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
  ...

10 files changed, 298 insertions, 101 deletions

diff --git a/include/linux/bio-integrity.h b/include/linux/bio-integrity.h
index dd831c269e99..dbf0f74c1529 100644
--- a/include/linux/bio-integrity.h
+++ b/include/linux/bio-integrity.h
@@ -72,7 +72,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, gfp_t gfp,
 		unsigned int nr);
 int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len,
 		unsigned int offset);
-int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len, u32 seed);
+int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len);
 void bio_integrity_unmap_user(struct bio *bio);
 bool bio_integrity_prep(struct bio *bio);
 void bio_integrity_advance(struct bio *bio, unsigned int bytes_done);
@@ -99,7 +99,7 @@ static inline void bioset_integrity_free(struct bio_set *bs)
 }
 
 static inline int bio_integrity_map_user(struct bio *bio, void __user *ubuf,
-					 ssize_t len, u32 seed)
+					 ssize_t len)
 {
 	return -EINVAL;
 }
diff --git a/include/linux/bio.h b/include/linux/bio.h
index faceadb040f9..60830a6a5939 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -418,8 +418,6 @@ bool __must_check bio_add_folio(struct bio *bio, struct folio *folio,
 				size_t len, size_t off);
 extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
 			   unsigned int, unsigned int);
-int bio_add_zone_append_page(struct bio *bio, struct page *page,
-			     unsigned int len, unsigned int offset);
 void __bio_add_page(struct bio *bio, struct page *page,
 		unsigned int len, unsigned int off);
 void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len,
@@ -677,6 +675,23 @@ static inline void bio_clear_polled(struct bio *bio)
 	bio->bi_opf &= ~REQ_POLLED;
 }
 
+/**
+ * bio_is_zone_append - is this a zone append bio?
+ * @bio:	bio to check
+ *
+ * Check if @bio is a zone append operation.  Core block layer code and end_io
+ * handlers must use this instead of an open coded REQ_OP_ZONE_APPEND check
+ * because the block layer can rewrite REQ_OP_ZONE_APPEND to REQ_OP_WRITE if
+ * it is not natively supported.
+ */
+static inline bool bio_is_zone_append(struct bio *bio)
+{
+	if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED))
+		return false;
+	return bio_op(bio) == REQ_OP_ZONE_APPEND ||
+		bio_flagged(bio, BIO_EMULATES_ZONE_APPEND);
+}
+
 struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
 		unsigned int nr_pages, blk_opf_t opf, gfp_t gfp);
 struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new);
diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h
index 676f8f860c47..c7eae0bfb013 100644
--- a/include/linux/blk-integrity.h
+++ b/include/linux/blk-integrity.h
@@ -28,7 +28,7 @@ static inline bool queue_limits_stack_integrity_bdev(struct queue_limits *t,
 int blk_rq_map_integrity_sg(struct request *, struct scatterlist *);
 int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
 int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf,
-			      ssize_t bytes, u32 seed);
+			      ssize_t bytes);
 
 static inline bool
 blk_integrity_queue_supports_integrity(struct request_queue *q)
@@ -104,8 +104,7 @@ static inline int blk_rq_map_integrity_sg(struct request *q,
 }
 static inline int blk_rq_integrity_map_user(struct request *rq,
 					    void __user *ubuf,
-					    ssize_t bytes,
-					    u32 seed)
+					    ssize_t bytes)
 {
 	return -EINVAL;
 }
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 4fecf46ef681..c596e0e4cb75 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -156,9 +156,6 @@ struct request {
 	struct blk_crypto_keyslot *crypt_keyslot;
 #endif
 
-	enum rw_hint write_hint;
-	unsigned short ioprio;
-
 	enum mq_rq_state state;
 	atomic_t ref;
 
@@ -222,7 +219,9 @@ static inline bool blk_rq_is_passthrough(struct request *rq)
 
 static inline unsigned short req_get_ioprio(struct request *req)
 {
-	return req->ioprio;
+	if (req->bio)
+		return req->bio->bi_ioprio;
+	return 0;
 }
 
 #define rq_data_dir(rq)		(op_is_write(req_op(rq)) ? WRITE : READ)
@@ -230,62 +229,61 @@ static inline unsigned short req_get_ioprio(struct request *req)
 #define rq_dma_dir(rq) \
 	(op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE)
 
-#define rq_list_add(listptr, rq)	do {		\
-	(rq)->rq_next = *(listptr);			\
-	*(listptr) = rq;				\
-} while (0)
-
-#define rq_list_add_tail(lastpptr, rq)	do {		\
-	(rq)->rq_next = NULL;				\
-	**(lastpptr) = rq;				\
-	*(lastpptr) = &rq->rq_next;			\
-} while (0)
-
-#define rq_list_pop(listptr)				\
-({							\
-	struct request *__req = NULL;			\
-	if ((listptr) && *(listptr))	{		\
-		__req = *(listptr);			\
-		*(listptr) = __req->rq_next;		\
-	}						\
-	__req;						\
-})
+static inline int rq_list_empty(const struct rq_list *rl)
+{
+	return rl->head == NULL;
+}
 
-#define rq_list_peek(listptr)				\
-({							\
-	struct request *__req = NULL;			\
-	if ((listptr) && *(listptr))			\
-		__req = *(listptr);			\
-	__req;						\
-})
+static inline void rq_list_init(struct rq_list *rl)
+{
+	rl->head = NULL;
+	rl->tail = NULL;
+}
 
-#define rq_list_for_each(listptr, pos)			\
-	for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos))
+static inline void rq_list_add_tail(struct rq_list *rl, struct request *rq)
+{
+	rq->rq_next = NULL;
+	if (rl->tail)
+		rl->tail->rq_next = rq;
+	else
+		rl->head = rq;
+	rl->tail = rq;
+}
 
-#define rq_list_for_each_safe(listptr, pos, nxt)			\
-	for (pos = rq_list_peek((listptr)), nxt = rq_list_next(pos);	\
-		pos; pos = nxt, nxt = pos ? rq_list_next(pos) : NULL)
+static inline void rq_list_add_head(struct rq_list *rl, struct request *rq)
+{
+	rq->rq_next = rl->head;
+	rl->head = rq;
+	if (!rl->tail)
+		rl->tail = rq;
+}
 
-#define rq_list_next(rq)	(rq)->rq_next
-#define rq_list_empty(list)	((list) == (struct request *) NULL)
+static inline struct request *rq_list_pop(struct rq_list *rl)
+{
+	struct request *rq = rl->head;
 
-/**
- * rq_list_move() - move a struct request from one list to another
- * @src: The source list @rq is currently in
- * @dst: The destination list that @rq will be appended to
- * @rq: The request to move
- * @prev: The request preceding @rq in @src (NULL if @rq is the head)
- */
-static inline void rq_list_move(struct request **src, struct request **dst,
-				struct request *rq, struct request *prev)
+	if (rq) {
+		rl->head = rl->head->rq_next;
+		if (!rl->head)
+			rl->tail = NULL;
+		rq->rq_next = NULL;
+	}
+
+	return rq;
+}
+
+static inline struct request *rq_list_peek(struct rq_list *rl)
 {
-	if (prev)
-		prev->rq_next = rq->rq_next;
-	else
-		*src = rq->rq_next;
-	rq_list_add(dst, rq);
+	return rl->head;
 }
 
+#define rq_list_for_each(rl, pos)					\
+	for (pos = rq_list_peek((rl)); (pos); pos = pos->rq_next)
+
+#define rq_list_for_each_safe(rl, pos, nxt)				\
+	for (pos = rq_list_peek((rl)), nxt = pos->rq_next;		\
+		pos; pos = nxt, nxt = pos ? pos->rq_next : NULL)
+
 /**
  * enum blk_eh_timer_return - How the timeout handler should proceed
  * @BLK_EH_DONE: The block driver completed the command or will complete it at
@@ -577,7 +575,7 @@ struct blk_mq_ops {
 	 * empty the @rqlist completely, then the rest will be queued
 	 * individually by the block layer upon return.
 	 */
-	void (*queue_rqs)(struct request **rqlist);
+	void (*queue_rqs)(struct rq_list *rqlist);
 
 	/**
 	 * @get_budget: Reserve budget before queue request, once .queue_rq is
@@ -857,12 +855,6 @@ void blk_mq_end_request_batch(struct io_comp_batch *ib);
  */
 static inline bool blk_mq_need_time_stamp(struct request *rq)
 {
-	/*
-	 * passthrough io doesn't use iostat accounting, cgroup stats
-	 * and io scheduler functionalities.
-	 */
-	if (blk_rq_is_passthrough(rq))
-		return false;
 	return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED));
 }
 
@@ -892,7 +884,7 @@ static inline bool blk_mq_add_to_batch(struct request *req,
 	else if (iob->complete != complete)
 		return false;
 	iob->need_ts |= blk_mq_need_time_stamp(req);
-	rq_list_add(&iob->req_list, req);
+	rq_list_add_tail(&iob->req_list, req);
 	return true;
 }
 
@@ -925,6 +917,8 @@ void blk_freeze_queue_start(struct request_queue *q);
 void blk_mq_freeze_queue_wait(struct request_queue *q);
 int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
 				     unsigned long timeout);
+void blk_mq_unfreeze_queue_non_owner(struct request_queue *q);
+void blk_freeze_queue_start_non_owner(struct request_queue *q);
 
 void blk_mq_map_queues(struct blk_mq_queue_map *qmap);
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
@@ -989,7 +983,6 @@ static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
 	rq->nr_phys_segments = nr_segs;
 	rq->__data_len = bio->bi_iter.bi_size;
 	rq->bio = rq->biotail = bio;
-	rq->ioprio = bio_prio(bio);
 }
 
 void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx,
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 *);
 };
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index b58d9405d65e..0a6e22038ce3 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -327,7 +327,8 @@ struct nvme_id_ctrl {
 	__le32			sanicap;
 	__le32			hmminds;
 	__le16			hmmaxd;
-	__u8			rsvd338[4];
+	__le16			nvmsetidmax;
+	__le16			endgidmax;
 	__u8			anatt;
 	__u8			anacap;
 	__le32			anagrpmax;
@@ -522,6 +523,7 @@ enum {
 	NVME_ID_CNS_NS_DESC_LIST	= 0x03,
 	NVME_ID_CNS_CS_NS		= 0x05,
 	NVME_ID_CNS_CS_CTRL		= 0x06,
+	NVME_ID_CNS_NS_ACTIVE_LIST_CS	= 0x07,
 	NVME_ID_CNS_NS_CS_INDEP		= 0x08,
 	NVME_ID_CNS_NS_PRESENT_LIST	= 0x10,
 	NVME_ID_CNS_NS_PRESENT		= 0x11,
@@ -530,6 +532,7 @@ enum {
 	NVME_ID_CNS_SCNDRY_CTRL_LIST	= 0x15,
 	NVME_ID_CNS_NS_GRANULARITY	= 0x16,
 	NVME_ID_CNS_UUID_LIST		= 0x17,
+	NVME_ID_CNS_ENDGRP_LIST		= 0x19,
 };
 
 enum {
@@ -560,6 +563,8 @@ enum {
 	NVME_NS_FLBAS_LBA_SHIFT	= 1,
 	NVME_NS_FLBAS_META_EXT	= 0x10,
 	NVME_NS_NMIC_SHARED	= 1 << 0,
+	NVME_NS_ROTATIONAL	= 1 << 4,
+	NVME_NS_VWC_NOT_PRESENT = 1 << 5,
 	NVME_LBAF_RP_BEST	= 0,
 	NVME_LBAF_RP_BETTER	= 1,
 	NVME_LBAF_RP_GOOD	= 2,
@@ -617,6 +622,40 @@ enum {
 	NVME_NIDT_CSI		= 0x04,
 };
 
+struct nvme_endurance_group_log {
+	__u8	egcw;
+	__u8	egfeat;
+	__u8	rsvd2;
+	__u8	avsp;
+	__u8	avspt;
+	__u8	pused;
+	__le16	did;
+	__u8	rsvd8[24];
+	__u8	ee[16];
+	__u8	dur[16];
+	__u8	duw[16];
+	__u8	muw[16];
+	__u8	hrc[16];
+	__u8	hwc[16];
+	__u8	mdie[16];
+	__u8	neile[16];
+	__u8	tegcap[16];
+	__u8	uegcap[16];
+	__u8	rsvd192[320];
+};
+
+struct nvme_rotational_media_log {
+	__le16	endgid;
+	__le16	numa;
+	__le16	nrs;
+	__u8	rsvd6[2];
+	__le32	spinc;
+	__le32	fspinc;
+	__le32	ldc;
+	__le32	fldc;
+	__u8	rsvd24[488];
+};
+
 struct nvme_smart_log {
 	__u8			critical_warning;
 	__u8			temperature[2];
@@ -1244,6 +1283,7 @@ enum {
 	NVME_FEAT_WRITE_PROTECT	= 0x84,
 	NVME_FEAT_VENDOR_START	= 0xC0,
 	NVME_FEAT_VENDOR_END	= 0xFF,
+	NVME_LOG_SUPPORTED	= 0x00,
 	NVME_LOG_ERROR		= 0x01,
 	NVME_LOG_SMART		= 0x02,
 	NVME_LOG_FW_SLOT	= 0x03,
@@ -1254,6 +1294,8 @@ enum {
 	NVME_LOG_TELEMETRY_CTRL = 0x08,
 	NVME_LOG_ENDURANCE_GROUP = 0x09,
 	NVME_LOG_ANA		= 0x0c,
+	NVME_LOG_FEATURES	= 0x12,
+	NVME_LOG_RMI		= 0x16,
 	NVME_LOG_DISC		= 0x70,
 	NVME_LOG_RESERVATION	= 0x80,
 	NVME_FWACT_REPL		= (0 << 3),
@@ -1261,6 +1303,24 @@ enum {
 	NVME_FWACT_ACTV		= (2 << 3),
 };
 
+struct nvme_supported_log {
+	__le32	lids[256];
+};
+
+enum {
+	NVME_LIDS_LSUPP	= 1 << 0,
+};
+
+struct nvme_supported_features_log {
+	__le32	fis[256];
+};
+
+enum {
+	NVME_FIS_FSUPP	= 1 << 0,
+	NVME_FIS_NSCPE	= 1 << 20,
+	NVME_FIS_CSCPE	= 1 << 21,
+};
+
 /* NVMe Namespace Write Protect State */
 enum {
 	NVME_NS_NO_WRITE_PROTECT = 0,
@@ -1281,7 +1341,8 @@ struct nvme_identify {
 	__u8			cns;
 	__u8			rsvd3;
 	__le16			ctrlid;
-	__u8			rsvd11[3];
+	__le16			cnssid;
+	__u8			rsvd11;
 	__u8			csi;
 	__u32			rsvd12[4];
 };
@@ -1389,7 +1450,7 @@ struct nvme_get_log_page_command {
 	__u8			lsp; /* upper 4 bits reserved */
 	__le16			numdl;
 	__le16			numdu;
-	__u16			rsvd11;
+	__le16			lsi;
 	union {
 		struct {
 			__le32 lpol;
@@ -2037,4 +2098,72 @@ struct nvme_completion {
 #define NVME_MINOR(ver)		(((ver) >> 8) & 0xff)
 #define NVME_TERTIARY(ver)	((ver) & 0xff)
 
+enum {
+	NVME_AEN_RESV_LOG_PAGE_AVALIABLE	= 0x00,
+};
+
+enum {
+	NVME_PR_LOG_EMPTY_LOG_PAGE			= 0x00,
+	NVME_PR_LOG_REGISTRATION_PREEMPTED		= 0x01,
+	NVME_PR_LOG_RESERVATION_RELEASED		= 0x02,
+	NVME_PR_LOG_RESERVATOIN_PREEMPTED		= 0x03,
+};
+
+enum {
+	NVME_PR_NOTIFY_BIT_REG_PREEMPTED		= 1,
+	NVME_PR_NOTIFY_BIT_RESV_RELEASED		= 2,
+	NVME_PR_NOTIFY_BIT_RESV_PREEMPTED		= 3,
+};
+
+struct nvme_pr_log {
+	__le64			count;
+	__u8			type;
+	__u8			nr_pages;
+	__u8			rsvd1[2];
+	__le32			nsid;
+	__u8			rsvd2[48];
+};
+
+struct nvmet_pr_register_data {
+	__le64	crkey;
+	__le64	nrkey;
+};
+
+struct nvmet_pr_acquire_data {
+	__le64	crkey;
+	__le64	prkey;
+};
+
+struct nvmet_pr_release_data {
+	__le64	crkey;
+};
+
+enum nvme_pr_capabilities {
+	NVME_PR_SUPPORT_PTPL				= 1,
+	NVME_PR_SUPPORT_WRITE_EXCLUSIVE			= 1 << 1,
+	NVME_PR_SUPPORT_EXCLUSIVE_ACCESS		= 1 << 2,
+	NVME_PR_SUPPORT_WRITE_EXCLUSIVE_REG_ONLY	= 1 << 3,
+	NVME_PR_SUPPORT_EXCLUSIVE_ACCESS_REG_ONLY	= 1 << 4,
+	NVME_PR_SUPPORT_WRITE_EXCLUSIVE_ALL_REGS	= 1 << 5,
+	NVME_PR_SUPPORT_EXCLUSIVE_ACCESS_ALL_REGS	= 1 << 6,
+	NVME_PR_SUPPORT_IEKEY_VER_1_3_DEF		= 1 << 7,
+};
+
+enum nvme_pr_register_action {
+	NVME_PR_REGISTER_ACT_REG		= 0,
+	NVME_PR_REGISTER_ACT_UNREG		= 1,
+	NVME_PR_REGISTER_ACT_REPLACE		= 1 << 1,
+};
+
+enum nvme_pr_acquire_action {
+	NVME_PR_ACQUIRE_ACT_ACQUIRE		= 0,
+	NVME_PR_ACQUIRE_ACT_PREEMPT		= 1,
+	NVME_PR_ACQUIRE_ACT_PREEMPT_AND_ABORT	= 1 << 1,
+};
+
+enum nvme_pr_release_action {
+	NVME_PR_RELEASE_ACT_RELEASE		= 0,
+	NVME_PR_RELEASE_ACT_CLEAR		= 1,
+};
+
 #endif /* _LINUX_NVME_H */
diff --git a/include/linux/sed-opal.h b/include/linux/sed-opal.h
index 2ac50822554e..80f33a93f944 100644
--- a/include/linux/sed-opal.h
+++ b/include/linux/sed-opal.h
@@ -52,6 +52,7 @@ static inline bool is_sed_ioctl(unsigned int cmd)
 	case IOC_OPAL_GET_GEOMETRY:
 	case IOC_OPAL_DISCOVERY:
 	case IOC_OPAL_REVERT_LSP:
+	case IOC_OPAL_SET_SID_PW:
 		return true;
 	}
 	return false;
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 1527d5d45e01..bd0ea07338eb 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -99,7 +99,7 @@ TRACE_EVENT(block_rq_requeue,
 		__entry->dev	   = rq->q->disk ? disk_devt(rq->q->disk) : 0;
 		__entry->sector    = blk_rq_trace_sector(rq);
 		__entry->nr_sector = blk_rq_trace_nr_sectors(rq);
-		__entry->ioprio    = rq->ioprio;
+		__entry->ioprio    = req_get_ioprio(rq);
 
 		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags);
 		__get_str(cmd)[0] = '\0';
@@ -136,7 +136,7 @@ DECLARE_EVENT_CLASS(block_rq_completion,
 		__entry->sector    = blk_rq_pos(rq);
 		__entry->nr_sector = nr_bytes >> 9;
 		__entry->error     = blk_status_to_errno(error);
-		__entry->ioprio    = rq->ioprio;
+		__entry->ioprio    = req_get_ioprio(rq);
 
 		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags);
 		__get_str(cmd)[0] = '\0';
@@ -209,7 +209,7 @@ DECLARE_EVENT_CLASS(block_rq,
 		__entry->sector    = blk_rq_trace_sector(rq);
 		__entry->nr_sector = blk_rq_trace_nr_sectors(rq);
 		__entry->bytes     = blk_rq_bytes(rq);
-		__entry->ioprio	   = rq->ioprio;
+		__entry->ioprio	   = req_get_ioprio(rq);
 
 		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags);
 		__get_str(cmd)[0] = '\0';
diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h
index d3994b7716bc..9025dd5a4f0f 100644
--- a/include/uapi/linux/sed-opal.h
+++ b/include/uapi/linux/sed-opal.h
@@ -215,5 +215,6 @@ struct opal_revert_lsp {
 #define IOC_OPAL_GET_GEOMETRY       _IOR('p', 238, struct opal_geometry)
 #define IOC_OPAL_DISCOVERY          _IOW('p', 239, struct opal_discovery)
 #define IOC_OPAL_REVERT_LSP         _IOW('p', 240, struct opal_revert_lsp)
+#define IOC_OPAL_SET_SID_PW         _IOW('p', 241, struct opal_new_pw)
 
 #endif /* _UAPI_SED_OPAL_H */
diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
index 12873639ea96..a8bc98bb69fc 100644
--- a/include/uapi/linux/ublk_cmd.h
+++ b/include/uapi/linux/ublk_cmd.h
@@ -147,8 +147,18 @@
  */
 #define UBLK_F_NEED_GET_DATA (1UL << 2)
 
+/*
+ * - Block devices are recoverable if ublk server exits and restarts
+ * - Outstanding I/O when ublk server exits is met with errors
+ * - I/O issued while there is no ublk server queues
+ */
 #define UBLK_F_USER_RECOVERY	(1UL << 3)
 
+/*
+ * - Block devices are recoverable if ublk server exits and restarts
+ * - Outstanding I/O when ublk server exits is reissued
+ * - I/O issued while there is no ublk server queues
+ */
 #define UBLK_F_USER_RECOVERY_REISSUE	(1UL << 4)
 
 /*
@@ -190,10 +200,18 @@
  */
 #define UBLK_F_ZONED (1ULL << 8)
 
+/*
+ * - Block devices are recoverable if ublk server exits and restarts
+ * - Outstanding I/O when ublk server exits is met with errors
+ * - I/O issued while there is no ublk server is met with errors
+ */
+#define UBLK_F_USER_RECOVERY_FAIL_IO (1ULL << 9)
+
 /* device state */
 #define UBLK_S_DEV_DEAD	0
 #define UBLK_S_DEV_LIVE	1
 #define UBLK_S_DEV_QUIESCED	2
+#define UBLK_S_DEV_FAIL_IO 	3
 
 /* shipped via sqe->cmd of io_uring command */
 struct ublksrv_ctrl_cmd {