Merge tag 'for-5.11/block-2020-12-14' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:
 "Another series of killing more code than what is being added, again
  thanks to Christoph's relentless cleanups and tech debt tackling.

  This contains:

   - blk-iocost improvements (Baolin Wang)

   - part0 iostat fix (Jeffle Xu)

   - Disable iopoll for split bios (Jeffle Xu)

   - block tracepoint cleanups (Christoph Hellwig)

   - Merging of struct block_device and hd_struct (Christoph Hellwig)

   - Rework/cleanup of how block device sizes are updated (Christoph
     Hellwig)

   - Simplification of gendisk lookup and removal of block device
     aliasing (Christoph Hellwig)

   - Block device ioctl cleanups (Christoph Hellwig)

   - Removal of bdget()/blkdev_get() as exported API (Christoph Hellwig)

   - Disk change rework, avoid ->revalidate_disk() (Christoph Hellwig)

   - sbitmap improvements (Pavel Begunkov)

   - Hybrid polling fix (Pavel Begunkov)

   - bvec iteration improvements (Pavel Begunkov)

   - Zone revalidation fixes (Damien Le Moal)

   - blk-throttle limit fix (Yu Kuai)

   - Various little fixes"

* tag 'for-5.11/block-2020-12-14' of git://git.kernel.dk/linux-block: (126 commits)
  blk-mq: fix msec comment from micro to milli seconds
  blk-mq: update arg in comment of blk_mq_map_queue
  blk-mq: add helper allocating tagset->tags
  Revert "block: Fix a lockdep complaint triggered by request queue flushing"
  nvme-loop: use blk_mq_hctx_set_fq_lock_class to set loop's lock class
  blk-mq: add new API of blk_mq_hctx_set_fq_lock_class
  block: disable iopoll for split bio
  block: Improve blk_revalidate_disk_zones() checks
  sbitmap: simplify wrap check
  sbitmap: replace CAS with atomic and
  sbitmap: remove swap_lock
  sbitmap: optimise sbitmap_deferred_clear()
  blk-mq: skip hybrid polling if iopoll doesn't spin
  blk-iocost: Factor out the base vrate change into a separate function
  blk-iocost: Factor out the active iocgs' state check into a separate function
  blk-iocost: Move the usage ratio calculation to the correct place
  blk-iocost: Remove unnecessary advance declaration
  blk-iocost: Fix some typos in comments
  blktrace: fix up a kerneldoc comment
  block: remove the request_queue to argument request based tracepoints
  ...

1 files changed, 30 insertions, 16 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index d35b3c0c876a..14a44699e9b6 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -95,7 +95,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
 }
 
 struct mq_inflight {
-	struct hd_struct *part;
+	struct block_device *part;
 	unsigned int inflight[2];
 };
 
@@ -105,13 +105,15 @@ static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
 {
 	struct mq_inflight *mi = priv;
 
-	if (rq->part == mi->part && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
+	if ((!mi->part->bd_partno || rq->part == mi->part) &&
+	    blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT)
 		mi->inflight[rq_data_dir(rq)]++;
 
 	return true;
 }
 
-unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part)
+unsigned int blk_mq_in_flight(struct request_queue *q,
+		struct block_device *part)
 {
 	struct mq_inflight mi = { .part = part };
 
@@ -120,8 +122,8 @@ unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part)
 	return mi.inflight[0] + mi.inflight[1];
 }
 
-void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
-			 unsigned int inflight[2])
+void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part,
+		unsigned int inflight[2])
 {
 	struct mq_inflight mi = { .part = part };
 
@@ -729,7 +731,7 @@ void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
 
-	trace_block_rq_issue(q, rq);
+	trace_block_rq_issue(rq);
 
 	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
 		rq->io_start_time_ns = ktime_get_ns();
@@ -756,7 +758,7 @@ static void __blk_mq_requeue_request(struct request *rq)
 
 	blk_mq_put_driver_tag(rq);
 
-	trace_block_rq_requeue(q, rq);
+	trace_block_rq_requeue(rq);
 	rq_qos_requeue(q, rq);
 
 	if (blk_mq_request_started(rq)) {
@@ -1590,7 +1592,7 @@ select_cpu:
  * __blk_mq_delay_run_hw_queue - Run (or schedule to run) a hardware queue.
  * @hctx: Pointer to the hardware queue to run.
  * @async: If we want to run the queue asynchronously.
- * @msecs: Microseconds of delay to wait before running the queue.
+ * @msecs: Milliseconds of delay to wait before running the queue.
  *
  * If !@async, try to run the queue now. Else, run the queue asynchronously and
  * with a delay of @msecs.
@@ -1619,7 +1621,7 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
 /**
  * blk_mq_delay_run_hw_queue - Run a hardware queue asynchronously.
  * @hctx: Pointer to the hardware queue to run.
- * @msecs: Microseconds of delay to wait before running the queue.
+ * @msecs: Milliseconds of delay to wait before running the queue.
  *
  * Run a hardware queue asynchronously with a delay of @msecs.
  */
@@ -1683,7 +1685,7 @@ EXPORT_SYMBOL(blk_mq_run_hw_queues);
 /**
  * blk_mq_delay_run_hw_queues - Run all hardware queues asynchronously.
  * @q: Pointer to the request queue to run.
- * @msecs: Microseconds of delay to wait before running the queues.
+ * @msecs: Milliseconds of delay to wait before running the queues.
  */
 void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs)
 {
@@ -1817,7 +1819,7 @@ static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx,
 
 	lockdep_assert_held(&ctx->lock);
 
-	trace_block_rq_insert(hctx->queue, rq);
+	trace_block_rq_insert(rq);
 
 	if (at_head)
 		list_add(&rq->queuelist, &ctx->rq_lists[type]);
@@ -1874,7 +1876,7 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 	 */
 	list_for_each_entry(rq, list, queuelist) {
 		BUG_ON(rq->mq_ctx != ctx);
-		trace_block_rq_insert(hctx->queue, rq);
+		trace_block_rq_insert(rq);
 	}
 
 	spin_lock(&ctx->lock);
@@ -2155,6 +2157,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 	unsigned int nr_segs;
 	blk_qc_t cookie;
 	blk_status_t ret;
+	bool hipri;
 
 	blk_queue_bounce(q, &bio);
 	__blk_queue_split(&bio, &nr_segs);
@@ -2171,6 +2174,8 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 
 	rq_qos_throttle(q, bio);
 
+	hipri = bio->bi_opf & REQ_HIPRI;
+
 	data.cmd_flags = bio->bi_opf;
 	rq = __blk_mq_alloc_request(&data);
 	if (unlikely(!rq)) {
@@ -2180,7 +2185,7 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 		goto queue_exit;
 	}
 
-	trace_block_getrq(q, bio, bio->bi_opf);
+	trace_block_getrq(bio);
 
 	rq_qos_track(q, rq, bio);
 
@@ -2263,6 +2268,8 @@ blk_qc_t blk_mq_submit_bio(struct bio *bio)
 		blk_mq_sched_insert_request(rq, false, true, true);
 	}
 
+	if (!hipri)
+		return BLK_QC_T_NONE;
 	return cookie;
 queue_exit:
 	blk_queue_exit(q);
@@ -3373,6 +3380,12 @@ static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set,
 	return 0;
 }
 
+static int blk_mq_alloc_tag_set_tags(struct blk_mq_tag_set *set,
+				int new_nr_hw_queues)
+{
+	return blk_mq_realloc_tag_set_tags(set, 0, new_nr_hw_queues);
+}
+
 /*
  * Alloc a tag set to be associated with one or more request queues.
  * May fail with EINVAL for various error conditions. May adjust the
@@ -3426,7 +3439,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids)
 		set->nr_hw_queues = nr_cpu_ids;
 
-	if (blk_mq_realloc_tag_set_tags(set, 0, set->nr_hw_queues) < 0)
+	if (blk_mq_alloc_tag_set_tags(set, set->nr_hw_queues) < 0)
 		return -ENOMEM;
 
 	ret = -ENOMEM;
@@ -3861,9 +3874,10 @@ int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin)
 	 * the state. Like for the other success return cases, the
 	 * caller is responsible for checking if the IO completed. If
 	 * the IO isn't complete, we'll get called again and will go
-	 * straight to the busy poll loop.
+	 * straight to the busy poll loop. If specified not to spin,
+	 * we also should not sleep.
 	 */
-	if (blk_mq_poll_hybrid(q, hctx, cookie))
+	if (spin && blk_mq_poll_hybrid(q, hctx, cookie))
 		return 1;
 
 	hctx->poll_considered++;