Merge tag 'for-6.8/block-2024-01-18' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:

 - NVMe pull request via Keith:
      - tcp, fc, and rdma target fixes (Maurizio, Daniel, Hannes,
        Christoph)
      - discard fixes and improvements (Christoph)
      - timeout debug improvements (Keith, Max)
      - various cleanups (Daniel, Max, Giuxen)
      - trace event string fixes (Arnd)
      - shadow doorbell setup on reset fix (William)
      - a write zeroes quirk for SK Hynix (Jim)

 - MD pull request via Song:
      - Sparse warning since v6.0 (Bart)
      - /proc/mdstat regression since v6.7 (Yu Kuai)

 - Use symbolic error value (Christian)

 - IO Priority documentation update (Christian)

 - Fix for accessing queue limits without having entered the queue
   (Christoph, me)

 - Fix for loop dio support (Christoph)

 - Move null_blk off deprecated ida interface (Christophe)

 - Ensure nbd initializes full msghdr (Eric)

 - Fix for a regression with the folio conversion, which is now easier
   to hit because of an unrelated change (Matthew)

 - Remove redundant check in virtio-blk (Li)

 - Fix for a potential hang in sbitmap (Ming)

 - Fix for partial zone appending (Damien)

 - Misc changes and fixes (Bart, me, Kemeng, Dmitry)

* tag 'for-6.8/block-2024-01-18' of git://git.kernel.dk/linux: (45 commits)
  Documentation: block: ioprio: Update schedulers
  loop: fix the the direct I/O support check when used on top of block devices
  blk-mq: Remove the hctx 'run' debugfs attribute
  nbd: always initialize struct msghdr completely
  block: Fix iterating over an empty bio with bio_for_each_folio_all
  block: bio-integrity: fix kcalloc() arguments order
  virtio_blk: remove duplicate check if queue is broken in virtblk_done
  sbitmap: remove stale comment in sbq_calc_wake_batch
  block: Correct a documentation comment in blk-cgroup.c
  null_blk: Remove usage of the deprecated ida_simple_xx() API
  block: ensure we hold a queue reference when using queue limits
  blk-mq: rename blk_mq_can_use_cached_rq
  block: print symbolic error name instead of error code
  blk-mq: fix IO hang from sbitmap wakeup race
  nvmet-rdma: avoid circular locking dependency on install_queue()
  nvmet-tcp: avoid circular locking dependency on install_queue()
  nvme-pci: set doorbell config before unquiescing
  block: fix partial zone append completion handling in req_bio_endio()
  block/iocost: silence warning on 'last_period' potentially being unused
  md/raid1: Use blk_opf_t for read and write operations
  ...

Author: torvalds

Documentation/block/ioprio.rst

@@ -6,17 +6,16 @@ Block io priorities
 Intro
 -----
 
-With the introduction of cfq v3 (aka cfq-ts or time sliced cfq), basic io
-priorities are supported for reads on files.  This enables users to io nice
-processes or process groups, similar to what has been possible with cpu
-scheduling for ages.  This document mainly details the current possibilities
-with cfq; other io schedulers do not support io priorities thus far.
+The io priority feature enables users to io nice processes or process groups,
+similar to what has been possible with cpu scheduling for ages. Support for io
+priorities is io scheduler dependent and currently supported by bfq and
+mq-deadline.
 
 Scheduling classes
 ------------------
 
-CFQ implements three generic scheduling classes that determine how io is
-served for a process.
+Three generic scheduling classes are implemented for io priorities that
+determine how io is served for a process.
 
 IOPRIO_CLASS_RT: This is the realtime io class. This scheduling class is given
 higher priority than any other in the system, processes from this class are

block/bio-integrity.c

@@ -336,7 +336,7 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes,
 	if (nr_vecs > BIO_MAX_VECS)
 		return -E2BIG;
 	if (nr_vecs > UIO_FASTIOV) {
-		bvec = kcalloc(sizeof(*bvec), nr_vecs, GFP_KERNEL);
+		bvec = kcalloc(nr_vecs, sizeof(*bvec), GFP_KERNEL);
 		if (!bvec)
 			return -ENOMEM;
 		pages = NULL;

block/blk-cgroup.c

@@ -300,7 +300,7 @@ static inline struct blkcg *blkcg_parent(struct blkcg *blkcg)
  * @disk: gendisk the new blkg is associated with
  * @gfp_mask: allocation mask to use
  *
- * Allocate a new blkg assocating @blkcg and @q.
+ * Allocate a new blkg associating @blkcg and @disk.
  */
 static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct gendisk *disk,
 				   gfp_t gfp_mask)

block/blk-iocost.c

@@ -1261,7 +1261,7 @@ static void weight_updated(struct ioc_gq *iocg, struct ioc_now *now)
 static bool iocg_activate(struct ioc_gq *iocg, struct ioc_now *now)
 {
 	struct ioc *ioc = iocg->ioc;
-	u64 last_period, cur_period;
+	u64 __maybe_unused last_period, cur_period;
 	u64 vtime, vtarget;
 	int i;
 

block/blk-mq-debugfs.c

@@ -479,23 +479,6 @@ static int hctx_sched_tags_bitmap_show(void *data, struct seq_file *m)
 	return res;
 }
 
-static int hctx_run_show(void *data, struct seq_file *m)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-
-	seq_printf(m, "%lu\n", hctx->run);
-	return 0;
-}
-
-static ssize_t hctx_run_write(void *data, const char __user *buf, size_t count,
-			      loff_t *ppos)
-{
-	struct blk_mq_hw_ctx *hctx = data;
-
-	hctx->run = 0;
-	return count;
-}
-
 static int hctx_active_show(void *data, struct seq_file *m)
 {
 	struct blk_mq_hw_ctx *hctx = data;
@@ -624,7 +607,6 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"tags_bitmap", 0400, hctx_tags_bitmap_show},
 	{"sched_tags", 0400, hctx_sched_tags_show},
 	{"sched_tags_bitmap", 0400, hctx_sched_tags_bitmap_show},
-	{"run", 0600, hctx_run_show, hctx_run_write},
 	{"active", 0400, hctx_active_show},
 	{"dispatch_busy", 0400, hctx_dispatch_busy_show},
 	{"type", 0400, hctx_type_show},

block/blk-mq-sched.c

@@ -324,8 +324,6 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 	if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)))
 		return;
 
-	hctx->run++;
-
 	/*
 	 * A return of -EAGAIN is an indication that hctx->dispatch is not
 	 * empty and we must run again in order to avoid starving flushes.

block/blk-mq.c

@@ -772,11 +772,16 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
 		/*
 		 * Partial zone append completions cannot be supported as the
 		 * BIO fragments may end up not being written sequentially.
+		 * For such case, force the completed nbytes to be equal to
+		 * the BIO size so that bio_advance() sets the BIO remaining
+		 * size to 0 and we end up calling bio_endio() before returning.
 		 */
-		if (bio->bi_iter.bi_size != nbytes)
+		if (bio->bi_iter.bi_size != nbytes) {
 			bio->bi_status = BLK_STS_IOERR;
-		else
+			nbytes = bio->bi_iter.bi_size;
+		} else {
 			bio->bi_iter.bi_sector = rq->__sector;
+		}
 	}
 
 	bio_advance(bio, nbytes);
@@ -1859,6 +1864,22 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
 	__add_wait_queue(wq, wait);
 
+	/*
+	 * Add one explicit barrier since blk_mq_get_driver_tag() may
+	 * not imply barrier in case of failure.
+	 *
+	 * Order adding us to wait queue and allocating driver tag.
+	 *
+	 * The pair is the one implied in sbitmap_queue_wake_up() which
+	 * orders clearing sbitmap tag bits and waitqueue_active() in
+	 * __sbitmap_queue_wake_up(), since waitqueue_active() is lockless
+	 *
+	 * Otherwise, re-order of adding wait queue and getting driver tag
+	 * may cause __sbitmap_queue_wake_up() to wake up nothing because
+	 * the waitqueue_active() may not observe us in wait queue.
+	 */
+	smp_mb();
+
 	/*
 	 * It's possible that a tag was freed in the window between the
 	 * allocation failure and adding the hardware queue to the wait
@@ -2891,8 +2912,11 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 	return NULL;
 }
 
-/* return true if this @rq can be used for @bio */
-static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug,
+/*
+ * Check if we can use the passed on request for submitting the passed in bio,
+ * and remove it from the request list if it can be used.
+ */
+static bool blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
 		struct bio *bio)
 {
 	enum hctx_type type = blk_mq_get_hctx_type(bio->bi_opf);
@@ -2952,12 +2976,6 @@ void blk_mq_submit_bio(struct bio *bio)
 	blk_status_t ret;
 
 	bio = blk_queue_bounce(bio, q);
-	if (bio_may_exceed_limits(bio, &q->limits)) {
-		bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
-		if (!bio)
-			return;
-	}
-
 	bio_set_ioprio(bio);
 
 	if (plug) {
@@ -2966,16 +2984,26 @@ void blk_mq_submit_bio(struct bio *bio)
 			rq = NULL;
 	}
 	if (rq) {
+		if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
+			bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+			if (!bio)
+				return;
+		}
 		if (!bio_integrity_prep(bio))
 			return;
 		if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
 			return;
-		if (blk_mq_can_use_cached_rq(rq, plug, bio))
+		if (blk_mq_use_cached_rq(rq, plug, bio))
 			goto done;
 		percpu_ref_get(&q->q_usage_counter);
 	} else {
 		if (unlikely(bio_queue_enter(bio)))
 			return;
+		if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
+			bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+			if (!bio)
+				goto fail;
+		}
 		if (!bio_integrity_prep(bio))
 			goto fail;
 	}

block/ioprio.c

@@ -139,32 +139,6 @@ SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
 	return ret;
 }
 
-/*
- * If the task has set an I/O priority, use that. Otherwise, return
- * the default I/O priority.
- *
- * Expected to be called for current task or with task_lock() held to keep
- * io_context stable.
- */
-int __get_task_ioprio(struct task_struct *p)
-{
-	struct io_context *ioc = p->io_context;
-	int prio;
-
-	if (p != current)
-		lockdep_assert_held(&p->alloc_lock);
-	if (ioc)
-		prio = ioc->ioprio;
-	else
-		prio = IOPRIO_DEFAULT;
-
-	if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE)
-		prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
-					 task_nice_ioprio(p));
-	return prio;
-}
-EXPORT_SYMBOL_GPL(__get_task_ioprio);
-
 static int get_task_ioprio(struct task_struct *p)
 {
 	int ret;

block/partitions/core.c

@@ -562,8 +562,8 @@ static bool blk_add_partition(struct gendisk *disk,
 	part = add_partition(disk, p, from, size, state->parts[p].flags,
 			     &state->parts[p].info);
 	if (IS_ERR(part) && PTR_ERR(part) != -ENXIO) {
-		printk(KERN_ERR " %s: p%d could not be added: %ld\n",
-		       disk->disk_name, p, -PTR_ERR(part));
+		printk(KERN_ERR " %s: p%d could not be added: %pe\n",
+		       disk->disk_name, p, part);
 		return true;
 	}
 

drivers/block/loop.c

@@ -165,39 +165,37 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file)
 	return get_size(lo->lo_offset, lo->lo_sizelimit, file);
 }
 
+/*
+ * We support direct I/O only if lo_offset is aligned with the logical I/O size
+ * of backing device, and the logical block size of loop is bigger than that of
+ * the backing device.
+ */
+static bool lo_bdev_can_use_dio(struct loop_device *lo,
+		struct block_device *backing_bdev)
+{
+	unsigned short sb_bsize = bdev_logical_block_size(backing_bdev);
+
+	if (queue_logical_block_size(lo->lo_queue) < sb_bsize)
+		return false;
+	if (lo->lo_offset & (sb_bsize - 1))
+		return false;
+	return true;
+}
+
 static void __loop_update_dio(struct loop_device *lo, bool dio)
 {
 	struct file *file = lo->lo_backing_file;
-	struct address_space *mapping = file->f_mapping;
-	struct inode *inode = mapping->host;
-	unsigned short sb_bsize = 0;
-	unsigned dio_align = 0;
+	struct inode *inode = file->f_mapping->host;
+	struct block_device *backing_bdev = NULL;
 	bool use_dio;
 
-	if (inode->i_sb->s_bdev) {
-		sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev);
-		dio_align = sb_bsize - 1;
-	}
+	if (S_ISBLK(inode->i_mode))
+		backing_bdev = I_BDEV(inode);
+	else if (inode->i_sb->s_bdev)
+		backing_bdev = inode->i_sb->s_bdev;
 
-	/*
-	 * We support direct I/O only if lo_offset is aligned with the
-	 * logical I/O size of backing device, and the logical block
-	 * size of loop is bigger than the backing device's.
-	 *
-	 * TODO: the above condition may be loosed in the future, and
-	 * direct I/O may be switched runtime at that time because most
-	 * of requests in sane applications should be PAGE_SIZE aligned
-	 */
-	if (dio) {
-		if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
-		    !(lo->lo_offset & dio_align) &&
-		    (file->f_mode & FMODE_CAN_ODIRECT))
-			use_dio = true;
-		else
-			use_dio = false;
-	} else {
-		use_dio = false;
-	}
+	use_dio = dio && (file->f_mode & FMODE_CAN_ODIRECT) &&
+		(!backing_bdev || lo_bdev_can_use_dio(lo, backing_bdev));
 
 	if (lo->use_dio == use_dio)
 		return;