Merge branch 'kvm-sev-es-ghcbv2' into HEAD

While the main additions from GHCB protocol version 1 to version 2
revolve mostly around SEV-SNP support, there are a number of changes
applicable to SEV-ES guests as well. Pluck a handful patches from the
SNP hypervisor patchset for GHCB-related changes that are also applicable
to SEV-ES.  A KVM_SEV_INIT2 field lets userspace can control the maximum
GHCB protocol version advertised to guests and manage compatibility
across kernels/versions.

Author: bonzini

Documentation/virt/kvm/x86/amd-memory-encryption.rst

@@ -95,13 +95,19 @@ Returns: 0 on success, -negative on error
         struct kvm_sev_init {
                 __u64 vmsa_features;  /* initial value of features field in VMSA */
                 __u32 flags;          /* must be 0 */
-                __u32 pad[9];
+                __u16 ghcb_version;   /* maximum guest GHCB version allowed */
+                __u16 pad1;
+                __u32 pad2[8];
         };
 
 It is an error if the hypervisor does not support any of the bits that
 are set in ``flags`` or ``vmsa_features``.  ``vmsa_features`` must be
 0 for SEV virtual machines, as they do not have a VMSA.
 
+``ghcb_version`` must be 0 for SEV virtual machines, as they do not issue GHCB
+requests. If ``ghcb_version`` is 0 for any other guest type, then the maximum
+allowed guest GHCB protocol will default to version 2.
+
 This command replaces the deprecated KVM_SEV_INIT and KVM_SEV_ES_INIT commands.
 The commands did not have any parameters (the ```data``` field was unused) and
 only work for the KVM_X86_DEFAULT_VM machine type (0).
@@ -112,7 +118,8 @@ They behave as if:
   KVM_SEV_ES_INIT
 
 * the ``flags`` and ``vmsa_features`` fields of ``struct kvm_sev_init`` are
-  set to zero
+  set to zero, and ``ghcb_version`` is set to 0 for KVM_SEV_INIT and 1 for
+  KVM_SEV_ES_INIT.
 
 If the ``KVM_X86_SEV_VMSA_FEATURES`` attribute does not exist, the hypervisor only
 supports KVM_SEV_INIT and KVM_SEV_ES_INIT.  In that case, note that KVM_SEV_ES_INIT

arch/x86/include/asm/sev-common.h

@@ -54,8 +54,10 @@
 	(((unsigned long)fn) << 32))
 
 /* AP Reset Hold */
-#define GHCB_MSR_AP_RESET_HOLD_REQ	0x006
-#define GHCB_MSR_AP_RESET_HOLD_RESP	0x007
+#define GHCB_MSR_AP_RESET_HOLD_REQ		0x006
+#define GHCB_MSR_AP_RESET_HOLD_RESP		0x007
+#define GHCB_MSR_AP_RESET_HOLD_RESULT_POS	12
+#define GHCB_MSR_AP_RESET_HOLD_RESULT_MASK	GENMASK_ULL(51, 0)
 
 /* GHCB GPA Register */
 #define GHCB_MSR_REG_GPA_REQ		0x012
@@ -99,6 +101,8 @@ enum psc_op {
 /* GHCB Hypervisor Feature Request/Response */
 #define GHCB_MSR_HV_FT_REQ		0x080
 #define GHCB_MSR_HV_FT_RESP		0x081
+#define GHCB_MSR_HV_FT_POS		12
+#define GHCB_MSR_HV_FT_MASK		GENMASK_ULL(51, 0)
 #define GHCB_MSR_HV_FT_RESP_VAL(v)			\
 	/* GHCBData[63:12] */				\
 	(((u64)(v) & GENMASK_ULL(63, 12)) >> 12)

arch/x86/include/uapi/asm/kvm.h

@@ -711,7 +711,9 @@ struct kvm_sev_cmd {
 struct kvm_sev_init {
 	__u64 vmsa_features;
 	__u32 flags;
-	__u32 pad[9];
+	__u16 ghcb_version;
+	__u16 pad1;
+	__u32 pad2[8];
 };
 
 struct kvm_sev_launch_start {

arch/x86/kvm/svm/sev.c

@@ -33,9 +33,12 @@
 #include "cpuid.h"
 #include "trace.h"
 
-#define GHCB_VERSION_MAX	1ULL
+#define GHCB_VERSION_MAX	2ULL
+#define GHCB_VERSION_DEFAULT	2ULL
 #define GHCB_VERSION_MIN	1ULL
 
+#define GHCB_HV_FT_SUPPORTED	GHCB_HV_FT_SNP
+
 /* enable/disable SEV support */
 static bool sev_enabled = true;
 module_param_named(sev, sev_enabled, bool, 0444);
@@ -49,6 +52,10 @@ static bool sev_es_debug_swap_enabled = true;
 module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444);
 static u64 sev_supported_vmsa_features;
 
+#define AP_RESET_HOLD_NONE		0
+#define AP_RESET_HOLD_NAE_EVENT		1
+#define AP_RESET_HOLD_MSR_PROTO		2
+
 static u8 sev_enc_bit;
 static DECLARE_RWSEM(sev_deactivate_lock);
 static DEFINE_MUTEX(sev_bitmap_lock);
@@ -262,12 +269,24 @@ static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp,
 	if (data->vmsa_features & ~valid_vmsa_features)
 		return -EINVAL;
 
+	if (data->ghcb_version > GHCB_VERSION_MAX || (!es_active && data->ghcb_version))
+		return -EINVAL;
+
 	if (unlikely(sev->active))
 		return -EINVAL;
 
 	sev->active = true;
 	sev->es_active = es_active;
 	sev->vmsa_features = data->vmsa_features;
+	sev->ghcb_version = data->ghcb_version;
+
+	/*
+	 * Currently KVM supports the full range of mandatory features defined
+	 * by version 2 of the GHCB protocol, so default to that for SEV-ES
+	 * guests created via KVM_SEV_INIT2.
+	 */
+	if (sev->es_active && !sev->ghcb_version)
+		sev->ghcb_version = GHCB_VERSION_DEFAULT;
 
 	ret = sev_asid_new(sev);
 	if (ret)
@@ -301,13 +320,22 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
 	struct kvm_sev_init data = {
 		.vmsa_features = 0,
+		.ghcb_version = 0,
 	};
 	unsigned long vm_type;
 
 	if (kvm->arch.vm_type != KVM_X86_DEFAULT_VM)
 		return -EINVAL;
 
 	vm_type = (argp->id == KVM_SEV_INIT ? KVM_X86_SEV_VM : KVM_X86_SEV_ES_VM);
+
+	/*
+	 * KVM_SEV_ES_INIT has been deprecated by KVM_SEV_INIT2, so it will
+	 * continue to only ever support the minimal GHCB protocol version.
+	 */
+	if (vm_type == KVM_X86_SEV_ES_VM)
+		data.ghcb_version = GHCB_VERSION_MIN;
+
 	return __sev_guest_init(kvm, argp, &data, vm_type);
 }
 
@@ -2697,6 +2725,8 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 	case SVM_VMGEXIT_AP_HLT_LOOP:
 	case SVM_VMGEXIT_AP_JUMP_TABLE:
 	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
+	case SVM_VMGEXIT_HV_FEATURES:
+	case SVM_VMGEXIT_TERM_REQUEST:
 		break;
 	default:
 		reason = GHCB_ERR_INVALID_EVENT;
@@ -2727,6 +2757,9 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 
 void sev_es_unmap_ghcb(struct vcpu_svm *svm)
 {
+	/* Clear any indication that the vCPU is in a type of AP Reset Hold */
+	svm->sev_es.ap_reset_hold_type = AP_RESET_HOLD_NONE;
+
 	if (!svm->sev_es.ghcb)
 		return;
 
@@ -2886,6 +2919,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	struct kvm_vcpu *vcpu = &svm->vcpu;
+	struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info;
 	u64 ghcb_info;
 	int ret = 1;
 
@@ -2896,7 +2930,7 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 
 	switch (ghcb_info) {
 	case GHCB_MSR_SEV_INFO_REQ:
-		set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX,
+		set_ghcb_msr(svm, GHCB_MSR_SEV_INFO((__u64)sev->ghcb_version,
 						    GHCB_VERSION_MIN,
 						    sev_enc_bit));
 		break;
@@ -2938,6 +2972,28 @@ static int sev_handle_vmgexit_msr_protocol(struct vcpu_svm *svm)
 				  GHCB_MSR_INFO_POS);
 		break;
 	}
+	case GHCB_MSR_AP_RESET_HOLD_REQ:
+		svm->sev_es.ap_reset_hold_type = AP_RESET_HOLD_MSR_PROTO;
+		ret = kvm_emulate_ap_reset_hold(&svm->vcpu);
+
+		/*
+		 * Preset the result to a non-SIPI return and then only set
+		 * the result to non-zero when delivering a SIPI.
+		 */
+		set_ghcb_msr_bits(svm, 0,
+				  GHCB_MSR_AP_RESET_HOLD_RESULT_MASK,
+				  GHCB_MSR_AP_RESET_HOLD_RESULT_POS);
+
+		set_ghcb_msr_bits(svm, GHCB_MSR_AP_RESET_HOLD_RESP,
+				  GHCB_MSR_INFO_MASK,
+				  GHCB_MSR_INFO_POS);
+		break;
+	case GHCB_MSR_HV_FT_REQ:
+		set_ghcb_msr_bits(svm, GHCB_HV_FT_SUPPORTED,
+				  GHCB_MSR_HV_FT_MASK, GHCB_MSR_HV_FT_POS);
+		set_ghcb_msr_bits(svm, GHCB_MSR_HV_FT_RESP,
+				  GHCB_MSR_INFO_MASK, GHCB_MSR_INFO_POS);
+		break;
 	case GHCB_MSR_TERM_REQ: {
 		u64 reason_set, reason_code;
 
@@ -3037,6 +3093,7 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 		ret = 1;
 		break;
 	case SVM_VMGEXIT_AP_HLT_LOOP:
+		svm->sev_es.ap_reset_hold_type = AP_RESET_HOLD_NAE_EVENT;
 		ret = kvm_emulate_ap_reset_hold(vcpu);
 		break;
 	case SVM_VMGEXIT_AP_JUMP_TABLE: {
@@ -3061,6 +3118,19 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 		ret = 1;
 		break;
 	}
+	case SVM_VMGEXIT_HV_FEATURES:
+		ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_HV_FT_SUPPORTED);
+
+		ret = 1;
+		break;
+	case SVM_VMGEXIT_TERM_REQUEST:
+		pr_info("SEV-ES guest requested termination: reason %#llx info %#llx\n",
+			control->exit_info_1, control->exit_info_2);
+		vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+		vcpu->run->system_event.type = KVM_SYSTEM_EVENT_SEV_TERM;
+		vcpu->run->system_event.ndata = 1;
+		vcpu->run->system_event.data[0] = control->ghcb_gpa;
+		break;
 	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
 		vcpu_unimpl(vcpu,
 			    "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
@@ -3221,11 +3291,14 @@ void sev_init_vmcb(struct vcpu_svm *svm)
 
 void sev_es_vcpu_reset(struct vcpu_svm *svm)
 {
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info;
+
 	/*
 	 * Set the GHCB MSR value as per the GHCB specification when emulating
 	 * vCPU RESET for an SEV-ES guest.
 	 */
-	set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX,
+	set_ghcb_msr(svm, GHCB_MSR_SEV_INFO((__u64)sev->ghcb_version,
 					    GHCB_VERSION_MIN,
 					    sev_enc_bit));
 }
@@ -3280,15 +3353,31 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
 		return;
 	}
 
-	/*
-	 * Subsequent SIPI: Return from an AP Reset Hold VMGEXIT, where
-	 * the guest will set the CS and RIP. Set SW_EXIT_INFO_2 to a
-	 * non-zero value.
-	 */
-	if (!svm->sev_es.ghcb)
-		return;
+	/* Subsequent SIPI */
+	switch (svm->sev_es.ap_reset_hold_type) {
+	case AP_RESET_HOLD_NAE_EVENT:
+		/*
+		 * Return from an AP Reset Hold VMGEXIT, where the guest will
+		 * set the CS and RIP. Set SW_EXIT_INFO_2 to a non-zero value.
+		 */
+		ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1);
+		break;
+	case AP_RESET_HOLD_MSR_PROTO:
+		/*
+		 * Return from an AP Reset Hold VMGEXIT, where the guest will
+		 * set the CS and RIP. Set GHCB data field to a non-zero value.
+		 */
+		set_ghcb_msr_bits(svm, 1,
+				  GHCB_MSR_AP_RESET_HOLD_RESULT_MASK,
+				  GHCB_MSR_AP_RESET_HOLD_RESULT_POS);
 
-	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1);
+		set_ghcb_msr_bits(svm, GHCB_MSR_AP_RESET_HOLD_RESP,
+				  GHCB_MSR_INFO_MASK,
+				  GHCB_MSR_INFO_POS);
+		break;
+	default:
+		break;
+	}
 }
 
 struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu)

arch/x86/kvm/svm/svm.h

@@ -87,6 +87,7 @@ struct kvm_sev_info {
 	struct list_head regions_list;  /* List of registered regions */
 	u64 ap_jump_table;	/* SEV-ES AP Jump Table address */
 	u64 vmsa_features;
+	u16 ghcb_version;	/* Highest guest GHCB protocol version allowed */
 	struct kvm *enc_context_owner; /* Owner of copied encryption context */
 	struct list_head mirror_vms; /* List of VMs mirroring */
 	struct list_head mirror_entry; /* Use as a list entry of mirrors */
@@ -199,6 +200,7 @@ struct vcpu_sev_es_state {
 	u8 valid_bitmap[16];
 	struct kvm_host_map ghcb_map;
 	bool received_first_sipi;
+	unsigned int ap_reset_hold_type;
 
 	/* SEV-ES scratch area support */
 	u64 sw_scratch;