1 files changed, 876 insertions, 39 deletions

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 566f4d18185b..9858d5ae9ddd 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -14,10 +14,20 @@
 #include <linux/psp-sev.h>
 #include <linux/pagemap.h>
 #include <linux/swap.h>
+#include <linux/processor.h>
+#include <linux/trace_events.h>
+#include <asm/fpu/internal.h>
+
+#include <asm/trapnr.h>
 
 #include "x86.h"
 #include "svm.h"
+#include "cpuid.h"
+#include "trace.h"
+
+#define __ex(x) __kvm_handle_fault_on_reboot(x)
 
+static u8 sev_enc_bit;
 static int sev_flush_asids(void);
 static DECLARE_RWSEM(sev_deactivate_lock);
 static DEFINE_MUTEX(sev_bitmap_lock);
@@ -25,7 +35,6 @@ unsigned int max_sev_asid;
 static unsigned int min_sev_asid;
 static unsigned long *sev_asid_bitmap;
 static unsigned long *sev_reclaim_asid_bitmap;
-#define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT)
 
 struct enc_region {
 	struct list_head list;
@@ -57,19 +66,19 @@ static int sev_flush_asids(void)
 }
 
 /* Must be called with the sev_bitmap_lock held */
-static bool __sev_recycle_asids(void)
+static bool __sev_recycle_asids(int min_asid, int max_asid)
 {
 	int pos;
 
 	/* Check if there are any ASIDs to reclaim before performing a flush */
-	pos = find_next_bit(sev_reclaim_asid_bitmap,
-			    max_sev_asid, min_sev_asid - 1);
-	if (pos >= max_sev_asid)
+	pos = find_next_bit(sev_reclaim_asid_bitmap, max_sev_asid, min_asid);
+	if (pos >= max_asid)
 		return false;
 
 	if (sev_flush_asids())
 		return false;
 
+	/* The flush process will flush all reclaimable SEV and SEV-ES ASIDs */
 	bitmap_xor(sev_asid_bitmap, sev_asid_bitmap, sev_reclaim_asid_bitmap,
 		   max_sev_asid);
 	bitmap_zero(sev_reclaim_asid_bitmap, max_sev_asid);
@@ -77,20 +86,23 @@ static bool __sev_recycle_asids(void)
 	return true;
 }
 
-static int sev_asid_new(void)
+static int sev_asid_new(struct kvm_sev_info *sev)
 {
+	int pos, min_asid, max_asid;
 	bool retry = true;
-	int pos;
 
 	mutex_lock(&sev_bitmap_lock);
 
 	/*
-	 * SEV-enabled guest must use asid from min_sev_asid to max_sev_asid.
+	 * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid.
+	 * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1.
 	 */
+	min_asid = sev->es_active ? 0 : min_sev_asid - 1;
+	max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid;
 again:
-	pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_sev_asid - 1);
-	if (pos >= max_sev_asid) {
-		if (retry && __sev_recycle_asids()) {
+	pos = find_next_zero_bit(sev_asid_bitmap, max_sev_asid, min_asid);
+	if (pos >= max_asid) {
+		if (retry && __sev_recycle_asids(min_asid, max_asid)) {
 			retry = false;
 			goto again;
 		}
@@ -172,7 +184,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
 	if (unlikely(sev->active))
 		return ret;
 
-	asid = sev_asid_new();
+	asid = sev_asid_new(sev);
 	if (asid < 0)
 		return ret;
 
@@ -191,6 +203,16 @@ e_free:
 	return ret;
 }
 
+static int sev_es_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp)
+{
+	if (!sev_es)
+		return -ENOTTY;
+
+	to_kvm_svm(kvm)->sev_info.es_active = true;
+
+	return sev_guest_init(kvm, argp);
+}
+
 static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error)
 {
 	struct sev_data_activate *data;
@@ -490,6 +512,96 @@ e_free:
 	return ret;
 }
 
+static int sev_es_sync_vmsa(struct vcpu_svm *svm)
+{
+	struct vmcb_save_area *save = &svm->vmcb->save;
+
+	/* Check some debug related fields before encrypting the VMSA */
+	if (svm->vcpu.guest_debug || (save->dr7 & ~DR7_FIXED_1))
+		return -EINVAL;
+
+	/* Sync registgers */
+	save->rax = svm->vcpu.arch.regs[VCPU_REGS_RAX];
+	save->rbx = svm->vcpu.arch.regs[VCPU_REGS_RBX];
+	save->rcx = svm->vcpu.arch.regs[VCPU_REGS_RCX];
+	save->rdx = svm->vcpu.arch.regs[VCPU_REGS_RDX];
+	save->rsp = svm->vcpu.arch.regs[VCPU_REGS_RSP];
+	save->rbp = svm->vcpu.arch.regs[VCPU_REGS_RBP];
+	save->rsi = svm->vcpu.arch.regs[VCPU_REGS_RSI];
+	save->rdi = svm->vcpu.arch.regs[VCPU_REGS_RDI];
+#ifdef CONFIG_X86_64
+	save->r8  = svm->vcpu.arch.regs[VCPU_REGS_R8];
+	save->r9  = svm->vcpu.arch.regs[VCPU_REGS_R9];
+	save->r10 = svm->vcpu.arch.regs[VCPU_REGS_R10];
+	save->r11 = svm->vcpu.arch.regs[VCPU_REGS_R11];
+	save->r12 = svm->vcpu.arch.regs[VCPU_REGS_R12];
+	save->r13 = svm->vcpu.arch.regs[VCPU_REGS_R13];
+	save->r14 = svm->vcpu.arch.regs[VCPU_REGS_R14];
+	save->r15 = svm->vcpu.arch.regs[VCPU_REGS_R15];
+#endif
+	save->rip = svm->vcpu.arch.regs[VCPU_REGS_RIP];
+
+	/* Sync some non-GPR registers before encrypting */
+	save->xcr0 = svm->vcpu.arch.xcr0;
+	save->pkru = svm->vcpu.arch.pkru;
+	save->xss  = svm->vcpu.arch.ia32_xss;
+
+	/*
+	 * SEV-ES will use a VMSA that is pointed to by the VMCB, not
+	 * the traditional VMSA that is part of the VMCB. Copy the
+	 * traditional VMSA as it has been built so far (in prep
+	 * for LAUNCH_UPDATE_VMSA) to be the initial SEV-ES state.
+	 */
+	memcpy(svm->vmsa, save, sizeof(*save));
+
+	return 0;
+}
+
+static int sev_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_launch_update_vmsa *vmsa;
+	int i, ret;
+
+	if (!sev_es_guest(kvm))
+		return -ENOTTY;
+
+	vmsa = kzalloc(sizeof(*vmsa), GFP_KERNEL);
+	if (!vmsa)
+		return -ENOMEM;
+
+	for (i = 0; i < kvm->created_vcpus; i++) {
+		struct vcpu_svm *svm = to_svm(kvm->vcpus[i]);
+
+		/* Perform some pre-encryption checks against the VMSA */
+		ret = sev_es_sync_vmsa(svm);
+		if (ret)
+			goto e_free;
+
+		/*
+		 * The LAUNCH_UPDATE_VMSA command will perform in-place
+		 * encryption of the VMSA memory content (i.e it will write
+		 * the same memory region with the guest's key), so invalidate
+		 * it first.
+		 */
+		clflush_cache_range(svm->vmsa, PAGE_SIZE);
+
+		vmsa->handle = sev->handle;
+		vmsa->address = __sme_pa(svm->vmsa);
+		vmsa->len = PAGE_SIZE;
+		ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, vmsa,
+				    &argp->error);
+		if (ret)
+			goto e_free;
+
+		svm->vcpu.arch.guest_state_protected = true;
+	}
+
+e_free:
+	kfree(vmsa);
+	return ret;
+}
+
 static int sev_launch_measure(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
 	void __user *measure = (void __user *)(uintptr_t)argp->data;
@@ -932,7 +1044,7 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 	struct kvm_sev_cmd sev_cmd;
 	int r;
 
-	if (!svm_sev_enabled())
+	if (!svm_sev_enabled() || !sev)
 		return -ENOTTY;
 
 	if (!argp)
@@ -947,12 +1059,18 @@ int svm_mem_enc_op(struct kvm *kvm, void __user *argp)
 	case KVM_SEV_INIT:
 		r = sev_guest_init(kvm, &sev_cmd);
 		break;
+	case KVM_SEV_ES_INIT:
+		r = sev_es_guest_init(kvm, &sev_cmd);
+		break;
 	case KVM_SEV_LAUNCH_START:
 		r = sev_launch_start(kvm, &sev_cmd);
 		break;
 	case KVM_SEV_LAUNCH_UPDATE_DATA:
 		r = sev_launch_update_data(kvm, &sev_cmd);
 		break;
+	case KVM_SEV_LAUNCH_UPDATE_VMSA:
+		r = sev_launch_update_vmsa(kvm, &sev_cmd);
+		break;
 	case KVM_SEV_LAUNCH_MEASURE:
 		r = sev_launch_measure(kvm, &sev_cmd);
 		break;
@@ -1125,49 +1243,61 @@ void sev_vm_destroy(struct kvm *kvm)
 	sev_asid_free(sev->asid);
 }
 
-int __init sev_hardware_setup(void)
+void __init sev_hardware_setup(void)
 {
-	struct sev_user_data_status *status;
-	int rc;
+	unsigned int eax, ebx, ecx, edx;
+	bool sev_es_supported = false;
+	bool sev_supported = false;
+
+	/* Does the CPU support SEV? */
+	if (!boot_cpu_has(X86_FEATURE_SEV))
+		goto out;
+
+	/* Retrieve SEV CPUID information */
+	cpuid(0x8000001f, &eax, &ebx, &ecx, &edx);
+
+	/* Set encryption bit location for SEV-ES guests */
+	sev_enc_bit = ebx & 0x3f;
 
 	/* Maximum number of encrypted guests supported simultaneously */
-	max_sev_asid = cpuid_ecx(0x8000001F);
+	max_sev_asid = ecx;
 
 	if (!svm_sev_enabled())
-		return 1;
+		goto out;
 
 	/* Minimum ASID value that should be used for SEV guest */
-	min_sev_asid = cpuid_edx(0x8000001F);
+	min_sev_asid = edx;
 
 	/* Initialize SEV ASID bitmaps */
 	sev_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
 	if (!sev_asid_bitmap)
-		return 1;
+		goto out;
 
 	sev_reclaim_asid_bitmap = bitmap_zalloc(max_sev_asid, GFP_KERNEL);
 	if (!sev_reclaim_asid_bitmap)
-		return 1;
+		goto out;
 
-	status = kmalloc(sizeof(*status), GFP_KERNEL);
-	if (!status)
-		return 1;
+	pr_info("SEV supported: %u ASIDs\n", max_sev_asid - min_sev_asid + 1);
+	sev_supported = true;
 
-	/*
-	 * Check SEV platform status.
-	 *
-	 * PLATFORM_STATUS can be called in any state, if we failed to query
-	 * the PLATFORM status then either PSP firmware does not support SEV
-	 * feature or SEV firmware is dead.
-	 */
-	rc = sev_platform_status(status, NULL);
-	if (rc)
-		goto err;
+	/* SEV-ES support requested? */
+	if (!sev_es)
+		goto out;
 
-	pr_info("SEV supported\n");
+	/* Does the CPU support SEV-ES? */
+	if (!boot_cpu_has(X86_FEATURE_SEV_ES))
+		goto out;
 
-err:
-	kfree(status);
-	return rc;
+	/* Has the system been allocated ASIDs for SEV-ES? */
+	if (min_sev_asid == 1)
+		goto out;
+
+	pr_info("SEV-ES supported: %u ASIDs\n", min_sev_asid - 1);
+	sev_es_supported = true;
+
+out:
+	sev = sev_supported;
+	sev_es = sev_es_supported;
 }
 
 void sev_hardware_teardown(void)
@@ -1181,13 +1311,329 @@ void sev_hardware_teardown(void)
 	sev_flush_asids();
 }
 
+/*
+ * Pages used by hardware to hold guest encrypted state must be flushed before
+ * returning them to the system.
+ */
+static void sev_flush_guest_memory(struct vcpu_svm *svm, void *va,
+				   unsigned long len)
+{
+	/*
+	 * If hardware enforced cache coherency for encrypted mappings of the
+	 * same physical page is supported, nothing to do.
+	 */
+	if (boot_cpu_has(X86_FEATURE_SME_COHERENT))
+		return;
+
+	/*
+	 * If the VM Page Flush MSR is supported, use it to flush the page
+	 * (using the page virtual address and the guest ASID).
+	 */
+	if (boot_cpu_has(X86_FEATURE_VM_PAGE_FLUSH)) {
+		struct kvm_sev_info *sev;
+		unsigned long va_start;
+		u64 start, stop;
+
+		/* Align start and stop to page boundaries. */
+		va_start = (unsigned long)va;
+		start = (u64)va_start & PAGE_MASK;
+		stop = PAGE_ALIGN((u64)va_start + len);
+
+		if (start < stop) {
+			sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info;
+
+			while (start < stop) {
+				wrmsrl(MSR_AMD64_VM_PAGE_FLUSH,
+				       start | sev->asid);
+
+				start += PAGE_SIZE;
+			}
+
+			return;
+		}
+
+		WARN(1, "Address overflow, using WBINVD\n");
+	}
+
+	/*
+	 * Hardware should always have one of the above features,
+	 * but if not, use WBINVD and issue a warning.
+	 */
+	WARN_ONCE(1, "Using WBINVD to flush guest memory\n");
+	wbinvd_on_all_cpus();
+}
+
+void sev_free_vcpu(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm;
+
+	if (!sev_es_guest(vcpu->kvm))
+		return;
+
+	svm = to_svm(vcpu);
+
+	if (vcpu->arch.guest_state_protected)
+		sev_flush_guest_memory(svm, svm->vmsa, PAGE_SIZE);
+	__free_page(virt_to_page(svm->vmsa));
+
+	if (svm->ghcb_sa_free)
+		kfree(svm->ghcb_sa);
+}
+
+static void dump_ghcb(struct vcpu_svm *svm)
+{
+	struct ghcb *ghcb = svm->ghcb;
+	unsigned int nbits;
+
+	/* Re-use the dump_invalid_vmcb module parameter */
+	if (!dump_invalid_vmcb) {
+		pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n");
+		return;
+	}
+
+	nbits = sizeof(ghcb->save.valid_bitmap) * 8;
+
+	pr_err("GHCB (GPA=%016llx):\n", svm->vmcb->control.ghcb_gpa);
+	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_code",
+	       ghcb->save.sw_exit_code, ghcb_sw_exit_code_is_valid(ghcb));
+	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_1",
+	       ghcb->save.sw_exit_info_1, ghcb_sw_exit_info_1_is_valid(ghcb));
+	pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_2",
+	       ghcb->save.sw_exit_info_2, ghcb_sw_exit_info_2_is_valid(ghcb));
+	pr_err("%-20s%016llx is_valid: %u\n", "sw_scratch",
+	       ghcb->save.sw_scratch, ghcb_sw_scratch_is_valid(ghcb));
+	pr_err("%-20s%*pb\n", "valid_bitmap", nbits, ghcb->save.valid_bitmap);
+}
+
+static void sev_es_sync_to_ghcb(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	struct ghcb *ghcb = svm->ghcb;
+
+	/*
+	 * The GHCB protocol so far allows for the following data
+	 * to be returned:
+	 *   GPRs RAX, RBX, RCX, RDX
+	 *
+	 * Copy their values to the GHCB if they are dirty.
+	 */
+	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RAX))
+		ghcb_set_rax(ghcb, vcpu->arch.regs[VCPU_REGS_RAX]);
+	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RBX))
+		ghcb_set_rbx(ghcb, vcpu->arch.regs[VCPU_REGS_RBX]);
+	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RCX))
+		ghcb_set_rcx(ghcb, vcpu->arch.regs[VCPU_REGS_RCX]);
+	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RDX))
+		ghcb_set_rdx(ghcb, vcpu->arch.regs[VCPU_REGS_RDX]);
+}
+
+static void sev_es_sync_from_ghcb(struct vcpu_svm *svm)
+{
+	struct vmcb_control_area *control = &svm->vmcb->control;
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	struct ghcb *ghcb = svm->ghcb;
+	u64 exit_code;
+
+	/*
+	 * The GHCB protocol so far allows for the following data
+	 * to be supplied:
+	 *   GPRs RAX, RBX, RCX, RDX
+	 *   XCR0
+	 *   CPL
+	 *
+	 * VMMCALL allows the guest to provide extra registers. KVM also
+	 * expects RSI for hypercalls, so include that, too.
+	 *
+	 * Copy their values to the appropriate location if supplied.
+	 */
+	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);
+
+	svm->vmcb->save.cpl = ghcb_get_cpl_if_valid(ghcb);
+
+	if (ghcb_xcr0_is_valid(ghcb)) {
+		vcpu->arch.xcr0 = ghcb_get_xcr0(ghcb);
+		kvm_update_cpuid_runtime(vcpu);
+	}
+
+	/* Copy the GHCB exit information into the VMCB fields */
+	exit_code = ghcb_get_sw_exit_code(ghcb);
+	control->exit_code = lower_32_bits(exit_code);
+	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);
+
+	/* Clear the valid entries fields */
+	memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
+}
+
+static int sev_es_validate_vmgexit(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu;
+	struct ghcb *ghcb;
+	u64 exit_code = 0;
+
+	ghcb = svm->ghcb;
+
+	/* Only GHCB Usage code 0 is supported */
+	if (ghcb->ghcb_usage)
+		goto vmgexit_err;
+
+	/*
+	 * Retrieve the exit code now even though is may not be marked valid
+	 * as it could help with debugging.
+	 */
+	exit_code = ghcb_get_sw_exit_code(ghcb);
+
+	if (!ghcb_sw_exit_code_is_valid(ghcb) ||
+	    !ghcb_sw_exit_info_1_is_valid(ghcb) ||
+	    !ghcb_sw_exit_info_2_is_valid(ghcb))
+		goto vmgexit_err;
+
+	switch (ghcb_get_sw_exit_code(ghcb)) {
+	case SVM_EXIT_READ_DR7:
+		break;
+	case SVM_EXIT_WRITE_DR7:
+		if (!ghcb_rax_is_valid(ghcb))
+			goto vmgexit_err;
+		break;
+	case SVM_EXIT_RDTSC:
+		break;
+	case SVM_EXIT_RDPMC:
+		if (!ghcb_rcx_is_valid(ghcb))
+			goto vmgexit_err;
+		break;
+	case SVM_EXIT_CPUID:
+		if (!ghcb_rax_is_valid(ghcb) ||
+		    !ghcb_rcx_is_valid(ghcb))
+			goto vmgexit_err;
+		if (ghcb_get_rax(ghcb) == 0xd)
+			if (!ghcb_xcr0_is_valid(ghcb))
+				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))
+				goto vmgexit_err;
+		} else {
+			if (!(ghcb_get_sw_exit_info_1(ghcb) & SVM_IOIO_TYPE_MASK))
+				if (!ghcb_rax_is_valid(ghcb))
+					goto vmgexit_err;
+		}
+		break;
+	case SVM_EXIT_MSR:
+		if (!ghcb_rcx_is_valid(ghcb))
+			goto vmgexit_err;
+		if (ghcb_get_sw_exit_info_1(ghcb)) {
+			if (!ghcb_rax_is_valid(ghcb) ||
+			    !ghcb_rdx_is_valid(ghcb))
+				goto vmgexit_err;
+		}
+		break;
+	case SVM_EXIT_VMMCALL:
+		if (!ghcb_rax_is_valid(ghcb) ||
+		    !ghcb_cpl_is_valid(ghcb))
+			goto vmgexit_err;
+		break;
+	case SVM_EXIT_RDTSCP:
+		break;
+	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))
+			goto vmgexit_err;
+		break;
+	case SVM_EXIT_MWAIT:
+		if (!ghcb_rax_is_valid(ghcb) ||
+		    !ghcb_rcx_is_valid(ghcb))
+			goto vmgexit_err;
+		break;
+	case SVM_VMGEXIT_MMIO_READ:
+	case SVM_VMGEXIT_MMIO_WRITE:
+		if (!ghcb_sw_scratch_is_valid(ghcb))
+			goto vmgexit_err;
+		break;
+	case SVM_VMGEXIT_NMI_COMPLETE:
+	case SVM_VMGEXIT_AP_JUMP_TABLE:
+	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
+		break;
+	default:
+		goto vmgexit_err;
+	}
+
+	return 0;
+
+vmgexit_err:
+	vcpu = &svm->vcpu;
+
+	if (ghcb->ghcb_usage) {
+		vcpu_unimpl(vcpu, "vmgexit: ghcb usage %#x is not valid\n",
+			    ghcb->ghcb_usage);
+	} else {
+		vcpu_unimpl(vcpu, "vmgexit: exit reason %#llx is not valid\n",
+			    exit_code);
+		dump_ghcb(svm);
+	}
+
+	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
+	vcpu->run->internal.ndata = 2;
+	vcpu->run->internal.data[0] = exit_code;
+	vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu;
+
+	return -EINVAL;
+}
+
+static void pre_sev_es_run(struct vcpu_svm *svm)
+{
+	if (!svm->ghcb)
+		return;
+
+	if (svm->ghcb_sa_free) {
+		/*
+		 * The scratch area lives outside the GHCB, so there is a
+		 * buffer that, depending on the operation performed, may
+		 * need to be synced, then freed.
+		 */
+		if (svm->ghcb_sa_sync) {
+			kvm_write_guest(svm->vcpu.kvm,
+					ghcb_get_sw_scratch(svm->ghcb),
+					svm->ghcb_sa, svm->ghcb_sa_len);
+			svm->ghcb_sa_sync = false;
+		}
+
+		kfree(svm->ghcb_sa);
+		svm->ghcb_sa = NULL;
+		svm->ghcb_sa_free = false;
+	}
+
+	trace_kvm_vmgexit_exit(svm->vcpu.vcpu_id, svm->ghcb);
+
+	sev_es_sync_to_ghcb(svm);
+
+	kvm_vcpu_unmap(&svm->vcpu, &svm->ghcb_map, true);
+	svm->ghcb = NULL;
+}
+
 void pre_sev_run(struct vcpu_svm *svm, int cpu)
 {
 	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
 	int asid = sev_get_asid(svm->vcpu.kvm);
 
+	/* Perform any SEV-ES pre-run actions */
+	pre_sev_es_run(svm);
+
 	/* Assign the asid allocated with this SEV guest */
-	svm->vmcb->control.asid = asid;
+	svm->asid = asid;
 
 	/*
 	 * Flush guest TLB:
@@ -1203,3 +1649,394 @@ void pre_sev_run(struct vcpu_svm *svm, int cpu)
 	svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID;
 	vmcb_mark_dirty(svm->vmcb, VMCB_ASID);
 }
+
+#define GHCB_SCRATCH_AREA_LIMIT		(16ULL * PAGE_SIZE)
+static bool setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
+{
+	struct vmcb_control_area *control = &svm->vmcb->control;
+	struct ghcb *ghcb = svm->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);
+	if (!scratch_gpa_beg) {
+		pr_err("vmgexit: scratch gpa not provided\n");
+		return false;
+	}
+
+	scratch_gpa_end = scratch_gpa_beg + len;
+	if (scratch_gpa_end < scratch_gpa_beg) {
+		pr_err("vmgexit: scratch length (%#llx) not valid for scratch address (%#llx)\n",
+		       len, scratch_gpa_beg);
+		return false;
+	}
+
+	if ((scratch_gpa_beg & PAGE_MASK) == control->ghcb_gpa) {
+		/* Scratch area begins within GHCB */
+		ghcb_scratch_beg = control->ghcb_gpa +
+				   offsetof(struct ghcb, shared_buffer);
+		ghcb_scratch_end = control->ghcb_gpa +
+				   offsetof(struct ghcb, reserved_1);
+
+		/*
+		 * If the scratch area begins within the GHCB, it must be
+		 * completely contained in the GHCB shared buffer area.
+		 */
+		if (scratch_gpa_beg < ghcb_scratch_beg ||
+		    scratch_gpa_end > ghcb_scratch_end) {
+			pr_err("vmgexit: scratch area is outside of GHCB shared buffer area (%#llx - %#llx)\n",
+			       scratch_gpa_beg, scratch_gpa_end);
+			return false;
+		}
+
+		scratch_va = (void *)svm->ghcb;
+		scratch_va += (scratch_gpa_beg - control->ghcb_gpa);
+	} else {
+		/*
+		 * The guest memory must be read into a kernel buffer, so
+		 * limit the size
+		 */
+		if (len > GHCB_SCRATCH_AREA_LIMIT) {
+			pr_err("vmgexit: scratch area exceeds KVM limits (%#llx requested, %#llx limit)\n",
+			       len, GHCB_SCRATCH_AREA_LIMIT);
+			return false;
+		}
+		scratch_va = kzalloc(len, GFP_KERNEL);
+		if (!scratch_va)
+			return false;
+
+		if (kvm_read_guest(svm->vcpu.kvm, scratch_gpa_beg, scratch_va, len)) {
+			/* Unable to copy scratch area from guest */
+			pr_err("vmgexit: kvm_read_guest for scratch area failed\n");
+
+			kfree(scratch_va);
+			return false;
+		}
+
+		/*
+		 * The scratch area is outside the GHCB. The operation will
+		 * dictate whether the buffer needs to be synced before running
+		 * the vCPU next time (i.e. a read was requested so the data
+		 * must be written back to the guest memory).
+		 */
+		svm->ghcb_sa_sync = sync;
+		svm->ghcb_sa_free = true;
+	}
+
+	svm->ghcb_sa = scratch_va;
+	svm->ghcb_sa_len = len;
+
+	return true;
+}
+
+static void set_ghcb_msr_bits(struct vcpu_svm *svm, u64 value, u64 mask,
+			      unsigned int pos)
+{
+	svm->vmcb->control.ghcb_gpa &= ~(mask << pos);
+	svm->vmcb->control.ghcb_gpa |= (value & mask) << pos;
+}
+
+static u64 get_ghcb_msr_bits(struct vcpu_svm *svm, u64 mask, unsigned int pos)
+{
+	return (svm->vmcb->control.ghcb_gpa >> pos) & mask;
+}
+
+static void set_ghcb_msr(struct vcpu_svm *svm, u64 value)
+{
+	svm->vmcb->control.ghcb_gpa = value;
+}
+
+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;
+	u64 ghcb_info;
+	int ret = 1;
+
+	ghcb_info = control->ghcb_gpa & GHCB_MSR_INFO_MASK;
+
+	trace_kvm_vmgexit_msr_protocol_enter(svm->vcpu.vcpu_id,
+					     control->ghcb_gpa);
+
+	switch (ghcb_info) {
+	case GHCB_MSR_SEV_INFO_REQ:
+		set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX,
+						    GHCB_VERSION_MIN,
+						    sev_enc_bit));
+		break;
+	case GHCB_MSR_CPUID_REQ: {
+		u64 cpuid_fn, cpuid_reg, cpuid_value;
+
+		cpuid_fn = get_ghcb_msr_bits(svm,
+					     GHCB_MSR_CPUID_FUNC_MASK,
+					     GHCB_MSR_CPUID_FUNC_POS);
+
+		/* Initialize the registers needed by the CPUID intercept */
+		vcpu->arch.regs[VCPU_REGS_RAX] = cpuid_fn;
+		vcpu->arch.regs[VCPU_REGS_RCX] = 0;
+
+		ret = svm_invoke_exit_handler(svm, SVM_EXIT_CPUID);
+		if (!ret) {
+			ret = -EINVAL;
+			break;
+		}
+
+		cpuid_reg = get_ghcb_msr_bits(svm,
+					      GHCB_MSR_CPUID_REG_MASK,
+					      GHCB_MSR_CPUID_REG_POS);
+		if (cpuid_reg == 0)
+			cpuid_value = vcpu->arch.regs[VCPU_REGS_RAX];
+		else if (cpuid_reg == 1)
+			cpuid_value = vcpu->arch.regs[VCPU_REGS_RBX];
+		else if (cpuid_reg == 2)
+			cpuid_value = vcpu->arch.regs[VCPU_REGS_RCX];
+		else
+			cpuid_value = vcpu->arch.regs[VCPU_REGS_RDX];
+
+		set_ghcb_msr_bits(svm, cpuid_value,
+				  GHCB_MSR_CPUID_VALUE_MASK,
+				  GHCB_MSR_CPUID_VALUE_POS);
+
+		set_ghcb_msr_bits(svm, GHCB_MSR_CPUID_RESP,
+				  GHCB_MSR_INFO_MASK,
+				  GHCB_MSR_INFO_POS);
+		break;
+	}
+	case GHCB_MSR_TERM_REQ: {
+		u64 reason_set, reason_code;
+
+		reason_set = get_ghcb_msr_bits(svm,
+					       GHCB_MSR_TERM_REASON_SET_MASK,
+					       GHCB_MSR_TERM_REASON_SET_POS);
+		reason_code = get_ghcb_msr_bits(svm,
+						GHCB_MSR_TERM_REASON_MASK,
+						GHCB_MSR_TERM_REASON_POS);
+		pr_info("SEV-ES guest requested termination: %#llx:%#llx\n",
+			reason_set, reason_code);
+		fallthrough;
+	}
+	default:
+		ret = -EINVAL;
+	}
+
+	trace_kvm_vmgexit_msr_protocol_exit(svm->vcpu.vcpu_id,
+					    control->ghcb_gpa, ret);
+
+	return ret;
+}
+
+int sev_handle_vmgexit(struct vcpu_svm *svm)
+{
+	struct vmcb_control_area *control = &svm->vmcb->control;
+	u64 ghcb_gpa, exit_code;
+	struct ghcb *ghcb;
+	int ret;
+
+	/* Validate the GHCB */
+	ghcb_gpa = control->ghcb_gpa;
+	if (ghcb_gpa & GHCB_MSR_INFO_MASK)
+		return sev_handle_vmgexit_msr_protocol(svm);
+
+	if (!ghcb_gpa) {
+		vcpu_unimpl(&svm->vcpu, "vmgexit: GHCB gpa is not set\n");
+		return -EINVAL;
+	}
+
+	if (kvm_vcpu_map(&svm->vcpu, ghcb_gpa >> PAGE_SHIFT, &svm->ghcb_map)) {
+		/* Unable to map GHCB from guest */
+		vcpu_unimpl(&svm->vcpu, "vmgexit: error mapping GHCB [%#llx] from guest\n",
+			    ghcb_gpa);
+		return -EINVAL;
+	}
+
+	svm->ghcb = svm->ghcb_map.hva;
+	ghcb = svm->ghcb_map.hva;
+
+	trace_kvm_vmgexit_enter(svm->vcpu.vcpu_id, ghcb);
+
+	exit_code = ghcb_get_sw_exit_code(ghcb);
+
+	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);
+
+	ret = -EINVAL;
+	switch (exit_code) {
+	case SVM_VMGEXIT_MMIO_READ:
+		if (!setup_vmgexit_scratch(svm, true, control->exit_info_2))
+			break;
+
+		ret = kvm_sev_es_mmio_read(&svm->vcpu,
+					   control->exit_info_1,
+					   control->exit_info_2,
+					   svm->ghcb_sa);
+		break;
+	case SVM_VMGEXIT_MMIO_WRITE:
+		if (!setup_vmgexit_scratch(svm, false, control->exit_info_2))
+			break;
+
+		ret = kvm_sev_es_mmio_write(&svm->vcpu,
+					    control->exit_info_1,
+					    control->exit_info_2,
+					    svm->ghcb_sa);
+		break;
+	case SVM_VMGEXIT_NMI_COMPLETE:
+		ret = svm_invoke_exit_handler(svm, SVM_EXIT_IRET);
+		break;
+	case SVM_VMGEXIT_AP_JUMP_TABLE: {
+		struct kvm_sev_info *sev = &to_kvm_svm(svm->vcpu.kvm)->sev_info;
+
+		switch (control->exit_info_1) {
+		case 0:
+			/* Set AP jump table address */
+			sev->ap_jump_table = control->exit_info_2;
+			break;
+		case 1:
+			/* Get AP jump table address */
+			ghcb_set_sw_exit_info_2(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, 1);
+			ghcb_set_sw_exit_info_2(ghcb,
+						X86_TRAP_UD |
+						SVM_EVTINJ_TYPE_EXEPT |
+						SVM_EVTINJ_VALID);
+		}
+
+		ret = 1;
+		break;
+	}
+	case SVM_VMGEXIT_UNSUPPORTED_EVENT:
+		vcpu_unimpl(&svm->vcpu,
+			    "vmgexit: unsupported event - exit_info_1=%#llx, exit_info_2=%#llx\n",
+			    control->exit_info_1, control->exit_info_2);
+		break;
+	default:
+		ret = svm_invoke_exit_handler(svm, exit_code);
+	}
+
+	return ret;
+}
+
+int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
+{
+	if (!setup_vmgexit_scratch(svm, in, svm->vmcb->control.exit_info_2))
+		return -EINVAL;
+
+	return kvm_sev_es_string_io(&svm->vcpu, size, port,
+				    svm->ghcb_sa, svm->ghcb_sa_len, in);
+}
+
+void sev_es_init_vmcb(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+
+	svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE;
+	svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
+
+	/*
+	 * 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.
+	 */
+	svm->vmcb->control.vmsa_pa = __pa(svm->vmsa);
+
+	/* Can't intercept CR register access, HV can't modify CR registers */
+	svm_clr_intercept(svm, INTERCEPT_CR0_READ);
+	svm_clr_intercept(svm, INTERCEPT_CR4_READ);
+	svm_clr_intercept(svm, INTERCEPT_CR8_READ);
+	svm_clr_intercept(svm, INTERCEPT_CR0_WRITE);
+	svm_clr_intercept(svm, INTERCEPT_CR4_WRITE);
+	svm_clr_intercept(svm, INTERCEPT_CR8_WRITE);
+
+	svm_clr_intercept(svm, INTERCEPT_SELECTIVE_CR0);
+
+	/* Track EFER/CR register changes */
+	svm_set_intercept(svm, TRAP_EFER_WRITE);
+	svm_set_intercept(svm, TRAP_CR0_WRITE);
+	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);
+
+	/* Can't intercept XSETBV, HV can't modify XCR0 directly */
+	svm_clr_intercept(svm, INTERCEPT_XSETBV);
+
+	/* Clear intercepts on selected MSRs */
+	set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1);
+	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
+	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);
+}
+
+void sev_es_create_vcpu(struct vcpu_svm *svm)
+{
+	/*
+	 * Set the GHCB MSR value as per the GHCB specification when creating
+	 * a vCPU for an SEV-ES guest.
+	 */
+	set_ghcb_msr(svm, GHCB_MSR_SEV_INFO(GHCB_VERSION_MAX,
+					    GHCB_VERSION_MIN,
+					    sev_enc_bit));
+}
+
+void sev_es_vcpu_load(struct vcpu_svm *svm, int cpu)
+{
+	struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
+	struct vmcb_save_area *hostsa;
+	unsigned int i;
+
+	/*
+	 * As an SEV-ES guest, hardware will restore the host state on VMEXIT,
+	 * of which one step is to perform a VMLOAD. Since hardware does not
+	 * perform a VMSAVE on VMRUN, the host savearea must be updated.
+	 */
+	asm volatile(__ex("vmsave") : : "a" (__sme_page_pa(sd->save_area)) : "memory");
+
+	/*
+	 * Certain MSRs are restored on VMEXIT, only save ones that aren't
+	 * restored.
+	 */
+	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) {
+		if (host_save_user_msrs[i].sev_es_restored)
+			continue;
+
+		rdmsrl(host_save_user_msrs[i].index, svm->host_user_msrs[i]);
+	}
+
+	/* XCR0 is restored on VMEXIT, save the current host value */
+	hostsa = (struct vmcb_save_area *)(page_address(sd->save_area) + 0x400);
+	hostsa->xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
+
+	/* PKRU is restored on VMEXIT, save the curent host value */
+	hostsa->pkru = read_pkru();
+
+	/* MSR_IA32_XSS is restored on VMEXIT, save the currnet host value */
+	hostsa->xss = host_xss;
+}
+
+void sev_es_vcpu_put(struct vcpu_svm *svm)
+{
+	unsigned int i;
+
+	/*
+	 * Certain MSRs are restored on VMEXIT and were saved with vmsave in
+	 * sev_es_vcpu_load() above. Only restore ones that weren't.
+	 */
+	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) {
+		if (host_save_user_msrs[i].sev_es_restored)
+			continue;
+
+		wrmsrl(host_save_user_msrs[i].index, svm->host_user_msrs[i]);
+	}
+}