From: Miaohe Lin <linmiaohe@huawei.com>
Date: Wed, 5 May 2021 01:33:25 +0000 (-0700)
Subject: mm/hugetlb: optimize the surplus state transfer code in move_hugetlb_state()
X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=5af1ab1d24e0842e2ca72c1fd0833864f6fa458a;p=linux.git

mm/hugetlb: optimize the surplus state transfer code in move_hugetlb_state()

We should not transfer the per-node surplus state when we do not cross the
node in order to save some cpu cycles

Link: https://lkml.kernel.org/r/20210308112809.26107-3-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 87104dc78e590..c3d47af591375 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5682,6 +5682,12 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason)
 		SetHPageTemporary(oldpage);
 		ClearHPageTemporary(newpage);
 
+		/*
+		 * There is no need to transfer the per-node surplus state
+		 * when we do not cross the node.
+		 */
+		if (new_nid == old_nid)
+			return;
 		spin_lock(&hugetlb_lock);
 		if (h->surplus_huge_pages_node[old_nid]) {
 			h->surplus_huge_pages_node[old_nid]--;