KVM: VMX: Add the deliver posted interrupt algorithm

Only deliver the posted interrupt when target vcpu is running
and there is no previous interrupt pending in pir.

Signed-off-by: Yang Zhang <yang.z.zhang@Intel.com>
Reviewed-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -701,6 +701,8 @@ struct kvm_x86_ops {
 	void (*hwapic_isr_update)(struct kvm *kvm, int isr);
 	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
 	void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set);
+	void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
+	void (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*get_tdp_level)(void);
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);

arch/x86/kvm/lapic.c

@@ -318,6 +318,19 @@ static u8 count_vectors(void *bitmap)
 	return count;
 }
 
+void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir)
+{
+	u32 i, pir_val;
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
+	for (i = 0; i <= 7; i++) {
+		pir_val = xchg(&pir[i], 0);
+		if (pir_val)
+			*((u32 *)(apic->regs + APIC_IRR + i * 0x10)) |= pir_val;
+	}
+}
+EXPORT_SYMBOL_GPL(kvm_apic_update_irr);
+
 static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic)
 {
 	apic->irr_pending = true;

arch/x86/kvm/lapic.h

@@ -54,6 +54,7 @@ u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu);
 void kvm_apic_set_version(struct kvm_vcpu *vcpu);
 
 void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr);
+void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir);
 int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest);
 int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda);
 int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,

arch/x86/kvm/svm.c

@@ -3577,6 +3577,11 @@ static void svm_hwapic_isr_update(struct kvm *kvm, int isr)
 	return;
 }
 
+static void svm_sync_pir_to_irr(struct kvm_vcpu *vcpu)
+{
+	return;
+}
+
 static int svm_nmi_allowed(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -4305,6 +4310,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.vm_has_apicv = svm_vm_has_apicv,
 	.load_eoi_exitmap = svm_load_eoi_exitmap,
 	.hwapic_isr_update = svm_hwapic_isr_update,
+	.sync_pir_to_irr = svm_sync_pir_to_irr,
 
 	.set_tss_addr = svm_set_tss_addr,
 	.get_tdp_level = get_npt_level,

arch/x86/kvm/vmx.c

@@ -375,6 +375,23 @@ struct pi_desc {
 	u32 rsvd[7];
 } __aligned(64);
 
+static bool pi_test_and_set_on(struct pi_desc *pi_desc)
+{
+	return test_and_set_bit(POSTED_INTR_ON,
+			(unsigned long *)&pi_desc->control);
+}
+
+static bool pi_test_and_clear_on(struct pi_desc *pi_desc)
+{
+	return test_and_clear_bit(POSTED_INTR_ON,
+			(unsigned long *)&pi_desc->control);
+}
+
+static int pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
+{
+	return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
+}
+
 struct vcpu_vmx {
 	struct kvm_vcpu       vcpu;
 	unsigned long         host_rsp;
@@ -639,6 +656,7 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
 static bool guest_state_valid(struct kvm_vcpu *vcpu);
 static u32 vmx_segment_access_rights(struct kvm_segment *var);
+static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu);
 
 static DEFINE_PER_CPU(struct vmcs *, vmxarea);
 static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
@@ -2846,8 +2864,11 @@ static __init int hardware_setup(void)
 
 	if (enable_apicv)
 		kvm_x86_ops->update_cr8_intercept = NULL;
-	else
+	else {
 		kvm_x86_ops->hwapic_irr_update = NULL;
+		kvm_x86_ops->deliver_posted_interrupt = NULL;
+		kvm_x86_ops->sync_pir_to_irr = vmx_sync_pir_to_irr_dummy;
+	}
 
 	if (nested)
 		nested_vmx_setup_ctls_msrs();
@@ -3908,6 +3929,45 @@ static int vmx_vm_has_apicv(struct kvm *kvm)
 	return enable_apicv && irqchip_in_kernel(kvm);
 }
 
+/*
+ * Send interrupt to vcpu via posted interrupt way.
+ * 1. If target vcpu is running(non-root mode), send posted interrupt
+ * notification to vcpu and hardware will sync PIR to vIRR atomically.
+ * 2. If target vcpu isn't running(root mode), kick it to pick up the
+ * interrupt from PIR in next vmentry.
+ */
+static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	int r;
+
+	if (pi_test_and_set_pir(vector, &vmx->pi_desc))
+		return;
+
+	r = pi_test_and_set_on(&vmx->pi_desc);
+	kvm_make_request(KVM_REQ_EVENT, vcpu);
+	if (!r && (vcpu->mode == IN_GUEST_MODE))
+		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
+				POSTED_INTR_VECTOR);
+	else
+		kvm_vcpu_kick(vcpu);
+}
+
+static void vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (!pi_test_and_clear_on(&vmx->pi_desc))
+		return;
+
+	kvm_apic_update_irr(vcpu, vmx->pi_desc.pir);
+}
+
+static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu)
+{
+	return;
+}
+
 /*
  * Set up the vmcs's constant host-state fields, i.e., host-state fields that
  * will not change in the lifetime of the guest.
@@ -7784,6 +7844,8 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.load_eoi_exitmap = vmx_load_eoi_exitmap,
 	.hwapic_irr_update = vmx_hwapic_irr_update,
 	.hwapic_isr_update = vmx_hwapic_isr_update,
+	.sync_pir_to_irr = vmx_sync_pir_to_irr,
+	.deliver_posted_interrupt = vmx_deliver_posted_interrupt,
 
 	.set_tss_addr = vmx_set_tss_addr,
 	.get_tdp_level = get_ept_level,

virt/kvm/kvm_main.c

@@ -1671,6 +1671,7 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
 			smp_send_reschedule(cpu);
 	put_cpu();
 }
+EXPORT_SYMBOL_GPL(kvm_vcpu_kick);
 #endif /* !CONFIG_S390 */
 
 void kvm_resched(struct kvm_vcpu *vcpu)