1 files changed, 100 insertions, 43 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 44a2fa6814c..32b958dbc49 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -54,6 +54,8 @@ static void do_deferred_remove(struct work_struct *w);
 
 static DECLARE_WORK(deferred_remove_work, do_deferred_remove);
 
+static struct workqueue_struct *deferred_remove_workqueue;
+
 /*
  * For bio-based dm.
  * One of these is allocated per bio.
@@ -94,13 +96,6 @@ struct dm_rq_clone_bio_info {
 	struct bio clone;
 };
 
-union map_info *dm_get_mapinfo(struct bio *bio)
-{
-	if (bio && bio->bi_private)
-		return &((struct dm_target_io *)bio->bi_private)->info;
-	return NULL;
-}
-
 union map_info *dm_get_rq_mapinfo(struct request *rq)
 {
 	if (rq && rq->end_io_data)
@@ -200,8 +195,8 @@ struct mapped_device {
 	/* forced geometry settings */
 	struct hd_geometry geometry;
 
-	/* sysfs handle */
-	struct kobject kobj;
+	/* kobject and completion */
+	struct dm_kobject_holder kobj_holder;
 
 	/* zero-length flush that will be cloned and submitted to targets */
 	struct bio flush_bio;
@@ -283,16 +278,24 @@ static int __init local_init(void)
 	if (r)
 		goto out_free_rq_tio_cache;
 
+	deferred_remove_workqueue = alloc_workqueue("kdmremove", WQ_UNBOUND, 1);
+	if (!deferred_remove_workqueue) {
+		r = -ENOMEM;
+		goto out_uevent_exit;
+	}
+
 	_major = major;
 	r = register_blkdev(_major, _name);
 	if (r < 0)
-		goto out_uevent_exit;
+		goto out_free_workqueue;
 
 	if (!_major)
 		_major = r;
 
 	return 0;
 
+out_free_workqueue:
+	destroy_workqueue(deferred_remove_workqueue);
 out_uevent_exit:
 	dm_uevent_exit();
 out_free_rq_tio_cache:
@@ -306,6 +309,7 @@ out_free_io_cache:
 static void local_exit(void)
 {
 	flush_scheduled_work();
+	destroy_workqueue(deferred_remove_workqueue);
 
 	kmem_cache_destroy(_rq_tio_cache);
 	kmem_cache_destroy(_io_cache);
@@ -414,7 +418,7 @@ static void dm_blk_close(struct gendisk *disk, fmode_t mode)
 
 	if (atomic_dec_and_test(&md->open_count) &&
 	    (test_bit(DMF_DEFERRED_REMOVE, &md->flags)))
-		schedule_work(&deferred_remove_work);
+		queue_work(deferred_remove_workqueue, &deferred_remove_work);
 
 	dm_put(md);
 
@@ -475,6 +479,11 @@ sector_t dm_get_size(struct mapped_device *md)
 	return get_capacity(md->disk);
 }
 
+struct request_queue *dm_get_md_queue(struct mapped_device *md)
+{
+	return md->queue;
+}
+
 struct dm_stats *dm_get_stats(struct mapped_device *md)
 {
 	return &md->stats;
@@ -757,10 +766,18 @@ static void dec_pending(struct dm_io *io, int error)
 	}
 }
 
+static void disable_write_same(struct mapped_device *md)
+{
+	struct queue_limits *limits = dm_get_queue_limits(md);
+
+	/* device doesn't really support WRITE SAME, disable it */
+	limits->max_write_same_sectors = 0;
+}
+
 static void clone_endio(struct bio *bio, int error)
 {
 	int r = 0;
-	struct dm_target_io *tio = bio->bi_private;
+	struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
 	struct dm_io *io = tio->io;
 	struct mapped_device *md = tio->io->md;
 	dm_endio_fn endio = tio->ti->type->end_io;
@@ -785,6 +802,10 @@ static void clone_endio(struct bio *bio, int error)
 		}
 	}
 
+	if (unlikely(r == -EREMOTEIO && (bio->bi_rw & REQ_WRITE_SAME) &&
+		     !bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors))
+		disable_write_same(md);
+
 	free_tio(md, tio);
 	dec_pending(io, error);
 }
@@ -794,7 +815,8 @@ static void clone_endio(struct bio *bio, int error)
  */
 static void end_clone_bio(struct bio *clone, int error)
 {
-	struct dm_rq_clone_bio_info *info = clone->bi_private;
+	struct dm_rq_clone_bio_info *info =
+		container_of(clone, struct dm_rq_clone_bio_info, clone);
 	struct dm_rq_target_io *tio = info->tio;
 	struct bio *bio = info->orig;
 	unsigned int nr_bytes = info->orig->bi_iter.bi_size;
@@ -978,6 +1000,10 @@ static void dm_done(struct request *clone, int error, bool mapped)
 			r = rq_end_io(tio->ti, clone, error, &tio->info);
 	}
 
+	if (unlikely(r == -EREMOTEIO && (clone->cmd_flags & REQ_WRITE_SAME) &&
+		     !clone->q->limits.max_write_same_sectors))
+		disable_write_same(tio->md);
+
 	if (r <= 0)
 		/* The target wants to complete the I/O */
 		dm_end_request(clone, r);
@@ -1111,6 +1137,46 @@ int dm_set_target_max_io_len(struct dm_target *ti, sector_t len)
 }
 EXPORT_SYMBOL_GPL(dm_set_target_max_io_len);
 
+/*
+ * A target may call dm_accept_partial_bio only from the map routine.  It is
+ * allowed for all bio types except REQ_FLUSH.
+ *
+ * dm_accept_partial_bio informs the dm that the target only wants to process
+ * additional n_sectors sectors of the bio and the rest of the data should be
+ * sent in a next bio.
+ *
+ * A diagram that explains the arithmetics:
+ * +--------------------+---------------+-------+
+ * |         1          |       2       |   3   |
+ * +--------------------+---------------+-------+
+ *
+ * <-------------- *tio->len_ptr --------------->
+ *                      <------- bi_size ------->
+ *                      <-- n_sectors -->
+ *
+ * Region 1 was already iterated over with bio_advance or similar function.
+ *	(it may be empty if the target doesn't use bio_advance)
+ * Region 2 is the remaining bio size that the target wants to process.
+ *	(it may be empty if region 1 is non-empty, although there is no reason
+ *	 to make it empty)
+ * The target requires that region 3 is to be sent in the next bio.
+ *
+ * If the target wants to receive multiple copies of the bio (via num_*bios, etc),
+ * the partially processed part (the sum of regions 1+2) must be the same for all
+ * copies of the bio.
+ */
+void dm_accept_partial_bio(struct bio *bio, unsigned n_sectors)
+{
+	struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
+	unsigned bi_size = bio->bi_iter.bi_size >> SECTOR_SHIFT;
+	BUG_ON(bio->bi_rw & REQ_FLUSH);
+	BUG_ON(bi_size > *tio->len_ptr);
+	BUG_ON(n_sectors > bi_size);
+	*tio->len_ptr -= bi_size - n_sectors;
+	bio->bi_iter.bi_size = n_sectors << SECTOR_SHIFT;
+}
+EXPORT_SYMBOL_GPL(dm_accept_partial_bio);
+
 static void __map_bio(struct dm_target_io *tio)
 {
 	int r;
@@ -1120,7 +1186,6 @@ static void __map_bio(struct dm_target_io *tio)
 	struct dm_target *ti = tio->ti;
 
 	clone->bi_end_io = clone_endio;
-	clone->bi_private = tio;
 
 	/*
 	 * Map the clone.  If r == 0 we don't need to do
@@ -1154,10 +1219,10 @@ struct clone_info {
 	struct bio *bio;
 	struct dm_io *io;
 	sector_t sector;
-	sector_t sector_count;
+	unsigned sector_count;
 };
 
-static void bio_setup_sector(struct bio *bio, sector_t sector, sector_t len)
+static void bio_setup_sector(struct bio *bio, sector_t sector, unsigned len)
 {
 	bio->bi_iter.bi_sector = sector;
 	bio->bi_iter.bi_size = to_bytes(len);
@@ -1195,7 +1260,6 @@ static struct dm_target_io *alloc_tio(struct clone_info *ci,
 
 	tio->io = ci->io;
 	tio->ti = ti;
-	memset(&tio->info, 0, sizeof(tio->info));
 	tio->target_bio_nr = target_bio_nr;
 
 	return tio;
@@ -1203,11 +1267,13 @@ static struct dm_target_io *alloc_tio(struct clone_info *ci,
 
 static void __clone_and_map_simple_bio(struct clone_info *ci,
 				       struct dm_target *ti,
-				       unsigned target_bio_nr, sector_t len)
+				       unsigned target_bio_nr, unsigned *len)
 {
 	struct dm_target_io *tio = alloc_tio(ci, ti, ci->bio->bi_max_vecs, target_bio_nr);
 	struct bio *clone = &tio->clone;
 
+	tio->len_ptr = len;
+
 	/*
 	 * Discard requests require the bio's inline iovecs be initialized.
 	 * ci->bio->bi_max_vecs is BIO_INLINE_VECS anyway, for both flush
@@ -1215,13 +1281,13 @@ static void __clone_and_map_simple_bio(struct clone_info *ci,
 	 */
 	 __bio_clone_fast(clone, ci->bio);
 	if (len)
-		bio_setup_sector(clone, ci->sector, len);
+		bio_setup_sector(clone, ci->sector, *len);
 
 	__map_bio(tio);
 }
 
 static void __send_duplicate_bios(struct clone_info *ci, struct dm_target *ti,
-				  unsigned num_bios, sector_t len)
+				  unsigned num_bios, unsigned *len)
 {
 	unsigned target_bio_nr;
 
@@ -1236,13 +1302,13 @@ static int __send_empty_flush(struct clone_info *ci)
 
 	BUG_ON(bio_has_data(ci->bio));
 	while ((ti = dm_table_get_target(ci->map, target_nr++)))
-		__send_duplicate_bios(ci, ti, ti->num_flush_bios, 0);
+		__send_duplicate_bios(ci, ti, ti->num_flush_bios, NULL);
 
 	return 0;
 }
 
 static void __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti,
-				     sector_t sector, unsigned len)
+				     sector_t sector, unsigned *len)
 {
 	struct bio *bio = ci->bio;
 	struct dm_target_io *tio;
@@ -1257,7 +1323,8 @@ static void __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti
 
 	for (target_bio_nr = 0; target_bio_nr < num_target_bios; target_bio_nr++) {
 		tio = alloc_tio(ci, ti, 0, target_bio_nr);
-		clone_bio(tio, bio, sector, len);
+		tio->len_ptr = len;
+		clone_bio(tio, bio, sector, *len);
 		__map_bio(tio);
 	}
 }
@@ -1286,7 +1353,7 @@ static int __send_changing_extent_only(struct clone_info *ci,
 				       is_split_required_fn is_split_required)
 {
 	struct dm_target *ti;
-	sector_t len;
+	unsigned len;
 	unsigned num_bios;
 
 	do {
@@ -1305,11 +1372,11 @@ static int __send_changing_extent_only(struct clone_info *ci,
 			return -EOPNOTSUPP;
 
 		if (is_split_required && !is_split_required(ti))
-			len = min(ci->sector_count, max_io_len_target_boundary(ci->sector, ti));
+			len = min((sector_t)ci->sector_count, max_io_len_target_boundary(ci->sector, ti));
 		else
-			len = min(ci->sector_count, max_io_len(ci->sector, ti));
+			len = min((sector_t)ci->sector_count, max_io_len(ci->sector, ti));
 
-		__send_duplicate_bios(ci, ti, num_bios, len);
+		__send_duplicate_bios(ci, ti, num_bios, &len);
 
 		ci->sector += len;
 	} while (ci->sector_count -= len);
@@ -1348,7 +1415,7 @@ static int __split_and_process_non_flush(struct clone_info *ci)
 
 	len = min_t(sector_t, max_io_len(ci->sector, ti), ci->sector_count);
 
-	__clone_and_map_data_bio(ci, ti, ci->sector, len);
+	__clone_and_map_data_bio(ci, ti, ci->sector, &len);
 
 	ci->sector += len;
 	ci->sector_count -= len;
@@ -1442,7 +1509,6 @@ static int dm_merge_bvec(struct request_queue *q,
 	 * just one page.
 	 */
 	else if (queue_max_hw_sectors(q) <= PAGE_SIZE >> 9)
-
 		max_size = 0;
 
 out:
@@ -1530,7 +1596,6 @@ static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
 	info->orig = bio_orig;
 	info->tio = tio;
 	bio->bi_end_io = end_clone_bio;
-	bio->bi_private = info;
 
 	return 0;
 }
@@ -1548,7 +1613,6 @@ static int setup_clone(struct request *clone, struct request *rq,
 	clone->cmd = rq->cmd;
 	clone->cmd_len = rq->cmd_len;
 	clone->sense = rq->sense;
-	clone->buffer = rq->buffer;
 	clone->end_io = end_clone_request;
 	clone->end_io_data = tio;
 
@@ -1908,6 +1972,7 @@ static struct mapped_device *alloc_dev(int minor)
 	init_waitqueue_head(&md->wait);
 	INIT_WORK(&md->work, dm_wq_work);
 	init_waitqueue_head(&md->eventq);
+	init_completion(&md->kobj_holder.completion);
 
 	md->disk->major = _major;
 	md->disk->first_minor = minor;
@@ -2171,7 +2236,7 @@ static struct dm_table *__unbind(struct mapped_device *md)
 		return NULL;
 
 	dm_table_event_callback(map, NULL, NULL);
-	rcu_assign_pointer(md->map, NULL);
+	RCU_INIT_POINTER(md->map, NULL);
 	dm_sync_table(md);
 
 	return map;
@@ -2450,7 +2515,7 @@ static void dm_wq_work(struct work_struct *work)
 static void dm_queue_flush(struct mapped_device *md)
 {
 	clear_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	queue_work(md->wq, &md->work);
 }
 
@@ -2769,20 +2834,14 @@ struct gendisk *dm_disk(struct mapped_device *md)
 
 struct kobject *dm_kobject(struct mapped_device *md)
 {
-	return &md->kobj;
+	return &md->kobj_holder.kobj;
 }
 
-/*
- * struct mapped_device should not be exported outside of dm.c
- * so use this check to verify that kobj is part of md structure
- */
 struct mapped_device *dm_get_from_kobject(struct kobject *kobj)
 {
 	struct mapped_device *md;
 
-	md = container_of(kobj, struct mapped_device, kobj);
-	if (&md->kobj != kobj)
-		return NULL;
+	md = container_of(kobj, struct mapped_device, kobj_holder.kobj);
 
 	if (test_bit(DMF_FREEING, &md->flags) ||
 	    dm_deleting_md(md))
@@ -2878,8 +2937,6 @@ static const struct block_device_operations dm_blk_dops = {
 	.owner = THIS_MODULE
 };
 
-EXPORT_SYMBOL(dm_get_mapinfo);
-
 /*
  * module hooks
  */