KVM: SVM: Stop walking list of routing table entries when updating IRTE

Now that KVM explicitly passes the new/current GSI routing to
pi_update_irte(), simply use the provided routing entry and stop walking
the routing table to find that entry.  KVM, via setup_routing_entry() and
sanity checked by kvm_get_msi_route(), disallows having a GSI configured
to trigger multiple MSIs.

I.e. this is subtly a glorified nop, as KVM allows at most one MSI per
GSI, the for-loop can only ever process one entry, and that entry is the
new/current entry (see the WARN_ON_ONCE() added by "KVM: x86: Pass new
routing entries and irqfd when updating IRTEs" to ensure @new matches the
entry found in the routing table).

Tested-by: Sairaj Kodilkar <sarunkod@amd.com>
Link: https://lore.kernel.org/r/20250611224604.313496-25-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

1 files changed, 43 insertions, 64 deletions

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index e09722f5b5fa..a1a5b86a37fe 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -844,11 +844,10 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 			unsigned int host_irq, uint32_t guest_irq,
 			struct kvm_kernel_irq_routing_entry *new)
 {
-	struct kvm_kernel_irq_routing_entry *e;
-	struct kvm_irq_routing_table *irq_rt;
 	bool enable_remapped_mode = true;
-	bool set = !!new;
-	int idx, ret = 0;
+	struct vcpu_data vcpu_info;
+	struct vcpu_svm *svm = NULL;
+	int ret = 0;
 
 	if (!kvm_arch_has_assigned_device(kvm) || !kvm_arch_has_irq_bypass())
 		return 0;
@@ -860,72 +859,53 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 	svm_ir_list_del(irqfd);
 
 	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);
-
-	if (guest_irq >= irq_rt->nr_rt_entries ||
-		hlist_empty(&irq_rt->map[guest_irq])) {
-		pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
-			     guest_irq, irq_rt->nr_rt_entries);
-		goto out;
-	}
-
-	hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
-		struct vcpu_data vcpu_info;
-		struct vcpu_svm *svm = NULL;
+		 __func__, host_irq, guest_irq, !!new);
+
+	/**
+	 * 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 virtualization is disabled for the vcpu.
+	 * 4. IRQ has incompatible delivery mode (SMI, INIT, etc)
+	 */
+	if (new && new->type == KVM_IRQ_ROUTING_MSI &&
+	    !get_pi_vcpu_info(kvm, new, &vcpu_info, &svm) &&
+	    kvm_vcpu_apicv_active(&svm->vcpu)) {
+		struct amd_iommu_pi_data pi;
 
-		if (e->type != KVM_IRQ_ROUTING_MSI)
-			continue;
+		enable_remapped_mode = false;
 
-		WARN_ON_ONCE(new && memcmp(e, new, sizeof(*new)));
+		/*
+		 * Try to enable guest_mode in IRTE.  Note, the address
+		 * of the vCPU's AVIC backing page is passed to the
+		 * IOMMU via vcpu_info->pi_desc_addr.
+		 */
+		pi.ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->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 setup with legacy mode in the following cases:
-		 * 1. When cannot target interrupt to a specific vcpu.
-		 * 2. Unsetting posted interrupt.
-		 * 3. APIC virtualization is disabled for the vcpu.
-		 * 4. IRQ has incompatible delivery mode (SMI, INIT, etc)
+		 * 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 (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set &&
-		    kvm_vcpu_apicv_active(&svm->vcpu)) {
-			struct amd_iommu_pi_data pi;
-
-			enable_remapped_mode = false;
-
-			/*
-			 * Try to enable guest_mode in IRTE.  Note, the address
-			 * of the vCPU's AVIC backing page is passed to the
-			 * IOMMU via vcpu_info->pi_desc_addr.
-			 */
-			pi.ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->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, irqfd, &pi);
-		}
+		if (!ret)
+			ret = svm_ir_list_add(svm, irqfd, &pi);
+	}
 
-		if (!ret && svm) {
-			trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id,
-						 e->gsi, vcpu_info.vector,
-						 vcpu_info.pi_desc_addr, set);
-		}
+	if (!ret && svm) {
+		trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id,
+					 guest_irq, vcpu_info.vector,
+					 vcpu_info.pi_desc_addr, !!new);
+	}
 
-		if (ret < 0) {
-			pr_err("%s: failed to update PI IRTE\n", __func__);
-			goto out;
-		}
+	if (ret < 0) {
+		pr_err("%s: failed to update PI IRTE\n", __func__);
+		goto out;
 	}
 
 	if (enable_remapped_mode)
@@ -933,7 +913,6 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 	else
 		ret = 0;
 out:
-	srcu_read_unlock(&kvm->irq_srcu, idx);
 	return ret;
 }