KVM: nVMX: Move nested code to dedicated files

From a functional perspective, this is (supposed to be) a straight
copy-paste of code.  Code was moved piecemeal to nested.c as not all
code that could/should be moved was obviously nested-only.  The nested
code was then re-ordered as needed to compile, i.e. stats may not show
this is being a "pure" move despite there not being any intended changes
in functionality.

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

4 files changed, 5959 insertions, 5921 deletions

diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 7f3f50aaa203..83dc7d6a0294 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -16,7 +16,7 @@ kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
 			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
 			   hyperv.o page_track.o debugfs.o
 
-kvm-intel-y		+= vmx/vmx.o vmx/pmu_intel.o vmx/vmcs12.o vmx/evmcs.o
+kvm-intel-y		+= vmx/vmx.o vmx/pmu_intel.o vmx/vmcs12.o vmx/evmcs.o vmx/nested.o
 kvm-amd-y		+= svm.o pmu_amd.o
 
 obj-$(CONFIG_KVM)	+= kvm.o
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
new file mode 100644
index 000000000000..70e6d604c2a0
--- /dev/null
+++ b/arch/x86/kvm/vmx/nested.c
@@ -0,0 +1,5674 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/frame.h>
+#include <linux/percpu.h>
+
+#include <asm/debugreg.h>
+#include <asm/mmu_context.h>
+
+#include "cpuid.h"
+#include "hyperv.h"
+#include "mmu.h"
+#include "nested.h"
+#include "trace.h"
+#include "x86.h"
+
+static bool __read_mostly enable_shadow_vmcs = 1;
+module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO);
+
+static bool __read_mostly nested_early_check = 0;
+module_param(nested_early_check, bool, S_IRUGO);
+
+extern const ulong vmx_early_consistency_check_return;
+
+/*
+ * Hyper-V requires all of these, so mark them as supported even though
+ * they are just treated the same as all-context.
+ */
+#define VMX_VPID_EXTENT_SUPPORTED_MASK		\
+	(VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT |	\
+	VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |	\
+	VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT |	\
+	VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT)
+
+#define VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE 5
+
+enum {
+	VMX_VMREAD_BITMAP,
+	VMX_VMWRITE_BITMAP,
+	VMX_BITMAP_NR
+};
+static unsigned long *vmx_bitmap[VMX_BITMAP_NR];
+
+#define vmx_vmread_bitmap                    (vmx_bitmap[VMX_VMREAD_BITMAP])
+#define vmx_vmwrite_bitmap                   (vmx_bitmap[VMX_VMWRITE_BITMAP])
+
+static u16 shadow_read_only_fields[] = {
+#define SHADOW_FIELD_RO(x) x,
+#include "vmcs_shadow_fields.h"
+};
+static int max_shadow_read_only_fields =
+	ARRAY_SIZE(shadow_read_only_fields);
+
+static u16 shadow_read_write_fields[] = {
+#define SHADOW_FIELD_RW(x) x,
+#include "vmcs_shadow_fields.h"
+};
+static int max_shadow_read_write_fields =
+	ARRAY_SIZE(shadow_read_write_fields);
+
+void init_vmcs_shadow_fields(void)
+{
+	int i, j;
+
+	memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
+	memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
+
+	for (i = j = 0; i < max_shadow_read_only_fields; i++) {
+		u16 field = shadow_read_only_fields[i];
+
+		if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 &&
+		    (i + 1 == max_shadow_read_only_fields ||
+		     shadow_read_only_fields[i + 1] != field + 1))
+			pr_err("Missing field from shadow_read_only_field %x\n",
+			       field + 1);
+
+		clear_bit(field, vmx_vmread_bitmap);
+#ifdef CONFIG_X86_64
+		if (field & 1)
+			continue;
+#endif
+		if (j < i)
+			shadow_read_only_fields[j] = field;
+		j++;
+	}
+	max_shadow_read_only_fields = j;
+
+	for (i = j = 0; i < max_shadow_read_write_fields; i++) {
+		u16 field = shadow_read_write_fields[i];
+
+		if (vmcs_field_width(field) == VMCS_FIELD_WIDTH_U64 &&
+		    (i + 1 == max_shadow_read_write_fields ||
+		     shadow_read_write_fields[i + 1] != field + 1))
+			pr_err("Missing field from shadow_read_write_field %x\n",
+			       field + 1);
+
+		/*
+		 * PML and the preemption timer can be emulated, but the
+		 * processor cannot vmwrite to fields that don't exist
+		 * on bare metal.
+		 */
+		switch (field) {
+		case GUEST_PML_INDEX:
+			if (!cpu_has_vmx_pml())
+				continue;
+			break;
+		case VMX_PREEMPTION_TIMER_VALUE:
+			if (!cpu_has_vmx_preemption_timer())
+				continue;
+			break;
+		case GUEST_INTR_STATUS:
+			if (!cpu_has_vmx_apicv())
+				continue;
+			break;
+		default:
+			break;
+		}
+
+		clear_bit(field, vmx_vmwrite_bitmap);
+		clear_bit(field, vmx_vmread_bitmap);
+#ifdef CONFIG_X86_64
+		if (field & 1)
+			continue;
+#endif
+		if (j < i)
+			shadow_read_write_fields[j] = field;
+		j++;
+	}
+	max_shadow_read_write_fields = j;
+}
+
+/*
+ * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
+ * set the success or error code of an emulated VMX instruction (as specified
+ * by Vol 2B, VMX Instruction Reference, "Conventions"), and skip the emulated
+ * instruction.
+ */
+static int nested_vmx_succeed(struct kvm_vcpu *vcpu)
+{
+	vmx_set_rflags(vcpu, vmx_get_rflags(vcpu)
+			& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
+			    X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF));
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
+static int nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
+{
+	vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
+			& ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF |
+			    X86_EFLAGS_SF | X86_EFLAGS_OF))
+			| X86_EFLAGS_CF);
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
+static int nested_vmx_failValid(struct kvm_vcpu *vcpu,
+				u32 vm_instruction_error)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	/*
+	 * failValid writes the error number to the current VMCS, which
+	 * can't be done if there isn't a current VMCS.
+	 */
+	if (vmx->nested.current_vmptr == -1ull && !vmx->nested.hv_evmcs)
+		return nested_vmx_failInvalid(vcpu);
+
+	vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
+			& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
+			    X86_EFLAGS_SF | X86_EFLAGS_OF))
+			| X86_EFLAGS_ZF);
+	get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error;
+	/*
+	 * We don't need to force a shadow sync because
+	 * VM_INSTRUCTION_ERROR is not shadowed
+	 */
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
+static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator)
+{
+	/* TODO: not to reset guest simply here. */
+	kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+	pr_debug_ratelimited("kvm: nested vmx abort, indicator %d\n", indicator);
+}
+
+static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
+{
+	vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS);
+	vmcs_write64(VMCS_LINK_POINTER, -1ull);
+}
+
+static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!vmx->nested.hv_evmcs)
+		return;
+
+	kunmap(vmx->nested.hv_evmcs_page);
+	kvm_release_page_dirty(vmx->nested.hv_evmcs_page);
+	vmx->nested.hv_evmcs_vmptr = -1ull;
+	vmx->nested.hv_evmcs_page = NULL;
+	vmx->nested.hv_evmcs = NULL;
+}
+
+/*
+ * Free whatever needs to be freed from vmx->nested when L1 goes down, or
+ * just stops using VMX.
+ */
+static void free_nested(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
+		return;
+
+	vmx->nested.vmxon = false;
+	vmx->nested.smm.vmxon = false;
+	free_vpid(vmx->nested.vpid02);
+	vmx->nested.posted_intr_nv = -1;
+	vmx->nested.current_vmptr = -1ull;
+	if (enable_shadow_vmcs) {
+		vmx_disable_shadow_vmcs(vmx);
+		vmcs_clear(vmx->vmcs01.shadow_vmcs);
+		free_vmcs(vmx->vmcs01.shadow_vmcs);
+		vmx->vmcs01.shadow_vmcs = NULL;
+	}
+	kfree(vmx->nested.cached_vmcs12);
+	kfree(vmx->nested.cached_shadow_vmcs12);
+	/* Unpin physical memory we referred to in the vmcs02 */
+	if (vmx->nested.apic_access_page) {
+		kvm_release_page_dirty(vmx->nested.apic_access_page);
+		vmx->nested.apic_access_page = NULL;
+	}
+	if (vmx->nested.virtual_apic_page) {
+		kvm_release_page_dirty(vmx->nested.virtual_apic_page);
+		vmx->nested.virtual_apic_page = NULL;
+	}
+	if (vmx->nested.pi_desc_page) {
+		kunmap(vmx->nested.pi_desc_page);
+		kvm_release_page_dirty(vmx->nested.pi_desc_page);
+		vmx->nested.pi_desc_page = NULL;
+		vmx->nested.pi_desc = NULL;
+	}
+
+	kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+
+	nested_release_evmcs(vcpu);
+
+	free_loaded_vmcs(&vmx->nested.vmcs02);
+}
+
+static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int cpu;
+
+	if (vmx->loaded_vmcs == vmcs)
+		return;
+
+	cpu = get_cpu();
+	vmx_vcpu_put(vcpu);
+	vmx->loaded_vmcs = vmcs;
+	vmx_vcpu_load(vcpu, cpu);
+	put_cpu();
+
+	vm_entry_controls_reset_shadow(vmx);
+	vm_exit_controls_reset_shadow(vmx);
+	vmx_segment_cache_clear(vmx);
+}
+
+/*
+ * Ensure that the current vmcs of the logical processor is the
+ * vmcs01 of the vcpu before calling free_nested().
+ */
+void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu)
+{
+	vcpu_load(vcpu);
+	vmx_switch_vmcs(vcpu, &to_vmx(vcpu)->vmcs01);
+	free_nested(vcpu);
+	vcpu_put(vcpu);
+}
+
+static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
+		struct x86_exception *fault)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 exit_reason;
+	unsigned long exit_qualification = vcpu->arch.exit_qualification;
+
+	if (vmx->nested.pml_full) {
+		exit_reason = EXIT_REASON_PML_FULL;
+		vmx->nested.pml_full = false;
+		exit_qualification &= INTR_INFO_UNBLOCK_NMI;
+	} else if (fault->error_code & PFERR_RSVD_MASK)
+		exit_reason = EXIT_REASON_EPT_MISCONFIG;
+	else
+		exit_reason = EXIT_REASON_EPT_VIOLATION;
+
+	nested_vmx_vmexit(vcpu, exit_reason, 0, exit_qualification);
+	vmcs12->guest_physical_address = fault->address;
+}
+
+static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
+{
+	WARN_ON(mmu_is_nested(vcpu));
+
+	vcpu->arch.mmu = &vcpu->arch.guest_mmu;
+	kvm_init_shadow_ept_mmu(vcpu,
+			to_vmx(vcpu)->nested.msrs.ept_caps &
+			VMX_EPT_EXECUTE_ONLY_BIT,
+			nested_ept_ad_enabled(vcpu),
+			nested_ept_get_cr3(vcpu));
+	vcpu->arch.mmu->set_cr3           = vmx_set_cr3;
+	vcpu->arch.mmu->get_cr3           = nested_ept_get_cr3;
+	vcpu->arch.mmu->inject_page_fault = nested_ept_inject_page_fault;
+	vcpu->arch.mmu->get_pdptr         = kvm_pdptr_read;
+
+	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
+}
+
+static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.mmu = &vcpu->arch.root_mmu;
+	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
+}
+
+static bool nested_vmx_is_page_fault_vmexit(struct vmcs12 *vmcs12,
+					    u16 error_code)
+{
+	bool inequality, bit;
+
+	bit = (vmcs12->exception_bitmap & (1u << PF_VECTOR)) != 0;
+	inequality =
+		(error_code & vmcs12->page_fault_error_code_mask) !=
+		 vmcs12->page_fault_error_code_match;
+	return inequality ^ bit;
+}
+
+
+/*
+ * KVM wants to inject page-faults which it got to the guest. This function
+ * checks whether in a nested guest, we need to inject them to L1 or L2.
+ */
+static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned long *exit_qual)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	unsigned int nr = vcpu->arch.exception.nr;
+	bool has_payload = vcpu->arch.exception.has_payload;
+	unsigned long payload = vcpu->arch.exception.payload;
+
+	if (nr == PF_VECTOR) {
+		if (vcpu->arch.exception.nested_apf) {
+			*exit_qual = vcpu->arch.apf.nested_apf_token;
+			return 1;
+		}
+		if (nested_vmx_is_page_fault_vmexit(vmcs12,
+						    vcpu->arch.exception.error_code)) {
+			*exit_qual = has_payload ? payload : vcpu->arch.cr2;
+			return 1;
+		}
+	} else if (vmcs12->exception_bitmap & (1u << nr)) {
+		if (nr == DB_VECTOR) {
+			if (!has_payload) {
+				payload = vcpu->arch.dr6;
+				payload &= ~(DR6_FIXED_1 | DR6_BT);
+				payload ^= DR6_RTM;
+			}
+			*exit_qual = payload;
+		} else
+			*exit_qual = 0;
+		return 1;
+	}
+
+	return 0;
+}
+
+
+static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
+		struct x86_exception *fault)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	WARN_ON(!is_guest_mode(vcpu));
+
+	if (nested_vmx_is_page_fault_vmexit(vmcs12, fault->error_code) &&
+		!to_vmx(vcpu)->nested.nested_run_pending) {
+		vmcs12->vm_exit_intr_error_code = fault->error_code;
+		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
+				  PF_VECTOR | INTR_TYPE_HARD_EXCEPTION |
+				  INTR_INFO_DELIVER_CODE_MASK | INTR_INFO_VALID_MASK,
+				  fault->address);
+	} else {
+		kvm_inject_page_fault(vcpu, fault);
+	}
+}
+
+static bool page_address_valid(struct kvm_vcpu *vcpu, gpa_t gpa)
+{
+	return PAGE_ALIGNED(gpa) && !(gpa >> cpuid_maxphyaddr(vcpu));
+}
+
+static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu,
+					       struct vmcs12 *vmcs12)
+{
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+		return 0;
+
+	if (!page_address_valid(vcpu, vmcs12->io_bitmap_a) ||
+	    !page_address_valid(vcpu, vmcs12->io_bitmap_b))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_check_msr_bitmap_controls(struct kvm_vcpu *vcpu,
+						struct vmcs12 *vmcs12)
+{
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
+		return 0;
+
+	if (!page_address_valid(vcpu, vmcs12->msr_bitmap))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu,
+						struct vmcs12 *vmcs12)
+{
+	if (!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
+		return 0;
+
+	if (!page_address_valid(vcpu, vmcs12->virtual_apic_page_addr))
+		return -EINVAL;
+
+	return 0;
+}
+
+/*
+ * Check if MSR is intercepted for L01 MSR bitmap.
+ */
+static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr)
+{
+	unsigned long *msr_bitmap;
+	int f = sizeof(unsigned long);
+
+	if (!cpu_has_vmx_msr_bitmap())
+		return true;
+
+	msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap;
+
+	if (msr <= 0x1fff) {
+		return !!test_bit(msr, msr_bitmap + 0x800 / f);
+	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+		msr &= 0x1fff;
+		return !!test_bit(msr, msr_bitmap + 0xc00 / f);
+	}
+
+	return true;
+}
+
+/*
+ * If a msr is allowed by L0, we should check whether it is allowed by L1.
+ * The corresponding bit will be cleared unless both of L0 and L1 allow it.
+ */
+static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1,
+					       unsigned long *msr_bitmap_nested,
+					       u32 msr, int type)
+{
+	int f = sizeof(unsigned long);
+
+	/*
+	 * See Intel PRM Vol. 3, 20.6.9 (MSR-Bitmap Address). Early manuals
+	 * have the write-low and read-high bitmap offsets the wrong way round.
+	 * We can control MSRs 0x00000000-0x00001fff and 0xc0000000-0xc0001fff.
+	 */
+	if (msr <= 0x1fff) {
+		if (type & MSR_TYPE_R &&
+		   !test_bit(msr, msr_bitmap_l1 + 0x000 / f))
+			/* read-low */
+			__clear_bit(msr, msr_bitmap_nested + 0x000 / f);
+
+		if (type & MSR_TYPE_W &&
+		   !test_bit(msr, msr_bitmap_l1 + 0x800 / f))
+			/* write-low */
+			__clear_bit(msr, msr_bitmap_nested + 0x800 / f);
+
+	} else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) {
+		msr &= 0x1fff;
+		if (type & MSR_TYPE_R &&
+		   !test_bit(msr, msr_bitmap_l1 + 0x400 / f))
+			/* read-high */
+			__clear_bit(msr, msr_bitmap_nested + 0x400 / f);
+
+		if (type & MSR_TYPE_W &&
+		   !test_bit(msr, msr_bitmap_l1 + 0xc00 / f))
+			/* write-high */
+			__clear_bit(msr, msr_bitmap_nested + 0xc00 / f);
+
+	}
+}
+
+/*
+ * Merge L0's and L1's MSR bitmap, return false to indicate that
+ * we do not use the hardware.
+ */
+static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
+						 struct vmcs12 *vmcs12)
+{
+	int msr;
+	struct page *page;
+	unsigned long *msr_bitmap_l1;
+	unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap;
+	/*
+	 * pred_cmd & spec_ctrl are trying to verify two things:
+	 *
+	 * 1. L0 gave a permission to L1 to actually passthrough the MSR. This
+	 *    ensures that we do not accidentally generate an L02 MSR bitmap
+	 *    from the L12 MSR bitmap that is too permissive.
+	 * 2. That L1 or L2s have actually used the MSR. This avoids
+	 *    unnecessarily merging of the bitmap if the MSR is unused. This
+	 *    works properly because we only update the L01 MSR bitmap lazily.
+	 *    So even if L0 should pass L1 these MSRs, the L01 bitmap is only
+	 *    updated to reflect this when L1 (or its L2s) actually write to
+	 *    the MSR.
+	 */
+	bool pred_cmd = !msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD);
+	bool spec_ctrl = !msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL);
+
+	/* Nothing to do if the MSR bitmap is not in use.  */
+	if (!cpu_has_vmx_msr_bitmap() ||
+	    !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
+		return false;
+
+	if (!nested_cpu_has_virt_x2apic_mode(vmcs12) &&
+	    !pred_cmd && !spec_ctrl)
+		return false;
+
+	page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->msr_bitmap);
+	if (is_error_page(page))
+		return false;
+
+	msr_bitmap_l1 = (unsigned long *)kmap(page);
+	if (nested_cpu_has_apic_reg_virt(vmcs12)) {
+		/*
+		 * L0 need not intercept reads for MSRs between 0x800 and 0x8ff, it
+		 * just lets the processor take the value from the virtual-APIC page;
+		 * take those 256 bits directly from the L1 bitmap.
+		 */
+		for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+			unsigned word = msr / BITS_PER_LONG;
+			msr_bitmap_l0[word] = msr_bitmap_l1[word];
+			msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
+		}
+	} else {
+		for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+			unsigned word = msr / BITS_PER_LONG;
+			msr_bitmap_l0[word] = ~0;
+			msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
+		}
+	}
+
+	nested_vmx_disable_intercept_for_msr(
+		msr_bitmap_l1, msr_bitmap_l0,
+		X2APIC_MSR(APIC_TASKPRI),
+		MSR_TYPE_W);
+
+	if (nested_cpu_has_vid(vmcs12)) {
+		nested_vmx_disable_intercept_for_msr(
+			msr_bitmap_l1, msr_bitmap_l0,
+			X2APIC_MSR(APIC_EOI),
+			MSR_TYPE_W);
+		nested_vmx_disable_intercept_for_msr(
+			msr_bitmap_l1, msr_bitmap_l0,
+			X2APIC_MSR(APIC_SELF_IPI),
+			MSR_TYPE_W);
+	}
+
+	if (spec_ctrl)
+		nested_vmx_disable_intercept_for_msr(
+					msr_bitmap_l1, msr_bitmap_l0,
+					MSR_IA32_SPEC_CTRL,
+					MSR_TYPE_R | MSR_TYPE_W);
+
+	if (pred_cmd)
+		nested_vmx_disable_intercept_for_msr(
+					msr_bitmap_l1, msr_bitmap_l0,
+					MSR_IA32_PRED_CMD,
+					MSR_TYPE_W);
+
+	kunmap(page);
+	kvm_release_page_clean(page);
+
+	return true;
+}
+
+static void nested_cache_shadow_vmcs12(struct kvm_vcpu *vcpu,
+				       struct vmcs12 *vmcs12)
+{
+	struct vmcs12 *shadow;
+	struct page *page;
+
+	if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
+	    vmcs12->vmcs_link_pointer == -1ull)
+		return;
+
+	shadow = get_shadow_vmcs12(vcpu);
+	page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->vmcs_link_pointer);
+
+	memcpy(shadow, kmap(page), VMCS12_SIZE);
+
+	kunmap(page);
+	kvm_release_page_clean(page);
+}
+
+static void nested_flush_cached_shadow_vmcs12(struct kvm_vcpu *vcpu,
+					      struct vmcs12 *vmcs12)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!nested_cpu_has_shadow_vmcs(vmcs12) ||
+	    vmcs12->vmcs_link_pointer == -1ull)
+		return;
+
+	kvm_write_guest(vmx->vcpu.kvm, vmcs12->vmcs_link_pointer,
+			get_shadow_vmcs12(vcpu), VMCS12_SIZE);
+}
+
+/*
+ * In nested virtualization, check if L1 has set
+ * VM_EXIT_ACK_INTR_ON_EXIT
+ */
+static bool nested_exit_intr_ack_set(struct kvm_vcpu *vcpu)
+{
+	return get_vmcs12(vcpu)->vm_exit_controls &
+		VM_EXIT_ACK_INTR_ON_EXIT;
+}
+
+static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu)
+{
+	return nested_cpu_has_nmi_exiting(get_vmcs12(vcpu));
+}
+
+static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu,
+					  struct vmcs12 *vmcs12)
+{
+	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
+	    !page_address_valid(vcpu, vmcs12->apic_access_addr))
+		return -EINVAL;
+	else
+		return 0;
+}
+
+static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
+					   struct vmcs12 *vmcs12)
+{
+	if (!nested_cpu_has_virt_x2apic_mode(vmcs12) &&
+	    !nested_cpu_has_apic_reg_virt(vmcs12) &&
+	    !nested_cpu_has_vid(vmcs12) &&
+	    !nested_cpu_has_posted_intr(vmcs12))
+		return 0;
+
+	/*
+	 * If virtualize x2apic mode is enabled,
+	 * virtualize apic access must be disabled.
+	 */
+	if (nested_cpu_has_virt_x2apic_mode(vmcs12) &&
+	    nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
+		return -EINVAL;
+
+	/*
+	 * If virtual interrupt delivery is enabled,
+	 * we must exit on external interrupts.
+	 */
+	if (nested_cpu_has_vid(vmcs12) &&
+	   !nested_exit_on_intr(vcpu))
+		return -EINVAL;
+
+	/*
+	 * bits 15:8 should be zero in posted_intr_nv,
+	 * the descriptor address has been already checked
+	 * in nested_get_vmcs12_pages.
+	 *
+	 * bits 5:0 of posted_intr_desc_addr should be zero.
+	 */
+	if (nested_cpu_has_posted_intr(vmcs12) &&
+	   (!nested_cpu_has_vid(vmcs12) ||
+	    !nested_exit_intr_ack_set(vcpu) ||
+	    (vmcs12->posted_intr_nv & 0xff00) ||
+	    (vmcs12->posted_intr_desc_addr & 0x3f) ||
+	    (vmcs12->posted_intr_desc_addr >> cpuid_maxphyaddr(vcpu))))
+		return -EINVAL;
+
+	/* tpr shadow is needed by all apicv features. */
+	if (!nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu,
+				       unsigned long count_field,
+				       unsigned long addr_field)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+	int maxphyaddr;
+	u64 count, addr;
+
+	if (vmcs12_read_any(vmcs12, count_field, &count) ||
+	    vmcs12_read_any(vmcs12, addr_field, &addr)) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+	if (count == 0)
+		return 0;
+	maxphyaddr = cpuid_maxphyaddr(vcpu);
+	if (!IS_ALIGNED(addr, 16) || addr >> maxphyaddr ||
+	    (addr + count * sizeof(struct vmx_msr_entry) - 1) >> maxphyaddr) {
+		pr_debug_ratelimited(
+			"nVMX: invalid MSR switch (0x%lx, %d, %llu, 0x%08llx)",
+			addr_field, maxphyaddr, count, addr);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int nested_vmx_check_msr_switch_controls(struct kvm_vcpu *vcpu,
+						struct vmcs12 *vmcs12)
+{
+	if (vmcs12->vm_exit_msr_load_count == 0 &&
+	    vmcs12->vm_exit_msr_store_count == 0 &&
+	    vmcs12->vm_entry_msr_load_count == 0)
+		return 0; /* Fast path */
+	if (nested_vmx_check_msr_switch(vcpu, VM_EXIT_MSR_LOAD_COUNT,
+					VM_EXIT_MSR_LOAD_ADDR) ||
+	    nested_vmx_check_msr_switch(vcpu, VM_EXIT_MSR_STORE_COUNT,
+					VM_EXIT_MSR_STORE_ADDR) ||
+	    nested_vmx_check_msr_switch(vcpu, VM_ENTRY_MSR_LOAD_COUNT,
+					VM_ENTRY_MSR_LOAD_ADDR))
+		return -EINVAL;
+	return 0;
+}
+
+static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu,
+					 struct vmcs12 *vmcs12)
+{
+	if (!nested_cpu_has_pml(vmcs12))
+		return 0;
+
+	if (!nested_cpu_has_ept(vmcs12) ||
+	    !page_address_valid(vcpu, vmcs12->pml_address))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_check_unrestricted_guest_controls(struct kvm_vcpu *vcpu,
+							struct vmcs12 *vmcs12)
+{
+	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST) &&
+	    !nested_cpu_has_ept(vmcs12))
+		return -EINVAL;
+	return 0;
+}
+
+static int nested_vmx_check_mode_based_ept_exec_controls(struct kvm_vcpu *vcpu,
+							 struct vmcs12 *vmcs12)
+{
+	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_MODE_BASED_EPT_EXEC) &&
+	    !nested_cpu_has_ept(vmcs12))
+		return -EINVAL;
+	return 0;
+}
+
+static int nested_vmx_check_shadow_vmcs_controls(struct kvm_vcpu *vcpu,
+						 struct vmcs12 *vmcs12)
+{
+	if (!nested_cpu_has_shadow_vmcs(vmcs12))
+		return 0;
+
+	if (!page_address_valid(vcpu, vmcs12->vmread_bitmap) ||
+	    !page_address_valid(vcpu, vmcs12->vmwrite_bitmap))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu,
+				       struct vmx_msr_entry *e)
+{
+	/* x2APIC MSR accesses are not allowed */
+	if (vcpu->arch.apic_base & X2APIC_ENABLE && e->index >> 8 == 0x8)
+		return -EINVAL;
+	if (e->index == MSR_IA32_UCODE_WRITE || /* SDM Table 35-2 */
+	    e->index == MSR_IA32_UCODE_REV)
+		return -EINVAL;
+	if (e->reserved != 0)
+		return -EINVAL;
+	return 0;
+}
+
+static int nested_vmx_load_msr_check(struct kvm_vcpu *vcpu,
+				     struct vmx_msr_entry *e)
+{
+	if (e->index == MSR_FS_BASE ||
+	    e->index == MSR_GS_BASE ||
+	    e->index == MSR_IA32_SMM_MONITOR_CTL || /* SMM is not supported */
+	    nested_vmx_msr_check_common(vcpu, e))
+		return -EINVAL;
+	return 0;
+}
+
+static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu,
+				      struct vmx_msr_entry *e)
+{
+	if (e->index == MSR_IA32_SMBASE || /* SMM is not supported */
+	    nested_vmx_msr_check_common(vcpu, e))
+		return -EINVAL;
+	return 0;
+}
+
+/*
+ * Load guest's/host's msr at nested entry/exit.
+ * return 0 for success, entry index for failure.
+ */
+static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
+{
+	u32 i;
+	struct vmx_msr_entry e;
+	struct msr_data msr;
+
+	msr.host_initiated = false;
+	for (i = 0; i < count; i++) {
+		if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e),
+					&e, sizeof(e))) {
+			pr_debug_ratelimited(
+				"%s cannot read MSR entry (%u, 0x%08llx)\n",
+				__func__, i, gpa + i * sizeof(e));
+			goto fail;
+		}
+		if (nested_vmx_load_msr_check(vcpu, &e)) {
+			pr_debug_ratelimited(
+				"%s check failed (%u, 0x%x, 0x%x)\n",
+				__func__, i, e.index, e.reserved);
+			goto fail;
+		}
+		msr.index = e.index;
+		msr.data = e.value;
+		if (kvm_set_msr(vcpu, &msr)) {
+			pr_debug_ratelimited(
+				"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
+				__func__, i, e.index, e.value);
+			goto fail;
+		}
+	}
+	return 0;
+fail:
+	return i + 1;
+}
+
+static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
+{
+	u32 i;
+	struct vmx_msr_entry e;
+
+	for (i = 0; i < count; i++) {
+		struct msr_data msr_info;
+		if (kvm_vcpu_read_guest(vcpu,
+					gpa + i * sizeof(e),
+					&e, 2 * sizeof(u32))) {
+			pr_debug_ratelimited(
+				"%s cannot read MSR entry (%u, 0x%08llx)\n",
+				__func__, i, gpa + i * sizeof(e));
+			return -EINVAL;
+		}
+		if (nested_vmx_store_msr_check(vcpu, &e)) {
+			pr_debug_ratelimited(
+				"%s check failed (%u, 0x%x, 0x%x)\n",
+				__func__, i, e.index, e.reserved);
+			return -EINVAL;
+		}
+		msr_info.host_initiated = false;
+		msr_info.index = e.index;
+		if (kvm_get_msr(vcpu, &msr_info)) {
+			pr_debug_ratelimited(
+				"%s cannot read MSR (%u, 0x%x)\n",
+				__func__, i, e.index);
+			return -EINVAL;
+		}
+		if (kvm_vcpu_write_guest(vcpu,
+					 gpa + i * sizeof(e) +
+					     offsetof(struct vmx_msr_entry, value),
+					 &msr_info.data, sizeof(msr_info.data))) {
+			pr_debug_ratelimited(
+				"%s cannot write MSR (%u, 0x%x, 0x%llx)\n",
+				__func__, i, e.index, msr_info.data);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val)
+{
+	unsigned long invalid_mask;
+
+	invalid_mask = (~0ULL) << cpuid_maxphyaddr(vcpu);
+	return (val & invalid_mask) == 0;
+}
+
+/*
+ * Load guest's/host's cr3 at nested entry/exit. nested_ept is true if we are
+ * emulating VM entry into a guest with EPT enabled.
+ * Returns 0 on success, 1 on failure. Invalid state exit qualification code
+ * is assigned to entry_failure_code on failure.
+ */
+static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept,
+			       u32 *entry_failure_code)
+{
+	if (cr3 != kvm_read_cr3(vcpu) || (!nested_ept && pdptrs_changed(vcpu))) {
+		if (!nested_cr3_valid(vcpu, cr3)) {
+			*entry_failure_code = ENTRY_FAIL_DEFAULT;
+			return 1;
+		}
+
+		/*
+		 * If PAE paging and EPT are both on, CR3 is not used by the CPU and
+		 * must not be dereferenced.
+		 */
+		if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu) &&
+		    !nested_ept) {
+			if (!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) {
+				*entry_failure_code = ENTRY_FAIL_PDPTE;
+				return 1;
+			}
+		}
+	}
+
+	if (!nested_ept)
+		kvm_mmu_new_cr3(vcpu, cr3, false);
+
+	vcpu->arch.cr3 = cr3;
+	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+
+	kvm_init_mmu(vcpu, false);
+
+	return 0;
+}
+
+/*
+ * Returns if KVM is able to config CPU to tag TLB entries
+ * populated by L2 differently than TLB entries populated
+ * by L1.
+ *
+ * If L1 uses EPT, then TLB entries are tagged with different EPTP.
+ *
+ * If L1 uses VPID and we allocated a vpid02, TLB entries are tagged
+ * with different VPID (L1 entries are tagged with vmx->vpid
+ * while L2 entries are tagged with vmx->nested.vpid02).
+ */
+static bool nested_has_guest_tlb_tag(struct kvm_vcpu *vcpu)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	return nested_cpu_has_ept(vmcs12) ||
+	       (nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02);
+}
+
+static u16 nested_get_vpid02(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	return vmx->nested.vpid02 ? vmx->nested.vpid02 : vmx->vpid;
+}
+
+
+static inline bool vmx_control_verify(u32 control, u32 low, u32 high)
+{
+	return fixed_bits_valid(control, low, high);
+}
+
+static inline u64 vmx_control_msr(u32 low, u32 high)
+{
+	return low | ((u64)high << 32);
+}
+
+static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask)
+{
+	superset &= mask;
+	subset &= mask;
+
+	return (superset | subset) == superset;
+}
+
+static int vmx_restore_vmx_basic(struct vcpu_vmx *vmx, u64 data)
+{
+	const u64 feature_and_reserved =
+		/* feature (except bit 48; see below) */
+		BIT_ULL(49) | BIT_ULL(54) | BIT_ULL(55) |
+		/* reserved */
+		BIT_ULL(31) | GENMASK_ULL(47, 45) | GENMASK_ULL(63, 56);
+	u64 vmx_basic = vmx->nested.msrs.basic;
+
+	if (!is_bitwise_subset(vmx_basic, data, feature_and_reserved))
+		return -EINVAL;
+
+	/*
+	 * KVM does not emulate a version of VMX that constrains physical
+	 * addresses of VMX structures (e.g. VMCS) to 32-bits.
+	 */
+	if (data & BIT_ULL(48))
+		return -EINVAL;
+
+	if (vmx_basic_vmcs_revision_id(vmx_basic) !=
+	    vmx_basic_vmcs_revision_id(data))
+		return -EINVAL;
+
+	if (vmx_basic_vmcs_size(vmx_basic) > vmx_basic_vmcs_size(data))
+		return -EINVAL;
+
+	vmx->nested.msrs.basic = data;
+	return 0;
+}
+
+static int
+vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
+{
+	u64 supported;
+	u32 *lowp, *highp;
+
+	switch (msr_index) {
+	case MSR_IA32_VMX_TRUE_PINBASED_CTLS:
+		lowp = &vmx->nested.msrs.pinbased_ctls_low;
+		highp = &vmx->nested.msrs.pinbased_ctls_high;
+		break;
+	case MSR_IA32_VMX_TRUE_PROCBASED_CTLS:
+		lowp = &vmx->nested.msrs.procbased_ctls_low;
+		highp = &vmx->nested.msrs.procbased_ctls_high;
+		break;
+	case MSR_IA32_VMX_TRUE_EXIT_CTLS:
+		lowp = &vmx->nested.msrs.exit_ctls_low;
+		highp = &vmx->nested.msrs.exit_ctls_high;
+		break;
+	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
+		lowp = &vmx->nested.msrs.entry_ctls_low;
+		highp = &vmx->nested.msrs.entry_ctls_high;
+		break;
+	case MSR_IA32_VMX_PROCBASED_CTLS2:
+		lowp = &vmx->nested.msrs.secondary_ctls_low;
+		highp = &vmx->nested.msrs.secondary_ctls_high;
+		break;
+	default:
+		BUG();
+	}
+
+	supported = vmx_control_msr(*lowp, *highp);
+
+	/* Check must-be-1 bits are still 1. */
+	if (!is_bitwise_subset(data, supported, GENMASK_ULL(31, 0)))
+		return -EINVAL;
+
+	/* Check must-be-0 bits are still 0. */
+	if (!is_bitwise_subset(supported, data, GENMASK_ULL(63, 32)))
+		return -EINVAL;
+
+	*lowp = data;
+	*highp = data >> 32;
+	return 0;
+}
+
+static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data)
+{
+	const u64 feature_and_reserved_bits =
+		/* feature */
+		BIT_ULL(5) | GENMASK_ULL(8, 6) | BIT_ULL(14) | BIT_ULL(15) |
+		BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30) |
+		/* reserved */
+		GENMASK_ULL(13, 9) | BIT_ULL(31);
+	u64 vmx_misc;
+
+	vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low,
+				   vmx->nested.msrs.misc_high);
+
+	if (!is_bitwise_subset(vmx_misc, data, feature_and_reserved_bits))
+		return -EINVAL;
+
+	if ((vmx->nested.msrs.pinbased_ctls_high &
+	     PIN_BASED_VMX_PREEMPTION_TIMER) &&
+	    vmx_misc_preemption_timer_rate(data) !=
+	    vmx_misc_preemption_timer_rate(vmx_misc))
+		return -EINVAL;
+
+	if (vmx_misc_cr3_count(data) > vmx_misc_cr3_count(vmx_misc))
+		return -EINVAL;
+
+	if (vmx_misc_max_msr(data) > vmx_misc_max_msr(vmx_misc))
+		return -EINVAL;
+
+	if (vmx_misc_mseg_revid(data) != vmx_misc_mseg_revid(vmx_misc))
+		return -EINVAL;
+
+	vmx->nested.msrs.misc_low = data;
+	vmx->neste