[PATCH v2 1/4] md/raid1: fix writes_pending and barrier reference leaks on write failures

[Abd-Alrhman Masalkhi]

raid1_make_request() acquires a writes_pending reference with
md_write_start() before calling raid1_write_request(). Several failure
paths in raid1_write_request() complete the bio and return without
reaching the normal write completion path, causing the corresponding
md_write_end() to be skipped.

Make raid1_write_request() return a status indicating whether the write
request was successfully queued. This allows raid1_make_request() to
call md_write_end() when raid1_write_request() fails.

Additionally, if wait_blocked_rdev() fails after wait_barrier()
succeeds, the associated barrier reference is not released.

Call allow_barrier() before returning from that path to keep the barrier
accounting balanced.

Fixes: b1a7ad8b5c4f ("md/raid1: Handle bio_split() errors")
Fixes: f2a38abf5f1c ("md/raid1: Atomic write support")
Fixes: 5aa705039c4f ("md: raid1 add nowait support")
Reported-by: sashiko-bot <sashiko-bot@xxxxxxxxxx>
Closes: https://sashiko.dev/#/patchset/20260611083514.754922-1-abd.masalkhi@xxxxxxxxx?part=1
Closes: https://sashiko.dev/#/patchset/20260611132500.763528-1-abd.masalkhi@xxxxxxxxx?part=1
Signed-off-by: Abd-Alrhman Masalkhi <abd.masalkhi@xxxxxxxxx>
---
Changes in v2:
 - fix writes_pending leaks in addition to the barrier reference leak.
 - make raid1_write_request() return whether the write was successfully
   queued so raid1_make_request() can release writes_pending references
   on failure paths.
 - Link v1: https://lore.kernel.org/linux-raid/20260611132500.763528-1-abd.masalkhi@xxxxxxxxx/
---
 drivers/md/raid1.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index b1ed4cc6ade4..f0e1c7125972 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1501,7 +1501,7 @@ static void raid1_start_write_behind(struct mddev *mddev, struct r1bio *r1_bio,
 
 }
 
-static void raid1_write_request(struct mddev *mddev, struct bio *bio,
+static bool raid1_write_request(struct mddev *mddev, struct bio *bio,
 				int max_write_sectors)
 {
 	struct r1conf *conf = mddev->private;
@@ -1512,6 +1512,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	int max_sectors;
 	bool write_behind = false;
 	bool is_discard = (bio_op(bio) == REQ_OP_DISCARD);
+	sector_t sector = bio->bi_iter.bi_sector;
 
 	if (mddev_is_clustered(mddev) &&
 	    mddev->cluster_ops->area_resyncing(mddev, WRITE,
@@ -1519,7 +1520,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 
 		if (bio->bi_opf & REQ_NOWAIT) {
 			bio_wouldblock_error(bio);
-			return;
+			return false;
 		}
 		wait_event_idle(conf->wait_barrier,
 				!mddev->cluster_ops->area_resyncing(mddev, WRITE,
@@ -1535,12 +1536,13 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	if (!wait_barrier(conf, bio->bi_iter.bi_sector,
 				bio->bi_opf & REQ_NOWAIT)) {
 		bio_wouldblock_error(bio);
-		return;
+		return false;
 	}
 
 	if (!wait_blocked_rdev(mddev, bio)) {
 		bio_wouldblock_error(bio);
-		return;
+		allow_barrier(conf, sector);
+		return false;
 	}
 
 	r1_bio = alloc_r1bio(mddev, bio);
@@ -1699,7 +1701,8 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 
 	/* In case raid1d snuck in to freeze_array */
 	wake_up_barrier(conf);
-	return;
+	return true;
+
 err_handle:
 	for (k = 0; k < i; k++) {
 		if (r1_bio->bios[k]) {
@@ -1709,6 +1712,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	}
 
 	raid_end_bio_io(r1_bio);
+	return false;
 }
 
 static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
@@ -1732,8 +1736,9 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
 	if (bio_data_dir(bio) == READ)
 		raid1_read_request(mddev, bio, sectors, NULL);
 	else {
-		md_write_start(mddev,bio);
-		raid1_write_request(mddev, bio, sectors);
+		md_write_start(mddev, bio);
+		if (!raid1_write_request(mddev, bio, sectors))
+			md_write_end(mddev);
 	}
 	return true;
 }
-- 
2.43.0