diff options
Diffstat (limited to 'arch/arm64')
50 files changed, 1182 insertions, 361 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 03934808b2ed..619ab046744a 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -123,6 +123,8 @@ config ARM64 select DMA_DIRECT_REMAP select EDAC_SUPPORT select FRAME_POINTER + select FUNCTION_ALIGNMENT_4B + select FUNCTION_ALIGNMENT_8B if DYNAMIC_FTRACE_WITH_CALL_OPS select GENERIC_ALLOCATOR select GENERIC_ARCH_TOPOLOGY select GENERIC_CLOCKEVENTS_BROADCAST @@ -186,6 +188,8 @@ config ARM64 select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_ARGS \ if $(cc-option,-fpatchable-function-entry=2) + select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS \ + if (DYNAMIC_FTRACE_WITH_ARGS && !CFI_CLANG) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ if DYNAMIC_FTRACE_WITH_ARGS select HAVE_EFFICIENT_UNALIGNED_ACCESS @@ -1456,10 +1460,23 @@ config XEN help Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64. +# include/linux/mmzone.h requires the following to be true: +# +# MAX_ORDER - 1 + PAGE_SHIFT <= SECTION_SIZE_BITS +# +# so the maximum value of MAX_ORDER is SECTION_SIZE_BITS + 1 - PAGE_SHIFT: +# +# | SECTION_SIZE_BITS | PAGE_SHIFT | max MAX_ORDER | default MAX_ORDER | +# ----+-------------------+--------------+-----------------+--------------------+ +# 4K | 27 | 12 | 16 | 11 | +# 16K | 27 | 14 | 14 | 12 | +# 64K | 29 | 16 | 14 | 14 | config ARCH_FORCE_MAX_ORDER - int + int "Maximum zone order" if ARM64_4K_PAGES || ARM64_16K_PAGES default "14" if ARM64_64K_PAGES + range 12 14 if ARM64_16K_PAGES default "12" if ARM64_16K_PAGES + range 11 16 if ARM64_4K_PAGES default "11" help The kernel memory allocator divides physically contiguous memory @@ -1472,7 +1489,7 @@ config ARCH_FORCE_MAX_ORDER This config option is actually maximum order plus one. For example, a value of 11 means that the largest free memory block is 2^10 pages. - We make sure that we can allocate upto a HugePage size for each configuration. + We make sure that we can allocate up to a HugePage size for each configuration. Hence we have : MAX_ORDER = (PMD_SHIFT - PAGE_SHIFT) + 1 => PAGE_SHIFT - 2 @@ -1818,7 +1835,7 @@ config ARM64_PTR_AUTH_KERNEL bool "Use pointer authentication for kernel" default y depends on ARM64_PTR_AUTH - depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_PAC + depends on (CC_HAS_SIGN_RETURN_ADDRESS || CC_HAS_BRANCH_PROT_PAC_RET) && AS_HAS_ARMV8_3 # Modern compilers insert a .note.gnu.property section note for PAC # 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) @@ -1843,7 +1860,7 @@ config CC_HAS_SIGN_RETURN_ADDRESS # GCC 7, 8 def_bool $(cc-option,-msign-return-address=all) -config AS_HAS_PAC +config AS_HAS_ARMV8_3 def_bool $(cc-option,-Wa$(comma)-march=armv8.3-a) config AS_HAS_CFI_NEGATE_RA_STATE diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms index d1970adf80ab..333d0af650d2 100644 --- a/arch/arm64/Kconfig.platforms +++ b/arch/arm64/Kconfig.platforms @@ -187,7 +187,7 @@ config ARCH_MVEBU select PINCTRL_ARMADA_CP110 select PINCTRL_AC5 help - This enables support for Marvell EBU familly, including: + This enables support for Marvell EBU family, including: - Armada 3700 SoC Family - Armada 7K SoC Family - Armada 8K SoC Family diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index d62bd221828f..c33b5da95b4a 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -63,50 +63,37 @@ stack_protector_prepare: prepare0 include/generated/asm-offsets.h)) endif -ifeq ($(CONFIG_AS_HAS_ARMV8_2), y) -# make sure to pass the newest target architecture to -march. -asm-arch := armv8.2-a -endif - -# Ensure that if the compiler supports branch protection we default it -# off, this will be overridden if we are using branch protection. -branch-prot-flags-y += $(call cc-option,-mbranch-protection=none) - -ifeq ($(CONFIG_ARM64_PTR_AUTH_KERNEL),y) -branch-prot-flags-$(CONFIG_CC_HAS_SIGN_RETURN_ADDRESS) := -msign-return-address=all -# We enable additional protection for leaf functions as there is some -# narrow potential for ROP protection benefits and no substantial -# performance impact has been observed. -PACRET-y := pac-ret+leaf - -# Using a shadow call stack in leaf functions is too costly, so avoid PAC there -# as well when we may be patching PAC into SCS -PACRET-$(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=$(PACRET-y)+bti + KBUILD_CFLAGS += -mbranch-protection=pac-ret+bti +else ifeq ($(CONFIG_ARM64_PTR_AUTH_KERNEL),y) + ifeq ($(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET),y) + KBUILD_CFLAGS += -mbranch-protection=pac-ret + else + KBUILD_CFLAGS += -msign-return-address=non-leaf + endif else -branch-prot-flags-$(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET) := -mbranch-protection=$(PACRET-y) -endif -# -march=armv8.3-a enables the non-nops instructions for PAC, to avoid the -# compiler to generate them and consequently to break the single image contract -# we pass it only to the assembler. This option is utilized only in case of non -# integrated assemblers. -ifeq ($(CONFIG_AS_HAS_PAC), y) -asm-arch := armv8.3-a -endif -endif - -KBUILD_CFLAGS += $(branch-prot-flags-y) - -ifeq ($(CONFIG_AS_HAS_ARMV8_4), y) -# make sure to pass the newest target architecture to -march. -asm-arch := armv8.4-a + KBUILD_CFLAGS += $(call cc-option,-mbranch-protection=none) endif +# Tell the assembler to support instructions from the latest target +# architecture. +# +# For non-integrated assemblers we'll pass this on the command line, and for +# integrated assemblers we'll define ARM64_ASM_ARCH and ARM64_ASM_PREAMBLE for +# inline usage. +# +# We cannot pass the same arch flag to the compiler as this would allow it to +# freely generate instructions which are not supported by earlier architecture +# versions, which would prevent a single kernel image from working on earlier +# hardware. ifeq ($(CONFIG_AS_HAS_ARMV8_5), y) -# make sure to pass the newest target architecture to -march. -asm-arch := armv8.5-a + asm-arch := armv8.5-a +else ifeq ($(CONFIG_AS_HAS_ARMV8_4), y) + asm-arch := armv8.4-a +else ifeq ($(CONFIG_AS_HAS_ARMV8_3), y) + asm-arch := armv8.3-a +else ifeq ($(CONFIG_AS_HAS_ARMV8_2), y) + asm-arch := armv8.2-a endif ifdef asm-arch @@ -139,7 +126,10 @@ endif CHECKFLAGS += -D__aarch64__ -ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_ARGS),y) +ifeq ($(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS),y) + KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY + CC_FLAGS_FTRACE := -fpatchable-function-entry=4,2 +else ifeq ($(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/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 48d4473e8eee..01281a5336cf 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -190,5 +190,10 @@ static inline void gic_arch_enable_irqs(void) asm volatile ("msr daifclr, #3" : : : "memory"); } +static inline bool gic_has_relaxed_pmr_sync(void) +{ + return cpus_have_cap(ARM64_HAS_GIC_PRIO_RELAXED_SYNC); +} + #endif /* __ASSEMBLY__ */ #endif /* __ASM_ARCH_GICV3_H */ diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 2cfc4245d2e2..3dd8982a9ce3 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -11,6 +11,8 @@ #include <linux/kasan-checks.h> +#include <asm/alternative-macros.h> + #define __nops(n) ".rept " #n "\nnop\n.endr\n" #define nops(n) asm volatile(__nops(n)) @@ -41,10 +43,11 @@ #ifdef CONFIG_ARM64_PSEUDO_NMI #define pmr_sync() \ do { \ - extern struct static_key_false gic_pmr_sync; \ - \ - if (static_branch_unlikely(&gic_pmr_sync)) \ - dsb(sy); \ + asm volatile( \ + ALTERNATIVE_CB("dsb sy", \ + ARM64_HAS_GIC_PRIO_RELAXED_SYNC, \ + alt_cb_patch_nops) \ + ); \ } while(0) #else #define pmr_sync() do {} while (0) diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 03d1c9d7af82..6bf013fb110d 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -769,6 +769,12 @@ static __always_inline bool system_supports_sme(void) cpus_have_const_cap(ARM64_SME); } +static __always_inline bool system_supports_sme2(void) +{ + return IS_ENABLED(CONFIG_ARM64_SME) && + cpus_have_const_cap(ARM64_SME2); +} + static __always_inline bool system_supports_fa64(void) { return IS_ENABLED(CONFIG_ARM64_SME) && @@ -806,7 +812,7 @@ static inline bool system_has_full_ptr_auth(void) static __always_inline bool system_uses_irq_prio_masking(void) { return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && - cpus_have_const_cap(ARM64_HAS_IRQ_PRIO_MASKING); + cpus_have_const_cap(ARM64_HAS_GIC_PRIO_MASKING); } static inline bool system_supports_mte(void) @@ -864,7 +870,11 @@ static inline bool cpu_has_hw_af(void) if (!IS_ENABLED(CONFIG_ARM64_HW_AFDBM)) return false; - mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); + /* + * Use cached version to avoid emulated msr operation on KVM + * guests. + */ + mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); return cpuid_feature_extract_unsigned_field(mmfr1, ID_AA64MMFR1_EL1_HAFDBS_SHIFT); } diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index 668569adf4d3..2cdd010f9524 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -53,10 +53,10 @@ cbz x0, .Lskip_spe_\@ // Skip if SPE not present mrs_s x0, SYS_PMBIDR_EL1 // If SPE available at EL2, - and x0, x0, #(1 << SYS_PMBIDR_EL1_P_SHIFT) + and x0, x0, #(1 << PMBIDR_EL1_P_SHIFT) cbnz x0, .Lskip_spe_el2_\@ // then permit sampling of physical - mov x0, #(1 << SYS_PMSCR_EL2_PCT_SHIFT | \ - 1 << SYS_PMSCR_EL2_PA_SHIFT) + mov x0, #(1 << PMSCR_EL2_PCT_SHIFT | \ + 1 << PMSCR_EL2_PA_SHIFT) msr_s SYS_PMSCR_EL2, x0 // addresses and physical counter .Lskip_spe_el2_\@: mov x0, #(MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT) @@ -177,7 +177,7 @@ /** * Initialize EL2 registers to sane values. This should be called early on all * cores that were booted in EL2. Note that everything gets initialised as - * if VHE was not evailable. The kernel context will be upgraded to VHE + * if VHE was not available. The kernel context will be upgraded to VHE * if possible later on in the boot process * * Regs: x0, x1 and x2 are clobbered. diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 15b34fbfca66..5f3271e9d5df 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -341,6 +341,7 @@ #define ESR_ELx_SME_ISS_ILL 1 #define ESR_ELx_SME_ISS_SM_DISABLED 2 #define ESR_ELx_SME_ISS_ZA_DISABLED 3 +#define ESR_ELx_SME_ISS_ZT_DISABLED 4 #ifndef __ASSEMBLY__ #include <asm/types.h> diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index e6fa1e2982c8..67f2fb781f59 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -61,7 +61,7 @@ extern void fpsimd_kvm_prepare(void); struct cpu_fp_state { struct user_fpsimd_state *st; void *sve_state; - void *za_state; + void *sme_state; u64 *svcr; unsigned int sve_vl; unsigned int sme_vl; @@ -105,6 +105,13 @@ static inline void *sve_pffr(struct thread_struct *thread) return (char *)thread->sve_state + sve_ffr_offset(vl); } +static inline void *thread_zt_state(struct thread_struct *thread) +{ + /* The ZT register state is stored immediately after the ZA state */ + unsigned int sme_vq = sve_vq_from_vl(thread_get_sme_vl(thread)); + return thread->sme_state + ZA_SIG_REGS_SIZE(sme_vq); +} + extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr); extern void sve_load_state(void const *state, u32 const *pfpsr, int restore_ffr); @@ -112,12 +119,13 @@ extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1); extern unsigned int sve_get_vl(void); extern void sve_set_vq(unsigned long vq_minus_1); extern void sme_set_vq(unsigned long vq_minus_1); -extern void za_save_state(void *state); -extern void za_load_state(void const *state); +extern void sme_save_state(void *state, int zt); +extern void sme_load_state(void const *state, int zt); struct arm64_cpu_capabilities; extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused); extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused); +extern void sme2_kernel_enable(const struct arm64_cpu_capabilities *__unused); extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused); extern u64 read_zcr_features(void); @@ -355,14 +363,20 @@ extern int sme_get_current_vl(void); /* * Return how many bytes of memory are required to store the full SME - * specific state (currently just ZA) for task, given task's currently - * configured vector length. + * specific state for task, given task's currently configured vector + * length. */ -static inline size_t za_state_size(struct task_struct const *task) +static inline size_t sme_state_size(struct task_struct const *task) { unsigned int vl = task_get_sme_vl(task); + size_t size; + + size = ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl)); + + if (system_supports_sme2()) + size += ZT_SIG_REG_SIZE; - return ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl)); + return size; } #else @@ -382,7 +396,7 @@ static inline int sme_max_virtualisable_vl(void) { return 0; } static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; } static inline int sme_get_current_vl(void) { return -EINVAL; } -static inline size_t za_state_size(struct task_struct const *task) +static inline size_t sme_state_size(struct task_struct const *task) { return 0; } diff --git a/arch/arm64/include/asm/fpsimdmacros.h b/arch/arm64/include/asm/fpsimdmacros.h index 5e0910cf4832..cd03819a3b68 100644 --- a/arch/arm64/include/asm/fpsimdmacros.h +++ b/arch/arm64/include/asm/fpsimdmacros.h @@ -221,6 +221,28 @@ .endm /* + * LDR (ZT0) + * + * LDR ZT0, nx + */ +.macro _ldr_zt nx + _check_general_reg \nx + .inst 0xe11f8000 \ + | (\nx << 5) +.endm + +/* + * STR (ZT0) + * + * STR ZT0, nx + */ +.macro _str_zt nx + _check_general_reg \nx + .inst 0xe13f8000 \ + | (\nx << 5) +.endm + +/* * Zero the entire ZA array * ZERO ZA */ diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index 5664729800ae..1c2672bbbf37 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -62,20 +62,7 @@ extern unsigned long ftrace_graph_call; extern void return_to_handler(void); -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_ARGS)) - return addr + AARCH64_INSN_SIZE; - /* - * addr is the address of the mcount call instruction. - * recordmcount does the necessary offset calculation. - */ - return addr; -} +unsigned long ftrace_call_adjust(unsigned long addr); #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS struct dyn_ftrace; diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 06dd12c514e6..5d45f19fda7f 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -31,12 +31,20 @@ #define COMPAT_HWCAP_VFPD32 (1 << 19) #define COMPAT_HWCAP_LPAE (1 << 20) #define COMPAT_HWCAP_EVTSTRM (1 << 21) +#define COMPAT_HWCAP_FPHP (1 << 22) +#define COMPAT_HWCAP_ASIMDHP (1 << 23) +#define COMPAT_HWCAP_ASIMDDP (1 << 24) +#define COMPAT_HWCAP_ASIMDFHM (1 << 25) +#define COMPAT_HWCAP_ASIMDBF16 (1 << 26) +#define COMPAT_HWCAP_I8MM (1 << 27) #define COMPAT_HWCAP2_AES (1 << 0) #define COMPAT_HWCAP2_PMULL (1 << 1) #define COMPAT_HWCAP2_SHA1 (1 << 2) #define COMPAT_HWCAP2_SHA2 (1 << 3) #define COMPAT_HWCAP2_CRC32 (1 << 4) +#define COMPAT_HWCAP2_SB (1 << 5) +#define COMPAT_HWCAP2_SSBS (1 << 6) #ifndef __ASSEMBLY__ #include <linux/log2.h> @@ -123,6 +131,12 @@ #define KERNEL_HWCAP_CSSC __khwcap2_feature(CSSC) #define KERNEL_HWCAP_RPRFM __khwcap2_feature(RPRFM) #define KERNEL_HWCAP_SVE2P1 __khwcap2_feature(SVE2P1) +#define KERNEL_HWCAP_SME2 __khwcap2_feature(SME2) +#define KERNEL_HWCAP_SME2P1 __khwcap2_feature(SME2P1) +#define KERNEL_HWCAP_SME_I16I32 __khwcap2_feature(SME_I16I32) +#define KERNEL_HWCAP_SME_BI32I32 __khwcap2_feature(SME_BI32I32) +#define KERNEL_HWCAP_SME_B16B16 __khwcap2_feature(SME_B16B16) +#define KERNEL_HWCAP_SME_F16F16 __khwcap2_feature(SME_F16F16) /* * 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 aaf1f52fbf3e..139a88e4e852 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -420,6 +420,7 @@ __AARCH64_INSN_FUNCS(sb, 0xFFFFFFFF, 0xD50330FF) __AARCH64_INSN_FUNCS(clrex, 0xFFFFF0FF, 0xD503305F) __AARCH64_INSN_FUNCS(ssbb, 0xFFFFFFFF, 0xD503309F) __AARCH64_INSN_FUNCS(pssbb, 0xFFFFFFFF, 0xD503349F) +__AARCH64_INSN_FUNCS(bti, 0xFFFFFF3F, 0xD503241f) #undef __AARCH64_INSN_FUNCS diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h index b57b9b1e4344..e0f5f6b73edd 100644 --- a/arch/arm64/include/asm/irqflags.h +++ b/arch/arm64/include/asm/irqflags.h @@ -21,43 +21,77 @@ * exceptions should be unmasked. */ -/* - * CPU interrupt mask handling. - */ -static inline void arch_local_irq_enable(void) +static __always_inline bool __irqflags_uses_pmr(void) { - if (system_has_prio_mask_debugging()) { - u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1); + return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && + alternative_has_feature_unlikely(ARM64_HAS_GIC_PRIO_MASKING); +} +static __always_inline void __daif_local_irq_enable(void) +{ + barrier(); + asm volatile("msr daifclr, #3"); + barrier(); +} + +static __always_inline void __pmr_local_irq_enable(void) +{ + if (IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING)) { + u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1); WARN_ON_ONCE(pmr != GIC_PRIO_IRQON && pmr != GIC_PRIO_IRQOFF); } - asm volatile(ALTERNATIVE( - "msr daifclr, #3 // arch_local_irq_enable", - __msr_s(SYS_ICC_PMR_EL1, "%0"), - ARM64_HAS_IRQ_PRIO_MASKING) - : - : "r" ((unsigned long) GIC_PRIO_IRQON) - : "memory"); - + barrier(); + write_sysreg_s(GIC_PRIO_IRQON, SYS_ICC_PMR_EL1); pmr_sync(); + barrier(); } -static inline void arch_local_irq_disable(void) +static inline void arch_local_irq_enable(void) { - if (system_has_prio_mask_debugging()) { - u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1); + if (__irqflags_uses_pmr()) { + __pmr_local_irq_enable(); + } else { + __daif_local_irq_enable(); + } +} +static __always_inline void __daif_local_irq_disable(void) +{ + barrier(); + asm volatile("msr daifset, #3"); + barrier(); +} + +static __always_inline void __pmr_local_irq_disable(void) +{ + if (IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING)) { + u32 pmr = read_sysreg_s(SYS_ICC_PMR_EL1); WARN_ON_ONCE(pmr != GIC_PRIO_IRQON && pmr != GIC_PRIO_IRQOFF); } - asm volatile(ALTERNATIVE( - "msr daifset, #3 // arch_local_irq_disable", - __msr_s(SYS_ICC_PMR_EL1, "%0"), - ARM64_HAS_IRQ_PRIO_MASKING) - : - : "r" ((unsigned long) GIC_PRIO_IRQOFF) - : "memory"); + barrier(); + write_sysreg_s(GIC_PRIO_IRQOFF, SYS_ICC_PMR_EL1); + barrier(); +} + +static inline void arch_local_irq_disable(void) +{ + if (__irqflags_uses_pmr()) { + __pmr_local_irq_disable(); + } else { + __daif_local_irq_disable(); + } +} + +static __always_inline unsigned long __daif_local_save_flags(void) +{ + return read_sysreg(daif); +} + +static __always_inline unsigned long __pmr_local_save_flags(void) +{ + return read_sysreg_s(SYS_ICC_PMR_EL1); } /* @@ -65,69 +99,108 @@ static inline void arch_local_irq_disable(void) */ static inline unsigned long arch_local_save_flags(void) { - unsigned long flags; + if (__irqflags_uses_pmr()) { + return __pmr_local_save_flags(); + } else { + return __daif_local_save_flags(); + } +} - asm volatile(ALTERNATIVE( - "mrs %0, daif", - __mrs_s("%0", SYS_ICC_PMR_EL1), - ARM64_HAS_IRQ_PRIO_MASKING) - : "=&r" (flags) - : - : "memory"); +static __always_inline bool __daif_irqs_disabled_flags(unsigned long flags) +{ + return flags & PSR_I_BIT; +} - return flags; +static __always_inline bool __pmr_irqs_disabled_flags(unsigned long flags) +{ + return flags != GIC_PRIO_IRQON; } -static inline int arch_irqs_disabled_flags(unsigned long flags) +static inline bool arch_irqs_disabled_flags(unsigned long flags) { - int res; + if (__irqflags_uses_pmr()) { + return __pmr_irqs_disabled_flags(flags); + } else { + return __daif_irqs_disabled_flags(flags); + } +} - asm volatile(ALTERNATIVE( - "and %w0, %w1, #" __stringify(PSR_I_BIT), - "eor %w0, %w1, #" __stringify(GIC_PRIO_IRQON), - ARM64_HAS_IRQ_PRIO_MASKING) - : "=&r" (res) - : "r" ((int) flags) - : "memory"); +static __always_inline bool __daif_irqs_disabled(void) +{ + return __daif_irqs_disabled_flags(__daif_local_save_flags()); +} - return res; +static __always_inline bool __pmr_irqs_disabled(void) +{ + return __pmr_irqs_disabled_flags(__pmr_local_save_flags()); } -static inline int arch_irqs_disabled(void) +static inline bool arch_irqs_disabled(void) { - return arch_irqs_disabled_flags(arch_local_save_flags()); + if (__irqflags_uses_pmr()) { + return __pmr_irqs_disabled(); + } else { + return __daif_irqs_disabled(); + } } -static inline unsigned long arch_local_irq_save(void) +static __always_inline unsigned long __daif_local_irq_save(void) { - unsigned long flags; + unsigned long flags = __daif_local_save_flags(); + + __daif_local_irq_disable(); + + return flags; +} - flags = arch_local_save_flags(); +static __always_inline unsigned long __pmr_local_irq_save(void) +{ + unsigned long flags = __pmr_local_save_flags(); /* * There are too many states with IRQs disabled, just keep the current * state if interrupts are already disabled/masked. */ - if (!arch_irqs_disabled_flags(flags)) - arch_local_irq_disable(); + if (!__pmr_irqs_disabled_flags(flags)) + __pmr_local_irq_disable(); return flags; } +static inline unsigned long arch_local_irq_save(void) +{ + if (__irqflags_uses_pmr()) { + return __pmr_local_irq_save(); + } else { + return __daif_local_irq_save(); + } +} + +static __always_inline void __daif_local_irq_restore(unsigned long flags) +{ + barrier(); + write_sysreg(flags, daif); + barrier(); +} + +static __always_inline void __pmr_local_irq_restore(unsigned long flags) +{ + barrier(); + write_sysreg_s(flags, SYS_ICC_PMR_EL1); + pmr_sync(); + barrier(); +} + /* * restore saved IRQ state */ static inline void arch_local_irq_restore(unsigned long flags) { - asm volatile(ALTERNATIVE( - "msr daif, %0", - __msr_s(SYS_ICC_PMR_EL1, "%0"), - ARM64_HAS_IRQ_PRIO_MASKING) - : - : "r" (flags) - : "memory"); - - pmr_sync(); + if (__irqflags_uses_pmr()) { + __pmr_local_irq_restore(flags); + } else { + __daif_local_irq_restore(flags); + } } #endif /* __ASM_IRQFLAGS_H */ diff --git a/arch/arm64/include/asm/linkage.h b/arch/arm64/include/asm/linkage.h index 1436fa1cde24..d3acd9c87509 100644 --- a/arch/arm64/include/asm/linkage.h +++ b/arch/arm64/include/asm/linkage.h @@ -5,8 +5,8 @@ #include <asm/assembler.h> #endif -#define __ALIGN .align 2 -#define __ALIGN_STR ".align 2" +#define __ALIGN .balign CONFIG_FUNCTION_ALIGNMENT +#define __ALIGN_STR ".balign " #CONFIG_FUNCTION_ALIGNMENT /* * When using in-kernel BTI we need to ensure that PCS-conformant diff --git a/arch/arm64/include/asm/patching.h b/arch/arm64/include/asm/patching.h index 6bf5adc56295..68908b82b168 100644 --- a/arch/arm64/include/asm/patching.h +++ b/arch/arm64/include/asm/patching.h @@ -7,6 +7,8 @@ int aarch64_insn_read(void *addr, u32 *insnp); int aarch64_insn_write(void *addr, u32 insn); +int aarch64_insn_write_literal_u64(void *addr, u64 val); + int aarch64_insn_patch_text_nosync(void *addr, u32 insn); int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt); diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index b4bbeed80fb6..832c9c8fb58f 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -275,6 +275,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte) } extern void __sync_icache_dcache(pte_t pteval); +bool pgattr_change_is_safe(u64 old, u64 new); /* * PTE bits configuration in the presence of hardware Dirty Bit Management @@ -292,7 +293,7 @@ extern void __sync_icache_dcache(pte_t pteval); * PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY) */ -static inline void __check_racy_pte_update(struct mm_struct *mm, pte_t *ptep, +static inline void __check_safe_pte_update(struct mm_struct *mm, pte_t *ptep, pte_t pte) { pte_t old_pte; @@ -318,6 +319,9 @@ static inline void __check_racy_pte_update(struct mm_struct *mm, pte_t *ptep, VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte), "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx", __func__, pte_val(old_pte), pte_val(pte)); + VM_WARN_ONCE(!pgattr_change_is_safe(pte_val(old_pte), pte_val(pte)), + "%s: unsafe attribute change: 0x%016llx -> 0x%016llx", + __func__, pte_val(old_pte), pte_val(pte)); } static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, @@ -346,7 +350,7 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr, mte_sync_tags(old_pte, pte); } - __check_racy_pte_update(mm, ptep, pte); + __check_safe_pte_update(mm, ptep, pte); set_pte(ptep, pte); } diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index d51b32a69309..3918f2a67970 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -161,7 +161,7 @@ struct thread_struct { 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 */ + void *sme_state; /* ZA and ZT state, if any */ unsigned int vl[ARM64_VEC_MAX]; /* vector length */ unsigned int vl_onexec[ARM64_VEC_MAX]; /* vl after next exec */ unsigned long fault_address; /* fault info */ diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h index 41b332c054ab..47ec58031f11 100644 --- a/arch/arm64/include/asm/ptrace.h +++ b/arch/arm64/include/asm/ptrace.h @@ -194,7 +194,7 @@ struct pt_regs { u32 unused2; #endif u64 sdei_ttbr1; - /* Only valid when ARM64_HAS_IRQ_PRIO_MASKING is enabled. */ + /* Only valid when ARM64_HAS_GIC_PRIO_MASKING is enabled. */ u64 pmr_save; u64 stackframe[2]; diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h index ff7da1268a52..13df982a0808 100644 --- a/arch/arm64/include/asm/scs.h +++ b/arch/arm64/include/asm/scs.h @@ -10,15 +10,16 @@ #ifdef CONFIG_SHADOW_CALL_STACK scs_sp .req x18 - .macro scs_load tsk - ldr scs_sp, [\tsk, #TSK_TI_SCS_SP] + .macro scs_load_current + get_current_task scs_sp + ldr scs_sp, [scs_sp, #TSK_TI_SCS_SP] .endm .macro scs_save tsk str scs_sp, [\tsk, #TSK_TI_SCS_SP] .endm #else - .macro scs_load tsk + .macro scs_load_current .endm .macro scs_save tsk diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 2facd7933948..043ecc3405e7 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -216,101 +216,22 @@ #define SYS_PAR_EL1_FST GENMASK(6, 1) /*** Statistical Profiling Extension ***/ -/* ID registers */ -#define SYS_PMSIDR_EL1 sys_reg(3, 0, 9, 9, 7) -#define SYS_PMSIDR_EL1_FE_SHIFT 0 -#define SYS_PMSIDR_EL1_FT_SHIFT 1 -#define SYS_PMSIDR_EL1_FL_SHIFT 2 -#define SYS_PMSIDR_EL1_ARCHINST_SHIFT 3 -#define SYS_PMSIDR_EL1_LDS_SHIFT 4 -#define SYS_PMSIDR_EL1_ERND_SHIFT 5 -#define SYS_PMSIDR_EL1_INTERVAL_SHIFT 8 -#define SYS_PMSIDR_EL1_INTERVAL_MASK 0xfUL -#define SYS_PMSIDR_EL1_MAXSIZE_SHIFT 12 -#define SYS_PMSIDR_EL1_MAXSIZE_MASK 0xfUL -#define SYS_PMSIDR_EL1_COUNTSIZE_SHIFT 16 -#define SYS_PMSIDR_EL1_COUNTSIZE_MASK 0xfUL - -#define SYS_PMBIDR_EL1 sys_reg(3, 0, 9, 10, 7) -#define SYS_PMBIDR_EL1_ALIGN_SHIFT 0 -#define SYS_PMBIDR_EL1_ALIGN_MASK 0xfU -#define SYS_PMBIDR_EL1_P_SHIFT 4 -#define SYS_PMBIDR_EL1_F_SHIFT 5 - -/* Sampling controls */ -#define SYS_PMSCR_EL1 sys_reg(3, 0, 9, 9, 0) -#define SYS_PMSCR_EL1_E0SPE_SHIFT 0 -#define SYS_PMSCR_EL1_E1SPE_SHIFT 1 -#define SYS_PMSCR_EL1_CX_SHIFT 3 -#define SYS_PMSCR_EL1_PA_SHIFT 4 -#define SYS_PMSCR_EL1_TS_SHIFT 5 -#define SYS_PMSCR_EL1_PCT_SHIFT 6 - -#define SYS_PMSCR_EL2 sys_reg(3, 4, 9, 9, 0) -#define SYS_PMSCR_EL2_E0HSPE_SHIFT 0 -#define SYS_PMSCR_EL2_E2SPE_SHIFT 1 -#define SYS_PMSCR_EL2_CX_SHIFT 3 -#define SYS_PMSCR_EL2_PA_SHIFT 4 -#define SYS_PMSCR_EL2_TS_SHIFT 5 -#define SYS_PMSCR_EL2_PCT_SHIFT 6 - -#define SYS_PMSICR_EL1 sys_reg(3, 0, 9, 9, 2) - -#define SYS_PMSIRR_EL1 sys_reg(3, 0, 9, 9, 3) -#define SYS_PMSIRR_EL1_RND_SHIFT 0 -#define SYS_PMSIRR_EL1_INTERVAL_SHIFT 8 -#define SYS_PMSIRR_EL1_INTERVAL_MASK 0xffffffUL - -/* Filtering controls */ -#define SYS_PMSNEVFR_EL1 sys_reg(3, 0, 9, 9, 1) - -#define SYS_PMSFCR_EL1 sys_reg(3, 0, 9, 9, 4) -#define SYS_PMSFCR_EL1_FE_SHIFT 0 -#define SYS_PMSFCR_EL1_FT_SHIFT 1 -#define SYS_PMSFCR_EL1_FL_SHIFT 2 -#define SYS_PMSFCR_EL1_B_SHIFT 16 -#define SYS_PMSFCR_EL1_LD_SHIFT 17 -#define SYS_PMSFCR_EL1_ST_SHIFT 18 - -#define SYS_PMSEVFR_EL1 sys_reg(3, 0, 9, 9, 5) -#define SYS_PMSEVFR_EL1_RES0_8_2 \ +#define PMSEVFR_EL1_RES0_IMP \ (GENMASK_ULL(47, 32) | GENMASK_ULL(23, 16) | GENMASK_ULL(11, 8) |\ BIT_ULL(6) | BIT_ULL(4) | BIT_ULL(2) | BIT_ULL(0)) -#define SYS_PMSEVFR_EL1_RES0_8_3 \ - (SYS_PMSEVFR_EL1_RES0_8_2 & ~(BIT_ULL(18) | BIT_ULL(17) | BIT_ULL(11))) - -#define SYS_PMSLATFR_EL1 sys_reg(3, 0, 9, 9, 6) -#define SYS_PMSLATFR_EL1_MINLAT_SHIFT 0 - -/* Buffer controls */ -#define SYS_PMBLIMITR_EL1 sys_reg(3, 0, 9, 10, 0) -#define SYS_PMBLIMITR_EL1_E_SHIFT 0 -#define SYS_PMBLIMITR_EL1_FM_SHIFT 1 -#define SYS_PMBLIMITR_EL1_FM_MASK 0x3UL -#define SYS_PMBLIMITR_EL1_FM_STOP_IRQ (0 << SYS_PMBLIMITR_EL1_FM_SHIFT) - -#define SYS_PMBPTR_EL1 sys_reg(3, 0, 9, 10, 1) +#define PMSEVFR_EL1_RES0_V1P1 \ + (PMSEVFR_EL1_RES0_IMP & ~(BIT_ULL(18) | BIT_ULL(17) | BIT_ULL(11))) +#define PMSEVFR_EL1_RES0_V1P2 \ + (PMSEVFR_EL1_RES0_V1P1 & ~BIT_ULL(6)) /* Buffer error reporting */ -#define SYS_PMBSR_EL1 sys_reg(3, 0, 9, 10, 3) -#define SYS_PMBSR_EL1_COLL_SHIFT 16 -#define SYS_PMBSR_EL1_S_SHIFT 17 -#define SYS_PMBSR_EL1_EA_SHIFT 18 -#define SYS_PMBSR_EL1_DL_SHIFT 19 -#define SYS_PMBSR_EL1_EC_SHIFT 26 -#define SYS_PMBSR_EL1_EC_MASK 0x3fUL - -#define SYS_PMBSR_EL1_EC_BUF (0x0UL << SYS_PMBSR_EL1_EC_SHIFT) -#define SYS_PMBSR_EL1_EC_FAULT_S1 (0x24UL << SYS_PMBSR_EL1_EC_SHIFT) -#define SYS_PMBSR_EL1_EC_FAULT_S2 (0x25UL << SYS_PMBSR_EL1_EC_SHIFT) - -#define SYS_PMBSR_EL1_FAULT_FSC_SHIFT 0 -#define SYS_PMBSR_EL1_FAULT_FSC_MASK 0x3fUL +#define PMBSR_EL1_FAULT_FSC_SHIFT PMBSR_EL1_MSS_SHIFT +#define PMBSR_EL1_FAULT_FSC_MASK PMBSR_EL1_MSS_MASK -#define SYS_PMBSR_EL1_BUF_BSC_SHIFT 0 -#define SYS_PMBSR_EL1_BUF_BSC_MASK 0x3fUL +#define PMBSR_EL1_BUF_BSC_SHIFT PMBSR_EL1_MSS_SHIFT +#define PMBSR_EL1_BUF_BSC_MASK PMBSR_EL1_MSS_MASK -#define SYS_PMBSR_EL1_BUF_BSC_FULL (0x1UL << SYS_PMBSR_EL1_BUF_BSC_SHIFT) +#define PMBSR_EL1_BUF_BSC_FULL 0x1UL /*** End of Statistical Profiling Extension ***/ @@ -810,8 +731,8 @@ #define ARM64_FEATURE_FIELD_BITS 4 -/* Create a mask for the feature bits of the specified feature. */ -#define ARM64_FEATURE_MASK(x) (GENMASK_ULL(x##_SHIFT + ARM64_FEATURE_FIELD_BITS - 1, x##_SHIFT)) +/* Defined for compatibility only, do not add new users. */ +#define ARM64_FEATURE_MASK(x) (x##_MASK) #ifdef __ASSEMBLY__ diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index b713d30544f1..69a4fb749c65 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -96,5 +96,11 @@ #define HWCAP2_CSSC (1UL << 34) #define HWCAP2_RPRFM (1UL << 35) #define HWCAP2_SVE2P1 (1UL << 36) +#define HWCAP2_SME2 (1UL << 37) +#define HWCAP2_SME2P1 (1UL << 38) +#define HWCAP2_SME_I16I32 (1UL << 39) +#define HWCAP2_SME_BI32I32 (1UL << 40) +#define HWCAP2_SME_B16B16 (1UL << 41) +#define HWCAP2_SME_F16F16 (1UL << 42) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index 9525041e4a14..656a10ea6c67 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -144,6 +144,14 @@ struct sve_context { #define SVE_SIG_FLAG_SM 0x1 /* Context describes streaming mode */ +/* TPIDR2_EL0 context */ +#define TPIDR2_MAGIC 0x54504902 + +struct tpidr2_context { + struct _aarch64_ctx head; + __u64 tpidr2; +}; + #define ZA_MAGIC 0x54366345 struct za_context { @@ -152,6 +160,14 @@ struct za_context { __u16 __reserved[3]; }; +#define ZT_MAGIC 0x5a544e01 + +struct zt_context { + struct _aarch64_ctx head; + __u16 nregs; + __u16 __reserved[3]; +}; + #endif /* !__ASSEMBLY__ */ #include <asm/sve_context.h> @@ -304,4 +320,15 @@ struct za_context { #define ZA_SIG_CONTEXT_SIZE(vq) \ (ZA_SIG_REGS_OFFSET + ZA_SIG_REGS_SIZE(vq)) +#define ZT_SIG_REG_SIZE 512 + +#define ZT_SIG_REG_BYTES (ZT_SIG_REG_SIZE / 8) + +#define ZT_SIG_REGS_OFFSET sizeof(struct zt_context) + +#define ZT_SIG_REGS_SIZE(n) (ZT_SIG_REG_BYTES * n) + +#define ZT_SIG_CONTEXT_SIZE(n) \ + (sizeof(struct zt_context) + ZT_SIG_REGS_SIZE(n)) + #endif /* _UAPI__ASM_SIGCONTEXT_H */ diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 2234624536d9..ae345b06e9f7 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -9,6 +9,7 @@ #include <linux/arm_sdei.h> #include <linux/sched.h> +#include <linux/ftrace.h> #include <linux/kexec.h> #include <linux/mm.h> #include <linux/dma-mapping.h> @@ -194,5 +195,8 @@ int main(void) DEFINE(KIMAGE_START, offsetof(struct kimage, start)); BLANK(); #endif +#ifdef CONFIG_FUNCTION_TRACER + DEFINE(FTRACE_OPS_FUNC, offsetof(struct ftrace_ops, func)); +#endif return 0; } diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index a77315b338e6..da0f656079ea 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -65,6 +65,7 @@ #include <linux/bsearch.h> #include <linux/cpumask.h> #include <linux/crash_dump.h> +#include <linux/kstrtox.h> #include <linux/sort.h> #include <linux/stop_machine.h> #include <linux/sysfs.h> @@ -283,16 +284,26 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I16I64_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F64F64_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I16I32_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_B16B16_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F16_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I8I32_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F32_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_B16F32_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_BI32I32_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F32F32_SHIFT, 1, 0), ARM64_FTR_END, }; @@ -444,8 +455,8 @@ static const struct arm64_ftr_bits ftr_mvfr0[] = { static const struct arm64_ftr_bits ftr_mvfr1[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDFMAC_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_FPHP_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDHP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_FPHP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDHP_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDSP_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDInt_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_EL1_SIMDLS_SHIFT, 4, 0), @@ -529,12 +540,12 @@ static const struct arm64_ftr_bits ftr_id_mmfr5[] = { }; static const struct arm64_ftr_bits ftr_id_isar6[] = { - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_I8MM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_BF16_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_I8MM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_BF16_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_SPECRES_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_SB_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_FHM_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_DP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_SB_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_FHM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_DP_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_EL1_JSCVT_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -562,7 +573,7 @@ static const struct arm64_ftr_bits ftr_id_pfr1[] = { }; static const struct arm64_ftr_bits ftr_id_pfr2[] = { - ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_EL1_SSBS_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_EL1_SSBS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_PFR2_EL1_CSV3_SHIFT, 4, 0), ARM64_FTR_END, }; @@ -1795,7 +1806,7 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) static int __init parse_kpti(char *str) { bool enabled; - int ret = strtobool(str, &enabled); + int ret = kstrtobool(str, &enabled); if (ret) return ret; @@ -2039,14 +2050,50 @@ static bool enable_pseudo_nmi; static int __init early_enable_pseudo_nmi(char *p) { - return strtobool(p, &enable_pseudo_nmi); + return kstrtobool(p, &enable_pseudo_nmi); } early_param("irqchip.gicv3_pseudo_nmi", early_enable_pseudo_nmi); static bool can_use_gic_priorities(const struct arm64_cpu_capabilities *entry, int scope) { - return enable_pseudo_nmi && has_useable_gicv3_cpuif(entry, scope); + /* + * ARM64_HAS_GIC_CPUIF_SYSREGS has a lower index, and is a boot CPU + * feature, so will be detected earlier. + */ + BUILD_BUG_ON(ARM64_HAS_GIC_PRIO_MASKING <= ARM64_HAS_GIC_CPUIF_SYSREGS); + if (!cpus_have_cap(ARM64_HAS_GIC_CPUIF_SYSREGS)) + return false; + + return enable_pseudo_nmi; +} + +static bool has_gic_prio_relaxed_sync(const struct arm64_cpu_capabilities *entry, + int scope) +{ + /* + * If we're not using priority masking then we won't be poking PMR_EL1, + * and there's no need to relax synchronization of writes to it, and + * ICC_CTLR_EL1 might not be accessible and we must avoid reads from + * that. + * + * ARM64_HAS_GIC_PRIO_MASKING has a lower index, and is a boot CPU + * feature, so will be detected earlier. + */ + BUILD_BUG_ON(ARM64_HAS_GIC_PRIO_RELAXED_SYNC <= ARM64_HAS_GIC_PRIO_MASKING); + if (!cpus_have_cap(ARM64_HAS_GIC_PRIO_MASKING)) + return false; + + /* + * When Priority Mask Hint Enable (PMHE) == 0b0, PMR is not used as a + * hint for interrupt distribution, a DSB is not necessary when + * unmasking IRQs via PMR, and we can relax the barrier to a NOP. + * + * Linux itself doesn't use 1:N distribution, so has no need to + * set PMHE. The only reason to have it set is if EL3 requires it + * (and we can't change it). + */ + return (gic_read_ctlr() & ICC_CTLR_EL1_PMHE_MASK) == 0; } #endif @@ -2142,7 +2189,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { }, { .desc = "GIC system register CPU interface", - .capability = ARM64_HAS_SYSREG_GIC_CPUIF, + .capability = ARM64_HAS_GIC_CPUIF_SYSREGS, .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, .matches = has_useable_gicv3_cpuif, .sys_reg = SYS_ID_AA64PFR0_EL1, @@ -2534,14 +2581,17 @@ static const struct arm64_cpu_capabilities arm64_features[] = { * Depends on having GICv3 */ .desc = "IRQ priority masking", - .capability = ARM64_HAS_IRQ_PRIO_MASKING, + .capability = ARM64_HAS_GIC_PRIO_MASKING, .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, .matches = can_use_gic_priorities, - .sys_reg = SYS_ID_AA64PFR0_EL1, - .field_pos = ID_AA64PFR0_EL1_GIC_SHIFT, - .field_width = 4, - .sign = FTR_UNSIGNED, - .min_field_value = 1, + }, + { + /* + * Depends on ARM64_HAS_GIC_PRIO_MASKING + */ + .capability = ARM64_HAS_GIC_PRIO_RELAXED_SYNC, + .type = ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE, + .matches = has_gic_prio_relaxed_sync, }, #endif #ifdef CONFIG_ARM64_E0PD @@ -2649,6 +2699,18 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .matches = has_cpuid_feature, .cpu_enable = fa64_kernel_enable, }, + { + .desc = "SME2", + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .capability = ARM64_SME2, + .sys_reg = SYS_ID_AA64PFR1_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64PFR1_EL1_SME_SHIFT, + .field_width = ID_AA64PFR1_EL1_SME_WIDTH, + .min_field_value = ID_AA64PFR1_EL1_SME_SME2, + .matches = has_cpuid_feature, + .cpu_enable = sme2_kernel_enable, + }, #endif /* CONFIG_ARM64_SME */ { .desc = "WFx with timeout", @@ -2777,7 +2839,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_FP_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_AdvSIMD_SHIFT, 4, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_AdvSIMD_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP), - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_DIT_SHIFT, 4, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DIT), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_EL1_DIT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DIT), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_DPB_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DCPOP), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_DPB_SHIFT, 4, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_DCPODP), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_EL1_JSCVT_SHIFT, 4, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_JSCVT), @@ -2827,11 +2889,17 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { #ifdef CONFIG_ARM64_SME HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_EL1_SME_SHIFT, 4, FTR_UNSIGNED, ID_AA64PFR1_EL1_SME_IMP, CAP_HWCAP, KERNEL_HWCAP_SME), HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_FA64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_SMEver_SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_SMEver_SME2, CAP_HWCAP, KERNEL_HWCAP_SME2), HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_I16I64_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_I16I64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F64F64_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F64F64_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F64F64), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_I16I32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_I16I32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_B16B16_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_B16B16_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F16F16_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F16F16_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16), HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_I8I32_SHIFT, 4, FTR_UNSIGNED, ID_AA64SMFR0_EL1_I8I32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32), HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F16F32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32), HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_B16F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_B16F32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32), + HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_BI32I32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_BI32I32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32), HWCAP_CAP(SYS_ID_AA64SMFR0_EL1, ID_AA64SMFR0_EL1_F32F32_SHIFT, 1, FTR_UNSIGNED, ID_AA64SMFR0_EL1_F32F32_IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32), #endif /* CONFIG_ARM64_SME */ {}, @@ -2866,11 +2934,19 @@ static const struct arm64_cpu_capabilities compat_elf_hwcaps[] = { /* Arm v8 mandates MVFR0.FPDP == {0, 2}. So, piggy back on this for the presence of VFP support */ HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_EL1_FPDP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP), HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_EL1_FPDP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3), + HWCAP_CAP(SYS_MVFR1_EL1, MVFR1_EL1_FPHP_SHIFT, 4, FTR_UNSIGNED, 3, CAP_COMPAT_HWCAP, COMPAT_HWCAP_FPHP), + HWCAP_CAP(SYS_MVFR1_EL1, MVFR1_EL1_SIMDHP_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_ASIMDHP), HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL), HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_AES_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES), HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_SHA1_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1), HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_SHA2_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA2), HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_EL1_CRC32_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_CRC32), + HWCAP_CAP(SYS_ID_ISAR6_EL1, ID_ISAR6_EL1_DP_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_ASIMDDP), + HWCAP_CAP(SYS_ID_ISAR6_EL1, ID_ISAR6_EL1_FHM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_ASIMDFHM), + HWCAP_CAP(SYS_ID_ISAR6_EL1, ID_ISAR6_EL1_SB_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SB), + HWCAP_CAP(SYS_ID_ISAR6_EL1, ID_ISAR6_EL1_BF16_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_ASIMDBF16), + HWCAP_CAP(SYS_ID_ISAR6_EL1, ID_ISAR6_EL1_I8MM_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_I8MM), + HWCAP_CAP(SYS_ID_PFR2_EL1, ID_PFR2_EL1_SSBS_SHIFT, 4, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SSBS), #endif {}, }; diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 379695262b77..eb4378c23b3c 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -119,6 +119,12 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_CSSC] = "cssc", [KERNEL_HWCAP_RPRFM] = "rprfm", [KERNEL_HWCAP_SVE2P1] = "sve2p1", + [KERNEL_HWCAP_SME2] = "sme2", + [KERNEL_HWCAP_SME2P1] = "sme2p1", + [KERNEL_HWCAP_SME_I16I32] = "smei16i32", + [KERNEL_HWCAP_SME_BI32I32] = "smebi32i32", + [KERNEL_HWCAP_SME_B16B16] = "smeb16b16", + [KERNEL_HWCAP_SME_F16F16] = "smef16f16", }; #ifdef CONFIG_COMPAT @@ -146,6 +152,12 @@ static const char *const compat_hwcap_str[] = { [COMPAT_KERNEL_HWCAP(VFPD32)] = NULL, /* Not possible on arm64 */ [COMPAT_KERNEL_HWCAP(LPAE)] = "lpae", [COMPAT_KERNEL_HWCAP(EVTSTRM)] = "evtstrm", + [COMPAT_KERNEL_HWCAP(FPHP)] = "fphp", + [COMPAT_KERNEL_HWCAP(ASIMDHP)] = "asimdhp", + [COMPAT_KERNEL_HWCAP(ASIMDDP)] = "asimddp", + [COMPAT_KERNEL_HWCAP(ASIMDFHM)] = "asimdfhm", + [COMPAT_KERNEL_HWCAP(ASIMDBF16)] = "asimdbf16", + [COMPAT_KERNEL_HWCAP(I8MM)] = "i8mm", }; #define COMPAT_KERNEL_HWCAP2(x) const_ilog2(COMPAT_HWCAP2_ ## x) @@ -155,6 +167,8 @@ static const char *const compat_hwcap2_str[] = { [COMPAT_KERNEL_HWCAP2(SHA1)] = "sha1", [COMPAT_KERNEL_HWCAP2(SHA2)] = "sha2", [COMPAT_KERNEL_HWCAP2(CRC32)] = "crc32", + [COMPAT_KERNEL_HWCAP2(SB)] = "sb", + [COMPAT_KERNEL_HWCAP2(SSBS)] = "ssbs", }; #endif /* CONFIG_COMPAT */ diff --git a/arch/arm64/kernel/entry-fpsimd.S b/arch/arm64/kernel/entry-fpsimd.S index 229436f33df5..6325db1a2179 100644 --- a/arch/arm64/kernel/entry-fpsimd.S +++ b/arch/arm64/kernel/entry-fpsimd.S @@ -100,25 +100,35 @@ SYM_FUNC_START(sme_set_vq) SYM_FUNC_END(sme_set_vq) /* - * Save the SME state + * Save the ZA and ZT state * * x0 - pointer to buffer for state + * x1 - number of ZT registers to save */ -SYM_FUNC_START(za_save_state) - _sme_rdsvl 1, 1 // x1 = VL/8 - sme_save_za 0, x1, 12 +SYM_FUNC_START(sme_save_state) + _sme_rdsvl 2, 1 // x2 = VL/8 + sme_save_za 0, x2, 12 // Leaves x0 pointing to the end of ZA + + cbz x1, 1f + _str_zt 0 +1: ret -SYM_FUNC_END(za_save_state) +SYM_FUNC_END(sme_save_state) /* - * Load the SME state + * Load the ZA and ZT state * * x0 - pointer to buffer for state + * x1 - number of ZT registers to save */ -SYM_FUNC_START(za_load_state) - _sme_rdsvl 1, 1 // x1 = VL/8 - sme_load_za 0, x1, 12 +SYM_FUNC_START(sme_load_state) + _sme_rdsvl 2, 1 // x2 = VL/8 + sme_load_za 0, x2, 12 // Leaves x0 pointing to the end of ZA + + cbz x1, 1f + _ldr_zt 0 +1: ret -SYM_FUNC_END(za_load_state) +SYM_FUNC_END(sme_load_state) #endif /* CONFIG_ARM64_SME */ diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S index 3b625f76ffba..350ed81324ac 100644 --- a/arch/arm64/kernel/entry-ftrace.S +++ b/arch/arm64/kernel/entry-ftrace.S @@ -65,13 +65,35 @@ SYM_CODE_START(ftrace_caller) stp x29, x30, [sp, #FREGS_SIZE] add x29, sp, #FREGS_SIZE - 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 - mov x3, sp // regs + /* Prepare arguments for the the tracer func */ + sub x0, x30, #AARCH64_INSN_SIZE // ip (callsite's BL insn) + mov x1, x9 // parent_ip (callsite's LR) + mov x3, sp // regs + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + /* + * The literal pointer to the ops is at an 8-byte aligned boundary + * which is either 12 or 16 bytes before the BL instruction in the call + * site. See ftrace_call_adjust() for details. + * + * Therefore here the LR points at `literal + 16` or `literal + 20`, + * and we can find the address of the literal in either case by + * aligning to an 8-byte boundary and subtracting 16. We do the + * alignment first as this allows us to fold the subtraction into the + * LDR. + */ + bic x2, x30, 0x7 + ldr x2, [x2, #-16] // op + + ldr x4, [x2, #FTRACE_OPS_FUNC] // op->func + blr x4 // op->func(ip, parent_ip, op, regs) + +#else + ldr_l x2, function_trace_op // op SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) - bl ftrace_stub + bl ftrace_stub // func(ip, parent_ip, op, regs) +#endif /* * At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 11cb99c4d298..ab2a6e33c052 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -275,7 +275,7 @@ alternative_if ARM64_HAS_ADDRESS_AUTH alternative_else_nop_endif 1: - scs_load tsk + scs_load_current .else add x21, sp, #PT_REGS_SIZE get_current_task tsk @@ -311,13 +311,16 @@ alternative_else_nop_endif .endif #ifdef CONFIG_ARM64_PSEUDO_NMI - /* Save pmr */ -alternative_if ARM64_HAS_IRQ_PRIO_MASKING +alternative_if_not ARM64_HAS_GIC_PRIO_MASKING + b .Lskip_pmr_save\@ +alternative_else_nop_endif + mrs_s x20, SYS_ICC_PMR_EL1 str x20, [sp, #S_PMR_SAVE] mov x20, #GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET msr_s SYS_ICC_PMR_EL1, x20 -alternative_else_nop_endif + +.Lskip_pmr_save\@: #endif /* @@ -336,15 +339,19 @@ alternative_else_nop_endif .endif #ifdef CONFIG_ARM64_PSEUDO_NMI - /* Restore pmr */ -alternative_if ARM64_HAS_IRQ_PRIO_MASKING +alternative_if_not ARM64_HAS_GIC_PRIO_MASKING + b .Lskip_pmr_restore\@ +alternative_else_nop_endif + ldr x20, [sp, #S_PMR_SAVE] msr_s SYS_ICC_PMR_EL1, x20 - mrs_s x21, SYS_ICC_CTLR_EL1 - tbz x21, #6, .L__skip_pmr_sync\@ // Check for ICC_CTLR_EL1.PMHE - dsb sy // Ensure priority change is seen by redistributor -.L__skip_pmr_sync\@: + + /* Ensure priority change is seen by redistributor */ +alternative_if_not ARM64_HAS_GIC_PRIO_RELAXED_SYNC + dsb sy alternative_else_nop_endif + +.Lskip_pmr_restore\@: #endif ldp x21, x22, [sp, #S_PC] // load ELR, SPSR @@ -848,7 +855,7 @@ SYM_FUNC_START(cpu_switch_to) msr sp_el0, x1 ptrauth_keys_install_kernel x1, x8, x9, x10 scs_save x0 - scs_load x1 + scs_load_current ret SYM_FUNC_END(cpu_switch_to) NOKPROBE(cpu_switch_to) @@ -876,19 +883,19 @@ NOKPROBE(ret_from_fork) */ SYM_FUNC_START(call_on_irq_stack) #ifdef CONFIG_SHADOW_CALL_STACK - stp scs_sp, xzr, [sp, #-16]! + get_current_task x16 + scs_save x16 ldr_this_cpu scs_sp, irq_shadow_call_stack_ptr, x17 #endif + /* Create a frame record to save our LR and SP (implicit in FP) */ stp x29, x30, [sp, #-16]! mov x29, sp ldr_this_cpu x16, irq_stack_ptr, x17 - mov x15, #IRQ_STACK_SIZE - add x16, x16, x15 /* Move to the new stack and call the function there */ - mov sp, x16 + add sp, x16, #IRQ_STACK_SIZE blr x1 /* @@ -897,9 +904,7 @@ SYM_FUNC_START(call_on_irq_stack) */ mov sp, x29 ldp x29, x30, [sp], #16 -#ifdef CONFIG_SHADOW_CALL_STACK - ldp scs_sp, xzr, [sp], #16 -#endif + scs_load_current ret SYM_FUNC_END(call_on_irq_stack) NOKPROBE(call_on_irq_stack) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index dcc81e7200d4..c11cb445ffca 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -299,7 +299,7 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, /* * TIF_SME controls whether a task can use SME without trapping while * in userspace, when TIF_SME is set then we must have storage - * alocated in sve_state and za_state to store the contents of both ZA + * alocated in sve_state and sme_state to store the contents of both ZA * and the SVE registers for both streaming and non-streaming modes. * * If both SVCR.ZA and SVCR.SM are disabled then at any point we @@ -429,7 +429,8 @@ static void task_fpsimd_load(void) write_sysreg_s(current->thread.svcr, SYS_SVCR); if (thread_za_enabled(¤t->thread)) - za_load_state(current->thread.za_state); + sme_load_state(current->thread.sme_state, + system_supports_sme2()); if (thread_sm_enabled(¤t->thread)) restore_ffr = system_supports_fa64(); @@ -490,7 +491,8 @@ static void fpsimd_save(void) *svcr = read_sysreg_s(SYS_SVCR); if (*svcr & SVCR_ZA_MASK) - za_save_state(last->za_state); + sme_save_state(last->sme_state, + system_supports_sme2()); /* If we are in streaming mode override regular SVE. */ if (*svcr & SVCR_SM_MASK) { @@ -1257,30 +1259,30 @@ void fpsimd_release_task(struct task_struct *dead_task) #ifdef CONFIG_ARM64_SME /* - * Ensure that task->thread.za_state is allocated and sufficiently large. + * Ensure that task->thread.sme_state is allocated and sufficiently large. * * This function should be used only in preparation for replacing - * task->thread.za_state with new data. The memory is always zeroed + * task->thread.sme_state with new data. The memory is always zeroed * here to prevent stale data from showing through: this is done in * the interest of testability and predictability, the architecture * guarantees that when ZA is enabled it will be zeroed. */ void sme_alloc(struct task_struct *task) { - if (task->thread.za_state) { - memset(task->thread.za_state, 0, za_state_size(task)); + if (task->thread.sme_state) { + memset(task->thread.sme_state, 0, sme_state_size(task)); return; } /* This could potentially be up to 64K. */ - task->thread.za_state = - kzalloc(za_state_size(task), GFP_KERNEL); + task->thread.sme_state = + kzalloc(sme_state_size(task), GFP_KERNEL); } static void sme_free(struct task_struct *task) { - kfree(task->thread.za_state); - task->thread.za_state = NULL; + kfree(task->thread.sme_state); + task->thread.sme_state = NULL; } void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) @@ -1302,6 +1304,17 @@ void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) * This must be called after sme_kernel_enable(), we rely on the * feature table being sorted to ensure this. */ +void sme2_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) +{ + /* Allow use of ZT0 */ + write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_EZT0_MASK, + SYS_SMCR_EL1); +} + +/* + * This must be called after sme_kernel_enable(), we rely on the + * feature table being sorted to ensure this. + */ void fa64_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p) { /* Allow use of FA64 */ @@ -1322,7 +1335,6 @@ u64 read_smcr_features(void) unsigned int vq_max; sme_kernel_enable(NULL); - sme_smstart_sm(); /* * Set the maximum possible VL. @@ -1332,11 +1344,9 @@ u64 read_smcr_features(void) smcr = read_sysreg_s(SYS_SMCR_EL1); smcr &= ~(u64)SMCR_ELx_LEN_MASK; /* Only the LEN field */ - vq_max = sve_vq_from_vl(sve_get_vl()); + vq_max = sve_vq_from_vl(sme_get_vl()); smcr |= vq_max - 1; /* set LEN field to maximum effective value */ - sme_smstop_sm(); - return smcr; } @@ -1488,7 +1498,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs) sve_alloc(current, false); sme_alloc(current); - if (!current->thread.sve_state || !current->thread.za_state) { + if (!current->thread.sve_state || !current->thread.sme_state) { force_sig(SIGKILL); return; } @@ -1609,7 +1619,7 @@ static void fpsimd_flush_thread_vl(enum vec_type type) void fpsimd_flush_thread(void) { void *sve_state = NULL; - void *za_state = NULL; + void *sme_state = NULL; if (!system_supports_fpsimd()) return; @@ -1634,8 +1644,8 @@ void fpsimd_flush_thread(void) clear_thread_flag(TIF_SME); /* Defer kfree() while in atomic context */ - za_state = current->thread.za_state; - current->thread.za_state = NULL; + sme_state = current->thread.sme_state; + current->thread.sme_state = NULL; fpsimd_flush_thread_vl(ARM64_VEC_SME); current->thread.svcr = 0; @@ -1645,7 +1655,7 @@ void fpsimd_flush_thread(void) put_cpu_fpsimd_context(); kfree(sve_state); - kfree(za_state); + kfree(sme_state); } /* @@ -1711,7 +1721,7 @@ static void fpsimd_bind_task_to_cpu(void) WARN_ON(!system_supports_fpsimd()); last->st = ¤t->thread.uw.fpsimd_state; last->sve_state = current->thread.sve_state; - last->za_state = current->thread.za_state; + last->sme_state = current->thread.sme_state; last->sve_vl = task_get_sve_vl(current); last->sme_vl = task_get_sme_vl(current); last->svcr = ¤t->thread.svcr; diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index b30b955a8921..5545fe1a9012 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -60,6 +60,89 @@ int ftrace_regs_query_register_offset(const char *name) } #endif +unsigned long ftrace_call_adjust(unsigned long addr) +{ + /* + * When using mcount, addr is the address of the mcount call + * instruction, and no adjustment is necessary. + */ + if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_ARGS)) + return addr; + + /* + * When using patchable-function-entry without pre-function NOPS, addr + * is the address of the first NOP after the function entry point. + * + * The compiler has either generated: + * + * addr+00: func: NOP // To be patched to MOV X9, LR + * addr+04: NOP // To be patched to BL <caller> + * + * Or: + * + * addr-04: BTI C + * addr+00: func: NOP // To be patched to MOV X9, LR + * addr+04: NOP // To be patched to BL <caller> + * + * We must adjust addr to the address of the NOP which will be patched + * to `BL <caller>`, which is at `addr + 4` bytes in either case. + * + */ + if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + return addr + AARCH64_INSN_SIZE; + + /* + * When using patchable-function-entry with pre-function NOPs, addr is + * the address of the first pre-function NOP. + * + * Starting from an 8-byte aligned base, the compiler has either + * generated: + * + * addr+00: NOP // Literal (first 32 bits) + * addr+04: NOP // Literal (last 32 bits) + * addr+08: func: NOP // To be patched to MOV X9, LR + * addr+12: NOP // To be patched to BL <caller> + * + * Or: + * + * addr+00: NOP // Literal (first 32 bits) + * addr+04: NOP // Literal (last 32 bits) + * addr+08: func: BTI C + * addr+12: NOP // To be patched to MOV X9, LR + * addr+16: NOP // To be patched to BL <caller> + * + * We must adjust addr to the address of the NOP which will be patched + * to `BL <caller>`, which is at either addr+12 or addr+16 depending on + * whether there is a BTI. + */ + + if (!IS_ALIGNED(addr, sizeof(unsigned long))) { + WARN_RATELIMIT(1, "Misaligned patch-site %pS\n", + (void *)(addr + 8)); + return 0; + } + + /* Skip the NOPs placed before the function entry point */ + addr += 2 * AARCH64_INSN_SIZE; + + /* Skip any BTI */ + if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) { + u32 insn = le32_to_cpu(*(__le32 *)addr); + + if (aarch64_insn_is_bti(insn)) { + addr += AARCH64_INSN_SIZE; + } else if (insn != aarch64_insn_gen_nop()) { + WARN_RATELIMIT(1, "unexpected insn in patch-site %pS: 0x%08x\n", + (void *)addr, insn); + } + } + + /* Skip the first NOP after function entry */ + addr += AARCH64_INSN_SIZE; + + return addr; +} + /* * Replace a single instruction, which may be a branch or NOP. * If @validate == true, a replaced instruction is checked against 'old'. @@ -98,6 +181,13 @@ int ftrace_update_ftrace_func(ftrace_func_t func) unsigned long pc; u32 new; + /* + * When using CALL_OPS, the function to call is associated with the + * call site, and we don't have a global function pointer to update. + */ + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + return 0; + pc = (unsigned long)ftrace_call; new = aarch64_insn_gen_branch_imm(pc, (unsigned long)func, AARCH64_INSN_BRANCH_LINK); @@ -176,6 +266,44 @@ static bool ftrace_find_callable_addr(struct dyn_ftrace *rec, return true; } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS +static const struct ftrace_ops *arm64_rec_get_ops(struct dyn_ftrace *rec) +{ + const struct ftrace_ops *ops = NULL; + + if (rec->flags & FTRACE_FL_CALL_OPS_EN) { + ops = ftrace_find_unique_ops(rec); + WARN_ON_ONCE(!ops); + } + + if (!ops) + ops = &ftrace_list_ops; + + return ops; +} + +static int ftrace_rec_set_ops(const struct dyn_ftrace *rec, + const struct ftrace_ops *ops) +{ + unsigned long literal = ALIGN_DOWN(rec->ip - 12, 8); + return aarch64_insn_write_literal_u64((void *)literal, + (unsigned long)ops); +} + +static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) +{ + return ftrace_rec_set_ops(rec, &ftrace_nop_ops); +} + +static int ftrace_rec_update_ops(struct dyn_ftrace *rec) +{ + return ftrace_rec_set_ops(rec, arm64_rec_get_ops(rec)); +} +#else +static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) { return 0; } +static int ftrace_rec_update_ops(struct dyn_ftrace *rec) { return 0; } +#endif + /* * Turn on the call to ftrace_caller() in instrumented function */ @@ -183,6 +311,11 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) { unsigned long pc = rec->ip; u32 old, new; + int ret; + + ret = ftrace_rec_update_ops(rec); + if (ret) + return ret; if (!ftrace_find_callable_addr(rec, NULL, &addr)) return -EINVAL; @@ -193,6 +326,19 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) return ftrace_modify_code(pc, old, new, true); } +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + if (WARN_ON_ONCE(old_addr != (unsigned long)ftrace_caller)) + return -EINVAL; + if (WARN_ON_ONCE(addr != (unsigned long)ftrace_caller)) + return -EINVAL; + + return ftrace_rec_update_ops(rec); +} +#endif + #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS /* * The compiler has inserted two NOPs before the regular function prologue. @@ -209,7 +355,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) * | NOP | MOV X9, LR | MOV X9, LR | * | NOP | NOP | BL <entry> | * - * The LR value will be recovered by ftrace_regs_entry, and restored into LR + * The LR value will be recovered by ftrace_caller, and restored into LR * before returning to the regular function prologue. When a function is not * being traced, the MOV is not harmful given x9 is not live per the AAPCS. * @@ -220,6 +366,11 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) { unsigned long pc = rec->ip - AARCH64_INSN_SIZE; u32 old, new; + int ret; + + ret = ftrace_rec_set_nop_ops(rec); + if (ret) + return ret; old = aarch64_insn_gen_nop(); new = aarch64_insn_gen_move_reg(AARCH64_INSN_REG_9, @@ -237,9 +388,14 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, { unsigned long pc = rec->ip; u32 old = 0, new; + int ret; new = aarch64_insn_gen_nop(); + ret = ftrace_rec_set_nop_ops(rec); + if (ret) + return ret; + /* * When using mcount, callsites in modules may have been initalized to * call an arbitrary module PLT (which redirects to the _mcount stub) diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 107a2b87577c..212d93aca5e6 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -455,7 +455,7 @@ SYM_FUNC_END(create_kernel_mapping) stp xzr, xzr, [sp, #S_STACKFRAME] add x29, sp, #S_STACKFRAME - scs_load \tsk + scs_load_current adr_l \tmp1, __per_cpu_offset ldr w\tmp2, [\tsk, #TSK_TI_CPU] diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S index 2ee18c860f2a..111ff33d93ee 100644 --- a/arch/arm64/kernel/hyp-stub.S +++ b/arch/arm64/kernel/hyp-stub.S @@ -132,6 +132,13 @@ SYM_CODE_START_LOCAL(__finalise_el2) orr x0, x0, SMCR_ELx_FA64_MASK .Lskip_sme_fa64: + // ZT0 available? + mrs_s x1, SYS_ID_AA64SMFR0_EL1 + __check_override id_aa64smfr0 ID_AA64SMFR0_EL1_SMEver_SHIFT 4 .Linit_sme_zt0 .Lskip_sme_zt0 +.Linit_sme_zt0: + orr x0, x0, SMCR_ELx_EZT0_MASK +.Lskip_sme_zt0: + orr x0, x0, #SMCR_ELx_LEN_MASK // Enable full SME vector msr_s SYS_SMCR_EL2, x0 // length for EL1. diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c index 95133765ed29..d833d78a7f31 100644 --- a/arch/arm64/kernel/idreg-override.c +++ b/arch/arm64/kernel/idreg-override.c @@ -131,6 +131,7 @@ static const struct ftr_set_desc smfr0 __initconst = { .name = "id_aa64smfr0", .override = &id_aa64smfr0_override, .fields = { + FIELD("smever", ID_AA64SMFR0_EL1_SMEver_SHIFT, NULL), /* FA64 is a one bit field... :-/ */ { "fa64", ID_AA64SMFR0_EL1_FA64_SHIFT, 1, }, {} diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 73388b21d07d..8309197c0ebd 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -68,9 +68,7 @@ KVM_NVHE_ALIAS(__hyp_stub_vectors); KVM_NVHE_ALIAS(vgic_v2_cpuif_trap); KVM_NVHE_ALIAS(vgic_v3_cpuif_trap); -/* Static key checked in pmr_sync(). */ #ifdef CONFIG_ARM64_PSEUDO_NMI -KVM_NVHE_ALIAS(gic_pmr_sync); /* Static key checked in GIC_PRIO_IRQOFF. */ KVM_NVHE_ALIAS(gic_nonsecure_priorities); #endif diff --git a/arch/arm64/kernel/patch-scs.c b/arch/arm64/kernel/patch-scs.c index 1b3da02d5b74..a1fe4b4ff591 100644 --- a/arch/arm64/kernel/patch-scs.c +++ b/arch/arm64/kernel/patch-scs.c @@ -130,7 +130,8 @@ struct eh_frame { static int noinstr scs_handle_fde_frame(const struct eh_frame *frame, bool fde_has_augmentation_data, - int code_alignment_factor) + int code_alignment_factor, + bool dry_run) { int size = frame->size - offsetof(struct eh_frame, opcodes) + 4; u64 loc = (u64)offset_to_ptr(&frame->initial_loc); @@ -184,7 +185,8 @@ static int noinstr scs_handle_fde_frame(const struct eh_frame *frame, break; case DW_CFA_negate_ra_state: - scs_patch_loc(loc - 4); + if (!dry_run) + scs_patch_loc(loc - 4); break; case 0x40 ... 0x7f: @@ -235,9 +237,12 @@ int noinstr scs_patch(const u8 eh_frame[], int size) } else { ret = scs_handle_fde_frame(frame, fde_has_augmentation_data, - code_alignment_factor); + code_alignment_factor, + true); if (ret) return ret; + scs_handle_fde_frame(frame, fde_has_augmentation_data, + code_alignment_factor, false); } p += sizeof(frame->size) + frame->size; diff --git a/arch/arm64/kernel/patching.c b/arch/arm64/kernel/patching.c index 33e0fabc0b79..b4835f6d594b 100644 --- a/arch/arm64/kernel/patching.c +++ b/arch/arm64/kernel/patching.c @@ -88,6 +88,23 @@ int __kprobes aarch64_insn_write(void *addr, u32 insn) return __aarch64_insn_write(addr, cpu_to_le32(insn)); } +noinstr int aarch64_insn_write_literal_u64(void *addr, u64 val) +{ + u64 *waddr; + unsigned long flags; + int ret; + + raw_spin_lock_irqsave(&patch_lock, flags); + waddr = patch_map(addr, FIX_TEXT_POKE0); + + ret = copy_to_kernel_nofault(waddr, &val, sizeof(val)); + + patch_unmap(FIX_TEXT_POKE0); + raw_spin_unlock_irqrestore(&patch_lock, flags); + + return ret; +} + int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn) { u32 *tp = addr; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 269ac1c25ae2..71d59b5abede 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -307,27 +307,28 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) /* * In the unlikely event that we create a new thread with ZA - * enabled we should retain the ZA state so duplicate it here. - * This may be shortly freed if we exec() or if CLONE_SETTLS - * but it's simpler to do it here. To avoid confusing the rest - * of the code ensure that we have a sve_state allocated - * whenever za_state is allocated. + * enabled we should retain the ZA and ZT state so duplicate + * it here. This may be shortly freed if we exec() or if + * CLONE_SETTLS but it's simpler to do it here. To avoid + * confusing the rest of the code ensure that we have a + * sve_state allocated whenever sme_state is allocated. */ if (thread_za_enabled(&src->thread)) { dst->thread.sve_state = kzalloc(sve_state_size(src), GFP_KERNEL); if (!dst->thread.sve_state) return -ENOMEM; - dst->thread.za_state = kmemdup(src->thread.za_state, - za_state_size(src), - GFP_KERNEL); - if (!dst->thread.za_state) { + + dst->thread.sme_state = kmemdup(src->thread.sme_state, + sme_state_size(src), + GFP_KERNEL); + if (!dst->thread.sme_state) { kfree(dst->thread.sve_state); dst->thread.sve_state = NULL; return -ENOMEM; } } else { - dst->thread.za_state = NULL; + dst->thread.sme_state = NULL; clear_tsk_thread_flag(dst, TIF_SME); } diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 2686ab157601..143a971d7511 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -683,7 +683,7 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset, unsigned long tls[2]; tls[0] = target->thread.uw.tp_value; - if (system_supports_sme()) + if (system_supports_tpidr2()) tls[1] = target->thread.tpidr2_el0; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, tls, 0, count); @@ -691,7 +691,7 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset, return ret; target->thread.uw.tp_value = tls[0]; - if (system_supports_sme()) + if (system_supports_tpidr2()) target->thread.tpidr2_el0 = tls[1]; return ret; @@ -1045,7 +1045,7 @@ static int za_get(struct task_struct *target, if (thread_za_enabled(&target->thread)) { start = end; end = ZA_PT_SIZE(vq); - membuf_write(&to, target->thread.za_state, end - start); + membuf_write(&to, target->thread.sme_state, end - start); } /* Zero any trailing padding */ @@ -1099,7 +1099,7 @@ static int za_set(struct task_struct *target, /* Allocate/reinit ZA storage */ sme_alloc(target); - if (!target->thread.za_state) { + if (!target->thread.sme_state) { ret = -ENOMEM; goto out; } @@ -1124,7 +1124,7 @@ static int za_set(struct task_struct *target, start = ZA_PT_ZA_OFFSET; end = ZA_PT_SIZE(vq); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, - target->thread.za_state, + target->thread.sme_state, start, end); if (ret) goto out; @@ -1138,6 +1138,51 @@ out: return ret; } +static int zt_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + if (!system_supports_sme2()) + return -EINVAL; + + /* + * If PSTATE.ZA is not set then ZT will be zeroed when it is + * enabled so report the current register value as zero. + */ + if (thread_za_enabled(&target->thread)) + membuf_write(&to, thread_zt_state(&target->thread), + ZT_SIG_REG_BYTES); + else + membuf_zero(&to, ZT_SIG_REG_BYTES); + + return 0; +} + +static int zt_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + + if (!system_supports_sme2()) + return -EINVAL; + + if (!thread_za_enabled(&target->thread)) { + sme_alloc(target); + if (!target->thread.sme_state) + return -ENOMEM; + } + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + thread_zt_state(&target->thread), + 0, ZT_SIG_REG_BYTES); + if (ret == 0) + target->thread.svcr |= SVCR_ZA_MASK; + + return ret; +} + #endif /* CONFIG_ARM64_SME */ #ifdef CONFIG_ARM64_PTR_AUTH @@ -1360,6 +1405,7 @@ enum aarch64_regset { #ifdef CONFIG_ARM64_SVE REGSET_SSVE, REGSET_ZA, + REGSET_ZT, #endif #ifdef CONFIG_ARM64_PTR_AUTH REGSET_PAC_MASK, @@ -1467,6 +1513,14 @@ static const struct user_regset aarch64_regsets[] = { .regset_get = za_get, .set = za_set, }, + [REGSET_ZT] = { /* SME ZT */ + .core_note_type = NT_ARM_ZT, + .n = 1, + .size = ZT_SIG_REG_BYTES, + .align = sizeof(u64), + .regset_get = zt_get, + .set = zt_set, + }, #endif #ifdef CONFIG_ARM64_PTR_AUTH [REGSET_PAC_MASK] = { diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index e0d09bf5b01b..ed692284f199 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -56,7 +56,9 @@ struct rt_sigframe_user_layout { unsigned long fpsimd_offset; unsigned long esr_offset; unsigned long sve_offset; + unsigned long tpidr2_offset; unsigned long za_offset; + unsigned long zt_offset; unsigned long extra_offset; unsigned long end_offset; }; @@ -220,7 +222,9 @@ static int restore_fpsimd_context(struct fpsimd_context __user *ctx) struct user_ctxs { struct fpsimd_context __user *fpsimd; struct sve_context __user *sve; + struct tpidr2_context __user *tpidr2; struct za_context __user *za; + struct zt_context __user *zt; }; #ifdef CONFIG_ARM64_SVE @@ -361,6 +365,32 @@ extern int preserve_sve_context(void __user *ctx); #ifdef CONFIG_ARM64_SME +static int preserve_tpidr2_context(struct tpidr2_context __user *ctx) +{ + int err = 0; + + current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0); + + __put_user_error(TPIDR2_MAGIC, &ctx->head.magic, err); + __put_user_error(sizeof(*ctx), &ctx->head.size, err); + __put_user_error(current->thread.tpidr2_el0, &ctx->tpidr2, err); + + return err; +} + +static int restore_tpidr2_context(struct user_ctxs *user) +{ + u64 tpidr2_el0; + int err = 0; + + /* Magic and size were validated deciding to call this function */ + __get_user_error(tpidr2_el0, &user->tpidr2->tpidr2, err); + if (!err) + current->thread.tpidr2_el0 = tpidr2_el0; + + return err; +} + static int preserve_za_context(struct za_context __user *ctx) { int err = 0; @@ -389,7 +419,7 @@ static int preserve_za_context(struct za_context __user *ctx) * fpsimd_signal_preserve_current_state(). */ err |= __copy_to_user((char __user *)ctx + ZA_SIG_REGS_OFFSET, - current->thread.za_state, + current->thread.sme_state, ZA_SIG_REGS_SIZE(vq)); } @@ -420,7 +450,7 @@ static int restore_za_context(struct user_ctxs *user) /* * Careful: we are about __copy_from_user() directly into - * thread.za_state with preemption enabled, so protection is + * thread.sme_state with preemption enabled, so protection is * needed to prevent a racing context switch from writing stale * registers back over the new data. */ @@ -429,13 +459,13 @@ static int restore_za_context(struct user_ctxs *user) /* From now, fpsimd_thread_switch() won't touch thread.sve_state */ sme_alloc(current); - if (!current->thread.za_state) { + if (!current->thread.sme_state) { current->thread.svcr &= ~SVCR_ZA_MASK; clear_thread_flag(TIF_SME); return -ENOMEM; } - err = __copy_from_user(current->thread.za_state, + err = __copy_from_user(current->thread.sme_state, (char __user const *)user->za + ZA_SIG_REGS_OFFSET, ZA_SIG_REGS_SIZE(vq)); @@ -447,11 +477,83 @@ static int restore_za_context(struct user_ctxs *user) return 0; } + +static int preserve_zt_context(struct zt_context __user *ctx) +{ + int err = 0; + u16 reserved[ARRAY_SIZE(ctx->__reserved)]; + + if (WARN_ON(!thread_za_enabled(¤t->thread))) + return -EINVAL; + + memset(reserved, 0, sizeof(reserved)); + + __put_user_error(ZT_MAGIC, &ctx->head.magic, err); + __put_user_error(round_up(ZT_SIG_CONTEXT_SIZE(1), 16), + &ctx->head.size, err); + __put_user_error(1, &ctx->nregs, err); + BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); + err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); + + /* + * This assumes that the ZT state has already been saved to + * the task struct by calling the function + * fpsimd_signal_preserve_current_state(). + */ + err |= __copy_to_user((char __user *)ctx + ZT_SIG_REGS_OFFSET, + thread_zt_state(¤t->thread), + ZT_SIG_REGS_SIZE(1)); + + return err ? -EFAULT : 0; +} + +static int restore_zt_context(struct user_ctxs *user) +{ + int err; + struct zt_context zt; + + /* ZA must be restored first for this check to be valid */ + if (!thread_za_enabled(¤t->thread)) + return -EINVAL; + + if (__copy_from_user(&zt, user->zt, sizeof(zt))) + return -EFAULT; + + if (zt.nregs != 1) + return -EINVAL; + + if (zt.head.size != ZT_SIG_CONTEXT_SIZE(zt.nregs)) + return -EINVAL; + + /* + * Careful: we are about __copy_from_user() directly into + * thread.zt_state with preemption enabled, so protection is + * needed to prevent a racing context switch from writing stale + * registers back over the new data. + */ + + fpsimd_flush_task_state(current); + /* From now, fpsimd_thread_switch() won't touch ZT in thread state */ + + err = __copy_from_user(thread_zt_state(¤t->thread), + (char __user const *)user->zt + + ZT_SIG_REGS_OFFSET, + ZT_SIG_REGS_SIZE(1)); + if (err) + return -EFAULT; + + return 0; +} + #else /* ! CONFIG_ARM64_SME */ /* Turn any non-optimised out attempts to use these into a link error: */ +extern int preserve_tpidr2_context(void __user *ctx); +extern int restore_tpidr2_context(struct user_ctxs *user); extern int preserve_za_context(void __user *ctx); extern int restore_za_context(struct user_ctxs *user); +extern int preserve_zt_context(void __user *ctx); +extern int restore_zt_context(struct user_ctxs *user); #endif /* ! CONFIG_ARM64_SME */ @@ -468,7 +570,9 @@ static int parse_user_sigframe(struct user_ctxs *user, user->fpsimd = NULL; user->sve = NULL; + user->tpidr2 = NULL; user->za = NULL; + user->zt = NULL; if (!IS_ALIGNED((unsigned long)base, 16)) goto invalid; @@ -534,6 +638,19 @@ static int parse_user_sigframe(struct user_ctxs *user, user->sve = (struct sve_context __user *)head; break; + case TPIDR2_MAGIC: + if (!system_supports_sme()) + goto invalid; + + if (user->tpidr2) + goto invalid; + + if (size != sizeof(*user->tpidr2)) + goto invalid; + + user->tpidr2 = (struct tpidr2_context __user *)head; + break; + case ZA_MAGIC: if (!system_supports_sme()) goto invalid; @@ -547,6 +664,19 @@ static int parse_user_sigframe(struct user_ctxs *user, user->za = (struct za_context __user *)head; break; + case ZT_MAGIC: + if (!system_supports_sme2()) + goto invalid; + + if (user->zt) + goto invalid; + + if (size < sizeof(*user->zt)) + goto invalid; + + user->zt = (struct zt_context __user *)head; + break; + case EXTRA_MAGIC: if (have_extra_context) goto invalid; @@ -666,9 +796,15 @@ static int restore_sigframe(struct pt_regs *regs, err = restore_fpsimd_context(user.fpsimd); } + if (err == 0 && system_supports_sme() && user.tpidr2) + err = restore_tpidr2_context(&user); + if (err == 0 && system_supports_sme() && user.za) err = restore_za_context(&user); + if (err == 0 && system_supports_sme2() && user.zt) + err = restore_zt_context(&user); + return err; } @@ -760,6 +896,11 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, else vl = task_get_sme_vl(current); + err = sigframe_alloc(user, &user->tpidr2_offset, + sizeof(struct tpidr2_context)); + if (err) + return err; + if (thread_za_enabled(¤t->thread)) vq = sve_vq_from_vl(vl); @@ -769,6 +910,15 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, return err; } + if (system_supports_sme2()) { + if (add_all || thread_za_enabled(¤t->thread)) { + err = sigframe_alloc(user, &user->zt_offset, + ZT_SIG_CONTEXT_SIZE(1)); + if (err) + return err; + } + } + return sigframe_alloc_end(user); } @@ -817,6 +967,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, err |= preserve_sve_context(sve_ctx); } + /* TPIDR2 if supported */ + if (system_supports_sme() && err == 0) { + struct tpidr2_context __user *tpidr2_ctx = + apply_user_offset(user, user->tpidr2_offset); + err |= preserve_tpidr2_context(tpidr2_ctx); + } + /* ZA state if present */ if (system_supports_sme() && err == 0 && user->za_offset) { struct za_context __user *za_ctx = @@ -824,6 +981,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, err |= preserve_za_context(za_ctx); } + /* ZT state if present */ + if (system_supports_sme2() && err == 0 && user->zt_offset) { + struct zt_context __user *zt_ctx = + apply_user_offset(user, user->zt_offset); + err |= preserve_zt_context(zt_ctx); + } + if (err == 0 && user->extra_offset) { char __user *sfp = (char __user *)user->sigframe; char __user *userp = diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index a5de47e3df2b..da84cf855c44 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -173,12 +173,8 @@ static inline void fp_user_discard(void) * register state to track, if this changes the KVM code will * need updating. */ - if (system_supports_sme() && test_thread_flag(TIF_SME)) { - u64 svcr = read_sysreg_s(SYS_SVCR); - - if (svcr & SVCR_SM_MASK) - sme_smstop_sm(); - } + if (system_supports_sme()) + sme_smstop_sm(); if (!system_supports_sve()) return; diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 4c0caa589e12..0ccc063daccb 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -162,10 +162,8 @@ static void dump_kernel_instr(const char *lvl, struct pt_regs *regs) if (!bad) p += sprintf(p, i == 0 ? "(%08x) " : "%08x ", val); - else { - p += sprintf(p, "bad PC value"); - break; - } + else + p += sprintf(p, i == 0 ? "(????????) " : "???????? "); } printk("%sCode: %s\n", lvl, str); diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 407415a5163a..1a43df27a204 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -93,6 +93,7 @@ jiffies = jiffies_64; #ifdef CONFIG_HIBERNATION #define HIBERNATE_TEXT \ + ALIGN_FUNCTION(); \ __hibernate_exit_text_start = .; \ *(.hibernate_exit.text) \ __hibernate_exit_text_end = .; @@ -102,6 +103,7 @@ jiffies = jiffies_64; #ifdef CONFIG_KEXEC_CORE #define KEXEC_TEXT \ + ALIGN_FUNCTION(); \ __relocate_new_kernel_start = .; \ *(.kexec_relocate.text) \ __relocate_new_kernel_end = .; @@ -355,6 +357,8 @@ ASSERT(__idmap_text_end - (__idmap_text_start & ~(SZ_4K - 1)) <= SZ_4K, #ifdef CONFIG_HIBERNATION ASSERT(__hibernate_exit_text_end - __hibernate_exit_text_start <= SZ_4K, "Hibernate exit text is bigger than 4 KiB") +ASSERT(__hibernate_exit_text_start == swsusp_arch_suspend_exit, + "Hibernate exit text does not start with swsusp_arch_suspend_exit") #endif #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 ASSERT((__entry_tramp_text_end - __entry_tramp_text_start) <= 3*PAGE_SIZE, @@ -381,4 +385,6 @@ ASSERT(swapper_pg_dir - tramp_pg_dir == TRAMP_SWAPPER_OFFSET, ASSERT(__relocate_new_kernel_end - __relocate_new_kernel_start <= SZ_4K, "kexec relocation code is bigger than 4 KiB") ASSERT(KEXEC_CONTROL_PAGE_SIZE >= SZ_4K, "KEXEC_CONTROL_PAGE_SIZE is broken") +ASSERT(__relocate_new_kernel_start == arm64_relocate_new_kernel, + "kexec control page does not start with arm64_relocate_new_kernel") #endif diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index fccf9ec01813..55f80fb93925 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -328,7 +328,7 @@ void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu) * we may need to check if the host state needs to be saved. */ if (cpuid_feature_extract_unsigned_field(dfr0, ID_AA64DFR0_EL1_PMSVer_SHIFT) && - !(read_sysreg_s(SYS_PMBIDR_EL1) & BIT(SYS_PMBIDR_EL1_P_SHIFT))) + !(read_sysreg_s(SYS_PMBIDR_EL1) & BIT(PMBIDR_EL1_P_SHIFT))) vcpu_set_flag(vcpu, DEBUG_STATE_SAVE_SPE); /* Check if we have TRBE implemented and available at the host */ diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 02dd7e9ebd39..235775d0c825 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -143,7 +143,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) 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.sme_state = NULL; fp_state.svcr = &vcpu->arch.svcr; fp_state.fp_type = &vcpu->arch.fp_type; diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index 435346ea1504..f3aa7738b477 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -171,7 +171,7 @@ alternative_else dsb sy // Synchronize against in-flight ld/st isb // Prevent an early read of side-effect free ISR mrs x2, isr_el1 - tbnz x2, #8, 2f // ISR_EL1.A + tbnz x2, #ISR_EL1_A_SHIFT, 2f ret nop 2: diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c index e17455773b98..2673bde62fad 100644 --- a/arch/arm64/kvm/hyp/nvhe/debug-sr.c +++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c @@ -27,7 +27,7 @@ static void __debug_save_spe(u64 *pmscr_el1) * Check if the host is actually using it ? */ reg = read_sysreg_s(SYS_PMBLIMITR_EL1); - if (!(reg & BIT(SYS_PMBLIMITR_EL1_E_SHIFT))) + if (!(reg & BIT(PMBLIMITR_EL1_E_SHIFT))) return; /* Yes; save the control register and disable data generation */ diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 14c87e8d69d8..34d5f7c4c64e 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -133,7 +133,7 @@ static phys_addr_t __init early_pgtable_alloc(int shift) return phys; } -static bool pgattr_change_is_safe(u64 old, u64 new) +bool pgattr_change_is_safe(u64 old, u64 new) { /* * The following mapping attributes may be updated in live @@ -142,9 +142,13 @@ static bool pgattr_change_is_safe(u64 old, u64 new) pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE | PTE_NG; /* creating or taking down mappings is always safe */ - if (old == 0 || new == 0) + if (!pte_valid(__pte(old)) || !pte_valid(__pte(new))) return true; + /* A live entry's pfn should not change */ + if (pte_pfn(__pte(old)) != pte_pfn(__pte(new))) + return false; + /* live contiguous mappings may not be manipulated at all */ if ((old | new) & PTE_CONT) return false; diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index a86ee376920a..b98f71120588 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -28,7 +28,9 @@ HAS_GENERIC_AUTH HAS_GENERIC_AUTH_ARCH_QARMA3 HAS_GENERIC_AUTH_ARCH_QARMA5 HAS_GENERIC_AUTH_IMP_DEF -HAS_IRQ_PRIO_MASKING +HAS_GIC_CPUIF_SYSREGS +HAS_GIC_PRIO_MASKING +HAS_GIC_PRIO_RELAXED_SYNC HAS_LDAPR HAS_LSE_ATOMICS HAS_NO_FPSIMD @@ -38,7 +40,6 @@ HAS_RAS_EXTN HAS_RNG HAS_SB HAS_STAGE2_FWB -HAS_SYSREG_GIC_CPUIF HAS_TIDCP1 HAS_TLB_RANGE HAS_VIRT_HOST_EXTN @@ -50,6 +51,7 @@ MTE MTE_ASYMM SME SME_FA64 +SME2 SPECTRE_V2 SPECTRE_V3A SPECTRE_V4 diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 184e58fd5631..ef9995cea1b4 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -689,17 +689,17 @@ EndEnum Enum 11:8 FPDP 0b0000 NI 0b0001 VFPv2 - 0b0001 VFPv3 + 0b0010 VFPv3 EndEnum Enum 7:4 FPSP 0b0000 NI 0b0001 VFPv2 - 0b0001 VFPv3 + 0b0010 VFPv3 EndEnum Enum 3:0 SIMDReg 0b0000 NI 0b0001 IMP_16x64 - 0b0001 IMP_32x64 + 0b0010 IMP_32x64 EndEnum EndSysreg @@ -718,7 +718,7 @@ EndEnum Enum 23:20 SIMDHP 0b0000 NI 0b0001 SIMDHP - 0b0001 SIMDHP_FLOAT + 0b0010 SIMDHP_FLOAT EndEnum Enum 19:16 SIMDSP 0b0000 NI @@ -894,6 +894,7 @@ EndEnum Enum 27:24 SME 0b0000 NI 0b0001 IMP + 0b0010 SME2 EndEnum Res0 23:20 Enum 19:16 MPAM_frac @@ -975,7 +976,9 @@ Enum 63 FA64 EndEnum Res0 62:60 Enum 59:56 SMEver - 0b0000 IMP + 0b0000 SME + 0b0001 SME2 + 0b0010 SME2p1 EndEnum Enum 55:52 I16I64 0b0000 NI @@ -986,7 +989,19 @@ Enum 48 F64F64 0b0 NI 0b1 IMP EndEnum -Res0 47:40 +Enum 47:44 I16I32 + 0b0000 NI + 0b0101 IMP +EndEnum +Enum 43 B16B16 + 0b0 NI + 0b1 IMP +EndEnum +Enum 42 F16F16 + 0b0 NI + 0b1 IMP +EndEnum +Res0 41:40 Enum 39:36 I8I32 0b0000 NI 0b1111 IMP @@ -999,7 +1014,10 @@ Enum 34 B16F32 0b0 NI 0b1 IMP EndEnum -Res0 33 +Enum 33 BI32I32 + 0b0 NI + 0b1 IMP +EndEnum Enum 32 F32F32 0b0 NI 0b1 IMP @@ -1599,7 +1617,8 @@ EndSysreg SysregFields SMCR_ELx Res0 63:32 Field 31 FA64 -Res0 30:9 +Field 30 EZT0 +Res0 29:9 Raz 8:4 Field 3:0 LEN EndSysregFields @@ -1618,6 +1637,130 @@ Sysreg FAR_EL1 3 0 6 0 0 Field 63:0 ADDR EndSysreg +Sysreg PMSCR_EL1 3 0 9 9 0 +Res0 63:8 +Field 7:6 PCT +Field 5 TS +Field 4 PA +Field 3 CX +Res0 2 +Field 1 E1SPE +Field 0 E0SPE +EndSysreg + +Sysreg PMSNEVFR_EL1 3 0 9 9 1 +Field 63:0 E +EndSysreg + +Sysreg PMSICR_EL1 3 0 9 9 2 +Field 63:56 ECOUNT +Res0 55:32 +Field 31:0 COUNT +EndSysreg + +Sysreg PMSIRR_EL1 3 0 9 9 3 +Res0 63:32 +Field 31:8 INTERVAL +Res0 7:1 +Field 0 RND +EndSysreg + +Sysreg PMSFCR_EL1 3 0 9 9 4 +Res0 63:19 +Field 18 ST +Field 17 LD +Field 16 B +Res0 15:4 +Field 3 FnE +Field 2 FL +Field 1 FT +Field 0 FE +EndSysreg + +Sysreg PMSEVFR_EL1 3 0 9 9 5 +Field 63:0 E +EndSysreg + +Sysreg PMSLATFR_EL1 3 0 9 9 6 +Res0 63:16 +Field 15:0 MINLAT +EndSysreg + +Sysreg PMSIDR_EL1 3 0 9 9 7 +Res0 63:25 +Field 24 PBT +Field 23:20 FORMAT +Enum 19:16 COUNTSIZE + 0b0010 12_BIT_SAT + 0b0011 16_BIT_SAT +EndEnum +Field 15:12 MAXSIZE +Enum 11:8 INTERVAL + 0b0000 256 + 0b0010 512 + 0b0011 768 + 0b0100 1024 + 0b0101 1536 + 0b0110 2048 + 0b0111 3072 + 0b1000 4096 +EndEnum +Res0 7 +Field 6 FnE +Field 5 ERND +Field 4 LDS +Field 3 ARCHINST +Field 2 FL +Field 1 FT +Field 0 FE +EndSysreg + +Sysreg PMBLIMITR_EL1 3 0 9 10 0 +Field 63:12 LIMIT +Res0 11:6 +Field 5 PMFZ +Res0 4:3 +Enum 2:1 FM + 0b00 FILL + 0b10 DISCARD +EndEnum +Field 0 E +EndSysreg + +Sysreg PMBPTR_EL1 3 0 9 10 1 +Field 63:0 PTR +EndSysreg + +Sysreg PMBSR_EL1 3 0 9 10 3 +Res0 63:32 +Enum 31:26 EC + 0b000000 BUF + 0b100100 FAULT_S1 + 0b100101 FAULT_S2 + 0b011110 FAULT_GPC + 0b011111 IMP_DEF +EndEnum +Res0 25:20 +Field 19 DL +Field 18 EA +Field 17 S +Field 16 COLL +Field 15:0 MSS +EndSysreg + +Sysreg PMBIDR_EL1 3 0 9 10 7 +Res0 63:12 +Enum 11:8 EA + 0b0000 NotDescribed + 0b0001 Ignored + 0b0010 SError +EndEnum +Res0 7:6 +Field 5 F +Field 4 P +Field 3:0 ALIGN +EndSysreg + SysregFields CONTEXTIDR_ELx Res0 63:32 Field 31:0 PROCID @@ -1772,6 +1915,21 @@ Sysreg FAR_EL2 3 4 6 0 0 Field 63:0 ADDR EndSysreg +Sysreg PMSCR_EL2 3 4 9 9 0 +Res0 63:8 +Enum 7:6 PCT + 0b00 VIRT + 0b01 PHYS + 0b11 GUEST +EndEnum +Field 5 TS +Field 4 PA +Field 3 CX +Res0 2 +Field 1 E2SPE +Field 0 E0HSPE +EndSysreg + Sysreg CONTEXTIDR_EL2 3 4 13 0 1 Fields CONTEXTIDR_ELx EndSysreg @@ -1842,3 +2000,18 @@ Field 23:16 LD Res0 15:8 Field 7:0 LR EndSysreg + +Sysreg ISR_EL1 3 0 12 1 0 +Res0 63:11 +Field 10 IS +Field 9 FS +Field 8 A +Field 7 I +Field 6 F +Res0 5:0 +EndSysreg + +Sysreg ICC_NMIAR1_EL1 3 0 12 9 5 +Res0 63:24 +Field 23:0 INTID +EndSysreg |