diff options
Diffstat (limited to 'arch')
354 files changed, 6150 insertions, 3576 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 6682b2a53e34..b8a4ff365582 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -1526,6 +1526,14 @@ config HAVE_ARCH_COMPILER_H linux/compiler-*.h in order to override macro definitions that those headers generally provide. +config HAVE_ARCH_LIBGCC_H + bool + help + An architecture can select this if it provides an + asm/libgcc.h header that should be included after + linux/libgcc.h in order to override macro definitions that + header generally provides. + config HAVE_ARCH_PREL32_RELOCATIONS bool help diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 5b2488142041..62da5827f471 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -6,6 +6,7 @@ config ARC def_bool y select ARC_TIMERS + select ARCH_HAS_CPU_CACHE_ALIASING select ARCH_HAS_CACHE_LINE_SIZE select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_DMA_PREP_COHERENT @@ -24,7 +25,6 @@ config ARC # for now, we don't need GENERIC_IRQ_PROBE, CONFIG_GENERIC_IRQ_CHIP select GENERIC_IRQ_SHOW select GENERIC_PCI_IOMAP - select GENERIC_PENDING_IRQ if SMP select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD select GENERIC_IOREMAP @@ -297,7 +297,6 @@ config ARC_PAGE_SIZE_16K config ARC_PAGE_SIZE_4K bool "4KB" select HAVE_PAGE_SIZE_4KB - depends on ARC_MMU_V3 || ARC_MMU_V4 endchoice @@ -474,7 +473,8 @@ config HIGHMEM config ARC_HAS_PAE40 bool "Support for the 40-bit Physical Address Extension" - depends on ISA_ARCV2 + depends on ARC_MMU_V4 + depends on !ARC_PAGE_SIZE_4K select HIGHMEM select PHYS_ADDR_T_64BIT help diff --git a/arch/arc/Makefile b/arch/arc/Makefile index 2390dd042e36..fb98478ed1ab 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -6,7 +6,7 @@ KBUILD_DEFCONFIG := haps_hs_smp_defconfig ifeq ($(CROSS_COMPILE),) -CROSS_COMPILE := $(call cc-cross-prefix, arc-linux- arceb-linux-) +CROSS_COMPILE := $(call cc-cross-prefix, arc-linux- arceb-linux- arc-linux-gnu-) endif cflags-y += -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__ diff --git a/arch/arc/boot/dts/axc001.dtsi b/arch/arc/boot/dts/axc001.dtsi index 2a151607b080..88bcc7ab6f5a 100644 --- a/arch/arc/boot/dts/axc001.dtsi +++ b/arch/arc/boot/dts/axc001.dtsi @@ -54,7 +54,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <30>; + ngpios = <30>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi index c0a812674ce9..9a2dc39a5cff 100644 --- a/arch/arc/boot/dts/axc003.dtsi +++ b/arch/arc/boot/dts/axc003.dtsi @@ -62,7 +62,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <30>; + ngpios = <30>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi index 67556f4b7057..f31382cb8be4 100644 --- a/arch/arc/boot/dts/axc003_idu.dtsi +++ b/arch/arc/boot/dts/axc003_idu.dtsi @@ -69,7 +69,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <30>; + ngpios = <30>; reg = <0>; interrupt-controller; #interrupt-cells = <2>; diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index b64435385304..3add2fe257f8 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -250,7 +250,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <32>; + ngpios = <32>; reg = <0>; }; @@ -258,7 +258,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <8>; + ngpios = <8>; reg = <1>; }; @@ -266,7 +266,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <8>; + ngpios = <8>; reg = <2>; }; }; @@ -281,7 +281,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <30>; + ngpios = <30>; reg = <0>; }; @@ -289,7 +289,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <10>; + ngpios = <10>; reg = <1>; }; @@ -297,7 +297,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <8>; + ngpios = <8>; reg = <2>; }; }; diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 41b980df862b..98bb850722a4 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -308,7 +308,7 @@ compatible = "snps,dw-apb-gpio-port"; gpio-controller; #gpio-cells = <2>; - snps,nr-gpios = <24>; + ngpios = <24>; reg = <0>; }; }; diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index 4b13f60fe7ca..005d9e4d187a 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -146,7 +146,7 @@ #ifndef __ASSEMBLY__ -#include <soc/arc/aux.h> +#include <soc/arc/arc_aux.h> /* Helpers */ #define TO_KB(bytes) ((bytes) >> 10) diff --git a/arch/arc/include/asm/cachetype.h b/arch/arc/include/asm/cachetype.h new file mode 100644 index 000000000000..acd3b6cb4bf5 --- /dev/null +++ b/arch/arc/include/asm/cachetype.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_ARC_CACHETYPE_H +#define __ASM_ARC_CACHETYPE_H + +#define cpu_dcache_is_aliasing() false +#define cpu_icache_is_aliasing() true + +#endif diff --git a/arch/arc/include/asm/cmpxchg.h b/arch/arc/include/asm/cmpxchg.h index 58045c898340..76f43db0890f 100644 --- a/arch/arc/include/asm/cmpxchg.h +++ b/arch/arc/include/asm/cmpxchg.h @@ -48,7 +48,7 @@ \ switch(sizeof((_p_))) { \ case 1: \ - _prev_ = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *)_p_, (uintptr_t)_o_, (uintptr_t)_n_); \ + _prev_ = (__typeof__(*(ptr)))cmpxchg_emu_u8((volatile u8 *__force)_p_, (uintptr_t)_o_, (uintptr_t)_n_); \ break; \ case 4: \ _prev_ = __cmpxchg(_p_, _o_, _n_); \ diff --git a/arch/arc/include/asm/mmu-arcv2.h b/arch/arc/include/asm/mmu-arcv2.h index d85dc0721907..41412642f279 100644 --- a/arch/arc/include/asm/mmu-arcv2.h +++ b/arch/arc/include/asm/mmu-arcv2.h @@ -9,7 +9,7 @@ #ifndef _ASM_ARC_MMU_ARCV2_H #define _ASM_ARC_MMU_ARCV2_H -#include <soc/arc/aux.h> +#include <soc/arc/arc_aux.h> /* * TLB Management regs diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 55373ca0d28b..cdd370ec9280 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -357,8 +357,6 @@ static void idu_cascade_isr(struct irq_desc *desc) static int idu_irq_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hwirq) { irq_set_chip_and_handler(virq, &idu_irq_chip, handle_level_irq); - irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); - return 0; } diff --git a/arch/arc/net/bpf_jit_arcv2.c b/arch/arc/net/bpf_jit_arcv2.c index 4458e409ca0a..6d989b6d88c6 100644 --- a/arch/arc/net/bpf_jit_arcv2.c +++ b/arch/arc/net/bpf_jit_arcv2.c @@ -2916,7 +2916,7 @@ bool check_jmp_32(u32 curr_off, u32 targ_off, u8 cond) addendum = (cond == ARC_CC_AL) ? 0 : INSN_len_normal; disp = get_displacement(curr_off + addendum, targ_off); - if (ARC_CC_AL) + if (cond == ARC_CC_AL) return is_valid_far_disp(disp); else return is_valid_near_disp(disp); diff --git a/arch/arm/boot/dts/nxp/imx/imxrt1050.dtsi b/arch/arm/boot/dts/nxp/imx/imxrt1050.dtsi index dd714d235d5f..b0bad0d1ba36 100644 --- a/arch/arm/boot/dts/nxp/imx/imxrt1050.dtsi +++ b/arch/arm/boot/dts/nxp/imx/imxrt1050.dtsi @@ -87,7 +87,7 @@ reg = <0x402c0000 0x4000>; interrupts = <110>; clocks = <&clks IMXRT1050_CLK_IPG_PDOF>, - <&clks IMXRT1050_CLK_OSC>, + <&clks IMXRT1050_CLK_AHB_PODF>, <&clks IMXRT1050_CLK_USDHC1>; clock-names = "ipg", "ahb", "per"; bus-width = <4>; diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index 0beecdde55f5..f25eadcba5e6 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -323,6 +323,7 @@ CONFIG_SND_SOC_IMX_SGTL5000=y CONFIG_SND_SOC_FSL_ASOC_CARD=y CONFIG_SND_SOC_AC97_CODEC=y CONFIG_SND_SOC_CS42XX8_I2C=y +CONFIG_SND_SOC_SPDIF=y CONFIG_SND_SOC_TLV320AIC3X_I2C=y CONFIG_SND_SOC_WM8960=y CONFIG_SND_SOC_WM8962=y diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c index 80ceb5bd2680..dd430477e7c1 100644 --- a/arch/arm/kernel/machine_kexec.c +++ b/arch/arm/kernel/machine_kexec.c @@ -127,29 +127,6 @@ void crash_smp_send_stop(void) cpus_stopped = 1; } -static void machine_kexec_mask_interrupts(void) -{ - unsigned int i; - struct irq_desc *desc; - - for_each_irq_desc(i, desc) { - struct irq_chip *chip; - - chip = irq_desc_get_chip(desc); - if (!chip) - continue; - - if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data)) - chip->irq_eoi(&desc->irq_data); - - if (chip->irq_mask) - chip->irq_mask(&desc->irq_data); - - if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data)) - chip->irq_disable(&desc->irq_data); - } -} - void machine_crash_shutdown(struct pt_regs *regs) { local_irq_disable(); diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig index e4fe059cd861..dc47b2312127 100644 --- a/arch/arm/mach-imx/Kconfig +++ b/arch/arm/mach-imx/Kconfig @@ -6,6 +6,7 @@ menuconfig ARCH_MXC select CLKSRC_IMX_GPT select GENERIC_IRQ_CHIP select GPIOLIB + select PINCTRL select PM_OPP if PM select SOC_BUS select SRAM diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 100570a048c5..83017757be8e 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -113,7 +113,7 @@ config ARM64 select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_HUGE_PMD_SHARE if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36) select ARCH_WANT_LD_ORPHAN_WARN - select ARCH_WANTS_EXECMEM_LATE if EXECMEM + select ARCH_WANTS_EXECMEM_LATE select ARCH_WANTS_NO_INSTR select ARCH_WANTS_THP_SWAP if ARM64_4K_PAGES select ARCH_HAS_UBSAN @@ -149,6 +149,7 @@ config ARM64 select GENERIC_IDLE_POLL_SETUP select GENERIC_IOREMAP select GENERIC_IRQ_IPI + select GENERIC_IRQ_KEXEC_CLEAR_VM_FORWARD select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW select GENERIC_IRQ_SHOW_LEVEL @@ -216,9 +217,11 @@ config ARM64 select HAVE_SAMPLE_FTRACE_DIRECT_MULTI select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_GUP_FAST + select HAVE_FTRACE_GRAPH_FUNC select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_TRACER select HAVE_FUNCTION_ERROR_INJECTION + select HAVE_FUNCTION_GRAPH_FREGS select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_GRAPH_RETVAL select HAVE_GCC_PLUGINS @@ -1379,7 +1382,6 @@ config ARM64_VA_BITS_48 config ARM64_VA_BITS_52 bool "52-bit" - depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN help Enable 52-bit virtual addressing for userspace when explicitly requested via a hint to mmap(). The kernel will also use 52-bit @@ -1431,7 +1433,6 @@ config ARM64_PA_BITS_48 config ARM64_PA_BITS_52 bool "52-bit" depends on ARM64_64K_PAGES || ARM64_VA_BITS_52 - depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN help Enable support for a 52-bit physical address space, introduced as part of the ARMv8.2-LPA extension. @@ -1681,6 +1682,7 @@ config RODATA_FULL_DEFAULT_ENABLED config ARM64_SW_TTBR0_PAN bool "Emulate Privileged Access Never using TTBR0_EL1 switching" depends on !KCSAN + select ARM64_PAN help Enabling this option prevents the kernel from accessing user-space memory directly by pointing TTBR0_EL1 to a reserved @@ -1937,7 +1939,6 @@ config ARM64_RAS_EXTN config ARM64_CNP bool "Enable support for Common Not Private (CNP) translations" default y - depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN help Common Not Private (CNP) allows translation table entries to be shared between different PEs in the same inner shareable @@ -2132,7 +2133,7 @@ config ARM64_MTE depends on AS_HAS_ARMV8_5 depends on AS_HAS_LSE_ATOMICS # Required for tag checking in the uaccess routines - depends on ARM64_PAN + select ARM64_PAN select ARCH_HAS_SUBPAGE_FAULTS select ARCH_USES_HIGH_VMA_FLAGS select ARCH_USES_PG_ARCH_2 diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index 370a9d2b6919..02007256709e 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -135,8 +135,6 @@ config ARCH_K3 select SOC_TI select TI_MESSAGE_MANAGER select TI_SCI_PROTOCOL - select TI_SCI_INTR_IRQCHIP - select TI_SCI_INTA_IRQCHIP select TI_K3_SOCINFO help This enables support for Texas Instruments' K3 multicore SoC diff --git a/arch/arm64/boot/dts/arm/fvp-base-revc.dts b/arch/arm64/boot/dts/arm/fvp-base-revc.dts index 19973ab4ea6b..9e10d7a6b5a2 100644 --- a/arch/arm64/boot/dts/arm/fvp-base-revc.dts +++ b/arch/arm64/boot/dts/arm/fvp-base-revc.dts @@ -233,7 +233,7 @@ #interrupt-cells = <0x1>; compatible = "pci-host-ecam-generic"; device_type = "pci"; - bus-range = <0x0 0x1>; + bus-range = <0x0 0xff>; reg = <0x0 0x40000000 0x0 0x10000000>; ranges = <0x2000000 0x0 0x50000000 0x0 0x50000000 0x0 0x10000000>; interrupt-map = <0 0 0 1 &gic 0 0 GIC_SPI 168 IRQ_TYPE_LEVEL_HIGH>, diff --git a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi index 6e5a984c1d4e..26a29e5e5078 100644 --- a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi +++ b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi @@ -67,7 +67,7 @@ l2_cache_l0: l2-cache-l0 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; @@ -91,7 +91,7 @@ l2_cache_l1: l2-cache-l1 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; @@ -115,7 +115,7 @@ l2_cache_l2: l2-cache-l2 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; @@ -139,7 +139,7 @@ l2_cache_l3: l2-cache-l3 { compatible = "cache"; cache-size = <0x80000>; - cache-line-size = <128>; + cache-line-size = <64>; cache-sets = <1024>; //512KiB(size)/64(line-size)=8192ways/8-way set cache-level = <2>; cache-unified; diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi index a60ebb718789..c32a6947ae9c 100644 --- a/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8-ss-audio.dtsi @@ -165,7 +165,7 @@ audio_subsys: bus@59000000 { }; esai0: esai@59010000 { - compatible = "fsl,imx8qm-esai"; + compatible = "fsl,imx8qm-esai", "fsl,imx6ull-esai"; reg = <0x59010000 0x10000>; interrupts = <GIC_SPI 409 IRQ_TYPE_LEVEL_HIGH>; clocks = <&esai0_lpcg IMX_LPCG_CLK_4>, diff --git a/arch/arm64/boot/dts/freescale/imx8qm-ss-audio.dtsi b/arch/arm64/boot/dts/freescale/imx8qm-ss-audio.dtsi index e24e639b98ee..c9b55f02497a 100644 --- a/arch/arm64/boot/dts/freescale/imx8qm-ss-audio.dtsi +++ b/arch/arm64/boot/dts/freescale/imx8qm-ss-audio.dtsi @@ -134,7 +134,7 @@ }; esai1: esai@59810000 { - compatible = "fsl,imx8qm-esai"; + compatible = "fsl,imx8qm-esai", "fsl,imx6ull-esai"; reg = <0x59810000 0x10000>; interrupts = <GIC_SPI 411 IRQ_TYPE_LEVEL_HIGH>; clocks = <&esai1_lpcg IMX_LPCG_CLK_0>, diff --git a/arch/arm64/boot/dts/freescale/imx95.dtsi b/arch/arm64/boot/dts/freescale/imx95.dtsi index d10f62eacfe0..e9c7a8265d71 100644 --- a/arch/arm64/boot/dts/freescale/imx95.dtsi +++ b/arch/arm64/boot/dts/freescale/imx95.dtsi @@ -1673,7 +1673,7 @@ netcmix_blk_ctrl: syscon@4c810000 { compatible = "nxp,imx95-netcmix-blk-ctrl", "syscon"; - reg = <0x0 0x4c810000 0x0 0x10000>; + reg = <0x0 0x4c810000 0x0 0x8>; #clock-cells = <1>; clocks = <&scmi_clk IMX95_CLK_BUSNETCMIX>; assigned-clocks = <&scmi_clk IMX95_CLK_BUSNETCMIX>; diff --git a/arch/arm64/boot/dts/qcom/sa8775p.dtsi b/arch/arm64/boot/dts/qcom/sa8775p.dtsi index 9f315a51a7c1..9da62d7c4d27 100644 --- a/arch/arm64/boot/dts/qcom/sa8775p.dtsi +++ b/arch/arm64/boot/dts/qcom/sa8775p.dtsi @@ -2440,6 +2440,7 @@ qcom,cmb-element-bits = <32>; qcom,cmb-msrs-num = <32>; + status = "disabled"; out-ports { port { @@ -6092,7 +6093,7 @@ <0x0 0x40000000 0x0 0xf20>, <0x0 0x40000f20 0x0 0xa8>, <0x0 0x40001000 0x0 0x4000>, - <0x0 0x40200000 0x0 0x100000>, + <0x0 0x40200000 0x0 0x1fe00000>, <0x0 0x01c03000 0x0 0x1000>, <0x0 0x40005000 0x0 0x2000>; reg-names = "parf", "dbi", "elbi", "atu", "addr_space", @@ -6250,7 +6251,7 @@ <0x0 0x60000000 0x0 0xf20>, <0x0 0x60000f20 0x0 0xa8>, <0x0 0x60001000 0x0 0x4000>, - <0x0 0x60200000 0x0 0x100000>, + <0x0 0x60200000 0x0 0x1fe00000>, <0x0 0x01c13000 0x0 0x1000>, <0x0 0x60005000 0x0 0x2000>; reg-names = "parf", "dbi", "elbi", "atu", "addr_space", diff --git a/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts b/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts index 975550139e10..66513fc8e67a 100644 --- a/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts +++ b/arch/arm64/boot/dts/qcom/x1e78100-lenovo-thinkpad-t14s.dts @@ -773,6 +773,10 @@ status = "okay"; }; +&usb_1_ss0_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss0_dwc3_hs { remote-endpoint = <&pmic_glink_ss0_hs_in>; }; @@ -801,6 +805,10 @@ status = "okay"; }; +&usb_1_ss1_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss1_dwc3_hs { remote-endpoint = <&pmic_glink_ss1_hs_in>; }; diff --git a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts index 39f9d9cdc10d..d51a9bdcf67f 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts +++ b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts @@ -1197,6 +1197,10 @@ status = "okay"; }; +&usb_1_ss0_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss0_dwc3_hs { remote-endpoint = <&pmic_glink_ss0_hs_in>; }; @@ -1225,6 +1229,10 @@ status = "okay"; }; +&usb_1_ss1_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss1_dwc3_hs { remote-endpoint = <&pmic_glink_ss1_hs_in>; }; @@ -1253,6 +1261,10 @@ status = "okay"; }; +&usb_1_ss2_dwc3 { + dr_mode = "host"; +}; + &usb_1_ss2_dwc3_hs { remote-endpoint = <&pmic_glink_ss2_hs_in>; }; diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi index 88805629ed2b..7e4f46ad8edd 100644 --- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi +++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi @@ -2924,7 +2924,7 @@ #address-cells = <3>; #size-cells = <2>; ranges = <0x01000000 0x0 0x00000000 0x0 0x70200000 0x0 0x100000>, - <0x02000000 0x0 0x70300000 0x0 0x70300000 0x0 0x1d00000>; + <0x02000000 0x0 0x70300000 0x0 0x70300000 0x0 0x3d00000>; bus-range = <0x00 0xff>; dma-coherent; @@ -4066,8 +4066,6 @@ dma-coherent; - usb-role-switch; - ports { #address-cells = <1>; #size-cells = <0>; @@ -4321,8 +4319,6 @@ dma-coherent; - usb-role-switch; - ports { #address-cells = <1>; #size-cells = <0>; @@ -4421,8 +4417,6 @@ dma-coherent; - usb-role-switch; - ports { #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index 0597de415fe0..7d992c3c01ce 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -333,6 +333,7 @@ power-domain@RK3328_PD_HEVC { reg = <RK3328_PD_HEVC>; + clocks = <&cru SCLK_VENC_CORE>; #power-domain-cells = <0>; }; power-domain@RK3328_PD_VIDEO { diff --git a/arch/arm64/boot/dts/rockchip/rk3568.dtsi b/arch/arm64/boot/dts/rockchip/rk3568.dtsi index ecaefe208e3e..695cccbdab0f 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3568.dtsi @@ -350,6 +350,7 @@ assigned-clocks = <&pmucru CLK_PCIEPHY0_REF>; assigned-clock-rates = <100000000>; resets = <&cru SRST_PIPEPHY0>; + reset-names = "phy"; rockchip,pipe-grf = <&pipegrf>; rockchip,pipe-phy-grf = <&pipe_phy_grf0>; #phy-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi b/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi index 62be06f3b863..e55390629114 100644 --- a/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk356x-base.dtsi @@ -1681,6 +1681,7 @@ assigned-clocks = <&pmucru CLK_PCIEPHY1_REF>; assigned-clock-rates = <100000000>; resets = <&cru SRST_PIPEPHY1>; + reset-names = "phy"; rockchip,pipe-grf = <&pipegrf>; rockchip,pipe-phy-grf = <&pipe_phy_grf1>; #phy-cells = <1>; @@ -1697,6 +1698,7 @@ assigned-clocks = <&pmucru CLK_PCIEPHY2_REF>; assigned-clock-rates = <100000000>; resets = <&cru SRST_PIPEPHY2>; + reset-names = "phy"; rockchip,pipe-grf = <&pipegrf>; rockchip,pipe-phy-grf = <&pipe_phy_grf2>; #phy-cells = <1>; diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts index c44d001da169..d597112f1d5b 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts +++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b.dts @@ -72,7 +72,7 @@ rfkill { compatible = "rfkill-gpio"; - label = "rfkill-pcie-wlan"; + label = "rfkill-m2-wlan"; radio-type = "wlan"; shutdown-gpios = <&gpio4 RK_PA2 GPIO_ACTIVE_HIGH>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi b/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi index 76a6e8e517e9..c9749cb50076 100644 --- a/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3588s-nanopi-r6.dtsi @@ -434,6 +434,7 @@ &sdmmc { bus-width = <4>; cap-sd-highspeed; + cd-gpios = <&gpio0 RK_PA4 GPIO_ACTIVE_LOW>; disable-wp; max-frequency = <150000000>; no-mmc; diff --git a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi index 467f084c6469..e11d282462bd 100644 --- a/arch/arm64/boot/dts/xilinx/zynqmp.dtsi +++ b/arch/arm64/boot/dts/xilinx/zynqmp.dtsi @@ -1306,11 +1306,14 @@ "dp_vtc_pixel_clk_in"; power-domains = <&zynqmp_firmware PD_DP>; resets = <&zynqmp_reset ZYNQMP_RESET_DP>; - dma-names = "vid0", "vid1", "vid2", "gfx0"; + dma-names = "vid0", "vid1", "vid2", "gfx0", + "aud0", "aud1"; dmas = <&zynqmp_dpdma ZYNQMP_DPDMA_VIDEO0>, <&zynqmp_dpdma ZYNQMP_DPDMA_VIDEO1>, <&zynqmp_dpdma ZYNQMP_DPDMA_VIDEO2>, - <&zynqmp_dpdma ZYNQMP_DPDMA_GRAPHICS>; + <&zynqmp_dpdma ZYNQMP_DPDMA_GRAPHICS>, + <&zynqmp_dpdma ZYNQMP_DPDMA_AUDIO0>, + <&zynqmp_dpdma ZYNQMP_DPDMA_AUDIO1>; ports { #address-cells = <1>; diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 4e350df9a02d..d2ff8f6c3231 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -8,6 +8,7 @@ syscall-y += unistd_32.h syscall-y += unistd_compat_32.h generic-y += early_ioremap.h +generic-y += fprobe.h generic-y += mcs_spinlock.h generic-y += mmzone.h generic-y += qrwlock.h diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 3d8d534a7a77..ad63457a05c5 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -343,6 +343,11 @@ alternative_cb_end // Narrow PARange to fit the PS field in TCR_ELx ubfx \tmp0, \tmp0, #ID_AA64MMFR0_EL1_PARANGE_SHIFT, #3 mov \tmp1, #ID_AA64MMFR0_EL1_PARANGE_MAX +#ifdef CONFIG_ARM64_LPA2 +alternative_if_not ARM64_HAS_VA52 + mov \tmp1, #ID_AA64MMFR0_EL1_PARANGE_48 +alternative_else_nop_endif +#endif cmp \tmp0, \tmp1 csel \tmp0, \tmp1, \tmp0, hi bfi \tcr, \tmp0, \pos, #3 diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index cbbf70e0f204..0b5ca6e0eb09 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -46,6 +46,8 @@ cpucap_is_possible(const unsigned int cap) return IS_ENABLED(CONFIG_ARM64_POE); case ARM64_HAS_GCS: return IS_ENABLED(CONFIG_ARM64_GCS); + case ARM64_HAFT: + return IS_ENABLED(CONFIG_ARM64_HAFT); case ARM64_UNMAP_KERNEL_AT_EL0: return IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0); case ARM64_WORKAROUND_843419: diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index cac5efc836c0..e0e4478f5fb5 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -853,8 +853,7 @@ static inline bool system_supports_gcs(void) static inline bool system_supports_haft(void) { - return IS_ENABLED(CONFIG_ARM64_HAFT) && - cpus_have_final_cap(ARM64_HAFT); + return cpus_have_final_cap(ARM64_HAFT); } static __always_inline bool system_supports_mpam(void) diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 85ef966c08cd..25e162651750 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -87,7 +87,7 @@ 1 << PMSCR_EL2_PA_SHIFT) msr_s SYS_PMSCR_EL2, x0 // addresses and physical counter .Lskip_spe_el2_\@: - mov x0, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT) + mov x0, #MDCR_EL2_E2PB_MASK orr x2, x2, x0 // If we don't have VHE, then // use EL1&0 translation. @@ -100,7 +100,7 @@ and x0, x0, TRBIDR_EL1_P cbnz x0, .Lskip_trace_\@ // If TRBE is available at EL2 - mov x0, #(MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT) + mov x0, #MDCR_EL2_E2TB_MASK orr x2, x2, x0 // allow the EL1&0 translation // to own it. @@ -154,7 +154,7 @@ /* Coprocessor traps */ .macro __init_el2_cptr __check_hvhe .LnVHE_\@, x1 - mov x0, #CPACR_ELx_FPEN + mov x0, #CPACR_EL1_FPEN msr cpacr_el1, x0 b .Lskip_set_cptr_\@ .LnVHE_\@: @@ -332,7 +332,7 @@ // (h)VHE case mrs x0, cpacr_el1 // Disable SVE traps - orr x0, x0, #CPACR_ELx_ZEN + orr x0, x0, #CPACR_EL1_ZEN msr cpacr_el1, x0 b .Lskip_set_cptr_\@ @@ -353,7 +353,7 @@ // (h)VHE case mrs x0, cpacr_el1 // Disable SME traps - orr x0, x0, #CPACR_ELx_SMEN + orr x0, x0, #CPACR_EL1_SMEN msr cpacr_el1, x0 b .Lskip_set_cptr_sme_\@ diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index 5ccff4de7f09..bfe3ce9df197 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -52,6 +52,8 @@ extern unsigned long ftrace_graph_call; extern void return_to_handler(void); unsigned long ftrace_call_adjust(unsigned long addr); +unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip); +#define ftrace_get_symaddr(fentry_ip) arch_ftrace_get_symaddr(fentry_ip) #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS #define HAVE_ARCH_FTRACE_REGS @@ -129,6 +131,38 @@ ftrace_override_function_with_return(struct ftrace_regs *fregs) arch_ftrace_regs(fregs)->pc = arch_ftrace_regs(fregs)->lr; } +static __always_inline unsigned long +ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->fp; +} + +static __always_inline unsigned long +ftrace_regs_get_return_address(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->lr; +} + +static __always_inline struct pt_regs * +ftrace_partial_regs(const struct ftrace_regs *fregs, struct pt_regs *regs) +{ + struct __arch_ftrace_regs *afregs = arch_ftrace_regs(fregs); + + memcpy(regs->regs, afregs->regs, sizeof(afregs->regs)); + regs->sp = afregs->sp; + regs->pc = afregs->pc; + regs->regs[29] = afregs->fp; + regs->regs[30] = afregs->lr; + return regs; +} + +#define arch_ftrace_fill_perf_regs(fregs, _regs) do { \ + (_regs)->pc = arch_ftrace_regs(fregs)->pc; \ + (_regs)->regs[29] = arch_ftrace_regs(fregs)->fp; \ + (_regs)->sp = arch_ftrace_regs(fregs)->sp; \ + (_regs)->pstate = PSR_MODE_EL1h; \ + } while (0) + int ftrace_regs_query_register_offset(const char *name); int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); @@ -186,23 +220,6 @@ static inline bool arch_syscall_match_sym_name(const char *sym, #ifndef __ASSEMBLY__ #ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - /* x0 - x7 */ - unsigned long regs[8]; - - unsigned long fp; - unsigned long __unused; -}; - -static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->regs[0]; -} - -static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->fp; -} void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, unsigned long frame_pointer); diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 2b6c61c608e2..1c3f9617d54f 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -93,6 +93,21 @@ #define KERNEL_HWCAP_PACA __khwcap_feature(PACA) #define KERNEL_HWCAP_PACG __khwcap_feature(PACG) #define KERNEL_HWCAP_GCS __khwcap_feature(GCS) +#define KERNEL_HWCAP_CMPBR __khwcap_feature(CMPBR) +#define KERNEL_HWCAP_FPRCVT __khwcap_feature(FPRCVT) +#define KERNEL_HWCAP_F8MM8 __khwcap_feature(F8MM8) +#define KERNEL_HWCAP_F8MM4 __khwcap_feature(F8MM4) +#define KERNEL_HWCAP_SVE_F16MM __khwcap_feature(SVE_F16MM) +#define KERNEL_HWCAP_SVE_ELTPERM __khwcap_feature(SVE_ELTPERM) +#define KERNEL_HWCAP_SVE_AES2 __khwcap_feature(SVE_AES2) +#define KERNEL_HWCAP_SVE_BFSCALE __khwcap_feature(SVE_BFSCALE) +#define KERNEL_HWCAP_SVE2P2 __khwcap_feature(SVE2P2) +#define KERNEL_HWCAP_SME2P2 __khwcap_feature(SME2P2) +#define KERNEL_HWCAP_SME_SBITPERM __khwcap_feature(SME_SBITPERM) +#define KERNEL_HWCAP_SME_AES __khwcap_feature(SME_AES) +#define KERNEL_HWCAP_SME_SFEXPA __khwcap_feature(SME_SFEXPA) +#define KERNEL_HWCAP_SME_STMOP __khwcap_feature(SME_STMOP) +#define KERNEL_HWCAP_SME_SMOP4 __khwcap_feature(SME_SMOP4) #define __khwcap2_feature(x) (const_ilog2(HWCAP2_ ## x) + 64) #define KERNEL_HWCAP_DCPODP __khwcap2_feature(DCPODP) diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 3e0f0de1d2da..43e365fbff0b 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -391,8 +391,6 @@ ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \ ECN(BKPT32), ECN(VECTOR32), ECN(BRK64), ECN(ERET) -#define CPACR_EL1_TTA (1 << 28) - #define kvm_mode_names \ { PSR_MODE_EL0t, "EL0t" }, \ { PSR_MODE_EL1t, "EL1t" }, \ diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index cf811009a33c..4f1d99725f6b 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -556,13 +556,13 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) ({ \ u64 cptr = 0; \ \ - if ((set) & CPACR_ELx_FPEN) \ + if ((set) & CPACR_EL1_FPEN) \ cptr |= CPTR_EL2_TFP; \ - if ((set) & CPACR_ELx_ZEN) \ + if ((set) & CPACR_EL1_ZEN) \ cptr |= CPTR_EL2_TZ; \ - if ((set) & CPACR_ELx_SMEN) \ + if ((set) & CPACR_EL1_SMEN) \ cptr |= CPTR_EL2_TSM; \ - if ((clr) & CPACR_ELx_TTA) \ + if ((clr) & CPACR_EL1_TTA) \ cptr |= CPTR_EL2_TTA; \ if ((clr) & CPTR_EL2_TAM) \ cptr |= CPTR_EL2_TAM; \ @@ -576,13 +576,13 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) ({ \ u64 cptr = 0; \ \ - if ((clr) & CPACR_ELx_FPEN) \ + if ((clr) & CPACR_EL1_FPEN) \ cptr |= CPTR_EL2_TFP; \ - if ((clr) & CPACR_ELx_ZEN) \ + if ((clr) & CPACR_EL1_ZEN) \ cptr |= CPTR_EL2_TZ; \ - if ((clr) & CPACR_ELx_SMEN) \ + if ((clr) & CPACR_EL1_SMEN) \ cptr |= CPTR_EL2_TSM; \ - if ((set) & CPACR_ELx_TTA) \ + if ((set) & CPACR_EL1_TTA) \ cptr |= CPTR_EL2_TTA; \ if ((set) & CPTR_EL2_TAM) \ cptr |= CPTR_EL2_TAM; \ @@ -595,13 +595,13 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu) #define cpacr_clear_set(clr, set) \ do { \ BUILD_BUG_ON((set) & CPTR_VHE_EL2_RES0); \ - BUILD_BUG_ON((clr) & CPACR_ELx_E0POE); \ - __build_check_all_or_none((clr), CPACR_ELx_FPEN); \ - __build_check_all_or_none((set), CPACR_ELx_FPEN); \ - __build_check_all_or_none((clr), CPACR_ELx_ZEN); \ - __build_check_all_or_none((set), CPACR_ELx_ZEN); \ - __build_check_all_or_none((clr), CPACR_ELx_SMEN); \ - __build_check_all_or_none((set), CPACR_ELx_SMEN); \ + BUILD_BUG_ON((clr) & CPACR_EL1_E0POE); \ + __build_check_all_or_none((clr), CPACR_EL1_FPEN); \ + __build_check_all_or_none((set), CPACR_EL1_FPEN); \ + __build_check_all_or_none((clr), CPACR_EL1_ZEN); \ + __build_check_all_or_none((set), CPACR_EL1_ZEN); \ + __build_check_all_or_none((clr), CPACR_EL1_SMEN); \ + __build_check_all_or_none((set), CPACR_EL1_SMEN); \ \ if (has_vhe() || has_hvhe()) \ sysreg_clear_set(cpacr_el1, clr, set); \ @@ -624,16 +624,16 @@ static __always_inline u64 kvm_get_reset_cptr_el2(struct kvm_vcpu *vcpu) u64 val; if (has_vhe()) { - val = (CPACR_ELx_FPEN | CPACR_EL1_ZEN_EL1EN); + val = (CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN); if (cpus_have_final_cap(ARM64_SME)) val |= CPACR_EL1_SMEN_EL1EN; } else if (has_hvhe()) { - val = CPACR_ELx_FPEN; + val = CPACR_EL1_FPEN; if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs()) - val |= CPACR_ELx_ZEN; + val |= CPACR_EL1_ZEN; if (cpus_have_final_cap(ARM64_SME)) - val |= CPACR_ELx_SMEN; + val |= CPACR_EL1_SMEN; } else { val = CPTR_NVHE_EL2_RES1; @@ -685,7 +685,7 @@ static inline bool ____cptr_xen_trap_enabled(const struct kvm_vcpu *vcpu, #define __guest_hyp_cptr_xen_trap_enabled(vcpu, xen) \ (!vcpu_has_nv(vcpu) ? false : \ ____cptr_xen_trap_enabled(vcpu, \ - SYS_FIELD_GET(CPACR_ELx, xen, \ + SYS_FIELD_GET(CPACR_EL1, xen, \ vcpu_sanitised_cptr_el2(vcpu)))) static inline bool guest_hyp_fpsimd_traps_enabled(const struct kvm_vcpu *vcpu) diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h index 233e65522716..6cd08198bf19 100644 --- a/arch/arm64/include/asm/kvm_nested.h +++ b/arch/arm64/include/asm/kvm_nested.h @@ -33,14 +33,14 @@ static inline u64 translate_tcr_el2_to_tcr_el1(u64 tcr) static inline u64 translate_cptr_el2_to_cpacr_el1(u64 cptr_el2) { - u64 cpacr_el1 = CPACR_ELx_RES1; + u64 cpacr_el1 = CPACR_EL1_RES1; if (cptr_el2 & CPTR_EL2_TTA) - cpacr_el1 |= CPACR_ELx_TTA; + cpacr_el1 |= CPACR_EL1_TTA; if (!(cptr_el2 & CPTR_EL2_TFP)) - cpacr_el1 |= CPACR_ELx_FPEN; + cpacr_el1 |= CPACR_EL1_FPEN; if (!(cptr_el2 & CPTR_EL2_TZ)) - cpacr_el1 |= CPACR_ELx_ZEN; + cpacr_el1 |= CPACR_EL1_ZEN; cpacr_el1 |= cptr_el2 & (CPTR_EL2_TCPAC | CPTR_EL2_TAM); diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 2ec96d91acc6..662471cfc536 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -109,8 +109,5 @@ static inline bool kaslr_requires_kpti(void) return true; } -#define INIT_MM_CONTEXT(name) \ - .pgd = swapper_pg_dir, - #endif /* !__ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index c78a988cca93..a9136cc551cc 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -222,12 +222,6 @@ */ #define S1_TABLE_AP (_AT(pmdval_t, 3) << 61) -/* - * Highest possible physical address supported. - */ -#define PHYS_MASK_SHIFT (CONFIG_ARM64_PA_BITS) -#define PHYS_MASK ((UL(1) << PHYS_MASK_SHIFT) - 1) - #define TTBR_CNP_BIT (UL(1) << 0) /* diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 9f9cf13bbd95..a95f1f77bb39 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -81,6 +81,7 @@ extern unsigned long prot_ns_shared; #define lpa2_is_enabled() false #define PTE_MAYBE_SHARED PTE_SHARED #define PMD_MAYBE_SHARED PMD_SECT_S +#define PHYS_MASK_SHIFT (CONFIG_ARM64_PA_BITS) #else static inline bool __pure lpa2_is_enabled(void) { @@ -89,9 +90,15 @@ static inline bool __pure lpa2_is_enabled(void) #define PTE_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PTE_SHARED) #define PMD_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PMD_SECT_S) +#define PHYS_MASK_SHIFT (lpa2_is_enabled() ? CONFIG_ARM64_PA_BITS : 48) #endif /* + * Highest possible physical address supported. + */ +#define PHYS_MASK ((UL(1) << PHYS_MASK_SHIFT) - 1) + +/* * If we have userspace only BTI we don't want to mark kernel pages * guarded even if the system does support BTI. */ diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 6986345b537a..0b2a2ad1b9e8 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -273,7 +273,7 @@ static inline pte_t pte_mknoncont(pte_t pte) return clear_pte_bit(pte, __pgprot(PTE_CONT)); } -static inline pte_t pte_mkpresent(pte_t pte) +static inline pte_t pte_mkvalid(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_VALID)); } @@ -896,7 +896,7 @@ static inline bool mm_pud_folded(const struct mm_struct *mm) pr_err("%s:%d: bad pud %016llx.\n", __FILE__, __LINE__, pud_val(e)) #define p4d_none(p4d) (pgtable_l4_enabled() && !p4d_val(p4d)) -#define p4d_bad(p4d) (pgtable_l4_enabled() && !(p4d_val(p4d) & 2)) +#define p4d_bad(p4d) (pgtable_l4_enabled() && !(p4d_val(p4d) & P4D_TABLE_BIT)) #define p4d_present(p4d) (!p4d_none(p4d)) static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) @@ -1023,7 +1023,7 @@ static inline bool mm_p4d_folded(const struct mm_struct *mm) pr_err("%s:%d: bad p4d %016llx.\n", __FILE__, __LINE__, p4d_val(e)) #define pgd_none(pgd) (pgtable_l5_enabled() && !pgd_val(pgd)) -#define pgd_bad(pgd) (pgtable_l5_enabled() && !(pgd_val(pgd) & 2)) +#define pgd_bad(pgd) (pgtable_l5_enabled() && !(pgd_val(pgd) & PGD_TABLE_BIT)) #define pgd_present(pgd) (!pgd_none(pgd)) static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) @@ -1345,7 +1345,7 @@ static inline void ___ptep_set_wrprotect(struct mm_struct *mm, } /* - * __ptep_set_wrprotect - mark read-only while trasferring potential hardware + * __ptep_set_wrprotect - mark read-only while transferring potential hardware * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit. */ static inline void __ptep_set_wrprotect(struct mm_struct *mm, diff --git a/arch/arm64/include/asm/rsi.h b/arch/arm64/include/asm/rsi.h index 188cbb9b23f5..b42aeac05340 100644 --- a/arch/arm64/include/asm/rsi.h +++ b/arch/arm64/include/asm/rsi.h @@ -10,6 +10,8 @@ #include <linux/jump_label.h> #include <asm/rsi_cmds.h> +#define RSI_PDEV_NAME "arm-cca-dev" + DECLARE_STATIC_KEY_FALSE(rsi_present); void __init arm64_rsi_init(void); diff --git a/arch/arm64/include/asm/seccomp.h b/arch/arm64/include/asm/seccomp.h index b83975555314..bf6bf40bc5ab 100644 --- a/arch/arm64/include/asm/seccomp.h +++ b/arch/arm64/include/asm/seccomp.h @@ -23,7 +23,6 @@ #define SECCOMP_ARCH_NATIVE_NR NR_syscalls #define SECCOMP_ARCH_NATIVE_NAME "aarch64" #ifdef CONFIG_COMPAT -#include <asm/unistd_compat_32.h> # define SECCOMP_ARCH_COMPAT AUDIT_ARCH_ARM # define SECCOMP_ARCH_COMPAT_NR __NR_compat32_syscalls # define SECCOMP_ARCH_COMPAT_NAME "arm" diff --git a/arch/arm64/include/asm/sparsemem.h b/arch/arm64/include/asm/sparsemem.h index 8a8acc220371..84783efdc9d1 100644 --- a/arch/arm64/include/asm/sparsemem.h +++ b/arch/arm64/include/asm/sparsemem.h @@ -5,7 +5,10 @@ #ifndef __ASM_SPARSEMEM_H #define __ASM_SPARSEMEM_H -#define MAX_PHYSMEM_BITS CONFIG_ARM64_PA_BITS +#include <asm/pgtable-prot.h> + +#define MAX_PHYSMEM_BITS PHYS_MASK_SHIFT +#define MAX_POSSIBLE_PHYSMEM_BITS (52) /* * Section size must be at least 512MB for 64K base diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 48d46b768eae..705a7afa8e58 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -56,6 +56,21 @@ #define HWCAP_PACA (1 << 30) #define HWCAP_PACG (1UL << 31) #define HWCAP_GCS (1UL << 32) +#define HWCAP_CMPBR (1UL << 33) +#define HWCAP_FPRCVT (1UL << 34) +#define HWCAP_F8MM8 (1UL << 35) +#define HWCAP_F8MM4 (1UL << 36) +#define HWCAP_SVE_F16MM (1UL << 37) +#define HWCAP_SVE_ELTPERM (1UL << 38) +#define HWCAP_SVE_AES2 (1UL << 39) +#define HWCAP_SVE_BFSCALE (1UL << 40) +#define HWCAP_SVE2P2 (1UL << 41) +#define HWCAP_SME2P2 (1UL << 42) +#define HWCAP_SME_SBITPERM (1UL << 43) +#define HWCAP_SME_AES (1UL << 44) +#define HWCAP_SME_SFEXPA (1UL << 45) +#define HWCAP_SME_STMOP (1UL << 46) +#define HWCAP_SME_SMOP4 (1UL << 47) /* * HWCAP2 flags - for AT_HWCAP2 diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 29bf85dacffe..eb1a840e4110 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -179,18 +179,6 @@ int main(void) DEFINE(FTRACE_OPS_FUNC, offsetof(struct ftrace_ops, func)); #endif BLANK(); -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - DEFINE(FGRET_REGS_X0, offsetof(struct fgraph_ret_regs, regs[0])); - DEFINE(FGRET_REGS_X1, offsetof(struct fgraph_ret_regs, regs[1])); - DEFINE(FGRET_REGS_X2, offsetof(struct fgraph_ret_regs, regs[2])); - DEFINE(FGRET_REGS_X3, offsetof(struct fgraph_ret_regs, regs[3])); - DEFINE(FGRET_REGS_X4, offsetof(struct fgraph_ret_regs, regs[4])); - DEFINE(FGRET_REGS_X5, offsetof(struct fgraph_ret_regs, regs[5])); - DEFINE(FGRET_REGS_X6, offsetof(struct fgraph_ret_regs, regs[6])); - DEFINE(FGRET_REGS_X7, offsetof(struct fgraph_ret_regs, regs[7])); - DEFINE(FGRET_REGS_FP, offsetof(struct fgraph_ret_regs, fp)); - DEFINE(FGRET_REGS_SIZE, sizeof(struct fgraph_ret_regs)); -#endif #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS DEFINE(FTRACE_OPS_DIRECT_CALL, offsetof(struct ftrace_ops, direct_call)); #endif diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index a983e8660987..4eb7c6698ae4 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -269,6 +269,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { }; static const struct arm64_ftr_bits ftr_id_aa64isar3[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR3_EL1_FPRCVT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR3_EL1_FAMINMAX_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -319,6 +320,8 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_F32MM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_F16MM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_I8MM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_SM4_SHIFT, 4, 0), @@ -331,6 +334,8 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_BitPerm_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_EltPerm_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_AES_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_SVEver_SHIFT, 4, 0), @@ -374,6 +379,16 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8DP4_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8DP2_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SBitPerm_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_AES_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SFEXPA_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_STMOP_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SMOP4_SHIFT, 1, 0), ARM64_FTR_END, }; @@ -382,6 +397,8 @@ static const struct arm64_ftr_bits ftr_id_aa64fpfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8FMA_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8DP4_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8DP2_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8MM8_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8MM4_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E4M3_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E5M2_SHIFT, 1, 0), ARM64_FTR_END, @@ -1005,17 +1022,16 @@ static void init_cpu_ftr_reg(u32 sys_reg, u64 new) /* Override was valid */ ftr_new = tmp; str = "forced"; - } else if (ftr_ovr == tmp) { + } else { /* Override was the safe value */ str = "already set"; } - if (str) - pr_warn("%s[%d:%d]: %s to %llx\n", - reg->name, - ftrp->shift + ftrp->width - 1, - ftrp->shift, str, - tmp & (BIT(ftrp->width) - 1)); + pr_warn("%s[%d:%d]: %s to %llx\n", + reg->name, + ftrp->shift + ftrp->width - 1, + ftrp->shift, str, + tmp & (BIT(ftrp->width) - 1)); } else if ((ftr_mask & reg->override->val) == ftr_mask) { reg->override->val &= ~ftr_mask; pr_warn("%s[%d:%d]: impossible override, ignored\n", @@ -1168,12 +1184,6 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1))) { unsigned long cpacr = cpacr_save_enable_kernel_sme(); - /* - * We mask out SMPS since even if the hardware - * supports priorities the kernel does not at present - * and we block access to them. - */ - info->reg_smidr = read_cpuid(SMIDR_EL1) & ~SMIDR_EL1_SMPS; vec_init_vq_map(ARM64_VEC_SME); cpacr_restore(cpacr); @@ -1424,13 +1434,6 @@ void update_cpu_features(int cpu, id_aa64pfr1_sme(read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1))) { unsigned long cpacr = cpacr_save_enable_kernel_sme(); - /* - * We mask out SMPS since even if the hardware - * supports priorities the kernel does not at present - * and we block access to them. - */ - info->reg_smidr = read_cpuid(SMIDR_EL1) & ~SMIDR_EL1_SMPS; - /* Probe vector lengths */ if (!system_capabilities_finalized()) vec_update_vq_map(ARM64_VEC_SME); @@ -2382,8 +2385,8 @@ static void cpu_enable_mops(const struct arm64_cpu_capabilities *__unused) #ifdef CONFIG_ARM64_POE static void cpu_enable_poe(const struct arm64_cpu_capabilities *__unused) { - sysreg_clear_set(REG_TCR2_EL1, 0, TCR2_EL1x_E0POE); - sysreg_clear_set(CPACR_EL1, 0, CPACR_ELx_E0POE); + sysreg_clear_set(REG_TCR2_EL1, 0, TCR2_EL1_E0POE); + sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_E0POE); } #endif @@ -3028,6 +3031,13 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = match, \ } +#define HWCAP_CAP_MATCH_ID(match, reg, field, min_value, cap_type, cap) \ + { \ + __HWCAP_CAP(#cap, cap_type, cap) \ + HWCAP_CPUID_MATCH(reg, field, min_value) \ + .matches = match, \ + } + #ifdef CONFIG_ARM64_PTR_AUTH static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = { { @@ -3056,6 +3066,13 @@ static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = { }; #endif +#ifdef CONFIG_ARM64_SVE +static bool has_sve_feature(const struct arm64_cpu_capabilities *cap, int scope) +{ + return system_supports_sve() && has_user_cpuid_feature(cap, scope); +} +#endif + static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR0_EL1, AES, PMULL, CAP_HWCAP, KERNEL_HWCAP_PMULL), HWCAP_CAP(ID_AA64ISAR0_EL1, AES, AES, CAP_HWCAP, KERNEL_HWCAP_AES), @@ -3098,19 +3115,24 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64MMFR2_EL1, AT, IMP, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE HWCAP_CAP(ID_AA64PFR0_EL1, SVE, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE), - HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1), - HWCAP_CAP(ID_AA64ZFR0_EL1, SVEver, SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), - HWCAP_CAP(ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES), - HWCAP_CAP(ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), - HWCAP_CAP(ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), - HWCAP_CAP(ID_AA64ZFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_B16B16), - HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), - HWCAP_CAP(ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16), - HWCAP_CAP(ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), - HWCAP_CAP(ID_AA64ZFR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4), - HWCAP_CAP(ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), - HWCAP_CAP(ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), - HWCAP_CAP(ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2p2, CAP_HWCAP, KERNEL_HWCAP_SVE2P2), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, AES, AES2, CAP_HWCAP, KERNEL_HWCAP_SVE_AES2), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_B16B16), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, B16B16, BFSCALE, CAP_HWCAP, KERNEL_HWCAP_SVE_BFSCALE), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, F16MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_F16MM), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, EltPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_ELTPERM), #endif #ifdef CONFIG_ARM64_GCS HWCAP_CAP(ID_AA64PFR1_EL1, GCS, IMP, CAP_HWCAP, KERNEL_HWCAP_GCS), @@ -3130,6 +3152,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64MMFR0_EL1, ECV, IMP, CAP_HWCAP, KERNEL_HWCAP_ECV), HWCAP_CAP(ID_AA64MMFR1_EL1, AFP, IMP, CAP_HWCAP, KERNEL_HWCAP_AFP), HWCAP_CAP(ID_AA64ISAR2_EL1, CSSC, IMP, CAP_HWCAP, KERNEL_HWCAP_CSSC), + HWCAP_CAP(ID_AA64ISAR2_EL1, CSSC, CMPBR, CAP_HWCAP, KERNEL_HWCAP_CMPBR), HWCAP_CAP(ID_AA64ISAR2_EL1, RPRFM, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRFM), HWCAP_CAP(ID_AA64ISAR2_EL1, RPRES, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRES), HWCAP_CAP(ID_AA64ISAR2_EL1, WFxT, IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT), @@ -3139,6 +3162,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME), HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), HWCAP_CAP(ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2), + HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p2, CAP_HWCAP, KERNEL_HWCAP_SME2P2), HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1), HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2), HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), @@ -3156,6 +3180,13 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA), HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4), HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2), + HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM8, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM8), + HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM4), + HWCAP_CAP(ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM), + HWCAP_CAP(ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES), + HWCAP_CAP(ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA), + HWCAP_CAP(ID_AA64SMFR0_EL1, STMOP, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_STMOP), + HWCAP_CAP(ID_AA64SMFR0_EL1, SMOP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SMOP4), #endif /* CONFIG_ARM64_SME */ HWCAP_CAP(ID_AA64FPFR0_EL1, F8CVT, IMP, CAP_HWCAP, KERNEL_HWCAP_F8CVT), HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA), @@ -3484,7 +3515,7 @@ static void verify_hyp_capabilities(void) return; safe_mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); - mmfr0 = read_cpuid(ID_AA64MMFR0_EL1); + mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); /* Verify VMID bits */ diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index d79e88fccdfc..285d7d538342 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -145,6 +145,21 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_SME_SF8DP4] = "smesf8dp4", [KERNEL_HWCAP_SME_SF8DP2] = "smesf8dp2", [KERNEL_HWCAP_POE] = "poe", + [KERNEL_HWCAP_CMPBR] = "cmpbr", + [KERNEL_HWCAP_FPRCVT] = "fprcvt", + [KERNEL_HWCAP_F8MM8] = "f8mm8", + [KERNEL_HWCAP_F8MM4] = "f8mm4", + [KERNEL_HWCAP_SVE_F16MM] = "svef16mm", + [KERNEL_HWCAP_SVE_ELTPERM] = "sveeltperm", + [KERNEL_HWCAP_SVE_AES2] = "sveaes2", + [KERNEL_HWCAP_SVE_BFSCALE] = "svebfscale", + [KERNEL_HWCAP_SVE2P2] = "sve2p2", + [KERNEL_HWCAP_SME2P2] = "sme2p2", + [KERNEL_HWCAP_SME_SBITPERM] = "smesbitperm", + [KERNEL_HWCAP_SME_AES] = "smeaes", + [KERNEL_HWCAP_SME_SFEXPA] = "smesfexpa", + [KERNEL_HWCAP_SME_STMOP] = "smestmop", + [KERNEL_HWCAP_SME_SMOP4] = "smesmop4", }; #ifdef CONFIG_COMPAT @@ -482,6 +497,16 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) if (id_aa64pfr0_mpam(info->reg_id_aa64pfr0)) info->reg_mpamidr = read_cpuid(MPAMIDR_EL1); + if (IS_ENABLED(CONFIG_ARM64_SME) && + id_aa64pfr1_sme(info->reg_id_aa64pfr1)) { + /* + * We mask out SMPS since even if the hardware + * supports priorities the kernel does not at present + * and we block access to them. + */ + info->reg_smidr = read_cpuid(SMIDR_EL1) & ~SMIDR_EL1_SMPS; + } + cpuinfo_detect_icache_policy(info); } diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index f0c16640ef21..169ccf600066 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -329,24 +329,28 @@ SYM_FUNC_END(ftrace_stub_graph) * @fp is checked against the value passed by ftrace_graph_caller(). */ SYM_CODE_START(return_to_handler) - /* save return value regs */ - sub sp, sp, #FGRET_REGS_SIZE - stp x0, x1, [sp, #FGRET_REGS_X0] - stp x2, x3, [sp, #FGRET_REGS_X2] - stp x4, x5, [sp, #FGRET_REGS_X4] - stp x6, x7, [sp, #FGRET_REGS_X6] - str x29, [sp, #FGRET_REGS_FP] // parent's fp + /* Make room for ftrace_regs */ + sub sp, sp, #FREGS_SIZE + + /* Save return value regs */ + stp x0, x1, [sp, #FREGS_X0] + stp x2, x3, [sp, #FREGS_X2] + stp x4, x5, [sp, #FREGS_X4] + stp x6, x7, [sp, #FREGS_X6] + + /* Save the callsite's FP */ + str x29, [sp, #FREGS_FP] mov x0, sp - bl ftrace_return_to_handler // addr = ftrace_return_to_hander(regs); + bl ftrace_return_to_handler // addr = ftrace_return_to_hander(fregs); mov x30, x0 // restore the original return address - /* restore return value regs */ - ldp x0, x1, [sp, #FGRET_REGS_X0] - ldp x2, x3, [sp, #FGRET_REGS_X2] - ldp x4, x5, [sp, #FGRET_REGS_X4] - ldp x6, x7, [sp, #FGRET_REGS_X6] - add sp, sp, #FGRET_REGS_SIZE + /* Restore return value regs */ + ldp x0, x1, [sp, #FREGS_X0] + ldp x2, x3, [sp, #FREGS_X2] + ldp x4, x5, [sp, #FREGS_X4] + ldp x6, x7, [sp, #FREGS_X6] + add sp, sp, #FREGS_SIZE ret SYM_CODE_END(return_to_handler) diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 245cb419ca24..d7c0d023dfe5 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -143,6 +143,69 @@ unsigned long ftrace_call_adjust(unsigned long addr) return addr; } +/* Convert fentry_ip to the symbol address without kallsyms */ +unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip) +{ + u32 insn; + + /* + * When using patchable-function-entry without pre-function NOPS, ftrace + * entry is the address of the first NOP after the function entry point. + * + * The compiler has either generated: + * + * func+00: func: NOP // To be patched to MOV X9, LR + * func+04: NOP // To be patched to BL <caller> + * + * Or: + * + * func-04: BTI C + * func+00: func: NOP // To be patched to MOV X9, LR + * func+04: NOP // To be patched to BL <caller> + * + * The fentry_ip is the address of `BL <caller>` which is at `func + 4` + * bytes in either case. + */ + if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + return fentry_ip - AARCH64_INSN_SIZE; + + /* + * When using patchable-function-entry with pre-function NOPs, BTI is + * a bit different. + * + * func+00: func: NOP // To be patched to MOV X9, LR + * func+04: NOP // To be patched to BL <caller> + * + * Or: + * + * func+00: func: BTI C + * func+04: NOP // To be patched to MOV X9, LR + * func+08: NOP // To be patched to BL <caller> + * + * The fentry_ip is the address of `BL <caller>` which is at either + * `func + 4` or `func + 8` depends on whether there is a BTI. + */ + + /* If there is no BTI, the func address should be one instruction before. */ + if (!IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) + return fentry_ip - AARCH64_INSN_SIZE; + + /* We want to be extra safe in case entry ip is on the page edge, + * but otherwise we need to avoid get_kernel_nofault()'s overhead. + */ + if ((fentry_ip & ~PAGE_MASK) < AARCH64_INSN_SIZE * 2) { + if (get_kernel_nofault(insn, (u32 *)(fentry_ip - AARCH64_INSN_SIZE * 2))) + return 0; + } else { + insn = *(u32 *)(fentry_ip - AARCH64_INSN_SIZE * 2); + } + + if (aarch64_insn_is_bti(le32_to_cpu((__le32)insn))) + return fentry_ip - AARCH64_INSN_SIZE * 2; + + return fentry_ip - AARCH64_INSN_SIZE; +} + /* * Replace a single instruction, which may be a branch or NOP. * If @validate == true, a replaced instruction is checked against 'old'. @@ -481,7 +544,20 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { - prepare_ftrace_return(ip, &arch_ftrace_regs(fregs)->lr, arch_ftrace_regs(fregs)->fp); + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long frame_pointer = arch_ftrace_regs(fregs)->fp; + unsigned long *parent = &arch_ftrace_regs(fregs)->lr; + unsigned long old; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + old = *parent; + + if (!function_graph_enter_regs(old, ip, frame_pointer, + (void *)frame_pointer, fregs)) { + *parent = return_hooker; + } } #else /* diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S index 65f76064c86b..ae990da1eae5 100644 --- a/arch/arm64/kernel/hyp-stub.S +++ b/arch/arm64/kernel/hyp-stub.S @@ -114,8 +114,8 @@ SYM_CODE_START_LOCAL(__finalise_el2) // Use EL2 translations for SPE & TRBE and disable access from EL1 mrs x0, mdcr_el2 - bic x0, x0, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT) - bic x0, x0, #(MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT) + bic x0, x0, #MDCR_EL2_E2PB_MASK + bic x0, x0, #MDCR_EL2_E2TB_MASK msr mdcr_el2, x0 // Transfer the MM state from EL1 to EL2 diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index 82e2203d86a3..6f121a0164a4 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -207,37 +207,6 @@ void machine_kexec(struct kimage *kimage) BUG(); /* Should never get here. */ } -static void machine_kexec_mask_interrupts(void) -{ - unsigned int i; - struct irq_desc *desc; - - for_each_irq_desc(i, desc) { - struct irq_chip *chip; - int ret; - - chip = irq_desc_get_chip(desc); - if (!chip) - continue; - - /* - * First try to remove the active state. If this - * fails, try to EOI the interrupt. - */ - ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false); - - if (ret && irqd_irq_inprogress(&desc->irq_data) && - chip->irq_eoi) - chip->irq_eoi(&desc->irq_data); - - if (chip->irq_mask) - chip->irq_mask(&desc->irq_data); - - if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data)) - chip->irq_disable(&desc->irq_data); - } -} - /** * machine_crash_shutdown - shutdown non-crashing cpus and save registers */ diff --git a/arch/arm64/kernel/pi/idreg-override.c b/arch/arm64/kernel/pi/idreg-override.c index 22159251eb3a..c6b185b885f7 100644 --- a/arch/arm64/kernel/pi/idreg-override.c +++ b/arch/arm64/kernel/pi/idreg-override.c @@ -83,6 +83,15 @@ static bool __init mmfr2_varange_filter(u64 val) id_aa64mmfr0_override.val |= (ID_AA64MMFR0_EL1_TGRAN_LPA2 - 1) << ID_AA64MMFR0_EL1_TGRAN_SHIFT; id_aa64mmfr0_override.mask |= 0xfU << ID_AA64MMFR0_EL1_TGRAN_SHIFT; + + /* + * Override PARange to 48 bits - the override will just be + * ignored if the actual PARange is smaller, but this is + * unlikely to be the case for LPA2 capable silicon. + */ + id_aa64mmfr0_override.val |= + ID_AA64MMFR0_EL1_PARANGE_48 << ID_AA64MMFR0_EL1_PARANGE_SHIFT; + id_aa64mmfr0_override.mask |= 0xfU << ID_AA64MMFR0_EL1_PARANGE_SHIFT; } #endif return true; diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c index f374a3e5a5fe..e57b043f324b 100644 --- a/arch/arm64/kernel/pi/map_kernel.c +++ b/arch/arm64/kernel/pi/map_kernel.c @@ -136,6 +136,12 @@ static void noinline __section(".idmap.text") set_ttbr0_for_lpa2(u64 ttbr) { u64 sctlr = read_sysreg(sctlr_el1); u64 tcr = read_sysreg(tcr_el1) | TCR_DS; + u64 mmfr0 = read_sysreg(id_aa64mmfr0_el1); + u64 parange = cpuid_feature_extract_unsigned_field(mmfr0, + ID_AA64MMFR0_EL1_PARANGE_SHIFT); + + tcr &= ~TCR_IPS_MASK; + tcr |= parange << TCR_IPS_SHIFT; asm(" msr sctlr_el1, %0 ;" " isb ;" diff --git a/arch/arm64/kernel/rsi.c b/arch/arm64/kernel/rsi.c index 3031f25c32ef..ce4778141ec7 100644 --- a/arch/arm64/kernel/rsi.c +++ b/arch/arm64/kernel/rsi.c @@ -8,6 +8,7 @@ #include <linux/psci.h> #include <linux/swiotlb.h> #include <linux/cc_platform.h> +#include <linux/platform_device.h> #include <asm/io.h> #include <asm/mem_encrypt.h> @@ -140,3 +141,17 @@ void __init arm64_rsi_init(void) static_branch_enable(&rsi_present); } +static struct platform_device rsi_dev = { + .name = RSI_PDEV_NAME, + .id = PLATFORM_DEVID_NONE +}; + +static int __init arm64_create_dummy_rsi_dev(void) +{ + if (is_realm_world() && + platform_device_register(&rsi_dev)) + pr_err("failed to register rsi platform device\n"); + return 0; +} + +arch_initcall(arm64_create_dummy_rsi_dev) diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 14ac6fdb872b..99ea26d400ff 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -36,15 +36,8 @@ #include <asm/traps.h> #include <asm/vdso.h> -#ifdef CONFIG_ARM64_GCS #define GCS_SIGNAL_CAP(addr) (((unsigned long)addr) & GCS_CAP_ADDR_MASK) -static bool gcs_signal_cap_valid(u64 addr, u64 val) -{ - return val == GCS_SIGNAL_CAP(addr); -} -#endif - /* * Do a signal return; undo the signal stack. These are aligned to 128-bit. */ @@ -1062,8 +1055,7 @@ static int restore_sigframe(struct pt_regs *regs, #ifdef CONFIG_ARM64_GCS static int gcs_restore_signal(void) { - unsigned long __user *gcspr_el0; - u64 cap; + u64 gcspr_el0, cap; int ret; if (!system_supports_gcs()) @@ -1072,7 +1064,7 @@ static int gcs_restore_signal(void) if (!(current->thread.gcs_el0_mode & PR_SHADOW_STACK_ENABLE)) return 0; - gcspr_el0 = (unsigned long __user *)read_sysreg_s(SYS_GCSPR_EL0); + gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0); /* * Ensure that any changes to the GCS done via GCS operations @@ -1087,22 +1079,23 @@ static int gcs_restore_signal(void) * then faults will be generated on GCS operations - the main * concern is to protect GCS pages. */ - ret = copy_from_user(&cap, gcspr_el0, sizeof(cap)); + ret = copy_from_user(&cap, (unsigned long __user *)gcspr_el0, + sizeof(cap)); if (ret) return -EFAULT; /* * Check that the cap is the actual GCS before replacing it. */ - if (!gcs_signal_cap_valid((u64)gcspr_el0, cap)) + if (cap != GCS_SIGNAL_CAP(gcspr_el0)) return -EINVAL; /* Invalidate the token to prevent reuse */ - put_user_gcs(0, (__user void*)gcspr_el0, &ret); + put_user_gcs(0, (unsigned long __user *)gcspr_el0, &ret); if (ret != 0) return -EFAULT; - write_sysreg_s(gcspr_el0 + 1, SYS_GCSPR_EL0); + write_sysreg_s(gcspr_el0 + 8, SYS_GCSPR_EL0); return 0; } @@ -1421,7 +1414,7 @@ static int get_sigframe(struct rt_sigframe_user_layout *user, static int gcs_signal_entry(__sigrestore_t sigtramp, struct ksignal *ksig) { - unsigned long __user *gcspr_el0; + u64 gcspr_el0; int ret = 0; if (!system_supports_gcs()) @@ -1434,18 +1427,20 @@ static int gcs_signal_entry(__sigrestore_t sigtramp, struct ksignal *ksig) * We are entering a signal handler, current register state is * active. */ - gcspr_el0 = (unsigned long __user *)read_sysreg_s(SYS_GCSPR_EL0); + gcspr_el0 = read_sysreg_s(SYS_GCSPR_EL0); /* * Push a cap and the GCS entry for the trampoline onto the GCS. */ - put_user_gcs((unsigned long)sigtramp, gcspr_el0 - 2, &ret); - put_user_gcs(GCS_SIGNAL_CAP(gcspr_el0 - 1), gcspr_el0 - 1, &ret); + put_user_gcs((unsigned long)sigtramp, + (unsigned long __user *)(gcspr_el0 - 16), &ret); + put_user_gcs(GCS_SIGNAL_CAP(gcspr_el0 - 8), + (unsigned long __user *)(gcspr_el0 - 8), &ret); if (ret != 0) return ret; - gcspr_el0 -= 2; - write_sysreg_s((unsigned long)gcspr_el0, SYS_GCSPR_EL0); + gcspr_el0 -= 16; + write_sysreg_s(gcspr_el0, SYS_GCSPR_EL0); return 0; } @@ -1462,10 +1457,33 @@ static int setup_return(struct pt_regs *regs, struct ksignal *ksig, struct rt_sigframe_user_layout *user, int usig) { __sigrestore_t sigtramp; + int err; + + if (ksig->ka.sa.sa_flags & SA_RESTORER) + sigtramp = ksig->ka.sa.sa_restorer; + else + sigtramp = VDSO_SYMBOL(current->mm->context.vdso, sigtramp); + + err = gcs_signal_entry(sigtramp, ksig); + if (err) + return err; + + /* + * We must not fail from this point onwards. We are going to update + * registers, including SP, in order to invoke the signal handler. If + * we failed and attempted to deliver a nested SIGSEGV to a handler + * after that point, the subsequent sigreturn would end up restoring + * the (partial) state for the original signal handler. + */ regs->regs[0] = usig; + if (ksig->ka.sa.sa_flags & SA_SIGINFO) { + regs->regs[1] = (unsigned long)&user->sigframe->info; + regs->regs[2] = (unsigned long)&user->sigframe->uc; + } regs->sp = (unsigned long)user->sigframe; regs->regs[29] = (unsigned long)&user->next_frame->fp; + regs->regs[30] = (unsigned long)sigtramp; regs->pc = (unsigned long)ksig->ka.sa.sa_handler; /* @@ -1506,14 +1524,7 @@ static int setup_return(struct pt_regs *regs, struct ksignal *ksig, sme_smstop(); } - if (ksig->ka.sa.sa_flags & SA_RESTORER) - sigtramp = ksig->ka.sa.sa_restorer; - else - sigtramp = VDSO_SYMBOL(current->mm->context.vdso, sigtramp); - - regs->regs[30] = (unsigned long)sigtramp; - - return gcs_signal_entry(sigtramp, ksig); + return 0; } static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, @@ -1537,14 +1548,16 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, err |= __save_altstack(&frame->uc.uc_stack, regs->sp); err |= setup_sigframe(&user, regs, set, &ua_state); - if (err == 0) { + if (ksig->ka.sa.sa_flags & SA_SIGINFO) + err |= copy_siginfo_to_user(&frame->info, &ksig->info); + + if (err == 0) err = setup_return(regs, ksig, &user, usig); - if (ksig->ka.sa.sa_flags & SA_SIGINFO) { - err |= copy_siginfo_to_user(&frame->info, &ksig->info); - regs->regs[1] = (unsigned long)&frame->info; - regs->regs[2] = (unsigned long)&frame->uc; - } - } + + /* + * We must not fail if setup_return() succeeded - see comment at the + * beginning of setup_return(). + */ if (err == 0) set_handler_user_access_state(); diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index caef85462acb..1d9d51d7627f 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -26,7 +26,6 @@ enum kunwind_source { KUNWIND_SOURCE_CALLER, KUNWIND_SOURCE_TASK, KUNWIND_SOURCE_REGS_PC, - KUNWIND_SOURCE_REGS_LR, }; union unwind_flags { @@ -138,8 +137,10 @@ kunwind_recover_return_address(struct kunwind_state *state) orig_pc = ftrace_graph_ret_addr(state->task, &state->graph_idx, state->common.pc, (void *)state->common.fp); - if (WARN_ON_ONCE(state->common.pc == orig_pc)) + if (state->common.pc == orig_pc) { + WARN_ON_ONCE(state->task == current); return -EINVAL; + } state->common.pc = orig_pc; state->flags.fgraph = 1; } @@ -178,23 +179,8 @@ int kunwind_next_regs_pc(struct kunwind_state *state) state->regs = regs; state->common.pc = regs->pc; state->common.fp = regs->regs[29]; - state->source = KUNWIND_SOURCE_REGS_PC; - return 0; -} - -static __always_inline int -kunwind_next_regs_lr(struct kunwind_state *state) -{ - /* - * The stack for the regs was consumed by kunwind_next_regs_pc(), so we - * cannot consume that again here, but we know the regs are safe to - * access. - */ - state->common.pc = state->regs->regs[30]; - state->common.fp = state->regs->regs[29]; state->regs = NULL; - state->source = KUNWIND_SOURCE_REGS_LR; - + state->source = KUNWIND_SOURCE_REGS_PC; return 0; } @@ -215,12 +201,12 @@ kunwind_next_frame_record_meta(struct kunwind_state *state) case FRAME_META_TYPE_FINAL: if (meta == &task_pt_regs(tsk)->stackframe) return -ENOENT; - WARN_ON_ONCE(1); + WARN_ON_ONCE(tsk == current); return -EINVAL; case FRAME_META_TYPE_PT_REGS: return kunwind_next_regs_pc(state); default: - WARN_ON_ONCE(1); + WARN_ON_ONCE(tsk == current); return -EINVAL; } } @@ -274,11 +260,8 @@ kunwind_next(struct kunwind_state *state) case KUNWIND_SOURCE_FRAME: case KUNWIND_SOURCE_CALLER: case KUNWIND_SOURCE_TASK: - case KUNWIND_SOURCE_REGS_LR: - err = kunwind_next_frame_record(state); - break; case KUNWIND_SOURCE_REGS_PC: - err = kunwind_next_regs_lr(state); + err = kunwind_next_frame_record(state); break; default: err = -EINVAL; @@ -436,7 +419,6 @@ static const char *state_source_string(const struct kunwind_state *state) case KUNWIND_SOURCE_CALLER: return "C"; case KUNWIND_SOURCE_TASK: return "T"; case KUNWIND_SOURCE_REGS_PC: return "P"; - case KUNWIND_SOURCE_REGS_LR: return "L"; default: return "U"; } } diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index a102c3aebdbc..7b2735ad32e9 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1990,8 +1990,7 @@ static int kvm_init_vector_slots(void) static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits) { struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu); - u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); - unsigned long tcr; + unsigned long tcr, ips; /* * Calculate the raw per-cpu offset without a translation from the @@ -2005,6 +2004,7 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits) params->mair_el2 = read_sysreg(mair_el1); tcr = read_sysreg(tcr_el1); + ips = FIELD_GET(TCR_IPS_MASK, tcr); if (cpus_have_final_cap(ARM64_KVM_HVHE)) { tcr |= TCR_EPD1_MASK; } else { @@ -2014,8 +2014,8 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits) tcr &= ~TCR_T0SZ_MASK; tcr |= TCR_T0SZ(hyp_va_bits); tcr &= ~TCR_EL2_PS_MASK; - tcr |= FIELD_PREP(TCR_EL2_PS_MASK, kvm_get_parange(mmfr0)); - if (kvm_lpa2_is_enabled()) + tcr |= FIELD_PREP(TCR_EL2_PS_MASK, ips); + if (lpa2_is_enabled()) tcr |= TCR_EL2_DS; params->tcr_el2 = tcr; diff --git a/arch/arm64/kvm/at.c b/arch/arm64/kvm/at.c index 8c5d7990e5b3..3a96c96816e9 100644 --- a/arch/arm64/kvm/at.c +++ b/arch/arm64/kvm/at.c @@ -111,7 +111,7 @@ static bool s1pie_enabled(struct kvm_vcpu *vcpu, enum trans_regime regime) return vcpu_read_sys_reg(vcpu, TCR2_EL2) & TCR2_EL2_PIE; case TR_EL10: return (__vcpu_sys_reg(vcpu, HCRX_EL2) & HCRX_EL2_TCR2En) && - (__vcpu_sys_reg(vcpu, TCR2_EL1) & TCR2_EL1x_PIE); + (__vcpu_sys_reg(vcpu, TCR2_EL1) & TCR2_EL1_PIE); default: BUG(); } @@ -140,8 +140,8 @@ static void compute_s1poe(struct kvm_vcpu *vcpu, struct s1_walk_info *wi) } val = __vcpu_sys_reg(vcpu, TCR2_EL1); - wi->poe = val & TCR2_EL1x_POE; - wi->e0poe = val & TCR2_EL1x_E0POE; + wi->poe = val & TCR2_EL1_POE; + wi->e0poe = val & TCR2_EL1_E0POE; } } @@ -739,8 +739,15 @@ static u64 compute_par_s12(struct kvm_vcpu *vcpu, u64 s1_par, final_attr = s1_parattr; break; default: - /* MemAttr[2]=0, Device from S2 */ - final_attr = s2_memattr & GENMASK(1,0) << 2; + /* + * MemAttr[2]=0, Device from S2. + * + * FWB does not influence the way that stage 1 + * memory types and attributes are combined + * with stage 2 Device type and attributes. + */ + final_attr = min(s2_memattr_to_attr(s2_memattr), + s1_parattr); } } else { /* Combination of R_HMNDG, R_TNHFM and R_GQFSF */ diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c index 1ffbfd1c3cf2..f1b7287e1f3c 100644 --- a/arch/arm64/kvm/emulate-nested.c +++ b/arch/arm64/kvm/emulate-nested.c @@ -494,7 +494,7 @@ static enum trap_behaviour check_cptr_tta(struct kvm_vcpu *vcpu) if (!vcpu_el2_e2h_is_set(vcpu)) val = translate_cptr_el2_to_cpacr_el1(val); - if (val & CPACR_ELx_TTA) + if (val & CPACR_EL1_TTA) return BEHAVE_FORWARD_RW; return BEHAVE_HANDLE_LOCALLY; diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index ea5484ce1f3b..98718bd65bf1 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -169,7 +169,7 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) if (has_vhe() && system_supports_sme()) { /* Also restore EL0 state seen on entry */ if (vcpu_get_flag(vcpu, HOST_SME_ENABLED)) - sysreg_clear_set(CPACR_EL1, 0, CPACR_ELx_SMEN); + sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_SMEN); else sysreg_clear_set(CPACR_EL1, CPACR_EL1_SMEN_EL0EN, diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 34f53707892d..abfa6ad92e91 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -419,9 +419,9 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) /* First disable enough traps to allow us to update the registers */ if (sve_guest || (is_protected_kvm_enabled() && system_supports_sve())) - cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN); + cpacr_clear_set(0, CPACR_EL1_FPEN | CPACR_EL1_ZEN); else - cpacr_clear_set(0, CPACR_ELx_FPEN); + cpacr_clear_set(0, CPACR_EL1_FPEN); isb(); /* Write out the host state if it's in the registers */ diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 6aa0b13d86e5..6c90ef6736d6 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -68,7 +68,7 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu) if (!guest_owns_fp_regs()) return; - cpacr_clear_set(0, CPACR_ELx_FPEN | CPACR_ELx_ZEN); + cpacr_clear_set(0, CPACR_EL1_FPEN | CPACR_EL1_ZEN); isb(); if (vcpu_has_sve(vcpu)) @@ -481,7 +481,7 @@ void handle_trap(struct kvm_cpu_context *host_ctxt) handle_host_smc(host_ctxt); break; case ESR_ELx_EC_SVE: - cpacr_clear_set(0, CPACR_ELx_ZEN); + cpacr_clear_set(0, CPACR_EL1_ZEN); isb(); sve_cond_update_zcr_vq(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, SYS_ZCR_EL2); diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index caba3e4bd09e..e75374d682f4 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -783,9 +783,6 @@ static int hyp_ack_unshare(u64 addr, const struct pkvm_mem_transition *tx) if (tx->initiator.id == PKVM_ID_HOST && hyp_page_count((void *)addr)) return -EBUSY; - if (__hyp_ack_skip_pgtable_check(tx)) - return 0; - return __hyp_check_page_state_range(addr, size, PKVM_PAGE_SHARED_BORROWED); } diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 01616c39a810..73e319891327 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -68,7 +68,7 @@ static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu) /* Trap SVE */ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_SVE), feature_ids)) { if (has_hvhe()) - cptr_clear |= CPACR_ELx_ZEN; + cptr_clear |= CPACR_EL1_ZEN; else cptr_set |= CPTR_EL2_TZ; } @@ -126,7 +126,7 @@ static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu) /* Trap SPE */ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMSVer), feature_ids)) { mdcr_set |= MDCR_EL2_TPMS; - mdcr_clear |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT; + mdcr_clear |= MDCR_EL2_E2PB_MASK; } /* Trap Trace Filter */ @@ -143,7 +143,7 @@ static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu) /* Trap External Trace */ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_ExtTrcBuff), feature_ids)) - mdcr_clear |= MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT; + mdcr_clear |= MDCR_EL2_E2TB_MASK; vcpu->arch.mdcr_el2 |= mdcr_set; vcpu->arch.mdcr_el2 &= ~mdcr_clear; diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index cc69106734ca..0f6b01b3da5c 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -48,14 +48,14 @@ static void __activate_traps(struct kvm_vcpu *vcpu) val |= has_hvhe() ? CPACR_EL1_TTA : CPTR_EL2_TTA; if (cpus_have_final_cap(ARM64_SME)) { if (has_hvhe()) - val &= ~CPACR_ELx_SMEN; + val &= ~CPACR_EL1_SMEN; else val |= CPTR_EL2_TSM; } if (!guest_owns_fp_regs()) { if (has_hvhe()) - val &= ~(CPACR_ELx_FPEN | CPACR_ELx_ZEN); + val &= ~(CPACR_EL1_FPEN | CPACR_EL1_ZEN); else val |= CPTR_EL2_TFP | CPTR_EL2_TZ; @@ -192,7 +192,7 @@ static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) /* Re-enable SVE traps if not supported for the guest vcpu. */ if (!vcpu_has_sve(vcpu)) - cpacr_clear_set(CPACR_ELx_ZEN, 0); + cpacr_clear_set(CPACR_EL1_ZEN, 0); } else { __fpsimd_save_state(*host_data_ptr(fpsimd_state)); diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index 40bd55966540..d2b6fa051d6b 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -35,14 +35,6 @@ static bool kvm_pgtable_walk_skip_cmo(const struct kvm_pgtable_visit_ctx *ctx) return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_CMO); } -static bool kvm_phys_is_valid(u64 phys) -{ - u64 parange_max = kvm_get_parange_max(); - u8 shift = id_aa64mmfr0_parange_to_phys_shift(parange_max); - - return phys < BIT(shift); -} - static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx, u64 phys) { u64 granule = kvm_granule_size(ctx->level); @@ -53,7 +45,7 @@ static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx, if (granule > (ctx->end - ctx->addr)) return false; - if (kvm_phys_is_valid(phys) && !IS_ALIGNED(phys, granule)) + if (!IS_ALIGNED(phys, granule)) return false; return IS_ALIGNED(ctx->addr, granule); @@ -587,6 +579,9 @@ struct stage2_map_data { /* Force mappings to page granularity */ bool force_pte; + + /* Walk should update owner_id only */ + bool annotation; }; u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift) @@ -885,18 +880,7 @@ static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx, { u64 phys = data->phys; - /* - * Stage-2 walks to update ownership data are communicated to the map - * walker using an invalid PA. Avoid offsetting an already invalid PA, - * which could overflow and make the address valid again. - */ - if (!kvm_phys_is_valid(phys)) - return phys; - - /* - * Otherwise, work out the correct PA based on how far the walk has - * gotten. - */ + /* Work out the correct PA based on how far the walk has gotten */ return phys + (ctx->addr - ctx->start); } @@ -908,6 +892,9 @@ static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx, if (data->force_pte && ctx->level < KVM_PGTABLE_LAST_LEVEL) return false; + if (data->annotation) + return true; + return kvm_block_mapping_supported(ctx, phys); } @@ -923,7 +910,7 @@ static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, if (!stage2_leaf_mapping_allowed(ctx, data)) return -E2BIG; - if (kvm_phys_is_valid(phys)) + if (!data->annotation) new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); else new = kvm_init_invalid_leaf_owner(data->owner_id); @@ -1085,11 +1072,11 @@ int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size, { int ret; struct stage2_map_data map_data = { - .phys = KVM_PHYS_INVALID, .mmu = pgt->mmu, .memcache = mc, .owner_id = owner_id, .force_pte = true, + .annotation = true, }; struct kvm_pgtable_walker walker = { .cb = stage2_map_walker, diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 80581b1c3995..59d992455793 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -77,12 +77,12 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM * shift value for trapping the AMU accesses. */ - u64 val = CPACR_ELx_TTA | CPTR_EL2_TAM; + u64 val = CPACR_EL1_TTA | CPTR_EL2_TAM; if (guest_owns_fp_regs()) { - val |= CPACR_ELx_FPEN; + val |= CPACR_EL1_FPEN; if (vcpu_has_sve(vcpu)) - val |= CPACR_ELx_ZEN; + val |= CPACR_EL1_ZEN; } else { __activate_traps_fpsimd32(vcpu); } @@ -122,13 +122,13 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) * hypervisor has traps enabled to dispel any illusion of something more * complicated taking place. */ - if (!(SYS_FIELD_GET(CPACR_ELx, FPEN, cptr) & BIT(0))) - val &= ~CPACR_ELx_FPEN; - if (!(SYS_FIELD_GET(CPACR_ELx, ZEN, cptr) & BIT(0))) - val &= ~CPACR_ELx_ZEN; + if (!(SYS_FIELD_GET(CPACR_EL1, FPEN, cptr) & BIT(0))) + val &= ~CPACR_EL1_FPEN; + if (!(SYS_FIELD_GET(CPACR_EL1, ZEN, cptr) & BIT(0))) + val &= ~CPACR_EL1_ZEN; if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, S2POE, IMP)) - val |= cptr & CPACR_ELx_E0POE; + val |= cptr & CPACR_EL1_E0POE; val |= cptr & CPTR_EL2_TCPAC; diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index 456102bc0b55..6c5950b9ceac 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -24,6 +24,7 @@ static DEFINE_MUTEX(arm_pmus_lock); static void kvm_pmu_create_perf_event(struct kvm_pmc *pmc); static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc); +static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc); static struct kvm_vcpu *kvm_pmc_to_vcpu(const struct kvm_pmc *pmc) { @@ -327,48 +328,25 @@ u64 kvm_pmu_implemented_counter_mask(struct kvm_vcpu *vcpu) return GENMASK(val - 1, 0) | BIT(ARMV8_PMU_CYCLE_IDX); } -/** - * kvm_pmu_enable_counter_mask - enable selected PMU counters - * @vcpu: The vcpu pointer - * @val: the value guest writes to PMCNTENSET register - * - * Call perf_event_enable to start counting the perf event - */ -void kvm_pmu_enable_counter_mask(struct kvm_vcpu *vcpu, u64 val) +static void kvm_pmc_enable_perf_event(struct kvm_pmc *pmc) { - int i; - if (!kvm_vcpu_has_pmu(vcpu)) - return; - - if (!(kvm_vcpu_read_pmcr(vcpu) & ARMV8_PMU_PMCR_E) || !val) + if (!pmc->perf_event) { + kvm_pmu_create_perf_event(pmc); return; + } - for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { - struct kvm_pmc *pmc; - - if (!(val & BIT(i))) - continue; - - pmc = kvm_vcpu_idx_to_pmc(vcpu, i); + perf_event_enable(pmc->perf_event); + if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE) + kvm_debug("fail to enable perf event\n"); +} - if (!pmc->perf_event) { - kvm_pmu_create_perf_event(pmc); - } else { - perf_event_enable(pmc->perf_event); - if (pmc->perf_event->state != PERF_EVENT_STATE_ACTIVE) - kvm_debug("fail to enable perf event\n"); - } - } +static void kvm_pmc_disable_perf_event(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) + perf_event_disable(pmc->perf_event); } -/** - * kvm_pmu_disable_counter_mask - disable selected PMU counters - * @vcpu: The vcpu pointer - * @val: the value guest writes to PMCNTENCLR register - * - * Call perf_event_disable to stop counting the perf event - */ -void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) +void kvm_pmu_reprogram_counter_mask(struct kvm_vcpu *vcpu, u64 val) { int i; @@ -376,16 +354,18 @@ void kvm_pmu_disable_counter_mask(struct kvm_vcpu *vcpu, u64 val) return; for (i = 0; i < KVM_ARMV8_PMU_MAX_COUNTERS; i++) { - struct kvm_pmc *pmc; + struct kvm_pmc *pmc = kvm_vcpu_idx_to_pmc(vcpu, i); if (!(val & BIT(i))) continue; - pmc = kvm_vcpu_idx_to_pmc(vcpu, i); - - if (pmc->perf_event) - perf_event_disable(pmc->perf_event); + if (kvm_pmu_counter_is_enabled(pmc)) + kvm_pmc_enable_perf_event(pmc); + else + kvm_pmc_disable_perf_event(pmc); } + + kvm_vcpu_pmu_restore_guest(vcpu); } /* @@ -626,27 +606,28 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val) if (!kvm_has_feat(vcpu->kvm, ID_AA64DFR0_EL1, PMUVer, V3P5)) val &= ~ARMV8_PMU_PMCR_LP; + /* Request a reload of the PMU to enable/disable affected counters */ + if ((__vcpu_sys_reg(vcpu, PMCR_EL0) ^ val) & ARMV8_PMU_PMCR_E) + kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); + /* The reset bits don't indicate any state, and shouldn't be saved. */ __vcpu_sys_reg(vcpu, PMCR_EL0) = val & ~(ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_P); - if (val & ARMV8_PMU_PMCR_E) { - kvm_pmu_enable_counter_mask(vcpu, - __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); - } else { - kvm_pmu_disable_counter_mask(vcpu, - __vcpu_sys_reg(vcpu, PMCNTENSET_EL0)); - } - if (val & ARMV8_PMU_PMCR_C) kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0); if (val & ARMV8_PMU_PMCR_P) { - unsigned long mask = kvm_pmu_accessible_counter_mask(vcpu); - mask &= ~BIT(ARMV8_PMU_CYCLE_IDX); + /* + * Unlike other PMU sysregs, the controls in PMCR_EL0 always apply + * to the 'guest' range of counters and never the 'hyp' range. + */ + unsigned long mask = kvm_pmu_implemented_counter_mask(vcpu) & + ~kvm_pmu_hyp_counter_mask(vcpu) & + ~BIT(ARMV8_PMU_CYCLE_IDX); + for_each_set_bit(i, &mask, 32) kvm_pmu_set_pmc_value(kvm_vcpu_idx_to_pmc(vcpu, i), 0, true); } - kvm_vcpu_pmu_restore_guest(vcpu); } static bool kvm_pmu_counter_is_enabled(struct kvm_pmc *pmc) @@ -910,11 +891,11 @@ void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu) { u64 mask = kvm_pmu_implemented_counter_mask(vcpu); - kvm_pmu_handle_pmcr(vcpu, kvm_vcpu_read_pmcr(vcpu)); - __vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= mask; __vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= mask; __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= mask; + + kvm_pmu_reprogram_counter_mask(vcpu, mask); } int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 83c6b4a07ef5..e4749ecbcd79 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1208,16 +1208,14 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p, mask = kvm_pmu_accessible_counter_mask(vcpu); if (p->is_write) { val = p->regval & mask; - if (r->Op2 & 0x1) { + if (r->Op2 & 0x1) /* accessing PMCNTENSET_EL0 */ __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val; - kvm_pmu_enable_counter_mask(vcpu, val); - kvm_vcpu_pmu_restore_guest(vcpu); - } else { + else /* accessing PMCNTENCLR_EL0 */ __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val; - kvm_pmu_disable_counter_mask(vcpu, val); - } + + kvm_pmu_reprogram_counter_mask(vcpu, val); } else { p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0); } @@ -1604,6 +1602,9 @@ static u64 __kvm_read_sanitised_id_reg(const struct kvm_vcpu *vcpu, if (!cpus_have_final_cap(ARM64_HAS_WFXT)) val &= ~ARM64_FEATURE_MASK(ID_AA64ISAR2_EL1_WFxT); break; + case SYS_ID_AA64ISAR3_EL1: + val &= ID_AA64ISAR3_EL1_FPRCVT | ID_AA64ISAR3_EL1_FAMINMAX; + break; case SYS_ID_AA64MMFR2_EL1: val &= ~ID_AA64MMFR2_EL1_CCIDX_MASK; break; @@ -2450,6 +2451,26 @@ static unsigned int s1pie_el2_visibility(const struct kvm_vcpu *vcpu, return __el2_visibility(vcpu, rd, s1pie_visibility); } +static bool access_mdcr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + u64 old = __vcpu_sys_reg(vcpu, MDCR_EL2); + + if (!access_rw(vcpu, p, r)) + return false; + + /* + * Request a reload of the PMU to enable/disable the counters affected + * by HPME. + */ + if ((old ^ __vcpu_sys_reg(vcpu, MDCR_EL2)) & MDCR_EL2_HPME) + kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu); + + return true; +} + + /* * Architected system registers. * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 @@ -2608,7 +2629,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_WRITABLE(ID_AA64ISAR2_EL1, ~(ID_AA64ISAR2_EL1_RES0 | ID_AA64ISAR2_EL1_APA3 | ID_AA64ISAR2_EL1_GPA3)), - ID_UNALLOCATED(6,3), + ID_WRITABLE(ID_AA64ISAR3_EL1, (ID_AA64ISAR3_EL1_FPRCVT | + ID_AA64ISAR3_EL1_FAMINMAX)), ID_UNALLOCATED(6,4), ID_UNALLOCATED(6,5), ID_UNALLOCATED(6,6), @@ -2618,7 +2640,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { ID_WRITABLE(ID_AA64MMFR0_EL1, ~(ID_AA64MMFR0_EL1_RES0 | ID_AA64MMFR0_EL1_TGRAN4_2 | ID_AA64MMFR0_EL1_TGRAN64_2 | - ID_AA64MMFR0_EL1_TGRAN16_2)), + ID_AA64MMFR0_EL1_TGRAN16_2 | + ID_AA64MMFR0_EL1_ASIDBITS)), ID_WRITABLE(ID_AA64MMFR1_EL1, ~(ID_AA64MMFR1_EL1_RES0 | ID_AA64MMFR1_EL1_HCX | ID_AA64MMFR1_EL1_TWED | @@ -2982,7 +3005,7 @@ static const struct sys_reg_desc sys_reg_descs[] = { EL2_REG(SCTLR_EL2, access_rw, reset_val, SCTLR_EL2_RES1), EL2_REG(ACTLR_EL2, access_rw, reset_val, 0), EL2_REG_VNCR(HCR_EL2, reset_hcr, 0), - EL2_REG(MDCR_EL2, access_rw, reset_val, 0), + EL2_REG(MDCR_EL2, access_mdcr, reset_val, 0), EL2_REG(CPTR_EL2, access_rw, reset_val, CPTR_NVHE_EL2_RES1), EL2_REG_VNCR(HSTR_EL2, reset_val, 0), EL2_REG_VNCR(HFGRTR_EL2, reset_val, 0), diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index f4c4494645c3..fb96802799c6 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -608,12 +608,22 @@ static void vgic_its_cache_translation(struct kvm *kvm, struct vgic_its *its, lockdep_assert_held(&its->its_lock); vgic_get_irq_kref(irq); + old = xa_store(&its->translation_cache, cache_key, irq, GFP_KERNEL_ACCOUNT); + + /* + * Put the reference taken on @irq if the store fails. Intentionally do + * not return the error as the translation cache is best effort. + */ + if (xa_is_err(old)) { + vgic_put_irq(kvm, irq); + return; + } + /* * We could have raced with another CPU caching the same * translation behind our back, ensure we don't leak a * reference if that is the case. */ - old = xa_store(&its->translation_cache, cache_key, irq, GFP_KERNEL_ACCOUNT); if (old) vgic_put_irq(kvm, old); } diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 3215adf48a1b..98a2a0e64e25 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -519,6 +519,18 @@ pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, static int __init hugetlbpage_init(void) { + /* + * HugeTLB pages are supported on maximum four page table + * levels (PUD, CONT PMD, PMD, CONT PTE) for a given base + * page size, corresponding to hugetlb_add_hstate() calls + * here. + * + * HUGE_MAX_HSTATE should at least match maximum supported + * HugeTLB page sizes on the platform. Any new addition to + * supported HugeTLB page sizes will also require changing + * HUGE_MAX_HSTATE as well. + */ + BUILD_BUG_ON(HUGE_MAX_HSTATE < 4); if (pud_sect_supported()) hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index ccdef53872a0..9c0b8d9558fc 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -279,7 +279,12 @@ void __init arm64_memblock_init(void) if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { extern u16 memstart_offset_seed; - u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1); + + /* + * Use the sanitised version of id_aa64mmfr0_el1 so that linear + * map randomization can be enabled by shrinking the IPA space. + */ + u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); int parange = cpuid_feature_extract_unsigned_field( mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT); s64 range = linear_region_size - diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index e2739b69e11b..b4df5bc5b1b8 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1169,7 +1169,8 @@ int __meminit vmemmap_check_pmd(pmd_t *pmdp, int node, unsigned long addr, unsigned long next) { vmemmap_verify((pte_t *)pmdp, node, addr, next); - return 1; + + return pmd_sect(READ_ONCE(*pmdp)); } int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index b8edc5765441..fb30c8804f87 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -501,7 +501,7 @@ alternative_else_nop_endif #ifdef CONFIG_ARM64_HAFT cmp x9, ID_AA64MMFR1_EL1_HAFDBS_HAFT b.lt 1f - orr tcr2, tcr2, TCR2_EL1x_HAFT + orr tcr2, tcr2, TCR2_EL1_HAFT #endif /* CONFIG_ARM64_HAFT */ 1: #endif /* CONFIG_ARM64_HW_AFDBM */ @@ -532,7 +532,8 @@ alternative_else_nop_endif #undef PTE_MAYBE_NG #undef PTE_MAYBE_SHARED - orr tcr2, tcr2, TCR2_EL1x_PIE + orr tcr2, tcr2, TCR2_EL1_PIE + msr REG_TCR2_EL1, x0 .Lskip_indirection: diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c index 0f7b484cb2ff..19c67ed1a21f 100644 --- a/arch/arm64/mm/trans_pgd.c +++ b/arch/arm64/mm/trans_pgd.c @@ -57,7 +57,7 @@ static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr) */ BUG_ON(!pfn_valid(pte_pfn(pte))); - __set_pte(dst_ptep, pte_mkpresent(pte_mkwrite_novma(pte))); + __set_pte(dst_ptep, pte_mkvalid(pte_mkwrite_novma(pte))); } } diff --git a/arch/arm64/tools/gen-sysreg.awk b/arch/arm64/tools/gen-sysreg.awk index d1254a056114..1a2afc9fdd42 100755 --- a/arch/arm64/tools/gen-sysreg.awk +++ b/arch/arm64/tools/gen-sysreg.awk @@ -206,7 +206,7 @@ END { # Currently this is effectivey a comment, in future we may want to emit # defines for the fields. -/^Fields/ && block_current() == "Sysreg" { +(/^Fields/ || /^Mapping/) && block_current() == "Sysreg" { expect_fields(2) if (next_bit != 63) diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index b081b54d6d22..94ca9cdb0b16 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -24,8 +24,16 @@ # ... # EndEnum -# Alternatively if multiple registers share the same layout then -# a SysregFields block can be used to describe the shared layout +# For VHE aliases (*_EL12, *_EL02) of system registers, a Mapping +# entry describes the register the alias actually accesses: + +# Sysreg <name_EL12> <op0> <op1> <crn> <crm> <op2> +# Mapping <name_EL1> +# EndSysreg + +# Where multiple system regsiters are not VHE aliases but share a +# common layout, a SysregFields block can be used to describe the +# shared layout: # SysregFields <fieldsname> # <field> @@ -1010,7 +1018,12 @@ UnsignedEnum 35:32 FPMR 0b0000 NI 0b0001 IMP EndEnum -Res0 31:12 +Res0 31:20 +UnsignedEnum 19:16 UINJ + 0b0000 NI + 0b0001 IMP +EndEnum +Res0 15:12 UnsignedEnum 11:8 MTEFAR 0b0000 NI 0b0001 IMP @@ -1035,7 +1048,10 @@ UnsignedEnum 55:52 F32MM 0b0000 NI 0b0001 IMP EndEnum -Res0 51:48 +UnsignedEnum 51:48 F16MM + 0b0000 NI + 0b0001 IMP +EndEnum UnsignedEnum 47:44 I8MM 0b0000 NI 0b0001 IMP @@ -1053,6 +1069,7 @@ Res0 31:28 UnsignedEnum 27:24 B16B16 0b0000 NI 0b0001 IMP + 0b0010 BFSCALE EndEnum UnsignedEnum 23:20 BF16 0b0000 NI @@ -1063,16 +1080,22 @@ UnsignedEnum 19:16 BitPerm 0b0000 NI 0b0001 IMP EndEnum -Res0 15:8 +UnsignedEnum 15:12 EltPerm + 0b0000 NI + 0b0001 IMP +EndEnum +Res0 11:8 UnsignedEnum 7:4 AES 0b0000 NI 0b0001 IMP 0b0010 PMULL128 + 0b0011 AES2 EndEnum UnsignedEnum 3:0 SVEver 0b0000 IMP 0b0001 SVE2 0b0010 SVE2p1 + 0b0011 SVE2p2 EndEnum EndSysreg @@ -1090,7 +1113,7 @@ UnsignedEnum 59:56 SMEver 0b0000 SME 0b0001 SME2 0b0010 SME2p1 - 0b0000 IMP + 0b0011 SME2p2 EndEnum UnsignedEnum 55:52 I16I64 0b0000 NI @@ -1154,7 +1177,29 @@ UnsignedEnum 28 SF8DP2 0b0 NI 0b1 IMP EndEnum -Res0 27:0 +Res0 27:26 +UnsignedEnum 25 SBitPerm + 0b0 NI + 0b1 IMP +EndEnum +UnsignedEnum 24 AES + 0b0 NI + 0b1 IMP +EndEnum +UnsignedEnum 23 SFEXPA + 0b0 NI + 0b1 IMP +EndEnum +Res0 22:17 +UnsignedEnum 16 STMOP + 0b0 NI + 0b1 IMP +EndEnum +Res0 15:1 +UnsignedEnum 0 SMOP4 + 0b0 NI + 0b1 IMP +EndEnum EndSysreg Sysreg ID_AA64FPFR0_EL1 3 0 0 4 7 @@ -1175,7 +1220,15 @@ UnsignedEnum 28 F8DP2 0b0 NI 0b1 IMP EndEnum -Res0 27:2 +UnsignedEnum 27 F8MM8 + 0b0 NI + 0b1 IMP +EndEnum +UnsignedEnum 26 F8MM4 + 0b0 NI + 0b1 IMP +EndEnum +Res0 25:2 UnsignedEnum 1 F8E4M3 0b0 NI 0b1 IMP @@ -1503,12 +1556,16 @@ EndEnum UnsignedEnum 55:52 CSSC 0b0000 NI 0b0001 IMP + 0b0010 CMPBR EndEnum UnsignedEnum 51:48 RPRFM 0b0000 NI 0b0001 IMP EndEnum -Res0 47:44 +UnsignedEnum 47:44 PCDPHINT + 0b0000 NI + 0b0001 IMP +EndEnum UnsignedEnum 43:40 PRFMSLC 0b0000 NI 0b0001 IMP @@ -1561,7 +1618,23 @@ EndEnum EndSysreg Sysreg ID_AA64ISAR3_EL1 3 0 0 6 3 -Res0 63:16 +Res0 63:32 +UnsignedEnum 31:28 FPRCVT + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 27:24 LSUI + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 23:20 OCCMO + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 19:16 LSFE + 0b0000 NI + 0b0001 IMP +EndEnum UnsignedEnum 15:12 PACM 0b0000 NI 0b0001 TRIVIAL_IMP @@ -1978,7 +2051,7 @@ Field 1 A Field 0 M EndSysreg -SysregFields CPACR_ELx +Sysreg CPACR_EL1 3 0 1 0 2 Res0 63:30 Field 29 E0POE Field 28 TTA @@ -1989,10 +2062,6 @@ Field 21:20 FPEN Res0 19:18 Field 17:16 ZEN Res0 15:0 -EndSysregFields - -Sysreg CPACR_EL1 3 0 1 0 2 -Fields CPACR_ELx EndSysreg Sysreg SMPRI_EL1 3 0 1 2 4 @@ -2947,23 +3016,23 @@ Field 63:0 PhysicalOffset EndSysreg Sysreg CPACR_EL12 3 5 1 0 2 -Fields CPACR_ELx +Mapping CPACR_EL1 EndSysreg Sysreg ZCR_EL12 3 5 1 2 0 -Fields ZCR_ELx +Mapping ZCR_EL1 EndSysreg Sysreg SMCR_EL12 3 5 1 2 6 -Fields SMCR_ELx +Mapping SMCR_EL1 EndSysreg Sysreg GCSCR_EL12 3 5 2 5 0 -Fields GCSCR_ELx +Mapping GCSCR_EL1 EndSysreg Sysreg GCSPR_EL12 3 5 2 5 1 -Fields GCSPR_ELx +Mapping GCSPR_EL1 EndSysreg Sysreg FAR_EL12 3 5 6 0 0 @@ -2975,7 +3044,7 @@ Fields MPAM1_ELx EndSysreg Sysreg CONTEXTIDR_EL12 3 5 13 0 1 -Fields CONTEXTIDR_ELx +Mapping CONTEXTIDR_EL1 EndSysreg SysregFields TTBRx_EL1 @@ -2992,7 +3061,7 @@ Sysreg TTBR1_EL1 3 0 2 0 1 Fields TTBRx_EL1 EndSysreg -SysregFields TCR2_EL1x +Sysreg TCR2_EL1 3 0 2 0 3 Res0 63:16 Field 15 DisCH1 Field 14 DisCH0 @@ -3006,14 +3075,10 @@ Field 3 POE Field 2 E0POE Field 1 PIE Field 0 PnCH -EndSysregFields - -Sysreg TCR2_EL1 3 0 2 0 3 -Fields TCR2_EL1x EndSysreg Sysreg TCR2_EL12 3 5 2 0 3 -Fields TCR2_EL1x +Mapping TCR2_EL1 EndSysreg Sysreg TCR2_EL2 3 4 2 0 3 @@ -3084,7 +3149,7 @@ Fields PIRx_ELx EndSysreg Sysreg PIRE0_EL12 3 5 10 2 2 -Fields PIRx_ELx +Mapping PIRE0_EL1 EndSysreg Sysreg PIRE0_EL2 3 4 10 2 2 @@ -3096,7 +3161,7 @@ Fields PIRx_ELx EndSysreg Sysreg PIR_EL12 3 5 10 2 3 -Fields PIRx_ELx +Mapping PIR_EL1 EndSysreg Sysreg PIR_EL2 3 4 10 2 3 @@ -3116,7 +3181,7 @@ Fields PIRx_ELx EndSysreg Sysreg POR_EL12 3 5 10 2 4 -Fields PIRx_ELx +Mapping POR_EL1 EndSysreg Sysreg S2POR_EL1 3 0 10 2 5 diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index 3eb51fbe804e..d987ba368ed6 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -20,7 +20,6 @@ config HEXAGON # select ARCH_HAS_CPU_IDLE_WAIT # select GPIOLIB # select HAVE_CLK - # select GENERIC_PENDING_IRQ if SMP select GENERIC_ATOMIC64 select HAVE_PERF_EVENTS # GENERIC_ALLOCATOR is used by dma_alloc_coherent() diff --git a/arch/hexagon/Makefile b/arch/hexagon/Makefile index 92d005958dfb..ff172cbe5881 100644 --- a/arch/hexagon/Makefile +++ b/arch/hexagon/Makefile @@ -32,3 +32,9 @@ KBUILD_LDFLAGS += $(ldflags-y) TIR_NAME := r19 KBUILD_CFLAGS += -ffixed-$(TIR_NAME) -DTHREADINFO_REG=$(TIR_NAME) -D__linux__ KBUILD_AFLAGS += -DTHREADINFO_REG=$(TIR_NAME) + +# Disable HexagonConstExtenders pass for LLVM versions prior to 19.1.0 +# https://github.com/llvm/llvm-project/issues/99714 +ifneq ($(call clang-min-version, 190100),y) +KBUILD_CFLAGS += -mllvm -hexagon-cext=false +endif diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index dae3a9104ca6..28f0221e22fb 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -81,6 +81,7 @@ config LOONGARCH select BUILDTIME_TABLE_SORT select COMMON_CLK select CPU_PM + select EDAC_SUPPORT select EFI select GENERIC_CLOCKEVENTS select GENERIC_CMOS_UPDATE @@ -128,16 +129,18 @@ config LOONGARCH select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_ARGS + select HAVE_FTRACE_REGS_HAVING_PT_REGS select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS if !ARCH_STRICT_ALIGN select HAVE_EXIT_THREAD select HAVE_GUP_FAST + select HAVE_FTRACE_GRAPH_FUNC select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_ERROR_INJECTION - select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_GRAPH_FREGS select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS diff --git a/arch/loongarch/include/asm/bug.h b/arch/loongarch/include/asm/bug.h index 08388876ade4..f6f254f2c5db 100644 --- a/arch/loongarch/include/asm/bug.h +++ b/arch/loongarch/include/asm/bug.h @@ -4,6 +4,7 @@ #include <asm/break.h> #include <linux/stringify.h> +#include <linux/objtool.h> #ifndef CONFIG_DEBUG_BUGVERBOSE #define _BUGVERBOSE_LOCATION(file, line) @@ -33,25 +34,25 @@ #define ASM_BUG_FLAGS(flags) \ __BUG_ENTRY(flags) \ - break BRK_BUG + break BRK_BUG; #define ASM_BUG() ASM_BUG_FLAGS(0) -#define __BUG_FLAGS(flags) \ - asm_inline volatile (__stringify(ASM_BUG_FLAGS(flags))); +#define __BUG_FLAGS(flags, extra) \ + asm_inline volatile (__stringify(ASM_BUG_FLAGS(flags)) \ + extra); #define __WARN_FLAGS(flags) \ do { \ instrumentation_begin(); \ - __BUG_FLAGS(BUGFLAG_WARNING|(flags)); \ - annotate_reachable(); \ + __BUG_FLAGS(BUGFLAG_WARNING|(flags), ANNOTATE_REACHABLE(10001b));\ instrumentation_end(); \ } while (0) #define BUG() \ do { \ instrumentation_begin(); \ - __BUG_FLAGS(0); \ + __BUG_FLAGS(0, ""); \ unreachable(); \ } while (0) diff --git a/arch/loongarch/include/asm/fprobe.h b/arch/loongarch/include/asm/fprobe.h new file mode 100644 index 000000000000..7af3b3126caf --- /dev/null +++ b/arch/loongarch/include/asm/fprobe.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_LOONGARCH_FPROBE_H +#define _ASM_LOONGARCH_FPROBE_H + +/* + * Explicitly undef ARCH_DEFINE_ENCODE_FPROBE_HEADER, because loongarch does not + * have enough number of fixed MSBs of the address of kernel objects for + * encoding the size of data in fprobe_header. Use 2-entries encoding instead. + */ +#undef ARCH_DEFINE_ENCODE_FPROBE_HEADER + +#endif /* _ASM_LOONGARCH_FPROBE_H */ diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h index 8f13eaeaa325..6e0a99763a9a 100644 --- a/arch/loongarch/include/asm/ftrace.h +++ b/arch/loongarch/include/asm/ftrace.h @@ -57,6 +57,16 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip) instruction_pointer_set(&arch_ftrace_regs(fregs)->regs, ip); } +#undef ftrace_regs_get_frame_pointer +#define ftrace_regs_get_frame_pointer(fregs) \ + (arch_ftrace_regs(fregs)->regs.regs[22]) + +static __always_inline unsigned long +ftrace_regs_get_return_address(struct ftrace_regs *fregs) +{ + return *(unsigned long *)(arch_ftrace_regs(fregs)->regs.regs[1]); +} + #define ftrace_graph_func ftrace_graph_func void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); @@ -78,26 +88,4 @@ __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) #endif /* CONFIG_FUNCTION_TRACER */ -#ifndef __ASSEMBLY__ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - /* a0 - a1 */ - unsigned long regs[2]; - - unsigned long fp; - unsigned long __unused; -}; - -static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->regs[0]; -} - -static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->fp; -} -#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */ -#endif - #endif /* _ASM_LOONGARCH_FTRACE_H */ diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c index 049c5c3e370c..8be1c38ad8eb 100644 --- a/arch/loongarch/kernel/asm-offsets.c +++ b/arch/loongarch/kernel/asm-offsets.c @@ -280,18 +280,6 @@ static void __used output_pbe_defines(void) } #endif -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -static void __used output_fgraph_ret_regs_defines(void) -{ - COMMENT("LoongArch fgraph_ret_regs offsets."); - OFFSET(FGRET_REGS_A0, fgraph_ret_regs, regs[0]); - OFFSET(FGRET_REGS_A1, fgraph_ret_regs, regs[1]); - OFFSET(FGRET_REGS_FP, fgraph_ret_regs, fp); - DEFINE(FGRET_REGS_SIZE, sizeof(struct fgraph_ret_regs)); - BLANK(); -} -#endif - static void __used output_kvm_defines(void) { COMMENT("KVM/LoongArch Specific offsets."); diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c index 18056229e22e..25c9a4cfd5fa 100644 --- a/arch/loongarch/kernel/ftrace_dyn.c +++ b/arch/loongarch/kernel/ftrace_dyn.c @@ -243,8 +243,16 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, { struct pt_regs *regs = &arch_ftrace_regs(fregs)->regs; unsigned long *parent = (unsigned long *)®s->regs[1]; + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long old; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + old = *parent; - prepare_ftrace_return(ip, (unsigned long *)parent); + if (!function_graph_enter_regs(old, ip, 0, parent, fregs)) + *parent = return_hooker; } #else static int ftrace_modify_graph_caller(bool enable) diff --git a/arch/loongarch/kernel/mcount.S b/arch/loongarch/kernel/mcount.S index 3015896016a0..b6850503e061 100644 --- a/arch/loongarch/kernel/mcount.S +++ b/arch/loongarch/kernel/mcount.S @@ -79,10 +79,11 @@ SYM_FUNC_START(ftrace_graph_caller) SYM_FUNC_END(ftrace_graph_caller) SYM_FUNC_START(return_to_handler) - PTR_ADDI sp, sp, -FGRET_REGS_SIZE - PTR_S a0, sp, FGRET_REGS_A0 - PTR_S a1, sp, FGRET_REGS_A1 - PTR_S zero, sp, FGRET_REGS_FP + /* Save return value regs */ + PTR_ADDI sp, sp, -PT_SIZE + PTR_S a0, sp, PT_R4 + PTR_S a1, sp, PT_R5 + PTR_S zero, sp, PT_R22 move a0, sp bl ftrace_return_to_handler @@ -90,9 +91,11 @@ SYM_FUNC_START(return_to_handler) /* Restore the real parent address: a0 -> ra */ move ra, a0 - PTR_L a0, sp, FGRET_REGS_A0 - PTR_L a1, sp, FGRET_REGS_A1 - PTR_ADDI sp, sp, FGRET_REGS_SIZE + /* Restore return value regs */ + PTR_L a0, sp, PT_R4 + PTR_L a1, sp, PT_R5 + PTR_ADDI sp, sp, PT_SIZE + jr ra SYM_FUNC_END(return_to_handler) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/loongarch/kernel/mcount_dyn.S b/arch/loongarch/kernel/mcount_dyn.S index 0c65cf09110c..d6b474ad1d5e 100644 --- a/arch/loongarch/kernel/mcount_dyn.S +++ b/arch/loongarch/kernel/mcount_dyn.S @@ -140,19 +140,19 @@ SYM_CODE_END(ftrace_graph_caller) SYM_CODE_START(return_to_handler) UNWIND_HINT_UNDEFINED /* Save return value regs */ - PTR_ADDI sp, sp, -FGRET_REGS_SIZE - PTR_S a0, sp, FGRET_REGS_A0 - PTR_S a1, sp, FGRET_REGS_A1 - PTR_S zero, sp, FGRET_REGS_FP + PTR_ADDI sp, sp, -PT_SIZE + PTR_S a0, sp, PT_R4 + PTR_S a1, sp, PT_R5 + PTR_S zero, sp, PT_R22 move a0, sp bl ftrace_return_to_handler move ra, a0 /* Restore return value regs */ - PTR_L a0, sp, FGRET_REGS_A0 - PTR_L a1, sp, FGRET_REGS_A1 - PTR_ADDI sp, sp, FGRET_REGS_SIZE + PTR_L a0, sp, PT_R4 + PTR_L a1, sp, PT_R5 + PTR_ADDI sp, sp, PT_SIZE jr ra SYM_CODE_END(return_to_handler) diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 7c4f7bcc89d7..b2ed0308c0ea 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -23,7 +23,9 @@ config M68K select GENERIC_LIB_ASHLDI3 select GENERIC_LIB_ASHRDI3 select GENERIC_LIB_LSHRDI3 + select GENERIC_LIB_MULDI3 select HAS_IOPORT if PCI || ISA || ATARI_ROM_ISA + select HAVE_ARCH_LIBGCC_H select HAVE_ARCH_SECCOMP select HAVE_ARCH_SECCOMP_FILTER select HAVE_ASM_MODVERSIONS diff --git a/arch/m68k/atari/nvram.c b/arch/m68k/atari/nvram.c index 7000d2443aa3..ededc31375c3 100644 --- a/arch/m68k/atari/nvram.c +++ b/arch/m68k/atari/nvram.c @@ -16,7 +16,9 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/spinlock.h> +#include <linux/string_choices.h> #include <linux/types.h> + #include <asm/atarihw.h> #include <asm/atariints.h> @@ -198,7 +200,7 @@ static void atari_nvram_proc_read(unsigned char *nvram, struct seq_file *seq, seq_printf(seq, "0x%02x (undefined)\n", nvram[1]); seq_printf(seq, "SCSI arbitration : %s\n", - (nvram[16] & 0x80) ? "on" : "off"); + str_on_off(nvram[16] & 0x80)); seq_puts(seq, "SCSI host ID : "); if (nvram[16] & 0x80) seq_printf(seq, "%d\n", nvram[16] & 7); @@ -236,7 +238,7 @@ static void atari_nvram_proc_read(unsigned char *nvram, struct seq_file *seq, vmode & 16 ? "VGA" : "TV", vmode & 32 ? "PAL" : "NTSC"); seq_printf(seq, " %soverscan, compat. mode %s%s\n", - vmode & 64 ? "" : "no ", vmode & 128 ? "on" : "off", + vmode & 64 ? "" : "no ", str_on_off(vmode & 128), vmode & 256 ? (vmode & 16 ? ", line doubling" : ", half screen") : ""); } diff --git a/arch/m68k/include/asm/libgcc.h b/arch/m68k/include/asm/libgcc.h new file mode 100644 index 000000000000..27e17195bd7b --- /dev/null +++ b/arch/m68k/include/asm/libgcc.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_M68K_LIBGCC_H +#define __ASM_M68K_LIBGCC_H + +#ifndef CONFIG_CPU_HAS_NO_MULDIV64 +/* + * For those 68K CPUs that support 64bit multiply define umul_ppm() + * for the common muldi3 libgcc helper function (in lib/muldi3.c). + * CPUs that don't have it (like the original 68000 and ColdFire) + * will fallback to using the C-coded version of umul_ppmm(). + */ +#define umul_ppmm(w1, w0, u, v) \ + do { \ + unsigned long __u = (u), __v = (v); \ + unsigned long __w0, __w1; \ + \ + __asm__ ("mulu%.l %3,%1:%0" \ + : "=d" (__w0), \ + "=d" (__w1) \ + : "%0" (__u), \ + "dmi" (__v)); \ + \ + (w0) = __w0; (w1) = __w1; \ + } while (0) +#endif /* !CONFIG_CPU_HAS_NO_MULDIV64 */ + +#endif /* __ASM_M68K_LIBGCC_H */ diff --git a/arch/m68k/include/asm/vga.h b/arch/m68k/include/asm/vga.h index 4742e6bc3ab8..cdd414fa8710 100644 --- a/arch/m68k/include/asm/vga.h +++ b/arch/m68k/include/asm/vga.h @@ -9,7 +9,7 @@ */ #ifndef CONFIG_PCI -#include <asm/raw_io.h> +#include <asm/io.h> #include <asm/kmap.h> /* @@ -29,9 +29,9 @@ #define inw_p(port) 0 #define outb_p(port, val) do { } while (0) #define outw(port, val) do { } while (0) -#define readb raw_inb -#define writeb raw_outb -#define writew raw_outw +#define readb __raw_readb +#define writeb __raw_writeb +#define writew __raw_writew #endif /* CONFIG_PCI */ #endif /* _ASM_M68K_VGA_H */ diff --git a/arch/m68k/lib/Makefile b/arch/m68k/lib/Makefile index 9158688e6cc6..15278a95259e 100644 --- a/arch/m68k/lib/Makefile +++ b/arch/m68k/lib/Makefile @@ -4,7 +4,7 @@ # Makefile for m68k-specific library files.. # -lib-y := muldi3.o memcpy.o memset.o memmove.o +lib-y := memcpy.o memset.o memmove.o lib-$(CONFIG_MMU) += uaccess.o lib-$(CONFIG_CPU_HAS_NO_MULDIV64) += mulsi3.o divsi3.o udivsi3.o diff --git a/arch/m68k/lib/muldi3.c b/arch/m68k/lib/muldi3.c deleted file mode 100644 index 5012a9b218c7..000000000000 --- a/arch/m68k/lib/muldi3.c +++ /dev/null @@ -1,97 +0,0 @@ -/* muldi3.c extracted from gcc-2.7.2.3/libgcc2.c and - gcc-2.7.2.3/longlong.h which is: */ -/* Copyright (C) 1989, 1992, 1993, 1994, 1995 Free Software Foundation, Inc. - -This file is part of GNU CC. - -GNU CC is free software; you can redistribute it and/or modify -it under the terms of the GNU General Public License as published by -the Free Software Foundation; either version 2, or (at your option) -any later version. - -GNU CC is distributed in the hope that it will be useful, -but WITHOUT ANY WARRANTY; without even the implied warranty of -MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -GNU General Public License for more details. */ - -#include <linux/compiler.h> -#include <linux/export.h> -#include <linux/libgcc.h> - -#ifdef CONFIG_CPU_HAS_NO_MULDIV64 - -#define SI_TYPE_SIZE 32 -#define __BITS4 (SI_TYPE_SIZE / 4) -#define __ll_B (1L << (SI_TYPE_SIZE / 2)) -#define __ll_lowpart(t) ((USItype) (t) % __ll_B) -#define __ll_highpart(t) ((USItype) (t) / __ll_B) - -#define umul_ppmm(w1, w0, u, v) \ - do { \ - USItype __x0, __x1, __x2, __x3; \ - USItype __ul, __vl, __uh, __vh; \ - \ - __ul = __ll_lowpart (u); \ - __uh = __ll_highpart (u); \ - __vl = __ll_lowpart (v); \ - __vh = __ll_highpart (v); \ - \ - __x0 = (USItype) __ul * __vl; \ - __x1 = (USItype) __ul * __vh; \ - __x2 = (USItype) __uh * __vl; \ - __x3 = (USItype) __uh * __vh; \ - \ - __x1 += __ll_highpart (__x0);/* this can't give carry */ \ - __x1 += __x2; /* but this indeed can */ \ - if (__x1 < __x2) /* did we get it? */ \ - __x3 += __ll_B; /* yes, add it in the proper pos. */ \ - \ - (w1) = __x3 + __ll_highpart (__x1); \ - (w0) = __ll_lowpart (__x1) * __ll_B + __ll_lowpart (__x0); \ - } while (0) - -#else - -#define umul_ppmm(w1, w0, u, v) \ - __asm__ ("mulu%.l %3,%1:%0" \ - : "=d" ((USItype)(w0)), \ - "=d" ((USItype)(w1)) \ - : "%0" ((USItype)(u)), \ - "dmi" ((USItype)(v))) - -#endif - -#define __umulsidi3(u, v) \ - ({DIunion __w; \ - umul_ppmm (__w.s.high, __w.s.low, u, v); \ - __w.ll; }) - -typedef int SItype __mode(SI); -typedef unsigned int USItype __mode(SI); -typedef int DItype __mode(DI); -typedef int word_type __mode(__word__); - -struct DIstruct {SItype high, low;}; - -typedef union -{ - struct DIstruct s; - DItype ll; -} DIunion; - -DItype -__muldi3 (DItype u, DItype v) -{ - DIunion w; - DIunion uu, vv; - - uu.ll = u; - vv.ll = v; - - w.ll = __umulsidi3 (uu.s.low, vv.s.low); - w.s.high += ((USItype) uu.s.low * (USItype) vv.s.high - + (USItype) uu.s.high * (USItype) vv.s.low); - - return w.ll; -} -EXPORT_SYMBOL(__muldi3); diff --git a/arch/nios2/kernel/cpuinfo.c b/arch/nios2/kernel/cpuinfo.c index 338849c430a5..7b1e8f9128e9 100644 --- a/arch/nios2/kernel/cpuinfo.c +++ b/arch/nios2/kernel/cpuinfo.c @@ -143,11 +143,11 @@ static int show_cpuinfo(struct seq_file *m, void *v) " DIV:\t\t%s\n" " BMX:\t\t%s\n" " CDX:\t\t%s\n", - cpuinfo.has_mul ? "yes" : "no", - cpuinfo.has_mulx ? "yes" : "no", - cpuinfo.has_div ? "yes" : "no", - cpuinfo.has_bmx ? "yes" : "no", - cpuinfo.has_cdx ? "yes" : "no"); + str_yes_no(cpuinfo.has_mul), + str_yes_no(cpuinfo.has_mulx), + str_yes_no(cpuinfo.has_div), + str_yes_no(cpuinfo.has_bmx), + str_yes_no(cpuinfo.has_cdx)); seq_printf(m, "Icache:\t\t%ukB, line length: %u\n", diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S index 440711d7bf40..ce6f2b08a35e 100644 --- a/arch/openrisc/kernel/entry.S +++ b/arch/openrisc/kernel/entry.S @@ -239,6 +239,8 @@ handler: ;\ /* =====================================================[ exceptions] === */ + __REF + /* ---[ 0x100: RESET exception ]----------------------------------------- */ EXCEPTION_ENTRY(_tng_kernel_start) diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S index 439e00f81e5d..bd760066f1cd 100644 --- a/arch/openrisc/kernel/head.S +++ b/arch/openrisc/kernel/head.S @@ -26,15 +26,15 @@ #include <asm/asm-offsets.h> #include <linux/of_fdt.h> -#define tophys(rd,rs) \ - l.movhi rd,hi(-KERNELBASE) ;\ +#define tophys(rd,rs) \ + l.movhi rd,hi(-KERNELBASE) ;\ l.add rd,rd,rs -#define CLEAR_GPR(gpr) \ +#define CLEAR_GPR(gpr) \ l.movhi gpr,0x0 -#define LOAD_SYMBOL_2_GPR(gpr,symbol) \ - l.movhi gpr,hi(symbol) ;\ +#define LOAD_SYMBOL_2_GPR(gpr,symbol) \ + l.movhi gpr,hi(symbol) ;\ l.ori gpr,gpr,lo(symbol) @@ -326,21 +326,21 @@ l.addi r1,r1,-(INT_FRAME_SIZE) ;\ /* r1 is KSP, r30 is __pa(KSP) */ ;\ tophys (r30,r1) ;\ - l.sw PT_GPR12(r30),r12 ;\ + l.sw PT_GPR12(r30),r12 ;\ l.mfspr r12,r0,SPR_EPCR_BASE ;\ l.sw PT_PC(r30),r12 ;\ l.mfspr r12,r0,SPR_ESR_BASE ;\ l.sw PT_SR(r30),r12 ;\ /* save r31 */ ;\ EXCEPTION_T_LOAD_GPR30(r12) ;\ - l.sw PT_GPR30(r30),r12 ;\ + l.sw PT_GPR30(r30),r12 ;\ /* save r10 as was prior to exception */ ;\ EXCEPTION_T_LOAD_GPR10(r12) ;\ - l.sw PT_GPR10(r30),r12 ;\ - /* save PT_SP as was prior to exception */ ;\ + l.sw PT_GPR10(r30),r12 ;\ + /* save PT_SP as was prior to exception */ ;\ EXCEPTION_T_LOAD_SP(r12) ;\ l.sw PT_SP(r30),r12 ;\ - l.sw PT_GPR13(r30),r13 ;\ + l.sw PT_GPR13(r30),r13 ;\ /* --> */ ;\ /* save exception r4, set r4 = EA */ ;\ l.sw PT_GPR4(r30),r4 ;\ @@ -357,6 +357,8 @@ /* =====================================================[ exceptions] === */ + __HEAD + /* ---[ 0x100: RESET exception ]----------------------------------------- */ .org 0x100 /* Jump to .init code at _start which lives in the .head section @@ -394,7 +396,7 @@ _dispatch_do_ipage_fault: .org 0x500 EXCEPTION_HANDLE(_timer_handler) -/* ---[ 0x600: Alignment exception ]-------------------------------------- */ +/* ---[ 0x600: Alignment exception ]------------------------------------- */ .org 0x600 EXCEPTION_HANDLE(_alignment_handler) @@ -424,7 +426,7 @@ _dispatch_do_ipage_fault: .org 0xc00 EXCEPTION_HANDLE(_sys_call_handler) -/* ---[ 0xd00: Floating point exception ]--------------------------------- */ +/* ---[ 0xd00: Floating point exception ]-------------------------------- */ .org 0xd00 EXCEPTION_HANDLE(_fpe_trap_handler) @@ -506,10 +508,10 @@ _dispatch_do_ipage_fault: /* .text*/ -/* This early stuff belongs in HEAD, but some of the functions below definitely +/* This early stuff belongs in the .init.text section, but some of the functions below definitely * don't... */ - __HEAD + __INIT .global _start _start: /* Init r0 to zero as per spec */ @@ -816,7 +818,7 @@ secondary_start: #endif -/* ========================================[ cache ]=== */ +/* ==========================================================[ cache ]=== */ /* alignment here so we don't change memory offsets with * memory controller defined diff --git a/arch/openrisc/kernel/vmlinux.lds.S b/arch/openrisc/kernel/vmlinux.lds.S index bc1306047837..049bff45f612 100644 --- a/arch/openrisc/kernel/vmlinux.lds.S +++ b/arch/openrisc/kernel/vmlinux.lds.S @@ -50,6 +50,7 @@ SECTIONS .text : AT(ADDR(.text) - LOAD_OFFSET) { _stext = .; + HEAD_TEXT TEXT_TEXT SCHED_TEXT LOCK_TEXT @@ -83,8 +84,6 @@ SECTIONS . = ALIGN(PAGE_SIZE); __init_begin = .; - HEAD_TEXT_SECTION - /* Page aligned */ INIT_TEXT_SECTION(PAGE_SIZE) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index a0ce777f9706..34b965fa45ac 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -145,6 +145,7 @@ config PPC select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_PMEM_API + select ARCH_HAS_PREEMPT_LAZY select ARCH_HAS_PTE_DEVMAP if PPC_BOOK3S_64 select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64 @@ -240,6 +241,7 @@ config PPC select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_GUP_FAST + select HAVE_FTRACE_GRAPH_FUNC select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_DESCRIPTORS if PPC64_ELF_ABI_V1 diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig index 53f43a34e1a9..b33f0034990c 100644 --- a/arch/powerpc/configs/cell_defconfig +++ b/arch/powerpc/configs/cell_defconfig @@ -168,7 +168,6 @@ CONFIG_INFINIBAND_MTHCA=m CONFIG_INFINIBAND_IPOIB=m CONFIG_INFINIBAND_IPOIB_DEBUG_DATA=y CONFIG_EDAC=y -CONFIG_EDAC_CELL=y CONFIG_UIO=m CONFIG_EXT2_FS=y CONFIG_EXT4_FS=y diff --git a/arch/powerpc/configs/pmac32_defconfig b/arch/powerpc/configs/pmac32_defconfig index 57ded82c2840..e8b3f67bf3f5 100644 --- a/arch/powerpc/configs/pmac32_defconfig +++ b/arch/powerpc/configs/pmac32_defconfig @@ -208,6 +208,7 @@ CONFIG_FB_ATY=y CONFIG_FB_ATY_CT=y CONFIG_FB_ATY_GX=y CONFIG_FB_3DFX=y +CONFIG_BACKLIGHT_CLASS_DEVICE=y # CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y diff --git a/arch/powerpc/configs/ppc6xx_defconfig b/arch/powerpc/configs/ppc6xx_defconfig index 4d77e17541e9..ca0c90e95837 100644 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@ -716,6 +716,7 @@ CONFIG_FB_TRIDENT=m CONFIG_FB_SM501=m CONFIG_FB_IBM_GXT4500=y CONFIG_LCD_PLATFORM=m +CONFIG_BACKLIGHT_CLASS_DEVICE=y CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_ROTATION=y CONFIG_LOGO=y diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h index db481b336bca..82da7c7a1d12 100644 --- a/arch/powerpc/include/asm/ftrace.h +++ b/arch/powerpc/include/asm/ftrace.h @@ -43,6 +43,13 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs * return arch_ftrace_regs(fregs)->regs.msr ? &arch_ftrace_regs(fregs)->regs : NULL; } +#define arch_ftrace_fill_perf_regs(fregs, _regs) do { \ + (_regs)->result = 0; \ + (_regs)->nip = arch_ftrace_regs(fregs)->regs.nip; \ + (_regs)->gpr[1] = arch_ftrace_regs(fregs)->regs.gpr[1]; \ + asm volatile("mfmsr %0" : "=r" ((_regs)->msr)); \ + } while (0) + static __always_inline void ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip) @@ -50,6 +57,12 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, regs_set_return_ip(&arch_ftrace_regs(fregs)->regs, ip); } +static __always_inline unsigned long +ftrace_regs_get_return_address(struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->regs.link; +} + struct ftrace_ops; #define ftrace_graph_func ftrace_graph_func diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h index 18a3028ac3b6..dad2e7980f24 100644 --- a/arch/powerpc/include/asm/hugetlb.h +++ b/arch/powerpc/include/asm/hugetlb.h @@ -15,6 +15,15 @@ extern bool hugetlb_disabled; +static inline bool hugepages_supported(void) +{ + if (hugetlb_disabled) + return false; + + return HPAGE_SHIFT != 0; +} +#define hugepages_supported hugepages_supported + void __init hugetlbpage_init_defaultsize(void); int slice_is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index 270ee93a0f7d..601e569303e1 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -61,7 +61,6 @@ struct pt_regs; extern void kexec_smp_wait(void); /* get and clear naca physid, wait for master to copy new code to 0 */ extern void default_machine_kexec(struct kimage *image); -extern void machine_kexec_mask_interrupts(void); void relocate_new_kernel(unsigned long indirection_page, unsigned long reboot_code_buffer, unsigned long start_address) __noreturn; diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h index 6ebca2996f18..2785c7462ebf 100644 --- a/arch/powerpc/include/asm/thread_info.h +++ b/arch/powerpc/include/asm/thread_info.h @@ -103,6 +103,7 @@ void arch_setup_new_exec(void); #define TIF_PATCH_PENDING 6 /* pending live patching update */ #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ #define TIF_SINGLESTEP 8 /* singlestepping active */ +#define TIF_NEED_RESCHED_LAZY 9 /* Scheduler driven lazy preemption */ #define TIF_SECCOMP 10 /* secure computing */ #define TIF_RESTOREALL 11 /* Restore all regs (implies NOERROR) */ #define TIF_NOERROR 12 /* Force successful syscall return */ @@ -122,6 +123,7 @@ void arch_setup_new_exec(void); #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) #define _TIF_SIGPENDING (1<<TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1<<TIF_NEED_RESCHED) +#define _TIF_NEED_RESCHED_LAZY (1<<TIF_NEED_RESCHED_LAZY) #define _TIF_NOTIFY_SIGNAL (1<<TIF_NOTIFY_SIGNAL) #define _TIF_POLLING_NRFLAG (1<<TIF_POLLING_NRFLAG) #define _TIF_32BIT (1<<TIF_32BIT) @@ -142,9 +144,10 @@ void arch_setup_new_exec(void); _TIF_SYSCALL_EMU) #define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ - _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ - _TIF_RESTORE_TM | _TIF_PATCH_PENDING | \ - _TIF_NOTIFY_SIGNAL) + _TIF_NEED_RESCHED_LAZY | _TIF_NOTIFY_RESUME | \ + _TIF_UPROBE | _TIF_RESTORE_TM | \ + _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL) + #define _TIF_PERSYSCALL_MASK (_TIF_RESTOREALL|_TIF_NOERROR) /* Bits in local_flags */ diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h index 221c8f8ff89b..9bdd8080299b 100644 --- a/arch/powerpc/include/asm/time.h +++ b/arch/powerpc/include/asm/time.h @@ -86,7 +86,7 @@ static inline unsigned long tb_ticks_since(unsigned long tstamp) #define mulhdu(x,y) \ ({unsigned long z; asm ("mulhdu %0,%1,%2" : "=r" (z) : "r" (x), "r" (y)); z;}) #else -extern u64 mulhdu(u64, u64); +#define mulhdu(x, y) mul_u64_u64_shr(x, y, 64) #endif extern void div128_by_32(u64 dividend_high, u64 dividend_low, diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c index af62ec974b97..8f4acc55407b 100644 --- a/arch/powerpc/kernel/interrupt.c +++ b/arch/powerpc/kernel/interrupt.c @@ -185,7 +185,7 @@ again: ti_flags = read_thread_flags(); while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) { local_irq_enable(); - if (ti_flags & _TIF_NEED_RESCHED) { + if (ti_flags & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) { schedule(); } else { /* @@ -396,7 +396,7 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs) /* Returning to a kernel context with local irqs enabled. */ WARN_ON_ONCE(!(regs->msr & MSR_EE)); again: - if (IS_ENABLED(CONFIG_PREEMPT)) { + if (IS_ENABLED(CONFIG_PREEMPTION)) { /* Return to preemptible kernel context */ if (unlikely(read_thread_flags() & _TIF_NEED_RESCHED)) { if (preempt_count() == 0) diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index 76381e14e800..0ebae6e4c19d 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -687,7 +687,7 @@ void iommu_table_clear(struct iommu_table *tbl) void iommu_table_reserve_pages(struct iommu_table *tbl, unsigned long res_start, unsigned long res_end) { - int i; + unsigned long i; WARN_ON_ONCE(res_end < res_start); /* diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S index 033cd00aa0fc..acb727f54e9d 100644 --- a/arch/powerpc/kernel/misc_32.S +++ b/arch/powerpc/kernel/misc_32.S @@ -28,32 +28,6 @@ .text /* - * This returns the high 64 bits of the product of two 64-bit numbers. - */ -_GLOBAL(mulhdu) - cmpwi r6,0 - cmpwi cr1,r3,0 - mr r10,r4 - mulhwu r4,r4,r5 - beq 1f - mulhwu r0,r10,r6 - mullw r7,r10,r5 - addc r7,r0,r7 - addze r4,r4 -1: beqlr cr1 /* all done if high part of A is 0 */ - mullw r9,r3,r5 - mulhwu r10,r3,r5 - beq 2f - mullw r0,r3,r6 - mulhwu r8,r3,r6 - addc r7,r0,r7 - adde r4,r4,r8 - addze r10,r10 -2: addc r4,r4,r9 - addze r3,r10 - blr - -/* * reloc_got2 runs through the .got2 section adding an offset * to each entry. */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index 7b739b9a91ab..ef91f71e07c4 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1960,8 +1960,8 @@ void start_thread(struct pt_regs *regs, unsigned long start, unsigned long sp) * address of _start and the second entry is the TOC * value we need to use. */ - __get_user(entry, (unsigned long __user *)start); - __get_user(toc, (unsigned long __user *)start+1); + get_user(entry, (unsigned long __user *)start); + get_user(toc, (unsigned long __user *)start+1); /* Check whether the e_entry function descriptor entries * need to be relocated before we can use them. diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c index 8e776ba39497..57082fac4668 100644 --- a/arch/powerpc/kernel/prom_init.c +++ b/arch/powerpc/kernel/prom_init.c @@ -2792,7 +2792,6 @@ static void __init flatten_device_tree(void) dt_struct_start, dt_struct_end); } -#ifdef CONFIG_PPC_CHRP /* * Pegasos and BriQ lacks the "ranges" property in the isa node * Pegasos needs decimal IRQ 14/15, not hexadecimal @@ -2843,11 +2842,7 @@ static void __init fixup_device_tree_chrp(void) } } } -#else -#define fixup_device_tree_chrp() -#endif -#if defined(CONFIG_PPC64) && defined(CONFIG_PPC_PMAC) static void __init fixup_device_tree_pmac64(void) { phandle u3, i2c, mpic; @@ -2887,11 +2882,7 @@ static void __init fixup_device_tree_pmac64(void) prom_setprop(i2c, "/u3@0,f8000000/i2c@f8001000", "interrupt-parent", &parent, sizeof(parent)); } -#else -#define fixup_device_tree_pmac64() -#endif -#ifdef CONFIG_PPC_PMAC static void __init fixup_device_tree_pmac(void) { __be32 val = 1; @@ -2911,11 +2902,7 @@ static void __init fixup_device_tree_pmac(void) prom_setprop(node, NULL, "#size-cells", &val, sizeof(val)); } } -#else -static inline void fixup_device_tree_pmac(void) { } -#endif -#ifdef CONFIG_PPC_EFIKA /* * The MPC5200 FEC driver requires an phy-handle property to tell it how * to talk to the phy. If the phy-handle property is missing, then this @@ -3047,11 +3034,7 @@ static void __init fixup_device_tree_efika(void) /* Make sure ethernet phy-handle property exists */ fixup_device_tree_efika_add_phy(); } -#else -#define fixup_device_tree_efika() -#endif -#ifdef CONFIG_PPC_PASEMI_NEMO /* * CFE supplied on Nemo is broken in several ways, biggest * problem is that it reassigns ISA interrupts to unused mpic ints. @@ -3127,17 +3110,23 @@ static void __init fixup_device_tree_pasemi(void) prom_setprop(iob, name, "device_type", "isa", sizeof("isa")); } -#else /* !CONFIG_PPC_PASEMI_NEMO */ -static inline void fixup_device_tree_pasemi(void) { } -#endif static void __init fixup_device_tree(void) { - fixup_device_tree_chrp(); - fixup_device_tree_pmac(); - fixup_device_tree_pmac64(); - fixup_device_tree_efika(); - fixup_device_tree_pasemi(); + if (IS_ENABLED(CONFIG_PPC_CHRP)) + fixup_device_tree_chrp(); + + if (IS_ENABLED(CONFIG_PPC_PMAC)) + fixup_device_tree_pmac(); + + if (IS_ENABLED(CONFIG_PPC_PMAC) && IS_ENABLED(CONFIG_PPC64)) + fixup_device_tree_pmac64(); + + if (IS_ENABLED(CONFIG_PPC_EFIKA)) + fixup_device_tree_efika(); + + if (IS_ENABLED(CONFIG_PPC_PASEMI_NEMO)) + fixup_device_tree_pasemi(); } static void __init prom_find_boot_cpu(void) diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 6fa179448c33..f7d7a93f07fc 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -834,8 +834,8 @@ static int __init check_cache_coherency(void) if (devtree_coherency != KERNEL_COHERENCY) { printk(KERN_ERR "kernel coherency:%s != device tree_coherency:%s\n", - KERNEL_COHERENCY ? "on" : "off", - devtree_coherency ? "on" : "off"); + str_on_off(KERNEL_COHERENCY), + str_on_off(devtree_coherency)); BUG(); } diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 5ccd791761e8..2f776f137a89 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -658,7 +658,6 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { unsigned long sp = arch_ftrace_regs(fregs)->regs.gpr[1]; - int bit; if (unlikely(ftrace_graph_is_dead())) goto out; @@ -666,14 +665,9 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; - bit = ftrace_test_recursion_trylock(ip, parent_ip); - if (bit < 0) - goto out; - - if (!function_graph_enter(parent_ip, ip, 0, (unsigned long *)sp)) + if (!function_graph_enter_regs(parent_ip, ip, 0, (unsigned long *)sp, fregs)) parent_ip = ppc_function_entry(return_to_handler); - ftrace_test_recursion_unlock(bit); out: arch_ftrace_regs(fregs)->regs.link = parent_ip; } diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c index 98787376eb87..ac35015f04c6 100644 --- a/arch/powerpc/kernel/trace/ftrace_64_pg.c +++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c @@ -787,10 +787,10 @@ int ftrace_disable_ftrace_graph_caller(void) * in current thread info. Return the address we want to divert to. */ static unsigned long -__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp) +__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp, + struct ftrace_regs *fregs) { unsigned long return_hooker; - int bit; if (unlikely(ftrace_graph_is_dead())) goto out; @@ -798,16 +798,11 @@ __prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp if (unlikely(atomic_read(¤t->tracing_graph_pause))) goto out; - bit = ftrace_test_recursion_trylock(ip, parent); - if (bit < 0) - goto out; - return_hooker = ppc_function_entry(return_to_handler); - if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp)) + if (!function_graph_enter_regs(parent, ip, 0, (unsigned long *)sp, fregs)) parent = return_hooker; - ftrace_test_recursion_unlock(bit); out: return parent; } @@ -816,13 +811,14 @@ out: void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { - arch_ftrace_regs(fregs)->regs.link = __prepare_ftrace_return(parent_ip, ip, arch_ftrace_regs(fregs)->regs.gpr[1]); + arch_ftrace_regs(fregs)->regs.link = __prepare_ftrace_return(parent_ip, ip, + arch_ftrace_regs(fregs)->regs.gpr[1], fregs); } #else unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp) { - return __prepare_ftrace_return(parent, ip, sp); + return __prepare_ftrace_return(parent, ip, sp, NULL); } #endif #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/powerpc/kernel/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32_wrapper.S index 10f92f265d51..20bca3548b44 100644 --- a/arch/powerpc/kernel/vdso32_wrapper.S +++ b/arch/powerpc/kernel/vdso32_wrapper.S @@ -2,7 +2,7 @@ #include <linux/linkage.h> #include <asm/page.h> - __PAGE_ALIGNED_DATA + .section ".data..ro_after_init", "aw" .globl vdso32_start, vdso32_end .balign PAGE_SIZE diff --git a/arch/powerpc/kernel/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64_wrapper.S index 839d1a61411d..1912936fa227 100644 --- a/arch/powerpc/kernel/vdso64_wrapper.S +++ b/arch/powerpc/kernel/vdso64_wrapper.S @@ -2,7 +2,7 @@ #include <linux/linkage.h> #include <asm/page.h> - __PAGE_ALIGNED_DATA + .section ".data..ro_after_init", "aw" .globl vdso64_start, vdso64_end .balign PAGE_SIZE diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c index b8333a49ea5d..58a930a47422 100644 --- a/arch/powerpc/kexec/core.c +++ b/arch/powerpc/kexec/core.c @@ -22,28 +22,6 @@ #include <asm/setup.h> #include <asm/firmware.h> -void machine_kexec_mask_interrupts(void) { - unsigned int i; - struct irq_desc *desc; - - for_each_irq_desc(i, desc) { - struct irq_chip *chip; - - chip = irq_desc_get_chip(desc); - if (!chip) - continue; - - if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data)) - chip->irq_eoi(&desc->irq_data); - - if (chip->irq_mask) - chip->irq_mask(&desc->irq_data); - - if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data)) - chip->irq_disable(&desc->irq_data); - } -} - #ifdef CONFIG_CRASH_DUMP void machine_crash_shutdown(struct pt_regs *regs) { diff --git a/arch/powerpc/kexec/core_32.c b/arch/powerpc/kexec/core_32.c index c95f96850c9e..deb28eb44f30 100644 --- a/arch/powerpc/kexec/core_32.c +++ b/arch/powerpc/kexec/core_32.c @@ -7,6 +7,7 @@ * Copyright (C) 2005 IBM Corporation. */ +#include <linux/irq.h> #include <linux/kexec.h> #include <linux/mm.h> #include <linux/string.h> diff --git a/arch/powerpc/kvm/e500.h b/arch/powerpc/kvm/e500.h index 6d0d329cbb35..f9acf866c709 100644 --- a/arch/powerpc/kvm/e500.h +++ b/arch/powerpc/kvm/e500.h @@ -34,6 +34,8 @@ enum vcpu_ftr { #define E500_TLB_BITMAP (1 << 30) /* TLB1 entry is mapped by host TLB0 */ #define E500_TLB_TLB0 (1 << 29) +/* entry is writable on the host */ +#define E500_TLB_WRITABLE (1 << 28) /* bits [6-5] MAS2_X1 and MAS2_X0 and [4-0] bits for WIMGE */ #define E500_TLB_MAS2_ATTR (0x7f) diff --git a/arch/powerpc/kvm/e500_mmu_host.c b/arch/powerpc/kvm/e500_mmu_host.c index e5a145b578a4..06caf8bbbe2b 100644 --- a/arch/powerpc/kvm/e500_mmu_host.c +++ b/arch/powerpc/kvm/e500_mmu_host.c @@ -45,11 +45,14 @@ static inline unsigned int tlb1_max_shadow_size(void) return host_tlb_params[1].entries - tlbcam_index - 1; } -static inline u32 e500_shadow_mas3_attrib(u32 mas3, int usermode) +static inline u32 e500_shadow_mas3_attrib(u32 mas3, bool writable, int usermode) { /* Mask off reserved bits. */ mas3 &= MAS3_ATTRIB_MASK; + if (!writable) + mas3 &= ~(MAS3_UW|MAS3_SW); + #ifndef CONFIG_KVM_BOOKE_HV if (!usermode) { /* Guest is in supervisor mode, @@ -242,17 +245,18 @@ static inline int tlbe_is_writable(struct kvm_book3e_206_tlb_entry *tlbe) return tlbe->mas7_3 & (MAS3_SW|MAS3_UW); } -static inline bool kvmppc_e500_ref_setup(struct tlbe_ref *ref, +static inline void kvmppc_e500_ref_setup(struct tlbe_ref *ref, struct kvm_book3e_206_tlb_entry *gtlbe, - kvm_pfn_t pfn, unsigned int wimg) + kvm_pfn_t pfn, unsigned int wimg, + bool writable) { ref->pfn = pfn; ref->flags = E500_TLB_VALID; + if (writable) + ref->flags |= E500_TLB_WRITABLE; /* Use guest supplied MAS2_G and MAS2_E */ ref->flags |= (gtlbe->mas2 & MAS2_ATTRIB_MASK) | wimg; - - return tlbe_is_writable(gtlbe); } static inline void kvmppc_e500_ref_release(struct tlbe_ref *ref) @@ -305,6 +309,7 @@ static void kvmppc_e500_setup_stlbe( { kvm_pfn_t pfn = ref->pfn; u32 pr = vcpu->arch.shared->msr & MSR_PR; + bool writable = !!(ref->flags & E500_TLB_WRITABLE); BUG_ON(!(ref->flags & E500_TLB_VALID)); @@ -312,7 +317,7 @@ static void kvmppc_e500_setup_stlbe( stlbe->mas1 = MAS1_TSIZE(tsize) | get_tlb_sts(gtlbe) | MAS1_VALID; stlbe->mas2 = (gvaddr & MAS2_EPN) | (ref->flags & E500_TLB_MAS2_ATTR); stlbe->mas7_3 = ((u64)pfn << PAGE_SHIFT) | - e500_shadow_mas3_attrib(gtlbe->mas7_3, pr); + e500_shadow_mas3_attrib(gtlbe->mas7_3, writable, pr); } static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, @@ -321,15 +326,14 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, struct tlbe_ref *ref) { struct kvm_memory_slot *slot; - unsigned long pfn = 0; /* silence GCC warning */ + unsigned int psize; + unsigned long pfn; struct page *page = NULL; unsigned long hva; - int pfnmap = 0; int tsize = BOOK3E_PAGESZ_4K; int ret = 0; unsigned long mmu_seq; struct kvm *kvm = vcpu_e500->vcpu.kvm; - unsigned long tsize_pages = 0; pte_t *ptep; unsigned int wimg = 0; pgd_t *pgdir; @@ -351,110 +355,12 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, slot = gfn_to_memslot(vcpu_e500->vcpu.kvm, gfn); hva = gfn_to_hva_memslot(slot, gfn); - if (tlbsel == 1) { - struct vm_area_struct *vma; - mmap_read_lock(kvm->mm); - - vma = find_vma(kvm->mm, hva); - if (vma && hva >= vma->vm_start && - (vma->vm_flags & VM_PFNMAP)) { - /* - * This VMA is a physically contiguous region (e.g. - * /dev/mem) that bypasses normal Linux page - * management. Find the overlap between the - * vma and the memslot. - */ - - unsigned long start, end; - unsigned long slot_start, slot_end; - - pfnmap = 1; - - start = vma->vm_pgoff; - end = start + - vma_pages(vma); - - pfn = start + ((hva - vma->vm_start) >> PAGE_SHIFT); - - slot_start = pfn - (gfn - slot->base_gfn); - slot_end = slot_start + slot->npages; - - if (start < slot_start) - start = slot_start; - if (end > slot_end) - end = slot_end; - - tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >> - MAS1_TSIZE_SHIFT; - - /* - * e500 doesn't implement the lowest tsize bit, - * or 1K pages. - */ - tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1); - - /* - * Now find the largest tsize (up to what the guest - * requested) that will cover gfn, stay within the - * range, and for which gfn and pfn are mutually - * aligned. - */ - - for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) { - unsigned long gfn_start, gfn_end; - tsize_pages = 1UL << (tsize - 2); - - gfn_start = gfn & ~(tsize_pages - 1); - gfn_end = gfn_start + tsize_pages; - - if (gfn_start + pfn - gfn < start) - continue; - if (gfn_end + pfn - gfn > end) - continue; - if ((gfn & (tsize_pages - 1)) != - (pfn & (tsize_pages - 1))) - continue; - - gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); - pfn &= ~(tsize_pages - 1); - break; - } - } else if (vma && hva >= vma->vm_start && - is_vm_hugetlb_page(vma)) { - unsigned long psize = vma_kernel_pagesize(vma); - - tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >> - MAS1_TSIZE_SHIFT; - - /* - * Take the largest page size that satisfies both host - * and guest mapping - */ - tsize = min(__ilog2(psize) - 10, tsize); - - /* - * e500 doesn't implement the lowest tsize bit, - * or 1K pages. - */ - tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1); - } - - mmap_read_unlock(kvm->mm); - } - - if (likely(!pfnmap)) { - tsize_pages = 1UL << (tsize + 10 - PAGE_SHIFT); - pfn = __kvm_faultin_pfn(slot, gfn, FOLL_WRITE, NULL, &page); - if (is_error_noslot_pfn(pfn)) { - if (printk_ratelimit()) - pr_err("%s: real page not found for gfn %lx\n", - __func__, (long)gfn); - return -EINVAL; - } - - /* Align guest and physical address to page map boundaries */ - pfn &= ~(tsize_pages - 1); - gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); + pfn = __kvm_faultin_pfn(slot, gfn, FOLL_WRITE, &writable, &page); + if (is_error_noslot_pfn(pfn)) { + if (printk_ratelimit()) + pr_err("%s: real page not found for gfn %lx\n", + __func__, (long)gfn); + return -EINVAL; } spin_lock(&kvm->mmu_lock); @@ -472,14 +378,13 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, * can't run hence pfn won't change. */ local_irq_save(flags); - ptep = find_linux_pte(pgdir, hva, NULL, NULL); + ptep = find_linux_pte(pgdir, hva, NULL, &psize); if (ptep) { pte_t pte = READ_ONCE(*ptep); if (pte_present(pte)) { wimg = (pte_val(pte) >> PTE_WIMGE_SHIFT) & MAS2_WIMGE_MASK; - local_irq_restore(flags); } else { local_irq_restore(flags); pr_err_ratelimited("%s: pte not present: gfn %lx,pfn %lx\n", @@ -488,10 +393,72 @@ static inline int kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500, goto out; } } - writable = kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg); + local_irq_restore(flags); + + if (psize && tlbsel == 1) { + unsigned long psize_pages, tsize_pages; + unsigned long start, end; + unsigned long slot_start, slot_end; + + psize_pages = 1UL << (psize - PAGE_SHIFT); + start = pfn & ~(psize_pages - 1); + end = start + psize_pages; + + slot_start = pfn - (gfn - slot->base_gfn); + slot_end = slot_start + slot->npages; + + if (start < slot_start) + start = slot_start; + if (end > slot_end) + end = slot_end; + + tsize = (gtlbe->mas1 & MAS1_TSIZE_MASK) >> + MAS1_TSIZE_SHIFT; + + /* + * Any page size that doesn't satisfy the host mapping + * will fail the start and end tests. + */ + tsize = min(psize - PAGE_SHIFT + BOOK3E_PAGESZ_4K, tsize); + + /* + * e500 doesn't implement the lowest tsize bit, + * or 1K pages. + */ + tsize = max(BOOK3E_PAGESZ_4K, tsize & ~1); + + /* + * Now find the largest tsize (up to what the guest + * requested) that will cover gfn, stay within the + * range, and for which gfn and pfn are mutually + * aligned. + */ + + for (; tsize > BOOK3E_PAGESZ_4K; tsize -= 2) { + unsigned long gfn_start, gfn_end; + tsize_pages = 1UL << (tsize - 2); + + gfn_start = gfn & ~(tsize_pages - 1); + gfn_end = gfn_start + tsize_pages; + + if (gfn_start + pfn - gfn < start) + continue; + if (gfn_end + pfn - gfn > end) + continue; + if ((gfn & (tsize_pages - 1)) != + (pfn & (tsize_pages - 1))) + continue; + + gvaddr &= ~((tsize_pages << PAGE_SHIFT) - 1); + pfn &= ~(tsize_pages - 1); + break; + } + } + kvmppc_e500_ref_setup(ref, gtlbe, pfn, wimg, writable); kvmppc_e500_setup_stlbe(&vcpu_e500->vcpu, gtlbe, tsize, ref, gvaddr, stlbe); + writable = tlbe_is_writable(stlbe); /* Clear i-cache for new pages */ kvmppc_mmu_flush_icache(pfn); diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c index d491da8d1838..58ed6bd613a6 100644 --- a/arch/powerpc/lib/vmx-helper.c +++ b/arch/powerpc/lib/vmx-helper.c @@ -45,7 +45,7 @@ int exit_vmx_usercopy(void) * set and we are preemptible. The hack here is to schedule a * decrementer to fire here and reschedule for us if necessary. */ - if (IS_ENABLED(CONFIG_PREEMPT) && need_resched()) + if (IS_ENABLED(CONFIG_PREEMPTION) && need_resched()) set_dec(1); return 0; } diff --git a/arch/powerpc/platforms/8xx/cpm1.c b/arch/powerpc/platforms/8xx/cpm1.c index b24d4102fbf6..1dc095ad48fc 100644 --- a/arch/powerpc/platforms/8xx/cpm1.c +++ b/arch/powerpc/platforms/8xx/cpm1.c @@ -45,7 +45,7 @@ #include <sysdev/fsl_soc.h> #ifdef CONFIG_8xx_GPIO -#include <linux/gpio/legacy-of-mm-gpiochip.h> +#include <linux/gpio/driver.h> #endif #define CPM_MAP_SIZE (0x4000) @@ -376,7 +376,8 @@ int __init cpm1_clk_setup(enum cpm_clk_target target, int clock, int mode) #ifdef CONFIG_8xx_GPIO struct cpm1_gpio16_chip { - struct of_mm_gpio_chip mm_gc; + struct gpio_chip gc; + void __iomem *regs; spinlock_t lock; /* shadowed data register to clear/set bits safely */ @@ -386,19 +387,17 @@ struct cpm1_gpio16_chip { int irq[16]; }; -static void cpm1_gpio16_save_regs(struct of_mm_gpio_chip *mm_gc) +static void cpm1_gpio16_save_regs(struct cpm1_gpio16_chip *cpm1_gc) { - struct cpm1_gpio16_chip *cpm1_gc = - container_of(mm_gc, struct cpm1_gpio16_chip, mm_gc); - struct cpm_ioport16 __iomem *iop = mm_gc->regs; + struct cpm_ioport16 __iomem *iop = cpm1_gc->regs; cpm1_gc->cpdata = in_be16(&iop->dat); } static int cpm1_gpio16_get(struct gpio_chip *gc, unsigned int gpio) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm_ioport16 __iomem *iop = mm_gc->regs; + struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc); + struct cpm_ioport16 __iomem *iop = cpm1_gc->regs; u16 pin_mask; pin_mask = 1 << (15 - gpio); @@ -406,11 +405,9 @@ static int cpm1_gpio16_get(struct gpio_chip *gc, unsigned int gpio) return !!(in_be16(&iop->dat) & pin_mask); } -static void __cpm1_gpio16_set(struct of_mm_gpio_chip *mm_gc, u16 pin_mask, - int value) +static void __cpm1_gpio16_set(struct cpm1_gpio16_chip *cpm1_gc, u16 pin_mask, int value) { - struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); - struct cpm_ioport16 __iomem *iop = mm_gc->regs; + struct cpm_ioport16 __iomem *iop = cpm1_gc->regs; if (value) cpm1_gc->cpdata |= pin_mask; @@ -422,38 +419,35 @@ static void __cpm1_gpio16_set(struct of_mm_gpio_chip *mm_gc, u16 pin_mask, static void cpm1_gpio16_set(struct gpio_chip *gc, unsigned int gpio, int value) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); + struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc); unsigned long flags; u16 pin_mask = 1 << (15 - gpio); spin_lock_irqsave(&cpm1_gc->lock, flags); - __cpm1_gpio16_set(mm_gc, pin_mask, value); + __cpm1_gpio16_set(cpm1_gc, pin_mask, value); spin_unlock_irqrestore(&cpm1_gc->lock, flags); } static int cpm1_gpio16_to_irq(struct gpio_chip *gc, unsigned int gpio) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); + struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc); return cpm1_gc->irq[gpio] ? : -ENXIO; } static int cpm1_gpio16_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); - struct cpm_ioport16 __iomem *iop = mm_gc->regs; + struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc); + struct cpm_ioport16 __iomem *iop = cpm1_gc->regs; unsigned long flags; u16 pin_mask = 1 << (15 - gpio); spin_lock_irqsave(&cpm1_gc->lock, flags); setbits16(&iop->dir, pin_mask); - __cpm1_gpio16_set(mm_gc, pin_mask, val); + __cpm1_gpio16_set(cpm1_gc, pin_mask, val); spin_unlock_irqrestore(&cpm1_gc->lock, flags); @@ -462,9 +456,8 @@ static int cpm1_gpio16_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) static int cpm1_gpio16_dir_in(struct gpio_chip *gc, unsigned int gpio) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); - struct cpm_ioport16 __iomem *iop = mm_gc->regs; + struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(gc); + struct cpm_ioport16 __iomem *iop = cpm1_gc->regs; unsigned long flags; u16 pin_mask = 1 << (15 - gpio); @@ -481,11 +474,10 @@ int cpm1_gpiochip_add16(struct device *dev) { struct device_node *np = dev->of_node; struct cpm1_gpio16_chip *cpm1_gc; - struct of_mm_gpio_chip *mm_gc; struct gpio_chip *gc; u16 mask; - cpm1_gc = kzalloc(sizeof(*cpm1_gc), GFP_KERNEL); + cpm1_gc = devm_kzalloc(dev, sizeof(*cpm1_gc), GFP_KERNEL); if (!cpm1_gc) return -ENOMEM; @@ -499,10 +491,8 @@ int cpm1_gpiochip_add16(struct device *dev) cpm1_gc->irq[i] = irq_of_parse_and_map(np, j++); } - mm_gc = &cpm1_gc->mm_gc; - gc = &mm_gc->gc; - - mm_gc->save_regs = cpm1_gpio16_save_regs; + gc = &cpm1_gc->gc; + gc->base = -1; gc->ngpio = 16; gc->direction_input = cpm1_gpio16_dir_in; gc->direction_output = cpm1_gpio16_dir_out; @@ -512,30 +502,39 @@ int cpm1_gpiochip_add16(struct device *dev) gc->parent = dev; gc->owner = THIS_MODULE; - return of_mm_gpiochip_add_data(np, mm_gc, cpm1_gc); + gc->label = devm_kasprintf(dev, GFP_KERNEL, "%pOF", np); + if (!gc->label) + return -ENOMEM; + + cpm1_gc->regs = devm_of_iomap(dev, np, 0, NULL); + if (IS_ERR(cpm1_gc->regs)) + return PTR_ERR(cpm1_gc->regs); + + cpm1_gpio16_save_regs(cpm1_gc); + + return devm_gpiochip_add_data(dev, gc, cpm1_gc); } struct cpm1_gpio32_chip { - struct of_mm_gpio_chip mm_gc; + struct gpio_chip gc; + void __iomem *regs; spinlock_t lock; /* shadowed data register to clear/set bits safely */ u32 cpdata; }; -static void cpm1_gpio32_save_regs(struct of_mm_gpio_chip *mm_gc) +static void cpm1_gpio32_save_regs(struct cpm1_gpio32_chip *cpm1_gc) { - struct cpm1_gpio32_chip *cpm1_gc = - container_of(mm_gc, struct cpm1_gpio32_chip, mm_gc); - struct cpm_ioport32b __iomem *iop = mm_gc->regs; + struct cpm_ioport32b __iomem *iop = cpm1_gc->regs; cpm1_gc->cpdata = in_be32(&iop->dat); } static int cpm1_gpio32_get(struct gpio_chip *gc, unsigned int gpio) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm_ioport32b __iomem *iop = mm_gc->regs; + struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc); + struct cpm_ioport32b __iomem *iop = cpm1_gc->regs; u32 pin_mask; pin_mask = 1 << (31 - gpio); @@ -543,11 +542,9 @@ static int cpm1_gpio32_get(struct gpio_chip *gc, unsigned int gpio) return !!(in_be32(&iop->dat) & pin_mask); } -static void __cpm1_gpio32_set(struct of_mm_gpio_chip *mm_gc, u32 pin_mask, - int value) +static void __cpm1_gpio32_set(struct cpm1_gpio32_chip *cpm1_gc, u32 pin_mask, int value) { - struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); - struct cpm_ioport32b __iomem *iop = mm_gc->regs; + struct cpm_ioport32b __iomem *iop = cpm1_gc->regs; if (value) cpm1_gc->cpdata |= pin_mask; @@ -559,30 +556,28 @@ static void __cpm1_gpio32_set(struct of_mm_gpio_chip *mm_gc, u32 pin_mask, static void cpm1_gpio32_set(struct gpio_chip *gc, unsigned int gpio, int value) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); + struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc); unsigned long flags; u32 pin_mask = 1 << (31 - gpio); spin_lock_irqsave(&cpm1_gc->lock, flags); - __cpm1_gpio32_set(mm_gc, pin_mask, value); + __cpm1_gpio32_set(cpm1_gc, pin_mask, value); spin_unlock_irqrestore(&cpm1_gc->lock, flags); } static int cpm1_gpio32_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); - struct cpm_ioport32b __iomem *iop = mm_gc->regs; + struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc); + struct cpm_ioport32b __iomem *iop = cpm1_gc->regs; unsigned long flags; u32 pin_mask = 1 << (31 - gpio); spin_lock_irqsave(&cpm1_gc->lock, flags); setbits32(&iop->dir, pin_mask); - __cpm1_gpio32_set(mm_gc, pin_mask, val); + __cpm1_gpio32_set(cpm1_gc, pin_mask, val); spin_unlock_irqrestore(&cpm1_gc->lock, flags); @@ -591,9 +586,8 @@ static int cpm1_gpio32_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) static int cpm1_gpio32_dir_in(struct gpio_chip *gc, unsigned int gpio) { - struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); - struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); - struct cpm_ioport32b __iomem *iop = mm_gc->regs; + struct cpm1_gpio32_chip *cpm1_gc = gpiochip_get_data(gc); + struct cpm_ioport32b __iomem *iop = cpm1_gc->regs; unsigned long flags; u32 pin_mask = 1 << (31 - gpio); @@ -610,19 +604,16 @@ int cpm1_gpiochip_add32(struct device *dev) { struct device_node *np = dev->of_node; struct cpm1_gpio32_chip *cpm1_gc; - struct of_mm_gpio_chip *mm_gc; struct gpio_chip *gc; - cpm1_gc = kzalloc(sizeof(*cpm1_gc), GFP_KERNEL); + cpm1_gc = devm_kzalloc(dev, sizeof(*cpm1_gc), GFP_KERNEL); if (!cpm1_gc) return -ENOMEM; spin_lock_init(&cpm1_gc->lock); - mm_gc = &cpm1_gc->mm_gc; - gc = &mm_gc->gc; - - mm_gc->save_regs = cpm1_gpio32_save_regs; + gc = &cpm1_gc->gc; + gc->base = -1; gc->ngpio = 32; gc->direction_input = cpm1_gpio32_dir_in; gc->direction_output = cpm1_gpio32_dir_out; @@ -631,7 +622,17 @@ int cpm1_gpiochip_add32(struct device *dev) gc->parent = dev; gc->owner = THIS_MODULE; - return of_mm_gpiochip_add_data(np, mm_gc, cpm1_gc); + gc->label = devm_kasprintf(dev, GFP_KERNEL, "%pOF", np); + if (!gc->label) + return -ENOMEM; + + cpm1_gc->regs = devm_of_iomap(dev, np, 0, NULL); + if (IS_ERR(cpm1_gc->regs)) + return PTR_ERR(cpm1_gc->regs); + + cpm1_gpio32_save_regs(cpm1_gc); + + return devm_gpiochip_add_data(dev, gc, cpm1_gc); } #endif /* CONFIG_8xx_GPIO */ diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c index f381b177ea06..0b6365d85d11 100644 --- a/arch/powerpc/platforms/book3s/vas-api.c +++ b/arch/powerpc/platforms/book3s/vas-api.c @@ -464,7 +464,43 @@ static vm_fault_t vas_mmap_fault(struct vm_fault *vmf) return VM_FAULT_SIGBUS; } +/* + * During mmap() paste address, mapping VMA is saved in VAS window + * struct which is used to unmap during migration if the window is + * still open. But the user space can remove this mapping with + * munmap() before closing the window and the VMA address will + * be invalid. Set VAS window VMA to NULL in this function which + * is called before VMA free. + */ +static void vas_mmap_close(struct vm_area_struct *vma) +{ + struct file *fp = vma->vm_file; + struct coproc_instance *cp_inst = fp->private_data; + struct vas_window *txwin; + + /* Should not happen */ + if (!cp_inst || !cp_inst->txwin) { + pr_err("No attached VAS window for the paste address mmap\n"); + return; + } + + txwin = cp_inst->txwin; + /* + * task_ref.vma is set in coproc_mmap() during mmap paste + * address. So it has to be the same VMA that is getting freed. + */ + if (WARN_ON(txwin->task_ref.vma != vma)) { + pr_err("Invalid paste address mmaping\n"); + return; + } + + mutex_lock(&txwin->task_ref.mmap_mutex); + txwin->task_ref.vma = NULL; + mutex_unlock(&txwin->task_ref.mmap_mutex); +} + static const struct vm_operations_struct vas_vm_ops = { + .close = vas_mmap_close, .fault = vas_mmap_fault, }; diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c index 534cd159e9ab..29f1a0cc59cd 100644 --- a/arch/powerpc/platforms/pseries/iommu.c +++ b/arch/powerpc/platforms/pseries/iommu.c @@ -1650,7 +1650,8 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn) iommu_table_setparms_common(newtbl, pci->phb->bus->number, create.liobn, dynamic_addr, dynamic_len, page_shift, NULL, &iommu_table_lpar_multi_ops); - iommu_init_table(newtbl, pci->phb->node, start, end); + iommu_init_table(newtbl, pci->phb->node, + start >> page_shift, end >> page_shift); pci->table_group->tables[default_win_removed ? 0 : 1] = newtbl; @@ -2065,7 +2066,9 @@ static long spapr_tce_create_table(struct iommu_table_group *table_group, int nu offset, 1UL << window_shift, IOMMU_PAGE_SHIFT_4K, NULL, &iommu_table_lpar_multi_ops); - iommu_init_table(tbl, pci->phb->node, start, end); + iommu_init_table(tbl, pci->phb->node, + start >> IOMMU_PAGE_SHIFT_4K, + end >> IOMMU_PAGE_SHIFT_4K); table_group->tables[0] = tbl; @@ -2136,7 +2139,7 @@ static long spapr_tce_create_table(struct iommu_table_group *table_group, int nu /* New table for using DDW instead of the default DMA window */ iommu_table_setparms_common(tbl, pci->phb->bus->number, create.liobn, win_addr, 1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops); - iommu_init_table(tbl, pci->phb->node, start, end); + iommu_init_table(tbl, pci->phb->node, start >> page_shift, end >> page_shift); pci->table_group->tables[num] = tbl; set_iommu_table_base(&pdev->dev, tbl); diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c index f4e841a36458..268859e4df87 100644 --- a/arch/powerpc/xmon/xmon.c +++ b/arch/powerpc/xmon/xmon.c @@ -2623,9 +2623,9 @@ static void dump_one_paca(int cpu) printf("paca for cpu 0x%x @ %px:\n", cpu, p); - printf(" %-*s = %s\n", 25, "possible", cpu_possible(cpu) ? "yes" : "no"); - printf(" %-*s = %s\n", 25, "present", cpu_present(cpu) ? "yes" : "no"); - printf(" %-*s = %s\n", 25, "online", cpu_online(cpu) ? "yes" : "no"); + printf(" %-*s = %s\n", 25, "possible", str_yes_no(cpu_possible(cpu))); + printf(" %-*s = %s\n", 25, "present", str_yes_no(cpu_present(cpu))); + printf(" %-*s = %s\n", 25, "online", str_yes_no(cpu_online(cpu))); #define DUMP(paca, name, format) \ printf(" %-*s = "format"\t(0x%lx)\n", 25, #name, 18, paca->name, \ diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index d4a7ca0388c0..c736e349f222 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -146,9 +146,10 @@ config RISCV select HAVE_DYNAMIC_FTRACE if !XIP_KERNEL && MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE) select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_DYNAMIC_FTRACE_WITH_ARGS if HAVE_DYNAMIC_FTRACE + select HAVE_FTRACE_GRAPH_FUNC select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL select HAVE_FUNCTION_GRAPH_TRACER - select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_GRAPH_FREGS select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION select HAVE_EBPF_JIT if MMU select HAVE_GUP_FAST if MMU diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild index de13d5a234f8..bd5fc9403295 100644 --- a/arch/riscv/include/asm/Kbuild +++ b/arch/riscv/include/asm/Kbuild @@ -4,6 +4,7 @@ syscall-y += syscall_table_64.h generic-y += early_ioremap.h generic-y += flat.h +generic-y += fprobe.h generic-y += kvm_para.h generic-y += mmzone.h generic-y += mcs_spinlock.h diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index 3d66437a1029..c4721ce44ca4 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -168,6 +168,11 @@ static __always_inline unsigned long ftrace_regs_get_stack_pointer(const struct return arch_ftrace_regs(fregs)->sp; } +static __always_inline unsigned long ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->s0; +} + static __always_inline unsigned long ftrace_regs_get_argument(struct ftrace_regs *fregs, unsigned int n) { @@ -181,6 +186,11 @@ static __always_inline unsigned long ftrace_regs_get_return_value(const struct f return arch_ftrace_regs(fregs)->a0; } +static __always_inline unsigned long ftrace_regs_get_return_address(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->ra; +} + static __always_inline void ftrace_regs_set_return_value(struct ftrace_regs *fregs, unsigned long ret) { @@ -192,6 +202,20 @@ static __always_inline void ftrace_override_function_with_return(struct ftrace_r arch_ftrace_regs(fregs)->epc = arch_ftrace_regs(fregs)->ra; } +static __always_inline struct pt_regs * +ftrace_partial_regs(const struct ftrace_regs *fregs, struct pt_regs *regs) +{ + struct __arch_ftrace_regs *afregs = arch_ftrace_regs(fregs); + + memcpy(®s->a0, afregs->args, sizeof(afregs->args)); + regs->epc = afregs->epc; + regs->ra = afregs->ra; + regs->sp = afregs->sp; + regs->s0 = afregs->s0; + regs->t1 = afregs->t1; + return regs; +} + int ftrace_regs_query_register_offset(const char *name); void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, @@ -208,25 +232,4 @@ static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsi #endif /* CONFIG_DYNAMIC_FTRACE */ -#ifndef __ASSEMBLY__ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - unsigned long a1; - unsigned long a0; - unsigned long s0; - unsigned long ra; -}; - -static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->a0; -} - -static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->s0; -} -#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */ -#endif - #endif /* _ASM_RISCV_FTRACE_H */ diff --git a/arch/riscv/include/asm/kfence.h b/arch/riscv/include/asm/kfence.h index 7388edd88986..d08bf7fb3aee 100644 --- a/arch/riscv/include/asm/kfence.h +++ b/arch/riscv/include/asm/kfence.h @@ -22,7 +22,9 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect) else set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT)); - flush_tlb_kernel_range(addr, addr + PAGE_SIZE); + preempt_disable(); + local_flush_tlb_kernel_range(addr, addr + PAGE_SIZE); + preempt_enable(); return true; } diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 71aabc5c6713..125f5ecd9565 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -122,6 +122,7 @@ struct kernel_mapping { extern struct kernel_mapping kernel_map; extern phys_addr_t phys_ram_base; +extern unsigned long vmemmap_start_pfn; #define is_kernel_mapping(x) \ ((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size)) diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index d4e99eef90ac..050fdc49b5ad 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -87,7 +87,7 @@ * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. */ -#define vmemmap ((struct page *)VMEMMAP_START - (phys_ram_base >> PAGE_SHIFT)) +#define vmemmap ((struct page *)VMEMMAP_START - vmemmap_start_pfn) #define PCI_IO_SIZE SZ_16M #define PCI_IO_END VMEMMAP_START diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h index 6c82318065cf..3d250824178b 100644 --- a/arch/riscv/include/asm/sbi.h +++ b/arch/riscv/include/asm/sbi.h @@ -159,6 +159,7 @@ struct riscv_pmu_snapshot_data { }; #define RISCV_PMU_RAW_EVENT_MASK GENMASK_ULL(47, 0) +#define RISCV_PMU_PLAT_FW_EVENT_MASK GENMASK_ULL(61, 0) #define RISCV_PMU_RAW_EVENT_IDX 0x20000 #define RISCV_PLAT_FW_EVENT 0xFFFF diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h index e5121b89acea..52f11bfd0079 100644 --- a/arch/riscv/include/asm/spinlock.h +++ b/arch/riscv/include/asm/spinlock.h @@ -3,8 +3,11 @@ #ifndef __ASM_RISCV_SPINLOCK_H #define __ASM_RISCV_SPINLOCK_H -#ifdef CONFIG_RISCV_COMBO_SPINLOCKS +#ifdef CONFIG_QUEUED_SPINLOCKS #define _Q_PENDING_LOOPS (1 << 9) +#endif + +#ifdef CONFIG_RISCV_COMBO_SPINLOCKS #define __no_arch_spinlock_redefine #include <asm/ticket_spinlock.h> diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index c200d329d4bd..33a5a9f2a0d4 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -23,21 +23,21 @@ REG_S a0, TASK_TI_A0(tp) csrr a0, CSR_CAUSE /* Exclude IRQs */ - blt a0, zero, _new_vmalloc_restore_context_a0 + blt a0, zero, .Lnew_vmalloc_restore_context_a0 REG_S a1, TASK_TI_A1(tp) /* Only check new_vmalloc if we are in page/protection fault */ li a1, EXC_LOAD_PAGE_FAULT - beq a0, a1, _new_vmalloc_kernel_address + beq a0, a1, .Lnew_vmalloc_kernel_address li a1, EXC_STORE_PAGE_FAULT - beq a0, a1, _new_vmalloc_kernel_address + beq a0, a1, .Lnew_vmalloc_kernel_address li a1, EXC_INST_PAGE_FAULT - bne a0, a1, _new_vmalloc_restore_context_a1 + bne a0, a1, .Lnew_vmalloc_restore_context_a1 -_new_vmalloc_kernel_address: +.Lnew_vmalloc_kernel_address: /* Is it a kernel address? */ csrr a0, CSR_TVAL - bge a0, zero, _new_vmalloc_restore_context_a1 + bge a0, zero, .Lnew_vmalloc_restore_context_a1 /* Check if a new vmalloc mapping appeared that could explain the trap */ REG_S a2, TASK_TI_A2(tp) @@ -69,7 +69,7 @@ _new_vmalloc_kernel_address: /* Check the value of new_vmalloc for this cpu */ REG_L a2, 0(a0) and a2, a2, a1 - beq a2, zero, _new_vmalloc_restore_context + beq a2, zero, .Lnew_vmalloc_restore_context /* Atomically reset the current cpu bit in new_vmalloc */ amoxor.d a0, a1, (a0) @@ -83,11 +83,11 @@ _new_vmalloc_kernel_address: csrw CSR_SCRATCH, x0 sret -_new_vmalloc_restore_context: +.Lnew_vmalloc_restore_context: REG_L a2, TASK_TI_A2(tp) -_new_vmalloc_restore_context_a1: +.Lnew_vmalloc_restore_context_a1: REG_L a1, TASK_TI_A1(tp) -_new_vmalloc_restore_context_a0: +.Lnew_vmalloc_restore_context_a0: REG_L a0, TASK_TI_A0(tp) .endm @@ -278,6 +278,7 @@ SYM_CODE_START_NOALIGN(ret_from_exception) #else sret #endif +SYM_INNER_LABEL(ret_from_exception_end, SYM_L_GLOBAL) SYM_CODE_END(ret_from_exception) ASM_NOKPROBE(ret_from_exception) diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c index 8cb9b211611d..3524db5e4fa0 100644 --- a/arch/riscv/kernel/ftrace.c +++ b/arch/riscv/kernel/ftrace.c @@ -214,7 +214,22 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { - prepare_ftrace_return(&arch_ftrace_regs(fregs)->ra, ip, arch_ftrace_regs(fregs)->s0); + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long frame_pointer = arch_ftrace_regs(fregs)->s0; + unsigned long *parent = &arch_ftrace_regs(fregs)->ra; + unsigned long old; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + /* + * We don't suffer access faults, so no extra fault-recovery assembly + * is needed here. + */ + old = *parent; + + if (!function_graph_enter_regs(old, ip, frame_pointer, parent, fregs)) + *parent = return_hooker; } #else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ extern void ftrace_graph_call(void); diff --git a/arch/riscv/kernel/jump_label.c b/arch/riscv/kernel/jump_label.c index 6eee6f736f68..654ed159c830 100644 --- a/arch/riscv/kernel/jump_label.c +++ b/arch/riscv/kernel/jump_label.c @@ -36,9 +36,15 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry, insn = RISCV_INSN_NOP; } - mutex_lock(&text_mutex); - patch_insn_write(addr, &insn, sizeof(insn)); - mutex_unlock(&text_mutex); + if (early_boot_irqs_disabled) { + riscv_patch_in_stop_machine = 1; + patch_insn_write(addr, &insn, sizeof(insn)); + riscv_patch_in_stop_machine = 0; + } else { + mutex_lock(&text_mutex); + patch_insn_write(addr, &insn, sizeof(insn)); + mutex_unlock(&text_mutex); + } return true; } diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c index 3c830a6f7ef4..2306ce3e5f22 100644 --- a/arch/riscv/kernel/machine_kexec.c +++ b/arch/riscv/kernel/machine_kexec.c @@ -114,29 +114,6 @@ void machine_shutdown(void) #endif } -static void machine_kexec_mask_interrupts(void) -{ - unsigned int i; - struct irq_desc *desc; - - for_each_irq_desc(i, desc) { - struct irq_chip *chip; - - chip = irq_desc_get_chip(desc); - if (!chip) - continue; - - if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data)) - chip->irq_eoi(&desc->irq_data); - - if (chip->irq_mask) - chip->irq_mask(&desc->irq_data); - - if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data)) - chip->irq_disable(&desc->irq_data); - } -} - /* * machine_crash_shutdown - Prepare to kexec after a kernel crash * diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S index 3a42f6287909..068168046e0e 100644 --- a/arch/riscv/kernel/mcount.S +++ b/arch/riscv/kernel/mcount.S @@ -12,6 +12,8 @@ #include <asm/asm-offsets.h> #include <asm/ftrace.h> +#define ABI_SIZE_ON_STACK 80 + .text .macro SAVE_ABI_STATE @@ -26,12 +28,12 @@ * register if a0 was not saved. */ .macro SAVE_RET_ABI_STATE - addi sp, sp, -4*SZREG - REG_S s0, 2*SZREG(sp) - REG_S ra, 3*SZREG(sp) - REG_S a0, 1*SZREG(sp) - REG_S a1, 0*SZREG(sp) - addi s0, sp, 4*SZREG + addi sp, sp, -ABI_SIZE_ON_STACK + REG_S ra, 1*SZREG(sp) + REG_S s0, 8*SZREG(sp) + REG_S a0, 10*SZREG(sp) + REG_S a1, 11*SZREG(sp) + addi s0, sp, ABI_SIZE_ON_STACK .endm .macro RESTORE_ABI_STATE @@ -41,11 +43,11 @@ .endm .macro RESTORE_RET_ABI_STATE - REG_L ra, 3*SZREG(sp) - REG_L s0, 2*SZREG(sp) - REG_L a0, 1*SZREG(sp) - REG_L a1, 0*SZREG(sp) - addi sp, sp, 4*SZREG + REG_L ra, 1*SZREG(sp) + REG_L s0, 8*SZREG(sp) + REG_L a0, 10*SZREG(sp) + REG_L a1, 11*SZREG(sp) + addi sp, sp, ABI_SIZE_ON_STACK .endm SYM_TYPED_FUNC_START(ftrace_stub) diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c index 1cd461f3d872..47d0ebeec93c 100644 --- a/arch/riscv/kernel/module.c +++ b/arch/riscv/kernel/module.c @@ -23,7 +23,7 @@ struct used_bucket { struct relocation_head { struct hlist_node node; - struct list_head *rel_entry; + struct list_head rel_entry; void *location; }; @@ -634,7 +634,7 @@ process_accumulated_relocations(struct module *me, location = rel_head_iter->location; list_for_each_entry_safe(rel_entry_iter, rel_entry_iter_tmp, - rel_head_iter->rel_entry, + &rel_head_iter->rel_entry, head) { curr_type = rel_entry_iter->type; reloc_handlers[curr_type].reloc_handler( @@ -704,16 +704,7 @@ static int add_relocation_to_accumulate(struct module *me, int type, return -ENOMEM; } - rel_head->rel_entry = - kmalloc(sizeof(struct list_head), GFP_KERNEL); - - if (!rel_head->rel_entry) { - kfree(entry); - kfree(rel_head); - return -ENOMEM; - } - - INIT_LIST_HEAD(rel_head->rel_entry); + INIT_LIST_HEAD(&rel_head->rel_entry); rel_head->location = location; INIT_HLIST_NODE(&rel_head->node); if (!current_head->first) { @@ -722,7 +713,6 @@ static int add_relocation_to_accumulate(struct module *me, int type, if (!bucket) { kfree(entry); - kfree(rel_head->rel_entry); kfree(rel_head); return -ENOMEM; } @@ -735,7 +725,7 @@ static int add_relocation_to_accumulate(struct module *me, int type, } /* Add relocation to head of discovered rel_head */ - list_add_tail(&entry->head, rel_head->rel_entry); + list_add_tail(&entry->head, &rel_head->rel_entry); return 0; } diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c index 380a0e8cecc0..c0738d6c6498 100644 --- a/arch/riscv/kernel/probes/kprobes.c +++ b/arch/riscv/kernel/probes/kprobes.c @@ -30,7 +30,7 @@ static void __kprobes arch_prepare_ss_slot(struct kprobe *p) p->ainsn.api.restore = (unsigned long)p->addr + len; patch_text_nosync(p->ainsn.api.insn, &p->opcode, len); - patch_text_nosync(p->ainsn.api.insn + len, &insn, GET_INSN_LENGTH(insn)); + patch_text_nosync((void *)p->ainsn.api.insn + len, &insn, GET_INSN_LENGTH(insn)); } static void __kprobes arch_prepare_simulate(struct kprobe *p) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 016b48fcd6f2..45010e71df86 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -227,7 +227,7 @@ static void __init init_resources(void) static void __init parse_dtb(void) { /* Early scan of device tree from init memory */ - if (early_init_dt_scan(dtb_early_va, __pa(dtb_early_va))) { + if (early_init_dt_scan(dtb_early_va, dtb_early_pa)) { const char *name = of_flat_dt_get_machine_name(); if (name) { diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 153a2db4c5fa..d4355c770c36 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -17,6 +17,7 @@ #ifdef CONFIG_FRAME_POINTER extern asmlinkage void handle_exception(void); +extern unsigned long ret_from_exception_end; static inline int fp_is_valid(unsigned long fp, unsigned long sp) { @@ -71,7 +72,8 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, fp = frame->fp; pc = ftrace_graph_ret_addr(current, &graph_idx, frame->ra, &frame->ra); - if (pc == (unsigned long)handle_exception) { + if (pc >= (unsigned long)handle_exception && + pc < (unsigned long)&ret_from_exception_end) { if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc))) break; diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 51ebfd23e007..8ff8e8b36524 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -35,7 +35,7 @@ int show_unhandled_signals = 1; -static DEFINE_SPINLOCK(die_lock); +static DEFINE_RAW_SPINLOCK(die_lock); static int copy_code(struct pt_regs *regs, u16 *val, const u16 *insns) { @@ -81,7 +81,7 @@ void die(struct pt_regs *regs, const char *str) oops_enter(); - spin_lock_irqsave(&die_lock, flags); + raw_spin_lock_irqsave(&die_lock, flags); console_verbose(); bust_spinlocks(1); @@ -100,7 +100,7 @@ void die(struct pt_regs *regs, const char *str) bust_spinlocks(0); add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); - spin_unlock_irqrestore(&die_lock, flags); + raw_spin_unlock_irqrestore(&die_lock, flags); oops_exit(); if (in_interrupt()) diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c index dcced4db7fe8..19afd1f23537 100644 --- a/arch/riscv/kvm/aia.c +++ b/arch/riscv/kvm/aia.c @@ -590,7 +590,7 @@ void kvm_riscv_aia_enable(void) csr_set(CSR_HIE, BIT(IRQ_S_GEXT)); /* Enable IRQ filtering for overflow interrupt only if sscofpmf is present */ if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSCOFPMF)) - csr_write(CSR_HVIEN, BIT(IRQ_PMU_OVF)); + csr_set(CSR_HVIEN, BIT(IRQ_PMU_OVF)); } void kvm_riscv_aia_disable(void) diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 0e8c20adcd98..8d167e09f1fe 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -33,6 +33,7 @@ #include <asm/pgtable.h> #include <asm/sections.h> #include <asm/soc.h> +#include <asm/sparsemem.h> #include <asm/tlbflush.h> #include "../kernel/head.h" @@ -62,6 +63,13 @@ EXPORT_SYMBOL(pgtable_l5_enabled); phys_addr_t phys_ram_base __ro_after_init; EXPORT_SYMBOL(phys_ram_base); +#ifdef CONFIG_SPARSEMEM_VMEMMAP +#define VMEMMAP_ADDR_ALIGN (1ULL << SECTION_SIZE_BITS) + +unsigned long vmemmap_start_pfn __ro_after_init; +EXPORT_SYMBOL(vmemmap_start_pfn); +#endif + unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss; EXPORT_SYMBOL(empty_zero_page); @@ -240,8 +248,12 @@ static void __init setup_bootmem(void) * Make sure we align the start of the memory on a PMD boundary so that * at worst, we map the linear mapping with PMD mappings. */ - if (!IS_ENABLED(CONFIG_XIP_KERNEL)) + if (!IS_ENABLED(CONFIG_XIP_KERNEL)) { phys_ram_base = memblock_start_of_DRAM() & PMD_MASK; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT; +#endif + } /* * In 64-bit, any use of __va/__pa before this point is wrong as we @@ -1101,6 +1113,9 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom); phys_ram_base = CONFIG_PHYS_RAM_BASE; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT; +#endif kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE; kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_start); @@ -1566,7 +1581,7 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) pmd_clear(pmd); } -static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) +static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud, bool is_vmemmap) { struct page *page = pud_page(*pud); struct ptdesc *ptdesc = page_ptdesc(page); @@ -1579,7 +1594,8 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) return; } - pagetable_pmd_dtor(ptdesc); + if (!is_vmemmap) + pagetable_pmd_dtor(ptdesc); if (PageReserved(page)) free_reserved_page(page); else @@ -1703,7 +1719,7 @@ static void __meminit remove_pud_mapping(pud_t *pud_base, unsigned long addr, un remove_pmd_mapping(pmd_base, addr, next, is_vmemmap, altmap); if (pgtable_l4_enabled) - free_pmd_table(pmd_base, pudp); + free_pmd_table(pmd_base, pudp, is_vmemmap); } } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 0077969170e8..5cbbb7daed44 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -183,16 +183,18 @@ config S390 select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_ARGS + select HAVE_FTRACE_REGS_HAVING_PT_REGS select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_EBPF_JIT if HAVE_MARCH_Z196_FEATURES select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_GUP_FAST select HAVE_FENTRY + select HAVE_FTRACE_GRAPH_FUNC select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_ARG_ACCESS_API select HAVE_FUNCTION_ERROR_INJECTION - select HAVE_FUNCTION_GRAPH_RETVAL + select HAVE_FUNCTION_GRAPH_FREGS select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS @@ -233,6 +235,7 @@ config S390 select HAVE_VIRT_CPU_ACCOUNTING_IDLE select IOMMU_HELPER if PCI select IOMMU_SUPPORT if PCI + select KASAN_VMALLOC if KASAN select LOCK_MM_AND_FIND_VMA select MMU_GATHER_MERGE_VMAS select MMU_GATHER_NO_GATHER @@ -255,6 +258,7 @@ config S390 select USER_STACKTRACE_SUPPORT select VDSO_GETRANDOM select VIRT_CPU_ACCOUNTING + select VMAP_STACK select ZONE_DMA # Note: keep the above list sorted alphabetically @@ -688,32 +692,6 @@ config MAX_PHYSMEM_BITS Increasing the number of bits also increases the kernel image size. By default 46 bits (64TB) are supported. -config CHECK_STACK - def_bool y - depends on !VMAP_STACK - prompt "Detect kernel stack overflow" - help - This option enables the compiler option -mstack-guard and - -mstack-size if they are available. If the compiler supports them - it will emit additional code to each function prolog to trigger - an illegal operation if the kernel stack is about to overflow. - - Say N if you are unsure. - -config STACK_GUARD - int "Size of the guard area (128-1024)" - range 128 1024 - depends on CHECK_STACK - default "256" - help - This allows you to specify the size of the guard area at the lower - end of the kernel stack. If the kernel stack points into the guard - area on function entry an illegal operation is triggered. The size - needs to be a power of 2. Please keep in mind that the size of an - interrupt frame is 184 bytes for 31 bit and 328 bytes on 64 bit. - The minimum size for the stack guard should be 256 for 31 bit and - 512 for 64 bit. - endmenu menu "I/O subsystem" diff --git a/arch/s390/Makefile b/arch/s390/Makefile index 7fd57398221e..3f25498dac65 100644 --- a/arch/s390/Makefile +++ b/arch/s390/Makefile @@ -72,15 +72,6 @@ cflags-$(CONFIG_FRAME_POINTER) += -fno-optimize-sibling-calls KBUILD_AFLAGS_DECOMPRESSOR += $(aflags-y) KBUILD_CFLAGS_DECOMPRESSOR += $(cflags-y) -ifneq ($(call cc-option,-mstack-size=8192 -mstack-guard=128),) - CC_FLAGS_CHECK_STACK := -mstack-size=$(STACK_SIZE) - ifeq ($(call cc-option,-mstack-size=8192),) - CC_FLAGS_CHECK_STACK += -mstack-guard=$(CONFIG_STACK_GUARD) - endif - export CC_FLAGS_CHECK_STACK - cflags-$(CONFIG_CHECK_STACK) += $(CC_FLAGS_CHECK_STACK) -endif - ifdef CONFIG_EXPOLINE ifdef CONFIG_EXPOLINE_EXTERN CC_FLAGS_EXPOLINE := -mindirect-branch=thunk-extern diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h index 7521a9d75fa2..56244fe78182 100644 --- a/arch/s390/boot/boot.h +++ b/arch/s390/boot/boot.h @@ -13,7 +13,6 @@ struct machine_info { unsigned char has_edat1 : 1; unsigned char has_edat2 : 1; - unsigned char has_nx : 1; }; struct vmlinux_info { diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c index abe6e6c0ab98..e6b06692ddc8 100644 --- a/arch/s390/boot/startup.c +++ b/arch/s390/boot/startup.c @@ -30,6 +30,9 @@ unsigned long __bootdata_preserved(vmemmap_size); unsigned long __bootdata_preserved(MODULES_VADDR); unsigned long __bootdata_preserved(MODULES_END); unsigned long __bootdata_preserved(max_mappable); +unsigned long __bootdata_preserved(page_noexec_mask); +unsigned long __bootdata_preserved(segment_noexec_mask); +unsigned long __bootdata_preserved(region_noexec_mask); int __bootdata_preserved(relocate_lowcore); u64 __bootdata_preserved(stfle_fac_list[16]); @@ -51,8 +54,14 @@ static void detect_facilities(void) } if (test_facility(78)) machine.has_edat2 = 1; - if (test_facility(130)) - machine.has_nx = 1; + page_noexec_mask = -1UL; + segment_noexec_mask = -1UL; + region_noexec_mask = -1UL; + if (!test_facility(130)) { + page_noexec_mask &= ~_PAGE_NOEXEC; + segment_noexec_mask &= ~_SEGMENT_ENTRY_NOEXEC; + region_noexec_mask &= ~_REGION_ENTRY_NOEXEC; + } } static int cmma_test_essa(void) @@ -234,6 +243,8 @@ static unsigned long get_vmem_size(unsigned long identity_size, vsize = round_up(SZ_2G + max_mappable, rte_size) + round_up(vmemmap_size, rte_size) + FIXMAP_SIZE + MODULES_LEN + KASLR_LEN; + if (IS_ENABLED(CONFIG_KMSAN)) + vsize += MODULES_LEN * 2; return size_add(vsize, vmalloc_size); } diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 145035f84a0e..881a1ece422f 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -63,13 +63,10 @@ static void kasan_populate_shadow(unsigned long kernel_start, unsigned long kern pud_t pud_z = __pud(__pa(kasan_early_shadow_pmd) | _REGION3_ENTRY); p4d_t p4d_z = __p4d(__pa(kasan_early_shadow_pud) | _REGION2_ENTRY); unsigned long memgap_start = 0; - unsigned long untracked_end; unsigned long start, end; int i; pte_z = __pte(__pa(kasan_early_shadow_page) | pgprot_val(PAGE_KERNEL_RO)); - if (!machine.has_nx) - pte_z = clear_pte_bit(pte_z, __pgprot(_PAGE_NOEXEC)); crst_table_init((unsigned long *)kasan_early_shadow_p4d, p4d_val(p4d_z)); crst_table_init((unsigned long *)kasan_early_shadow_pud, pud_val(pud_z)); crst_table_init((unsigned long *)kasan_early_shadow_pmd, pmd_val(pmd_z)); @@ -93,15 +90,10 @@ static void kasan_populate_shadow(unsigned long kernel_start, unsigned long kern kasan_populate(kernel_start + TEXT_OFFSET, kernel_end, POPULATE_KASAN_MAP_SHADOW); kasan_populate(0, (unsigned long)__identity_va(0), POPULATE_KASAN_ZERO_SHADOW); kasan_populate(AMODE31_START, AMODE31_END, POPULATE_KASAN_ZERO_SHADOW); - if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { - untracked_end = VMALLOC_START; - /* shallowly populate kasan shadow for vmalloc and modules */ - kasan_populate(VMALLOC_START, MODULES_END, POPULATE_KASAN_SHALLOW); - } else { - untracked_end = MODULES_VADDR; - } + /* shallowly populate kasan shadow for vmalloc and modules */ + kasan_populate(VMALLOC_START, MODULES_END, POPULATE_KASAN_SHALLOW); /* populate kasan shadow for untracked memory */ - kasan_populate((unsigned long)__identity_va(ident_map_size), untracked_end, + kasan_populate((unsigned long)__identity_va(ident_map_size), VMALLOC_START, POPULATE_KASAN_ZERO_SHADOW); kasan_populate(kernel_end, _REGION1_SIZE, POPULATE_KASAN_ZERO_SHADOW); } @@ -300,13 +292,11 @@ static void pgtable_pte_populate(pmd_t *pmd, unsigned long addr, unsigned long e continue; entry = __pte(_pa(addr, PAGE_SIZE, mode)); entry = set_pte_bit(entry, PAGE_KERNEL); - if (!machine.has_nx) - entry = clear_pte_bit(entry, __pgprot(_PAGE_NOEXEC)); set_pte(pte, entry); pages++; } } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_4K, pages); } @@ -326,8 +316,6 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e if (can_large_pmd(pmd, addr, next, mode)) { entry = __pmd(_pa(addr, _SEGMENT_SIZE, mode)); entry = set_pmd_bit(entry, SEGMENT_KERNEL); - if (!machine.has_nx) - entry = clear_pmd_bit(entry, __pgprot(_SEGMENT_ENTRY_NOEXEC)); set_pmd(pmd, entry); pages++; continue; @@ -339,7 +327,7 @@ static void pgtable_pmd_populate(pud_t *pud, unsigned long addr, unsigned long e } pgtable_pte_populate(pmd, addr, next, mode); } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_1M, pages); } @@ -359,8 +347,6 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e if (can_large_pud(pud, addr, next, mode)) { entry = __pud(_pa(addr, _REGION3_SIZE, mode)); entry = set_pud_bit(entry, REGION3_KERNEL); - if (!machine.has_nx) - entry = clear_pud_bit(entry, __pgprot(_REGION_ENTRY_NOEXEC)); set_pud(pud, entry); pages++; continue; @@ -372,7 +358,7 @@ static void pgtable_pud_populate(p4d_t *p4d, unsigned long addr, unsigned long e } pgtable_pmd_populate(pud, addr, next, mode); } - if (mode == POPULATE_DIRECT) + if (mode == POPULATE_IDENTITY) update_page_count(PG_DIRECT_MAP_2G, pages); } diff --git a/arch/s390/configs/kasan.config b/arch/s390/configs/kasan.config index 84c2b551e992..cefbe2ba1228 100644 --- a/arch/s390/configs/kasan.config +++ b/arch/s390/configs/kasan.config @@ -1,4 +1,4 @@ # Help: Enable KASan for debugging CONFIG_KASAN=y CONFIG_KASAN_INLINE=y -CONFIG_KASAN_VMALLOC=y +CONFIG_KERNEL_IMAGE_BASE=0x7FFFE0000000 diff --git a/arch/s390/include/asm/abs_lowcore.h b/arch/s390/include/asm/abs_lowcore.h index d20df8c923fc..004d17ea05cf 100644 --- a/arch/s390/include/asm/abs_lowcore.h +++ b/arch/s390/include/asm/abs_lowcore.h @@ -2,7 +2,7 @@ #ifndef _ASM_S390_ABS_LOWCORE_H #define _ASM_S390_ABS_LOWCORE_H -#include <asm/sections.h> +#include <linux/smp.h> #include <asm/lowcore.h> #define ABS_LOWCORE_MAP_SIZE (NR_CPUS * sizeof(struct lowcore)) @@ -25,7 +25,7 @@ static inline void put_abs_lowcore(struct lowcore *lc) put_cpu(); } -extern int __bootdata_preserved(relocate_lowcore); +extern int relocate_lowcore; static inline int have_relocated_lowcore(void) { diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h index 6723fca64018..b36dd6a1d652 100644 --- a/arch/s390/include/asm/atomic.h +++ b/arch/s390/include/asm/atomic.h @@ -17,13 +17,13 @@ static __always_inline int arch_atomic_read(const atomic_t *v) { - return __atomic_read(v); + return __atomic_read(&v->counter); } #define arch_atomic_read arch_atomic_read static __always_inline void arch_atomic_set(atomic_t *v, int i) { - __atomic_set(v, i); + __atomic_set(&v->counter, i); } #define arch_atomic_set arch_atomic_set @@ -45,6 +45,36 @@ static __always_inline void arch_atomic_add(int i, atomic_t *v) } #define arch_atomic_add arch_atomic_add +static __always_inline void arch_atomic_inc(atomic_t *v) +{ + __atomic_add_const(1, &v->counter); +} +#define arch_atomic_inc arch_atomic_inc + +static __always_inline void arch_atomic_dec(atomic_t *v) +{ + __atomic_add_const(-1, &v->counter); +} +#define arch_atomic_dec arch_atomic_dec + +static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) +{ + return __atomic_add_and_test_barrier(-i, &v->counter); +} +#define arch_atomic_sub_and_test arch_atomic_sub_and_test + +static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) +{ + return __atomic_add_const_and_test_barrier(-1, &v->counter); +} +#define arch_atomic_dec_and_test arch_atomic_dec_and_test + +static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) +{ + return __atomic_add_const_and_test_barrier(1, &v->counter); +} +#define arch_atomic_inc_and_test arch_atomic_inc_and_test + #define arch_atomic_sub(_i, _v) arch_atomic_add(-(int)(_i), _v) #define arch_atomic_sub_return(_i, _v) arch_atomic_add_return(-(int)(_i), _v) #define arch_atomic_fetch_sub(_i, _v) arch_atomic_fetch_add(-(int)(_i), _v) @@ -94,13 +124,13 @@ static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int n static __always_inline s64 arch_atomic64_read(const atomic64_t *v) { - return __atomic64_read(v); + return __atomic64_read((long *)&v->counter); } #define arch_atomic64_read arch_atomic64_read static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i) { - __atomic64_set(v, i); + __atomic64_set((long *)&v->counter, i); } #define arch_atomic64_set arch_atomic64_set @@ -122,6 +152,36 @@ static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v) } #define arch_atomic64_add arch_atomic64_add +static __always_inline void arch_atomic64_inc(atomic64_t *v) +{ + __atomic64_add_const(1, (long *)&v->counter); +} +#define arch_atomic64_inc arch_atomic64_inc + +static __always_inline void arch_atomic64_dec(atomic64_t *v) +{ + __atomic64_add_const(-1, (long *)&v->counter); +} +#define arch_atomic64_dec arch_atomic64_dec + +static __always_inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v) +{ + return __atomic64_add_and_test_barrier(-i, (long *)&v->counter); +} +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test + +static __always_inline bool arch_atomic64_dec_and_test(atomic64_t *v) +{ + return __atomic64_add_const_and_test_barrier(-1, (long *)&v->counter); +} +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test + +static __always_inline bool arch_atomic64_inc_and_test(atomic64_t *v) +{ + return __atomic64_add_const_and_test_barrier(1, (long *)&v->counter); +} +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test + static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 new) { return arch_xchg(&v->counter, new); diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h index 1d6b2056fad8..585678bbcd7a 100644 --- a/arch/s390/include/asm/atomic_ops.h +++ b/arch/s390/include/asm/atomic_ops.h @@ -10,50 +10,51 @@ #include <linux/limits.h> #include <asm/march.h> +#include <asm/asm.h> -static __always_inline int __atomic_read(const atomic_t *v) +static __always_inline int __atomic_read(const int *ptr) { - int c; + int val; asm volatile( - " l %[c],%[counter]\n" - : [c] "=d" (c) : [counter] "R" (v->counter)); - return c; + " l %[val],%[ptr]\n" + : [val] "=d" (val) : [ptr] "R" (*ptr)); + return val; } -static __always_inline void __atomic_set(atomic_t *v, int i) +static __always_inline void __atomic_set(int *ptr, int val) { - if (__builtin_constant_p(i) && i >= S16_MIN && i <= S16_MAX) { + if (__builtin_constant_p(val) && val >= S16_MIN && val <= S16_MAX) { asm volatile( - " mvhi %[counter], %[i]\n" - : [counter] "=Q" (v->counter) : [i] "K" (i)); + " mvhi %[ptr],%[val]\n" + : [ptr] "=Q" (*ptr) : [val] "K" (val)); } else { asm volatile( - " st %[i],%[counter]\n" - : [counter] "=R" (v->counter) : [i] "d" (i)); + " st %[val],%[ptr]\n" + : [ptr] "=R" (*ptr) : [val] "d" (val)); } } -static __always_inline s64 __atomic64_read(const atomic64_t *v) +static __always_inline long __atomic64_read(const long *ptr) { - s64 c; + long val; asm volatile( - " lg %[c],%[counter]\n" - : [c] "=d" (c) : [counter] "RT" (v->counter)); - return c; + " lg %[val],%[ptr]\n" + : [val] "=d" (val) : [ptr] "RT" (*ptr)); + return val; } -static __always_inline void __atomic64_set(atomic64_t *v, s64 i) +static __always_inline void __atomic64_set(long *ptr, long val) { - if (__builtin_constant_p(i) && i >= S16_MIN && i <= S16_MAX) { + if (__builtin_constant_p(val) && val >= S16_MIN && val <= S16_MAX) { asm volatile( - " mvghi %[counter], %[i]\n" - : [counter] "=Q" (v->counter) : [i] "K" (i)); + " mvghi %[ptr],%[val]\n" + : [ptr] "=Q" (*ptr) : [val] "K" (val)); } else { asm volatile( - " stg %[i],%[counter]\n" - : [counter] "=RT" (v->counter) : [i] "d" (i)); + " stg %[val],%[ptr]\n" + : [ptr] "=RT" (*ptr) : [val] "d" (val)); } } @@ -73,7 +74,7 @@ static __always_inline op_type op_name(op_type val, op_type *ptr) \ } \ #define __ATOMIC_OPS(op_name, op_type, op_string) \ - __ATOMIC_OP(op_name, op_type, op_string, "\n") \ + __ATOMIC_OP(op_name, op_type, op_string, "") \ __ATOMIC_OP(op_name##_barrier, op_type, op_string, "bcr 14,0\n") __ATOMIC_OPS(__atomic_add, int, "laa") @@ -99,7 +100,7 @@ static __always_inline void op_name(op_type val, op_type *ptr) \ } #define __ATOMIC_CONST_OPS(op_name, op_type, op_string) \ - __ATOMIC_CONST_OP(op_name, op_type, op_string, "\n") \ + __ATOMIC_CONST_OP(op_name, op_type, op_string, "") \ __ATOMIC_CONST_OP(op_name##_barrier, op_type, op_string, "bcr 14,0\n") __ATOMIC_CONST_OPS(__atomic_add_const, int, "asi") @@ -169,4 +170,76 @@ __ATOMIC64_OPS(__atomic64_xor, "xgr") #endif /* MARCH_HAS_Z196_FEATURES */ +#if defined(MARCH_HAS_Z196_FEATURES) && defined(__HAVE_ASM_FLAG_OUTPUTS__) + +#define __ATOMIC_TEST_OP(op_name, op_type, op_string, op_barrier) \ +static __always_inline bool op_name(op_type val, op_type *ptr) \ +{ \ + op_type tmp; \ + int cc; \ + \ + asm volatile( \ + op_string " %[tmp],%[val],%[ptr]\n" \ + op_barrier \ + : "=@cc" (cc), [tmp] "=d" (tmp), [ptr] "+QS" (*ptr) \ + : [val] "d" (val) \ + : "memory"); \ + return (cc == 0) || (cc == 2); \ +} \ + +#define __ATOMIC_TEST_OPS(op_name, op_type, op_string) \ + __ATOMIC_TEST_OP(op_name, op_type, op_string, "") \ + __ATOMIC_TEST_OP(op_name##_barrier, op_type, op_string, "bcr 14,0\n") + +__ATOMIC_TEST_OPS(__atomic_add_and_test, int, "laal") +__ATOMIC_TEST_OPS(__atomic64_add_and_test, long, "laalg") + +#undef __ATOMIC_TEST_OPS +#undef __ATOMIC_TEST_OP + +#define __ATOMIC_CONST_TEST_OP(op_name, op_type, op_string, op_barrier) \ +static __always_inline bool op_name(op_type val, op_type *ptr) \ +{ \ + int cc; \ + \ + asm volatile( \ + op_string " %[ptr],%[val]\n" \ + op_barrier \ + : "=@cc" (cc), [ptr] "+QS" (*ptr) \ + : [val] "i" (val) \ + : "memory"); \ + return (cc == 0) || (cc == 2); \ +} + +#define __ATOMIC_CONST_TEST_OPS(op_name, op_type, op_string) \ + __ATOMIC_CONST_TEST_OP(op_name, op_type, op_string, "") \ + __ATOMIC_CONST_TEST_OP(op_name##_barrier, op_type, op_string, "bcr 14,0\n") + +__ATOMIC_CONST_TEST_OPS(__atomic_add_const_and_test, int, "alsi") +__ATOMIC_CONST_TEST_OPS(__atomic64_add_const_and_test, long, "algsi") + +#undef __ATOMIC_CONST_TEST_OPS +#undef __ATOMIC_CONST_TEST_OP + +#else /* defined(MARCH_HAS_Z196_FEATURES) && defined(__HAVE_ASM_FLAG_OUTPUTS__) */ + +#define __ATOMIC_TEST_OP(op_name, op_func, op_type) \ +static __always_inline bool op_name(op_type val, op_type *ptr) \ +{ \ + return op_func(val, ptr) == -val; \ +} + +__ATOMIC_TEST_OP(__atomic_add_and_test, __atomic_add, int) +__ATOMIC_TEST_OP(__atomic_add_and_test_barrier, __atomic_add_barrier, int) +__ATOMIC_TEST_OP(__atomic_add_const_and_test, __atomic_add, int) +__ATOMIC_TEST_OP(__atomic_add_const_and_test_barrier, __atomic_add_barrier, int) +__ATOMIC_TEST_OP(__atomic64_add_and_test, __atomic64_add, long) +__ATOMIC_TEST_OP(__atomic64_add_and_test_barrier, __atomic64_add_barrier, long) +__ATOMIC_TEST_OP(__atomic64_add_const_and_test, __atomic64_add, long) +__ATOMIC_TEST_OP(__atomic64_add_const_and_test_barrier, __atomic64_add_barrier, long) + +#undef __ATOMIC_TEST_OP + +#endif /* defined(MARCH_HAS_Z196_FEATURES) && defined(__HAVE_ASM_FLAG_OUTPUTS__) */ + #endif /* __ARCH_S390_ATOMIC_OPS__ */ diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 54a079cd39ed..15aa64e3020e 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -36,184 +36,41 @@ #include <linux/typecheck.h> #include <linux/compiler.h> #include <linux/types.h> -#include <asm/atomic_ops.h> -#include <asm/barrier.h> - -#define __BITOPS_WORDS(bits) (((bits) + BITS_PER_LONG - 1) / BITS_PER_LONG) - -static inline unsigned long * -__bitops_word(unsigned long nr, const volatile unsigned long *ptr) -{ - unsigned long addr; - - addr = (unsigned long)ptr + ((nr ^ (nr & (BITS_PER_LONG - 1))) >> 3); - return (unsigned long *)addr; -} - -static inline unsigned long __bitops_mask(unsigned long nr) -{ - return 1UL << (nr & (BITS_PER_LONG - 1)); -} - -static __always_inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr) -{ - unsigned long *addr = __bitops_word(nr, ptr); - unsigned long mask = __bitops_mask(nr); - - __atomic64_or(mask, (long *)addr); -} - -static __always_inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr) -{ - unsigned long *addr = __bitops_word(nr, ptr); - unsigned long mask = __bitops_mask(nr); - - __atomic64_and(~mask, (long *)addr); -} - -static __always_inline void arch_change_bit(unsigned long nr, - volatile unsigned long *ptr) -{ - unsigned long *addr = __bitops_word(nr, ptr); - unsigned long mask = __bitops_mask(nr); - - __atomic64_xor(mask, (long *)addr); -} - -static inline bool arch_test_and_set_bit(unsigned long nr, - volatile unsigned long *ptr) -{ - unsigned long *addr = __bitops_word(nr, ptr); - unsigned long mask = __bitops_mask(nr); - unsigned long old; - - old = __atomic64_or_barrier(mask, (long *)addr); - return old & mask; -} - -static inline bool arch_test_and_clear_bit(unsigned long nr, - volatile unsigned long *ptr) -{ - unsigned long *addr = __bitops_word(nr, ptr); - unsigned long mask = __bitops_mask(nr); - unsigned long old; - - old = __atomic64_and_barrier(~mask, (long *)addr); - return old & mask; -} - -static inline bool arch_test_and_change_bit(unsigned long nr, - volatile unsigned long *ptr) -{ - unsigned long *addr = __bitops_word(nr, ptr); - unsigned long mask = __bitops_mask(nr); - unsigned long old; - - old = __atomic64_xor_barrier(mask, (long *)addr); - return old & mask; -} - -static __always_inline void -arch___set_bit(unsigned long nr, volatile unsigned long *addr) -{ - unsigned long *p = __bitops_word(nr, addr); - unsigned long mask = __bitops_mask(nr); - - *p |= mask; -} - -static __always_inline void -arch___clear_bit(unsigned long nr, volatile unsigned long *addr) -{ - unsigned long *p = __bitops_word(nr, addr); - unsigned long mask = __bitops_mask(nr); - - *p &= ~mask; -} - -static __always_inline void -arch___change_bit(unsigned long nr, volatile unsigned long *addr) -{ - unsigned long *p = __bitops_word(nr, addr); - unsigned long mask = __bitops_mask(nr); - - *p ^= mask; -} - -static __always_inline bool -arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) -{ - unsigned long *p = __bitops_word(nr, addr); - unsigned long mask = __bitops_mask(nr); - unsigned long old; - - old = *p; - *p |= mask; - return old & mask; -} - -static __always_inline bool -arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) -{ - unsigned long *p = __bitops_word(nr, addr); - unsigned long mask = __bitops_mask(nr); - unsigned long old; - - old = *p; - *p &= ~mask; - return old & mask; -} - -static __always_inline bool -arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) -{ - unsigned long *p = __bitops_word(nr, addr); - unsigned long mask = __bitops_mask(nr); - unsigned long old; - - old = *p; - *p ^= mask; - return old & mask; -} - -#define arch_test_bit generic_test_bit -#define arch_test_bit_acquire generic_test_bit_acquire - -static inline bool arch_test_and_set_bit_lock(unsigned long nr, - volatile unsigned long *ptr) -{ - if (arch_test_bit(nr, ptr)) - return true; - return arch_test_and_set_bit(nr, ptr); -} - -static inline void arch_clear_bit_unlock(unsigned long nr, - volatile unsigned long *ptr) -{ - smp_mb__before_atomic(); - arch_clear_bit(nr, ptr); -} - -static inline void arch___clear_bit_unlock(unsigned long nr, - volatile unsigned long *ptr) -{ - smp_mb(); - arch___clear_bit(nr, ptr); -} - -static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, - volatile unsigned long *ptr) -{ - unsigned long old; - - old = __atomic64_xor_barrier(mask, (long *)ptr); - return old & BIT(7); +#include <asm/asm.h> + +#define arch___set_bit generic___set_bit +#define arch___clear_bit generic___clear_bit +#define arch___change_bit generic___change_bit +#define arch___test_and_set_bit generic___test_and_set_bit +#define arch___test_and_clear_bit generic___test_and_clear_bit +#define arch___test_and_change_bit generic___test_and_change_bit +#define arch_test_bit_acquire generic_test_bit_acquire + +static __always_inline bool arch_test_bit(unsigned long nr, const volatile unsigned long *ptr) +{ +#ifdef __HAVE_ASM_FLAG_OUTPUTS__ + const volatile unsigned char *addr; + unsigned long mask; + int cc; + + if (__builtin_constant_p(nr)) { + addr = (const volatile unsigned char *)ptr; + addr += (nr ^ (BITS_PER_LONG - BITS_PER_BYTE)) / BITS_PER_BYTE; + mask = 1UL << (nr & (BITS_PER_BYTE - 1)); + asm volatile( + " tm %[addr],%[mask]\n" + : "=@cc" (cc) + : [addr] "R" (*addr), [mask] "I" (mask) + ); + return cc == 3; + } +#endif + return generic_test_bit(nr, ptr); } -#define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte -#include <asm-generic/bitops/instrumented-atomic.h> -#include <asm-generic/bitops/instrumented-non-atomic.h> -#include <asm-generic/bitops/instrumented-lock.h> +#include <asm-generic/bitops/atomic.h> +#include <asm-generic/bitops/non-instrumented-non-atomic.h> +#include <asm-generic/bitops/lock.h> /* * Functions which use MSB0 bit numbering. diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h index 46f5c9660616..d86dea5900e7 100644 --- a/arch/s390/include/asm/checksum.h +++ b/arch/s390/include/asm/checksum.h @@ -25,7 +25,7 @@ static inline __wsum cksm(const void *buff, int len, __wsum sum) instrument_read(buff, len); kmsan_check_memory(buff, len); - asm volatile("\n" + asm volatile( "0: cksm %[sum],%[rp]\n" " jo 0b\n" : [sum] "+&d" (sum), [rp] "+&d" (rp.pair) : : "cc", "memory"); diff --git a/arch/s390/include/asm/css_chars.h b/arch/s390/include/asm/css_chars.h index 638137d46c85..a03f64033760 100644 --- a/arch/s390/include/asm/css_chars.h +++ b/arch/s390/include/asm/css_chars.h @@ -25,7 +25,7 @@ struct css_general_char { u64 : 2; u64 : 3; - u64 aif_osa : 1; /* bit 67 */ + u64 aif_qdio : 1;/* bit 67 */ u64 : 12; u64 eadm_rf : 1; /* bit 80 */ u64 : 1; diff --git a/arch/s390/include/asm/debug.h b/arch/s390/include/asm/debug.h index a7f7bdc9e19c..6375276d94ea 100644 --- a/arch/s390/include/asm/debug.h +++ b/arch/s390/include/asm/debug.h @@ -85,6 +85,10 @@ int debug_dflt_header_fn(debug_info_t *id, struct debug_view *view, int area, debug_entry_t *entry, char *out_buf, size_t out_buf_size); +#define DEBUG_SPRINTF_MAX_ARGS 10 +int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view, + char *out_buf, size_t out_buf_size, + const char *inbuf); struct debug_view { char name[DEBUG_MAX_NAME_LEN]; debug_prolog_proc_t *prolog_proc; @@ -114,6 +118,9 @@ debug_info_t *debug_register_mode(const char *name, int pages, int nr_areas, int buf_size, umode_t mode, uid_t uid, gid_t gid); +ssize_t debug_dump(debug_info_t *id, struct debug_view *view, + char *buf, size_t buf_size, bool reverse); + void debug_unregister(debug_info_t *id); void debug_set_level(debug_info_t *id, int new_level); diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h index e1316e181230..5790630e31f0 100644 --- a/arch/s390/include/asm/diag.h +++ b/arch/s390/include/asm/diag.h @@ -36,8 +36,10 @@ enum diag_stat_enum { DIAG_STAT_X2FC, DIAG_STAT_X304, DIAG_STAT_X308, + DIAG_STAT_X310, DIAG_STAT_X318, DIAG_STAT_X320, + DIAG_STAT_X324, DIAG_STAT_X49C, DIAG_STAT_X500, NR_DIAG_STAT diff --git a/arch/s390/include/asm/ebcdic.h b/arch/s390/include/asm/ebcdic.h index efb50fc6866c..7164cb658435 100644 --- a/arch/s390/include/asm/ebcdic.h +++ b/arch/s390/include/asm/ebcdic.h @@ -22,18 +22,18 @@ extern __u8 _ebc_toupper[256]; /* EBCDIC -> uppercase */ static inline void codepage_convert(const __u8 *codepage, volatile char *addr, unsigned long nr) { - if (nr-- <= 0) + if (!nr--) return; asm volatile( - " bras 1,1f\n" - " tr 0(1,%0),0(%2)\n" - "0: tr 0(256,%0),0(%2)\n" + " j 2f\n" + "0: tr 0(1,%0),0(%2)\n" + "1: tr 0(256,%0),0(%2)\n" " la %0,256(%0)\n" - "1: ahi %1,-256\n" - " jnm 0b\n" - " ex %1,0(1)" + "2: aghi %1,-256\n" + " jnm 1b\n" + " exrl %1,0b" : "+&a" (addr), "+&a" (nr) - : "a" (codepage) : "cc", "memory", "1"); + : "a" (codepage) : "cc", "memory"); } #define ASCEBC(addr,nr) codepage_convert(_ascebc, addr, nr) diff --git a/arch/s390/include/asm/fprobe.h b/arch/s390/include/asm/fprobe.h new file mode 100644 index 000000000000..5ef600b372f4 --- /dev/null +++ b/arch/s390/include/asm/fprobe.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_S390_FPROBE_H +#define _ASM_S390_FPROBE_H + +#include <asm-generic/fprobe.h> + +#undef FPROBE_HEADER_MSB_PATTERN +#define FPROBE_HEADER_MSB_PATTERN 0 + +#endif /* _ASM_S390_FPROBE_H */ diff --git a/arch/s390/include/asm/fpu-insn.h b/arch/s390/include/asm/fpu-insn.h index c1e2e521d9af..de510c9f6efa 100644 --- a/arch/s390/include/asm/fpu-insn.h +++ b/arch/s390/include/asm/fpu-insn.h @@ -103,7 +103,7 @@ static inline void fpu_lfpc_safe(unsigned int *fpc) u32 tmp; instrument_read(fpc, sizeof(*fpc)); - asm volatile("\n" + asm_inline volatile( "0: lfpc %[fpc]\n" "1: nopr %%r7\n" ".pushsection .fixup, \"ax\"\n" @@ -188,7 +188,7 @@ static __always_inline void fpu_vgfmg(u8 v1, u8 v2, u8 v3) static __always_inline void fpu_vl(u8 v1, const void *vxr) { instrument_read(vxr, sizeof(__vector128)); - asm volatile("\n" + asm volatile( " la 1,%[vxr]\n" " VL %[v1],0,,1\n" : @@ -246,7 +246,7 @@ static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr) size = min(index + 1, sizeof(__vector128)); instrument_read(vxr, size); - asm volatile("\n" + asm volatile( " la 1,%[vxr]\n" " VLL %[v1],%[index],0,1\n" : @@ -284,7 +284,7 @@ static __always_inline void fpu_vll(u8 v1, u32 index, const void *vxr) } *_v = (void *)(_vxrs); \ \ instrument_read(_v, size); \ - asm volatile("\n" \ + asm volatile( \ " la 1,%[vxrs]\n" \ " VLM %[v1],%[v3],0,1\n" \ : \ @@ -367,7 +367,7 @@ static __always_inline void fpu_vsrlb(u8 v1, u8 v2, u8 v3) static __always_inline void fpu_vst(u8 v1, const void *vxr) { instrument_write(vxr, sizeof(__vector128)); - asm volatile("\n" + asm volatile( " la 1,%[vxr]\n" " VST %[v1],0,,1\n" : [vxr] "=R" (*(__vector128 *)vxr) @@ -396,7 +396,7 @@ static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) size = min(index + 1, sizeof(__vector128)); instrument_write(vxr, size); - asm volatile("\n" + asm volatile( " la 1,%[vxr]\n" " VSTL %[v1],%[index],0,1\n" : [vxr] "=R" (*(u8 *)vxr) @@ -430,7 +430,7 @@ static __always_inline void fpu_vstl(u8 v1, u32 index, const void *vxr) } *_v = (void *)(_vxrs); \ \ instrument_write(_v, size); \ - asm volatile("\n" \ + asm volatile( \ " la 1,%[vxrs]\n" \ " VSTM %[v1],%[v3],0,1\n" \ : [vxrs] "=R" (*_v) \ diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h index fc97d75dc752..a3b73a4f626e 100644 --- a/arch/s390/include/asm/ftrace.h +++ b/arch/s390/include/asm/ftrace.h @@ -39,6 +39,7 @@ struct dyn_arch_ftrace { }; struct module; struct dyn_ftrace; +struct ftrace_ops; bool ftrace_need_init_nop(void); #define ftrace_need_init_nop ftrace_need_init_nop @@ -62,30 +63,32 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs * return NULL; } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - unsigned long gpr2; - unsigned long fp; -}; - -static __always_inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) +static __always_inline void +ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, + unsigned long ip) { - return ret_regs->gpr2; + arch_ftrace_regs(fregs)->regs.psw.addr = ip; } -static __always_inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) +#undef ftrace_regs_get_frame_pointer +static __always_inline unsigned long +ftrace_regs_get_frame_pointer(struct ftrace_regs *fregs) { - return ret_regs->fp; + return ftrace_regs_get_stack_pointer(fregs); } -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -static __always_inline void -ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, - unsigned long ip) +static __always_inline unsigned long +ftrace_regs_get_return_address(const struct ftrace_regs *fregs) { - arch_ftrace_regs(fregs)->regs.psw.addr = ip; + return arch_ftrace_regs(fregs)->regs.gprs[14]; } +#define arch_ftrace_fill_perf_regs(fregs, _regs) do { \ + (_regs)->psw.mask = 0; \ + (_regs)->psw.addr = arch_ftrace_regs(fregs)->regs.psw.addr; \ + (_regs)->gprs[15] = arch_ftrace_regs(fregs)->regs.gprs[15]; \ + } while (0) + #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS /* * When an ftrace registered caller is tracing a function that is @@ -126,6 +129,10 @@ static inline bool arch_syscall_match_sym_name(const char *sym, return !strcmp(sym + 7, name) || !strcmp(sym + 8, name); } +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs); +#define ftrace_graph_func ftrace_graph_func + #endif /* __ASSEMBLY__ */ #ifdef CONFIG_FUNCTION_TRACER diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h index eaeaeb3ff0be..752a2310f0d6 100644 --- a/arch/s390/include/asm/futex.h +++ b/arch/s390/include/asm/futex.h @@ -44,7 +44,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, break; case FUTEX_OP_ANDN: __futex_atomic_op("lr %2,%1\nnr %2,%5\n", - ret, oldval, newval, uaddr, oparg); + ret, oldval, newval, uaddr, ~oparg); break; case FUTEX_OP_XOR: __futex_atomic_op("lr %2,%1\nxr %2,%5\n", diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h index a40664b236e9..7c52acaf9f82 100644 --- a/arch/s390/include/asm/hugetlb.h +++ b/arch/s390/include/asm/hugetlb.h @@ -20,12 +20,13 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz); void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte); + pte_t *ptep, pte_t pte); + #define __HAVE_ARCH_HUGE_PTEP_GET -extern pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep); +pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep); + #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR -extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep); +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep); static inline void arch_clear_hugetlb_flags(struct folio *folio) { @@ -56,6 +57,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, pte_t pte, int dirty) { int changed = !pte_same(huge_ptep_get(vma->vm_mm, addr, ptep), pte); + if (changed) { huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); __set_huge_pte_at(vma->vm_mm, addr, ptep, pte); @@ -68,19 +70,8 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep); - __set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte)); -} -#define __HAVE_ARCH_HUGE_PTE_NONE -static inline int huge_pte_none(pte_t pte) -{ - return pte_none(pte); -} - -#define __HAVE_ARCH_HUGE_PTE_NONE_MOSTLY -static inline int huge_pte_none_mostly(pte_t pte) -{ - return huge_pte_none(pte) || is_pte_marker(pte); + __set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte)); } #define __HAVE_ARCH_HUGE_PTE_MKUFFD_WP diff --git a/arch/s390/include/asm/page-states.h b/arch/s390/include/asm/page-states.h index 08fcbd628120..794fdb21500a 100644 --- a/arch/s390/include/asm/page-states.h +++ b/arch/s390/include/asm/page-states.h @@ -7,7 +7,6 @@ #ifndef PAGE_STATES_H #define PAGE_STATES_H -#include <asm/sections.h> #include <asm/page.h> #define ESSA_GET_STATE 0 @@ -21,7 +20,7 @@ #define ESSA_MAX ESSA_SET_STABLE_NODAT -extern int __bootdata_preserved(cmma_flag); +extern int cmma_flag; static __always_inline unsigned long essa(unsigned long paddr, unsigned char cmd) { diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 48268095b0a3..a3b51056a177 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -17,7 +17,6 @@ #include <linux/page-flags.h> #include <linux/radix-tree.h> #include <linux/atomic.h> -#include <asm/sections.h> #include <asm/ctlreg.h> #include <asm/bug.h> #include <asm/page.h> @@ -35,7 +34,7 @@ enum { PG_DIRECT_MAP_MAX }; -extern atomic_long_t __bootdata_preserved(direct_pages_count[PG_DIRECT_MAP_MAX]); +extern atomic_long_t direct_pages_count[PG_DIRECT_MAP_MAX]; static inline void update_page_count(int level, long count) { @@ -85,14 +84,14 @@ extern unsigned long zero_page_mask; * happen without trampolines and in addition the placement within a * 2GB frame is branch prediction unit friendly. */ -extern unsigned long __bootdata_preserved(VMALLOC_START); -extern unsigned long __bootdata_preserved(VMALLOC_END); +extern unsigned long VMALLOC_START; +extern unsigned long VMALLOC_END; #define VMALLOC_DEFAULT_SIZE ((512UL << 30) - MODULES_LEN) -extern struct page *__bootdata_preserved(vmemmap); -extern unsigned long __bootdata_preserved(vmemmap_size); +extern struct page *vmemmap; +extern unsigned long vmemmap_size; -extern unsigned long __bootdata_preserved(MODULES_VADDR); -extern unsigned long __bootdata_preserved(MODULES_END); +extern unsigned long MODULES_VADDR; +extern unsigned long MODULES_END; #define MODULES_VADDR MODULES_VADDR #define MODULES_END MODULES_END #define MODULES_LEN (1UL << 31) @@ -125,6 +124,8 @@ static inline int is_module_addr(void *addr) #define KASLR_LEN 0UL #endif +void setup_protection_map(void); + /* * A 64 bit pagetable entry of S390 has following format: * | PFRA |0IPC| OS | @@ -443,98 +444,107 @@ static inline int is_module_addr(void *addr) /* * Page protection definitions. */ -#define PAGE_NONE __pgprot(_PAGE_PRESENT | _PAGE_INVALID | _PAGE_PROTECT) -#define PAGE_RO __pgprot(_PAGE_PRESENT | _PAGE_READ | \ +#define __PAGE_NONE (_PAGE_PRESENT | _PAGE_INVALID | _PAGE_PROTECT) +#define __PAGE_RO (_PAGE_PRESENT | _PAGE_READ | \ _PAGE_NOEXEC | _PAGE_INVALID | _PAGE_PROTECT) -#define PAGE_RX __pgprot(_PAGE_PRESENT | _PAGE_READ | \ +#define __PAGE_RX (_PAGE_PRESENT | _PAGE_READ | \ _PAGE_INVALID | _PAGE_PROTECT) -#define PAGE_RW __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ +#define __PAGE_RW (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ _PAGE_NOEXEC | _PAGE_INVALID | _PAGE_PROTECT) -#define PAGE_RWX __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ +#define __PAGE_RWX (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ _PAGE_INVALID | _PAGE_PROTECT) - -#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ +#define __PAGE_SHARED (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ _PAGE_YOUNG | _PAGE_DIRTY | _PAGE_NOEXEC) -#define PAGE_KERNEL __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ +#define __PAGE_KERNEL (_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ _PAGE_YOUNG | _PAGE_DIRTY | _PAGE_NOEXEC) -#define PAGE_KERNEL_RO __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_YOUNG | \ +#define __PAGE_KERNEL_RO (_PAGE_PRESENT | _PAGE_READ | _PAGE_YOUNG | \ _PAGE_PROTECT | _PAGE_NOEXEC) -#define PAGE_KERNEL_EXEC __pgprot(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | \ - _PAGE_YOUNG | _PAGE_DIRTY) -/* - * On s390 the page table entry has an invalid bit and a read-only bit. - * Read permission implies execute permission and write permission - * implies read permission. - */ - /*xwr*/ +extern unsigned long page_noexec_mask; + +#define __pgprot_page_mask(x) __pgprot((x) & page_noexec_mask) + +#define PAGE_NONE __pgprot_page_mask(__PAGE_NONE) +#define PAGE_RO __pgprot_page_mask(__PAGE_RO) +#define PAGE_RX __pgprot_page_mask(__PAGE_RX) +#define PAGE_RW __pgprot_page_mask(__PAGE_RW) +#define PAGE_RWX __pgprot_page_mask(__PAGE_RWX) +#define PAGE_SHARED __pgprot_page_mask(__PAGE_SHARED) +#define PAGE_KERNEL __pgprot_page_mask(__PAGE_KERNEL) +#define PAGE_KERNEL_RO __pgprot_page_mask(__PAGE_KERNEL_RO) /* * Segment entry (large page) protection definitions. */ -#define SEGMENT_NONE __pgprot(_SEGMENT_ENTRY_PRESENT | \ +#define __SEGMENT_NONE (_SEGMENT_ENTRY_PRESENT | \ _SEGMENT_ENTRY_INVALID | \ _SEGMENT_ENTRY_PROTECT) -#define SEGMENT_RO __pgprot(_SEGMENT_ENTRY_PRESENT | \ +#define __SEGMENT_RO (_SEGMENT_ENTRY_PRESENT | \ _SEGMENT_ENTRY_PROTECT | \ _SEGMENT_ENTRY_READ | \ _SEGMENT_ENTRY_NOEXEC) -#define SEGMENT_RX __pgprot(_SEGMENT_ENTRY_PRESENT | \ +#define __SEGMENT_RX (_SEGMENT_ENTRY_PRESENT | \ _SEGMENT_ENTRY_PROTECT | \ _SEGMENT_ENTRY_READ) -#define SEGMENT_RW __pgprot(_SEGMENT_ENTRY_PRESENT | \ +#define __SEGMENT_RW (_SEGMENT_ENTRY_PRESENT | \ _SEGMENT_ENTRY_READ | \ _SEGMENT_ENTRY_WRITE | \ _SEGMENT_ENTRY_NOEXEC) -#define SEGMENT_RWX __pgprot(_SEGMENT_ENTRY_PRESENT | \ +#define __SEGMENT_RWX (_SEGMENT_ENTRY_PRESENT | \ _SEGMENT_ENTRY_READ | \ _SEGMENT_ENTRY_WRITE) -#define SEGMENT_KERNEL __pgprot(_SEGMENT_ENTRY | \ +#define __SEGMENT_KERNEL (_SEGMENT_ENTRY | \ _SEGMENT_ENTRY_LARGE | \ _SEGMENT_ENTRY_READ | \ _SEGMENT_ENTRY_WRITE | \ _SEGMENT_ENTRY_YOUNG | \ _SEGMENT_ENTRY_DIRTY | \ _SEGMENT_ENTRY_NOEXEC) -#define SEGMENT_KERNEL_RO __pgprot(_SEGMENT_ENTRY | \ +#define __SEGMENT_KERNEL_RO (_SEGMENT_ENTRY | \ _SEGMENT_ENTRY_LARGE | \ _SEGMENT_ENTRY_READ | \ _SEGMENT_ENTRY_YOUNG | \ _SEGMENT_ENTRY_PROTECT | \ _SEGMENT_ENTRY_NOEXEC) -#define SEGMENT_KERNEL_EXEC __pgprot(_SEGMENT_ENTRY | \ - _SEGMENT_ENTRY_LARGE | \ - _SEGMENT_ENTRY_READ | \ - _SEGMENT_ENTRY_WRITE | \ - _SEGMENT_ENTRY_YOUNG | \ - _SEGMENT_ENTRY_DIRTY) + +extern unsigned long segment_noexec_mask; + +#define __pgprot_segment_mask(x) __pgprot((x) & segment_noexec_mask) + +#define SEGMENT_NONE __pgprot_segment_mask(__SEGMENT_NONE) +#define SEGMENT_RO __pgprot_segment_mask(__SEGMENT_RO) +#define SEGMENT_RX __pgprot_segment_mask(__SEGMENT_RX) +#define SEGMENT_RW __pgprot_segment_mask(__SEGMENT_RW) +#define SEGMENT_RWX __pgprot_segment_mask(__SEGMENT_RWX) +#define SEGMENT_KERNEL __pgprot_segment_mask(__SEGMENT_KERNEL) +#define SEGMENT_KERNEL_RO __pgprot_segment_mask(__SEGMENT_KERNEL_RO) /* * Region3 entry (large page) protection definitions. */ -#define REGION3_KERNEL __pgprot(_REGION_ENTRY_TYPE_R3 | \ +#define __REGION3_KERNEL (_REGION_ENTRY_TYPE_R3 | \ _REGION3_ENTRY_PRESENT | \ - _REGION3_ENTRY_LARGE | \ - _REGION3_ENTRY_READ | \ - _REGION3_ENTRY_WRITE | \ - _REGION3_ENTRY_YOUNG | \ + _REGION3_ENTRY_LARGE | \ + _REGION3_ENTRY_READ | \ + _REGION3_ENTRY_WRITE | \ + _REGION3_ENTRY_YOUNG | \ _REGION3_ENTRY_DIRTY | \ _REGION_ENTRY_NOEXEC) -#define REGION3_KERNEL_RO __pgprot(_REGION_ENTRY_TYPE_R3 | \ - _REGION3_ENTRY_PRESENT | \ - _REGION3_ENTRY_LARGE | \ - _REGION3_ENTRY_READ | \ - _REGION3_ENTRY_YOUNG | \ - _REGION_ENTRY_PROTECT | \ - _REGION_ENTRY_NOEXEC) -#define REGION3_KERNEL_EXEC __pgprot(_REGION_ENTRY_TYPE_R3 | \ +#define __REGION3_KERNEL_RO (_REGION_ENTRY_TYPE_R3 | \ _REGION3_ENTRY_PRESENT | \ - _REGION3_ENTRY_LARGE | \ - _REGION3_ENTRY_READ | \ - _REGION3_ENTRY_WRITE | \ - _REGION3_ENTRY_YOUNG | \ - _REGION3_ENTRY_DIRTY) + _REGION3_ENTRY_LARGE | \ + _REGION3_ENTRY_READ | \ + _REGION3_ENTRY_YOUNG | \ + _REGION_ENTRY_PROTECT | \ + _REGION_ENTRY_NOEXEC) + +extern unsigned long region_noexec_mask; + +#define __pgprot_region_mask(x) __pgprot((x) & region_noexec_mask) + +#define REGION3_KERNEL __pgprot_region_mask(__REGION3_KERNEL) +#define REGION3_KERNEL_RO __pgprot_region_mask(__REGION3_KERNEL_RO) static inline bool mm_p4d_folded(struct mm_struct *mm) { @@ -1435,8 +1445,6 @@ static inline pte_t mk_pte_phys(unsigned long physpage, pgprot_t pgprot) pte_t __pte; __pte = __pte(physpage | pgprot_val(pgprot)); - if (!MACHINE_HAS_NX) - __pte = clear_pte_bit(__pte, __pgprot(_PAGE_NOEXEC)); return pte_mkyoung(__pte); } @@ -1804,8 +1812,6 @@ static inline int pmdp_clear_flush_young(struct vm_area_struct *vma, static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t entry) { - if (!MACHINE_HAS_NX) - entry = clear_pmd_bit(entry, __pgprot(_SEGMENT_ENTRY_NOEXEC)); set_pmd(pmdp, entry); } diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h index 2c29bdf12127..6ccd033acfe5 100644 --- a/arch/s390/include/asm/preempt.h +++ b/arch/s390/include/asm/preempt.h @@ -8,12 +8,19 @@ #include <asm/cmpxchg.h> #include <asm/march.h> -#ifdef MARCH_HAS_Z196_FEATURES - /* We use the MSB mostly because its available */ #define PREEMPT_NEED_RESCHED 0x80000000 + +/* + * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such + * that a decrement hitting 0 means we can and should reschedule. + */ #define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED) +/* + * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users + * that think a non-zero value indicates we cannot preempt. + */ static __always_inline int preempt_count(void) { return READ_ONCE(get_lowcore()->preempt_count) & ~PREEMPT_NEED_RESCHED; @@ -29,6 +36,15 @@ static __always_inline void preempt_count_set(int pc) } while (!arch_try_cmpxchg(&get_lowcore()->preempt_count, &old, new)); } +/* + * We fold the NEED_RESCHED bit into the preempt count such that + * preempt_enable() can decrement and test for needing to reschedule with a + * short instruction sequence. + * + * We invert the actual bit, so that when the decrement hits 0 we know we both + * need to resched (the bit is cleared) and can resched (no preempt count). + */ + static __always_inline void set_preempt_need_resched(void) { __atomic_and(~PREEMPT_NEED_RESCHED, &get_lowcore()->preempt_count); @@ -64,67 +80,24 @@ static __always_inline void __preempt_count_sub(int val) __preempt_count_add(-val); } +/* + * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule + * a decrement which hits zero means we have no preempt_count and should + * reschedule. + */ static __always_inline bool __preempt_count_dec_and_test(void) { - return __atomic_add(-1, &get_lowcore()->preempt_count) == 1; -} - -static __always_inline bool should_resched(int preempt_offset) -{ - return unlikely(READ_ONCE(get_lowcore()->preempt_count) == - preempt_offset); -} - -#else /* MARCH_HAS_Z196_FEATURES */ - -#define PREEMPT_ENABLED (0) - -static __always_inline int preempt_count(void) -{ - return READ_ONCE(get_lowcore()->preempt_count); -} - -static __always_inline void preempt_count_set(int pc) -{ - get_lowcore()->preempt_count = pc; -} - -static __always_inline void set_preempt_need_resched(void) -{ -} - -static __always_inline void clear_preempt_need_resched(void) -{ -} - -static __always_inline bool test_preempt_need_resched(void) -{ - return false; -} - -static __always_inline void __preempt_count_add(int val) -{ - get_lowcore()->preempt_count += val; -} - -static __always_inline void __preempt_count_sub(int val) -{ - get_lowcore()->preempt_count -= val; -} - -static __always_inline bool __preempt_count_dec_and_test(void) -{ - return !--get_lowcore()->preempt_count && tif_need_resched(); + return __atomic_add_const_and_test(-1, &get_lowcore()->preempt_count); } +/* + * Returns true when we need to resched and can (barring IRQ state). + */ static __always_inline bool should_resched(int preempt_offset) { - return unlikely(preempt_count() == preempt_offset && - tif_need_resched()); + return unlikely(READ_ONCE(get_lowcore()->preempt_count) == preempt_offset); } -#endif /* MARCH_HAS_Z196_FEATURES */ - #define init_task_preempt_count(p) do { } while (0) /* Deferred to CPU bringup time */ #define init_idle_preempt_count(p, cpu) do { } while (0) diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 8761fd01a9f0..4f8d5592c298 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -163,8 +163,7 @@ static __always_inline void __stackleak_poison(unsigned long erase_low, " la %[addr],256(%[addr])\n" " brctg %[tmp],0b\n" "1: stg %[poison],0(%[addr])\n" - " larl %[tmp],3f\n" - " ex %[count],0(%[tmp])\n" + " exrl %[count],3f\n" " j 4f\n" "2: stg %[poison],0(%[addr])\n" " j 4f\n" diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index eb00fa1771da..4da3b2956285 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -16,6 +16,11 @@ /* 24 + 16 * SCLP_MAX_CORES */ #define EXT_SCCB_READ_CPU (3 * PAGE_SIZE) +#define SCLP_ERRNOTIFY_AQ_RESET 0 +#define SCLP_ERRNOTIFY_AQ_REPAIR 1 +#define SCLP_ERRNOTIFY_AQ_INFO_LOG 2 +#define SCLP_ERRNOTIFY_AQ_OPTICS_DATA 3 + #ifndef __ASSEMBLY__ #include <linux/uio.h> #include <asm/chpid.h> @@ -87,8 +92,10 @@ struct sclp_info { unsigned char has_kss : 1; unsigned char has_diag204_bif : 1; unsigned char has_gisaf : 1; + unsigned char has_diag310 : 1; unsigned char has_diag318 : 1; unsigned char has_diag320 : 1; + unsigned char has_diag324 : 1; unsigned char has_sipl : 1; unsigned char has_sipl_eckd : 1; unsigned char has_dirq : 1; @@ -111,6 +118,34 @@ struct sclp_info { }; extern struct sclp_info sclp; +struct sccb_header { + u16 length; + u8 function_code; + u8 control_mask[3]; + u16 response_code; +} __packed; + +struct evbuf_header { + u16 length; + u8 type; + u8 flags; + u16 _reserved; +} __packed; + +struct err_notify_evbuf { + struct evbuf_header header; + u8 action; + u8 atype; + u32 fh; + u32 fid; + u8 data[]; +} __packed; + +struct err_notify_sccb { + struct sccb_header header; + struct err_notify_evbuf evbuf; +} __packed; + struct zpci_report_error_header { u8 version; /* Interface version byte */ u8 action; /* Action qualifier byte diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h index e95b2c8081eb..ea150ea83e57 100644 --- a/arch/s390/include/asm/tlb.h +++ b/arch/s390/include/asm/tlb.h @@ -140,11 +140,11 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, { if (mm_pud_folded(tlb->mm)) return; + __tlb_adjust_range(tlb, address, PAGE_SIZE); tlb->mm->context.flush_mm = 1; tlb->freed_tables = 1; tlb->cleared_p4ds = 1; tlb_remove_ptdesc(tlb, pud); } - #endif /* _S390_TLB_H */ diff --git a/arch/s390/include/uapi/asm/diag.h b/arch/s390/include/uapi/asm/diag.h new file mode 100644 index 000000000000..b7e6ccb4ff6e --- /dev/null +++ b/arch/s390/include/uapi/asm/diag.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Diag ioctls and its associated structures definitions. + * + * Copyright IBM Corp. 2024 + */ + +#ifndef __S390_UAPI_ASM_DIAG_H +#define __S390_UAPI_ASM_DIAG_H + +#include <linux/types.h> + +#define DIAG_MAGIC_STR 'D' + +struct diag324_pib { + __u64 address; + __u64 sequence; +}; + +struct diag310_memtop { + __u64 address; + __u64 nesting_lvl; +}; + +/* Diag ioctl definitions */ +#define DIAG324_GET_PIBBUF _IOWR(DIAG_MAGIC_STR, 0x77, struct diag324_pib) +#define DIAG324_GET_PIBLEN _IOR(DIAG_MAGIC_STR, 0x78, size_t) +#define DIAG310_GET_STRIDE _IOR(DIAG_MAGIC_STR, 0x79, size_t) +#define DIAG310_GET_MEMTOPLEN _IOWR(DIAG_MAGIC_STR, 0x7a, size_t) +#define DIAG310_GET_MEMTOPBUF _IOWR(DIAG_MAGIC_STR, 0x7b, struct diag310_memtop) + +#endif /* __S390_UAPI_ASM_DIAG_H */ diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 48caae8c7e10..db5f3a3faefb 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -38,12 +38,13 @@ CFLAGS_unwind_bc.o += -fno-optimize-sibling-calls obj-y := head64.o traps.o time.o process.o early.o setup.o idle.o vtime.o obj-y += processor.o syscall.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o -obj-y += debug.o irq.o ipl.o dis.o diag.o vdso.o cpufeature.o +obj-y += debug.o irq.o ipl.o dis.o vdso.o cpufeature.o obj-y += sysinfo.o lgr.o os_info.o ctlreg.o obj-y += runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o obj-y += entry.o reipl.o kdebugfs.o alternative.o obj-y += nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o unwind_bc.o obj-y += smp.o text_amode31.o stacktrace.o abs_lowcore.o facility.o uv.o wti.o +obj-y += diag/ extra-y += vmlinux.lds diff --git a/arch/s390/kernel/abs_lowcore.c b/arch/s390/kernel/abs_lowcore.c index 09cd24cbe74e..88f0b91d7a73 100644 --- a/arch/s390/kernel/abs_lowcore.c +++ b/arch/s390/kernel/abs_lowcore.c @@ -2,6 +2,7 @@ #include <linux/pgtable.h> #include <asm/abs_lowcore.h> +#include <asm/sections.h> unsigned long __bootdata_preserved(__abs_lowcore); int __bootdata_preserved(relocate_lowcore); diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c index 862a9140528e..36709112ae7a 100644 --- a/arch/s390/kernel/asm-offsets.c +++ b/arch/s390/kernel/asm-offsets.c @@ -175,12 +175,6 @@ int main(void) DEFINE(OLDMEM_SIZE, PARMAREA + offsetof(struct parmarea, oldmem_size)); DEFINE(COMMAND_LINE, PARMAREA + offsetof(struct parmarea, command_line)); DEFINE(MAX_COMMAND_LINE_SIZE, PARMAREA + offsetof(struct parmarea, max_command_line_size)); -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - /* function graph return value tracing */ - OFFSET(__FGRAPH_RET_GPR2, fgraph_ret_regs, gpr2); - OFFSET(__FGRAPH_RET_FP, fgraph_ret_regs, fp); - DEFINE(__FGRAPH_RET_SIZE, sizeof(struct fgraph_ret_regs)); -#endif OFFSET(__FTRACE_REGS_PT_REGS, __arch_ftrace_regs, regs); DEFINE(__FTRACE_REGS_SIZE, sizeof(struct __arch_ftrace_regs)); diff --git a/arch/s390/kernel/cpacf.c b/arch/s390/kernel/cpacf.c index c8575dbc890d..4b9b34f95d72 100644 --- a/arch/s390/kernel/cpacf.c +++ b/arch/s390/kernel/cpacf.c @@ -14,7 +14,7 @@ #define CPACF_QUERY(name, instruction) \ static ssize_t name##_query_raw_read(struct file *fp, \ struct kobject *kobj, \ - struct bin_attribute *attr, \ + const struct bin_attribute *attr, \ char *buf, loff_t offs, \ size_t count) \ { \ @@ -24,7 +24,7 @@ static ssize_t name##_query_raw_read(struct file *fp, \ return -EOPNOTSUPP; \ return memory_read_from_buffer(buf, count, &offs, &mask, sizeof(mask)); \ } \ -static BIN_ATTR_RO(name##_query_raw, sizeof(cpacf_mask_t)) +static const BIN_ATTR_RO(name##_query_raw, sizeof(cpacf_mask_t)) CPACF_QUERY(km, KM); CPACF_QUERY(kmc, KMC); @@ -40,20 +40,20 @@ CPACF_QUERY(prno, PRNO); CPACF_QUERY(kma, KMA); CPACF_QUERY(kdsa, KDSA); -#define CPACF_QAI(name, instruction) \ -static ssize_t name##_query_auth_info_raw_read( \ - struct file *fp, struct kobject *kobj, \ - struct bin_attribute *attr, char *buf, loff_t offs, \ - size_t count) \ -{ \ - cpacf_qai_t qai; \ - \ - if (!cpacf_qai(CPACF_##instruction, &qai)) \ - return -EOPNOTSUPP; \ - return memory_read_from_buffer(buf, count, &offs, &qai, \ - sizeof(qai)); \ -} \ -static BIN_ATTR_RO(name##_query_auth_info_raw, sizeof(cpacf_qai_t)) +#define CPACF_QAI(name, instruction) \ +static ssize_t name##_query_auth_info_raw_read( \ + struct file *fp, struct kobject *kobj, \ + const struct bin_attribute *attr, char *buf, loff_t offs, \ + size_t count) \ +{ \ + cpacf_qai_t qai; \ + \ + if (!cpacf_qai(CPACF_##instruction, &qai)) \ + return -EOPNOTSUPP; \ + return memory_read_from_buffer(buf, count, &offs, &qai, \ + sizeof(qai)); \ +} \ +static const BIN_ATTR_RO(name##_query_auth_info_raw, sizeof(cpacf_qai_t)) CPACF_QAI(km, KM); CPACF_QAI(kmc, KMC); @@ -69,7 +69,7 @@ CPACF_QAI(prno, PRNO); CPACF_QAI(kma, KMA); CPACF_QAI(kdsa, KDSA); -static struct bin_attribute *cpacf_attrs[] = { +static const struct bin_attribute *const cpacf_attrs[] = { &bin_attr_km_query_raw, &bin_attr_kmc_query_raw, &bin_attr_kimd_query_raw, @@ -101,7 +101,7 @@ static struct bin_attribute *cpacf_attrs[] = { static const struct attribute_group cpacf_attr_grp = { .name = "cpacf", - .bin_attrs = cpacf_attrs, + .bin_attrs_new = cpacf_attrs, }; static int __init cpacf_init(void) diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c index de19fd8a6a95..ba6b7329a10e 100644 --- a/arch/s390/kernel/debug.c +++ b/arch/s390/kernel/debug.c @@ -24,6 +24,7 @@ #include <linux/export.h> #include <linux/init.h> #include <linux/fs.h> +#include <linux/math.h> #include <linux/minmax.h> #include <linux/debugfs.h> @@ -94,9 +95,6 @@ static int debug_input_flush_fn(debug_info_t *id, struct debug_view *view, static int debug_hex_ascii_format_fn(debug_info_t *id, struct debug_view *view, char *out_buf, size_t out_buf_size, const char *in_buf); -static int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view, - char *out_buf, size_t out_buf_size, - const char *inbuf); static void debug_areas_swap(debug_info_t *a, debug_info_t *b); static void debug_events_append(debug_info_t *dest, debug_info_t *src); @@ -354,7 +352,10 @@ static debug_info_t *debug_info_copy(debug_info_t *in, int mode) for (i = 0; i < in->nr_areas; i++) { for (j = 0; j < in->pages_per_area; j++) memcpy(rc->areas[i][j], in->areas[i][j], PAGE_SIZE); + rc->active_pages[i] = in->active_pages[i]; + rc->active_entries[i] = in->active_entries[i]; } + rc->active_area = in->active_area; out: spin_unlock_irqrestore(&in->lock, flags); return rc; @@ -422,11 +423,17 @@ out: return len; } -/* - * debug_next_entry: - * - goto next entry in p_info +/** + * debug_next_entry - Go to the next entry + * @p_info: Private info that is manipulated + * + * Sets the current position in @p_info to the next entry. If no further entry + * exists the current position is set to one after the end the return value + * indicates that no further entries exist. + * + * Return: True if there are more following entries, false otherwise */ -static inline int debug_next_entry(file_private_info_t *p_info) +static inline bool debug_next_entry(file_private_info_t *p_info) { debug_info_t *id; @@ -434,10 +441,10 @@ static inline int debug_next_entry(file_private_info_t *p_info) if (p_info->act_entry == DEBUG_PROLOG_ENTRY) { p_info->act_entry = 0; p_info->act_page = 0; - goto out; + return true; } if (!id->areas) - return 1; + return false; p_info->act_entry += id->entry_size; /* switch to next page, if we reached the end of the page */ if (p_info->act_entry > (PAGE_SIZE - id->entry_size)) { @@ -450,10 +457,87 @@ static inline int debug_next_entry(file_private_info_t *p_info) p_info->act_page = 0; } if (p_info->act_area >= id->nr_areas) - return 1; + return false; } -out: - return 0; + return true; +} + +/** + * debug_to_act_entry - Go to the currently active entry + * @p_info: Private info that is manipulated + * + * Sets the current position in @p_info to the currently active + * entry of @p_info->debug_info_snap + */ +static void debug_to_act_entry(file_private_info_t *p_info) +{ + debug_info_t *snap_id; + + snap_id = p_info->debug_info_snap; + p_info->act_area = snap_id->active_area; + p_info->act_page = snap_id->active_pages[snap_id->active_area]; + p_info->act_entry = snap_id->active_entries[snap_id->active_area]; +} + +/** + * debug_prev_entry - Go to the previous entry + * @p_info: Private info that is manipulated + * + * Sets the current position in @p_info to the previous entry. If no previous entry + * exists the current position is set left as DEBUG_PROLOG_ENTRY and the return value + * indicates that no previous entries exist. + * + * Return: True if there are more previous entries, false otherwise + */ + +static inline bool debug_prev_entry(file_private_info_t *p_info) +{ + debug_info_t *id; + + id = p_info->debug_info_snap; + if (p_info->act_entry == DEBUG_PROLOG_ENTRY) + debug_to_act_entry(p_info); + if (!id->areas) + return false; + p_info->act_entry -= id->entry_size; + /* switch to prev page, if we reached the beginning of the page */ + if (p_info->act_entry < 0) { + /* end of previous page */ + p_info->act_entry = rounddown(PAGE_SIZE, id->entry_size) - id->entry_size; + p_info->act_page--; + if (p_info->act_page < 0) { + /* previous area */ + p_info->act_area--; + p_info->act_page = id->pages_per_area - 1; + } + if (p_info->act_area < 0) + p_info->act_area = (id->nr_areas - 1) % id->nr_areas; + } + /* check full circle */ + if (id->active_area == p_info->act_area && + id->active_pages[id->active_area] == p_info->act_page && + id->active_entries[id->active_area] == p_info->act_entry) + return false; + return true; +} + +/** + * debug_move_entry - Go to next entry in either the forward or backward direction + * @p_info: Private info that is manipulated + * @reverse: If true go to the next entry in reverse i.e. previous + * + * Sets the current position in @p_info to the next (@reverse == false) or + * previous (@reverse == true) entry. + * + * Return: True if there are further entries in that direction, + * false otherwise. + */ +static bool debug_move_entry(file_private_info_t *p_info, bool reverse) +{ + if (reverse) + return debug_prev_entry(p_info); + else + return debug_next_entry(p_info); } /* @@ -495,7 +579,7 @@ static ssize_t debug_output(struct file *file, /* file descriptor */ } if (copy_size == formatted_line_residue) { entry_offset = 0; - if (debug_next_entry(p_info)) + if (!debug_next_entry(p_info)) goto out; } } @@ -530,6 +614,42 @@ static ssize_t debug_input(struct file *file, const char __user *user_buf, return rc; /* number of input characters */ } +static file_private_info_t *debug_file_private_alloc(debug_info_t *debug_info, + struct debug_view *view) +{ + debug_info_t *debug_info_snapshot; + file_private_info_t *p_info; + + /* + * Make snapshot of current debug areas to get it consistent. + * To copy all the areas is only needed, if we have a view which + * formats the debug areas. + */ + if (!view->format_proc && !view->header_proc) + debug_info_snapshot = debug_info_copy(debug_info, NO_AREAS); + else + debug_info_snapshot = debug_info_copy(debug_info, ALL_AREAS); + + if (!debug_info_snapshot) + return NULL; + p_info = kmalloc(sizeof(file_private_info_t), GFP_KERNEL); + if (!p_info) { + debug_info_free(debug_info_snapshot); + return NULL; + } + p_info->offset = 0; + p_info->debug_info_snap = debug_info_snapshot; + p_info->debug_info_org = debug_info; + p_info->view = view; + p_info->act_area = 0; + p_info->act_page = 0; + p_info->act_entry = DEBUG_PROLOG_ENTRY; + p_info->act_entry_offset = 0; + debug_info_get(debug_info); + + return p_info; +} + /* * debug_open: * - called for user open() @@ -538,7 +658,7 @@ static ssize_t debug_input(struct file *file, const char __user *user_buf, */ static int debug_open(struct inode *inode, struct file *file) { - debug_info_t *debug_info, *debug_info_snapshot; + debug_info_t *debug_info; file_private_info_t *p_info; int i, rc = 0; @@ -556,42 +676,26 @@ static int debug_open(struct inode *inode, struct file *file) goto out; found: - - /* Make snapshot of current debug areas to get it consistent. */ - /* To copy all the areas is only needed, if we have a view which */ - /* formats the debug areas. */ - - if (!debug_info->views[i]->format_proc && !debug_info->views[i]->header_proc) - debug_info_snapshot = debug_info_copy(debug_info, NO_AREAS); - else - debug_info_snapshot = debug_info_copy(debug_info, ALL_AREAS); - - if (!debug_info_snapshot) { - rc = -ENOMEM; - goto out; - } - p_info = kmalloc(sizeof(file_private_info_t), GFP_KERNEL); + p_info = debug_file_private_alloc(debug_info, debug_info->views[i]); if (!p_info) { - debug_info_free(debug_info_snapshot); rc = -ENOMEM; goto out; } - p_info->offset = 0; - p_info->debug_info_snap = debug_info_snapshot; - p_info->debug_info_org = debug_info; - p_info->view = debug_info->views[i]; - p_info->act_area = 0; - p_info->act_page = 0; - p_info->act_entry = DEBUG_PROLOG_ENTRY; - p_info->act_entry_offset = 0; file->private_data = p_info; - debug_info_get(debug_info); nonseekable_open(inode, file); out: mutex_unlock(&debug_mutex); return rc; } +static void debug_file_private_free(file_private_info_t *p_info) +{ + if (p_info->debug_info_snap) + debug_info_free(p_info->debug_info_snap); + debug_info_put(p_info->debug_info_org); + kfree(p_info); +} + /* * debug_close: * - called for user close() @@ -602,13 +706,59 @@ static int debug_close(struct inode *inode, struct file *file) file_private_info_t *p_info; p_info = (file_private_info_t *) file->private_data; - if (p_info->debug_info_snap) - debug_info_free(p_info->debug_info_snap); - debug_info_put(p_info->debug_info_org); - kfree(file->private_data); + debug_file_private_free(p_info); + file->private_data = NULL; return 0; /* success */ } +/** + * debug_dump - Get a textual representation of debug info, or as much as fits + * @id: Debug information to use + * @view: View with which to dump the debug information + * @buf: Buffer the textual debug data representation is written to + * @buf_size: Size of the buffer, including the trailing '\0' byte + * @reverse: Go backwards from the last written entry + * + * This function may be used whenever a textual representation of the debug + * information is required without using an s390dbf file. + * + * Note: It is the callers responsibility to supply a view that is compatible + * with the debug information data. + * + * Return: On success returns the number of bytes written to the buffer not + * including the trailing '\0' byte. If bug_size == 0 the function returns 0. + * On failure an error code less than 0 is returned. + */ +ssize_t debug_dump(debug_info_t *id, struct debug_view *view, + char *buf, size_t buf_size, bool reverse) +{ + file_private_info_t *p_info; + size_t size, offset = 0; + + /* Need space for '\0' byte */ + if (buf_size < 1) + return 0; + buf_size--; + + p_info = debug_file_private_alloc(id, view); + if (!p_info) + return -ENOMEM; + + /* There is always at least the DEBUG_PROLOG_ENTRY */ + do { + size = debug_format_entry(p_info); + size = min(size, buf_size - offset); + memcpy(buf + offset, p_info->temp_buf, size); + offset += size; + if (offset >= buf_size) + break; + } while (debug_move_entry(p_info, reverse)); + debug_file_private_free(p_info); + buf[offset] = '\0'; + + return offset; +} + /* Create debugfs entries and add to internal list. */ static void _debug_register(debug_info_t *id) { @@ -1532,8 +1682,8 @@ EXPORT_SYMBOL(debug_dflt_header_fn); #define DEBUG_SPRINTF_MAX_ARGS 10 -static int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view, - char *out_buf, size_t out_buf_size, const char *inbuf) +int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view, + char *out_buf, size_t out_buf_size, const char *inbuf) { debug_sprintf_entry_t *curr_event = (debug_sprintf_entry_t *)inbuf; int num_longs, num_used_args = 0, i, rc = 0; @@ -1570,6 +1720,7 @@ static int debug_sprintf_format_fn(debug_info_t *id, struct debug_view *view, out: return rc; } +EXPORT_SYMBOL(debug_sprintf_format_fn); /* * debug_init: diff --git a/arch/s390/kernel/diag/Makefile b/arch/s390/kernel/diag/Makefile new file mode 100644 index 000000000000..956aee6c4090 --- /dev/null +++ b/arch/s390/kernel/diag/Makefile @@ -0,0 +1 @@ +obj-y := diag_misc.o diag324.o diag.o diag310.o diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag/diag.c index cdd6e31344fa..e15b8dee3228 100644 --- a/arch/s390/kernel/diag.c +++ b/arch/s390/kernel/diag/diag.c @@ -17,7 +17,7 @@ #include <asm/trace/diag.h> #include <asm/sections.h> #include <asm/asm.h> -#include "entry.h" +#include "../entry.h" struct diag_stat { unsigned int counter[NR_DIAG_STAT]; @@ -51,8 +51,10 @@ static const struct diag_desc diag_map[NR_DIAG_STAT] = { [DIAG_STAT_X2FC] = { .code = 0x2fc, .name = "Guest Performance Data" }, [DIAG_STAT_X304] = { .code = 0x304, .name = "Partition-Resource Service" }, [DIAG_STAT_X308] = { .code = 0x308, .name = "List-Directed IPL" }, + [DIAG_STAT_X310] = { .code = 0x310, .name = "Memory Topology Information" }, [DIAG_STAT_X318] = { .code = 0x318, .name = "CP Name and Version Codes" }, [DIAG_STAT_X320] = { .code = 0x320, .name = "Certificate Store" }, + [DIAG_STAT_X324] = { .code = 0x324, .name = "Power Information Block" }, [DIAG_STAT_X49C] = { .code = 0x49c, .name = "Warning-Track Interruption" }, [DIAG_STAT_X500] = { .code = 0x500, .name = "Virtio Service" }, }; diff --git a/arch/s390/kernel/diag/diag310.c b/arch/s390/kernel/diag/diag310.c new file mode 100644 index 000000000000..d6a34454aa5a --- /dev/null +++ b/arch/s390/kernel/diag/diag310.c @@ -0,0 +1,276 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Request memory topology information via diag0x310. + * + * Copyright IBM Corp. 2025 + */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/uaccess.h> +#include <linux/vmalloc.h> +#include <asm/diag.h> +#include <asm/sclp.h> +#include <uapi/asm/diag.h> +#include "diag_ioctl.h" + +#define DIAG310_LEVELMIN 1 +#define DIAG310_LEVELMAX 6 + +enum diag310_sc { + DIAG310_SUBC_0 = 0, + DIAG310_SUBC_1 = 1, + DIAG310_SUBC_4 = 4, + DIAG310_SUBC_5 = 5 +}; + +enum diag310_retcode { + DIAG310_RET_SUCCESS = 0x0001, + DIAG310_RET_BUSY = 0x0101, + DIAG310_RET_OPNOTSUPP = 0x0102, + DIAG310_RET_SC4_INVAL = 0x0401, + DIAG310_RET_SC4_NODATA = 0x0402, + DIAG310_RET_SC5_INVAL = 0x0501, + DIAG310_RET_SC5_NODATA = 0x0502, + DIAG310_RET_SC5_ESIZE = 0x0503 +}; + +union diag310_response { + u64 response; + struct { + u64 result : 32; + u64 : 16; + u64 rc : 16; + }; +}; + +union diag310_req_subcode { + u64 subcode; + struct { + u64 : 48; + u64 st : 8; + u64 sc : 8; + }; +}; + +union diag310_req_size { + u64 size; + struct { + u64 page_count : 32; + u64 : 32; + }; +}; + +static inline unsigned long diag310(unsigned long subcode, unsigned long size, void *addr) +{ + union register_pair rp = { .even = (unsigned long)addr, .odd = size }; + + diag_stat_inc(DIAG_STAT_X310); + asm volatile("diag %[rp],%[subcode],0x310\n" + : [rp] "+d" (rp.pair) + : [subcode] "d" (subcode) + : "memory"); + return rp.odd; +} + +static int diag310_result_to_errno(unsigned int result) +{ + switch (result) { + case DIAG310_RET_BUSY: + return -EBUSY; + case DIAG310_RET_OPNOTSUPP: + return -EOPNOTSUPP; + default: + return -EINVAL; + } +} + +static int diag310_get_subcode_mask(unsigned long *mask) +{ + union diag310_response res; + + res.response = diag310(DIAG310_SUBC_0, 0, NULL); + if (res.rc != DIAG310_RET_SUCCESS) + return diag310_result_to_errno(res.rc); + *mask = res.response; + return 0; +} + +static int diag310_get_memtop_stride(unsigned long *stride) +{ + union diag310_response res; + + res.response = diag310(DIAG310_SUBC_1, 0, NULL); + if (res.rc != DIAG310_RET_SUCCESS) + return diag310_result_to_errno(res.rc); + *stride = res.result; + return 0; +} + +static int diag310_get_memtop_size(unsigned long *pages, unsigned long level) +{ + union diag310_req_subcode req = { .sc = DIAG310_SUBC_4, .st = level }; + union diag310_response res; + + res.response = diag310(req.subcode, 0, NULL); + switch (res.rc) { + case DIAG310_RET_SUCCESS: + *pages = res.result; + return 0; + case DIAG310_RET_SC4_NODATA: + return -ENODATA; + case DIAG310_RET_SC4_INVAL: + return -EINVAL; + default: + return diag310_result_to_errno(res.rc); + } +} + +static int diag310_store_topology_map(void *buf, unsigned long pages, unsigned long level) +{ + union diag310_req_subcode req_sc = { .sc = DIAG310_SUBC_5, .st = level }; + union diag310_req_size req_size = { .page_count = pages }; + union diag310_response res; + + res.response = diag310(req_sc.subcode, req_size.size, buf); + switch (res.rc) { + case DIAG310_RET_SUCCESS: + return 0; + case DIAG310_RET_SC5_NODATA: + return -ENODATA; + case DIAG310_RET_SC5_ESIZE: + return -EOVERFLOW; + case DIAG310_RET_SC5_INVAL: + return -EINVAL; + default: + return diag310_result_to_errno(res.rc); + } +} + +static int diag310_check_features(void) +{ + static int features_available; + unsigned long mask; + int rc; + + if (READ_ONCE(features_available)) + return 0; + if (!sclp.has_diag310) + return -EOPNOTSUPP; + rc = diag310_get_subcode_mask(&mask); + if (rc) + return rc; + if (!test_bit_inv(DIAG310_SUBC_1, &mask)) + return -EOPNOTSUPP; + if (!test_bit_inv(DIAG310_SUBC_4, &mask)) + return -EOPNOTSUPP; + if (!test_bit_inv(DIAG310_SUBC_5, &mask)) + return -EOPNOTSUPP; + WRITE_ONCE(features_available, 1); + return 0; +} + +static int memtop_get_stride_len(unsigned long *res) +{ + static unsigned long memtop_stride; + unsigned long stride; + int rc; + + stride = READ_ONCE(memtop_stride); + if (!stride) { + rc = diag310_get_memtop_stride(&stride); + if (rc) + return rc; + WRITE_ONCE(memtop_stride, stride); + } + *res = stride; + return 0; +} + +static int memtop_get_page_count(unsigned long *res, unsigned long level) +{ + static unsigned long memtop_pages[DIAG310_LEVELMAX]; + unsigned long pages; + int rc; + + if (level > DIAG310_LEVELMAX || level < DIAG310_LEVELMIN) + return -EINVAL; + pages = READ_ONCE(memtop_pages[level - 1]); + if (!pages) { + rc = diag310_get_memtop_size(&pages, level); + if (rc) + return rc; + WRITE_ONCE(memtop_pages[level - 1], pages); + } + *res = pages; + return 0; +} + +long diag310_memtop_stride(unsigned long arg) +{ + size_t __user *argp = (void __user *)arg; + unsigned long stride; + int rc; + + rc = diag310_check_features(); + if (rc) + return rc; + rc = memtop_get_stride_len(&stride); + if (rc) + return rc; + if (put_user(stride, argp)) + return -EFAULT; + return 0; +} + +long diag310_memtop_len(unsigned long arg) +{ + size_t __user *argp = (void __user *)arg; + unsigned long pages, level; + int rc; + + rc = diag310_check_features(); + if (rc) + return rc; + if (get_user(level, argp)) + return -EFAULT; + rc = memtop_get_page_count(&pages, level); + if (rc) + return rc; + if (put_user(pages * PAGE_SIZE, argp)) + return -EFAULT; + return 0; +} + +long diag310_memtop_buf(unsigned long arg) +{ + struct diag310_memtop __user *udata = (struct diag310_memtop __user *)arg; + unsigned long level, pages, data_size; + u64 address; + void *buf; + int rc; + + rc = diag310_check_features(); + if (rc) + return rc; + if (get_user(level, &udata->nesting_lvl)) + return -EFAULT; + if (get_user(address, &udata->address)) + return -EFAULT; + rc = memtop_get_page_count(&pages, level); + if (rc) + return rc; + data_size = pages * PAGE_SIZE; + buf = __vmalloc_node(data_size, PAGE_SIZE, GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT, + NUMA_NO_NODE, __builtin_return_address(0)); + if (!buf) + return -ENOMEM; + rc = diag310_store_topology_map(buf, pages, level); + if (rc) + goto out; + if (copy_to_user((void __user *)address, buf, data_size)) + rc = -EFAULT; +out: + vfree(buf); + return rc; +} diff --git a/arch/s390/kernel/diag/diag324.c b/arch/s390/kernel/diag/diag324.c new file mode 100644 index 000000000000..7fa4c0b7eb6c --- /dev/null +++ b/arch/s390/kernel/diag/diag324.c @@ -0,0 +1,224 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Request power readings for resources in a computing environment via + * diag 0x324. diag 0x324 stores the power readings in the power information + * block (pib). + * + * Copyright IBM Corp. 2024 + */ + +#define pr_fmt(fmt) "diag324: " fmt +#include <linux/fs.h> +#include <linux/gfp.h> +#include <linux/ioctl.h> +#include <linux/jiffies.h> +#include <linux/kernel.h> +#include <linux/ktime.h> +#include <linux/string.h> +#include <linux/slab.h> +#include <linux/timer.h> +#include <linux/types.h> +#include <linux/uaccess.h> +#include <linux/vmalloc.h> + +#include <asm/diag.h> +#include <asm/sclp.h> +#include <asm/timex.h> +#include <uapi/asm/diag.h> +#include "diag_ioctl.h" + +enum subcode { + DIAG324_SUBC_0 = 0, + DIAG324_SUBC_1 = 1, + DIAG324_SUBC_2 = 2, +}; + +enum retcode { + DIAG324_RET_SUCCESS = 0x0001, + DIAG324_RET_SUBC_NOTAVAIL = 0x0103, + DIAG324_RET_INSUFFICIENT_SIZE = 0x0104, + DIAG324_RET_READING_UNAVAILABLE = 0x0105, +}; + +union diag324_response { + u64 response; + struct { + u64 installed : 32; + u64 : 16; + u64 rc : 16; + } sc0; + struct { + u64 format : 16; + u64 : 16; + u64 pib_len : 16; + u64 rc : 16; + } sc1; + struct { + u64 : 48; + u64 rc : 16; + } sc2; +}; + +union diag324_request { + u64 request; + struct { + u64 : 32; + u64 allocated : 16; + u64 : 12; + u64 sc : 4; + } sc2; +}; + +struct pib { + u32 : 8; + u32 num : 8; + u32 len : 16; + u32 : 24; + u32 hlen : 8; + u64 : 64; + u64 intv; + u8 r[]; +} __packed; + +struct pibdata { + struct pib *pib; + ktime_t expire; + u64 sequence; + size_t len; + int rc; +}; + +static DEFINE_MUTEX(pibmutex); +static struct pibdata pibdata; + +#define PIBWORK_DELAY (5 * NSEC_PER_SEC) + +static void pibwork_handler(struct work_struct *work); +static DECLARE_DELAYED_WORK(pibwork, pibwork_handler); + +static unsigned long diag324(unsigned long subcode, void *addr) +{ + union register_pair rp = { .even = (unsigned long)addr }; + + diag_stat_inc(DIAG_STAT_X324); + asm volatile("diag %[rp],%[subcode],0x324\n" + : [rp] "+d" (rp.pair) + : [subcode] "d" (subcode) + : "memory"); + return rp.odd; +} + +static void pibwork_handler(struct work_struct *work) +{ + struct pibdata *data = &pibdata; + ktime_t timedout; + + mutex_lock(&pibmutex); + timedout = ktime_add_ns(data->expire, PIBWORK_DELAY); + if (ktime_before(ktime_get(), timedout)) { + mod_delayed_work(system_wq, &pibwork, nsecs_to_jiffies(PIBWORK_DELAY)); + goto out; + } + vfree(data->pib); + data->pib = NULL; +out: + mutex_unlock(&pibmutex); +} + +static void pib_update(struct pibdata *data) +{ + union diag324_request req = { .sc2.sc = DIAG324_SUBC_2, .sc2.allocated = data->len }; + union diag324_response res; + int rc; + + memset(data->pib, 0, data->len); + res.response = diag324(req.request, data->pib); + switch (res.sc2.rc) { + case DIAG324_RET_SUCCESS: + rc = 0; + break; + case DIAG324_RET_SUBC_NOTAVAIL: + rc = -ENOENT; + break; + case DIAG324_RET_INSUFFICIENT_SIZE: + rc = -EMSGSIZE; + break; + case DIAG324_RET_READING_UNAVAILABLE: + rc = -EBUSY; + break; + default: + rc = -EINVAL; + } + data->rc = rc; +} + +long diag324_pibbuf(unsigned long arg) +{ + struct diag324_pib __user *udata = (struct diag324_pib __user *)arg; + struct pibdata *data = &pibdata; + static bool first = true; + u64 address; + int rc; + + if (!data->len) + return -EOPNOTSUPP; + if (get_user(address, &udata->address)) + return -EFAULT; + mutex_lock(&pibmutex); + rc = -ENOMEM; + if (!data->pib) + data->pib = vmalloc(data->len); + if (!data->pib) + goto out; + if (first || ktime_after(ktime_get(), data->expire)) { + pib_update(data); + data->sequence++; + data->expire = ktime_add_ns(ktime_get(), tod_to_ns(data->pib->intv)); + mod_delayed_work(system_wq, &pibwork, nsecs_to_jiffies(PIBWORK_DELAY)); + first = false; + } + rc = data->rc; + if (rc != 0 && rc != -EBUSY) + goto out; + rc = copy_to_user((void __user *)address, data->pib, data->pib->len); + rc |= put_user(data->sequence, &udata->sequence); + if (rc) + rc = -EFAULT; +out: + mutex_unlock(&pibmutex); + return rc; +} + +long diag324_piblen(unsigned long arg) +{ + struct pibdata *data = &pibdata; + + if (!data->len) + return -EOPNOTSUPP; + if (put_user(data->len, (size_t __user *)arg)) + return -EFAULT; + return 0; +} + +static int __init diag324_init(void) +{ + union diag324_response res; + unsigned long installed; + + if (!sclp.has_diag324) + return -EOPNOTSUPP; + res.response = diag324(DIAG324_SUBC_0, NULL); + if (res.sc0.rc != DIAG324_RET_SUCCESS) + return -EOPNOTSUPP; + installed = res.response; + if (!test_bit_inv(DIAG324_SUBC_1, &installed)) + return -EOPNOTSUPP; + if (!test_bit_inv(DIAG324_SUBC_2, &installed)) + return -EOPNOTSUPP; + res.response = diag324(DIAG324_SUBC_1, NULL); + if (res.sc1.rc != DIAG324_RET_SUCCESS) + return -EOPNOTSUPP; + pibdata.len = res.sc1.pib_len; + return 0; +} +device_initcall(diag324_init); diff --git a/arch/s390/kernel/diag/diag_ioctl.h b/arch/s390/kernel/diag/diag_ioctl.h new file mode 100644 index 000000000000..7080be946785 --- /dev/null +++ b/arch/s390/kernel/diag/diag_ioctl.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _DIAG_IOCTL_H +#define _DIAG_IOCTL_H + +#include <linux/types.h> + +long diag324_pibbuf(unsigned long arg); +long diag324_piblen(unsigned long arg); + +long diag310_memtop_stride(unsigned long arg); +long diag310_memtop_len(unsigned long arg); +long diag310_memtop_buf(unsigned long arg); + +#endif /* _DIAG_IOCTL_H */ diff --git a/arch/s390/kernel/diag/diag_misc.c b/arch/s390/kernel/diag/diag_misc.c new file mode 100644 index 000000000000..efffe02ea02e --- /dev/null +++ b/arch/s390/kernel/diag/diag_misc.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Provide diagnose information via misc device /dev/diag. + * + * Copyright IBM Corp. 2024 + */ + +#include <linux/fs.h> +#include <linux/init.h> +#include <linux/ioctl.h> +#include <linux/kernel.h> +#include <linux/miscdevice.h> +#include <linux/types.h> + +#include <uapi/asm/diag.h> +#include "diag_ioctl.h" + +static long diag_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) +{ + long rc; + + switch (cmd) { + case DIAG324_GET_PIBLEN: + rc = diag324_piblen(arg); + break; + case DIAG324_GET_PIBBUF: + rc = diag324_pibbuf(arg); + break; + case DIAG310_GET_STRIDE: + rc = diag310_memtop_stride(arg); + break; + case DIAG310_GET_MEMTOPLEN: + rc = diag310_memtop_len(arg); + break; + case DIAG310_GET_MEMTOPBUF: + rc = diag310_memtop_buf(arg); + break; + default: + rc = -ENOIOCTLCMD; + break; + } + return rc; +} + +static const struct file_operations fops = { + .owner = THIS_MODULE, + .open = nonseekable_open, + .unlocked_ioctl = diag_ioctl, +}; + +static struct miscdevice diagdev = { + .name = "diag", + .minor = MISC_DYNAMIC_MINOR, + .fops = &fops, + .mode = 0444, +}; + +static int diag_init(void) +{ + return misc_register(&diagdev); +} + +device_initcall(diag_init); diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S index 960c08700cf6..4cc3408c4dac 100644 --- a/arch/s390/kernel/entry.S +++ b/arch/s390/kernel/entry.S @@ -52,16 +52,7 @@ _LPP_OFFSET = __LC_LPP ALT_FACILITY(193) .endm - .macro CHECK_STACK savearea, lowcore -#ifdef CONFIG_CHECK_STACK - tml %r15,THREAD_SIZE - CONFIG_STACK_GUARD - la %r14,\savearea(\lowcore) - jz stack_overflow -#endif - .endm - .macro CHECK_VMAP_STACK savearea, lowcore, oklabel -#ifdef CONFIG_VMAP_STACK lgr %r14,%r15 nill %r14,0x10000 - THREAD_SIZE oill %r14,STACK_INIT_OFFSET @@ -77,9 +68,6 @@ _LPP_OFFSET = __LC_LPP je \oklabel la %r14,\savearea(\lowcore) j stack_overflow -#else - j \oklabel -#endif .endm /* @@ -326,8 +314,7 @@ SYM_CODE_START(pgm_check_handler) jnz 2f # -> enabled, can't be a double fault tm __LC_PGM_ILC+3(%r13),0x80 # check for per exception jnz .Lpgm_svcper # -> single stepped svc -2: CHECK_STACK __LC_SAVE_AREA,%r13 - aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) +2: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) # CHECK_VMAP_STACK branches to stack_overflow or 4f CHECK_VMAP_STACK __LC_SAVE_AREA,%r13,4f 3: lg %r15,__LC_KERNEL_STACK(%r13) @@ -394,8 +381,7 @@ SYM_CODE_START(\name) BPENTER __SF_SIE_FLAGS(%r15),_TIF_ISOLATE_BP_GUEST SIEEXIT __SF_SIE_CONTROL(%r15),%r13 #endif -0: CHECK_STACK __LC_SAVE_AREA,%r13 - aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) +0: aghi %r15,-(STACK_FRAME_OVERHEAD + __PT_SIZE) j 2f 1: lctlg %c1,%c1,__LC_KERNEL_ASCE(%r13) lg %r15,__LC_KERNEL_STACK(%r13) @@ -603,7 +589,6 @@ SYM_CODE_END(early_pgm_check_handler) .section .kprobes.text, "ax" -#if defined(CONFIG_CHECK_STACK) || defined(CONFIG_VMAP_STACK) /* * The synchronous or the asynchronous stack overflowed. We are dead. * No need to properly save the registers, we are going to panic anyway. @@ -621,7 +606,6 @@ SYM_CODE_START(stack_overflow) lgr %r2,%r11 # pass pointer to pt_regs jg kernel_stack_overflow SYM_CODE_END(stack_overflow) -#endif .section .data, "aw" .balign 4 diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h index 21969520f947..a1f28879c87e 100644 --- a/arch/s390/kernel/entry.h +++ b/arch/s390/kernel/entry.h @@ -41,7 +41,6 @@ void do_restart(void *arg); void __init startup_init(void); void die(struct pt_regs *regs, const char *str); int setup_profiling_timer(unsigned int multiplier); -unsigned long prepare_ftrace_return(unsigned long parent, unsigned long sp, unsigned long ip); struct s390_mmap_arg_struct; struct fadvise64_64_args; diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c index 51439a71e392..c0b2c97efefb 100644 --- a/arch/s390/kernel/ftrace.c +++ b/arch/s390/kernel/ftrace.c @@ -261,43 +261,23 @@ void ftrace_arch_code_modify_post_process(void) } #ifdef CONFIG_FUNCTION_GRAPH_TRACER -/* - * Hook the return address and push it in the stack of return addresses - * in current thread info. - */ -unsigned long prepare_ftrace_return(unsigned long ra, unsigned long sp, - unsigned long ip) -{ - if (unlikely(ftrace_graph_is_dead())) - goto out; - if (unlikely(atomic_read(¤t->tracing_graph_pause))) - goto out; - ip -= MCOUNT_INSN_SIZE; - if (!function_graph_enter(ra, ip, 0, (void *) sp)) - ra = (unsigned long) return_to_handler; -out: - return ra; -} -NOKPROBE_SYMBOL(prepare_ftrace_return); -/* - * Patch the kernel code at ftrace_graph_caller location. The instruction - * there is branch relative on condition. To enable the ftrace graph code - * block, we simply patch the mask field of the instruction to zero and - * turn the instruction into a nop. - * To disable the ftrace graph code the mask field will be patched to - * all ones, which turns the instruction into an unconditional branch. - */ -int ftrace_enable_ftrace_graph_caller(void) +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs) { - /* Expect brc 0xf,... */ - return ftrace_patch_branch_mask(ftrace_graph_caller, 0xa7f4, false); -} + unsigned long *parent = &arch_ftrace_regs(fregs)->regs.gprs[14]; + int bit; -int ftrace_disable_ftrace_graph_caller(void) -{ - /* Expect brc 0x0,... */ - return ftrace_patch_branch_mask(ftrace_graph_caller, 0xa704, true); + if (unlikely(ftrace_graph_is_dead())) + return; + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + bit = ftrace_test_recursion_trylock(ip, *parent); + if (bit < 0) + return; + if (!function_graph_enter_regs(*parent, ip, 0, parent, fregs)) + *parent = (unsigned long)&return_to_handler; + ftrace_test_recursion_unlock(bit); } #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c index edbb52ce3f1e..69be2309cde0 100644 --- a/arch/s390/kernel/ipl.c +++ b/arch/s390/kernel/ipl.c @@ -270,7 +270,7 @@ static ssize_t sys_##_prefix##_##_name##_store(struct kobject *kobj, \ if (len >= sizeof(_value)) \ return -E2BIG; \ len = strscpy(_value, buf, sizeof(_value)); \ - if (len < 0) \ + if ((ssize_t)len < 0) \ return len; \ strim(_value); \ return len; \ @@ -280,58 +280,58 @@ static struct kobj_attribute sys_##_prefix##_##_name##_attr = \ sys_##_prefix##_##_name##_show, \ sys_##_prefix##_##_name##_store) -#define IPL_ATTR_SCP_DATA_SHOW_FN(_prefix, _ipl_block) \ -static ssize_t sys_##_prefix##_scp_data_show(struct file *filp, \ - struct kobject *kobj, \ - struct bin_attribute *attr, \ - char *buf, loff_t off, \ - size_t count) \ -{ \ - size_t size = _ipl_block.scp_data_len; \ - void *scp_data = _ipl_block.scp_data; \ - \ - return memory_read_from_buffer(buf, count, &off, \ - scp_data, size); \ +#define IPL_ATTR_SCP_DATA_SHOW_FN(_prefix, _ipl_block) \ +static ssize_t sys_##_prefix##_scp_data_show(struct file *filp, \ + struct kobject *kobj, \ + const struct bin_attribute *attr, \ + char *buf, loff_t off, \ + size_t count) \ +{ \ + size_t size = _ipl_block.scp_data_len; \ + void *scp_data = _ipl_block.scp_data; \ + \ + return memory_read_from_buffer(buf, count, &off, \ + scp_data, size); \ } #define IPL_ATTR_SCP_DATA_STORE_FN(_prefix, _ipl_block_hdr, _ipl_block, _ipl_bp_len, _ipl_bp0_len)\ -static ssize_t sys_##_prefix##_scp_data_store(struct file *filp, \ - struct kobject *kobj, \ - struct bin_attribute *attr, \ - char *buf, loff_t off, \ - size_t count) \ -{ \ - size_t scpdata_len = count; \ - size_t padding; \ - \ - if (off) \ - return -EINVAL; \ - \ - memcpy(_ipl_block.scp_data, buf, count); \ - if (scpdata_len % 8) { \ - padding = 8 - (scpdata_len % 8); \ - memset(_ipl_block.scp_data + scpdata_len, \ - 0, padding); \ - scpdata_len += padding; \ - } \ - \ - _ipl_block_hdr.len = _ipl_bp_len + scpdata_len; \ - _ipl_block.len = _ipl_bp0_len + scpdata_len; \ - _ipl_block.scp_data_len = scpdata_len; \ - \ - return count; \ +static ssize_t sys_##_prefix##_scp_data_store(struct file *filp, \ + struct kobject *kobj, \ + const struct bin_attribute *attr, \ + char *buf, loff_t off, \ + size_t count) \ +{ \ + size_t scpdata_len = count; \ + size_t padding; \ + \ + if (off) \ + return -EINVAL; \ + \ + memcpy(_ipl_block.scp_data, buf, count); \ + if (scpdata_len % 8) { \ + padding = 8 - (scpdata_len % 8); \ + memset(_ipl_block.scp_data + scpdata_len, \ + 0, padding); \ + scpdata_len += padding; \ + } \ + \ + _ipl_block_hdr.len = _ipl_bp_len + scpdata_len; \ + _ipl_block.len = _ipl_bp0_len + scpdata_len; \ + _ipl_block.scp_data_len = scpdata_len; \ + \ + return count; \ } #define DEFINE_IPL_ATTR_SCP_DATA_RO(_prefix, _ipl_block, _size) \ IPL_ATTR_SCP_DATA_SHOW_FN(_prefix, _ipl_block) \ -static struct bin_attribute sys_##_prefix##_scp_data_attr = \ +static const struct bin_attribute sys_##_prefix##_scp_data_attr = \ __BIN_ATTR(scp_data, 0444, sys_##_prefix##_scp_data_show, \ NULL, _size) #define DEFINE_IPL_ATTR_SCP_DATA_RW(_prefix, _ipl_block_hdr, _ipl_block, _ipl_bp_len, _ipl_bp0_len, _size)\ IPL_ATTR_SCP_DATA_SHOW_FN(_prefix, _ipl_block) \ IPL_ATTR_SCP_DATA_STORE_FN(_prefix, _ipl_block_hdr, _ipl_block, _ipl_bp_len, _ipl_bp0_len)\ -static struct bin_attribute sys_##_prefix##_scp_data_attr = \ +static const struct bin_attribute sys_##_prefix##_scp_data_attr = \ __BIN_ATTR(scp_data, 0644, sys_##_prefix##_scp_data_show, \ sys_##_prefix##_scp_data_store, _size) @@ -434,19 +434,19 @@ static struct kobj_attribute sys_ipl_device_attr = __ATTR(device, 0444, sys_ipl_device_show, NULL); static ssize_t sys_ipl_parameter_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { return memory_read_from_buffer(buf, count, &off, &ipl_block, ipl_block.hdr.len); } -static struct bin_attribute sys_ipl_parameter_attr = +static const struct bin_attribute sys_ipl_parameter_attr = __BIN_ATTR(binary_parameter, 0444, sys_ipl_parameter_read, NULL, PAGE_SIZE); DEFINE_IPL_ATTR_SCP_DATA_RO(ipl_fcp, ipl_block.fcp, PAGE_SIZE); -static struct bin_attribute *ipl_fcp_bin_attrs[] = { +static const struct bin_attribute *const ipl_fcp_bin_attrs[] = { &sys_ipl_parameter_attr, &sys_ipl_fcp_scp_data_attr, NULL, @@ -454,7 +454,7 @@ static struct bin_attribute *ipl_fcp_bin_attrs[] = { DEFINE_IPL_ATTR_SCP_DATA_RO(ipl_nvme, ipl_block.nvme, PAGE_SIZE); -static struct bin_attribute *ipl_nvme_bin_attrs[] = { +static const struct bin_attribute *const ipl_nvme_bin_attrs[] = { &sys_ipl_parameter_attr, &sys_ipl_nvme_scp_data_attr, NULL, @@ -462,7 +462,7 @@ static struct bin_attribute *ipl_nvme_bin_attrs[] = { DEFINE_IPL_ATTR_SCP_DATA_RO(ipl_eckd, ipl_block.eckd, PAGE_SIZE); -static struct bin_attribute *ipl_eckd_bin_attrs[] = { +static const struct bin_attribute *const ipl_eckd_bin_attrs[] = { &sys_ipl_parameter_attr, &sys_ipl_eckd_scp_data_attr, NULL, @@ -593,9 +593,9 @@ static struct attribute *ipl_fcp_attrs[] = { NULL, }; -static struct attribute_group ipl_fcp_attr_group = { +static const struct attribute_group ipl_fcp_attr_group = { .attrs = ipl_fcp_attrs, - .bin_attrs = ipl_fcp_bin_attrs, + .bin_attrs_new = ipl_fcp_bin_attrs, }; static struct attribute *ipl_nvme_attrs[] = { @@ -607,9 +607,9 @@ static struct attribute *ipl_nvme_attrs[] = { NULL, }; -static struct attribute_group ipl_nvme_attr_group = { +static const struct attribute_group ipl_nvme_attr_group = { .attrs = ipl_nvme_attrs, - .bin_attrs = ipl_nvme_bin_attrs, + .bin_attrs_new = ipl_nvme_bin_attrs, }; static struct attribute *ipl_eckd_attrs[] = { @@ -620,9 +620,9 @@ static struct attribute *ipl_eckd_attrs[] = { NULL, }; -static struct attribute_group ipl_eckd_attr_group = { +static const struct attribute_group ipl_eckd_attr_group = { .attrs = ipl_eckd_attrs, - .bin_attrs = ipl_eckd_bin_attrs, + .bin_attrs_new = ipl_eckd_bin_attrs, }; /* CCW ipl device attributes */ @@ -640,11 +640,11 @@ static struct attribute *ipl_ccw_attrs_lpar[] = { NULL, }; -static struct attribute_group ipl_ccw_attr_group_vm = { +static const struct attribute_group ipl_ccw_attr_group_vm = { .attrs = ipl_ccw_attrs_vm, }; -static struct attribute_group ipl_ccw_attr_group_lpar = { +static const struct attribute_group ipl_ccw_attr_group_lpar = { .attrs = ipl_ccw_attrs_lpar }; @@ -655,7 +655,7 @@ static struct attribute *ipl_common_attrs[] = { NULL, }; -static struct attribute_group ipl_common_attr_group = { +static const struct attribute_group ipl_common_attr_group = { .attrs = ipl_common_attrs, }; @@ -808,7 +808,7 @@ DEFINE_IPL_ATTR_SCP_DATA_RW(reipl_fcp, reipl_block_fcp->hdr, IPL_BP_FCP_LEN, IPL_BP0_FCP_LEN, DIAG308_SCPDATA_SIZE); -static struct bin_attribute *reipl_fcp_bin_attrs[] = { +static const struct bin_attribute *const reipl_fcp_bin_attrs[] = { &sys_reipl_fcp_scp_data_attr, NULL, }; @@ -917,9 +917,9 @@ static struct attribute *reipl_fcp_attrs[] = { NULL, }; -static struct attribute_group reipl_fcp_attr_group = { +static const struct attribute_group reipl_fcp_attr_group = { .attrs = reipl_fcp_attrs, - .bin_attrs = reipl_fcp_bin_attrs, + .bin_attrs_new = reipl_fcp_bin_attrs, }; static struct kobj_attribute sys_reipl_fcp_clear_attr = @@ -932,7 +932,7 @@ DEFINE_IPL_ATTR_SCP_DATA_RW(reipl_nvme, reipl_block_nvme->hdr, IPL_BP_NVME_LEN, IPL_BP0_NVME_LEN, DIAG308_SCPDATA_SIZE); -static struct bin_attribute *reipl_nvme_bin_attrs[] = { +static const struct bin_attribute *const reipl_nvme_bin_attrs[] = { &sys_reipl_nvme_scp_data_attr, NULL, }; @@ -955,9 +955,9 @@ static struct attribute *reipl_nvme_attrs[] = { NULL, }; -static struct attribute_group reipl_nvme_attr_group = { +static const struct attribute_group reipl_nvme_attr_group = { .attrs = reipl_nvme_attrs, - .bin_attrs = reipl_nvme_bin_attrs + .bin_attrs_new = reipl_nvme_bin_attrs }; static ssize_t reipl_nvme_clear_show(struct kobject *kobj, @@ -1031,7 +1031,7 @@ DEFINE_IPL_ATTR_SCP_DATA_RW(reipl_eckd, reipl_block_eckd->hdr, IPL_BP_ECKD_LEN, IPL_BP0_ECKD_LEN, DIAG308_SCPDATA_SIZE); -static struct bin_attribute *reipl_eckd_bin_attrs[] = { +static const struct bin_attribute *const reipl_eckd_bin_attrs[] = { &sys_reipl_eckd_scp_data_attr, NULL, }; @@ -1048,9 +1048,9 @@ static struct attribute *reipl_eckd_attrs[] = { NULL, }; -static struct attribute_group reipl_eckd_attr_group = { +static const struct attribute_group reipl_eckd_attr_group = { .attrs = reipl_eckd_attrs, - .bin_attrs = reipl_eckd_bin_attrs + .bin_attrs_new = reipl_eckd_bin_attrs }; static ssize_t reipl_eckd_clear_show(struct kobject *kobj, @@ -1587,15 +1587,15 @@ static struct attribute *dump_fcp_attrs[] = { NULL, }; -static struct bin_attribute *dump_fcp_bin_attrs[] = { +static const struct bin_attribute *const dump_fcp_bin_attrs[] = { &sys_dump_fcp_scp_data_attr, NULL, }; -static struct attribute_group dump_fcp_attr_group = { +static const struct attribute_group dump_fcp_attr_group = { .name = IPL_FCP_STR, .attrs = dump_fcp_attrs, - .bin_attrs = dump_fcp_bin_attrs, + .bin_attrs_new = dump_fcp_bin_attrs, }; /* NVME dump device attributes */ @@ -1621,15 +1621,15 @@ static struct attribute *dump_nvme_attrs[] = { NULL, }; -static struct bin_attribute *dump_nvme_bin_attrs[] = { +static const struct bin_attribute *const dump_nvme_bin_attrs[] = { &sys_dump_nvme_scp_data_attr, NULL, }; -static struct attribute_group dump_nvme_attr_group = { +static const struct attribute_group dump_nvme_attr_group = { .name = IPL_NVME_STR, .attrs = dump_nvme_attrs, - .bin_attrs = dump_nvme_bin_attrs, + .bin_attrs_new = dump_nvme_bin_attrs, }; /* ECKD dump device attributes */ @@ -1655,15 +1655,15 @@ static struct attribute *dump_eckd_attrs[] = { NULL, }; -static struct bin_attribute *dump_eckd_bin_attrs[] = { +static const struct bin_attribute *const dump_eckd_bin_attrs[] = { &sys_dump_eckd_scp_data_attr, NULL, }; -static struct attribute_group dump_eckd_attr_group = { +static const struct attribute_group dump_eckd_attr_group = { .name = IPL_ECKD_STR, .attrs = dump_eckd_attrs, - .bin_attrs = dump_eckd_bin_attrs, + .bin_attrs_new = dump_eckd_bin_attrs, }; /* CCW dump device attributes */ diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S index 7e267ef63a7f..1fec370fecf4 100644 --- a/arch/s390/kernel/mcount.S +++ b/arch/s390/kernel/mcount.S @@ -104,17 +104,6 @@ SYM_CODE_START(ftrace_common) lgr %r3,%r14 la %r5,STACK_FREGS(%r15) BASR_EX %r14,%r1 -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -# The j instruction gets runtime patched to a nop instruction. -# See ftrace_enable_ftrace_graph_caller. -SYM_INNER_LABEL(ftrace_graph_caller, SYM_L_GLOBAL) - j .Lftrace_graph_caller_end - lmg %r2,%r3,(STACK_FREGS_PTREGS_GPRS+14*8)(%r15) - lg %r4,(STACK_FREGS_PTREGS_PSW+8)(%r15) - brasl %r14,prepare_ftrace_return - stg %r2,(STACK_FREGS_PTREGS_GPRS+14*8)(%r15) -.Lftrace_graph_caller_end: -#endif lg %r0,(STACK_FREGS_PTREGS_PSW+8)(%r15) #ifdef MARCH_HAS_Z196_FEATURES ltg %r1,STACK_FREGS_PTREGS_ORIG_GPR2(%r15) @@ -134,14 +123,14 @@ SYM_CODE_END(ftrace_common) SYM_FUNC_START(return_to_handler) stmg %r2,%r5,32(%r15) lgr %r1,%r15 - aghi %r15,-(STACK_FRAME_OVERHEAD+__FGRAPH_RET_SIZE) + # allocate ftrace_regs and stack frame for ftrace_return_to_handler + aghi %r15,-STACK_FRAME_SIZE_FREGS stg %r1,__SF_BACKCHAIN(%r15) - la %r3,STACK_FRAME_OVERHEAD(%r15) - stg %r1,__FGRAPH_RET_FP(%r3) - stg %r2,__FGRAPH_RET_GPR2(%r3) - lgr %r2,%r3 + stg %r2,(STACK_FREGS_PTREGS_GPRS+2*8)(%r15) + stg %r1,(STACK_FREGS_PTREGS_GPRS+15*8)(%r15) + la %r2,STACK_FRAME_OVERHEAD(%r15) brasl %r14,ftrace_return_to_handler - aghi %r15,STACK_FRAME_OVERHEAD+__FGRAPH_RET_SIZE + aghi %r15,STACK_FRAME_SIZE_FREGS lgr %r14,%r2 lmg %r2,%r5,32(%r15) BR_EX %r14 diff --git a/arch/s390/kernel/os_info.c b/arch/s390/kernel/os_info.c index 29080d6d5d8d..c2a468986212 100644 --- a/arch/s390/kernel/os_info.c +++ b/arch/s390/kernel/os_info.c @@ -18,6 +18,7 @@ #include <asm/physmem_info.h> #include <asm/maccess.h> #include <asm/asm-offsets.h> +#include <asm/sections.h> #include <asm/ipl.h> /* diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index b0bc68da6a11..33205dd410e4 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -981,7 +981,7 @@ static int cfdiag_push_sample(struct perf_event *event, if (event->attr.sample_type & PERF_SAMPLE_RAW) { raw.frag.size = cpuhw->usedss; raw.frag.data = cpuhw->stop; - perf_sample_save_raw_data(&data, &raw); + perf_sample_save_raw_data(&data, event, &raw); } overflow = perf_event_overflow(event, &data, ®s); diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 1e99514fb7ae..5f60248cb468 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -981,7 +981,7 @@ static void cpumsf_pmu_disable(struct pmu *pmu) cpuhw->flags &= ~PMU_F_ENABLED; } -/* perf_exclude_event() - Filter event +/* perf_event_exclude() - Filter event * @event: The perf event * @regs: pt_regs structure * @sde_regs: Sample-data-entry (sde) regs structure @@ -990,7 +990,7 @@ static void cpumsf_pmu_disable(struct pmu *pmu) * * Return non-zero if the event shall be excluded. */ -static int perf_exclude_event(struct perf_event *event, struct pt_regs *regs, +static int perf_event_exclude(struct perf_event *event, struct pt_regs *regs, struct perf_sf_sde_regs *sde_regs) { if (event->attr.exclude_user && user_mode(regs)) @@ -1073,7 +1073,7 @@ static int perf_push_sample(struct perf_event *event, data.tid_entry.pid = basic->hpp & LPP_PID_MASK; overflow = 0; - if (perf_exclude_event(event, ®s, sde_regs)) + if (perf_event_exclude(event, ®s, sde_regs)) goto out; if (perf_event_overflow(event, &data, ®s)) { overflow = 1; diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c index fa7325454266..10725f5a6f0f 100644 --- a/arch/s390/kernel/perf_pai_crypto.c +++ b/arch/s390/kernel/perf_pai_crypto.c @@ -478,7 +478,7 @@ static int paicrypt_push_sample(size_t rawsize, struct paicrypt_map *cpump, if (event->attr.sample_type & PERF_SAMPLE_RAW) { raw.frag.size = rawsize; raw.frag.data = cpump->save; - perf_sample_save_raw_data(&data, &raw); + perf_sample_save_raw_data(&data, event, &raw); } overflow = perf_event_overflow(event, &data, ®s); diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c index 7f462bef1fc0..a8f0bad99cf0 100644 --- a/arch/s390/kernel/perf_pai_ext.c +++ b/arch/s390/kernel/perf_pai_ext.c @@ -503,7 +503,7 @@ static int paiext_push_sample(size_t rawsize, struct paiext_map *cpump, if (event->attr.sample_type & PERF_SAMPLE_RAW) { raw.frag.size = rawsize; raw.frag.data = cpump->save; - perf_sample_save_raw_data(&data, &raw); + perf_sample_save_raw_data(&data, event, &raw); } overflow = perf_event_overflow(event, &data, ®s); diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index a3fea683b227..0ce550faf073 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -157,18 +157,18 @@ u64 __bootdata_preserved(stfle_fac_list[16]); EXPORT_SYMBOL(stfle_fac_list); struct oldmem_data __bootdata_preserved(oldmem_data); -unsigned long VMALLOC_START; +unsigned long __bootdata_preserved(VMALLOC_START); EXPORT_SYMBOL(VMALLOC_START); -unsigned long VMALLOC_END; +unsigned long __bootdata_preserved(VMALLOC_END); EXPORT_SYMBOL(VMALLOC_END); -struct page *vmemmap; +struct page *__bootdata_preserved(vmemmap); EXPORT_SYMBOL(vmemmap); -unsigned long vmemmap_size; +unsigned long __bootdata_preserved(vmemmap_size); -unsigned long MODULES_VADDR; -unsigned long MODULES_END; +unsigned long __bootdata_preserved(MODULES_VADDR); +unsigned long __bootdata_preserved(MODULES_END); /* An array with a pointer to the lowcore of every CPU. */ struct lowcore *lowcore_ptr[NR_CPUS]; @@ -359,25 +359,17 @@ void *restart_stack; unsigned long stack_alloc(void) { -#ifdef CONFIG_VMAP_STACK - void *ret; + void *stack; - ret = __vmalloc_node(THREAD_SIZE, THREAD_SIZE, THREADINFO_GFP, - NUMA_NO_NODE, __builtin_return_address(0)); - kmemleak_not_leak(ret); - return (unsigned long)ret; -#else - return __get_free_pages(GFP_KERNEL, THREAD_SIZE_ORDER); -#endif + stack = __vmalloc_node(THREAD_SIZE, THREAD_SIZE, THREADINFO_GFP, + NUMA_NO_NODE, __builtin_return_address(0)); + kmemleak_not_leak(stack); + return (unsigned long)stack; } void stack_free(unsigned long stack) { -#ifdef CONFIG_VMAP_STACK - vfree((void *) stack); -#else - free_pages(stack, THREAD_SIZE_ORDER); -#endif + vfree((void *)stack); } static unsigned long __init stack_alloc_early(void) @@ -979,6 +971,7 @@ void __init setup_arch(char **cmdline_p) if (test_facility(193)) static_branch_enable(&cpu_has_bear); + setup_protection_map(); /* * Create kernel page tables. */ diff --git a/arch/s390/kernel/text_amode31.S b/arch/s390/kernel/text_amode31.S index c0a70efa2426..26f2981aa09e 100644 --- a/arch/s390/kernel/text_amode31.S +++ b/arch/s390/kernel/text_amode31.S @@ -18,8 +18,7 @@ * affects a few functions that are not performance-relevant. */ .macro BR_EX_AMODE31_r14 - larl %r1,0f - ex 0,0(%r1) + exrl 0,0f j . 0: br %r14 .endm diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 4f9c301a705b..39f5ed21f31a 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -556,6 +556,16 @@ static void __init alloc_masks(struct sysinfo_15_1_x *info, } } +static int __init detect_polarization(union topology_entry *tle) +{ + struct topology_core *tl_core; + + while (tle->nl) + tle = next_tle(tle); + tl_core = (struct topology_core *)tle; + return tl_core->pp != POLARIZATION_HRZ; +} + void __init topology_init_early(void) { struct sysinfo_15_1_x *info; @@ -575,6 +585,7 @@ void __init topology_init_early(void) __func__, PAGE_SIZE, PAGE_SIZE); info = tl_info; store_topology(info); + cpu_management = detect_polarization(info->tle); pr_info("The CPU configuration topology of the machine is: %d %d %d %d %d %d / %d\n", info->mag[0], info->mag[1], info->mag[2], info->mag[3], info->mag[4], info->mag[5], info->mnest); diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile index 37bb4b761229..ad206f2068d8 100644 --- a/arch/s390/kernel/vdso64/Makefile +++ b/arch/s390/kernel/vdso64/Makefile @@ -5,7 +5,7 @@ include $(srctree)/lib/vdso/Makefile obj-vdso64 = vdso_user_wrapper.o note.o vgetrandom-chacha.o obj-cvdso64 = vdso64_generic.o getcpu.o vgetrandom.o -VDSO_CFLAGS_REMOVE := -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE) $(CC_FLAGS_CHECK_STACK) +VDSO_CFLAGS_REMOVE := -pg $(CC_FLAGS_FTRACE) $(CC_FLAGS_EXPOLINE) CFLAGS_REMOVE_getcpu.o = $(VDSO_CFLAGS_REMOVE) CFLAGS_REMOVE_vgetrandom.o = $(VDSO_CFLAGS_REMOVE) CFLAGS_REMOVE_vdso64_generic.o = $(VDSO_CFLAGS_REMOVE) diff --git a/arch/s390/kernel/vmcore_info.c b/arch/s390/kernel/vmcore_info.c index 23f7d7619a99..cc8933e04ff7 100644 --- a/arch/s390/kernel/vmcore_info.c +++ b/arch/s390/kernel/vmcore_info.c @@ -1,8 +1,9 @@ // SPDX-License-Identifier: GPL-2.0-only #include <linux/vmcore_info.h> -#include <asm/abs_lowcore.h> #include <linux/mm.h> +#include <asm/abs_lowcore.h> +#include <asm/sections.h> #include <asm/setup.h> void arch_crash_save_vmcoreinfo(void) diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index ea8dce299954..d4f031e086fc 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -2678,9 +2678,13 @@ static int flic_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) kvm_s390_clear_float_irqs(dev->kvm); break; case KVM_DEV_FLIC_APF_ENABLE: + if (kvm_is_ucontrol(dev->kvm)) + return -EINVAL; dev->kvm->arch.gmap->pfault_enabled = 1; break; case KVM_DEV_FLIC_APF_DISABLE_WAIT: + if (kvm_is_ucontrol(dev->kvm)) + return -EINVAL; dev->kvm->arch.gmap->pfault_enabled = 0; /* * Make sure no async faults are in transition when @@ -2894,6 +2898,8 @@ int kvm_set_routing_entry(struct kvm *kvm, switch (ue->type) { /* we store the userspace addresses instead of the guest addresses */ case KVM_IRQ_ROUTING_S390_ADAPTER: + if (kvm_is_ucontrol(kvm)) + return -EINVAL; e->set = set_adapter_int; uaddr = gmap_translate(kvm->arch.gmap, ue->u.adapter.summary_addr); if (uaddr == -EFAULT) diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 150b9387860a..a687695d8f68 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -854,7 +854,7 @@ unpin: static void unpin_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page, gpa_t gpa) { - hpa_t hpa = (hpa_t) vsie_page->scb_o; + hpa_t hpa = virt_to_phys(vsie_page->scb_o); if (hpa) unpin_guest_page(vcpu->kvm, gpa, hpa); diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S index 08f60a42b9a6..d026debf250c 100644 --- a/arch/s390/lib/mem.S +++ b/arch/s390/lib/mem.S @@ -34,8 +34,7 @@ SYM_FUNC_START(__memmove) la %r3,256(%r3) brctg %r0,.Lmemmove_forward_loop .Lmemmove_forward_remainder: - larl %r5,.Lmemmove_mvc - ex %r4,0(%r5) + exrl %r4,.Lmemmove_mvc .Lmemmove_exit: BR_EX %r14 .Lmemmove_reverse: @@ -83,8 +82,7 @@ SYM_FUNC_START(__memset) la %r1,256(%r1) brctg %r3,.Lmemset_clear_loop .Lmemset_clear_remainder: - larl %r3,.Lmemset_xc - ex %r4,0(%r3) + exrl %r4,.Lmemset_xc .Lmemset_exit: BR_EX %r14 .Lmemset_fill: @@ -102,8 +100,7 @@ SYM_FUNC_START(__memset) brctg %r5,.Lmemset_fill_loop .Lmemset_fill_remainder: stc %r3,0(%r1) - larl %r5,.Lmemset_mvc - ex %r4,0(%r5) + exrl %r4,.Lmemset_mvc BR_EX %r14 .Lmemset_fill_exit: stc %r3,0(%r1) @@ -132,8 +129,7 @@ SYM_FUNC_START(__memcpy) lgr %r1,%r2 jnz .Lmemcpy_loop .Lmemcpy_remainder: - larl %r5,.Lmemcpy_mvc - ex %r4,0(%r5) + exrl %r4,.Lmemcpy_mvc .Lmemcpy_exit: BR_EX %r14 .Lmemcpy_loop: @@ -175,8 +171,7 @@ SYM_FUNC_START(__memset\bits) brctg %r5,.L__memset_loop\bits .L__memset_remainder\bits: \insn %r3,0(%r1) - larl %r5,.L__memset_mvc\bits - ex %r4,0(%r5) + exrl %r4,.L__memset_mvc\bits BR_EX %r14 .L__memset_store\bits: \insn %r3,0(%r2) diff --git a/arch/s390/lib/xor.c b/arch/s390/lib/xor.c index fb924a8041dc..ce7bcf7c0032 100644 --- a/arch/s390/lib/xor.c +++ b/arch/s390/lib/xor.c @@ -15,7 +15,6 @@ static void xor_xc_2(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p2) { asm volatile( - " larl 1,2f\n" " aghi %0,-1\n" " jm 3f\n" " srlg 0,%0,8\n" @@ -25,12 +24,12 @@ static void xor_xc_2(unsigned long bytes, unsigned long * __restrict p1, " la %1,256(%1)\n" " la %2,256(%2)\n" " brctg 0,0b\n" - "1: ex %0,0(1)\n" + "1: exrl %0,2f\n" " j 3f\n" "2: xc 0(1,%1),0(%2)\n" "3:\n" : : "d" (bytes), "a" (p1), "a" (p2) - : "0", "1", "cc", "memory"); + : "0", "cc", "memory"); } static void xor_xc_3(unsigned long bytes, unsigned long * __restrict p1, @@ -38,9 +37,8 @@ static void xor_xc_3(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p3) { asm volatile( - " larl 1,2f\n" " aghi %0,-1\n" - " jm 3f\n" + " jm 4f\n" " srlg 0,%0,8\n" " ltgr 0,0\n" " jz 1f\n" @@ -50,14 +48,14 @@ static void xor_xc_3(unsigned long bytes, unsigned long * __restrict p1, " la %2,256(%2)\n" " la %3,256(%3)\n" " brctg 0,0b\n" - "1: ex %0,0(1)\n" - " ex %0,6(1)\n" - " j 3f\n" + "1: exrl %0,2f\n" + " exrl %0,3f\n" + " j 4f\n" "2: xc 0(1,%1),0(%2)\n" - " xc 0(1,%1),0(%3)\n" - "3:\n" + "3: xc 0(1,%1),0(%3)\n" + "4:\n" : "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3) - : : "0", "1", "cc", "memory"); + : : "0", "cc", "memory"); } static void xor_xc_4(unsigned long bytes, unsigned long * __restrict p1, @@ -66,9 +64,8 @@ static void xor_xc_4(unsigned long bytes, unsigned long * __restrict p1, const unsigned long * __restrict p4) { asm volatile( - " larl 1,2f\n" " aghi %0,-1\n" - " jm 3f\n" + " jm 5f\n" " srlg 0,%0,8\n" " ltgr 0,0\n" " jz 1f\n" @@ -80,16 +77,16 @@ static void xor_xc_4(unsigned long bytes, unsigned long * __restrict p1, " la %3,256(%3)\n" " la %4,256(%4)\n" " brctg 0,0b\n" - "1: ex %0,0(1)\n" - " ex %0,6(1)\n" - " ex %0,12(1)\n" - " j 3f\n" + "1: exrl %0,2f\n" + " exrl %0,3f\n" + " exrl %0,4f\n" + " j 5f\n" "2: xc 0(1,%1),0(%2)\n" - " xc 0(1,%1),0(%3)\n" - " xc 0(1,%1),0(%4)\n" - "3:\n" + "3: xc 0(1,%1),0(%3)\n" + "4: xc 0(1,%1),0(%4)\n" + "5:\n" : "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4) - : : "0", "1", "cc", "memory"); + : : "0", "cc", "memory"); } static void xor_xc_5(unsigned long bytes, unsigned long * __restrict p1, @@ -101,7 +98,7 @@ static void xor_xc_5(unsigned long bytes, unsigned long * __restrict p1, asm volatile( " larl 1,2f\n" " aghi %0,-1\n" - " jm 3f\n" + " jm 6f\n" " srlg 0,%0,8\n" " ltgr 0,0\n" " jz 1f\n" @@ -115,19 +112,19 @@ static void xor_xc_5(unsigned long bytes, unsigned long * __restrict p1, " la %4,256(%4)\n" " la %5,256(%5)\n" " brctg 0,0b\n" - "1: ex %0,0(1)\n" - " ex %0,6(1)\n" - " ex %0,12(1)\n" - " ex %0,18(1)\n" - " j 3f\n" + "1: exrl %0,2f\n" + " exrl %0,3f\n" + " exrl %0,4f\n" + " exrl %0,5f\n" + " j 6f\n" "2: xc 0(1,%1),0(%2)\n" - " xc 0(1,%1),0(%3)\n" - " xc 0(1,%1),0(%4)\n" - " xc 0(1,%1),0(%5)\n" - "3:\n" + "3: xc 0(1,%1),0(%3)\n" + "4: xc 0(1,%1),0(%4)\n" + "5: xc 0(1,%1),0(%5)\n" + "6:\n" : "+d" (bytes), "+a" (p1), "+a" (p2), "+a" (p3), "+a" (p4), "+a" (p5) - : : "0", "1", "cc", "memory"); + : : "0", "cc", "memory"); } struct xor_block_template xor_block_xc = { diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 7a96623a9d2e..f2298f7a3f21 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -56,6 +56,15 @@ pgd_t invalid_pg_dir[PTRS_PER_PGD] __section(".bss..invalid_pg_dir"); struct ctlreg __bootdata_preserved(s390_invalid_asce); +unsigned long __bootdata_preserved(page_noexec_mask); +EXPORT_SYMBOL(page_noexec_mask); + +unsigned long __bootdata_preserved(segment_noexec_mask); +EXPORT_SYMBOL(segment_noexec_mask); + +unsigned long __bootdata_preserved(region_noexec_mask); +EXPORT_SYMBOL(region_noexec_mask); + unsigned long empty_zero_page, zero_page_mask; EXPORT_SYMBOL(empty_zero_page); EXPORT_SYMBOL(zero_page_mask); diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index 28a18c42ba99..44426e0f2944 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -17,6 +17,7 @@ #include <asm/asm-extable.h> #include <asm/abs_lowcore.h> #include <asm/stacktrace.h> +#include <asm/sections.h> #include <asm/maccess.h> #include <asm/ctlreg.h> diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c index 33f3504be90b..76f376876e0d 100644 --- a/arch/s390/mm/mmap.c +++ b/arch/s390/mm/mmap.c @@ -196,22 +196,28 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) } } -static const pgprot_t protection_map[16] = { - [VM_NONE] = PAGE_NONE, - [VM_READ] = PAGE_RO, - [VM_WRITE] = PAGE_RO, - [VM_WRITE | VM_READ] = PAGE_RO, - [VM_EXEC] = PAGE_RX, - [VM_EXEC | VM_READ] = PAGE_RX, - [VM_EXEC | VM_WRITE] = PAGE_RX, - [VM_EXEC | VM_WRITE | VM_READ] = PAGE_RX, - [VM_SHARED] = PAGE_NONE, - [VM_SHARED | VM_READ] = PAGE_RO, - [VM_SHARED | VM_WRITE] = PAGE_RW, - [VM_SHARED | VM_WRITE | VM_READ] = PAGE_RW, - [VM_SHARED | VM_EXEC] = PAGE_RX, - [VM_SHARED | VM_EXEC | VM_READ] = PAGE_RX, - [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_RWX, - [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_RWX -}; +static pgprot_t protection_map[16] __ro_after_init; + +void __init setup_protection_map(void) +{ + pgprot_t *pm = protection_map; + + pm[VM_NONE] = PAGE_NONE; + pm[VM_READ] = PAGE_RO; + pm[VM_WRITE] = PAGE_RO; + pm[VM_WRITE | VM_READ] = PAGE_RO; + pm[VM_EXEC] = PAGE_RX; + pm[VM_EXEC | VM_READ] = PAGE_RX; + pm[VM_EXEC | VM_WRITE] = PAGE_RX; + pm[VM_EXEC | VM_WRITE | VM_READ] = PAGE_RX; + pm[VM_SHARED] = PAGE_NONE; + pm[VM_SHARED | VM_READ] = PAGE_RO; + pm[VM_SHARED | VM_WRITE] = PAGE_RW; + pm[VM_SHARED | VM_WRITE | VM_READ] = PAGE_RW; + pm[VM_SHARED | VM_EXEC] = PAGE_RX; + pm[VM_SHARED | VM_EXEC | VM_READ] = PAGE_RX; + pm[VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_RWX; + pm[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_RWX; +} + DECLARE_VM_GET_PAGE_PROT diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c index 8f56a21a077f..eae97fb61712 100644 --- a/arch/s390/mm/pageattr.c +++ b/arch/s390/mm/pageattr.c @@ -109,8 +109,6 @@ static int walk_pte_level(pmd_t *pmdp, unsigned long addr, unsigned long end, } else if (flags & SET_MEMORY_DEF) { new = __pte(pte_val(new) & PAGE_MASK); new = set_pte_bit(new, PAGE_KERNEL); - if (!MACHINE_HAS_NX) - new = clear_pte_bit(new, __pgprot(_PAGE_NOEXEC)); } pgt_set((unsigned long *)ptep, pte_val(new), addr, CRDTE_DTT_PAGE); ptep++; @@ -167,8 +165,6 @@ static void modify_pmd_page(pmd_t *pmdp, unsigned long addr, } else if (flags & SET_MEMORY_DEF) { new = __pmd(pmd_val(new) & PMD_MASK); new = set_pmd_bit(new, SEGMENT_KERNEL); - if (!MACHINE_HAS_NX) - new = clear_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_NOEXEC)); } pgt_set((unsigned long *)pmdp, pmd_val(new), addr, CRDTE_DTT_SEGMENT); } @@ -256,8 +252,6 @@ static void modify_pud_page(pud_t *pudp, unsigned long addr, } else if (flags & SET_MEMORY_DEF) { new = __pud(pud_val(new) & PUD_MASK); new = set_pud_bit(new, REGION3_KERNEL); - if (!MACHINE_HAS_NX) - new = clear_pud_bit(new, __pgprot(_REGION_ENTRY_NOEXEC)); } pgt_set((unsigned long *)pudp, pud_val(new), addr, CRDTE_DTT_REGION3); } diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index cea5dba80468..f05e62e037c2 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -360,8 +360,6 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pgste_t pgste; struct mm_struct *mm = vma->vm_mm; - if (!MACHINE_HAS_NX) - pte = clear_pte_bit(pte, __pgprot(_PAGE_NOEXEC)); if (mm_has_pgste(mm)) { pgste = pgste_get(ptep); pgste_set_key(ptep, pgste, pte, mm); diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 665b8228afeb..7c684c54e721 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -171,9 +171,6 @@ static int __ref modify_pte_table(pmd_t *pmd, unsigned long addr, pte_t *pte; prot = pgprot_val(PAGE_KERNEL); - if (!MACHINE_HAS_NX) - prot &= ~_PAGE_NOEXEC; - pte = pte_offset_kernel(pmd, addr); for (; addr < end; addr += PAGE_SIZE, pte++) { if (!add) { @@ -230,9 +227,6 @@ static int __ref modify_pmd_table(pud_t *pud, unsigned long addr, pte_t *pte; prot = pgprot_val(SEGMENT_KERNEL); - if (!MACHINE_HAS_NX) - prot &= ~_SEGMENT_ENTRY_NOEXEC; - pmd = pmd_offset(pud, addr); for (; addr < end; addr = next, pmd++) { next = pmd_addr_end(addr, end); @@ -324,8 +318,6 @@ static int modify_pud_table(p4d_t *p4d, unsigned long addr, unsigned long end, pmd_t *pmd; prot = pgprot_val(REGION3_KERNEL); - if (!MACHINE_HAS_NX) - prot &= ~_REGION_ENTRY_NOEXEC; pud = pud_offset(p4d, addr); for (; addr < end; addr = next, pud++) { next = pud_addr_end(addr, end); diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile index 2c21f0394c9a..df73c5182990 100644 --- a/arch/s390/pci/Makefile +++ b/arch/s390/pci/Makefile @@ -5,6 +5,6 @@ obj-$(CONFIG_PCI) += pci.o pci_irq.o pci_clp.o \ pci_event.o pci_debug.o pci_insn.o pci_mmio.o \ - pci_bus.o pci_kvm_hook.o + pci_bus.o pci_kvm_hook.o pci_report.o obj-$(CONFIG_PCI_IOV) += pci_iov.o obj-$(CONFIG_SYSFS) += pci_sysfs.o diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index 7f7b732b3f3e..7bd7721c1239 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -16,6 +16,7 @@ #include <asm/sclp.h> #include "pci_bus.h" +#include "pci_report.h" /* Content Code Description for PCI Function Error */ struct zpci_ccdf_err { @@ -169,6 +170,8 @@ static pci_ers_result_t zpci_event_do_reset(struct pci_dev *pdev, static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) { pci_ers_result_t ers_res = PCI_ERS_RESULT_DISCONNECT; + struct zpci_dev *zdev = to_zpci(pdev); + char *status_str = "success"; struct pci_driver *driver; /* @@ -186,29 +189,37 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) if (is_passed_through(pdev)) { pr_info("%s: Cannot be recovered in the host because it is a pass-through device\n", pci_name(pdev)); + status_str = "failed (pass-through)"; goto out_unlock; } driver = to_pci_driver(pdev->dev.driver); if (!is_driver_supported(driver)) { - if (!driver) + if (!driver) { pr_info("%s: Cannot be recovered because no driver is bound to the device\n", pci_name(pdev)); - else + status_str = "failed (no driver)"; + } else { pr_info("%s: The %s driver bound to the device does not support error recovery\n", pci_name(pdev), driver->name); + status_str = "failed (no driver support)"; + } goto out_unlock; } ers_res = zpci_event_notify_error_detected(pdev, driver); - if (ers_result_indicates_abort(ers_res)) + if (ers_result_indicates_abort(ers_res)) { + status_str = "failed (abort on detection)"; goto out_unlock; + } if (ers_res == PCI_ERS_RESULT_CAN_RECOVER) { ers_res = zpci_event_do_error_state_clear(pdev, driver); - if (ers_result_indicates_abort(ers_res)) + if (ers_result_indicates_abort(ers_res)) { + status_str = "failed (abort on MMIO enable)"; goto out_unlock; + } } if (ers_res == PCI_ERS_RESULT_NEED_RESET) @@ -217,6 +228,7 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) if (ers_res != PCI_ERS_RESULT_RECOVERED) { pr_err("%s: Automatic recovery failed; operator intervention is required\n", pci_name(pdev)); + status_str = "failed (driver can't recover)"; goto out_unlock; } @@ -225,6 +237,7 @@ static pci_ers_result_t zpci_event_attempt_error_recovery(struct pci_dev *pdev) driver->err_handler->resume(pdev); out_unlock: pci_dev_unlock(pdev); + zpci_report_status(zdev, "recovery", status_str); return ers_res; } diff --git a/arch/s390/pci/pci_report.c b/arch/s390/pci/pci_report.c new file mode 100644 index 000000000000..1b494e5ecc4d --- /dev/null +++ b/arch/s390/pci/pci_report.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright IBM Corp. 2024 + * + * Author(s): + * Niklas Schnelle <schnelle@linux.ibm.com> + * + */ + +#define KMSG_COMPONENT "zpci" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/kernel.h> +#include <linux/sprintf.h> +#include <linux/pci.h> + +#include <asm/sclp.h> +#include <asm/debug.h> +#include <asm/pci_debug.h> + +#include "pci_report.h" + +#define ZPCI_ERR_LOG_ID_KERNEL_REPORT 0x4714 + +struct zpci_report_error_data { + u64 timestamp; + u64 err_log_id; + char log_data[]; +} __packed; + +#define ZPCI_REPORT_SIZE (PAGE_SIZE - sizeof(struct err_notify_sccb)) +#define ZPCI_REPORT_DATA_SIZE (ZPCI_REPORT_SIZE - sizeof(struct zpci_report_error_data)) + +struct zpci_report_error { + struct zpci_report_error_header header; + struct zpci_report_error_data data; +} __packed; + +static const char *zpci_state_str(pci_channel_state_t state) +{ + switch (state) { + case pci_channel_io_normal: + return "normal"; + case pci_channel_io_frozen: + return "frozen"; + case pci_channel_io_perm_failure: + return "permanent-failure"; + default: + return "invalid"; + }; +} + +static int debug_log_header_fn(debug_info_t *id, struct debug_view *view, + int area, debug_entry_t *entry, char *out_buf, + size_t out_buf_size) +{ + unsigned long sec, usec; + unsigned int level; + char *except_str; + int rc = 0; + + level = entry->level; + sec = entry->clock; + usec = do_div(sec, USEC_PER_SEC); + + if (entry->exception) + except_str = "*"; + else + except_str = "-"; + rc += scnprintf(out_buf, out_buf_size, "%011ld:%06lu %1u %1s %04u ", + sec, usec, level, except_str, + entry->cpu); + return rc; +} + +static int debug_prolog_header(debug_info_t *id, struct debug_view *view, + char *out_buf, size_t out_buf_size) +{ + return scnprintf(out_buf, out_buf_size, "sec:usec level except cpu msg\n"); +} + +static struct debug_view debug_log_view = { + "pci_msg_log", + &debug_prolog_header, + &debug_log_header_fn, + &debug_sprintf_format_fn, + NULL, + NULL +}; + +/** + * zpci_report_status - Report the status of operations on a PCI device + * @zdev: The PCI device for which to report status + * @operation: A string representing the operation reported + * @status: A string representing the status of the operation + * + * This function creates a human readable report about an operation such as + * PCI device recovery and forwards this to the platform using the SCLP Write + * Event Data mechanism. Besides the operation and status strings the report + * also contains additional information about the device deemed useful for + * debug such as the currently bound device driver, if any, and error state. + * Additionally a string representation of pci_debug_msg_id, or as much as fits, + * is also included. + * + * Return: 0 on success an error code < 0 otherwise. + */ +int zpci_report_status(struct zpci_dev *zdev, const char *operation, const char *status) +{ + struct zpci_report_error *report; + struct pci_driver *driver = NULL; + struct pci_dev *pdev = NULL; + char *buf, *end; + int ret; + + if (!zdev || !zdev->zbus) + return -ENODEV; + + /* Protected virtualization hosts get nothing from us */ + if (prot_virt_guest) + return -ENODATA; + + report = (void *)get_zeroed_page(GFP_KERNEL); + if (!report) + return -ENOMEM; + if (zdev->zbus->bus) + pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); + if (pdev) + driver = to_pci_driver(pdev->dev.driver); + + buf = report->data.log_data; + end = report->data.log_data + ZPCI_REPORT_DATA_SIZE; + buf += scnprintf(buf, end - buf, "report: %s\n", operation); + buf += scnprintf(buf, end - buf, "status: %s\n", status); + buf += scnprintf(buf, end - buf, "state: %s\n", + (pdev) ? zpci_state_str(pdev->error_state) : "n/a"); + buf += scnprintf(buf, end - buf, "driver: %s\n", (driver) ? driver->name : "n/a"); + ret = debug_dump(pci_debug_msg_id, &debug_log_view, buf, end - buf, true); + if (ret < 0) + pr_err("Reading PCI debug messages failed with code %d\n", ret); + else + buf += ret; + + report->header.version = 1; + report->header.action = SCLP_ERRNOTIFY_AQ_INFO_LOG; + report->header.length = buf - (char *)&report->data; + report->data.timestamp = ktime_get_clocktai_seconds(); + report->data.err_log_id = ZPCI_ERR_LOG_ID_KERNEL_REPORT; + + ret = sclp_pci_report(&report->header, zdev->fh, zdev->fid); + if (ret) + pr_err("Reporting PCI status failed with code %d\n", ret); + else + pr_info("Reported PCI device status\n"); + + free_page((unsigned long)report); + + return ret; +} diff --git a/arch/s390/pci/pci_report.h b/arch/s390/pci/pci_report.h new file mode 100644 index 000000000000..e08003d51a97 --- /dev/null +++ b/arch/s390/pci/pci_report.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright IBM Corp. 2024 + * + * Author(s): + * Niklas Schnelle <schnelle@linux.ibm.com> + * + */ +#ifndef __S390_PCI_REPORT_H +#define __S390_PCI_REPORT_H + +struct zpci_dev; + +int zpci_report_status(struct zpci_dev *zdev, const char *operation, const char *status); + +#endif /* __S390_PCI_REPORT_H */ diff --git a/arch/s390/pci/pci_sysfs.c b/arch/s390/pci/pci_sysfs.c index 5f46ad58dcd1..2de1ea6c3a8c 100644 --- a/arch/s390/pci/pci_sysfs.c +++ b/arch/s390/pci/pci_sysfs.c @@ -135,7 +135,7 @@ out: static DEVICE_ATTR_WO(recover); static ssize_t util_string_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct device *dev = kobj_to_dev(kobj); @@ -145,10 +145,10 @@ static ssize_t util_string_read(struct file *filp, struct kobject *kobj, return memory_read_from_buffer(buf, count, &off, zdev->util_str, sizeof(zdev->util_str)); } -static BIN_ATTR_RO(util_string, CLP_UTIL_STR_LEN); +static const BIN_ATTR_RO(util_string, CLP_UTIL_STR_LEN); static ssize_t report_error_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, char *buf, + const struct bin_attribute *attr, char *buf, loff_t off, size_t count) { struct zpci_report_error_header *report = (void *) buf; @@ -164,7 +164,7 @@ static ssize_t report_error_write(struct file *filp, struct kobject *kobj, return ret ? ret : count; } -static BIN_ATTR(report_error, S_IWUSR, NULL, report_error_write, PAGE_SIZE); +static const BIN_ATTR(report_error, S_IWUSR, NULL, report_error_write, PAGE_SIZE); static ssize_t uid_is_unique_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -203,7 +203,7 @@ const struct attribute_group zpci_ident_attr_group = { .is_visible = zpci_index_is_visible, }; -static struct bin_attribute *zpci_bin_attrs[] = { +static const struct bin_attribute *const zpci_bin_attrs[] = { &bin_attr_util_string, &bin_attr_report_error, NULL, @@ -227,7 +227,7 @@ static struct attribute *zpci_dev_attrs[] = { const struct attribute_group zpci_attr_group = { .attrs = zpci_dev_attrs, - .bin_attrs = zpci_bin_attrs, + .bin_attrs_new = zpci_bin_attrs, }; static struct attribute *pfip_attrs[] = { diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 66c1a8835e36..0b1e61f72fb3 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -865,7 +865,6 @@ static int ubd_add(int n, char **error_out) ubd_dev->tag_set.ops = &ubd_mq_ops; ubd_dev->tag_set.queue_depth = 64; ubd_dev->tag_set.numa_node = NUMA_NO_NODE; - ubd_dev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; ubd_dev->tag_set.driver_data = ubd_dev; ubd_dev->tag_set.nr_hw_queues = 1; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9d7bd0ae48c4..27c21c9b6a70 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -83,7 +83,6 @@ config X86 select ARCH_HAS_DMA_OPS if GART_IOMMU || XEN select ARCH_HAS_EARLY_DEBUG if KGDB select ARCH_HAS_ELF_RANDOMIZE - select ARCH_HAS_EXECMEM_ROX if X86_64 select ARCH_HAS_FAST_MULTIPLIER select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL @@ -225,6 +224,7 @@ config X86 select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS select HAVE_DYNAMIC_FTRACE_WITH_ARGS if X86_64 + select HAVE_FTRACE_REGS_HAVING_PT_REGS if X86_64 select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS select HAVE_SAMPLE_FTRACE_DIRECT if X86_64 select HAVE_SAMPLE_FTRACE_DIRECT_MULTI if X86_64 @@ -234,8 +234,9 @@ config X86 select HAVE_EXIT_THREAD select HAVE_GUP_FAST select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE + select HAVE_FTRACE_GRAPH_FUNC if HAVE_FUNCTION_GRAPH_TRACER select HAVE_FTRACE_MCOUNT_RECORD - select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FUNCTION_GRAPH_FREGS if HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_GRAPH_TRACER if X86_32 || (X86_64 && DYNAMIC_FTRACE) select HAVE_FUNCTION_TRACER select HAVE_GCC_PLUGINS @@ -1189,7 +1190,7 @@ config X86_MCE_INTEL config X86_MCE_AMD def_bool y prompt "AMD MCE features" - depends on X86_MCE && X86_LOCAL_APIC && AMD_NB + depends on X86_MCE && X86_LOCAL_APIC help Additional support for AMD specific MCE features such as the DRAM Error Threshold. @@ -1559,6 +1560,7 @@ config AMD_MEM_ENCRYPT select ARCH_HAS_CC_PLATFORM select X86_MEM_ENCRYPT select UNACCEPTED_MEMORY + select CRYPTO_LIB_AESGCM help Say yes to enable support for the encryption of system memory. This requires an AMD processor that supports Secure Memory @@ -3129,6 +3131,10 @@ endif # X86_32 config AMD_NB def_bool y + depends on AMD_NODE + +config AMD_NODE + def_bool y depends on CPU_SUP_AMD && PCI endmenu diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 74777a97e394..1eb4d23cdaae 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -97,7 +97,7 @@ config IOMMU_DEBUG code. When you use it make sure you have a big enough IOMMU/AGP aperture. Most of the options enabled by this can be set more finegrained using the iommu= command line - options. See Documentation/arch/x86/x86_64/boot-options.rst for more + options. See Documentation/admin-guide/kernel-parameters.txt for more details. config IOMMU_LEAK diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index f4d82379bf44..f03d59ea6e40 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -25,10 +25,6 @@ #include "efi.h" #include <generated/compile.h> -#include <linux/module.h> -#include <linux/uts.h> -#include <linux/utsname.h> -#include <linux/ctype.h> #include <generated/utsversion.h> #include <generated/utsrelease.h> diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index cd44e120fe53..bb55934c1cee 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -401,7 +401,8 @@ finish: * by the guest kernel. As and when a new feature is implemented in the * guest kernel, a corresponding bit should be added to the mask. */ -#define SNP_FEATURES_PRESENT MSR_AMD64_SNP_DEBUG_SWAP +#define SNP_FEATURES_PRESENT (MSR_AMD64_SNP_DEBUG_SWAP | \ + MSR_AMD64_SNP_SECURE_TSC) u64 snp_get_unsupported_features(u64 status) { diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index 0f81f70aca82..9a0ddda3aa69 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -65,7 +65,6 @@ static __maybe_unused __always_inline bool amd_cc_platform_vtom(enum cc_attr att * up under SME the trampoline area cannot be encrypted, whereas under SEV * the trampoline area must be encrypted. */ - static bool noinstr amd_cc_platform_has(enum cc_attr attr) { #ifdef CONFIG_AMD_MEM_ENCRYPT @@ -97,6 +96,9 @@ static bool noinstr amd_cc_platform_has(enum cc_attr attr) case CC_ATTR_GUEST_SEV_SNP: return sev_status & MSR_AMD64_SEV_SNP_ENABLED; + case CC_ATTR_GUEST_SNP_SECURE_TSC: + return sev_status & MSR_AMD64_SNP_SECURE_TSC; + case CC_ATTR_HOST_SEV_SNP: return cc_flags.host_sev_snp; diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c index c5b0148b8c0a..65d676c0f7bc 100644 --- a/arch/x86/coco/sev/core.c +++ b/arch/x86/coco/sev/core.c @@ -25,6 +25,7 @@ #include <linux/psp-sev.h> #include <linux/dmi.h> #include <uapi/linux/sev-guest.h> +#include <crypto/gcm.h> #include <asm/init.h> #include <asm/cpu_entry_area.h> @@ -95,6 +96,15 @@ static u64 sev_hv_features __ro_after_init; /* Secrets page physical address from the CC blob */ static u64 secrets_pa __ro_after_init; +/* + * For Secure TSC guests, the BSP fetches TSC_INFO using SNP guest messaging and + * initializes snp_tsc_scale and snp_tsc_offset. These values are replicated + * across the APs VMSA fields (TSC_SCALE and TSC_OFFSET). + */ +static u64 snp_tsc_scale __ro_after_init; +static u64 snp_tsc_offset __ro_after_init; +static u64 snp_tsc_freq_khz __ro_after_init; + /* #VC handler runtime per-CPU data */ struct sev_es_runtime_data { struct ghcb ghcb_page; @@ -1276,6 +1286,12 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip) vmsa->vmpl = snp_vmpl; vmsa->sev_features = sev_status >> 2; + /* Populate AP's TSC scale/offset to get accurate TSC values. */ + if (cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC)) { + vmsa->tsc_scale = snp_tsc_scale; + vmsa->tsc_offset = snp_tsc_offset; + } + /* Switch the page over to a VMSA page now that it is initialized */ ret = snp_set_vmsa(vmsa, caa, apic_id, true); if (ret) { @@ -1418,6 +1434,41 @@ static enum es_result __vc_handle_msr_caa(struct pt_regs *regs, bool write) return ES_OK; } +/* + * TSC related accesses should not exit to the hypervisor when a guest is + * executing with Secure TSC enabled, so special handling is required for + * accesses of MSR_IA32_TSC and MSR_AMD64_GUEST_TSC_FREQ. + */ +static enum es_result __vc_handle_secure_tsc_msrs(struct pt_regs *regs, bool write) +{ + u64 tsc; + + /* + * GUEST_TSC_FREQ should not be intercepted when Secure TSC is enabled. + * Terminate the SNP guest when the interception is enabled. + */ + if (regs->cx == MSR_AMD64_GUEST_TSC_FREQ) + return ES_VMM_ERROR; + + /* + * Writes: Writing to MSR_IA32_TSC can cause subsequent reads of the TSC + * to return undefined values, so ignore all writes. + * + * Reads: Reads of MSR_IA32_TSC should return the current TSC value, use + * the value returned by rdtsc_ordered(). + */ + if (write) { + WARN_ONCE(1, "TSC MSR writes are verboten!\n"); + return ES_OK; + } + + tsc = rdtsc_ordered(); + regs->ax = lower_32_bits(tsc); + regs->dx = upper_32_bits(tsc); + + return ES_OK; +} + static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { struct pt_regs *regs = ctxt->regs; @@ -1427,8 +1478,18 @@ static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt) /* Is it a WRMSR? */ write = ctxt->insn.opcode.bytes[1] == 0x30; - if (regs->cx == MSR_SVSM_CAA) + switch (regs->cx) { + case MSR_SVSM_CAA: return __vc_handle_msr_caa(regs, write); + case MSR_IA32_TSC: + case MSR_AMD64_GUEST_TSC_FREQ: + if (sev_status & MSR_AMD64_SNP_SECURE_TSC) + return __vc_handle_secure_tsc_msrs(regs, write); + else + break; + default: + break; + } ghcb_set_rcx(ghcb, regs->cx); if (write) { @@ -2508,8 +2569,8 @@ int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, } EXPORT_SYMBOL_GPL(snp_issue_svsm_attest_req); -int snp_issue_guest_request(struct snp_guest_req *req, struct snp_req_data *input, - struct snp_guest_request_ioctl *rio) +static int snp_issue_guest_request(struct snp_guest_req *req, struct snp_req_data *input, + struct snp_guest_request_ioctl *rio) { struct ghcb_state state; struct es_em_ctxt ctxt; @@ -2571,7 +2632,6 @@ e_restore_irq: return ret; } -EXPORT_SYMBOL_GPL(snp_issue_guest_request); static struct platform_device sev_guest_device = { .name = "sev-guest", @@ -2580,15 +2640,9 @@ static struct platform_device sev_guest_device = { static int __init snp_init_platform_device(void) { - struct sev_guest_platform_data data; - if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) return -ENODEV; - data.secrets_gpa = secrets_pa; - if (platform_device_add_data(&sev_guest_device, &data, sizeof(data))) - return -ENODEV; - if (platform_device_register(&sev_guest_device)) return -ENODEV; @@ -2667,3 +2721,581 @@ static int __init sev_sysfs_init(void) } arch_initcall(sev_sysfs_init); #endif // CONFIG_SYSFS + +static void free_shared_pages(void *buf, size_t sz) +{ + unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; + int ret; + + if (!buf) + return; + + ret = set_memory_encrypted((unsigned long)buf, npages); + if (ret) { + WARN_ONCE(ret, "failed to restore encryption mask (leak it)\n"); + return; + } + + __free_pages(virt_to_page(buf), get_order(sz)); +} + +static void *alloc_shared_pages(size_t sz) +{ + unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; + struct page *page; + int ret; + + page = alloc_pages(GFP_KERNEL_ACCOUNT, get_order(sz)); + if (!page) + return NULL; + + ret = set_memory_decrypted((unsigned long)page_address(page), npages); + if (ret) { + pr_err("failed to mark page shared, ret=%d\n", ret); + __free_pages(page, get_order(sz)); + return NULL; + } + + return page_address(page); +} + +static u8 *get_vmpck(int id, struct snp_secrets_page *secrets, u32 **seqno) +{ + u8 *key = NULL; + + switch (id) { + case 0: + *seqno = &secrets->os_area.msg_seqno_0; + key = secrets->vmpck0; + break; + case 1: + *seqno = &secrets->os_area.msg_seqno_1; + key = secrets->vmpck1; + break; + case 2: + *seqno = &secrets->os_area.msg_seqno_2; + key = secrets->vmpck2; + break; + case 3: + *seqno = &secrets->os_area.msg_seqno_3; + key = secrets->vmpck3; + break; + default: + break; + } + + return key; +} + +static struct aesgcm_ctx *snp_init_crypto(u8 *key, size_t keylen) +{ + struct aesgcm_ctx *ctx; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return NULL; + + if (aesgcm_expandkey(ctx, key, keylen, AUTHTAG_LEN)) { + pr_err("Crypto context initialization failed\n"); + kfree(ctx); + return NULL; + } + + return ctx; +} + +int snp_msg_init(struct snp_msg_desc *mdesc, int vmpck_id) +{ + /* Adjust the default VMPCK key based on the executing VMPL level */ + if (vmpck_id == -1) + vmpck_id = snp_vmpl; + + mdesc->vmpck = get_vmpck(vmpck_id, mdesc->secrets, &mdesc->os_area_msg_seqno); + if (!mdesc->vmpck) { + pr_err("Invalid VMPCK%d communication key\n", vmpck_id); + return -EINVAL; + } + + /* Verify that VMPCK is not zero. */ + if (!memchr_inv(mdesc->vmpck, 0, VMPCK_KEY_LEN)) { + pr_err("Empty VMPCK%d communication key\n", vmpck_id); + return -EINVAL; + } + + mdesc->vmpck_id = vmpck_id; + + mdesc->ctx = snp_init_crypto(mdesc->vmpck, VMPCK_KEY_LEN); + if (!mdesc->ctx) + return -ENOMEM; + + return 0; +} +EXPORT_SYMBOL_GPL(snp_msg_init); + +struct snp_msg_desc *snp_msg_alloc(void) +{ + struct snp_msg_desc *mdesc; + void __iomem *mem; + + BUILD_BUG_ON(sizeof(struct snp_guest_msg) > PAGE_SIZE); + + mdesc = kzalloc(sizeof(struct snp_msg_desc), GFP_KERNEL); + if (!mdesc) + return ERR_PTR(-ENOMEM); + + mem = ioremap_encrypted(secrets_pa, PAGE_SIZE); + if (!mem) + goto e_free_mdesc; + + mdesc->secrets = (__force struct snp_secrets_page *)mem; + + /* Allocate the shared page used for the request and response message. */ + mdesc->request = alloc_shared_pages(sizeof(struct snp_guest_msg)); + if (!mdesc->request) + goto e_unmap; + + mdesc->response = alloc_shared_pages(sizeof(struct snp_guest_msg)); + if (!mdesc->response) + goto e_free_request; + + mdesc->certs_data = alloc_shared_pages(SEV_FW_BLOB_MAX_SIZE); + if (!mdesc->certs_data) + goto e_free_response; + + /* initial the input address for guest request */ + mdesc->input.req_gpa = __pa(mdesc->request); + mdesc->input.resp_gpa = __pa(mdesc->response); + mdesc->input.data_gpa = __pa(mdesc->certs_data); + + return mdesc; + +e_free_response: + free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg)); +e_free_request: + free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg)); +e_unmap: + iounmap(mem); +e_free_mdesc: + kfree(mdesc); + + return ERR_PTR(-ENOMEM); +} +EXPORT_SYMBOL_GPL(snp_msg_alloc); + +void snp_msg_free(struct snp_msg_desc *mdesc) +{ + if (!mdesc) + return; + + kfree(mdesc->ctx); + free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg)); + free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg)); + free_shared_pages(mdesc->certs_data, SEV_FW_BLOB_MAX_SIZE); + iounmap((__force void __iomem *)mdesc->secrets); + + memset(mdesc, 0, sizeof(*mdesc)); + kfree(mdesc); +} +EXPORT_SYMBOL_GPL(snp_msg_free); + +/* Mutex to serialize the shared buffer access and command handling. */ +static DEFINE_MUTEX(snp_cmd_mutex); + +/* + * If an error is received from the host or AMD Secure Processor (ASP) there + * are two options. Either retry the exact same encrypted request or discontinue + * using the VMPCK. + * + * This is because in the current encryption scheme GHCB v2 uses AES-GCM to + * encrypt the requests. The IV for this scheme is the sequence number. GCM + * cannot tolerate IV reuse. + * + * The ASP FW v1.51 only increments the sequence numbers on a successful + * guest<->ASP back and forth and only accepts messages at its exact sequence + * number. + * + * So if the sequence number were to be reused the encryption scheme is + * vulnerable. If the sequence number were incremented for a fresh IV the ASP + * will reject the request. + */ +static void snp_disable_vmpck(struct snp_msg_desc *mdesc) +{ + pr_alert("Disabling VMPCK%d communication key to prevent IV reuse.\n", + mdesc->vmpck_id); + memzero_explicit(mdesc->vmpck, VMPCK_KEY_LEN); + mdesc->vmpck = NULL; +} + +static inline u64 __snp_get_msg_seqno(struct snp_msg_desc *mdesc) +{ + u64 count; + + lockdep_assert_held(&snp_cmd_mutex); + + /* Read the current message sequence counter from secrets pages */ + count = *mdesc->os_area_msg_seqno; + + return count + 1; +} + +/* Return a non-zero on success */ +static u64 snp_get_msg_seqno(struct snp_msg_desc *mdesc) +{ + u64 count = __snp_get_msg_seqno(mdesc); + + /* + * The message sequence counter for the SNP guest request is a 64-bit + * value but the version 2 of GHCB specification defines a 32-bit storage + * for it. If the counter exceeds the 32-bit value then return zero. + * The caller should check the return value, but if the caller happens to + * not check the value and use it, then the firmware treats zero as an + * invalid number and will fail the message request. + */ + if (count >= UINT_MAX) { + pr_err("request message sequence counter overflow\n"); + return 0; + } + + return count; +} + +static void snp_inc_msg_seqno(struct snp_msg_desc *mdesc) +{ + /* + * The counter is also incremented by the PSP, so increment it by 2 + * and save in secrets page. + */ + *mdesc->os_area_msg_seqno += 2; +} + +static int verify_and_dec_payload(struct snp_msg_desc *mdesc, struct snp_guest_req *req) +{ + struct snp_guest_msg *resp_msg = &mdesc->secret_response; + struct snp_guest_msg *req_msg = &mdesc->secret_request; + struct snp_guest_msg_hdr *req_msg_hdr = &req_msg->hdr; + struct snp_guest_msg_hdr *resp_msg_hdr = &resp_msg->hdr; + struct aesgcm_ctx *ctx = mdesc->ctx; + u8 iv[GCM_AES_IV_SIZE] = {}; + + pr_debug("response [seqno %lld type %d version %d sz %d]\n", + resp_msg_hdr->msg_seqno, resp_msg_hdr->msg_type, resp_msg_hdr->msg_version, + resp_msg_hdr->msg_sz); + + /* Copy response from shared memory to encrypted memory. */ + memcpy(resp_msg, mdesc->response, sizeof(*resp_msg)); + + /* Verify that the sequence counter is incremented by 1 */ + if (unlikely(resp_msg_hdr->msg_seqno != (req_msg_hdr->msg_seqno + 1))) + return -EBADMSG; + + /* Verify response message type and version number. */ + if (resp_msg_hdr->msg_type != (req_msg_hdr->msg_type + 1) || + resp_msg_hdr->msg_version != req_msg_hdr->msg_version) + return -EBADMSG; + + /* + * If the message size is greater than our buffer length then return + * an error. + */ + if (unlikely((resp_msg_hdr->msg_sz + ctx->authsize) > req->resp_sz)) + return -EBADMSG; + + /* Decrypt the payload */ + memcpy(iv, &resp_msg_hdr->msg_seqno, min(sizeof(iv), sizeof(resp_msg_hdr->msg_seqno))); + if (!aesgcm_decrypt(ctx, req->resp_buf, resp_msg->payload, resp_msg_hdr->msg_sz, + &resp_msg_hdr->algo, AAD_LEN, iv, resp_msg_hdr->authtag)) + return -EBADMSG; + + return 0; +} + +static int enc_payload(struct snp_msg_desc *mdesc, u64 seqno, struct snp_guest_req *req) +{ + struct snp_guest_msg *msg = &mdesc->secret_request; + struct snp_guest_msg_hdr *hdr = &msg->hdr; + struct aesgcm_ctx *ctx = mdesc->ctx; + u8 iv[GCM_AES_IV_SIZE] = {}; + + memset(msg, 0, sizeof(*msg)); + + hdr->algo = SNP_AEAD_AES_256_GCM; + hdr->hdr_version = MSG_HDR_VER; + hdr->hdr_sz = sizeof(*hdr); + hdr->msg_type = req->msg_type; + hdr->msg_version = req->msg_version; + hdr->msg_seqno = seqno; + hdr->msg_vmpck = req->vmpck_id; + hdr->msg_sz = req->req_sz; + + /* Verify the sequence number is non-zero */ + if (!hdr->msg_seqno) + return -ENOSR; + + pr_debug("request [seqno %lld type %d version %d sz %d]\n", + hdr->msg_seqno, hdr->msg_type, hdr->msg_version, hdr->msg_sz); + + if (WARN_ON((req->req_sz + ctx->authsize) > sizeof(msg->payload))) + return -EBADMSG; + + memcpy(iv, &hdr->msg_seqno, min(sizeof(iv), sizeof(hdr->msg_seqno))); + aesgcm_encrypt(ctx, msg->payload, req->req_buf, req->req_sz, &hdr->algo, + AAD_LEN, iv, hdr->authtag); + + return 0; +} + +static int __handle_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, + struct snp_guest_request_ioctl *rio) +{ + unsigned long req_start = jiffies; + unsigned int override_npages = 0; + u64 override_err = 0; + int rc; + +retry_request: + /* + * Call firmware to process the request. In this function the encrypted + * message enters shared memory with the host. So after this call the + * sequence number must be incremented or the VMPCK must be deleted to + * prevent reuse of the IV. + */ + rc = snp_issue_guest_request(req, &mdesc->input, rio); + switch (rc) { + case -ENOSPC: + /* + * If the extended guest request fails due to having too + * small of a certificate data buffer, retry the same + * guest request without the extended data request in + * order to increment the sequence number and thus avoid + * IV reuse. + */ + override_npages = mdesc->input.data_npages; + req->exit_code = SVM_VMGEXIT_GUEST_REQUEST; + + /* + * Override the error to inform callers the given extended + * request buffer size was too small and give the caller the + * required buffer size. + */ + override_err = SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN); + + /* + * If this call to the firmware succeeds, the sequence number can + * be incremented allowing for continued use of the VMPCK. If + * there is an error reflected in the return value, this value + * is checked further down and the result will be the deletion + * of the VMPCK and the error code being propagated back to the + * user as an ioctl() return code. + */ + goto retry_request; + + /* + * The host may return SNP_GUEST_VMM_ERR_BUSY if the request has been + * throttled. Retry in the driver to avoid returning and reusing the + * message sequence number on a different message. + */ + case -EAGAIN: + if (jiffies - req_start > SNP_REQ_MAX_RETRY_DURATION) { + rc = -ETIMEDOUT; + break; + } + schedule_timeout_killable(SNP_REQ_RETRY_DELAY); + goto retry_request; + } + + /* + * Increment the message sequence number. There is no harm in doing + * this now because decryption uses the value stored in the response + * structure and any failure will wipe the VMPCK, preventing further + * use anyway. + */ + snp_inc_msg_seqno(mdesc); + + if (override_err) { + rio->exitinfo2 = override_err; + + /* + * If an extended guest request was issued and the supplied certificate + * buffer was not large enough, a standard guest request was issued to + * prevent IV reuse. If the standard request was successful, return -EIO + * back to the caller as would have originally been returned. + */ + if (!rc && override_err == SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN)) + rc = -EIO; + } + + if (override_npages) + mdesc->input.data_npages = override_npages; + + return rc; +} + +int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, + struct snp_guest_request_ioctl *rio) +{ + u64 seqno; + int rc; + + guard(mutex)(&snp_cmd_mutex); + + /* Check if the VMPCK is not empty */ + if (!mdesc->vmpck || !memchr_inv(mdesc->vmpck, 0, VMPCK_KEY_LEN)) { + pr_err_ratelimited("VMPCK is disabled\n"); + return -ENOTTY; + } + + /* Get message sequence and verify that its a non-zero */ + seqno = snp_get_msg_seqno(mdesc); + if (!seqno) + return -EIO; + + /* Clear shared memory's response for the host to populate. */ + memset(mdesc->response, 0, sizeof(struct snp_guest_msg)); + + /* Encrypt the userspace provided payload in mdesc->secret_request. */ + rc = enc_payload(mdesc, seqno, req); + if (rc) + return rc; + + /* + * Write the fully encrypted request to the shared unencrypted + * request page. + */ + memcpy(mdesc->request, &mdesc->secret_request, sizeof(mdesc->secret_request)); + + rc = __handle_guest_request(mdesc, req, rio); + if (rc) { + if (rc == -EIO && + rio->exitinfo2 == SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN)) + return rc; + + pr_alert("Detected error from ASP request. rc: %d, exitinfo2: 0x%llx\n", + rc, rio->exitinfo2); + + snp_disable_vmpck(mdesc); + return rc; + } + + rc = verify_and_dec_payload(mdesc, req); + if (rc) { + pr_alert("Detected unexpected decode failure from ASP. rc: %d\n", rc); + snp_disable_vmpck(mdesc); + return rc; + } + + return 0; +} +EXPORT_SYMBOL_GPL(snp_send_guest_request); + +static int __init snp_get_tsc_info(void) +{ + struct snp_guest_request_ioctl *rio; + struct snp_tsc_info_resp *tsc_resp; + struct snp_tsc_info_req *tsc_req; + struct snp_msg_desc *mdesc; + struct snp_guest_req *req; + int rc = -ENOMEM; + + tsc_req = kzalloc(sizeof(*tsc_req), GFP_KERNEL); + if (!tsc_req) + return rc; + + /* + * The intermediate response buffer is used while decrypting the + * response payload. Make sure that it has enough space to cover + * the authtag. + */ + tsc_resp = kzalloc(sizeof(*tsc_resp) + AUTHTAG_LEN, GFP_KERNEL); + if (!tsc_resp) + goto e_free_tsc_req; + + req = kzalloc(sizeof(*req), GFP_KERNEL); + if (!req) + goto e_free_tsc_resp; + + rio = kzalloc(sizeof(*rio), GFP_KERNEL); + if (!rio) + goto e_free_req; + + mdesc = snp_msg_alloc(); + if (IS_ERR_OR_NULL(mdesc)) + goto e_free_rio; + + rc = snp_msg_init(mdesc, snp_vmpl); + if (rc) + goto e_free_mdesc; + + req->msg_version = MSG_HDR_VER; + req->msg_type = SNP_MSG_TSC_INFO_REQ; + req->vmpck_id = snp_vmpl; + req->req_buf = tsc_req; + req->req_sz = sizeof(*tsc_req); + req->resp_buf = (void *)tsc_resp; + req->resp_sz = sizeof(*tsc_resp) + AUTHTAG_LEN; + req->exit_code = SVM_VMGEXIT_GUEST_REQUEST; + + rc = snp_send_guest_request(mdesc, req, rio); + if (rc) + goto e_request; + + pr_debug("%s: response status 0x%x scale 0x%llx offset 0x%llx factor 0x%x\n", + __func__, tsc_resp->status, tsc_resp->tsc_scale, tsc_resp->tsc_offset, + tsc_resp->tsc_factor); + + if (!tsc_resp->status) { + snp_tsc_scale = tsc_resp->tsc_scale; + snp_tsc_offset = tsc_resp->tsc_offset; + } else { + pr_err("Failed to get TSC info, response status 0x%x\n", tsc_resp->status); + rc = -EIO; + } + +e_request: + /* The response buffer contains sensitive data, explicitly clear it. */ + memzero_explicit(tsc_resp, sizeof(*tsc_resp) + AUTHTAG_LEN); +e_free_mdesc: + snp_msg_free(mdesc); +e_free_rio: + kfree(rio); +e_free_req: + kfree(req); + e_free_tsc_resp: + kfree(tsc_resp); +e_free_tsc_req: + kfree(tsc_req); + + return rc; +} + +void __init snp_secure_tsc_prepare(void) +{ + if (!cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC)) + return; + + if (snp_get_tsc_info()) { + pr_alert("Unable to retrieve Secure TSC info from ASP\n"); + sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SECURE_TSC); + } + + pr_debug("SecureTSC enabled"); +} + +static unsigned long securetsc_get_tsc_khz(void) +{ + return snp_tsc_freq_khz; +} + +void __init snp_secure_tsc_init(void) +{ + unsigned long long tsc_freq_mhz; + + if (!cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC)) + return; + + setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); + rdmsrl(MSR_AMD64_GUEST_TSC_FREQ, tsc_freq_mhz); + snp_tsc_freq_khz = (unsigned long)(tsc_freq_mhz * 1000); + + x86_platform.calibrate_cpu = securetsc_get_tsc_khz; + x86_platform.calibrate_tsc = securetsc_get_tsc_khz; +} diff --git a/arch/x86/coco/sev/shared.c b/arch/x86/coco/sev/shared.c index 71de53194089..4386f37bd31d 100644 --- a/arch/x86/coco/sev/shared.c +++ b/arch/x86/coco/sev/shared.c @@ -1140,6 +1140,16 @@ static enum es_result vc_handle_rdtsc(struct ghcb *ghcb, bool rdtscp = (exit_code == SVM_EXIT_RDTSCP); enum es_result ret; + /* + * The hypervisor should not be intercepting RDTSC/RDTSCP when Secure + * TSC is enabled. A #VC exception will be generated if the RDTSC/RDTSCP + * instructions are being intercepted. If this should occur and Secure + * TSC is enabled, guest execution should be terminated as the guest + * cannot rely on the TSC value provided by the hypervisor. + */ + if (sev_status & MSR_AMD64_SNP_SECURE_TSC) + return ES_VMM_ERROR; + ret = sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, 0, 0); if (ret != ES_OK) return ret; diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 1b5be07f8669..f52dbe0ad93c 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -308,10 +308,9 @@ SYM_CODE_END(xen_error_entry) movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */ .endif - call \cfunc - /* For some configurations \cfunc ends up being a noreturn. */ - REACHABLE + ANNOTATE_REACHABLE + call \cfunc jmp error_return .endm @@ -529,10 +528,10 @@ SYM_CODE_START(\asmsym) movq %rsp, %rdi /* pt_regs pointer into first argument */ movq ORIG_RAX(%rsp), %rsi /* get error code into 2nd argument*/ movq $-1, ORIG_RAX(%rsp) /* no syscall to restart */ - call \cfunc /* For some configurations \cfunc ends up being a noreturn. */ - REACHABLE + ANNOTATE_REACHABLE + call \cfunc jmp paranoid_exit diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index b4a1a2576510..30d6ceb4c8ad 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -1001,8 +1001,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) if (!x86_perf_event_set_period(event)) continue; - if (has_branch_stack(event)) - perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index e91970b01d62..e7a8b8758e08 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -31,6 +31,8 @@ static u32 ibs_caps; #define IBS_FETCH_CONFIG_MASK (IBS_FETCH_RAND_EN | IBS_FETCH_MAX_CNT) #define IBS_OP_CONFIG_MASK IBS_OP_MAX_CNT +/* attr.config2 */ +#define IBS_SW_FILTER_MASK 1 /* * IBS states: @@ -290,6 +292,16 @@ static int perf_ibs_init(struct perf_event *event) if (has_branch_stack(event)) return -EOPNOTSUPP; + /* handle exclude_{user,kernel} in the IRQ handler */ + if (event->attr.exclude_host || event->attr.exclude_guest || + event->attr.exclude_idle) + return -EINVAL; + + if (!(event->attr.config2 & IBS_SW_FILTER_MASK) && + (event->attr.exclude_kernel || event->attr.exclude_user || + event->attr.exclude_hv)) + return -EINVAL; + ret = validate_group(event); if (ret) return ret; @@ -550,24 +562,14 @@ static struct attribute *attrs_empty[] = { NULL, }; -static struct attribute_group empty_format_group = { - .name = "format", - .attrs = attrs_empty, -}; - static struct attribute_group empty_caps_group = { .name = "caps", .attrs = attrs_empty, }; -static const struct attribute_group *empty_attr_groups[] = { - &empty_format_group, - &empty_caps_group, - NULL, -}; - PMU_FORMAT_ATTR(rand_en, "config:57"); PMU_FORMAT_ATTR(cnt_ctl, "config:19"); +PMU_FORMAT_ATTR(swfilt, "config2:0"); PMU_EVENT_ATTR_STRING(l3missonly, fetch_l3missonly, "config:59"); PMU_EVENT_ATTR_STRING(l3missonly, op_l3missonly, "config:16"); PMU_EVENT_ATTR_STRING(zen4_ibs_extensions, zen4_ibs_extensions, "1"); @@ -578,8 +580,9 @@ zen4_ibs_extensions_is_visible(struct kobject *kobj, struct attribute *attr, int return ibs_caps & IBS_CAPS_ZEN4 ? attr->mode : 0; } -static struct attribute *rand_en_attrs[] = { +static struct attribute *fetch_attrs[] = { &format_attr_rand_en.attr, + &format_attr_swfilt.attr, NULL, }; @@ -593,9 +596,9 @@ static struct attribute *zen4_ibs_extensions_attrs[] = { NULL, }; -static struct attribute_group group_rand_en = { +static struct attribute_group group_fetch_formats = { .name = "format", - .attrs = rand_en_attrs, + .attrs = fetch_attrs, }; static struct attribute_group group_fetch_l3missonly = { @@ -611,7 +614,7 @@ static struct attribute_group group_zen4_ibs_extensions = { }; static const struct attribute_group *fetch_attr_groups[] = { - &group_rand_en, + &group_fetch_formats, &empty_caps_group, NULL, }; @@ -628,6 +631,11 @@ cnt_ctl_is_visible(struct kobject *kobj, struct attribute *attr, int i) return ibs_caps & IBS_CAPS_OPCNT ? attr->mode : 0; } +static struct attribute *op_attrs[] = { + &format_attr_swfilt.attr, + NULL, +}; + static struct attribute *cnt_ctl_attrs[] = { &format_attr_cnt_ctl.attr, NULL, @@ -638,6 +646,11 @@ static struct attribute *op_l3missonly_attrs[] = { NULL, }; +static struct attribute_group group_op_formats = { + .name = "format", + .attrs = op_attrs, +}; + static struct attribute_group group_cnt_ctl = { .name = "format", .attrs = cnt_ctl_attrs, @@ -650,6 +663,12 @@ static struct attribute_group group_op_l3missonly = { .is_visible = zen4_ibs_extensions_is_visible, }; +static const struct attribute_group *op_attr_groups[] = { + &group_op_formats, + &empty_caps_group, + NULL, +}; + static const struct attribute_group *op_attr_update[] = { &group_cnt_ctl, &group_op_l3missonly, @@ -667,7 +686,6 @@ static struct perf_ibs perf_ibs_fetch = { .start = perf_ibs_start, .stop = perf_ibs_stop, .read = perf_ibs_read, - .capabilities = PERF_PMU_CAP_NO_EXCLUDE, }, .msr = MSR_AMD64_IBSFETCHCTL, .config_mask = IBS_FETCH_CONFIG_MASK, @@ -691,7 +709,6 @@ static struct perf_ibs perf_ibs_op = { .start = perf_ibs_start, .stop = perf_ibs_stop, .read = perf_ibs_read, - .capabilities = PERF_PMU_CAP_NO_EXCLUDE, }, .msr = MSR_AMD64_IBSOPCTL, .config_mask = IBS_OP_CONFIG_MASK, @@ -1111,6 +1128,12 @@ fail: regs.flags |= PERF_EFLAGS_EXACT; } + if ((event->attr.config2 & IBS_SW_FILTER_MASK) && + perf_exclude_event(event, ®s)) { + throttle = perf_event_account_interrupt(event); + goto out; + } + if (event->attr.sample_type & PERF_SAMPLE_RAW) { raw = (struct perf_raw_record){ .frag = { @@ -1118,7 +1141,7 @@ fail: .data = ibs_data.data, }, }; - perf_sample_save_raw_data(&data, &raw); + perf_sample_save_raw_data(&data, event, &raw); } if (perf_ibs == &perf_ibs_op) @@ -1129,8 +1152,7 @@ fail: * recorded as part of interrupt regs. Thus we need to use rip from * interrupt regs while unwinding call stack. */ - if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) - perf_sample_save_callchain(&data, event, iregs); + perf_sample_save_callchain(&data, event, iregs); throttle = perf_event_overflow(event, &data, ®s); out: @@ -1228,7 +1250,7 @@ static __init int perf_ibs_op_init(void) if (ibs_caps & IBS_CAPS_ZEN4) perf_ibs_op.config_mask |= IBS_OP_L3MISSONLY; - perf_ibs_op.pmu.attr_groups = empty_attr_groups; + perf_ibs_op.pmu.attr_groups = op_attr_groups; perf_ibs_op.pmu.attr_update = op_attr_update; return perf_ibs_pmu_init(&perf_ibs_op, "ibs_op"); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index c75c482d4c52..8f218ac0d445 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1707,8 +1707,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs) perf_sample_data_init(&data, 0, event->hw.last_period); - if (has_branch_stack(event)) - perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index bb284aff7bfd..7601196d1d18 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -429,6 +429,16 @@ static struct event_constraint intel_lnc_event_constraints[] = { EVENT_CONSTRAINT_END }; +static struct extra_reg intel_lnc_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0xfffffffffffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0xfffffffffffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + INTEL_UEVENT_EXTRA_REG(0x02c6, MSR_PEBS_FRONTEND, 0x9, FE), + INTEL_UEVENT_EXTRA_REG(0x03c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE), + INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0xf, FE), + INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE), + EVENT_EXTRA_END +}; EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); @@ -2816,6 +2826,9 @@ static void intel_pmu_enable_fixed(struct perf_event *event) return; idx = INTEL_PMC_IDX_FIXED_SLOTS; + + if (event->attr.config1 & INTEL_TD_CFG_METRIC_CLEAR) + bits |= INTEL_FIXED_3_METRICS_CLEAR; } intel_set_masks(event, idx); @@ -4071,7 +4084,12 @@ static int intel_pmu_hw_config(struct perf_event *event) * is used in a metrics group, it too cannot support sampling. */ if (intel_pmu_has_cap(event, PERF_CAP_METRICS_IDX) && is_topdown_event(event)) { - if (event->attr.config1 || event->attr.config2) + /* The metrics_clear can only be set for the slots event */ + if (event->attr.config1 && + (!is_slots_event(event) || (event->attr.config1 & ~INTEL_TD_CFG_METRIC_CLEAR))) + return -EINVAL; + + if (event->attr.config2) return -EINVAL; /* @@ -4680,6 +4698,8 @@ PMU_FORMAT_ATTR(in_tx, "config:32" ); PMU_FORMAT_ATTR(in_tx_cp, "config:33" ); PMU_FORMAT_ATTR(eq, "config:36" ); /* v6 + */ +PMU_FORMAT_ATTR(metrics_clear, "config1:0"); /* PERF_CAPABILITIES.RDPMC_METRICS_CLEAR */ + static ssize_t umask2_show(struct device *dev, struct device_attribute *attr, char *page) @@ -4699,6 +4719,7 @@ static struct device_attribute format_attr_umask2 = static struct attribute *format_evtsel_ext_attrs[] = { &format_attr_umask2.attr, &format_attr_eq.attr, + &format_attr_metrics_clear.attr, NULL }; @@ -4723,6 +4744,13 @@ evtsel_ext_is_visible(struct kobject *kobj, struct attribute *attr, int i) if (i == 1) return (mask & ARCH_PERFMON_EVENTSEL_EQ) ? attr->mode : 0; + /* PERF_CAPABILITIES.RDPMC_METRICS_CLEAR */ + if (i == 2) { + union perf_capabilities intel_cap = hybrid(dev_get_drvdata(dev), intel_cap); + + return intel_cap.rdpmc_metrics_clear ? attr->mode : 0; + } + return 0; } @@ -5371,42 +5399,32 @@ static __init void intel_clovertown_quirk(void) x86_pmu.pebs_constraints = NULL; } -static const struct x86_cpu_desc isolation_ucodes[] = { - INTEL_CPU_DESC(INTEL_HASWELL, 3, 0x0000001f), - INTEL_CPU_DESC(INTEL_HASWELL_L, 1, 0x0000001e), - INTEL_CPU_DESC(INTEL_HASWELL_G, 1, 0x00000015), - INTEL_CPU_DESC(INTEL_HASWELL_X, 2, 0x00000037), - INTEL_CPU_DESC(INTEL_HASWELL_X, 4, 0x0000000a), - INTEL_CPU_DESC(INTEL_BROADWELL, 4, 0x00000023), - INTEL_CPU_DESC(INTEL_BROADWELL_G, 1, 0x00000014), - INTEL_CPU_DESC(INTEL_BROADWELL_D, 2, 0x00000010), - INTEL_CPU_DESC(INTEL_BROADWELL_D, 3, 0x07000009), - INTEL_CPU_DESC(INTEL_BROADWELL_D, 4, 0x0f000009), - INTEL_CPU_DESC(INTEL_BROADWELL_D, 5, 0x0e000002), - INTEL_CPU_DESC(INTEL_BROADWELL_X, 1, 0x0b000014), - INTEL_CPU_DESC(INTEL_SKYLAKE_X, 3, 0x00000021), - INTEL_CPU_DESC(INTEL_SKYLAKE_X, 4, 0x00000000), - INTEL_CPU_DESC(INTEL_SKYLAKE_X, 5, 0x00000000), - INTEL_CPU_DESC(INTEL_SKYLAKE_X, 6, 0x00000000), - INTEL_CPU_DESC(INTEL_SKYLAKE_X, 7, 0x00000000), - INTEL_CPU_DESC(INTEL_SKYLAKE_X, 11, 0x00000000), - INTEL_CPU_DESC(INTEL_SKYLAKE_L, 3, 0x0000007c), - INTEL_CPU_DESC(INTEL_SKYLAKE, 3, 0x0000007c), - INTEL_CPU_DESC(INTEL_KABYLAKE, 9, 0x0000004e), - INTEL_CPU_DESC(INTEL_KABYLAKE_L, 9, 0x0000004e), - INTEL_CPU_DESC(INTEL_KABYLAKE_L, 10, 0x0000004e), - INTEL_CPU_DESC(INTEL_KABYLAKE_L, 11, 0x0000004e), - INTEL_CPU_DESC(INTEL_KABYLAKE_L, 12, 0x0000004e), - INTEL_CPU_DESC(INTEL_KABYLAKE, 10, 0x0000004e), - INTEL_CPU_DESC(INTEL_KABYLAKE, 11, 0x0000004e), - INTEL_CPU_DESC(INTEL_KABYLAKE, 12, 0x0000004e), - INTEL_CPU_DESC(INTEL_KABYLAKE, 13, 0x0000004e), +static const struct x86_cpu_id isolation_ucodes[] = { + X86_MATCH_VFM_STEPS(INTEL_HASWELL, 3, 3, 0x0000001f), + X86_MATCH_VFM_STEPS(INTEL_HASWELL_L, 1, 1, 0x0000001e), + X86_MATCH_VFM_STEPS(INTEL_HASWELL_G, 1, 1, 0x00000015), + X86_MATCH_VFM_STEPS(INTEL_HASWELL_X, 2, 2, 0x00000037), + X86_MATCH_VFM_STEPS(INTEL_HASWELL_X, 4, 4, 0x0000000a), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL, 4, 4, 0x00000023), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_G, 1, 1, 0x00000014), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D, 2, 2, 0x00000010), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D, 3, 3, 0x07000009), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D, 4, 4, 0x0f000009), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D, 5, 5, 0x0e000002), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_X, 1, 1, 0x0b000014), + X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_X, 3, 3, 0x00000021), + X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_X, 4, 7, 0x00000000), + X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_X, 11, 11, 0x00000000), + X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_L, 3, 3, 0x0000007c), + X86_MATCH_VFM_STEPS(INTEL_SKYLAKE, 3, 3, 0x0000007c), + X86_MATCH_VFM_STEPS(INTEL_KABYLAKE, 9, 13, 0x0000004e), + X86_MATCH_VFM_STEPS(INTEL_KABYLAKE_L, 9, 12, 0x0000004e), {} }; static void intel_check_pebs_isolation(void) { - x86_pmu.pebs_no_isolation = !x86_cpu_has_min_microcode_rev(isolation_ucodes); + x86_pmu.pebs_no_isolation = !x86_match_min_microcode_rev(isolation_ucodes); } static __init void intel_pebs_isolation_quirk(void) @@ -5416,16 +5434,16 @@ static __init void intel_pebs_isolation_quirk(void) intel_check_pebs_isolation(); } -static const struct x86_cpu_desc pebs_ucodes[] = { - INTEL_CPU_DESC(INTEL_SANDYBRIDGE, 7, 0x00000028), - INTEL_CPU_DESC(INTEL_SANDYBRIDGE_X, 6, 0x00000618), - INTEL_CPU_DESC(INTEL_SANDYBRIDGE_X, 7, 0x0000070c), +static const struct x86_cpu_id pebs_ucodes[] = { + X86_MATCH_VFM_STEPS(INTEL_SANDYBRIDGE, 7, 7, 0x00000028), + X86_MATCH_VFM_STEPS(INTEL_SANDYBRIDGE_X, 6, 6, 0x00000618), + X86_MATCH_VFM_STEPS(INTEL_SANDYBRIDGE_X, 7, 7, 0x0000070c), {} }; static bool intel_snb_pebs_broken(void) { - return !x86_cpu_has_min_microcode_rev(pebs_ucodes); + return !x86_match_min_microcode_rev(pebs_ucodes); } static void intel_snb_check_microcode(void) @@ -6422,7 +6440,7 @@ static __always_inline void intel_pmu_init_lnc(struct pmu *pmu) intel_pmu_init_glc(pmu); hybrid(pmu, event_constraints) = intel_lnc_event_constraints; hybrid(pmu, pebs_constraints) = intel_lnc_pebs_event_constraints; - hybrid(pmu, extra_regs) = intel_rwc_extra_regs; + hybrid(pmu, extra_regs) = intel_lnc_extra_regs; } static __always_inline void intel_pmu_init_skt(struct pmu *pmu) @@ -7135,6 +7153,7 @@ __init int intel_pmu_init(void) case INTEL_METEORLAKE: case INTEL_METEORLAKE_L: + case INTEL_ARROWLAKE_U: intel_pmu_init_hybrid(hybrid_big_small); x86_pmu.pebs_latency_data = cmt_latency_data; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8afc4ad3cd16..ba74e1198328 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1489,7 +1489,7 @@ void intel_pmu_pebs_enable(struct perf_event *event) * hence we need to drain when changing said * size. */ - intel_pmu_drain_large_pebs(cpuc); + intel_pmu_drain_pebs_buffer(); adaptive_pebs_record_size_update(); wrmsrl(MSR_PEBS_DATA_CFG, pebs_data_cfg); cpuc->active_pebs_data_cfg = pebs_data_cfg; @@ -1789,8 +1789,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, * previous PMI context or an (I)RET happened between the record and * PMI. */ - if (sample_type & PERF_SAMPLE_CALLCHAIN) - perf_sample_save_callchain(data, event, iregs); + perf_sample_save_callchain(data, event, iregs); /* * We use the interrupt regs as a base because the PEBS record does not @@ -1889,8 +1888,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, if (x86_pmu.intel_cap.pebs_format >= 3) setup_pebs_time(event, data, pebs->tsc); - if (has_branch_stack(event)) - perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL); + perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL); } static void adaptive_pebs_save_regs(struct pt_regs *regs, @@ -1917,8 +1915,6 @@ static void adaptive_pebs_save_regs(struct pt_regs *regs, } #define PEBS_LATENCY_MASK 0xffff -#define PEBS_CACHE_LATENCY_OFFSET 32 -#define PEBS_RETIRE_LATENCY_OFFSET 32 /* * With adaptive PEBS the layout depends on what fields are configured. @@ -1932,8 +1928,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct pebs_basic *basic = __pebs; void *next_record = basic + 1; - u64 sample_type; - u64 format_size; + u64 sample_type, format_group; struct pebs_meminfo *meminfo = NULL; struct pebs_gprs *gprs = NULL; struct x86_perf_regs *perf_regs; @@ -1945,7 +1940,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, perf_regs->xmm_regs = NULL; sample_type = event->attr.sample_type; - format_size = basic->format_size; + format_group = basic->format_group; perf_sample_data_init(data, 0, event->hw.last_period); data->period = event->hw.last_period; @@ -1957,8 +1952,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, * previous PMI context or an (I)RET happened between the record and * PMI. */ - if (sample_type & PERF_SAMPLE_CALLCHAIN) - perf_sample_save_callchain(data, event, iregs); + perf_sample_save_callchain(data, event, iregs); *regs = *iregs; /* The ip in basic is EventingIP */ @@ -1967,7 +1961,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) { if (x86_pmu.flags & PMU_FL_RETIRE_LATENCY) - data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK; + data->weight.var3_w = basic->retire_latency; else data->weight.var3_w = 0; } @@ -1977,12 +1971,12 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, * But PERF_SAMPLE_TRANSACTION needs gprs->ax. * Save the pointer here but process later. */ - if (format_size & PEBS_DATACFG_MEMINFO) { + if (format_group & PEBS_DATACFG_MEMINFO) { meminfo = next_record; next_record = meminfo + 1; } - if (format_size & PEBS_DATACFG_GP) { + if (format_group & PEBS_DATACFG_GP) { gprs = next_record; next_record = gprs + 1; @@ -1995,14 +1989,13 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, adaptive_pebs_save_regs(regs, gprs); } - if (format_size & PEBS_DATACFG_MEMINFO) { + if (format_group & PEBS_DATACFG_MEMINFO) { if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) { - u64 weight = meminfo->latency; + u64 latency = x86_pmu.flags & PMU_FL_INSTR_LATENCY ? + meminfo->cache_latency : meminfo->mem_latency; - if (x86_pmu.flags & PMU_FL_INSTR_LATENCY) { - data->weight.var2_w = weight & PEBS_LATENCY_MASK; - weight >>= PEBS_CACHE_LATENCY_OFFSET; - } + if (x86_pmu.flags & PMU_FL_INSTR_LATENCY) + data->weight.var2_w = meminfo->instr_latency; /* * Although meminfo::latency is defined as a u64, @@ -2010,12 +2003,13 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, * in practice on Ice Lake and earlier platforms. */ if (sample_type & PERF_SAMPLE_WEIGHT) { - data->weight.full = weight ?: + data->weight.full = latency ?: intel_get_tsx_weight(meminfo->tsx_tuning); } else { - data->weight.var1_dw = (u32)(weight & PEBS_LATENCY_MASK) ?: + data->weight.var1_dw = (u32)latency ?: intel_get_tsx_weight(meminfo->tsx_tuning); } + data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE; } @@ -2036,16 +2030,16 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, } } - if (format_size & PEBS_DATACFG_XMMS) { + if (format_group & PEBS_DATACFG_XMMS) { struct pebs_xmm *xmm = next_record; next_record = xmm + 1; perf_regs->xmm_regs = xmm->xmm; } - if (format_size & PEBS_DATACFG_LBRS) { + if (format_group & PEBS_DATACFG_LBRS) { struct lbr_entry *lbr = next_record; - int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT) + int num_lbr = ((format_group >> PEBS_DATACFG_LBR_SHIFT) & 0xff) + 1; next_record = next_record + num_lbr * sizeof(struct lbr_entry); @@ -2055,11 +2049,11 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, } } - WARN_ONCE(next_record != __pebs + (format_size >> 48), - "PEBS record size %llu, expected %llu, config %llx\n", - format_size >> 48, + WARN_ONCE(next_record != __pebs + basic->format_size, + "PEBS record size %u, expected %llu, config %llx\n", + basic->format_size, (u64)(next_record - __pebs), - basic->format_size); + format_group); } static inline void * @@ -2170,46 +2164,33 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count) return 0; } +typedef void (*setup_fn)(struct perf_event *, struct pt_regs *, void *, + struct perf_sample_data *, struct pt_regs *); + +static struct pt_regs dummy_iregs; + static __always_inline void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, + struct pt_regs *regs, struct perf_sample_data *data, - void *base, void *top, - int bit, int count, - void (*setup_sample)(struct perf_event *, - struct pt_regs *, - void *, - struct perf_sample_data *, - struct pt_regs *)) + void *at, + setup_fn setup_sample) { - struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - struct hw_perf_event *hwc = &event->hw; - struct x86_perf_regs perf_regs; - struct pt_regs *regs = &perf_regs.regs; - void *at = get_next_pebs_record_by_bit(base, top, bit); - static struct pt_regs dummy_iregs; - - if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { - /* - * Now, auto-reload is only enabled in fixed period mode. - * The reload value is always hwc->sample_period. - * May need to change it, if auto-reload is enabled in - * freq mode later. - */ - intel_pmu_save_and_restart_reload(event, count); - } else if (!intel_pmu_save_and_restart(event)) - return; - - if (!iregs) - iregs = &dummy_iregs; + setup_sample(event, iregs, at, data, regs); + perf_event_output(event, data, regs); +} - while (count > 1) { - setup_sample(event, iregs, at, data, regs); - perf_event_output(event, data, regs); - at += cpuc->pebs_record_size; - at = get_next_pebs_record_by_bit(at, top, bit); - count--; - } +static __always_inline void +__intel_pmu_pebs_last_event(struct perf_event *event, + struct pt_regs *iregs, + struct pt_regs *regs, + struct perf_sample_data *data, + void *at, + int count, + setup_fn setup_sample) +{ + struct hw_perf_event *hwc = &event->hw; setup_sample(event, iregs, at, data, regs); if (iregs == &dummy_iregs) { @@ -2228,6 +2209,44 @@ __intel_pmu_pebs_event(struct perf_event *event, if (perf_event_overflow(event, data, regs)) x86_pmu_stop(event, 0); } + + if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { + /* + * Now, auto-reload is only enabled in fixed period mode. + * The reload value is always hwc->sample_period. + * May need to change it, if auto-reload is enabled in + * freq mode later. + */ + intel_pmu_save_and_restart_reload(event, count); + } else + intel_pmu_save_and_restart(event); +} + +static __always_inline void +__intel_pmu_pebs_events(struct perf_event *event, + struct pt_regs *iregs, + struct perf_sample_data *data, + void *base, void *top, + int bit, int count, + setup_fn setup_sample) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct x86_perf_regs perf_regs; + struct pt_regs *regs = &perf_regs.regs; + void *at = get_next_pebs_record_by_bit(base, top, bit); + int cnt = count; + + if (!iregs) + iregs = &dummy_iregs; + + while (cnt > 1) { + __intel_pmu_pebs_event(event, iregs, regs, data, at, setup_sample); + at += cpuc->pebs_record_size; + at = get_next_pebs_record_by_bit(at, top, bit); + cnt--; + } + + __intel_pmu_pebs_last_event(event, iregs, regs, data, at, count, setup_sample); } static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_data *data) @@ -2264,8 +2283,8 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_ return; } - __intel_pmu_pebs_event(event, iregs, data, at, top, 0, n, - setup_pebs_fixed_sample_data); + __intel_pmu_pebs_events(event, iregs, data, at, top, 0, n, + setup_pebs_fixed_sample_data); } static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size) @@ -2396,9 +2415,9 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d } if (counts[bit]) { - __intel_pmu_pebs_event(event, iregs, data, base, - top, bit, counts[bit], - setup_pebs_fixed_sample_data); + __intel_pmu_pebs_events(event, iregs, data, base, + top, bit, counts[bit], + setup_pebs_fixed_sample_data); } } } @@ -2406,8 +2425,12 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_data *data) { short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; + void *last[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS]; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct debug_store *ds = cpuc->ds; + struct x86_perf_regs perf_regs; + struct pt_regs *regs = &perf_regs.regs; + struct pebs_basic *basic; struct perf_event *event; void *base, *at, *top; int bit; @@ -2429,30 +2452,41 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d return; } - for (at = base; at < top; at += cpuc->pebs_record_size) { + if (!iregs) + iregs = &dummy_iregs; + + /* Process all but the last event for each counter. */ + for (at = base; at < top; at += basic->format_size) { u64 pebs_status; - pebs_status = get_pebs_status(at) & cpuc->pebs_enabled; - pebs_status &= mask; + basic = at; + if (basic->format_size != cpuc->pebs_record_size) + continue; - for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX) - counts[bit]++; + pebs_status = basic->applicable_counters & cpuc->pebs_enabled & mask; + for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX) { + event = cpuc->events[bit]; + + if (WARN_ON_ONCE(!event) || + WARN_ON_ONCE(!event->attr.precise_ip)) + continue; + + if (counts[bit]++) { + __intel_pmu_pebs_event(event, iregs, regs, data, last[bit], + setup_pebs_adaptive_sample_data); + } + last[bit] = at; + } } for_each_set_bit(bit, (unsigned long *)&mask, X86_PMC_IDX_MAX) { - if (counts[bit] == 0) + if (!counts[bit]) continue; event = cpuc->events[bit]; - if (WARN_ON_ONCE(!event)) - continue; - - if (WARN_ON_ONCE(!event->attr.precise_ip)) - continue; - __intel_pmu_pebs_event(event, iregs, data, base, - top, bit, counts[bit], - setup_pebs_adaptive_sample_data); + __intel_pmu_pebs_last_event(event, iregs, regs, data, last[bit], + counts[bit], setup_pebs_adaptive_sample_data); } } @@ -2517,6 +2551,7 @@ void __init intel_ds_init(void) x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME; break; + case 6: case 5: x86_pmu.pebs_ept = 1; fallthrough; diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 4b0373bc8ab4..fa37565f6418 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -18,6 +18,7 @@ #include <linux/slab.h> #include <linux/device.h> +#include <asm/cpuid.h> #include <asm/perf_event.h> #include <asm/insn.h> #include <asm/io.h> @@ -201,10 +202,10 @@ static int __init pt_pmu_hw_init(void) * otherwise, zero for numerator stands for "not enumerated" * as per SDM */ - if (boot_cpu_data.cpuid_level >= CPUID_TSC_LEAF) { + if (boot_cpu_data.cpuid_level >= CPUID_LEAF_TSC) { u32 eax, ebx, ecx, edx; - cpuid(CPUID_TSC_LEAF, &eax, &ebx, &ecx, &edx); + cpuid(CPUID_LEAF_TSC, &eax, &ebx, &ecx, &edx); pt_pmu.tsc_art_num = ebx; pt_pmu.tsc_art_den = eax; diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h index 7ee94fc6d7cb..2ac36250b656 100644 --- a/arch/x86/events/intel/pt.h +++ b/arch/x86/events/intel/pt.h @@ -37,9 +37,6 @@ struct topa_entry { u64 rsvd4 : 12; }; -/* TSC to Core Crystal Clock Ratio */ -#define CPUID_TSC_LEAF 0x15 - struct pt_pmu { struct pmu pmu; u32 caps[PT_CPUID_REGS_NUM * PT_CPUID_LEAVES]; diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index d98fac567684..60b3078b7502 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -745,7 +745,7 @@ static int uncore_pmu_event_init(struct perf_event *event) pmu = uncore_event_to_pmu(event); /* no device found for this pmu */ - if (pmu->func_id < 0) + if (!pmu->registered) return -ENOENT; /* Sampling not supported yet */ @@ -992,7 +992,7 @@ static void uncore_types_exit(struct intel_uncore_type **types) uncore_type_exit(*types); } -static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) +static int __init uncore_type_init(struct intel_uncore_type *type) { struct intel_uncore_pmu *pmus; size_t size; @@ -1005,7 +1005,6 @@ static int __init uncore_type_init(struct intel_uncore_type *type, bool setid) size = uncore_max_dies() * sizeof(struct intel_uncore_box *); for (i = 0; i < type->num_boxes; i++) { - pmus[i].func_id = setid ? i : -1; pmus[i].pmu_idx = i; pmus[i].type = type; pmus[i].boxes = kzalloc(size, GFP_KERNEL); @@ -1055,12 +1054,12 @@ err: } static int __init -uncore_types_init(struct intel_uncore_type **types, bool setid) +uncore_types_init(struct intel_uncore_type **types) { int ret; for (; *types; types++) { - ret = uncore_type_init(*types, setid); + ret = uncore_type_init(*types); if (ret) return ret; } @@ -1160,11 +1159,6 @@ static int uncore_pci_pmu_register(struct pci_dev *pdev, if (!box) return -ENOMEM; - if (pmu->func_id < 0) - pmu->func_id = pdev->devfn; - else - WARN_ON_ONCE(pmu->func_id != pdev->devfn); - atomic_inc(&box->refcnt); box->dieid = die; box->pci_dev = pdev; @@ -1410,7 +1404,7 @@ static int __init uncore_pci_init(void) goto err; } - ret = uncore_types_init(uncore_pci_uncores, false); + ret = uncore_types_init(uncore_pci_uncores); if (ret) goto errtype; @@ -1678,7 +1672,7 @@ static int __init uncore_cpu_init(void) { int ret; - ret = uncore_types_init(uncore_msr_uncores, true); + ret = uncore_types_init(uncore_msr_uncores); if (ret) goto err; @@ -1697,7 +1691,7 @@ static int __init uncore_mmio_init(void) struct intel_uncore_type **types = uncore_mmio_uncores; int ret; - ret = uncore_types_init(types, true); + ret = uncore_types_init(types); if (ret) goto err; @@ -1910,6 +1904,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_VFM(INTEL_ATOM_GRACEMONT, &adl_uncore_init), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT_X, &gnr_uncore_init), X86_MATCH_VFM(INTEL_ATOM_CRESTMONT, &gnr_uncore_init), + X86_MATCH_VFM(INTEL_ATOM_DARKMONT_X, &gnr_uncore_init), {}, }; MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match); diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 79ff32e13dcc..3dcb88c0ecfa 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -125,7 +125,6 @@ struct intel_uncore_pmu { struct pmu pmu; char name[UNCORE_PMU_NAME_LEN]; int pmu_idx; - int func_id; bool registered; atomic_t activeboxes; cpumask_t cpu_mask; diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 3934e1e4e3b1..edb7fd50efe0 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -910,7 +910,7 @@ static int snb_uncore_imc_event_init(struct perf_event *event) pmu = uncore_event_to_pmu(event); /* no device found for this pmu */ - if (pmu->func_id < 0) + if (!pmu->registered) return -ENOENT; /* Sampling not supported yet */ diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index ca98744343b8..60973c209c0e 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -6684,17 +6684,8 @@ void spr_uncore_mmio_init(void) /* GNR uncore support */ #define UNCORE_GNR_NUM_UNCORE_TYPES 23 -#define UNCORE_GNR_TYPE_15 15 -#define UNCORE_GNR_B2UPI 18 -#define UNCORE_GNR_TYPE_21 21 -#define UNCORE_GNR_TYPE_22 22 int gnr_uncore_units_ignore[] = { - UNCORE_SPR_UPI, - UNCORE_GNR_TYPE_15, - UNCORE_GNR_B2UPI, - UNCORE_GNR_TYPE_21, - UNCORE_GNR_TYPE_22, UNCORE_IGNORE_END }; @@ -6703,6 +6694,31 @@ static struct intel_uncore_type gnr_uncore_ubox = { .attr_update = uncore_alias_groups, }; +static struct intel_uncore_type gnr_uncore_pciex8 = { + SPR_UNCORE_PCI_COMMON_FORMAT(), + .name = "pciex8", +}; + +static struct intel_uncore_type gnr_uncore_pciex16 = { + SPR_UNCORE_PCI_COMMON_FORMAT(), + .name = "pciex16", +}; + +static struct intel_uncore_type gnr_uncore_upi = { + SPR_UNCORE_PCI_COMMON_FORMAT(), + .name = "upi", +}; + +static struct intel_uncore_type gnr_uncore_b2upi = { + SPR_UNCORE_PCI_COMMON_FORMAT(), + .name = "b2upi", +}; + +static struct intel_uncore_type gnr_uncore_b2hot = { + .name = "b2hot", + .attr_update = uncore_alias_groups, +}; + static struct intel_uncore_type gnr_uncore_b2cmi = { SPR_UNCORE_PCI_COMMON_FORMAT(), .name = "b2cmi", @@ -6727,21 +6743,21 @@ static struct intel_uncore_type *gnr_uncores[UNCORE_GNR_NUM_UNCORE_TYPES] = { &gnr_uncore_ubox, &spr_uncore_imc, NULL, + &gnr_uncore_upi, NULL, NULL, NULL, + &spr_uncore_cxlcm, + &spr_uncore_cxldp, NULL, - NULL, - NULL, - NULL, - NULL, + &gnr_uncore_b2hot, &gnr_uncore_b2cmi, &gnr_uncore_b2cxl, - NULL, + &gnr_uncore_b2upi, NULL, &gnr_uncore_mdf_sbo, - NULL, - NULL, + &gnr_uncore_pciex16, + &gnr_uncore_pciex8, }; static struct freerunning_counters gnr_iio_freerunning[] = { diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 82c6f45ce975..31c2771545a6 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -624,6 +624,7 @@ union perf_capabilities { u64 pebs_output_pt_available:1; u64 pebs_timing_info:1; u64 anythread_deprecated:1; + u64 rdpmc_metrics_clear:1; }; u64 capabilities; }; diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index a8defc813c36..d3bb3865c1b1 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -39,6 +39,10 @@ * event: rapl_energy_psys * perf code: 0x5 * + * core counter: consumption of a single physical core + * event: rapl_energy_core (power_core PMU) + * perf code: 0x1 + * * We manage those counters as free running (read-only). They may be * use simultaneously by other tools, such as turbostat. * @@ -70,18 +74,22 @@ MODULE_LICENSE("GPL"); /* * RAPL energy status counters */ -enum perf_rapl_events { +enum perf_rapl_pkg_events { PERF_RAPL_PP0 = 0, /* all cores */ PERF_RAPL_PKG, /* entire package */ PERF_RAPL_RAM, /* DRAM */ PERF_RAPL_PP1, /* gpu */ PERF_RAPL_PSYS, /* psys */ - PERF_RAPL_MAX, - NR_RAPL_DOMAINS = PERF_RAPL_MAX, + PERF_RAPL_PKG_EVENTS_MAX, + NR_RAPL_PKG_DOMAINS = PERF_RAPL_PKG_EVENTS_MAX, }; -static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { +#define PERF_RAPL_CORE 0 /* single core */ +#define PERF_RAPL_CORE_EVENTS_MAX 1 +#define NR_RAPL_CORE_DOMAINS PERF_RAPL_CORE_EVENTS_MAX + +static const char *const rapl_pkg_domain_names[NR_RAPL_PKG_DOMAINS] __initconst = { "pp0-core", "package", "dram", @@ -89,6 +97,8 @@ static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { "psys", }; +static const char *const rapl_core_domain_name __initconst = "core"; + /* * event code: LSB 8 bits, passed in attr->config * any other bit is reserved @@ -112,7 +122,7 @@ static struct perf_pmu_events_attr event_attr_##v = { \ * considered as either pkg-scope or die-scope, and we are considering * them as die-scope. */ -#define rapl_pmu_is_pkg_scope() \ +#define rapl_pkg_pmu_is_pkg_scope() \ (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || \ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) @@ -129,7 +139,8 @@ struct rapl_pmu { struct rapl_pmus { struct pmu pmu; unsigned int nr_rapl_pmu; - struct rapl_pmu *pmus[] __counted_by(nr_rapl_pmu); + unsigned int cntr_mask; + struct rapl_pmu *rapl_pmu[] __counted_by(nr_rapl_pmu); }; enum rapl_unit_quirk { @@ -139,44 +150,43 @@ enum rapl_unit_quirk { }; struct rapl_model { - struct perf_msr *rapl_msrs; - unsigned long events; + struct perf_msr *rapl_pkg_msrs; + struct perf_msr *rapl_core_msrs; + unsigned long pkg_events; + unsigned long core_events; unsigned int msr_power_unit; enum rapl_unit_quirk unit_quirk; }; /* 1/2^hw_unit Joule */ -static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly; -static struct rapl_pmus *rapl_pmus; -static unsigned int rapl_cntr_mask; +static int rapl_pkg_hw_unit[NR_RAPL_PKG_DOMAINS] __read_mostly; +static int rapl_core_hw_unit __read_mostly; +static struct rapl_pmus *rapl_pmus_pkg; +static struct rapl_pmus *rapl_pmus_core; static u64 rapl_timer_ms; -static struct perf_msr *rapl_msrs; +static struct rapl_model *rapl_model; /* - * Helper functions to get the correct topology macros according to the + * Helper function to get the correct topology id according to the * RAPL PMU scope. */ -static inline unsigned int get_rapl_pmu_idx(int cpu) -{ - return rapl_pmu_is_pkg_scope() ? topology_logical_package_id(cpu) : - topology_logical_die_id(cpu); -} - -static inline const struct cpumask *get_rapl_pmu_cpumask(int cpu) -{ - return rapl_pmu_is_pkg_scope() ? topology_core_cpumask(cpu) : - topology_die_cpumask(cpu); -} - -static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu) +static inline unsigned int get_rapl_pmu_idx(int cpu, int scope) { - unsigned int rapl_pmu_idx = get_rapl_pmu_idx(cpu); - /* - * The unsigned check also catches the '-1' return value for non - * existent mappings in the topology map. + * Returns unsigned int, which converts the '-1' return value + * (for non-existent mappings in topology map) to UINT_MAX, so + * the error check in the caller is simplified. */ - return rapl_pmu_idx < rapl_pmus->nr_rapl_pmu ? rapl_pmus->pmus[rapl_pmu_idx] : NULL; + switch (scope) { + case PERF_PMU_SCOPE_PKG: + return topology_logical_package_id(cpu); + case PERF_PMU_SCOPE_DIE: + return topology_logical_die_id(cpu); + case PERF_PMU_SCOPE_CORE: + return topology_logical_core_id(cpu); + default: + return -EINVAL; + } } static inline u64 rapl_read_counter(struct perf_event *event) @@ -186,19 +196,20 @@ static inline u64 rapl_read_counter(struct perf_event *event) return raw; } -static inline u64 rapl_scale(u64 v, int cfg) +static inline u64 rapl_scale(u64 v, struct perf_event *event) { - if (cfg > NR_RAPL_DOMAINS) { - pr_warn("Invalid domain %d, failed to scale data\n", cfg); - return v; - } + int hw_unit = rapl_pkg_hw_unit[event->hw.config - 1]; + + if (event->pmu->scope == PERF_PMU_SCOPE_CORE) + hw_unit = rapl_core_hw_unit; + /* * scale delta to smallest unit (1/2^32) * users must then scale back: count * 1/(1e9*2^32) to get Joules * or use ldexp(count, -32). * Watts = Joules/Time delta */ - return v << (32 - rapl_hw_unit[cfg - 1]); + return v << (32 - hw_unit); } static u64 rapl_event_update(struct perf_event *event) @@ -225,7 +236,7 @@ static u64 rapl_event_update(struct perf_event *event) delta = (new_raw_count << shift) - (prev_raw_count << shift); delta >>= shift; - sdelta = rapl_scale(delta, event->hw.config); + sdelta = rapl_scale(delta, event); local64_add(sdelta, &event->count); @@ -240,34 +251,34 @@ static void rapl_start_hrtimer(struct rapl_pmu *pmu) static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer) { - struct rapl_pmu *pmu = container_of(hrtimer, struct rapl_pmu, hrtimer); + struct rapl_pmu *rapl_pmu = container_of(hrtimer, struct rapl_pmu, hrtimer); struct perf_event *event; unsigned long flags; - if (!pmu->n_active) + if (!rapl_pmu->n_active) return HRTIMER_NORESTART; - raw_spin_lock_irqsave(&pmu->lock, flags); + raw_spin_lock_irqsave(&rapl_pmu->lock, flags); - list_for_each_entry(event, &pmu->active_list, active_entry) + list_for_each_entry(event, &rapl_pmu->active_list, active_entry) rapl_event_update(event); - raw_spin_unlock_irqrestore(&pmu->lock, flags); + raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags); - hrtimer_forward_now(hrtimer, pmu->timer_interval); + hrtimer_forward_now(hrtimer, rapl_pmu->timer_interval); return HRTIMER_RESTART; } -static void rapl_hrtimer_init(struct rapl_pmu *pmu) +static void rapl_hrtimer_init(struct rapl_pmu *rapl_pmu) { - struct hrtimer *hr = &pmu->hrtimer; + struct hrtimer *hr = &rapl_pmu->hrtimer; hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hr->function = rapl_hrtimer_handle; } -static void __rapl_pmu_event_start(struct rapl_pmu *pmu, +static void __rapl_pmu_event_start(struct rapl_pmu *rapl_pmu, struct perf_event *event) { if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) @@ -275,39 +286,39 @@ static void __rapl_pmu_event_start(struct rapl_pmu *pmu, event->hw.state = 0; - list_add_tail(&event->active_entry, &pmu->active_list); + list_add_tail(&event->active_entry, &rapl_pmu->active_list); local64_set(&event->hw.prev_count, rapl_read_counter(event)); - pmu->n_active++; - if (pmu->n_active == 1) - rapl_start_hrtimer(pmu); + rapl_pmu->n_active++; + if (rapl_pmu->n_active == 1) + rapl_start_hrtimer(rapl_pmu); } static void rapl_pmu_event_start(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = event->pmu_private; + struct rapl_pmu *rapl_pmu = event->pmu_private; unsigned long flags; - raw_spin_lock_irqsave(&pmu->lock, flags); - __rapl_pmu_event_start(pmu, event); - raw_spin_unlock_irqrestore(&pmu->lock, flags); + raw_spin_lock_irqsave(&rapl_pmu->lock, flags); + __rapl_pmu_event_start(rapl_pmu, event); + raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags); } static void rapl_pmu_event_stop(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = event->pmu_private; + struct rapl_pmu *rapl_pmu = event->pmu_private; struct hw_perf_event *hwc = &event->hw; unsigned long flags; - raw_spin_lock_irqsave(&pmu->lock, flags); + raw_spin_lock_irqsave(&rapl_pmu->lock, flags); /* mark event as deactivated and stopped */ if (!(hwc->state & PERF_HES_STOPPED)) { - WARN_ON_ONCE(pmu->n_active <= 0); - pmu->n_active--; - if (pmu->n_active == 0) - hrtimer_cancel(&pmu->hrtimer); + WARN_ON_ONCE(rapl_pmu->n_active <= 0); + rapl_pmu->n_active--; + if (rapl_pmu->n_active == 0) + hrtimer_cancel(&rapl_pmu->hrtimer); list_del(&event->active_entry); @@ -325,23 +336,23 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode) hwc->state |= PERF_HES_UPTODATE; } - raw_spin_unlock_irqrestore(&pmu->lock, flags); + raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags); } static int rapl_pmu_event_add(struct perf_event *event, int mode) { - struct rapl_pmu *pmu = event->pmu_private; + struct rapl_pmu *rapl_pmu = event->pmu_private; struct hw_perf_event *hwc = &event->hw; unsigned long flags; - raw_spin_lock_irqsave(&pmu->lock, flags); + raw_spin_lock_irqsave(&rapl_pmu->lock, flags); hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; if (mode & PERF_EF_START) - __rapl_pmu_event_start(pmu, event); + __rapl_pmu_event_start(rapl_pmu, event); - raw_spin_unlock_irqrestore(&pmu->lock, flags); + raw_spin_unlock_irqrestore(&rapl_pmu->lock, flags); return 0; } @@ -354,12 +365,14 @@ static void rapl_pmu_event_del(struct perf_event *event, int flags) static int rapl_pmu_event_init(struct perf_event *event) { u64 cfg = event->attr.config & RAPL_EVENT_MASK; - int bit, ret = 0; - struct rapl_pmu *pmu; + int bit, rapl_pmus_scope, ret = 0; + struct rapl_pmu *rapl_pmu; + unsigned int rapl_pmu_idx; + struct rapl_pmus *rapl_pmus; - /* only look at RAPL events */ - if (event->attr.type != rapl_pmus->pmu.type) - return -ENOENT; + /* unsupported modes and filters */ + if (event->attr.sample_period) /* no sampling */ + return -EINVAL; /* check only supported bits are set */ if (event->attr.config & ~RAPL_EVENT_MASK) @@ -368,26 +381,49 @@ static int rapl_pmu_event_init(struct perf_event *event) if (event->cpu < 0) return -EINVAL; - if (!cfg || cfg >= NR_RAPL_DOMAINS + 1) + rapl_pmus = container_of(event->pmu, struct rapl_pmus, pmu); + if (!rapl_pmus) + return -EINVAL; + rapl_pmus_scope = rapl_pmus->pmu.scope; + + if (rapl_pmus_scope == PERF_PMU_SCOPE_PKG || rapl_pmus_scope == PERF_PMU_SCOPE_DIE) { + /* only look at RAPL package events */ + if (event->attr.type != rapl_pmus_pkg->pmu.type) + return -ENOENT; + + cfg = array_index_nospec((long)cfg, NR_RAPL_PKG_DOMAINS + 1); + if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1) + return -EINVAL; + + bit = cfg - 1; + event->hw.event_base = rapl_model->rapl_pkg_msrs[bit].msr; + } else if (rapl_pmus_scope == PERF_PMU_SCOPE_CORE) { + /* only look at RAPL core events */ + if (event->attr.type != rapl_pmus_core->pmu.type) + return -ENOENT; + + cfg = array_index_nospec((long)cfg, NR_RAPL_CORE_DOMAINS + 1); + if (!cfg || cfg >= NR_RAPL_PKG_DOMAINS + 1) + return -EINVAL; + + bit = cfg - 1; + event->hw.event_base = rapl_model->rapl_core_msrs[bit].msr; + } else return -EINVAL; - - cfg = array_index_nospec((long)cfg, NR_RAPL_DOMAINS + 1); - bit = cfg - 1; /* check event supported */ - if (!(rapl_cntr_mask & (1 << bit))) + if (!(rapl_pmus->cntr_mask & (1 << bit))) return -EINVAL; - /* unsupported modes and filters */ - if (event->attr.sample_period) /* no sampling */ + rapl_pmu_idx = get_rapl_pmu_idx(event->cpu, rapl_pmus_scope); + if (rapl_pmu_idx >= rapl_pmus->nr_rapl_pmu) return -EINVAL; - /* must be done before validate_group */ - pmu = cpu_to_rapl_pmu(event->cpu); - if (!pmu) + rapl_pmu = rapl_pmus->rapl_pmu[rapl_pmu_idx]; + if (!rapl_pmu) return -EINVAL; - event->pmu_private = pmu; - event->hw.event_base = rapl_msrs[bit].msr; + + event->pmu_private = rapl_pmu; event->hw.config = cfg; event->hw.idx = bit; @@ -404,12 +440,14 @@ RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); RAPL_EVENT_ATTR_STR(energy-gpu , rapl_gpu, "event=0x04"); RAPL_EVENT_ATTR_STR(energy-psys, rapl_psys, "event=0x05"); +RAPL_EVENT_ATTR_STR(energy-core, rapl_core, "event=0x01"); RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-pkg.unit , rapl_pkg_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-ram.unit , rapl_ram_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-gpu.unit , rapl_gpu_unit, "Joules"); RAPL_EVENT_ATTR_STR(energy-psys.unit, rapl_psys_unit, "Joules"); +RAPL_EVENT_ATTR_STR(energy-core.unit, rapl_core_unit, "Joules"); /* * we compute in 0.23 nJ increments regardless of MSR @@ -419,6 +457,7 @@ RAPL_EVENT_ATTR_STR(energy-pkg.scale, rapl_pkg_scale, "2.3283064365386962890 RAPL_EVENT_ATTR_STR(energy-ram.scale, rapl_ram_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-gpu.scale, rapl_gpu_scale, "2.3283064365386962890625e-10"); RAPL_EVENT_ATTR_STR(energy-psys.scale, rapl_psys_scale, "2.3283064365386962890625e-10"); +RAPL_EVENT_ATTR_STR(energy-core.scale, rapl_core_scale, "2.3283064365386962890625e-10"); /* * There are no default events, but we need to create @@ -451,6 +490,12 @@ static const struct attribute_group *rapl_attr_groups[] = { NULL, }; +static const struct attribute_group *rapl_core_attr_groups[] = { + &rapl_pmu_format_group, + &rapl_pmu_events_group, + NULL, +}; + static struct attribute *rapl_events_cores[] = { EVENT_PTR(rapl_cores), EVENT_PTR(rapl_cores_unit), @@ -511,6 +556,18 @@ static struct attribute_group rapl_events_psys_group = { .attrs = rapl_events_psys, }; +static struct attribute *rapl_events_core[] = { + EVENT_PTR(rapl_core), + EVENT_PTR(rapl_core_unit), + EVENT_PTR(rapl_core_scale), + NULL, +}; + +static struct attribute_group rapl_events_core_group = { + .name = "events", + .attrs = rapl_events_core, +}; + static bool test_msr(int idx, void *data) { return test_bit(idx, (unsigned long *) data); @@ -536,11 +593,11 @@ static struct perf_msr intel_rapl_spr_msrs[] = { }; /* - * Force to PERF_RAPL_MAX size due to: - * - perf_msr_probe(PERF_RAPL_MAX) + * Force to PERF_RAPL_PKG_EVENTS_MAX size due to: + * - perf_msr_probe(PERF_RAPL_PKG_EVENTS_MAX) * - want to use same event codes across both architectures */ -static struct perf_msr amd_rapl_msrs[] = { +static struct perf_msr amd_rapl_pkg_msrs[] = { [PERF_RAPL_PP0] = { 0, &rapl_events_cores_group, NULL, false, 0 }, [PERF_RAPL_PKG] = { MSR_AMD_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr, false, RAPL_MSR_MASK }, [PERF_RAPL_RAM] = { 0, &rapl_events_ram_group, NULL, false, 0 }, @@ -548,18 +605,25 @@ static struct perf_msr amd_rapl_msrs[] = { [PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group, NULL, false, 0 }, }; -static int rapl_check_hw_unit(struct rapl_model *rm) +static struct perf_msr amd_rapl_core_msrs[] = { + [PERF_RAPL_CORE] = { MSR_AMD_CORE_ENERGY_STATUS, &rapl_events_core_group, + test_msr, false, RAPL_MSR_MASK }, +}; + +static int rapl_check_hw_unit(void) { u64 msr_rapl_power_unit_bits; int i; /* protect rdmsrl() to handle virtualization */ - if (rdmsrl_safe(rm->msr_power_unit, &msr_rapl_power_unit_bits)) + if (rdmsrl_safe(rapl_model->msr_power_unit, &msr_rapl_power_unit_bits)) return -1; - for (i = 0; i < NR_RAPL_DOMAINS; i++) - rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; + for (i = 0; i < NR_RAPL_PKG_DOMAINS; i++) + rapl_pkg_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; - switch (rm->unit_quirk) { + rapl_core_hw_unit = (msr_rapl_power_unit_bits >> 8) & 0x1FULL; + + switch (rapl_model->unit_quirk) { /* * DRAM domain on HSW server and KNL has fixed energy unit which can be * different than the unit from power unit MSR. See @@ -567,17 +631,16 @@ static int rapl_check_hw_unit(struct rapl_model *rm) * of 2. Datasheet, September 2014, Reference Number: 330784-001 " */ case RAPL_UNIT_QUIRK_INTEL_HSW: - rapl_hw_unit[PERF_RAPL_RAM] = 16; + rapl_pkg_hw_unit[PERF_RAPL_RAM] = 16; break; /* SPR uses a fixed energy unit for Psys domain. */ case RAPL_UNIT_QUIRK_INTEL_SPR: - rapl_hw_unit[PERF_RAPL_PSYS] = 0; + rapl_pkg_hw_unit[PERF_RAPL_PSYS] = 0; break; default: break; } - /* * Calculate the timer rate: * Use reference of 200W for scaling the timeout to avoid counter @@ -586,9 +649,9 @@ static int rapl_check_hw_unit(struct rapl_model *rm) * if hw unit is 32, then we use 2 ms 1/200/2 */ rapl_timer_ms = 2; - if (rapl_hw_unit[0] < 32) { + if (rapl_pkg_hw_unit[0] < 32) { rapl_timer_ms = (1000 / (2 * 100)); - rapl_timer_ms *= (1ULL << (32 - rapl_hw_unit[0] - 1)); + rapl_timer_ms *= (1ULL << (32 - rapl_pkg_hw_unit[0] - 1)); } return 0; } @@ -596,24 +659,32 @@ static int rapl_check_hw_unit(struct rapl_model *rm) static void __init rapl_advertise(void) { int i; + int num_counters = hweight32(rapl_pmus_pkg->cntr_mask); + + if (rapl_pmus_core) + num_counters += hweight32(rapl_pmus_core->cntr_mask); pr_info("API unit is 2^-32 Joules, %d fixed counters, %llu ms ovfl timer\n", - hweight32(rapl_cntr_mask), rapl_timer_ms); + num_counters, rapl_timer_ms); - for (i = 0; i < NR_RAPL_DOMAINS; i++) { - if (rapl_cntr_mask & (1 << i)) { + for (i = 0; i < NR_RAPL_PKG_DOMAINS; i++) { + if (rapl_pmus_pkg->cntr_mask & (1 << i)) { pr_info("hw unit of domain %s 2^-%d Joules\n", - rapl_domain_names[i], rapl_hw_unit[i]); + rapl_pkg_domain_names[i], rapl_pkg_hw_unit[i]); } } + + if (rapl_pmus_core && (rapl_pmus_core->cntr_mask & (1 << PERF_RAPL_CORE))) + pr_info("hw unit of domain %s 2^-%d Joules\n", + rapl_core_domain_name, rapl_core_hw_unit); } -static void cleanup_rapl_pmus(void) +static void cleanup_rapl_pmus(struct rapl_pmus *rapl_pmus) { int i; for (i = 0; i < rapl_pmus->nr_rapl_pmu; i++) - kfree(rapl_pmus->pmus[i]); + kfree(rapl_pmus->rapl_pmu[i]); kfree(rapl_pmus); } @@ -626,46 +697,60 @@ static const struct attribute_group *rapl_attr_update[] = { NULL, }; -static int __init init_rapl_pmu(void) +static const struct attribute_group *rapl_core_attr_update[] = { + &rapl_events_core_group, + NULL, +}; + +static int __init init_rapl_pmu(struct rapl_pmus *rapl_pmus) { - struct rapl_pmu *pmu; + struct rapl_pmu *rapl_pmu; int idx; for (idx = 0; idx < rapl_pmus->nr_rapl_pmu; idx++) { - pmu = kzalloc(sizeof(*pmu), GFP_KERNEL); - if (!pmu) + rapl_pmu = kzalloc(sizeof(*rapl_pmu), GFP_KERNEL); + if (!rapl_pmu) goto free; - raw_spin_lock_init(&pmu->lock); - INIT_LIST_HEAD(&pmu->active_list); - pmu->pmu = &rapl_pmus->pmu; - pmu->timer_interval = ms_to_ktime(rapl_timer_ms); - rapl_hrtimer_init(pmu); + raw_spin_lock_init(&rapl_pmu->lock); + INIT_LIST_HEAD(&rapl_pmu->active_list); + rapl_pmu->pmu = &rapl_pmus->pmu; + rapl_pmu->timer_interval = ms_to_ktime(rapl_timer_ms); + rapl_hrtimer_init(rapl_pmu); - rapl_pmus->pmus[idx] = pmu; + rapl_pmus->rapl_pmu[idx] = rapl_pmu; } return 0; free: for (; idx > 0; idx--) - kfree(rapl_pmus->pmus[idx - 1]); + kfree(rapl_pmus->rapl_pmu[idx - 1]); return -ENOMEM; } -static int __init init_rapl_pmus(void) +static int __init init_rapl_pmus(struct rapl_pmus **rapl_pmus_ptr, int rapl_pmu_scope, + const struct attribute_group **rapl_attr_groups, + const struct attribute_group **rapl_attr_update) { int nr_rapl_pmu = topology_max_packages(); - int rapl_pmu_scope = PERF_PMU_SCOPE_PKG; + struct rapl_pmus *rapl_pmus; - if (!rapl_pmu_is_pkg_scope()) { - nr_rapl_pmu *= topology_max_dies_per_package(); - rapl_pmu_scope = PERF_PMU_SCOPE_DIE; - } + /* + * rapl_pmu_scope must be either PKG, DIE or CORE + */ + if (rapl_pmu_scope == PERF_PMU_SCOPE_DIE) + nr_rapl_pmu *= topology_max_dies_per_package(); + else if (rapl_pmu_scope == PERF_PMU_SCOPE_CORE) + nr_rapl_pmu *= topology_num_cores_per_package(); + else if (rapl_pmu_scope != PERF_PMU_SCOPE_PKG) + return -EINVAL; - rapl_pmus = kzalloc(struct_size(rapl_pmus, pmus, nr_rapl_pmu), GFP_KERNEL); + rapl_pmus = kzalloc(struct_size(rapl_pmus, rapl_pmu, nr_rapl_pmu), GFP_KERNEL); if (!rapl_pmus) return -ENOMEM; + *rapl_pmus_ptr = rapl_pmus; + rapl_pmus->nr_rapl_pmu = nr_rapl_pmu; rapl_pmus->pmu.attr_groups = rapl_attr_groups; rapl_pmus->pmu.attr_update = rapl_attr_update; @@ -680,75 +765,77 @@ static int __init init_rapl_pmus(void) rapl_pmus->pmu.module = THIS_MODULE; rapl_pmus->pmu.capabilities = PERF_PMU_CAP_NO_EXCLUDE; - return init_rapl_pmu(); + return init_rapl_pmu(rapl_pmus); } static struct rapl_model model_snb = { - .events = BIT(PERF_RAPL_PP0) | + .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_PP1), .msr_power_unit = MSR_RAPL_POWER_UNIT, - .rapl_msrs = intel_rapl_msrs, + .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_snbep = { - .events = BIT(PERF_RAPL_PP0) | + .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), .msr_power_unit = MSR_RAPL_POWER_UNIT, - .rapl_msrs = intel_rapl_msrs, + .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_hsw = { - .events = BIT(PERF_RAPL_PP0) | + .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PP1), .msr_power_unit = MSR_RAPL_POWER_UNIT, - .rapl_msrs = intel_rapl_msrs, + .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_hsx = { - .events = BIT(PERF_RAPL_PP0) | + .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), .unit_quirk = RAPL_UNIT_QUIRK_INTEL_HSW, .msr_power_unit = MSR_RAPL_POWER_UNIT, - .rapl_msrs = intel_rapl_msrs, + .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_knl = { - .events = BIT(PERF_RAPL_PKG) | + .pkg_events = BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM), .unit_quirk = RAPL_UNIT_QUIRK_INTEL_HSW, .msr_power_unit = MSR_RAPL_POWER_UNIT, - .rapl_msrs = intel_rapl_msrs, + .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_skl = { - .events = BIT(PERF_RAPL_PP0) | + .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PP1) | BIT(PERF_RAPL_PSYS), .msr_power_unit = MSR_RAPL_POWER_UNIT, - .rapl_msrs = intel_rapl_msrs, + .rapl_pkg_msrs = intel_rapl_msrs, }; static struct rapl_model model_spr = { - .events = BIT(PERF_RAPL_PP0) | + .pkg_events = BIT(PERF_RAPL_PP0) | BIT(PERF_RAPL_PKG) | BIT(PERF_RAPL_RAM) | BIT(PERF_RAPL_PSYS), .unit_quirk = RAPL_UNIT_QUIRK_INTEL_SPR, .msr_power_unit = MSR_RAPL_POWER_UNIT, - .rapl_msrs = intel_rapl_spr_msrs, + .rapl_pkg_msrs = intel_rapl_spr_msrs, }; static struct rapl_model model_amd_hygon = { - .events = BIT(PERF_RAPL_PKG), + .pkg_events = BIT(PERF_RAPL_PKG), + .core_events = BIT(PERF_RAPL_CORE), .msr_power_unit = MSR_AMD_RAPL_POWER_UNIT, - .rapl_msrs = amd_rapl_msrs, + .rapl_pkg_msrs = amd_rapl_pkg_msrs, + .rapl_core_msrs = amd_rapl_core_msrs, }; static const struct x86_cpu_id rapl_model_match[] __initconst = { @@ -804,45 +891,73 @@ MODULE_DEVICE_TABLE(x86cpu, rapl_model_match); static int __init rapl_pmu_init(void) { const struct x86_cpu_id *id; - struct rapl_model *rm; + int rapl_pkg_pmu_scope = PERF_PMU_SCOPE_DIE; int ret; + if (rapl_pkg_pmu_is_pkg_scope()) + rapl_pkg_pmu_scope = PERF_PMU_SCOPE_PKG; + id = x86_match_cpu(rapl_model_match); if (!id) return -ENODEV; - rm = (struct rapl_model *) id->driver_data; - - rapl_msrs = rm->rapl_msrs; + rapl_model = (struct rapl_model *) id->driver_data; - rapl_cntr_mask = perf_msr_probe(rapl_msrs, PERF_RAPL_MAX, - false, (void *) &rm->events); - - ret = rapl_check_hw_unit(rm); + ret = rapl_check_hw_unit(); if (ret) return ret; - ret = init_rapl_pmus(); + ret = init_rapl_pmus(&rapl_pmus_pkg, rapl_pkg_pmu_scope, rapl_attr_groups, + rapl_attr_update); if (ret) return ret; - ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1); + rapl_pmus_pkg->cntr_mask = perf_msr_probe(rapl_model->rapl_pkg_msrs, + PERF_RAPL_PKG_EVENTS_MAX, false, + (void *) &rapl_model->pkg_events); + + ret = perf_pmu_register(&rapl_pmus_pkg->pmu, "power", -1); if (ret) goto out; + if (rapl_model->core_events) { + ret = init_rapl_pmus(&rapl_pmus_core, PERF_PMU_SCOPE_CORE, + rapl_core_attr_groups, + rapl_core_attr_update); + if (ret) { + pr_warn("power-core PMU initialization failed (%d)\n", ret); + goto core_init_failed; + } + + rapl_pmus_core->cntr_mask = perf_msr_probe(rapl_model->rapl_core_msrs, + PERF_RAPL_CORE_EVENTS_MAX, false, + (void *) &rapl_model->core_events); + + ret = perf_pmu_register(&rapl_pmus_core->pmu, "power_core", -1); + if (ret) { + pr_warn("power-core PMU registration failed (%d)\n", ret); + cleanup_rapl_pmus(rapl_pmus_core); + } + } + +core_init_failed: rapl_advertise(); return 0; out: pr_warn("Initialization failed (%d), disabled\n", ret); - cleanup_rapl_pmus(); + cleanup_rapl_pmus(rapl_pmus_pkg); return ret; } module_init(rapl_pmu_init); static void __exit intel_rapl_exit(void) { - perf_pmu_unregister(&rapl_pmus->pmu); - cleanup_rapl_pmus(); + if (rapl_pmus_core) { + perf_pmu_unregister(&rapl_pmus_core->pmu); + cleanup_rapl_pmus(rapl_pmus_core); + } + perf_pmu_unregister(&rapl_pmus_pkg->pmu); + cleanup_rapl_pmus(rapl_pmus_pkg); } module_exit(intel_rapl_exit); diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c index 3215a4a07408..64b921360b0f 100644 --- a/arch/x86/hyperv/irqdomain.c +++ b/arch/x86/hyperv/irqdomain.c @@ -304,7 +304,7 @@ static struct irq_chip hv_pci_msi_controller = { .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_compose_msi_msg = hv_irq_compose_msi_msg, .irq_set_affinity = msi_domain_set_affinity, - .flags = IRQCHIP_SKIP_SET_WAKE, + .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MOVE_DEFERRED, }; static struct msi_domain_ops pci_msi_domain_ops = { diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 60fc3ed72830..90aabe1fd3b6 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -664,7 +664,7 @@ void __init hv_vtom_init(void) x86_platform.guest.enc_status_change_finish = hv_vtom_set_host_visibility; /* Set WB as the default cache mode. */ - mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK); + guest_force_mtrr_state(NULL, 0, MTRR_TYPE_WRBACK); } #endif /* defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST) */ diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 6c23d1661b17..58f4ddecc5fa 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -10,5 +10,6 @@ generated-y += unistd_64_x32.h generated-y += xen-hypercalls.h generic-y += early_ioremap.h +generic-y += fprobe.h generic-y += mcs_spinlock.h generic-y += mmzone.h diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index dc03a647776d..e3903b731305 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -4,6 +4,7 @@ #include <linux/types.h> #include <linux/stringify.h> +#include <linux/objtool.h> #include <asm/asm.h> #define ALT_FLAGS_SHIFT 16 @@ -55,16 +56,6 @@ #endif /* - * objtool annotation to ignore the alternatives and only consider the original - * instruction(s). - */ -#define ANNOTATE_IGNORE_ALTERNATIVE \ - "999:\n\t" \ - ".pushsection .discard.ignore_alts\n\t" \ - ".long 999b\n\t" \ - ".popsection\n\t" - -/* * The patching flags are part of the upper bits of the @ft_flags parameter when * specifying them. The split is currently like this: * @@ -311,17 +302,6 @@ void nop_func(void); #endif /* - * objtool annotation to ignore the alternatives and only consider the original - * instruction(s). - */ -.macro ANNOTATE_IGNORE_ALTERNATIVE - .Lannotate_\@: - .pushsection .discard.ignore_alts - .long .Lannotate_\@ - .popsection -.endm - -/* * Issue one struct alt_instr descriptor entry (need to put it into * the section .altinstructions, see below). This entry contains * enough information for the alternatives patching code to patch an diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index d0caac26533f..4c4efb93045e 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -4,7 +4,7 @@ #include <linux/ioport.h> #include <linux/pci.h> -#include <linux/refcount.h> +#include <asm/amd_node.h> struct amd_nb_bus_dev_range { u8 bus; @@ -21,49 +21,16 @@ extern int amd_numa_init(void); extern int amd_get_subcaches(int); extern int amd_set_subcaches(int, unsigned long); -int __must_check amd_smn_read(u16 node, u32 address, u32 *value); -int __must_check amd_smn_write(u16 node, u32 address, u32 value); - struct amd_l3_cache { unsigned indices; u8 subcaches[4]; }; -struct threshold_block { - unsigned int block; /* Number within bank */ - unsigned int bank; /* MCA bank the block belongs to */ - unsigned int cpu; /* CPU which controls MCA bank */ - u32 address; /* MSR address for the block */ - u16 interrupt_enable; /* Enable/Disable APIC interrupt */ - bool interrupt_capable; /* Bank can generate an interrupt. */ - - u16 threshold_limit; /* - * Value upon which threshold - * interrupt is generated. - */ - - struct kobject kobj; /* sysfs object */ - struct list_head miscj; /* - * List of threshold blocks - * within a bank. - */ -}; - -struct threshold_bank { - struct kobject *kobj; - struct threshold_block *blocks; - - /* initialized to the number of CPUs on the node sharing this bank */ - refcount_t cpus; - unsigned int shared; -}; - struct amd_northbridge { struct pci_dev *root; struct pci_dev *misc; struct pci_dev *link; struct amd_l3_cache l3_cache; - struct threshold_bank *bank4; }; struct amd_northbridge_info { @@ -82,23 +49,6 @@ u16 amd_nb_num(void); bool amd_nb_has_feature(unsigned int feature); struct amd_northbridge *node_to_amd_nb(int node); -static inline u16 amd_pci_dev_to_node_id(struct pci_dev *pdev) -{ - struct pci_dev *misc; - int i; - - for (i = 0; i != amd_nb_num(); i++) { - misc = node_to_amd_nb(i)->misc; - - if (pci_domain_nr(misc->bus) == pci_domain_nr(pdev->bus) && - PCI_SLOT(misc->devfn) == PCI_SLOT(pdev->devfn)) - return i; - } - - WARN(1, "Unable to find AMD Northbridge id for %s\n", pci_name(pdev)); - return 0; -} - static inline bool amd_gart_present(void) { if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) diff --git a/arch/x86/include/asm/amd_node.h b/arch/x86/include/asm/amd_node.h new file mode 100644 index 000000000000..113ad3e8ee40 --- /dev/null +++ b/arch/x86/include/asm/amd_node.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD Node helper functions and common defines + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + * + * Note: + * Items in this file may only be used in a single place. + * However, it's prudent to keep all AMD Node functionality + * in a unified place rather than spreading throughout the + * kernel. + */ + +#ifndef _ASM_X86_AMD_NODE_H_ +#define _ASM_X86_AMD_NODE_H_ + +#include <linux/pci.h> + +#define MAX_AMD_NUM_NODES 8 +#define AMD_NODE0_PCI_SLOT 0x18 + +struct pci_dev *amd_node_get_func(u16 node, u8 func); +struct pci_dev *amd_node_get_root(u16 node); + +static inline u16 amd_num_nodes(void) +{ + return topology_amd_nodes_per_pkg() * topology_max_packages(); +} + +int __must_check amd_smn_read(u16 node, u32 address, u32 *value); +int __must_check amd_smn_write(u16 node, u32 address, u32 value); + +#endif /*_ASM_X86_AMD_NODE_H_*/ diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index 806649c7f23d..e85ac0c7c039 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -92,7 +92,7 @@ do { \ do { \ __auto_type __flags = BUGFLAG_WARNING|(flags); \ instrumentation_begin(); \ - _BUG_FLAGS(ASM_UD2, __flags, ASM_REACHABLE); \ + _BUG_FLAGS(ASM_UD2, __flags, ANNOTATE_REACHABLE(1b)); \ instrumentation_end(); \ } while (0) diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index e4121d9aa9e1..ba32e0f44cba 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -56,7 +56,6 @@ /* x86_cpu_id::flags */ #define X86_CPU_ID_FLAG_ENTRY_VALID BIT(0) -#define X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins) /** * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching * @_vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY @@ -208,6 +207,7 @@ VFM_MODEL(vfm), \ X86_STEPPING_ANY, X86_FEATURE_ANY, data) +#define __X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins) /** * X86_MATCH_VFM_STEPPINGS - Match encoded vendor/family/model/stepping * @vfm: Encoded 8-bits each for vendor, family, model @@ -218,12 +218,13 @@ * * feature is set to wildcard */ -#define X86_MATCH_VFM_STEPPINGS(vfm, steppings, data) \ - X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \ - VFM_VENDOR(vfm), \ - VFM_FAMILY(vfm), \ - VFM_MODEL(vfm), \ - steppings, X86_FEATURE_ANY, data) +#define X86_MATCH_VFM_STEPS(vfm, min_step, max_step, data) \ + X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \ + VFM_VENDOR(vfm), \ + VFM_FAMILY(vfm), \ + VFM_MODEL(vfm), \ + __X86_STEPPINGS(min_step, max_step), \ + X86_FEATURE_ANY, data) /** * X86_MATCH_VFM_FEATURE - Match encoded vendor/family/model/feature @@ -242,41 +243,7 @@ VFM_MODEL(vfm), \ X86_STEPPING_ANY, feature, data) -/* - * Match specific microcode revisions. - * - * vendor/family/model/stepping must be all set. - * - * Only checks against the boot CPU. When mixed-stepping configs are - * valid for a CPU model, add a quirk for every valid stepping and - * do the fine-tuning in the quirk handler. - */ - -struct x86_cpu_desc { - u8 x86_family; - u8 x86_vendor; - u8 x86_model; - u8 x86_stepping; - u32 x86_microcode_rev; -}; - -#define INTEL_CPU_DESC(vfm, stepping, revision) { \ - .x86_family = VFM_FAMILY(vfm), \ - .x86_vendor = VFM_VENDOR(vfm), \ - .x86_model = VFM_MODEL(vfm), \ - .x86_stepping = (stepping), \ - .x86_microcode_rev = (revision), \ -} - -#define AMD_CPU_DESC(fam, model, stepping, revision) { \ - .x86_family = (fam), \ - .x86_vendor = X86_VENDOR_AMD, \ - .x86_model = (model), \ - .x86_stepping = (stepping), \ - .x86_microcode_rev = (revision), \ -} - extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match); -extern bool x86_cpu_has_min_microcode_rev(const struct x86_cpu_desc *table); +extern bool x86_match_min_microcode_rev(const struct x86_cpu_id *table); #endif /* _ASM_X86_CPU_DEVICE_ID */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 0b9611da6c53..de1ad09fe8d7 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -132,11 +132,12 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; x86_this_cpu_test_bit(bit, cpu_info.x86_capability)) /* - * This macro is for detection of features which need kernel - * infrastructure to be used. It may *not* directly test the CPU - * itself. Use the cpu_has() family if you want true runtime - * testing of CPU features, like in hypervisor code where you are - * supporting a possible guest feature where host support for it + * This is the default CPU features testing macro to use in code. + * + * It is for detection of features which need kernel infrastructure to be + * used. It may *not* directly test the CPU itself. Use the cpu_has() family + * if you want true runtime testing of CPU features, like in hypervisor code + * where you are supporting a possible guest feature where host support for it * is not relevant. */ #define cpu_feature_enabled(bit) \ @@ -161,13 +162,6 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) /* - * Static testing of CPU features. Used the same as boot_cpu_has(). It - * statically patches the target code for additional performance. Use - * static_cpu_has() only in fast paths, where every cycle counts. Which - * means that the boot_cpu_has() variant is already fast enough for the - * majority of cases and you should stick to using it as it is generally - * only two instructions: a RIP-relative MOV and a TEST. - * * Do not use an "m" constraint for [cap_byte] here: gcc doesn't know * that this is only used on a fallback path and will sometimes cause * it to manifest the address of boot_cpu_data in a register, fouling diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 17b6590748c0..508c0dad116b 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -83,8 +83,8 @@ #define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */ #define X86_FEATURE_K8 ( 3*32+ 4) /* Opteron, Athlon64 */ #define X86_FEATURE_ZEN5 ( 3*32+ 5) /* CPU based on Zen5 microarchitecture */ -#define X86_FEATURE_P3 ( 3*32+ 6) /* P3 */ -#define X86_FEATURE_P4 ( 3*32+ 7) /* P4 */ +/* Free ( 3*32+ 6) */ +/* Free ( 3*32+ 7) */ #define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */ #define X86_FEATURE_UP ( 3*32+ 9) /* "up" SMP kernel running on UP */ #define X86_FEATURE_ART ( 3*32+10) /* "art" Always running timer (ART) */ @@ -443,15 +443,18 @@ #define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* Speculative Store Bypass Disable */ /* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */ -#define X86_FEATURE_SME (19*32+ 0) /* "sme" AMD Secure Memory Encryption */ -#define X86_FEATURE_SEV (19*32+ 1) /* "sev" AMD Secure Encrypted Virtualization */ +#define X86_FEATURE_SME (19*32+ 0) /* "sme" Secure Memory Encryption */ +#define X86_FEATURE_SEV (19*32+ 1) /* "sev" Secure Encrypted Virtualization */ #define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* VM Page Flush MSR is supported */ -#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" AMD Secure Encrypted Virtualization - Encrypted State */ -#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" AMD Secure Encrypted Virtualization - Secure Nested Paging */ +#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" Secure Encrypted Virtualization - Secure Nested Paging */ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* Virtual TSC_AUX */ -#define X86_FEATURE_SME_COHERENT (19*32+10) /* AMD hardware-enforced cache coherency */ -#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" AMD SEV-ES full debug state swap support */ +#define X86_FEATURE_SME_COHERENT (19*32+10) /* hardware-enforced cache coherency */ +#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" SEV-ES full debug state swap support */ +#define X86_FEATURE_RMPREAD (19*32+21) /* RMPREAD instruction */ +#define X86_FEATURE_SEGMENTED_RMP (19*32+23) /* Segmented RMP support */ #define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */ +#define X86_FEATURE_HV_INUSE_WR_ALLOWED (19*32+30) /* Allow Write to in-use hypervisor-owned pages */ /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ #define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */ @@ -464,6 +467,7 @@ #define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */ #define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */ #define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */ +#define X86_FEATURE_SRSO_USER_KERNEL_NO (20*32+30) /* CPU is not affected by SRSO across user/kernel boundaries */ /* * Extended auxiliary flags: Linux defined - for features scattered in various diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h index 239b9ba5c398..b2b9b4ef3dae 100644 --- a/arch/x86/include/asm/cpuid.h +++ b/arch/x86/include/asm/cpuid.h @@ -21,6 +21,13 @@ enum cpuid_regs_idx { CPUID_EDX, }; +#define CPUID_LEAF_MWAIT 0x5 +#define CPUID_LEAF_DCA 0x9 +#define CPUID_LEAF_XSTATE 0x0d +#define CPUID_LEAF_TSC 0x15 +#define CPUID_LEAF_FREQ 0x16 +#define CPUID_LEAF_TILE 0x1d + #ifdef CONFIG_X86_32 bool have_cpuid_p(void); #else diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h index d4427b88ee12..7f39fe7980c5 100644 --- a/arch/x86/include/asm/fpu/xstate.h +++ b/arch/x86/include/asm/fpu/xstate.h @@ -12,10 +12,6 @@ /* Bit 63 of XCR0 is reserved for future expansion */ #define XFEATURE_MASK_EXTEND (~(XFEATURE_MASK_FPSSE | (1ULL << 63))) -#define XSTATE_CPUID 0x0000000d - -#define TILE_CPUID 0x0000001d - #define FXSAVE_SIZE 512 #define XSAVE_HDR_SIZE 64 diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 6e8cf0fa48fc..f9cb4d07df58 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -34,6 +34,27 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) return addr; } +static inline unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip) +{ +#ifdef CONFIG_X86_KERNEL_IBT + u32 instr; + + /* We want to be extra safe in case entry ip is on the page edge, + * but otherwise we need to avoid get_kernel_nofault()'s overhead. + */ + if ((fentry_ip & ~PAGE_MASK) < ENDBR_INSN_SIZE) { + if (get_kernel_nofault(instr, (u32 *)(fentry_ip - ENDBR_INSN_SIZE))) + return fentry_ip; + } else { + instr = *(u32 *)(fentry_ip - ENDBR_INSN_SIZE); + } + if (is_endbr(instr)) + fentry_ip -= ENDBR_INSN_SIZE; +#endif + return fentry_ip; +} +#define ftrace_get_symaddr(fentry_ip) arch_ftrace_get_symaddr(fentry_ip) + #ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS #include <linux/ftrace_regs.h> @@ -47,10 +68,23 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs) return &arch_ftrace_regs(fregs)->regs; } +#define arch_ftrace_fill_perf_regs(fregs, _regs) do { \ + (_regs)->ip = arch_ftrace_regs(fregs)->regs.ip; \ + (_regs)->sp = arch_ftrace_regs(fregs)->regs.sp; \ + (_regs)->cs = __KERNEL_CS; \ + (_regs)->flags = 0; \ + } while (0) + #define ftrace_regs_set_instruction_pointer(fregs, _ip) \ do { arch_ftrace_regs(fregs)->regs.ip = (_ip); } while (0) +static __always_inline unsigned long +ftrace_regs_get_return_address(struct ftrace_regs *fregs) +{ + return *(unsigned long *)ftrace_regs_get_stack_pointer(fregs); +} + struct ftrace_ops; #define ftrace_graph_func ftrace_graph_func void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, @@ -134,24 +168,4 @@ static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs) #endif /* !COMPILE_OFFSETS */ #endif /* !__ASSEMBLY__ */ -#ifndef __ASSEMBLY__ -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -struct fgraph_ret_regs { - unsigned long ax; - unsigned long dx; - unsigned long bp; -}; - -static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->ax; -} - -static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs) -{ - return ret_regs->bp; -} -#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */ -#endif - #endif /* _ASM_X86_FTRACE_H */ diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index b71ad173f877..562a547c29a5 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -100,8 +100,8 @@ } #define ASM_CALL_ARG0 \ - "call %c[__func] \n" \ - ASM_REACHABLE + "1: call %c[__func] \n" \ + ANNOTATE_REACHABLE(1b) #define ASM_CALL_ARG1 \ "movq %[arg1], %%rdi \n" \ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 4543cf2eb5e8..eb2db07ef39c 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -276,7 +276,7 @@ static inline void cmci_rediscover(void) {} static inline void cmci_recheck(void) {} #endif -int mce_available(struct cpuinfo_x86 *c); +bool mce_available(struct cpuinfo_x86 *c); bool mce_is_memory_error(struct mce *m); bool mce_is_correctable(struct mce *m); bool mce_usable_address(struct mce *m); @@ -296,7 +296,7 @@ enum mcp_flags { void machine_check_poll(enum mcp_flags flags, mce_banks_t *b); -int mce_notify_irq(void); +bool mce_notify_irq(void); DECLARE_PER_CPU(struct mce, injectm); @@ -386,8 +386,6 @@ static inline bool amd_mce_is_memory_error(struct mce *m) { return false; }; static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { } #endif -static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_amd_feature_init(c); } - unsigned long copy_mc_fragile_handle_tail(char *to, char *from, unsigned len); #endif /* _ASM_X86_MCE_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 3ae84c3b8e6d..9a71880eec07 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -608,6 +608,7 @@ #define MSR_AMD_PERF_CTL 0xc0010062 #define MSR_AMD_PERF_STATUS 0xc0010063 #define MSR_AMD_PSTATE_DEF_BASE 0xc0010064 +#define MSR_AMD64_GUEST_TSC_FREQ 0xc0010134 #define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 #define MSR_AMD64_OSVW_STATUS 0xc0010141 #define MSR_AMD_PPIN_CTL 0xc00102f0 @@ -644,6 +645,7 @@ #define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */ #define MSR_AMD64_SVM_AVIC_DOORBELL 0xc001011b #define MSR_AMD64_VM_PAGE_FLUSH 0xc001011e +#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 @@ -682,11 +684,12 @@ #define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT) #define MSR_AMD64_SNP_RESV_BIT 18 #define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT) - -#define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f - #define MSR_AMD64_RMP_BASE 0xc0010132 #define MSR_AMD64_RMP_END 0xc0010133 +#define MSR_AMD64_RMP_CFG 0xc0010136 +#define MSR_AMD64_SEG_RMP_ENABLED_BIT 0 +#define MSR_AMD64_SEG_RMP_ENABLED BIT_ULL(MSR_AMD64_SEG_RMP_ENABLED_BIT) +#define MSR_AMD64_RMP_SEGMENT_SHIFT(x) (((x) & GENMASK_ULL(13, 8)) >> 8) #define MSR_SVSM_CAA 0xc001f000 diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index 4218248083d9..c69e269937c5 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -58,8 +58,8 @@ struct mtrr_state_type { */ # ifdef CONFIG_MTRR void mtrr_bp_init(void); -void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var, - mtrr_type def_type); +void guest_force_mtrr_state(struct mtrr_var_range *var, unsigned int num_var, + mtrr_type def_type); extern u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform); extern void mtrr_save_fixed_ranges(void *); extern void mtrr_save_state(void); @@ -75,9 +75,9 @@ void mtrr_disable(void); void mtrr_enable(void); void mtrr_generic_set_state(void); # else -static inline void mtrr_overwrite_state(struct mtrr_var_range *var, - unsigned int num_var, - mtrr_type def_type) +static inline void guest_force_mtrr_state(struct mtrr_var_range *var, + unsigned int num_var, + mtrr_type def_type) { } diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 920426d691ce..ce857ef54cf1 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -15,7 +15,6 @@ #define MWAIT_HINT2SUBSTATE(hint) ((hint) & MWAIT_CSTATE_MASK) #define MWAIT_C1_SUBSTATE_MASK 0xf0 -#define CPUID_MWAIT_LEAF 5 #define CPUID5_ECX_EXTENSIONS_SUPPORTED 0x1 #define CPUID5_ECX_INTERRUPT_BREAK 0x2 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 96b410b1d4e8..7e8bf78c03d5 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -180,18 +180,6 @@ #ifdef __ASSEMBLY__ /* - * This should be used immediately before an indirect jump/call. It tells - * objtool the subsequent indirect jump/call is vouched safe for retpoline - * builds. - */ -.macro ANNOTATE_RETPOLINE_SAFE -.Lhere_\@: - .pushsection .discard.retpoline_safe - .long .Lhere_\@ - .popsection -.endm - -/* * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions * vs RETBleed validation. */ @@ -350,12 +338,6 @@ #else /* __ASSEMBLY__ */ -#define ANNOTATE_RETPOLINE_SAFE \ - "999:\n\t" \ - ".pushsection .discard.retpoline_safe\n\t" \ - ".long 999b\n\t" \ - ".popsection\n\t" - typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; extern retpoline_thunk_t __x86_indirect_thunk_array[]; extern retpoline_thunk_t __x86_indirect_call_thunk_array[]; diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index d4eb9e1d61b8..041aff51eb50 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -180,13 +180,6 @@ static inline void halt(void) PVOP_VCALL0(irq.halt); } -extern noinstr void pv_native_wbinvd(void); - -static __always_inline void wbinvd(void) -{ - PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT_XEN); -} - static inline u64 paravirt_read_msr(unsigned msr) { return PVOP_CALL1(u64, cpu.read_msr, msr); diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 8d4fbe1be489..fea56b04f436 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -86,8 +86,6 @@ struct pv_cpu_ops { void (*update_io_bitmap)(void); #endif - void (*wbinvd)(void); - /* cpuid emulation, mostly so that caps bits can be disabled */ void (*cpuid)(unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index d95f902acc52..1ac79f361645 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -41,6 +41,7 @@ #define INTEL_FIXED_0_USER (1ULL << 1) #define INTEL_FIXED_0_ANYTHREAD (1ULL << 2) #define INTEL_FIXED_0_ENABLE_PMI (1ULL << 3) +#define INTEL_FIXED_3_METRICS_CLEAR (1ULL << 2) #define HSW_IN_TX (1ULL << 32) #define HSW_IN_TX_CHECKPOINTED (1ULL << 33) @@ -372,6 +373,9 @@ static inline bool use_fixed_pseudo_encoding(u64 code) #define INTEL_TD_METRIC_MAX INTEL_TD_METRIC_MEM_BOUND #define INTEL_TD_METRIC_NUM 8 +#define INTEL_TD_CFG_METRIC_CLEAR_BIT 0 +#define INTEL_TD_CFG_METRIC_CLEAR BIT_ULL(INTEL_TD_CFG_METRIC_CLEAR_BIT) + static inline bool is_metric_idx(int idx) { return (unsigned)(idx - INTEL_PMC_IDX_METRIC_BASE) < INTEL_TD_METRIC_NUM; @@ -422,7 +426,9 @@ static inline bool is_topdown_idx(int idx) */ struct pebs_basic { - u64 format_size; + u64 format_group:32, + retire_latency:16, + format_size:16; u64 ip; u64 applicable_counters; u64 tsc; @@ -431,7 +437,17 @@ struct pebs_basic { struct pebs_meminfo { u64 address; u64 aux; - u64 latency; + union { + /* pre Alder Lake */ + u64 mem_latency; + /* Alder Lake and later */ + struct { + u64 instr_latency:16; + u64 pad2:16; + u64 cache_latency:16; + u64 pad3:16; + }; + }; u64 tsx_tuning; }; diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index c0975815980c..c0cd10182e90 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -98,6 +98,7 @@ struct cpuinfo_topology { // Logical ID mappings u32 logical_pkg_id; u32 logical_die_id; + u32 logical_core_id; // AMD Node ID and Nodes per Package info u32 amd_node_id; @@ -230,6 +231,8 @@ static inline unsigned long long l1tf_pfn_limit(void) return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT); } +void init_cpu_devs(void); +void get_cpu_vendor(struct cpuinfo_x86 *c); extern void early_cpu_init(void); extern void identify_secondary_cpu(struct cpuinfo_x86 *); extern void print_cpu_info(struct cpuinfo_x86 *); diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index 50f5666938c0..6ef92432a5ce 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -206,6 +206,7 @@ struct snp_psc_desc { #define GHCB_TERM_NO_SVSM 7 /* SVSM is not advertised in the secrets page */ #define GHCB_TERM_SVSM_VMPL0 8 /* SVSM is present but has set VMPL to 0 */ #define GHCB_TERM_SVSM_CAA 9 /* SVSM is present but CAA is not page aligned */ +#define GHCB_TERM_SECURE_TSC 10 /* Secure TSC initialization failed */ #define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK) diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 91f08af31078..5d9685f92e5c 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -14,6 +14,7 @@ #include <asm/insn.h> #include <asm/sev-common.h> #include <asm/coco.h> +#include <asm/set_memory.h> #define GHCB_PROTOCOL_MIN 1ULL #define GHCB_PROTOCOL_MAX 2ULL @@ -124,6 +125,9 @@ struct snp_req_data { #define AAD_LEN 48 #define MSG_HDR_VER 1 +#define SNP_REQ_MAX_RETRY_DURATION (60*HZ) +#define SNP_REQ_RETRY_DELAY (2*HZ) + /* See SNP spec SNP_GUEST_REQUEST section for the structure */ enum msg_type { SNP_MSG_TYPE_INVALID = 0, @@ -142,6 +146,9 @@ enum msg_type { SNP_MSG_VMRK_REQ, SNP_MSG_VMRK_RSP, + SNP_MSG_TSC_INFO_REQ = 17, + SNP_MSG_TSC_INFO_RSP, + SNP_MSG_TYPE_MAX }; @@ -170,9 +177,20 @@ struct snp_guest_msg { u8 payload[PAGE_SIZE - sizeof(struct snp_guest_msg_hdr)]; } __packed; -struct sev_guest_platform_data { - u64 secrets_gpa; -}; +#define SNP_TSC_INFO_REQ_SZ 128 + +struct snp_tsc_info_req { + u8 rsvd[SNP_TSC_INFO_REQ_SZ]; +} __packed; + +struct snp_tsc_info_resp { + u32 status; + u32 rsvd1; + u64 tsc_scale; + u64 tsc_offset; + u32 tsc_factor; + u8 rsvd2[100]; +} __packed; struct snp_guest_req { void *req_buf; @@ -253,6 +271,7 @@ struct snp_msg_desc { u32 *os_area_msg_seqno; u8 *vmpck; + int vmpck_id; }; /* @@ -445,8 +464,6 @@ void snp_set_wakeup_secondary_cpu(void); bool snp_init(struct boot_params *bp); void __noreturn snp_abort(void); void snp_dmi_setup(void); -int snp_issue_guest_request(struct snp_guest_req *req, struct snp_req_data *input, - struct snp_guest_request_ioctl *rio); int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, struct svsm_attest_call *input); void snp_accept_memory(phys_addr_t start, phys_addr_t end); u64 snp_get_unsupported_features(u64 status); @@ -458,6 +475,15 @@ void set_pte_enc_mask(pte_t *kpte, unsigned long pfn, pgprot_t new_prot); void snp_kexec_finish(void); void snp_kexec_begin(void); +int snp_msg_init(struct snp_msg_desc *mdesc, int vmpck_id); +struct snp_msg_desc *snp_msg_alloc(void); +void snp_msg_free(struct snp_msg_desc *mdesc); +int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, + struct snp_guest_request_ioctl *rio); + +void __init snp_secure_tsc_prepare(void); +void __init snp_secure_tsc_init(void); + #else /* !CONFIG_AMD_MEM_ENCRYPT */ #define snp_vmpl 0 @@ -480,11 +506,6 @@ static inline void snp_set_wakeup_secondary_cpu(void) { } static inline bool snp_init(struct boot_params *bp) { return false; } static inline void snp_abort(void) { } static inline void snp_dmi_setup(void) { } -static inline int snp_issue_guest_request(struct snp_guest_req *req, struct snp_req_data *input, - struct snp_guest_request_ioctl *rio) -{ - return -ENOTTY; -} static inline int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, struct svsm_attest_call *input) { return -ENOTTY; @@ -498,6 +519,13 @@ static inline int prepare_pte_enc(struct pte_enc_desc *d) { return 0; } static inline void set_pte_enc_mask(pte_t *kpte, unsigned long pfn, pgprot_t new_prot) { } static inline void snp_kexec_finish(void) { } static inline void snp_kexec_begin(void) { } +static inline int snp_msg_init(struct snp_msg_desc *mdesc, int vmpck_id) { return -1; } +static inline struct snp_msg_desc *snp_msg_alloc(void) { return NULL; } +static inline void snp_msg_free(struct snp_msg_desc *mdesc) { } +static inline int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, + struct snp_guest_request_ioctl *rio) { return -ENODEV; } +static inline void __init snp_secure_tsc_prepare(void) { } +static inline void __init snp_secure_tsc_init(void) { } #endif /* CONFIG_AMD_MEM_ENCRYPT */ diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index bab490379c65..2de1e5a75c57 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -13,30 +13,26 @@ #include <asm/cpufeatures.h> #include <asm/alternative.h> -/* "Raw" instruction opcodes */ -#define __ASM_CLAC ".byte 0x0f,0x01,0xca" -#define __ASM_STAC ".byte 0x0f,0x01,0xcb" - #ifdef __ASSEMBLY__ #define ASM_CLAC \ - ALTERNATIVE "", __ASM_CLAC, X86_FEATURE_SMAP + ALTERNATIVE "", "clac", X86_FEATURE_SMAP #define ASM_STAC \ - ALTERNATIVE "", __ASM_STAC, X86_FEATURE_SMAP + ALTERNATIVE "", "stac", X86_FEATURE_SMAP #else /* __ASSEMBLY__ */ static __always_inline void clac(void) { /* Note: a barrier is implicit in alternative() */ - alternative("", __ASM_CLAC, X86_FEATURE_SMAP); + alternative("", "clac", X86_FEATURE_SMAP); } static __always_inline void stac(void) { /* Note: a barrier is implicit in alternative() */ - alternative("", __ASM_STAC, X86_FEATURE_SMAP); + alternative("", "stac", X86_FEATURE_SMAP); } static __always_inline unsigned long smap_save(void) @@ -44,7 +40,7 @@ static __always_inline unsigned long smap_save(void) unsigned long flags; asm volatile ("# smap_save\n\t" - ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC "\n\t", + ALTERNATIVE("", "pushf; pop %0; " "clac" "\n\t", X86_FEATURE_SMAP) : "=rm" (flags) : : "memory", "cc"); @@ -61,9 +57,9 @@ static __always_inline void smap_restore(unsigned long flags) /* These macros can be used in asm() statements */ #define ASM_CLAC \ - ALTERNATIVE("", __ASM_CLAC, X86_FEATURE_SMAP) + ALTERNATIVE("", "clac", X86_FEATURE_SMAP) #define ASM_STAC \ - ALTERNATIVE("", __ASM_STAC, X86_FEATURE_SMAP) + ALTERNATIVE("", "stac", X86_FEATURE_SMAP) #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index aec6e2d3aa1d..03e7c2d49559 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -115,7 +115,7 @@ static inline void wrpkru(u32 pkru) } #endif -static __always_inline void native_wbinvd(void) +static __always_inline void wbinvd(void) { asm volatile("wbinvd": : :"memory"); } @@ -167,12 +167,6 @@ static inline void __write_cr4(unsigned long x) { native_write_cr4(x); } - -static __always_inline void wbinvd(void) -{ - native_wbinvd(); -} - #endif /* CONFIG_PARAVIRT_XXL */ static __always_inline void clflush(volatile void *__p) @@ -217,7 +211,7 @@ fail: #define nop() asm volatile ("nop") -static inline void serialize(void) +static __always_inline void serialize(void) { /* Instruction opcode for SERIALIZE; supported in binutils >= 2.35. */ asm volatile(".byte 0xf, 0x1, 0xe8" ::: "memory"); diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index 125c407e2abe..41502bd2afd6 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -65,4 +65,19 @@ extern bool __static_call_fixup(void *tramp, u8 op, void *dest); +extern void __static_call_update_early(void *tramp, void *func); + +#define static_call_update_early(name, _func) \ +({ \ + typeof(&STATIC_CALL_TRAMP(name)) __F = (_func); \ + if (static_call_initialized) { \ + __static_call_update(&STATIC_CALL_KEY(name), \ + STATIC_CALL_TRAMP_ADDR(name), __F);\ + } else { \ + WRITE_ONCE(STATIC_CALL_KEY(name).func, _func); \ + __static_call_update_early(STATIC_CALL_TRAMP_ADDR(name),\ + __F); \ + } \ +}) + #endif /* _ASM_STATIC_CALL_H */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 2b59b9951c90..92e18798f197 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -417,7 +417,9 @@ struct sev_es_save_area { u8 reserved_0x298[80]; u32 pkru; u32 tsc_aux; - u8 reserved_0x2f0[24]; + u64 tsc_scale; + u64 tsc_offset; + u8 reserved_0x300[8]; u64 rcx; u64 rdx; u64 rbx; @@ -564,7 +566,7 @@ static inline void __unused_size_checks(void) BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x1c0); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x248); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x298); - BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x2f0); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x300); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x320); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x380); BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x3f0); diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h index ab7382f92aff..96bda43538ee 100644 --- a/arch/x86/include/asm/sync_core.h +++ b/arch/x86/include/asm/sync_core.h @@ -8,7 +8,7 @@ #include <asm/special_insns.h> #ifdef CONFIG_X86_32 -static inline void iret_to_self(void) +static __always_inline void iret_to_self(void) { asm volatile ( "pushfl\n\t" @@ -19,7 +19,7 @@ static inline void iret_to_self(void) : ASM_CALL_CONSTRAINT : : "memory"); } #else -static inline void iret_to_self(void) +static __always_inline void iret_to_self(void) { unsigned int tmp; @@ -55,7 +55,7 @@ static inline void iret_to_self(void) * Like all of Linux's memory ordering operations, this is a * compiler barrier as well. */ -static inline void sync_core(void) +static __always_inline void sync_core(void) { /* * The SERIALIZE instruction is the most straightforward way to diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index fd41103ad342..ec134b719144 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -143,6 +143,7 @@ extern const struct cpumask *cpu_clustergroup_mask(int cpu); #define topology_logical_package_id(cpu) (cpu_data(cpu).topo.logical_pkg_id) #define topology_physical_package_id(cpu) (cpu_data(cpu).topo.pkg_id) #define topology_logical_die_id(cpu) (cpu_data(cpu).topo.logical_die_id) +#define topology_logical_core_id(cpu) (cpu_data(cpu).topo.logical_core_id) #define topology_die_id(cpu) (cpu_data(cpu).topo.die_id) #define topology_core_id(cpu) (cpu_data(cpu).topo.core_id) #define topology_ppin(cpu) (cpu_data(cpu).ppin) @@ -250,7 +251,7 @@ extern bool x86_topology_update; #include <asm/percpu.h> DECLARE_PER_CPU_READ_MOSTLY(int, sched_core_priority); -extern unsigned int __read_mostly sysctl_sched_itmt_enabled; +extern bool __read_mostly sysctl_sched_itmt_enabled; /* Interface to set priority of a cpu */ void sched_set_itmt_core_prio(int prio, int core_cpu); @@ -263,7 +264,7 @@ void sched_clear_itmt_support(void); #else /* CONFIG_SCHED_MC_PRIO */ -#define sysctl_sched_itmt_enabled 0 +#define sysctl_sched_itmt_enabled false static inline void sched_set_itmt_core_prio(int prio, int core_cpu) { } diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index b0a887209400..c52f0133425b 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -63,13 +63,13 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, */ static inline void __user *mask_user_address(const void __user *ptr) { - unsigned long mask; + void __user *ret; asm("cmp %1,%0\n\t" - "sbb %0,%0" - :"=r" (mask) - :"r" (ptr), - "0" (runtime_const_ptr(USER_PTR_MAX))); - return (__force void __user *)(mask | (__force unsigned long)ptr); + "cmova %1,%0" + :"=r" (ret) + :"r" (runtime_const_ptr(USER_PTR_MAX)), + "0" (ptr)); + return ret; } #define masked_user_access_begin(x) ({ \ __auto_type __masked_ptr = (x); \ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index a2dd24947eb8..97771b9d33af 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -39,9 +39,11 @@ #include <linux/string.h> #include <linux/types.h> #include <linux/pgtable.h> +#include <linux/instrumentation.h> #include <trace/events/xen.h> +#include <asm/alternative.h> #include <asm/page.h> #include <asm/smap.h> #include <asm/nospec-branch.h> @@ -86,11 +88,20 @@ struct xen_dm_op_buf; * there aren't more than 5 arguments...) */ -extern struct { char _entry[32]; } hypercall_page[]; +void xen_hypercall_func(void); +DECLARE_STATIC_CALL(xen_hypercall, xen_hypercall_func); -#define __HYPERCALL "call hypercall_page+%c[offset]" -#define __HYPERCALL_ENTRY(x) \ - [offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0])) +#ifdef MODULE +#define __ADDRESSABLE_xen_hypercall +#else +#define __ADDRESSABLE_xen_hypercall __ADDRESSABLE_ASM_STR(__SCK__xen_hypercall) +#endif + +#define __HYPERCALL \ + __ADDRESSABLE_xen_hypercall \ + "call __SCT__xen_hypercall" + +#define __HYPERCALL_ENTRY(x) "a" (x) #ifdef CONFIG_X86_32 #define __HYPERCALL_RETREG "eax" @@ -148,7 +159,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_0ARG(); \ asm volatile (__HYPERCALL \ : __HYPERCALL_0PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER0); \ (type)__res; \ }) @@ -159,7 +170,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_1ARG(a1); \ asm volatile (__HYPERCALL \ : __HYPERCALL_1PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER1); \ (type)__res; \ }) @@ -170,7 +181,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_2ARG(a1, a2); \ asm volatile (__HYPERCALL \ : __HYPERCALL_2PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER2); \ (type)__res; \ }) @@ -181,7 +192,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_3ARG(a1, a2, a3); \ asm volatile (__HYPERCALL \ : __HYPERCALL_3PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER3); \ (type)__res; \ }) @@ -192,7 +203,7 @@ extern struct { char _entry[32]; } hypercall_page[]; __HYPERCALL_4ARG(a1, a2, a3, a4); \ asm volatile (__HYPERCALL \ : __HYPERCALL_4PARAM \ - : __HYPERCALL_ENTRY(name) \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ : __HYPERCALL_CLOBBER4); \ (type)__res; \ }) @@ -206,12 +217,9 @@ xen_single_call(unsigned int call, __HYPERCALL_DECLS; __HYPERCALL_5ARG(a1, a2, a3, a4, a5); - if (call >= PAGE_SIZE / sizeof(hypercall_page[0])) - return -EINVAL; - - asm volatile(CALL_NOSPEC + asm volatile(__HYPERCALL : __HYPERCALL_5PARAM - : [thunk_target] "a" (&hypercall_page[call]) + : __HYPERCALL_ENTRY(call) : __HYPERCALL_CLOBBER5); return (long)__res; diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index f7918980667a..b43eb7e384eb 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -119,6 +119,7 @@ obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_HPET_TIMER) += hpet.o obj-$(CONFIG_AMD_NB) += amd_nb.o +obj-$(CONFIG_AMD_NODE) += amd_node.o obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o obj-$(CONFIG_KVM_GUEST) += kvm.o kvmclock.o diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index f3ffd0a3a012..5854f0b8f0f1 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -13,6 +13,7 @@ #include <linux/sched.h> #include <acpi/processor.h> +#include <asm/cpuid.h> #include <asm/mwait.h> #include <asm/special_insns.h> @@ -128,7 +129,7 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx) unsigned int cstate_type; /* C-state type and not ACPI C-state type */ unsigned int num_cstate_subtype; - cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx); + cpuid(CPUID_LEAF_MWAIT, &eax, &ebx, &ecx, &edx); /* Check whether this particular cx_type (in CST) is supported or not */ cstate_type = (((cx->address >> MWAIT_SUBSTATE_SIZE) & @@ -172,7 +173,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu, struct cpuinfo_x86 *c = &cpu_data(cpu); long retval; - if (!cpu_cstate_entry || c->cpuid_level < CPUID_MWAIT_LEAF) + if (!cpu_cstate_entry || c->cpuid_level < CPUID_LEAF_MWAIT) return -1; if (reg->bit_offset != NATIVE_CSTATE_BEYOND_HALT) diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 9fe9972d2071..11fac09e3a8c 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -15,66 +15,8 @@ #include <linux/pci_ids.h> #include <asm/amd_nb.h> -#define PCI_DEVICE_ID_AMD_17H_ROOT 0x1450 -#define PCI_DEVICE_ID_AMD_17H_M10H_ROOT 0x15d0 -#define PCI_DEVICE_ID_AMD_17H_M30H_ROOT 0x1480 -#define PCI_DEVICE_ID_AMD_17H_M60H_ROOT 0x1630 -#define PCI_DEVICE_ID_AMD_17H_MA0H_ROOT 0x14b5 -#define PCI_DEVICE_ID_AMD_19H_M10H_ROOT 0x14a4 -#define PCI_DEVICE_ID_AMD_19H_M40H_ROOT 0x14b5 -#define PCI_DEVICE_ID_AMD_19H_M60H_ROOT 0x14d8 -#define PCI_DEVICE_ID_AMD_19H_M70H_ROOT 0x14e8 -#define PCI_DEVICE_ID_AMD_1AH_M00H_ROOT 0x153a -#define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507 -#define PCI_DEVICE_ID_AMD_1AH_M60H_ROOT 0x1122 -#define PCI_DEVICE_ID_AMD_MI200_ROOT 0x14bb -#define PCI_DEVICE_ID_AMD_MI300_ROOT 0x14f8 - -#define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 -#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec -#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F4 0x1494 -#define PCI_DEVICE_ID_AMD_17H_M60H_DF_F4 0x144c -#define PCI_DEVICE_ID_AMD_17H_M70H_DF_F4 0x1444 -#define PCI_DEVICE_ID_AMD_17H_MA0H_DF_F4 0x1728 -#define PCI_DEVICE_ID_AMD_19H_DF_F4 0x1654 -#define PCI_DEVICE_ID_AMD_19H_M10H_DF_F4 0x14b1 -#define PCI_DEVICE_ID_AMD_19H_M40H_DF_F4 0x167d -#define PCI_DEVICE_ID_AMD_19H_M50H_DF_F4 0x166e -#define PCI_DEVICE_ID_AMD_19H_M60H_DF_F4 0x14e4 -#define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4 0x14f4 -#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc -#define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4 0x12c4 -#define PCI_DEVICE_ID_AMD_1AH_M20H_DF_F4 0x16fc -#define PCI_DEVICE_ID_AMD_1AH_M60H_DF_F4 0x124c -#define PCI_DEVICE_ID_AMD_1AH_M70H_DF_F4 0x12bc -#define PCI_DEVICE_ID_AMD_MI200_DF_F4 0x14d4 -#define PCI_DEVICE_ID_AMD_MI300_DF_F4 0x152c - -/* Protect the PCI config register pairs used for SMN. */ -static DEFINE_MUTEX(smn_mutex); - static u32 *flush_words; -static const struct pci_device_id amd_root_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_MA0H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M10H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_ROOT) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_ROOT) }, - {} -}; - -#define PCI_DEVICE_ID_AMD_CNB17H_F4 0x1704 - static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_K8_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, @@ -84,70 +26,6 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M60H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_MA0H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M10H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M70H_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F3) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_DF_F3) }, - {} -}; - -static const struct pci_device_id amd_nb_link_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M60H_NB_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_M30H_NB_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M10H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M30H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M60H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_M70H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_17H_MA0H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M10H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M70H_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F4) }, - { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_DF_F4) }, - {} -}; - -static const struct pci_device_id hygon_root_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_ROOT) }, - {} -}; - -static const struct pci_device_id hygon_nb_misc_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_DF_F3) }, - {} -}; - -static const struct pci_device_id hygon_nb_link_ids[] = { - { PCI_DEVICE(PCI_VENDOR_ID_HYGON, PCI_DEVICE_ID_AMD_17H_DF_F4) }, {} }; @@ -178,176 +56,37 @@ struct amd_northbridge *node_to_amd_nb(int node) } EXPORT_SYMBOL_GPL(node_to_amd_nb); -static struct pci_dev *next_northbridge(struct pci_dev *dev, - const struct pci_device_id *ids) -{ - do { - dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev); - if (!dev) - break; - } while (!pci_match_id(ids, dev)); - return dev; -} - -/* - * SMN accesses may fail in ways that are difficult to detect here in the called - * functions amd_smn_read() and amd_smn_write(). Therefore, callers must do - * their own checking based on what behavior they expect. - * - * For SMN reads, the returned value may be zero if the register is Read-as-Zero. - * Or it may be a "PCI Error Response", e.g. all 0xFFs. The "PCI Error Response" - * can be checked here, and a proper error code can be returned. - * - * But the Read-as-Zero response cannot be verified here. A value of 0 may be - * correct in some cases, so callers must check that this correct is for the - * register/fields they need. - * - * For SMN writes, success can be determined through a "write and read back" - * However, this is not robust when done here. - * - * Possible issues: - * - * 1) Bits that are "Write-1-to-Clear". In this case, the read value should - * *not* match the write value. - * - * 2) Bits that are "Read-as-Zero"/"Writes-Ignored". This information cannot be - * known here. - * - * 3) Bits that are "Reserved / Set to 1". Ditto above. - * - * Callers of amd_smn_write() should do the "write and read back" check - * themselves, if needed. - * - * For #1, they can see if their target bits got cleared. - * - * For #2 and #3, they can check if their target bits got set as intended. - * - * This matches what is done for RDMSR/WRMSR. As long as there's no #GP, then - * the operation is considered a success, and the caller does their own - * checking. - */ -static int __amd_smn_rw(u16 node, u32 address, u32 *value, bool write) -{ - struct pci_dev *root; - int err = -ENODEV; - - if (node >= amd_northbridges.num) - goto out; - - root = node_to_amd_nb(node)->root; - if (!root) - goto out; - - mutex_lock(&smn_mutex); - - err = pci_write_config_dword(root, 0x60, address); - if (err) { - pr_warn("Error programming SMN address 0x%x.\n", address); - goto out_unlock; - } - - err = (write ? pci_write_config_dword(root, 0x64, *value) - : pci_read_config_dword(root, 0x64, value)); - -out_unlock: - mutex_unlock(&smn_mutex); - -out: - return err; -} - -int __must_check amd_smn_read(u16 node, u32 address, u32 *value) -{ - int err = __amd_smn_rw(node, address, value, false); - - if (PCI_POSSIBLE_ERROR(*value)) { - err = -ENODEV; - *value = 0; - } - - return err; -} -EXPORT_SYMBOL_GPL(amd_smn_read); - -int __must_check amd_smn_write(u16 node, u32 address, u32 value) -{ - return __amd_smn_rw(node, address, &value, true); -} -EXPORT_SYMBOL_GPL(amd_smn_write); - - static int amd_cache_northbridges(void) { - const struct pci_device_id *misc_ids = amd_nb_misc_ids; - const struct pci_device_id *link_ids = amd_nb_link_ids; - const struct pci_device_id *root_ids = amd_root_ids; - struct pci_dev *root, *misc, *link; struct amd_northbridge *nb; - u16 roots_per_misc = 0; - u16 misc_count = 0; - u16 root_count = 0; - u16 i, j; + u16 i; if (amd_northbridges.num) return 0; - if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { - root_ids = hygon_root_ids; - misc_ids = hygon_nb_misc_ids; - link_ids = hygon_nb_link_ids; - } - - misc = NULL; - while ((misc = next_northbridge(misc, misc_ids))) - misc_count++; - - if (!misc_count) - return -ENODEV; - - root = NULL; - while ((root = next_northbridge(root, root_ids))) - root_count++; + amd_northbridges.num = amd_num_nodes(); - if (root_count) { - roots_per_misc = root_count / misc_count; - - /* - * There should be _exactly_ N roots for each DF/SMN - * interface. - */ - if (!roots_per_misc || (root_count % roots_per_misc)) { - pr_info("Unsupported AMD DF/PCI configuration found\n"); - return -ENODEV; - } - } - - nb = kcalloc(misc_count, sizeof(struct amd_northbridge), GFP_KERNEL); + nb = kcalloc(amd_northbridges.num, sizeof(struct amd_northbridge), GFP_KERNEL); if (!nb) return -ENOMEM; amd_northbridges.nb = nb; - amd_northbridges.num = misc_count; - link = misc = root = NULL; for (i = 0; i < amd_northbridges.num; i++) { - node_to_amd_nb(i)->root = root = - next_northbridge(root, root_ids); - node_to_amd_nb(i)->misc = misc = - next_northbridge(misc, misc_ids); - node_to_amd_nb(i)->link = link = - next_northbridge(link, link_ids); + node_to_amd_nb(i)->root = amd_node_get_root(i); + node_to_amd_nb(i)->misc = amd_node_get_func(i, 3); /* - * If there are more PCI root devices than data fabric/ - * system management network interfaces, then the (N) - * PCI roots per DF/SMN interface are functionally the - * same (for DF/SMN access) and N-1 are redundant. N-1 - * PCI roots should be skipped per DF/SMN interface so - * the following DF/SMN interfaces get mapped to - * correct PCI roots. + * Each Northbridge must have a 'misc' device. + * If not, then uninitialize everything. */ - for (j = 1; j < roots_per_misc; j++) - root = next_northbridge(root, root_ids); + if (!node_to_amd_nb(i)->misc) { + amd_northbridges.num = 0; + kfree(nb); + return -ENODEV; + } + + node_to_amd_nb(i)->link = amd_node_get_func(i, 4); } if (amd_gart_present()) @@ -385,7 +124,6 @@ static int amd_cache_northbridges(void) */ bool __init early_is_amd_nb(u32 device) { - const struct pci_device_id *misc_ids = amd_nb_misc_ids; const struct pci_device_id *id; u32 vendor = device & 0xffff; @@ -393,11 +131,11 @@ bool __init early_is_amd_nb(u32 device) boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) return false; - if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) - misc_ids = hygon_nb_misc_ids; + if (cpu_feature_enabled(X86_FEATURE_ZEN)) + return false; device >>= 16; - for (id = misc_ids; id->vendor; id++) + for (id = amd_nb_misc_ids; id->vendor; id++) if (vendor == id->vendor && device == id->device) return true; return false; @@ -582,6 +320,10 @@ static __init void fix_erratum_688(void) static __init int init_amd_nbs(void) { + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) + return 0; + amd_cache_northbridges(); amd_cache_gart(); diff --git a/arch/x86/kernel/amd_node.c b/arch/x86/kernel/amd_node.c new file mode 100644 index 000000000000..d2ec7fd555c5 --- /dev/null +++ b/arch/x86/kernel/amd_node.c @@ -0,0 +1,215 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * AMD Node helper functions and common defines + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam <Yazen.Ghannam@amd.com> + */ + +#include <asm/amd_node.h> + +/* + * AMD Nodes are a physical collection of I/O devices within an SoC. There can be one + * or more nodes per package. + * + * The nodes are software-visible through PCI config space. All nodes are enumerated + * on segment 0 bus 0. The device (slot) numbers range from 0x18 to 0x1F (maximum 8 + * nodes) with 0x18 corresponding to node 0, 0x19 to node 1, etc. Each node can be a + * multi-function device. + * + * On legacy systems, these node devices represent integrated Northbridge functionality. + * On Zen-based systems, these node devices represent Data Fabric functionality. + * + * See "Configuration Space Accesses" section in BKDGs or + * "Processor x86 Core" -> "Configuration Space" section in PPRs. + */ +struct pci_dev *amd_node_get_func(u16 node, u8 func) +{ + if (node >= MAX_AMD_NUM_NODES) + return NULL; + + return pci_get_domain_bus_and_slot(0, 0, PCI_DEVFN(AMD_NODE0_PCI_SLOT + node, func)); +} + +#define DF_BLK_INST_CNT 0x040 +#define DF_CFG_ADDR_CNTL_LEGACY 0x084 +#define DF_CFG_ADDR_CNTL_DF4 0xC04 + +#define DF_MAJOR_REVISION GENMASK(27, 24) + +static u16 get_cfg_addr_cntl_offset(struct pci_dev *df_f0) +{ + u32 reg; + + /* + * Revision fields added for DF4 and later. + * + * Major revision of '0' is found pre-DF4. Field is Read-as-Zero. + */ + if (pci_read_config_dword(df_f0, DF_BLK_INST_CNT, ®)) + return 0; + + if (reg & DF_MAJOR_REVISION) + return DF_CFG_ADDR_CNTL_DF4; + + return DF_CFG_ADDR_CNTL_LEGACY; +} + +struct pci_dev *amd_node_get_root(u16 node) +{ + struct pci_dev *root; + u16 cntl_off; + u8 bus; + + if (!cpu_feature_enabled(X86_FEATURE_ZEN)) + return NULL; + + /* + * D18F0xXXX [Config Address Control] (DF::CfgAddressCntl) + * Bits [7:0] (SecBusNum) holds the bus number of the root device for + * this Data Fabric instance. The segment, device, and function will be 0. + */ + struct pci_dev *df_f0 __free(pci_dev_put) = amd_node_get_func(node, 0); + if (!df_f0) + return NULL; + + cntl_off = get_cfg_addr_cntl_offset(df_f0); + if (!cntl_off) + return NULL; + + if (pci_read_config_byte(df_f0, cntl_off, &bus)) + return NULL; + + /* Grab the pointer for the actual root device instance. */ + root = pci_get_domain_bus_and_slot(0, bus, 0); + + pci_dbg(root, "is root for AMD node %u\n", node); + return root; +} + +static struct pci_dev **amd_roots; + +/* Protect the PCI config register pairs used for SMN. */ +static DEFINE_MUTEX(smn_mutex); + +#define SMN_INDEX_OFFSET 0x60 +#define SMN_DATA_OFFSET 0x64 + +/* + * SMN accesses may fail in ways that are difficult to detect here in the called + * functions amd_smn_read() and amd_smn_write(). Therefore, callers must do + * their own checking based on what behavior they expect. + * + * For SMN reads, the returned value may be zero if the register is Read-as-Zero. + * Or it may be a "PCI Error Response", e.g. all 0xFFs. The "PCI Error Response" + * can be checked here, and a proper error code can be returned. + * + * But the Read-as-Zero response cannot be verified here. A value of 0 may be + * correct in some cases, so callers must check that this correct is for the + * register/fields they need. + * + * For SMN writes, success can be determined through a "write and read back" + * However, this is not robust when done here. + * + * Possible issues: + * + * 1) Bits that are "Write-1-to-Clear". In this case, the read value should + * *not* match the write value. + * + * 2) Bits that are "Read-as-Zero"/"Writes-Ignored". This information cannot be + * known here. + * + * 3) Bits that are "Reserved / Set to 1". Ditto above. + * + * Callers of amd_smn_write() should do the "write and read back" check + * themselves, if needed. + * + * For #1, they can see if their target bits got cleared. + * + * For #2 and #3, they can check if their target bits got set as intended. + * + * This matches what is done for RDMSR/WRMSR. As long as there's no #GP, then + * the operation is considered a success, and the caller does their own + * checking. + */ +static int __amd_smn_rw(u8 i_off, u8 d_off, u16 node, u32 address, u32 *value, bool write) +{ + struct pci_dev *root; + int err = -ENODEV; + + if (node >= amd_num_nodes()) + return err; + + root = amd_roots[node]; + if (!root) + return err; + + guard(mutex)(&smn_mutex); + + err = pci_write_config_dword(root, i_off, address); + if (err) { + pr_warn("Error programming SMN address 0x%x.\n", address); + return pcibios_err_to_errno(err); + } + + err = (write ? pci_write_config_dword(root, d_off, *value) + : pci_read_config_dword(root, d_off, value)); + + return pcibios_err_to_errno(err); +} + +int __must_check amd_smn_read(u16 node, u32 address, u32 *value) +{ + int err = __amd_smn_rw(SMN_INDEX_OFFSET, SMN_DATA_OFFSET, node, address, value, false); + + if (PCI_POSSIBLE_ERROR(*value)) { + err = -ENODEV; + *value = 0; + } + + return err; +} +EXPORT_SYMBOL_GPL(amd_smn_read); + +int __must_check amd_smn_write(u16 node, u32 address, u32 value) +{ + return __amd_smn_rw(SMN_INDEX_OFFSET, SMN_DATA_OFFSET, node, address, &value, true); +} +EXPORT_SYMBOL_GPL(amd_smn_write); + +static int amd_cache_roots(void) +{ + u16 node, num_nodes = amd_num_nodes(); + + amd_roots = kcalloc(num_nodes, sizeof(*amd_roots), GFP_KERNEL); + if (!amd_roots) + return -ENOMEM; + + for (node = 0; node < num_nodes; node++) + amd_roots[node] = amd_node_get_root(node); + + return 0; +} + +static int __init amd_smn_init(void) +{ + int err; + + if (!cpu_feature_enabled(X86_FEATURE_ZEN)) + return 0; + + guard(mutex)(&smn_mutex); + + if (amd_roots) + return 0; + + err = amd_cache_roots(); + if (err) + return err; + + return 0; +} + +fs_initcall(amd_smn_init); diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index c5fb28e6451a..e893dc6f11c1 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -509,19 +509,19 @@ static struct clock_event_device lapic_clockevent = { static DEFINE_PER_CPU(struct clock_event_device, lapic_events); static const struct x86_cpu_id deadline_match[] __initconst = { - X86_MATCH_VFM_STEPPINGS(INTEL_HASWELL_X, X86_STEPPINGS(0x2, 0x2), 0x3a), /* EP */ - X86_MATCH_VFM_STEPPINGS(INTEL_HASWELL_X, X86_STEPPINGS(0x4, 0x4), 0x0f), /* EX */ + X86_MATCH_VFM_STEPS(INTEL_HASWELL_X, 0x2, 0x2, 0x3a), /* EP */ + X86_MATCH_VFM_STEPS(INTEL_HASWELL_X, 0x4, 0x4, 0x0f), /* EX */ X86_MATCH_VFM(INTEL_BROADWELL_X, 0x0b000020), - X86_MATCH_VFM_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPINGS(0x2, 0x2), 0x00000011), - X86_MATCH_VFM_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPINGS(0x3, 0x3), 0x0700000e), - X86_MATCH_VFM_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPINGS(0x4, 0x4), 0x0f00000c), - X86_MATCH_VFM_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPINGS(0x5, 0x5), 0x0e000003), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D, 0x2, 0x2, 0x00000011), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D, 0x3, 0x3, 0x0700000e), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D, 0x4, 0x4, 0x0f00000c), + X86_MATCH_VFM_STEPS(INTEL_BROADWELL_D, 0x5, 0x5, 0x0e000003), - X86_MATCH_VFM_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPINGS(0x3, 0x3), 0x01000136), - X86_MATCH_VFM_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPINGS(0x4, 0x4), 0x02000014), - X86_MATCH_VFM_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPINGS(0x5, 0xf), 0), + X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_X, 0x3, 0x3, 0x01000136), + X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_X, 0x4, 0x4, 0x02000014), + X86_MATCH_VFM_STEPS(INTEL_SKYLAKE_X, 0x5, 0xf, 0), X86_MATCH_VFM(INTEL_HASWELL, 0x22), X86_MATCH_VFM(INTEL_HASWELL_L, 0x20), @@ -2582,19 +2582,12 @@ int apic_is_clustered_box(void) /* * APIC command line parameters */ -static int __init setup_disableapic(char *arg) +static int __init setup_nolapic(char *arg) { apic_is_disabled = true; setup_clear_cpu_cap(X86_FEATURE_APIC); return 0; } -early_param("disableapic", setup_disableapic); - -/* same as disableapic, for compatibility */ -static int __init setup_nolapic(char *arg) -{ - return setup_disableapic(arg); -} early_param("nolapic", setup_nolapic); static int __init parse_lapic_timer_c2_ok(char *arg) diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 1029ea4ac8ba..17af7ced2c73 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1165,7 +1165,7 @@ static void io_apic_print_entries(unsigned int apic, unsigned int nr_entries) (entry.ir_index_15 << 15) | entry.ir_index_0_14, entry.ir_zero); } else { apic_dbg("%s, %s, D(%02X%02X), M(%1d)\n", buf, - entry.dest_mode_logical ? "logical " : "physic al", + entry.dest_mode_logical ? "logical " : "physical", entry.virt_destid_8_14, entry.destid_0_7, entry.delivery_mode); } } @@ -1861,7 +1861,7 @@ static struct irq_chip ioapic_chip __read_mostly = { .irq_set_affinity = ioapic_set_affinity, .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_get_irqchip_state = ioapic_irq_get_chip_state, - .flags = IRQCHIP_SKIP_SET_WAKE | + .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MOVE_DEFERRED | IRQCHIP_AFFINITY_PRE_STARTUP, }; diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 340769242dea..66bc5d3e79db 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -214,6 +214,7 @@ static bool x86_init_dev_msi_info(struct device *dev, struct irq_domain *domain, if (WARN_ON_ONCE(domain != real_parent)) return false; info->chip->irq_set_affinity = msi_set_affinity; + info->chip->flags |= IRQCHIP_MOVE_DEFERRED; break; case DOMAIN_BUS_DMAR: case DOMAIN_BUS_AMDVI: @@ -315,7 +316,7 @@ static struct irq_chip dmar_msi_controller = { .irq_retrigger = irq_chip_retrigger_hierarchy, .irq_compose_msi_msg = dmar_msi_compose_msg, .irq_write_msi_msg = dmar_msi_write_msg, - .flags = IRQCHIP_SKIP_SET_WAKE | + .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MOVE_DEFERRED | IRQCHIP_AFFINITY_PRE_STARTUP, }; diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index 465647456753..f17d16607882 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -143,11 +143,6 @@ static bool skip_addr(void *dest) dest < (void*)relocate_kernel + KEXEC_CONTROL_CODE_MAX_SIZE) return true; #endif -#ifdef CONFIG_XEN - if (dest >= (void *)hypercall_page && - dest < (void*)hypercall_page + PAGE_SIZE) - return true; -#endif return false; } diff --git a/arch/x86/kernel/cet.c b/arch/x86/kernel/cet.c index d2c732a34e5d..303bf74d175b 100644 --- a/arch/x86/kernel/cet.c +++ b/arch/x86/kernel/cet.c @@ -81,6 +81,34 @@ static void do_user_cp_fault(struct pt_regs *regs, unsigned long error_code) static __ro_after_init bool ibt_fatal = true; +/* + * By definition, all missing-ENDBRANCH #CPs are a result of WFE && !ENDBR. + * + * For the kernel IBT no ENDBR selftest where #CPs are deliberately triggered, + * the WFE state of the interrupted context needs to be cleared to let execution + * continue. Otherwise when the CPU resumes from the instruction that just + * caused the previous #CP, another missing-ENDBRANCH #CP is raised and the CPU + * enters a dead loop. + * + * This is not a problem with IDT because it doesn't preserve WFE and IRET doesn't + * set WFE. But FRED provides space on the entry stack (in an expanded CS area) + * to save and restore the WFE state, thus the WFE state is no longer clobbered, + * so software must clear it. + */ +static void ibt_clear_fred_wfe(struct pt_regs *regs) +{ + /* + * No need to do any FRED checks. + * + * For IDT event delivery, the high-order 48 bits of CS are pushed + * as 0s into the stack, and later IRET ignores these bits. + * + * For FRED, a test to check if fred_cs.wfe is set would be dropped + * by compilers. + */ + regs->fred_cs.wfe = 0; +} + static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) { if ((error_code & CP_EC) != CP_ENDBR) { @@ -90,6 +118,7 @@ static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) if (unlikely(regs->ip == (unsigned long)&ibt_selftest_noendbr)) { regs->ax = 0; + ibt_clear_fred_wfe(regs); return; } @@ -97,6 +126,7 @@ static void do_kernel_cp_fault(struct pt_regs *regs, unsigned long error_code) if (!ibt_fatal) { printk(KERN_DEFAULT CUT_HERE); __warn(__FILE__, __LINE__, (void *)regs->ip, TAINT_WARN, regs, NULL); + ibt_clear_fred_wfe(regs); return; } BUG(); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 79d2e17f6582..54194f5995de 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -355,10 +355,15 @@ static void bsp_determine_snp(struct cpuinfo_x86 *c) /* * RMP table entry format is not architectural and is defined by the * per-processor PPR. Restrict SNP support on the known CPU models - * for which the RMP table entry format is currently defined for. + * for which the RMP table entry format is currently defined or for + * processors which support the architecturally defined RMPREAD + * instruction. */ if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && - c->x86 >= 0x19 && snp_probe_rmptable_info()) { + (cpu_feature_enabled(X86_FEATURE_ZEN3) || + cpu_feature_enabled(X86_FEATURE_ZEN4) || + cpu_feature_enabled(X86_FEATURE_RMPREAD)) && + snp_probe_rmptable_info()) { cc_platform_set(CC_ATTR_HOST_SEV_SNP); } else { setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); @@ -795,10 +800,9 @@ static void init_amd_bd(struct cpuinfo_x86 *c) clear_rdrand_cpuid_bit(c); } -static const struct x86_cpu_desc erratum_1386_microcode[] = { - AMD_CPU_DESC(0x17, 0x1, 0x2, 0x0800126e), - AMD_CPU_DESC(0x17, 0x31, 0x0, 0x08301052), - {}, +static const struct x86_cpu_id erratum_1386_microcode[] = { + X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, 0x17, 0x01), 0x2, 0x2, 0x0800126e), + X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, 0x17, 0x31), 0x0, 0x0, 0x08301052), }; static void fix_erratum_1386(struct cpuinfo_x86 *c) @@ -814,7 +818,7 @@ static void fix_erratum_1386(struct cpuinfo_x86 *c) * Clear the feature flag only on microcode revisions which * don't have the fix. */ - if (x86_cpu_has_min_microcode_rev(erratum_1386_microcode)) + if (x86_match_min_microcode_rev(erratum_1386_microcode)) return; clear_cpu_cap(c, X86_FEATURE_XSAVES); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 47a01d4028f6..5a505aa65489 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -2615,6 +2615,9 @@ static void __init srso_select_mitigation(void) break; case SRSO_CMD_SAFE_RET: + if (boot_cpu_has(X86_FEATURE_SRSO_USER_KERNEL_NO)) + goto ibpb_on_vmexit; + if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) { /* * Enable the return thunk for generated code @@ -2658,6 +2661,7 @@ static void __init srso_select_mitigation(void) } break; +ibpb_on_vmexit: case SRSO_CMD_IBPB_ON_VMEXIT: if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) { if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index a5c28975c608..7cce91b19fb2 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -29,6 +29,7 @@ #include <asm/alternative.h> #include <asm/cmdline.h> +#include <asm/cpuid.h> #include <asm/perf_event.h> #include <asm/mmu_context.h> #include <asm/doublefault.h> @@ -636,9 +637,9 @@ struct cpuid_dependent_feature { static const struct cpuid_dependent_feature cpuid_dependent_features[] = { - { X86_FEATURE_MWAIT, 0x00000005 }, - { X86_FEATURE_DCA, 0x00000009 }, - { X86_FEATURE_XSAVE, 0x0000000d }, + { X86_FEATURE_MWAIT, CPUID_LEAF_MWAIT }, + { X86_FEATURE_DCA, CPUID_LEAF_DCA }, + { X86_FEATURE_XSAVE, CPUID_LEAF_XSTATE }, { 0, 0 } }; @@ -867,7 +868,7 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c) tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]); } -static void get_cpu_vendor(struct cpuinfo_x86 *c) +void get_cpu_vendor(struct cpuinfo_x86 *c) { char *v = c->x86_vendor_id; int i; @@ -1201,8 +1202,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define VULNBL(vendor, family, model, blacklist) \ X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, blacklist) -#define VULNBL_INTEL_STEPPINGS(vfm, steppings, issues) \ - X86_MATCH_VFM_STEPPINGS(vfm, steppings, issues) +#define VULNBL_INTEL_STEPS(vfm, max_stepping, issues) \ + X86_MATCH_VFM_STEPS(vfm, X86_STEP_MIN, max_stepping, issues) #define VULNBL_AMD(family, blacklist) \ VULNBL(AMD, family, X86_MODEL_ANY, blacklist) @@ -1227,49 +1228,50 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define RFDS BIT(7) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { - VULNBL_INTEL_STEPPINGS(INTEL_IVYBRIDGE, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_HASWELL, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_HASWELL_L, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_HASWELL_G, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_HASWELL_X, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL_D, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL_G, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL_X, X86_STEPPING_ANY, MMIO), - VULNBL_INTEL_STEPPINGS(INTEL_BROADWELL, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(INTEL_SKYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_SKYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_KABYLAKE_L, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_KABYLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPPINGS(INTEL_CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED), - VULNBL_INTEL_STEPPINGS(INTEL_ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(INTEL_ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS), - VULNBL_INTEL_STEPPINGS(INTEL_ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS), - VULNBL_INTEL_STEPPINGS(INTEL_COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(INTEL_COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED), - VULNBL_INTEL_STEPPINGS(INTEL_COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(INTEL_TIGERLAKE_L, X86_STEPPING_ANY, GDS), - VULNBL_INTEL_STEPPINGS(INTEL_TIGERLAKE, X86_STEPPING_ANY, GDS), - VULNBL_INTEL_STEPPINGS(INTEL_LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPPINGS(INTEL_ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS), - VULNBL_INTEL_STEPPINGS(INTEL_ALDERLAKE, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_ALDERLAKE_L, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_RAPTORLAKE, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_RAPTORLAKE_P, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_RAPTORLAKE_S, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GRACEMONT, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO | RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GOLDMONT, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GOLDMONT_D, X86_STEPPING_ANY, RFDS), - VULNBL_INTEL_STEPPINGS(INTEL_ATOM_GOLDMONT_PLUS, X86_STEPPING_ANY, RFDS), + VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS), + VULNBL_INTEL_STEPS(INTEL_HASWELL, X86_STEP_MAX, SRBDS), + VULNBL_INTEL_STEPS(INTEL_HASWELL_L, X86_STEP_MAX, SRBDS), + VULNBL_INTEL_STEPS(INTEL_HASWELL_G, X86_STEP_MAX, SRBDS), + VULNBL_INTEL_STEPS(INTEL_HASWELL_X, X86_STEP_MAX, MMIO), + VULNBL_INTEL_STEPS(INTEL_BROADWELL_D, X86_STEP_MAX, MMIO), + VULNBL_INTEL_STEPS(INTEL_BROADWELL_G, X86_STEP_MAX, SRBDS), + VULNBL_INTEL_STEPS(INTEL_BROADWELL_X, X86_STEP_MAX, MMIO), + VULNBL_INTEL_STEPS(INTEL_BROADWELL, X86_STEP_MAX, SRBDS), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L, X86_STEP_MAX, RETBLEED), + VULNBL_INTEL_STEPS(INTEL_ICELAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_ICELAKE_D, X86_STEP_MAX, MMIO | GDS), + VULNBL_INTEL_STEPS(INTEL_ICELAKE_X, X86_STEP_MAX, MMIO | GDS), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L, X86_STEP_MAX, GDS), + VULNBL_INTEL_STEPS(INTEL_TIGERLAKE, X86_STEP_MAX, GDS), + VULNBL_INTEL_STEPS(INTEL_LAKEFIELD, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_ALDERLAKE, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_P, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_RAPTORLAKE_S, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_ATOM_GRACEMONT, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT, X86_STEP_MAX, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT_D, X86_STEP_MAX, MMIO | RFDS), + VULNBL_INTEL_STEPS(INTEL_ATOM_TREMONT_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RFDS), + VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT_D, X86_STEP_MAX, RFDS), + VULNBL_INTEL_STEPS(INTEL_ATOM_GOLDMONT_PLUS, X86_STEP_MAX, RFDS), VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO), VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO), VULNBL_AMD(0x19, SRSO), + VULNBL_AMD(0x1a, SRSO), {} }; @@ -1649,15 +1651,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) detect_nopl(); } -void __init early_cpu_init(void) +void __init init_cpu_devs(void) { const struct cpu_dev *const *cdev; int count = 0; -#ifdef CONFIG_PROCESSOR_SELECT - pr_info("KERNEL supported cpus:\n"); -#endif - for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) { const struct cpu_dev *cpudev = *cdev; @@ -1665,20 +1663,30 @@ void __init early_cpu_init(void) break; cpu_devs[count] = cpudev; count++; + } +} +void __init early_cpu_init(void) +{ #ifdef CONFIG_PROCESSOR_SELECT - { - unsigned int j; - - for (j = 0; j < 2; j++) { - if (!cpudev->c_ident[j]) - continue; - pr_info(" %s %s\n", cpudev->c_vendor, - cpudev->c_ident[j]); - } - } + unsigned int i, j; + + pr_info("KERNEL supported cpus:\n"); #endif + + init_cpu_devs(); + +#ifdef CONFIG_PROCESSOR_SELECT + for (i = 0; i < X86_VENDOR_NUM && cpu_devs[i]; i++) { + for (j = 0; j < 2; j++) { + if (!cpu_devs[i]->c_ident[j]) + continue; + pr_info(" %s %s\n", cpu_devs[i]->c_vendor, + cpu_devs[i]->c_ident[j]); + } } +#endif + early_identify_cpu(&boot_cpu_data); } diff --git a/arch/x86/kernel/cpu/debugfs.c b/arch/x86/kernel/cpu/debugfs.c index 10719aba6276..cacfd3f6abef 100644 --- a/arch/x86/kernel/cpu/debugfs.c +++ b/arch/x86/kernel/cpu/debugfs.c @@ -25,6 +25,7 @@ static int cpu_debug_show(struct seq_file *m, void *p) seq_printf(m, "cpu_type: %s\n", get_topology_cpu_type_name(c)); seq_printf(m, "logical_pkg_id: %u\n", c->topo.logical_pkg_id); seq_printf(m, "logical_die_id: %u\n", c->topo.logical_die_id); + seq_printf(m, "logical_core_id: %u\n", c->topo.logical_core_id); seq_printf(m, "llc_id: %u\n", c->topo.llc_id); seq_printf(m, "l2c_id: %u\n", c->topo.l2c_id); seq_printf(m, "amd_node_id: %u\n", c->topo.amd_node_id); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 8ded9f859a3a..3dce22f00dc3 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -599,11 +599,6 @@ static void init_intel(struct cpuinfo_x86 *c) if (p) strcpy(c->x86_model_id, p); } - - if (c->x86 == 15) - set_cpu_cap(c, X86_FEATURE_P4); - if (c->x86 == 6) - set_cpu_cap(c, X86_FEATURE_P3); #endif /* Work around errata */ diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index 8e7de733320a..4f3c65429f82 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -6,7 +6,7 @@ #include <linux/slab.h> /** - * x86_match_cpu - match current CPU again an array of x86_cpu_ids + * x86_match_cpu - match current CPU against an array of x86_cpu_ids * @match: Pointer to array of x86_cpu_ids. Last entry terminated with * {}. * @@ -56,33 +56,13 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match) } EXPORT_SYMBOL(x86_match_cpu); -static const struct x86_cpu_desc * -x86_match_cpu_with_stepping(const struct x86_cpu_desc *match) +bool x86_match_min_microcode_rev(const struct x86_cpu_id *table) { - struct cpuinfo_x86 *c = &boot_cpu_data; - const struct x86_cpu_desc *m; - - for (m = match; m->x86_family | m->x86_model; m++) { - if (c->x86_vendor != m->x86_vendor) - continue; - if (c->x86 != m->x86_family) - continue; - if (c->x86_model != m->x86_model) - continue; - if (c->x86_stepping != m->x86_stepping) - continue; - return m; - } - return NULL; -} - -bool x86_cpu_has_min_microcode_rev(const struct x86_cpu_desc *table) -{ - const struct x86_cpu_desc *res = x86_match_cpu_with_stepping(table); + const struct x86_cpu_id *res = x86_match_cpu(table); - if (!res || res->x86_microcode_rev > boot_cpu_data.microcode) + if (!res || res->driver_data > boot_cpu_data.microcode) return false; return true; } -EXPORT_SYMBOL_GPL(x86_cpu_has_min_microcode_rev); +EXPORT_SYMBOL_GPL(x86_match_min_microcode_rev); diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 6ca80fff1fea..1075a90141da 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -4,8 +4,6 @@ * * Written by Jacob Shin - AMD, Inc. * Maintained by: Borislav Petkov <bp@alien8.de> - * - * All MC4_MISCi registers are shared between cores on a node. */ #include <linux/interrupt.h> #include <linux/notifier.h> @@ -20,7 +18,6 @@ #include <linux/smp.h> #include <linux/string.h> -#include <asm/amd_nb.h> #include <asm/traps.h> #include <asm/apic.h> #include <asm/mce.h> @@ -221,6 +218,32 @@ static const struct smca_hwid smca_hwid_mcatypes[] = { #define MAX_MCATYPE_NAME_LEN 30 static char buf_mcatype[MAX_MCATYPE_NAME_LEN]; +struct threshold_block { + /* This block's number within its bank. */ + unsigned int block; + /* MCA bank number that contains this block. */ + unsigned int bank; + /* CPU which controls this block's MCA bank. */ + unsigned int cpu; + /* MCA_MISC MSR address for this block. */ + u32 address; + /* Enable/Disable APIC interrupt. */ + bool interrupt_enable; + /* Bank can generate an interrupt. */ + bool interrupt_capable; + /* Value upon which threshold interrupt is generated. */ + u16 threshold_limit; + /* sysfs object */ + struct kobject kobj; + /* List of threshold blocks within this block's MCA bank. */ + struct list_head miscj; +}; + +struct threshold_bank { + struct kobject *kobj; + struct threshold_block *blocks; +}; + static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks); /* @@ -333,19 +356,6 @@ struct thresh_restart { u16 old_limit; }; -static inline bool is_shared_bank(int bank) -{ - /* - * Scalable MCA provides for only one core to have access to the MSRs of - * a shared bank. - */ - if (mce_flags.smca) - return false; - - /* Bank 4 is for northbridge reporting and is thus shared */ - return (bank == 4); -} - static const char *bank4_names(const struct threshold_block *b) { switch (b->address) { @@ -381,7 +391,7 @@ static bool lvt_interrupt_supported(unsigned int bank, u32 msr_high_bits) return msr_high_bits & BIT(28); } -static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) +static bool lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) { int msr = (hi & MASK_LVTOFF_HI) >> 20; @@ -389,7 +399,7 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) pr_err(FW_BUG "cpu %d, failed to setup threshold interrupt " "for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu, b->bank, b->block, b->address, hi, lo); - return 0; + return false; } if (apic != msr) { @@ -399,15 +409,15 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) * was set is reserved. Return early here: */ if (mce_flags.smca) - return 0; + return false; pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d " "for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu, apic, b->bank, b->block, b->address, hi, lo); - return 0; + return false; } - return 1; + return true; }; /* Reprogram MCx_MISC MSR behind this threshold bank. */ @@ -1198,35 +1208,10 @@ out_free: return err; } -static int __threshold_add_blocks(struct threshold_bank *b) -{ - struct list_head *head = &b->blocks->miscj; - struct threshold_block *pos = NULL; - struct threshold_block *tmp = NULL; - int err = 0; - - err = kobject_add(&b->blocks->kobj, b->kobj, b->blocks->kobj.name); - if (err) - return err; - - list_for_each_entry_safe(pos, tmp, head, miscj) { - - err = kobject_add(&pos->kobj, b->kobj, pos->kobj.name); - if (err) { - list_for_each_entry_safe_reverse(pos, tmp, head, miscj) - kobject_del(&pos->kobj); - - return err; - } - } - return err; -} - static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, unsigned int bank) { struct device *dev = this_cpu_read(mce_device); - struct amd_northbridge *nb = NULL; struct threshold_bank *b = NULL; const char *name = get_name(cpu, bank, NULL); int err = 0; @@ -1234,26 +1219,6 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, if (!dev) return -ENODEV; - if (is_shared_bank(bank)) { - nb = node_to_amd_nb(topology_amd_node_id(cpu)); - - /* threshold descriptor already initialized on this node? */ - if (nb && nb->bank4) { - /* yes, use it */ - b = nb->bank4; - err = kobject_add(b->kobj, &dev->kobj, name); - if (err) - goto out; - - bp[bank] = b; - refcount_inc(&b->cpus); - - err = __threshold_add_blocks(b); - - goto out; - } - } - b = kzalloc(sizeof(struct threshold_bank), GFP_KERNEL); if (!b) { err = -ENOMEM; @@ -1267,17 +1232,6 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, goto out_free; } - if (is_shared_bank(bank)) { - b->shared = 1; - refcount_set(&b->cpus, 1); - - /* nb is already initialized, see above */ - if (nb) { - WARN_ON(nb->bank4); - nb->bank4 = b; - } - } - err = allocate_threshold_blocks(cpu, b, bank, 0, mca_msr_reg(bank, MCA_MISC)); if (err) goto out_kobj; @@ -1310,40 +1264,11 @@ static void deallocate_threshold_blocks(struct threshold_bank *bank) kobject_put(&bank->blocks->kobj); } -static void __threshold_remove_blocks(struct threshold_bank *b) -{ - struct threshold_block *pos = NULL; - struct threshold_block *tmp = NULL; - - kobject_put(b->kobj); - - list_for_each_entry_safe(pos, tmp, &b->blocks->miscj, miscj) - kobject_put(b->kobj); -} - static void threshold_remove_bank(struct threshold_bank *bank) { - struct amd_northbridge *nb; - if (!bank->blocks) goto out_free; - if (!bank->shared) - goto out_dealloc; - - if (!refcount_dec_and_test(&bank->cpus)) { - __threshold_remove_blocks(bank); - return; - } else { - /* - * The last CPU on this node using the shared bank is going - * away, remove that bank now. - */ - nb = node_to_amd_nb(topology_amd_node_id(smp_processor_id())); - nb->bank4 = NULL; - } - -out_dealloc: deallocate_threshold_blocks(bank); out_free: diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 7fb5556a0b53..0dc00c9894c7 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -151,7 +151,7 @@ EXPORT_PER_CPU_SYMBOL_GPL(injectm); void mce_log(struct mce_hw_err *err) { - if (!mce_gen_pool_add(err)) + if (mce_gen_pool_add(err)) irq_work_queue(&mce_irq_work); } EXPORT_SYMBOL_GPL(mce_log); @@ -492,10 +492,10 @@ static noinstr void mce_gather_info(struct mce_hw_err *err, struct pt_regs *regs } } -int mce_available(struct cpuinfo_x86 *c) +bool mce_available(struct cpuinfo_x86 *c) { if (mca_cfg.disabled) - return 0; + return false; return cpu_has(c, X86_FEATURE_MCE) && cpu_has(c, X86_FEATURE_MCA); } @@ -1778,7 +1778,7 @@ static void mce_timer_delete_all(void) * Can be called from interrupt context, but not from machine check/NMI * context. */ -int mce_notify_irq(void) +bool mce_notify_irq(void) { /* Not more than two messages every minute */ static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); @@ -1789,9 +1789,9 @@ int mce_notify_irq(void) if (__ratelimit(&ratelimit)) pr_info(HW_ERR "Machine check events logged\n"); - return 1; + return true; } - return 0; + return false; } EXPORT_SYMBOL_GPL(mce_notify_irq); @@ -1910,101 +1910,120 @@ static void __mcheck_cpu_check_banks(void) } } -/* Add per CPU specific workarounds here */ -static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) +static void apply_quirks_amd(struct cpuinfo_x86 *c) { struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); - struct mca_config *cfg = &mca_cfg; - - if (c->x86_vendor == X86_VENDOR_UNKNOWN) { - pr_info("unknown CPU type - not enabling MCE support\n"); - return -EOPNOTSUPP; - } /* This should be disabled by the BIOS, but isn't always */ - if (c->x86_vendor == X86_VENDOR_AMD) { - if (c->x86 == 15 && this_cpu_read(mce_num_banks) > 4) { - /* - * disable GART TBL walk error reporting, which - * trips off incorrectly with the IOMMU & 3ware - * & Cerberus: - */ - clear_bit(10, (unsigned long *)&mce_banks[4].ctl); - } - if (c->x86 < 0x11 && cfg->bootlog < 0) { - /* - * Lots of broken BIOS around that don't clear them - * by default and leave crap in there. Don't log: - */ - cfg->bootlog = 0; - } + if (c->x86 == 15 && this_cpu_read(mce_num_banks) > 4) { /* - * Various K7s with broken bank 0 around. Always disable - * by default. + * disable GART TBL walk error reporting, which + * trips off incorrectly with the IOMMU & 3ware + * & Cerberus: */ - if (c->x86 == 6 && this_cpu_read(mce_num_banks) > 0) - mce_banks[0].ctl = 0; + clear_bit(10, (unsigned long *)&mce_banks[4].ctl); + } + if (c->x86 < 0x11 && mca_cfg.bootlog < 0) { /* - * overflow_recov is supported for F15h Models 00h-0fh - * even though we don't have a CPUID bit for it. + * Lots of broken BIOS around that don't clear them + * by default and leave crap in there. Don't log: */ - if (c->x86 == 0x15 && c->x86_model <= 0xf) - mce_flags.overflow_recov = 1; + mca_cfg.bootlog = 0; + } - if (c->x86 >= 0x17 && c->x86 <= 0x1A) - mce_flags.zen_ifu_quirk = 1; + /* + * Various K7s with broken bank 0 around. Always disable + * by default. + */ + if (c->x86 == 6 && this_cpu_read(mce_num_banks)) + mce_banks[0].ctl = 0; - } + /* + * overflow_recov is supported for F15h Models 00h-0fh + * even though we don't have a CPUID bit for it. + */ + if (c->x86 == 0x15 && c->x86_model <= 0xf) + mce_flags.overflow_recov = 1; - if (c->x86_vendor == X86_VENDOR_INTEL) { - /* - * SDM documents that on family 6 bank 0 should not be written - * because it aliases to another special BIOS controlled - * register. - * But it's not aliased anymore on model 0x1a+ - * Don't ignore bank 0 completely because there could be a - * valid event later, merely don't write CTL0. - */ + if (c->x86 >= 0x17 && c->x86 <= 0x1A) + mce_flags.zen_ifu_quirk = 1; +} - if (c->x86 == 6 && c->x86_model < 0x1A && this_cpu_read(mce_num_banks) > 0) - mce_banks[0].init = false; +static void apply_quirks_intel(struct cpuinfo_x86 *c) +{ + struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); - /* - * All newer Intel systems support MCE broadcasting. Enable - * synchronization with a one second timeout. - */ - if ((c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xe)) && - cfg->monarch_timeout < 0) - cfg->monarch_timeout = USEC_PER_SEC; + /* Older CPUs (prior to family 6) don't need quirks. */ + if (c->x86_vfm < INTEL_PENTIUM_PRO) + return; - /* - * There are also broken BIOSes on some Pentium M and - * earlier systems: - */ - if (c->x86 == 6 && c->x86_model <= 13 && cfg->bootlog < 0) - cfg->bootlog = 0; + /* + * SDM documents that on family 6 bank 0 should not be written + * because it aliases to another special BIOS controlled + * register. + * But it's not aliased anymore on model 0x1a+ + * Don't ignore bank 0 completely because there could be a + * valid event later, merely don't write CTL0. + */ + if (c->x86_vfm < INTEL_NEHALEM_EP && this_cpu_read(mce_num_banks)) + mce_banks[0].init = false; - if (c->x86_vfm == INTEL_SANDYBRIDGE_X) - mce_flags.snb_ifu_quirk = 1; + /* + * All newer Intel systems support MCE broadcasting. Enable + * synchronization with a one second timeout. + */ + if (c->x86_vfm >= INTEL_CORE_YONAH && mca_cfg.monarch_timeout < 0) + mca_cfg.monarch_timeout = USEC_PER_SEC; - /* - * Skylake, Cascacde Lake and Cooper Lake require a quirk on - * rep movs. - */ - if (c->x86_vfm == INTEL_SKYLAKE_X) - mce_flags.skx_repmov_quirk = 1; + /* + * There are also broken BIOSes on some Pentium M and + * earlier systems: + */ + if (c->x86_vfm < INTEL_CORE_YONAH && mca_cfg.bootlog < 0) + mca_cfg.bootlog = 0; + + if (c->x86_vfm == INTEL_SANDYBRIDGE_X) + mce_flags.snb_ifu_quirk = 1; + + /* + * Skylake, Cascacde Lake and Cooper Lake require a quirk on + * rep movs. + */ + if (c->x86_vfm == INTEL_SKYLAKE_X) + mce_flags.skx_repmov_quirk = 1; +} + +static void apply_quirks_zhaoxin(struct cpuinfo_x86 *c) +{ + /* + * All newer Zhaoxin CPUs support MCE broadcasting. Enable + * synchronization with a one second timeout. + */ + if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) { + if (mca_cfg.monarch_timeout < 0) + mca_cfg.monarch_timeout = USEC_PER_SEC; } +} - if (c->x86_vendor == X86_VENDOR_ZHAOXIN) { - /* - * All newer Zhaoxin CPUs support MCE broadcasting. Enable - * synchronization with a one second timeout. - */ - if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) { - if (cfg->monarch_timeout < 0) - cfg->monarch_timeout = USEC_PER_SEC; - } +/* Add per CPU specific workarounds here */ +static bool __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) +{ + struct mca_config *cfg = &mca_cfg; + + switch (c->x86_vendor) { + case X86_VENDOR_UNKNOWN: + pr_info("unknown CPU type - not enabling MCE support\n"); + return false; + case X86_VENDOR_AMD: + apply_quirks_amd(c); + break; + case X86_VENDOR_INTEL: + apply_quirks_intel(c); + break; + case X86_VENDOR_ZHAOXIN: + apply_quirks_zhaoxin(c); + break; } if (cfg->monarch_timeout < 0) @@ -2012,28 +2031,28 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (cfg->bootlog != 0) cfg->panic_timeout = 30; - return 0; + return true; } -static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) +static bool __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) { if (c->x86 != 5) - return 0; + return false; switch (c->x86_vendor) { case X86_VENDOR_INTEL: intel_p5_mcheck_init(c); mce_flags.p5 = 1; - return 1; + return true; case X86_VENDOR_CENTAUR: winchip_mcheck_init(c); mce_flags.winchip = 1; - return 1; + return true; default: - return 0; + return false; } - return 0; + return false; } /* @@ -2099,13 +2118,9 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) mce_intel_feature_init(c); break; - case X86_VENDOR_AMD: { - mce_amd_feature_init(c); - break; - } - + case X86_VENDOR_AMD: case X86_VENDOR_HYGON: - mce_hygon_feature_init(c); + mce_amd_feature_init(c); break; case X86_VENDOR_CENTAUR: @@ -2279,12 +2294,12 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) __mcheck_cpu_cap_init(); - if (__mcheck_cpu_apply_quirks(c) < 0) { + if (!__mcheck_cpu_apply_quirks(c)) { mca_cfg.disabled = 1; return; } - if (mce_gen_pool_init()) { + if (!mce_gen_pool_init()) { mca_cfg.disabled = 1; pr_emerg("Couldn't allocate MCE records pool!\n"); return; diff --git a/arch/x86/kernel/cpu/mce/genpool.c b/arch/x86/kernel/cpu/mce/genpool.c index d0be6dda0c14..3ca9c007a666 100644 --- a/arch/x86/kernel/cpu/mce/genpool.c +++ b/arch/x86/kernel/cpu/mce/genpool.c @@ -94,64 +94,63 @@ bool mce_gen_pool_empty(void) return llist_empty(&mce_event_llist); } -int mce_gen_pool_add(struct mce_hw_err *err) +bool mce_gen_pool_add(struct mce_hw_err *err) { struct mce_evt_llist *node; if (filter_mce(&err->m)) - return -EINVAL; + return false; if (!mce_evt_pool) - return -EINVAL; + return false; node = (void *)gen_pool_alloc(mce_evt_pool, sizeof(*node)); if (!node) { pr_warn_ratelimited("MCE records pool full!\n"); - return -ENOMEM; + return false; } memcpy(&node->err, err, sizeof(*err)); llist_add(&node->llnode, &mce_event_llist); - return 0; + return true; } -static int mce_gen_pool_create(void) +static bool mce_gen_pool_create(void) { int mce_numrecords, mce_poolsz, order; struct gen_pool *gpool; - int ret = -ENOMEM; void *mce_pool; order = order_base_2(sizeof(struct mce_evt_llist)); gpool = gen_pool_create(order, -1); if (!gpool) - return ret; + return false; mce_numrecords = max(MCE_MIN_ENTRIES, num_possible_cpus() * MCE_PER_CPU); mce_poolsz = mce_numrecords * (1 << order); mce_pool = kmalloc(mce_poolsz, GFP_KERNEL); if (!mce_pool) { gen_pool_destroy(gpool); - return ret; + return false; } - ret = gen_pool_add(gpool, (unsigned long)mce_pool, mce_poolsz, -1); - if (ret) { + + if (gen_pool_add(gpool, (unsigned long)mce_pool, mce_poolsz, -1)) { gen_pool_destroy(gpool); kfree(mce_pool); - return ret; + return false; } mce_evt_pool = gpool; - return ret; + return true; } -int mce_gen_pool_init(void) +bool mce_gen_pool_init(void) { /* Just init mce_gen_pool once. */ if (mce_evt_pool) - return 0; + return true; return mce_gen_pool_create(); } diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index b3cd2c61b11d..f863df0ff42c 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -75,12 +75,12 @@ static u16 cmci_threshold[MAX_NR_BANKS]; */ #define CMCI_STORM_THRESHOLD 32749 -static int cmci_supported(int *banks) +static bool cmci_supported(int *banks) { u64 cap; if (mca_cfg.cmci_disabled || mca_cfg.ignore_ce) - return 0; + return false; /* * Vendor check is not strictly needed, but the initial @@ -89,10 +89,11 @@ static int cmci_supported(int *banks) */ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) - return 0; + return false; if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6) - return 0; + return false; + rdmsrl(MSR_IA32_MCG_CAP, cap); *banks = min_t(unsigned, MAX_NR_BANKS, cap & MCG_BANKCNT_MASK); return !!(cap & MCG_CMCI_P); diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 84f810598231..95a504ece43e 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -31,8 +31,8 @@ struct mce_evt_llist { void mce_gen_pool_process(struct work_struct *__unused); bool mce_gen_pool_empty(void); -int mce_gen_pool_add(struct mce_hw_err *err); -int mce_gen_pool_init(void); +bool mce_gen_pool_add(struct mce_hw_err *err); +bool mce_gen_pool_init(void); struct llist_node *mce_gen_pool_prepare_records(void); int mce_severity(struct mce *a, struct pt_regs *regs, char **msg, bool is_excp); diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c index 89e31e1e5c9c..f4a007616468 100644 --- a/arch/x86/kernel/cpu/mce/threshold.c +++ b/arch/x86/kernel/cpu/mce/threshold.c @@ -90,7 +90,7 @@ void cmci_storm_end(unsigned int bank) storm->banks[bank].in_storm_mode = false; /* If no banks left in storm mode, stop polling. */ - if (!this_cpu_dec_return(storm_desc.stormy_bank_count)) + if (!--storm->stormy_bank_count) mce_timer_kick(false); } diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index fb5d0c67fbab..a5dac7f3c0a0 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -283,13 +283,13 @@ __verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize) * exceed the per-family maximum). @sh_psize is the size read from the section * header. */ -static unsigned int __verify_patch_size(u32 sh_psize, size_t buf_size) +static bool __verify_patch_size(u32 sh_psize, size_t buf_size) { u8 family = x86_family(bsp_cpuid_1_eax); u32 max_size; if (family >= 0x15) - return min_t(u32, sh_psize, buf_size); + goto ret; #define F1XH_MPB_MAX_SIZE 2048 #define F14H_MPB_MAX_SIZE 1824 @@ -303,13 +303,15 @@ static unsigned int __verify_patch_size(u32 sh_psize, size_t buf_size) break; default: WARN(1, "%s: WTF family: 0x%x\n", __func__, family); - return 0; + return false; } - if (sh_psize > min_t(u32, buf_size, max_size)) - return 0; + if (sh_psize > max_size) + return false; - return sh_psize; +ret: + /* Working with the whole buffer so < is ok. */ + return sh_psize <= buf_size; } /* @@ -324,7 +326,6 @@ static int verify_patch(const u8 *buf, size_t buf_size, u32 *patch_size) { u8 family = x86_family(bsp_cpuid_1_eax); struct microcode_header_amd *mc_hdr; - unsigned int ret; u32 sh_psize; u16 proc_id; u8 patch_fam; @@ -348,8 +349,7 @@ static int verify_patch(const u8 *buf, size_t buf_size, u32 *patch_size) return -1; } - ret = __verify_patch_size(sh_psize, buf_size); - if (!ret) { + if (!__verify_patch_size(sh_psize, buf_size)) { pr_debug("Per-family patch size mismatch.\n"); return -1; } @@ -381,8 +381,8 @@ static bool mc_patch_matches(struct microcode_amd *mc, u16 eq_id) /* * This scans the ucode blob for the proper container as we can have multiple - * containers glued together. Returns the equivalence ID from the equivalence - * table or 0 if none found. + * containers glued together. + * * Returns the amount of bytes consumed while scanning. @desc contains all the * data we're going to use in later stages of the application. */ @@ -484,7 +484,7 @@ static void scan_containers(u8 *ucode, size_t size, struct cont_desc *desc) } } -static int __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize) +static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize) { unsigned long p_addr = (unsigned long)&mc->hdr.data_code; u32 rev, dummy; @@ -508,9 +508,9 @@ static int __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize) native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); if (rev != mc->hdr.patch_id) - return -1; + return false; - return 0; + return true; } /* @@ -528,13 +528,12 @@ static bool early_apply_microcode(u32 old_rev, void *ucode, size_t size) { struct cont_desc desc = { 0 }; struct microcode_amd *mc; - bool ret = false; scan_containers(ucode, size, &desc); mc = desc.mc; if (!mc) - return ret; + return false; /* * Allow application of the same revision to pick up SMT-specific @@ -542,9 +541,9 @@ static bool early_apply_microcode(u32 old_rev, void *ucode, size_t size) * up-to-date. */ if (old_rev > mc->hdr.patch_id) - return ret; + return false; - return !__apply_microcode_amd(mc, desc.psize); + return __apply_microcode_amd(mc, desc.psize); } static bool get_builtin_microcode(struct cpio_data *cp) @@ -569,14 +568,19 @@ static bool get_builtin_microcode(struct cpio_data *cp) return false; } -static void __init find_blobs_in_containers(struct cpio_data *ret) +static bool __init find_blobs_in_containers(struct cpio_data *ret) { struct cpio_data cp; + bool found; if (!get_builtin_microcode(&cp)) cp = find_microcode_in_initrd(ucode_path); - *ret = cp; + found = cp.data && cp.size; + if (found) + *ret = cp; + + return found; } void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_eax) @@ -591,8 +595,7 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_ /* Needed in load_microcode_amd() */ ucode_cpu_info[0].cpu_sig.sig = cpuid_1_eax; - find_blobs_in_containers(&cp); - if (!(cp.data && cp.size)) + if (!find_blobs_in_containers(&cp)) return; if (early_apply_microcode(ed->old_rev, cp.data, cp.size)) @@ -612,8 +615,7 @@ static int __init save_microcode_in_initrd(void) if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) return 0; - find_blobs_in_containers(&cp); - if (!(cp.data && cp.size)) + if (!find_blobs_in_containers(&cp)) return -EINVAL; scan_containers(cp.data, cp.size, &desc); @@ -760,7 +762,7 @@ void reload_ucode_amd(unsigned int cpu) rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy); if (rev < mc->hdr.patch_id) { - if (!__apply_microcode_amd(mc, p->size)) + if (__apply_microcode_amd(mc, p->size)) pr_info_once("reload revision: 0x%08x\n", mc->hdr.patch_id); } } @@ -813,7 +815,7 @@ static enum ucode_state apply_microcode_amd(int cpu) goto out; } - if (__apply_microcode_amd(mc_amd, p->size)) { + if (!__apply_microcode_amd(mc_amd, p->size)) { pr_err("CPU%d: update failed for patch_level=0x%08x\n", cpu, mc_amd->hdr.patch_id); return UCODE_ERROR; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index d18078834ded..dc12fe5ef3ca 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -223,6 +223,63 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs) hyperv_cleanup(); } #endif /* CONFIG_CRASH_DUMP */ + +static u64 hv_ref_counter_at_suspend; +static void (*old_save_sched_clock_state)(void); +static void (*old_restore_sched_clock_state)(void); + +/* + * Hyper-V clock counter resets during hibernation. Save and restore clock + * offset during suspend/resume, while also considering the time passed + * before suspend. This is to make sure that sched_clock using hv tsc page + * based clocksource, proceeds from where it left off during suspend and + * it shows correct time for the timestamps of kernel messages after resume. + */ +static void save_hv_clock_tsc_state(void) +{ + hv_ref_counter_at_suspend = hv_read_reference_counter(); +} + +static void restore_hv_clock_tsc_state(void) +{ + /* + * Adjust the offsets used by hv tsc clocksource to + * account for the time spent before hibernation. + * adjusted value = reference counter (time) at suspend + * - reference counter (time) now. + */ + hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter()); +} + +/* + * Functions to override save_sched_clock_state and restore_sched_clock_state + * functions of x86_platform. The Hyper-V clock counter is reset during + * suspend-resume and the offset used to measure time needs to be + * corrected, post resume. + */ +static void hv_save_sched_clock_state(void) +{ + old_save_sched_clock_state(); + save_hv_clock_tsc_state(); +} + +static void hv_restore_sched_clock_state(void) +{ + restore_hv_clock_tsc_state(); + old_restore_sched_clock_state(); +} + +static void __init x86_setup_ops_for_tsc_pg_clock(void) +{ + if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) + return; + + old_save_sched_clock_state = x86_platform.save_sched_clock_state; + x86_platform.save_sched_clock_state = hv_save_sched_clock_state; + + old_restore_sched_clock_state = x86_platform.restore_sched_clock_state; + x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state; +} #endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) @@ -579,6 +636,7 @@ static void __init ms_hyperv_init_platform(void) /* Register Hyper-V specific clocksource */ hv_init_clocksource(); + x86_setup_ops_for_tsc_pg_clock(); hv_vtl_init_platform(); #endif /* diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 7b29ebda024f..2fdfda2b60e4 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -423,7 +423,7 @@ void __init mtrr_copy_map(void) } /** - * mtrr_overwrite_state - set static MTRR state + * guest_force_mtrr_state - set static MTRR state for a guest * * Used to set MTRR state via different means (e.g. with data obtained from * a hypervisor). @@ -436,8 +436,8 @@ void __init mtrr_copy_map(void) * @num_var: length of the @var array * @def_type: default caching type */ -void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var, - mtrr_type def_type) +void guest_force_mtrr_state(struct mtrr_var_range *var, unsigned int num_var, + mtrr_type def_type) { unsigned int i; diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 989d368be04f..ecbda0341a8a 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -625,7 +625,7 @@ void mtrr_save_state(void) static int __init mtrr_init_finalize(void) { /* - * Map might exist if mtrr_overwrite_state() has been called or if + * Map might exist if guest_force_mtrr_state() has been called or if * mtrr_enabled() returns true. */ mtrr_copy_map(); diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index b681c2e07dbf..3d1735ed8d1f 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -234,7 +234,9 @@ static __init bool __get_mem_config_intel(struct rdt_resource *r) r->membw.throttle_mode = THREAD_THROTTLE_PER_THREAD; else r->membw.throttle_mode = THREAD_THROTTLE_MAX; - thread_throttle_mode_init(); + + resctrl_file_fflags_init("thread_throttle_mode", + RFTYPE_CTRL_INFO | RFTYPE_RES_MB); r->alloc_capable = true; @@ -961,6 +963,11 @@ static __init bool get_rdt_mon_resources(void) if (!rdt_mon_features) return false; + if (is_mbm_local_enabled()) + mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID; + else if (is_mbm_total_enabled()) + mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID; + return !rdt_get_mon_l3_config(r); } diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 200d89a64027..536351159cc2 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -518,6 +518,76 @@ static int smp_mon_event_count(void *arg) return 0; } +ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + + /* Valid input requires a trailing newline */ + if (nbytes == 0 || buf[nbytes - 1] != '\n') + return -EINVAL; + buf[nbytes - 1] = '\0'; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (!rdtgrp) { + rdtgroup_kn_unlock(of->kn); + return -ENOENT; + } + rdt_last_cmd_clear(); + + if (!strcmp(buf, "mbm_local_bytes")) { + if (is_mbm_local_enabled()) + rdtgrp->mba_mbps_event = QOS_L3_MBM_LOCAL_EVENT_ID; + else + ret = -EINVAL; + } else if (!strcmp(buf, "mbm_total_bytes")) { + if (is_mbm_total_enabled()) + rdtgrp->mba_mbps_event = QOS_L3_MBM_TOTAL_EVENT_ID; + else + ret = -EINVAL; + } else { + ret = -EINVAL; + } + + if (ret) + rdt_last_cmd_printf("Unsupported event id '%s'\n", buf); + + rdtgroup_kn_unlock(of->kn); + + return ret ?: nbytes; +} + +int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + + if (rdtgrp) { + switch (rdtgrp->mba_mbps_event) { + case QOS_L3_MBM_LOCAL_EVENT_ID: + seq_puts(s, "mbm_local_bytes\n"); + break; + case QOS_L3_MBM_TOTAL_EVENT_ID: + seq_puts(s, "mbm_total_bytes\n"); + break; + default: + pr_warn_once("Bad event %d\n", rdtgrp->mba_mbps_event); + ret = -EINVAL; + break; + } + } else { + ret = -ENOENT; + } + + rdtgroup_kn_unlock(of->kn); + + return ret; +} + void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, struct rdt_mon_domain *d, struct rdtgroup *rdtgrp, cpumask_t *cpumask, int evtid, int first) diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 955999aecfca..20c898f09b7e 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -283,6 +283,7 @@ struct pseudo_lock_region { * monitor only or ctrl_mon group * @mon: mongroup related data * @mode: mode of resource group + * @mba_mbps_event: input monitoring event id when mba_sc is enabled * @plr: pseudo-locked region */ struct rdtgroup { @@ -295,6 +296,7 @@ struct rdtgroup { enum rdt_group_type type; struct mongroup mon; enum rdtgrp_mode mode; + enum resctrl_event_id mba_mbps_event; struct pseudo_lock_region *plr; }; @@ -508,6 +510,7 @@ extern struct mutex rdtgroup_mutex; extern struct rdt_hw_resource rdt_resources_all[]; extern struct rdtgroup rdtgroup_default; extern struct dentry *debugfs_resctrl; +extern enum resctrl_event_id mba_mbps_default_event; enum resctrl_res_level { RDT_RESOURCE_L3, @@ -607,6 +610,10 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off); int rdtgroup_schemata_show(struct kernfs_open_file *of, struct seq_file *s, void *v); +ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off); +int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of, + struct seq_file *s, void *v); bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d, unsigned long cbm, int closid, bool exclusive); unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain *d, @@ -647,10 +654,8 @@ void cqm_handle_limbo(struct work_struct *work); bool has_busy_rmid(struct rdt_mon_domain *d); void __check_limbo(struct rdt_mon_domain *d, bool force_free); void rdt_domain_reconfigure_cdp(struct rdt_resource *r); -void __init thread_throttle_mode_init(void); -void __init mbm_config_rftype_init(const char *config); +void resctrl_file_fflags_init(const char *config, unsigned long fflags); void rdt_staged_configs_clear(void); bool closid_allocated(unsigned int closid); int resctrl_find_cleanest_closid(void); - #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 5fcb3d635d91..94a1d9780461 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -663,9 +663,12 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) */ static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr) { - u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); - struct mbm_state *m = &rr->d->mbm_local[idx]; u64 cur_bw, bytes, cur_bytes; + struct mbm_state *m; + + m = get_mbm_state(rr->d, closid, rmid, rr->evtid); + if (WARN_ON_ONCE(!m)) + return; cur_bytes = rr->val; bytes = cur_bytes - m->prev_bw_bytes; @@ -752,20 +755,20 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm) u32 closid, rmid, cur_msr_val, new_msr_val; struct mbm_state *pmbm_data, *cmbm_data; struct rdt_ctrl_domain *dom_mba; + enum resctrl_event_id evt_id; struct rdt_resource *r_mba; - u32 cur_bw, user_bw, idx; struct list_head *head; struct rdtgroup *entry; - - if (!is_mbm_local_enabled()) - return; + u32 cur_bw, user_bw; r_mba = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; + evt_id = rgrp->mba_mbps_event; closid = rgrp->closid; rmid = rgrp->mon.rmid; - idx = resctrl_arch_rmid_idx_encode(closid, rmid); - pmbm_data = &dom_mbm->mbm_local[idx]; + pmbm_data = get_mbm_state(dom_mbm, closid, rmid, evt_id); + if (WARN_ON_ONCE(!pmbm_data)) + return; dom_mba = get_ctrl_domain_from_cpu(smp_processor_id(), r_mba); if (!dom_mba) { @@ -784,7 +787,9 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm) */ head = &rgrp->mon.crdtgrp_list; list_for_each_entry(entry, head, mon.crdtgrp_list) { - cmbm_data = &dom_mbm->mbm_local[entry->mon.rmid]; + cmbm_data = get_mbm_state(dom_mbm, entry->closid, entry->mon.rmid, evt_id); + if (WARN_ON_ONCE(!cmbm_data)) + return; cur_bw += cmbm_data->prev_bw; } @@ -813,54 +818,45 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm) resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val); } -static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d, - u32 closid, u32 rmid) +static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *d, + u32 closid, u32 rmid, enum resctrl_event_id evtid) { struct rmid_read rr = {0}; rr.r = r; rr.d = d; + rr.evtid = evtid; + rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); + if (IS_ERR(rr.arch_mon_ctx)) { + pr_warn_ratelimited("Failed to allocate monitor context: %ld", + PTR_ERR(rr.arch_mon_ctx)); + return; + } + + __mon_event_count(closid, rmid, &rr); /* - * This is protected from concurrent reads from user - * as both the user and we hold the global mutex. + * If the software controller is enabled, compute the + * bandwidth for this event id. */ - if (is_mbm_total_enabled()) { - rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID; - rr.val = 0; - rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); - if (IS_ERR(rr.arch_mon_ctx)) { - pr_warn_ratelimited("Failed to allocate monitor context: %ld", - PTR_ERR(rr.arch_mon_ctx)); - return; - } - - __mon_event_count(closid, rmid, &rr); + if (is_mba_sc(NULL)) + mbm_bw_count(closid, rmid, &rr); - resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); - } - if (is_mbm_local_enabled()) { - rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; - rr.val = 0; - rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); - if (IS_ERR(rr.arch_mon_ctx)) { - pr_warn_ratelimited("Failed to allocate monitor context: %ld", - PTR_ERR(rr.arch_mon_ctx)); - return; - } - - __mon_event_count(closid, rmid, &rr); + resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); +} - /* - * Call the MBA software controller only for the - * control groups and when user has enabled - * the software controller explicitly. - */ - if (is_mba_sc(NULL)) - mbm_bw_count(closid, rmid, &rr); +static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d, + u32 closid, u32 rmid) +{ + /* + * This is protected from concurrent reads from user as both + * the user and overflow handler hold the global mutex. + */ + if (is_mbm_total_enabled()) + mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID); - resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); - } + if (is_mbm_local_enabled()) + mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID); } /* @@ -1224,11 +1220,13 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r) if (rdt_cpu_has(X86_FEATURE_CQM_MBM_TOTAL)) { mbm_total_event.configurable = true; - mbm_config_rftype_init("mbm_total_bytes_config"); + resctrl_file_fflags_init("mbm_total_bytes_config", + RFTYPE_MON_INFO | RFTYPE_RES_CACHE); } if (rdt_cpu_has(X86_FEATURE_CQM_MBM_LOCAL)) { mbm_local_event.configurable = true; - mbm_config_rftype_init("mbm_local_bytes_config"); + resctrl_file_fflags_init("mbm_local_bytes_config", + RFTYPE_MON_INFO | RFTYPE_RES_CACHE); } } diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 972e6b6b0481..42cc162f7fc9 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -459,7 +459,7 @@ static int pseudo_lock_fn(void *_rdtgrp) * increase likelihood that allocated cache portion will be filled * with associated memory. */ - native_wbinvd(); + wbinvd(); /* * Always called with interrupts enabled. By disabling interrupts @@ -1205,20 +1205,14 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel) plr->cpu = cpu; if (sel == 1) - thread = kthread_create_on_node(measure_cycles_lat_fn, plr, - cpu_to_node(cpu), - "pseudo_lock_measure/%u", - cpu); + thread = kthread_run_on_cpu(measure_cycles_lat_fn, plr, + cpu, "pseudo_lock_measure/%u"); else if (sel == 2) - thread = kthread_create_on_node(measure_l2_residency, plr, - cpu_to_node(cpu), - "pseudo_lock_measure/%u", - cpu); + thread = kthread_run_on_cpu(measure_l2_residency, plr, + cpu, "pseudo_lock_measure/%u"); else if (sel == 3) - thread = kthread_create_on_node(measure_l3_residency, plr, - cpu_to_node(cpu), - "pseudo_lock_measure/%u", - cpu); + thread = kthread_run_on_cpu(measure_l3_residency, plr, + cpu, "pseudo_lock_measure/%u"); else goto out; @@ -1226,8 +1220,6 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel) ret = PTR_ERR(thread); goto out; } - kthread_bind(thread, cpu); - wake_up_process(thread); ret = wait_event_interruptible(plr->lock_thread_wq, plr->thread_done == 1); @@ -1315,18 +1307,14 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp) plr->thread_done = 0; - thread = kthread_create_on_node(pseudo_lock_fn, rdtgrp, - cpu_to_node(plr->cpu), - "pseudo_lock/%u", plr->cpu); + thread = kthread_run_on_cpu(pseudo_lock_fn, rdtgrp, + plr->cpu, "pseudo_lock/%u"); if (IS_ERR(thread)) { ret = PTR_ERR(thread); rdt_last_cmd_printf("Locking thread returned error %d\n", ret); goto out_cstates; } - kthread_bind(thread, plr->cpu); - wake_up_process(thread); - ret = wait_event_interruptible(plr->lock_thread_wq, plr->thread_done == 1); if (ret < 0) { diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index d906a1cd8491..6419e04d8a7b 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -65,6 +65,15 @@ static void rdtgroup_destroy_root(void); struct dentry *debugfs_resctrl; +/* + * Memory bandwidth monitoring event to use for the default CTRL_MON group + * and each new CTRL_MON group created by the user. Only relevant when + * the filesystem is mounted with the "mba_MBps" option so it does not + * matter that it remains uninitialized on systems that do not support + * the "mba_MBps" option. + */ +enum resctrl_event_id mba_mbps_default_event; + static bool resctrl_debug; void rdt_last_cmd_clear(void) @@ -1942,6 +1951,13 @@ static struct rftype res_common_files[] = { .fflags = RFTYPE_CTRL_BASE, }, { + .name = "mba_MBps_event", + .mode = 0644, + .kf_ops = &rdtgroup_kf_single_ops, + .write = rdtgroup_mba_mbps_event_write, + .seq_show = rdtgroup_mba_mbps_event_show, + }, + { .name = "mode", .mode = 0644, .kf_ops = &rdtgroup_kf_single_ops, @@ -2020,24 +2036,13 @@ static struct rftype *rdtgroup_get_rftype_by_name(const char *name) return NULL; } -void __init thread_throttle_mode_init(void) -{ - struct rftype *rft; - - rft = rdtgroup_get_rftype_by_name("thread_throttle_mode"); - if (!rft) - return; - - rft->fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB; -} - -void __init mbm_config_rftype_init(const char *config) +void resctrl_file_fflags_init(const char *config, unsigned long fflags) { struct rftype *rft; rft = rdtgroup_get_rftype_by_name(config); if (rft) - rft->fflags = RFTYPE_MON_INFO | RFTYPE_RES_CACHE; + rft->fflags = fflags; } /** @@ -2343,7 +2348,7 @@ static bool supports_mba_mbps(void) struct rdt_resource *rmbm = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; - return (is_mbm_local_enabled() && + return (is_mbm_enabled() && r->alloc_capable && is_mba_linear() && r->ctrl_scope == rmbm->mon_scope); } @@ -2357,6 +2362,7 @@ static int set_mba_sc(bool mba_sc) struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl; u32 num_closid = resctrl_arch_get_num_closid(r); struct rdt_ctrl_domain *d; + unsigned long fflags; int i; if (!supports_mba_mbps() || mba_sc == is_mba_sc(r)) @@ -2364,11 +2370,16 @@ static int set_mba_sc(bool mba_sc) r->membw.mba_sc = mba_sc; + rdtgroup_default.mba_mbps_event = mba_mbps_default_event; + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { for (i = 0; i < num_closid; i++) d->mbps_val[i] = MBA_MAX_MBPS; } + fflags = mba_sc ? RFTYPE_CTRL_BASE | RFTYPE_MON_BASE : 0; + resctrl_file_fflags_init("mba_MBps_event", fflags); + return 0; } @@ -2768,7 +2779,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param) ctx->enable_cdpl2 = true; return 0; case Opt_mba_mbps: - msg = "mba_MBps requires local MBM and linear scale MBA at L3 scope"; + msg = "mba_MBps requires MBM and linear scale MBA at L3 scope"; if (!supports_mba_mbps()) return invalfc(fc, msg); ctx->enable_mba_mbps = true; @@ -3622,6 +3633,8 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, rdt_last_cmd_puts("kernfs subdir error\n"); goto out_del_list; } + if (is_mba_sc(NULL)) + rdtgrp->mba_mbps_event = mba_mbps_default_event; } goto out_unlock; diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index b2e313ea17bf..01456236a6dd 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -428,7 +428,7 @@ void __init topology_apply_cmdline_limits_early(void) { unsigned int possible = nr_cpu_ids; - /* 'maxcpus=0' 'nosmp' 'nolapic' 'disableapic' */ + /* 'maxcpus=0' 'nosmp' 'nolapic' */ if (!setup_max_cpus || apic_is_disabled) possible = 1; diff --git a/arch/x86/kernel/cpu/topology_common.c b/arch/x86/kernel/cpu/topology_common.c index 8277c64f88db..b5a5e1411469 100644 --- a/arch/x86/kernel/cpu/topology_common.c +++ b/arch/x86/kernel/cpu/topology_common.c @@ -185,6 +185,7 @@ static void topo_set_ids(struct topo_scan *tscan, bool early) if (!early) { c->topo.logical_pkg_id = topology_get_logical_id(apicid, TOPO_PKG_DOMAIN); c->topo.logical_die_id = topology_get_logical_id(apicid, TOPO_DIE_DOMAIN); + c->topo.logical_core_id = topology_get_logical_id(apicid, TOPO_CORE_DOMAIN); } /* Package relative core ID */ diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 6bc1eb2a21bd..887b0b8e21e3 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -190,7 +190,8 @@ int ssp_get(struct task_struct *target, const struct user_regset *regset, struct fpu *fpu = &target->thread.fpu; struct cet_user_state *cetregs; - if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK)) + if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || + !ssp_active(target, regset)) return -ENODEV; sync_fpstate(fpu); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 22abb5ee0cf2..27417b685c1d 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -20,6 +20,7 @@ #include <asm/fpu/signal.h> #include <asm/fpu/xcr.h> +#include <asm/cpuid.h> #include <asm/tlbflush.h> #include <asm/prctl.h> #include <asm/elf.h> @@ -232,7 +233,7 @@ static void __init setup_xstate_cache(void) xmm_space); for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) { - cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, i, &eax, &ebx, &ecx, &edx); xstate_sizes[i] = eax; xstate_flags[i] = ecx; @@ -398,7 +399,7 @@ int xfeature_size(int xfeature_nr) u32 eax, ebx, ecx, edx; CHECK_XFEATURE(xfeature_nr); - cpuid_count(XSTATE_CPUID, xfeature_nr, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, xfeature_nr, &eax, &ebx, &ecx, &edx); return eax; } @@ -441,9 +442,9 @@ static void __init __xstate_dump_leaves(void) * just in case there are some goodies up there */ for (i = 0; i < XFEATURE_MAX + 10; i++) { - cpuid_count(XSTATE_CPUID, i, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, i, &eax, &ebx, &ecx, &edx); pr_warn("CPUID[%02x, %02x]: eax=%08x ebx=%08x ecx=%08x edx=%08x\n", - XSTATE_CPUID, i, eax, ebx, ecx, edx); + CPUID_LEAF_XSTATE, i, eax, ebx, ecx, edx); } } @@ -484,7 +485,7 @@ static int __init check_xtile_data_against_struct(int size) * Check the maximum palette id: * eax: the highest numbered palette subleaf. */ - cpuid_count(TILE_CPUID, 0, &max_palid, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_TILE, 0, &max_palid, &ebx, &ecx, &edx); /* * Cross-check each tile size and find the maximum number of @@ -498,7 +499,7 @@ static int __init check_xtile_data_against_struct(int size) * eax[31:16]: bytes per title * ebx[31:16]: the max names (or max number of tiles) */ - cpuid_count(TILE_CPUID, palid, &eax, &ebx, &edx, &edx); + cpuid_count(CPUID_LEAF_TILE, palid, &eax, &ebx, &edx, &edx); tile_size = eax >> 16; max = ebx >> 16; @@ -633,7 +634,7 @@ static unsigned int __init get_compacted_size(void) * are no supervisor states, but XSAVEC still uses compacted * format. */ - cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, 1, &eax, &ebx, &ecx, &edx); return ebx; } @@ -674,7 +675,7 @@ static unsigned int __init get_xsave_size_user(void) * containing all the *user* state components * corresponding to bits currently set in XCR0. */ - cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, 0, &eax, &ebx, &ecx, &edx); return ebx; } @@ -763,21 +764,16 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) return; } - if (boot_cpu_data.cpuid_level < XSTATE_CPUID) { - WARN_ON_FPU(1); - return; - } - /* * Find user xstates supported by the processor. */ - cpuid_count(XSTATE_CPUID, 0, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, 0, &eax, &ebx, &ecx, &edx); fpu_kernel_cfg.max_features = eax + ((u64)edx << 32); /* * Find supervisor xstates supported by the processor. */ - cpuid_count(XSTATE_CPUID, 1, &eax, &ebx, &ecx, &edx); + cpuid_count(CPUID_LEAF_XSTATE, 1, &eax, &ebx, &ecx, &edx); fpu_kernel_cfg.max_features |= ecx + ((u64)edx << 32); if ((fpu_kernel_cfg.max_features & XFEATURE_MASK_FPSSE) != XFEATURE_MASK_FPSSE) { diff --git a/arch/x86/kernel/fred.c b/arch/x86/kernel/fred.c index 8d32c3f48abc..5e2cd1004980 100644 --- a/arch/x86/kernel/fred.c +++ b/arch/x86/kernel/fred.c @@ -50,7 +50,13 @@ void cpu_init_fred_exceptions(void) FRED_CONFIG_ENTRYPOINT(asm_fred_entrypoint_user)); wrmsrl(MSR_IA32_FRED_STKLVLS, 0); - wrmsrl(MSR_IA32_FRED_RSP0, 0); + + /* + * Ater a CPU offline/online cycle, the FRED RSP0 MSR should be + * resynchronized with its per-CPU cache. + */ + wrmsrl(MSR_IA32_FRED_RSP0, __this_cpu_read(fred_rsp0)); + wrmsrl(MSR_IA32_FRED_RSP1, 0); wrmsrl(MSR_IA32_FRED_RSP2, 0); wrmsrl(MSR_IA32_FRED_RSP3, 0); diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 4dd0ad6c94d6..166bc0ea3bdf 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -607,16 +607,8 @@ int ftrace_disable_ftrace_graph_caller(void) } #endif /* CONFIG_DYNAMIC_FTRACE && !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */ -/* - * Hook the return address and push it in the stack of return addrs - * in current thread info. - */ -void prepare_ftrace_return(unsigned long ip, unsigned long *parent, - unsigned long frame_pointer) +static inline bool skip_ftrace_return(void) { - unsigned long return_hooker = (unsigned long)&return_to_handler; - int bit; - /* * When resuming from suspend-to-ram, this function can be indirectly * called from early CPU startup code while the CPU is in real mode, @@ -626,23 +618,31 @@ void prepare_ftrace_return(unsigned long ip, unsigned long *parent, * This check isn't as accurate as virt_addr_valid(), but it should be * good enough for this purpose, and it's fast. */ - if (unlikely((long)__builtin_frame_address(0) >= 0)) - return; + if ((long)__builtin_frame_address(0) >= 0) + return true; - if (unlikely(ftrace_graph_is_dead())) - return; + if (ftrace_graph_is_dead()) + return true; - if (unlikely(atomic_read(¤t->tracing_graph_pause))) - return; + if (atomic_read(¤t->tracing_graph_pause)) + return true; + return false; +} - bit = ftrace_test_recursion_trylock(ip, *parent); - if (bit < 0) +/* + * Hook the return address and push it in the stack of return addrs + * in current thread info. + */ +void prepare_ftrace_return(unsigned long ip, unsigned long *parent, + unsigned long frame_pointer) +{ + unsigned long return_hooker = (unsigned long)&return_to_handler; + + if (unlikely(skip_ftrace_return())) return; if (!function_graph_enter(*parent, ip, frame_pointer, parent)) *parent = return_hooker; - - ftrace_test_recursion_unlock(bit); } #ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS @@ -651,8 +651,15 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, { struct pt_regs *regs = &arch_ftrace_regs(fregs)->regs; unsigned long *stack = (unsigned long *)kernel_stack_pointer(regs); + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long *parent = (unsigned long *)stack; + + if (unlikely(skip_ftrace_return())) + return; + - prepare_ftrace_return(ip, (unsigned long *)stack, 0); + if (!function_graph_enter_regs(*parent, ip, 0, parent, fregs)) + *parent = return_hooker; } #endif diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S index 58d9ed50fe61..f4e0c3361234 100644 --- a/arch/x86/kernel/ftrace_32.S +++ b/arch/x86/kernel/ftrace_32.S @@ -187,14 +187,15 @@ SYM_CODE_END(ftrace_graph_caller) .globl return_to_handler return_to_handler: - pushl $0 - pushl %edx - pushl %eax + subl $(PTREGS_SIZE), %esp + movl $0, PT_EBP(%esp) + movl %edx, PT_EDX(%esp) + movl %eax, PT_EAX(%esp) movl %esp, %eax call ftrace_return_to_handler movl %eax, %ecx - popl %eax - popl %edx - addl $4, %esp # skip ebp + movl PT_EAX(%esp), %eax + movl PT_EDX(%esp), %edx + addl $(PTREGS_SIZE), %esp JMP_NOSPEC ecx #endif diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 214f30e9f0c0..d51647228596 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -348,21 +348,22 @@ STACK_FRAME_NON_STANDARD_FP(__fentry__) SYM_CODE_START(return_to_handler) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR - subq $24, %rsp - /* Save the return values */ - movq %rax, (%rsp) - movq %rdx, 8(%rsp) - movq %rbp, 16(%rsp) + /* Save ftrace_regs for function exit context */ + subq $(FRAME_SIZE), %rsp + + movq %rax, RAX(%rsp) + movq %rdx, RDX(%rsp) + movq %rbp, RBP(%rsp) movq %rsp, %rdi call ftrace_return_to_handler movq %rax, %rdi - movq 8(%rsp), %rdx - movq (%rsp), %rax + movq RDX(%rsp), %rdx + movq RAX(%rsp), %rax - addq $24, %rsp + addq $(FRAME_SIZE), %rsp /* * Jump back to the old return address. This cannot be JMP_NOSPEC rdi * since IBT would demand that contain ENDBR, which simply isn't so for diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index c96ae8fee95e..9182303a50b0 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -7,6 +7,7 @@ #include <linux/cpu.h> #include <linux/irq.h> +#include <asm/cpuid.h> #include <asm/irq_remapping.h> #include <asm/hpet.h> #include <asm/time.h> @@ -516,22 +517,14 @@ static int hpet_msi_init(struct irq_domain *domain, struct msi_domain_info *info, unsigned int virq, irq_hw_number_t hwirq, msi_alloc_info_t *arg) { - irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); irq_domain_set_info(domain, virq, arg->hwirq, info->chip, NULL, handle_edge_irq, arg->data, "edge"); return 0; } -static void hpet_msi_free(struct irq_domain *domain, - struct msi_domain_info *info, unsigned int virq) -{ - irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT); -} - static struct msi_domain_ops hpet_msi_domain_ops = { .msi_init = hpet_msi_init, - .msi_free = hpet_msi_free, }; static struct msi_domain_info hpet_msi_domain_info = { @@ -927,10 +920,7 @@ static bool __init mwait_pc10_supported(void) if (!cpu_feature_enabled(X86_FEATURE_MWAIT)) return false; - if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF) - return false; - - cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &mwait_substates); + cpuid(CPUID_LEAF_MWAIT, &eax, &ebx, &ecx, &mwait_substates); return (ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) && (ecx & CPUID5_ECX_INTERRUPT_BREAK) && diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c index 51b805c727fc..9cea1fc36c18 100644 --- a/arch/x86/kernel/itmt.c +++ b/arch/x86/kernel/itmt.c @@ -19,6 +19,7 @@ #include <linux/sched.h> #include <linux/cpumask.h> #include <linux/cpuset.h> +#include <linux/debugfs.h> #include <linux/mutex.h> #include <linux/sysctl.h> #include <linux/nodemask.h> @@ -34,49 +35,38 @@ static bool __read_mostly sched_itmt_capable; * of higher turbo frequency for cpus supporting Intel Turbo Boost Max * Technology 3.0. * - * It can be set via /proc/sys/kernel/sched_itmt_enabled + * It can be set via /sys/kernel/debug/x86/sched_itmt_enabled */ -unsigned int __read_mostly sysctl_sched_itmt_enabled; +bool __read_mostly sysctl_sched_itmt_enabled; -static int sched_itmt_update_handler(const struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +static ssize_t sched_itmt_enabled_write(struct file *filp, + const char __user *ubuf, + size_t cnt, loff_t *ppos) { - unsigned int old_sysctl; - int ret; + ssize_t result; + bool orig; - mutex_lock(&itmt_update_mutex); + guard(mutex)(&itmt_update_mutex); - if (!sched_itmt_capable) { - mutex_unlock(&itmt_update_mutex); - return -EINVAL; - } - - old_sysctl = sysctl_sched_itmt_enabled; - ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + orig = sysctl_sched_itmt_enabled; + result = debugfs_write_file_bool(filp, ubuf, cnt, ppos); - if (!ret && write && old_sysctl != sysctl_sched_itmt_enabled) { + if (sysctl_sched_itmt_enabled != orig) { x86_topology_update = true; rebuild_sched_domains(); } - mutex_unlock(&itmt_update_mutex); - - return ret; + return result; } -static struct ctl_table itmt_kern_table[] = { - { - .procname = "sched_itmt_enabled", - .data = &sysctl_sched_itmt_enabled, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = sched_itmt_update_handler, - .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, - }, +static const struct file_operations dfs_sched_itmt_fops = { + .read = debugfs_read_file_bool, + .write = sched_itmt_enabled_write, + .open = simple_open, + .llseek = default_llseek, }; -static struct ctl_table_header *itmt_sysctl_header; +static struct dentry *dfs_sched_itmt; /** * sched_set_itmt_support() - Indicate platform supports ITMT @@ -97,16 +87,18 @@ static struct ctl_table_header *itmt_sysctl_header; */ int sched_set_itmt_support(void) { - mutex_lock(&itmt_update_mutex); + guard(mutex)(&itmt_update_mutex); - if (sched_itmt_capable) { - mutex_unlock(&itmt_update_mutex); + if (sched_itmt_capable) return 0; - } - itmt_sysctl_header = register_sysctl("kernel", itmt_kern_table); - if (!itmt_sysctl_header) { - mutex_unlock(&itmt_update_mutex); + dfs_sched_itmt = debugfs_create_file_unsafe("sched_itmt_enabled", + 0644, + arch_debugfs_dir, + &sysctl_sched_itmt_enabled, + &dfs_sched_itmt_fops); + if (IS_ERR_OR_NULL(dfs_sched_itmt)) { + dfs_sched_itmt = NULL; return -ENOMEM; } @@ -117,8 +109,6 @@ int sched_set_itmt_support(void) x86_topology_update = true; rebuild_sched_domains(); - mutex_unlock(&itmt_update_mutex); - return 0; } @@ -134,18 +124,15 @@ int sched_set_itmt_support(void) */ void sched_clear_itmt_support(void) { - mutex_lock(&itmt_update_mutex); + guard(mutex)(&itmt_update_mutex); - if (!sched_itmt_capable) { - mutex_unlock(&itmt_update_mutex); + if (!sched_itmt_capable) return; - } + sched_itmt_capable = false; - if (itmt_sysctl_header) { - unregister_sysctl_table(itmt_sysctl_header); - itmt_sysctl_header = NULL; - } + debugfs_remove(dfs_sched_itmt); + dfs_sched_itmt = NULL; if (sysctl_sched_itmt_enabled) { /* disable sched_itmt if we are no longer ITMT capable */ @@ -153,8 +140,6 @@ void sched_clear_itmt_support(void) x86_topology_update = true; rebuild_sched_domains(); } - - mutex_unlock(&itmt_update_mutex); } int arch_asym_cpu_priority(int cpu) diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 21e9e4845354..7a422a6c5983 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -983,7 +983,7 @@ static void __init kvm_init_platform(void) x86_platform.apic_post_init = kvm_apic_init; /* Set WB as the default cache mode for SEV-SNP and TDX */ - mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK); + guest_force_mtrr_state(NULL, 0, MTRR_TYPE_WRBACK); } #if defined(CONFIG_AMD_MEM_ENCRYPT) diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index fec381533555..927e33e6843a 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -116,11 +116,6 @@ static noinstr void pv_native_set_debugreg(int regno, unsigned long val) native_set_debugreg(regno, val); } -noinstr void pv_native_wbinvd(void) -{ - native_wbinvd(); -} - static noinstr void pv_native_safe_halt(void) { native_safe_halt(); @@ -148,7 +143,6 @@ struct paravirt_patch_template pv_ops = { .cpu.read_cr0 = native_read_cr0, .cpu.write_cr0 = native_write_cr0, .cpu.write_cr4 = native_write_cr4, - .cpu.wbinvd = pv_native_wbinvd, .cpu.read_msr = native_read_msr, .cpu.write_msr = native_write_msr, .cpu.read_msr_safe = native_read_msr_safe, diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index f323d83e40a7..6267363e0189 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -108,10 +108,6 @@ void __init pci_iommu_alloc(void) swiotlb_init(x86_swiotlb_enable, x86_swiotlb_flags); } -/* - * See <Documentation/arch/x86/x86_64/boot-options.rst> for the iommu kernel - * parameter documentation. - */ static __init int iommu_setup(char *p) { iommu_merge = 1; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index f63f8fd00a91..6da6769d7254 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -30,6 +30,7 @@ #include <linux/hw_breakpoint.h> #include <linux/entry-common.h> #include <asm/cpu.h> +#include <asm/cpuid.h> #include <asm/apic.h> #include <linux/uaccess.h> #include <asm/mwait.h> @@ -825,7 +826,7 @@ void __noreturn stop_this_cpu(void *dummy) * X86_FEATURE_SME due to cmdline options. */ if (c->extended_cpuid_level >= 0x8000001f && (cpuid_eax(0x8000001f) & BIT(0))) - native_wbinvd(); + wbinvd(); /* * This brings a cache line back and dirties it, but @@ -838,7 +839,7 @@ void __noreturn stop_this_cpu(void *dummy) #ifdef CONFIG_SMP if (smp_ops.stop_this_cpu) { smp_ops.stop_this_cpu(); - unreachable(); + BUG(); } #endif @@ -846,7 +847,7 @@ void __noreturn stop_this_cpu(void *dummy) /* * Use native_halt() so that memory contents don't change * (stack usage and variables) after possibly issuing the - * native_wbinvd() above. + * wbinvd() above. */ native_halt(); } @@ -877,7 +878,7 @@ static __init bool prefer_mwait_c1_over_halt(void) if (boot_cpu_has_bug(X86_BUG_MONITOR) || boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) return false; - cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx); + cpuid(CPUID_LEAF_MWAIT, &eax, &ebx, &ecx, &edx); /* * If MWAIT extensions are not available, it is safe to use MWAIT diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 615922838c51..dc1dd3f3e67f 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -883,7 +883,7 @@ static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) if (smp_ops.stop_this_cpu) { smp_ops.stop_this_cpu(); - unreachable(); + BUG(); } /* Assume hlt works */ diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 1236f25fc8d1..540443d699e3 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -13,6 +13,7 @@ #include <asm/pgtable_types.h> #include <asm/nospec-branch.h> #include <asm/unwind_hints.h> +#include <asm/asm-offsets.h> /* * Must be relocatable PIC code callable as a C function, in particular diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index b5a8f0891135..c10850ae6f09 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -64,6 +64,7 @@ #include <asm/acpi.h> #include <asm/cacheinfo.h> +#include <asm/cpuid.h> #include <asm/desc.h> #include <asm/nmi.h> #include <asm/irq.h> @@ -482,12 +483,6 @@ static int x86_core_flags(void) return cpu_core_flags() | x86_sched_itmt_flags(); } #endif -#ifdef CONFIG_SCHED_SMT -static int x86_smt_flags(void) -{ - return cpu_smt_flags(); -} -#endif #ifdef CONFIG_SCHED_CLUSTER static int x86_cluster_flags(void) { @@ -495,15 +490,6 @@ static int x86_cluster_flags(void) } #endif -static int x86_die_flags(void) -{ - if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU) || - cpu_feature_enabled(X86_FEATURE_AMD_HETEROGENEOUS_CORES)) - return x86_sched_itmt_flags(); - - return 0; -} - /* * Set if a package/die has multiple NUMA nodes inside. * AMD Magny-Cours, Intel Cluster-on-Die, and Intel @@ -519,7 +505,7 @@ static void __init build_sched_topology(void) #ifdef CONFIG_SCHED_SMT x86_topology[i++] = (struct sched_domain_topology_level){ - cpu_smt_mask, x86_smt_flags, SD_INIT_NAME(SMT) + cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }; #endif #ifdef CONFIG_SCHED_CLUSTER @@ -539,7 +525,7 @@ static void __init build_sched_topology(void) */ if (!x86_has_numa_in_package) { x86_topology[i++] = (struct sched_domain_topology_level){ - cpu_cpu_mask, x86_die_flags, SD_INIT_NAME(PKG) + cpu_cpu_mask, x86_sched_itmt_flags, SD_INIT_NAME(PKG) }; } @@ -1291,10 +1277,8 @@ static inline void mwait_play_dead(void) return; if (!this_cpu_has(X86_FEATURE_CLFLUSH)) return; - if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF) - return; - eax = CPUID_MWAIT_LEAF; + eax = CPUID_LEAF_MWAIT; ecx = 0; native_cpuid(&eax, &ebx, &ecx, &edx); diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 4eefaac64c6c..9e51242ed125 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -172,6 +172,14 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) } EXPORT_SYMBOL_GPL(arch_static_call_transform); +noinstr void __static_call_update_early(void *tramp, void *func) +{ + BUG_ON(system_state != SYSTEM_BOOTING); + BUG_ON(static_call_initialized); + __text_gen_insn(tramp, JMP32_INSN_OPCODE, tramp, func, JMP32_INSN_SIZE); + sync_core(); +} + #ifdef CONFIG_MITIGATION_RETHUNK /* * This is called by apply_returns() to fix up static call trampolines, diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 67aeaba4ba9c..34dec0b72ea8 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -16,6 +16,7 @@ #include <linux/static_key.h> #include <linux/static_call.h> +#include <asm/cpuid.h> #include <asm/hpet.h> #include <asm/timer.h> #include <asm/vgtod.h> @@ -30,6 +31,7 @@ #include <asm/i8259.h> #include <asm/topology.h> #include <asm/uv/uv.h> +#include <asm/sev.h> unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -665,13 +667,13 @@ unsigned long native_calibrate_tsc(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 0; - if (boot_cpu_data.cpuid_level < 0x15) + if (boot_cpu_data.cpuid_level < CPUID_LEAF_TSC) return 0; eax_denominator = ebx_numerator = ecx_hz = edx = 0; /* CPUID 15H TSC/Crystal ratio, plus optionally Crystal Hz */ - cpuid(0x15, &eax_denominator, &ebx_numerator, &ecx_hz, &edx); + cpuid(CPUID_LEAF_TSC, &eax_denominator, &ebx_numerator, &ecx_hz, &edx); if (ebx_numerator == 0 || eax_denominator == 0) return 0; @@ -680,8 +682,8 @@ unsigned long native_calibrate_tsc(void) /* * Denverton SoCs don't report crystal clock, and also don't support - * CPUID.0x16 for the calculation below, so hardcode the 25MHz crystal - * clock. + * CPUID_LEAF_FREQ for the calculation below, so hardcode the 25MHz + * crystal clock. */ if (crystal_khz == 0 && boot_cpu_data.x86_vfm == INTEL_ATOM_GOLDMONT_D) @@ -700,10 +702,10 @@ unsigned long native_calibrate_tsc(void) * clock, but we can easily calculate it to a high degree of accuracy * by considering the crystal ratio and the CPU speed. */ - if (crystal_khz == 0 && boot_cpu_data.cpuid_level >= 0x16) { + if (crystal_khz == 0 && boot_cpu_data.cpuid_level >= CPUID_LEAF_FREQ) { unsigned int eax_base_mhz, ebx, ecx, edx; - cpuid(0x16, &eax_base_mhz, &ebx, &ecx, &edx); + cpuid(CPUID_LEAF_FREQ, &eax_base_mhz, &ebx, &ecx, &edx); crystal_khz = eax_base_mhz * 1000 * eax_denominator / ebx_numerator; } @@ -738,12 +740,12 @@ static unsigned long cpu_khz_from_cpuid(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 0; - if (boot_cpu_data.cpuid_level < 0x16) + if (boot_cpu_data.cpuid_level < CPUID_LEAF_FREQ) return 0; eax_base_mhz = ebx_max_mhz = ecx_bus_mhz = edx = 0; - cpuid(0x16, &eax_base_mhz, &ebx_max_mhz, &ecx_bus_mhz, &edx); + cpuid(CPUID_LEAF_FREQ, &eax_base_mhz, &ebx_max_mhz, &ecx_bus_mhz, &edx); return eax_base_mhz * 1000; } @@ -1067,10 +1069,8 @@ core_initcall(cpufreq_register_tsc_scaling); #endif /* CONFIG_CPU_FREQ */ -#define ART_CPUID_LEAF (0x15) #define ART_MIN_DENOMINATOR (1) - /* * If ART is present detect the numerator:denominator to convert to TSC */ @@ -1078,7 +1078,7 @@ static void __init detect_art(void) { unsigned int unused; - if (boot_cpu_data.cpuid_level < ART_CPUID_LEAF) + if (boot_cpu_data.cpuid_level < CPUID_LEAF_TSC) return; /* @@ -1091,7 +1091,7 @@ static void __init detect_art(void) tsc_async_resets) return; - cpuid(ART_CPUID_LEAF, &art_base_clk.denominator, + cpuid(CPUID_LEAF_TSC, &art_base_clk.denominator, &art_base_clk.numerator, &art_base_clk.freq_khz, &unused); art_base_clk.freq_khz /= KHZ; @@ -1515,6 +1515,9 @@ void __init tsc_early_init(void) /* Don't change UV TSC multi-chassis synchronization */ if (is_early_uv_system()) return; + + snp_secure_tsc_init(); + if (!determine_cpu_tsc_frequencies(true)) return; tsc_enable_sched_clock(); diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index fab3ac9a4574..6a17396c8174 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -519,14 +519,10 @@ INIT_PER_CPU(irq_stack_backing_store); * linker will never mark as relocatable. (Using just ABSOLUTE() is not * sufficient for that). */ -#ifdef CONFIG_XEN #ifdef CONFIG_XEN_PV xen_elfnote_entry_value = ABSOLUTE(xen_elfnote_entry) + ABSOLUTE(startup_xen); #endif -xen_elfnote_hypercall_page_value = - ABSOLUTE(xen_elfnote_hypercall_page) + ABSOLUTE(hypercall_page); -#endif #ifdef CONFIG_PVH xen_elfnote_phys32_entry_value = ABSOLUTE(xen_elfnote_phys32_entry) + ABSOLUTE(pvh_start_xen - LOAD_OFFSET); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 097bdc022d0f..f7e222953cab 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -36,6 +36,26 @@ u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly; EXPORT_SYMBOL_GPL(kvm_cpu_caps); +struct cpuid_xstate_sizes { + u32 eax; + u32 ebx; + u32 ecx; +}; + +static struct cpuid_xstate_sizes xstate_sizes[XFEATURE_MAX] __ro_after_init; + +void __init kvm_init_xstate_sizes(void) +{ + u32 ign; + int i; + + for (i = XFEATURE_YMM; i < ARRAY_SIZE(xstate_sizes); i++) { + struct cpuid_xstate_sizes *xs = &xstate_sizes[i]; + + cpuid_count(0xD, i, &xs->eax, &xs->ebx, &xs->ecx, &ign); + } +} + u32 xstate_required_size(u64 xstate_bv, bool compacted) { int feature_bit = 0; @@ -44,14 +64,15 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted) xstate_bv &= XFEATURE_MASK_EXTEND; while (xstate_bv) { if (xstate_bv & 0x1) { - u32 eax, ebx, ecx, edx, offset; - cpuid_count(0xD, feature_bit, &eax, &ebx, &ecx, &edx); + struct cpuid_xstate_sizes *xs = &xstate_sizes[feature_bit]; + u32 offset; + /* ECX[1]: 64B alignment in compacted form */ if (compacted) - offset = (ecx & 0x2) ? ALIGN(ret, 64) : ret; + offset = (xs->ecx & 0x2) ? ALIGN(ret, 64) : ret; else - offset = ebx; - ret = max(ret, offset + eax); + offset = xs->ebx; + ret = max(ret, offset + xs->eax); } xstate_bv >>= 1; @@ -800,7 +821,7 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_mask(CPUID_8000_0021_EAX, F(NO_NESTED_DATA_BP) | F(LFENCE_RDTSC) | 0 /* SmmPgCfgLock */ | F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ | - F(WRMSR_XX_BASE_NS) + F(WRMSR_XX_BASE_NS) | F(SRSO_USER_KERNEL_NO) ); kvm_cpu_cap_check_and_set(X86_FEATURE_SBPB); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index c8dc66eddefd..f16a7b2c2adc 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -31,6 +31,7 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, bool exact_only); +void __init kvm_init_xstate_sizes(void); u32 xstate_required_size(u64 xstate_bv, bool compacted); int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 22e7ad235123..2401606db260 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3364,18 +3364,6 @@ static bool fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, return true; } -static bool is_access_allowed(struct kvm_page_fault *fault, u64 spte) -{ - if (fault->exec) - return is_executable_pte(spte); - - if (fault->write) - return is_writable_pte(spte); - - /* Fault was on Read access */ - return spte & PT_PRESENT_MASK; -} - /* * Returns the last level spte pointer of the shadow page walk for the given * gpa, and sets *spte to the spte value. This spte may be non-preset. If no diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index f332b33bc817..af10bc0380a3 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -462,6 +462,23 @@ static inline bool is_mmu_writable_spte(u64 spte) } /* + * Returns true if the access indicated by @fault is allowed by the existing + * SPTE protections. Note, the caller is responsible for checking that the + * SPTE is a shadow-present, leaf SPTE (either before or after). + */ +static inline bool is_access_allowed(struct kvm_page_fault *fault, u64 spte) +{ + if (fault->exec) + return is_executable_pte(spte); + + if (fault->write) + return is_writable_pte(spte); + + /* Fault was on Read access */ + return spte & PT_PRESENT_MASK; +} + +/* * If the MMU-writable flag is cleared, i.e. the SPTE is write-protected for * write-tracking, remote TLBs must be flushed, even if the SPTE was read-only, * as KVM allows stale Writable TLB entries to exist. When dirty logging, KVM diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 4508d868f1cd..2f15e0e33903 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -985,6 +985,11 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, if (fault->prefetch && is_shadow_present_pte(iter->old_spte)) return RET_PF_SPURIOUS; + if (is_shadow_present_pte(iter->old_spte) && + is_access_allowed(fault, iter->old_spte) && + is_last_spte(iter->old_spte, iter->level)) + return RET_PF_SPURIOUS; + if (unlikely(!fault->slot)) new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL); else diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 4b74ea91f4e6..65fd245a9953 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -1199,6 +1199,12 @@ bool avic_hardware_setup(void) return false; } + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP) && + !boot_cpu_has(X86_FEATURE_HV_INUSE_WR_ALLOWED)) { + pr_warn("AVIC disabled: missing HvInUseWrAllowed on SNP-enabled system\n"); + return false; + } + if (boot_cpu_has(X86_FEATURE_AVIC)) { pr_info("AVIC enabled\n"); } else if (force_avic) { diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 943bd074a5d3..fe6cc763fd51 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -3820,7 +3820,7 @@ next_range: goto next_range; } - unreachable(); + BUG(); } static int __sev_snp_update_protected_guest_state(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index dd15cc635655..21dacd312779 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3201,15 +3201,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) if (data & ~supported_de_cfg) return 1; - /* - * Don't let the guest change the host-programmed value. The - * MSR is very model specific, i.e. contains multiple bits that - * are completely unknown to KVM, and the one bit known to KVM - * is simply a reflection of hardware capabilities. - */ - if (!msr->host_initiated && data != svm->msr_decfg) - return 1; - svm->msr_decfg = data; break; } diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h index 1715d2ab07be..ad9116a99bcc 100644 --- a/arch/x86/kvm/vmx/posted_intr.h +++ b/arch/x86/kvm/vmx/posted_intr.h @@ -2,7 +2,7 @@ #ifndef __KVM_X86_VMX_POSTED_INTR_H #define __KVM_X86_VMX_POSTED_INTR_H -#include <linux/find.h> +#include <linux/bitmap.h> #include <asm/posted_intr.h> void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2e713480933a..c79a8cc57ba4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9976,7 +9976,7 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu) { u64 ret = vcpu->run->hypercall.ret; - if (!is_64_bit_mode(vcpu)) + if (!is_64_bit_hypercall(vcpu)) ret = (u32)ret; kvm_rax_write(vcpu, ret); ++vcpu->stat.hypercalls; @@ -12724,6 +12724,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_hv_init_vm(kvm); kvm_xen_init_vm(kvm); + if (ignore_msrs && !report_ignored_msrs) { + pr_warn_once("Running KVM with ignore_msrs=1 and report_ignored_msrs=0 is not a\n" + "a supported configuration. Lying to the guest about the existence of MSRs\n" + "may cause the guest operating system to hang or produce errors. If a guest\n" + "does not run without ignore_msrs=1, please report it to kvm@vger.kernel.org.\n"); + } + return 0; out_uninit_mmu: @@ -13997,6 +14004,8 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_rmp_fault); static int __init kvm_x86_init(void) { + kvm_init_xstate_sizes(); + kvm_mmu_x86_module_init(); mitigate_smt_rsb &= boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible(); return 0; diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 4357ec2a0bfc..89ecd57c9d42 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -44,9 +44,8 @@ .pushsection runtime_ptr_USER_PTR_MAX,"a" .long 1b - 8 - . .popsection - cmp %rax, %rdx - sbb %rdx, %rdx - or %rdx, %rax + cmp %rdx, %rax + cmova %rdx, %rax .else cmp $TASK_SIZE_MAX-\size+1, %eax jae .Lbad_get_user diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e6c469b323cc..ac52255fab01 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -678,7 +678,7 @@ page_fault_oops(struct pt_regs *regs, unsigned long error_code, ASM_CALL_ARG3, , [arg1] "r" (regs), [arg2] "r" (address), [arg3] "r" (&info)); - unreachable(); + BUG(); } #endif diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index c6d29f283001..62aa4d66a032 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -1080,7 +1080,8 @@ struct execmem_info __init *execmem_arch_setup(void) start = MODULES_VADDR + offset; - if (IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX)) { + if (IS_ENABLED(CONFIG_ARCH_HAS_EXECMEM_ROX) && + cpu_feature_enabled(X86_FEATURE_PSE)) { pgprot = PAGE_KERNEL_ROX; flags = EXECMEM_KASAN_SHADOW | EXECMEM_ROX_CACHE; } else { diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 8d29163568a7..38ff7791a9c7 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -593,8 +593,7 @@ static bool memremap_should_map_decrypted(resource_size_t phys_addr, * Examine the physical address to determine if it is EFI data. Check * it against the boot params structure and EFI tables and memory types. */ -static bool memremap_is_efi_data(resource_size_t phys_addr, - unsigned long size) +static bool memremap_is_efi_data(resource_size_t phys_addr) { u64 paddr; @@ -632,42 +631,54 @@ static bool memremap_is_efi_data(resource_size_t phys_addr, * Examine the physical address to determine if it is boot data by checking * it against the boot params setup_data chain. */ -static bool memremap_is_setup_data(resource_size_t phys_addr, - unsigned long size) +static bool __ref __memremap_is_setup_data(resource_size_t phys_addr, bool early) { + unsigned int setup_data_sz = sizeof(struct setup_data); struct setup_indirect *indirect; struct setup_data *data; u64 paddr, paddr_next; paddr = boot_params.hdr.setup_data; while (paddr) { - unsigned int len; + unsigned int len, size; if (phys_addr == paddr) return true; - data = memremap(paddr, sizeof(*data), - MEMREMAP_WB | MEMREMAP_DEC); + if (early) + data = early_memremap_decrypted(paddr, setup_data_sz); + else + data = memremap(paddr, setup_data_sz, MEMREMAP_WB | MEMREMAP_DEC); if (!data) { - pr_warn("failed to memremap setup_data entry\n"); + pr_warn("failed to remap setup_data entry\n"); return false; } + size = setup_data_sz; + paddr_next = data->next; len = data->len; if ((phys_addr > paddr) && - (phys_addr < (paddr + sizeof(struct setup_data) + len))) { - memunmap(data); + (phys_addr < (paddr + setup_data_sz + len))) { + if (early) + early_memunmap(data, setup_data_sz); + else + memunmap(data); return true; } if (data->type == SETUP_INDIRECT) { - memunmap(data); - data = memremap(paddr, sizeof(*data) + len, - MEMREMAP_WB | MEMREMAP_DEC); + size += len; + if (early) { + early_memunmap(data, setup_data_sz); + data = early_memremap_decrypted(paddr, size); + } else { + memunmap(data); + data = memremap(paddr, size, MEMREMAP_WB | MEMREMAP_DEC); + } if (!data) { - pr_warn("failed to memremap indirect setup_data\n"); + pr_warn("failed to remap indirect setup_data\n"); return false; } @@ -679,7 +690,10 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, } } - memunmap(data); + if (early) + early_memunmap(data, size); + else + memunmap(data); if ((phys_addr > paddr) && (phys_addr < (paddr + len))) return true; @@ -690,67 +704,14 @@ static bool memremap_is_setup_data(resource_size_t phys_addr, return false; } -/* - * Examine the physical address to determine if it is boot data by checking - * it against the boot params setup_data chain (early boot version). - */ -static bool __init early_memremap_is_setup_data(resource_size_t phys_addr, - unsigned long size) +static bool memremap_is_setup_data(resource_size_t phys_addr) { - struct setup_indirect *indirect; - struct setup_data *data; - u64 paddr, paddr_next; - - paddr = boot_params.hdr.setup_data; - while (paddr) { - unsigned int len, size; - - if (phys_addr == paddr) - return true; - - data = early_memremap_decrypted(paddr, sizeof(*data)); - if (!data) { - pr_warn("failed to early memremap setup_data entry\n"); - return false; - } - - size = sizeof(*data); - - paddr_next = data->next; - len = data->len; - - if ((phys_addr > paddr) && - (phys_addr < (paddr + sizeof(struct setup_data) + len))) { - early_memunmap(data, sizeof(*data)); - return true; - } - - if (data->type == SETUP_INDIRECT) { - size += len; - early_memunmap(data, sizeof(*data)); - data = early_memremap_decrypted(paddr, size); - if (!data) { - pr_warn("failed to early memremap indirect setup_data\n"); - return false; - } - - indirect = (struct setup_indirect *)data->data; - - if (indirect->type != SETUP_INDIRECT) { - paddr = indirect->addr; - len = indirect->len; - } - } - - early_memunmap(data, size); - - if ((phys_addr > paddr) && (phys_addr < (paddr + len))) - return true; - - paddr = paddr_next; - } + return __memremap_is_setup_data(phys_addr, false); +} - return false; +static bool __init early_memremap_is_setup_data(resource_size_t phys_addr) +{ + return __memremap_is_setup_data(phys_addr, true); } /* @@ -771,8 +732,8 @@ bool arch_memremap_can_ram_remap(resource_size_t phys_addr, unsigned long size, return false; if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { - if (memremap_is_setup_data(phys_addr, size) || - memremap_is_efi_data(phys_addr, size)) + if (memremap_is_setup_data(phys_addr) || + memremap_is_efi_data(phys_addr)) return false; } @@ -797,8 +758,8 @@ pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr, encrypted_prot = true; if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { - if (early_memremap_is_setup_data(phys_addr, size) || - memremap_is_efi_data(phys_addr, size)) + if (early_memremap_is_setup_data(phys_addr) || + memremap_is_efi_data(phys_addr)) encrypted_prot = false; } diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 0a120d85d7bb..95bae74fdab2 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -94,6 +94,8 @@ void __init mem_encrypt_init(void) /* Call into SWIOTLB to update the SWIOTLB DMA buffers */ swiotlb_update_mem_attributes(); + snp_secure_tsc_prepare(); + print_mem_encrypt_feature_info(); } diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 774f9677458f..b56c5c073003 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -541,6 +541,9 @@ void __init sme_early_init(void) * kernel mapped. */ snp_update_svsm_ca(); + + if (sev_status & MSR_AMD64_SNP_SECURE_TSC) + setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); } void __init mem_encrypt_free_decrypted_mem(void) diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 0681ecfe3430..592fb9d97e77 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -9,7 +9,7 @@ #include <linux/pci.h> #include <linux/suspend.h> #include <linux/vgaarb.h> -#include <asm/amd_nb.h> +#include <asm/amd_node.h> #include <asm/hpet.h> #include <asm/pci_x86.h> @@ -828,7 +828,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7910, rs690_fix_64bit_dma); #endif -#ifdef CONFIG_AMD_NB +#ifdef CONFIG_AMD_NODE #define AMD_15B8_RCC_DEV2_EPF0_STRAP2 0x10136008 #define AMD_15B8_RCC_DEV2_EPF0_STRAP2_NO_SOFT_RESET_DEV2_F0_MASK 0x00000080L diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index a379501b7a69..4f200ac96ce0 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -92,8 +92,6 @@ static int uv_domain_alloc(struct irq_domain *domain, unsigned int virq, if (ret >= 0) { if (info->uv.limit == UV_AFFINITY_CPU) irq_set_status_flags(virq, IRQ_NO_BALANCING); - else - irq_set_status_flags(virq, IRQ_MOVE_PCNTXT); chip_data->pnode = uv_blade_to_pnode(info->uv.blade); chip_data->offset = info->uv.offset; @@ -113,7 +111,6 @@ static void uv_domain_free(struct irq_domain *domain, unsigned int virq, BUG_ON(nr_irqs != 1); kfree(irq_data->chip_data); - irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT); irq_clear_status_flags(virq, IRQ_NO_BALANCING); irq_domain_free_irqs_top(domain, virq, nr_irqs); } diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c index 9a6a943d8e41..1dcc027ec77e 100644 --- a/arch/x86/virt/svm/sev.c +++ b/arch/x86/virt/svm/sev.c @@ -18,6 +18,7 @@ #include <linux/cpumask.h> #include <linux/iommu.h> #include <linux/amd-iommu.h> +#include <linux/nospec.h> #include <asm/sev.h> #include <asm/processor.h> @@ -31,10 +32,29 @@ #include <asm/iommu.h> /* - * The RMP entry format is not architectural. The format is defined in PPR - * Family 19h Model 01h, Rev B1 processor. + * The RMP entry information as returned by the RMPREAD instruction. */ struct rmpentry { + u64 gpa; + u8 assigned :1, + rsvd1 :7; + u8 pagesize :1, + hpage_region_status :1, + rsvd2 :6; + u8 immutable :1, + rsvd3 :7; + u8 rsvd4; + u32 asid; +} __packed; + +/* + * The raw RMP entry format is not architectural. The format is defined in PPR + * Family 19h Model 01h, Rev B1 processor. This format represents the actual + * entry in the RMP table memory. The bitfield definitions are used for machines + * without the RMPREAD instruction (Zen3 and Zen4), otherwise the "hi" and "lo" + * fields are only used for dumping the raw data. + */ +struct rmpentry_raw { union { struct { u64 assigned : 1, @@ -58,12 +78,48 @@ struct rmpentry { */ #define RMPTABLE_CPU_BOOKKEEPING_SZ 0x4000 +/* + * For a non-segmented RMP table, use the maximum physical addressing as the + * segment size in order to always arrive at index 0 in the table. + */ +#define RMPTABLE_NON_SEGMENTED_SHIFT 52 + +struct rmp_segment_desc { + struct rmpentry_raw *rmp_entry; + u64 max_index; + u64 size; +}; + +/* + * Segmented RMP Table support. + * - The segment size is used for two purposes: + * - Identify the amount of memory covered by an RMP segment + * - Quickly locate an RMP segment table entry for a physical address + * + * - The RMP segment table contains pointers to an RMP table that covers + * a specific portion of memory. There can be up to 512 8-byte entries, + * one pages worth. + */ +#define RST_ENTRY_MAPPED_SIZE(x) ((x) & GENMASK_ULL(19, 0)) +#define RST_ENTRY_SEGMENT_BASE(x) ((x) & GENMASK_ULL(51, 20)) + +#define RST_SIZE SZ_4K +static struct rmp_segment_desc **rmp_segment_table __ro_after_init; +static unsigned int rst_max_index __ro_after_init = 512; + +static unsigned int rmp_segment_shift; +static u64 rmp_segment_size; +static u64 rmp_segment_mask; + +#define RST_ENTRY_INDEX(x) ((x) >> rmp_segment_shift) +#define RMP_ENTRY_INDEX(x) ((u64)(PHYS_PFN((x) & rmp_segment_mask))) + +static u64 rmp_cfg; + /* Mask to apply to a PFN to get the first PFN of a 2MB page */ #define PFN_PMD_MASK GENMASK_ULL(63, PMD_SHIFT - PAGE_SHIFT) static u64 probed_rmp_base, probed_rmp_size; -static struct rmpentry *rmptable __ro_after_init; -static u64 rmptable_max_pfn __ro_after_init; static LIST_HEAD(snp_leaked_pages_list); static DEFINE_SPINLOCK(snp_leaked_pages_list_lock); @@ -116,36 +172,6 @@ static __init void snp_enable(void *arg) __snp_enable(smp_processor_id()); } -#define RMP_ADDR_MASK GENMASK_ULL(51, 13) - -bool snp_probe_rmptable_info(void) -{ - u64 rmp_sz, rmp_base, rmp_end; - - rdmsrl(MSR_AMD64_RMP_BASE, rmp_base); - rdmsrl(MSR_AMD64_RMP_END, rmp_end); - - if (!(rmp_base & RMP_ADDR_MASK) || !(rmp_end & RMP_ADDR_MASK)) { - pr_err("Memory for the RMP table has not been reserved by BIOS\n"); - return false; - } - - if (rmp_base > rmp_end) { - pr_err("RMP configuration not valid: base=%#llx, end=%#llx\n", rmp_base, rmp_end); - return false; - } - - rmp_sz = rmp_end - rmp_base + 1; - - probed_rmp_base = rmp_base; - probed_rmp_size = rmp_sz; - - pr_info("RMP table physical range [0x%016llx - 0x%016llx]\n", - rmp_base, rmp_end); - - return true; -} - static void __init __snp_fixup_e820_tables(u64 pa) { if (IS_ALIGNED(pa, PMD_SIZE)) @@ -178,35 +204,176 @@ static void __init __snp_fixup_e820_tables(u64 pa) } } -void __init snp_fixup_e820_tables(void) +static void __init fixup_e820_tables_for_segmented_rmp(void) +{ + u64 pa, *rst, size, mapped_size; + unsigned int i; + + __snp_fixup_e820_tables(probed_rmp_base); + + pa = probed_rmp_base + RMPTABLE_CPU_BOOKKEEPING_SZ; + + __snp_fixup_e820_tables(pa + RST_SIZE); + + rst = early_memremap(pa, RST_SIZE); + if (!rst) + return; + + for (i = 0; i < rst_max_index; i++) { + pa = RST_ENTRY_SEGMENT_BASE(rst[i]); + mapped_size = RST_ENTRY_MAPPED_SIZE(rst[i]); + if (!mapped_size) + continue; + + __snp_fixup_e820_tables(pa); + + /* + * Mapped size in GB. Mapped size is allowed to exceed + * the segment coverage size, but gets reduced to the + * segment coverage size. + */ + mapped_size <<= 30; + if (mapped_size > rmp_segment_size) + mapped_size = rmp_segment_size; + + /* Calculate the RMP segment size (16 bytes/page mapped) */ + size = PHYS_PFN(mapped_size) << 4; + + __snp_fixup_e820_tables(pa + size); + } + + early_memunmap(rst, RST_SIZE); +} + +static void __init fixup_e820_tables_for_contiguous_rmp(void) { __snp_fixup_e820_tables(probed_rmp_base); __snp_fixup_e820_tables(probed_rmp_base + probed_rmp_size); } -/* - * Do the necessary preparations which are verified by the firmware as - * described in the SNP_INIT_EX firmware command description in the SNP - * firmware ABI spec. - */ -static int __init snp_rmptable_init(void) +void __init snp_fixup_e820_tables(void) { - u64 max_rmp_pfn, calc_rmp_sz, rmptable_size, rmp_end, val; - void *rmptable_start; + if (rmp_cfg & MSR_AMD64_SEG_RMP_ENABLED) { + fixup_e820_tables_for_segmented_rmp(); + } else { + fixup_e820_tables_for_contiguous_rmp(); + } +} - if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) - return 0; +static bool __init clear_rmptable_bookkeeping(void) +{ + void *bk; - if (!amd_iommu_snp_en) - goto nosnp; + bk = memremap(probed_rmp_base, RMPTABLE_CPU_BOOKKEEPING_SZ, MEMREMAP_WB); + if (!bk) { + pr_err("Failed to map RMP bookkeeping area\n"); + return false; + } + + memset(bk, 0, RMPTABLE_CPU_BOOKKEEPING_SZ); + + memunmap(bk); + + return true; +} + +static bool __init alloc_rmp_segment_desc(u64 segment_pa, u64 segment_size, u64 pa) +{ + u64 rst_index, rmp_segment_size_max; + struct rmp_segment_desc *desc; + void *rmp_segment; + + /* Calculate the maximum size an RMP can be (16 bytes/page mapped) */ + rmp_segment_size_max = PHYS_PFN(rmp_segment_size) << 4; + + /* Validate the RMP segment size */ + if (segment_size > rmp_segment_size_max) { + pr_err("Invalid RMP size 0x%llx for configured segment size 0x%llx\n", + segment_size, rmp_segment_size_max); + return false; + } + + /* Validate the RMP segment table index */ + rst_index = RST_ENTRY_INDEX(pa); + if (rst_index >= rst_max_index) { + pr_err("Invalid RMP segment base address 0x%llx for configured segment size 0x%llx\n", + pa, rmp_segment_size); + return false; + } + + if (rmp_segment_table[rst_index]) { + pr_err("RMP segment descriptor already exists at index %llu\n", rst_index); + return false; + } + + rmp_segment = memremap(segment_pa, segment_size, MEMREMAP_WB); + if (!rmp_segment) { + pr_err("Failed to map RMP segment addr 0x%llx size 0x%llx\n", + segment_pa, segment_size); + return false; + } + + desc = kzalloc(sizeof(*desc), GFP_KERNEL); + if (!desc) { + memunmap(rmp_segment); + return false; + } + + desc->rmp_entry = rmp_segment; + desc->max_index = segment_size / sizeof(*desc->rmp_entry); + desc->size = segment_size; + + rmp_segment_table[rst_index] = desc; + + return true; +} + +static void __init free_rmp_segment_table(void) +{ + unsigned int i; + + for (i = 0; i < rst_max_index; i++) { + struct rmp_segment_desc *desc; + + desc = rmp_segment_table[i]; + if (!desc) + continue; + + memunmap(desc->rmp_entry); + + kfree(desc); + } + + free_page((unsigned long)rmp_segment_table); + + rmp_segment_table = NULL; +} + +/* Allocate the table used to index into the RMP segments */ +static bool __init alloc_rmp_segment_table(void) +{ + struct page *page; + + page = alloc_page(__GFP_ZERO); + if (!page) + return false; + + rmp_segment_table = page_address(page); + + return true; +} + +static bool __init setup_contiguous_rmptable(void) +{ + u64 max_rmp_pfn, calc_rmp_sz, rmptable_segment, rmptable_size, rmp_end; if (!probed_rmp_size) - goto nosnp; + return false; rmp_end = probed_rmp_base + probed_rmp_size - 1; /* - * Calculate the amount the memory that must be reserved by the BIOS to + * Calculate the amount of memory that must be reserved by the BIOS to * address the whole RAM, including the bookkeeping area. The RMP itself * must also be covered. */ @@ -218,15 +385,140 @@ static int __init snp_rmptable_init(void) if (calc_rmp_sz > probed_rmp_size) { pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n", calc_rmp_sz, probed_rmp_size); - goto nosnp; + return false; } - rmptable_start = memremap(probed_rmp_base, probed_rmp_size, MEMREMAP_WB); - if (!rmptable_start) { - pr_err("Failed to map RMP table\n"); - goto nosnp; + if (!alloc_rmp_segment_table()) + return false; + + /* Map only the RMP entries */ + rmptable_segment = probed_rmp_base + RMPTABLE_CPU_BOOKKEEPING_SZ; + rmptable_size = probed_rmp_size - RMPTABLE_CPU_BOOKKEEPING_SZ; + + if (!alloc_rmp_segment_desc(rmptable_segment, rmptable_size, 0)) { + free_rmp_segment_table(); + return false; } + return true; +} + +static bool __init setup_segmented_rmptable(void) +{ + u64 rst_pa, *rst, pa, ram_pa_end, ram_pa_max; + unsigned int i, max_index; + + if (!probed_rmp_base) + return false; + + if (!alloc_rmp_segment_table()) + return false; + + rst_pa = probed_rmp_base + RMPTABLE_CPU_BOOKKEEPING_SZ; + rst = memremap(rst_pa, RST_SIZE, MEMREMAP_WB); + if (!rst) { + pr_err("Failed to map RMP segment table addr 0x%llx\n", rst_pa); + goto e_free; + } + + pr_info("Segmented RMP using %lluGB segments\n", rmp_segment_size >> 30); + + ram_pa_max = max_pfn << PAGE_SHIFT; + + max_index = 0; + ram_pa_end = 0; + for (i = 0; i < rst_max_index; i++) { + u64 rmp_segment, rmp_size, mapped_size; + + mapped_size = RST_ENTRY_MAPPED_SIZE(rst[i]); + if (!mapped_size) + continue; + + max_index = i; + + /* + * Mapped size in GB. Mapped size is allowed to exceed the + * segment coverage size, but gets reduced to the segment + * coverage size. + */ + mapped_size <<= 30; + if (mapped_size > rmp_segment_size) { + pr_info("RMP segment %u mapped size (0x%llx) reduced to 0x%llx\n", + i, mapped_size, rmp_segment_size); + mapped_size = rmp_segment_size; + } + + rmp_segment = RST_ENTRY_SEGMENT_BASE(rst[i]); + + /* Calculate the RMP segment size (16 bytes/page mapped) */ + rmp_size = PHYS_PFN(mapped_size) << 4; + + pa = (u64)i << rmp_segment_shift; + + /* + * Some segments may be for MMIO mapped above system RAM. These + * segments are used for Trusted I/O. + */ + if (pa < ram_pa_max) + ram_pa_end = pa + mapped_size; + + if (!alloc_rmp_segment_desc(rmp_segment, rmp_size, pa)) + goto e_unmap; + + pr_info("RMP segment %u physical address [0x%llx - 0x%llx] covering [0x%llx - 0x%llx]\n", + i, rmp_segment, rmp_segment + rmp_size - 1, pa, pa + mapped_size - 1); + } + + if (ram_pa_max > ram_pa_end) { + pr_err("Segmented RMP does not cover full system RAM (expected 0x%llx got 0x%llx)\n", + ram_pa_max, ram_pa_end); + goto e_unmap; + } + + /* Adjust the maximum index based on the found segments */ + rst_max_index = max_index + 1; + + memunmap(rst); + + return true; + +e_unmap: + memunmap(rst); + +e_free: + free_rmp_segment_table(); + + return false; +} + +static bool __init setup_rmptable(void) +{ + if (rmp_cfg & MSR_AMD64_SEG_RMP_ENABLED) { + return setup_segmented_rmptable(); + } else { + return setup_contiguous_rmptable(); + } +} + +/* + * Do the necessary preparations which are verified by the firmware as + * described in the SNP_INIT_EX firmware command description in the SNP + * firmware ABI spec. + */ +static int __init snp_rmptable_init(void) +{ + unsigned int i; + u64 val; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return 0; + + if (!amd_iommu_snp_en) + goto nosnp; + + if (!setup_rmptable()) + goto nosnp; + /* * Check if SEV-SNP is already enabled, this can happen in case of * kexec boot. @@ -235,7 +527,22 @@ static int __init snp_rmptable_init(void) if (val & MSR_AMD64_SYSCFG_SNP_EN) goto skip_enable; - memset(rmptable_start, 0, probed_rmp_size); + /* Zero out the RMP bookkeeping area */ + if (!clear_rmptable_bookkeeping()) { + free_rmp_segment_table(); + goto nosnp; + } + + /* Zero out the RMP entries */ + for (i = 0; i < rst_max_index; i++) { + struct rmp_segment_desc *desc; + + desc = rmp_segment_table[i]; + if (!desc) + continue; + + memset(desc->rmp_entry, 0, desc->size); + } /* Flush the caches to ensure that data is written before SNP is enabled. */ wbinvd_on_all_cpus(); @@ -246,12 +553,6 @@ static int __init snp_rmptable_init(void) on_each_cpu(snp_enable, NULL, 1); skip_enable: - rmptable_start += RMPTABLE_CPU_BOOKKEEPING_SZ; - rmptable_size = probed_rmp_size - RMPTABLE_CPU_BOOKKEEPING_SZ; - - rmptable = (struct rmpentry *)rmptable_start; - rmptable_max_pfn = rmptable_size / sizeof(struct rmpentry) - 1; - cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/rmptable_init:online", __snp_enable, NULL); /* @@ -272,48 +573,212 @@ nosnp: */ device_initcall(snp_rmptable_init); -static struct rmpentry *get_rmpentry(u64 pfn) +static void set_rmp_segment_info(unsigned int segment_shift) +{ + rmp_segment_shift = segment_shift; + rmp_segment_size = 1ULL << rmp_segment_shift; + rmp_segment_mask = rmp_segment_size - 1; +} + +#define RMP_ADDR_MASK GENMASK_ULL(51, 13) + +static bool probe_contiguous_rmptable_info(void) { - if (WARN_ON_ONCE(pfn > rmptable_max_pfn)) + u64 rmp_sz, rmp_base, rmp_end; + + rdmsrl(MSR_AMD64_RMP_BASE, rmp_base); + rdmsrl(MSR_AMD64_RMP_END, rmp_end); + + if (!(rmp_base & RMP_ADDR_MASK) || !(rmp_end & RMP_ADDR_MASK)) { + pr_err("Memory for the RMP table has not been reserved by BIOS\n"); + return false; + } + + if (rmp_base > rmp_end) { + pr_err("RMP configuration not valid: base=%#llx, end=%#llx\n", rmp_base, rmp_end); + return false; + } + + rmp_sz = rmp_end - rmp_base + 1; + + /* Treat the contiguous RMP table as a single segment */ + rst_max_index = 1; + + set_rmp_segment_info(RMPTABLE_NON_SEGMENTED_SHIFT); + + probed_rmp_base = rmp_base; + probed_rmp_size = rmp_sz; + + pr_info("RMP table physical range [0x%016llx - 0x%016llx]\n", + rmp_base, rmp_end); + + return true; +} + +static bool probe_segmented_rmptable_info(void) +{ + unsigned int eax, ebx, segment_shift, segment_shift_min, segment_shift_max; + u64 rmp_base, rmp_end; + + rdmsrl(MSR_AMD64_RMP_BASE, rmp_base); + if (!(rmp_base & RMP_ADDR_MASK)) { + pr_err("Memory for the RMP table has not been reserved by BIOS\n"); + return false; + } + + rdmsrl(MSR_AMD64_RMP_END, rmp_end); + WARN_ONCE(rmp_end & RMP_ADDR_MASK, + "Segmented RMP enabled but RMP_END MSR is non-zero\n"); + + /* Obtain the min and max supported RMP segment size */ + eax = cpuid_eax(0x80000025); + segment_shift_min = eax & GENMASK(5, 0); + segment_shift_max = (eax & GENMASK(11, 6)) >> 6; + + /* Verify the segment size is within the supported limits */ + segment_shift = MSR_AMD64_RMP_SEGMENT_SHIFT(rmp_cfg); + if (segment_shift > segment_shift_max || segment_shift < segment_shift_min) { + pr_err("RMP segment size (%u) is not within advertised bounds (min=%u, max=%u)\n", + segment_shift, segment_shift_min, segment_shift_max); + return false; + } + + /* Override the max supported RST index if a hardware limit exists */ + ebx = cpuid_ebx(0x80000025); + if (ebx & BIT(10)) + rst_max_index = ebx & GENMASK(9, 0); + + set_rmp_segment_info(segment_shift); + + probed_rmp_base = rmp_base; + probed_rmp_size = 0; + + pr_info("Segmented RMP base table physical range [0x%016llx - 0x%016llx]\n", + rmp_base, rmp_base + RMPTABLE_CPU_BOOKKEEPING_SZ + RST_SIZE); + + return true; +} + +bool snp_probe_rmptable_info(void) +{ + if (cpu_feature_enabled(X86_FEATURE_SEGMENTED_RMP)) + rdmsrl(MSR_AMD64_RMP_CFG, rmp_cfg); + + if (rmp_cfg & MSR_AMD64_SEG_RMP_ENABLED) + return probe_segmented_rmptable_info(); + else + return probe_contiguous_rmptable_info(); +} + +/* + * About the array_index_nospec() usage below: + * + * This function can get called by exported functions like + * snp_lookup_rmpentry(), which is used by the KVM #PF handler, among + * others, and since the @pfn passed in cannot always be trusted, + * speculation should be stopped as a protective measure. + */ +static struct rmpentry_raw *get_raw_rmpentry(u64 pfn) +{ + u64 paddr, rst_index, segment_index; + struct rmp_segment_desc *desc; + + if (!rmp_segment_table) + return ERR_PTR(-ENODEV); + + paddr = pfn << PAGE_SHIFT; + + rst_index = RST_ENTRY_INDEX(paddr); + if (unlikely(rst_index >= rst_max_index)) return ERR_PTR(-EFAULT); - return &rmptable[pfn]; + rst_index = array_index_nospec(rst_index, rst_max_index); + + desc = rmp_segment_table[rst_index]; + if (unlikely(!desc)) + return ERR_PTR(-EFAULT); + + segment_index = RMP_ENTRY_INDEX(paddr); + if (unlikely(segment_index >= desc->max_index)) + return ERR_PTR(-EFAULT); + + segment_index = array_index_nospec(segment_index, desc->max_index); + + return desc->rmp_entry + segment_index; +} + +static int get_rmpentry(u64 pfn, struct rmpentry *e) +{ + struct rmpentry_raw *e_raw; + + if (cpu_feature_enabled(X86_FEATURE_RMPREAD)) { + int ret; + + /* Binutils version 2.44 supports the RMPREAD mnemonic. */ + asm volatile(".byte 0xf2, 0x0f, 0x01, 0xfd" + : "=a" (ret) + : "a" (pfn << PAGE_SHIFT), "c" (e) + : "memory", "cc"); + + return ret; + } + + e_raw = get_raw_rmpentry(pfn); + if (IS_ERR(e_raw)) + return PTR_ERR(e_raw); + + /* + * Map the raw RMP table entry onto the RMPREAD output format. + * The 2MB region status indicator (hpage_region_status field) is not + * calculated, since the overhead could be significant and the field + * is not used. + */ + memset(e, 0, sizeof(*e)); + e->gpa = e_raw->gpa << PAGE_SHIFT; + e->asid = e_raw->asid; + e->assigned = e_raw->assigned; + e->pagesize = e_raw->pagesize; + e->immutable = e_raw->immutable; + + return 0; } -static struct rmpentry *__snp_lookup_rmpentry(u64 pfn, int *level) +static int __snp_lookup_rmpentry(u64 pfn, struct rmpentry *e, int *level) { - struct rmpentry *large_entry, *entry; + struct rmpentry e_large; + int ret; if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) - return ERR_PTR(-ENODEV); + return -ENODEV; - entry = get_rmpentry(pfn); - if (IS_ERR(entry)) - return entry; + ret = get_rmpentry(pfn, e); + if (ret) + return ret; /* * Find the authoritative RMP entry for a PFN. This can be either a 4K * RMP entry or a special large RMP entry that is authoritative for a * whole 2M area. */ - large_entry = get_rmpentry(pfn & PFN_PMD_MASK); - if (IS_ERR(large_entry)) - return large_entry; + ret = get_rmpentry(pfn & PFN_PMD_MASK, &e_large); + if (ret) + return ret; - *level = RMP_TO_PG_LEVEL(large_entry->pagesize); + *level = RMP_TO_PG_LEVEL(e_large.pagesize); - return entry; + return 0; } int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { - struct rmpentry *e; + struct rmpentry e; + int ret; - e = __snp_lookup_rmpentry(pfn, level); - if (IS_ERR(e)) - return PTR_ERR(e); + ret = __snp_lookup_rmpentry(pfn, &e, level); + if (ret) + return ret; - *assigned = !!e->assigned; + *assigned = !!e.assigned; return 0; } EXPORT_SYMBOL_GPL(snp_lookup_rmpentry); @@ -326,20 +791,28 @@ EXPORT_SYMBOL_GPL(snp_lookup_rmpentry); */ static void dump_rmpentry(u64 pfn) { + struct rmpentry_raw *e_raw; u64 pfn_i, pfn_end; - struct rmpentry *e; - int level; + struct rmpentry e; + int level, ret; - e = __snp_lookup_rmpentry(pfn, &level); - if (IS_ERR(e)) { - pr_err("Failed to read RMP entry for PFN 0x%llx, error %ld\n", - pfn, PTR_ERR(e)); + ret = __snp_lookup_rmpentry(pfn, &e, &level); + if (ret) { + pr_err("Failed to read RMP entry for PFN 0x%llx, error %d\n", + pfn, ret); return; } - if (e->assigned) { + if (e.assigned) { + e_raw = get_raw_rmpentry(pfn); + if (IS_ERR(e_raw)) { + pr_err("Failed to read RMP contents for PFN 0x%llx, error %ld\n", + pfn, PTR_ERR(e_raw)); + return; + } + pr_info("PFN 0x%llx, RMP entry: [0x%016llx - 0x%016llx]\n", - pfn, e->lo, e->hi); + pfn, e_raw->lo, e_raw->hi); return; } @@ -358,16 +831,16 @@ static void dump_rmpentry(u64 pfn) pfn, pfn_i, pfn_end); while (pfn_i < pfn_end) { - e = __snp_lookup_rmpentry(pfn_i, &level); - if (IS_ERR(e)) { - pr_err("Error %ld reading RMP entry for PFN 0x%llx\n", - PTR_ERR(e), pfn_i); + e_raw = get_raw_rmpentry(pfn_i); + if (IS_ERR(e_raw)) { + pr_err("Error %ld reading RMP contents for PFN 0x%llx\n", + PTR_ERR(e_raw), pfn_i); pfn_i++; continue; } - if (e->lo || e->hi) - pr_info("PFN: 0x%llx, [0x%016llx - 0x%016llx]\n", pfn_i, e->lo, e->hi); + if (e_raw->lo || e_raw->hi) + pr_info("PFN: 0x%llx, [0x%016llx - 0x%016llx]\n", pfn_i, e_raw->lo, e_raw->hi); pfn_i++; } } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 84e5adbd0925..43dcd8c7badc 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -2,6 +2,7 @@ #include <linux/console.h> #include <linux/cpu.h> +#include <linux/instrumentation.h> #include <linux/kexec.h> #include <linux/memblock.h> #include <linux/slab.h> @@ -21,7 +22,8 @@ #include "xen-ops.h" -EXPORT_SYMBOL_GPL(hypercall_page); +DEFINE_STATIC_CALL(xen_hypercall, xen_hypercall_hvm); +EXPORT_STATIC_CALL_TRAMP(xen_hypercall); /* * Pointer to the xen_vcpu_info structure or @@ -68,6 +70,67 @@ EXPORT_SYMBOL(xen_start_flags); */ struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info; +static __ref void xen_get_vendor(void) +{ + init_cpu_devs(); + cpu_detect(&boot_cpu_data); + get_cpu_vendor(&boot_cpu_data); +} + +void xen_hypercall_setfunc(void) +{ + if (static_call_query(xen_hypercall) != xen_hypercall_hvm) + return; + + if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) + static_call_update(xen_hypercall, xen_hypercall_amd); + else + static_call_update(xen_hypercall, xen_hypercall_intel); +} + +/* + * Evaluate processor vendor in order to select the correct hypercall + * function for HVM/PVH guests. + * Might be called very early in boot before vendor has been set by + * early_cpu_init(). + */ +noinstr void *__xen_hypercall_setfunc(void) +{ + void (*func)(void); + + /* + * Xen is supported only on CPUs with CPUID, so testing for + * X86_FEATURE_CPUID is a test for early_cpu_init() having been + * run. + * + * Note that __xen_hypercall_setfunc() is noinstr only due to a nasty + * dependency chain: it is being called via the xen_hypercall static + * call when running as a PVH or HVM guest. Hypercalls need to be + * noinstr due to PV guests using hypercalls in noinstr code. So we + * can safely tag the function body as "instrumentation ok", since + * the PV guest requirement is not of interest here (xen_get_vendor() + * calls noinstr functions, and static_call_update_early() might do + * so, too). + */ + instrumentation_begin(); + + if (!boot_cpu_has(X86_FEATURE_CPUID)) + xen_get_vendor(); + + if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) + func = xen_hypercall_amd; + else + func = xen_hypercall_intel; + + static_call_update_early(xen_hypercall, func); + + instrumentation_end(); + + return func; +} + static int xen_cpu_up_online(unsigned int cpu) { xen_init_lock_cpu(cpu); diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 24d2957a4726..fe57ff85d004 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -106,15 +106,8 @@ static void __init init_hvm_pv_info(void) /* PVH set up hypercall page in xen_prepare_pvh(). */ if (xen_pvh_domain()) pv_info.name = "Xen PVH"; - else { - u64 pfn; - uint32_t msr; - + else pv_info.name = "Xen HVM"; - msr = cpuid_ebx(base + 2); - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - } xen_setup_features(); @@ -300,6 +293,10 @@ static uint32_t __init xen_platform_hvm(void) if (xen_pv_domain()) return 0; + /* Set correct hypercall function. */ + if (xen_domain) + xen_hypercall_setfunc(); + if (xen_pvh_domain() && nopv) { /* Guest booting via the Xen-PVH boot entry goes here */ pr_info("\"nopv\" parameter is ignored in PVH guest\n"); diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index d6818c6cafda..5e57835e999d 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -49,6 +49,7 @@ #include <xen/hvc-console.h> #include <xen/acpi.h> +#include <asm/cpuid.h> #include <asm/paravirt.h> #include <asm/apic.h> #include <asm/page.h> @@ -171,7 +172,7 @@ static void __init xen_set_mtrr_data(void) /* Only overwrite MTRR state if any MTRR could be got from Xen. */ if (reg) - mtrr_overwrite_state(var, reg, MTRR_TYPE_UNCACHABLE); + guest_force_mtrr_state(var, reg, MTRR_TYPE_UNCACHABLE); #endif } @@ -195,7 +196,7 @@ static void __init xen_pv_init_platform(void) if (xen_initial_domain()) xen_set_mtrr_data(); else - mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK); + guest_force_mtrr_state(NULL, 0, MTRR_TYPE_WRBACK); /* Adjust nr_cpu_ids before "enumeration" happens */ xen_smp_count_cpus(); @@ -230,7 +231,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, or_ebx = smp_processor_id() << 24; break; - case CPUID_MWAIT_LEAF: + case CPUID_LEAF_MWAIT: /* Synthesize the values.. */ *ax = 0; *bx = 0; @@ -300,7 +301,7 @@ static bool __init xen_check_mwait(void) * ecx and edx. The hypercall provides only partial information. */ - ax = CPUID_MWAIT_LEAF; + ax = CPUID_LEAF_MWAIT; bx = 0; cx = 0; dx = 0; @@ -1161,8 +1162,6 @@ static const typeof(pv_ops) xen_cpu_ops __initconst = { .write_cr4 = xen_write_cr4, - .wbinvd = pv_native_wbinvd, - .read_msr = xen_read_msr, .write_msr = xen_write_msr, @@ -1341,6 +1340,9 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) xen_domain_type = XEN_PV_DOMAIN; xen_start_flags = xen_start_info->flags; + /* Interrupts are guaranteed to be off initially. */ + early_boot_irqs_disabled = true; + static_call_update_early(xen_hypercall, xen_hypercall_pv); xen_setup_features(); @@ -1431,7 +1433,6 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv)); local_irq_disable(); - early_boot_irqs_disabled = true; xen_raw_console_write("mapping kernel into physical memory\n"); xen_setup_kernel_pagetable((pgd_t *)xen_start_info->pt_base, diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index bf68c329fc01..0e3d930bcb89 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -129,17 +129,10 @@ static void __init pvh_arch_setup(void) void __init xen_pvh_init(struct boot_params *boot_params) { - u32 msr; - u64 pfn; - xen_pvh = 1; xen_domain_type = XEN_HVM_DOMAIN; xen_start_flags = pvh_start_info.flags; - msr = cpuid_ebx(xen_cpuid_base() + 2); - pfn = __pa(hypercall_page); - wrmsr_safe(msr, (u32)pfn, (u32)(pfn >> 32)); - x86_init.oem.arch_setup = pvh_arch_setup; x86_init.oem.banner = xen_banner; diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 83189cf5cdce..b518f36d1ca2 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -20,10 +20,33 @@ #include <linux/init.h> #include <linux/linkage.h> +#include <linux/objtool.h> #include <../entry/calling.h> .pushsection .noinstr.text, "ax" /* + * PV hypercall interface to the hypervisor. + * + * Called via inline asm(), so better preserve %rcx and %r11. + * + * Input: + * %eax: hypercall number + * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall + * Output: %rax + */ +SYM_FUNC_START(xen_hypercall_pv) + ANNOTATE_NOENDBR + push %rcx + push %r11 + UNWIND_HINT_SAVE + syscall + UNWIND_HINT_RESTORE + pop %r11 + pop %rcx + RET +SYM_FUNC_END(xen_hypercall_pv) + +/* * Disabling events is simply a matter of making the event mask * non-zero. */ @@ -176,7 +199,6 @@ SYM_CODE_START(xen_early_idt_handler_array) SYM_CODE_END(xen_early_idt_handler_array) __FINIT -hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 /* * Xen64 iret frame: * @@ -186,17 +208,28 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32 * cs * rip <-- standard iret frame * - * flags + * flags <-- xen_iret must push from here on * - * rcx } - * r11 }<-- pushed by hypercall page - * rsp->rax } + * rcx + * r11 + * rsp->rax */ +.macro xen_hypercall_iret + pushq $0 /* Flags */ + push %rcx + push %r11 + push %rax + mov $__HYPERVISOR_iret, %eax + syscall /* Do the IRET. */ +#ifdef CONFIG_MITIGATION_SLS + int3 +#endif +.endm + SYM_CODE_START(xen_iret) UNWIND_HINT_UNDEFINED ANNOTATE_NOENDBR - pushq $0 - jmp hypercall_iret + xen_hypercall_iret SYM_CODE_END(xen_iret) /* @@ -301,8 +334,7 @@ SYM_CODE_START(xen_entry_SYSENTER_compat) ENDBR lea 16(%rsp), %rsp /* strip %rcx, %r11 */ mov $-ENOSYS, %rax - pushq $0 - jmp hypercall_iret + xen_hypercall_iret SYM_CODE_END(xen_entry_SYSENTER_compat) SYM_CODE_END(xen_entry_SYSCALL_compat) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 7f6c69dbb816..9252652afe59 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -6,9 +6,11 @@ #include <linux/elfnote.h> #include <linux/init.h> +#include <linux/instrumentation.h> #include <asm/boot.h> #include <asm/asm.h> +#include <asm/frame.h> #include <asm/msr.h> #include <asm/page_types.h> #include <asm/percpu.h> @@ -20,28 +22,6 @@ #include <xen/interface/xen-mca.h> #include <asm/xen/interface.h> -.pushsection .noinstr.text, "ax" - .balign PAGE_SIZE -SYM_CODE_START(hypercall_page) - .rept (PAGE_SIZE / 32) - UNWIND_HINT_FUNC - ANNOTATE_NOENDBR - ANNOTATE_UNRET_SAFE - ret - /* - * Xen will write the hypercall page, and sort out ENDBR. - */ - .skip 31, 0xcc - .endr - -#define HYPERCALL(n) \ - .equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \ - .type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32 -#include <asm/xen-hypercalls.h> -#undef HYPERCALL -SYM_CODE_END(hypercall_page) -.popsection - #ifdef CONFIG_XEN_PV __INIT SYM_CODE_START(startup_xen) @@ -87,6 +67,87 @@ SYM_CODE_END(xen_cpu_bringup_again) #endif #endif + .pushsection .noinstr.text, "ax" +/* + * Xen hypercall interface to the hypervisor. + * + * Input: + * %eax: hypercall number + * 32-bit: + * %ebx, %ecx, %edx, %esi, %edi: args 1..5 for the hypercall + * 64-bit: + * %rdi, %rsi, %rdx, %r10, %r8: args 1..5 for the hypercall + * Output: %[er]ax + */ +SYM_FUNC_START(xen_hypercall_hvm) + ENDBR + FRAME_BEGIN + /* Save all relevant registers (caller save and arguments). */ +#ifdef CONFIG_X86_32 + push %eax + push %ebx + push %ecx + push %edx + push %esi + push %edi +#else + push %rax + push %rcx + push %rdx + push %rdi + push %rsi + push %r11 + push %r10 + push %r9 + push %r8 +#ifdef CONFIG_FRAME_POINTER + pushq $0 /* Dummy push for stack alignment. */ +#endif +#endif + /* Set the vendor specific function. */ + call __xen_hypercall_setfunc + /* Set ZF = 1 if AMD, Restore saved registers. */ +#ifdef CONFIG_X86_32 + lea xen_hypercall_amd, %ebx + cmp %eax, %ebx + pop %edi + pop %esi + pop %edx + pop %ecx + pop %ebx + pop %eax +#else + lea xen_hypercall_amd(%rip), %rbx + cmp %rax, %rbx +#ifdef CONFIG_FRAME_POINTER + pop %rax /* Dummy pop. */ +#endif + pop %r8 + pop %r9 + pop %r10 + pop %r11 + pop %rsi + pop %rdi + pop %rdx + pop %rcx + pop %rax +#endif + /* Use correct hypercall function. */ + jz xen_hypercall_amd + jmp xen_hypercall_intel +SYM_FUNC_END(xen_hypercall_hvm) + +SYM_FUNC_START(xen_hypercall_amd) + vmmcall + RET +SYM_FUNC_END(xen_hypercall_amd) + +SYM_FUNC_START(xen_hypercall_intel) + vmcall + RET +SYM_FUNC_END(xen_hypercall_intel) + .popsection + ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS, .asciz "linux") ELFNOTE(Xen, XEN_ELFNOTE_GUEST_VERSION, .asciz "2.6") ELFNOTE(Xen, XEN_ELFNOTE_XEN_VERSION, .asciz "xen-3.0") @@ -116,8 +177,6 @@ SYM_CODE_END(xen_cpu_bringup_again) #else # define FEATURES_DOM0 0 #endif - ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, .globl xen_elfnote_hypercall_page; - xen_elfnote_hypercall_page: _ASM_PTR xen_elfnote_hypercall_page_value - .) ELFNOTE(Xen, XEN_ELFNOTE_SUPPORTED_FEATURES, .long FEATURES_PV | FEATURES_PVH | FEATURES_DOM0) ELFNOTE(Xen, XEN_ELFNOTE_LOADER, .asciz "generic") diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index e1b782e823e6..63c13a2ccf55 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -326,4 +326,13 @@ static inline void xen_smp_intr_free_pv(unsigned int cpu) {} static inline void xen_smp_count_cpus(void) { } #endif /* CONFIG_SMP */ +#ifdef CONFIG_XEN_PV +void xen_hypercall_pv(void); +#endif +void xen_hypercall_hvm(void); +void xen_hypercall_amd(void); +void xen_hypercall_intel(void); +void xen_hypercall_setfunc(void); +void *__xen_hypercall_setfunc(void); + #endif /* XEN_OPS_H */ |