KVM: nVMX: Fix trying to cancel vmlauch/vmresume

------------[ cut here ]------------
WARNING: CPU: 7 PID: 3861 at /home/kernel/ssd/kvm/arch/x86/kvm//vmx.c:11299 nested_vmx_vmexit+0x176e/0x1980 [kvm_intel]
CPU: 7 PID: 3861 Comm: qemu-system-x86 Tainted: G        W  OE   4.13.0-rc4+ #11
RIP: 0010:nested_vmx_vmexit+0x176e/0x1980 [kvm_intel]
Call Trace:
 ? kvm_multiple_exception+0x149/0x170 [kvm]
 ? handle_emulation_failure+0x79/0x230 [kvm]
 ? load_vmcs12_host_state+0xa80/0xa80 [kvm_intel]
 ? check_chain_key+0x137/0x1e0
 ? reexecute_instruction.part.168+0x130/0x130 [kvm]
 nested_vmx_inject_exception_vmexit+0xb7/0x100 [kvm_intel]
 ? nested_vmx_inject_exception_vmexit+0xb7/0x100 [kvm_intel]
 vmx_queue_exception+0x197/0x300 [kvm_intel]
 kvm_arch_vcpu_ioctl_run+0x1b0c/0x2c90 [kvm]
 ? kvm_arch_vcpu_runnable+0x220/0x220 [kvm]
 ? preempt_count_sub+0x18/0xc0
 ? restart_apic_timer+0x17d/0x300 [kvm]
 ? kvm_lapic_restart_hv_timer+0x37/0x50 [kvm]
 ? kvm_arch_vcpu_load+0x1d8/0x350 [kvm]
 kvm_vcpu_ioctl+0x4e4/0x910 [kvm]
 ? kvm_vcpu_ioctl+0x4e4/0x910 [kvm]
 ? kvm_dev_ioctl+0xbe0/0xbe0 [kvm]

The flag "nested_run_pending", which can override the decision of which should run
next, L1 or L2. nested_run_pending=1 means that we *must* run L2 next, not L1. This
is necessary in particular when L1 did a VMLAUNCH of L2 and therefore expects L2 to
be run (and perhaps be injected with an event it specified, etc.). Nested_run_pending
is especially intended to avoid switching  to L1 in the injection decision-point.

This can be handled just like the other cases in vmx_check_nested_events, instead of
having a special case in vmx_queue_exception.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Wanpeng Li <wanpeng.li@hotmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 17 insertions, 14 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e9e5f4fd834f..e0d2ca092788 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2472,15 +2472,14 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu,
  * 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)
+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;
 
 	if (nr == PF_VECTOR) {
 		if (vcpu->arch.exception.nested_apf) {
-			nested_vmx_inject_exception_vmexit(vcpu,
-							   vcpu->arch.apf.nested_apf_token);
+			*exit_qual = vcpu->arch.apf.nested_apf_token;
 			return 1;
 		}
 		/*
@@ -2494,16 +2493,15 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu)
 		 */
 		if (nested_vmx_is_page_fault_vmexit(vmcs12,
 						    vcpu->arch.exception.error_code)) {
-			nested_vmx_inject_exception_vmexit(vcpu, vcpu->arch.cr2);
+			*exit_qual = vcpu->arch.cr2;
 			return 1;
 		}
 	} else {
-		unsigned long exit_qual = 0;
-		if (nr == DB_VECTOR)
-			exit_qual = vcpu->arch.dr6;
-
 		if (vmcs12->exception_bitmap & (1u << nr)) {
-			nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+			if (nr == DB_VECTOR)
+				*exit_qual = vcpu->arch.dr6;
+			else
+				*exit_qual = 0;
 			return 1;
 		}
 	}
@@ -2516,14 +2514,9 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned nr = vcpu->arch.exception.nr;
 	bool has_error_code = vcpu->arch.exception.has_error_code;
-	bool reinject = vcpu->arch.exception.injected;
 	u32 error_code = vcpu->arch.exception.error_code;
 	u32 intr_info = nr | INTR_INFO_VALID_MASK;
 
-	if (!reinject && is_guest_mode(vcpu) &&
-	    nested_vmx_check_exception(vcpu))
-		return;
-
 	if (has_error_code) {
 		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
 		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
@@ -11011,10 +11004,20 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
 static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long exit_qual;
 
 	if (kvm_event_needs_reinjection(vcpu))
 		return -EBUSY;
 
+	if (vcpu->arch.exception.pending &&
+		nested_vmx_check_exception(vcpu, &exit_qual)) {
+		if (vmx->nested.nested_run_pending)
+			return -EBUSY;
+		nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+		vcpu->arch.exception.pending = false;
+		return 0;
+	}
+
 	if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
 	    vmx->nested.preemption_timer_expired) {
 		if (vmx->nested.nested_run_pending)