KVM: SVM: Require AP's "requested" SEV_FEATURES to match KVM's view

When handling an "AP Create" event, return an error if the "requested" SEV
features for the vCPU don't exactly match KVM's view of the VM-scoped
features.  There is no known use case for heterogeneous SEV features across
vCPUs, and while KVM can't actually enforce an exact match since the value
in RAX isn't guaranteed to match what the guest shoved into the VMSA, KVM
can at least avoid knowingly letting the guest run in an unsupported state.

E.g. if a VM is created with DebugSwap disabled, KVM will intercept #DBs
and DRs for all vCPUs, even if an AP is "created" with DebugSwap enabled in
its VMSA.

Note, the GHCB spec only "requires" that "AP use the same interrupt
injection mechanism as the BSP", but given the disaster that is DebugSwap
and SEV_FEATURES in general, it's safe to say that AMD didn't consider all
possible complications with mismatching features between the BSP and APs.

Opportunistically fold the check into the relevant request flavors; the
"request < AP_DESTROY" check is just a bizarre way of implementing the
AP_CREATE_ON_INIT => AP_CREATE fallthrough.

Fixes: e366f92 ("KVM: SEV: Support SEV-SNP AP Creation NAE event")
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta@amd.com>
Link: https://lore.kernel.org/r/20250227012541.3234589-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

Author: sean-jc

arch/x86/include/asm/svm.h

@@ -291,10 +291,6 @@ static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_
 #define SVM_SEV_FEAT_ALTERNATE_INJECTION		BIT(4)
 #define SVM_SEV_FEAT_DEBUG_SWAP				BIT(5)
 
-#define SVM_SEV_FEAT_INT_INJ_MODES		\
-	(SVM_SEV_FEAT_RESTRICTED_INJECTION |	\
-	 SVM_SEV_FEAT_ALTERNATE_INJECTION)
-
 struct vmcb_seg {
 	u16 selector;
 	u16 attrib;

arch/x86/kvm/svm/sev.c

@@ -3938,6 +3938,7 @@ void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu)
 
 static int sev_snp_ap_creation(struct vcpu_svm *svm)
 {
+	struct kvm_sev_info *sev = to_kvm_sev_info(svm->vcpu.kvm);
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 	struct kvm_vcpu *target_vcpu;
 	struct vcpu_svm *target_svm;
@@ -3969,26 +3970,18 @@ static int sev_snp_ap_creation(struct vcpu_svm *svm)
 
 	mutex_lock(&target_svm->sev_es.snp_vmsa_mutex);
 
-	/* Interrupt injection mode shouldn't change for AP creation */
-	if (request < SVM_VMGEXIT_AP_DESTROY) {
-		u64 sev_features;
-
-		sev_features = vcpu->arch.regs[VCPU_REGS_RAX];
-		sev_features ^= to_kvm_sev_info(svm->vcpu.kvm)->vmsa_features;
-
-		if (sev_features & SVM_SEV_FEAT_INT_INJ_MODES) {
-			vcpu_unimpl(vcpu, "vmgexit: invalid AP injection mode [%#lx] from guest\n",
-				    vcpu->arch.regs[VCPU_REGS_RAX]);
-			ret = -EINVAL;
-			goto out;
-		}
-	}
-
 	switch (request) {
 	case SVM_VMGEXIT_AP_CREATE_ON_INIT:
 		kick = false;
 		fallthrough;
 	case SVM_VMGEXIT_AP_CREATE:
+		if (vcpu->arch.regs[VCPU_REGS_RAX] != sev->vmsa_features) {
+			vcpu_unimpl(vcpu, "vmgexit: mismatched AP sev_features [%#lx] != [%#llx] from guest\n",
+				    vcpu->arch.regs[VCPU_REGS_RAX], sev->vmsa_features);
+			ret = -EINVAL;
+			goto out;
+		}
+
 		if (!page_address_valid(vcpu, svm->vmcb->control.exit_info_2)) {
 			vcpu_unimpl(vcpu, "vmgexit: invalid AP VMSA address [%#llx] from guest\n",
 				    svm->vmcb->control.exit_info_2);