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
  ...

Documentation/block/biodoc.txt

@@ -632,7 +632,7 @@ to i/o submission, if the bio fields are likely to be accessed after the
 i/o is issued (since the bio may otherwise get freed in case i/o completion
 happens in the meantime).
 
-The bio_clone() routine may be used to duplicate a bio, where the clone
+The bio_clone_fast() routine may be used to duplicate a bio, where the clone
 shares the bio_vec_list with the original bio (i.e. both point to the
 same bio_vec_list). This would typically be used for splitting i/o requests
 in lvm or md.

arch/s390/include/asm/eadm.h

@@ -3,6 +3,7 @@
 
 #include <linux/types.h>
 #include <linux/device.h>
+#include <linux/blkdev.h>
 
 struct arqb {
 	u64 data;
@@ -105,13 +106,14 @@ struct scm_driver {
 	int (*probe) (struct scm_device *scmdev);
 	int (*remove) (struct scm_device *scmdev);
 	void (*notify) (struct scm_device *scmdev, enum scm_event event);
-	void (*handler) (struct scm_device *scmdev, void *data, int error);
+	void (*handler) (struct scm_device *scmdev, void *data,
+			blk_status_t error);
 };
 
 int scm_driver_register(struct scm_driver *scmdrv);
 void scm_driver_unregister(struct scm_driver *scmdrv);
 
 int eadm_start_aob(struct aob *aob);
-void scm_irq_handler(struct aob *aob, int error);
+void scm_irq_handler(struct aob *aob, blk_status_t error);
 
 #endif /* _ASM_S390_EADM_H */

arch/um/drivers/ubd_kern.c

@@ -534,7 +534,7 @@ static void ubd_handler(void)
 		for (count = 0; count < n/sizeof(struct io_thread_req *); count++) {
 			blk_end_request(
 				(*irq_req_buffer)[count]->req,
-				0,
+				BLK_STS_OK,
 				(*irq_req_buffer)[count]->length
 			);
 			kfree((*irq_req_buffer)[count]);

block/badblocks.c

@@ -533,6 +533,7 @@ ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len,
 	case 3:
 		if (newline != '\n')
 			return -EINVAL;
+		/* fall through */
 	case 2:
 		if (length <= 0)
 			return -EINVAL;

block/bfq-iosched.c

@@ -725,8 +725,12 @@ static void bfq_updated_next_req(struct bfq_data *bfqd,
 }
 
 static void
-bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
+bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_data *bfqd,
+		      struct bfq_io_cq *bic, bool bfq_already_existing)
 {
+	unsigned int old_wr_coeff = bfqq->wr_coeff;
+	bool busy = bfq_already_existing && bfq_bfqq_busy(bfqq);
+
 	if (bic->saved_idle_window)
 		bfq_mark_bfqq_idle_window(bfqq);
 	else
@@ -754,6 +758,14 @@ bfq_bfqq_resume_state(struct bfq_queue *bfqq, struct bfq_io_cq *bic)
 
 	/* make sure weight will be updated, however we got here */
 	bfqq->entity.prio_changed = 1;
+
+	if (likely(!busy))
+		return;
+
+	if (old_wr_coeff == 1 && bfqq->wr_coeff > 1)
+		bfqd->wr_busy_queues++;
+	else if (old_wr_coeff > 1 && bfqq->wr_coeff == 1)
+		bfqd->wr_busy_queues--;
 }
 
 static int bfqq_process_refs(struct bfq_queue *bfqq)
@@ -4290,10 +4302,16 @@ static void bfq_put_rq_priv_body(struct bfq_queue *bfqq)
 	bfq_put_queue(bfqq);
 }
 
-static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
+static void bfq_finish_request(struct request *rq)
 {
-	struct bfq_queue *bfqq = RQ_BFQQ(rq);
-	struct bfq_data *bfqd = bfqq->bfqd;
+	struct bfq_queue *bfqq;
+	struct bfq_data *bfqd;
+
+	if (!rq->elv.icq)
+		return;
+
+	bfqq = RQ_BFQQ(rq);
+	bfqd = bfqq->bfqd;
 
 	if (rq->rq_flags & RQF_STARTED)
 		bfqg_stats_update_completion(bfqq_group(bfqq),
@@ -4324,7 +4342,7 @@ static void bfq_put_rq_private(struct request_queue *q, struct request *rq)
 		 */
 
 		if (!RB_EMPTY_NODE(&rq->rb_node))
-			bfq_remove_request(q, rq);
+			bfq_remove_request(rq->q, rq);
 		bfq_put_rq_priv_body(bfqq);
 	}
 
@@ -4394,20 +4412,21 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd,
 /*
  * Allocate bfq data structures associated with this request.
  */
-static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
-			      struct bio *bio)
+static void bfq_prepare_request(struct request *rq, struct bio *bio)
 {
+	struct request_queue *q = rq->q;
 	struct bfq_data *bfqd = q->elevator->elevator_data;
-	struct bfq_io_cq *bic = icq_to_bic(rq->elv.icq);
+	struct bfq_io_cq *bic;
 	const int is_sync = rq_is_sync(rq);
 	struct bfq_queue *bfqq;
 	bool new_queue = false;
-	bool split = false;
+	bool bfqq_already_existing = false, split = false;
 
-	spin_lock_irq(&bfqd->lock);
+	if (!rq->elv.icq)
+		return;
+	bic = icq_to_bic(rq->elv.icq);
 
-	if (!bic)
-		goto queue_fail;
+	spin_lock_irq(&bfqd->lock);
 
 	bfq_check_ioprio_change(bic, bio);
 
@@ -4432,6 +4451,8 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 				bfqq = bfq_get_bfqq_handle_split(bfqd, bic, bio,
 								 true, is_sync,
 								 NULL);
+			else
+				bfqq_already_existing = true;
 		}
 	}
 
@@ -4457,7 +4478,8 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 			 * queue: restore the idle window and the
 			 * possible weight raising period.
 			 */
-			bfq_bfqq_resume_state(bfqq, bic);
+			bfq_bfqq_resume_state(bfqq, bfqd, bic,
+					      bfqq_already_existing);
 		}
 	}
 
@@ -4465,13 +4487,6 @@ static int bfq_get_rq_private(struct request_queue *q, struct request *rq,
 		bfq_handle_burst(bfqd, bfqq);
 
 	spin_unlock_irq(&bfqd->lock);
-
-	return 0;
-
-queue_fail:
-	spin_unlock_irq(&bfqd->lock);
-
-	return 1;
 }
 
 static void bfq_idle_slice_timer_body(struct bfq_queue *bfqq)
@@ -4950,8 +4965,8 @@ static struct elv_fs_entry bfq_attrs[] = {
 
 static struct elevator_type iosched_bfq_mq = {
 	.ops.mq = {
-		.get_rq_priv		= bfq_get_rq_private,
-		.put_rq_priv		= bfq_put_rq_private,
+		.prepare_request	= bfq_prepare_request,
+		.finish_request		= bfq_finish_request,
 		.exit_icq		= bfq_exit_icq,
 		.insert_requests	= bfq_insert_requests,
 		.dispatch_request	= bfq_dispatch_request,

block/bio-integrity.c

@@ -224,7 +224,7 @@ static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
  * @bio:	bio to generate/verify integrity metadata for
  * @proc_fn:	Pointer to the relevant processing function
  */
-static int bio_integrity_process(struct bio *bio,
+static blk_status_t bio_integrity_process(struct bio *bio,
 				 integrity_processing_fn *proc_fn)
 {
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
@@ -232,7 +232,7 @@ static int bio_integrity_process(struct bio *bio,
 	struct bvec_iter bviter;
 	struct bio_vec bv;
 	struct bio_integrity_payload *bip = bio_integrity(bio);
-	unsigned int ret = 0;
+	blk_status_t ret = BLK_STS_OK;
 	void *prot_buf = page_address(bip->bip_vec->bv_page) +
 		bip->bip_vec->bv_offset;
 
@@ -369,7 +369,7 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 	struct bio *bio = bip->bip_bio;
 	struct blk_integrity *bi = bdev_get_integrity(bio->bi_bdev);
 
-	bio->bi_error = bio_integrity_process(bio, bi->profile->verify_fn);
+	bio->bi_status = bio_integrity_process(bio, bi->profile->verify_fn);
 
 	/* Restore original bio completion handler */
 	bio->bi_end_io = bip->bip_end_io;
@@ -398,7 +398,7 @@ void bio_integrity_endio(struct bio *bio)
 	 * integrity metadata.  Restore original bio end_io handler
 	 * and run it.
 	 */
-	if (bio->bi_error) {
+	if (bio->bi_status) {
 		bio->bi_end_io = bip->bip_end_io;
 		bio_endio(bio);
 

block/bio.c

@@ -315,8 +315,8 @@ static struct bio *__bio_chain_endio(struct bio *bio)
 {
 	struct bio *parent = bio->bi_private;
 
-	if (!parent->bi_error)
-		parent->bi_error = bio->bi_error;
+	if (!parent->bi_status)
+		parent->bi_status = bio->bi_status;
 	bio_put(bio);
 	return parent;
 }
@@ -369,6 +369,8 @@ static void punt_bios_to_rescuer(struct bio_set *bs)
 	struct bio_list punt, nopunt;
 	struct bio *bio;
 
+	if (WARN_ON_ONCE(!bs->rescue_workqueue))
+		return;
 	/*
 	 * In order to guarantee forward progress we must punt only bios that
 	 * were allocated from this bio_set; otherwise, if there was a bio on
@@ -480,7 +482,8 @@ struct bio *bio_alloc_bioset(gfp_t gfp_mask, unsigned int nr_iovecs,
 
 		if (current->bio_list &&
 		    (!bio_list_empty(&current->bio_list[0]) ||
-		     !bio_list_empty(&current->bio_list[1])))
+		     !bio_list_empty(&current->bio_list[1])) &&
+		    bs->rescue_workqueue)
 			gfp_mask &= ~__GFP_DIRECT_RECLAIM;
 
 		p = mempool_alloc(bs->bio_pool, gfp_mask);
@@ -550,7 +553,7 @@ EXPORT_SYMBOL(zero_fill_bio);
  *
  * Description:
  *   Put a reference to a &struct bio, either one you have gotten with
- *   bio_alloc, bio_get or bio_clone. The last put of a bio will free it.
+ *   bio_alloc, bio_get or bio_clone_*. The last put of a bio will free it.
  **/
 void bio_put(struct bio *bio)
 {
@@ -599,6 +602,7 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
 	bio->bi_bdev = bio_src->bi_bdev;
 	bio_set_flag(bio, BIO_CLONED);
 	bio->bi_opf = bio_src->bi_opf;
+	bio->bi_write_hint = bio_src->bi_write_hint;
 	bio->bi_iter = bio_src->bi_iter;
 	bio->bi_io_vec = bio_src->bi_io_vec;
 
@@ -682,6 +686,7 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
 		return NULL;
 	bio->bi_bdev		= bio_src->bi_bdev;
 	bio->bi_opf		= bio_src->bi_opf;
+	bio->bi_write_hint	= bio_src->bi_write_hint;
 	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
 	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
 
@@ -924,7 +929,7 @@ static void submit_bio_wait_endio(struct bio *bio)
 {
 	struct submit_bio_ret *ret = bio->bi_private;
 
-	ret->error = bio->bi_error;
+	ret->error = blk_status_to_errno(bio->bi_status);
 	complete(&ret->event);
 }
 
@@ -1823,8 +1828,8 @@ again:
 	}
 
 	if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {
-		trace_block_bio_complete(bdev_get_queue(bio->bi_bdev),
-					 bio, bio->bi_error);
+		trace_block_bio_complete(bdev_get_queue(bio->bi_bdev), bio,
+					 blk_status_to_errno(bio->bi_status));
 		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
 	}
 
@@ -1927,9 +1932,29 @@ void bioset_free(struct bio_set *bs)
 }
 EXPORT_SYMBOL(bioset_free);
 
-static struct bio_set *__bioset_create(unsigned int pool_size,
-				       unsigned int front_pad,
-				       bool create_bvec_pool)
+/**
+ * bioset_create  - Create a bio_set
+ * @pool_size:	Number of bio and bio_vecs to cache in the mempool
+ * @front_pad:	Number of bytes to allocate in front of the returned bio
+ * @flags:	Flags to modify behavior, currently %BIOSET_NEED_BVECS
+ *              and %BIOSET_NEED_RESCUER
+ *
+ * Description:
+ *    Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
+ *    to ask for a number of bytes to be allocated in front of the bio.
+ *    Front pad allocation is useful for embedding the bio inside
+ *    another structure, to avoid allocating extra data to go with the bio.
+ *    Note that the bio must be embedded at the END of that structure always,
+ *    or things will break badly.
+ *    If %BIOSET_NEED_BVECS is set in @flags, a separate pool will be allocated
+ *    for allocating iovecs.  This pool is not needed e.g. for bio_clone_fast().
+ *    If %BIOSET_NEED_RESCUER is set, a workqueue is created which can be used to
+ *    dispatch queued requests when the mempool runs out of space.
+ *
+ */
+struct bio_set *bioset_create(unsigned int pool_size,
+			      unsigned int front_pad,
+			      int flags)
 {
 	unsigned int back_pad = BIO_INLINE_VECS * sizeof(struct bio_vec);
 	struct bio_set *bs;
@@ -1954,12 +1979,15 @@ static struct bio_set *__bioset_create(unsigned int pool_size,
 	if (!bs->bio_pool)
 		goto bad;
 
-	if (create_bvec_pool) {
+	if (flags & BIOSET_NEED_BVECS) {
 		bs->bvec_pool = biovec_create_pool(pool_size);
 		if (!bs->bvec_pool)
 			goto bad;
 	}
 
+	if (!(flags & BIOSET_NEED_RESCUER))
+		return bs;
+
 	bs->rescue_workqueue = alloc_workqueue("bioset", WQ_MEM_RECLAIM, 0);
 	if (!bs->rescue_workqueue)
 		goto bad;
@@ -1969,41 +1997,8 @@ bad:
 	bioset_free(bs);
 	return NULL;
 }
-
-/**
- * bioset_create  - Create a bio_set
- * @pool_size:	Number of bio and bio_vecs to cache in the mempool
- * @front_pad:	Number of bytes to allocate in front of the returned bio
- *
- * Description:
- *    Set up a bio_set to be used with @bio_alloc_bioset. Allows the caller
- *    to ask for a number of bytes to be allocated in front of the bio.
- *    Front pad allocation is useful for embedding the bio inside
- *    another structure, to avoid allocating extra data to go with the bio.
- *    Note that the bio must be embedded at the END of that structure always,
- *    or things will break badly.
- */
-struct bio_set *bioset_create(unsigned int pool_size, unsigned int front_pad)
-{
-	return __bioset_create(pool_size, front_pad, true);
-}
 EXPORT_SYMBOL(bioset_create);
 
-/**
- * bioset_create_nobvec  - Create a bio_set without bio_vec mempool
- * @pool_size:	Number of bio to cache in the mempool
- * @front_pad:	Number of bytes to allocate in front of the returned bio
- *
- * Description:
- *    Same functionality as bioset_create() except that mempool is not
- *    created for bio_vecs. Saving some memory for bio_clone_fast() users.
- */
-struct bio_set *bioset_create_nobvec(unsigned int pool_size, unsigned int front_pad)
-{
-	return __bioset_create(pool_size, front_pad, false);
-}
-EXPORT_SYMBOL(bioset_create_nobvec);
-
 #ifdef CONFIG_BLK_CGROUP
 
 /**
@@ -2118,7 +2113,7 @@ static int __init init_bio(void)
 	bio_integrity_init();
 	biovec_init_slabs();
 
-	fs_bio_set = bioset_create(BIO_POOL_SIZE, 0);
+	fs_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
 	if (!fs_bio_set)
 		panic("bio: can't allocate bios\n");
 

block/blk-core.c

@@ -129,11 +129,70 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 }
 EXPORT_SYMBOL(blk_rq_init);
 
+static const struct {
+	int		errno;
+	const char	*name;
+} blk_errors[] = {
+	[BLK_STS_OK]		= { 0,		"" },
+	[BLK_STS_NOTSUPP]	= { -EOPNOTSUPP, "operation not supported" },
+	[BLK_STS_TIMEOUT]	= { -ETIMEDOUT,	"timeout" },
+	[BLK_STS_NOSPC]		= { -ENOSPC,	"critical space allocation" },
+	[BLK_STS_TRANSPORT]	= { -ENOLINK,	"recoverable transport" },
+	[BLK_STS_TARGET]	= { -EREMOTEIO,	"critical target" },
+	[BLK_STS_NEXUS]		= { -EBADE,	"critical nexus" },
+	[BLK_STS_MEDIUM]	= { -ENODATA,	"critical medium" },
+	[BLK_STS_PROTECTION]	= { -EILSEQ,	"protection" },
+	[BLK_STS_RESOURCE]	= { -ENOMEM,	"kernel resource" },
+	[BLK_STS_AGAIN]		= { -EAGAIN,	"nonblocking retry" },
+
+	/* device mapper special case, should not leak out: */
+	[BLK_STS_DM_REQUEUE]	= { -EREMCHG, "dm internal retry" },
+
+	/* everything else not covered above: */
+	[BLK_STS_IOERR]		= { -EIO,	"I/O" },
+};
+
+blk_status_t errno_to_blk_status(int errno)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(blk_errors); i++) {
+		if (blk_errors[i].errno == errno)
+			return (__force blk_status_t)i;
+	}
+
+	return BLK_STS_IOERR;
+}
+EXPORT_SYMBOL_GPL(errno_to_blk_status);
+
+int blk_status_to_errno(blk_status_t status)
+{
+	int idx = (__force int)status;
+
+	if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors)))
+		return -EIO;
+	return blk_errors[idx].errno;
+}
+EXPORT_SYMBOL_GPL(blk_status_to_errno);
+
+static void print_req_error(struct request *req, blk_status_t status)
+{
+	int idx = (__force int)status;
+
+	if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors)))
+		return;
+
+	printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu\n",
+			   __func__, blk_errors[idx].name, req->rq_disk ?
+			   req->rq_disk->disk_name : "?",
+			   (unsigned long long)blk_rq_pos(req));
+}
+
 static void req_bio_endio(struct request *rq, struct bio *bio,
-			  unsigned int nbytes, int error)
+			  unsigned int nbytes, blk_status_t error)
 {
 	if (error)
-		bio->bi_error = error;
+		bio->bi_status = error;
 
 	if (unlikely(rq->rq_flags & RQF_QUIET))
 		bio_set_flag(bio, BIO_QUIET);
@@ -177,10 +236,13 @@ static void blk_delay_work(struct work_struct *work)
  * Description:
  *   Sometimes queueing needs to be postponed for a little while, to allow
  *   resources to come back. This function will make sure that queueing is
- *   restarted around the specified time. Queue lock must be held.
+ *   restarted around the specified time.
  */
 void blk_delay_queue(struct request_queue *q, unsigned long msecs)
 {
+	lockdep_assert_held(q->queue_lock);
+	WARN_ON_ONCE(q->mq_ops);
+
 	if (likely(!blk_queue_dead(q)))
 		queue_delayed_work(kblockd_workqueue, &q->delay_work,
 				   msecs_to_jiffies(msecs));
@@ -198,6 +260,9 @@ EXPORT_SYMBOL(blk_delay_queue);
  **/
 void blk_start_queue_async(struct request_queue *q)
 {
+	lockdep_assert_held(q->queue_lock);
+	WARN_ON_ONCE(q->mq_ops);
+
 	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
 	blk_run_queue_async(q);
 }
@@ -210,11 +275,13 @@ EXPORT_SYMBOL(blk_start_queue_async);
  * Description:
  *   blk_start_queue() will clear the stop flag on the queue, and call
  *   the request_fn for the queue if it was in a stopped state when
- *   entered. Also see blk_stop_queue(). Queue lock must be held.
+ *   entered. Also see blk_stop_queue().
  **/
 void blk_start_queue(struct request_queue *q)
 {
+	lockdep_assert_held(q->queue_lock);
 	WARN_ON(!irqs_disabled());
+	WARN_ON_ONCE(q->mq_ops);
 
 	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
 	__blk_run_queue(q);
@@ -233,10 +300,13 @@ EXPORT_SYMBOL(blk_start_queue);
  *   or if it simply chooses not to queue more I/O at one point, it can
  *   call this function to prevent the request_fn from being called until
  *   the driver has signalled it's ready to go again. This happens by calling
- *   blk_start_queue() to restart queue operations. Queue lock must be held.
+ *   blk_start_queue() to restart queue operations.
  **/
 void blk_stop_queue(struct request_queue *q)
 {
+	lockdep_assert_held(q->queue_lock);
+	WARN_ON_ONCE(q->mq_ops);
+
 	cancel_delayed_work(&q->delay_work);
 	queue_flag_set(QUEUE_FLAG_STOPPED, q);
 }
@@ -289,6 +359,9 @@ EXPORT_SYMBOL(blk_sync_queue);
  */
 inline void __blk_run_queue_uncond(struct request_queue *q)
 {
+	lockdep_assert_held(q->queue_lock);
+	WARN_ON_ONCE(q->mq_ops);
+
 	if (unlikely(blk_queue_dead(q)))
 		return;
 
@@ -310,11 +383,13 @@ EXPORT_SYMBOL_GPL(__blk_run_queue_uncond);
  * @q:	The queue to run
  *
  * Description:
- *    See @blk_run_queue. This variant must be called with the queue lock
- *    held and interrupts disabled.
+ *    See @blk_run_queue.
  */
 void __blk_run_queue(struct request_queue *q)
 {
+	lockdep_assert_held(q->queue_lock);
+	WARN_ON_ONCE(q->mq_ops);
+
 	if (unlikely(blk_queue_stopped(q)))
 		return;
 
@@ -328,10 +403,18 @@ EXPORT_SYMBOL(__blk_run_queue);
  *
  * Description:
  *    Tells kblockd to perform the equivalent of @blk_run_queue on behalf
- *    of us. The caller must hold the queue lock.
+ *    of us.
+ *
+ * Note:
+ *    Since it is not allowed to run q->delay_work after blk_cleanup_queue()
+ *    has canceled q->delay_work, callers must hold the queue lock to avoid
+ *    race conditions between blk_cleanup_queue() and blk_run_queue_async().
  */
 void blk_run_queue_async(struct request_queue *q)
 {
+	lockdep_assert_held(q->queue_lock);
+	WARN_ON_ONCE(q->mq_ops);
+
 	if (likely(!blk_queue_stopped(q) && !blk_queue_dead(q)))
 		mod_delayed_work(kblockd_workqueue, &q->delay_work, 0);
 }
@@ -349,6 +432,8 @@ void blk_run_queue(struct request_queue *q)
 {
 	unsigned long flags;
 
+	WARN_ON_ONCE(q->mq_ops);
+
 	spin_lock_irqsave(q->queue_lock, flags);
 	__blk_run_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
@@ -377,6 +462,7 @@ static void __blk_drain_queue(struct request_queue *q, bool drain_all)
 	int i;
 
 	lockdep_assert_held(q->queue_lock);
+	WARN_ON_ONCE(q->mq_ops);
 
 	while (true) {
 		bool drain = false;
@@ -455,6 +541,8 @@ static void __blk_drain_queue(struct request_queue *q, bool drain_all)
  */
 void blk_queue_bypass_start(struct request_queue *q)
 {
+	WARN_ON_ONCE(q->mq_ops);
+
 	spin_lock_irq(q->queue_lock);
 	q->bypass_depth++;
 	queue_flag_set(QUEUE_FLAG_BYPASS, q);
@@ -481,6 +569,9 @@ EXPORT_SYMBOL_GPL(blk_queue_bypass_start);
  * @q: queue of interest
  *
  * Leave bypass mode and restore the normal queueing behavior.
+ *
+ * Note: although blk_queue_bypass_start() is only called for blk-sq queues,
+ * this function is called for both blk-sq and blk-mq queues.
  */
 void blk_queue_bypass_end(struct request_queue *q)
 {
@@ -732,7 +823,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	if (q->id < 0)
 		goto fail_q;
 
-	q->bio_split = bioset_create(BIO_POOL_SIZE, 0);
+	q->bio_split = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
 	if (!q->bio_split)
 		goto fail_id;
 
@@ -878,6 +969,8 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio);
 
 int blk_init_allocated_queue(struct request_queue *q)
 {
+	WARN_ON_ONCE(q->mq_ops);
+
 	q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, q->cmd_size);
 	if (!q->fq)
 		return -ENOMEM;
@@ -1015,6 +1108,8 @@ int blk_update_nr_requests(struct request_queue *q, unsigned int nr)
 	struct request_list *rl;
 	int on_thresh, off_thresh;
 
+	WARN_ON_ONCE(q->mq_ops);
+
 	spin_lock_irq(q->queue_lock);
 	q->nr_requests = nr;
 	blk_queue_congestion_threshold(q);
@@ -1077,6 +1172,8 @@ static struct request *__get_request(struct request_list *rl, unsigned int op,
 	int may_queue;
 	req_flags_t rq_flags = RQF_ALLOCED;
 
+	lockdep_assert_held(q->queue_lock);
+
 	if (unlikely(blk_queue_dying(q)))
 		return ERR_PTR(-ENODEV);
 
@@ -1250,12 +1347,20 @@ static struct request *get_request(struct request_queue *q, unsigned int op,
 	struct request_list *rl;
 	struct request *rq;
 
+	lockdep_assert_held(q->queue_lock);
+	WARN_ON_ONCE(q->mq_ops);
+
 	rl = blk_get_rl(q, bio);	/* transferred to @rq on success */
 retry:
 	rq = __get_request(rl, op, bio, gfp_mask);
 	if (!IS_ERR(rq))
 		return rq;
 
+	if (op & REQ_NOWAIT) {
+		blk_put_rl(rl);
+		return ERR_PTR(-EAGAIN);
+	}
+
 	if (!gfpflags_allow_blocking(gfp_mask) || unlikely(blk_queue_dying(q))) {
 		blk_put_rl(rl);
 		return rq;
@@ -1283,16 +1388,18 @@ retry:
 	goto retry;
 }
 
-static struct request *blk_old_get_request(struct request_queue *q, int rw,
-		gfp_t gfp_mask)
+static struct request *blk_old_get_request(struct request_queue *q,
+					   unsigned int op, gfp_t gfp_mask)
 {
 	struct request *rq;
 
+	WARN_ON_ONCE(q->mq_ops);
+
 	/* create ioc upfront */
 	create_io_context(gfp_mask, q->node);
 
 	spin_lock_irq(q->queue_lock);
-	rq = get_request(q, rw, NULL, gfp_mask);
+	rq = get_request(q, op, NULL, gfp_mask);
 	if (IS_ERR(rq)) {
 		spin_unlock_irq(q->queue_lock);
 		return rq;
@@ -1305,14 +1412,24 @@ static struct request *blk_old_get_request(struct request_queue *q, int rw,
 	return rq;
 }
 
-struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
+struct request *blk_get_request(struct request_queue *q, unsigned int op,
+				gfp_t gfp_mask)
 {
-	if (q->mq_ops)
-		return blk_mq_alloc_request(q, rw,
+	struct request *req;
+
+	if (q->mq_ops) {
+		req = blk_mq_alloc_request(q, op,
 			(gfp_mask & __GFP_DIRECT_RECLAIM) ?
 				0 : BLK_MQ_REQ_NOWAIT);
-	else
-		return blk_old_get_request(q, rw, gfp_mask);
+		if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn)
+			q->mq_ops->initialize_rq_fn(req);
+	} else {
+		req = blk_old_get_request(q, op, gfp_mask);
+		if (!IS_ERR(req) && q->initialize_rq_fn)
+			q->initialize_rq_fn(req);
+	}
+
+	return req;
 }
 EXPORT_SYMBOL(blk_get_request);
 
@@ -1328,6 +1445,9 @@ EXPORT_SYMBOL(blk_get_request);
  */
 void blk_requeue_request(struct request_queue *q, struct request *rq)
 {
+	lockdep_assert_held(q->queue_lock);
+	WARN_ON_ONCE(q->mq_ops);
+
 	blk_delete_timer(rq);
 	blk_clear_rq_complete(rq);
 	trace_block_rq_requeue(q, rq);
@@ -1402,9 +1522,6 @@ static void blk_pm_put_request(struct request *rq)
 static inline void blk_pm_put_request(struct request *rq) {}
 #endif
 
-/*
- * queue lock must be held
- */
 void __blk_put_request(struct request_queue *q, struct request *req)
 {
 	req_flags_t rq_flags = req->rq_flags;
@@ -1417,6 +1534,8 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 		return;
 	}
 
+	lockdep_assert_held(q->queue_lock);
+
 	blk_pm_put_request(req);
 
 	elv_completed_request(q, req);
@@ -1646,6 +1765,7 @@ void blk_init_request_from_bio(struct request *req, struct bio *bio)
 		req->ioprio = ioc->ioprio;
 	else
 		req->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
+	req->write_hint = bio->bi_write_hint;
 	blk_rq_bio_prep(req->q, req, bio);
 }
 EXPORT_SYMBOL_GPL(blk_init_request_from_bio);
@@ -1665,10 +1785,10 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 	 */
 	blk_queue_bounce(q, &bio);
 
-	blk_queue_split(q, &bio, q->bio_split);
+	blk_queue_split(q, &bio);
 
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
-		bio->bi_error = -EIO;
+		bio->bi_status = BLK_STS_IOERR;
 		bio_endio(bio);
 		return BLK_QC_T_NONE;
 	}
@@ -1726,7 +1846,10 @@ get_rq:
 	req = get_request(q, bio->bi_opf, bio, GFP_NOIO);
 	if (IS_ERR(req)) {
 		__wbt_done(q->rq_wb, wb_acct);
-		bio->bi_error = PTR_ERR(req);
+		if (PTR_ERR(req) == -ENOMEM)
+			bio->bi_status = BLK_STS_RESOURCE;
+		else
+			bio->bi_status = BLK_STS_IOERR;
 		bio_endio(bio);
 		goto out_unlock;
 	}
@@ -1881,7 +2004,7 @@ generic_make_request_checks(struct bio *bio)
 {
 	struct request_queue *q;
 	int nr_sectors = bio_sectors(bio);
-	int err = -EIO;
+	blk_status_t status = BLK_STS_IOERR;
 	char b[BDEVNAME_SIZE];
 	struct hd_struct *part;
 
@@ -1900,6 +2023,14 @@ generic_make_request_checks(struct bio *bio)
 		goto end_io;
 	}
 
+	/*
+	 * For a REQ_NOWAIT based request, return -EOPNOTSUPP
+	 * if queue is not a request based queue.
+	 */
+
+	if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_rq_based(q))
+		goto not_supported;
+
 	part = bio->bi_bdev->bd_part;
 	if (should_fail_request(part, bio->bi_iter.bi_size) ||
 	    should_fail_request(&part_to_disk(part)->part0,
@@ -1924,7 +2055,7 @@ generic_make_request_checks(struct bio *bio)
 	    !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
 		bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA);
 		if (!nr_sectors) {
-			err = 0;
+			status = BLK_STS_OK;
 			goto end_io;
 		}
 	}
@@ -1976,9 +2107,9 @@ generic_make_request_checks(struct bio *bio)
 	return true;
 
 not_supported:
-	err = -EOPNOTSUPP;
+	status = BLK_STS_NOTSUPP;
 end_io:
-	bio->bi_error = err;
+	bio->bi_status = status;
 	bio_endio(bio);
 	return false;
 }
@@ -2057,7 +2188,7 @@ blk_qc_t generic_make_request(struct bio *bio)
 	do {
 		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 
-		if (likely(blk_queue_enter(q, false) == 0)) {
+		if (likely(blk_queue_enter(q, bio->bi_opf & REQ_NOWAIT) == 0)) {
 			struct bio_list lower, same;
 
 			/* Create a fresh bio_list for all subordinate requests */
@@ -2082,7 +2213,11 @@ blk_qc_t generic_make_request(struct bio *bio)
 			bio_list_merge(&bio_list_on_stack[0], &same);
 			bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]);
 		} else {
-			bio_io_error(bio);
+			if (unlikely(!blk_queue_dying(q) &&
+					(bio->bi_opf & REQ_NOWAIT)))
+				bio_wouldblock_error(bio);
+			else
+				bio_io_error(bio);
 		}
 		bio = bio_list_pop(&bio_list_on_stack[0]);
 	} while (bio);
@@ -2183,29 +2318,29 @@ static int blk_cloned_rq_check_limits(struct request_queue *q,
  * @q:  the queue to submit the request
  * @rq: the request being queued
  */
-int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
+blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 {
 	unsigned long flags;
 	int where = ELEVATOR_INSERT_BACK;
 
 	if (blk_cloned_rq_check_limits(q, rq))
-		return -EIO;
+		return BLK_STS_IOERR;
 
 	if (rq->rq_disk &&
 	    should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq)))
-		return -EIO;
+		return BLK_STS_IOERR;
 
 	if (q->mq_ops) {
 		if (blk_queue_io_stat(q))
 			blk_account_io_start(rq, true);
 		blk_mq_sched_insert_request(rq, false, true, false, false);
-		return 0;
+		return BLK_STS_OK;
 	}
 
 	spin_lock_irqsave(q->queue_lock, flags);
 	if (unlikely(blk_queue_dying(q))) {
 		spin_unlock_irqrestore(q->queue_lock, flags);
-		return -ENODEV;
+		return BLK_STS_IOERR;
 	}
 
 	/*
@@ -2222,7 +2357,7 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 		__blk_run_queue(q);
 	spin_unlock_irqrestore(q->queue_lock, flags);
 
-	return 0;
+	return BLK_STS_OK;
 }
 EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
 
@@ -2238,9 +2373,6 @@ EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
  *
  * Return:
  *     The number of bytes to fail.
- *
- * Context:
- *     queue_lock must be held.
  */
 unsigned int blk_rq_err_bytes(const struct request *rq)
 {
@@ -2380,15 +2512,15 @@ void blk_account_io_start(struct request *rq, bool new_io)
  * Return:
  *     Pointer to the request at the top of @q if available.  Null
  *     otherwise.
- *
- * Context:
- *     queue_lock must be held.
  */
 struct request *blk_peek_request(struct request_queue *q)
 {
 	struct request *rq;
 	int ret;
 
+	lockdep_assert_held(q->queue_lock);
+	WARN_ON_ONCE(q->mq_ops);
+
 	while ((rq = __elv_next_request(q)) != NULL) {
 
 		rq = blk_pm_peek_request(q, rq);
@@ -2456,15 +2588,14 @@ struct request *blk_peek_request(struct request_queue *q)
 			rq = NULL;
 			break;
 		} else if (ret == BLKPREP_KILL || ret == BLKPREP_INVALID) {
-			int err = (ret == BLKPREP_INVALID) ? -EREMOTEIO : -EIO;
-
 			rq->rq_flags |= RQF_QUIET;
 			/*
 			 * Mark this request as started so we don't trigger
 			 * any debug logic in the end I/O path.
 			 */
 			blk_start_request(rq);
-			__blk_end_request_all(rq, err);
+			__blk_end_request_all(rq, ret == BLKPREP_INVALID ?
+					BLK_STS_TARGET : BLK_STS_IOERR);
 		} else {
 			printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
 			break;
@@ -2505,12 +2636,12 @@ void blk_dequeue_request(struct request *rq)
  *
  *     Block internal functions which don't want to start timer should
  *     call blk_dequeue_request().
- *
- * Context:
- *     queue_lock must be held.
  */
 void blk_start_request(struct request *req)
 {
+	lockdep_assert_held(req->q->queue_lock);
+	WARN_ON_ONCE(req->q->mq_ops);
+
 	blk_dequeue_request(req);
 
 	if (test_bit(QUEUE_FLAG_STATS, &req->q->queue_flags)) {
@@ -2535,14 +2666,14 @@ EXPORT_SYMBOL(blk_start_request);
  * Return:
  *     Pointer to the request at the top of @q if available.  Null
  *     otherwise.
- *
- * Context:
- *     queue_lock must be held.
  */
 struct request *blk_fetch_request(struct request_queue *q)
 {
 	struct request *rq;
 
+	lockdep_assert_held(q->queue_lock);
+	WARN_ON_ONCE(q->mq_ops);
+
 	rq = blk_peek_request(q);
 	if (rq)
 		blk_start_request(rq);
@@ -2553,7 +2684,7 @@ EXPORT_SYMBOL(blk_fetch_request);
 /**
  * blk_update_request - Special helper function for request stacking drivers
  * @req:      the request being processed
- * @error:    %0 for success, < %0 for error
+ * @error:    block status code
  * @nr_bytes: number of bytes to complete @req
  *
  * Description:
@@ -2572,49 +2703,19 @@ EXPORT_SYMBOL(blk_fetch_request);
  *     %false - this request doesn't have any more data
  *     %true  - this request has more data
  **/
-bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
+bool blk_update_request(struct request *req, blk_status_t error,
+		unsigned int nr_bytes)
 {
 	int total_bytes;
 
-	trace_block_rq_complete(req, error, nr_bytes);
+	trace_block_rq_complete(req, blk_status_to_errno(error), nr_bytes);
 
 	if (!req->bio)
 		return false;
 
-	if (error && !blk_rq_is_passthrough(req) &&
-	    !(req->rq_flags & RQF_QUIET)) {
-		char *error_type;
-
-		switch (error) {
-		case -ENOLINK:
-			error_type = "recoverable transport";
-			break;
-		case -EREMOTEIO:
-			error_type = "critical target";
-			break;
-		case -EBADE:
-			error_type = "critical nexus";
-			break;
-		case -ETIMEDOUT:
-			error_type = "timeout";
-			break;
-		case -ENOSPC:
-			error_type = "critical space allocation";
-			break;
-		case -ENODATA:
-			error_type = "critical medium";
-			break;
-		case -EIO:
-		default:
-			error_type = "I/O";
-			break;
-		}
-		printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu\n",
-				   __func__, error_type, req->rq_disk ?
-				   req->rq_disk->disk_name : "?",
-				   (unsigned long long)blk_rq_pos(req));
-
-	}
+	if (unlikely(error && !blk_rq_is_passthrough(req) &&
+		     !(req->rq_flags & RQF_QUIET)))
+		print_req_error(req, error);
 
 	blk_account_io_completion(req, nr_bytes);
 
@@ -2680,7 +2781,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
 }
 EXPORT_SYMBOL_GPL(blk_update_request);
 
-static bool blk_update_bidi_request(struct request *rq, int error,
+static bool blk_update_bidi_request(struct request *rq, blk_status_t error,
 				    unsigned int nr_bytes,
 				    unsigned int bidi_bytes)
 {
@@ -2718,13 +2819,13 @@ void blk_unprep_request(struct request *req)
 }
 EXPORT_SYMBOL_GPL(blk_unprep_request);
 
-/*
- * queue lock must be held
- */
-void blk_finish_request(struct request *req, int error)
+void blk_finish_request(struct request *req, blk_status_t error)
 {
 	struct request_queue *q = req->q;
 
+	lockdep_assert_held(req->q->queue_lock);
+	WARN_ON_ONCE(q->mq_ops);
+
 	if (req->rq_flags & RQF_STATS)
 		blk_stat_add(req);
 
@@ -2758,7 +2859,7 @@ EXPORT_SYMBOL(blk_finish_request);
 /**
  * blk_end_bidi_request - Complete a bidi request
  * @rq:         the request to complete
- * @error:      %0 for success, < %0 for error
+ * @error:      block status code
  * @nr_bytes:   number of bytes to complete @rq
  * @bidi_bytes: number of bytes to complete @rq->next_rq
  *
@@ -2772,12 +2873,14 @@ EXPORT_SYMBOL(blk_finish_request);
  *     %false - we are done with this request
  *     %true  - still buffers pending for this request
  **/
-static bool blk_end_bidi_request(struct request *rq, int error,
+static bool blk_end_bidi_request(struct request *rq, blk_status_t error,
 				 unsigned int nr_bytes, unsigned int bidi_bytes)
 {
 	struct request_queue *q = rq->q;
 	unsigned long flags;
 
+	WARN_ON_ONCE(q->mq_ops);
+
 	if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
 		return true;
 
@@ -2791,7 +2894,7 @@ static bool blk_end_bidi_request(struct request *rq, int error,
 /**
  * __blk_end_bidi_request - Complete a bidi request with queue lock held
  * @rq:         the request to complete
- * @error:      %0 for success, < %0 for error
+ * @error:      block status code
  * @nr_bytes:   number of bytes to complete @rq
  * @bidi_bytes: number of bytes to complete @rq->next_rq
  *
@@ -2803,9 +2906,12 @@ static bool blk_end_bidi_request(struct request *rq, int error,
  *     %false - we are done with this request
  *     %true  - still buffers pending for this request
  **/
-static bool __blk_end_bidi_request(struct request *rq, int error,
+static bool __blk_end_bidi_request(struct request *rq, blk_status_t error,
 				   unsigned int nr_bytes, unsigned int bidi_bytes)
 {
+	lockdep_assert_held(rq->q->queue_lock);
+	WARN_ON_ONCE(rq->q->mq_ops);
+
 	if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
 		return true;
 
@@ -2817,7 +2923,7 @@ static bool __blk_end_bidi_request(struct request *rq, int error,
 /**
  * blk_end_request - Helper function for drivers to complete the request.
  * @rq:       the request being processed
- * @error:    %0 for success, < %0 for error
+ * @error:    block status code
  * @nr_bytes: number of bytes to complete
  *
  * Description:
@@ -2828,8 +2934,10 @@ static bool __blk_end_bidi_request(struct request *rq, int error,
  *     %false - we are done with this request
  *     %true  - still buffers pending for this request
  **/
-bool blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
+bool blk_end_request(struct request *rq, blk_status_t error,
+		unsigned int nr_bytes)
 {
+	WARN_ON_ONCE(rq->q->mq_ops);
 	return blk_end_bidi_request(rq, error, nr_bytes, 0);
 }
 EXPORT_SYMBOL(blk_end_request);
@@ -2837,12 +2945,12 @@ EXPORT_SYMBOL(blk_end_request);
 /**
  * blk_end_request_all - Helper function for drives to finish the request.
  * @rq: the request to finish
- * @error: %0 for success, < %0 for error
+ * @error: block status code
  *
  * Description:
  *     Completely finish @rq.
  */
-void blk_end_request_all(struct request *rq, int error)
+void blk_end_request_all(struct request *rq, blk_status_t error)
 {
 	bool pending;
 	unsigned int bidi_bytes = 0;
@@ -2858,7 +2966,7 @@ EXPORT_SYMBOL(blk_end_request_all);
 /**
  * __blk_end_request - Helper function for drivers to complete the request.
  * @rq:       the request being processed
- * @error:    %0 for success, < %0 for error
+ * @error:    block status code
  * @nr_bytes: number of bytes to complete
  *
  * Description:
@@ -2868,8 +2976,12 @@ EXPORT_SYMBOL(blk_end_request_all);
  *     %false - we are done with this request
  *     %true  - still buffers pending for this request
  **/
-bool __blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
+bool __blk_end_request(struct request *rq, blk_status_t error,
+		unsigned int nr_bytes)
 {
+	lockdep_assert_held(rq->q->queue_lock);
+	WARN_ON_ONCE(rq->q->mq_ops);
+
 	return __blk_end_bidi_request(rq, error, nr_bytes, 0);
 }
 EXPORT_SYMBOL(__blk_end_request);
@@ -2877,16 +2989,19 @@ EXPORT_SYMBOL(__blk_end_request);
 /**
  * __blk_end_request_all - Helper function for drives to finish the request.
  * @rq: the request to finish
- * @error: %0 for success, < %0 for error
+ * @error:    block status code
  *
  * Description:
  *     Completely finish @rq.  Must be called with queue lock held.
  */
-void __blk_end_request_all(struct request *rq, int error)
+void __blk_end_request_all(struct request *rq, blk_status_t error)
 {
 	bool pending;
 	unsigned int bidi_bytes = 0;
 
+	lockdep_assert_held(rq->q->queue_lock);
+	WARN_ON_ONCE(rq->q->mq_ops);
+
 	if (unlikely(blk_bidi_rq(rq)))
 		bidi_bytes = blk_rq_bytes(rq->next_rq);
 
@@ -2898,7 +3013,7 @@ EXPORT_SYMBOL(__blk_end_request_all);
 /**
  * __blk_end_request_cur - Helper function to finish the current request chunk.
  * @rq: the request to finish the current chunk for
- * @error: %0 for success, < %0 for error
+ * @error:    block status code
  *
  * Description:
  *     Complete the current consecutively mapped chunk from @rq.  Must
@@ -2908,7 +3023,7 @@ EXPORT_SYMBOL(__blk_end_request_all);
  *     %false - we are done with this request
  *     %true  - still buffers pending for this request
  */
-bool __blk_end_request_cur(struct request *rq, int error)
+bool __blk_end_request_cur(struct request *rq, blk_status_t error)
 {
 	return __blk_end_request(rq, error, blk_rq_cur_bytes(rq));
 }
@@ -3151,6 +3266,8 @@ static void queue_unplugged(struct request_queue *q, unsigned int depth,
 			    bool from_schedule)
 	__releases(q->queue_lock)
 {
+	lockdep_assert_held(q->queue_lock);
+
 	trace_block_unplug(q, depth, !from_schedule);
 
 	if (from_schedule)
@@ -3249,7 +3366,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		 * Short-circuit if @q is dead
 		 */
 		if (unlikely(blk_queue_dying(q))) {
-			__blk_end_request_all(rq, -ENODEV);
+			__blk_end_request_all(rq, BLK_STS_IOERR);
 			continue;
 		}
 

block/blk-exec.c

@@ -16,7 +16,7 @@
  * @rq: request to complete
  * @error: end I/O status of the request
  */
-static void blk_end_sync_rq(struct request *rq, int error)
+static void blk_end_sync_rq(struct request *rq, blk_status_t error)
 {
 	struct completion *waiting = rq->end_io_data;
 
@@ -69,7 +69,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 
 	if (unlikely(blk_queue_dying(q))) {
 		rq->rq_flags |= RQF_QUIET;
-		__blk_end_request_all(rq, -ENXIO);
+		__blk_end_request_all(rq, BLK_STS_IOERR);
 		spin_unlock_irq(q->queue_lock);
 		return;
 	}

block/blk-flush.c

@@ -164,7 +164,7 @@ static bool blk_flush_queue_rq(struct request *rq, bool add_front)
  */
 static bool blk_flush_complete_seq(struct request *rq,
 				   struct blk_flush_queue *fq,
-				   unsigned int seq, int error)
+				   unsigned int seq, blk_status_t error)
 {
 	struct request_queue *q = rq->q;
 	struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx];
@@ -216,7 +216,7 @@ static bool blk_flush_complete_seq(struct request *rq,
 	return kicked | queued;
 }
 
-static void flush_end_io(struct request *flush_rq, int error)
+static void flush_end_io(struct request *flush_rq, blk_status_t error)
 {
 	struct request_queue *q = flush_rq->q;
 	struct list_head *running;
@@ -341,11 +341,13 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq)
 	return blk_flush_queue_rq(flush_rq, false);
 }
 
-static void flush_data_end_io(struct request *rq, int error)
+static void flush_data_end_io(struct request *rq, blk_status_t error)
 {
 	struct request_queue *q = rq->q;
 	struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);
 
+	lockdep_assert_held(q->queue_lock);
+
 	/*
 	 * Updating q->in_flight[] here for making this tag usable
 	 * early. Because in blk_queue_start_tag(),
@@ -382,7 +384,7 @@ static void flush_data_end_io(struct request *rq, int error)
 		blk_run_queue_async(q);
 }
 
-static void mq_flush_data_end_io(struct request *rq, int error)
+static void mq_flush_data_end_io(struct request *rq, blk_status_t error)
 {
 	struct request_queue *q = rq->q;
 	struct blk_mq_hw_ctx *hctx;
@@ -411,9 +413,6 @@ static void mq_flush_data_end_io(struct request *rq, int error)
  * or __blk_mq_run_hw_queue() to dispatch request.
  * @rq is being submitted.  Analyze what needs to be done and put it on the
  * right queue.
- *
- * CONTEXT:
- * spin_lock_irq(q->queue_lock) in !mq case
  */
 void blk_insert_flush(struct request *rq)
 {
@@ -422,6 +421,9 @@ void blk_insert_flush(struct request *rq)
 	unsigned int policy = blk_flush_policy(fflags, rq);
 	struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx);
 
+	if (!q->mq_ops)
+		lockdep_assert_held(q->queue_lock);
+
 	/*
 	 * @policy now records what operations need to be done.  Adjust
 	 * REQ_PREFLUSH and FUA for the driver.

block/blk-integrity.c

@@ -384,9 +384,9 @@ static struct kobj_type integrity_ktype = {
 	.sysfs_ops	= &integrity_ops,
 };
 
-static int blk_integrity_nop_fn(struct blk_integrity_iter *iter)
+static blk_status_t blk_integrity_nop_fn(struct blk_integrity_iter *iter)
 {
-	return 0;
+	return BLK_STS_OK;
 }
 
 static const struct blk_integrity_profile nop_profile = {

block/blk-map.c

@@ -16,6 +16,8 @@
  */
 int blk_rq_append_bio(struct request *rq, struct bio *bio)
 {
+	blk_queue_bounce(rq->q, &bio);
+
 	if (!rq->bio) {
 		blk_rq_bio_prep(rq->q, rq, bio);
 	} else {
@@ -72,15 +74,13 @@ static int __blk_rq_map_user_iov(struct request *rq,
 		map_data->offset += bio->bi_iter.bi_size;
 
 	orig_bio = bio;
-	blk_queue_bounce(q, &bio);
 
 	/*
 	 * We link the bounce buffer in and could have to traverse it
 	 * later so we have to get a ref to prevent it from being freed
 	 */
-	bio_get(bio);
-
 	ret = blk_rq_append_bio(rq, bio);
+	bio_get(bio);
 	if (ret) {
 		bio_endio(bio);
 		__blk_rq_unmap_user(orig_bio);
@@ -249,7 +249,6 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
 		return ret;
 	}
 
-	blk_queue_bounce(q, &rq->bio);
 	return 0;
 }
 EXPORT_SYMBOL(blk_rq_map_kern);

block/blk-merge.c

@@ -108,30 +108,8 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 	bool do_split = true;
 	struct bio *new = NULL;
 	const unsigned max_sectors = get_max_io_size(q, bio);
-	unsigned bvecs = 0;
 
 	bio_for_each_segment(bv, bio, iter) {
-		/*
-		 * With arbitrary bio size, the incoming bio may be very
-		 * big. We have to split the bio into small bios so that
-		 * each holds at most BIO_MAX_PAGES bvecs because
-		 * bio_clone() can fail to allocate big bvecs.
-		 *
-		 * It should have been better to apply the limit per
-		 * request queue in which bio_clone() is involved,
-		 * instead of globally. The biggest blocker is the
-		 * bio_clone() in bio bounce.
-		 *
-		 * If bio is splitted by this reason, we should have
-		 * allowed to continue bios merging, but don't do
-		 * that now for making the change simple.
-		 *
-		 * TODO: deal with bio bounce's bio_clone() gracefully
-		 * and convert the global limit into per-queue limit.
-		 */
-		if (bvecs++ >= BIO_MAX_PAGES)
-			goto split;
-
 		/*
 		 * If the queue doesn't support SG gaps and adding this
 		 * offset would create a gap, disallow it.
@@ -202,8 +180,7 @@ split:
 	return do_split ? new : NULL;
 }
 
-void blk_queue_split(struct request_queue *q, struct bio **bio,
-		     struct bio_set *bs)
+void blk_queue_split(struct request_queue *q, struct bio **bio)
 {
 	struct bio *split, *res;
 	unsigned nsegs;
@@ -211,13 +188,13 @@ void blk_queue_split(struct request_queue *q, struct bio **bio,
 	switch (bio_op(*bio)) {
 	case REQ_OP_DISCARD:
 	case REQ_OP_SECURE_ERASE:
-		split = blk_bio_discard_split(q, *bio, bs, &nsegs);
+		split = blk_bio_discard_split(q, *bio, q->bio_split, &nsegs);
 		break;
 	case REQ_OP_WRITE_ZEROES:
-		split = blk_bio_write_zeroes_split(q, *bio, bs, &nsegs);
+		split = blk_bio_write_zeroes_split(q, *bio, q->bio_split, &nsegs);
 		break;
 	case REQ_OP_WRITE_SAME:
-		split = blk_bio_write_same_split(q, *bio, bs, &nsegs);
+		split = blk_bio_write_same_split(q, *bio, q->bio_split, &nsegs);
 		break;
 	default:
 		split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs);
@@ -671,6 +648,9 @@ static void blk_account_io_merge(struct request *req)
 static struct request *attempt_merge(struct request_queue *q,
 				     struct request *req, struct request *next)
 {
+	if (!q->mq_ops)
+		lockdep_assert_held(q->queue_lock);
+
 	if (!rq_mergeable(req) || !rq_mergeable(next))
 		return NULL;
 
@@ -692,6 +672,13 @@ static struct request *attempt_merge(struct request_queue *q,
 	    !blk_write_same_mergeable(req->bio, next->bio))
 		return NULL;
 
+	/*
+	 * Don't allow merge of different write hints, or for a hint with
+	 * non-hint IO.
+	 */
+	if (req->write_hint != next->write_hint)
+		return NULL;
+
 	/*
 	 * If we are allowed to merge, then append bio list
 	 * from next to rq and release next. merge_requests_fn
@@ -811,6 +798,13 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	    !blk_write_same_mergeable(rq->bio, bio))
 		return false;
 
+	/*
+	 * Don't allow merge of different write hints, or for a hint with
+	 * non-hint IO.
+	 */
+	if (rq->write_hint != bio->bi_write_hint)
+		return false;
+
 	return true;
 }
 

block/blk-mq-cpumap.c

@@ -14,10 +14,15 @@
 #include "blk.h"
 #include "blk-mq.h"
 
-static int cpu_to_queue_index(unsigned int nr_cpus, unsigned int nr_queues,
-			      const int cpu)
+static int cpu_to_queue_index(unsigned int nr_queues, const int cpu,
+			      const struct cpumask *online_mask)
 {
-	return cpu * nr_queues / nr_cpus;
+	/*
+	 * Non online CPU will be mapped to queue index 0.
+	 */
+	if (!cpumask_test_cpu(cpu, online_mask))
+		return 0;
+	return cpu % nr_queues;
 }
 
 static int get_first_sibling(unsigned int cpu)
@@ -36,55 +41,26 @@ int blk_mq_map_queues(struct blk_mq_tag_set *set)
 	unsigned int *map = set->mq_map;
 	unsigned int nr_queues = set->nr_hw_queues;
 	const struct cpumask *online_mask = cpu_online_mask;
-	unsigned int i, nr_cpus, nr_uniq_cpus, queue, first_sibling;
-	cpumask_var_t cpus;
-
-	if (!alloc_cpumask_var(&cpus, GFP_ATOMIC))
-		return -ENOMEM;
-
-	cpumask_clear(cpus);
-	nr_cpus = nr_uniq_cpus = 0;
-	for_each_cpu(i, online_mask) {
-		nr_cpus++;
-		first_sibling = get_first_sibling(i);
-		if (!cpumask_test_cpu(first_sibling, cpus))
-			nr_uniq_cpus++;
-		cpumask_set_cpu(i, cpus);
-	}
-
-	queue = 0;
-	for_each_possible_cpu(i) {
-		if (!cpumask_test_cpu(i, online_mask)) {
-			map[i] = 0;
-			continue;
-		}
+	unsigned int cpu, first_sibling;
 
+	for_each_possible_cpu(cpu) {
 		/*
-		 * Easy case - we have equal or more hardware queues. Or
-		 * there are no thread siblings to take into account. Do
-		 * 1:1 if enough, or sequential mapping if less.
+		 * First do sequential mapping between CPUs and queues.
+		 * In case we still have CPUs to map, and we have some number of
+		 * threads per cores then map sibling threads to the same queue for
+		 * performace optimizations.
 		 */
-		if (nr_queues >= nr_cpus || nr_cpus == nr_uniq_cpus) {
-			map[i] = cpu_to_queue_index(nr_cpus, nr_queues, queue);
-			queue++;
-			continue;
+		if (cpu < nr_queues) {
+			map[cpu] = cpu_to_queue_index(nr_queues, cpu, online_mask);
+		} else {
+			first_sibling = get_first_sibling(cpu);
+			if (first_sibling == cpu)
+				map[cpu] = cpu_to_queue_index(nr_queues, cpu, online_mask);
+			else
+				map[cpu] = map[first_sibling];
 		}
-
-		/*
-		 * Less then nr_cpus queues, and we have some number of
-		 * threads per cores. Map sibling threads to the same
-		 * queue.
-		 */
-		first_sibling = get_first_sibling(i);
-		if (first_sibling == i) {
-			map[i] = cpu_to_queue_index(nr_uniq_cpus, nr_queues,
-							queue);
-			queue++;
-		} else
-			map[i] = map[first_sibling];
 	}
 
-	free_cpumask_var(cpus);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(blk_mq_map_queues);

block/blk-mq-debugfs.c

@@ -114,10 +114,12 @@ static ssize_t queue_state_write(void *data, const char __user *buf,
 		blk_mq_run_hw_queues(q, true);
 	} else if (strcmp(op, "start") == 0) {
 		blk_mq_start_stopped_hw_queues(q, true);
+	} else if (strcmp(op, "kick") == 0) {
+		blk_mq_kick_requeue_list(q);
 	} else {
 		pr_err("%s: unsupported operation '%s'\n", __func__, op);
 inval:
-		pr_err("%s: use either 'run' or 'start'\n", __func__);
+		pr_err("%s: use 'run', 'start' or 'kick'\n", __func__);
 		return -EINVAL;
 	}
 	return count;
@@ -133,6 +135,29 @@ static void print_stat(struct seq_file *m, struct blk_rq_stat *stat)
 	}
 }
 
+static int queue_write_hint_show(void *data, struct seq_file *m)
+{
+	struct request_queue *q = data;
+	int i;
+
+	for (i = 0; i < BLK_MAX_WRITE_HINTS; i++)
+		seq_printf(m, "hint%d: %llu\n", i, q->write_hints[i]);
+
+	return 0;
+}
+
+static ssize_t queue_write_hint_store(void *data, const char __user *buf,
+				      size_t count, loff_t *ppos)
+{
+	struct request_queue *q = data;
+	int i;
+
+	for (i = 0; i < BLK_MAX_WRITE_HINTS; i++)
+		q->write_hints[i] = 0;
+
+	return count;
+}
+
 static int queue_poll_stat_show(void *data, struct seq_file *m)
 {
 	struct request_queue *q = data;
@@ -267,6 +292,14 @@ static const char *const rqf_name[] = {
 };
 #undef RQF_NAME
 
+#define RQAF_NAME(name) [REQ_ATOM_##name] = #name
+static const char *const rqaf_name[] = {
+	RQAF_NAME(COMPLETE),
+	RQAF_NAME(STARTED),
+	RQAF_NAME(POLL_SLEPT),
+};
+#undef RQAF_NAME
+
 int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
 {
 	const struct blk_mq_ops *const mq_ops = rq->q->mq_ops;
@@ -283,6 +316,8 @@ int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
 	seq_puts(m, ", .rq_flags=");
 	blk_flags_show(m, (__force unsigned int)rq->rq_flags, rqf_name,
 		       ARRAY_SIZE(rqf_name));
+	seq_puts(m, ", .atomic_flags=");
+	blk_flags_show(m, rq->atomic_flags, rqaf_name, ARRAY_SIZE(rqaf_name));
 	seq_printf(m, ", .tag=%d, .internal_tag=%d", rq->tag,
 		   rq->internal_tag);
 	if (mq_ops->show_rq)
@@ -298,6 +333,37 @@ int blk_mq_debugfs_rq_show(struct seq_file *m, void *v)
 }
 EXPORT_SYMBOL_GPL(blk_mq_debugfs_rq_show);
 
+static void *queue_requeue_list_start(struct seq_file *m, loff_t *pos)
+	__acquires(&q->requeue_lock)
+{
+	struct request_queue *q = m->private;
+
+	spin_lock_irq(&q->requeue_lock);
+	return seq_list_start(&q->requeue_list, *pos);
+}
+
+static void *queue_requeue_list_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct request_queue *q = m->private;
+
+	return seq_list_next(v, &q->requeue_list, pos);
+}
+
+static void queue_requeue_list_stop(struct seq_file *m, void *v)
+	__releases(&q->requeue_lock)
+{
+	struct request_queue *q = m->private;
+
+	spin_unlock_irq(&q->requeue_lock);
+}
+
+static const struct seq_operations queue_requeue_list_seq_ops = {
+	.start	= queue_requeue_list_start,
+	.next	= queue_requeue_list_next,
+	.stop	= queue_requeue_list_stop,
+	.show	= blk_mq_debugfs_rq_show,
+};
+
 static void *hctx_dispatch_start(struct seq_file *m, loff_t *pos)
 	__acquires(&hctx->lock)
 {
@@ -329,6 +395,36 @@ static const struct seq_operations hctx_dispatch_seq_ops = {
 	.show	= blk_mq_debugfs_rq_show,
 };
 
+struct show_busy_params {
+	struct seq_file		*m;
+	struct blk_mq_hw_ctx	*hctx;
+};
+
+/*
+ * Note: the state of a request may change while this function is in progress,
+ * e.g. due to a concurrent blk_mq_finish_request() call.
+ */
+static void hctx_show_busy_rq(struct request *rq, void *data, bool reserved)
+{
+	const struct show_busy_params *params = data;
+
+	if (blk_mq_map_queue(rq->q, rq->mq_ctx->cpu) == params->hctx &&
+	    test_bit(REQ_ATOM_STARTED, &rq->atomic_flags))
+		__blk_mq_debugfs_rq_show(params->m,
+					 list_entry_rq(&rq->queuelist));
+}
+
+static int hctx_busy_show(void *data, struct seq_file *m)
+{
+	struct blk_mq_hw_ctx *hctx = data;
+	struct show_busy_params params = { .m = m, .hctx = hctx };
+
+	blk_mq_tagset_busy_iter(hctx->queue->tag_set, hctx_show_busy_rq,
+				&params);
+
+	return 0;
+}
+
 static int hctx_ctx_map_show(void *data, struct seq_file *m)
 {
 	struct blk_mq_hw_ctx *hctx = data;
@@ -655,7 +751,9 @@ const struct file_operations blk_mq_debugfs_fops = {
 
 static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
 	{"poll_stat", 0400, queue_poll_stat_show},
+	{"requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops},
 	{"state", 0600, queue_state_show, queue_state_write},
+	{"write_hints", 0600, queue_write_hint_show, queue_write_hint_store},
 	{},
 };
 
@@ -663,6 +761,7 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"state", 0400, hctx_state_show},
 	{"flags", 0400, hctx_flags_show},
 	{"dispatch", 0400, .seq_ops = &hctx_dispatch_seq_ops},
+	{"busy", 0400, hctx_busy_show},
 	{"ctx_map", 0400, hctx_ctx_map_show},
 	{"tags", 0400, hctx_tags_show},
 	{"tags_bitmap", 0400, hctx_tags_bitmap_show},

block/blk-mq-sched.c

@@ -31,11 +31,10 @@ void blk_mq_sched_free_hctx_data(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_free_hctx_data);
 
-static void __blk_mq_sched_assign_ioc(struct request_queue *q,
-				      struct request *rq,
-				      struct bio *bio,
-				      struct io_context *ioc)
+void blk_mq_sched_assign_ioc(struct request *rq, struct bio *bio)
 {
+	struct request_queue *q = rq->q;
+	struct io_context *ioc = rq_ioc(bio);
 	struct io_cq *icq;
 
 	spin_lock_irq(q->queue_lock);
@@ -47,25 +46,8 @@ static void __blk_mq_sched_assign_ioc(struct request_queue *q,
 		if (!icq)
 			return;
 	}
-
+	get_io_context(icq->ioc);
 	rq->elv.icq = icq;
-	if (!blk_mq_sched_get_rq_priv(q, rq, bio)) {
-		rq->rq_flags |= RQF_ELVPRIV;
-		get_io_context(icq->ioc);
-		return;
-	}
-
-	rq->elv.icq = NULL;
-}
-
-static void blk_mq_sched_assign_ioc(struct request_queue *q,
-				    struct request *rq, struct bio *bio)
-{
-	struct io_context *ioc;
-
-	ioc = rq_ioc(bio);
-	if (ioc)
-		__blk_mq_sched_assign_ioc(q, rq, bio, ioc);
 }
 
 /*
@@ -107,71 +89,6 @@ static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
 	return false;
 }
 
-struct request *blk_mq_sched_get_request(struct request_queue *q,
-					 struct bio *bio,
-					 unsigned int op,
-					 struct blk_mq_alloc_data *data)
-{
-	struct elevator_queue *e = q->elevator;
-	struct request *rq;
-
-	blk_queue_enter_live(q);
-	data->q = q;
-	if (likely(!data->ctx))
-		data->ctx = blk_mq_get_ctx(q);
-	if (likely(!data->hctx))
-		data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
-
-	if (e) {
-		data->flags |= BLK_MQ_REQ_INTERNAL;
-
-		/*
-		 * Flush requests are special and go directly to the
-		 * dispatch list.
-		 */
-		if (!op_is_flush(op) && e->type->ops.mq.get_request) {
-			rq = e->type->ops.mq.get_request(q, op, data);
-			if (rq)
-				rq->rq_flags |= RQF_QUEUED;
-		} else
-			rq = __blk_mq_alloc_request(data, op);
-	} else {
-		rq = __blk_mq_alloc_request(data, op);
-	}
-
-	if (rq) {
-		if (!op_is_flush(op)) {
-			rq->elv.icq = NULL;
-			if (e && e->type->icq_cache)
-				blk_mq_sched_assign_ioc(q, rq, bio);
-		}
-		data->hctx->queued++;
-		return rq;
-	}
-
-	blk_queue_exit(q);
-	return NULL;
-}
-
-void blk_mq_sched_put_request(struct request *rq)
-{
-	struct request_queue *q = rq->q;
-	struct elevator_queue *e = q->elevator;
-
-	if (rq->rq_flags & RQF_ELVPRIV) {
-		blk_mq_sched_put_rq_priv(rq->q, rq);
-		if (rq->elv.icq) {
-			put_io_context(rq->elv.icq->ioc);
-			rq->elv.icq = NULL;
-		}
-	}
-
-	if ((rq->rq_flags & RQF_QUEUED) && e && e->type->ops.mq.put_request)
-		e->type->ops.mq.put_request(rq);
-	else
-		blk_mq_finish_request(rq);
-}
-
 void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 {
 	struct request_queue *q = hctx->queue;
@@ -180,7 +97,8 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	bool did_work = false;
 	LIST_HEAD(rq_list);
 
-	if (unlikely(blk_mq_hctx_stopped(hctx)))
+	/* RCU or SRCU read lock is needed before checking quiesced flag */
+	if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
 		return;
 
 	hctx->run++;
@@ -260,19 +178,73 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
 }
 EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
 
+/*
+ * Reverse check our software queue for entries that we could potentially
+ * merge with. Currently includes a hand-wavy stop count of 8, to not spend
+ * too much time checking for merges.
+ */
+static bool blk_mq_attempt_merge(struct request_queue *q,
+				 struct blk_mq_ctx *ctx, struct bio *bio)
+{
+	struct request *rq;
+	int checked = 8;
+
+	lockdep_assert_held(&ctx->lock);
+
+	list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) {
+		bool merged = false;
+
+		if (!checked--)
+			break;
+
+		if (!blk_rq_merge_ok(rq, bio))
+			continue;
+
+		switch (blk_try_merge(rq, bio)) {
+		case ELEVATOR_BACK_MERGE:
+			if (blk_mq_sched_allow_merge(q, rq, bio))
+				merged = bio_attempt_back_merge(q, rq, bio);
+			break;
+		case ELEVATOR_FRONT_MERGE:
+			if (blk_mq_sched_allow_merge(q, rq, bio))
+				merged = bio_attempt_front_merge(q, rq, bio);
+			break;
+		case ELEVATOR_DISCARD_MERGE:
+			merged = bio_attempt_discard_merge(q, rq, bio);
+			break;
+		default:
+			continue;
+		}
+
+		if (merged)
+			ctx->rq_merged++;
+		return merged;
+	}
+
+	return false;
+}
+
 bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
 {
 	struct elevator_queue *e = q->elevator;
+	struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+	bool ret = false;
 
-	if (e->type->ops.mq.bio_merge) {
-		struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
-		struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
-
+	if (e && e->type->ops.mq.bio_merge) {
 		blk_mq_put_ctx(ctx);
 		return e->type->ops.mq.bio_merge(hctx, bio);
 	}
 
-	return false;
+	if (hctx->flags & BLK_MQ_F_SHOULD_MERGE) {
+		/* default per sw-queue merge */
+		spin_lock(&ctx->lock);
+		ret = blk_mq_attempt_merge(q, ctx, bio);
+		spin_unlock(&ctx->lock);
+	}
+
+	blk_mq_put_ctx(ctx);
+	return ret;
 }
 
 bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq)

block/blk-mq-sched.h

@@ -7,8 +7,7 @@
 void blk_mq_sched_free_hctx_data(struct request_queue *q,
 				 void (*exit)(struct blk_mq_hw_ctx *));
 
-struct request *blk_mq_sched_get_request(struct request_queue *q, struct bio *bio, unsigned int op, struct blk_mq_alloc_data *data);
-void blk_mq_sched_put_request(struct request *rq);
+void blk_mq_sched_assign_ioc(struct request *rq, struct bio *bio);
 
 void blk_mq_sched_request_inserted(struct request *rq);
 bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
@@ -38,35 +37,12 @@ int blk_mq_sched_init(struct request_queue *q);
 static inline bool
 blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
 {
-	struct elevator_queue *e = q->elevator;
-
-	if (!e || blk_queue_nomerges(q) || !bio_mergeable(bio))
+	if (blk_queue_nomerges(q) || !bio_mergeable(bio))
 		return false;
 
 	return __blk_mq_sched_bio_merge(q, bio);
 }
 
-static inline int blk_mq_sched_get_rq_priv(struct request_queue *q,
-					   struct request *rq,
-					   struct bio *bio)
-{
-	struct elevator_queue *e = q->elevator;
-
-	if (e && e->type->ops.mq.get_rq_priv)
-		return e->type->ops.mq.get_rq_priv(q, rq, bio);
-
-	return 0;
-}
-
-static inline void blk_mq_sched_put_rq_priv(struct request_queue *q,
-					    struct request *rq)
-{
-	struct elevator_queue *e = q->elevator;
-
-	if (e && e->type->ops.mq.put_rq_priv)
-		e->type->ops.mq.put_rq_priv(q, rq);
-}
-
 static inline bool
 blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
 			 struct bio *bio)

block/blk-mq.c

@@ -42,7 +42,6 @@ static LIST_HEAD(all_q_list);
 
 static void blk_mq_poll_stats_start(struct request_queue *q);
 static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
-static void __blk_mq_stop_hw_queues(struct request_queue *q, bool sync);
 
 static int blk_mq_poll_stats_bkt(const struct request *rq)
 {
@@ -154,13 +153,28 @@ void blk_mq_unfreeze_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
 
+/*
+ * FIXME: replace the scsi_internal_device_*block_nowait() calls in the
+ * mpt3sas driver such that this function can be removed.
+ */
+void blk_mq_quiesce_queue_nowait(struct request_queue *q)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	queue_flag_set(QUEUE_FLAG_QUIESCED, q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+}
+EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);
+
 /**
- * blk_mq_quiesce_queue() - wait until all ongoing queue_rq calls have finished
+ * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished
  * @q: request queue.
  *
  * Note: this function does not prevent that the struct request end_io()
- * callback function is invoked. Additionally, it is not prevented that
- * new queue_rq() calls occur unless the queue has been stopped first.
+ * callback function is invoked. Once this function is returned, we make
+ * sure no dispatch can happen until the queue is unquiesced via
+ * blk_mq_unquiesce_queue().
  */
 void blk_mq_quiesce_queue(struct request_queue *q)
 {
@@ -168,11 +182,11 @@ void blk_mq_quiesce_queue(struct request_queue *q)
 	unsigned int i;
 	bool rcu = false;
 
-	__blk_mq_stop_hw_queues(q, true);
+	blk_mq_quiesce_queue_nowait(q);
 
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (hctx->flags & BLK_MQ_F_BLOCKING)
-			synchronize_srcu(&hctx->queue_rq_srcu);
+			synchronize_srcu(hctx->queue_rq_srcu);
 		else
 			rcu = true;
 	}
@@ -181,6 +195,26 @@ void blk_mq_quiesce_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);
 
+/*
+ * blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue()
+ * @q: request queue.
+ *
+ * This function recovers queue into the state before quiescing
+ * which is done by blk_mq_quiesce_queue.
+ */
+void blk_mq_unquiesce_queue(struct request_queue *q)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(q->queue_lock, flags);
+	queue_flag_clear(QUEUE_FLAG_QUIESCED, q);
+	spin_unlock_irqrestore(q->queue_lock, flags);
+
+	/* dispatch requests which are inserted during quiescing */
+	blk_mq_run_hw_queues(q, true);
+}
+EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue);
+
 void blk_mq_wake_waiters(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
@@ -204,15 +238,33 @@ bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
 }
 EXPORT_SYMBOL(blk_mq_can_queue);
 
-void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
-			struct request *rq, unsigned int op)
+static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
+		unsigned int tag, unsigned int op)
 {
+	struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
+	struct request *rq = tags->static_rqs[tag];
+
+	rq->rq_flags = 0;
+
+	if (data->flags & BLK_MQ_REQ_INTERNAL) {
+		rq->tag = -1;
+		rq->internal_tag = tag;
+	} else {
+		if (blk_mq_tag_busy(data->hctx)) {
+			rq->rq_flags = RQF_MQ_INFLIGHT;
+			atomic_inc(&data->hctx->nr_active);
+		}
+		rq->tag = tag;
+		rq->internal_tag = -1;
+		data->hctx->tags->rqs[rq->tag] = rq;
+	}
+
 	INIT_LIST_HEAD(&rq->queuelist);
 	/* csd/requeue_work/fifo_time is initialized before use */
-	rq->q = q;
-	rq->mq_ctx = ctx;
+	rq->q = data->q;
+	rq->mq_ctx = data->ctx;
 	rq->cmd_flags = op;
-	if (blk_queue_io_stat(q))
+	if (blk_queue_io_stat(data->q))
 		rq->rq_flags |= RQF_IO_STAT;
 	/* do not touch atomic flags, it needs atomic ops against the timer */
 	rq->cpu = -1;
@@ -241,44 +293,60 @@ void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	rq->end_io_data = NULL;
 	rq->next_rq = NULL;
 
-	ctx->rq_dispatched[op_is_sync(op)]++;
+	data->ctx->rq_dispatched[op_is_sync(op)]++;
+	return rq;
 }
-EXPORT_SYMBOL_GPL(blk_mq_rq_ctx_init);
 
-struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
-				       unsigned int op)
+static struct request *blk_mq_get_request(struct request_queue *q,
+		struct bio *bio, unsigned int op,
+		struct blk_mq_alloc_data *data)
 {
+	struct elevator_queue *e = q->elevator;
 	struct request *rq;
 	unsigned int tag;
 
-	tag = blk_mq_get_tag(data);
-	if (tag != BLK_MQ_TAG_FAIL) {
-		struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
+	blk_queue_enter_live(q);
+	data->q = q;
+	if (likely(!data->ctx))
+		data->ctx = blk_mq_get_ctx(q);
+	if (likely(!data->hctx))
+		data->hctx = blk_mq_map_queue(q, data->ctx->cpu);
+	if (op & REQ_NOWAIT)
+		data->flags |= BLK_MQ_REQ_NOWAIT;
 
-		rq = tags->static_rqs[tag];
+	if (e) {
+		data->flags |= BLK_MQ_REQ_INTERNAL;
 
-		if (data->flags & BLK_MQ_REQ_INTERNAL) {
-			rq->tag = -1;
-			rq->internal_tag = tag;
-		} else {
-			if (blk_mq_tag_busy(data->hctx)) {
-				rq->rq_flags = RQF_MQ_INFLIGHT;
-				atomic_inc(&data->hctx->nr_active);
-			}
-			rq->tag = tag;
-			rq->internal_tag = -1;
-			data->hctx->tags->rqs[rq->tag] = rq;
-		}
+		/*
+		 * Flush requests are special and go directly to the
+		 * dispatch list.
+		 */
+		if (!op_is_flush(op) && e->type->ops.mq.limit_depth)
+			e->type->ops.mq.limit_depth(op, data);
+	}
 
-		blk_mq_rq_ctx_init(data->q, data->ctx, rq, op);
-		return rq;
+	tag = blk_mq_get_tag(data);
+	if (tag == BLK_MQ_TAG_FAIL) {
+		blk_queue_exit(q);
+		return NULL;
 	}
 
-	return NULL;
+	rq = blk_mq_rq_ctx_init(data, tag, op);
+	if (!op_is_flush(op)) {
+		rq->elv.icq = NULL;
+		if (e && e->type->ops.mq.prepare_request) {
+			if (e->type->icq_cache && rq_ioc(bio))
+				blk_mq_sched_assign_ioc(rq, bio);
+
+			e->type->ops.mq.prepare_request(rq, bio);
+			rq->rq_flags |= RQF_ELVPRIV;
+		}
+	}
+	data->hctx->queued++;
+	return rq;
 }
-EXPORT_SYMBOL_GPL(__blk_mq_alloc_request);
 
-struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
+struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
 		unsigned int flags)
 {
 	struct blk_mq_alloc_data alloc_data = { .flags = flags };
@@ -289,7 +357,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 	if (ret)
 		return ERR_PTR(ret);
 
-	rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
+	rq = blk_mq_get_request(q, NULL, op, &alloc_data);
 
 	blk_mq_put_ctx(alloc_data.ctx);
 	blk_queue_exit(q);
@@ -304,8 +372,8 @@ struct request *blk_mq_alloc_request(struct request_queue *q, int rw,
 }
 EXPORT_SYMBOL(blk_mq_alloc_request);
 
-struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
-		unsigned int flags, unsigned int hctx_idx)
+struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
+		unsigned int op, unsigned int flags, unsigned int hctx_idx)
 {
 	struct blk_mq_alloc_data alloc_data = { .flags = flags };
 	struct request *rq;
@@ -340,7 +408,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
 	cpu = cpumask_first(alloc_data.hctx->cpumask);
 	alloc_data.ctx = __blk_mq_get_ctx(q, cpu);
 
-	rq = blk_mq_sched_get_request(q, NULL, rw, &alloc_data);
+	rq = blk_mq_get_request(q, NULL, op, &alloc_data);
 
 	blk_queue_exit(q);
 
@@ -351,17 +419,28 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw,
 }
 EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
 
-void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
-			     struct request *rq)
+void blk_mq_free_request(struct request *rq)
 {
-	const int sched_tag = rq->internal_tag;
 	struct request_queue *q = rq->q;
+	struct elevator_queue *e = q->elevator;
+	struct blk_mq_ctx *ctx = rq->mq_ctx;
+	struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
+	const int sched_tag = rq->internal_tag;
 
+	if (rq->rq_flags & RQF_ELVPRIV) {
+		if (e && e->type->ops.mq.finish_request)
+			e->type->ops.mq.finish_request(rq);
+		if (rq->elv.icq) {
+			put_io_context(rq->elv.icq->ioc);
+			rq->elv.icq = NULL;
+		}
+	}
+
+	ctx->rq_completed[rq_is_sync(rq)]++;
 	if (rq->rq_flags & RQF_MQ_INFLIGHT)
 		atomic_dec(&hctx->nr_active);
 
 	wbt_done(q->rq_wb, &rq->issue_stat);
-	rq->rq_flags = 0;
 
 	clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags);
 	clear_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags);
@@ -372,29 +451,9 @@ void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 	blk_mq_sched_restart(hctx);
 	blk_queue_exit(q);
 }
-
-static void blk_mq_finish_hctx_request(struct blk_mq_hw_ctx *hctx,
-				     struct request *rq)
-{
-	struct blk_mq_ctx *ctx = rq->mq_ctx;
-
-	ctx->rq_completed[rq_is_sync(rq)]++;
-	__blk_mq_finish_request(hctx, ctx, rq);
-}
-
-void blk_mq_finish_request(struct request *rq)
-{
-	blk_mq_finish_hctx_request(blk_mq_map_queue(rq->q, rq->mq_ctx->cpu), rq);
-}
-EXPORT_SYMBOL_GPL(blk_mq_finish_request);
-
-void blk_mq_free_request(struct request *rq)
-{
-	blk_mq_sched_put_request(rq);
-}
 EXPORT_SYMBOL_GPL(blk_mq_free_request);
 
-inline void __blk_mq_end_request(struct request *rq, int error)
+inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
 {
 	blk_account_io_done(rq);
 
@@ -409,7 +468,7 @@ inline void __blk_mq_end_request(struct request *rq, int error)
 }
 EXPORT_SYMBOL(__blk_mq_end_request);
 
-void blk_mq_end_request(struct request *rq, int error)
+void blk_mq_end_request(struct request *rq, blk_status_t error)
 {
 	if (blk_update_request(rq, error, blk_rq_bytes(rq)))
 		BUG();
@@ -753,50 +812,6 @@ static void blk_mq_timeout_work(struct work_struct *work)
 	blk_queue_exit(q);
 }
 
-/*
- * Reverse check our software queue for entries that we could potentially
- * merge with. Currently includes a hand-wavy stop count of 8, to not spend
- * too much time checking for merges.
- */
-static bool blk_mq_attempt_merge(struct request_queue *q,
-				 struct blk_mq_ctx *ctx, struct bio *bio)
-{
-	struct request *rq;
-	int checked = 8;
-
-	list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) {
-		bool merged = false;
-
-		if (!checked--)
-			break;
-
-		if (!blk_rq_merge_ok(rq, bio))
-			continue;
-
-		switch (blk_try_merge(rq, bio)) {
-		case ELEVATOR_BACK_MERGE:
-			if (blk_mq_sched_allow_merge(q, rq, bio))
-				merged = bio_attempt_back_merge(q, rq, bio);
-			break;
-		case ELEVATOR_FRONT_MERGE:
-			if (blk_mq_sched_allow_merge(q, rq, bio))
-				merged = bio_attempt_front_merge(q, rq, bio);
-			break;
-		case ELEVATOR_DISCARD_MERGE:
-			merged = bio_attempt_discard_merge(q, rq, bio);
-			break;
-		default:
-			continue;
-		}
-
-		if (merged)
-			ctx->rq_merged++;
-		return merged;
-	}
-
-	return false;
-}
-
 struct flush_busy_ctx_data {
 	struct blk_mq_hw_ctx *hctx;
 	struct list_head *list;
@@ -968,7 +983,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
 {
 	struct blk_mq_hw_ctx *hctx;
 	struct request *rq;
-	int errors, queued, ret = BLK_MQ_RQ_QUEUE_OK;
+	int errors, queued;
 
 	if (list_empty(list))
 		return false;
@@ -979,6 +994,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
 	errors = queued = 0;
 	do {
 		struct blk_mq_queue_data bd;
+		blk_status_t ret;
 
 		rq = list_first_entry(list, struct request, queuelist);
 		if (!blk_mq_get_driver_tag(rq, &hctx, false)) {
@@ -1019,25 +1035,20 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
 		}
 
 		ret = q->mq_ops->queue_rq(hctx, &bd);
-		switch (ret) {
-		case BLK_MQ_RQ_QUEUE_OK:
-			queued++;
-			break;
-		case BLK_MQ_RQ_QUEUE_BUSY:
+		if (ret == BLK_STS_RESOURCE) {
 			blk_mq_put_driver_tag_hctx(hctx, rq);
 			list_add(&rq->queuelist, list);
 			__blk_mq_requeue_request(rq);
 			break;
-		default:
-			pr_err("blk-mq: bad return on queue: %d\n", ret);
-		case BLK_MQ_RQ_QUEUE_ERROR:
+		}
+
+		if (unlikely(ret != BLK_STS_OK)) {
 			errors++;
-			blk_mq_end_request(rq, -EIO);
-			break;
+			blk_mq_end_request(rq, BLK_STS_IOERR);
+			continue;
 		}
 
-		if (ret == BLK_MQ_RQ_QUEUE_BUSY)
-			break;
+		queued++;
 	} while (!list_empty(list));
 
 	hctx->dispatched[queued_to_index(queued)]++;
@@ -1075,7 +1086,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list)
 		 * - blk_mq_run_hw_queue() checks whether or not a queue has
 		 *   been stopped before rerunning a queue.
 		 * - Some but not all block drivers stop a queue before
-		 *   returning BLK_MQ_RQ_QUEUE_BUSY. Two exceptions are scsi-mq
+		 *   returning BLK_STS_RESOURCE. Two exceptions are scsi-mq
 		 *   and dm-rq.
 		 */
 		if (!blk_mq_sched_needs_restart(hctx) &&
@@ -1100,9 +1111,9 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx)
 	} else {
 		might_sleep();
 
-		srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
+		srcu_idx = srcu_read_lock(hctx->queue_rq_srcu);
 		blk_mq_sched_dispatch_requests(hctx);
-		srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
+		srcu_read_unlock(hctx->queue_rq_srcu, srcu_idx);
 	}
 }
 
@@ -1134,8 +1145,10 @@ static int blk_mq_hctx_next_cpu(struct blk_mq_hw_ctx *hctx)
 static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
 					unsigned long msecs)
 {
-	if (unlikely(blk_mq_hctx_stopped(hctx) ||
-		     !blk_mq_hw_queue_mapped(hctx)))
+	if (WARN_ON_ONCE(!blk_mq_hw_queue_mapped(hctx)))
+		return;
+
+	if (unlikely(blk_mq_hctx_stopped(hctx)))
 		return;
 
 	if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
@@ -1201,34 +1214,39 @@ bool blk_mq_queue_stopped(struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_mq_queue_stopped);
 
-static void __blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx, bool sync)
+/*
+ * This function is often used for pausing .queue_rq() by driver when
+ * there isn't enough resource or some conditions aren't satisfied, and
+ * BLK_MQ_RQ_QUEUE_BUSY is usually returned.
+ *
+ * We do not guarantee that dispatch can be drained or blocked
+ * after blk_mq_stop_hw_queue() returns. Please use
+ * blk_mq_quiesce_queue() for that requirement.
+ */
+void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
 {
-	if (sync)
-		cancel_delayed_work_sync(&hctx->run_work);
-	else
-		cancel_delayed_work(&hctx->run_work);
+	cancel_delayed_work(&hctx->run_work);
 
 	set_bit(BLK_MQ_S_STOPPED, &hctx->state);
 }
-
-void blk_mq_stop_hw_queue(struct blk_mq_hw_ctx *hctx)
-{
-	__blk_mq_stop_hw_queue(hctx, false);
-}
 EXPORT_SYMBOL(blk_mq_stop_hw_queue);
 
-static void __blk_mq_stop_hw_queues(struct request_queue *q, bool sync)
+/*
+ * This function is often used for pausing .queue_rq() by driver when
+ * there isn't enough resource or some conditions aren't satisfied, and
+ * BLK_MQ_RQ_QUEUE_BUSY is usually returned.
+ *
+ * We do not guarantee that dispatch can be drained or blocked
+ * after blk_mq_stop_hw_queues() returns. Please use
+ * blk_mq_quiesce_queue() for that requirement.
+ */
+void blk_mq_stop_hw_queues(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
 	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i)
-		__blk_mq_stop_hw_queue(hctx, sync);
-}
-
-void blk_mq_stop_hw_queues(struct request_queue *q)
-{
-	__blk_mq_stop_hw_queues(q, false);
+		blk_mq_stop_hw_queue(hctx);
 }
 EXPORT_SYMBOL(blk_mq_stop_hw_queues);
 
@@ -1295,7 +1313,7 @@ static void blk_mq_run_work_fn(struct work_struct *work)
 
 void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 {
-	if (unlikely(!blk_mq_hw_queue_mapped(hctx)))
+	if (WARN_ON_ONCE(!blk_mq_hw_queue_mapped(hctx)))
 		return;
 
 	/*
@@ -1317,6 +1335,8 @@ static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 
+	lockdep_assert_held(&ctx->lock);
+
 	trace_block_rq_insert(hctx->queue, rq);
 
 	if (at_head)
@@ -1330,6 +1350,8 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
 
+	lockdep_assert_held(&ctx->lock);
+
 	__blk_mq_insert_req_list(hctx, rq, at_head);
 	blk_mq_hctx_mark_pending(hctx, ctx);
 }
@@ -1427,30 +1449,13 @@ static inline bool hctx_allow_merges(struct blk_mq_hw_ctx *hctx)
 		!blk_queue_nomerges(hctx->queue);
 }
 
-static inline bool blk_mq_merge_queue_io(struct blk_mq_hw_ctx *hctx,
-					 struct blk_mq_ctx *ctx,
-					 struct request *rq, struct bio *bio)
+static inline void blk_mq_queue_io(struct blk_mq_hw_ctx *hctx,
+				   struct blk_mq_ctx *ctx,
+				   struct request *rq)
 {
-	if (!hctx_allow_merges(hctx) || !bio_mergeable(bio)) {
-		blk_mq_bio_to_request(rq, bio);
-		spin_lock(&ctx->lock);
-insert_rq:
-		__blk_mq_insert_request(hctx, rq, false);
-		spin_unlock(&ctx->lock);
-		return false;
-	} else {
-		struct request_queue *q = hctx->queue;
-
-		spin_lock(&ctx->lock);
-		if (!blk_mq_attempt_merge(q, ctx, bio)) {
-			blk_mq_bio_to_request(rq, bio);
-			goto insert_rq;
-		}
-
-		spin_unlock(&ctx->lock);
-		__blk_mq_finish_request(hctx, ctx, rq);
-		return true;
-	}
+	spin_lock(&ctx->lock);
+	__blk_mq_insert_request(hctx, rq, false);
+	spin_unlock(&ctx->lock);
 }
 
 static blk_qc_t request_to_qc_t(struct blk_mq_hw_ctx *hctx, struct request *rq)
@@ -1471,10 +1476,11 @@ static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 		.last = true,
 	};
 	blk_qc_t new_cookie;
-	int ret;
+	blk_status_t ret;
 	bool run_queue = true;
 
-	if (blk_mq_hctx_stopped(hctx)) {
+	/* RCU or SRCU read lock is needed before checking quiesced flag */
+	if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)) {
 		run_queue = false;
 		goto insert;
 	}
@@ -1493,18 +1499,19 @@ static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 	 * would have done
 	 */
 	ret = q->mq_ops->queue_rq(hctx, &bd);
-	if (ret == BLK_MQ_RQ_QUEUE_OK) {
+	switch (ret) {
+	case BLK_STS_OK:
 		*cookie = new_cookie;
 		return;
-	}
-
-	if (ret == BLK_MQ_RQ_QUEUE_ERROR) {
+	case BLK_STS_RESOURCE:
+		__blk_mq_requeue_request(rq);
+		goto insert;
+	default:
 		*cookie = BLK_QC_T_NONE;
-		blk_mq_end_request(rq, -EIO);
+		blk_mq_end_request(rq, ret);
 		return;
 	}
 
-	__blk_mq_requeue_request(rq);
 insert:
 	blk_mq_sched_insert_request(rq, false, run_queue, false, may_sleep);
 }
@@ -1521,9 +1528,9 @@ static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 
 		might_sleep();
 
-		srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
+		srcu_idx = srcu_read_lock(hctx->queue_rq_srcu);
 		__blk_mq_try_issue_directly(hctx, rq, cookie, true);
-		srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
+		srcu_read_unlock(hctx->queue_rq_srcu, srcu_idx);
 	}
 }
 
@@ -1541,7 +1548,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	blk_queue_bounce(q, &bio);
 
-	blk_queue_split(q, &bio, q->bio_split);
+	blk_queue_split(q, &bio);
 
 	if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) {
 		bio_io_error(bio);
@@ -1559,9 +1566,11 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 	trace_block_getrq(q, bio, bio->bi_opf);
 
-	rq = blk_mq_sched_get_request(q, bio, bio->bi_opf, &data);
+	rq = blk_mq_get_request(q, bio, bio->bi_opf, &data);
 	if (unlikely(!rq)) {
 		__wbt_done(q->rq_wb, wb_acct);
+		if (bio->bi_opf & REQ_NOWAIT)
+			bio_wouldblock_error(bio);
 		return BLK_QC_T_NONE;
 	}
 
@@ -1639,11 +1648,12 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
 		blk_mq_sched_insert_request(rq, false, true, true, true);
-	} else if (!blk_mq_merge_queue_io(data.hctx, data.ctx, rq, bio)) {
+	} else {
 		blk_mq_put_ctx(data.ctx);
+		blk_mq_bio_to_request(rq, bio);
+		blk_mq_queue_io(data.hctx, data.ctx, rq);
 		blk_mq_run_hw_queue(data.hctx, true);
-	} else
-		blk_mq_put_ctx(data.ctx);
+	}
 
 	return cookie;
 }
@@ -1866,7 +1876,7 @@ static void blk_mq_exit_hctx(struct request_queue *q,
 		set->ops->exit_hctx(hctx, hctx_idx);
 
 	if (hctx->flags & BLK_MQ_F_BLOCKING)
-		cleanup_srcu_struct(&hctx->queue_rq_srcu);
+		cleanup_srcu_struct(hctx->queue_rq_srcu);
 
 	blk_mq_remove_cpuhp(hctx);
 	blk_free_flush_queue(hctx->fq);
@@ -1900,7 +1910,6 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	spin_lock_init(&hctx->lock);
 	INIT_LIST_HEAD(&hctx->dispatch);
 	hctx->queue = q;
-	hctx->queue_num = hctx_idx;
 	hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED;
 
 	cpuhp_state_add_instance_nocalls(CPUHP_BLK_MQ_DEAD, &hctx->cpuhp_dead);
@@ -1939,7 +1948,7 @@ static int blk_mq_init_hctx(struct request_queue *q,
 		goto free_fq;
 
 	if (hctx->flags & BLK_MQ_F_BLOCKING)
-		init_srcu_struct(&hctx->queue_rq_srcu);
+		init_srcu_struct(hctx->queue_rq_srcu);
 
 	blk_mq_debugfs_register_hctx(q, hctx);
 
@@ -2224,6 +2233,20 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set)
 }
 EXPORT_SYMBOL(blk_mq_init_queue);
 
+static int blk_mq_hw_ctx_size(struct blk_mq_tag_set *tag_set)
+{
+	int hw_ctx_size = sizeof(struct blk_mq_hw_ctx);
+
+	BUILD_BUG_ON(ALIGN(offsetof(struct blk_mq_hw_ctx, queue_rq_srcu),
+			   __alignof__(struct blk_mq_hw_ctx)) !=
+		     sizeof(struct blk_mq_hw_ctx));
+
+	if (tag_set->flags & BLK_MQ_F_BLOCKING)
+		hw_ctx_size += sizeof(struct srcu_struct);
+
+	return hw_ctx_size;
+}
+
 static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 						struct request_queue *q)
 {
@@ -2238,7 +2261,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 			continue;
 
 		node = blk_mq_hw_queue_to_node(q->mq_map, i);
-		hctxs[i] = kzalloc_node(sizeof(struct blk_mq_hw_ctx),
+		hctxs[i] = kzalloc_node(blk_mq_hw_ctx_size(set),
 					GFP_KERNEL, node);
 		if (!hctxs[i])
 			break;

block/blk-mq.h

@@ -128,17 +128,6 @@ static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data
 	return data->hctx->tags;
 }
 
-/*
- * Internal helpers for request allocation/init/free
- */
-void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
-			struct request *rq, unsigned int op);
-void __blk_mq_finish_request(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
-				struct request *rq);
-void blk_mq_finish_request(struct request *rq);
-struct request *__blk_mq_alloc_request(struct blk_mq_alloc_data *data,
-					unsigned int op);
-
 static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
 {
 	return test_bit(BLK_MQ_S_STOPPED, &hctx->state);

block/blk-settings.c

@@ -172,11 +172,6 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
 	q->nr_batching = BLK_BATCH_REQ;
 
 	blk_set_default_limits(&q->limits);
-
-	/*
-	 * by default assume old behaviour and bounce for any highmem page
-	 */
-	blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
 }
 EXPORT_SYMBOL(blk_queue_make_request);
 

block/blk-tag.c

@@ -258,15 +258,14 @@ EXPORT_SYMBOL(blk_queue_resize_tags);
  *    all transfers have been done for a request. It's important to call
  *    this function before end_that_request_last(), as that will put the
  *    request back on the free list thus corrupting the internal tag list.
- *
- *  Notes:
- *   queue lock must be held.
  **/
 void blk_queue_end_tag(struct request_queue *q, struct request *rq)
 {
 	struct blk_queue_tag *bqt = q->queue_tags;
 	unsigned tag = rq->tag; /* negative tags invalid */
 
+	lockdep_assert_held(q->queue_lock);
+
 	BUG_ON(tag >= bqt->real_max_depth);
 
 	list_del_init(&rq->queuelist);
@@ -307,9 +306,6 @@ EXPORT_SYMBOL(blk_queue_end_tag);
  *    calling this function.  The request will also be removed from
  *    the request queue, so it's the drivers responsibility to readd
  *    it if it should need to be restarted for some reason.
- *
- *  Notes:
- *   queue lock must be held.
  **/
 int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 {
@@ -317,6 +313,8 @@ int blk_queue_start_tag(struct request_queue *q, struct request *rq)
 	unsigned max_depth;
 	int tag;
 
+	lockdep_assert_held(q->queue_lock);
+
 	if (unlikely((rq->rq_flags & RQF_QUEUED))) {
 		printk(KERN_ERR
 		       "%s: request %p for device [%s] already tagged %d",
@@ -389,14 +387,13 @@ EXPORT_SYMBOL(blk_queue_start_tag);
  *   Hardware conditions may dictate a need to stop all pending requests.
  *   In this case, we will safely clear the block side of the tag queue and
  *   readd all requests to the request queue in the right order.
- *
- *  Notes:
- *   queue lock must be held.
  **/
 void blk_queue_invalidate_tags(struct request_queue *q)
 {
 	struct list_head *tmp, *n;
 
+	lockdep_assert_held(q->queue_lock);
+
 	list_for_each_safe(tmp, n, &q->tag_busy_list)
 		blk_requeue_request(q, list_entry_rq(tmp));
 }

block/blk-timeout.c

@@ -189,13 +189,15 @@ unsigned long blk_rq_timeout(unsigned long timeout)
  * Notes:
  *    Each request has its own timer, and as it is added to the queue, we
  *    set up the timer. When the request completes, we cancel the timer.
- *    Queue lock must be held for the non-mq case, mq case doesn't care.
  */
 void blk_add_timer(struct request *req)
 {
 	struct request_queue *q = req->q;
 	unsigned long expiry;
 
+	if (!q->mq_ops)
+		lockdep_assert_held(q->queue_lock);
+
 	/* blk-mq has its own handler, so we don't need ->rq_timed_out_fn */
 	if (!q->mq_ops && !q->rq_timed_out_fn)
 		return;

block/blk.h

@@ -143,6 +143,8 @@ static inline struct request *__elv_next_request(struct request_queue *q)
 	struct request *rq;
 	struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL);
 
+	WARN_ON_ONCE(q->mq_ops);
+
 	while (1) {
 		if (!list_empty(&q->queue_head)) {
 			rq = list_entry_rq(q->queue_head.next);
@@ -334,4 +336,17 @@ static inline void blk_throtl_bio_endio(struct bio *bio) { }
 static inline void blk_throtl_stat_add(struct request *rq, u64 time) { }
 #endif
 
+#ifdef CONFIG_BOUNCE
+extern int init_emergency_isa_pool(void);
+extern void blk_queue_bounce(struct request_queue *q, struct bio **bio);
+#else
+static inline int init_emergency_isa_pool(void)
+{
+	return 0;
+}
+static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
+{
+}
+#endif /* CONFIG_BOUNCE */
+
 #endif /* BLK_INTERNAL_H */

block/bounce.c

@@ -22,10 +22,12 @@
 #include <asm/tlbflush.h>
 
 #include <trace/events/block.h>
+#include "blk.h"
 
 #define POOL_SIZE	64
 #define ISA_POOL_SIZE	16
 
+static struct bio_set *bounce_bio_set, *bounce_bio_split;
 static mempool_t *page_pool, *isa_page_pool;
 
 #if defined(CONFIG_HIGHMEM) || defined(CONFIG_NEED_BOUNCE_POOL)
@@ -40,6 +42,14 @@ static __init int init_emergency_pool(void)
 	BUG_ON(!page_pool);
 	pr_info("pool size: %d pages\n", POOL_SIZE);
 
+	bounce_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS);
+	BUG_ON(!bounce_bio_set);
+	if (bioset_integrity_create(bounce_bio_set, BIO_POOL_SIZE))
+		BUG_ON(1);
+
+	bounce_bio_split = bioset_create(BIO_POOL_SIZE, 0, 0);
+	BUG_ON(!bounce_bio_split);
+
 	return 0;
 }
 
@@ -143,7 +153,7 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool)
 		mempool_free(bvec->bv_page, pool);
 	}
 
-	bio_orig->bi_error = bio->bi_error;
+	bio_orig->bi_status = bio->bi_status;
 	bio_endio(bio_orig);
 	bio_put(bio);
 }
@@ -163,7 +173,7 @@ static void __bounce_end_io_read(struct bio *bio, mempool_t *pool)
 {
 	struct bio *bio_orig = bio->bi_private;
 
-	if (!bio->bi_error)
+	if (!bio->bi_status)
 		copy_to_high_bio_irq(bio_orig, bio);
 
 	bounce_end_io(bio, pool);
@@ -186,20 +196,31 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 	int rw = bio_data_dir(*bio_orig);
 	struct bio_vec *to, from;
 	struct bvec_iter iter;
-	unsigned i;
-
-	bio_for_each_segment(from, *bio_orig, iter)
-		if (page_to_pfn(from.bv_page) > queue_bounce_pfn(q))
-			goto bounce;
+	unsigned i = 0;
+	bool bounce = false;
+	int sectors = 0;
+
+	bio_for_each_segment(from, *bio_orig, iter) {
+		if (i++ < BIO_MAX_PAGES)
+			sectors += from.bv_len >> 9;
+		if (page_to_pfn(from.bv_page) > q->limits.bounce_pfn)
+			bounce = true;
+	}
+	if (!bounce)
+		return;
 
-	return;
-bounce:
-	bio = bio_clone_bioset(*bio_orig, GFP_NOIO, fs_bio_set);
+	if (sectors < bio_sectors(*bio_orig)) {
+		bio = bio_split(*bio_orig, sectors, GFP_NOIO, bounce_bio_split);
+		bio_chain(bio, *bio_orig);
+		generic_make_request(*bio_orig);
+		*bio_orig = bio;
+	}
+	bio = bio_clone_bioset(*bio_orig, GFP_NOIO, bounce_bio_set);
 
 	bio_for_each_segment_all(to, bio, i) {
 		struct page *page = to->bv_page;
 
-		if (page_to_pfn(page) <= queue_bounce_pfn(q))
+		if (page_to_pfn(page) <= q->limits.bounce_pfn)
 			continue;
 
 		to->bv_page = mempool_alloc(pool, q->bounce_gfp);
@@ -251,7 +272,7 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
 	 * don't waste time iterating over bio segments
 	 */
 	if (!(q->bounce_gfp & GFP_DMA)) {
-		if (queue_bounce_pfn(q) >= blk_max_pfn)
+		if (q->limits.bounce_pfn >= blk_max_pfn)
 			return;
 		pool = page_pool;
 	} else {
@@ -264,5 +285,3 @@ void blk_queue_bounce(struct request_queue *q, struct bio **bio_orig)
 	 */
 	__blk_queue_bounce(q, bio_orig, pool);
 }
-
-EXPORT_SYMBOL(blk_queue_bounce);

block/bsg-lib.c

@@ -37,7 +37,7 @@ static void bsg_destroy_job(struct kref *kref)
 	struct bsg_job *job = container_of(kref, struct bsg_job, kref);
 	struct request *rq = job->req;
 
-	blk_end_request_all(rq, scsi_req(rq)->result);
+	blk_end_request_all(rq, BLK_STS_OK);
 
 	put_device(job->dev);	/* release reference for the request */
 
@@ -202,7 +202,7 @@ static void bsg_request_fn(struct request_queue *q)
 		ret = bsg_create_job(dev, req);
 		if (ret) {
 			scsi_req(req)->result = ret;
-			blk_end_request_all(req, ret);
+			blk_end_request_all(req, BLK_STS_OK);
 			spin_lock_irq(q->queue_lock);
 			continue;
 		}
@@ -246,6 +246,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, char *name,
 	q->bsg_job_size = dd_job_size;
 	q->bsg_job_fn = job_fn;
 	queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q);
+	queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, q);
 	blk_queue_softirq_done(q, bsg_softirq_done);
 	blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT);
 

block/bsg.c

@@ -236,7 +236,6 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm)
 	rq = blk_get_request(q, op, GFP_KERNEL);
 	if (IS_ERR(rq))
 		return rq;
-	scsi_req_init(rq);
 
 	ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd, has_write_perm);
 	if (ret)
@@ -294,14 +293,14 @@ out:
  * async completion call-back from the block layer, when scsi/ide/whatever
  * calls end_that_request_last() on a request
  */
-static void bsg_rq_end_io(struct request *rq, int uptodate)
+static void bsg_rq_end_io(struct request *rq, blk_status_t status)
 {
 	struct bsg_command *bc = rq->end_io_data;
 	struct bsg_device *bd = bc->bd;
 	unsigned long flags;
 
-	dprintk("%s: finished rq %p bc %p, bio %p stat %d\n",
-		bd->name, rq, bc, bc->bio, uptodate);
+	dprintk("%s: finished rq %p bc %p, bio %p\n",
+		bd->name, rq, bc, bc->bio);
 
 	bc->hdr.duration = jiffies_to_msecs(jiffies - bc->hdr.duration);
 
@@ -750,6 +749,12 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
 #ifdef BSG_DEBUG
 	unsigned char buf[32];
 #endif
+
+	if (!blk_queue_scsi_passthrough(rq)) {
+		WARN_ONCE(true, "Attempt to register a non-SCSI queue\n");
+		return ERR_PTR(-EINVAL);
+	}
+
 	if (!blk_get_queue(rq))
 		return ERR_PTR(-ENXIO);
 

block/cfq-iosched.c

@@ -982,15 +982,6 @@ static inline u64 max_vdisktime(u64 min_vdisktime, u64 vdisktime)
 	return min_vdisktime;
 }
 
-static inline u64 min_vdisktime(u64 min_vdisktime, u64 vdisktime)
-{
-	s64 delta = (s64)(vdisktime - min_vdisktime);
-	if (delta < 0)
-		min_vdisktime = vdisktime;
-
-	return min_vdisktime;
-}
-
 static void update_min_vdisktime(struct cfq_rb_root *st)
 {
 	struct cfq_group *cfqg;

block/elevator.c

@@ -681,6 +681,7 @@ void __elv_add_request(struct request_queue *q, struct request *rq, int where)
 		 */
 		if (elv_attempt_insert_merge(q, rq))
 			break;
+		/* fall through */
 	case ELEVATOR_INSERT_SORT:
 		BUG_ON(blk_rq_is_passthrough(rq));
 		rq->rq_flags |= RQF_SORTED;

block/genhd.c

@@ -36,7 +36,7 @@ struct kobject *block_depr;
 static DEFINE_SPINLOCK(ext_devt_lock);
 static DEFINE_IDR(ext_devt_idr);
 
-static struct device_type disk_type;
+static const struct device_type disk_type;
 
 static void disk_check_events(struct disk_events *ev,
 			      unsigned int *clearing_ptr);
@@ -1183,7 +1183,7 @@ static char *block_devnode(struct device *dev, umode_t *mode,
 	return NULL;
 }
 
-static struct device_type disk_type = {
+static const struct device_type disk_type = {
 	.name		= "disk",
 	.groups		= disk_attr_groups,
 	.release	= disk_release,

block/ioprio.c

@@ -75,7 +75,8 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
 		case IOPRIO_CLASS_RT:
 			if (!capable(CAP_SYS_ADMIN))
 				return -EPERM;
-			/* fall through, rt has prio field too */
+			/* fall through */
+			/* rt has prio field too */
 		case IOPRIO_CLASS_BE:
 			if (data >= IOPRIO_BE_NR || data < 0)
 				return -EINVAL;

block/kyber-iosched.c

@@ -426,33 +426,29 @@ static void rq_clear_domain_token(struct kyber_queue_data *kqd,
 	}
 }
 
-static struct request *kyber_get_request(struct request_queue *q,
-					 unsigned int op,
-					 struct blk_mq_alloc_data *data)
+static void kyber_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
 {
-	struct kyber_queue_data *kqd = q->elevator->elevator_data;
-	struct request *rq;
-
 	/*
 	 * We use the scheduler tags as per-hardware queue queueing tokens.
 	 * Async requests can be limited at this stage.
 	 */
-	if (!op_is_sync(op))
+	if (!op_is_sync(op)) {
+		struct kyber_queue_data *kqd = data->q->elevator->elevator_data;
+
 		data->shallow_depth = kqd->async_depth;
+	}
+}
 
-	rq = __blk_mq_alloc_request(data, op);
-	if (rq)
-		rq_set_domain_token(rq, -1);
-	return rq;
+static void kyber_prepare_request(struct request *rq, struct bio *bio)
+{
+	rq_set_domain_token(rq, -1);
 }
 
-static void kyber_put_request(struct request *rq)
+static void kyber_finish_request(struct request *rq)
 {
-	struct request_queue *q = rq->q;
-	struct kyber_queue_data *kqd = q->elevator->elevator_data;
+	struct kyber_queue_data *kqd = rq->q->elevator->elevator_data;
 
 	rq_clear_domain_token(kqd, rq);
-	blk_mq_finish_request(rq);
 }
 
 static void kyber_completed_request(struct request *rq)
@@ -815,8 +811,9 @@ static struct elevator_type kyber_sched = {
 		.exit_sched = kyber_exit_sched,
 		.init_hctx = kyber_init_hctx,
 		.exit_hctx = kyber_exit_hctx,
-		.get_request = kyber_get_request,
-		.put_request = kyber_put_request,
+		.limit_depth = kyber_limit_depth,
+		.prepare_request = kyber_prepare_request,
+		.finish_request = kyber_finish_request,
 		.completed_request = kyber_completed_request,
 		.dispatch_request = kyber_dispatch_request,
 		.has_work = kyber_has_work,

block/scsi_ioctl.c

@@ -326,7 +326,6 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
 	req = scsi_req(rq);
-	scsi_req_init(rq);
 
 	if (hdr->cmd_len > BLK_MAX_CDB) {
 		req->cmd = kzalloc(hdr->cmd_len, GFP_KERNEL);
@@ -456,7 +455,6 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 		goto error_free_buffer;
 	}
 	req = scsi_req(rq);
-	scsi_req_init(rq);
 
 	cmdlen = COMMAND_SIZE(opcode);
 
@@ -542,7 +540,6 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 	rq = blk_get_request(q, REQ_OP_SCSI_OUT, __GFP_RECLAIM);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
-	scsi_req_init(rq);
 	rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
 	scsi_req(rq)->cmd[0] = cmd;
 	scsi_req(rq)->cmd[4] = data;
@@ -744,10 +741,14 @@ int scsi_cmd_blk_ioctl(struct block_device *bd, fmode_t mode,
 }
 EXPORT_SYMBOL(scsi_cmd_blk_ioctl);
 
-void scsi_req_init(struct request *rq)
+/**
+ * scsi_req_init - initialize certain fields of a scsi_request structure
+ * @req: Pointer to a scsi_request structure.
+ * Initializes .__cmd[], .cmd, .cmd_len and .sense_len but no other members
+ * of struct scsi_request.
+ */
+void scsi_req_init(struct scsi_request *req)
 {
-	struct scsi_request *req = scsi_req(rq);
-
 	memset(req->__cmd, 0, sizeof(req->__cmd));
 	req->cmd = req->__cmd;
 	req->cmd_len = BLK_MAX_CDB;

block/t10-pi.c

@@ -46,8 +46,8 @@ static __be16 t10_pi_ip_fn(void *data, unsigned int len)
  * 16 bit app tag, 32 bit reference tag. Type 3 does not define the ref
  * tag.
  */
-static int t10_pi_generate(struct blk_integrity_iter *iter, csum_fn *fn,
-			   unsigned int type)
+static blk_status_t t10_pi_generate(struct blk_integrity_iter *iter,
+		csum_fn *fn, unsigned int type)
 {
 	unsigned int i;
 
@@ -67,11 +67,11 @@ static int t10_pi_generate(struct blk_integrity_iter *iter, csum_fn *fn,
 		iter->seed++;
 	}
 
-	return 0;
+	return BLK_STS_OK;
 }
 
-static int t10_pi_verify(struct blk_integrity_iter *iter, csum_fn *fn,
-				unsigned int type)
+static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
+		csum_fn *fn, unsigned int type)
 {
 	unsigned int i;
 
@@ -91,7 +91,7 @@ static int t10_pi_verify(struct blk_integrity_iter *iter, csum_fn *fn,
 				       "(rcvd %u)\n", iter->disk_name,
 				       (unsigned long long)
 				       iter->seed, be32_to_cpu(pi->ref_tag));
-				return -EILSEQ;
+				return BLK_STS_PROTECTION;
 			}
 			break;
 		case 3:
@@ -108,7 +108,7 @@ static int t10_pi_verify(struct blk_integrity_iter *iter, csum_fn *fn,
 			       "(rcvd %04x, want %04x)\n", iter->disk_name,
 			       (unsigned long long)iter->seed,
 			       be16_to_cpu(pi->guard_tag), be16_to_cpu(csum));
-			return -EILSEQ;
+			return BLK_STS_PROTECTION;
 		}
 
 next:
@@ -117,45 +117,45 @@ next:
 		iter->seed++;
 	}
 
-	return 0;
+	return BLK_STS_OK;
 }
 
-static int t10_pi_type1_generate_crc(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type1_generate_crc(struct blk_integrity_iter *iter)
 {
 	return t10_pi_generate(iter, t10_pi_crc_fn, 1);
 }
 
-static int t10_pi_type1_generate_ip(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type1_generate_ip(struct blk_integrity_iter *iter)
 {
 	return t10_pi_generate(iter, t10_pi_ip_fn, 1);
 }
 
-static int t10_pi_type1_verify_crc(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type1_verify_crc(struct blk_integrity_iter *iter)
 {
 	return t10_pi_verify(iter, t10_pi_crc_fn, 1);
 }
 
-static int t10_pi_type1_verify_ip(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type1_verify_ip(struct blk_integrity_iter *iter)
 {
 	return t10_pi_verify(iter, t10_pi_ip_fn, 1);
 }
 
-static int t10_pi_type3_generate_crc(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type3_generate_crc(struct blk_integrity_iter *iter)
 {
 	return t10_pi_generate(iter, t10_pi_crc_fn, 3);
 }
 
-static int t10_pi_type3_generate_ip(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type3_generate_ip(struct blk_integrity_iter *iter)
 {
 	return t10_pi_generate(iter, t10_pi_ip_fn, 3);
 }
 
-static int t10_pi_type3_verify_crc(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type3_verify_crc(struct blk_integrity_iter *iter)
 {
 	return t10_pi_verify(iter, t10_pi_crc_fn, 3);
 }
 
-static int t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
+static blk_status_t t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
 {
 	return t10_pi_verify(iter, t10_pi_ip_fn, 3);
 }

drivers/block/DAC960.c

@@ -3464,7 +3464,7 @@ static inline bool DAC960_ProcessCompletedRequest(DAC960_Command_T *Command,
 						 bool SuccessfulIO)
 {
 	struct request *Request = Command->Request;
-	int Error = SuccessfulIO ? 0 : -EIO;
+	blk_status_t Error = SuccessfulIO ? BLK_STS_OK : BLK_STS_IOERR;
 
 	pci_unmap_sg(Command->Controller->PCIDevice, Command->cmd_sglist,
 		Command->SegmentCount, Command->DmaDirection);

drivers/block/amiflop.c

@@ -1378,7 +1378,7 @@ static void redo_fd_request(void)
 	struct amiga_floppy_struct *floppy;
 	char *data;
 	unsigned long flags;
-	int err;
+	blk_status_t err;
 
 next_req:
 	rq = set_next_request();
@@ -1392,7 +1392,7 @@ next_req:
 
 next_segment:
 	/* Here someone could investigate to be more efficient */
-	for (cnt = 0, err = 0; cnt < blk_rq_cur_sectors(rq); cnt++) {
+	for (cnt = 0, err = BLK_STS_OK; cnt < blk_rq_cur_sectors(rq); cnt++) {
 #ifdef DEBUG
 		printk("fd: sector %ld + %d requested for %s\n",
 		       blk_rq_pos(rq), cnt,
@@ -1400,7 +1400,7 @@ next_segment:
 #endif
 		block = blk_rq_pos(rq) + cnt;
 		if ((int)block > floppy->blocks) {
-			err = -EIO;
+			err = BLK_STS_IOERR;
 			break;
 		}
 
@@ -1413,7 +1413,7 @@ next_segment:
 #endif
 
 		if (get_track(drive, track) == -1) {
-			err = -EIO;
+			err = BLK_STS_IOERR;
 			break;
 		}
 
@@ -1424,7 +1424,7 @@ next_segment:
 
 			/* keep the drive spinning while writes are scheduled */
 			if (!fd_motor_on(drive)) {
-				err = -EIO;
+				err = BLK_STS_IOERR;
 				break;
 			}
 			/*

drivers/block/aoe/aoeblk.c

@@ -388,6 +388,7 @@ aoeblk_gdalloc(void *vp)
 			d->aoemajor, d->aoeminor);
 		goto err_mempool;
 	}
+	blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
 
 	spin_lock_irqsave(&d->lock, flags);
 	WARN_ON(!(d->flags & DEVFL_GD_NOW));

drivers/block/aoe/aoecmd.c

@@ -1070,8 +1070,8 @@ aoe_end_request(struct aoedev *d, struct request *rq, int fastfail)
 		d->ip.rq = NULL;
 	do {
 		bio = rq->bio;
-		bok = !fastfail && !bio->bi_error;
-	} while (__blk_end_request(rq, bok ? 0 : -EIO, bio->bi_iter.bi_size));
+		bok = !fastfail && !bio->bi_status;
+	} while (__blk_end_request(rq, bok ? BLK_STS_OK : BLK_STS_IOERR, bio->bi_iter.bi_size));
 
 	/* cf. http://lkml.org/lkml/2006/10/31/28 */
 	if (!fastfail)
@@ -1131,7 +1131,7 @@ ktiocomplete(struct frame *f)
 			ahout->cmdstat, ahin->cmdstat,
 			d->aoemajor, d->aoeminor);
 noskb:		if (buf)
-			buf->bio->bi_error = -EIO;
+			buf->bio->bi_status = BLK_STS_IOERR;
 		goto out;
 	}
 
@@ -1144,7 +1144,7 @@ noskb:		if (buf)
 				"aoe: runt data size in read from",
 				(long) d->aoemajor, d->aoeminor,
 			       skb->len, n);
-			buf->bio->bi_error = -EIO;
+			buf->bio->bi_status = BLK_STS_IOERR;
 			break;
 		}
 		if (n > f->iter.bi_size) {
@@ -1152,7 +1152,7 @@ noskb:		if (buf)
 				"aoe: too-large data size in read from",
 				(long) d->aoemajor, d->aoeminor,
 				n, f->iter.bi_size);
-			buf->bio->bi_error = -EIO;
+			buf->bio->bi_status = BLK_STS_IOERR;
 			break;
 		}
 		bvcpy(skb, f->buf->bio, f->iter, n);
@@ -1654,7 +1654,7 @@ aoe_failbuf(struct aoedev *d, struct buf *buf)
 	if (buf == NULL)
 		return;
 	buf->iter.bi_size = 0;
-	buf->bio->bi_error = -EIO;
+	buf->bio->bi_status = BLK_STS_IOERR;
 	if (buf->nframesout == 0)
 		aoe_end_buf(d, buf);
 }

drivers/block/aoe/aoedev.c

@@ -170,7 +170,7 @@ aoe_failip(struct aoedev *d)
 	if (rq == NULL)
 		return;
 	while ((bio = d->ip.nxbio)) {
-		bio->bi_error = -EIO;
+		bio->bi_status = BLK_STS_IOERR;
 		d->ip.nxbio = bio->bi_next;
 		n = (unsigned long) rq->special;
 		rq->special = (void *) --n;

drivers/block/ataflop.c

@@ -378,7 +378,7 @@ static DEFINE_TIMER(readtrack_timer, fd_readtrack_check, 0, 0);
 static DEFINE_TIMER(timeout_timer, fd_times_out, 0, 0);
 static DEFINE_TIMER(fd_timer, check_change, 0, 0);
 	
-static void fd_end_request_cur(int err)
+static void fd_end_request_cur(blk_status_t err)
 {
 	if (!__blk_end_request_cur(fd_request, err))
 		fd_request = NULL;
@@ -620,7 +620,7 @@ static void fd_error( void )
 	fd_request->error_count++;
 	if (fd_request->error_count >= MAX_ERRORS) {
 		printk(KERN_ERR "fd%d: too many errors.\n", SelectedDrive );
-		fd_end_request_cur(-EIO);
+		fd_end_request_cur(BLK_STS_IOERR);
 	}
 	else if (fd_request->error_count == RECALIBRATE_ERRORS) {
 		printk(KERN_WARNING "fd%d: recalibrating\n", SelectedDrive );
@@ -739,7 +739,7 @@ static void do_fd_action( int drive )
 		    }
 		    else {
 			/* all sectors finished */
-			fd_end_request_cur(0);
+			fd_end_request_cur(BLK_STS_OK);
 			redo_fd_request();
 			return;
 		    }
@@ -1144,7 +1144,7 @@ static void fd_rwsec_done1(int status)
 	}
 	else {
 		/* all sectors finished */
-		fd_end_request_cur(0);
+		fd_end_request_cur(BLK_STS_OK);
 		redo_fd_request();
 	}
 	return;
@@ -1445,7 +1445,7 @@ repeat:
 	if (!UD.connected) {
 		/* drive not connected */
 		printk(KERN_ERR "Unknown Device: fd%d\n", drive );
-		fd_end_request_cur(-EIO);
+		fd_end_request_cur(BLK_STS_IOERR);
 		goto repeat;
 	}
 		
@@ -1461,12 +1461,12 @@ repeat:
 		/* user supplied disk type */
 		if (--type >= NUM_DISK_MINORS) {
 			printk(KERN_WARNING "fd%d: invalid disk format", drive );
-			fd_end_request_cur(-EIO);
+			fd_end_request_cur(BLK_STS_IOERR);
 			goto repeat;
 		}
 		if (minor2disktype[type].drive_types > DriveType)  {
 			printk(KERN_WARNING "fd%d: unsupported disk format", drive );
-			fd_end_request_cur(-EIO);
+			fd_end_request_cur(BLK_STS_IOERR);
 			goto repeat;
 		}
 		type = minor2disktype[type].index;
@@ -1476,7 +1476,7 @@ repeat:
 	}
 	
 	if (blk_rq_pos(fd_request) + 1 > UDT->blocks) {
-		fd_end_request_cur(-EIO);
+		fd_end_request_cur(BLK_STS_IOERR);
 		goto repeat;
 	}
 

drivers/block/brd.c

@@ -418,7 +418,6 @@ static struct brd_device *brd_alloc(int i)
 
 	blk_queue_make_request(brd->brd_queue, brd_make_request);
 	blk_queue_max_hw_sectors(brd->brd_queue, 1024);
-	blk_queue_bounce_limit(brd->brd_queue, BLK_BOUNCE_ANY);
 
 	/* This is so fdisk will align partitions on 4k, because of
 	 * direct_access API needing 4k alignment, returning a PFN

drivers/block/cciss.c

@@ -1864,7 +1864,8 @@ static void cciss_softirq_done(struct request *rq)
 	/* set the residual count for pc requests */
 	if (blk_rq_is_passthrough(rq))
 		scsi_req(rq)->resid_len = c->err_info->ResidualCnt;
-	blk_end_request_all(rq, scsi_req(rq)->result ? -EIO : 0);
+	blk_end_request_all(rq, scsi_req(rq)->result ?
+			BLK_STS_IOERR : BLK_STS_OK);
 
 	spin_lock_irqsave(&h->lock, flags);
 	cmd_free(h, c);
@@ -1956,6 +1957,7 @@ static int cciss_add_disk(ctlr_info_t *h, struct gendisk *disk,
 	disk->queue->cmd_size = sizeof(struct scsi_request);
 	disk->queue->request_fn = do_cciss_request;
 	disk->queue->queue_lock = &h->lock;
+	queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, disk->queue);
 	if (blk_init_allocated_queue(disk->queue) < 0)
 		goto cleanup_queue;
 

drivers/block/drbd/drbd_actlog.c

@@ -178,7 +178,7 @@ static int _drbd_md_sync_page_io(struct drbd_device *device,
 	else
 		submit_bio(bio);
 	wait_until_done_or_force_detached(device, bdev, &device->md_io.done);
-	if (!bio->bi_error)
+	if (!bio->bi_status)
 		err = device->md_io.error;
 
  out:

drivers/block/drbd/drbd_bitmap.c

@@ -959,16 +959,16 @@ static void drbd_bm_endio(struct bio *bio)
 	    !bm_test_page_unchanged(b->bm_pages[idx]))
 		drbd_warn(device, "bitmap page idx %u changed during IO!\n", idx);
 
-	if (bio->bi_error) {
+	if (bio->bi_status) {
 		/* ctx error will hold the completed-last non-zero error code,
 		 * in case error codes differ. */
-		ctx->error = bio->bi_error;
+		ctx->error = blk_status_to_errno(bio->bi_status);
 		bm_set_page_io_err(b->bm_pages[idx]);
 		/* Not identical to on disk version of it.
 		 * Is BM_PAGE_IO_ERROR enough? */
 		if (__ratelimit(&drbd_ratelimit_state))
 			drbd_err(device, "IO ERROR %d on bitmap page idx %u\n",
-					bio->bi_error, idx);
+					bio->bi_status, idx);
 	} else {
 		bm_clear_page_io_err(b->bm_pages[idx]);
 		dynamic_drbd_dbg(device, "bitmap page idx %u completed\n", idx);

drivers/block/drbd/drbd_int.h

@@ -1441,6 +1441,9 @@ extern struct bio_set *drbd_md_io_bio_set;
 /* to allocate from that set */
 extern struct bio *bio_alloc_drbd(gfp_t gfp_mask);
 
+/* And a bio_set for cloning */
+extern struct bio_set *drbd_io_bio_set;
+
 extern struct mutex resources_mutex;
 
 extern int conn_lowest_minor(struct drbd_connection *connection);
@@ -1627,7 +1630,7 @@ static inline void drbd_generic_make_request(struct drbd_device *device,
 	__release(local);
 	if (!bio->bi_bdev) {
 		drbd_err(device, "drbd_generic_make_request: bio->bi_bdev == NULL\n");
-		bio->bi_error = -ENODEV;
+		bio->bi_status = BLK_STS_IOERR;
 		bio_endio(bio);
 		return;
 	}

drivers/block/drbd/drbd_main.c

@@ -128,6 +128,7 @@ mempool_t *drbd_request_mempool;
 mempool_t *drbd_ee_mempool;
 mempool_t *drbd_md_io_page_pool;
 struct bio_set *drbd_md_io_bio_set;
+struct bio_set *drbd_io_bio_set;
 
 /* I do not use a standard mempool, because:
    1) I want to hand out the pre-allocated objects first.
@@ -2098,6 +2099,8 @@ static void drbd_destroy_mempools(void)
 
 	/* D_ASSERT(device, atomic_read(&drbd_pp_vacant)==0); */
 
+	if (drbd_io_bio_set)
+		bioset_free(drbd_io_bio_set);
 	if (drbd_md_io_bio_set)
 		bioset_free(drbd_md_io_bio_set);
 	if (drbd_md_io_page_pool)
@@ -2115,6 +2118,7 @@ static void drbd_destroy_mempools(void)
 	if (drbd_al_ext_cache)
 		kmem_cache_destroy(drbd_al_ext_cache);
 
+	drbd_io_bio_set      = NULL;
 	drbd_md_io_bio_set   = NULL;
 	drbd_md_io_page_pool = NULL;
 	drbd_ee_mempool      = NULL;
@@ -2142,6 +2146,7 @@ static int drbd_create_mempools(void)
 	drbd_pp_pool         = NULL;
 	drbd_md_io_page_pool = NULL;
 	drbd_md_io_bio_set   = NULL;
+	drbd_io_bio_set      = NULL;
 
 	/* caches */
 	drbd_request_cache = kmem_cache_create(
@@ -2165,7 +2170,13 @@ static int drbd_create_mempools(void)
 		goto Enomem;
 
 	/* mempools */
-	drbd_md_io_bio_set = bioset_create(DRBD_MIN_POOL_PAGES, 0);
+	drbd_io_bio_set = bioset_create(BIO_POOL_SIZE, 0, BIOSET_NEED_RESCUER);
+	if (drbd_io_bio_set == NULL)
+		goto Enomem;
+
+	drbd_md_io_bio_set = bioset_create(DRBD_MIN_POOL_PAGES, 0,
+					   BIOSET_NEED_BVECS |
+					   BIOSET_NEED_RESCUER);
 	if (drbd_md_io_bio_set == NULL)
 		goto Enomem;
 
@@ -2839,7 +2850,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
 	/* Setting the max_hw_sectors to an odd value of 8kibyte here
 	   This triggers a max_bio_size message upon first attach or connect */
 	blk_queue_max_hw_sectors(q, DRBD_MAX_BIO_SIZE_SAFE >> 8);
-	blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
 	q->queue_lock = &resource->req_lock;
 
 	device->md_io.page = alloc_page(GFP_KERNEL);

drivers/block/drbd/drbd_nl.c

@@ -2294,7 +2294,7 @@ _check_net_options(struct drbd_connection *connection, struct net_conf *old_net_
 static enum drbd_ret_code
 check_net_options(struct drbd_connection *connection, struct net_conf *new_net_conf)
 {
-	static enum drbd_ret_code rv;
+	enum drbd_ret_code rv;
 	struct drbd_peer_device *peer_device;
 	int i;
 

drivers/block/drbd/drbd_receiver.c

@@ -1229,9 +1229,9 @@ void one_flush_endio(struct bio *bio)
 	struct drbd_device *device = octx->device;
 	struct issue_flush_context *ctx = octx->ctx;
 
-	if (bio->bi_error) {
-		ctx->error = bio->bi_error;
-		drbd_info(device, "local disk FLUSH FAILED with status %d\n", bio->bi_error);
+	if (bio->bi_status) {
+		ctx->error = blk_status_to_errno(bio->bi_status);
+		drbd_info(device, "local disk FLUSH FAILED with status %d\n", bio->bi_status);
 	}
 	kfree(octx);
 	bio_put(bio);

drivers/block/drbd/drbd_req.c

@@ -203,7 +203,7 @@ void start_new_tl_epoch(struct drbd_connection *connection)
 void complete_master_bio(struct drbd_device *device,
 		struct bio_and_error *m)
 {
-	m->bio->bi_error = m->error;
+	m->bio->bi_status = errno_to_blk_status(m->error);
 	bio_endio(m->bio);
 	dec_ap_bio(device);
 }
@@ -1157,7 +1157,7 @@ static void drbd_process_discard_req(struct drbd_request *req)
 
 	if (blkdev_issue_zeroout(bdev, req->i.sector, req->i.size >> 9,
 			GFP_NOIO, 0))
-		req->private_bio->bi_error = -EIO;
+		req->private_bio->bi_status = BLK_STS_IOERR;
 	bio_endio(req->private_bio);
 }
 
@@ -1225,7 +1225,7 @@ drbd_request_prepare(struct drbd_device *device, struct bio *bio, unsigned long
 		/* only pass the error to the upper layers.
 		 * if user cannot handle io errors, that's not our business. */
 		drbd_err(device, "could not kmalloc() req\n");
-		bio->bi_error = -ENOMEM;
+		bio->bi_status = BLK_STS_RESOURCE;
 		bio_endio(bio);
 		return ERR_PTR(-ENOMEM);
 	}
@@ -1560,7 +1560,7 @@ blk_qc_t drbd_make_request(struct request_queue *q, struct bio *bio)
 	struct drbd_device *device = (struct drbd_device *) q->queuedata;
 	unsigned long start_jif;
 
-	blk_queue_split(q, &bio, q->bio_split);
+	blk_queue_split(q, &bio);
 
 	start_jif = jiffies;
 

drivers/block/drbd/drbd_req.h

@@ -263,7 +263,7 @@ enum drbd_req_state_bits {
 static inline void drbd_req_make_private_bio(struct drbd_request *req, struct bio *bio_src)
 {
 	struct bio *bio;
-	bio = bio_clone(bio_src, GFP_NOIO); /* XXX cannot fail?? */
+	bio = bio_clone_fast(bio_src, GFP_NOIO, drbd_io_bio_set);
 
 	req->private_bio = bio;
 

drivers/block/drbd/drbd_worker.c

@@ -63,7 +63,7 @@ void drbd_md_endio(struct bio *bio)
 	struct drbd_device *device;
 
 	device = bio->bi_private;
-	device->md_io.error = bio->bi_error;
+	device->md_io.error = blk_status_to_errno(bio->bi_status);
 
 	/* We grabbed an extra reference in _drbd_md_sync_page_io() to be able
 	 * to timeout on the lower level device, and eventually detach from it.
@@ -177,13 +177,13 @@ void drbd_peer_request_endio(struct bio *bio)
 	bool is_discard = bio_op(bio) == REQ_OP_WRITE_ZEROES ||
 			  bio_op(bio) == REQ_OP_DISCARD;
 
-	if (bio->bi_error && __ratelimit(&drbd_ratelimit_state))
+	if (bio->bi_status && __ratelimit(&drbd_ratelimit_state))
 		drbd_warn(device, "%s: error=%d s=%llus\n",
 				is_write ? (is_discard ? "discard" : "write")
-					: "read", bio->bi_error,
+					: "read", bio->bi_status,
 				(unsigned long long)peer_req->i.sector);
 
-	if (bio->bi_error)
+	if (bio->bi_status)
 		set_bit(__EE_WAS_ERROR, &peer_req->flags);
 
 	bio_put(bio); /* no need for the bio anymore */
@@ -243,16 +243,16 @@ void drbd_request_endio(struct bio *bio)
 		if (__ratelimit(&drbd_ratelimit_state))
 			drbd_emerg(device, "delayed completion of aborted local request; disk-timeout may be too aggressive\n");
 
-		if (!bio->bi_error)
+		if (!bio->bi_status)
 			drbd_panic_after_delayed_completion_of_aborted_request(device);
 	}
 
 	/* to avoid recursion in __req_mod */
-	if (unlikely(bio->bi_error)) {
+	if (unlikely(bio->bi_status)) {
 		switch (bio_op(bio)) {
 		case REQ_OP_WRITE_ZEROES:
 		case REQ_OP_DISCARD:
-			if (bio->bi_error == -EOPNOTSUPP)
+			if (bio->bi_status == BLK_STS_NOTSUPP)
 				what = DISCARD_COMPLETED_NOTSUPP;
 			else
 				what = DISCARD_COMPLETED_WITH_ERROR;
@@ -272,7 +272,7 @@ void drbd_request_endio(struct bio *bio)
 	}
 
 	bio_put(req->private_bio);
-	req->private_bio = ERR_PTR(bio->bi_error);
+	req->private_bio = ERR_PTR(blk_status_to_errno(bio->bi_status));
 
 	/* not req_mod(), we need irqsave here! */
 	spin_lock_irqsave(&device->resource->req_lock, flags);

drivers/block/floppy.c

@@ -2202,7 +2202,7 @@ static int do_format(int drive, struct format_descr *tmp_format_req)
  * =============================
  */
 
-static void floppy_end_request(struct request *req, int error)
+static void floppy_end_request(struct request *req, blk_status_t error)
 {
 	unsigned int nr_sectors = current_count_sectors;
 	unsigned int drive = (unsigned long)req->rq_disk->private_data;
@@ -2263,7 +2263,7 @@ static void request_done(int uptodate)
 			DRWE->last_error_generation = DRS->generation;
 		}
 		spin_lock_irqsave(q->queue_lock, flags);
-		floppy_end_request(req, -EIO);
+		floppy_end_request(req, BLK_STS_IOERR);
 		spin_unlock_irqrestore(q->queue_lock, flags);
 	}
 }
@@ -3780,9 +3780,9 @@ static void floppy_rb0_cb(struct bio *bio)
 	struct rb0_cbdata *cbdata = (struct rb0_cbdata *)bio->bi_private;
 	int drive = cbdata->drive;
 
-	if (bio->bi_error) {
+	if (bio->bi_status) {
 		pr_info("floppy: error %d while reading block 0\n",
-			bio->bi_error);
+			bio->bi_status);
 		set_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags);
 	}
 	complete(&cbdata->complete);
@@ -4203,6 +4203,7 @@ static int __init do_floppy_init(void)
 			goto out_put_disk;
 		}
 
+		blk_queue_bounce_limit(disks[drive]->queue, BLK_BOUNCE_HIGH);
 		blk_queue_max_hw_sectors(disks[drive]->queue, 64);
 		disks[drive]->major = FLOPPY_MAJOR;
 		disks[drive]->first_minor = TOMINOR(drive);

drivers/block/loop.c

@@ -221,7 +221,8 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
 }
 
 static int
-figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
+figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit,
+		 loff_t logical_blocksize)
 {
 	loff_t size = get_size(offset, sizelimit, lo->lo_backing_file);
 	sector_t x = (sector_t)size;
@@ -233,6 +234,12 @@ figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
 		lo->lo_offset = offset;
 	if (lo->lo_sizelimit != sizelimit)
 		lo->lo_sizelimit = sizelimit;
+	if (lo->lo_flags & LO_FLAGS_BLOCKSIZE) {
+		lo->lo_logical_blocksize = logical_blocksize;
+		blk_queue_physical_block_size(lo->lo_queue, lo->lo_blocksize);
+		blk_queue_logical_block_size(lo->lo_queue,
+					     lo->lo_logical_blocksize);
+	}
 	set_capacity(lo->lo_disk, x);
 	bd_set_size(bdev, (loff_t)get_capacity(bdev->bd_disk) << 9);
 	/* let user-space know about the new size */
@@ -457,7 +464,7 @@ static void lo_complete_rq(struct request *rq)
 		zero_fill_bio(bio);
 	}
 
-	blk_mq_end_request(rq, cmd->ret < 0 ? -EIO : 0);
+	blk_mq_end_request(rq, cmd->ret < 0 ? BLK_STS_IOERR : BLK_STS_OK);
 }
 
 static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
@@ -813,6 +820,7 @@ static void loop_config_discard(struct loop_device *lo)
 	struct file *file = lo->lo_backing_file;
 	struct inode *inode = file->f_mapping->host;
 	struct request_queue *q = lo->lo_queue;
+	int lo_bits = 9;
 
 	/*
 	 * We use punch hole to reclaim the free space used by the
@@ -832,8 +840,11 @@ static void loop_config_discard(struct loop_device *lo)
 
 	q->limits.discard_granularity = inode->i_sb->s_blocksize;
 	q->limits.discard_alignment = 0;
-	blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
-	blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
+	if (lo->lo_flags & LO_FLAGS_BLOCKSIZE)
+		lo_bits = blksize_bits(lo->lo_logical_blocksize);
+
+	blk_queue_max_discard_sectors(q, UINT_MAX >> lo_bits);
+	blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> lo_bits);
 	queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
 }
 
@@ -843,10 +854,16 @@ static void loop_unprepare_queue(struct loop_device *lo)
 	kthread_stop(lo->worker_task);
 }
 
+static int loop_kthread_worker_fn(void *worker_ptr)
+{
+	current->flags |= PF_LESS_THROTTLE;
+	return kthread_worker_fn(worker_ptr);
+}
+
 static int loop_prepare_queue(struct loop_device *lo)
 {
 	kthread_init_worker(&lo->worker);
-	lo->worker_task = kthread_run(kthread_worker_fn,
+	lo->worker_task = kthread_run(loop_kthread_worker_fn,
 			&lo->worker, "loop%d", lo->lo_number);
 	if (IS_ERR(lo->worker_task))
 		return -ENOMEM;
@@ -921,6 +938,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
 
 	lo->use_dio = false;
 	lo->lo_blocksize = lo_blocksize;
+	lo->lo_logical_blocksize = 512;
 	lo->lo_device = bdev;
 	lo->lo_flags = lo_flags;
 	lo->lo_backing_file = file;
@@ -1086,6 +1104,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	int err;
 	struct loop_func_table *xfer;
 	kuid_t uid = current_uid();
+	int lo_flags = lo->lo_flags;
 
 	if (lo->lo_encrypt_key_size &&
 	    !uid_eq(lo->lo_key_owner, uid) &&
@@ -1118,12 +1137,30 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	if (err)
 		goto exit;
 
+	if (info->lo_flags & LO_FLAGS_BLOCKSIZE) {
+		if (!(lo->lo_flags & LO_FLAGS_BLOCKSIZE))
+			lo->lo_logical_blocksize = 512;
+		lo->lo_flags |= LO_FLAGS_BLOCKSIZE;
+		if (LO_INFO_BLOCKSIZE(info) != 512 &&
+		    LO_INFO_BLOCKSIZE(info) != 1024 &&
+		    LO_INFO_BLOCKSIZE(info) != 2048 &&
+		    LO_INFO_BLOCKSIZE(info) != 4096)
+			return -EINVAL;
+		if (LO_INFO_BLOCKSIZE(info) > lo->lo_blocksize)
+			return -EINVAL;
+	}
+
 	if (lo->lo_offset != info->lo_offset ||
-	    lo->lo_sizelimit != info->lo_sizelimit)
-		if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) {
+	    lo->lo_sizelimit != info->lo_sizelimit ||
+	    lo->lo_flags != lo_flags ||
+	    ((lo->lo_flags & LO_FLAGS_BLOCKSIZE) &&
+	     lo->lo_logical_blocksize != LO_INFO_BLOCKSIZE(info))) {
+		if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit,
+				     LO_INFO_BLOCKSIZE(info))) {
 			err = -EFBIG;
 			goto exit;
 		}
+	}
 
 	loop_config_discard(lo);
 
@@ -1306,12 +1343,13 @@ loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) {
 	return err;
 }
 
-static int loop_set_capacity(struct loop_device *lo, struct block_device *bdev)
+static int loop_set_capacity(struct loop_device *lo)
 {
 	if (unlikely(lo->lo_state != Lo_bound))
 		return -ENXIO;
 
-	return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit);
+	return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit,
+				lo->lo_logical_blocksize);
 }
 
 static int loop_set_dio(struct loop_device *lo, unsigned long arg)
@@ -1369,7 +1407,7 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 	case LOOP_SET_CAPACITY:
 		err = -EPERM;
 		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
-			err = loop_set_capacity(lo, bdev);
+			err = loop_set_capacity(lo);
 		break;
 	case LOOP_SET_DIRECT_IO:
 		err = -EPERM;
@@ -1645,7 +1683,7 @@ int loop_unregister_transfer(int number)
 EXPORT_SYMBOL(loop_register_transfer);
 EXPORT_SYMBOL(loop_unregister_transfer);
 
-static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 		const struct blk_mq_queue_data *bd)
 {
 	struct loop_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
@@ -1654,7 +1692,7 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	blk_mq_start_request(bd->rq);
 
 	if (lo->lo_state != Lo_bound)
-		return BLK_MQ_RQ_QUEUE_ERROR;
+		return BLK_STS_IOERR;
 
 	switch (req_op(cmd->rq)) {
 	case REQ_OP_FLUSH:
@@ -1669,7 +1707,7 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	kthread_queue_work(&lo->worker, &cmd->work);
 
-	return BLK_MQ_RQ_QUEUE_OK;
+	return BLK_STS_OK;
 }
 
 static void loop_handle_cmd(struct loop_cmd *cmd)

drivers/block/loop.h

@@ -49,6 +49,7 @@ struct loop_device {
 	struct file *	lo_backing_file;
 	struct block_device *lo_device;
 	unsigned	lo_blocksize;
+	unsigned	lo_logical_blocksize;
 	void		*key_data; 
 
 	gfp_t		old_gfp_mask;

drivers/block/mtip32xx/mtip32xx.c

@@ -532,7 +532,7 @@ static int mtip_read_log_page(struct mtip_port *port, u8 page, u16 *buffer,
 static int mtip_get_smart_attr(struct mtip_port *port, unsigned int id,
 						struct smart_attr *attrib);
 
-static void mtip_complete_command(struct mtip_cmd *cmd, int status)
+static void mtip_complete_command(struct mtip_cmd *cmd, blk_status_t status)
 {
 	struct request *req = blk_mq_rq_from_pdu(cmd);
 
@@ -568,7 +568,7 @@ static void mtip_handle_tfe(struct driver_data *dd)
 	if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &port->flags)) {
 		cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL);
 		dbg_printk(MTIP_DRV_NAME " TFE for the internal command\n");
-		mtip_complete_command(cmd, -EIO);
+		mtip_complete_command(cmd, BLK_STS_IOERR);
 		return;
 	}
 
@@ -667,7 +667,7 @@ static void mtip_handle_tfe(struct driver_data *dd)
 					tag,
 					fail_reason != NULL ?
 						fail_reason : "unknown");
-					mtip_complete_command(cmd, -ENODATA);
+					mtip_complete_command(cmd, BLK_STS_MEDIUM);
 					continue;
 				}
 			}
@@ -690,7 +690,7 @@ static void mtip_handle_tfe(struct driver_data *dd)
 			dev_warn(&port->dd->pdev->dev,
 				"retiring tag %d\n", tag);
 
-			mtip_complete_command(cmd, -EIO);
+			mtip_complete_command(cmd, BLK_STS_IOERR);
 		}
 	}
 	print_tags(dd, "reissued (TFE)", tagaccum, cmd_cnt);
@@ -1063,23 +1063,10 @@ static int mtip_exec_internal_command(struct mtip_port *port,
 	/* insert request and run queue */
 	blk_execute_rq(rq->q, NULL, rq, true);
 
-	rv = int_cmd->status;
-	if (rv < 0) {
-		if (rv == -ERESTARTSYS) { /* interrupted */
-			dev_err(&dd->pdev->dev,
-				"Internal command [%02X] was interrupted after %u ms\n",
-				fis->command,
-				jiffies_to_msecs(jiffies - start));
-			rv = -EINTR;
-			goto exec_ic_exit;
-		} else if (rv == 0) /* timeout */
-			dev_err(&dd->pdev->dev,
-				"Internal command did not complete [%02X] within timeout of  %lu ms\n",
-				fis->command, timeout);
-		else
-			dev_err(&dd->pdev->dev,
-				"Internal command [%02X] wait returned code [%d] after %lu ms - unhandled\n",
-				fis->command, rv, timeout);
+	if (int_cmd->status) {
+		dev_err(&dd->pdev->dev, "Internal command [%02X] failed %d\n",
+				fis->command, int_cmd->status);
+		rv = -EIO;
 
 		if (mtip_check_surprise_removal(dd->pdev) ||
 			test_bit(MTIP_DDF_REMOVE_PENDING_BIT,
@@ -2753,7 +2740,7 @@ static void mtip_abort_cmd(struct request *req, void *data,
 	dbg_printk(MTIP_DRV_NAME " Aborting request, tag = %d\n", req->tag);
 
 	clear_bit(req->tag, dd->port->cmds_to_issue);
-	cmd->status = -EIO;
+	cmd->status = BLK_STS_IOERR;
 	mtip_softirq_done_fn(req);
 }
 
@@ -3597,7 +3584,7 @@ static int mtip_submit_request(struct blk_mq_hw_ctx *hctx, struct request *rq)
 		int err;
 
 		err = mtip_send_trim(dd, blk_rq_pos(rq), blk_rq_sectors(rq));
-		blk_mq_end_request(rq, err);
+		blk_mq_end_request(rq, err ? BLK_STS_IOERR : BLK_STS_OK);
 		return 0;
 	}
 
@@ -3633,8 +3620,8 @@ static bool mtip_check_unal_depth(struct blk_mq_hw_ctx *hctx,
 	return false;
 }
 
-static int mtip_issue_reserved_cmd(struct blk_mq_hw_ctx *hctx,
-				   struct request *rq)
+static blk_status_t mtip_issue_reserved_cmd(struct blk_mq_hw_ctx *hctx,
+		struct request *rq)
 {
 	struct driver_data *dd = hctx->queue->queuedata;
 	struct mtip_int_cmd *icmd = rq->special;
@@ -3642,7 +3629,7 @@ static int mtip_issue_reserved_cmd(struct blk_mq_hw_ctx *hctx,
 	struct mtip_cmd_sg *command_sg;
 
 	if (mtip_commands_active(dd->port))
-		return BLK_MQ_RQ_QUEUE_BUSY;
+		return BLK_STS_RESOURCE;
 
 	/* Populate the SG list */
 	cmd->command_header->opts =
@@ -3666,10 +3653,10 @@ static int mtip_issue_reserved_cmd(struct blk_mq_hw_ctx *hctx,
 
 	blk_mq_start_request(rq);
 	mtip_issue_non_ncq_command(dd->port, rq->tag);
-	return BLK_MQ_RQ_QUEUE_OK;
+	return 0;
 }
 
-static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t mtip_queue_rq(struct blk_mq_hw_ctx *hctx,
 			 const struct blk_mq_queue_data *bd)
 {
 	struct request *rq = bd->rq;
@@ -3681,15 +3668,14 @@ static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx,
 		return mtip_issue_reserved_cmd(hctx, rq);
 
 	if (unlikely(mtip_check_unal_depth(hctx, rq)))
-		return BLK_MQ_RQ_QUEUE_BUSY;
+		return BLK_STS_RESOURCE;
 
 	blk_mq_start_request(rq);
 
 	ret = mtip_submit_request(hctx, rq);
 	if (likely(!ret))
-		return BLK_MQ_RQ_QUEUE_OK;
-
-	return BLK_MQ_RQ_QUEUE_ERROR;
+		return BLK_STS_OK;
+	return BLK_STS_IOERR;
 }
 
 static void mtip_free_cmd(struct blk_mq_tag_set *set, struct request *rq,
@@ -3730,7 +3716,7 @@ static enum blk_eh_timer_return mtip_cmd_timeout(struct request *req,
 	if (reserved) {
 		struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req);
 
-		cmd->status = -ETIME;
+		cmd->status = BLK_STS_TIMEOUT;
 		return BLK_EH_HANDLED;
 	}
 
@@ -3961,7 +3947,7 @@ static void mtip_no_dev_cleanup(struct request *rq, void *data, bool reserv)
 {
 	struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
 
-	cmd->status = -ENODEV;
+	cmd->status = BLK_STS_IOERR;
 	blk_mq_complete_request(rq);
 }
 

drivers/block/mtip32xx/mtip32xx.h

@@ -342,7 +342,7 @@ struct mtip_cmd {
 	int retries; /* The number of retries left for this command. */
 
 	int direction; /* Data transfer direction */
-	int status;
+	blk_status_t status;
 };
 
 /* Structure used to describe a port. */

drivers/block/nbd.c

@@ -116,7 +116,7 @@ struct nbd_cmd {
 	int index;
 	int cookie;
 	struct completion send_complete;
-	int status;
+	blk_status_t status;
 };
 
 #if IS_ENABLED(CONFIG_DEBUG_FS)
@@ -286,7 +286,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 	struct nbd_config *config;
 
 	if (!refcount_inc_not_zero(&nbd->config_refs)) {
-		cmd->status = -EIO;
+		cmd->status = BLK_STS_TIMEOUT;
 		return BLK_EH_HANDLED;
 	}
 
@@ -331,7 +331,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 				    "Connection timed out\n");
 	}
 	set_bit(NBD_TIMEDOUT, &config->runtime_flags);
-	cmd->status = -EIO;
+	cmd->status = BLK_STS_IOERR;
 	sock_shutdown(nbd);
 	nbd_config_put(nbd);
 
@@ -400,6 +400,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	unsigned long size = blk_rq_bytes(req);
 	struct bio *bio;
 	u32 type;
+	u32 nbd_cmd_flags = 0;
 	u32 tag = blk_mq_unique_tag(req);
 	int sent = nsock->sent, skip = 0;
 
@@ -429,6 +430,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 		return -EIO;
 	}
 
+	if (req->cmd_flags & REQ_FUA)
+		nbd_cmd_flags |= NBD_CMD_FLAG_FUA;
+
 	/* We did a partial send previously, and we at least sent the whole
 	 * request struct, so just go and send the rest of the pages in the
 	 * request.
@@ -442,7 +446,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	}
 	cmd->index = index;
 	cmd->cookie = nsock->cookie;
-	request.type = htonl(type);
+	request.type = htonl(type | nbd_cmd_flags);
 	if (type != NBD_CMD_FLUSH) {
 		request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
 		request.len = htonl(size);
@@ -465,7 +469,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 				nsock->pending = req;
 				nsock->sent = sent;
 			}
-			return BLK_MQ_RQ_QUEUE_BUSY;
+			return BLK_STS_RESOURCE;
 		}
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 			"Send control failed (result %d)\n", result);
@@ -506,7 +510,7 @@ send_pages:
 					 */
 					nsock->pending = req;
 					nsock->sent = sent;
-					return BLK_MQ_RQ_QUEUE_BUSY;
+					return BLK_STS_RESOURCE;
 				}
 				dev_err(disk_to_dev(nbd->disk),
 					"Send data failed (result %d)\n",
@@ -574,7 +578,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 	if (ntohl(reply.error)) {
 		dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n",
 			ntohl(reply.error));
-		cmd->status = -EIO;
+		cmd->status = BLK_STS_IOERR;
 		return cmd;
 	}
 
@@ -599,7 +603,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 				 */
 				if (nbd_disconnected(config) ||
 				    config->num_connections <= 1) {
-					cmd->status = -EIO;
+					cmd->status = BLK_STS_IOERR;
 					return cmd;
 				}
 				return ERR_PTR(-EIO);
@@ -651,7 +655,7 @@ static void nbd_clear_req(struct request *req, void *data, bool reserved)
 	if (!blk_mq_request_started(req))
 		return;
 	cmd = blk_mq_rq_to_pdu(req);
-	cmd->status = -EIO;
+	cmd->status = BLK_STS_IOERR;
 	blk_mq_complete_request(req);
 }
 
@@ -740,7 +744,7 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
 		nbd_config_put(nbd);
 		return -EINVAL;
 	}
-	cmd->status = 0;
+	cmd->status = BLK_STS_OK;
 again:
 	nsock = config->socks[index];
 	mutex_lock(&nsock->tx_lock);
@@ -794,7 +798,7 @@ out:
 	return ret;
 }
 
-static int nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 			const struct blk_mq_queue_data *bd)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
@@ -818,13 +822,9 @@ static int nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 * appropriate.
 	 */
 	ret = nbd_handle_cmd(cmd, hctx->queue_num);
-	if (ret < 0)
-		ret = BLK_MQ_RQ_QUEUE_ERROR;
-	if (!ret)
-		ret = BLK_MQ_RQ_QUEUE_OK;
 	complete(&cmd->send_complete);
 
-	return ret;
+	return ret < 0 ? BLK_STS_IOERR : BLK_STS_OK;
 }
 
 static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
@@ -910,6 +910,7 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
 			continue;
 		}
 		sk_set_memalloc(sock->sk);
+		sock->sk->sk_sndtimeo = nbd->tag_set.timeout;
 		atomic_inc(&config->recv_threads);
 		refcount_inc(&nbd->config_refs);
 		old = nsock->sock;
@@ -957,8 +958,12 @@ static void nbd_parse_flags(struct nbd_device *nbd)
 		set_disk_ro(nbd->disk, false);
 	if (config->flags & NBD_FLAG_SEND_TRIM)
 		queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
-	if (config->flags & NBD_FLAG_SEND_FLUSH)
-		blk_queue_write_cache(nbd->disk->queue, true, false);
+	if (config->flags & NBD_FLAG_SEND_FLUSH) {
+		if (config->flags & NBD_FLAG_SEND_FUA)
+			blk_queue_write_cache(nbd->disk->queue, true, true);
+		else
+			blk_queue_write_cache(nbd->disk->queue, true, false);
+	}
 	else
 		blk_queue_write_cache(nbd->disk->queue, false, false);
 }
@@ -1071,6 +1076,7 @@ static int nbd_start_device(struct nbd_device *nbd)
 			return -ENOMEM;
 		}
 		sk_set_memalloc(config->socks[i]->sock->sk);
+		config->socks[i]->sock->sk->sk_sndtimeo = nbd->tag_set.timeout;
 		atomic_inc(&config->recv_threads);
 		refcount_inc(&nbd->config_refs);
 		INIT_WORK(&args->work, recv_work);
@@ -1305,6 +1311,8 @@ static int nbd_dbg_flags_show(struct seq_file *s, void *unused)
 		seq_puts(s, "NBD_FLAG_READ_ONLY\n");
 	if (flags & NBD_FLAG_SEND_FLUSH)
 		seq_puts(s, "NBD_FLAG_SEND_FLUSH\n");
+	if (flags & NBD_FLAG_SEND_FUA)
+		seq_puts(s, "NBD_FLAG_SEND_FUA\n");
 	if (flags & NBD_FLAG_SEND_TRIM)
 		seq_puts(s, "NBD_FLAG_SEND_TRIM\n");
 

drivers/block/null_blk.c

@@ -35,7 +35,8 @@ struct nullb {
 	struct request_queue *q;
 	struct gendisk *disk;
 	struct nvm_dev *ndev;
-	struct blk_mq_tag_set tag_set;
+	struct blk_mq_tag_set *tag_set;
+	struct blk_mq_tag_set __tag_set;
 	struct hrtimer timer;
 	unsigned int queue_depth;
 	spinlock_t lock;
@@ -50,6 +51,7 @@ static struct mutex lock;
 static int null_major;
 static int nullb_indexes;
 static struct kmem_cache *ppa_cache;
+static struct blk_mq_tag_set tag_set;
 
 enum {
 	NULL_IRQ_NONE		= 0,
@@ -109,7 +111,7 @@ static int bs = 512;
 module_param(bs, int, S_IRUGO);
 MODULE_PARM_DESC(bs, "Block size (in bytes)");
 
-static int nr_devices = 2;
+static int nr_devices = 1;
 module_param(nr_devices, int, S_IRUGO);
 MODULE_PARM_DESC(nr_devices, "Number of devices to register");
 
@@ -121,6 +123,10 @@ static bool blocking;
 module_param(blocking, bool, S_IRUGO);
 MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device");
 
+static bool shared_tags;
+module_param(shared_tags, bool, S_IRUGO);
+MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq");
+
 static int irqmode = NULL_IRQ_SOFTIRQ;
 
 static int null_set_irqmode(const char *str, const struct kernel_param *kp)
@@ -229,11 +235,11 @@ static void end_cmd(struct nullb_cmd *cmd)
 
 	switch (queue_mode)  {
 	case NULL_Q_MQ:
-		blk_mq_end_request(cmd->rq, 0);
+		blk_mq_end_request(cmd->rq, BLK_STS_OK);
 		return;
 	case NULL_Q_RQ:
 		INIT_LIST_HEAD(&cmd->rq->queuelist);
-		blk_end_request_all(cmd->rq, 0);
+		blk_end_request_all(cmd->rq, BLK_STS_OK);
 		break;
 	case NULL_Q_BIO:
 		bio_endio(cmd->bio);
@@ -356,7 +362,7 @@ static void null_request_fn(struct request_queue *q)
 	}
 }
 
-static int null_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 			 const struct blk_mq_queue_data *bd)
 {
 	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
@@ -373,34 +379,11 @@ static int null_queue_rq(struct blk_mq_hw_ctx *hctx,
 	blk_mq_start_request(bd->rq);
 
 	null_handle_cmd(cmd);
-	return BLK_MQ_RQ_QUEUE_OK;
-}
-
-static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
-{
-	BUG_ON(!nullb);
-	BUG_ON(!nq);
-
-	init_waitqueue_head(&nq->wait);
-	nq->queue_depth = nullb->queue_depth;
-}
-
-static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
-			  unsigned int index)
-{
-	struct nullb *nullb = data;
-	struct nullb_queue *nq = &nullb->queues[index];
-
-	hctx->driver_data = nq;
-	null_init_queue(nullb, nq);
-	nullb->nr_queues++;
-
-	return 0;
+	return BLK_STS_OK;
 }
 
 static const struct blk_mq_ops null_mq_ops = {
 	.queue_rq       = null_queue_rq,
-	.init_hctx	= null_init_hctx,
 	.complete	= null_softirq_done_fn,
 };
 
@@ -422,11 +405,12 @@ static void cleanup_queues(struct nullb *nullb)
 
 #ifdef CONFIG_NVM
 
-static void null_lnvm_end_io(struct request *rq, int error)
+static void null_lnvm_end_io(struct request *rq, blk_status_t status)
 {
 	struct nvm_rq *rqd = rq->end_io_data;
 
-	rqd->error = error;
+	/* XXX: lighnvm core seems to expect NVM_RSP_* values here.. */
+	rqd->error = status ? -EIO : 0;
 	nvm_end_io(rqd);
 
 	blk_put_request(rq);
@@ -591,8 +575,8 @@ static void null_del_dev(struct nullb *nullb)
 	else
 		del_gendisk(nullb->disk);
 	blk_cleanup_queue(nullb->q);
-	if (queue_mode == NULL_Q_MQ)
-		blk_mq_free_tag_set(&nullb->tag_set);
+	if (queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set)
+		blk_mq_free_tag_set(nullb->tag_set);
 	if (!use_lightnvm)
 		put_disk(nullb->disk);
 	cleanup_queues(nullb);
@@ -614,6 +598,32 @@ static const struct block_device_operations null_fops = {
 	.release =	null_release,
 };
 
+static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
+{
+	BUG_ON(!nullb);
+	BUG_ON(!nq);
+
+	init_waitqueue_head(&nq->wait);
+	nq->queue_depth = nullb->queue_depth;
+}
+
+static void null_init_queues(struct nullb *nullb)
+{
+	struct request_queue *q = nullb->q;
+	struct blk_mq_hw_ctx *hctx;
+	struct nullb_queue *nq;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (!hctx->nr_ctx || !hctx->tags)
+			continue;
+		nq = &nullb->queues[i];
+		hctx->driver_data = nq;
+		null_init_queue(nullb, nq);
+		nullb->nr_queues++;
+	}
+}
+
 static int setup_commands(struct nullb_queue *nq)
 {
 	struct nullb_cmd *cmd;
@@ -694,6 +704,22 @@ static int null_gendisk_register(struct nullb *nullb)
 	return 0;
 }
 
+static int null_init_tag_set(struct blk_mq_tag_set *set)
+{
+	set->ops = &null_mq_ops;
+	set->nr_hw_queues = submit_queues;
+	set->queue_depth = hw_queue_depth;
+	set->numa_node = home_node;
+	set->cmd_size	= sizeof(struct nullb_cmd);
+	set->flags = BLK_MQ_F_SHOULD_MERGE;
+	set->driver_data = NULL;
+
+	if (blocking)
+		set->flags |= BLK_MQ_F_BLOCKING;
+
+	return blk_mq_alloc_tag_set(set);
+}
+
 static int null_add_dev(void)
 {
 	struct nullb *nullb;
@@ -715,26 +741,23 @@ static int null_add_dev(void)
 		goto out_free_nullb;
 
 	if (queue_mode == NULL_Q_MQ) {
-		nullb->tag_set.ops = &null_mq_ops;
-		nullb->tag_set.nr_hw_queues = submit_queues;
-		nullb->tag_set.queue_depth = hw_queue_depth;
-		nullb->tag_set.numa_node = home_node;
-		nullb->tag_set.cmd_size	= sizeof(struct nullb_cmd);
-		nullb->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
-		nullb->tag_set.driver_data = nullb;
-
-		if (blocking)
-			nullb->tag_set.flags |= BLK_MQ_F_BLOCKING;
-
-		rv = blk_mq_alloc_tag_set(&nullb->tag_set);
+		if (shared_tags) {
+			nullb->tag_set = &tag_set;
+			rv = 0;
+		} else {
+			nullb->tag_set = &nullb->__tag_set;
+			rv = null_init_tag_set(nullb->tag_set);
+		}
+
 		if (rv)
 			goto out_cleanup_queues;
 
-		nullb->q = blk_mq_init_queue(&nullb->tag_set);
+		nullb->q = blk_mq_init_queue(nullb->tag_set);
 		if (IS_ERR(nullb->q)) {
 			rv = -ENOMEM;
 			goto out_cleanup_tags;
 		}
+		null_init_queues(nullb);
 	} else if (queue_mode == NULL_Q_BIO) {
 		nullb->q = blk_alloc_queue_node(GFP_KERNEL, home_node);
 		if (!nullb->q) {
@@ -787,8 +810,8 @@ static int null_add_dev(void)
 out_cleanup_blk_queue:
 	blk_cleanup_queue(nullb->q);
 out_cleanup_tags:
-	if (queue_mode == NULL_Q_MQ)
-		blk_mq_free_tag_set(&nullb->tag_set);
+	if (queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set)
+		blk_mq_free_tag_set(nullb->tag_set);
 out_cleanup_queues:
 	cleanup_queues(nullb);
 out_free_nullb:
@@ -821,6 +844,9 @@ static int __init null_init(void)
 		queue_mode = NULL_Q_MQ;
 	}
 
+	if (queue_mode == NULL_Q_MQ && shared_tags)
+		null_init_tag_set(&tag_set);
+
 	if (queue_mode == NULL_Q_MQ && use_per_node_hctx) {
 		if (submit_queues < nr_online_nodes) {
 			pr_warn("null_blk: submit_queues param is set to %u.",
@@ -881,6 +907,9 @@ static void __exit null_exit(void)
 	}
 	mutex_unlock(&lock);
 
+	if (queue_mode == NULL_Q_MQ && shared_tags)
+		blk_mq_free_tag_set(&tag_set);
+
 	kmem_cache_destroy(ppa_cache);
 }
 

drivers/block/paride/pcd.c

@@ -305,6 +305,7 @@ static void pcd_init_units(void)
 			put_disk(disk);
 			continue;
 		}
+		blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
 		cd->disk = disk;
 		cd->pi = &cd->pia;
 		cd->present = 0;
@@ -783,7 +784,7 @@ static void pcd_request(void)
 			ps_set_intr(do_pcd_read, NULL, 0, nice);
 			return;
 		} else {
-			__blk_end_request_all(pcd_req, -EIO);
+			__blk_end_request_all(pcd_req, BLK_STS_IOERR);
 			pcd_req = NULL;
 		}
 	}
@@ -794,7 +795,7 @@ static void do_pcd_request(struct request_queue *q)
 	pcd_request();
 }
 
-static inline void next_request(int err)
+static inline void next_request(blk_status_t err)
 {
 	unsigned long saved_flags;
 
@@ -837,7 +838,7 @@ static void pcd_start(void)
 
 	if (pcd_command(pcd_current, rd_cmd, 2048, "read block")) {
 		pcd_bufblk = -1;
-		next_request(-EIO);
+		next_request(BLK_STS_IOERR);
 		return;
 	}
 
@@ -871,7 +872,7 @@ static void do_pcd_read_drq(void)
 			return;
 		}
 		pcd_bufblk = -1;
-		next_request(-EIO);
+		next_request(BLK_STS_IOERR);
 		return;
 	}
 

drivers/block/paride/pd.c

@@ -438,7 +438,7 @@ static void run_fsm(void)
 				phase = NULL;
 				spin_lock_irqsave(&pd_lock, saved_flags);
 				if (!__blk_end_request_cur(pd_req,
-						res == Ok ? 0 : -EIO)) {
+						res == Ok ? 0 : BLK_STS_IOERR)) {
 					if (!set_next_request())
 						stop = 1;
 				}
@@ -863,6 +863,7 @@ static void pd_probe_drive(struct pd_unit *disk)
 		return;
 	}
 	blk_queue_max_hw_sectors(p->queue, cluster);
+	blk_queue_bounce_limit(p->queue, BLK_BOUNCE_HIGH);
 
 	if (disk->drive == -1) {
 		for (disk->drive = 0; disk->drive <= 1; disk->drive++)

drivers/block/paride/pf.c

@@ -293,6 +293,7 @@ static void __init pf_init_units(void)
 			return;
 		}
 		blk_queue_max_segments(disk->queue, cluster);
+		blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
 		pf->disk = disk;
 		pf->pi = &pf->pia;
 		pf->media_status = PF_NM;
@@ -801,7 +802,7 @@ static int set_next_request(void)
 	return pf_req != NULL;
 }
 
-static void pf_end_request(int err)
+static void pf_end_request(blk_status_t err)
 {
 	if (pf_req && !__blk_end_request_cur(pf_req, err))
 		pf_req = NULL;
@@ -821,7 +822,7 @@ repeat:
 	pf_count = blk_rq_cur_sectors(pf_req);
 
 	if (pf_block + pf_count > get_capacity(pf_req->rq_disk)) {
-		pf_end_request(-EIO);
+		pf_end_request(BLK_STS_IOERR);
 		goto repeat;
 	}
 
@@ -836,7 +837,7 @@ repeat:
 		pi_do_claimed(pf_current->pi, do_pf_write);
 	else {
 		pf_busy = 0;
-		pf_end_request(-EIO);
+		pf_end_request(BLK_STS_IOERR);
 		goto repeat;
 	}
 }
@@ -868,7 +869,7 @@ static int pf_next_buf(void)
 	return 0;
 }
 
-static inline void next_request(int err)
+static inline void next_request(blk_status_t err)
 {
 	unsigned long saved_flags;
 
@@ -896,7 +897,7 @@ static void do_pf_read_start(void)
 			pi_do_claimed(pf_current->pi, do_pf_read_start);
 			return;
 		}
-		next_request(-EIO);
+		next_request(BLK_STS_IOERR);
 		return;
 	}
 	pf_mask = STAT_DRQ;
@@ -915,7 +916,7 @@ static void do_pf_read_drq(void)
 				pi_do_claimed(pf_current->pi, do_pf_read_start);
 				return;
 			}
-			next_request(-EIO);
+			next_request(BLK_STS_IOERR);
 			return;
 		}
 		pi_read_block(pf_current->pi, pf_buf, 512);
@@ -942,7 +943,7 @@ static void do_pf_write_start(void)
 			pi_do_claimed(pf_current->pi, do_pf_write_start);
 			return;
 		}
-		next_request(-EIO);
+		next_request(BLK_STS_IOERR);
 		return;
 	}
 
@@ -955,7 +956,7 @@ static void do_pf_write_start(void)
 				pi_do_claimed(pf_current->pi, do_pf_write_start);
 				return;
 			}
-			next_request(-EIO);
+			next_request(BLK_STS_IOERR);
 			return;
 		}
 		pi_write_block(pf_current->pi, pf_buf, 512);
@@ -975,7 +976,7 @@ static void do_pf_write_done(void)
 			pi_do_claimed(pf_current->pi, do_pf_write_start);
 			return;
 		}
-		next_request(-EIO);
+		next_request(BLK_STS_IOERR);
 		return;
 	}
 	pi_disconnect(pf_current->pi);

drivers/block/pktcdvd.c

@@ -98,6 +98,7 @@ static int write_congestion_on  = PKT_WRITE_CONGESTION_ON;
 static int write_congestion_off = PKT_WRITE_CONGESTION_OFF;
 static struct mutex ctl_mutex;	/* Serialize open/close/setup/teardown */
 static mempool_t *psd_pool;
+static struct bio_set *pkt_bio_set;
 
 static struct class	*class_pktcdvd = NULL;    /* /sys/class/pktcdvd */
 static struct dentry	*pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */
@@ -707,7 +708,6 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
 			     REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, __GFP_RECLAIM);
 	if (IS_ERR(rq))
 		return PTR_ERR(rq);
-	scsi_req_init(rq);
 
 	if (cgc->buflen) {
 		ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen,
@@ -952,9 +952,9 @@ static void pkt_end_io_read(struct bio *bio)
 
 	pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n",
 		bio, (unsigned long long)pkt->sector,
-		(unsigned long long)bio->bi_iter.bi_sector, bio->bi_error);
+		(unsigned long long)bio->bi_iter.bi_sector, bio->bi_status);
 
-	if (bio->bi_error)
+	if (bio->bi_status)
 		atomic_inc(&pkt->io_errors);
 	if (atomic_dec_and_test(&pkt->io_wait)) {
 		atomic_inc(&pkt->run_sm);
@@ -969,7 +969,7 @@ static void pkt_end_io_packet_write(struct bio *bio)
 	struct pktcdvd_device *pd = pkt->pd;
 	BUG_ON(!pd);
 
-	pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_error);
+	pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_status);
 
 	pd->stats.pkt_ended++;
 
@@ -1305,16 +1305,16 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
 	pkt_queue_bio(pd, pkt->w_bio);
 }
 
-static void pkt_finish_packet(struct packet_data *pkt, int error)
+static void pkt_finish_packet(struct packet_data *pkt, blk_status_t status)
 {
 	struct bio *bio;
 
-	if (error)
+	if (status)
 		pkt->cache_valid = 0;
 
 	/* Finish all bios corresponding to this packet */
 	while ((bio = bio_list_pop(&pkt->orig_bios))) {
-		bio->bi_error = error;
+		bio->bi_status = status;
 		bio_endio(bio);
 	}
 }
@@ -1349,7 +1349,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data
 			if (atomic_read(&pkt->io_wait) > 0)
 				return;
 
-			if (!pkt->w_bio->bi_error) {
+			if (!pkt->w_bio->bi_status) {
 				pkt_set_state(pkt, PACKET_FINISHED_STATE);
 			} else {
 				pkt_set_state(pkt, PACKET_RECOVERY_STATE);
@@ -1366,7 +1366,7 @@ static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data
 			break;
 
 		case PACKET_FINISHED_STATE:
-			pkt_finish_packet(pkt, pkt->w_bio->bi_error);
+			pkt_finish_packet(pkt, pkt->w_bio->bi_status);
 			return;
 
 		default:
@@ -2301,7 +2301,7 @@ static void pkt_end_io_read_cloned(struct bio *bio)
 	struct packet_stacked_data *psd = bio->bi_private;
 	struct pktcdvd_device *pd = psd->pd;
 
-	psd->bio->bi_error = bio->bi_error;
+	psd->bio->bi_status = bio->bi_status;
 	bio_put(bio);
 	bio_endio(psd->bio);
 	mempool_free(psd, psd_pool);
@@ -2310,7 +2310,7 @@ static void pkt_end_io_read_cloned(struct bio *bio)
 
 static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
 {
-	struct bio *cloned_bio = bio_clone(bio, GFP_NOIO);
+	struct bio *cloned_bio = bio_clone_fast(bio, GFP_NOIO, pkt_bio_set);
 	struct packet_stacked_data *psd = mempool_alloc(psd_pool, GFP_NOIO);
 
 	psd->pd = pd;
@@ -2412,9 +2412,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio)
 	char b[BDEVNAME_SIZE];
 	struct bio *split;
 
-	blk_queue_bounce(q, &bio);
-
-	blk_queue_split(q, &bio, q->bio_split);
+	blk_queue_split(q, &bio);
 
 	pd = q->queuedata;
 	if (!pd) {
@@ -2455,7 +2453,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio)
 
 			split = bio_split(bio, last_zone -
 					  bio->bi_iter.bi_sector,
-					  GFP_NOIO, fs_bio_set);
+					  GFP_NOIO, pkt_bio_set);
 			bio_chain(split, bio);
 		} else {
 			split = bio;
@@ -2583,6 +2581,11 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	bdev = bdget(dev);
 	if (!bdev)
 		return -ENOMEM;
+	if (!blk_queue_scsi_passthrough(bdev_get_queue(bdev))) {
+		WARN_ONCE(true, "Attempt to register a non-SCSI queue\n");
+		bdput(bdev);
+		return -EINVAL;
+	}
 	ret = blkdev_get(bdev, FMODE_READ | FMODE_NDELAY, NULL);
 	if (ret)
 		return ret;
@@ -2919,6 +2922,11 @@ static int __init pkt_init(void)
 					sizeof(struct packet_stacked_data));
 	if (!psd_pool)
 		return -ENOMEM;
+	pkt_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0);
+	if (!pkt_bio_set) {
+		mempool_destroy(psd_pool);
+		return -ENOMEM;
+	}
 
 	ret = register_blkdev(pktdev_major, DRIVER_NAME);
 	if (ret < 0) {
@@ -2951,6 +2959,7 @@ out:
 	unregister_blkdev(pktdev_major, DRIVER_NAME);
 out2:
 	mempool_destroy(psd_pool);
+	bioset_free(pkt_bio_set);
 	return ret;
 }
 
@@ -2964,6 +2973,7 @@ static void __exit pkt_exit(void)
 
 	unregister_blkdev(pktdev_major, DRIVER_NAME);
 	mempool_destroy(psd_pool);
+	bioset_free(pkt_bio_set);
 }
 
 MODULE_DESCRIPTION("Packet writing layer for CD/DVD drives");

drivers/block/ps3disk.c

@@ -158,7 +158,7 @@ static int ps3disk_submit_request_sg(struct ps3_storage_device *dev,
 	if (res) {
 		dev_err(&dev->sbd.core, "%s:%u: %s failed %d\n", __func__,
 			__LINE__, op, res);
-		__blk_end_request_all(req, -EIO);
+		__blk_end_request_all(req, BLK_STS_IOERR);
 		return 0;
 	}
 
@@ -180,7 +180,7 @@ static int ps3disk_submit_flush_request(struct ps3_storage_device *dev,
 	if (res) {
 		dev_err(&dev->sbd.core, "%s:%u: sync cache failed 0x%llx\n",
 			__func__, __LINE__, res);
-		__blk_end_request_all(req, -EIO);
+		__blk_end_request_all(req, BLK_STS_IOERR);
 		return 0;
 	}
 
@@ -208,7 +208,7 @@ static void ps3disk_do_request(struct ps3_storage_device *dev,
 			break;
 		default:
 			blk_dump_rq_flags(req, DEVICE_NAME " bad request");
-			__blk_end_request_all(req, -EIO);
+			__blk_end_request_all(req, BLK_STS_IOERR);
 		}
 	}
 }
@@ -231,7 +231,8 @@ static irqreturn_t ps3disk_interrupt(int irq, void *data)
 	struct ps3_storage_device *dev = data;
 	struct ps3disk_private *priv;
 	struct request *req;
-	int res, read, error;
+	int res, read;
+	blk_status_t error;
 	u64 tag, status;
 	const char *op;
 
@@ -269,7 +270,7 @@ static irqreturn_t ps3disk_interrupt(int irq, void *data)
 	if (status) {
 		dev_dbg(&dev->sbd.core, "%s:%u: %s failed 0x%llx\n", __func__,
 			__LINE__, op, status);
-		error = -EIO;
+		error = BLK_STS_IOERR;
 	} else {
 		dev_dbg(&dev->sbd.core, "%s:%u: %s completed\n", __func__,
 			__LINE__, op);

drivers/block/ps3vram.c

@@ -428,7 +428,7 @@ static void ps3vram_cache_cleanup(struct ps3_system_bus_device *dev)
 	kfree(priv->cache.tags);
 }
 
-static int ps3vram_read(struct ps3_system_bus_device *dev, loff_t from,
+static blk_status_t ps3vram_read(struct ps3_system_bus_device *dev, loff_t from,
 			size_t len, size_t *retlen, u_char *buf)
 {
 	struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
@@ -438,7 +438,7 @@ static int ps3vram_read(struct ps3_system_bus_device *dev, loff_t from,
 		(unsigned int)from, len);
 
 	if (from >= priv->size)
-		return -EIO;
+		return BLK_STS_IOERR;
 
 	if (len > priv->size - from)
 		len = priv->size - from;
@@ -472,14 +472,14 @@ static int ps3vram_read(struct ps3_system_bus_device *dev, loff_t from,
 	return 0;
 }
 
-static int ps3vram_write(struct ps3_system_bus_device *dev, loff_t to,
+static blk_status_t ps3vram_write(struct ps3_system_bus_device *dev, loff_t to,
 			 size_t len, size_t *retlen, const u_char *buf)
 {
 	struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
 	unsigned int cached, count;
 
 	if (to >= priv->size)
-		return -EIO;
+		return BLK_STS_IOERR;
 
 	if (len > priv->size - to)
 		len = priv->size - to;
@@ -554,7 +554,7 @@ static struct bio *ps3vram_do_bio(struct ps3_system_bus_device *dev,
 	int write = bio_data_dir(bio) == WRITE;
 	const char *op = write ? "write" : "read";
 	loff_t offset = bio->bi_iter.bi_sector << 9;
-	int error = 0;
+	blk_status_t error = 0;
 	struct bio_vec bvec;
 	struct bvec_iter iter;
 	struct bio *next;
@@ -578,7 +578,7 @@ static struct bio *ps3vram_do_bio(struct ps3_system_bus_device *dev,
 
 		if (retlen != len) {
 			dev_err(&dev->core, "Short %s\n", op);
-			error = -EIO;
+			error = BLK_STS_IOERR;
 			goto out;
 		}
 
@@ -593,7 +593,7 @@ out:
 	next = bio_list_peek(&priv->list);
 	spin_unlock_irq(&priv->lock);
 
-	bio->bi_error = error;
+	bio->bi_status = error;
 	bio_endio(bio);
 	return next;
 }
@@ -606,7 +606,7 @@ static blk_qc_t ps3vram_make_request(struct request_queue *q, struct bio *bio)
 
 	dev_dbg(&dev->core, "%s\n", __func__);
 
-	blk_queue_split(q, &bio, q->bio_split);
+	blk_queue_split(q, &bio);
 
 	spin_lock_irq(&priv->lock);
 	busy = !bio_list_empty(&priv->list);

drivers/block/rbd.c

@@ -442,6 +442,8 @@ static DEFINE_SPINLOCK(rbd_client_list_lock);
 static struct kmem_cache	*rbd_img_request_cache;
 static struct kmem_cache	*rbd_obj_request_cache;
 
+static struct bio_set		*rbd_bio_clone;
+
 static int rbd_major;
 static DEFINE_IDA(rbd_dev_id_ida);
 
@@ -1363,7 +1365,7 @@ static struct bio *bio_clone_range(struct bio *bio_src,
 {
 	struct bio *bio;
 
-	bio = bio_clone(bio_src, gfpmask);
+	bio = bio_clone_fast(bio_src, gfpmask, rbd_bio_clone);
 	if (!bio)
 		return NULL;	/* ENOMEM */
 
@@ -2293,11 +2295,13 @@ static bool rbd_img_obj_end_request(struct rbd_obj_request *obj_request)
 		rbd_assert(img_request->obj_request != NULL);
 		more = obj_request->which < img_request->obj_request_count - 1;
 	} else {
+		blk_status_t status = errno_to_blk_status(result);
+
 		rbd_assert(img_request->rq != NULL);
 
-		more = blk_update_request(img_request->rq, result, xferred);
+		more = blk_update_request(img_request->rq, status, xferred);
 		if (!more)
-			__blk_mq_end_request(img_request->rq, result);
+			__blk_mq_end_request(img_request->rq, status);
 	}
 
 	return more;
@@ -4150,17 +4154,17 @@ err_rq:
 			 obj_op_name(op_type), length, offset, result);
 	ceph_put_snap_context(snapc);
 err:
-	blk_mq_end_request(rq, result);
+	blk_mq_end_request(rq, errno_to_blk_status(result));
 }
 
-static int rbd_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t rbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 		const struct blk_mq_queue_data *bd)
 {
 	struct request *rq = bd->rq;
 	struct work_struct *work = blk_mq_rq_to_pdu(rq);
 
 	queue_work(rbd_wq, work);
-	return BLK_MQ_RQ_QUEUE_OK;
+	return BLK_STS_OK;
 }
 
 static void rbd_free_disk(struct rbd_device *rbd_dev)
@@ -6414,8 +6418,16 @@ static int rbd_slab_init(void)
 	if (!rbd_obj_request_cache)
 		goto out_err;
 
+	rbd_assert(!rbd_bio_clone);
+	rbd_bio_clone = bioset_create(BIO_POOL_SIZE, 0, 0);
+	if (!rbd_bio_clone)
+		goto out_err_clone;
+
 	return 0;
 
+out_err_clone:
+	kmem_cache_destroy(rbd_obj_request_cache);
+	rbd_obj_request_cache = NULL;
 out_err:
 	kmem_cache_destroy(rbd_img_request_cache);
 	rbd_img_request_cache = NULL;
@@ -6431,6 +6443,10 @@ static void rbd_slab_exit(void)
 	rbd_assert(rbd_img_request_cache);
 	kmem_cache_destroy(rbd_img_request_cache);
 	rbd_img_request_cache = NULL;
+
+	rbd_assert(rbd_bio_clone);
+	bioset_free(rbd_bio_clone);
+	rbd_bio_clone = NULL;
 }
 
 static int __init rbd_init(void)

drivers/block/rsxx/dev.c

@@ -149,9 +149,9 @@ static blk_qc_t rsxx_make_request(struct request_queue *q, struct bio *bio)
 {
 	struct rsxx_cardinfo *card = q->queuedata;
 	struct rsxx_bio_meta *bio_meta;
-	int st = -EINVAL;
+	blk_status_t st = BLK_STS_IOERR;
 
-	blk_queue_split(q, &bio, q->bio_split);
+	blk_queue_split(q, &bio);
 
 	might_sleep();
 
@@ -161,15 +161,11 @@ static blk_qc_t rsxx_make_request(struct request_queue *q, struct bio *bio)
 	if (bio_end_sector(bio) > get_capacity(card->gendisk))
 		goto req_err;
 
-	if (unlikely(card->halt)) {
-		st = -EFAULT;
+	if (unlikely(card->halt))
 		goto req_err;
-	}
 
-	if (unlikely(card->dma_fault)) {
-		st = (-EFAULT);
+	if (unlikely(card->dma_fault))
 		goto req_err;
-	}
 
 	if (bio->bi_iter.bi_size == 0) {
 		dev_err(CARD_TO_DEV(card), "size zero BIO!\n");
@@ -178,7 +174,7 @@ static blk_qc_t rsxx_make_request(struct request_queue *q, struct bio *bio)
 
 	bio_meta = kmem_cache_alloc(bio_meta_pool, GFP_KERNEL);
 	if (!bio_meta) {
-		st = -ENOMEM;
+		st = BLK_STS_RESOURCE;
 		goto req_err;
 	}
 
@@ -205,7 +201,7 @@ queue_err:
 	kmem_cache_free(bio_meta_pool, bio_meta);
 req_err:
 	if (st)
-		bio->bi_error = st;
+		bio->bi_status = st;
 	bio_endio(bio);
 	return BLK_QC_T_NONE;
 }
@@ -288,7 +284,6 @@ int rsxx_setup_dev(struct rsxx_cardinfo *card)
 	}
 
 	blk_queue_make_request(card->queue, rsxx_make_request);
-	blk_queue_bounce_limit(card->queue, BLK_BOUNCE_ANY);
 	blk_queue_max_hw_sectors(card->queue, blkdev_max_hw_sectors);
 	blk_queue_physical_block_size(card->queue, RSXX_HW_BLK_SIZE);
 

drivers/block/rsxx/dma.c

@@ -611,7 +611,7 @@ static void rsxx_schedule_done(struct work_struct *work)
 	mutex_unlock(&ctrl->work_lock);
 }
 
-static int rsxx_queue_discard(struct rsxx_cardinfo *card,
+static blk_status_t rsxx_queue_discard(struct rsxx_cardinfo *card,
 				  struct list_head *q,
 				  unsigned int laddr,
 				  rsxx_dma_cb cb,
@@ -621,7 +621,7 @@ static int rsxx_queue_discard(struct rsxx_cardinfo *card,
 
 	dma = kmem_cache_alloc(rsxx_dma_pool, GFP_KERNEL);
 	if (!dma)
-		return -ENOMEM;
+		return BLK_STS_RESOURCE;
 
 	dma->cmd          = HW_CMD_BLK_DISCARD;
 	dma->laddr        = laddr;
@@ -640,7 +640,7 @@ static int rsxx_queue_discard(struct rsxx_cardinfo *card,
 	return 0;
 }
 
-static int rsxx_queue_dma(struct rsxx_cardinfo *card,
+static blk_status_t rsxx_queue_dma(struct rsxx_cardinfo *card,
 			      struct list_head *q,
 			      int dir,
 			      unsigned int dma_off,
@@ -655,7 +655,7 @@ static int rsxx_queue_dma(struct rsxx_cardinfo *card,
 
 	dma = kmem_cache_alloc(rsxx_dma_pool, GFP_KERNEL);
 	if (!dma)
-		return -ENOMEM;
+		return BLK_STS_RESOURCE;
 
 	dma->cmd          = dir ? HW_CMD_BLK_WRITE : HW_CMD_BLK_READ;
 	dma->laddr        = laddr;
@@ -677,7 +677,7 @@ static int rsxx_queue_dma(struct rsxx_cardinfo *card,
 	return 0;
 }
 
-int rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
+blk_status_t rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
 			   struct bio *bio,
 			   atomic_t *n_dmas,
 			   rsxx_dma_cb cb,
@@ -694,7 +694,7 @@ int rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
 	unsigned int dma_len;
 	int dma_cnt[RSXX_MAX_TARGETS];
 	int tgt;
-	int st;
+	blk_status_t st;
 	int i;
 
 	addr8 = bio->bi_iter.bi_sector << 9; /* sectors are 512 bytes */
@@ -769,7 +769,6 @@ bvec_err:
 	for (i = 0; i < card->n_targets; i++)
 		rsxx_cleanup_dma_queue(&card->ctrl[i], &dma_list[i],
 					FREE_DMA);
-
 	return st;
 }
 

drivers/block/rsxx/rsxx_priv.h

@@ -391,7 +391,7 @@ int rsxx_dma_cancel(struct rsxx_dma_ctrl *ctrl);
 void rsxx_dma_cleanup(void);
 void rsxx_dma_queue_reset(struct rsxx_cardinfo *card);
 int rsxx_dma_configure(struct rsxx_cardinfo *card);
-int rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
+blk_status_t rsxx_dma_queue_bio(struct rsxx_cardinfo *card,
 			   struct bio *bio,
 			   atomic_t *n_dmas,
 			   rsxx_dma_cb cb,

drivers/block/skd_main.c

@@ -451,8 +451,8 @@ static void skd_send_special_fitmsg(struct skd_device *skdev,
 				    struct skd_special_context *skspcl);
 static void skd_request_fn(struct request_queue *rq);
 static void skd_end_request(struct skd_device *skdev,
-			    struct skd_request_context *skreq, int error);
-static int skd_preop_sg_list(struct skd_device *skdev,
+		struct skd_request_context *skreq, blk_status_t status);
+static bool skd_preop_sg_list(struct skd_device *skdev,
 			     struct skd_request_context *skreq);
 static void skd_postop_sg_list(struct skd_device *skdev,
 			       struct skd_request_context *skreq);
@@ -491,7 +491,7 @@ static void skd_fail_all_pending(struct skd_device *skdev)
 		if (req == NULL)
 			break;
 		blk_start_request(req);
-		__blk_end_request_all(req, -EIO);
+		__blk_end_request_all(req, BLK_STS_IOERR);
 	}
 }
 
@@ -545,7 +545,6 @@ static void skd_request_fn(struct request_queue *q)
 	struct request *req = NULL;
 	struct skd_scsi_request *scsi_req;
 	unsigned long io_flags;
-	int error;
 	u32 lba;
 	u32 count;
 	int data_dir;
@@ -716,9 +715,7 @@ static void skd_request_fn(struct request_queue *q)
 		if (!req->bio)
 			goto skip_sg;
 
-		error = skd_preop_sg_list(skdev, skreq);
-
-		if (error != 0) {
+		if (!skd_preop_sg_list(skdev, skreq)) {
 			/*
 			 * Complete the native request with error.
 			 * Note that the request context is still at the
@@ -730,7 +727,7 @@ static void skd_request_fn(struct request_queue *q)
 			 */
 			pr_debug("%s:%s:%d error Out\n",
 				 skdev->name, __func__, __LINE__);
-			skd_end_request(skdev, skreq, error);
+			skd_end_request(skdev, skreq, BLK_STS_RESOURCE);
 			continue;
 		}
 
@@ -805,7 +802,7 @@ skip_sg:
 }
 
 static void skd_end_request(struct skd_device *skdev,
-			    struct skd_request_context *skreq, int error)
+		struct skd_request_context *skreq, blk_status_t error)
 {
 	if (unlikely(error)) {
 		struct request *req = skreq->req;
@@ -822,7 +819,7 @@ static void skd_end_request(struct skd_device *skdev,
 	__blk_end_request_all(skreq->req, error);
 }
 
-static int skd_preop_sg_list(struct skd_device *skdev,
+static bool skd_preop_sg_list(struct skd_device *skdev,
 			     struct skd_request_context *skreq)
 {
 	struct request *req = skreq->req;
@@ -839,7 +836,7 @@ static int skd_preop_sg_list(struct skd_device *skdev,
 
 	n_sg = blk_rq_map_sg(skdev->queue, req, sg);
 	if (n_sg <= 0)
-		return -EINVAL;
+		return false;
 
 	/*
 	 * Map scatterlist to PCI bus addresses.
@@ -847,7 +844,7 @@ static int skd_preop_sg_list(struct skd_device *skdev,
 	 */
 	n_sg = pci_map_sg(skdev->pdev, sg, n_sg, pci_dir);
 	if (n_sg <= 0)
-		return -EINVAL;
+		return false;
 
 	SKD_ASSERT(n_sg <= skdev->sgs_per_request);
 
@@ -882,7 +879,7 @@ static int skd_preop_sg_list(struct skd_device *skdev,
 		}
 	}
 
-	return 0;
+	return true;
 }
 
 static void skd_postop_sg_list(struct skd_device *skdev,
@@ -2333,7 +2330,7 @@ static void skd_resolve_req_exception(struct skd_device *skdev,
 	switch (skd_check_status(skdev, cmp_status, &skreq->err_info)) {
 	case SKD_CHECK_STATUS_REPORT_GOOD:
 	case SKD_CHECK_STATUS_REPORT_SMART_ALERT:
-		skd_end_request(skdev, skreq, 0);
+		skd_end_request(skdev, skreq, BLK_STS_OK);
 		break;
 
 	case SKD_CHECK_STATUS_BUSY_IMMINENT:
@@ -2355,7 +2352,7 @@ static void skd_resolve_req_exception(struct skd_device *skdev,
 
 	case SKD_CHECK_STATUS_REPORT_ERROR:
 	default:
-		skd_end_request(skdev, skreq, -EIO);
+		skd_end_request(skdev, skreq, BLK_STS_IOERR);
 		break;
 	}
 }
@@ -2748,7 +2745,7 @@ static int skd_isr_completion_posted(struct skd_device *skdev,
 			 * native request.
 			 */
 			if (likely(cmp_status == SAM_STAT_GOOD))
-				skd_end_request(skdev, skreq, 0);
+				skd_end_request(skdev, skreq, BLK_STS_OK);
 			else
 				skd_resolve_req_exception(skdev, skreq);
 		}
@@ -3190,7 +3187,7 @@ static void skd_recover_requests(struct skd_device *skdev, int requeue)
 			    SKD_MAX_RETRIES)
 				blk_requeue_request(skdev->queue, skreq->req);
 			else
-				skd_end_request(skdev, skreq, -EIO);
+				skd_end_request(skdev, skreq, BLK_STS_IOERR);
 
 			skreq->req = NULL;
 
@@ -4276,6 +4273,7 @@ static int skd_cons_disk(struct skd_device *skdev)
 		rc = -ENOMEM;
 		goto err_out;
 	}
+	blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH);
 
 	skdev->queue = q;
 	disk->queue = q;

drivers/block/sunvdc.c

@@ -316,7 +316,7 @@ static void vdc_end_one(struct vdc_port *port, struct vio_dring_state *dr,
 
 	rqe->req = NULL;
 
-	__blk_end_request(req, (desc->status ? -EIO : 0), desc->size);
+	__blk_end_request(req, (desc->status ? BLK_STS_IOERR : 0), desc->size);
 
 	vdc_blk_queue_start(port);
 }
@@ -1023,7 +1023,7 @@ static void vdc_queue_drain(struct vdc_port *port)
 	struct request *req;
 
 	while ((req = blk_fetch_request(port->disk->queue)) != NULL)
-		__blk_end_request_all(req, -EIO);
+		__blk_end_request_all(req, BLK_STS_IOERR);
 }
 
 static void vdc_ldc_reset_timer(unsigned long _arg)

drivers/block/swim.c

@@ -493,7 +493,7 @@ static inline int swim_read_sector(struct floppy_state *fs,
 	return ret;
 }
 
-static int floppy_read_sectors(struct floppy_state *fs,
+static blk_status_t floppy_read_sectors(struct floppy_state *fs,
 			       int req_sector, int sectors_nb,
 			       unsigned char *buffer)
 {
@@ -516,7 +516,7 @@ static int floppy_read_sectors(struct floppy_state *fs,
 			ret = swim_read_sector(fs, side, track, sector,
 						buffer);
 			if (try-- == 0)
-				return -EIO;
+				return BLK_STS_IOERR;
 		} while (ret != 512);
 
 		buffer += ret;
@@ -553,7 +553,7 @@ static void do_fd_request(struct request_queue *q)
 
 	req = swim_next_request(swd);
 	while (req) {
-		int err = -EIO;
+		blk_status_t err = BLK_STS_IOERR;
 
 		fs = req->rq_disk->private_data;
 		if (blk_rq_pos(req) >= fs->total_secs)
@@ -864,6 +864,8 @@ static int swim_floppy_init(struct swim_priv *swd)
 			put_disk(swd->unit[drive].disk);
 			goto exit_put_disks;
 		}
+		blk_queue_bounce_limit(swd->unit[drive].disk->queue,
+				BLK_BOUNCE_HIGH);
 		swd->unit[drive].disk->queue->queuedata = swd;
 		swd->unit[drive].swd = swd;
 	}

drivers/block/swim3.c

@@ -257,7 +257,7 @@ static unsigned int floppy_check_events(struct gendisk *disk,
 					unsigned int clearing);
 static int floppy_revalidate(struct gendisk *disk);
 
-static bool swim3_end_request(struct floppy_state *fs, int err, unsigned int nr_bytes)
+static bool swim3_end_request(struct floppy_state *fs, blk_status_t err, unsigned int nr_bytes)
 {
 	struct request *req = fs->cur_req;
 	int rc;
@@ -334,7 +334,7 @@ static void start_request(struct floppy_state *fs)
 		if (fs->mdev->media_bay &&
 		    check_media_bay(fs->mdev->media_bay) != MB_FD) {
 			swim3_dbg("%s", "  media bay absent, dropping req\n");
-			swim3_end_request(fs, -ENODEV, 0);
+			swim3_end_request(fs, BLK_STS_IOERR, 0);
 			continue;
 		}
 
@@ -350,12 +350,12 @@ static void start_request(struct floppy_state *fs)
 		if (blk_rq_pos(req) >= fs->total_secs) {
 			swim3_dbg("  pos out of bounds (%ld, max is %ld)\n",
 				  (long)blk_rq_pos(req), (long)fs->total_secs);
-			swim3_end_request(fs, -EIO, 0);
+			swim3_end_request(fs, BLK_STS_IOERR, 0);
 			continue;
 		}
 		if (fs->ejected) {
 			swim3_dbg("%s", "  disk ejected\n");
-			swim3_end_request(fs, -EIO, 0);
+			swim3_end_request(fs, BLK_STS_IOERR, 0);
 			continue;
 		}
 
@@ -364,7 +364,7 @@ static void start_request(struct floppy_state *fs)
 				fs->write_prot = swim3_readbit(fs, WRITE_PROT);
 			if (fs->write_prot) {
 				swim3_dbg("%s", "  try to write, disk write protected\n");
-				swim3_end_request(fs, -EIO, 0);
+				swim3_end_request(fs, BLK_STS_IOERR, 0);
 				continue;
 			}
 		}
@@ -548,7 +548,7 @@ static void act(struct floppy_state *fs)
 				if (fs->retries > 5) {
 					swim3_err("Wrong cylinder in transfer, want: %d got %d\n",
 						  fs->req_cyl, fs->cur_cyl);
-					swim3_end_request(fs, -EIO, 0);
+					swim3_end_request(fs, BLK_STS_IOERR, 0);
 					fs->state = idle;
 					return;
 				}
@@ -584,7 +584,7 @@ static void scan_timeout(unsigned long data)
 	out_8(&sw->intr_enable, 0);
 	fs->cur_cyl = -1;
 	if (fs->retries > 5) {
-		swim3_end_request(fs, -EIO, 0);
+		swim3_end_request(fs, BLK_STS_IOERR, 0);
 		fs->state = idle;
 		start_request(fs);
 	} else {
@@ -608,7 +608,7 @@ static void seek_timeout(unsigned long data)
 	out_8(&sw->select, RELAX);
 	out_8(&sw->intr_enable, 0);
 	swim3_err("%s", "Seek timeout\n");
-	swim3_end_request(fs, -EIO, 0);
+	swim3_end_request(fs, BLK_STS_IOERR, 0);
 	fs->state = idle;
 	start_request(fs);
 	spin_unlock_irqrestore(&swim3_lock, flags);
@@ -637,7 +637,7 @@ static void settle_timeout(unsigned long data)
 		goto unlock;
 	}
 	swim3_err("%s", "Seek settle timeout\n");
-	swim3_end_request(fs, -EIO, 0);
+	swim3_end_request(fs, BLK_STS_IOERR, 0);
 	fs->state = idle;
 	start_request(fs);
  unlock:
@@ -666,7 +666,7 @@ static void xfer_timeout(unsigned long data)
 	swim3_err("Timeout %sing sector %ld\n",
 	       (rq_data_dir(fs->cur_req)==WRITE? "writ": "read"),
 	       (long)blk_rq_pos(fs->cur_req));
-	swim3_end_request(fs, -EIO, 0);
+	swim3_end_request(fs, BLK_STS_IOERR, 0);
 	fs->state = idle;
 	start_request(fs);
 	spin_unlock_irqrestore(&swim3_lock, flags);
@@ -703,7 +703,7 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id)
 				swim3_err("%s", "Seen sector but cyl=ff?\n");
 				fs->cur_cyl = -1;
 				if (fs->retries > 5) {
-					swim3_end_request(fs, -EIO, 0);
+					swim3_end_request(fs, BLK_STS_IOERR, 0);
 					fs->state = idle;
 					start_request(fs);
 				} else {
@@ -786,7 +786,7 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id)
 				swim3_err("Error %sing block %ld (err=%x)\n",
 				       rq_data_dir(req) == WRITE? "writ": "read",
 				       (long)blk_rq_pos(req), err);
-				swim3_end_request(fs, -EIO, 0);
+				swim3_end_request(fs, BLK_STS_IOERR, 0);
 				fs->state = idle;
 			}
 		} else {
@@ -795,7 +795,7 @@ static irqreturn_t swim3_interrupt(int irq, void *dev_id)
 				swim3_err("fd dma error: stat=%x resid=%d\n", stat, resid);
 				swim3_err("  state=%d, dir=%x, intr=%x, err=%x\n",
 					  fs->state, rq_data_dir(req), intr, err);
-				swim3_end_request(fs, -EIO, 0);
+				swim3_end_request(fs, BLK_STS_IOERR, 0);
 				fs->state = idle;
 				start_request(fs);
 				break;
@@ -1223,6 +1223,7 @@ static int swim3_attach(struct macio_dev *mdev,
 		put_disk(disk);
 		return -ENOMEM;
 	}
+	blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
 	disk->queue->queuedata = &floppy_states[index];
 
 	if (index == 0) {
@@ -1245,7 +1246,7 @@ static int swim3_attach(struct macio_dev *mdev,
 	return 0;
 }
 
-static struct of_device_id swim3_match[] =
+static const struct of_device_id swim3_match[] =
 {
 	{
 	.name		= "swim3",

drivers/block/sx8.c

@@ -745,7 +745,7 @@ static unsigned int carm_fill_get_fw_ver(struct carm_host *host,
 
 static inline void carm_end_request_queued(struct carm_host *host,
 					   struct carm_request *crq,
-					   int error)
+					   blk_status_t error)
 {
 	struct request *req = crq->rq;
 	int rc;
@@ -791,7 +791,7 @@ static inline void carm_round_robin(struct carm_host *host)
 }
 
 static inline void carm_end_rq(struct carm_host *host, struct carm_request *crq,
-			       int error)
+			       blk_status_t error)
 {
 	carm_end_request_queued(host, crq, error);
 	if (max_queue == 1)
@@ -869,14 +869,14 @@ queue_one_request:
 	sg = &crq->sg[0];
 	n_elem = blk_rq_map_sg(q, rq, sg);
 	if (n_elem <= 0) {
-		carm_end_rq(host, crq, -EIO);
+		carm_end_rq(host, crq, BLK_STS_IOERR);
 		return;		/* request with no s/g entries? */
 	}
 
 	/* map scatterlist to PCI bus addresses */
 	n_elem = pci_map_sg(host->pdev, sg, n_elem, pci_dir);
 	if (n_elem <= 0) {
-		carm_end_rq(host, crq, -EIO);
+		carm_end_rq(host, crq, BLK_STS_IOERR);
 		return;		/* request with no s/g entries? */
 	}
 	crq->n_elem = n_elem;
@@ -937,7 +937,7 @@ queue_one_request:
 
 static void carm_handle_array_info(struct carm_host *host,
 				   struct carm_request *crq, u8 *mem,
-				   int error)
+				   blk_status_t error)
 {
 	struct carm_port *port;
 	u8 *msg_data = mem + sizeof(struct carm_array_info);
@@ -997,7 +997,7 @@ out:
 
 static void carm_handle_scan_chan(struct carm_host *host,
 				  struct carm_request *crq, u8 *mem,
-				  int error)
+				  blk_status_t error)
 {
 	u8 *msg_data = mem + IOC_SCAN_CHAN_OFFSET;
 	unsigned int i, dev_count = 0;
@@ -1029,7 +1029,7 @@ out:
 }
 
 static void carm_handle_generic(struct carm_host *host,
-				struct carm_request *crq, int error,
+				struct carm_request *crq, blk_status_t error,
 				int cur_state, int next_state)
 {
 	DPRINTK("ENTER\n");
@@ -1045,7 +1045,7 @@ static void carm_handle_generic(struct carm_host *host,
 }
 
 static inline void carm_handle_rw(struct carm_host *host,
-				  struct carm_request *crq, int error)
+				  struct carm_request *crq, blk_status_t error)
 {
 	int pci_dir;
 
@@ -1067,7 +1067,7 @@ static inline void carm_handle_resp(struct carm_host *host,
 	u32 handle = le32_to_cpu(ret_handle_le);
 	unsigned int msg_idx;
 	struct carm_request *crq;
-	int error = (status == RMSG_OK) ? 0 : -EIO;
+	blk_status_t error = (status == RMSG_OK) ? 0 : BLK_STS_IOERR;
 	u8 *mem;
 
 	VPRINTK("ENTER, handle == 0x%x\n", handle);
@@ -1155,7 +1155,7 @@ static inline void carm_handle_resp(struct carm_host *host,
 err_out:
 	printk(KERN_WARNING DRV_NAME "(%s): BUG: unhandled message type %d/%d\n",
 	       pci_name(host->pdev), crq->msg_type, crq->msg_subtype);
-	carm_end_rq(host, crq, -EIO);
+	carm_end_rq(host, crq, BLK_STS_IOERR);
 }
 
 static inline void carm_handle_responses(struct carm_host *host)

drivers/block/umem.c

@@ -454,7 +454,7 @@ static void process_page(unsigned long data)
 				PCI_DMA_TODEVICE : PCI_DMA_FROMDEVICE);
 		if (control & DMASCR_HARD_ERROR) {
 			/* error */
-			bio->bi_error = -EIO;
+			bio->bi_status = BLK_STS_IOERR;
 			dev_printk(KERN_WARNING, &card->dev->dev,
 				"I/O error on sector %d/%d\n",
 				le32_to_cpu(desc->local_addr)>>9,
@@ -529,7 +529,7 @@ static blk_qc_t mm_make_request(struct request_queue *q, struct bio *bio)
 		 (unsigned long long)bio->bi_iter.bi_sector,
 		 bio->bi_iter.bi_size);
 
-	blk_queue_split(q, &bio, q->bio_split);
+	blk_queue_split(q, &bio);
 
 	spin_lock_irq(&card->lock);
 	*card->biotail = bio;

drivers/block/virtio_blk.c

@@ -64,15 +64,15 @@ struct virtblk_req {
 	struct scatterlist sg[];
 };
 
-static inline int virtblk_result(struct virtblk_req *vbr)
+static inline blk_status_t virtblk_result(struct virtblk_req *vbr)
 {
 	switch (vbr->status) {
 	case VIRTIO_BLK_S_OK:
-		return 0;
+		return BLK_STS_OK;
 	case VIRTIO_BLK_S_UNSUPP:
-		return -ENOTTY;
+		return BLK_STS_NOTSUPP;
 	default:
-		return -EIO;
+		return BLK_STS_IOERR;
 	}
 }
 
@@ -214,7 +214,7 @@ static void virtblk_done(struct virtqueue *vq)
 	spin_unlock_irqrestore(&vblk->vqs[qid].lock, flags);
 }
 
-static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 			   const struct blk_mq_queue_data *bd)
 {
 	struct virtio_blk *vblk = hctx->queue->queuedata;
@@ -246,7 +246,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 		break;
 	default:
 		WARN_ON_ONCE(1);
-		return BLK_MQ_RQ_QUEUE_ERROR;
+		return BLK_STS_IOERR;
 	}
 
 	vbr->out_hdr.type = cpu_to_virtio32(vblk->vdev, type);
@@ -276,8 +276,8 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 		/* Out of mem doesn't actually happen, since we fall back
 		 * to direct descriptors */
 		if (err == -ENOMEM || err == -ENOSPC)
-			return BLK_MQ_RQ_QUEUE_BUSY;
-		return BLK_MQ_RQ_QUEUE_ERROR;
+			return BLK_STS_RESOURCE;
+		return BLK_STS_IOERR;
 	}
 
 	if (bd->last && virtqueue_kick_prepare(vblk->vqs[qid].vq))
@@ -286,7 +286,7 @@ static int virtio_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	if (notify)
 		virtqueue_notify(vblk->vqs[qid].vq);
-	return BLK_MQ_RQ_QUEUE_OK;
+	return BLK_STS_OK;
 }
 
 /* return id (s/n) string for *disk to *id_str
@@ -307,7 +307,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
 		goto out;
 
 	blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
-	err = virtblk_result(blk_mq_rq_to_pdu(req));
+	err = blk_status_to_errno(virtblk_result(blk_mq_rq_to_pdu(req)));
 out:
 	blk_put_request(req);
 	return err;
@@ -720,9 +720,6 @@ static int virtblk_probe(struct virtio_device *vdev)
 	/* We can handle whatever the host told us to handle. */
 	blk_queue_max_segments(q, vblk->sg_elems-2);
 
-	/* No need to bounce any requests */
-	blk_queue_bounce_limit(q, BLK_BOUNCE_ANY);
-
 	/* No real sector limit. */
 	blk_queue_max_hw_sectors(q, -1U);
 

drivers/block/xen-blkback/blkback.c

@@ -1066,20 +1066,17 @@ static void xen_blk_drain_io(struct xen_blkif_ring *ring)
 	atomic_set(&blkif->drain, 0);
 }
 
-/*
- * Completion callback on the bio's. Called as bh->b_end_io()
- */
-
-static void __end_block_io_op(struct pending_req *pending_req, int error)
+static void __end_block_io_op(struct pending_req *pending_req,
+		blk_status_t error)
 {
 	/* An error fails the entire request. */
-	if ((pending_req->operation == BLKIF_OP_FLUSH_DISKCACHE) &&
-	    (error == -EOPNOTSUPP)) {
+	if (pending_req->operation == BLKIF_OP_FLUSH_DISKCACHE &&
+	    error == BLK_STS_NOTSUPP) {
 		pr_debug("flush diskcache op failed, not supported\n");
 		xen_blkbk_flush_diskcache(XBT_NIL, pending_req->ring->blkif->be, 0);
 		pending_req->status = BLKIF_RSP_EOPNOTSUPP;
-	} else if ((pending_req->operation == BLKIF_OP_WRITE_BARRIER) &&
-		    (error == -EOPNOTSUPP)) {
+	} else if (pending_req->operation == BLKIF_OP_WRITE_BARRIER &&
+		   error == BLK_STS_NOTSUPP) {
 		pr_debug("write barrier op failed, not supported\n");
 		xen_blkbk_barrier(XBT_NIL, pending_req->ring->blkif->be, 0);
 		pending_req->status = BLKIF_RSP_EOPNOTSUPP;
@@ -1103,7 +1100,7 @@ static void __end_block_io_op(struct pending_req *pending_req, int error)
  */
 static void end_block_io_op(struct bio *bio)
 {
-	__end_block_io_op(bio->bi_private, bio->bi_error);
+	__end_block_io_op(bio->bi_private, bio->bi_status);
 	bio_put(bio);
 }
 
@@ -1420,7 +1417,7 @@ static int dispatch_rw_block_io(struct xen_blkif_ring *ring,
 	for (i = 0; i < nbio; i++)
 		bio_put(biolist[i]);
 	atomic_set(&pending_req->pendcnt, 1);
-	__end_block_io_op(pending_req, -EINVAL);
+	__end_block_io_op(pending_req, BLK_STS_RESOURCE);
 	msleep(1); /* back off a bit */
 	return -EIO;
 }

drivers/block/xen-blkfront.c

@@ -110,11 +110,6 @@ struct blk_shadow {
 	unsigned long associated_id;
 };
 
-struct split_bio {
-	struct bio *bio;
-	atomic_t pending;
-};
-
 struct blkif_req {
 	int	error;
 };
@@ -881,7 +876,7 @@ static inline bool blkif_request_flush_invalid(struct request *req,
 		 !info->feature_fua));
 }
 
-static int blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
+static blk_status_t blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
 			  const struct blk_mq_queue_data *qd)
 {
 	unsigned long flags;
@@ -904,16 +899,16 @@ static int blkif_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	flush_requests(rinfo);
 	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
-	return BLK_MQ_RQ_QUEUE_OK;
+	return BLK_STS_OK;
 
 out_err:
 	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
-	return BLK_MQ_RQ_QUEUE_ERROR;
+	return BLK_STS_IOERR;
 
 out_busy:
 	spin_unlock_irqrestore(&rinfo->ring_lock, flags);
 	blk_mq_stop_hw_queue(hctx);
-	return BLK_MQ_RQ_QUEUE_BUSY;
+	return BLK_STS_RESOURCE;
 }
 
 static void blkif_complete_rq(struct request *rq)
@@ -958,9 +953,6 @@ static void blkif_set_queue_limits(struct blkfront_info *info)
 
 	/* Make sure buffer addresses are sector-aligned. */
 	blk_queue_dma_alignment(rq, 511);
-
-	/* Make sure we don't use bounce buffers. */
-	blk_queue_bounce_limit(rq, BLK_BOUNCE_ANY);
 }
 
 static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
@@ -1601,14 +1593,18 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 			continue;
 		}
 
-		blkif_req(req)->error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
+		if (bret->status == BLKIF_RSP_OKAY)
+			blkif_req(req)->error = BLK_STS_OK;
+		else
+			blkif_req(req)->error = BLK_STS_IOERR;
+
 		switch (bret->operation) {
 		case BLKIF_OP_DISCARD:
 			if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
 				struct request_queue *rq = info->rq;
 				printk(KERN_WARNING "blkfront: %s: %s op failed\n",
 					   info->gd->disk_name, op_name(bret->operation));
-				blkif_req(req)->error = -EOPNOTSUPP;
+				blkif_req(req)->error = BLK_STS_NOTSUPP;
 				info->feature_discard = 0;
 				info->feature_secdiscard = 0;
 				queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
@@ -1626,11 +1622,11 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
 				     rinfo->shadow[id].req.u.rw.nr_segments == 0)) {
 				printk(KERN_WARNING "blkfront: %s: empty %s op failed\n",
 				       info->gd->disk_name, op_name(bret->operation));
-				blkif_req(req)->error = -EOPNOTSUPP;
+				blkif_req(req)->error = BLK_STS_NOTSUPP;
 			}
 			if (unlikely(blkif_req(req)->error)) {
-				if (blkif_req(req)->error == -EOPNOTSUPP)
-					blkif_req(req)->error = 0;
+				if (blkif_req(req)->error == BLK_STS_NOTSUPP)
+					blkif_req(req)->error = BLK_STS_OK;
 				info->feature_fua = 0;
 				info->feature_flush = 0;
 				xlvbd_flush(info);
@@ -1996,28 +1992,13 @@ static int blkfront_probe(struct xenbus_device *dev,
 	return 0;
 }
 
-static void split_bio_end(struct bio *bio)
-{
-	struct split_bio *split_bio = bio->bi_private;
-
-	if (atomic_dec_and_test(&split_bio->pending)) {
-		split_bio->bio->bi_phys_segments = 0;
-		split_bio->bio->bi_error = bio->bi_error;
-		bio_endio(split_bio->bio);
-		kfree(split_bio);
-	}
-	bio_put(bio);
-}
-
 static int blkif_recover(struct blkfront_info *info)
 {
-	unsigned int i, r_index;
+	unsigned int r_index;
 	struct request *req, *n;
 	int rc;
-	struct bio *bio, *cloned_bio;
-	unsigned int segs, offset;
-	int pending, size;
-	struct split_bio *split_bio;
+	struct bio *bio;
+	unsigned int segs;
 
 	blkfront_gather_backend_features(info);
 	/* Reset limits changed by blk_mq_update_nr_hw_queues(). */
@@ -2056,34 +2037,6 @@ static int blkif_recover(struct blkfront_info *info)
 
 	while ((bio = bio_list_pop(&info->bio_list)) != NULL) {
 		/* Traverse the list of pending bios and re-queue them */
-		if (bio_segments(bio) > segs) {
-			/*
-			 * This bio has more segments than what we can
-			 * handle, we have to split it.
-			 */
-			pending = (bio_segments(bio) + segs - 1) / segs;
-			split_bio = kzalloc(sizeof(*split_bio), GFP_NOIO);
-			BUG_ON(split_bio == NULL);
-			atomic_set(&split_bio->pending, pending);
-			split_bio->bio = bio;
-			for (i = 0; i < pending; i++) {
-				offset = (i * segs * XEN_PAGE_SIZE) >> 9;
-				size = min((unsigned int)(segs * XEN_PAGE_SIZE) >> 9,
-					   (unsigned int)bio_sectors(bio) - offset);
-				cloned_bio = bio_clone(bio, GFP_NOIO);
-				BUG_ON(cloned_bio == NULL);
-				bio_trim(cloned_bio, offset, size);
-				cloned_bio->bi_private = split_bio;
-				cloned_bio->bi_end_io = split_bio_end;
-				submit_bio(cloned_bio);
-			}
-			/*
-			 * Now we have to wait for all those smaller bios to
-			 * end, so we can also end the "parent" bio.
-			 */
-			continue;
-		}
-		/* We don't need to split this bio */
 		submit_bio(bio);
 	}
 
@@ -2137,7 +2090,7 @@ static int blkfront_resume(struct xenbus_device *dev)
 			merge_bio.tail = shadow[j].request->biotail;
 			bio_list_merge(&info->bio_list, &merge_bio);
 			shadow[j].request->bio = NULL;
-			blk_mq_end_request(shadow[j].request, 0);
+			blk_mq_end_request(shadow[j].request, BLK_STS_OK);
 		}
 	}
 

drivers/block/xsysace.c

@@ -471,7 +471,7 @@ static struct request *ace_get_next_request(struct request_queue *q)
 		if (!blk_rq_is_passthrough(req))
 			break;
 		blk_start_request(req);
-		__blk_end_request_all(req, -EIO);
+		__blk_end_request_all(req, BLK_STS_IOERR);
 	}
 	return req;
 }
@@ -499,11 +499,11 @@ static void ace_fsm_dostate(struct ace_device *ace)
 
 		/* Drop all in-flight and pending requests */
 		if (ace->req) {
-			__blk_end_request_all(ace->req, -EIO);
+			__blk_end_request_all(ace->req, BLK_STS_IOERR);
 			ace->req = NULL;
 		}
 		while ((req = blk_fetch_request(ace->queue)) != NULL)
-			__blk_end_request_all(req, -EIO);
+			__blk_end_request_all(req, BLK_STS_IOERR);
 
 		/* Drop back to IDLE state and notify waiters */
 		ace->fsm_state = ACE_FSM_STATE_IDLE;
@@ -728,7 +728,7 @@ static void ace_fsm_dostate(struct ace_device *ace)
 		}
 
 		/* bio finished; is there another one? */
-		if (__blk_end_request_cur(ace->req, 0)) {
+		if (__blk_end_request_cur(ace->req, BLK_STS_OK)) {
 			/* dev_dbg(ace->dev, "next block; h=%u c=%u\n",
 			 *      blk_rq_sectors(ace->req),
 			 *      blk_rq_cur_sectors(ace->req));
@@ -993,6 +993,7 @@ static int ace_setup(struct ace_device *ace)
 	if (ace->queue == NULL)
 		goto err_blk_initq;
 	blk_queue_logical_block_size(ace->queue, 512);
+	blk_queue_bounce_limit(ace->queue, BLK_BOUNCE_HIGH);
 
 	/*
 	 * Allocate and initialize GD structure

drivers/block/z2ram.c

@@ -74,14 +74,14 @@ static void do_z2_request(struct request_queue *q)
 	while (req) {
 		unsigned long start = blk_rq_pos(req) << 9;
 		unsigned long len  = blk_rq_cur_bytes(req);
-		int err = 0;
+		blk_status_t err = BLK_STS_OK;
 
 		if (start + len > z2ram_size) {
 			pr_err(DEVICE_NAME ": bad access: block=%llu, "
 			       "count=%u\n",
 			       (unsigned long long)blk_rq_pos(req),
 			       blk_rq_cur_sectors(req));
-			err = -EIO;
+			err = BLK_STS_IOERR;
 			goto done;
 		}
 		while (len) {

drivers/cdrom/cdrom.c

@@ -2178,6 +2178,12 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 	if (!q)
 		return -ENXIO;
 
+	if (!blk_queue_scsi_passthrough(q)) {
+		WARN_ONCE(true,
+			  "Attempt read CDDA info through a non-SCSI queue\n");
+		return -EINVAL;
+	}
+
 	cdi->last_sense = 0;
 
 	while (nframes) {
@@ -2195,7 +2201,6 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 			break;
 		}
 		req = scsi_req(rq);
-		scsi_req_init(rq);
 
 		ret = blk_rq_map_user(q, rq, NULL, ubuf, len, GFP_KERNEL);
 		if (ret) {

drivers/cdrom/gdrom.c

@@ -583,7 +583,8 @@ static int gdrom_set_interrupt_handlers(void)
  */
 static void gdrom_readdisk_dma(struct work_struct *work)
 {
-	int err, block, block_cnt;
+	int block, block_cnt;
+	blk_status_t err;
 	struct packet_command *read_command;
 	struct list_head *elem, *next;
 	struct request *req;
@@ -641,7 +642,7 @@ static void gdrom_readdisk_dma(struct work_struct *work)
 		__raw_writeb(1, GDROM_DMA_STATUS_REG);
 		wait_event_interruptible_timeout(request_queue,
 			gd.transfer == 0, GDROM_DEFAULT_TIMEOUT);
-		err = gd.transfer ? -EIO : 0;
+		err = gd.transfer ? BLK_STS_IOERR : BLK_STS_OK;
 		gd.transfer = 0;
 		gd.pending = 0;
 		/* now seek to take the request spinlock
@@ -670,11 +671,11 @@ static void gdrom_request(struct request_queue *rq)
 			break;
 		case REQ_OP_WRITE:
 			pr_notice("Read only device - write request ignored\n");
-			__blk_end_request_all(req, -EIO);
+			__blk_end_request_all(req, BLK_STS_IOERR);
 			break;
 		default:
 			printk(KERN_DEBUG "gdrom: Non-fs request ignored\n");
-			__blk_end_request_all(req, -EIO);
+			__blk_end_request_all(req, BLK_STS_IOERR);
 			break;
 		}
 	}
@@ -812,6 +813,7 @@ static int probe_gdrom(struct platform_device *devptr)
 		err = -ENOMEM;
 		goto probe_fail_requestq;
 	}
+	blk_queue_bounce_limit(gd.gdrom_rq, BLK_BOUNCE_HIGH);
 
 	err = probe_gdrom_setupqueue();
 	if (err)

drivers/ide/ide-atapi.c

@@ -93,7 +93,6 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
 	int error;
 
 	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	scsi_req_init(rq);
 	ide_req(rq)->type = ATA_PRIV_MISC;
 	rq->special = (char *)pc;
 
@@ -200,7 +199,7 @@ void ide_prep_sense(ide_drive_t *drive, struct request *rq)
 	memset(sense, 0, sizeof(*sense));
 
 	blk_rq_init(rq->q, sense_rq);
-	scsi_req_init(sense_rq);
+	scsi_req_init(req);
 
 	err = blk_rq_map_kern(drive->queue, sense_rq, sense, sense_len,
 			      GFP_NOIO);
@@ -273,7 +272,7 @@ void ide_retry_pc(ide_drive_t *drive)
 	ide_requeue_and_plug(drive, failed_rq);
 	if (ide_queue_sense_rq(drive, pc)) {
 		blk_start_request(failed_rq);
-		ide_complete_rq(drive, -EIO, blk_rq_bytes(failed_rq));
+		ide_complete_rq(drive, BLK_STS_IOERR, blk_rq_bytes(failed_rq));
 	}
 }
 EXPORT_SYMBOL_GPL(ide_retry_pc);
@@ -437,7 +436,8 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 
 	/* No more interrupts */
 	if ((stat & ATA_DRQ) == 0) {
-		int uptodate, error;
+		int uptodate;
+		blk_status_t error;
 
 		debug_log("Packet command completed, %d bytes transferred\n",
 			  blk_rq_bytes(rq));
@@ -490,7 +490,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 
 		if (ata_misc_request(rq)) {
 			scsi_req(rq)->result = 0;
-			error = 0;
+			error = BLK_STS_OK;
 		} else {
 
 			if (blk_rq_is_passthrough(rq) && uptodate <= 0) {
@@ -498,7 +498,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
 					scsi_req(rq)->result = -EIO;
 			}
 
-			error = uptodate ? 0 : -EIO;
+			error = uptodate ? BLK_STS_OK : BLK_STS_IOERR;
 		}
 
 		ide_complete_rq(drive, error, blk_rq_bytes(rq));

drivers/ide/ide-cd.c

@@ -228,7 +228,7 @@ static void ide_cd_complete_failed_rq(ide_drive_t *drive, struct request *rq)
 		scsi_req(failed)->sense_len = scsi_req(rq)->sense_len;
 		cdrom_analyze_sense_data(drive, failed);
 
-		if (ide_end_rq(drive, failed, -EIO, blk_rq_bytes(failed)))
+		if (ide_end_rq(drive, failed, BLK_STS_IOERR, blk_rq_bytes(failed)))
 			BUG();
 	} else
 		cdrom_analyze_sense_data(drive, NULL);
@@ -438,7 +438,6 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 
 		rq = blk_get_request(drive->queue,
 			write ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN,  __GFP_RECLAIM);
-		scsi_req_init(rq);
 		memcpy(scsi_req(rq)->cmd, cmd, BLK_MAX_CDB);
 		ide_req(rq)->type = ATA_PRIV_PC;
 		rq->rq_flags |= rq_flags;
@@ -508,7 +507,7 @@ static bool ide_cd_error_cmd(ide_drive_t *drive, struct ide_cmd *cmd)
 		nr_bytes -= cmd->last_xfer_len;
 
 	if (nr_bytes > 0) {
-		ide_complete_rq(drive, 0, nr_bytes);
+		ide_complete_rq(drive, BLK_STS_OK, nr_bytes);
 		return true;
 	}
 
@@ -674,7 +673,7 @@ static ide_startstop_t cdrom_newpc_intr(ide_drive_t *drive)
 out_end:
 	if (blk_rq_is_scsi(rq) && rc == 0) {
 		scsi_req(rq)->resid_len = 0;
-		blk_end_request_all(rq, 0);
+		blk_end_request_all(rq, BLK_STS_OK);
 		hwif->rq = NULL;
 	} else {
 		if (sense && uptodate)
@@ -699,7 +698,7 @@ out_end:
 				scsi_req(rq)->resid_len += cmd->last_xfer_len;
 		}
 
-		ide_complete_rq(drive, uptodate ? 0 : -EIO, blk_rq_bytes(rq));
+		ide_complete_rq(drive, uptodate ? BLK_STS_OK : BLK_STS_IOERR, blk_rq_bytes(rq));
 
 		if (sense && rc == 2)
 			ide_error(drive, "request sense failure", stat);
@@ -844,7 +843,7 @@ out_end:
 	if (nsectors == 0)
 		nsectors = 1;
 
-	ide_complete_rq(drive, uptodate ? 0 : -EIO, nsectors << 9);
+	ide_complete_rq(drive, uptodate ? BLK_STS_OK : BLK_STS_IOERR, nsectors << 9);
 
 	return ide_stopped;
 }

drivers/ide/ide-cd_ioctl.c

@@ -304,7 +304,6 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 	int ret;
 
 	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	scsi_req_init(rq);
 	ide_req(rq)->type = ATA_PRIV_MISC;
 	rq->rq_flags = RQF_QUIET;
 	blk_execute_rq(drive->queue, cd->disk, rq, 0);

drivers/ide/ide-devsets.c

@@ -166,7 +166,6 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting,
 		return setting->set(drive, arg);
 
 	rq = blk_get_request(q, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	scsi_req_init(rq);
 	ide_req(rq)->type = ATA_PRIV_MISC;
 	scsi_req(rq)->cmd_len = 5;
 	scsi_req(rq)->cmd[0] = REQ_DEVSET_EXEC;

drivers/ide/ide-disk.c

@@ -478,7 +478,6 @@ static int set_multcount(ide_drive_t *drive, int arg)
 		return -EBUSY;
 
 	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	scsi_req_init(rq);
 	ide_req(rq)->type = ATA_PRIV_TASKFILE;
 
 	drive->mult_req = arg;

drivers/ide/ide-dma.c

@@ -104,7 +104,7 @@ ide_startstop_t ide_dma_intr(ide_drive_t *drive)
 			if ((cmd->tf_flags & IDE_TFLAG_FS) == 0)
 				ide_finish_cmd(drive, cmd, stat);
 			else
-				ide_complete_rq(drive, 0,
+				ide_complete_rq(drive, BLK_STS_OK,
 						blk_rq_sectors(cmd->rq) << 9);
 			return ide_stopped;
 		}

drivers/ide/ide-eh.c

@@ -135,7 +135,7 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat)
 			return ide_stopped;
 		}
 		scsi_req(rq)->result = err;
-		ide_complete_rq(drive, err ? -EIO : 0, blk_rq_bytes(rq));
+		ide_complete_rq(drive, err ? BLK_STS_IOERR : BLK_STS_OK, blk_rq_bytes(rq));
 		return ide_stopped;
 	}
 
@@ -143,7 +143,7 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat)
 }
 EXPORT_SYMBOL_GPL(ide_error);
 
-static inline void ide_complete_drive_reset(ide_drive_t *drive, int err)
+static inline void ide_complete_drive_reset(ide_drive_t *drive, blk_status_t err)
 {
 	struct request *rq = drive->hwif->rq;
 
@@ -151,7 +151,7 @@ static inline void ide_complete_drive_reset(ide_drive_t *drive, int err)
 	    scsi_req(rq)->cmd[0] == REQ_DRIVE_RESET) {
 		if (err <= 0 && scsi_req(rq)->result == 0)
 			scsi_req(rq)->result = -EIO;
-		ide_complete_rq(drive, err ? err : 0, blk_rq_bytes(rq));
+		ide_complete_rq(drive, err, blk_rq_bytes(rq));
 	}
 }
 
@@ -191,7 +191,7 @@ static ide_startstop_t atapi_reset_pollfunc(ide_drive_t *drive)
 	}
 	/* done polling */
 	hwif->polling = 0;
-	ide_complete_drive_reset(drive, 0);
+	ide_complete_drive_reset(drive, BLK_STS_OK);
 	return ide_stopped;
 }
 
@@ -225,7 +225,7 @@ static ide_startstop_t reset_pollfunc(ide_drive_t *drive)
 	ide_hwif_t *hwif = drive->hwif;
 	const struct ide_port_ops *port_ops = hwif->port_ops;
 	u8 tmp;
-	int err = 0;
+	blk_status_t err = BLK_STS_OK;
 
 	if (port_ops && port_ops->reset_poll) {
 		err = port_ops->reset_poll(drive);
@@ -247,7 +247,7 @@ static ide_startstop_t reset_pollfunc(ide_drive_t *drive)
 		printk(KERN_ERR "%s: reset timed-out, status=0x%02x\n",
 			hwif->name, tmp);
 		drive->failures++;
-		err = -EIO;
+		err = BLK_STS_IOERR;
 	} else  {
 		tmp = ide_read_error(drive);
 
@@ -257,7 +257,7 @@ static ide_startstop_t reset_pollfunc(ide_drive_t *drive)
 		} else {
 			ide_reset_report_error(hwif, tmp);
 			drive->failures++;
-			err = -EIO;
+			err = BLK_STS_IOERR;
 		}
 	}
 out:
@@ -392,7 +392,7 @@ static ide_startstop_t do_reset1(ide_drive_t *drive, int do_not_try_atapi)
 
 	if (io_ports->ctl_addr == 0) {
 		spin_unlock_irqrestore(&hwif->lock, flags);
-		ide_complete_drive_reset(drive, -ENXIO);
+		ide_complete_drive_reset(drive, BLK_STS_IOERR);
 		return ide_stopped;
 	}
 

drivers/ide/ide-floppy.c

@@ -143,7 +143,7 @@ static ide_startstop_t ide_floppy_issue_pc(ide_drive_t *drive,
 
 		drive->failed_pc = NULL;
 		drive->pc_callback(drive, 0);
-		ide_complete_rq(drive, -EIO, done);
+		ide_complete_rq(drive, BLK_STS_IOERR, done);
 		return ide_stopped;
 	}
 
@@ -248,7 +248,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
 
 		if (ata_misc_request(rq)) {
 			scsi_req(rq)->result = 0;
-			ide_complete_rq(drive, 0, blk_rq_bytes(rq));
+			ide_complete_rq(drive, BLK_STS_OK, blk_rq_bytes(rq));
 			return ide_stopped;
 		} else
 			goto out_end;
@@ -303,7 +303,7 @@ out_end:
 	drive->failed_pc = NULL;
 	if (blk_rq_is_passthrough(rq) && scsi_req(rq)->result == 0)
 		scsi_req(rq)->result = -EIO;
-	ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
+	ide_complete_rq(drive, BLK_STS_IOERR, blk_rq_bytes(rq));
 	return ide_stopped;
 }
 

drivers/ide/ide-io.c

@@ -54,7 +54,7 @@
 #include <linux/uaccess.h>
 #include <asm/io.h>
 
-int ide_end_rq(ide_drive_t *drive, struct request *rq, int error,
+int ide_end_rq(ide_drive_t *drive, struct request *rq, blk_status_t error,
 	       unsigned int nr_bytes)
 {
 	/*
@@ -112,7 +112,7 @@ void ide_complete_cmd(ide_drive_t *drive, struct ide_cmd *cmd, u8 stat, u8 err)
 	}
 }
 
-int ide_complete_rq(ide_drive_t *drive, int error, unsigned int nr_bytes)
+int ide_complete_rq(ide_drive_t *drive, blk_status_t error, unsigned int nr_bytes)
 {
 	ide_hwif_t *hwif = drive->hwif;
 	struct request *rq = hwif->rq;
@@ -122,7 +122,7 @@ int ide_complete_rq(ide_drive_t *drive, int error, unsigned int nr_bytes)
 	 * if failfast is set on a request, override number of sectors
 	 * and complete the whole request right now
 	 */
-	if (blk_noretry_request(rq) && error <= 0)
+	if (blk_noretry_request(rq) && error)
 		nr_bytes = blk_rq_sectors(rq) << 9;
 
 	rc = ide_end_rq(drive, rq, error, nr_bytes);
@@ -149,7 +149,7 @@ void ide_kill_rq(ide_drive_t *drive, struct request *rq)
 			scsi_req(rq)->result = -EIO;
 	}
 
-	ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
+	ide_complete_rq(drive, BLK_STS_IOERR, blk_rq_bytes(rq));
 }
 
 static void ide_tf_set_specify_cmd(ide_drive_t *drive, struct ide_taskfile *tf)
@@ -272,7 +272,7 @@ static ide_startstop_t execute_drive_cmd (ide_drive_t *drive,
  	printk("%s: DRIVE_CMD (null)\n", drive->name);
 #endif
 	scsi_req(rq)->result = 0;
-	ide_complete_rq(drive, 0, blk_rq_bytes(rq));
+	ide_complete_rq(drive, BLK_STS_OK, blk_rq_bytes(rq));
 
  	return ide_stopped;
 }

drivers/ide/ide-ioctls.c

@@ -126,7 +126,6 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg)
 		struct request *rq;
 
 		rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
-		scsi_req_init(rq);
 		ide_req(rq)->type = ATA_PRIV_TASKFILE;
 		blk_execute_rq(drive->queue, NULL, rq, 0);
 		err = scsi_req(rq)->result ? -EIO : 0;
@@ -224,7 +223,6 @@ static int generic_drive_reset(ide_drive_t *drive)
 	int ret = 0;
 
 	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	scsi_req_init(rq);
 	ide_req(rq)->type = ATA_PRIV_MISC;
 	scsi_req(rq)->cmd_len = 1;
 	scsi_req(rq)->cmd[0] = REQ_DRIVE_RESET;

drivers/ide/ide-park.c

@@ -32,7 +32,6 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	spin_unlock_irq(&hwif->lock);
 
 	rq = blk_get_request(q, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	scsi_req_init(rq);
 	scsi_req(rq)->cmd[0] = REQ_PARK_HEADS;
 	scsi_req(rq)->cmd_len = 1;
 	ide_req(rq)->type = ATA_PRIV_MISC;
@@ -48,7 +47,6 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
 	 * timeout has expired, so power management will be reenabled.
 	 */
 	rq = blk_get_request(q, REQ_OP_DRV_IN, GFP_NOWAIT);
-	scsi_req_init(rq);
 	if (IS_ERR(rq))
 		goto out;
 

drivers/ide/ide-pm.c

@@ -19,7 +19,6 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 
 	memset(&rqpm, 0, sizeof(rqpm));
 	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	scsi_req_init(rq);
 	ide_req(rq)->type = ATA_PRIV_PM_SUSPEND;
 	rq->special = &rqpm;
 	rqpm.pm_step = IDE_PM_START_SUSPEND;
@@ -40,7 +39,7 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
 	return ret;
 }
 
-static void ide_end_sync_rq(struct request *rq, int error)
+static void ide_end_sync_rq(struct request *rq, blk_status_t error)
 {
 	complete(rq->end_io_data);
 }
@@ -57,7 +56,7 @@ static int ide_pm_execute_rq(struct request *rq)
 	if (unlikely(blk_queue_dying(q))) {
 		rq->rq_flags |= RQF_QUIET;
 		scsi_req(rq)->result = -ENXIO;
-		__blk_end_request_all(rq, 0);
+		__blk_end_request_all(rq, BLK_STS_OK);
 		spin_unlock_irq(q->queue_lock);
 		return -ENXIO;
 	}
@@ -91,7 +90,6 @@ int generic_ide_resume(struct device *dev)
 
 	memset(&rqpm, 0, sizeof(rqpm));
 	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	scsi_req_init(rq);
 	ide_req(rq)->type = ATA_PRIV_PM_RESUME;
 	rq->rq_flags |= RQF_PREEMPT;
 	rq->special = &rqpm;
@@ -235,7 +233,7 @@ void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq)
 
 	drive->hwif->rq = NULL;
 
-	if (blk_end_request(rq, 0, 0))
+	if (blk_end_request(rq, BLK_STS_OK, 0))
 		BUG();
 }
 

drivers/ide/ide-probe.c

@@ -741,12 +741,12 @@ static void ide_port_tune_devices(ide_hwif_t *hwif)
 	}
 }
 
-static int ide_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp)
+static void ide_initialize_rq(struct request *rq)
 {
 	struct ide_request *req = blk_mq_rq_to_pdu(rq);
 
+	scsi_req_init(&req->sreq);
 	req->sreq.sense = req->sense;
-	return 0;
 }
 
 /*
@@ -771,8 +771,9 @@ static int ide_init_queue(ide_drive_t *drive)
 		return 1;
 
 	q->request_fn = do_ide_request;
-	q->init_rq_fn = ide_init_rq;
+	q->initialize_rq_fn = ide_initialize_rq;
 	q->cmd_size = sizeof(struct ide_request);
+	queue_flag_set_unlocked(QUEUE_FLAG_SCSI_PASSTHROUGH, q);
 	if (blk_init_allocated_queue(q) < 0) {
 		blk_cleanup_queue(q);
 		return 1;

drivers/ide/ide-tape.c

@@ -474,7 +474,7 @@ static ide_startstop_t ide_tape_issue_pc(ide_drive_t *drive,
 
 		drive->failed_pc = NULL;
 		drive->pc_callback(drive, 0);
-		ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
+		ide_complete_rq(drive, BLK_STS_IOERR, blk_rq_bytes(rq));
 		return ide_stopped;
 	}
 	ide_debug_log(IDE_DBG_SENSE, "retry #%d, cmd: 0x%02x", pc->retries,
@@ -855,7 +855,6 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
 	BUG_ON(size < 0 || size % tape->blk_size);
 
 	rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
-	scsi_req_init(rq);
 	ide_req(rq)->type = ATA_PRIV_MISC;
 	scsi_req(rq)->cmd[13] = cmd;
 	rq->rq_disk = tape->disk;

drivers/ide/ide-taskfile.c

@@ -318,7 +318,7 @@ static void ide_error_cmd(ide_drive_t *drive, struct ide_cmd *cmd)
 		}
 
 		if (nr_bytes > 0)
-			ide_complete_rq(drive, 0, nr_bytes);
+			ide_complete_rq(drive, BLK_STS_OK, nr_bytes);
 	}
 }
 
@@ -336,7 +336,7 @@ void ide_finish_cmd(ide_drive_t *drive, struct ide_cmd *cmd, u8 stat)
 		ide_driveid_update(drive);
 	}
 
-	ide_complete_rq(drive, err ? -EIO : 0, blk_rq_bytes(rq));
+	ide_complete_rq(drive, err ? BLK_STS_IOERR : BLK_STS_OK, blk_rq_bytes(rq));
 }
 
 /*
@@ -394,7 +394,7 @@ out_end:
 	if ((cmd->tf_flags & IDE_TFLAG_FS) == 0)
 		ide_finish_cmd(drive, cmd, stat);
 	else
-		ide_complete_rq(drive, 0, blk_rq_sectors(cmd->rq) << 9);
+		ide_complete_rq(drive, BLK_STS_OK, blk_rq_sectors(cmd->rq) << 9);
 	return ide_stopped;
 out_err:
 	ide_error_cmd(drive, cmd);
@@ -433,7 +433,6 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
 	rq = blk_get_request(drive->queue,
 		(cmd->tf_flags & IDE_TFLAG_WRITE) ?
 			REQ_OP_DRV_OUT : REQ_OP_DRV_IN, __GFP_RECLAIM);
-	scsi_req_init(rq);
 	ide_req(rq)->type = ATA_PRIV_TASKFILE;
 
 	/*

drivers/ide/siimage.c

@@ -406,7 +406,7 @@ static int siimage_dma_test_irq(ide_drive_t *drive)
  *	yet.
  */
 
-static int sil_sata_reset_poll(ide_drive_t *drive)
+static blk_status_t sil_sata_reset_poll(ide_drive_t *drive)
 {
 	ide_hwif_t *hwif = drive->hwif;
 	void __iomem *sata_status_addr
@@ -419,11 +419,11 @@ static int sil_sata_reset_poll(ide_drive_t *drive)
 		if ((sata_stat & 0x03) != 0x03) {
 			printk(KERN_WARNING "%s: reset phy dead, status=0x%08x\n",
 					    hwif->name, sata_stat);
-			return -ENXIO;
+			return BLK_STS_IOERR;
 		}
 	}
 
-	return 0;
+	return BLK_STS_OK;
 }
 
 /**

drivers/lightnvm/core.c

@@ -252,8 +252,9 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
 	}
 	mutex_unlock(&dev->mlock);
 
-	if (nvm_reserve_luns(dev, s->lun_begin, s->lun_end))
-		return -ENOMEM;
+	ret = nvm_reserve_luns(dev, s->lun_begin, s->lun_end);
+	if (ret)
+		return ret;
 
 	t = kmalloc(sizeof(struct nvm_target), GFP_KERNEL);
 	if (!t) {
@@ -640,6 +641,7 @@ EXPORT_SYMBOL(nvm_max_phys_sects);
 int nvm_submit_io(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
 {
 	struct nvm_dev *dev = tgt_dev->parent;
+	int ret;
 
 	if (!dev->ops->submit_io)
 		return -ENODEV;
@@ -647,7 +649,12 @@ int nvm_submit_io(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
 	nvm_rq_tgt_to_dev(tgt_dev, rqd);
 
 	rqd->dev = tgt_dev;
-	return dev->ops->submit_io(dev, rqd);
+
+	/* In case of error, fail with right address format */
+	ret = dev->ops->submit_io(dev, rqd);
+	if (ret)
+		nvm_rq_dev_to_tgt(tgt_dev, rqd);
+	return ret;
 }
 EXPORT_SYMBOL(nvm_submit_io);
 

drivers/lightnvm/pblk-cache.c

@@ -31,9 +31,13 @@ int pblk_write_to_cache(struct pblk *pblk, struct bio *bio, unsigned long flags)
 	 */
 retry:
 	ret = pblk_rb_may_write_user(&pblk->rwb, bio, nr_entries, &bpos);
-	if (ret == NVM_IO_REQUEUE) {
+	switch (ret) {
+	case NVM_IO_REQUEUE:
 		io_schedule();
 		goto retry;
+	case NVM_IO_ERR:
+		pblk_pipeline_stop(pblk);
+		goto out;
 	}
 
 	if (unlikely(!bio_has_data(bio)))
@@ -58,6 +62,8 @@ retry:
 	atomic_long_add(nr_entries, &pblk->req_writes);
 #endif
 
+	pblk_rl_inserted(&pblk->rl, nr_entries);
+
 out:
 	pblk_write_should_kick(pblk);
 	return ret;

drivers/lightnvm/pblk-core.c

@@ -17,7 +17,6 @@
  */
 
 #include "pblk.h"
-#include <linux/time.h>
 
 static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
 			 struct ppa_addr *ppa)
@@ -34,7 +33,7 @@ static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
 		pr_err("pblk: attempted to erase bb: line:%d, pos:%d\n",
 							line->id, pos);
 
-	pblk_line_run_ws(pblk, NULL, ppa, pblk_line_mark_bb);
+	pblk_line_run_ws(pblk, NULL, ppa, pblk_line_mark_bb, pblk->bb_wq);
 }
 
 static void __pblk_end_io_erase(struct pblk *pblk, struct nvm_rq *rqd)
@@ -54,6 +53,8 @@ static void __pblk_end_io_erase(struct pblk *pblk, struct nvm_rq *rqd)
 		*ppa = rqd->ppa_addr;
 		pblk_mark_bb(pblk, line, ppa);
 	}
+
+	atomic_dec(&pblk->inflight_io);
 }
 
 /* Erase completion assumes that only one block is erased at the time */
@@ -61,13 +62,12 @@ static void pblk_end_io_erase(struct nvm_rq *rqd)
 {
 	struct pblk *pblk = rqd->private;
 
-	up(&pblk->erase_sem);
 	__pblk_end_io_erase(pblk, rqd);
-	mempool_free(rqd, pblk->r_rq_pool);
+	mempool_free(rqd, pblk->g_rq_pool);
 }
 
-static void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line,
-				  u64 paddr)
+void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line,
+			   u64 paddr)
 {
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct list_head *move_list = NULL;
@@ -88,7 +88,7 @@ static void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line,
 		spin_unlock(&line->lock);
 		return;
 	}
-	line->vsc--;
+	le32_add_cpu(line->vsc, -1);
 
 	if (line->state == PBLK_LINESTATE_CLOSED)
 		move_list = pblk_line_gc_list(pblk, line);
@@ -130,18 +130,6 @@ void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa)
 	__pblk_map_invalidate(pblk, line, paddr);
 }
 
-void pblk_map_pad_invalidate(struct pblk *pblk, struct pblk_line *line,
-			     u64 paddr)
-{
-	__pblk_map_invalidate(pblk, line, paddr);
-
-	pblk_rb_sync_init(&pblk->rwb, NULL);
-	line->left_ssecs--;
-	if (!line->left_ssecs)
-		pblk_line_run_ws(pblk, line, NULL, pblk_line_close_ws);
-	pblk_rb_sync_end(&pblk->rwb, NULL);
-}
-
 static void pblk_invalidate_range(struct pblk *pblk, sector_t slba,
 				  unsigned int nr_secs)
 {
@@ -172,8 +160,8 @@ struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw)
 		pool = pblk->w_rq_pool;
 		rq_size = pblk_w_rq_size;
 	} else {
-		pool = pblk->r_rq_pool;
-		rq_size = pblk_r_rq_size;
+		pool = pblk->g_rq_pool;
+		rq_size = pblk_g_rq_size;
 	}
 
 	rqd = mempool_alloc(pool, GFP_KERNEL);
@@ -189,7 +177,7 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int rw)
 	if (rw == WRITE)
 		pool = pblk->w_rq_pool;
 	else
-		pool = pblk->r_rq_pool;
+		pool = pblk->g_rq_pool;
 
 	mempool_free(rqd, pool);
 }
@@ -271,35 +259,26 @@ void pblk_end_io_sync(struct nvm_rq *rqd)
 	complete(waiting);
 }
 
-void pblk_flush_writer(struct pblk *pblk)
+void pblk_wait_for_meta(struct pblk *pblk)
 {
-	struct bio *bio;
-	int ret;
-	DECLARE_COMPLETION_ONSTACK(wait);
-
-	bio = bio_alloc(GFP_KERNEL, 1);
-	if (!bio)
-		return;
-
-	bio->bi_iter.bi_sector = 0; /* internal bio */
-	bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_OP_FLUSH);
-	bio->bi_private = &wait;
-	bio->bi_end_io = pblk_end_bio_sync;
+	do {
+		if (!atomic_read(&pblk->inflight_io))
+			break;
 
-	ret = pblk_write_to_cache(pblk, bio, 0);
-	if (ret == NVM_IO_OK) {
-		if (!wait_for_completion_io_timeout(&wait,
-				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
-			pr_err("pblk: flush cache timed out\n");
-		}
-	} else if (ret != NVM_IO_DONE) {
-		pr_err("pblk: tear down bio failed\n");
-	}
+		schedule();
+	} while (1);
+}
 
-	if (bio->bi_error)
-		pr_err("pblk: flush sync write failed (%u)\n", bio->bi_error);
+static void pblk_flush_writer(struct pblk *pblk)
+{
+	pblk_rb_flush(&pblk->rwb);
+	do {
+		if (!pblk_rb_sync_count(&pblk->rwb))
+			break;
 
-	bio_put(bio);
+		pblk_write_kick(pblk);
+		schedule();
+	} while (1);
 }
 
 struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
@@ -307,28 +286,31 @@ struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
 	struct pblk_line_meta *lm = &pblk->lm;
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct list_head *move_list = NULL;
+	int vsc = le32_to_cpu(*line->vsc);
 
-	if (!line->vsc) {
+	lockdep_assert_held(&line->lock);
+
+	if (!vsc) {
 		if (line->gc_group != PBLK_LINEGC_FULL) {
 			line->gc_group = PBLK_LINEGC_FULL;
 			move_list = &l_mg->gc_full_list;
 		}
-	} else if (line->vsc < lm->mid_thrs) {
+	} else if (vsc < lm->high_thrs) {
 		if (line->gc_group != PBLK_LINEGC_HIGH) {
 			line->gc_group = PBLK_LINEGC_HIGH;
 			move_list = &l_mg->gc_high_list;
 		}
-	} else if (line->vsc < lm->high_thrs) {
+	} else if (vsc < lm->mid_thrs) {
 		if (line->gc_group != PBLK_LINEGC_MID) {
 			line->gc_group = PBLK_LINEGC_MID;
 			move_list = &l_mg->gc_mid_list;
 		}
-	} else if (line->vsc < line->sec_in_line) {
+	} else if (vsc < line->sec_in_line) {
 		if (line->gc_group != PBLK_LINEGC_LOW) {
 			line->gc_group = PBLK_LINEGC_LOW;
 			move_list = &l_mg->gc_low_list;
 		}
-	} else if (line->vsc == line->sec_in_line) {
+	} else if (vsc == line->sec_in_line) {
 		if (line->gc_group != PBLK_LINEGC_EMPTY) {
 			line->gc_group = PBLK_LINEGC_EMPTY;
 			move_list = &l_mg->gc_empty_list;
@@ -338,7 +320,7 @@ struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
 		line->gc_group = PBLK_LINEGC_NONE;
 		move_list =  &l_mg->corrupt_list;
 		pr_err("pblk: corrupted vsc for line %d, vsc:%d (%d/%d/%d)\n",
-						line->id, line->vsc,
+						line->id, vsc,
 						line->sec_in_line,
 						lm->high_thrs, lm->mid_thrs);
 	}
@@ -397,6 +379,11 @@ void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd)
 #endif
 }
 
+void pblk_set_sec_per_write(struct pblk *pblk, int sec_per_write)
+{
+	pblk->sec_per_write = sec_per_write;
+}
+
 int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
@@ -431,21 +418,23 @@ int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
 		}
 	}
 #endif
+
+	atomic_inc(&pblk->inflight_io);
+
 	return nvm_submit_io(dev, rqd);
 }
 
 struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
 			      unsigned int nr_secs, unsigned int len,
-			      gfp_t gfp_mask)
+			      int alloc_type, gfp_t gfp_mask)
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
-	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	void *kaddr = data;
 	struct page *page;
 	struct bio *bio;
 	int i, ret;
 
-	if (l_mg->emeta_alloc_type == PBLK_KMALLOC_META)
+	if (alloc_type == PBLK_KMALLOC_META)
 		return bio_map_kern(dev->q, kaddr, len, gfp_mask);
 
 	bio = bio_kmalloc(gfp_mask, nr_secs);
@@ -478,7 +467,7 @@ out:
 int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
 		   unsigned long secs_to_flush)
 {
-	int max = pblk->max_write_pgs;
+	int max = pblk->sec_per_write;
 	int min = pblk->min_write_pgs;
 	int secs_to_sync = 0;
 
@@ -492,12 +481,26 @@ int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
 	return secs_to_sync;
 }
 
-static u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line,
-			     int nr_secs)
+void pblk_dealloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs)
+{
+	u64 addr;
+	int i;
+
+	addr = find_next_zero_bit(line->map_bitmap,
+					pblk->lm.sec_per_line, line->cur_sec);
+	line->cur_sec = addr - nr_secs;
+
+	for (i = 0; i < nr_secs; i++, line->cur_sec--)
+		WARN_ON(!test_and_clear_bit(line->cur_sec, line->map_bitmap));
+}
+
+u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs)
 {
 	u64 addr;
 	int i;
 
+	lockdep_assert_held(&line->lock);
+
 	/* logic error: ppa out-of-bounds. Prevent generating bad address */
 	if (line->cur_sec + nr_secs > pblk->lm.sec_per_line) {
 		WARN(1, "pblk: page allocation out of bounds\n");
@@ -528,27 +531,38 @@ u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs)
 	return addr;
 }
 
+u64 pblk_lookup_page(struct pblk *pblk, struct pblk_line *line)
+{
+	u64 paddr;
+
+	spin_lock(&line->lock);
+	paddr = find_next_zero_bit(line->map_bitmap,
+					pblk->lm.sec_per_line, line->cur_sec);
+	spin_unlock(&line->lock);
+
+	return paddr;
+}
+
 /*
  * Submit emeta to one LUN in the raid line at the time to avoid a deadlock when
  * taking the per LUN semaphore.
  */
 static int pblk_line_submit_emeta_io(struct pblk *pblk, struct pblk_line *line,
-				     u64 paddr, int dir)
+				     void *emeta_buf, u64 paddr, int dir)
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
 	struct nvm_geo *geo = &dev->geo;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct pblk_line_meta *lm = &pblk->lm;
+	void *ppa_list, *meta_list;
 	struct bio *bio;
 	struct nvm_rq rqd;
-	struct ppa_addr *ppa_list;
-	dma_addr_t dma_ppa_list;
-	void *emeta = line->emeta;
+	dma_addr_t dma_ppa_list, dma_meta_list;
 	int min = pblk->min_write_pgs;
-	int left_ppas = lm->emeta_sec;
+	int left_ppas = lm->emeta_sec[0];
 	int id = line->id;
 	int rq_ppas, rq_len;
 	int cmd_op, bio_op;
-	int flags;
 	int i, j;
 	int ret;
 	DECLARE_COMPLETION_ONSTACK(wait);
@@ -556,25 +570,28 @@ static int pblk_line_submit_emeta_io(struct pblk *pblk, struct pblk_line *line,
 	if (dir == WRITE) {
 		bio_op = REQ_OP_WRITE;
 		cmd_op = NVM_OP_PWRITE;
-		flags = pblk_set_progr_mode(pblk, WRITE);
 	} else if (dir == READ) {
 		bio_op = REQ_OP_READ;
 		cmd_op = NVM_OP_PREAD;
-		flags = pblk_set_read_mode(pblk);
 	} else
 		return -EINVAL;
 
-	ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_ppa_list);
-	if (!ppa_list)
+	meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+							&dma_meta_list);
+	if (!meta_list)
 		return -ENOMEM;
 
+	ppa_list = meta_list + pblk_dma_meta_size;
+	dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
+
 next_rq:
 	memset(&rqd, 0, sizeof(struct nvm_rq));
 
 	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
 	rq_len = rq_ppas * geo->sec_size;
 
-	bio = pblk_bio_map_addr(pblk, emeta, rq_ppas, rq_len, GFP_KERNEL);
+	bio = pblk_bio_map_addr(pblk, emeta_buf, rq_ppas, rq_len,
+					l_mg->emeta_alloc_type, GFP_KERNEL);
 	if (IS_ERR(bio)) {
 		ret = PTR_ERR(bio);
 		goto free_rqd_dma;
@@ -584,27 +601,38 @@ next_rq:
 	bio_set_op_attrs(bio, bio_op, 0);
 
 	rqd.bio = bio;
-	rqd.opcode = cmd_op;
-	rqd.flags = flags;
-	rqd.nr_ppas = rq_ppas;
+	rqd.meta_list = meta_list;
 	rqd.ppa_list = ppa_list;
+	rqd.dma_meta_list = dma_meta_list;
 	rqd.dma_ppa_list = dma_ppa_list;
+	rqd.opcode = cmd_op;
+	rqd.nr_ppas = rq_ppas;
 	rqd.end_io = pblk_end_io_sync;
 	rqd.private = &wait;
 
 	if (dir == WRITE) {
+		struct pblk_sec_meta *meta_list = rqd.meta_list;
+
+		rqd.flags = pblk_set_progr_mode(pblk, WRITE);
 		for (i = 0; i < rqd.nr_ppas; ) {
 			spin_lock(&line->lock);
 			paddr = __pblk_alloc_page(pblk, line, min);
 			spin_unlock(&line->lock);
-			for (j = 0; j < min; j++, i++, paddr++)
+			for (j = 0; j < min; j++, i++, paddr++) {
+				meta_list[i].lba = cpu_to_le64(ADDR_EMPTY);
 				rqd.ppa_list[i] =
 					addr_to_gen_ppa(pblk, paddr, id);
+			}
 		}
 	} else {
 		for (i = 0; i < rqd.nr_ppas; ) {
 			struct ppa_addr ppa = addr_to_gen_ppa(pblk, paddr, id);
 			int pos = pblk_dev_ppa_to_pos(geo, ppa);
+			int read_type = PBLK_READ_RANDOM;
+
+			if (pblk_io_aligned(pblk, rq_ppas))
+				read_type = PBLK_READ_SEQUENTIAL;
+			rqd.flags = pblk_set_read_mode(pblk, read_type);
 
 			while (test_bit(pos, line->blk_bitmap)) {
 				paddr += min;
@@ -645,9 +673,11 @@ next_rq:
 				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
 		pr_err("pblk: emeta I/O timed out\n");
 	}
+	atomic_dec(&pblk->inflight_io);
 	reinit_completion(&wait);
 
-	bio_put(bio);
+	if (likely(pblk->l_mg.emeta_alloc_type == PBLK_VMALLOC_META))
+		bio_put(bio);
 
 	if (rqd.error) {
 		if (dir == WRITE)
@@ -656,12 +686,12 @@ next_rq:
 			pblk_log_read_err(pblk, &rqd);
 	}
 
-	emeta += rq_len;
+	emeta_buf += rq_len;
 	left_ppas -= rq_ppas;
 	if (left_ppas)
 		goto next_rq;
 free_rqd_dma:
-	nvm_dev_dma_free(dev->parent, ppa_list, dma_ppa_list);
+	nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_list);
 	return ret;
 }
 
@@ -697,21 +727,24 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
 		bio_op = REQ_OP_WRITE;
 		cmd_op = NVM_OP_PWRITE;
 		flags = pblk_set_progr_mode(pblk, WRITE);
-		lba_list = pblk_line_emeta_to_lbas(line->emeta);
+		lba_list = emeta_to_lbas(pblk, line->emeta->buf);
 	} else if (dir == READ) {
 		bio_op = REQ_OP_READ;
 		cmd_op = NVM_OP_PREAD;
-		flags = pblk_set_read_mode(pblk);
+		flags = pblk_set_read_mode(pblk, PBLK_READ_SEQUENTIAL);
 	} else
 		return -EINVAL;
 
 	memset(&rqd, 0, sizeof(struct nvm_rq));
 
-	rqd.ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
-							&rqd.dma_ppa_list);
-	if (!rqd.ppa_list)
+	rqd.meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+							&rqd.dma_meta_list);
+	if (!rqd.meta_list)
 		return -ENOMEM;
 
+	rqd.ppa_list = rqd.meta_list + pblk_dma_meta_size;
+	rqd.dma_ppa_list = rqd.dma_meta_list + pblk_dma_meta_size;
+
 	bio = bio_map_kern(dev->q, line->smeta, lm->smeta_len, GFP_KERNEL);
 	if (IS_ERR(bio)) {
 		ret = PTR_ERR(bio);
@@ -729,9 +762,15 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
 	rqd.private = &wait;
 
 	for (i = 0; i < lm->smeta_sec; i++, paddr++) {
+		struct pblk_sec_meta *meta_list = rqd.meta_list;
+
 		rqd.ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id);
-		if (dir == WRITE)
-			lba_list[paddr] = cpu_to_le64(ADDR_EMPTY);
+
+		if (dir == WRITE) {
+			__le64 addr_empty = cpu_to_le64(ADDR_EMPTY);
+
+			meta_list[i].lba = lba_list[paddr] = addr_empty;
+		}
 	}
 
 	/*
@@ -750,6 +789,7 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
 				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
 		pr_err("pblk: smeta I/O timed out\n");
 	}
+	atomic_dec(&pblk->inflight_io);
 
 	if (rqd.error) {
 		if (dir == WRITE)
@@ -759,7 +799,7 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
 	}
 
 free_ppa_list:
-	nvm_dev_dma_free(dev->parent, rqd.ppa_list, rqd.dma_ppa_list);
+	nvm_dev_dma_free(dev->parent, rqd.meta_list, rqd.dma_meta_list);
 
 	return ret;
 }
@@ -771,9 +811,11 @@ int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line)
 	return pblk_line_submit_smeta_io(pblk, line, bpaddr, READ);
 }
 
-int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line)
+int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line,
+			 void *emeta_buf)
 {
-	return pblk_line_submit_emeta_io(pblk, line, line->emeta_ssec, READ);
+	return pblk_line_submit_emeta_io(pblk, line, emeta_buf,
+						line->emeta_ssec, READ);
 }
 
 static void pblk_setup_e_rq(struct pblk *pblk, struct nvm_rq *rqd,
@@ -789,7 +831,7 @@ static void pblk_setup_e_rq(struct pblk *pblk, struct nvm_rq *rqd,
 static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa)
 {
 	struct nvm_rq rqd;
-	int ret;
+	int ret = 0;
 	DECLARE_COMPLETION_ONSTACK(wait);
 
 	memset(&rqd, 0, sizeof(struct nvm_rq));
@@ -824,14 +866,14 @@ out:
 	rqd.private = pblk;
 	__pblk_end_io_erase(pblk, &rqd);
 
-	return 0;
+	return ret;
 }
 
 int pblk_line_erase(struct pblk *pblk, struct pblk_line *line)
 {
 	struct pblk_line_meta *lm = &pblk->lm;
 	struct ppa_addr ppa;
-	int bit = -1;
+	int ret, bit = -1;
 
 	/* Erase only good blocks, one at a time */
 	do {
@@ -850,27 +892,59 @@ int pblk_line_erase(struct pblk *pblk, struct pblk_line *line)
 		WARN_ON(test_and_set_bit(bit, line->erase_bitmap));
 		spin_unlock(&line->lock);
 
-		if (pblk_blk_erase_sync(pblk, ppa)) {
+		ret = pblk_blk_erase_sync(pblk, ppa);
+		if (ret) {
 			pr_err("pblk: failed to erase line %d\n", line->id);
-			return -ENOMEM;
+			return ret;
 		}
 	} while (1);
 
 	return 0;
 }
 
+static void pblk_line_setup_metadata(struct pblk_line *line,
+				     struct pblk_line_mgmt *l_mg,
+				     struct pblk_line_meta *lm)
+{
+	int meta_line;
+
+	lockdep_assert_held(&l_mg->free_lock);
+
+retry_meta:
+	meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES);
+	if (meta_line == PBLK_DATA_LINES) {
+		spin_unlock(&l_mg->free_lock);
+		io_schedule();
+		spin_lock(&l_mg->free_lock);
+		goto retry_meta;
+	}
+
+	set_bit(meta_line, &l_mg->meta_bitmap);
+	line->meta_line = meta_line;
+
+	line->smeta = l_mg->sline_meta[meta_line];
+	line->emeta = l_mg->eline_meta[meta_line];
+
+	memset(line->smeta, 0, lm->smeta_len);
+	memset(line->emeta->buf, 0, lm->emeta_len[0]);
+
+	line->emeta->mem = 0;
+	atomic_set(&line->emeta->sync, 0);
+}
+
 /* For now lines are always assumed full lines. Thus, smeta former and current
  * lun bitmaps are omitted.
  */
-static int pblk_line_set_metadata(struct pblk *pblk, struct pblk_line *line,
+static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line,
 				  struct pblk_line *cur)
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
 	struct nvm_geo *geo = &dev->geo;
 	struct pblk_line_meta *lm = &pblk->lm;
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
-	struct line_smeta *smeta = line->smeta;
-	struct line_emeta *emeta = line->emeta;
+	struct pblk_emeta *emeta = line->emeta;
+	struct line_emeta *emeta_buf = emeta->buf;
+	struct line_smeta *smeta_buf = (struct line_smeta *)line->smeta;
 	int nr_blk_line;
 
 	/* After erasing the line, new bad blocks might appear and we risk
@@ -893,42 +967,44 @@ static int pblk_line_set_metadata(struct pblk *pblk, struct pblk_line *line,
 	}
 
 	/* Run-time metadata */
-	line->lun_bitmap = ((void *)(smeta)) + sizeof(struct line_smeta);
+	line->lun_bitmap = ((void *)(smeta_buf)) + sizeof(struct line_smeta);
 
 	/* Mark LUNs allocated in this line (all for now) */
 	bitmap_set(line->lun_bitmap, 0, lm->lun_bitmap_len);
 
-	smeta->header.identifier = cpu_to_le32(PBLK_MAGIC);
-	memcpy(smeta->header.uuid, pblk->instance_uuid, 16);
-	smeta->header.id = cpu_to_le32(line->id);
-	smeta->header.type = cpu_to_le16(line->type);
-	smeta->header.version = cpu_to_le16(1);
+	smeta_buf->header.identifier = cpu_to_le32(PBLK_MAGIC);
+	memcpy(smeta_buf->header.uuid, pblk->instance_uuid, 16);
+	smeta_buf->header.id = cpu_to_le32(line->id);
+	smeta_buf->header.type = cpu_to_le16(line->type);
+	smeta_buf->header.version = cpu_to_le16(1);
 
 	/* Start metadata */
-	smeta->seq_nr = cpu_to_le64(line->seq_nr);
-	smeta->window_wr_lun = cpu_to_le32(geo->nr_luns);
+	smeta_buf->seq_nr = cpu_to_le64(line->seq_nr);
+	smeta_buf->window_wr_lun = cpu_to_le32(geo->nr_luns);
 
 	/* Fill metadata among lines */
 	if (cur) {
 		memcpy(line->lun_bitmap, cur->lun_bitmap, lm->lun_bitmap_len);
-		smeta->prev_id = cpu_to_le32(cur->id);
-		cur->emeta->next_id = cpu_to_le32(line->id);
+		smeta_buf->prev_id = cpu_to_le32(cur->id);
+		cur->emeta->buf->next_id = cpu_to_le32(line->id);
 	} else {
-		smeta->prev_id = cpu_to_le32(PBLK_LINE_EMPTY);
+		smeta_buf->prev_id = cpu_to_le32(PBLK_LINE_EMPTY);
 	}
 
 	/* All smeta must be set at this point */
-	smeta->header.crc = cpu_to_le32(pblk_calc_meta_header_crc(pblk, smeta));
-	smeta->crc = cpu_to_le32(pblk_calc_smeta_crc(pblk, smeta));
+	smeta_buf->header.crc = cpu_to_le32(
+			pblk_calc_meta_header_crc(pblk, &smeta_buf->header));
+	smeta_buf->crc = cpu_to_le32(pblk_calc_smeta_crc(pblk, smeta_buf));
 
 	/* End metadata */
-	memcpy(&emeta->header, &smeta->header, sizeof(struct line_header));
-	emeta->seq_nr = cpu_to_le64(line->seq_nr);
-	emeta->nr_lbas = cpu_to_le64(line->sec_in_line);
-	emeta->nr_valid_lbas = cpu_to_le64(0);
-	emeta->next_id = cpu_to_le32(PBLK_LINE_EMPTY);
-	emeta->crc = cpu_to_le32(0);
-	emeta->prev_id = smeta->prev_id;
+	memcpy(&emeta_buf->header, &smeta_buf->header,
+						sizeof(struct line_header));
+	emeta_buf->seq_nr = cpu_to_le64(line->seq_nr);
+	emeta_buf->nr_lbas = cpu_to_le64(line->sec_in_line);
+	emeta_buf->nr_valid_lbas = cpu_to_le64(0);
+	emeta_buf->next_id = cpu_to_le32(PBLK_LINE_EMPTY);
+	emeta_buf->crc = cpu_to_le32(0);
+	emeta_buf->prev_id = smeta_buf->prev_id;
 
 	return 1;
 }
@@ -965,7 +1041,6 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
 	/* Mark smeta metadata sectors as bad sectors */
 	bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line);
 	off = bit * geo->sec_per_pl;
-retry_smeta:
 	bitmap_set(line->map_bitmap, off, lm->smeta_sec);
 	line->sec_in_line -= lm->smeta_sec;
 	line->smeta_ssec = off;
@@ -973,8 +1048,7 @@ retry_smeta:
 
 	if (init && pblk_line_submit_smeta_io(pblk, line, off, WRITE)) {
 		pr_debug("pblk: line smeta I/O failed. Retry\n");
-		off += geo->sec_per_pl;
-		goto retry_smeta;
+		return 1;
 	}
 
 	bitmap_copy(line->invalid_bitmap, line->map_bitmap, lm->sec_per_line);
@@ -983,8 +1057,8 @@ retry_smeta:
 	 * blocks to make sure that there are enough sectors to store emeta
 	 */
 	bit = lm->sec_per_line;
-	off = lm->sec_per_line - lm->emeta_sec;
-	bitmap_set(line->invalid_bitmap, off, lm->emeta_sec);
+	off = lm->sec_per_line - lm->emeta_sec[0];
+	bitmap_set(line->invalid_bitmap, off, lm->emeta_sec[0]);
 	while (nr_bb) {
 		off -= geo->sec_per_pl;
 		if (!test_bit(off, line->invalid_bitmap)) {
@@ -993,9 +1067,11 @@ retry_smeta:
 		}
 	}
 
-	line->sec_in_line -= lm->emeta_sec;
+	line->sec_in_line -= lm->emeta_sec[0];
 	line->emeta_ssec = off;
-	line->vsc = line->left_ssecs = line->left_msecs = line->sec_in_line;
+	line->nr_valid_lbas = 0;
+	line->left_msecs = line->sec_in_line;
+	*line->vsc = cpu_to_le32(line->sec_in_line);
 
 	if (lm->sec_per_line - line->sec_in_line !=
 		bitmap_weight(line->invalid_bitmap, lm->sec_per_line)) {
@@ -1034,14 +1110,20 @@ static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line)
 
 	spin_lock(&line->lock);
 	if (line->state != PBLK_LINESTATE_FREE) {
+		mempool_free(line->invalid_bitmap, pblk->line_meta_pool);
+		mempool_free(line->map_bitmap, pblk->line_meta_pool);
 		spin_unlock(&line->lock);
-		WARN(1, "pblk: corrupted line state\n");
-		return -EINTR;
+		WARN(1, "pblk: corrupted line %d, state %d\n",
+							line->id, line->state);
+		return -EAGAIN;
 	}
+
 	line->state = PBLK_LINESTATE_OPEN;
 
 	atomic_set(&line->left_eblks, blk_in_line);
 	atomic_set(&line->left_seblks, blk_in_line);
+
+	line->meta_distance = lm->meta_distance;
 	spin_unlock(&line->lock);
 
 	/* Bad blocks do not need to be erased */
@@ -1091,15 +1173,15 @@ struct pblk_line *pblk_line_get(struct pblk *pblk)
 {
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct pblk_line_meta *lm = &pblk->lm;
-	struct pblk_line *line = NULL;
-	int bit;
+	struct pblk_line *line;
+	int ret, bit;
 
 	lockdep_assert_held(&l_mg->free_lock);
 
-retry_get:
+retry:
 	if (list_empty(&l_mg->free_list)) {
 		pr_err("pblk: no free lines\n");
-		goto out;
+		return NULL;
 	}
 
 	line = list_first_entry(&l_mg->free_list, struct pblk_line, list);
@@ -1115,16 +1197,22 @@ retry_get:
 		list_add_tail(&line->list, &l_mg->bad_list);
 
 		pr_debug("pblk: line %d is bad\n", line->id);
-		goto retry_get;
+		goto retry;
 	}
 
-	if (pblk_line_prepare(pblk, line)) {
-		pr_err("pblk: failed to prepare line %d\n", line->id);
-		list_add(&line->list, &l_mg->free_list);
-		return NULL;
+	ret = pblk_line_prepare(pblk, line);
+	if (ret) {
+		if (ret == -EAGAIN) {
+			list_add(&line->list, &l_mg->corrupt_list);
+			goto retry;
+		} else {
+			pr_err("pblk: failed to prepare line %d\n", line->id);
+			list_add(&line->list, &l_mg->free_list);
+			l_mg->nr_free_lines++;
+			return NULL;
+		}
 	}
 
-out:
 	return line;
 }
 
@@ -1134,6 +1222,7 @@ static struct pblk_line *pblk_line_retry(struct pblk *pblk,
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct pblk_line *retry_line;
 
+retry:
 	spin_lock(&l_mg->free_lock);
 	retry_line = pblk_line_get(pblk);
 	if (!retry_line) {
@@ -1150,23 +1239,25 @@ static struct pblk_line *pblk_line_retry(struct pblk *pblk,
 	l_mg->data_line = retry_line;
 	spin_unlock(&l_mg->free_lock);
 
-	if (pblk_line_erase(pblk, retry_line)) {
-		spin_lock(&l_mg->free_lock);
-		l_mg->data_line = NULL;
-		spin_unlock(&l_mg->free_lock);
-		return NULL;
-	}
-
 	pblk_rl_free_lines_dec(&pblk->rl, retry_line);
 
+	if (pblk_line_erase(pblk, retry_line))
+		goto retry;
+
 	return retry_line;
 }
 
+static void pblk_set_space_limit(struct pblk *pblk)
+{
+	struct pblk_rl *rl = &pblk->rl;
+
+	atomic_set(&rl->rb_space, 0);
+}
+
 struct pblk_line *pblk_line_get_first_data(struct pblk *pblk)
 {
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct pblk_line *line;
-	int meta_line;
 	int is_next = 0;
 
 	spin_lock(&l_mg->free_lock);
@@ -1180,30 +1271,37 @@ struct pblk_line *pblk_line_get_first_data(struct pblk *pblk)
 	line->type = PBLK_LINETYPE_DATA;
 	l_mg->data_line = line;
 
-	meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES);
-	set_bit(meta_line, &l_mg->meta_bitmap);
-	line->smeta = l_mg->sline_meta[meta_line].meta;
-	line->emeta = l_mg->eline_meta[meta_line].meta;
-	line->meta_line = meta_line;
+	pblk_line_setup_metadata(line, l_mg, &pblk->lm);
 
 	/* Allocate next line for preparation */
 	l_mg->data_next = pblk_line_get(pblk);
-	if (l_mg->data_next) {
+	if (!l_mg->data_next) {
+		/* If we cannot get a new line, we need to stop the pipeline.
+		 * Only allow as many writes in as we can store safely and then
+		 * fail gracefully
+		 */
+		pblk_set_space_limit(pblk);
+
+		l_mg->data_next = NULL;
+	} else {
 		l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
 		l_mg->data_next->type = PBLK_LINETYPE_DATA;
 		is_next = 1;
 	}
 	spin_unlock(&l_mg->free_lock);
 
+	if (pblk_line_erase(pblk, line)) {
+		line = pblk_line_retry(pblk, line);
+		if (!line)
+			return NULL;
+	}
+
 	pblk_rl_free_lines_dec(&pblk->rl, line);
 	if (is_next)
 		pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
 
-	if (pblk_line_erase(pblk, line))
-		return NULL;
-
 retry_setup:
-	if (!pblk_line_set_metadata(pblk, line, NULL)) {
+	if (!pblk_line_init_metadata(pblk, line, NULL)) {
 		line = pblk_line_retry(pblk, line);
 		if (!line)
 			return NULL;
@@ -1222,69 +1320,89 @@ retry_setup:
 	return line;
 }
 
-struct pblk_line *pblk_line_replace_data(struct pblk *pblk)
+static void pblk_stop_writes(struct pblk *pblk, struct pblk_line *line)
+{
+	lockdep_assert_held(&pblk->l_mg.free_lock);
+
+	pblk_set_space_limit(pblk);
+	pblk->state = PBLK_STATE_STOPPING;
+}
+
+void pblk_pipeline_stop(struct pblk *pblk)
+{
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	int ret;
+
+	spin_lock(&l_mg->free_lock);
+	if (pblk->state == PBLK_STATE_RECOVERING ||
+					pblk->state == PBLK_STATE_STOPPED) {
+		spin_unlock(&l_mg->free_lock);
+		return;
+	}
+	pblk->state = PBLK_STATE_RECOVERING;
+	spin_unlock(&l_mg->free_lock);
+
+	pblk_flush_writer(pblk);
+	pblk_wait_for_meta(pblk);
+
+	ret = pblk_recov_pad(pblk);
+	if (ret) {
+		pr_err("pblk: could not close data on teardown(%d)\n", ret);
+		return;
+	}
+
+	flush_workqueue(pblk->bb_wq);
+	pblk_line_close_meta_sync(pblk);
+
+	spin_lock(&l_mg->free_lock);
+	pblk->state = PBLK_STATE_STOPPED;
+	l_mg->data_line = NULL;
+	l_mg->data_next = NULL;
+	spin_unlock(&l_mg->free_lock);
+}
+
+void pblk_line_replace_data(struct pblk *pblk)
 {
-	struct pblk_line_meta *lm = &pblk->lm;
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct pblk_line *cur, *new;
 	unsigned int left_seblks;
-	int meta_line;
 	int is_next = 0;
 
 	cur = l_mg->data_line;
 	new = l_mg->data_next;
 	if (!new)
-		return NULL;
+		return;
 	l_mg->data_line = new;
 
-retry_line:
+	spin_lock(&l_mg->free_lock);
+	if (pblk->state != PBLK_STATE_RUNNING) {
+		l_mg->data_line = NULL;
+		l_mg->data_next = NULL;
+		spin_unlock(&l_mg->free_lock);
+		return;
+	}
+
+	pblk_line_setup_metadata(new, l_mg, &pblk->lm);
+	spin_unlock(&l_mg->free_lock);
+
+retry_erase:
 	left_seblks = atomic_read(&new->left_seblks);
 	if (left_seblks) {
 		/* If line is not fully erased, erase it */
 		if (atomic_read(&new->left_eblks)) {
 			if (pblk_line_erase(pblk, new))
-				return NULL;
+				return;
 		} else {
 			io_schedule();
 		}
-		goto retry_line;
+		goto retry_erase;
 	}
 
-	spin_lock(&l_mg->free_lock);
-	/* Allocate next line for preparation */
-	l_mg->data_next = pblk_line_get(pblk);
-	if (l_mg->data_next) {
-		l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
-		l_mg->data_next->type = PBLK_LINETYPE_DATA;
-		is_next = 1;
-	}
-
-retry_meta:
-	meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES);
-	if (meta_line == PBLK_DATA_LINES) {
-		spin_unlock(&l_mg->free_lock);
-		io_schedule();
-		spin_lock(&l_mg->free_lock);
-		goto retry_meta;
-	}
-
-	set_bit(meta_line, &l_mg->meta_bitmap);
-	new->smeta = l_mg->sline_meta[meta_line].meta;
-	new->emeta = l_mg->eline_meta[meta_line].meta;
-	new->meta_line = meta_line;
-
-	memset(new->smeta, 0, lm->smeta_len);
-	memset(new->emeta, 0, lm->emeta_len);
-	spin_unlock(&l_mg->free_lock);
-
-	if (is_next)
-		pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
-
 retry_setup:
-	if (!pblk_line_set_metadata(pblk, new, cur)) {
+	if (!pblk_line_init_metadata(pblk, new, cur)) {
 		new = pblk_line_retry(pblk, new);
 		if (!new)
-			return NULL;
+			return;
 
 		goto retry_setup;
 	}
@@ -1292,12 +1410,30 @@ retry_setup:
 	if (!pblk_line_init_bb(pblk, new, 1)) {
 		new = pblk_line_retry(pblk, new);
 		if (!new)
-			return NULL;
+			return;
 
 		goto retry_setup;
 	}
 
-	return new;
+	/* Allocate next line for preparation */
+	spin_lock(&l_mg->free_lock);
+	l_mg->data_next = pblk_line_get(pblk);
+	if (!l_mg->data_next) {
+		/* If we cannot get a new line, we need to stop the pipeline.
+		 * Only allow as many writes in as we can store safely and then
+		 * fail gracefully
+		 */
+		pblk_stop_writes(pblk, new);
+		l_mg->data_next = NULL;
+	} else {
+		l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
+		l_mg->data_next->type = PBLK_LINETYPE_DATA;
+		is_next = 1;
+	}
+	spin_unlock(&l_mg->free_lock);
+
+	if (is_next)
+		pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
 }
 
 void pblk_line_free(struct pblk *pblk, struct pblk_line *line)
@@ -1307,6 +1443,8 @@ void pblk_line_free(struct pblk *pblk, struct pblk_line *line)
 	if (line->invalid_bitmap)
 		mempool_free(line->invalid_bitmap, pblk->line_meta_pool);
 
+	*line->vsc = cpu_to_le32(EMPTY_ENTRY);
+
 	line->map_bitmap = NULL;
 	line->invalid_bitmap = NULL;
 	line->smeta = NULL;
@@ -1339,8 +1477,8 @@ int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr ppa)
 	struct nvm_rq *rqd;
 	int err;
 
-	rqd = mempool_alloc(pblk->r_rq_pool, GFP_KERNEL);
-	memset(rqd, 0, pblk_r_rq_size);
+	rqd = mempool_alloc(pblk->g_rq_pool, GFP_KERNEL);
+	memset(rqd, 0, pblk_g_rq_size);
 
 	pblk_setup_e_rq(pblk, rqd, ppa);
 
@@ -1368,7 +1506,8 @@ struct pblk_line *pblk_line_get_data(struct pblk *pblk)
 	return pblk->l_mg.data_line;
 }
 
-struct pblk_line *pblk_line_get_data_next(struct pblk *pblk)
+/* For now, always erase next line */
+struct pblk_line *pblk_line_get_erase(struct pblk *pblk)
 {
 	return pblk->l_mg.data_next;
 }
@@ -1378,18 +1517,58 @@ int pblk_line_is_full(struct pblk_line *line)
 	return (line->left_msecs == 0);
 }
 
+void pblk_line_close_meta_sync(struct pblk *pblk)
+{
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_line *line, *tline;
+	LIST_HEAD(list);
+
+	spin_lock(&l_mg->close_lock);
+	if (list_empty(&l_mg->emeta_list)) {
+		spin_unlock(&l_mg->close_lock);
+		return;
+	}
+
+	list_cut_position(&list, &l_mg->emeta_list, l_mg->emeta_list.prev);
+	spin_unlock(&l_mg->close_lock);
+
+	list_for_each_entry_safe(line, tline, &list, list) {
+		struct pblk_emeta *emeta = line->emeta;
+
+		while (emeta->mem < lm->emeta_len[0]) {
+			int ret;
+
+			ret = pblk_submit_meta_io(pblk, line);
+			if (ret) {
+				pr_err("pblk: sync meta line %d failed (%d)\n",
+							line->id, ret);
+				return;
+			}
+		}
+	}
+
+	pblk_wait_for_meta(pblk);
+	flush_workqueue(pblk->close_wq);
+}
+
+static void pblk_line_should_sync_meta(struct pblk *pblk)
+{
+	if (pblk_rl_is_limit(&pblk->rl))
+		pblk_line_close_meta_sync(pblk);
+}
+
 void pblk_line_close(struct pblk *pblk, struct pblk_line *line)
 {
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct list_head *move_list;
 
-	line->emeta->crc = cpu_to_le32(pblk_calc_emeta_crc(pblk, line->emeta));
-
-	if (pblk_line_submit_emeta_io(pblk, line, line->cur_sec, WRITE))
-		pr_err("pblk: line %d close I/O failed\n", line->id);
+#ifdef CONFIG_NVM_DEBUG
+	struct pblk_line_meta *lm = &pblk->lm;
 
-	WARN(!bitmap_full(line->map_bitmap, line->sec_in_line),
+	WARN(!bitmap_full(line->map_bitmap, lm->sec_per_line),
 				"pblk: corrupt closed line %d\n", line->id);
+#endif
 
 	spin_lock(&l_mg->free_lock);
 	WARN_ON(!test_and_clear_bit(line->meta_line, &l_mg->meta_bitmap));
@@ -1410,6 +1589,31 @@ void pblk_line_close(struct pblk *pblk, struct pblk_line *line)
 
 	spin_unlock(&line->lock);
 	spin_unlock(&l_mg->gc_lock);
+
+	pblk_gc_should_kick(pblk);
+}
+
+void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line)
+{
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_emeta *emeta = line->emeta;
+	struct line_emeta *emeta_buf = emeta->buf;
+
+	/* No need for exact vsc value; avoid a big line lock and take aprox. */
+	memcpy(emeta_to_vsc(pblk, emeta_buf), l_mg->vsc_list, lm->vsc_list_len);
+	memcpy(emeta_to_bb(emeta_buf), line->blk_bitmap, lm->blk_bitmap_len);
+
+	emeta_buf->nr_valid_lbas = cpu_to_le64(line->nr_valid_lbas);
+	emeta_buf->crc = cpu_to_le32(pblk_calc_emeta_crc(pblk, emeta_buf));
+
+	spin_lock(&l_mg->close_lock);
+	spin_lock(&line->lock);
+	list_add_tail(&line->list, &l_mg->emeta_list);
+	spin_unlock(&line->lock);
+	spin_unlock(&l_mg->close_lock);
+
+	pblk_line_should_sync_meta(pblk);
 }
 
 void pblk_line_close_ws(struct work_struct *work)
@@ -1449,7 +1653,8 @@ void pblk_line_mark_bb(struct work_struct *work)
 }
 
 void pblk_line_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
-		      void (*work)(struct work_struct *))
+		      void (*work)(struct work_struct *),
+		      struct workqueue_struct *wq)
 {
 	struct pblk_line_ws *line_ws;
 
@@ -1462,7 +1667,7 @@ void pblk_line_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
 	line_ws->priv = priv;
 
 	INIT_WORK(&line_ws->ws, work);
-	queue_work(pblk->kw_wq, &line_ws->ws);
+	queue_work(wq, &line_ws->ws);
 }
 
 void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
@@ -1471,7 +1676,7 @@ void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
 	struct nvm_tgt_dev *dev = pblk->dev;
 	struct nvm_geo *geo = &dev->geo;
 	struct pblk_lun *rlun;
-	int lun_id = ppa_list[0].g.ch * geo->luns_per_chnl + ppa_list[0].g.lun;
+	int pos = pblk_ppa_to_pos(geo, ppa_list[0]);
 	int ret;
 
 	/*
@@ -1488,10 +1693,10 @@ void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
 	/* If the LUN has been locked for this same request, do no attempt to
 	 * lock it again
 	 */
-	if (test_and_set_bit(lun_id, lun_bitmap))
+	if (test_and_set_bit(pos, lun_bitmap))
 		return;
 
-	rlun = &pblk->luns[lun_id];
+	rlun = &pblk->luns[pos];
 	ret = down_timeout(&rlun->wr_sem, msecs_to_jiffies(5000));
 	if (ret) {
 		switch (ret) {

drivers/lightnvm/pblk-gc.c

@@ -20,8 +20,7 @@
 
 static void pblk_gc_free_gc_rq(struct pblk_gc_rq *gc_rq)
 {
-	kfree(gc_rq->data);
-	kfree(gc_rq->lba_list);
+	vfree(gc_rq->data);
 	kfree(gc_rq);
 }
 
@@ -37,10 +36,8 @@ static int pblk_gc_write(struct pblk *pblk)
 		return 1;
 	}
 
-	list_for_each_entry_safe(gc_rq, tgc_rq, &gc->w_list, list) {
-		list_move_tail(&gc_rq->list, &w_list);
-		gc->w_entries--;
-	}
+	list_cut_position(&w_list, &gc->w_list, gc->w_list.prev);
+	gc->w_entries = 0;
 	spin_unlock(&gc->w_lock);
 
 	list_for_each_entry_safe(gc_rq, tgc_rq, &w_list, list) {
@@ -48,9 +45,8 @@ static int pblk_gc_write(struct pblk *pblk)
 				gc_rq->nr_secs, gc_rq->secs_to_gc,
 				gc_rq->line, PBLK_IOTYPE_GC);
 
-		kref_put(&gc_rq->line->ref, pblk_line_put);
-
 		list_del(&gc_rq->list);
+		kref_put(&gc_rq->line->ref, pblk_line_put);
 		pblk_gc_free_gc_rq(gc_rq);
 	}
 
@@ -66,52 +62,41 @@ static void pblk_gc_writer_kick(struct pblk_gc *gc)
  * Responsible for managing all memory related to a gc request. Also in case of
  * failure
  */
-static int pblk_gc_move_valid_secs(struct pblk *pblk, struct pblk_line *line,
-				   u64 *lba_list, unsigned int nr_secs)
+static int pblk_gc_move_valid_secs(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
 {
 	struct nvm_tgt_dev *dev = pblk->dev;
 	struct nvm_geo *geo = &dev->geo;
 	struct pblk_gc *gc = &pblk->gc;
-	struct pblk_gc_rq *gc_rq;
+	struct pblk_line *line = gc_rq->line;
 	void *data;
 	unsigned int secs_to_gc;
-	int ret = NVM_IO_OK;
+	int ret = 0;
 
-	data = kmalloc(nr_secs * geo->sec_size, GFP_KERNEL);
+	data = vmalloc(gc_rq->nr_secs * geo->sec_size);
 	if (!data) {
-		ret = NVM_IO_ERR;
-		goto free_lba_list;
+		ret = -ENOMEM;
+		goto out;
 	}
 
 	/* Read from GC victim block */
-	if (pblk_submit_read_gc(pblk, lba_list, data, nr_secs,
+	if (pblk_submit_read_gc(pblk, gc_rq->lba_list, data, gc_rq->nr_secs,
 							&secs_to_gc, line)) {
-		ret = NVM_IO_ERR;
+		ret = -EFAULT;
 		goto free_data;
 	}
 
 	if (!secs_to_gc)
-		goto free_data;
-
-	gc_rq = kmalloc(sizeof(struct pblk_gc_rq), GFP_KERNEL);
-	if (!gc_rq) {
-		ret = NVM_IO_ERR;
-		goto free_data;
-	}
+		goto free_rq;
 
-	gc_rq->line = line;
 	gc_rq->data = data;
-	gc_rq->lba_list = lba_list;
-	gc_rq->nr_secs = nr_secs;
 	gc_rq->secs_to_gc = secs_to_gc;
 
-	kref_get(&line->ref);
-
 retry:
 	spin_lock(&gc->w_lock);
-	if (gc->w_entries > 256) {
+	if (gc->w_entries >= PBLK_GC_W_QD) {
 		spin_unlock(&gc->w_lock);
-		usleep_range(256, 1024);
+		pblk_gc_writer_kick(&pblk->gc);
+		usleep_range(128, 256);
 		goto retry;
 	}
 	gc->w_entries++;
@@ -120,13 +105,14 @@ retry:
 
 	pblk_gc_writer_kick(&pblk->gc);
 
-	return NVM_IO_OK;
+	return 0;
 
+free_rq:
+	kfree(gc_rq);
 free_data:
-	kfree(data);
-free_lba_list:
-	kfree(lba_list);
-
+	vfree(data);
+out:
+	kref_put(&line->ref, pblk_line_put);
 	return ret;
 }
 
@@ -149,141 +135,207 @@ static void pblk_put_line_back(struct pblk *pblk, struct pblk_line *line)
 }
 
 static void pblk_gc_line_ws(struct work_struct *work)
+{
+	struct pblk_line_ws *line_rq_ws = container_of(work,
+						struct pblk_line_ws, ws);
+	struct pblk *pblk = line_rq_ws->pblk;
+	struct pblk_gc *gc = &pblk->gc;
+	struct pblk_line *line = line_rq_ws->line;
+	struct pblk_gc_rq *gc_rq = line_rq_ws->priv;
+
+	up(&gc->gc_sem);
+
+	if (pblk_gc_move_valid_secs(pblk, gc_rq)) {
+		pr_err("pblk: could not GC all sectors: line:%d (%d/%d)\n",
+						line->id, *line->vsc,
+						gc_rq->nr_secs);
+	}
+
+	mempool_free(line_rq_ws, pblk->line_ws_pool);
+}
+
+static void pblk_gc_line_prepare_ws(struct work_struct *work)
 {
 	struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws,
 									ws);
 	struct pblk *pblk = line_ws->pblk;
-	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct pblk_line *line = line_ws->line;
+	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct pblk_line_meta *lm = &pblk->lm;
-	__le64 *lba_list = line_ws->priv;
-	u64 *gc_list;
-	int sec_left;
-	int nr_ppas, bit;
-	int put_line = 1;
+	struct pblk_gc *gc = &pblk->gc;
+	struct line_emeta *emeta_buf;
+	struct pblk_line_ws *line_rq_ws;
+	struct pblk_gc_rq *gc_rq;
+	__le64 *lba_list;
+	int sec_left, nr_secs, bit;
+	int ret;
 
-	pr_debug("pblk: line '%d' being reclaimed for GC\n", line->id);
+	emeta_buf = pblk_malloc(lm->emeta_len[0], l_mg->emeta_alloc_type,
+								GFP_KERNEL);
+	if (!emeta_buf) {
+		pr_err("pblk: cannot use GC emeta\n");
+		return;
+	}
 
-	spin_lock(&line->lock);
-	sec_left = line->vsc;
-	if (!sec_left) {
-		/* Lines are erased before being used (l_mg->data_/log_next) */
-		spin_unlock(&line->lock);
-		goto out;
+	ret = pblk_line_read_emeta(pblk, line, emeta_buf);
+	if (ret) {
+		pr_err("pblk: line %d read emeta failed (%d)\n", line->id, ret);
+		goto fail_free_emeta;
+	}
+
+	/* If this read fails, it means that emeta is corrupted. For now, leave
+	 * the line untouched. TODO: Implement a recovery routine that scans and
+	 * moves all sectors on the line.
+	 */
+	lba_list = pblk_recov_get_lba_list(pblk, emeta_buf);
+	if (!lba_list) {
+		pr_err("pblk: could not interpret emeta (line %d)\n", line->id);
+		goto fail_free_emeta;
 	}
-	spin_unlock(&line->lock);
 
+	sec_left = pblk_line_vsc(line);
 	if (sec_left < 0) {
 		pr_err("pblk: corrupted GC line (%d)\n", line->id);
-		put_line = 0;
-		pblk_put_line_back(pblk, line);
-		goto out;
+		goto fail_free_emeta;
 	}
 
 	bit = -1;
 next_rq:
-	gc_list = kmalloc_array(pblk->max_write_pgs, sizeof(u64), GFP_KERNEL);
-	if (!gc_list) {
-		put_line = 0;
-		pblk_put_line_back(pblk, line);
-		goto out;
-	}
+	gc_rq = kmalloc(sizeof(struct pblk_gc_rq), GFP_KERNEL);
+	if (!gc_rq)
+		goto fail_free_emeta;
 
-	nr_ppas = 0;
+	nr_secs = 0;
 	do {
 		bit = find_next_zero_bit(line->invalid_bitmap, lm->sec_per_line,
 								bit + 1);
 		if (bit > line->emeta_ssec)
 			break;
 
-		gc_list[nr_ppas++] = le64_to_cpu(lba_list[bit]);
-	} while (nr_ppas < pblk->max_write_pgs);
+		gc_rq->lba_list[nr_secs++] = le64_to_cpu(lba_list[bit]);
+	} while (nr_secs < pblk->max_write_pgs);
 
-	if (unlikely(!nr_ppas)) {
-		kfree(gc_list);
+	if (unlikely(!nr_secs)) {
+		kfree(gc_rq);
 		goto out;
 	}
 
-	if (pblk_gc_move_valid_secs(pblk, line, gc_list, nr_ppas)) {
-		pr_err("pblk: could not GC all sectors: line:%d (%d/%d/%d)\n",
-						line->id, line->vsc,
-						nr_ppas, nr_ppas);
-		put_line = 0;
-		pblk_put_line_back(pblk, line);
-		goto out;
-	}
+	gc_rq->nr_secs = nr_secs;
+	gc_rq->line = line;
+
+	line_rq_ws = mempool_alloc(pblk->line_ws_pool, GFP_KERNEL);
+	if (!line_rq_ws)
+		goto fail_free_gc_rq;
 
-	sec_left -= nr_ppas;
+	line_rq_ws->pblk = pblk;
+	line_rq_ws->line = line;
+	line_rq_ws->priv = gc_rq;
+
+	down(&gc->gc_sem);
+	kref_get(&line->ref);
+
+	INIT_WORK(&line_rq_ws->ws, pblk_gc_line_ws);
+	queue_work(gc->gc_line_reader_wq, &line_rq_ws->ws);
+
+	sec_left -= nr_secs;
 	if (sec_left > 0)
 		goto next_rq;
 
 out:
-	pblk_mfree(line->emeta, l_mg->emeta_alloc_type);
+	pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
 	mempool_free(line_ws, pblk->line_ws_pool);
-	atomic_dec(&pblk->gc.inflight_gc);
-	if (put_line)
-		kref_put(&line->ref, pblk_line_put);
+
+	kref_put(&line->ref, pblk_line_put);
+	atomic_dec(&gc->inflight_gc);
+
+	return;
+
+fail_free_gc_rq:
+	kfree(gc_rq);
+fail_free_emeta:
+	pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
+	pblk_put_line_back(pblk, line);
+	kref_put(&line->ref, pblk_line_put);
+	mempool_free(line_ws, pblk->line_ws_pool);
+	atomic_dec(&gc->inflight_gc);
+
+	pr_err("pblk: Failed to GC line %d\n", line->id);
 }
 
 static int pblk_gc_line(struct pblk *pblk, struct pblk_line *line)
 {
-	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
-	struct pblk_line_meta *lm = &pblk->lm;
+	struct pblk_gc *gc = &pblk->gc;
 	struct pblk_line_ws *line_ws;
-	__le64 *lba_list;
-	int ret;
 
-	line_ws = mempool_alloc(pblk->line_ws_pool, GFP_KERNEL);
-	line->emeta = pblk_malloc(lm->emeta_len, l_mg->emeta_alloc_type,
-								GFP_KERNEL);
-	if (!line->emeta) {
-		pr_err("pblk: cannot use GC emeta\n");
-		goto fail_free_ws;
-	}
-
-	ret = pblk_line_read_emeta(pblk, line);
-	if (ret) {
-		pr_err("pblk: line %d read emeta failed (%d)\n", line->id, ret);
-		goto fail_free_emeta;
-	}
+	pr_debug("pblk: line '%d' being reclaimed for GC\n", line->id);
 
-	/* If this read fails, it means that emeta is corrupted. For now, leave
-	 * the line untouched. TODO: Implement a recovery routine that scans and
-	 * moves all sectors on the line.
-	 */
-	lba_list = pblk_recov_get_lba_list(pblk, line->emeta);
-	if (!lba_list) {
-		pr_err("pblk: could not interpret emeta (line %d)\n", line->id);
-		goto fail_free_emeta;
-	}
+	line_ws = mempool_alloc(pblk->line_ws_pool, GFP_KERNEL);
+	if (!line_ws)
+		return -ENOMEM;
 
 	line_ws->pblk = pblk;
 	line_ws->line = line;
-	line_ws->priv = lba_list;
 
-	INIT_WORK(&line_ws->ws, pblk_gc_line_ws);
-	queue_work(pblk->gc.gc_reader_wq, &line_ws->ws);
+	INIT_WORK(&line_ws->ws, pblk_gc_line_prepare_ws);
+	queue_work(gc->gc_reader_wq, &line_ws->ws);
 
 	return 0;
+}
 
-fail_free_emeta:
-	pblk_mfree(line->emeta, l_mg->emeta_alloc_type);
-fail_free_ws:
-	mempool_free(line_ws, pblk->line_ws_pool);
-	pblk_put_line_back(pblk, line);
+static int pblk_gc_read(struct pblk *pblk)
+{
+	struct pblk_gc *gc = &pblk->gc;
+	struct pblk_line *line;
+
+	spin_lock(&gc->r_lock);
+	if (list_empty(&gc->r_list)) {
+		spin_unlock(&gc->r_lock);
+		return 1;
+	}
+
+	line = list_first_entry(&gc->r_list, struct pblk_line, list);
+	list_del(&line->list);
+	spin_unlock(&gc->r_lock);
+
+	pblk_gc_kick(pblk);
 
-	return 1;
+	if (pblk_gc_line(pblk, line))
+		pr_err("pblk: failed to GC line %d\n", line->id);
+
+	return 0;
 }
 
-static void pblk_gc_lines(struct pblk *pblk, struct list_head *gc_list)
+static void pblk_gc_reader_kick(struct pblk_gc *gc)
 {
-	struct pblk_line *line, *tline;
+	wake_up_process(gc->gc_reader_ts);
+}
 
-	list_for_each_entry_safe(line, tline, gc_list, list) {
-		if (pblk_gc_line(pblk, line))
-			pr_err("pblk: failed to GC line %d\n", line->id);
-		list_del(&line->list);
+static struct pblk_line *pblk_gc_get_victim_line(struct pblk *pblk,
+						 struct list_head *group_list)
+{
+	struct pblk_line *line, *victim;
+	int line_vsc, victim_vsc;
+
+	victim = list_first_entry(group_list, struct pblk_line, list);
+	list_for_each_entry(line, group_list, list) {
+		line_vsc = le32_to_cpu(*line->vsc);
+		victim_vsc = le32_to_cpu(*victim->vsc);
+		if (line_vsc < victim_vsc)
+			victim = line;
 	}
+
+	return victim;
+}
+
+static bool pblk_gc_should_run(struct pblk_gc *gc, struct pblk_rl *rl)
+{
+	unsigned int nr_blocks_free, nr_blocks_need;
+
+	nr_blocks_need = pblk_rl_high_thrs(rl);
+	nr_blocks_free = pblk_rl_nr_free_blks(rl);
+
+	/* This is not critical, no need to take lock here */
+	return ((gc->gc_active) && (nr_blocks_need > nr_blocks_free));
 }
 
 /*
@@ -296,71 +348,83 @@ static void pblk_gc_run(struct pblk *pblk)
 {
 	struct pblk_line_mgmt *l_mg = &pblk->l_mg;
 	struct pblk_gc *gc = &pblk->gc;
-	struct pblk_line *line, *tline;
-	unsigned int nr_blocks_free, nr_blocks_need;
+	struct pblk_line *line;
 	struct list_head *group_list;
-	int run_gc, gc_group = 0;
-	int prev_gc = 0;
-	int inflight_gc = atomic_read(&gc->inflight_gc);
-	LIST_HEAD(gc_list);
+	bool run_gc;
+	int inflight_gc, gc_group = 0, prev_group = 0;
+
+	do {
+		spin_lock(&l_mg->gc_lock);
+		if (list_empty(&l_mg->gc_full_list)) {
+			spin_unlock(&l_mg->gc_lock);
+			break;
+		}
+
+		line = list_first_entry(&l_mg->gc_full_list,
+							struct pblk_line, list);
 
-	spin_lock(&l_mg->gc_lock);
-	list_for_each_entry_safe(line, tline, &l_mg->gc_full_list, list) {
 		spin_lock(&line->lock);
 		WARN_ON(line->state != PBLK_LINESTATE_CLOSED);
 		line->state = PBLK_LINESTATE_GC;
 		spin_unlock(&line->lock);
 
 		list_del(&line->list);
+		spin_unlock(&l_mg->gc_lock);
+
 		kref_put(&line->ref, pblk_line_put);
-	}
-	spin_unlock(&l_mg->gc_lock);
+	} while (1);
 
-	nr_blocks_need = pblk_rl_gc_thrs(&pblk->rl);
-	nr_blocks_free = pblk_rl_nr_free_blks(&pblk->rl);
-	run_gc = (nr_blocks_need > nr_blocks_free || gc->gc_forced);
+	run_gc = pblk_gc_should_run(&pblk->gc, &pblk->rl);
+	if (!run_gc || (atomic_read(&gc->inflight_gc) >= PBLK_GC_L_QD))
+		return;
 
 next_gc_group:
 	group_list = l_mg->gc_lists[gc_group++];
-	spin_lock(&l_mg->gc_lock);
-	while (run_gc && !list_empty(group_list)) {
-		/* No need to queue up more GC lines than we can handle */
-		if (!run_gc || inflight_gc > gc->gc_jobs_active) {
+
+	do {
+		spin_lock(&l_mg->gc_lock);
+		if (list_empty(group_list)) {
 			spin_unlock(&l_mg->gc_lock);
-			pblk_gc_lines(pblk, &gc_list);
-			return;
+			break;
 		}
 
-		line = list_first_entry(group_list, struct pblk_line, list);
-		nr_blocks_free += atomic_read(&line->blk_in_line);
+		line = pblk_gc_get_victim_line(pblk, group_list);
 
 		spin_lock(&line->lock);
 		WARN_ON(line->state != PBLK_LINESTATE_CLOSED);
 		line->state = PBLK_LINESTATE_GC;
-		list_move_tail(&line->list, &gc_list);
-		atomic_inc(&gc->inflight_gc);
-		inflight_gc++;
 		spin_unlock(&line->lock);
 
-		prev_gc = 1;
-		run_gc = (nr_blocks_need > nr_blocks_free || gc->gc_forced);
-	}
-	spin_unlock(&l_mg->gc_lock);
+		list_del(&line->list);
+		spin_unlock(&l_mg->gc_lock);
+
+		spin_lock(&gc->r_lock);
+		list_add_tail(&line->list, &gc->r_list);
+		spin_unlock(&gc->r_lock);
 
-	pblk_gc_lines(pblk, &gc_list);
+		inflight_gc = atomic_inc_return(&gc->inflight_gc);
+		pblk_gc_reader_kick(gc);
 
-	if (!prev_gc && pblk->rl.rb_state > gc_group &&
-						gc_group < PBLK_NR_GC_LISTS)
+		prev_group = 1;
+
+		/* No need to queue up more GC lines than we can handle */
+		run_gc = pblk_gc_should_run(&pblk->gc, &pblk->rl);
+		if (!run_gc || inflight_gc >= PBLK_GC_L_QD)
+			break;
+	} while (1);
+
+	if (!prev_group && pblk->rl.rb_state > gc_group &&
+						gc_group < PBLK_GC_NR_LISTS)
 		goto next_gc_group;
 }
 
-
-static void pblk_gc_kick(struct pblk *pblk)
+void pblk_gc_kick(struct pblk *pblk)
 {
 	struct pblk_gc *gc = &pblk->gc;
 
 	wake_up_process(gc->gc_ts);
 	pblk_gc_writer_kick(gc);
+	pblk_gc_reader_kick(gc);
 	mod_timer(&gc->gc_timer, jiffies + msecs_to_jiffies(GC_TIME_MSECS));
 }
 
@@ -398,42 +462,34 @@ static int pblk_gc_writer_ts(void *data)
 	return 0;
 }
 
-static void pblk_gc_start(struct pblk *pblk)
+static int pblk_gc_reader_ts(void *data)
 {
-	pblk->gc.gc_active = 1;
+	struct pblk *pblk = data;
 
-	pr_debug("pblk: gc start\n");
+	while (!kthread_should_stop()) {
+		if (!pblk_gc_read(pblk))
+			continue;
+		set_current_state(TASK_INTERRUPTIBLE);
+		io_schedule();
+	}
+
+	return 0;
 }
 
-int pblk_gc_status(struct pblk *pblk)
+static void pblk_gc_start(struct pblk *pblk)
 {
-	struct pblk_gc *gc = &pblk->gc;
-	int ret;
-
-	spin_lock(&gc->lock);
-	ret = gc->gc_active;
-	spin_unlock(&gc->lock);
-
-	return ret;
+	pblk->gc.gc_active = 1;
+	pr_debug("pblk: gc start\n");
 }
 
-static void __pblk_gc_should_start(struct pblk *pblk)
+void pblk_gc_should_start(struct pblk *pblk)
 {
 	struct pblk_gc *gc = &pblk->gc;
 
-	lockdep_assert_held(&gc->lock);
-
 	if (gc->gc_enabled && !gc->gc_active)
 		pblk_gc_start(pblk);
-}
 
-void pblk_gc_should_start(struct pblk *pblk)
-{
-	struct pblk_gc *gc = &pblk->gc;
-
-	spin_lock(&gc->lock);
-	__pblk_gc_should_start(pblk);
-	spin_unlock(&gc->lock);
+	pblk_gc_kick(pblk);
 }
 
 /*
@@ -442,10 +498,7 @@ void pblk_gc_should_start(struct pblk *pblk)
  */
 static void pblk_gc_stop(struct pblk *pblk, int flush_wq)
 {
-	spin_lock(&pblk->gc.lock);
 	pblk->gc.gc_active = 0;
-	spin_unlock(&pblk->gc.lock);
-
 	pr_debug("pblk: gc stop\n");
 }
 
@@ -468,20 +521,25 @@ void pblk_gc_sysfs_state_show(struct pblk *pblk, int *gc_enabled,
 	spin_unlock(&gc->lock);
 }
 
-void pblk_gc_sysfs_force(struct pblk *pblk, int force)
+int pblk_gc_sysfs_force(struct pblk *pblk, int force)
 {
 	struct pblk_gc *gc = &pblk->gc;
-	int rsv = 0;
+
+	if (force < 0 || force > 1)
+		return -EINVAL;
 
 	spin_lock(&gc->lock);
-	if (force) {
-		gc->gc_enabled = 1;
-		rsv = 64;
-	}
-	pblk_rl_set_gc_rsc(&pblk->rl, rsv);
 	gc->gc_forced = force;
-	__pblk_gc_should_start(pblk);
+
+	if (force)
+		gc->gc_enabled = 1;
+	else
+		gc->gc_enabled = 0;
 	spin_unlock(&gc->lock);
+
+	pblk_gc_should_start(pblk);
+
+	return 0;
 }
 
 int pblk_gc_init(struct pblk *pblk)
@@ -503,30 +561,58 @@ int pblk_gc_init(struct pblk *pblk)
 		goto fail_free_main_kthread;
 	}
 
+	gc->gc_reader_ts = kthread_create(pblk_gc_reader_ts, pblk,
+							"pblk-gc-reader-ts");
+	if (IS_ERR(gc->gc_reader_ts)) {
+		pr_err("pblk: could not allocate GC reader kthread\n");
+		ret = PTR_ERR(gc->gc_reader_ts);
+		goto fail_free_writer_kthread;
+	}
+
 	setup_timer(&gc->gc_timer, pblk_gc_timer, (unsigned long)pblk);
 	mod_timer(&gc->gc_timer, jiffies + msecs_to_jiffies(GC_TIME_MSECS));
 
 	gc->gc_active = 0;
 	gc->gc_forced = 0;
 	gc->gc_enabled = 1;
-	gc->gc_jobs_active = 8;
 	gc->w_entries = 0;
 	atomic_set(&gc->inflight_gc, 0);
 
-	gc->gc_reader_wq = alloc_workqueue("pblk-gc-reader-wq",
-			WQ_MEM_RECLAIM | WQ_UNBOUND, gc->gc_jobs_active);
+	/* Workqueue that reads valid sectors from a line and submit them to the
+	 * GC writer to be recycled.
+	 */
+	gc->gc_line_reader_wq = alloc_workqueue("pblk-gc-line-reader-wq",
+			WQ_MEM_RECLAIM | WQ_UNBOUND, PBLK_GC_MAX_READERS);
+	if (!gc->gc_line_reader_wq) {
+		pr_err("pblk: could not allocate GC line reader workqueue\n");
+		ret = -ENOMEM;
+		goto fail_free_reader_kthread;
+	}
+
+	/* Workqueue that prepare lines for GC */
+	gc->gc_reader_wq = alloc_workqueue("pblk-gc-line_wq",
+					WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
 	if (!gc->gc_reader_wq) {
 		pr_err("pblk: could not allocate GC reader workqueue\n");
 		ret = -ENOMEM;
-		goto fail_free_writer_kthread;
+		goto fail_free_reader_line_wq;
 	}
 
 	spin_lock_init(&gc->lock);
 	spin_lock_init(&gc->w_lock);
+	spin_lock_init(&gc->r_lock);
+
+	sema_init(&gc->gc_sem, 128);
+
 	INIT_LIST_HEAD(&gc->w_list);
+	INIT_LIST_HEAD(&gc->r_list);
 
 	return 0;
 
+fail_free_reader_line_wq:
+	destroy_workqueue(gc->gc_line_reader_wq);
+fail_free_reader_kthread:
+	kthread_stop(gc->gc_reader_ts);
 fail_free_writer_kthread:
 	kthread_stop(gc->gc_writer_ts);
 fail_free_main_kthread:
@@ -540,6 +626,7 @@ void pblk_gc_exit(struct pblk *pblk)
 	struct pblk_gc *gc = &pblk->gc;
 
 	flush_workqueue(gc->gc_reader_wq);
+	flush_workqueue(gc->gc_line_reader_wq);
 
 	del_timer(&gc->gc_timer);
 	pblk_gc_stop(pblk, 1);
@@ -547,9 +634,15 @@ void pblk_gc_exit(struct pblk *pblk)
 	if (gc->gc_ts)
 		kthread_stop(gc->gc_ts);
 
-	if (pblk->gc.gc_reader_wq)
-		destroy_workqueue(pblk->gc.gc_reader_wq);
+	if (gc->gc_reader_wq)
+		destroy_workqueue(gc->gc_reader_wq);
+
+	if (gc->gc_line_reader_wq)
+		destroy_workqueue(gc->gc_line_reader_wq);
 
 	if (gc->gc_writer_ts)
 		kthread_stop(gc->gc_writer_ts);
+
+	if (gc->gc_reader_ts)
+		kthread_stop(gc->gc_reader_ts);
 }