Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM fixes from Radim Krčmář:

 - fix build without CONFIG_HAVE_KVM_IRQ_ROUTING

 - fix NULL access in x86 CR access

 - fix race with VMX posted interrups

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: VMX: remove WARN_ON_ONCE in kvm_vcpu_trigger_posted_interrupt
  KVM: VMX: do not change SN bit in vmx_update_pi_irte()
  KVM: x86: Fix the NULL pointer parameter in check_cr_write()
  Revert "KVM: Don't accept obviously wrong gsi values via KVM_IRQFD"

2 files changed, 27 insertions, 20 deletions

diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 16bf6655aa85..15f527b44aa7 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -4102,10 +4102,12 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt)
 		ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
 		if (efer & EFER_LMA) {
 			u64 maxphyaddr;
-			u32 eax = 0x80000008;
+			u32 eax, ebx, ecx, edx;
 
-			if (ctxt->ops->get_cpuid(ctxt, &eax, NULL, NULL,
-						 NULL, false))
+			eax = 0x80000008;
+			ecx = 0;
+			if (ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx,
+						 &edx, false))
 				maxphyaddr = eax & 0xff;
 			else
 				maxphyaddr = 36;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 06c0c6d0541e..0726ca7a1b02 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5077,21 +5077,30 @@ static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
 	int pi_vec = nested ? POSTED_INTR_NESTED_VECTOR : POSTED_INTR_VECTOR;
 
 	if (vcpu->mode == IN_GUEST_MODE) {
-		struct vcpu_vmx *vmx = to_vmx(vcpu);
-
 		/*
-		 * Currently, we don't support urgent interrupt,
-		 * all interrupts are recognized as non-urgent
-		 * interrupt, so we cannot post interrupts when
-		 * 'SN' is set.
+		 * The vector of interrupt to be delivered to vcpu had
+		 * been set in PIR before this function.
+		 *
+		 * Following cases will be reached in this block, and
+		 * we always send a notification event in all cases as
+		 * explained below.
+		 *
+		 * Case 1: vcpu keeps in non-root mode. Sending a
+		 * notification event posts the interrupt to vcpu.
 		 *
-		 * If the vcpu is in guest mode, it means it is
-		 * running instead of being scheduled out and
-		 * waiting in the run queue, and that's the only
-		 * case when 'SN' is set currently, warning if
-		 * 'SN' is set.
+		 * Case 2: vcpu exits to root mode and is still
+		 * runnable. PIR will be synced to vIRR before the
+		 * next vcpu entry. Sending a notification event in
+		 * this case has no effect, as vcpu is not in root
+		 * mode.
+		 *
+		 * Case 3: vcpu exits to root mode and is blocked.
+		 * vcpu_block() has already synced PIR to vIRR and
+		 * never blocks vcpu if vIRR is not cleared. Therefore,
+		 * a blocked vcpu here does not wait for any requested
+		 * interrupts in PIR, and sending a notification event
+		 * which has no effect is safe here.
 		 */
-		WARN_ON_ONCE(pi_test_sn(&vmx->pi_desc));
 
 		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec);
 		return true;
@@ -11911,12 +11920,8 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 
 		if (set)
 			ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
-		else {
-			/* suppress notification event before unposting */
-			pi_set_sn(vcpu_to_pi_desc(vcpu));
+		else
 			ret = irq_set_vcpu_affinity(host_irq, NULL);
-			pi_clear_sn(vcpu_to_pi_desc(vcpu));
-		}
 
 		if (ret < 0) {
 			printk(KERN_INFO "%s: failed to update PI IRTE\n",