1 files changed, 86 insertions, 58 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0f03b21e66e4..ac85ec73a409 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -636,9 +636,12 @@ static void __mddev_put(struct mddev *mddev)
 	    mddev->ctime || mddev->hold_active)
 		return;
 
-	/* Array is not configured at all, and not held active, so destroy it */
+	/*
+	 * If array is freed by stopping array, MD_DELETED is set by
+	 * do_md_stop(), MD_DELETED is still set here in case mddev is freed
+	 * directly by closing a mddev that is created by create_on_open.
+	 */
 	set_bit(MD_DELETED, &mddev->flags);
-
 	/*
 	 * Call queue_work inside the spinlock so that flush_workqueue() after
 	 * mddev_find will succeed in waiting for the work to be done.
@@ -873,6 +876,16 @@ void mddev_unlock(struct mddev *mddev)
 		kobject_del(&rdev->kobj);
 		export_rdev(rdev, mddev);
 	}
+
+	/* Call del_gendisk after release reconfig_mutex to avoid
+	 * deadlock (e.g. call del_gendisk under the lock and an
+	 * access to sysfs files waits the lock)
+	 * And MD_DELETED is only used for md raid which is set in
+	 * do_md_stop. dm raid only uses md_stop to stop. So dm raid
+	 * doesn't need to check MD_DELETED when getting reconfig lock
+	 */
+	if (test_bit(MD_DELETED, &mddev->flags))
+		del_gendisk(mddev->gendisk);
 }
 EXPORT_SYMBOL_GPL(mddev_unlock);
 
@@ -1402,13 +1415,13 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *freshest, stru
 			mddev->layout = -1;
 
 		if (sb->state & (1<<MD_SB_CLEAN))
-			mddev->recovery_cp = MaxSector;
+			mddev->resync_offset = MaxSector;
 		else {
 			if (sb->events_hi == sb->cp_events_hi &&
 				sb->events_lo == sb->cp_events_lo) {
-				mddev->recovery_cp = sb->recovery_cp;
+				mddev->resync_offset = sb->resync_offset;
 			} else
-				mddev->recovery_cp = 0;
+				mddev->resync_offset = 0;
 		}
 
 		memcpy(mddev->uuid+0, &sb->set_uuid0, 4);
@@ -1534,13 +1547,13 @@ static void super_90_sync(struct mddev *mddev, struct md_rdev *rdev)
 	mddev->minor_version = sb->minor_version;
 	if (mddev->in_sync)
 	{
-		sb->recovery_cp = mddev->recovery_cp;
+		sb->resync_offset = mddev->resync_offset;
 		sb->cp_events_hi = (mddev->events>>32);
 		sb->cp_events_lo = (u32)mddev->events;
-		if (mddev->recovery_cp == MaxSector)
+		if (mddev->resync_offset == MaxSector)
 			sb->state = (1<< MD_SB_CLEAN);
 	} else
-		sb->recovery_cp = 0;
+		sb->resync_offset = 0;
 
 	sb->layout = mddev->layout;
 	sb->chunk_size = mddev->chunk_sectors << 9;
@@ -1888,7 +1901,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *freshest, struc
 		mddev->bitmap_info.default_space = (4096-1024) >> 9;
 		mddev->reshape_backwards = 0;
 
-		mddev->recovery_cp = le64_to_cpu(sb->resync_offset);
+		mddev->resync_offset = le64_to_cpu(sb->resync_offset);
 		memcpy(mddev->uuid, sb->set_uuid, 16);
 
 		mddev->max_disks =  (4096-256)/2;
@@ -2074,7 +2087,7 @@ static void super_1_sync(struct mddev *mddev, struct md_rdev *rdev)
 	sb->utime = cpu_to_le64((__u64)mddev->utime);
 	sb->events = cpu_to_le64(mddev->events);
 	if (mddev->in_sync)
-		sb->resync_offset = cpu_to_le64(mddev->recovery_cp);
+		sb->resync_offset = cpu_to_le64(mddev->resync_offset);
 	else if (test_bit(MD_JOURNAL_CLEAN, &mddev->flags))
 		sb->resync_offset = cpu_to_le64(MaxSector);
 	else
@@ -2754,7 +2767,7 @@ repeat:
 	/* If this is just a dirty<->clean transition, and the array is clean
 	 * and 'events' is odd, we can roll back to the previous clean state */
 	if (nospares
-	    && (mddev->in_sync && mddev->recovery_cp == MaxSector)
+	    && (mddev->in_sync && mddev->resync_offset == MaxSector)
 	    && mddev->can_decrease_events
 	    && mddev->events != 1) {
 		mddev->events--;
@@ -4290,9 +4303,9 @@ __ATTR(chunk_size, S_IRUGO|S_IWUSR, chunk_size_show, chunk_size_store);
 static ssize_t
 resync_start_show(struct mddev *mddev, char *page)
 {
-	if (mddev->recovery_cp == MaxSector)
+	if (mddev->resync_offset == MaxSector)
 		return sprintf(page, "none\n");
-	return sprintf(page, "%llu\n", (unsigned long long)mddev->recovery_cp);
+	return sprintf(page, "%llu\n", (unsigned long long)mddev->resync_offset);
 }
 
 static ssize_t
@@ -4318,7 +4331,7 @@ resync_start_store(struct mddev *mddev, const char *buf, size_t len)
 		err = -EBUSY;
 
 	if (!err) {
-		mddev->recovery_cp = n;
+		mddev->resync_offset = n;
 		if (mddev->pers)
 			set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags);
 	}
@@ -5774,19 +5787,30 @@ md_attr_store(struct kobject *kobj, struct attribute *attr,
 	struct md_sysfs_entry *entry = container_of(attr, struct md_sysfs_entry, attr);
 	struct mddev *mddev = container_of(kobj, struct mddev, kobj);
 	ssize_t rv;
+	struct kernfs_node *kn = NULL;
 
 	if (!entry->store)
 		return -EIO;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EACCES;
+
+	if (entry->store == array_state_store && cmd_match(page, "clear"))
+		kn = sysfs_break_active_protection(kobj, attr);
+
 	spin_lock(&all_mddevs_lock);
 	if (!mddev_get(mddev)) {
 		spin_unlock(&all_mddevs_lock);
+		if (kn)
+			sysfs_unbreak_active_protection(kn);
 		return -EBUSY;
 	}
 	spin_unlock(&all_mddevs_lock);
 	rv = entry->store(mddev, page, length);
 	mddev_put(mddev);
+
+	if (kn)
+		sysfs_unbreak_active_protection(kn);
+
 	return rv;
 }
 
@@ -5794,12 +5818,6 @@ static void md_kobj_release(struct kobject *ko)
 {
 	struct mddev *mddev = container_of(ko, struct mddev, kobj);
 
-	if (mddev->sysfs_state)
-		sysfs_put(mddev->sysfs_state);
-	if (mddev->sysfs_level)
-		sysfs_put(mddev->sysfs_level);
-
-	del_gendisk(mddev->gendisk);
 	put_disk(mddev->gendisk);
 }
 
@@ -6405,7 +6423,7 @@ static void md_clean(struct mddev *mddev)
 	mddev->external_size = 0;
 	mddev->dev_sectors = 0;
 	mddev->raid_disks = 0;
-	mddev->recovery_cp = 0;
+	mddev->resync_offset = 0;
 	mddev->resync_min = 0;
 	mddev->resync_max = MaxSector;
 	mddev->reshape_position = MaxSector;
@@ -6413,15 +6431,10 @@ static void md_clean(struct mddev *mddev)
 	mddev->persistent = 0;
 	mddev->level = LEVEL_NONE;
 	mddev->clevel[0] = 0;
-	/*
-	 * Don't clear MD_CLOSING, or mddev can be opened again.
-	 * 'hold_active != 0' means mddev is still in the creation
-	 * process and will be used later.
-	 */
-	if (mddev->hold_active)
-		mddev->flags = 0;
-	else
-		mddev->flags &= BIT_ULL_MASK(MD_CLOSING);
+	/* if UNTIL_STOP is set, it's cleared here */
+	mddev->hold_active = 0;
+	/* Don't clear MD_CLOSING, or mddev can be opened again. */
+	mddev->flags &= BIT_ULL_MASK(MD_CLOSING);
 	mddev->sb_flags = 0;
 	mddev->ro = MD_RDWR;
 	mddev->metadata_type[0] = 0;
@@ -6516,8 +6529,6 @@ static void __md_stop(struct mddev *mddev)
 	if (mddev->private)
 		pers->free(mddev, mddev->private);
 	mddev->private = NULL;
-	if (pers->sync_request && mddev->to_remove == NULL)
-		mddev->to_remove = &md_redundancy_group;
 	put_pers(pers);
 	clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 
@@ -6646,10 +6657,8 @@ static int do_md_stop(struct mddev *mddev, int mode)
 		mddev->bitmap_info.offset = 0;
 
 		export_array(mddev);
-
 		md_clean(mddev);
-		if (mddev->hold_active == UNTIL_STOP)
-			mddev->hold_active = 0;
+		set_bit(MD_DELETED, &mddev->flags);
 	}
 	md_new_event();
 	sysfs_notify_dirent_safe(mddev->sysfs_state);
@@ -7359,9 +7368,9 @@ int md_set_array_info(struct mddev *mddev, struct mdu_array_info_s *info)
 	 * openned
 	 */
 	if (info->state & (1<<MD_SB_CLEAN))
-		mddev->recovery_cp = MaxSector;
+		mddev->resync_offset = MaxSector;
 	else
-		mddev->recovery_cp = 0;
+		mddev->resync_offset = 0;
 	mddev->persistent    = ! info->not_persistent;
 	mddev->external	     = 0;
 
@@ -8300,7 +8309,7 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev)
 				seq_printf(seq, "\tresync=REMOTE");
 			return 1;
 		}
-		if (mddev->recovery_cp < MaxSector) {
+		if (mddev->resync_offset < MaxSector) {
 			seq_printf(seq, "\tresync=PENDING");
 			return 1;
 		}
@@ -8943,7 +8952,7 @@ static sector_t md_sync_position(struct mddev *mddev, enum sync_action action)
 		return mddev->resync_min;
 	case ACTION_RESYNC:
 		if (!mddev->bitmap)
-			return mddev->recovery_cp;
+			return mddev->resync_offset;
 		return 0;
 	case ACTION_RESHAPE:
 		/*
@@ -9181,8 +9190,8 @@ void md_do_sync(struct md_thread *thread)
 				   atomic_read(&mddev->recovery_active) == 0);
 			mddev->curr_resync_completed = j;
 			if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) &&
-			    j > mddev->recovery_cp)
-				mddev->recovery_cp = j;
+			    j > mddev->resync_offset)
+				mddev->resync_offset = j;
 			update_time = jiffies;
 			set_bit(MD_SB_CHANGE_CLEAN, &mddev->sb_flags);
 			sysfs_notify_dirent_safe(mddev->sysfs_completed);
@@ -9302,19 +9311,19 @@ void md_do_sync(struct md_thread *thread)
 	    mddev->curr_resync > MD_RESYNC_ACTIVE) {
 		if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
 			if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
-				if (mddev->curr_resync >= mddev->recovery_cp) {
+				if (mddev->curr_resync >= mddev->resync_offset) {
 					pr_debug("md: checkpointing %s of %s.\n",
 						 desc, mdname(mddev));
 					if (test_bit(MD_RECOVERY_ERROR,
 						&mddev->recovery))
-						mddev->recovery_cp =
+						mddev->resync_offset =
 							mddev->curr_resync_completed;
 					else
-						mddev->recovery_cp =
+						mddev->resync_offset =
 							mddev->curr_resync;
 				}
 			} else
-				mddev->recovery_cp = MaxSector;
+				mddev->resync_offset = MaxSector;
 		} else {
 			if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery))
 				mddev->curr_resync = MaxSector;
@@ -9418,6 +9427,12 @@ static bool rdev_is_spare(struct md_rdev *rdev)
 
 static bool rdev_addable(struct md_rdev *rdev)
 {
+	struct mddev *mddev;
+
+	mddev = READ_ONCE(rdev->mddev);
+	if (!mddev)
+		return false;
+
 	/* rdev is already used, don't add it again. */
 	if (test_bit(Candidate, &rdev->flags) || rdev->raid_disk >= 0 ||
 	    test_bit(Faulty, &rdev->flags))
@@ -9428,7 +9443,7 @@ static bool rdev_addable(struct md_rdev *rdev)
 		return true;
 
 	/* Allow to add if array is read-write. */
-	if (md_is_rdwr(rdev->mddev))
+	if (md_is_rdwr(mddev))
 		return true;
 
 	/*
@@ -9456,17 +9471,11 @@ static bool md_spares_need_change(struct mddev *mddev)
 	return false;
 }
 
-static int remove_and_add_spares(struct mddev *mddev,
-				 struct md_rdev *this)
+static int remove_spares(struct mddev *mddev, struct md_rdev *this)
 {
 	struct md_rdev *rdev;
-	int spares = 0;
 	int removed = 0;
 
-	if (this && test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
-		/* Mustn't remove devices when resync thread is running */
-		return 0;
-
 	rdev_for_each(rdev, mddev) {
 		if ((this == NULL || rdev == this) && rdev_removeable(rdev) &&
 		    !mddev->pers->hot_remove_disk(mddev, rdev)) {
@@ -9480,6 +9489,21 @@ static int remove_and_add_spares(struct mddev *mddev,
 	if (removed && mddev->kobj.sd)
 		sysfs_notify_dirent_safe(mddev->sysfs_degraded);
 
+	return removed;
+}
+
+static int remove_and_add_spares(struct mddev *mddev,
+				 struct md_rdev *this)
+{
+	struct md_rdev *rdev;
+	int spares = 0;
+	int removed = 0;
+
+	if (this && test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+		/* Mustn't remove devices when resync thread is running */
+		return 0;
+
+	removed = remove_spares(mddev, this);
 	if (this && removed)
 		goto no_add;
 
@@ -9521,7 +9545,8 @@ static bool md_choose_sync_action(struct mddev *mddev, int *spares)
 	}
 
 	/* Check if resync is in progress. */
-	if (mddev->recovery_cp < MaxSector) {
+	if (mddev->resync_offset < MaxSector) {
+		remove_spares(mddev, NULL);
 		set_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		return true;
@@ -9701,7 +9726,7 @@ void md_check_recovery(struct mddev *mddev)
 		test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
 		(mddev->external == 0 && mddev->safemode == 1) ||
 		(mddev->safemode == 2
-		 && !mddev->in_sync && mddev->recovery_cp == MaxSector)
+		 && !mddev->in_sync && mddev->resync_offset == MaxSector)
 		))
 		return;
 
@@ -9758,8 +9783,8 @@ void md_check_recovery(struct mddev *mddev)
 			 * remove disk.
 			 */
 			rdev_for_each_safe(rdev, tmp, mddev) {
-				if (test_and_clear_bit(ClusterRemove, &rdev->flags) &&
-						rdev->raid_disk < 0)
+				if (rdev->raid_disk < 0 &&
+				    test_and_clear_bit(ClusterRemove, &rdev->flags))
 					md_kick_rdev_from_array(rdev);
 			}
 		}
@@ -10065,8 +10090,11 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev)
 
 	/* Check for change of roles in the active devices */
 	rdev_for_each_safe(rdev2, tmp, mddev) {
-		if (test_bit(Faulty, &rdev2->flags))
+		if (test_bit(Faulty, &rdev2->flags)) {
+			if (test_bit(ClusterRemove, &rdev2->flags))
+				set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 			continue;
+		}
 
 		/* Check if the roles changed */
 		role = le16_to_cpu(sb->dev_roles[rdev2->desc_nr]);