[PATCH v3 3/3] KVM: SVM: use .prepare_guest_switch() to handle CPU register save/setup

[Michael Roth <michael.roth@amd.com>]

Currently we save host state like user-visible host MSRs, and do some
initial guest register setup for MSR_TSC_AUX and MSR_AMD64_TSC_RATIO
in svm_vcpu_load(). Defer this until just before we enter the guest by
moving the handling to kvm_x86_ops.prepare_guest_switch() similarly to
how it is done for the VMX implementation.

Additionally, since handling of saving/restoring host user MSRs is the
same both with/without SEV-ES enabled, move that handling to common
code.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Michael Roth <michael.roth@amd.com>
---
 arch/x86/kvm/svm/sev.c | 22 +-----------
 arch/x86/kvm/svm/svm.c | 76 +++++++++++++++++++++++++++++-------------
 arch/x86/kvm/svm/svm.h |  5 +--
 3 files changed, 56 insertions(+), 47 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 2a93b63322f4..9e7272adf861 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -1990,11 +1990,10 @@ void sev_es_create_vcpu(struct vcpu_svm *svm)
 					    sev_enc_bit));
 }
 
-void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu)
+void sev_es_prepare_guest_switch(struct vcpu_svm *svm, unsigned int cpu)
 {
 	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
 	struct vmcb_save_area *hostsa;
-	unsigned int i;
 
 	/*
 	 * As an SEV-ES guest, hardware will restore the host state on VMEXIT,
@@ -2003,13 +2002,6 @@ void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu)
 	 */
 	asm volatile(__ex("vmsave") : : "a" (__sme_page_pa(sd->save_area)) : "memory");
 
-	/*
-	 * Certain MSRs are restored on VMEXIT, only save ones that aren't
-	 * restored.
-	 */
-	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
-		rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
-
 	/* XCR0 is restored on VMEXIT, save the current host value */
 	hostsa = (struct vmcb_save_area *)(page_address(sd->save_area) + 0x400);
 	hostsa->xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
@@ -2020,15 +2012,3 @@ void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu)
 	/* MSR_IA32_XSS is restored on VMEXIT, save the currnet host value */
 	hostsa->xss = host_xss;
 }
-
-void sev_es_vcpu_put(struct vcpu_svm *svm)
-{
-	unsigned int i;
-
-	/*
-	 * Certain MSRs are restored on VMEXIT and were saved with vmsave in
-	 * sev_es_vcpu_load() above. Only restore ones that weren't.
-	 */
-	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
-		wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
-}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 7e1b5b452244..8f16402019e7 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1359,6 +1359,7 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 		svm->vmsa = page_address(vmsa_page);
 
 	svm->asid_generation = 0;
+	svm->guest_state_loaded = false;
 	init_vmcb(svm);
 
 	svm_init_osvw(vcpu);
@@ -1406,23 +1407,30 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 	__free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER);
 }
 
-static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
-	int i;
+	struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu);
+	unsigned int i;
 
-	if (unlikely(cpu != vcpu->cpu)) {
-		svm->asid_generation = 0;
-		vmcb_mark_all_dirty(svm->vmcb);
-	}
+	if (svm->guest_state_loaded)
+		return;
+
+	/*
+	 * Certain MSRs are restored on VMEXIT (sev-es), or vmload of host save
+	 * area (non-sev-es). Save ones that aren't so we can restore them
+	 * individually later.
+	 */
+	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
+		rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
 
+	/*
+	 * Save additional host state that will be restored on VMEXIT (sev-es)
+	 * or subsequent vmload of host save area.
+	 */
 	if (sev_es_guest(svm->vcpu.kvm)) {
-		sev_es_vcpu_load(svm, cpu);
+		sev_es_prepare_guest_switch(svm, vcpu->cpu);
 	} else {
-		for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
-			rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
-
 		asm volatile(__ex("vmsave %%"_ASM_AX)
 			     : : "a" (page_to_phys(sd->save_area)) : "memory");
 	}
@@ -1434,10 +1442,42 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 			wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio);
 		}
 	}
+
 	/* This assumes that the kernel never uses MSR_TSC_AUX */
 	if (static_cpu_has(X86_FEATURE_RDTSCP))
 		wrmsrl(MSR_TSC_AUX, svm->tsc_aux);
 
+	svm->guest_state_loaded = true;
+}
+
+static void svm_prepare_host_switch(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	unsigned int i;
+
+	if (!svm->guest_state_loaded)
+		return;
+
+	/*
+	 * Certain MSRs are restored on VMEXIT (sev-es), or vmload of host save
+	 * area (non-sev-es). Restore the ones that weren't.
+	 */
+	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
+		wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
+
+	svm->guest_state_loaded = false;
+}
+
+static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
+
+	if (unlikely(cpu != vcpu->cpu)) {
+		svm->asid_generation = 0;
+		vmcb_mark_all_dirty(svm->vmcb);
+	}
+
 	if (sd->current_vmcb != svm->vmcb) {
 		sd->current_vmcb = svm->vmcb;
 		indirect_branch_prediction_barrier();
@@ -1447,18 +1487,10 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 static void svm_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	struct vcpu_svm *svm = to_svm(vcpu);
-	int i;
-
 	avic_vcpu_put(vcpu);
+	svm_prepare_host_switch(vcpu);
 
 	++vcpu->stat.host_state_reload;
-	if (sev_es_guest(svm->vcpu.kvm)) {
-		sev_es_vcpu_put(svm);
-	} else {
-		for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
-			wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
-	}
 }
 
 static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
@@ -3536,10 +3568,6 @@ static void svm_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t gva)
 	invlpga(gva, svm->vmcb->control.asid);
 }
 
-static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu)
-{
-}
-
 static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index a476449862f8..52d30a6e879c 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -171,6 +171,8 @@ struct vcpu_svm {
 	u64 ghcb_sa_len;
 	bool ghcb_sa_sync;
 	bool ghcb_sa_free;
+
+	bool guest_state_loaded;
 };
 
 struct svm_cpu_data {
@@ -569,8 +571,7 @@ int sev_handle_vmgexit(struct vcpu_svm *svm);
 int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in);
 void sev_es_init_vmcb(struct vcpu_svm *svm);
 void sev_es_create_vcpu(struct vcpu_svm *svm);
-void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu);
-void sev_es_vcpu_put(struct vcpu_svm *svm);
+void sev_es_prepare_guest_switch(struct vcpu_svm *svm, unsigned int cpu);
 
 /* vmenter.S */
 
-- 
2.25.1