1 files changed, 475 insertions, 176 deletions

diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index e22e6c892..d2bbe8cc1 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -112,22 +112,30 @@ DECLARE_DM_KCOPYD_THROTTLE_WITH_MODULE_PARM(snapshot_copy_throttle,
 /*
  * Key building.
  */
-static void build_data_key(struct dm_thin_device *td,
-			   dm_block_t b, struct dm_cell_key *key)
+enum lock_space {
+	VIRTUAL,
+	PHYSICAL
+};
+
+static void build_key(struct dm_thin_device *td, enum lock_space ls,
+		      dm_block_t b, dm_block_t e, struct dm_cell_key *key)
 {
-	key->virtual = 0;
+	key->virtual = (ls == VIRTUAL);
 	key->dev = dm_thin_dev_id(td);
 	key->block_begin = b;
-	key->block_end = b + 1ULL;
+	key->block_end = e;
+}
+
+static void build_data_key(struct dm_thin_device *td, dm_block_t b,
+			   struct dm_cell_key *key)
+{
+	build_key(td, PHYSICAL, b, b + 1llu, key);
 }
 
 static void build_virtual_key(struct dm_thin_device *td, dm_block_t b,
 			      struct dm_cell_key *key)
 {
-	key->virtual = 1;
-	key->dev = dm_thin_dev_id(td);
-	key->block_begin = b;
-	key->block_end = b + 1ULL;
+	build_key(td, VIRTUAL, b, b + 1llu, key);
 }
 
 /*----------------------------------------------------------------*/
@@ -313,6 +321,138 @@ struct thin_c {
 
 /*----------------------------------------------------------------*/
 
+/**
+ * __blkdev_issue_discard_async - queue a discard with async completion
+ * @bdev:	blockdev to issue discard for
+ * @sector:	start sector
+ * @nr_sects:	number of sectors to discard
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @flags:	BLKDEV_IFL_* flags to control behaviour
+ * @parent_bio: parent discard bio that all sub discards get chained to
+ *
+ * Description:
+ *    Asynchronously issue a discard request for the sectors in question.
+ *    NOTE: this variant of blk-core's blkdev_issue_discard() is a stop-gap
+ *    that is being kept local to DM thinp until the block changes to allow
+ *    late bio splitting land upstream.
+ */
+static int __blkdev_issue_discard_async(struct block_device *bdev, sector_t sector,
+					sector_t nr_sects, gfp_t gfp_mask, unsigned long flags,
+					struct bio *parent_bio)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+	int type = REQ_WRITE | REQ_DISCARD;
+	unsigned int max_discard_sectors, granularity;
+	int alignment;
+	struct bio *bio;
+	int ret = 0;
+	struct blk_plug plug;
+
+	if (!q)
+		return -ENXIO;
+
+	if (!blk_queue_discard(q))
+		return -EOPNOTSUPP;
+
+	/* Zero-sector (unknown) and one-sector granularities are the same.  */
+	granularity = max(q->limits.discard_granularity >> 9, 1U);
+	alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
+
+	/*
+	 * Ensure that max_discard_sectors is of the proper
+	 * granularity, so that requests stay aligned after a split.
+	 */
+	max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9);
+	max_discard_sectors -= max_discard_sectors % granularity;
+	if (unlikely(!max_discard_sectors)) {
+		/* Avoid infinite loop below. Being cautious never hurts. */
+		return -EOPNOTSUPP;
+	}
+
+	if (flags & BLKDEV_DISCARD_SECURE) {
+		if (!blk_queue_secdiscard(q))
+			return -EOPNOTSUPP;
+		type |= REQ_SECURE;
+	}
+
+	blk_start_plug(&plug);
+	while (nr_sects) {
+		unsigned int req_sects;
+		sector_t end_sect, tmp;
+
+		/*
+		 * Required bio_put occurs in bio_endio thanks to bio_chain below
+		 */
+		bio = bio_alloc(gfp_mask, 1);
+		if (!bio) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		req_sects = min_t(sector_t, nr_sects, max_discard_sectors);
+
+		/*
+		 * If splitting a request, and the next starting sector would be
+		 * misaligned, stop the discard at the previous aligned sector.
+		 */
+		end_sect = sector + req_sects;
+		tmp = end_sect;
+		if (req_sects < nr_sects &&
+		    sector_div(tmp, granularity) != alignment) {
+			end_sect = end_sect - alignment;
+			sector_div(end_sect, granularity);
+			end_sect = end_sect * granularity + alignment;
+			req_sects = end_sect - sector;
+		}
+
+		bio_chain(bio, parent_bio);
+
+		bio->bi_iter.bi_sector = sector;
+		bio->bi_bdev = bdev;
+
+		bio->bi_iter.bi_size = req_sects << 9;
+		nr_sects -= req_sects;
+		sector = end_sect;
+
+		submit_bio(type, bio);
+
+		/*
+		 * We can loop for a long time in here, if someone does
+		 * full device discards (like mkfs). Be nice and allow
+		 * us to schedule out to avoid softlocking if preempt
+		 * is disabled.
+		 */
+		cond_resched();
+	}
+	blk_finish_plug(&plug);
+
+	return ret;
+}
+
+static bool block_size_is_power_of_two(struct pool *pool)
+{
+	return pool->sectors_per_block_shift >= 0;
+}
+
+static sector_t block_to_sectors(struct pool *pool, dm_block_t b)
+{
+	return block_size_is_power_of_two(pool) ?
+		(b << pool->sectors_per_block_shift) :
+		(b * pool->sectors_per_block);
+}
+
+static int issue_discard(struct thin_c *tc, dm_block_t data_b, dm_block_t data_e,
+			 struct bio *parent_bio)
+{
+	sector_t s = block_to_sectors(tc->pool, data_b);
+	sector_t len = block_to_sectors(tc->pool, data_e - data_b);
+
+	return __blkdev_issue_discard_async(tc->pool_dev->bdev, s, len,
+					    GFP_NOWAIT, 0, parent_bio);
+}
+
+/*----------------------------------------------------------------*/
+
 /*
  * wake_worker() is used when new work is queued and when pool_resume is
  * ready to continue deferred IO processing.
@@ -462,6 +602,7 @@ struct dm_thin_endio_hook {
 	struct dm_deferred_entry *all_io_entry;
 	struct dm_thin_new_mapping *overwrite_mapping;
 	struct rb_node rb_node;
+	struct dm_bio_prison_cell *cell;
 };
 
 static void __merge_bio_list(struct bio_list *bios, struct bio_list *master)
@@ -525,16 +666,21 @@ static void requeue_io(struct thin_c *tc)
 	requeue_deferred_cells(tc);
 }
 
-static void error_retry_list(struct pool *pool)
+static void error_retry_list_with_code(struct pool *pool, int error)
 {
 	struct thin_c *tc;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(tc, &pool->active_thins, list)
-		error_thin_bio_list(tc, &tc->retry_on_resume_list, -EIO);
+		error_thin_bio_list(tc, &tc->retry_on_resume_list, error);
 	rcu_read_unlock();
 }
 
+static void error_retry_list(struct pool *pool)
+{
+	return error_retry_list_with_code(pool, -EIO);
+}
+
 /*
  * This section of code contains the logic for processing a thin device's IO.
  * Much of the code depends on pool object resources (lists, workqueues, etc)
@@ -542,11 +688,6 @@ static void error_retry_list(struct pool *pool)
  * target.
  */
 
-static bool block_size_is_power_of_two(struct pool *pool)
-{
-	return pool->sectors_per_block_shift >= 0;
-}
-
 static dm_block_t get_bio_block(struct thin_c *tc, struct bio *bio)
 {
 	struct pool *pool = tc->pool;
@@ -560,6 +701,34 @@ static dm_block_t get_bio_block(struct thin_c *tc, struct bio *bio)
 	return block_nr;
 }
 
+/*
+ * Returns the _complete_ blocks that this bio covers.
+ */
+static void get_bio_block_range(struct thin_c *tc, struct bio *bio,
+				dm_block_t *begin, dm_block_t *end)
+{
+	struct pool *pool = tc->pool;
+	sector_t b = bio->bi_iter.bi_sector;
+	sector_t e = b + (bio->bi_iter.bi_size >> SECTOR_SHIFT);
+
+	b += pool->sectors_per_block - 1ull; /* so we round up */
+
+	if (block_size_is_power_of_two(pool)) {
+		b >>= pool->sectors_per_block_shift;
+		e >>= pool->sectors_per_block_shift;
+	} else {
+		(void) sector_div(b, pool->sectors_per_block);
+		(void) sector_div(e, pool->sectors_per_block);
+	}
+
+	if (e < b)
+		/* Can happen if the bio is within a single block. */
+		e = b;
+
+	*begin = b;
+	*end = e;
+}
+
 static void remap(struct thin_c *tc, struct bio *bio, dm_block_t block)
 {
 	struct pool *pool = tc->pool;
@@ -648,7 +817,7 @@ struct dm_thin_new_mapping {
 	struct list_head list;
 
 	bool pass_discard:1;
-	bool definitely_not_shared:1;
+	bool maybe_shared:1;
 
 	/*
 	 * Track quiescing, copying and zeroing preparation actions.  When this
@@ -659,9 +828,9 @@ struct dm_thin_new_mapping {
 
 	int err;
 	struct thin_c *tc;
-	dm_block_t virt_block;
+	dm_block_t virt_begin, virt_end;
 	dm_block_t data_block;
-	struct dm_bio_prison_cell *cell, *cell2;
+	struct dm_bio_prison_cell *cell;
 
 	/*
 	 * If the bio covers the whole area of a block then we can avoid
@@ -706,6 +875,8 @@ static void overwrite_endio(struct bio *bio, int err)
 	struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
 	struct dm_thin_new_mapping *m = h->overwrite_mapping;
 
+	bio->bi_end_io = m->saved_bi_end_io;
+
 	m->err = err;
 	complete_mapping_preparation(m);
 }
@@ -794,10 +965,6 @@ static void inc_remap_and_issue_cell(struct thin_c *tc,
 
 static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m)
 {
-	if (m->bio) {
-		m->bio->bi_end_io = m->saved_bi_end_io;
-		atomic_inc(&m->bio->bi_remaining);
-	}
 	cell_error(m->tc->pool, m->cell);
 	list_del(&m->list);
 	mempool_free(m, m->tc->pool->mapping_pool);
@@ -807,15 +974,9 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m)
 {
 	struct thin_c *tc = m->tc;
 	struct pool *pool = tc->pool;
-	struct bio *bio;
+	struct bio *bio = m->bio;
 	int r;
 
-	bio = m->bio;
-	if (bio) {
-		bio->bi_end_io = m->saved_bi_end_io;
-		atomic_inc(&bio->bi_remaining);
-	}
-
 	if (m->err) {
 		cell_error(pool, m->cell);
 		goto out;
@@ -826,7 +987,7 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m)
 	 * Any I/O for this block arriving after this point will get
 	 * remapped to it directly.
 	 */
-	r = dm_thin_insert_block(tc->td, m->virt_block, m->data_block);
+	r = dm_thin_insert_block(tc->td, m->virt_begin, m->data_block);
 	if (r) {
 		metadata_operation_failed(pool, "dm_thin_insert_block", r);
 		cell_error(pool, m->cell);
@@ -853,50 +1014,112 @@ out:
 	mempool_free(m, pool->mapping_pool);
 }
 
-static void process_prepared_discard_fail(struct dm_thin_new_mapping *m)
+/*----------------------------------------------------------------*/
+
+static void free_discard_mapping(struct dm_thin_new_mapping *m)
 {
 	struct thin_c *tc = m->tc;
+	if (m->cell)
+		cell_defer_no_holder(tc, m->cell);
+	mempool_free(m, tc->pool->mapping_pool);
+}
 
+static void process_prepared_discard_fail(struct dm_thin_new_mapping *m)
+{
 	bio_io_error(m->bio);
+	free_discard_mapping(m);
+}
+
+static void process_prepared_discard_success(struct dm_thin_new_mapping *m)
+{
+	bio_endio(m->bio, 0);
+	free_discard_mapping(m);
+}
+
+static void process_prepared_discard_no_passdown(struct dm_thin_new_mapping *m)
+{
+	int r;
+	struct thin_c *tc = m->tc;
+
+	r = dm_thin_remove_range(tc->td, m->cell->key.block_begin, m->cell->key.block_end);
+	if (r) {
+		metadata_operation_failed(tc->pool, "dm_thin_remove_range", r);
+		bio_io_error(m->bio);
+	} else
+		bio_endio(m->bio, 0);
+
 	cell_defer_no_holder(tc, m->cell);
-	cell_defer_no_holder(tc, m->cell2);
 	mempool_free(m, tc->pool->mapping_pool);
 }
 
-static void process_prepared_discard_passdown(struct dm_thin_new_mapping *m)
+static int passdown_double_checking_shared_status(struct dm_thin_new_mapping *m)
 {
+	/*
+	 * We've already unmapped this range of blocks, but before we
+	 * passdown we have to check that these blocks are now unused.
+	 */
+	int r;
+	bool used = true;
 	struct thin_c *tc = m->tc;
+	struct pool *pool = tc->pool;
+	dm_block_t b = m->data_block, e, end = m->data_block + m->virt_end - m->virt_begin;
 
-	inc_all_io_entry(tc->pool, m->bio);
-	cell_defer_no_holder(tc, m->cell);
-	cell_defer_no_holder(tc, m->cell2);
+	while (b != end) {
+		/* find start of unmapped run */
+		for (; b < end; b++) {
+			r = dm_pool_block_is_used(pool->pmd, b, &used);
+			if (r)
+				return r;
 
-	if (m->pass_discard)
-		if (m->definitely_not_shared)
-			remap_and_issue(tc, m->bio, m->data_block);
-		else {
-			bool used = false;
-			if (dm_pool_block_is_used(tc->pool->pmd, m->data_block, &used) || used)
-				bio_endio(m->bio, 0);
-			else
-				remap_and_issue(tc, m->bio, m->data_block);
+			if (!used)
+				break;
 		}
-	else
-		bio_endio(m->bio, 0);
 
-	mempool_free(m, tc->pool->mapping_pool);
+		if (b == end)
+			break;
+
+		/* find end of run */
+		for (e = b + 1; e != end; e++) {
+			r = dm_pool_block_is_used(pool->pmd, e, &used);
+			if (r)
+				return r;
+
+			if (used)
+				break;
+		}
+
+		r = issue_discard(tc, b, e, m->bio);
+		if (r)
+			return r;
+
+		b = e;
+	}
+
+	return 0;
 }
 
-static void process_prepared_discard(struct dm_thin_new_mapping *m)
+static void process_prepared_discard_passdown(struct dm_thin_new_mapping *m)
 {
 	int r;
 	struct thin_c *tc = m->tc;
+	struct pool *pool = tc->pool;
 
-	r = dm_thin_remove_block(tc->td, m->virt_block);
+	r = dm_thin_remove_range(tc->td, m->virt_begin, m->virt_end);
 	if (r)
-		DMERR_LIMIT("dm_thin_remove_block() failed");
+		metadata_operation_failed(pool, "dm_thin_remove_range", r);
 
-	process_prepared_discard_passdown(m);
+	else if (m->maybe_shared)
+		r = passdown_double_checking_shared_status(m);
+	else
+		r = issue_discard(tc, m->data_block, m->data_block + (m->virt_end - m->virt_begin), m->bio);
+
+	/*
+	 * Even if r is set, there could be sub discards in flight that we
+	 * need to wait for.
+	 */
+	bio_endio(m->bio, r);
+	cell_defer_no_holder(tc, m->cell);
+	mempool_free(m, pool->mapping_pool);
 }
 
 static void process_prepared(struct pool *pool, struct list_head *head,
@@ -980,7 +1203,7 @@ static void ll_zero(struct thin_c *tc, struct dm_thin_new_mapping *m,
 }
 
 static void remap_and_issue_overwrite(struct thin_c *tc, struct bio *bio,
-				      dm_block_t data_block,
+				      dm_block_t data_begin,
 				      struct dm_thin_new_mapping *m)
 {
 	struct pool *pool = tc->pool;
@@ -990,7 +1213,7 @@ static void remap_and_issue_overwrite(struct thin_c *tc, struct bio *bio,
 	m->bio = bio;
 	save_and_set_endio(bio, &m->saved_bi_end_io, overwrite_endio);
 	inc_all_io_entry(pool, bio);
-	remap_and_issue(tc, bio, data_block);
+	remap_and_issue(tc, bio, data_begin);
 }
 
 /*
@@ -1007,7 +1230,8 @@ static void schedule_copy(struct thin_c *tc, dm_block_t virt_block,
 	struct dm_thin_new_mapping *m = get_next_mapping(pool);
 
 	m->tc = tc;
-	m->virt_block = virt_block;
+	m->virt_begin = virt_block;
+	m->virt_end = virt_block + 1u;
 	m->data_block = data_dest;
 	m->cell = cell;
 
@@ -1086,7 +1310,8 @@ static void schedule_zero(struct thin_c *tc, dm_block_t virt_block,
 
 	atomic_set(&m->prepare_actions, 1); /* no need to quiesce */
 	m->tc = tc;
-	m->virt_block = virt_block;
+	m->virt_begin = virt_block;
+	m->virt_end = virt_block + 1u;
 	m->data_block = data_block;
 	m->cell = cell;
 
@@ -1095,16 +1320,14 @@ static void schedule_zero(struct thin_c *tc, dm_block_t virt_block,
 	 * zeroing pre-existing data, we can issue the bio immediately.
 	 * Otherwise we use kcopyd to zero the data first.
 	 */
-	if (!pool->pf.zero_new_blocks)
+	if (pool->pf.zero_new_blocks) {
+		if (io_overwrites_block(pool, bio))
+			remap_and_issue_overwrite(tc, bio, data_block, m);
+		else
+			ll_zero(tc, m, data_block * pool->sectors_per_block,
+				(data_block + 1) * pool->sectors_per_block);
+	} else
 		process_prepared_mapping(m);
-
-	else if (io_overwrites_block(pool, bio))
-		remap_and_issue_overwrite(tc, bio, data_block, m);
-
-	else
-		ll_zero(tc, m,
-			data_block * pool->sectors_per_block,
-			(data_block + 1) * pool->sectors_per_block);
 }
 
 static void schedule_external_copy(struct thin_c *tc, dm_block_t virt_block,
@@ -1295,99 +1518,149 @@ static void retry_bios_on_resume(struct pool *pool, struct dm_bio_prison_cell *c
 		retry_on_resume(bio);
 }
 
-static void process_discard_cell(struct thin_c *tc, struct dm_bio_prison_cell *cell)
+static void process_discard_cell_no_passdown(struct thin_c *tc,
+					     struct dm_bio_prison_cell *virt_cell)
 {
-	int r;
-	struct bio *bio = cell->holder;
 	struct pool *pool = tc->pool;
-	struct dm_bio_prison_cell *cell2;
-	struct dm_cell_key key2;
-	dm_block_t block = get_bio_block(tc, bio);
-	struct dm_thin_lookup_result lookup_result;
-	struct dm_thin_new_mapping *m;
+	struct dm_thin_new_mapping *m = get_next_mapping(pool);
 
-	if (tc->requeue_mode) {
-		cell_requeue(pool, cell);
-		return;
-	}
+	/*
+	 * We don't need to lock the data blocks, since there's no
+	 * passdown.  We only lock data blocks for allocation and breaking sharing.
+	 */
+	m->tc = tc;
+	m->virt_begin = virt_cell->key.block_begin;
+	m->virt_end = virt_cell->key.block_end;
+	m->cell = virt_cell;
+	m->bio = virt_cell->holder;
 
-	r = dm_thin_find_block(tc->td, block, 1, &lookup_result);
-	switch (r) {
-	case 0:
-		/*
-		 * Check nobody is fiddling with this pool block.  This can
-		 * happen if someone's in the process of breaking sharing
-		 * on this block.
-		 */
-		build_data_key(tc->td, lookup_result.block, &key2);
-		if (bio_detain(tc->pool, &key2, bio, &cell2)) {
-			cell_defer_no_holder(tc, cell);
-			break;
-		}
+	if (!dm_deferred_set_add_work(pool->all_io_ds, &m->list))
+		pool->process_prepared_discard(m);
+}
 
-		if (io_overlaps_block(pool, bio)) {
-			/*
-			 * IO may still be going to the destination block.  We must
-			 * quiesce before we can do the removal.
-			 */
-			m = get_next_mapping(pool);
-			m->tc = tc;
-			m->pass_discard = pool->pf.discard_passdown;
-			m->definitely_not_shared = !lookup_result.shared;
-			m->virt_block = block;
-			m->data_block = lookup_result.block;
-			m->cell = cell;
-			m->cell2 = cell2;
-			m->bio = bio;
-
-			if (!dm_deferred_set_add_work(pool->all_io_ds, &m->list))
-				pool->process_prepared_discard(m);
+/*
+ * FIXME: DM local hack to defer parent bios's end_io until we
+ * _know_ all chained sub range discard bios have completed.
+ * Will go away once late bio splitting lands upstream!
+ */
+static inline void __bio_inc_remaining(struct bio *bio)
+{
+	bio->bi_flags |= (1 << BIO_CHAIN);
+	smp_mb__before_atomic();
+	atomic_inc(&bio->__bi_remaining);
+}
 
-		} else {
-			inc_all_io_entry(pool, bio);
-			cell_defer_no_holder(tc, cell);
-			cell_defer_no_holder(tc, cell2);
+static void break_up_discard_bio(struct thin_c *tc, dm_block_t begin, dm_block_t end,
+				 struct bio *bio)
+{
+	struct pool *pool = tc->pool;
+
+	int r;
+	bool maybe_shared;
+	struct dm_cell_key data_key;
+	struct dm_bio_prison_cell *data_cell;
+	struct dm_thin_new_mapping *m;
+	dm_block_t virt_begin, virt_end, data_begin;
+
+	while (begin != end) {
+		r = ensure_next_mapping(pool);
+		if (r)
+			/* we did our best */
+			return;
 
+		r = dm_thin_find_mapped_range(tc->td, begin, end, &virt_begin, &virt_end,
+					      &data_begin, &maybe_shared);
+		if (r)
 			/*
-			 * The DM core makes sure that the discard doesn't span
-			 * a block boundary.  So we submit the discard of a
-			 * partial block appropriately.
+			 * Silently fail, letting any mappings we've
+			 * created complete.
 			 */
-			if ((!lookup_result.shared) && pool->pf.discard_passdown)
-				remap_and_issue(tc, bio, lookup_result.block);
-			else
-				bio_endio(bio, 0);
+			break;
+
+		build_key(tc->td, PHYSICAL, data_begin, data_begin + (virt_end - virt_begin), &data_key);
+		if (bio_detain(tc->pool, &data_key, NULL, &data_cell)) {
+			/* contention, we'll give up with this range */
+			begin = virt_end;
+			continue;
 		}
-		break;
 
-	case -ENODATA:
 		/*
-		 * It isn't provisioned, just forget it.
+		 * IO may still be going to the destination block.  We must
+		 * quiesce before we can do the removal.
 		 */
-		cell_defer_no_holder(tc, cell);
-		bio_endio(bio, 0);
-		break;
+		m = get_next_mapping(pool);
+		m->tc = tc;
+		m->maybe_shared = maybe_shared;
+		m->virt_begin = virt_begin;
+		m->virt_end = virt_end;
+		m->data_block = data_begin;
+		m->cell = data_cell;
+		m->bio = bio;
 
-	default:
-		DMERR_LIMIT("%s: dm_thin_find_block() failed: error = %d",
-			    __func__, r);
-		cell_defer_no_holder(tc, cell);
-		bio_io_error(bio);
-		break;
+		/*
+		 * The parent bio must not complete before sub discard bios are
+		 * chained to it (see __blkdev_issue_discard_async's bio_chain)!
+		 *
+		 * This per-mapping bi_remaining increment is paired with
+		 * the implicit decrement that occurs via bio_endio() in
+		 * process_prepared_discard_{passdown,no_passdown}.
+		 */
+		__bio_inc_remaining(bio);
+		if (!dm_deferred_set_add_work(pool->all_io_ds, &m->list))
+			pool->process_prepared_discard(m);
+
+		begin = virt_end;
 	}
 }
 
+static void process_discard_cell_passdown(struct thin_c *tc, struct dm_bio_prison_cell *virt_cell)
+{
+	struct bio *bio = virt_cell->holder;
+	struct dm_thin_endio_hook *h = dm_per_bio_data(bio, sizeof(struct dm_thin_endio_hook));
+
+	/*
+	 * The virt_cell will only get freed once the origin bio completes.
+	 * This means it will remain locked while all the individual
+	 * passdown bios are in flight.
+	 */
+	h->cell = virt_cell;
+	break_up_discard_bio(tc, virt_cell->key.block_begin, virt_cell->key.block_end, bio);
+
+	/*
+	 * We complete the bio now, knowing that the bi_remaining field
+	 * will prevent completion until the sub range discards have
+	 * completed.
+	 */
+	bio_endio(bio, 0);
+}
+
 static void process_discard_bio(struct thin_c *tc, struct bio *bio)
 {
-	struct dm_bio_prison_cell *cell;
-	struct dm_cell_key key;
-	dm_block_t block = get_bio_block(tc, bio);
+	dm_block_t begin, end;
+	struct dm_cell_key virt_key;
+	struct dm_bio_prison_cell *virt_cell;
 
-	build_virtual_key(tc->td, block, &key);
-	if (bio_detain(tc->pool, &key, bio, &cell))
+	get_bio_block_range(tc, bio, &begin, &end);
+	if (begin == end) {
+		/*
+		 * The discard covers less than a block.
+		 */
+		bio_endio(bio, 0);
 		return;
+	}
 
-	process_discard_cell(tc, cell);
+	build_key(tc->td, VIRTUAL, begin, end, &virt_key);
+	if (bio_detain(tc->pool, &virt_key, bio, &virt_cell))
+		/*
+		 * Potential starvation issue: We're relying on the
+		 * fs/application being well behaved, and not trying to
+		 * send IO to a region at the same time as discarding it.
+		 * If they do this persistently then it's possible this
+		 * cell will never be granted.
+		 */
+		return;
+
+	tc->pool->process_discard_cell(tc, virt_cell);
 }
 
 static void break_sharing(struct thin_c *tc, struct bio *bio, dm_block_t block,
@@ -2014,18 +2287,23 @@ static void do_waker(struct work_struct *ws)
 	queue_delayed_work(pool->wq, &pool->waker, COMMIT_PERIOD);
 }
 
+static void notify_of_pool_mode_change_to_oods(struct pool *pool);
+
 /*
  * We're holding onto IO to allow userland time to react.  After the
  * timeout either the pool will have been resized (and thus back in
- * PM_WRITE mode), or we degrade to PM_READ_ONLY and start erroring IO.
+ * PM_WRITE mode), or we degrade to PM_OUT_OF_DATA_SPACE w/ error_if_no_space.
  */
 static void do_no_space_timeout(struct work_struct *ws)
 {
 	struct pool *pool = container_of(to_delayed_work(ws), struct pool,
 					 no_space_timeout);
 
-	if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space)
-		set_pool_mode(pool, PM_READ_ONLY);
+	if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) {
+		pool->pf.error_if_no_space = true;
+		notify_of_pool_mode_change_to_oods(pool);
+		error_retry_list_with_code(pool, -ENOSPC);
+	}
 }
 
 /*----------------------------------------------------------------*/
@@ -2103,6 +2381,32 @@ static void notify_of_pool_mode_change(struct pool *pool, const char *new_mode)
 	       dm_device_name(pool->pool_md), new_mode);
 }
 
+static void notify_of_pool_mode_change_to_oods(struct pool *pool)
+{
+	if (!pool->pf.error_if_no_space)
+		notify_of_pool_mode_change(pool, "out-of-data-space (queue IO)");
+	else
+		notify_of_pool_mode_change(pool, "out-of-data-space (error IO)");
+}
+
+static bool passdown_enabled(struct pool_c *pt)
+{
+	return pt->adjusted_pf.discard_passdown;
+}
+
+static void set_discard_callbacks(struct pool *pool)
+{
+	struct pool_c *pt = pool->ti->private;
+
+	if (passdown_enabled(pt)) {
+		pool->process_discard_cell = process_discard_cell_passdown;
+		pool->process_prepared_discard = process_prepared_discard_passdown;
+	} else {
+		pool->process_discard_cell = process_discard_cell_no_passdown;
+		pool->process_prepared_discard = process_prepared_discard_no_passdown;
+	}
+}
+
 static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 {
 	struct pool_c *pt = pool->ti->private;
@@ -2154,7 +2458,7 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 		pool->process_cell = process_cell_read_only;
 		pool->process_discard_cell = process_cell_success;
 		pool->process_prepared_mapping = process_prepared_mapping_fail;
-		pool->process_prepared_discard = process_prepared_discard_passdown;
+		pool->process_prepared_discard = process_prepared_discard_success;
 
 		error_retry_list(pool);
 		break;
@@ -2169,13 +2473,12 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 		 * frequently seeing this mode.
 		 */
 		if (old_mode != new_mode)
-			notify_of_pool_mode_change(pool, "out-of-data-space");
+			notify_of_pool_mode_change_to_oods(pool);
 		pool->process_bio = process_bio_read_only;
 		pool->process_discard = process_discard_bio;
 		pool->process_cell = process_cell_read_only;
-		pool->process_discard_cell = process_discard_cell;
 		pool->process_prepared_mapping = process_prepared_mapping;
-		pool->process_prepared_discard = process_prepared_discard;
+		set_discard_callbacks(pool);
 
 		if (!pool->pf.error_if_no_space && no_space_timeout)
 			queue_delayed_work(pool->wq, &pool->no_space_timeout, no_space_timeout);
@@ -2188,9 +2491,8 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode)
 		pool->process_bio = process_bio;
 		pool->process_discard = process_discard_bio;
 		pool->process_cell = process_cell;
-		pool->process_discard_cell = process_discard_cell;
 		pool->process_prepared_mapping = process_prepared_mapping;
-		pool->process_prepared_discard = process_prepared_discard;
+		set_discard_callbacks(pool);
 		break;
 	}
 
@@ -2279,6 +2581,7 @@ static void thin_hook_bio(struct thin_c *tc, struct bio *bio)
 	h->shared_read_entry = NULL;
 	h->all_io_entry = NULL;
 	h->overwrite_mapping = NULL;
+	h->cell = NULL;
 }
 
 /*
@@ -2426,7 +2729,6 @@ static void disable_passdown_if_not_supported(struct pool_c *pt)
 	struct pool *pool = pt->pool;
 	struct block_device *data_bdev = pt->data_dev->bdev;
 	struct queue_limits *data_limits = &bdev_get_queue(data_bdev)->limits;
-	sector_t block_size = pool->sectors_per_block << SECTOR_SHIFT;
 	const char *reason = NULL;
 	char buf[BDEVNAME_SIZE];
 
@@ -2439,12 +2741,6 @@ static void disable_passdown_if_not_supported(struct pool_c *pt)
 	else if (data_limits->max_discard_sectors < pool->sectors_per_block)
 		reason = "max discard sectors smaller than a block";
 
-	else if (data_limits->discard_granularity > block_size)
-		reason = "discard granularity larger than a block";
-
-	else if (!is_factor(block_size, data_limits->discard_granularity))
-		reason = "discard granularity not a factor of block size";
-
 	if (reason) {
 		DMWARN("Data device (%s) %s: Disabling discard passdown.", bdevname(data_bdev, buf), reason);
 		pt->adjusted_pf.discard_passdown = false;
@@ -3389,7 +3685,7 @@ static int pool_message(struct dm_target *ti, unsigned argc, char **argv)
 	if (get_pool_mode(pool) >= PM_READ_ONLY) {
 		DMERR("%s: unable to service pool target messages in READ_ONLY or FAIL mode",
 		      dm_device_name(pool->pool_md));
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 
 	if (!strcasecmp(argv[0], "create_thin"))
@@ -3447,6 +3743,7 @@ static void emit_flags(struct pool_features *pf, char *result,
  * Status line is:
  *    <transaction id> <used metadata sectors>/<total metadata sectors>
  *    <used data sectors>/<total data sectors> <held metadata root>
+ *    <pool mode> <discard config> <no space config> <needs_check>
  */
 static void pool_status(struct dm_target *ti, status_type_t type,
 			unsigned status_flags, char *result, unsigned maxlen)
@@ -3548,6 +3845,11 @@ static void pool_status(struct dm_target *ti, status_type_t type,
 		else
 			DMEMIT("queue_if_no_space ");
 
+		if (dm_pool_metadata_needs_check(pool->pmd))
+			DMEMIT("needs_check ");
+		else
+			DMEMIT("- ");
+
 		break;
 
 	case STATUSTYPE_TABLE:
@@ -3587,24 +3889,6 @@ static int pool_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
 	return min(max_size, q->merge_bvec_fn(q, bvm, biovec));
 }
 
-static void set_discard_limits(struct pool_c *pt, struct queue_limits *limits)
-{
-	struct pool *pool = pt->pool;
-	struct queue_limits *data_limits;
-
-	limits->max_discard_sectors = pool->sectors_per_block;
-
-	/*
-	 * discard_granularity is just a hint, and not enforced.
-	 */
-	if (pt->adjusted_pf.discard_passdown) {
-		data_limits = &bdev_get_queue(pt->data_dev->bdev)->limits;
-		limits->discard_granularity = max(data_limits->discard_granularity,
-						  pool->sectors_per_block << SECTOR_SHIFT);
-	} else
-		limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
-}
-
 static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	struct pool_c *pt = ti->private;
@@ -3659,14 +3943,17 @@ static void pool_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 	disable_passdown_if_not_supported(pt);
 
-	set_discard_limits(pt, limits);
+	/*
+	 * The pool uses the same discard limits as the underlying data
+	 * device.  DM core has already set this up.
+	 */
 }
 
 static struct target_type pool_target = {
 	.name = "thin-pool",
 	.features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE |
 		    DM_TARGET_IMMUTABLE,
-	.version = {1, 14, 0},
+	.version = {1, 16, 0},
 	.module = THIS_MODULE,
 	.ctr = pool_ctr,
 	.dtr = pool_dtr,
@@ -3825,8 +4112,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	if (tc->pool->pf.discard_enabled) {
 		ti->discards_supported = true;
 		ti->num_discard_bios = 1;
-		/* Discard bios must be split on a block boundary */
-		ti->split_discard_bios = true;
+		ti->split_discard_bios = false;
 	}
 
 	mutex_unlock(&dm_thin_pool_table.mutex);
@@ -3913,6 +4199,9 @@ static int thin_endio(struct dm_target *ti, struct bio *bio, int err)
 		}
 	}
 
+	if (h->cell)
+		cell_defer_no_holder(h->tc, h->cell);
+
 	return 0;
 }
 
@@ -4040,9 +4329,18 @@ static int thin_iterate_devices(struct dm_target *ti,
 	return 0;
 }
 
+static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
+{
+	struct thin_c *tc = ti->private;
+	struct pool *pool = tc->pool;
+
+	limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
+	limits->max_discard_sectors = 2048 * 1024 * 16; /* 16G */
+}
+
 static struct target_type thin_target = {
 	.name = "thin",
-	.version = {1, 14, 0},
+	.version = {1, 16, 0},
 	.module	= THIS_MODULE,
 	.ctr = thin_ctr,
 	.dtr = thin_dtr,
@@ -4054,6 +4352,7 @@ static struct target_type thin_target = {
 	.status = thin_status,
 	.merge = thin_merge,
 	.iterate_devices = thin_iterate_devices,
+	.io_hints = thin_io_hints,
 };
 
 /*----------------------------------------------------------------*/