diff options
Diffstat (limited to 'arch/arm64')
56 files changed, 1085 insertions, 562 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 505c8a1ccbe0..957ec4d02428 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config ARM64 def_bool y + select ACPI_APMT if ACPI select ACPI_CCA_REQUIRED if ACPI select ACPI_GENERIC_GSI if ACPI select ACPI_GTDT if ACPI @@ -117,6 +118,7 @@ config ARM64 select CPU_PM if (SUSPEND || CPU_IDLE) select CRC32 select DCACHE_WORD_ACCESS + select DYNAMIC_FTRACE if FUNCTION_TRACER select DMA_DIRECT_REMAP select EDAC_SUPPORT select FRAME_POINTER @@ -181,8 +183,10 @@ config ARM64 select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE + select HAVE_DYNAMIC_FTRACE_WITH_ARGS \ + if $(cc-option,-fpatchable-function-entry=2) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ - if DYNAMIC_FTRACE_WITH_REGS + if DYNAMIC_FTRACE_WITH_ARGS select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_FAST_GUP select HAVE_FTRACE_MCOUNT_RECORD @@ -233,16 +237,16 @@ config ARM64 help ARM 64-bit (AArch64) Linux support. -config CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_REGS +config CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS def_bool CC_IS_CLANG # https://github.com/ClangBuiltLinux/linux/issues/1507 depends on AS_IS_GNU || (AS_IS_LLVM && (LD_IS_LLD || LD_VERSION >= 23600)) - select HAVE_DYNAMIC_FTRACE_WITH_REGS + select HAVE_DYNAMIC_FTRACE_WITH_ARGS -config GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_REGS +config GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_ARGS def_bool CC_IS_GCC depends on $(cc-option,-fpatchable-function-entry=2) - select HAVE_DYNAMIC_FTRACE_WITH_REGS + select HAVE_DYNAMIC_FTRACE_WITH_ARGS config 64BIT def_bool y @@ -370,6 +374,9 @@ config KASAN_SHADOW_OFFSET default 0xeffffff800000000 if ARM64_VA_BITS_36 && KASAN_SW_TAGS default 0xffffffffffffffff +config UNWIND_TABLES + bool + source "arch/arm64/Kconfig.platforms" menu "Kernel Features" @@ -964,6 +971,22 @@ config ARM64_ERRATUM_2457168 If unsure, say Y. +config ARM64_ERRATUM_2645198 + bool "Cortex-A715: 2645198: Workaround possible [ESR|FAR]_ELx corruption" + default y + help + This option adds the workaround for ARM Cortex-A715 erratum 2645198. + + If a Cortex-A715 cpu sees a page mapping permissions change from executable + to non-executable, it may corrupt the ESR_ELx and FAR_ELx registers on the + next instruction abort caused by permission fault. + + Only user-space does executable to non-executable permission transition via + mprotect() system call. Workaround the problem by doing a break-before-make + TLB invalidation, for all changes to executable user space mappings. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y @@ -1816,7 +1839,7 @@ config ARM64_PTR_AUTH_KERNEL # which is only understood by binutils starting with version 2.33.1. depends on LD_IS_LLD || LD_VERSION >= 23301 || (CC_IS_GCC && GCC_VERSION < 90100) depends on !CC_IS_CLANG || AS_HAS_CFI_NEGATE_RA_STATE - depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS) + depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_ARGS) help If the compiler supports the -mbranch-protection or -msign-return-address flag (e.g. GCC 7 or later), then this option @@ -1826,7 +1849,7 @@ config ARM64_PTR_AUTH_KERNEL disabled with minimal loss of protection. This feature works with FUNCTION_GRAPH_TRACER option only if - DYNAMIC_FTRACE_WITH_REGS is enabled. + DYNAMIC_FTRACE_WITH_ARGS is enabled. config CC_HAS_BRANCH_PROT_PAC_RET # GCC 9 or later, clang 8 or later @@ -1924,7 +1947,7 @@ config ARM64_BTI_KERNEL depends on !CC_IS_GCC # https://github.com/llvm/llvm-project/commit/a88c722e687e6780dcd6a58718350dc76fcc4cc9 depends on !CC_IS_CLANG || CLANG_VERSION >= 120000 - depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_REGS) + depends on (!FUNCTION_GRAPH_TRACER || DYNAMIC_FTRACE_WITH_ARGS) help Build the kernel with Branch Target Identification annotations and enable enforcement of this for kernel code. When this option @@ -2157,6 +2180,15 @@ config ARCH_NR_GPIO If unsure, leave the default value. +config UNWIND_PATCH_PAC_INTO_SCS + bool "Enable shadow call stack dynamically using code patching" + # needs Clang with https://reviews.llvm.org/D111780 incorporated + depends on CC_IS_CLANG && CLANG_VERSION >= 150000 + depends on ARM64_PTR_AUTH_KERNEL && CC_HAS_BRANCH_PROT_PAC_RET + depends on SHADOW_CALL_STACK + select UNWIND_TABLES + select DYNAMIC_SCS + endmenu # "Kernel Features" menu "Boot options" diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 5e56d26a2239..d62bd221828f 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -45,8 +45,13 @@ KBUILD_CFLAGS += $(call cc-option,-mabi=lp64) KBUILD_AFLAGS += $(call cc-option,-mabi=lp64) # Avoid generating .eh_frame* sections. +ifneq ($(CONFIG_UNWIND_TABLES),y) KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables KBUILD_AFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables +else +KBUILD_CFLAGS += -fasynchronous-unwind-tables +KBUILD_AFLAGS += -fasynchronous-unwind-tables +endif ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y) prepare: stack_protector_prepare @@ -72,10 +77,16 @@ branch-prot-flags-$(CONFIG_CC_HAS_SIGN_RETURN_ADDRESS) := -msign-return-address= # We enable additional protection for leaf functions as there is some # narrow potential for ROP protection benefits and no substantial # performance impact has been observed. +PACRET-y := pac-ret+leaf + +# Using a shadow call stack in leaf functions is too costly, so avoid PAC there +# as well when we may be patching PAC into SCS +PACRET-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS) := pac-ret + ifeq ($(CONFIG_ARM64_BTI_KERNEL),y) -branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET_BTI) := -mbranch-protection=pac-ret+leaf+bti +branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET_BTI) := -mbranch-protection=$(PACRET-y)+bti else -branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET) := -mbranch-protection=pac-ret+leaf +branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET) := -mbranch-protection=$(PACRET-y) endif # -march=armv8.3-a enables the non-nops instructions for PAC, to avoid the # compiler to generate them and consequently to break the single image contract @@ -128,7 +139,7 @@ endif CHECKFLAGS += -D__aarch64__ -ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_REGS),y) +ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_ARGS),y) KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY CC_FLAGS_FTRACE := -fpatchable-function-entry=2 endif diff --git a/arch/arm64/include/asm/alternative-macros.h b/arch/arm64/include/asm/alternative-macros.h index 3622e9f4fb44..bdf1f6bcd010 100644 --- a/arch/arm64/include/asm/alternative-macros.h +++ b/arch/arm64/include/asm/alternative-macros.h @@ -224,7 +224,7 @@ alternative_endif #include <linux/types.h> static __always_inline bool -alternative_has_feature_likely(unsigned long feature) +alternative_has_feature_likely(const unsigned long feature) { compiletime_assert(feature < ARM64_NCAPS, "feature must be < ARM64_NCAPS"); @@ -242,7 +242,7 @@ l_no: } static __always_inline bool -alternative_has_feature_unlikely(unsigned long feature) +alternative_has_feature_unlikely(const unsigned long feature) { compiletime_assert(feature < ARM64_NCAPS, "feature must be < ARM64_NCAPS"); diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index e5957a53be39..89038067ef34 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -660,12 +660,10 @@ alternative_endif .endm .macro pte_to_phys, phys, pte -#ifdef CONFIG_ARM64_PA_BITS_52 - ubfiz \phys, \pte, #(48 - 16 - 12), #16 - bfxil \phys, \pte, #16, #32 - lsl \phys, \phys, #16 -#else and \phys, \pte, #PTE_ADDR_MASK +#ifdef CONFIG_ARM64_PA_BITS_52 + orr \phys, \phys, \phys, lsl #PTE_ADDR_HIGH_SHIFT + and \phys, \phys, GENMASK_ULL(PHYS_MASK_SHIFT - 1, PAGE_SHIFT) #endif .endm diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index abc418650fec..4b1ad810436f 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -80,6 +80,7 @@ #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A710 0xD47 +#define ARM_CPU_PART_CORTEX_A715 0xD4D #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B @@ -142,6 +143,7 @@ #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) +#define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715) #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 6f86b7ab6c28..e6fa1e2982c8 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -56,11 +56,20 @@ extern void fpsimd_signal_preserve_current_state(void); extern void fpsimd_preserve_current_state(void); extern void fpsimd_restore_current_state(void); extern void fpsimd_update_current_state(struct user_fpsimd_state const *state); +extern void fpsimd_kvm_prepare(void); + +struct cpu_fp_state { + struct user_fpsimd_state *st; + void *sve_state; + void *za_state; + u64 *svcr; + unsigned int sve_vl; + unsigned int sme_vl; + enum fp_type *fp_type; + enum fp_type to_save; +}; -extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state, - void *sve_state, unsigned int sve_vl, - void *za_state, unsigned int sme_vl, - u64 *svcr); +extern void fpsimd_bind_state_to_cpu(struct cpu_fp_state *fp_state); extern void fpsimd_flush_task_state(struct task_struct *target); extern void fpsimd_save_and_flush_cpu_state(void); diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index 329dbbd4d50b..5664729800ae 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -23,7 +23,7 @@ */ #define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS #define ARCH_SUPPORTS_FTRACE_OPS 1 #else #define MCOUNT_ADDR ((unsigned long)_mcount) @@ -33,8 +33,7 @@ #define MCOUNT_INSN_SIZE AARCH64_INSN_SIZE #define FTRACE_PLT_IDX 0 -#define FTRACE_REGS_PLT_IDX 1 -#define NR_FTRACE_PLTS 2 +#define NR_FTRACE_PLTS 1 /* * Currently, gcc tends to save the link register after the local variables @@ -69,7 +68,7 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) * Adjust addr to point at the BL in the callsite. * See ftrace_init_nop() for the callsite sequence. */ - if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS)) return addr + AARCH64_INSN_SIZE; /* * addr is the address of the mcount call instruction. @@ -78,10 +77,71 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) return addr; } -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS struct dyn_ftrace; struct ftrace_ops; -struct ftrace_regs; + +#define arch_ftrace_get_regs(regs) NULL + +struct ftrace_regs { + /* x0 - x8 */ + unsigned long regs[9]; + unsigned long __unused; + + unsigned long fp; + unsigned long lr; + + unsigned long sp; + unsigned long pc; +}; + +static __always_inline unsigned long +ftrace_regs_get_instruction_pointer(const struct ftrace_regs *fregs) +{ + return fregs->pc; +} + +static __always_inline void +ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, + unsigned long pc) +{ + fregs->pc = pc; +} + +static __always_inline unsigned long +ftrace_regs_get_stack_pointer(const struct ftrace_regs *fregs) +{ + return fregs->sp; +} + +static __always_inline unsigned long +ftrace_regs_get_argument(struct ftrace_regs *fregs, unsigned int n) +{ + if (n < 8) + return fregs->regs[n]; + return 0; +} + +static __always_inline unsigned long +ftrace_regs_get_return_value(const struct ftrace_regs *fregs) +{ + return fregs->regs[0]; +} + +static __always_inline void +ftrace_regs_set_return_value(struct ftrace_regs *fregs, + unsigned long ret) +{ + fregs->regs[0] = ret; +} + +static __always_inline void +ftrace_override_function_with_return(struct ftrace_regs *fregs) +{ + fregs->pc = fregs->lr; +} + +int ftrace_regs_query_register_offset(const char *name); int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); #define ftrace_init_nop ftrace_init_nop diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index d20f5da2d76f..6a4a1ab8eb23 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -49,6 +49,15 @@ extern pte_t huge_ptep_get(pte_t *ptep); void __init arm64_hugetlb_cma_reserve(void); +#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start +extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); + +#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit +extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t new_pte); + #include <asm-generic/hugetlb.h> #endif /* __ASM_HUGETLB_H */ diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 298b386d3ebe..06dd12c514e6 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -120,6 +120,9 @@ #define KERNEL_HWCAP_WFXT __khwcap2_feature(WFXT) #define KERNEL_HWCAP_EBF16 __khwcap2_feature(EBF16) #define KERNEL_HWCAP_SVE_EBF16 __khwcap2_feature(SVE_EBF16) +#define KERNEL_HWCAP_CSSC __khwcap2_feature(CSSC) +#define KERNEL_HWCAP_RPRFM __khwcap2_feature(RPRFM) +#define KERNEL_HWCAP_SVE2P1 __khwcap2_feature(SVE2P1) /* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 834bff720582..aaf1f52fbf3e 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -13,31 +13,6 @@ #include <asm/insn-def.h> #ifndef __ASSEMBLY__ -/* - * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a - * Section C3.1 "A64 instruction index by encoding": - * AArch64 main encoding table - * Bit position - * 28 27 26 25 Encoding Group - * 0 0 - - Unallocated - * 1 0 0 - Data processing, immediate - * 1 0 1 - Branch, exception generation and system instructions - * - 1 - 0 Loads and stores - * - 1 0 1 Data processing - register - * 0 1 1 1 Data processing - SIMD and floating point - * 1 1 1 1 Data processing - SIMD and floating point - * "-" means "don't care" - */ -enum aarch64_insn_encoding_class { - AARCH64_INSN_CLS_UNKNOWN, /* UNALLOCATED */ - AARCH64_INSN_CLS_SVE, /* SVE instructions */ - AARCH64_INSN_CLS_DP_IMM, /* Data processing - immediate */ - AARCH64_INSN_CLS_DP_REG, /* Data processing - register */ - AARCH64_INSN_CLS_DP_FPSIMD, /* Data processing - SIMD and FP */ - AARCH64_INSN_CLS_LDST, /* Loads and stores */ - AARCH64_INSN_CLS_BR_SYS, /* Branch, exception generation and - * system instructions */ -}; enum aarch64_insn_hint_cr_op { AARCH64_INSN_HINT_NOP = 0x0 << 5, @@ -326,6 +301,23 @@ static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \ return (val); \ } +/* + * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a + * Section C3.1 "A64 instruction index by encoding": + * AArch64 main encoding table + * Bit position + * 28 27 26 25 Encoding Group + * 0 0 - - Unallocated + * 1 0 0 - Data processing, immediate + * 1 0 1 - Branch, exception generation and system instructions + * - 1 - 0 Loads and stores + * - 1 0 1 Data processing - register + * 0 1 1 1 Data processing - SIMD and floating point + * 1 1 1 1 Data processing - SIMD and floating point + * "-" means "don't care" + */ +__AARCH64_INSN_FUNCS(class_branch_sys, 0x1c000000, 0x14000000) + __AARCH64_INSN_FUNCS(adr, 0x9F000000, 0x10000000) __AARCH64_INSN_FUNCS(adrp, 0x9F000000, 0x90000000) __AARCH64_INSN_FUNCS(prfm, 0x3FC00000, 0x39800000) @@ -431,58 +423,122 @@ __AARCH64_INSN_FUNCS(pssbb, 0xFFFFFFFF, 0xD503349F) #undef __AARCH64_INSN_FUNCS -bool aarch64_insn_is_steppable_hint(u32 insn); -bool aarch64_insn_is_branch_imm(u32 insn); +static __always_inline bool aarch64_insn_is_steppable_hint(u32 insn) +{ + if (!aarch64_insn_is_hint(insn)) + return false; + + switch (insn & 0xFE0) { + case AARCH64_INSN_HINT_XPACLRI: + case AARCH64_INSN_HINT_PACIA_1716: + case AARCH64_INSN_HINT_PACIB_1716: + case AARCH64_INSN_HINT_PACIAZ: + case AARCH64_INSN_HINT_PACIASP: + case AARCH64_INSN_HINT_PACIBZ: + case AARCH64_INSN_HINT_PACIBSP: + case AARCH64_INSN_HINT_BTI: + case AARCH64_INSN_HINT_BTIC: + case AARCH64_INSN_HINT_BTIJ: + case AARCH64_INSN_HINT_BTIJC: + case AARCH64_INSN_HINT_NOP: + return true; + default: + return false; + } +} + +static __always_inline bool aarch64_insn_is_branch(u32 insn) +{ + /* b, bl, cb*, tb*, ret*, b.cond, br*, blr* */ + + return aarch64_insn_is_b(insn) || + aarch64_insn_is_bl(insn) || + aarch64_insn_is_cbz(insn) || + aarch64_insn_is_cbnz(insn) || + aarch64_insn_is_tbz(insn) || + aarch64_insn_is_tbnz(insn) || + aarch64_insn_is_ret(insn) || + aarch64_insn_is_ret_auth(insn) || + aarch64_insn_is_br(insn) || + aarch64_insn_is_br_auth(insn) || + aarch64_insn_is_blr(insn) || + aarch64_insn_is_blr_auth(insn) || + aarch64_insn_is_bcond(insn); +} -static inline bool aarch64_insn_is_adr_adrp(u32 insn) +static __always_inline bool aarch64_insn_is_branch_imm(u32 insn) { - return aarch64_insn_is_adr(insn) || aarch64_insn_is_adrp(insn); + return aarch64_insn_is_b(insn) || + aarch64_insn_is_bl(insn) || + aarch64_insn_is_tbz(insn) || + aarch64_insn_is_tbnz(insn) || + aarch64_insn_is_cbz(insn) || + aarch64_insn_is_cbnz(insn) || + aarch64_insn_is_bcond(insn); } -static inline bool aarch64_insn_is_dsb(u32 insn) +static __always_inline bool aarch64_insn_is_adr_adrp(u32 insn) { - return aarch64_insn_is_dsb_base(insn) || aarch64_insn_is_dsb_nxs(insn); + return aarch64_insn_is_adr(insn) || + aarch64_insn_is_adrp(insn); } -static inline bool aarch64_insn_is_barrier(u32 insn) +static __always_inline bool aarch64_insn_is_dsb(u32 insn) { - return aarch64_insn_is_dmb(insn) || aarch64_insn_is_dsb(insn) || - aarch64_insn_is_isb(insn) || aarch64_insn_is_sb(insn) || - aarch64_insn_is_clrex(insn) || aarch64_insn_is_ssbb(insn) || + return aarch64_insn_is_dsb_base(insn) || + aarch64_insn_is_dsb_nxs(insn); +} + +static __always_inline bool aarch64_insn_is_barrier(u32 insn) +{ + return aarch64_insn_is_dmb(insn) || + aarch64_insn_is_dsb(insn) || + aarch64_insn_is_isb(insn) || + aarch64_insn_is_sb(insn) || + aarch64_insn_is_clrex(insn) || + aarch64_insn_is_ssbb(insn) || aarch64_insn_is_pssbb(insn); } -static inline bool aarch64_insn_is_store_single(u32 insn) +static __always_inline bool aarch64_insn_is_store_single(u32 insn) { return aarch64_insn_is_store_imm(insn) || aarch64_insn_is_store_pre(insn) || aarch64_insn_is_store_post(insn); } -static inline bool aarch64_insn_is_store_pair(u32 insn) +static __always_inline bool aarch64_insn_is_store_pair(u32 insn) { return aarch64_insn_is_stp(insn) || aarch64_insn_is_stp_pre(insn) || aarch64_insn_is_stp_post(insn); } -static inline bool aarch64_insn_is_load_single(u32 insn) +static __always_inline bool aarch64_insn_is_load_single(u32 insn) { return aarch64_insn_is_load_imm(insn) || aarch64_insn_is_load_pre(insn) || aarch64_insn_is_load_post(insn); } -static inline bool aarch64_insn_is_load_pair(u32 insn) +static __always_inline bool aarch64_insn_is_load_pair(u32 insn) { return aarch64_insn_is_ldp(insn) || aarch64_insn_is_ldp_pre(insn) || aarch64_insn_is_ldp_post(insn); } +static __always_inline bool aarch64_insn_uses_literal(u32 insn) +{ + /* ldr/ldrsw (literal), prfm */ + + return aarch64_insn_is_ldr_lit(insn) || + aarch64_insn_is_ldrsw_lit(insn) || + aarch64_insn_is_adr_adrp(insn) || + aarch64_insn_is_prfm_lit(insn); +} + enum aarch64_insn_encoding_class aarch64_get_insn_class(u32 insn); -bool aarch64_insn_uses_literal(u32 insn); -bool aarch64_insn_is_branch(u32 insn); u64 aarch64_insn_decode_immediate(enum aarch64_insn_imm_type type, u32 insn); u32 aarch64_insn_encode_immediate(enum aarch64_insn_imm_type type, u32 insn, u64 imm); @@ -496,8 +552,18 @@ u32 aarch64_insn_gen_comp_branch_imm(unsigned long pc, unsigned long addr, enum aarch64_insn_branch_type type); u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr, enum aarch64_insn_condition cond); -u32 aarch64_insn_gen_hint(enum aarch64_insn_hint_cr_op op); -u32 aarch64_insn_gen_nop(void); + +static __always_inline u32 +aarch64_insn_gen_hint(enum aarch64_insn_hint_cr_op op) +{ + return aarch64_insn_get_hint_value() | op; +} + +static __always_inline u32 aarch64_insn_gen_nop(void) +{ + return aarch64_insn_gen_hint(AARCH64_INSN_HINT_NOP); +} + u32 aarch64_insn_gen_branch_reg(enum aarch64_insn_register reg, enum aarch64_insn_branch_type type); u32 aarch64_insn_gen_load_store_reg(enum aarch64_insn_register reg, @@ -580,10 +646,6 @@ u32 aarch64_insn_gen_extr(enum aarch64_insn_variant variant, enum aarch64_insn_register Rn, enum aarch64_insn_register Rd, u8 lsb); -u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base, - enum aarch64_insn_prfm_type type, - enum aarch64_insn_prfm_target target, - enum aarch64_insn_prfm_policy policy); #ifdef CONFIG_ARM64_LSE_ATOMICS u32 aarch64_insn_gen_atomic_ld_op(enum aarch64_insn_register result, enum aarch64_insn_register address, diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index cea441b6aa5d..48ddc0f45d22 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -15,8 +15,8 @@ #define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE -static __always_inline bool arch_static_branch(struct static_key *key, - bool branch) +static __always_inline bool arch_static_branch(struct static_key * const key, + const bool branch) { asm_volatile_goto( "1: nop \n\t" @@ -32,8 +32,8 @@ l_yes: return true; } -static __always_inline bool arch_static_branch_jump(struct static_key *key, - bool branch) +static __always_inline bool arch_static_branch_jump(struct static_key * const key, + const bool branch) { asm_volatile_goto( "1: b %l[l_yes] \n\t" diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 45e2136322ba..fd34ab155d0b 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -306,8 +306,18 @@ struct vcpu_reset_state { struct kvm_vcpu_arch { struct kvm_cpu_context ctxt; - /* Guest floating point state */ + /* + * Guest floating point state + * + * The architecture has two main floating point extensions, + * the original FPSIMD and SVE. These have overlapping + * register views, with the FPSIMD V registers occupying the + * low 128 bits of the SVE Z registers. When the core + * floating point code saves the register state of a task it + * records which view it saved in fp_type. + */ void *sve_state; + enum fp_type fp_type; unsigned int sve_max_vl; u64 svcr; diff --git a/arch/arm64/include/asm/module.lds.h b/arch/arm64/include/asm/module.lds.h index 094701ec5500..dbba4b7559aa 100644 --- a/arch/arm64/include/asm/module.lds.h +++ b/arch/arm64/include/asm/module.lds.h @@ -17,4 +17,12 @@ SECTIONS { */ .text.hot : { *(.text.hot) } #endif + +#ifdef CONFIG_UNWIND_TABLES + /* + * Currently, we only use unwind info at module load time, so we can + * put it into the .init allocation. + */ + .init.eh_frame : { *(.eh_frame) } +#endif } diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 5ab8d163198f..f658aafc47df 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -159,6 +159,7 @@ #ifdef CONFIG_ARM64_PA_BITS_52 #define PTE_ADDR_HIGH (_AT(pteval_t, 0xf) << 12) #define PTE_ADDR_MASK (PTE_ADDR_LOW | PTE_ADDR_HIGH) +#define PTE_ADDR_HIGH_SHIFT 36 #else #define PTE_ADDR_MASK PTE_ADDR_LOW #endif diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 71a1af42f0e8..8ef2a03ee553 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -77,11 +77,11 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; static inline phys_addr_t __pte_to_phys(pte_t pte) { return (pte_val(pte) & PTE_ADDR_LOW) | - ((pte_val(pte) & PTE_ADDR_HIGH) << 36); + ((pte_val(pte) & PTE_ADDR_HIGH) << PTE_ADDR_HIGH_SHIFT); } static inline pteval_t __phys_to_pte_val(phys_addr_t phys) { - return (phys | (phys >> 36)) & PTE_ADDR_MASK; + return (phys | (phys >> PTE_ADDR_HIGH_SHIFT)) & PTE_ADDR_MASK; } #else #define __pte_to_phys(pte) (pte_val(pte) & PTE_ADDR_MASK) @@ -1096,6 +1096,15 @@ static inline bool pud_sect_supported(void) } +#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION +#define ptep_modify_prot_start ptep_modify_prot_start +extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); + +#define ptep_modify_prot_commit ptep_modify_prot_commit +extern void ptep_modify_prot_commit(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t new_pte); #endif /* !__ASSEMBLY__ */ #endif /* __ASM_PGTABLE_H */ diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 445aa3af3b76..0dcb1f7f485d 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -122,6 +122,12 @@ enum vec_type { ARM64_VEC_MAX, }; +enum fp_type { + FP_STATE_CURRENT, /* Save based on current task state. */ + FP_STATE_FPSIMD, + FP_STATE_SVE, +}; + struct cpu_context { unsigned long x19; unsigned long x20; @@ -152,6 +158,7 @@ struct thread_struct { struct user_fpsimd_state fpsimd_state; } uw; + enum fp_type fp_type; /* registers FPSIMD or SVE? */ unsigned int fpsimd_cpu; void *sve_state; /* SVE registers, if any */ void *za_state; /* ZA register, if any */ @@ -396,18 +403,5 @@ long get_tagged_addr_ctrl(struct task_struct *task); #define GET_TAGGED_ADDR_CTRL() get_tagged_addr_ctrl(current) #endif -/* - * For CONFIG_GCC_PLUGIN_STACKLEAK - * - * These need to be macros because otherwise we get stuck in a nightmare - * of header definitions for the use of task_stack_page. - */ - -/* - * The top of the current task's task stack - */ -#define current_top_of_stack() ((unsigned long)current->stack + THREAD_SIZE) -#define on_thread_stack() (on_task_stack(current, current_stack_pointer, 1)) - #endif /* __ASSEMBLY__ */ #endif /* __ASM_PROCESSOR_H */ diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h index 8297bccf0784..ff7da1268a52 100644 --- a/arch/arm64/include/asm/scs.h +++ b/arch/arm64/include/asm/scs.h @@ -5,6 +5,7 @@ #ifdef __ASSEMBLY__ #include <asm/asm-offsets.h> +#include <asm/sysreg.h> #ifdef CONFIG_SHADOW_CALL_STACK scs_sp .req x18 @@ -24,6 +25,54 @@ .endm #endif /* CONFIG_SHADOW_CALL_STACK */ + +#else + +#include <linux/scs.h> +#include <asm/cpufeature.h> + +#ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS +static inline bool should_patch_pac_into_scs(void) +{ + u64 reg; + + /* + * We only enable the shadow call stack dynamically if we are running + * on a system that does not implement PAC or BTI. PAC and SCS provide + * roughly the same level of protection, and BTI relies on the PACIASP + * instructions serving as landing pads, preventing us from patching + * those instructions into something else. + */ + reg = read_sysreg_s(SYS_ID_AA64ISAR1_EL1); + if (SYS_FIELD_GET(ID_AA64ISAR1_EL1, APA, reg) | + SYS_FIELD_GET(ID_AA64ISAR1_EL1, API, reg)) + return false; + + reg = read_sysreg_s(SYS_ID_AA64ISAR2_EL1); + if (SYS_FIELD_GET(ID_AA64ISAR2_EL1, APA3, reg)) + return false; + + if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) { + reg = read_sysreg_s(SYS_ID_AA64PFR1_EL1); + if (reg & (0xf << ID_AA64PFR1_EL1_BT_SHIFT)) + return false; + } + return true; +} + +static inline void dynamic_scs_init(void) +{ + if (should_patch_pac_into_scs()) { + pr_info("Enabling dynamic shadow call stack\n"); + static_branch_enable(&dynamic_scs_enabled); + } +} +#else +static inline void dynamic_scs_init(void) {} +#endif + +int scs_patch(const u8 eh_frame[], int size); + #endif /* __ASSEMBLY __ */ #endif /* _ASM_SCS_H */ diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index 5a0edb064ea4..4e5354beafb0 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -57,6 +57,8 @@ static inline bool on_task_stack(const struct task_struct *tsk, return stackinfo_on_stack(&info, sp, size); } +#define on_thread_stack() (on_task_stack(current, current_stack_pointer, 1)) + #ifdef CONFIG_VMAP_STACK DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack); diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 097488cee174..1312fb48f18b 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -90,20 +90,24 @@ */ #define pstate_field(op1, op2) ((op1) << Op1_shift | (op2) << Op2_shift) #define PSTATE_Imm_shift CRm_shift +#define SET_PSTATE(x, r) __emit_inst(0xd500401f | PSTATE_ ## r | ((!!x) << PSTATE_Imm_shift)) #define PSTATE_PAN pstate_field(0, 4) #define PSTATE_UAO pstate_field(0, 3) #define PSTATE_SSBS pstate_field(3, 1) +#define PSTATE_DIT pstate_field(3, 2) #define PSTATE_TCO pstate_field(3, 4) -#define SET_PSTATE_PAN(x) __emit_inst(0xd500401f | PSTATE_PAN | ((!!x) << PSTATE_Imm_shift)) -#define SET_PSTATE_UAO(x) __emit_inst(0xd500401f | PSTATE_UAO | ((!!x) << PSTATE_Imm_shift)) -#define SET_PSTATE_SSBS(x) __emit_inst(0xd500401f | PSTATE_SSBS | ((!!x) << PSTATE_Imm_shift)) -#define SET_PSTATE_TCO(x) __emit_inst(0xd500401f | PSTATE_TCO | ((!!x) << PSTATE_Imm_shift)) +#define SET_PSTATE_PAN(x) SET_PSTATE((x), PAN) +#define SET_PSTATE_UAO(x) SET_PSTATE((x), UAO) +#define SET_PSTATE_SSBS(x) SET_PSTATE((x), SSBS) +#define SET_PSTATE_DIT(x) SET_PSTATE((x), DIT) +#define SET_PSTATE_TCO(x) SET_PSTATE((x), TCO) #define set_pstate_pan(x) asm volatile(SET_PSTATE_PAN(x)) #define set_pstate_uao(x) asm volatile(SET_PSTATE_UAO(x)) #define set_pstate_ssbs(x) asm volatile(SET_PSTATE_SSBS(x)) +#define set_pstate_dit(x) asm volatile(SET_PSTATE_DIT(x)) #define __SYS_BARRIER_INSN(CRm, op2, Rt) \ __emit_inst(0xd5000000 | sys_insn(0, 3, 3, (CRm), (op2)) | ((Rt) & 0x1f)) diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h index 315eef654e39..ba4bff5ca674 100644 --- a/arch/arm64/include/asm/uprobes.h +++ b/arch/arm64/include/asm/uprobes.h @@ -12,7 +12,7 @@ #define MAX_UINSN_BYTES AARCH64_INSN_SIZE -#define UPROBE_SWBP_INSN BRK64_OPCODE_UPROBES +#define UPROBE_SWBP_INSN cpu_to_le32(BRK64_OPCODE_UPROBES) #define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE #define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 9b245da6f507..b713d30544f1 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -93,5 +93,8 @@ #define HWCAP2_WFXT (1UL << 31) #define HWCAP2_EBF16 (1UL << 32) #define HWCAP2_SVE_EBF16 (1UL << 33) +#define HWCAP2_CSSC (1UL << 34) +#define HWCAP2_RPRFM (1UL << 35) +#define HWCAP2_SVE2P1 (1UL << 36) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 2f361a883d8c..8dd925f4a4c6 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -80,6 +80,8 @@ obj-$(CONFIG_ARM64_PTR_AUTH) += pointer_auth.o obj-$(CONFIG_ARM64_MTE) += mte.o obj-y += vdso-wrap.o obj-$(CONFIG_COMPAT_VDSO) += vdso32-wrap.o +obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS) += patch-scs.o +CFLAGS_patch-scs.o += -mbranch-protection=none # Force dependency (vdso*-wrap.S includes vdso.so through incbin) $(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 1197e7679882..2234624536d9 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -82,6 +82,19 @@ int main(void) DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe)); DEFINE(PT_REGS_SIZE, sizeof(struct pt_regs)); BLANK(); +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS + DEFINE(FREGS_X0, offsetof(struct ftrace_regs, regs[0])); + DEFINE(FREGS_X2, offsetof(struct ftrace_regs, regs[2])); + DEFINE(FREGS_X4, offsetof(struct ftrace_regs, regs[4])); + DEFINE(FREGS_X6, offsetof(struct ftrace_regs, regs[6])); + DEFINE(FREGS_X8, offsetof(struct ftrace_regs, regs[8])); + DEFINE(FREGS_FP, offsetof(struct ftrace_regs, fp)); + DEFINE(FREGS_LR, offsetof(struct ftrace_regs, lr)); + DEFINE(FREGS_SP, offsetof(struct ftrace_regs, sp)); + DEFINE(FREGS_PC, offsetof(struct ftrace_regs, pc)); + DEFINE(FREGS_SIZE, sizeof(struct ftrace_regs)); + BLANK(); +#endif #ifdef CONFIG_COMPAT DEFINE(COMPAT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0)); DEFINE(COMPAT_RT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_rt_sigframe, sig.uc.uc_mcontext.arm_r0)); diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 89ac00084f38..307faa2b4395 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -661,6 +661,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = { CAP_MIDR_RANGE_LIST(trbe_write_out_of_range_cpus), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_2645198 + { + .desc = "ARM erratum 2645198", + .capability = ARM64_WORKAROUND_2645198, + ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A715) + }, +#endif #ifdef CONFIG_ARM64_ERRATUM_2077057 { .desc = "ARM erratum 2077057", diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 935579e5517a..ff74d78145bd 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -212,6 +212,8 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { }; static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), FTR_STRICT, FTR_EXACT, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, 0), @@ -2101,6 +2103,11 @@ static void cpu_trap_el0_impdef(const struct arm64_cpu_capabilities *__unused) sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_TIDCP); } +static void cpu_enable_dit(const struct arm64_cpu_capabilities *__unused) +{ + set_pstate_dit(1); +} + /* Internal helper functions to match cpu capability type */ static bool cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap) @@ -2664,6 +2671,18 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .cpu_enable = cpu_trap_el0_impdef, }, + { + .desc = "Data independent timing control (DIT)", + .capability = ARM64_HAS_DIT, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .sys_reg = SYS_ID_AA64PFR0_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64PFR0_EL1_DIT_SHIFT, + .field_width = 4, + .min_field_value = ID_AA64PFR0_EL1_DIT_IMP, + .matches = has_cpuid_feature, + .cpu_enable = cpu_enable_dit, + }, {}, }; @@ -2772,6 +2791,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_EL1_AT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_SVE_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR0_EL1_SVE_IMP, CAP_HWCAP, KERNEL_HWCAP_SVE), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SVEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SVEver_SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_SVEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_SVEver_SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_AES_IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_EL1_AES_SHIFT, 4, FTR_UNSIGNED, ID_AA64ZFR0_EL1_AES_PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), @@ -2798,6 +2818,8 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { #endif /* CONFIG_ARM64_MTE */ HWCAP_CAP(SYS_ID_AA64MMFR0_EL1, ID_AA64MMFR0_EL1_ECV_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ECV), HWCAP_CAP(SYS_ID_AA64MMFR1_EL1, ID_AA64MMFR1_EL1_AFP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AFP), + HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_CSSC_IMP, CAP_HWCAP, KERNEL_HWCAP_CSSC), + HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_RPRFM_IMP, CAP_HWCAP, KERNEL_HWCAP_RPRFM), HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_RPRES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RPRES), HWCAP_CAP(SYS_ID_AA64ISAR2_EL1, ID_AA64ISAR2_EL1_WFxT_SHIFT, 4, FTR_UNSIGNED, ID_AA64ISAR2_EL1_WFxT_IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT), #ifdef CONFIG_ARM64_SME diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 28d4f442b0bc..379695262b77 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -116,6 +116,9 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_WFXT] = "wfxt", [KERNEL_HWCAP_EBF16] = "ebf16", [KERNEL_HWCAP_SVE_EBF16] = "sveebf16", + [KERNEL_HWCAP_CSSC] = "cssc", + [KERNEL_HWCAP_RPRFM] = "rprfm", + [KERNEL_HWCAP_SVE2P1] = "sve2p1", }; #ifdef CONFIG_COMPAT diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 795344ab4ec4..30cc2a9d1757 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -13,83 +13,58 @@ #include <asm/ftrace.h> #include <asm/insn.h> -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS /* * Due to -fpatchable-function-entry=2, the compiler has placed two NOPs before * the regular function prologue. For an enabled callsite, ftrace_init_nop() and * ftrace_make_call() have patched those NOPs to: * * MOV X9, LR - * BL <entry> - * - * ... where <entry> is either ftrace_caller or ftrace_regs_caller. + * BL ftrace_caller * * Each instrumented function follows the AAPCS, so here x0-x8 and x18-x30 are * live (x18 holds the Shadow Call Stack pointer), and x9-x17 are safe to * clobber. * - * We save the callsite's context into a pt_regs before invoking any ftrace - * callbacks. So that we can get a sensible backtrace, we create a stack record - * for the callsite and the ftrace entry assembly. This is not sufficient for - * reliable stacktrace: until we create the callsite stack record, its caller - * is missing from the LR and existing chain of frame records. + * We save the callsite's context into a struct ftrace_regs before invoking any + * ftrace callbacks. So that we can get a sensible backtrace, we create frame + * records for the callsite and the ftrace entry assembly. This is not + * sufficient for reliable stacktrace: until we create the callsite stack + * record, its caller is missing from the LR and existing chain of frame + * records. */ - .macro ftrace_regs_entry, allregs=0 - /* Make room for pt_regs, plus a callee frame */ - sub sp, sp, #(PT_REGS_SIZE + 16) - - /* Save function arguments (and x9 for simplicity) */ - stp x0, x1, [sp, #S_X0] - stp x2, x3, [sp, #S_X2] - stp x4, x5, [sp, #S_X4] - stp x6, x7, [sp, #S_X6] - stp x8, x9, [sp, #S_X8] - - /* Optionally save the callee-saved registers, always save the FP */ - .if \allregs == 1 - stp x10, x11, [sp, #S_X10] - stp x12, x13, [sp, #S_X12] - stp x14, x15, [sp, #S_X14] - stp x16, x17, [sp, #S_X16] - stp x18, x19, [sp, #S_X18] - stp x20, x21, [sp, #S_X20] - stp x22, x23, [sp, #S_X22] - stp x24, x25, [sp, #S_X24] - stp x26, x27, [sp, #S_X26] - stp x28, x29, [sp, #S_X28] - .else - str x29, [sp, #S_FP] - .endif - - /* Save the callsite's SP and LR */ - add x10, sp, #(PT_REGS_SIZE + 16) - stp x9, x10, [sp, #S_LR] +SYM_CODE_START(ftrace_caller) + bti c - /* Save the PC after the ftrace callsite */ - str x30, [sp, #S_PC] + /* Save original SP */ + mov x10, sp - /* Create a frame record for the callsite above pt_regs */ - stp x29, x9, [sp, #PT_REGS_SIZE] - add x29, sp, #PT_REGS_SIZE + /* Make room for ftrace regs, plus two frame records */ + sub sp, sp, #(FREGS_SIZE + 32) - /* Create our frame record within pt_regs. */ - stp x29, x30, [sp, #S_STACKFRAME] - add x29, sp, #S_STACKFRAME - .endm + /* Save function arguments */ + stp x0, x1, [sp, #FREGS_X0] + stp x2, x3, [sp, #FREGS_X2] + stp x4, x5, [sp, #FREGS_X4] + stp x6, x7, [sp, #FREGS_X6] + str x8, [sp, #FREGS_X8] -SYM_CODE_START(ftrace_regs_caller) - bti c - ftrace_regs_entry 1 - b ftrace_common -SYM_CODE_END(ftrace_regs_caller) + /* Save the callsite's FP, LR, SP */ + str x29, [sp, #FREGS_FP] + str x9, [sp, #FREGS_LR] + str x10, [sp, #FREGS_SP] -SYM_CODE_START(ftrace_caller) - bti c - ftrace_regs_entry 0 - b ftrace_common -SYM_CODE_END(ftrace_caller) + /* Save the PC after the ftrace callsite */ + str x30, [sp, #FREGS_PC] + + /* Create a frame record for the callsite above the ftrace regs */ + stp x29, x9, [sp, #FREGS_SIZE + 16] + add x29, sp, #FREGS_SIZE + 16 + + /* Create our frame record above the ftrace regs */ + stp x29, x30, [sp, #FREGS_SIZE] + add x29, sp, #FREGS_SIZE -SYM_CODE_START(ftrace_common) sub x0, x30, #AARCH64_INSN_SIZE // ip (callsite's BL insn) mov x1, x9 // parent_ip (callsite's LR) ldr_l x2, function_trace_op // op @@ -104,24 +79,24 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) * to restore x0-x8, x29, and x30. */ /* Restore function arguments */ - ldp x0, x1, [sp] - ldp x2, x3, [sp, #S_X2] - ldp x4, x5, [sp, #S_X4] - ldp x6, x7, [sp, #S_X6] - ldr x8, [sp, #S_X8] + ldp x0, x1, [sp, #FREGS_X0] + ldp x2, x3, [sp, #FREGS_X2] + ldp x4, x5, [sp, #FREGS_X4] + ldp x6, x7, [sp, #FREGS_X6] + ldr x8, [sp, #FREGS_X8] /* Restore the callsite's FP, LR, PC */ - ldr x29, [sp, #S_FP] - ldr x30, [sp, #S_LR] - ldr x9, [sp, #S_PC] + ldr x29, [sp, #FREGS_FP] + ldr x30, [sp, #FREGS_LR] + ldr x9, [sp, #FREGS_PC] /* Restore the callsite's SP */ - add sp, sp, #PT_REGS_SIZE + 16 + add sp, sp, #FREGS_SIZE + 32 ret x9 -SYM_CODE_END(ftrace_common) +SYM_CODE_END(ftrace_caller) -#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ +#else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ /* * Gcc with -pg will put the following code in the beginning of each function: @@ -195,44 +170,6 @@ SYM_CODE_END(ftrace_common) add \reg, \reg, #8 .endm -#ifndef CONFIG_DYNAMIC_FTRACE -/* - * void _mcount(unsigned long return_address) - * @return_address: return address to instrumented function - * - * This function makes calls, if enabled, to: - * - tracer function to probe instrumented function's entry, - * - ftrace_graph_caller to set up an exit hook - */ -SYM_FUNC_START(_mcount) - mcount_enter - - ldr_l x2, ftrace_trace_function - adr x0, ftrace_stub - cmp x0, x2 // if (ftrace_trace_function - b.eq skip_ftrace_call // != ftrace_stub) { - - mcount_get_pc x0 // function's pc - mcount_get_lr x1 // function's lr (= parent's pc) - blr x2 // (*ftrace_trace_function)(pc, lr); - -skip_ftrace_call: // } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - ldr_l x2, ftrace_graph_return - cmp x0, x2 // if ((ftrace_graph_return - b.ne ftrace_graph_caller // != ftrace_stub) - - ldr_l x2, ftrace_graph_entry // || (ftrace_graph_entry - adr_l x0, ftrace_graph_entry_stub // != ftrace_graph_entry_stub)) - cmp x0, x2 - b.ne ftrace_graph_caller // ftrace_graph_caller(); -#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ - mcount_exit -SYM_FUNC_END(_mcount) -EXPORT_SYMBOL(_mcount) -NOKPROBE(_mcount) - -#else /* CONFIG_DYNAMIC_FTRACE */ /* * _mcount() is used to build the kernel with -pg option, but all the branch * instructions to _mcount() are replaced to NOP initially at kernel start up, @@ -272,7 +209,6 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL) // ftrace_graph_caller(); mcount_exit SYM_FUNC_END(ftrace_caller) -#endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* @@ -293,7 +229,7 @@ SYM_FUNC_START(ftrace_graph_caller) mcount_exit SYM_FUNC_END(ftrace_graph_caller) #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ -#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ SYM_TYPED_FUNC_START(ftrace_stub) ret diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index e28137d64b76..11cb99c4d298 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -197,6 +197,9 @@ alternative_cb_end .endm .macro kernel_entry, el, regsize = 64 + .if \el == 0 + alternative_insn nop, SET_PSTATE_DIT(1), ARM64_HAS_DIT + .endif .if \regsize == 32 mov w0, w0 // zero upper 32 bits of x0 .endif diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 23834d96d1e7..dcc81e7200d4 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -118,16 +118,8 @@ * returned from the 2nd syscall yet, TIF_FOREIGN_FPSTATE is still set so * whatever is in the FPSIMD registers is not saved to memory, but discarded. */ -struct fpsimd_last_state_struct { - struct user_fpsimd_state *st; - void *sve_state; - void *za_state; - u64 *svcr; - unsigned int sve_vl; - unsigned int sme_vl; -}; -static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state); +static DEFINE_PER_CPU(struct cpu_fp_state, fpsimd_last_state); __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX] = { #ifdef CONFIG_ARM64_SVE @@ -330,15 +322,6 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, * The task can execute SVE instructions while in userspace without * trapping to the kernel. * - * When stored, Z0-Z31 (incorporating Vn in bits[127:0] or the - * corresponding Zn), P0-P15 and FFR are encoded in - * task->thread.sve_state, formatted appropriately for vector - * length task->thread.sve_vl or, if SVCR.SM is set, - * task->thread.sme_vl. - * - * task->thread.sve_state must point to a valid buffer at least - * sve_state_size(task) bytes in size. - * * During any syscall, the kernel may optionally clear TIF_SVE and * discard the vector state except for the FPSIMD subset. * @@ -348,7 +331,15 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, * do_sve_acc() to be called, which does some preparation and then * sets TIF_SVE. * - * When stored, FPSIMD registers V0-V31 are encoded in + * During any syscall, the kernel may optionally clear TIF_SVE and + * discard the vector state except for the FPSIMD subset. + * + * The data will be stored in one of two formats: + * + * * FPSIMD only - FP_STATE_FPSIMD: + * + * When the FPSIMD only state stored task->thread.fp_type is set to + * FP_STATE_FPSIMD, the FPSIMD registers V0-V31 are encoded in * task->thread.uw.fpsimd_state; bits [max : 128] for each of Z0-Z31 are * logically zero but not stored anywhere; P0-P15 and FFR are not * stored and have unspecified values from userspace's point of @@ -356,7 +347,23 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, * but userspace is discouraged from relying on this. * * task->thread.sve_state does not need to be non-NULL, valid or any - * particular size: it must not be dereferenced. + * particular size: it must not be dereferenced and any data stored + * there should be considered stale and not referenced. + * + * * SVE state - FP_STATE_SVE: + * + * When the full SVE state is stored task->thread.fp_type is set to + * FP_STATE_SVE and Z0-Z31 (incorporating Vn in bits[127:0] or the + * corresponding Zn), P0-P15 and FFR are encoded in in + * task->thread.sve_state, formatted appropriately for vector + * length task->thread.sve_vl or, if SVCR.SM is set, + * task->thread.sme_vl. The storage for the vector registers in + * task->thread.uw.fpsimd_state should be ignored. + * + * task->thread.sve_state must point to a valid buffer at least + * sve_state_size(task) bytes in size. The data stored in + * task->thread.uw.fpsimd_state.vregs should be considered stale + * and not referenced. * * * FPSR and FPCR are always stored in task->thread.uw.fpsimd_state * irrespective of whether TIF_SVE is clear or set, since these are @@ -378,11 +385,37 @@ static void task_fpsimd_load(void) WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context()); - /* Check if we should restore SVE first */ - if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) { - sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1); - restore_sve_regs = true; - restore_ffr = true; + if (system_supports_sve()) { + switch (current->thread.fp_type) { + case FP_STATE_FPSIMD: + /* Stop tracking SVE for this task until next use. */ + if (test_and_clear_thread_flag(TIF_SVE)) + sve_user_disable(); + break; + case FP_STATE_SVE: + if (!thread_sm_enabled(¤t->thread) && + !WARN_ON_ONCE(!test_and_set_thread_flag(TIF_SVE))) + sve_user_enable(); + + if (test_thread_flag(TIF_SVE)) + sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1); + + restore_sve_regs = true; + restore_ffr = true; + break; + default: + /* + * This indicates either a bug in + * fpsimd_save() or memory corruption, we + * should always record an explicit format + * when we save. We always at least have the + * memory allocated for FPSMID registers so + * try that and hope for the best. + */ + WARN_ON_ONCE(1); + clear_thread_flag(TIF_SVE); + break; + } } /* Restore SME, override SVE register configuration if needed */ @@ -398,18 +431,19 @@ static void task_fpsimd_load(void) if (thread_za_enabled(¤t->thread)) za_load_state(current->thread.za_state); - if (thread_sm_enabled(¤t->thread)) { - restore_sve_regs = true; + if (thread_sm_enabled(¤t->thread)) restore_ffr = system_supports_fa64(); - } } - if (restore_sve_regs) + if (restore_sve_regs) { + WARN_ON_ONCE(current->thread.fp_type != FP_STATE_SVE); sve_load_state(sve_pffr(¤t->thread), ¤t->thread.uw.fpsimd_state.fpsr, restore_ffr); - else + } else { + WARN_ON_ONCE(current->thread.fp_type != FP_STATE_FPSIMD); fpsimd_load_state(¤t->thread.uw.fpsimd_state); + } } /* @@ -419,12 +453,12 @@ static void task_fpsimd_load(void) * last, if KVM is involved this may be the guest VM context rather * than the host thread for the VM pointed to by current. This means * that we must always reference the state storage via last rather - * than via current, other than the TIF_ flags which KVM will - * carefully maintain for us. + * than via current, if we are saving KVM state then it will have + * ensured that the type of registers to save is set in last->to_save. */ static void fpsimd_save(void) { - struct fpsimd_last_state_struct const *last = + struct cpu_fp_state const *last = this_cpu_ptr(&fpsimd_last_state); /* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */ bool save_sve_regs = false; @@ -437,7 +471,14 @@ static void fpsimd_save(void) if (test_thread_flag(TIF_FOREIGN_FPSTATE)) return; - if (test_thread_flag(TIF_SVE)) { + /* + * If a task is in a syscall the ABI allows us to only + * preserve the state shared with FPSIMD so don't bother + * saving the full SVE state in that case. + */ + if ((last->to_save == FP_STATE_CURRENT && test_thread_flag(TIF_SVE) && + !in_syscall(current_pt_regs())) || + last->to_save == FP_STATE_SVE) { save_sve_regs = true; save_ffr = true; vl = last->sve_vl; @@ -474,8 +515,10 @@ static void fpsimd_save(void) sve_save_state((char *)last->sve_state + sve_ffr_offset(vl), &last->st->fpsr, save_ffr); + *last->fp_type = FP_STATE_SVE; } else { fpsimd_save_state(last->st); + *last->fp_type = FP_STATE_FPSIMD; } } @@ -768,8 +811,7 @@ void fpsimd_sync_to_sve(struct task_struct *task) */ void sve_sync_to_fpsimd(struct task_struct *task) { - if (test_tsk_thread_flag(task, TIF_SVE) || - thread_sm_enabled(&task->thread)) + if (task->thread.fp_type == FP_STATE_SVE) sve_to_fpsimd(task); } @@ -848,8 +890,10 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, fpsimd_flush_task_state(task); if (test_and_clear_tsk_thread_flag(task, TIF_SVE) || - thread_sm_enabled(&task->thread)) + thread_sm_enabled(&task->thread)) { sve_to_fpsimd(task); + task->thread.fp_type = FP_STATE_FPSIMD; + } if (system_supports_sme() && type == ARM64_VEC_SME) { task->thread.svcr &= ~(SVCR_SM_MASK | @@ -1368,6 +1412,7 @@ static void sve_init_regs(void) fpsimd_bind_task_to_cpu(); } else { fpsimd_to_sve(current); + current->thread.fp_type = FP_STATE_SVE; } } @@ -1596,6 +1641,8 @@ void fpsimd_flush_thread(void) current->thread.svcr = 0; } + current->thread.fp_type = FP_STATE_FPSIMD; + put_cpu_fpsimd_context(); kfree(sve_state); kfree(za_state); @@ -1628,14 +1675,38 @@ void fpsimd_signal_preserve_current_state(void) } /* + * Called by KVM when entering the guest. + */ +void fpsimd_kvm_prepare(void) +{ + if (!system_supports_sve()) + return; + + /* + * KVM does not save host SVE state since we can only enter + * the guest from a syscall so the ABI means that only the + * non-saved SVE state needs to be saved. If we have left + * SVE enabled for performance reasons then update the task + * state to be FPSIMD only. + */ + get_cpu_fpsimd_context(); + + if (test_and_clear_thread_flag(TIF_SVE)) { + sve_to_fpsimd(current); + current->thread.fp_type = FP_STATE_FPSIMD; + } + + put_cpu_fpsimd_context(); +} + +/* * Associate current's FPSIMD context with this cpu * The caller must have ownership of the cpu FPSIMD context before calling * this function. */ static void fpsimd_bind_task_to_cpu(void) { - struct fpsimd_last_state_struct *last = - this_cpu_ptr(&fpsimd_last_state); + struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state); WARN_ON(!system_supports_fpsimd()); last->st = ¤t->thread.uw.fpsimd_state; @@ -1644,6 +1715,8 @@ static void fpsimd_bind_task_to_cpu(void) last->sve_vl = task_get_sve_vl(current); last->sme_vl = task_get_sme_vl(current); last->svcr = ¤t->thread.svcr; + last->fp_type = ¤t->thread.fp_type; + last->to_save = FP_STATE_CURRENT; current->thread.fpsimd_cpu = smp_processor_id(); /* @@ -1665,22 +1738,14 @@ static void fpsimd_bind_task_to_cpu(void) } } -void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, - unsigned int sve_vl, void *za_state, - unsigned int sme_vl, u64 *svcr) +void fpsimd_bind_state_to_cpu(struct cpu_fp_state *state) { - struct fpsimd_last_state_struct *last = - this_cpu_ptr(&fpsimd_last_state); + struct cpu_fp_state *last = this_cpu_ptr(&fpsimd_last_state); WARN_ON(!system_supports_fpsimd()); WARN_ON(!in_softirq() && !irqs_disabled()); - last->st = st; - last->svcr = svcr; - last->sve_state = sve_state; - last->za_state = za_state; - last->sve_vl = sve_vl; - last->sme_vl = sme_vl; + *last = *state; } /* @@ -1838,7 +1903,7 @@ void kernel_neon_begin(void) /* Invalidate any task state remaining in the fpsimd regs: */ fpsimd_flush_cpu_state(); } -EXPORT_SYMBOL(kernel_neon_begin); +EXPORT_SYMBOL_GPL(kernel_neon_begin); /* * kernel_neon_end(): give the CPU FPSIMD registers back to the current task @@ -1856,7 +1921,7 @@ void kernel_neon_end(void) put_cpu_fpsimd_context(); } -EXPORT_SYMBOL(kernel_neon_end); +EXPORT_SYMBOL_GPL(kernel_neon_end); #ifdef CONFIG_EFI diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index 8745175f4a75..b30b955a8921 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -17,7 +17,49 @@ #include <asm/insn.h> #include <asm/patching.h> -#ifdef CONFIG_DYNAMIC_FTRACE +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS +struct fregs_offset { + const char *name; + int offset; +}; + +#define FREGS_OFFSET(n, field) \ +{ \ + .name = n, \ + .offset = offsetof(struct ftrace_regs, field), \ +} + +static const struct fregs_offset fregs_offsets[] = { + FREGS_OFFSET("x0", regs[0]), + FREGS_OFFSET("x1", regs[1]), + FREGS_OFFSET("x2", regs[2]), + FREGS_OFFSET("x3", regs[3]), + FREGS_OFFSET("x4", regs[4]), + FREGS_OFFSET("x5", regs[5]), + FREGS_OFFSET("x6", regs[6]), + FREGS_OFFSET("x7", regs[7]), + FREGS_OFFSET("x8", regs[8]), + + FREGS_OFFSET("x29", fp), + FREGS_OFFSET("x30", lr), + FREGS_OFFSET("lr", lr), + + FREGS_OFFSET("sp", sp), + FREGS_OFFSET("pc", pc), +}; + +int ftrace_regs_query_register_offset(const char *name) +{ + for (int i = 0; i < ARRAY_SIZE(fregs_offsets); i++) { + const struct fregs_offset *roff = &fregs_offsets[i]; + if (!strcmp(roff->name, name)) + return roff->offset; + } + + return -EINVAL; +} +#endif + /* * Replace a single instruction, which may be a branch or NOP. * If @validate == true, a replaced instruction is checked against 'old'. @@ -70,9 +112,6 @@ static struct plt_entry *get_ftrace_plt(struct module *mod, unsigned long addr) if (addr == FTRACE_ADDR) return &plt[FTRACE_PLT_IDX]; - if (addr == FTRACE_REGS_ADDR && - IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) - return &plt[FTRACE_REGS_PLT_IDX]; #endif return NULL; } @@ -154,25 +193,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return ftrace_modify_code(pc, old, new, true); } -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS -int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, - unsigned long addr) -{ - unsigned long pc = rec->ip; - u32 old, new; - - if (!ftrace_find_callable_addr(rec, NULL, &old_addr)) - return -EINVAL; - if (!ftrace_find_callable_addr(rec, NULL, &addr)) - return -EINVAL; - - old = aarch64_insn_gen_branch_imm(pc, old_addr, - AARCH64_INSN_BRANCH_LINK); - new = aarch64_insn_gen_branch_imm(pc, addr, AARCH64_INSN_BRANCH_LINK); - - return ftrace_modify_code(pc, old, new, true); -} - +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS /* * The compiler has inserted two NOPs before the regular function prologue. * All instrumented functions follow the AAPCS, so x0-x8 and x19-x30 are live, @@ -228,7 +249,7 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, * * Note: 'mod' is only set at module load time. */ - if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) && + if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS) && IS_ENABLED(CONFIG_ARM64_MODULE_PLTS) && mod) { return aarch64_insn_patch_text_nosync((void *)pc, new); } @@ -246,7 +267,6 @@ void arch_ftrace_update_code(int command) command |= FTRACE_MAY_SLEEP; ftrace_modify_all_code(command); } -#endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER /* @@ -277,21 +297,11 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent, } } -#ifdef CONFIG_DYNAMIC_FTRACE - -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs) { - /* - * When DYNAMIC_FTRACE_WITH_REGS is selected, `fregs` can never be NULL - * and arch_ftrace_get_regs(fregs) will always give a non-NULL pt_regs - * in which we can safely modify the LR. - */ - struct pt_regs *regs = arch_ftrace_get_regs(fregs); - unsigned long *parent = (unsigned long *)&procedure_link_pointer(regs); - - prepare_ftrace_return(ip, parent, frame_pointer(regs)); + prepare_ftrace_return(ip, &fregs->lr, fregs->fp); } #else /* @@ -323,6 +333,5 @@ int ftrace_disable_ftrace_graph_caller(void) { return ftrace_modify_graph_caller(false); } -#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */ -#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 2196aad7b55b..952e17bd1c0b 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -462,6 +462,9 @@ SYM_FUNC_START_LOCAL(__primary_switched) bl early_fdt_map // Try mapping the FDT early mov x0, x20 // pass the full boot status bl init_feature_override // Parse cpu feature overrides +#ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS + bl scs_patch_vmlinux +#endif mov x0, x20 bl finalise_el2 // Prefer VHE if possible ldp x29, x30, [sp], #16 diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 38dbd3828f13..6ad5c6ef5329 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -10,20 +10,21 @@ * Copyright (C) 2012 ARM Ltd. */ -#include <linux/irq.h> -#include <linux/memory.h> -#include <linux/smp.h> #include <linux/hardirq.h> #include <linux/init.h> +#include <linux/irq.h> #include <linux/irqchip.h> #include <linux/kprobes.h> +#include <linux/memory.h> #include <linux/scs.h> #include <linux/seq_file.h> +#include <linux/smp.h> #include <linux/vmalloc.h> #include <asm/daifflags.h> #include <asm/exception.h> -#include <asm/vmap_stack.h> #include <asm/softirq_stack.h> +#include <asm/stacktrace.h> +#include <asm/vmap_stack.h> /* Only access this in an NMI enter/exit */ DEFINE_PER_CPU(struct nmi_ctx, nmi_contexts); @@ -41,7 +42,7 @@ static void init_irq_scs(void) { int cpu; - if (!IS_ENABLED(CONFIG_SHADOW_CALL_STACK)) + if (!scs_is_enabled()) return; for_each_possible_cpu(cpu) diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index 76b41e4ca9fa..5af4975caeb5 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -15,9 +15,11 @@ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/moduleloader.h> +#include <linux/scs.h> #include <linux/vmalloc.h> #include <asm/alternative.h> #include <asm/insn.h> +#include <asm/scs.h> #include <asm/sections.h> void *module_alloc(unsigned long size) @@ -497,9 +499,6 @@ static int module_init_ftrace_plt(const Elf_Ehdr *hdr, __init_plt(&plts[FTRACE_PLT_IDX], FTRACE_ADDR); - if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS)) - __init_plt(&plts[FTRACE_REGS_PLT_IDX], FTRACE_REGS_ADDR); - mod->arch.ftrace_trampolines = plts; #endif return 0; @@ -514,5 +513,11 @@ int module_finalize(const Elf_Ehdr *hdr, if (s) apply_alternatives_module((void *)s->sh_addr, s->sh_size); + if (scs_is_dynamic()) { + s = find_section(hdr, sechdrs, ".init.eh_frame"); + if (s) + scs_patch((void *)s->sh_addr, s->sh_size); + } + return module_init_ftrace_plt(hdr, sechdrs, me); } diff --git a/arch/arm64/kernel/patch-scs.c b/arch/arm64/kernel/patch-scs.c new file mode 100644 index 000000000000..1b3da02d5b74 --- /dev/null +++ b/arch/arm64/kernel/patch-scs.c @@ -0,0 +1,257 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2022 - Google LLC + * Author: Ard Biesheuvel <ardb@google.com> + */ + +#include <linux/bug.h> +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/linkage.h> +#include <linux/printk.h> +#include <linux/types.h> + +#include <asm/cacheflush.h> +#include <asm/scs.h> + +// +// This minimal DWARF CFI parser is partially based on the code in +// arch/arc/kernel/unwind.c, and on the document below: +// https://refspecs.linuxbase.org/LSB_4.0.0/LSB-Core-generic/LSB-Core-generic/ehframechpt.html +// + +#define DW_CFA_nop 0x00 +#define DW_CFA_set_loc 0x01 +#define DW_CFA_advance_loc1 0x02 +#define DW_CFA_advance_loc2 0x03 +#define DW_CFA_advance_loc4 0x04 +#define DW_CFA_offset_extended 0x05 +#define DW_CFA_restore_extended 0x06 +#define DW_CFA_undefined 0x07 +#define DW_CFA_same_value 0x08 +#define DW_CFA_register 0x09 +#define DW_CFA_remember_state 0x0a +#define DW_CFA_restore_state 0x0b +#define DW_CFA_def_cfa 0x0c +#define DW_CFA_def_cfa_register 0x0d +#define DW_CFA_def_cfa_offset 0x0e +#define DW_CFA_def_cfa_expression 0x0f +#define DW_CFA_expression 0x10 +#define DW_CFA_offset_extended_sf 0x11 +#define DW_CFA_def_cfa_sf 0x12 +#define DW_CFA_def_cfa_offset_sf 0x13 +#define DW_CFA_val_offset 0x14 +#define DW_CFA_val_offset_sf 0x15 +#define DW_CFA_val_expression 0x16 +#define DW_CFA_lo_user 0x1c +#define DW_CFA_negate_ra_state 0x2d +#define DW_CFA_GNU_args_size 0x2e +#define DW_CFA_GNU_negative_offset_extended 0x2f +#define DW_CFA_hi_user 0x3f + +extern const u8 __eh_frame_start[], __eh_frame_end[]; + +enum { + PACIASP = 0xd503233f, + AUTIASP = 0xd50323bf, + SCS_PUSH = 0xf800865e, + SCS_POP = 0xf85f8e5e, +}; + +static void __always_inline scs_patch_loc(u64 loc) +{ + u32 insn = le32_to_cpup((void *)loc); + + switch (insn) { + case PACIASP: + *(u32 *)loc = cpu_to_le32(SCS_PUSH); + break; + case AUTIASP: + *(u32 *)loc = cpu_to_le32(SCS_POP); + break; + default: + /* + * While the DW_CFA_negate_ra_state directive is guaranteed to + * appear right after a PACIASP/AUTIASP instruction, it may + * also appear after a DW_CFA_restore_state directive that + * restores a state that is only partially accurate, and is + * followed by DW_CFA_negate_ra_state directive to toggle the + * PAC bit again. So we permit other instructions here, and ignore + * them. + */ + return; + } + dcache_clean_pou(loc, loc + sizeof(u32)); +} + +/* + * Skip one uleb128/sleb128 encoded quantity from the opcode stream. All bytes + * except the last one have bit #7 set. + */ +static int __always_inline skip_xleb128(const u8 **opcode, int size) +{ + u8 c; + + do { + c = *(*opcode)++; + size--; + } while (c & BIT(7)); + + return size; +} + +struct eh_frame { + /* + * The size of this frame if 0 < size < U32_MAX, 0 terminates the list. + */ + u32 size; + + /* + * The first frame is a Common Information Entry (CIE) frame, followed + * by one or more Frame Description Entry (FDE) frames. In the former + * case, this field is 0, otherwise it is the negated offset relative + * to the associated CIE frame. + */ + u32 cie_id_or_pointer; + + union { + struct { // CIE + u8 version; + u8 augmentation_string[]; + }; + + struct { // FDE + s32 initial_loc; + s32 range; + u8 opcodes[]; + }; + }; +}; + +static int noinstr scs_handle_fde_frame(const struct eh_frame *frame, + bool fde_has_augmentation_data, + int code_alignment_factor) +{ + int size = frame->size - offsetof(struct eh_frame, opcodes) + 4; + u64 loc = (u64)offset_to_ptr(&frame->initial_loc); + const u8 *opcode = frame->opcodes; + + if (fde_has_augmentation_data) { + int l; + + // assume single byte uleb128_t + if (WARN_ON(*opcode & BIT(7))) + return -ENOEXEC; + + l = *opcode++; + opcode += l; + size -= l + 1; + } + + /* + * Starting from 'loc', apply the CFA opcodes that advance the location + * pointer, and identify the locations of the PAC instructions. + */ + while (size-- > 0) { + switch (*opcode++) { + case DW_CFA_nop: + case DW_CFA_remember_state: + case DW_CFA_restore_state: + break; + + case DW_CFA_advance_loc1: + loc += *opcode++ * code_alignment_factor; + size--; + break; + + case DW_CFA_advance_loc2: + loc += *opcode++ * code_alignment_factor; + loc += (*opcode++ << 8) * code_alignment_factor; + size -= 2; + break; + + case DW_CFA_def_cfa: + case DW_CFA_offset_extended: + size = skip_xleb128(&opcode, size); + fallthrough; + case DW_CFA_def_cfa_offset: + case DW_CFA_def_cfa_offset_sf: + case DW_CFA_def_cfa_register: + case DW_CFA_same_value: + case DW_CFA_restore_extended: + case 0x80 ... 0xbf: + size = skip_xleb128(&opcode, size); + break; + + case DW_CFA_negate_ra_state: + scs_patch_loc(loc - 4); + break; + + case 0x40 ... 0x7f: + // advance loc + loc += (opcode[-1] & 0x3f) * code_alignment_factor; + break; + + case 0xc0 ... 0xff: + break; + + default: + pr_err("unhandled opcode: %02x in FDE frame %lx\n", opcode[-1], (uintptr_t)frame); + return -ENOEXEC; + } + } + return 0; +} + +int noinstr scs_patch(const u8 eh_frame[], int size) +{ + const u8 *p = eh_frame; + + while (size > 4) { + const struct eh_frame *frame = (const void *)p; + bool fde_has_augmentation_data = true; + int code_alignment_factor = 1; + int ret; + + if (frame->size == 0 || + frame->size == U32_MAX || + frame->size > size) + break; + + if (frame->cie_id_or_pointer == 0) { + const u8 *p = frame->augmentation_string; + + /* a 'z' in the augmentation string must come first */ + fde_has_augmentation_data = *p == 'z'; + + /* + * The code alignment factor is a uleb128 encoded field + * but given that the only sensible values are 1 or 4, + * there is no point in decoding the whole thing. + */ + p += strlen(p) + 1; + if (!WARN_ON(*p & BIT(7))) + code_alignment_factor = *p; + } else { + ret = scs_handle_fde_frame(frame, + fde_has_augmentation_data, + code_alignment_factor); + if (ret) + return ret; + } + + p += sizeof(frame->size) + frame->size; + size -= sizeof(frame->size) + frame->size; + } + return 0; +} + +asmlinkage void __init scs_patch_vmlinux(void) +{ + if (!should_patch_pac_into_scs()) + return; + + WARN_ON(scs_patch(__eh_frame_start, __eh_frame_end - __eh_frame_start)); + icache_inval_all_pou(); + isb(); +} diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 7b0643fe2f13..a15b3c1d15d9 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -1146,7 +1146,8 @@ static void __armv8pmu_probe_pmu(void *info) dfr0 = read_sysreg(id_aa64dfr0_el1); pmuver = cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMUVer_SHIFT); - if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF || pmuver == 0) + if (pmuver == ID_AA64DFR0_EL1_PMUVer_IMP_DEF || + pmuver == ID_AA64DFR0_EL1_PMUVer_NI) return; cpu_pmu->pmuver = pmuver; diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile index 839291430cb3..4c0ea3cd4ea4 100644 --- a/arch/arm64/kernel/pi/Makefile +++ b/arch/arm64/kernel/pi/Makefile @@ -7,6 +7,7 @@ KBUILD_CFLAGS := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \ -I$(srctree)/scripts/dtc/libfdt -fno-stack-protector \ -include $(srctree)/include/linux/hidden.h \ -D__DISABLE_EXPORTS -ffreestanding -D__NO_FORTIFY \ + -fno-asynchronous-unwind-tables -fno-unwind-tables \ $(call cc-option,-fno-addrsig) # remove SCS flags from all objects in this directory diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c index 104101f633b1..968d5fffe233 100644 --- a/arch/arm64/kernel/probes/decode-insn.c +++ b/arch/arm64/kernel/probes/decode-insn.c @@ -24,7 +24,7 @@ static bool __kprobes aarch64_insn_is_steppable(u32 insn) * currently safe. Lastly, MSR instructions can do any number of nasty * things we can't handle during single-stepping. */ - if (aarch64_get_insn_class(insn) == AARCH64_INSN_CLS_BR_SYS) { + if (aarch64_insn_is_class_branch_sys(insn)) { if (aarch64_insn_is_branch(insn) || aarch64_insn_is_msr_imm(insn) || aarch64_insn_is_msr_reg(insn) || diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index c9e4d0720285..f35d059a9a36 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -294,19 +294,12 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr) } break; - case KPROBE_HIT_ACTIVE: - case KPROBE_HIT_SSDONE: - /* - * In case the user-specified fault handler returned - * zero, try to fix up. - */ - if (fixup_exception(regs)) - return 1; } return 0; } -static void __kprobes kprobe_handler(struct pt_regs *regs) +static int __kprobes +kprobe_breakpoint_handler(struct pt_regs *regs, unsigned long esr) { struct kprobe *p, *cur_kprobe; struct kprobe_ctlblk *kcb; @@ -316,39 +309,44 @@ static void __kprobes kprobe_handler(struct pt_regs *regs) cur_kprobe = kprobe_running(); p = get_kprobe((kprobe_opcode_t *) addr); + if (WARN_ON_ONCE(!p)) { + /* + * Something went wrong. This BRK used an immediate reserved + * for kprobes, but we couldn't find any corresponding probe. + */ + return DBG_HOOK_ERROR; + } - if (p) { - if (cur_kprobe) { - if (reenter_kprobe(p, regs, kcb)) - return; - } else { - /* Probe hit */ - set_current_kprobe(p); - kcb->kprobe_status = KPROBE_HIT_ACTIVE; - - /* - * If we have no pre-handler or it returned 0, we - * continue with normal processing. If we have a - * pre-handler and it returned non-zero, it will - * modify the execution path and no need to single - * stepping. Let's just reset current kprobe and exit. - */ - if (!p->pre_handler || !p->pre_handler(p, regs)) { - setup_singlestep(p, regs, kcb, 0); - } else - reset_current_kprobe(); - } + if (cur_kprobe) { + /* Hit a kprobe inside another kprobe */ + if (!reenter_kprobe(p, regs, kcb)) + return DBG_HOOK_ERROR; + } else { + /* Probe hit */ + set_current_kprobe(p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + + /* + * If we have no pre-handler or it returned 0, we + * continue with normal processing. If we have a + * pre-handler and it returned non-zero, it will + * modify the execution path and not need to single-step + * Let's just reset current kprobe and exit. + */ + if (!p->pre_handler || !p->pre_handler(p, regs)) + setup_singlestep(p, regs, kcb, 0); + else + reset_current_kprobe(); } - /* - * The breakpoint instruction was removed right - * after we hit it. Another cpu has removed - * either a probepoint or a debugger breakpoint - * at this address. In either case, no further - * handling of this interrupt is appropriate. - * Return back to original instruction, and continue. - */ + + return DBG_HOOK_HANDLED; } +static struct break_hook kprobes_break_hook = { + .imm = KPROBES_BRK_IMM, + .fn = kprobe_breakpoint_handler, +}; + static int __kprobes kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned long esr) { @@ -373,18 +371,6 @@ static struct break_hook kprobes_break_ss_hook = { .fn = kprobe_breakpoint_ss_handler, }; -static int __kprobes -kprobe_breakpoint_handler(struct pt_regs *regs, unsigned long esr) -{ - kprobe_handler(regs); - return DBG_HOOK_HANDLED; -} - -static struct break_hook kprobes_break_hook = { - .imm = KPROBES_BRK_IMM, - .fn = kprobe_breakpoint_handler, -}; - /* * Provide a blacklist of symbols identifying ranges which cannot be kprobed. * This blacklist is exposed to userspace via debugfs (kprobes/blacklist). diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 044a7d7f1f6a..19cd05eea3f0 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -331,6 +331,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) clear_tsk_thread_flag(dst, TIF_SME); } + dst->thread.fp_type = FP_STATE_FPSIMD; + /* clear any pending asynchronous tag fault raised by the parent */ clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT); diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index c2fb5755bbec..979dbdc36d52 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -907,8 +907,7 @@ static int sve_set_common(struct task_struct *target, ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, SVE_PT_FPSIMD_OFFSET); clear_tsk_thread_flag(target, TIF_SVE); - if (type == ARM64_VEC_SME) - fpsimd_force_sync_to_sve(target); + target->thread.fp_type = FP_STATE_FPSIMD; goto out; } @@ -931,6 +930,7 @@ static int sve_set_common(struct task_struct *target, if (!target->thread.sve_state) { ret = -ENOMEM; clear_tsk_thread_flag(target, TIF_SVE); + target->thread.fp_type = FP_STATE_FPSIMD; goto out; } @@ -942,6 +942,7 @@ static int sve_set_common(struct task_struct *target, */ fpsimd_sync_to_sve(target); set_tsk_thread_flag(target, TIF_SVE); + target->thread.fp_type = FP_STATE_SVE; BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); start = SVE_PT_SVE_OFFSET; diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c index d56e170e1ca7..830be01af32d 100644 --- a/arch/arm64/kernel/sdei.c +++ b/arch/arm64/kernel/sdei.c @@ -144,7 +144,7 @@ static int init_sdei_scs(void) int cpu; int err = 0; - if (!IS_ENABLED(CONFIG_SHADOW_CALL_STACK)) + if (!scs_is_enabled()) return 0; for_each_possible_cpu(cpu) { diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index fea3223704b6..12cfe9d0d3fa 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -30,6 +30,7 @@ #include <linux/efi.h> #include <linux/psci.h> #include <linux/sched/task.h> +#include <linux/scs.h> #include <linux/mm.h> #include <asm/acpi.h> @@ -42,6 +43,7 @@ #include <asm/cpu_ops.h> #include <asm/kasan.h> #include <asm/numa.h> +#include <asm/scs.h> #include <asm/sections.h> #include <asm/setup.h> #include <asm/smp_plat.h> @@ -312,6 +314,8 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) jump_label_init(); parse_early_param(); + dynamic_scs_init(); + /* * Unmask asynchronous aborts and fiq after bringing up possible * earlycon. (Report possible System Errors once we can report this diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 9ad911f1647c..e0d09bf5b01b 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -207,6 +207,7 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx) __get_user_error(fpsimd.fpcr, &ctx->fpcr, err); clear_thread_flag(TIF_SVE); + current->thread.fp_type = FP_STATE_FPSIMD; /* load the hardware registers from the fpsimd_state structure */ if (!err) @@ -292,6 +293,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user) if (sve.head.size <= sizeof(*user->sve)) { clear_thread_flag(TIF_SVE); current->thread.svcr &= ~SVCR_SM_MASK; + current->thread.fp_type = FP_STATE_FPSIMD; goto fpsimd_only; } @@ -327,6 +329,7 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user) current->thread.svcr |= SVCR_SM_MASK; else set_thread_flag(TIF_SVE); + current->thread.fp_type = FP_STATE_SVE; fpsimd_only: /* copy the FP and status/control registers */ @@ -932,9 +935,11 @@ static void setup_return(struct pt_regs *regs, struct k_sigaction *ka, * FPSIMD register state - flush the saved FPSIMD * register state in case it gets loaded. */ - if (current->thread.svcr & SVCR_SM_MASK) + if (current->thread.svcr & SVCR_SM_MASK) { memset(¤t->thread.uw.fpsimd_state, 0, sizeof(current->thread.uw.fpsimd_state)); + current->thread.fp_type = FP_STATE_FPSIMD; + } current->thread.svcr &= ~(SVCR_ZA_MASK | SVCR_SM_MASK); diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 634279b3b03d..117e2c180f3c 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -23,8 +23,8 @@ * * The regs must be on a stack currently owned by the calling task. */ -static inline void unwind_init_from_regs(struct unwind_state *state, - struct pt_regs *regs) +static __always_inline void unwind_init_from_regs(struct unwind_state *state, + struct pt_regs *regs) { unwind_init_common(state, current); @@ -58,8 +58,8 @@ static __always_inline void unwind_init_from_caller(struct unwind_state *state) * duration of the unwind, or the unwind will be bogus. It is never valid to * call this for the current task. */ -static inline void unwind_init_from_task(struct unwind_state *state, - struct task_struct *task) +static __always_inline void unwind_init_from_task(struct unwind_state *state, + struct task_struct *task) { unwind_init_common(state, task); @@ -186,7 +186,7 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl) : stackinfo_get_unknown(); \ }) -noinline notrace void arch_stack_walk(stack_trace_consume_fn consume_entry, +noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, struct task_struct *task, struct pt_regs *regs) { diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 8b02d310838f..e7163f31f716 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -60,6 +60,8 @@ void notrace __cpu_suspend_exit(void) * PSTATE was not saved over suspend/resume, re-enable any detected * features that might not have been set correctly. */ + if (cpus_have_const_cap(ARM64_HAS_DIT)) + set_pstate_dit(1); __uaccess_enable_hw_pan(); /* diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index d72e8f23422d..a5de47e3df2b 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -183,21 +183,12 @@ static inline void fp_user_discard(void) if (!system_supports_sve()) return; - /* - * If SME is not active then disable SVE, the registers will - * be cleared when userspace next attempts to access them and - * we do not need to track the SVE register state until then. - */ - clear_thread_flag(TIF_SVE); + if (test_thread_flag(TIF_SVE)) { + unsigned int sve_vq_minus_one; - /* - * task_fpsimd_load() won't be called to update CPACR_EL1 in - * ret_to_user unless TIF_FOREIGN_FPSTATE is still set, which only - * happens if a context switch or kernel_neon_begin() or context - * modification (sigreturn, ptrace) intervenes. - * So, ensure that CPACR_EL1 is already correct for the fast-path case. - */ - sve_user_disable(); + sve_vq_minus_one = sve_vq_from_vl(task_get_sve_vl(current)) - 1; + sve_flush_live(true, sve_vq_minus_one); + } } void do_el0_svc(struct pt_regs *regs) diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 45131e354e27..4c13dafc98b8 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -121,6 +121,17 @@ jiffies = jiffies_64; #define TRAMP_TEXT #endif +#ifdef CONFIG_UNWIND_TABLES +#define UNWIND_DATA_SECTIONS \ + .eh_frame : { \ + __eh_frame_start = .; \ + *(.eh_frame) \ + __eh_frame_end = .; \ + } +#else +#define UNWIND_DATA_SECTIONS +#endif + /* * The size of the PE/COFF section that covers the kernel image, which * runs from _stext to _edata, must be a round multiple of the PE/COFF @@ -231,6 +242,8 @@ SECTIONS __alt_instructions_end = .; } + UNWIND_DATA_SECTIONS + . = ALIGN(SEGMENT_ALIGN); __inittext_end = .; __initdata_begin = .; diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index ec8e4494873d..02dd7e9ebd39 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -75,11 +75,12 @@ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) { BUG_ON(!current->mm); - BUG_ON(test_thread_flag(TIF_SVE)); if (!system_supports_fpsimd()) return; + fpsimd_kvm_prepare(); + vcpu->arch.fp_state = FP_STATE_HOST_OWNED; vcpu_clear_flag(vcpu, HOST_SVE_ENABLED); @@ -129,20 +130,31 @@ void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu) */ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) { + struct cpu_fp_state fp_state; + WARN_ON_ONCE(!irqs_disabled()); if (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED) { + /* * Currently we do not support SME guests so SVCR is * always 0 and we just need a variable to point to. */ - fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs, - vcpu->arch.sve_state, - vcpu->arch.sve_max_vl, - NULL, 0, &vcpu->arch.svcr); + fp_state.st = &vcpu->arch.ctxt.fp_regs; + fp_state.sve_state = vcpu->arch.sve_state; + fp_state.sve_vl = vcpu->arch.sve_max_vl; + fp_state.za_state = NULL; + fp_state.svcr = &vcpu->arch.svcr; + fp_state.fp_type = &vcpu->arch.fp_type; + + if (vcpu_has_sve(vcpu)) + fp_state.to_save = FP_STATE_SVE; + else + fp_state.to_save = FP_STATE_FPSIMD; + + fpsimd_bind_state_to_cpu(&fp_state); clear_thread_flag(TIF_FOREIGN_FPSTATE); - update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu)); } } @@ -199,7 +211,5 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0); } - update_thread_flag(TIF_SVE, 0); - local_irq_restore(flags); } diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index be0a2bc3e20d..530347cdebe3 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -96,6 +96,7 @@ KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_CFI) # when profile optimization is applied. gen-hyprel does not support SHT_REL and # causes a build failure. Remove profile optimization flags. KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%, $(KBUILD_CFLAGS)) +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables # KVM nVHE code is run at a different exception code with a different map, so # compiler instrumentation that inserts callbacks or checks into the code may diff --git a/arch/arm64/lib/insn.c b/arch/arm64/lib/insn.c index 49e972beeac7..924934cb85ee 100644 --- a/arch/arm64/lib/insn.c +++ b/arch/arm64/lib/insn.c @@ -20,91 +20,6 @@ #define AARCH64_INSN_N_BIT BIT(22) #define AARCH64_INSN_LSL_12 BIT(22) -static const int aarch64_insn_encoding_class[] = { - AARCH64_INSN_CLS_UNKNOWN, - AARCH64_INSN_CLS_UNKNOWN, - AARCH64_INSN_CLS_SVE, - AARCH64_INSN_CLS_UNKNOWN, - AARCH64_INSN_CLS_LDST, - AARCH64_INSN_CLS_DP_REG, - AARCH64_INSN_CLS_LDST, - AARCH64_INSN_CLS_DP_FPSIMD, - AARCH64_INSN_CLS_DP_IMM, - AARCH64_INSN_CLS_DP_IMM, - AARCH64_INSN_CLS_BR_SYS, - AARCH64_INSN_CLS_BR_SYS, - AARCH64_INSN_CLS_LDST, - AARCH64_INSN_CLS_DP_REG, - AARCH64_INSN_CLS_LDST, - AARCH64_INSN_CLS_DP_FPSIMD, -}; - -enum aarch64_insn_encoding_class __kprobes aarch64_get_insn_class(u32 insn) -{ - return aarch64_insn_encoding_class[(insn >> 25) & 0xf]; -} - -bool __kprobes aarch64_insn_is_steppable_hint(u32 insn) -{ - if (!aarch64_insn_is_hint(insn)) - return false; - - switch (insn & 0xFE0) { - case AARCH64_INSN_HINT_XPACLRI: - case AARCH64_INSN_HINT_PACIA_1716: - case AARCH64_INSN_HINT_PACIB_1716: - case AARCH64_INSN_HINT_PACIAZ: - case AARCH64_INSN_HINT_PACIASP: - case AARCH64_INSN_HINT_PACIBZ: - case AARCH64_INSN_HINT_PACIBSP: - case AARCH64_INSN_HINT_BTI: - case AARCH64_INSN_HINT_BTIC: - case AARCH64_INSN_HINT_BTIJ: - case AARCH64_INSN_HINT_BTIJC: - case AARCH64_INSN_HINT_NOP: - return true; - default: - return false; - } -} - -bool aarch64_insn_is_branch_imm(u32 insn) -{ - return (aarch64_insn_is_b(insn) || aarch64_insn_is_bl(insn) || - aarch64_insn_is_tbz(insn) || aarch64_insn_is_tbnz(insn) || - aarch64_insn_is_cbz(insn) || aarch64_insn_is_cbnz(insn) || - aarch64_insn_is_bcond(insn)); -} - -bool __kprobes aarch64_insn_uses_literal(u32 insn) -{ - /* ldr/ldrsw (literal), prfm */ - - return aarch64_insn_is_ldr_lit(insn) || - aarch64_insn_is_ldrsw_lit(insn) || - aarch64_insn_is_adr_adrp(insn) || - aarch64_insn_is_prfm_lit(insn); -} - -bool __kprobes aarch64_insn_is_branch(u32 insn) -{ - /* b, bl, cb*, tb*, ret*, b.cond, br*, blr* */ - - return aarch64_insn_is_b(insn) || - aarch64_insn_is_bl(insn) || - aarch64_insn_is_cbz(insn) || - aarch64_insn_is_cbnz(insn) || - aarch64_insn_is_tbz(insn) || - aarch64_insn_is_tbnz(insn) || - aarch64_insn_is_ret(insn) || - aarch64_insn_is_ret_auth(insn) || - aarch64_insn_is_br(insn) || - aarch64_insn_is_br_auth(insn) || - aarch64_insn_is_blr(insn) || - aarch64_insn_is_blr_auth(insn) || - aarch64_insn_is_bcond(insn); -} - static int __kprobes aarch64_get_imm_shift_mask(enum aarch64_insn_imm_type type, u32 *maskp, int *shiftp) { @@ -435,16 +350,6 @@ u32 aarch64_insn_gen_cond_branch_imm(unsigned long pc, unsigned long addr, offset >> 2); } -u32 __kprobes aarch64_insn_gen_hint(enum aarch64_insn_hint_cr_op op) -{ - return aarch64_insn_get_hint_value() | op; -} - -u32 __kprobes aarch64_insn_gen_nop(void) -{ - return aarch64_insn_gen_hint(AARCH64_INSN_HINT_NOP); -} - u32 aarch64_insn_gen_branch_reg(enum aarch64_insn_register reg, enum aarch64_insn_branch_type type) { @@ -816,76 +721,6 @@ u32 aarch64_insn_gen_cas(enum aarch64_insn_register result, } #endif -static u32 aarch64_insn_encode_prfm_imm(enum aarch64_insn_prfm_type type, - enum aarch64_insn_prfm_target target, - enum aarch64_insn_prfm_policy policy, - u32 insn) -{ - u32 imm_type = 0, imm_target = 0, imm_policy = 0; - - switch (type) { - case AARCH64_INSN_PRFM_TYPE_PLD: - break; - case AARCH64_INSN_PRFM_TYPE_PLI: - imm_type = BIT(0); - break; - case AARCH64_INSN_PRFM_TYPE_PST: - imm_type = BIT(1); - break; - default: - pr_err("%s: unknown prfm type encoding %d\n", __func__, type); - return AARCH64_BREAK_FAULT; - } - - switch (target) { - case AARCH64_INSN_PRFM_TARGET_L1: - break; - case AARCH64_INSN_PRFM_TARGET_L2: - imm_target = BIT(0); - break; - case AARCH64_INSN_PRFM_TARGET_L3: - imm_target = BIT(1); - break; - default: - pr_err("%s: unknown prfm target encoding %d\n", __func__, target); - return AARCH64_BREAK_FAULT; - } - - switch (policy) { - case AARCH64_INSN_PRFM_POLICY_KEEP: - break; - case AARCH64_INSN_PRFM_POLICY_STRM: - imm_policy = BIT(0); - break; - default: - pr_err("%s: unknown prfm policy encoding %d\n", __func__, policy); - return AARCH64_BREAK_FAULT; - } - - /* In this case, imm5 is encoded into Rt field. */ - insn &= ~GENMASK(4, 0); - insn |= imm_policy | (imm_target << 1) | (imm_type << 3); - - return insn; -} - -u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base, - enum aarch64_insn_prfm_type type, - enum aarch64_insn_prfm_target target, - enum aarch64_insn_prfm_policy policy) -{ - u32 insn = aarch64_insn_get_prfm_value(); - - insn = aarch64_insn_encode_ldst_size(AARCH64_INSN_SIZE_64, insn); - - insn = aarch64_insn_encode_prfm_imm(type, target, policy, insn); - - insn = aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RN, insn, - base); - - return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_12, insn, 0); -} - u32 aarch64_insn_gen_add_sub_imm(enum aarch64_insn_register dst, enum aarch64_insn_register src, int imm, enum aarch64_insn_variant variant, diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 3e9cf9826417..3eb2825d08cf 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -354,6 +354,11 @@ static bool is_el1_mte_sync_tag_check_fault(unsigned long esr) return false; } +static bool is_translation_fault(unsigned long esr) +{ + return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_FAULT; +} + static void __do_kernel_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { @@ -386,7 +391,8 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr, } else if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else { - if (kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs)) + if (is_translation_fault(esr) && + kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs)) return; msg = "paging request"; diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 35e9a468d13e..cd8d96e1fa1a 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -559,3 +559,24 @@ bool __init arch_hugetlb_valid_size(unsigned long size) { return __hugetlb_valid_size(size); } + +pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +{ + if (IS_ENABLED(CONFIG_ARM64_WORKAROUND_2645198) && + cpus_have_const_cap(ARM64_WORKAROUND_2645198)) { + /* + * Break-before-make (BBM) is required for all user space mappings + * when the permission changes from executable to non-executable + * in cases where cpu is affected with errata #2645198. + */ + if (pte_user_exec(READ_ONCE(*ptep))) + return huge_ptep_clear_flush(vma, addr, ptep); + } + return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); +} + +void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte) +{ + set_huge_pte_at(vma->vm_mm, addr, ptep, pte); +} diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 4b4651ee47f2..58a0bb2c17f1 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -96,6 +96,8 @@ phys_addr_t __ro_after_init arm64_dma_phys_limit = PHYS_MASK + 1; #define CRASH_ADDR_LOW_MAX arm64_dma_phys_limit #define CRASH_ADDR_HIGH_MAX (PHYS_MASK + 1) +#define DEFAULT_CRASH_KERNEL_LOW_SIZE (128UL << 20) + static int __init reserve_crashkernel_low(unsigned long long low_size) { unsigned long long low_base; @@ -130,6 +132,7 @@ static void __init reserve_crashkernel(void) unsigned long long crash_max = CRASH_ADDR_LOW_MAX; char *cmdline = boot_command_line; int ret; + bool fixed_base = false; if (!IS_ENABLED(CONFIG_KEXEC_CORE)) return; @@ -147,7 +150,9 @@ static void __init reserve_crashkernel(void) * is not allowed. */ ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base); - if (ret && (ret != -ENOENT)) + if (ret == -ENOENT) + crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; + else if (ret) return; crash_max = CRASH_ADDR_HIGH_MAX; @@ -159,18 +164,32 @@ static void __init reserve_crashkernel(void) crash_size = PAGE_ALIGN(crash_size); /* User specifies base address explicitly. */ - if (crash_base) + if (crash_base) { + fixed_base = true; crash_max = crash_base + crash_size; + } +retry: crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, crash_base, crash_max); if (!crash_base) { + /* + * If the first attempt was for low memory, fall back to + * high memory, the minimum required low memory will be + * reserved later. + */ + if (!fixed_base && (crash_max == CRASH_ADDR_LOW_MAX)) { + crash_max = CRASH_ADDR_HIGH_MAX; + crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; + goto retry; + } + pr_warn("cannot allocate crashkernel (size:0x%llx)\n", crash_size); return; } - if ((crash_base >= CRASH_ADDR_LOW_MAX) && + if ((crash_base > CRASH_ADDR_LOW_MAX - crash_low_size) && crash_low_size && reserve_crashkernel_low(crash_low_size)) { memblock_phys_free(crash_base, crash_size); return; diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 9a7c38965154..5a19950e7289 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1702,3 +1702,24 @@ static int __init prevent_bootmem_remove_init(void) } early_initcall(prevent_bootmem_remove_init); #endif + +pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) +{ + if (IS_ENABLED(CONFIG_ARM64_WORKAROUND_2645198) && + cpus_have_const_cap(ARM64_WORKAROUND_2645198)) { + /* + * Break-before-make (BBM) is required for all user space mappings + * when the permission changes from executable to non-executable + * in cases where cpu is affected with errata #2645198. + */ + if (pte_user_exec(READ_ONCE(*ptep))) + return ptep_clear_flush(vma, addr, ptep); + } + return ptep_get_and_clear(vma->vm_mm, addr, ptep); +} + +void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, + pte_t old_pte, pte_t pte) +{ + set_pte_at(vma->vm_mm, addr, ptep, pte); +} diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index f1c0347ec31a..dfeb2c51e257 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -20,6 +20,7 @@ HAS_CNP HAS_CRC32 HAS_DCPODP HAS_DCPOP +HAS_DIT HAS_E0PD HAS_ECV HAS_EPAN @@ -70,6 +71,7 @@ WORKAROUND_2038923 WORKAROUND_2064142 WORKAROUND_2077057 WORKAROUND_2457168 +WORKAROUND_2645198 WORKAROUND_2658417 WORKAROUND_TRBE_OVERWRITE_FILL_MODE WORKAROUND_TSB_FLUSH_FAILURE diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index bd5fceb26c54..184e58fd5631 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -964,6 +964,7 @@ EndEnum Enum 3:0 SVEver 0b0000 IMP 0b0001 SVE2 + 0b0010 SVE2p1 EndEnum EndSysreg @@ -1238,7 +1239,16 @@ EndEnum EndSysreg Sysreg ID_AA64ISAR2_EL1 3 0 0 6 2 -Res0 63:28 +Res0 63:56 +Enum 55:52 CSSC + 0b0000 NI + 0b0001 IMP +EndEnum +Enum 51:48 RPRFM + 0b0000 NI + 0b0001 IMP +EndEnum +Res0 47:28 Enum 27:24 PAC_frac 0b0000 NI 0b0001 IMP |