Merge tag 'for-5.9/block-20200802' of git://git.kernel.dk/linux-block

Pull core block updates from Jens Axboe:
 "Good amount of cleanups and tech debt removals in here, and as a
  result, the diffstat shows a nice net reduction in code.

   - Softirq completion cleanups (Christoph)

   - Stop using ->queuedata (Christoph)

   - Cleanup bd claiming (Christoph)

   - Use check_events, moving away from the legacy media change
     (Christoph)

   - Use inode i_blkbits consistently (Christoph)

   - Remove old unused writeback congestion bits (Christoph)

   - Cleanup/unify submission path (Christoph)

   - Use bio_uninit consistently, instead of bio_disassociate_blkg
     (Christoph)

   - sbitmap cleared bits handling (John)

   - Request merging blktrace event addition (Jan)

   - sysfs add/remove race fixes (Luis)

   - blk-mq tag fixes/optimizations (Ming)

   - Duplicate words in comments (Randy)

   - Flush deferral cleanup (Yufen)

   - IO context locking/retry fixes (John)

   - struct_size() usage (Gustavo)

   - blk-iocost fixes (Chengming)

   - blk-cgroup IO stats fixes (Boris)

   - Various little fixes"

* tag 'for-5.9/block-20200802' of git://git.kernel.dk/linux-block: (135 commits)
  block: blk-timeout: delete duplicated word
  block: blk-mq-sched: delete duplicated word
  block: blk-mq: delete duplicated word
  block: genhd: delete duplicated words
  block: elevator: delete duplicated word and fix typos
  block: bio: delete duplicated words
  block: bfq-iosched: fix duplicated word
  iocost_monitor: start from the oldest usage index
  iocost: Fix check condition of iocg abs_vdebt
  block: Remove callback typedefs for blk_mq_ops
  block: Use non _rcu version of list functions for tag_set_list
  blk-cgroup: show global disk stats in root cgroup io.stat
  blk-cgroup: make iostat functions visible to stat printing
  block: improve discard bio alignment in __blkdev_issue_discard()
  block: change REQ_OP_ZONE_RESET and REQ_OP_ZONE_RESET_ALL to be odd numbers
  block: defer flush request no matter whether we have elevator
  block: make blk_timeout_init() static
  block: remove retry loop in ioc_release_fn()
  block: remove unnecessary ioc nested locking
  block: integrate bd_start_claiming into __blkdev_get
  ...

1 files changed, 55 insertions, 31 deletions

diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 5ef0484513ec..7ba62d68885a 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -348,7 +348,7 @@ static int __blk_trace_remove(struct request_queue *q)
 	struct blk_trace *bt;
 
 	bt = rcu_replace_pointer(q->blk_trace, NULL,
-				 lockdep_is_held(&q->blk_trace_mutex));
+				 lockdep_is_held(&q->debugfs_mutex));
 	if (!bt)
 		return -EINVAL;
 
@@ -362,9 +362,9 @@ int blk_trace_remove(struct request_queue *q)
 {
 	int ret;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 	ret = __blk_trace_remove(q);
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 
 	return ret;
 }
@@ -483,12 +483,11 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	struct dentry *dir = NULL;
 	int ret;
 
+	lockdep_assert_held(&q->debugfs_mutex);
+
 	if (!buts->buf_size || !buts->buf_nr)
 		return -EINVAL;
 
-	if (!blk_debugfs_root)
-		return -ENOENT;
-
 	strncpy(buts->name, name, BLKTRACE_BDEV_SIZE);
 	buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0';
 
@@ -503,7 +502,7 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	 * we can be.
 	 */
 	if (rcu_dereference_protected(q->blk_trace,
-				      lockdep_is_held(&q->blk_trace_mutex))) {
+				      lockdep_is_held(&q->debugfs_mutex))) {
 		pr_warn("Concurrent blktraces are not allowed on %s\n",
 			buts->name);
 		return -EBUSY;
@@ -522,12 +521,29 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!bt->msg_data)
 		goto err;
 
-	ret = -ENOENT;
-
-	dir = debugfs_lookup(buts->name, blk_debugfs_root);
-	if (!dir)
+	/*
+	 * When tracing the whole disk reuse the existing debugfs directory
+	 * created by the block layer on init. For partitions block devices,
+	 * and scsi-generic block devices we create a temporary new debugfs
+	 * directory that will be removed once the trace ends.
+	 */
+	if (bdev && bdev == bdev->bd_contains)
+		dir = q->debugfs_dir;
+	else
 		bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
 
+	/*
+	 * As blktrace relies on debugfs for its interface the debugfs directory
+	 * is required, contrary to the usual mantra of not checking for debugfs
+	 * files or directories.
+	 */
+	if (IS_ERR_OR_NULL(dir)) {
+		pr_warn("debugfs_dir not present for %s so skipping\n",
+			buts->name);
+		ret = -ENOENT;
+		goto err;
+	}
+
 	bt->dev = dev;
 	atomic_set(&bt->dropped, 0);
 	INIT_LIST_HEAD(&bt->running_list);
@@ -563,8 +579,6 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 
 	ret = 0;
 err:
-	if (dir && !bt->dir)
-		dput(dir);
 	if (ret)
 		blk_trace_free(bt);
 	return ret;
@@ -597,9 +611,9 @@ int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 {
 	int ret;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 	ret = __blk_trace_setup(q, name, dev, bdev, arg);
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 
 	return ret;
 }
@@ -645,7 +659,7 @@ static int __blk_trace_startstop(struct request_queue *q, int start)
 	struct blk_trace *bt;
 
 	bt = rcu_dereference_protected(q->blk_trace,
-				       lockdep_is_held(&q->blk_trace_mutex));
+				       lockdep_is_held(&q->debugfs_mutex));
 	if (bt == NULL)
 		return -EINVAL;
 
@@ -685,9 +699,9 @@ int blk_trace_startstop(struct request_queue *q, int start)
 {
 	int ret;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 	ret = __blk_trace_startstop(q, start);
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 
 	return ret;
 }
@@ -716,7 +730,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 	if (!q)
 		return -ENXIO;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 
 	switch (cmd) {
 	case BLKTRACESETUP:
@@ -743,7 +757,7 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
 		break;
 	}
 
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 	return ret;
 }
 
@@ -754,14 +768,14 @@ int blk_trace_ioctl(struct block_device *bdev, unsigned cmd, char __user *arg)
  **/
 void blk_trace_shutdown(struct request_queue *q)
 {
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 	if (rcu_dereference_protected(q->blk_trace,
-				      lockdep_is_held(&q->blk_trace_mutex))) {
+				      lockdep_is_held(&q->debugfs_mutex))) {
 		__blk_trace_startstop(q, 0);
 		__blk_trace_remove(q);
 	}
 
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 }
 
 #ifdef CONFIG_BLK_CGROUP
@@ -846,6 +860,13 @@ static void blk_add_trace_rq_issue(void *ignore,
 			 blk_trace_request_get_cgid(q, rq));
 }
 
+static void blk_add_trace_rq_merge(void *ignore,
+				   struct request_queue *q, struct request *rq)
+{
+	blk_add_trace_rq(rq, 0, blk_rq_bytes(rq), BLK_TA_BACKMERGE,
+			 blk_trace_request_get_cgid(q, rq));
+}
+
 static void blk_add_trace_rq_requeue(void *ignore,
 				     struct request_queue *q,
 				     struct request *rq)
@@ -1130,6 +1151,8 @@ static void blk_register_tracepoints(void)
 	WARN_ON(ret);
 	ret = register_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
 	WARN_ON(ret);
+	ret = register_trace_block_rq_merge(blk_add_trace_rq_merge, NULL);
+	WARN_ON(ret);
 	ret = register_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
 	WARN_ON(ret);
 	ret = register_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
@@ -1176,6 +1199,7 @@ static void blk_unregister_tracepoints(void)
 	unregister_trace_block_bio_bounce(blk_add_trace_bio_bounce, NULL);
 	unregister_trace_block_rq_complete(blk_add_trace_rq_complete, NULL);
 	unregister_trace_block_rq_requeue(blk_add_trace_rq_requeue, NULL);
+	unregister_trace_block_rq_merge(blk_add_trace_rq_merge, NULL);
 	unregister_trace_block_rq_issue(blk_add_trace_rq_issue, NULL);
 	unregister_trace_block_rq_insert(blk_add_trace_rq_insert, NULL);
 
@@ -1642,7 +1666,7 @@ static int blk_trace_remove_queue(struct request_queue *q)
 	struct blk_trace *bt;
 
 	bt = rcu_replace_pointer(q->blk_trace, NULL,
-				 lockdep_is_held(&q->blk_trace_mutex));
+				 lockdep_is_held(&q->debugfs_mutex));
 	if (bt == NULL)
 		return -EINVAL;
 
@@ -1817,10 +1841,10 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 	if (q == NULL)
 		goto out_bdput;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 
 	bt = rcu_dereference_protected(q->blk_trace,
-				       lockdep_is_held(&q->blk_trace_mutex));
+				       lockdep_is_held(&q->debugfs_mutex));
 	if (attr == &dev_attr_enable) {
 		ret = sprintf(buf, "%u\n", !!bt);
 		goto out_unlock_bdev;
@@ -1838,7 +1862,7 @@ static ssize_t sysfs_blk_trace_attr_show(struct device *dev,
 		ret = sprintf(buf, "%llu\n", bt->end_lba);
 
 out_unlock_bdev:
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 out_bdput:
 	bdput(bdev);
 out:
@@ -1881,10 +1905,10 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	if (q == NULL)
 		goto out_bdput;
 
-	mutex_lock(&q->blk_trace_mutex);
+	mutex_lock(&q->debugfs_mutex);
 
 	bt = rcu_dereference_protected(q->blk_trace,
-				       lockdep_is_held(&q->blk_trace_mutex));
+				       lockdep_is_held(&q->debugfs_mutex));
 	if (attr == &dev_attr_enable) {
 		if (!!value == !!bt) {
 			ret = 0;
@@ -1901,7 +1925,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	if (bt == NULL) {
 		ret = blk_trace_setup_queue(q, bdev);
 		bt = rcu_dereference_protected(q->blk_trace,
-				lockdep_is_held(&q->blk_trace_mutex));
+				lockdep_is_held(&q->debugfs_mutex));
 	}
 
 	if (ret == 0) {
@@ -1916,7 +1940,7 @@ static ssize_t sysfs_blk_trace_attr_store(struct device *dev,
 	}
 
 out_unlock_bdev:
-	mutex_unlock(&q->blk_trace_mutex);
+	mutex_unlock(&q->debugfs_mutex);
 out_bdput:
 	bdput(bdev);
 out: