1 files changed, 56 insertions, 53 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2f64e5d0ae53..c48404017e4f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1811,7 +1811,7 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
 	struct kvm_vcpu_arch *vcpu = &v->arch;
 	struct pvclock_vcpu_time_info guest_hv_clock;
 
-	if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time,
+	if (unlikely(kvm_vcpu_read_guest_cached(v, &vcpu->pv_time,
 		&guest_hv_clock, sizeof(guest_hv_clock))))
 		return;
 
@@ -1832,9 +1832,9 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
 	BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
 
 	vcpu->hv_clock.version = guest_hv_clock.version + 1;
-	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
-				&vcpu->hv_clock,
-				sizeof(vcpu->hv_clock.version));
+	kvm_vcpu_write_guest_cached(v, &vcpu->pv_time,
+				    &vcpu->hv_clock,
+				    sizeof(vcpu->hv_clock.version));
 
 	smp_wmb();
 
@@ -1848,16 +1848,16 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
 
 	trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock);
 
-	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
-				&vcpu->hv_clock,
-				sizeof(vcpu->hv_clock));
+	kvm_vcpu_write_guest_cached(v, &vcpu->pv_time,
+				    &vcpu->hv_clock,
+				    sizeof(vcpu->hv_clock));
 
 	smp_wmb();
 
 	vcpu->hv_clock.version++;
-	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
-				&vcpu->hv_clock,
-				sizeof(vcpu->hv_clock.version));
+	kvm_vcpu_write_guest_cached(v, &vcpu->pv_time,
+				    &vcpu->hv_clock,
+				    sizeof(vcpu->hv_clock.version));
 }
 
 static int kvm_guest_time_update(struct kvm_vcpu *v)
@@ -2090,7 +2090,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 		return 0;
 	}
 
-	if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa,
+	if (kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.apf.data, gpa,
 					sizeof(u32)))
 		return 1;
 
@@ -2109,7 +2109,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
 		return;
 
-	if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
+	if (unlikely(kvm_vcpu_read_guest_cached(vcpu, &vcpu->arch.st.stime,
 		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
 		return;
 
@@ -2120,7 +2120,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.st.steal.version += 1;
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
+	kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.st.stime,
 		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
 
 	smp_wmb();
@@ -2129,14 +2129,14 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 		vcpu->arch.st.last_steal;
 	vcpu->arch.st.last_steal = current->sched_info.run_delay;
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
+	kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.st.stime,
 		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
 
 	smp_wmb();
 
 	vcpu->arch.st.steal.version += 1;
 
-	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
+	kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.st.stime,
 		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
 }
 
@@ -2241,7 +2241,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!(data & 1))
 			break;
 
-		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+		if (kvm_vcpu_gfn_to_hva_cache_init(vcpu,
 		     &vcpu->arch.pv_time, data & ~1ULL,
 		     sizeof(struct pvclock_vcpu_time_info)))
 			vcpu->arch.pv_time_enabled = false;
@@ -2262,7 +2262,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (data & KVM_STEAL_RESERVED_MASK)
 			return 1;
 
-		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime,
+		if (kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.st.stime,
 						data & KVM_STEAL_VALID_BITS,
 						sizeof(struct kvm_steal_time)))
 			return 1;
@@ -2672,6 +2672,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_DISABLE_QUIRKS:
 	case KVM_CAP_SET_BOOT_CPU_ID:
  	case KVM_CAP_SPLIT_IRQCHIP:
+	case KVM_CAP_IMMEDIATE_EXIT:
 #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
 	case KVM_CAP_ASSIGN_DEV_IRQ:
 	case KVM_CAP_PCI_2_3:
@@ -2875,7 +2876,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.st.steal.preempted = 1;
 
-	kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
+	kvm_vcpu_write_guest_offset_cached(vcpu, &vcpu->arch.st.stime,
 			&vcpu->arch.st.steal.preempted,
 			offsetof(struct kvm_steal_time, preempted),
 			sizeof(vcpu->arch.st.steal.preempted));
@@ -2909,7 +2910,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
 				    struct kvm_lapic_state *s)
 {
-	if (vcpu->arch.apicv_active)
+	if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active)
 		kvm_x86_ops->sync_pir_to_irr(vcpu);
 
 	return kvm_apic_get_state(vcpu, s);
@@ -6659,7 +6660,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 	if (irqchip_split(vcpu->kvm))
 		kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
 	else {
-		if (vcpu->arch.apicv_active)
+		if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active)
 			kvm_x86_ops->sync_pir_to_irr(vcpu);
 		kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
 	}
@@ -6750,10 +6751,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			r = 0;
 			goto out;
 		}
-		if (kvm_check_request(KVM_REQ_DEACTIVATE_FPU, vcpu)) {
-			vcpu->fpu_active = 0;
-			kvm_x86_ops->fpu_deactivate(vcpu);
-		}
 		if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) {
 			/* Page is swapped out. Do synthetic halt */
 			vcpu->arch.apf.halted = true;
@@ -6813,20 +6810,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_hv_process_stimers(vcpu);
 	}
 
-	/*
-	 * KVM_REQ_EVENT is not set when posted interrupts are set by
-	 * VT-d hardware, so we have to update RVI unconditionally.
-	 */
-	if (kvm_lapic_enabled(vcpu)) {
-		/*
-		 * Update architecture specific hints for APIC
-		 * virtual interrupt delivery.
-		 */
-		if (vcpu->arch.apicv_active)
-			kvm_x86_ops->hwapic_irr_update(vcpu,
-				kvm_lapic_find_highest_irr(vcpu));
-	}
-
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
 		++vcpu->stat.req_event;
 		kvm_apic_accept_events(vcpu);
@@ -6869,22 +6852,40 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	preempt_disable();
 
 	kvm_x86_ops->prepare_guest_switch(vcpu);
-	if (vcpu->fpu_active)
-		kvm_load_guest_fpu(vcpu);
+	kvm_load_guest_fpu(vcpu);
+
+	/*
+	 * Disable IRQs before setting IN_GUEST_MODE.  Posted interrupt
+	 * IPI are then delayed after guest entry, which ensures that they
+	 * result in virtual interrupt delivery.
+	 */
+	local_irq_disable();
 	vcpu->mode = IN_GUEST_MODE;
 
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 
 	/*
-	 * We should set ->mode before check ->requests,
-	 * Please see the comment in kvm_make_all_cpus_request.
-	 * This also orders the write to mode from any reads
-	 * to the page tables done while the VCPU is running.
-	 * Please see the comment in kvm_flush_remote_tlbs.
+	 * 1) We should set ->mode before checking ->requests.  Please see
+	 * the comment in kvm_make_all_cpus_request.
+	 *
+	 * 2) For APICv, we should set ->mode before checking PIR.ON.  This
+	 * pairs with the memory barrier implicit in pi_test_and_set_on
+	 * (see vmx_deliver_posted_interrupt).
+	 *
+	 * 3) This also orders the write to mode from any reads to the page
+	 * tables done while the VCPU is running.  Please see the comment
+	 * in kvm_flush_remote_tlbs.
 	 */
 	smp_mb__after_srcu_read_unlock();
 
-	local_irq_disable();
+	/*
+	 * This handles the case where a posted interrupt was
+	 * notified with kvm_vcpu_kick.
+	 */
+	if (kvm_lapic_enabled(vcpu)) {
+		if (kvm_x86_ops->sync_pir_to_irr && vcpu->arch.apicv_active)
+			kvm_x86_ops->sync_pir_to_irr(vcpu);
+	}
 
 	if (vcpu->mode == EXITING_GUEST_MODE || vcpu->requests
 	    || need_resched() || signal_pending(current)) {
@@ -7023,6 +7024,9 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
 
 static inline bool kvm_vcpu_running(struct kvm_vcpu *vcpu)
 {
+	if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events)
+		kvm_x86_ops->check_nested_events(vcpu, false);
+
 	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
 		!vcpu->arch.apf.halted);
 }
@@ -7194,7 +7198,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	} else
 		WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed);
 
-	r = vcpu_run(vcpu);
+	if (kvm_run->immediate_exit)
+		r = -EINTR;
+	else
+		r = vcpu_run(vcpu);
 
 out:
 	post_kvm_run_save(vcpu);
@@ -8389,9 +8396,6 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
-	if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events)
-		kvm_x86_ops->check_nested_events(vcpu, false);
-
 	return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
 }
 
@@ -8528,9 +8532,8 @@ static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
 
 static int apf_put_user(struct kvm_vcpu *vcpu, u32 val)
 {
-
-	return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &val,
-				      sizeof(val));
+	return kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.apf.data, &val,
+					   sizeof(val));
 }
 
 void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,