diff options
62 files changed, 2647 insertions, 241 deletions
diff --git a/Documentation/arch/arm64/elf_hwcaps.rst b/Documentation/arch/arm64/elf_hwcaps.rst index ced7b335e2e0..448c1664879b 100644 --- a/Documentation/arch/arm64/elf_hwcaps.rst +++ b/Documentation/arch/arm64/elf_hwcaps.rst @@ -317,6 +317,55 @@ HWCAP2_LRCPC3 HWCAP2_LSE128 Functionality implied by ID_AA64ISAR0_EL1.Atomic == 0b0011. +HWCAP2_FPMR + Functionality implied by ID_AA64PFR2_EL1.FMR == 0b0001. + +HWCAP2_LUT + Functionality implied by ID_AA64ISAR2_EL1.LUT == 0b0001. + +HWCAP2_FAMINMAX + Functionality implied by ID_AA64ISAR3_EL1.FAMINMAX == 0b0001. + +HWCAP2_F8CVT + Functionality implied by ID_AA64FPFR0_EL1.F8CVT == 0b1. + +HWCAP2_F8FMA + Functionality implied by ID_AA64FPFR0_EL1.F8FMA == 0b1. + +HWCAP2_F8DP4 + Functionality implied by ID_AA64FPFR0_EL1.F8DP4 == 0b1. + +HWCAP2_F8DP2 + Functionality implied by ID_AA64FPFR0_EL1.F8DP2 == 0b1. + +HWCAP2_F8E4M3 + Functionality implied by ID_AA64FPFR0_EL1.F8E4M3 == 0b1. + +HWCAP2_F8E5M2 + Functionality implied by ID_AA64FPFR0_EL1.F8E5M2 == 0b1. + +HWCAP2_SME_LUTV2 + Functionality implied by ID_AA64SMFR0_EL1.LUTv2 == 0b1. + +HWCAP2_SME_F8F16 + Functionality implied by ID_AA64SMFR0_EL1.F8F16 == 0b1. + +HWCAP2_SME_F8F32 + Functionality implied by ID_AA64SMFR0_EL1.F8F32 == 0b1. + +HWCAP2_SME_SF8FMA + Functionality implied by ID_AA64SMFR0_EL1.SF8FMA == 0b1. + +HWCAP2_SME_SF8DP4 + Functionality implied by ID_AA64SMFR0_EL1.SF8DP4 == 0b1. + +HWCAP2_SME_SF8DP2 + Functionality implied by ID_AA64SMFR0_EL1.SF8DP2 == 0b1. + +HWCAP2_SME_SF8DP4 + Functionality implied by ID_AA64SMFR0_EL1.SF8DP4 == 0b1. + + 4. Unused AT_HWCAP bits ----------------------- diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst index e8c2ce1f9df6..fa16b895c997 100644 --- a/Documentation/arch/arm64/silicon-errata.rst +++ b/Documentation/arch/arm64/silicon-errata.rst @@ -35,8 +35,9 @@ can be triggered by Linux). For software workarounds that may adversely impact systems unaffected by the erratum in question, a Kconfig entry is added under "Kernel Features" -> "ARM errata workarounds via the alternatives framework". -These are enabled by default and patched in at runtime when an affected -CPU is detected. For less-intrusive workarounds, a Kconfig option is not +With the exception of workarounds for errata deemed "rare" by Arm, these +are enabled by default and patched in at runtime when an affected CPU is +detected. For less-intrusive workarounds, a Kconfig option is not available and the code is structured (preferably with a comment) in such a way that the erratum will not be hit. diff --git a/Documentation/arch/arm64/sme.rst b/Documentation/arch/arm64/sme.rst index 3d0e53ecac4f..be317d457417 100644 --- a/Documentation/arch/arm64/sme.rst +++ b/Documentation/arch/arm64/sme.rst @@ -75,7 +75,7 @@ model features for SME is included in Appendix A. 2. Vector lengths ------------------ -SME defines a second vector length similar to the SVE vector length which is +SME defines a second vector length similar to the SVE vector length which controls the size of the streaming mode SVE vectors and the ZA matrix array. The ZA matrix is square with each side having as many bytes as a streaming mode SVE vector. @@ -238,12 +238,12 @@ prctl(PR_SME_SET_VL, unsigned long arg) bits of Z0..Z31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become unspecified, including both streaming and non-streaming SVE state. Calling PR_SME_SET_VL with vl equal to the thread's current vector - length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag, + length, or calling PR_SME_SET_VL with the PR_SME_SET_VL_ONEXEC flag, does not constitute a change to the vector length for this purpose. * Changing the vector length causes PSTATE.ZA and PSTATE.SM to be cleared. Calling PR_SME_SET_VL with vl equal to the thread's current vector - length, or calling PR_SME_SET_VL with the PR_SVE_SET_VL_ONEXEC flag, + length, or calling PR_SME_SET_VL with the PR_SME_SET_VL_ONEXEC flag, does not constitute a change to the vector length for this purpose. @@ -379,9 +379,8 @@ The regset data starts with struct user_za_header, containing: /proc/sys/abi/sme_default_vector_length Writing the text representation of an integer to this file sets the system - default vector length to the specified value, unless the value is greater - than the maximum vector length supported by the system in which case the - default vector length is set to that maximum. + default vector length to the specified value rounded to a supported value + using the same rules as for setting vector length via PR_SME_SET_VL. The result can be determined by reopening the file and reading its contents. diff --git a/Documentation/arch/arm64/sve.rst b/Documentation/arch/arm64/sve.rst index 0d9a426e9f85..8d8837fc39ec 100644 --- a/Documentation/arch/arm64/sve.rst +++ b/Documentation/arch/arm64/sve.rst @@ -117,11 +117,6 @@ the SVE instruction set architecture. * The SVE registers are not used to pass arguments to or receive results from any syscall. -* In practice the affected registers/bits will be preserved or will be replaced - with zeros on return from a syscall, but userspace should not make - assumptions about this. The kernel behaviour may vary on a case-by-case - basis. - * All other SVE state of a thread, including the currently configured vector length, the state of the PR_SVE_VL_INHERIT flag, and the deferred vector length (if any), is preserved across all syscalls, subject to the specific @@ -428,9 +423,8 @@ The regset data starts with struct user_sve_header, containing: /proc/sys/abi/sve_default_vector_length Writing the text representation of an integer to this file sets the system - default vector length to the specified value, unless the value is greater - than the maximum vector length supported by the system in which case the - default vector length is set to that maximum. + default vector length to the specified value rounded to a supported value + using the same rules as for setting vector length via PR_SVE_SET_VL. The result can be determined by reopening the file and reading its contents. diff --git a/Documentation/rust/arch-support.rst b/Documentation/rust/arch-support.rst index 73203ba1e901..5c4fa9f5d1cd 100644 --- a/Documentation/rust/arch-support.rst +++ b/Documentation/rust/arch-support.rst @@ -15,6 +15,7 @@ support corresponds to ``S`` values in the ``MAINTAINERS`` file. ============= ================ ============================================== Architecture Level of support Constraints ============= ================ ============================================== +``arm64`` Maintained Little Endian only. ``loongarch`` Maintained - ``um`` Maintained ``x86_64`` only. ``x86`` Maintained ``x86_64`` only. @@ -561,7 +561,6 @@ KBUILD_CFLAGS += -fno-strict-aliasing KBUILD_CPPFLAGS := -D__KERNEL__ KBUILD_RUSTFLAGS := $(rust_common_flags) \ - --target=$(objtree)/scripts/target.json \ -Cpanic=abort -Cembed-bitcode=n -Clto=n \ -Cforce-unwind-tables=n -Ccodegen-units=1 \ -Csymbol-mangling-version=v0 \ diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index aa7c1d435139..e14e92eb5ba5 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -120,6 +120,7 @@ config ARM64 select CLONE_BACKWARDS select COMMON_CLK select CPU_PM if (SUSPEND || CPU_IDLE) + select CPUMASK_OFFSTACK if NR_CPUS > 256 select CRC32 select DCACHE_WORD_ACCESS select DYNAMIC_FTRACE if FUNCTION_TRACER @@ -198,7 +199,7 @@ config ARM64 if DYNAMIC_FTRACE_WITH_ARGS && DYNAMIC_FTRACE_WITH_CALL_OPS select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS \ if (DYNAMIC_FTRACE_WITH_ARGS && !CFI_CLANG && \ - !CC_OPTIMIZE_FOR_SIZE) + (CC_IS_CLANG || !CC_OPTIMIZE_FOR_SIZE)) select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ if DYNAMIC_FTRACE_WITH_ARGS select HAVE_SAMPLE_FTRACE_DIRECT @@ -229,6 +230,7 @@ config ARM64 select HAVE_FUNCTION_ARG_ACCESS_API select MMU_GATHER_RCU_TABLE_FREE select HAVE_RSEQ + select HAVE_RUST if CPU_LITTLE_ENDIAN select HAVE_STACKPROTECTOR select HAVE_SYSCALL_TRACEPOINTS select HAVE_KPROBES @@ -547,9 +549,8 @@ config ARM64_ERRATUM_832075 If unsure, say Y. config ARM64_ERRATUM_834220 - bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault" + bool "Cortex-A57: 834220: Stage 2 translation fault might be incorrectly reported in presence of a Stage 1 fault (rare)" depends on KVM - default y help This option adds an alternative code sequence to work around ARM erratum 834220 on Cortex-A57 parts up to r1p2. @@ -565,7 +566,7 @@ config ARM64_ERRATUM_834220 as it depends on the alternative framework, which will only patch the kernel if an affected CPU is detected. - If unsure, say Y. + If unsure, say N. config ARM64_ERRATUM_1742098 bool "Cortex-A57/A72: 1742098: ELR recorded incorrectly on interrupt taken between cryptographic instructions in a sequence" @@ -692,8 +693,7 @@ config ARM64_WORKAROUND_REPEAT_TLBI bool config ARM64_ERRATUM_2441007 - bool "Cortex-A55: Completion of affected memory accesses might not be guaranteed by completion of a TLBI" - default y + bool "Cortex-A55: Completion of affected memory accesses might not be guaranteed by completion of a TLBI (rare)" select ARM64_WORKAROUND_REPEAT_TLBI help This option adds a workaround for ARM Cortex-A55 erratum #2441007. @@ -706,11 +706,10 @@ config ARM64_ERRATUM_2441007 Work around this by adding the affected CPUs to the list that needs TLB sequences to be done twice. - If unsure, say Y. + If unsure, say N. config ARM64_ERRATUM_1286807 - bool "Cortex-A76: Modification of the translation table for a virtual address might lead to read-after-read ordering violation" - default y + bool "Cortex-A76: Modification of the translation table for a virtual address might lead to read-after-read ordering violation (rare)" select ARM64_WORKAROUND_REPEAT_TLBI help This option adds a workaround for ARM Cortex-A76 erratum 1286807. @@ -724,6 +723,8 @@ config ARM64_ERRATUM_1286807 invalidated has been observed by other observers. The workaround repeats the TLBI+DSB operation. + If unsure, say N. + config ARM64_ERRATUM_1463225 bool "Cortex-A76: Software Step might prevent interrupt recognition" default y @@ -743,8 +744,7 @@ config ARM64_ERRATUM_1463225 If unsure, say Y. config ARM64_ERRATUM_1542419 - bool "Neoverse-N1: workaround mis-ordering of instruction fetches" - default y + bool "Neoverse-N1: workaround mis-ordering of instruction fetches (rare)" help This option adds a workaround for ARM Neoverse-N1 erratum 1542419. @@ -756,7 +756,7 @@ config ARM64_ERRATUM_1542419 Workaround the issue by hiding the DIC feature from EL0. This forces user-space to perform cache maintenance. - If unsure, say Y. + If unsure, say N. config ARM64_ERRATUM_1508412 bool "Cortex-A77: 1508412: workaround deadlock on sequence of NC/Device load and store exclusive or PAR read" @@ -931,8 +931,7 @@ config ARM64_ERRATUM_2224489 If unsure, say Y. config ARM64_ERRATUM_2441009 - bool "Cortex-A510: Completion of affected memory accesses might not be guaranteed by completion of a TLBI" - default y + bool "Cortex-A510: Completion of affected memory accesses might not be guaranteed by completion of a TLBI (rare)" select ARM64_WORKAROUND_REPEAT_TLBI help This option adds a workaround for ARM Cortex-A510 erratum #2441009. @@ -945,7 +944,7 @@ config ARM64_ERRATUM_2441009 Work around this by adding the affected CPUs to the list that needs TLB sequences to be done twice. - If unsure, say Y. + If unsure, say N. config ARM64_ERRATUM_2064142 bool "Cortex-A510: 2064142: workaround TRBE register writes while disabled" @@ -1427,7 +1426,7 @@ config SCHED_SMT config NR_CPUS int "Maximum number of CPUs (2-4096)" range 2 4096 - default "256" + default "512" config HOTPLUG_CPU bool "Support for hot-pluggable CPUs" diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index a88cdf910687..0e075d3c546b 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -41,6 +41,8 @@ KBUILD_CFLAGS += -mgeneral-regs-only \ KBUILD_CFLAGS += $(call cc-disable-warning, psabi) KBUILD_AFLAGS += $(compat_vdso) +KBUILD_RUSTFLAGS += --target=aarch64-unknown-none -Ctarget-feature="-neon" + KBUILD_CFLAGS += $(call cc-option,-mabi=lp64) KBUILD_AFLAGS += $(call cc-option,-mabi=lp64) @@ -65,7 +67,9 @@ endif ifeq ($(CONFIG_ARM64_BTI_KERNEL),y) KBUILD_CFLAGS += -mbranch-protection=pac-ret+bti + KBUILD_RUSTFLAGS += -Zbranch-protection=bti,pac-ret else ifeq ($(CONFIG_ARM64_PTR_AUTH_KERNEL),y) + KBUILD_RUSTFLAGS += -Zbranch-protection=pac-ret ifeq ($(CONFIG_CC_HAS_BRANCH_PROT_PAC_RET),y) KBUILD_CFLAGS += -mbranch-protection=pac-ret else diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 513787e43329..96b18a707507 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -38,10 +38,6 @@ msr daifset, #0xf .endm - .macro enable_daif - msr daifclr, #0xf - .endm - /* * Save/restore interrupts. */ diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h index 1abdcd508a11..beb42c62b6ac 100644 --- a/arch/arm64/include/asm/brk-imm.h +++ b/arch/arm64/include/asm/brk-imm.h @@ -11,6 +11,7 @@ * 0x004: for installing kprobes * 0x005: for installing uprobes * 0x006: for kprobe software single-step + * 0x007: for kretprobe return * Allowed values for kgdb are 0x400 - 0x7ff * 0x100: for triggering a fault on purpose (reserved) * 0x400: for dynamic BRK instruction @@ -23,6 +24,7 @@ #define KPROBES_BRK_IMM 0x004 #define UPROBES_BRK_IMM 0x005 #define KPROBES_BRK_SS_IMM 0x006 +#define KRETPROBES_BRK_IMM 0x007 #define FAULT_BRK_IMM 0x100 #define KGDB_DYN_DBG_BRK_IMM 0x400 #define KGDB_COMPILED_DBG_BRK_IMM 0x401 diff --git a/arch/arm64/include/asm/cpu.h b/arch/arm64/include/asm/cpu.h index b1e43f56ee46..96379be913cd 100644 --- a/arch/arm64/include/asm/cpu.h +++ b/arch/arm64/include/asm/cpu.h @@ -52,14 +52,17 @@ struct cpuinfo_arm64 { u64 reg_id_aa64isar0; u64 reg_id_aa64isar1; u64 reg_id_aa64isar2; + u64 reg_id_aa64isar3; u64 reg_id_aa64mmfr0; u64 reg_id_aa64mmfr1; u64 reg_id_aa64mmfr2; u64 reg_id_aa64mmfr3; u64 reg_id_aa64pfr0; u64 reg_id_aa64pfr1; + u64 reg_id_aa64pfr2; u64 reg_id_aa64zfr0; u64 reg_id_aa64smfr0; + u64 reg_id_aa64fpfr0; struct cpuinfo_32bit aarch32; }; diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 21c824edf8ce..34fcdbc65d7d 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -768,6 +768,11 @@ static __always_inline bool system_supports_tpidr2(void) return system_supports_sme(); } +static __always_inline bool system_supports_fpmr(void) +{ + return alternative_has_cap_unlikely(ARM64_HAS_FPMR); +} + static __always_inline bool system_supports_cnp(void) { return alternative_has_cap_unlikely(ARM64_HAS_CNP); diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h index 97932fbf973d..3f93f4eef953 100644 --- a/arch/arm64/include/asm/elf.h +++ b/arch/arm64/include/asm/elf.h @@ -201,16 +201,16 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm, #define COMPAT_ELF_PLATFORM ("v8l") #endif -#ifdef CONFIG_COMPAT - -/* PIE load location for compat arm. Must match ARM ELF_ET_DYN_BASE. */ -#define COMPAT_ELF_ET_DYN_BASE 0x000400000UL - /* AArch32 registers. */ #define COMPAT_ELF_NGREG 18 typedef unsigned int compat_elf_greg_t; typedef compat_elf_greg_t compat_elf_gregset_t[COMPAT_ELF_NGREG]; +#ifdef CONFIG_COMPAT + +/* PIE load location for compat arm. Must match ARM ELF_ET_DYN_BASE. */ +#define COMPAT_ELF_ET_DYN_BASE 0x000400000UL + /* AArch32 EABI. */ #define EF_ARM_EABI_MASK 0xff000000 int compat_elf_check_arch(const struct elf32_hdr *); diff --git a/arch/arm64/include/asm/exception.h b/arch/arm64/include/asm/exception.h index ad688e157c9b..f296662590c7 100644 --- a/arch/arm64/include/asm/exception.h +++ b/arch/arm64/include/asm/exception.h @@ -74,7 +74,7 @@ void do_el0_fpac(struct pt_regs *regs, unsigned long esr); void do_el1_fpac(struct pt_regs *regs, unsigned long esr); void do_el0_mops(struct pt_regs *regs, unsigned long esr); void do_serror(struct pt_regs *regs, unsigned long esr); -void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags); +void do_signal(struct pt_regs *regs); void __noreturn panic_bad_stack(struct pt_regs *regs, unsigned long esr, unsigned long far); #endif /* __ASM_EXCEPTION_H */ diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 50e5f25d3024..47cbd1da40b4 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -21,7 +21,6 @@ #include <linux/stddef.h> #include <linux/types.h> -#ifdef CONFIG_COMPAT /* Masks for extracting the FPSR and FPCR from the FPSCR */ #define VFP_FPSCR_STAT_MASK 0xf800009f #define VFP_FPSCR_CTRL_MASK 0x07f79f00 @@ -30,7 +29,6 @@ * control/status register. */ #define VFP_STATE_SIZE ((32 * 8) + 4) -#endif static inline unsigned long cpacr_save_enable_kernel_sve(void) { @@ -89,6 +87,7 @@ struct cpu_fp_state { void *sve_state; void *sme_state; u64 *svcr; + u64 *fpmr; unsigned int sve_vl; unsigned int sme_vl; enum fp_type *fp_type; @@ -154,6 +153,7 @@ extern void cpu_enable_sve(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sme(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sme2(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_fa64(const struct arm64_cpu_capabilities *__unused); +extern void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__unused); extern u64 read_smcr_features(void); diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h index 84055329cd8b..bd81cf17744a 100644 --- a/arch/arm64/include/asm/hw_breakpoint.h +++ b/arch/arm64/include/asm/hw_breakpoint.h @@ -59,7 +59,6 @@ static inline void decode_ctrl_reg(u32 reg, /* Watchpoints */ #define ARM_BREAKPOINT_LOAD 1 #define ARM_BREAKPOINT_STORE 2 -#define AARCH64_ESR_ACCESS_MASK (1 << 6) /* Lengths */ #define ARM_BREAKPOINT_LEN_1 0x1 diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index cd71e09ea14d..4edd3b61df11 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -142,6 +142,21 @@ #define KERNEL_HWCAP_SVE_B16B16 __khwcap2_feature(SVE_B16B16) #define KERNEL_HWCAP_LRCPC3 __khwcap2_feature(LRCPC3) #define KERNEL_HWCAP_LSE128 __khwcap2_feature(LSE128) +#define KERNEL_HWCAP_FPMR __khwcap2_feature(FPMR) +#define KERNEL_HWCAP_LUT __khwcap2_feature(LUT) +#define KERNEL_HWCAP_FAMINMAX __khwcap2_feature(FAMINMAX) +#define KERNEL_HWCAP_F8CVT __khwcap2_feature(F8CVT) +#define KERNEL_HWCAP_F8FMA __khwcap2_feature(F8FMA) +#define KERNEL_HWCAP_F8DP4 __khwcap2_feature(F8DP4) +#define KERNEL_HWCAP_F8DP2 __khwcap2_feature(F8DP2) +#define KERNEL_HWCAP_F8E4M3 __khwcap2_feature(F8E4M3) +#define KERNEL_HWCAP_F8E5M2 __khwcap2_feature(F8E5M2) +#define KERNEL_HWCAP_SME_LUTV2 __khwcap2_feature(SME_LUTV2) +#define KERNEL_HWCAP_SME_F8F16 __khwcap2_feature(SME_F8F16) +#define KERNEL_HWCAP_SME_F8F32 __khwcap2_feature(SME_F8F32) +#define KERNEL_HWCAP_SME_SF8FMA __khwcap2_feature(SME_SF8FMA) +#define KERNEL_HWCAP_SME_SF8DP4 __khwcap2_feature(SME_SF8DP4) +#define KERNEL_HWCAP_SME_SF8DP2 __khwcap2_feature(SME_SF8DP2) /* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h index 3b694511b98f..8d825522c55c 100644 --- a/arch/arm64/include/asm/io.h +++ b/arch/arm64/include/asm/io.h @@ -24,25 +24,29 @@ #define __raw_writeb __raw_writeb static __always_inline void __raw_writeb(u8 val, volatile void __iomem *addr) { - asm volatile("strb %w0, [%1]" : : "rZ" (val), "r" (addr)); + volatile u8 __iomem *ptr = addr; + asm volatile("strb %w0, %1" : : "rZ" (val), "Qo" (*ptr)); } #define __raw_writew __raw_writew static __always_inline void __raw_writew(u16 val, volatile void __iomem *addr) { - asm volatile("strh %w0, [%1]" : : "rZ" (val), "r" (addr)); + volatile u16 __iomem *ptr = addr; + asm volatile("strh %w0, %1" : : "rZ" (val), "Qo" (*ptr)); } #define __raw_writel __raw_writel static __always_inline void __raw_writel(u32 val, volatile void __iomem *addr) { - asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr)); + volatile u32 __iomem *ptr = addr; + asm volatile("str %w0, %1" : : "rZ" (val), "Qo" (*ptr)); } #define __raw_writeq __raw_writeq static __always_inline void __raw_writeq(u64 val, volatile void __iomem *addr) { - asm volatile("str %x0, [%1]" : : "rZ" (val), "r" (addr)); + volatile u64 __iomem *ptr = addr; + asm volatile("str %x0, %1" : : "rZ" (val), "Qo" (*ptr)); } #define __raw_readb __raw_readb diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 3c6f8ba1e479..7f45ce9170bb 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -105,7 +105,7 @@ #define HCRX_GUEST_FLAGS \ (HCRX_EL2_SMPME | HCRX_EL2_TCR2En | \ (cpus_have_final_cap(ARM64_HAS_MOPS) ? (HCRX_EL2_MSCEn | HCRX_EL2_MCE2) : 0)) -#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En) +#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM) /* TCR_EL2 Registers bits */ #define TCR_EL2_DS (1UL << 32) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 21c57b812569..b779cbc2211c 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -543,6 +543,7 @@ struct kvm_vcpu_arch { enum fp_type fp_type; unsigned int sve_max_vl; u64 svcr; + u64 fpmr; /* Stage 2 paging state used by the hardware on next switch */ struct kvm_s2_mmu *hw_mmu; diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index d82305ab420f..60904a6c4b42 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -30,8 +30,8 @@ * keep a constant PAGE_OFFSET and "fallback" to using the higher end * of the VMEMMAP where 52-bit support is not available in hardware. */ -#define VMEMMAP_SHIFT (PAGE_SHIFT - STRUCT_PAGE_MAX_SHIFT) -#define VMEMMAP_SIZE ((_PAGE_END(VA_BITS_MIN) - PAGE_OFFSET) >> VMEMMAP_SHIFT) +#define VMEMMAP_RANGE (_PAGE_END(VA_BITS_MIN) - PAGE_OFFSET) +#define VMEMMAP_SIZE ((VMEMMAP_RANGE >> PAGE_SHIFT) * sizeof(struct page)) /* * PAGE_OFFSET - the virtual address of the start of the linear map, at the @@ -47,11 +47,11 @@ #define MODULES_END (MODULES_VADDR + MODULES_VSIZE) #define MODULES_VADDR (_PAGE_END(VA_BITS_MIN)) #define MODULES_VSIZE (SZ_2G) -#define VMEMMAP_START (-(UL(1) << (VA_BITS - VMEMMAP_SHIFT))) -#define VMEMMAP_END (VMEMMAP_START + VMEMMAP_SIZE) -#define PCI_IO_END (VMEMMAP_START - SZ_8M) -#define PCI_IO_START (PCI_IO_END - PCI_IO_SIZE) -#define FIXADDR_TOP (VMEMMAP_START - SZ_32M) +#define VMEMMAP_START (VMEMMAP_END - VMEMMAP_SIZE) +#define VMEMMAP_END (-UL(SZ_1G)) +#define PCI_IO_START (VMEMMAP_END + SZ_8M) +#define PCI_IO_END (PCI_IO_START + PCI_IO_SIZE) +#define FIXADDR_TOP (-UL(SZ_8M)) #if VA_BITS > 48 #define VA_BITS_MIN (48) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 79ce70fbb751..522c21348ae8 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -18,11 +18,15 @@ * VMALLOC range. * * VMALLOC_START: beginning of the kernel vmalloc space - * VMALLOC_END: extends to the available space below vmemmap, PCI I/O space - * and fixed mappings + * VMALLOC_END: extends to the available space below vmemmap */ #define VMALLOC_START (MODULES_END) -#define VMALLOC_END (VMEMMAP_START - SZ_256M) +#if VA_BITS == VA_BITS_MIN +#define VMALLOC_END (VMEMMAP_START - SZ_8M) +#else +#define VMEMMAP_UNUSED_NPAGES ((_PAGE_OFFSET(vabits_actual) - PAGE_OFFSET) >> PAGE_SHIFT) +#define VMALLOC_END (VMEMMAP_START + VMEMMAP_UNUSED_NPAGES * sizeof(struct page) - SZ_8M) +#endif #define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 5b0a04810b23..f77371232d8c 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -155,6 +155,8 @@ struct thread_struct { struct { unsigned long tp_value; /* TLS register */ unsigned long tp2_value; + u64 fpmr; + unsigned long pad; struct user_fpsimd_state fpsimd_state; } uw; @@ -253,6 +255,8 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset, BUILD_BUG_ON(sizeof_field(struct thread_struct, uw) != sizeof_field(struct thread_struct, uw.tp_value) + sizeof_field(struct thread_struct, uw.tp2_value) + + sizeof_field(struct thread_struct, uw.fpmr) + + sizeof_field(struct thread_struct, uw.pad) + sizeof_field(struct thread_struct, uw.fpsimd_state)); *offset = offsetof(struct thread_struct, uw); diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 5023599fa278..285610e626f5 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -107,5 +107,20 @@ #define HWCAP2_SVE_B16B16 (1UL << 45) #define HWCAP2_LRCPC3 (1UL << 46) #define HWCAP2_LSE128 (1UL << 47) +#define HWCAP2_FPMR (1UL << 48) +#define HWCAP2_LUT (1UL << 49) +#define HWCAP2_FAMINMAX (1UL << 50) +#define HWCAP2_F8CVT (1UL << 51) +#define HWCAP2_F8FMA (1UL << 52) +#define HWCAP2_F8DP4 (1UL << 53) +#define HWCAP2_F8DP2 (1UL << 54) +#define HWCAP2_F8E4M3 (1UL << 55) +#define HWCAP2_F8E5M2 (1UL << 56) +#define HWCAP2_SME_LUTV2 (1UL << 57) +#define HWCAP2_SME_F8F16 (1UL << 58) +#define HWCAP2_SME_F8F32 (1UL << 59) +#define HWCAP2_SME_SF8FMA (1UL << 60) +#define HWCAP2_SME_SF8DP4 (1UL << 61) +#define HWCAP2_SME_SF8DP2 (1UL << 62) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index f23c1dc3f002..8a45b7a411e0 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -152,6 +152,14 @@ struct tpidr2_context { __u64 tpidr2; }; +/* FPMR context */ +#define FPMR_MAGIC 0x46504d52 + +struct fpmr_context { + struct _aarch64_ctx head; + __u64 fpmr; +}; + #define ZA_MAGIC 0x54366345 struct za_context { diff --git a/arch/arm64/include/uapi/asm/sve_context.h b/arch/arm64/include/uapi/asm/sve_context.h index 754ab751b523..72aefc081061 100644 --- a/arch/arm64/include/uapi/asm/sve_context.h +++ b/arch/arm64/include/uapi/asm/sve_context.h @@ -13,6 +13,17 @@ #define __SVE_VQ_BYTES 16 /* number of bytes per quadword */ +/* + * Yes, __SVE_VQ_MAX is 512 QUADWORDS. + * + * To help ensure forward portability, this is much larger than the + * current maximum value defined by the SVE architecture. While arrays + * or static allocations can be sized based on this value, watch out! + * It will waste a surprisingly large amount of memory. + * + * Dynamic sizing based on the actual runtime vector length is likely to + * be preferable for most purposes. + */ #define __SVE_VQ_MIN 1 #define __SVE_VQ_MAX 512 diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 5a7dbbe0ce63..81496083c041 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -75,8 +75,8 @@ int main(void) DEFINE(S_FP, offsetof(struct pt_regs, regs[29])); DEFINE(S_LR, offsetof(struct pt_regs, regs[30])); DEFINE(S_SP, offsetof(struct pt_regs, sp)); - DEFINE(S_PSTATE, offsetof(struct pt_regs, pstate)); DEFINE(S_PC, offsetof(struct pt_regs, pc)); + DEFINE(S_PSTATE, offsetof(struct pt_regs, pstate)); DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno)); DEFINE(S_SDEI_TTBR1, offsetof(struct pt_regs, sdei_ttbr1)); DEFINE(S_PMR_SAVE, offsetof(struct pt_regs, pmr_save)); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 8d1a634a403e..6e1cca7b2098 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -220,6 +220,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { }; static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_LUT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CLRBHB_SHIFT, 4, 0), @@ -234,6 +235,11 @@ static const struct arm64_ftr_bits ftr_id_aa64isar2[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_id_aa64isar3[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR3_EL1_FAMINMAX_SHIFT, 4, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_CSV3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_CSV2_SHIFT, 4, 0), @@ -267,6 +273,11 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_id_aa64pfr2[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR2_EL1_FPMR_SHIFT, 4, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_F64MM_SHIFT, 4, 0), @@ -295,6 +306,8 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_LUTv2_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SMEver_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I16I64_SHIFT, 4, 0), @@ -307,6 +320,10 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F16_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F8F16_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F8F32_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I8I32_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F16F32_SHIFT, 1, 0), @@ -316,6 +333,22 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_BI32I32_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_F32F32_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8FMA_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8DP4_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8DP2_SHIFT, 1, 0), + ARM64_FTR_END, +}; + +static const struct arm64_ftr_bits ftr_id_aa64fpfr0[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8CVT_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8FMA_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8DP4_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8DP2_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E4M3_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E5M2_SHIFT, 1, 0), ARM64_FTR_END, }; @@ -702,10 +735,12 @@ static const struct __ftr_reg_entry { &id_aa64pfr0_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1, &id_aa64pfr1_override), + ARM64_FTR_REG(SYS_ID_AA64PFR2_EL1, ftr_id_aa64pfr2), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0, &id_aa64zfr0_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64SMFR0_EL1, ftr_id_aa64smfr0, &id_aa64smfr0_override), + ARM64_FTR_REG(SYS_ID_AA64FPFR0_EL1, ftr_id_aa64fpfr0), /* Op1 = 0, CRn = 0, CRm = 5 */ ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0), @@ -717,6 +752,7 @@ static const struct __ftr_reg_entry { &id_aa64isar1_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64ISAR2_EL1, ftr_id_aa64isar2, &id_aa64isar2_override), + ARM64_FTR_REG(SYS_ID_AA64ISAR3_EL1, ftr_id_aa64isar3), /* Op1 = 0, CRn = 0, CRm = 7 */ ARM64_FTR_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0), @@ -1043,14 +1079,17 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) init_cpu_ftr_reg(SYS_ID_AA64ISAR0_EL1, info->reg_id_aa64isar0); init_cpu_ftr_reg(SYS_ID_AA64ISAR1_EL1, info->reg_id_aa64isar1); init_cpu_ftr_reg(SYS_ID_AA64ISAR2_EL1, info->reg_id_aa64isar2); + init_cpu_ftr_reg(SYS_ID_AA64ISAR3_EL1, info->reg_id_aa64isar3); init_cpu_ftr_reg(SYS_ID_AA64MMFR0_EL1, info->reg_id_aa64mmfr0); init_cpu_ftr_reg(SYS_ID_AA64MMFR1_EL1, info->reg_id_aa64mmfr1); init_cpu_ftr_reg(SYS_ID_AA64MMFR2_EL1, info->reg_id_aa64mmfr2); init_cpu_ftr_reg(SYS_ID_AA64MMFR3_EL1, info->reg_id_aa64mmfr3); init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0); init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1); + init_cpu_ftr_reg(SYS_ID_AA64PFR2_EL1, info->reg_id_aa64pfr2); init_cpu_ftr_reg(SYS_ID_AA64ZFR0_EL1, info->reg_id_aa64zfr0); init_cpu_ftr_reg(SYS_ID_AA64SMFR0_EL1, info->reg_id_aa64smfr0); + init_cpu_ftr_reg(SYS_ID_AA64FPFR0_EL1, info->reg_id_aa64fpfr0); if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) init_32bit_cpu_features(&info->aarch32); @@ -1272,6 +1311,8 @@ void update_cpu_features(int cpu, info->reg_id_aa64isar1, boot->reg_id_aa64isar1); taint |= check_update_ftr_reg(SYS_ID_AA64ISAR2_EL1, cpu, info->reg_id_aa64isar2, boot->reg_id_aa64isar2); + taint |= check_update_ftr_reg(SYS_ID_AA64ISAR3_EL1, cpu, + info->reg_id_aa64isar3, boot->reg_id_aa64isar3); /* * Differing PARange support is fine as long as all peripherals and @@ -1291,6 +1332,8 @@ void update_cpu_features(int cpu, info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0); taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu, info->reg_id_aa64pfr1, boot->reg_id_aa64pfr1); + taint |= check_update_ftr_reg(SYS_ID_AA64PFR2_EL1, cpu, + info->reg_id_aa64pfr2, boot->reg_id_aa64pfr2); taint |= check_update_ftr_reg(SYS_ID_AA64ZFR0_EL1, cpu, info->reg_id_aa64zfr0, boot->reg_id_aa64zfr0); @@ -1298,6 +1341,9 @@ void update_cpu_features(int cpu, taint |= check_update_ftr_reg(SYS_ID_AA64SMFR0_EL1, cpu, info->reg_id_aa64smfr0, boot->reg_id_aa64smfr0); + taint |= check_update_ftr_reg(SYS_ID_AA64FPFR0_EL1, cpu, + info->reg_id_aa64fpfr0, boot->reg_id_aa64fpfr0); + /* Probe vector lengths */ if (IS_ENABLED(CONFIG_ARM64_SVE) && id_aa64pfr0_sve(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1))) { @@ -1410,8 +1456,10 @@ u64 __read_sysreg_by_encoding(u32 sys_id) read_sysreg_case(SYS_ID_AA64PFR0_EL1); read_sysreg_case(SYS_ID_AA64PFR1_EL1); + read_sysreg_case(SYS_ID_AA64PFR2_EL1); read_sysreg_case(SYS_ID_AA64ZFR0_EL1); read_sysreg_case(SYS_ID_AA64SMFR0_EL1); + read_sysreg_case(SYS_ID_AA64FPFR0_EL1); read_sysreg_case(SYS_ID_AA64DFR0_EL1); read_sysreg_case(SYS_ID_AA64DFR1_EL1); read_sysreg_case(SYS_ID_AA64MMFR0_EL1); @@ -1421,6 +1469,7 @@ u64 __read_sysreg_by_encoding(u32 sys_id) read_sysreg_case(SYS_ID_AA64ISAR0_EL1); read_sysreg_case(SYS_ID_AA64ISAR1_EL1); read_sysreg_case(SYS_ID_AA64ISAR2_EL1); + read_sysreg_case(SYS_ID_AA64ISAR3_EL1); read_sysreg_case(SYS_CNTFRQ_EL0); read_sysreg_case(SYS_CTR_EL0); @@ -2739,6 +2788,14 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_lpa2, }, + { + .desc = "FPMR", + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .capability = ARM64_HAS_FPMR, + .matches = has_cpuid_feature, + .cpu_enable = cpu_enable_fpmr, + ARM64_CPUID_FIELDS(ID_AA64PFR2_EL1, FPMR, IMP) + }, {}, }; @@ -2822,6 +2879,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMD), HWCAP_CAP(ID_AA64PFR0_EL1, AdvSIMD, FP16, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP), HWCAP_CAP(ID_AA64PFR0_EL1, DIT, IMP, CAP_HWCAP, KERNEL_HWCAP_DIT), + HWCAP_CAP(ID_AA64PFR2_EL1, FPMR, IMP, CAP_HWCAP, KERNEL_HWCAP_FPMR), HWCAP_CAP(ID_AA64ISAR1_EL1, DPB, IMP, CAP_HWCAP, KERNEL_HWCAP_DCPOP), HWCAP_CAP(ID_AA64ISAR1_EL1, DPB, DPB2, CAP_HWCAP, KERNEL_HWCAP_DCPODP), HWCAP_CAP(ID_AA64ISAR1_EL1, JSCVT, IMP, CAP_HWCAP, KERNEL_HWCAP_JSCVT), @@ -2835,6 +2893,8 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR1_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_EBF16), HWCAP_CAP(ID_AA64ISAR1_EL1, DGH, IMP, CAP_HWCAP, KERNEL_HWCAP_DGH), HWCAP_CAP(ID_AA64ISAR1_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_I8MM), + HWCAP_CAP(ID_AA64ISAR2_EL1, LUT, IMP, CAP_HWCAP, KERNEL_HWCAP_LUT), + HWCAP_CAP(ID_AA64ISAR3_EL1, FAMINMAX, IMP, CAP_HWCAP, KERNEL_HWCAP_FAMINMAX), HWCAP_CAP(ID_AA64MMFR2_EL1, AT, IMP, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE HWCAP_CAP(ID_AA64PFR0_EL1, SVE, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE), @@ -2875,6 +2935,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { #ifdef CONFIG_ARM64_SME HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME), HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), + HWCAP_CAP(ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2), HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1), HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2), HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64), @@ -2882,12 +2943,23 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64SMFR0_EL1, I16I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I32), HWCAP_CAP(ID_AA64SMFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16B16), HWCAP_CAP(ID_AA64SMFR0_EL1, F16F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F16), + HWCAP_CAP(ID_AA64SMFR0_EL1, F8F16, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F16), + HWCAP_CAP(ID_AA64SMFR0_EL1, F8F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F8F32), HWCAP_CAP(ID_AA64SMFR0_EL1, I8I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I8I32), HWCAP_CAP(ID_AA64SMFR0_EL1, F16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F16F32), HWCAP_CAP(ID_AA64SMFR0_EL1, B16F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_B16F32), HWCAP_CAP(ID_AA64SMFR0_EL1, BI32I32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_BI32I32), HWCAP_CAP(ID_AA64SMFR0_EL1, F32F32, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_F32F32), + HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA), + HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4), + HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2), #endif /* CONFIG_ARM64_SME */ + HWCAP_CAP(ID_AA64FPFR0_EL1, F8CVT, IMP, CAP_HWCAP, KERNEL_HWCAP_F8CVT), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP4), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP2), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8E4M3, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E4M3), + HWCAP_CAP(ID_AA64FPFR0_EL1, F8E5M2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E5M2), {}, }; @@ -3052,13 +3124,9 @@ static void __init enable_cpu_capabilities(u16 scope_mask) boot_scope = !!(scope_mask & SCOPE_BOOT_CPU); for (i = 0; i < ARM64_NCAPS; i++) { - unsigned int num; - caps = cpucap_ptrs[i]; - if (!caps || !(caps->type & scope_mask)) - continue; - num = caps->capability; - if (!cpus_have_cap(num)) + if (!caps || !(caps->type & scope_mask) || + !cpus_have_cap(caps->capability)) continue; if (boot_scope && caps->cpu_enable) diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 47043c0d95ec..f0abb150f73e 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -128,6 +128,21 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_SVE_B16B16] = "sveb16b16", [KERNEL_HWCAP_LRCPC3] = "lrcpc3", [KERNEL_HWCAP_LSE128] = "lse128", + [KERNEL_HWCAP_FPMR] = "fpmr", + [KERNEL_HWCAP_LUT] = "lut", + [KERNEL_HWCAP_FAMINMAX] = "faminmax", + [KERNEL_HWCAP_F8CVT] = "f8cvt", + [KERNEL_HWCAP_F8FMA] = "f8fma", + [KERNEL_HWCAP_F8DP4] = "f8dp4", + [KERNEL_HWCAP_F8DP2] = "f8dp2", + [KERNEL_HWCAP_F8E4M3] = "f8e4m3", + [KERNEL_HWCAP_F8E5M2] = "f8e5m2", + [KERNEL_HWCAP_SME_LUTV2] = "smelutv2", + [KERNEL_HWCAP_SME_F8F16] = "smef8f16", + [KERNEL_HWCAP_SME_F8F32] = "smef8f32", + [KERNEL_HWCAP_SME_SF8FMA] = "smesf8fma", + [KERNEL_HWCAP_SME_SF8DP4] = "smesf8dp4", + [KERNEL_HWCAP_SME_SF8DP2] = "smesf8dp2", }; #ifdef CONFIG_COMPAT @@ -443,14 +458,17 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_id_aa64isar0 = read_cpuid(ID_AA64ISAR0_EL1); info->reg_id_aa64isar1 = read_cpuid(ID_AA64ISAR1_EL1); info->reg_id_aa64isar2 = read_cpuid(ID_AA64ISAR2_EL1); + info->reg_id_aa64isar3 = read_cpuid(ID_AA64ISAR3_EL1); info->reg_id_aa64mmfr0 = read_cpuid(ID_AA64MMFR0_EL1); info->reg_id_aa64mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); info->reg_id_aa64mmfr2 = read_cpuid(ID_AA64MMFR2_EL1); info->reg_id_aa64mmfr3 = read_cpuid(ID_AA64MMFR3_EL1); info->reg_id_aa64pfr0 = read_cpuid(ID_AA64PFR0_EL1); info->reg_id_aa64pfr1 = read_cpuid(ID_AA64PFR1_EL1); + info->reg_id_aa64pfr2 = read_cpuid(ID_AA64PFR2_EL1); info->reg_id_aa64zfr0 = read_cpuid(ID_AA64ZFR0_EL1); info->reg_id_aa64smfr0 = read_cpuid(ID_AA64SMFR0_EL1); + info->reg_id_aa64fpfr0 = read_cpuid(ID_AA64FPFR0_EL1); if (id_aa64pfr1_mte(info->reg_id_aa64pfr1)) info->reg_gmid = read_cpuid(GMID_EL1); diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 0fc94207e69a..b77a15955f28 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -10,6 +10,7 @@ #include <linux/linkage.h> #include <linux/lockdep.h> #include <linux/ptrace.h> +#include <linux/resume_user_mode.h> #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/thread_info.h> @@ -126,16 +127,49 @@ static __always_inline void __exit_to_user_mode(void) lockdep_hardirqs_on(CALLER_ADDR0); } +static void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) +{ + do { + local_irq_enable(); + + if (thread_flags & _TIF_NEED_RESCHED) + schedule(); + + if (thread_flags & _TIF_UPROBE) + uprobe_notify_resume(regs); + + if (thread_flags & _TIF_MTE_ASYNC_FAULT) { + clear_thread_flag(TIF_MTE_ASYNC_FAULT); + send_sig_fault(SIGSEGV, SEGV_MTEAERR, + (void __user *)NULL, current); + } + + if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) + do_signal(regs); + + if (thread_flags & _TIF_NOTIFY_RESUME) + resume_user_mode_work(regs); + + if (thread_flags & _TIF_FOREIGN_FPSTATE) + fpsimd_restore_current_state(); + + local_irq_disable(); + thread_flags = read_thread_flags(); + } while (thread_flags & _TIF_WORK_MASK); +} + static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs) { unsigned long flags; - local_daif_mask(); + local_irq_disable(); flags = read_thread_flags(); if (unlikely(flags & _TIF_WORK_MASK)) do_notify_resume(regs, flags); + local_daif_mask(); + lockdep_sys_exit(); } diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index a5dc6f764195..0cd2bfb38bb0 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -359,6 +359,9 @@ static void task_fpsimd_load(void) WARN_ON(preemptible()); WARN_ON(test_thread_flag(TIF_KERNEL_FPSTATE)); + if (system_supports_fpmr()) + write_sysreg_s(current->thread.uw.fpmr, SYS_FPMR); + if (system_supports_sve() || system_supports_sme()) { switch (current->thread.fp_type) { case FP_STATE_FPSIMD: @@ -446,6 +449,9 @@ static void fpsimd_save_user_state(void) if (test_thread_flag(TIF_FOREIGN_FPSTATE)) return; + if (system_supports_fpmr()) + *(last->fpmr) = read_sysreg_s(SYS_FPMR); + /* * If a task is in a syscall the ABI allows us to only * preserve the state shared with FPSIMD so don't bother @@ -688,6 +694,12 @@ static void sve_to_fpsimd(struct task_struct *task) } } +void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__always_unused p) +{ + write_sysreg_s(read_sysreg_s(SYS_SCTLR_EL1) | SCTLR_EL1_EnFPM_MASK, + SYS_SCTLR_EL1); +} + #ifdef CONFIG_ARM64_SVE /* * Call __sve_free() directly only if you know task can't be scheduled @@ -1134,6 +1146,8 @@ void cpu_enable_sve(const struct arm64_cpu_capabilities *__always_unused p) { write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_ZEN_EL1EN, CPACR_EL1); isb(); + + write_sysreg_s(0, SYS_ZCR_EL1); } void __init sve_setup(void) @@ -1245,6 +1259,9 @@ void cpu_enable_sme(const struct arm64_cpu_capabilities *__always_unused p) write_sysreg(read_sysreg(CPACR_EL1) | CPACR_EL1_SMEN_EL1EN, CPACR_EL1); isb(); + /* Ensure all bits in SMCR are set to known values */ + write_sysreg_s(0, SYS_SMCR_EL1); + /* Allow EL0 to access TPIDR2 */ write_sysreg(read_sysreg(SCTLR_EL1) | SCTLR_ELx_ENTP2, SCTLR_EL1); isb(); @@ -1680,6 +1697,7 @@ static void fpsimd_bind_task_to_cpu(void) last->sve_vl = task_get_sve_vl(current); last->sme_vl = task_get_sme_vl(current); last->svcr = ¤t->thread.svcr; + last->fpmr = ¤t->thread.uw.fpmr; last->fp_type = ¤t->thread.fp_type; last->to_save = FP_STATE_CURRENT; current->thread.fpsimd_cpu = smp_processor_id(); diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index 35225632d70a..2f5755192c2b 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -21,6 +21,7 @@ #include <asm/current.h> #include <asm/debug-monitors.h> +#include <asm/esr.h> #include <asm/hw_breakpoint.h> #include <asm/traps.h> #include <asm/cputype.h> @@ -779,7 +780,7 @@ static int watchpoint_handler(unsigned long addr, unsigned long esr, * Check that the access type matches. * 0 => load, otherwise => store */ - access = (esr & AARCH64_ESR_ACCESS_MASK) ? HW_BREAKPOINT_W : + access = (esr & ESR_ELx_WNR) ? HW_BREAKPOINT_W : HW_BREAKPOINT_R; if (!(access & hw_breakpoint_type(wp))) continue; diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 5e4dc72ab1bd..e931ce078a00 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -36,6 +36,8 @@ PROVIDE(__pi___memcpy = __pi_memcpy); PROVIDE(__pi___memmove = __pi_memmove); PROVIDE(__pi___memset = __pi_memset); +PROVIDE(__pi_vabits_actual = vabits_actual); + #ifdef CONFIG_KVM /* diff --git a/arch/arm64/kernel/pi/kaslr_early.c b/arch/arm64/kernel/pi/kaslr_early.c index 17bff6e399e4..b9e0bb4bc6a9 100644 --- a/arch/arm64/kernel/pi/kaslr_early.c +++ b/arch/arm64/kernel/pi/kaslr_early.c @@ -14,6 +14,7 @@ #include <asm/archrandom.h> #include <asm/memory.h> +#include <asm/pgtable.h> /* taken from lib/string.c */ static char *__strstr(const char *s1, const char *s2) @@ -87,7 +88,7 @@ static u64 get_kaslr_seed(void *fdt) asmlinkage u64 kaslr_early_init(void *fdt) { - u64 seed; + u64 seed, range; if (is_kaslr_disabled_cmdline(fdt)) return 0; @@ -102,9 +103,9 @@ asmlinkage u64 kaslr_early_init(void *fdt) /* * OK, so we are proceeding with KASLR enabled. Calculate a suitable * kernel image offset from the seed. Let's place the kernel in the - * middle half of the VMALLOC area (VA_BITS_MIN - 2), and stay clear of - * the lower and upper quarters to avoid colliding with other - * allocations. + * 'middle' half of the VMALLOC area, and stay clear of the lower and + * upper quarters to avoid colliding with other allocations. */ - return BIT(VA_BITS_MIN - 3) + (seed & GENMASK(VA_BITS_MIN - 3, 0)); + range = (VMALLOC_END - KIMAGE_VADDR) / 2; + return range / 2 + (((__uint128_t)range * seed) >> 64); } diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 70b91a8c6bb3..327855a11df2 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -371,6 +371,21 @@ static struct break_hook kprobes_break_ss_hook = { .fn = kprobe_breakpoint_ss_handler, }; +static int __kprobes +kretprobe_breakpoint_handler(struct pt_regs *regs, unsigned long esr) +{ + if (regs->pc != (unsigned long)__kretprobe_trampoline) + return DBG_HOOK_ERROR; + + regs->pc = kretprobe_trampoline_handler(regs, (void *)regs->regs[29]); + return DBG_HOOK_HANDLED; +} + +static struct break_hook kretprobes_break_hook = { + .imm = KRETPROBES_BRK_IMM, + .fn = kretprobe_breakpoint_handler, +}; + /* * Provide a blacklist of symbols identifying ranges which cannot be kprobed. * This blacklist is exposed to userspace via debugfs (kprobes/blacklist). @@ -396,11 +411,6 @@ int __init arch_populate_kprobe_blacklist(void) return ret; } -void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs) -{ - return (void *)kretprobe_trampoline_handler(regs, (void *)regs->regs[29]); -} - void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { @@ -420,6 +430,7 @@ int __init arch_init_kprobes(void) { register_kernel_break_hook(&kprobes_break_hook); register_kernel_break_hook(&kprobes_break_ss_hook); + register_kernel_break_hook(&kretprobes_break_hook); return 0; } diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S index 9a6499bed58b..a362f3dbb3d1 100644 --- a/arch/arm64/kernel/probes/kprobes_trampoline.S +++ b/arch/arm64/kernel/probes/kprobes_trampoline.S @@ -4,83 +4,17 @@ */ #include <linux/linkage.h> -#include <asm/asm-offsets.h> +#include <asm/asm-bug.h> #include <asm/assembler.h> .text - .macro save_all_base_regs - stp x0, x1, [sp, #S_X0] - stp x2, x3, [sp, #S_X2] - stp x4, x5, [sp, #S_X4] - stp x6, x7, [sp, #S_X6] - stp x8, x9, [sp, #S_X8] - stp x10, x11, [sp, #S_X10] - stp x12, x13, [sp, #S_X12] - stp x14, x15, [sp, #S_X14] - stp x16, x17, [sp, #S_X16] - stp x18, x19, [sp, #S_X18] - stp x20, x21, [sp, #S_X20] - stp x22, x23, [sp, #S_X22] - stp x24, x25, [sp, #S_X24] - stp x26, x27, [sp, #S_X26] - stp x28, x29, [sp, #S_X28] - add x0, sp, #PT_REGS_SIZE - stp lr, x0, [sp, #S_LR] - /* - * Construct a useful saved PSTATE - */ - mrs x0, nzcv - mrs x1, daif - orr x0, x0, x1 - mrs x1, CurrentEL - orr x0, x0, x1 - mrs x1, SPSel - orr x0, x0, x1 - stp xzr, x0, [sp, #S_PC] - .endm - - .macro restore_all_base_regs - ldr x0, [sp, #S_PSTATE] - and x0, x0, #(PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT) - msr nzcv, x0 - ldp x0, x1, [sp, #S_X0] - ldp x2, x3, [sp, #S_X2] - ldp x4, x5, [sp, #S_X4] - ldp x6, x7, [sp, #S_X6] - ldp x8, x9, [sp, #S_X8] - ldp x10, x11, [sp, #S_X10] - ldp x12, x13, [sp, #S_X12] - ldp x14, x15, [sp, #S_X14] - ldp x16, x17, [sp, #S_X16] - ldp x18, x19, [sp, #S_X18] - ldp x20, x21, [sp, #S_X20] - ldp x22, x23, [sp, #S_X22] - ldp x24, x25, [sp, #S_X24] - ldp x26, x27, [sp, #S_X26] - ldp x28, x29, [sp, #S_X28] - .endm - SYM_CODE_START(__kretprobe_trampoline) - sub sp, sp, #PT_REGS_SIZE - - save_all_base_regs - - /* Setup a frame pointer. */ - add x29, sp, #S_FP - - mov x0, sp - bl trampoline_probe_handler /* - * Replace trampoline address in lr with actual orig_ret_addr return - * address. + * Trigger a breakpoint exception. The PC will be adjusted by + * kretprobe_breakpoint_handler(), and no subsequent instructions will + * be executed from the trampoline. */ - mov lr, x0 - - /* The frame pointer (x29) is restored with other registers. */ - restore_all_base_regs - - add sp, sp, #PT_REGS_SIZE - ret - + brk #KRETPROBES_BRK_IMM + ASM_BUG() SYM_CODE_END(__kretprobe_trampoline) diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 7387b68c745b..4ae31b7af6c3 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -290,9 +290,6 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) fpsimd_preserve_current_state(); *dst = *src; - /* We rely on the above assignment to initialize dst's thread_flags: */ - BUILD_BUG_ON(!IS_ENABLED(CONFIG_THREAD_INFO_IN_TASK)); - /* * Detach src's sve_state (if any) from dst so that it does not * get erroneously used or freed prematurely. dst's copies diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index dc6cf0e37194..b096c8be3bcf 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -174,7 +174,6 @@ static void ptrace_hbptriggered(struct perf_event *bp, struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp); const char *desc = "Hardware breakpoint trap (ptrace)"; -#ifdef CONFIG_COMPAT if (is_compat_task()) { int si_errno = 0; int i; @@ -196,7 +195,7 @@ static void ptrace_hbptriggered(struct perf_event *bp, desc); return; } -#endif + arm64_force_sig_fault(SIGTRAP, TRAP_HWBKPT, bkpt->trigger, desc); } @@ -698,6 +697,39 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset, return ret; } +static int fpmr_get(struct task_struct *target, const struct user_regset *regset, + struct membuf to) +{ + if (!system_supports_fpmr()) + return -EINVAL; + + if (target == current) + fpsimd_preserve_current_state(); + + return membuf_store(&to, target->thread.uw.fpmr); +} + +static int fpmr_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + unsigned long fpmr; + + if (!system_supports_fpmr()) + return -EINVAL; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpmr, 0, count); + if (ret) + return ret; + + target->thread.uw.fpmr = fpmr; + + fpsimd_flush_task_state(target); + + return 0; +} + static int system_call_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) @@ -1419,6 +1451,7 @@ enum aarch64_regset { REGSET_HW_BREAK, REGSET_HW_WATCH, #endif + REGSET_FPMR, REGSET_SYSTEM_CALL, #ifdef CONFIG_ARM64_SVE REGSET_SVE, @@ -1497,6 +1530,14 @@ static const struct user_regset aarch64_regsets[] = { .regset_get = system_call_get, .set = system_call_set, }, + [REGSET_FPMR] = { + .core_note_type = NT_ARM_FPMR, + .n = 1, + .size = sizeof(u64), + .align = sizeof(u64), + .regset_get = fpmr_get, + .set = fpmr_set, + }, #ifdef CONFIG_ARM64_SVE [REGSET_SVE] = { /* Scalable Vector Extension */ .core_note_type = NT_ARM_SVE, @@ -1596,7 +1637,6 @@ static const struct user_regset_view user_aarch64_view = { .regsets = aarch64_regsets, .n = ARRAY_SIZE(aarch64_regsets) }; -#ifdef CONFIG_COMPAT enum compat_regset { REGSET_COMPAT_GPR, REGSET_COMPAT_VFP, @@ -1853,6 +1893,7 @@ static const struct user_regset_view user_aarch32_ptrace_view = { .regsets = aarch32_ptrace_regsets, .n = ARRAY_SIZE(aarch32_ptrace_regsets) }; +#ifdef CONFIG_COMPAT static int compat_ptrace_read_user(struct task_struct *tsk, compat_ulong_t off, compat_ulong_t __user *ret) { @@ -2114,7 +2155,6 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, const struct user_regset_view *task_user_regset_view(struct task_struct *task) { -#ifdef CONFIG_COMPAT /* * Core dumping of 32-bit tasks or compat ptrace requests must use the * user_aarch32_view compatible with arm32. Native ptrace requests on @@ -2125,7 +2165,7 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task) return &user_aarch32_view; else if (is_compat_thread(task_thread_info(task))) return &user_aarch32_ptrace_view; -#endif + return &user_aarch64_view; } diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 42c690bb2d60..ab43bfa85368 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -320,9 +320,8 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) dynamic_scs_init(); /* - * Unmask asynchronous aborts and fiq after bringing up possible - * earlycon. (Report possible System Errors once we can report this - * occurred). + * Unmask SError as soon as possible after initializing earlycon so + * that we can report any SErrors immediately. */ local_daif_restore(DAIF_PROCCTX_NOIRQ); diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 0e8beb3349ea..ac69b604cac9 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -16,8 +16,8 @@ #include <linux/uaccess.h> #include <linux/sizes.h> #include <linux/string.h> -#include <linux/resume_user_mode.h> #include <linux/ratelimit.h> +#include <linux/rseq.h> #include <linux/syscalls.h> #include <asm/daifflags.h> @@ -60,6 +60,7 @@ struct rt_sigframe_user_layout { unsigned long tpidr2_offset; unsigned long za_offset; unsigned long zt_offset; + unsigned long fpmr_offset; unsigned long extra_offset; unsigned long end_offset; }; @@ -182,6 +183,8 @@ struct user_ctxs { u32 za_size; struct zt_context __user *zt; u32 zt_size; + struct fpmr_context __user *fpmr; + u32 fpmr_size; }; static int preserve_fpsimd_context(struct fpsimd_context __user *ctx) @@ -227,6 +230,33 @@ static int restore_fpsimd_context(struct user_ctxs *user) return err ? -EFAULT : 0; } +static int preserve_fpmr_context(struct fpmr_context __user *ctx) +{ + int err = 0; + + current->thread.uw.fpmr = read_sysreg_s(SYS_FPMR); + + __put_user_error(FPMR_MAGIC, &ctx->head.magic, err); + __put_user_error(sizeof(*ctx), &ctx->head.size, err); + __put_user_error(current->thread.uw.fpmr, &ctx->fpmr, err); + + return err; +} + +static int restore_fpmr_context(struct user_ctxs *user) +{ + u64 fpmr; + int err = 0; + + if (user->fpmr_size != sizeof(*user->fpmr)) + return -EINVAL; + + __get_user_error(fpmr, &user->fpmr->fpmr, err); + if (!err) + write_sysreg_s(fpmr, SYS_FPMR); + + return err; +} #ifdef CONFIG_ARM64_SVE @@ -590,6 +620,7 @@ static int parse_user_sigframe(struct user_ctxs *user, user->tpidr2 = NULL; user->za = NULL; user->zt = NULL; + user->fpmr = NULL; if (!IS_ALIGNED((unsigned long)base, 16)) goto invalid; @@ -684,6 +715,17 @@ static int parse_user_sigframe(struct user_ctxs *user, user->zt_size = size; break; + case FPMR_MAGIC: + if (!system_supports_fpmr()) + goto invalid; + + if (user->fpmr) + goto invalid; + + user->fpmr = (struct fpmr_context __user *)head; + user->fpmr_size = size; + break; + case EXTRA_MAGIC: if (have_extra_context) goto invalid; @@ -806,6 +848,9 @@ static int restore_sigframe(struct pt_regs *regs, if (err == 0 && system_supports_tpidr2() && user.tpidr2) err = restore_tpidr2_context(&user); + if (err == 0 && system_supports_fpmr() && user.fpmr) + err = restore_fpmr_context(&user); + if (err == 0 && system_supports_sme() && user.za) err = restore_za_context(&user); @@ -928,6 +973,13 @@ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, } } + if (system_supports_fpmr()) { + err = sigframe_alloc(user, &user->fpmr_offset, + sizeof(struct fpmr_context)); + if (err) + return err; + } + return sigframe_alloc_end(user); } @@ -983,6 +1035,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, err |= preserve_tpidr2_context(tpidr2_ctx); } + /* FPMR if supported */ + if (system_supports_fpmr() && err == 0) { + struct fpmr_context __user *fpmr_ctx = + apply_user_offset(user, user->fpmr_offset); + err |= preserve_fpmr_context(fpmr_ctx); + } + /* ZA state if present */ if (system_supports_sme() && err == 0 && user->za_offset) { struct za_context __user *za_ctx = @@ -1207,7 +1266,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) * the kernel can handle, and then we build all the user-level signal handling * stack-frames in one go after that. */ -static void do_signal(struct pt_regs *regs) +void do_signal(struct pt_regs *regs) { unsigned long continue_addr = 0, restart_addr = 0; int retval = 0; @@ -1278,41 +1337,6 @@ static void do_signal(struct pt_regs *regs) restore_saved_sigmask(); } -void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags) -{ - do { - if (thread_flags & _TIF_NEED_RESCHED) { - /* Unmask Debug and SError for the next task */ - local_daif_restore(DAIF_PROCCTX_NOIRQ); - - schedule(); - } else { - local_daif_restore(DAIF_PROCCTX); - - if (thread_flags & _TIF_UPROBE) - uprobe_notify_resume(regs); - - if (thread_flags & _TIF_MTE_ASYNC_FAULT) { - clear_thread_flag(TIF_MTE_ASYNC_FAULT); - send_sig_fault(SIGSEGV, SEGV_MTEAERR, - (void __user *)NULL, current); - } - - if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) - do_signal(regs); - - if (thread_flags & _TIF_NOTIFY_RESUME) - resume_user_mode_work(regs); - - if (thread_flags & _TIF_FOREIGN_FPSTATE) - fpsimd_restore_current_state(); - } - - local_daif_mask(); - thread_flags = read_thread_flags(); - } while (thread_flags & _TIF_WORK_MASK); -} - unsigned long __ro_after_init signal_minsigstksz; /* diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 9a70d9746b66..ad198262b981 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -20,14 +20,11 @@ long sys_ni_syscall(void); static long do_ni_syscall(struct pt_regs *regs, int scno) { -#ifdef CONFIG_COMPAT - long ret; if (is_compat_task()) { - ret = compat_arm_syscall(regs, scno); + long ret = compat_arm_syscall(regs, scno); if (ret != -ENOSYS) return ret; } -#endif return sys_ni_syscall(); } diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 8c1d0d4853df..e3e611e30e91 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -153,6 +153,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) fp_state.sve_vl = vcpu->arch.sve_max_vl; fp_state.sme_state = NULL; fp_state.svcr = &vcpu->arch.svcr; + fp_state.fpmr = &vcpu->arch.fpmr; fp_state.fp_type = &vcpu->arch.fp_type; if (vcpu_has_sve(vcpu)) diff --git a/arch/arm64/mm/fixmap.c b/arch/arm64/mm/fixmap.c index c0a3301203bd..6fc17b2e1714 100644 --- a/arch/arm64/mm/fixmap.c +++ b/arch/arm64/mm/fixmap.c @@ -16,6 +16,9 @@ #include <asm/pgalloc.h> #include <asm/tlbflush.h> +/* ensure that the fixmap region does not grow down into the PCI I/O region */ +static_assert(FIXADDR_TOT_START > PCI_IO_END); + #define NR_BM_PTE_TABLES \ SPAN_NR_ENTRIES(FIXADDR_TOT_START, FIXADDR_TOP, PMD_SHIFT) #define NR_BM_PMD_TABLES \ diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c index e305b6593c4e..5f0849528ccf 100644 --- a/arch/arm64/mm/ptdump.c +++ b/arch/arm64/mm/ptdump.c @@ -26,34 +26,6 @@ #include <asm/ptdump.h> -enum address_markers_idx { - PAGE_OFFSET_NR = 0, - PAGE_END_NR, -#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) - KASAN_START_NR, -#endif -}; - -static struct addr_marker address_markers[] = { - { PAGE_OFFSET, "Linear Mapping start" }, - { 0 /* PAGE_END */, "Linear Mapping end" }, -#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) - { 0 /* KASAN_SHADOW_START */, "Kasan shadow start" }, - { KASAN_SHADOW_END, "Kasan shadow end" }, -#endif - { MODULES_VADDR, "Modules start" }, - { MODULES_END, "Modules end" }, - { VMALLOC_START, "vmalloc() area" }, - { VMALLOC_END, "vmalloc() end" }, - { FIXADDR_TOT_START, "Fixmap start" }, - { FIXADDR_TOP, "Fixmap end" }, - { PCI_IO_START, "PCI I/O start" }, - { PCI_IO_END, "PCI I/O end" }, - { VMEMMAP_START, "vmemmap start" }, - { VMEMMAP_START + VMEMMAP_SIZE, "vmemmap end" }, - { -1, NULL }, -}; - #define pt_dump_seq_printf(m, fmt, args...) \ ({ \ if (m) \ @@ -339,9 +311,8 @@ static void __init ptdump_initialize(void) pg_level[i].mask |= pg_level[i].bits[j].mask; } -static struct ptdump_info kernel_ptdump_info = { +static struct ptdump_info kernel_ptdump_info __ro_after_init = { .mm = &init_mm, - .markers = address_markers, .base_addr = PAGE_OFFSET, }; @@ -375,10 +346,31 @@ void ptdump_check_wx(void) static int __init ptdump_init(void) { - address_markers[PAGE_END_NR].start_address = PAGE_END; + u64 page_offset = _PAGE_OFFSET(vabits_actual); + u64 vmemmap_start = (u64)virt_to_page((void *)page_offset); + struct addr_marker m[] = { + { PAGE_OFFSET, "Linear Mapping start" }, + { PAGE_END, "Linear Mapping end" }, #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) - address_markers[KASAN_START_NR].start_address = KASAN_SHADOW_START; + { KASAN_SHADOW_START, "Kasan shadow start" }, + { KASAN_SHADOW_END, "Kasan shadow end" }, #endif + { MODULES_VADDR, "Modules start" }, + { MODULES_END, "Modules end" }, + { VMALLOC_START, "vmalloc() area" }, + { VMALLOC_END, "vmalloc() end" }, + { vmemmap_start, "vmemmap start" }, + { VMEMMAP_END, "vmemmap end" }, + { PCI_IO_START, "PCI I/O start" }, + { PCI_IO_END, "PCI I/O end" }, + { FIXADDR_TOT_START, "Fixmap start" }, + { FIXADDR_TOP, "Fixmap end" }, + { -1, NULL }, + }; + static struct addr_marker address_markers[ARRAY_SIZE(m)] __ro_after_init; + + kernel_ptdump_info.markers = memcpy(address_markers, m, sizeof(m)); + ptdump_initialize(); ptdump_debugfs_register(&kernel_ptdump_info, "kernel_page_tables"); return 0; diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index b912b1409fc0..63283550c8e8 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -26,6 +26,7 @@ HAS_ECV HAS_ECV_CNTPOFF HAS_EPAN HAS_EVT +HAS_FPMR HAS_FGT HAS_FPSIMD HAS_GENERIC_AUTH diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 4c9b67934367..508224a0e078 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -200,6 +200,7 @@ UnsignedEnum 27:24 PerfMon 0b0110 PMUv3p5 0b0111 PMUv3p7 0b1000 PMUv3p8 + 0b1001 PMUv3p9 0b1111 IMPDEF EndEnum Enum 23:20 MProfDbg @@ -231,6 +232,7 @@ Enum 3:0 CopDbg 0b1000 Debugv8p2 0b1001 Debugv8p4 0b1010 Debugv8p8 + 0b1011 Debugv8p9 EndEnum EndSysreg @@ -1221,6 +1223,7 @@ UnsignedEnum 35:32 PMSVer 0b0010 V1P1 0b0011 V1P2 0b0100 V1P3 + 0b0101 V1P4 EndEnum Field 31:28 CTX_CMPs Res0 27:24 @@ -1247,11 +1250,41 @@ UnsignedEnum 3:0 DebugVer 0b1000 V8P2 0b1001 V8P4 0b1010 V8P8 + 0b1011 V8P9 EndEnum EndSysreg Sysreg ID_AA64DFR1_EL1 3 0 0 5 1 -Res0 63:0 +Field 63:56 ABL_CMPs +UnsignedEnum 55:52 DPFZS + 0b0000 IGNR + 0b0001 FRZN +EndEnum +UnsignedEnum 51:48 EBEP + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 47:44 ITE + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 43:40 ABLE + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 39:36 PMICNTR + 0b0000 NI + 0b0001 IMP +EndEnum +UnsignedEnum 35:32 SPMU + 0b0000 NI + 0b0001 IMP + 0b0010 IMP_SPMZR +EndEnum +Field 31:24 CTX_CMPs +Field 23:16 WRPs +Field 15:8 BRPs +Field 7:0 SYSPMUID EndSysreg Sysreg ID_AA64AFR0_EL1 3 0 0 5 4 diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index 983aa2b1629a..fa4fb09909ae 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -82,6 +82,7 @@ KBUILD_AFLAGS_MODULE += -Wa,-mla-global-with-abs KBUILD_CFLAGS_MODULE += -fplt -Wa,-mla-global-with-abs,-mla-local-with-abs endif +KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json KBUILD_RUSTFLAGS_MODULE += -Crelocation-model=pic ifeq ($(CONFIG_RELOCATABLE),y) diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 2264db14a25d..18cf8f0cf7cd 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -68,6 +68,7 @@ export BITS # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383 # KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx +KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2 ifeq ($(CONFIG_X86_KERNEL_IBT),y) diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 9417309b7230..b54b313bcf07 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -440,6 +440,7 @@ typedef struct elf64_shdr { #define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ #define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ #define NT_ARM_ZT 0x40d /* ARM SME ZT registers */ +#define NT_ARM_FPMR 0x40e /* ARM floating point mode register */ #define NT_ARC_V2 0x600 /* ARCv2 accumulator/extra registers */ #define NT_VMCOREDD 0x700 /* Vmcore Device Dump Note */ #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ diff --git a/rust/Makefile b/rust/Makefile index 9d2a16cc91cb..fe045dbc701e 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -297,6 +297,7 @@ bindgen_skip_c_flags := -mno-fp-ret-in-387 -mpreferred-stack-boundary=% \ # Derived from `scripts/Makefile.clang`. BINDGEN_TARGET_x86 := x86_64-linux-gnu +BINDGEN_TARGET_arm64 := aarch64-linux-gnu BINDGEN_TARGET := $(BINDGEN_TARGET_$(SRCARCH)) # All warnings are inhibited since GCC builds are very experimental, @@ -434,8 +435,11 @@ $(obj)/core.o: private skip_clippy = 1 $(obj)/core.o: private skip_flags = -Dunreachable_pub $(obj)/core.o: private rustc_objcopy = $(foreach sym,$(redirect-intrinsics),--redefine-sym $(sym)=__rust$(sym)) $(obj)/core.o: private rustc_target_flags = $(core-cfgs) -$(obj)/core.o: $(RUST_LIB_SRC)/core/src/lib.rs scripts/target.json FORCE +$(obj)/core.o: $(RUST_LIB_SRC)/core/src/lib.rs FORCE $(call if_changed_dep,rustc_library) +ifneq ($(or $(CONFIG_X86_64),$(CONFIG_LOONGARCH)),) +$(obj)/core.o: scripts/target.json +endif $(obj)/compiler_builtins.o: private rustc_objcopy = -w -W '__*' $(obj)/compiler_builtins.o: $(src)/compiler_builtins.rs $(obj)/core.o FORCE diff --git a/scripts/Makefile b/scripts/Makefile index 576cf64be667..6673cbb6194f 100644 --- a/scripts/Makefile +++ b/scripts/Makefile @@ -11,12 +11,14 @@ hostprogs-always-$(CONFIG_MODULE_SIG_FORMAT) += sign-file hostprogs-always-$(CONFIG_SYSTEM_EXTRA_CERTIFICATE) += insert-sys-cert hostprogs-always-$(CONFIG_RUST_KERNEL_DOCTESTS) += rustdoc_test_builder hostprogs-always-$(CONFIG_RUST_KERNEL_DOCTESTS) += rustdoc_test_gen -always-$(CONFIG_RUST) += target.json +ifneq ($(or $(CONFIG_X86_64),$(CONFIG_LOONGARCH)),) +always-$(CONFIG_RUST) += target.json filechk_rust_target = $< < include/config/auto.conf $(obj)/target.json: scripts/generate_rust_target include/config/auto.conf FORCE $(call filechk,rust_target) +endif hostprogs += generate_rust_target generate_rust_target-rust := y diff --git a/scripts/generate_rust_target.rs b/scripts/generate_rust_target.rs index 0da52b548ba5..9e117957ea7b 100644 --- a/scripts/generate_rust_target.rs +++ b/scripts/generate_rust_target.rs @@ -148,7 +148,9 @@ fn main() { let mut ts = TargetSpec::new(); // `llvm-target`s are taken from `scripts/Makefile.clang`. - if cfg.has("X86_64") { + if cfg.has("ARM64") { + panic!("arm64 uses the builtin rustc aarch64-unknown-none target"); + } else if cfg.has("X86_64") { ts.push("arch", "x86_64"); ts.push( "data-layout", diff --git a/tools/testing/selftests/arm64/abi/hwcap.c b/tools/testing/selftests/arm64/abi/hwcap.c index 1189e77c8152..d8909b2b535a 100644 --- a/tools/testing/selftests/arm64/abi/hwcap.c +++ b/tools/testing/selftests/arm64/abi/hwcap.c @@ -58,11 +58,46 @@ static void cssc_sigill(void) asm volatile(".inst 0xdac01c00" : : : "x0"); } +static void f8cvt_sigill(void) +{ + /* FSCALE V0.4H, V0.4H, V0.4H */ + asm volatile(".inst 0x2ec03c00"); +} + +static void f8dp2_sigill(void) +{ + /* FDOT V0.4H, V0.4H, V0.5H */ + asm volatile(".inst 0xe40fc00"); +} + +static void f8dp4_sigill(void) +{ + /* FDOT V0.2S, V0.2S, V0.2S */ + asm volatile(".inst 0xe00fc00"); +} + +static void f8fma_sigill(void) +{ + /* FMLALB V0.8H, V0.16B, V0.16B */ + asm volatile(".inst 0xec0fc00"); +} + +static void faminmax_sigill(void) +{ + /* FAMIN V0.4H, V0.4H, V0.4H */ + asm volatile(".inst 0x2ec01c00"); +} + static void fp_sigill(void) { asm volatile("fmov s0, #1"); } +static void fpmr_sigill(void) +{ + asm volatile("mrs x0, S3_3_C4_C4_2" : : : "x0"); +} + static void ilrcpc_sigill(void) { /* LDAPUR W0, [SP, #8] */ @@ -95,6 +130,12 @@ static void lse128_sigill(void) : "cc", "memory"); } +static void lut_sigill(void) +{ + /* LUTI2 V0.16B, { V0.16B }, V[0] */ + asm volatile(".inst 0x4e801000"); +} + static void mops_sigill(void) { char dst[1], src[1]; @@ -216,6 +257,78 @@ static void smef16f16_sigill(void) asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); } +static void smef8f16_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* FDOT ZA.H[W0, 0], Z0.B-Z1.B, Z0.B-Z1.B */ + asm volatile(".inst 0xc1a01020" : : : ); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smef8f32_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* FDOT ZA.S[W0, 0], { Z0.B-Z1.B }, Z0.B[0] */ + asm volatile(".inst 0xc1500038" : : : ); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smelutv2_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* LUTI4 { Z0.B-Z3.B }, ZT0, { Z0-Z1 } */ + asm volatile(".inst 0xc08b0000" : : : ); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smesf8dp2_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* FDOT Z0.H, Z0.B, Z0.B[0] */ + asm volatile(".inst 0x64204400" : : : ); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smesf8dp4_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* FDOT Z0.S, Z0.B, Z0.B[0] */ + asm volatile(".inst 0xc1a41C00" : : : ); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + +static void smesf8fma_sigill(void) +{ + /* SMSTART */ + asm volatile("msr S0_3_C4_C7_3, xzr" : : : ); + + /* FMLALB V0.8H, V0.16B, V0.16B */ + asm volatile(".inst 0xec0fc00"); + + /* SMSTOP */ + asm volatile("msr S0_3_C4_C6_3, xzr" : : : ); +} + static void sve_sigill(void) { /* RDVL x0, #0 */ @@ -354,6 +467,53 @@ static const struct hwcap_data { .sigill_fn = cssc_sigill, }, { + .name = "F8CVT", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_F8CVT, + .cpuinfo = "f8cvt", + .sigill_fn = f8cvt_sigill, + }, + { + .name = "F8DP4", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_F8DP4, + .cpuinfo = "f8dp4", + .sigill_fn = f8dp4_sigill, + }, + { + .name = "F8DP2", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_F8DP2, + .cpuinfo = "f8dp4", + .sigill_fn = f8dp2_sigill, + }, + { + .name = "F8E5M2", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_F8E5M2, + .cpuinfo = "f8e5m2", + }, + { + .name = "F8E4M3", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_F8E4M3, + .cpuinfo = "f8e4m3", + }, + { + .name = "F8FMA", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_F8FMA, + .cpuinfo = "f8fma", + .sigill_fn = f8fma_sigill, + }, + { + .name = "FAMINMAX", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_FAMINMAX, + .cpuinfo = "faminmax", + .sigill_fn = faminmax_sigill, + }, + { .name = "FP", .at_hwcap = AT_HWCAP, .hwcap_bit = HWCAP_FP, @@ -361,6 +521,14 @@ static const struct hwcap_data { .sigill_fn = fp_sigill, }, { + .name = "FPMR", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_FPMR, + .cpuinfo = "fpmr", + .sigill_fn = fpmr_sigill, + .sigill_reliable = true, + }, + { .name = "JSCVT", .at_hwcap = AT_HWCAP, .hwcap_bit = HWCAP_JSCVT, @@ -412,6 +580,13 @@ static const struct hwcap_data { .sigill_fn = lse128_sigill, }, { + .name = "LUT", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_LUT, + .cpuinfo = "lut", + .sigill_fn = lut_sigill, + }, + { .name = "MOPS", .at_hwcap = AT_HWCAP2, .hwcap_bit = HWCAP2_MOPS, @@ -512,6 +687,48 @@ static const struct hwcap_data { .sigill_fn = smef16f16_sigill, }, { + .name = "SME F8F16", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_SME_F8F16, + .cpuinfo = "smef8f16", + .sigill_fn = smef8f16_sigill, + }, + { + .name = "SME F8F32", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_SME_F8F32, + .cpuinfo = "smef8f32", + .sigill_fn = smef8f32_sigill, + }, + { + .name = "SME LUTV2", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_SME_LUTV2, + .cpuinfo = "smelutv2", + .sigill_fn = smelutv2_sigill, + }, + { + .name = "SME SF8FMA", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_SME_SF8FMA, + .cpuinfo = "smesf8fma", + .sigill_fn = smesf8fma_sigill, + }, + { + .name = "SME SF8DP2", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_SME_SF8DP2, + .cpuinfo = "smesf8dp2", + .sigill_fn = smesf8dp2_sigill, + }, + { + .name = "SME SF8DP4", + .at_hwcap = AT_HWCAP2, + .hwcap_bit = HWCAP2_SME_SF8DP4, + .cpuinfo = "smesf8dp4", + .sigill_fn = smesf8dp4_sigill, + }, + { .name = "SVE", .at_hwcap = AT_HWCAP, .hwcap_bit = HWCAP_SVE, diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore index ebc86757bdd8..00e52c966281 100644 --- a/tools/testing/selftests/arm64/fp/.gitignore +++ b/tools/testing/selftests/arm64/fp/.gitignore @@ -1,4 +1,5 @@ fp-pidbench +fp-ptrace fp-stress fpsimd-test rdvl-sme diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile index b413b0af07f9..55d4f00d9e8e 100644 --- a/tools/testing/selftests/arm64/fp/Makefile +++ b/tools/testing/selftests/arm64/fp/Makefile @@ -5,7 +5,9 @@ top_srcdir = $(realpath ../../../../../) CFLAGS += $(KHDR_INCLUDES) -TEST_GEN_PROGS := fp-stress \ +TEST_GEN_PROGS := \ + fp-ptrace \ + fp-stress \ sve-ptrace sve-probe-vls \ vec-syscfg \ za-fork za-ptrace @@ -24,6 +26,7 @@ EXTRA_CLEAN += $(OUTPUT)/asm-utils.o $(OUTPUT)/rdvl.o $(OUTPUT)/za-fork-asm.o # Build with nolibc to avoid effects due to libc's clone() support $(OUTPUT)/fp-pidbench: fp-pidbench.S $(OUTPUT)/asm-utils.o $(CC) -nostdlib $^ -o $@ +$(OUTPUT)/fp-ptrace: fp-ptrace.c fp-ptrace-asm.S $(OUTPUT)/fpsimd-test: fpsimd-test.S $(OUTPUT)/asm-utils.o $(CC) -nostdlib $^ -o $@ $(OUTPUT)/rdvl-sve: rdvl-sve.c $(OUTPUT)/rdvl.o diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace-asm.S b/tools/testing/selftests/arm64/fp/fp-ptrace-asm.S new file mode 100644 index 000000000000..7ad59d92d02b --- /dev/null +++ b/tools/testing/selftests/arm64/fp/fp-ptrace-asm.S @@ -0,0 +1,279 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2021-3 ARM Limited. +// +// Assembly portion of the FP ptrace test + +// +// Load values from memory into registers, break on a breakpoint, then +// break on a further breakpoint +// + +#include "fp-ptrace.h" +#include "sme-inst.h" + +.arch_extension sve + +// Load and save register values with pauses for ptrace +// +// x0 - SVE in use +// x1 - SME in use +// x2 - SME2 in use +// x3 - FA64 supported + +.globl load_and_save +load_and_save: + stp x11, x12, [sp, #-0x10]! + + // This should be redundant in the SVE case + ldr x7, =v_in + ldp q0, q1, [x7] + ldp q2, q3, [x7, #16 * 2] + ldp q4, q5, [x7, #16 * 4] + ldp q6, q7, [x7, #16 * 6] + ldp q8, q9, [x7, #16 * 8] + ldp q10, q11, [x7, #16 * 10] + ldp q12, q13, [x7, #16 * 12] + ldp q14, q15, [x7, #16 * 14] + ldp q16, q17, [x7, #16 * 16] + ldp q18, q19, [x7, #16 * 18] + ldp q20, q21, [x7, #16 * 20] + ldp q22, q23, [x7, #16 * 22] + ldp q24, q25, [x7, #16 * 24] + ldp q26, q27, [x7, #16 * 26] + ldp q28, q29, [x7, #16 * 28] + ldp q30, q31, [x7, #16 * 30] + + // SME? + cbz x1, check_sve_in + + adrp x7, svcr_in + ldr x7, [x7, :lo12:svcr_in] + // SVCR is 0 by default, avoid triggering SME if not in use + cbz x7, check_sve_in + msr S3_3_C4_C2_2, x7 + + // ZA? + tbz x7, #SVCR_ZA_SHIFT, check_sm_in + rdsvl 11, 1 + mov w12, #0 + ldr x6, =za_in +1: _ldr_za 12, 6 + add x6, x6, x11 + add x12, x12, #1 + cmp x11, x12 + bne 1b + + // ZT? + cbz x2, check_sm_in + adrp x6, zt_in + add x6, x6, :lo12:zt_in + _ldr_zt 6 + + // In streaming mode? +check_sm_in: + tbz x7, #SVCR_SM_SHIFT, check_sve_in + mov x4, x3 // Load FFR if we have FA64 + b load_sve + + // SVE? +check_sve_in: + cbz x0, wait_for_writes + mov x4, #1 + +load_sve: + ldr x7, =z_in + ldr z0, [x7, #0, MUL VL] + ldr z1, [x7, #1, MUL VL] + ldr z2, [x7, #2, MUL VL] + ldr z3, [x7, #3, MUL VL] + ldr z4, [x7, #4, MUL VL] + ldr z5, [x7, #5, MUL VL] + ldr z6, [x7, #6, MUL VL] + ldr z7, [x7, #7, MUL VL] + ldr z8, [x7, #8, MUL VL] + ldr z9, [x7, #9, MUL VL] + ldr z10, [x7, #10, MUL VL] + ldr z11, [x7, #11, MUL VL] + ldr z12, [x7, #12, MUL VL] + ldr z13, [x7, #13, MUL VL] + ldr z14, [x7, #14, MUL VL] + ldr z15, [x7, #15, MUL VL] + ldr z16, [x7, #16, MUL VL] + ldr z17, [x7, #17, MUL VL] + ldr z18, [x7, #18, MUL VL] + ldr z19, [x7, #19, MUL VL] + ldr z20, [x7, #20, MUL VL] + ldr z21, [x7, #21, MUL VL] + ldr z22, [x7, #22, MUL VL] + ldr z23, [x7, #23, MUL VL] + ldr z24, [x7, #24, MUL VL] + ldr z25, [x7, #25, MUL VL] + ldr z26, [x7, #26, MUL VL] + ldr z27, [x7, #27, MUL VL] + ldr z28, [x7, #28, MUL VL] + ldr z29, [x7, #29, MUL VL] + ldr z30, [x7, #30, MUL VL] + ldr z31, [x7, #31, MUL VL] + + // FFR is not present in base SME + cbz x4, 1f + ldr x7, =ffr_in + ldr p0, [x7] + ldr x7, [x7, #0] + cbz x7, 1f + wrffr p0.b +1: + + ldr x7, =p_in + ldr p0, [x7, #0, MUL VL] + ldr p1, [x7, #1, MUL VL] + ldr p2, [x7, #2, MUL VL] + ldr p3, [x7, #3, MUL VL] + ldr p4, [x7, #4, MUL VL] + ldr p5, [x7, #5, MUL VL] + ldr p6, [x7, #6, MUL VL] + ldr p7, [x7, #7, MUL VL] + ldr p8, [x7, #8, MUL VL] + ldr p9, [x7, #9, MUL VL] + ldr p10, [x7, #10, MUL VL] + ldr p11, [x7, #11, MUL VL] + ldr p12, [x7, #12, MUL VL] + ldr p13, [x7, #13, MUL VL] + ldr p14, [x7, #14, MUL VL] + ldr p15, [x7, #15, MUL VL] + +wait_for_writes: + // Wait for the parent + brk #0 + + // Save values + ldr x7, =v_out + stp q0, q1, [x7] + stp q2, q3, [x7, #16 * 2] + stp q4, q5, [x7, #16 * 4] + stp q6, q7, [x7, #16 * 6] + stp q8, q9, [x7, #16 * 8] + stp q10, q11, [x7, #16 * 10] + stp q12, q13, [x7, #16 * 12] + stp q14, q15, [x7, #16 * 14] + stp q16, q17, [x7, #16 * 16] + stp q18, q19, [x7, #16 * 18] + stp q20, q21, [x7, #16 * 20] + stp q22, q23, [x7, #16 * 22] + stp q24, q25, [x7, #16 * 24] + stp q26, q27, [x7, #16 * 26] + stp q28, q29, [x7, #16 * 28] + stp q30, q31, [x7, #16 * 30] + + // SME? + cbz x1, check_sve_out + + rdsvl 11, 1 + adrp x6, sme_vl_out + str x11, [x6, :lo12:sme_vl_out] + + mrs x7, S3_3_C4_C2_2 + adrp x6, svcr_out + str x7, [x6, :lo12:svcr_out] + + // ZA? + tbz x7, #SVCR_ZA_SHIFT, check_sm_out + mov w12, #0 + ldr x6, =za_out +1: _str_za 12, 6 + add x6, x6, x11 + add x12, x12, #1 + cmp x11, x12 + bne 1b + + // ZT? + cbz x2, check_sm_out + adrp x6, zt_out + add x6, x6, :lo12:zt_out + _str_zt 6 + + // In streaming mode? +check_sm_out: + tbz x7, #SVCR_SM_SHIFT, check_sve_out + mov x4, x3 // FFR? + b read_sve + + // SVE? +check_sve_out: + cbz x0, wait_for_reads + mov x4, #1 + + rdvl x7, #1 + adrp x6, sve_vl_out + str x7, [x6, :lo12:sve_vl_out] + +read_sve: + ldr x7, =z_out + str z0, [x7, #0, MUL VL] + str z1, [x7, #1, MUL VL] + str z2, [x7, #2, MUL VL] + str z3, [x7, #3, MUL VL] + str z4, [x7, #4, MUL VL] + str z5, [x7, #5, MUL VL] + str z6, [x7, #6, MUL VL] + str z7, [x7, #7, MUL VL] + str z8, [x7, #8, MUL VL] + str z9, [x7, #9, MUL VL] + str z10, [x7, #10, MUL VL] + str z11, [x7, #11, MUL VL] + str z12, [x7, #12, MUL VL] + str z13, [x7, #13, MUL VL] + str z14, [x7, #14, MUL VL] + str z15, [x7, #15, MUL VL] + str z16, [x7, #16, MUL VL] + str z17, [x7, #17, MUL VL] + str z18, [x7, #18, MUL VL] + str z19, [x7, #19, MUL VL] + str z20, [x7, #20, MUL VL] + str z21, [x7, #21, MUL VL] + str z22, [x7, #22, MUL VL] + str z23, [x7, #23, MUL VL] + str z24, [x7, #24, MUL VL] + str z25, [x7, #25, MUL VL] + str z26, [x7, #26, MUL VL] + str z27, [x7, #27, MUL VL] + str z28, [x7, #28, MUL VL] + str z29, [x7, #29, MUL VL] + str z30, [x7, #30, MUL VL] + str z31, [x7, #31, MUL VL] + + ldr x7, =p_out + str p0, [x7, #0, MUL VL] + str p1, [x7, #1, MUL VL] + str p2, [x7, #2, MUL VL] + str p3, [x7, #3, MUL VL] + str p4, [x7, #4, MUL VL] + str p5, [x7, #5, MUL VL] + str p6, [x7, #6, MUL VL] + str p7, [x7, #7, MUL VL] + str p8, [x7, #8, MUL VL] + str p9, [x7, #9, MUL VL] + str p10, [x7, #10, MUL VL] + str p11, [x7, #11, MUL VL] + str p12, [x7, #12, MUL VL] + str p13, [x7, #13, MUL VL] + str p14, [x7, #14, MUL VL] + str p15, [x7, #15, MUL VL] + + // Only save FFR if it exists + cbz x4, wait_for_reads + ldr x7, =ffr_out + rdffr p0.b + str p0, [x7] + +wait_for_reads: + // Wait for the parent + brk #0 + + // Ensure we don't leave ourselves in streaming mode + cbz x1, out + msr S3_3_C4_C2_2, xzr + +out: + ldp x11, x12, [sp, #-0x10] + ret diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.c b/tools/testing/selftests/arm64/fp/fp-ptrace.c new file mode 100644 index 000000000000..c7ceafe5f471 --- /dev/null +++ b/tools/testing/selftests/arm64/fp/fp-ptrace.c @@ -0,0 +1,1503 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023 ARM Limited. + * Original author: Mark Brown <broonie@kernel.org> + */ + +#define _GNU_SOURCE + +#include <errno.h> +#include <stdbool.h> +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +#include <sys/auxv.h> +#include <sys/prctl.h> +#include <sys/ptrace.h> +#include <sys/types.h> +#include <sys/uio.h> +#include <sys/wait.h> + +#include <linux/kernel.h> + +#include <asm/sigcontext.h> +#include <asm/sve_context.h> +#include <asm/ptrace.h> + +#include "../../kselftest.h" + +#include "fp-ptrace.h" + +/* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */ +#ifndef NT_ARM_SVE +#define NT_ARM_SVE 0x405 +#endif + +#ifndef NT_ARM_SSVE +#define NT_ARM_SSVE 0x40b +#endif + +#ifndef NT_ARM_ZA +#define NT_ARM_ZA 0x40c +#endif + +#ifndef NT_ARM_ZT +#define NT_ARM_ZT 0x40d +#endif + +#define ARCH_VQ_MAX 256 + +/* VL 128..2048 in powers of 2 */ +#define MAX_NUM_VLS 5 + +#define NUM_FPR 32 +__uint128_t v_in[NUM_FPR]; +__uint128_t v_expected[NUM_FPR]; +__uint128_t v_out[NUM_FPR]; + +char z_in[__SVE_ZREGS_SIZE(ARCH_VQ_MAX)]; +char z_expected[__SVE_ZREGS_SIZE(ARCH_VQ_MAX)]; +char z_out[__SVE_ZREGS_SIZE(ARCH_VQ_MAX)]; + +char p_in[__SVE_PREGS_SIZE(ARCH_VQ_MAX)]; +char p_expected[__SVE_PREGS_SIZE(ARCH_VQ_MAX)]; +char p_out[__SVE_PREGS_SIZE(ARCH_VQ_MAX)]; + +char ffr_in[__SVE_PREG_SIZE(ARCH_VQ_MAX)]; +char ffr_expected[__SVE_PREG_SIZE(ARCH_VQ_MAX)]; +char ffr_out[__SVE_PREG_SIZE(ARCH_VQ_MAX)]; + +char za_in[ZA_SIG_REGS_SIZE(ARCH_VQ_MAX)]; +char za_expected[ZA_SIG_REGS_SIZE(ARCH_VQ_MAX)]; +char za_out[ZA_SIG_REGS_SIZE(ARCH_VQ_MAX)]; + +char zt_in[ZT_SIG_REG_BYTES]; +char zt_expected[ZT_SIG_REG_BYTES]; +char zt_out[ZT_SIG_REG_BYTES]; + +uint64_t sve_vl_out; +uint64_t sme_vl_out; +uint64_t svcr_in, svcr_expected, svcr_out; + +void load_and_save(int sve, int sme, int sme2, int fa64); + +static bool got_alarm; + +static void handle_alarm(int sig, siginfo_t *info, void *context) +{ + got_alarm = true; +} + +#ifdef CONFIG_CPU_BIG_ENDIAN +static __uint128_t arm64_cpu_to_le128(__uint128_t x) +{ + u64 a = swab64(x); + u64 b = swab64(x >> 64); + + return ((__uint128_t)a << 64) | b; +} +#else +static __uint128_t arm64_cpu_to_le128(__uint128_t x) +{ + return x; +} +#endif + +#define arm64_le128_to_cpu(x) arm64_cpu_to_le128(x) + +static bool sve_supported(void) +{ + return getauxval(AT_HWCAP) & HWCAP_SVE; +} + +static bool sme_supported(void) +{ + return getauxval(AT_HWCAP2) & HWCAP2_SME; +} + +static bool sme2_supported(void) +{ + return getauxval(AT_HWCAP2) & HWCAP2_SME2; +} + +static bool fa64_supported(void) +{ + return getauxval(AT_HWCAP2) & HWCAP2_SME_FA64; +} + +static bool compare_buffer(const char *name, void *out, + void *expected, size_t size) +{ + void *tmp; + + if (memcmp(out, expected, size) == 0) + return true; + + ksft_print_msg("Mismatch in %s\n", name); + + /* Did we just get zeros back? */ + tmp = malloc(size); + if (!tmp) { + ksft_print_msg("OOM allocating %lu bytes for %s\n", + size, name); + ksft_exit_fail(); + } + memset(tmp, 0, size); + + if (memcmp(out, tmp, size) == 0) + ksft_print_msg("%s is zero\n", name); + + free(tmp); + + return false; +} + +struct test_config { + int sve_vl_in; + int sve_vl_expected; + int sme_vl_in; + int sme_vl_expected; + int svcr_in; + int svcr_expected; +}; + +struct test_definition { + const char *name; + bool sve_vl_change; + bool (*supported)(struct test_config *config); + void (*set_expected_values)(struct test_config *config); + void (*modify_values)(pid_t child, struct test_config *test_config); +}; + +static int vl_in(struct test_config *config) +{ + int vl; + + if (config->svcr_in & SVCR_SM) + vl = config->sme_vl_in; + else + vl = config->sve_vl_in; + + return vl; +} + +static int vl_expected(struct test_config *config) +{ + int vl; + + if (config->svcr_expected & SVCR_SM) + vl = config->sme_vl_expected; + else + vl = config->sve_vl_expected; + + return vl; +} + +static void run_child(struct test_config *config) +{ + int ret; + + /* Let the parent attach to us */ + ret = ptrace(PTRACE_TRACEME, 0, 0, 0); + if (ret < 0) + ksft_exit_fail_msg("PTRACE_TRACEME failed: %s (%d)\n", + strerror(errno), errno); + + /* VL setup */ + if (sve_supported()) { + ret = prctl(PR_SVE_SET_VL, config->sve_vl_in); + if (ret != config->sve_vl_in) { + ksft_print_msg("Failed to set SVE VL %d: %d\n", + config->sve_vl_in, ret); + } + } + + if (sme_supported()) { + ret = prctl(PR_SME_SET_VL, config->sme_vl_in); + if (ret != config->sme_vl_in) { + ksft_print_msg("Failed to set SME VL %d: %d\n", + config->sme_vl_in, ret); + } + } + + /* Load values and wait for the parent */ + load_and_save(sve_supported(), sme_supported(), + sme2_supported(), fa64_supported()); + + exit(0); +} + +static void read_one_child_regs(pid_t child, char *name, + struct iovec *iov_parent, + struct iovec *iov_child) +{ + int len = iov_parent->iov_len; + int ret; + + ret = process_vm_readv(child, iov_parent, 1, iov_child, 1, 0); + if (ret == -1) + ksft_print_msg("%s read failed: %s (%d)\n", + name, strerror(errno), errno); + else if (ret != len) + ksft_print_msg("Short read of %s: %d\n", name, ret); +} + +static void read_child_regs(pid_t child) +{ + struct iovec iov_parent, iov_child; + + /* + * Since the child fork()ed from us the buffer addresses are + * the same in parent and child. + */ + iov_parent.iov_base = &v_out; + iov_parent.iov_len = sizeof(v_out); + iov_child.iov_base = &v_out; + iov_child.iov_len = sizeof(v_out); + read_one_child_regs(child, "FPSIMD", &iov_parent, &iov_child); + + if (sve_supported() || sme_supported()) { + iov_parent.iov_base = &sve_vl_out; + iov_parent.iov_len = sizeof(sve_vl_out); + iov_child.iov_base = &sve_vl_out; + iov_child.iov_len = sizeof(sve_vl_out); + read_one_child_regs(child, "SVE VL", &iov_parent, &iov_child); + + iov_parent.iov_base = &z_out; + iov_parent.iov_len = sizeof(z_out); + iov_child.iov_base = &z_out; + iov_child.iov_len = sizeof(z_out); + read_one_child_regs(child, "Z", &iov_parent, &iov_child); + + iov_parent.iov_base = &p_out; + iov_parent.iov_len = sizeof(p_out); + iov_child.iov_base = &p_out; + iov_child.iov_len = sizeof(p_out); + read_one_child_regs(child, "P", &iov_parent, &iov_child); + + iov_parent.iov_base = &ffr_out; + iov_parent.iov_len = sizeof(ffr_out); + iov_child.iov_base = &ffr_out; + iov_child.iov_len = sizeof(ffr_out); + read_one_child_regs(child, "FFR", &iov_parent, &iov_child); + } + + if (sme_supported()) { + iov_parent.iov_base = &sme_vl_out; + iov_parent.iov_len = sizeof(sme_vl_out); + iov_child.iov_base = &sme_vl_out; + iov_child.iov_len = sizeof(sme_vl_out); + read_one_child_regs(child, "SME VL", &iov_parent, &iov_child); + + iov_parent.iov_base = &svcr_out; + iov_parent.iov_len = sizeof(svcr_out); + iov_child.iov_base = &svcr_out; + iov_child.iov_len = sizeof(svcr_out); + read_one_child_regs(child, "SVCR", &iov_parent, &iov_child); + + iov_parent.iov_base = &za_out; + iov_parent.iov_len = sizeof(za_out); + iov_child.iov_base = &za_out; + iov_child.iov_len = sizeof(za_out); + read_one_child_regs(child, "ZA", &iov_parent, &iov_child); + } + + if (sme2_supported()) { + iov_parent.iov_base = &zt_out; + iov_parent.iov_len = sizeof(zt_out); + iov_child.iov_base = &zt_out; + iov_child.iov_len = sizeof(zt_out); + read_one_child_regs(child, "ZT", &iov_parent, &iov_child); + } +} + +static bool continue_breakpoint(pid_t child, + enum __ptrace_request restart_type) +{ + struct user_pt_regs pt_regs; + struct iovec iov; + int ret; + + /* Get PC */ + iov.iov_base = &pt_regs; + iov.iov_len = sizeof(pt_regs); + ret = ptrace(PTRACE_GETREGSET, child, NT_PRSTATUS, &iov); + if (ret < 0) { + ksft_print_msg("Failed to get PC: %s (%d)\n", + strerror(errno), errno); + return false; + } + + /* Skip over the BRK */ + pt_regs.pc += 4; + ret = ptrace(PTRACE_SETREGSET, child, NT_PRSTATUS, &iov); + if (ret < 0) { + ksft_print_msg("Failed to skip BRK: %s (%d)\n", + strerror(errno), errno); + return false; + } + + /* Restart */ + ret = ptrace(restart_type, child, 0, 0); + if (ret < 0) { + ksft_print_msg("Failed to restart child: %s (%d)\n", + strerror(errno), errno); + return false; + } + + return true; +} + +static bool check_ptrace_values_sve(pid_t child, struct test_config *config) +{ + struct user_sve_header *sve; + struct user_fpsimd_state *fpsimd; + struct iovec iov; + int ret, vq; + bool pass = true; + + if (!sve_supported()) + return true; + + vq = __sve_vq_from_vl(config->sve_vl_in); + + iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + iov.iov_base = malloc(iov.iov_len); + if (!iov.iov_base) { + ksft_print_msg("OOM allocating %lu byte SVE buffer\n", + iov.iov_len); + return false; + } + + ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_SVE, &iov); + if (ret != 0) { + ksft_print_msg("Failed to read initial SVE: %s (%d)\n", + strerror(errno), errno); + pass = false; + goto out; + } + + sve = iov.iov_base; + + if (sve->vl != config->sve_vl_in) { + ksft_print_msg("Mismatch in initial SVE VL: %d != %d\n", + sve->vl, config->sve_vl_in); + pass = false; + } + + /* If we are in streaming mode we should just read FPSIMD */ + if ((config->svcr_in & SVCR_SM) && (sve->flags & SVE_PT_REGS_SVE)) { + ksft_print_msg("NT_ARM_SVE reports SVE with PSTATE.SM\n"); + pass = false; + } + + if (sve->size != SVE_PT_SIZE(vq, sve->flags)) { + ksft_print_msg("Mismatch in SVE header size: %d != %lu\n", + sve->size, SVE_PT_SIZE(vq, sve->flags)); + pass = false; + } + + /* The registers might be in completely different formats! */ + if (sve->flags & SVE_PT_REGS_SVE) { + if (!compare_buffer("initial SVE Z", + iov.iov_base + SVE_PT_SVE_ZREG_OFFSET(vq, 0), + z_in, SVE_PT_SVE_ZREGS_SIZE(vq))) + pass = false; + + if (!compare_buffer("initial SVE P", + iov.iov_base + SVE_PT_SVE_PREG_OFFSET(vq, 0), + p_in, SVE_PT_SVE_PREGS_SIZE(vq))) + pass = false; + + if (!compare_buffer("initial SVE FFR", + iov.iov_base + SVE_PT_SVE_FFR_OFFSET(vq), + ffr_in, SVE_PT_SVE_PREG_SIZE(vq))) + pass = false; + } else { + fpsimd = iov.iov_base + SVE_PT_FPSIMD_OFFSET; + if (!compare_buffer("initial V via SVE", &fpsimd->vregs[0], + v_in, sizeof(v_in))) + pass = false; + } + +out: + free(iov.iov_base); + return pass; +} + +static bool check_ptrace_values_ssve(pid_t child, struct test_config *config) +{ + struct user_sve_header *sve; + struct user_fpsimd_state *fpsimd; + struct iovec iov; + int ret, vq; + bool pass = true; + + if (!sme_supported()) + return true; + + vq = __sve_vq_from_vl(config->sme_vl_in); + + iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + iov.iov_base = malloc(iov.iov_len); + if (!iov.iov_base) { + ksft_print_msg("OOM allocating %lu byte SSVE buffer\n", + iov.iov_len); + return false; + } + + ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_SSVE, &iov); + if (ret != 0) { + ksft_print_msg("Failed to read initial SSVE: %s (%d)\n", + strerror(errno), errno); + pass = false; + goto out; + } + + sve = iov.iov_base; + + if (sve->vl != config->sme_vl_in) { + ksft_print_msg("Mismatch in initial SSVE VL: %d != %d\n", + sve->vl, config->sme_vl_in); + pass = false; + } + + if ((config->svcr_in & SVCR_SM) && !(sve->flags & SVE_PT_REGS_SVE)) { + ksft_print_msg("NT_ARM_SSVE reports FPSIMD with PSTATE.SM\n"); + pass = false; + } + + if (sve->size != SVE_PT_SIZE(vq, sve->flags)) { + ksft_print_msg("Mismatch in SSVE header size: %d != %lu\n", + sve->size, SVE_PT_SIZE(vq, sve->flags)); + pass = false; + } + + /* The registers might be in completely different formats! */ + if (sve->flags & SVE_PT_REGS_SVE) { + if (!compare_buffer("initial SSVE Z", + iov.iov_base + SVE_PT_SVE_ZREG_OFFSET(vq, 0), + z_in, SVE_PT_SVE_ZREGS_SIZE(vq))) + pass = false; + + if (!compare_buffer("initial SSVE P", + iov.iov_base + SVE_PT_SVE_PREG_OFFSET(vq, 0), + p_in, SVE_PT_SVE_PREGS_SIZE(vq))) + pass = false; + + if (!compare_buffer("initial SSVE FFR", + iov.iov_base + SVE_PT_SVE_FFR_OFFSET(vq), + ffr_in, SVE_PT_SVE_PREG_SIZE(vq))) + pass = false; + } else { + fpsimd = iov.iov_base + SVE_PT_FPSIMD_OFFSET; + if (!compare_buffer("initial V via SSVE", + &fpsimd->vregs[0], v_in, sizeof(v_in))) + pass = false; + } + +out: + free(iov.iov_base); + return pass; +} + +static bool check_ptrace_values_za(pid_t child, struct test_config *config) +{ + struct user_za_header *za; + struct iovec iov; + int ret, vq; + bool pass = true; + + if (!sme_supported()) + return true; + + vq = __sve_vq_from_vl(config->sme_vl_in); + + iov.iov_len = ZA_SIG_CONTEXT_SIZE(vq); + iov.iov_base = malloc(iov.iov_len); + if (!iov.iov_base) { + ksft_print_msg("OOM allocating %lu byte ZA buffer\n", + iov.iov_len); + return false; + } + + ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_ZA, &iov); + if (ret != 0) { + ksft_print_msg("Failed to read initial ZA: %s (%d)\n", + strerror(errno), errno); + pass = false; + goto out; + } + + za = iov.iov_base; + + if (za->vl != config->sme_vl_in) { + ksft_print_msg("Mismatch in initial SME VL: %d != %d\n", + za->vl, config->sme_vl_in); + pass = false; + } + + /* If PSTATE.ZA is not set we should just read the header */ + if (config->svcr_in & SVCR_ZA) { + if (za->size != ZA_PT_SIZE(vq)) { + ksft_print_msg("Unexpected ZA ptrace read size: %d != %lu\n", + za->size, ZA_PT_SIZE(vq)); + pass = false; + } + + if (!compare_buffer("initial ZA", + iov.iov_base + ZA_PT_ZA_OFFSET, + za_in, ZA_PT_ZA_SIZE(vq))) + pass = false; + } else { + if (za->size != sizeof(*za)) { + ksft_print_msg("Unexpected ZA ptrace read size: %d != %lu\n", + za->size, sizeof(*za)); + pass = false; + } + } + +out: + free(iov.iov_base); + return pass; +} + +static bool check_ptrace_values_zt(pid_t child, struct test_config *config) +{ + uint8_t buf[512]; + struct iovec iov; + int ret; + + if (!sme2_supported()) + return true; + + iov.iov_base = &buf; + iov.iov_len = ZT_SIG_REG_BYTES; + ret = ptrace(PTRACE_GETREGSET, child, NT_ARM_ZT, &iov); + if (ret != 0) { + ksft_print_msg("Failed to read initial ZT: %s (%d)\n", + strerror(errno), errno); + return false; + } + + return compare_buffer("initial ZT", buf, zt_in, ZT_SIG_REG_BYTES); +} + + +static bool check_ptrace_values(pid_t child, struct test_config *config) +{ + bool pass = true; + struct user_fpsimd_state fpsimd; + struct iovec iov; + int ret; + + iov.iov_base = &fpsimd; + iov.iov_len = sizeof(fpsimd); + ret = ptrace(PTRACE_GETREGSET, child, NT_PRFPREG, &iov); + if (ret == 0) { + if (!compare_buffer("initial V", &fpsimd.vregs, v_in, + sizeof(v_in))) { + pass = false; + } + } else { + ksft_print_msg("Failed to read initial V: %s (%d)\n", + strerror(errno), errno); + pass = false; + } + + if (!check_ptrace_values_sve(child, config)) + pass = false; + + if (!check_ptrace_values_ssve(child, config)) + pass = false; + + if (!check_ptrace_values_za(child, config)) + pass = false; + + if (!check_ptrace_values_zt(child, config)) + pass = false; + + return pass; +} + +static bool run_parent(pid_t child, struct test_definition *test, + struct test_config *config) +{ + int wait_status, ret; + pid_t pid; + bool pass; + + /* Initial attach */ + while (1) { + pid = waitpid(child, &wait_status, 0); + if (pid < 0) { + if (errno == EINTR) + continue; + ksft_exit_fail_msg("waitpid() failed: %s (%d)\n", + strerror(errno), errno); + } + + if (pid == child) + break; + } + + if (WIFEXITED(wait_status)) { + ksft_print_msg("Child exited loading values with status %d\n", + WEXITSTATUS(wait_status)); + pass = false; + goto out; + } + + if (WIFSIGNALED(wait_status)) { + ksft_print_msg("Child died from signal %d loading values\n", + WTERMSIG(wait_status)); + pass = false; + goto out; + } + + /* Read initial values via ptrace */ + pass = check_ptrace_values(child, config); + + /* Do whatever writes we want to do */ + if (test->modify_values) + test->modify_values(child, config); + + if (!continue_breakpoint(child, PTRACE_CONT)) + goto cleanup; + + while (1) { + pid = waitpid(child, &wait_status, 0); + if (pid < 0) { + if (errno == EINTR) + continue; + ksft_exit_fail_msg("waitpid() failed: %s (%d)\n", + strerror(errno), errno); + } + + if (pid == child) + break; + } + + if (WIFEXITED(wait_status)) { + ksft_print_msg("Child exited saving values with status %d\n", + WEXITSTATUS(wait_status)); + pass = false; + goto out; + } + + if (WIFSIGNALED(wait_status)) { + ksft_print_msg("Child died from signal %d saving values\n", + WTERMSIG(wait_status)); + pass = false; + goto out; + } + + /* See what happened as a result */ + read_child_regs(child); + + if (!continue_breakpoint(child, PTRACE_DETACH)) + goto cleanup; + + /* The child should exit cleanly */ + got_alarm = false; + alarm(1); + while (1) { + if (got_alarm) { + ksft_print_msg("Wait for child timed out\n"); + goto cleanup; + } + + pid = waitpid(child, &wait_status, 0); + if (pid < 0) { + if (errno == EINTR) + continue; + ksft_exit_fail_msg("waitpid() failed: %s (%d)\n", + strerror(errno), errno); + } + + if (pid == child) + break; + } + alarm(0); + + if (got_alarm) { + ksft_print_msg("Timed out waiting for child\n"); + pass = false; + goto cleanup; + } + + if (pid == child && WIFSIGNALED(wait_status)) { + ksft_print_msg("Child died from signal %d cleaning up\n", + WTERMSIG(wait_status)); + pass = false; + goto out; + } + + if (pid == child && WIFEXITED(wait_status)) { + if (WEXITSTATUS(wait_status) != 0) { + ksft_print_msg("Child exited with error %d\n", + WEXITSTATUS(wait_status)); + pass = false; + } + } else { + ksft_print_msg("Child did not exit cleanly\n"); + pass = false; + goto cleanup; + } + + goto out; + +cleanup: + ret = kill(child, SIGKILL); + if (ret != 0) { + ksft_print_msg("kill() failed: %s (%d)\n", + strerror(errno), errno); + return false; + } + + while (1) { + pid = waitpid(child, &wait_status, 0); + if (pid < 0) { + if (errno == EINTR) + continue; + ksft_exit_fail_msg("waitpid() failed: %s (%d)\n", + strerror(errno), errno); + } + + if (pid == child) + break; + } + +out: + return pass; +} + +static void fill_random(void *buf, size_t size) +{ + int i; + uint32_t *lbuf = buf; + + /* random() returns a 32 bit number regardless of the size of long */ + for (i = 0; i < size / sizeof(uint32_t); i++) + lbuf[i] = random(); +} + +static void fill_random_ffr(void *buf, size_t vq) +{ + uint8_t *lbuf = buf; + int bits, i; + + /* + * Only values with a continuous set of 0..n bits set are + * valid for FFR, set all bits then clear a random number of + * high bits. + */ + memset(buf, 0, __SVE_FFR_SIZE(vq)); + + bits = random() % (__SVE_FFR_SIZE(vq) * 8); + for (i = 0; i < bits / 8; i++) + lbuf[i] = 0xff; + if (bits / 8 != __SVE_FFR_SIZE(vq)) + lbuf[i] = (1 << (bits % 8)) - 1; +} + +static void fpsimd_to_sve(__uint128_t *v, char *z, int vl) +{ + int vq = __sve_vq_from_vl(vl); + int i; + __uint128_t *p; + + if (!vl) + return; + + for (i = 0; i < __SVE_NUM_ZREGS; i++) { + p = (__uint128_t *)&z[__SVE_ZREG_OFFSET(vq, i)]; + *p = arm64_cpu_to_le128(v[i]); + } +} + +static void set_initial_values(struct test_config *config) +{ + int vq = __sve_vq_from_vl(vl_in(config)); + int sme_vq = __sve_vq_from_vl(config->sme_vl_in); + + svcr_in = config->svcr_in; + svcr_expected = config->svcr_expected; + svcr_out = 0; + + fill_random(&v_in, sizeof(v_in)); + memcpy(v_expected, v_in, sizeof(v_in)); + memset(v_out, 0, sizeof(v_out)); + + /* Changes will be handled in the test case */ + if (sve_supported() || (config->svcr_in & SVCR_SM)) { + /* The low 128 bits of Z are shared with the V registers */ + fill_random(&z_in, __SVE_ZREGS_SIZE(vq)); + fpsimd_to_sve(v_in, z_in, vl_in(config)); + memcpy(z_expected, z_in, __SVE_ZREGS_SIZE(vq)); + memset(z_out, 0, sizeof(z_out)); + + fill_random(&p_in, __SVE_PREGS_SIZE(vq)); + memcpy(p_expected, p_in, __SVE_PREGS_SIZE(vq)); + memset(p_out, 0, sizeof(p_out)); + + if ((config->svcr_in & SVCR_SM) && !fa64_supported()) + memset(ffr_in, 0, __SVE_PREG_SIZE(vq)); + else + fill_random_ffr(&ffr_in, vq); + memcpy(ffr_expected, ffr_in, __SVE_PREG_SIZE(vq)); + memset(ffr_out, 0, __SVE_PREG_SIZE(vq)); + } + + if (config->svcr_in & SVCR_ZA) + fill_random(za_in, ZA_SIG_REGS_SIZE(sme_vq)); + else + memset(za_in, 0, ZA_SIG_REGS_SIZE(sme_vq)); + if (config->svcr_expected & SVCR_ZA) + memcpy(za_expected, za_in, ZA_SIG_REGS_SIZE(sme_vq)); + else + memset(za_expected, 0, ZA_SIG_REGS_SIZE(sme_vq)); + if (sme_supported()) + memset(za_out, 0, sizeof(za_out)); + + if (sme2_supported()) { + if (config->svcr_in & SVCR_ZA) + fill_random(zt_in, ZT_SIG_REG_BYTES); + else + memset(zt_in, 0, ZT_SIG_REG_BYTES); + if (config->svcr_expected & SVCR_ZA) + memcpy(zt_expected, zt_in, ZT_SIG_REG_BYTES); + else + memset(zt_expected, 0, ZT_SIG_REG_BYTES); + memset(zt_out, 0, sizeof(zt_out)); + } +} + +static bool check_memory_values(struct test_config *config) +{ + bool pass = true; + int vq, sme_vq; + + if (!compare_buffer("saved V", v_out, v_expected, sizeof(v_out))) + pass = false; + + vq = __sve_vq_from_vl(vl_expected(config)); + sme_vq = __sve_vq_from_vl(config->sme_vl_expected); + + if (svcr_out != svcr_expected) { + ksft_print_msg("Mismatch in saved SVCR %lx != %lx\n", + svcr_out, svcr_expected); + pass = false; + } + + if (sve_vl_out != config->sve_vl_expected) { + ksft_print_msg("Mismatch in SVE VL: %ld != %d\n", + sve_vl_out, config->sve_vl_expected); + pass = false; + } + + if (sme_vl_out != config->sme_vl_expected) { + ksft_print_msg("Mismatch in SME VL: %ld != %d\n", + sme_vl_out, config->sme_vl_expected); + pass = false; + } + + if (!compare_buffer("saved Z", z_out, z_expected, + __SVE_ZREGS_SIZE(vq))) + pass = false; + + if (!compare_buffer("saved P", p_out, p_expected, + __SVE_PREGS_SIZE(vq))) + pass = false; + + if (!compare_buffer("saved FFR", ffr_out, ffr_expected, + __SVE_PREG_SIZE(vq))) + pass = false; + + if (!compare_buffer("saved ZA", za_out, za_expected, + ZA_PT_ZA_SIZE(sme_vq))) + pass = false; + + if (!compare_buffer("saved ZT", zt_out, zt_expected, ZT_SIG_REG_BYTES)) + pass = false; + + return pass; +} + +static bool sve_sme_same(struct test_config *config) +{ + if (config->sve_vl_in != config->sve_vl_expected) + return false; + + if (config->sme_vl_in != config->sme_vl_expected) + return false; + + if (config->svcr_in != config->svcr_expected) + return false; + + return true; +} + +static bool sve_write_supported(struct test_config *config) +{ + if (!sve_supported() && !sme_supported()) + return false; + + if ((config->svcr_in & SVCR_ZA) != (config->svcr_expected & SVCR_ZA)) + return false; + + if (config->svcr_expected & SVCR_SM) { + if (config->sve_vl_in != config->sve_vl_expected) { + return false; + } + + /* Changing the SME VL disables ZA */ + if ((config->svcr_expected & SVCR_ZA) && + (config->sme_vl_in != config->sme_vl_expected)) { + return false; + } + } else { + if (config->sme_vl_in != config->sme_vl_expected) { + return false; + } + } + + return true; +} + +static void fpsimd_write_expected(struct test_config *config) +{ + int vl; + + fill_random(&v_expected, sizeof(v_expected)); + + /* The SVE registers are flushed by a FPSIMD write */ + vl = vl_expected(config); + + memset(z_expected, 0, __SVE_ZREGS_SIZE(__sve_vq_from_vl(vl))); + memset(p_expected, 0, __SVE_PREGS_SIZE(__sve_vq_from_vl(vl))); + memset(ffr_expected, 0, __SVE_PREG_SIZE(__sve_vq_from_vl(vl))); + + fpsimd_to_sve(v_expected, z_expected, vl); +} + +static void fpsimd_write(pid_t child, struct test_config *test_config) +{ + struct user_fpsimd_state fpsimd; + struct iovec iov; + int ret; + + memset(&fpsimd, 0, sizeof(fpsimd)); + memcpy(&fpsimd.vregs, v_expected, sizeof(v_expected)); + + iov.iov_base = &fpsimd; + iov.iov_len = sizeof(fpsimd); + ret = ptrace(PTRACE_SETREGSET, child, NT_PRFPREG, &iov); + if (ret == -1) + ksft_print_msg("FPSIMD set failed: (%s) %d\n", + strerror(errno), errno); +} + +static void sve_write_expected(struct test_config *config) +{ + int vl = vl_expected(config); + int sme_vq = __sve_vq_from_vl(config->sme_vl_expected); + + fill_random(z_expected, __SVE_ZREGS_SIZE(__sve_vq_from_vl(vl))); + fill_random(p_expected, __SVE_PREGS_SIZE(__sve_vq_from_vl(vl))); + + if ((svcr_expected & SVCR_SM) && !fa64_supported()) + memset(ffr_expected, 0, __SVE_PREG_SIZE(sme_vq)); + else + fill_random_ffr(ffr_expected, __sve_vq_from_vl(vl)); + + /* Share the low bits of Z with V */ + fill_random(&v_expected, sizeof(v_expected)); + fpsimd_to_sve(v_expected, z_expected, vl); + + if (config->sme_vl_in != config->sme_vl_expected) { + memset(za_expected, 0, ZA_PT_ZA_SIZE(sme_vq)); + memset(zt_expected, 0, sizeof(zt_expected)); + } +} + +static void sve_write(pid_t child, struct test_config *config) +{ + struct user_sve_header *sve; + struct iovec iov; + int ret, vl, vq, regset; + + vl = vl_expected(config); + vq = __sve_vq_from_vl(vl); + + iov.iov_len = SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE); + iov.iov_base = malloc(iov.iov_len); + if (!iov.iov_base) { + ksft_print_msg("Failed allocating %lu byte SVE write buffer\n", + iov.iov_len); + return; + } + memset(iov.iov_base, 0, iov.iov_len); + + sve = iov.iov_base; + sve->size = iov.iov_len; + sve->flags = SVE_PT_REGS_SVE; + sve->vl = vl; + + memcpy(iov.iov_base + SVE_PT_SVE_ZREG_OFFSET(vq, 0), + z_expected, SVE_PT_SVE_ZREGS_SIZE(vq)); + memcpy(iov.iov_base + SVE_PT_SVE_PREG_OFFSET(vq, 0), + p_expected, SVE_PT_SVE_PREGS_SIZE(vq)); + memcpy(iov.iov_base + SVE_PT_SVE_FFR_OFFSET(vq), + ffr_expected, SVE_PT_SVE_PREG_SIZE(vq)); + + if (svcr_expected & SVCR_SM) + regset = NT_ARM_SSVE; + else + regset = NT_ARM_SVE; + + ret = ptrace(PTRACE_SETREGSET, child, regset, &iov); + if (ret != 0) + ksft_print_msg("Failed to write SVE: %s (%d)\n", + strerror(errno), errno); + + free(iov.iov_base); +} + +static bool za_write_supported(struct test_config *config) +{ + if (config->svcr_expected & SVCR_SM) { + if (!(config->svcr_in & SVCR_SM)) + return false; + + /* Changing the SME VL exits streaming mode */ + if (config->sme_vl_in != config->sme_vl_expected) { + return false; + } + } + + /* Can't disable SM outside a VL change */ + if ((config->svcr_in & SVCR_SM) && + !(config->svcr_expected & SVCR_SM)) + return false; + + return true; +} + +static void za_write_expected(struct test_config *config) +{ + int sme_vq, sve_vq; + + sme_vq = __sve_vq_from_vl(config->sme_vl_expected); + + if (config->svcr_expected & SVCR_ZA) { + fill_random(za_expected, ZA_PT_ZA_SIZE(sme_vq)); + } else { + memset(za_expected, 0, ZA_PT_ZA_SIZE(sme_vq)); + memset(zt_expected, 0, sizeof(zt_expected)); + } + + /* Changing the SME VL flushes ZT, SVE state and exits SM */ + if (config->sme_vl_in != config->sme_vl_expected) { + svcr_expected &= ~SVCR_SM; + + sve_vq = __sve_vq_from_vl(vl_expected(config)); + memset(z_expected, 0, __SVE_ZREGS_SIZE(sve_vq)); + memset(p_expected, 0, __SVE_PREGS_SIZE(sve_vq)); + memset(ffr_expected, 0, __SVE_PREG_SIZE(sve_vq)); + memset(zt_expected, 0, sizeof(zt_expected)); + + fpsimd_to_sve(v_expected, z_expected, vl_expected(config)); + } +} + +static void za_write(pid_t child, struct test_config *config) +{ + struct user_za_header *za; + struct iovec iov; + int ret, vq; + + vq = __sve_vq_from_vl(config->sme_vl_expected); + + if (config->svcr_expected & SVCR_ZA) + iov.iov_len = ZA_PT_SIZE(vq); + else + iov.iov_len = sizeof(*za); + iov.iov_base = malloc(iov.iov_len); + if (!iov.iov_base) { + ksft_print_msg("Failed allocating %lu byte ZA write buffer\n", + iov.iov_len); + return; + } + memset(iov.iov_base, 0, iov.iov_len); + + za = iov.iov_base; + za->size = iov.iov_len; + za->vl = config->sme_vl_expected; + if (config->svcr_expected & SVCR_ZA) + memcpy(iov.iov_base + ZA_PT_ZA_OFFSET, za_expected, + ZA_PT_ZA_SIZE(vq)); + + ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_ZA, &iov); + if (ret != 0) + ksft_print_msg("Failed to write ZA: %s (%d)\n", + strerror(errno), errno); + + free(iov.iov_base); +} + +static bool zt_write_supported(struct test_config *config) +{ + if (!sme2_supported()) + return false; + if (config->sme_vl_in != config->sme_vl_expected) + return false; + if (!(config->svcr_expected & SVCR_ZA)) + return false; + if ((config->svcr_in & SVCR_SM) != (config->svcr_expected & SVCR_SM)) + return false; + + return true; +} + +static void zt_write_expected(struct test_config *config) +{ + int sme_vq; + + sme_vq = __sve_vq_from_vl(config->sme_vl_expected); + + if (config->svcr_expected & SVCR_ZA) { + fill_random(zt_expected, sizeof(zt_expected)); + } else { + memset(za_expected, 0, ZA_PT_ZA_SIZE(sme_vq)); + memset(zt_expected, 0, sizeof(zt_expected)); + } +} + +static void zt_write(pid_t child, struct test_config *config) +{ + struct iovec iov; + int ret; + + iov.iov_len = ZT_SIG_REG_BYTES; + iov.iov_base = zt_expected; + ret = ptrace(PTRACE_SETREGSET, child, NT_ARM_ZT, &iov); + if (ret != 0) + ksft_print_msg("Failed to write ZT: %s (%d)\n", + strerror(errno), errno); +} + +/* Actually run a test */ +static void run_test(struct test_definition *test, struct test_config *config) +{ + pid_t child; + char name[1024]; + bool pass; + + if (sve_supported() && sme_supported()) + snprintf(name, sizeof(name), "%s, SVE %d->%d, SME %d/%x->%d/%x", + test->name, + config->sve_vl_in, config->sve_vl_expected, + config->sme_vl_in, config->svcr_in, + config->sme_vl_expected, config->svcr_expected); + else if (sve_supported()) + snprintf(name, sizeof(name), "%s, SVE %d->%d", test->name, + config->sve_vl_in, config->sve_vl_expected); + else if (sme_supported()) + snprintf(name, sizeof(name), "%s, SME %d/%x->%d/%x", + test->name, + config->sme_vl_in, config->svcr_in, + config->sme_vl_expected, config->svcr_expected); + else + snprintf(name, sizeof(name), "%s", test->name); + + if (test->supported && !test->supported(config)) { + ksft_test_result_skip("%s\n", name); + return; + } + + set_initial_values(config); + + if (test->set_expected_values) + test->set_expected_values(config); + + child = fork(); + if (child < 0) + ksft_exit_fail_msg("fork() failed: %s (%d)\n", + strerror(errno), errno); + /* run_child() never returns */ + if (child == 0) + run_child(config); + + pass = run_parent(child, test, config); + if (!check_memory_values(config)) + pass = false; + + ksft_test_result(pass, "%s\n", name); +} + +static void run_tests(struct test_definition defs[], int count, + struct test_config *config) +{ + int i; + + for (i = 0; i < count; i++) + run_test(&defs[i], config); +} + +static struct test_definition base_test_defs[] = { + { + .name = "No writes", + .supported = sve_sme_same, + }, + { + .name = "FPSIMD write", + .supported = sve_sme_same, + .set_expected_values = fpsimd_write_expected, + .modify_values = fpsimd_write, + }, +}; + +static struct test_definition sve_test_defs[] = { + { + .name = "SVE write", + .supported = sve_write_supported, + .set_expected_values = sve_write_expected, + .modify_values = sve_write, + }, +}; + +static struct test_definition za_test_defs[] = { + { + .name = "ZA write", + .supported = za_write_supported, + .set_expected_values = za_write_expected, + .modify_values = za_write, + }, +}; + +static struct test_definition zt_test_defs[] = { + { + .name = "ZT write", + .supported = zt_write_supported, + .set_expected_values = zt_write_expected, + .modify_values = zt_write, + }, +}; + +static int sve_vls[MAX_NUM_VLS], sme_vls[MAX_NUM_VLS]; +static int sve_vl_count, sme_vl_count; + +static void probe_vls(const char *name, int vls[], int *vl_count, int set_vl) +{ + unsigned int vq; + int vl; + + *vl_count = 0; + + for (vq = ARCH_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", + strerror(errno), errno); + + 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; + *vl_count += 1; + } + + if (*vl_count > 2) { + /* Just use the minimum and maximum */ + vls[1] = vls[*vl_count - 1]; + ksft_print_msg("%d %s VLs, using %d and %d\n", + *vl_count, name, vls[0], vls[1]); + *vl_count = 2; + } else { + ksft_print_msg("%d %s VLs\n", *vl_count, name); + } +} + +static struct { + int svcr_in, svcr_expected; +} svcr_combinations[] = { + { .svcr_in = 0, .svcr_expected = 0, }, + { .svcr_in = 0, .svcr_expected = SVCR_SM, }, + { .svcr_in = 0, .svcr_expected = SVCR_ZA, }, + /* Can't enable both SM and ZA with a single ptrace write */ + + { .svcr_in = SVCR_SM, .svcr_expected = 0, }, + { .svcr_in = SVCR_SM, .svcr_expected = SVCR_SM, }, + { .svcr_in = SVCR_SM, .svcr_expected = SVCR_ZA, }, + { .svcr_in = SVCR_SM, .svcr_expected = SVCR_SM | SVCR_ZA, }, + + { .svcr_in = SVCR_ZA, .svcr_expected = 0, }, + { .svcr_in = SVCR_ZA, .svcr_expected = SVCR_SM, }, + { .svcr_in = SVCR_ZA, .svcr_expected = SVCR_ZA, }, + { .svcr_in = SVCR_ZA, .svcr_expected = SVCR_SM | SVCR_ZA, }, + + { .svcr_in = SVCR_SM | SVCR_ZA, .svcr_expected = 0, }, + { .svcr_in = SVCR_SM | SVCR_ZA, .svcr_expected = SVCR_SM, }, + { .svcr_in = SVCR_SM | SVCR_ZA, .svcr_expected = SVCR_ZA, }, + { .svcr_in = SVCR_SM | SVCR_ZA, .svcr_expected = SVCR_SM | SVCR_ZA, }, +}; + +static void run_sve_tests(void) +{ + struct test_config test_config; + int i, j; + + if (!sve_supported()) + return; + + test_config.sme_vl_in = sme_vls[0]; + test_config.sme_vl_expected = sme_vls[0]; + test_config.svcr_in = 0; + test_config.svcr_expected = 0; + + for (i = 0; i < sve_vl_count; i++) { + test_config.sve_vl_in = sve_vls[i]; + + for (j = 0; j < sve_vl_count; j++) { + test_config.sve_vl_expected = sve_vls[j]; + + run_tests(base_test_defs, + ARRAY_SIZE(base_test_defs), + &test_config); + if (sve_supported()) + run_tests(sve_test_defs, + ARRAY_SIZE(sve_test_defs), + &test_config); + } + } + +} + +static void run_sme_tests(void) +{ + struct test_config test_config; + int i, j, k; + + if (!sme_supported()) + return; + + test_config.sve_vl_in = sve_vls[0]; + test_config.sve_vl_expected = sve_vls[0]; + + /* + * Every SME VL/SVCR combination + */ + for (i = 0; i < sme_vl_count; i++) { + test_config.sme_vl_in = sme_vls[i]; + + for (j = 0; j < sme_vl_count; j++) { + test_config.sme_vl_expected = sme_vls[j]; + + for (k = 0; k < ARRAY_SIZE(svcr_combinations); k++) { + test_config.svcr_in = svcr_combinations[k].svcr_in; + test_config.svcr_expected = svcr_combinations[k].svcr_expected; + + run_tests(base_test_defs, + ARRAY_SIZE(base_test_defs), + &test_config); + run_tests(sve_test_defs, + ARRAY_SIZE(sve_test_defs), + &test_config); + run_tests(za_test_defs, + ARRAY_SIZE(za_test_defs), + &test_config); + + if (sme2_supported()) + run_tests(zt_test_defs, + ARRAY_SIZE(zt_test_defs), + &test_config); + } + } + } +} + +int main(void) +{ + struct test_config test_config; + struct sigaction sa; + int tests, ret, tmp; + + srandom(getpid()); + + ksft_print_header(); + + if (sve_supported()) { + probe_vls("SVE", sve_vls, &sve_vl_count, PR_SVE_SET_VL); + + tests = ARRAY_SIZE(base_test_defs) + + ARRAY_SIZE(sve_test_defs); + tests *= sve_vl_count * sve_vl_count; + } else { + /* Only run the FPSIMD tests */ + sve_vl_count = 1; + tests = ARRAY_SIZE(base_test_defs); + } + + if (sme_supported()) { + probe_vls("SME", sme_vls, &sme_vl_count, PR_SME_SET_VL); + + tmp = ARRAY_SIZE(base_test_defs) + ARRAY_SIZE(sve_test_defs) + + ARRAY_SIZE(za_test_defs); + + if (sme2_supported()) + tmp += ARRAY_SIZE(zt_test_defs); + + tmp *= sme_vl_count * sme_vl_count; + tmp *= ARRAY_SIZE(svcr_combinations); + tests += tmp; + } else { + sme_vl_count = 1; + } + + if (sme2_supported()) + ksft_print_msg("SME2 supported\n"); + + if (fa64_supported()) + ksft_print_msg("FA64 supported\n"); + + ksft_set_plan(tests); + + /* Get signal handers ready before we start any children */ + memset(&sa, 0, sizeof(sa)); + sa.sa_sigaction = handle_alarm; + sa.sa_flags = SA_RESTART | SA_SIGINFO; + sigemptyset(&sa.sa_mask); + ret = sigaction(SIGALRM, &sa, NULL); + if (ret < 0) + ksft_print_msg("Failed to install SIGALRM handler: %s (%d)\n", + strerror(errno), errno); + + /* + * Run the test set if there is no SVE or SME, with those we + * have to pick a VL for each run. + */ + if (!sve_supported()) { + test_config.sve_vl_in = 0; + test_config.sve_vl_expected = 0; + test_config.sme_vl_in = 0; + test_config.sme_vl_expected = 0; + test_config.svcr_in = 0; + test_config.svcr_expected = 0; + + run_tests(base_test_defs, ARRAY_SIZE(base_test_defs), + &test_config); + } + + run_sve_tests(); + run_sme_tests(); + + ksft_finished(); +} diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.h b/tools/testing/selftests/arm64/fp/fp-ptrace.h new file mode 100644 index 000000000000..db4f2c4d750c --- /dev/null +++ b/tools/testing/selftests/arm64/fp/fp-ptrace.h @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright (C) 2021-3 ARM Limited. + +#ifndef FP_PTRACE_H +#define FP_PTRACE_H + +#define SVCR_SM_SHIFT 0 +#define SVCR_ZA_SHIFT 1 + +#define SVCR_SM (1 << SVCR_SM_SHIFT) +#define SVCR_ZA (1 << SVCR_ZA_SHIFT) + +#endif diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore index 839e3a252629..1ce5b5eac386 100644 --- a/tools/testing/selftests/arm64/signal/.gitignore +++ b/tools/testing/selftests/arm64/signal/.gitignore @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only mangle_* fake_sigreturn_* +fpmr_* sme_* ssve_* sve_* diff --git a/tools/testing/selftests/arm64/signal/testcases/fpmr_siginfo.c b/tools/testing/selftests/arm64/signal/testcases/fpmr_siginfo.c new file mode 100644 index 000000000000..e9d24685e741 --- /dev/null +++ b/tools/testing/selftests/arm64/signal/testcases/fpmr_siginfo.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 ARM Limited + * + * Verify that the FPMR 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_FPMR "S3_3_C4_C4_2" + +static uint64_t get_fpmr(void) +{ + uint64_t val; + + asm volatile ( + "mrs %0, " SYS_FPMR "\n" + : "=r"(val) + : + : "cc"); + + return val; +} + +int fpmr_present(struct tdescr *td, siginfo_t *si, ucontext_t *uc) +{ + struct _aarch64_ctx *head = GET_BUF_RESV_HEAD(context); + struct fpmr_context *fpmr_ctx; + size_t offset; + bool in_sigframe; + bool have_fpmr; + __u64 orig_fpmr; + + have_fpmr = getauxval(AT_HWCAP2) & HWCAP2_FPMR; + if (have_fpmr) + orig_fpmr = get_fpmr(); + + if (!get_current_context(td, &context.uc, sizeof(context))) + return 1; + + fpmr_ctx = (struct fpmr_context *) + get_header(head, FPMR_MAGIC, td->live_sz, &offset); + + in_sigframe = fpmr_ctx != NULL; + + fprintf(stderr, "FPMR sigframe %s on system %s FPMR\n", + in_sigframe ? "present" : "absent", + have_fpmr ? "with" : "without"); + + td->pass = (in_sigframe == have_fpmr); + + if (have_fpmr && fpmr_ctx) { + if (fpmr_ctx->fpmr != orig_fpmr) { + fprintf(stderr, "FPMR in frame is %llx, was %llx\n", + fpmr_ctx->fpmr, orig_fpmr); + td->pass = false; + } + } + + return 0; +} + +struct tdescr tde = { + .name = "FPMR", + .descr = "Validate that FPMR is present as expected", + .timeout = 3, + .run = fpmr_present, +}; diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c index 9f580b55b388..674b88cc8c39 100644 --- a/tools/testing/selftests/arm64/signal/testcases/testcases.c +++ b/tools/testing/selftests/arm64/signal/testcases/testcases.c @@ -209,6 +209,14 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err) zt = (struct zt_context *)head; new_flags |= ZT_CTX; break; + case FPMR_MAGIC: + if (flags & FPMR_CTX) + *err = "Multiple FPMR_MAGIC"; + else if (head->size != + sizeof(struct fpmr_context)) + *err = "Bad size for fpmr_context"; + new_flags |= FPMR_CTX; + break; case EXTRA_MAGIC: if (flags & EXTRA_CTX) *err = "Multiple EXTRA_MAGIC"; diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.h b/tools/testing/selftests/arm64/signal/testcases/testcases.h index a08ab0d6207a..7727126347e0 100644 --- a/tools/testing/selftests/arm64/signal/testcases/testcases.h +++ b/tools/testing/selftests/arm64/signal/testcases/testcases.h @@ -19,6 +19,7 @@ #define ZA_CTX (1 << 2) #define EXTRA_CTX (1 << 3) #define ZT_CTX (1 << 4) +#define FPMR_CTX (1 << 5) #define KSFT_BAD_MAGIC 0xdeadbeef |