[PATCH v4 12/12] KVM: selftests: Trigger L2->L1 exits stress save+restore and #PF test

[Yosry Ahmed <yosry@kernel.org>]

Extend the testing coverage in L2 by forcing a nested VM-Exit from L2 to
L1 right after restore on every other iteration. Forcing a nested
VM-Exit while L0 has control (e.g. without explicitly running L2 and
making a hypercall) is valuable, as it often happens during live
migration (e.g. L1 timer interrupt fires by the time the VM lands on the
destination).

To force the nested VM-Exit inject a #UD in to the saved vCPU state, and
intercept #UD from L1.

With this change, the test reliably reproduces the CR2 bug fixed by
commit 5c247d08bc81 ("KVM: nSVM: Use vcpu->arch.cr2 when updating vmcb12
on nested #VMEXIT") -- at least on Milan, Genoa, and Turin CPUs.

Assisted-by: Gemini:gemini-3.1-pro
Signed-off-by: Yosry Ahmed <yosry@kernel.org>
---
 .../selftests/kvm/include/x86/processor.h     |  5 +++
 .../kvm/x86/save_restore_pf_stress_test.c     | 45 ++++++++++++++++---
 2 files changed, 44 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h
index 2889782b0016b..461c8aef7d37b 100644
--- a/tools/testing/selftests/kvm/include/x86/processor.h
+++ b/tools/testing/selftests/kvm/include/x86/processor.h
@@ -959,6 +959,11 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vcpu *vcpu);
 void vcpu_load_state(struct kvm_vcpu *vcpu, struct kvm_x86_state *state);
 void kvm_x86_state_cleanup(struct kvm_x86_state *state);
 
+static inline bool kvm_x86_state_is_guest_mode(struct kvm_x86_state *state)
+{
+	return state->nested.size && (state->nested.flags & KVM_STATE_NESTED_GUEST_MODE);
+}
+
 const struct kvm_msr_list *kvm_get_msr_index_list(void);
 const struct kvm_msr_list *kvm_get_feature_msr_index_list(void);
 bool kvm_msr_is_in_save_restore_list(u32 msr_index);
diff --git a/tools/testing/selftests/kvm/x86/save_restore_pf_stress_test.c b/tools/testing/selftests/kvm/x86/save_restore_pf_stress_test.c
index 0e5ddeb5af444..ba1d723001e94 100644
--- a/tools/testing/selftests/kvm/x86/save_restore_pf_stress_test.c
+++ b/tools/testing/selftests/kvm/x86/save_restore_pf_stress_test.c
@@ -87,8 +87,13 @@ static void guest_access_memory(void *arg)
 static void l1_svm_code(struct svm_test_data *svm)
 {
 	generic_svm_setup(svm, guest_access_memory);
-	run_guest(svm->vmcb, svm->vmcb_gpa);
-	GUEST_ASSERT(false);
+	svm->vmcb->control.intercept_exceptions |= BIT(UD_VECTOR);
+
+	while (1) {
+		run_guest(svm->vmcb, svm->vmcb_gpa);
+		GUEST_ASSERT_EQ(svm->vmcb->control.exit_code,
+				(SVM_EXIT_EXCP_BASE + UD_VECTOR));
+	}
 }
 
 static void l1_vmx_code(struct vmx_pages *vmx)
@@ -97,13 +102,17 @@ static void l1_vmx_code(struct vmx_pages *vmx)
 	GUEST_ASSERT(load_vmcs(vmx));
 	prepare_vmcs(vmx, guest_access_memory);
 
-	/* Ignore any #PF */
-	GUEST_ASSERT(!vmwrite(EXCEPTION_BITMAP, BIT(PF_VECTOR)));
+	/* Intercept UD, ignore any #PF */
+	GUEST_ASSERT(!vmwrite(EXCEPTION_BITMAP, BIT(UD_VECTOR) | BIT(PF_VECTOR)));
 	GUEST_ASSERT(!vmwrite(PAGE_FAULT_ERROR_CODE_MASK, 0));
 	GUEST_ASSERT(!vmwrite(PAGE_FAULT_ERROR_CODE_MATCH, -1));
 
 	GUEST_ASSERT(!vmlaunch());
-	GUEST_ASSERT(false);
+	while (1) {
+		GUEST_ASSERT_EQ(vmreadz(VM_EXIT_REASON), EXIT_REASON_EXCEPTION_NMI);
+		GUEST_ASSERT_EQ(vmreadz(VM_EXIT_INTR_INFO) & 0xff, UD_VECTOR);
+		GUEST_ASSERT(!vmresume());
+	}
 }
 
 static void l1_guest_code(void *test_data)
@@ -141,6 +150,19 @@ static void vcpu_sigusr_ignore(void)
 	sigaction(SIGUSR1, &sa, NULL);
 }
 
+static void kvm_x86_state_queue_ud(struct kvm_x86_state *state)
+{
+	if (state->events.exception.pending || state->events.exception.injected)
+		return;
+
+	state->events.flags |= KVM_VCPUEVENT_VALID_PAYLOAD;
+	state->events.exception.pending = true;
+	state->events.exception.injected = false;
+	state->events.exception.nr = UD_VECTOR;
+	state->events.exception.has_error_code = false;
+	state->events.exception_has_payload = false;
+}
+
 static void run_test(bool nested)
 {
 	struct kvm_x86_state *state;
@@ -156,6 +178,7 @@ static void run_test(bool nested)
 
 	vm = vm_create_with_one_vcpu(&vcpu, nested ? l1_guest_code : guest_access_memory);
 	vm_install_exception_handler(vm, PF_VECTOR, guest_pf_handler);
+	vm_enable_cap(vm, KVM_CAP_EXCEPTION_PAYLOAD, -2ul);
 
 	if (nested) {
 		if (kvm_cpu_has(X86_FEATURE_SVM))
@@ -224,8 +247,16 @@ static void run_test(bool nested)
 
 		state = vcpu_save_state(vcpu);
 
+		/*
+		 * If the vCPU is in guest mode, inject a #UD to trigger an
+		 * L2->L1 VM-Exit every other iteration.
+		 */
+		if (kvm_x86_state_is_guest_mode(state) && i % 2 == 0)
+			kvm_x86_state_queue_ud(state);
+
 		kvm_vm_release(vm);
 		vcpu = vm_recreate_with_one_vcpu(vm);
+		vm_enable_cap(vm, KVM_CAP_EXCEPTION_PAYLOAD, -2ul);
 		vcpu_load_state(vcpu, state);
 		kvm_x86_state_cleanup(state);
 
@@ -247,7 +278,9 @@ int main(int argc, char *argv[])
 	pr_info("Running save+restore stress test...\n");
 	run_test(/*nested=*/false);
 
-	if (!kvm_cpu_has(X86_FEATURE_SVM) && !kvm_cpu_has(X86_FEATURE_VMX)) {
+	if (!kvm_has_cap(KVM_CAP_EXCEPTION_PAYLOAD) ||
+	    !kvm_has_cap(KVM_CAP_NESTED_STATE) ||
+	    (!kvm_cpu_has(X86_FEATURE_SVM) && !kvm_cpu_has(X86_FEATURE_VMX))) {
 		pr_info("Nested virtualization not supported, skipping nested test\n");
 		return 0;
 	}
-- 
2.55.0.229.g6434b31f56-goog