Merge tag 'block-6.17-20250822' of git://git.kernel.dk/linux

Pull block fixes from Jens Axboe:
 "A set of fixes for block that should go into this tree. A bit larger
  than what I usually have at this point in time, a lot of that is the
  continued fixing of the lockdep annotation for queue freezing that we
  recently added, which has highlighted a number of little issues here
  and there. This contains:

   - MD pull request via Yu:

       - Add a legacy_async_del_gendisk mode, to prevent a user tools
         regression. New user tools releases will not use such a mode,
         the old release with a new kernel now will have warning about
         deprecated behavior, and we prepare to remove this legacy mode
         after about a year later

       - The rename in kernel causing user tools build failure, revert
         the rename in mdp_superblock_s

       - Fix a regression that interrupted resync can be shown as
         recover from mdstat or sysfs

   - Improve file size detection for loop, particularly for networked
     file systems, by using getattr to get the size rather than the
     cached inode size.

   - Hotplug CPU lock vs queue freeze fix

   - Lockdep fix while updating the number of hardware queues

   - Fix stacking for PI devices

   - Silence bio_check_eod() for the known case of device removal where
     the size is truncated to 0 sectors"

* tag 'block-6.17-20250822' of git://git.kernel.dk/linux:
  block: avoid cpu_hotplug_lock depedency on freeze_lock
  block: decrement block_rq_qos static key in rq_qos_del()
  block: skip q->rq_qos check in rq_qos_done_bio()
  blk-mq: fix lockdep warning in __blk_mq_update_nr_hw_queues
  block: tone down bio_check_eod
  loop: use vfs_getattr_nosec for accurate file size
  loop: Consolidate size calculation logic into lo_calculate_size()
  block: remove newlines from the warnings in blk_validate_integrity_limits
  block: handle pi_tuple_size in queue_limits_stack_integrity
  selftests: ublk: Use ARRAY_SIZE() macro to improve code
  md: fix sync_action incorrect display during resync
  md: add helper rdev_needs_recovery()
  md: keep recovery_cp in mdp_superblock_s
  md: add legacy_async_del_gendisk mode

Author: torvalds

block/blk-core.c

@@ -557,7 +557,7 @@ static inline int bio_check_eod(struct bio *bio)
 	sector_t maxsector = bdev_nr_sectors(bio->bi_bdev);
 	unsigned int nr_sectors = bio_sectors(bio);
 
-	if (nr_sectors &&
+	if (nr_sectors && maxsector &&
 	    (nr_sectors > maxsector ||
 	     bio->bi_iter.bi_sector > maxsector - nr_sectors)) {
 		pr_info_ratelimited("%s: attempt to access beyond end of device\n"

block/blk-mq-debugfs.c

@@ -95,6 +95,7 @@ static const char *const blk_queue_flag_name[] = {
 	QUEUE_FLAG_NAME(SQ_SCHED),
 	QUEUE_FLAG_NAME(DISABLE_WBT_DEF),
 	QUEUE_FLAG_NAME(NO_ELV_SWITCH),
+	QUEUE_FLAG_NAME(QOS_ENABLED),
 };
 #undef QUEUE_FLAG_NAME
 

block/blk-mq.c

@@ -5033,6 +5033,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	unsigned int memflags;
 	int i;
 	struct xarray elv_tbl, et_tbl;
+	bool queues_frozen = false;
 
 	lockdep_assert_held(&set->tag_list_lock);
 
@@ -5056,9 +5057,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		blk_mq_sysfs_unregister_hctxs(q);
 	}
 
-	list_for_each_entry(q, &set->tag_list, tag_set_list)
-		blk_mq_freeze_queue_nomemsave(q);
-
 	/*
 	 * Switch IO scheduler to 'none', cleaning up the data associated
 	 * with the previous scheduler. We will switch back once we are done
@@ -5068,6 +5066,9 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		if (blk_mq_elv_switch_none(q, &elv_tbl))
 			goto switch_back;
 
+	list_for_each_entry(q, &set->tag_list, tag_set_list)
+		blk_mq_freeze_queue_nomemsave(q);
+	queues_frozen = true;
 	if (blk_mq_realloc_tag_set_tags(set, nr_hw_queues) < 0)
 		goto switch_back;
 
@@ -5091,8 +5092,12 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 	}
 switch_back:
 	/* The blk_mq_elv_switch_back unfreezes queue for us. */
-	list_for_each_entry(q, &set->tag_list, tag_set_list)
+	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+		/* switch_back expects queue to be frozen */
+		if (!queues_frozen)
+			blk_mq_freeze_queue_nomemsave(q);
 		blk_mq_elv_switch_back(q, &elv_tbl, &et_tbl);
+	}
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_sysfs_register_hctxs(q);

block/blk-rq-qos.c

@@ -2,8 +2,6 @@
 
 #include "blk-rq-qos.h"
 
-__read_mostly DEFINE_STATIC_KEY_FALSE(block_rq_qos);
-
 /*
  * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded,
  * false if 'v' + 1 would be bigger than 'below'.
@@ -319,8 +317,8 @@ void rq_qos_exit(struct request_queue *q)
 		struct rq_qos *rqos = q->rq_qos;
 		q->rq_qos = rqos->next;
 		rqos->ops->exit(rqos);
-		static_branch_dec(&block_rq_qos);
 	}
+	blk_queue_flag_clear(QUEUE_FLAG_QOS_ENABLED, q);
 	mutex_unlock(&q->rq_qos_mutex);
 }
 
@@ -346,7 +344,7 @@ int rq_qos_add(struct rq_qos *rqos, struct gendisk *disk, enum rq_qos_id id,
 		goto ebusy;
 	rqos->next = q->rq_qos;
 	q->rq_qos = rqos;
-	static_branch_inc(&block_rq_qos);
+	blk_queue_flag_set(QUEUE_FLAG_QOS_ENABLED, q);
 
 	blk_mq_unfreeze_queue(q, memflags);
 
@@ -377,6 +375,8 @@ void rq_qos_del(struct rq_qos *rqos)
 			break;
 		}
 	}
+	if (!q->rq_qos)
+		blk_queue_flag_clear(QUEUE_FLAG_QOS_ENABLED, q);
 	blk_mq_unfreeze_queue(q, memflags);
 
 	mutex_lock(&q->debugfs_mutex);

block/blk-rq-qos.h

@@ -12,7 +12,6 @@
 #include "blk-mq-debugfs.h"
 
 struct blk_mq_debugfs_attr;
-extern struct static_key_false block_rq_qos;
 
 enum rq_qos_id {
 	RQ_QOS_WBT,
@@ -113,43 +112,55 @@ void __rq_qos_queue_depth_changed(struct rq_qos *rqos);
 
 static inline void rq_qos_cleanup(struct request_queue *q, struct bio *bio)
 {
-	if (static_branch_unlikely(&block_rq_qos) && q->rq_qos)
+	if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
+			q->rq_qos)
 		__rq_qos_cleanup(q->rq_qos, bio);
 }
 
 static inline void rq_qos_done(struct request_queue *q, struct request *rq)
 {
-	if (static_branch_unlikely(&block_rq_qos) && q->rq_qos &&
-	    !blk_rq_is_passthrough(rq))
+	if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
+			q->rq_qos && !blk_rq_is_passthrough(rq))
 		__rq_qos_done(q->rq_qos, rq);
 }
 
 static inline void rq_qos_issue(struct request_queue *q, struct request *rq)
 {
-	if (static_branch_unlikely(&block_rq_qos) && q->rq_qos)
+	if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
+			q->rq_qos)
 		__rq_qos_issue(q->rq_qos, rq);
 }
 
 static inline void rq_qos_requeue(struct request_queue *q, struct request *rq)
 {
-	if (static_branch_unlikely(&block_rq_qos) && q->rq_qos)
+	if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
+			q->rq_qos)
 		__rq_qos_requeue(q->rq_qos, rq);
 }
 
 static inline void rq_qos_done_bio(struct bio *bio)
 {
-	if (static_branch_unlikely(&block_rq_qos) &&
-	    bio->bi_bdev && (bio_flagged(bio, BIO_QOS_THROTTLED) ||
-			     bio_flagged(bio, BIO_QOS_MERGED))) {
-		struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-		if (q->rq_qos)
-			__rq_qos_done_bio(q->rq_qos, bio);
-	}
+	struct request_queue *q;
+
+	if (!bio->bi_bdev || (!bio_flagged(bio, BIO_QOS_THROTTLED) &&
+			     !bio_flagged(bio, BIO_QOS_MERGED)))
+		return;
+
+	q = bdev_get_queue(bio->bi_bdev);
+
+	/*
+	 * If a bio has BIO_QOS_xxx set, it implicitly implies that
+	 * q->rq_qos is present. So, we skip re-checking q->rq_qos
+	 * here as an extra optimization and directly call
+	 * __rq_qos_done_bio().
+	 */
+	__rq_qos_done_bio(q->rq_qos, bio);
 }
 
 static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio)
 {
-	if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) {
+	if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
+			q->rq_qos) {
 		bio_set_flag(bio, BIO_QOS_THROTTLED);
 		__rq_qos_throttle(q->rq_qos, bio);
 	}
@@ -158,22 +169,25 @@ static inline void rq_qos_throttle(struct request_queue *q, struct bio *bio)
 static inline void rq_qos_track(struct request_queue *q, struct request *rq,
 				struct bio *bio)
 {
-	if (static_branch_unlikely(&block_rq_qos) && q->rq_qos)
+	if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
+			q->rq_qos)
 		__rq_qos_track(q->rq_qos, rq, bio);
 }
 
 static inline void rq_qos_merge(struct request_queue *q, struct request *rq,
 				struct bio *bio)
 {
-	if (static_branch_unlikely(&block_rq_qos) && q->rq_qos) {
+	if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
+			q->rq_qos) {
 		bio_set_flag(bio, BIO_QOS_MERGED);
 		__rq_qos_merge(q->rq_qos, rq, bio);
 	}
 }
 
 static inline void rq_qos_queue_depth_changed(struct request_queue *q)
 {
-	if (static_branch_unlikely(&block_rq_qos) && q->rq_qos)
+	if (unlikely(test_bit(QUEUE_FLAG_QOS_ENABLED, &q->queue_flags)) &&
+			q->rq_qos)
 		__rq_qos_queue_depth_changed(q->rq_qos);
 }
 

block/blk-settings.c

@@ -157,25 +157,22 @@ static int blk_validate_integrity_limits(struct queue_limits *lim)
 	switch (bi->csum_type) {
 	case BLK_INTEGRITY_CSUM_NONE:
 		if (bi->pi_tuple_size) {
-			pr_warn("pi_tuple_size must be 0 when checksum type \
-				 is none\n");
+			pr_warn("pi_tuple_size must be 0 when checksum type is none\n");
 			return -EINVAL;
 		}
 		break;
 	case BLK_INTEGRITY_CSUM_CRC:
 	case BLK_INTEGRITY_CSUM_IP:
 		if (bi->pi_tuple_size != sizeof(struct t10_pi_tuple)) {
-			pr_warn("pi_tuple_size mismatch for T10 PI: expected \
-				 %zu, got %u\n",
+			pr_warn("pi_tuple_size mismatch for T10 PI: expected %zu, got %u\n",
 				 sizeof(struct t10_pi_tuple),
 				 bi->pi_tuple_size);
 			return -EINVAL;
 		}
 		break;
 	case BLK_INTEGRITY_CSUM_CRC64:
 		if (bi->pi_tuple_size != sizeof(struct crc64_pi_tuple)) {
-			pr_warn("pi_tuple_size mismatch for CRC64 PI: \
-				 expected %zu, got %u\n",
+			pr_warn("pi_tuple_size mismatch for CRC64 PI: expected %zu, got %u\n",
 				 sizeof(struct crc64_pi_tuple),
 				 bi->pi_tuple_size);
 			return -EINVAL;
@@ -972,6 +969,8 @@ bool queue_limits_stack_integrity(struct queue_limits *t,
 			goto incompatible;
 		if (ti->csum_type != bi->csum_type)
 			goto incompatible;
+		if (ti->pi_tuple_size != bi->pi_tuple_size)
+			goto incompatible;
 		if ((ti->flags & BLK_INTEGRITY_REF_TAG) !=
 		    (bi->flags & BLK_INTEGRITY_REF_TAG))
 			goto incompatible;
@@ -980,6 +979,7 @@ bool queue_limits_stack_integrity(struct queue_limits *t,
 		ti->flags |= (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) |
 			     (bi->flags & BLK_INTEGRITY_REF_TAG);
 		ti->csum_type = bi->csum_type;
+		ti->pi_tuple_size = bi->pi_tuple_size;
 		ti->metadata_size = bi->metadata_size;
 		ti->pi_offset = bi->pi_offset;
 		ti->interval_exp = bi->interval_exp;

drivers/block/loop.c

@@ -137,32 +137,36 @@ static void loop_global_unlock(struct loop_device *lo, bool global)
 static int max_part;
 static int part_shift;
 
-static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file)
+static loff_t lo_calculate_size(struct loop_device *lo, struct file *file)
 {
+	struct kstat stat;
 	loff_t loopsize;
+	int ret;
 
-	/* Compute loopsize in bytes */
-	loopsize = i_size_read(file->f_mapping->host);
-	if (offset > 0)
-		loopsize -= offset;
+	/*
+	 * Get the accurate file size. This provides better results than
+	 * cached inode data, particularly for network filesystems where
+	 * metadata may be stale.
+	 */
+	ret = vfs_getattr_nosec(&file->f_path, &stat, STATX_SIZE, 0);
+	if (ret)
+		return 0;
+
+	loopsize = stat.size;
+	if (lo->lo_offset > 0)
+		loopsize -= lo->lo_offset;
 	/* offset is beyond i_size, weird but possible */
 	if (loopsize < 0)
 		return 0;
-
-	if (sizelimit > 0 && sizelimit < loopsize)
-		loopsize = sizelimit;
+	if (lo->lo_sizelimit > 0 && lo->lo_sizelimit < loopsize)
+		loopsize = lo->lo_sizelimit;
 	/*
 	 * Unfortunately, if we want to do I/O on the device,
 	 * the number of 512-byte sectors has to fit into a sector_t.
 	 */
 	return loopsize >> 9;
 }
 
-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
@@ -569,7 +573,7 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	error = -EINVAL;
 
 	/* size of the new backing store needs to be the same */
-	if (get_loop_size(lo, file) != get_loop_size(lo, old_file))
+	if (lo_calculate_size(lo, file) != lo_calculate_size(lo, old_file))
 		goto out_err;
 
 	/*
@@ -1063,7 +1067,7 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode,
 	loop_update_dio(lo);
 	loop_sysfs_init(lo);
 
-	size = get_loop_size(lo, file);
+	size = lo_calculate_size(lo, file);
 	loop_set_size(lo, size);
 
 	/* Order wrt reading lo_state in loop_validate_file(). */
@@ -1255,8 +1259,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 	if (partscan)
 		clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
 	if (!err && size_changed) {
-		loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit,
-					   lo->lo_backing_file);
+		loff_t new_size = lo_calculate_size(lo, lo->lo_backing_file);
 		loop_set_size(lo, new_size);
 	}
 out_unlock:
@@ -1399,7 +1402,7 @@ static int loop_set_capacity(struct loop_device *lo)
 	if (unlikely(lo->lo_state != Lo_bound))
 		return -ENXIO;
 
-	size = get_loop_size(lo, lo->lo_backing_file);
+	size = lo_calculate_size(lo, lo->lo_backing_file);
 	loop_set_size(lo, size);
 
 	return 0;