[PATCH 5/5] f2fs: fix to search whole dirty segmap when get_victim

[Chao Yu <chao2.yu@samsung.com>]

In ->get_victim we get max_search value from dirty_i->nr_dirty without
protection of seglist_lock, after that, nr_dirty can be increased/decreased
before we hold seglist_lock lock.
Then in main loop we attempt to traverse all dirty section one time to find
victim section, but it's not accurate to use max_search as the total loop count,
because we might lose checking several sections or check sections redundantly
for the case of nr_dirty are increased or decreased previously.

Signed-off-by: Chao Yu <chao2.yu@samsung.com>
---
 fs/f2fs/gc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 075ea1e..4481edc 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -263,14 +263,14 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 	unsigned int secno, max_cost;
 	int nsearched = 0;
 
+	mutex_lock(&dirty_i->seglist_lock);
+
 	p.alloc_mode = alloc_mode;
 	select_policy(sbi, gc_type, type, &p);
 
 	p.min_segno = NULL_SEGNO;
 	p.min_cost = max_cost = get_max_cost(sbi, &p);
 
-	mutex_lock(&dirty_i->seglist_lock);
-
 	if (p.alloc_mode == LFS && gc_type == FG_GC) {
 		p.min_segno = check_bg_victims(sbi);
 		if (p.min_segno != NULL_SEGNO)
-- 
2.0.1.474.g72c7794



------------------------------------------------------------------------------
Want excitement?
Manually upgrade your production database.
When you want reliability, choose Perforce
Perforce version control. Predictably reliable.
http://pubads.g.doubleclick.net/gampad/clk?id=157508191&iu=/4140/ostg.clktrk