1 files changed, 297 insertions, 136 deletions

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 0c240ed04f96..ae0ac12382b9 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -6,11 +6,13 @@
  *
  * Copyright 2010 Red Hat, Inc. and/or its affiliates.
  */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kvm_types.h>
 #include <linux/kvm_host.h>
 #include <linux/kernel.h>
 #include <linux/highmem.h>
+#include <linux/psp.h>
 #include <linux/psp-sev.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
@@ -21,7 +23,9 @@
 #include <asm/pkru.h>
 #include <asm/trapnr.h>
 #include <asm/fpu/xcr.h>
+#include <asm/debugreg.h>
 
+#include "mmu.h"
 #include "x86.h"
 #include "svm.h"
 #include "svm_ops.h"
@@ -51,9 +55,14 @@ module_param_named(sev, sev_enabled, bool, 0444);
 /* enable/disable SEV-ES support */
 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;
+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 u8 sev_enc_bit;
@@ -195,7 +204,7 @@ static void sev_asid_free(struct kvm_sev_info *sev)
 	__set_bit(sev->asid, sev_reclaim_asid_bitmap);
 
 	for_each_possible_cpu(cpu) {
-		sd = per_cpu(svm_data, cpu);
+		sd = per_cpu_ptr(&svm_data, cpu);
 		sd->sev_vmcbs[sev->asid] = NULL;
 	}
 
@@ -237,6 +246,7 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle)
 static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
+	struct sev_platform_init_args init_args = {0};
 	int asid, ret;
 
 	if (kvm->created_vcpus)
@@ -253,7 +263,8 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 		goto e_no_asid;
 	sev->asid = asid;
 
-	ret = sev_platform_init(&argp->error);
+	init_args.probe = false;
+	ret = sev_platform_init(&init_args);
 	if (ret)
 		goto e_free;
 
@@ -265,6 +276,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	return 0;
 
 e_free:
+	argp->error = init_args.error;
 	sev_asid_free(sev);
 	sev->asid = 0;
 e_no_asid:
@@ -464,9 +476,9 @@ static void sev_clflush_pages(struct page *pages[], unsigned long npages)
 		return;
 
 	for (i = 0; i < npages; i++) {
-		page_virtual = kmap_atomic(pages[i]);
+		page_virtual = kmap_local_page(pages[i]);
 		clflush_cache_range(page_virtual, PAGE_SIZE);
-		kunmap_atomic(page_virtual);
+		kunmap_local(page_virtual);
 		cond_resched();
 	}
 }
@@ -603,6 +615,15 @@ 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");
+	}
+
+	pr_debug("Virtual Machine Save Area (VMSA):\n");
+	print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false);
+
 	return 0;
 }
 
@@ -613,6 +634,11 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
 	struct vcpu_svm *svm = to_svm(vcpu);
 	int ret;
 
+	if (vcpu->guest_debug) {
+		pr_warn_once("KVM_SET_GUEST_DEBUG for SEV-ES guest is not supported");
+		return -EINVAL;
+	}
+
 	/* Perform some pre-encryption checks against the VMSA */
 	ret = sev_es_sync_vmsa(svm);
 	if (ret)
@@ -808,7 +834,7 @@ static int __sev_dbg_decrypt_user(struct kvm *kvm, unsigned long paddr,
 	if (!IS_ALIGNED(dst_paddr, 16) ||
 	    !IS_ALIGNED(paddr,     16) ||
 	    !IS_ALIGNED(size,      16)) {
-		tpage = (void *)alloc_page(GFP_KERNEL | __GFP_ZERO);
+		tpage = (void *)alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
 		if (!tpage)
 			return -ENOMEM;
 
@@ -1289,7 +1315,7 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 
 	/* Check if we are crossing the page boundary */
 	offset = params.guest_uaddr & (PAGE_SIZE - 1);
-	if ((params.guest_len + offset > PAGE_SIZE))
+	if (params.guest_len > PAGE_SIZE || (params.guest_len + offset) > PAGE_SIZE)
 		return -EINVAL;
 
 	/* Pin guest memory */
@@ -1469,7 +1495,7 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 
 	/* Check if we are crossing the page boundary */
 	offset = params.guest_uaddr & (PAGE_SIZE - 1);
-	if ((params.guest_len + offset > PAGE_SIZE))
+	if (params.guest_len > PAGE_SIZE || (params.guest_len + offset) > PAGE_SIZE)
 		return -EINVAL;
 
 	hdr = psp_copy_user_blob(params.hdr_uaddr, params.hdr_len);
@@ -1606,38 +1632,35 @@ static int sev_lock_vcpus_for_migration(struct kvm *kvm,
 {
 	struct kvm_vcpu *vcpu;
 	unsigned long i, j;
-	bool first = true;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		if (mutex_lock_killable_nested(&vcpu->mutex, role))
 			goto out_unlock;
 
-		if (first) {
+#ifdef CONFIG_PROVE_LOCKING
+		if (!i)
 			/*
 			 * Reset the role to one that avoids colliding with
 			 * the role used for the first vcpu mutex.
 			 */
 			role = SEV_NR_MIGRATION_ROLES;
-			first = false;
-		} else {
+		else
 			mutex_release(&vcpu->mutex.dep_map, _THIS_IP_);
-		}
+#endif
 	}
 
 	return 0;
 
 out_unlock:
 
-	first = true;
 	kvm_for_each_vcpu(j, vcpu, kvm) {
 		if (i == j)
 			break;
 
-		if (first)
-			first = false;
-		else
+#ifdef CONFIG_PROVE_LOCKING
+		if (j)
 			mutex_acquire(&vcpu->mutex.dep_map, role, 0, _THIS_IP_);
-
+#endif
 
 		mutex_unlock(&vcpu->mutex);
 	}
@@ -1722,7 +1745,7 @@ static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm)
 		 * Note, the source is not required to have the same number of
 		 * vCPUs as the destination when migrating a vanilla SEV VM.
 		 */
-		src_vcpu = kvm_get_vcpu(dst_kvm, i);
+		src_vcpu = kvm_get_vcpu(src_kvm, i);
 		src_svm = to_svm(src_vcpu);
 
 		/*
@@ -1765,18 +1788,20 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 {
 	struct kvm_sev_info *dst_sev = &to_kvm_svm(kvm)->sev_info;
 	struct kvm_sev_info *src_sev, *cg_cleanup_sev;
-	struct file *source_kvm_file;
+	struct fd f = fdget(source_fd);
 	struct kvm *source_kvm;
 	bool charged = false;
 	int ret;
 
-	source_kvm_file = fget(source_fd);
-	if (!file_is_kvm(source_kvm_file)) {
+	if (!f.file)
+		return -EBADF;
+
+	if (!file_is_kvm(f.file)) {
 		ret = -EBADF;
 		goto out_fput;
 	}
 
-	source_kvm = source_kvm_file->private_data;
+	source_kvm = f.file->private_data;
 	ret = sev_lock_two_vms(kvm, source_kvm);
 	if (ret)
 		goto out_fput;
@@ -1826,8 +1851,7 @@ out_dst_cgroup:
 out_unlock:
 	sev_unlock_two_vms(kvm, source_kvm);
 out_fput:
-	if (source_kvm_file)
-		fput(source_kvm_file);
+	fdput(f);
 	return ret;
 }
 
@@ -1957,20 +1981,22 @@ int sev_mem_enc_register_region(struct kvm *kvm,
 		goto e_free;
 	}
 
-	region->uaddr = range->addr;
-	region->size = range->size;
-
-	list_add_tail(&region->list, &sev->regions_list);
-	mutex_unlock(&kvm->lock);
-
 	/*
 	 * The guest may change the memory encryption attribute from C=0 -> C=1
 	 * or vice versa for this memory range. Lets make sure caches are
 	 * flushed to ensure that guest data gets written into memory with
-	 * correct C-bit.
+	 * correct C-bit.  Note, this must be done before dropping kvm->lock,
+	 * as region and its array of pages can be freed by a different task
+	 * once kvm->lock is released.
 	 */
 	sev_clflush_pages(region->pages, region->npages);
 
+	region->uaddr = range->addr;
+	region->size = range->size;
+
+	list_add_tail(&region->list, &sev->regions_list);
+	mutex_unlock(&kvm->lock);
+
 	return ret;
 
 e_free:
@@ -2044,18 +2070,20 @@ failed:
 
 int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 {
-	struct file *source_kvm_file;
+	struct fd f = fdget(source_fd);
 	struct kvm *source_kvm;
 	struct kvm_sev_info *source_sev, *mirror_sev;
 	int ret;
 
-	source_kvm_file = fget(source_fd);
-	if (!file_is_kvm(source_kvm_file)) {
+	if (!f.file)
+		return -EBADF;
+
+	if (!file_is_kvm(f.file)) {
 		ret = -EBADF;
 		goto e_source_fput;
 	}
 
-	source_kvm = source_kvm_file->private_data;
+	source_kvm = f.file->private_data;
 	ret = sev_lock_two_vms(kvm, source_kvm);
 	if (ret)
 		goto e_source_fput;
@@ -2101,8 +2129,7 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd)
 e_unlock:
 	sev_unlock_two_vms(kvm, source_kvm);
 e_source_fput:
-	if (source_kvm_file)
-		fput(source_kvm_file);
+	fdput(f);
 	return ret;
 }
 
@@ -2166,16 +2193,19 @@ void __init sev_hardware_setup(void)
 	bool sev_es_supported = false;
 	bool sev_supported = false;
 
-	if (!sev_enabled || !npt_enabled)
+	if (!sev_enabled || !npt_enabled || !nrips)
 		goto out;
 
 	/*
 	 * SEV must obviously be supported in hardware.  Sanity check that the
 	 * CPU supports decode assists, which is mandatory for SEV guests to
-	 * support instruction emulation.
+	 * support instruction emulation.  Ditto for flushing by ASID, as SEV
+	 * guests are bound to a single ASID, i.e. KVM can't rotate to a new
+	 * ASID to effect a TLB flush.
 	 */
 	if (!boot_cpu_has(X86_FEATURE_SEV) ||
-	    WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS)))
+	    WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS)) ||
+	    WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_FLUSHBYASID)))
 		goto out;
 
 	/* Retrieve SEV CPUID information */
@@ -2211,16 +2241,22 @@ void __init sev_hardware_setup(void)
 	}
 
 	sev_asid_count = max_sev_asid - min_sev_asid + 1;
-	if (misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count))
-		goto out;
-
-	pr_info("SEV supported: %u ASIDs\n", sev_asid_count);
+	WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count));
 	sev_supported = true;
 
 	/* SEV-ES support requested? */
 	if (!sev_es_enabled)
 		goto out;
 
+	/*
+	 * SEV-ES requires MMIO caching as KVM doesn't have access to the guest
+	 * instruction stream, i.e. can't emulate in response to a #NPF and
+	 * instead relies on #NPF(RSVD) being reflected into the guest as #VC
+	 * (the guest can then do a #VMGEXIT to request MMIO emulation).
+	 */
+	if (!enable_mmio_caching)
+		goto out;
+
 	/* Does the CPU support SEV-ES? */
 	if (!boot_cpu_has(X86_FEATURE_SEV_ES))
 		goto out;
@@ -2230,15 +2266,24 @@ void __init sev_hardware_setup(void)
 		goto out;
 
 	sev_es_asid_count = min_sev_asid - 1;
-	if (misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count))
-		goto out;
-
-	pr_info("SEV-ES supported: %u ASIDs\n", sev_es_asid_count);
+	WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV_ES, sev_es_asid_count));
 	sev_es_supported = true;
 
 out:
+	if (boot_cpu_has(X86_FEATURE_SEV))
+		pr_info("SEV %s (ASIDs %u - %u)\n",
+			sev_supported ? "enabled" : "disabled",
+			min_sev_asid, max_sev_asid);
+	if (boot_cpu_has(X86_FEATURE_SEV_ES))
+		pr_info("SEV-ES %s (ASIDs %u - %u)\n",
+			sev_es_supported ? "enabled" : "disabled",
+			min_sev_asid > 1 ? 1 : 0, min_sev_asid - 1);
+
 	sev_enabled = sev_supported;
 	sev_es_enabled = sev_es_supported;
+	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
 }
 
@@ -2400,15 +2445,18 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
 	 */
 	memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs));
 
-	vcpu->arch.regs[VCPU_REGS_RAX] = ghcb_get_rax_if_valid(ghcb);
-	vcpu->arch.regs[VCPU_REGS_RBX] = ghcb_get_rbx_if_valid(ghcb);
-	vcpu->arch.regs[VCPU_REGS_RCX] = ghcb_get_rcx_if_valid(ghcb);
-	vcpu->arch.regs[VCPU_REGS_RDX] = ghcb_get_rdx_if_valid(ghcb);
-	vcpu->arch.regs[VCPU_REGS_RSI] = ghcb_get_rsi_if_valid(ghcb);
+	BUILD_BUG_ON(sizeof(svm->sev_es.valid_bitmap) != sizeof(ghcb->save.valid_bitmap));
+	memcpy(&svm->sev_es.valid_bitmap, &ghcb->save.valid_bitmap, sizeof(ghcb->save.valid_bitmap));
 
-	svm->vmcb->save.cpl = ghcb_get_cpl_if_valid(ghcb);
+	vcpu->arch.regs[VCPU_REGS_RAX] = kvm_ghcb_get_rax_if_valid(svm, ghcb);
+	vcpu->arch.regs[VCPU_REGS_RBX] = kvm_ghcb_get_rbx_if_valid(svm, ghcb);
+	vcpu->arch.regs[VCPU_REGS_RCX] = kvm_ghcb_get_rcx_if_valid(svm, ghcb);
+	vcpu->arch.regs[VCPU_REGS_RDX] = kvm_ghcb_get_rdx_if_valid(svm, ghcb);
+	vcpu->arch.regs[VCPU_REGS_RSI] = kvm_ghcb_get_rsi_if_valid(svm, ghcb);
 
-	if (ghcb_xcr0_is_valid(ghcb)) {
+	svm->vmcb->save.cpl = kvm_ghcb_get_cpl_if_valid(svm, ghcb);
+
+	if (kvm_ghcb_xcr0_is_valid(svm)) {
 		vcpu->arch.xcr0 = ghcb_get_xcr0(ghcb);
 		kvm_update_cpuid_runtime(vcpu);
 	}
@@ -2419,84 +2467,88 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
 	control->exit_code_hi = upper_32_bits(exit_code);
 	control->exit_info_1 = ghcb_get_sw_exit_info_1(ghcb);
 	control->exit_info_2 = ghcb_get_sw_exit_info_2(ghcb);
+	svm->sev_es.sw_scratch = kvm_ghcb_get_sw_scratch_if_valid(svm, ghcb);
 
 	/* Clear the valid entries fields */
 	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
 }
 
+static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control)
+{
+	return (((u64)control->exit_code_hi) << 32) | control->exit_code;
+}
+
 static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 {
-	struct kvm_vcpu *vcpu;
-	struct ghcb *ghcb;
+	struct vmcb_control_area *control = &svm->vmcb->control;
+	struct kvm_vcpu *vcpu = &svm->vcpu;
 	u64 exit_code;
 	u64 reason;
 
-	ghcb = svm->sev_es.ghcb;
-
 	/*
 	 * Retrieve the exit code now even though it may not be marked valid
 	 * as it could help with debugging.
 	 */
-	exit_code = ghcb_get_sw_exit_code(ghcb);
+	exit_code = kvm_ghcb_get_sw_exit_code(control);
 
 	/* Only GHCB Usage code 0 is supported */
-	if (ghcb->ghcb_usage) {
+	if (svm->sev_es.ghcb->ghcb_usage) {
 		reason = GHCB_ERR_INVALID_USAGE;
 		goto vmgexit_err;
 	}
 
 	reason = GHCB_ERR_MISSING_INPUT;
 
-	if (!ghcb_sw_exit_code_is_valid(ghcb) ||
-	    !ghcb_sw_exit_info_1_is_valid(ghcb) ||
-	    !ghcb_sw_exit_info_2_is_valid(ghcb))
+	if (!kvm_ghcb_sw_exit_code_is_valid(svm) ||
+	    !kvm_ghcb_sw_exit_info_1_is_valid(svm) ||
+	    !kvm_ghcb_sw_exit_info_2_is_valid(svm))
 		goto vmgexit_err;
 
-	switch (ghcb_get_sw_exit_code(ghcb)) {
+	switch (exit_code) {
 	case SVM_EXIT_READ_DR7:
 		break;
 	case SVM_EXIT_WRITE_DR7:
-		if (!ghcb_rax_is_valid(ghcb))
+		if (!kvm_ghcb_rax_is_valid(svm))
 			goto vmgexit_err;
 		break;
 	case SVM_EXIT_RDTSC:
 		break;
 	case SVM_EXIT_RDPMC:
-		if (!ghcb_rcx_is_valid(ghcb))
+		if (!kvm_ghcb_rcx_is_valid(svm))
 			goto vmgexit_err;
 		break;
 	case SVM_EXIT_CPUID:
-		if (!ghcb_rax_is_valid(ghcb) ||
-		    !ghcb_rcx_is_valid(ghcb))
+		if (!kvm_ghcb_rax_is_valid(svm) ||
+		    !kvm_ghcb_rcx_is_valid(svm))
 			goto vmgexit_err;
-		if (ghcb_get_rax(ghcb) == 0xd)
-			if (!ghcb_xcr0_is_valid(ghcb))
+		if (vcpu->arch.regs[VCPU_REGS_RAX] == 0xd)
+			if (!kvm_ghcb_xcr0_is_valid(svm))
 				goto vmgexit_err;
 		break;
 	case SVM_EXIT_INVD:
 		break;
 	case SVM_EXIT_IOIO:
-		if (ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_STR_MASK) {
-			if (!ghcb_sw_scratch_is_valid(ghcb))
+		if (control->exit_info_1 & SVM_IOIO_STR_MASK) {
+			if (!kvm_ghcb_sw_scratch_is_valid(svm))
 				goto vmgexit_err;
 		} else {
-			if (!(ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_TYPE_MASK))
-				if (!ghcb_rax_is_valid(ghcb))
+			if (!(control->exit_info_1 & SVM_IOIO_TYPE_MASK))
+				if (!kvm_ghcb_rax_is_valid(svm))
 					goto vmgexit_err;
 		}
 		break;
 	case SVM_EXIT_MSR:
-		if (!ghcb_rcx_is_valid(ghcb))
+		if (!kvm_ghcb_rcx_is_valid(svm))
 			goto vmgexit_err;
-		if (ghcb_get_sw_exit_info_1(ghcb)) {
-			if (!ghcb_rax_is_valid(ghcb) ||
-			    !ghcb_rdx_is_valid(ghcb))
+		if (control->exit_info_1) {
+			if (!kvm_ghcb_rax_is_valid(svm) ||
+			    !kvm_ghcb_rdx_is_valid(svm))
 				goto vmgexit_err;
 		}
 		break;
 	case SVM_EXIT_VMMCALL:
-		if (!ghcb_rax_is_valid(ghcb) ||
-		    !ghcb_cpl_is_valid(ghcb))
+		if (!kvm_ghcb_rax_is_valid(svm) ||
+		    !kvm_ghcb_cpl_is_valid(svm))
 			goto vmgexit_err;
 		break;
 	case SVM_EXIT_RDTSCP:
@@ -2504,19 +2556,19 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 	case SVM_EXIT_WBINVD:
 		break;
 	case SVM_EXIT_MONITOR:
-		if (!ghcb_rax_is_valid(ghcb) ||
-		    !ghcb_rcx_is_valid(ghcb) ||
-		    !ghcb_rdx_is_valid(ghcb))
+		if (!kvm_ghcb_rax_is_valid(svm) ||
+		    !kvm_ghcb_rcx_is_valid(svm) ||
+		    !kvm_ghcb_rdx_is_valid(svm))
 			goto vmgexit_err;
 		break;
 	case SVM_EXIT_MWAIT:
-		if (!ghcb_rax_is_valid(ghcb) ||
-		    !ghcb_rcx_is_valid(ghcb))
+		if (!kvm_ghcb_rax_is_valid(svm) ||
+		    !kvm_ghcb_rcx_is_valid(svm))
 			goto vmgexit_err;
 		break;
 	case SVM_VMGEXIT_MMIO_READ:
 	case SVM_VMGEXIT_MMIO_WRITE:
-		if (!ghcb_sw_scratch_is_valid(ghcb))
+		if (!kvm_ghcb_sw_scratch_is_valid(svm))
 			goto vmgexit_err;
 		break;
 	case SVM_VMGEXIT_NMI_COMPLETE:
@@ -2532,11 +2584,9 @@ static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
 	return 0;
 
 vmgexit_err:
-	vcpu = &svm->vcpu;
-
 	if (reason == GHCB_ERR_INVALID_USAGE) {
 		vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n",
-			    ghcb->ghcb_usage);
+			    svm->sev_es.ghcb->ghcb_usage);
 	} else if (reason == GHCB_ERR_INVALID_EVENT) {
 		vcpu_unimpl(vcpu, "vmgexit: exit code %#llx is not valid\n",
 			    exit_code);
@@ -2546,11 +2596,8 @@ vmgexit_err:
 		dump_ghcb(svm);
 	}
 
-	/* Clear the valid entries fields */
-	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
-
-	ghcb_set_sw_exit_info_1(ghcb, 2);
-	ghcb_set_sw_exit_info_2(ghcb, reason);
+	ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2);
+	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, reason);
 
 	/* Resume the guest to "return" the error code. */
 	return 1;
@@ -2569,7 +2616,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm)
 		 */
 		if (svm->sev_es.ghcb_sa_sync) {
 			kvm_write_guest(svm->vcpu.kvm,
-					ghcb_get_sw_scratch(svm->sev_es.ghcb),
+					svm->sev_es.sw_scratch,
 					svm->sev_es.ghcb_sa,
 					svm->sev_es.ghcb_sa_len);
 			svm->sev_es.ghcb_sa_sync = false;
@@ -2590,7 +2637,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm)
 
 void pre_sev_run(struct vcpu_svm *svm, int cpu)
 {
-	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
+	struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
 	int asid = sev_get_asid(svm->vcpu.kvm);
 
 	/* Assign the asid allocated with this SEV guest */
@@ -2615,12 +2662,11 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu)
 static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
-	struct ghcb *ghcb = svm->sev_es.ghcb;
 	u64 ghcb_scratch_beg, ghcb_scratch_end;
 	u64 scratch_gpa_beg, scratch_gpa_end;
 	void *scratch_va;
 
-	scratch_gpa_beg = ghcb_get_sw_scratch(ghcb);
+	scratch_gpa_beg = svm->sev_es.sw_scratch;
 	if (!scratch_gpa_beg) {
 		pr_err("vmgexit: scratch gpa not provided\n");
 		goto e_scratch;
@@ -2638,7 +2684,7 @@ static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 		ghcb_scratch_beg = control->ghcb_gpa +
 				   offsetof(struct ghcb, shared_buffer);
 		ghcb_scratch_end = control->ghcb_gpa +
-				   offsetof(struct ghcb, reserved_1);
+				   offsetof(struct ghcb, reserved_0xff0);
 
 		/*
 		 * If the scratch area begins within the GHCB, it must be
@@ -2691,8 +2737,8 @@ static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
 	return 0;
 
 e_scratch:
-	ghcb_set_sw_exit_info_1(ghcb, 2);
-	ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_SCRATCH_AREA);
+	ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 2);
+	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, GHCB_ERR_INVALID_SCRATCH_AREA);
 
 	return 1;
 }
@@ -2805,7 +2851,6 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	u64 ghcb_gpa, exit_code;
-	struct ghcb *ghcb;
 	int ret;
 
 	/* Validate the GHCB */
@@ -2830,20 +2875,18 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 	}
 
 	svm->sev_es.ghcb = svm->sev_es.ghcb_map.hva;
-	ghcb = svm->sev_es.ghcb_map.hva;
 
-	trace_kvm_vmgexit_enter(vcpu->vcpu_id, ghcb);
-
-	exit_code = ghcb_get_sw_exit_code(ghcb);
+	trace_kvm_vmgexit_enter(vcpu->vcpu_id, svm->sev_es.ghcb);
 
+	sev_es_sync_from_ghcb(svm);
 	ret = sev_es_validate_vmgexit(svm);
 	if (ret)
 		return ret;
 
-	sev_es_sync_from_ghcb(svm);
-	ghcb_set_sw_exit_info_1(ghcb, 0);
-	ghcb_set_sw_exit_info_2(ghcb, 0);
+	ghcb_set_sw_exit_info_1(svm->sev_es.ghcb, 0);
+	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 0);
 
+	exit_code = kvm_ghcb_get_sw_exit_code(control);
 	switch (exit_code) {
 	case SVM_VMGEXIT_MMIO_READ:
 		ret = setup_vmgexit_scratch(svm, true, control->exit_info_2);
@@ -2866,7 +2909,10 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 					    svm->sev_es.ghcb_sa);
 		break;
 	case SVM_VMGEXIT_NMI_COMPLETE:
-		ret = svm_invoke_exit_handler(vcpu, SVM_EXIT_IRET);
+		++vcpu->stat.nmi_window_exits;
+		svm->nmi_masked = false;
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+		ret = 1;
 		break;
 	case SVM_VMGEXIT_AP_HLT_LOOP:
 		ret = kvm_emulate_ap_reset_hold(vcpu);
@@ -2881,13 +2927,13 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
 			break;
 		case 1:
 			/* Get AP jump table address */
-			ghcb_set_sw_exit_info_2(ghcb, sev->ap_jump_table);
+			ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, sev->ap_jump_table);
 			break;
 		default:
 			pr_err("svm: vmgexit: unsupported AP jump table request - exit_info_1=%#llx\n",
 			       control->exit_info_1);
-			ghcb_set_sw_exit_info_1(ghcb, 2);
-			ghcb_set_sw_exit_info_2(ghcb, GHCB_ERR_INVALID_INPUT);
+			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;
@@ -2927,8 +2973,54 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
 				    count, in);
 }
 
+static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+
+	if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) {
+		bool v_tsc_aux = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) ||
+				 guest_cpuid_has(vcpu, X86_FEATURE_RDPID);
+
+		set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux);
+	}
+
+	/*
+	 * For SEV-ES, accesses to MSR_IA32_XSS should not be intercepted if
+	 * the host/guest supports its use.
+	 *
+	 * guest_can_use() checks a number of requirements on the host/guest to
+	 * ensure that MSR_IA32_XSS is available, but it might report true even
+	 * if X86_FEATURE_XSAVES isn't configured in the guest to ensure host
+	 * MSR_IA32_XSS is always properly restored. For SEV-ES, it is better
+	 * to further check that the guest CPUID actually supports
+	 * X86_FEATURE_XSAVES so that accesses to MSR_IA32_XSS by misbehaved
+	 * guests will still get intercepted and caught in the normal
+	 * kvm_emulate_rdmsr()/kvm_emulated_wrmsr() paths.
+	 */
+	if (guest_can_use(vcpu, X86_FEATURE_XSAVES) &&
+	    guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 1, 1);
+	else
+		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 0, 0);
+}
+
+void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	struct kvm_cpuid_entry2 *best;
+
+	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
+	best = kvm_find_cpuid_entry(vcpu, 0x8000001F);
+	if (best)
+		vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f));
+
+	if (sev_es_guest(svm->vcpu.kvm))
+		sev_es_vcpu_after_set_cpuid(svm);
+}
+
 static void sev_es_init_vmcb(struct vcpu_svm *svm)
 {
+	struct vmcb *vmcb = svm->vmcb01.ptr;
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 
 	svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE;
@@ -2937,9 +3029,12 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	/*
 	 * An SEV-ES guest requires a VMSA area that is a separate from the
 	 * VMCB page. Do not include the encryption mask on the VMSA physical
-	 * address since hardware will access it using the guest key.
+	 * address since hardware will access it using the guest key.  Note,
+	 * the VMSA will be NULL if this vCPU is the destination for intrahost
+	 * migration, and will be copied later.
 	 */
-	svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+	if (svm->sev_es.vmsa)
+		svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
 
 	/* Can't intercept CR register access, HV can't modify CR registers */
 	svm_clr_intercept(svm, INTERCEPT_CR0_READ);
@@ -2957,8 +3052,23 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	svm_set_intercept(svm, TRAP_CR4_WRITE);
 	svm_set_intercept(svm, TRAP_CR8_WRITE);
 
-	/* No support for enable_vmware_backdoor */
-	clr_exception_intercept(svm, GP_VECTOR);
+	vmcb->control.intercepts[INTERCEPT_DR] = 0;
+	if (!sev_es_debug_swap_enabled) {
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_READ);
+		vmcb_set_intercept(&vmcb->control, INTERCEPT_DR7_WRITE);
+		recalc_intercepts(svm);
+	} else {
+		/*
+		 * Disable #DB intercept iff DebugSwap is enabled.  KVM doesn't
+		 * allow debugging SEV-ES guests, and enables DebugSwap iff
+		 * NO_NESTED_DATA_BP is supported, so there's no reason to
+		 * intercept #DB when DebugSwap is enabled.  For simplicity
+		 * with respect to guest debug, intercept #DB for other VMs
+		 * even if NO_NESTED_DATA_BP is supported, i.e. even if the
+		 * guest can't DoS the CPU with infinite #DB vectoring.
+		 */
+		clr_exception_intercept(svm, DB_VECTOR);
+	}
 
 	/* Can't intercept XSETBV, HV can't modify XCR0 directly */
 	svm_clr_intercept(svm, INTERCEPT_XSETBV);
@@ -2970,14 +3080,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
-
-	if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) &&
-	    (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP) ||
-	     guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDPID))) {
-		set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, 1, 1);
-		if (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP))
-			svm_clr_intercept(svm, INTERCEPT_RDTSCP);
-	}
 }
 
 void sev_init_vmcb(struct vcpu_svm *svm)
@@ -2985,6 +3087,12 @@ void sev_init_vmcb(struct vcpu_svm *svm)
 	svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ENABLE;
 	clr_exception_intercept(svm, UD_VECTOR);
 
+	/*
+	 * Don't intercept #GP for SEV guests, e.g. for the VMware backdoor, as
+	 * KVM can't decrypt guest memory to decode the faulting instruction.
+	 */
+	clr_exception_intercept(svm, GP_VECTOR);
+
 	if (sev_es_guest(svm->vcpu.kvm))
 		sev_es_init_vmcb(svm);
 }
@@ -3003,20 +3111,41 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm)
 void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa)
 {
 	/*
-	 * As an SEV-ES guest, hardware will restore the host state on VMEXIT,
-	 * of which one step is to perform a VMLOAD.  KVM performs the
-	 * corresponding VMSAVE in svm_prepare_guest_switch for both
-	 * traditional and SEV-ES guests.
+	 * All host state for SEV-ES guests is categorized into three swap types
+	 * based on how it is handled by hardware during a world switch:
+	 *
+	 * A: VMRUN:   Host state saved in host save area
+	 *    VMEXIT:  Host state loaded from host save area
+	 *
+	 * B: VMRUN:   Host state _NOT_ saved in host save area
+	 *    VMEXIT:  Host state loaded from host save area
+	 *
+	 * C: VMRUN:   Host state _NOT_ saved in host save area
+	 *    VMEXIT:  Host state initialized to default(reset) values
+	 *
+	 * Manually save type-B state, i.e. state that is loaded by VMEXIT but
+	 * isn't saved by VMRUN, that isn't already saved by VMSAVE (performed
+	 * by common SVM code).
 	 */
-
-	/* XCR0 is restored on VMEXIT, save the current host value */
 	hostsa->xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
-
-	/* PKRU is restored on VMEXIT, save the current host value */
 	hostsa->pkru = read_pkru();
-
-	/* MSR_IA32_XSS is restored on VMEXIT, save the currnet host value */
 	hostsa->xss = host_xss;
+
+	/*
+	 * If DebugSwap is enabled, debug registers are loaded but NOT saved by
+	 * 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) {
+		hostsa->dr0 = native_get_debugreg(0);
+		hostsa->dr1 = native_get_debugreg(1);
+		hostsa->dr2 = native_get_debugreg(2);
+		hostsa->dr3 = native_get_debugreg(3);
+		hostsa->dr0_addr_mask = amd_get_dr_addr_mask(0);
+		hostsa->dr1_addr_mask = amd_get_dr_addr_mask(1);
+		hostsa->dr2_addr_mask = amd_get_dr_addr_mask(2);
+		hostsa->dr3_addr_mask = amd_get_dr_addr_mask(3);
+	}
 }
 
 void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
@@ -3039,3 +3168,35 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector)
 
 	ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1);
 }
+
+struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu)
+{
+	unsigned long pfn;
+	struct page *p;
+
+	if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+		return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+
+	/*
+	 * Allocate an SNP-safe page to workaround the SNP erratum where
+	 * the CPU will incorrectly signal an RMP violation #PF if a
+	 * hugepage (2MB or 1GB) collides with the RMP entry of a
+	 * 2MB-aligned VMCB, VMSA, or AVIC backing page.
+	 *
+	 * Allocate one extra page, choose a page which is not
+	 * 2MB-aligned, and free the other.
+	 */
+	p = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1);
+	if (!p)
+		return NULL;
+
+	split_page(p, 1);
+
+	pfn = page_to_pfn(p);
+	if (IS_ALIGNED(pfn, PTRS_PER_PMD))
+		__free_page(p++);
+	else
+		__free_page(p + 1);
+
+	return p;
+}