Merge tag 'md-7.2-20260531' of https://git.kernel.org/pub/scm/linux/kernel/git/mdraid/linux into for-7.2/block

Pull MD updates and fixes from Yu Kuai:

"Bug Fixes:
 - Only requeue dm-raid bios when dm is suspending. (Benjamin Marzinski)
 - Reset raid10 read_slot when reusing r10bio for discard. (Chen Cheng)
 - Fix raid1/raid10 deadlock in read error recovery path.
   (Abd-Alrhman Masalkhi)
 - Fix raid1/raid10 error-path detection with md_cloned_bio().
   (Abd-Alrhman Masalkhi)
 - Fix raid1/raid10 bio accounting for split md cloned bios.
   (Abd-Alrhman Masalkhi)
 - Fix raid1 nr_pending leak in REQ_ATOMIC bad-block path.
   (Abd-Alrhman Masalkhi)

 Improvements:
 - Skip redundant raid_disks updates when the value is unchanged.
   (Abd-Alrhman Masalkhi)

 Cleanups:
 - Update MAINTAINERS email addresses. (Yu Kuai, Li Nan)
 - Clean up raid1 read error handling. (Christoph Hellwig)
 - Move the exceed_read_errors condition out of fix_read_error().
   (Christoph Hellwig)
 - Use str_plural() in raid0 dump_zones(). (Thorsten Blum)"

* tag 'md-7.2-20260531' of https://git.kernel.org/pub/scm/linux/kernel/git/mdraid/linux:
  md/raid0: use str_plural helper in dump_zones
  raid1: fix nr_pending leak in REQ_ATOMIC bad-block error path
  md/raid1: move the exceed_read_errors condition out of fix_read_error
  md/raid1: cleanup handle_read_error
  md/raid1,raid10: fix bio accounting for split md cloned bios
  md/raid1,raid10: fix error-path detection with md_cloned_bio()
  md/raid1,raid10: fix deadlock in read error recovery path
  md/raid10: reset read_slot when reusing r10bio for discard
  md: skip redundant raid_disks update when value is unchanged
  dm-raid: only requeue bios when dm is suspending
  MAINTAINERS: Update Li Nan's E-mail address
  MAINTAINERS: update Yu Kuai's email address

7 files changed, 93 insertions, 54 deletions

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index c5dc083c7244..8f5a5e1342a9 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3831,6 +3831,7 @@ static void raid_presuspend(struct dm_target *ti)
 	 * resume, raid_postsuspend() is too late.
 	 */
 	set_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
+	set_bit(MD_DM_SUSPENDING, &mddev->flags);
 
 	if (!reshape_interrupted(mddev))
 		return;
@@ -3847,13 +3848,16 @@ static void raid_presuspend(struct dm_target *ti)
 static void raid_presuspend_undo(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
+	struct mddev *mddev = &rs->md;
 
+	clear_bit(MD_DM_SUSPENDING, &mddev->flags);
 	clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
 }
 
 static void raid_postsuspend(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
+	struct mddev *mddev = &rs->md;
 
 	if (!test_and_set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) {
 		/*
@@ -3864,6 +3868,8 @@ static void raid_postsuspend(struct dm_target *ti)
 		mddev_suspend(&rs->md, false);
 		rs->md.ro = MD_RDONLY;
 	}
+	clear_bit(MD_DM_SUSPENDING, &mddev->flags);
+
 }
 
 static void attempt_restore_of_faulty_devices(struct raid_set *rs)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 8b568eee8743..096bb64e87bd 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -395,17 +395,24 @@ static bool is_suspended(struct mddev *mddev, struct bio *bio)
 bool md_handle_request(struct mddev *mddev, struct bio *bio)
 {
 check_suspended:
-	if (is_suspended(mddev, bio)) {
-		/* Bail out if REQ_NOWAIT is set for the bio */
-		if (bio->bi_opf & REQ_NOWAIT) {
-			bio_wouldblock_error(bio);
-			return true;
+	if (unlikely(md_cloned_bio(mddev, bio))) {
+		/*
+		 * This bio is an MD cloned bio and already holds an
+		 * active_io reference, so percpu_ref_get() is safe here.
+		 */
+		percpu_ref_get(&mddev->active_io);
+	} else {
+		if (is_suspended(mddev, bio)) {
+			/* Bail out if REQ_NOWAIT is set for the bio */
+			if (bio->bi_opf & REQ_NOWAIT) {
+				bio_wouldblock_error(bio);
+				return true;
+			}
+			wait_event(mddev->sb_wait, !is_suspended(mddev, bio));
 		}
-		wait_event(mddev->sb_wait, !is_suspended(mddev, bio));
+		if (!percpu_ref_tryget_live(&mddev->active_io))
+			goto check_suspended;
 	}
-	if (!percpu_ref_tryget_live(&mddev->active_io))
-		goto check_suspended;
-
 	if (!mddev->pers->make_request(mddev, bio)) {
 		percpu_ref_put(&mddev->active_io);
 		if (mddev_is_dm(mddev) && mddev->pers->prepare_suspend)
@@ -4414,9 +4421,10 @@ raid_disks_store(struct mddev *mddev, const char *buf, size_t len)
 	err = mddev_suspend_and_lock(mddev);
 	if (err)
 		return err;
-	if (mddev->pers)
-		err = update_raid_disks(mddev, n);
-	else if (mddev->reshape_position != MaxSector) {
+	if (mddev->pers) {
+		if (n != mddev->raid_disks)
+			err = update_raid_disks(mddev, n);
+	} else if (mddev->reshape_position != MaxSector) {
 		struct md_rdev *rdev;
 		int olddisks = mddev->raid_disks - mddev->delta_disks;
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 52c378086046..d8daf0f75cbb 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -346,6 +346,7 @@ struct md_cluster_operations;
  * @MD_HAS_SUPERBLOCK: There is persistence sb in member disks.
  * @MD_FAILLAST_DEV: Allow last rdev to be removed.
  * @MD_SERIALIZE_POLICY: Enforce write IO is not reordered, just used by raid1.
+ * @MD_DM_SUSPENDING: This DM raid device is suspending.
  *
  * change UNSUPPORTED_MDDEV_FLAGS for each array type if new flag is added
  */
@@ -365,6 +366,7 @@ enum mddev_flags {
 	MD_HAS_SUPERBLOCK,
 	MD_FAILLAST_DEV,
 	MD_SERIALIZE_POLICY,
+	MD_DM_SUSPENDING,
 };
 
 enum mddev_sb_flags {
@@ -1042,6 +1044,11 @@ void mddev_update_io_opt(struct mddev *mddev, unsigned int nr_stripes);
 
 extern const struct block_device_operations md_fops;
 
+static inline bool md_cloned_bio(struct mddev *mddev, struct bio *bio)
+{
+	return bio->bi_pool == &mddev->io_clone_set;
+}
+
 /*
  * MD devices can be used undeneath by DM, in which case ->gendisk is NULL.
  */
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 2cdaf7495d92..2c000b3a5f49 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -14,6 +14,7 @@
 #include <linux/seq_file.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/string_choices.h>
 #include <trace/events/block.h>
 #include "md.h"
 #include "raid0.h"
@@ -43,7 +44,7 @@ static void dump_zones(struct mddev *mddev)
 	int raid_disks = conf->strip_zone[0].nb_dev;
 	pr_debug("md: RAID0 configuration for %s - %d zone%s\n",
 		 mdname(mddev),
-		 conf->nr_strip_zones, conf->nr_strip_zones==1?"":"s");
+		 conf->nr_strip_zones, str_plural(conf->nr_strip_zones));
 	for (j = 0; j < conf->nr_strip_zones; j++) {
 		char line[200];
 		int len = 0;
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index cc628a1be52c..5b9368bd9e70 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1343,11 +1343,18 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	bool r1bio_existed = !!r1_bio;
 
 	/*
-	 * If r1_bio is set, we are blocking the raid1d thread
-	 * so there is a tiny risk of deadlock.  So ask for
+	 * An md cloned bio indicates we are in the error path.
+	 * This is more reliable than checking r1_bio, which might
+	 * be NULL even in the error path if a failed bio was split.
+	 */
+	bool err_path = md_cloned_bio(mddev, bio);
+
+	/*
+	 * If we are in the error path, we are blocking the raid1d
+	 * thread so there is a tiny risk of deadlock.  So ask for
 	 * emergency memory if needed.
 	 */
-	gfp_t gfp = r1_bio ? (GFP_NOIO | __GFP_HIGH) : GFP_NOIO;
+	gfp_t gfp = err_path ? (GFP_NOIO | __GFP_HIGH) : GFP_NOIO;
 
 	/*
 	 * Still need barrier for READ in case that whole
@@ -1411,7 +1418,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
 	}
 
 	r1_bio->read_disk = rdisk;
-	if (!r1bio_existed) {
+	if (likely(!md_cloned_bio(mddev, bio))) {
 		md_account_bio(mddev, &bio);
 		r1_bio->master_bio = bio;
 	}
@@ -1596,8 +1603,10 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 				 * complexity of supporting that is not worth
 				 * the benefit.
 				 */
-				if (bio->bi_opf & REQ_ATOMIC)
+				if (bio->bi_opf & REQ_ATOMIC) {
+					rdev_dec_pending(rdev, mddev);
 					goto err_handle;
+				}
 
 				good_sectors = first_bad - r1_bio->sector;
 				if (good_sectors < max_sectors)
@@ -2411,11 +2420,6 @@ static void fix_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 	struct mddev *mddev = conf->mddev;
 	struct md_rdev *rdev = conf->mirrors[read_disk].rdev;
 
-	if (exceed_read_errors(mddev, rdev)) {
-		r1_bio->bios[r1_bio->read_disk] = IO_BLOCKED;
-		return;
-	}
-
 	while(sectors) {
 		int s = sectors;
 		int d = read_disk;
@@ -2627,35 +2631,36 @@ static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
 
 static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
 {
+	struct md_rdev *rdev = conf->mirrors[r1_bio->read_disk].rdev;
+	struct bio *bio = r1_bio->bios[r1_bio->read_disk];
 	struct mddev *mddev = conf->mddev;
-	struct bio *bio;
-	struct md_rdev *rdev;
 	sector_t sector;
 
 	clear_bit(R1BIO_ReadError, &r1_bio->state);
-	/* we got a read error. Maybe the drive is bad.  Maybe just
-	 * the block and we can fix it.
-	 * We freeze all other IO, and try reading the block from
-	 * other devices.  When we find one, we re-write
-	 * and check it that fixes the read error.
-	 * This is all done synchronously while the array is
-	 * frozen
-	 */
 
-	bio = r1_bio->bios[r1_bio->read_disk];
 	bio_put(bio);
 	r1_bio->bios[r1_bio->read_disk] = NULL;
 
-	rdev = conf->mirrors[r1_bio->read_disk].rdev;
-	if (mddev->ro == 0
-	    && !test_bit(FailFast, &rdev->flags)) {
-		freeze_array(conf, 1);
-		fix_read_error(conf, r1_bio);
-		unfreeze_array(conf);
-	} else if (mddev->ro == 0 && test_bit(FailFast, &rdev->flags)) {
+	/*
+	 * We got a read error. Maybe the drive is bad.  Maybe just the block
+	 * and we can fix it.
+	 *
+	 * If allowed, freeze all other IO, and try reading the block from other
+	 * devices.  If we find one, we re-write and check it that fixes the
+	 * read error.  This is all done synchronously while the array is
+	 * frozen.
+	 */
+	if (mddev->ro) {
+		r1_bio->bios[r1_bio->read_disk] = IO_BLOCKED;
+	} else if (test_bit(FailFast, &rdev->flags)) {
 		md_error(mddev, rdev);
 	} else {
-		r1_bio->bios[r1_bio->read_disk] = IO_BLOCKED;
+		freeze_array(conf, 1);
+		if (exceed_read_errors(mddev, rdev))
+			r1_bio->bios[r1_bio->read_disk] = IO_BLOCKED;
+		else
+			fix_read_error(conf, r1_bio);
+		unfreeze_array(conf);
 	}
 
 	rdev_dec_pending(rdev, conf->mddev);
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index f905dc391b74..cee5a253a281 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1146,7 +1146,7 @@ static bool regular_request_wait(struct mddev *mddev, struct r10conf *conf,
 }
 
 static void raid10_read_request(struct mddev *mddev, struct bio *bio,
-				struct r10bio *r10_bio, bool io_accounting)
+				struct r10bio *r10_bio)
 {
 	struct r10conf *conf = mddev->private;
 	struct bio *read_bio;
@@ -1155,7 +1155,20 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	char b[BDEVNAME_SIZE];
 	int slot = r10_bio->read_slot;
 	struct md_rdev *err_rdev = NULL;
-	gfp_t gfp = GFP_NOIO;
+
+	/*
+	 * An md cloned bio indicates we are in the error path.
+	 * This is more reliable than checking slot, which might
+	 * be -1 even in the error path if a failed bio was split.
+	 */
+	bool err_path = md_cloned_bio(mddev, bio);
+
+	/*
+	 * If we are in the error path, we are blocking the raid10d
+	 * thread so there is a tiny risk of deadlock.  So ask for
+	 * emergency memory if needed.
+	 */
+	gfp_t gfp = err_path ? (GFP_NOIO | __GFP_HIGH) : GFP_NOIO;
 
 	if (slot >= 0 && r10_bio->devs[slot].rdev) {
 		/*
@@ -1166,11 +1179,6 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 		 * we lose the device name in error messages.
 		 */
 		int disk;
-		/*
-		 * As we are blocking raid10, it is a little safer to
-		 * use __GFP_HIGH.
-		 */
-		gfp = GFP_NOIO | __GFP_HIGH;
 
 		disk = r10_bio->devs[slot].devnum;
 		err_rdev = conf->mirrors[disk].rdev;
@@ -1218,7 +1226,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
 	}
 	slot = r10_bio->read_slot;
 
-	if (io_accounting) {
+	if (likely(!md_cloned_bio(mddev, bio))) {
 		md_account_bio(mddev, &bio);
 		r10_bio->master_bio = bio;
 	}
@@ -1544,7 +1552,7 @@ static void __make_request(struct mddev *mddev, struct bio *bio, int sectors)
 			conf->geo.raid_disks);
 
 	if (bio_data_dir(bio) == READ)
-		raid10_read_request(mddev, bio, r10_bio, true);
+		raid10_read_request(mddev, bio, r10_bio);
 	else
 		raid10_write_request(mddev, bio, r10_bio);
 }
@@ -1727,6 +1735,7 @@ retry_discard:
 	r10_bio->mddev = mddev;
 	r10_bio->state = 0;
 	r10_bio->sectors = 0;
+	r10_bio->read_slot = -1;
 	memset(r10_bio->devs, 0, sizeof(r10_bio->devs[0]) * geo->raid_disks);
 	wait_blocked_dev(mddev, r10_bio);
 
@@ -2858,7 +2867,7 @@ static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio)
 
 	rdev_dec_pending(rdev, mddev);
 	r10_bio->state = 0;
-	raid10_read_request(mddev, r10_bio->master_bio, r10_bio, false);
+	raid10_read_request(mddev, r10_bio->master_bio, r10_bio);
 	/*
 	 * allow_barrier after re-submit to ensure no sync io
 	 * can be issued while regular io pending.
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 0d76e82f4506..65ae7d8930fc 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -6042,8 +6042,11 @@ out_release:
 	raid5_release_stripe(sh);
 out:
 	if (ret == STRIPE_SCHEDULE_AND_RETRY && reshape_interrupted(mddev)) {
-		bi->bi_status = BLK_STS_RESOURCE;
-		ret = STRIPE_WAIT_RESHAPE;
+		if (!mddev_is_dm(mddev) ||
+		    test_bit(MD_DM_SUSPENDING, &mddev->flags)) {
+			bi->bi_status = BLK_STS_RESOURCE;
+			ret = STRIPE_WAIT_RESHAPE;
+		}
 		pr_err_ratelimited("dm-raid456: io across reshape position while reshape can't make progress");
 	}
 	return ret;