5 files changed, 94 insertions, 8 deletions

diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index bb9b92ebbf8e..0da5efaad85c 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -248,7 +248,7 @@ struct cache {
 	/*
 	 * Fields for converting from sectors to blocks.
 	 */
-	uint32_t sectors_per_block;
+	sector_t sectors_per_block;
 	int sectors_per_block_shift;
 
 	spinlock_t lock;
@@ -3544,11 +3544,11 @@ static void cache_status(struct dm_target *ti, status_type_t type,
 
 		residency = policy_residency(cache->policy);
 
-		DMEMIT("%u %llu/%llu %u %llu/%llu %u %u %u %u %u %u %lu ",
+		DMEMIT("%u %llu/%llu %llu %llu/%llu %u %u %u %u %u %u %lu ",
 		       (unsigned)DM_CACHE_METADATA_BLOCK_SIZE,
 		       (unsigned long long)(nr_blocks_metadata - nr_free_blocks_metadata),
 		       (unsigned long long)nr_blocks_metadata,
-		       cache->sectors_per_block,
+		       (unsigned long long)cache->sectors_per_block,
 		       (unsigned long long) from_cblock(residency),
 		       (unsigned long long) from_cblock(cache->cache_size),
 		       (unsigned) atomic_read(&cache->stats.read_hit),
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index 8289804ccd99..d5ea9f28ae70 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -175,6 +175,7 @@ static void dm_stat_free(struct rcu_head *head)
 	int cpu;
 	struct dm_stat *s = container_of(head, struct dm_stat, rcu_head);
 
+	kfree(s->histogram_boundaries);
 	kfree(s->program_id);
 	kfree(s->aux_data);
 	for_each_possible_cpu(cpu) {
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 3384a3eef917..397f0454100b 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1467,11 +1467,62 @@ void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
 }
 EXPORT_SYMBOL_GPL(dm_accept_partial_bio);
 
+/*
+ * Flush current->bio_list when the target map method blocks.
+ * This fixes deadlocks in snapshot and possibly in other targets.
+ */
+struct dm_offload {
+	struct blk_plug plug;
+	struct blk_plug_cb cb;
+};
+
+static void flush_current_bio_list(struct blk_plug_cb *cb, bool from_schedule)
+{
+	struct dm_offload *o = container_of(cb, struct dm_offload, cb);
+	struct bio_list list;
+	struct bio *bio;
+
+	INIT_LIST_HEAD(&o->cb.list);
+
+	if (unlikely(!current->bio_list))
+		return;
+
+	list = *current->bio_list;
+	bio_list_init(current->bio_list);
+
+	while ((bio = bio_list_pop(&list))) {
+		struct bio_set *bs = bio->bi_pool;
+		if (unlikely(!bs) || bs == fs_bio_set) {
+			bio_list_add(current->bio_list, bio);
+			continue;
+		}
+
+		spin_lock(&bs->rescue_lock);
+		bio_list_add(&bs->rescue_list, bio);
+		queue_work(bs->rescue_workqueue, &bs->rescue_work);
+		spin_unlock(&bs->rescue_lock);
+	}
+}
+
+static void dm_offload_start(struct dm_offload *o)
+{
+	blk_start_plug(&o->plug);
+	o->cb.callback = flush_current_bio_list;
+	list_add(&o->cb.list, &current->plug->cb_list);
+}
+
+static void dm_offload_end(struct dm_offload *o)
+{
+	list_del(&o->cb.list);
+	blk_finish_plug(&o->plug);
+}
+
 static void __map_bio(struct dm_target_io *tio)
 {
 	int r;
 	sector_t sector;
 	struct mapped_device *md;
+	struct dm_offload o;
 	struct bio *clone = &tio->clone;
 	struct dm_target *ti = tio->ti;
 
@@ -1484,7 +1535,11 @@ static void __map_bio(struct dm_target_io *tio)
 	 */
 	atomic_inc(&tio->io->io_count);
 	sector = clone->bi_iter.bi_sector;
+
+	dm_offload_start(&o);
 	r = ti->type->map(ti, clone);
+	dm_offload_end(&o);
+
 	if (r == DM_MAPIO_REMAPPED) {
 		/* the bio has been remapped so dispatch it */
 
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index b7fe7e9fc777..6ba3227e29b2 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -52,18 +52,26 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector)
 	return conf->disks + lo;
 }
 
+/*
+ * In linear_congested() conf->raid_disks is used as a copy of
+ * mddev->raid_disks to iterate conf->disks[], because conf->raid_disks
+ * and conf->disks[] are created in linear_conf(), they are always
+ * consitent with each other, but mddev->raid_disks does not.
+ */
 static int linear_congested(struct mddev *mddev, int bits)
 {
 	struct linear_conf *conf;
 	int i, ret = 0;
 
-	conf = mddev->private;
+	rcu_read_lock();
+	conf = rcu_dereference(mddev->private);
 
-	for (i = 0; i < mddev->raid_disks && !ret ; i++) {
+	for (i = 0; i < conf->raid_disks && !ret ; i++) {
 		struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev);
 		ret |= bdi_congested(&q->backing_dev_info, bits);
 	}
 
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -143,6 +151,19 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 			conf->disks[i-1].end_sector +
 			conf->disks[i].rdev->sectors;
 
+	/*
+	 * conf->raid_disks is copy of mddev->raid_disks. The reason to
+	 * keep a copy of mddev->raid_disks in struct linear_conf is,
+	 * mddev->raid_disks may not be consistent with pointers number of
+	 * conf->disks[] when it is updated in linear_add() and used to
+	 * iterate old conf->disks[] earray in linear_congested().
+	 * Here conf->raid_disks is always consitent with number of
+	 * pointers in conf->disks[] array, and mddev->private is updated
+	 * with rcu_assign_pointer() in linear_addr(), such race can be
+	 * avoided.
+	 */
+	conf->raid_disks = raid_disks;
+
 	return conf;
 
 out:
@@ -195,15 +216,23 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
 	if (!newconf)
 		return -ENOMEM;
 
+	/* newconf->raid_disks already keeps a copy of * the increased
+	 * value of mddev->raid_disks, WARN_ONCE() is just used to make
+	 * sure of this. It is possible that oldconf is still referenced
+	 * in linear_congested(), therefore kfree_rcu() is used to free
+	 * oldconf until no one uses it anymore.
+	 */
 	mddev_suspend(mddev);
-	oldconf = mddev->private;
+	oldconf = rcu_dereference(mddev->private);
 	mddev->raid_disks++;
-	mddev->private = newconf;
+	WARN_ONCE(mddev->raid_disks != newconf->raid_disks,
+		"copied raid_disks doesn't match mddev->raid_disks");
+	rcu_assign_pointer(mddev->private, newconf);
 	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	mddev_resume(mddev);
 	revalidate_disk(mddev->gendisk);
-	kfree(oldconf);
+	kfree_rcu(oldconf, rcu);
 	return 0;
 }
 
diff --git a/drivers/md/linear.h b/drivers/md/linear.h
index b685ddd7d7f7..8d392e6098b3 100644
--- a/drivers/md/linear.h
+++ b/drivers/md/linear.h
@@ -10,6 +10,7 @@ struct linear_conf
 {
 	struct rcu_head		rcu;
 	sector_t		array_sectors;
+	int			raid_disks; /* a copy of mddev->raid_disks */
 	struct dev_info		disks[0];
 };
 #endif