diff options
Diffstat (limited to 'arch')
118 files changed, 1602 insertions, 1541 deletions
diff --git a/arch/alpha/kernel/proto.h b/arch/alpha/kernel/proto.h index 5816a31c1b38..2c89c1c55712 100644 --- a/arch/alpha/kernel/proto.h +++ b/arch/alpha/kernel/proto.h @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/interrupt.h> +#include <linux/screen_info.h> #include <linux/io.h> /* Prototypes of functions used across modules here in this directory. */ @@ -113,6 +114,7 @@ extern int boot_cpuid; #ifdef CONFIG_VERBOSE_MCHECK extern unsigned long alpha_verbose_mcheck; #endif +extern struct screen_info vgacon_screen_info; /* srmcons.c */ #if defined(CONFIG_ALPHA_GENERIC) || defined(CONFIG_ALPHA_SRM) diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index c80258ec332f..0738f9396f95 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -131,13 +131,14 @@ static void determine_cpu_caches (unsigned int); static char __initdata command_line[COMMAND_LINE_SIZE]; +#ifdef CONFIG_VGA_CONSOLE /* * The format of "screen_info" is strange, and due to early * i386-setup code. This is just enough to make the console * code think we're on a VGA color display. */ -struct screen_info screen_info = { +struct screen_info vgacon_screen_info = { .orig_x = 0, .orig_y = 25, .orig_video_cols = 80, @@ -145,8 +146,7 @@ struct screen_info screen_info = { .orig_video_isVGA = 1, .orig_video_points = 16 }; - -EXPORT_SYMBOL(screen_info); +#endif /* * The direct map I/O window, if any. This should be the same @@ -652,7 +652,7 @@ setup_arch(char **cmdline_p) #ifdef CONFIG_VT #if defined(CONFIG_VGA_CONSOLE) - conswitchp = &vga_con; + vgacon_register_screen(&vgacon_screen_info); #endif #endif diff --git a/arch/alpha/kernel/sys_sio.c b/arch/alpha/kernel/sys_sio.c index 7c420d8dac53..086488ed83a7 100644 --- a/arch/alpha/kernel/sys_sio.c +++ b/arch/alpha/kernel/sys_sio.c @@ -57,11 +57,13 @@ sio_init_irq(void) static inline void __init alphabook1_init_arch(void) { +#ifdef CONFIG_VGA_CONSOLE /* The AlphaBook1 has LCD video fixed at 800x600, 37 rows and 100 cols. */ - screen_info.orig_y = 37; - screen_info.orig_video_cols = 100; - screen_info.orig_video_lines = 37; + vgacon_screen_info.orig_y = 37; + vgacon_screen_info.orig_video_cols = 100; + vgacon_screen_info.orig_video_lines = 37; +#endif lca_init_arch(); } diff --git a/arch/arm/Makefile b/arch/arm/Makefile index 547e5856eaa0..5ba42f69f8ce 100644 --- a/arch/arm/Makefile +++ b/arch/arm/Makefile @@ -304,11 +304,7 @@ $(INSTALL_TARGETS): KBUILD_IMAGE = $(boot)/$(patsubst %install,%Image,$@) $(INSTALL_TARGETS): $(call cmd,install) -PHONY += vdso_install -vdso_install: -ifeq ($(CONFIG_VDSO),y) - $(Q)$(MAKE) $(build)=arch/arm/vdso $@ -endif +vdso-install-$(CONFIG_VDSO) += arch/arm/vdso/vdso.so.dbg # My testing targets (bypasses dependencies) bp:; $(Q)$(MAKE) $(build)=$(boot) $(boot)/bootpImage @@ -331,7 +327,6 @@ define archhelp echo ' Install using (your) ~/bin/$(INSTALLKERNEL) or' echo ' (distribution) /sbin/$(INSTALLKERNEL) or' echo ' install to $$(INSTALL_PATH) and run lilo' - echo ' vdso_install - Install unstripped vdso.so to $$(INSTALL_MOD_PATH)/vdso' echo echo ' multi_v7_lpae_defconfig - multi_v7_defconfig with CONFIG_ARM_LPAE enabled' endef diff --git a/arch/arm/boot/dts/qcom/qcom-msm8226.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8226.dtsi index 98cc5ea637e1..97a377b5a0ec 100644 --- a/arch/arm/boot/dts/qcom/qcom-msm8226.dtsi +++ b/arch/arm/boot/dts/qcom/qcom-msm8226.dtsi @@ -242,6 +242,17 @@ status = "disabled"; }; + blsp1_uart2: serial@f991e000 { + compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm"; + reg = <0xf991e000 0x1000>; + interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&gcc GCC_BLSP1_UART2_APPS_CLK>, + <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "core", + "iface"; + status = "disabled"; + }; + blsp1_uart3: serial@f991f000 { compatible = "qcom,msm-uartdm-v1.4", "qcom,msm-uartdm"; reg = <0xf991f000 0x1000>; @@ -325,6 +336,21 @@ #size-cells = <0>; }; + blsp1_i2c6: i2c@f9928000 { + compatible = "qcom,i2c-qup-v2.1.1"; + reg = <0xf9928000 0x1000>; + interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&gcc GCC_BLSP1_QUP6_I2C_APPS_CLK>, + <&gcc GCC_BLSP1_AHB_CLK>; + clock-names = "core", + "iface"; + pinctrl-0 = <&blsp1_i2c6_pins>; + pinctrl-names = "default"; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + cci: cci@fda0c000 { compatible = "qcom,msm8226-cci"; #address-cells = <1>; @@ -472,6 +498,13 @@ bias-disable; }; + blsp1_i2c6_pins: blsp1-i2c6-state { + pins = "gpio22", "gpio23"; + function = "blsp_i2c6"; + drive-strength = <2>; + bias-disable; + }; + cci_default: cci-default-state { pins = "gpio29", "gpio30"; function = "cci_i2c0"; diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig index b2f0862f4bd9..7b1b41b4b160 100644 --- a/arch/arm/configs/omap2plus_defconfig +++ b/arch/arm/configs/omap2plus_defconfig @@ -477,7 +477,6 @@ CONFIG_LIRC=y CONFIG_RC_DEVICES=y CONFIG_IR_GPIO_TX=m CONFIG_IR_PWM_TX=m -CONFIG_IR_RX51=m CONFIG_IR_SPI=m CONFIG_MEDIA_SUPPORT=m CONFIG_V4L_PLATFORM_DRIVERS=y diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h index 546af8b1e3f6..cc106f946c69 100644 --- a/arch/arm/include/asm/setup.h +++ b/arch/arm/include/asm/setup.h @@ -11,6 +11,7 @@ #ifndef __ASMARM_SETUP_H #define __ASMARM_SETUP_H +#include <linux/screen_info.h> #include <uapi/asm/setup.h> @@ -35,4 +36,8 @@ void early_mm_init(const struct machine_desc *); void adjust_lowmem_bounds(void); void setup_dma_zone(const struct machine_desc *desc); +#ifdef CONFIG_VGA_CONSOLE +extern struct screen_info vgacon_screen_info; +#endif + #endif diff --git a/arch/arm/include/asm/vga.h b/arch/arm/include/asm/vga.h index 7c0bee57855a..6c430ec371df 100644 --- a/arch/arm/include/asm/vga.h +++ b/arch/arm/include/asm/vga.h @@ -5,6 +5,7 @@ #include <linux/io.h> extern unsigned long vga_base; +extern struct screen_info vgacon_screen_info; #define VGA_MAP_MEM(x,s) (vga_base + (x)) diff --git a/arch/arm/kernel/atags_parse.c b/arch/arm/kernel/atags_parse.c index 33f6eb5213a5..4ec591bde3df 100644 --- a/arch/arm/kernel/atags_parse.c +++ b/arch/arm/kernel/atags_parse.c @@ -69,18 +69,18 @@ static int __init parse_tag_mem32(const struct tag *tag) __tagtable(ATAG_MEM, parse_tag_mem32); -#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE) +#if defined(CONFIG_ARCH_FOOTBRIDGE) && defined(CONFIG_VGA_CONSOLE) static int __init parse_tag_videotext(const struct tag *tag) { - screen_info.orig_x = tag->u.videotext.x; - screen_info.orig_y = tag->u.videotext.y; - screen_info.orig_video_page = tag->u.videotext.video_page; - screen_info.orig_video_mode = tag->u.videotext.video_mode; - screen_info.orig_video_cols = tag->u.videotext.video_cols; - screen_info.orig_video_ega_bx = tag->u.videotext.video_ega_bx; - screen_info.orig_video_lines = tag->u.videotext.video_lines; - screen_info.orig_video_isVGA = tag->u.videotext.video_isvga; - screen_info.orig_video_points = tag->u.videotext.video_points; + vgacon_screen_info.orig_x = tag->u.videotext.x; + vgacon_screen_info.orig_y = tag->u.videotext.y; + vgacon_screen_info.orig_video_page = tag->u.videotext.video_page; + vgacon_screen_info.orig_video_mode = tag->u.videotext.video_mode; + vgacon_screen_info.orig_video_cols = tag->u.videotext.video_cols; + vgacon_screen_info.orig_video_ega_bx = tag->u.videotext.video_ega_bx; + vgacon_screen_info.orig_video_lines = tag->u.videotext.video_lines; + vgacon_screen_info.orig_video_isVGA = tag->u.videotext.video_isvga; + vgacon_screen_info.orig_video_points = tag->u.videotext.video_points; return 0; } diff --git a/arch/arm/kernel/efi.c b/arch/arm/kernel/efi.c index e94655ef16bb..6f9ec7d28a71 100644 --- a/arch/arm/kernel/efi.c +++ b/arch/arm/kernel/efi.c @@ -123,12 +123,6 @@ void __init arm_efi_init(void) { efi_init(); - if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI) { - /* dummycon on ARM needs non-zero values for columns/lines */ - screen_info.orig_video_cols = 80; - screen_info.orig_video_lines = 25; - } - /* ARM does not permit early mappings to persist across paging_init() */ efi_memmap_unmap(); diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index b01cac05bd4c..ff2299ce1ad7 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -928,9 +928,8 @@ static void __init request_standard_resources(const struct machine_desc *mdesc) request_resource(&ioport_resource, &lp2); } -#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE) || \ - defined(CONFIG_EFI) -struct screen_info screen_info = { +#if defined(CONFIG_VGA_CONSOLE) +struct screen_info vgacon_screen_info = { .orig_video_lines = 30, .orig_video_cols = 80, .orig_video_mode = 0, @@ -1194,7 +1193,7 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_VT #if defined(CONFIG_VGA_CONSOLE) - conswitchp = &vga_con; + vgacon_register_screen(&vgacon_screen_info); #endif #endif diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile index 515ca33b854c..d761bd2e2f40 100644 --- a/arch/arm/vdso/Makefile +++ b/arch/arm/vdso/Makefile @@ -63,28 +63,3 @@ quiet_cmd_vdsold_and_vdso_check = LD $@ quiet_cmd_vdsomunge = MUNGE $@ cmd_vdsomunge = $(objtree)/$(obj)/vdsomunge $< $@ - -# -# Install the unstripped copy of vdso.so.dbg. If our toolchain -# supports build-id, install .build-id links as well. -# -# Cribbed from arch/x86/vdso/Makefile. -# -quiet_cmd_vdso_install = INSTALL $< -define cmd_vdso_install - cp $< "$(MODLIB)/vdso/vdso.so"; \ - if readelf -n $< | grep -q 'Build ID'; then \ - buildid=`readelf -n $< |grep 'Build ID' |sed -e 's/^.*Build ID: \(.*\)$$/\1/'`; \ - first=`echo $$buildid | cut -b-2`; \ - last=`echo $$buildid | cut -b3-`; \ - mkdir -p "$(MODLIB)/vdso/.build-id/$$first"; \ - ln -sf "../../vdso.so" "$(MODLIB)/vdso/.build-id/$$first/$$last.debug"; \ - fi -endef - -$(MODLIB)/vdso: FORCE - @mkdir -p $(MODLIB)/vdso - -PHONY += vdso_install -vdso_install: $(obj)/vdso.so.dbg $(MODLIB)/vdso - $(call cmd,vdso_install) diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 2d49aea0ff67..4bd85cc0d32b 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -169,12 +169,6 @@ install: KBUILD_IMAGE := $(boot)/Image install zinstall: $(call cmd,install) -PHONY += vdso_install -vdso_install: - $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso $@ - $(if $(CONFIG_COMPAT_VDSO), \ - $(Q)$(MAKE) $(build)=arch/arm64/kernel/vdso32 $@) - archprepare: $(Q)$(MAKE) $(build)=arch/arm64/tools kapi ifeq ($(CONFIG_ARM64_ERRATUM_843419),y) @@ -205,6 +199,9 @@ ifdef CONFIG_COMPAT_VDSO endif endif +vdso-install-y += arch/arm64/kernel/vdso/vdso.so.dbg +vdso-install-$(CONFIG_COMPAT_VDSO) += arch/arm64/kernel/vdso32/vdso.so.dbg:vdso32.so + include $(srctree)/scripts/Makefile.defconf PHONY += virtconfig diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi index 4a74f3b6d775..bf7de35ffcbc 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi @@ -859,7 +859,7 @@ pinctrl-names = "default"; pinctrl-0 = <&scp_pins>; - cros_ec { + cros-ec-rpmsg { compatible = "google,cros-ec-rpmsg"; mediatek,rpmsg-name = "cros-ec-rpmsg"; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi index 1447eed0ea36..f2281250ac35 100644 --- a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi @@ -1312,7 +1312,7 @@ pinctrl-names = "default"; pinctrl-0 = <&scp_pins>; - cros-ec { + cros-ec-rpmsg { compatible = "google,cros-ec-rpmsg"; mediatek,rpmsg-name = "cros-ec-rpmsg"; }; diff --git a/arch/arm64/boot/dts/qcom/sm8550-mtp.dts b/arch/arm64/boot/dts/qcom/sm8550-mtp.dts index 5b3488736fbe..9a70875028b7 100644 --- a/arch/arm64/boot/dts/qcom/sm8550-mtp.dts +++ b/arch/arm64/boot/dts/qcom/sm8550-mtp.dts @@ -59,6 +59,7 @@ compatible = "qcom,sm8550-pmic-glink", "qcom,pmic-glink"; #address-cells = <1>; #size-cells = <0>; + orientation-gpios = <&tlmm 11 GPIO_ACTIVE_HIGH>; connector@0 { compatible = "usb-c-connector"; diff --git a/arch/arm64/boot/dts/qcom/sm8550-qrd.dts b/arch/arm64/boot/dts/qcom/sm8550-qrd.dts index 320662024e89..eef811def39b 100644 --- a/arch/arm64/boot/dts/qcom/sm8550-qrd.dts +++ b/arch/arm64/boot/dts/qcom/sm8550-qrd.dts @@ -77,6 +77,7 @@ compatible = "qcom,sm8550-pmic-glink", "qcom,pmic-glink"; #address-cells = <1>; #size-cells = <0>; + orientation-gpios = <&tlmm 11 GPIO_ACTIVE_HIGH>; connector@0 { compatible = "usb-c-connector"; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi index 2993e1255042..7064c0e9179f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588s.dtsi @@ -443,6 +443,27 @@ status = "disabled"; }; + usb_host2_xhci: usb@fcd00000 { + compatible = "rockchip,rk3588-dwc3", "snps,dwc3"; + reg = <0x0 0xfcd00000 0x0 0x400000>; + interrupts = <GIC_SPI 222 IRQ_TYPE_LEVEL_HIGH 0>; + clocks = <&cru REF_CLK_USB3OTG2>, <&cru SUSPEND_CLK_USB3OTG2>, + <&cru ACLK_USB3OTG2>, <&cru CLK_UTMI_OTG2>, + <&cru CLK_PIPEPHY2_PIPE_U3_G>; + clock-names = "ref_clk", "suspend_clk", "bus_clk", "utmi", "pipe"; + dr_mode = "host"; + phys = <&combphy2_psu PHY_TYPE_USB3>; + phy-names = "usb3-phy"; + phy_type = "utmi_wide"; + resets = <&cru SRST_A_USB3OTG2>; + snps,dis_enblslpm_quirk; + snps,dis-u2-freeclk-exists-quirk; + snps,dis-del-phy-power-chg-quirk; + snps,dis-tx-ipgap-linecheck-quirk; + snps,dis_rxdet_inp3_quirk; + status = "disabled"; + }; + pmu1grf: syscon@fd58a000 { compatible = "rockchip,rk3588-pmugrf", "syscon", "simple-mfd"; reg = <0x0 0xfd58a000 0x0 0x10000>; diff --git a/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts b/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts index 00891a0f8fc3..9a6bd0a3c94f 100644 --- a/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts +++ b/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts @@ -896,6 +896,12 @@ pinctrl-names = "default"; pinctrl-0 = <&wifi_debug_uart_pins_default>; status = "okay"; + + mcu { + compatible = "ti,cc1352p7"; + reset-gpios = <&main_gpio0 72 GPIO_ACTIVE_LOW>; + vdds-supply = <&vdd_3v3>; + }; }; &dss { diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 3f8c9c143552..0228001347be 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -71,10 +71,6 @@ static __init pteval_t create_mapping_protection(efi_memory_desc_t *md) return pgprot_val(PAGE_KERNEL_EXEC); } -/* we will fill this structure from the stub, so don't put it in .bss */ -struct screen_info screen_info __section(".data"); -EXPORT_SYMBOL(screen_info); - int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) { pteval_t prot_val = create_mapping_protection(md); diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 35f3c7959513..5e4dc72ab1bd 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -27,7 +27,9 @@ PROVIDE(__efistub__text = _text); PROVIDE(__efistub__end = _end); PROVIDE(__efistub___inittext_end = __inittext_end); PROVIDE(__efistub__edata = _edata); +#if defined(CONFIG_EFI_EARLYCON) || defined(CONFIG_SYSFB) PROVIDE(__efistub_screen_info = screen_info); +#endif PROVIDE(__efistub__ctype = _ctype); PROVIDE(__pi___memcpy = __pi_memcpy); diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index fe7a53c6781f..8818287f1095 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -78,13 +78,3 @@ include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE # Actual build commands quiet_cmd_vdsold_and_vdso_check = LD $@ cmd_vdsold_and_vdso_check = $(cmd_ld); $(cmd_vdso_check) - -# Install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ - -vdso.so: $(obj)/vdso.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso.so diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 2f73e5bca213..1f911a76c5af 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -172,13 +172,3 @@ gen-vdsosym := $(srctree)/$(src)/../vdso/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ # The AArch64 nm should be able to read an AArch32 binary cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ - -# Install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL32 $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/vdso32.so - -vdso.so: $(obj)/vdso.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso.so diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c index 106fbf0b6f3b..51012e90780d 100644 --- a/arch/csky/kernel/setup.c +++ b/arch/csky/kernel/setup.c @@ -8,22 +8,10 @@ #include <linux/of_fdt.h> #include <linux/start_kernel.h> #include <linux/dma-map-ops.h> -#include <linux/screen_info.h> #include <asm/sections.h> #include <asm/mmu_context.h> #include <asm/pgalloc.h> -#ifdef CONFIG_DUMMY_CONSOLE -struct screen_info screen_info = { - .orig_video_lines = 30, - .orig_video_cols = 80, - .orig_video_mode = 0, - .orig_video_ega_bx = 0, - .orig_video_isVGA = 1, - .orig_video_points = 8 -}; -#endif - static void __init csky_memblock_init(void) { unsigned long lowmem_size = PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET); diff --git a/arch/csky/kernel/vdso/Makefile b/arch/csky/kernel/vdso/Makefile index 299e4e41ebc5..ddf784a62c11 100644 --- a/arch/csky/kernel/vdso/Makefile +++ b/arch/csky/kernel/vdso/Makefile @@ -58,13 +58,3 @@ quiet_cmd_vdsold = VDSOLD $@ # that contains the same symbols at the same offsets. quiet_cmd_so2s = SO2S $@ cmd_so2s = $(NM) -D $< | $(srctree)/$(src)/so2s.sh > $@ - -# install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ - -vdso.so: $(obj)/vdso.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso.so diff --git a/arch/hexagon/kernel/Makefile b/arch/hexagon/kernel/Makefile index e73cb321630e..3fdf937eb572 100644 --- a/arch/hexagon/kernel/Makefile +++ b/arch/hexagon/kernel/Makefile @@ -17,5 +17,3 @@ obj-y += vm_vectors.o obj-$(CONFIG_HAS_DMA) += dma.o obj-$(CONFIG_STACKTRACE) += stacktrace.o - -obj-$(CONFIG_VGA_CONSOLE) += screen_info.o diff --git a/arch/hexagon/kernel/screen_info.c b/arch/hexagon/kernel/screen_info.c deleted file mode 100644 index 1e1ceb18bafe..000000000000 --- a/arch/hexagon/kernel/screen_info.c +++ /dev/null @@ -1,3 +0,0 @@ -#include <linux/screen_info.h> - -struct screen_info screen_info; diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index fb0fada43197..b86f2ff31659 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -136,9 +136,7 @@ vdso_prepare: prepare0 $(Q)$(MAKE) $(build)=arch/loongarch/vdso include/generated/vdso-offsets.h endif -PHONY += vdso_install -vdso_install: - $(Q)$(MAKE) $(build)=arch/loongarch/vdso $@ +vdso-install-y += arch/loongarch/vdso/vdso.so.dbg all: $(notdir $(KBUILD_IMAGE)) diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c index 9fc10cea21e1..acb5d3385675 100644 --- a/arch/loongarch/kernel/efi.c +++ b/arch/loongarch/kernel/efi.c @@ -68,6 +68,11 @@ void __init efi_runtime_init(void) unsigned long __initdata screen_info_table = EFI_INVALID_TABLE_ADDR; +#if defined(CONFIG_SYSFB) || defined(CONFIG_EFI_EARLYCON) +struct screen_info screen_info __section(".data"); +EXPORT_SYMBOL_GPL(screen_info); +#endif + static void __init init_screen_info(void) { struct screen_info *si; @@ -115,7 +120,8 @@ void __init efi_init(void) set_bit(EFI_CONFIG_TABLES, &efi.flags); - init_screen_info(); + if (IS_ENABLED(CONFIG_EFI_EARLYCON) || IS_ENABLED(CONFIG_SYSFB)) + init_screen_info(); if (boot_memmap == EFI_INVALID_TABLE_ADDR) return; diff --git a/arch/loongarch/kernel/image-vars.h b/arch/loongarch/kernel/image-vars.h index e561989d02de..5087416b9678 100644 --- a/arch/loongarch/kernel/image-vars.h +++ b/arch/loongarch/kernel/image-vars.h @@ -12,7 +12,9 @@ __efistub_kernel_entry = kernel_entry; __efistub_kernel_asize = kernel_asize; __efistub_kernel_fsize = kernel_fsize; __efistub_kernel_offset = kernel_offset; +#if defined(CONFIG_EFI_EARLYCON) || defined(CONFIG_SYSFB) __efistub_screen_info = screen_info; +#endif #endif diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index b35186f7b254..d183a745fb85 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -16,7 +16,6 @@ #include <linux/dmi.h> #include <linux/efi.h> #include <linux/export.h> -#include <linux/screen_info.h> #include <linux/memblock.h> #include <linux/initrd.h> #include <linux/ioport.h> @@ -57,8 +56,6 @@ #define SMBIOS_CORE_PACKAGE_OFFSET 0x23 #define LOONGSON_EFI_ENABLE (1 << 3) -struct screen_info screen_info __section(".data"); - unsigned long fw_arg0, fw_arg1, fw_arg2; DEFINE_PER_CPU(unsigned long, kernelsp); struct cpuinfo_loongarch cpu_data[NR_CPUS] __read_mostly; diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile index 5c97d1463328..c74c9921304f 100644 --- a/arch/loongarch/vdso/Makefile +++ b/arch/loongarch/vdso/Makefile @@ -83,13 +83,3 @@ $(obj)/vdso.so: $(obj)/vdso.so.dbg FORCE obj-y += vdso.o $(obj)/vdso.o : $(obj)/vdso.so - -# install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ - -vdso.so: $(obj)/vdso.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso.so diff --git a/arch/mips/Makefile.postlink b/arch/mips/Makefile.postlink index 34e3bd71f3b0..6cfdc149d3bc 100644 --- a/arch/mips/Makefile.postlink +++ b/arch/mips/Makefile.postlink @@ -31,9 +31,6 @@ ifeq ($(CONFIG_RELOCATABLE),y) $(call if_changed,relocs) endif -%.ko: FORCE - @true - clean: @true diff --git a/arch/mips/jazz/setup.c b/arch/mips/jazz/setup.c index 04aab419a0fc..e318ea11c858 100644 --- a/arch/mips/jazz/setup.c +++ b/arch/mips/jazz/setup.c @@ -13,7 +13,6 @@ #include <linux/init.h> #include <linux/ioport.h> #include <linux/console.h> -#include <linux/screen_info.h> #include <linux/platform_device.h> #include <linux/serial_8250.h> #include <linux/dma-mapping.h> @@ -76,14 +75,6 @@ void __init plat_mem_setup(void) _machine_restart = jazz_machine_restart; -#ifdef CONFIG_VT - screen_info = (struct screen_info) { - .orig_video_cols = 160, - .orig_video_lines = 64, - .orig_video_points = 16, - }; -#endif - add_preferred_console("ttyS", 0, "9600"); } diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 08321c945ac4..2d2ca024bd47 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -15,7 +15,6 @@ #include <linux/delay.h> #include <linux/ioport.h> #include <linux/export.h> -#include <linux/screen_info.h> #include <linux/memblock.h> #include <linux/initrd.h> #include <linux/root_dev.h> @@ -54,10 +53,6 @@ struct cpuinfo_mips cpu_data[NR_CPUS] __read_mostly; EXPORT_SYMBOL(cpu_data); -#ifdef CONFIG_VT -struct screen_info screen_info; -#endif - /* * Setup information * @@ -793,12 +788,6 @@ void __init setup_arch(char **cmdline_p) if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64)) check_bugs64_early(); -#if defined(CONFIG_VT) -#if defined(CONFIG_VGA_CONSOLE) - conswitchp = &vga_con; -#endif -#endif - arch_mem_init(cmdline_p); dmi_setup(); diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c index 21cb3ac1237b..3a2836e9d856 100644 --- a/arch/mips/mti-malta/malta-setup.c +++ b/arch/mips/mti-malta/malta-setup.c @@ -161,7 +161,7 @@ static void __init pci_clock_check(void) #if defined(CONFIG_VT) && defined(CONFIG_VGA_CONSOLE) static void __init screen_info_setup(void) { - screen_info = (struct screen_info) { + static struct screen_info si = { .orig_x = 0, .orig_y = 25, .ext_mem_k = 0, @@ -175,6 +175,8 @@ static void __init screen_info_setup(void) .orig_video_isVGA = VIDEO_TYPE_VGAC, .orig_video_points = 16 }; + + vgacon_register_screen(&si); } #endif diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c index 76683993cdd3..38c90b5e8754 100644 --- a/arch/mips/sibyte/swarm/setup.c +++ b/arch/mips/sibyte/swarm/setup.c @@ -13,6 +13,7 @@ #include <linux/memblock.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/console.h> #include <linux/screen_info.h> #include <linux/initrd.h> @@ -112,6 +113,19 @@ int update_persistent_clock64(struct timespec64 now) } } +#ifdef CONFIG_VGA_CONSOLE +static struct screen_info vgacon_screen_info = { + .orig_video_page = 52, + .orig_video_mode = 3, + .orig_video_cols = 80, + .flags = 12, + .orig_video_ega_bx = 3, + .orig_video_lines = 25, + .orig_video_isVGA = 0x22, + .orig_video_points = 16, +}; +#endif + void __init plat_mem_setup(void) { #ifdef CONFIG_SIBYTE_BCM1x80 @@ -129,17 +143,8 @@ void __init plat_mem_setup(void) if (m41t81_probe()) swarm_rtc_type = RTC_M41T81; -#ifdef CONFIG_VT - screen_info = (struct screen_info) { - .orig_video_page = 52, - .orig_video_mode = 3, - .orig_video_cols = 80, - .flags = 12, - .orig_video_ega_bx = 3, - .orig_video_lines = 25, - .orig_video_isVGA = 0x22, - .orig_video_points = 16, - }; +#ifdef CONFIG_VGA_CONSOLE + vgacon_register_screen(&vgacon_screen_info); /* XXXKW for CFE, get lines/cols from environment */ #endif } diff --git a/arch/mips/sni/setup.c b/arch/mips/sni/setup.c index efad85c8c823..42fdb939c88d 100644 --- a/arch/mips/sni/setup.c +++ b/arch/mips/sni/setup.c @@ -38,19 +38,21 @@ extern void sni_machine_power_off(void); static void __init sni_display_setup(void) { -#if defined(CONFIG_VT) && defined(CONFIG_VGA_CONSOLE) && defined(CONFIG_FW_ARC) - struct screen_info *si = &screen_info; +#if defined(CONFIG_VGA_CONSOLE) && defined(CONFIG_FW_ARC) + static struct screen_info si; DISPLAY_STATUS *di; di = ArcGetDisplayStatus(1); if (di) { - si->orig_x = di->CursorXPosition; - si->orig_y = di->CursorYPosition; - si->orig_video_cols = di->CursorMaxXPosition; - si->orig_video_lines = di->CursorMaxYPosition; - si->orig_video_isVGA = VIDEO_TYPE_VGAC; - si->orig_video_points = 16; + si.orig_x = di->CursorXPosition; + si.orig_y = di->CursorYPosition; + si.orig_video_cols = di->CursorMaxXPosition; + si.orig_video_lines = di->CursorMaxYPosition; + si.orig_video_isVGA = VIDEO_TYPE_VGAC; + si.orig_video_points = 16; + + vgacon_register_screen(&si); } #endif } diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c index 8582ed965844..da122a5fa43b 100644 --- a/arch/nios2/kernel/setup.c +++ b/arch/nios2/kernel/setup.c @@ -19,7 +19,6 @@ #include <linux/memblock.h> #include <linux/initrd.h> #include <linux/of_fdt.h> -#include <linux/screen_info.h> #include <asm/mmu_context.h> #include <asm/sections.h> @@ -36,10 +35,6 @@ static struct pt_regs fake_regs = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0}; -#ifdef CONFIG_VT -struct screen_info screen_info; -#endif - /* Copy a short hook instruction sequence to the exception address */ static inline void copy_exception_handler(unsigned int addr) { diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile index 968ebe17494c..920db57b6b4c 100644 --- a/arch/parisc/Makefile +++ b/arch/parisc/Makefile @@ -177,12 +177,8 @@ vdso_prepare: prepare0 $(Q)$(MAKE) $(build)=arch/parisc/kernel/vdso32 include/generated/vdso32-offsets.h endif -PHONY += vdso_install - -vdso_install: - $(Q)$(MAKE) $(build)=arch/parisc/kernel/vdso $@ - $(if $(CONFIG_COMPAT_VDSO), \ - $(Q)$(MAKE) $(build)=arch/parisc/kernel/vdso32 $@) +vdso-install-y += arch/parisc/kernel/vdso32/vdso32.so +vdso-install-$(CONFIG_64BIT) += arch/parisc/kernel/vdso64/vdso64.so install: KBUILD_IMAGE := vmlinux zinstall: KBUILD_IMAGE := vmlinuz diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig index f6ded7147b4d..19a804860ed5 100644 --- a/arch/parisc/configs/generic-64bit_defconfig +++ b/arch/parisc/configs/generic-64bit_defconfig @@ -248,7 +248,6 @@ CONFIG_UIO_AEC=m CONFIG_UIO_SERCOS3=m CONFIG_UIO_PCI_GENERIC=m CONFIG_STAGING=y -CONFIG_QLGE=m CONFIG_EXT2_FS=y CONFIG_EXT2_FS_XATTR=y CONFIG_EXT2_FS_SECURITY=y diff --git a/arch/powerpc/Makefile.postlink b/arch/powerpc/Makefile.postlink index 1f860b3c9bec..ae5a4256b03d 100644 --- a/arch/powerpc/Makefile.postlink +++ b/arch/powerpc/Makefile.postlink @@ -35,9 +35,6 @@ ifdef CONFIG_RELOCATABLE $(call if_changed,relocs_check) endif -%.ko: FORCE - @true - clean: rm -f .tmp_symbols.txt diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index ca92cf0ffde1..9b142b9d5187 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -22,7 +22,6 @@ #include <linux/seq_file.h> #include <linux/ioport.h> #include <linux/console.h> -#include <linux/screen_info.h> #include <linux/root_dev.h> #include <linux/cpu.h> #include <linux/unistd.h> @@ -98,21 +97,6 @@ int boot_cpu_hwid = -1; int dcache_bsize; int icache_bsize; -/* - * This still seems to be needed... -- paulus - */ -struct screen_info screen_info = { - .orig_x = 0, - .orig_y = 25, - .orig_video_cols = 80, - .orig_video_lines = 25, - .orig_video_isVGA = 1, - .orig_video_points = 16 -}; -#if defined(CONFIG_FB_VGA16_MODULE) -EXPORT_SYMBOL(screen_info); -#endif - /* Variables required to store legacy IO irq routing */ int of_i8042_kbd_irq; EXPORT_SYMBOL_GPL(of_i8042_kbd_irq); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index eaa15a20e6ae..18b03ad0e6b9 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -39,6 +39,7 @@ config RISCV select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST select ARCH_HAS_UBSAN_SANITIZE_ALL select ARCH_HAS_VDSO_DATA + select ARCH_KEEP_MEMBLOCK if ACPI select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT select ARCH_STACKWALK @@ -48,6 +49,7 @@ config RISCV select ARCH_SUPPORTS_HUGETLBFS if MMU select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU select ARCH_SUPPORTS_PER_VMA_LOCK if MMU + select ARCH_SUPPORTS_SHADOW_CALL_STACK if HAVE_SHADOW_CALL_STACK select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS select ARCH_USES_CFI_TRAPS if CFI_CLANG @@ -174,6 +176,11 @@ config GCC_SUPPORTS_DYNAMIC_FTRACE def_bool CC_IS_GCC depends on $(cc-option,-fpatchable-function-entry=8) +config HAVE_SHADOW_CALL_STACK + def_bool $(cc-option,-fsanitize=shadow-call-stack) + # https://github.com/riscv-non-isa/riscv-elf-psabi-doc/commit/a484e843e6eeb51f0cb7b8819e50da6d2444d769 + depends on $(ld-option,--no-relax-gp) + config ARCH_MMAP_RND_BITS_MIN default 18 if 64BIT default 8 diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index b43a6bb7e4dc..a74be78678eb 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -54,6 +54,10 @@ endif endif endif +ifeq ($(CONFIG_SHADOW_CALL_STACK),y) + KBUILD_LDFLAGS += --no-relax-gp +endif + # ISA string setting riscv-march-$(CONFIG_ARCH_RV32I) := rv32ima riscv-march-$(CONFIG_ARCH_RV64I) := rv64ima @@ -130,12 +134,6 @@ endif libs-y += arch/riscv/lib/ libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a -PHONY += vdso_install -vdso_install: - $(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso $@ - $(if $(CONFIG_COMPAT),$(Q)$(MAKE) \ - $(build)=arch/riscv/kernel/compat_vdso compat_$@) - ifeq ($(KBUILD_EXTMOD),) ifeq ($(CONFIG_MMU),y) prepare: vdso_prepare @@ -147,6 +145,9 @@ vdso_prepare: prepare0 endif endif +vdso-install-y += arch/riscv/kernel/vdso/vdso.so.dbg +vdso-install-$(CONFIG_COMPAT) += arch/riscv/kernel/compat_vdso/compat_vdso.so.dbg:../compat_vdso/compat_vdso.so + ifneq ($(CONFIG_XIP_KERNEL),y) ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_ARCH_CANAAN),yy) KBUILD_IMAGE := $(boot)/loader.bin diff --git a/arch/riscv/Makefile.postlink b/arch/riscv/Makefile.postlink index a46fc578b30b..829b9abc91f6 100644 --- a/arch/riscv/Makefile.postlink +++ b/arch/riscv/Makefile.postlink @@ -36,9 +36,6 @@ ifdef CONFIG_RELOCATABLE $(call if_changed,relocs_strip) endif -%.ko: FORCE - @true - clean: @true diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index 1edf3cd886c5..938fa07ddf77 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -37,6 +37,13 @@ CONFIG_SMP=y CONFIG_HOTPLUG_CPU=y CONFIG_PM=y CONFIG_CPU_IDLE=y +CONFIG_CPU_FREQ=y +CONFIG_CPU_FREQ_STAT=y +CONFIG_CPU_FREQ_GOV_POWERSAVE=m +CONFIG_CPU_FREQ_GOV_USERSPACE=y +CONFIG_CPU_FREQ_GOV_ONDEMAND=y +CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m +CONFIG_CPUFREQ_DT=y CONFIG_VIRTUALIZATION=y CONFIG_KVM=m CONFIG_ACPI=y @@ -95,6 +102,7 @@ CONFIG_NETLINK_DIAG=y CONFIG_CGROUP_NET_PRIO=y CONFIG_NET_9P=y CONFIG_NET_9P_VIRTIO=y +CONFIG_CAN=m CONFIG_PCI=y CONFIG_PCIEPORTBUS=y CONFIG_PCI_HOST_GENERIC=y @@ -102,6 +110,11 @@ CONFIG_PCIE_XILINX=y CONFIG_PCIE_FU740=y CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y +CONFIG_MTD=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_CFI=y +CONFIG_MTD_CFI_ADV_OPTIONS=y +CONFIG_MTD_SPI_NOR=y CONFIG_BLK_DEV_LOOP=y CONFIG_VIRTIO_BLK=y CONFIG_BLK_DEV_NVME=m @@ -124,8 +137,11 @@ CONFIG_VIRTIO_NET=y CONFIG_MACB=y CONFIG_E1000E=y CONFIG_R8169=y +CONFIG_RAVB=y CONFIG_STMMAC_ETH=m +CONFIG_MICREL_PHY=y CONFIG_MICROSEMI_PHY=y +CONFIG_CAN_RCAR_CANFD=m CONFIG_INPUT_MOUSEDEV=y CONFIG_KEYBOARD_SUN4I_LRADC=m CONFIG_SERIAL_8250=y @@ -136,16 +152,24 @@ CONFIG_SERIAL_SH_SCI=y CONFIG_VIRTIO_CONSOLE=y CONFIG_HW_RANDOM=y CONFIG_HW_RANDOM_VIRTIO=y +CONFIG_I2C_CHARDEV=m CONFIG_I2C_MV64XXX=m +CONFIG_I2C_RIIC=y CONFIG_SPI=y +CONFIG_SPI_RSPI=m CONFIG_SPI_SIFIVE=y CONFIG_SPI_SUN6I=y # CONFIG_PTP_1588_CLOCK is not set CONFIG_GPIO_SIFIVE=y +CONFIG_CPU_THERMAL=y +CONFIG_DEVFREQ_THERMAL=y +CONFIG_RZG2L_THERMAL=y CONFIG_WATCHDOG=y CONFIG_SUNXI_WATCHDOG=y +CONFIG_RENESAS_RZG2LWDT=y CONFIG_REGULATOR=y CONFIG_REGULATOR_FIXED_VOLTAGE=y +CONFIG_REGULATOR_GPIO=y CONFIG_DRM=m CONFIG_DRM_RADEON=m CONFIG_DRM_NOUVEAU=m @@ -153,39 +177,67 @@ CONFIG_DRM_SUN4I=m CONFIG_DRM_VIRTIO_GPU=m CONFIG_FB=y CONFIG_FRAMEBUFFER_CONSOLE=y +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_SND_SOC=y +CONFIG_SND_SOC_RZ=m +CONFIG_SND_SOC_WM8978=m +CONFIG_SND_SIMPLE_CARD=m CONFIG_USB=y +CONFIG_USB_OTG=y CONFIG_USB_XHCI_HCD=y CONFIG_USB_XHCI_PLATFORM=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_HCD_PLATFORM=y CONFIG_USB_OHCI_HCD=y CONFIG_USB_OHCI_HCD_PLATFORM=y +CONFIG_USB_RENESAS_USBHS=m CONFIG_USB_STORAGE=y CONFIG_USB_UAS=y CONFIG_USB_MUSB_HDRC=m CONFIG_USB_MUSB_SUNXI=m CONFIG_NOP_USB_XCEIV=m +CONFIG_USB_GADGET=y +CONFIG_USB_RENESAS_USBHS_UDC=m +CONFIG_USB_CONFIGFS=m +CONFIG_USB_CONFIGFS_SERIAL=y +CONFIG_USB_CONFIGFS_ACM=y +CONFIG_USB_CONFIGFS_OBEX=y +CONFIG_USB_CONFIGFS_NCM=y +CONFIG_USB_CONFIGFS_ECM=y +CONFIG_USB_CONFIGFS_ECM_SUBSET=y +CONFIG_USB_CONFIGFS_RNDIS=y +CONFIG_USB_CONFIGFS_EEM=y +CONFIG_USB_CONFIGFS_MASS_STORAGE=y +CONFIG_USB_CONFIGFS_F_FS=y CONFIG_MMC=y CONFIG_MMC_SDHCI=y CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_SDHCI_CADENCE=y CONFIG_MMC_SPI=y +CONFIG_MMC_SDHI=y CONFIG_MMC_SUNXI=y CONFIG_RTC_CLASS=y CONFIG_RTC_DRV_SUN6I=y CONFIG_DMADEVICES=y CONFIG_DMA_SUN6I=m +CONFIG_RZ_DMAC=y CONFIG_VIRTIO_PCI=y CONFIG_VIRTIO_BALLOON=y CONFIG_VIRTIO_INPUT=y CONFIG_VIRTIO_MMIO=y +CONFIG_RENESAS_OSTM=y CONFIG_SUN8I_DE2_CCU=m CONFIG_SUN50I_IOMMU=y CONFIG_RPMSG_CHAR=y CONFIG_RPMSG_CTRL=y CONFIG_RPMSG_VIRTIO=y CONFIG_ARCH_R9A07G043=y +CONFIG_IIO=y +CONFIG_RZG2L_ADC=m +CONFIG_RESET_RZG2L_USBPHY_CTRL=y CONFIG_PHY_SUN4I_USB=m +CONFIG_PHY_RCAR_GEN3_USB2=y CONFIG_LIBNVDIMM=y CONFIG_NVMEM_SUNXI_SID=y CONFIG_EXT4_FS=y diff --git a/arch/riscv/include/asm/acpi.h b/arch/riscv/include/asm/acpi.h index d5604d2073bc..7dad0cf9d701 100644 --- a/arch/riscv/include/asm/acpi.h +++ b/arch/riscv/include/asm/acpi.h @@ -66,6 +66,8 @@ int acpi_get_riscv_isa(struct acpi_table_header *table, unsigned int cpu, const char **isa); static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; } +void acpi_get_cbo_block_size(struct acpi_table_header *table, u32 *cbom_size, + u32 *cboz_size, u32 *cbop_size); #else static inline void acpi_init_rintc_map(void) { } static inline struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu) @@ -79,6 +81,10 @@ static inline int acpi_get_riscv_isa(struct acpi_table_header *table, return -EINVAL; } +static inline void acpi_get_cbo_block_size(struct acpi_table_header *table, + u32 *cbom_size, u32 *cboz_size, + u32 *cbop_size) { } + #endif /* CONFIG_ACPI */ #endif /*_ASM_ACPI_H*/ diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h index 61ba8ed43d8f..36b955c762ba 100644 --- a/arch/riscv/include/asm/asm-prototypes.h +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -25,7 +25,6 @@ DECLARE_DO_ERROR_INFO(do_trap_ecall_s); DECLARE_DO_ERROR_INFO(do_trap_ecall_m); DECLARE_DO_ERROR_INFO(do_trap_break); -asmlinkage unsigned long get_overflow_stack(void); asmlinkage void handle_bad_stack(struct pt_regs *regs); asmlinkage void do_page_fault(struct pt_regs *regs); asmlinkage void do_irq(struct pt_regs *regs); diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h index 114bbadaef41..b0487b39e674 100644 --- a/arch/riscv/include/asm/asm.h +++ b/arch/riscv/include/asm/asm.h @@ -82,6 +82,47 @@ .endr .endm +#ifdef CONFIG_SMP +#ifdef CONFIG_32BIT +#define PER_CPU_OFFSET_SHIFT 2 +#else +#define PER_CPU_OFFSET_SHIFT 3 +#endif + +.macro asm_per_cpu dst sym tmp + REG_L \tmp, TASK_TI_CPU_NUM(tp) + slli \tmp, \tmp, PER_CPU_OFFSET_SHIFT + la \dst, __per_cpu_offset + add \dst, \dst, \tmp + REG_L \tmp, 0(\dst) + la \dst, \sym + add \dst, \dst, \tmp +.endm +#else /* CONFIG_SMP */ +.macro asm_per_cpu dst sym tmp + la \dst, \sym +.endm +#endif /* CONFIG_SMP */ + +.macro load_per_cpu dst ptr tmp + asm_per_cpu \dst \ptr \tmp + REG_L \dst, 0(\dst) +.endm + +#ifdef CONFIG_SHADOW_CALL_STACK +/* gp is used as the shadow call stack pointer instead */ +.macro load_global_pointer +.endm +#else +/* load __global_pointer to gp */ +.macro load_global_pointer +.option push +.option norelax + la gp, __global_pointer$ +.option pop +.endm +#endif /* CONFIG_SHADOW_CALL_STACK */ + /* save all GPs except x1 ~ x5 */ .macro save_from_x6_to_x31 REG_S x6, PT_T1(sp) diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h index d0345bd659c9..13b7d35648a9 100644 --- a/arch/riscv/include/asm/cpufeature.h +++ b/arch/riscv/include/asm/cpufeature.h @@ -31,5 +31,6 @@ DECLARE_PER_CPU(long, misaligned_access_speed); extern struct riscv_isainfo hart_isa[NR_CPUS]; void check_unaligned_access(int cpu); +void riscv_user_isa_enable(void); #endif diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h index b55b434f0059..0ac18a4135be 100644 --- a/arch/riscv/include/asm/errata_list.h +++ b/arch/riscv/include/asm/errata_list.h @@ -95,25 +95,25 @@ asm volatile(ALTERNATIVE( \ #endif /* - * dcache.ipa rs1 (invalidate, physical address) + * th.dcache.ipa rs1 (invalidate, physical address) * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | * 0000001 01010 rs1 000 00000 0001011 - * dache.iva rs1 (invalida, virtual address) + * th.dache.iva rs1 (invalida, virtual address) * 0000001 00110 rs1 000 00000 0001011 * - * dcache.cpa rs1 (clean, physical address) + * th.dcache.cpa rs1 (clean, physical address) * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | * 0000001 01001 rs1 000 00000 0001011 - * dcache.cva rs1 (clean, virtual address) + * th.dcache.cva rs1 (clean, virtual address) * 0000001 00101 rs1 000 00000 0001011 * - * dcache.cipa rs1 (clean then invalidate, physical address) + * th.dcache.cipa rs1 (clean then invalidate, physical address) * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | * 0000001 01011 rs1 000 00000 0001011 - * dcache.civa rs1 (... virtual address) + * th.dcache.civa rs1 (... virtual address) * 0000001 00111 rs1 000 00000 0001011 * - * sync.s (make sure all cache operations finished) + * th.sync.s (make sure all cache operations finished) * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | * 0000000 11001 00000 000 00000 0001011 */ diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 6fc51c1b34cf..fe6656af967a 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -72,6 +72,7 @@ #ifndef __ASSEMBLY__ #include <linux/jump_label.h> +#include <asm/cpufeature.h> unsigned long riscv_get_elf_hwcap(void); @@ -139,6 +140,21 @@ l_yes: return true; } +static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext) +{ + if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_likely(ext)) + return true; + + return __riscv_isa_extension_available(hart_isa[cpu].isa, ext); +} + +static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsigned long ext) +{ + if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && riscv_has_extension_unlikely(ext)) + return true; + + return __riscv_isa_extension_available(hart_isa[cpu].isa, ext); +} #endif #endif /* _ASM_RISCV_HWCAP_H */ diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h index 78936f4ff513..5c48f48e79a6 100644 --- a/arch/riscv/include/asm/hwprobe.h +++ b/arch/riscv/include/asm/hwprobe.h @@ -8,6 +8,11 @@ #include <uapi/asm/hwprobe.h> -#define RISCV_HWPROBE_MAX_KEY 5 +#define RISCV_HWPROBE_MAX_KEY 6 + +static inline bool riscv_hwprobe_key_is_valid(__s64 key) +{ + return key >= 0 && key <= RISCV_HWPROBE_MAX_KEY; +} #endif diff --git a/arch/riscv/include/asm/irq_stack.h b/arch/riscv/include/asm/irq_stack.h index e4042d297580..6441ded3b0cf 100644 --- a/arch/riscv/include/asm/irq_stack.h +++ b/arch/riscv/include/asm/irq_stack.h @@ -12,6 +12,9 @@ DECLARE_PER_CPU(ulong *, irq_stack_ptr); +asmlinkage void call_on_irq_stack(struct pt_regs *regs, + void (*func)(struct pt_regs *)); + #ifdef CONFIG_VMAP_STACK /* * To ensure that VMAP'd stack overflow detection works correctly, all VMAP'd diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 5488ecc337b6..57e887bfa34c 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -33,8 +33,8 @@ #define PAGE_OFFSET _AC(CONFIG_PAGE_OFFSET, UL) #endif /* - * By default, CONFIG_PAGE_OFFSET value corresponds to SV48 address space so - * define the PAGE_OFFSET value for SV39. + * By default, CONFIG_PAGE_OFFSET value corresponds to SV57 address space so + * define the PAGE_OFFSET value for SV48 and SV39. */ #define PAGE_OFFSET_L4 _AC(0xffffaf8000000000, UL) #define PAGE_OFFSET_L3 _AC(0xffffffd800000000, UL) diff --git a/arch/riscv/include/asm/pgtable-32.h b/arch/riscv/include/asm/pgtable-32.h index 59ba1fbaf784..00f3369570a8 100644 --- a/arch/riscv/include/asm/pgtable-32.h +++ b/arch/riscv/include/asm/pgtable-32.h @@ -33,4 +33,7 @@ _PAGE_WRITE | _PAGE_EXEC | \ _PAGE_USER | _PAGE_GLOBAL)) +static const __maybe_unused int pgtable_l4_enabled; +static const __maybe_unused int pgtable_l5_enabled; + #endif /* _ASM_RISCV_PGTABLE_32_H */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index b2ba3f79cfe9..c8e8867c42f6 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -811,7 +811,7 @@ extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, * bit 5: _PAGE_PROT_NONE (zero) * bit 6: exclusive marker * bits 7 to 11: swap type - * bits 11 to XLEN-1: swap offset + * bits 12 to XLEN-1: swap offset */ #define __SWP_TYPE_SHIFT 7 #define __SWP_TYPE_BITS 5 @@ -914,7 +914,6 @@ extern uintptr_t _dtb_early_pa; #define dtb_early_pa _dtb_early_pa #endif /* CONFIG_XIP_KERNEL */ extern u64 satp_mode; -extern bool pgtable_l4_enabled; void paging_init(void); void misc_mem_init(void); diff --git a/arch/riscv/include/asm/scs.h b/arch/riscv/include/asm/scs.h new file mode 100644 index 000000000000..0e45db78b24b --- /dev/null +++ b/arch/riscv/include/asm/scs.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_SCS_H +#define _ASM_SCS_H + +#ifdef __ASSEMBLY__ +#include <asm/asm-offsets.h> + +#ifdef CONFIG_SHADOW_CALL_STACK + +/* Load init_shadow_call_stack to gp. */ +.macro scs_load_init_stack + la gp, init_shadow_call_stack + XIP_FIXUP_OFFSET gp +.endm + +/* Load the per-CPU IRQ shadow call stack to gp. */ +.macro scs_load_irq_stack tmp + load_per_cpu gp, irq_shadow_call_stack_ptr, \tmp +.endm + +/* Load task_scs_sp(current) to gp. */ +.macro scs_load_current + REG_L gp, TASK_TI_SCS_SP(tp) +.endm + +/* Load task_scs_sp(current) to gp, but only if tp has changed. */ +.macro scs_load_current_if_task_changed prev + beq \prev, tp, _skip_scs + scs_load_current +_skip_scs: +.endm + +/* Save gp to task_scs_sp(current). */ +.macro scs_save_current + REG_S gp, TASK_TI_SCS_SP(tp) +.endm + +#else /* CONFIG_SHADOW_CALL_STACK */ + +.macro scs_load_init_stack +.endm +.macro scs_load_irq_stack tmp +.endm +.macro scs_load_current +.endm +.macro scs_load_current_if_task_changed prev +.endm +.macro scs_save_current +.endm + +#endif /* CONFIG_SHADOW_CALL_STACK */ +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_SCS_H */ diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h index 1833beb00489..574779900bfb 100644 --- a/arch/riscv/include/asm/thread_info.h +++ b/arch/riscv/include/asm/thread_info.h @@ -34,9 +34,6 @@ #ifndef __ASSEMBLY__ -extern long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE / sizeof(long)]; -extern unsigned long spin_shadow_stack; - #include <asm/processor.h> #include <asm/csr.h> @@ -60,8 +57,20 @@ struct thread_info { long user_sp; /* User stack pointer */ int cpu; unsigned long syscall_work; /* SYSCALL_WORK_ flags */ +#ifdef CONFIG_SHADOW_CALL_STACK + void *scs_base; + void *scs_sp; +#endif }; +#ifdef CONFIG_SHADOW_CALL_STACK +#define INIT_SCS \ + .scs_base = init_shadow_call_stack, \ + .scs_sp = init_shadow_call_stack, +#else +#define INIT_SCS +#endif + /* * macros/functions for gaining access to the thread information structure * @@ -71,6 +80,7 @@ struct thread_info { { \ .flags = 0, \ .preempt_count = INIT_PREEMPT_COUNT, \ + INIT_SCS \ } void arch_release_task_struct(struct task_struct *tsk); diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h index 14f5d27783b8..96b65a5396df 100644 --- a/arch/riscv/include/asm/vdso/processor.h +++ b/arch/riscv/include/asm/vdso/processor.h @@ -14,7 +14,7 @@ static inline void cpu_relax(void) __asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy)); #endif -#ifdef __riscv_zihintpause +#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE /* * Reduce instruction retirement. * This assumes the PC changes. diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h index d43e306ce2f9..b659ffcfcdb4 100644 --- a/arch/riscv/include/uapi/asm/hwprobe.h +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -29,6 +29,7 @@ struct riscv_hwprobe { #define RISCV_HWPROBE_EXT_ZBA (1 << 3) #define RISCV_HWPROBE_EXT_ZBB (1 << 4) #define RISCV_HWPROBE_EXT_ZBS (1 << 5) +#define RISCV_HWPROBE_EXT_ZICBOZ (1 << 6) #define RISCV_HWPROBE_KEY_CPUPERF_0 5 #define RISCV_HWPROBE_MISALIGNED_UNKNOWN (0 << 0) #define RISCV_HWPROBE_MISALIGNED_EMULATED (1 << 0) @@ -36,6 +37,7 @@ struct riscv_hwprobe { #define RISCV_HWPROBE_MISALIGNED_FAST (3 << 0) #define RISCV_HWPROBE_MISALIGNED_UNSUPPORTED (4 << 0) #define RISCV_HWPROBE_MISALIGNED_MASK (7 << 0) +#define RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE 6 /* Increase RISCV_HWPROBE_MAX_KEY when adding items. */ #endif diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c index 56cb2c986c48..e619edc8b0cc 100644 --- a/arch/riscv/kernel/acpi.c +++ b/arch/riscv/kernel/acpi.c @@ -14,9 +14,10 @@ */ #include <linux/acpi.h> +#include <linux/efi.h> #include <linux/io.h> +#include <linux/memblock.h> #include <linux/pci.h> -#include <linux/efi.h> int acpi_noirq = 1; /* skip ACPI IRQ initialization */ int acpi_disabled = 1; @@ -217,7 +218,89 @@ void __init __acpi_unmap_table(void __iomem *map, unsigned long size) void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) { - return (void __iomem *)memremap(phys, size, MEMREMAP_WB); + efi_memory_desc_t *md, *region = NULL; + pgprot_t prot; + + if (WARN_ON_ONCE(!efi_enabled(EFI_MEMMAP))) + return NULL; + + for_each_efi_memory_desc(md) { + u64 end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT); + + if (phys < md->phys_addr || phys >= end) + continue; + + if (phys + size > end) { + pr_warn(FW_BUG "requested region covers multiple EFI memory regions\n"); + return NULL; + } + region = md; + break; + } + + /* + * It is fine for AML to remap regions that are not represented in the + * EFI memory map at all, as it only describes normal memory, and MMIO + * regions that require a virtual mapping to make them accessible to + * the EFI runtime services. + */ + prot = PAGE_KERNEL_IO; + if (region) { + switch (region->type) { + case EFI_LOADER_CODE: + case EFI_LOADER_DATA: + case EFI_BOOT_SERVICES_CODE: + case EFI_BOOT_SERVICES_DATA: + case EFI_CONVENTIONAL_MEMORY: + case EFI_PERSISTENT_MEMORY: + if (memblock_is_map_memory(phys) || + !memblock_is_region_memory(phys, size)) { + pr_warn(FW_BUG "requested region covers kernel memory\n"); + return NULL; + } + + /* + * Mapping kernel memory is permitted if the region in + * question is covered by a single memblock with the + * NOMAP attribute set: this enables the use of ACPI + * table overrides passed via initramfs. + * This particular use case only requires read access. + */ + fallthrough; + + case EFI_RUNTIME_SERVICES_CODE: + /* + * This would be unusual, but not problematic per se, + * as long as we take care not to create a writable + * mapping for executable code. + */ + prot = PAGE_KERNEL_RO; + break; + + case EFI_ACPI_RECLAIM_MEMORY: + /* + * ACPI reclaim memory is used to pass firmware tables + * and other data that is intended for consumption by + * the OS only, which may decide it wants to reclaim + * that memory and use it for something else. We never + * do that, but we usually add it to the linear map + * anyway, in which case we should use the existing + * mapping. + */ + if (memblock_is_map_memory(phys)) + return (void __iomem *)__va(phys); + fallthrough; + + default: + if (region->attribute & EFI_MEMORY_WB) + prot = PAGE_KERNEL; + else if ((region->attribute & EFI_MEMORY_WC) || + (region->attribute & EFI_MEMORY_WT)) + prot = pgprot_writecombine(PAGE_KERNEL); + } + } + + return ioremap_prot(phys, size, pgprot_val(prot)); } #ifdef CONFIG_PCI diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index d6a75aac1d27..a03129f40c46 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -14,6 +14,7 @@ #include <asm/thread_info.h> #include <asm/ptrace.h> #include <asm/cpu_ops_sbi.h> +#include <asm/stacktrace.h> #include <asm/suspend.h> void asm_offsets(void); @@ -38,7 +39,11 @@ void asm_offsets(void) OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count); OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp); OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp); +#ifdef CONFIG_SHADOW_CALL_STACK + OFFSET(TASK_TI_SCS_SP, task_struct, thread_info.scs_sp); +#endif + OFFSET(TASK_TI_CPU_NUM, task_struct, thread_info.cpu); OFFSET(TASK_THREAD_F0, task_struct, thread.fstate.f[0]); OFFSET(TASK_THREAD_F1, task_struct, thread.fstate.f[1]); OFFSET(TASK_THREAD_F2, task_struct, thread.fstate.f[2]); @@ -479,4 +484,8 @@ void asm_offsets(void) OFFSET(KERNEL_MAP_VIRT_ADDR, kernel_mapping, virt_addr); OFFSET(SBI_HART_BOOT_TASK_PTR_OFFSET, sbi_hart_boot_data, task_ptr); OFFSET(SBI_HART_BOOT_STACK_PTR_OFFSET, sbi_hart_boot_data, stack_ptr); + + DEFINE(STACKFRAME_SIZE_ON_STACK, ALIGN(sizeof(struct stackframe), STACK_ALIGN)); + OFFSET(STACKFRAME_FP, stackframe, fp); + OFFSET(STACKFRAME_RA, stackframe, ra); } diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile index b86e5e2c3aea..62fa393b2eb2 100644 --- a/arch/riscv/kernel/compat_vdso/Makefile +++ b/arch/riscv/kernel/compat_vdso/Makefile @@ -76,13 +76,3 @@ quiet_cmd_compat_vdsold = VDSOLD $@ # actual build commands quiet_cmd_compat_vdsoas = VDSOAS $@ cmd_compat_vdsoas = $(COMPAT_CC) $(a_flags) $(COMPAT_CC_FLAGS) -c -o $@ $< - -# install commands for the unstripped file -quiet_cmd_compat_vdso_install = INSTALL $@ - cmd_compat_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/compat_vdso/$@ - -compat_vdso.so: $(obj)/compat_vdso.so.dbg - @mkdir -p $(MODLIB)/compat_vdso - $(call cmd,compat_vdso_install) - -compat_vdso_install: compat_vdso.so diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index e3803822ab5a..7aeba01dcfd4 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -93,10 +93,10 @@ static bool riscv_isa_extension_check(int id) return true; case RISCV_ISA_EXT_ZICBOZ: if (!riscv_cboz_block_size) { - pr_err("Zicboz detected in ISA string, but no cboz-block-size found\n"); + pr_err("Zicboz detected in ISA string, disabling as no cboz-block-size found\n"); return false; } else if (!is_power_of_2(riscv_cboz_block_size)) { - pr_err("cboz-block-size present, but is not a power-of-2\n"); + pr_err("Zicboz disabled as cboz-block-size present, but is not a power-of-2\n"); return false; } return true; @@ -206,10 +206,11 @@ static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct risc switch (*ext) { case 's': /* - * Workaround for invalid single-letter 's' & 'u'(QEMU). + * Workaround for invalid single-letter 's' & 'u' (QEMU). * No need to set the bit in riscv_isa as 's' & 'u' are - * not valid ISA extensions. It works until multi-letter - * extension starting with "Su" appears. + * not valid ISA extensions. It works unless the first + * multi-letter extension in the ISA string begins with + * "Su" and is not prefixed with an underscore. */ if (ext[-1] != '_' && ext[1] == 'u') { ++isa; @@ -655,6 +656,12 @@ static int check_unaligned_access_boot_cpu(void) arch_initcall(check_unaligned_access_boot_cpu); +void riscv_user_isa_enable(void) +{ + if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_ZICBOZ)) + csr_set(CSR_SENVCFG, ENVCFG_CBZE); +} + #ifdef CONFIG_RISCV_ALTERNATIVE /* * Alternative patch sites consider 48 bits when determining when to patch diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 143a2bb3e697..9f92c067f7e1 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -9,10 +9,15 @@ #include <asm/asm.h> #include <asm/csr.h> +#include <asm/scs.h> #include <asm/unistd.h> +#include <asm/page.h> #include <asm/thread_info.h> #include <asm/asm-offsets.h> #include <asm/errata_list.h> +#include <linux/sizes.h> + + .section .irqentry.text, "ax" SYM_CODE_START(handle_exception) /* @@ -73,10 +78,11 @@ _save_context: csrw CSR_SCRATCH, x0 /* Load the global pointer */ -.option push -.option norelax - la gp, __global_pointer$ -.option pop + load_global_pointer + + /* Load the kernel shadow call stack pointer if coming from userspace */ + scs_load_current_if_task_changed s5 + move a0, sp /* pt_regs */ la ra, ret_from_exception @@ -123,6 +129,9 @@ SYM_CODE_START_NOALIGN(ret_from_exception) addi s0, sp, PT_SIZE_ON_STACK REG_S s0, TASK_TI_KERNEL_SP(tp) + /* Save the kernel shadow call stack pointer */ + scs_save_current + /* * Save TP into the scratch register , so we can find the kernel data * structures again. @@ -170,67 +179,15 @@ SYM_CODE_END(ret_from_exception) #ifdef CONFIG_VMAP_STACK SYM_CODE_START_LOCAL(handle_kernel_stack_overflow) - /* - * Takes the psuedo-spinlock for the shadow stack, in case multiple - * harts are concurrently overflowing their kernel stacks. We could - * store any value here, but since we're overflowing the kernel stack - * already we only have SP to use as a scratch register. So we just - * swap in the address of the spinlock, as that's definately non-zero. - * - * Pairs with a store_release in handle_bad_stack(). - */ -1: la sp, spin_shadow_stack - REG_AMOSWAP_AQ sp, sp, (sp) - bnez sp, 1b - - la sp, shadow_stack - addi sp, sp, SHADOW_OVERFLOW_STACK_SIZE - - //save caller register to shadow stack - addi sp, sp, -(PT_SIZE_ON_STACK) - REG_S x1, PT_RA(sp) - REG_S x5, PT_T0(sp) - REG_S x6, PT_T1(sp) - REG_S x7, PT_T2(sp) - REG_S x10, PT_A0(sp) - REG_S x11, PT_A1(sp) - REG_S x12, PT_A2(sp) - REG_S x13, PT_A3(sp) - REG_S x14, PT_A4(sp) - REG_S x15, PT_A5(sp) - REG_S x16, PT_A6(sp) - REG_S x17, PT_A7(sp) - REG_S x28, PT_T3(sp) - REG_S x29, PT_T4(sp) - REG_S x30, PT_T5(sp) - REG_S x31, PT_T6(sp) - - la ra, restore_caller_reg - tail get_overflow_stack + /* we reach here from kernel context, sscratch must be 0 */ + csrrw x31, CSR_SCRATCH, x31 + asm_per_cpu sp, overflow_stack, x31 + li x31, OVERFLOW_STACK_SIZE + add sp, sp, x31 + /* zero out x31 again and restore x31 */ + xor x31, x31, x31 + csrrw x31, CSR_SCRATCH, x31 -restore_caller_reg: - //save per-cpu overflow stack - REG_S a0, -8(sp) - //restore caller register from shadow_stack - REG_L x1, PT_RA(sp) - REG_L x5, PT_T0(sp) - REG_L x6, PT_T1(sp) - REG_L x7, PT_T2(sp) - REG_L x10, PT_A0(sp) - REG_L x11, PT_A1(sp) - REG_L x12, PT_A2(sp) - REG_L x13, PT_A3(sp) - REG_L x14, PT_A4(sp) - REG_L x15, PT_A5(sp) - REG_L x16, PT_A6(sp) - REG_L x17, PT_A7(sp) - REG_L x28, PT_T3(sp) - REG_L x29, PT_T4(sp) - REG_L x30, PT_T5(sp) - REG_L x31, PT_T6(sp) - - //load per-cpu overflow stack - REG_L sp, -8(sp) addi sp, sp, -(PT_SIZE_ON_STACK) //save context to overflow stack @@ -268,6 +225,43 @@ SYM_CODE_START(ret_from_fork) tail syscall_exit_to_user_mode SYM_CODE_END(ret_from_fork) +#ifdef CONFIG_IRQ_STACKS +/* + * void call_on_irq_stack(struct pt_regs *regs, + * void (*func)(struct pt_regs *)); + * + * Calls func(regs) using the per-CPU IRQ stack. + */ +SYM_FUNC_START(call_on_irq_stack) + /* Create a frame record to save ra and s0 (fp) */ + addi sp, sp, -STACKFRAME_SIZE_ON_STACK + REG_S ra, STACKFRAME_RA(sp) + REG_S s0, STACKFRAME_FP(sp) + addi s0, sp, STACKFRAME_SIZE_ON_STACK + + /* Switch to the per-CPU shadow call stack */ + scs_save_current + scs_load_irq_stack t0 + + /* Switch to the per-CPU IRQ stack and call the handler */ + load_per_cpu t0, irq_stack_ptr, t1 + li t1, IRQ_STACK_SIZE + add sp, t0, t1 + jalr a1 + + /* Switch back to the thread shadow call stack */ + scs_load_current + + /* Switch back to the thread stack and restore ra and s0 */ + addi sp, s0, -STACKFRAME_SIZE_ON_STACK + REG_L ra, STACKFRAME_RA(sp) + REG_L s0, STACKFRAME_FP(sp) + addi sp, sp, STACKFRAME_SIZE_ON_STACK + + ret +SYM_FUNC_END(call_on_irq_stack) +#endif /* CONFIG_IRQ_STACKS */ + /* * Integer register context switch * The callee-saved registers must be saved and restored. @@ -297,6 +291,8 @@ SYM_FUNC_START(__switch_to) REG_S s9, TASK_THREAD_S9_RA(a3) REG_S s10, TASK_THREAD_S10_RA(a3) REG_S s11, TASK_THREAD_S11_RA(a3) + /* Save the kernel shadow call stack pointer */ + scs_save_current /* Restore context from next->thread */ REG_L ra, TASK_THREAD_RA_RA(a4) REG_L sp, TASK_THREAD_SP_RA(a4) @@ -314,6 +310,8 @@ SYM_FUNC_START(__switch_to) REG_L s11, TASK_THREAD_S11_RA(a4) /* The offset of thread_info in task_struct is zero. */ move tp, a1 + /* Switch to the next shadow call stack */ + scs_load_current ret SYM_FUNC_END(__switch_to) diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 3710ea5d160f..18f97ec0f7ed 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -14,6 +14,7 @@ #include <asm/cpu_ops_sbi.h> #include <asm/hwcap.h> #include <asm/image.h> +#include <asm/scs.h> #include <asm/xip_fixup.h> #include "efi-header.S" @@ -110,10 +111,7 @@ relocate_enable_mmu: csrw CSR_TVEC, a0 /* Reload the global pointer */ -.option push -.option norelax - la gp, __global_pointer$ -.option pop + load_global_pointer /* * Switch to kernel page tables. A full fence is necessary in order to @@ -134,10 +132,7 @@ secondary_start_sbi: csrw CSR_IP, zero /* Load the global pointer */ - .option push - .option norelax - la gp, __global_pointer$ - .option pop + load_global_pointer /* * Disable FPU & VECTOR to detect illegal usage of @@ -159,6 +154,7 @@ secondary_start_sbi: XIP_FIXUP_OFFSET a3 add a3, a3, a1 REG_L sp, (a3) + scs_load_current .Lsecondary_start_common: @@ -228,10 +224,7 @@ pmp_done: #endif /* CONFIG_RISCV_M_MODE */ /* Load the global pointer */ -.option push -.option norelax - la gp, __global_pointer$ -.option pop + load_global_pointer /* * Disable FPU & VECTOR to detect illegal usage of @@ -298,6 +291,7 @@ clear_bss_done: la sp, init_thread_union + THREAD_SIZE XIP_FIXUP_OFFSET sp addi sp, sp, -PT_SIZE_ON_STACK + scs_load_init_stack #ifdef CONFIG_BUILTIN_DTB la a0, __dtb_start XIP_FIXUP_OFFSET a0 @@ -316,6 +310,7 @@ clear_bss_done: la tp, init_task la sp, init_thread_union + THREAD_SIZE addi sp, sp, -PT_SIZE_ON_STACK + scs_load_current #ifdef CONFIG_KASAN call kasan_early_init diff --git a/arch/riscv/kernel/image-vars.h b/arch/riscv/kernel/image-vars.h index ea1a10355ce9..3df30dd1c458 100644 --- a/arch/riscv/kernel/image-vars.h +++ b/arch/riscv/kernel/image-vars.h @@ -28,7 +28,9 @@ __efistub__start_kernel = _start_kernel; __efistub__end = _end; __efistub__edata = _edata; __efistub___init_text_end = __init_text_end; +#if defined(CONFIG_EFI_EARLYCON) || defined(CONFIG_SYSFB) __efistub_screen_info = screen_info; +#endif #endif diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c index 9cc0a7669271..9ceda02507ca 100644 --- a/arch/riscv/kernel/irq.c +++ b/arch/riscv/kernel/irq.c @@ -9,6 +9,7 @@ #include <linux/irqchip.h> #include <linux/irqdomain.h> #include <linux/module.h> +#include <linux/scs.h> #include <linux/seq_file.h> #include <asm/sbi.h> #include <asm/smp.h> @@ -34,6 +35,24 @@ EXPORT_SYMBOL_GPL(riscv_get_intc_hwnode); #ifdef CONFIG_IRQ_STACKS #include <asm/irq_stack.h> +DECLARE_PER_CPU(ulong *, irq_shadow_call_stack_ptr); + +#ifdef CONFIG_SHADOW_CALL_STACK +DEFINE_PER_CPU(ulong *, irq_shadow_call_stack_ptr); +#endif + +static void init_irq_scs(void) +{ + int cpu; + + if (!scs_is_enabled()) + return; + + for_each_possible_cpu(cpu) + per_cpu(irq_shadow_call_stack_ptr, cpu) = + scs_alloc(cpu_to_node(cpu)); +} + DEFINE_PER_CPU(ulong *, irq_stack_ptr); #ifdef CONFIG_VMAP_STACK @@ -61,40 +80,22 @@ static void init_irq_stacks(void) #endif /* CONFIG_VMAP_STACK */ #ifdef CONFIG_SOFTIRQ_ON_OWN_STACK +static void ___do_softirq(struct pt_regs *regs) +{ + __do_softirq(); +} + void do_softirq_own_stack(void) { -#ifdef CONFIG_IRQ_STACKS - if (on_thread_stack()) { - ulong *sp = per_cpu(irq_stack_ptr, smp_processor_id()) - + IRQ_STACK_SIZE/sizeof(ulong); - __asm__ __volatile( - "addi sp, sp, -"RISCV_SZPTR "\n" - REG_S" ra, (sp) \n" - "addi sp, sp, -"RISCV_SZPTR "\n" - REG_S" s0, (sp) \n" - "addi s0, sp, 2*"RISCV_SZPTR "\n" - "move sp, %[sp] \n" - "call __do_softirq \n" - "addi sp, s0, -2*"RISCV_SZPTR"\n" - REG_L" s0, (sp) \n" - "addi sp, sp, "RISCV_SZPTR "\n" - REG_L" ra, (sp) \n" - "addi sp, sp, "RISCV_SZPTR "\n" - : - : [sp] "r" (sp) - : "a0", "a1", "a2", "a3", "a4", "a5", "a6", "a7", - "t0", "t1", "t2", "t3", "t4", "t5", "t6", -#ifndef CONFIG_FRAME_POINTER - "s0", -#endif - "memory"); - } else -#endif + if (on_thread_stack()) + call_on_irq_stack(NULL, ___do_softirq); + else __do_softirq(); } #endif /* CONFIG_SOFTIRQ_ON_OWN_STACK */ #else +static void init_irq_scs(void) {} static void init_irq_stacks(void) {} #endif /* CONFIG_IRQ_STACKS */ @@ -106,6 +107,7 @@ int arch_show_interrupts(struct seq_file *p, int prec) void __init init_IRQ(void) { + init_irq_scs(); init_irq_stacks(); irqchip_init(); if (!handle_arch_irq) diff --git a/arch/riscv/kernel/kexec_relocate.S b/arch/riscv/kernel/kexec_relocate.S index 059c5e216ae7..de0a4b35d01e 100644 --- a/arch/riscv/kernel/kexec_relocate.S +++ b/arch/riscv/kernel/kexec_relocate.S @@ -17,27 +17,17 @@ SYM_CODE_START(riscv_kexec_relocate) * s1: (const) Phys address to jump to after relocation * s2: (const) Phys address of the FDT image * s3: (const) The hartid of the current hart - * s4: Pointer to the destination address for the relocation - * s5: (const) Number of words per page - * s6: (const) 1, used for subtraction - * s7: (const) kernel_map.va_pa_offset, used when switching MMU off - * s8: (const) Physical address of the main loop - * s9: (debug) indirection page counter - * s10: (debug) entry counter - * s11: (debug) copied words counter + * s4: (const) kernel_map.va_pa_offset, used when switching MMU off + * s5: Pointer to the destination address for the relocation + * s6: (const) Physical address of the main loop */ mv s0, a0 mv s1, a1 mv s2, a2 mv s3, a3 - mv s4, zero - li s5, (PAGE_SIZE / RISCV_SZPTR) - li s6, 1 - mv s7, a4 - mv s8, zero - mv s9, zero - mv s10, zero - mv s11, zero + mv s4, a4 + mv s5, zero + mv s6, zero /* Disable / cleanup interrupts */ csrw CSR_SIE, zero @@ -52,21 +42,27 @@ SYM_CODE_START(riscv_kexec_relocate) * the start of the loop below so that we jump there in * any case. */ - la s8, 1f - sub s8, s8, s7 - csrw CSR_STVEC, s8 + la s6, 1f + sub s6, s6, s4 + csrw CSR_STVEC, s6 + + /* + * With C-extension, here we get 42 Bytes and the next + * .align directive would pad zeros here up to 44 Bytes. + * So manually put a nop here to avoid zeros padding. + */ + nop /* Process entries in a loop */ .align 2 1: - addi s10, s10, 1 REG_L t0, 0(s0) /* t0 = *image->entry */ addi s0, s0, RISCV_SZPTR /* image->entry++ */ /* IND_DESTINATION entry ? -> save destination address */ andi t1, t0, 0x1 beqz t1, 2f - andi s4, t0, ~0x1 + andi s5, t0, ~0x1 j 1b 2: @@ -74,9 +70,8 @@ SYM_CODE_START(riscv_kexec_relocate) andi t1, t0, 0x2 beqz t1, 2f andi s0, t0, ~0x2 - addi s9, s9, 1 csrw CSR_SATP, zero - jalr zero, s8, 0 + jr s6 2: /* IND_DONE entry ? -> jump to done label */ @@ -92,14 +87,13 @@ SYM_CODE_START(riscv_kexec_relocate) andi t1, t0, 0x8 beqz t1, 1b /* Unknown entry type, ignore it */ andi t0, t0, ~0x8 - mv t3, s5 /* i = num words per page */ + li t3, (PAGE_SIZE / RISCV_SZPTR) /* i = num words per page */ 3: /* copy loop */ REG_L t1, (t0) /* t1 = *src_ptr */ - REG_S t1, (s4) /* *dst_ptr = *src_ptr */ + REG_S t1, (s5) /* *dst_ptr = *src_ptr */ addi t0, t0, RISCV_SZPTR /* stc_ptr++ */ - addi s4, s4, RISCV_SZPTR /* dst_ptr++ */ - sub t3, t3, s6 /* i-- */ - addi s11, s11, 1 /* c++ */ + addi s5, s5, RISCV_SZPTR /* dst_ptr++ */ + addi t3, t3, -0x1 /* i-- */ beqz t3, 1b /* copy done ? */ j 3b @@ -146,7 +140,7 @@ SYM_CODE_START(riscv_kexec_relocate) */ fence.i - jalr zero, a2, 0 + jr a2 SYM_CODE_END(riscv_kexec_relocate) riscv_kexec_relocate_end: diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index aac853ae4eb7..535a837de55d 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -15,7 +15,6 @@ #include <linux/memblock.h> #include <linux/sched.h> #include <linux/console.h> -#include <linux/screen_info.h> #include <linux/of_fdt.h> #include <linux/sched/task.h> #include <linux/smp.h> @@ -26,6 +25,7 @@ #include <asm/acpi.h> #include <asm/alternative.h> #include <asm/cacheflush.h> +#include <asm/cpufeature.h> #include <asm/cpu_ops.h> #include <asm/early_ioremap.h> #include <asm/pgtable.h> @@ -40,17 +40,6 @@ #include "head.h" -#if defined(CONFIG_DUMMY_CONSOLE) || defined(CONFIG_EFI) -struct screen_info screen_info __section(".data") = { - .orig_video_lines = 30, - .orig_video_cols = 80, - .orig_video_mode = 0, - .orig_video_ega_bx = 0, - .orig_video_isVGA = 1, - .orig_video_points = 8 -}; -#endif - /* * The lucky hart to first increment this variable will boot the other cores. * This is used before the kernel initializes the BSS so it can't be in the @@ -301,10 +290,13 @@ void __init setup_arch(char **cmdline_p) riscv_fill_hwcap(); init_rt_signal_env(); apply_boot_alternatives(); + if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) && riscv_isa_extension_available(NULL, ZICBOM)) riscv_noncoherent_supported(); riscv_set_dma_cache_alignment(); + + riscv_user_isa_enable(); } static int __init topology_init(void) diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index 1b8da4e40a4d..d1b0a6fc3adf 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -25,6 +25,8 @@ #include <linux/of.h> #include <linux/sched/task_stack.h> #include <linux/sched/mm.h> + +#include <asm/cpufeature.h> #include <asm/cpu_ops.h> #include <asm/cpufeature.h> #include <asm/irq.h> @@ -253,6 +255,8 @@ asmlinkage __visible void smp_callin(void) elf_hwcap &= ~COMPAT_HWCAP_ISA_V; } + riscv_user_isa_enable(); + /* * Remote TLB flushes are ignored while the CPU is offline, so emit * a local TLB flush right now just in case. diff --git a/arch/riscv/kernel/suspend_entry.S b/arch/riscv/kernel/suspend_entry.S index f7960c7c5f9e..d5cf8b575777 100644 --- a/arch/riscv/kernel/suspend_entry.S +++ b/arch/riscv/kernel/suspend_entry.S @@ -61,10 +61,7 @@ END(__cpu_suspend_enter) SYM_TYPED_FUNC_START(__cpu_resume_enter) /* Load the global pointer */ - .option push - .option norelax - la gp, __global_pointer$ - .option pop + load_global_pointer #ifdef CONFIG_MMU /* Save A0 and A1 */ diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index b651ec698a91..c712037dbe10 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -145,26 +145,38 @@ static void hwprobe_isa_ext0(struct riscv_hwprobe *pair, for_each_cpu(cpu, cpus) { struct riscv_isainfo *isainfo = &hart_isa[cpu]; - if (riscv_isa_extension_available(isainfo->isa, ZBA)) - pair->value |= RISCV_HWPROBE_EXT_ZBA; - else - missing |= RISCV_HWPROBE_EXT_ZBA; +#define EXT_KEY(ext) \ + do { \ + if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_EXT_##ext)) \ + pair->value |= RISCV_HWPROBE_EXT_##ext; \ + else \ + missing |= RISCV_HWPROBE_EXT_##ext; \ + } while (false) - if (riscv_isa_extension_available(isainfo->isa, ZBB)) - pair->value |= RISCV_HWPROBE_EXT_ZBB; - else - missing |= RISCV_HWPROBE_EXT_ZBB; - - if (riscv_isa_extension_available(isainfo->isa, ZBS)) - pair->value |= RISCV_HWPROBE_EXT_ZBS; - else - missing |= RISCV_HWPROBE_EXT_ZBS; + /* + * Only use EXT_KEY() for extensions which can be exposed to userspace, + * regardless of the kernel's configuration, as no other checks, besides + * presence in the hart_isa bitmap, are made. + */ + EXT_KEY(ZBA); + EXT_KEY(ZBB); + EXT_KEY(ZBS); + EXT_KEY(ZICBOZ); +#undef EXT_KEY } /* Now turn off reporting features if any CPU is missing it. */ pair->value &= ~missing; } +static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext) +{ + struct riscv_hwprobe pair; + + hwprobe_isa_ext0(&pair, cpus); + return (pair.value & ext); +} + static u64 hwprobe_misaligned(const struct cpumask *cpus) { int cpu; @@ -215,6 +227,12 @@ static void hwprobe_one_pair(struct riscv_hwprobe *pair, pair->value = hwprobe_misaligned(cpus); break; + case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE: + pair->value = 0; + if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ)) + pair->value = riscv_cboz_block_size; + break; + /* * For forward compatibility, unknown keys don't fail the whole * call, but get their element key set to -1 and value set to 0 diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index fae8f610d867..c9d698518bae 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -360,34 +360,10 @@ static void noinstr handle_riscv_irq(struct pt_regs *regs) asmlinkage void noinstr do_irq(struct pt_regs *regs) { irqentry_state_t state = irqentry_enter(regs); -#ifdef CONFIG_IRQ_STACKS - if (on_thread_stack()) { - ulong *sp = per_cpu(irq_stack_ptr, smp_processor_id()) - + IRQ_STACK_SIZE/sizeof(ulong); - __asm__ __volatile( - "addi sp, sp, -"RISCV_SZPTR "\n" - REG_S" ra, (sp) \n" - "addi sp, sp, -"RISCV_SZPTR "\n" - REG_S" s0, (sp) \n" - "addi s0, sp, 2*"RISCV_SZPTR "\n" - "move sp, %[sp] \n" - "move a0, %[regs] \n" - "call handle_riscv_irq \n" - "addi sp, s0, -2*"RISCV_SZPTR"\n" - REG_L" s0, (sp) \n" - "addi sp, sp, "RISCV_SZPTR "\n" - REG_L" ra, (sp) \n" - "addi sp, sp, "RISCV_SZPTR "\n" - : - : [sp] "r" (sp), [regs] "r" (regs) - : "a0", "a1", "a2", "a3", "a4", "a5", "a6", "a7", - "t0", "t1", "t2", "t3", "t4", "t5", "t6", -#ifndef CONFIG_FRAME_POINTER - "s0", -#endif - "memory"); - } else -#endif + + if (IS_ENABLED(CONFIG_IRQ_STACKS) && on_thread_stack()) + call_on_irq_stack(regs, handle_riscv_irq); + else handle_riscv_irq(regs); irqentry_exit(regs, state); @@ -410,48 +386,14 @@ int is_valid_bugaddr(unsigned long pc) #endif /* CONFIG_GENERIC_BUG */ #ifdef CONFIG_VMAP_STACK -/* - * Extra stack space that allows us to provide panic messages when the kernel - * has overflowed its stack. - */ -static DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], +DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack)__aligned(16); -/* - * A temporary stack for use by handle_kernel_stack_overflow. This is used so - * we can call into C code to get the per-hart overflow stack. Usage of this - * stack must be protected by spin_shadow_stack. - */ -long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE/sizeof(long)] __aligned(16); - -/* - * A pseudo spinlock to protect the shadow stack from being used by multiple - * harts concurrently. This isn't a real spinlock because the lock side must - * be taken without a valid stack and only a single register, it's only taken - * while in the process of panicing anyway so the performance and error - * checking a proper spinlock gives us doesn't matter. - */ -unsigned long spin_shadow_stack; - -asmlinkage unsigned long get_overflow_stack(void) -{ - return (unsigned long)this_cpu_ptr(overflow_stack) + - OVERFLOW_STACK_SIZE; -} asmlinkage void handle_bad_stack(struct pt_regs *regs) { unsigned long tsk_stk = (unsigned long)current->stack; unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack); - /* - * We're done with the shadow stack by this point, as we're on the - * overflow stack. Tell any other concurrent overflowing harts that - * they can proceed with panicing by releasing the pseudo-spinlock. - * - * This pairs with an amoswap.aq in handle_kernel_stack_overflow. - */ - smp_store_release(&spin_shadow_stack, 0); - console_verbose(); pr_emerg("Insufficient stack space to handle exception!\n"); diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile index 6b1dba11bf6d..9b517fe1b8a8 100644 --- a/arch/riscv/kernel/vdso/Makefile +++ b/arch/riscv/kernel/vdso/Makefile @@ -36,7 +36,7 @@ CPPFLAGS_vdso.lds += -DHAS_VGETTIMEOFDAY endif # Disable -pg to prevent insert call site -CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) # Disable profiling and instrumentation for VDSO code GCOV_PROFILE := n @@ -73,13 +73,3 @@ quiet_cmd_vdsold = VDSOLD $@ cmd_vdsold = $(LD) $(ld_flags) -T $(filter-out FORCE,$^) -o $@.tmp && \ $(OBJCOPY) $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \ rm $@.tmp - -# install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ - -vdso.so: $(obj)/vdso.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso.so diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c index d40bec6ac078..cadf725ef798 100644 --- a/arch/riscv/kernel/vdso/hwprobe.c +++ b/arch/riscv/kernel/vdso/hwprobe.c @@ -37,7 +37,7 @@ int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, /* This is something we can handle, fill out the pairs. */ while (p < end) { - if (p->key <= RISCV_HWPROBE_MAX_KEY) { + if (riscv_hwprobe_key_is_valid(p->key)) { p->value = avd->all_cpu_hwprobe_values[p->key]; } else { diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c index f1387272a551..55a34f2020a8 100644 --- a/arch/riscv/mm/cacheflush.c +++ b/arch/riscv/mm/cacheflush.c @@ -3,7 +3,9 @@ * Copyright (C) 2017 SiFive */ +#include <linux/acpi.h> #include <linux/of.h> +#include <asm/acpi.h> #include <asm/cacheflush.h> #ifdef CONFIG_SMP @@ -124,13 +126,24 @@ void __init riscv_init_cbo_blocksizes(void) unsigned long cbom_hartid, cboz_hartid; u32 cbom_block_size = 0, cboz_block_size = 0; struct device_node *node; + struct acpi_table_header *rhct; + acpi_status status; - for_each_of_cpu_node(node) { - /* set block-size for cbom and/or cboz extension if available */ - cbo_get_block_size(node, "riscv,cbom-block-size", - &cbom_block_size, &cbom_hartid); - cbo_get_block_size(node, "riscv,cboz-block-size", - &cboz_block_size, &cboz_hartid); + if (acpi_disabled) { + for_each_of_cpu_node(node) { + /* set block-size for cbom and/or cboz extension if available */ + cbo_get_block_size(node, "riscv,cbom-block-size", + &cbom_block_size, &cbom_hartid); + cbo_get_block_size(node, "riscv,cboz-block-size", + &cboz_block_size, &cboz_hartid); + } + } else { + status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct); + if (ACPI_FAILURE(status)) + return; + + acpi_get_cbo_block_size(rhct, &cbom_block_size, &cboz_block_size, NULL); + acpi_put_table((struct acpi_table_header *)rhct); } if (cbom_block_size) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index d9a4e8702864..b128ed3c5a37 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -49,10 +49,12 @@ u64 satp_mode __ro_after_init = SATP_MODE_32; #endif EXPORT_SYMBOL(satp_mode); +#ifdef CONFIG_64BIT bool pgtable_l4_enabled = IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_XIP_KERNEL); bool pgtable_l5_enabled = IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_XIP_KERNEL); EXPORT_SYMBOL(pgtable_l4_enabled); EXPORT_SYMBOL(pgtable_l5_enabled); +#endif phys_addr_t phys_ram_base __ro_after_init; EXPORT_SYMBOL(phys_ram_base); diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c index 20a9f991a6d7..e9090b38f811 100644 --- a/arch/riscv/mm/ptdump.c +++ b/arch/riscv/mm/ptdump.c @@ -384,6 +384,9 @@ static int __init ptdump_init(void) kernel_ptd_info.base_addr = KERN_VIRT_START; + pg_level[1].name = pgtable_l5_enabled ? "P4D" : "PGD"; + pg_level[2].name = pgtable_l4_enabled ? "PUD" : "PGD"; + for (i = 0; i < ARRAY_SIZE(pg_level); i++) for (j = 0; j < ARRAY_SIZE(pte_bits); j++) pg_level[i].mask |= pte_bits[j].mask; diff --git a/arch/riscv/purgatory/Makefile b/arch/riscv/purgatory/Makefile index 9e6476719abb..280b0eb352b8 100644 --- a/arch/riscv/purgatory/Makefile +++ b/arch/riscv/purgatory/Makefile @@ -81,6 +81,14 @@ ifdef CONFIG_CFI_CLANG PURGATORY_CFLAGS_REMOVE += $(CC_FLAGS_CFI) endif +ifdef CONFIG_RELOCATABLE +PURGATORY_CFLAGS_REMOVE += -fPIE +endif + +ifdef CONFIG_SHADOW_CALL_STACK +PURGATORY_CFLAGS_REMOVE += $(CC_FLAGS_SCS) +endif + CFLAGS_REMOVE_purgatory.o += $(PURGATORY_CFLAGS_REMOVE) CFLAGS_purgatory.o += $(PURGATORY_CFLAGS) diff --git a/arch/s390/Makefile b/arch/s390/Makefile index a53a36ee0731..73873e451686 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -138,9 +138,6 @@ bzImage: vmlinux zfcpdump: $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ -vdso_install: - $(Q)$(MAKE) $(build)=arch/$(ARCH)/kernel/vdso64 $@ - archheaders: $(Q)$(MAKE) $(build)=$(syscalls) uapi @@ -160,6 +157,9 @@ vdso_prepare: prepare0 $(if $(CONFIG_COMPAT),$(Q)$(MAKE) \ $(build)=arch/s390/kernel/vdso32 include/generated/vdso32-offsets.h) +vdso-install-y += arch/s390/kernel/vdso64/vdso64.so.dbg +vdso-install-$(CONFIG_COMPAT) += arch/s390/kernel/vdso32/vdso32.so.dbg + ifdef CONFIG_EXPOLINE_EXTERN modules_prepare: expoline_prepare expoline_prepare: scripts diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile index 23e868b79a6c..caec7db6f966 100644 --- a/arch/s390/kernel/vdso32/Makefile +++ b/arch/s390/kernel/vdso32/Makefile @@ -61,16 +61,6 @@ quiet_cmd_vdso32as = VDSO32A $@ quiet_cmd_vdso32cc = VDSO32C $@ cmd_vdso32cc = $(CC) $(c_flags) -c -o $@ $< -# install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ - -vdso32.so: $(obj)/vdso32.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso32.so - # Generate VDSO offsets using helper script gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index fc1c6ff8178f..e3c9085f8fa7 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -70,16 +70,6 @@ quiet_cmd_vdso64as = VDSO64A $@ quiet_cmd_vdso64cc = VDSO64C $@ cmd_vdso64cc = $(CC) $(c_flags) -c -o $@ $< -# install commands for the unstripped file -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ - -vdso64.so: $(obj)/vdso64.so.dbg - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -vdso_install: vdso64.so - # Generate VDSO offsets using helper script gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index b3da2757faaf..3d80515298d2 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -7,7 +7,6 @@ * Copyright (C) 1999 Niibe Yutaka * Copyright (C) 2002 - 2010 Paul Mundt */ -#include <linux/screen_info.h> #include <linux/ioport.h> #include <linux/init.h> #include <linux/initrd.h> @@ -69,10 +68,6 @@ EXPORT_SYMBOL(cpu_data); struct sh_machine_vector sh_mv = { .mv_name = "generic", }; EXPORT_SYMBOL(sh_mv); -#ifdef CONFIG_VT -struct screen_info screen_info; -#endif - extern int root_mountflags; #define RAMDISK_IMAGE_START_MASK 0x07FF diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile index 7417345c6639..5f6035936131 100644 --- a/arch/sparc/Makefile +++ b/arch/sparc/Makefile @@ -76,9 +76,8 @@ install: archheaders: $(Q)$(MAKE) $(build)=arch/sparc/kernel/syscalls all -PHONY += vdso_install -vdso_install: - $(Q)$(MAKE) $(build)=arch/sparc/vdso $@ +vdso-install-$(CONFIG_SPARC64) += arch/sparc/vdso/vdso64.so.dbg +vdso-install-$(CONFIG_COMPAT) += arch/sparc/vdso/vdso32.so.dbg # This is the image used for packaging KBUILD_IMAGE := $(boot)/zImage diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c index 34ef7febf0d5..e3b72a7b46d3 100644 --- a/arch/sparc/kernel/setup_32.c +++ b/arch/sparc/kernel/setup_32.c @@ -17,7 +17,6 @@ #include <linux/initrd.h> #include <asm/smp.h> #include <linux/user.h> -#include <linux/screen_info.h> #include <linux/delay.h> #include <linux/fs.h> #include <linux/seq_file.h> @@ -51,18 +50,6 @@ #include "kernel.h" -struct screen_info screen_info = { - 0, 0, /* orig-x, orig-y */ - 0, /* unused */ - 0, /* orig-video-page */ - 0, /* orig-video-mode */ - 128, /* orig-video-cols */ - 0,0,0, /* ega_ax, ega_bx, ega_cx */ - 54, /* orig-video-lines */ - 0, /* orig-video-isVGA */ - 16 /* orig-video-points */ -}; - /* Typing sync at the prom prompt calls the function pointed to by * romvec->pv_synchook which I set to the following function. * This should sync all filesystems and return, for now it just diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index 6546ca9d4d3f..6a4797dec34b 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -15,7 +15,6 @@ #include <linux/ptrace.h> #include <asm/smp.h> #include <linux/user.h> -#include <linux/screen_info.h> #include <linux/delay.h> #include <linux/fs.h> #include <linux/seq_file.h> @@ -68,18 +67,6 @@ DEFINE_SPINLOCK(ns87303_lock); EXPORT_SYMBOL(ns87303_lock); -struct screen_info screen_info = { - 0, 0, /* orig-x, orig-y */ - 0, /* unused */ - 0, /* orig-video-page */ - 0, /* orig-video-mode */ - 128, /* orig-video-cols */ - 0, 0, 0, /* unused, ega_bx, unused */ - 54, /* orig-video-lines */ - 0, /* orig-video-isVGA */ - 16 /* orig-video-points */ -}; - static void prom_console_write(struct console *con, const char *s, unsigned int n) { diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile index 77d7b9032158..d08c3a0443f3 100644 --- a/arch/sparc/vdso/Makefile +++ b/arch/sparc/vdso/Makefile @@ -116,30 +116,3 @@ quiet_cmd_vdso = VDSO $@ VDSO_LDFLAGS = -shared --hash-style=both --build-id=sha1 -Bsymbolic GCOV_PROFILE := n - -# -# Install the unstripped copies of vdso*.so. If our toolchain supports -# build-id, install .build-id links as well. -# -quiet_cmd_vdso_install = INSTALL $(@:install_%=%) -define cmd_vdso_install - cp $< "$(MODLIB)/vdso/$(@:install_%=%)"; \ - if readelf -n $< |grep -q 'Build ID'; then \ - buildid=`readelf -n $< |grep 'Build ID' |sed -e 's/^.*Build ID: \(.*\)$$/\1/'`; \ - first=`echo $$buildid | cut -b-2`; \ - last=`echo $$buildid | cut -b3-`; \ - mkdir -p "$(MODLIB)/vdso/.build-id/$$first"; \ - ln -sf "../../$(@:install_%=%)" "$(MODLIB)/vdso/.build-id/$$first/$$last.debug"; \ - fi -endef - -vdso_img_insttargets := $(vdso_img_sodbg:%.dbg=install_%) - -$(MODLIB)/vdso: FORCE - @mkdir -p $(MODLIB)/vdso - -$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE - $(call cmd,vdso_install) - -PHONY += vdso_install $(vdso_img_insttargets) -vdso_install: $(vdso_img_insttargets) FORCE diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6a917f62eff2..3762f41bb092 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1313,16 +1313,41 @@ config MICROCODE def_bool y depends on CPU_SUP_AMD || CPU_SUP_INTEL +config MICROCODE_INITRD32 + def_bool y + depends on MICROCODE && X86_32 && BLK_DEV_INITRD + config MICROCODE_LATE_LOADING bool "Late microcode loading (DANGEROUS)" default n - depends on MICROCODE + depends on MICROCODE && SMP help Loading microcode late, when the system is up and executing instructions is a tricky business and should be avoided if possible. Just the sequence of synchronizing all cores and SMT threads is one fragile dance which does not guarantee that cores might not softlock after the loading. Therefore, - use this at your own risk. Late loading taints the kernel too. + use this at your own risk. Late loading taints the kernel unless the + microcode header indicates that it is safe for late loading via the + minimal revision check. This minimal revision check can be enforced on + the kernel command line with "microcode.minrev=Y". + +config MICROCODE_LATE_FORCE_MINREV + bool "Enforce late microcode loading minimal revision check" + default n + depends on MICROCODE_LATE_LOADING + help + To prevent that users load microcode late which modifies already + in use features, newer microcode patches have a minimum revision field + in the microcode header, which tells the kernel which minimum + revision must be active in the CPU to safely load that new microcode + late into the running system. If disabled the check will not + be enforced but the kernel will be tainted when the minimal + revision check fails. + + This minimal revision check can also be controlled via the + "microcode.minrev" parameter on the kernel command line. + + If unsure say Y. config X86_MSR tristate "/dev/cpu/*/msr - Model-specific register support" diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 4de6ddaf4b84..1a068de12a56 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -294,9 +294,10 @@ PHONY += install install: $(call cmd,install) -PHONY += vdso_install -vdso_install: - $(Q)$(MAKE) $(build)=arch/x86/entry/vdso $@ +vdso-install-$(CONFIG_X86_64) += arch/x86/entry/vdso/vdso64.so.dbg +vdso-install-$(CONFIG_X86_X32_ABI) += arch/x86/entry/vdso/vdsox32.so.dbg +vdso-install-$(CONFIG_X86_32) += arch/x86/entry/vdso/vdso32.so.dbg +vdso-install-$(CONFIG_IA32_EMULATION) += arch/x86/entry/vdso/vdso32.so.dbg archprepare: checkbin checkbin: diff --git a/arch/x86/Makefile.postlink b/arch/x86/Makefile.postlink index 936093d29160..fef2e977cc7d 100644 --- a/arch/x86/Makefile.postlink +++ b/arch/x86/Makefile.postlink @@ -34,9 +34,6 @@ ifeq ($(CONFIG_X86_NEED_RELOCS),y) $(call cmd,strip_relocs) endif -%.ko: FORCE - @true - clean: @rm -f $(OUT_RELOCS)/vmlinux.relocs diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index d11206ceff3b..1b5d17a9f70d 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -106,6 +106,27 @@ int tdx_mcall_get_report0(u8 *reportdata, u8 *tdreport) } EXPORT_SYMBOL_GPL(tdx_mcall_get_report0); +/** + * tdx_hcall_get_quote() - Wrapper to request TD Quote using GetQuote + * hypercall. + * @buf: Address of the directly mapped shared kernel buffer which + * contains TDREPORT. The same buffer will be used by VMM to + * store the generated TD Quote output. + * @size: size of the tdquote buffer (4KB-aligned). + * + * Refer to section titled "TDG.VP.VMCALL<GetQuote>" in the TDX GHCI + * v1.0 specification for more information on GetQuote hypercall. + * It is used in the TDX guest driver module to get the TD Quote. + * + * Return 0 on success or error code on failure. + */ +u64 tdx_hcall_get_quote(u8 *buf, size_t size) +{ + /* Since buf is a shared memory, set the shared (decrypted) bits */ + return _tdx_hypercall(TDVMCALL_GET_QUOTE, cc_mkdec(virt_to_phys(buf)), size, 0, 0); +} +EXPORT_SYMBOL_GPL(tdx_hcall_get_quote); + static void __noreturn tdx_panic(const char *msg) { struct tdx_module_args args = { diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 83c0afb7c741..b1b8dd1608f7 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -191,31 +191,4 @@ GCOV_PROFILE := n quiet_cmd_vdso_and_check = VDSO $@ cmd_vdso_and_check = $(cmd_vdso); $(cmd_vdso_check) -# -# Install the unstripped copies of vdso*.so. If our toolchain supports -# build-id, install .build-id links as well. -# -quiet_cmd_vdso_install = INSTALL $(@:install_%=%) -define cmd_vdso_install - cp $< "$(MODLIB)/vdso/$(@:install_%=%)"; \ - if readelf -n $< |grep -q 'Build ID'; then \ - buildid=`readelf -n $< |grep 'Build ID' |sed -e 's/^.*Build ID: \(.*\)$$/\1/'`; \ - first=`echo $$buildid | cut -b-2`; \ - last=`echo $$buildid | cut -b3-`; \ - mkdir -p "$(MODLIB)/vdso/.build-id/$$first"; \ - ln -sf "../../$(@:install_%=%)" "$(MODLIB)/vdso/.build-id/$$first/$$last.debug"; \ - fi -endef - -vdso_img_insttargets := $(vdso_img_sodbg:%.dbg=install_%) - -$(MODLIB)/vdso: FORCE - @mkdir -p $(MODLIB)/vdso - -$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso - $(call cmd,vdso_install) - -PHONY += vdso_install $(vdso_img_insttargets) -vdso_install: $(vdso_img_insttargets) - clean-files := vdso32.so vdso32.so.dbg vdso64* vdso-image-*.c vdsox32.so* diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index b0d192f613b7..d21f48f1c242 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -276,7 +276,8 @@ struct apic { u32 disable_esr : 1, dest_mode_logical : 1, - x2apic_set_max_apicid : 1; + x2apic_set_max_apicid : 1, + nmi_to_offline_cpu : 1; u32 (*calc_dest_apicid)(unsigned int cpu); @@ -531,6 +532,8 @@ extern u32 apic_flat_calc_apicid(unsigned int cpu); extern void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap); extern u32 default_cpu_present_to_apicid(int mps_cpu); +void apic_send_nmi_to_offline_cpu(unsigned int cpu); + #else /* CONFIG_X86_LOCAL_APIC */ static inline u32 read_apic_id(void) { return 0; } diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index 25050d953eee..fecc4fe1d68a 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -71,26 +71,12 @@ static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {} extern __noendbr void cet_disable(void); -struct ucode_cpu_info; +struct cpu_signature; -int intel_cpu_collect_info(struct ucode_cpu_info *uci); - -static inline bool intel_cpu_signatures_match(unsigned int s1, unsigned int p1, - unsigned int s2, unsigned int p2) -{ - if (s1 != s2) - return false; - - /* Processor flags are either both 0 ... */ - if (!p1 && !p2) - return true; - - /* ... or they intersect. */ - return p1 & p2; -} +void intel_collect_cpu_info(struct cpu_signature *sig); extern u64 x86_read_arch_cap_msr(void); -int intel_find_matching_signature(void *mc, unsigned int csig, int cpf); +bool intel_find_matching_signature(void *mc, struct cpu_signature *sig); int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type); extern struct cpumask cpus_stop_mask; diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index bbbe9d744977..695e569159c1 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -23,6 +23,8 @@ static inline void load_ucode_ap(void) { } static inline void microcode_bsp_resume(void) { } #endif +extern unsigned long initrd_start_early; + #ifdef CONFIG_CPU_SUP_INTEL /* Intel specific microcode defines. Public for IFS */ struct microcode_header_intel { @@ -36,7 +38,8 @@ struct microcode_header_intel { unsigned int datasize; unsigned int totalsize; unsigned int metasize; - unsigned int reserved[2]; + unsigned int min_req_ver; + unsigned int reserved; }; struct microcode_intel { @@ -68,11 +71,19 @@ static inline u32 intel_get_microcode_revision(void) return rev; } +#endif /* !CONFIG_CPU_SUP_INTEL */ -void show_ucode_info_early(void); +bool microcode_nmi_handler(void); +void microcode_offline_nmi_handler(void); -#else /* CONFIG_CPU_SUP_INTEL */ -static inline void show_ucode_info_early(void) { } -#endif /* !CONFIG_CPU_SUP_INTEL */ +#ifdef CONFIG_MICROCODE_LATE_LOADING +DECLARE_STATIC_KEY_FALSE(microcode_nmi_handler_enable); +static __always_inline bool microcode_nmi_handler_enabled(void) +{ + return static_branch_unlikely(µcode_nmi_handler_enable); +} +#else +static __always_inline bool microcode_nmi_handler_enabled(void) { return false; } +#endif #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index f3495623ac99..bf483fcb4e57 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -126,6 +126,7 @@ void clear_bss(void); #ifdef __i386__ asmlinkage void __init __noreturn i386_start_kernel(void); +void __init mk_early_pgtbl_32(void); #else asmlinkage void __init __noreturn x86_64_start_kernel(char *real_mode); diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h index f74695dea217..ccce7ebd8677 100644 --- a/arch/x86/include/asm/shared/tdx.h +++ b/arch/x86/include/asm/shared/tdx.h @@ -23,6 +23,7 @@ /* TDX hypercall Leaf IDs */ #define TDVMCALL_MAP_GPA 0x10001 +#define TDVMCALL_GET_QUOTE 0x10002 #define TDVMCALL_REPORT_FATAL_ERROR 0x10003 #define TDVMCALL_STATUS_RETRY 1 diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h index adcbe3f1de30..f3d5305a60fc 100644 --- a/arch/x86/include/asm/tdx.h +++ b/arch/x86/include/asm/tdx.h @@ -56,6 +56,8 @@ bool tdx_early_handle_ve(struct pt_regs *regs); int tdx_mcall_get_report0(u8 *reportdata, u8 *tdreport); +u64 tdx_hcall_get_quote(u8 *buf, size_t size); + #else static inline void tdx_early_init(void) { }; diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 3269a0e23d3a..0000325ab98f 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -16,6 +16,7 @@ CFLAGS_REMOVE_kvmclock.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg CFLAGS_REMOVE_head64.o = -pg +CFLAGS_REMOVE_head32.o = -pg CFLAGS_REMOVE_sev.o = -pg CFLAGS_REMOVE_rethook.o = -pg endif diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 37daa3fd6819..7139867d69cd 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -103,6 +103,7 @@ static struct apic apic_flat __ro_after_init = { .send_IPI_allbutself = default_send_IPI_allbutself, .send_IPI_all = default_send_IPI_all, .send_IPI_self = default_send_IPI_self, + .nmi_to_offline_cpu = true, .read = native_apic_mem_read, .write = native_apic_mem_write, @@ -173,6 +174,7 @@ static struct apic apic_physflat __ro_after_init = { .send_IPI_allbutself = default_send_IPI_allbutself, .send_IPI_all = default_send_IPI_all, .send_IPI_self = default_send_IPI_self, + .nmi_to_offline_cpu = true, .read = native_apic_mem_read, .write = native_apic_mem_write, diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 0078730a512e..5da693d633b7 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -97,6 +97,14 @@ sendmask: __apic_send_IPI_mask(mask, CALL_FUNCTION_VECTOR); } +void apic_send_nmi_to_offline_cpu(unsigned int cpu) +{ + if (WARN_ON_ONCE(!apic->nmi_to_offline_cpu)) + return; + if (WARN_ON_ONCE(!cpumask_test_cpu(cpu, &cpus_booted_once_mask))) + return; + apic->send_IPI(cpu, NMI_VECTOR); +} #endif /* CONFIG_SMP */ static inline int __prepare_ICR2(unsigned int mask) diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index affbff65e497..a8306089c91b 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -251,6 +251,7 @@ static struct apic apic_x2apic_cluster __ro_after_init = { .send_IPI_allbutself = x2apic_send_IPI_allbutself, .send_IPI_all = x2apic_send_IPI_all, .send_IPI_self = x2apic_send_IPI_self, + .nmi_to_offline_cpu = true, .read = native_apic_msr_read, .write = native_apic_msr_write, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 7c9fe28f742f..558a4a8824f4 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -166,6 +166,7 @@ static struct apic apic_x2apic_phys __ro_after_init = { .send_IPI_allbutself = x2apic_send_IPI_allbutself, .send_IPI_all = x2apic_send_IPI_all, .send_IPI_self = x2apic_send_IPI_self, + .nmi_to_offline_cpu = true, .read = native_apic_msr_read, .write = native_apic_msr_write, diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 5d9591146244..b14fc8c1c953 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -2164,8 +2164,6 @@ static inline void setup_getcpu(int cpu) } #ifdef CONFIG_X86_64 -static inline void ucode_cpu_init(int cpu) { } - static inline void tss_setup_ist(struct tss_struct *tss) { /* Set up the per-CPU TSS IST stacks */ @@ -2176,16 +2174,8 @@ static inline void tss_setup_ist(struct tss_struct *tss) /* Only mapped when SEV-ES is active */ tss->x86_tss.ist[IST_INDEX_VC] = __this_cpu_ist_top_va(VC); } - #else /* CONFIG_X86_64 */ - -static inline void ucode_cpu_init(int cpu) -{ - show_ucode_info_early(); -} - static inline void tss_setup_ist(struct tss_struct *tss) { } - #endif /* !CONFIG_X86_64 */ static inline void tss_setup_io_bitmap(struct tss_struct *tss) @@ -2241,8 +2231,6 @@ void cpu_init(void) struct task_struct *cur = current; int cpu = raw_smp_processor_id(); - ucode_cpu_init(cpu); - #ifdef CONFIG_NUMA if (this_cpu_read(numa_node) == 0 && early_cpu_to_node(cpu) != NUMA_NO_NODE) diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index bbd1dc38ea03..9373ec01c5ae 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -37,6 +37,16 @@ #include "internal.h" +struct ucode_patch { + struct list_head plist; + void *data; + unsigned int size; + u32 patch_id; + u16 equiv_cpu; +}; + +static LIST_HEAD(microcode_cache); + #define UCODE_MAGIC 0x00414d44 #define UCODE_EQUIV_CPU_TABLE_TYPE 0x00000000 #define UCODE_UCODE_TYPE 0x00000001 @@ -121,24 +131,20 @@ static u16 find_equiv_id(struct equiv_cpu_table *et, u32 sig) /* * Check whether there is a valid microcode container file at the beginning - * of @buf of size @buf_size. Set @early to use this function in the early path. + * of @buf of size @buf_size. */ -static bool verify_container(const u8 *buf, size_t buf_size, bool early) +static bool verify_container(const u8 *buf, size_t buf_size) { u32 cont_magic; if (buf_size <= CONTAINER_HDR_SZ) { - if (!early) - pr_debug("Truncated microcode container header.\n"); - + pr_debug("Truncated microcode container header.\n"); return false; } cont_magic = *(const u32 *)buf; if (cont_magic != UCODE_MAGIC) { - if (!early) - pr_debug("Invalid magic value (0x%08x).\n", cont_magic); - + pr_debug("Invalid magic value (0x%08x).\n", cont_magic); return false; } @@ -147,23 +153,20 @@ static bool verify_container(const u8 *buf, size_t buf_size, bool early) /* * Check whether there is a valid, non-truncated CPU equivalence table at the - * beginning of @buf of size @buf_size. Set @early to use this function in the - * early path. + * beginning of @buf of size @buf_size. */ -static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early) +static bool verify_equivalence_table(const u8 *buf, size_t buf_size) { const u32 *hdr = (const u32 *)buf; u32 cont_type, equiv_tbl_len; - if (!verify_container(buf, buf_size, early)) + if (!verify_container(buf, buf_size)) return false; cont_type = hdr[1]; if (cont_type != UCODE_EQUIV_CPU_TABLE_TYPE) { - if (!early) - pr_debug("Wrong microcode container equivalence table type: %u.\n", - cont_type); - + pr_debug("Wrong microcode container equivalence table type: %u.\n", + cont_type); return false; } @@ -172,9 +175,7 @@ static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early) equiv_tbl_len = hdr[2]; if (equiv_tbl_len < sizeof(struct equiv_cpu_entry) || buf_size < equiv_tbl_len) { - if (!early) - pr_debug("Truncated equivalence table.\n"); - + pr_debug("Truncated equivalence table.\n"); return false; } @@ -183,22 +184,19 @@ static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early) /* * Check whether there is a valid, non-truncated microcode patch section at the - * beginning of @buf of size @buf_size. Set @early to use this function in the - * early path. + * beginning of @buf of size @buf_size. * * On success, @sh_psize returns the patch size according to the section header, * to the caller. */ static bool -__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize, bool early) +__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize) { u32 p_type, p_size; const u32 *hdr; if (buf_size < SECTION_HDR_SIZE) { - if (!early) - pr_debug("Truncated patch section.\n"); - + pr_debug("Truncated patch section.\n"); return false; } @@ -207,17 +205,13 @@ __verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize, bool early p_size = hdr[1]; if (p_type != UCODE_UCODE_TYPE) { - if (!early) - pr_debug("Invalid type field (0x%x) in container file section header.\n", - p_type); - + pr_debug("Invalid type field (0x%x) in container file section header.\n", + p_type); return false; } if (p_size < sizeof(struct microcode_header_amd)) { - if (!early) - pr_debug("Patch of size %u too short.\n", p_size); - + pr_debug("Patch of size %u too short.\n", p_size); return false; } @@ -269,7 +263,7 @@ static unsigned int __verify_patch_size(u8 family, u32 sh_psize, size_t buf_size * 0: success */ static int -verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool early) +verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size) { struct microcode_header_amd *mc_hdr; unsigned int ret; @@ -277,7 +271,7 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool ea u16 proc_id; u8 patch_fam; - if (!__verify_patch_section(buf, buf_size, &sh_psize, early)) + if (!__verify_patch_section(buf, buf_size, &sh_psize)) return -1; /* @@ -292,16 +286,13 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool ea * size sh_psize, as the section claims. */ if (buf_size < sh_psize) { - if (!early) - pr_debug("Patch of size %u truncated.\n", sh_psize); - + pr_debug("Patch of size %u truncated.\n", sh_psize); return -1; } ret = __verify_patch_size(family, sh_psize, buf_size); if (!ret) { - if (!early) - pr_debug("Per-family patch size mismatch.\n"); + pr_debug("Per-family patch size mismatch.\n"); return -1; } @@ -309,8 +300,7 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool ea mc_hdr = (struct microcode_header_amd *)(buf + SECTION_HDR_SIZE); if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) { - if (!early) - pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n", mc_hdr->patch_id); + pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n", mc_hdr->patch_id); return -1; } @@ -337,7 +327,7 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc) u16 eq_id; u8 *buf; - if (!verify_equivalence_table(ucode, size, true)) + if (!verify_equivalence_table(ucode, size)) return 0; buf = ucode; @@ -364,7 +354,7 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc) u32 patch_size; int ret; - ret = verify_patch(x86_family(desc->cpuid_1_eax), buf, size, &patch_size, true); + ret = verify_patch(x86_family(desc->cpuid_1_eax), buf, size, &patch_size); if (ret < 0) { /* * Patch verification failed, skip to the next container, if @@ -456,14 +446,8 @@ static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size) { struct cont_desc desc = { 0 }; struct microcode_amd *mc; - u32 rev, dummy, *new_rev; bool ret = false; - -#ifdef CONFIG_X86_32 - new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); -#else - new_rev = &ucode_new_rev; -#endif + u32 rev, dummy; desc.cpuid_1_eax = cpuid_1_eax; @@ -484,8 +468,8 @@ static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size) return ret; if (!__apply_microcode_amd(mc)) { - *new_rev = mc->hdr.patch_id; - ret = true; + ucode_new_rev = mc->hdr.patch_id; + ret = true; } return ret; @@ -501,7 +485,7 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) if (family >= 0x15) snprintf(fw_name, sizeof(fw_name), - "amd-ucode/microcode_amd_fam%.2xh.bin", family); + "amd-ucode/microcode_amd_fam%02hhxh.bin", family); if (firmware_request_builtin(&fw, fw_name)) { cp->size = fw.size; @@ -512,36 +496,23 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) return false; } -static void find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpio_data *ret) +static void __init find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpio_data *ret) { - struct ucode_cpu_info *uci; struct cpio_data cp; - const char *path; - bool use_pa; - - if (IS_ENABLED(CONFIG_X86_32)) { - uci = (struct ucode_cpu_info *)__pa_nodebug(ucode_cpu_info); - path = (const char *)__pa_nodebug(ucode_path); - use_pa = true; - } else { - uci = ucode_cpu_info; - path = ucode_path; - use_pa = false; - } if (!get_builtin_microcode(&cp, x86_family(cpuid_1_eax))) - cp = find_microcode_in_initrd(path, use_pa); - - /* Needed in load_microcode_amd() */ - uci->cpu_sig.sig = cpuid_1_eax; + cp = find_microcode_in_initrd(ucode_path); *ret = cp; } -static void apply_ucode_from_containers(unsigned int cpuid_1_eax) +void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax) { struct cpio_data cp = { }; + /* Needed in load_microcode_amd() */ + ucode_cpu_info[0].cpu_sig.sig = cpuid_1_eax; + find_blobs_in_containers(cpuid_1_eax, &cp); if (!(cp.data && cp.size)) return; @@ -549,20 +520,20 @@ static void apply_ucode_from_containers(unsigned int cpuid_1_eax) early_apply_microcode(cpuid_1_eax, cp.data, cp.size); } -void load_ucode_amd_early(unsigned int cpuid_1_eax) -{ - return apply_ucode_from_containers(cpuid_1_eax); -} - static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size); -int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) +static int __init save_microcode_in_initrd(void) { + unsigned int cpuid_1_eax = native_cpuid_eax(1); + struct cpuinfo_x86 *c = &boot_cpu_data; struct cont_desc desc = { 0 }; enum ucode_state ret; struct cpio_data cp; - cp = find_microcode_in_initrd(ucode_path, false); + if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) + return 0; + + find_blobs_in_containers(cpuid_1_eax, &cp); if (!(cp.data && cp.size)) return -EINVAL; @@ -578,6 +549,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) return 0; } +early_initcall(save_microcode_in_initrd); /* * a small, trivial cache of per-family ucode patches @@ -631,7 +603,6 @@ static struct ucode_patch *find_patch(unsigned int cpu) struct ucode_cpu_info *uci = ucode_cpu_info + cpu; u16 equiv_id; - equiv_id = find_equiv_id(&equiv_table, uci->cpu_sig.sig); if (!equiv_id) return NULL; @@ -733,12 +704,20 @@ out: return ret; } +void load_ucode_amd_ap(unsigned int cpuid_1_eax) +{ + unsigned int cpu = smp_processor_id(); + + ucode_cpu_info[cpu].cpu_sig.sig = cpuid_1_eax; + apply_microcode_amd(cpu); +} + static size_t install_equiv_cpu_table(const u8 *buf, size_t buf_size) { u32 equiv_tbl_len; const u32 *hdr; - if (!verify_equivalence_table(buf, buf_size, false)) + if (!verify_equivalence_table(buf, buf_size)) return 0; hdr = (const u32 *)buf; @@ -784,7 +763,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover, u16 proc_id; int ret; - ret = verify_patch(family, fw, leftover, patch_size, false); + ret = verify_patch(family, fw, leftover, patch_size); if (ret) return ret; @@ -909,6 +888,9 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device) enum ucode_state ret = UCODE_NFOUND; const struct firmware *fw; + if (force_minrev) + return UCODE_NFOUND; + if (c->x86 >= 0x15) snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86); @@ -918,7 +900,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device) } ret = UCODE_ERROR; - if (!verify_container(fw->data, fw->size, false)) + if (!verify_container(fw->data, fw->size)) goto fw_release; ret = load_microcode_amd(c->x86, fw->data, fw->size); @@ -938,10 +920,11 @@ static void microcode_fini_cpu_amd(int cpu) } static struct microcode_ops microcode_amd_ops = { - .request_microcode_fw = request_microcode_amd, - .collect_cpu_info = collect_cpu_info_amd, - .apply_microcode = apply_microcode_amd, - .microcode_fini_cpu = microcode_fini_cpu_amd, + .request_microcode_fw = request_microcode_amd, + .collect_cpu_info = collect_cpu_info_amd, + .apply_microcode = apply_microcode_amd, + .microcode_fini_cpu = microcode_fini_cpu_amd, + .nmi_safe = true, }; struct microcode_ops * __init init_amd_microcode(void) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 6cc7a2c181da..666d25bbc5ad 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -23,6 +23,7 @@ #include <linux/miscdevice.h> #include <linux/capability.h> #include <linux/firmware.h> +#include <linux/cpumask.h> #include <linux/kernel.h> #include <linux/delay.h> #include <linux/mutex.h> @@ -31,6 +32,7 @@ #include <linux/fs.h> #include <linux/mm.h> +#include <asm/apic.h> #include <asm/cpu_device_id.h> #include <asm/perf_event.h> #include <asm/processor.h> @@ -42,11 +44,10 @@ #define DRIVER_VERSION "2.2" static struct microcode_ops *microcode_ops; -static bool dis_ucode_ldr = true; +bool dis_ucode_ldr = true; -bool initrd_gone; - -LIST_HEAD(microcode_cache); +bool force_minrev = IS_ENABLED(CONFIG_MICROCODE_LATE_FORCE_MINREV); +module_param(force_minrev, bool, S_IRUSR | S_IWUSR); /* * Synchronization. @@ -90,10 +91,7 @@ static bool amd_check_current_patch_level(void) native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy); - if (IS_ENABLED(CONFIG_X86_32)) - levels = (u32 *)__pa_nodebug(&final_levels); - else - levels = final_levels; + levels = final_levels; for (i = 0; levels[i]; i++) { if (lvl == levels[i]) @@ -105,17 +103,8 @@ static bool amd_check_current_patch_level(void) static bool __init check_loader_disabled_bsp(void) { static const char *__dis_opt_str = "dis_ucode_ldr"; - -#ifdef CONFIG_X86_32 - const char *cmdline = (const char *)__pa_nodebug(boot_command_line); - const char *option = (const char *)__pa_nodebug(__dis_opt_str); - bool *res = (bool *)__pa_nodebug(&dis_ucode_ldr); - -#else /* CONFIG_X86_64 */ const char *cmdline = boot_command_line; const char *option = __dis_opt_str; - bool *res = &dis_ucode_ldr; -#endif /* * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not @@ -123,17 +112,17 @@ static bool __init check_loader_disabled_bsp(void) * that's good enough as they don't land on the BSP path anyway. */ if (native_cpuid_ecx(1) & BIT(31)) - return *res; + return true; if (x86_cpuid_vendor() == X86_VENDOR_AMD) { if (amd_check_current_patch_level()) - return *res; + return true; } if (cmdline_find_option_bool(cmdline, option) <= 0) - *res = false; + dis_ucode_ldr = false; - return *res; + return dis_ucode_ldr; } void __init load_ucode_bsp(void) @@ -168,23 +157,14 @@ void __init load_ucode_bsp(void) if (intel) load_ucode_intel_bsp(); else - load_ucode_amd_early(cpuid_1_eax); -} - -static bool check_loader_disabled_ap(void) -{ -#ifdef CONFIG_X86_32 - return *((bool *)__pa_nodebug(&dis_ucode_ldr)); -#else - return dis_ucode_ldr; -#endif + load_ucode_amd_bsp(cpuid_1_eax); } void load_ucode_ap(void) { unsigned int cpuid_1_eax; - if (check_loader_disabled_ap()) + if (dis_ucode_ldr) return; cpuid_1_eax = native_cpuid_eax(1); @@ -196,97 +176,44 @@ void load_ucode_ap(void) break; case X86_VENDOR_AMD: if (x86_family(cpuid_1_eax) >= 0x10) - load_ucode_amd_early(cpuid_1_eax); - break; - default: - break; - } -} - -static int __init save_microcode_in_initrd(void) -{ - struct cpuinfo_x86 *c = &boot_cpu_data; - int ret = -EINVAL; - - switch (c->x86_vendor) { - case X86_VENDOR_INTEL: - if (c->x86 >= 6) - ret = save_microcode_in_initrd_intel(); - break; - case X86_VENDOR_AMD: - if (c->x86 >= 0x10) - ret = save_microcode_in_initrd_amd(cpuid_eax(1)); + load_ucode_amd_ap(cpuid_1_eax); break; default: break; } - - initrd_gone = true; - - return ret; } -struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) +struct cpio_data __init find_microcode_in_initrd(const char *path) { #ifdef CONFIG_BLK_DEV_INITRD unsigned long start = 0; size_t size; #ifdef CONFIG_X86_32 - struct boot_params *params; - - if (use_pa) - params = (struct boot_params *)__pa_nodebug(&boot_params); - else - params = &boot_params; - - size = params->hdr.ramdisk_size; - - /* - * Set start only if we have an initrd image. We cannot use initrd_start - * because it is not set that early yet. - */ + size = boot_params.hdr.ramdisk_size; + /* Early load on BSP has a temporary mapping. */ if (size) - start = params->hdr.ramdisk_image; + start = initrd_start_early; -# else /* CONFIG_X86_64 */ +#else /* CONFIG_X86_64 */ size = (unsigned long)boot_params.ext_ramdisk_size << 32; size |= boot_params.hdr.ramdisk_size; if (size) { start = (unsigned long)boot_params.ext_ramdisk_image << 32; start |= boot_params.hdr.ramdisk_image; - start += PAGE_OFFSET; } -# endif +#endif /* * Fixup the start address: after reserve_initrd() runs, initrd_start * has the virtual address of the beginning of the initrd. It also * possibly relocates the ramdisk. In either case, initrd_start contains * the updated address so use that instead. - * - * initrd_gone is for the hotplug case where we've thrown out initrd - * already. */ - if (!use_pa) { - if (initrd_gone) - return (struct cpio_data){ NULL, 0, "" }; - if (initrd_start) - start = initrd_start; - } else { - /* - * The picture with physical addresses is a bit different: we - * need to get the *physical* address to which the ramdisk was - * relocated, i.e., relocated_ramdisk (not initrd_start) and - * since we're running from physical addresses, we need to access - * relocated_ramdisk through its *physical* address too. - */ - u64 *rr = (u64 *)__pa_nodebug(&relocated_ramdisk); - if (*rr) - start = *rr; - } + if (initrd_start) + start = initrd_start; return find_cpio_data(path, (void *)start, size, NULL); #else /* !CONFIG_BLK_DEV_INITRD */ @@ -330,117 +257,298 @@ static struct platform_device *microcode_pdev; * requirement can be relaxed in the future. Right now, this is conservative * and good. */ -#define SPINUNIT 100 /* 100 nsec */ +enum sibling_ctrl { + /* Spinwait with timeout */ + SCTRL_WAIT, + /* Invoke the microcode_apply() callback */ + SCTRL_APPLY, + /* Proceed without invoking the microcode_apply() callback */ + SCTRL_DONE, +}; + +struct microcode_ctrl { + enum sibling_ctrl ctrl; + enum ucode_state result; + unsigned int ctrl_cpu; + bool nmi_enabled; +}; -static int check_online_cpus(void) +DEFINE_STATIC_KEY_FALSE(microcode_nmi_handler_enable); +static DEFINE_PER_CPU(struct microcode_ctrl, ucode_ctrl); +static atomic_t late_cpus_in, offline_in_nmi; +static unsigned int loops_per_usec; +static cpumask_t cpu_offline_mask; + +static noinstr bool wait_for_cpus(atomic_t *cnt) { - unsigned int cpu; + unsigned int timeout, loops; - /* - * Make sure all CPUs are online. It's fine for SMT to be disabled if - * all the primary threads are still online. - */ - for_each_present_cpu(cpu) { - if (topology_is_primary_thread(cpu) && !cpu_online(cpu)) { - pr_err("Not all CPUs online, aborting microcode update.\n"); - return -EINVAL; + WARN_ON_ONCE(raw_atomic_dec_return(cnt) < 0); + + for (timeout = 0; timeout < USEC_PER_SEC; timeout++) { + if (!raw_atomic_read(cnt)) + return true; + + for (loops = 0; loops < loops_per_usec; loops++) + cpu_relax(); + + /* If invoked directly, tickle the NMI watchdog */ + if (!microcode_ops->use_nmi && !(timeout % USEC_PER_MSEC)) { + instrumentation_begin(); + touch_nmi_watchdog(); + instrumentation_end(); } } - - return 0; + /* Prevent the late comers from making progress and let them time out */ + raw_atomic_inc(cnt); + return false; } -static atomic_t late_cpus_in; -static atomic_t late_cpus_out; - -static int __wait_for_cpus(atomic_t *t, long long timeout) +static noinstr bool wait_for_ctrl(void) { - int all_cpus = num_online_cpus(); - - atomic_inc(t); + unsigned int timeout, loops; - while (atomic_read(t) < all_cpus) { - if (timeout < SPINUNIT) { - pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n", - all_cpus - atomic_read(t)); - return 1; - } + for (timeout = 0; timeout < USEC_PER_SEC; timeout++) { + if (raw_cpu_read(ucode_ctrl.ctrl) != SCTRL_WAIT) + return true; - ndelay(SPINUNIT); - timeout -= SPINUNIT; + for (loops = 0; loops < loops_per_usec; loops++) + cpu_relax(); - touch_nmi_watchdog(); + /* If invoked directly, tickle the NMI watchdog */ + if (!microcode_ops->use_nmi && !(timeout % USEC_PER_MSEC)) { + instrumentation_begin(); + touch_nmi_watchdog(); + instrumentation_end(); + } } - return 0; + return false; } /* - * Returns: - * < 0 - on error - * 0 - success (no update done or microcode was updated) + * Protected against instrumentation up to the point where the primary + * thread completed the update. See microcode_nmi_handler() for details. */ -static int __reload_late(void *info) +static noinstr bool load_secondary_wait(unsigned int ctrl_cpu) { - int cpu = smp_processor_id(); - enum ucode_state err; - int ret = 0; + /* Initial rendezvous to ensure that all CPUs have arrived */ + if (!wait_for_cpus(&late_cpus_in)) { + raw_cpu_write(ucode_ctrl.result, UCODE_TIMEOUT); + return false; + } /* - * Wait for all CPUs to arrive. A load will not be attempted unless all - * CPUs show up. - * */ - if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC)) - return -1; + * Wait for primary threads to complete. If one of them hangs due + * to the update, there is no way out. This is non-recoverable + * because the CPU might hold locks or resources and confuse the + * scheduler, watchdogs etc. There is no way to safely evacuate the + * machine. + */ + if (wait_for_ctrl()) + return true; + instrumentation_begin(); + panic("Microcode load: Primary CPU %d timed out\n", ctrl_cpu); + instrumentation_end(); +} + +/* + * Protected against instrumentation up to the point where the primary + * thread completed the update. See microcode_nmi_handler() for details. + */ +static noinstr void load_secondary(unsigned int cpu) +{ + unsigned int ctrl_cpu = raw_cpu_read(ucode_ctrl.ctrl_cpu); + enum ucode_state ret; + + if (!load_secondary_wait(ctrl_cpu)) { + instrumentation_begin(); + pr_err_once("load: %d CPUs timed out\n", + atomic_read(&late_cpus_in) - 1); + instrumentation_end(); + return; + } + + /* Primary thread completed. Allow to invoke instrumentable code */ + instrumentation_begin(); /* - * On an SMT system, it suffices to load the microcode on one sibling of - * the core because the microcode engine is shared between the threads. - * Synchronization still needs to take place so that no concurrent - * loading attempts happen on multiple threads of an SMT core. See - * below. + * If the primary succeeded then invoke the apply() callback, + * otherwise copy the state from the primary thread. */ - if (cpumask_first(topology_sibling_cpumask(cpu)) == cpu) - err = microcode_ops->apply_microcode(cpu); + if (this_cpu_read(ucode_ctrl.ctrl) == SCTRL_APPLY) + ret = microcode_ops->apply_microcode(cpu); else - goto wait_for_siblings; + ret = per_cpu(ucode_ctrl.result, ctrl_cpu); - if (err >= UCODE_NFOUND) { - if (err == UCODE_ERROR) { - pr_warn("Error reloading microcode on CPU %d\n", cpu); - ret = -1; - } + this_cpu_write(ucode_ctrl.result, ret); + this_cpu_write(ucode_ctrl.ctrl, SCTRL_DONE); + instrumentation_end(); +} + +static void __load_primary(unsigned int cpu) +{ + struct cpumask *secondaries = topology_sibling_cpumask(cpu); + enum sibling_ctrl ctrl; + enum ucode_state ret; + unsigned int sibling; + + /* Initial rendezvous to ensure that all CPUs have arrived */ + if (!wait_for_cpus(&late_cpus_in)) { + this_cpu_write(ucode_ctrl.result, UCODE_TIMEOUT); + pr_err_once("load: %d CPUs timed out\n", atomic_read(&late_cpus_in) - 1); + return; } -wait_for_siblings: - if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC)) - panic("Timeout during microcode update!\n"); + ret = microcode_ops->apply_microcode(cpu); + this_cpu_write(ucode_ctrl.result, ret); + this_cpu_write(ucode_ctrl.ctrl, SCTRL_DONE); /* - * At least one thread has completed update on each core. - * For others, simply call the update to make sure the - * per-cpu cpuinfo can be updated with right microcode - * revision. + * If the update was successful, let the siblings run the apply() + * callback. If not, tell them it's done. This also covers the + * case where the CPU has uniform loading at package or system + * scope implemented but does not advertise it. */ - if (cpumask_first(topology_sibling_cpumask(cpu)) != cpu) - err = microcode_ops->apply_microcode(cpu); + if (ret == UCODE_UPDATED || ret == UCODE_OK) + ctrl = SCTRL_APPLY; + else + ctrl = SCTRL_DONE; + + for_each_cpu(sibling, secondaries) { + if (sibling != cpu) + per_cpu(ucode_ctrl.ctrl, sibling) = ctrl; + } +} + +static bool kick_offline_cpus(unsigned int nr_offl) +{ + unsigned int cpu, timeout; + + for_each_cpu(cpu, &cpu_offline_mask) { + /* Enable the rendezvous handler and send NMI */ + per_cpu(ucode_ctrl.nmi_enabled, cpu) = true; + apic_send_nmi_to_offline_cpu(cpu); + } + + /* Wait for them to arrive */ + for (timeout = 0; timeout < (USEC_PER_SEC / 2); timeout++) { + if (atomic_read(&offline_in_nmi) == nr_offl) + return true; + udelay(1); + } + /* Let the others time out */ + return false; +} + +static void release_offline_cpus(void) +{ + unsigned int cpu; + + for_each_cpu(cpu, &cpu_offline_mask) + per_cpu(ucode_ctrl.ctrl, cpu) = SCTRL_DONE; +} + +static void load_primary(unsigned int cpu) +{ + unsigned int nr_offl = cpumask_weight(&cpu_offline_mask); + bool proceed = true; + + /* Kick soft-offlined SMT siblings if required */ + if (!cpu && nr_offl) + proceed = kick_offline_cpus(nr_offl); - return ret; + /* If the soft-offlined CPUs did not respond, abort */ + if (proceed) + __load_primary(cpu); + + /* Unconditionally release soft-offlined SMT siblings if required */ + if (!cpu && nr_offl) + release_offline_cpus(); +} + +/* + * Minimal stub rendezvous handler for soft-offlined CPUs which participate + * in the NMI rendezvous to protect against a concurrent NMI on affected + * CPUs. + */ +void noinstr microcode_offline_nmi_handler(void) +{ + if (!raw_cpu_read(ucode_ctrl.nmi_enabled)) + return; + raw_cpu_write(ucode_ctrl.nmi_enabled, false); + raw_cpu_write(ucode_ctrl.result, UCODE_OFFLINE); + raw_atomic_inc(&offline_in_nmi); + wait_for_ctrl(); +} + +static noinstr bool microcode_update_handler(void) +{ + unsigned int cpu = raw_smp_processor_id(); + + if (raw_cpu_read(ucode_ctrl.ctrl_cpu) == cpu) { + instrumentation_begin(); + load_primary(cpu); + instrumentation_end(); + } else { + load_secondary(cpu); + } + + instrumentation_begin(); + touch_nmi_watchdog(); + instrumentation_end(); + + return true; } /* - * Reload microcode late on all CPUs. Wait for a sec until they - * all gather together. + * Protection against instrumentation is required for CPUs which are not + * safe against an NMI which is delivered to the secondary SMT sibling + * while the primary thread updates the microcode. Instrumentation can end + * up in #INT3, #DB and #PF. The IRET from those exceptions reenables NMI + * which is the opposite of what the NMI rendezvous is trying to achieve. + * + * The primary thread is safe versus instrumentation as the actual + * microcode update handles this correctly. It's only the sibling code + * path which must be NMI safe until the primary thread completed the + * update. */ -static int microcode_reload_late(void) +bool noinstr microcode_nmi_handler(void) +{ + if (!raw_cpu_read(ucode_ctrl.nmi_enabled)) + return false; + + raw_cpu_write(ucode_ctrl.nmi_enabled, false); + return microcode_update_handler(); +} + +static int load_cpus_stopped(void *unused) +{ + if (microcode_ops->use_nmi) { + /* Enable the NMI handler and raise NMI */ + this_cpu_write(ucode_ctrl.nmi_enabled, true); + apic->send_IPI(smp_processor_id(), NMI_VECTOR); + } else { + /* Just invoke the handler directly */ + microcode_update_handler(); + } + return 0; +} + +static int load_late_stop_cpus(bool is_safe) { - int old = boot_cpu_data.microcode, ret; + unsigned int cpu, updated = 0, failed = 0, timedout = 0, siblings = 0; + unsigned int nr_offl, offline = 0; + int old_rev = boot_cpu_data.microcode; struct cpuinfo_x86 prev_info; - pr_err("Attempting late microcode loading - it is dangerous and taints the kernel.\n"); - pr_err("You should switch to early loading, if possible.\n"); + if (!is_safe) { + pr_err("Late microcode loading without minimal revision check.\n"); + pr_err("You should switch to early loading, if possible.\n"); + } - atomic_set(&late_cpus_in, 0); - atomic_set(&late_cpus_out, 0); + atomic_set(&late_cpus_in, num_online_cpus()); + atomic_set(&offline_in_nmi, 0); + loops_per_usec = loops_per_jiffy / (TICK_NSEC / 1000); /* * Take a snapshot before the microcode update in order to compare and @@ -448,52 +556,162 @@ static int microcode_reload_late(void) */ store_cpu_caps(&prev_info); - ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask); - if (!ret) { - pr_info("Reload succeeded, microcode revision: 0x%x -> 0x%x\n", - old, boot_cpu_data.microcode); - microcode_check(&prev_info); - } else { - pr_info("Reload failed, current microcode revision: 0x%x\n", - boot_cpu_data.microcode); + if (microcode_ops->use_nmi) + static_branch_enable_cpuslocked(µcode_nmi_handler_enable); + + stop_machine_cpuslocked(load_cpus_stopped, NULL, cpu_online_mask); + + if (microcode_ops->use_nmi) + static_branch_disable_cpuslocked(µcode_nmi_handler_enable); + + /* Analyze the results */ + for_each_cpu_and(cpu, cpu_present_mask, &cpus_booted_once_mask) { + switch (per_cpu(ucode_ctrl.result, cpu)) { + case UCODE_UPDATED: updated++; break; + case UCODE_TIMEOUT: timedout++; break; + case UCODE_OK: siblings++; break; + case UCODE_OFFLINE: offline++; break; + default: failed++; break; + } + } + + if (microcode_ops->finalize_late_load) + microcode_ops->finalize_late_load(!updated); + + if (!updated) { + /* Nothing changed. */ + if (!failed && !timedout) + return 0; + + nr_offl = cpumask_weight(&cpu_offline_mask); + if (offline < nr_offl) { + pr_warn("%u offline siblings did not respond.\n", + nr_offl - atomic_read(&offline_in_nmi)); + return -EIO; + } + pr_err("update failed: %u CPUs failed %u CPUs timed out\n", + failed, timedout); + return -EIO; + } + + if (!is_safe || failed || timedout) + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); + + pr_info("load: updated on %u primary CPUs with %u siblings\n", updated, siblings); + if (failed || timedout) { + pr_err("load incomplete. %u CPUs timed out or failed\n", + num_online_cpus() - (updated + siblings)); + } + pr_info("revision: 0x%x -> 0x%x\n", old_rev, boot_cpu_data.microcode); + microcode_check(&prev_info); + + return updated + siblings == num_online_cpus() ? 0 : -EIO; +} + +/* + * This function does two things: + * + * 1) Ensure that all required CPUs which are present and have been booted + * once are online. + * + * To pass this check, all primary threads must be online. + * + * If the microcode load is not safe against NMI then all SMT threads + * must be online as well because they still react to NMIs when they are + * soft-offlined and parked in one of the play_dead() variants. So if a + * NMI hits while the primary thread updates the microcode the resulting + * behaviour is undefined. The default play_dead() implementation on + * modern CPUs uses MWAIT, which is also not guaranteed to be safe + * against a microcode update which affects MWAIT. + * + * As soft-offlined CPUs still react on NMIs, the SMT sibling + * restriction can be lifted when the vendor driver signals to use NMI + * for rendezvous and the APIC provides a mechanism to send an NMI to a + * soft-offlined CPU. The soft-offlined CPUs are then able to + * participate in the rendezvous in a trivial stub handler. + * + * 2) Initialize the per CPU control structure and create a cpumask + * which contains "offline"; secondary threads, so they can be handled + * correctly by a control CPU. + */ +static bool setup_cpus(void) +{ + struct microcode_ctrl ctrl = { .ctrl = SCTRL_WAIT, .result = -1, }; + bool allow_smt_offline; + unsigned int cpu; + + allow_smt_offline = microcode_ops->nmi_safe || + (microcode_ops->use_nmi && apic->nmi_to_offline_cpu); + + cpumask_clear(&cpu_offline_mask); + + for_each_cpu_and(cpu, cpu_present_mask, &cpus_booted_once_mask) { + /* + * Offline CPUs sit in one of the play_dead() functions + * with interrupts disabled, but they still react on NMIs + * and execute arbitrary code. Also MWAIT being updated + * while the offline CPU sits there is not necessarily safe + * on all CPU variants. + * + * Mark them in the offline_cpus mask which will be handled + * by CPU0 later in the update process. + * + * Ensure that the primary thread is online so that it is + * guaranteed that all cores are updated. + */ + if (!cpu_online(cpu)) { + if (topology_is_primary_thread(cpu) || !allow_smt_offline) { + pr_err("CPU %u not online, loading aborted\n", cpu); + return false; + } + cpumask_set_cpu(cpu, &cpu_offline_mask); + per_cpu(ucode_ctrl, cpu) = ctrl; + continue; + } + + /* + * Initialize the per CPU state. This is core scope for now, + * but prepared to take package or system scope into account. + */ + ctrl.ctrl_cpu = cpumask_first(topology_sibling_cpumask(cpu)); + per_cpu(ucode_ctrl, cpu) = ctrl; } + return true; +} + +static int load_late_locked(void) +{ + if (!setup_cpus()) + return -EBUSY; - return ret; + switch (microcode_ops->request_microcode_fw(0, µcode_pdev->dev)) { + case UCODE_NEW: + return load_late_stop_cpus(false); + case UCODE_NEW_SAFE: + return load_late_stop_cpus(true); + case UCODE_NFOUND: + return -ENOENT; + default: + return -EBADFD; + } } static ssize_t reload_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { - enum ucode_state tmp_ret = UCODE_OK; - int bsp = boot_cpu_data.cpu_index; unsigned long val; - ssize_t ret = 0; + ssize_t ret; ret = kstrtoul(buf, 0, &val); if (ret || val != 1) return -EINVAL; cpus_read_lock(); - - ret = check_online_cpus(); - if (ret) - goto put; - - tmp_ret = microcode_ops->request_microcode_fw(bsp, µcode_pdev->dev); - if (tmp_ret != UCODE_NEW) - goto put; - - ret = microcode_reload_late(); -put: + ret = load_late_locked(); cpus_read_unlock(); - if (ret == 0) - ret = size; - - add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); - - return ret; + return ret ? : size; } static DEVICE_ATTR_WO(reload); @@ -535,17 +753,6 @@ static void microcode_fini_cpu(int cpu) microcode_ops->microcode_fini_cpu(cpu); } -static enum ucode_state microcode_init_cpu(int cpu) -{ - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - - memset(uci, 0, sizeof(*uci)); - - microcode_ops->collect_cpu_info(cpu, &uci->cpu_sig); - - return microcode_ops->apply_microcode(cpu); -} - /** * microcode_bsp_resume - Update boot CPU microcode during resume. */ @@ -564,19 +771,18 @@ static struct syscore_ops mc_syscore_ops = { .resume = microcode_bsp_resume, }; -static int mc_cpu_starting(unsigned int cpu) -{ - enum ucode_state err = microcode_ops->apply_microcode(cpu); - - pr_debug("%s: CPU%d, err: %d\n", __func__, cpu, err); - - return err == UCODE_ERROR; -} - static int mc_cpu_online(unsigned int cpu) { + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; struct device *dev = get_cpu_device(cpu); + memset(uci, 0, sizeof(*uci)); + + microcode_ops->collect_cpu_info(cpu, &uci->cpu_sig); + cpu_data(cpu).microcode = uci->cpu_sig.rev; + if (!cpu) + boot_cpu_data.microcode = uci->cpu_sig.rev; + if (sysfs_create_group(&dev->kobj, &mc_attr_group)) pr_err("Failed to create group for CPU%d\n", cpu); return 0; @@ -584,33 +790,13 @@ static int mc_cpu_online(unsigned int cpu) static int mc_cpu_down_prep(unsigned int cpu) { - struct device *dev; - - dev = get_cpu_device(cpu); + struct device *dev = get_cpu_device(cpu); microcode_fini_cpu(cpu); - - /* Suspend is in progress, only remove the interface */ sysfs_remove_group(&dev->kobj, &mc_attr_group); - pr_debug("%s: CPU%d\n", __func__, cpu); - return 0; } -static void setup_online_cpu(struct work_struct *work) -{ - int cpu = smp_processor_id(); - enum ucode_state err; - - err = microcode_init_cpu(cpu); - if (err == UCODE_ERROR) { - pr_err("Error applying microcode on CPU%d\n", cpu); - return; - } - - mc_cpu_online(cpu); -} - static struct attribute *cpu_root_microcode_attrs[] = { #ifdef CONFIG_MICROCODE_LATE_LOADING &dev_attr_reload.attr, @@ -656,14 +842,9 @@ static int __init microcode_init(void) } } - /* Do per-CPU setup */ - schedule_on_each_cpu(setup_online_cpu); - register_syscore_ops(&mc_syscore_ops); - cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:starting", - mc_cpu_starting, NULL); - cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/microcode:online", - mc_cpu_online, mc_cpu_down_prep); + cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/microcode:online", + mc_cpu_online, mc_cpu_down_prep); pr_info("Microcode Update Driver: v%s.", DRIVER_VERSION); @@ -674,5 +855,4 @@ static int __init microcode_init(void) return error; } -fs_initcall(save_microcode_in_initrd); late_initcall(microcode_init); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 94dd6af9c963..6024feb98d29 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -14,7 +14,6 @@ #include <linux/earlycpio.h> #include <linux/firmware.h> #include <linux/uaccess.h> -#include <linux/vmalloc.h> #include <linux/initrd.h> #include <linux/kernel.h> #include <linux/slab.h> @@ -32,11 +31,14 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin"; +#define UCODE_BSP_LOADED ((struct microcode_intel *)0x1UL) + /* Current microcode patch used in early patching on the APs. */ -static struct microcode_intel *intel_ucode_patch; +static struct microcode_intel *ucode_patch_va __read_mostly; +static struct microcode_intel *ucode_patch_late __read_mostly; /* last level cache size per core */ -static int llc_size_per_core; +static unsigned int llc_size_per_core __ro_after_init; /* microcode format is extended from prescott processors */ struct extended_signature { @@ -66,60 +68,52 @@ static inline unsigned int exttable_size(struct extended_sigtable *et) return et->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE; } -int intel_cpu_collect_info(struct ucode_cpu_info *uci) +void intel_collect_cpu_info(struct cpu_signature *sig) { - unsigned int val[2]; - unsigned int family, model; - struct cpu_signature csig = { 0 }; - unsigned int eax, ebx, ecx, edx; - - memset(uci, 0, sizeof(*uci)); - - eax = 0x00000001; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - csig.sig = eax; + sig->sig = cpuid_eax(1); + sig->pf = 0; + sig->rev = intel_get_microcode_revision(); - family = x86_family(eax); - model = x86_model(eax); + if (x86_model(sig->sig) >= 5 || x86_family(sig->sig) > 6) { + unsigned int val[2]; - if (model >= 5 || family > 6) { /* get processor flags from MSR 0x17 */ native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); - csig.pf = 1 << ((val[1] >> 18) & 7); + sig->pf = 1 << ((val[1] >> 18) & 7); } +} +EXPORT_SYMBOL_GPL(intel_collect_cpu_info); - csig.rev = intel_get_microcode_revision(); - - uci->cpu_sig = csig; +static inline bool cpu_signatures_match(struct cpu_signature *s1, unsigned int sig2, + unsigned int pf2) +{ + if (s1->sig != sig2) + return false; - return 0; + /* Processor flags are either both 0 or they intersect. */ + return ((!s1->pf && !pf2) || (s1->pf & pf2)); } -EXPORT_SYMBOL_GPL(intel_cpu_collect_info); -/* - * Returns 1 if update has been found, 0 otherwise. - */ -int intel_find_matching_signature(void *mc, unsigned int csig, int cpf) +bool intel_find_matching_signature(void *mc, struct cpu_signature *sig) { struct microcode_header_intel *mc_hdr = mc; - struct extended_sigtable *ext_hdr; struct extended_signature *ext_sig; + struct extended_sigtable *ext_hdr; int i; - if (intel_cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf)) - return 1; + if (cpu_signatures_match(sig, mc_hdr->sig, mc_hdr->pf)) + return true; /* Look for ext. headers: */ if (get_totalsize(mc_hdr) <= intel_microcode_get_datasize(mc_hdr) + MC_HEADER_SIZE) - return 0; + return false; ext_hdr = mc + intel_microcode_get_datasize(mc_hdr) + MC_HEADER_SIZE; ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE; for (i = 0; i < ext_hdr->count; i++) { - if (intel_cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf)) - return 1; + if (cpu_signatures_match(sig, ext_sig->sig, ext_sig->pf)) + return true; ext_sig++; } return 0; @@ -240,264 +234,91 @@ int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type) } EXPORT_SYMBOL_GPL(intel_microcode_sanity_check); -/* - * Returns 1 if update has been found, 0 otherwise. - */ -static int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev) +static void update_ucode_pointer(struct microcode_intel *mc) { - struct microcode_header_intel *mc_hdr = mc; - - if (mc_hdr->rev <= new_rev) - return 0; - - return intel_find_matching_signature(mc, csig, cpf); -} - -static struct ucode_patch *memdup_patch(void *data, unsigned int size) -{ - struct ucode_patch *p; - - p = kzalloc(sizeof(struct ucode_patch), GFP_KERNEL); - if (!p) - return NULL; - - p->data = kmemdup(data, size, GFP_KERNEL); - if (!p->data) { - kfree(p); - return NULL; - } - - return p; -} - -static void save_microcode_patch(struct ucode_cpu_info *uci, void *data, unsigned int size) -{ - struct microcode_header_intel *mc_hdr, *mc_saved_hdr; - struct ucode_patch *iter, *tmp, *p = NULL; - bool prev_found = false; - unsigned int sig, pf; - - mc_hdr = (struct microcode_header_intel *)data; - - list_for_each_entry_safe(iter, tmp, µcode_cache, plist) { - mc_saved_hdr = (struct microcode_header_intel *)iter->data; - sig = mc_saved_hdr->sig; - pf = mc_saved_hdr->pf; - - if (intel_find_matching_signature(data, sig, pf)) { - prev_found = true; - - if (mc_hdr->rev <= mc_saved_hdr->rev) - continue; - - p = memdup_patch(data, size); - if (!p) - pr_err("Error allocating buffer %p\n", data); - else { - list_replace(&iter->plist, &p->plist); - kfree(iter->data); - kfree(iter); - } - } - } + kvfree(ucode_patch_va); /* - * There weren't any previous patches found in the list cache; save the - * newly found. + * Save the virtual address for early loading and for eventual free + * on late loading. */ - if (!prev_found) { - p = memdup_patch(data, size); - if (!p) - pr_err("Error allocating buffer for %p\n", data); - else - list_add_tail(&p->plist, µcode_cache); - } - - if (!p) - return; + ucode_patch_va = mc; +} - if (!intel_find_matching_signature(p->data, uci->cpu_sig.sig, uci->cpu_sig.pf)) - return; +static void save_microcode_patch(struct microcode_intel *patch) +{ + unsigned int size = get_totalsize(&patch->hdr); + struct microcode_intel *mc; - /* - * Save for early loading. On 32-bit, that needs to be a physical - * address as the APs are running from physical addresses, before - * paging has been enabled. - */ - if (IS_ENABLED(CONFIG_X86_32)) - intel_ucode_patch = (struct microcode_intel *)__pa_nodebug(p->data); + mc = kvmemdup(patch, size, GFP_KERNEL); + if (mc) + update_ucode_pointer(mc); else - intel_ucode_patch = p->data; + pr_err("Unable to allocate microcode memory size: %u\n", size); } -/* - * Get microcode matching with BSP's model. Only CPUs with the same model as - * BSP can stay in the platform. - */ -static struct microcode_intel * -scan_microcode(void *data, size_t size, struct ucode_cpu_info *uci, bool save) +/* Scan blob for microcode matching the boot CPUs family, model, stepping */ +static __init struct microcode_intel *scan_microcode(void *data, size_t size, + struct ucode_cpu_info *uci, + bool save) { struct microcode_header_intel *mc_header; struct microcode_intel *patch = NULL; + u32 cur_rev = uci->cpu_sig.rev; unsigned int mc_size; - while (size) { - if (size < sizeof(struct microcode_header_intel)) - break; - + for (; size >= sizeof(struct microcode_header_intel); size -= mc_size, data += mc_size) { mc_header = (struct microcode_header_intel *)data; mc_size = get_totalsize(mc_header); - if (!mc_size || - mc_size > size || + if (!mc_size || mc_size > size || intel_microcode_sanity_check(data, false, MC_HEADER_TYPE_MICROCODE) < 0) break; - size -= mc_size; - - if (!intel_find_matching_signature(data, uci->cpu_sig.sig, - uci->cpu_sig.pf)) { - data += mc_size; + if (!intel_find_matching_signature(data, &uci->cpu_sig)) continue; - } + /* + * For saving the early microcode, find the matching revision which + * was loaded on the BSP. + * + * On the BSP during early boot, find a newer revision than + * actually loaded in the CPU. + */ if (save) { - save_microcode_patch(uci, data, mc_size); - goto next; - } - - - if (!patch) { - if (!has_newer_microcode(data, - uci->cpu_sig.sig, - uci->cpu_sig.pf, - uci->cpu_sig.rev)) - goto next; - - } else { - struct microcode_header_intel *phdr = &patch->hdr; - - if (!has_newer_microcode(data, - phdr->sig, - phdr->pf, - phdr->rev)) - goto next; + if (cur_rev != mc_header->rev) + continue; + } else if (cur_rev >= mc_header->rev) { + continue; } - /* We have a newer patch, save it. */ patch = data; - -next: - data += mc_size; + cur_rev = mc_header->rev; } - if (size) - return NULL; - - return patch; + return size ? NULL : patch; } -static bool load_builtin_intel_microcode(struct cpio_data *cp) +static enum ucode_state __apply_microcode(struct ucode_cpu_info *uci, + struct microcode_intel *mc, + u32 *cur_rev) { - unsigned int eax = 1, ebx, ecx = 0, edx; - struct firmware fw; - char name[30]; - - if (IS_ENABLED(CONFIG_X86_32)) - return false; - - native_cpuid(&eax, &ebx, &ecx, &edx); - - sprintf(name, "intel-ucode/%02x-%02x-%02x", - x86_family(eax), x86_model(eax), x86_stepping(eax)); - - if (firmware_request_builtin(&fw, name)) { - cp->size = fw.size; - cp->data = (void *)fw.data; - return true; - } - - return false; -} - -static void print_ucode_info(int old_rev, int new_rev, unsigned int date) -{ - pr_info_once("updated early: 0x%x -> 0x%x, date = %04x-%02x-%02x\n", - old_rev, - new_rev, - date & 0xffff, - date >> 24, - (date >> 16) & 0xff); -} - -#ifdef CONFIG_X86_32 - -static int delay_ucode_info; -static int current_mc_date; -static int early_old_rev; - -/* - * Print early updated ucode info after printk works. This is delayed info dump. - */ -void show_ucode_info_early(void) -{ - struct ucode_cpu_info uci; - - if (delay_ucode_info) { - intel_cpu_collect_info(&uci); - print_ucode_info(early_old_rev, uci.cpu_sig.rev, current_mc_date); - delay_ucode_info = 0; - } -} - -/* - * At this point, we can not call printk() yet. Delay printing microcode info in - * show_ucode_info_early() until printk() works. - */ -static void print_ucode(int old_rev, int new_rev, int date) -{ - int *delay_ucode_info_p; - int *current_mc_date_p; - int *early_old_rev_p; - - delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info); - current_mc_date_p = (int *)__pa_nodebug(¤t_mc_date); - early_old_rev_p = (int *)__pa_nodebug(&early_old_rev); - - *delay_ucode_info_p = 1; - *current_mc_date_p = date; - *early_old_rev_p = old_rev; -} -#else - -static inline void print_ucode(int old_rev, int new_rev, int date) -{ - print_ucode_info(old_rev, new_rev, date); -} -#endif - -static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) -{ - struct microcode_intel *mc; - u32 rev, old_rev; + u32 rev; - mc = uci->mc; if (!mc) - return 0; + return UCODE_NFOUND; /* * Save us the MSR write below - which is a particular expensive * operation - when the other hyperthread has updated the microcode * already. */ - rev = intel_get_microcode_revision(); - if (rev >= mc->hdr.rev) { - uci->cpu_sig.rev = rev; + *cur_rev = intel_get_microcode_revision(); + if (*cur_rev >= mc->hdr.rev) { + uci->cpu_sig.rev = *cur_rev; return UCODE_OK; } - old_rev = rev; - /* * Writeback and invalidate caches before updating microcode to avoid * internal issues depending on what the microcode is updating. @@ -509,247 +330,182 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) rev = intel_get_microcode_revision(); if (rev != mc->hdr.rev) - return -1; + return UCODE_ERROR; uci->cpu_sig.rev = rev; + return UCODE_UPDATED; +} - if (early) - print_ucode(old_rev, uci->cpu_sig.rev, mc->hdr.date); - else - print_ucode_info(old_rev, uci->cpu_sig.rev, mc->hdr.date); +static enum ucode_state apply_microcode_early(struct ucode_cpu_info *uci) +{ + struct microcode_intel *mc = uci->mc; + enum ucode_state ret; + u32 cur_rev, date; - return 0; + ret = __apply_microcode(uci, mc, &cur_rev); + if (ret == UCODE_UPDATED) { + date = mc->hdr.date; + pr_info_once("updated early: 0x%x -> 0x%x, date = %04x-%02x-%02x\n", + cur_rev, mc->hdr.rev, date & 0xffff, date >> 24, (date >> 16) & 0xff); + } + return ret; } -int __init save_microcode_in_initrd_intel(void) +static __init bool load_builtin_intel_microcode(struct cpio_data *cp) { - struct ucode_cpu_info uci; - struct cpio_data cp; - - /* - * initrd is going away, clear patch ptr. We will scan the microcode one - * last time before jettisoning and save a patch, if found. Then we will - * update that pointer too, with a stable patch address to use when - * resuming the cores. - */ - intel_ucode_patch = NULL; + unsigned int eax = 1, ebx, ecx = 0, edx; + struct firmware fw; + char name[30]; - if (!load_builtin_intel_microcode(&cp)) - cp = find_microcode_in_initrd(ucode_path, false); + if (IS_ENABLED(CONFIG_X86_32)) + return false; - if (!(cp.data && cp.size)) - return 0; + native_cpuid(&eax, &ebx, &ecx, &edx); - intel_cpu_collect_info(&uci); + sprintf(name, "intel-ucode/%02x-%02x-%02x", + x86_family(eax), x86_model(eax), x86_stepping(eax)); - scan_microcode(cp.data, cp.size, &uci, true); - return 0; + if (firmware_request_builtin(&fw, name)) { + cp->size = fw.size; + cp->data = (void *)fw.data; + return true; + } + return false; } -/* - * @res_patch, output: a pointer to the patch we found. - */ -static struct microcode_intel *__load_ucode_intel(struct ucode_cpu_info *uci) +static __init struct microcode_intel *get_microcode_blob(struct ucode_cpu_info *uci, bool save) { - static const char *path; struct cpio_data cp; - bool use_pa; - if (IS_ENABLED(CONFIG_X86_32)) { - path = (const char *)__pa_nodebug(ucode_path); - use_pa = true; - } else { - path = ucode_path; - use_pa = false; - } - - /* try built-in microcode first */ if (!load_builtin_intel_microcode(&cp)) - cp = find_microcode_in_initrd(path, use_pa); + cp = find_microcode_in_initrd(ucode_path); if (!(cp.data && cp.size)) return NULL; - intel_cpu_collect_info(uci); + intel_collect_cpu_info(&uci->cpu_sig); - return scan_microcode(cp.data, cp.size, uci, false); + return scan_microcode(cp.data, cp.size, uci, save); } -void __init load_ucode_intel_bsp(void) +/* + * Invoked from an early init call to save the microcode blob which was + * selected during early boot when mm was not usable. The microcode must be + * saved because initrd is going away. It's an early init call so the APs + * just can use the pointer and do not have to scan initrd/builtin firmware + * again. + */ +static int __init save_builtin_microcode(void) { - struct microcode_intel *patch; struct ucode_cpu_info uci; - patch = __load_ucode_intel(&uci); - if (!patch) - return; + if (xchg(&ucode_patch_va, NULL) != UCODE_BSP_LOADED) + return 0; - uci.mc = patch; + if (dis_ucode_ldr || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return 0; - apply_microcode_early(&uci, true); + uci.mc = get_microcode_blob(&uci, true); + if (uci.mc) + save_microcode_patch(uci.mc); + return 0; } +early_initcall(save_builtin_microcode); -void load_ucode_intel_ap(void) +/* Load microcode on BSP from initrd or builtin blobs */ +void __init load_ucode_intel_bsp(void) { - struct microcode_intel *patch, **iup; struct ucode_cpu_info uci; - if (IS_ENABLED(CONFIG_X86_32)) - iup = (struct microcode_intel **) __pa_nodebug(&intel_ucode_patch); - else - iup = &intel_ucode_patch; - - if (!*iup) { - patch = __load_ucode_intel(&uci); - if (!patch) - return; - - *iup = patch; - } - - uci.mc = *iup; - - apply_microcode_early(&uci, true); + uci.mc = get_microcode_blob(&uci, false); + if (uci.mc && apply_microcode_early(&uci) == UCODE_UPDATED) + ucode_patch_va = UCODE_BSP_LOADED; } -static struct microcode_intel *find_patch(struct ucode_cpu_info *uci) +void load_ucode_intel_ap(void) { - struct microcode_header_intel *phdr; - struct ucode_patch *iter, *tmp; - - list_for_each_entry_safe(iter, tmp, µcode_cache, plist) { - - phdr = (struct microcode_header_intel *)iter->data; - - if (phdr->rev <= uci->cpu_sig.rev) - continue; - - if (!intel_find_matching_signature(phdr, - uci->cpu_sig.sig, - uci->cpu_sig.pf)) - continue; + struct ucode_cpu_info uci; - return iter->data; - } - return NULL; + uci.mc = ucode_patch_va; + if (uci.mc) + apply_microcode_early(&uci); } +/* Reload microcode on resume */ void reload_ucode_intel(void) { - struct microcode_intel *p; - struct ucode_cpu_info uci; - - intel_cpu_collect_info(&uci); - - p = find_patch(&uci); - if (!p) - return; - - uci.mc = p; + struct ucode_cpu_info uci = { .mc = ucode_patch_va, }; - apply_microcode_early(&uci, false); + if (uci.mc) + apply_microcode_early(&uci); } static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) { - struct cpuinfo_x86 *c = &cpu_data(cpu_num); - unsigned int val[2]; - - memset(csig, 0, sizeof(*csig)); - - csig->sig = cpuid_eax(0x00000001); - - if ((c->x86_model >= 5) || (c->x86 > 6)) { - /* get processor flags from MSR 0x17 */ - rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); - csig->pf = 1 << ((val[1] >> 18) & 7); - } - - csig->rev = c->microcode; - + intel_collect_cpu_info(csig); return 0; } -static enum ucode_state apply_microcode_intel(int cpu) +static enum ucode_state apply_microcode_late(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - struct cpuinfo_x86 *c = &cpu_data(cpu); - bool bsp = c->cpu_index == boot_cpu_data.cpu_index; - struct microcode_intel *mc; + struct microcode_intel *mc = ucode_patch_late; enum ucode_state ret; - static int prev_rev; - u32 rev; + u32 cur_rev; - /* We should bind the task to the CPU */ - if (WARN_ON(raw_smp_processor_id() != cpu)) + if (WARN_ON_ONCE(smp_processor_id() != cpu)) return UCODE_ERROR; - /* Look for a newer patch in our cache: */ - mc = find_patch(uci); - if (!mc) { - mc = uci->mc; - if (!mc) - return UCODE_NFOUND; - } + ret = __apply_microcode(uci, mc, &cur_rev); + if (ret != UCODE_UPDATED && ret != UCODE_OK) + return ret; - /* - * Save us the MSR write below - which is a particular expensive - * operation - when the other hyperthread has updated the microcode - * already. - */ - rev = intel_get_microcode_revision(); - if (rev >= mc->hdr.rev) { - ret = UCODE_OK; - goto out; + if (!cpu && uci->cpu_sig.rev != cur_rev) { + pr_info("Updated to revision 0x%x, date = %04x-%02x-%02x\n", + uci->cpu_sig.rev, mc->hdr.date & 0xffff, mc->hdr.date >> 24, + (mc->hdr.date >> 16) & 0xff); } - /* - * Writeback and invalidate caches before updating microcode to avoid - * internal issues depending on what the microcode is updating. - */ - native_wbinvd(); + cpu_data(cpu).microcode = uci->cpu_sig.rev; + if (!cpu) + boot_cpu_data.microcode = uci->cpu_sig.rev; - /* write microcode via MSR 0x79 */ - wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); + return ret; +} - rev = intel_get_microcode_revision(); +static bool ucode_validate_minrev(struct microcode_header_intel *mc_header) +{ + int cur_rev = boot_cpu_data.microcode; - if (rev != mc->hdr.rev) { - pr_err("CPU%d update to revision 0x%x failed\n", - cpu, mc->hdr.rev); - return UCODE_ERROR; + /* + * When late-loading, ensure the header declares a minimum revision + * required to perform a late-load. The previously reserved field + * is 0 in older microcode blobs. + */ + if (!mc_header->min_req_ver) { + pr_info("Unsafe microcode update: Microcode header does not specify a required min version\n"); + return false; } - if (bsp && rev != prev_rev) { - pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n", - rev, - mc->hdr.date & 0xffff, - mc->hdr.date >> 24, - (mc->hdr.date >> 16) & 0xff); - prev_rev = rev; + /* + * Check whether the current revision is either greater or equal to + * to the minimum revision specified in the header. + */ + if (cur_rev < mc_header->min_req_ver) { + pr_info("Unsafe microcode update: Current revision 0x%x too old\n", cur_rev); + pr_info("Current should be at 0x%x or higher. Use early loading instead\n", mc_header->min_req_ver); + return false; } - - ret = UCODE_UPDATED; - -out: - uci->cpu_sig.rev = rev; - c->microcode = rev; - - /* Update boot_cpu_data's revision too, if we're on the BSP: */ - if (bsp) - boot_cpu_data.microcode = rev; - - return ret; + return true; } -static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter) +static enum ucode_state parse_microcode_blobs(int cpu, struct iov_iter *iter) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - unsigned int curr_mc_size = 0, new_mc_size = 0; - enum ucode_state ret = UCODE_OK; - int new_rev = uci->cpu_sig.rev; + bool is_safe, new_is_safe = false; + int cur_rev = uci->cpu_sig.rev; + unsigned int curr_mc_size = 0; u8 *new_mc = NULL, *mc = NULL; - unsigned int csig, cpf; while (iov_iter_count(iter)) { struct microcode_header_intel mc_header; @@ -758,68 +514,66 @@ static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter) if (!copy_from_iter_full(&mc_header, sizeof(mc_header), iter)) { pr_err("error! Truncated or inaccessible header in microcode data file\n"); - break; + goto fail; } mc_size = get_totalsize(&mc_header); if (mc_size < sizeof(mc_header)) { pr_err("error! Bad data in microcode data file (totalsize too small)\n"); - break; + goto fail; } data_size = mc_size - sizeof(mc_header); if (data_size > iov_iter_count(iter)) { pr_err("error! Bad data in microcode data file (truncated file?)\n"); - break; + goto fail; } /* For performance reasons, reuse mc area when possible */ if (!mc || mc_size > curr_mc_size) { - vfree(mc); - mc = vmalloc(mc_size); + kvfree(mc); + mc = kvmalloc(mc_size, GFP_KERNEL); if (!mc) - break; + goto fail; curr_mc_size = mc_size; } memcpy(mc, &mc_header, sizeof(mc_header)); data = mc + sizeof(mc_header); if (!copy_from_iter_full(data, data_size, iter) || - intel_microcode_sanity_check(mc, true, MC_HEADER_TYPE_MICROCODE) < 0) { - break; - } + intel_microcode_sanity_check(mc, true, MC_HEADER_TYPE_MICROCODE) < 0) + goto fail; - csig = uci->cpu_sig.sig; - cpf = uci->cpu_sig.pf; - if (has_newer_microcode(mc, csig, cpf, new_rev)) { - vfree(new_mc); - new_rev = mc_header.rev; - new_mc = mc; - new_mc_size = mc_size; - mc = NULL; /* trigger new vmalloc */ - ret = UCODE_NEW; - } - } + if (cur_rev >= mc_header.rev) + continue; - vfree(mc); + if (!intel_find_matching_signature(mc, &uci->cpu_sig)) + continue; - if (iov_iter_count(iter)) { - vfree(new_mc); - return UCODE_ERROR; + is_safe = ucode_validate_minrev(&mc_header); + if (force_minrev && !is_safe) + continue; + + kvfree(new_mc); + cur_rev = mc_header.rev; + new_mc = mc; + new_is_safe = is_safe; + mc = NULL; } + if (iov_iter_count(iter)) + goto fail; + + kvfree(mc); if (!new_mc) return UCODE_NFOUND; - vfree(uci->mc); - uci->mc = (struct microcode_intel *)new_mc; - - /* Save for CPU hotplug */ - save_microcode_patch(uci, new_mc, new_mc_size); + ucode_patch_late = (struct microcode_intel *)new_mc; + return new_is_safe ? UCODE_NEW_SAFE : UCODE_NEW; - pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", - cpu, new_rev, uci->cpu_sig.rev); - - return ret; +fail: + kvfree(mc); + kvfree(new_mc); + return UCODE_ERROR; } static bool is_blacklisted(unsigned int cpu) @@ -868,26 +622,36 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device) kvec.iov_base = (void *)firmware->data; kvec.iov_len = firmware->size; iov_iter_kvec(&iter, ITER_SOURCE, &kvec, 1, firmware->size); - ret = generic_load_microcode(cpu, &iter); + ret = parse_microcode_blobs(cpu, &iter); release_firmware(firmware); return ret; } +static void finalize_late_load(int result) +{ + if (!result) + update_ucode_pointer(ucode_patch_late); + else + kvfree(ucode_patch_late); + ucode_patch_late = NULL; +} + static struct microcode_ops microcode_intel_ops = { - .request_microcode_fw = request_microcode_fw, - .collect_cpu_info = collect_cpu_info, - .apply_microcode = apply_microcode_intel, + .request_microcode_fw = request_microcode_fw, + .collect_cpu_info = collect_cpu_info, + .apply_microcode = apply_microcode_late, + .finalize_late_load = finalize_late_load, + .use_nmi = IS_ENABLED(CONFIG_X86_64), }; -static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c) +static __init void calc_llc_size_per_core(struct cpuinfo_x86 *c) { u64 llc_size = c->x86_cache_size * 1024ULL; do_div(llc_size, c->x86_max_cores); - - return (int)llc_size; + llc_size_per_core = (unsigned int)llc_size; } struct microcode_ops * __init init_intel_microcode(void) @@ -900,7 +664,7 @@ struct microcode_ops * __init init_intel_microcode(void) return NULL; } - llc_size_per_core = calc_llc_size_per_core(c); + calc_llc_size_per_core(c); return µcode_intel_ops; } diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h index bf883aa71233..f8047b12329a 100644 --- a/arch/x86/kernel/cpu/microcode/internal.h +++ b/arch/x86/kernel/cpu/microcode/internal.h @@ -8,43 +8,37 @@ #include <asm/cpu.h> #include <asm/microcode.h> -struct ucode_patch { - struct list_head plist; - void *data; /* Intel uses only this one */ - unsigned int size; - u32 patch_id; - u16 equiv_cpu; -}; - -extern struct list_head microcode_cache; - struct device; enum ucode_state { UCODE_OK = 0, UCODE_NEW, + UCODE_NEW_SAFE, UCODE_UPDATED, UCODE_NFOUND, UCODE_ERROR, + UCODE_TIMEOUT, + UCODE_OFFLINE, }; struct microcode_ops { enum ucode_state (*request_microcode_fw)(int cpu, struct device *dev); - void (*microcode_fini_cpu)(int cpu); /* - * The generic 'microcode_core' part guarantees that - * the callbacks below run on a target cpu when they - * are being called. + * The generic 'microcode_core' part guarantees that the callbacks + * below run on a target CPU when they are being called. * See also the "Synchronization" section in microcode_core.c. */ - enum ucode_state (*apply_microcode)(int cpu); - int (*collect_cpu_info)(int cpu, struct cpu_signature *csig); + enum ucode_state (*apply_microcode)(int cpu); + int (*collect_cpu_info)(int cpu, struct cpu_signature *csig); + void (*finalize_late_load)(int result); + unsigned int nmi_safe : 1, + use_nmi : 1; }; extern struct ucode_cpu_info ucode_cpu_info[]; -struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa); +struct cpio_data find_microcode_in_initrd(const char *path); #define MAX_UCODE_COUNT 128 @@ -94,12 +88,12 @@ static inline unsigned int x86_cpuid_family(void) return x86_family(eax); } -extern bool initrd_gone; +extern bool dis_ucode_ldr; +extern bool force_minrev; #ifdef CONFIG_CPU_SUP_AMD void load_ucode_amd_bsp(unsigned int family); void load_ucode_amd_ap(unsigned int family); -void load_ucode_amd_early(unsigned int cpuid_1_eax); int save_microcode_in_initrd_amd(unsigned int family); void reload_ucode_amd(unsigned int cpu); struct microcode_ops *init_amd_microcode(void); @@ -107,7 +101,6 @@ void exit_amd_microcode(void); #else /* CONFIG_CPU_SUP_AMD */ static inline void load_ucode_amd_bsp(unsigned int family) { } static inline void load_ucode_amd_ap(unsigned int family) { } -static inline void load_ucode_amd_early(unsigned int family) { } static inline int save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; } static inline void reload_ucode_amd(unsigned int cpu) { } static inline struct microcode_ops *init_amd_microcode(void) { return NULL; } @@ -117,13 +110,11 @@ static inline void exit_amd_microcode(void) { } #ifdef CONFIG_CPU_SUP_INTEL void load_ucode_intel_bsp(void); void load_ucode_intel_ap(void); -int save_microcode_in_initrd_intel(void); void reload_ucode_intel(void); struct microcode_ops *init_intel_microcode(void); #else /* CONFIG_CPU_SUP_INTEL */ static inline void load_ucode_intel_bsp(void) { } static inline void load_ucode_intel_ap(void) { } -static inline int save_microcode_in_initrd_intel(void) { return -EINVAL; } static inline void reload_ucode_intel(void) { } static inline struct microcode_ops *init_intel_microcode(void) { return NULL; } #endif /* !CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 246a609f889b..de001b2146ab 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -19,6 +19,7 @@ #include <asm/apic.h> #include <asm/io_apic.h> #include <asm/bios_ebda.h> +#include <asm/microcode.h> #include <asm/tlbflush.h> #include <asm/bootparam_utils.h> @@ -29,11 +30,33 @@ static void __init i386_default_early_setup(void) x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc; } +#ifdef CONFIG_MICROCODE_INITRD32 +unsigned long __initdata initrd_start_early; +static pte_t __initdata *initrd_pl2p_start, *initrd_pl2p_end; + +static void zap_early_initrd_mapping(void) +{ + pte_t *pl2p = initrd_pl2p_start; + + for (; pl2p < initrd_pl2p_end; pl2p++) { + *pl2p = (pte_t){ .pte = 0 }; + + if (!IS_ENABLED(CONFIG_X86_PAE)) + *(pl2p + ((PAGE_OFFSET >> PGDIR_SHIFT))) = (pte_t) {.pte = 0}; + } +} +#else +static inline void zap_early_initrd_mapping(void) { } +#endif + asmlinkage __visible void __init __noreturn i386_start_kernel(void) { /* Make sure IDT is set up before any exception happens */ idt_setup_early_handler(); + load_ucode_bsp(); + zap_early_initrd_mapping(); + cr4_init_shadow(); sanitize_boot_params(&boot_params); @@ -69,52 +92,83 @@ asmlinkage __visible void __init __noreturn i386_start_kernel(void) * to the first kernel PMD. Note the upper half of each PMD or PTE are * always zero at this stage. */ -void __init mk_early_pgtbl_32(void); -void __init mk_early_pgtbl_32(void) -{ -#ifdef __pa -#undef __pa -#endif -#define __pa(x) ((unsigned long)(x) - PAGE_OFFSET) - pte_t pte, *ptep; - int i; - unsigned long *ptr; - /* Enough space to fit pagetables for the low memory linear map */ - const unsigned long limit = __pa(_end) + - (PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT); #ifdef CONFIG_X86_PAE - pmd_t pl2, *pl2p = (pmd_t *)__pa(initial_pg_pmd); -#define SET_PL2(pl2, val) { (pl2).pmd = (val); } +typedef pmd_t pl2_t; +#define pl2_base initial_pg_pmd +#define SET_PL2(val) { .pmd = (val), } #else - pgd_t pl2, *pl2p = (pgd_t *)__pa(initial_page_table); -#define SET_PL2(pl2, val) { (pl2).pgd = (val); } +typedef pgd_t pl2_t; +#define pl2_base initial_page_table +#define SET_PL2(val) { .pgd = (val), } #endif - ptep = (pte_t *)__pa(__brk_base); - pte.pte = PTE_IDENT_ATTR; - +static __init __no_stack_protector pte_t init_map(pte_t pte, pte_t **ptep, pl2_t **pl2p, + const unsigned long limit) +{ while ((pte.pte & PTE_PFN_MASK) < limit) { + pl2_t pl2 = SET_PL2((unsigned long)*ptep | PDE_IDENT_ATTR); + int i; + + **pl2p = pl2; + if (!IS_ENABLED(CONFIG_X86_PAE)) { + /* Kernel PDE entry */ + *(*pl2p + ((PAGE_OFFSET >> PGDIR_SHIFT))) = pl2; + } - SET_PL2(pl2, (unsigned long)ptep | PDE_IDENT_ATTR); - *pl2p = pl2; -#ifndef CONFIG_X86_PAE - /* Kernel PDE entry */ - *(pl2p + ((PAGE_OFFSET >> PGDIR_SHIFT))) = pl2; -#endif for (i = 0; i < PTRS_PER_PTE; i++) { - *ptep = pte; + **ptep = pte; pte.pte += PAGE_SIZE; - ptep++; + (*ptep)++; } - - pl2p++; + (*pl2p)++; } + return pte; +} + +void __init __no_stack_protector mk_early_pgtbl_32(void) +{ + /* Enough space to fit pagetables for the low memory linear map */ + unsigned long limit = __pa_nodebug(_end) + (PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT); + pte_t pte, *ptep = (pte_t *)__pa_nodebug(__brk_base); + struct boot_params __maybe_unused *params; + pl2_t *pl2p = (pl2_t *)__pa_nodebug(pl2_base); + unsigned long *ptr; + + pte.pte = PTE_IDENT_ATTR; + pte = init_map(pte, &ptep, &pl2p, limit); - ptr = (unsigned long *)__pa(&max_pfn_mapped); + ptr = (unsigned long *)__pa_nodebug(&max_pfn_mapped); /* Can't use pte_pfn() since it's a call with CONFIG_PARAVIRT */ *ptr = (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT; - ptr = (unsigned long *)__pa(&_brk_end); + ptr = (unsigned long *)__pa_nodebug(&_brk_end); *ptr = (unsigned long)ptep + PAGE_OFFSET; -} +#ifdef CONFIG_MICROCODE_INITRD32 + /* Running on a hypervisor? */ + if (native_cpuid_ecx(1) & BIT(31)) + return; + + params = (struct boot_params *)__pa_nodebug(&boot_params); + if (!params->hdr.ramdisk_size || !params->hdr.ramdisk_image) + return; + + /* Save the virtual start address */ + ptr = (unsigned long *)__pa_nodebug(&initrd_start_early); + *ptr = (pte.pte & PTE_PFN_MASK) + PAGE_OFFSET; + *ptr += ((unsigned long)params->hdr.ramdisk_image) & ~PAGE_MASK; + + /* Save PLP2 for cleanup */ + ptr = (unsigned long *)__pa_nodebug(&initrd_pl2p_start); + *ptr = (unsigned long)pl2p + PAGE_OFFSET; + + limit = (unsigned long)params->hdr.ramdisk_image; + pte.pte = PTE_IDENT_ATTR | PFN_ALIGN(limit); + limit = (unsigned long)params->hdr.ramdisk_image + params->hdr.ramdisk_size; + + init_map(pte, &ptep, &pl2p, limit); + + ptr = (unsigned long *)__pa_nodebug(&initrd_pl2p_end); + *ptr = (unsigned long)pl2p + PAGE_OFFSET; +#endif +} diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index b6554212b7c7..487ac57e2c81 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -118,11 +118,6 @@ SYM_CODE_START(startup_32) movl %eax, pa(olpc_ofw_pgd) #endif -#ifdef CONFIG_MICROCODE - /* Early load ucode on BSP. */ - call load_ucode_bsp -#endif - /* Create early pagetables. */ call mk_early_pgtbl_32 @@ -157,11 +152,6 @@ SYM_FUNC_START(startup_32_smp) movl %eax,%ss leal -__PAGE_OFFSET(%ecx),%esp -#ifdef CONFIG_MICROCODE - /* Early load ucode on AP. */ - call load_ucode_ap -#endif - .Ldefault_entry: movl $(CR0_STATE & ~X86_CR0_PG),%eax movl %eax,%cr0 diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 4766b6bed443..17e955ab69fe 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -33,6 +33,7 @@ #include <asm/reboot.h> #include <asm/cache.h> #include <asm/nospec-branch.h> +#include <asm/microcode.h> #include <asm/sev.h> #define CREATE_TRACE_POINTS @@ -343,6 +344,9 @@ static noinstr void default_do_nmi(struct pt_regs *regs) instrumentation_begin(); + if (microcode_nmi_handler_enabled() && microcode_nmi_handler()) + goto out; + handled = nmi_handle(NMI_LOCAL, regs); __this_cpu_add(nmi_stats.normal, handled); if (handled) { @@ -498,8 +502,11 @@ DEFINE_IDTENTRY_RAW(exc_nmi) if (IS_ENABLED(CONFIG_NMI_CHECK_CPU)) raw_atomic_long_inc(&nsp->idt_calls); - if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id())) + if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id())) { + if (microcode_nmi_handler_enabled()) + microcode_offline_nmi_handler(); return; + } if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { this_cpu_write(nmi_state, NMI_LATCHED); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 163c35db3d04..1526747bedf2 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1167,7 +1167,7 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_VT #if defined(CONFIG_VGA_CONSOLE) if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) - conswitchp = &vga_con; + vgacon_register_screen(&screen_info); #endif #endif x86_init.oem.banner(); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c4aca66f0902..2cc2aa120b4b 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -272,12 +272,9 @@ static void notrace start_secondary(void *unused) cpu_init_exception_handling(); /* - * 32-bit systems load the microcode from the ASM startup code for - * historical reasons. - * - * On 64-bit systems load it before reaching the AP alive - * synchronization point below so it is not part of the full per - * CPU serialized bringup part when "parallel" bringup is enabled. + * Load the microcode before reaching the AP alive synchronization + * point below so it is not part of the full per CPU serialized + * bringup part when "parallel" bringup is enabled. * * That's even safe when hyperthreading is enabled in the CPU as * the core code starts the primary threads first and leaves the @@ -290,8 +287,7 @@ static void notrace start_secondary(void *unused) * CPUID, MSRs etc. must be strictly serialized to maintain * software state correctness. */ - if (IS_ENABLED(CONFIG_X86_64)) - load_ucode_ap(); + load_ucode_ap(); /* * Synchronization point with the hotplug core. Sets this CPUs diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index 6825e146a62f..b86d634730b2 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -67,15 +67,3 @@ quiet_cmd_vdso = VDSO $@ VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv -z noexecstack GCOV_PROFILE := n - -# -# Install the unstripped copy of vdso*.so listed in $(vdso-install-y). -# -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ -$(vdso-install-y): %.so: $(obj)/%.so.dbg FORCE - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -PHONY += vdso_install $(vdso-install-y) -vdso_install: $(vdso-install-y) diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c index 52d6e4870a04..bdec4a773af0 100644 --- a/arch/xtensa/kernel/setup.c +++ b/arch/xtensa/kernel/setup.c @@ -19,7 +19,6 @@ #include <linux/init.h> #include <linux/mm.h> #include <linux/proc_fs.h> -#include <linux/screen_info.h> #include <linux/kernel.h> #include <linux/percpu.h> #include <linux/reboot.h> @@ -49,17 +48,6 @@ #include <asm/timex.h> #include <asm/traps.h> -#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE) -struct screen_info screen_info = { - .orig_x = 0, - .orig_y = 24, - .orig_video_cols = 80, - .orig_video_lines = 24, - .orig_video_isVGA = 1, - .orig_video_points = 16, -}; -#endif - #ifdef CONFIG_BLK_DEV_INITRD extern unsigned long initrd_start; extern unsigned long initrd_end; |