Re: [PATCH v4 10/20] KVM:x86: Make guest supervisor states as non-XSAVE managed

[Chao Gao <chao.gao@intel.com>]

On Thu, Jul 20, 2023 at 11:03:42PM -0400, Yang Weijiang wrote:
>+static void kvm_save_cet_supervisor_ssp(struct kvm_vcpu *vcpu)
>+{
>+	preempt_disable();

what's the purpose of disabling preemption?

>+	if (unlikely(guest_can_use(vcpu, X86_FEATURE_SHSTK))) {
>+		rdmsrl(MSR_IA32_PL0_SSP, vcpu->arch.cet_s_ssp[0]);
>+		rdmsrl(MSR_IA32_PL1_SSP, vcpu->arch.cet_s_ssp[1]);
>+		rdmsrl(MSR_IA32_PL2_SSP, vcpu->arch.cet_s_ssp[2]);
>+		/*
>+		 * Omit reset to host PL{1,2}_SSP because Linux will never use
>+		 * these MSRs.
>+		 */
>+		wrmsrl(MSR_IA32_PL0_SSP, 0);

You don't need to reset the MSR because current host doesn't enable SSS
and leaving guest value in the MSR won't affect host behavior.

>+	}
>+	preempt_enable();
>+}
>+
>+static void kvm_reload_cet_supervisor_ssp(struct kvm_vcpu *vcpu)
>+{
>+	preempt_disable();
>+	if (unlikely(guest_can_use(vcpu, X86_FEATURE_SHSTK))) {
>+		wrmsrl(MSR_IA32_PL0_SSP, vcpu->arch.cet_s_ssp[0]);
>+		wrmsrl(MSR_IA32_PL1_SSP, vcpu->arch.cet_s_ssp[1]);
>+		wrmsrl(MSR_IA32_PL2_SSP, vcpu->arch.cet_s_ssp[2]);
>+	}
>+	preempt_enable();
>+}

save/load PLx_SSP in kvm_sched_in/out() and in VCPU_RUN ioctl is sub-optimal.

How about:
1. expose kvm_save/reload_cet_supervisor_ssp()
2. reload guest PLx_SSP in {vmx,svm}_prepare_switch_to_guest()
3. save guest PLx_SSP in vmx_prepare_switch_to_host() and
   svm_prepare_host_switch()?

this way existing svm/vmx->guest_state_loaded can help to reduce a lot of
unnecessary PLx_SSP MSR accesses.

>+
> int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
> {
> 	struct kvm_queued_exception *ex = &vcpu->arch.exception;
>@@ -11222,6 +11249,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
> 	kvm_sigset_activate(vcpu);
> 	kvm_run->flags = 0;
> 	kvm_load_guest_fpu(vcpu);
>+	kvm_reload_cet_supervisor_ssp(vcpu);
> 
> 	kvm_vcpu_srcu_read_lock(vcpu);
> 	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
>@@ -11310,6 +11338,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
> 	r = vcpu_run(vcpu);
> 
> out:
>+	kvm_save_cet_supervisor_ssp(vcpu);
> 	kvm_put_guest_fpu(vcpu);
> 	if (kvm_run->kvm_valid_regs)
> 		store_regs(vcpu);
>@@ -12398,9 +12427,17 @@ void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
> 		pmu->need_cleanup = true;
> 		kvm_make_request(KVM_REQ_PMU, vcpu);
> 	}
>+
>+	kvm_reload_cet_supervisor_ssp(vcpu);
>+
> 	static_call(kvm_x86_sched_in)(vcpu, cpu);
> }
> 
>+void kvm_arch_sched_out(struct kvm_vcpu *vcpu, int cpu)
>+{

@cpu its meaning isn't clear and isn't used and ...

>+	kvm_save_cet_supervisor_ssp(vcpu);
>+}
>+
> void kvm_arch_free_vm(struct kvm *kvm)
> {
> 	kfree(to_kvm_hv(kvm)->hv_pa_pg);
>diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
>index d90331f16db1..b3032a5f0641 100644
>--- a/include/linux/kvm_host.h
>+++ b/include/linux/kvm_host.h
>@@ -1423,6 +1423,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
> int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu);
> 
> void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu);
>+void kvm_arch_sched_out(struct kvm_vcpu *vcpu, int cpu);
> 
> void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
> void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
>diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
>index 66c1447d3c7f..42f28e8905e1 100644
>--- a/virt/kvm/kvm_main.c
>+++ b/virt/kvm/kvm_main.c
>@@ -5885,6 +5885,7 @@ static void kvm_sched_out(struct preempt_notifier *pn,
> {
> 	struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
> 
>+	kvm_arch_sched_out(vcpu, 0);

passing 0 always looks problematic.

> 	if (current->on_rq) {
> 		WRITE_ONCE(vcpu->preempted, true);
> 		WRITE_ONCE(vcpu->ready, true);
>-- 
>2.27.0
>