diff options
99 files changed, 1726 insertions, 657 deletions
diff --git a/Documentation/arm64/booting.rst b/Documentation/arm64/booting.rst index f8d0a7288c73..ffeccdd6bdac 100644 --- a/Documentation/arm64/booting.rst +++ b/Documentation/arm64/booting.rst @@ -223,7 +223,7 @@ Before jumping into the kernel, the following conditions must be met: For systems with a GICv3 interrupt controller to be used in v3 mode: - If EL3 is present: - - ICC_SRE_EL3.Enable (bit 3) must be initialiased to 0b1. + - ICC_SRE_EL3.Enable (bit 3) must be initialised to 0b1. - ICC_SRE_EL3.SRE (bit 0) must be initialised to 0b1. - ICC_CTLR_EL3.PMHE (bit 6) must be set to the same value across all CPUs the kernel is executing on, and must stay constant diff --git a/Documentation/arm64/elf_hwcaps.rst b/Documentation/arm64/elf_hwcaps.rst index 8a9d4bf7daf4..83e57e4d38e2 100644 --- a/Documentation/arm64/elf_hwcaps.rst +++ b/Documentation/arm64/elf_hwcaps.rst @@ -14,7 +14,7 @@ Some hardware or software features are only available on some CPU implementations, and/or with certain kernel configurations, but have no architected discovery mechanism available to userspace code at EL0. The kernel exposes the presence of these features to userspace through a set -of flags called hwcaps, exposed in the auxilliary vector. +of flags called hwcaps, exposed in the auxiliary vector. Userspace software can test for features by acquiring the AT_HWCAP or AT_HWCAP2 entry of the auxiliary vector, and testing whether the relevant diff --git a/Documentation/arm64/sme.rst b/Documentation/arm64/sme.rst index 68d1efb7d171..1c43ea12eb4f 100644 --- a/Documentation/arm64/sme.rst +++ b/Documentation/arm64/sme.rst @@ -117,6 +117,9 @@ be zeroed. * Signal handlers are invoked with streaming mode and ZA disabled. +* A new signal frame record TPIDR2_MAGIC is added formatted as a struct + tpidr2_context to allow access to TPIDR2_EL0 from signal handlers. + * A new signal frame record za_context encodes the ZA register contents on signal delivery. [1] diff --git a/Documentation/arm64/sve.rst b/Documentation/arm64/sve.rst index c7a356bf4e8f..1b90a30382ac 100644 --- a/Documentation/arm64/sve.rst +++ b/Documentation/arm64/sve.rst @@ -175,7 +175,7 @@ the SVE instruction set architecture. When returning from a signal handler: * If there is no sve_context record in the signal frame, or if the record is - present but contains no register data as desribed in the previous section, + present but contains no register data as described in the previous section, then the SVE registers/bits become non-live and take unspecified values. * If sve_context is present in the signal frame and contains full register @@ -223,7 +223,7 @@ prctl(PR_SVE_SET_VL, unsigned long arg) Defer the requested vector length change until the next execve() performed by this thread. - The effect is equivalent to implicit exceution of the following + The effect is equivalent to implicit execution of the following call immediately after the next execve() (if any) by the thread: prctl(PR_SVE_SET_VL, arg & ~PR_SVE_SET_VL_ONEXEC) diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index f82a819eb0db..311e83038bdb 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -252,5 +252,10 @@ static inline void gic_arch_enable_irqs(void) WARN_ON_ONCE(true); } +static inline bool gic_has_relaxed_pmr_sync(void) +{ + return false; +} + #endif /* !__ASSEMBLY__ */ #endif /* !__ASM_ARCH_GICV3_H */ 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 fc2c739f48f1..6bf013fb110d 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -812,7 +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) @@ -870,7 +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/efi.h b/arch/arm64/include/asm/efi.h index 31d13a6001df..0f0e729b40ef 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -105,6 +105,8 @@ static inline unsigned long efi_get_kimg_min_align(void) #define EFI_ALLOC_ALIGN SZ_64K #define EFI_ALLOC_LIMIT ((1UL << 48) - 1) +extern unsigned long primary_entry_offset(void); + /* * On ARM systems, virtually remapped UEFI runtime services are set up in two * distinct stages: 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/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 475c803ecf42..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> 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/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 1312fb48f18b..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 ***/ @@ -575,6 +496,7 @@ #define SCTLR_ELx_DSSBS (BIT(44)) #define SCTLR_ELx_ATA (BIT(43)) +#define SCTLR_ELx_EE_SHIFT 25 #define SCTLR_ELx_ENIA_SHIFT 31 #define SCTLR_ELx_ITFSB (BIT(37)) @@ -583,7 +505,7 @@ #define SCTLR_ELx_LSMAOE (BIT(29)) #define SCTLR_ELx_nTLSMD (BIT(28)) #define SCTLR_ELx_ENDA (BIT(27)) -#define SCTLR_ELx_EE (BIT(25)) +#define SCTLR_ELx_EE (BIT(SCTLR_ELx_EE_SHIFT)) #define SCTLR_ELx_EIS (BIT(22)) #define SCTLR_ELx_IESB (BIT(21)) #define SCTLR_ELx_TSCXT (BIT(20)) @@ -809,8 +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/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index 46e9072985a5..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 { 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 5bd959bd9a1f..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> @@ -454,8 +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), @@ -539,12 +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, }; @@ -572,7 +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, }; @@ -1805,7 +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; @@ -2049,14 +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 @@ -2152,7 +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, @@ -2544,14 +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 @@ -2799,7 +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), @@ -2894,11 +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 85e54417d141..eb4378c23b3c 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -152,6 +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) @@ -161,6 +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-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 cec8b43e7888..c11cb445ffca 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1335,7 +1335,6 @@ u64 read_smcr_features(void) unsigned int vq_max; sme_kernel_enable(NULL); - sme_smstart_sm(); /* * Set the maximum possible VL. @@ -1345,11 +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; } 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 952e17bd1c0b..212d93aca5e6 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -70,13 +70,14 @@ __EFI_PE_HEADER - __INIT + .section ".idmap.text","awx" /* * The following callee saved general purpose registers are used on the * primary lowlevel boot path: * * Register Scope Purpose + * x19 primary_entry() .. start_kernel() whether we entered with the MMU on * x20 primary_entry() .. __primary_switch() CPU boot mode * x21 primary_entry() .. start_kernel() FDT pointer passed at boot in x0 * x22 create_idmap() .. start_kernel() ID map VA of the DT blob @@ -86,10 +87,22 @@ * x28 create_idmap() callee preserved temp register */ SYM_CODE_START(primary_entry) + bl record_mmu_state bl preserve_boot_args + bl create_idmap + + /* + * If we entered with the MMU and caches on, clean the ID mapped part + * of the primary boot code to the PoC so we can safely execute it with + * the MMU off. + */ + cbz x19, 0f + adrp x0, __idmap_text_start + adr_l x1, __idmap_text_end + bl dcache_clean_poc +0: mov x0, x19 bl init_kernel_el // w0=cpu_boot_mode mov x20, x0 - bl create_idmap /* * The following calls CPU setup code, see arch/arm64/mm/proc.S for @@ -109,6 +122,40 @@ SYM_CODE_START(primary_entry) b __primary_switch SYM_CODE_END(primary_entry) + __INIT +SYM_CODE_START_LOCAL(record_mmu_state) + mrs x19, CurrentEL + cmp x19, #CurrentEL_EL2 + mrs x19, sctlr_el1 + b.ne 0f + mrs x19, sctlr_el2 +0: +CPU_LE( tbnz x19, #SCTLR_ELx_EE_SHIFT, 1f ) +CPU_BE( tbz x19, #SCTLR_ELx_EE_SHIFT, 1f ) + tst x19, #SCTLR_ELx_C // Z := (C == 0) + and x19, x19, #SCTLR_ELx_M // isolate M bit + csel x19, xzr, x19, eq // clear x19 if Z + ret + + /* + * Set the correct endianness early so all memory accesses issued + * before init_kernel_el() occur in the correct byte order. Note that + * this means the MMU must be disabled, or the active ID map will end + * up getting interpreted with the wrong byte order. + */ +1: eor x19, x19, #SCTLR_ELx_EE + bic x19, x19, #SCTLR_ELx_M + b.ne 2f + pre_disable_mmu_workaround + msr sctlr_el2, x19 + b 3f + pre_disable_mmu_workaround +2: msr sctlr_el1, x19 +3: isb + mov x19, xzr + ret +SYM_CODE_END(record_mmu_state) + /* * Preserve the arguments passed by the bootloader in x0 .. x3 */ @@ -119,11 +166,14 @@ SYM_CODE_START_LOCAL(preserve_boot_args) stp x21, x1, [x0] // x0 .. x3 at kernel entry stp x2, x3, [x0, #16] + cbnz x19, 0f // skip cache invalidation if MMU is on dmb sy // needed before dc ivac with // MMU off add x1, x0, #0x20 // 4 x 8 bytes b dcache_inval_poc // tail call +0: str_l x19, mmu_enabled_at_boot, x0 + ret SYM_CODE_END(preserve_boot_args) SYM_FUNC_START_LOCAL(clear_page_tables) @@ -360,12 +410,13 @@ SYM_FUNC_START_LOCAL(create_idmap) * accesses (MMU disabled), invalidate those tables again to * remove any speculatively loaded cache lines. */ + cbnz x19, 0f // skip cache invalidation if MMU is on dmb sy adrp x0, init_idmap_pg_dir adrp x1, init_idmap_pg_end bl dcache_inval_poc - ret x28 +0: ret x28 SYM_FUNC_END(create_idmap) SYM_FUNC_START_LOCAL(create_kernel_mapping) @@ -404,7 +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] @@ -489,14 +540,17 @@ SYM_FUNC_END(__primary_switched) * Returns either BOOT_CPU_MODE_EL1 or BOOT_CPU_MODE_EL2 in x0 if * booted in EL1 or EL2 respectively, with the top 32 bits containing * potential context flags. These flags are *not* stored in __boot_cpu_mode. + * + * x0: whether we are being called from the primary boot path with the MMU on */ SYM_FUNC_START(init_kernel_el) - mrs x0, CurrentEL - cmp x0, #CurrentEL_EL2 + mrs x1, CurrentEL + cmp x1, #CurrentEL_EL2 b.eq init_el2 SYM_INNER_LABEL(init_el1, SYM_L_LOCAL) mov_q x0, INIT_SCTLR_EL1_MMU_OFF + pre_disable_mmu_workaround msr sctlr_el1, x0 isb mov_q x0, INIT_PSTATE_EL1 @@ -506,6 +560,14 @@ SYM_INNER_LABEL(init_el1, SYM_L_LOCAL) eret SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) + msr elr_el2, lr + + // clean all HYP code to the PoC if we booted at EL2 with the MMU on + cbz x0, 0f + adrp x0, __hyp_idmap_text_start + adr_l x1, __hyp_text_end + bl dcache_clean_poc +0: mov_q x0, HCR_HOST_NVHE_FLAGS msr hcr_el2, x0 isb @@ -529,38 +591,27 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL) cbz x0, 1f /* Set a sane SCTLR_EL1, the VHE way */ + pre_disable_mmu_workaround msr_s SYS_SCTLR_EL12, x1 mov x2, #BOOT_CPU_FLAG_E2H b 2f 1: + pre_disable_mmu_workaround msr sctlr_el1, x1 mov x2, xzr 2: - msr elr_el2, lr mov w0, #BOOT_CPU_MODE_EL2 orr x0, x0, x2 eret SYM_FUNC_END(init_kernel_el) -/* - * Sets the __boot_cpu_mode flag depending on the CPU boot mode passed - * in w0. See arch/arm64/include/asm/virt.h for more info. - */ -SYM_FUNC_START_LOCAL(set_cpu_boot_mode_flag) - adr_l x1, __boot_cpu_mode - cmp w0, #BOOT_CPU_MODE_EL2 - b.ne 1f - add x1, x1, #4 -1: str w0, [x1] // Save CPU boot mode - ret -SYM_FUNC_END(set_cpu_boot_mode_flag) - /* * This provides a "holding pen" for platforms to hold all secondary * cores are held until we're ready for them to initialise. */ SYM_FUNC_START(secondary_holding_pen) + mov x0, xzr bl init_kernel_el // w0=cpu_boot_mode mrs x2, mpidr_el1 mov_q x1, MPIDR_HWID_BITMASK @@ -578,6 +629,7 @@ SYM_FUNC_END(secondary_holding_pen) * be used where CPUs are brought online dynamically by the kernel. */ SYM_FUNC_START(secondary_entry) + mov x0, xzr bl init_kernel_el // w0=cpu_boot_mode b secondary_startup SYM_FUNC_END(secondary_entry) @@ -587,7 +639,6 @@ SYM_FUNC_START_LOCAL(secondary_startup) * Common entry point for secondary CPUs. */ mov x20, x0 // preserve boot mode - bl finalise_el2 bl __cpu_secondary_check52bitva #if VA_BITS > 48 ldr_l x0, vabits_actual @@ -600,9 +651,14 @@ SYM_FUNC_START_LOCAL(secondary_startup) br x8 SYM_FUNC_END(secondary_startup) + .text SYM_FUNC_START_LOCAL(__secondary_switched) mov x0, x20 bl set_cpu_boot_mode_flag + + mov x0, x20 + bl finalise_el2 + str_l xzr, __early_cpu_boot_status, x3 adr_l x5, vectors msr vbar_el1, x5 @@ -629,6 +685,19 @@ SYM_FUNC_START_LOCAL(__secondary_too_slow) SYM_FUNC_END(__secondary_too_slow) /* + * Sets the __boot_cpu_mode flag depending on the CPU boot mode passed + * in w0. See arch/arm64/include/asm/virt.h for more info. + */ +SYM_FUNC_START_LOCAL(set_cpu_boot_mode_flag) + adr_l x1, __boot_cpu_mode + cmp w0, #BOOT_CPU_MODE_EL2 + b.ne 1f + add x1, x1, #4 +1: str w0, [x1] // Save CPU boot mode + ret +SYM_FUNC_END(set_cpu_boot_mode_flag) + +/* * The booting CPU updates the failed status @__early_cpu_boot_status, * with MMU turned off. * @@ -659,6 +728,7 @@ SYM_FUNC_END(__secondary_too_slow) * Checks if the selected granule size is supported by the CPU. * If it isn't, park the CPU */ + .section ".idmap.text","awx" SYM_FUNC_START(__enable_mmu) mrs x3, ID_AA64MMFR0_EL1 ubfx x3, x3, #ID_AA64MMFR0_EL1_TGRAN_SHIFT, 4 diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index d0e9bb5c91fc..8309197c0ebd 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -10,7 +10,7 @@ #error This file should only be included in vmlinux.lds.S #endif -PROVIDE(__efistub_primary_entry_offset = primary_entry - _text); +PROVIDE(__efistub_primary_entry = primary_entry); /* * The EFI stub has its own symbol namespace prefixed by __efistub_, to @@ -21,10 +21,11 @@ PROVIDE(__efistub_primary_entry_offset = primary_entry - _text); * linked at. The routines below are all implemented in assembler in a * position independent manner */ -PROVIDE(__efistub_dcache_clean_poc = __pi_dcache_clean_poc); +PROVIDE(__efistub_caches_clean_inval_pou = __pi_caches_clean_inval_pou); PROVIDE(__efistub__text = _text); PROVIDE(__efistub__end = _end); +PROVIDE(__efistub___inittext_end = __inittext_end); PROVIDE(__efistub__edata = _edata); PROVIDE(__efistub_screen_info = screen_info); PROVIDE(__efistub__ctype = _ctype); @@ -67,9 +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/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index f35d059a9a36..70b91a8c6bb3 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -387,10 +387,6 @@ int __init arch_populate_kprobe_blacklist(void) (unsigned long)__irqentry_text_end); if (ret) return ret; - ret = kprobe_add_area_blacklist((unsigned long)__idmap_text_start, - (unsigned long)__idmap_text_end); - if (ret) - return ret; ret = kprobe_add_area_blacklist((unsigned long)__hyp_text_start, (unsigned long)__hyp_text_end); if (ret || is_kernel_in_hyp_mode()) diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 38be7ca202af..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; diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 12cfe9d0d3fa..b8ec7b3ac9cb 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -58,6 +58,7 @@ static int num_standard_resources; static struct resource *standard_resources; phys_addr_t __fdt_pointer __initdata; +u64 mmu_enabled_at_boot __initdata; /* * Standard memory resources @@ -332,8 +333,12 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) xen_early_init(); efi_init(); - if (!efi_enabled(EFI_BOOT) && ((u64)_text % MIN_KIMG_ALIGN) != 0) - pr_warn(FW_BUG "Kernel image misaligned at boot, please fix your bootloader!"); + if (!efi_enabled(EFI_BOOT)) { + if ((u64)_text % MIN_KIMG_ALIGN) + pr_warn(FW_BUG "Kernel image misaligned at boot, please fix your bootloader!"); + WARN_TAINT(mmu_enabled_at_boot, TAINT_FIRMWARE_WORKAROUND, + FW_BUG "Booted with MMU enabled!"); + } arm64_memblock_init(); @@ -442,3 +447,11 @@ static int __init register_arm64_panic_block(void) return 0; } device_initcall(register_arm64_panic_block); + +static int __init check_mmu_enabled_at_boot(void) +{ + if (!efi_enabled(EFI_BOOT) && mmu_enabled_at_boot) + panic("Non-EFI boot detected with MMU and caches enabled"); + return 0; +} +device_initcall_sync(check_mmu_enabled_at_boot); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 1c5e557a3617..ed692284f199 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -56,6 +56,7 @@ 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; @@ -221,6 +222,7 @@ 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; }; @@ -363,6 +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; @@ -520,6 +548,8 @@ static int restore_zt_context(struct user_ctxs *user) #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); @@ -540,6 +570,7 @@ static int parse_user_sigframe(struct user_ctxs *user, user->fpsimd = NULL; user->sve = NULL; + user->tpidr2 = NULL; user->za = NULL; user->zt = NULL; @@ -607,6 +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; @@ -752,6 +796,9 @@ 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); @@ -849,6 +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); @@ -915,6 +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 = diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index 97c9de57725d..2ae7cff1953a 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -99,8 +99,9 @@ SYM_FUNC_END(__cpu_suspend_enter) .pushsection ".idmap.text", "awx" SYM_CODE_START(cpu_resume) + mov x0, xzr bl init_kernel_el - bl finalise_el2 + mov x19, x0 // preserve boot mode #if VA_BITS > 48 ldr_l x0, vabits_actual #endif @@ -116,6 +117,9 @@ SYM_CODE_END(cpu_resume) .popsection SYM_FUNC_START(_cpu_resume) + mov x0, x19 + bl finalise_el2 + mrs x1, mpidr_el1 adr_l x8, mpidr_hash // x8 = struct mpidr_hash virt address 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 4c13dafc98b8..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 = .; @@ -179,7 +181,6 @@ SECTIONS LOCK_TEXT KPROBES_TEXT HYPERVISOR_TEXT - IDMAP_TEXT *(.gnu.warning) . = ALIGN(16); *(.got) /* Global offset table */ @@ -206,6 +207,7 @@ SECTIONS TRAMP_TEXT HIBERNATE_TEXT KEXEC_TEXT + IDMAP_TEXT . = ALIGN(PAGE_SIZE); } @@ -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/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/cache.S b/arch/arm64/mm/cache.S index 081058d4e436..503567c864fd 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -56,6 +56,7 @@ SYM_FUNC_START(caches_clean_inval_pou) caches_clean_inval_pou_macro ret SYM_FUNC_END(caches_clean_inval_pou) +SYM_FUNC_ALIAS(__pi_caches_clean_inval_pou, caches_clean_inval_pou) /* * caches_clean_inval_user_pou(start,end) 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/mm/proc.S b/arch/arm64/mm/proc.S index 066fa60b93d2..91410f488090 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -110,7 +110,6 @@ SYM_FUNC_END(cpu_do_suspend) * * x0: Address of context pointer */ - .pushsection ".idmap.text", "awx" SYM_FUNC_START(cpu_do_resume) ldp x2, x3, [x0] ldp x4, x5, [x0, #16] @@ -166,7 +165,6 @@ alternative_else_nop_endif isb ret SYM_FUNC_END(cpu_do_resume) - .popsection #endif .pushsection ".idmap.text", "awx" diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 1222b0ed63a2..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 diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 13c87d8a42f1..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 @@ -1637,6 +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 @@ -1791,6 +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 @@ -1861,3 +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 diff --git a/drivers/acpi/acpica/Makefile b/drivers/acpi/acpica/Makefile index 9e0d95d76fff..30f3fc13c29d 100644 --- a/drivers/acpi/acpica/Makefile +++ b/drivers/acpi/acpica/Makefile @@ -3,7 +3,7 @@ # Makefile for ACPICA Core interpreter # -ccflags-y := -Os -D_LINUX -DBUILDING_ACPICA +ccflags-y := -D_LINUX -DBUILDING_ACPICA ccflags-$(CONFIG_ACPI_DEBUG) += -DACPI_DEBUG_OUTPUT # use acpi.o to put all files here into acpi.o modparam namespace diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile index be8b8c6e8b40..80d85a5169fb 100644 --- a/drivers/firmware/efi/libstub/Makefile +++ b/drivers/firmware/efi/libstub/Makefile @@ -87,7 +87,7 @@ lib-$(CONFIG_EFI_GENERIC_STUB) += efi-stub.o string.o intrinsics.o systable.o \ screen_info.o efi-stub-entry.o lib-$(CONFIG_ARM) += arm32-stub.o -lib-$(CONFIG_ARM64) += arm64.o arm64-stub.o arm64-entry.o smbios.o +lib-$(CONFIG_ARM64) += arm64.o arm64-stub.o smbios.o lib-$(CONFIG_X86) += x86-stub.o lib-$(CONFIG_RISCV) += riscv.o riscv-stub.o lib-$(CONFIG_LOONGARCH) += loongarch.o loongarch-stub.o @@ -141,7 +141,7 @@ STUBCOPY_RELOC-$(CONFIG_ARM) := R_ARM_ABS # STUBCOPY_FLAGS-$(CONFIG_ARM64) += --prefix-alloc-sections=.init \ --prefix-symbols=__efistub_ -STUBCOPY_RELOC-$(CONFIG_ARM64) := R_AARCH64_ABS64 +STUBCOPY_RELOC-$(CONFIG_ARM64) := R_AARCH64_ABS # For RISC-V, we don't need anything special other than arm64. Keep all the # symbols in .init section and make sure that no absolute symbols references diff --git a/drivers/firmware/efi/libstub/arm64-entry.S b/drivers/firmware/efi/libstub/arm64-entry.S deleted file mode 100644 index b5c17e89a4fc..000000000000 --- a/drivers/firmware/efi/libstub/arm64-entry.S +++ /dev/null @@ -1,67 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * EFI entry point. - * - * Copyright (C) 2013, 2014 Red Hat, Inc. - * Author: Mark Salter <msalter@redhat.com> - */ -#include <linux/linkage.h> -#include <asm/assembler.h> - - /* - * The entrypoint of a arm64 bare metal image is at offset #0 of the - * image, so this is a reasonable default for primary_entry_offset. - * Only when the EFI stub is integrated into the core kernel, it is not - * guaranteed that the PE/COFF header has been copied to memory too, so - * in this case, primary_entry_offset should be overridden by the - * linker and point to primary_entry() directly. - */ - .weak primary_entry_offset - -SYM_CODE_START(efi_enter_kernel) - /* - * efi_pe_entry() will have copied the kernel image if necessary and we - * end up here with device tree address in x1 and the kernel entry - * point stored in x0. Save those values in registers which are - * callee preserved. - */ - ldr w2, =primary_entry_offset - add x19, x0, x2 // relocated Image entrypoint - - mov x0, x1 // DTB address - mov x1, xzr - mov x2, xzr - mov x3, xzr - - /* - * Clean the remainder of this routine to the PoC - * so that we can safely disable the MMU and caches. - */ - adr x4, 1f - dc civac, x4 - dsb sy - - /* Turn off Dcache and MMU */ - mrs x4, CurrentEL - cmp x4, #CurrentEL_EL2 - mrs x4, sctlr_el1 - b.ne 0f - mrs x4, sctlr_el2 -0: bic x4, x4, #SCTLR_ELx_M - bic x4, x4, #SCTLR_ELx_C - b.eq 1f - b 2f - - .balign 32 -1: pre_disable_mmu_workaround - msr sctlr_el2, x4 - isb - br x19 // jump to kernel entrypoint - -2: pre_disable_mmu_workaround - msr sctlr_el1, x4 - isb - br x19 // jump to kernel entrypoint - - .org 1b + 32 -SYM_CODE_END(efi_enter_kernel) diff --git a/drivers/firmware/efi/libstub/arm64-stub.c b/drivers/firmware/efi/libstub/arm64-stub.c index 7327b98d8e3f..d4a6b12a8741 100644 --- a/drivers/firmware/efi/libstub/arm64-stub.c +++ b/drivers/firmware/efi/libstub/arm64-stub.c @@ -58,7 +58,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, efi_handle_t image_handle) { efi_status_t status; - unsigned long kernel_size, kernel_memsize = 0; + unsigned long kernel_size, kernel_codesize, kernel_memsize; u32 phys_seed = 0; u64 min_kimg_align = efi_get_kimg_min_align(); @@ -93,6 +93,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, SEGMENT_ALIGN >> 10); kernel_size = _edata - _text; + kernel_codesize = __inittext_end - _text; kernel_memsize = kernel_size + (_end - _edata); *reserve_size = kernel_memsize; @@ -121,7 +122,7 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, */ *image_addr = (u64)_text; *reserve_size = 0; - goto clean_image_to_poc; + return EFI_SUCCESS; } status = efi_allocate_pages_aligned(*reserve_size, reserve_addr, @@ -137,14 +138,21 @@ efi_status_t handle_kernel_image(unsigned long *image_addr, *image_addr = *reserve_addr; memcpy((void *)*image_addr, _text, kernel_size); + caches_clean_inval_pou(*image_addr, *image_addr + kernel_codesize); -clean_image_to_poc: + return EFI_SUCCESS; +} + +asmlinkage void primary_entry(void); + +unsigned long primary_entry_offset(void) +{ /* - * Clean the copied Image to the PoC, and ensure it is not shadowed by - * stale icache entries from before relocation. + * When built as part of the kernel, the EFI stub cannot branch to the + * kernel proper via the image header, as the PE/COFF header is + * strictly not part of the in-memory presentation of the image, only + * of the file representation. So instead, we need to jump to the + * actual entrypoint in the .text region of the image. */ - dcache_clean_poc(*image_addr, *image_addr + kernel_size); - asm("ic ialluis"); - - return EFI_SUCCESS; + return (char *)primary_entry - _text; } diff --git a/drivers/firmware/efi/libstub/arm64.c b/drivers/firmware/efi/libstub/arm64.c index ff2d18c42ee7..f5da4fbccd86 100644 --- a/drivers/firmware/efi/libstub/arm64.c +++ b/drivers/firmware/efi/libstub/arm64.c @@ -56,6 +56,12 @@ efi_status_t check_platform_features(void) return EFI_SUCCESS; } +#ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE +#define DCTYPE "civac" +#else +#define DCTYPE "cvau" +#endif + void efi_cache_sync_image(unsigned long image_base, unsigned long alloc_size, unsigned long code_size) @@ -64,13 +70,38 @@ void efi_cache_sync_image(unsigned long image_base, u64 lsize = 4 << cpuid_feature_extract_unsigned_field(ctr, CTR_EL0_DminLine_SHIFT); - do { - asm("dc civac, %0" :: "r"(image_base)); - image_base += lsize; - alloc_size -= lsize; - } while (alloc_size >= lsize); + /* only perform the cache maintenance if needed for I/D coherency */ + if (!(ctr & BIT(CTR_EL0_IDC_SHIFT))) { + do { + asm("dc " DCTYPE ", %0" :: "r"(image_base)); + image_base += lsize; + code_size -= lsize; + } while (code_size >= lsize); + } asm("ic ialluis"); dsb(ish); isb(); } + +unsigned long __weak primary_entry_offset(void) +{ + /* + * By default, we can invoke the kernel via the branch instruction in + * the image header, so offset #0. This will be overridden by the EFI + * stub build that is linked into the core kernel, as in that case, the + * image header may not have been loaded into memory, or may be mapped + * with non-executable permissions. + */ + return 0; +} + +void __noreturn efi_enter_kernel(unsigned long entrypoint, + unsigned long fdt_addr, + unsigned long fdt_size) +{ + void (* __noreturn enter_kernel)(u64, u64, u64, u64); + + enter_kernel = (void *)entrypoint + primary_entry_offset(); + enter_kernel(fdt_addr, 0, 0, 0); +} diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 997104d4338e..3779836737c8 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -89,15 +89,6 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key); */ static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis); -/* - * Global static key controlling whether an update to PMR allowing more - * interrupts requires to be propagated to the redistributor (DSB SY). - * And this needs to be exported for modules to be able to enable - * interrupts... - */ -DEFINE_STATIC_KEY_FALSE(gic_pmr_sync); -EXPORT_SYMBOL(gic_pmr_sync); - DEFINE_STATIC_KEY_FALSE(gic_nonsecure_priorities); EXPORT_SYMBOL(gic_nonsecure_priorities); @@ -1768,16 +1759,8 @@ static void gic_enable_nmi_support(void) for (i = 0; i < gic_data.ppi_nr; i++) refcount_set(&ppi_nmi_refs[i], 0); - /* - * 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). - */ - if (gic_read_ctlr() & ICC_CTLR_EL1_PMHE_MASK) - static_branch_enable(&gic_pmr_sync); - pr_info("Pseudo-NMIs enabled using %s ICC_PMR_EL1 synchronisation\n", - static_branch_unlikely(&gic_pmr_sync) ? "forced" : "relaxed"); + gic_has_relaxed_pmr_sync() ? "relaxed" : "forced"); /* * How priority values are used by the GIC depends on two things: diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c index 210bc2f4d555..6ae697a3800d 100644 --- a/drivers/irqchip/irq-gic.c +++ b/drivers/irqchip/irq-gic.c @@ -54,7 +54,7 @@ static void gic_check_cpu_features(void) { - WARN_TAINT_ONCE(this_cpu_has_cap(ARM64_HAS_SYSREG_GIC_CPUIF), + WARN_TAINT_ONCE(this_cpu_has_cap(ARM64_HAS_GIC_CPUIF_SYSREGS), TAINT_CPU_OUT_OF_SPEC, "GICv3 system registers enabled, broken firmware!\n"); } diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c index b80a9b74662b..e220714954b0 100644 --- a/drivers/perf/arm-cmn.c +++ b/drivers/perf/arm-cmn.c @@ -1865,6 +1865,7 @@ static void arm_cmn_init_dtm(struct arm_cmn_dtm *dtm, struct arm_cmn_node *xp, i dtm->base = xp->pmu_base + CMN_DTM_OFFSET(idx); dtm->pmu_config_low = CMN_DTM_PMU_CONFIG_PMU_EN; + writeq_relaxed(dtm->pmu_config_low, dtm->base + CMN_DTM_PMU_CONFIG); for (i = 0; i < 4; i++) { dtm->wp_event[i] = -1; writeq_relaxed(0, dtm->base + CMN_DTM_WPn_MASK(i)); diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c index 00e3a637f7b6..b9ba4c4fe5a2 100644 --- a/drivers/perf/arm_spe_pmu.c +++ b/drivers/perf/arm_spe_pmu.c @@ -12,6 +12,7 @@ #define DRVNAME PMUNAME "_pmu" #define pr_fmt(fmt) DRVNAME ": " fmt +#include <linux/bitfield.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/capability.h> @@ -84,6 +85,7 @@ struct arm_spe_pmu { #define SPE_PMU_FEAT_ARCH_INST (1UL << 3) #define SPE_PMU_FEAT_LDS (1UL << 4) #define SPE_PMU_FEAT_ERND (1UL << 5) +#define SPE_PMU_FEAT_INV_FILT_EVT (1UL << 6) #define SPE_PMU_FEAT_DEV_PROBED (1UL << 63) u64 features; @@ -201,6 +203,10 @@ static const struct attribute_group arm_spe_pmu_cap_group = { #define ATTR_CFG_FLD_min_latency_LO 0 #define ATTR_CFG_FLD_min_latency_HI 11 +#define ATTR_CFG_FLD_inv_event_filter_CFG config3 /* PMSNEVFR_EL1 */ +#define ATTR_CFG_FLD_inv_event_filter_LO 0 +#define ATTR_CFG_FLD_inv_event_filter_HI 63 + /* Why does everything I do descend into this? */ #define __GEN_PMU_FORMAT_ATTR(cfg, lo, hi) \ (lo) == (hi) ? #cfg ":" #lo "\n" : #cfg ":" #lo "-" #hi @@ -231,6 +237,7 @@ GEN_PMU_FORMAT_ATTR(branch_filter); GEN_PMU_FORMAT_ATTR(load_filter); GEN_PMU_FORMAT_ATTR(store_filter); GEN_PMU_FORMAT_ATTR(event_filter); +GEN_PMU_FORMAT_ATTR(inv_event_filter); GEN_PMU_FORMAT_ATTR(min_latency); static struct attribute *arm_spe_pmu_formats_attr[] = { @@ -242,12 +249,27 @@ static struct attribute *arm_spe_pmu_formats_attr[] = { &format_attr_load_filter.attr, &format_attr_store_filter.attr, &format_attr_event_filter.attr, + &format_attr_inv_event_filter.attr, &format_attr_min_latency.attr, NULL, }; +static umode_t arm_spe_pmu_format_attr_is_visible(struct kobject *kobj, + struct attribute *attr, + int unused) + { + struct device *dev = kobj_to_dev(kobj); + struct arm_spe_pmu *spe_pmu = dev_get_drvdata(dev); + + if (attr == &format_attr_inv_event_filter.attr && !(spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT)) + return 0; + + return attr->mode; +} + static const struct attribute_group arm_spe_pmu_format_group = { .name = "format", + .is_visible = arm_spe_pmu_format_attr_is_visible, .attrs = arm_spe_pmu_formats_attr, }; @@ -282,18 +304,18 @@ static u64 arm_spe_event_to_pmscr(struct perf_event *event) struct perf_event_attr *attr = &event->attr; u64 reg = 0; - reg |= ATTR_CFG_GET_FLD(attr, ts_enable) << SYS_PMSCR_EL1_TS_SHIFT; - reg |= ATTR_CFG_GET_FLD(attr, pa_enable) << SYS_PMSCR_EL1_PA_SHIFT; - reg |= ATTR_CFG_GET_FLD(attr, pct_enable) << SYS_PMSCR_EL1_PCT_SHIFT; + reg |= FIELD_PREP(PMSCR_EL1_TS, ATTR_CFG_GET_FLD(attr, ts_enable)); + reg |= FIELD_PREP(PMSCR_EL1_PA, ATTR_CFG_GET_FLD(attr, pa_enable)); + reg |= FIELD_PREP(PMSCR_EL1_PCT, ATTR_CFG_GET_FLD(attr, pct_enable)); if (!attr->exclude_user) - reg |= BIT(SYS_PMSCR_EL1_E0SPE_SHIFT); + reg |= PMSCR_EL1_E0SPE; if (!attr->exclude_kernel) - reg |= BIT(SYS_PMSCR_EL1_E1SPE_SHIFT); + reg |= PMSCR_EL1_E1SPE; if (get_spe_event_has_cx(event)) - reg |= BIT(SYS_PMSCR_EL1_CX_SHIFT); + reg |= PMSCR_EL1_CX; return reg; } @@ -302,8 +324,7 @@ static void arm_spe_event_sanitise_period(struct perf_event *event) { struct arm_spe_pmu *spe_pmu = to_spe_pmu(event->pmu); u64 period = event->hw.sample_period; - u64 max_period = SYS_PMSIRR_EL1_INTERVAL_MASK - << SYS_PMSIRR_EL1_INTERVAL_SHIFT; + u64 max_period = PMSIRR_EL1_INTERVAL_MASK; if (period < spe_pmu->min_period) period = spe_pmu->min_period; @@ -322,7 +343,7 @@ static u64 arm_spe_event_to_pmsirr(struct perf_event *event) arm_spe_event_sanitise_period(event); - reg |= ATTR_CFG_GET_FLD(attr, jitter) << SYS_PMSIRR_EL1_RND_SHIFT; + reg |= FIELD_PREP(PMSIRR_EL1_RND, ATTR_CFG_GET_FLD(attr, jitter)); reg |= event->hw.sample_period; return reg; @@ -333,18 +354,21 @@ static u64 arm_spe_event_to_pmsfcr(struct perf_event *event) struct perf_event_attr *attr = &event->attr; u64 reg = 0; - reg |= ATTR_CFG_GET_FLD(attr, load_filter) << SYS_PMSFCR_EL1_LD_SHIFT; - reg |= ATTR_CFG_GET_FLD(attr, store_filter) << SYS_PMSFCR_EL1_ST_SHIFT; - reg |= ATTR_CFG_GET_FLD(attr, branch_filter) << SYS_PMSFCR_EL1_B_SHIFT; + reg |= FIELD_PREP(PMSFCR_EL1_LD, ATTR_CFG_GET_FLD(attr, load_filter)); + reg |= FIELD_PREP(PMSFCR_EL1_ST, ATTR_CFG_GET_FLD(attr, store_filter)); + reg |= FIELD_PREP(PMSFCR_EL1_B, ATTR_CFG_GET_FLD(attr, branch_filter)); if (reg) - reg |= BIT(SYS_PMSFCR_EL1_FT_SHIFT); + reg |= PMSFCR_EL1_FT; if (ATTR_CFG_GET_FLD(attr, event_filter)) - reg |= BIT(SYS_PMSFCR_EL1_FE_SHIFT); + reg |= PMSFCR_EL1_FE; + + if (ATTR_CFG_GET_FLD(attr, inv_event_filter)) + reg |= PMSFCR_EL1_FnE; if (ATTR_CFG_GET_FLD(attr, min_latency)) - reg |= BIT(SYS_PMSFCR_EL1_FL_SHIFT); + reg |= PMSFCR_EL1_FL; return reg; } @@ -355,11 +379,16 @@ static u64 arm_spe_event_to_pmsevfr(struct perf_event *event) return ATTR_CFG_GET_FLD(attr, event_filter); } +static u64 arm_spe_event_to_pmsnevfr(struct perf_event *event) +{ + struct perf_event_attr *attr = &event->attr; + return ATTR_CFG_GET_FLD(attr, inv_event_filter); +} + static u64 arm_spe_event_to_pmslatfr(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; - return ATTR_CFG_GET_FLD(attr, min_latency) - << SYS_PMSLATFR_EL1_MINLAT_SHIFT; + return FIELD_PREP(PMSLATFR_EL1_MINLAT, ATTR_CFG_GET_FLD(attr, min_latency)); } static void arm_spe_pmu_pad_buf(struct perf_output_handle *handle, int len) @@ -511,7 +540,7 @@ static void arm_spe_perf_aux_output_begin(struct perf_output_handle *handle, limit = buf->snapshot ? arm_spe_pmu_next_snapshot_off(handle) : arm_spe_pmu_next_off(handle); if (limit) - limit |= BIT(SYS_PMBLIMITR_EL1_E_SHIFT); + limit |= PMBLIMITR_EL1_E; limit += (u64)buf->base; base = (u64)buf->base + PERF_IDX2OFF(handle->head, buf); @@ -570,28 +599,28 @@ arm_spe_pmu_buf_get_fault_act(struct perf_output_handle *handle) /* Service required? */ pmbsr = read_sysreg_s(SYS_PMBSR_EL1); - if (!(pmbsr & BIT(SYS_PMBSR_EL1_S_SHIFT))) + if (!FIELD_GET(PMBSR_EL1_S, pmbsr)) return SPE_PMU_BUF_FAULT_ACT_SPURIOUS; /* * If we've lost data, disable profiling and also set the PARTIAL * flag to indicate that the last record is corrupted. */ - if (pmbsr & BIT(SYS_PMBSR_EL1_DL_SHIFT)) + if (FIELD_GET(PMBSR_EL1_DL, pmbsr)) perf_aux_output_flag(handle, PERF_AUX_FLAG_TRUNCATED | PERF_AUX_FLAG_PARTIAL); /* Report collisions to userspace so that it can up the period */ - if (pmbsr & BIT(SYS_PMBSR_EL1_COLL_SHIFT)) + if (FIELD_GET(PMBSR_EL1_COLL, pmbsr)) perf_aux_output_flag(handle, PERF_AUX_FLAG_COLLISION); /* We only expect buffer management events */ - switch (pmbsr & (SYS_PMBSR_EL1_EC_MASK << SYS_PMBSR_EL1_EC_SHIFT)) { - case SYS_PMBSR_EL1_EC_BUF: + switch (FIELD_GET(PMBSR_EL1_EC, pmbsr)) { + case PMBSR_EL1_EC_BUF: /* Handled below */ break; - case SYS_PMBSR_EL1_EC_FAULT_S1: - case SYS_PMBSR_EL1_EC_FAULT_S2: + case PMBSR_EL1_EC_FAULT_S1: + case PMBSR_EL1_EC_FAULT_S2: err_str = "Unexpected buffer fault"; goto out_err; default: @@ -600,9 +629,8 @@ arm_spe_pmu_buf_get_fault_act(struct perf_output_handle *handle) } /* Buffer management event */ - switch (pmbsr & - (SYS_PMBSR_EL1_BUF_BSC_MASK << SYS_PMBSR_EL1_BUF_BSC_SHIFT)) { - case SYS_PMBSR_EL1_BUF_BSC_FULL: + switch (FIELD_GET(PMBSR_EL1_BUF_BSC_MASK, pmbsr)) { + case PMBSR_EL1_BUF_BSC_FULL: ret = SPE_PMU_BUF_FAULT_ACT_OK; goto out_stop; default: @@ -677,11 +705,13 @@ static u64 arm_spe_pmsevfr_res0(u16 pmsver) { switch (pmsver) { case ID_AA64DFR0_EL1_PMSVer_IMP: - return SYS_PMSEVFR_EL1_RES0_8_2; + return PMSEVFR_EL1_RES0_IMP; case ID_AA64DFR0_EL1_PMSVer_V1P1: + return PMSEVFR_EL1_RES0_V1P1; + case ID_AA64DFR0_EL1_PMSVer_V1P2: /* Return the highest version we support in default */ default: - return SYS_PMSEVFR_EL1_RES0_8_3; + return PMSEVFR_EL1_RES0_V1P2; } } @@ -703,6 +733,9 @@ static int arm_spe_pmu_event_init(struct perf_event *event) if (arm_spe_event_to_pmsevfr(event) & arm_spe_pmsevfr_res0(spe_pmu->pmsver)) return -EOPNOTSUPP; + if (arm_spe_event_to_pmsnevfr(event) & arm_spe_pmsevfr_res0(spe_pmu->pmsver)) + return -EOPNOTSUPP; + if (attr->exclude_idle) return -EOPNOTSUPP; @@ -717,23 +750,26 @@ static int arm_spe_pmu_event_init(struct perf_event *event) return -EINVAL; reg = arm_spe_event_to_pmsfcr(event); - if ((reg & BIT(SYS_PMSFCR_EL1_FE_SHIFT)) && + if ((FIELD_GET(PMSFCR_EL1_FE, reg)) && !(spe_pmu->features & SPE_PMU_FEAT_FILT_EVT)) return -EOPNOTSUPP; - if ((reg & BIT(SYS_PMSFCR_EL1_FT_SHIFT)) && + if ((FIELD_GET(PMSFCR_EL1_FnE, reg)) && + !(spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT)) + return -EOPNOTSUPP; + + if ((FIELD_GET(PMSFCR_EL1_FT, reg)) && !(spe_pmu->features & SPE_PMU_FEAT_FILT_TYP)) return -EOPNOTSUPP; - if ((reg & BIT(SYS_PMSFCR_EL1_FL_SHIFT)) && + if ((FIELD_GET(PMSFCR_EL1_FL, reg)) && !(spe_pmu->features & SPE_PMU_FEAT_FILT_LAT)) return -EOPNOTSUPP; set_spe_event_has_cx(event); reg = arm_spe_event_to_pmscr(event); if (!perfmon_capable() && - (reg & (BIT(SYS_PMSCR_EL1_PA_SHIFT) | - BIT(SYS_PMSCR_EL1_PCT_SHIFT)))) + (reg & (PMSCR_EL1_PA | PMSCR_EL1_PCT))) return -EACCES; return 0; @@ -757,6 +793,11 @@ static void arm_spe_pmu_start(struct perf_event *event, int flags) reg = arm_spe_event_to_pmsevfr(event); write_sysreg_s(reg, SYS_PMSEVFR_EL1); + if (spe_pmu->features & SPE_PMU_FEAT_INV_FILT_EVT) { + reg = arm_spe_event_to_pmsnevfr(event); + write_sysreg_s(reg, SYS_PMSNEVFR_EL1); + } + reg = arm_spe_event_to_pmslatfr(event); write_sysreg_s(reg, SYS_PMSLATFR_EL1); @@ -971,14 +1012,14 @@ static void __arm_spe_pmu_dev_probe(void *info) /* Read PMBIDR first to determine whether or not we have access */ reg = read_sysreg_s(SYS_PMBIDR_EL1); - if (reg & BIT(SYS_PMBIDR_EL1_P_SHIFT)) { + if (FIELD_GET(PMBIDR_EL1_P, reg)) { dev_err(dev, "profiling buffer owned by higher exception level\n"); return; } /* Minimum alignment. If it's out-of-range, then fail the probe */ - fld = reg >> SYS_PMBIDR_EL1_ALIGN_SHIFT & SYS_PMBIDR_EL1_ALIGN_MASK; + fld = FIELD_GET(PMBIDR_EL1_ALIGN, reg); spe_pmu->align = 1 << fld; if (spe_pmu->align > SZ_2K) { dev_err(dev, "unsupported PMBIDR.Align [%d] on CPU %d\n", @@ -988,58 +1029,61 @@ static void __arm_spe_pmu_dev_probe(void *info) /* It's now safe to read PMSIDR and figure out what we've got */ reg = read_sysreg_s(SYS_PMSIDR_EL1); - if (reg & BIT(SYS_PMSIDR_EL1_FE_SHIFT)) + if (FIELD_GET(PMSIDR_EL1_FE, reg)) spe_pmu->features |= SPE_PMU_FEAT_FILT_EVT; - if (reg & BIT(SYS_PMSIDR_EL1_FT_SHIFT)) + if (FIELD_GET(PMSIDR_EL1_FnE, reg)) + spe_pmu->features |= SPE_PMU_FEAT_INV_FILT_EVT; + + if (FIELD_GET(PMSIDR_EL1_FT, reg)) spe_pmu->features |= SPE_PMU_FEAT_FILT_TYP; - if (reg & BIT(SYS_PMSIDR_EL1_FL_SHIFT)) + if (FIELD_GET(PMSIDR_EL1_FL, reg)) spe_pmu->features |= SPE_PMU_FEAT_FILT_LAT; - if (reg & BIT(SYS_PMSIDR_EL1_ARCHINST_SHIFT)) + if (FIELD_GET(PMSIDR_EL1_ARCHINST, reg)) spe_pmu->features |= SPE_PMU_FEAT_ARCH_INST; - if (reg & BIT(SYS_PMSIDR_EL1_LDS_SHIFT)) + if (FIELD_GET(PMSIDR_EL1_LDS, reg)) spe_pmu->features |= SPE_PMU_FEAT_LDS; - if (reg & BIT(SYS_PMSIDR_EL1_ERND_SHIFT)) + if (FIELD_GET(PMSIDR_EL1_ERND, reg)) spe_pmu->features |= SPE_PMU_FEAT_ERND; /* This field has a spaced out encoding, so just use a look-up */ - fld = reg >> SYS_PMSIDR_EL1_INTERVAL_SHIFT & SYS_PMSIDR_EL1_INTERVAL_MASK; + fld = FIELD_GET(PMSIDR_EL1_INTERVAL, reg); switch (fld) { - case 0: + case PMSIDR_EL1_INTERVAL_256: spe_pmu->min_period = 256; break; - case 2: + case PMSIDR_EL1_INTERVAL_512: spe_pmu->min_period = 512; break; - case 3: + case PMSIDR_EL1_INTERVAL_768: spe_pmu->min_period = 768; break; - case 4: + case PMSIDR_EL1_INTERVAL_1024: spe_pmu->min_period = 1024; break; - case 5: + case PMSIDR_EL1_INTERVAL_1536: spe_pmu->min_period = 1536; break; - case 6: + case PMSIDR_EL1_INTERVAL_2048: spe_pmu->min_period = 2048; break; - case 7: + case PMSIDR_EL1_INTERVAL_3072: spe_pmu->min_period = 3072; break; default: dev_warn(dev, "unknown PMSIDR_EL1.Interval [%d]; assuming 8\n", fld); fallthrough; - case 8: + case PMSIDR_EL1_INTERVAL_4096: spe_pmu->min_period = 4096; } /* Maximum record size. If it's out-of-range, then fail the probe */ - fld = reg >> SYS_PMSIDR_EL1_MAXSIZE_SHIFT & SYS_PMSIDR_EL1_MAXSIZE_MASK; + fld = FIELD_GET(PMSIDR_EL1_MAXSIZE, reg); spe_pmu->max_record_sz = 1 << fld; if (spe_pmu->max_record_sz > SZ_2K || spe_pmu->max_record_sz < 16) { dev_err(dev, "unsupported PMSIDR_EL1.MaxSize [%d] on CPU %d\n", @@ -1047,22 +1091,22 @@ static void __arm_spe_pmu_dev_probe(void *info) return; } - fld = reg >> SYS_PMSIDR_EL1_COUNTSIZE_SHIFT & SYS_PMSIDR_EL1_COUNTSIZE_MASK; + fld = FIELD_GET(PMSIDR_EL1_COUNTSIZE, reg); switch (fld) { default: dev_warn(dev, "unknown PMSIDR_EL1.CountSize [%d]; assuming 2\n", fld); fallthrough; - case 2: + case PMSIDR_EL1_COUNTSIZE_12_BIT_SAT: spe_pmu->counter_sz = 12; break; - case 3: + case PMSIDR_EL1_COUNTSIZE_16_BIT_SAT: spe_pmu->counter_sz = 16; } dev_info(dev, - "probed for CPUs %*pbl [max_record_sz %u, align %u, features 0x%llx]\n", - cpumask_pr_args(&spe_pmu->supported_cpus), + "probed SPEv1.%d for CPUs %*pbl [max_record_sz %u, align %u, features 0x%llx]\n", + spe_pmu->pmsver - 1, cpumask_pr_args(&spe_pmu->supported_cpus), spe_pmu->max_record_sz, spe_pmu->align, spe_pmu->features); spe_pmu->features |= SPE_PMU_FEAT_DEV_PROBED; diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c index 8e058e08fe81..5222ba1e79d0 100644 --- a/drivers/perf/fsl_imx8_ddr_perf.c +++ b/drivers/perf/fsl_imx8_ddr_perf.c @@ -97,7 +97,6 @@ struct ddr_pmu { struct hlist_node node; struct device *dev; struct perf_event *events[NUM_COUNTERS]; - int active_events; enum cpuhp_state cpuhp_state; const struct fsl_ddr_devtype_data *devtype_data; int irq; @@ -530,7 +529,6 @@ static int ddr_perf_event_add(struct perf_event *event, int flags) } pmu->events[counter] = event; - pmu->active_events++; hwc->idx = counter; hwc->state |= PERF_HES_STOPPED; @@ -562,7 +560,6 @@ static void ddr_perf_event_del(struct perf_event *event, int flags) ddr_perf_event_stop(event, PERF_EF_UPDATE); ddr_perf_free_counter(pmu, counter); - pmu->active_events--; hwc->idx = -1; } diff --git a/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c index a9bb73f76be4..4c67d57217a7 100644 --- a/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_cpa_pmu.c @@ -316,21 +316,7 @@ static int hisi_cpa_pmu_probe(struct platform_device *pdev) if (!name) return -ENOMEM; - cpa_pmu->pmu = (struct pmu) { - .name = name, - .module = THIS_MODULE, - .task_ctx_nr = perf_invalid_context, - .event_init = hisi_uncore_pmu_event_init, - .pmu_enable = hisi_uncore_pmu_enable, - .pmu_disable = hisi_uncore_pmu_disable, - .add = hisi_uncore_pmu_add, - .del = hisi_uncore_pmu_del, - .start = hisi_uncore_pmu_start, - .stop = hisi_uncore_pmu_stop, - .read = hisi_uncore_pmu_read, - .attr_groups = cpa_pmu->pmu_events.attr_groups, - .capabilities = PERF_PMU_CAP_NO_EXCLUDE, - }; + hisi_pmu_init(cpa_pmu, name, THIS_MODULE); /* Power Management should be disabled before using CPA PMU. */ hisi_cpa_pmu_disable_pm(cpa_pmu); diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c index 50d0c0a2f1fe..8c3ffcbfd4c0 100644 --- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c @@ -516,7 +516,7 @@ static int hisi_ddrc_pmu_probe(struct platform_device *pdev) "hisi_sccl%u_ddrc%u", ddrc_pmu->sccl_id, ddrc_pmu->index_id); - hisi_pmu_init(&ddrc_pmu->pmu, name, ddrc_pmu->pmu_events.attr_groups, THIS_MODULE); + hisi_pmu_init(ddrc_pmu, name, THIS_MODULE); ret = perf_pmu_register(&ddrc_pmu->pmu, name, -1); if (ret) { diff --git a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c index 13017b3412a5..806698b9eabf 100644 --- a/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_hha_pmu.c @@ -519,7 +519,7 @@ static int hisi_hha_pmu_probe(struct platform_device *pdev) name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_hha%u", hha_pmu->sccl_id, hha_pmu->index_id); - hisi_pmu_init(&hha_pmu->pmu, name, hha_pmu->pmu_events.attr_groups, THIS_MODULE); + hisi_pmu_init(hha_pmu, name, THIS_MODULE); ret = perf_pmu_register(&hha_pmu->pmu, name, -1); if (ret) { diff --git a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c index 2995f3630d49..5b2c35f1658a 100644 --- a/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_l3c_pmu.c @@ -557,7 +557,7 @@ static int hisi_l3c_pmu_probe(struct platform_device *pdev) */ name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "hisi_sccl%u_l3c%u", l3c_pmu->sccl_id, l3c_pmu->ccl_id); - hisi_pmu_init(&l3c_pmu->pmu, name, l3c_pmu->pmu_events.attr_groups, THIS_MODULE); + hisi_pmu_init(l3c_pmu, name, THIS_MODULE); ret = perf_pmu_register(&l3c_pmu->pmu, name, -1); if (ret) { diff --git a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c index 47d3cc9b6eec..afe3419f3f6d 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_pa_pmu.c @@ -412,7 +412,7 @@ static int hisi_pa_pmu_probe(struct platform_device *pdev) return ret; } - hisi_pmu_init(&pa_pmu->pmu, name, pa_pmu->pmu_events.attr_groups, THIS_MODULE); + hisi_pmu_init(pa_pmu, name, THIS_MODULE); ret = perf_pmu_register(&pa_pmu->pmu, name, -1); if (ret) { dev_err(pa_pmu->dev, "PMU register failed, ret = %d\n", ret); diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c index fbc8a93d5eac..f1b0f5e1a28f 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c @@ -531,9 +531,11 @@ int hisi_uncore_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node) } EXPORT_SYMBOL_GPL(hisi_uncore_pmu_offline_cpu); -void hisi_pmu_init(struct pmu *pmu, const char *name, - const struct attribute_group **attr_groups, struct module *module) +void hisi_pmu_init(struct hisi_pmu *hisi_pmu, const char *name, + struct module *module) { + struct pmu *pmu = &hisi_pmu->pmu; + pmu->name = name; pmu->module = module; pmu->task_ctx_nr = perf_invalid_context; @@ -545,7 +547,8 @@ void hisi_pmu_init(struct pmu *pmu, const char *name, pmu->start = hisi_uncore_pmu_start; pmu->stop = hisi_uncore_pmu_stop; pmu->read = hisi_uncore_pmu_read; - pmu->attr_groups = attr_groups; + pmu->attr_groups = hisi_pmu->pmu_events.attr_groups; + pmu->capabilities = PERF_PMU_CAP_NO_EXCLUDE; } EXPORT_SYMBOL_GPL(hisi_pmu_init); diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.h b/drivers/perf/hisilicon/hisi_uncore_pmu.h index b59de33cd059..f8e3cc6903d7 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pmu.h +++ b/drivers/perf/hisilicon/hisi_uncore_pmu.h @@ -121,6 +121,6 @@ ssize_t hisi_uncore_pmu_identifier_attr_show(struct device *dev, int hisi_uncore_pmu_init_irq(struct hisi_pmu *hisi_pmu, struct platform_device *pdev); -void hisi_pmu_init(struct pmu *pmu, const char *name, - const struct attribute_group **attr_groups, struct module *module); +void hisi_pmu_init(struct hisi_pmu *hisi_pmu, const char *name, + struct module *module); #endif /* __HISI_UNCORE_PMU_H__ */ diff --git a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c index b9c79f17230c..1e354433776a 100644 --- a/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_sllc_pmu.c @@ -445,7 +445,7 @@ static int hisi_sllc_pmu_probe(struct platform_device *pdev) return ret; } - hisi_pmu_init(&sllc_pmu->pmu, name, sllc_pmu->pmu_events.attr_groups, THIS_MODULE); + hisi_pmu_init(sllc_pmu, name, THIS_MODULE); ret = perf_pmu_register(&sllc_pmu->pmu, name, -1); if (ret) { diff --git a/drivers/perf/marvell_cn10k_ddr_pmu.c b/drivers/perf/marvell_cn10k_ddr_pmu.c index 665b382a0ee3..b94a5f6cc22b 100644 --- a/drivers/perf/marvell_cn10k_ddr_pmu.c +++ b/drivers/perf/marvell_cn10k_ddr_pmu.c @@ -12,6 +12,7 @@ #include <linux/of_device.h> #include <linux/perf_event.h> #include <linux/hrtimer.h> +#include <linux/acpi.h> /* Performance Counters Operating Mode Control Registers */ #define DDRC_PERF_CNT_OP_MODE_CTRL 0x8020 @@ -717,10 +718,19 @@ static const struct of_device_id cn10k_ddr_pmu_of_match[] = { MODULE_DEVICE_TABLE(of, cn10k_ddr_pmu_of_match); #endif +#ifdef CONFIG_ACPI +static const struct acpi_device_id cn10k_ddr_pmu_acpi_match[] = { + {"MRVL000A", 0}, + {}, +}; +MODULE_DEVICE_TABLE(acpi, cn10k_ddr_pmu_acpi_match); +#endif + static struct platform_driver cn10k_ddr_pmu_driver = { .driver = { .name = "cn10k-ddr-pmu", .of_match_table = of_match_ptr(cn10k_ddr_pmu_of_match), + .acpi_match_table = ACPI_PTR(cn10k_ddr_pmu_acpi_match), .suppress_bind_attrs = true, }, .probe = cn10k_ddr_perf_probe, diff --git a/drivers/perf/marvell_cn10k_tad_pmu.c b/drivers/perf/marvell_cn10k_tad_pmu.c index a1166afb3702..3972197e2210 100644 --- a/drivers/perf/marvell_cn10k_tad_pmu.c +++ b/drivers/perf/marvell_cn10k_tad_pmu.c @@ -13,6 +13,7 @@ #include <linux/cpuhotplug.h> #include <linux/perf_event.h> #include <linux/platform_device.h> +#include <linux/acpi.h> #define TAD_PFC_OFFSET 0x800 #define TAD_PFC(counter) (TAD_PFC_OFFSET | (counter << 3)) @@ -254,7 +255,7 @@ static const struct attribute_group *tad_pmu_attr_groups[] = { static int tad_pmu_probe(struct platform_device *pdev) { - struct device_node *node = pdev->dev.of_node; + struct device *dev = &pdev->dev; struct tad_region *regions; struct tad_pmu *tad_pmu; struct resource *res; @@ -276,21 +277,21 @@ static int tad_pmu_probe(struct platform_device *pdev) return -ENODEV; } - ret = of_property_read_u32(node, "marvell,tad-page-size", - &tad_page_size); + ret = device_property_read_u32(dev, "marvell,tad-page-size", + &tad_page_size); if (ret) { dev_err(&pdev->dev, "Can't find tad-page-size property\n"); return ret; } - ret = of_property_read_u32(node, "marvell,tad-pmu-page-size", - &tad_pmu_page_size); + ret = device_property_read_u32(dev, "marvell,tad-pmu-page-size", + &tad_pmu_page_size); if (ret) { dev_err(&pdev->dev, "Can't find tad-pmu-page-size property\n"); return ret; } - ret = of_property_read_u32(node, "marvell,tad-cnt", &tad_cnt); + ret = device_property_read_u32(dev, "marvell,tad-cnt", &tad_cnt); if (ret) { dev_err(&pdev->dev, "Can't find tad-cnt property\n"); return ret; @@ -369,10 +370,19 @@ static const struct of_device_id tad_pmu_of_match[] = { }; #endif +#ifdef CONFIG_ACPI +static const struct acpi_device_id tad_pmu_acpi_match[] = { + {"MRVL000B", 0}, + {}, +}; +MODULE_DEVICE_TABLE(acpi, tad_pmu_acpi_match); +#endif + static struct platform_driver tad_pmu_driver = { .driver = { .name = "cn10k_tad_pmu", .of_match_table = of_match_ptr(tad_pmu_of_match), + .acpi_match_table = ACPI_PTR(tad_pmu_acpi_match), .suppress_bind_attrs = true, }, .probe = tad_pmu_probe, diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h index 898b3458b24a..b83126452c65 100644 --- a/include/linux/compiler_attributes.h +++ b/include/linux/compiler_attributes.h @@ -76,12 +76,6 @@ #endif /* - * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-cold-function-attribute - * gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-cold-label-attribute - */ -#define __cold __attribute__((__cold__)) - -/* * Note the long name. * * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-const-function-attribute diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 7c1afe0f4129..aab34e30128e 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -79,6 +79,33 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } /* Attributes */ #include <linux/compiler_attributes.h> +#if CONFIG_FUNCTION_ALIGNMENT > 0 +#define __function_aligned __aligned(CONFIG_FUNCTION_ALIGNMENT) +#else +#define __function_aligned +#endif + +/* + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-cold-function-attribute + * gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-cold-label-attribute + * + * When -falign-functions=N is in use, we must avoid the cold attribute as + * contemporary versions of GCC drop the alignment for cold functions. Worse, + * GCC can implicitly mark callees of cold functions as cold themselves, so + * it's not sufficient to add __function_aligned here as that will not ensure + * that callees are correctly aligned. + * + * See: + * + * https://lore.kernel.org/lkml/Y77%2FqVgvaJidFpYt@FVFF77S0Q05N + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88345#c9 + */ +#if !defined(CONFIG_CC_IS_GCC) || (CONFIG_FUNCTION_ALIGNMENT == 0) +#define __cold __attribute__((__cold__)) +#else +#define __cold +#endif + /* Builtins */ /* diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 99f1146614c0..366c730beaa3 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -39,6 +39,7 @@ static inline void ftrace_boot_snapshot(void) { } struct ftrace_ops; struct ftrace_regs; +struct dyn_ftrace; #ifdef CONFIG_FUNCTION_TRACER /* @@ -57,6 +58,9 @@ void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); void arch_ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); #endif +extern const struct ftrace_ops ftrace_nop_ops; +extern const struct ftrace_ops ftrace_list_ops; +struct ftrace_ops *ftrace_find_unique_ops(struct dyn_ftrace *rec); #endif /* CONFIG_FUNCTION_TRACER */ /* Main tracing buffer and events set up */ @@ -391,8 +395,6 @@ struct ftrace_func_entry { unsigned long direct; /* for direct lookup only */ }; -struct dyn_ftrace; - #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS extern int ftrace_direct_func_count; int register_ftrace_direct(unsigned long ip, unsigned long addr); @@ -563,6 +565,8 @@ bool is_ftrace_trampoline(unsigned long addr); * IPMODIFY - the record allows for the IP address to be changed. * DISABLED - the record is not ready to be touched yet * DIRECT - there is a direct function to call + * CALL_OPS - the record can use callsite-specific ops + * CALL_OPS_EN - the function is set up to use callsite-specific ops * * When a new ftrace_ops is registered and wants a function to save * pt_regs, the rec->flags REGS is set. When the function has been @@ -580,9 +584,11 @@ enum { FTRACE_FL_DISABLED = (1UL << 25), FTRACE_FL_DIRECT = (1UL << 24), FTRACE_FL_DIRECT_EN = (1UL << 23), + FTRACE_FL_CALL_OPS = (1UL << 22), + FTRACE_FL_CALL_OPS_EN = (1UL << 21), }; -#define FTRACE_REF_MAX_SHIFT 23 +#define FTRACE_REF_MAX_SHIFT 21 #define FTRACE_REF_MAX ((1UL << FTRACE_REF_MAX_SHIFT) - 1) #define ftrace_rec_count(rec) ((rec)->flags & FTRACE_REF_MAX) @@ -820,7 +826,8 @@ static inline int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) */ extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr); -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +#if defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS) || \ + defined(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS) /** * ftrace_modify_call - convert from one addr to another (no nop) * @rec: the call site record (e.g. mcount/fentry) @@ -833,6 +840,9 @@ extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr); * what we expect it to be, and then on success of the compare, * it should write to the location. * + * When using call ops, this is called when the associated ops change, even + * when (addr == old_addr). + * * The code segment at @rec->ip should be a caller to @old_addr * * Return must be: diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index ccb7f5dad59b..37675437b768 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -374,6 +374,7 @@ enum perf_event_read_format { #define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */ #define PERF_ATTR_SIZE_VER6 120 /* add: aux_sample_size */ #define PERF_ATTR_SIZE_VER7 128 /* add: sig_data */ +#define PERF_ATTR_SIZE_VER8 136 /* add: config3 */ /* * Hardware event_id to monitor via a performance monitoring event: @@ -515,6 +516,8 @@ struct perf_event_attr { * truncated accordingly on 32 bit architectures. */ __u64 sig_data; + + __u64 config3; /* extension of config2 */ }; /* diff --git a/kernel/exit.c b/kernel/exit.c index 15dc2ec80c46..c8e0375705f4 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1898,7 +1898,14 @@ bool thread_group_exited(struct pid *pid) } EXPORT_SYMBOL(thread_group_exited); -__weak void abort(void) +/* + * This needs to be __function_aligned as GCC implicitly makes any + * implementation of abort() cold and drops alignment specified by + * -falign-functions=N. + * + * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88345#c11 + */ +__weak __function_aligned void abort(void) { BUG(); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 197545241ab8..5df427a2321d 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -42,6 +42,9 @@ config HAVE_DYNAMIC_FTRACE_WITH_REGS config HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS bool +config HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS + bool + config HAVE_DYNAMIC_FTRACE_WITH_ARGS bool help @@ -257,6 +260,10 @@ config DYNAMIC_FTRACE_WITH_DIRECT_CALLS depends on DYNAMIC_FTRACE_WITH_REGS depends on HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +config DYNAMIC_FTRACE_WITH_CALL_OPS + def_bool y + depends on HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS + config DYNAMIC_FTRACE_WITH_ARGS def_bool y depends on DYNAMIC_FTRACE diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 442438b93fe9..e634b80f49d1 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -125,6 +125,33 @@ struct ftrace_ops global_ops; void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, struct ftrace_ops *op, struct ftrace_regs *fregs); +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS +/* + * Stub used to invoke the list ops without requiring a separate trampoline. + */ +const struct ftrace_ops ftrace_list_ops = { + .func = ftrace_ops_list_func, + .flags = FTRACE_OPS_FL_STUB, +}; + +static void ftrace_ops_nop_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, + struct ftrace_regs *fregs) +{ + /* do nothing */ +} + +/* + * Stub used when a call site is disabled. May be called transiently by threads + * which have made it into ftrace_caller but haven't yet recovered the ops at + * the point the call site is disabled. + */ +const struct ftrace_ops ftrace_nop_ops = { + .func = ftrace_ops_nop_func, + .flags = FTRACE_OPS_FL_STUB, +}; +#endif + static inline void ftrace_ops_init(struct ftrace_ops *ops) { #ifdef CONFIG_DYNAMIC_FTRACE @@ -1814,6 +1841,18 @@ static bool __ftrace_hash_rec_update(struct ftrace_ops *ops, * if rec count is zero. */ } + + /* + * If the rec has a single associated ops, and ops->func can be + * called directly, allow the call site to call via the ops. + */ + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS) && + ftrace_rec_count(rec) == 1 && + ftrace_ops_get_func(ops) == ops->func) + rec->flags |= FTRACE_FL_CALL_OPS; + else + rec->flags &= ~FTRACE_FL_CALL_OPS; + count++; /* Must match FTRACE_UPDATE_CALLS in ftrace_modify_all_code() */ @@ -2108,8 +2147,9 @@ void ftrace_bug(int failed, struct dyn_ftrace *rec) struct ftrace_ops *ops = NULL; pr_info("ftrace record flags: %lx\n", rec->flags); - pr_cont(" (%ld)%s", ftrace_rec_count(rec), - rec->flags & FTRACE_FL_REGS ? " R" : " "); + pr_cont(" (%ld)%s%s", ftrace_rec_count(rec), + rec->flags & FTRACE_FL_REGS ? " R" : " ", + rec->flags & FTRACE_FL_CALL_OPS ? " O" : " "); if (rec->flags & FTRACE_FL_TRAMP_EN) { ops = ftrace_find_tramp_ops_any(rec); if (ops) { @@ -2177,6 +2217,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) * want the direct enabled (it will be done via the * direct helper). But if DIRECT_EN is set, and * the count is not one, we need to clear it. + * */ if (ftrace_rec_count(rec) == 1) { if (!(rec->flags & FTRACE_FL_DIRECT) != @@ -2185,6 +2226,19 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) } else if (rec->flags & FTRACE_FL_DIRECT_EN) { flag |= FTRACE_FL_DIRECT; } + + /* + * Ops calls are special, as count matters. + * As with direct calls, they must only be enabled when count + * is one, otherwise they'll be handled via the list ops. + */ + if (ftrace_rec_count(rec) == 1) { + if (!(rec->flags & FTRACE_FL_CALL_OPS) != + !(rec->flags & FTRACE_FL_CALL_OPS_EN)) + flag |= FTRACE_FL_CALL_OPS; + } else if (rec->flags & FTRACE_FL_CALL_OPS_EN) { + flag |= FTRACE_FL_CALL_OPS; + } } /* If the state of this record hasn't changed, then do nothing */ @@ -2229,6 +2283,21 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) rec->flags &= ~FTRACE_FL_DIRECT_EN; } } + + if (flag & FTRACE_FL_CALL_OPS) { + if (ftrace_rec_count(rec) == 1) { + if (rec->flags & FTRACE_FL_CALL_OPS) + rec->flags |= FTRACE_FL_CALL_OPS_EN; + else + rec->flags &= ~FTRACE_FL_CALL_OPS_EN; + } else { + /* + * Can only call directly if there's + * only one set of associated ops. + */ + rec->flags &= ~FTRACE_FL_CALL_OPS_EN; + } + } } /* @@ -2258,7 +2327,8 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update) * and REGS states. The _EN flags must be disabled though. */ rec->flags &= ~(FTRACE_FL_ENABLED | FTRACE_FL_TRAMP_EN | - FTRACE_FL_REGS_EN | FTRACE_FL_DIRECT_EN); + FTRACE_FL_REGS_EN | FTRACE_FL_DIRECT_EN | + FTRACE_FL_CALL_OPS_EN); } ftrace_bug_type = FTRACE_BUG_NOP; @@ -2431,6 +2501,25 @@ ftrace_find_tramp_ops_new(struct dyn_ftrace *rec) return NULL; } +struct ftrace_ops * +ftrace_find_unique_ops(struct dyn_ftrace *rec) +{ + struct ftrace_ops *op, *found = NULL; + unsigned long ip = rec->ip; + + do_for_each_ftrace_op(op, ftrace_ops_list) { + + if (hash_contains_ip(ip, op->func_hash)) { + if (found) + return NULL; + found = op; + } + + } while_for_each_ftrace_op(op); + + return found; +} + #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS /* Protected by rcu_tasks for reading, and direct_mutex for writing */ static struct ftrace_hash *direct_functions = EMPTY_HASH; @@ -3780,11 +3869,12 @@ static int t_show(struct seq_file *m, void *v) if (iter->flags & FTRACE_ITER_ENABLED) { struct ftrace_ops *ops; - seq_printf(m, " (%ld)%s%s%s", + seq_printf(m, " (%ld)%s%s%s%s", ftrace_rec_count(rec), rec->flags & FTRACE_FL_REGS ? " R" : " ", rec->flags & FTRACE_FL_IPMODIFY ? " I" : " ", - rec->flags & FTRACE_FL_DIRECT ? " D" : " "); + rec->flags & FTRACE_FL_DIRECT ? " D" : " ", + rec->flags & FTRACE_FL_CALL_OPS ? " O" : " "); if (rec->flags & FTRACE_FL_TRAMP_EN) { ops = ftrace_find_tramp_ops_any(rec); if (ops) { @@ -3800,6 +3890,15 @@ static int t_show(struct seq_file *m, void *v) } else { add_trampoline_func(m, NULL, rec); } + if (rec->flags & FTRACE_FL_CALL_OPS_EN) { + ops = ftrace_find_unique_ops(rec); + if (ops) { + seq_printf(m, "\tops: %pS (%pS)", + ops, ops->func); + } else { + seq_puts(m, "\tops: ERROR!"); + } + } if (rec->flags & FTRACE_FL_DIRECT) { unsigned long direct; diff --git a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S index 6ddf392329c9..df3230fdac39 100644 --- a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S +++ b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S @@ -124,8 +124,11 @@ do_syscall: str x29, [x2], #8 // FP str x30, [x2], #8 // LR - // Load FPRs if we're not doing SVE + // Load FPRs if we're not doing neither SVE nor streaming SVE cbnz x0, 1f + ldr x2, =svcr_in + tbnz x2, #SVCR_SM_SHIFT, 1f + ldr x2, =fpr_in ldp q0, q1, [x2] ldp q2, q3, [x2, #16 * 2] @@ -143,10 +146,11 @@ do_syscall: ldp q26, q27, [x2, #16 * 26] ldp q28, q29, [x2, #16 * 28] ldp q30, q31, [x2, #16 * 30] + + b 2f 1: // Load the SVE registers if we're doing SVE/SME - cbz x0, 1f ldr x2, =z_in ldr z0, [x2, #0, MUL VL] @@ -187,9 +191,9 @@ do_syscall: ldr x2, =ffr_in ldr p0, [x2] ldr x2, [x2, #0] - cbz x2, 2f + cbz x2, 1f wrffr p0.b -2: +1: ldr x2, =p_in ldr p0, [x2, #0, MUL VL] @@ -208,7 +212,7 @@ do_syscall: ldr p13, [x2, #13, MUL VL] ldr p14, [x2, #14, MUL VL] ldr p15, [x2, #15, MUL VL] -1: +2: // Do the syscall svc #0 diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.c b/tools/testing/selftests/arm64/abi/syscall-abi.c index 9800f9dc6b35..18cc123e2347 100644 --- a/tools/testing/selftests/arm64/abi/syscall-abi.c +++ b/tools/testing/selftests/arm64/abi/syscall-abi.c @@ -20,10 +20,13 @@ #include "syscall-abi.h" -#define NUM_VL ((SVE_VQ_MAX - SVE_VQ_MIN) + 1) - static int default_sme_vl; +static int sve_vl_count; +static unsigned int sve_vls[SVE_VQ_MAX]; +static int sme_vl_count; +static unsigned int sme_vls[SVE_VQ_MAX]; + extern void do_syscall(int sve_vl, int sme_vl); static void fill_random(void *buf, size_t size) @@ -83,6 +86,7 @@ static int check_gpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, uint64_t s #define NUM_FPR 32 uint64_t fpr_in[NUM_FPR * 2]; uint64_t fpr_out[NUM_FPR * 2]; +uint64_t fpr_zero[NUM_FPR * 2]; static void setup_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, uint64_t svcr) @@ -97,7 +101,7 @@ static int check_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, int errors = 0; int i; - if (!sve_vl) { + if (!sve_vl && !(svcr & SVCR_SM_MASK)) { for (i = 0; i < ARRAY_SIZE(fpr_in); i++) { if (fpr_in[i] != fpr_out[i]) { ksft_print_msg("%s Q%d/%d mismatch %llx != %llx\n", @@ -109,6 +113,18 @@ static int check_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, } } + /* + * In streaming mode the whole register set should be cleared + * by the transition out of streaming mode. + */ + if (svcr & SVCR_SM_MASK) { + if (memcmp(fpr_zero, fpr_out, sizeof(fpr_out)) != 0) { + ksft_print_msg("%s FPSIMD registers non-zero exiting SM\n", + cfg->name); + errors++; + } + } + return errors; } @@ -284,8 +300,8 @@ static int check_svcr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, return errors; } -uint8_t za_in[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)]; -uint8_t za_out[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)]; +uint8_t za_in[ZA_SIG_REGS_SIZE(SVE_VQ_MAX)]; +uint8_t za_out[ZA_SIG_REGS_SIZE(SVE_VQ_MAX)]; static void setup_za(struct syscall_cfg *cfg, int sve_vl, int sme_vl, uint64_t svcr) @@ -385,73 +401,78 @@ static bool do_test(struct syscall_cfg *cfg, int sve_vl, int sme_vl, static void test_one_syscall(struct syscall_cfg *cfg) { - int sve_vq, sve_vl; - int sme_vq, sme_vl; + int sve, sme; + int ret; /* FPSIMD only case */ ksft_test_result(do_test(cfg, 0, default_sme_vl, 0), "%s FPSIMD\n", cfg->name); - if (!(getauxval(AT_HWCAP) & HWCAP_SVE)) - return; - - for (sve_vq = SVE_VQ_MAX; sve_vq > 0; --sve_vq) { - sve_vl = prctl(PR_SVE_SET_VL, sve_vq * 16); - if (sve_vl == -1) + for (sve = 0; sve < sve_vl_count; sve++) { + ret = prctl(PR_SVE_SET_VL, sve_vls[sve]); + if (ret == -1) ksft_exit_fail_msg("PR_SVE_SET_VL failed: %s (%d)\n", strerror(errno), errno); - sve_vl &= PR_SVE_VL_LEN_MASK; - - if (sve_vq != sve_vq_from_vl(sve_vl)) - sve_vq = sve_vq_from_vl(sve_vl); + ksft_test_result(do_test(cfg, sve_vls[sve], default_sme_vl, 0), + "%s SVE VL %d\n", cfg->name, sve_vls[sve]); - ksft_test_result(do_test(cfg, sve_vl, default_sme_vl, 0), - "%s SVE VL %d\n", cfg->name, sve_vl); - - if (!(getauxval(AT_HWCAP2) & HWCAP2_SME)) - continue; - - for (sme_vq = SVE_VQ_MAX; sme_vq > 0; --sme_vq) { - sme_vl = prctl(PR_SME_SET_VL, sme_vq * 16); - if (sme_vl == -1) + for (sme = 0; sme < sme_vl_count; sme++) { + ret = prctl(PR_SME_SET_VL, sme_vls[sme]); + if (ret == -1) ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n", strerror(errno), errno); - sme_vl &= PR_SME_VL_LEN_MASK; - - if (sme_vq != sve_vq_from_vl(sme_vl)) - sme_vq = sve_vq_from_vl(sme_vl); - - ksft_test_result(do_test(cfg, sve_vl, sme_vl, + ksft_test_result(do_test(cfg, sve_vls[sve], + sme_vls[sme], SVCR_ZA_MASK | SVCR_SM_MASK), "%s SVE VL %d/SME VL %d SM+ZA\n", - cfg->name, sve_vl, sme_vl); - ksft_test_result(do_test(cfg, sve_vl, sme_vl, - SVCR_SM_MASK), + cfg->name, sve_vls[sve], + sme_vls[sme]); + ksft_test_result(do_test(cfg, sve_vls[sve], + sme_vls[sme], SVCR_SM_MASK), "%s SVE VL %d/SME VL %d SM\n", - cfg->name, sve_vl, sme_vl); - ksft_test_result(do_test(cfg, sve_vl, sme_vl, - SVCR_ZA_MASK), + cfg->name, sve_vls[sve], + sme_vls[sme]); + ksft_test_result(do_test(cfg, sve_vls[sve], + sme_vls[sme], SVCR_ZA_MASK), "%s SVE VL %d/SME VL %d ZA\n", - cfg->name, sve_vl, sme_vl); + cfg->name, sve_vls[sve], + sme_vls[sme]); } } + + for (sme = 0; sme < sme_vl_count; sme++) { + ret = prctl(PR_SME_SET_VL, sme_vls[sme]); + if (ret == -1) + ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n", + strerror(errno), errno); + + ksft_test_result(do_test(cfg, 0, sme_vls[sme], + SVCR_ZA_MASK | SVCR_SM_MASK), + "%s SME VL %d SM+ZA\n", + cfg->name, sme_vls[sme]); + ksft_test_result(do_test(cfg, 0, sme_vls[sme], SVCR_SM_MASK), + "%s SME VL %d SM\n", + cfg->name, sme_vls[sme]); + ksft_test_result(do_test(cfg, 0, sme_vls[sme], SVCR_ZA_MASK), + "%s SME VL %d ZA\n", + cfg->name, sme_vls[sme]); + } } -int sve_count_vls(void) +void sve_count_vls(void) { unsigned int vq; - int vl_count = 0; int vl; if (!(getauxval(AT_HWCAP) & HWCAP_SVE)) - return 0; + return; /* * Enumerate up to SVE_VQ_MAX vector lengths */ - for (vq = SVE_VQ_MAX; vq > 0; --vq) { + for (vq = SVE_VQ_MAX; vq > 0; vq /= 2) { vl = prctl(PR_SVE_SET_VL, vq * 16); if (vl == -1) ksft_exit_fail_msg("PR_SVE_SET_VL failed: %s (%d)\n", @@ -462,28 +483,22 @@ int sve_count_vls(void) if (vq != sve_vq_from_vl(vl)) vq = sve_vq_from_vl(vl); - vl_count++; + sve_vls[sve_vl_count++] = vl; } - - return vl_count; } -int sme_count_vls(void) +void sme_count_vls(void) { unsigned int vq; - int vl_count = 0; int vl; if (!(getauxval(AT_HWCAP2) & HWCAP2_SME)) - return 0; - - /* Ensure we configure a SME VL, used to flag if SVCR is set */ - default_sme_vl = 16; + return; /* * Enumerate up to SVE_VQ_MAX vector lengths */ - for (vq = SVE_VQ_MAX; vq > 0; --vq) { + for (vq = SVE_VQ_MAX; vq > 0; vq /= 2) { vl = prctl(PR_SME_SET_VL, vq * 16); if (vl == -1) ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n", @@ -491,13 +506,18 @@ int sme_count_vls(void) vl &= PR_SME_VL_LEN_MASK; + /* Found lowest VL */ + if (sve_vq_from_vl(vl) > vq) + break; + if (vq != sve_vq_from_vl(vl)) vq = sve_vq_from_vl(vl); - vl_count++; + sme_vls[sme_vl_count++] = vl; } - return vl_count; + /* Ensure we configure a SME VL, used to flag if SVCR is set */ + default_sme_vl = sme_vls[0]; } int main(void) @@ -509,8 +529,13 @@ int main(void) srandom(getpid()); ksft_print_header(); - tests += sve_count_vls(); - tests += (sve_count_vls() * sme_count_vls()) * 3; + + sve_count_vls(); + sme_count_vls(); + + tests += sve_vl_count; + tests += sme_vl_count * 3; + tests += (sve_vl_count * sme_vl_count) * 3; ksft_set_plan(ARRAY_SIZE(syscalls) * tests); if (getauxval(AT_HWCAP2) & HWCAP2_SME2) diff --git a/tools/testing/selftests/arm64/bti/test.c b/tools/testing/selftests/arm64/bti/test.c index 67b77ab83c20..2cd8dcee5aec 100644 --- a/tools/testing/selftests/arm64/bti/test.c +++ b/tools/testing/selftests/arm64/bti/test.c @@ -6,6 +6,7 @@ #include "system.h" +#include <stdbool.h> #include <stddef.h> #include <linux/errno.h> #include <linux/auxvec.h> @@ -101,7 +102,8 @@ static void handler(int n, siginfo_t *si __always_unused, uc->uc_mcontext.pstate &= ~PSR_BTYPE_MASK; } -static int skip_all; +/* Does the system have BTI? */ +static bool have_bti; static void __do_test(void (*trampoline)(void (*)(void)), void (*fn)(void), @@ -109,19 +111,11 @@ static void __do_test(void (*trampoline)(void (*)(void)), const char *name, int expect_sigill) { - if (skip_all) { - test_skipped++; - putstr("ok "); - putnum(test_num); - putstr(" "); - puttestname(name, trampoline_name); - putstr(" # SKIP\n"); - - return; - } - - /* Branch Target exceptions should only happen in BTI binaries: */ - if (!BTI) + /* + * Branch Target exceptions should only happen for BTI + * binaries running on a system with BTI: + */ + if (!BTI || !have_bti) expect_sigill = 0; sigill_expected = expect_sigill; @@ -199,9 +193,10 @@ void start(int *argcp) putstr("# HWCAP2_BTI present\n"); if (!(hwcap & HWCAP_PACA)) putstr("# Bad hardware? Expect problems.\n"); + have_bti = true; } else { putstr("# HWCAP2_BTI not present\n"); - skip_all = 1; + have_bti = false; } putstr("# Test binary"); diff --git a/tools/testing/selftests/arm64/fp/assembler.h b/tools/testing/selftests/arm64/fp/assembler.h index 90bd433d2665..9b38a0da407d 100644 --- a/tools/testing/selftests/arm64/fp/assembler.h +++ b/tools/testing/selftests/arm64/fp/assembler.h @@ -57,7 +57,7 @@ endfunction // Utility macro to print a literal string // Clobbers x0-x4,x8 .macro puts string - .pushsection .rodata.str1.1, "aMS", 1 + .pushsection .rodata.str1.1, "aMS", @progbits, 1 .L__puts_literal\@: .string "\string" .popsection diff --git a/tools/testing/selftests/arm64/fp/fp-pidbench.S b/tools/testing/selftests/arm64/fp/fp-pidbench.S index 16a436389bfc..73830f6bc99b 100644 --- a/tools/testing/selftests/arm64/fp/fp-pidbench.S +++ b/tools/testing/selftests/arm64/fp/fp-pidbench.S @@ -31,7 +31,6 @@ // Main program entry point .globl _start function _start -_start: puts "Iterations per test: " mov x20, #10000 lsl x20, x20, #8 diff --git a/tools/testing/selftests/arm64/fp/fp-stress.c b/tools/testing/selftests/arm64/fp/fp-stress.c index 520385fcfede..dd31647b00a2 100644 --- a/tools/testing/selftests/arm64/fp/fp-stress.c +++ b/tools/testing/selftests/arm64/fp/fp-stress.c @@ -390,7 +390,7 @@ static void probe_vls(int vls[], int *vl_count, int set_vl) *vl_count = 0; - for (vq = SVE_VQ_MAX; vq > 0; --vq) { + for (vq = SVE_VQ_MAX; vq > 0; vq /= 2) { vl = prctl(set_vl, vq * 16); if (vl == -1) ksft_exit_fail_msg("SET_VL failed: %s (%d)\n", @@ -398,6 +398,9 @@ static void probe_vls(int vls[], int *vl_count, int set_vl) vl &= PR_SVE_VL_LEN_MASK; + if (*vl_count && (vl == vls[*vl_count - 1])) + break; + vq = sve_vq_from_vl(vl); vls[*vl_count] = vl; diff --git a/tools/testing/selftests/arm64/fp/fpsimd-test.S b/tools/testing/selftests/arm64/fp/fpsimd-test.S index 918d04885a33..8b960d01ed2e 100644 --- a/tools/testing/selftests/arm64/fp/fpsimd-test.S +++ b/tools/testing/selftests/arm64/fp/fpsimd-test.S @@ -215,7 +215,6 @@ endfunction // Main program entry point .globl _start function _start -_start: mov x23, #0 // signal count mov w0, #SIGINT diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c index 8c4847977583..6d61992fe8a0 100644 --- a/tools/testing/selftests/arm64/fp/sve-ptrace.c +++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c @@ -30,6 +30,16 @@ #define NT_ARM_SSVE 0x40b #endif +/* + * The architecture defines the maximum VQ as 16 but for extensibility + * the kernel specifies the SVE_VQ_MAX as 512 resulting in us running + * a *lot* more tests than are useful if we use it. Until the + * architecture is extended let's limit our coverage to what is + * currently allowed, plus one extra to ensure we cover constraining + * the VL as expected. + */ +#define TEST_VQ_MAX 17 + struct vec_type { const char *name; unsigned long hwcap_type; @@ -55,7 +65,7 @@ static const struct vec_type vec_types[] = { }, }; -#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 4) +#define VL_TESTS (((TEST_VQ_MAX - SVE_VQ_MIN) + 1) * 4) #define FLAG_TESTS 2 #define FPSIMD_TESTS 2 @@ -689,7 +699,7 @@ static int do_parent(pid_t child) } /* Step through every possible VQ */ - for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) { + for (vq = SVE_VQ_MIN; vq <= TEST_VQ_MAX; vq++) { vl = sve_vl_from_vq(vq); /* First, try to set this vector length */ diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S index 2a18cb4c528c..4328895dfc87 100644 --- a/tools/testing/selftests/arm64/fp/sve-test.S +++ b/tools/testing/selftests/arm64/fp/sve-test.S @@ -378,7 +378,6 @@ endfunction // Main program entry point .globl _start function _start -_start: mov x23, #0 // Irritation signal count mov w0, #SIGINT diff --git a/tools/testing/selftests/arm64/fp/za-ptrace.c b/tools/testing/selftests/arm64/fp/za-ptrace.c index bf6158654056..ac27d87396fc 100644 --- a/tools/testing/selftests/arm64/fp/za-ptrace.c +++ b/tools/testing/selftests/arm64/fp/za-ptrace.c @@ -25,7 +25,17 @@ #define NT_ARM_ZA 0x40c #endif -#define EXPECTED_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3) +/* + * The architecture defines the maximum VQ as 16 but for extensibility + * the kernel specifies the SVE_VQ_MAX as 512 resulting in us running + * a *lot* more tests than are useful if we use it. Until the + * architecture is extended let's limit our coverage to what is + * currently allowed, plus one extra to ensure we cover constraining + * the VL as expected. + */ +#define TEST_VQ_MAX 17 + +#define EXPECTED_TESTS (((TEST_VQ_MAX - SVE_VQ_MIN) + 1) * 3) static void fill_buf(char *buf, size_t size) { @@ -301,7 +311,7 @@ static int do_parent(pid_t child) ksft_print_msg("Parent is %d, child is %d\n", getpid(), child); /* Step through every possible VQ */ - for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) { + for (vq = SVE_VQ_MIN; vq <= TEST_VQ_MAX; vq++) { vl = sve_vl_from_vq(vq); /* First, try to set this vector length */ diff --git a/tools/testing/selftests/arm64/fp/za-test.S b/tools/testing/selftests/arm64/fp/za-test.S index 53c54af65704..9dcd70911397 100644 --- a/tools/testing/selftests/arm64/fp/za-test.S +++ b/tools/testing/selftests/arm64/fp/za-test.S @@ -231,7 +231,6 @@ endfunction // Main program entry point .globl _start function _start -_start: mov x23, #0 // signal count mov w0, #SIGINT diff --git a/tools/testing/selftests/arm64/mte/Makefile b/tools/testing/selftests/arm64/mte/Makefile index 037046f5784e..0d7ac3db8390 100644 --- a/tools/testing/selftests/arm64/mte/Makefile +++ b/tools/testing/selftests/arm64/mte/Makefile @@ -1,24 +1,33 @@ # SPDX-License-Identifier: GPL-2.0 # Copyright (C) 2020 ARM Limited -# preserve CC value from top level Makefile -ifeq ($(CC),cc) -CC := $(CROSS_COMPILE)gcc -endif - CFLAGS += -std=gnu99 -I. -pthread LDFLAGS += -pthread SRCS := $(filter-out mte_common_util.c,$(wildcard *.c)) PROGS := $(patsubst %.c,%,$(SRCS)) +ifeq ($(LLVM),) +# For GCC check that the toolchain has MTE support. + +# preserve CC value from top level Makefile +ifeq ($(CC),cc) +CC := $(CROSS_COMPILE)gcc +endif + #check if the compiler works well mte_cc_support := $(shell if ($(CC) $(CFLAGS) -march=armv8.5-a+memtag -E -x c /dev/null -o /dev/null 2>&1) then echo "1"; fi) +else + +# All supported clang versions also support MTE. +mte_cc_support := 1 + +endif + ifeq ($(mte_cc_support),1) # Generated binaries to be installed by top KSFT script TEST_GEN_PROGS := $(PROGS) -# Get Kernel headers installed and use them. else $(warning compiler "$(CC)" does not support the ARMv8.5 MTE extension.) $(warning test program "mte" will not be created.) diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore index b7fbb65183e8..8ab4c86837fd 100644 --- a/tools/testing/selftests/arm64/signal/.gitignore +++ b/tools/testing/selftests/arm64/signal/.gitignore @@ -4,6 +4,7 @@ fake_sigreturn_* sme_* ssve_* sve_* +tpidr2_siginfo za_* zt_* !*.[ch] diff --git a/tools/testing/selftests/arm64/signal/Makefile b/tools/testing/selftests/arm64/signal/Makefile index be7520a863b0..8f5febaf1a9a 100644 --- a/tools/testing/selftests/arm64/signal/Makefile +++ b/tools/testing/selftests/arm64/signal/Makefile @@ -22,6 +22,10 @@ $(TEST_GEN_PROGS): $(PROGS) # Common test-unit targets to build common-layout test-cases executables # Needs secondary expansion to properly include the testcase c-file in pre-reqs +COMMON_SOURCES := test_signals.c test_signals_utils.c testcases/testcases.c \ + signals.S +COMMON_HEADERS := test_signals.h test_signals_utils.h testcases/testcases.h + .SECONDEXPANSION: -$(PROGS): test_signals.c test_signals_utils.c testcases/testcases.c signals.S $$@.c test_signals.h test_signals_utils.h testcases/testcases.h - $(CC) $(CFLAGS) $^ -o $@ +$(PROGS): $$@.c ${COMMON_SOURCES} ${COMMON_HEADERS} + $(CC) $(CFLAGS) ${@}.c ${COMMON_SOURCES} -o $@ diff --git a/tools/testing/selftests/arm64/signal/test_signals.c b/tools/testing/selftests/arm64/signal/test_signals.c index 416b1ff43199..00051b40d71e 100644 --- a/tools/testing/selftests/arm64/signal/test_signals.c +++ b/tools/testing/selftests/arm64/signal/test_signals.c @@ -12,12 +12,10 @@ #include "test_signals.h" #include "test_signals_utils.h" -struct tdescr *current; +struct tdescr *current = &tde; int main(int argc, char *argv[]) { - current = &tde; - ksft_print_msg("%s :: %s\n", current->name, current->descr); if (test_setup(current) && test_init(current)) { test_run(current); diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c index 07f518f0e58d..40be8443949d 100644 --- a/tools/testing/selftests/arm64/signal/test_signals_utils.c +++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c @@ -193,8 +193,10 @@ static bool handle_signal_copyctx(struct tdescr *td, * in the copy, this was previously validated in * ASSERT_GOOD_CONTEXT(). */ - to_copy = offset + sizeof(struct extra_context) + 16 + - extra->size; + to_copy = __builtin_offsetof(ucontext_t, + uc_mcontext.__reserved); + to_copy += offset + sizeof(struct extra_context) + 16; + to_copy += extra->size; copied_extra = (struct extra_context *)&(td->live_uc->uc_mcontext.__reserved[offset]); } else { copied_extra = NULL; diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c index d0a178945b1a..3d37daafcff5 100644 --- a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c +++ b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c @@ -34,6 +34,10 @@ static bool sme_get_vls(struct tdescr *td) vl &= PR_SME_VL_LEN_MASK; + /* Did we find the lowest supported VL? */ + if (vq < sve_vq_from_vl(vl)) + break; + /* Skip missing VLs */ vq = sve_vq_from_vl(vl); @@ -92,6 +96,11 @@ static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc, return 1; } + if (!(ssve->flags & SVE_SIG_FLAG_SM)) { + fprintf(stderr, "SVE_SIG_FLAG_SM not set in SVE record\n"); + return 1; + } + /* The actual size validation is done in get_current_context() */ fprintf(stderr, "Got expected size %u and VL %d\n", head->size, ssve->vl); @@ -116,12 +125,7 @@ static int sme_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc) struct tdescr tde = { .name = "Streaming SVE registers", .descr = "Check that we get the right Streaming SVE registers reported", - /* - * We shouldn't require FA64 but things like memset() used in the - * helpers might use unsupported instructions so for now disable - * the test unless we've got the full instruction set. - */ - .feats_required = FEAT_SME | FEAT_SME_FA64, + .feats_required = FEAT_SME, .timeout = 3, .init = sme_get_vls, .run = sme_regs, diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c new file mode 100644 index 000000000000..9dc5f128bbc0 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 ARM Limited + * + * Verify that both the streaming SVE and ZA register context in + * signal frames is set up as expected when enabled simultaneously. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/prctl.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +static union { + ucontext_t uc; + char buf[1024 * 128]; +} context; +static unsigned int vls[SVE_VQ_MAX]; +unsigned int nvls = 0; + +static bool sme_get_vls(struct tdescr *td) +{ + int vq, vl; + + /* + * Enumerate up to SVE_VQ_MAX vector lengths + */ + for (vq = SVE_VQ_MAX; vq > 0; --vq) { + vl = prctl(PR_SME_SET_VL, vq * 16); + if (vl == -1) + return false; + + vl &= PR_SME_VL_LEN_MASK; + + /* Did we find the lowest supported VL? */ + if (vq < sve_vq_from_vl(vl)) + break; + + /* Skip missing VLs */ + vq = sve_vq_from_vl(vl); + + vls[nvls++] = vl; + } + + /* We need at least one VL */ + if (nvls < 1) { + fprintf(stderr, "Only %d VL supported\n", nvls); + return false; + } + + return true; +} + +static void setup_regs(void) +{ + /* smstart sm; real data is TODO */ + asm volatile(".inst 0xd503437f" : : : ); + + /* smstart za; real data is TODO */ + asm volatile(".inst 0xd503457f" : : : ); +} + +static char zeros[ZA_SIG_REGS_SIZE(SVE_VQ_MAX)]; + +static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc, + unsigned int vl) +{ + size_t offset; + struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context); + struct _aarch64_ctx *regs; + struct sve_context *ssve; + struct za_context *za; + int ret; + + fprintf(stderr, "Testing VL %d\n", vl); + + ret = prctl(PR_SME_SET_VL, vl); + if (ret != vl) { + fprintf(stderr, "Failed to set VL, got %d\n", ret); + return 1; + } + + /* + * Get a signal context which should have the SVE and ZA + * frames in it. + */ + setup_regs(); + if (!get_current_context(td, &context.uc, sizeof(context))) + return 1; + + regs = get_header(head, SVE_MAGIC, GET_BUF_RESV_SIZE(context), + &offset); + if (!regs) { + fprintf(stderr, "No SVE context\n"); + return 1; + } + + ssve = (struct sve_context *)regs; + if (ssve->vl != vl) { + fprintf(stderr, "Got SSVE VL %d, expected %d\n", ssve->vl, vl); + return 1; + } + + if (!(ssve->flags & SVE_SIG_FLAG_SM)) { + fprintf(stderr, "SVE_SIG_FLAG_SM not set in SVE record\n"); + return 1; + } + + fprintf(stderr, "Got expected SSVE size %u and VL %d\n", + regs->size, ssve->vl); + + regs = get_header(head, ZA_MAGIC, GET_BUF_RESV_SIZE(context), + &offset); + if (!regs) { + fprintf(stderr, "No ZA context\n"); + return 1; + } + + za = (struct za_context *)regs; + if (za->vl != vl) { + fprintf(stderr, "Got ZA VL %d, expected %d\n", za->vl, vl); + return 1; + } + + fprintf(stderr, "Got expected ZA size %u and VL %d\n", + regs->size, za->vl); + + /* We didn't load any data into ZA so it should be all zeros */ + if (memcmp(zeros, (char *)za + ZA_SIG_REGS_OFFSET, + ZA_SIG_REGS_SIZE(sve_vq_from_vl(za->vl))) != 0) { + fprintf(stderr, "ZA data invalid\n"); + return 1; + } + + return 0; +} + +static int sme_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + int i; + + for (i = 0; i < nvls; i++) { + if (do_one_sme_vl(td, si, uc, vls[i])) + return 1; + } + + td->pass = 1; + + return 0; +} + +struct tdescr tde = { + .name = "Streaming SVE registers", + .descr = "Check that we get the right Streaming SVE registers reported", + .feats_required = FEAT_SME, + .timeout = 3, + .init = sme_get_vls, + .run = sme_regs, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c index 27d495fa52f8..9f580b55b388 100644 --- a/tools/testing/selftests/arm64/signal/testcases/testcases.c +++ b/tools/testing/selftests/arm64/signal/testcases/testcases.c @@ -184,6 +184,10 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err) if (head->size != sizeof(struct esr_context)) *err = "Bad size for esr_context"; break; + case TPIDR2_MAGIC: + if (head->size != sizeof(struct tpidr2_context)) + *err = "Bad size for tpidr2_context"; + break; case SVE_MAGIC: if (flags & SVE_CTX) *err = "Multiple SVE_MAGIC"; diff --git a/tools/testing/selftests/arm64/signal/testcases/tpidr2_siginfo.c b/tools/testing/selftests/arm64/signal/testcases/tpidr2_siginfo.c new file mode 100644 index 000000000000..6a2c82bf7ead --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/tpidr2_siginfo.c @@ -0,0 +1,90 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022 ARM Limited + * + * Verify that the TPIDR2 register context in signal frames is set up as + * expected. + */ + +#include <signal.h> +#include <ucontext.h> +#include <sys/auxv.h> +#include <sys/prctl.h> +#include <unistd.h> +#include <asm/sigcontext.h> + +#include "test_signals_utils.h" +#include "testcases.h" + +static union { + ucontext_t uc; + char buf[1024 * 128]; +} context; + +#define SYS_TPIDR2 "S3_3_C13_C0_5" + +static uint64_t get_tpidr2(void) +{ + uint64_t val; + + asm volatile ( + "mrs %0, " SYS_TPIDR2 "\n" + : "=r"(val) + : + : "cc"); + + return val; +} + +int tpidr2_present(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context); + struct tpidr2_context *tpidr2_ctx; + size_t offset; + bool in_sigframe; + bool have_sme; + __u64 orig_tpidr2; + + have_sme = getauxval(AT_HWCAP2) & HWCAP2_SME; + if (have_sme) + orig_tpidr2 = get_tpidr2(); + + if (!get_current_context(td, &context.uc, sizeof(context))) + return 1; + + tpidr2_ctx = (struct tpidr2_context *) + get_header(head, TPIDR2_MAGIC, td->live_sz, &offset); + + in_sigframe = tpidr2_ctx != NULL; + + fprintf(stderr, "TPIDR2 sigframe %s on system %s SME\n", + in_sigframe ? "present" : "absent", + have_sme ? "with" : "without"); + + td->pass = (in_sigframe == have_sme); + + /* + * Check that the value we read back was the one present at + * the time that the signal was triggered. TPIDR2 is owned by + * libc so we can't safely choose the value and it is possible + * that we may need to revisit this in future if something + * starts deciding to set a new TPIDR2 between us reading and + * the signal. + */ + if (have_sme && tpidr2_ctx) { + if (tpidr2_ctx->tpidr2 != orig_tpidr2) { + fprintf(stderr, "TPIDR2 in frame is %llx, was %llx\n", + tpidr2_ctx->tpidr2, orig_tpidr2); + td->pass = false; + } + } + + return 0; +} + +struct tdescr tde = { + .name = "TPIDR2", + .descr = "Validate that TPIDR2 is present as expected", + .timeout = 3, + .run = tpidr2_present, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/za_regs.c b/tools/testing/selftests/arm64/signal/testcases/za_regs.c index ea45acb115d5..174ad6656696 100644 --- a/tools/testing/selftests/arm64/signal/testcases/za_regs.c +++ b/tools/testing/selftests/arm64/signal/testcases/za_regs.c @@ -34,6 +34,10 @@ static bool sme_get_vls(struct tdescr *td) vl &= PR_SME_VL_LEN_MASK; + /* Did we find the lowest supported VL? */ + if (vq < sve_vq_from_vl(vl)) + break; + /* Skip missing VLs */ vq = sve_vq_from_vl(vl); |