Merge tag 'md/4.2-fixes' of git://neil.brown.name/md

Pull md fixes from Neil Brown:
 "Some md fixes for 4.2

  Several are tagged for -stable.
  A few aren't because they are not very, serious or because they are in
  the 'experimental' cluster code"

* tag 'md/4.2-fixes' of git://neil.brown.name/md:
  md/raid5: clear R5_NeedReplace when no longer needed.
  Fix read-balancing during node failure
  md-cluster: fix bitmap sub-offset in bitmap_read_sb
  md: Return error if request_module fails and returns positive value
  md: Skip cluster setup in case of error while reading bitmap
  md/raid1: fix test for 'was read error from last working device'.
  md: Skip cluster setup for dm-raid
  md: flush ->event_work before stopping array.
  md/raid10: always set reshape_safe when initializing reshape_position.
  md/raid5: avoid races when changing cache size.

8 files changed, 71 insertions, 27 deletions

diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index ed2346d..e51de52 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -494,7 +494,7 @@ static int bitmap_new_disk_sb(struct bitmap *bitmap)
 	bitmap_super_t *sb;
 	unsigned long chunksize, daemon_sleep, write_behind;
 
-	bitmap->storage.sb_page = alloc_page(GFP_KERNEL);
+	bitmap->storage.sb_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
 	if (bitmap->storage.sb_page == NULL)
 		return -ENOMEM;
 	bitmap->storage.sb_page->index = 0;
@@ -541,6 +541,7 @@ static int bitmap_new_disk_sb(struct bitmap *bitmap)
 	sb->state = cpu_to_le32(bitmap->flags);
 	bitmap->events_cleared = bitmap->mddev->events;
 	sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
+	bitmap->mddev->bitmap_info.nodes = 0;
 
 	kunmap_atomic(sb);
 
@@ -558,6 +559,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 	unsigned long sectors_reserved = 0;
 	int err = -EINVAL;
 	struct page *sb_page;
+	loff_t offset = bitmap->mddev->bitmap_info.offset;
 
 	if (!bitmap->storage.file && !bitmap->mddev->bitmap_info.offset) {
 		chunksize = 128 * 1024 * 1024;
@@ -584,9 +586,9 @@ re_read:
 		bm_blocks = ((bm_blocks+7) >> 3) + sizeof(bitmap_super_t);
 		/* to 4k blocks */
 		bm_blocks = DIV_ROUND_UP_SECTOR_T(bm_blocks, 4096);
-		bitmap->mddev->bitmap_info.offset += bitmap->cluster_slot * (bm_blocks << 3);
+		offset = bitmap->mddev->bitmap_info.offset + (bitmap->cluster_slot * (bm_blocks << 3));
 		pr_info("%s:%d bm slot: %d offset: %llu\n", __func__, __LINE__,
-			bitmap->cluster_slot, (unsigned long long)bitmap->mddev->bitmap_info.offset);
+			bitmap->cluster_slot, offset);
 	}
 
 	if (bitmap->storage.file) {
@@ -597,7 +599,7 @@ re_read:
 				bitmap, bytes, sb_page);
 	} else {
 		err = read_sb_page(bitmap->mddev,
-				   bitmap->mddev->bitmap_info.offset,
+				   offset,
 				   sb_page,
 				   0, sizeof(bitmap_super_t));
 	}
@@ -611,8 +613,16 @@ re_read:
 	daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ;
 	write_behind = le32_to_cpu(sb->write_behind);
 	sectors_reserved = le32_to_cpu(sb->sectors_reserved);
-	nodes = le32_to_cpu(sb->nodes);
-	strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64);
+	/* XXX: This is a hack to ensure that we don't use clustering
+	 *  in case:
+	 *	- dm-raid is in use and
+	 *	- the nodes written in bitmap_sb is erroneous.
+	 */
+	if (!bitmap->mddev->sync_super) {
+		nodes = le32_to_cpu(sb->nodes);
+		strlcpy(bitmap->mddev->bitmap_info.cluster_name,
+				sb->cluster_name, 64);
+	}
 
 	/* verify that the bitmap-specific fields are valid */
 	if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
@@ -671,7 +681,7 @@ out:
 	kunmap_atomic(sb);
 	/* Assiging chunksize is required for "re_read" */
 	bitmap->mddev->bitmap_info.chunksize = chunksize;
-	if (nodes && (bitmap->cluster_slot < 0)) {
+	if (err == 0 && nodes && (bitmap->cluster_slot < 0)) {
 		err = md_setup_cluster(bitmap->mddev, nodes);
 		if (err) {
 			pr_err("%s: Could not setup cluster service (%d)\n",
@@ -1866,10 +1876,6 @@ int bitmap_copy_from_slot(struct mddev *mddev, int slot,
 	if (IS_ERR(bitmap))
 		return PTR_ERR(bitmap);
 
-	rv = bitmap_read_sb(bitmap);
-	if (rv)
-		goto err;
-
 	rv = bitmap_init_from_disk(bitmap, 0);
 	if (rv)
 		goto err;
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index fcfc4b9..0072190 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -44,6 +44,7 @@ struct resync_info {
 
 /* md_cluster_info flags */
 #define		MD_CLUSTER_WAITING_FOR_NEWDISK		1
+#define		MD_CLUSTER_SUSPEND_READ_BALANCING	2
 
 
 struct md_cluster_info {
@@ -275,6 +276,9 @@ clear_bit:
 
 static void recover_prep(void *arg)
 {
+	struct mddev *mddev = arg;
+	struct md_cluster_info *cinfo = mddev->cluster_info;
+	set_bit(MD_CLUSTER_SUSPEND_READ_BALANCING, &cinfo->state);
 }
 
 static void recover_slot(void *arg, struct dlm_slot *slot)
@@ -307,6 +311,7 @@ static void recover_done(void *arg, struct dlm_slot *slots,
 
 	cinfo->slot_number = our_slot;
 	complete(&cinfo->completion);
+	clear_bit(MD_CLUSTER_SUSPEND_READ_BALANCING, &cinfo->state);
 }
 
 static const struct dlm_lockspace_ops md_ls_ops = {
@@ -816,12 +821,17 @@ static void resync_finish(struct mddev *mddev)
 	resync_send(mddev, RESYNCING, 0, 0);
 }
 
-static int area_resyncing(struct mddev *mddev, sector_t lo, sector_t hi)
+static int area_resyncing(struct mddev *mddev, int direction,
+		sector_t lo, sector_t hi)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
 	int ret = 0;
 	struct suspend_info *s;
 
+	if ((direction == READ) &&
+		test_bit(MD_CLUSTER_SUSPEND_READ_BALANCING, &cinfo->state))
+		return 1;
+
 	spin_lock_irq(&cinfo->suspend_lock);
 	if (list_empty(&cinfo->suspend_list))
 		goto out;
diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h
index 6817ee0..00defe2 100644
--- a/drivers/md/md-cluster.h
+++ b/drivers/md/md-cluster.h
@@ -18,7 +18,7 @@ struct md_cluster_operations {
 	int (*metadata_update_start)(struct mddev *mddev);
 	int (*metadata_update_finish)(struct mddev *mddev);
 	int (*metadata_update_cancel)(struct mddev *mddev);
-	int (*area_resyncing)(struct mddev *mddev, sector_t lo, sector_t hi);
+	int (*area_resyncing)(struct mddev *mddev, int direction, sector_t lo, sector_t hi);
 	int (*add_new_disk_start)(struct mddev *mddev, struct md_rdev *rdev);
 	int (*add_new_disk_finish)(struct mddev *mddev);
 	int (*new_disk_ack)(struct mddev *mddev, bool ack);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index d429c30..0c2a4e8 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5382,6 +5382,8 @@ static void __md_stop(struct mddev *mddev)
 {
 	struct md_personality *pers = mddev->pers;
 	mddev_detach(mddev);
+	/* Ensure ->event_work is done */
+	flush_workqueue(md_misc_wq);
 	spin_lock(&mddev->lock);
 	mddev->ready = 0;
 	mddev->pers = NULL;
@@ -7437,7 +7439,7 @@ int md_setup_cluster(struct mddev *mddev, int nodes)
 	err = request_module("md-cluster");
 	if (err) {
 		pr_err("md-cluster module not found.\n");
-		return err;
+		return -ENOENT;
 	}
 
 	spin_lock(&pers_lock);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index f80f1af..94f5b55 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -336,7 +336,7 @@ static void raid1_end_read_request(struct bio *bio, int error)
 		spin_lock_irqsave(&conf->device_lock, flags);
 		if (r1_bio->mddev->degraded == conf->raid_disks ||
 		    (r1_bio->mddev->degraded == conf->raid_disks-1 &&
-		     !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags)))
+		     test_bit(In_sync, &conf->mirrors[mirror].rdev->flags)))
 			uptodate = 1;
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 	}
@@ -541,7 +541,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 
 	if ((conf->mddev->recovery_cp < this_sector + sectors) ||
 	    (mddev_is_clustered(conf->mddev) &&
-	    md_cluster_ops->area_resyncing(conf->mddev, this_sector,
+	    md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
 		    this_sector + sectors)))
 		choose_first = 1;
 	else
@@ -1111,7 +1111,8 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 	    ((bio_end_sector(bio) > mddev->suspend_lo &&
 	    bio->bi_iter.bi_sector < mddev->suspend_hi) ||
 	    (mddev_is_clustered(mddev) &&
-	     md_cluster_ops->area_resyncing(mddev, bio->bi_iter.bi_sector, bio_end_sector(bio))))) {
+	     md_cluster_ops->area_resyncing(mddev, WRITE,
+		     bio->bi_iter.bi_sector, bio_end_sector(bio))))) {
 		/* As the suspend_* range is controlled by
 		 * userspace, we want an interruptible
 		 * wait.
@@ -1124,7 +1125,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
 			if (bio_end_sector(bio) <= mddev->suspend_lo ||
 			    bio->bi_iter.bi_sector >= mddev->suspend_hi ||
 			    (mddev_is_clustered(mddev) &&
-			     !md_cluster_ops->area_resyncing(mddev,
+			     !md_cluster_ops->area_resyncing(mddev, WRITE,
 				     bio->bi_iter.bi_sector, bio_end_sector(bio))))
 				break;
 			schedule();
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 940f2f3..38c58e1 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3556,6 +3556,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
 			/* far_copies must be 1 */
 			conf->prev.stride = conf->dev_sectors;
 	}
+	conf->reshape_safe = conf->reshape_progress;
 	spin_lock_init(&conf->device_lock);
 	INIT_LIST_HEAD(&conf->retry_list);
 
@@ -3760,7 +3761,6 @@ static int run(struct mddev *mddev)
 		}
 		conf->offset_diff = min_offset_diff;
 
-		conf->reshape_safe = conf->reshape_progress;
 		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 		set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
@@ -4103,6 +4103,7 @@ static int raid10_start_reshape(struct mddev *mddev)
 		conf->reshape_progress = size;
 	} else
 		conf->reshape_progress = 0;
+	conf->reshape_safe = conf->reshape_progress;
 	spin_unlock_irq(&conf->device_lock);
 
 	if (mddev->delta_disks && mddev->bitmap) {
@@ -4170,6 +4171,7 @@ abort:
 		rdev->new_data_offset = rdev->data_offset;
 	smp_wmb();
 	conf->reshape_progress = MaxSector;
+	conf->reshape_safe = MaxSector;
 	mddev->reshape_position = MaxSector;
 	spin_unlock_irq(&conf->device_lock);
 	return ret;
@@ -4524,6 +4526,7 @@ static void end_reshape(struct r10conf *conf)
 	md_finish_reshape(conf->mddev);
 	smp_wmb();
 	conf->reshape_progress = MaxSector;
+	conf->reshape_safe = MaxSector;
 	spin_unlock_irq(&conf->device_lock);
 
 	/* read-ahead size must cover two whole stripes, which is
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 59e44e9..643d217 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2162,6 +2162,9 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	if (!sc)
 		return -ENOMEM;
 
+	/* Need to ensure auto-resizing doesn't interfere */
+	mutex_lock(&conf->cache_size_mutex);
+
 	for (i = conf->max_nr_stripes; i; i--) {
 		nsh = alloc_stripe(sc, GFP_KERNEL);
 		if (!nsh)
@@ -2178,6 +2181,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 			kmem_cache_free(sc, nsh);
 		}
 		kmem_cache_destroy(sc);
+		mutex_unlock(&conf->cache_size_mutex);
 		return -ENOMEM;
 	}
 	/* Step 2 - Must use GFP_NOIO now.
@@ -2224,6 +2228,7 @@ static int resize_stripes(struct r5conf *conf, int newsize)
 	} else
 		err = -ENOMEM;
 
+	mutex_unlock(&conf->cache_size_mutex);
 	/* Step 4, return new stripes to service */
 	while(!list_empty(&newstripes)) {
 		nsh = list_entry(newstripes.next, struct stripe_head, lru);
@@ -4061,8 +4066,10 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 				 &first_bad, &bad_sectors))
 			set_bit(R5_ReadRepl, &dev->flags);
 		else {
-			if (rdev)
+			if (rdev && !test_bit(Faulty, &rdev->flags))
 				set_bit(R5_NeedReplace, &dev->flags);
+			else
+				clear_bit(R5_NeedReplace, &dev->flags);
 			rdev = rcu_dereference(conf->disks[i].rdev);
 			clear_bit(R5_ReadRepl, &dev->flags);
 		}
@@ -5857,12 +5864,14 @@ static void raid5d(struct md_thread *thread)
 	pr_debug("%d stripes handled\n", handled);
 
 	spin_unlock_irq(&conf->device_lock);
-	if (test_and_clear_bit(R5_ALLOC_MORE, &conf->cache_state)) {
+	if (test_and_clear_bit(R5_ALLOC_MORE, &conf->cache_state) &&
+	    mutex_trylock(&conf->cache_size_mutex)) {
 		grow_one_stripe(conf, __GFP_NOWARN);
 		/* Set flag even if allocation failed.  This helps
 		 * slow down allocation requests when mem is short
 		 */
 		set_bit(R5_DID_ALLOC, &conf->cache_state);
+		mutex_unlock(&conf->cache_size_mutex);
 	}
 
 	async_tx_issue_pending_all();
@@ -5894,18 +5903,22 @@ raid5_set_cache_size(struct mddev *mddev, int size)
 		return -EINVAL;
 
 	conf->min_nr_stripes = size;
+	mutex_lock(&conf->cache_size_mutex);
 	while (size < conf->max_nr_stripes &&
 	       drop_one_stripe(conf))
 		;
+	mutex_unlock(&conf->cache_size_mutex);
 
 
 	err = md_allow_write(mddev);
 	if (err)
 		return err;
 
+	mutex_lock(&conf->cache_size_mutex);
 	while (size > conf->max_nr_stripes)
 		if (!grow_one_stripe(conf, GFP_KERNEL))
 			break;
+	mutex_unlock(&conf->cache_size_mutex);
 
 	return 0;
 }
@@ -6371,11 +6384,18 @@ static unsigned long raid5_cache_scan(struct shrinker *shrink,
 				      struct shrink_control *sc)
 {
 	struct r5conf *conf = container_of(shrink, struct r5conf, shrinker);
-	int ret = 0;
-	while (ret < sc->nr_to_scan) {
-		if (drop_one_stripe(conf) == 0)
-			return SHRINK_STOP;
-		ret++;
+	unsigned long ret = SHRINK_STOP;
+
+	if (mutex_trylock(&conf->cache_size_mutex)) {
+		ret= 0;
+		while (ret < sc->nr_to_scan) {
+			if (drop_one_stripe(conf) == 0) {
+				ret = SHRINK_STOP;
+				break;
+			}
+			ret++;
+		}
+		mutex_unlock(&conf->cache_size_mutex);
 	}
 	return ret;
 }
@@ -6444,6 +6464,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 		goto abort;
 	spin_lock_init(&conf->device_lock);
 	seqcount_init(&conf->gen_lock);
+	mutex_init(&conf->cache_size_mutex);
 	init_waitqueue_head(&conf->wait_for_quiescent);
 	for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) {
 		init_waitqueue_head(&conf->wait_for_stripe[i]);
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 02c3bf8..d051442 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -482,7 +482,8 @@ struct r5conf {
 	 */
 	int			active_name;
 	char			cache_name[2][32];
-	struct kmem_cache		*slab_cache; /* for allocating stripes */
+	struct kmem_cache	*slab_cache; /* for allocating stripes */
+	struct mutex		cache_size_mutex; /* Protect changes to cache size */
 
 	int			seq_flush, seq_write;
 	int			quiesce;