diff options
| -rw-r--r-- | arch/arm64/include/asm/fpsimd.h | 12 | ||||
| -rw-r--r-- | arch/arm64/include/uapi/asm/ptrace.h | 138 | ||||
| -rw-r--r-- | arch/arm64/kernel/fpsimd.c | 60 | ||||
| -rw-r--r-- | arch/arm64/kernel/ptrace.c | 280 | ||||
| -rw-r--r-- | include/uapi/linux/elf.h | 1 |
5 files changed, 482 insertions, 9 deletions
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index d8e0dc9f65a1..d754e5a6949c 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -38,13 +38,16 @@ struct fpsimd_state { __uint128_t vregs[32]; u32 fpsr; u32 fpcr; + /* + * For ptrace compatibility, pad to next 128-bit + * boundary here if extending this struct. + */ }; }; /* the id of the last cpu to have restored this state */ unsigned int cpu; }; - #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* Masks for extracting the FPSR and FPCR from the FPSCR */ #define VFP_FPSCR_STAT_MASK 0xf800009f @@ -88,6 +91,10 @@ extern size_t sve_state_size(struct task_struct const *task); extern void sve_alloc(struct task_struct *task); extern void fpsimd_release_task(struct task_struct *task); +extern void fpsimd_sync_to_sve(struct task_struct *task); +extern void sve_sync_to_fpsimd(struct task_struct *task); +extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task); + extern int sve_set_vector_length(struct task_struct *task, unsigned long vl, unsigned long flags); @@ -104,6 +111,9 @@ extern void __init sve_setup(void); static inline void sve_alloc(struct task_struct *task) { } static inline void fpsimd_release_task(struct task_struct *task) { } +static inline void sve_sync_to_fpsimd(struct task_struct *task) { } +static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { } + static inline void sve_init_vq_map(void) { } static inline void sve_update_vq_map(void) { } static inline int sve_verify_vq_map(void) { return 0; } diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 3697d95ba0a1..e7085589f81c 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -22,6 +22,7 @@ #include <linux/types.h> #include <asm/hwcap.h> +#include <asm/sigcontext.h> /* @@ -62,6 +63,8 @@ #ifndef __ASSEMBLY__ +#include <linux/prctl.h> + /* * User structures for general purpose, floating point and debug registers. */ @@ -89,6 +92,141 @@ struct user_hwdebug_state { } dbg_regs[16]; }; +/* SVE/FP/SIMD state (NT_ARM_SVE) */ + +struct user_sve_header { + __u32 size; /* total meaningful regset content in bytes */ + __u32 max_size; /* maxmium possible size for this thread */ + __u16 vl; /* current vector length */ + __u16 max_vl; /* maximum possible vector length */ + __u16 flags; + __u16 __reserved; +}; + +/* Definitions for user_sve_header.flags: */ +#define SVE_PT_REGS_MASK (1 << 0) + +#define SVE_PT_REGS_FPSIMD 0 +#define SVE_PT_REGS_SVE SVE_PT_REGS_MASK + +/* + * Common SVE_PT_* flags: + * These must be kept in sync with prctl interface in <linux/ptrace.h> + */ +#define SVE_PT_VL_INHERIT (PR_SVE_VL_INHERIT >> 16) +#define SVE_PT_VL_ONEXEC (PR_SVE_SET_VL_ONEXEC >> 16) + + +/* + * The remainder of the SVE state follows struct user_sve_header. The + * total size of the SVE state (including header) depends on the + * metadata in the header: SVE_PT_SIZE(vq, flags) gives the total size + * of the state in bytes, including the header. + * + * Refer to <asm/sigcontext.h> for details of how to pass the correct + * "vq" argument to these macros. + */ + +/* Offset from the start of struct user_sve_header to the register data */ +#define SVE_PT_REGS_OFFSET \ + ((sizeof(struct sve_context) + (SVE_VQ_BYTES - 1)) \ + / SVE_VQ_BYTES * SVE_VQ_BYTES) + +/* + * The register data content and layout depends on the value of the + * flags field. + */ + +/* + * (flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD case: + * + * The payload starts at offset SVE_PT_FPSIMD_OFFSET, and is of type + * struct user_fpsimd_state. Additional data might be appended in the + * future: use SVE_PT_FPSIMD_SIZE(vq, flags) to compute the total size. + * SVE_PT_FPSIMD_SIZE(vq, flags) will never be less than + * sizeof(struct user_fpsimd_state). + */ + +#define SVE_PT_FPSIMD_OFFSET SVE_PT_REGS_OFFSET + +#define SVE_PT_FPSIMD_SIZE(vq, flags) (sizeof(struct user_fpsimd_state)) + +/* + * (flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE case: + * + * The payload starts at offset SVE_PT_SVE_OFFSET, and is of size + * SVE_PT_SVE_SIZE(vq, flags). + * + * Additional macros describe the contents and layout of the payload. + * For each, SVE_PT_SVE_x_OFFSET(args) is the start offset relative to + * the start of struct user_sve_header, and SVE_PT_SVE_x_SIZE(args) is + * the size in bytes: + * + * x type description + * - ---- ----------- + * ZREGS \ + * ZREG | + * PREGS | refer to <asm/sigcontext.h> + * PREG | + * FFR / + * + * FPSR uint32_t FPSR + * FPCR uint32_t FPCR + * + * Additional data might be appended in the future. + */ + +#define SVE_PT_SVE_ZREG_SIZE(vq) SVE_SIG_ZREG_SIZE(vq) +#define SVE_PT_SVE_PREG_SIZE(vq) SVE_SIG_PREG_SIZE(vq) +#define SVE_PT_SVE_FFR_SIZE(vq) SVE_SIG_FFR_SIZE(vq) +#define SVE_PT_SVE_FPSR_SIZE sizeof(__u32) +#define SVE_PT_SVE_FPCR_SIZE sizeof(__u32) + +#define __SVE_SIG_TO_PT(offset) \ + ((offset) - SVE_SIG_REGS_OFFSET + SVE_PT_REGS_OFFSET) + +#define SVE_PT_SVE_OFFSET SVE_PT_REGS_OFFSET + +#define SVE_PT_SVE_ZREGS_OFFSET \ + __SVE_SIG_TO_PT(SVE_SIG_ZREGS_OFFSET) +#define SVE_PT_SVE_ZREG_OFFSET(vq, n) \ + __SVE_SIG_TO_PT(SVE_SIG_ZREG_OFFSET(vq, n)) +#define SVE_PT_SVE_ZREGS_SIZE(vq) \ + (SVE_PT_SVE_ZREG_OFFSET(vq, SVE_NUM_ZREGS) - SVE_PT_SVE_ZREGS_OFFSET) + +#define SVE_PT_SVE_PREGS_OFFSET(vq) \ + __SVE_SIG_TO_PT(SVE_SIG_PREGS_OFFSET(vq)) +#define SVE_PT_SVE_PREG_OFFSET(vq, n) \ + __SVE_SIG_TO_PT(SVE_SIG_PREG_OFFSET(vq, n)) +#define SVE_PT_SVE_PREGS_SIZE(vq) \ + (SVE_PT_SVE_PREG_OFFSET(vq, SVE_NUM_PREGS) - \ + SVE_PT_SVE_PREGS_OFFSET(vq)) + +#define SVE_PT_SVE_FFR_OFFSET(vq) \ + __SVE_SIG_TO_PT(SVE_SIG_FFR_OFFSET(vq)) + +#define SVE_PT_SVE_FPSR_OFFSET(vq) \ + ((SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq) + \ + (SVE_VQ_BYTES - 1)) \ + / SVE_VQ_BYTES * SVE_VQ_BYTES) +#define SVE_PT_SVE_FPCR_OFFSET(vq) \ + (SVE_PT_SVE_FPSR_OFFSET(vq) + SVE_PT_SVE_FPSR_SIZE) + +/* + * Any future extension appended after FPCR must be aligned to the next + * 128-bit boundary. + */ + +#define SVE_PT_SVE_SIZE(vq, flags) \ + ((SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE \ + - SVE_PT_SVE_OFFSET + (SVE_VQ_BYTES - 1)) \ + / SVE_VQ_BYTES * SVE_VQ_BYTES) + +#define SVE_PT_SIZE(vq, flags) \ + (((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_SVE ? \ + SVE_PT_SVE_OFFSET + SVE_PT_SVE_SIZE(vq, flags) \ + : SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags)) + #endif /* __ASSEMBLY__ */ #endif /* _UAPI__ASM_PTRACE_H */ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 1e531156f1d7..b82d44693b9d 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -428,6 +428,66 @@ void sve_alloc(struct task_struct *task) BUG_ON(!task->thread.sve_state); } + +/* + * Ensure that task->thread.sve_state is up to date with respect to + * the user task, irrespective of when SVE is in use or not. + * + * This should only be called by ptrace. task must be non-runnable. + * task->thread.sve_state must point to at least sve_state_size(task) + * bytes of allocated kernel memory. + */ +void fpsimd_sync_to_sve(struct task_struct *task) +{ + if (!test_tsk_thread_flag(task, TIF_SVE)) + fpsimd_to_sve(task); +} + +/* + * Ensure that task->thread.fpsimd_state is up to date with respect to + * the user task, irrespective of whether SVE is in use or not. + * + * This should only be called by ptrace. task must be non-runnable. + * task->thread.sve_state must point to at least sve_state_size(task) + * bytes of allocated kernel memory. + */ +void sve_sync_to_fpsimd(struct task_struct *task) +{ + if (test_tsk_thread_flag(task, TIF_SVE)) + sve_to_fpsimd(task); +} + +/* + * Ensure that task->thread.sve_state is up to date with respect to + * the task->thread.fpsimd_state. + * + * This should only be called by ptrace to merge new FPSIMD register + * values into a task for which SVE is currently active. + * task must be non-runnable. + * task->thread.sve_state must point to at least sve_state_size(task) + * bytes of allocated kernel memory. + * task->thread.fpsimd_state must already have been initialised with + * the new FPSIMD register values to be merged in. + */ +void sve_sync_from_fpsimd_zeropad(struct task_struct *task) +{ + unsigned int vq; + void *sst = task->thread.sve_state; + struct fpsimd_state const *fst = &task->thread.fpsimd_state; + unsigned int i; + + if (!test_tsk_thread_flag(task, TIF_SVE)) + return; + + vq = sve_vq_from_vl(task->thread.sve_vl); + + memset(sst, 0, SVE_SIG_REGS_SIZE(vq)); + + for (i = 0; i < 32; ++i) + memcpy(ZREG(sst, vq, i), &fst->vregs[i], + sizeof(fst->vregs[i])); +} + int sve_set_vector_length(struct task_struct *task, unsigned long vl, unsigned long flags) { diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 9cbb6123208f..7c44658b316d 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -32,6 +32,7 @@ #include <linux/security.h> #include <linux/init.h> #include <linux/signal.h> +#include <linux/string.h> #include <linux/uaccess.h> #include <linux/perf_event.h> #include <linux/hw_breakpoint.h> @@ -40,6 +41,7 @@ #include <linux/elf.h> #include <asm/compat.h> +#include <asm/cpufeature.h> #include <asm/debug-monitors.h> #include <asm/pgtable.h> #include <asm/stacktrace.h> @@ -618,17 +620,56 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset, /* * TODO: update fp accessors for lazy context switching (sync/flush hwstate) */ -static int fpr_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - void *kbuf, void __user *ubuf) +static int __fpr_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf, unsigned int start_pos) { struct user_fpsimd_state *uregs; + + sve_sync_to_fpsimd(target); + uregs = &target->thread.fpsimd_state.user_fpsimd; + return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, + start_pos, start_pos + sizeof(*uregs)); +} + +static int fpr_get(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ if (target == current) fpsimd_preserve_current_state(); - return user_regset_copyout(&pos, &count, &kbuf, &ubuf, uregs, 0, -1); + return __fpr_get(target, regset, pos, count, kbuf, ubuf, 0); +} + +static int __fpr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf, + unsigned int start_pos) +{ + int ret; + struct user_fpsimd_state newstate; + + /* + * Ensure target->thread.fpsimd_state is up to date, so that a + * short copyin can't resurrect stale data. + */ + sve_sync_to_fpsimd(target); + + newstate = target->thread.fpsimd_state.user_fpsimd; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, + start_pos, start_pos + sizeof(newstate)); + if (ret) + return ret; + + target->thread.fpsimd_state.user_fpsimd = newstate; + + return ret; } static int fpr_set(struct task_struct *target, const struct user_regset *regset, @@ -636,15 +677,14 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, const void *kbuf, const void __user *ubuf) { int ret; - struct user_fpsimd_state newstate = - target->thread.fpsimd_state.user_fpsimd; - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, 0, -1); + ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, 0); if (ret) return ret; - target->thread.fpsimd_state.user_fpsimd = newstate; + sve_sync_from_fpsimd_zeropad(target); fpsimd_flush_task_state(target); + return ret; } @@ -702,6 +742,215 @@ static int system_call_set(struct task_struct *target, return ret; } +#ifdef CONFIG_ARM64_SVE + +static void sve_init_header_from_task(struct user_sve_header *header, + struct task_struct *target) +{ + unsigned int vq; + + memset(header, 0, sizeof(*header)); + + header->flags = test_tsk_thread_flag(target, TIF_SVE) ? + SVE_PT_REGS_SVE : SVE_PT_REGS_FPSIMD; + if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) + header->flags |= SVE_PT_VL_INHERIT; + + header->vl = target->thread.sve_vl; + vq = sve_vq_from_vl(header->vl); + + header->max_vl = sve_max_vl; + if (WARN_ON(!sve_vl_valid(sve_max_vl))) + header->max_vl = header->vl; + + header->size = SVE_PT_SIZE(vq, header->flags); + header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl), + SVE_PT_REGS_SVE); +} + +static unsigned int sve_size_from_header(struct user_sve_header const *header) +{ + return ALIGN(header->size, SVE_VQ_BYTES); +} + +static unsigned int sve_get_size(struct task_struct *target, + const struct user_regset *regset) +{ + struct user_sve_header header; + + if (!system_supports_sve()) + return 0; + + sve_init_header_from_task(&header, target); + return sve_size_from_header(&header); +} + +static int sve_get(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + struct user_sve_header header; + unsigned int vq; + unsigned long start, end; + + if (!system_supports_sve()) + return -EINVAL; + + /* Header */ + sve_init_header_from_task(&header, target); + vq = sve_vq_from_vl(header.vl); + + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &header, + 0, sizeof(header)); + if (ret) + return ret; + + if (target == current) + fpsimd_preserve_current_state(); + + /* Registers: FPSIMD-only case */ + + BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header)); + if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD) + return __fpr_get(target, regset, pos, count, kbuf, ubuf, + SVE_PT_FPSIMD_OFFSET); + + /* Otherwise: full SVE case */ + + BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); + start = SVE_PT_SVE_OFFSET; + end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + target->thread.sve_state, + start, end); + if (ret) + return ret; + + start = end; + end = SVE_PT_SVE_FPSR_OFFSET(vq); + ret = user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, + start, end); + if (ret) + return ret; + + /* + * Copy fpsr, and fpcr which must follow contiguously in + * struct fpsimd_state: + */ + start = end; + end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.fpsimd_state.fpsr, + start, end); + if (ret) + return ret; + + start = end; + end = sve_size_from_header(&header); + return user_regset_copyout_zero(&pos, &count, &kbuf, &ubuf, + start, end); +} + +static int sve_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; + struct user_sve_header header; + unsigned int vq; + unsigned long start, end; + + if (!system_supports_sve()) + return -EINVAL; + + /* Header */ + if (count < sizeof(header)) + return -EINVAL; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header, + 0, sizeof(header)); + if (ret) + goto out; + + /* + * Apart from PT_SVE_REGS_MASK, all PT_SVE_* flags are consumed by + * sve_set_vector_length(), which will also validate them for us: + */ + ret = sve_set_vector_length(target, header.vl, + ((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16); + if (ret) + goto out; + + /* Actual VL set may be less than the user asked for: */ + vq = sve_vq_from_vl(target->thread.sve_vl); + + /* Registers: FPSIMD-only case */ + + BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header)); + if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD) { + ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, + SVE_PT_FPSIMD_OFFSET); + clear_tsk_thread_flag(target, TIF_SVE); + goto out; + } + + /* Otherwise: full SVE case */ + + /* + * If setting a different VL from the requested VL and there is + * register data, the data layout will be wrong: don't even + * try to set the registers in this case. + */ + if (count && vq != sve_vq_from_vl(header.vl)) { + ret = -EIO; + goto out; + } + + sve_alloc(target); + + /* + * Ensure target->thread.sve_state is up to date with target's + * FPSIMD regs, so that a short copyin leaves trailing registers + * unmodified. + */ + fpsimd_sync_to_sve(target); + set_tsk_thread_flag(target, TIF_SVE); + + BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); + start = SVE_PT_SVE_OFFSET; + end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + target->thread.sve_state, + start, end); + if (ret) + goto out; + + start = end; + end = SVE_PT_SVE_FPSR_OFFSET(vq); + ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, + start, end); + if (ret) + goto out; + + /* + * Copy fpsr, and fpcr which must follow contiguously in + * struct fpsimd_state: + */ + start = end; + end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.fpsimd_state.fpsr, + start, end); + +out: + fpsimd_flush_task_state(target); + return ret; +} + +#endif /* CONFIG_ARM64_SVE */ + enum aarch64_regset { REGSET_GPR, REGSET_FPR, @@ -711,6 +960,9 @@ enum aarch64_regset { REGSET_HW_WATCH, #endif REGSET_SYSTEM_CALL, +#ifdef CONFIG_ARM64_SVE + REGSET_SVE, +#endif }; static const struct user_regset aarch64_regsets[] = { @@ -768,6 +1020,18 @@ static const struct user_regset aarch64_regsets[] = { .get = system_call_get, .set = system_call_set, }, +#ifdef CONFIG_ARM64_SVE + [REGSET_SVE] = { /* Scalable Vector Extension */ + .core_note_type = NT_ARM_SVE, + .n = DIV_ROUND_UP(SVE_PT_SIZE(SVE_VQ_MAX, SVE_PT_REGS_SVE), + SVE_VQ_BYTES), + .size = SVE_VQ_BYTES, + .align = SVE_VQ_BYTES, + .get = sve_get, + .set = sve_set, + .get_size = sve_get_size, + }, +#endif }; static const struct user_regset_view user_aarch64_view = { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index b5280db9ef6a..735b8f4d12fc 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -416,6 +416,7 @@ typedef struct elf64_shdr { #define NT_ARM_HW_BREAK 0x402 /* ARM hardware breakpoint registers */ #define NT_ARM_HW_WATCH 0x403 /* ARM hardware watchpoint registers */ #define NT_ARM_SYSTEM_CALL 0x404 /* ARM system call number */ +#define NT_ARM_SVE 0x405 /* ARM Scalable Vector Extension registers */ #define NT_METAG_CBUF 0x500 /* Metag catch buffer registers */ #define NT_METAG_RPIPE 0x501 /* Metag read pipeline state */ #define NT_METAG_TLS 0x502 /* Metag TLS pointer */ |