1 files changed, 470 insertions, 211 deletions

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 90a1ca939627..8a6db11dcb43 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -19,11 +19,14 @@
 #include <linux/kernel.h>
 
 #include <asm/msr-index.h>
+#include <asm/debugreg.h>
 
 #include "kvm_emulate.h"
 #include "trace.h"
 #include "mmu.h"
 #include "x86.h"
+#include "cpuid.h"
+#include "lapic.h"
 #include "svm.h"
 
 static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
@@ -58,7 +61,7 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
 static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	u64 cr3 = svm->nested.nested_cr3;
+	u64 cr3 = svm->nested.ctl.nested_cr3;
 	u64 pdpte;
 	int ret;
 
@@ -73,19 +76,22 @@ static unsigned long nested_svm_get_tdp_cr3(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	return svm->nested.nested_cr3;
+	return svm->nested.ctl.nested_cr3;
 }
 
 static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
 {
+	struct vcpu_svm *svm = to_svm(vcpu);
+	struct vmcb *hsave = svm->nested.hsave;
+
 	WARN_ON(mmu_is_nested(vcpu));
 
 	vcpu->arch.mmu = &vcpu->arch.guest_mmu;
-	kvm_init_shadow_mmu(vcpu);
+	kvm_init_shadow_mmu(vcpu, X86_CR0_PG, hsave->save.cr4, hsave->save.efer);
 	vcpu->arch.mmu->get_guest_pgd     = nested_svm_get_tdp_cr3;
 	vcpu->arch.mmu->get_pdptr         = nested_svm_get_tdp_pdptr;
 	vcpu->arch.mmu->inject_page_fault = nested_svm_inject_npf_exit;
-	vcpu->arch.mmu->shadow_root_level = kvm_x86_ops.get_tdp_level(vcpu);
+	vcpu->arch.mmu->shadow_root_level = vcpu->arch.tdp_level;
 	reset_shadow_zero_bits_mask(vcpu, vcpu->arch.mmu);
 	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
 }
@@ -98,8 +104,7 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu)
 
 void recalc_intercepts(struct vcpu_svm *svm)
 {
-	struct vmcb_control_area *c, *h;
-	struct nested_state *g;
+	struct vmcb_control_area *c, *h, *g;
 
 	mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
 
@@ -108,14 +113,16 @@ void recalc_intercepts(struct vcpu_svm *svm)
 
 	c = &svm->vmcb->control;
 	h = &svm->nested.hsave->control;
-	g = &svm->nested;
+	g = &svm->nested.ctl;
+
+	svm->nested.host_intercept_exceptions = h->intercept_exceptions;
 
 	c->intercept_cr = h->intercept_cr;
 	c->intercept_dr = h->intercept_dr;
 	c->intercept_exceptions = h->intercept_exceptions;
 	c->intercept = h->intercept;
 
-	if (svm->vcpu.arch.hflags & HF_VINTR_MASK) {
+	if (g->int_ctl & V_INTR_MASKING_MASK) {
 		/* We only want the cr8 intercept bits of L1 */
 		c->intercept_cr &= ~(1U << INTERCEPT_CR8_READ);
 		c->intercept_cr &= ~(1U << INTERCEPT_CR8_WRITE);
@@ -137,11 +144,9 @@ void recalc_intercepts(struct vcpu_svm *svm)
 	c->intercept |= g->intercept;
 }
 
-static void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *from_vmcb)
+static void copy_vmcb_control_area(struct vmcb_control_area *dst,
+				   struct vmcb_control_area *from)
 {
-	struct vmcb_control_area *dst  = &dst_vmcb->control;
-	struct vmcb_control_area *from = &from_vmcb->control;
-
 	dst->intercept_cr         = from->intercept_cr;
 	dst->intercept_dr         = from->intercept_dr;
 	dst->intercept_exceptions = from->intercept_exceptions;
@@ -149,7 +154,7 @@ static void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *from_vmcb
 	dst->iopm_base_pa         = from->iopm_base_pa;
 	dst->msrpm_base_pa        = from->msrpm_base_pa;
 	dst->tsc_offset           = from->tsc_offset;
-	dst->asid                 = from->asid;
+	/* asid not copied, it is handled manually for svm->vmcb.  */
 	dst->tlb_ctl              = from->tlb_ctl;
 	dst->int_ctl              = from->int_ctl;
 	dst->int_vector           = from->int_vector;
@@ -178,7 +183,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 	 */
 	int i;
 
-	if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT)))
+	if (!(svm->nested.ctl.intercept & (1ULL << INTERCEPT_MSR_PROT)))
 		return true;
 
 	for (i = 0; i < MSRPM_OFFSETS; i++) {
@@ -189,7 +194,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 			break;
 
 		p      = msrpm_offsets[i];
-		offset = svm->nested.vmcb_msrpm + (p * 4);
+		offset = svm->nested.ctl.msrpm_base_pa + (p * 4);
 
 		if (kvm_vcpu_read_guest(&svm->vcpu, offset, &value, 4))
 			return false;
@@ -202,41 +207,111 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 	return true;
 }
 
-static bool nested_vmcb_checks(struct vmcb *vmcb)
+static bool nested_vmcb_check_controls(struct vmcb_control_area *control)
 {
-	if ((vmcb->save.efer & EFER_SVME) == 0)
+	if ((control->intercept & (1ULL << INTERCEPT_VMRUN)) == 0)
 		return false;
 
-	if ((vmcb->control.intercept & (1ULL << INTERCEPT_VMRUN)) == 0)
+	if (control->asid == 0)
 		return false;
 
-	if (vmcb->control.asid == 0)
-		return false;
-
-	if ((vmcb->control.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) &&
+	if ((control->nested_ctl & SVM_NESTED_CTL_NP_ENABLE) &&
 	    !npt_enabled)
 		return false;
 
 	return true;
 }
 
-void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
-			  struct vmcb *nested_vmcb, struct kvm_host_map *map)
+static bool nested_vmcb_checks(struct vmcb *vmcb)
 {
-	bool evaluate_pending_interrupts =
-		is_intercept(svm, INTERCEPT_VINTR) ||
-		is_intercept(svm, INTERCEPT_IRET);
+	if ((vmcb->save.efer & EFER_SVME) == 0)
+		return false;
 
-	if (kvm_get_rflags(&svm->vcpu) & X86_EFLAGS_IF)
-		svm->vcpu.arch.hflags |= HF_HIF_MASK;
-	else
-		svm->vcpu.arch.hflags &= ~HF_HIF_MASK;
+	if (((vmcb->save.cr0 & X86_CR0_CD) == 0) &&
+	    (vmcb->save.cr0 & X86_CR0_NW))
+		return false;
 
-	if (nested_vmcb->control.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) {
-		svm->nested.nested_cr3 = nested_vmcb->control.nested_cr3;
-		nested_svm_init_mmu_context(&svm->vcpu);
+	return nested_vmcb_check_controls(&vmcb->control);
+}
+
+static void load_nested_vmcb_control(struct vcpu_svm *svm,
+				     struct vmcb_control_area *control)
+{
+	copy_vmcb_control_area(&svm->nested.ctl, control);
+
+	/* Copy it here because nested_svm_check_controls will check it.  */
+	svm->nested.ctl.asid           = control->asid;
+	svm->nested.ctl.msrpm_base_pa &= ~0x0fffULL;
+	svm->nested.ctl.iopm_base_pa  &= ~0x0fffULL;
+}
+
+/*
+ * Synchronize fields that are written by the processor, so that
+ * they can be copied back into the nested_vmcb.
+ */
+void sync_nested_vmcb_control(struct vcpu_svm *svm)
+{
+	u32 mask;
+	svm->nested.ctl.event_inj      = svm->vmcb->control.event_inj;
+	svm->nested.ctl.event_inj_err  = svm->vmcb->control.event_inj_err;
+
+	/* Only a few fields of int_ctl are written by the processor.  */
+	mask = V_IRQ_MASK | V_TPR_MASK;
+	if (!(svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK) &&
+	    is_intercept(svm, SVM_EXIT_VINTR)) {
+		/*
+		 * In order to request an interrupt window, L0 is usurping
+		 * svm->vmcb->control.int_ctl and possibly setting V_IRQ
+		 * even if it was clear in L1's VMCB.  Restoring it would be
+		 * wrong.  However, in this case V_IRQ will remain true until
+		 * interrupt_window_interception calls svm_clear_vintr and
+		 * restores int_ctl.  We can just leave it aside.
+		 */
+		mask &= ~V_IRQ_MASK;
 	}
+	svm->nested.ctl.int_ctl        &= ~mask;
+	svm->nested.ctl.int_ctl        |= svm->vmcb->control.int_ctl & mask;
+}
+
+/*
+ * Transfer any event that L0 or L1 wanted to inject into L2 to
+ * EXIT_INT_INFO.
+ */
+static void nested_vmcb_save_pending_event(struct vcpu_svm *svm,
+					   struct vmcb *nested_vmcb)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	u32 exit_int_info = 0;
+	unsigned int nr;
+
+	if (vcpu->arch.exception.injected) {
+		nr = vcpu->arch.exception.nr;
+		exit_int_info = nr | SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_EXEPT;
+
+		if (vcpu->arch.exception.has_error_code) {
+			exit_int_info |= SVM_EVTINJ_VALID_ERR;
+			nested_vmcb->control.exit_int_info_err =
+				vcpu->arch.exception.error_code;
+		}
+
+	} else if (vcpu->arch.nmi_injected) {
+		exit_int_info = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI;
 
+	} else if (vcpu->arch.interrupt.injected) {
+		nr = vcpu->arch.interrupt.nr;
+		exit_int_info = nr | SVM_EVTINJ_VALID;
+
+		if (vcpu->arch.interrupt.soft)
+			exit_int_info |= SVM_EVTINJ_TYPE_SOFT;
+		else
+			exit_int_info |= SVM_EVTINJ_TYPE_INTR;
+	}
+
+	nested_vmcb->control.exit_int_info = exit_int_info;
+}
+
+static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *nested_vmcb)
+{
 	/* Load the nested guest state */
 	svm->vmcb->save.es = nested_vmcb->save.es;
 	svm->vmcb->save.cs = nested_vmcb->save.cs;
@@ -248,14 +323,7 @@ void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
 	svm_set_efer(&svm->vcpu, nested_vmcb->save.efer);
 	svm_set_cr0(&svm->vcpu, nested_vmcb->save.cr0);
 	svm_set_cr4(&svm->vcpu, nested_vmcb->save.cr4);
-	if (npt_enabled) {
-		svm->vmcb->save.cr3 = nested_vmcb->save.cr3;
-		svm->vcpu.arch.cr3 = nested_vmcb->save.cr3;
-	} else
-		(void)kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3);
-
-	/* Guest paging mode is active - reset mmu */
-	kvm_mmu_reset_context(&svm->vcpu);
+	(void)kvm_set_cr3(&svm->vcpu, nested_vmcb->save.cr3);
 
 	svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = nested_vmcb->save.cr2;
 	kvm_rax_write(&svm->vcpu, nested_vmcb->save.rax);
@@ -267,40 +335,36 @@ void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
 	svm->vmcb->save.rsp = nested_vmcb->save.rsp;
 	svm->vmcb->save.rip = nested_vmcb->save.rip;
 	svm->vmcb->save.dr7 = nested_vmcb->save.dr7;
-	svm->vmcb->save.dr6 = nested_vmcb->save.dr6;
+	svm->vcpu.arch.dr6  = nested_vmcb->save.dr6;
 	svm->vmcb->save.cpl = nested_vmcb->save.cpl;
+}
 
-	svm->nested.vmcb_msrpm = nested_vmcb->control.msrpm_base_pa & ~0x0fffULL;
-	svm->nested.vmcb_iopm  = nested_vmcb->control.iopm_base_pa  & ~0x0fffULL;
+static void nested_prepare_vmcb_control(struct vcpu_svm *svm)
+{
+	const u32 mask = V_INTR_MASKING_MASK | V_GIF_ENABLE_MASK | V_GIF_MASK;
+	if (svm->nested.ctl.nested_ctl & SVM_NESTED_CTL_NP_ENABLE)
+		nested_svm_init_mmu_context(&svm->vcpu);
 
-	/* cache intercepts */
-	svm->nested.intercept_cr         = nested_vmcb->control.intercept_cr;
-	svm->nested.intercept_dr         = nested_vmcb->control.intercept_dr;
-	svm->nested.intercept_exceptions = nested_vmcb->control.intercept_exceptions;
-	svm->nested.intercept            = nested_vmcb->control.intercept;
+	/* Guest paging mode is active - reset mmu */
+	kvm_mmu_reset_context(&svm->vcpu);
 
-	svm_flush_tlb(&svm->vcpu, true);
-	svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK;
-	if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK)
-		svm->vcpu.arch.hflags |= HF_VINTR_MASK;
-	else
-		svm->vcpu.arch.hflags &= ~HF_VINTR_MASK;
+	svm_flush_tlb(&svm->vcpu);
 
-	svm->vcpu.arch.tsc_offset += nested_vmcb->control.tsc_offset;
-	svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset;
+	svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset =
+		svm->vcpu.arch.l1_tsc_offset + svm->nested.ctl.tsc_offset;
 
-	svm->vmcb->control.virt_ext = nested_vmcb->control.virt_ext;
-	svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
-	svm->vmcb->control.int_state = nested_vmcb->control.int_state;
-	svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
-	svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
+	svm->vmcb->control.int_ctl             =
+		(svm->nested.ctl.int_ctl & ~mask) |
+		(svm->nested.hsave->control.int_ctl & mask);
 
-	svm->vmcb->control.pause_filter_count =
-		nested_vmcb->control.pause_filter_count;
-	svm->vmcb->control.pause_filter_thresh =
-		nested_vmcb->control.pause_filter_thresh;
+	svm->vmcb->control.virt_ext            = svm->nested.ctl.virt_ext;
+	svm->vmcb->control.int_vector          = svm->nested.ctl.int_vector;
+	svm->vmcb->control.int_state           = svm->nested.ctl.int_state;
+	svm->vmcb->control.event_inj           = svm->nested.ctl.event_inj;
+	svm->vmcb->control.event_inj_err       = svm->nested.ctl.event_inj_err;
 
-	kvm_vcpu_unmap(&svm->vcpu, map, true);
+	svm->vmcb->control.pause_filter_count  = svm->nested.ctl.pause_filter_count;
+	svm->vmcb->control.pause_filter_thresh = svm->nested.ctl.pause_filter_thresh;
 
 	/* Enter Guest-Mode */
 	enter_guest_mode(&svm->vcpu);
@@ -311,25 +375,18 @@ void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
 	 */
 	recalc_intercepts(svm);
 
-	svm->nested.vmcb = vmcb_gpa;
+	mark_all_dirty(svm->vmcb);
+}
 
-	/*
-	 * If L1 had a pending IRQ/NMI before executing VMRUN,
-	 * which wasn't delivered because it was disallowed (e.g.
-	 * interrupts disabled), L0 needs to evaluate if this pending
-	 * event should cause an exit from L2 to L1 or be delivered
-	 * directly to L2.
-	 *
-	 * Usually this would be handled by the processor noticing an
-	 * IRQ/NMI window request.  However, VMRUN can unblock interrupts
-	 * by implicitly setting GIF, so force L0 to perform pending event
-	 * evaluation by requesting a KVM_REQ_EVENT.
-	 */
-	enable_gif(svm);
-	if (unlikely(evaluate_pending_interrupts))
-		kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
+void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
+			  struct vmcb *nested_vmcb)
+{
+	svm->nested.vmcb = vmcb_gpa;
+	load_nested_vmcb_control(svm, &nested_vmcb->control);
+	nested_prepare_vmcb_save(svm, nested_vmcb);
+	nested_prepare_vmcb_control(svm);
 
-	mark_all_dirty(svm->vmcb);
+	svm_set_gif(svm, true);
 }
 
 int nested_svm_vmrun(struct vcpu_svm *svm)
@@ -341,8 +398,12 @@ int nested_svm_vmrun(struct vcpu_svm *svm)
 	struct kvm_host_map map;
 	u64 vmcb_gpa;
 
-	vmcb_gpa = svm->vmcb->save.rax;
+	if (is_smm(&svm->vcpu)) {
+		kvm_queue_exception(&svm->vcpu, UD_VECTOR);
+		return 1;
+	}
 
+	vmcb_gpa = svm->vmcb->save.rax;
 	ret = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(vmcb_gpa), &map);
 	if (ret == -EINVAL) {
 		kvm_inject_gp(&svm->vcpu, 0);
@@ -360,10 +421,7 @@ int nested_svm_vmrun(struct vcpu_svm *svm)
 		nested_vmcb->control.exit_code_hi = 0;
 		nested_vmcb->control.exit_info_1  = 0;
 		nested_vmcb->control.exit_info_2  = 0;
-
-		kvm_vcpu_unmap(&svm->vcpu, &map, true);
-
-		return ret;
+		goto out;
 	}
 
 	trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb_gpa,
@@ -403,9 +461,10 @@ int nested_svm_vmrun(struct vcpu_svm *svm)
 	else
 		hsave->save.cr3    = kvm_read_cr3(&svm->vcpu);
 
-	copy_vmcb_control_area(hsave, vmcb);
+	copy_vmcb_control_area(&hsave->control, &vmcb->control);
 
-	enter_svm_guest_mode(svm, vmcb_gpa, nested_vmcb, &map);
+	svm->nested.nested_run_pending = 1;
+	enter_svm_guest_mode(svm, vmcb_gpa, nested_vmcb);
 
 	if (!nested_svm_vmrun_msrpm(svm)) {
 		svm->vmcb->control.exit_code    = SVM_EXIT_ERR;
@@ -416,6 +475,9 @@ int nested_svm_vmrun(struct vcpu_svm *svm)
 		nested_svm_vmexit(svm);
 	}
 
+out:
+	kvm_vcpu_unmap(&svm->vcpu, &map, true);
+
 	return ret;
 }
 
@@ -443,13 +505,6 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	struct vmcb *vmcb = svm->vmcb;
 	struct kvm_host_map map;
 
-	trace_kvm_nested_vmexit_inject(vmcb->control.exit_code,
-				       vmcb->control.exit_info_1,
-				       vmcb->control.exit_info_2,
-				       vmcb->control.exit_int_info,
-				       vmcb->control.exit_int_info_err,
-				       KVM_ISA_SVM);
-
 	rc = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->nested.vmcb), &map);
 	if (rc) {
 		if (rc == -EINVAL)
@@ -462,9 +517,13 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	/* Exit Guest-Mode */
 	leave_guest_mode(&svm->vcpu);
 	svm->nested.vmcb = 0;
+	WARN_ON_ONCE(svm->nested.nested_run_pending);
+
+	/* in case we halted in L2 */
+	svm->vcpu.arch.mp_state = KVM_MP_STATE_RUNNABLE;
 
 	/* Give the current vmcb to the guest */
-	disable_gif(svm);
+	svm_set_gif(svm, false);
 
 	nested_vmcb->save.es     = vmcb->save.es;
 	nested_vmcb->save.cs     = vmcb->save.cs;
@@ -478,62 +537,42 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	nested_vmcb->save.cr2    = vmcb->save.cr2;
 	nested_vmcb->save.cr4    = svm->vcpu.arch.cr4;
 	nested_vmcb->save.rflags = kvm_get_rflags(&svm->vcpu);
-	nested_vmcb->save.rip    = vmcb->save.rip;
-	nested_vmcb->save.rsp    = vmcb->save.rsp;
-	nested_vmcb->save.rax    = vmcb->save.rax;
+	nested_vmcb->save.rip    = kvm_rip_read(&svm->vcpu);
+	nested_vmcb->save.rsp    = kvm_rsp_read(&svm->vcpu);
+	nested_vmcb->save.rax    = kvm_rax_read(&svm->vcpu);
 	nested_vmcb->save.dr7    = vmcb->save.dr7;
-	nested_vmcb->save.dr6    = vmcb->save.dr6;
+	nested_vmcb->save.dr6    = svm->vcpu.arch.dr6;
 	nested_vmcb->save.cpl    = vmcb->save.cpl;
 
-	nested_vmcb->control.int_ctl           = vmcb->control.int_ctl;
-	nested_vmcb->control.int_vector        = vmcb->control.int_vector;
 	nested_vmcb->control.int_state         = vmcb->control.int_state;
 	nested_vmcb->control.exit_code         = vmcb->control.exit_code;
 	nested_vmcb->control.exit_code_hi      = vmcb->control.exit_code_hi;
 	nested_vmcb->control.exit_info_1       = vmcb->control.exit_info_1;
 	nested_vmcb->control.exit_info_2       = vmcb->control.exit_info_2;
-	nested_vmcb->control.exit_int_info     = vmcb->control.exit_int_info;
-	nested_vmcb->control.exit_int_info_err = vmcb->control.exit_int_info_err;
+
+	if (nested_vmcb->control.exit_code != SVM_EXIT_ERR)
+		nested_vmcb_save_pending_event(svm, nested_vmcb);
 
 	if (svm->nrips_enabled)
 		nested_vmcb->control.next_rip  = vmcb->control.next_rip;
 
-	/*
-	 * If we emulate a VMRUN/#VMEXIT in the same host #vmexit cycle we have
-	 * to make sure that we do not lose injected events. So check event_inj
-	 * here and copy it to exit_int_info if it is valid.
-	 * Exit_int_info and event_inj can't be both valid because the case
-	 * below only happens on a VMRUN instruction intercept which has
-	 * no valid exit_int_info set.
-	 */
-	if (vmcb->control.event_inj & SVM_EVTINJ_VALID) {
-		struct vmcb_control_area *nc = &nested_vmcb->control;
-
-		nc->exit_int_info     = vmcb->control.event_inj;
-		nc->exit_int_info_err = vmcb->control.event_inj_err;
-	}
-
-	nested_vmcb->control.tlb_ctl           = 0;
-	nested_vmcb->control.event_inj         = 0;
-	nested_vmcb->control.event_inj_err     = 0;
+	nested_vmcb->control.int_ctl           = svm->nested.ctl.int_ctl;
+	nested_vmcb->control.tlb_ctl           = svm->nested.ctl.tlb_ctl;
+	nested_vmcb->control.event_inj         = svm->nested.ctl.event_inj;
+	nested_vmcb->control.event_inj_err     = svm->nested.ctl.event_inj_err;
 
 	nested_vmcb->control.pause_filter_count =
 		svm->vmcb->control.pause_filter_count;
 	nested_vmcb->control.pause_filter_thresh =
 		svm->vmcb->control.pause_filter_thresh;
 
-	/* We always set V_INTR_MASKING and remember the old value in hflags */
-	if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK))
-		nested_vmcb->control.int_ctl &= ~V_INTR_MASKING_MASK;
-
 	/* Restore the original control entries */
-	copy_vmcb_control_area(vmcb, hsave);
+	copy_vmcb_control_area(&vmcb->control, &hsave->control);
 
-	svm->vcpu.arch.tsc_offset = svm->vmcb->control.tsc_offset;
-	kvm_clear_exception_queue(&svm->vcpu);
-	kvm_clear_interrupt_queue(&svm->vcpu);
+	svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset =
+		svm->vcpu.arch.l1_tsc_offset;
 
-	svm->nested.nested_cr3 = 0;
+	svm->nested.ctl.nested_cr3 = 0;
 
 	/* Restore selected save entries */
 	svm->vmcb->save.es = hsave->save.es;
@@ -561,6 +600,13 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 
 	mark_all_dirty(svm->vmcb);
 
+	trace_kvm_nested_vmexit_inject(nested_vmcb->control.exit_code,
+				       nested_vmcb->control.exit_info_1,
+				       nested_vmcb->control.exit_info_2,
+				       nested_vmcb->control.exit_int_info,
+				       nested_vmcb->control.exit_int_info_err,
+				       KVM_ISA_SVM);
+
 	kvm_vcpu_unmap(&svm->vcpu, &map, true);
 
 	nested_svm_uninit_mmu_context(&svm->vcpu);
@@ -578,12 +624,28 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 	return 0;
 }
 
+/*
+ * Forcibly leave nested mode in order to be able to reset the VCPU later on.
+ */
+void svm_leave_nested(struct vcpu_svm *svm)
+{
+	if (is_guest_mode(&svm->vcpu)) {
+		struct vmcb *hsave = svm->nested.hsave;
+		struct vmcb *vmcb = svm->vmcb;
+
+		svm->nested.nested_run_pending = 0;
+		leave_guest_mode(&svm->vcpu);
+		copy_vmcb_control_area(&vmcb->control, &hsave->control);
+		nested_svm_uninit_mmu_context(&svm->vcpu);
+	}
+}
+
 static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
 {
 	u32 offset, msr, value;
 	int write, mask;
 
-	if (!(svm->nested.intercept & (1ULL << INTERCEPT_MSR_PROT)))
+	if (!(svm->nested.ctl.intercept & (1ULL << INTERCEPT_MSR_PROT)))
 		return NESTED_EXIT_HOST;
 
 	msr    = svm->vcpu.arch.regs[VCPU_REGS_RCX];
@@ -597,37 +659,12 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
 	/* Offset is in 32 bit units but need in 8 bit units */
 	offset *= 4;
 
-	if (kvm_vcpu_read_guest(&svm->vcpu, svm->nested.vmcb_msrpm + offset, &value, 4))
+	if (kvm_vcpu_read_guest(&svm->vcpu, svm->nested.ctl.msrpm_base_pa + offset, &value, 4))
 		return NESTED_EXIT_DONE;
 
 	return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
 }
 
-/* DB exceptions for our internal use must not cause vmexit */
-static int nested_svm_intercept_db(struct vcpu_svm *svm)
-{
-	unsigned long dr6;
-
-	/* if we're not singlestepping, it's not ours */
-	if (!svm->nmi_singlestep)
-		return NESTED_EXIT_DONE;
-
-	/* if it's not a singlestep exception, it's not ours */
-	if (kvm_get_dr(&svm->vcpu, 6, &dr6))
-		return NESTED_EXIT_DONE;
-	if (!(dr6 & DR6_BS))
-		return NESTED_EXIT_DONE;
-
-	/* if the guest is singlestepping, it should get the vmexit */
-	if (svm->nmi_singlestep_guest_rflags & X86_EFLAGS_TF) {
-		disable_nmi_singlestep(svm);
-		return NESTED_EXIT_DONE;
-	}
-
-	/* it's ours, the nested hypervisor must not see this one */
-	return NESTED_EXIT_HOST;
-}
-
 static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
 {
 	unsigned port, size, iopm_len;
@@ -635,13 +672,13 @@ static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
 	u8 start_bit;
 	u64 gpa;
 
-	if (!(svm->nested.intercept & (1ULL << INTERCEPT_IOIO_PROT)))
+	if (!(svm->nested.ctl.intercept & (1ULL << INTERCEPT_IOIO_PROT)))
 		return NESTED_EXIT_HOST;
 
 	port = svm->vmcb->control.exit_info_1 >> 16;
 	size = (svm->vmcb->control.exit_info_1 & SVM_IOIO_SIZE_MASK) >>
 		SVM_IOIO_SIZE_SHIFT;
-	gpa  = svm->nested.vmcb_iopm + (port / 8);
+	gpa  = svm->nested.ctl.iopm_base_pa + (port / 8);
 	start_bit = port % 8;
 	iopm_len = (start_bit + size > 8) ? 2 : 1;
 	mask = (0xf >> (4 - size)) << start_bit;
@@ -667,28 +704,23 @@ static int nested_svm_intercept(struct vcpu_svm *svm)
 		break;
 	case SVM_EXIT_READ_CR0 ... SVM_EXIT_WRITE_CR8: {
 		u32 bit = 1U << (exit_code - SVM_EXIT_READ_CR0);
-		if (svm->nested.intercept_cr & bit)
+		if (svm->nested.ctl.intercept_cr & bit)
 			vmexit = NESTED_EXIT_DONE;
 		break;
 	}
 	case SVM_EXIT_READ_DR0 ... SVM_EXIT_WRITE_DR7: {
 		u32 bit = 1U << (exit_code - SVM_EXIT_READ_DR0);
-		if (svm->nested.intercept_dr & bit)
+		if (svm->nested.ctl.intercept_dr & bit)
 			vmexit = NESTED_EXIT_DONE;
 		break;
 	}
 	case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: {
-		u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE);
-		if (svm->nested.intercept_exceptions & excp_bits) {
-			if (exit_code == SVM_EXIT_EXCP_BASE + DB_VECTOR)
-				vmexit = nested_svm_intercept_db(svm);
-			else
-				vmexit = NESTED_EXIT_DONE;
-		}
-		/* async page fault always cause vmexit */
-		else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) &&
-			 svm->vcpu.arch.exception.nested_apf != 0)
-			vmexit = NESTED_EXIT_DONE;
+		/*
+		 * Host-intercepted exceptions have been checked already in
+		 * nested_svm_exit_special.  There is nothing to do here,
+		 * the vmexit is injected by svm_check_nested_events.
+		 */
+		vmexit = NESTED_EXIT_DONE;
 		break;
 	}
 	case SVM_EXIT_ERR: {
@@ -697,7 +729,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm)
 	}
 	default: {
 		u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR);
-		if (svm->nested.intercept & exit_bits)
+		if (svm->nested.ctl.intercept & exit_bits)
 			vmexit = NESTED_EXIT_DONE;
 	}
 	}
@@ -733,62 +765,140 @@ int nested_svm_check_permissions(struct vcpu_svm *svm)
 	return 0;
 }
 
-int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
-			       bool has_error_code, u32 error_code)
+static bool nested_exit_on_exception(struct vcpu_svm *svm)
 {
-	int vmexit;
+	unsigned int nr = svm->vcpu.arch.exception.nr;
 
-	if (!is_guest_mode(&svm->vcpu))
-		return 0;
+	return (svm->nested.ctl.intercept_exceptions & (1 << nr));
+}
 
-	vmexit = nested_svm_intercept(svm);
-	if (vmexit != NESTED_EXIT_DONE)
-		return 0;
+static void nested_svm_inject_exception_vmexit(struct vcpu_svm *svm)
+{
+	unsigned int nr = svm->vcpu.arch.exception.nr;
 
 	svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr;
 	svm->vmcb->control.exit_code_hi = 0;
-	svm->vmcb->control.exit_info_1 = error_code;
+
+	if (svm->vcpu.arch.exception.has_error_code)
+		svm->vmcb->control.exit_info_1 = svm->vcpu.arch.exception.error_code;
 
 	/*
 	 * EXITINFO2 is undefined for all exception intercepts other
 	 * than #PF.
 	 */
-	if (svm->vcpu.arch.exception.nested_apf)
-		svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token;
-	else if (svm->vcpu.arch.exception.has_payload)
-		svm->vmcb->control.exit_info_2 = svm->vcpu.arch.exception.payload;
-	else
-		svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
+	if (nr == PF_VECTOR) {
+		if (svm->vcpu.arch.exception.nested_apf)
+			svm->vmcb->control.exit_info_2 = svm->vcpu.arch.apf.nested_apf_token;
+		else if (svm->vcpu.arch.exception.has_payload)
+			svm->vmcb->control.exit_info_2 = svm->vcpu.arch.exception.payload;
+		else
+			svm->vmcb->control.exit_info_2 = svm->vcpu.arch.cr2;
+	} else if (nr == DB_VECTOR) {
+		/* See inject_pending_event.  */
+		kvm_deliver_exception_payload(&svm->vcpu);
+		if (svm->vcpu.arch.dr7 & DR7_GD) {
+			svm->vcpu.arch.dr7 &= ~DR7_GD;
+			kvm_update_dr7(&svm->vcpu);
+		}
+	} else
+		WARN_ON(svm->vcpu.arch.exception.has_payload);
 
-	svm->nested.exit_required = true;
-	return vmexit;
+	nested_svm_vmexit(svm);
+}
+
+static void nested_svm_smi(struct vcpu_svm *svm)
+{
+	svm->vmcb->control.exit_code = SVM_EXIT_SMI;
+	svm->vmcb->control.exit_info_1 = 0;
+	svm->vmcb->control.exit_info_2 = 0;
+
+	nested_svm_vmexit(svm);
+}
+
+static void nested_svm_nmi(struct vcpu_svm *svm)
+{
+	svm->vmcb->control.exit_code = SVM_EXIT_NMI;
+	svm->vmcb->control.exit_info_1 = 0;
+	svm->vmcb->control.exit_info_2 = 0;
+
+	nested_svm_vmexit(svm);
 }
 
 static void nested_svm_intr(struct vcpu_svm *svm)
 {
+	trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip);
+
 	svm->vmcb->control.exit_code   = SVM_EXIT_INTR;
 	svm->vmcb->control.exit_info_1 = 0;
 	svm->vmcb->control.exit_info_2 = 0;
 
-	/* nested_svm_vmexit this gets called afterwards from handle_exit */
-	svm->nested.exit_required = true;
-	trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip);
+	nested_svm_vmexit(svm);
 }
 
-static bool nested_exit_on_intr(struct vcpu_svm *svm)
+static inline bool nested_exit_on_init(struct vcpu_svm *svm)
 {
-	return (svm->nested.intercept & 1ULL);
+	return (svm->nested.ctl.intercept & (1ULL << INTERCEPT_INIT));
 }
 
-int svm_check_nested_events(struct kvm_vcpu *vcpu)
+static void nested_svm_init(struct vcpu_svm *svm)
+{
+	svm->vmcb->control.exit_code   = SVM_EXIT_INIT;
+	svm->vmcb->control.exit_info_1 = 0;
+	svm->vmcb->control.exit_info_2 = 0;
+
+	nested_svm_vmexit(svm);
+}
+
+
+static int svm_check_nested_events(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	bool block_nested_events =
-		kvm_event_needs_reinjection(vcpu) || svm->nested.exit_required;
+		kvm_event_needs_reinjection(vcpu) || svm->nested.nested_run_pending;
+	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(svm)) {
+	if (lapic_in_kernel(vcpu) &&
+	    test_bit(KVM_APIC_INIT, &apic->pending_events)) {
 		if (block_nested_events)
 			return -EBUSY;
+		if (!nested_exit_on_init(svm))
+			return 0;
+		nested_svm_init(svm);
+		return 0;
+	}
+
+	if (vcpu->arch.exception.pending) {
+		if (block_nested_events)
+                        return -EBUSY;
+		if (!nested_exit_on_exception(svm))
+			return 0;
+		nested_svm_inject_exception_vmexit(svm);
+		return 0;
+	}
+
+	if (vcpu->arch.smi_pending && !svm_smi_blocked(vcpu)) {
+		if (block_nested_events)
+			return -EBUSY;
+		if (!nested_exit_on_smi(svm))
+			return 0;
+		nested_svm_smi(svm);
+		return 0;
+	}
+
+	if (vcpu->arch.nmi_pending && !svm_nmi_blocked(vcpu)) {
+		if (block_nested_events)
+			return -EBUSY;
+		if (!nested_exit_on_nmi(svm))
+			return 0;
+		nested_svm_nmi(svm);
+		return 0;
+	}
+
+	if (kvm_cpu_has_interrupt(vcpu) && !svm_interrupt_blocked(vcpu)) {
+		if (block_nested_events)
+			return -EBUSY;
+		if (!nested_exit_on_intr(svm))
+			return 0;
 		nested_svm_intr(svm);
 		return 0;
 	}
@@ -803,21 +913,170 @@ int nested_svm_exit_special(struct vcpu_svm *svm)
 	switch (exit_code) {
 	case SVM_EXIT_INTR:
 	case SVM_EXIT_NMI:
-	case SVM_EXIT_EXCP_BASE + MC_VECTOR:
-		return NESTED_EXIT_HOST;
 	case SVM_EXIT_NPF:
-		/* For now we are always handling NPFs when using them */
-		if (npt_enabled)
+		return NESTED_EXIT_HOST;
+	case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: {
+		u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE);
+
+		if (get_host_vmcb(svm)->control.intercept_exceptions & excp_bits)
 			return NESTED_EXIT_HOST;
-		break;
-	case SVM_EXIT_EXCP_BASE + PF_VECTOR:
-		/* When we're shadowing, trap PFs, but not async PF */
-		if (!npt_enabled && svm->vcpu.arch.apf.host_apf_reason == 0)
+		else if (exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR &&
+			 svm->vcpu.arch.apf.host_apf_flags)
+			/* Trap async PF even if not shadowing */
 			return NESTED_EXIT_HOST;
 		break;
+	}
 	default:
 		break;
 	}
 
 	return NESTED_EXIT_CONTINUE;
 }
+
+static int svm_get_nested_state(struct kvm_vcpu *vcpu,
+				struct kvm_nested_state __user *user_kvm_nested_state,
+				u32 user_data_size)
+{
+	struct vcpu_svm *svm;
+	struct kvm_nested_state kvm_state = {
+		.flags = 0,
+		.format = KVM_STATE_NESTED_FORMAT_SVM,
+		.size = sizeof(kvm_state),
+	};
+	struct vmcb __user *user_vmcb = (struct vmcb __user *)
+		&user_kvm_nested_state->data.svm[0];
+
+	if (!vcpu)
+		return kvm_state.size + KVM_STATE_NESTED_SVM_VMCB_SIZE;
+
+	svm = to_svm(vcpu);
+
+	if (user_data_size < kvm_state.size)
+		goto out;
+
+	/* First fill in the header and copy it out.  */
+	if (is_guest_mode(vcpu)) {
+		kvm_state.hdr.svm.vmcb_pa = svm->nested.vmcb;
+		kvm_state.size += KVM_STATE_NESTED_SVM_VMCB_SIZE;
+		kvm_state.flags |= KVM_STATE_NESTED_GUEST_MODE;
+
+		if (svm->nested.nested_run_pending)
+			kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING;
+	}
+
+	if (gif_set(svm))
+		kvm_state.flags |= KVM_STATE_NESTED_GIF_SET;
+
+	if (copy_to_user(user_kvm_nested_state, &kvm_state, sizeof(kvm_state)))
+		return -EFAULT;
+
+	if (!is_guest_mode(vcpu))
+		goto out;
+
+	/*
+	 * Copy over the full size of the VMCB rather than just the size
+	 * of the structs.
+	 */
+	if (clear_user(user_vmcb, KVM_STATE_NESTED_SVM_VMCB_SIZE))
+		return -EFAULT;
+	if (copy_to_user(&user_vmcb->control, &svm->nested.ctl,
+			 sizeof(user_vmcb->control)))
+		return -EFAULT;
+	if (copy_to_user(&user_vmcb->save, &svm->nested.hsave->save,
+			 sizeof(user_vmcb->save)))
+		return -EFAULT;
+
+out:
+	return kvm_state.size;
+}
+
+static int svm_set_nested_state(struct kvm_vcpu *vcpu,
+				struct kvm_nested_state __user *user_kvm_nested_state,
+				struct kvm_nested_state *kvm_state)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	struct vmcb *hsave = svm->nested.hsave;
+	struct vmcb __user *user_vmcb = (struct vmcb __user *)
+		&user_kvm_nested_state->data.svm[0];
+	struct vmcb_control_area ctl;
+	struct vmcb_save_area save;
+	u32 cr0;
+
+	if (kvm_state->format != KVM_STATE_NESTED_FORMAT_SVM)
+		return -EINVAL;
+
+	if (kvm_state->flags & ~(KVM_STATE_NESTED_GUEST_MODE |
+				 KVM_STATE_NESTED_RUN_PENDING |
+				 KVM_STATE_NESTED_GIF_SET))
+		return -EINVAL;
+
+	/*
+	 * If in guest mode, vcpu->arch.efer actually refers to the L2 guest's
+	 * EFER.SVME, but EFER.SVME still has to be 1 for VMRUN to succeed.
+	 */
+	if (!(vcpu->arch.efer & EFER_SVME)) {
+		/* GIF=1 and no guest mode are required if SVME=0.  */
+		if (kvm_state->flags != KVM_STATE_NESTED_GIF_SET)
+			return -EINVAL;
+	}
+
+	/* SMM temporarily disables SVM, so we cannot be in guest mode.  */
+	if (is_smm(vcpu) && (kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE))
+		return -EINVAL;
+
+	if (!(kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE)) {
+		svm_leave_nested(svm);
+		goto out_set_gif;
+	}
+
+	if (!page_address_valid(vcpu, kvm_state->hdr.svm.vmcb_pa))
+		return -EINVAL;
+	if (kvm_state->size < sizeof(*kvm_state) + KVM_STATE_NESTED_SVM_VMCB_SIZE)
+		return -EINVAL;
+	if (copy_from_user(&ctl, &user_vmcb->control, sizeof(ctl)))
+		return -EFAULT;
+	if (copy_from_user(&save, &user_vmcb->save, sizeof(save)))
+		return -EFAULT;
+
+	if (!nested_vmcb_check_controls(&ctl))
+		return -EINVAL;
+
+	/*
+	 * Processor state contains L2 state.  Check that it is
+	 * valid for guest mode (see nested_vmcb_checks).
+	 */
+	cr0 = kvm_read_cr0(vcpu);
+        if (((cr0 & X86_CR0_CD) == 0) && (cr0 & X86_CR0_NW))
+                return -EINVAL;
+
+	/*
+	 * Validate host state saved from before VMRUN (see
+	 * nested_svm_check_permissions).
+	 * TODO: validate reserved bits for all saved state.
+	 */
+	if (!(save.cr0 & X86_CR0_PG))
+		return -EINVAL;
+
+	/*
+	 * All checks done, we can enter guest mode.  L1 control fields
+	 * come from the nested save state.  Guest state is already
+	 * in the registers, the save area of the nested state instead
+	 * contains saved L1 state.
+	 */
+	copy_vmcb_control_area(&hsave->control, &svm->vmcb->control);
+	hsave->save = save;
+
+	svm->nested.vmcb = kvm_state->hdr.svm.vmcb_pa;
+	load_nested_vmcb_control(svm, &ctl);
+	nested_prepare_vmcb_control(svm);
+
+out_set_gif:
+	svm_set_gif(svm, !!(kvm_state->flags & KVM_STATE_NESTED_GIF_SET));
+	return 0;
+}
+
+struct kvm_x86_nested_ops svm_nested_ops = {
+	.check_events = svm_check_nested_events,
+	.get_state = svm_get_nested_state,
+	.set_state = svm_set_nested_state,
+};