From 03e00e373cab981ad808271b2650700cfa0fbda6 Mon Sep 17 00:00:00 2001 From: Len Brown Date: Sun, 6 Apr 2025 14:49:20 -0400 Subject: [PATCH 01/16] tools/power turbostat: v2025.05.06 Support up to 8192 processors Add cpuidle governor debug telemetry, disabled by default Update default output to exclude cpuidle invocation counts Bug fixes Signed-off-by: Len Brown --- tools/power/x86/turbostat/turbostat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index ab184f95cdaf..1b9fdc1a7ee8 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -9594,7 +9594,7 @@ int get_and_dump_counters(void) void print_version() { - fprintf(outf, "turbostat version 2025.02.02 - Len Brown \n"); + fprintf(outf, "turbostat version 2025.04.06 - Len Brown \n"); } #define COMMAND_LINE_SIZE 2048 -- 2.51.0 From 0efdedb3358aa78102967f242379686f94315830 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Thomas=20Wei=C3=9Fschuh?= Date: Wed, 2 Apr 2025 21:21:57 +0100 Subject: [PATCH 02/16] tools/include: make uapi/linux/types.h usable from assembly MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit The "real" linux/types.h UAPI header gracefully degrades to a NOOP when included from assembly code. Mirror this behaviour in the tools/ variant. Test for __ASSEMBLER__ over __ASSEMBLY__ as the former is provided by the toolchain automatically. Reported-by: Mark Brown Closes: https://lore.kernel.org/lkml/af553c62-ca2f-4956-932c-dd6e3a126f58@sirena.org.uk/ Fixes: c9fbaa879508 ("selftests: vDSO: parse_vdso: Use UAPI headers instead of libc headers") Signed-off-by: Thomas Weißschuh Link: https://patch.msgid.link/20250321-uapi-consistency-v1-1-439070118dc0@linutronix.de Signed-off-by: Mark Brown Reviewed-by: Mark Brown Signed-off-by: Linus Torvalds --- tools/include/uapi/linux/types.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/include/uapi/linux/types.h b/tools/include/uapi/linux/types.h index 91fa51a9c31d..85aa327245c6 100644 --- a/tools/include/uapi/linux/types.h +++ b/tools/include/uapi/linux/types.h @@ -4,6 +4,8 @@ #include +#ifndef __ASSEMBLER__ + /* copied from linux:include/uapi/linux/types.h */ #define __bitwise typedef __u16 __bitwise __le16; @@ -20,4 +22,5 @@ typedef __u32 __bitwise __wsum; #define __aligned_be64 __be64 __attribute__((aligned(8))) #define __aligned_le64 __le64 __attribute__((aligned(8))) +#endif /* __ASSEMBLER__ */ #endif /* _UAPI_LINUX_TYPES_H */ -- 2.51.0 From 0af2f6be1b4281385b618cb86ad946eded089ac8 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 6 Apr 2025 13:11:33 -0700 Subject: [PATCH 03/16] Linux 6.15-rc1 --- Makefile | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index e55726a71d95..38689a0c3605 100644 --- a/Makefile +++ b/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 -PATCHLEVEL = 14 +PATCHLEVEL = 15 SUBLEVEL = 0 -EXTRAVERSION = +EXTRAVERSION = -rc1 NAME = Baby Opossum Posse # *DOCUMENTATION* -- 2.51.0 From 95507570fb2f75544af69760cd5d8f48fc5c7f20 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 9 Apr 2025 17:39:58 +0100 Subject: [PATCH 04/16] arm64/fpsimd: Avoid RES0 bits in the SME trap handler The SME trap handler consumes RES0 bits from the ESR when determining the reason for the trap, and depends upon those bits reading as zero. This may break in future when those RES0 bits are allocated a meaning and stop reading as zero. For SME traps taken with ESR_ELx.EC == 0b011101, the specific reason for the trap is indicated by ESR_ELx.ISS.SMTC ("SME Trap Code"). This field occupies bits [2:0] of ESR_ELx.ISS, and as of ARM DDI 0487 L.a, bits [24:3] of ESR_ELx.ISS are RES0. ESR_ELx.ISS itself occupies bits [24:0] of ESR_ELx. Extract the SMTC field specifically, matching the way we handle ESR_ELx fields elsewhere, and ensuring that the handler is future-proof. Fixes: 8bd7f91c03d8 ("arm64/sme: Implement traps and syscall handling for SME") Signed-off-by: Mark Rutland Cc: Marc Zyngier Cc: Mark Brown Cc: Will Deacon Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20250409164010.3480271-2-mark.rutland@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/esr.h | 14 ++++++++------ arch/arm64/kernel/fpsimd.c | 2 +- 2 files changed, 9 insertions(+), 7 deletions(-) diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index d1b1a33f9a8b..63aed18a933f 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -371,12 +371,14 @@ /* * ISS values for SME traps */ - -#define ESR_ELx_SME_ISS_SME_DISABLED 0 -#define ESR_ELx_SME_ISS_ILL 1 -#define ESR_ELx_SME_ISS_SM_DISABLED 2 -#define ESR_ELx_SME_ISS_ZA_DISABLED 3 -#define ESR_ELx_SME_ISS_ZT_DISABLED 4 +#define ESR_ELx_SME_ISS_SMTC_MASK GENMASK(2, 0) +#define ESR_ELx_SME_ISS_SMTC(esr) ((esr) & ESR_ELx_SME_ISS_SMTC_MASK) + +#define ESR_ELx_SME_ISS_SMTC_SME_DISABLED 0 +#define ESR_ELx_SME_ISS_SMTC_ILL 1 +#define ESR_ELx_SME_ISS_SMTC_SM_DISABLED 2 +#define ESR_ELx_SME_ISS_SMTC_ZA_DISABLED 3 +#define ESR_ELx_SME_ISS_SMTC_ZT_DISABLED 4 /* ISS field definitions for MOPS exceptions */ #define ESR_ELx_MOPS_ISS_MEM_INST (UL(1) << 24) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 8370d55f0353..1ee5f330b8ed 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1436,7 +1436,7 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs) * If this not a trap due to SME being disabled then something * is being used in the wrong mode, report as SIGILL. */ - if (ESR_ELx_ISS(esr) != ESR_ELx_SME_ISS_SME_DISABLED) { + if (ESR_ELx_SME_ISS_SMTC(esr) != ESR_ELx_SME_ISS_SMTC_SME_DISABLED) { force_signal_inject(SIGILL, ILL_ILLOPC, regs->pc, 0); return; } -- 2.51.0 From 61db0e0ba398a3726ca0e6a6399898d3d4c7b0f9 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 9 Apr 2025 17:39:59 +0100 Subject: [PATCH 05/16] arm64/fpsimd: Remove unused fpsimd_force_sync_to_sve() There have been no users of fpsimd_force_sync_to_sve() since commit: bbc6172eefdb276b ("arm64/fpsimd: SME no longer requires SVE register state") Remove fpsimd_force_sync_to_sve(). Signed-off-by: Mark Rutland Cc: Marc Zyngier Cc: Mark Brown Cc: Will Deacon Link: https://lore.kernel.org/r/20250409164010.3480271-3-mark.rutland@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/fpsimd.h | 1 - arch/arm64/kernel/fpsimd.c | 14 -------------- 2 files changed, 15 deletions(-) diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 564bc09b3e06..9c3e88ec873a 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -196,7 +196,6 @@ struct vl_info { extern void sve_alloc(struct task_struct *task, bool flush); 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/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 1ee5f330b8ed..1391a491f222 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -758,20 +758,6 @@ void sve_alloc(struct task_struct *task, bool flush) kzalloc(sve_state_size(task), GFP_KERNEL); } - -/* - * 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. -- 2.51.0 From 45fd86986b79c3ada56d3a14e712447e992433aa Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 9 Apr 2025 17:40:00 +0100 Subject: [PATCH 06/16] arm64/fpsimd: Remove redundant SVE trap manipulation When task_fpsimd_load() loads the saved FPSIMD/SVE/SME state, it configures EL0 SVE traps by calling sve_user_{enable,disable}(). This is unnecessary, and this is suspicious/confusing as task_fpsimd_load() does not configure EL0 SME traps. All calls to task_fpsimd_load() are followed by a call to fpsimd_bind_task_to_cpu(), where the latter configures traps for SVE and SME dependent upon the current values of TIF_SVE and TIF_SME, overriding any trap configuration performed by task_fpsimd_load(). The calls to sve_user_{enable,disable}() calls in task_fpsimd_load() have been redundant (though benign) since they were introduced in commit: a0136be443d51803 ("arm64/fpsimd: Load FP state based on recorded data type") Remove the unnecessary and confusing SVE trap manipulation. Signed-off-by: Mark Rutland Cc: Marc Zyngier Cc: Mark Brown Cc: Will Deacon Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20250409164010.3480271-4-mark.rutland@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/fpsimd.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 1391a491f222..757445d72e5b 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -366,13 +366,11 @@ static void task_fpsimd_load(void) switch (current->thread.fp_type) { case FP_STATE_FPSIMD: /* Stop tracking SVE for this task until next use. */ - if (test_and_clear_thread_flag(TIF_SVE)) - sve_user_disable(); + clear_thread_flag(TIF_SVE); break; case FP_STATE_SVE: - if (!thread_sm_enabled(¤t->thread) && - !WARN_ON_ONCE(!test_and_set_thread_flag(TIF_SVE))) - sve_user_enable(); + if (!thread_sm_enabled(¤t->thread)) + WARN_ON_ONCE(!test_and_set_thread_flag(TIF_SVE)); if (test_thread_flag(TIF_SVE)) sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1); -- 2.51.0 From d7649a4a601ebf4603f0a673f554ab350b6cfede Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 9 Apr 2025 17:40:01 +0100 Subject: [PATCH 07/16] arm64/fpsimd: Remove opportunistic freeing of SME state When a task's SVE vector length (NSVL) is changed, and the task happens to have SVCR.{SM,ZA}=={0,0}, vec_set_vector_length() opportunistically frees the task's sme_state and clears TIF_SME. The opportunistic freeing was added with no rationale in commit: d4d5be94a8787242 ("arm64/fpsimd: Ensure SME storage is allocated after SVE VL changes") That commit fixed an unrelated problem where the task's sve_state was freed while it could be used to store streaming mode register state, where the fix was to re-allocate the task's sve_state. There is no need to free and/or reallocate the task's sme_state when the SVE vector length changes, and there is no need to clear TIF_SME. Given the SME vector length (SVL) doesn't change, the task's sme_state remains correctly sized. Remove the unnecessary opportunistic freeing of the task's sme_state when the task's SVE vector length is changed. The task's sme_state is still freed when the SME vector length is changed. Signed-off-by: Mark Rutland Cc: Marc Zyngier Cc: Mark Brown Cc: Will Deacon Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20250409164010.3480271-5-mark.rutland@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/fpsimd.c | 17 ++++------------- 1 file changed, 4 insertions(+), 13 deletions(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 757445d72e5b..128774015772 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -868,19 +868,10 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, task->thread.fp_type = FP_STATE_FPSIMD; } - if (system_supports_sme()) { - if (type == ARM64_VEC_SME || - !(task->thread.svcr & (SVCR_SM_MASK | SVCR_ZA_MASK))) { - /* - * We are changing the SME VL or weren't using - * SME anyway, discard the state and force a - * reallocation. - */ - task->thread.svcr &= ~(SVCR_SM_MASK | - SVCR_ZA_MASK); - clear_tsk_thread_flag(task, TIF_SME); - free_sme = true; - } + if (system_supports_sme() && type == ARM64_VEC_SME) { + task->thread.svcr &= ~(SVCR_SM_MASK | SVCR_ZA_MASK); + clear_tsk_thread_flag(task, TIF_SME); + free_sme = true; } if (task == current) -- 2.51.0 From d3eaab3c70905c5467e5c4ea403053d67505adeb Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 9 Apr 2025 17:40:02 +0100 Subject: [PATCH 08/16] arm64/fpsimd: Discard stale CPU state when handling SME traps The logic for handling SME traps manipulates saved FPSIMD/SVE/SME state incorrectly, and a race with preemption can result in a task having TIF_SME set and TIF_FOREIGN_FPSTATE clear even though the live CPU state is stale (e.g. with SME traps enabled). This can result in warnings from do_sme_acc() where SME traps are not expected while TIF_SME is set: | /* With TIF_SME userspace shouldn't generate any traps */ | if (test_and_set_thread_flag(TIF_SME)) | WARN_ON(1); This is very similar to the SVE issue we fixed in commit: 751ecf6afd6568ad ("arm64/sve: Discard stale CPU state when handling SVE traps") The race can occur when the SME trap handler is preempted before and after manipulating the saved FPSIMD/SVE/SME state, starting and ending on the same CPU, e.g. | void do_sme_acc(unsigned long esr, struct pt_regs *regs) | { | // Trap on CPU 0 with TIF_SME clear, SME traps enabled | // task->fpsimd_cpu is 0. | // per_cpu_ptr(&fpsimd_last_state, 0) is task. | | ... | | // Preempted; migrated from CPU 0 to CPU 1. | // TIF_FOREIGN_FPSTATE is set. | | get_cpu_fpsimd_context(); | | /* With TIF_SME userspace shouldn't generate any traps */ | if (test_and_set_thread_flag(TIF_SME)) | WARN_ON(1); | | if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { | unsigned long vq_minus_one = | sve_vq_from_vl(task_get_sme_vl(current)) - 1; | sme_set_vq(vq_minus_one); | | fpsimd_bind_task_to_cpu(); | } | | put_cpu_fpsimd_context(); | | // Preempted; migrated from CPU 1 to CPU 0. | // task->fpsimd_cpu is still 0 | // If per_cpu_ptr(&fpsimd_last_state, 0) is still task then: | // - Stale HW state is reused (with SME traps enabled) | // - TIF_FOREIGN_FPSTATE is cleared | // - A return to userspace skips HW state restore | } Fix the case where the state is not live and TIF_FOREIGN_FPSTATE is set by calling fpsimd_flush_task_state() to detach from the saved CPU state. This ensures that a subsequent context switch will not reuse the stale CPU state, and will instead set TIF_FOREIGN_FPSTATE, forcing the new state to be reloaded from memory prior to a return to userspace. Note: this was originallly posted as [1]. Fixes: 8bd7f91c03d8 ("arm64/sme: Implement traps and syscall handling for SME") Reported-by: Mark Rutland Signed-off-by: Mark Brown Link: https://lore.kernel.org/linux-arm-kernel/20241204-arm64-sme-reenable-v2-1-bae87728251d@kernel.org/ [ Rutland: rewrite commit message ] Signed-off-by: Mark Rutland Cc: Marc Zyngier Cc: Will Deacon Link: https://lore.kernel.org/r/20250409164010.3480271-6-mark.rutland@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/fpsimd.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 128774015772..b4858d85292b 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1435,6 +1435,8 @@ void do_sme_acc(unsigned long esr, struct pt_regs *regs) sme_set_vq(vq_minus_one); fpsimd_bind_task_to_cpu(); + } else { + fpsimd_flush_task_state(current); } put_cpu_fpsimd_context(); -- 2.51.0 From e5fa85fce08b21ed41643cb7968bf66bbd0532e3 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Wed, 9 Apr 2025 17:40:03 +0100 Subject: [PATCH 09/16] arm64/fpsimd: Don't corrupt FPMR when streaming mode changes When the effective value of PSTATE.SM is changed from 0 to 1 or from 1 to 0 by any method, an entry or exit to/from streaming SVE mode is performed, and hardware automatically resets a number of registers. As of ARM DDI 0487 L.a, this means: * All implemented bits of the SVE vector registers are set to zero. * All implemented bits of the SVE predicate registers are set to zero. * All implemented bits of FFR are set to zero, if FFR is implemented in the new mode. * FPSR is set to 0x0000_0000_0800_009f. * FPMR is set to 0, if FPMR is implemented. Currently task_fpsimd_load() restores FPMR before restoring SVCR (which is an accessor for PSTATE.{SM,ZA}), and so the restored value of FPMR may be clobbered if the restored value of PSTATE.SM happens to differ from the initial value of PSTATE.SM. Fix this by moving the restore of FPMR later. Note: this was originally posted as [1]. Fixes: 203f2b95a882 ("arm64/fpsimd: Support FEAT_FPMR") Signed-off-by: Mark Brown Link: https://lore.kernel.org/linux-arm-kernel/20241204-arm64-sme-reenable-v2-2-bae87728251d@kernel.org/ [ Rutland: rewrite commit message ] Signed-off-by: Mark Rutland Link: https://lore.kernel.org/r/20250409164010.3480271-7-mark.rutland@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/fpsimd.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index b4858d85292b..b19736f354a7 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -359,9 +359,6 @@ 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: @@ -411,6 +408,9 @@ static void task_fpsimd_load(void) restore_ffr = system_supports_fa64(); } + if (system_supports_fpmr()) + write_sysreg_s(current->thread.uw.fpmr, SYS_FPMR); + if (restore_sve_regs) { WARN_ON_ONCE(current->thread.fp_type != FP_STATE_SVE); sve_load_state(sve_pffr(¤t->thread), -- 2.51.0 From 01098d893fa8a6edb2b56e178b798e3e6b674f02 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 9 Apr 2025 17:40:04 +0100 Subject: [PATCH 10/16] arm64/fpsimd: Avoid clobbering kernel FPSIMD state with SMSTOP On system with SME, a thread's kernel FPSIMD state may be erroneously clobbered during a context switch immediately after that state is restored. Systems without SME are unaffected. If the CPU happens to be in streaming SVE mode before a context switch to a thread with kernel FPSIMD state, fpsimd_thread_switch() will restore the kernel FPSIMD state using fpsimd_load_kernel_state() while the CPU is still in streaming SVE mode. When fpsimd_thread_switch() subsequently calls fpsimd_flush_cpu_state(), this will execute an SMSTOP, causing an exit from streaming SVE mode. The exit from streaming SVE mode will cause the hardware to reset a number of FPSIMD/SVE/SME registers, clobbering the FPSIMD state. Fix this by calling fpsimd_flush_cpu_state() before restoring the kernel FPSIMD state. Fixes: e92bee9f861b ("arm64/fpsimd: Avoid erroneous elide of user state reload") Signed-off-by: Mark Rutland Cc: Ard Biesheuvel Cc: Mark Brown Cc: Will Deacon Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20250409164010.3480271-8-mark.rutland@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/fpsimd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index b19736f354a7..4a0b0bb3a3fa 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1550,8 +1550,8 @@ void fpsimd_thread_switch(struct task_struct *next) fpsimd_save_user_state(); if (test_tsk_thread_flag(next, TIF_KERNEL_FPSTATE)) { - fpsimd_load_kernel_state(next); fpsimd_flush_cpu_state(); + fpsimd_load_kernel_state(next); } else { /* * Fix up TIF_FOREIGN_FPSTATE to correctly describe next's -- 2.51.0 From a90878f297d3dba906a6261deccb1bd4a791ba52 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 9 Apr 2025 17:40:05 +0100 Subject: [PATCH 11/16] arm64/fpsimd: Reset FPMR upon exec() An exec() is expected to reset all FPSIMD/SVE/SME state, and barring special handling of the vector lengths, the state is expected to reset to zero. This reset is handled in fpsimd_flush_thread(), which the core exec() code calls via flush_thread(). When support was added for FPMR, no logic was added to fpsimd_flush_thread() to reset the FPMR value, and thus it is erroneously inherited across an exec(). Add the missing reset of FPMR. Fixes: 203f2b95a882 ("arm64/fpsimd: Support FEAT_FPMR") Signed-off-by: Mark Rutland Cc: Marc Zyngier Cc: Mark Brown Cc: Will Deacon Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20250409164010.3480271-9-mark.rutland@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/fpsimd.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 4a0b0bb3a3fa..0b6fda5b7bad 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1638,6 +1638,9 @@ void fpsimd_flush_thread(void) current->thread.svcr = 0; } + if (system_supports_fpmr()) + current->thread.uw.fpmr = 0; + current->thread.fp_type = FP_STATE_FPSIMD; put_cpu_fpsimd_context(); -- 2.51.0 From c94f2f326146a34066a0070ed90b8bc656b1842f Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 9 Apr 2025 17:40:06 +0100 Subject: [PATCH 12/16] arm64/fpsimd: Fix merging of FPSIMD state during signal return For backwards compatibility reasons, when a signal return occurs which restores SVE state, the effective lower 128 bits of each of the SVE vector registers are restored from the corresponding FPSIMD vector register in the FPSIMD signal frame, overriding the values in the SVE signal frame. This is intended to be the case regardless of streaming mode. To make this happen, restore_sve_fpsimd_context() uses fpsimd_update_current_state() to merge the lower 128 bits from the FPSIMD signal frame into the SVE register state. Unfortunately, fpsimd_update_current_state() performs this merging dependent upon TIF_SVE, which is not always correct for streaming SVE register state: * When restoring non-streaming SVE register state there is no observable problem, as the signal return code configures TIF_SVE and the saved fp_type to match before calling fpsimd_update_current_state(), which observes either: - TIF_SVE set AND fp_type == FP_STATE_SVE - TIF_SVE clear AND fp_type == FP_STATE_FPSIMD * On systems which have SME but not SVE, TIF_SVE cannot be set. Thus the merging will never happen for the streaming SVE register state. * On systems which have SVE and SME, TIF_SVE can be set and cleared independently of PSTATE.SM. Thus the merging may or may not happen for streaming SVE register state. As TIF_SVE can be cleared non-deterministically during syscalls (including at the start of sigreturn()), the merging may occur non-deterministically from the perspective of userspace. This logic has been broken since its introduction in commit: 85ed24dad2904f7c ("arm64/sme: Implement streaming SVE signal handling") ... at which point both fpsimd_signal_preserve_current_state() and fpsimd_update_current_state() only checked TIF SVE. When PSTATE.SM==1 and TIF_SVE was clear, signal delivery would place stale FPSIMD state into the FPSIMD signal frame, and signal return would not merge this into the restored register state. Subsequently, signal delivery was fixed as part of commit: 61da7c8e2a602f66 ("arm64/signal: Don't assume that TIF_SVE means we saved SVE state") ... but signal restore was not given a corresponding fix, and when TIF_SVE was clear, signal restore would still fail to merge the FPSIMD state into the restored SVE register state. The 'Fixes' tag did not indicate that this had been broken since its introduction. Fix this by merging the FPSIMD state dependent upon the saved fp_type, matching what we (currently) do during signal delivery. As described above, when backporting this commit, it will also be necessary to backport commit: 61da7c8e2a602f66 ("arm64/signal: Don't assume that TIF_SVE means we saved SVE state") ... and prior to commit: baa8515281b30861 ("arm64/fpsimd: Track the saved FPSIMD state type separately to TIF_SVE") ... it will be necessary for fpsimd_signal_preserve_current_state() and fpsimd_update_current_state() to consider both TIF_SVE and thread_sm_enabled(¤t->thread), in place of the saved fp_type. Fixes: 85ed24dad290 ("arm64/sme: Implement streaming SVE signal handling") Signed-off-by: Mark Rutland Cc: Marc Zyngier Cc: Mark Brown Cc: Will Deacon Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20250409164010.3480271-10-mark.rutland@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/fpsimd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 0b6fda5b7bad..11f21809d3b7 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1781,7 +1781,7 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state) get_cpu_fpsimd_context(); current->thread.uw.fpsimd_state = *state; - if (test_thread_flag(TIF_SVE)) + if (current->thread.fp_type == FP_STATE_SVE) fpsimd_to_sve(current); task_fpsimd_load(); -- 2.51.0 From d3a181588df9401d319fe2dc24bf1a364a687cc2 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 9 Apr 2025 17:40:07 +0100 Subject: [PATCH 13/16] arm64/fpsimd: Add fpsimd_save_and_flush_current_state() When the current task's FPSIMD/SVE/SME state may be live on *any* CPU in the system, special care must be taken when manipulating that state, as this manipulation can race with preemption and/or asynchronous usage of FPSIMD/SVE/SME (e.g. kernel-mode NEON in softirq handlers). Even when manipulation is is protected with get_cpu_fpsimd_context() and get_cpu_fpsimd_context(), the logic necessary when the state is live on the current CPU can be wildly different from the logic necessary when the state is not live on the current CPU. A number of historical and extant issues result from failing to handle these cases consistetntly and/or correctly. To make it easier to get such manipulation correct, add a new fpsimd_save_and_flush_current_state() helper function, which ensures that the current task's state has been saved to memory and any stale state on any CPU has been "flushed" such that is not live on any CPU in the system. This will allow code to safely manipulate the saved state without risk of races. Subsequent patches will use the new function. Signed-off-by: Mark Rutland Cc: Marc Zyngier Cc: Mark Brown Cc: Will Deacon Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20250409164010.3480271-11-mark.rutland@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/fpsimd.h | 1 + arch/arm64/kernel/fpsimd.c | 11 +++++++++++ 2 files changed, 12 insertions(+) diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 9c3e88ec873a..1a18f851b614 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -96,6 +96,7 @@ struct cpu_fp_state { extern void fpsimd_bind_state_to_cpu(struct cpu_fp_state *fp_state); extern void fpsimd_flush_task_state(struct task_struct *target); +extern void fpsimd_save_and_flush_current_state(void); extern void fpsimd_save_and_flush_cpu_state(void); static inline bool thread_sm_enabled(struct thread_struct *thread) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 11f21809d3b7..ea07c4577f17 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1819,6 +1819,17 @@ void fpsimd_flush_task_state(struct task_struct *t) barrier(); } +void fpsimd_save_and_flush_current_state(void) +{ + if (!system_supports_fpsimd()) + return; + + get_cpu_fpsimd_context(); + fpsimd_save_user_state(); + fpsimd_flush_task_state(current); + put_cpu_fpsimd_context(); +} + /* * Save the FPSIMD state to memory and invalidate cpu view. * This function must be called with preemption disabled. -- 2.51.0 From 3aa4d74438afa1324513a7a6bc30f57e8727ad86 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 9 Apr 2025 17:40:08 +0100 Subject: [PATCH 14/16] arm64/fpsimd: signal32: Always save+flush state early There are several issues with the way the native signal handling code manipulates FPSIMD/SVE/SME state. To fix those issues, subsequent patches will rework the native signal handling code to always save+flush the current task's FPSIMD/SVE/SME state before manipulating that state. In preparation for those changes, rework the compat signal handling code to save+flush the current task's FPSIMD state before manipulating it. Subsequent patches will remove fpsimd_signal_preserve_current_state() and fpsimd_update_current_state(). Compat tasks can only have FPSIMD state, and cannot have any SVE or SME state. Thus, the SVE state manipulation present in fpsimd_signal_preserve_current_state() and fpsimd_update_current_state() is not necessary, and it is safe to directly manipulate current->thread.uw.fpsimd_state once it has been saved+flushed. Use fpsimd_save_and_flush_current_state() to save+flush the state for both signal delivery and signal return, before the state is manipulated in any way. While it would be safe for compat_restore_vfp_context() to use fpsimd_flush_task_state(current), there are several extant issues in the native signal code resulting from incorrect use of fpsimd_flush_task_state(), and for consistency it is preferable to use fpsimd_save_and_flush_current_state(). Signed-off-by: Mark Rutland Cc: Marc Zyngier Cc: Mark Brown Cc: Will Deacon Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20250409164010.3480271-12-mark.rutland@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/signal32.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 81e798b6dada..bb3b526ff43f 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -103,7 +103,7 @@ static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame) * Note that this also saves V16-31, which aren't visible * in AArch32. */ - fpsimd_signal_preserve_current_state(); + fpsimd_save_and_flush_current_state(); /* Place structure header on the stack */ __put_user_error(magic, &frame->magic, err); @@ -169,14 +169,17 @@ static int compat_restore_vfp_context(struct compat_vfp_sigframe __user *frame) fpsimd.fpsr = fpscr & VFP_FPSCR_STAT_MASK; fpsimd.fpcr = fpscr & VFP_FPSCR_CTRL_MASK; + if (err) + return -EFAULT; + /* * We don't need to touch the exception register, so * reload the hardware state. */ - if (!err) - fpsimd_update_current_state(&fpsimd); + fpsimd_save_and_flush_current_state(); + current->thread.uw.fpsimd_state = fpsimd; - return err ? -EFAULT : 0; + return 0; } static int compat_restore_sigframe(struct pt_regs *regs, -- 2.51.0 From 929fa99b1215966fc8a6ccc2e14b92e36c3c42f3 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 9 Apr 2025 17:40:09 +0100 Subject: [PATCH 15/16] arm64/fpsimd: signal: Always save+flush state early There are several issues with the way the native signal handling code manipulates FPSIMD/SVE/SME state, described in detail below. These issues largely result from races with preemption and inconsistent handling of live state vs saved state. Known issues with native FPSIMD/SVE/SME state management include: * On systems with FPMR, the code to save/restore the FPMR accesses the register while it is not owned by the current task. Consequently, this may corrupt the FPMR of the current task and/or may corrupt the FPMR of an unrelated task. The FPMR save/restore has been broken since it was introduced in commit: 8c46def44409fc91 ("arm64/signal: Add FPMR signal handling") * On systems with SME, setup_return() modifies both the live register state and the saved state register state regardless of whether the task's state is live, and without holding the cpu fpsimd context. Consequently: - This may corrupt the state an unrelated task which has PSTATE.SM set and/or PSTATE.ZA set. - The task may enter the signal handler in streaming mode, and or with ZA storage enabled unexpectedly. - The task may enter the signal handler in non-streaming SVE mode with stale SVE register state, which may have been inherited from streaming SVE mode unexpectedly. Where the streaming and non-streaming vector lengths differ, this may be packed into registers arbitrarily. This logic has been broken since it was introduced in commit: 40a8e87bb32855b3 ("arm64/sme: Disable ZA and streaming mode when handling signals") Further incorrect manipulation of state was added in commits: ea64baacbc36a0d5 ("arm64/signal: Flush FPSIMD register state when disabling streaming mode") baa8515281b30861 ("arm64/fpsimd: Track the saved FPSIMD state type separately to TIF_SVE") * Several restoration functions use fpsimd_flush_task_state() to discard the live FPSIMD/SVE/SME while the in-memory copy is stale. When a subset of the FPSIMD/SVE/SME state is restored, the remainder may be non-deterministically reset to a stale snapshot from some arbitrary point in the past. This non-deterministic discarding was introduced in commit: 8cd969d28fd2848d ("arm64/sve: Signal handling support") As of that commit, when TIF_SVE was initially clear, failure to restore the SVE signal frame could reset the FPSIMD registers to a stale snapshot. The pattern of discarding unsaved state was subsequently copied into restoration functions for some new state in commits: 39782210eb7e8763 ("arm64/sme: Implement ZA signal handling") ee072cf708048c0d ("arm64/sme: Implement signal handling for ZT") * On systems with SME/SME2, the entire FPSIMD/SVE/SME state may be loaded onto the CPU redundantly. Either restore_fpsimd_context() or restore_sve_fpsimd_context() will load the entire FPSIMD/SVE/SME state via fpsimd_update_current_state() before restore_za_context() and restore_zt_context() each discard the state via fpsimd_flush_task_state(). This is purely redundant work, and not a functional bug. To fix these issues, rework the native signal handling code to always save+flush the current task's FPSIMD/SVE/SME state before manipulating that state. This avoids races with preemption and ensures that state is manipulated consistently regardless of whether it happened to be live prior to manipulation. This largely involes: * Using fpsimd_save_and_flush_current_state() to save+flush the state for both signal delivery and signal return, before the state is manipulated in any way. * Removing fpsimd_signal_preserve_current_state() and updating preserve_fpsimd_context() to explicitly ensure that the FPSIMD state is up-to-date, as preserve_fpsimd_context() is the only consumer of the FPSIMD state during signal delivery. * Modifying fpsimd_update_current_state() to not reload the FPSIMD state onto the CPU. Ideally we'd remove fpsimd_update_current_state() entirely, but I've left that for subsequent patches as there are a number of of other problems with the FPSIMD<->SVE conversion helpers that should be addressed at the same time. For now I've removed the misleading comment. For setup_return(), we need to decide (for ABI reasons) whether signal delivery should have all the side-effects of an SMSTOP. For now I've left a TODO comment, as there are other questions in this area that I'll address with subsequent patches. Fixes: 8c46def44409 ("arm64/signal: Add FPMR signal handling") Fixes: 40a8e87bb328 ("arm64/sme: Disable ZA and streaming mode when handling signals") Fixes: ea64baacbc36 ("arm64/signal: Flush FPSIMD register state when disabling streaming mode") Fixes: baa8515281b3 ("arm64/fpsimd: Track the saved FPSIMD state type separately to TIF_SVE") Fixes: 8cd969d28fd2 ("arm64/sve: Signal handling support") Fixes: 39782210eb7e ("arm64/sme: Implement ZA signal handling") Fixes: ee072cf70804 ("arm64/sme: Implement signal handling for ZT") Signed-off-by: Mark Rutland Cc: Marc Zyngier Cc: Mark Brown Cc: Will Deacon Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20250409164010.3480271-13-mark.rutland@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/fpsimd.h | 1 - arch/arm64/kernel/fpsimd.c | 28 -------------- arch/arm64/kernel/signal.c | 66 ++++++--------------------------- 3 files changed, 12 insertions(+), 83 deletions(-) diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 1a18f851b614..b7adb2c72204 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -76,7 +76,6 @@ extern void fpsimd_load_state(struct user_fpsimd_state *state); extern void fpsimd_thread_switch(struct task_struct *next); extern void fpsimd_flush_thread(void); -extern void fpsimd_signal_preserve_current_state(void); extern void fpsimd_preserve_current_state(void); extern void fpsimd_restore_current_state(void); extern void fpsimd_update_current_state(struct user_fpsimd_state const *state); diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index ea07c4577f17..b0874402f7ec 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1662,18 +1662,6 @@ void fpsimd_preserve_current_state(void) put_cpu_fpsimd_context(); } -/* - * Like fpsimd_preserve_current_state(), but ensure that - * current->thread.uw.fpsimd_state is updated so that it can be copied to - * the signal frame. - */ -void fpsimd_signal_preserve_current_state(void) -{ - fpsimd_preserve_current_state(); - if (current->thread.fp_type == FP_STATE_SVE) - sve_to_fpsimd(current); -} - /* * Associate current's FPSIMD context with this cpu * The caller must have ownership of the cpu FPSIMD context before calling @@ -1766,30 +1754,14 @@ void fpsimd_restore_current_state(void) put_cpu_fpsimd_context(); } -/* - * Load an updated userland FPSIMD state for 'current' from memory and set the - * flag that indicates that the FPSIMD register contents are the most recent - * FPSIMD state of 'current'. This is used by the signal code to restore the - * register state when returning from a signal handler in FPSIMD only cases, - * any SVE context will be discarded. - */ void fpsimd_update_current_state(struct user_fpsimd_state const *state) { if (WARN_ON(!system_supports_fpsimd())) return; - get_cpu_fpsimd_context(); - current->thread.uw.fpsimd_state = *state; if (current->thread.fp_type == FP_STATE_SVE) fpsimd_to_sve(current); - - task_fpsimd_load(); - fpsimd_bind_task_to_cpu(); - - clear_thread_flag(TIF_FOREIGN_FPSTATE); - - put_cpu_fpsimd_context(); } /* diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index a7c37afb4ebe..0de9c452c6c0 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -250,6 +250,8 @@ static int preserve_fpsimd_context(struct fpsimd_context __user *ctx) ¤t->thread.uw.fpsimd_state; int err; + sve_sync_to_fpsimd(current); + /* copy the FP and status/control registers */ err = __copy_to_user(ctx->vregs, fpsimd->vregs, sizeof(fpsimd->vregs)); __put_user_error(fpsimd->fpsr, &ctx->fpsr, err); @@ -291,8 +293,6 @@ 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); @@ -310,7 +310,7 @@ static int restore_fpmr_context(struct user_ctxs *user) __get_user_error(fpmr, &user->fpmr->fpmr, err); if (!err) - write_sysreg_s(fpmr, SYS_FPMR); + current->thread.uw.fpmr = fpmr; return err; } @@ -372,11 +372,6 @@ static int preserve_sve_context(struct sve_context __user *ctx) err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); if (vq) { - /* - * This assumes that the SVE state has already been saved to - * the task struct by calling the function - * fpsimd_signal_preserve_current_state(). - */ err |= __copy_to_user((char __user *)ctx + SVE_SIG_REGS_OFFSET, current->thread.sve_state, SVE_SIG_REGS_SIZE(vq)); @@ -432,16 +427,6 @@ static int restore_sve_fpsimd_context(struct user_ctxs *user) if (user->sve_size < SVE_SIG_CONTEXT_SIZE(vq)) return -EINVAL; - /* - * Careful: we are about __copy_from_user() directly into - * thread.sve_state with preemption enabled, so protection is - * needed to prevent a racing context switch from writing stale - * registers back over the new data. - */ - - fpsimd_flush_task_state(current); - /* From now, fpsimd_thread_switch() won't touch thread.sve_state */ - sve_alloc(current, true); if (!current->thread.sve_state) { clear_thread_flag(TIF_SVE); @@ -541,11 +526,6 @@ static int preserve_za_context(struct za_context __user *ctx) err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); if (vq) { - /* - * This assumes that the ZA state has already been saved to - * the task struct by calling the function - * fpsimd_signal_preserve_current_state(). - */ err |= __copy_to_user((char __user *)ctx + ZA_SIG_REGS_OFFSET, current->thread.sme_state, ZA_SIG_REGS_SIZE(vq)); @@ -580,16 +560,6 @@ static int restore_za_context(struct user_ctxs *user) if (user->za_size < ZA_SIG_CONTEXT_SIZE(vq)) return -EINVAL; - /* - * Careful: we are about __copy_from_user() directly into - * thread.sme_state with preemption enabled, so protection is - * needed to prevent a racing context switch from writing stale - * registers back over the new data. - */ - - fpsimd_flush_task_state(current); - /* From now, fpsimd_thread_switch() won't touch thread.sve_state */ - sme_alloc(current, true); if (!current->thread.sme_state) { current->thread.svcr &= ~SVCR_ZA_MASK; @@ -627,11 +597,6 @@ static int preserve_zt_context(struct zt_context __user *ctx) BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); - /* - * This assumes that the ZT state has already been saved to - * the task struct by calling the function - * fpsimd_signal_preserve_current_state(). - */ err |= __copy_to_user((char __user *)ctx + ZT_SIG_REGS_OFFSET, thread_zt_state(¤t->thread), ZT_SIG_REGS_SIZE(1)); @@ -657,16 +622,6 @@ static int restore_zt_context(struct user_ctxs *user) if (nregs != 1) return -EINVAL; - /* - * Careful: we are about __copy_from_user() directly into - * thread.zt_state with preemption enabled, so protection is - * needed to prevent a racing context switch from writing stale - * registers back over the new data. - */ - - fpsimd_flush_task_state(current); - /* From now, fpsimd_thread_switch() won't touch ZT in thread state */ - err = __copy_from_user(thread_zt_state(¤t->thread), (char __user const *)user->zt + ZT_SIG_REGS_OFFSET, @@ -1017,6 +972,8 @@ static int restore_sigframe(struct pt_regs *regs, */ forget_syscall(regs); + fpsimd_save_and_flush_current_state(); + err |= !valid_user_regs(®s->user_regs, current); if (err == 0) err = parse_user_sigframe(&user, sf); @@ -1510,8 +1467,11 @@ static int setup_return(struct pt_regs *regs, struct ksignal *ksig, /* * If we were in streaming mode the saved register * state was SVE but we will exit SM and use the - * FPSIMD register state - flush the saved FPSIMD - * register state in case it gets loaded. + * FPSIMD register state. + * + * TODO: decide if this should behave as SMSTOP (e.g. reset + * FPSR + FPMR), or whether this should only clear the scalable + * registers + ZA state. */ if (current->thread.svcr & SVCR_SM_MASK) { memset(¤t->thread.uw.fpsimd_state, 0, @@ -1519,9 +1479,7 @@ static int setup_return(struct pt_regs *regs, struct ksignal *ksig, current->thread.fp_type = FP_STATE_FPSIMD; } - current->thread.svcr &= ~(SVCR_ZA_MASK | - SVCR_SM_MASK); - sme_smstop(); + current->thread.svcr &= ~(SVCR_ZA_MASK | SVCR_SM_MASK); } return 0; @@ -1535,7 +1493,7 @@ static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, struct user_access_state ua_state; int err = 0; - fpsimd_signal_preserve_current_state(); + fpsimd_save_and_flush_current_state(); if (get_sigframe(&user, ksig, regs)) return 1; -- 2.51.0 From 2fe2b96c3818a043eb013a9db1885de75987715d Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Wed, 9 Apr 2025 17:40:10 +0100 Subject: [PATCH 16/16] arm64/fpsimd: signal: Simplify preserve_tpidr2_context() During a context-switch, tls_thread_switch() reads and writes a task's thread_struct::tpidr2_el0 field. Other code shouldn't access this field for an active task, as such accesses would form a data-race with a concurrent context-switch. The usage in preserve_tpidr2_context() is suspicious, but benign as any race with a context switch will write the same value back to current->thread.tpidr2_el0. Make this clearer and match restore_tpidr2_context() by using a temporary variable instead, avoiding the (benign) data-race. Signed-off-by: Mark Rutland Cc: Marc Zyngier Cc: Mark Brown Cc: Will Deacon Reviewed-by: Mark Brown Link: https://lore.kernel.org/r/20250409164010.3480271-14-mark.rutland@arm.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/signal.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index 0de9c452c6c0..73f1ab56d81b 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -478,13 +478,12 @@ extern int preserve_sve_context(void __user *ctx); static int preserve_tpidr2_context(struct tpidr2_context __user *ctx) { + u64 tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0); int err = 0; - current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0); - __put_user_error(TPIDR2_MAGIC, &ctx->head.magic, err); __put_user_error(sizeof(*ctx), &ctx->head.size, err); - __put_user_error(current->thread.tpidr2_el0, &ctx->tpidr2, err); + __put_user_error(tpidr2_el0, &ctx->tpidr2, err); return err; } -- 2.51.0