Merge tag 'block-5.10-2020-10-12' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Series of merge handling cleanups (Baolin, Christoph)

 - Series of blk-throttle fixes and cleanups (Baolin)

 - Series cleaning up BDI, seperating the block device from the
   backing_dev_info (Christoph)

 - Removal of bdget() as a generic API (Christoph)

 - Removal of blkdev_get() as a generic API (Christoph)

 - Cleanup of is-partition checks (Christoph)

 - Series reworking disk revalidation (Christoph)

 - Series cleaning up bio flags (Christoph)

 - bio crypt fixes (Eric)

 - IO stats inflight tweak (Gabriel)

 - blk-mq tags fixes (Hannes)

 - Buffer invalidation fixes (Jan)

 - Allow soft limits for zone append (Johannes)

 - Shared tag set improvements (John, Kashyap)

 - Allow IOPRIO_CLASS_RT for CAP_SYS_NICE (Khazhismel)

 - DM no-wait support (Mike, Konstantin)

 - Request allocation improvements (Ming)

 - Allow md/dm/bcache to use IO stat helpers (Song)

 - Series improving blk-iocost (Tejun)

 - Various cleanups (Geert, Damien, Danny, Julia, Tetsuo, Tian, Wang,
   Xianting, Yang, Yufen, yangerkun)

* tag 'block-5.10-2020-10-12' of git://git.kernel.dk/linux-block: (191 commits)
  block: fix uapi blkzoned.h comments
  blk-mq: move cancel of hctx->run_work to the front of blk_exit_queue
  blk-mq: get rid of the dead flush handle code path
  block: get rid of unnecessary local variable
  block: fix comment and add lockdep assert
  blk-mq: use helper function to test hw stopped
  block: use helper function to test queue register
  block: remove redundant mq check
  block: invoke blk_mq_exit_sched no matter whether have .exit_sched
  percpu_ref: don't refer to ref->data if it isn't allocated
  block: ratelimit handle_bad_sector() message
  blk-throttle: Re-use the throtl_set_slice_end()
  blk-throttle: Open code __throtl_de/enqueue_tg()
  blk-throttle: Move service tree validation out of the throtl_rb_first()
  blk-throttle: Move the list operation after list validation
  blk-throttle: Fix IO hang for a corner case
  blk-throttle: Avoid tracking latency if low limit is invalid
  blk-throttle: Avoid getting the current time if tg->last_finish_time is 0
  blk-throttle: Remove a meaningless parameter for throtl_downgrade_state()
  block: Remove redundant 'return' statement
  ...

Author: torvalds

Documentation/filesystems/locking.rst

@@ -488,9 +488,6 @@ getgeo:			no
 swap_slot_free_notify:	no	(see below)
 ======================= ===================
 
-unlock_native_capacity and revalidate_disk are called only from
-check_disk_change().
-
 swap_slot_free_notify is called with swap_lock and sometimes the page lock
 held.
 

Documentation/userspace-api/ioctl/hdio.rst

@@ -181,7 +181,7 @@ HDIO_SET_UNMASKINTR
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 1]
 	  - EBUSY	Controller busy
@@ -231,7 +231,7 @@ HDIO_SET_MULTCOUNT
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range supported by disk.
 	  - EBUSY	Controller busy or blockmode already set.
@@ -295,7 +295,7 @@ HDIO_GET_IDENTITY
 		the ATA specification.
 
 	error returns:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - ENOMSG	IDENTIFY DEVICE information not available
 
 	notes:
@@ -355,7 +355,7 @@ HDIO_SET_KEEPSETTINGS
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 1]
 	  - EBUSY		Controller busy
@@ -1055,7 +1055,7 @@ HDIO_SET_32BIT
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 3]
 	  - EBUSY	Controller busy
@@ -1085,7 +1085,7 @@ HDIO_SET_NOWERR
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 1]
 	  - EBUSY		Controller busy
@@ -1113,7 +1113,7 @@ HDIO_SET_DMA
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 1]
 	  - EBUSY	Controller busy
@@ -1141,7 +1141,7 @@ HDIO_SET_PIO_MODE
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 255]
 	  - EBUSY	Controller busy
@@ -1237,7 +1237,7 @@ HDIO_SET_WCACHE
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 1]
 	  - EBUSY	Controller busy
@@ -1265,7 +1265,7 @@ HDIO_SET_ACOUSTIC
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 254]
 	  - EBUSY	Controller busy
@@ -1305,7 +1305,7 @@ HDIO_SET_ADDRESS
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 2]
 	  - EBUSY		Controller busy
@@ -1331,7 +1331,7 @@ HDIO_SET_IDE_SCSI
 
 
 	error return:
-	  - EINVAL	(bdev != bdev->bd_contains) (not sure what this means)
+	  - EINVAL	Called on a partition instead of the whole disk device
 	  - EACCES	Access denied:  requires CAP_SYS_ADMIN
 	  - EINVAL	value out of range [0 1]
 	  - EBUSY	Controller busy

block/Kconfig

@@ -161,8 +161,6 @@ config BLK_WBT_MQ
 	depends on BLK_WBT
 	help
 	Enable writeback throttling by default on multiqueue devices.
-	Multiqueue currently doesn't have support for IO scheduling,
-	enabling this option is recommended.
 
 config BLK_DEBUG_FS
 	bool "Block layer debugging information in debugfs"

block/bfq-iosched.c

@@ -4640,6 +4640,9 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
 {
 	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
 
+	if (!atomic_read(&hctx->elevator_queued))
+		return false;
+
 	/*
 	 * Avoiding lock: a race on bfqd->busy_queues should cause at
 	 * most a call to dispatch for nothing
@@ -5554,6 +5557,7 @@ static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx,
 		rq = list_first_entry(list, struct request, queuelist);
 		list_del_init(&rq->queuelist);
 		bfq_insert_request(hctx, rq, at_head);
+		atomic_inc(&hctx->elevator_queued);
 	}
 }
 
@@ -5921,6 +5925,7 @@ static void bfq_finish_requeue_request(struct request *rq)
 
 		bfq_completed_request(bfqq, bfqd);
 		bfq_finish_requeue_request_body(bfqq);
+		atomic_dec(&rq->mq_hctx->elevator_queued);
 
 		spin_unlock_irqrestore(&bfqd->lock, flags);
 	} else {
@@ -6360,8 +6365,8 @@ static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx)
 	struct blk_mq_tags *tags = hctx->sched_tags;
 	unsigned int min_shallow;
 
-	min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags);
-	sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow);
+	min_shallow = bfq_update_depths(bfqd, tags->bitmap_tags);
+	sbitmap_queue_min_shallow_depth(tags->bitmap_tags, min_shallow);
 }
 
 static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)

block/bio.c

@@ -713,20 +713,18 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
 
 	__bio_clone_fast(b, bio);
 
-	bio_crypt_clone(b, bio, gfp_mask);
+	if (bio_crypt_clone(b, bio, gfp_mask) < 0)
+		goto err_put;
 
-	if (bio_integrity(bio)) {
-		int ret;
-
-		ret = bio_integrity_clone(b, bio, gfp_mask);
-
-		if (ret < 0) {
-			bio_put(b);
-			return NULL;
-		}
-	}
+	if (bio_integrity(bio) &&
+	    bio_integrity_clone(b, bio, gfp_mask) < 0)
+		goto err_put;
 
 	return b;
+
+err_put:
+	bio_put(b);
+	return NULL;
 }
 EXPORT_SYMBOL(bio_clone_fast);
 

block/blk-cgroup.c

@@ -119,15 +119,24 @@ static void blkg_async_bio_workfn(struct work_struct *work)
 					     async_bio_work);
 	struct bio_list bios = BIO_EMPTY_LIST;
 	struct bio *bio;
+	struct blk_plug plug;
+	bool need_plug = false;
 
 	/* as long as there are pending bios, @blkg can't go away */
 	spin_lock_bh(&blkg->async_bio_lock);
 	bio_list_merge(&bios, &blkg->async_bios);
 	bio_list_init(&blkg->async_bios);
 	spin_unlock_bh(&blkg->async_bio_lock);
 
+	/* start plug only when bio_list contains at least 2 bios */
+	if (bios.head && bios.head->bi_next) {
+		need_plug = true;
+		blk_start_plug(&plug);
+	}
 	while ((bio = bio_list_pop(&bios)))
 		submit_bio(bio);
+	if (need_plug)
+		blk_finish_plug(&plug);
 }
 
 /**
@@ -1613,16 +1622,24 @@ static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now)
 static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
 {
 	unsigned long pflags;
+	bool clamp;
 	u64 now = ktime_to_ns(ktime_get());
 	u64 exp;
 	u64 delay_nsec = 0;
 	int tok;
 
 	while (blkg->parent) {
-		if (atomic_read(&blkg->use_delay)) {
+		int use_delay = atomic_read(&blkg->use_delay);
+
+		if (use_delay) {
+			u64 this_delay;
+
 			blkcg_scale_delay(blkg, now);
-			delay_nsec = max_t(u64, delay_nsec,
-					   atomic64_read(&blkg->delay_nsec));
+			this_delay = atomic64_read(&blkg->delay_nsec);
+			if (this_delay > delay_nsec) {
+				delay_nsec = this_delay;
+				clamp = use_delay > 0;
+			}
 		}
 		blkg = blkg->parent;
 	}
@@ -1634,10 +1651,13 @@ static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
 	 * Let's not sleep for all eternity if we've amassed a huge delay.
 	 * Swapping or metadata IO can accumulate 10's of seconds worth of
 	 * delay, and we want userspace to be able to do _something_ so cap the
-	 * delays at 1 second.  If there's 10's of seconds worth of delay then
-	 * the tasks will be delayed for 1 second for every syscall.
+	 * delays at 0.25s. If there's 10's of seconds worth of delay then the
+	 * tasks will be delayed for 0.25 second for every syscall. If
+	 * blkcg_set_delay() was used as indicated by negative use_delay, the
+	 * caller is responsible for regulating the range.
 	 */
-	delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC);
+	if (clamp)
+		delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC);
 
 	if (use_memdelay)
 		psi_memstall_enter(&pflags);