1 files changed, 207 insertions, 0 deletions

diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index 482036612adf..2be6b66b3856 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -138,6 +138,14 @@ struct its_ite {
 	u32 event_id;
 };
 
+struct vgic_translation_cache_entry {
+	struct list_head	entry;
+	phys_addr_t		db;
+	u32			devid;
+	u32			eventid;
+	struct vgic_irq		*irq;
+};
+
 /**
  * struct vgic_its_abi - ITS abi ops and settings
  * @cte_esz: collection table entry size
@@ -527,6 +535,127 @@ static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm,
 	return 0;
 }
 
+static struct vgic_irq *__vgic_its_check_cache(struct vgic_dist *dist,
+					       phys_addr_t db,
+					       u32 devid, u32 eventid)
+{
+	struct vgic_translation_cache_entry *cte;
+
+	list_for_each_entry(cte, &dist->lpi_translation_cache, entry) {
+		/*
+		 * If we hit a NULL entry, there is nothing after this
+		 * point.
+		 */
+		if (!cte->irq)
+			break;
+
+		if (cte->db != db || cte->devid != devid ||
+		    cte->eventid != eventid)
+			continue;
+
+		/*
+		 * Move this entry to the head, as it is the most
+		 * recently used.
+		 */
+		if (!list_is_first(&cte->entry, &dist->lpi_translation_cache))
+			list_move(&cte->entry, &dist->lpi_translation_cache);
+
+		return cte->irq;
+	}
+
+	return NULL;
+}
+
+static struct vgic_irq *vgic_its_check_cache(struct kvm *kvm, phys_addr_t db,
+					     u32 devid, u32 eventid)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	struct vgic_irq *irq;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
+	irq = __vgic_its_check_cache(dist, db, devid, eventid);
+	raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
+
+	return irq;
+}
+
+static void vgic_its_cache_translation(struct kvm *kvm, struct vgic_its *its,
+				       u32 devid, u32 eventid,
+				       struct vgic_irq *irq)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	struct vgic_translation_cache_entry *cte;
+	unsigned long flags;
+	phys_addr_t db;
+
+	/* Do not cache a directly injected interrupt */
+	if (irq->hw)
+		return;
+
+	raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
+
+	if (unlikely(list_empty(&dist->lpi_translation_cache)))
+		goto out;
+
+	/*
+	 * We could have raced with another CPU caching the same
+	 * translation behind our back, so let's check it is not in
+	 * already
+	 */
+	db = its->vgic_its_base + GITS_TRANSLATER;
+	if (__vgic_its_check_cache(dist, db, devid, eventid))
+		goto out;
+
+	/* Always reuse the last entry (LRU policy) */
+	cte = list_last_entry(&dist->lpi_translation_cache,
+			      typeof(*cte), entry);
+
+	/*
+	 * Caching the translation implies having an extra reference
+	 * to the interrupt, so drop the potential reference on what
+	 * was in the cache, and increment it on the new interrupt.
+	 */
+	if (cte->irq)
+		__vgic_put_lpi_locked(kvm, cte->irq);
+
+	vgic_get_irq_kref(irq);
+
+	cte->db		= db;
+	cte->devid	= devid;
+	cte->eventid	= eventid;
+	cte->irq	= irq;
+
+	/* Move the new translation to the head of the list */
+	list_move(&cte->entry, &dist->lpi_translation_cache);
+
+out:
+	raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
+}
+
+void vgic_its_invalidate_cache(struct kvm *kvm)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	struct vgic_translation_cache_entry *cte;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&dist->lpi_list_lock, flags);
+
+	list_for_each_entry(cte, &dist->lpi_translation_cache, entry) {
+		/*
+		 * If we hit a NULL entry, there is nothing after this
+		 * point.
+		 */
+		if (!cte->irq)
+			break;
+
+		__vgic_put_lpi_locked(kvm, cte->irq);
+		cte->irq = NULL;
+	}
+
+	raw_spin_unlock_irqrestore(&dist->lpi_list_lock, flags);
+}
+
 int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its,
 			 u32 devid, u32 eventid, struct vgic_irq **irq)
 {
@@ -547,6 +676,8 @@ int vgic_its_resolve_lpi(struct kvm *kvm, struct vgic_its *its,
 	if (!vcpu->arch.vgic_cpu.lpis_enabled)
 		return -EBUSY;
 
+	vgic_its_cache_translation(kvm, its, devid, eventid, ite->irq);
+
 	*irq = ite->irq;
 	return 0;
 }
@@ -608,6 +739,25 @@ static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its,
 	return 0;
 }
 
+int vgic_its_inject_cached_translation(struct kvm *kvm, struct kvm_msi *msi)
+{
+	struct vgic_irq *irq;
+	unsigned long flags;
+	phys_addr_t db;
+
+	db = (u64)msi->address_hi << 32 | msi->address_lo;
+	irq = vgic_its_check_cache(kvm, db, msi->devid, msi->data);
+
+	if (!irq)
+		return -1;
+
+	raw_spin_lock_irqsave(&irq->irq_lock, flags);
+	irq->pending_latch = true;
+	vgic_queue_irq_unlock(kvm, irq, flags);
+
+	return 0;
+}
+
 /*
  * Queries the KVM IO bus framework to get the ITS pointer from the given
  * doorbell address.
@@ -619,6 +769,9 @@ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi)
 	struct vgic_its *its;
 	int ret;
 
+	if (!vgic_its_inject_cached_translation(kvm, msi))
+		return 1;
+
 	its = vgic_msi_to_its(kvm, msi);
 	if (IS_ERR(its))
 		return PTR_ERR(its);
@@ -691,6 +844,8 @@ static int vgic_its_cmd_handle_discard(struct kvm *kvm, struct vgic_its *its,
 		 * don't bother here since we clear the ITTE anyway and the
 		 * pending state is a property of the ITTE struct.
 		 */
+		vgic_its_invalidate_cache(kvm);
+
 		its_free_ite(kvm, ite);
 		return 0;
 	}
@@ -726,6 +881,8 @@ static int vgic_its_cmd_handle_movi(struct kvm *kvm, struct vgic_its *its,
 	ite->collection = collection;
 	vcpu = kvm_get_vcpu(kvm, collection->target_addr);
 
+	vgic_its_invalidate_cache(kvm);
+
 	return update_affinity(ite->irq, vcpu);
 }
 
@@ -954,6 +1111,8 @@ static void vgic_its_free_device(struct kvm *kvm, struct its_device *device)
 	list_for_each_entry_safe(ite, temp, &device->itt_head, ite_list)
 		its_free_ite(kvm, ite);
 
+	vgic_its_invalidate_cache(kvm);
+
 	list_del(&device->dev_list);
 	kfree(device);
 }
@@ -1059,6 +1218,7 @@ static int vgic_its_cmd_handle_mapc(struct kvm *kvm, struct vgic_its *its,
 
 	if (!valid) {
 		vgic_its_free_collection(its, coll_id);
+		vgic_its_invalidate_cache(kvm);
 	} else {
 		collection = find_collection(its, coll_id);
 
@@ -1207,6 +1367,8 @@ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its,
 		vgic_put_irq(kvm, irq);
 	}
 
+	vgic_its_invalidate_cache(kvm);
+
 	kfree(intids);
 	return 0;
 }
@@ -1557,6 +1719,8 @@ static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its,
 		goto out;
 
 	its->enabled = !!(val & GITS_CTLR_ENABLE);
+	if (!its->enabled)
+		vgic_its_invalidate_cache(kvm);
 
 	/*
 	 * Try to process any pending commands. This function bails out early
@@ -1657,6 +1821,47 @@ out:
 	return ret;
 }
 
+/* Default is 16 cached LPIs per vcpu */
+#define LPI_DEFAULT_PCPU_CACHE_SIZE	16
+
+void vgic_lpi_translation_cache_init(struct kvm *kvm)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	unsigned int sz;
+	int i;
+
+	if (!list_empty(&dist->lpi_translation_cache))
+		return;
+
+	sz = atomic_read(&kvm->online_vcpus) * LPI_DEFAULT_PCPU_CACHE_SIZE;
+
+	for (i = 0; i < sz; i++) {
+		struct vgic_translation_cache_entry *cte;
+
+		/* An allocation failure is not fatal */
+		cte = kzalloc(sizeof(*cte), GFP_KERNEL);
+		if (WARN_ON(!cte))
+			break;
+
+		INIT_LIST_HEAD(&cte->entry);
+		list_add(&cte->entry, &dist->lpi_translation_cache);
+	}
+}
+
+void vgic_lpi_translation_cache_destroy(struct kvm *kvm)
+{
+	struct vgic_dist *dist = &kvm->arch.vgic;
+	struct vgic_translation_cache_entry *cte, *tmp;
+
+	vgic_its_invalidate_cache(kvm);
+
+	list_for_each_entry_safe(cte, tmp,
+				 &dist->lpi_translation_cache, entry) {
+		list_del(&cte->entry);
+		kfree(cte);
+	}
+}
+
 #define INITIAL_BASER_VALUE						  \
 	(GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWb)		| \
 	 GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, SameAsInner)		| \
@@ -1685,6 +1890,8 @@ static int vgic_its_create(struct kvm_device *dev, u32 type)
 			kfree(its);
 			return ret;
 		}
+
+		vgic_lpi_translation_cache_init(dev->kvm);
 	}
 
 	mutex_init(&its->its_lock);