#define GHCB_VERSION_DEFAULT 2ULL
#define GHCB_VERSION_MIN 1ULL
-#define GHCB_HV_FT_SUPPORTED GHCB_HV_FT_SNP
+#define GHCB_HV_FT_SUPPORTED (GHCB_HV_FT_SNP | GHCB_HV_FT_SNP_AP_CREATION)
/* enable/disable SEV support */
static bool sev_enabled = true;
if (!kvm_ghcb_sw_scratch_is_valid(svm))
goto vmgexit_err;
break;
+ case SVM_VMGEXIT_AP_CREATION:
+ if (!sev_snp_guest(vcpu->kvm))
+ goto vmgexit_err;
+ if (lower_32_bits(control->exit_info_1) != SVM_VMGEXIT_AP_DESTROY)
+ if (!kvm_ghcb_rax_is_valid(svm))
+ goto vmgexit_err;
+ break;
case SVM_VMGEXIT_NMI_COMPLETE:
case SVM_VMGEXIT_AP_HLT_LOOP:
case SVM_VMGEXIT_AP_JUMP_TABLE:
unreachable();
}
+static int __sev_snp_update_protected_guest_state(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ WARN_ON(!mutex_is_locked(&svm->sev_es.snp_vmsa_mutex));
+
+ /* Mark the vCPU as offline and not runnable */
+ vcpu->arch.pv.pv_unhalted = false;
+ vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
+
+ /* Clear use of the VMSA */
+ svm->vmcb->control.vmsa_pa = INVALID_PAGE;
+
+ if (VALID_PAGE(svm->sev_es.snp_vmsa_gpa)) {
+ gfn_t gfn = gpa_to_gfn(svm->sev_es.snp_vmsa_gpa);
+ struct kvm_memory_slot *slot;
+ kvm_pfn_t pfn;
+
+ slot = gfn_to_memslot(vcpu->kvm, gfn);
+ if (!slot)
+ return -EINVAL;
+
+ /*
+ * The new VMSA will be private memory guest memory, so
+ * retrieve the PFN from the gmem backend.
+ */
+ if (kvm_gmem_get_pfn(vcpu->kvm, slot, gfn, &pfn, NULL))
+ return -EINVAL;
+
+ /*
+ * From this point forward, the VMSA will always be a
+ * guest-mapped page rather than the initial one allocated
+ * by KVM in svm->sev_es.vmsa. In theory, svm->sev_es.vmsa
+ * could be free'd and cleaned up here, but that involves
+ * cleanups like wbinvd_on_all_cpus() which would ideally
+ * be handled during teardown rather than guest boot.
+ * Deferring that also allows the existing logic for SEV-ES
+ * VMSAs to be re-used with minimal SNP-specific changes.
+ */
+ svm->sev_es.snp_has_guest_vmsa = true;
+
+ /* Use the new VMSA */
+ svm->vmcb->control.vmsa_pa = pfn_to_hpa(pfn);
+
+ /* Mark the vCPU as runnable */
+ vcpu->arch.pv.pv_unhalted = false;
+ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+
+ svm->sev_es.snp_vmsa_gpa = INVALID_PAGE;
+
+ /*
+ * gmem pages aren't currently migratable, but if this ever
+ * changes then care should be taken to ensure
+ * svm->sev_es.vmsa is pinned through some other means.
+ */
+ kvm_release_pfn_clean(pfn);
+ }
+
+ /*
+ * When replacing the VMSA during SEV-SNP AP creation,
+ * mark the VMCB dirty so that full state is always reloaded.
+ */
+ vmcb_mark_all_dirty(svm->vmcb);
+
+ return 0;
+}
+
+/*
+ * Invoked as part of svm_vcpu_reset() processing of an init event.
+ */
+void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+ int ret;
+
+ if (!sev_snp_guest(vcpu->kvm))
+ return;
+
+ mutex_lock(&svm->sev_es.snp_vmsa_mutex);
+
+ if (!svm->sev_es.snp_ap_waiting_for_reset)
+ goto unlock;
+
+ svm->sev_es.snp_ap_waiting_for_reset = false;
+
+ ret = __sev_snp_update_protected_guest_state(vcpu);
+ if (ret)
+ vcpu_unimpl(vcpu, "snp: AP state update on init failed\n");
+
+unlock:
+ mutex_unlock(&svm->sev_es.snp_vmsa_mutex);
+}
+
+static int sev_snp_ap_creation(struct vcpu_svm *svm)
+{
+ struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info;
+ struct kvm_vcpu *vcpu = &svm->vcpu;
+ struct kvm_vcpu *target_vcpu;
+ struct vcpu_svm *target_svm;
+ unsigned int request;
+ unsigned int apic_id;
+ bool kick;
+ int ret;
+
+ request = lower_32_bits(svm->vmcb->control.exit_info_1);
+ apic_id = upper_32_bits(svm->vmcb->control.exit_info_1);
+
+ /* Validate the APIC ID */
+ target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, apic_id);
+ if (!target_vcpu) {
+ vcpu_unimpl(vcpu, "vmgexit: invalid AP APIC ID [%#x] from guest\n",
+ apic_id);
+ return -EINVAL;
+ }
+
+ ret = 0;
+
+ target_svm = to_svm(target_vcpu);
+
+ /*
+ * The target vCPU is valid, so the vCPU will be kicked unless the
+ * request is for CREATE_ON_INIT. For any errors at this stage, the
+ * kick will place the vCPU in an non-runnable state.
+ */
+ kick = true;
+
+ mutex_lock(&target_svm->sev_es.snp_vmsa_mutex);
+
+ target_svm->sev_es.snp_vmsa_gpa = INVALID_PAGE;
+ target_svm->sev_es.snp_ap_waiting_for_reset = true;
+
+ /* 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 ^= sev->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 (!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);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * Malicious guest can RMPADJUST a large page into VMSA which
+ * will hit the SNP erratum where the CPU will incorrectly signal
+ * an RMP violation #PF if a hugepage collides with the RMP entry
+ * of VMSA page, reject the AP CREATE request if VMSA address from
+ * guest is 2M aligned.
+ */
+ if (IS_ALIGNED(svm->vmcb->control.exit_info_2, PMD_SIZE)) {
+ vcpu_unimpl(vcpu,
+ "vmgexit: AP VMSA address [%llx] from guest is unsafe as it is 2M aligned\n",
+ svm->vmcb->control.exit_info_2);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ target_svm->sev_es.snp_vmsa_gpa = svm->vmcb->control.exit_info_2;
+ break;
+ case SVM_VMGEXIT_AP_DESTROY:
+ break;
+ default:
+ vcpu_unimpl(vcpu, "vmgexit: invalid AP creation request [%#x] from guest\n",
+ request);
+ ret = -EINVAL;
+ break;
+ }
+
+out:
+ if (kick) {
+ kvm_make_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu);
+
+ if (target_vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)
+ kvm_make_request(KVM_REQ_UNBLOCK, target_vcpu);
+
+ kvm_vcpu_kick(target_vcpu);
+ }
+
+ mutex_unlock(&target_svm->sev_es.snp_vmsa_mutex);
+
+ return ret;
+}
+
static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
{
struct vmcb_control_area *control = &svm->vmcb->control;
ret = snp_begin_psc(svm, svm->sev_es.ghcb_sa);
break;
+ case SVM_VMGEXIT_AP_CREATION:
+ ret = sev_snp_ap_creation(svm);
+ if (ret) {
+ ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2);
+ ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_INPUT);
+ }
+
+ ret = 1;
+ break;
case SVM_VMGEXIT_UNSUPPORTED_EVENT:
vcpu_unimpl(vcpu,
"vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
* the VMSA will be NULL if this vCPU is the destination for intrahost
* migration, and will be copied later.
*/
- if (svm->sev_es.vmsa)
+ if (svm->sev_es.vmsa && !svm->sev_es.snp_has_guest_vmsa)
svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
/* Can't intercept CR register access, HV can't modify CR registers */
set_ghcb_msr(svm, GHCB_MSR_SEV_INFO((__u64)sev->ghcb_version,
GHCB_VERSION_MIN,
sev_enc_bit));
+
+ mutex_init(&svm->sev_es.snp_vmsa_mutex);
}
void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa)
return p;
}
+void sev_vcpu_unblocking(struct kvm_vcpu *vcpu)
+{
+ if (!sev_snp_guest(vcpu->kvm))
+ return;
+
+ if (kvm_test_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, vcpu) &&
+ vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)
+ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+}
+
void sev_handle_rmp_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code)
{
struct kvm_memory_slot *slot;
projects / nvme.git / commitdiff