1 files changed, 151 insertions, 39 deletions

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index e5a4d9b0e79f..022d92fb4b85 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -23,6 +23,7 @@
 #include <asm/pkru.h>
 #include <asm/trapnr.h>
 #include <asm/fpu/xcr.h>
+#include <asm/fpu/xstate.h>
 #include <asm/debugreg.h>
 
 #include "mmu.h"
@@ -32,22 +33,9 @@
 #include "cpuid.h"
 #include "trace.h"
 
-#ifndef CONFIG_KVM_AMD_SEV
-/*
- * When this config is not defined, SEV feature is not supported and APIs in
- * this file are not used but this file still gets compiled into the KVM AMD
- * module.
- *
- * We will not have MISC_CG_RES_SEV and MISC_CG_RES_SEV_ES entries in the enum
- * misc_res_type {} defined in linux/misc_cgroup.h.
- *
- * Below macros allow compilation to succeed.
- */
-#define MISC_CG_RES_SEV MISC_CG_RES_TYPES
-#define MISC_CG_RES_SEV_ES MISC_CG_RES_TYPES
-#endif
+#define GHCB_VERSION_MAX	1ULL
+#define GHCB_VERSION_MIN	1ULL
 
-#ifdef CONFIG_KVM_AMD_SEV
 /* enable/disable SEV support */
 static bool sev_enabled = true;
 module_param_named(sev, sev_enabled, bool, 0444);
@@ -57,13 +45,9 @@ static bool sev_es_enabled = true;
 module_param_named(sev_es, sev_es_enabled, bool, 0444);
 
 /* enable/disable SEV-ES DebugSwap support */
-static bool sev_es_debug_swap_enabled = false;
+static bool sev_es_debug_swap_enabled = true;
 module_param_named(debug_swap, sev_es_debug_swap_enabled, bool, 0444);
-#else
-#define sev_enabled false
-#define sev_es_enabled false
-#define sev_es_debug_swap_enabled false
-#endif /* CONFIG_KVM_AMD_SEV */
+static u64 sev_supported_vmsa_features;
 
 static u8 sev_enc_bit;
 static DECLARE_RWSEM(sev_deactivate_lock);
@@ -113,7 +97,15 @@ static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid)
 
 static inline bool is_mirroring_enc_context(struct kvm *kvm)
 {
-	return !!to_kvm_svm(kvm)->sev_info.enc_context_owner;
+	return !!to_kvm_sev_info(kvm)->enc_context_owner;
+}
+
+static bool sev_vcpu_has_debug_swap(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info;
+
+	return sev->vmsa_features & SVM_SEV_FEAT_DEBUG_SWAP;
 }
 
 /* Must be called with the sev_bitmap_lock held */
@@ -251,20 +243,32 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
 	sev_decommission(handle);
 }
 
-static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
+static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp,
+			    struct kvm_sev_init *data,
+			    unsigned long vm_type)
 {
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct sev_platform_init_args init_args = {0};
+	bool es_active = vm_type != KVM_X86_SEV_VM;
+	u64 valid_vmsa_features = es_active ? sev_supported_vmsa_features : 0;
 	int ret;
 
 	if (kvm->created_vcpus)
 		return -EINVAL;
 
+	if (data->flags)
+		return -EINVAL;
+
+	if (data->vmsa_features & ~valid_vmsa_features)
+		return -EINVAL;
+
 	if (unlikely(sev->active))
 		return -EINVAL;
 
 	sev->active = true;
-	sev->es_active = argp->id == KVM_SEV_ES_INIT;
+	sev->es_active = es_active;
+	sev->vmsa_features = data->vmsa_features;
+
 	ret = sev_asid_new(sev);
 	if (ret)
 		goto e_no_asid;
@@ -276,6 +280,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 
 	INIT_LIST_HEAD(&sev->regions_list);
 	INIT_LIST_HEAD(&sev->mirror_vms);
+	sev->need_init = false;
 
 	kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_SEV);
 
@@ -286,11 +291,44 @@ e_free:
 	sev_asid_free(sev);
 	sev->asid = 0;
 e_no_asid:
+	sev->vmsa_features = 0;
 	sev->es_active = false;
 	sev->active = false;
 	return ret;
 }
 
+static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	struct kvm_sev_init data = {
+		.vmsa_features = 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);
+	return __sev_guest_init(kvm, argp, &data, vm_type);
+}
+
+static int sev_guest_init2(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct kvm_sev_init data;
+
+	if (!sev->need_init)
+		return -EINVAL;
+
+	if (kvm->arch.vm_type != KVM_X86_SEV_VM &&
+	    kvm->arch.vm_type != KVM_X86_SEV_ES_VM)
+		return -EINVAL;
+
+	if (copy_from_user(&data, u64_to_user_ptr(argp->data), sizeof(data)))
+		return -EFAULT;
+
+	return __sev_guest_init(kvm, argp, &data, kvm->arch.vm_type);
+}
+
 static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error)
 {
 	unsigned int asid = sev_get_asid(kvm);
@@ -580,7 +618,13 @@ e_unpin:
 
 static int sev_es_sync_vmsa(struct vcpu_svm *svm)
 {
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info;
 	struct sev_es_save_area *save = svm->sev_es.vmsa;
+	struct xregs_state *xsave;
+	const u8 *s;
+	u8 *d;
+	int i;
 
 	/* Check some debug related fields before encrypting the VMSA */
 	if (svm->vcpu.guest_debug || (svm->vmcb->save.dr7 & ~DR7_FIXED_1))
@@ -621,10 +665,44 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm)
 	save->xss  = svm->vcpu.arch.ia32_xss;
 	save->dr6  = svm->vcpu.arch.dr6;
 
-	if (sev_es_debug_swap_enabled) {
-		save->sev_features |= SVM_SEV_FEAT_DEBUG_SWAP;
-		pr_warn_once("Enabling DebugSwap with KVM_SEV_ES_INIT. "
-			     "This will not work starting with Linux 6.10\n");
+	save->sev_features = sev->vmsa_features;
+
+	/*
+	 * Skip FPU and AVX setup with KVM_SEV_ES_INIT to avoid
+	 * breaking older measurements.
+	 */
+	if (vcpu->kvm->arch.vm_type != KVM_X86_DEFAULT_VM) {
+		xsave = &vcpu->arch.guest_fpu.fpstate->regs.xsave;
+		save->x87_dp = xsave->i387.rdp;
+		save->mxcsr = xsave->i387.mxcsr;
+		save->x87_ftw = xsave->i387.twd;
+		save->x87_fsw = xsave->i387.swd;
+		save->x87_fcw = xsave->i387.cwd;
+		save->x87_fop = xsave->i387.fop;
+		save->x87_ds = 0;
+		save->x87_cs = 0;
+		save->x87_rip = xsave->i387.rip;
+
+		for (i = 0; i < 8; i++) {
+			/*
+			 * The format of the x87 save area is undocumented and
+			 * definitely not what you would expect.  It consists of
+			 * an 8*8 bytes area with bytes 0-7, and an 8*2 bytes
+			 * area with bytes 8-9 of each register.
+			 */
+			d = save->fpreg_x87 + i * 8;
+			s = ((u8 *)xsave->i387.st_space) + i * 16;
+			memcpy(d, s, 8);
+			save->fpreg_x87[64 + i * 2] = s[8];
+			save->fpreg_x87[64 + i * 2 + 1] = s[9];
+		}
+		memcpy(save->fpreg_xmm, xsave->i387.xmm_space, 256);
+
+		s = get_xsave_addr(xsave, XFEATURE_YMM);
+		if (s)
+			memcpy(save->fpreg_ymm, s, 256);
+		else
+			memset(save->fpreg_ymm, 0, 256);
 	}
 
 	pr_debug("Virtual Machine Save Area (VMSA):\n");
@@ -658,13 +736,20 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
 	clflush_cache_range(svm->sev_es.vmsa, PAGE_SIZE);
 
 	vmsa.reserved = 0;
-	vmsa.handle = to_kvm_svm(kvm)->sev_info.handle;
+	vmsa.handle = to_kvm_sev_info(kvm)->handle;
 	vmsa.address = __sme_pa(svm->sev_es.vmsa);
 	vmsa.len = PAGE_SIZE;
 	ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
 	if (ret)
 	  return ret;
 
+	/*
+	 * SEV-ES guests maintain an encrypted version of their FPU
+	 * state which is restored and saved on VMRUN and VMEXIT.
+	 * Mark vcpu->arch.guest_fpu->fpstate as scratch so it won't
+	 * do xsave/xrstor on it.
+	 */
+	fpstate_set_confidential(&vcpu->arch.guest_fpu);
 	vcpu->arch.guest_state_protected = true;
 	return 0;
 }
@@ -1705,6 +1790,7 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm)
 	dst->pages_locked = src->pages_locked;
 	dst->enc_context_owner = src->enc_context_owner;
 	dst->es_active = src->es_active;
+	dst->vmsa_features = src->vmsa_features;
 
 	src->asid = 0;
 	src->active = false;
@@ -1812,7 +1898,8 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 	if (ret)
 		goto out_fput;
 
-	if (sev_guest(kvm) || !sev_guest(source_kvm)) {
+	if (kvm->arch.vm_type != source_kvm->arch.vm_type ||
+	    sev_guest(kvm) || !sev_guest(source_kvm)) {
 		ret = -EINVAL;
 		goto out_unlock;
 	}
@@ -1861,6 +1948,21 @@ out_fput:
 	return ret;
 }
 
+int sev_dev_get_attr(u32 group, u64 attr, u64 *val)
+{
+	if (group != KVM_X86_GRP_SEV)
+		return -ENXIO;
+
+	switch (attr) {
+	case KVM_X86_SEV_VMSA_FEATURES:
+		*val = sev_supported_vmsa_features;
+		return 0;
+
+	default:
+		return -ENXIO;
+	}
+}
+
 int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_sev_cmd sev_cmd;
@@ -1894,6 +1996,9 @@ int sev_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
 	case KVM_SEV_INIT:
 		r = sev_guest_init(kvm, &sev_cmd);
 		break;
+	case KVM_SEV_INIT2:
+		r = sev_guest_init2(kvm, &sev_cmd);
+		break;
 	case KVM_SEV_LAUNCH_START:
 		r = sev_launch_start(kvm, &sev_cmd);
 		break;
@@ -2121,6 +2226,7 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 	mirror_sev->asid = source_sev->asid;
 	mirror_sev->fd = source_sev->fd;
 	mirror_sev->es_active = source_sev->es_active;
+	mirror_sev->need_init = false;
 	mirror_sev->handle = source_sev->handle;
 	INIT_LIST_HEAD(&mirror_sev->regions_list);
 	INIT_LIST_HEAD(&mirror_sev->mirror_vms);
@@ -2186,15 +2292,18 @@ void sev_vm_destroy(struct kvm *kvm)
 
 void __init sev_set_cpu_caps(void)
 {
-	if (!sev_enabled)
-		kvm_cpu_cap_clear(X86_FEATURE_SEV);
-	if (!sev_es_enabled)
-		kvm_cpu_cap_clear(X86_FEATURE_SEV_ES);
+	if (sev_enabled) {
+		kvm_cpu_cap_set(X86_FEATURE_SEV);
+		kvm_caps.supported_vm_types |= BIT(KVM_X86_SEV_VM);
+	}
+	if (sev_es_enabled) {
+		kvm_cpu_cap_set(X86_FEATURE_SEV_ES);
+		kvm_caps.supported_vm_types |= BIT(KVM_X86_SEV_ES_VM);
+	}
 }
 
 void __init sev_hardware_setup(void)
 {
-#ifdef CONFIG_KVM_AMD_SEV
 	unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count;
 	bool sev_es_supported = false;
 	bool sev_supported = false;
@@ -2294,7 +2403,10 @@ out:
 	if (!sev_es_enabled || !cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP) ||
 	    !cpu_feature_enabled(X86_FEATURE_NO_NESTED_DATA_BP))
 		sev_es_debug_swap_enabled = false;
-#endif
+
+	sev_supported_vmsa_features = 0;
+	if (sev_es_debug_swap_enabled)
+		sev_supported_vmsa_features |= SVM_SEV_FEAT_DEBUG_SWAP;
 }
 
 void sev_hardware_unsetup(void)
@@ -3063,7 +3175,7 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	svm_set_intercept(svm, TRAP_CR8_WRITE);
 
 	vmcb->control.intercepts[INTERCEPT_DR] = 0;
-	if (!sev_es_debug_swap_enabled) {
+	if (!sev_vcpu_has_debug_swap(svm)) {
 		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
 		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
 		recalc_intercepts(svm);
@@ -3118,7 +3230,7 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm)
 					    sev_enc_bit));
 }
 
-void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa)
+void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa)
 {
 	/*
 	 * All host state for SEV-ES guests is categorized into three swap types
@@ -3146,7 +3258,7 @@ void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa)
 	 * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU both
 	 * saves and loads debug registers (Type-A).
 	 */
-	if (sev_es_debug_swap_enabled) {
+	if (sev_vcpu_has_debug_swap(svm)) {
 		hostsa->dr0 = native_get_debugreg(0);
 		hostsa->dr1 = native_get_debugreg(1);
 		hostsa->dr2 = native_get_debugreg(2);