = spte; if (!is_shadow_present_pte(spte)) break; - } walk_shadow_page_lockless_end(vcpu); @@ -3520,14 +3519,12 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes) return leaf; } -/* return true if reserved bit is detected on spte. */ +/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { - u64 sptes[PT64_ROOT_MAX_LEVEL]; + u64 sptes[PT64_ROOT_MAX_LEVEL + 1]; struct rsvd_bits_validate *rsvd_check; - int root = vcpu->arch.mmu->shadow_root_level; - int leaf; - int level; + int root, leaf, level; bool reserved = false; if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) { @@ -3536,35 +3533,45 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) } if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) - leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes); + leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root); else - leaf = get_walk(vcpu, addr, sptes); + leaf = get_walk(vcpu, addr, sptes, &root); + + if (unlikely(leaf < 0)) { + *sptep = 0ull; + return reserved; + } + + *sptep = sptes[leaf]; + + /* + * Skip reserved bits checks on the terminal leaf if it's not a valid + * SPTE. Note, this also (intentionally) skips MMIO SPTEs, which, by + * design, always have reserved bits set. The purpose of the checks is + * to detect reserved bits on non-MMIO SPTEs. i.e. buggy SPTEs. + */ + if (!is_shadow_present_pte(sptes[leaf])) + leaf++; rsvd_check = &vcpu->arch.mmu->shadow_zero_check; - for (level = root; level >= leaf; level--) { - if (!is_shadow_present_pte(sptes[level - 1])) - break; + for (level = root; level >= leaf; level--) /* * Use a bitwise-OR instead of a logical-OR to aggregate the * reserved bit and EPT's invalid memtype/XWR checks to avoid * adding a Jcc in the loop. */ - reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level - 1]) | - __is_rsvd_bits_set(rsvd_check, sptes[level - 1], - level); - } + reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level]) | + __is_rsvd_bits_set(rsvd_check, sptes[level], level); if (reserved) { pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n", __func__, addr); for (level = root; level >= leaf; level--) pr_err("------ spte 0x%llx level %d.\n", - sptes[level - 1], level); + sptes[level], level); } - *sptep = sptes[leaf - 1]; - return reserved; } diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 4bd2f1dc0172..b56d604809b8 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -44,7 +44,48 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); } -#define for_each_tdp_mmu_root(_kvm, _root) \ +static void tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root) +{ + if (kvm_mmu_put_root(kvm, root)) + kvm_tdp_mmu_free_root(kvm, root); +} + +static inline bool tdp_mmu_next_root_valid(struct kvm *kvm, + struct kvm_mmu_page *root) +{ + lockdep_assert_held(&kvm->mmu_lock); + + if (list_entry_is_head(root, &kvm->arch.tdp_mmu_roots, link)) + return false; + + kvm_mmu_get_root(kvm, root); + return true; + +} + +static inline struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, + struct kvm_mmu_page *root) +{ + struct kvm_mmu_page *next_root; + + next_root = list_next_entry(root, link); + tdp_mmu_put_root(kvm, root); + return next_root; +} + +/* + * Note: this iterator gets and puts references to the roots it iterates over. + * This makes it safe to release the MMU lock and yield within the loop, but + * if exiting the loop early, the caller must drop the reference to the most + * recent root. (Unless keeping a live reference is desirable.) + */ +#define for_each_tdp_mmu_root_yield_safe(_kvm, _root) \ + for (_root = list_first_entry(&_kvm->arch.tdp_mmu_roots, \ + typeof(*_root), link); \ + tdp_mmu_next_root_valid(_kvm, _root); \ + _root = tdp_mmu_next_root(_kvm, _root)) + +#define for_each_tdp_mmu_root(_kvm, _root) \ list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa) @@ -447,18 +488,9 @@ bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end) struct kvm_mmu_page *root; bool flush = false; - for_each_tdp_mmu_root(kvm, root) { - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - + for_each_tdp_mmu_root_yield_safe(kvm, root) flush |= zap_gfn_range(kvm, root, start, end, true); - kvm_mmu_put_root(kvm, root); - } - return flush; } @@ -619,13 +651,7 @@ static int kvm_tdp_mmu_handle_hva_range(struct kvm *kvm, unsigned long start, int ret = 0; int as_id; - for_each_tdp_mmu_root(kvm, root) { - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - + for_each_tdp_mmu_root_yield_safe(kvm, root) { as_id = kvm_mmu_page_as_id(root); slots = __kvm_memslots(kvm, as_id); kvm_for_each_memslot(memslot, slots) { @@ -647,8 +673,6 @@ static int kvm_tdp_mmu_handle_hva_range(struct kvm *kvm, unsigned long start, ret |= handler(kvm, memslot, root, gfn_start, gfn_end, data); } - - kvm_mmu_put_root(kvm, root); } return ret; @@ -838,21 +862,13 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, struct kvm_memory_slot *slot, int root_as_id; bool spte_set = false; - for_each_tdp_mmu_root(kvm, root) { + for_each_tdp_mmu_root_yield_safe(kvm, root) { root_as_id = kvm_mmu_page_as_id(root); if (root_as_id != slot->as_id) continue; - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages, min_level); - - kvm_mmu_put_root(kvm, root); } return spte_set; @@ -906,21 +922,13 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, struct kvm_memory_slot *slot) int root_as_id; bool spte_set = false; - for_each_tdp_mmu_root(kvm, root) { + for_each_tdp_mmu_root_yield_safe(kvm, root) { root_as_id = kvm_mmu_page_as_id(root); if (root_as_id != slot->as_id) continue; - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages); - - kvm_mmu_put_root(kvm, root); } return spte_set; @@ -1029,28 +1037,20 @@ bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot) int root_as_id; bool spte_set = false; - for_each_tdp_mmu_root(kvm, root) { + for_each_tdp_mmu_root_yield_safe(kvm, root) { root_as_id = kvm_mmu_page_as_id(root); if (root_as_id != slot->as_id) continue; - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - spte_set |= set_dirty_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages); - - kvm_mmu_put_root(kvm, root); } return spte_set; } /* - * Clear non-leaf entries (and free associated page tables) which could - * be replaced by large mappings, for GFNs within the slot. + * Clear leaf entries which could be replaced by large mappings, for + * GFNs within the slot. */ static void zap_collapsible_spte_range(struct kvm *kvm, struct kvm_mmu_page *root, @@ -1062,7 +1062,7 @@ static void zap_collapsible_spte_range(struct kvm *kvm, tdp_root_for_each_pte(iter, root, start, end) { if (!is_shadow_present_pte(iter.old_spte) || - is_last_spte(iter.old_spte, iter.level)) + !is_last_spte(iter.old_spte, iter.level)) continue; pfn = spte_to_pfn(iter.old_spte); @@ -1089,21 +1089,13 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, struct kvm_mmu_page *root; int root_as_id; - for_each_tdp_mmu_root(kvm, root) { + for_each_tdp_mmu_root_yield_safe(kvm, root) { root_as_id = kvm_mmu_page_as_id(root); if (root_as_id != slot->as_id) continue; - /* - * Take a reference on the root so that it cannot be freed if - * this thread releases the MMU lock and yields in this loop. - */ - kvm_mmu_get_root(kvm, root); - zap_collapsible_spte_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages); - - kvm_mmu_put_root(kvm, root); } } @@ -1160,16 +1152,19 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, * Return the level of the lowest level SPTE added to sptes. * That SPTE may be non-present. */ -int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes) +int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, + int *root_level) { struct tdp_iter iter; struct kvm_mmu *mmu = vcpu->arch.mmu; - int leaf = vcpu->arch.mmu->shadow_root_level; gfn_t gfn = addr >> PAGE_SHIFT; + int leaf = -1; + + *root_level = vcpu->arch.mmu->shadow_root_level; tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { leaf = iter.level; - sptes[leaf - 1] = iter.old_spte; + sptes[leaf] = iter.old_spte; } return leaf; diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 556e065503f6..cbbdbadd1526 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -44,5 +44,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn); -int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes); +int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, + int *root_level); + #endif /* __KVM_X86_MMU_TDP_MMU_H */ diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index b0b667456b2e..db30670dd8c4 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -199,6 +199,10 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + + if (WARN_ON(!is_guest_mode(vcpu))) + return true; + if (!nested_svm_vmrun_msrpm(svm)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = @@ -227,6 +231,7 @@ static bool nested_vmcb_check_controls(struct vmcb_control_area *control) static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12) { + struct kvm_vcpu *vcpu = &svm->vcpu; bool vmcb12_lma; if ((vmcb12->save.efer & EFER_SVME) == 0) @@ -240,18 +245,10 @@ static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12) vmcb12_lma = (vmcb12->save.efer & EFER_LME) && (vmcb12->save.cr0 & X86_CR0_PG); - if (!vmcb12_lma) { - if (vmcb12->save.cr4 & X86_CR4_PAE) { - if (vmcb12->save.cr3 & MSR_CR3_LEGACY_PAE_RESERVED_MASK) - return false; - } else { - if (vmcb12->save.cr3 & MSR_CR3_LEGACY_RESERVED_MASK) - return false; - } - } else { + if (vmcb12_lma) { if (!(vmcb12->save.cr4 & X86_CR4_PAE) || !(vmcb12->save.cr0 & X86_CR0_PE) || - (vmcb12->save.cr3 & MSR_CR3_LONG_MBZ_MASK)) + (vmcb12->save.cr3 & vcpu->arch.cr3_lm_rsvd_bits)) return false; } if (!kvm_is_valid_cr4(&svm->vcpu, vmcb12->save.cr4)) @@ -595,6 +592,8 @@ int nested_svm_vmexit(struct vcpu_svm *svm) svm->nested.vmcb12_gpa = 0; WARN_ON_ONCE(svm->nested.nested_run_pending); + kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, &svm->vcpu); + /* in case we halted in L2 */ svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -754,6 +753,7 @@ void svm_leave_nested(struct vcpu_svm *svm) leave_guest_mode(&svm->vcpu); copy_vmcb_control_area(&vmcb->control, &hsave->control); nested_svm_uninit_mmu_context(&svm->vcpu); + vmcb_mark_all_dirty(svm->vmcb); } kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, &svm->vcpu); @@ -1194,6 +1194,10 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu, * in the registers, the save area of the nested state instead * contains saved L1 state. */ + + svm->nested.nested_run_pending = + !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING); + copy_vmcb_control_area(&hsave->control, &svm->vmcb->control); hsave->save = *save; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 9858d5ae9ddd..48017fef1cd9 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -342,6 +342,8 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, unsigned long first, last; int ret; + lockdep_assert_held(&kvm->lock); + if (ulen == 0 || uaddr + ulen < uaddr) return ERR_PTR(-EINVAL); @@ -1119,12 +1121,20 @@ int svm_register_enc_region(struct kvm *kvm, if (!region) return -ENOMEM; + mutex_lock(&kvm->lock); region->pages = sev_pin_memory(kvm, range->addr, range->size, ®ion->npages, 1); if (IS_ERR(region->pages)) { ret = PTR_ERR(region->pages); + mutex_unlock(&kvm->lock); goto e_free; } + region->uaddr = range->addr; + region->size = range->size; + + list_add_tail(®ion->list, &sev->regions_list); + mutex_unlock(&kvm->lock); + /* * The guest may change the memory encryption attribute from C=0 -> C=1 * or vice versa for this memory range. Lets make sure caches are @@ -1133,13 +1143,6 @@ int svm_register_enc_region(struct kvm *kvm, */ sev_clflush_pages(region->pages, region->npages); - region->uaddr = range->addr; - region->size = range->size; - - mutex_lock(&kvm->lock); - list_add_tail(®ion->list, &sev->regions_list); - mutex_unlock(&kvm->lock); - return ret; e_free: @@ -1415,16 +1418,13 @@ static void sev_es_sync_to_ghcb(struct vcpu_svm *svm) * to be returned: * GPRs RAX, RBX, RCX, RDX * - * Copy their values to the GHCB if they are dirty. + * Copy their values, even if they may not have been written during the + * VM-Exit. It's the guest's responsibility to not consume random data. */ - if (kvm_register_is_dirty(vcpu, VCPU_REGS_RAX)) - ghcb_set_rax(ghcb, vcpu->arch.regs[VCPU_REGS_RAX]); - if (kvm_register_is_dirty(vcpu, VCPU_REGS_RBX)) - ghcb_set_rbx(ghcb, vcpu->arch.regs[VCPU_REGS_RBX]); - if (kvm_register_is_dirty(vcpu, VCPU_REGS_RCX)) - ghcb_set_rcx(ghcb, vcpu->arch.regs[VCPU_REGS_RCX]); - if (kvm_register_is_dirty(vcpu, VCPU_REGS_RDX)) - ghcb_set_rdx(ghcb, vcpu->arch.regs[VCPU_REGS_RDX]); + ghcb_set_rax(ghcb, vcpu->arch.regs[VCPU_REGS_RAX]); + ghcb_set_rbx(ghcb, vcpu->arch.regs[VCPU_REGS_RBX]); + ghcb_set_rcx(ghcb, vcpu->arch.regs[VCPU_REGS_RCX]); + ghcb_set_rdx(ghcb, vcpu->arch.regs[VCPU_REGS_RDX]); } static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) @@ -1563,6 +1563,7 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm) goto vmgexit_err; break; case SVM_VMGEXIT_NMI_COMPLETE: + case SVM_VMGEXIT_AP_HLT_LOOP: case SVM_VMGEXIT_AP_JUMP_TABLE: case SVM_VMGEXIT_UNSUPPORTED_EVENT: break; @@ -1888,6 +1889,9 @@ int sev_handle_vmgexit(struct vcpu_svm *svm) case SVM_VMGEXIT_NMI_COMPLETE: ret = svm_invoke_exit_handler(svm, SVM_EXIT_IRET); break; + case SVM_VMGEXIT_AP_HLT_LOOP: + ret = kvm_emulate_ap_reset_hold(&svm->vcpu); + break; case SVM_VMGEXIT_AP_JUMP_TABLE: { struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info; @@ -2001,7 +2005,7 @@ void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu) * of which one step is to perform a VMLOAD. Since hardware does not * perform a VMSAVE on VMRUN, the host savearea must be updated. */ - asm volatile(__ex("vmsave") : : "a" (__sme_page_pa(sd->save_area)) : "memory"); + asm volatile(__ex("vmsave %0") : : "a" (__sme_page_pa(sd->save_area)) : "memory"); /* * Certain MSRs are restored on VMEXIT, only save ones that aren't @@ -2040,3 +2044,21 @@ void sev_es_vcpu_put(struct vcpu_svm *svm) wrmsrl(host_save_user_msrs[i].index, svm->host_user_msrs[i]); } } + +void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* First SIPI: Use the values as initially set by the VMM */ + if (!svm->received_first_sipi) { + svm->received_first_sipi = true; + return; + } + + /* + * Subsequent SIPI: Return from an AP Reset Hold VMGEXIT, where + * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a + * non-zero value. + */ + ghcb_set_sw_exit_info_2(svm->ghcb, 1); +} diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index cce0143a6f80..3442d44ca53b 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -454,6 +454,11 @@ static int has_svm(void) return 0; } + if (sev_active()) { + pr_info("KVM is unsupported when running as an SEV guest\n"); + return 0; + } + return 1; } @@ -3677,8 +3682,6 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) return EXIT_FASTPATH_NONE; } -void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs); - static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, struct vcpu_svm *svm) { @@ -3741,6 +3744,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + trace_kvm_entry(vcpu); + svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP]; @@ -4384,6 +4389,14 @@ static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) (vmcb_is_intercept(&svm->vmcb->control, INTERCEPT_INIT)); } +static void svm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) +{ + if (!sev_es_guest(vcpu->kvm)) + return kvm_vcpu_deliver_sipi_vector(vcpu, vector); + + sev_vcpu_deliver_sipi_vector(vcpu, vector); +} + static void svm_vm_destroy(struct kvm *kvm) { avic_vm_destroy(kvm); @@ -4526,6 +4539,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .msr_filter_changed = svm_msr_filter_changed, .complete_emulated_msr = svm_complete_emulated_msr, + + .vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector, }; static struct kvm_x86_init_ops svm_init_ops __initdata = { diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 5431e6335e2e..6e7d070f8b86 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -185,6 +185,7 @@ struct vcpu_svm { struct vmcb_save_area *vmsa; struct ghcb *ghcb; struct kvm_host_map ghcb_map; + bool received_first_sipi; /* SEV-ES scratch area support */ void *ghcb_sa; @@ -402,9 +403,6 @@ static inline bool gif_set(struct vcpu_svm *svm) } /* svm.c */ -#define MSR_CR3_LEGACY_RESERVED_MASK 0xfe7U -#define MSR_CR3_LEGACY_PAE_RESERVED_MASK 0x7U -#define MSR_CR3_LONG_MBZ_MASK 0xfff0000000000000U #define MSR_INVALID 0xffffffffU extern int sev; @@ -591,6 +589,7 @@ void sev_es_init_vmcb(struct vcpu_svm *svm); void sev_es_create_vcpu(struct vcpu_svm *svm); void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu); void sev_es_vcpu_put(struct vcpu_svm *svm); +void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); /* vmenter.S */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index e2f26564a12d..f2b9bfb58206 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3124,13 +3124,9 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) return 0; } -static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) +static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) { - struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); - struct kvm_host_map *map; - struct page *page; - u64 hpa; /* * hv_evmcs may end up being not mapped after migration (when @@ -3153,6 +3149,17 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) } } + return true; +} + +static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct kvm_host_map *map; + struct page *page; + u64 hpa; + if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) { /* * Translate L1 physical address to host physical @@ -3221,6 +3228,18 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS); else exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS); + + return true; +} + +static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) +{ + if (!nested_get_evmcs_page(vcpu)) + return false; + + if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu)) + return false; + return true; } @@ -4442,6 +4461,8 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, /* trying to cancel vmlaunch/vmresume is a bug */ WARN_ON_ONCE(vmx->nested.nested_run_pending); + kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); + /* Service the TLB flush request for L2 before switching to L1. */ if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) kvm_vcpu_flush_tlb_current(vcpu); @@ -6075,11 +6096,14 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, if (is_guest_mode(vcpu)) { sync_vmcs02_to_vmcs12(vcpu, vmcs12); sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); - } else if (!vmx->nested.need_vmcs12_to_shadow_sync) { - if (vmx->nested.hv_evmcs) - copy_enlightened_to_vmcs12(vmx); - else if (enable_shadow_vmcs) - copy_shadow_to_vmcs12(vmx); + } else { + copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu)); + if (!vmx->nested.need_vmcs12_to_shadow_sync) { + if (vmx->nested.hv_evmcs) + copy_enlightened_to_vmcs12(vmx); + else if (enable_shadow_vmcs) + copy_shadow_to_vmcs12(vmx); + } } BUILD_BUG_ON(sizeof(user_vmx_nested_state->vmcs12) < VMCS12_SIZE); @@ -6600,7 +6624,7 @@ struct kvm_x86_nested_ops vmx_nested_ops = { .hv_timer_pending = nested_vmx_preemption_timer_pending, .get_state = vmx_get_nested_state, .set_state = vmx_set_nested_state, - .get_nested_state_pages = nested_get_vmcs12_pages, + .get_nested_state_pages = vmx_get_nested_state_pages, .write_log_dirty = nested_vmx_write_pml_buffer, .enable_evmcs = nested_enable_evmcs, .get_evmcs_version = nested_get_evmcs_version, diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index a886a47daebd..cdf5f34518f4 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -29,7 +29,7 @@ static struct kvm_event_hw_type_mapping intel_arch_events[] = { [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, - [7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES }, + [7] = { 0x00, 0x03, PERF_COUNT_HW_REF_CPU_CYCLES }, }; /* mapping between fixed pmc index and intel_arch_events array */ @@ -345,7 +345,9 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters, x86_pmu.num_counters_gp); + eax.split.bit_width = min_t(int, eax.split.bit_width, x86_pmu.bit_width_gp); pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1; + eax.split.mask_length = min_t(int, eax.split.mask_length, x86_pmu.events_mask_len); pmu->available_event_types = ~entry->ebx & ((1ull << eax.split.mask_length) - 1); @@ -355,6 +357,8 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->nr_arch_fixed_counters = min_t(int, edx.split.num_counters_fixed, x86_pmu.num_counters_fixed); + edx.split.bit_width_fixed = min_t(int, + edx.split.bit_width_fixed, x86_pmu.bit_width_fixed); pmu->counter_bitmask[KVM_PMC_FIXED] = ((u64)1 << edx.split.bit_width_fixed) - 1; } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 75c9c6a0a3a4..eb69fef57485 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -6653,6 +6653,8 @@ reenter_guest: if (vmx->emulation_required) return EXIT_FASTPATH_NONE; + trace_kvm_entry(vcpu); + if (vmx->ple_window_dirty) { vmx->ple_window_dirty = false; vmcs_write32(PLE_WINDOW, vmx->ple_window); @@ -6858,11 +6860,20 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu) switch (index) { case MSR_IA32_TSX_CTRL: /* - * No need to pass TSX_CTRL_CPUID_CLEAR through, so - * let's avoid changing CPUID bits under the host - * kernel's feet. + * TSX_CTRL_CPUID_CLEAR is handled in the CPUID + * interception. Keep the host value unchanged to avoid + * changing CPUID bits under the host kernel's feet. + * + * hle=0, rtm=0, tsx_ctrl=1 can be found with some + * combinations of new kernel and old userspace. If + * those guests run on a tsx=off host, do allow guests + * to use TSX_CTRL, but do not change the value on the + * host so that TSX remains always disabled. */ - vmx->guest_uret_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; + if (boot_cpu_has(X86_FEATURE_RTM)) + vmx->guest_uret_msrs[j].mask = ~(u64)TSX_CTRL_CPUID_CLEAR; + else + vmx->guest_uret_msrs[j].mask = 0; break; default: vmx->guest_uret_msrs[j].mask = -1ull; @@ -7707,6 +7718,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .msr_filter_changed = vmx_msr_filter_changed, .complete_emulated_msr = kvm_complete_insn_gp, .cpu_dirty_log_size = vmx_cpu_dirty_log_size, + + .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, }; static __init int hardware_setup(void) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3f7c1fc7a3ce..1b404e4d7dd8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -105,6 +105,7 @@ static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; static void update_cr8_intercept(struct kvm_vcpu *vcpu); static void process_nmi(struct kvm_vcpu *vcpu); +static void process_smi(struct kvm_vcpu *vcpu); static void enter_smm(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); @@ -1393,16 +1394,24 @@ static u64 kvm_get_arch_capabilities(void) if (!boot_cpu_has_bug(X86_BUG_MDS)) data |= ARCH_CAP_MDS_NO; - /* - * On TAA affected systems: - * - nothing to do if TSX is disabled on the host. - * - we emulate TSX_CTRL if present on the host. - * This lets the guest use VERW to clear CPU buffers. - */ - if (!boot_cpu_has(X86_FEATURE_RTM)) - data &= ~(ARCH_CAP_TAA_NO | ARCH_CAP_TSX_CTRL_MSR); - else if (!boot_cpu_has_bug(X86_BUG_TAA)) + if (!boot_cpu_has(X86_FEATURE_RTM)) { + /* + * If RTM=0 because the kernel has disabled TSX, the host might + * have TAA_NO or TSX_CTRL. Clear TAA_NO (the guest sees RTM=0 + * and therefore knows that there cannot be TAA) but keep + * TSX_CTRL: some buggy userspaces leave it set on tsx=on hosts, + * and we want to allow migrating those guests to tsx=off hosts. + */ + data &= ~ARCH_CAP_TAA_NO; + } else if (!boot_cpu_has_bug(X86_BUG_TAA)) { data |= ARCH_CAP_TAA_NO; + } else { + /* + * Nothing to do here; we emulate TSX_CTRL if present on the + * host so the guest can choose between disabling TSX or + * using VERW to clear CPU buffers. + */ + } return data; } @@ -4230,6 +4239,9 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, { process_nmi(vcpu); + if (kvm_check_request(KVM_REQ_SMI, vcpu)) + process_smi(vcpu); + /* * In guest mode, payload delivery should be deferred, * so that the L1 hypervisor can intercept #PF before @@ -7976,17 +7988,22 @@ void kvm_arch_exit(void) kmem_cache_destroy(x86_fpu_cache); } -int kvm_vcpu_halt(struct kvm_vcpu *vcpu) +static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) { ++vcpu->stat.halt_exits; if (lapic_in_kernel(vcpu)) { - vcpu->arch.mp_state = KVM_MP_STATE_HALTED; + vcpu->arch.mp_state = state; return 1; } else { - vcpu->run->exit_reason = KVM_EXIT_HLT; + vcpu->run->exit_reason = reason; return 0; } } + +int kvm_vcpu_halt(struct kvm_vcpu *vcpu) +{ + return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_HALTED, KVM_EXIT_HLT); +} EXPORT_SYMBOL_GPL(kvm_vcpu_halt); int kvm_emulate_halt(struct kvm_vcpu *vcpu) @@ -8000,6 +8017,14 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_halt); +int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu) +{ + int ret = kvm_skip_emulated_instruction(vcpu); + + return __kvm_vcpu_halt(vcpu, KVM_MP_STATE_AP_RESET_HOLD, KVM_EXIT_AP_RESET_HOLD) && ret; +} +EXPORT_SYMBOL_GPL(kvm_emulate_ap_reset_hold); + #ifdef CONFIG_X86_64 static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, unsigned long clock_type) @@ -8973,8 +8998,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_x86_ops.request_immediate_exit(vcpu); } - trace_kvm_entry(vcpu); - fpregs_assert_state_consistent(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) switch_fpu_return(); @@ -9094,6 +9117,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) kvm_apic_accept_events(vcpu); switch(vcpu->arch.mp_state) { case KVM_MP_STATE_HALTED: + case KVM_MP_STATE_AP_RESET_HOLD: vcpu->arch.pv.pv_unhalted = false; vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -9520,8 +9544,9 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, kvm_load_guest_fpu(vcpu); kvm_apic_accept_events(vcpu); - if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED && - vcpu->arch.pv.pv_unhalted) + if ((vcpu->arch.mp_state == KVM_MP_STATE_HALTED || + vcpu->arch.mp_state == KVM_MP_STATE_AP_RESET_HOLD) && + vcpu->arch.pv.pv_unhalted) mp_state->mp_state = KVM_MP_STATE_RUNNABLE; else mp_state->mp_state = vcpu->arch.mp_state; @@ -9599,6 +9624,8 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) */ if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA)) return false; + if (sregs->cr3 & vcpu->arch.cr3_lm_rsvd_bits) + return false; } else { /* * Not in 64-bit mode: EFER.LMA is clear and the code @@ -9976,6 +10003,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) fx_init(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); + vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63); vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; @@ -10152,6 +10180,7 @@ void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); kvm_rip_write(vcpu, 0); } +EXPORT_SYMBOL_GPL(kvm_vcpu_deliver_sipi_vector); int kvm_arch_hardware_enable(void) { @@ -10476,7 +10505,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, return 0; old_npages = slot->npages; - hva = 0; + hva = slot->userspace_addr; } for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { @@ -11538,6 +11567,7 @@ int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size, } EXPORT_SYMBOL_GPL(kvm_sev_es_string_io); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_entry); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index c5ee0f5ce0f1..0f727b50bd3d 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -425,6 +425,8 @@ bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type); __reserved_bits |= X86_CR4_UMIP; \ if (!__cpu_has(__c, X86_FEATURE_VMX)) \ __reserved_bits |= X86_CR4_VMXE; \ + if (!__cpu_has(__c, X86_FEATURE_PCID)) \ + __reserved_bits |= X86_CR4_PCIDE; \ __reserved_bits; \ }) diff --git a/arch/x86/lib/mmx_32.c b/arch/x86/lib/mmx_32.c index 4321fa02e18d..419365c48b2a 100644 --- a/arch/x86/lib/mmx_32.c +++ b/arch/x86/lib/mmx_32.c @@ -26,6 +26,16 @@ #include <asm/fpu/api.h> #include <asm/asm.h> +/* + * Use KFPU_387. MMX instructions are not affected by MXCSR, + * but both AMD and Intel documentation states that even integer MMX + * operations will result in #MF if an exception is pending in FCW. + * + * EMMS is not needed afterwards because, after calling kernel_fpu_end(), + * any subsequent user of the 387 stack will reinitialize it using + * KFPU_387. + */ + void *_mmx_memcpy(void *to, const void *from, size_t len) { void *p; @@ -37,7 +47,7 @@ void *_mmx_memcpy(void *to, const void *from, size_t len) p = to; i = len >> 6; /* len/64 */ - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( "1: prefetch (%0)\n" /* This set is 28 bytes */ @@ -127,7 +137,7 @@ static void fast_clear_page(void *page) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( " pxor %%mm0, %%mm0\n" : : @@ -160,7 +170,7 @@ static void fast_copy_page(void *to, void *from) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); /* * maybe the prefetch stuff can go before the expensive fnsave... @@ -247,7 +257,7 @@ static void fast_clear_page(void *page) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( " pxor %%mm0, %%mm0\n" : : @@ -282,7 +292,7 @@ static void fast_copy_page(void *to, void *from) { int i; - kernel_fpu_begin(); + kernel_fpu_begin_mask(KFPU_387); __asm__ __volatile__ ( "1: prefetch (%0)\n" diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index c79e5736ab2b..c3d5f0236f35 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -382,6 +382,7 @@ bool sev_active(void) { return sev_status & MSR_AMD64_SEV_ENABLED; } +EXPORT_SYMBOL_GPL(sev_active); /* Needs to be called from non-instrumentable code */ bool noinstr sev_es_active(void) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index dfd82f51ba66..f6a9e2e36642 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -829,6 +829,8 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr) } free_page((unsigned long)pmd_sv); + + pgtable_pmd_page_dtor(virt_to_page(pmd)); free_page((unsigned long)pmd); return 1; diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index e1e8d4e3a213..8efd003540ca 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -115,31 +115,12 @@ void efi_sync_low_kernel_mappings(void) pud_t *pud_k, *pud_efi; pgd_t *efi_pgd = efi_mm.pgd; - /* - * We can share all PGD entries apart from the one entry that - * covers the EFI runtime mapping space. - * - * Make sure the EFI runtime region mappings are guaranteed to - * only span a single PGD entry and that the entry also maps - * other important kernel regions. - */ - MAYBE_BUILD_BUG_ON(pgd_index(EFI_VA_END) != pgd_index(MODULES_END)); - MAYBE_BUILD_BUG_ON((EFI_VA_START & PGDIR_MASK) != - (EFI_VA_END & PGDIR_MASK)); - pgd_efi = efi_pgd + pgd_index(PAGE_OFFSET); pgd_k = pgd_offset_k(PAGE_OFFSET); num_entries = pgd_index(EFI_VA_END) - pgd_index(PAGE_OFFSET); memcpy(pgd_efi, pgd_k, sizeof(pgd_t) * num_entries); - /* - * As with PGDs, we share all P4D entries apart from the one entry - * that covers the EFI runtime mapping space. - */ - BUILD_BUG_ON(p4d_index(EFI_VA_END) != p4d_index(MODULES_END)); - BUILD_BUG_ON((EFI_VA_START & P4D_MASK) != (EFI_VA_END & P4D_MASK)); - pgd_efi = efi_pgd + pgd_index(EFI_VA_END); pgd_k = pgd_offset_k(EFI_VA_END); p4d_efi = p4d_offset(pgd_efi, 0); diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 9e87ab010c82..e68ea5f4ad1c 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -164,10 +164,10 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu) else per_cpu(xen_vcpu_id, cpu) = cpu; rc = xen_vcpu_setup(cpu); - if (rc) + if (rc || !xen_have_vector_callback) return rc; - if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock)) + if (xen_feature(XENFEAT_hvm_safe_pvclock)) xen_setup_timer(cpu); rc = xen_smp_intr_init(cpu); @@ -188,6 +188,8 @@ static int xen_cpu_dead_hvm(unsigned int cpu) return 0; } +static bool no_vector_callback __initdata; + static void __init xen_hvm_guest_init(void) { if (xen_pv_domain()) @@ -207,7 +209,7 @@ static void __init xen_hvm_guest_init(void) xen_panic_handler_init(); - if (xen_feature(XENFEAT_hvm_callback_vector)) + if (!no_vector_callback && xen_feature(XENFEAT_hvm_callback_vector)) xen_have_vector_callback = 1; xen_hvm_smp_init(); @@ -233,6 +235,13 @@ static __init int xen_parse_nopv(char *arg) } early_param("xen_nopv", xen_parse_nopv); +static __init int xen_parse_no_vector_callback(char *arg) +{ + no_vector_callback = true; + return 0; +} +early_param("xen_no_vector_callback", xen_parse_no_vector_callback); + bool __init xen_hvm_need_lapic(void) { if (xen_pv_domain()) diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 4409306364dc..9a5a50cdaab5 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -583,6 +583,13 @@ DEFINE_IDTENTRY_RAW(xenpv_exc_debug) exc_debug(regs); } +DEFINE_IDTENTRY_RAW(exc_xen_unknown_trap) +{ + /* This should never happen and there is no way to handle it. */ + pr_err("Unknown trap in Xen PV mode."); + BUG(); +} + struct trap_array_entry { void (*orig)(void); void (*xen)(void); @@ -631,6 +638,7 @@ static bool __ref get_trap_addr(void **addr, unsigned int ist) { unsigned int nr; bool ist_okay = false; + bool found = false; /* * Replace trap handler addresses by Xen specific ones. @@ -645,6 +653,7 @@ static bool __ref get_trap_addr(void **addr, unsigned int ist) if (*addr == entry->orig) { *addr = entry->xen; ist_okay = entry->ist_okay; + found = true; break; } } @@ -655,9 +664,13 @@ static bool __ref get_trap_addr(void **addr, unsigned int ist) nr = (*addr - (void *)early_idt_handler_array[0]) / EARLY_IDT_HANDLER_SIZE; *addr = (void *)xen_early_idt_handler_array[nr]; + found = true; } - if (WARN_ON(ist != 0 && !ist_okay)) + if (!found) + *addr = (void *)xen_asm_exc_xen_unknown_trap; + + if (WARN_ON(found && ist != 0 && !ist_okay)) return false; return true; diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c index f5e7db4f82ab..6ff3c887e0b9 100644 --- a/arch/x86/xen/smp_hvm.c +++ b/arch/x86/xen/smp_hvm.c @@ -33,9 +33,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) int cpu; native_smp_prepare_cpus(max_cpus); - WARN_ON(xen_smp_intr_init(0)); - xen_init_lock_cpu(0); + if (xen_have_vector_callback) { + WARN_ON(xen_smp_intr_init(0)); + xen_init_lock_cpu(0); + } for_each_possible_cpu(cpu) { if (cpu == 0) @@ -50,9 +52,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) static void xen_hvm_cpu_die(unsigned int cpu) { if (common_cpu_die(cpu) == 0) { - xen_smp_intr_free(cpu); - xen_uninit_lock_cpu(cpu); - xen_teardown_timer(cpu); + if (xen_have_vector_callback) { + xen_smp_intr_free(cpu); + xen_uninit_lock_cpu(cpu); + xen_teardown_timer(cpu); + } } } #else @@ -64,14 +68,19 @@ static void xen_hvm_cpu_die(unsigned int cpu) void __init xen_hvm_smp_init(void) { - if (!xen_have_vector_callback) + smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu; + smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; + smp_ops.smp_cpus_done = xen_smp_cpus_done; + smp_ops.cpu_die = xen_hvm_cpu_die; + + if (!xen_have_vector_callback) { +#ifdef CONFIG_PARAVIRT_SPINLOCKS + nopvspin = true; +#endif return; + } - smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; smp_ops.smp_send_reschedule = xen_smp_send_reschedule; - smp_ops.cpu_die = xen_hvm_cpu_die; smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi; smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi; - smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu; - smp_ops.smp_cpus_done = xen_smp_cpus_done; } diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 1cb0e84b9161..53cf8aa35032 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -178,6 +178,7 @@ xen_pv_trap asm_exc_simd_coprocessor_error #ifdef CONFIG_IA32_EMULATION xen_pv_trap entry_INT80_compat #endif +xen_pv_trap asm_exc_xen_unknown_trap xen_pv_trap asm_exc_xen_hypervisor_callback __INIT |