[PATCH v4 12/17] svm: Temporary deactivate AVIC during ExtINT handling

[Suthikulpanit, Suravee]

AMD AVIC does not support ExtINT. Therefore, AVIC must be temporary
deactivated and fall back to using legacy interrupt injection via vINTR
and interrupt window.

Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@xxxxxxx>
---
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/svm.c              | 37 ++++++++++++++++++++++++++++++++++---
 2 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 55d6476..fe61269 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -857,6 +857,7 @@ enum kvm_irqchip_mode {
 #define APICV_DEACT_BIT_DISABLE    0
 #define APICV_DEACT_BIT_HYPERV     1
 #define APICV_DEACT_BIT_NESTED     2
+#define APICV_DEACT_BIT_IRQWIN     3
 
 struct kvm_arch {
 	unsigned long n_used_mmu_pages;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 7f59b1a..0e7ff04 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -388,6 +388,8 @@ struct amd_svm_iommu_ir {
 static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 static void svm_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa);
 static void svm_complete_interrupts(struct vcpu_svm *svm);
+static void svm_request_update_avic(struct kvm_vcpu *vcpu, bool activate);
+static bool svm_get_enable_apicv(struct kvm *kvm);
 static inline void avic_post_state_restore(struct kvm_vcpu *vcpu);
 
 static int nested_svm_exit_handled(struct vcpu_svm *svm);
@@ -4479,6 +4481,15 @@ static int interrupt_window_interception(struct vcpu_svm *svm)
 {
 	kvm_make_request(KVM_REQ_EVENT, &svm->vcpu);
 	svm_clear_vintr(svm);
+
+	/*
+	 * For AVIC, the only reason to end up here is ExtINTs.
+	 * In this case AVIC was temporarily disabled for
+	 * requesting the IRQ window and we have to re-enable it.
+	 */
+	if (svm_get_enable_apicv(svm->vcpu.kvm))
+		svm_request_update_avic(&svm->vcpu, true);
+
 	svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
 	mark_dirty(svm->vmcb, VMCB_INTR);
 	++svm->vcpu.stat.irq_window_exits;
@@ -5166,6 +5177,21 @@ static void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
 {
 }
 
+static void svm_request_update_avic(struct kvm_vcpu *vcpu, bool activate)
+{
+	if (!lapic_in_kernel(vcpu))
+		return;
+	/*
+	 * kvm_request_apicv_update() expects a prior read unlock
+	 * on the the kvm->srcu since it subsequently calls read lock
+	 * and re-unlock in __x86_set_memory_region()
+	 * when updating APIC_ACCESS_PAGE_PRIVATE_MEMSLOT.
+	 */
+	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+	kvm_request_apicv_update(vcpu->kvm, activate, APICV_DEACT_BIT_IRQWIN);
+	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+}
+
 static int svm_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
 {
 	int ret = 0;
@@ -5504,9 +5530,6 @@ static void enable_irq_window(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (kvm_vcpu_apicv_active(vcpu))
-		return;
-
 	/*
 	 * In case GIF=0 we can't rely on the CPU to tell us when GIF becomes
 	 * 1, because that's a separate STGI/VMRUN intercept.  The next time we
@@ -5516,6 +5539,14 @@ static void enable_irq_window(struct kvm_vcpu *vcpu)
 	 * window under the assumption that the hardware will set the GIF.
 	 */
 	if ((vgif_enabled(svm) || gif_set(svm)) && nested_svm_intr(svm)) {
+		/*
+		 * IRQ window is not needed when AVIC is enabled,
+		 * unless we have pending ExtINT since it cannot be injected
+		 * via AVIC. In such case, we need to temporarily disable AVIC,
+		 * and fallback to injecting IRQ via V_IRQ.
+		 */
+		if (kvm_vcpu_apicv_active(vcpu))
+			svm_request_update_avic(vcpu, false);
 		svm_set_vintr(svm);
 		svm_inject_irq(svm, 0x0);
 	}
-- 
1.8.3.1