diff mbox series

[RESEND] drbd: fix potential silent data corruption

Message ID 20220330185551.3553196-1-christoph.boehmwalder@linbit.com (mailing list archive)
State New, archived
Headers show
Series [RESEND] drbd: fix potential silent data corruption | expand

Commit Message

Christoph Böhmwalder March 30, 2022, 6:55 p.m. UTC 
From: Lars Ellenberg <lars.ellenberg@linbit.com>

Scenario:
---------

bio chain generated by blk_queue_split().
Some split bio fails and propagates its error status to the "parent" bio.
But then the (last part of the) parent bio itself completes without error.

We would clobber the already recorded error status with BLK_STS_OK,
causing silent data corruption.

Reproducer:
-----------

How to trigger this in the real world within seconds:

DRBD on top of degraded parity raid,
small stripe_cache_size, large read_ahead setting.
Drop page cache (sysctl vm.drop_caches=1, fadvise "DONTNEED",
umount and mount again, "reboot").

Cause significant read ahead.

Large read ahead request is split by blk_queue_split().
Parts of the read ahead that are already in the stripe cache,
or find an available stripe cache to use, can be serviced.
Parts of the read ahead that would need "too much work",
would need to wait for a "stripe_head" to become available,
are rejected immediately.

For larger read ahead requests that are split in many pieces, it is very
likely that some "splits" will be serviced, but then the stripe cache is
exhausted/busy, and the remaining ones will be rejected.

Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Christoph Böhmwalder <christoph.boehmwalder@linbit.com>
Cc: <stable@vger.kernel.org> # 4.13.x
---
 drivers/block/drbd/drbd_req.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

Comments

Christoph Hellwig March 31, 2022, 5:45 a.m. UTC | #1 
The change looks good, but this really should grow a proper Fixes tag.
Christoph Hellwig March 31, 2022, 5:46 a.m. UTC | #2 
On Wed, Mar 30, 2022 at 10:45:47PM -0700, Christoph Hellwig wrote:
> The change looks good, but this really should grow a proper Fixes tag.
> 

And for the resend fix the spelling of Jens' email address.
diff mbox series

Patch

diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index c04394518b07..e1e58e91ee58 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -180,7 +180,8 @@  void start_new_tl_epoch(struct drbd_connection *connection)
 void complete_master_bio(struct drbd_device *device,
 		struct bio_and_error *m)
 {
-	m->bio->bi_status = errno_to_blk_status(m->error);
+	if (unlikely(m->error))
+		m->bio->bi_status = errno_to_blk_status(m->error);
 	bio_endio(m->bio);
 	dec_ap_bio(device);
 }