Merge branch 'for-next/iommu/iova' into for-next/iommu/core

IOVA allocator updates for 5.11, including removal of unused symbols and
functions as well as some optimisations to improve allocation behaviour
in the face of fragmentation.

* for-next/iommu/iova:
  iommu: Stop exporting free_iova_mem()
  iommu: Stop exporting alloc_iova_mem()
  iommu: Delete split_and_remove_iova()
  iommu: avoid taking iova_rbtree_lock twice
  iommu/iova: Free global iova rcache on iova alloc failure
  iommu/iova: Retry from last rb tree node if iova search fails

1 files changed, 47 insertions, 53 deletions

diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 30d969a4c5fd..4bb3293ae4d7 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -25,6 +25,7 @@ static void init_iova_rcaches(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 void free_global_cached_iovas(struct iova_domain *iovad);
 
 void
 init_iova_domain(struct iova_domain *iovad, unsigned long granule,
@@ -184,8 +185,9 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 	struct rb_node *curr, *prev;
 	struct iova *curr_iova;
 	unsigned long flags;
-	unsigned long new_pfn;
+	unsigned long new_pfn, retry_pfn;
 	unsigned long align_mask = ~0UL;
+	unsigned long high_pfn = limit_pfn, low_pfn = iovad->start_pfn;
 
 	if (size_aligned)
 		align_mask <<= fls_long(size - 1);
@@ -198,15 +200,25 @@ static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 
 	curr = __get_cached_rbnode(iovad, limit_pfn);
 	curr_iova = rb_entry(curr, struct iova, node);
+	retry_pfn = curr_iova->pfn_hi + 1;
+
+retry:
 	do {
-		limit_pfn = min(limit_pfn, curr_iova->pfn_lo);
-		new_pfn = (limit_pfn - size) & align_mask;
+		high_pfn = min(high_pfn, curr_iova->pfn_lo);
+		new_pfn = (high_pfn - size) & align_mask;
 		prev = curr;
 		curr = rb_prev(curr);
 		curr_iova = rb_entry(curr, struct iova, node);
-	} while (curr && new_pfn <= curr_iova->pfn_hi);
-
-	if (limit_pfn < size || new_pfn < iovad->start_pfn) {
+	} 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);
+			goto retry;
+		}
 		iovad->max32_alloc_size = size;
 		goto iova32_full;
 	}
@@ -231,18 +243,16 @@ static struct kmem_cache *iova_cache;
 static unsigned int iova_cache_users;
 static DEFINE_MUTEX(iova_cache_mutex);
 
-struct iova *alloc_iova_mem(void)
+static struct iova *alloc_iova_mem(void)
 {
 	return kmem_cache_zalloc(iova_cache, GFP_ATOMIC | __GFP_NOWARN);
 }
-EXPORT_SYMBOL(alloc_iova_mem);
 
-void free_iova_mem(struct iova *iova)
+static void free_iova_mem(struct iova *iova)
 {
 	if (iova->pfn_lo != IOVA_ANCHOR)
 		kmem_cache_free(iova_cache, iova);
 }
-EXPORT_SYMBOL(free_iova_mem);
 
 int iova_cache_get(void)
 {
@@ -390,10 +400,14 @@ EXPORT_SYMBOL_GPL(__free_iova);
 void
 free_iova(struct iova_domain *iovad, unsigned long pfn)
 {
-	struct iova *iova = find_iova(iovad, pfn);
+	unsigned long flags;
+	struct iova *iova;
 
+	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
+	iova = private_find_iova(iovad, pfn);
 	if (iova)
-		__free_iova(iovad, iova);
+		private_free_iova(iovad, iova);
+	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
 
 }
 EXPORT_SYMBOL_GPL(free_iova);
@@ -431,6 +445,7 @@ retry:
 		flush_rcache = false;
 		for_each_online_cpu(cpu)
 			free_cpu_cached_iovas(cpu, iovad);
+		free_global_cached_iovas(iovad);
 		goto retry;
 	}
 
@@ -725,47 +740,6 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
 }
 EXPORT_SYMBOL_GPL(copy_reserved_iova);
 
-struct iova *
-split_and_remove_iova(struct iova_domain *iovad, struct iova *iova,
-		      unsigned long pfn_lo, unsigned long pfn_hi)
-{
-	unsigned long flags;
-	struct iova *prev = NULL, *next = NULL;
-
-	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
-	if (iova->pfn_lo < pfn_lo) {
-		prev = alloc_and_init_iova(iova->pfn_lo, pfn_lo - 1);
-		if (prev == NULL)
-			goto error;
-	}
-	if (iova->pfn_hi > pfn_hi) {
-		next = alloc_and_init_iova(pfn_hi + 1, iova->pfn_hi);
-		if (next == NULL)
-			goto error;
-	}
-
-	__cached_rbnode_delete_update(iovad, iova);
-	rb_erase(&iova->node, &iovad->rbroot);
-
-	if (prev) {
-		iova_insert_rbtree(&iovad->rbroot, prev, NULL);
-		iova->pfn_lo = pfn_lo;
-	}
-	if (next) {
-		iova_insert_rbtree(&iovad->rbroot, next, NULL);
-		iova->pfn_hi = pfn_hi;
-	}
-	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
-
-	return iova;
-
-error:
-	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
-	if (prev)
-		free_iova_mem(prev);
-	return NULL;
-}
-
 /*
  * Magazine caches for IOVA ranges.  For an introduction to magazines,
  * see the USENIX 2001 paper "Magazines and Vmem: Extending the Slab
@@ -1046,5 +1020,25 @@ void free_cpu_cached_iovas(unsigned int cpu, struct iova_domain *iovad)
 	}
 }
 
+/*
+ * free all the IOVA ranges of global cache
+ */
+static void free_global_cached_iovas(struct iova_domain *iovad)
+{
+	struct iova_rcache *rcache;
+	unsigned long flags;
+	int i, j;
+
+	for (i = 0; i < IOVA_RANGE_CACHE_MAX_SIZE; ++i) {
+		rcache = &iovad->rcaches[i];
+		spin_lock_irqsave(&rcache->lock, flags);
+		for (j = 0; j < rcache->depot_size; ++j) {
+			iova_magazine_free_pfns(rcache->depot[j], iovad);
+			iova_magazine_free(rcache->depot[j]);
+		}
+		rcache->depot_size = 0;
+		spin_unlock_irqrestore(&rcache->lock, flags);
+	}
+}
 MODULE_AUTHOR("Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>");
 MODULE_LICENSE("GPL");