1 files changed, 51 insertions, 83 deletions

diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 530c0fe14229..a7724ba45b43 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -263,7 +263,6 @@ out_uevent_exit:
 
 static void local_exit(void)
 {
-	flush_scheduled_work();
 	destroy_workqueue(deferred_remove_workqueue);
 
 	unregister_blkdev(_major, _name);
@@ -676,19 +675,20 @@ static void start_io_acct(struct dm_io *io)
 				    false, 0, &io->stats_aux);
 }
 
-static void end_io_acct(struct dm_io *io)
+static void end_io_acct(struct mapped_device *md, struct bio *bio,
+			unsigned long start_time, struct dm_stats_aux *stats_aux)
 {
-	struct mapped_device *md = io->md;
-	struct bio *bio = io->orig_bio;
-	unsigned long duration = jiffies - io->start_time;
-
-	generic_end_io_acct(md->queue, bio_op(bio), &dm_disk(md)->part0,
-			    io->start_time);
+	unsigned long duration = jiffies - start_time;
 
 	if (unlikely(dm_stats_used(&md->stats)))
 		dm_stats_account_io(&md->stats, bio_data_dir(bio),
 				    bio->bi_iter.bi_sector, bio_sectors(bio),
-				    true, duration, &io->stats_aux);
+				    true, duration, stats_aux);
+
+	smp_wmb();
+
+	generic_end_io_acct(md->queue, bio_op(bio), &dm_disk(md)->part0,
+			    start_time);
 
 	/* nudge anyone waiting on suspend queue */
 	if (unlikely(wq_has_sleeper(&md->wait)))
@@ -909,6 +909,8 @@ static void dec_pending(struct dm_io *io, blk_status_t error)
 	blk_status_t io_error;
 	struct bio *bio;
 	struct mapped_device *md = io->md;
+	unsigned long start_time = 0;
+	struct dm_stats_aux stats_aux;
 
 	/* Push-back supersedes any I/O errors */
 	if (unlikely(error)) {
@@ -935,8 +937,10 @@ static void dec_pending(struct dm_io *io, blk_status_t error)
 
 		io_error = io->status;
 		bio = io->orig_bio;
-		end_io_acct(io);
+		start_time = io->start_time;
+		stats_aux = io->stats_aux;
 		free_io(md, io);
+		end_io_acct(md, bio, start_time, &stats_aux);
 
 		if (io_error == BLK_STS_DM_REQUEUE)
 			return;
@@ -995,7 +999,7 @@ static void clone_endio(struct bio *bio)
 	struct mapped_device *md = tio->io->md;
 	dm_endio_fn endio = tio->ti->type->end_io;
 
-	if (unlikely(error == BLK_STS_TARGET) && md->type != DM_TYPE_NVME_BIO_BASED) {
+	if (unlikely(error == BLK_STS_TARGET)) {
 		if (bio_op(bio) == REQ_OP_DISCARD &&
 		    !bio->bi_disk->queue->limits.max_discard_sectors)
 			disable_discard(md);
@@ -1320,7 +1324,6 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
 	sector = clone->bi_iter.bi_sector;
 
 	if (unlikely(swap_bios_limit(ti, clone))) {
-		struct mapped_device *md = io->md;
 		int latch = get_swap_bios();
 		if (unlikely(latch != md->swap_bios))
 			__set_swap_bios_limit(md, latch);
@@ -1335,24 +1338,17 @@ static blk_qc_t __map_bio(struct dm_target_io *tio)
 		/* the bio has been remapped so dispatch it */
 		trace_block_bio_remap(clone->bi_disk->queue, clone,
 				      bio_dev(io->orig_bio), sector);
-		if (md->type == DM_TYPE_NVME_BIO_BASED)
-			ret = direct_make_request(clone);
-		else
-			ret = generic_make_request(clone);
+		ret = generic_make_request(clone);
 		break;
 	case DM_MAPIO_KILL:
-		if (unlikely(swap_bios_limit(ti, clone))) {
-			struct mapped_device *md = io->md;
+		if (unlikely(swap_bios_limit(ti, clone)))
 			up(&md->swap_bios_semaphore);
-		}
 		free_tio(tio);
 		dec_pending(io, BLK_STS_IOERR);
 		break;
 	case DM_MAPIO_REQUEUE:
-		if (unlikely(swap_bios_limit(ti, clone))) {
-			struct mapped_device *md = io->md;
+		if (unlikely(swap_bios_limit(ti, clone)))
 			up(&md->swap_bios_semaphore);
-		}
 		free_tio(tio);
 		dec_pending(io, BLK_STS_DM_REQUEUE);
 		break;
@@ -1727,51 +1723,6 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md,
 	return ret;
 }
 
-/*
- * Optimized variant of __split_and_process_bio that leverages the
- * fact that targets that use it do _not_ have a need to split bios.
- */
-static blk_qc_t __process_bio(struct mapped_device *md, struct dm_table *map,
-			      struct bio *bio, struct dm_target *ti)
-{
-	struct clone_info ci;
-	blk_qc_t ret = BLK_QC_T_NONE;
-	int error = 0;
-
-	init_clone_info(&ci, md, map, bio);
-
-	if (bio->bi_opf & REQ_PREFLUSH) {
-		struct bio flush_bio;
-
-		/*
-		 * Use an on-stack bio for this, it's safe since we don't
-		 * need to reference it after submit. It's just used as
-		 * the basis for the clone(s).
-		 */
-		bio_init(&flush_bio, NULL, 0);
-		flush_bio.bi_opf = REQ_OP_WRITE | REQ_PREFLUSH | REQ_SYNC;
-		ci.bio = &flush_bio;
-		ci.sector_count = 0;
-		error = __send_empty_flush(&ci);
-		bio_uninit(ci.bio);
-		/* dec_pending submits any data associated with flush */
-	} else {
-		struct dm_target_io *tio;
-
-		ci.bio = bio;
-		ci.sector_count = bio_sectors(bio);
-		if (__process_abnormal_io(&ci, ti, &error))
-			goto out;
-
-		tio = alloc_tio(&ci, ti, 0, GFP_NOIO);
-		ret = __clone_and_map_simple_bio(&ci, tio, NULL);
-	}
-out:
-	/* drop the extra reference count */
-	dec_pending(ci.io, errno_to_blk_status(error));
-	return ret;
-}
-
 static blk_qc_t dm_process_bio(struct mapped_device *md,
 			       struct dm_table *map, struct bio *bio)
 {
@@ -1802,8 +1753,6 @@ static blk_qc_t dm_process_bio(struct mapped_device *md,
 		/* regular IO is split by __split_and_process_bio */
 	}
 
-	if (dm_get_md_type(md) == DM_TYPE_NVME_BIO_BASED)
-		return __process_bio(md, map, bio, ti);
 	return __split_and_process_bio(md, map, bio);
 }
 
@@ -2045,7 +1994,9 @@ static struct mapped_device *alloc_dev(int minor)
 	if (!md->bdev)
 		goto bad;
 
-	dm_stats_init(&md->stats);
+	r = dm_stats_init(&md->stats);
+	if (r < 0)
+		goto bad;
 
 	/* Populate the mapping, nobody knows we exist yet */
 	spin_lock(&_minor_lock);
@@ -2195,12 +2146,10 @@ static struct dm_table *__bind(struct mapped_device *md, struct dm_table *t,
 	if (request_based)
 		dm_stop_queue(q);
 
-	if (request_based || md->type == DM_TYPE_NVME_BIO_BASED) {
+	if (request_based) {
 		/*
-		 * Leverage the fact that request-based DM targets and
-		 * NVMe bio based targets are immutable singletons
-		 * - used to optimize both dm_request_fn and dm_mq_queue_rq;
-		 *   and __process_bio.
+		 * Leverage the fact that request-based DM targets are
+		 * immutable singletons - used to optimize dm_mq_queue_rq.
 		 */
 		md->immutable_target = dm_table_get_immutable_target(t);
 	}
@@ -2329,7 +2278,6 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
 		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:
@@ -2491,6 +2439,8 @@ static int dm_wait_for_completion(struct mapped_device *md, long task_state)
 	}
 	finish_wait(&md->wait, &wait);
 
+	smp_rmb();
+
 	return r;
 }
 
@@ -2859,6 +2809,9 @@ static void __dm_internal_suspend(struct mapped_device *md, unsigned suspend_fla
 
 static void __dm_internal_resume(struct mapped_device *md)
 {
+	int r;
+	struct dm_table *map;
+
 	BUG_ON(!md->internal_suspend_count);
 
 	if (--md->internal_suspend_count)
@@ -2867,12 +2820,23 @@ static void __dm_internal_resume(struct mapped_device *md)
 	if (dm_suspended_md(md))
 		goto done; /* resume from nested suspend */
 
-	/*
-	 * NOTE: existing callers don't need to call dm_table_resume_targets
-	 * (which may fail -- so best to avoid it for now by passing NULL map)
-	 */
-	(void) __dm_resume(md, NULL);
-
+	map = rcu_dereference_protected(md->map, lockdep_is_held(&md->suspend_lock));
+	r = __dm_resume(md, map);
+	if (r) {
+		/*
+		 * If a preresume method of some target failed, we are in a
+		 * tricky situation. We can't return an error to the caller. We
+		 * can't fake success because then the "resume" and
+		 * "postsuspend" methods would not be paired correctly, and it
+		 * would break various targets, for example it would cause list
+		 * corruption in the "origin" target.
+		 *
+		 * So, we fake normal suspend here, to make sure that the
+		 * "resume" and "postsuspend" methods will be paired correctly.
+		 */
+		DMERR("Preresume method failed: %d", r);
+		set_bit(DMF_SUSPENDED, &md->flags);
+	}
 done:
 	clear_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
 	smp_mb__after_atomic();
@@ -3063,7 +3027,6 @@ struct dm_md_mempools *dm_alloc_md_mempools(struct mapped_device *md, enum dm_qu
 	switch (type) {
 	case DM_TYPE_BIO_BASED:
 	case DM_TYPE_DAX_BIO_BASED:
-	case DM_TYPE_NVME_BIO_BASED:
 		pool_size = max(dm_get_reserved_bio_based_ios(), min_pool_size);
 		front_pad = roundup(per_io_data_size, __alignof__(struct dm_target_io)) + offsetof(struct dm_target_io, clone);
 		io_front_pad = roundup(front_pad,  __alignof__(struct dm_io)) + offsetof(struct dm_io, tio);
@@ -3132,6 +3095,11 @@ static int dm_call_pr(struct block_device *bdev, iterate_devices_callout_fn fn,
 		goto out;
 	ti = dm_table_get_target(table, 0);
 
+	if (dm_suspended_md(md)) {
+		ret = -EAGAIN;
+		goto out;
+	}
+
 	ret = -EINVAL;
 	if (!ti->type->iterate_devices)
 		goto out;