Merge tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull request via Keith:
      - Various cleanups all around (Irvin, Chaitanya, Christophe)
      - Better struct packing (Christophe JAILLET)
      - Reduce controller error logs for optional commands (Keith)
      - Support for >=64KiB block sizes (Daniel Gomez)
      - Fabrics fixes and code organization (Max, Chaitanya, Daniel
        Wagner)

 - bcache updates via Coly:
      - Fix a race at init time (Mingzhe Zou)
      - Misc fixes and cleanups (Andrea, Thomas, Zheng, Ye)

 - use page pinning in the block layer for dio (David)

 - convert old block dio code to page pinning (David, Christoph)

 - cleanups for pktcdvd (Andy)

 - cleanups for rnbd (Guoqing)

 - use the unchecked __bio_add_page() for the initial single page
   additions (Johannes)

 - fix overflows in the Amiga partition handling code (Michael)

 - improve mq-deadline zoned device support (Bart)

 - keep passthrough requests out of the IO schedulers (Christoph, Ming)

 - improve support for flush requests, making them less special to deal
   with (Christoph)

 - add bdev holder ops and shutdown methods (Christoph)

 - fix the name_to_dev_t() situation and use cases (Christoph)

 - decouple the block open flags from fmode_t (Christoph)

 - ublk updates and cleanups, including adding user copy support (Ming)

 - BFQ sanity checking (Bart)

 - convert brd from radix to xarray (Pankaj)

 - constify various structures (Thomas, Ivan)

 - more fine grained persistent reservation ioctl capability checks
   (Jingbo)

 - misc fixes and cleanups (Arnd, Azeem, Demi, Ed, Hengqi, Hou, Jan,
   Jordy, Li, Min, Yu, Zhong, Waiman)

* tag 'for-6.5/block-2023-06-23' of git://git.kernel.dk/linux: (266 commits)
  scsi/sg: don't grab scsi host module reference
  ext4: Fix warning in blkdev_put()
  block: don't return -EINVAL for not found names in devt_from_devname
  cdrom: Fix spectre-v1 gadget
  block: Improve kernel-doc headers
  blk-mq: don't insert passthrough request into sw queue
  bsg: make bsg_class a static const structure
  ublk: make ublk_chr_class a static const structure
  aoe: make aoe_class a static const structure
  block/rnbd: make all 'class' structures const
  block: fix the exclusive open mask in disk_scan_partitions
  block: add overflow checks for Amiga partition support
  block: change all __u32 annotations to __be32 in affs_hardblocks.h
  block: fix signed int overflow in Amiga partition support
  block: add capacity validation in bdev_add_partition()
  block: fine-granular CAP_SYS_ADMIN for Persistent Reservation
  block: disallow Persistent Reservation on partitions
  reiserfs: fix blkdev_put() warning from release_journal_dev()
  block: fix wrong mode for blkdev_get_by_dev() from disk_scan_partitions()
  block: document the holder argument to blkdev_get_by_path
  ...

22 files changed, 250 insertions, 163 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index b3e7529ff55e..c4f5b5228105 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -229,7 +229,7 @@ static inline void bio_cnt_set(struct bio *bio, unsigned int count)
 
 static inline bool bio_flagged(struct bio *bio, unsigned int bit)
 {
-	return (bio->bi_flags & (1U << bit)) != 0;
+	return bio->bi_flags & (1U << bit);
 }
 
 static inline void bio_set_flag(struct bio *bio, unsigned int bit)
@@ -465,14 +465,18 @@ extern void bio_uninit(struct bio *);
 void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf);
 void bio_chain(struct bio *, struct bio *);
 
-int bio_add_page(struct bio *, struct page *, unsigned len, unsigned off);
-bool bio_add_folio(struct bio *, struct folio *, size_t len, size_t off);
+int __must_check bio_add_page(struct bio *bio, struct page *page, unsigned len,
+			      unsigned off);
+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,
+			  size_t off);
 int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter);
 void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter);
 void __bio_release_pages(struct bio *bio, bool mark_dirty);
@@ -488,7 +492,7 @@ void zero_fill_bio(struct bio *bio);
 
 static inline void bio_release_pages(struct bio *bio, bool mark_dirty)
 {
-	if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+	if (bio_flagged(bio, BIO_PAGE_PINNED))
 		__bio_release_pages(bio, mark_dirty);
 }
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 06caacd77ed6..f401067ac03a 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -28,8 +28,6 @@ typedef __u32 __bitwise req_flags_t;
 
 /* drive already may have started this one */
 #define RQF_STARTED		((__force req_flags_t)(1 << 1))
-/* may not be passed by ioscheduler */
-#define RQF_SOFTBARRIER		((__force req_flags_t)(1 << 3))
 /* request for flush sequence */
 #define RQF_FLUSH_SEQ		((__force req_flags_t)(1 << 4))
 /* merge of different types, fail separately */
@@ -38,12 +36,14 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_MQ_INFLIGHT		((__force req_flags_t)(1 << 6))
 /* don't call prep for this one */
 #define RQF_DONTPREP		((__force req_flags_t)(1 << 7))
+/* use hctx->sched_tags */
+#define RQF_SCHED_TAGS		((__force req_flags_t)(1 << 8))
+/* use an I/O scheduler for this request */
+#define RQF_USE_SCHED		((__force req_flags_t)(1 << 9))
 /* vaguely specified driver internal error.  Ignored by the block layer */
 #define RQF_FAILED		((__force req_flags_t)(1 << 10))
 /* don't warn about errors */
 #define RQF_QUIET		((__force req_flags_t)(1 << 11))
-/* elevator private data attached */
-#define RQF_ELVPRIV		((__force req_flags_t)(1 << 12))
 /* account into disk and partition IO statistics */
 #define RQF_IO_STAT		((__force req_flags_t)(1 << 13))
 /* runtime pm request */
@@ -59,13 +59,11 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_ZONE_WRITE_LOCKED	((__force req_flags_t)(1 << 19))
 /* ->timeout has been called, don't expire again */
 #define RQF_TIMED_OUT		((__force req_flags_t)(1 << 21))
-/* queue has elevator attached */
-#define RQF_ELV			((__force req_flags_t)(1 << 22))
-#define RQF_RESV			((__force req_flags_t)(1 << 23))
+#define RQF_RESV		((__force req_flags_t)(1 << 23))
 
 /* flags that prevent us from merging requests: */
 #define RQF_NOMERGE_FLAGS \
-	(RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
+	(RQF_STARTED | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
 
 enum mq_rq_state {
 	MQ_RQ_IDLE		= 0,
@@ -169,25 +167,20 @@ struct request {
 		void *completion_data;
 	};
 
-
 	/*
 	 * Three pointers are available for the IO schedulers, if they need
-	 * more they have to dynamically allocate it.  Flush requests are
-	 * never put on the IO scheduler. So let the flush fields share
-	 * space with the elevator data.
+	 * more they have to dynamically allocate it.
 	 */
-	union {
-		struct {
-			struct io_cq		*icq;
-			void			*priv[2];
-		} elv;
-
-		struct {
-			unsigned int		seq;
-			struct list_head	list;
-			rq_end_io_fn		*saved_end_io;
-		} flush;
-	};
+	struct {
+		struct io_cq		*icq;
+		void			*priv[2];
+	} elv;
+
+	struct {
+		unsigned int		seq;
+		struct list_head	list;
+		rq_end_io_fn		*saved_end_io;
+	} flush;
 
 	union {
 		struct __call_single_data csd;
@@ -208,7 +201,7 @@ static inline enum req_op req_op(const struct request *req)
 
 static inline bool blk_rq_is_passthrough(struct request *rq)
 {
-	return blk_op_is_passthrough(req_op(rq));
+	return blk_op_is_passthrough(rq->cmd_flags);
 }
 
 static inline unsigned short req_get_ioprio(struct request *req)
@@ -746,8 +739,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 struct blk_mq_tags {
 	unsigned int nr_tags;
 	unsigned int nr_reserved_tags;
-
-	atomic_t active_queues;
+	unsigned int active_queues;
 
 	struct sbitmap_queue bitmap_tags;
 	struct sbitmap_queue breserved_tags;
@@ -844,7 +836,7 @@ void blk_mq_end_request_batch(struct io_comp_batch *ib);
  */
 static inline bool blk_mq_need_time_stamp(struct request *rq)
 {
-	return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV));
+	return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED));
 }
 
 static inline bool blk_mq_is_reserved_rq(struct request *rq)
@@ -860,7 +852,7 @@ static inline bool blk_mq_add_to_batch(struct request *req,
 				       struct io_comp_batch *iob, int ioerror,
 				       void (*complete)(struct io_comp_batch *))
 {
-	if (!iob || (req->rq_flags & RQF_ELV) || ioerror ||
+	if (!iob || (req->rq_flags & RQF_USE_SCHED) || ioerror ||
 			(req->end_io && !blk_rq_is_passthrough(req)))
 		return false;
 
@@ -1164,6 +1156,18 @@ static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
 	return disk_zone_is_seq(rq->q->disk, blk_rq_pos(rq));
 }
 
+/**
+ * blk_rq_is_seq_zoned_write() - Check if @rq requires write serialization.
+ * @rq: Request to examine.
+ *
+ * Note: REQ_OP_ZONE_APPEND requests do not require serialization.
+ */
+static inline bool blk_rq_is_seq_zoned_write(struct request *rq)
+{
+	return op_needs_zoned_write_locking(req_op(rq)) &&
+		blk_rq_zone_is_seq(rq);
+}
+
 bool blk_req_needs_zone_write_lock(struct request *rq);
 bool blk_req_zone_write_trylock(struct request *rq);
 void __blk_req_zone_write_lock(struct request *rq);
@@ -1194,6 +1198,11 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
 	return !blk_req_zone_is_write_locked(rq);
 }
 #else /* CONFIG_BLK_DEV_ZONED */
+static inline bool blk_rq_is_seq_zoned_write(struct request *rq)
+{
+	return false;
+}
+
 static inline bool blk_req_needs_zone_write_lock(struct request *rq)
 {
 	return false;
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 740afe80f297..752a54e3284b 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -55,6 +55,8 @@ struct block_device {
 	struct super_block *	bd_super;
 	void *			bd_claiming;
 	void *			bd_holder;
+	const struct blk_holder_ops *bd_holder_ops;
+	struct mutex		bd_holder_lock;
 	/* The counter of freeze processes */
 	int			bd_fsfreeze_count;
 	int			bd_holders;
@@ -323,7 +325,7 @@ struct bio {
  * bio flags
  */
 enum {
-	BIO_NO_PAGE_REF,	/* don't put release vec pages */
+	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 */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c0ffe203a602..ed44a997f629 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -41,7 +41,7 @@ struct blk_stat_callback;
 struct blk_crypto_profile;
 
 extern const struct device_type disk_type;
-extern struct device_type part_type;
+extern const struct device_type part_type;
 extern struct class block_class;
 
 /*
@@ -112,6 +112,19 @@ struct blk_integrity {
 	unsigned char				tag_size;
 };
 
+typedef unsigned int __bitwise blk_mode_t;
+
+/* open for reading */
+#define BLK_OPEN_READ		((__force blk_mode_t)(1 << 0))
+/* open for writing */
+#define BLK_OPEN_WRITE		((__force blk_mode_t)(1 << 1))
+/* open exclusively (vs other exclusive openers */
+#define BLK_OPEN_EXCL		((__force blk_mode_t)(1 << 2))
+/* opened with O_NDELAY */
+#define BLK_OPEN_NDELAY		((__force blk_mode_t)(1 << 3))
+/* open for "writes" only for ioctls (specialy hack for floppy.c) */
+#define BLK_OPEN_WRITE_IOCTL	((__force blk_mode_t)(1 << 4))
+
 struct gendisk {
 	/*
 	 * major/first_minor/minors should not be set by any new driver, the
@@ -187,6 +200,7 @@ struct gendisk {
 	struct badblocks *bb;
 	struct lockdep_map lockdep_map;
 	u64 diskseq;
+	blk_mode_t open_mode;
 
 	/*
 	 * Independent sector access ranges. This is always NULL for
@@ -318,7 +332,6 @@ typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
 void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model);
 
 #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);
@@ -328,33 +341,11 @@ extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
 			    gfp_t gfp_mask);
 int blk_revalidate_disk_zones(struct gendisk *disk,
 			      void (*update_driver_data)(struct gendisk *disk));
-
-extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
-				     unsigned int cmd, unsigned long arg);
-extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
-				  unsigned int cmd, unsigned long arg);
-
 #else /* CONFIG_BLK_DEV_ZONED */
-
 static inline unsigned int bdev_nr_zones(struct block_device *bdev)
 {
 	return 0;
 }
-
-static inline int blkdev_report_zones_ioctl(struct block_device *bdev,
-					    fmode_t mode, unsigned int cmd,
-					    unsigned long arg)
-{
-	return -ENOTTY;
-}
-
-static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev,
-					 fmode_t mode, unsigned int cmd,
-					 unsigned long arg)
-{
-	return -ENOTTY;
-}
-
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 /*
@@ -392,6 +383,7 @@ struct request_queue {
 
 	struct blk_queue_stats	*stats;
 	struct rq_qos		*rq_qos;
+	struct mutex		rq_qos_mutex;
 
 	const struct blk_mq_ops	*mq_ops;
 
@@ -487,6 +479,7 @@ struct request_queue {
 	 * for flush operations
 	 */
 	struct blk_flush_queue	*fq;
+	struct list_head	flush_list;
 
 	struct list_head	requeue_list;
 	spinlock_t		requeue_lock;
@@ -815,7 +808,7 @@ int __register_blkdev(unsigned int major, const char *name,
 	__register_blkdev(major, name, NULL)
 void unregister_blkdev(unsigned int major, const char *name);
 
-bool bdev_check_media_change(struct block_device *bdev);
+bool disk_check_media_change(struct gendisk *disk);
 int __invalidate_device(struct block_device *bdev, bool kill_dirty);
 void set_capacity(struct gendisk *disk, sector_t size);
 
@@ -836,7 +829,6 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev,
 
 dev_t part_devt(struct gendisk *disk, u8 partno);
 void inc_diskseq(struct gendisk *disk);
-dev_t blk_lookup_devt(const char *name, int partno);
 void blk_request_module(dev_t devt);
 
 extern int blk_register_queue(struct gendisk *disk);
@@ -1281,15 +1273,18 @@ static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec)
 	return disk_zone_no(bdev->bd_disk, sec);
 }
 
-static inline bool bdev_op_is_zoned_write(struct block_device *bdev,
-					  blk_opf_t op)
+/* Whether write serialization is required for @op on zoned devices. */
+static inline bool op_needs_zoned_write_locking(enum req_op op)
 {
-	if (!bdev_is_zoned(bdev))
-		return false;
-
 	return op == REQ_OP_WRITE || op == REQ_OP_WRITE_ZEROES;
 }
 
+static inline bool bdev_op_is_zoned_write(struct block_device *bdev,
+					  enum req_op op)
+{
+	return bdev_is_zoned(bdev) && op_needs_zoned_write_locking(op);
+}
+
 static inline sector_t bdev_zone_sectors(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
@@ -1380,10 +1375,12 @@ struct block_device_operations {
 	void (*submit_bio)(struct bio *bio);
 	int (*poll_bio)(struct bio *bio, struct io_comp_batch *iob,
 			unsigned int flags);
-	int (*open) (struct block_device *, fmode_t);
-	void (*release) (struct gendisk *, fmode_t);
-	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
-	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
+	int (*open)(struct gendisk *disk, blk_mode_t mode);
+	void (*release)(struct gendisk *disk);
+	int (*ioctl)(struct block_device *bdev, blk_mode_t mode,
+			unsigned cmd, unsigned long arg);
+	int (*compat_ioctl)(struct block_device *bdev, blk_mode_t mode,
+			unsigned cmd, unsigned long arg);
 	unsigned int (*check_events) (struct gendisk *disk,
 				      unsigned int clearing);
 	void (*unlock_native_capacity) (struct gendisk *);
@@ -1410,7 +1407,7 @@ struct block_device_operations {
 };
 
 #ifdef CONFIG_COMPAT
-extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t,
+extern int blkdev_compat_ptr_ioctl(struct block_device *, blk_mode_t,
 				      unsigned int, unsigned long);
 #else
 #define blkdev_compat_ptr_ioctl NULL
@@ -1463,22 +1460,31 @@ void blkdev_show(struct seq_file *seqf, off_t offset);
 #define BLKDEV_MAJOR_MAX	0
 #endif
 
-struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
-		void *holder);
-struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder);
-int bd_prepare_to_claim(struct block_device *bdev, void *holder);
+struct blk_holder_ops {
+	void (*mark_dead)(struct block_device *bdev);
+};
+
+/*
+ * Return the correct open flags for blkdev_get_by_* for super block flags
+ * as stored in sb->s_flags.
+ */
+#define sb_open_mode(flags) \
+	(BLK_OPEN_READ | (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE))
+
+struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder,
+		const struct blk_holder_ops *hops);
+struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode,
+		void *holder, const struct blk_holder_ops *hops);
+int bd_prepare_to_claim(struct block_device *bdev, void *holder,
+		const struct blk_holder_ops *hops);
 void bd_abort_claiming(struct block_device *bdev, void *holder);
-void blkdev_put(struct block_device *bdev, fmode_t mode);
+void blkdev_put(struct block_device *bdev, void *holder);
 
 /* just for blk-cgroup, don't use elsewhere */
 struct block_device *blkdev_get_no_open(dev_t dev);
 void blkdev_put_no_open(struct block_device *bdev);
 
-struct block_device *bdev_alloc(struct gendisk *disk, u8 partno);
-void bdev_add(struct block_device *bdev, dev_t dev);
 struct block_device *I_BDEV(struct inode *inode);
-int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart,
-		loff_t lend);
 
 #ifdef CONFIG_BLOCK
 void invalidate_bdev(struct block_device *bdev);
@@ -1488,6 +1494,7 @@ int sync_blockdev_nowait(struct block_device *bdev);
 void sync_bdevs(bool wait);
 void bdev_statx_dioalign(struct inode *inode, struct kstat *stat);
 void printk_all_partitions(void);
+int __init early_lookup_bdev(const char *pathname, dev_t *dev);
 #else
 static inline void invalidate_bdev(struct block_device *bdev)
 {
@@ -1509,6 +1516,10 @@ static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
 static inline void printk_all_partitions(void)
 {
 }
+static inline int early_lookup_bdev(const char *pathname, dev_t *dev)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_BLOCK */
 
 int fsync_bdev(struct block_device *bdev);
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index cfbda114348c..122c62e561fc 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -85,10 +85,14 @@ extern int blk_trace_remove(struct request_queue *q);
 # define blk_add_driver_data(rq, data, len)		do {} while (0)
 # define blk_trace_setup(q, name, dev, bdev, arg)	(-ENOTTY)
 # define blk_trace_startstop(q, start)			(-ENOTTY)
-# define blk_trace_remove(q)				(-ENOTTY)
 # define blk_add_trace_msg(q, fmt, ...)			do { } while (0)
 # define blk_add_cgroup_trace_msg(q, cg, fmt, ...)	do { } while (0)
 # define blk_trace_note_message_enabled(q)		(false)
+
+static inline int blk_trace_remove(struct request_queue *q)
+{
+	return -ENOTTY;
+}
 #endif /* CONFIG_BLK_DEV_IO_TRACE */
 
 #ifdef CONFIG_COMPAT
diff --git a/include/linux/bsg.h b/include/linux/bsg.h
index 1ac81c809da9..ee2df73edf83 100644
--- a/include/linux/bsg.h
+++ b/include/linux/bsg.h
@@ -9,7 +9,7 @@ struct device;
 struct request_queue;
 
 typedef int (bsg_sg_io_fn)(struct request_queue *, struct sg_io_v4 *hdr,
-		fmode_t mode, unsigned int timeout);
+		bool open_for_write, unsigned int timeout);
 
 struct bsg_device *bsg_register_queue(struct request_queue *q,
 		struct device *parent, const char *name,
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index 67caa909e3e6..98c6fd0b39b6 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -13,6 +13,7 @@
 
 #include <linux/fs.h>		/* not really needed, later.. */
 #include <linux/list.h>
+#include <linux/blkdev.h>
 #include <scsi/scsi_common.h>
 #include <uapi/linux/cdrom.h>
 
@@ -61,9 +62,9 @@ struct cdrom_device_info {
 	__u8 last_sense;
 	__u8 media_written;		/* dirty flag, DVD+RW bookkeeping */
 	unsigned short mmc3_profile;	/* current MMC3 profile */
-	int for_data;
 	int (*exit)(struct cdrom_device_info *);
 	int mrw_mode_page;
+	bool opened_for_data;
 	__s64 last_media_change_ms;
 };
 
@@ -101,11 +102,10 @@ int cdrom_read_tocentry(struct cdrom_device_info *cdi,
 		struct cdrom_tocentry *entry);
 
 /* the general block_device operations structure: */
-extern int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev,
-			fmode_t mode);
-extern void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode);
-extern int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev,
-		       fmode_t mode, unsigned int cmd, unsigned long arg);
+int cdrom_open(struct cdrom_device_info *cdi, blk_mode_t mode);
+void cdrom_release(struct cdrom_device_info *cdi);
+int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev,
+		unsigned int cmd, unsigned long arg);
 extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi,
 				       unsigned int clearing);
 
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index a52d2b9a6846..69d0435c7ebb 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -166,17 +166,15 @@ void dm_error(const char *message);
 struct dm_dev {
 	struct block_device *bdev;
 	struct dax_device *dax_dev;
-	fmode_t mode;
+	blk_mode_t mode;
 	char name[16];
 };
 
-dev_t dm_get_dev_t(const char *path);
-
 /*
  * Constructors should call these functions to ensure destination devices
  * are opened/closed correctly.
  */
-int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
+int dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode,
 		  struct dm_dev **result);
 void dm_put_device(struct dm_target *ti, struct dm_dev *d);
 
@@ -545,7 +543,7 @@ int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo);
 /*
  * First create an empty table.
  */
-int dm_table_create(struct dm_table **result, fmode_t mode,
+int dm_table_create(struct dm_table **result, blk_mode_t mode,
 		    unsigned int num_targets, struct mapped_device *md);
 
 /*
@@ -588,7 +586,7 @@ void dm_sync_table(struct mapped_device *md);
  * Queries
  */
 sector_t dm_table_get_size(struct dm_table *t);
-fmode_t dm_table_get_mode(struct dm_table *t);
+blk_mode_t dm_table_get_mode(struct dm_table *t);
 struct mapped_device *dm_table_get_md(struct dm_table *t);
 const char *dm_table_device_name(struct dm_table *t);
 
diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h
index c244267a6744..7738f458995f 100644
--- a/include/linux/device/driver.h
+++ b/include/linux/device/driver.h
@@ -126,7 +126,7 @@ int __must_check driver_register(struct device_driver *drv);
 void driver_unregister(struct device_driver *drv);
 
 struct device_driver *driver_find(const char *name, const struct bus_type *bus);
-int driver_probe_done(void);
+bool __init driver_probe_done(void);
 void wait_for_device_probe(void);
 void __init wait_for_init_devices_probe(void);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 42129a67d98d..ed5b32dc2625 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -119,13 +119,6 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define FMODE_PWRITE		((__force fmode_t)0x10)
 /* File is opened for execution with sys_execve / sys_uselib */
 #define FMODE_EXEC		((__force fmode_t)0x20)
-/* File is opened with O_NDELAY (only set for block devices) */
-#define FMODE_NDELAY		((__force fmode_t)0x40)
-/* File is opened with O_EXCL (only set for block devices) */
-#define FMODE_EXCL		((__force fmode_t)0x80)
-/* File is opened using open(.., 3, ..) and is writeable only for ioctls
-   (specialy hack for floppy.c) */
-#define FMODE_WRITE_IOCTL	((__force fmode_t)0x100)
 /* 32bit hashes as llseek() offset (for directories) */
 #define FMODE_32BITHASH         ((__force fmode_t)0x200)
 /* 64bit hashes as llseek() offset (for directories) */
@@ -1224,7 +1217,6 @@ struct super_block {
 	uuid_t			s_uuid;		/* UUID */
 
 	unsigned int		s_max_links;
-	fmode_t			s_mode;
 
 	/*
 	 * The next field is for VFS *only*. No filesystems have any business
@@ -1944,6 +1936,7 @@ struct super_operations {
 				  struct shrink_control *);
 	long (*free_cached_objects)(struct super_block *,
 				    struct shrink_control *);
+	void (*shutdown)(struct super_block *sb);
 };
 
 /*
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 27ce77080c79..200068d98686 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1910,6 +1910,28 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
 	return page_maybe_dma_pinned(page);
 }
 
+/**
+ * is_zero_page - Query if a page is a zero page
+ * @page: The page to query
+ *
+ * This returns true if @page is one of the permanent zero pages.
+ */
+static inline bool is_zero_page(const struct page *page)
+{
+	return is_zero_pfn(page_to_pfn(page));
+}
+
+/**
+ * is_zero_folio - Query if a folio is a zero page
+ * @folio: The folio to query
+ *
+ * This returns true if @folio is one of the permanent zero pages.
+ */
+static inline bool is_zero_folio(const struct folio *folio)
+{
+	return is_zero_page(&folio->page);
+}
+
 /* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */
 #ifdef CONFIG_MIGRATION
 static inline bool is_longterm_pinnable_page(struct page *page)
@@ -1920,8 +1942,8 @@ static inline bool is_longterm_pinnable_page(struct page *page)
 	if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
 		return false;
 #endif
-	/* The zero page may always be pinned */
-	if (is_zero_pfn(page_to_pfn(page)))
+	/* The zero page can be "pinned" but gets special handling. */
+	if (is_zero_page(page))
 		return true;
 
 	/* Coherent device memory must always allow eviction. */
@@ -2383,6 +2405,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages,
 			unsigned int gup_flags, struct page **pages);
 int pin_user_pages_fast(unsigned long start, int nr_pages,
 			unsigned int gup_flags, struct page **pages);
+void folio_add_pin(struct folio *folio);
 
 int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc);
 int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 1ea326c368f7..4b81ea90440e 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -107,7 +107,6 @@ extern struct vfsmount *vfs_submount(const struct dentry *mountpoint,
 extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list);
 extern void mark_mounts_for_expiry(struct list_head *mounts);
 
-extern dev_t name_to_dev_t(const char *name);
 extern bool path_is_mountpoint(const struct path *path);
 
 extern bool our_mnt(struct vfsmount *mnt);
diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h
index 15cc9b95e32b..6e471436bba5 100644
--- a/include/linux/mtd/blktrans.h
+++ b/include/linux/mtd/blktrans.h
@@ -34,7 +34,7 @@ struct mtd_blktrans_dev {
 	struct blk_mq_tag_set *tag_set;
 	spinlock_t queue_lock;
 	void *priv;
-	fmode_t file_mode;
+	bool writable;
 };
 
 struct mtd_blktrans_ops {
diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h
index fa092b9be2fd..4109f1bd6128 100644
--- a/include/linux/nvme-fc-driver.h
+++ b/include/linux/nvme-fc-driver.h
@@ -185,7 +185,6 @@ enum nvmefc_fcp_datadir {
  * @first_sgl: memory for 1st scatter/gather list segment for payload data
  * @sg_cnt:    number of elements in the scatter/gather list
  * @io_dir:    direction of the FCP request (see NVMEFC_FCP_xxx)
- * @sqid:      The nvme SQID the command is being issued on
  * @done:      The callback routine the LLDD is to invoke upon completion of
  *             the FCP operation. req argument is the pointer to the original
  *             FCP IO operation.
@@ -194,12 +193,13 @@ enum nvmefc_fcp_datadir {
  *             while processing the operation. The length of the buffer
  *             corresponds to the fcprqst_priv_sz value specified in the
  *             nvme_fc_port_template supplied by the LLDD.
+ * @sqid:      The nvme SQID the command is being issued on
  *
  * Values set by the LLDD indicating completion status of the FCP operation.
  * Must be set prior to calling the done() callback.
+ * @rcv_rsplen: length, in bytes, of the FCP RSP IU received.
  * @transferred_length: amount of payload data, in bytes, that were
  *             transferred. Should equal payload_length on success.
- * @rcv_rsplen: length, in bytes, of the FCP RSP IU received.
  * @status:    Completion status of the FCP operation. must be 0 upon success,
  *             negative errno value upon failure (ex: -EIO). Note: this is
  *             NOT a reflection of the NVME CQE completion status. Only the
@@ -219,14 +219,14 @@ struct nvmefc_fcp_req {
 	int			sg_cnt;
 	enum nvmefc_fcp_datadir	io_dir;
 
-	__le16			sqid;
-
 	void (*done)(struct nvmefc_fcp_req *req);
 
 	void			*private;
 
-	u32			transferred_length;
+	__le16			sqid;
+
 	u16			rcv_rsplen;
+	u32			transferred_length;
 	u32			status;
 } __aligned(sizeof(u64));	/* alignment for other things alloc'd with */
 
diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h
index f9c5ac80d59b..80cb00db42a4 100644
--- a/include/linux/pktcdvd.h
+++ b/include/linux/pktcdvd.h
@@ -156,7 +156,6 @@ struct pktcdvd_device
 {
 	struct block_device	*bdev;		/* dev attached */
 	dev_t			pkt_dev;	/* our dev */
-	char			name[20];
 	struct packet_settings	settings;
 	struct packet_stats	stats;
 	int			refcnt;		/* Open count */
diff --git a/include/linux/root_dev.h b/include/linux/root_dev.h
index 4e78651371ba..847c9a06101b 100644
--- a/include/linux/root_dev.h
+++ b/include/linux/root_dev.h
@@ -9,15 +9,8 @@
 enum {
 	Root_NFS = MKDEV(UNNAMED_MAJOR, 255),
 	Root_CIFS = MKDEV(UNNAMED_MAJOR, 254),
+	Root_Generic = MKDEV(UNNAMED_MAJOR, 253),
 	Root_RAM0 = MKDEV(RAMDISK_MAJOR, 0),
-	Root_RAM1 = MKDEV(RAMDISK_MAJOR, 1),
-	Root_FD0 = MKDEV(FLOPPY_MAJOR, 0),
-	Root_HDA1 = MKDEV(IDE0_MAJOR, 1),
-	Root_HDA2 = MKDEV(IDE0_MAJOR, 2),
-	Root_SDA1 = MKDEV(SCSI_DISK0_MAJOR, 1),
-	Root_SDA2 = MKDEV(SCSI_DISK0_MAJOR, 2),
-	Root_HDC1 = MKDEV(IDE1_MAJOR, 1),
-	Root_SR0 = MKDEV(SCSI_CDROM_MAJOR, 0),
 };
 
 extern dev_t ROOT_DEV;
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 60c342bb7ab8..8e7d2c425340 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -277,14 +277,8 @@ void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_
 void iov_iter_discard(struct iov_iter *i, unsigned int direction, size_t count);
 void iov_iter_xarray(struct iov_iter *i, unsigned int direction, struct xarray *xarray,
 		     loff_t start, size_t count);
-ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages,
-		size_t maxsize, unsigned maxpages, size_t *start,
-		iov_iter_extraction_t extraction_flags);
 ssize_t iov_iter_get_pages2(struct iov_iter *i, struct page **pages,
 			size_t maxsize, unsigned maxpages, size_t *start);
-ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
-		struct page ***pages, size_t maxsize, size_t *start,
-		iov_iter_extraction_t extraction_flags);
 ssize_t iov_iter_get_pages_alloc2(struct iov_iter *i, struct page ***pages,
 			size_t maxsize, size_t *start);
 int iov_iter_npages(const struct iov_iter *i, int maxpages);
diff --git a/include/scsi/scsi_ioctl.h b/include/scsi/scsi_ioctl.h
index beac64e38b87..a207c07da9d2 100644
--- a/include/scsi/scsi_ioctl.h
+++ b/include/scsi/scsi_ioctl.h
@@ -45,11 +45,11 @@ typedef struct scsi_fctargaddress {
 
 int scsi_ioctl_block_when_processing_errors(struct scsi_device *sdev,
 		int cmd, bool ndelay);
-int scsi_ioctl(struct scsi_device *sdev, fmode_t mode, int cmd,
+int scsi_ioctl(struct scsi_device *sdev, bool open_for_write, int cmd,
 		void __user *arg);
 int get_sg_io_hdr(struct sg_io_hdr *hdr, const void __user *argp);
 int put_sg_io_hdr(const struct sg_io_hdr *hdr, void __user *argp);
-bool scsi_cmd_allowed(unsigned char *cmd, fmode_t mode);
+bool scsi_cmd_allowed(unsigned char *cmd, bool open_for_write);
 
 #endif /* __KERNEL__ */
 #endif /* _SCSI_IOCTL_H */
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 7f4dfbdf12a6..40e60c33cc6f 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -246,6 +246,32 @@ DEFINE_EVENT(block_rq, block_rq_merge,
 );
 
 /**
+ * block_io_start - insert a request for execution
+ * @rq: block IO operation request
+ *
+ * Called when block operation request @rq is queued for execution
+ */
+DEFINE_EVENT(block_rq, block_io_start,
+
+	TP_PROTO(struct request *rq),
+
+	TP_ARGS(rq)
+);
+
+/**
+ * block_io_done - block IO operation request completed
+ * @rq: block IO operation request
+ *
+ * Called when block operation request @rq is completed
+ */
+DEFINE_EVENT(block_rq, block_io_done,
+
+	TP_PROTO(struct request *rq),
+
+	TP_ARGS(rq)
+);
+
+/**
  * block_bio_complete - completed all work on the block operation
  * @q: queue holding the block operation
  * @bio: block operation completed
diff --git a/include/uapi/linux/affs_hardblocks.h b/include/uapi/linux/affs_hardblocks.h
index 5e2fb8481252..a5aff2eb5f70 100644
--- a/include/uapi/linux/affs_hardblocks.h
+++ b/include/uapi/linux/affs_hardblocks.h
@@ -7,42 +7,42 @@
 /* Just the needed definitions for the RDB of an Amiga HD. */
 
 struct RigidDiskBlock {
-	__u32	rdb_ID;
+	__be32	rdb_ID;
 	__be32	rdb_SummedLongs;
-	__s32	rdb_ChkSum;
-	__u32	rdb_HostID;
+	__be32	rdb_ChkSum;
+	__be32	rdb_HostID;
 	__be32	rdb_BlockBytes;
-	__u32	rdb_Flags;
-	__u32	rdb_BadBlockList;
+	__be32	rdb_Flags;
+	__be32	rdb_BadBlockList;
 	__be32	rdb_PartitionList;
-	__u32	rdb_FileSysHeaderList;
-	__u32	rdb_DriveInit;
-	__u32	rdb_Reserved1[6];
-	__u32	rdb_Cylinders;
-	__u32	rdb_Sectors;
-	__u32	rdb_Heads;
-	__u32	rdb_Interleave;
-	__u32	rdb_Park;
-	__u32	rdb_Reserved2[3];
-	__u32	rdb_WritePreComp;
-	__u32	rdb_ReducedWrite;
-	__u32	rdb_StepRate;
-	__u32	rdb_Reserved3[5];
-	__u32	rdb_RDBBlocksLo;
-	__u32	rdb_RDBBlocksHi;
-	__u32	rdb_LoCylinder;
-	__u32	rdb_HiCylinder;
-	__u32	rdb_CylBlocks;
-	__u32	rdb_AutoParkSeconds;
-	__u32	rdb_HighRDSKBlock;
-	__u32	rdb_Reserved4;
+	__be32	rdb_FileSysHeaderList;
+	__be32	rdb_DriveInit;
+	__be32	rdb_Reserved1[6];
+	__be32	rdb_Cylinders;
+	__be32	rdb_Sectors;
+	__be32	rdb_Heads;
+	__be32	rdb_Interleave;
+	__be32	rdb_Park;
+	__be32	rdb_Reserved2[3];
+	__be32	rdb_WritePreComp;
+	__be32	rdb_ReducedWrite;
+	__be32	rdb_StepRate;
+	__be32	rdb_Reserved3[5];
+	__be32	rdb_RDBBlocksLo;
+	__be32	rdb_RDBBlocksHi;
+	__be32	rdb_LoCylinder;
+	__be32	rdb_HiCylinder;
+	__be32	rdb_CylBlocks;
+	__be32	rdb_AutoParkSeconds;
+	__be32	rdb_HighRDSKBlock;
+	__be32	rdb_Reserved4;
 	char	rdb_DiskVendor[8];
 	char	rdb_DiskProduct[16];
 	char	rdb_DiskRevision[4];
 	char	rdb_ControllerVendor[8];
 	char	rdb_ControllerProduct[16];
 	char	rdb_ControllerRevision[4];
-	__u32	rdb_Reserved5[10];
+	__be32	rdb_Reserved5[10];
 };
 
 #define	IDNAME_RIGIDDISK	0x5244534B	/* "RDSK" */
@@ -50,16 +50,16 @@ struct RigidDiskBlock {
 struct PartitionBlock {
 	__be32	pb_ID;
 	__be32	pb_SummedLongs;
-	__s32	pb_ChkSum;
-	__u32	pb_HostID;
+	__be32	pb_ChkSum;
+	__be32	pb_HostID;
 	__be32	pb_Next;
-	__u32	pb_Flags;
-	__u32	pb_Reserved1[2];
-	__u32	pb_DevFlags;
+	__be32	pb_Flags;
+	__be32	pb_Reserved1[2];
+	__be32	pb_DevFlags;
 	__u8	pb_DriveName[32];
-	__u32	pb_Reserved2[15];
+	__be32	pb_Reserved2[15];
 	__be32	pb_Environment[17];
-	__u32	pb_EReserved[15];
+	__be32	pb_EReserved[15];
 };
 
 #define	IDNAME_PARTITION	0x50415254	/* "PART" */
diff --git a/include/uapi/linux/pktcdvd.h b/include/uapi/linux/pktcdvd.h
index 6a5552dfd6af..987a3022dc5f 100644
--- a/include/uapi/linux/pktcdvd.h
+++ b/include/uapi/linux/pktcdvd.h
@@ -16,6 +16,7 @@
 #include <linux/types.h>
 
 /*
+ * UNUSED:
  * 1 for normal debug messages, 2 is very verbose. 0 to turn it off.
  */
 #define PACKET_DEBUG		1
diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
index 640bf687b94a..4b8558db90e1 100644
--- a/include/uapi/linux/ublk_cmd.h
+++ b/include/uapi/linux/ublk_cmd.h
@@ -47,6 +47,14 @@
 	_IOWR('u', UBLK_CMD_END_USER_RECOVERY, struct ublksrv_ctrl_cmd)
 #define UBLK_U_CMD_GET_DEV_INFO2	\
 	_IOR('u', UBLK_CMD_GET_DEV_INFO2, struct ublksrv_ctrl_cmd)
+#define UBLK_U_CMD_GET_FEATURES	\
+	_IOR('u', 0x13, struct ublksrv_ctrl_cmd)
+
+/*
+ * 64bits are enough now, and it should be easy to extend in case of
+ * running out of feature flags
+ */
+#define UBLK_FEATURES_LEN  8
 
 /*
  * IO commands, issued by ublk server, and handled by ublk driver.
@@ -93,9 +101,29 @@
 #define UBLKSRV_CMD_BUF_OFFSET	0
 #define UBLKSRV_IO_BUF_OFFSET	0x80000000
 
-/* tag bit is 12bit, so at most 4096 IOs for each queue */
+/* tag bit is 16bit, so far limit at most 4096 IOs for each queue */
 #define UBLK_MAX_QUEUE_DEPTH	4096
 
+/* single IO buffer max size is 32MB */
+#define UBLK_IO_BUF_OFF		0
+#define UBLK_IO_BUF_BITS	25
+#define UBLK_IO_BUF_BITS_MASK	((1ULL << UBLK_IO_BUF_BITS) - 1)
+
+/* so at most 64K IOs for each queue */
+#define UBLK_TAG_OFF		UBLK_IO_BUF_BITS
+#define UBLK_TAG_BITS		16
+#define UBLK_TAG_BITS_MASK	((1ULL << UBLK_TAG_BITS) - 1)
+
+/* max 4096 queues */
+#define UBLK_QID_OFF		(UBLK_TAG_OFF + UBLK_TAG_BITS)
+#define UBLK_QID_BITS		12
+#define UBLK_QID_BITS_MASK	((1ULL << UBLK_QID_BITS) - 1)
+
+#define UBLK_MAX_NR_QUEUES	(1U << UBLK_QID_BITS)
+
+#define UBLKSRV_IO_BUF_TOTAL_BITS	(UBLK_QID_OFF + UBLK_QID_BITS)
+#define UBLKSRV_IO_BUF_TOTAL_SIZE	(1ULL << UBLKSRV_IO_BUF_TOTAL_BITS)
+
 /*
  * zero copy requires 4k block size, and can remap ublk driver's io
  * request into ublksrv's vm space
@@ -145,6 +173,9 @@
 /* use ioctl encoding for uring command */
 #define UBLK_F_CMD_IOCTL_ENCODE	(1UL << 6)
 
+/* Copy between request and user buffer by pread()/pwrite() */
+#define UBLK_F_USER_COPY	(1UL << 7)
+
 /* device state */
 #define UBLK_S_DEV_DEAD	0
 #define UBLK_S_DEV_LIVE	1