Merge tag 'for-6.11/block-20240710' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe updates via Keith:
     - Device initialization memory leak fixes (Keith)
     - More constants defined (Weiwen)
     - Target debugfs support (Hannes)
     - PCIe subsystem reset enhancements (Keith)
     - Queue-depth multipath policy (Redhat and PureStorage)
     - Implement get_unique_id (Christoph)
     - Authentication error fixes (Gaosheng)

 - MD updates via Song
     - sync_action fix and refactoring (Yu Kuai)
     - Various small fixes (Christoph Hellwig, Li Nan, and Ofir Gal, Yu
       Kuai, Benjamin Marzinski, Christophe JAILLET, Yang Li)

 - Fix loop detach/open race (Gulam)

 - Fix lower control limit for blk-throttle (Yu)

 - Add module descriptions to various drivers (Jeff)

 - Add support for atomic writes for block devices, and statx reporting
   for same. Includes SCSI and NVMe (John, Prasad, Alan)

 - Add IO priority information to block trace points (Dongliang)

 - Various zone improvements and tweaks (Damien)

 - mq-deadline tag reservation improvements (Bart)

 - Ignore direct reclaim swap writes in writeback throttling (Baokun)

 - Block integrity improvements and fixes (Anuj)

 - Add basic support for rust based block drivers. Has a dummy null_blk
   variant for now (Andreas)

 - Series converting driver settings to queue limits, and cleanups and
   fixes related to that (Christoph)

 - Cleanup for poking too deeply into the bvec internals, in preparation
   for DMA mapping API changes (Christoph)

 - Various minor tweaks and fixes (Jiapeng, John, Kanchan, Mikulas,
   Ming, Zhu, Damien, Christophe, Chaitanya)

* tag 'for-6.11/block-20240710' of git://git.kernel.dk/linux: (206 commits)
  floppy: add missing MODULE_DESCRIPTION() macro
  loop: add missing MODULE_DESCRIPTION() macro
  ublk_drv: add missing MODULE_DESCRIPTION() macro
  xen/blkback: add missing MODULE_DESCRIPTION() macro
  block/rnbd: Constify struct kobj_type
  block: take offset into account in blk_bvec_map_sg again
  block: fix get_max_segment_size() warning
  loop: Don't bother validating blocksize
  virtio_blk: Don't bother validating blocksize
  null_blk: Don't bother validating blocksize
  block: Validate logical block size in blk_validate_limits()
  virtio_blk: Fix default logical block size fallback
  nvmet-auth: fix nvmet_auth hash error handling
  nvme: implement ->get_unique_id
  block: pass a phys_addr_t to get_max_segment_size
  block: add a bvec_phys helper
  blk-lib: check for kill signal in ioctl BLKZEROOUT
  block: limit the Write Zeroes to manually writing zeroes fallback
  block: refacto blkdev_issue_zeroout
  block: move read-only and supported checks into (__)blkdev_issue_zeroout
  ...

15 files changed, 363 insertions, 227 deletions

diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h
index 7428cb43952d..804f856ed3e5 100644
--- a/include/linux/blk-integrity.h
+++ b/include/linux/blk-integrity.h
@@ -7,51 +7,38 @@
 struct request;
 
 enum blk_integrity_flags {
-	BLK_INTEGRITY_VERIFY		= 1 << 0,
-	BLK_INTEGRITY_GENERATE		= 1 << 1,
+	BLK_INTEGRITY_NOVERIFY		= 1 << 0,
+	BLK_INTEGRITY_NOGENERATE	= 1 << 1,
 	BLK_INTEGRITY_DEVICE_CAPABLE	= 1 << 2,
-	BLK_INTEGRITY_IP_CHECKSUM	= 1 << 3,
+	BLK_INTEGRITY_REF_TAG		= 1 << 3,
+	BLK_INTEGRITY_STACKED		= 1 << 4,
 };
 
-struct blk_integrity_iter {
-	void			*prot_buf;
-	void			*data_buf;
-	sector_t		seed;
-	unsigned int		data_size;
-	unsigned short		interval;
-	unsigned char		tuple_size;
-	unsigned char		pi_offset;
-	const char		*disk_name;
-};
-
-typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *);
-typedef void (integrity_prepare_fn) (struct request *);
-typedef void (integrity_complete_fn) (struct request *, unsigned int);
-
-struct blk_integrity_profile {
-	integrity_processing_fn		*generate_fn;
-	integrity_processing_fn		*verify_fn;
-	integrity_prepare_fn		*prepare_fn;
-	integrity_complete_fn		*complete_fn;
-	const char			*name;
-};
+const char *blk_integrity_profile_name(struct blk_integrity *bi);
+bool queue_limits_stack_integrity(struct queue_limits *t,
+		struct queue_limits *b);
+static inline bool queue_limits_stack_integrity_bdev(struct queue_limits *t,
+		struct block_device *bdev)
+{
+	return queue_limits_stack_integrity(t, &bdev->bd_disk->queue->limits);
+}
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
-void blk_integrity_register(struct gendisk *, struct blk_integrity *);
-void blk_integrity_unregister(struct gendisk *);
-int blk_integrity_compare(struct gendisk *, struct gendisk *);
 int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
 				   struct scatterlist *);
 int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
 
-static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
+static inline bool
+blk_integrity_queue_supports_integrity(struct request_queue *q)
 {
-	struct blk_integrity *bi = &disk->queue->integrity;
+	return q->limits.integrity.tuple_size;
+}
 
-	if (!bi->profile)
+static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
+{
+	if (!blk_integrity_queue_supports_integrity(disk->queue))
 		return NULL;
-
-	return bi;
+	return &disk->queue->limits.integrity;
 }
 
 static inline struct blk_integrity *
@@ -60,12 +47,6 @@ bdev_get_integrity(struct block_device *bdev)
 	return blk_get_integrity(bdev->bd_disk);
 }
 
-static inline bool
-blk_integrity_queue_supports_integrity(struct request_queue *q)
-{
-	return q->integrity.profile;
-}
-
 static inline unsigned short
 queue_max_integrity_segments(const struct request_queue *q)
 {
@@ -100,14 +81,13 @@ static inline bool blk_integrity_rq(struct request *rq)
 }
 
 /*
- * Return the first bvec that contains integrity data.  Only drivers that are
- * limited to a single integrity segment should use this helper.
+ * Return the current bvec that contains the integrity data. bip_iter may be
+ * advanced to iterate over the integrity data.
  */
-static inline struct bio_vec *rq_integrity_vec(struct request *rq)
+static inline struct bio_vec rq_integrity_vec(struct request *rq)
 {
-	if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1))
-		return NULL;
-	return rq->bio->bi_integrity->bip_vec;
+	return mp_bvec_iter_bvec(rq->bio->bi_integrity->bip_vec,
+				 rq->bio->bi_integrity->bip_iter);
 }
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 static inline int blk_rq_count_integrity_sg(struct request_queue *q,
@@ -134,17 +114,6 @@ blk_integrity_queue_supports_integrity(struct request_queue *q)
 {
 	return false;
 }
-static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b)
-{
-	return 0;
-}
-static inline void blk_integrity_register(struct gendisk *d,
-					 struct blk_integrity *b)
-{
-}
-static inline void blk_integrity_unregister(struct gendisk *d)
-{
-}
 static inline unsigned short
 queue_max_integrity_segments(const struct request_queue *q)
 {
@@ -167,9 +136,11 @@ static inline int blk_integrity_rq(struct request *rq)
 	return 0;
 }
 
-static inline struct bio_vec *rq_integrity_vec(struct request *rq)
+static inline struct bio_vec rq_integrity_vec(struct request *rq)
 {
-	return NULL;
+	/* the optimizer will remove all calls to this function */
+	return (struct bio_vec){ };
 }
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
+
 #endif /* _LINUX_BLK_INTEGRITY_H */
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 781c4500491b..632edd71f8c6 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -162,6 +162,11 @@ typedef u16 blk_short_t;
  */
 #define BLK_STS_DURATION_LIMIT	((__force blk_status_t)17)
 
+/*
+ * Invalid size or alignment.
+ */
+#define BLK_STS_INVAL	((__force blk_status_t)19)
+
 /**
  * blk_path_error - returns true if error may be path related
  * @error: status the request was completed with
@@ -370,7 +375,7 @@ enum req_flag_bits {
 	__REQ_SWAP,		/* swap I/O */
 	__REQ_DRV,		/* for driver use */
 	__REQ_FS_PRIVATE,	/* for file system (submitter) use */
-
+	__REQ_ATOMIC,		/* for atomic write operations */
 	/*
 	 * Command specific flags, keep last:
 	 */
@@ -402,6 +407,7 @@ enum req_flag_bits {
 #define REQ_SWAP	(__force blk_opf_t)(1ULL << __REQ_SWAP)
 #define REQ_DRV		(__force blk_opf_t)(1ULL << __REQ_DRV)
 #define REQ_FS_PRIVATE	(__force blk_opf_t)(1ULL << __REQ_FS_PRIVATE)
+#define REQ_ATOMIC	(__force blk_opf_t)(1ULL << __REQ_ATOMIC)
 
 #define REQ_NOUNMAP	(__force blk_opf_t)(1ULL << __REQ_NOUNMAP)
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 24c36929920b..b8196e219ac2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -105,9 +105,16 @@ enum {
 struct disk_events;
 struct badblocks;
 
+enum blk_integrity_checksum {
+	BLK_INTEGRITY_CSUM_NONE		= 0,
+	BLK_INTEGRITY_CSUM_IP		= 1,
+	BLK_INTEGRITY_CSUM_CRC		= 2,
+	BLK_INTEGRITY_CSUM_CRC64	= 3,
+} __packed ;
+
 struct blk_integrity {
-	const struct blk_integrity_profile	*profile;
 	unsigned char				flags;
+	enum blk_integrity_checksum		csum_type;
 	unsigned char				tuple_size;
 	unsigned char				pi_offset;
 	unsigned char				interval_exp;
@@ -261,6 +268,7 @@ static inline dev_t disk_devt(struct gendisk *disk)
 	return MKDEV(disk->major, disk->first_minor);
 }
 
+/* blk_validate_limits() validates bsize, so drivers don't usually need to */
 static inline int blk_validate_block_size(unsigned long bsize)
 {
 	if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize))
@@ -275,17 +283,75 @@ static inline bool blk_op_is_passthrough(blk_opf_t op)
 	return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT;
 }
 
+/* flags set by the driver in queue_limits.features */
+typedef unsigned int __bitwise blk_features_t;
+
+/* supports a volatile write cache */
+#define BLK_FEAT_WRITE_CACHE		((__force blk_features_t)(1u << 0))
+
+/* supports passing on the FUA bit */
+#define BLK_FEAT_FUA			((__force blk_features_t)(1u << 1))
+
+/* rotational device (hard drive or floppy) */
+#define BLK_FEAT_ROTATIONAL		((__force blk_features_t)(1u << 2))
+
+/* contributes to the random number pool */
+#define BLK_FEAT_ADD_RANDOM		((__force blk_features_t)(1u << 3))
+
+/* do disk/partitions IO accounting */
+#define BLK_FEAT_IO_STAT		((__force blk_features_t)(1u << 4))
+
+/* don't modify data until writeback is done */
+#define BLK_FEAT_STABLE_WRITES		((__force blk_features_t)(1u << 5))
+
+/* always completes in submit context */
+#define BLK_FEAT_SYNCHRONOUS		((__force blk_features_t)(1u << 6))
+
+/* supports REQ_NOWAIT */
+#define BLK_FEAT_NOWAIT			((__force blk_features_t)(1u << 7))
+
+/* supports DAX */
+#define BLK_FEAT_DAX			((__force blk_features_t)(1u << 8))
+
+/* supports I/O polling */
+#define BLK_FEAT_POLL			((__force blk_features_t)(1u << 9))
+
+/* is a zoned device */
+#define BLK_FEAT_ZONED			((__force blk_features_t)(1u << 10))
+
+/* supports PCI(e) p2p requests */
+#define BLK_FEAT_PCI_P2PDMA		((__force blk_features_t)(1u << 12))
+
+/* 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))
+
 /*
- * BLK_BOUNCE_NONE:	never bounce (default)
- * BLK_BOUNCE_HIGH:	bounce all highmem pages
+ * Flags automatically inherited when stacking limits.
  */
-enum blk_bounce {
-	BLK_BOUNCE_NONE,
-	BLK_BOUNCE_HIGH,
-};
+#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_RAID_PARTIAL_STRIPES_EXPENSIVE)
+
+/* internal flags in queue_limits.flags */
+typedef unsigned int __bitwise blk_flags_t;
+
+/* do not send FLUSH/FUA commands despite advertising a write cache */
+#define BLK_FLAG_WRITE_CACHE_DISABLED	((__force blk_flags_t)(1u << 0))
+
+/* I/O topology is misaligned */
+#define BLK_FLAG_MISALIGNED		((__force blk_flags_t)(1u << 1))
 
 struct queue_limits {
-	enum blk_bounce		bounce;
+	blk_features_t		features;
+	blk_flags_t		flags;
 	unsigned long		seg_boundary_mask;
 	unsigned long		virt_boundary_mask;
 
@@ -310,14 +376,20 @@ struct queue_limits {
 	unsigned int		discard_alignment;
 	unsigned int		zone_write_granularity;
 
+	/* atomic write limits */
+	unsigned int		atomic_write_hw_max;
+	unsigned int		atomic_write_max_sectors;
+	unsigned int		atomic_write_hw_boundary;
+	unsigned int		atomic_write_boundary_sectors;
+	unsigned int		atomic_write_hw_unit_min;
+	unsigned int		atomic_write_unit_min;
+	unsigned int		atomic_write_hw_unit_max;
+	unsigned int		atomic_write_unit_max;
+
 	unsigned short		max_segments;
 	unsigned short		max_integrity_segments;
 	unsigned short		max_discard_segments;
 
-	unsigned char		misaligned;
-	unsigned char		discard_misaligned;
-	unsigned char		raid_partial_stripes_expensive;
-	bool			zoned;
 	unsigned int		max_open_zones;
 	unsigned int		max_active_zones;
 
@@ -327,13 +399,14 @@ struct queue_limits {
 	 * due to possible offsets.
 	 */
 	unsigned int		dma_alignment;
+	unsigned int		dma_pad_mask;
+
+	struct blk_integrity	integrity;
 };
 
 typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
 			       void *data);
 
-void disk_set_zoned(struct gendisk *disk);
-
 #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);
@@ -414,10 +487,6 @@ struct request_queue {
 
 	struct queue_limits	limits;
 
-#ifdef  CONFIG_BLK_DEV_INTEGRITY
-	struct blk_integrity integrity;
-#endif	/* CONFIG_BLK_DEV_INTEGRITY */
-
 #ifdef CONFIG_PM
 	struct device		*dev;
 	enum rpm_status		rpm_status;
@@ -439,8 +508,6 @@ struct request_queue {
 	 */
 	int			id;
 
-	unsigned int		dma_pad_mask;
-
 	/*
 	 * queue settings
 	 */
@@ -526,38 +593,20 @@ struct request_queue {
 #define QUEUE_FLAG_NOMERGES     3	/* disable merge attempts */
 #define QUEUE_FLAG_SAME_COMP	4	/* complete on same CPU-group */
 #define QUEUE_FLAG_FAIL_IO	5	/* fake timeout */
-#define QUEUE_FLAG_NONROT	6	/* non-rotational device (SSD) */
-#define QUEUE_FLAG_VIRT		QUEUE_FLAG_NONROT /* paravirt device */
-#define QUEUE_FLAG_IO_STAT	7	/* do disk/partitions IO accounting */
 #define QUEUE_FLAG_NOXMERGES	9	/* No extended merges */
-#define QUEUE_FLAG_ADD_RANDOM	10	/* Contributes to random pool */
-#define QUEUE_FLAG_SYNCHRONOUS	11	/* always completes in submit context */
 #define QUEUE_FLAG_SAME_FORCE	12	/* force complete on same CPU */
-#define QUEUE_FLAG_HW_WC	13	/* Write back caching supported */
 #define QUEUE_FLAG_INIT_DONE	14	/* queue is initialized */
-#define QUEUE_FLAG_STABLE_WRITES 15	/* don't modify blks until WB is done */
-#define QUEUE_FLAG_POLL		16	/* IO polling enabled if set */
-#define QUEUE_FLAG_WC		17	/* Write back caching */
-#define QUEUE_FLAG_FUA		18	/* device supports FUA writes */
-#define QUEUE_FLAG_DAX		19	/* device supports DAX */
 #define QUEUE_FLAG_STATS	20	/* track IO start and completion times */
 #define QUEUE_FLAG_REGISTERED	22	/* queue has been registered to a disk */
 #define QUEUE_FLAG_QUIESCED	24	/* queue has been quiesced */
-#define QUEUE_FLAG_PCI_P2PDMA	25	/* device supports PCI p2p requests */
-#define QUEUE_FLAG_ZONE_RESETALL 26	/* supports Zone Reset All */
 #define QUEUE_FLAG_RQ_ALLOC_TIME 27	/* record rq->alloc_time_ns */
 #define QUEUE_FLAG_HCTX_ACTIVE	28	/* at least one blk-mq hctx is active */
-#define QUEUE_FLAG_NOWAIT       29	/* device supports NOWAIT */
 #define QUEUE_FLAG_SQ_SCHED     30	/* single queue style io dispatch */
-#define QUEUE_FLAG_SKIP_TAGSET_QUIESCE	31 /* quiesce_tagset skip the queue*/
 
-#define QUEUE_FLAG_MQ_DEFAULT	((1UL << QUEUE_FLAG_IO_STAT) |		\
-				 (1UL << QUEUE_FLAG_SAME_COMP) |	\
-				 (1UL << QUEUE_FLAG_NOWAIT))
+#define QUEUE_FLAG_MQ_DEFAULT	(1UL << QUEUE_FLAG_SAME_COMP)
 
 void blk_queue_flag_set(unsigned int flag, struct request_queue *q);
 void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
-bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_dying(q)	test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags)
@@ -565,16 +614,10 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_noxmerges(q)	\
 	test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
-#define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
-#define blk_queue_stable_writes(q) \
-	test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags)
-#define blk_queue_io_stat(q)	test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
-#define blk_queue_add_random(q)	test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
-#define blk_queue_zone_resetall(q)	\
-	test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags)
-#define blk_queue_dax(q)	test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags)
-#define blk_queue_pci_p2pdma(q)	\
-	test_bit(QUEUE_FLAG_PCI_P2PDMA, &(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_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
 #define blk_queue_rq_alloc_time(q)	\
 	test_bit(QUEUE_FLAG_RQ_ALLOC_TIME, &(q)->queue_flags)
@@ -590,7 +633,7 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_registered(q)	test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
 #define blk_queue_sq_sched(q)	test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags)
 #define blk_queue_skip_tagset_quiesce(q) \
-	test_bit(QUEUE_FLAG_SKIP_TAGSET_QUIESCE, &(q)->queue_flags)
+	((q)->limits.features & BLK_FEAT_SKIP_TAGSET_QUIESCE)
 
 extern void blk_set_pm_only(struct request_queue *q);
 extern void blk_clear_pm_only(struct request_queue *q);
@@ -620,16 +663,26 @@ static inline enum rpm_status queue_rpm_status(struct request_queue *q)
 
 static inline bool blk_queue_is_zoned(struct request_queue *q)
 {
-	return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && q->limits.zoned;
+	return IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+		(q->limits.features & BLK_FEAT_ZONED);
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
-unsigned int bdev_nr_zones(struct block_device *bdev);
-
 static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
-	return blk_queue_is_zoned(disk->queue) ? disk->nr_zones : 0;
+	return disk->nr_zones;
+}
+bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs);
+#else /* CONFIG_BLK_DEV_ZONED */
+static inline unsigned int disk_nr_zones(struct gendisk *disk)
+{
+	return 0;
 }
+static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
+{
+	return false;
+}
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 {
@@ -638,16 +691,9 @@ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 	return sector >> ilog2(disk->queue->limits.chunk_sectors);
 }
 
-static inline void disk_set_max_open_zones(struct gendisk *disk,
-		unsigned int max_open_zones)
-{
-	disk->queue->limits.max_open_zones = max_open_zones;
-}
-
-static inline void disk_set_max_active_zones(struct gendisk *disk,
-		unsigned int max_active_zones)
+static inline unsigned int bdev_nr_zones(struct block_device *bdev)
 {
-	disk->queue->limits.max_active_zones = max_active_zones;
+	return disk_nr_zones(bdev->bd_disk);
 }
 
 static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
@@ -660,36 +706,6 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
 	return bdev->bd_disk->queue->limits.max_active_zones;
 }
 
-bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs);
-#else /* CONFIG_BLK_DEV_ZONED */
-static inline unsigned int bdev_nr_zones(struct block_device *bdev)
-{
-	return 0;
-}
-
-static inline unsigned int disk_nr_zones(struct gendisk *disk)
-{
-	return 0;
-}
-static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
-{
-	return 0;
-}
-static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
-{
-	return 0;
-}
-
-static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
-{
-	return 0;
-}
-static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
-{
-	return false;
-}
-#endif /* CONFIG_BLK_DEV_ZONED */
-
 static inline unsigned int blk_queue_depth(struct request_queue *q)
 {
 	if (q->queue_depth)
@@ -880,14 +896,15 @@ static inline bool bio_straddles_zones(struct bio *bio)
 }
 
 /*
- * Return how much of the chunk is left to be used for I/O at a given offset.
+ * Return how much within the boundary is left to be used for I/O at a given
+ * offset.
  */
-static inline unsigned int blk_chunk_sectors_left(sector_t offset,
-		unsigned int chunk_sectors)
+static inline unsigned int blk_boundary_sectors_left(sector_t offset,
+		unsigned int boundary_sectors)
 {
-	if (unlikely(!is_power_of_2(chunk_sectors)))
-		return chunk_sectors - sector_div(offset, chunk_sectors);
-	return chunk_sectors - (offset & (chunk_sectors - 1));
+	if (unlikely(!is_power_of_2(boundary_sectors)))
+		return boundary_sectors - sector_div(offset, boundary_sectors);
+	return boundary_sectors - (offset & (boundary_sectors - 1));
 }
 
 /**
@@ -904,7 +921,6 @@ static inline unsigned int blk_chunk_sectors_left(sector_t offset,
  */
 static inline struct queue_limits
 queue_limits_start_update(struct request_queue *q)
-	__acquires(q->limits_lock)
 {
 	mutex_lock(&q->limits_lock);
 	return q->limits;
@@ -927,26 +943,31 @@ static inline void queue_limits_cancel_update(struct request_queue *q)
 }
 
 /*
+ * These helpers are for drivers that have sloppy feature negotiation and might
+ * have to disable DISCARD, WRITE_ZEROES or SECURE_DISCARD from the I/O
+ * completion handler when the device returned an indicator that the respective
+ * feature is not actually supported.  They are racy and the driver needs to
+ * cope with that.  Try to avoid this scheme if you can.
+ */
+static inline void blk_queue_disable_discard(struct request_queue *q)
+{
+	q->limits.max_discard_sectors = 0;
+}
+
+static inline void blk_queue_disable_secure_erase(struct request_queue *q)
+{
+	q->limits.max_secure_erase_sectors = 0;
+}
+
+static inline void blk_queue_disable_write_zeroes(struct request_queue *q)
+{
+	q->limits.max_write_zeroes_sectors = 0;
+}
+
+/*
  * Access functions for manipulating queue properties
  */
-extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
-void blk_queue_max_secure_erase_sectors(struct request_queue *q,
-		unsigned int max_sectors);
-extern void blk_queue_max_discard_sectors(struct request_queue *q,
-		unsigned int max_discard_sectors);
-extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
-		unsigned int max_write_same_sectors);
-extern void blk_queue_logical_block_size(struct request_queue *, unsigned int);
-extern void blk_queue_max_zone_append_sectors(struct request_queue *q,
-		unsigned int max_zone_append_sectors);
-extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
-void blk_queue_zone_write_granularity(struct request_queue *q,
-				      unsigned int size);
-extern void blk_queue_alignment_offset(struct request_queue *q,
-				       unsigned int alignment);
-void disk_update_readahead(struct gendisk *disk);
 extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
-extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
 extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);
 extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth);
 extern void blk_set_stacking_limits(struct queue_limits *lim);
@@ -954,9 +975,7 @@ extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 			    sector_t offset);
 void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev,
 		sector_t offset, const char *pfx);
-extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
 extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
-extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua);
 
 struct blk_independent_access_ranges *
 disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges);
@@ -1077,6 +1096,7 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
 
 #define BLKDEV_ZERO_NOUNMAP	(1 << 0)  /* do not free blocks */
 #define BLKDEV_ZERO_NOFALLBACK	(1 << 1)  /* don't write explicit zeroes */
+#define BLKDEV_ZERO_KILLABLE	(1 << 2)  /* interruptible by fatal signals */
 
 extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
@@ -1204,12 +1224,7 @@ static inline unsigned int bdev_max_segments(struct block_device *bdev)
 
 static inline unsigned queue_logical_block_size(const struct request_queue *q)
 {
-	int retval = 512;
-
-	if (q && q->limits.logical_block_size)
-		retval = q->limits.logical_block_size;
-
-	return retval;
+	return q->limits.logical_block_size;
 }
 
 static inline unsigned int bdev_logical_block_size(struct block_device *bdev)
@@ -1295,29 +1310,38 @@ static inline bool bdev_nonrot(struct block_device *bdev)
 
 static inline bool bdev_synchronous(struct block_device *bdev)
 {
-	return test_bit(QUEUE_FLAG_SYNCHRONOUS,
-			&bdev_get_queue(bdev)->queue_flags);
+	return bdev->bd_disk->queue->limits.features & BLK_FEAT_SYNCHRONOUS;
 }
 
 static inline bool bdev_stable_writes(struct block_device *bdev)
 {
-	return test_bit(QUEUE_FLAG_STABLE_WRITES,
-			&bdev_get_queue(bdev)->queue_flags);
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
+	    q->limits.integrity.csum_type != BLK_INTEGRITY_CSUM_NONE)
+		return true;
+	return q->limits.features & BLK_FEAT_STABLE_WRITES;
+}
+
+static inline bool blk_queue_write_cache(struct request_queue *q)
+{
+	return (q->limits.features & BLK_FEAT_WRITE_CACHE) &&
+		!(q->limits.flags & BLK_FLAG_WRITE_CACHE_DISABLED);
 }
 
 static inline bool bdev_write_cache(struct block_device *bdev)
 {
-	return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags);
+	return blk_queue_write_cache(bdev_get_queue(bdev));
 }
 
 static inline bool bdev_fua(struct block_device *bdev)
 {
-	return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags);
+	return bdev_get_queue(bdev)->limits.features & BLK_FEAT_FUA;
 }
 
 static inline bool bdev_nowait(struct block_device *bdev)
 {
-	return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags);
+	return bdev->bd_disk->queue->limits.features & BLK_FEAT_NOWAIT;
 }
 
 static inline bool bdev_is_zoned(struct block_device *bdev)
@@ -1359,7 +1383,31 @@ static inline bool bdev_is_zone_start(struct block_device *bdev,
 
 static inline int queue_dma_alignment(const struct request_queue *q)
 {
-	return q ? q->limits.dma_alignment : 511;
+	return q->limits.dma_alignment;
+}
+
+static inline unsigned int
+queue_atomic_write_unit_max_bytes(const struct request_queue *q)
+{
+	return q->limits.atomic_write_unit_max;
+}
+
+static inline unsigned int
+queue_atomic_write_unit_min_bytes(const struct request_queue *q)
+{
+	return q->limits.atomic_write_unit_min;
+}
+
+static inline unsigned int
+queue_atomic_write_boundary_bytes(const struct request_queue *q)
+{
+	return q->limits.atomic_write_boundary_sectors << SECTOR_SHIFT;
+}
+
+static inline unsigned int
+queue_atomic_write_max_bytes(const struct request_queue *q)
+{
+	return q->limits.atomic_write_max_sectors << SECTOR_SHIFT;
 }
 
 static inline unsigned int bdev_dma_alignment(struct block_device *bdev)
@@ -1374,10 +1422,16 @@ static inline bool bdev_iter_is_aligned(struct block_device *bdev,
 				   bdev_logical_block_size(bdev) - 1);
 }
 
+static inline int blk_lim_dma_alignment_and_pad(struct queue_limits *lim)
+{
+	return lim->dma_alignment | lim->dma_pad_mask;
+}
+
 static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr,
 				 unsigned int len)
 {
-	unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask;
+	unsigned int alignment = blk_lim_dma_alignment_and_pad(&q->limits);
+
 	return !(addr & alignment) && !(len & alignment);
 }
 
@@ -1563,7 +1617,7 @@ int sync_blockdev(struct block_device *bdev);
 int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend);
 int sync_blockdev_nowait(struct block_device *bdev);
 void sync_bdevs(bool wait);
-void bdev_statx_dioalign(struct inode *inode, struct kstat *stat);
+void bdev_statx(struct path *, struct kstat *, u32);
 void printk_all_partitions(void);
 int __init early_lookup_bdev(const char *pathname, dev_t *dev);
 #else
@@ -1581,7 +1635,8 @@ static inline int sync_blockdev_nowait(struct block_device *bdev)
 static inline void sync_bdevs(bool wait)
 {
 }
-static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
+static inline void bdev_statx(struct path *path, struct kstat *stat,
+				u32 request_mask)
 {
 }
 static inline void printk_all_partitions(void)
@@ -1603,6 +1658,27 @@ struct io_comp_batch {
 	void (*complete)(struct io_comp_batch *);
 };
 
+static inline bool bdev_can_atomic_write(struct block_device *bdev)
+{
+	struct request_queue *bd_queue = bdev->bd_queue;
+	struct queue_limits *limits = &bd_queue->limits;
+
+	if (!limits->atomic_write_unit_min)
+		return false;
+
+	if (bdev_is_partition(bdev)) {
+		sector_t bd_start_sect = bdev->bd_start_sect;
+		unsigned int alignment =
+			max(limits->atomic_write_unit_min,
+			    limits->atomic_write_hw_boundary);
+
+		if (!IS_ALIGNED(bd_start_sect, alignment >> SECTOR_SHIFT))
+			return false;
+	}
+
+	return true;
+}
+
 #define DEFINE_IO_COMP_BATCH(name)	struct io_comp_batch name = { }
 
 #endif /* _LINUX_BLKDEV_H */
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index bd1e361b351c..f41c7f0ef91e 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -280,4 +280,18 @@ static inline void *bvec_virt(struct bio_vec *bvec)
 	return page_address(bvec->bv_page) + bvec->bv_offset;
 }
 
+/**
+ * bvec_phys - return the physical address for a bvec
+ * @bvec: bvec to return the physical address for
+ */
+static inline phys_addr_t bvec_phys(const struct bio_vec *bvec)
+{
+	/*
+	 * Note this open codes page_to_phys because page_to_phys is defined in
+	 * <asm/io.h>, which we don't want to pull in here.  If it ever moves to
+	 * a sensible place we should start using it.
+	 */
+	return PFN_PHYS(page_to_pfn(bvec->bv_page)) + bvec->bv_offset;
+}
+
 #endif /* __LINUX_BVEC_H */
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 82b2195efaca..15d28164bbbd 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -358,6 +358,13 @@ struct dm_target {
 	bool discards_supported:1;
 
 	/*
+	 * Automatically set by dm-core if this target supports
+	 * REQ_OP_ZONE_RESET_ALL. Otherwise, this operation will be emulated
+	 * using REQ_OP_ZONE_RESET. Target drivers must not set this manually.
+	 */
+	bool zone_reset_all_supported:1;
+
+	/*
 	 * Set if this target requires that discards be split on
 	 * 'max_discard_sectors' boundaries.
 	 */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index dc9f9c4b2572..fd34b5755c0b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -125,8 +125,10 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define FMODE_EXEC		((__force fmode_t)(1 << 5))
 /* File writes are restricted (block device specific) */
 #define FMODE_WRITE_RESTRICTED	((__force fmode_t)(1 << 6))
+/* File supports atomic writes */
+#define FMODE_CAN_ATOMIC_WRITE	((__force fmode_t)(1 << 7))
 
-/* FMODE_* bits 7 to 8 */
+/* FMODE_* bit 8 */
 
 /* 32bit hashes as llseek() offset (for directories) */
 #define FMODE_32BITHASH         ((__force fmode_t)(1 << 9))
@@ -317,6 +319,7 @@ struct readahead_control;
 #define IOCB_SYNC		(__force int) RWF_SYNC
 #define IOCB_NOWAIT		(__force int) RWF_NOWAIT
 #define IOCB_APPEND		(__force int) RWF_APPEND
+#define IOCB_ATOMIC		(__force int) RWF_ATOMIC
 
 /* non-RWF related bits - start at 16 */
 #define IOCB_EVENTFD		(1 << 16)
@@ -351,6 +354,7 @@ struct readahead_control;
 	{ IOCB_SYNC,		"SYNC" }, \
 	{ IOCB_NOWAIT,		"NOWAIT" }, \
 	{ IOCB_APPEND,		"APPEND" }, \
+	{ IOCB_ATOMIC,		"ATOMIC"}, \
 	{ IOCB_EVENTFD,		"EVENTFD"}, \
 	{ IOCB_DIRECT,		"DIRECT" }, \
 	{ IOCB_WRITE,		"WRITE" }, \
@@ -3254,6 +3258,9 @@ extern const struct inode_operations page_symlink_inode_operations;
 extern void kfree_link(void *);
 void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *);
 void generic_fill_statx_attr(struct inode *inode, struct kstat *stat);
+void generic_fill_statx_atomic_writes(struct kstat *stat,
+				      unsigned int unit_min,
+				      unsigned int unit_max);
 extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int);
 extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
 void __inode_add_bytes(struct inode *inode, loff_t bytes);
@@ -3430,7 +3437,8 @@ static inline int iocb_flags(struct file *file)
 	return res;
 }
 
-static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
+static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags,
+				     int rw_type)
 {
 	int kiocb_flags = 0;
 
@@ -3449,6 +3457,12 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 			return -EOPNOTSUPP;
 		kiocb_flags |= IOCB_NOIO;
 	}
+	if (flags & RWF_ATOMIC) {
+		if (rw_type != WRITE)
+			return -EOPNOTSUPP;
+		if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE))
+			return -EOPNOTSUPP;
+	}
 	kiocb_flags |= (__force int) (flags & RWF_SUPPORTED);
 	if (flags & RWF_SYNC)
 		kiocb_flags |= IOCB_DSYNC;
@@ -3643,4 +3657,6 @@ static inline bool vfs_empty_path(int dfd, const char __user *path)
 	return !c;
 }
 
+bool generic_atomic_write_valid(struct iov_iter *iter, loff_t pos);
+
 #endif /* _LINUX_FS_H */
diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h
index 4109f1bd6128..89ea1ebd975a 100644
--- a/include/linux/nvme-fc-driver.h
+++ b/include/linux/nvme-fc-driver.h
@@ -920,6 +920,9 @@ struct nvmet_fc_target_port {
  *       further references to hosthandle.
  *       Entrypoint is Mandatory if the lldd calls nvmet_fc_invalidate_host().
  *
+ * @host_traddr: called by the transport to retrieve the node name and
+ *       port name of the host port address.
+ *
  * @max_hw_queues:  indicates the maximum number of hw queues the LLDD
  *       supports for cpu affinitization.
  *       Value is Mandatory. Must be at least 1.
@@ -975,6 +978,7 @@ struct nvmet_fc_target_template {
 	void (*ls_abort)(struct nvmet_fc_target_port *targetport,
 				void *hosthandle, struct nvmefc_ls_req *lsreq);
 	void (*host_release)(void *hosthandle);
+	int (*host_traddr)(void *hosthandle, u64 *wwnn, u64 *wwpn);
 
 	u32	max_hw_queues;
 	u16	max_sgl_segments;
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index c693ac344ec0..c12a329dd463 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -25,6 +25,9 @@
 
 #define NVME_NSID_ALL		0xffffffff
 
+/* Special NSSR value, 'NVMe' */
+#define NVME_SUBSYS_RESET	0x4E564D65
+
 enum nvme_subsys_type {
 	/* Referral to another discovery type target subsystem */
 	NVME_NQN_DISC	= 1,
@@ -1848,6 +1851,7 @@ enum {
 	/*
 	 * Generic Command Status:
 	 */
+	NVME_SCT_GENERIC		= 0x0,
 	NVME_SC_SUCCESS			= 0x0,
 	NVME_SC_INVALID_OPCODE		= 0x1,
 	NVME_SC_INVALID_FIELD		= 0x2,
@@ -1895,6 +1899,7 @@ enum {
 	/*
 	 * Command Specific Status:
 	 */
+	NVME_SCT_COMMAND_SPECIFIC	= 0x100,
 	NVME_SC_CQ_INVALID		= 0x100,
 	NVME_SC_QID_INVALID		= 0x101,
 	NVME_SC_QUEUE_SIZE		= 0x102,
@@ -1968,6 +1973,7 @@ enum {
 	/*
 	 * Media and Data Integrity Errors:
 	 */
+	NVME_SCT_MEDIA_ERROR		= 0x200,
 	NVME_SC_WRITE_FAULT		= 0x280,
 	NVME_SC_READ_ERROR		= 0x281,
 	NVME_SC_GUARD_CHECK		= 0x282,
@@ -1980,6 +1986,7 @@ enum {
 	/*
 	 * Path-related Errors:
 	 */
+	NVME_SCT_PATH			= 0x300,
 	NVME_SC_INTERNAL_PATH_ERROR	= 0x300,
 	NVME_SC_ANA_PERSISTENT_LOSS	= 0x301,
 	NVME_SC_ANA_INACCESSIBLE	= 0x302,
@@ -1988,11 +1995,17 @@ enum {
 	NVME_SC_HOST_PATH_ERROR		= 0x370,
 	NVME_SC_HOST_ABORTED_CMD	= 0x371,
 
-	NVME_SC_CRD			= 0x1800,
-	NVME_SC_MORE			= 0x2000,
-	NVME_SC_DNR			= 0x4000,
+	NVME_SC_MASK			= 0x00ff, /* Status Code */
+	NVME_SCT_MASK			= 0x0700, /* Status Code Type */
+	NVME_SCT_SC_MASK		= NVME_SCT_MASK | NVME_SC_MASK,
+
+	NVME_STATUS_CRD			= 0x1800, /* Command Retry Delayed */
+	NVME_STATUS_MORE		= 0x2000,
+	NVME_STATUS_DNR			= 0x4000, /* Do Not Retry */
 };
 
+#define NVME_SCT(status) ((status) >> 8 & 7)
+
 struct nvme_completion {
 	/*
 	 * Used by Admin and Fabrics commands to return data:
diff --git a/include/linux/stat.h b/include/linux/stat.h
index bf92441dbad2..3d900c86981c 100644
--- a/include/linux/stat.h
+++ b/include/linux/stat.h
@@ -54,6 +54,9 @@ struct kstat {
 	u32		dio_offset_align;
 	u64		change_cookie;
 	u64		subvol;
+	u32		atomic_write_unit_min;
+	u32		atomic_write_unit_max;
+	u32		atomic_write_segments_max;
 };
 
 /* These definitions are internal to the kernel for now. Mainly used by nfsd. */
diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h
index 248f4ac95642..2c59fe3efcd4 100644
--- a/include/linux/t10-pi.h
+++ b/include/linux/t10-pi.h
@@ -41,18 +41,12 @@ static inline u32 t10_pi_ref_tag(struct request *rq)
 {
 	unsigned int shift = ilog2(queue_logical_block_size(rq->q));
 
-#ifdef CONFIG_BLK_DEV_INTEGRITY
-	if (rq->q->integrity.interval_exp)
-		shift = rq->q->integrity.interval_exp;
-#endif
+	if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
+	    rq->q->limits.integrity.interval_exp)
+		shift = rq->q->limits.integrity.interval_exp;
 	return blk_rq_pos(rq) >> (shift - SECTOR_SHIFT) & 0xffffffff;
 }
 
-extern const struct blk_integrity_profile t10_pi_type1_crc;
-extern const struct blk_integrity_profile t10_pi_type1_ip;
-extern const struct blk_integrity_profile t10_pi_type3_crc;
-extern const struct blk_integrity_profile t10_pi_type3_ip;
-
 struct crc64_pi_tuple {
 	__be64 guard_tag;
 	__be16 app_tag;
@@ -72,14 +66,10 @@ static inline u64 ext_pi_ref_tag(struct request *rq)
 {
 	unsigned int shift = ilog2(queue_logical_block_size(rq->q));
 
-#ifdef CONFIG_BLK_DEV_INTEGRITY
-	if (rq->q->integrity.interval_exp)
-		shift = rq->q->integrity.interval_exp;
-#endif
+	if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
+	    rq->q->limits.integrity.interval_exp)
+		shift = rq->q->limits.integrity.interval_exp;
 	return lower_48_bits(blk_rq_pos(rq) >> (shift - SECTOR_SHIFT));
 }
 
-extern const struct blk_integrity_profile ext_pi_type1_crc64;
-extern const struct blk_integrity_profile ext_pi_type3_crc64;
-
 #endif
diff --git a/include/scsi/scsi_proto.h b/include/scsi/scsi_proto.h
index 843106e1109f..70e1262b2e20 100644
--- a/include/scsi/scsi_proto.h
+++ b/include/scsi/scsi_proto.h
@@ -120,6 +120,7 @@
 #define WRITE_SAME_16	      0x93
 #define ZBC_OUT		      0x94
 #define ZBC_IN		      0x95
+#define WRITE_ATOMIC_16	0x9c
 #define SERVICE_ACTION_BIDIRECTIONAL 0x9d
 #define SERVICE_ACTION_IN_16  0x9e
 #define SERVICE_ACTION_OUT_16 0x9f
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 0e128ad51460..1527d5d45e01 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -9,9 +9,17 @@
 #include <linux/blkdev.h>
 #include <linux/buffer_head.h>
 #include <linux/tracepoint.h>
+#include <uapi/linux/ioprio.h>
 
 #define RWBS_LEN	8
 
+#define IOPRIO_CLASS_STRINGS \
+	{ IOPRIO_CLASS_NONE,	"none" }, \
+	{ IOPRIO_CLASS_RT,	"rt" }, \
+	{ IOPRIO_CLASS_BE,	"be" }, \
+	{ IOPRIO_CLASS_IDLE,	"idle" }, \
+	{ IOPRIO_CLASS_INVALID,	"invalid"}
+
 #ifdef CONFIG_BUFFER_HEAD
 DECLARE_EVENT_CLASS(block_buffer,
 
@@ -82,6 +90,7 @@ TRACE_EVENT(block_rq_requeue,
 		__field(  dev_t,	dev			)
 		__field(  sector_t,	sector			)
 		__field(  unsigned int,	nr_sector		)
+		__field(  unsigned short, ioprio		)
 		__array(  char,		rwbs,	RWBS_LEN	)
 		__dynamic_array( char,	cmd,	1		)
 	),
@@ -90,16 +99,20 @@ 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;
 
 		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags);
 		__get_str(cmd)[0] = '\0';
 	),
 
-	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+	TP_printk("%d,%d %s (%s) %llu + %u %s,%u,%u [%d]",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->rwbs, __get_str(cmd),
-		  (unsigned long long)__entry->sector,
-		  __entry->nr_sector, 0)
+		  (unsigned long long)__entry->sector, __entry->nr_sector,
+		  __print_symbolic(IOPRIO_PRIO_CLASS(__entry->ioprio),
+				   IOPRIO_CLASS_STRINGS),
+		  IOPRIO_PRIO_HINT(__entry->ioprio),
+		  IOPRIO_PRIO_LEVEL(__entry->ioprio),  0)
 );
 
 DECLARE_EVENT_CLASS(block_rq_completion,
@@ -113,6 +126,7 @@ DECLARE_EVENT_CLASS(block_rq_completion,
 		__field(  sector_t,	sector			)
 		__field(  unsigned int,	nr_sector		)
 		__field(  int	,	error			)
+		__field(  unsigned short, ioprio		)
 		__array(  char,		rwbs,	RWBS_LEN	)
 		__dynamic_array( char,	cmd,	1		)
 	),
@@ -122,16 +136,20 @@ 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;
 
 		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags);
 		__get_str(cmd)[0] = '\0';
 	),
 
-	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+	TP_printk("%d,%d %s (%s) %llu + %u %s,%u,%u [%d]",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->rwbs, __get_str(cmd),
-		  (unsigned long long)__entry->sector,
-		  __entry->nr_sector, __entry->error)
+		  (unsigned long long)__entry->sector, __entry->nr_sector,
+		  __print_symbolic(IOPRIO_PRIO_CLASS(__entry->ioprio),
+				   IOPRIO_CLASS_STRINGS),
+		  IOPRIO_PRIO_HINT(__entry->ioprio),
+		  IOPRIO_PRIO_LEVEL(__entry->ioprio), __entry->error)
 );
 
 /**
@@ -180,6 +198,7 @@ DECLARE_EVENT_CLASS(block_rq,
 		__field(  sector_t,	sector			)
 		__field(  unsigned int,	nr_sector		)
 		__field(  unsigned int,	bytes			)
+		__field(  unsigned short, ioprio		)
 		__array(  char,		rwbs,	RWBS_LEN	)
 		__array(  char,         comm,   TASK_COMM_LEN   )
 		__dynamic_array( char,	cmd,	1		)
@@ -190,17 +209,21 @@ 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;
 
 		blk_fill_rwbs(__entry->rwbs, rq->cmd_flags);
 		__get_str(cmd)[0] = '\0';
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 	),
 
-	TP_printk("%d,%d %s %u (%s) %llu + %u [%s]",
+	TP_printk("%d,%d %s %u (%s) %llu + %u %s,%u,%u [%s]",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->rwbs, __entry->bytes, __get_str(cmd),
-		  (unsigned long long)__entry->sector,
-		  __entry->nr_sector, __entry->comm)
+		  (unsigned long long)__entry->sector, __entry->nr_sector,
+		  __print_symbolic(IOPRIO_PRIO_CLASS(__entry->ioprio),
+				   IOPRIO_CLASS_STRINGS),
+		  IOPRIO_PRIO_HINT(__entry->ioprio),
+		  IOPRIO_PRIO_LEVEL(__entry->ioprio), __entry->comm)
 );
 
 /**
diff --git a/include/trace/events/scsi.h b/include/trace/events/scsi.h
index 8e2d9b1b0e77..05f1945ed204 100644
--- a/include/trace/events/scsi.h
+++ b/include/trace/events/scsi.h
@@ -102,6 +102,7 @@
 		scsi_opcode_name(WRITE_32),			\
 		scsi_opcode_name(WRITE_SAME_32),		\
 		scsi_opcode_name(ATA_16),			\
+		scsi_opcode_name(WRITE_ATOMIC_16),		\
 		scsi_opcode_name(ATA_12))
 
 #define scsi_hostbyte_name(result)	{ result, #result }
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 45e4e64fd664..191a7e88a8ab 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -329,9 +329,12 @@ typedef int __bitwise __kernel_rwf_t;
 /* per-IO negation of O_APPEND */
 #define RWF_NOAPPEND	((__force __kernel_rwf_t)0x00000020)
 
+/* Atomic Write */
+#define RWF_ATOMIC	((__force __kernel_rwf_t)0x00000040)
+
 /* mask of flags supported by the kernel */
 #define RWF_SUPPORTED	(RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
-			 RWF_APPEND | RWF_NOAPPEND)
+			 RWF_APPEND | RWF_NOAPPEND | RWF_ATOMIC)
 
 /* Pagemap ioctl */
 #define PAGEMAP_SCAN	_IOWR('f', 16, struct pm_scan_arg)
diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h
index 95770941ee2c..887a25286441 100644
--- a/include/uapi/linux/stat.h
+++ b/include/uapi/linux/stat.h
@@ -128,7 +128,13 @@ struct statx {
 	__u32	stx_dio_offset_align;	/* File offset alignment for direct I/O */
 	/* 0xa0 */
 	__u64	stx_subvol;	/* Subvolume identifier */
-	__u64	__spare3[11];	/* Spare space for future expansion */
+	__u32	stx_atomic_write_unit_min;	/* Min atomic write unit in bytes */
+	__u32	stx_atomic_write_unit_max;	/* Max atomic write unit in bytes */
+	/* 0xb0 */
+	__u32   stx_atomic_write_segments_max;	/* Max atomic write segment count */
+	__u32   __spare1[1];
+	/* 0xb8 */
+	__u64	__spare3[9];	/* Spare space for future expansion */
 	/* 0x100 */
 };
 
@@ -157,6 +163,7 @@ struct statx {
 #define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
 #define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
 #define STATX_SUBVOL		0x00008000U	/* Want/got stx_subvol */
+#define STATX_WRITE_ATOMIC	0x00010000U	/* Want/got atomic_write_* fields */
 
 #define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
 
@@ -192,6 +199,7 @@ struct statx {
 #define STATX_ATTR_MOUNT_ROOT		0x00002000 /* Root of a mount */
 #define STATX_ATTR_VERITY		0x00100000 /* [I] Verity protected file */
 #define STATX_ATTR_DAX			0x00200000 /* File is currently in DAX state */
+#define STATX_ATTR_WRITE_ATOMIC		0x00400000 /* File supports atomic write operations */
 
 
 #endif /* _UAPI_LINUX_STAT_H */