Merge tag 'for-6.8/block-2024-01-08' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:
 "Pretty quiet round this time around. This contains:

   - NVMe updates via Keith:
        - nvme fabrics spec updates (Guixin, Max)
        - nvme target udpates (Guixin, Evan)
        - nvme attribute refactoring (Daniel)
        - nvme-fc numa fix (Keith)

   - MD updates via Song:
        - Fix/Cleanup RCU usage from conf->disks[i].rdev (Yu Kuai)
        - Fix raid5 hang issue (Junxiao Bi)
        - Add Yu Kuai as Reviewer of the md subsystem
        - Remove deprecated flavors (Song Liu)
        - raid1 read error check support (Li Nan)
        - Better handle events off-by-1 case (Alex Lyakas)

   - Efficiency improvements for passthrough (Kundan)

   - Support for mapping integrity data directly (Keith)

   - Zoned write fix (Damien)

   - rnbd fixes (Kees, Santosh, Supriti)

   - Default to a sane discard size granularity (Christoph)

   - Make the default max transfer size naming less confusing
     (Christoph)

   - Remove support for deprecated host aware zoned model (Christoph)

   - Misc fixes (me, Li, Matthew, Min, Ming, Randy, liyouhong, Daniel,
     Bart, Christoph)"

* tag 'for-6.8/block-2024-01-08' of git://git.kernel.dk/linux: (78 commits)
  block: Treat sequential write preferred zone type as invalid
  block: remove disk_clear_zoned
  sd: remove the !ZBC && blk_queue_is_zoned case in sd_read_block_characteristics
  drivers/block/xen-blkback/common.h: Fix spelling typo in comment
  blk-cgroup: fix rcu lockdep warning in blkg_lookup()
  blk-cgroup: don't use removal safe list iterators
  block: floor the discard granularity to the physical block size
  mtd_blkdevs: use the default discard granularity
  bcache: use the default discard granularity
  zram: use the default discard granularity
  null_blk: use the default discard granularity
  nbd: use the default discard granularity
  ubd: use the default discard granularity
  block: default the discard granularity to sector size
  bcache: discard_granularity should not be smaller than a sector
  block: remove two comments in bio_split_discard
  block: rename and document BLK_DEF_MAX_SECTORS
  loop: don't abuse BLK_DEF_MAX_SECTORS
  aoe: don't abuse BLK_DEF_MAX_SECTORS
  null_blk: don't cap max_hw_sectors to BLK_DEF_MAX_SECTORS
  ...

1 files changed, 68 insertions, 91 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c30a98e08423..99e4f5e72213 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -266,18 +266,6 @@ static inline bool blk_op_is_passthrough(blk_opf_t op)
 }
 
 /*
- * Zoned block device models (zoned limit).
- *
- * Note: This needs to be ordered from the least to the most severe
- * restrictions for the inheritance in blk_stack_limits() to work.
- */
-enum blk_zoned_model {
-	BLK_ZONED_NONE = 0,	/* Regular block device */
-	BLK_ZONED_HA,		/* Host-aware zoned block device */
-	BLK_ZONED_HM,		/* Host-managed zoned block device */
-};
-
-/*
  * BLK_BOUNCE_NONE:	never bounce (default)
  * BLK_BOUNCE_HIGH:	bounce all highmem pages
  */
@@ -318,7 +306,7 @@ struct queue_limits {
 	unsigned char		misaligned;
 	unsigned char		discard_misaligned;
 	unsigned char		raid_partial_stripes_expensive;
-	enum blk_zoned_model	zoned;
+	bool			zoned;
 
 	/*
 	 * Drivers that set dma_alignment to less than 511 must be prepared to
@@ -331,24 +319,15 @@ struct queue_limits {
 typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
 			       void *data);
 
-void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model);
+void disk_set_zoned(struct gendisk *disk);
 
-#ifdef CONFIG_BLK_DEV_ZONED
 #define BLK_ALL_ZONES  ((unsigned int)-1)
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
-			unsigned int nr_zones, report_zones_cb cb, void *data);
-unsigned int bdev_nr_zones(struct block_device *bdev);
-extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
-			    sector_t sectors, sector_t nr_sectors,
-			    gfp_t gfp_mask);
+		unsigned int nr_zones, report_zones_cb cb, void *data);
+int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
+		sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask);
 int blk_revalidate_disk_zones(struct gendisk *disk,
-			      void (*update_driver_data)(struct gendisk *disk));
-#else /* CONFIG_BLK_DEV_ZONED */
-static inline unsigned int bdev_nr_zones(struct block_device *bdev)
-{
-	return 0;
-}
-#endif /* CONFIG_BLK_DEV_ZONED */
+		void (*update_driver_data)(struct gendisk *disk));
 
 /*
  * Independent access ranges: struct blk_independent_access_range describes
@@ -378,59 +357,51 @@ struct blk_independent_access_ranges {
 };
 
 struct request_queue {
-	struct request		*last_merge;
-	struct elevator_queue	*elevator;
-
-	struct percpu_ref	q_usage_counter;
+	/*
+	 * The queue owner gets to use this for whatever they like.
+	 * ll_rw_blk doesn't touch it.
+	 */
+	void			*queuedata;
 
-	struct blk_queue_stats	*stats;
-	struct rq_qos		*rq_qos;
-	struct mutex		rq_qos_mutex;
+	struct elevator_queue	*elevator;
 
 	const struct blk_mq_ops	*mq_ops;
 
 	/* sw queues */
 	struct blk_mq_ctx __percpu	*queue_ctx;
 
+	/*
+	 * various queue flags, see QUEUE_* below
+	 */
+	unsigned long		queue_flags;
+
+	unsigned int		rq_timeout;
+
 	unsigned int		queue_depth;
 
+	refcount_t		refs;
+
 	/* hw dispatch queues */
-	struct xarray		hctx_table;
 	unsigned int		nr_hw_queues;
+	struct xarray		hctx_table;
 
-	/*
-	 * The queue owner gets to use this for whatever they like.
-	 * ll_rw_blk doesn't touch it.
-	 */
-	void			*queuedata;
-
-	/*
-	 * various queue flags, see QUEUE_* below
-	 */
-	unsigned long		queue_flags;
-	/*
-	 * Number of contexts that have called blk_set_pm_only(). If this
-	 * counter is above zero then only RQF_PM requests are processed.
-	 */
-	atomic_t		pm_only;
+	struct percpu_ref	q_usage_counter;
 
-	/*
-	 * ida allocated id for this queue.  Used to index queues from
-	 * ioctx.
-	 */
-	int			id;
+	struct request		*last_merge;
 
 	spinlock_t		queue_lock;
 
-	struct gendisk		*disk;
+	int			quiesce_depth;
 
-	refcount_t		refs;
+	struct gendisk		*disk;
 
 	/*
 	 * mq queue kobject
 	 */
 	struct kobject *mq_kobj;
 
+	struct queue_limits	limits;
+
 #ifdef  CONFIG_BLK_DEV_INTEGRITY
 	struct blk_integrity integrity;
 #endif	/* CONFIG_BLK_DEV_INTEGRITY */
@@ -441,24 +412,40 @@ struct request_queue {
 #endif
 
 	/*
-	 * queue settings
+	 * Number of contexts that have called blk_set_pm_only(). If this
+	 * counter is above zero then only RQF_PM requests are processed.
 	 */
-	unsigned long		nr_requests;	/* Max # of requests */
+	atomic_t		pm_only;
+
+	struct blk_queue_stats	*stats;
+	struct rq_qos		*rq_qos;
+	struct mutex		rq_qos_mutex;
+
+	/*
+	 * ida allocated id for this queue.  Used to index queues from
+	 * ioctx.
+	 */
+	int			id;
 
 	unsigned int		dma_pad_mask;
 
+	/*
+	 * queue settings
+	 */
+	unsigned long		nr_requests;	/* Max # of requests */
+
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 	struct blk_crypto_profile *crypto_profile;
 	struct kobject *crypto_kobject;
 #endif
 
-	unsigned int		rq_timeout;
-
 	struct timer_list	timeout;
 	struct work_struct	timeout_work;
 
 	atomic_t		nr_active_requests_shared_tags;
 
+	unsigned int		required_elevator_features;
+
 	struct blk_mq_tags	*sched_shared_tags;
 
 	struct list_head	icq_list;
@@ -469,11 +456,12 @@ struct request_queue {
 	struct mutex		blkcg_mutex;
 #endif
 
-	struct queue_limits	limits;
+	int			node;
 
-	unsigned int		required_elevator_features;
+	spinlock_t		requeue_lock;
+	struct list_head	requeue_list;
+	struct delayed_work	requeue_work;
 
-	int			node;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	struct blk_trace __rcu	*blk_trace;
 #endif
@@ -483,10 +471,6 @@ struct request_queue {
 	struct blk_flush_queue	*fq;
 	struct list_head	flush_list;
 
-	struct list_head	requeue_list;
-	spinlock_t		requeue_lock;
-	struct delayed_work	requeue_work;
-
 	struct mutex		sysfs_lock;
 	struct mutex		sysfs_dir_lock;
 
@@ -511,8 +495,6 @@ struct request_queue {
 	 */
 	struct mutex		mq_freeze_lock;
 
-	int			quiesce_depth;
-
 	struct blk_mq_tag_set	*tag_set;
 	struct list_head	tag_set_list;
 
@@ -625,26 +607,14 @@ static inline enum rpm_status queue_rpm_status(struct request_queue *q)
 }
 #endif
 
-static inline enum blk_zoned_model
-blk_queue_zoned_model(struct request_queue *q)
-{
-	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED))
-		return q->limits.zoned;
-	return BLK_ZONED_NONE;
-}
-
 static inline bool blk_queue_is_zoned(struct request_queue *q)
 {
-	switch (blk_queue_zoned_model(q)) {
-	case BLK_ZONED_HA:
-	case BLK_ZONED_HM:
-		return true;
-	default:
-		return false;
-	}
+	return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && q->limits.zoned;
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
+unsigned int bdev_nr_zones(struct block_device *bdev);
+
 static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
 	return blk_queue_is_zoned(disk->queue) ? disk->nr_zones : 0;
@@ -689,6 +659,11 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
 }
 
 #else /* CONFIG_BLK_DEV_ZONED */
+static inline unsigned int bdev_nr_zones(struct block_device *bdev)
+{
+	return 0;
+}
+
 static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
 	return 0;
@@ -1082,7 +1057,14 @@ enum blk_default_limits {
 	BLK_SEG_BOUNDARY_MASK	= 0xFFFFFFFFUL,
 };
 
-#define BLK_DEF_MAX_SECTORS 2560u
+/*
+ * Default upper limit for the software max_sectors limit used for
+ * regular file system I/O.  This can be increased through sysfs.
+ *
+ * Not to be confused with the max_hw_sector limit that is entirely
+ * controlled by the driver, usually based on hardware limits.
+ */
+#define BLK_DEF_MAX_SECTORS_CAP	2560u
 
 static inline unsigned long queue_segment_boundary(const struct request_queue *q)
 {
@@ -1261,11 +1243,6 @@ static inline bool bdev_nowait(struct block_device *bdev)
 	return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags);
 }
 
-static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
-{
-	return blk_queue_zoned_model(bdev_get_queue(bdev));
-}
-
 static inline bool bdev_is_zoned(struct block_device *bdev)
 {
 	return blk_queue_is_zoned(bdev_get_queue(bdev));