[PATCH v3 04/62] KVM: SVM: Track per-vCPU IRTEs using kvm_kernel_irqfd structure

[Sean Christopherson <seanjc@google.com>]

Track the IRTEs that are posting to an SVM vCPU via the associated irqfd
structure and GSI routing instead of dynamically allocating a separate
data structure.  In addition to eliminating an atomic allocation, this
will allow hoisting much of the IRTE update logic to common x86.

Cc: Sairaj Kodilkar <sarunkod@amd.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/avic.c   | 71 +++++++++++++++------------------------
 arch/x86/kvm/svm/svm.h    | 10 +++---
 include/linux/kvm_irqfd.h |  3 ++
 3 files changed, 36 insertions(+), 48 deletions(-)

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index adacf00d6664..d33c01379421 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -75,14 +75,6 @@ static bool next_vm_id_wrapped = 0;
 static DEFINE_SPINLOCK(svm_vm_data_hash_lock);
 bool x2avic_enabled;
 
-/*
- * 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 */
-};
-
 static void avic_activate_vmcb(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = svm->vmcb01.ptr;
@@ -746,8 +738,8 @@ static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
 {
 	int ret = 0;
 	unsigned long flags;
-	struct amd_svm_iommu_ir *ir;
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct kvm_kernel_irqfd *irqfd;
 
 	if (!kvm_arch_has_assigned_device(vcpu->kvm))
 		return 0;
@@ -761,11 +753,11 @@ static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
 	if (list_empty(&svm->ir_list))
 		goto out;
 
-	list_for_each_entry(ir, &svm->ir_list, node) {
+	list_for_each_entry(irqfd, &svm->ir_list, vcpu_list) {
 		if (activate)
-			ret = amd_iommu_activate_guest_mode(ir->data);
+			ret = amd_iommu_activate_guest_mode(irqfd->irq_bypass_data);
 		else
-			ret = amd_iommu_deactivate_guest_mode(ir->data);
+			ret = amd_iommu_deactivate_guest_mode(irqfd->irq_bypass_data);
 		if (ret)
 			break;
 	}
@@ -774,27 +766,30 @@ static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
 	return ret;
 }
 
-static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
+static void svm_ir_list_del(struct vcpu_svm *svm,
+			    struct kvm_kernel_irqfd *irqfd,
+			    struct amd_iommu_pi_data *pi)
 {
 	unsigned long flags;
-	struct amd_svm_iommu_ir *cur;
+	struct kvm_kernel_irqfd *cur;
 
 	spin_lock_irqsave(&svm->ir_list_lock, flags);
-	list_for_each_entry(cur, &svm->ir_list, node) {
-		if (cur->data != pi->ir_data)
+	list_for_each_entry(cur, &svm->ir_list, vcpu_list) {
+		if (cur->irq_bypass_data != pi->ir_data)
 			continue;
-		list_del(&cur->node);
-		kfree(cur);
+		if (WARN_ON_ONCE(cur != irqfd))
+			continue;
+		list_del(&irqfd->vcpu_list);
 		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)
+static int svm_ir_list_add(struct vcpu_svm *svm,
+			   struct kvm_kernel_irqfd *irqfd,
+			   struct amd_iommu_pi_data *pi)
 {
-	int ret = 0;
 	unsigned long flags;
-	struct amd_svm_iommu_ir *ir;
 	u64 entry;
 
 	if (WARN_ON_ONCE(!pi->ir_data))
@@ -811,25 +806,14 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
 		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;
-		}
+		if (!prev_vcpu)
+			return -EINVAL;
 
 		prev_svm = to_svm(prev_vcpu);
-		svm_ir_list_del(prev_svm, pi);
+		svm_ir_list_del(prev_svm, irqfd, 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_ATOMIC | __GFP_ACCOUNT);
-	if (!ir) {
-		ret = -ENOMEM;
-		goto out;
-	}
-	ir->data = pi->ir_data;
+	irqfd->irq_bypass_data = pi->ir_data;
 
 	spin_lock_irqsave(&svm->ir_list_lock, flags);
 
@@ -844,10 +828,9 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
 		amd_iommu_update_ga(entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK,
 				    true, pi->ir_data);
 
-	list_add(&ir->node, &svm->ir_list);
+	list_add(&irqfd->vcpu_list, &svm->ir_list);
 	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
-out:
-	return ret;
+	return 0;
 }
 
 /*
@@ -951,7 +934,7 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 			 * scheduling information in IOMMU irte.
 			 */
 			if (!ret && pi.is_guest_mode)
-				svm_ir_list_add(svm, &pi);
+				svm_ir_list_add(svm, irqfd, &pi);
 		}
 
 		if (!ret && svm) {
@@ -992,7 +975,7 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 
 			vcpu = kvm_get_vcpu_by_id(kvm, id);
 			if (vcpu)
-				svm_ir_list_del(to_svm(vcpu), &pi);
+				svm_ir_list_del(to_svm(vcpu), irqfd, &pi);
 		}
 	}
 out:
@@ -1004,8 +987,8 @@ static inline int
 avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
 {
 	int ret = 0;
-	struct amd_svm_iommu_ir *ir;
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct kvm_kernel_irqfd *irqfd;
 
 	lockdep_assert_held(&svm->ir_list_lock);
 
@@ -1019,8 +1002,8 @@ avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
 	if (list_empty(&svm->ir_list))
 		return 0;
 
-	list_for_each_entry(ir, &svm->ir_list, node) {
-		ret = amd_iommu_update_ga(cpu, r, ir->data);
+	list_for_each_entry(irqfd, &svm->ir_list, vcpu_list) {
+		ret = amd_iommu_update_ga(cpu, r, irqfd->irq_bypass_data);
 		if (ret)
 			return ret;
 	}
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index b35fce30d923..cc27877d69ae 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -310,10 +310,12 @@ struct vcpu_svm {
 	u64 *avic_physical_id_cache;
 
 	/*
-	 * 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.
+	 * Per-vCPU list of irqfds that are eligible to post IRQs directly to
+	 * the vCPU (a.k.a. device posted IRQs, a.k.a. IRQ bypass).  The list
+	 * is used to reconfigure IRTEs when the vCPU is loaded/put (to set the
+	 * target pCPU), when AVIC is toggled on/off (to (de)activate bypass),
+	 * and if the irqfd becomes ineligible for posting (to put the IRTE
+	 * back into remapped mode).
 	 */
 	struct list_head ir_list;
 	spinlock_t ir_list_lock;
diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h
index 8ad43692e3bb..6510a48e62aa 100644
--- a/include/linux/kvm_irqfd.h
+++ b/include/linux/kvm_irqfd.h
@@ -59,6 +59,9 @@ struct kvm_kernel_irqfd {
 	struct work_struct shutdown;
 	struct irq_bypass_consumer consumer;
 	struct irq_bypass_producer *producer;
+
+	struct list_head vcpu_list;
+	void *irq_bypass_data;
 };
 
 #endif /* __LINUX_KVM_IRQFD_H */
-- 
2.50.0.rc1.591.g9c95f17f64-goog