nested.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Kernel-based Virtual Machine driver for Linux
 *
 * AMD SVM support
 *
 * Copyright (C) 2006 Qumranet, Inc.
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
 *
 * Authors:
 *   Yaniv Kamay  <yaniv@qumranet.com>
 *   Avi Kivity   <avi@qumranet.com>
 */

#define pr_fmt(fmt) "SVM: " fmt

#include <linux/kvm_types.h>
#include <linux/kvm_host.h>
#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 "lapic.h"
#include "svm.h"

static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
				       struct x86_exception *fault)
{
	struct vcpu_svm *svm = to_svm(vcpu);

	if (svm->vmcb->control.exit_code != SVM_EXIT_NPF) {
		/*
		 * TODO: track the cause of the nested page fault, and
		 * correctly fill in the high bits of exit_info_1.
		 */
		svm->vmcb->control.exit_code = SVM_EXIT_NPF;
		svm->vmcb->control.exit_code_hi = 0;
		svm->vmcb->control.exit_info_1 = (1ULL << 32);
		svm->vmcb->control.exit_info_2 = fault->address;
	}

	svm->vmcb->control.exit_info_1 &= ~0xffffffffULL;
	svm->vmcb->control.exit_info_1 |= fault->error_code;

	/*
	 * The present bit is always zero for page structure faults on real
	 * hardware.
	 */
	if (svm->vmcb->control.exit_info_1 & (2ULL << 32))
		svm->vmcb->control.exit_info_1 &= ~1;

	nested_svm_vmexit(svm);
}

static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index)
{
	struct vcpu_svm *svm = to_svm(vcpu);
	u64 cr3 = svm->nested.ctl.nested_cr3;
	u64 pdpte;
	int ret;

	ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(__sme_clr(cr3)), &pdpte,
				       offset_in_page(cr3) + index * 8, 8);
	if (ret)
		return 0;
	return pdpte;
}

static unsigned long nested_svm_get_tdp_cr3(struct kvm_vcpu *vcpu)
{
	struct vcpu_svm *svm = to_svm(vcpu);

	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, 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 = vcpu->arch.tdp_level;
	reset_shadow_zero_bits_mask(vcpu, vcpu->arch.mmu);
	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
}

static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu)
{
	vcpu->arch.mmu = &vcpu->arch.root_mmu;
	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
}

void recalc_intercepts(struct vcpu_svm *svm)
{
	struct vmcb_control_area *c, *h, *g;

	mark_dirty(svm->vmcb, VMCB_INTERCEPTS);

	if (!is_guest_mode(&svm->vcpu))
		return;

	c = &svm->vmcb->control;
	h = &svm->nested.hsave->control;
	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 (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);

		/*
		 * Once running L2 with HF_VINTR_MASK, EFLAGS.IF does not
		 * affect any interrupt we may want to inject; therefore,
		 * interrupt window vmexits are irrelevant to L0.
		 */
		c->intercept &= ~(1ULL << INTERCEPT_VINTR);
	}

	/* We don't want to see VMMCALLs from a nested guest */
	c->intercept &= ~(1ULL << INTERCEPT_VMMCALL);

	c->intercept_cr |= g->intercept_cr;
	c->intercept_dr |= g->intercept_dr;
	c->intercept_exceptions |= g->intercept_exceptions;
	c->intercept |= g->intercept;
}

static void copy_vmcb_control_area(struct vmcb_control_area *dst,
				   struct vmcb_control_area *from)
{
	dst->intercept_cr         = from->intercept_cr;
	dst->intercept_dr         = from->intercept_dr;
	dst->intercept_exceptions = from->intercept_exceptions;
	dst->intercept            = from->intercept;
	dst->iopm_base_pa         = from->iopm_base_pa;
	dst->msrpm_base_pa        = from->msrpm_base_pa;
	dst->tsc_offset           = from->tsc_offset;
	/* 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;
	dst->int_state            = from->int_state;
	dst->exit_code            = from->exit_code;
	dst->exit_code_hi         = from->exit_code_hi;
	dst->exit_info_1          = from->exit_info_1;
	dst->exit_info_2          = from->exit_info_2;
	dst->exit_int_info        = from->exit_int_info;
	dst->exit_int_info_err    = from->exit_int_info_err;
	dst->nested_ctl           = from->nested_ctl;
	dst->event_inj            = from->event_inj;
	dst->event_inj_err        = from->event_inj_err;
	dst->nested_cr3           = from->nested_cr3;
	dst->virt_ext              = from->virt_ext;
	dst->pause_filter_count   = from->pause_filter_count;
	dst->pause_filter_thresh  = from->pause_filter_thresh;
}

static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
{
	/*
	 * This function merges the msr permission bitmaps of kvm and the
	 * nested vmcb. It is optimized in that it only merges the parts where
	 * the kvm msr permission bitmap may contain zero bits
	 */
	int i;

	if (!(svm->nested.ctl.intercept & (1ULL << INTERCEPT_MSR_PROT)))
		return true;

	for (i = 0; i < MSRPM_OFFSETS; i++) {
		u32 value, p;
		u64 offset;

		if (msrpm_offsets[i] == 0xffffffff)
			break;

		p      = msrpm_offsets[i];
		offset = svm->nested.ctl.msrpm_base_pa + (p * 4);

		if (kvm_vcpu_read_guest(&svm->vcpu, offset, &value, 4))
			return false;

		svm->nested.msrpm[p] = svm->msrpm[p] | value;
	}

	svm->vmcb->control.msrpm_base_pa = __sme_set(__pa(svm->nested.msrpm));

	return true;
}

static bool nested_vmcb_check_controls(struct vmcb_control_area *control)
{
	if ((control->intercept & (1ULL << INTERCEPT_VMRUN)) == 0)
		return false;

	if (control->asid == 0)
		return false;

	if ((control->nested_ctl & SVM_NESTED_CTL_NP_ENABLE) &&
	    !npt_enabled)
		return false;

	return true;
}

static bool nested_vmcb_checks(struct vmcb *vmcb)
{
	if ((vmcb->save.efer & EFER_SVME) == 0)
		return false;

	if (((vmcb->save.cr0 & X86_CR0_CD) == 0) &&
	    (vmcb->save.cr0 & X86_CR0_NW))
		return false;

	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);

	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;
	svm->vmcb->save.ss = nested_vmcb->save.ss;
	svm->vmcb->save.ds = nested_vmcb->save.ds;
	svm->vmcb->save.gdtr = nested_vmcb->save.gdtr;
	svm->vmcb->save.idtr = nested_vmcb->save.idtr;
	kvm_set_rflags(&svm->vcpu, nested_vmcb->save.rflags);
	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);
	(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);
	kvm_rsp_write(&svm->vcpu, nested_vmcb->save.rsp);
	kvm_rip_write(&svm->vcpu, nested_vmcb->save.rip);

	/* In case we don't even reach vcpu_run, the fields are not updated */
	svm->vmcb->save.rax = nested_vmcb->save.rax;
	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->vcpu.arch.dr6  = nested_vmcb->save.dr6;
	svm->vmcb->save.cpl = nested_vmcb->save.cpl;
}

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);

	/* Guest paging mode is active - reset mmu */
	kvm_mmu_reset_context(&svm->vcpu);

	svm_flush_tlb(&svm->vcpu);

	svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset =
		svm->vcpu.arch.l1_tsc_offset + svm->nested.ctl.tsc_offset;

	svm->vmcb->control.int_ctl             =
		(svm->nested.ctl.int_ctl & ~mask) |
		(svm->nested.hsave->control.int_ctl & mask);

	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;

	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);

	/*
	 * Merge guest and host intercepts - must be called  with vcpu in
	 * guest-mode to take affect here
	 */
	recalc_intercepts(svm);

	mark_all_dirty(svm->vmcb);
}

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);

	svm_set_gif(svm, true);
}

int nested_svm_vmrun(struct vcpu_svm *svm)
{
	int ret;
	struct vmcb *nested_vmcb;
	struct vmcb *hsave = svm->nested.hsave;
	struct vmcb *vmcb = svm->vmcb;
	struct kvm_host_map map;
	u64 vmcb_gpa;

	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);
		return 1;
	} else if (ret) {
		return kvm_skip_emulated_instruction(&svm->vcpu);
	}

	ret = kvm_skip_emulated_instruction(&svm->vcpu);

	nested_vmcb = map.hva;

	if (!nested_vmcb_checks(nested_vmcb)) {
		nested_vmcb->control.exit_code    = SVM_EXIT_ERR;
		nested_vmcb->control.exit_code_hi = 0;
		nested_vmcb->control.exit_info_1  = 0;
		nested_vmcb->control.exit_info_2  = 0;
		goto out;
	}

	trace_kvm_nested_vmrun(svm->vmcb->save.rip, vmcb_gpa,
			       nested_vmcb->save.rip,
			       nested_vmcb->control.int_ctl,
			       nested_vmcb->control.event_inj,
			       nested_vmcb->control.nested_ctl);

	trace_kvm_nested_intercepts(nested_vmcb->control.intercept_cr & 0xffff,
				    nested_vmcb->control.intercept_cr >> 16,
				    nested_vmcb->control.intercept_exceptions,
				    nested_vmcb->control.intercept);

	/* Clear internal status */
	kvm_clear_exception_queue(&svm->vcpu);
	kvm_clear_interrupt_queue(&svm->vcpu);

	/*
	 * Save the old vmcb, so we don't need to pick what we save, but can
	 * restore everything when a VMEXIT occurs
	 */
	hsave->save.es     = vmcb->save.es;
	hsave->save.cs     = vmcb->save.cs;
	hsave->save.ss     = vmcb->save.ss;
	hsave->save.ds     = vmcb->save.ds;
	hsave->save.gdtr   = vmcb->save.gdtr;
	hsave->save.idtr   = vmcb->save.idtr;
	hsave->save.efer   = svm->vcpu.arch.efer;
	hsave->save.cr0    = kvm_read_cr0(&svm->vcpu);
	hsave->save.cr4    = svm->vcpu.arch.cr4;
	hsave->save.rflags = kvm_get_rflags(&svm->vcpu);
	hsave->save.rip    = kvm_rip_read(&svm->vcpu);
	hsave->save.rsp    = vmcb->save.rsp;
	hsave->save.rax    = vmcb->save.rax;
	if (npt_enabled)
		hsave->save.cr3    = vmcb->save.cr3;
	else
		hsave->save.cr3    = kvm_read_cr3(&svm->vcpu);

	copy_vmcb_control_area(&hsave->control, &vmcb->control);

	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;
		svm->vmcb->control.exit_code_hi = 0;
		svm->vmcb->control.exit_info_1  = 0;
		svm->vmcb->control.exit_info_2  = 0;

		nested_svm_vmexit(svm);
	}

out:
	kvm_vcpu_unmap(&svm->vcpu, &map, true);

	return ret;
}

void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
{
	to_vmcb->save.fs = from_vmcb->save.fs;
	to_vmcb->save.gs = from_vmcb->save.gs;
	to_vmcb->save.tr = from_vmcb->save.tr;
	to_vmcb->save.ldtr = from_vmcb->save.ldtr;
	to_vmcb->save.kernel_gs_base = from_vmcb->save.kernel_gs_base;
	to_vmcb->save.star = from_vmcb->save.star;
	to_vmcb->save.lstar = from_vmcb->save.lstar;
	to_vmcb->save.cstar = from_vmcb->save.cstar;
	to_vmcb->save.sfmask = from_vmcb->save.sfmask;
	to_vmcb->save.sysenter_cs = from_vmcb->save.sysenter_cs;
	to_vmcb->save.sysenter_esp = from_vmcb->save.sysenter_esp;
	to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip;
}

int nested_svm_vmexit(struct vcpu_svm *svm)
{
	int rc;
	struct vmcb *nested_vmcb;
	struct vmcb *hsave = svm->nested.hsave;
	struct vmcb *vmcb = svm->vmcb;
	struct kvm_host_map map;

	rc = kvm_vcpu_map(&svm->vcpu, gpa_to_gfn(svm->nested.vmcb), &map);
	if (rc) {
		if (rc == -EINVAL)
			kvm_inject_gp(&svm->vcpu, 0);
		return 1;
	}

	nested_vmcb = map.hva;

	/* 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 */
	svm_set_gif(svm, false);

	nested_vmcb->save.es     = vmcb->save.es;
	nested_vmcb->save.cs     = vmcb->save.cs;
	nested_vmcb->save.ss     = vmcb->save.ss;
	nested_vmcb->save.ds     = vmcb->save.ds;
	nested_vmcb->save.gdtr   = vmcb->save.gdtr;
	nested_vmcb->save.idtr   = vmcb->save.idtr;
	nested_vmcb->save.efer   = svm->vcpu.arch.efer;
	nested_vmcb->save.cr0    = kvm_read_cr0(&svm->vcpu);
	nested_vmcb->save.cr3    = kvm_read_cr3(&svm->vcpu);
	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    = 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    = svm->vcpu.arch.dr6;
	nested_vmcb->save.cpl    = vmcb->save.cpl;

	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;

	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;

	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;

	/* Restore the original control entries */
	copy_vmcb_control_area(&vmcb->control, &hsave->control);

	svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset =
		svm->vcpu.arch.l1_tsc_offset;

	svm->nested.ctl.nested_cr3 = 0;

	/* Restore selected save entries */
	svm->vmcb->save.es = hsave->save.es;
	svm->vmcb->save.cs = hsave->save.cs;
	svm->vmcb->save.ss = hsave->save.ss;
	svm->vmcb->save.ds = hsave->save.ds;
	svm->vmcb->save.gdtr = hsave->save.gdtr;
	svm->vmcb->save.idtr = hsave->save.idtr;
	kvm_set_rflags(&svm->vcpu, hsave->save.rflags);
	svm_set_efer(&svm->vcpu, hsave->save.efer);
	svm_set_cr0(&svm->vcpu, hsave->save.cr0 | X86_CR0_PE);
	svm_set_cr4(&svm->vcpu, hsave->save.cr4);
	if (npt_enabled) {
		svm->vmcb->save.cr3 = hsave->save.cr3;
		svm->vcpu.arch.cr3 = hsave->save.cr3;
	} else {
		(void)kvm_set_cr3(&svm->vcpu, hsave->save.cr3);
	}
	kvm_rax_write(&svm->vcpu, hsave->save.rax);
	kvm_rsp_write(&svm->vcpu, hsave->save.rsp);
	kvm_rip_write(&svm->vcpu, hsave->save.rip);
	svm->vmcb->save.dr7 = 0;
	svm->vmcb->save.cpl = 0;
	svm->vmcb->control.exit_int_info = 0;

	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);
	kvm_mmu_reset_context(&svm->vcpu);
	kvm_mmu_load(&svm->vcpu);

	/*
	 * Drop what we picked up for L2 via svm_complete_interrupts() so it
	 * doesn't end up in L1.
	 */
	svm->vcpu.arch.nmi_injected = false;
	kvm_clear_exception_queue(&svm->vcpu);
	kvm_clear_interrupt_queue(&svm->vcpu);

	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.ctl.intercept & (1ULL << INTERCEPT_MSR_PROT)))
		return NESTED_EXIT_HOST;

	msr    = svm->vcpu.arch.regs[VCPU_REGS_RCX];
	offset = svm_msrpm_offset(msr);
	write  = svm->vmcb->control.exit_info_1 & 1;
	mask   = 1 << ((2 * (msr & 0xf)) + write);

	if (offset == MSR_INVALID)
		return NESTED_EXIT_DONE;

	/* Offset is in 32 bit units but need in 8 bit units */
	offset *= 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;
}

static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
{
	unsigned port, size, iopm_len;
	u16 val, mask;
	u8 start_bit;
	u64 gpa;

	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.ctl.iopm_base_pa + (port / 8);
	start_bit = port % 8;
	iopm_len = (start_bit + size > 8) ? 2 : 1;
	mask = (0xf >> (4 - size)) << start_bit;
	val = 0;

	if (kvm_vcpu_read_guest(&svm->vcpu, gpa, &val, iopm_len))
		return NESTED_EXIT_DONE;

	return (val & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
}

static int nested_svm_intercept(struct vcpu_svm *svm)
{
	u32 exit_code = svm->vmcb->control.exit_code;
	int vmexit = NESTED_EXIT_HOST;

	switch (exit_code) {
	case SVM_EXIT_MSR:
		vmexit = nested_svm_exit_handled_msr(svm);
		break;
	case SVM_EXIT_IOIO:
		vmexit = nested_svm_intercept_ioio(svm);
		break;
	case SVM_EXIT_READ_CR0 ... SVM_EXIT_WRITE_CR8: {
		u32 bit = 1U << (exit_code - SVM_EXIT_READ_CR0);
		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.ctl.intercept_dr & bit)
			vmexit = NESTED_EXIT_DONE;
		break;
	}
	case SVM_EXIT_EXCP_BASE ... SVM_EXIT_EXCP_BASE + 0x1f: {
		/*
		 * 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: {
		vmexit = NESTED_EXIT_DONE;
		break;
	}
	default: {
		u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR);
		if (svm->nested.ctl.intercept & exit_bits)
			vmexit = NESTED_EXIT_DONE;
	}
	}

	return vmexit;
}

int nested_svm_exit_handled(struct vcpu_svm *svm)
{
	int vmexit;

	vmexit = nested_svm_intercept(svm);

	if (vmexit == NESTED_EXIT_DONE)
		nested_svm_vmexit(svm);

	return vmexit;
}

int nested_svm_check_permissions(struct vcpu_svm *svm)
{
	if (!(svm->vcpu.arch.efer & EFER_SVME) ||
	    !is_paging(&svm->vcpu)) {
		kvm_queue_exception(&svm->vcpu, UD_VECTOR);
		return 1;
	}

	if (svm->vmcb->save.cpl) {
		kvm_inject_gp(&svm->vcpu, 0);
		return 1;
	}

	return 0;
}

static bool nested_exit_on_exception(struct vcpu_svm *svm)
{
	unsigned int nr = svm->vcpu.arch.exception.nr;

	return (svm->nested.ctl.intercept_exceptions & (1 << nr));
}

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;

	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 (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);

	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(svm);
}

static inline bool nested_exit_on_init(struct vcpu_svm *svm)
{
	return (svm->nested.ctl.intercept & (1ULL << INTERCEPT_INIT));
}

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.nested_run_pending;
	struct kvm_lapic *apic = vcpu->arch.apic;

	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;
	}

	return 0;
}

int nested_svm_exit_special(struct vcpu_svm *svm)
{
	u32 exit_code = svm->vmcb->control.exit_code;

	switch (exit_code) {
	case SVM_EXIT_INTR:
	case SVM_EXIT_NMI:
	case SVM_EXIT_NPF:
		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;
		else if (exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR &&
			 svm->vcpu.arch.apf.host_apf_reason)
			/* Trap async PF even if not shadowing */
			return NESTED_EXIT_HOST;
		break;
	}
	default:
		break;
	}

	return NESTED_EXIT_CONTINUE;
}

struct kvm_x86_nested_ops svm_nested_ops = {
	.check_events = svm_check_nested_events,
};