1 files changed, 100 insertions, 47 deletions

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 9c941535f78c..ba34e94049c7 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -7,6 +7,7 @@
 #include <asm/mmu_context.h>
 
 #include "cpuid.h"
+#include "evmcs.h"
 #include "hyperv.h"
 #include "mmu.h"
 #include "nested.h"
@@ -245,7 +246,8 @@ static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
 	src = &prev->host_state;
 	dest = &vmx->loaded_vmcs->host_state;
 
-	vmx_set_host_fs_gs(dest, src->fs_sel, src->gs_sel, src->fs_base, src->gs_base);
+	vmx_set_vmcs_host_state(dest, src->cr3, src->fs_sel, src->gs_sel,
+				src->fs_base, src->gs_base);
 	dest->ldt_sel = src->ldt_sel;
 #ifdef CONFIG_X86_64
 	dest->ds_sel = src->ds_sel;
@@ -269,7 +271,13 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
 	vmx_sync_vmcs_host_state(vmx, prev);
 	put_cpu();
 
-	vmx_register_cache_reset(vcpu);
+	vcpu->arch.regs_avail = ~VMX_REGS_LAZY_LOAD_SET;
+
+	/*
+	 * All lazily updated registers will be reloaded from VMCS12 on both
+	 * vmentry and vmexit.
+	 */
+	vcpu->arch.regs_dirty = 0;
 }
 
 /*
@@ -391,9 +399,11 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
 
 static void nested_ept_new_eptp(struct kvm_vcpu *vcpu)
 {
-	kvm_init_shadow_ept_mmu(vcpu,
-				to_vmx(vcpu)->nested.msrs.ept_caps &
-				VMX_EPT_EXECUTE_ONLY_BIT,
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	bool execonly = vmx->nested.msrs.ept_caps & VMX_EPT_EXECUTE_ONLY_BIT;
+	int ept_lpage_level = ept_caps_to_lpage_level(vmx->nested.msrs.ept_caps);
+
+	kvm_init_shadow_ept_mmu(vcpu, execonly, ept_lpage_level,
 				nested_ept_ad_enabled(vcpu),
 				nested_ept_get_eptp(vcpu));
 }
@@ -591,6 +601,7 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	int msr;
 	unsigned long *msr_bitmap_l1;
 	unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap;
+	struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
 	struct kvm_host_map *map = &vmx->nested.msr_bitmap_map;
 
 	/* Nothing to do if the MSR bitmap is not in use.  */
@@ -598,6 +609,19 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	    !nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
 		return false;
 
+	/*
+	 * MSR bitmap update can be skipped when:
+	 * - MSR bitmap for L1 hasn't changed.
+	 * - Nested hypervisor (L1) is attempting to launch the same L2 as
+	 *   before.
+	 * - Nested hypervisor (L1) has enabled 'Enlightened MSR Bitmap' feature
+	 *   and tells KVM (L0) there were no changes in MSR bitmap for L2.
+	 */
+	if (!vmx->nested.force_msr_bitmap_recalc && evmcs &&
+	    evmcs->hv_enlightenments_control.msr_bitmap &&
+	    evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP)
+		return true;
+
 	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map))
 		return false;
 
@@ -664,6 +688,8 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 
 	kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false);
 
+	vmx->nested.force_msr_bitmap_recalc = false;
+
 	return true;
 }
 
@@ -1095,7 +1121,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3,
 	 * must not be dereferenced.
 	 */
 	if (reload_pdptrs && !nested_ept && is_pae_paging(vcpu) &&
-	    CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) {
+	    CC(!load_pdptrs(vcpu, cr3))) {
 		*entry_failure_code = ENTRY_FAIL_PDPTE;
 		return -EINVAL;
 	}
@@ -1104,7 +1130,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3,
 		kvm_mmu_new_pgd(vcpu, cr3);
 
 	vcpu->arch.cr3 = cr3;
-	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
+	kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3);
 
 	/* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */
 	kvm_init_mmu(vcpu);
@@ -2021,10 +2047,13 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld(
 	 * Clean fields data can't be used on VMLAUNCH and when we switch
 	 * between different L2 guests as KVM keeps a single VMCS12 per L1.
 	 */
-	if (from_launch || evmcs_gpa_changed)
+	if (from_launch || evmcs_gpa_changed) {
 		vmx->nested.hv_evmcs->hv_clean_fields &=
 			~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
 
+		vmx->nested.force_msr_bitmap_recalc = true;
+	}
+
 	return EVMPTRLD_SUCCEEDED;
 }
 
@@ -3027,7 +3056,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long cr3, cr4;
+	unsigned long cr4;
 	bool vm_fail;
 
 	if (!nested_early_check)
@@ -3050,12 +3079,6 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 	 */
 	vmcs_writel(GUEST_RFLAGS, 0);
 
-	cr3 = __get_current_cr3_fast();
-	if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
-		vmcs_writel(HOST_CR3, cr3);
-		vmx->loaded_vmcs->host_state.cr3 = cr3;
-	}
-
 	cr4 = cr4_read_shadow();
 	if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
 		vmcs_writel(HOST_CR4, cr4);
@@ -3145,7 +3168,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 		 * the guest CR3 might be restored prior to setting the nested
 		 * state which can lead to a load of wrong PDPTRs.
 		 */
-		if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3)))
+		if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3)))
 			return false;
 	}
 
@@ -3504,10 +3527,13 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	if (evmptrld_status == EVMPTRLD_ERROR) {
 		kvm_queue_exception(vcpu, UD_VECTOR);
 		return 1;
-	} else if (CC(evmptrld_status == EVMPTRLD_VMFAIL)) {
-		return nested_vmx_failInvalid(vcpu);
 	}
 
+	kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_BRANCH_INSTRUCTIONS);
+
+	if (CC(evmptrld_status == EVMPTRLD_VMFAIL))
+		return nested_vmx_failInvalid(vcpu);
+
 	if (CC(!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) &&
 	       vmx->nested.current_vmptr == INVALID_GPA))
 		return nested_vmx_failInvalid(vcpu);
@@ -3603,7 +3629,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		    !(nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING) &&
 		      (vmcs12->guest_rflags & X86_EFLAGS_IF))) {
 			vmx->nested.nested_run_pending = 0;
-			return kvm_vcpu_halt(vcpu);
+			return kvm_emulate_halt_noskip(vcpu);
 		}
 		break;
 	case GUEST_ACTIVITY_WAIT_SIPI:
@@ -4826,18 +4852,20 @@ static struct vmcs *alloc_shadow_vmcs(struct kvm_vcpu *vcpu)
 	struct loaded_vmcs *loaded_vmcs = vmx->loaded_vmcs;
 
 	/*
-	 * We should allocate a shadow vmcs for vmcs01 only when L1
-	 * executes VMXON and free it when L1 executes VMXOFF.
-	 * As it is invalid to execute VMXON twice, we shouldn't reach
-	 * here when vmcs01 already have an allocated shadow vmcs.
+	 * KVM allocates a shadow VMCS only when L1 executes VMXON and frees it
+	 * when L1 executes VMXOFF or the vCPU is forced out of nested
+	 * operation.  VMXON faults if the CPU is already post-VMXON, so it
+	 * should be impossible to already have an allocated shadow VMCS.  KVM
+	 * doesn't support virtualization of VMCS shadowing, so vmcs01 should
+	 * always be the loaded VMCS.
 	 */
-	WARN_ON(loaded_vmcs == &vmx->vmcs01 && loaded_vmcs->shadow_vmcs);
+	if (WARN_ON(loaded_vmcs != &vmx->vmcs01 || loaded_vmcs->shadow_vmcs))
+		return loaded_vmcs->shadow_vmcs;
+
+	loaded_vmcs->shadow_vmcs = alloc_vmcs(true);
+	if (loaded_vmcs->shadow_vmcs)
+		vmcs_clear(loaded_vmcs->shadow_vmcs);
 
-	if (!loaded_vmcs->shadow_vmcs) {
-		loaded_vmcs->shadow_vmcs = alloc_vmcs(true);
-		if (loaded_vmcs->shadow_vmcs)
-			vmcs_clear(loaded_vmcs->shadow_vmcs);
-	}
 	return loaded_vmcs->shadow_vmcs;
 }
 
@@ -5074,27 +5102,49 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
 
-	/*
-	 * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA,
-	 * any VMREAD sets the ALU flags for VMfailInvalid.
-	 */
-	if (vmx->nested.current_vmptr == INVALID_GPA ||
-	    (is_guest_mode(vcpu) &&
-	     get_vmcs12(vcpu)->vmcs_link_pointer == INVALID_GPA))
-		return nested_vmx_failInvalid(vcpu);
-
 	/* Decode instruction info and find the field to read */
 	field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf));
 
-	offset = vmcs_field_to_offset(field);
-	if (offset < 0)
-		return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
+	if (!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) {
+		/*
+		 * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA,
+		 * any VMREAD sets the ALU flags for VMfailInvalid.
+		 */
+		if (vmx->nested.current_vmptr == INVALID_GPA ||
+		    (is_guest_mode(vcpu) &&
+		     get_vmcs12(vcpu)->vmcs_link_pointer == INVALID_GPA))
+			return nested_vmx_failInvalid(vcpu);
 
-	if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field))
-		copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
+		offset = get_vmcs12_field_offset(field);
+		if (offset < 0)
+			return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
+
+		if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field))
+			copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
+
+		/* Read the field, zero-extended to a u64 value */
+		value = vmcs12_read_any(vmcs12, field, offset);
+	} else {
+		/*
+		 * Hyper-V TLFS (as of 6.0b) explicitly states, that while an
+		 * enlightened VMCS is active VMREAD/VMWRITE instructions are
+		 * unsupported. Unfortunately, certain versions of Windows 11
+		 * don't comply with this requirement which is not enforced in
+		 * genuine Hyper-V. Allow VMREAD from an enlightened VMCS as a
+		 * workaround, as misbehaving guests will panic on VM-Fail.
+		 * Note, enlightened VMCS is incompatible with shadow VMCS so
+		 * all VMREADs from L2 should go to L1.
+		 */
+		if (WARN_ON_ONCE(is_guest_mode(vcpu)))
+			return nested_vmx_failInvalid(vcpu);
 
-	/* Read the field, zero-extended to a u64 value */
-	value = vmcs12_read_any(vmcs12, field, offset);
+		offset = evmcs_field_offset(field, NULL);
+		if (offset < 0)
+			return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
+
+		/* Read the field, zero-extended to a u64 value */
+		value = evmcs_read_any(vmx->nested.hv_evmcs, field, offset);
+	}
 
 	/*
 	 * Now copy part of this value to register or memory, as requested.
@@ -5189,7 +5239,7 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu)
 
 	field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf));
 
-	offset = vmcs_field_to_offset(field);
+	offset = get_vmcs12_field_offset(field);
 	if (offset < 0)
 		return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
 
@@ -5258,6 +5308,7 @@ static void set_current_vmptr(struct vcpu_vmx *vmx, gpa_t vmptr)
 		vmx->nested.need_vmcs12_to_shadow_sync = true;
 	}
 	vmx->nested.dirty_vmcs12 = true;
+	vmx->nested.force_msr_bitmap_recalc = true;
 }
 
 /* Emulate the VMPTRLD instruction */
@@ -6393,6 +6444,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 		goto error_guest_mode;
 
 	vmx->nested.dirty_vmcs12 = true;
+	vmx->nested.force_msr_bitmap_recalc = true;
 	ret = nested_vmx_enter_non_root_mode(vcpu, false);
 	if (ret)
 		goto error_guest_mode;
@@ -6435,7 +6487,7 @@ static u64 nested_vmx_calc_vmcs_enum_msr(void)
 	max_idx = 0;
 	for (i = 0; i < nr_vmcs12_fields; i++) {
 		/* The vmcs12 table is very, very sparsely populated. */
-		if (!vmcs_field_to_offset_table[i])
+		if (!vmcs12_field_offsets[i])
 			continue;
 
 		idx = vmcs_field_index(VMCS12_IDX_TO_ENC(i));
@@ -6744,6 +6796,7 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
 }
 
 struct kvm_x86_nested_ops vmx_nested_ops = {
+	.leave_nested = vmx_leave_nested,
 	.check_events = vmx_check_nested_events,
 	.hv_timer_pending = nested_vmx_preemption_timer_pending,
 	.triple_fault = nested_vmx_triple_fault,