Merge branch 'for-4.13/block' of git://git.kernel.dk/linux-block

Pull core block/IO updates from Jens Axboe:
 "This is the main pull request for the block layer for 4.13. Not a huge
  round in terms of features, but there's a lot of churn related to some
  core cleanups.

  Note this depends on the UUID tree pull request, that Christoph
  already sent out.

  This pull request contains:

   - A series from Christoph, unifying the error/stats codes in the
     block layer. We now use blk_status_t everywhere, instead of using
     different schemes for different places.

   - Also from Christoph, some cleanups around request allocation and IO
     scheduler interactions in blk-mq.

   - And yet another series from Christoph, cleaning up how we handle
     and do bounce buffering in the block layer.

   - A blk-mq debugfs series from Bart, further improving on the support
     we have for exporting internal information to aid debugging IO
     hangs or stalls.

   - Also from Bart, a series that cleans up the request initialization
     differences across types of devices.

   - A series from Goldwyn Rodrigues, allowing the block layer to return
     failure if we will block and the user asked for non-blocking.

   - Patch from Hannes for supporting setting loop devices block size to
     that of the underlying device.

   - Two series of patches from Javier, fixing various issues with
     lightnvm, particular around pblk.

   - A series from me, adding support for write hints. This comes with
     NVMe support as well, so applications can help guide data placement
     on flash to improve performance, latencies, and write
     amplification.

   - A series from Ming, improving and hardening blk-mq support for
     stopping/starting and quiescing hardware queues.

   - Two pull requests for NVMe updates. Nothing major on the feature
     side, but lots of cleanups and bug fixes. From the usual crew.

   - A series from Neil Brown, greatly improving the bio rescue set
     support. Most notably, this kills the bio rescue work queues, if we
     don't really need them.

   - Lots of other little bug fixes that are all over the place"

* 'for-4.13/block' of git://git.kernel.dk/linux-block: (217 commits)
  lightnvm: pblk: set line bitmap check under debug
  lightnvm: pblk: verify that cache read is still valid
  lightnvm: pblk: add initialization check
  lightnvm: pblk: remove target using async. I/Os
  lightnvm: pblk: use vmalloc for GC data buffer
  lightnvm: pblk: use right metadata buffer for recovery
  lightnvm: pblk: schedule if data is not ready
  lightnvm: pblk: remove unused return variable
  lightnvm: pblk: fix double-free on pblk init
  lightnvm: pblk: fix bad le64 assignations
  nvme: Makefile: remove dead build rule
  blk-mq: map all HWQ also in hyperthreaded system
  nvmet-rdma: register ib_client to not deadlock in device removal
  nvme_fc: fix error recovery on link down.
  nvmet_fc: fix crashes on bad opcodes
  nvme_fc: Fix crash when nvme controller connection fails.
  nvme_fc: replace ioabort msleep loop with completion
  nvme_fc: fix double calls to nvme_cleanup_cmd()
  nvme-fabrics: verify that a controller returns the correct NQN
  nvme: simplify nvme_dev_attrs_are_visible
  ...

drivers/md/bcache/bcache.h

@@ -849,10 +849,11 @@ static inline void wake_up_allocators(struct cache_set *c)
 
 /* Forward declarations */
 
-void bch_count_io_errors(struct cache *, int, const char *);
+void bch_count_io_errors(struct cache *, blk_status_t, const char *);
 void bch_bbio_count_io_errors(struct cache_set *, struct bio *,
-			      int, const char *);
-void bch_bbio_endio(struct cache_set *, struct bio *, int, const char *);
+			      blk_status_t, const char *);
+void bch_bbio_endio(struct cache_set *, struct bio *, blk_status_t,
+		const char *);
 void bch_bbio_free(struct bio *, struct cache_set *);
 struct bio *bch_bbio_alloc(struct cache_set *);
 

drivers/md/bcache/btree.c

@@ -307,7 +307,7 @@ static void bch_btree_node_read(struct btree *b)
 	bch_submit_bbio(bio, b->c, &b->key, 0);
 	closure_sync(&cl);
 
-	if (bio->bi_error)
+	if (bio->bi_status)
 		set_btree_node_io_error(b);
 
 	bch_bbio_free(bio, b->c);
@@ -374,10 +374,10 @@ static void btree_node_write_endio(struct bio *bio)
 	struct closure *cl = bio->bi_private;
 	struct btree *b = container_of(cl, struct btree, io);
 
-	if (bio->bi_error)
+	if (bio->bi_status)
 		set_btree_node_io_error(b);
 
-	bch_bbio_count_io_errors(b->c, bio, bio->bi_error, "writing btree");
+	bch_bbio_count_io_errors(b->c, bio, bio->bi_status, "writing btree");
 	closure_put(cl);
 }
 

drivers/md/bcache/debug.c

@@ -110,7 +110,7 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
 	struct bio_vec bv, cbv;
 	struct bvec_iter iter, citer = { 0 };
 
-	check = bio_clone(bio, GFP_NOIO);
+	check = bio_clone_kmalloc(bio, GFP_NOIO);
 	if (!check)
 		return;
 	check->bi_opf = REQ_OP_READ;

drivers/md/bcache/io.c

@@ -50,7 +50,7 @@ void bch_submit_bbio(struct bio *bio, struct cache_set *c,
 
 /* IO errors */
 
-void bch_count_io_errors(struct cache *ca, int error, const char *m)
+void bch_count_io_errors(struct cache *ca, blk_status_t error, const char *m)
 {
 	/*
 	 * The halflife of an error is:
@@ -103,7 +103,7 @@ void bch_count_io_errors(struct cache *ca, int error, const char *m)
 }
 
 void bch_bbio_count_io_errors(struct cache_set *c, struct bio *bio,
-			      int error, const char *m)
+			      blk_status_t error, const char *m)
 {
 	struct bbio *b = container_of(bio, struct bbio, bio);
 	struct cache *ca = PTR_CACHE(c, &b->key, 0);
@@ -132,7 +132,7 @@ void bch_bbio_count_io_errors(struct cache_set *c, struct bio *bio,
 }
 
 void bch_bbio_endio(struct cache_set *c, struct bio *bio,
-		    int error, const char *m)
+		    blk_status_t error, const char *m)
 {
 	struct closure *cl = bio->bi_private;
 

drivers/md/bcache/journal.c

@@ -549,7 +549,7 @@ static void journal_write_endio(struct bio *bio)
 {
 	struct journal_write *w = bio->bi_private;
 
-	cache_set_err_on(bio->bi_error, w->c, "journal io error");
+	cache_set_err_on(bio->bi_status, w->c, "journal io error");
 	closure_put(&w->c->journal.io);
 }
 

drivers/md/bcache/movinggc.c

@@ -63,14 +63,14 @@ static void read_moving_endio(struct bio *bio)
 	struct moving_io *io = container_of(bio->bi_private,
 					    struct moving_io, cl);
 
-	if (bio->bi_error)
-		io->op.error = bio->bi_error;
+	if (bio->bi_status)
+		io->op.status = bio->bi_status;
 	else if (!KEY_DIRTY(&b->key) &&
 		 ptr_stale(io->op.c, &b->key, 0)) {
-		io->op.error = -EINTR;
+		io->op.status = BLK_STS_IOERR;
 	}
 
-	bch_bbio_endio(io->op.c, bio, bio->bi_error, "reading data to move");
+	bch_bbio_endio(io->op.c, bio, bio->bi_status, "reading data to move");
 }
 
 static void moving_init(struct moving_io *io)
@@ -92,7 +92,7 @@ static void write_moving(struct closure *cl)
 	struct moving_io *io = container_of(cl, struct moving_io, cl);
 	struct data_insert_op *op = &io->op;
 
-	if (!op->error) {
+	if (!op->status) {
 		moving_init(io);
 
 		io->bio.bio.bi_iter.bi_sector = KEY_START(&io->w->key);

drivers/md/bcache/request.c

@@ -81,7 +81,7 @@ static void bch_data_insert_keys(struct closure *cl)
 	if (ret == -ESRCH) {
 		op->replace_collision = true;
 	} else if (ret) {
-		op->error		= -ENOMEM;
+		op->status		= BLK_STS_RESOURCE;
 		op->insert_data_done	= true;
 	}
 
@@ -178,17 +178,17 @@ static void bch_data_insert_endio(struct bio *bio)
 	struct closure *cl = bio->bi_private;
 	struct data_insert_op *op = container_of(cl, struct data_insert_op, cl);
 
-	if (bio->bi_error) {
+	if (bio->bi_status) {
 		/* TODO: We could try to recover from this. */
 		if (op->writeback)
-			op->error = bio->bi_error;
+			op->status = bio->bi_status;
 		else if (!op->replace)
 			set_closure_fn(cl, bch_data_insert_error, op->wq);
 		else
 			set_closure_fn(cl, NULL, NULL);
 	}
 
-	bch_bbio_endio(op->c, bio, bio->bi_error, "writing data to cache");
+	bch_bbio_endio(op->c, bio, bio->bi_status, "writing data to cache");
 }
 
 static void bch_data_insert_start(struct closure *cl)
@@ -488,15 +488,15 @@ static void bch_cache_read_endio(struct bio *bio)
 	 * from the backing device.
 	 */
 
-	if (bio->bi_error)
-		s->iop.error = bio->bi_error;
+	if (bio->bi_status)
+		s->iop.status = bio->bi_status;
 	else if (!KEY_DIRTY(&b->key) &&
 		 ptr_stale(s->iop.c, &b->key, 0)) {
 		atomic_long_inc(&s->iop.c->cache_read_races);
-		s->iop.error = -EINTR;
+		s->iop.status = BLK_STS_IOERR;
 	}
 
-	bch_bbio_endio(s->iop.c, bio, bio->bi_error, "reading from cache");
+	bch_bbio_endio(s->iop.c, bio, bio->bi_status, "reading from cache");
 }
 
 /*
@@ -593,9 +593,9 @@ static void request_endio(struct bio *bio)
 {
 	struct closure *cl = bio->bi_private;
 
-	if (bio->bi_error) {
+	if (bio->bi_status) {
 		struct search *s = container_of(cl, struct search, cl);
-		s->iop.error = bio->bi_error;
+		s->iop.status = bio->bi_status;
 		/* Only cache read errors are recoverable */
 		s->recoverable = false;
 	}
@@ -611,7 +611,7 @@ static void bio_complete(struct search *s)
 				    &s->d->disk->part0, s->start_time);
 
 		trace_bcache_request_end(s->d, s->orig_bio);
-		s->orig_bio->bi_error = s->iop.error;
+		s->orig_bio->bi_status = s->iop.status;
 		bio_endio(s->orig_bio);
 		s->orig_bio = NULL;
 	}
@@ -664,7 +664,7 @@ static inline struct search *search_alloc(struct bio *bio,
 	s->iop.inode		= d->id;
 	s->iop.write_point	= hash_long((unsigned long) current, 16);
 	s->iop.write_prio	= 0;
-	s->iop.error		= 0;
+	s->iop.status		= 0;
 	s->iop.flags		= 0;
 	s->iop.flush_journal	= op_is_flush(bio->bi_opf);
 	s->iop.wq		= bcache_wq;
@@ -707,7 +707,7 @@ static void cached_dev_read_error(struct closure *cl)
 		/* Retry from the backing device: */
 		trace_bcache_read_retry(s->orig_bio);
 
-		s->iop.error = 0;
+		s->iop.status = 0;
 		do_bio_hook(s, s->orig_bio);
 
 		/* XXX: invalidate cache */
@@ -767,7 +767,7 @@ static void cached_dev_read_done_bh(struct closure *cl)
 				  !s->cache_miss, s->iop.bypass);
 	trace_bcache_read(s->orig_bio, !s->cache_miss, s->iop.bypass);
 
-	if (s->iop.error)
+	if (s->iop.status)
 		continue_at_nobarrier(cl, cached_dev_read_error, bcache_wq);
 	else if (s->iop.bio || verify(dc, &s->bio.bio))
 		continue_at_nobarrier(cl, cached_dev_read_done, bcache_wq);

drivers/md/bcache/request.h

@@ -10,7 +10,7 @@ struct data_insert_op {
 	unsigned		inode;
 	uint16_t		write_point;
 	uint16_t		write_prio;
-	short			error;
+	blk_status_t		status;
 
 	union {
 		uint16_t	flags;

drivers/md/bcache/super.c

@@ -271,7 +271,7 @@ static void write_super_endio(struct bio *bio)
 {
 	struct cache *ca = bio->bi_private;
 
-	bch_count_io_errors(ca, bio->bi_error, "writing superblock");
+	bch_count_io_errors(ca, bio->bi_status, "writing superblock");
 	closure_put(&ca->set->sb_write);
 }
 
@@ -321,7 +321,7 @@ static void uuid_endio(struct bio *bio)
 	struct closure *cl = bio->bi_private;
 	struct cache_set *c = container_of(cl, struct cache_set, uuid_write);
 
-	cache_set_err_on(bio->bi_error, c, "accessing uuids");
+	cache_set_err_on(bio->bi_status, c, "accessing uuids");
 	bch_bbio_free(bio, c);
 	closure_put(cl);
 }
@@ -494,7 +494,7 @@ static void prio_endio(struct bio *bio)
 {
 	struct cache *ca = bio->bi_private;
 
-	cache_set_err_on(bio->bi_error, ca->set, "accessing priorities");
+	cache_set_err_on(bio->bi_status, ca->set, "accessing priorities");
 	bch_bbio_free(bio, ca->set);
 	closure_put(&ca->prio);
 }
@@ -782,7 +782,9 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 
 	minor *= BCACHE_MINORS;
 
-	if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
+	if (!(d->bio_split = bioset_create(4, offsetof(struct bbio, bio),
+					   BIOSET_NEED_BVECS |
+					   BIOSET_NEED_RESCUER)) ||
 	    !(d->disk = alloc_disk(BCACHE_MINORS))) {
 		ida_simple_remove(&bcache_minor, minor);
 		return -ENOMEM;
@@ -1516,7 +1518,9 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 				sizeof(struct bbio) + sizeof(struct bio_vec) *
 				bucket_pages(c))) ||
 	    !(c->fill_iter = mempool_create_kmalloc_pool(1, iter_size)) ||
-	    !(c->bio_split = bioset_create(4, offsetof(struct bbio, bio))) ||
+	    !(c->bio_split = bioset_create(4, offsetof(struct bbio, bio),
+					   BIOSET_NEED_BVECS |
+					   BIOSET_NEED_RESCUER)) ||
 	    !(c->uuids = alloc_bucket_pages(GFP_KERNEL, c)) ||
 	    !(c->moving_gc_wq = alloc_workqueue("bcache_gc",
 						WQ_MEM_RECLAIM, 0)) ||

drivers/md/bcache/writeback.c

@@ -167,7 +167,7 @@ static void dirty_endio(struct bio *bio)
 	struct keybuf_key *w = bio->bi_private;
 	struct dirty_io *io = w->private;
 
-	if (bio->bi_error)
+	if (bio->bi_status)
 		SET_KEY_DIRTY(&w->key, false);
 
 	closure_put(&io->cl);
@@ -195,7 +195,7 @@ static void read_dirty_endio(struct bio *bio)
 	struct dirty_io *io = w->private;
 
 	bch_count_io_errors(PTR_CACHE(io->dc->disk.c, &w->key, 0),
-			    bio->bi_error, "reading dirty data from cache");
+			    bio->bi_status, "reading dirty data from cache");
 
 	dirty_endio(bio);
 }

drivers/md/dm-bio-prison-v1.c

@@ -229,7 +229,7 @@ void dm_cell_release_no_holder(struct dm_bio_prison *prison,
 EXPORT_SYMBOL_GPL(dm_cell_release_no_holder);
 
 void dm_cell_error(struct dm_bio_prison *prison,
-		   struct dm_bio_prison_cell *cell, int error)
+		   struct dm_bio_prison_cell *cell, blk_status_t error)
 {
 	struct bio_list bios;
 	struct bio *bio;
@@ -238,7 +238,7 @@ void dm_cell_error(struct dm_bio_prison *prison,
 	dm_cell_release(prison, cell, &bios);
 
 	while ((bio = bio_list_pop(&bios))) {
-		bio->bi_error = error;
+		bio->bi_status = error;
 		bio_endio(bio);
 	}
 }

drivers/md/dm-bio-prison-v1.h

@@ -91,7 +91,7 @@ void dm_cell_release_no_holder(struct dm_bio_prison *prison,
 			       struct dm_bio_prison_cell *cell,
 			       struct bio_list *inmates);
 void dm_cell_error(struct dm_bio_prison *prison,
-		   struct dm_bio_prison_cell *cell, int error);
+		   struct dm_bio_prison_cell *cell, blk_status_t error);
 
 /*
  * Visits the cell and then releases.  Guarantees no new inmates are

drivers/md/dm-bufio.c

@@ -145,8 +145,8 @@ struct dm_buffer {
 	enum data_mode data_mode;
 	unsigned char list_mode;		/* LIST_* */
 	unsigned hold_count;
-	int read_error;
-	int write_error;
+	blk_status_t read_error;
+	blk_status_t write_error;
 	unsigned long state;
 	unsigned long last_accessed;
 	struct dm_bufio_client *c;
@@ -555,7 +555,7 @@ static void dmio_complete(unsigned long error, void *context)
 {
 	struct dm_buffer *b = context;
 
-	b->bio.bi_error = error ? -EIO : 0;
+	b->bio.bi_status = error ? BLK_STS_IOERR : 0;
 	b->bio.bi_end_io(&b->bio);
 }
 
@@ -588,7 +588,7 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t sector,
 
 	r = dm_io(&io_req, 1, &region, NULL);
 	if (r) {
-		b->bio.bi_error = r;
+		b->bio.bi_status = errno_to_blk_status(r);
 		end_io(&b->bio);
 	}
 }
@@ -596,7 +596,7 @@ static void use_dmio(struct dm_buffer *b, int rw, sector_t sector,
 static void inline_endio(struct bio *bio)
 {
 	bio_end_io_t *end_fn = bio->bi_private;
-	int error = bio->bi_error;
+	blk_status_t status = bio->bi_status;
 
 	/*
 	 * Reset the bio to free any attached resources
@@ -604,7 +604,7 @@ static void inline_endio(struct bio *bio)
 	 */
 	bio_reset(bio);
 
-	bio->bi_error = error;
+	bio->bi_status = status;
 	end_fn(bio);
 }
 
@@ -685,11 +685,12 @@ static void write_endio(struct bio *bio)
 {
 	struct dm_buffer *b = container_of(bio, struct dm_buffer, bio);
 
-	b->write_error = bio->bi_error;
-	if (unlikely(bio->bi_error)) {
+	b->write_error = bio->bi_status;
+	if (unlikely(bio->bi_status)) {
 		struct dm_bufio_client *c = b->c;
-		int error = bio->bi_error;
-		(void)cmpxchg(&c->async_write_error, 0, error);
+
+		(void)cmpxchg(&c->async_write_error, 0,
+				blk_status_to_errno(bio->bi_status));
 	}
 
 	BUG_ON(!test_bit(B_WRITING, &b->state));
@@ -1063,7 +1064,7 @@ static void read_endio(struct bio *bio)
 {
 	struct dm_buffer *b = container_of(bio, struct dm_buffer, bio);
 
-	b->read_error = bio->bi_error;
+	b->read_error = bio->bi_status;
 
 	BUG_ON(!test_bit(B_READING, &b->state));
 
@@ -1107,7 +1108,7 @@ static void *new_read(struct dm_bufio_client *c, sector_t block,
 	wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE);
 
 	if (b->read_error) {
-		int error = b->read_error;
+		int error = blk_status_to_errno(b->read_error);
 
 		dm_bufio_release(b);
 
@@ -1257,7 +1258,8 @@ EXPORT_SYMBOL_GPL(dm_bufio_write_dirty_buffers_async);
  */
 int dm_bufio_write_dirty_buffers(struct dm_bufio_client *c)
 {
-	int a, f;
+	blk_status_t a;
+	int f;
 	unsigned long buffers_processed = 0;
 	struct dm_buffer *b, *tmp;
 

drivers/md/dm-cache-target.c

@@ -119,7 +119,7 @@ static void iot_io_end(struct io_tracker *iot, sector_t len)
  */
 struct continuation {
 	struct work_struct ws;
-	int input;
+	blk_status_t input;
 };
 
 static inline void init_continuation(struct continuation *k,
@@ -145,7 +145,7 @@ struct batcher {
 	/*
 	 * The operation that everyone is waiting for.
 	 */
-	int (*commit_op)(void *context);
+	blk_status_t (*commit_op)(void *context);
 	void *commit_context;
 
 	/*
@@ -171,8 +171,7 @@ struct batcher {
 static void __commit(struct work_struct *_ws)
 {
 	struct batcher *b = container_of(_ws, struct batcher, commit_work);
-
-	int r;
+	blk_status_t r;
 	unsigned long flags;
 	struct list_head work_items;
 	struct work_struct *ws, *tmp;
@@ -205,7 +204,7 @@ static void __commit(struct work_struct *_ws)
 
 	while ((bio = bio_list_pop(&bios))) {
 		if (r) {
-			bio->bi_error = r;
+			bio->bi_status = r;
 			bio_endio(bio);
 		} else
 			b->issue_op(bio, b->issue_context);
@@ -213,7 +212,7 @@ static void __commit(struct work_struct *_ws)
 }
 
 static void batcher_init(struct batcher *b,
-			 int (*commit_op)(void *),
+			 blk_status_t (*commit_op)(void *),
 			 void *commit_context,
 			 void (*issue_op)(struct bio *bio, void *),
 			 void *issue_context,
@@ -955,7 +954,7 @@ static void writethrough_endio(struct bio *bio)
 
 	dm_unhook_bio(&pb->hook_info, bio);
 
-	if (bio->bi_error) {
+	if (bio->bi_status) {
 		bio_endio(bio);
 		return;
 	}
@@ -1220,7 +1219,7 @@ static void copy_complete(int read_err, unsigned long write_err, void *context)
 	struct dm_cache_migration *mg = container_of(context, struct dm_cache_migration, k);
 
 	if (read_err || write_err)
-		mg->k.input = -EIO;
+		mg->k.input = BLK_STS_IOERR;
 
 	queue_continuation(mg->cache->wq, &mg->k);
 }
@@ -1266,8 +1265,8 @@ static void overwrite_endio(struct bio *bio)
 
 	dm_unhook_bio(&pb->hook_info, bio);
 
-	if (bio->bi_error)
-		mg->k.input = bio->bi_error;
+	if (bio->bi_status)
+		mg->k.input = bio->bi_status;
 
 	queue_continuation(mg->cache->wq, &mg->k);
 }
@@ -1323,8 +1322,10 @@ static void mg_complete(struct dm_cache_migration *mg, bool success)
 		if (mg->overwrite_bio) {
 			if (success)
 				force_set_dirty(cache, cblock);
+			else if (mg->k.input)
+				mg->overwrite_bio->bi_status = mg->k.input;
 			else
-				mg->overwrite_bio->bi_error = (mg->k.input ? : -EIO);
+				mg->overwrite_bio->bi_status = BLK_STS_IOERR;
 			bio_endio(mg->overwrite_bio);
 		} else {
 			if (success)
@@ -1504,7 +1505,7 @@ static void mg_copy(struct work_struct *ws)
 		r = copy(mg, is_policy_promote);
 		if (r) {
 			DMERR_LIMIT("%s: migration copy failed", cache_device_name(cache));
-			mg->k.input = -EIO;
+			mg->k.input = BLK_STS_IOERR;
 			mg_complete(mg, false);
 		}
 	}
@@ -1907,12 +1908,12 @@ static int commit(struct cache *cache, bool clean_shutdown)
 /*
  * Used by the batcher.
  */
-static int commit_op(void *context)
+static blk_status_t commit_op(void *context)
 {
 	struct cache *cache = context;
 
 	if (dm_cache_changed_this_transaction(cache->cmd))
-		return commit(cache, false);
+		return errno_to_blk_status(commit(cache, false));
 
 	return 0;
 }
@@ -2018,7 +2019,7 @@ static void requeue_deferred_bios(struct cache *cache)
 	bio_list_init(&cache->deferred_bios);
 
 	while ((bio = bio_list_pop(&bios))) {
-		bio->bi_error = DM_ENDIO_REQUEUE;
+		bio->bi_status = BLK_STS_DM_REQUEUE;
 		bio_endio(bio);
 	}
 }
@@ -2820,7 +2821,8 @@ static int cache_map(struct dm_target *ti, struct bio *bio)
 	return r;
 }
 
-static int cache_end_io(struct dm_target *ti, struct bio *bio, int error)
+static int cache_end_io(struct dm_target *ti, struct bio *bio,
+		blk_status_t *error)
 {
 	struct cache *cache = ti->private;
 	unsigned long flags;
@@ -2838,7 +2840,7 @@ static int cache_end_io(struct dm_target *ti, struct bio *bio, int error)
 	bio_drop_shared_lock(cache, bio);
 	accounted_complete(cache, bio);
 
-	return 0;
+	return DM_ENDIO_DONE;
 }
 
 static int write_dirty_bitset(struct cache *cache)

drivers/md/dm-crypt.c

@@ -71,7 +71,7 @@ struct dm_crypt_io {
 	struct convert_context ctx;
 
 	atomic_t io_pending;
-	int error;
+	blk_status_t error;
 	sector_t sector;
 
 	struct rb_node rb_node;
@@ -1292,7 +1292,7 @@ static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_
 /*
  * Encrypt / decrypt data from one bio to another one (can be the same one)
  */
-static int crypt_convert(struct crypt_config *cc,
+static blk_status_t crypt_convert(struct crypt_config *cc,
 			 struct convert_context *ctx)
 {
 	unsigned int tag_offset = 0;
@@ -1343,13 +1343,13 @@ static int crypt_convert(struct crypt_config *cc,
 		 */
 		case -EBADMSG:
 			atomic_dec(&ctx->cc_pending);
-			return -EILSEQ;
+			return BLK_STS_PROTECTION;
 		/*
 		 * There was an error while processing the request.
 		 */
 		default:
 			atomic_dec(&ctx->cc_pending);
-			return -EIO;
+			return BLK_STS_IOERR;
 		}
 	}
 
@@ -1463,7 +1463,7 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 {
 	struct crypt_config *cc = io->cc;
 	struct bio *base_bio = io->base_bio;
-	int error = io->error;
+	blk_status_t error = io->error;
 
 	if (!atomic_dec_and_test(&io->io_pending))
 		return;
@@ -1476,7 +1476,7 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
 	else
 		kfree(io->integrity_metadata);
 
-	base_bio->bi_error = error;
+	base_bio->bi_status = error;
 	bio_endio(base_bio);
 }
 
@@ -1502,7 +1502,7 @@ static void crypt_endio(struct bio *clone)
 	struct dm_crypt_io *io = clone->bi_private;
 	struct crypt_config *cc = io->cc;
 	unsigned rw = bio_data_dir(clone);
-	int error;
+	blk_status_t error;
 
 	/*
 	 * free the processed pages
@@ -1510,7 +1510,7 @@ static void crypt_endio(struct bio *clone)
 	if (rw == WRITE)
 		crypt_free_buffer_pages(cc, clone);
 
-	error = clone->bi_error;
+	error = clone->bi_status;
 	bio_put(clone);
 
 	if (rw == READ && !error) {
@@ -1570,7 +1570,7 @@ static void kcryptd_io_read_work(struct work_struct *work)
 
 	crypt_inc_pending(io);
 	if (kcryptd_io_read(io, GFP_NOIO))
-		io->error = -ENOMEM;
+		io->error = BLK_STS_RESOURCE;
 	crypt_dec_pending(io);
 }
 
@@ -1656,7 +1656,7 @@ static void kcryptd_crypt_write_io_submit(struct dm_crypt_io *io, int async)
 	sector_t sector;
 	struct rb_node **rbp, *parent;
 
-	if (unlikely(io->error < 0)) {
+	if (unlikely(io->error)) {
 		crypt_free_buffer_pages(cc, clone);
 		bio_put(clone);
 		crypt_dec_pending(io);
@@ -1697,7 +1697,7 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 	struct bio *clone;
 	int crypt_finished;
 	sector_t sector = io->sector;
-	int r;
+	blk_status_t r;
 
 	/*
 	 * Prevent io from disappearing until this function completes.
@@ -1707,7 +1707,7 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 
 	clone = crypt_alloc_buffer(io, io->base_bio->bi_iter.bi_size);
 	if (unlikely(!clone)) {
-		io->error = -EIO;
+		io->error = BLK_STS_IOERR;
 		goto dec;
 	}
 
@@ -1718,7 +1718,7 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
 
 	crypt_inc_pending(io);
 	r = crypt_convert(cc, &io->ctx);
-	if (r < 0)
+	if (r)
 		io->error = r;
 	crypt_finished = atomic_dec_and_test(&io->ctx.cc_pending);
 
@@ -1740,7 +1740,7 @@ static void kcryptd_crypt_read_done(struct dm_crypt_io *io)
 static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
 {
 	struct crypt_config *cc = io->cc;
-	int r = 0;
+	blk_status_t r;
 
 	crypt_inc_pending(io);
 
@@ -1748,7 +1748,7 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
 			   io->sector);
 
 	r = crypt_convert(cc, &io->ctx);
-	if (r < 0)
+	if (r)
 		io->error = r;
 
 	if (atomic_dec_and_test(&io->ctx.cc_pending))
@@ -1781,9 +1781,9 @@ static void kcryptd_async_done(struct crypto_async_request *async_req,
 	if (error == -EBADMSG) {
 		DMERR_LIMIT("INTEGRITY AEAD ERROR, sector %llu",
 			    (unsigned long long)le64_to_cpu(*org_sector_of_dmreq(cc, dmreq)));
-		io->error = -EILSEQ;
+		io->error = BLK_STS_PROTECTION;
 	} else if (error < 0)
-		io->error = -EIO;
+		io->error = BLK_STS_IOERR;
 
 	crypt_free_req(cc, req_of_dmreq(cc, dmreq), io->base_bio);
 
@@ -2677,7 +2677,8 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto bad;
 	}
 
-	cc->bs = bioset_create(MIN_IOS, 0);
+	cc->bs = bioset_create(MIN_IOS, 0, (BIOSET_NEED_BVECS |
+					    BIOSET_NEED_RESCUER));
 	if (!cc->bs) {
 		ti->error = "Cannot allocate crypt bioset";
 		goto bad;
@@ -2795,10 +2796,10 @@ static int crypt_map(struct dm_target *ti, struct bio *bio)
 	 * and is aligned to this size as defined in IO hints.
 	 */
 	if (unlikely((bio->bi_iter.bi_sector & ((cc->sector_size >> SECTOR_SHIFT) - 1)) != 0))
-		return -EIO;
+		return DM_MAPIO_KILL;
 
 	if (unlikely(bio->bi_iter.bi_size & (cc->sector_size - 1)))
-		return -EIO;
+		return DM_MAPIO_KILL;
 
 	io = dm_per_bio_data(bio, cc->per_bio_data_size);
 	crypt_io_init(io, cc, bio, dm_target_offset(ti, bio->bi_iter.bi_sector));

drivers/md/dm-flakey.c

@@ -321,7 +321,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 		if (bio_data_dir(bio) == READ) {
 			if (!fc->corrupt_bio_byte && !test_bit(DROP_WRITES, &fc->flags) &&
 			    !test_bit(ERROR_WRITES, &fc->flags))
-				return -EIO;
+				return DM_MAPIO_KILL;
 			goto map_bio;
 		}
 
@@ -349,7 +349,7 @@ static int flakey_map(struct dm_target *ti, struct bio *bio)
 		/*
 		 * By default, error all I/O.
 		 */
-		return -EIO;
+		return DM_MAPIO_KILL;
 	}
 
 map_bio:
@@ -358,12 +358,13 @@ map_bio:
 	return DM_MAPIO_REMAPPED;
 }
 
-static int flakey_end_io(struct dm_target *ti, struct bio *bio, int error)
+static int flakey_end_io(struct dm_target *ti, struct bio *bio,
+		blk_status_t *error)
 {
 	struct flakey_c *fc = ti->private;
 	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
 
-	if (!error && pb->bio_submitted && (bio_data_dir(bio) == READ)) {
+	if (!*error && pb->bio_submitted && (bio_data_dir(bio) == READ)) {
 		if (fc->corrupt_bio_byte && (fc->corrupt_bio_rw == READ) &&
 		    all_corrupt_bio_flags_match(bio, fc)) {
 			/*
@@ -377,11 +378,11 @@ static int flakey_end_io(struct dm_target *ti, struct bio *bio, int error)
 			 * Error read during the down_interval if drop_writes
 			 * and error_writes were not configured.
 			 */
-			return -EIO;
+			*error = BLK_STS_IOERR;
 		}
 	}
 
-	return error;
+	return DM_ENDIO_DONE;
 }
 
 static void flakey_status(struct dm_target *ti, status_type_t type,

drivers/md/dm-integrity.c

@@ -246,7 +246,7 @@ struct dm_integrity_io {
 	unsigned metadata_offset;
 
 	atomic_t in_flight;
-	int bi_error;
+	blk_status_t bi_status;
 
 	struct completion *completion;
 
@@ -1118,8 +1118,8 @@ static void submit_flush_bio(struct dm_integrity_c *ic, struct dm_integrity_io *
 static void do_endio(struct dm_integrity_c *ic, struct bio *bio)
 {
 	int r = dm_integrity_failed(ic);
-	if (unlikely(r) && !bio->bi_error)
-		bio->bi_error = r;
+	if (unlikely(r) && !bio->bi_status)
+		bio->bi_status = errno_to_blk_status(r);
 	bio_endio(bio);
 }
 
@@ -1127,7 +1127,7 @@ static void do_endio_flush(struct dm_integrity_c *ic, struct dm_integrity_io *di
 {
 	struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
 
-	if (unlikely(dio->fua) && likely(!bio->bi_error) && likely(!dm_integrity_failed(ic)))
+	if (unlikely(dio->fua) && likely(!bio->bi_status) && likely(!dm_integrity_failed(ic)))
 		submit_flush_bio(ic, dio);
 	else
 		do_endio(ic, bio);
@@ -1146,9 +1146,9 @@ static void dec_in_flight(struct dm_integrity_io *dio)
 
 		bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
 
-		if (unlikely(dio->bi_error) && !bio->bi_error)
-			bio->bi_error = dio->bi_error;
-		if (likely(!bio->bi_error) && unlikely(bio_sectors(bio) != dio->range.n_sectors)) {
+		if (unlikely(dio->bi_status) && !bio->bi_status)
+			bio->bi_status = dio->bi_status;
+		if (likely(!bio->bi_status) && unlikely(bio_sectors(bio) != dio->range.n_sectors)) {
 			dio->range.logical_sector += dio->range.n_sectors;
 			bio_advance(bio, dio->range.n_sectors << SECTOR_SHIFT);
 			INIT_WORK(&dio->work, integrity_bio_wait);
@@ -1322,7 +1322,7 @@ skip_io:
 	dec_in_flight(dio);
 	return;
 error:
-	dio->bi_error = r;
+	dio->bi_status = errno_to_blk_status(r);
 	dec_in_flight(dio);
 }
 
@@ -1335,7 +1335,7 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio)
 	sector_t area, offset;
 
 	dio->ic = ic;
-	dio->bi_error = 0;
+	dio->bi_status = 0;
 
 	if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
 		submit_flush_bio(ic, dio);
@@ -1356,13 +1356,13 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio)
 		DMERR("Too big sector number: 0x%llx + 0x%x > 0x%llx",
 		      (unsigned long long)dio->range.logical_sector, bio_sectors(bio),
 		      (unsigned long long)ic->provided_data_sectors);
-		return -EIO;
+		return DM_MAPIO_KILL;
 	}
 	if (unlikely((dio->range.logical_sector | bio_sectors(bio)) & (unsigned)(ic->sectors_per_block - 1))) {
 		DMERR("Bio not aligned on %u sectors: 0x%llx, 0x%x",
 		      ic->sectors_per_block,
 		      (unsigned long long)dio->range.logical_sector, bio_sectors(bio));
-		return -EIO;
+		return DM_MAPIO_KILL;
 	}
 
 	if (ic->sectors_per_block > 1) {
@@ -1372,7 +1372,7 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio)
 			if (unlikely((bv.bv_offset | bv.bv_len) & ((ic->sectors_per_block << SECTOR_SHIFT) - 1))) {
 				DMERR("Bio vector (%u,%u) is not aligned on %u-sector boundary",
 					bv.bv_offset, bv.bv_len, ic->sectors_per_block);
-				return -EIO;
+				return DM_MAPIO_KILL;
 			}
 		}
 	}
@@ -1387,18 +1387,18 @@ static int dm_integrity_map(struct dm_target *ti, struct bio *bio)
 				wanted_tag_size *= ic->tag_size;
 			if (unlikely(wanted_tag_size != bip->bip_iter.bi_size)) {
 				DMERR("Invalid integrity data size %u, expected %u", bip->bip_iter.bi_size, wanted_tag_size);
-				return -EIO;
+				return DM_MAPIO_KILL;
 			}
 		}
 	} else {
 		if (unlikely(bip != NULL)) {
 			DMERR("Unexpected integrity data when using internal hash");
-			return -EIO;
+			return DM_MAPIO_KILL;
 		}
 	}
 
 	if (unlikely(ic->mode == 'R') && unlikely(dio->write))
-		return -EIO;
+		return DM_MAPIO_KILL;
 
 	get_area_and_offset(ic, dio->range.logical_sector, &area, &offset);
 	dio->metadata_block = get_metadata_sector_and_offset(ic, area, offset, &dio->metadata_offset);

drivers/md/dm-io.c

@@ -58,7 +58,8 @@ struct dm_io_client *dm_io_client_create(void)
 	if (!client->pool)
 		goto bad;
 
-	client->bios = bioset_create(min_ios, 0);
+	client->bios = bioset_create(min_ios, 0, (BIOSET_NEED_BVECS |
+						  BIOSET_NEED_RESCUER));
 	if (!client->bios)
 		goto bad;
 
@@ -124,7 +125,7 @@ static void complete_io(struct io *io)
 	fn(error_bits, context);
 }
 
-static void dec_count(struct io *io, unsigned int region, int error)
+static void dec_count(struct io *io, unsigned int region, blk_status_t error)
 {
 	if (error)
 		set_bit(region, &io->error_bits);
@@ -137,9 +138,9 @@ static void endio(struct bio *bio)
 {
 	struct io *io;
 	unsigned region;
-	int error;
+	blk_status_t error;
 
-	if (bio->bi_error && bio_data_dir(bio) == READ)
+	if (bio->bi_status && bio_data_dir(bio) == READ)
 		zero_fill_bio(bio);
 
 	/*
@@ -147,7 +148,7 @@ static void endio(struct bio *bio)
 	 */
 	retrieve_io_and_region_from_bio(bio, &io, &region);
 
-	error = bio->bi_error;
+	error = bio->bi_status;
 	bio_put(bio);
 
 	dec_count(io, region, error);
@@ -319,7 +320,7 @@ static void do_region(int op, int op_flags, unsigned region,
 	if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES ||
 	     op == REQ_OP_WRITE_SAME) && special_cmd_max_sectors == 0) {
 		atomic_inc(&io->count);
-		dec_count(io, region, -EOPNOTSUPP);
+		dec_count(io, region, BLK_STS_NOTSUPP);
 		return;
 	}
 

drivers/md/dm-log-writes.c

@@ -150,10 +150,10 @@ static void log_end_io(struct bio *bio)
 {
 	struct log_writes_c *lc = bio->bi_private;
 
-	if (bio->bi_error) {
+	if (bio->bi_status) {
 		unsigned long flags;
 
-		DMERR("Error writing log block, error=%d", bio->bi_error);
+		DMERR("Error writing log block, error=%d", bio->bi_status);
 		spin_lock_irqsave(&lc->blocks_lock, flags);
 		lc->logging_enabled = false;
 		spin_unlock_irqrestore(&lc->blocks_lock, flags);
@@ -586,7 +586,7 @@ static int log_writes_map(struct dm_target *ti, struct bio *bio)
 		spin_lock_irq(&lc->blocks_lock);
 		lc->logging_enabled = false;
 		spin_unlock_irq(&lc->blocks_lock);
-		return -ENOMEM;
+		return DM_MAPIO_KILL;
 	}
 	INIT_LIST_HEAD(&block->list);
 	pb->block = block;
@@ -639,7 +639,7 @@ static int log_writes_map(struct dm_target *ti, struct bio *bio)
 			spin_lock_irq(&lc->blocks_lock);
 			lc->logging_enabled = false;
 			spin_unlock_irq(&lc->blocks_lock);
-			return -ENOMEM;
+			return DM_MAPIO_KILL;
 		}
 
 		src = kmap_atomic(bv.bv_page);
@@ -664,7 +664,8 @@ map_bio:
 	return DM_MAPIO_REMAPPED;
 }
 
-static int normal_end_io(struct dm_target *ti, struct bio *bio, int error)
+static int normal_end_io(struct dm_target *ti, struct bio *bio,
+		blk_status_t *error)
 {
 	struct log_writes_c *lc = ti->private;
 	struct per_bio_data *pb = dm_per_bio_data(bio, sizeof(struct per_bio_data));
@@ -686,7 +687,7 @@ static int normal_end_io(struct dm_target *ti, struct bio *bio, int error)
 		spin_unlock_irqrestore(&lc->blocks_lock, flags);
 	}
 
-	return error;
+	return DM_ENDIO_DONE;
 }
 
 /*

drivers/md/dm-mpath.c

@@ -559,13 +559,13 @@ static int __multipath_map_bio(struct multipath *m, struct bio *bio, struct dm_m
 		if (test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags))
 			return DM_MAPIO_REQUEUE;
 		dm_report_EIO(m);
-		return -EIO;
+		return DM_MAPIO_KILL;
 	}
 
 	mpio->pgpath = pgpath;
 	mpio->nr_bytes = nr_bytes;
 
-	bio->bi_error = 0;
+	bio->bi_status = 0;
 	bio->bi_bdev = pgpath->path.dev->bdev;
 	bio->bi_opf |= REQ_FAILFAST_TRANSPORT;
 
@@ -621,11 +621,19 @@ static void process_queued_bios(struct work_struct *work)
 	blk_start_plug(&plug);
 	while ((bio = bio_list_pop(&bios))) {
 		r = __multipath_map_bio(m, bio, get_mpio_from_bio(bio));
-		if (r < 0 || r == DM_MAPIO_REQUEUE) {
-			bio->bi_error = r;
+		switch (r) {
+		case DM_MAPIO_KILL:
+			bio->bi_status = BLK_STS_IOERR;
 			bio_endio(bio);
-		} else if (r == DM_MAPIO_REMAPPED)
+			break;
+		case DM_MAPIO_REQUEUE:
+			bio->bi_status = BLK_STS_DM_REQUEUE;
+			bio_endio(bio);
+			break;
+		case DM_MAPIO_REMAPPED:
 			generic_make_request(bio);
+			break;
+		}
 	}
 	blk_finish_plug(&plug);
 }
@@ -1442,22 +1450,15 @@ static void activate_path_work(struct work_struct *work)
 	activate_or_offline_path(pgpath);
 }
 
-static int noretry_error(int error)
+static int noretry_error(blk_status_t error)
 {
 	switch (error) {
-	case -EBADE:
-		/*
-		 * EBADE signals an reservation conflict.
-		 * We shouldn't fail the path here as we can communicate with
-		 * the target.  We should failover to the next path, but in
-		 * doing so we might be causing a ping-pong between paths.
-		 * So just return the reservation conflict error.
-		 */
-	case -EOPNOTSUPP:
-	case -EREMOTEIO:
-	case -EILSEQ:
-	case -ENODATA:
-	case -ENOSPC:
+	case BLK_STS_NOTSUPP:
+	case BLK_STS_NOSPC:
+	case BLK_STS_TARGET:
+	case BLK_STS_NEXUS:
+	case BLK_STS_MEDIUM:
+	case BLK_STS_RESOURCE:
 		return 1;
 	}
 
@@ -1466,7 +1467,7 @@ static int noretry_error(int error)
 }
 
 static int multipath_end_io(struct dm_target *ti, struct request *clone,
-			    int error, union map_info *map_context)
+			    blk_status_t error, union map_info *map_context)
 {
 	struct dm_mpath_io *mpio = get_mpio(map_context);
 	struct pgpath *pgpath = mpio->pgpath;
@@ -1493,7 +1494,7 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
 
 		if (atomic_read(&m->nr_valid_paths) == 0 &&
 		    !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
-			if (error == -EIO)
+			if (error == BLK_STS_IOERR)
 				dm_report_EIO(m);
 			/* complete with the original error */
 			r = DM_ENDIO_DONE;
@@ -1510,24 +1511,26 @@ static int multipath_end_io(struct dm_target *ti, struct request *clone,
 	return r;
 }
 
-static int do_end_io_bio(struct multipath *m, struct bio *clone,
-			 int error, struct dm_mpath_io *mpio)
+static int multipath_end_io_bio(struct dm_target *ti, struct bio *clone,
+		blk_status_t *error)
 {
+	struct multipath *m = ti->private;
+	struct dm_mpath_io *mpio = get_mpio_from_bio(clone);
+	struct pgpath *pgpath = mpio->pgpath;
 	unsigned long flags;
+	int r = DM_ENDIO_DONE;
 
-	if (!error)
-		return 0;	/* I/O complete */
+	if (!*error || noretry_error(*error))
+		goto done;
 
-	if (noretry_error(error))
-		return error;
-
-	if (mpio->pgpath)
-		fail_path(mpio->pgpath);
+	if (pgpath)
+		fail_path(pgpath);
 
 	if (atomic_read(&m->nr_valid_paths) == 0 &&
 	    !test_bit(MPATHF_QUEUE_IF_NO_PATH, &m->flags)) {
 		dm_report_EIO(m);
-		return -EIO;
+		*error = BLK_STS_IOERR;
+		goto done;
 	}
 
 	/* Queue for the daemon to resubmit */
@@ -1539,23 +1542,11 @@ static int do_end_io_bio(struct multipath *m, struct bio *clone,
 	if (!test_bit(MPATHF_QUEUE_IO, &m->flags))
 		queue_work(kmultipathd, &m->process_queued_bios);
 
-	return DM_ENDIO_INCOMPLETE;
-}
-
-static int multipath_end_io_bio(struct dm_target *ti, struct bio *clone, int error)
-{
-	struct multipath *m = ti->private;
-	struct dm_mpath_io *mpio = get_mpio_from_bio(clone);
-	struct pgpath *pgpath;
-	struct path_selector *ps;
-	int r;
-
-	BUG_ON(!mpio);
-
-	r = do_end_io_bio(m, clone, error, mpio);
-	pgpath = mpio->pgpath;
+	r = DM_ENDIO_INCOMPLETE;
+done:
 	if (pgpath) {
-		ps = &pgpath->pg->ps;
+		struct path_selector *ps = &pgpath->pg->ps;
+
 		if (ps->type->end_io)
 			ps->type->end_io(ps, &pgpath->path, mpio->nr_bytes);
 	}