1 files changed, 74 insertions, 71 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 4e09b6ff5b4..66ceaff6455 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -86,12 +86,17 @@ struct dm_rq_target_io {
 };
 
 /*
- * For request-based dm.
- * One of these is allocated per bio.
+ * For request-based dm - the bio clones we allocate are embedded in these
+ * structs.
+ *
+ * We allocate these with bio_alloc_bioset, using the front_pad parameter when
+ * the bioset is created - this means the bio has to come at the end of the
+ * struct.
  */
 struct dm_rq_clone_bio_info {
 	struct bio *orig;
 	struct dm_rq_target_io *tio;
+	struct bio clone;
 };
 
 union map_info *dm_get_mapinfo(struct bio *bio)
@@ -211,6 +216,11 @@ struct dm_md_mempools {
 static struct kmem_cache *_io_cache;
 static struct kmem_cache *_tio_cache;
 static struct kmem_cache *_rq_tio_cache;
+
+/*
+ * Unused now, and needs to be deleted. But since io_pool is overloaded and it's
+ * still used for _io_cache, I'm leaving this for a later cleanup
+ */
 static struct kmem_cache *_rq_bio_info_cache;
 
 static int __init local_init(void)
@@ -467,16 +477,6 @@ static void free_rq_tio(struct dm_rq_target_io *tio)
 	mempool_free(tio, tio->md->tio_pool);
 }
 
-static struct dm_rq_clone_bio_info *alloc_bio_info(struct mapped_device *md)
-{
-	return mempool_alloc(md->io_pool, GFP_ATOMIC);
-}
-
-static void free_bio_info(struct dm_rq_clone_bio_info *info)
-{
-	mempool_free(info, info->tio->md->io_pool);
-}
-
 static int md_in_flight(struct mapped_device *md)
 {
 	return atomic_read(&md->pending[READ]) +
@@ -681,11 +681,6 @@ static void clone_endio(struct bio *bio, int error)
 		}
 	}
 
-	/*
-	 * Store md for cleanup instead of tio which is about to get freed.
-	 */
-	bio->bi_private = md->bs;
-
 	free_tio(md, tio);
 	bio_put(bio);
 	dec_pending(io, error);
@@ -865,10 +860,14 @@ static void dm_done(struct request *clone, int error, bool mapped)
 {
 	int r = error;
 	struct dm_rq_target_io *tio = clone->end_io_data;
-	dm_request_endio_fn rq_end_io = tio->ti->type->rq_end_io;
+	dm_request_endio_fn rq_end_io = NULL;
 
-	if (mapped && rq_end_io)
-		r = rq_end_io(tio->ti, clone, error, &tio->info);
+	if (tio->ti) {
+		rq_end_io = tio->ti->type->rq_end_io;
+
+		if (mapped && rq_end_io)
+			r = rq_end_io(tio->ti, clone, error, &tio->info);
+	}
 
 	if (r <= 0)
 		/* The target wants to complete the I/O */
@@ -1032,11 +1031,6 @@ static void __map_bio(struct dm_target *ti, struct bio *clone,
 		/* error the io and bail out, or requeue it if needed */
 		md = tio->io->md;
 		dec_pending(tio->io, r);
-		/*
-		 * Store bio_set for cleanup.
-		 */
-		clone->bi_end_io = NULL;
-		clone->bi_private = md->bs;
 		bio_put(clone);
 		free_tio(md, tio);
 	} else if (r) {
@@ -1055,13 +1049,6 @@ struct clone_info {
 	unsigned short idx;
 };
 
-static void dm_bio_destructor(struct bio *bio)
-{
-	struct bio_set *bs = bio->bi_private;
-
-	bio_free(bio, bs);
-}
-
 /*
  * Creates a little bio that just does part of a bvec.
  */
@@ -1073,7 +1060,6 @@ static struct bio *split_bvec(struct bio *bio, sector_t sector,
 	struct bio_vec *bv = bio->bi_io_vec + idx;
 
 	clone = bio_alloc_bioset(GFP_NOIO, 1, bs);
-	clone->bi_destructor = dm_bio_destructor;
 	*clone->bi_io_vec = *bv;
 
 	clone->bi_sector = sector;
@@ -1086,7 +1072,7 @@ static struct bio *split_bvec(struct bio *bio, sector_t sector,
 	clone->bi_flags |= 1 << BIO_CLONED;
 
 	if (bio_integrity(bio)) {
-		bio_integrity_clone(clone, bio, GFP_NOIO, bs);
+		bio_integrity_clone(clone, bio, GFP_NOIO);
 		bio_integrity_trim(clone,
 				   bio_sector_offset(bio, idx, offset), len);
 	}
@@ -1105,7 +1091,6 @@ static struct bio *clone_bio(struct bio *bio, sector_t sector,
 
 	clone = bio_alloc_bioset(GFP_NOIO, bio->bi_max_vecs, bs);
 	__bio_clone(clone, bio);
-	clone->bi_destructor = dm_bio_destructor;
 	clone->bi_sector = sector;
 	clone->bi_idx = idx;
 	clone->bi_vcnt = idx + bv_count;
@@ -1113,7 +1098,7 @@ static struct bio *clone_bio(struct bio *bio, sector_t sector,
 	clone->bi_flags &= ~(1 << BIO_SEG_VALID);
 
 	if (bio_integrity(bio)) {
-		bio_integrity_clone(clone, bio, GFP_NOIO, bs);
+		bio_integrity_clone(clone, bio, GFP_NOIO);
 
 		if (idx != bio->bi_idx || clone->bi_size < bio->bi_size)
 			bio_integrity_trim(clone,
@@ -1148,9 +1133,8 @@ static void __issue_target_request(struct clone_info *ci, struct dm_target *ti,
 	 * ci->bio->bi_max_vecs is BIO_INLINE_VECS anyway, for both flush
 	 * and discard, so no need for concern about wasted bvec allocations.
 	 */
-	clone = bio_alloc_bioset(GFP_NOIO, ci->bio->bi_max_vecs, ci->md->bs);
-	__bio_clone(clone, ci->bio);
-	clone->bi_destructor = dm_bio_destructor;
+	clone = bio_clone_bioset(ci->bio, GFP_NOIO, ci->md->bs);
+
 	if (len) {
 		clone->bi_sector = ci->sector;
 		clone->bi_size = to_bytes(len);
@@ -1480,30 +1464,17 @@ void dm_dispatch_request(struct request *rq)
 }
 EXPORT_SYMBOL_GPL(dm_dispatch_request);
 
-static void dm_rq_bio_destructor(struct bio *bio)
-{
-	struct dm_rq_clone_bio_info *info = bio->bi_private;
-	struct mapped_device *md = info->tio->md;
-
-	free_bio_info(info);
-	bio_free(bio, md->bs);
-}
-
 static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
 				 void *data)
 {
 	struct dm_rq_target_io *tio = data;
-	struct mapped_device *md = tio->md;
-	struct dm_rq_clone_bio_info *info = alloc_bio_info(md);
-
-	if (!info)
-		return -ENOMEM;
+	struct dm_rq_clone_bio_info *info =
+		container_of(bio, struct dm_rq_clone_bio_info, clone);
 
 	info->orig = bio_orig;
 	info->tio = tio;
 	bio->bi_end_io = end_clone_bio;
 	bio->bi_private = info;
-	bio->bi_destructor = dm_rq_bio_destructor;
 
 	return 0;
 }
@@ -1588,15 +1559,6 @@ static int map_request(struct dm_target *ti, struct request *clone,
 	int r, requeued = 0;
 	struct dm_rq_target_io *tio = clone->end_io_data;
 
-	/*
-	 * Hold the md reference here for the in-flight I/O.
-	 * We can't rely on the reference count by device opener,
-	 * because the device may be closed during the request completion
-	 * when all bios are completed.
-	 * See the comment in rq_completed() too.
-	 */
-	dm_get(md);
-
 	tio->ti = ti;
 	r = ti->type->map_rq(ti, clone, &tio->info);
 	switch (r) {
@@ -1628,6 +1590,26 @@ static int map_request(struct dm_target *ti, struct request *clone,
 	return requeued;
 }
 
+static struct request *dm_start_request(struct mapped_device *md, struct request *orig)
+{
+	struct request *clone;
+
+	blk_start_request(orig);
+	clone = orig->special;
+	atomic_inc(&md->pending[rq_data_dir(clone)]);
+
+	/*
+	 * Hold the md reference here for the in-flight I/O.
+	 * We can't rely on the reference count by device opener,
+	 * because the device may be closed during the request completion
+	 * when all bios are completed.
+	 * See the comment in rq_completed() too.
+	 */
+	dm_get(md);
+
+	return clone;
+}
+
 /*
  * q->request_fn for request-based dm.
  * Called with the queue lock held.
@@ -1657,14 +1639,21 @@ static void dm_request_fn(struct request_queue *q)
 			pos = blk_rq_pos(rq);
 
 		ti = dm_table_find_target(map, pos);
-		BUG_ON(!dm_target_is_valid(ti));
+		if (!dm_target_is_valid(ti)) {
+			/*
+			 * Must perform setup, that dm_done() requires,
+			 * before calling dm_kill_unmapped_request
+			 */
+			DMERR_LIMIT("request attempted access beyond the end of device");
+			clone = dm_start_request(md, rq);
+			dm_kill_unmapped_request(clone, -EIO);
+			continue;
+		}
 
 		if (ti->type->busy && ti->type->busy(ti))
 			goto delay_and_out;
 
-		blk_start_request(rq);
-		clone = rq->special;
-		atomic_inc(&md->pending[rq_data_dir(clone)]);
+		clone = dm_start_request(md, rq);
 
 		spin_unlock(q->queue_lock);
 		if (map_request(ti, clone, md))
@@ -1684,8 +1673,6 @@ delay_and_out:
 	blk_delay_queue(q, HZ / 10);
 out:
 	dm_table_put(map);
-
-	return;
 }
 
 int dm_underlying_device_busy(struct request_queue *q)
@@ -2409,7 +2396,7 @@ static void dm_queue_flush(struct mapped_device *md)
  */
 struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table)
 {
-	struct dm_table *map = ERR_PTR(-EINVAL);
+	struct dm_table *live_map, *map = ERR_PTR(-EINVAL);
 	struct queue_limits limits;
 	int r;
 
@@ -2419,6 +2406,19 @@ struct dm_table *dm_swap_table(struct mapped_device *md, struct dm_table *table)
 	if (!dm_suspended_md(md))
 		goto out;
 
+	/*
+	 * If the new table has no data devices, retain the existing limits.
+	 * This helps multipath with queue_if_no_path if all paths disappear,
+	 * then new I/O is queued based on these limits, and then some paths
+	 * reappear.
+	 */
+	if (dm_table_has_no_data_devices(table)) {
+		live_map = dm_get_live_table(md);
+		if (live_map)
+			limits = md->queue->limits;
+		dm_table_put(live_map);
+	}
+
 	r = dm_calculate_queue_limits(table, &limits);
 	if (r) {
 		map = ERR_PTR(r);
@@ -2738,7 +2738,10 @@ struct dm_md_mempools *dm_alloc_md_mempools(unsigned type, unsigned integrity)
 	if (!pools->tio_pool)
 		goto free_io_pool_and_out;
 
-	pools->bs = bioset_create(pool_size, 0);
+	pools->bs = (type == DM_TYPE_BIO_BASED) ?
+		bioset_create(pool_size, 0) :
+		bioset_create(pool_size,
+			      offsetof(struct dm_rq_clone_bio_info, clone));
 	if (!pools->bs)
 		goto free_tio_pool_and_out;