In SME the use of both streaming SVE mode and ZA are tracked through PSTATE.SM and PSTATE.ZA, visible through the system register SVCR. In order to context switch the floating point state for SME we need to context switch the contents of this register as part of context switching the floating point state.
Since changing the vector length exits streaming SVE mode and disables ZA we also make sure we update SVCR appropriately when setting vector length, and similarly ensure that new threads have streaming SVE mode and ZA disabled.
Signed-off-by: Mark Brown broonie@kernel.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com --- arch/arm64/include/asm/fpsimd.h | 3 ++- arch/arm64/include/asm/processor.h | 1 + arch/arm64/include/asm/thread_info.h | 1 + arch/arm64/kernel/fpsimd.c | 18 +++++++++++++++++- arch/arm64/kernel/process.c | 2 ++ arch/arm64/kvm/fpsimd.c | 7 ++++++- 6 files changed, 29 insertions(+), 3 deletions(-)
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 38fd6aab7feb..821d270980da 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -46,7 +46,8 @@ extern void fpsimd_restore_current_state(void); extern void fpsimd_update_current_state(struct user_fpsimd_state const *state);
extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state, - void *sve_state, unsigned int sve_vl); + void *sve_state, unsigned int sve_vl, + u64 *svcr);
extern void fpsimd_flush_task_state(struct task_struct *target); extern void fpsimd_save_and_flush_cpu_state(void); diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index 849e97d418a8..22cd11e86854 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -169,6 +169,7 @@ struct thread_struct { u64 mte_ctrl; #endif u64 sctlr_user; + u64 svcr; u64 tpidr2_el0; };
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 4e6b58dcd6f9..848739c15de8 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -82,6 +82,7 @@ int arch_dup_task_struct(struct task_struct *dst, #define TIF_SVE_VL_INHERIT 24 /* Inherit SVE vl_onexec across exec */ #define TIF_SSBD 25 /* Wants SSB mitigation */ #define TIF_TAGGED_ADDR 26 /* Allow tagged user addresses */ +#define TIF_SME 27 /* SME in use */ #define TIF_SME_VL_INHERIT 28 /* Inherit SME vl_onexec across exec */
#define _TIF_SIGPENDING (1 << TIF_SIGPENDING) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 231f2d85b65e..1c113349f6cc 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -121,6 +121,7 @@ struct fpsimd_last_state_struct { struct user_fpsimd_state *st; void *sve_state; + u64 *svcr; unsigned int sve_vl; };
@@ -359,6 +360,9 @@ static void task_fpsimd_load(void) WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context());
+ if (IS_ENABLED(CONFIG_ARM64_SME) && test_thread_flag(TIF_SME)) + write_sysreg_s(current->thread.svcr, SYS_SVCR_EL0); + if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) { sve_set_vq(sve_vq_from_vl(task_get_sve_vl(current)) - 1); sve_load_state(sve_pffr(¤t->thread), @@ -390,6 +394,12 @@ static void fpsimd_save(void) if (test_thread_flag(TIF_FOREIGN_FPSTATE)) return;
+ if (IS_ENABLED(CONFIG_ARM64_SME) && + test_thread_flag(TIF_SME)) { + u64 *svcr = last->svcr; + *svcr = read_sysreg_s(SYS_SVCR_EL0); + } + if (IS_ENABLED(CONFIG_ARM64_SVE) && test_thread_flag(TIF_SVE)) { if (WARN_ON(sve_get_vl() != last->sve_vl)) { @@ -741,6 +751,10 @@ int vec_set_vector_length(struct task_struct *task, enum vec_type type, if (test_and_clear_tsk_thread_flag(task, TIF_SVE)) sve_to_fpsimd(task);
+ if (system_supports_sme() && type == ARM64_VEC_SME) + task->thread.svcr &= ~(SYS_SVCR_EL0_SM_MASK | + SYS_SVCR_EL0_ZA_MASK); + if (task == current) put_cpu_fpsimd_context();
@@ -1404,6 +1418,7 @@ static void fpsimd_bind_task_to_cpu(void) last->st = ¤t->thread.uw.fpsimd_state; last->sve_state = current->thread.sve_state; last->sve_vl = task_get_sve_vl(current); + last->svcr = ¤t->thread.svcr; current->thread.fpsimd_cpu = smp_processor_id();
if (system_supports_sve()) { @@ -1418,7 +1433,7 @@ static void fpsimd_bind_task_to_cpu(void) }
void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, - unsigned int sve_vl) + unsigned int sve_vl, u64 *svcr) { struct fpsimd_last_state_struct *last = this_cpu_ptr(&fpsimd_last_state); @@ -1427,6 +1442,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, WARN_ON(!in_softirq() && !irqs_disabled());
last->st = st; + last->svcr = svcr; last->sve_state = sve_state; last->sve_vl = sve_vl; } diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index e20571f19718..07f235b46cf5 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -310,6 +310,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) dst->thread.sve_state = NULL; clear_tsk_thread_flag(dst, TIF_SVE);
+ dst->thread.svcr = 0; + /* clear any pending asynchronous tag fault raised by the parent */ clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 397fdac75cb1..ac09f1f682ff 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -109,9 +109,14 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) WARN_ON_ONCE(!irqs_disabled());
if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) { + /* + * Currently we do not support SME guests so SVCR is + * always 0 and we just need a variable to point to. + */ fpsimd_bind_state_to_cpu(&vcpu->arch.ctxt.fp_regs, vcpu->arch.sve_state, - vcpu->arch.sve_max_vl); + vcpu->arch.sve_max_vl, + NULL);
clear_thread_flag(TIF_FOREIGN_FPSTATE); update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu));