__vmalloc_area_node never pass -1 to alloc_pages_node.
It means node's validity check is unnecessary.
So we can use alloc_pages_exact_node instead of alloc_pages_node.
It could avoid comparison and branch as 6484eb3e2a81807722 tried.
Cc: Nick Piggin <npiggin@xxxxxxx>
Signed-off-by: Minchan Kim <minchan.kim@xxxxxxxxx>
---
mm/vmalloc.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index ae00746..7abf423 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1499,7 +1499,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
if (node < 0)
page = alloc_page(gfp_mask);
else
- page = alloc_pages_node(node, gfp_mask, 0);
+ page = alloc_pages_exact_node(node, gfp_mask, 0);
if (unlikely(!page)) {
/* Successfully allocated i pages, free them in __vunmap() */
--
1.7.0.5
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>