path: root/arch/x86/kvm/svm/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 "cpuid.h"
#include "lapic.h"
#include "svm.h"

#define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK

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;

	nested_svm_vmexit(svm);
}

static void svm_inject_page_fault_nested(struct kvm_vcpu *vcpu, struct x86_exception *fault)
{
       struct vcpu_svm *svm = to_svm(vcpu);
       WARN_ON(!is_guest_mode(vcpu));

	if (vmcb12_is_intercept(&svm->nested.ctl,
				INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) &&
	    !svm->nested.nested_run_pending) {
               svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + PF_VECTOR;
               svm->vmcb->control.exit_code_hi = 0;
               svm->vmcb->control.exit_info_1 = fault->error_code;
               svm->vmcb->control.exit_info_2 = fault->address;
               nested_svm_vmexit(svm);
       } else {
               kvm_inject_page_fault(vcpu, fault);
       }
}

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(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);

	WARN_ON(mmu_is_nested(vcpu));

	vcpu->arch.mmu = &vcpu->arch.guest_mmu;

	/*
	 * The NPT format depends on L1's CR4 and EFER, which is in vmcb01.  Note,
	 * when called via KVM_SET_NESTED_STATE, that state may _not_ match current
	 * vCPU state.  CR0.WP is explicitly ignored, while CR0.PG is required.
	 */
	kvm_init_shadow_npt_mmu(vcpu, X86_CR0_PG, svm->vmcb01.ptr->save.cr4,
				svm->vmcb01.ptr->save.efer,
				svm->nested.ctl.nested_cr3);
	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.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;
	struct vmcb_ctrl_area_cached *g;
	unsigned int i;

	vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS);

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

	c = &svm->vmcb->control;
	h = &svm->vmcb01.ptr->control;
	g = &svm->nested.ctl;

	for (i = 0; i < MAX_INTERCEPT; i++)
		c->intercepts[i] = h->intercepts[i];

	if (g->int_ctl & V_INTR_MASKING_MASK) {
		/* We only want the cr8 intercept bits of L1 */
		vmcb_clr_intercept(c, INTERCEPT_CR8_READ);
		vmcb_clr_intercept(c, 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.
		 */
		vmcb_clr_intercept(c, INTERCEPT_VINTR);
	}

	/* We don't want to see VMMCALLs from a nested guest */
	vmcb_clr_intercept(c, INTERCEPT_VMMCALL);

	for (i = 0; i < MAX_INTERCEPT; i++)
		c->intercepts[i] |= g->intercepts[i];

	/* If SMI is not intercepted, ignore guest SMI intercept as well  */
	if (!intercept_smi)
		vmcb_clr_intercept(c, INTERCEPT_SMI);

	vmcb_set_intercept(c, INTERCEPT_VMLOAD);
	vmcb_set_intercept(c, INTERCEPT_VMSAVE);
}

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 (!(vmcb12_is_intercept(&svm->nested.ctl, 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;
}

/*
 * Bits 11:0 of bitmap address are ignored by hardware
 */
static bool nested_svm_check_bitmap_pa(struct kvm_vcpu *vcpu, u64 pa, u32 size)
{
	u64 addr = PAGE_ALIGN(pa);

	return kvm_vcpu_is_legal_gpa(vcpu, addr) &&
	    kvm_vcpu_is_legal_gpa(vcpu, addr + size - 1);
}

static bool nested_svm_check_tlb_ctl(struct kvm_vcpu *vcpu, u8 tlb_ctl)
{
	/* Nested FLUSHBYASID is not supported yet.  */
	switch(tlb_ctl) {
		case TLB_CONTROL_DO_NOTHING:
		case TLB_CONTROL_FLUSH_ALL_ASID:
			return true;
		default:
			return false;
	}
}

static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu,
					 struct vmcb_ctrl_area_cached *control)
{
	if (CC(!vmcb12_is_intercept(control, INTERCEPT_VMRUN)))
		return false;

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

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

	if (CC(!nested_svm_check_bitmap_pa(vcpu, control->msrpm_base_pa,
					   MSRPM_SIZE)))
		return false;
	if (CC(!nested_svm_check_bitmap_pa(vcpu, control->iopm_base_pa,
					   IOPM_SIZE)))
		return false;

	if (CC(!nested_svm_check_tlb_ctl(vcpu, control->tlb_ctl)))
		return false;

	return true;
}

/* Common checks that apply to both L1 and L2 state.  */
static bool __nested_vmcb_check_save(struct kvm_vcpu *vcpu,