Merge branch 'kvm-svm-harden' into HEAD

This fixes three issues in nested SVM:

1) in the shutdown_interception() vmexit handler we call kvm_vcpu_reset().
However, if running nested and L1 doesn't intercept shutdown, the function
resets vcpu->arch.hflags without properly leaving the nested state.
This leaves the vCPU in inconsistent state and later triggers a kernel
panic in SVM code.  The same bug can likely be triggered by sending INIT
via local apic to a vCPU which runs a nested guest.

On VMX we are lucky that the issue can't happen because VMX always
intercepts triple faults, thus triple fault in L2 will always be
redirected to L1.  Plus, handle_triple_fault() doesn't reset the vCPU.
INIT IPI can't happen on VMX either because INIT events are masked while
in VMX mode.

Secondarily, KVM doesn't honour SHUTDOWN intercept bit of L1 on SVM.
A normal hypervisor should always intercept SHUTDOWN, a unit test on
the other hand might want to not do so.

Finally, the guest can trigger a kernel non rate limited printk on SVM
from the guest, which is fixed as well.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

4 files changed, 34 insertions, 27 deletions

diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 4c620999d230..995bc0f90759 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1091,6 +1091,12 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
 
 static void nested_svm_triple_fault(struct kvm_vcpu *vcpu)
 {
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SHUTDOWN))
+		return;
+
+	kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 	nested_svm_simple_vmexit(to_svm(vcpu), SVM_EXIT_SHUTDOWN);
 }
 
@@ -1125,6 +1131,9 @@ void svm_free_nested(struct vcpu_svm *svm)
 	if (!svm->nested.initialized)
 		return;
 
+	if (WARN_ON_ONCE(svm->vmcb != svm->vmcb01.ptr))
+		svm_switch_vmcb(svm, &svm->vmcb01);
+
 	svm_vcpu_free_msrpm(svm->nested.msrpm);
 	svm->nested.msrpm = NULL;
 
@@ -1143,9 +1152,6 @@ void svm_free_nested(struct vcpu_svm *svm)
 	svm->nested.initialized = false;
 }
 
-/*
- * Forcibly leave nested mode in order to be able to reset the VCPU later on.
- */
 void svm_leave_nested(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 9f88c8e6766e..c0950ae86b2b 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -346,12 +346,6 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 	return 0;
 }
 
-static int is_external_interrupt(u32 info)
-{
-	info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID;
-	return info == (SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR);
-}
-
 static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -1438,6 +1432,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu)
 	 */
 	svm_clear_current_vmcb(svm->vmcb);
 
+	svm_leave_nested(vcpu);
 	svm_free_nested(svm);
 
 	sev_free_vcpu(vcpu);
@@ -3425,15 +3420,6 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 		return 0;
 	}
 
-	if (is_external_interrupt(svm->vmcb->control.exit_int_info) &&
-	    exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR &&
-	    exit_code != SVM_EXIT_NPF && exit_code != SVM_EXIT_TASK_SWITCH &&
-	    exit_code != SVM_EXIT_INTR && exit_code != SVM_EXIT_NMI)
-		printk(KERN_ERR "%s: unexpected exit_int_info 0x%x "
-		       "exit_code 0x%x\n",
-		       __func__, svm->vmcb->control.exit_int_info,
-		       exit_code);
-
 	if (exit_fastpath != EXIT_FASTPATH_NONE)
 		return 1;
 
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 0c62352dda6a..5b0d4859e4b7 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -4854,6 +4854,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 
 static void nested_vmx_triple_fault(struct kvm_vcpu *vcpu)
 {
+	kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 	nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0);
 }
 
@@ -6440,9 +6441,6 @@ out:
 	return kvm_state.size;
 }
 
-/*
- * Forcibly leave nested mode in order to be able to reset the VCPU later on.
- */
 void vmx_leave_nested(struct kvm_vcpu *vcpu)
 {
 	if (is_guest_mode(vcpu)) {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ecea83f0da49..5384c567f68f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -628,6 +628,12 @@ static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vecto
 	ex->payload = payload;
 }
 
+/* Forcibly leave the nested mode in cases like a vCPU reset */
+static void kvm_leave_nested(struct kvm_vcpu *vcpu)
+{
+	kvm_x86_ops.nested_ops->leave_nested(vcpu);
+}
+
 static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 		unsigned nr, bool has_error, u32 error_code,
 	        bool has_payload, unsigned long payload, bool reinject)
@@ -5195,7 +5201,7 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 
 	if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
 		if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
-			kvm_x86_ops.nested_ops->leave_nested(vcpu);
+			kvm_leave_nested(vcpu);
 			kvm_smm_changed(vcpu, events->smi.smm);
 		}
 
@@ -9805,7 +9811,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 
 int kvm_check_nested_events(struct kvm_vcpu *vcpu)
 {
-	if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
+	if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
 		kvm_x86_ops.nested_ops->triple_fault(vcpu);
 		return 1;
 	}
@@ -10560,15 +10566,16 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			r = 0;
 			goto out;
 		}
-		if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
-			if (is_guest_mode(vcpu)) {
+		if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
+			if (is_guest_mode(vcpu))
 				kvm_x86_ops.nested_ops->triple_fault(vcpu);
-			} else {
+
+			if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
 				vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
 				vcpu->mmio_needed = 0;
 				r = 0;
-				goto out;
 			}
+			goto out;
 		}
 		if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) {
 			/* Page is swapped out. Do synthetic halt */
@@ -11997,8 +12004,18 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	WARN_ON_ONCE(!init_event &&
 		     (old_cr0 || kvm_read_cr3(vcpu) || kvm_read_cr4(vcpu)));
 
+	/*
+	 * SVM doesn't unconditionally VM-Exit on INIT and SHUTDOWN, thus it's
+	 * possible to INIT the vCPU while L2 is active.  Force the vCPU back
+	 * into L1 as EFER.SVME is cleared on INIT (along with all other EFER
+	 * bits), i.e. virtualization is disabled.
+	 */
+	if (is_guest_mode(vcpu))
+		kvm_leave_nested(vcpu);
+
 	kvm_lapic_reset(vcpu, init_event);
 
+	WARN_ON_ONCE(is_guest_mode(vcpu) || is_smm(vcpu));
 	vcpu->arch.hflags = 0;
 
 	vcpu->arch.smi_pending = 0;