[PATCH v12 10/29] KVM: SEV: Add KVM_SEV_SNP_LAUNCH_START command

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

From: Brijesh Singh <brijesh.singh@amd.com>

KVM_SEV_SNP_LAUNCH_START begins the launch process for an SEV-SNP guest.
The command initializes a cryptographic digest context used to construct
the measurement of the guest. Other commands can then at that point be
used to load/encrypt data into the guest's initial launch image.

For more information see the SEV-SNP specification.

Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Ashish Kalra <ashish.kalra@amd.com>
[mdr: hold sev_deactivate_lock when calling SEV_CMD_SNP_DECOMMISSION]
Signed-off-by: Michael Roth <michael.roth@amd.com>
---
 .../virt/kvm/x86/amd-memory-encryption.rst    |  23 ++-
 arch/x86/include/uapi/asm/kvm.h               |   8 +
 arch/x86/kvm/svm/sev.c                        | 152 +++++++++++++++++-
 arch/x86/kvm/svm/svm.h                        |   1 +
 4 files changed, 180 insertions(+), 4 deletions(-)

diff --git a/Documentation/virt/kvm/x86/amd-memory-encryption.rst b/Documentation/virt/kvm/x86/amd-memory-encryption.rst
index f7c007d34114..a10b817c162d 100644
--- a/Documentation/virt/kvm/x86/amd-memory-encryption.rst
+++ b/Documentation/virt/kvm/x86/amd-memory-encryption.rst
@@ -459,6 +459,25 @@ issued by the hypervisor to make the guest ready for execution.
 
 Returns: 0 on success, -negative on error
 
+18. KVM_SEV_SNP_LAUNCH_START
+----------------------------
+
+The KVM_SNP_LAUNCH_START command is used for creating the memory encryption
+context for the SEV-SNP guest.
+
+Parameters (in): struct  kvm_sev_snp_launch_start
+
+Returns: 0 on success, -negative on error
+
+::
+
+        struct kvm_sev_snp_launch_start {
+                __u64 policy;           /* Guest policy to use. */
+                __u8 gosvw[16];         /* Guest OS visible workarounds. */
+        };
+
+See the SEV-SNP spec [snp-fw-abi]_ for further detail on the launch input.
+
 Device attribute API
 ====================
 
@@ -490,9 +509,11 @@ References
 ==========
 
 
-See [white-paper]_, [api-spec]_, [amd-apm]_ and [kvm-forum]_ for more info.
+See [white-paper]_, [api-spec]_, [amd-apm]_, [kvm-forum]_, and [snp-fw-abi]_
+for more info.
 
 .. [white-paper] https://developer.amd.com/wordpress/media/2013/12/AMD_Memory_Encryption_Whitepaper_v7-Public.pdf
 .. [api-spec] https://support.amd.com/TechDocs/55766_SEV-KM_API_Specification.pdf
 .. [amd-apm] https://support.amd.com/TechDocs/24593.pdf (section 15.34)
 .. [kvm-forum]  https://www.linux-kvm.org/images/7/74/02x08A-Thomas_Lendacky-AMDs_Virtualizatoin_Memory_Encryption_Technology.pdf
+.. [snp-fw-abi] https://www.amd.com/system/files/TechDocs/56860.pdf
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 725b75cfe9ff..350ddd5264ea 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -693,6 +693,9 @@ enum sev_cmd_id {
 	/* Second time is the charm; improved versions of the above ioctls.  */
 	KVM_SEV_INIT2,
 
+	/* SNP-specific commands */
+	KVM_SEV_SNP_LAUNCH_START,
+
 	KVM_SEV_NR_MAX,
 };
 
@@ -818,6 +821,11 @@ struct kvm_sev_receive_update_data {
 	__u32 pad2;
 };
 
+struct kvm_sev_snp_launch_start {
+	__u64 policy;
+	__u8 gosvw[16];
+};
+
 #define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
 #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
 
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 3d9771163562..6c7c77e33e62 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -25,6 +25,7 @@
 #include <asm/fpu/xcr.h>
 #include <asm/fpu/xstate.h>
 #include <asm/debugreg.h>
+#include <asm/sev.h>
 
 #include "mmu.h"
 #include "x86.h"
@@ -58,6 +59,10 @@ static u64 sev_supported_vmsa_features;
 #define AP_RESET_HOLD_NAE_EVENT		1
 #define AP_RESET_HOLD_MSR_PROTO		2
 
+/* As defined by SEV-SNP Firmware ABI, under "Guest Policy". */
+#define SNP_POLICY_MASK_SMT		BIT_ULL(16)
+#define SNP_POLICY_MASK_SINGLE_SOCKET	BIT_ULL(20)
+
 static u8 sev_enc_bit;
 static DECLARE_RWSEM(sev_deactivate_lock);
 static DEFINE_MUTEX(sev_bitmap_lock);
@@ -68,6 +73,8 @@ static unsigned int nr_asids;
 static unsigned long *sev_asid_bitmap;
 static unsigned long *sev_reclaim_asid_bitmap;
 
+static int snp_decommission_context(struct kvm *kvm);
+
 struct enc_region {
 	struct list_head list;
 	unsigned long npages;
@@ -94,12 +101,17 @@ static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid)
 	down_write(&sev_deactivate_lock);
 
 	wbinvd_on_all_cpus();
-	ret = sev_guest_df_flush(&error);
+
+	if (sev_snp_enabled)
+		ret = sev_do_cmd(SEV_CMD_SNP_DF_FLUSH, NULL, &error);
+	else
+		ret = sev_guest_df_flush(&error);
 
 	up_write(&sev_deactivate_lock);
 
 	if (ret)
-		pr_err("SEV: DF_FLUSH failed, ret=%d, error=%#x\n", ret, error);
+		pr_err("SEV%s: DF_FLUSH failed, ret=%d, error=%#x\n",
+		       sev_snp_enabled ? "-SNP" : "", ret, error);
 
 	return ret;
 }
@@ -1967,6 +1979,102 @@ int sev_dev_get_attr(u64 attr, u64 *val)
 	}
 }
 
+/*
+ * The guest context contains all the information, keys and metadata
+ * associated with the guest that the firmware tracks to implement SEV
+ * and SNP features. The firmware stores the guest context in hypervisor
+ * provide page via the SNP_GCTX_CREATE command.
+ */
+static void *snp_context_create(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	struct sev_data_snp_addr data = {};
+	void *context;
+	int rc;
+
+	/* Allocate memory for context page */
+	context = snp_alloc_firmware_page(GFP_KERNEL_ACCOUNT);
+	if (!context)
+		return NULL;
+
+	data.address = __psp_pa(context);
+	rc = __sev_issue_cmd(argp->sev_fd, SEV_CMD_SNP_GCTX_CREATE, &data, &argp->error);
+	if (rc) {
+		pr_warn("Failed to create SEV-SNP context, rc %d fw_error %d",
+			rc, argp->error);
+		snp_free_firmware_page(context);
+		return NULL;
+	}
+
+	return context;
+}
+
+static int snp_bind_asid(struct kvm *kvm, int *error)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct sev_data_snp_activate data = {0};
+
+	data.gctx_paddr = __psp_pa(sev->snp_context);
+	data.asid = sev_get_asid(kvm);
+	return sev_issue_cmd(kvm, SEV_CMD_SNP_ACTIVATE, &data, error);
+}
+
+static int snp_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct sev_data_snp_launch_start start = {0};
+	struct kvm_sev_snp_launch_start params;
+	int rc;
+
+	if (!sev_snp_guest(kvm))
+		return -ENOTTY;
+
+	if (copy_from_user(&params, u64_to_user_ptr(argp->data), sizeof(params)))
+		return -EFAULT;
+
+	/* Don't allow userspace to allocate memory for more than 1 SNP context. */
+	if (sev->snp_context) {
+		pr_debug("SEV-SNP context already exists. Refusing to allocate an additional one.");
+		return -EINVAL;
+	}
+
+	sev->snp_context = snp_context_create(kvm, argp);
+	if (!sev->snp_context)
+		return -ENOTTY;
+
+	if (params.policy & SNP_POLICY_MASK_SINGLE_SOCKET) {
+		pr_debug("SEV-SNP hypervisor does not support limiting guests to a single socket.");
+		return -EINVAL;
+	}
+
+	if (!(params.policy & SNP_POLICY_MASK_SMT)) {
+		pr_debug("SEV-SNP hypervisor does not support limiting guests to a single SMT thread.");
+		return -EINVAL;
+	}
+
+	start.gctx_paddr = __psp_pa(sev->snp_context);
+	start.policy = params.policy;
+	memcpy(start.gosvw, params.gosvw, sizeof(params.gosvw));
+	rc = __sev_issue_cmd(argp->sev_fd, SEV_CMD_SNP_LAUNCH_START, &start, &argp->error);
+	if (rc) {
+		pr_debug("SEV_CMD_SNP_LAUNCH_START command failed, rc %d\n", rc);
+		goto e_free_context;
+	}
+
+	sev->fd = argp->sev_fd;
+	rc = snp_bind_asid(kvm, &argp->error);
+	if (rc) {
+		pr_debug("Failed to bind ASID to SEV-SNP context, rc %d\n", rc);
+		goto e_free_context;
+	}
+
+	return 0;
+
+e_free_context:
+	snp_decommission_context(kvm);
+
+	return rc;
+}
+
 int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_sev_cmd sev_cmd;
@@ -2054,6 +2162,9 @@ int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
 	case KVM_SEV_RECEIVE_FINISH:
 		r = sev_receive_finish(kvm, &sev_cmd);
 		break;
+	case KVM_SEV_SNP_LAUNCH_START:
+		r = snp_launch_start(kvm, &sev_cmd);
+		break;
 	default:
 		r = -EINVAL;
 		goto out;
@@ -2249,6 +2360,33 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 	return ret;
 }
 
+static int snp_decommission_context(struct kvm *kvm)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct sev_data_snp_addr data = {};
+	int ret;
+
+	/* If context is not created then do nothing */
+	if (!sev->snp_context)
+		return 0;
+
+	data.address = __sme_pa(sev->snp_context);
+	down_write(&sev_deactivate_lock);
+	ret = sev_do_cmd(SEV_CMD_SNP_DECOMMISSION, &data, NULL);
+	if (WARN_ONCE(ret, "failed to release guest context")) {
+		up_write(&sev_deactivate_lock);
+		return ret;
+	}
+
+	up_write(&sev_deactivate_lock);
+
+	/* free the context page now */
+	snp_free_firmware_page(sev->snp_context);
+	sev->snp_context = NULL;
+
+	return 0;
+}
+
 void sev_vm_destroy(struct kvm *kvm)
 {
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
@@ -2290,7 +2428,15 @@ void sev_vm_destroy(struct kvm *kvm)
 		}
 	}
 
-	sev_unbind_asid(kvm, sev->handle);
+	if (sev_snp_guest(kvm)) {
+		if (snp_decommission_context(kvm)) {
+			WARN_ONCE(1, "Failed to free SNP guest context, leaking asid!\n");
+			return;
+		}
+	} else {
+		sev_unbind_asid(kvm, sev->handle);
+	}
+
 	sev_asid_free(sev);
 }
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 4a01a81dd9b9..a3c190642c57 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -92,6 +92,7 @@ struct kvm_sev_info {
 	struct list_head mirror_entry; /* Use as a list entry of mirrors */
 	struct misc_cg *misc_cg; /* For misc cgroup accounting */
 	atomic_t migration_in_progress;
+	void *snp_context;      /* SNP guest context page */
 };
 
 struct kvm_svm {
-- 
2.25.1