Merge tag 'for-6.13/block-20241118' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe updates via Keith:
      - Use uring_cmd helper (Pavel)
      - Host Memory Buffer allocation enhancements (Christoph)
      - Target persistent reservation support (Guixin)
      - Persistent reservation tracing (Guixen)
      - NVMe 2.1 specification support (Keith)
      - Rotational Meta Support (Matias, Wang, Keith)
      - Volatile cache detection enhancment (Guixen)

 - MD updates via Song:
      - Maintainers update
      - raid5 sync IO fix
      - Enhance handling of faulty and blocked devices
      - raid5-ppl atomic improvement
      - md-bitmap fix

 - Support for manually defining embedded partition tables

 - Zone append fixes and cleanups

 - Stop sending the queued requests in the plug list to the driver
   ->queue_rqs() handle in reverse order.

 - Zoned write plug cleanups

 - Cleanups disk stats tracking and add support for disk stats for
   passthrough IO

 - Add preparatory support for file system atomic writes

 - Add lockdep support for queue freezing. Already found a bunch of
   issues, and some fixes for that are in here. More will be coming.

 - Fix race between queue stopping/quiescing and IO queueing

 - ublk recovery improvements

 - Fix ublk mmap for 64k pages

 - Various fixes and cleanups

* tag 'for-6.13/block-20241118' of git://git.kernel.dk/linux: (118 commits)
  MAINTAINERS: Update git tree for mdraid subsystem
  block: make struct rq_list available for !CONFIG_BLOCK
  block/genhd: use seq_put_decimal_ull for diskstats decimal values
  block: don't reorder requests in blk_mq_add_to_batch
  block: don't reorder requests in blk_add_rq_to_plug
  block: add a rq_list type
  block: remove rq_list_move
  virtio_blk: reverse request order in virtio_queue_rqs
  nvme-pci: reverse request order in nvme_queue_rqs
  btrfs: validate queue limits
  block: export blk_validate_limits
  nvmet: add tracing of reservation commands
  nvme: parse reservation commands's action and rtype to string
  nvmet: report ns's vwc not present
  md/raid5: Increase r5conf.cache_name size
  block: remove the ioprio field from struct request
  block: remove the write_hint field from struct request
  nvme: check ns's volatile write cache not present
  nvme: add rotational support
  nvme: use command set independent id ns if available
  ...

1 files changed, 68 insertions, 27 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c2cc3c146d74..a1fd0ddce5cf 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -25,6 +25,7 @@
 #include <linux/uuid.h>
 #include <linux/xarray.h>
 #include <linux/file.h>
+#include <linux/lockdep.h>
 
 struct module;
 struct request_queue;
@@ -194,7 +195,7 @@ struct gendisk {
 	unsigned int		nr_zones;
 	unsigned int		zone_capacity;
 	unsigned int		last_zone_capacity;
-	unsigned long		*conv_zones_bitmap;
+	unsigned long __rcu	*conv_zones_bitmap;
 	unsigned int            zone_wplugs_hash_bits;
 	spinlock_t              zone_wplugs_lock;
 	struct mempool_s	*zone_wplugs_pool;
@@ -349,6 +350,9 @@ typedef unsigned int __bitwise blk_flags_t;
 /* I/O topology is misaligned */
 #define BLK_FLAG_MISALIGNED		((__force blk_flags_t)(1u << 1))
 
+/* passthrough command IO accounting */
+#define BLK_FLAG_IOSTATS_PASSTHROUGH	((__force blk_flags_t)(1u << 2))
+
 struct queue_limits {
 	blk_features_t		features;
 	blk_flags_t		flags;
@@ -371,6 +375,7 @@ struct queue_limits {
 	unsigned int		max_user_discard_sectors;
 	unsigned int		max_secure_erase_sectors;
 	unsigned int		max_write_zeroes_sectors;
+	unsigned int		max_hw_zone_append_sectors;
 	unsigned int		max_zone_append_sectors;
 	unsigned int		discard_granularity;
 	unsigned int		discard_alignment;
@@ -471,6 +476,11 @@ struct request_queue {
 	struct xarray		hctx_table;
 
 	struct percpu_ref	q_usage_counter;
+	struct lock_class_key	io_lock_cls_key;
+	struct lockdep_map	io_lockdep_map;
+
+	struct lock_class_key	q_lock_cls_key;
+	struct lockdep_map	q_lockdep_map;
 
 	struct request		*last_merge;
 
@@ -566,6 +576,10 @@ struct request_queue {
 	struct throtl_data *td;
 #endif
 	struct rcu_head		rcu_head;
+#ifdef CONFIG_LOCKDEP
+	struct task_struct	*mq_freeze_owner;
+	int			mq_freeze_owner_depth;
+#endif
 	wait_queue_head_t	mq_freeze_wq;
 	/*
 	 * Protect concurrent access to q_usage_counter by
@@ -617,6 +631,8 @@ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
 	test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
 #define blk_queue_nonrot(q)	(!((q)->limits.features & BLK_FEAT_ROTATIONAL))
 #define blk_queue_io_stat(q)	((q)->limits.features & BLK_FEAT_IO_STAT)
+#define blk_queue_passthrough_stat(q)	\
+	((q)->limits.flags & BLK_FLAG_IOSTATS_PASSTHROUGH)
 #define blk_queue_dax(q)	((q)->limits.features & BLK_FEAT_DAX)
 #define blk_queue_pci_p2pdma(q)	((q)->limits.features & BLK_FEAT_PCI_P2PDMA)
 #ifdef CONFIG_BLK_RQ_ALLOC_TIME
@@ -725,6 +741,9 @@ static inline unsigned int blk_queue_depth(struct request_queue *q)
 #define for_each_bio(_bio)		\
 	for (; _bio; _bio = _bio->bi_next)
 
+int __must_check add_disk_fwnode(struct device *parent, struct gendisk *disk,
+				 const struct attribute_group **groups,
+				 struct fwnode_handle *fwnode);
 int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 				 const struct attribute_group **groups);
 static inline int __must_check add_disk(struct gendisk *disk)
@@ -929,6 +948,7 @@ queue_limits_start_update(struct request_queue *q)
 int queue_limits_commit_update(struct request_queue *q,
 		struct queue_limits *lim);
 int queue_limits_set(struct request_queue *q, struct queue_limits *lim);
+int blk_validate_limits(struct queue_limits *lim);
 
 /**
  * queue_limits_cancel_update - cancel an atomic update of queue limits
@@ -986,6 +1006,11 @@ extern void blk_put_queue(struct request_queue *);
 
 void blk_mark_disk_dead(struct gendisk *disk);
 
+struct rq_list {
+	struct request *head;
+	struct request *tail;
+};
+
 #ifdef CONFIG_BLOCK
 /*
  * blk_plug permits building a queue of related requests by holding the I/O
@@ -999,10 +1024,10 @@ void blk_mark_disk_dead(struct gendisk *disk);
  * blk_flush_plug() is called.
  */
 struct blk_plug {
-	struct request *mq_list; /* blk-mq requests */
+	struct rq_list mq_list; /* blk-mq requests */
 
 	/* if ios_left is > 1, we can batch tag/rq allocations */
-	struct request *cached_rq;
+	struct rq_list cached_rqs;
 	u64 cur_ktime;
 	unsigned short nr_ios;
 
@@ -1145,6 +1170,11 @@ enum blk_default_limits {
  */
 #define BLK_DEF_MAX_SECTORS_CAP	2560u
 
+static inline struct queue_limits *bdev_limits(struct block_device *bdev)
+{
+	return &bdev_get_queue(bdev)->limits;
+}
+
 static inline unsigned long queue_segment_boundary(const struct request_queue *q)
 {
 	return q->limits.seg_boundary_mask;
@@ -1185,25 +1215,9 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q)
 	return q->limits.max_segment_size;
 }
 
-static inline unsigned int
-queue_limits_max_zone_append_sectors(const struct queue_limits *l)
-{
-	unsigned int max_sectors = min(l->chunk_sectors, l->max_hw_sectors);
-
-	return min_not_zero(l->max_zone_append_sectors, max_sectors);
-}
-
-static inline unsigned int queue_max_zone_append_sectors(struct request_queue *q)
-{
-	if (!blk_queue_is_zoned(q))
-		return 0;
-
-	return queue_limits_max_zone_append_sectors(&q->limits);
-}
-
 static inline bool queue_emulates_zone_append(struct request_queue *q)
 {
-	return blk_queue_is_zoned(q) && !q->limits.max_zone_append_sectors;
+	return blk_queue_is_zoned(q) && !q->limits.max_hw_zone_append_sectors;
 }
 
 static inline bool bdev_emulates_zone_append(struct block_device *bdev)
@@ -1214,7 +1228,7 @@ static inline bool bdev_emulates_zone_append(struct block_device *bdev)
 static inline unsigned int
 bdev_max_zone_append_sectors(struct block_device *bdev)
 {
-	return queue_max_zone_append_sectors(bdev_get_queue(bdev));
+	return bdev_limits(bdev)->max_zone_append_sectors;
 }
 
 static inline unsigned int bdev_max_segments(struct block_device *bdev)
@@ -1279,23 +1293,23 @@ unsigned int bdev_discard_alignment(struct block_device *bdev);
 
 static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev)
 {
-	return bdev_get_queue(bdev)->limits.max_discard_sectors;
+	return bdev_limits(bdev)->max_discard_sectors;
 }
 
 static inline unsigned int bdev_discard_granularity(struct block_device *bdev)
 {
-	return bdev_get_queue(bdev)->limits.discard_granularity;
+	return bdev_limits(bdev)->discard_granularity;
 }
 
 static inline unsigned int
 bdev_max_secure_erase_sectors(struct block_device *bdev)
 {
-	return bdev_get_queue(bdev)->limits.max_secure_erase_sectors;
+	return bdev_limits(bdev)->max_secure_erase_sectors;
 }
 
 static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev)
 {
-	return bdev_get_queue(bdev)->limits.max_write_zeroes_sectors;
+	return bdev_limits(bdev)->max_write_zeroes_sectors;
 }
 
 static inline bool bdev_nonrot(struct block_device *bdev)
@@ -1331,7 +1345,7 @@ static inline bool bdev_write_cache(struct block_device *bdev)
 
 static inline bool bdev_fua(struct block_device *bdev)
 {
-	return bdev_get_queue(bdev)->limits.features & BLK_FEAT_FUA;
+	return bdev_limits(bdev)->features & BLK_FEAT_FUA;
 }
 
 static inline bool bdev_nowait(struct block_device *bdev)
@@ -1376,6 +1390,33 @@ static inline bool bdev_is_zone_start(struct block_device *bdev,
 	return bdev_offset_from_zone_start(bdev, sector) == 0;
 }
 
+/**
+ * bdev_zone_is_seq - check if a sector belongs to a sequential write zone
+ * @bdev:	block device to check
+ * @sector:	sector number
+ *
+ * Check if @sector on @bdev is contained in a sequential write required zone.
+ */
+static inline bool bdev_zone_is_seq(struct block_device *bdev, sector_t sector)
+{
+	bool is_seq = false;
+
+#if IS_ENABLED(CONFIG_BLK_DEV_ZONED)
+	if (bdev_is_zoned(bdev)) {
+		struct gendisk *disk = bdev->bd_disk;
+		unsigned long *bitmap;
+
+		rcu_read_lock();
+		bitmap = rcu_dereference(disk->conv_zones_bitmap);
+		is_seq = !bitmap ||
+			!test_bit(disk_zone_no(disk, sector), bitmap);
+		rcu_read_unlock();
+	}
+#endif
+
+	return is_seq;
+}
+
 static inline int queue_dma_alignment(const struct request_queue *q)
 {
 	return q->limits.dma_alignment;
@@ -1648,7 +1689,7 @@ int bdev_thaw(struct block_device *bdev);
 void bdev_fput(struct file *bdev_file);
 
 struct io_comp_batch {
-	struct request *req_list;
+	struct rq_list req_list;
 	bool need_ts;
 	void (*complete)(struct io_comp_batch *);
 };