summaryrefslogtreecommitdiffstats
path: root/drivers/md/raid5-cache.c
diff options
context:
space:
mode:
authorNeilBrown <neilb@suse.com>2017-03-15 04:05:13 +0100
committerShaohua Li <shli@fb.com>2017-03-23 03:16:30 +0100
commit016c76ac76e4c678b01a75a602dc6be0282f5b29 (patch)
treeed943bdfc80ab4ff7aa3228023f6f0dc0c0992fa /drivers/md/raid5-cache.c
parentmd/raid5: call bio_endio() directly rather than queueing for later. (diff)
downloadlinux-016c76ac76e4c678b01a75a602dc6be0282f5b29.tar.xz
linux-016c76ac76e4c678b01a75a602dc6be0282f5b29.zip
md/raid5: use bio_inc_remaining() instead of repurposing bi_phys_segments as a counter
md/raid5 needs to keep track of how many stripe_heads are processing a bio so that it can delay calling bio_endio() until all stripe_heads have completed. It currently uses 16 bits of ->bi_phys_segments for this purpose. 16 bits is only enough for 256M requests, and it is possible for a single bio to be larger than this, which causes problems. Also, the bio struct contains a larger counter, __bi_remaining, which has a purpose very similar to the purpose of our counter. So stop using ->bi_phys_segments, and instead use __bi_remaining. This means we don't need to initialize the counter, as our caller initializes it to '1'. It also means we can call bio_endio() directly as it tests this counter internally. Signed-off-by: NeilBrown <neilb@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
Diffstat (limited to 'drivers/md/raid5-cache.c')
-rw-r--r--drivers/md/raid5-cache.c3
1 files changed, 1 insertions, 2 deletions
diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 5be8dbc5d91b..25eb048298fe 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -318,8 +318,7 @@ r5c_return_dev_pending_writes(struct r5conf *conf, struct r5dev *dev)
dev->sector + STRIPE_SECTORS) {
wbi2 = r5_next_bio(wbi, dev->sector);
md_write_end(conf->mddev);
- if (!raid5_dec_bi_active_stripes(wbi))
- bio_endio(wbi);
+ bio_endio(wbi);
wbi = wbi2;
}
}