[PATCH OLK-5.10 47/80] arm64/sme: Implement ZA signal handling

From: Mark Brown broonie@kernel.org

mainline inclusion from mainline-v5.19-rc1 commit 39782210eb7e87634d96cacb6ece370bc59d74ba category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8E73O CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

-------------------------------------------------

Implement support for ZA in signal handling in a very similar way to how we implement support for SVE registers, using a signal context structure with optional register state after it. Where present this register state stores the ZA matrix as a series of horizontal vectors numbered from 0 to VL/8 in the endinanness independent format used for vectors.

As with SVE we do not allow changes in the vector length during signal return but we do allow ZA to be enabled or disabled.

Signed-off-by: Mark Brown broonie@kernel.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Link: https://lore.kernel.org/r/20220419112247.711548-20-broonie@kernel.org Signed-off-by: Catalin Marinas catalin.marinas@arm.com Conflicts: arch/arm64/kernel/signal.c Signed-off-by: Wang ShaoBo bobo.shaobowang@huawei.com --- arch/arm64/include/asm/signal_common.h | 14 +++ arch/arm64/include/uapi/asm/sigcontext.h | 41 ++++++++ arch/arm64/kernel/fpsimd.c | 3 - arch/arm64/kernel/signal.c | 124 +++++++++++++++++++++++ 4 files changed, 179 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/signal_common.h b/arch/arm64/include/asm/signal_common.h index 4f20ab2abac7f..b7389dffd3676 100644 --- a/arch/arm64/include/asm/signal_common.h +++ b/arch/arm64/include/asm/signal_common.h @@ -37,6 +37,7 @@ struct rt_sigframe_user_layout { unsigned long fpsimd_offset; unsigned long esr_offset; unsigned long sve_offset; + unsigned long za_offset; unsigned long extra_offset; unsigned long end_offset; }; @@ -44,6 +45,7 @@ struct rt_sigframe_user_layout { struct user_ctxs { struct fpsimd_context __user *fpsimd; struct sve_context __user *sve; + struct za_context __user *za; };

struct frame_record { @@ -129,6 +131,7 @@ static int get_sigframe(struct rt_sigframe_user_layout *user, return 0; }

+extern int restore_za_context(struct user_ctxs *user); static int restore_sigframe(struct pt_regs *regs, struct rt_sigframe __user *sf) { @@ -170,9 +173,13 @@ static int restore_sigframe(struct pt_regs *regs, } }

+ if (err == 0 && system_supports_sme() && user.za) + err = restore_za_context(&user); + return err; }

+extern int preserve_za_context(struct za_context __user *ctx); static int setup_sigframe(struct rt_sigframe_user_layout *user, struct pt_regs *regs, sigset_t *set) { @@ -220,6 +227,13 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, err |= preserve_sve_context(sve_ctx); }

+ /* ZA state if present */ + if (system_supports_sme() && err == 0 && user->za_offset) { + struct za_context __user *za_ctx = + apply_user_offset(user, user->za_offset); + err |= preserve_za_context(za_ctx); + } + if (err == 0 && user->extra_offset) setup_extra_context((char __user *)user->sigframe, user->size, (char __user *)apply_user_offset(user, diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h index 57e9f8c3ee9e5..4aaf31e3bf167 100644 --- a/arch/arm64/include/uapi/asm/sigcontext.h +++ b/arch/arm64/include/uapi/asm/sigcontext.h @@ -140,6 +140,14 @@ struct sve_context {

#define SVE_SIG_FLAG_SM 0x1 /* Context describes streaming mode */

+#define ZA_MAGIC 0x54366345 + +struct za_context { + struct _aarch64_ctx head; + __u16 vl; + __u16 __reserved[3]; +}; + #endif /* !__ASSEMBLY__ */

#include <asm/sve_context.h> @@ -259,4 +267,37 @@ struct sve_context { #define SVE_SIG_CONTEXT_SIZE(vq) \ (SVE_SIG_REGS_OFFSET + SVE_SIG_REGS_SIZE(vq))

+/* + * If the ZA register is enabled for the thread at signal delivery then, + * za_context.head.size >= ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl)) + * and the register data may be accessed using the ZA_SIG_*() macros. + * + * If za_context.head.size < ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za_context.vl)) + * then ZA was not enabled and no register data was included in which case + * ZA register was not enabled for the thread and no register data + * the ZA_SIG_*() macros should not be used except for this check. + * + * The same convention applies when returning from a signal: a caller + * will need to remove or resize the za_context block if it wants to + * enable the ZA register when it was previously non-live or vice-versa. + * This may require the caller to allocate fresh memory and/or move other + * context blocks in the signal frame. + * + * Changing the vector length during signal return is not permitted: + * za_context.vl must equal the thread's current SME vector length when + * doing a sigreturn. + */ + +#define ZA_SIG_REGS_OFFSET \ + ((sizeof(struct za_context) + (__SVE_VQ_BYTES - 1)) \ + / __SVE_VQ_BYTES * __SVE_VQ_BYTES) + +#define ZA_SIG_REGS_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES)) + +#define ZA_SIG_ZAV_OFFSET(vq, n) (ZA_SIG_REGS_OFFSET + \ + (SVE_SIG_ZREG_SIZE(vq) * n)) + +#define ZA_SIG_CONTEXT_SIZE(vq) \ + (ZA_SIG_REGS_OFFSET + ZA_SIG_REGS_SIZE(vq)) + #endif /* _UAPI__ASM_SIGCONTEXT_H */ diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 43493265caa3b..41e3622bf92c9 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1169,9 +1169,6 @@ void fpsimd_release_task(struct task_struct *dead_task)

#ifdef CONFIG_ARM64_SME

-/* This will move to uapi/asm/sigcontext.h when signals are implemented */ -#define ZA_SIG_REGS_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES)) - /* * Ensure that task->thread.za_state is allocated and sufficiently large. * diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index aa5eec803df4b..d8f1418f771f0 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -294,6 +294,98 @@ int restore_sve_fpsimd_context(struct user_ctxs *user)

#endif /* ! CONFIG_ARM64_SVE */

+#ifdef CONFIG_ARM64_SME + +int preserve_za_context(struct za_context __user *ctx) +{ + int err = 0; + u16 reserved[ARRAY_SIZE(ctx->__reserved)]; + unsigned int vl = task_get_sme_vl(current); + unsigned int vq; + + if (thread_za_enabled(&current->thread)) + vq = sve_vq_from_vl(vl); + else + vq = 0; + + memset(reserved, 0, sizeof(reserved)); + + __put_user_error(ZA_MAGIC, &ctx->head.magic, err); + __put_user_error(round_up(ZA_SIG_CONTEXT_SIZE(vq), 16), + &ctx->head.size, err); + __put_user_error(vl, &ctx->vl, err); + BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); + 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.za_state, + ZA_SIG_REGS_SIZE(vq)); + } + + return err ? -EFAULT : 0; +} + +int restore_za_context(struct user_ctxs __user *user) +{ + int err; + unsigned int vq; + struct za_context za; + + if (__copy_from_user(&za, user->za, sizeof(za))) + return -EFAULT; + + if (za.vl != task_get_sme_vl(current)) + return -EINVAL; + + if (za.head.size <= sizeof(*user->za)) { + current->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK; + return 0; + } + + vq = sve_vq_from_vl(za.vl); + + if (za.head.size < ZA_SIG_CONTEXT_SIZE(vq)) + return -EINVAL; + + /* + * Careful: we are about __copy_from_user() directly into + * thread.za_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); + if (!current->thread.za_state) { + current->thread.svcr &= ~SYS_SVCR_EL0_ZA_MASK; + clear_thread_flag(TIF_SME); + return -ENOMEM; + } + + err = __copy_from_user(current->thread.za_state, + (char __user const *)user->za + + ZA_SIG_REGS_OFFSET, + ZA_SIG_REGS_SIZE(vq)); + if (err) + return -EFAULT; + + set_thread_flag(TIF_SME); + current->thread.svcr |= SYS_SVCR_EL0_ZA_MASK; + + return 0; +} +#else /* ! CONFIG_ARM64_SME */ + +#endif /* ! CONFIG_ARM64_SME */ + int __parse_user_sigcontext(struct user_ctxs *user, struct sigcontext __user const *sc, void __user const *sigframe_base) @@ -307,6 +399,7 @@ int __parse_user_sigcontext(struct user_ctxs *user,

user->fpsimd = NULL; user->sve = NULL; + user->za = NULL;

if (!IS_ALIGNED((unsigned long)base, 16)) goto invalid; @@ -372,6 +465,19 @@ int __parse_user_sigcontext(struct user_ctxs *user, user->sve = (struct sve_context __user *)head; break;

+ case ZA_MAGIC: + if (!system_supports_sme()) + goto invalid; + + if (user->za) + goto invalid; + + if (size < sizeof(*user->za)) + goto invalid; + + user->za = (struct za_context __user *)head; + break; + case EXTRA_MAGIC: if (have_extra_context) goto invalid; @@ -506,6 +612,24 @@ int setup_sigframe_layout(struct rt_sigframe_user_layout *user, bool add_all) return err; }

+ if (system_supports_sme()) { + unsigned int vl; + unsigned int vq = 0; + + if (add_all) + vl = sme_max_vl(); + else + vl = task_get_sme_vl(current); + + if (thread_za_enabled(&current->thread)) + vq = sve_vq_from_vl(vl); + + err = sigframe_alloc(user, &user->za_offset, + ZA_SIG_CONTEXT_SIZE(vq)); + if (err) + return err; + } + return sigframe_alloc_end(user); }