Zone write plugging

index b0f314f4bc14..2f58ae018464 100644
@@ -130,6 +130,7 @@ static void blk_flush_restore_request(struct request *rq)
 	 * original @rq->bio.  Restore it.
 	 */
 	rq->bio = rq->biotail;
+	rq->__sector = rq->bio->bi_iter.bi_sector;
 
 	/* make @rq a normal request */
 	rq->rq_flags &= ~RQF_FLUSH_SEQ;

index b8dbfed8b28b..fcbf0953a179 100644
@@ -762,31 +762,6 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
 }
 EXPORT_SYMBOL(blk_dump_rq_flags);
 
-static void req_bio_endio(struct request *rq, struct bio *bio,
-			  unsigned int nbytes, blk_status_t error)
-{
-	if (unlikely(error)) {
-		bio->bi_status = error;
-	} else if (req_op(rq) == REQ_OP_ZONE_APPEND) {
-		/*
-		 * Partial zone append completions cannot be supported as the
-		 * BIO fragments may end up not being written sequentially.
-		 */
-		if (bio->bi_iter.bi_size != nbytes)
-			bio->bi_status = BLK_STS_IOERR;
-		else
-			bio->bi_iter.bi_sector = rq->__sector;
-	}
-
-	bio_advance(bio, nbytes);
-
-	if (unlikely(rq->rq_flags & RQF_QUIET))
-		bio_set_flag(bio, BIO_QUIET);
-	/* don't actually finish bio if it's part of flush sequence */
-	if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
-		bio_endio(bio);
-}
-
 static void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
 	if (req->part && blk_do_io_stat(req)) {

@@ -890,6 +865,8 @@ static void blk_complete_request(struct request *req)
 bool blk_update_request(struct request *req, blk_status_t error,
 		unsigned int nr_bytes)
 {
+	bool is_flush = req->rq_flags & RQF_FLUSH_SEQ;
+	bool quiet = req->rq_flags & RQF_QUIET;
 	int total_bytes;
 
 	trace_block_rq_complete(req, error, nr_bytes);

@@ -910,9 +887,8 @@ bool blk_update_request(struct request *req, blk_status_t error,
 	if (blk_crypto_rq_has_keyslot(req) && nr_bytes >= blk_rq_bytes(req))
 		__blk_crypto_rq_put_keyslot(req);
 
-	if (unlikely(error && !blk_rq_is_passthrough(req) &&
-		     !(req->rq_flags & RQF_QUIET)) &&
-		     !test_bit(GD_DEAD, &req->q->disk->state)) {
+	if (unlikely(error && !blk_rq_is_passthrough(req) && !quiet) &&
+	    !test_bit(GD_DEAD, &req->q->disk->state)) {
 		blk_print_req_error(req, error);
 		trace_block_rq_error(req, error, nr_bytes);
 	}

@@ -924,12 +900,34 @@ bool blk_update_request(struct request *req, blk_status_t error,
 		struct bio *bio = req->bio;
 		unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes);
 
-		if (bio_bytes == bio->bi_iter.bi_size)
+		if (unlikely(error))
+			bio->bi_status = error;
+
+		if (bio_bytes == bio->bi_iter.bi_size) {
 			req->bio = bio->bi_next;
+		} else if (req_op(req) == REQ_OP_ZONE_APPEND &&
+			   error == BLK_STS_OK) {
+			/*
+			 * Partial zone append completions cannot be supported
+			 * as the BIO fragments may end up not being written
+			 * sequentially.
+			 */
+			bio->bi_status = BLK_STS_IOERR;
+		}
 
 		/* Completion has already been traced */
 		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
-		req_bio_endio(req, bio, bio_bytes, error);
+		if (unlikely(quiet))
+			bio_set_flag(bio, BIO_QUIET);
+
+		bio_advance(bio, bio_bytes);
+
+		/* Don't actually finish bio if it's part of flush sequence */
+		if (!bio->bi_iter.bi_size && !is_flush) {
+			if (req_op(req) == REQ_OP_ZONE_APPEND)
+				bio->bi_iter.bi_sector = req->__sector;
+			bio_endio(bio);
+		}
 
 		total_bytes += bio_bytes;
 		nr_bytes -= bio_bytes;

index fcbf0953a179..88b541e8873f 100644
@@ -821,8 +821,7 @@ static void blk_complete_request(struct request *req)
 		/* Completion has already been traced */
 		bio_clear_flag(bio, BIO_TRACE_COMPLETION);
 
-		if (req_op(req) == REQ_OP_ZONE_APPEND)
-			bio->bi_iter.bi_sector = req->__sector;
+		blk_zone_update_request_bio(req, bio);
 
 		if (!is_flush)
 			bio_endio(bio);

@@ -923,10 +922,10 @@ bool blk_update_request(struct request *req, blk_status_t error,
 		bio_advance(bio, bio_bytes);
 
 		/* Don't actually finish bio if it's part of flush sequence */
-		if (!bio->bi_iter.bi_size && !is_flush) {
-			if (req_op(req) == REQ_OP_ZONE_APPEND)
-				bio->bi_iter.bi_sector = req->__sector;
-			bio_endio(bio);
+		if (!bio->bi_iter.bi_size) {
+			blk_zone_update_request_bio(req, bio);
+			if (!is_flush)
+				bio_endio(bio);
 		}
 
 		total_bytes += bio_bytes;

index d9f584984bc4..17786052f32d 100644
@@ -408,12 +408,29 @@ static inline struct bio *blk_queue_bounce(struct bio *bio,
 
 #ifdef CONFIG_BLK_DEV_ZONED
 void disk_free_zone_bitmaps(struct gendisk *disk);
+static inline void blk_zone_update_request_bio(struct request *rq,
+					       struct bio *bio)
+{
+	/*
+	 * For zone append requests, the request sector indicates the location
+	 * at which the BIO data was written. Return this value to the BIO
+	 * issuer through the BIO iter sector.
+	 */
+	if (req_op(rq) == REQ_OP_ZONE_APPEND)
+		bio->bi_iter.bi_sector = rq->__sector;
+}
 int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd,
 		unsigned long arg);
 int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 		unsigned int cmd, unsigned long arg);
 #else /* CONFIG_BLK_DEV_ZONED */
-static inline void disk_free_zone_bitmaps(struct gendisk *disk) {}
+static inline void disk_free_zone_bitmaps(struct gendisk *disk)
+{
+}
+static inline void blk_zone_update_request_bio(struct request *rq,
+					       struct bio *bio)
+{
+}
 static inline int blkdev_report_zones_ioctl(struct block_device *bdev,
 		unsigned int cmd, unsigned long arg)
 {

index c3e8f7cf96be..ec7bd7091467 100644
@@ -853,6 +853,13 @@ static inline unsigned int bio_zone_no(struct bio *bio)
 	return disk_zone_no(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector);
 }
 
+static inline bool bio_straddles_zones(struct bio *bio)
+{
+	return bio_sectors(bio) &&
+		bio_zone_no(bio) !=
+		disk_zone_no(bio->bi_bdev->bd_disk, bio_end_sector(bio) - 1);
+}
+
 static inline unsigned int bio_zone_is_seq(struct bio *bio)
 {
 	return disk_zone_is_seq(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector);

@@ -1328,6 +1335,12 @@ static inline sector_t bdev_offset_from_zone_start(struct block_device *bdev,
 	return sector & (bdev_zone_sectors(bdev) - 1);
 }
 
+static inline sector_t bio_offset_from_zone_start(struct bio *bio)
+{
+	return bdev_offset_from_zone_start(bio->bi_bdev,
+					   bio->bi_iter.bi_sector);
+}
+
 static inline bool bdev_is_zone_start(struct block_device *bdev,
 				      sector_t sector)
 {

index 4e3483a16b75..3363b1321908 100644
@@ -972,13 +972,7 @@ static void blk_account_io_merge_bio(struct request *req)
 	part_stat_unlock();
 }
 
-enum bio_merge_status {
-	BIO_MERGE_OK,
-	BIO_MERGE_NONE,
-	BIO_MERGE_FAILED,
-};
-
-static enum bio_merge_status bio_attempt_back_merge(struct request *req,
+enum bio_merge_status bio_attempt_back_merge(struct request *req,
 		struct bio *bio, unsigned int nr_segs)
 {
 	const blk_opf_t ff = bio_failfast(bio);

index 17786052f32d..bca50a9510c8 100644
@@ -269,6 +269,14 @@ static inline void bio_integrity_free(struct bio *bio)
 unsigned long blk_rq_timeout(unsigned long timeout);
 void blk_add_timer(struct request *req);
 
+enum bio_merge_status {
+	BIO_MERGE_OK,
+	BIO_MERGE_NONE,
+	BIO_MERGE_FAILED,
+};
+
+enum bio_merge_status bio_attempt_back_merge(struct request *req,
+		struct bio *bio, unsigned int nr_segs);
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 		unsigned int nr_segs);
 bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,

index da0f4b2a8fa0..23d9bb21c459 100644
@@ -438,6 +438,7 @@ struct blk_revalidate_zone_args {
 	unsigned long	*conv_zones_bitmap;
 	unsigned long	*seq_zones_wlock;
 	unsigned int	nr_zones;
+	unsigned int	zone_capacity;
 	sector_t	sector;
 };
 

@@ -482,9 +483,20 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
 		return -ENODEV;
 	}
 
+	if (!zone->capacity || zone->capacity > zone->len) {
+		pr_warn("%s: Invalid zone capacity\n",
+			disk->disk_name);
+		return -ENODEV;
+	}
+
 	/* Check zone type */
 	switch (zone->type) {
 	case BLK_ZONE_TYPE_CONVENTIONAL:
+		if (zone->capacity != zone->len) {
+			pr_warn("%s: Invalid conventional zone capacity\n",
+				disk->disk_name);
+			return -ENODEV;
+		}
 		if (!args->conv_zones_bitmap) {
 			args->conv_zones_bitmap =
 				blk_alloc_zone_bitmap(q->node, args->nr_zones);

@@ -500,6 +512,18 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
 			if (!args->seq_zones_wlock)
 				return -ENOMEM;
 		}
+
+		/*
+		 * Remember the capacity of the first sequential zone and check
+		 * if it is constant for all zones.
+		 */
+		if (!args->zone_capacity)
+			args->zone_capacity = zone->capacity;
+		if (zone->capacity != args->zone_capacity) {
+			pr_warn("%s: Invalid variable zone capacity\n",
+				disk->disk_name);
+			return -ENODEV;
+		}
 		break;
 	case BLK_ZONE_TYPE_SEQWRITE_PREF:
 	default:

@@ -595,6 +619,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
 	blk_mq_freeze_queue(q);
 	if (ret > 0) {
 		disk->nr_zones = args.nr_zones;
+		disk->zone_capacity = args.zone_capacity;
 		swap(disk->seq_zones_wlock, args.seq_zones_wlock);
 		swap(disk->conv_zones_bitmap, args.conv_zones_bitmap);
 		if (update_driver_data)

@@ -608,6 +633,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
 
 	kfree(args.seq_zones_wlock);
 	kfree(args.conv_zones_bitmap);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);

index ec7bd7091467..4e81f714cca7 100644
@@ -191,6 +191,7 @@ struct gendisk {
 	 * blk_mq_unfreeze_queue().
 	 */
 	unsigned int		nr_zones;
+	unsigned int		zone_capacity;
 	unsigned long		*conv_zones_bitmap;
 	unsigned long		*seq_zones_wlock;
 #endif /* CONFIG_BLK_DEV_ZONED */

index d24420ed1c4c..127c06443bca 100644
@@ -1576,6 +1576,12 @@ void bio_endio(struct bio *bio)
 	if (!bio_integrity_endio(bio))
 		return;
 
+	/*
+	 * For write BIOs to zoned devices, signal the completion of the BIO so
+	 * that the next write BIO can be submitted by zone write plugging.
+	 */
+	blk_zone_write_bio_endio(bio);
+
 	rq_qos_done_bio(bio);
 
 	if (bio->bi_bdev && bio_flagged(bio, BIO_TRACE_COMPLETION)) {

index 3363b1321908..7a9f8187ea62 100644
@@ -377,6 +377,7 @@ struct bio *__bio_split_to_limits(struct bio *bio,
 		blkcg_bio_issue_init(split);
 		bio_chain(split, bio);
 		trace_block_split(split, bio->bi_iter.bi_sector);
+		WARN_ON_ONCE(bio_zone_write_plugging(bio));
 		submit_bio_noacct(bio);
 		return split;
 	}

@@ -988,6 +989,9 @@ enum bio_merge_status bio_attempt_back_merge(struct request *req,
 
 	blk_update_mixed_merge(req, bio, false);
 
+	if (req->rq_flags & RQF_ZONE_WRITE_PLUGGING)
+		blk_zone_write_plug_bio_merged(bio);
+
 	req->biotail->bi_next = bio;
 	req->biotail = bio;
 	req->__data_len += bio->bi_iter.bi_size;

@@ -1003,6 +1007,13 @@ static enum bio_merge_status bio_attempt_front_merge(struct request *req,
 {
 	const blk_opf_t ff = bio_failfast(bio);
 
+	/*
+	 * A front merge for zone writes can happen only if the user submitted
+	 * writes out of order. Do not attempt this to let the write fail.
+	 */
+	if (req->rq_flags & RQF_ZONE_WRITE_PLUGGING)
+		return BIO_MERGE_FAILED;
+
 	if (!ll_front_merge_fn(req, bio, nr_segs))
 		return BIO_MERGE_FAILED;
 

index 88b541e8873f..2c6a317bef7c 100644
@@ -828,6 +828,8 @@ static void blk_complete_request(struct request *req)
 		bio = next;
 	} while (bio);
 
+	blk_zone_write_complete_request(req);
+
 	/*
 	 * Reset counters so that the request stacking driver
 	 * can find how many bytes remain in the request

@@ -939,6 +941,7 @@ bool blk_update_request(struct request *req, blk_status_t error,
 	 * completely done
 	 */
 	if (!req->bio) {
+		blk_zone_write_complete_request(req);
 		/*
 		 * Reset counters so that the request stacking driver
 		 * can find how many bytes remain in the request

@@ -2963,15 +2966,30 @@ void blk_mq_submit_bio(struct bio *bio)
 	struct request *rq;
 	blk_status_t ret;
 
+	/*
+	 * If the plug has a cached request for this queue, try use it.
+	 */
+	rq = blk_mq_peek_cached_request(plug, q, bio->bi_opf);
+
+	/*
+	 * A BIO that was released from a zone write plug has already been
+	 * through the preparation in this function, already holds a reference
+	 * on the queue usage counter, and is the only write BIO in-flight for
+	 * the target zone. Go straight to preparing a request for it.
+	 */
+	if (bio_zone_write_plugging(bio)) {
+		nr_segs = bio->__bi_nr_segments;
+		if (rq)
+			blk_queue_exit(q);
+		goto new_request;
+	}
+
 	bio = blk_queue_bounce(bio, q);
 
 	/*
-	 * If the plug has a cached request for this queue, try use it.
-	 *
 	 * The cached request already holds a q_usage_counter reference and we
 	 * don't have to acquire a new one if we use it.
 	 */
-	rq = blk_mq_peek_cached_request(plug, q, bio->bi_opf);
 	if (!rq) {
 		if (unlikely(bio_queue_enter(bio)))
 			return;

@@ -2988,6 +3006,10 @@ void blk_mq_submit_bio(struct bio *bio)
 	if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
 		goto queue_exit;
 
+	if (blk_queue_is_zoned(q) && blk_zone_write_plug_bio(bio, nr_segs))
+		goto queue_exit;
+
+new_request:
 	if (!rq) {
 		rq = blk_mq_get_new_requests(q, plug, bio, nr_segs);
 		if (unlikely(!rq))

@@ -3006,6 +3028,7 @@ void blk_mq_submit_bio(struct bio *bio)
 	if (ret != BLK_STS_OK) {
 		bio->bi_status = ret;
 		bio_endio(bio);
+		blk_zone_write_complete_request(rq);
 		blk_mq_free_request(rq);
 		return;
 	}

@@ -3013,6 +3036,9 @@ void blk_mq_submit_bio(struct bio *bio)
 	if (op_is_flush(bio->bi_opf) && blk_insert_flush(rq))
 		return;
 
+	if (bio_zone_write_plugging(bio))
+		blk_zone_write_plug_attempt_merge(rq);
+
 	if (plug) {
 		blk_add_rq_to_plug(plug, rq);
 		return;

1,151 lines not on this page · raw message

73 lines not on this page · raw message

index bb29a68e1d67..eb893df56d51 100644
@@ -1182,7 +1182,7 @@ static void disk_release(struct device *dev)
 
 	disk_release_events(disk);
 	kfree(disk->random);
-	disk_free_zone_bitmaps(disk);
+	disk_free_zone_resources(disk);
 	xa_destroy(&disk->part_tbl);
 
 	disk->queue->disk = NULL;

@@ -1364,6 +1364,7 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id,
 	if (blkcg_init_disk(disk))
 		goto out_erase_part0;
 
+	disk_init_zone_resources(disk);
 	rand_initialize_disk(disk);
 	disk_to_dev(disk)->class = &block_class;
 	disk_to_dev(disk)->type = &disk_type;

index d3d8fd8e229b..60090c8366fb 100644
@@ -56,6 +56,8 @@ typedef __u32 __bitwise req_flags_t;
 #define RQF_SPECIAL_PAYLOAD	((__force req_flags_t)(1 << 18))
 /* The per-zone write lock is held for this request */
 #define RQF_ZONE_WRITE_LOCKED	((__force req_flags_t)(1 << 19))
+/* The request completion needs to be signaled to zone write pluging. */
+#define RQF_ZONE_WRITE_PLUGGING	((__force req_flags_t)(1 << 20))
 /* ->timeout has been called, don't expire again */
 #define RQF_TIMED_OUT		((__force req_flags_t)(1 << 21))
 #define RQF_RESV		((__force req_flags_t)(1 << 23))

index cb1526ec44b5..ed45de07d2ef 100644
@@ -234,7 +234,12 @@ struct bio {
 
 	struct bvec_iter	bi_iter;
 
-	blk_qc_t		bi_cookie;
+	union {
+		/* for polled bios: */
+		blk_qc_t		bi_cookie;
+		/* for plugged zoned writes only: */
+		unsigned int		__bi_nr_segments;
+	};
 	bio_end_io_t		*bi_end_io;
 	void			*bi_private;
 #ifdef CONFIG_BLK_CGROUP

@@ -305,6 +310,7 @@ enum {
 	BIO_QOS_MERGED,		/* but went through rq_qos merge path */
 	BIO_REMAPPED,
 	BIO_ZONE_WRITE_LOCKED,	/* Owns a zoned device zone write lock */
+	BIO_ZONE_WRITE_PLUGGING, /* bio handled through zone write plugging */
 	BIO_FLAG_LAST
 };
 

index 4e81f714cca7..a95b883512ea 100644
@@ -194,6 +194,12 @@ struct gendisk {
 	unsigned int		zone_capacity;
 	unsigned long		*conv_zones_bitmap;
 	unsigned long		*seq_zones_wlock;
+	unsigned int            zone_wplugs_hash_bits;
+	spinlock_t              zone_wplugs_lock;
+	struct mempool_s	*zone_wplugs_pool;
+	struct hlist_head       *zone_wplugs_hash;
+	struct list_head        zone_wplugs_err_list;
+	struct work_struct	zone_wplugs_work;
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 #if IS_ENABLED(CONFIG_CDROM)

@@ -663,6 +669,7 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
 	return bdev->bd_disk->queue->limits.max_active_zones;
 }
 
+bool blk_zone_write_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)
 {

@@ -690,6 +697,11 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
 {
 	return 0;
 }
+static inline bool blk_zone_write_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)

index 9c9600642299..3dceeaaeb973 100644
@@ -1502,6 +1502,38 @@ struct blk_revalidate_zone_args {
 	sector_t	sector;
 };
 
+/*
+ * Update the disk zone resources information and device queue limits.
+ * The disk queue is frozen when this is executed.
+ */
+static int disk_update_zone_resources(struct gendisk *disk,
+				      struct blk_revalidate_zone_args *args)
+{
+	struct request_queue *q = disk->queue;
+	struct queue_limits lim;
+
+	disk->nr_zones = args->nr_zones;
+	disk->zone_capacity = args->zone_capacity;
+	swap(disk->seq_zones_wlock, args->seq_zones_wlock);
+	swap(disk->conv_zones_bitmap, args->conv_zones_bitmap);
+
+	/*
+	 * If the device has no limit on the maximum number of open and active
+	 * zones, set its max open zone limit to the mempool size to indicate
+	 * to the user that there is a potential performance impact due to
+	 * dynamic zone write plug allocation when simultaneously writing to
+	 * more zones than the size of the mempool.
+	 */
+	if (disk->zone_wplugs_pool) {
+		lim = queue_limits_start_update(q);
+		if (!lim.max_open_zones && !lim.max_active_zones)
+			lim.max_open_zones = disk->zone_wplugs_pool->min_nr;
+		return queue_limits_commit_update(q, &lim);
+	}
+
+	return 0;
+}
+
 /*
  * Helper function to check the validity of zones of a zoned block device.
  */

@@ -1702,17 +1734,14 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
 	 */
 	blk_mq_freeze_queue(q);
 	if (ret > 0) {
-		disk->nr_zones = args.nr_zones;
-		disk->zone_capacity = args.zone_capacity;
-		swap(disk->seq_zones_wlock, args.seq_zones_wlock);
-		swap(disk->conv_zones_bitmap, args.conv_zones_bitmap);
+		ret = disk_update_zone_resources(disk, &args);
 		if (update_driver_data)
 			update_driver_data(disk);
-		ret = 0;
 	} else {
 		pr_warn("%s: failed to revalidate zones\n", disk->disk_name);
-		disk_free_zone_resources(disk);
 	}
+	if (ret)
+		disk_free_zone_resources(disk);
 	blk_mq_unfreeze_queue(q);
 
 	kfree(args.seq_zones_wlock);

index a16b5abdbbf5..3bf28149e104 100644
@@ -602,7 +602,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 		return BLK_STS_IOERR;
 
 	/* Make sure the BIO is small enough and will not get split */
-	if (nr_sectors > q->limits.max_zone_append_sectors)
+	if (nr_sectors > queue_max_zone_append_sectors(q))
 		return BLK_STS_IOERR;
 
 	bio->bi_opf |= REQ_NOMERGE;

index cdbaef159c4b..c0197e1e7485 100644
@@ -412,24 +412,32 @@ EXPORT_SYMBOL(blk_queue_max_write_zeroes_sectors);
  * blk_queue_max_zone_append_sectors - set max sectors for a single zone append
  * @q:  the request queue for the device
  * @max_zone_append_sectors: maximum number of sectors to write per command
+ *
+ * Sets the maximum number of sectors allowed for zone append commands. If
+ * Specifying 0 for @max_zone_append_sectors indicates that the queue does
+ * not natively support zone append operations and that the block layer must
+ * emulate these operations using regular writes.
  **/
 void blk_queue_max_zone_append_sectors(struct request_queue *q,
 		unsigned int max_zone_append_sectors)
 {
-	unsigned int max_sectors;
+	unsigned int max_sectors = 0;
 
 	if (WARN_ON(!blk_queue_is_zoned(q)))
 		return;
 
-	max_sectors = min(q->limits.max_hw_sectors, max_zone_append_sectors);
-	max_sectors = min(q->limits.chunk_sectors, max_sectors);
+	if (max_zone_append_sectors) {
+		max_sectors = min(q->limits.max_hw_sectors,
+				  max_zone_append_sectors);
+		max_sectors = min(q->limits.chunk_sectors, max_sectors);
 
-	/*
-	 * Signal eventual driver bugs resulting in the max_zone_append sectors limit
-	 * being 0 due to a 0 argument, the chunk_sectors limit (zone size) not set,
-	 * or the max_hw_sectors limit not set.
-	 */
-	WARN_ON(!max_sectors);
+		/*
+		 * Signal eventual driver bugs resulting in the max_zone_append
+		 * sectors limit being 0 due to the chunk_sectors limit (zone
+		 * size) not set or the max_hw_sectors limit not set.
+		 */
+		WARN_ON_ONCE(!max_sectors);
+	}
 
 	q->limits.max_zone_append_sectors = max_sectors;
 }

@@ -756,8 +764,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors);
 	t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors,
 					b->max_write_zeroes_sectors);
-	t->max_zone_append_sectors = min(t->max_zone_append_sectors,
-					b->max_zone_append_sectors);
+	t->max_zone_append_sectors = min(queue_limits_max_zone_append_sectors(t),
+					 queue_limits_max_zone_append_sectors(b));
 	t->bounce = max(t->bounce, b->bounce);
 
 	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,

index 8c8f69d8ba48..e3ed5a921aff 100644
@@ -224,7 +224,7 @@ static ssize_t queue_zone_write_granularity_show(struct request_queue *q,
 
 static ssize_t queue_zone_append_max_show(struct request_queue *q, char *page)
 {
-	unsigned long long max_sectors = q->limits.max_zone_append_sectors;
+	unsigned long long max_sectors = queue_max_zone_append_sectors(q);
 
 	return sprintf(page, "%llu\n", max_sectors << SECTOR_SHIFT);
 }

index 3dceeaaeb973..ec917081cc0f 100644
@@ -1691,7 +1691,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
 		return -ENODEV;
 	}
 
-	if (!q->limits.max_zone_append_sectors) {
+	if (!queue_max_zone_append_sectors(q)) {
 		pr_warn("%s: Invalid 0 maximum zone append limit\n",
 			disk->disk_name);
 		return -ENODEV;

index a95b883512ea..7a621f23393f 100644
@@ -1174,12 +1174,29 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q)
 	return q->limits.max_segment_size;
 }
 
-static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q)
+static inline unsigned int queue_limits_max_zone_append_sectors(struct queue_limits *l)
 {
+	unsigned int max_sectors = min(l->chunk_sectors, l->max_hw_sectors);
 
-	const struct queue_limits *l = &q->limits;
+	return min_not_zero(l->max_zone_append_sectors, max_sectors);
+}
+
+static inline unsigned int queue_max_zone_append_sectors(struct request_queue *q)
+{
+	if (!blk_queue_is_zoned(q))
+		return 0;
 
-	return min(l->max_zone_append_sectors, l->max_sectors);
+	return queue_limits_max_zone_append_sectors(&q->limits);
+}
+
+static inline bool queue_emulates_zone_append(struct request_queue *q)
+{
+	return blk_queue_is_zoned(q) && !q->limits.max_zone_append_sectors;
+}
+
+static inline bool bdev_emulates_zone_append(struct block_device *bdev)
+{
+	return queue_emulates_zone_append(bdev_get_queue(bdev));
 }
 
 static inline unsigned int

index 2c6a317bef7c..98afae838126 100644
@@ -906,8 +906,7 @@ bool blk_update_request(struct request *req, blk_status_t error,
 
 		if (bio_bytes == bio->bi_iter.bi_size) {
 			req->bio = bio->bi_next;
-		} else if (req_op(req) == REQ_OP_ZONE_APPEND &&
-			   error == BLK_STS_OK) {
+		} else if (bio_is_zone_append(bio) && error == BLK_STS_OK) {
 			/*
 			 * Partial zone append completions cannot be supported
 			 * as the BIO fragments may end up not being written

118 lines not on this page · raw message

index 18778e397e66..5da46f066e8f 100644
@@ -421,6 +421,11 @@ static inline bool bio_zone_write_plugging(struct bio *bio)
 {
 	return bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING);
 }
+static inline bool bio_is_zone_append(struct bio *bio)
+{
+	return bio_op(bio) == REQ_OP_ZONE_APPEND ||
+		bio_flagged(bio, BIO_EMULATES_ZONE_APPEND);
+}
 void blk_zone_write_plug_bio_merged(struct bio *bio);
 void blk_zone_write_plug_attempt_merge(struct request *rq);
 static inline void blk_zone_update_request_bio(struct request *rq,

@@ -430,8 +435,9 @@ static inline void blk_zone_update_request_bio(struct request *rq,
 	 * For zone append requests, the request sector indicates the location
 	 * at which the BIO data was written. Return this value to the BIO
 	 * issuer through the BIO iter sector.
-	 * For plugged zone writes, we need the original BIO sector so
-	 * that blk_zone_write_plug_bio_endio() can lookup the zone write plug.
+	 * For plugged zone writes, which include emulated zone append, we need
+	 * the original BIO sector so that blk_zone_write_plug_bio_endio() can
+	 * lookup the zone write plug.
 	 */
 	if (req_op(rq) == REQ_OP_ZONE_APPEND || bio_zone_write_plugging(bio))
 		bio->bi_iter.bi_sector = rq->__sector;

@@ -464,6 +470,10 @@ static inline bool bio_zone_write_plugging(struct bio *bio)
 {
 	return false;
 }
+static inline bool bio_is_zone_append(struct bio *bio)
+{
+	return false;
+}
 static inline void blk_zone_write_plug_bio_merged(struct bio *bio)
 {
 }

index ed45de07d2ef..29b3170431e7 100644
@@ -311,6 +311,7 @@ enum {
 	BIO_REMAPPED,
 	BIO_ZONE_WRITE_LOCKED,	/* Owns a zoned device zone write lock */
 	BIO_ZONE_WRITE_PLUGGING, /* bio handled through zone write plugging */
+	BIO_EMULATES_ZONE_APPEND, /* bio emulates a zone append operation */
 	BIO_FLAG_LAST
 };
 

index 4dc9a5f3b4da..1441f7aa3036 100644
@@ -1510,12 +1510,28 @@ void disk_free_zone_resources(struct gendisk *disk)
 	disk->nr_zones = 0;
 }
 
+static inline bool disk_need_zone_resources(struct gendisk *disk)
+{
+	/*
+	 * All mq zoned devices need zone resources so that the block layer
+	 * can automatically handle write BIO plugging. BIO-based device drivers
+	 * (e.g. DM devices) are normally responsible for handling zone write
+	 * ordering and do not need zone resources, unless the driver requires
+	 * zone append emulation.
+	 */
+	return queue_is_mq(disk->queue) ||
+		queue_emulates_zone_append(disk->queue);
+}
+
 static int disk_revalidate_zone_resources(struct gendisk *disk,
 					  unsigned int nr_zones)
 {
 	struct queue_limits *lim = &disk->queue->limits;
 	unsigned int pool_size;
 
+	if (!disk_need_zone_resources(disk))
+		return 0;
+
 	/*
 	 * If the device has no limit on the maximum number of open and active
 	 * zones, use BLK_ZONE_WPLUG_DEFAULT_POOL_SIZE.

@@ -1633,6 +1649,9 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
 				disk->disk_name);
 			return -ENODEV;
 		}
+
+		if (!disk_need_zone_resources(disk))
+			break;
 		if (!args->conv_zones_bitmap) {
 			args->conv_zones_bitmap =
 				blk_alloc_zone_bitmap(q->node, args->nr_zones);

@@ -1664,10 +1683,11 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
 		/*
 		 * We need to track the write pointer of all zones that are not
 		 * empty nor full. So make sure we have a zone write plug for
-		 * such zone.
+		 * such zone if the device has a zone write plug hash table.
 		 */
 		wp_offset = blk_zone_wp_offset(zone);
-		if (wp_offset && wp_offset < zone_sectors) {
+		if (disk->zone_wplugs_hash &&
+		    wp_offset && wp_offset < zone_sectors) {
 			zwplug = disk_get_and_lock_zone_wplug(disk, zone->start,
 							      GFP_NOIO, &flags);
 			if (!zwplug)

@@ -1698,8 +1718,8 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
  * be called within the disk ->revalidate method for blk-mq based drivers.
  * Before calling this function, the device driver must already have set the
  * device zone size (chunk_sector limit) and the max zone append limit.
- * For BIO based drivers, this function cannot be used. BIO based device drivers
- * only need to set disk->nr_zones so that the sysfs exposed value is correct.
+ * BIO based drivers can also use this function as long as the device queue
+ * can be safely frozen.
  * If the @update_driver_data callback function is not NULL, the callback is
  * executed with the device request queue frozen after all zones have been
  * checked.

@@ -1716,8 +1736,6 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
 
 	if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
 		return -EIO;
-	if (WARN_ON_ONCE(!queue_is_mq(q)))
-		return -EIO;
 
 	if (!capacity)
 		return -ENODEV;

index e6757a30dcca..08700bfc3e23 100644
@@ -140,7 +140,7 @@ struct mapped_device {
 
 #ifdef CONFIG_BLK_DEV_ZONED
 	unsigned int nr_zones;
-	unsigned int *zwp_offset;
+	void *zone_revalidate_map;
 #endif
 
 #ifdef CONFIG_IMA

538 lines not on this page · raw message

109 lines not on this page · raw message

index 7f1acbf6bd9e..6e951cd42074 100644
@@ -104,14 +104,12 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t);
 int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q);
 void dm_zone_endio(struct dm_io *io, struct bio *clone);
 #ifdef CONFIG_BLK_DEV_ZONED
-void dm_cleanup_zoned_dev(struct mapped_device *md);
 int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
 			unsigned int nr_zones, report_zones_cb cb, void *data);
 bool dm_is_zone_write(struct mapped_device *md, struct bio *bio);
 int dm_zone_map_bio(struct dm_target_io *io);
 #else
-static inline void dm_cleanup_zoned_dev(struct mapped_device *md) {}
-#define dm_blk_report_zones	NULL
+#define dm_blk_report_zones    NULL
 static inline bool dm_is_zone_write(struct mapped_device *md, struct bio *bio)
 {
 	return false;

index 3cf898670290..dcba9530ffa5 100644
@@ -1260,12 +1260,6 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd)
 		}
 	}
 
-	if (req_op(rq) == REQ_OP_ZONE_APPEND) {
-		ret = sd_zbc_prepare_zone_append(cmd, &lba, nr_blocks);
-		if (ret)
-			goto fail;
-	}
-
 	fua = rq->cmd_flags & REQ_FUA ? 0x8 : 0;
 	dix = scsi_prot_sg_count(cmd);
 	dif = scsi_host_dif_capable(cmd->device->host, sdkp->protection_type);

@@ -1348,7 +1342,6 @@ static blk_status_t sd_init_command(struct scsi_cmnd *cmd)
 		return sd_setup_flush_cmnd(cmd);
 	case REQ_OP_READ:
 	case REQ_OP_WRITE:
-	case REQ_OP_ZONE_APPEND:
 		return sd_setup_read_write_cmnd(cmd);
 	case REQ_OP_ZONE_RESET:
 		return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_RESET_WRITE_POINTER,

@@ -3979,7 +3972,6 @@ static void scsi_disk_release(struct device *dev)
 	struct scsi_disk *sdkp = to_scsi_disk(dev);
 
 	ida_free(&sd_index_ida, sdkp->index);
-	sd_zbc_free_zone_info(sdkp);
 	put_device(&sdkp->device->sdev_gendev);
 	free_opal_dev(sdkp->opal_dev);
 

index 5c4285a582b2..49dd600bfa48 100644
@@ -104,12 +104,6 @@ struct scsi_disk {
 	 * between zone starting LBAs is constant.
 	 */
 	u32		zone_starting_lba_gran;
-	u32		*zones_wp_offset;
-	spinlock_t	zones_wp_offset_lock;
-	u32		*rev_wp_offset;
-	struct mutex	rev_mutex;
-	struct work_struct zone_wp_offset_work;
-	char		*zone_wp_update_buf;
 #endif
 	atomic_t	openers;
 	sector_t	capacity;	/* size in logical blocks */

@@ -245,7 +239,6 @@ static inline int sd_is_zoned(struct scsi_disk *sdkp)
 
 #ifdef CONFIG_BLK_DEV_ZONED
 
-void sd_zbc_free_zone_info(struct scsi_disk *sdkp);
 int sd_zbc_read_zones(struct scsi_disk *sdkp, u8 buf[SD_BUF_SIZE]);
 int sd_zbc_revalidate_zones(struct scsi_disk *sdkp);
 blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,

@@ -255,13 +248,8 @@ unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
 int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
 		unsigned int nr_zones, report_zones_cb cb, void *data);
 
-blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba,
-				        unsigned int nr_blocks);
-
 #else /* CONFIG_BLK_DEV_ZONED */
 
-static inline void sd_zbc_free_zone_info(struct scsi_disk *sdkp) {}
-
 static inline int sd_zbc_read_zones(struct scsi_disk *sdkp, u8 buf[SD_BUF_SIZE])
 {
 	return 0;

@@ -285,13 +273,6 @@ static inline unsigned int sd_zbc_complete(struct scsi_cmnd *cmd,
 	return good_bytes;
 }
 
-static inline blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd,
-						      sector_t *lba,
-						      unsigned int nr_blocks)
-{
-	return BLK_STS_TARGET;
-}
-
 #define sd_zbc_report_zones NULL
 
 #endif /* CONFIG_BLK_DEV_ZONED */

416 lines not on this page · raw message

index bea3d5cf8a83..ab6af84e327c 100644
@@ -249,8 +249,7 @@ static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)
 static void ublk_dev_param_zoned_apply(struct ublk_device *ub)
 {
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ub->ub_disk->queue);
-	blk_queue_required_elevator_features(ub->ub_disk->queue,
-					     ELEVATOR_F_ZBD_SEQ_WRITE);
+
 	ub->ub_disk->nr_zones = ublk_get_nr_zones(ub);
 }
 

index 1689e2584104..8e217f8fadcd 100644
@@ -165,7 +165,6 @@ int null_register_zoned_dev(struct nullb *nullb)
 	struct request_queue *q = nullb->q;
 
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
-	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
 	nullb->disk->nr_zones = bdev_nr_zones(nullb->disk->part0);
 	return blk_revalidate_disk_zones(nullb->disk, NULL);
 }

index 71c39bcd872c..a5a50ba6ad9f 100644
@@ -253,6 +253,11 @@ static unsigned int g_zone_max_active;
 module_param_named(zone_max_active, g_zone_max_active, uint, 0444);
 MODULE_PARM_DESC(zone_max_active, "Maximum number of active zones when block device is zoned. Default: 0 (no limit)");
 
+static int g_zone_append_max_sectors = INT_MAX;
+module_param_named(zone_append_max_sectors, g_zone_append_max_sectors, int, 0444);
+MODULE_PARM_DESC(zone_append_max_sectors,
+		 "Maximum size of a zone append command (in 512B sectors). Specify 0 for zone append emulation");
+
 static struct nullb_device *null_alloc_dev(void);
 static void null_free_dev(struct nullb_device *dev);
 static void null_del_dev(struct nullb *nullb);

@@ -436,6 +441,7 @@ NULLB_DEVICE_ATTR(zone_capacity, ulong, NULL);
 NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
 NULLB_DEVICE_ATTR(zone_max_open, uint, NULL);
 NULLB_DEVICE_ATTR(zone_max_active, uint, NULL);
+NULLB_DEVICE_ATTR(zone_append_max_sectors, uint, NULL);
 NULLB_DEVICE_ATTR(virt_boundary, bool, NULL);
 NULLB_DEVICE_ATTR(no_sched, bool, NULL);
 NULLB_DEVICE_ATTR(shared_tags, bool, NULL);

@@ -580,6 +586,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_zone_nr_conv,
 	&nullb_device_attr_zone_max_open,
 	&nullb_device_attr_zone_max_active,
+	&nullb_device_attr_zone_append_max_sectors,
 	&nullb_device_attr_zone_readonly,
 	&nullb_device_attr_zone_offline,
 	&nullb_device_attr_virt_boundary,

@@ -671,7 +678,7 @@ static ssize_t memb_group_features_show(struct config_item *item, char *page)
 			"shared_tags,size,submit_queues,use_per_node_hctx,"
 			"virt_boundary,zoned,zone_capacity,zone_max_active,"
 			"zone_max_open,zone_nr_conv,zone_offline,zone_readonly,"
-			"zone_size\n");
+			"zone_size,zone_append_max_sectors\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);

@@ -751,6 +758,7 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->zone_nr_conv = g_zone_nr_conv;
 	dev->zone_max_open = g_zone_max_open;
 	dev->zone_max_active = g_zone_max_active;
+	dev->zone_append_max_sectors = g_zone_append_max_sectors;
 	dev->virt_boundary = g_virt_boundary;
 	dev->no_sched = g_no_sched;
 	dev->shared_tags = g_shared_tags;

index 477b97746823..a9c5df650ddb 100644
@@ -82,6 +82,7 @@ struct nullb_device {
 	unsigned int zone_nr_conv; /* number of conventional zones */
 	unsigned int zone_max_open; /* max number of open zones */
 	unsigned int zone_max_active; /* max number of active zones */
+	unsigned int zone_append_max_sectors; /* Max sectors per zone append command */
 	unsigned int submit_queues; /* number of submission queues */
 	unsigned int prev_submit_queues; /* number of submission queues before change */
 	unsigned int poll_queues; /* number of IOPOLL submission queues */

index 8e217f8fadcd..159746b0661c 100644
@@ -62,6 +62,7 @@ int null_init_zoned_dev(struct nullb_device *dev,
 			struct queue_limits *lim)
 {
 	sector_t dev_capacity_sects, zone_capacity_sects;
+	sector_t zone_append_max_bytes;
 	struct nullb_zone *zone;
 	sector_t sector = 0;
 	unsigned int i;

@@ -103,6 +104,12 @@ int null_init_zoned_dev(struct nullb_device *dev,
 			dev->zone_nr_conv);
 	}
 
+	zone_append_max_bytes =
+		ALIGN_DOWN(dev->zone_append_max_sectors << SECTOR_SHIFT,
+			   dev->blocksize);
+	dev->zone_append_max_sectors =
+		min(zone_append_max_bytes >> SECTOR_SHIFT, zone_capacity_sects);
+
 	/* Max active zones has to be < nbr of seq zones in order to be enforceable */
 	if (dev->zone_max_active >= dev->nr_zones - dev->zone_nr_conv) {
 		dev->zone_max_active = 0;

@@ -154,7 +161,7 @@ int null_init_zoned_dev(struct nullb_device *dev,
 
 	lim->zoned = true;
 	lim->chunk_sectors = dev->zone_size_sects;
-	lim->max_zone_append_sectors = dev->zone_size_sects;
+	lim->max_zone_append_sectors = dev->zone_append_max_sectors;
 	lim->max_open_zones = dev->zone_max_open;
 	lim->max_active_zones = dev->zone_max_active;
 	return 0;

@@ -163,10 +170,16 @@ int null_init_zoned_dev(struct nullb_device *dev,
 int null_register_zoned_dev(struct nullb *nullb)
 {
 	struct request_queue *q = nullb->q;
+	struct gendisk *disk = nullb->disk;
 
 	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
-	nullb->disk->nr_zones = bdev_nr_zones(nullb->disk->part0);
-	return blk_revalidate_disk_zones(nullb->disk, NULL);
+	disk->nr_zones = bdev_nr_zones(disk->part0);
+
+	pr_info("%s: using %s zone append\n",
+		disk->disk_name,
+		queue_emulates_zone_append(q) ? "emulated" : "native");
+
+	return blk_revalidate_disk_zones(disk, NULL);
 }
 
 void null_free_zoned_dev(struct nullb_device *dev)

@@ -365,6 +378,9 @@ static blk_status_t null_zone_write(struct nullb_cmd *cmd, sector_t sector,
 
 	trace_nullb_zone_op(cmd, zno, zone->cond);
 
+	if (WARN_ON_ONCE(append && !dev->zone_append_max_sectors))
+		return BLK_STS_IOERR;
+
 	if (zone->type == BLK_ZONE_TYPE_CONVENTIONAL) {
 		if (append)
 			return BLK_STS_IOERR;

index a5a50ba6ad9f..578660b1ad01 100644
@@ -225,6 +225,10 @@ static unsigned long g_cache_size;
 module_param_named(cache_size, g_cache_size, ulong, 0444);
 MODULE_PARM_DESC(mbps, "Cache size in MiB for memory-backed device. Default: 0 (none)");
 
+static bool g_fua = true;
+module_param_named(fua, g_fua, bool, 0444);
+MODULE_PARM_DESC(zoned, "Enable/disable FUA support when cache_size is used. Default: true");
+
 static unsigned int g_mbps;
 module_param_named(mbps, g_mbps, uint, 0444);
 MODULE_PARM_DESC(mbps, "Limit maximum bandwidth (in MiB/s). Default: 0 (no limit)");

@@ -446,6 +450,7 @@ NULLB_DEVICE_ATTR(virt_boundary, bool, NULL);
 NULLB_DEVICE_ATTR(no_sched, bool, NULL);
 NULLB_DEVICE_ATTR(shared_tags, bool, NULL);
 NULLB_DEVICE_ATTR(shared_tag_bitmap, bool, NULL);
+NULLB_DEVICE_ATTR(fua, bool, NULL);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
 {

@@ -593,6 +598,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_no_sched,
 	&nullb_device_attr_shared_tags,
 	&nullb_device_attr_shared_tag_bitmap,
+	&nullb_device_attr_fua,
 	NULL,
 };
 

@@ -671,7 +677,7 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item)
 static ssize_t memb_group_features_show(struct config_item *item, char *page)
 {
 	return snprintf(page, PAGE_SIZE,
-			"badblocks,blocking,blocksize,cache_size,"
+			"badblocks,blocking,blocksize,cache_size,fua,"
 			"completion_nsec,discard,home_node,hw_queue_depth,"
 			"irqmode,max_sectors,mbps,memory_backed,no_sched,"
 			"poll_queues,power,queue_mode,shared_tag_bitmap,"

@@ -763,6 +769,8 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->no_sched = g_no_sched;
 	dev->shared_tags = g_shared_tags;
 	dev->shared_tag_bitmap = g_shared_tag_bitmap;
+	dev->fua = g_fua;
+
 	return dev;
 }
 

@@ -1920,7 +1928,7 @@ static int null_add_dev(struct nullb_device *dev)
 
 	if (dev->cache_size > 0) {
 		set_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags);
-		blk_queue_write_cache(nullb->q, true, true);
+		blk_queue_write_cache(nullb->q, true, dev->fua);
 	}
 
 	nullb->q->queuedata = nullb;

index a9c5df650ddb..3234e6c85eed 100644
@@ -105,6 +105,7 @@ struct nullb_device {
 	bool no_sched; /* no IO scheduler for the device */
 	bool shared_tags; /* share tag set between devices for blk-mq */
 	bool shared_tag_bitmap; /* use hostwide shared tags */
+	bool fua; /* Support FUA */
 };
 
 struct nullb {

index 3148d9f1bde6..0021d06041c1 100644
@@ -52,14 +52,10 @@ bool nvmet_bdev_zns_enable(struct nvmet_ns *ns)
 	if (get_capacity(bd_disk) & (bdev_zone_sectors(ns->bdev) - 1))
 		return false;
 	/*
-	 * ZNS does not define a conventional zone type. If the underlying
-	 * device has a bitmap set indicating the existence of conventional
-	 * zones, reject the device. Otherwise, use report zones to detect if
-	 * the device has conventional zones.
+	 * ZNS does not define a conventional zone type. Use report zones
+	 * to detect if the device has conventional zones and reject it if
+	 * it does.
 	 */
-	if (ns->bdev->bd_disk->conv_zones_bitmap)
-		return false;
-
 	ret = blkdev_report_zones(ns->bdev, 0, bdev_nr_zones(ns->bdev),
 				  validate_conv_zones_cb, NULL);
 	if (ret < 0)

index 98afae838126..e1e13d755033 100644
@@ -1921,19 +1921,6 @@ static void blk_mq_handle_dev_resource(struct request *rq,
 	__blk_mq_requeue_request(rq);
 }
 
-static void blk_mq_handle_zone_resource(struct request *rq,
-					struct list_head *zone_list)
-{
-	/*
-	 * If we end up here it is because we cannot dispatch a request to a
-	 * specific zone due to LLD level zone-write locking or other zone
-	 * related resource not being available. In this case, set the request
-	 * aside in zone_list for retrying it later.
-	 */
-	list_add(&rq->queuelist, zone_list);
-	__blk_mq_requeue_request(rq);
-}
-
 enum prep_dispatch {
 	PREP_DISPATCH_OK,
 	PREP_DISPATCH_NO_TAG,

@@ -2019,7 +2006,6 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 	struct request *rq;
 	int queued;
 	blk_status_t ret = BLK_STS_OK;
-	LIST_HEAD(zone_list);
 	bool needs_resource = false;
 
 	if (list_empty(list))

@@ -2061,23 +2047,11 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
 		case BLK_STS_DEV_RESOURCE:
 			blk_mq_handle_dev_resource(rq, list);
 			goto out;
-		case BLK_STS_ZONE_RESOURCE:
-			/*
-			 * Move the request to zone_list and keep going through
-			 * the dispatch list to find more requests the drive can
-			 * accept.
-			 */
-			blk_mq_handle_zone_resource(rq, &zone_list);
-			needs_resource = true;
-			break;
 		default:
 			blk_mq_end_request(rq, ret);
 		}
 	} while (!list_empty(list));
 out:
-	if (!list_empty(&zone_list))
-		list_splice_tail_init(&zone_list, list);
-
 	/* If we didn't flush the entire list, we could have told the driver
 	 * there was more coming, but that turned out to be a lie.
 	 */

index 2e28e2360c85..9ca96116bd33 100644
@@ -1870,7 +1870,6 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 	case BLK_STS_OK:
 		break;
 	case BLK_STS_RESOURCE:
-	case BLK_STS_ZONE_RESOURCE:
 		if (scsi_device_blocked(sdev))
 			ret = BLK_STS_DEV_RESOURCE;
 		break;

index 29b3170431e7..ffe0c112b128 100644
@@ -136,18 +136,6 @@ typedef u16 blk_short_t;
  */
 #define BLK_STS_DEV_RESOURCE	((__force blk_status_t)13)
 
-/*
- * BLK_STS_ZONE_RESOURCE is returned from the driver to the block layer if zone
- * related resources are unavailable, but the driver can guarantee the queue
- * will be rerun in the future once the resources become available again.
- *
- * This is different from BLK_STS_DEV_RESOURCE in that it explicitly references
- * a zone specific resource and IO to a different zone on the same device could
- * still be served. Examples of that are zones that are write-locked, but a read
- * to the same zone could be served.
- */
-#define BLK_STS_ZONE_RESOURCE	((__force blk_status_t)14)
-
 /*
  * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion
  * path if the device returns a status indicating that too many zone resources

@@ -155,7 +143,7 @@ typedef u16 blk_short_t;
  * after the number of open zones decreases below the device's limits, which is
  * reported in the request_queue's max_open_zones.
  */
-#define BLK_STS_ZONE_OPEN_RESOURCE	((__force blk_status_t)15)
+#define BLK_STS_ZONE_OPEN_RESOURCE	((__force blk_status_t)14)
 
 /*
  * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion

@@ -164,20 +152,20 @@ typedef u16 blk_short_t;
  * after the number of active zones decreases below the device's limits, which
  * is reported in the request_queue's max_active_zones.
  */
-#define BLK_STS_ZONE_ACTIVE_RESOURCE	((__force blk_status_t)16)
+#define BLK_STS_ZONE_ACTIVE_RESOURCE	((__force blk_status_t)15)
 
 /*
  * BLK_STS_OFFLINE is returned from the driver when the target device is offline
  * or is being taken offline. This could help differentiate the case where a
  * device is intentionally being shut down from a real I/O error.
  */
-#define BLK_STS_OFFLINE		((__force blk_status_t)17)
+#define BLK_STS_OFFLINE		((__force blk_status_t)16)
 
 /*
  * BLK_STS_DURATION_LIMIT is returned from the driver when the target device
  * aborted the command because it exceeded one of its Command Duration Limits.
  */
-#define BLK_STS_DURATION_LIMIT	((__force blk_status_t)18)
+#define BLK_STS_DURATION_LIMIT	((__force blk_status_t)17)
 
 /**
  * blk_path_error - returns true if error may be path related

index 1441f7aa3036..8e821974d46b 100644
@@ -1711,21 +1711,17 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
 /**
  * blk_revalidate_disk_zones - (re)allocate and initialize zone bitmaps
  * @disk:	Target disk
- * @update_driver_data:	Callback to update driver data on the frozen disk
  *
- * Helper function for low-level device drivers to check and (re) allocate and
- * initialize a disk request queue zone bitmaps. This functions should normally
- * be called within the disk ->revalidate method for blk-mq based drivers.
+ * Helper function for low-level device drivers to check, (re) allocate and
+ * initialize resources used for managing zoned disks. This function should
+ * normally be called by blk-mq based drivers when a zoned gendisk is probed
+ * and when the zone configuration of the gendisk changes (e.g. after a format).
  * Before calling this function, the device driver must already have set the
  * device zone size (chunk_sector limit) and the max zone append limit.
  * BIO based drivers can also use this function as long as the device queue
  * can be safely frozen.
- * If the @update_driver_data callback function is not NULL, the callback is
- * executed with the device request queue frozen after all zones have been
- * checked.
  */
-int blk_revalidate_disk_zones(struct gendisk *disk,
-			      void (*update_driver_data)(struct gendisk *disk))
+int blk_revalidate_disk_zones(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
 	sector_t zone_sectors = q->limits.chunk_sectors;

@@ -1792,13 +1788,10 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
 	 * referencing the bitmaps).
 	 */
 	blk_mq_freeze_queue(q);
-	if (ret > 0) {
+	if (ret > 0)
 		ret = disk_update_zone_resources(disk, &args);
-		if (update_driver_data)
-			update_driver_data(disk);
-	} else {
+	else
 		pr_warn("%s: failed to revalidate zones\n", disk->disk_name);
-	}
 	if (ret)
 		disk_free_zone_resources(disk);
 	blk_mq_unfreeze_queue(q);

index 159746b0661c..34f4d273df38 100644
@@ -179,7 +179,7 @@ int null_register_zoned_dev(struct nullb *nullb)
 		disk->disk_name,
 		queue_emulates_zone_append(q) ? "emulated" : "native");
 
-	return blk_revalidate_disk_zones(disk, NULL);
+	return blk_revalidate_disk_zones(disk);
 }
 
 void null_free_zoned_dev(struct nullb_device *dev)

index ab6af84e327c..851c78913de2 100644
@@ -221,7 +221,7 @@ static int ublk_get_nr_zones(const struct ublk_device *ub)
 
 static int ublk_revalidate_disk_zones(struct ublk_device *ub)
 {
-	return blk_revalidate_disk_zones(ub->ub_disk, NULL);
+	return blk_revalidate_disk_zones(ub->ub_disk);
 }
 
 static int ublk_dev_param_zoned_validate(const struct ublk_device *ub)

index 42dea7601d87..c1af0a7d56c8 100644
@@ -1543,7 +1543,7 @@ static int virtblk_probe(struct virtio_device *vdev)
 	 */
 	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && lim.zoned) {
 		blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, vblk->disk->queue);
-		err = blk_revalidate_disk_zones(vblk->disk, NULL);
+		err = blk_revalidate_disk_zones(vblk->disk);
 		if (err)
 			goto out_cleanup_disk;
 	}

index 174fda0a301c..99d27fba01d3 100644
@@ -169,7 +169,7 @@ static int dm_revalidate_zones(struct mapped_device *md, struct dm_table *t)
 	 * our table for dm_blk_report_zones() to use directly.
 	 */
 	md->zone_revalidate_map = t;
-	ret = blk_revalidate_disk_zones(disk, NULL);
+	ret = blk_revalidate_disk_zones(disk);
 	md->zone_revalidate_map = NULL;
 
 	if (ret) {

index 943d72bdd794..c9955ecd1790 100644
@@ -2150,7 +2150,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	blk_mq_unfreeze_queue(ns->disk->queue);
 
 	if (blk_queue_is_zoned(ns->queue)) {
-		ret = blk_revalidate_disk_zones(ns->disk, NULL);
+		ret = blk_revalidate_disk_zones(ns->disk);
 		if (ret && !nvme_first_scan(ns->disk))
 			goto out;
 	}

index d0ead9858954..806036e48abe 100644
@@ -572,7 +572,7 @@ int sd_zbc_revalidate_zones(struct scsi_disk *sdkp)
 	blk_queue_max_zone_append_sectors(q, 0);
 
 	flags = memalloc_noio_save();
-	ret = blk_revalidate_disk_zones(disk, NULL);
+	ret = blk_revalidate_disk_zones(disk);
 	memalloc_noio_restore(flags);
 	if (ret) {
 		sdkp->zone_info = (struct zoned_disk_info){ };

index 7a621f23393f..19f59e0e5f29 100644
@@ -336,8 +336,7 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 		unsigned int nr_zones, report_zones_cb cb, void *data);
 int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
 		sector_t sectors, sector_t nr_sectors);
-int blk_revalidate_disk_zones(struct gendisk *disk,
-		void (*update_driver_data)(struct gendisk *disk));
+int blk_revalidate_disk_zones(struct gendisk *disk);
 
 /*
  * Independent access ranges: struct blk_independent_access_range describes

index 02a916ba62ee..dce8d746b5bd 100644
@@ -102,7 +102,6 @@ struct deadline_data {
 	int prio_aging_expire;
 
 	spinlock_t lock;
-	spinlock_t zone_lock;
 };
 
 /* Maps an I/O priority class to a deadline scheduler priority. */

@@ -157,8 +156,7 @@ deadline_latter_request(struct request *rq)
 }
 
 /*
- * Return the first request for which blk_rq_pos() >= @pos. For zoned devices,
- * return the first request after the start of the zone containing @pos.
+ * Return the first request for which blk_rq_pos() >= @pos.
  */
 static inline struct request *deadline_from_pos(struct dd_per_prio *per_prio,
 				enum dd_data_dir data_dir, sector_t pos)

@@ -170,14 +168,6 @@ static inline struct request *deadline_from_pos(struct dd_per_prio *per_prio,
 		return NULL;
 
 	rq = rb_entry_rq(node);
-	/*
-	 * A zoned write may have been requeued with a starting position that
-	 * is below that of the most recently dispatched request. Hence, for
-	 * zoned writes, start searching from the start of a zone.
-	 */
-	if (blk_rq_is_seq_zoned_write(rq))
-		pos = round_down(pos, rq->q->limits.chunk_sectors);
-
 	while (node) {
 		rq = rb_entry_rq(node);
 		if (blk_rq_pos(rq) >= pos) {

@@ -308,36 +298,6 @@ static inline bool deadline_check_fifo(struct dd_per_prio *per_prio,
 	return time_is_before_eq_jiffies((unsigned long)rq->fifo_time);
 }
 
-/*
- * Check if rq has a sequential request preceding it.
- */
-static bool deadline_is_seq_write(struct deadline_data *dd, struct request *rq)
-{
-	struct request *prev = deadline_earlier_request(rq);
-
-	if (!prev)
-		return false;
-
-	return blk_rq_pos(prev) + blk_rq_sectors(prev) == blk_rq_pos(rq);
-}
-
-/*
- * Skip all write requests that are sequential from @rq, even if we cross
- * a zone boundary.
- */
-static struct request *deadline_skip_seq_writes(struct deadline_data *dd,
-						struct request *rq)
-{
-	sector_t pos = blk_rq_pos(rq);
-
-	do {
-		pos += blk_rq_sectors(rq);
-		rq = deadline_latter_request(rq);
-	} while (rq && blk_rq_pos(rq) == pos);
-
-	return rq;
-}
-
 /*
  * For the specified data direction, return the next request to
  * dispatch using arrival ordered lists.

@@ -346,40 +306,10 @@ static struct request *
 deadline_fifo_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
 		      enum dd_data_dir data_dir)
 {
-	struct request *rq, *rb_rq, *next;
-	unsigned long flags;
-
 	if (list_empty(&per_prio->fifo_list[data_dir]))
 		return NULL;
 
-	rq = rq_entry_fifo(per_prio->fifo_list[data_dir].next);
-	if (data_dir == DD_READ || !blk_queue_is_zoned(rq->q))
-		return rq;
-
-	/*
-	 * Look for a write request that can be dispatched, that is one with
-	 * an unlocked target zone. For some HDDs, breaking a sequential
-	 * write stream can lead to lower throughput, so make sure to preserve
-	 * sequential write streams, even if that stream crosses into the next
-	 * zones and these zones are unlocked.
-	 */
-	spin_lock_irqsave(&dd->zone_lock, flags);
-	list_for_each_entry_safe(rq, next, &per_prio->fifo_list[DD_WRITE],
-				 queuelist) {
-		/* Check whether a prior request exists for the same zone. */
-		rb_rq = deadline_from_pos(per_prio, data_dir, blk_rq_pos(rq));
-		if (rb_rq && blk_rq_pos(rb_rq) < blk_rq_pos(rq))
-			rq = rb_rq;
-		if (blk_req_can_dispatch_to_zone(rq) &&
-		    (blk_queue_nonrot(rq->q) ||
-		     !deadline_is_seq_write(dd, rq)))
-			goto out;
-	}
-	rq = NULL;
-out:
-	spin_unlock_irqrestore(&dd->zone_lock, flags);
-
-	return rq;
+	return rq_entry_fifo(per_prio->fifo_list[data_dir].next);
 }
 
 /*

@@ -390,36 +320,8 @@ static struct request *
 deadline_next_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
 		      enum dd_data_dir data_dir)
 {
-	struct request *rq;
-	unsigned long flags;
-
-	rq = deadline_from_pos(per_prio, data_dir,
-			       per_prio->latest_pos[data_dir]);
-	if (!rq)
-		return NULL;
-
-	if (data_dir == DD_READ || !blk_queue_is_zoned(rq->q))
-		return rq;
-
-	/*
-	 * Look for a write request that can be dispatched, that is one with
-	 * an unlocked target zone. For some HDDs, breaking a sequential
-	 * write stream can lead to lower throughput, so make sure to preserve
-	 * sequential write streams, even if that stream crosses into the next
-	 * zones and these zones are unlocked.
-	 */
-	spin_lock_irqsave(&dd->zone_lock, flags);
-	while (rq) {
-		if (blk_req_can_dispatch_to_zone(rq))
-			break;
-		if (blk_queue_nonrot(rq->q))
-			rq = deadline_latter_request(rq);
-		else
-			rq = deadline_skip_seq_writes(dd, rq);
-	}
-	spin_unlock_irqrestore(&dd->zone_lock, flags);
-
-	return rq;
+	return deadline_from_pos(per_prio, data_dir,
+				 per_prio->latest_pos[data_dir]);
 }
 
 /*

@@ -525,10 +427,6 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd,
 		rq = next_rq;
 	}
 
-	/*
-	 * For a zoned block device, if we only have writes queued and none of
-	 * them can be dispatched, rq will be NULL.
-	 */
 	if (!rq)
 		return NULL;
 

@@ -549,10 +447,6 @@ static struct request *__dd_dispatch_request(struct deadline_data *dd,
 	prio = ioprio_class_to_prio[ioprio_class];
 	dd->per_prio[prio].latest_pos[data_dir] = blk_rq_pos(rq);
 	dd->per_prio[prio].stats.dispatched++;
-	/*
-	 * If the request needs its target zone locked, do it.
-	 */
-	blk_req_zone_write_lock(rq);
 	rq->rq_flags |= RQF_STARTED;
 	return rq;
 }

@@ -722,7 +616,6 @@ static int dd_init_sched(struct request_queue *q, struct elevator_type *e)
 	dd->fifo_batch = fifo_batch;
 	dd->prio_aging_expire = prio_aging_expire;
 	spin_lock_init(&dd->lock);
-	spin_lock_init(&dd->zone_lock);
 
 	/* We dispatch from request queue wide instead of hw queue */
 	blk_queue_flag_set(QUEUE_FLAG_SQ_SCHED, q);

@@ -804,12 +697,6 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 
 	lockdep_assert_held(&dd->lock);
 
-	/*
-	 * This may be a requeue of a write request that has locked its
-	 * target zone. If it is the case, this releases the zone lock.
-	 */
-	blk_req_zone_write_unlock(rq);
-
 	prio = ioprio_class_to_prio[ioprio_class];
 	per_prio = &dd->per_prio[prio];
 	if (!rq->elv.priv[0]) {

@@ -841,18 +728,6 @@ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
 		 */
 		rq->fifo_time = jiffies + dd->fifo_expire[data_dir];
 		insert_before = &per_prio->fifo_list[data_dir];
-#ifdef CONFIG_BLK_DEV_ZONED
-		/*
-		 * Insert zoned writes such that requests are sorted by
-		 * position per zone.
-		 */
-		if (blk_rq_is_seq_zoned_write(rq)) {
-			struct request *rq2 = deadline_latter_request(rq);
-
-			if (rq2 && blk_rq_zone_no(rq2) == blk_rq_zone_no(rq))
-				insert_before = &rq2->queuelist;
-		}
-#endif
 		list_add_tail(&rq->queuelist, insert_before);
 	}
 }

@@ -887,33 +762,8 @@ static void dd_prepare_request(struct request *rq)
 	rq->elv.priv[0] = NULL;
 }
 
-static bool dd_has_write_work(struct blk_mq_hw_ctx *hctx)
-{
-	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
-	enum dd_prio p;
-
-	for (p = 0; p <= DD_PRIO_MAX; p++)
-		if (!list_empty_careful(&dd->per_prio[p].fifo_list[DD_WRITE]))
-			return true;
-
-	return false;
-}
-
 /*
  * Callback from inside blk_mq_free_request().
- *
- * For zoned block devices, write unlock the target zone of
- * completed write requests. Do this while holding the zone lock
- * spinlock so that the zone is never unlocked while deadline_fifo_request()
- * or deadline_next_request() are executing. This function is called for
- * all requests, whether or not these requests complete successfully.
- *
- * For a zoned block device, __dd_dispatch_request() may have stopped
- * dispatching requests if all the queued requests are write requests directed
- * at zones that are already locked due to on-going write requests. To ensure
- * write request dispatch progress in this case, mark the queue as needing a
- * restart to ensure that the queue is run again after completion of the
- * request and zones being unlocked.
  */
 static void dd_finish_request(struct request *rq)
 {

@@ -928,21 +778,8 @@ static void dd_finish_request(struct request *rq)
 	 * called dd_insert_requests(). Skip requests that bypassed I/O
 	 * scheduling. See also blk_mq_request_bypass_insert().
 	 */
-	if (!rq->elv.priv[0])
-		return;
-
-	atomic_inc(&per_prio->stats.completed);
-
-	if (blk_queue_is_zoned(q)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&dd->zone_lock, flags);
-		blk_req_zone_write_unlock(rq);
-		spin_unlock_irqrestore(&dd->zone_lock, flags);
-
-		if (dd_has_write_work(rq->mq_hctx))
-			blk_mq_sched_mark_restart_hctx(rq->mq_hctx);
-	}
+	if (rq->elv.priv[0])
+		atomic_inc(&per_prio->stats.completed);
 }
 
 static bool dd_has_work_for_prio(struct dd_per_prio *per_prio)

@@ -1266,7 +1103,6 @@ static struct elevator_type mq_deadline = {
 	.elevator_attrs = deadline_attrs,
 	.elevator_name = "mq-deadline",
 	.elevator_alias = "deadline",
-	.elevator_features = ELEVATOR_F_ZBD_SEQ_WRITE,
 	.elevator_owner = THIS_MODULE,
 };
 MODULE_ALIAS("mq-deadline-iosched");

index c0197e1e7485..715f4b6356c4 100644
@@ -1052,22 +1052,6 @@ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
 }
 EXPORT_SYMBOL_GPL(blk_queue_write_cache);
 
-/**
- * blk_queue_required_elevator_features - Set a queue required elevator features
- * @q:		the request queue for the target device
- * @features:	Required elevator features OR'ed together
- *
- * Tell the block layer that for the device controlled through @q, only the
- * only elevators that can be used are those that implement at least the set of
- * features specified by @features.
- */
-void blk_queue_required_elevator_features(struct request_queue *q,
-					  unsigned int features)
-{
-	q->required_elevator_features = features;
-}
-EXPORT_SYMBOL_GPL(blk_queue_required_elevator_features);
-
 /**
  * blk_queue_can_use_dma_map_merging - configure queue for merging segments.
  * @q:		the request queue for the device

76 lines not on this page · raw message

index 7ca3d7b6ed82..e9a050a96e53 100644
@@ -74,7 +74,6 @@ struct elevator_type
 	struct elv_fs_entry *elevator_attrs;
 	const char *elevator_name;
 	const char *elevator_alias;
-	const unsigned int elevator_features;
 	struct module *elevator_owner;
 #ifdef CONFIG_BLK_DEBUG_FS
 	const struct blk_mq_debugfs_attr *queue_debugfs_attrs;

index 19f59e0e5f29..618d354ceb94 100644
@@ -453,8 +453,6 @@ struct request_queue {
 
 	atomic_t		nr_active_requests_shared_tags;
 
-	unsigned int		required_elevator_features;
-
 	struct blk_mq_tags	*sched_shared_tags;
 
 	struct list_head	icq_list;

@@ -959,14 +957,6 @@ disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges);
 void disk_set_independent_access_ranges(struct gendisk *disk,
 				struct blk_independent_access_ranges *iars);
 
-/*
- * Elevator features for blk_queue_required_elevator_features:
- */
-/* Supports zoned block devices sequential write constraint */
-#define ELEVATOR_F_ZBD_SEQ_WRITE	(1U << 0)
-
-extern void blk_queue_required_elevator_features(struct request_queue *q,
-						 unsigned int features);
 extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
 					      struct device *dev);
 

index 3bf28149e104..e1a5344c2257 100644
@@ -589,8 +589,7 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q,
 		return BLK_STS_NOTSUPP;
 
 	/* The bio sector must point to the start of a sequential zone */
-	if (!bdev_is_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector) ||
-	    !bio_zone_is_seq(bio))
+	if (!bdev_is_zone_start(bio->bi_bdev, bio->bi_iter.bi_sector))
 		return BLK_STS_IOERR;
 
 	/*

deleted file mode 100644
index a77b099c34b7..000000000000
@@ -1,22 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2017 Western Digital Corporation or its affiliates.
- */
-
-#include <linux/blkdev.h>
-#include "blk-mq-debugfs.h"
-
-int queue_zone_wlock_show(void *data, struct seq_file *m)
-{
-	struct request_queue *q = data;
-	unsigned int i;
-
-	if (!q->disk->seq_zones_wlock)
-		return 0;
-
-	for (i = 0; i < q->disk->nr_zones; i++)
-		if (test_bit(i, q->disk->seq_zones_wlock))
-			seq_printf(m, "%u\n", i);
-
-	return 0;
-}

index 9c7d4b6117d4..3ebe2c29b624 100644
@@ -83,7 +83,7 @@ static inline void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos)
 }
 #endif
 
-#ifdef CONFIG_BLK_DEBUG_FS_ZONED
+#if defined(CONFIG_BLK_DEV_ZONED) && defined(CONFIG_BLK_DEBUG_FS)
 int queue_zone_wlock_show(void *data, struct seq_file *m);
 #else
 static inline int queue_zone_wlock_show(void *data, struct seq_file *m)

index 8e821974d46b..66cbf4ca3882 100644
@@ -23,6 +23,7 @@
 
 #include "blk.h"
 #include "blk-mq-sched.h"
+#include "blk-mq-debugfs.h"
 
 #define ZONE_COND_NAME(name) [BLK_ZONE_COND_##name] = #name
 static const char *const zone_cond_name[] = {

@@ -1802,3 +1803,22 @@ int blk_revalidate_disk_zones(struct gendisk *disk)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
+
+#ifdef CONFIG_BLK_DEBUG_FS
+
+int queue_zone_wlock_show(void *data, struct seq_file *m)
+{
+	struct request_queue *q = data;
+	unsigned int i;
+
+	if (!q->disk->seq_zones_wlock)
+		return 0;
+
+	for (i = 0; i < q->disk->nr_zones; i++)
+		if (test_bit(i, q->disk->seq_zones_wlock))
+			seq_printf(m, "%u\n", i);
+
+	return 0;
+}
+
+#endif

index 94668e72ab09..ca1f2b9422d5 100644
@@ -160,7 +160,7 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
 	{ "requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops },
 	{ "pm_only", 0600, queue_pm_only_show, NULL },
 	{ "state", 0600, queue_state_show, queue_state_write },
-	{ "zone_wlock", 0400, queue_zone_wlock_show, NULL },
+	{ "zone_wplugs", 0400, queue_zone_wplugs_show, NULL },
 	{ },
 };
 

index 3ebe2c29b624..c80e453e3014 100644
@@ -84,9 +84,9 @@ static inline void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos)
 #endif
 
 #if defined(CONFIG_BLK_DEV_ZONED) && defined(CONFIG_BLK_DEBUG_FS)
-int queue_zone_wlock_show(void *data, struct seq_file *m);
+int queue_zone_wplugs_show(void *data, struct seq_file *m);
 #else
-static inline int queue_zone_wlock_show(void *data, struct seq_file *m)
+static inline int queue_zone_wplugs_show(void *data, struct seq_file *m)
 {
 	return 0;
 }

index 66cbf4ca3882..2478775fb9d6 100644
@@ -1806,17 +1806,34 @@ EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
 
 #ifdef CONFIG_BLK_DEBUG_FS
 
-int queue_zone_wlock_show(void *data, struct seq_file *m)
+int queue_zone_wplugs_show(void *data, struct seq_file *m)
 {
 	struct request_queue *q = data;
-	unsigned int i;
+	struct gendisk *disk = q->disk;
+	struct blk_zone_wplug *zwplug;
+	unsigned int zwp_wp_offset, zwp_flags;
+	unsigned int zwp_zone_no, zwp_ref;
+	unsigned int zwp_bio_list_size, i;
+	unsigned long flags;
 
-	if (!q->disk->seq_zones_wlock)
-		return 0;
+	rcu_read_lock();
+	for (i = 0; i < disk_zone_wplugs_hash_size(disk); i++) {
+		hlist_for_each_entry_rcu(zwplug,
+					 &disk->zone_wplugs_hash[i], node) {
+			spin_lock_irqsave(&zwplug->lock, flags);
+			zwp_zone_no = zwplug->zone_no;
+			zwp_flags = zwplug->flags;
+			zwp_ref = atomic_read(&zwplug->ref);
+			zwp_wp_offset = zwplug->wp_offset;
+			zwp_bio_list_size = bio_list_size(&zwplug->bio_list);
+			spin_unlock_irqrestore(&zwplug->lock, flags);
 
-	for (i = 0; i < q->disk->nr_zones; i++)
-		if (test_bit(i, q->disk->seq_zones_wlock))
-			seq_printf(m, "%u\n", i);
+			seq_printf(m, "%u 0x%x %u %u %u\n",
+				   zwp_zone_no, zwp_flags, zwp_ref,
+				   zwp_wp_offset, zwp_bio_list_size);
+		}
+	}
+	rcu_read_unlock();
 
 	return 0;
 }

index ca1f2b9422d5..770c0c2b72fa 100644
@@ -256,7 +256,6 @@ static const char *const rqf_name[] = {
 	RQF_NAME(HASHED),
 	RQF_NAME(STATS),
 	RQF_NAME(SPECIAL_PAYLOAD),
-	RQF_NAME(ZONE_WRITE_LOCKED),
 	RQF_NAME(TIMED_OUT),
 	RQF_NAME(RESV),
 };

114 lines not on this page · raw message

93 lines not on this page · raw message

index ffe0c112b128..5751292fee6a 100644
@@ -297,7 +297,6 @@ enum {
 	BIO_QOS_THROTTLED,	/* bio went through rq_qos throttle path */
 	BIO_QOS_MERGED,		/* but went through rq_qos merge path */
 	BIO_REMAPPED,
-	BIO_ZONE_WRITE_LOCKED,	/* Owns a zoned device zone write lock */
 	BIO_ZONE_WRITE_PLUGGING, /* bio handled through zone write plugging */
 	BIO_EMULATES_ZONE_APPEND, /* bio emulates a zone append operation */
 	BIO_FLAG_LAST

index 618d354ceb94..d8cc24a1635b 100644
@@ -177,23 +177,14 @@ struct gendisk {
 
 #ifdef CONFIG_BLK_DEV_ZONED
 	/*
-	 * Zoned block device information for request dispatch control.
-	 * nr_zones is the total number of zones of the device. This is always
-	 * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones
-	 * bits which indicates if a zone is conventional (bit set) or
-	 * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones
-	 * bits which indicates if a zone is write locked, that is, if a write
-	 * request targeting the zone was dispatched.
-	 *
-	 * Reads of this information must be protected with blk_queue_enter() /
-	 * blk_queue_exit(). Modifying this information is only allowed while
-	 * no requests are being processed. See also blk_mq_freeze_queue() and
-	 * blk_mq_unfreeze_queue().
+	 * Zoned block device information. Reads of this information must be
+	 * protected with blk_queue_enter() / blk_queue_exit(). Modifying this
+	 * information is only allowed while no requests are being processed.
+	 * See also blk_mq_freeze_queue() and blk_mq_unfreeze_queue().
 	 */
 	unsigned int		nr_zones;
 	unsigned int		zone_capacity;
 	unsigned long		*conv_zones_bitmap;
-	unsigned long		*seq_zones_wlock;
 	unsigned int            zone_wplugs_hash_bits;
 	spinlock_t              zone_wplugs_lock;
 	struct mempool_s	*zone_wplugs_pool;

@@ -635,15 +626,6 @@ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 	return sector >> ilog2(disk->queue->limits.chunk_sectors);
 }
 
-static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
-{
-	if (!blk_queue_is_zoned(disk->queue))
-		return false;
-	if (!disk->conv_zones_bitmap)
-		return true;
-	return !test_bit(disk_zone_no(disk, sector), disk->conv_zones_bitmap);
-}
-
 static inline void disk_set_max_open_zones(struct gendisk *disk,
 		unsigned int max_open_zones)
 {

@@ -677,10 +659,6 @@ static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
 	return 0;
 }
-static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
-{
-	return false;
-}
 static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 {
 	return 0;

@@ -870,11 +848,6 @@ static inline bool bio_straddles_zones(struct bio *bio)
 		disk_zone_no(bio->bi_bdev->bd_disk, bio_end_sector(bio) - 1);
 }
 
-static inline unsigned int bio_zone_is_seq(struct bio *bio)
-{
-	return disk_zone_is_seq(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector);
-}
-
 /*
  * Return how much of the chunk is left to be used for I/O at a given offset.
  */

index e1a5344c2257..47400a4fe851 100644
@@ -907,12 +907,6 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
 	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
 		return 0;
 
-	/*
-	 * As the requests that require a zone lock are not plugged in the
-	 * first place, directly accessing the plug instead of using
-	 * blk_mq_plug() should not have any consequences during flushing for
-	 * zoned devices.
-	 */
 	blk_flush_plug(current->plug, false);
 
 	/*

index 7a9f8187ea62..3228868283a4 100644
@@ -1112,10 +1112,9 @@ static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q,
 bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
 		unsigned int nr_segs)
 {
-	struct blk_plug *plug;
+	struct blk_plug *plug = current->plug;
 	struct request *rq;
 
-	plug = blk_mq_plug(bio);
 	if (!plug || rq_list_empty(plug->mq_list))
 		return false;
 

index e1e13d755033..045b195faad4 100644
@@ -1330,11 +1330,6 @@ void blk_execute_rq_nowait(struct request *rq, bool at_head)
 
 	blk_account_io_start(rq);
 
-	/*
-	 * As plugging can be enabled for passthrough requests on a zoned
-	 * device, directly accessing the plug instead of using blk_mq_plug()
-	 * should not have any consequences.
-	 */
 	if (current->plug && !at_head) {
 		blk_add_rq_to_plug(current->plug, rq);
 		return;

@@ -2932,7 +2927,7 @@ static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
 void blk_mq_submit_bio(struct bio *bio)
 {
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	struct blk_plug *plug = blk_mq_plug(bio);
+	struct blk_plug *plug = current->plug;
 	const int is_sync = op_is_sync(bio->bi_opf);
 	struct blk_mq_hw_ctx *hctx;
 	unsigned int nr_segs = 1;

index f75a9ecfebde..260beea8e332 100644
@@ -365,37 +365,6 @@ static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap)
 		qmap->mq_map[cpu] = 0;
 }
 
-/*
- * blk_mq_plug() - Get caller context plug
- * @bio : the bio being submitted by the caller context
- *
- * Plugging, by design, may delay the insertion of BIOs into the elevator in
- * order to increase BIO merging opportunities. This however can cause BIO
- * insertion order to change from the order in which submit_bio() is being
- * executed in the case of multiple contexts concurrently issuing BIOs to a
- * device, even if these context are synchronized to tightly control BIO issuing
- * order. While this is not a problem with regular block devices, this ordering
- * change can cause write BIO failures with zoned block devices as these
- * require sequential write patterns to zones. Prevent this from happening by
- * ignoring the plug state of a BIO issuing context if it is for a zoned block
- * device and the BIO to plug is a write operation.
- *
- * Return current->plug if the bio can be plugged and NULL otherwise
- */
-static inline struct blk_plug *blk_mq_plug( struct bio *bio)
-{
-	/* Zoned block device write operation case: do not plug the BIO */
-	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
-	    bdev_op_is_zoned_write(bio->bi_bdev, bio_op(bio)))
-		return NULL;
-
-	/*
-	 * For regular block devices or read operations, use the context plug
-	 * which may be NULL if blk_start_plug() was not executed.
-	 */
-	return current->plug;
-}
-
 /* Free all requests on the list */
 static inline void blk_mq_free_requests(struct list_head *list)
 {

index d8cc24a1635b..5b86af75a29f 100644
@@ -1300,18 +1300,6 @@ static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec)
 	return disk_zone_no(bdev->bd_disk, sec);
 }
 
-/* Whether write serialization is required for @op on zoned devices. */
-static inline bool op_needs_zoned_write_locking(enum req_op op)
-{
-	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);