diff mbox series

[v2,5/7] iommu/iova: to optimize the allocation performance of dma64

Message ID 1490930665-9696-6-git-send-email-thunder.leizhen@huawei.com
State Superseded
Headers show
Series iommu/iova: improve the allocation performance of dma64 | expand

Commit Message

Leizhen (ThunderTown) March 31, 2017, 3:24 a.m. UTC
Currently we always search free iova space for dma64 begin at the last
node of iovad rb-tree. In the worst case, there maybe too many nodes exist
at the tail, so that we should traverse many times for the first loop in
__alloc_and_insert_iova_range. As we traced, more than 10K times for the
case of iperf.

__alloc_and_insert_iova_range:
	......
	curr = __get_cached_rbnode(iovad, &limit_pfn);
		//--> return rb_last(&iovad->rbroot);
	while (curr) {
		......
		curr = rb_prev(curr);
	}

So add cached64_node to take the same effect as cached32_node, and add
the start_pfn boundary of dma64, to prevent a iova cross both dma32 and
dma64 area.
	|-------------------|------------------------------|
	|<--cached32_node-->|<--------cached64_node------->|
	|                   |
    start_pfn         dma_32bit_pfn + 1

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>

---
 drivers/iommu/iova.c | 46 +++++++++++++++++++++++++++-------------------
 include/linux/iova.h |  5 +++--
 2 files changed, 30 insertions(+), 21 deletions(-)

-- 
2.5.0
diff mbox series

Patch

diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 87a9332..23abe84 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -37,10 +37,15 @@  insert_iova_boundary(struct iova_domain *iovad)
 {
 	struct iova *iova;
 	unsigned long start_pfn_32bit = iovad->start_pfn;
+	unsigned long start_pfn_64bit = iovad->dma_32bit_pfn + 1;
 
 	iova = reserve_iova(iovad, start_pfn_32bit, start_pfn_32bit);
 	BUG_ON(!iova);
 	iovad->cached32_node = &iova->node;
+
+	iova = reserve_iova(iovad, start_pfn_64bit, start_pfn_64bit);
+	BUG_ON(!iova);
+	iovad->cached64_node = &iova->node;
 }
 
 void
@@ -62,8 +67,8 @@  init_iova_domain(struct iova_domain *iovad, unsigned long granule,
 	init_iova_rcaches(iovad);
 
 	/*
-	 * Insert boundary nodes for dma32. So cached32_node can not be NULL in
-	 * future.
+	 * Insert boundary nodes for dma32 and dma64. So cached32_node and
+	 * cached64_node can not be NULL in future.
 	 */
 	insert_iova_boundary(iovad);
 }
@@ -75,10 +80,10 @@  __get_cached_rbnode(struct iova_domain *iovad, unsigned long *limit_pfn)
 	struct rb_node *cached_node;
 	struct rb_node *next_node;
 
-	if (*limit_pfn > iovad->dma_32bit_pfn)
-		return rb_last(&iovad->rbroot);
-	else
+	if (*limit_pfn <= iovad->dma_32bit_pfn)
 		cached_node = iovad->cached32_node;
+	else
+		cached_node = iovad->cached64_node;
 
 	next_node = rb_next(cached_node);
 	if (next_node) {
@@ -94,29 +99,32 @@  static void
 __cached_rbnode_insert_update(struct iova_domain *iovad, struct iova *new)
 {
 	struct iova *cached_iova;
+	struct rb_node **cached_node;
 
-	if (new->pfn_hi > iovad->dma_32bit_pfn)
-		return;
+	if (new->pfn_hi <= iovad->dma_32bit_pfn)
+		cached_node = &iovad->cached32_node;
+	else
+		cached_node = &iovad->cached64_node;
 
-	cached_iova = rb_entry(iovad->cached32_node, struct iova, node);
+	cached_iova = rb_entry(*cached_node, struct iova, node);
 	if (new->pfn_lo <= cached_iova->pfn_lo)
-		iovad->cached32_node = rb_prev(&new->node);
+		*cached_node = rb_prev(&new->node);
 }
 
 static void
 __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
 {
 	struct iova *cached_iova;
-	struct rb_node *curr;
+	struct rb_node **cached_node;
 
-	curr = iovad->cached32_node;
-	cached_iova = rb_entry(curr, struct iova, node);
+	if (free->pfn_hi <= iovad->dma_32bit_pfn)
+		cached_node = &iovad->cached32_node;
+	else
+		cached_node = &iovad->cached64_node;
 
-	if (free->pfn_lo >= cached_iova->pfn_lo) {
-		/* only cache if it's below 32bit pfn */
-		if (free->pfn_hi <= iovad->dma_32bit_pfn)
-			iovad->cached32_node = rb_prev(&free->node);
-	}
+	cached_iova = rb_entry(*cached_node, struct iova, node);
+	if (free->pfn_lo >= cached_iova->pfn_lo)
+		*cached_node = rb_prev(&free->node);
 }
 
 /*
@@ -283,7 +291,7 @@  EXPORT_SYMBOL_GPL(iova_cache_put);
  * alloc_iova - allocates an iova
  * @iovad: - iova domain in question
  * @size: - size of page frames to allocate
- * @limit_pfn: - max limit address
+ * @limit_pfn: - max limit address(included)
  * @size_aligned: - set if size_aligned address range is required
  * This function allocates an iova in the range iovad->start_pfn to limit_pfn,
  * searching top-down from limit_pfn to iovad->start_pfn. If the size_aligned
@@ -402,7 +410,7 @@  EXPORT_SYMBOL_GPL(free_iova);
  * alloc_iova_fast - allocates an iova from rcache
  * @iovad: - iova domain in question
  * @size: - size of page frames to allocate
- * @limit_pfn: - max limit address
+ * @limit_pfn: - max limit address(included)
  * This function tries to satisfy an iova allocation from the rcache,
  * and falls back to regular allocation on failure.
 */
diff --git a/include/linux/iova.h b/include/linux/iova.h
index f27bb2c..844d723 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -40,10 +40,11 @@  struct iova_rcache {
 struct iova_domain {
 	spinlock_t	iova_rbtree_lock; /* Lock to protect update of rbtree */
 	struct rb_root	rbroot;		/* iova domain rbtree root */
-	struct rb_node	*cached32_node; /* Save last alloced node */
+	struct rb_node	*cached32_node; /* Save last alloced node, 32bits */
+	struct rb_node	*cached64_node; /* Save last alloced node, 64bits */
 	unsigned long	granule;	/* pfn granularity for this domain */
 	unsigned long	start_pfn;	/* Lower limit for this domain */
-	unsigned long	dma_32bit_pfn;
+	unsigned long	dma_32bit_pfn;	/* max dma32 limit address(included) */
 	struct iova_rcache rcaches[IOVA_RANGE_CACHE_MAX_SIZE];	/* IOVA range caches */
 };