1 files changed, 165 insertions, 97 deletions

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index f8b7bc04b3e7..cf206855ebf0 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -58,8 +58,9 @@ static void svm_inject_page_fault_nested(struct kvm_vcpu *vcpu, struct x86_excep
        struct vcpu_svm *svm = to_svm(vcpu);
        WARN_ON(!is_guest_mode(vcpu));
 
-       if (vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_EXCEPTION_OFFSET + PF_VECTOR) &&
-	   !svm->nested.nested_run_pending) {
+	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;
@@ -121,7 +122,8 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu)
 
 void recalc_intercepts(struct vcpu_svm *svm)
 {
-	struct vmcb_control_area *c, *h, *g;
+	struct vmcb_control_area *c, *h;
+	struct vmcb_ctrl_area_cached *g;
 	unsigned int i;
 
 	vmcb_mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
@@ -163,37 +165,6 @@ void recalc_intercepts(struct vcpu_svm *svm)
 	vmcb_set_intercept(c, INTERCEPT_VMSAVE);
 }
 
-static void copy_vmcb_control_area(struct vmcb_control_area *dst,
-				   struct vmcb_control_area *from)
-{
-	unsigned int i;
-
-	for (i = 0; i < MAX_INTERCEPT; i++)
-		dst->intercepts[i] = from->intercepts[i];
-
-	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)
 {
 	/*
@@ -203,7 +174,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 	 */
 	int i;
 
-	if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)))
+	if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)))
 		return true;
 
 	for (i = 0; i < MSRPM_OFFSETS; i++) {
@@ -250,10 +221,10 @@ static bool nested_svm_check_tlb_ctl(struct kvm_vcpu *vcpu, u8 tlb_ctl)
 	}
 }
 
-static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu,
-				       struct vmcb_control_area *control)
+static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu,
+					 struct vmcb_ctrl_area_cached *control)
 {
-	if (CC(!vmcb_is_intercept(control, INTERCEPT_VMRUN)))
+	if (CC(!vmcb12_is_intercept(control, INTERCEPT_VMRUN)))
 		return false;
 
 	if (CC(control->asid == 0))
@@ -275,9 +246,20 @@ static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu,
 	return true;
 }
 
-static bool nested_vmcb_check_cr3_cr4(struct kvm_vcpu *vcpu,
-				      struct vmcb_save_area *save)
+/* Common checks that apply to both L1 and L2 state.  */
+static bool __nested_vmcb_check_save(struct kvm_vcpu *vcpu,
+				     struct vmcb_save_area_cached *save)
 {
+	if (CC(!(save->efer & EFER_SVME)))
+		return false;
+
+	if (CC((save->cr0 & X86_CR0_CD) == 0 && (save->cr0 & X86_CR0_NW)) ||
+	    CC(save->cr0 & ~0xffffffffULL))
+		return false;
+
+	if (CC(!kvm_dr6_valid(save->dr6)) || CC(!kvm_dr7_valid(save->dr7)))
+		return false;
+
 	/*
 	 * These checks are also performed by KVM_SET_SREGS,
 	 * except that EFER.LMA is not checked by SVM against
@@ -293,48 +275,90 @@ static bool nested_vmcb_check_cr3_cr4(struct kvm_vcpu *vcpu,
 	if (CC(!kvm_is_valid_cr4(vcpu, save->cr4)))
 		return false;
 
+	if (CC(!kvm_valid_efer(vcpu, save->efer)))
+		return false;
+
 	return true;
 }
 
-/* Common checks that apply to both L1 and L2 state.  */
-static bool nested_vmcb_valid_sregs(struct kvm_vcpu *vcpu,
-				    struct vmcb_save_area *save)
+static bool nested_vmcb_check_save(struct kvm_vcpu *vcpu)
 {
-	/*
-	 * FIXME: these should be done after copying the fields,
-	 * to avoid TOC/TOU races.  For these save area checks
-	 * the possible damage is limited since kvm_set_cr0 and
-	 * kvm_set_cr4 handle failure; EFER_SVME is an exception
-	 * so it is force-set later in nested_prepare_vmcb_save.
-	 */
-	if (CC(!(save->efer & EFER_SVME)))
-		return false;
+	struct vcpu_svm *svm = to_svm(vcpu);
+	struct vmcb_save_area_cached *save = &svm->nested.save;
 
-	if (CC((save->cr0 & X86_CR0_CD) == 0 && (save->cr0 & X86_CR0_NW)) ||
-	    CC(save->cr0 & ~0xffffffffULL))
-		return false;
+	return __nested_vmcb_check_save(vcpu, save);
+}
 
-	if (CC(!kvm_dr6_valid(save->dr6)) || CC(!kvm_dr7_valid(save->dr7)))
-		return false;
+static bool nested_vmcb_check_controls(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	struct vmcb_ctrl_area_cached *ctl = &svm->nested.ctl;
 
-	if (!nested_vmcb_check_cr3_cr4(vcpu, save))
-		return false;
+	return __nested_vmcb_check_controls(vcpu, ctl);
+}
 
-	if (CC(!kvm_valid_efer(vcpu, save->efer)))
-		return false;
+static
+void __nested_copy_vmcb_control_to_cache(struct vmcb_ctrl_area_cached *to,
+					 struct vmcb_control_area *from)
+{
+	unsigned int i;
 
-	return true;
+	for (i = 0; i < MAX_INTERCEPT; i++)
+		to->intercepts[i] = from->intercepts[i];
+
+	to->iopm_base_pa        = from->iopm_base_pa;
+	to->msrpm_base_pa       = from->msrpm_base_pa;
+	to->tsc_offset          = from->tsc_offset;
+	to->tlb_ctl             = from->tlb_ctl;
+	to->int_ctl             = from->int_ctl;
+	to->int_vector          = from->int_vector;
+	to->int_state           = from->int_state;
+	to->exit_code           = from->exit_code;
+	to->exit_code_hi        = from->exit_code_hi;
+	to->exit_info_1         = from->exit_info_1;
+	to->exit_info_2         = from->exit_info_2;
+	to->exit_int_info       = from->exit_int_info;
+	to->exit_int_info_err   = from->exit_int_info_err;
+	to->nested_ctl          = from->nested_ctl;
+	to->event_inj           = from->event_inj;
+	to->event_inj_err       = from->event_inj_err;
+	to->nested_cr3          = from->nested_cr3;
+	to->virt_ext            = from->virt_ext;
+	to->pause_filter_count  = from->pause_filter_count;
+	to->pause_filter_thresh = from->pause_filter_thresh;
+
+	/* Copy asid here because nested_vmcb_check_controls will check it.  */
+	to->asid           = from->asid;
+	to->msrpm_base_pa &= ~0x0fffULL;
+	to->iopm_base_pa  &= ~0x0fffULL;
 }
 
-void nested_load_control_from_vmcb12(struct vcpu_svm *svm,
-				     struct vmcb_control_area *control)
+void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm,
+				       struct vmcb_control_area *control)
 {
-	copy_vmcb_control_area(&svm->nested.ctl, control);
+	__nested_copy_vmcb_control_to_cache(&svm->nested.ctl, control);
+}
+
+static void __nested_copy_vmcb_save_to_cache(struct vmcb_save_area_cached *to,
+					     struct vmcb_save_area *from)
+{
+	/*
+	 * Copy only fields that are validated, as we need them
+	 * to avoid TOC/TOU races.
+	 */
+	to->efer = from->efer;
+	to->cr0 = from->cr0;
+	to->cr3 = from->cr3;
+	to->cr4 = from->cr4;
 
-	/* Copy it here because nested_svm_check_controls will check it.  */
-	svm->nested.ctl.asid           = control->asid;
-	svm->nested.ctl.msrpm_base_pa &= ~0x0fffULL;
-	svm->nested.ctl.iopm_base_pa  &= ~0x0fffULL;
+	to->dr6 = from->dr6;
+	to->dr7 = from->dr7;
+}
+
+void nested_copy_vmcb_save_to_cache(struct vcpu_svm *svm,
+				    struct vmcb_save_area *save)
+{
+	__nested_copy_vmcb_save_to_cache(&svm->nested.save, save);
 }
 
 /*
@@ -437,14 +461,13 @@ static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3,
 		return -EINVAL;
 
 	if (reload_pdptrs && !nested_npt && is_pae_paging(vcpu) &&
-	    CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)))
+	    CC(!load_pdptrs(vcpu, cr3)))
 		return -EINVAL;
 
 	if (!nested_npt)
 		kvm_mmu_new_pgd(vcpu, cr3);
 
 	vcpu->arch.cr3 = cr3;
-	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
 
 	/* Re-initialize the MMU, e.g. to pick up CR4 MMU role changes. */
 	kvm_init_mmu(vcpu);
@@ -490,15 +513,10 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12
 
 	kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags | X86_EFLAGS_FIXED);
 
-	/*
-	 * Force-set EFER_SVME even though it is checked earlier on the
-	 * VMCB12, because the guest can flip the bit between the check
-	 * and now.  Clearing EFER_SVME would call svm_free_nested.
-	 */
-	svm_set_efer(&svm->vcpu, vmcb12->save.efer | EFER_SVME);
+	svm_set_efer(&svm->vcpu, svm->nested.save.efer);
 
-	svm_set_cr0(&svm->vcpu, vmcb12->save.cr0);
-	svm_set_cr4(&svm->vcpu, vmcb12->save.cr4);
+	svm_set_cr0(&svm->vcpu, svm->nested.save.cr0);
+	svm_set_cr4(&svm->vcpu, svm->nested.save.cr4);
 
 	svm->vcpu.arch.cr2 = vmcb12->save.cr2;
 
@@ -513,8 +531,8 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12
 
 	/* These bits will be set properly on the first execution when new_vmc12 is true */
 	if (unlikely(new_vmcb12 || vmcb_is_dirty(vmcb12, VMCB_DR))) {
-		svm->vmcb->save.dr7 = vmcb12->save.dr7 | DR7_FIXED_1;
-		svm->vcpu.arch.dr6  = vmcb12->save.dr6 | DR6_ACTIVE_LOW;
+		svm->vmcb->save.dr7 = svm->nested.save.dr7 | DR7_FIXED_1;
+		svm->vcpu.arch.dr6  = svm->nested.save.dr6 | DR6_ACTIVE_LOW;
 		vmcb_mark_dirty(svm->vmcb, VMCB_DR);
 	}
 }
@@ -628,7 +646,7 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa,
 	nested_vmcb02_prepare_control(svm);
 	nested_vmcb02_prepare_save(svm, vmcb12);
 
-	ret = nested_svm_load_cr3(&svm->vcpu, vmcb12->save.cr3,
+	ret = nested_svm_load_cr3(&svm->vcpu, svm->nested.save.cr3,
 				  nested_npt_enabled(svm), from_vmrun);
 	if (ret)
 		return ret;
@@ -678,10 +696,11 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
 	if (WARN_ON_ONCE(!svm->nested.initialized))
 		return -EINVAL;
 
-	nested_load_control_from_vmcb12(svm, &vmcb12->control);
+	nested_copy_vmcb_control_to_cache(svm, &vmcb12->control);
+	nested_copy_vmcb_save_to_cache(svm, &vmcb12->save);
 
-	if (!nested_vmcb_valid_sregs(vcpu, &vmcb12->save) ||
-	    !nested_vmcb_check_controls(vcpu, &svm->nested.ctl)) {
+	if (!nested_vmcb_check_save(vcpu) ||
+	    !nested_vmcb_check_controls(vcpu)) {
 		vmcb12->control.exit_code    = SVM_EXIT_ERR;
 		vmcb12->control.exit_code_hi = 0;
 		vmcb12->control.exit_info_1  = 0;
@@ -988,7 +1007,7 @@ static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
 	u32 offset, msr, value;
 	int write, mask;
 
-	if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)))
+	if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)))
 		return NESTED_EXIT_HOST;
 
 	msr    = svm->vcpu.arch.regs[VCPU_REGS_RCX];
@@ -1015,7 +1034,7 @@ static int nested_svm_intercept_ioio(struct vcpu_svm *svm)
 	u8 start_bit;
 	u64 gpa;
 
-	if (!(vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_IOIO_PROT)))
+	if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_IOIO_PROT)))
 		return NESTED_EXIT_HOST;
 
 	port = svm->vmcb->control.exit_info_1 >> 16;
@@ -1046,12 +1065,12 @@ static int nested_svm_intercept(struct vcpu_svm *svm)
 		vmexit = nested_svm_intercept_ioio(svm);
 		break;
 	case SVM_EXIT_READ_CR0 ... SVM_EXIT_WRITE_CR8: {
-		if (vmcb_is_intercept(&svm->nested.ctl, exit_code))
+		if (vmcb12_is_intercept(&svm->nested.ctl, exit_code))
 			vmexit = NESTED_EXIT_DONE;
 		break;
 	}
 	case SVM_EXIT_READ_DR0 ... SVM_EXIT_WRITE_DR7: {
-		if (vmcb_is_intercept(&svm->nested.ctl, exit_code))
+		if (vmcb12_is_intercept(&svm->nested.ctl, exit_code))
 			vmexit = NESTED_EXIT_DONE;
 		break;
 	}
@@ -1069,7 +1088,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm)
 		break;
 	}
 	default: {
-		if (vmcb_is_intercept(&svm->nested.ctl, exit_code))
+		if (vmcb12_is_intercept(&svm->nested.ctl, exit_code))
 			vmexit = NESTED_EXIT_DONE;
 	}
 	}
@@ -1147,7 +1166,7 @@ static void nested_svm_inject_exception_vmexit(struct vcpu_svm *svm)
 
 static inline bool nested_exit_on_init(struct vcpu_svm *svm)
 {
-	return vmcb_is_intercept(&svm->nested.ctl, INTERCEPT_INIT);
+	return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_INIT);
 }
 
 static int svm_check_nested_events(struct kvm_vcpu *vcpu)
@@ -1251,11 +1270,47 @@ void nested_svm_update_tsc_ratio_msr(struct kvm_vcpu *vcpu)
 	svm_write_tsc_multiplier(vcpu, vcpu->arch.tsc_scaling_ratio);
 }
 
+/* Inverse operation of nested_copy_vmcb_control_to_cache(). asid is copied too. */
+static void nested_copy_vmcb_cache_to_control(struct vmcb_control_area *dst,
+					      struct vmcb_ctrl_area_cached *from)
+{
+	unsigned int i;
+
+	memset(dst, 0, sizeof(struct vmcb_control_area));
+
+	for (i = 0; i < MAX_INTERCEPT; i++)
+		dst->intercepts[i] = from->intercepts[i];
+
+	dst->iopm_base_pa         = from->iopm_base_pa;
+	dst->msrpm_base_pa        = from->msrpm_base_pa;
+	dst->tsc_offset           = from->tsc_offset;
+	dst->asid                 = from->asid;
+	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 int svm_get_nested_state(struct kvm_vcpu *vcpu,
 				struct kvm_nested_state __user *user_kvm_nested_state,
 				u32 user_data_size)
 {
 	struct vcpu_svm *svm;
+	struct vmcb_control_area *ctl;
+	unsigned long r;
 	struct kvm_nested_state kvm_state = {
 		.flags = 0,
 		.format = KVM_STATE_NESTED_FORMAT_SVM,
@@ -1297,9 +1352,18 @@ static int svm_get_nested_state(struct kvm_vcpu *vcpu,
 	 */
 	if (clear_user(user_vmcb, KVM_STATE_NESTED_SVM_VMCB_SIZE))
 		return -EFAULT;
-	if (copy_to_user(&user_vmcb->control, &svm->nested.ctl,
-			 sizeof(user_vmcb->control)))
+
+	ctl = kzalloc(sizeof(*ctl), GFP_KERNEL);
+	if (!ctl)
+		return -ENOMEM;
+
+	nested_copy_vmcb_cache_to_control(ctl, &svm->nested.ctl);
+	r = copy_to_user(&user_vmcb->control, ctl,
+			 sizeof(user_vmcb->control));
+	kfree(ctl);
+	if (r)
 		return -EFAULT;
+
 	if (copy_to_user(&user_vmcb->save, &svm->vmcb01.ptr->save,
 			 sizeof(user_vmcb->save)))
 		return -EFAULT;
@@ -1316,6 +1380,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 		&user_kvm_nested_state->data.svm[0];
 	struct vmcb_control_area *ctl;
 	struct vmcb_save_area *save;
+	struct vmcb_save_area_cached save_cached;
+	struct vmcb_ctrl_area_cached ctl_cached;
 	unsigned long cr0;
 	int ret;
 
@@ -1368,7 +1434,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 		goto out_free;
 
 	ret = -EINVAL;
-	if (!nested_vmcb_check_controls(vcpu, ctl))
+	__nested_copy_vmcb_control_to_cache(&ctl_cached, ctl);
+	if (!__nested_vmcb_check_controls(vcpu, &ctl_cached))
 		goto out_free;
 
 	/*
@@ -1383,10 +1450,11 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	 * Validate host state saved from before VMRUN (see
 	 * nested_svm_check_permissions).
 	 */
+	__nested_copy_vmcb_save_to_cache(&save_cached, save);
 	if (!(save->cr0 & X86_CR0_PG) ||
 	    !(save->cr0 & X86_CR0_PE) ||
 	    (save->rflags & X86_EFLAGS_VM) ||
-	    !nested_vmcb_valid_sregs(vcpu, save))
+	    !__nested_vmcb_check_save(vcpu, &save_cached))
 		goto out_free;
 
 	/*
@@ -1422,7 +1490,7 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa;
 
 	svm_copy_vmrun_state(&svm->vmcb01.ptr->save, save);
-	nested_load_control_from_vmcb12(svm, ctl);
+	nested_copy_vmcb_control_to_cache(svm, ctl);
 
 	svm_switch_vmcb(svm, &svm->nested.vmcb02);
 	nested_vmcb02_prepare_control(svm);
@@ -1449,7 +1517,7 @@ static bool svm_get_nested_state_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;
 
 	if (!nested_svm_vmrun_msrpm(svm)) {