Merge tag 'md-6.11-20240612' of...

Merge tag 'md-6.11-20240612' of git://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-6.11/block

Pull MD updates from Song:

"The major changes in this PR are:

 - sync_action fix and refactoring, by Yu Kuai;
 - Various small fixes by Christoph Hellwig, Li Nan, and Ofir Gal."

* tag 'md-6.11-20240612' of git://git.kernel.org/pub/scm/linux/kernel/git/song/md:
  md/raid5: avoid BUG_ON() while continue reshape after reassembling
  md: pass in max_sectors for pers->sync_request()
  md: factor out helpers for different sync_action in md_do_sync()
  md: replace last_sync_action with new enum type
  md: use new helpers in md_do_sync()
  md: don't fail action_store() if sync_thread is not registered
  md: remove parameter check_seq for stop_sync_thread()
  md: replace sysfs api sync_action with new helpers
  md: factor out helper to start reshape from action_store()
  md: add new helpers for sync_action
  md: add a new enum type sync_action
  md: rearrange recovery_flags
  md/md-bitmap: fix writing non bitmap pages
  md/raid1: don't free conf on raid0_run failure
  md/raid0: don't free conf on raid0_run failure
  md: make md_flush_request() more readable
  md: fix deadlock between mddev_suspend and flush bio
  md: change the return value type of md_write_start to void
  md: do not delete safemode_timer in mddev_suspend

drivers/md/dm-raid.c

@@ -3542,7 +3542,7 @@ static void raid_status(struct dm_target *ti, status_type_t type,
 		recovery = rs->md.recovery;
 		state = decipher_sync_action(mddev, recovery);
 		progress = rs_get_progress(rs, recovery, state, resync_max_sectors);
-		resync_mismatches = (mddev->last_sync_action && !strcasecmp(mddev->last_sync_action, "check")) ?
+		resync_mismatches = mddev->last_sync_action == ACTION_CHECK ?
 				    atomic64_read(&mddev->resync_mismatches) : 0;
 
 		/* HM FIXME: do we want another state char for raid0? It shows 'D'/'A'/'-' now */

drivers/md/md-bitmap.c

@@ -227,6 +227,8 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap,
 	struct block_device *bdev;
 	struct mddev *mddev = bitmap->mddev;
 	struct bitmap_storage *store = &bitmap->storage;
+	unsigned int bitmap_limit = (bitmap->storage.file_pages - pg_index) <<
+		PAGE_SHIFT;
 	loff_t sboff, offset = mddev->bitmap_info.offset;
 	sector_t ps = pg_index * PAGE_SIZE / SECTOR_SIZE;
 	unsigned int size = PAGE_SIZE;
@@ -269,11 +271,9 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap,
 		if (size == 0)
 			/* bitmap runs in to data */
 			return -EINVAL;
-	} else {
-		/* DATA METADATA BITMAP - no problems */
 	}
 
-	md_super_write(mddev, rdev, sboff + ps, (int) size, page);
+	md_super_write(mddev, rdev, sboff + ps, (int)min(size, bitmap_limit), page);
 	return 0;
 }
 

drivers/md/md.h

@@ -34,6 +34,61 @@
  */
 #define	MD_FAILFAST	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT)
 
+/* Status of sync thread. */
+enum sync_action {
+	/*
+	 * Represent by MD_RECOVERY_SYNC, start when:
+	 * 1) after assemble, sync data from first rdev to other copies, this
+	 * must be done first before other sync actions and will only execute
+	 * once;
+	 * 2) resize the array(notice that this is not reshape), sync data for
+	 * the new range;
+	 */
+	ACTION_RESYNC,
+	/*
+	 * Represent by MD_RECOVERY_RECOVER, start when:
+	 * 1) for new replacement, sync data based on the replace rdev or
+	 * available copies from other rdev;
+	 * 2) for new member disk while the array is degraded, sync data from
+	 * other rdev;
+	 * 3) reassemble after power failure or re-add a hot removed rdev, sync
+	 * data from first rdev to other copies based on bitmap;
+	 */
+	ACTION_RECOVER,
+	/*
+	 * Represent by MD_RECOVERY_SYNC | MD_RECOVERY_REQUESTED |
+	 * MD_RECOVERY_CHECK, start when user echo "check" to sysfs api
+	 * sync_action, used to check if data copies from differenct rdev are
+	 * the same. The number of mismatch sectors will be exported to user
+	 * by sysfs api mismatch_cnt;
+	 */
+	ACTION_CHECK,
+	/*
+	 * Represent by MD_RECOVERY_SYNC | MD_RECOVERY_REQUESTED, start when
+	 * user echo "repair" to sysfs api sync_action, usually paired with
+	 * ACTION_CHECK, used to force syncing data once user found that there
+	 * are inconsistent data,
+	 */
+	ACTION_REPAIR,
+	/*
+	 * Represent by MD_RECOVERY_RESHAPE, start when new member disk is added
+	 * to the conf, notice that this is different from spares or
+	 * replacement;
+	 */
+	ACTION_RESHAPE,
+	/*
+	 * Represent by MD_RECOVERY_FROZEN, can be set by sysfs api sync_action
+	 * or internal usage like setting the array read-only, will forbid above
+	 * actions.
+	 */
+	ACTION_FROZEN,
+	/*
+	 * All above actions don't match.
+	 */
+	ACTION_IDLE,
+	NR_SYNC_ACTIONS,
+};
+
 /*
  * The struct embedded in rdev is used to serialize IO.
  */
@@ -371,13 +426,12 @@ struct mddev {
 	struct md_thread __rcu		*thread;	/* management thread */
 	struct md_thread __rcu		*sync_thread;	/* doing resync or reconstruct */
 
-	/* 'last_sync_action' is initialized to "none".  It is set when a
-	 * sync operation (i.e "data-check", "requested-resync", "resync",
-	 * "recovery", or "reshape") is started.  It holds this value even
+	/*
+	 * Set when a sync operation is started. It holds this value even
 	 * when the sync thread is "frozen" (interrupted) or "idle" (stopped
 	 * or finished). It is overwritten when a new sync operation is begun.
 	 */
-	char				*last_sync_action;
+	enum sync_action		last_sync_action;
 	sector_t			curr_resync;	/* last block scheduled */
 	/* As resync requests can complete out of order, we cannot easily track
 	 * how much resync has been completed.  So we occasionally pause until
@@ -540,8 +594,6 @@ struct mddev {
 	 */
 	struct list_head		deleting;
 
-	/* Used to synchronize idle and frozen for action_store() */
-	struct mutex			sync_mutex;
 	/* The sequence number for sync thread */
 	atomic_t sync_seq;
 
@@ -551,22 +603,46 @@ struct mddev {
 };
 
 enum recovery_flags {
+	/* flags for sync thread running status */
+
+	/*
+	 * set when one of sync action is set and new sync thread need to be
+	 * registered, or just add/remove spares from conf.
+	 */
+	MD_RECOVERY_NEEDED,
+	/* sync thread is running, or about to be started */
+	MD_RECOVERY_RUNNING,
+	/* sync thread needs to be aborted for some reason */
+	MD_RECOVERY_INTR,
+	/* sync thread is done and is waiting to be unregistered */
+	MD_RECOVERY_DONE,
+	/* running sync thread must abort immediately, and not restart */
+	MD_RECOVERY_FROZEN,
+	/* waiting for pers->start() to finish */
+	MD_RECOVERY_WAIT,
+	/* interrupted because io-error */
+	MD_RECOVERY_ERROR,
+
+	/* flags determines sync action, see details in enum sync_action */
+
+	/* if just this flag is set, action is resync. */
+	MD_RECOVERY_SYNC,
+	/*
+	 * paired with MD_RECOVERY_SYNC, if MD_RECOVERY_CHECK is not set,
+	 * action is repair, means user requested resync.
+	 */
+	MD_RECOVERY_REQUESTED,
 	/*
-	 * If neither SYNC or RESHAPE are set, then it is a recovery.
-	 */
-	MD_RECOVERY_RUNNING,	/* a thread is running, or about to be started */
-	MD_RECOVERY_SYNC,	/* actually doing a resync, not a recovery */
-	MD_RECOVERY_RECOVER,	/* doing recovery, or need to try it. */
-	MD_RECOVERY_INTR,	/* resync needs to be aborted for some reason */
-	MD_RECOVERY_DONE,	/* thread is done and is waiting to be reaped */
-	MD_RECOVERY_NEEDED,	/* we might need to start a resync/recover */
-	MD_RECOVERY_REQUESTED,	/* user-space has requested a sync (used with SYNC) */
-	MD_RECOVERY_CHECK,	/* user-space request for check-only, no repair */
-	MD_RECOVERY_RESHAPE,	/* A reshape is happening */
-	MD_RECOVERY_FROZEN,	/* User request to abort, and not restart, any action */
-	MD_RECOVERY_ERROR,	/* sync-action interrupted because io-error */
-	MD_RECOVERY_WAIT,	/* waiting for pers->start() to finish */
-	MD_RESYNCING_REMOTE,	/* remote node is running resync thread */
+	 * paired with MD_RECOVERY_SYNC and MD_RECOVERY_REQUESTED, action is
+	 * check.
+	 */
+	MD_RECOVERY_CHECK,
+	/* recovery, or need to try it */
+	MD_RECOVERY_RECOVER,
+	/* reshape */
+	MD_RECOVERY_RESHAPE,
+	/* remote node is running resync thread */
+	MD_RESYNCING_REMOTE,
 };
 
 enum md_ro_state {
@@ -653,7 +729,8 @@ struct md_personality
 	int (*hot_add_disk) (struct mddev *mddev, struct md_rdev *rdev);
 	int (*hot_remove_disk) (struct mddev *mddev, struct md_rdev *rdev);
 	int (*spare_active) (struct mddev *mddev);
-	sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr, int *skipped);
+	sector_t (*sync_request)(struct mddev *mddev, sector_t sector_nr,
+				 sector_t max_sector, int *skipped);
 	int (*resize) (struct mddev *mddev, sector_t sectors);
 	sector_t (*size) (struct mddev *mddev, sector_t sectors, int raid_disks);
 	int (*check_reshape) (struct mddev *mddev);
@@ -785,7 +862,10 @@ extern void md_unregister_thread(struct mddev *mddev, struct md_thread __rcu **t
 extern void md_wakeup_thread(struct md_thread __rcu *thread);
 extern void md_check_recovery(struct mddev *mddev);
 extern void md_reap_sync_thread(struct mddev *mddev);
-extern bool md_write_start(struct mddev *mddev, struct bio *bi);
+extern enum sync_action md_sync_action(struct mddev *mddev);
+extern enum sync_action md_sync_action_by_name(const char *page);
+extern const char *md_sync_action_name(enum sync_action action);
+extern void md_write_start(struct mddev *mddev, struct bio *bi);
 extern void md_write_inc(struct mddev *mddev, struct bio *bi);
 extern void md_write_end(struct mddev *mddev);
 extern void md_done_sync(struct mddev *mddev, int blocks, int ok);

drivers/md/raid0.c

@@ -365,18 +365,13 @@ static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks
 	return array_sectors;
 }
 
-static void free_conf(struct mddev *mddev, struct r0conf *conf)
-{
-	kfree(conf->strip_zone);
-	kfree(conf->devlist);
-	kfree(conf);
-}
-
 static void raid0_free(struct mddev *mddev, void *priv)
 {
 	struct r0conf *conf = priv;
 
-	free_conf(mddev, conf);
+	kfree(conf->strip_zone);
+	kfree(conf->devlist);
+	kfree(conf);
 }
 
 static int raid0_set_limits(struct mddev *mddev)
@@ -415,7 +410,7 @@ static int raid0_run(struct mddev *mddev)
 	if (!mddev_is_dm(mddev)) {
 		ret = raid0_set_limits(mddev);
 		if (ret)
-			goto out_free_conf;
+			return ret;
 	}
 
 	/* calculate array device size */
@@ -427,13 +422,7 @@ static int raid0_run(struct mddev *mddev)
 
 	dump_zones(mddev);
 
-	ret = md_integrity_register(mddev);
-	if (ret)
-		goto out_free_conf;
-	return 0;
-out_free_conf:
-	free_conf(mddev, conf);
-	return ret;
+	return md_integrity_register(mddev);
 }
 
 /*

drivers/md/raid1.c

@@ -1687,8 +1687,7 @@ 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 {
-		if (!md_write_start(mddev,bio))
-			return false;
+		md_write_start(mddev,bio);
 		raid1_write_request(mddev, bio, sectors);
 	}
 	return true;
@@ -2757,12 +2756,12 @@ static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf)
  */
 
 static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
-				   int *skipped)
+				   sector_t max_sector, int *skipped)
 {
 	struct r1conf *conf = mddev->private;
 	struct r1bio *r1_bio;
 	struct bio *bio;
-	sector_t max_sector, nr_sectors;
+	sector_t nr_sectors;
 	int disk = -1;
 	int i;
 	int wonly = -1;
@@ -2778,7 +2777,6 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 		if (init_resync(conf))
 			return 0;
 
-	max_sector = mddev->dev_sectors;
 	if (sector_nr >= max_sector) {
 		/* If we aborted, we need to abort the
 		 * sync on the 'current' bitmap chunk (there will
@@ -3204,7 +3202,6 @@ static int raid1_set_limits(struct mddev *mddev)
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
-static void raid1_free(struct mddev *mddev, void *priv);
 static int raid1_run(struct mddev *mddev)
 {
 	struct r1conf *conf;
@@ -3238,7 +3235,7 @@ static int raid1_run(struct mddev *mddev)
 	if (!mddev_is_dm(mddev)) {
 		ret = raid1_set_limits(mddev);
 		if (ret)
-			goto abort;
+			return ret;
 	}
 
 	mddev->degraded = 0;
@@ -3252,8 +3249,7 @@ static int raid1_run(struct mddev *mddev)
 	 */
 	if (conf->raid_disks - mddev->degraded < 1) {
 		md_unregister_thread(mddev, &conf->thread);
-		ret = -EINVAL;
-		goto abort;
+		return -EINVAL;
 	}
 
 	if (conf->raid_disks - mddev->degraded == 1)
@@ -3277,14 +3273,8 @@ static int raid1_run(struct mddev *mddev)
 	md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
 
 	ret = md_integrity_register(mddev);
-	if (ret) {
+	if (ret)
 		md_unregister_thread(mddev, &mddev->thread);
-		goto abort;
-	}
-	return 0;
-
-abort:
-	raid1_free(mddev, conf);
 	return ret;
 }
 

drivers/md/raid10.c

@@ -1836,8 +1836,7 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio)
 	    && md_flush_request(mddev, bio))
 		return true;
 
-	if (!md_write_start(mddev, bio))
-		return false;
+	md_write_start(mddev, bio);
 
 	if (unlikely(bio_op(bio) == REQ_OP_DISCARD))
 		if (!raid10_handle_discard(mddev, bio))
@@ -3140,12 +3139,12 @@ static void raid10_set_cluster_sync_high(struct r10conf *conf)
  */
 
 static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
-			     int *skipped)
+				    sector_t max_sector, int *skipped)
 {
 	struct r10conf *conf = mddev->private;
 	struct r10bio *r10_bio;
 	struct bio *biolist = NULL, *bio;
-	sector_t max_sector, nr_sectors;
+	sector_t nr_sectors;
 	int i;
 	int max_sync;
 	sector_t sync_blocks;
@@ -3175,10 +3174,6 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
 			return 0;
 
  skipped:
-	max_sector = mddev->dev_sectors;
-	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ||
-	    test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
-		max_sector = mddev->resync_max_sectors;
 	if (sector_nr >= max_sector) {
 		conf->cluster_sync_low = 0;
 		conf->cluster_sync_high = 0;

drivers/md/raid5.c

@@ -6078,8 +6078,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 		ctx.do_flush = bi->bi_opf & REQ_PREFLUSH;
 	}
 
-	if (!md_write_start(mddev, bi))
-		return false;
+	md_write_start(mddev, bi);
 	/*
 	 * If array is degraded, better not do chunk aligned read because
 	 * later we might have to read it again in order to reconstruct
@@ -6255,7 +6254,9 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 	safepos = conf->reshape_safe;
 	sector_div(safepos, data_disks);
 	if (mddev->reshape_backwards) {
-		BUG_ON(writepos < reshape_sectors);
+		if (WARN_ON(writepos < reshape_sectors))
+			return MaxSector;
+
 		writepos -= reshape_sectors;
 		readpos += reshape_sectors;
 		safepos += reshape_sectors;
@@ -6273,14 +6274,18 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 	 * to set 'stripe_addr' which is where we will write to.
 	 */
 	if (mddev->reshape_backwards) {
-		BUG_ON(conf->reshape_progress == 0);
+		if (WARN_ON(conf->reshape_progress == 0))
+			return MaxSector;
+
 		stripe_addr = writepos;
-		BUG_ON((mddev->dev_sectors &
-			~((sector_t)reshape_sectors - 1))
-		       - reshape_sectors - stripe_addr
-		       != sector_nr);
+		if (WARN_ON((mddev->dev_sectors &
+		    ~((sector_t)reshape_sectors - 1)) -
+		    reshape_sectors - stripe_addr != sector_nr))
+			return MaxSector;
 	} else {
-		BUG_ON(writepos != sector_nr + reshape_sectors);
+		if (WARN_ON(writepos != sector_nr + reshape_sectors))
+			return MaxSector;
+
 		stripe_addr = sector_nr;
 	}
 
@@ -6458,11 +6463,10 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 }
 
 static inline sector_t raid5_sync_request(struct mddev *mddev, sector_t sector_nr,
-					  int *skipped)
+					  sector_t max_sector, int *skipped)
 {
 	struct r5conf *conf = mddev->private;
 	struct stripe_head *sh;
-	sector_t max_sector = mddev->dev_sectors;
 	sector_t sync_blocks;
 	int still_degraded = 0;
 	int i;