Merge tag 'md-6.13-20241105' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-6.13/block

Pull MD changes from Song:

"1. Enhance handling of faulty and blocked devices, by Yu Kuai.
 2. raid5-ppl atomic improvement, by Uros Bizjak.
 3. md-bitmap fix, by Yuan Can."

* tag 'md-6.13-20241105' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md:
  md/md-bitmap: Add missing destroy_work_on_stack()
  md/raid5: don't set Faulty rdev for blocked_rdev
  md/raid10: don't wait for Faulty rdev in wait_blocked_rdev()
  md/raid1: don't wait for Faulty rdev in wait_blocked_rdev()
  md/raid1: factor out helper to handle blocked rdev from raid1_write_request()
  md: don't record new badblocks for faulty rdev
  md: don't wait faulty rdev in md_wait_for_blocked_rdev()
  md: add a new helper rdev_blocked()
  md/raid5-ppl: Use atomic64_inc_return() in ppl_new_iounit()

Author: axboe

drivers/md/md-bitmap.c

@@ -1285,6 +1285,7 @@ static void bitmap_unplug_async(struct bitmap *bitmap)
 
 	queue_work(md_bitmap_wq, &unplug_work.work);
 	wait_for_completion(&done);
+	destroy_work_on_stack(&unplug_work.work);
 }
 
 static void bitmap_unplug(struct mddev *mddev, bool sync)

drivers/md/md.c

@@ -9762,9 +9762,7 @@ EXPORT_SYMBOL(md_reap_sync_thread);
 void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev)
 {
 	sysfs_notify_dirent_safe(rdev->sysfs_state);
-	wait_event_timeout(rdev->blocked_wait,
-			   !test_bit(Blocked, &rdev->flags) &&
-			   !test_bit(BlockedBadBlocks, &rdev->flags),
+	wait_event_timeout(rdev->blocked_wait, !rdev_blocked(rdev),
 			   msecs_to_jiffies(5000));
 	rdev_dec_pending(rdev, mddev);
 }
@@ -9793,6 +9791,17 @@ int rdev_set_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 {
 	struct mddev *mddev = rdev->mddev;
 	int rv;
+
+	/*
+	 * Recording new badblocks for faulty rdev will force unnecessary
+	 * super block updating. This is fragile for external management because
+	 * userspace daemon may trying to remove this device and deadlock may
+	 * occur. This will be probably solved in the mdadm, but it is safer to
+	 * avoid it.
+	 */
+	if (test_bit(Faulty, &rdev->flags))
+		return 1;
+
 	if (is_new)
 		s += rdev->new_data_offset;
 	else

drivers/md/md.h

@@ -1002,6 +1002,30 @@ static inline void mddev_trace_remap(struct mddev *mddev, struct bio *bio,
 		trace_block_bio_remap(bio, disk_devt(mddev->gendisk), sector);
 }
 
+static inline bool rdev_blocked(struct md_rdev *rdev)
+{
+	/*
+	 * Blocked will be set by error handler and cleared by daemon after
+	 * updating superblock, meanwhile write IO should be blocked to prevent
+	 * reading old data after power failure.
+	 */
+	if (test_bit(Blocked, &rdev->flags))
+		return true;
+
+	/*
+	 * Faulty device should not be accessed anymore, there is no need to
+	 * wait for bad block to be acknowledged.
+	 */
+	if (test_bit(Faulty, &rdev->flags))
+		return false;
+
+	/* rdev is blocked by badblocks. */
+	if (test_bit(BlockedBadBlocks, &rdev->flags))
+		return true;
+
+	return false;
+}
+
 #define mddev_add_trace_msg(mddev, fmt, args...)			\
 do {									\
 	if (!mddev_is_dm(mddev))					\

drivers/md/raid1.c

@@ -1412,14 +1412,47 @@ 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;
+
+		/* 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)
+			set_bit(BlockedBadBlocks, &rdev->flags);
+
+		if (rdev_blocked(rdev)) {
+			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;
+		}
+	}
+
+	return true;
+}
+
 static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 				int max_write_sectors)
 {
 	struct r1conf *conf = mddev->private;
 	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 +1490,11 @@ 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 +1510,6 @@ 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 +1522,6 @@ 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 +1537,6 @@ 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 +1567,6 @@ 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

drivers/md/raid10.c

@@ -1285,50 +1285,46 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
 
 static void wait_blocked_dev(struct mddev *mddev, struct r10bio *r10_bio)
 {
-	int i;
 	struct r10conf *conf = mddev->private;
 	struct md_rdev *blocked_rdev;
+	int i;
 
 retry_wait:
 	blocked_rdev = NULL;
 	for (i = 0; i < conf->copies; i++) {
 		struct md_rdev *rdev, *rrdev;
 
 		rdev = conf->mirrors[i].rdev;
-		rrdev = conf->mirrors[i].replacement;
-		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
-			atomic_inc(&rdev->nr_pending);
-			blocked_rdev = rdev;
-			break;
-		}
-		if (rrdev && unlikely(test_bit(Blocked, &rrdev->flags))) {
-			atomic_inc(&rrdev->nr_pending);
-			blocked_rdev = rrdev;
-			break;
-		}
-
-		if (rdev && test_bit(WriteErrorSeen, &rdev->flags)) {
+		if (rdev) {
 			sector_t dev_sector = r10_bio->devs[i].addr;
 
 			/*
 			 * Discard request doesn't care the write result
 			 * so it doesn't need to wait blocked disk here.
 			 */
-			if (!r10_bio->sectors)
-				continue;
-
-			if (rdev_has_badblock(rdev, dev_sector,
-					      r10_bio->sectors) < 0) {
+			if (test_bit(WriteErrorSeen, &rdev->flags) &&
+			    r10_bio->sectors &&
+			    rdev_has_badblock(rdev, dev_sector,
+					      r10_bio->sectors) < 0)
 				/*
-				 * Mustn't write here until the bad block
-				 * is acknowledged
+				 * Mustn't write here until the bad
+				 * block is acknowledged
 				 */
-				atomic_inc(&rdev->nr_pending);
 				set_bit(BlockedBadBlocks, &rdev->flags);
+
+			if (rdev_blocked(rdev)) {
 				blocked_rdev = rdev;
+				atomic_inc(&rdev->nr_pending);
 				break;
 			}
 		}
+
+		rrdev = conf->mirrors[i].replacement;
+		if (rrdev && rdev_blocked(rrdev)) {
+			atomic_inc(&rrdev->nr_pending);
+			blocked_rdev = rrdev;
+			break;
+		}
 	}
 
 	if (unlikely(blocked_rdev)) {

drivers/md/raid5-ppl.c

@@ -258,7 +258,7 @@ static struct ppl_io_unit *ppl_new_iounit(struct ppl_log *log,
 	memset(pplhdr->reserved, 0xff, PPL_HDR_RESERVED);
 	pplhdr->signature = cpu_to_le32(ppl_conf->signature);
 
-	io->seq = atomic64_add_return(1, &ppl_conf->seq);
+	io->seq = atomic64_inc_return(&ppl_conf->seq);
 	pplhdr->generation = cpu_to_le64(io->seq);
 
 	return io;

drivers/md/raid5.c

@@ -4724,14 +4724,13 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 		if (rdev) {
 			is_bad = rdev_has_badblock(rdev, sh->sector,
 						   RAID5_STRIPE_SECTORS(conf));
-			if (s->blocked_rdev == NULL
-			    && (test_bit(Blocked, &rdev->flags)
-				|| is_bad < 0)) {
+			if (s->blocked_rdev == NULL) {
 				if (is_bad < 0)
-					set_bit(BlockedBadBlocks,
-						&rdev->flags);
-				s->blocked_rdev = rdev;
-				atomic_inc(&rdev->nr_pending);
+					set_bit(BlockedBadBlocks, &rdev->flags);
+				if (rdev_blocked(rdev)) {
+					s->blocked_rdev = rdev;
+					atomic_inc(&rdev->nr_pending);
+				}
 			}
 		}
 		clear_bit(R5_Insync, &dev->flags);