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
  ...

kernel/trace/blktrace.c

@@ -458,14 +458,9 @@ static const struct rchan_callbacks blk_relay_callbacks = {
 static void blk_trace_setup_lba(struct blk_trace *bt,
 				struct block_device *bdev)
 {
-	struct hd_struct *part = NULL;
-
-	if (bdev)
-		part = bdev->bd_part;
-
-	if (part) {
-		bt->start_lba = part->start_sect;
-		bt->end_lba = part->start_sect + part->nr_sects;
+	if (bdev) {
+		bt->start_lba = bdev->bd_start_sect;
+		bt->end_lba = bdev->bd_start_sect + bdev_nr_sectors(bdev);
 	} else {
 		bt->start_lba = 0;
 		bt->end_lba = -1ULL;
@@ -800,12 +795,12 @@ static u64 blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio)
 #endif
 
 static u64
-blk_trace_request_get_cgid(struct request_queue *q, struct request *rq)
+blk_trace_request_get_cgid(struct request *rq)
 {
 	if (!rq->bio)
 		return 0;
 	/* Use the first bio */
-	return blk_trace_bio_get_cgid(q, rq->bio);
+	return blk_trace_bio_get_cgid(rq->q, rq->bio);
 }
 
 /*
@@ -846,40 +841,35 @@ static void blk_add_trace_rq(struct request *rq, int error,
 	rcu_read_unlock();
 }
 
-static void blk_add_trace_rq_insert(void *ignore,
-				    struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_insert(void *ignore, struct request *rq)
 {
 	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_INSERT,
-			 blk_trace_request_get_cgid(q, rq));
+			 blk_trace_request_get_cgid(rq));
 }
 
-static void blk_add_trace_rq_issue(void *ignore,
-				   struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_issue(void *ignore, struct request *rq)
 {
 	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_ISSUE,
-			 blk_trace_request_get_cgid(q, rq));
+			 blk_trace_request_get_cgid(rq));
 }
 
-static void blk_add_trace_rq_merge(void *ignore,
-				   struct request_queue *q, struct request *rq)
+static void blk_add_trace_rq_merge(void *ignore, struct request *rq)
 {
 	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_BACKMERGE,
-			 blk_trace_request_get_cgid(q, rq));
+			 blk_trace_request_get_cgid(rq));
 }
 
-static void blk_add_trace_rq_requeue(void *ignore,
-				     struct request_queue *q,
-				     struct request *rq)
+static void blk_add_trace_rq_requeue(void *ignore, struct request *rq)
 {
 	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_REQUEUE,
-			 blk_trace_request_get_cgid(q, rq));
+			 blk_trace_request_get_cgid(rq));
 }
 
 static void blk_add_trace_rq_complete(void *ignore, struct request *rq,
 			int error, unsigned int nr_bytes)
 {
 	blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE,
-			 blk_trace_request_get_cgid(rq->q, rq));
+			 blk_trace_request_get_cgid(rq));
 }
 
 /**
@@ -911,10 +901,9 @@ static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
 	rcu_read_unlock();
 }
 
-static void blk_add_trace_bio_bounce(void *ignore,
-				     struct request_queue *q, struct bio *bio)
+static void blk_add_trace_bio_bounce(void *ignore, struct bio *bio)
 {
-	blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0);
+	blk_add_trace_bio(bio->bi_disk->queue, bio, BLK_TA_BOUNCE, 0);
 }
 
 static void blk_add_trace_bio_complete(void *ignore,
@@ -924,63 +913,24 @@ static void blk_add_trace_bio_complete(void *ignore,
 			  blk_status_to_errno(bio->bi_status));
 }
 
-static void blk_add_trace_bio_backmerge(void *ignore,
-					struct request_queue *q,
-					struct request *rq,
-					struct bio *bio)
+static void blk_add_trace_bio_backmerge(void *ignore, struct bio *bio)
 {
-	blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0);
+	blk_add_trace_bio(bio->bi_disk->queue, bio, BLK_TA_BACKMERGE, 0);
 }
 
-static void blk_add_trace_bio_frontmerge(void *ignore,
-					 struct request_queue *q,
-					 struct request *rq,
-					 struct bio *bio)
+static void blk_add_trace_bio_frontmerge(void *ignore, struct bio *bio)
 {
-	blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0);
+	blk_add_trace_bio(bio->bi_disk->queue, bio, BLK_TA_FRONTMERGE, 0);
 }
 
-static void blk_add_trace_bio_queue(void *ignore,
-				    struct request_queue *q, struct bio *bio)
+static void blk_add_trace_bio_queue(void *ignore, struct bio *bio)
 {
-	blk_add_trace_bio(q, bio, BLK_TA_QUEUE, 0);
+	blk_add_trace_bio(bio->bi_disk->queue, bio, BLK_TA_QUEUE, 0);
 }
 
-static void blk_add_trace_getrq(void *ignore,
-				struct request_queue *q,
-				struct bio *bio, int rw)
+static void blk_add_trace_getrq(void *ignore, struct bio *bio)
 {
-	if (bio)
-		blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0);
-	else {
-		struct blk_trace *bt;
-
-		rcu_read_lock();
-		bt = rcu_dereference(q->blk_trace);
-		if (bt)
-			__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_GETRQ, 0, 0,
-					NULL, 0);
-		rcu_read_unlock();
-	}
-}
-
-
-static void blk_add_trace_sleeprq(void *ignore,
-				  struct request_queue *q,
-				  struct bio *bio, int rw)
-{
-	if (bio)
-		blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0);
-	else {
-		struct blk_trace *bt;
-
-		rcu_read_lock();
-		bt = rcu_dereference(q->blk_trace);
-		if (bt)
-			__blk_add_trace(bt, 0, 0, rw, 0, BLK_TA_SLEEPRQ,
-					0, 0, NULL, 0);
-		rcu_read_unlock();
-	}
+	blk_add_trace_bio(bio->bi_disk->queue, bio, BLK_TA_GETRQ, 0);
 }
 
 static void blk_add_trace_plug(void *ignore, struct request_queue *q)
@@ -1015,10 +965,9 @@ static void blk_add_trace_unplug(void *ignore, struct request_queue *q,
 	rcu_read_unlock();
 }
 
-static void blk_add_trace_split(void *ignore,
-				struct request_queue *q, struct bio *bio,
-				unsigned int pdu)
+static void blk_add_trace_split(void *ignore, struct bio *bio, unsigned int pdu)
 {
+	struct request_queue *q = bio->bi_disk->queue;
 	struct blk_trace *bt;
 
 	rcu_read_lock();
@@ -1039,20 +988,16 @@ static void blk_add_trace_split(void *ignore,
 /**
  * blk_add_trace_bio_remap - Add a trace for a bio-remap operation
  * @ignore:	trace callback data parameter (not used)
- * @q:		queue the io is for
  * @bio:	the source bio
- * @dev:	target device
+ * @dev:	source device
  * @from:	source sector
  *
- * Description:
- *     Device mapper or raid target sometimes need to split a bio because
- *     it spans a stripe (or similar). Add a trace for that action.
- *
+ * Called after a bio is remapped to a different device and/or sector.
  **/
-static void blk_add_trace_bio_remap(void *ignore,
-				    struct request_queue *q, struct bio *bio,
-				    dev_t dev, sector_t from)
+static void blk_add_trace_bio_remap(void *ignore, struct bio *bio, dev_t dev,
+				    sector_t from)
 {
+	struct request_queue *q = bio->bi_disk->queue;
 	struct blk_trace *bt;
 	struct blk_io_trace_remap r;
 
@@ -1077,7 +1022,6 @@ static void blk_add_trace_bio_remap(void *ignore,
 /**
  * blk_add_trace_rq_remap - Add a trace for a request-remap operation
  * @ignore:	trace callback data parameter (not used)
- * @q:		queue the io is for
  * @rq:		the source request
  * @dev:	target device
  * @from:	source sector
@@ -1087,16 +1031,14 @@ static void blk_add_trace_bio_remap(void *ignore,
  *     Add a trace for that action.
  *
  **/
-static void blk_add_trace_rq_remap(void *ignore,
-				   struct request_queue *q,
-				   struct request *rq, dev_t dev,
+static void blk_add_trace_rq_remap(void *ignore, struct request *rq, dev_t dev,
 				   sector_t from)
 {
 	struct blk_trace *bt;
 	struct blk_io_trace_remap r;
 
 	rcu_read_lock();
-	bt = rcu_dereference(q->blk_trace);
+	bt = rcu_dereference(rq->q->blk_trace);
 	if (likely(!bt)) {
 		rcu_read_unlock();
 		return;
@@ -1108,13 +1050,12 @@ static void blk_add_trace_rq_remap(void *ignore,
 
 	__blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq),
 			rq_data_dir(rq), 0, BLK_TA_REMAP, 0,
-			sizeof(r), &r, blk_trace_request_get_cgid(q, rq));
+			sizeof(r), &r, blk_trace_request_get_cgid(rq));
 	rcu_read_unlock();
 }
 
 /**
  * blk_add_driver_data - Add binary message with driver-specific data
- * @q:		queue the io is for
  * @rq:		io request
  * @data:	driver-specific data
  * @len:	length of driver-specific data
@@ -1123,14 +1064,12 @@ static void blk_add_trace_rq_remap(void *ignore,
  *     Some drivers might want to write driver-specific data per request.
  *
  **/
-void blk_add_driver_data(struct request_queue *q,
-			 struct request *rq,
-			 void *data, size_t len)
+void blk_add_driver_data(struct request *rq, void *data, size_t len)
 {
 	struct blk_trace *bt;
 
 	rcu_read_lock();
-	bt = rcu_dereference(q->blk_trace);
+	bt = rcu_dereference(rq->q->blk_trace);
 	if (likely(!bt)) {
 		rcu_read_unlock();
 		return;
@@ -1138,7 +1077,7 @@ void blk_add_driver_data(struct request_queue *q,
 
 	__blk_add_trace(bt, blk_rq_trace_sector(rq), blk_rq_bytes(rq), 0, 0,
 				BLK_TA_DRV_DATA, 0, len, data,
-				blk_trace_request_get_cgid(q, rq));
+				blk_trace_request_get_cgid(rq));
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(blk_add_driver_data);
@@ -1169,8 +1108,6 @@ static void blk_register_tracepoints(void)
 	WARN_ON(ret);
 	ret = register_trace_block_getrq(blk_add_trace_getrq, NULL);
 	WARN_ON(ret);
-	ret = register_trace_block_sleeprq(blk_add_trace_sleeprq, NULL);
-	WARN_ON(ret);
 	ret = register_trace_block_plug(blk_add_trace_plug, NULL);
 	WARN_ON(ret);
 	ret = register_trace_block_unplug(blk_add_trace_unplug, NULL);
@@ -1190,7 +1127,6 @@ static void blk_unregister_tracepoints(void)
 	unregister_trace_block_split(blk_add_trace_split, NULL);
 	unregister_trace_block_unplug(blk_add_trace_unplug, NULL);
 	unregister_trace_block_plug(blk_add_trace_plug, NULL);
-	unregister_trace_block_sleeprq(blk_add_trace_sleeprq, NULL);
 	unregister_trace_block_getrq(blk_add_trace_getrq, NULL);
 	unregister_trace_block_bio_queue(blk_add_trace_bio_queue, NULL);
 	unregister_trace_block_bio_frontmerge(blk_add_trace_bio_frontmerge, NULL);
@@ -1815,30 +1751,15 @@ static ssize_t blk_trace_mask2str(char *buf, int mask)
 	return p - buf;
 }
 
-static struct request_queue *blk_trace_get_queue(struct block_device *bdev)
-{
-	if (bdev->bd_disk == NULL)
-		return NULL;
-
-	return bdev_get_queue(bdev);
-}
-
 static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 					 struct device_attribute *attr,
 					 char *buf)
 {
-	struct block_device *bdev = bdget_part(dev_to_part(dev));
-	struct request_queue *q;
+	struct block_device *bdev = dev_to_bdev(dev);
+	struct request_queue *q = bdev_get_queue(bdev);
 	struct blk_trace *bt;
 	ssize_t ret = -ENXIO;
 
-	if (bdev == NULL)
-		goto out;
-
-	q = blk_trace_get_queue(bdev);
-	if (q == NULL)
-		goto out_bdput;
-
 	mutex_lock(&q->debugfs_mutex);
 
 	bt = rcu_dereference_protected(q->blk_trace,
@@ -1861,9 +1782,6 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 
 out_unlock_bdev:
 	mutex_unlock(&q->debugfs_mutex);
-out_bdput:
-	bdput(bdev);
-out:
 	return ret;
 }
 
@@ -1871,8 +1789,8 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 					  struct device_attribute *attr,
 					  const char *buf, size_t count)
 {
-	struct block_device *bdev;
-	struct request_queue *q;
+	struct block_device *bdev = dev_to_bdev(dev);
+	struct request_queue *q = bdev_get_queue(bdev);
 	struct blk_trace *bt;
 	u64 value;
 	ssize_t ret = -EINVAL;
@@ -1888,17 +1806,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 				goto out;
 			value = ret;
 		}
-	} else if (kstrtoull(buf, 0, &value))
-		goto out;
-
-	ret = -ENXIO;
-	bdev = bdget_part(dev_to_part(dev));
-	if (bdev == NULL)
-		goto out;
-
-	q = blk_trace_get_queue(bdev);
-	if (q == NULL)
-		goto out_bdput;
+	} else {
+		if (kstrtoull(buf, 0, &value))
+			goto out;
+	}
 
 	mutex_lock(&q->debugfs_mutex);
 
@@ -1936,8 +1847,6 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 
 out_unlock_bdev:
 	mutex_unlock(&q->debugfs_mutex);
-out_bdput:
-	bdput(bdev);
 out:
 	return ret ? ret : count;
 }