[RFC,v9,33/51] KVM: SVM: Add KVM_SEV_SNP_LAUNCH_FINISH command

Commit Message

Michael Roth June 12, 2023, 4:25 a.m. UTC

From: Brijesh Singh <[e-mail]>

The KVM_SEV_SNP_LAUNCH_FINISH finalize the cryptographic digest and stores
it as the measurement of the guest at launch.

While finalizing the launch flow, it also issues the LAUNCH_UPDATE command
to encrypt the VMSA pages.

If its an SNP guest, then VMSA was added in the RMP entry as
a guest owned page and also removed from the kernel direct map
so flush it later after it is transitioned back to hypervisor
state and restored in the direct map.

Signed-off-by: Brijesh Singh <[e-mail]>
Signed-off-by: Harald Hoyer <[e-mail]>
Signed-off-by: Ashish Kalra <[e-mail]>
[mdr: always measure BSP first to get consistent launch measurements]
Signed-off-by: Michael Roth <[e-mail]>
---
 .../virt/kvm/x86/amd-memory-encryption.rst    |  24 +++
 arch/x86/kvm/svm/sev.c                        | 146 ++++++++++++++++++
 include/uapi/linux/kvm.h                      |  14 ++
 3 files changed, 184 insertions(+)

Patch

diff --git a/Documentation/virt/kvm/x86/amd-memory-encryption.rst b/Documentation/virt/kvm/x86/amd-memory-encryption.rst
index d8492af09796..cd77a19577fe 100644
--- a/Documentation/virt/kvm/x86/amd-memory-encryption.rst
+++ b/Documentation/virt/kvm/x86/amd-memory-encryption.rst
@@ -513,6 +513,30 @@  Returns: 0 on success, -negative on error
 See the SEV-SNP spec for further details on how to build the VMPL permission
 mask and page type.
 
+21. KVM_SNP_LAUNCH_FINISH
+-------------------------
+
+After completion of the SNP guest launch flow, the KVM_SNP_LAUNCH_FINISH command can be
+issued to make the guest ready for the execution.
+
+Parameters (in): struct kvm_sev_snp_launch_finish
+
+Returns: 0 on success, -negative on error
+
+::
+
+        struct kvm_sev_snp_launch_finish {
+                __u64 id_block_uaddr;
+                __u64 id_auth_uaddr;
+                __u8 id_block_en;
+                __u8 auth_key_en;
+                __u8 host_data[32];
+                __u8 pad[6];
+        };
+
+
+See SEV-SNP specification for further details on launch finish input parameters.
+
 References
 ==========
 
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 6a82767d940f..a7cbdc24ccdb 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -66,6 +66,8 @@  static bool sev_snp_enabled;
 #define AP_RESET_HOLD_NAE_EVENT		1
 #define AP_RESET_HOLD_MSR_PROTO		2
 
+#define INITIAL_VMSA_GPA 0xFFFFFFFFF000
+
 static u8 sev_enc_bit;
 static DECLARE_RWSEM(sev_deactivate_lock);
 static DEFINE_MUTEX(sev_bitmap_lock);
@@ -727,7 +729,29 @@  static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (!sev_es_guest(kvm))
 		return -ENOTTY;
 
+	/* Handle boot vCPU first to ensure consistent measurement of initial state. */
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (vcpu->vcpu_id != 0)
+			continue;
+
+		ret = mutex_lock_killable(&vcpu->mutex);
+		if (ret)
+			return ret;
+
+		ret = __sev_launch_update_vmsa(kvm, vcpu, &argp->error);
+
+		mutex_unlock(&vcpu->mutex);
+		if (ret)
+			return ret;
+
+		break;
+	}
+
+	/* Handle remaining vCPUs. */
 	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (vcpu->vcpu_id == 0)
+			continue;
+
 		ret = mutex_lock_killable(&vcpu->mutex);
 		if (ret)
 			return ret;
@@ -2139,6 +2163,109 @@  static int snp_launch_update(struct kvm *kvm, struct kvm_sev_cmd *argp)
 				      snp_launch_update_gfn_handler, argp);
 }
 
+static int snp_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct sev_data_snp_launch_update data = {};
+	struct kvm_vcpu *vcpu;
+	unsigned long i;
+	int ret;
+
+	data.gctx_paddr = __psp_pa(sev->snp_context);
+	data.page_type = SNP_PAGE_TYPE_VMSA;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		struct vcpu_svm *svm = to_svm(vcpu);
+		u64 pfn = __pa(svm->sev_es.vmsa) >> PAGE_SHIFT;
+
+		/* Perform some pre-encryption checks against the VMSA */
+		ret = sev_es_sync_vmsa(svm);
+		if (ret)
+			return ret;
+
+		/* Transition the VMSA page to a firmware state. */
+		ret = rmp_make_private(pfn, INITIAL_VMSA_GPA, PG_LEVEL_4K, sev->asid, true);
+		if (ret)
+			return ret;
+
+		/* Issue the SNP command to encrypt the VMSA */
+		data.address = __sme_pa(svm->sev_es.vmsa);
+		ret = __sev_issue_cmd(argp->sev_fd, SEV_CMD_SNP_LAUNCH_UPDATE,
+				      &data, &argp->error);
+		if (ret) {
+			snp_page_reclaim(pfn);
+			return ret;
+		}
+
+		svm->vcpu.arch.guest_state_protected = true;
+	}
+
+	return 0;
+}
+
+static int snp_launch_finish(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_snp_launch_finish params;
+	struct sev_data_snp_launch_finish *data;
+	void *id_block = NULL, *id_auth = NULL;
+	int ret;
+
+	if (!sev_snp_guest(kvm))
+		return -ENOTTY;
+
+	if (!sev->snp_context)
+		return -EINVAL;
+
+	if (copy_from_user(&params, (void __user *)(uintptr_t)argp->data, sizeof(params)))
+		return -EFAULT;
+
+	/* Measure all vCPUs using LAUNCH_UPDATE before finalizing the launch flow. */
+	ret = snp_launch_update_vmsa(kvm, argp);
+	if (ret)
+		return ret;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL_ACCOUNT);
+	if (!data)
+		return -ENOMEM;
+
+	if (params.id_block_en) {
+		id_block = psp_copy_user_blob(params.id_block_uaddr, KVM_SEV_SNP_ID_BLOCK_SIZE);
+		if (IS_ERR(id_block)) {
+			ret = PTR_ERR(id_block);
+			goto e_free;
+		}
+
+		data->id_block_en = 1;
+		data->id_block_paddr = __sme_pa(id_block);
+
+		id_auth = psp_copy_user_blob(params.id_auth_uaddr, KVM_SEV_SNP_ID_AUTH_SIZE);
+		if (IS_ERR(id_auth)) {
+			ret = PTR_ERR(id_auth);
+			goto e_free_id_block;
+		}
+
+		data->id_auth_paddr = __sme_pa(id_auth);
+
+		if (params.auth_key_en)
+			data->auth_key_en = 1;
+	}
+
+	memcpy(data->host_data, params.host_data, KVM_SEV_SNP_FINISH_DATA_SIZE);
+	data->gctx_paddr = __psp_pa(sev->snp_context);
+	ret = sev_issue_cmd(kvm, SEV_CMD_SNP_LAUNCH_FINISH, data, &argp->error);
+
+	kfree(id_auth);
+
+e_free_id_block:
+	kfree(id_block);
+
+e_free:
+	kfree(data);
+
+	return ret;
+}
+
 int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_sev_cmd sev_cmd;
@@ -2235,6 +2362,9 @@  int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
 	case KVM_SEV_SNP_LAUNCH_UPDATE:
 		r = snp_launch_update(kvm, &sev_cmd);
 		break;
+	case KVM_SEV_SNP_LAUNCH_FINISH:
+		r = snp_launch_finish(kvm, &sev_cmd);
+		break;
 	default:
 		r = -EINVAL;
 		goto out;
@@ -2695,11 +2825,27 @@  void sev_free_vcpu(struct kvm_vcpu *vcpu)
 
 	svm = to_svm(vcpu);
 
+	/*
+	 * If its an SNP guest, then VMSA was added in the RMP entry as
+	 * a guest owned page. Transition the page to hypervisor state
+	 * before releasing it back to the system.
+	 * Also the page is removed from the kernel direct map, so flush it
+	 * later after it is transitioned back to hypervisor state and
+	 * restored in the direct map.
+	 */
+	if (sev_snp_guest(vcpu->kvm)) {
+		u64 pfn = __pa(svm->sev_es.vmsa) >> PAGE_SHIFT;
+
+		if (host_rmp_make_shared(pfn, PG_LEVEL_4K, true))
+			goto skip_vmsa_free;
+	}
+
 	if (vcpu->arch.guest_state_protected)
 		sev_flush_encrypted_page(vcpu, svm->sev_es.vmsa);
 
 	__free_page(virt_to_page(svm->sev_es.vmsa));
 
+skip_vmsa_free:
 	if (svm->sev_es.ghcb_sa_free)
 		kvfree(svm->sev_es.ghcb_sa);
 }
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 4961d2e67a4b..1fb6a6615d09 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1930,6 +1930,7 @@  enum sev_cmd_id {
 	KVM_SEV_SNP_INIT,
 	KVM_SEV_SNP_LAUNCH_START,
 	KVM_SEV_SNP_LAUNCH_UPDATE,
+	KVM_SEV_SNP_LAUNCH_FINISH,
 
 	KVM_SEV_NR_MAX,
 };
@@ -2064,6 +2065,19 @@  struct kvm_sev_snp_launch_update {
 	__u8 vmpl1_perms;
 };
 
+#define KVM_SEV_SNP_ID_BLOCK_SIZE	96
+#define KVM_SEV_SNP_ID_AUTH_SIZE	4096
+#define KVM_SEV_SNP_FINISH_DATA_SIZE	32
+
+struct kvm_sev_snp_launch_finish {
+	__u64 id_block_uaddr;
+	__u64 id_auth_uaddr;
+	__u8 id_block_en;
+	__u8 auth_key_en;
+	__u8 host_data[KVM_SEV_SNP_FINISH_DATA_SIZE];
+	__u8 pad[6];
+};
+
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)
 #define KVM_DEV_ASSIGN_MASK_INTX	(1 << 2)