svm: Implements update_pi_irte hook to setup posted interrupt

This patch implements update_pi_irte function hook to allow SVM
communicate to IOMMU driver regarding how to set up IRTE for handling
posted interrupt.

In case AVIC is enabled, during vcpu_load/unload, SVM needs to update
IOMMU IRTE with appropriate host physical APIC ID. Also, when
vcpu_blocking/unblocking, SVM needs to update the is-running bit in
the IOMMU IRTE. Both are achieved via calling amd_iommu_update_ga().

However, if GA mode is not enabled for the pass-through device,
IOMMU driver will simply just return when calling amd_iommu_update_ga.

Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/svm.c

@@ -43,6 +43,7 @@
 #include <asm/desc.h>
 #include <asm/debugreg.h>
 #include <asm/kvm_para.h>
+#include <asm/irq_remapping.h>
 
 #include <asm/virtext.h>
 #include "trace.h"
@@ -200,6 +201,23 @@ struct vcpu_svm {
 	struct page *avic_backing_page;
 	u64 *avic_physical_id_cache;
 	bool avic_is_running;
+
+	/*
+	 * Per-vcpu list of struct amd_svm_iommu_ir:
+	 * This is used mainly to store interrupt remapping information used
+	 * when update the vcpu affinity. This avoids the need to scan for
+	 * IRTE and try to match ga_tag in the IOMMU driver.
+	 */
+	struct list_head ir_list;
+	spinlock_t ir_list_lock;
+};
+
+/*
+ * This is a wrapper of struct amd_iommu_ir_data.
+ */
+struct amd_svm_iommu_ir {
+	struct list_head node;	/* Used by SVM for per-vcpu ir_list */
+	void *data;		/* Storing pointer to struct amd_ir_data */
 };
 
 #define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK	(0xFF)
@@ -1440,31 +1458,34 @@ free_avic:
 	return err;
 }
 
-/**
+static inline int
- * This function is called during VCPU halt/unhalt.
+avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
- */
-static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
 {
-	u64 entry;
+	int ret = 0;
-	int h_physical_id = kvm_cpu_get_apicid(vcpu->cpu);
+	unsigned long flags;
+	struct amd_svm_iommu_ir *ir;
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (!kvm_vcpu_apicv_active(vcpu))
+	if (!kvm_arch_has_assigned_device(vcpu->kvm))
-		return;
+		return 0;
 
-	svm->avic_is_running = is_run;
+	/*
+	 * Here, we go through the per-vcpu ir_list to update all existing
+	 * interrupt remapping table entry targeting this vcpu.
+	 */
+	spin_lock_irqsave(&svm->ir_list_lock, flags);
 
-	/* ID = 0xff (broadcast), ID > 0xff (reserved) */
+	if (list_empty(&svm->ir_list))
-	if (WARN_ON(h_physical_id >= AVIC_MAX_PHYSICAL_ID_COUNT))
+		goto out;
-		return;
 
-	entry = READ_ONCE(*(svm->avic_physical_id_cache));
+	list_for_each_entry(ir, &svm->ir_list, node) {
-	WARN_ON(is_run == !!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK));
+		ret = amd_iommu_update_ga(cpu, r, ir->data);
-
+		if (ret)
-	entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
+			break;
-	if (is_run)
+	}
-		entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
+out:
-	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
+	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+	return ret;
 }
 
 static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -1491,6 +1512,8 @@ static void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
 
 	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
+	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id,
+					svm->avic_is_running);
 }
 
 static void avic_vcpu_put(struct kvm_vcpu *vcpu)
@@ -1502,10 +1525,27 @@ static void avic_vcpu_put(struct kvm_vcpu *vcpu)
 		return;
 
 	entry = READ_ONCE(*(svm->avic_physical_id_cache));
+	if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
+		avic_update_iommu_vcpu_affinity(vcpu, -1, 0);
+
 	entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
 	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
 }
 
+/**
+ * This function is called during VCPU halt/unhalt.
+ */
+static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	svm->avic_is_running = is_run;
+	if (is_run)
+		avic_vcpu_load(vcpu, vcpu->cpu);
+	else
+		avic_vcpu_put(vcpu);
+}
+
 static void svm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -1567,6 +1607,9 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 		err = avic_init_backing_page(&svm->vcpu);
 		if (err)
 			goto free_page4;
+
+		INIT_LIST_HEAD(&svm->ir_list);
+		spin_lock_init(&svm->ir_list_lock);
 	}
 
 	/* We initialize this flag to true to make sure that the is_running
@@ -4363,6 +4406,209 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 		kvm_vcpu_wake_up(vcpu);
 }
 
+static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
+{
+	unsigned long flags;
+	struct amd_svm_iommu_ir *cur;
+
+	spin_lock_irqsave(&svm->ir_list_lock, flags);
+	list_for_each_entry(cur, &svm->ir_list, node) {
+		if (cur->data != pi->ir_data)
+			continue;
+		list_del(&cur->node);
+		kfree(cur);
+		break;
+	}
+	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+}
+
+static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
+{
+	int ret = 0;
+	unsigned long flags;
+	struct amd_svm_iommu_ir *ir;
+
+	/**
+	 * In some cases, the existing irte is updaed and re-set,
+	 * so we need to check here if it's already been * added
+	 * to the ir_list.
+	 */
+	if (pi->ir_data && (pi->prev_ga_tag != 0)) {
+		struct kvm *kvm = svm->vcpu.kvm;
+		u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag);
+		struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
+		struct vcpu_svm *prev_svm;
+
+		if (!prev_vcpu) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		prev_svm = to_svm(prev_vcpu);
+		svm_ir_list_del(prev_svm, pi);
+	}
+
+	/**
+	 * Allocating new amd_iommu_pi_data, which will get
+	 * add to the per-vcpu ir_list.
+	 */
+	ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL);
+	if (!ir) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	ir->data = pi->ir_data;
+
+	spin_lock_irqsave(&svm->ir_list_lock, flags);
+	list_add(&ir->node, &svm->ir_list);
+	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+out:
+	return ret;
+}
+
+/**
+ * Note:
+ * The HW cannot support posting multicast/broadcast
+ * interrupts to a vCPU. So, we still use legacy interrupt
+ * remapping for these kind of interrupts.
+ *
+ * For lowest-priority interrupts, we only support
+ * those with single CPU as the destination, e.g. user
+ * configures the interrupts via /proc/irq or uses
+ * irqbalance to make the interrupts single-CPU.
+ */
+static int
+get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
+		 struct vcpu_data *vcpu_info, struct vcpu_svm **svm)
+{
+	struct kvm_lapic_irq irq;
+	struct kvm_vcpu *vcpu = NULL;
+
+	kvm_set_msi_irq(kvm, e, &irq);
+
+	if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) {
+		pr_debug("SVM: %s: use legacy intr remap mode for irq %u\n",
+			 __func__, irq.vector);
+		return -1;
+	}
+
+	pr_debug("SVM: %s: use GA mode for irq %u\n", __func__,
+		 irq.vector);
+	*svm = to_svm(vcpu);
+	vcpu_info->pi_desc_addr = page_to_phys((*svm)->avic_backing_page);
+	vcpu_info->vector = irq.vector;
+
+	return 0;
+}
+
+/*
+ * svm_update_pi_irte - set IRTE for Posted-Interrupts
+ *
+ * @kvm: kvm
+ * @host_irq: host irq of the interrupt
+ * @guest_irq: gsi of the interrupt
+ * @set: set or unset PI
+ * returns 0 on success, < 0 on failure
+ */
+static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
+			      uint32_t guest_irq, bool set)
+{
+	struct kvm_kernel_irq_routing_entry *e;
+	struct kvm_irq_routing_table *irq_rt;
+	int idx, ret = -EINVAL;
+
+	if (!kvm_arch_has_assigned_device(kvm) ||
+	    !irq_remapping_cap(IRQ_POSTING_CAP))
+		return 0;
+
+	pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n",
+		 __func__, host_irq, guest_irq, set);
+
+	idx = srcu_read_lock(&kvm->irq_srcu);
+	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
+	WARN_ON(guest_irq >= irq_rt->nr_rt_entries);
+
+	hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
+		struct vcpu_data vcpu_info;
+		struct vcpu_svm *svm = NULL;
+
+		if (e->type != KVM_IRQ_ROUTING_MSI)
+			continue;
+
+		/**
+		 * Here, we setup with legacy mode in the following cases:
+		 * 1. When cannot target interrupt to a specific vcpu.
+		 * 2. Unsetting posted interrupt.
+		 * 3. APIC virtialization is disabled for the vcpu.
+		 */
+		if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set &&
+		    kvm_vcpu_apicv_active(&svm->vcpu)) {
+			struct amd_iommu_pi_data pi;
+
+			/* Try to enable guest_mode in IRTE */
+			pi.base = page_to_phys(svm->avic_backing_page) & AVIC_HPA_MASK;
+			pi.ga_tag = AVIC_GATAG(kvm->arch.avic_vm_id,
+						     svm->vcpu.vcpu_id);
+			pi.is_guest_mode = true;
+			pi.vcpu_data = &vcpu_info;
+			ret = irq_set_vcpu_affinity(host_irq, &pi);
+
+			/**
+			 * Here, we successfully setting up vcpu affinity in
+			 * IOMMU guest mode. Now, we need to store the posted
+			 * interrupt information in a per-vcpu ir_list so that
+			 * we can reference to them directly when we update vcpu
+			 * scheduling information in IOMMU irte.
+			 */
+			if (!ret && pi.is_guest_mode)
+				svm_ir_list_add(svm, &pi);
+		} else {
+			/* Use legacy mode in IRTE */
+			struct amd_iommu_pi_data pi;
+
+			/**
+			 * Here, pi is used to:
+			 * - Tell IOMMU to use legacy mode for this interrupt.
+			 * - Retrieve ga_tag of prior interrupt remapping data.
+			 */
+			pi.is_guest_mode = false;
+			ret = irq_set_vcpu_affinity(host_irq, &pi);
+
+			/**
+			 * Check if the posted interrupt was previously
+			 * setup with the guest_mode by checking if the ga_tag
+			 * was cached. If so, we need to clean up the per-vcpu
+			 * ir_list.
+			 */
+			if (!ret && pi.prev_ga_tag) {
+				int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
+				struct kvm_vcpu *vcpu;
+
+				vcpu = kvm_get_vcpu_by_id(kvm, id);
+				if (vcpu)
+					svm_ir_list_del(to_svm(vcpu), &pi);
+			}
+		}
+
+		if (!ret && svm) {
+			trace_kvm_pi_irte_update(svm->vcpu.vcpu_id,
+						 host_irq, e->gsi,
+						 vcpu_info.vector,
+						 vcpu_info.pi_desc_addr, set);
+		}
+
+		if (ret < 0) {
+			pr_err("%s: failed to update PI IRTE\n", __func__);
+			goto out;
+		}
+	}
+
+	ret = 0;
+out:
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+	return ret;
+}
+
 static int svm_nmi_allowed(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -5195,6 +5441,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 
 	.pmu_ops = &amd_pmu_ops,
 	.deliver_posted_interrupt = svm_deliver_avic_intr,
+	.update_pi_irte = svm_update_pi_irte,
 };
 
 static int __init svm_init(void)