diff mbox series

[RESEND,4/7] md/raid1: factor out helper to handle blocked rdev from raid1_write_request()

Message ID 20241031033114.3845582-5-yukuai1@huaweicloud.com (mailing list archive)
State Accepted
Headers show
Series md: enhance faulty checking for blocked handling | expand

Commit Message

Yu Kuai Oct. 31, 2024, 3:31 a.m. UTC
From: Yu Kuai <yukuai3@huawei.com>

Currently raid1 is preparing IO for underlying disks while checking if
any disk is blocked, if so allocated resources must be released, then
waiting for rdev to be unblocked and try to prepare IO again.

Make code cleaner by checking blocked rdev first, it doesn't matter if
rdev is blocked while issuing IO, the IO will wait for rdev to be
unblocked or not.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Tested-by: Mariusz Tkaczyk <mariusz.tkaczyk@linux.intel.com>
---
 drivers/md/raid1.c | 84 ++++++++++++++++++++++++++--------------------
 1 file changed, 48 insertions(+), 36 deletions(-)
diff mbox series

Patch

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 6c9d24203f39..1679c1e9b3d5 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1412,6 +1412,49 @@  static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	submit_bio_noacct(read_bio);
 }
 
+static bool wait_blocked_rdev(struct mddev *mddev, struct bio *bio)
+{
+	struct r1conf *conf = mddev->private;
+	int disks = conf->raid_disks * 2;
+	int i;
+
+retry:
+	for (i = 0; i < disks; i++) {
+		struct md_rdev *rdev = conf->mirrors[i].rdev;
+
+		if (!rdev)
+			continue;
+
+		if (test_bit(Blocked, &rdev->flags)) {
+			if (bio->bi_opf & REQ_NOWAIT)
+				return false;
+
+			mddev_add_trace_msg(rdev->mddev, "raid1 wait rdev %d blocked",
+					    rdev->raid_disk);
+			atomic_inc(&rdev->nr_pending);
+			md_wait_for_blocked_rdev(rdev, rdev->mddev);
+			goto retry;
+		}
+
+		/* don't write here until the bad block is acknowledged */
+		if (test_bit(WriteErrorSeen, &rdev->flags) &&
+		    rdev_has_badblock(rdev, bio->bi_iter.bi_sector,
+				      bio_sectors(bio)) < 0) {
+			if (bio->bi_opf & REQ_NOWAIT)
+				return false;
+
+			set_bit(BlockedBadBlocks, &rdev->flags);
+			mddev_add_trace_msg(rdev->mddev, "raid1 wait rdev %d blocked",
+					    rdev->raid_disk);
+			atomic_inc(&rdev->nr_pending);
+			md_wait_for_blocked_rdev(rdev, rdev->mddev);
+			goto retry;
+		}
+	}
+
+	return true;
+}
+
 static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 				int max_write_sectors)
 {
@@ -1419,7 +1462,6 @@  static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	struct r1bio *r1_bio;
 	int i, disks;
 	unsigned long flags;
-	struct md_rdev *blocked_rdev;
 	int first_clone;
 	int max_sectors;
 	bool write_behind = false;
@@ -1457,7 +1499,11 @@  static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		return;
 	}
 
- retry_write:
+	if (!wait_blocked_rdev(mddev, bio)) {
+		bio_wouldblock_error(bio);
+		return;
+	}
+
 	r1_bio = alloc_r1bio(mddev, bio);
 	r1_bio->sectors = max_write_sectors;
 
@@ -1473,7 +1519,6 @@  static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	 */
 
 	disks = conf->raid_disks * 2;
-	blocked_rdev = NULL;
 	max_sectors = r1_bio->sectors;
 	for (i = 0;  i < disks; i++) {
 		struct md_rdev *rdev = conf->mirrors[i].rdev;
@@ -1486,11 +1531,6 @@  static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		if (!is_discard && rdev && test_bit(WriteMostly, &rdev->flags))
 			write_behind = true;
 
-		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
-			atomic_inc(&rdev->nr_pending);
-			blocked_rdev = rdev;
-			break;
-		}
 		r1_bio->bios[i] = NULL;
 		if (!rdev || test_bit(Faulty, &rdev->flags)) {
 			if (i < conf->raid_disks)
@@ -1506,13 +1546,6 @@  static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 
 			is_bad = is_badblock(rdev, r1_bio->sector, max_sectors,
 					     &first_bad, &bad_sectors);
-			if (is_bad < 0) {
-				/* mustn't write here until the bad block is
-				 * acknowledged*/
-				set_bit(BlockedBadBlocks, &rdev->flags);
-				blocked_rdev = rdev;
-				break;
-			}
 			if (is_bad && first_bad <= r1_bio->sector) {
 				/* Cannot write here at all */
 				bad_sectors -= (r1_bio->sector - first_bad);
@@ -1543,27 +1576,6 @@  static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		r1_bio->bios[i] = bio;
 	}
 
-	if (unlikely(blocked_rdev)) {
-		/* Wait for this device to become unblocked */
-		int j;
-
-		for (j = 0; j < i; j++)
-			if (r1_bio->bios[j])
-				rdev_dec_pending(conf->mirrors[j].rdev, mddev);
-		mempool_free(r1_bio, &conf->r1bio_pool);
-		allow_barrier(conf, bio->bi_iter.bi_sector);
-
-		if (bio->bi_opf & REQ_NOWAIT) {
-			bio_wouldblock_error(bio);
-			return;
-		}
-		mddev_add_trace_msg(mddev, "raid1 wait rdev %d blocked",
-				blocked_rdev->raid_disk);
-		md_wait_for_blocked_rdev(blocked_rdev, mddev);
-		wait_barrier(conf, bio->bi_iter.bi_sector, false);
-		goto retry_write;
-	}
-
 	/*
 	 * When using a bitmap, we may call alloc_behind_master_bio below.
 	 * alloc_behind_master_bio allocates a copy of the data payload a page