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;
 		}
 	}
 
@@ -4457,21 +4478,15 @@ 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);
 		}
 	}
 
 	if (unlikely(bfq_bfqq_just_created(bfqq)))
 		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

@@ -224,15 +224,15 @@ 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);
 	struct blk_integrity_iter iter;
 	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 @@ void bio_endio(struct bio *bio)
 	}
 
 	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 @@ static struct bio_set *__bioset_create(unsigned int pool_size,
 	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");