[ Upstream commit deeb8f9a80fdae5a62525656d65c7070c28bd3a4 ]
In order to avoid needlessly saving and restoring the guest registers KVM relies on the host FPSMID code to save the guest registers when we context switch away from the guest. This is done by binding the KVM guest state to the CPU on top of the task state that was originally there, then carefully managing the TIF_SVE flag for the task to cause the host to save the full SVE state when needed regardless of the needs of the host task. This works well enough but isn't terribly direct about what is going on and makes it much more complicated to try to optimise what we're doing with the SVE register state.
Let's instead have KVM pass in the register state it wants saving when it binds to the CPU. We introduce a new FP_STATE_CURRENT for use during normal task binding to indicate that we should base our decisions on the current task. This should not be used when actually saving. Ideally we might want to use a separate enum for the type to save but this enum and the enum values would then need to be named which has problems with clarity and ambiguity.
In order to ease any future debugging that might be required this patch does not actually update any of the decision making about what to save, it merely starts tracking the new information and warns if the requested state is not what we would otherwise have decided to save.
Signed-off-by: Mark Brown broonie@kernel.org Reviewed-by: Catalin Marinas catalin.marinas@arm.com Reviewed-by: Marc Zyngier maz@kernel.org Link: https://lore.kernel.org/r/20221115094640.112848-4-broonie@kernel.org Signed-off-by: Will Deacon will@kernel.org [ Mark: trivial backport ] Signed-off-by: Mark Rutland mark.rutland@arm.com Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/fpsimd.h | 3 ++- arch/arm64/include/asm/processor.h | 1 + arch/arm64/kernel/fpsimd.c | 27 ++++++++++++++++++++++++--- arch/arm64/kvm/fpsimd.c | 9 ++++++++- 4 files changed, 35 insertions(+), 5 deletions(-)
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index e10894100c73..7622782d0bb9 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -61,7 +61,8 @@ extern void fpsimd_kvm_prepare(void); extern void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *state, void *sve_state, unsigned int sve_vl, void *za_state, unsigned int sme_vl, - u64 *svcr, enum fp_type *type); + u64 *svcr, enum fp_type *type, + enum fp_type to_save);
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 208434a2e924..1b822e618bb4 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -123,6 +123,7 @@ enum vec_type { };
enum fp_type { + FP_STATE_CURRENT, /* Save based on current task state. */ FP_STATE_FPSIMD, FP_STATE_SVE, }; diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 2e0cecf02bf8..1f6fd9229e53 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -126,6 +126,7 @@ struct fpsimd_last_state_struct { unsigned int sve_vl; unsigned int sme_vl; enum fp_type *fp_type; + enum fp_type to_save; };
static DEFINE_PER_CPU(struct fpsimd_last_state_struct, fpsimd_last_state); @@ -356,7 +357,8 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, * but userspace is discouraged from relying on this. * * task->thread.sve_state does not need to be non-NULL, valid or any - * particular size: it must not be dereferenced. + * particular size: it must not be dereferenced and any data stored + * there should be considered stale and not referenced. * * * SVE state - FP_STATE_SVE: * @@ -369,7 +371,9 @@ void task_set_vl_onexec(struct task_struct *task, enum vec_type type, * task->thread.uw.fpsimd_state should be ignored. * * task->thread.sve_state must point to a valid buffer at least - * sve_state_size(task) bytes in size. + * sve_state_size(task) bytes in size. The data stored in + * task->thread.uw.fpsimd_state.vregs should be considered stale + * and not referenced. * * * FPSR and FPCR are always stored in task->thread.uw.fpsimd_state * irrespective of whether TIF_SVE is clear or set, since these are @@ -459,6 +463,21 @@ static void fpsimd_save(void) vl = last->sve_vl; }
+ /* + * Validate that an explicitly specified state to save is + * consistent with the task state. + */ + switch (last->to_save) { + case FP_STATE_CURRENT: + break; + case FP_STATE_FPSIMD: + WARN_ON_ONCE(save_sve_regs); + break; + case FP_STATE_SVE: + WARN_ON_ONCE(!save_sve_regs); + break; + } + if (system_supports_sme()) { u64 *svcr = last->svcr;
@@ -1709,6 +1728,7 @@ static void fpsimd_bind_task_to_cpu(void) last->sme_vl = task_get_sme_vl(current); last->svcr = ¤t->thread.svcr; last->fp_type = ¤t->thread.fp_type; + last->to_save = FP_STATE_CURRENT; current->thread.fpsimd_cpu = smp_processor_id();
/* @@ -1733,7 +1753,7 @@ 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, void *za_state, unsigned int sme_vl, u64 *svcr, - enum fp_type *type) + enum fp_type *type, enum fp_type to_save) { struct fpsimd_last_state_struct *last = this_cpu_ptr(&fpsimd_last_state); @@ -1748,6 +1768,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, last->sve_vl = sve_vl; last->sme_vl = sme_vl; last->fp_type = type; + last->to_save = to_save; }
/* diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index a4b4502ad850..89c02ce797b8 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -130,9 +130,16 @@ void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu) */ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) { + enum fp_type fp_type; + WARN_ON_ONCE(!irqs_disabled());
if (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED) { + if (vcpu_has_sve(vcpu)) + fp_type = FP_STATE_SVE; + else + fp_type = FP_STATE_FPSIMD; + /* * Currently we do not support SME guests so SVCR is * always 0 and we just need a variable to point to. @@ -141,7 +148,7 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) vcpu->arch.sve_state, vcpu->arch.sve_max_vl, NULL, 0, &vcpu->arch.svcr, - &vcpu->arch.fp_type); + &vcpu->arch.fp_type, fp_type);
clear_thread_flag(TIF_FOREIGN_FPSTATE); update_thread_flag(TIF_SVE, vcpu_has_sve(vcpu));