From 761b9b366cec0c81a1cd80930f00611d86521d1b Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 31 Jan 2022 16:54:53 +0000 Subject: elf: Introduce the ARM MTE ELF segment type Memory tags will be dumped in the core file as segments with their own type. Discussions with the binutils and the generic ABI community settled on using new definitions in the PT_*PROC space (and to be documented in the processor-specific ABIs). Introduce PT_ARM_MEMTAG_MTE as (PT_LOPROC + 0x1). Not included in this patch since there is no upstream support but the CHERI/BSD community will also reserve: #define PT_ARM_MEMTAG_CHERI (PT_LOPROC + 0x2) #define PT_RISCV_MEMTAG_CHERI (PT_LOPROC + 0x3) Signed-off-by: Catalin Marinas Acked-by: Luis Machado Link: https://lore.kernel.org/r/20220131165456.2160675-3-catalin.marinas@arm.com Signed-off-by: Will Deacon --- include/uapi/linux/elf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/uapi/linux/elf.h') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 61bf4774b8f2..fe8e5b74cb39 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -40,6 +40,9 @@ typedef __s64 Elf64_Sxword; #define PT_GNU_STACK (PT_LOOS + 0x474e551) +/* ARM MTE memory tag segment type */ +#define PT_ARM_MEMTAG_MTE (PT_LOPROC + 0x1) + /* * Extended Numbering * -- cgit v1.2.3 From 4f0bfdfd8323e5b461fc1042143a1097dba9fced Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 23 Feb 2022 19:34:31 -0800 Subject: ELF: Properly redefine PT_GNU_* in terms of PT_LOOS The PT_GNU_* program header types are actually offsets from PT_LOOS, so redefine them as such, reorder them, and add the missing PT_GNU_RELRO. Cc: Eric Biederman Cc: Peter Collingbourne Cc: Catalin Marinas Cc: Dave Martin Signed-off-by: Kees Cook --- include/uapi/linux/elf.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux/elf.h') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 61bf4774b8f2..6438d55529bf 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -35,10 +35,11 @@ typedef __s64 Elf64_Sxword; #define PT_HIOS 0x6fffffff /* OS-specific */ #define PT_LOPROC 0x70000000 #define PT_HIPROC 0x7fffffff -#define PT_GNU_EH_FRAME 0x6474e550 -#define PT_GNU_PROPERTY 0x6474e553 - +#define PT_GNU_EH_FRAME (PT_LOOS + 0x474e550) #define PT_GNU_STACK (PT_LOOS + 0x474e551) +#define PT_GNU_RELRO (PT_LOOS + 0x474e552) +#define PT_GNU_PROPERTY (PT_LOOS + 0x474e553) + /* * Extended Numbering -- cgit v1.2.3 From e12310a0d30f260b26297bc8d7c95769489af038 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 19 Apr 2022 12:22:28 +0100 Subject: arm64/sme: Implement ptrace support for streaming mode SVE registers The streaming mode SVE registers are represented using the same data structures as for SVE but since the vector lengths supported and in use may not be the same as SVE we represent them with a new type NT_ARM_SSVE. Unfortunately we only have a single 16 bit reserved field available in the header so there is no space to fit the current and maximum vector length for both standard and streaming SVE mode without redefining the structure in a way the creates a complicatd and fragile ABI. Since FFR is not present in streaming mode it is read and written as zero. Setting NT_ARM_SSVE registers will put the task into streaming mode, similarly setting NT_ARM_SVE registers will exit it. Reads that do not correspond to the current mode of the task will return the header with no register data. For compatibility reasons on write setting no flag for the register type will be interpreted as setting SVE registers, though users can provide no register data as an alternative mechanism for doing so. Signed-off-by: Mark Brown Reviewed-by: Catalin Marinas Link: https://lore.kernel.org/r/20220419112247.711548-21-broonie@kernel.org Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/fpsimd.h | 1 + arch/arm64/include/uapi/asm/ptrace.h | 13 ++- arch/arm64/kernel/fpsimd.c | 31 +++-- arch/arm64/kernel/ptrace.c | 214 +++++++++++++++++++++++++++-------- include/uapi/linux/elf.h | 1 + 5 files changed, 201 insertions(+), 59 deletions(-) (limited to 'include/uapi/linux/elf.h') diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 6c33bc832ed4..5afcd0709aae 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -144,6 +144,7 @@ struct vl_info { 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 fpsimd_force_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); diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 758ae984ff97..522b925a78c1 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -109,7 +109,7 @@ struct user_hwdebug_state { } dbg_regs[16]; }; -/* SVE/FP/SIMD state (NT_ARM_SVE) */ +/* SVE/FP/SIMD state (NT_ARM_SVE & NT_ARM_SSVE) */ struct user_sve_header { __u32 size; /* total meaningful regset content in bytes */ @@ -220,6 +220,7 @@ struct user_sve_header { (SVE_PT_SVE_PREG_OFFSET(vq, __SVE_NUM_PREGS) - \ SVE_PT_SVE_PREGS_OFFSET(vq)) +/* For streaming mode SVE (SSVE) FFR must be read and written as zero */ #define SVE_PT_SVE_FFR_OFFSET(vq) \ (SVE_PT_REGS_OFFSET + __SVE_FFR_OFFSET(vq)) @@ -240,10 +241,12 @@ struct user_sve_header { - 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)) +#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) \ + : ((((flags) & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD ? \ + SVE_PT_FPSIMD_OFFSET + SVE_PT_FPSIMD_SIZE(vq, flags) \ + : SVE_PT_REGS_OFFSET))) /* pointer authentication masks (NT_ARM_PAC_MASK) */ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 80f7ca12f855..94f06e9d37cf 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -643,7 +643,7 @@ static void fpsimd_to_sve(struct task_struct *task) if (!system_supports_sve()) return; - vq = sve_vq_from_vl(task_get_sve_vl(task)); + vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); __fpsimd_to_sve(sst, fst, vq); } @@ -660,7 +660,7 @@ static void fpsimd_to_sve(struct task_struct *task) */ static void sve_to_fpsimd(struct task_struct *task) { - unsigned int vq; + unsigned int vq, vl; void const *sst = task->thread.sve_state; struct user_fpsimd_state *fst = &task->thread.uw.fpsimd_state; unsigned int i; @@ -669,7 +669,8 @@ static void sve_to_fpsimd(struct task_struct *task) if (!system_supports_sve()) return; - vq = sve_vq_from_vl(task_get_sve_vl(task)); + vl = thread_get_cur_vl(&task->thread); + vq = sve_vq_from_vl(vl); for (i = 0; i < SVE_NUM_ZREGS; ++i) { p = (__uint128_t const *)ZREG(sst, vq, i); fst->vregs[i] = arm64_le128_to_cpu(*p); @@ -717,6 +718,19 @@ void sve_alloc(struct task_struct *task) } +/* + * Force the FPSIMD state shared with SVE to be updated in the SVE state + * even if the SVE state is the current active state. + * + * 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_force_sync_to_sve(struct task_struct *task) +{ + fpsimd_to_sve(task); +} + /* * 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. @@ -727,7 +741,8 @@ void sve_alloc(struct task_struct *task) */ void fpsimd_sync_to_sve(struct task_struct *task) { - if (!test_tsk_thread_flag(task, TIF_SVE)) + if (!test_tsk_thread_flag(task, TIF_SVE) && + !thread_sm_enabled(&task->thread)) fpsimd_to_sve(task); } @@ -741,7 +756,8 @@ void fpsimd_sync_to_sve(struct task_struct *task) */ void sve_sync_to_fpsimd(struct task_struct *task) { - if (test_tsk_thread_flag(task, TIF_SVE)) + if (test_tsk_thread_flag(task, TIF_SVE) || + thread_sm_enabled(&task->thread)) sve_to_fpsimd(task); } @@ -766,7 +782,7 @@ void sve_sync_from_fpsimd_zeropad(struct task_struct *task) if (!test_tsk_thread_flag(task, TIF_SVE)) return; - vq = sve_vq_from_vl(task_get_sve_vl(task)); + vq = sve_vq_from_vl(thread_get_cur_vl(&task->thread)); memset(sst, 0, SVE_SIG_REGS_SIZE(vq)); __fpsimd_to_sve(sst, fst, vq); @@ -810,8 +826,7 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, /* * To ensure the FPSIMD bits of the SVE vector registers are preserved, * write any live register state back to task_struct, and convert to a - * regular FPSIMD thread. Since the vector length can only be changed - * with a syscall we can't be in streaming mode while reconfiguring. + * regular FPSIMD thread. */ if (task == current) { get_cpu_fpsimd_context(); diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 230a47b9189e..60185c27b394 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -713,21 +713,51 @@ static int system_call_set(struct task_struct *target, #ifdef CONFIG_ARM64_SVE static void sve_init_header_from_task(struct user_sve_header *header, - struct task_struct *target) + struct task_struct *target, + enum vec_type type) { unsigned int vq; + bool active; + bool fpsimd_only; + enum vec_type task_type; 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; + /* Check if the requested registers are active for the task */ + if (thread_sm_enabled(&target->thread)) + task_type = ARM64_VEC_SME; + else + task_type = ARM64_VEC_SVE; + active = (task_type == type); + + switch (type) { + case ARM64_VEC_SVE: + if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) + header->flags |= SVE_PT_VL_INHERIT; + fpsimd_only = !test_tsk_thread_flag(target, TIF_SVE); + break; + case ARM64_VEC_SME: + if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) + header->flags |= SVE_PT_VL_INHERIT; + fpsimd_only = false; + break; + default: + WARN_ON_ONCE(1); + return; + } - header->vl = task_get_sve_vl(target); + if (active) { + if (fpsimd_only) { + header->flags |= SVE_PT_REGS_FPSIMD; + } else { + header->flags |= SVE_PT_REGS_SVE; + } + } + + header->vl = task_get_vl(target, type); vq = sve_vq_from_vl(header->vl); - header->max_vl = sve_max_vl(); + header->max_vl = vec_max_vl(type); 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); @@ -738,19 +768,17 @@ static unsigned int sve_size_from_header(struct user_sve_header const *header) return ALIGN(header->size, SVE_VQ_BYTES); } -static int sve_get(struct task_struct *target, - const struct user_regset *regset, - struct membuf to) +static int sve_get_common(struct task_struct *target, + const struct user_regset *regset, + struct membuf to, + enum vec_type type) { 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); + sve_init_header_from_task(&header, target, type); vq = sve_vq_from_vl(header.vl); membuf_write(&to, &header, sizeof(header)); @@ -758,49 +786,61 @@ static int sve_get(struct task_struct *target, 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) + BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); + + switch ((header.flags & SVE_PT_REGS_MASK)) { + case SVE_PT_REGS_FPSIMD: return __fpr_get(target, regset, to); - /* Otherwise: full SVE case */ + case SVE_PT_REGS_SVE: + start = SVE_PT_SVE_OFFSET; + end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); + membuf_write(&to, target->thread.sve_state, end - start); - 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); - membuf_write(&to, target->thread.sve_state, end - start); + start = end; + end = SVE_PT_SVE_FPSR_OFFSET(vq); + membuf_zero(&to, end - start); - start = end; - end = SVE_PT_SVE_FPSR_OFFSET(vq); - membuf_zero(&to, end - start); + /* + * 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; + membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr, + end - start); - /* - * 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; - membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr, end - start); + start = end; + end = sve_size_from_header(&header); + return membuf_zero(&to, end - start); - start = end; - end = sve_size_from_header(&header); - return membuf_zero(&to, end - start); + default: + return 0; + } } -static int sve_set(struct task_struct *target, +static int sve_get(struct task_struct *target, const struct user_regset *regset, - unsigned int pos, unsigned int count, - const void *kbuf, const void __user *ubuf) + struct membuf to) +{ + if (!system_supports_sve()) + return -EINVAL; + + return sve_get_common(target, regset, to, ARM64_VEC_SVE); +} + +static int sve_set_common(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf, + enum vec_type type) { 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; @@ -813,13 +853,37 @@ static int sve_set(struct task_struct *target, * Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are consumed by * vec_set_vector_length(), which will also validate them for us: */ - ret = vec_set_vector_length(target, ARM64_VEC_SVE, header.vl, + ret = vec_set_vector_length(target, type, 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(task_get_sve_vl(target)); + vq = sve_vq_from_vl(task_get_vl(target, type)); + + /* Enter/exit streaming mode */ + if (system_supports_sme()) { + u64 old_svcr = target->thread.svcr; + + switch (type) { + case ARM64_VEC_SVE: + target->thread.svcr &= ~SYS_SVCR_EL0_SM_MASK; + break; + case ARM64_VEC_SME: + target->thread.svcr |= SYS_SVCR_EL0_SM_MASK; + break; + default: + WARN_ON_ONCE(1); + return -EINVAL; + } + + /* + * If we switched then invalidate any existing SVE + * state and ensure there's storage. + */ + if (target->thread.svcr != old_svcr) + sve_alloc(target); + } /* Registers: FPSIMD-only case */ @@ -828,10 +892,15 @@ static int sve_set(struct task_struct *target, ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, SVE_PT_FPSIMD_OFFSET); clear_tsk_thread_flag(target, TIF_SVE); + if (type == ARM64_VEC_SME) + fpsimd_force_sync_to_sve(target); goto out; } - /* Otherwise: full SVE case */ + /* + * Otherwise: no registers or full SVE case. For backwards + * compatibility reasons we treat empty flags as SVE registers. + */ /* * If setting a different VL from the requested VL and there is @@ -852,8 +921,9 @@ static int sve_set(struct task_struct *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 regs, so that a short copyin leaves trailing + * registers unmodified. Always enable SVE even if going into + * streaming mode. */ fpsimd_sync_to_sve(target); set_tsk_thread_flag(target, TIF_SVE); @@ -889,8 +959,46 @@ out: return ret; } +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) +{ + if (!system_supports_sve()) + return -EINVAL; + + return sve_set_common(target, regset, pos, count, kbuf, ubuf, + ARM64_VEC_SVE); +} + #endif /* CONFIG_ARM64_SVE */ +#ifdef CONFIG_ARM64_SME + +static int ssve_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + if (!system_supports_sme()) + return -EINVAL; + + return sve_get_common(target, regset, to, ARM64_VEC_SME); +} + +static int ssve_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + if (!system_supports_sme()) + return -EINVAL; + + return sve_set_common(target, regset, pos, count, kbuf, ubuf, + ARM64_VEC_SME); +} + +#endif /* CONFIG_ARM64_SME */ + #ifdef CONFIG_ARM64_PTR_AUTH static int pac_mask_get(struct task_struct *target, const struct user_regset *regset, @@ -1108,6 +1216,9 @@ enum aarch64_regset { #ifdef CONFIG_ARM64_SVE REGSET_SVE, #endif +#ifdef CONFIG_ARM64_SVE + REGSET_SSVE, +#endif #ifdef CONFIG_ARM64_PTR_AUTH REGSET_PAC_MASK, REGSET_PAC_ENABLED_KEYS, @@ -1188,6 +1299,17 @@ static const struct user_regset aarch64_regsets[] = { .set = sve_set, }, #endif +#ifdef CONFIG_ARM64_SME + [REGSET_SSVE] = { /* Streaming mode SVE */ + .core_note_type = NT_ARM_SSVE, + .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, + .regset_get = ssve_get, + .set = ssve_set, + }, +#endif #ifdef CONFIG_ARM64_PTR_AUTH [REGSET_PAC_MASK] = { .core_note_type = NT_ARM_PAC_MASK, diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 787c657bfae8..a8dc688e1826 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -431,6 +431,7 @@ typedef struct elf64_shdr { #define NT_ARM_PACG_KEYS 0x408 /* ARM pointer authentication generic key */ #define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */ #define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */ +#define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ #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 */ -- cgit v1.2.3 From 776b4a1cf36411e96972455ca72906b722b80ea1 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 19 Apr 2022 12:22:29 +0100 Subject: arm64/sme: Add ptrace support for ZA The ZA array can be read and written with the NT_ARM_ZA. Similarly to our interface for the SVE vector registers the regset consists of a header with information on the current vector length followed by an optional register data payload, represented as for signals as a series of horizontal vectors from 0 to VL/8 in the endianness independent format used for vectors. On get if ZA is enabled then register data will be provided, otherwise it will be omitted. On set if register data is provided then ZA is enabled and initialized using the provided data, otherwise it is disabled. Signed-off-by: Mark Brown Reviewed-by: Catalin Marinas Link: https://lore.kernel.org/r/20220419112247.711548-22-broonie@kernel.org Signed-off-by: Catalin Marinas --- arch/arm64/include/uapi/asm/ptrace.h | 56 ++++++++++++++ arch/arm64/kernel/ptrace.c | 144 +++++++++++++++++++++++++++++++++++ include/uapi/linux/elf.h | 1 + 3 files changed, 201 insertions(+) (limited to 'include/uapi/linux/elf.h') diff --git a/arch/arm64/include/uapi/asm/ptrace.h b/arch/arm64/include/uapi/asm/ptrace.h index 522b925a78c1..7fa2f7036aa7 100644 --- a/arch/arm64/include/uapi/asm/ptrace.h +++ b/arch/arm64/include/uapi/asm/ptrace.h @@ -268,6 +268,62 @@ struct user_pac_generic_keys { __uint128_t apgakey; }; +/* ZA state (NT_ARM_ZA) */ + +struct user_za_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; +}; + +/* + * Common ZA_PT_* flags: + * These must be kept in sync with prctl interface in + */ +#define ZA_PT_VL_INHERIT ((1 << 17) /* PR_SME_VL_INHERIT */ >> 16) +#define ZA_PT_VL_ONEXEC ((1 << 18) /* PR_SME_SET_VL_ONEXEC */ >> 16) + + +/* + * The remainder of the ZA state follows struct user_za_header. The + * total size of the ZA state (including header) depends on the + * metadata in the header: ZA_PT_SIZE(vq, flags) gives the total size + * of the state in bytes, including the header. + * + * Refer to for details of how to pass the correct + * "vq" argument to these macros. + */ + +/* Offset from the start of struct user_za_header to the register data */ +#define ZA_PT_ZA_OFFSET \ + ((sizeof(struct user_za_header) + (__SVE_VQ_BYTES - 1)) \ + / __SVE_VQ_BYTES * __SVE_VQ_BYTES) + +/* + * The payload starts at offset ZA_PT_ZA_OFFSET, and is of size + * ZA_PT_ZA_SIZE(vq, flags). + * + * The ZA array is stored as a sequence of horizontal vectors ZAV of SVL/8 + * bytes each, starting from vector 0. + * + * Additional data might be appended in the future. + * + * The ZA matrix is represented in memory in an endianness-invariant layout + * which differs from the layout used for the FPSIMD V-registers on big-endian + * systems: see sigcontext.h for more explanation. + */ + +#define ZA_PT_ZAV_OFFSET(vq, n) \ + (ZA_PT_ZA_OFFSET + ((vq * __SVE_VQ_BYTES) * n)) + +#define ZA_PT_ZA_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES)) + +#define ZA_PT_SIZE(vq) \ + (ZA_PT_ZA_OFFSET + ZA_PT_ZA_SIZE(vq)) + #endif /* __ASSEMBLY__ */ #endif /* _UAPI__ASM_PTRACE_H */ diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 60185c27b394..47d8a7472171 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -997,6 +997,141 @@ static int ssve_set(struct task_struct *target, ARM64_VEC_SME); } +static int za_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct user_za_header header; + unsigned int vq; + unsigned long start, end; + + if (!system_supports_sme()) + return -EINVAL; + + /* Header */ + memset(&header, 0, sizeof(header)); + + if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) + header.flags |= ZA_PT_VL_INHERIT; + + header.vl = task_get_sme_vl(target); + vq = sve_vq_from_vl(header.vl); + header.max_vl = sme_max_vl(); + header.max_size = ZA_PT_SIZE(vq); + + /* If ZA is not active there is only the header */ + if (thread_za_enabled(&target->thread)) + header.size = ZA_PT_SIZE(vq); + else + header.size = ZA_PT_ZA_OFFSET; + + membuf_write(&to, &header, sizeof(header)); + + BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header)); + end = ZA_PT_ZA_OFFSET; + + if (target == current) + fpsimd_preserve_current_state(); + + /* Any register data to include? */ + if (thread_za_enabled(&target->thread)) { + start = end; + end = ZA_PT_SIZE(vq); + membuf_write(&to, target->thread.za_state, end - start); + } + + /* Zero any trailing padding */ + start = end; + end = ALIGN(header.size, SVE_VQ_BYTES); + return membuf_zero(&to, end - start); +} + +static int za_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_za_header header; + unsigned int vq; + unsigned long start, end; + + if (!system_supports_sme()) + 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; + + /* + * All current ZA_PT_* flags are consumed by + * vec_set_vector_length(), which will also validate them for + * us: + */ + ret = vec_set_vector_length(target, ARM64_VEC_SME, header.vl, + ((unsigned long)header.flags) << 16); + if (ret) + goto out; + + /* Actual VL set may be less than the user asked for: */ + vq = sve_vq_from_vl(task_get_sme_vl(target)); + + /* Ensure there is some SVE storage for streaming mode */ + if (!target->thread.sve_state) { + sve_alloc(target); + if (!target->thread.sve_state) { + clear_thread_flag(TIF_SME); + ret = -ENOMEM; + goto out; + } + } + + /* Allocate/reinit ZA storage */ + sme_alloc(target); + if (!target->thread.za_state) { + ret = -ENOMEM; + clear_tsk_thread_flag(target, TIF_SME); + goto out; + } + + /* If there is no data then disable ZA */ + if (!count) { + target->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK; + goto out; + } + + /* + * 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 (vq != sve_vq_from_vl(header.vl)) { + ret = -EIO; + goto out; + } + + BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header)); + start = ZA_PT_ZA_OFFSET; + end = ZA_PT_SIZE(vq); + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + target->thread.za_state, + start, end); + if (ret) + goto out; + + /* Mark ZA as active and let userspace use it */ + set_tsk_thread_flag(target, TIF_SME); + target->thread.svcr |= SYS_SVCR_EL0_ZA_MASK; + +out: + fpsimd_flush_task_state(target); + return ret; +} + #endif /* CONFIG_ARM64_SME */ #ifdef CONFIG_ARM64_PTR_AUTH @@ -1218,6 +1353,7 @@ enum aarch64_regset { #endif #ifdef CONFIG_ARM64_SVE REGSET_SSVE, + REGSET_ZA, #endif #ifdef CONFIG_ARM64_PTR_AUTH REGSET_PAC_MASK, @@ -1309,6 +1445,14 @@ static const struct user_regset aarch64_regsets[] = { .regset_get = ssve_get, .set = ssve_set, }, + [REGSET_ZA] = { /* SME ZA */ + .core_note_type = NT_ARM_ZA, + .n = DIV_ROUND_UP(ZA_PT_ZA_SIZE(SVE_VQ_MAX), SVE_VQ_BYTES), + .size = SVE_VQ_BYTES, + .align = SVE_VQ_BYTES, + .regset_get = za_get, + .set = za_set, + }, #endif #ifdef CONFIG_ARM64_PTR_AUTH [REGSET_PAC_MASK] = { diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index a8dc688e1826..97808f958903 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -432,6 +432,7 @@ typedef struct elf64_shdr { #define NT_ARM_TAGGED_ADDR_CTRL 0x409 /* arm64 tagged address control (prctl()) */ #define NT_ARM_PAC_ENABLED_KEYS 0x40a /* arm64 ptr auth enabled keys (prctl()) */ #define NT_ARM_SSVE 0x40b /* ARM Streaming SVE registers */ +#define NT_ARM_ZA 0x40c /* ARM SME ZA registers */ #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 */ -- cgit v1.2.3 From c35fe2a68f29a0bda15ae994154cacaae5f69791 Mon Sep 17 00:00:00 2001 From: Catalin Marinas Date: Mon, 25 Apr 2022 16:18:33 +0100 Subject: elf: Fix the arm64 MTE ELF segment name and value Unfortunately, the name/value choice for the MTE ELF segment type (PT_ARM_MEMTAG_MTE) was pretty poor: LOPROC+1 is already in use by PT_AARCH64_UNWIND, as defined in the AArch64 ELF ABI (https://github.com/ARM-software/abi-aa/blob/main/aaelf64/aaelf64.rst). Update the ELF segment type value to LOPROC+2 and also change the define to PT_AARCH64_MEMTAG_MTE to match the AArch64 ELF ABI namespace. The AArch64 ELF ABI document is updating accordingly (segment type not previously mentioned in the document). Signed-off-by: Catalin Marinas Fixes: 761b9b366cec ("elf: Introduce the ARM MTE ELF segment type") Cc: Will Deacon Cc: Jonathan Corbet Cc: Eric Biederman Cc: Kees Cook Cc: Luis Machado Cc: Richard Earnshaw Link: https://lore.kernel.org/r/20220425151833.2603830-1-catalin.marinas@arm.com Signed-off-by: Will Deacon --- Documentation/arm64/memory-tagging-extension.rst | 4 ++-- arch/arm64/kernel/elfcore.c | 2 +- include/uapi/linux/elf.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux/elf.h') diff --git a/Documentation/arm64/memory-tagging-extension.rst b/Documentation/arm64/memory-tagging-extension.rst index dd27f78d7608..dbae47bba25e 100644 --- a/Documentation/arm64/memory-tagging-extension.rst +++ b/Documentation/arm64/memory-tagging-extension.rst @@ -228,10 +228,10 @@ Core dump support ----------------- The allocation tags for user memory mapped with ``PROT_MTE`` are dumped -in the core file as additional ``PT_ARM_MEMTAG_MTE`` segments. The +in the core file as additional ``PT_AARCH64_MEMTAG_MTE`` segments. The program header for such segment is defined as: -:``p_type``: ``PT_ARM_MEMTAG_MTE`` +:``p_type``: ``PT_AARCH64_MEMTAG_MTE`` :``p_flags``: 0 :``p_offset``: segment file offset :``p_vaddr``: segment virtual address, same as the corresponding diff --git a/arch/arm64/kernel/elfcore.c b/arch/arm64/kernel/elfcore.c index 2b3f3d0544b9..98d67444a5b6 100644 --- a/arch/arm64/kernel/elfcore.c +++ b/arch/arm64/kernel/elfcore.c @@ -95,7 +95,7 @@ int elf_core_write_extra_phdrs(struct coredump_params *cprm, loff_t offset) for_each_mte_vma(current, vma) { struct elf_phdr phdr; - phdr.p_type = PT_ARM_MEMTAG_MTE; + phdr.p_type = PT_AARCH64_MEMTAG_MTE; phdr.p_offset = offset; phdr.p_vaddr = vma->vm_start; phdr.p_paddr = 0; diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 787c657bfae8..7ce993e6786c 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -42,7 +42,7 @@ typedef __s64 Elf64_Sxword; /* ARM MTE memory tag segment type */ -#define PT_ARM_MEMTAG_MTE (PT_LOPROC + 0x1) +#define PT_AARCH64_MEMTAG_MTE (PT_LOPROC + 0x2) /* * Extended Numbering -- cgit v1.2.3 From c9b516f16be5896a3d798f8efb03acbd2ceec715 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 12 May 2022 20:38:36 -0700 Subject: ELF, uapi: fixup ELF_ST_TYPE definition This is very theoretical compile failure: ELF_ST_TYPE(st_info = A) Cast will bind first and st_info will stop being lvalue: error: lvalue required as left operand of assignment Given that the only use of this macro is ELF_ST_TYPE(sym->st_info) where st_info is "unsigned char" I've decided to remove cast especially given that companion macro ELF_ST_BIND doesn't use cast. Link: https://lkml.kernel.org/r/Ymv7G1BeX4kt3obz@localhost.localdomain Signed-off-by: Alexey Dobriyan Acked-by: Kees Cook Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton --- include/uapi/linux/elf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux/elf.h') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 787c657bfae8..237f21a5e0f6 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -134,7 +134,7 @@ typedef __s64 Elf64_Sxword; #define STT_TLS 6 #define ELF_ST_BIND(x) ((x) >> 4) -#define ELF_ST_TYPE(x) (((unsigned int) x) & 0xf) +#define ELF_ST_TYPE(x) ((x) & 0xf) #define ELF32_ST_BIND(x) ELF_ST_BIND(x) #define ELF32_ST_TYPE(x) ELF_ST_TYPE(x) #define ELF64_ST_BIND(x) ELF_ST_BIND(x) -- cgit v1.2.3 From 08145b087e4481458f6075f3af58021a3cf8a940 Mon Sep 17 00:00:00 2001 From: Huacai Chen Date: Tue, 31 May 2022 18:04:10 +0800 Subject: LoongArch: Add ELF-related definitions Add ELF-related definitions for LoongArch, including: EM_LOONGARCH, KEXEC_ARCH_LOONGARCH, AUDIT_ARCH_LOONGARCH32, AUDIT_ARCH_LOONGARCH64 and NT_LOONGARCH_*. Reviewed-by: WANG Xuerui Reviewed-by: Jiaxun Yang Signed-off-by: Huacai Chen --- include/uapi/linux/audit.h | 2 ++ include/uapi/linux/elf-em.h | 1 + include/uapi/linux/elf.h | 5 +++++ include/uapi/linux/kexec.h | 1 + scripts/sorttable.c | 5 +++++ 5 files changed, 14 insertions(+) (limited to 'include/uapi/linux/elf.h') diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 8eda133ca4c1..7c1dc818b1d5 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -439,6 +439,8 @@ enum { #define AUDIT_ARCH_UNICORE (EM_UNICORE|__AUDIT_ARCH_LE) #define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) #define AUDIT_ARCH_XTENSA (EM_XTENSA) +#define AUDIT_ARCH_LOONGARCH32 (EM_LOONGARCH|__AUDIT_ARCH_LE) +#define AUDIT_ARCH_LOONGARCH64 (EM_LOONGARCH|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) #define AUDIT_PERM_EXEC 1 #define AUDIT_PERM_WRITE 2 diff --git a/include/uapi/linux/elf-em.h b/include/uapi/linux/elf-em.h index f47e853546fa..ef38c2bc5ab7 100644 --- a/include/uapi/linux/elf-em.h +++ b/include/uapi/linux/elf-em.h @@ -51,6 +51,7 @@ #define EM_RISCV 243 /* RISC-V */ #define EM_BPF 247 /* Linux BPF - in-kernel virtual machine */ #define EM_CSKY 252 /* C-SKY */ +#define EM_LOONGARCH 258 /* LoongArch */ #define EM_FRV 0x5441 /* Fujitsu FR-V */ /* diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index c4abd09c3da9..2b9f5e9985e5 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -438,6 +438,11 @@ typedef struct elf64_shdr { #define NT_MIPS_DSP 0x800 /* MIPS DSP ASE registers */ #define NT_MIPS_FP_MODE 0x801 /* MIPS floating-point mode */ #define NT_MIPS_MSA 0x802 /* MIPS SIMD registers */ +#define NT_LOONGARCH_CPUCFG 0xa00 /* LoongArch CPU config registers */ +#define NT_LOONGARCH_CSR 0xa01 /* LoongArch control and status registers */ +#define NT_LOONGARCH_LSX 0xa02 /* LoongArch Loongson SIMD Extension registers */ +#define NT_LOONGARCH_LASX 0xa03 /* LoongArch Loongson Advanced SIMD Extension registers */ +#define NT_LOONGARCH_LBT 0xa04 /* LoongArch Loongson Binary Translation registers */ /* Note types with note name "GNU" */ #define NT_GNU_PROPERTY_TYPE_0 5 diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h index fb7e2ef60825..981016e05cfa 100644 --- a/include/uapi/linux/kexec.h +++ b/include/uapi/linux/kexec.h @@ -43,6 +43,7 @@ #define KEXEC_ARCH_MIPS ( 8 << 16) #define KEXEC_ARCH_AARCH64 (183 << 16) #define KEXEC_ARCH_RISCV (243 << 16) +#define KEXEC_ARCH_LOONGARCH (258 << 16) /* The artificial cap on the number of segments passed to kexec_load. */ #define KEXEC_SEGMENT_MAX 16 diff --git a/scripts/sorttable.c b/scripts/sorttable.c index d00504c5f530..fba40e99f354 100644 --- a/scripts/sorttable.c +++ b/scripts/sorttable.c @@ -60,6 +60,10 @@ #define EM_RISCV 243 #endif +#ifndef EM_LOONGARCH +#define EM_LOONGARCH 258 +#endif + static uint32_t (*r)(const uint32_t *); static uint16_t (*r2)(const uint16_t *); static uint64_t (*r8)(const uint64_t *); @@ -313,6 +317,7 @@ static int do_file(char const *const fname, void *addr) case EM_ARCOMPACT: case EM_ARCV2: case EM_ARM: + case EM_LOONGARCH: case EM_MICROBLAZE: case EM_MIPS: case EM_XTENSA: -- cgit v1.2.3