23 files changed, 78 insertions, 424 deletions

diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index dd012ebface0..a190bf47076d 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1228,36 +1228,8 @@ static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode,
 	return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg);
 }
 
-static int cached_dev_congested(void *data, int bits)
-{
-	struct bcache_device *d = data;
-	struct cached_dev *dc = container_of(d, struct cached_dev, disk);
-	struct request_queue *q = bdev_get_queue(dc->bdev);
-	int ret = 0;
-
-	if (bdi_congested(q->backing_dev_info, bits))
-		return 1;
-
-	if (cached_dev_get(dc)) {
-		unsigned int i;
-		struct cache *ca;
-
-		for_each_cache(ca, d->c, i) {
-			q = bdev_get_queue(ca->bdev);
-			ret |= bdi_congested(q->backing_dev_info, bits);
-		}
-
-		cached_dev_put(dc);
-	}
-
-	return ret;
-}
-
 void bch_cached_dev_request_init(struct cached_dev *dc)
 {
-	struct gendisk *g = dc->disk.disk;
-
-	g->queue->backing_dev_info->congested_fn = cached_dev_congested;
 	dc->disk.cache_miss			= cached_dev_cache_miss;
 	dc->disk.ioctl				= cached_dev_ioctl;
 }
@@ -1341,27 +1313,8 @@ static int flash_dev_ioctl(struct bcache_device *d, fmode_t mode,
 	return -ENOTTY;
 }
 
-static int flash_dev_congested(void *data, int bits)
-{
-	struct bcache_device *d = data;
-	struct request_queue *q;
-	struct cache *ca;
-	unsigned int i;
-	int ret = 0;
-
-	for_each_cache(ca, d->c, i) {
-		q = bdev_get_queue(ca->bdev);
-		ret |= bdi_congested(q->backing_dev_info, bits);
-	}
-
-	return ret;
-}
-
 void bch_flash_dev_request_init(struct bcache_device *d)
 {
-	struct gendisk *g = d->disk;
-
-	g->queue->backing_dev_info->congested_fn = flash_dev_congested;
 	d->cache_miss				= flash_dev_cache_miss;
 	d->ioctl				= flash_dev_ioctl;
 }
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index de13f6e91696..9e45faa054b6 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -885,7 +885,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size,
 		return -ENOMEM;
 
 	d->disk->queue			= q;
-	q->backing_dev_info->congested_data = d;
 	q->limits.max_hw_sectors	= UINT_MAX;
 	q->limits.max_sectors		= UINT_MAX;
 	q->limits.max_segment_size	= UINT_MAX;
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 9eccced92896..96c93802ee4d 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -421,8 +421,6 @@ struct cache {
 
 	struct rw_semaphore quiesce_lock;
 
-	struct dm_target_callbacks callbacks;
-
 	/*
 	 * origin_blocks entries, discarded if set.
 	 */
@@ -2423,20 +2421,6 @@ static void set_cache_size(struct cache *cache, dm_cblock_t size)
 	cache->cache_size = size;
 }
 
-static int is_congested(struct dm_dev *dev, int bdi_bits)
-{
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-	return bdi_congested(q->backing_dev_info, bdi_bits);
-}
-
-static int cache_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
-{
-	struct cache *cache = container_of(cb, struct cache, callbacks);
-
-	return is_congested(cache->origin_dev, bdi_bits) ||
-		is_congested(cache->cache_dev, bdi_bits);
-}
-
 #define DEFAULT_MIGRATION_THRESHOLD 2048
 
 static int cache_create(struct cache_args *ca, struct cache **result)
@@ -2471,9 +2455,6 @@ static int cache_create(struct cache_args *ca, struct cache **result)
 			goto bad;
 	}
 
-	cache->callbacks.congested_fn = cache_is_congested;
-	dm_table_add_target_callbacks(ti->table, &cache->callbacks);
-
 	cache->metadata_dev = ca->metadata_dev;
 	cache->origin_dev = ca->origin_dev;
 	cache->cache_dev = ca->cache_dev;
diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c
index 59ed8a67c2e3..bdb255edc200 100644
--- a/drivers/md/dm-clone-target.c
+++ b/drivers/md/dm-clone-target.c
@@ -68,7 +68,6 @@ struct hash_table_bucket;
 
 struct clone {
 	struct dm_target *ti;
-	struct dm_target_callbacks callbacks;
 
 	struct dm_dev *metadata_dev;
 	struct dm_dev *dest_dev;
@@ -1518,18 +1517,6 @@ error:
 	DMEMIT("Error");
 }
 
-static int clone_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
-{
-	struct request_queue *dest_q, *source_q;
-	struct clone *clone = container_of(cb, struct clone, callbacks);
-
-	source_q = bdev_get_queue(clone->source_dev->bdev);
-	dest_q = bdev_get_queue(clone->dest_dev->bdev);
-
-	return (bdi_congested(dest_q->backing_dev_info, bdi_bits) |
-		bdi_congested(source_q->backing_dev_info, bdi_bits));
-}
-
 static sector_t get_dev_size(struct dm_dev *dev)
 {
 	return i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT;
@@ -1930,8 +1917,6 @@ static int clone_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto out_with_mempool;
 
 	mutex_init(&clone->commit_lock);
-	clone->callbacks.congested_fn = clone_is_congested;
-	dm_table_add_target_callbacks(ti->table, &clone->callbacks);
 
 	/* Enable flushes */
 	ti->num_flush_bios = 1;
diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c
index 566ddbdb16a4..b24e3839bb3a 100644
--- a/drivers/md/dm-era-target.c
+++ b/drivers/md/dm-era-target.c
@@ -1137,7 +1137,6 @@ static int metadata_get_stats(struct era_metadata *md, void *ptr)
 
 struct era {
 	struct dm_target *ti;
-	struct dm_target_callbacks callbacks;
 
 	struct dm_dev *metadata_dev;
 	struct dm_dev *origin_dev;
@@ -1375,18 +1374,6 @@ static void stop_worker(struct era *era)
 /*----------------------------------------------------------------
  * Target methods
  *--------------------------------------------------------------*/
-static int dev_is_congested(struct dm_dev *dev, int bdi_bits)
-{
-	struct request_queue *q = bdev_get_queue(dev->bdev);
-	return bdi_congested(q->backing_dev_info, bdi_bits);
-}
-
-static int era_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
-{
-	struct era *era = container_of(cb, struct era, callbacks);
-	return dev_is_congested(era->origin_dev, bdi_bits);
-}
-
 static void era_destroy(struct era *era)
 {
 	if (era->md)
@@ -1514,8 +1501,6 @@ static int era_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	ti->flush_supported = true;
 
 	ti->num_discard_bios = 1;
-	era->callbacks.congested_fn = era_is_congested;
-	dm_table_add_target_callbacks(ti->table, &era->callbacks);
 
 	return 0;
 }
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 10e8b2fe787b..d9e270957e18 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -242,7 +242,6 @@ struct raid_set {
 
 	struct mddev md;
 	struct raid_type *raid_type;
-	struct dm_target_callbacks callbacks;
 
 	sector_t array_sectors;
 	sector_t dev_sectors;
@@ -1705,13 +1704,6 @@ static void do_table_event(struct work_struct *ws)
 	dm_table_event(rs->ti->table);
 }
 
-static int raid_is_congested(struct dm_target_callbacks *cb, int bits)
-{
-	struct raid_set *rs = container_of(cb, struct raid_set, callbacks);
-
-	return mddev_congested(&rs->md, bits);
-}
-
 /*
  * Make sure a valid takover (level switch) is being requested on @rs
  *
@@ -3248,9 +3240,6 @@ size_check:
 		goto bad_md_start;
 	}
 
-	rs->callbacks.congested_fn = raid_is_congested;
-	dm_table_add_target_callbacks(ti->table, &rs->callbacks);
-
 	/* If raid4/5/6 journal mode explicitly requested (only possible with journal dev) -> set it */
 	if (test_bit(__CTR_FLAG_JOURNAL_MODE, &rs->ctr_flags)) {
 		r = r5c_journal_mode_set(&rs->md, rs->journal_dev.mode);
@@ -3310,7 +3299,6 @@ static void raid_dtr(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
 
-	list_del_init(&rs->callbacks.list);
 	md_stop(&rs->md);
 	raid_set_free(rs);
 }
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 5aec1cd09348..7ce387a1cc6a 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -146,10 +146,6 @@ static void rq_end_stats(struct mapped_device *md, struct request *orig)
  */
 static void rq_completed(struct mapped_device *md)
 {
-	/* nudge anyone waiting on suspend queue */
-	if (unlikely(wq_has_sleeper(&md->wait)))
-		wake_up(&md->wait);
-
 	/*
 	 * dm_put() must be at the end of this function. See the comment above
 	 */
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 8277b959e00b..0ea5b7367179 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -64,8 +64,6 @@ struct dm_table {
 	void *event_context;
 
 	struct dm_md_mempools *mempools;
-
-	struct list_head target_callbacks;
 };
 
 /*
@@ -190,7 +188,6 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&t->devices);
-	INIT_LIST_HEAD(&t->target_callbacks);
 
 	if (!num_targets)
 		num_targets = KEYS_PER_NODE;
@@ -361,7 +358,7 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev,
  * This upgrades the mode on an already open dm_dev, being
  * careful to leave things as they were if we fail to reopen the
  * device and not to touch the existing bdev field in case
- * it is accessed concurrently inside dm_table_any_congested().
+ * it is accessed concurrently.
  */
 static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
 			struct mapped_device *md)
@@ -2052,38 +2049,6 @@ int dm_table_resume_targets(struct dm_table *t)
 	return 0;
 }
 
-void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb)
-{
-	list_add(&cb->list, &t->target_callbacks);
-}
-EXPORT_SYMBOL_GPL(dm_table_add_target_callbacks);
-
-int dm_table_any_congested(struct dm_table *t, int bdi_bits)
-{
-	struct dm_dev_internal *dd;
-	struct list_head *devices = dm_table_get_devices(t);
-	struct dm_target_callbacks *cb;
-	int r = 0;
-
-	list_for_each_entry(dd, devices, list) {
-		struct request_queue *q = bdev_get_queue(dd->dm_dev->bdev);
-		char b[BDEVNAME_SIZE];
-
-		if (likely(q))
-			r |= bdi_congested(q->backing_dev_info, bdi_bits);
-		else
-			DMWARN_LIMIT("%s: any_congested: nonexistent device %s",
-				     dm_device_name(t->md),
-				     bdevname(dd->dm_dev->bdev, b));
-	}
-
-	list_for_each_entry(cb, &t->target_callbacks, list)
-		if (cb->congested_fn)
-			r |= cb->congested_fn(cb, bdi_bits);
-
-	return r;
-}
-
 struct mapped_device *dm_table_get_md(struct dm_table *t)
 {
 	return t->md;
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index fe2de2888709..fff4c50df74d 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -326,7 +326,6 @@ struct pool_c {
 	struct pool *pool;
 	struct dm_dev *data_dev;
 	struct dm_dev *metadata_dev;
-	struct dm_target_callbacks callbacks;
 
 	dm_block_t low_water_blocks;
 	struct pool_features requested_pf; /* Features requested during table load */
@@ -2796,18 +2795,6 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio)
 	}
 }
 
-static int pool_is_congested(struct dm_target_callbacks *cb, int bdi_bits)
-{
-	struct pool_c *pt = container_of(cb, struct pool_c, callbacks);
-	struct request_queue *q;
-
-	if (get_pool_mode(pt->pool) == PM_OUT_OF_DATA_SPACE)
-		return 1;
-
-	q = bdev_get_queue(pt->data_dev->bdev);
-	return bdi_congested(q->backing_dev_info, bdi_bits);
-}
-
 static void requeue_bios(struct pool *pool)
 {
 	struct thin_c *tc;
@@ -3420,9 +3407,6 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	dm_pool_register_pre_commit_callback(pool->pmd,
 					     metadata_pre_commit_callback, pool);
 
-	pt->callbacks.congested_fn = pool_is_congested;
-	dm_table_add_target_callbacks(ti->table, &pt->callbacks);
-
 	mutex_unlock(&dm_thin_pool_table.mutex);
 
 	return 0;
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 44004f07b4a1..8aa306ebc2ab 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -2266,6 +2266,12 @@ invalid_optional:
 	}
 
 	if (WC_MODE_PMEM(wc)) {
+		if (!dax_synchronous(wc->ssd_dev->dax_dev)) {
+			r = -EOPNOTSUPP;
+			ti->error = "Asynchronous persistent memory not supported as pmem cache";
+			goto bad;
+		}
+
 		r = persistent_memory_claim(wc);
 		if (r) {
 			ti->error = "Unable to map persistent memory for cache";
diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index 5cf6f5f552e0..b298fefb022e 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -2217,8 +2217,15 @@ struct dm_zone *dmz_alloc_zone(struct dmz_metadata *zmd, unsigned int dev_idx,
 {
 	struct list_head *list;
 	struct dm_zone *zone;
-	int i = 0;
+	int i;
+
+	/* Schedule reclaim to ensure free zones are available */
+	if (!(flags & DMZ_ALLOC_RECLAIM)) {
+		for (i = 0; i < zmd->nr_devs; i++)
+			dmz_schedule_reclaim(zmd->dev[i].reclaim);
+	}
 
+	i = 0;
 again:
 	if (flags & DMZ_ALLOC_CACHE)
 		list = &zmd->unmap_cache_list;
diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c
index dd1eebf6e50f..9c0ecc9568a4 100644
--- a/drivers/md/dm-zoned-reclaim.c
+++ b/drivers/md/dm-zoned-reclaim.c
@@ -456,6 +456,8 @@ static unsigned int dmz_reclaim_percentage(struct dmz_reclaim *zrc)
 		nr_zones = dmz_nr_rnd_zones(zmd, zrc->dev_idx);
 		nr_unmap = dmz_nr_unmap_rnd_zones(zmd, zrc->dev_idx);
 	}
+	if (nr_unmap <= 1)
+		return 0;
 	return nr_unmap * 100 / nr_zones;
 }
 
@@ -501,7 +503,7 @@ static void dmz_reclaim_work(struct work_struct *work)
 {
 	struct dmz_reclaim *zrc = container_of(work, struct dmz_reclaim, work.work);
 	struct dmz_metadata *zmd = zrc->metadata;
-	unsigned int p_unmap, nr_unmap_rnd = 0, nr_rnd = 0;
+	unsigned int p_unmap;
 	int ret;
 
 	if (dmz_dev_is_dying(zmd))
@@ -527,9 +529,6 @@ static void dmz_reclaim_work(struct work_struct *work)
 		zrc->kc_throttle.throttle = min(75U, 100U - p_unmap / 2);
 	}
 
-	nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd, zrc->dev_idx);
-	nr_rnd = dmz_nr_rnd_zones(zmd, zrc->dev_idx);
-
 	DMDEBUG("(%s/%u): Reclaim (%u): %s, %u%% free zones (%u/%u cache %u/%u random)",
 		dmz_metadata_label(zmd), zrc->dev_idx,
 		zrc->kc_throttle.throttle,
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index 7fcf198547d5..697f9de37355 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -400,15 +400,7 @@ static void dmz_handle_bio(struct dmz_target *dmz, struct dm_chunk_work *cw,
 		dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
 	struct dmz_metadata *zmd = dmz->metadata;
 	struct dm_zone *zone;
-	int i, ret;
-
-	/*
-	 * Write may trigger a zone allocation. So make sure the
-	 * allocation can succeed.
-	 */
-	if (bio_op(bio) == REQ_OP_WRITE)
-		for (i = 0; i < dmz->nr_ddevs; i++)
-			dmz_schedule_reclaim(dmz->dev[i].reclaim);
+	int ret;
 
 	dmz_lock_metadata(zmd);
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index a02842afe358..b2b07d954547 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/signal.h>
 #include <linux/blkpg.h>
 #include <linux/bio.h>
@@ -654,28 +655,6 @@ static void free_tio(struct dm_target_io *tio)
 	bio_put(&tio->clone);
 }
 
-static bool md_in_flight_bios(struct mapped_device *md)
-{
-	int cpu;
-	struct hd_struct *part = &dm_disk(md)->part0;
-	long sum = 0;
-
-	for_each_possible_cpu(cpu) {
-		sum += part_stat_local_read_cpu(part, in_flight[0], cpu);
-		sum += part_stat_local_read_cpu(part, in_flight[1], cpu);
-	}
-
-	return sum != 0;
-}
-
-static bool md_in_flight(struct mapped_device *md)
-{
-	if (queue_is_mq(md->queue))
-		return blk_mq_queue_inflight(md->queue);
-	else
-		return md_in_flight_bios(md);
-}
-
 u64 dm_start_time_ns_from_clone(struct bio *bio)
 {
 	struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
@@ -1834,31 +1813,6 @@ static blk_qc_t dm_submit_bio(struct bio *bio)
 	return ret;
 }
 
-static int dm_any_congested(void *congested_data, int bdi_bits)
-{
-	int r = bdi_bits;
-	struct mapped_device *md = congested_data;
-	struct dm_table *map;
-
-	if (!test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) {
-		if (dm_request_based(md)) {
-			/*
-			 * With request-based DM we only need to check the
-			 * top-level queue for congestion.
-			 */
-			struct backing_dev_info *bdi = md->queue->backing_dev_info;
-			r = bdi->wb.congested->state & bdi_bits;
-		} else {
-			map = dm_get_live_table_fast(md);
-			if (map)
-				r = dm_table_any_congested(map, bdi_bits);
-			dm_put_live_table_fast(md);
-		}
-	}
-
-	return r;
-}
-
 /*-----------------------------------------------------------------
  * An IDR is used to keep track of allocated minor numbers.
  *---------------------------------------------------------------*/
@@ -2297,12 +2251,6 @@ struct queue_limits *dm_get_queue_limits(struct mapped_device *md)
 }
 EXPORT_SYMBOL_GPL(dm_get_queue_limits);
 
-static void dm_init_congested_fn(struct mapped_device *md)
-{
-	md->queue->backing_dev_info->congested_data = md;
-	md->queue->backing_dev_info->congested_fn = dm_any_congested;
-}
-
 /*
  * Setup the DM device's queue based on md's type
  */
@@ -2319,12 +2267,10 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 			DMERR("Cannot initialize queue for request-based dm-mq mapped device");
 			return r;
 		}
-		dm_init_congested_fn(md);
 		break;
 	case DM_TYPE_BIO_BASED:
 	case DM_TYPE_DAX_BIO_BASED:
 	case DM_TYPE_NVME_BIO_BASED:
-		dm_init_congested_fn(md);
 		break;
 	case DM_TYPE_NONE:
 		WARN_ON_ONCE(true);
@@ -2464,15 +2410,29 @@ void dm_put(struct mapped_device *md)
 }
 EXPORT_SYMBOL_GPL(dm_put);
 
-static int dm_wait_for_completion(struct mapped_device *md, long task_state)
+static bool md_in_flight_bios(struct mapped_device *md)
+{
+	int cpu;
+	struct hd_struct *part = &dm_disk(md)->part0;
+	long sum = 0;
+
+	for_each_possible_cpu(cpu) {
+		sum += part_stat_local_read_cpu(part, in_flight[0], cpu);
+		sum += part_stat_local_read_cpu(part, in_flight[1], cpu);
+	}
+
+	return sum != 0;
+}
+
+static int dm_wait_for_bios_completion(struct mapped_device *md, long task_state)
 {
 	int r = 0;
 	DEFINE_WAIT(wait);
 
-	while (1) {
+	while (true) {
 		prepare_to_wait(&md->wait, &wait, task_state);
 
-		if (!md_in_flight(md))
+		if (!md_in_flight_bios(md))
 			break;
 
 		if (signal_pending_state(task_state, current)) {
@@ -2487,6 +2447,28 @@ static int dm_wait_for_completion(struct mapped_device *md, long task_state)
 	return r;
 }
 
+static int dm_wait_for_completion(struct mapped_device *md, long task_state)
+{
+	int r = 0;
+
+	if (!queue_is_mq(md->queue))
+		return dm_wait_for_bios_completion(md, task_state);
+
+	while (true) {
+		if (!blk_mq_queue_inflight(md->queue))
+			break;
+
+		if (signal_pending_state(task_state, current)) {
+			r = -EINTR;
+			break;
+		}
+
+		msleep(5);
+	}
+
+	return r;
+}
+
 /*
  * Process the deferred bios
  */
@@ -2920,17 +2902,25 @@ EXPORT_SYMBOL_GPL(dm_internal_resume_fast);
 int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
 		       unsigned cookie)
 {
+	int r;
+	unsigned noio_flag;
 	char udev_cookie[DM_COOKIE_LENGTH];
 	char *envp[] = { udev_cookie, NULL };
 
+	noio_flag = memalloc_noio_save();
+
 	if (!cookie)
-		return kobject_uevent(&disk_to_dev(md->disk)->kobj, action);
+		r = kobject_uevent(&disk_to_dev(md->disk)->kobj, action);
 	else {
 		snprintf(udev_cookie, DM_COOKIE_LENGTH, "%s=%u",
 			 DM_COOKIE_ENV_VAR_NAME, cookie);
-		return kobject_uevent_env(&disk_to_dev(md->disk)->kobj,
-					  action, envp);
+		r = kobject_uevent_env(&disk_to_dev(md->disk)->kobj,
+				       action, envp);
 	}
+
+	memalloc_noio_restore(noio_flag);
+
+	return r;
 }
 
 uint32_t dm_next_uevent_seq(struct mapped_device *md)
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index d7c4f6606b5f..4f5fe664d05a 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -63,7 +63,6 @@ void dm_table_presuspend_targets(struct dm_table *t);
 void dm_table_presuspend_undo_targets(struct dm_table *t);
 void dm_table_postsuspend_targets(struct dm_table *t);
 int dm_table_resume_targets(struct dm_table *t);
-int dm_table_any_congested(struct dm_table *t, int bdi_bits);
 enum dm_queue_mode dm_table_get_type(struct dm_table *t);
 struct target_type *dm_table_get_immutable_target_type(struct dm_table *t);
 struct dm_target *dm_table_get_immutable_target(struct dm_table *t);
diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c
index 8efada3ee16f..c2ae9125c4c3 100644
--- a/drivers/md/md-linear.c
+++ b/drivers/md/md-linear.c
@@ -46,29 +46,6 @@ 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;
-
-	rcu_read_lock();
-	conf = rcu_dereference(mddev->private);
-
-	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;
-}
-
 static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks)
 {
 	struct linear_conf *conf;
@@ -322,7 +299,6 @@ static struct md_personality linear_personality =
 	.hot_add_disk	= linear_add,
 	.size		= linear_size,
 	.quiesce	= linear_quiesce,
-	.congested	= linear_congested,
 };
 
 static int __init linear_init (void)
diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c
index 277fdfd9ee54..776bbe542db5 100644
--- a/drivers/md/md-multipath.c
+++ b/drivers/md/md-multipath.c
@@ -151,28 +151,6 @@ static void multipath_status(struct seq_file *seq, struct mddev *mddev)
 	seq_putc(seq, ']');
 }
 
-static int multipath_congested(struct mddev *mddev, int bits)
-{
-	struct mpconf *conf = mddev->private;
-	int i, ret = 0;
-
-	rcu_read_lock();
-	for (i = 0; i < mddev->raid_disks ; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
-		if (rdev && !test_bit(Faulty, &rdev->flags)) {
-			struct request_queue *q = bdev_get_queue(rdev->bdev);
-
-			ret |= bdi_congested(q->backing_dev_info, bits);
-			/* Just like multipath_map, we just check the
-			 * first available device
-			 */
-			break;
-		}
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
 /*
  * Careful, this can execute in IRQ contexts as well!
  */
@@ -478,7 +456,6 @@ static struct md_personality multipath_personality =
 	.hot_add_disk	= multipath_add_disk,
 	.hot_remove_disk= multipath_remove_disk,
 	.size		= multipath_size,
-	.congested	= multipath_congested,
 };
 
 static int __init multipath_init (void)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index fc33f2f8a415..bc06f046d9e7 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -577,26 +577,6 @@ void mddev_resume(struct mddev *mddev)
 }
 EXPORT_SYMBOL_GPL(mddev_resume);
 
-int mddev_congested(struct mddev *mddev, int bits)
-{
-	struct md_personality *pers = mddev->pers;
-	int ret = 0;
-
-	rcu_read_lock();
-	if (mddev->suspended)
-		ret = 1;
-	else if (pers && pers->congested)
-		ret = pers->congested(mddev, bits);
-	rcu_read_unlock();
-	return ret;
-}
-EXPORT_SYMBOL_GPL(mddev_congested);
-static int md_congested(void *data, int bits)
-{
-	struct mddev *mddev = data;
-	return mddev_congested(mddev, bits);
-}
-
 /*
  * Generic flush handling for md
  */
@@ -5719,6 +5699,7 @@ static int md_alloc(dev_t dev, char *name)
 	 * remove it now.
 	 */
 	disk->flags |= GENHD_FL_EXT_DEVT;
+	disk->events |= DISK_EVENT_MEDIA_CHANGE;
 	mddev->gendisk = disk;
 	/* As soon as we call add_disk(), another thread could get
 	 * through to md_open, so make sure it doesn't get too far
@@ -6016,8 +5997,6 @@ int md_run(struct mddev *mddev)
 			blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue);
 		else
 			blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue);
-		mddev->queue->backing_dev_info->congested_data = mddev;
-		mddev->queue->backing_dev_info->congested_fn = md_congested;
 	}
 	if (pers->sync_request) {
 		if (mddev->kobj.sd &&
@@ -6402,7 +6381,6 @@ static int do_md_stop(struct mddev *mddev, int mode,
 
 		__md_stop_writes(mddev);
 		__md_stop(mddev);
-		mddev->queue->backing_dev_info->congested_fn = NULL;
 
 		/* tell userspace to handle 'inactive' */
 		sysfs_notify_dirent_safe(mddev->sysfs_state);
@@ -7858,20 +7836,17 @@ static void md_release(struct gendisk *disk, fmode_t mode)
 	mddev_put(mddev);
 }
 
-static int md_media_changed(struct gendisk *disk)
-{
-	struct mddev *mddev = disk->private_data;
-
-	return mddev->changed;
-}
-
-static int md_revalidate(struct gendisk *disk)
+static unsigned int md_check_events(struct gendisk *disk, unsigned int clearing)
 {
 	struct mddev *mddev = disk->private_data;
+	unsigned int ret = 0;
 
+	if (mddev->changed)
+		ret = DISK_EVENT_MEDIA_CHANGE;
 	mddev->changed = 0;
-	return 0;
+	return ret;
 }
+
 static const struct block_device_operations md_fops =
 {
 	.owner		= THIS_MODULE,
@@ -7883,8 +7858,7 @@ static const struct block_device_operations md_fops =
 	.compat_ioctl	= md_compat_ioctl,
 #endif
 	.getgeo		= md_getgeo,
-	.media_changed  = md_media_changed,
-	.revalidate_disk= md_revalidate,
+	.check_events	= md_check_events,
 };
 
 static int md_thread(void *arg)
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 1e172b3e499f..f79b5b4101ef 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -604,9 +604,6 @@ struct md_personality
 	 * array.
 	 */
 	void *(*takeover) (struct mddev *mddev);
-	/* congested implements bdi.congested_fn().
-	 * Will not be called while array is 'suspended' */
-	int (*congested)(struct mddev *mddev, int bits);
 	/* Changes the consistency policy of an active array. */
 	int (*change_consistency_policy)(struct mddev *mddev, const char *buf);
 };
@@ -717,7 +714,6 @@ extern void md_done_sync(struct mddev *mddev, int blocks, int ok);
 extern void md_error(struct mddev *mddev, struct md_rdev *rdev);
 extern void md_finish_reshape(struct mddev *mddev);
 
-extern int mddev_congested(struct mddev *mddev, int bits);
 extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio);
 extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
 			   sector_t sector, int size, struct page *page);
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index e9e91c8d8afc..f54a449f97aa 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -29,21 +29,6 @@ module_param(default_layout, int, 0644);
 	 (1L << MD_HAS_PPL) |		\
 	 (1L << MD_HAS_MULTIPLE_PPLS))
 
-static int raid0_congested(struct mddev *mddev, int bits)
-{
-	struct r0conf *conf = mddev->private;
-	struct md_rdev **devlist = conf->devlist;
-	int raid_disks = conf->strip_zone[0].nb_dev;
-	int i, ret = 0;
-
-	for (i = 0; i < raid_disks && !ret ; i++) {
-		struct request_queue *q = bdev_get_queue(devlist[i]->bdev);
-
-		ret |= bdi_congested(q->backing_dev_info, bits);
-	}
-	return ret;
-}
-
 /*
  * inform the user of the raid configuration
 */
@@ -818,7 +803,6 @@ static struct md_personality raid0_personality=
 	.size		= raid0_size,
 	.takeover	= raid0_takeover,
 	.quiesce	= raid0_quiesce,
-	.congested	= raid0_congested,
 };
 
 static int __init raid0_init (void)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 2aa2649cca66..960d854c07f8 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -786,36 +786,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 	return best_disk;
 }
 
-static int raid1_congested(struct mddev *mddev, int bits)
-{
-	struct r1conf *conf = mddev->private;
-	int i, ret = 0;
-
-	if ((bits & (1 << WB_async_congested)) &&
-	    conf->pending_count >= max_queued_requests)
-		return 1;
-
-	rcu_read_lock();
-	for (i = 0; i < conf->raid_disks * 2; i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
-		if (rdev && !test_bit(Faulty, &rdev->flags)) {
-			struct request_queue *q = bdev_get_queue(rdev->bdev);
-
-			BUG_ON(!q);
-
-			/* Note the '|| 1' - when read_balance prefers
-			 * non-congested targets, it can be removed
-			 */
-			if ((bits & (1 << WB_async_congested)) || 1)
-				ret |= bdi_congested(q->backing_dev_info, bits);
-			else
-				ret &= bdi_congested(q->backing_dev_info, bits);
-		}
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
 static void flush_bio_list(struct r1conf *conf, struct bio *bio)
 {
 	/* flush any pending bitmap writes to disk before proceeding w/ I/O */
@@ -3396,7 +3366,6 @@ static struct md_personality raid1_personality =
 	.check_reshape	= raid1_reshape,
 	.quiesce	= raid1_quiesce,
 	.takeover	= raid1_takeover,
-	.congested	= raid1_congested,
 };
 
 static int __init raid_init(void)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 2c47474fa69d..b1d0c9d4ef77 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -848,31 +848,6 @@ static struct md_rdev *read_balance(struct r10conf *conf,
 	return rdev;
 }
 
-static int raid10_congested(struct mddev *mddev, int bits)
-{
-	struct r10conf *conf = mddev->private;
-	int i, ret = 0;
-
-	if ((bits & (1 << WB_async_congested)) &&
-	    conf->pending_count >= max_queued_requests)
-		return 1;
-
-	rcu_read_lock();
-	for (i = 0;
-	     (i < conf->geo.raid_disks || i < conf->prev.raid_disks)
-		     && ret == 0;
-	     i++) {
-		struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
-		if (rdev && !test_bit(Faulty, &rdev->flags)) {
-			struct request_queue *q = bdev_get_queue(rdev->bdev);
-
-			ret |= bdi_congested(q->backing_dev_info, bits);
-		}
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
 static void flush_pending_writes(struct r10conf *conf)
 {
 	/* Any writes that have been queued but are awaiting
@@ -4929,7 +4904,6 @@ static struct md_personality raid10_personality =
 	.start_reshape	= raid10_start_reshape,
 	.finish_reshape	= raid10_finish_reshape,
 	.update_reshape_pos = raid10_update_reshape_pos,
-	.congested	= raid10_congested,
 };
 
 static int __init raid_init(void)
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index a4fbafa5b8f8..d7780b1dd0c5 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5099,28 +5099,6 @@ static void activate_bit_delay(struct r5conf *conf,
 	}
 }
 
-static int raid5_congested(struct mddev *mddev, int bits)
-{
-	struct r5conf *conf = mddev->private;
-
-	/* No difference between reads and writes.  Just check
-	 * how busy the stripe_cache is
-	 */
-
-	if (test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state))
-		return 1;
-
-	/* Also checks whether there is pressure on r5cache log space */
-	if (test_bit(R5C_LOG_TIGHT, &conf->cache_state))
-		return 1;
-	if (conf->quiesce)
-		return 1;
-	if (atomic_read(&conf->empty_inactive_list_nr))
-		return 1;
-
-	return 0;
-}
-
 static int in_chunk_boundary(struct mddev *mddev, struct bio *bio)
 {
 	struct r5conf *conf = mddev->private;
@@ -8427,7 +8405,6 @@ static struct md_personality raid6_personality =
 	.finish_reshape = raid5_finish_reshape,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid6_takeover,
-	.congested	= raid5_congested,
 	.change_consistency_policy = raid5_change_consistency_policy,
 };
 static struct md_personality raid5_personality =
@@ -8452,7 +8429,6 @@ static struct md_personality raid5_personality =
 	.finish_reshape = raid5_finish_reshape,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid5_takeover,
-	.congested	= raid5_congested,
 	.change_consistency_policy = raid5_change_consistency_policy,
 };
 
@@ -8478,7 +8454,6 @@ static struct md_personality raid4_personality =
 	.finish_reshape = raid5_finish_reshape,
 	.quiesce	= raid5_quiesce,
 	.takeover	= raid4_takeover,
-	.congested	= raid5_congested,
 	.change_consistency_policy = raid5_change_consistency_policy,
 };