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

Pull block layer fixes from Jens Axboe:
 "Final small batch of fixes to be included before -rc1.  Some general
  cleanups in here as well, but some of the blk-mq fixes we need for the
  NVMe conversion and/or scsi-mq.  The pull request contains:

   - Support for not merging across a specified "chunk size", if set by
     the driver.  Some NVMe devices perform poorly for IO that crosses
     such a chunk, so we need to support it generically as part of
     request merging avoid having to do complicated split logic.  From
     me.

   - Bump max tag depth to 10Ki tags.  Some scsi devices have a huge
     shared tag space.  Before we failed with EINVAL if a too large tag
     depth was specified, now we truncate it and pass back the actual
     value.  From me.

   - Various blk-mq rq init fixes from me and others.

   - A fix for enter on a dying queue for blk-mq from Keith.  This is
     needed to prevent oopsing on hot device removal.

   - Fixup for blk-mq timer addition from Ming Lei.

   - Small round of performance fixes for mtip32xx from Sam Bradshaw.

   - Minor stack leak fix from Rickard Strandqvist.

   - Two __init annotations from Fabian Frederick"

* 'for-linus' of git://git.kernel.dk/linux-block:
  block: add __init to blkcg_policy_register
  block: add __init to elv_register
  block: ensure that bio_add_page() always accepts a page for an empty bio
  blk-mq: add timer in blk_mq_start_request
  blk-mq: always initialize request->start_time
  block: blk-exec.c: Cleaning up local variable address returnd
  mtip32xx: minor performance enhancements
  blk-mq: ->timeout should be cleared in blk_mq_rq_ctx_init()
  blk-mq: don't allow queue entering for a dying queue
  blk-mq: bump max tag depth to 10K tags
  block: add blk_rq_set_block_pc()
  block: add notion of a chunk size for request merging

10 files changed, 81 insertions, 31 deletions

diff --git a/block/bio.c b/block/bio.c
index 1ba33657160..8c2e55e39a1 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -849,7 +849,13 @@ int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
 		 unsigned int offset)
 {
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	return __bio_add_page(q, bio, page, len, offset, queue_max_sectors(q));
+	unsigned int max_sectors;
+
+	max_sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector);
+	if ((max_sectors < (len >> 9)) && !bio->bi_iter.bi_size)
+		max_sectors = len >> 9;
+
+	return __bio_add_page(q, bio, page, len, offset, max_sectors);
 }
 EXPORT_SYMBOL(bio_add_page);
 
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 9f5bce33e6f..069bc202ffe 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1093,7 +1093,7 @@ EXPORT_SYMBOL_GPL(blkcg_deactivate_policy);
  * Register @pol with blkcg core.  Might sleep and @pol may be modified on
  * successful registration.  Returns 0 on success and -errno on failure.
  */
-int blkcg_policy_register(struct blkcg_policy *pol)
+int __init blkcg_policy_register(struct blkcg_policy *pol)
 {
 	int i, ret;
 
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index d692b29c083..cbb7f943f78 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -145,7 +145,7 @@ void blkcg_drain_queue(struct request_queue *q);
 void blkcg_exit_queue(struct request_queue *q);
 
 /* Blkio controller policy registration */
-int blkcg_policy_register(struct blkcg_policy *pol);
+int __init blkcg_policy_register(struct blkcg_policy *pol);
 void blkcg_policy_unregister(struct blkcg_policy *pol);
 int blkcg_activate_policy(struct request_queue *q,
 			  const struct blkcg_policy *pol);
@@ -580,7 +580,7 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { ret
 static inline int blkcg_init_queue(struct request_queue *q) { return 0; }
 static inline void blkcg_drain_queue(struct request_queue *q) { }
 static inline void blkcg_exit_queue(struct request_queue *q) { }
-static inline int blkcg_policy_register(struct blkcg_policy *pol) { return 0; }
+static inline int __init blkcg_policy_register(struct blkcg_policy *pol) { return 0; }
 static inline void blkcg_policy_unregister(struct blkcg_policy *pol) { }
 static inline int blkcg_activate_policy(struct request_queue *q,
 					const struct blkcg_policy *pol) { return 0; }
diff --git a/block/blk-core.c b/block/blk-core.c
index 40d654861c3..9aca8c71e70 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1218,6 +1218,8 @@ struct request *blk_make_request(struct request_queue *q, struct bio *bio,
 	if (unlikely(!rq))
 		return ERR_PTR(-ENOMEM);
 
+	blk_rq_set_block_pc(rq);
+
 	for_each_bio(bio) {
 		struct bio *bounce_bio = bio;
 		int ret;
@@ -1235,6 +1237,22 @@ struct request *blk_make_request(struct request_queue *q, struct bio *bio,
 EXPORT_SYMBOL(blk_make_request);
 
 /**
+ * blk_rq_set_block_pc - initialize a requeest to type BLOCK_PC
+ * @rq:		request to be initialized
+ *
+ */
+void blk_rq_set_block_pc(struct request *rq)
+{
+	rq->cmd_type = REQ_TYPE_BLOCK_PC;
+	rq->__data_len = 0;
+	rq->__sector = (sector_t) -1;
+	rq->bio = rq->biotail = NULL;
+	memset(rq->__cmd, 0, sizeof(rq->__cmd));
+	rq->cmd = rq->__cmd;
+}
+EXPORT_SYMBOL(blk_rq_set_block_pc);
+
+/**
  * blk_requeue_request - put a request back on queue
  * @q:		request queue where request should be inserted
  * @rq:		request to be inserted
diff --git a/block/blk-exec.c b/block/blk-exec.c
index dbf4502b1d6..f4d27b12c90 100644
--- a/block/blk-exec.c
+++ b/block/blk-exec.c
@@ -132,6 +132,11 @@ int blk_execute_rq(struct request_queue *q, struct gendisk *bd_disk,
 	if (rq->errors)
 		err = -EIO;
 
+	if (rq->sense == sense)	{
+		rq->sense = NULL;
+		rq->sense_len = 0;
+	}
+
 	return err;
 }
 EXPORT_SYMBOL(blk_execute_rq);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4e4cd620805..e11f5f8e031 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -82,8 +82,10 @@ static int blk_mq_queue_enter(struct request_queue *q)
 
 	__percpu_counter_add(&q->mq_usage_counter, 1, 1000000);
 	smp_wmb();
-	/* we have problems to freeze the queue if it's initializing */
-	if (!blk_queue_bypass(q) || !blk_queue_init_done(q))
+
+	/* we have problems freezing the queue if it's initializing */
+	if (!blk_queue_dying(q) &&
+	    (!blk_queue_bypass(q) || !blk_queue_init_done(q)))
 		return 0;
 
 	__percpu_counter_add(&q->mq_usage_counter, -1, 1000000);
@@ -183,6 +185,7 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	RB_CLEAR_NODE(&rq->rb_node);
 	rq->rq_disk = NULL;
 	rq->part = NULL;
+	rq->start_time = jiffies;
 #ifdef CONFIG_BLK_CGROUP
 	rq->rl = NULL;
 	set_start_time_ns(rq);
@@ -202,6 +205,8 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	rq->sense = NULL;
 
 	INIT_LIST_HEAD(&rq->timeout_list);
+	rq->timeout = 0;
+
 	rq->end_io = NULL;
 	rq->end_io_data = NULL;
 	rq->next_rq = NULL;
@@ -406,16 +411,7 @@ static void blk_mq_start_request(struct request *rq, bool last)
 	if (unlikely(blk_bidi_rq(rq)))
 		rq->next_rq->resid_len = blk_rq_bytes(rq->next_rq);
 
-	/*
-	 * Just mark start time and set the started bit. Due to memory
-	 * ordering, we know we'll see the correct deadline as long as
-	 * REQ_ATOMIC_STARTED is seen. Use the default queue timeout,
-	 * unless one has been set in the request.
-	 */
-	if (!rq->timeout)
-		rq->deadline = jiffies + q->rq_timeout;
-	else
-		rq->deadline = jiffies + rq->timeout;
+	blk_add_timer(rq);
 
 	/*
 	 * Mark us as started and clear complete. Complete might have been
@@ -967,11 +963,6 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx,
 		list_add_tail(&rq->queuelist, &ctx->rq_list);
 
 	blk_mq_hctx_mark_pending(hctx, ctx);
-
-	/*
-	 * We do this early, to ensure we are on the right CPU.
-	 */
-	blk_add_timer(rq);
 }
 
 void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue,
@@ -1100,10 +1091,8 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio)
 {
 	init_request_from_bio(rq, bio);
 
-	if (blk_do_io_stat(rq)) {
-		rq->start_time = jiffies;
+	if (blk_do_io_stat(rq))
 		blk_account_io_start(rq, 1);
-	}
 }
 
 static inline bool blk_mq_merge_queue_io(struct blk_mq_hw_ctx *hctx,
@@ -1216,7 +1205,6 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio)
 
 		blk_mq_bio_to_request(rq, bio);
 		blk_mq_start_request(rq, true);
-		blk_add_timer(rq);
 
 		/*
 		 * For OK queue, we are done. For error, kill it. Any other
@@ -1967,13 +1955,19 @@ static int blk_mq_queue_reinit_notify(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+/*
+ * Alloc a tag set to be associated with one or more request queues.
+ * May fail with EINVAL for various error conditions. May adjust the
+ * requested depth down, if if it too large. In that case, the set
+ * value will be stored in set->queue_depth.
+ */
 int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 {
 	int i;
 
 	if (!set->nr_hw_queues)
 		return -EINVAL;
-	if (!set->queue_depth || set->queue_depth > BLK_MQ_MAX_DEPTH)
+	if (!set->queue_depth)
 		return -EINVAL;
 	if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN)
 		return -EINVAL;
@@ -1981,6 +1975,11 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (!set->nr_hw_queues || !set->ops->queue_rq || !set->ops->map_queue)
 		return -EINVAL;
 
+	if (set->queue_depth > BLK_MQ_MAX_DEPTH) {
+		pr_info("blk-mq: reduced tag depth to %u\n",
+			BLK_MQ_MAX_DEPTH);
+		set->queue_depth = BLK_MQ_MAX_DEPTH;
+	}
 
 	set->tags = kmalloc_node(set->nr_hw_queues *
 				 sizeof(struct blk_mq_tags *),
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 5d21239bc85..f1a1795a568 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -113,6 +113,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
 	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
+	lim->chunk_sectors = 0;
 	lim->max_write_same_sectors = 0;
 	lim->max_discard_sectors = 0;
 	lim->discard_granularity = 0;
@@ -277,6 +278,26 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto
 EXPORT_SYMBOL(blk_queue_max_hw_sectors);
 
 /**
+ * blk_queue_chunk_sectors - set size of the chunk for this queue
+ * @q:  the request queue for the device
+ * @chunk_sectors:  chunk sectors in the usual 512b unit
+ *
+ * Description:
+ *    If a driver doesn't want IOs to cross a given chunk size, it can set
+ *    this limit and prevent merging across chunks. Note that the chunk size
+ *    must currently be a power-of-2 in sectors. Also note that the block
+ *    layer must accept a page worth of data at any offset. So if the
+ *    crossing of chunks is a hard limitation in the driver, it must still be
+ *    prepared to split single page bios.
+ **/
+void blk_queue_chunk_sectors(struct request_queue *q, unsigned int chunk_sectors)
+{
+	BUG_ON(!is_power_of_2(chunk_sectors));
+	q->limits.chunk_sectors = chunk_sectors;
+}
+EXPORT_SYMBOL(blk_queue_chunk_sectors);
+
+/**
  * blk_queue_max_discard_sectors - set max sectors for a single discard
  * @q:  the request queue for the device
  * @max_discard_sectors: maximum number of sectors to discard
diff --git a/block/bsg.c b/block/bsg.c
index e5214c14809..ff46addde5d 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -196,7 +196,6 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 	 * fill in request structure
 	 */
 	rq->cmd_len = hdr->request_len;
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 
 	rq->timeout = msecs_to_jiffies(hdr->timeout);
 	if (!rq->timeout)
@@ -273,6 +272,8 @@ bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm,
 	rq = blk_get_request(q, rw, GFP_KERNEL);
 	if (!rq)
 		return ERR_PTR(-ENOMEM);
+	blk_rq_set_block_pc(rq);
+
 	ret = blk_fill_sgv4_hdr_rq(q, rq, hdr, bd, has_write_perm);
 	if (ret)
 		goto out;
diff --git a/block/elevator.c b/block/elevator.c
index 1e01b66a0b9..f35edddfe9b 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -845,7 +845,7 @@ void elv_unregister_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL(elv_unregister_queue);
 
-int elv_register(struct elevator_type *e)
+int __init elv_register(struct elevator_type *e)
 {
 	char *def = "";
 
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 9c28a5b3804..14695c6221c 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -229,7 +229,6 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 	 * fill in request structure
 	 */
 	rq->cmd_len = hdr->cmd_len;
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 
 	rq->timeout = msecs_to_jiffies(hdr->timeout);
 	if (!rq->timeout)
@@ -311,6 +310,7 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	rq = blk_get_request(q, writing ? WRITE : READ, GFP_KERNEL);
 	if (!rq)
 		return -ENOMEM;
+	blk_rq_set_block_pc(rq);
 
 	if (blk_fill_sghdr_rq(q, rq, hdr, mode)) {
 		blk_put_request(rq);
@@ -491,7 +491,7 @@ int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
 	memset(sense, 0, sizeof(sense));
 	rq->sense = sense;
 	rq->sense_len = 0;
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
+	blk_rq_set_block_pc(rq);
 
 	blk_execute_rq(q, disk, rq, 0);
 
@@ -524,7 +524,7 @@ static int __blk_send_generic(struct request_queue *q, struct gendisk *bd_disk,
 	int err;
 
 	rq = blk_get_request(q, WRITE, __GFP_WAIT);
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
+	blk_rq_set_block_pc(rq);
 	rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
 	rq->cmd[0] = cmd;
 	rq->cmd[4] = data;