1 files changed, 52 insertions, 35 deletions

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index d268224227f0..b8ea1969113d 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -276,7 +276,7 @@ static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
 {
 	struct vmcs_host_state *dest, *src;
 
-	if (unlikely(!vmx->guest_state_loaded))
+	if (unlikely(!vmx->vt.guest_state_loaded))
 		return;
 
 	src = &prev->host_state;
@@ -302,7 +302,7 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
 	cpu = get_cpu();
 	prev = vmx->loaded_vmcs;
 	vmx->loaded_vmcs = vmcs;
-	vmx_vcpu_load_vmcs(vcpu, cpu, prev);
+	vmx_vcpu_load_vmcs(vcpu, cpu);
 	vmx_sync_vmcs_host_state(vmx, prev);
 	put_cpu();
 
@@ -426,7 +426,7 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
 		 * tables also changed, but KVM should not treat EPT Misconfig
 		 * VM-Exits as writes.
 		 */
-		WARN_ON_ONCE(vmx->exit_reason.basic != EXIT_REASON_EPT_VIOLATION);
+		WARN_ON_ONCE(vmx->vt.exit_reason.basic != EXIT_REASON_EPT_VIOLATION);
 
 		/*
 		 * PML Full and EPT Violation VM-Exits both use bit 12 to report
@@ -715,6 +715,12 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
 					 MSR_IA32_FLUSH_CMD, MSR_TYPE_W);
 
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_IA32_APERF, MSR_TYPE_R);
+
+	nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+					 MSR_IA32_MPERF, MSR_TYPE_R);
+
 	kvm_vcpu_unmap(vcpu, &map);
 
 	vmx->nested.force_msr_bitmap_recalc = false;
@@ -825,12 +831,30 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low,
+				       vmx->nested.msrs.misc_high);
+
+	return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER;
+}
+
 static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu,
 				       u32 count, u64 addr)
 {
 	if (count == 0)
 		return 0;
 
+	/*
+	 * Exceeding the limit results in architecturally _undefined_ behavior,
+	 * i.e. KVM is allowed to do literally anything in response to a bad
+	 * limit.  Immediately generate a consistency check so that code that
+	 * consumes the count doesn't need to worry about extreme edge cases.
+	 */
+	if (count > nested_vmx_max_atomic_switch_msrs(vcpu))
+		return -EINVAL;
+
 	if (!kvm_vcpu_is_legal_aligned_gpa(vcpu, addr, 16) ||
 	    !kvm_vcpu_is_legal_gpa(vcpu, (addr + count * sizeof(struct vmx_msr_entry) - 1)))
 		return -EINVAL;
@@ -941,15 +965,6 @@ static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
-static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low,
-				       vmx->nested.msrs.misc_high);
-
-	return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER;
-}
-
 /*
  * Load guest's/host's msr at nested entry/exit.
  * return 0 for success, entry index for failure.
@@ -966,7 +981,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 	u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu);
 
 	for (i = 0; i < count; i++) {
-		if (unlikely(i >= max_msr_list_size))
+		if (WARN_ON_ONCE(i >= max_msr_list_size))
 			goto fail;
 
 		if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e),
@@ -1054,7 +1069,7 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
 	u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu);
 
 	for (i = 0; i < count; i++) {
-		if (unlikely(i >= max_msr_list_size))
+		if (WARN_ON_ONCE(i >= max_msr_list_size))
 			return -EINVAL;
 
 		if (!read_and_check_msr_entry(vcpu, gpa, i, &e))
@@ -2654,10 +2669,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	if (vmx->nested.nested_run_pending &&
 	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
 		kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
-		vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
+		vmx_guest_debugctl_write(vcpu, vmcs12->guest_ia32_debugctl &
+					       vmx_get_supported_debugctl(vcpu, false));
 	} else {
 		kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
-		vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl);
+		vmx_guest_debugctl_write(vcpu, vmx->nested.pre_vmenter_debugctl);
 	}
 	if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending ||
 	    !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
@@ -3147,7 +3163,8 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) &&
-	    CC(!kvm_dr7_valid(vmcs12->guest_dr7)))
+	    (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) ||
+	     CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false))))
 		return -EINVAL;
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
@@ -3521,7 +3538,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 
 	if (!vmx->nested.nested_run_pending ||
 	    !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
-		vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
+		vmx->nested.pre_vmenter_debugctl = vmx_guest_debugctl_read();
 	if (kvm_mpx_supported() &&
 	    (!vmx->nested.nested_run_pending ||
 	     !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
@@ -4521,12 +4538,12 @@ static void copy_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu,
 
 	cpu = get_cpu();
 	vmx->loaded_vmcs = &vmx->nested.vmcs02;
-	vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->vmcs01);
+	vmx_vcpu_load_vmcs(vcpu, cpu);
 
 	sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
 
 	vmx->loaded_vmcs = &vmx->vmcs01;
-	vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->nested.vmcs02);
+	vmx_vcpu_load_vmcs(vcpu, cpu);
 	put_cpu();
 }
 
@@ -4599,6 +4616,12 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
 		(vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE);
 
+	/*
+	 * Note!  Save DR7, but intentionally don't grab DEBUGCTL from vmcs02.
+	 * Writes to DEBUGCTL that aren't intercepted by L1 are immediately
+	 * propagated to vmcs12 (see vmx_set_msr()), as the value loaded into
+	 * vmcs02 doesn't strictly track vmcs12.
+	 */
 	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS)
 		vmcs12->guest_dr7 = vcpu->arch.dr7;
 
@@ -4623,7 +4646,7 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 {
 	/* update exit information fields: */
 	vmcs12->vm_exit_reason = vm_exit_reason;
-	if (to_vmx(vcpu)->exit_reason.enclave_mode)
+	if (vmx_get_exit_reason(vcpu).enclave_mode)
 		vmcs12->vm_exit_reason |= VMX_EXIT_REASONS_SGX_ENCLAVE_MODE;
 	vmcs12->exit_qualification = exit_qualification;
 
@@ -4789,13 +4812,13 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	__vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR);
 
 	kvm_set_dr(vcpu, 7, 0x400);
-	vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+	vmx_guest_debugctl_write(vcpu, 0);
 
 	if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
 				vmcs12->vm_exit_msr_load_count))
 		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL);
 
-	to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu);
+	to_vt(vcpu)->emulation_required = vmx_emulation_required(vcpu);
 }
 
 static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
@@ -4844,6 +4867,9 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
 			WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7)));
 	}
 
+	/* Reload DEBUGCTL to ensure vmcs01 has a fresh FREEZE_IN_SMM value. */
+	vmx_reload_guest_debugctl(vcpu);
+
 	/*
 	 * Note that calling vmx_set_{efer,cr0,cr4} is important as they
 	 * handle a variety of side effects to KVM's software model.
@@ -5021,16 +5047,7 @@ void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 
 	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
 
-	/*
-	 * If IBRS is advertised to the vCPU, KVM must flush the indirect
-	 * branch predictors when transitioning from L2 to L1, as L1 expects
-	 * hardware (KVM in this case) to provide separate predictor modes.
-	 * Bare metal isolates VMX root (host) from VMX non-root (guest), but
-	 * doesn't isolate different VMCSs, i.e. in this case, doesn't provide
-	 * separate modes for L2 vs L1.
-	 */
-	if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL))
-		indirect_branch_prediction_barrier();
+	kvm_nested_vmexit_handle_ibrs(vcpu);
 
 	/* Update any VMCS fields that might have changed while L2 ran */
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
@@ -6128,7 +6145,7 @@ fail:
 	 * nested VM-Exit.  Pass the original exit reason, i.e. don't hardcode
 	 * EXIT_REASON_VMFUNC as the exit reason.
 	 */
-	nested_vmx_vmexit(vcpu, vmx->exit_reason.full,
+	nested_vmx_vmexit(vcpu, vmx->vt.exit_reason.full,
 			  vmx_get_intr_info(vcpu),
 			  vmx_get_exit_qual(vcpu));
 	return 1;
@@ -6573,7 +6590,7 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu,
 bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	union vmx_exit_reason exit_reason = vmx->exit_reason;
+	union vmx_exit_reason exit_reason = vmx->vt.exit_reason;
 	unsigned long exit_qual;
 	u32 exit_intr_info;