md: separate flags for superblock changes

The mddev->flags are used for different purposes. There are a lot of
places we check/change the flags without masking unrelated flags, we
could check/change unrelated flags. These usage are most for superblock
write, so spearate superblock related flags. This should make the code
clearer and also fix real bugs.
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>

drivers/md/bitmap.c

@@ -1623,7 +1623,7 @@ void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector, bool force)
 		   atomic_read(&bitmap->mddev->recovery_active) == 0);
 
 	bitmap->mddev->curr_resync_completed = sector;
-	set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);
+	set_bit(MD_SB_CHANGE_CLEAN, &bitmap->mddev->sb_flags);
 	sector &= ~((1ULL << bitmap->counts.chunkshift) - 1);
 	s = 0;
 	while (s < sector && s < bitmap->mddev->resync_max_sectors) {
@@ -2296,7 +2296,7 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 		/* Ensure new bitmap info is stored in
 		 * metadata promptly.
 		 */
-		set_bit(MD_CHANGE_DEVS, &mddev->flags);
+		set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 		md_wakeup_thread(mddev->thread);
 	}
 	rv = 0;

drivers/md/dm-raid.c

@@ -2011,7 +2011,7 @@ static int super_load(struct md_rdev *rdev, struct md_rdev *refdev)
 		sb->compat_features = cpu_to_le32(FEATURE_FLAG_SUPPORTS_V190);
 
 		/* Force writing of superblocks to disk */
-		set_bit(MD_CHANGE_DEVS, &rdev->mddev->flags);
+		set_bit(MD_SB_CHANGE_DEVS, &rdev->mddev->sb_flags);
 
 		/* Any superblock is better than none, choose that if given */
 		return refdev ? 0 : 1;
@@ -3497,7 +3497,7 @@ static void rs_update_sbs(struct raid_set *rs)
 	struct mddev *mddev = &rs->md;
 	int ro = mddev->ro;
 
-	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 	mddev->ro = 0;
 	md_update_sb(mddev, 1);
 	mddev->ro = ro;

drivers/md/md.h

@@ -213,9 +213,6 @@ extern int rdev_clear_badblocks(struct md_rdev *rdev, sector_t s, int sectors,
 struct md_cluster_info;
 
 enum mddev_flags {
-	MD_CHANGE_DEVS,		/* Some device status has changed */
-	MD_CHANGE_CLEAN,	/* transition to or from 'clean' */
-	MD_CHANGE_PENDING,	/* switch from 'clean' to 'active' in progress */
 	MD_ARRAY_FIRST_USE,	/* First use of array, needs initialization */
 	MD_CLOSING,		/* If set, we are closing the array, do not open
 				 * it then */
@@ -231,11 +228,15 @@ enum mddev_flags {
 				 * supported as calls to md_error() will
 				 * never cause the array to become failed.
 				 */
-	MD_NEED_REWRITE,	/* metadata write needs to be repeated */
 };
-#define MD_UPDATE_SB_FLAGS (BIT(MD_CHANGE_DEVS) | \
-			    BIT(MD_CHANGE_CLEAN) | \
-			    BIT(MD_CHANGE_PENDING))	/* If these are set, md_update_sb needed */
+
+enum mddev_sb_flags {
+	MD_SB_CHANGE_DEVS,		/* Some device status has changed */
+	MD_SB_CHANGE_CLEAN,	/* transition to or from 'clean' */
+	MD_SB_CHANGE_PENDING,	/* switch from 'clean' to 'active' in progress */
+	MD_SB_NEED_REWRITE,	/* metadata write needs to be repeated */
+};
+
 struct mddev {
 	void				*private;
 	struct md_personality		*pers;
@@ -243,6 +244,7 @@ struct mddev {
 	int				md_minor;
 	struct list_head		disks;
 	unsigned long			flags;
+	unsigned long			sb_flags;
 
 	int				suspended;
 	atomic_t			active_io;

drivers/md/multipath.c

@@ -208,7 +208,7 @@ static void multipath_error (struct mddev *mddev, struct md_rdev *rdev)
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 	}
 	set_bit(Faulty, &rdev->flags);
-	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 	pr_err("multipath: IO failure on %s, disabling IO path.\n"
 	       "multipath: Operation continuing on %d IO paths.\n",
 	       bdevname(rdev->bdev, b),

drivers/md/raid1.c

@@ -1517,8 +1517,8 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
 	 * if recovery is running, make sure it aborts.
 	 */
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-	set_mask_bits(&mddev->flags, 0,
-		      BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
+	set_mask_bits(&mddev->sb_flags, 0,
+		      BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
 	pr_crit("md/raid1:%s: Disk failure on %s, disabling device.\n"
 		"md/raid1:%s: Operation continuing on %d devices.\n",
 		mdname(mddev), bdevname(rdev->bdev, b),
@@ -2464,10 +2464,10 @@ static void raid1d(struct md_thread *thread)
 	md_check_recovery(mddev);
 
 	if (!list_empty_careful(&conf->bio_end_io_list) &&
-	    !test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+	    !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
 		LIST_HEAD(tmp);
 		spin_lock_irqsave(&conf->device_lock, flags);
-		if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+		if (!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
 			while (!list_empty(&conf->bio_end_io_list)) {
 				list_move(conf->bio_end_io_list.prev, &tmp);
 				conf->nr_queued--;
@@ -2521,7 +2521,7 @@ static void raid1d(struct md_thread *thread)
 			generic_make_request(r1_bio->bios[r1_bio->read_disk]);
 
 		cond_resched();
-		if (mddev->flags & ~(1<<MD_CHANGE_PENDING))
+		if (mddev->sb_flags & ~(1<<MD_SB_CHANGE_PENDING))
 			md_check_recovery(mddev);
 	}
 	blk_finish_plug(&plug);
@@ -2724,7 +2724,7 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
 							min_bad, 0
 					) && ok;
 			}
-		set_bit(MD_CHANGE_DEVS, &mddev->flags);
+		set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 		*skipped = 1;
 		put_buf(r1_bio);
 

drivers/md/raid10.c

@@ -1138,12 +1138,12 @@ static void __make_request(struct mddev *mddev, struct bio *bio)
 		bio->bi_iter.bi_sector < conf->reshape_progress))) {
 		/* Need to update reshape_position in metadata */
 		mddev->reshape_position = conf->reshape_progress;
-		set_mask_bits(&mddev->flags, 0,
-			      BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
+		set_mask_bits(&mddev->sb_flags, 0,
+			      BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
 		md_wakeup_thread(mddev->thread);
 		raid10_log(conf->mddev, "wait reshape metadata");
 		wait_event(mddev->sb_wait,
-			   !test_bit(MD_CHANGE_PENDING, &mddev->flags));
+			   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
 
 		conf->reshape_safe = mddev->reshape_position;
 	}
@@ -1652,8 +1652,8 @@ static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
 	set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 	set_bit(Blocked, &rdev->flags);
 	set_bit(Faulty, &rdev->flags);
-	set_mask_bits(&mddev->flags, 0,
-		      BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
+	set_mask_bits(&mddev->sb_flags, 0,
+		      BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 	pr_crit("md/raid10:%s: Disk failure on %s, disabling device.\n"
 		"md/raid10:%s: Operation continuing on %d devices.\n",
@@ -2761,10 +2761,10 @@ static void raid10d(struct md_thread *thread)
 	md_check_recovery(mddev);
 
 	if (!list_empty_careful(&conf->bio_end_io_list) &&
-	    !test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+	    !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
 		LIST_HEAD(tmp);
 		spin_lock_irqsave(&conf->device_lock, flags);
-		if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+		if (!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
 			while (!list_empty(&conf->bio_end_io_list)) {
 				list_move(conf->bio_end_io_list.prev, &tmp);
 				conf->nr_queued--;
@@ -2822,7 +2822,7 @@ static void raid10d(struct md_thread *thread)
 		}
 
 		cond_resched();
-		if (mddev->flags & ~(1<<MD_CHANGE_PENDING))
+		if (mddev->sb_flags & ~(1<<MD_SB_CHANGE_PENDING))
 			md_check_recovery(mddev);
 	}
 	blk_finish_plug(&plug);
@@ -4209,7 +4209,7 @@ static int raid10_start_reshape(struct mddev *mddev)
 	spin_unlock_irq(&conf->device_lock);
 	mddev->raid_disks = conf->geo.raid_disks;
 	mddev->reshape_position = conf->reshape_progress;
-	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 
 	clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
@@ -4404,9 +4404,9 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
 		else
 			mddev->curr_resync_completed = conf->reshape_progress;
 		conf->reshape_checkpoint = jiffies;
-		set_bit(MD_CHANGE_DEVS, &mddev->flags);
+		set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 		md_wakeup_thread(mddev->thread);
-		wait_event(mddev->sb_wait, mddev->flags == 0 ||
+		wait_event(mddev->sb_wait, mddev->sb_flags == 0 ||
 			   test_bit(MD_RECOVERY_INTR, &mddev->recovery));
 		if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
 			allow_barrier(conf);

drivers/md/raid5-cache.c

@@ -1206,8 +1206,8 @@ static void r5l_write_super_and_discard_space(struct r5l_log *log,
 	 * there is a deadlock. We workaround this issue with a trylock.
 	 * FIXME: we could miss discard if we can't take reconfig mutex
 	 */
-	set_mask_bits(&mddev->flags, 0,
-		BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
+	set_mask_bits(&mddev->sb_flags, 0,
+		BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
 	if (!mddev_trylock(mddev))
 		return;
 	md_update_sb(mddev, 1);
@@ -2197,7 +2197,7 @@ static void r5l_write_super(struct r5l_log *log, sector_t cp)
 	struct mddev *mddev = log->rdev->mddev;
 
 	log->rdev->journal_tail = cp;
-	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 }
 
 static ssize_t r5c_journal_mode_show(struct mddev *mddev, char *page)

drivers/md/raid5.c

@@ -961,7 +961,7 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
 			if (bad < 0) {
 				set_bit(BlockedBadBlocks, &rdev->flags);
 				if (!conf->mddev->external &&
-				    conf->mddev->flags) {
+				    conf->mddev->sb_flags) {
 					/* It is very unlikely, but we might
 					 * still need to write out the
 					 * bad block log - better give it
@@ -2547,8 +2547,8 @@ static void raid5_error(struct mddev *mddev, struct md_rdev *rdev)
 
 	set_bit(Blocked, &rdev->flags);
 	set_bit(Faulty, &rdev->flags);
-	set_mask_bits(&mddev->flags, 0,
-		      BIT(MD_CHANGE_DEVS) | BIT(MD_CHANGE_PENDING));
+	set_mask_bits(&mddev->sb_flags, 0,
+		      BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
 	pr_crit("md/raid:%s: Disk failure on %s, disabling device.\n"
 		"md/raid:%s: Operation continuing on %d devices.\n",
 		mdname(mddev),
@@ -4761,7 +4761,7 @@ static void handle_stripe(struct stripe_head *sh)
 	}
 
 	if (!bio_list_empty(&s.return_bi)) {
-		if (test_bit(MD_CHANGE_PENDING, &conf->mddev->flags)) {
+		if (test_bit(MD_SB_CHANGE_PENDING, &conf->mddev->sb_flags)) {
 			spin_lock_irq(&conf->device_lock);
 			bio_list_merge(&conf->return_bi, &s.return_bi);
 			spin_unlock_irq(&conf->device_lock);
@@ -5617,9 +5617,9 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 		mddev->reshape_position = conf->reshape_progress;
 		mddev->curr_resync_completed = sector_nr;
 		conf->reshape_checkpoint = jiffies;
-		set_bit(MD_CHANGE_DEVS, &mddev->flags);
+		set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 		md_wakeup_thread(mddev->thread);
-		wait_event(mddev->sb_wait, mddev->flags == 0 ||
+		wait_event(mddev->sb_wait, mddev->sb_flags == 0 ||
 			   test_bit(MD_RECOVERY_INTR, &mddev->recovery));
 		if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
 			return 0;
@@ -5715,10 +5715,10 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
 		mddev->reshape_position = conf->reshape_progress;
 		mddev->curr_resync_completed = sector_nr;
 		conf->reshape_checkpoint = jiffies;
-		set_bit(MD_CHANGE_DEVS, &mddev->flags);
+		set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 		md_wakeup_thread(mddev->thread);
 		wait_event(mddev->sb_wait,
-			   !test_bit(MD_CHANGE_DEVS, &mddev->flags)
+			   !test_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags)
 			   || test_bit(MD_RECOVERY_INTR, &mddev->recovery));
 		if (test_bit(MD_RECOVERY_INTR, &mddev->recovery))
 			goto ret;
@@ -5993,10 +5993,10 @@ static void raid5d(struct md_thread *thread)
 	md_check_recovery(mddev);
 
 	if (!bio_list_empty(&conf->return_bi) &&
-	    !test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+	    !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
 		struct bio_list tmp = BIO_EMPTY_LIST;
 		spin_lock_irq(&conf->device_lock);
-		if (!test_bit(MD_CHANGE_PENDING, &mddev->flags)) {
+		if (!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
 			bio_list_merge(&tmp, &conf->return_bi);
 			bio_list_init(&conf->return_bi);
 		}
@@ -6043,7 +6043,7 @@ static void raid5d(struct md_thread *thread)
 			break;
 		handled += batch_size;
 
-		if (mddev->flags & ~(1<<MD_CHANGE_PENDING)) {
+		if (mddev->sb_flags & ~(1 << MD_SB_CHANGE_PENDING)) {
 			spin_unlock_irq(&conf->device_lock);
 			md_check_recovery(mddev);
 			spin_lock_irq(&conf->device_lock);
@@ -7640,7 +7640,7 @@ static int raid5_start_reshape(struct mddev *mddev)
 	}
 	mddev->raid_disks = conf->raid_disks;
 	mddev->reshape_position = conf->reshape_progress;
-	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 
 	clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
@@ -7906,7 +7906,7 @@ static int raid5_check_reshape(struct mddev *mddev)
 			conf->chunk_sectors = new_chunk ;
 			mddev->chunk_sectors = new_chunk;
 		}
-		set_bit(MD_CHANGE_DEVS, &mddev->flags);
+		set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
 		md_wakeup_thread(mddev->thread);
 	}
 	return check_reshape(mddev);