Merge tag 'for-6.16/block-20250523' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - ublk updates:
      - Add support for updating the size of a ublk instance
      - Zero-copy improvements
      - Auto-registering of buffers for zero-copy
      - Series simplifying and improving GET_DATA and request lookup
      - Series adding quiesce support
      - Lots of selftests additions
      - Various cleanups

 - NVMe updates via Christoph:
      - add per-node DMA pools and use them for PRP/SGL allocations
        (Caleb Sander Mateos, Keith Busch)
      - nvme-fcloop refcounting fixes (Daniel Wagner)
      - support delayed removal of the multipath node and optionally
        support the multipath node for private namespaces (Nilay Shroff)
      - support shared CQs in the PCI endpoint target code (Wilfred
        Mallawa)
      - support admin-queue only authentication (Hannes Reinecke)
      - use the crc32c library instead of the crypto API (Eric Biggers)
      - misc cleanups (Christoph Hellwig, Marcelo Moreira, Hannes
        Reinecke, Leon Romanovsky, Gustavo A. R. Silva)

 - MD updates via Yu:
      - Fix that normal IO can be starved by sync IO, found by mkfs on
        newly created large raid5, with some clean up patches for bdev
        inflight counters

 - Clean up brd, getting rid of atomic kmaps and bvec poking

 - Add loop driver specifically for zoned IO testing

 - Eliminate blk-rq-qos calls with a static key, if not enabled

 - Improve hctx locking for when a plug has IO for multiple queues
   pending

 - Remove block layer bouncing support, which in turn means we can
   remove the per-node bounce stat as well

 - Improve blk-throttle support

 - Improve delay support for blk-throttle

 - Improve brd discard support

 - Unify IO scheduler switching. This should also fix a bunch of lockdep
   warnings we've been seeing, after enabling lockdep support for queue
   freezing/unfreezeing

 - Add support for block write streams via FDP (flexible data placement)
   on NVMe

 - Add a bunch of block helpers, facilitating the removal of a bunch of
   duplicated boilerplate code

 - Remove obsolete BLK_MQ pci and virtio Kconfig options

 - Add atomic/untorn write support to blktrace

 - Various little cleanups and fixes

* tag 'for-6.16/block-20250523' of git://git.kernel.dk/linux: (186 commits)
  selftests: ublk: add test for UBLK_F_QUIESCE
  ublk: add feature UBLK_F_QUIESCE
  selftests: ublk: add test case for UBLK_U_CMD_UPDATE_SIZE
  traceevent/block: Add REQ_ATOMIC flag to block trace events
  ublk: run auto buf unregisgering in same io_ring_ctx with registering
  io_uring: add helper io_uring_cmd_ctx_handle()
  ublk: remove io argument from ublk_auto_buf_reg_fallback()
  ublk: handle ublk_set_auto_buf_reg() failure correctly in ublk_fetch()
  selftests: ublk: add test for covering UBLK_AUTO_BUF_REG_FALLBACK
  selftests: ublk: support UBLK_F_AUTO_BUF_REG
  ublk: support UBLK_AUTO_BUF_REG_FALLBACK
  ublk: register buffer to local io_uring with provided buf index via UBLK_F_AUTO_BUF_REG
  ublk: prepare for supporting to register request buffer automatically
  ublk: convert to refcount_t
  selftests: ublk: make IO & device removal test more stressful
  nvme: rename nvme_mpath_shutdown_disk to nvme_mpath_remove_disk
  nvme: introduce multipath_always_on module param
  nvme-multipath: introduce delayed removal of the multipath head node
  nvme-pci: derive and better document max segments limits
  nvme-pci: use struct_size for allocation struct nvme_dev
  ...

15 files changed, 299 insertions, 34 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index b786ec5bcc81..9c37c66ef9ca 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -403,7 +403,6 @@ static inline int bio_iov_vecs_to_alloc(struct iov_iter *iter, int max_segs)
 
 struct request_queue;
 
-extern int submit_bio_wait(struct bio *bio);
 void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table,
 	      unsigned short max_vecs, blk_opf_t opf);
 extern void bio_uninit(struct bio *);
@@ -418,6 +417,30 @@ 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,
 			  size_t off);
+void bio_add_virt_nofail(struct bio *bio, void *vaddr, unsigned len);
+
+/**
+ * bio_add_max_vecs - number of bio_vecs needed to add data to a bio
+ * @kaddr: kernel virtual address to add
+ * @len: length in bytes to add
+ *
+ * Calculate how many bio_vecs need to be allocated to add the kernel virtual
+ * address range in [@kaddr:@len] in the worse case.
+ */
+static inline unsigned int bio_add_max_vecs(void *kaddr, unsigned int len)
+{
+	if (is_vmalloc_addr(kaddr))
+		return DIV_ROUND_UP(offset_in_page(kaddr) + len, PAGE_SIZE);
+	return 1;
+}
+
+unsigned int bio_add_vmalloc_chunk(struct bio *bio, void *vaddr, unsigned len);
+bool bio_add_vmalloc(struct bio *bio, void *vaddr, unsigned int len);
+
+int submit_bio_wait(struct bio *bio);
+int bdev_rw_virt(struct block_device *bdev, sector_t sector, void *data,
+		size_t len, enum req_op op);
+
 int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter);
 void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter);
 void __bio_release_pages(struct bio *bio, bool mark_dirty);
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 8eb9b3310167..de8c85a03bb7 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -9,6 +9,7 @@
 #include <linux/prefetch.h>
 #include <linux/srcu.h>
 #include <linux/rw_hint.h>
+#include <linux/rwsem.h>
 
 struct blk_mq_tags;
 struct blk_flush_queue;
@@ -506,6 +507,9 @@ enum hctx_type {
  *		   request_queue.tag_set_list.
  * @srcu:	   Use as lock when type of the request queue is blocking
  *		   (BLK_MQ_F_BLOCKING).
+ * @update_nr_hwq_lock:
+ * 		   Synchronize updating nr_hw_queues with add/del disk &
+ * 		   switching elevator.
  */
 struct blk_mq_tag_set {
 	const struct blk_mq_ops	*ops;
@@ -527,6 +531,8 @@ struct blk_mq_tag_set {
 	struct mutex		tag_list_lock;
 	struct list_head	tag_list;
 	struct srcu_struct	*srcu;
+
+	struct rw_semaphore	update_nr_hwq_lock;
 };
 
 /**
@@ -1031,8 +1037,8 @@ int blk_rq_map_user_io(struct request *, struct rq_map_data *,
 int blk_rq_map_user_iov(struct request_queue *, struct request *,
 		struct rq_map_data *, const struct iov_iter *, gfp_t);
 int blk_rq_unmap_user(struct bio *);
-int blk_rq_map_kern(struct request_queue *, struct request *, void *,
-		unsigned int, gfp_t);
+int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len,
+		gfp_t gfp);
 int blk_rq_append_bio(struct request *rq, struct bio *bio);
 void blk_execute_rq_nowait(struct request *rq, bool at_head);
 blk_status_t blk_execute_rq(struct request *rq, bool at_head);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index dce7615c35e7..3d1577f07c1c 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -220,6 +220,7 @@ struct bio {
 	unsigned short		bi_flags;	/* BIO_* below */
 	unsigned short		bi_ioprio;
 	enum rw_hint		bi_write_hint;
+	u8			bi_write_stream;
 	blk_status_t		bi_status;
 	atomic_t		__bi_remaining;
 
@@ -286,7 +287,6 @@ struct bio {
 enum {
 	BIO_PAGE_PINNED,	/* Unpin pages in bio_release_pages() */
 	BIO_CLONED,		/* doesn't own data */
-	BIO_BOUNCED,		/* bio is a bounce bio */
 	BIO_QUIET,		/* Make BIO Quiet */
 	BIO_CHAIN,		/* chained bio, ->bi_remaining in effect */
 	BIO_REFFED,		/* bio has elevated ->bi_cnt */
@@ -296,6 +296,14 @@ enum {
 				 * of this bio. */
 	BIO_CGROUP_ACCT,	/* has been accounted to a cgroup */
 	BIO_QOS_THROTTLED,	/* bio went through rq_qos throttle path */
+	/*
+	 * This bio has completed bps throttling at the single tg granularity,
+	 * which is different from BIO_BPS_THROTTLED. When the bio is enqueued
+	 * into the sq->queued of the upper tg, or is about to be dispatched,
+	 * this flag needs to be cleared. Since blk-throttle and rq_qos are not
+	 * on the same hierarchical level, reuse the value.
+	 */
+	BIO_TG_BPS_THROTTLED = BIO_QOS_THROTTLED,
 	BIO_QOS_MERGED,		/* but went through rq_qos merge path */
 	BIO_REMAPPED,
 	BIO_ZONE_WRITE_PLUGGING, /* bio handled through zone write plugging */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 9a1f0ee40b56..332b56f323d9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -182,7 +182,6 @@ struct gendisk {
 	struct list_head slave_bdevs;
 #endif
 	struct timer_rand_state *random;
-	atomic_t sync_io;		/* RAID */
 	struct disk_events *ev;
 
 #ifdef CONFIG_BLK_DEV_ZONED
@@ -218,6 +217,8 @@ struct gendisk {
 	 * devices that do not have multiple independent access ranges.
 	 */
 	struct blk_independent_access_ranges *ia_ranges;
+
+	struct mutex rqos_state_mutex;	/* rqos state change mutex */
 };
 
 /**
@@ -331,9 +332,6 @@ typedef unsigned int __bitwise blk_features_t;
 /* skip this queue in blk_mq_(un)quiesce_tagset */
 #define BLK_FEAT_SKIP_TAGSET_QUIESCE	((__force blk_features_t)(1u << 13))
 
-/* bounce all highmem pages */
-#define BLK_FEAT_BOUNCE_HIGH		((__force blk_features_t)(1u << 14))
-
 /* undocumented magic for bcache */
 #define BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE \
 	((__force blk_features_t)(1u << 15))
@@ -347,7 +345,7 @@ typedef unsigned int __bitwise blk_features_t;
  */
 #define BLK_FEAT_INHERIT_MASK \
 	(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | BLK_FEAT_ROTATIONAL | \
-	 BLK_FEAT_STABLE_WRITES | BLK_FEAT_ZONED | BLK_FEAT_BOUNCE_HIGH | \
+	 BLK_FEAT_STABLE_WRITES | BLK_FEAT_ZONED | \
 	 BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE)
 
 /* internal flags in queue_limits.flags */
@@ -405,6 +403,9 @@ struct queue_limits {
 	unsigned short		max_integrity_segments;
 	unsigned short		max_discard_segments;
 
+	unsigned short		max_write_streams;
+	unsigned int		write_stream_granularity;
+
 	unsigned int		max_open_zones;
 	unsigned int		max_active_zones;
 
@@ -644,6 +645,8 @@ enum {
 	QUEUE_FLAG_RQ_ALLOC_TIME,	/* record rq->alloc_time_ns */
 	QUEUE_FLAG_HCTX_ACTIVE,		/* at least one blk-mq hctx is active */
 	QUEUE_FLAG_SQ_SCHED,		/* single queue style io dispatch */
+	QUEUE_FLAG_DISABLE_WBT_DEF,	/* for sched to disable/enable wbt */
+	QUEUE_FLAG_NO_ELV_SWITCH,	/* can't switch elevator any more */
 	QUEUE_FLAG_MAX
 };
 
@@ -679,6 +682,10 @@ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
 #define blk_queue_sq_sched(q)	test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags)
 #define blk_queue_skip_tagset_quiesce(q) \
 	((q)->limits.features & BLK_FEAT_SKIP_TAGSET_QUIESCE)
+#define blk_queue_disable_wbt(q)	\
+	test_bit(QUEUE_FLAG_DISABLE_WBT_DEF, &(q)->queue_flags)
+#define blk_queue_no_elv_switch(q)	\
+	test_bit(QUEUE_FLAG_NO_ELV_SWITCH, &(q)->queue_flags)
 
 extern void blk_set_pm_only(struct request_queue *q);
 extern void blk_clear_pm_only(struct request_queue *q);
@@ -1288,6 +1295,13 @@ static inline unsigned int bdev_max_segments(struct block_device *bdev)
 	return queue_max_segments(bdev_get_queue(bdev));
 }
 
+static inline unsigned short bdev_max_write_streams(struct block_device *bdev)
+{
+	if (bdev_is_partition(bdev))
+		return 0;
+	return bdev_limits(bdev)->max_write_streams;
+}
+
 static inline unsigned queue_logical_block_size(const struct request_queue *q)
 {
 	return q->limits.logical_block_size;
diff --git a/include/linux/dmapool.h b/include/linux/dmapool.h
index f632ecfb4238..06c4de602b2f 100644
--- a/include/linux/dmapool.h
+++ b/include/linux/dmapool.h
@@ -11,6 +11,7 @@
 #ifndef LINUX_DMAPOOL_H
 #define	LINUX_DMAPOOL_H
 
+#include <linux/nodemask_types.h>
 #include <linux/scatterlist.h>
 #include <asm/io.h>
 
@@ -18,8 +19,8 @@ struct device;
 
 #ifdef CONFIG_HAS_DMA
 
-struct dma_pool *dma_pool_create(const char *name, struct device *dev, 
-			size_t size, size_t align, size_t allocation);
+struct dma_pool *dma_pool_create_node(const char *name, struct device *dev,
+		size_t size, size_t align, size_t boundary, int node);
 
 void dma_pool_destroy(struct dma_pool *pool);
 
@@ -35,9 +36,12 @@ struct dma_pool *dmam_pool_create(const char *name, struct device *dev,
 void dmam_pool_destroy(struct dma_pool *pool);
 
 #else /* !CONFIG_HAS_DMA */
-static inline struct dma_pool *dma_pool_create(const char *name,
-	struct device *dev, size_t size, size_t align, size_t allocation)
-{ return NULL; }
+static inline struct dma_pool *dma_pool_create_node(const char *name,
+		struct device *dev, size_t size, size_t align, size_t boundary,
+		int node)
+{
+	return NULL;
+}
 static inline void dma_pool_destroy(struct dma_pool *pool) { }
 static inline void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
 				   dma_addr_t *handle) { return NULL; }
@@ -49,6 +53,13 @@ static inline struct dma_pool *dmam_pool_create(const char *name,
 static inline void dmam_pool_destroy(struct dma_pool *pool) { }
 #endif /* !CONFIG_HAS_DMA */
 
+static inline struct dma_pool *dma_pool_create(const char *name,
+		struct device *dev, size_t size, size_t align, size_t boundary)
+{
+	return dma_pool_create_node(name, dev, size, align, boundary,
+				    NUMA_NO_NODE);
+}
+
 static inline void *dma_pool_zalloc(struct dma_pool *pool, gfp_t mem_flags,
 				    dma_addr_t *handle)
 {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 81f8f0aec563..b807045614c6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -408,6 +408,7 @@ struct kiocb {
 	void			*private;
 	int			ki_flags;
 	u16			ki_ioprio; /* See linux/ioprio.h */
+	u8			ki_write_stream;
 	union {
 		/*
 		 * Only used for async buffered reads, where it denotes the
diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
index 0634a3de1782..53408124c1e5 100644
--- a/include/linux/io_uring/cmd.h
+++ b/include/linux/io_uring/cmd.h
@@ -140,6 +140,15 @@ static inline struct io_uring_cmd_data *io_uring_cmd_get_async_data(struct io_ur
 	return cmd_to_io_kiocb(cmd)->async_data;
 }
 
+/*
+ * Return uring_cmd's context reference as its context handle for driver to
+ * track per-context resource, such as registered kernel IO buffer
+ */
+static inline void *io_uring_cmd_ctx_handle(struct io_uring_cmd *cmd)
+{
+	return cmd_to_io_kiocb(cmd)->ctx;
+}
+
 int io_buffer_register_bvec(struct io_uring_cmd *cmd, struct request *rq,
 			    void (*release)(void *), unsigned int index,
 			    unsigned int issue_flags);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 6ccec1bf2896..b1c459f7a485 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -148,7 +148,6 @@ enum zone_stat_item {
 	NR_ZONE_WRITE_PENDING,	/* Count of dirty, writeback and unstable pages */
 	NR_MLOCK,		/* mlock()ed pages found and moved off LRU */
 	/* Second 128 byte cacheline */
-	NR_BOUNCE,
 #if IS_ENABLED(CONFIG_ZSMALLOC)
 	NR_ZSPAGES,		/* allocated in zsmalloc */
 #endif
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 2479ed10f53e..51308f65b72f 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -303,6 +303,7 @@ enum nvme_ctrl_attr {
 	NVME_CTRL_ATTR_TBKAS		= (1 << 6),
 	NVME_CTRL_ATTR_ELBAS		= (1 << 15),
 	NVME_CTRL_ATTR_RHII		= (1 << 18),
+	NVME_CTRL_ATTR_FDPS		= (1 << 19),
 };
 
 struct nvme_id_ctrl {
@@ -689,6 +690,44 @@ struct nvme_rotational_media_log {
 	__u8	rsvd24[488];
 };
 
+struct nvme_fdp_config {
+	__u8			flags;
+#define FDPCFG_FDPE	(1U << 0)
+	__u8			fdpcidx;
+	__le16			reserved;
+};
+
+struct nvme_fdp_ruh_desc {
+	__u8			ruht;
+	__u8			reserved[3];
+};
+
+struct nvme_fdp_config_desc {
+	__le16			dsze;
+	__u8			fdpa;
+	__u8			vss;
+	__le32			nrg;
+	__le16			nruh;
+	__le16			maxpids;
+	__le32			nns;
+	__le64			runs;
+	__le32			erutl;
+	__u8			rsvd28[36];
+	struct nvme_fdp_ruh_desc ruhs[];
+};
+
+struct nvme_fdp_config_log {
+	__le16			numfdpc;
+	__u8			ver;
+	__u8			rsvd3;
+	__le32			sze;
+	__u8			rsvd8[8];
+	/*
+	 * This is followed by variable number of nvme_fdp_config_desc
+	 * structures, but sparse doesn't like nested variable sized arrays.
+	 */
+};
+
 struct nvme_smart_log {
 	__u8			critical_warning;
 	__u8			temperature[2];
@@ -915,6 +954,7 @@ enum nvme_opcode {
 	nvme_cmd_resv_register	= 0x0d,
 	nvme_cmd_resv_report	= 0x0e,
 	nvme_cmd_resv_acquire	= 0x11,
+	nvme_cmd_io_mgmt_recv	= 0x12,
 	nvme_cmd_resv_release	= 0x15,
 	nvme_cmd_zone_mgmt_send	= 0x79,
 	nvme_cmd_zone_mgmt_recv	= 0x7a,
@@ -936,6 +976,7 @@ enum nvme_opcode {
 		nvme_opcode_name(nvme_cmd_resv_register),	\
 		nvme_opcode_name(nvme_cmd_resv_report),		\
 		nvme_opcode_name(nvme_cmd_resv_acquire),	\
+		nvme_opcode_name(nvme_cmd_io_mgmt_recv),	\
 		nvme_opcode_name(nvme_cmd_resv_release),	\
 		nvme_opcode_name(nvme_cmd_zone_mgmt_send),	\
 		nvme_opcode_name(nvme_cmd_zone_mgmt_recv),	\
@@ -1087,6 +1128,7 @@ enum {
 	NVME_RW_PRINFO_PRCHK_GUARD	= 1 << 12,
 	NVME_RW_PRINFO_PRACT		= 1 << 13,
 	NVME_RW_DTYPE_STREAMS		= 1 << 4,
+	NVME_RW_DTYPE_DPLCMT		= 2 << 4,
 	NVME_WZ_DEAC			= 1 << 9,
 };
 
@@ -1174,6 +1216,38 @@ struct nvme_zone_mgmt_recv_cmd {
 	__le32			cdw14[2];
 };
 
+struct nvme_io_mgmt_recv_cmd {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__le32			nsid;
+	__le64			rsvd2[2];
+	union nvme_data_ptr	dptr;
+	__u8			mo;
+	__u8			rsvd11;
+	__u16			mos;
+	__le32			numd;
+	__le32			cdw12[4];
+};
+
+enum {
+	NVME_IO_MGMT_RECV_MO_RUHS	= 1,
+};
+
+struct nvme_fdp_ruh_status_desc {
+	__le16			pid;
+	__le16			ruhid;
+	__le32			earutr;
+	__le64			ruamw;
+	__u8			reserved[16];
+};
+
+struct nvme_fdp_ruh_status {
+	__u8			rsvd0[14];
+	__le16			nruhsd;
+	struct nvme_fdp_ruh_status_desc ruhsd[];
+};
+
 enum {
 	NVME_ZRA_ZONE_REPORT		= 0,
 	NVME_ZRASF_ZONE_REPORT_ALL	= 0,
@@ -1309,6 +1383,7 @@ enum {
 	NVME_FEAT_PLM_WINDOW	= 0x14,
 	NVME_FEAT_HOST_BEHAVIOR	= 0x16,
 	NVME_FEAT_SANITIZE	= 0x17,
+	NVME_FEAT_FDP		= 0x1d,
 	NVME_FEAT_SW_PROGRESS	= 0x80,
 	NVME_FEAT_HOST_ID	= 0x81,
 	NVME_FEAT_RESV_MASK	= 0x82,
@@ -1329,6 +1404,7 @@ enum {
 	NVME_LOG_ANA		= 0x0c,
 	NVME_LOG_FEATURES	= 0x12,
 	NVME_LOG_RMI		= 0x16,
+	NVME_LOG_FDP_CONFIGS	= 0x20,
 	NVME_LOG_DISC		= 0x70,
 	NVME_LOG_RESERVATION	= 0x80,
 	NVME_FWACT_REPL		= (0 << 3),
@@ -1923,6 +1999,7 @@ struct nvme_command {
 		struct nvmf_auth_receive_command auth_receive;
 		struct nvme_dbbuf dbbuf;
 		struct nvme_directive_cmd directive;
+		struct nvme_io_mgmt_recv_cmd imr;
 	};
 };
 
diff --git a/include/linux/part_stat.h b/include/linux/part_stat.h
index c5e9cac0575e..eeeff2a04529 100644
--- a/include/linux/part_stat.h
+++ b/include/linux/part_stat.h
@@ -79,4 +79,6 @@ static inline void part_stat_set_all(struct block_device *part, int value)
 #define part_stat_local_read_cpu(part, field, cpu)			\
 	local_read(&(part_stat_get_cpu(part, field, cpu)))
 
+unsigned int bdev_count_inflight(struct block_device *part);
+
 #endif /* _LINUX_PART_STAT_H */
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 26bc23419cfd..c53812b9026f 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -670,8 +670,6 @@ struct Scsi_Host {
 	/* The transport requires the LUN bits NOT to be stored in CDB[1] */
 	unsigned no_scsi2_lun_in_cdb:1;
 
-	unsigned no_highmem:1;
-
 	/*
 	 * Optional work queue to be utilized by the transport
 	 */
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index bd0ea07338eb..14a924c0e303 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -11,7 +11,7 @@
 #include <linux/tracepoint.h>
 #include <uapi/linux/ioprio.h>
 
-#define RWBS_LEN	8
+#define RWBS_LEN	9
 
 #define IOPRIO_CLASS_STRINGS \
 	{ IOPRIO_CLASS_NONE,	"none" }, \
@@ -361,21 +361,6 @@ DECLARE_EVENT_CLASS(block_bio,
 );
 
 /**
- * block_bio_bounce - used bounce buffer when processing block operation
- * @bio: block operation
- *
- * A bounce buffer was used to handle the block operation @bio in @q.
- * This occurs when hardware limitations prevent a direct transfer of
- * data between the @bio data memory area and the IO device.  Use of a
- * bounce buffer requires extra copying of data and decreases
- * performance.
- */
-DEFINE_EVENT(block_bio, block_bio_bounce,
-	TP_PROTO(struct bio *bio),
-	TP_ARGS(bio)
-);
-
-/**
  * block_bio_backmerge - merging block operation to the end of an existing operation
  * @bio: new block operation to merge
  *
diff --git a/include/uapi/linux/blktrace_api.h b/include/uapi/linux/blktrace_api.h
index 690621b610e5..1bfb635e309b 100644
--- a/include/uapi/linux/blktrace_api.h
+++ b/include/uapi/linux/blktrace_api.h
@@ -49,7 +49,7 @@ enum blktrace_act {
 	__BLK_TA_UNPLUG_TIMER,		/* queue was unplugged by timer */
 	__BLK_TA_INSERT,		/* insert request */
 	__BLK_TA_SPLIT,			/* bio was split */
-	__BLK_TA_BOUNCE,		/* bio was bounced */
+	__BLK_TA_BOUNCE,		/* unused, was: bio was bounced */
 	__BLK_TA_REMAP,			/* bio was remapped */
 	__BLK_TA_ABORT,			/* request aborted */
 	__BLK_TA_DRV_DATA,		/* driver-specific binary data */
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 8f1fc12bac46..50e372ea97c5 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -93,6 +93,10 @@ struct io_uring_sqe {
 			__u16	addr_len;
 			__u16	__pad3[1];
 		};
+		struct {
+			__u8	write_stream;
+			__u8	__pad4[3];
+		};
 	};
 	union {
 		struct {
diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
index 583b86681c93..56c7e3fc666f 100644
--- a/include/uapi/linux/ublk_cmd.h
+++ b/include/uapi/linux/ublk_cmd.h
@@ -51,6 +51,10 @@
 	_IOR('u', 0x13, struct ublksrv_ctrl_cmd)
 #define UBLK_U_CMD_DEL_DEV_ASYNC	\
 	_IOR('u', 0x14, struct ublksrv_ctrl_cmd)
+#define UBLK_U_CMD_UPDATE_SIZE		\
+	_IOWR('u', 0x15, struct ublksrv_ctrl_cmd)
+#define UBLK_U_CMD_QUIESCE_DEV		\
+	_IOWR('u', 0x16, struct ublksrv_ctrl_cmd)
 
 /*
  * 64bits are enough now, and it should be easy to extend in case of
@@ -211,6 +215,63 @@
  */
 #define UBLK_F_USER_RECOVERY_FAIL_IO (1ULL << 9)
 
+/*
+ * Resizing a block device is possible with UBLK_U_CMD_UPDATE_SIZE
+ * New size is passed in cmd->data[0] and is in units of sectors
+ */
+#define UBLK_F_UPDATE_SIZE		 (1ULL << 10)
+
+/*
+ * request buffer is registered automatically to uring_cmd's io_uring
+ * context before delivering this io command to ublk server, meantime
+ * it is un-registered automatically when completing this io command.
+ *
+ * For using this feature:
+ *
+ * - ublk server has to create sparse buffer table on the same `io_ring_ctx`
+ *   for issuing `UBLK_IO_FETCH_REQ` and `UBLK_IO_COMMIT_AND_FETCH_REQ`.
+ *   If uring_cmd isn't issued on same `io_ring_ctx`, it is ublk server's
+ *   responsibility to unregister the buffer by issuing `IO_UNREGISTER_IO_BUF`
+ *   manually, otherwise this ublk request won't complete.
+ *
+ * - ublk server passes auto buf register data via uring_cmd's sqe->addr,
+ *   `struct ublk_auto_buf_reg` is populated from sqe->addr, please see
+ *   the definition of ublk_sqe_addr_to_auto_buf_reg()
+ *
+ * - pass buffer index from `ublk_auto_buf_reg.index`
+ *
+ * - all reserved fields in `ublk_auto_buf_reg` need to be zeroed
+ *
+ * - pass flags from `ublk_auto_buf_reg.flags` if needed
+ *
+ * This way avoids extra cost from two uring_cmd, but also simplifies backend
+ * implementation, such as, the dependency on IO_REGISTER_IO_BUF and
+ * IO_UNREGISTER_IO_BUF becomes not necessary.
+ *
+ * If wrong data or flags are provided, both IO_FETCH_REQ and
+ * IO_COMMIT_AND_FETCH_REQ are failed, for the latter, the ublk IO request
+ * won't be completed until new IO_COMMIT_AND_FETCH_REQ command is issued
+ * successfully
+ */
+#define UBLK_F_AUTO_BUF_REG 	(1ULL << 11)
+
+/*
+ * Control command `UBLK_U_CMD_QUIESCE_DEV` is added for quiescing device,
+ * which state can be transitioned to `UBLK_S_DEV_QUIESCED` or
+ * `UBLK_S_DEV_FAIL_IO` finally, and it needs ublk server cooperation for
+ * handling `UBLK_IO_RES_ABORT` correctly.
+ *
+ * Typical use case is for supporting to upgrade ublk server application,
+ * meantime keep ublk block device persistent during the period.
+ *
+ * This feature is only available when UBLK_F_USER_RECOVERY is enabled.
+ *
+ * Note, this command returns -EBUSY in case that all IO commands are being
+ * handled by ublk server and not completed in specified time period which
+ * is passed from the control command parameter.
+ */
+#define UBLK_F_QUIESCE		(1ULL << 12)
+
 /* device state */
 #define UBLK_S_DEV_DEAD	0
 #define UBLK_S_DEV_LIVE	1
@@ -297,6 +358,17 @@ struct ublksrv_ctrl_dev_info {
 #define		UBLK_IO_F_FUA			(1U << 13)
 #define		UBLK_IO_F_NOUNMAP		(1U << 15)
 #define		UBLK_IO_F_SWAP			(1U << 16)
+/*
+ * For UBLK_F_AUTO_BUF_REG & UBLK_AUTO_BUF_REG_FALLBACK only.
+ *
+ * This flag is set if auto buffer register is failed & ublk server passes
+ * UBLK_AUTO_BUF_REG_FALLBACK, and ublk server need to register buffer
+ * manually for handling the delivered IO command if this flag is observed
+ *
+ * ublk server has to check this flag if UBLK_AUTO_BUF_REG_FALLBACK is
+ * passed in.
+ */
+#define		UBLK_IO_F_NEED_REG_BUF		(1U << 17)
 
 /*
  * io cmd is described by this structure, and stored in share memory, indexed
@@ -331,6 +403,62 @@ static inline __u32 ublksrv_get_flags(const struct ublksrv_io_desc *iod)
 	return iod->op_flags >> 8;
 }
 
+/*
+ * If this flag is set, fallback by completing the uring_cmd and setting
+ * `UBLK_IO_F_NEED_REG_BUF` in case of auto-buf-register failure;
+ * otherwise the client ublk request is failed silently
+ *
+ * If ublk server passes this flag, it has to check if UBLK_IO_F_NEED_REG_BUF
+ * is set in `ublksrv_io_desc.op_flags`. If UBLK_IO_F_NEED_REG_BUF is set,
+ * ublk server needs to register io buffer manually for handling IO command.
+ */
+#define UBLK_AUTO_BUF_REG_FALLBACK 	(1 << 0)
+#define UBLK_AUTO_BUF_REG_F_MASK 	UBLK_AUTO_BUF_REG_FALLBACK
+
+struct ublk_auto_buf_reg {
+	/* index for registering the delivered request buffer */
+	__u16  index;
+	__u8   flags;
+	__u8   reserved0;
+
+	/*
+	 * io_ring FD can be passed via the reserve field in future for
+	 * supporting to register io buffer to external io_uring
+	 */
+	__u32  reserved1;
+};
+
+/*
+ * For UBLK_F_AUTO_BUF_REG, auto buffer register data is carried via
+ * uring_cmd's sqe->addr:
+ *
+ * 	- bit0 ~ bit15: buffer index
+ * 	- bit16 ~ bit23: flags
+ * 	- bit24 ~ bit31: reserved0
+ * 	- bit32 ~ bit63: reserved1
+ */
+static inline struct ublk_auto_buf_reg ublk_sqe_addr_to_auto_buf_reg(
+		__u64 sqe_addr)
+{
+	struct ublk_auto_buf_reg reg = {
+		.index = sqe_addr & 0xffff,
+		.flags = (sqe_addr >> 16) & 0xff,
+		.reserved0 = (sqe_addr >> 24) & 0xff,
+		.reserved1 = sqe_addr >> 32,
+	};
+
+	return reg;
+}
+
+static inline __u64
+ublk_auto_buf_reg_to_sqe_addr(const struct ublk_auto_buf_reg *buf)
+{
+	__u64 addr = buf->index | (__u64)buf->flags << 16 | (__u64)buf->reserved0 << 24 |
+		(__u64)buf->reserved1 << 32;
+
+	return addr;
+}
+
 /* issued to ublk driver via /dev/ublkcN */
 struct ublksrv_io_cmd {
 	__u16	q_id;