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
  ...

10 files changed, 43 insertions, 38 deletions

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index c3ea03c9a1a8..dee542fff68e 100644
--- a/drivers/md/bcache/bcache.h
+++ b/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 *);
 
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 450d0e848ae4..866dcf78ff8e 100644
--- a/drivers/md/bcache/btree.c
+++ b/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);
 }
 
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 06f55056aaae..35a5a7210e51 100644
--- a/drivers/md/bcache/debug.c
+++ b/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;
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index db45a88c0ce9..6a9b85095e7b 100644
--- a/drivers/md/bcache/io.c
+++ b/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;
 
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 1198e53d5670..0352d05e495c 100644
--- a/drivers/md/bcache/journal.c
+++ b/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);
 }
 
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index 13b8a907006d..f633b30c962e 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/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);
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 709c9cc34369..019b3df9f1c6 100644
--- a/drivers/md/bcache/request.c
+++ b/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);
diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h
index 1ff36875c2b3..7689176951ce 100644
--- a/drivers/md/bcache/request.h
+++ b/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;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index e57353e39168..8352fad765f6 100644
--- a/drivers/md/bcache/super.c
+++ b/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)) ||
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 6ac2e48b9235..42c66e76f05e 100644
--- a/drivers/md/bcache/writeback.c
+++ b/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);
 }