Merge 3.12-rc3 into driver-core-next

We want the driver core and sysfs fixes in here to make merges and
development easier.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

17 files changed, 226 insertions, 89 deletions

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index b39f6f0b45f2..0f12382aa35d 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -498,7 +498,7 @@ struct cached_dev {
 	 */
 	atomic_t		has_dirty;
 
-	struct ratelimit	writeback_rate;
+	struct bch_ratelimit	writeback_rate;
 	struct delayed_work	writeback_rate_update;
 
 	/*
@@ -507,10 +507,9 @@ struct cached_dev {
 	 */
 	sector_t		last_read;
 
-	/* Number of writeback bios in flight */
-	atomic_t		in_flight;
+	/* Limit number of writeback bios in flight */
+	struct semaphore	in_flight;
 	struct closure_with_timer writeback;
-	struct closure_waitlist	writeback_wait;
 
 	struct keybuf		writeback_keys;
 
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 8010eed06a51..22d1ae72c282 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -926,28 +926,45 @@ struct bkey *bch_next_recurse_key(struct btree *b, struct bkey *search)
 
 /* Mergesort */
 
+static void sort_key_next(struct btree_iter *iter,
+			  struct btree_iter_set *i)
+{
+	i->k = bkey_next(i->k);
+
+	if (i->k == i->end)
+		*i = iter->data[--iter->used];
+}
+
 static void btree_sort_fixup(struct btree_iter *iter)
 {
 	while (iter->used > 1) {
 		struct btree_iter_set *top = iter->data, *i = top + 1;
-		struct bkey *k;
 
 		if (iter->used > 2 &&
 		    btree_iter_cmp(i[0], i[1]))
 			i++;
 
-		for (k = i->k;
-		     k != i->end && bkey_cmp(top->k, &START_KEY(k)) > 0;
-		     k = bkey_next(k))
-			if (top->k > i->k)
-				__bch_cut_front(top->k, k);
-			else if (KEY_SIZE(k))
-				bch_cut_back(&START_KEY(k), top->k);
-
-		if (top->k < i->k || k == i->k)
+		if (bkey_cmp(top->k, &START_KEY(i->k)) <= 0)
 			break;
 
-		heap_sift(iter, i - top, btree_iter_cmp);
+		if (!KEY_SIZE(i->k)) {
+			sort_key_next(iter, i);
+			heap_sift(iter, i - top, btree_iter_cmp);
+			continue;
+		}
+
+		if (top->k > i->k) {
+			if (bkey_cmp(top->k, i->k) >= 0)
+				sort_key_next(iter, i);
+			else
+				bch_cut_front(top->k, i->k);
+
+			heap_sift(iter, i - top, btree_iter_cmp);
+		} else {
+			/* can't happen because of comparison func */
+			BUG_ON(!bkey_cmp(&START_KEY(top->k), &START_KEY(i->k)));
+			bch_cut_back(&START_KEY(i->k), top->k);
+		}
 	}
 }
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index f9764e61978b..f42fc7ed9cd6 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -255,7 +255,7 @@ void bch_btree_node_read(struct btree *b)
 
 	return;
 err:
-	bch_cache_set_error(b->c, "io error reading bucket %lu",
+	bch_cache_set_error(b->c, "io error reading bucket %zu",
 			    PTR_BUCKET_NR(b->c, &b->key, 0));
 }
 
@@ -612,7 +612,7 @@ static unsigned long bch_mca_scan(struct shrinker *shrink,
 		return SHRINK_STOP;
 
 	/* Return -1 if we can't do anything right now */
-	if (sc->gfp_mask & __GFP_WAIT)
+	if (sc->gfp_mask & __GFP_IO)
 		mutex_lock(&c->bucket_lock);
 	else if (!mutex_trylock(&c->bucket_lock))
 		return -1;
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index ba95ab84b2be..8435f81e5d85 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -153,7 +153,8 @@ int bch_journal_read(struct cache_set *c, struct list_head *list,
 		bitmap_zero(bitmap, SB_JOURNAL_BUCKETS);
 		pr_debug("%u journal buckets", ca->sb.njournal_buckets);
 
-		/* Read journal buckets ordered by golden ratio hash to quickly
+		/*
+		 * Read journal buckets ordered by golden ratio hash to quickly
 		 * find a sequence of buckets with valid journal entries
 		 */
 		for (i = 0; i < ca->sb.njournal_buckets; i++) {
@@ -166,18 +167,20 @@ int bch_journal_read(struct cache_set *c, struct list_head *list,
 				goto bsearch;
 		}
 
-		/* If that fails, check all the buckets we haven't checked
+		/*
+		 * If that fails, check all the buckets we haven't checked
 		 * already
 		 */
 		pr_debug("falling back to linear search");
 
-		for (l = 0; l < ca->sb.njournal_buckets; l++) {
-			if (test_bit(l, bitmap))
-				continue;
-
+		for (l = find_first_zero_bit(bitmap, ca->sb.njournal_buckets);
+		     l < ca->sb.njournal_buckets;
+		     l = find_next_zero_bit(bitmap, ca->sb.njournal_buckets, l + 1))
 			if (read_bucket(l))
 				goto bsearch;
-		}
+
+		if (list_empty(list))
+			continue;
 bsearch:
 		/* Binary search */
 		m = r = find_next_bit(bitmap, ca->sb.njournal_buckets, l + 1);
@@ -197,10 +200,12 @@ bsearch:
 				r = m;
 		}
 
-		/* Read buckets in reverse order until we stop finding more
+		/*
+		 * Read buckets in reverse order until we stop finding more
 		 * journal entries
 		 */
-		pr_debug("finishing up");
+		pr_debug("finishing up: m %u njournal_buckets %u",
+			 m, ca->sb.njournal_buckets);
 		l = m;
 
 		while (1) {
@@ -228,9 +233,10 @@ bsearch:
 			}
 	}
 
-	c->journal.seq = list_entry(list->prev,
-				    struct journal_replay,
-				    list)->j.seq;
+	if (!list_empty(list))
+		c->journal.seq = list_entry(list->prev,
+					    struct journal_replay,
+					    list)->j.seq;
 
 	return 0;
 #undef read_bucket
@@ -428,7 +434,7 @@ static void do_journal_discard(struct cache *ca)
 		return;
 	}
 
-	switch (atomic_read(&ja->discard_in_flight) == DISCARD_IN_FLIGHT) {
+	switch (atomic_read(&ja->discard_in_flight)) {
 	case DISCARD_IN_FLIGHT:
 		return;
 
@@ -689,6 +695,7 @@ void bch_journal_meta(struct cache_set *c, struct closure *cl)
 		if (cl)
 			BUG_ON(!closure_wait(&w->wait, cl));
 
+		closure_flush(&c->journal.io);
 		__journal_try_write(c, true);
 	}
 }
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 786a1a4f74d8..71eb233b9ace 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -997,14 +997,17 @@ static void request_write(struct cached_dev *dc, struct search *s)
 	} else {
 		bch_writeback_add(dc);
 
-		if (s->op.flush_journal) {
+		if (bio->bi_rw & REQ_FLUSH) {
 			/* Also need to send a flush to the backing device */
-			s->op.cache_bio = bio_clone_bioset(bio, GFP_NOIO,
-							   dc->disk.bio_split);
+			struct bio *flush = bio_alloc_bioset(0, GFP_NOIO,
+							     dc->disk.bio_split);
 
-			bio->bi_size = 0;
-			bio->bi_vcnt = 0;
-			closure_bio_submit(bio, cl, s->d);
+			flush->bi_rw	= WRITE_FLUSH;
+			flush->bi_bdev	= bio->bi_bdev;
+			flush->bi_end_io = request_endio;
+			flush->bi_private = cl;
+
+			closure_bio_submit(flush, cl, s->d);
 		} else {
 			s->op.cache_bio = bio;
 		}
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 4fe6ab2fbe2e..924dcfdae111 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -223,8 +223,13 @@ STORE(__cached_dev)
 	}
 
 	if (attr == &sysfs_label) {
-		/* note: endlines are preserved */
-		memcpy(dc->sb.label, buf, SB_LABEL_SIZE);
+		if (size > SB_LABEL_SIZE)
+			return -EINVAL;
+		memcpy(dc->sb.label, buf, size);
+		if (size < SB_LABEL_SIZE)
+			dc->sb.label[size] = '\0';
+		if (size && dc->sb.label[size - 1] == '\n')
+			dc->sb.label[size - 1] = '\0';
 		bch_write_bdev_super(dc, NULL);
 		if (dc->disk.c) {
 			memcpy(dc->disk.c->uuids[dc->disk.id].label,
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index 98eb81159a22..420dad545c7d 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -190,7 +190,16 @@ void bch_time_stats_update(struct time_stats *stats, uint64_t start_time)
 	stats->last = now ?: 1;
 }
 
-unsigned bch_next_delay(struct ratelimit *d, uint64_t done)
+/**
+ * bch_next_delay() - increment @d by the amount of work done, and return how
+ * long to delay until the next time to do some work.
+ *
+ * @d - the struct bch_ratelimit to update
+ * @done - the amount of work done, in arbitrary units
+ *
+ * Returns the amount of time to delay by, in jiffies
+ */
+uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done)
 {
 	uint64_t now = local_clock();
 
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 1ae2a73ad85f..ea345c6896f4 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -450,17 +450,23 @@ read_attribute(name ## _last_ ## frequency_units)
 	(ewma) >> factor;						\
 })
 
-struct ratelimit {
+struct bch_ratelimit {
+	/* Next time we want to do some work, in nanoseconds */
 	uint64_t		next;
+
+	/*
+	 * Rate at which we want to do work, in units per nanosecond
+	 * The units here correspond to the units passed to bch_next_delay()
+	 */
 	unsigned		rate;
 };
 
-static inline void ratelimit_reset(struct ratelimit *d)
+static inline void bch_ratelimit_reset(struct bch_ratelimit *d)
 {
 	d->next = local_clock();
 }
 
-unsigned bch_next_delay(struct ratelimit *d, uint64_t done);
+uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done);
 
 #define __DIV_SAFE(n, d, zero)						\
 ({									\
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 22cbff551628..ba3ee48320f2 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -94,11 +94,15 @@ static void update_writeback_rate(struct work_struct *work)
 
 static unsigned writeback_delay(struct cached_dev *dc, unsigned sectors)
 {
+	uint64_t ret;
+
 	if (atomic_read(&dc->disk.detaching) ||
 	    !dc->writeback_percent)
 		return 0;
 
-	return bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL);
+	ret = bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL);
+
+	return min_t(uint64_t, ret, HZ);
 }
 
 /* Background writeback */
@@ -208,7 +212,7 @@ normal_refill:
 
 	up_write(&dc->writeback_lock);
 
-	ratelimit_reset(&dc->writeback_rate);
+	bch_ratelimit_reset(&dc->writeback_rate);
 
 	/* Punt to workqueue only so we don't recurse and blow the stack */
 	continue_at(cl, read_dirty, dirty_wq);
@@ -318,9 +322,7 @@ static void write_dirty_finish(struct closure *cl)
 	}
 
 	bch_keybuf_del(&dc->writeback_keys, w);
-	atomic_dec_bug(&dc->in_flight);
-
-	closure_wake_up(&dc->writeback_wait);
+	up(&dc->in_flight);
 
 	closure_return_with_destructor(cl, dirty_io_destructor);
 }
@@ -349,7 +351,7 @@ static void write_dirty(struct closure *cl)
 
 	closure_bio_submit(&io->bio, cl, &io->dc->disk);
 
-	continue_at(cl, write_dirty_finish, dirty_wq);
+	continue_at(cl, write_dirty_finish, system_wq);
 }
 
 static void read_dirty_endio(struct bio *bio, int error)
@@ -369,7 +371,7 @@ static void read_dirty_submit(struct closure *cl)
 
 	closure_bio_submit(&io->bio, cl, &io->dc->disk);
 
-	continue_at(cl, write_dirty, dirty_wq);
+	continue_at(cl, write_dirty, system_wq);
 }
 
 static void read_dirty(struct closure *cl)
@@ -394,12 +396,8 @@ static void read_dirty(struct closure *cl)
 
 		if (delay > 0 &&
 		    (KEY_START(&w->key) != dc->last_read ||
-		     jiffies_to_msecs(delay) > 50)) {
-			w->private = NULL;
-
-			closure_delay(&dc->writeback, delay);
-			continue_at(cl, read_dirty, dirty_wq);
-		}
+		     jiffies_to_msecs(delay) > 50))
+			delay = schedule_timeout_uninterruptible(delay);
 
 		dc->last_read	= KEY_OFFSET(&w->key);
 
@@ -424,15 +422,10 @@ static void read_dirty(struct closure *cl)
 
 		trace_bcache_writeback(&w->key);
 
-		closure_call(&io->cl, read_dirty_submit, NULL, &dc->disk.cl);
+		down(&dc->in_flight);
+		closure_call(&io->cl, read_dirty_submit, NULL, cl);
 
 		delay = writeback_delay(dc, KEY_SIZE(&w->key));
-
-		atomic_inc(&dc->in_flight);
-
-		if (!closure_wait_event(&dc->writeback_wait, cl,
-					atomic_read(&dc->in_flight) < 64))
-			continue_at(cl, read_dirty, dirty_wq);
 	}
 
 	if (0) {
@@ -442,7 +435,11 @@ err:
 		bch_keybuf_del(&dc->writeback_keys, w);
 	}
 
-	refill_dirty(cl);
+	/*
+	 * Wait for outstanding writeback IOs to finish (and keybuf slots to be
+	 * freed) before refilling again
+	 */
+	continue_at(cl, refill_dirty, dirty_wq);
 }
 
 /* Init */
@@ -484,6 +481,7 @@ void bch_sectors_dirty_init(struct cached_dev *dc)
 
 void bch_cached_dev_writeback_init(struct cached_dev *dc)
 {
+	sema_init(&dc->in_flight, 64);
 	closure_init_unlocked(&dc->writeback);
 	init_rwsem(&dc->writeback_lock);
 
@@ -513,7 +511,7 @@ void bch_writeback_exit(void)
 
 int __init bch_writeback_init(void)
 {
-	dirty_wq = create_singlethread_workqueue("bcache_writeback");
+	dirty_wq = create_workqueue("bcache_writeback");
 	if (!dirty_wq)
 		return -ENOMEM;
 
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index ea49834377c8..2a20986a2fec 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -19,8 +19,6 @@
 #define DM_MSG_PREFIX "io"
 
 #define DM_IO_MAX_REGIONS	BITS_PER_LONG
-#define MIN_IOS		16
-#define MIN_BIOS	16
 
 struct dm_io_client {
 	mempool_t *pool;
@@ -50,16 +48,17 @@ static struct kmem_cache *_dm_io_cache;
 struct dm_io_client *dm_io_client_create(void)
 {
 	struct dm_io_client *client;
+	unsigned min_ios = dm_get_reserved_bio_based_ios();
 
 	client = kmalloc(sizeof(*client), GFP_KERNEL);
 	if (!client)
 		return ERR_PTR(-ENOMEM);
 
-	client->pool = mempool_create_slab_pool(MIN_IOS, _dm_io_cache);
+	client->pool = mempool_create_slab_pool(min_ios, _dm_io_cache);
 	if (!client->pool)
 		goto bad;
 
-	client->bios = bioset_create(MIN_BIOS, 0);
+	client->bios = bioset_create(min_ios, 0);
 	if (!client->bios)
 		goto bad;
 
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index b759a127f9c3..de570a558764 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -7,6 +7,7 @@
 
 #include <linux/device-mapper.h>
 
+#include "dm.h"
 #include "dm-path-selector.h"
 #include "dm-uevent.h"
 
@@ -116,8 +117,6 @@ struct dm_mpath_io {
 
 typedef int (*action_fn) (struct pgpath *pgpath);
 
-#define MIN_IOS 256	/* Mempool size */
-
 static struct kmem_cache *_mpio_cache;
 
 static struct workqueue_struct *kmultipathd, *kmpath_handlerd;
@@ -190,6 +189,7 @@ static void free_priority_group(struct priority_group *pg,
 static struct multipath *alloc_multipath(struct dm_target *ti)
 {
 	struct multipath *m;
+	unsigned min_ios = dm_get_reserved_rq_based_ios();
 
 	m = kzalloc(sizeof(*m), GFP_KERNEL);
 	if (m) {
@@ -202,7 +202,7 @@ static struct multipath *alloc_multipath(struct dm_target *ti)
 		INIT_WORK(&m->trigger_event, trigger_event);
 		init_waitqueue_head(&m->pg_init_wait);
 		mutex_init(&m->work_mutex);
-		m->mpio_pool = mempool_create_slab_pool(MIN_IOS, _mpio_cache);
+		m->mpio_pool = mempool_create_slab_pool(min_ios, _mpio_cache);
 		if (!m->mpio_pool) {
 			kfree(m);
 			return NULL;
@@ -1268,6 +1268,7 @@ static int noretry_error(int error)
 	case -EREMOTEIO:
 	case -EILSEQ:
 	case -ENODATA:
+	case -ENOSPC:
 		return 1;
 	}
 
@@ -1298,8 +1299,17 @@ static int do_end_io(struct multipath *m, struct request *clone,
 	if (!error && !clone->errors)
 		return 0;	/* I/O complete */
 
-	if (noretry_error(error))
+	if (noretry_error(error)) {
+		if ((clone->cmd_flags & REQ_WRITE_SAME) &&
+		    !clone->q->limits.max_write_same_sectors) {
+			struct queue_limits *limits;
+
+			/* device doesn't really support WRITE SAME, disable it */
+			limits = dm_get_queue_limits(dm_table_get_md(m->ti->table));
+			limits->max_write_same_sectors = 0;
+		}
 		return error;
+	}
 
 	if (mpio->pgpath)
 		fail_path(mpio->pgpath);
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 3ac415675b6c..4caa8e6d59d7 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -256,7 +256,7 @@ static int chunk_io(struct pstore *ps, void *area, chunk_t chunk, int rw,
 	 */
 	INIT_WORK_ONSTACK(&req.work, do_metadata);
 	queue_work(ps->metadata_wq, &req.work);
-	flush_work(&req.work);
+	flush_workqueue(ps->metadata_wq);
 
 	return req.result;
 }
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index c434e5aab2df..aec57d76db5d 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -725,17 +725,16 @@ static int calc_max_buckets(void)
  */
 static int init_hash_tables(struct dm_snapshot *s)
 {
-	sector_t hash_size, cow_dev_size, origin_dev_size, max_buckets;
+	sector_t hash_size, cow_dev_size, max_buckets;
 
 	/*
 	 * Calculate based on the size of the original volume or
 	 * the COW volume...
 	 */
 	cow_dev_size = get_dev_size(s->cow->bdev);
-	origin_dev_size = get_dev_size(s->origin->bdev);
 	max_buckets = calc_max_buckets();
 
-	hash_size = min(origin_dev_size, cow_dev_size) >> s->store->chunk_shift;
+	hash_size = cow_dev_size >> s->store->chunk_shift;
 	hash_size = min(hash_size, max_buckets);
 
 	if (hash_size < 64)
diff --git a/drivers/md/dm-stats.c b/drivers/md/dm-stats.c
index 8ae31e8d3d64..3d404c1371ed 100644
--- a/drivers/md/dm-stats.c
+++ b/drivers/md/dm-stats.c
@@ -451,19 +451,26 @@ static void dm_stat_for_entry(struct dm_stat *s, size_t entry,
 	struct dm_stat_percpu *p;
 
 	/*
-	 * For strict correctness we should use local_irq_disable/enable
+	 * For strict correctness we should use local_irq_save/restore
 	 * instead of preempt_disable/enable.
 	 *
-	 * This is racy if the driver finishes bios from non-interrupt
-	 * context as well as from interrupt context or from more different
-	 * interrupts.
+	 * preempt_disable/enable is racy if the driver finishes bios
+	 * from non-interrupt context as well as from interrupt context
+	 * or from more different interrupts.
 	 *
-	 * However, the race only results in not counting some events,
-	 * so it is acceptable.
+	 * On 64-bit architectures the race only results in not counting some
+	 * events, so it is acceptable.  On 32-bit architectures the race could
+	 * cause the counter going off by 2^32, so we need to do proper locking
+	 * there.
 	 *
 	 * part_stat_lock()/part_stat_unlock() have this race too.
 	 */
+#if BITS_PER_LONG == 32
+	unsigned long flags;
+	local_irq_save(flags);
+#else
 	preempt_disable();
+#endif
 	p = &s->stat_percpu[smp_processor_id()][entry];
 
 	if (!end) {
@@ -478,7 +485,11 @@ static void dm_stat_for_entry(struct dm_stat *s, size_t entry,
 		p->ticks[idx] += duration;
 	}
 
+#if BITS_PER_LONG == 32
+	local_irq_restore(flags);
+#else
 	preempt_enable();
+#endif
 }
 
 static void __dm_stat_bio(struct dm_stat *s, unsigned long bi_rw,
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index ed063427d676..2c0cf511ec23 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -2095,6 +2095,7 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	 * them down to the data device.  The thin device's discard
 	 * processing will cause mappings to be removed from the btree.
 	 */
+	ti->discard_zeroes_data_unsupported = true;
 	if (pf.discard_enabled && pf.discard_passdown) {
 		ti->num_discard_bios = 1;
 
@@ -2104,7 +2105,6 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		 * thin devices' discard limits consistent).
 		 */
 		ti->discards_supported = true;
-		ti->discard_zeroes_data_unsupported = true;
 	}
 	ti->private = pt;
 
@@ -2689,8 +2689,16 @@ static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	 * They get transferred to the live pool in bind_control_target()
 	 * called from pool_preresume().
 	 */
-	if (!pt->adjusted_pf.discard_enabled)
+	if (!pt->adjusted_pf.discard_enabled) {
+		/*
+		 * Must explicitly disallow stacking discard limits otherwise the
+		 * block layer will stack them if pool's data device has support.
+		 * QUEUE_FLAG_DISCARD wouldn't be set but there is no way for the
+		 * user to see that, so make sure to set all discard limits to 0.
+		 */
+		limits->discard_granularity = 0;
 		return;
+	}
 
 	disable_passdown_if_not_supported(pt);
 
@@ -2826,10 +2834,10 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	ti->per_bio_data_size = sizeof(struct dm_thin_endio_hook);
 
 	/* In case the pool supports discards, pass them on. */
+	ti->discard_zeroes_data_unsupported = true;
 	if (tc->pool->pf.discard_enabled) {
 		ti->discards_supported = true;
 		ti->num_discard_bios = 1;
-		ti->discard_zeroes_data_unsupported = true;
 		/* Discard bios must be split on a block boundary */
 		ti->split_discard_bios = true;
 	}
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 6a5e9ed2fcc3..b3e26c7d1417 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -211,10 +211,55 @@ struct dm_md_mempools {
 	struct bio_set *bs;
 };
 
-#define MIN_IOS 256
+#define RESERVED_BIO_BASED_IOS		16
+#define RESERVED_REQUEST_BASED_IOS	256
+#define RESERVED_MAX_IOS		1024
 static struct kmem_cache *_io_cache;
 static struct kmem_cache *_rq_tio_cache;
 
+/*
+ * Bio-based DM's mempools' reserved IOs set by the user.
+ */
+static unsigned reserved_bio_based_ios = RESERVED_BIO_BASED_IOS;
+
+/*
+ * Request-based DM's mempools' reserved IOs set by the user.
+ */
+static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS;
+
+static unsigned __dm_get_reserved_ios(unsigned *reserved_ios,
+				      unsigned def, unsigned max)
+{
+	unsigned ios = ACCESS_ONCE(*reserved_ios);
+	unsigned modified_ios = 0;
+
+	if (!ios)
+		modified_ios = def;
+	else if (ios > max)
+		modified_ios = max;
+
+	if (modified_ios) {
+		(void)cmpxchg(reserved_ios, ios, modified_ios);
+		ios = modified_ios;
+	}
+
+	return ios;
+}
+
+unsigned dm_get_reserved_bio_based_ios(void)
+{
+	return __dm_get_reserved_ios(&reserved_bio_based_ios,
+				     RESERVED_BIO_BASED_IOS, RESERVED_MAX_IOS);
+}
+EXPORT_SYMBOL_GPL(dm_get_reserved_bio_based_ios);
+
+unsigned dm_get_reserved_rq_based_ios(void)
+{
+	return __dm_get_reserved_ios(&reserved_rq_based_ios,
+				     RESERVED_REQUEST_BASED_IOS, RESERVED_MAX_IOS);
+}
+EXPORT_SYMBOL_GPL(dm_get_reserved_rq_based_ios);
+
 static int __init local_init(void)
 {
 	int r = -ENOMEM;
@@ -2278,6 +2323,17 @@ struct target_type *dm_get_immutable_target_type(struct mapped_device *md)
 }
 
 /*
+ * The queue_limits are only valid as long as you have a reference
+ * count on 'md'.
+ */
+struct queue_limits *dm_get_queue_limits(struct mapped_device *md)
+{
+	BUG_ON(!atomic_read(&md->holders));
+	return &md->queue->limits;
+}
+EXPORT_SYMBOL_GPL(dm_get_queue_limits);
+
+/*
  * Fully initialize a request-based queue (->elevator, ->request_fn, etc).
  */
 static int dm_init_request_based_queue(struct mapped_device *md)
@@ -2862,18 +2918,18 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity, u
 
 	if (type == DM_TYPE_BIO_BASED) {
 		cachep = _io_cache;
-		pool_size = 16;
+		pool_size = dm_get_reserved_bio_based_ios();
 		front_pad = roundup(per_bio_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
 	} else if (type == DM_TYPE_REQUEST_BASED) {
 		cachep = _rq_tio_cache;
-		pool_size = MIN_IOS;
+		pool_size = dm_get_reserved_rq_based_ios();
 		front_pad = offsetof(struct dm_rq_clone_bio_info, clone);
 		/* per_bio_data_size is not used. See __bind_mempools(). */
 		WARN_ON(per_bio_data_size != 0);
 	} else
 		goto out;
 
-	pools->io_pool = mempool_create_slab_pool(MIN_IOS, cachep);
+	pools->io_pool = mempool_create_slab_pool(pool_size, cachep);
 	if (!pools->io_pool)
 		goto out;
 
@@ -2924,6 +2980,13 @@ module_exit(dm_exit);
 
 module_param(major, uint, 0);
 MODULE_PARM_DESC(major, "The major number of the device mapper");
+
+module_param(reserved_bio_based_ios, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(reserved_bio_based_ios, "Reserved IOs in bio-based mempools");
+
+module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools");
+
 MODULE_DESCRIPTION(DM_NAME " driver");
 MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 5e604cc7b4aa..1d1ad7b7e527 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -184,6 +184,9 @@ void dm_free_md_mempools(struct dm_md_mempools *pools);
 /*
  * Helpers that are used by DM core
  */
+unsigned dm_get_reserved_bio_based_ios(void);
+unsigned dm_get_reserved_rq_based_ios(void);
+
 static inline bool dm_message_test_buffer_overflow(char *result, unsigned maxlen)
 {
 	return !maxlen || strlen(result) + 1 >= maxlen;