[v3,5/6] iommu/iova: move the caculation of pad mask out of loop

Message ID 1495094397-9132-6-git-send-email-thunder.leizhen@huawei.com
State New
Headers show
Series
  • iommu/iova: improve the allocation performance of dma64
Related show

Commit Message

Zhen Lei May 18, 2017, 7:59 a.m.
I'm not sure whether the compiler can optimize it, but move it out will
be better. At least, it does not require lock protection.

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

---
 drivers/iommu/iova.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

-- 
2.5.0

Patch hide | download patch | download mbox

diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 711b10a..338930b 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -155,23 +155,16 @@  iova_insert_rbtree(struct rb_root *root, struct iova *iova,
 	rb_insert_color(&iova->node, root);
 }
 
-/*
- * Computes the padding size required, to make the start address
- * naturally aligned on the power-of-two order of its size
- */
-static unsigned int
-iova_get_pad_size(unsigned int size, unsigned int limit_pfn)
-{
-	return (limit_pfn + 1 - size) & (__roundup_pow_of_two(size) - 1);
-}
-
 static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 		unsigned long size, unsigned long limit_pfn,
 			struct iova *new, bool size_aligned)
 {
 	struct rb_node *prev, *curr;
 	unsigned long flags;
-	unsigned int pad_size = 0;
+	unsigned long pad_mask, pad_size = 0;
+
+	if (size_aligned)
+		pad_mask = __roundup_pow_of_two(size) - 1;
 
 	/* Walk the tree backwards */
 	spin_lock_irqsave(&iovad->iova_rbtree_lock, flags);
@@ -185,8 +178,13 @@  static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
 		else if (limit_pfn < curr_iova->pfn_hi)
 			goto adjust_limit_pfn;
 		else {
+			/*
+			 * Computes the padding size required, to make the start
+			 * address naturally aligned on the power-of-two order
+			 * of its size
+			 */
 			if (size_aligned)
-				pad_size = iova_get_pad_size(size, limit_pfn);
+				pad_size = (limit_pfn + 1 - size) & pad_mask;
 			if ((curr_iova->pfn_hi + size + pad_size) <= limit_pfn)
 				break;	/* found a free slot */
 		}