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

1 files changed, 21 insertions, 22 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4e4cd62..e11f5f8 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 *),