1 files changed, 83 insertions, 13 deletions

diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index e6e2fa85271c..b7ecd5b08039 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -22,11 +22,28 @@ static unsigned long iova_rcache_get(struct iova_domain *iovad,
 				     unsigned long size,
 				     unsigned long limit_pfn);
 static void init_iova_rcaches(struct iova_domain *iovad);
+static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad);
 static void free_iova_rcaches(struct iova_domain *iovad);
 static void fq_destroy_all_entries(struct iova_domain *iovad);
 static void fq_flush_timeout(struct timer_list *t);
+
+static int iova_cpuhp_dead(unsigned int cpu, struct hlist_node *node)
+{
+	struct iova_domain *iovad;
+
+	iovad = hlist_entry_safe(node, struct iova_domain, cpuhp_dead);
+
+	free_cpu_cached_iovas(cpu, iovad);
+	return 0;
+}
+
 static void free_global_cached_iovas(struct iova_domain *iovad);
 
+static struct iova *to_iova(struct rb_node *node)
+{
+	return rb_entry(node, struct iova, node);
+}
+
 void
 init_iova_domain(struct iova_domain *iovad, unsigned long granule,
 	unsigned long start_pfn)
@@ -51,6 +68,7 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule,
 	iovad->anchor.pfn_lo = iovad->anchor.pfn_hi = IOVA_ANCHOR;
 	rb_link_node(&iovad->anchor.node, NULL, &iovad->rbroot.rb_node);
 	rb_insert_color(&iovad->anchor.node, &iovad->rbroot);
+	cpuhp_state_add_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD, &iovad->cpuhp_dead);
 	init_iova_rcaches(iovad);
 }
 EXPORT_SYMBOL_GPL(init_iova_domain);
@@ -136,7 +154,7 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
 {
 	struct iova *cached_iova;
 
-	cached_iova = rb_entry(iovad->cached32_node, struct iova, node);
+	cached_iova = to_iova(iovad->cached32_node);
 	if (free == cached_iova ||
 	    (free->pfn_hi < iovad->dma_32bit_pfn &&
 	     free->pfn_lo >= cached_iova->pfn_lo)) {
@@ -144,11 +162,48 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
 		iovad->max32_alloc_size = iovad->dma_32bit_pfn;
 	}
 
-	cached_iova = rb_entry(iovad->cached_node, struct iova, node);
+	cached_iova = to_iova(iovad->cached_node);
 	if (free->pfn_lo >= cached_iova->pfn_lo)
 		iovad->cached_node = rb_next(&free->node);
 }
 
+static struct rb_node *iova_find_limit(struct iova_domain *iovad, unsigned long limit_pfn)
+{
+	struct rb_node *node, *next;
+	/*
+	 * Ideally what we'd like to judge here is whether limit_pfn is close
+	 * enough to the highest-allocated IOVA that starting the allocation
+	 * walk from the anchor node will be quicker than this initial work to
+	 * find an exact starting point (especially if that ends up being the
+	 * anchor node anyway). This is an incredibly crude approximation which
+	 * only really helps the most likely case, but is at least trivially easy.
+	 */
+	if (limit_pfn > iovad->dma_32bit_pfn)
+		return &iovad->anchor.node;
+
+	node = iovad->rbroot.rb_node;
+	while (to_iova(node)->pfn_hi < limit_pfn)
+		node = node->rb_right;
+
+search_left:
+	while (node->rb_left && to_iova(node->rb_left)->pfn_lo >= limit_pfn)
+		node = node->rb_left;
+
+	if (!node->rb_left)
+		return node;
+
+	next = node->rb_left;
+	while (next->rb_right) {
+		next = next->rb_right;
+		if (to_iova(next)->pfn_lo >= limit_pfn) {
+			node = next;
+			goto search_left;
+		}
+	}
+
+	return node;
+}
+
 /* Insert the iova into domain rbtree by holding writer lock */
 static void
 iova_insert_rbtree(struct rb_root *root, struct iova *iova,
@@ -159,7 +214,7 @@ iova_insert_rbtree(struct rb_root *root, struct iova *iova,
 	new = (start) ? &start : &(root->rb_node);
 	/* Figure out where to put new node */
 	while (*new) {
-		struct iova *this = rb_entry(*new, struct iova, node);
+		struct iova *this = to_iova(*new);
 
 		parent = *new;
 
@@ -198,7 +253,7 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 		goto iova32_full;
 
 	curr = __get_cached_rbnode(iovad, limit_pfn);
-	curr_iova = rb_entry(curr, struct iova, node);
+	curr_iova = to_iova(curr);
 	retry_pfn = curr_iova->pfn_hi + 1;
 
 retry:
@@ -207,15 +262,15 @@ retry:
 		new_pfn = (high_pfn - size) & align_mask;
 		prev = curr;
 		curr = rb_prev(curr);
-		curr_iova = rb_entry(curr, struct iova, node);
+		curr_iova = to_iova(curr);
 	} while (curr && new_pfn <= curr_iova->pfn_hi && new_pfn >= low_pfn);
 
 	if (high_pfn < size || new_pfn < low_pfn) {
 		if (low_pfn == iovad->start_pfn && retry_pfn < limit_pfn) {
 			high_pfn = limit_pfn;
 			low_pfn = retry_pfn;
-			curr = &iovad->anchor.node;
-			curr_iova = rb_entry(curr, struct iova, node);
+			curr = iova_find_limit(iovad, limit_pfn);
+			curr_iova = to_iova(curr);
 			goto retry;
 		}
 		iovad->max32_alloc_size = size;
@@ -257,10 +312,21 @@ int iova_cache_get(void)
 {
 	mutex_lock(&iova_cache_mutex);
 	if (!iova_cache_users) {
+		int ret;
+
+		ret = cpuhp_setup_state_multi(CPUHP_IOMMU_IOVA_DEAD, "iommu/iova:dead", NULL,
+					iova_cpuhp_dead);
+		if (ret) {
+			mutex_unlock(&iova_cache_mutex);
+			pr_err("Couldn't register cpuhp handler\n");
+			return ret;
+		}
+
 		iova_cache = kmem_cache_create(
 			"iommu_iova", sizeof(struct iova), 0,
 			SLAB_HWCACHE_ALIGN, NULL);
 		if (!iova_cache) {
+			cpuhp_remove_multi_state(CPUHP_IOMMU_IOVA_DEAD);
 			mutex_unlock(&iova_cache_mutex);
 			pr_err("Couldn't create iova cache\n");
 			return -ENOMEM;
@@ -282,8 +348,10 @@ void iova_cache_put(void)
 		return;
 	}
 	iova_cache_users--;
-	if (!iova_cache_users)
+	if (!iova_cache_users) {
+		cpuhp_remove_multi_state(CPUHP_IOMMU_IOVA_DEAD);
 		kmem_cache_destroy(iova_cache);
+	}
 	mutex_unlock(&iova_cache_mutex);
 }
 EXPORT_SYMBOL_GPL(iova_cache_put);
@@ -331,7 +399,7 @@ private_find_iova(struct iova_domain *iovad, unsigned long pfn)
 	assert_spin_locked(&iovad->iova_rbtree_lock);
 
 	while (node) {
-		struct iova *iova = rb_entry(node, struct iova, node);
+		struct iova *iova = to_iova(node);
 
 		if (pfn < iova->pfn_lo)
 			node = node->rb_left;
@@ -467,7 +535,6 @@ free_iova_fast(struct iova_domain *iovad, unsigned long pfn, unsigned long size)
 
 	free_iova(iovad, pfn);
 }
-EXPORT_SYMBOL_GPL(free_iova_fast);
 
 #define fq_ring_for_each(i, fq) \
 	for ((i) = (fq)->head; (i) != (fq)->tail; (i) = ((i) + 1) % IOVA_FQ_SIZE)
@@ -606,6 +673,9 @@ void put_iova_domain(struct iova_domain *iovad)
 {
 	struct iova *iova, *tmp;
 
+	cpuhp_state_remove_instance_nocalls(CPUHP_IOMMU_IOVA_DEAD,
+					    &iovad->cpuhp_dead);
+
 	free_iova_flush_queue(iovad);
 	free_iova_rcaches(iovad);
 	rbtree_postorder_for_each_entry_safe(iova, tmp, &iovad->rbroot, node)
@@ -617,7 +687,7 @@ static int
 __is_range_overlap(struct rb_node *node,
 	unsigned long pfn_lo, unsigned long pfn_hi)
 {
-	struct iova *iova = rb_entry(node, struct iova, node);
+	struct iova *iova = to_iova(node);
 
 	if ((pfn_lo <= iova->pfn_hi) && (pfn_hi >= iova->pfn_lo))
 		return 1;
@@ -685,7 +755,7 @@ reserve_iova(struct iova_domain *iovad,
 	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
 	for (node = rb_first(&iovad->rbroot); node; node = rb_next(node)) {
 		if (__is_range_overlap(node, pfn_lo, pfn_hi)) {
-			iova = rb_entry(node, struct iova, node);
+			iova = to_iova(node);
 			__adjust_overlap_range(iova, &pfn_lo, &pfn_hi);
 			if ((pfn_lo >= iova->pfn_lo) &&
 				(pfn_hi <= iova->pfn_hi))
@@ -970,7 +1040,7 @@ static void free_iova_rcaches(struct iova_domain *iovad)
 /*
  * free all the IOVA ranges cached by a cpu (used when cpu is unplugged)
  */
-void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad)
+static void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad)
 {
 	struct iova_cpu_rcache *cpu_rcache;
 	struct iova_rcache *rcache;