Merge branch 'for-5.5/block' into for-5.5/drivers

Pull in dependencies for the new zoned open/close/finish support.

* for-5.5/block: (32 commits)
  block: add zone open, close and finish ioctl support
  block: add zone open, close and finish operations
  block: Simplify REQ_OP_ZONE_RESET_ALL handling
  block: Remove REQ_OP_ZONE_RESET plugging
  block: Warn if elevator= parameter is used
  block: avoid blk_bio_segment_split for small I/O operations
  blk-mq: make sure that line break can be printed
  block: sed-opal: Introduce Opal Datastore UID
  block: sed-opal: Add support to read/write opal tables generically
  block: sed-opal: Generalizing write data to any opal table
  bdev: Refresh bdev size for disks without partitioning
  bdev: Factor out bdev revalidation into a common helper
  blk-mq: avoid sysfs buffer overflow with too many CPU cores
  blk-mq: Make blk_mq_run_hw_queue() return void
  fcntl: fix typo in RWH_WRITE_LIFE_NOT_SET r/w hint name
  blk-mq: fill header with kernel-doc
  blk-mq: remove needless goto from blk_mq_get_driver_tag
  block: reorder bio::__bi_remaining for better packing
  block: Reduce the amount of memory used for tag sets
  block: Reduce the amount of memory required per request queue
  ...

block/blk-core.c

@@ -132,6 +132,9 @@ static const char *const blk_op_name[] = {
 	REQ_OP_NAME(SECURE_ERASE),
 	REQ_OP_NAME(ZONE_RESET),
 	REQ_OP_NAME(ZONE_RESET_ALL),
+	REQ_OP_NAME(ZONE_OPEN),
+	REQ_OP_NAME(ZONE_CLOSE),
+	REQ_OP_NAME(ZONE_FINISH),
 	REQ_OP_NAME(WRITE_SAME),
 	REQ_OP_NAME(WRITE_ZEROES),
 	REQ_OP_NAME(SCSI_IN),
@@ -336,14 +339,14 @@ EXPORT_SYMBOL_GPL(blk_set_queue_dying);
  */
 void blk_cleanup_queue(struct request_queue *q)
 {
+	WARN_ON_ONCE(blk_queue_registered(q));
+
 	/* mark @q DYING, no new request or merges will be allowed afterwards */
-	mutex_lock(&q->sysfs_lock);
 	blk_set_queue_dying(q);
 
 	blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q);
 	blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
 	blk_queue_flag_set(QUEUE_FLAG_DYING, q);
-	mutex_unlock(&q->sysfs_lock);
 
 	/*
 	 * Drain all requests queued before DYING marking. Set DEAD flag to
@@ -849,10 +852,10 @@ static inline int blk_partition_remap(struct bio *bio)
 		goto out;
 
 	/*
-	 * Zone reset does not include bi_size so bio_sectors() is always 0.
-	 * Include a test for the reset op code and perform the remap if needed.
+	 * Zone management bios do not have a sector count but they do have
+	 * a start sector filled out and need to be remapped.
 	 */
-	if (bio_sectors(bio) || bio_op(bio) == REQ_OP_ZONE_RESET) {
+	if (bio_sectors(bio) || op_is_zone_mgmt(bio_op(bio))) {
 		if (bio_check_eod(bio, part_nr_sects_read(p)))
 			goto out;
 		bio->bi_iter.bi_sector += p->start_sect;
@@ -936,6 +939,9 @@ generic_make_request_checks(struct bio *bio)
 			goto not_supported;
 		break;
 	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_OPEN:
+	case REQ_OP_ZONE_CLOSE:
+	case REQ_OP_ZONE_FINISH:
 		if (!blk_queue_is_zoned(q))
 			goto not_supported;
 		break;

block/blk-exec.c

@@ -55,6 +55,8 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk,
 	rq->rq_disk = bd_disk;
 	rq->end_io = done;
 
+	blk_account_io_start(rq, true);
+
 	/*
 	 * don't check dying flag for MQ because the request won't
 	 * be reused after dying flag is set

block/blk-merge.c

@@ -293,7 +293,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q,
 void __blk_queue_split(struct request_queue *q, struct bio **bio,
 		unsigned int *nr_segs)
 {
-	struct bio *split;
+	struct bio *split = NULL;
 
 	switch (bio_op(*bio)) {
 	case REQ_OP_DISCARD:
@@ -309,6 +309,20 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio,
 				nr_segs);
 		break;
 	default:
+		/*
+		 * All drivers must accept single-segments bios that are <=
+		 * PAGE_SIZE.  This is a quick and dirty check that relies on
+		 * the fact that bi_io_vec[0] is always valid if a bio has data.
+		 * The check might lead to occasional false negatives when bios
+		 * are cloned, but compared to the performance impact of cloned
+		 * bios themselves the loop below doesn't matter anyway.
+		 */
+		if (!q->limits.chunk_sectors &&
+		    (*bio)->bi_vcnt == 1 &&
+		    (*bio)->bi_io_vec[0].bv_len <= PAGE_SIZE) {
+			*nr_segs = 1;
+			break;
+		}
 		split = blk_bio_segment_split(q, *bio, &q->bio_split, nr_segs);
 		break;
 	}

block/blk-mq-sysfs.c

@@ -74,10 +74,8 @@ static ssize_t blk_mq_sysfs_show(struct kobject *kobj, struct attribute *attr,
 	if (!entry->show)
 		return -EIO;
 
-	res = -ENOENT;
 	mutex_lock(&q->sysfs_lock);
-	if (!blk_queue_dying(q))
-		res = entry->show(ctx, page);
+	res = entry->show(ctx, page);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -97,10 +95,8 @@ static ssize_t blk_mq_sysfs_store(struct kobject *kobj, struct attribute *attr,
 	if (!entry->store)
 		return -EIO;
 
-	res = -ENOENT;
 	mutex_lock(&q->sysfs_lock);
-	if (!blk_queue_dying(q))
-		res = entry->store(ctx, page, length);
+	res = entry->store(ctx, page, length);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -120,10 +116,8 @@ static ssize_t blk_mq_hw_sysfs_show(struct kobject *kobj,
 	if (!entry->show)
 		return -EIO;
 
-	res = -ENOENT;
 	mutex_lock(&q->sysfs_lock);
-	if (!blk_queue_dying(q))
-		res = entry->show(hctx, page);
+	res = entry->show(hctx, page);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -144,10 +138,8 @@ static ssize_t blk_mq_hw_sysfs_store(struct kobject *kobj,
 	if (!entry->store)
 		return -EIO;
 
-	res = -ENOENT;
 	mutex_lock(&q->sysfs_lock);
-	if (!blk_queue_dying(q))
-		res = entry->store(hctx, page, length);
+	res = entry->store(hctx, page, length);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
 }
@@ -166,20 +158,25 @@ static ssize_t blk_mq_hw_sysfs_nr_reserved_tags_show(struct blk_mq_hw_ctx *hctx,
 
 static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page)
 {
+	const size_t size = PAGE_SIZE - 1;
 	unsigned int i, first = 1;
-	ssize_t ret = 0;
+	int ret = 0, pos = 0;
 
 	for_each_cpu(i, hctx->cpumask) {
 		if (first)
-			ret += sprintf(ret + page, "%u", i);
+			ret = snprintf(pos + page, size - pos, "%u", i);
 		else
-			ret += sprintf(ret + page, ", %u", i);
+			ret = snprintf(pos + page, size - pos, ", %u", i);
+
+		if (ret >= size - pos)
+			break;
 
 		first = 0;
+		pos += ret;
 	}
 
-	ret += sprintf(ret + page, "\n");
-	return ret;
+	ret = snprintf(pos + page, size + 1 - pos, "\n");
+	return pos + ret;
 }
 
 static struct blk_mq_hw_ctx_sysfs_entry blk_mq_hw_sysfs_nr_tags = {

block/blk-mq.c

@@ -93,7 +93,7 @@ static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
 
 struct mq_inflight {
 	struct hd_struct *part;
-	unsigned int *inflight;
+	unsigned int inflight[2];
 };
 
 static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
@@ -102,45 +102,29 @@ static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
 {
 	struct mq_inflight *mi = priv;
 
-	/*
-	 * index[0] counts the specific partition that was asked for.
-	 */
 	if (rq->part == mi->part)
-		mi->inflight[0]++;
+		mi->inflight[rq_data_dir(rq)]++;
 
 	return true;
 }
 
 unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part)
 {
-	unsigned inflight[2];
-	struct mq_inflight mi = { .part = part, .inflight = inflight, };
+	struct mq_inflight mi = { .part = part };
 
-	inflight[0] = inflight[1] = 0;
 	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
 
-	return inflight[0];
-}
-
-static bool blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx,
-				     struct request *rq, void *priv,
-				     bool reserved)
-{
-	struct mq_inflight *mi = priv;
-
-	if (rq->part == mi->part)
-		mi->inflight[rq_data_dir(rq)]++;
-
-	return true;
+	return mi.inflight[0] + mi.inflight[1];
 }
 
 void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
 			 unsigned int inflight[2])
 {
-	struct mq_inflight mi = { .part = part, .inflight = inflight, };
+	struct mq_inflight mi = { .part = part };
 
-	inflight[0] = inflight[1] = 0;
-	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi);
+	blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
+	inflight[0] = mi.inflight[0];
+	inflight[1] = mi.inflight[1];
 }
 
 void blk_freeze_queue_start(struct request_queue *q)
@@ -663,18 +647,6 @@ bool blk_mq_complete_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
-int blk_mq_request_started(struct request *rq)
-{
-	return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
-}
-EXPORT_SYMBOL_GPL(blk_mq_request_started);
-
-int blk_mq_request_completed(struct request *rq)
-{
-	return blk_mq_rq_state(rq) == MQ_RQ_COMPLETE;
-}
-EXPORT_SYMBOL_GPL(blk_mq_request_completed);
-
 void blk_mq_start_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
@@ -1064,7 +1036,7 @@ bool blk_mq_get_driver_tag(struct request *rq)
 	bool shared;
 
 	if (rq->tag != -1)
-		goto done;
+		return true;
 
 	if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
 		data.flags |= BLK_MQ_REQ_RESERVED;
@@ -1079,7 +1051,6 @@ bool blk_mq_get_driver_tag(struct request *rq)
 		data.hctx->tags->rqs[rq->tag] = rq;
 	}
 
-done:
 	return rq->tag != -1;
 }
 
@@ -1486,7 +1457,7 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
 }
 EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
 
-bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
+void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 {
 	int srcu_idx;
 	bool need_run;
@@ -1504,12 +1475,8 @@ bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 		blk_mq_hctx_has_pending(hctx);
 	hctx_unlock(hctx, srcu_idx);
 
-	if (need_run) {
+	if (need_run)
 		__blk_mq_delay_run_hw_queue(hctx, async, 0);
-		return true;
-	}
-
-	return false;
 }
 EXPORT_SYMBOL(blk_mq_run_hw_queue);
 
@@ -2789,6 +2756,23 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	int i, j, end;
 	struct blk_mq_hw_ctx **hctxs = q->queue_hw_ctx;
 
+	if (q->nr_hw_queues < set->nr_hw_queues) {
+		struct blk_mq_hw_ctx **new_hctxs;
+
+		new_hctxs = kcalloc_node(set->nr_hw_queues,
+				       sizeof(*new_hctxs), GFP_KERNEL,
+				       set->numa_node);
+		if (!new_hctxs)
+			return;
+		if (hctxs)
+			memcpy(new_hctxs, hctxs, q->nr_hw_queues *
+			       sizeof(*hctxs));
+		q->queue_hw_ctx = new_hctxs;
+		q->nr_hw_queues = set->nr_hw_queues;
+		kfree(hctxs);
+		hctxs = new_hctxs;
+	}
+
 	/* protect against switching io scheduler  */
 	mutex_lock(&q->sysfs_lock);
 	for (i = 0; i < set->nr_hw_queues; i++) {
@@ -2844,19 +2828,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	mutex_unlock(&q->sysfs_lock);
 }
 
-/*
- * Maximum number of hardware queues we support. For single sets, we'll never
- * have more than the CPUs (software queues). For multiple sets, the tag_set
- * user may have set ->nr_hw_queues larger.
- */
-static unsigned int nr_hw_queues(struct blk_mq_tag_set *set)
-{
-	if (set->nr_maps == 1)
-		return nr_cpu_ids;
-
-	return max(set->nr_hw_queues, nr_cpu_ids);
-}
-
 struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 						  struct request_queue *q,
 						  bool elevator_init)
@@ -2876,12 +2847,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	/* init q->mq_kobj and sw queues' kobjects */
 	blk_mq_sysfs_init(q);
 
-	q->nr_queues = nr_hw_queues(set);
-	q->queue_hw_ctx = kcalloc_node(q->nr_queues, sizeof(*(q->queue_hw_ctx)),
-						GFP_KERNEL, set->numa_node);
-	if (!q->queue_hw_ctx)
-		goto err_sys_init;
-
 	INIT_LIST_HEAD(&q->unused_hctx_list);
 	spin_lock_init(&q->unused_hctx_lock);
 
@@ -2929,7 +2894,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 err_hctxs:
 	kfree(q->queue_hw_ctx);
 	q->nr_hw_queues = 0;
-err_sys_init:
 	blk_mq_sysfs_deinit(q);
 err_poll:
 	blk_stat_free_callback(q->poll_cb);
@@ -3030,6 +2994,29 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 	}
 }
 
+static int blk_mq_realloc_tag_set_tags(struct blk_mq_tag_set *set,
+				  int cur_nr_hw_queues, int new_nr_hw_queues)
+{
+	struct blk_mq_tags **new_tags;
+
+	if (cur_nr_hw_queues >= new_nr_hw_queues)
+		return 0;
+
+	new_tags = kcalloc_node(new_nr_hw_queues, sizeof(struct blk_mq_tags *),
+				GFP_KERNEL, set->numa_node);
+	if (!new_tags)
+		return -ENOMEM;
+
+	if (set->tags)
+		memcpy(new_tags, set->tags, cur_nr_hw_queues *
+		       sizeof(*set->tags));
+	kfree(set->tags);
+	set->tags = new_tags;
+	set->nr_hw_queues = new_nr_hw_queues;
+
+	return 0;
+}
+
 /*
  * Alloc a tag set to be associated with one or more request queues.
  * May fail with EINVAL for various error conditions. May adjust the
@@ -3083,9 +3070,7 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
 	if (set->nr_maps == 1 && set->nr_hw_queues > nr_cpu_ids)
 		set->nr_hw_queues = nr_cpu_ids;
 
-	set->tags = kcalloc_node(nr_hw_queues(set), sizeof(struct blk_mq_tags *),
-				 GFP_KERNEL, set->numa_node);
-	if (!set->tags)
+	if (blk_mq_realloc_tag_set_tags(set, 0, set->nr_hw_queues) < 0)
 		return -ENOMEM;
 
 	ret = -ENOMEM;
@@ -3126,7 +3111,7 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 {
 	int i, j;
 
-	for (i = 0; i < nr_hw_queues(set); i++)
+	for (i = 0; i < set->nr_hw_queues; i++)
 		blk_mq_free_map_and_requests(set, i);
 
 	for (j = 0; j < set->nr_maps; j++) {
@@ -3270,10 +3255,6 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 
 	list_for_each_entry(q, &set->tag_list, tag_set_list)
 		blk_mq_freeze_queue(q);
-	/*
-	 * Sync with blk_mq_queue_tag_busy_iter.
-	 */
-	synchronize_rcu();
 	/*
 	 * Switch IO scheduler to 'none', cleaning up the data associated
 	 * with the previous scheduler. We will switch back once we are done
@@ -3288,6 +3269,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		blk_mq_sysfs_unregister(q);
 	}
 
+	if (blk_mq_realloc_tag_set_tags(set, set->nr_hw_queues, nr_hw_queues) <
+	    0)
+		goto reregister;
+
 	prev_nr_hw_queues = set->nr_hw_queues;
 	set->nr_hw_queues = nr_hw_queues;
 	blk_mq_update_queue_map(set);
@@ -3304,6 +3289,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 		blk_mq_map_swqueue(q);
 	}
 
+reregister:
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
 		blk_mq_sysfs_register(q);
 		blk_mq_debugfs_register_hctxs(q);

block/blk-mq.h

@@ -128,15 +128,6 @@ extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
 
 void blk_mq_release(struct request_queue *q);
 
-/**
- * blk_mq_rq_state() - read the current MQ_RQ_* state of a request
- * @rq: target request.
- */
-static inline enum mq_rq_state blk_mq_rq_state(struct request *rq)
-{
-	return READ_ONCE(rq->state);
-}
-
 static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
 					   unsigned int cpu)
 {

block/blk-stat.c

@@ -53,7 +53,7 @@ void blk_stat_add(struct request *rq, u64 now)
 	struct request_queue *q = rq->q;
 	struct blk_stat_callback *cb;
 	struct blk_rq_stat *stat;
-	int bucket;
+	int bucket, cpu;
 	u64 value;
 
 	value = (now >= rq->io_start_time_ns) ? now - rq->io_start_time_ns : 0;
@@ -61,6 +61,7 @@ void blk_stat_add(struct request *rq, u64 now)
 	blk_throtl_stat_add(rq, value);
 
 	rcu_read_lock();
+	cpu = get_cpu();
 	list_for_each_entry_rcu(cb, &q->stats->callbacks, list) {
 		if (!blk_stat_is_active(cb))
 			continue;
@@ -69,10 +70,10 @@ void blk_stat_add(struct request *rq, u64 now)
 		if (bucket < 0)
 			continue;
 
-		stat = &get_cpu_ptr(cb->cpu_stat)[bucket];
+		stat = &per_cpu_ptr(cb->cpu_stat, cpu)[bucket];
 		blk_rq_stat_add(stat, value);
-		put_cpu_ptr(cb->cpu_stat);
 	}
+	put_cpu();
 	rcu_read_unlock();
 }
 

block/blk-sysfs.c

@@ -801,10 +801,6 @@ queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 	if (!entry->show)
 		return -EIO;
 	mutex_lock(&q->sysfs_lock);
-	if (blk_queue_dying(q)) {
-		mutex_unlock(&q->sysfs_lock);
-		return -ENOENT;
-	}
 	res = entry->show(q, page);
 	mutex_unlock(&q->sysfs_lock);
 	return res;
@@ -823,10 +819,6 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,
 
 	q = container_of(kobj, struct request_queue, kobj);
 	mutex_lock(&q->sysfs_lock);
-	if (blk_queue_dying(q)) {
-		mutex_unlock(&q->sysfs_lock);
-		return -ENOENT;
-	}
 	res = entry->store(q, page, length);
 	mutex_unlock(&q->sysfs_lock);
 	return res;

block/blk-zoned.c

@@ -202,32 +202,14 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(blkdev_report_zones);
 
-/*
- * Special case of zone reset operation to reset all zones in one command,
- * useful for applications like mkfs.
- */
-static int __blkdev_reset_all_zones(struct block_device *bdev, gfp_t gfp_mask)
-{
-	struct bio *bio = bio_alloc(gfp_mask, 0);
-	int ret;
-
-	/* across the zones operations, don't need any sectors */
-	bio_set_dev(bio, bdev);
-	bio_set_op_attrs(bio, REQ_OP_ZONE_RESET_ALL, 0);
-
-	ret = submit_bio_wait(bio);
-	bio_put(bio);
-
-	return ret;
-}
-
 static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev,
+						sector_t sector,
 						sector_t nr_sectors)
 {
 	if (!blk_queue_zone_resetall(bdev_get_queue(bdev)))
 		return false;
 
-	if (nr_sectors != part_nr_sects_read(bdev->bd_part))
+	if (sector || nr_sectors != part_nr_sects_read(bdev->bd_part))
 		return false;
 	/*
 	 * REQ_OP_ZONE_RESET_ALL can be executed only if the block device is
@@ -239,26 +221,29 @@ static inline bool blkdev_allow_reset_all_zones(struct block_device *bdev,
 }
 
 /**
- * blkdev_reset_zones - Reset zones write pointer
+ * blkdev_zone_mgmt - Execute a zone management operation on a range of zones
  * @bdev:	Target block device
- * @sector:	Start sector of the first zone to reset
- * @nr_sectors:	Number of sectors, at least the length of one zone
+ * @op:		Operation to be performed on the zones
+ * @sector:	Start sector of the first zone to operate on
+ * @nr_sectors:	Number of sectors, should be at least the length of one zone and
+ *		must be zone size aligned.
  * @gfp_mask:	Memory allocation flags (for bio_alloc)
  *
  * Description:
- *    Reset the write pointer of the zones contained in the range
+ *    Perform the specified operation on the range of zones specified by
  *    @sector..@sector+@nr_sectors. Specifying the entire disk sector range
  *    is valid, but the specified range should not contain conventional zones.
+ *    The operation to execute on each zone can be a zone reset, open, close
+ *    or finish request.
  */
-int blkdev_reset_zones(struct block_device *bdev,
-		       sector_t sector, sector_t nr_sectors,
-		       gfp_t gfp_mask)
+int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
+		     sector_t sector, sector_t nr_sectors,
+		     gfp_t gfp_mask)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
-	sector_t zone_sectors;
+	sector_t zone_sectors = blk_queue_zone_sectors(q);
 	sector_t end_sector = sector + nr_sectors;
 	struct bio *bio = NULL;
-	struct blk_plug plug;
 	int ret;
 
 	if (!blk_queue_is_zoned(q))
@@ -267,15 +252,14 @@ int blkdev_reset_zones(struct block_device *bdev,
 	if (bdev_read_only(bdev))
 		return -EPERM;
 
+	if (!op_is_zone_mgmt(op))
+		return -EOPNOTSUPP;
+
 	if (!nr_sectors || end_sector > bdev->bd_part->nr_sects)
 		/* Out of range */
 		return -EINVAL;
 
-	if (blkdev_allow_reset_all_zones(bdev, nr_sectors))
-		return  __blkdev_reset_all_zones(bdev, gfp_mask);
-
 	/* Check alignment (handle eventual smaller last zone) */
-	zone_sectors = blk_queue_zone_sectors(q);
 	if (sector & (zone_sectors - 1))
 		return -EINVAL;
 
@@ -283,29 +267,34 @@ int blkdev_reset_zones(struct block_device *bdev,
 	    end_sector != bdev->bd_part->nr_sects)
 		return -EINVAL;
 
-	blk_start_plug(&plug);
 	while (sector < end_sector) {
-
 		bio = blk_next_bio(bio, 0, gfp_mask);
-		bio->bi_iter.bi_sector = sector;
 		bio_set_dev(bio, bdev);
-		bio_set_op_attrs(bio, REQ_OP_ZONE_RESET, 0);
 
+		/*
+		 * Special case for the zone reset operation that reset all
+		 * zones, this is useful for applications like mkfs.
+		 */
+		if (op == REQ_OP_ZONE_RESET &&
+		    blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) {
+			bio->bi_opf = REQ_OP_ZONE_RESET_ALL;
+			break;
+		}
+
+		bio->bi_opf = op;
+		bio->bi_iter.bi_sector = sector;
 		sector += zone_sectors;
 
 		/* This may take a while, so be nice to others */
 		cond_resched();
-
 	}
 
 	ret = submit_bio_wait(bio);
 	bio_put(bio);
 
-	blk_finish_plug(&plug);
-
 	return ret;
 }
-EXPORT_SYMBOL_GPL(blkdev_reset_zones);
+EXPORT_SYMBOL_GPL(blkdev_zone_mgmt);
 
 /*
  * BLKREPORTZONE ioctl processing.
@@ -368,15 +357,16 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 }
 
 /*
- * BLKRESETZONE ioctl processing.
+ * BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing.
  * Called from blkdev_ioctl.
  */
-int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
-			     unsigned int cmd, unsigned long arg)
+int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
+			   unsigned int cmd, unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
 	struct request_queue *q;
 	struct blk_zone_range zrange;
+	enum req_opf op;
 
 	if (!argp)
 		return -EINVAL;
@@ -397,8 +387,25 @@ int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
 	if (copy_from_user(&zrange, argp, sizeof(struct blk_zone_range)))
 		return -EFAULT;
 
-	return blkdev_reset_zones(bdev, zrange.sector, zrange.nr_sectors,
-				  GFP_KERNEL);
+	switch (cmd) {
+	case BLKRESETZONE:
+		op = REQ_OP_ZONE_RESET;
+		break;
+	case BLKOPENZONE:
+		op = REQ_OP_ZONE_OPEN;
+		break;
+	case BLKCLOSEZONE:
+		op = REQ_OP_ZONE_CLOSE;
+		break;
+	case BLKFINISHZONE:
+		op = REQ_OP_ZONE_FINISH;
+		break;
+	default:
+		return -ENOTTY;
+	}
+
+	return blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors,
+				GFP_KERNEL);
 }
 
 static inline unsigned long *blk_alloc_zone_bitmap(int node,

block/blk.h

@@ -242,14 +242,11 @@ int blk_dev_init(void);
  * Contribute to IO statistics IFF:
  *
  *	a) it's attached to a gendisk, and
- *	b) the queue had IO stats enabled when this request was started, and
- *	c) it's a file system request
+ *	b) the queue had IO stats enabled when this request was started
  */
 static inline bool blk_do_io_stat(struct request *rq)
 {
-	return rq->rq_disk &&
-	       (rq->rq_flags & RQF_IO_STAT) &&
-		!blk_rq_is_passthrough(rq);
+	return rq->rq_disk && (rq->rq_flags & RQF_IO_STAT);
 }
 
 static inline void req_set_nomerge(struct request_queue *q, struct request *req)

block/elevator.c

@@ -831,3 +831,12 @@ struct request *elv_rb_latter_request(struct request_queue *q,
 	return NULL;
 }
 EXPORT_SYMBOL(elv_rb_latter_request);
+
+static int __init elevator_setup(char *str)
+{
+	pr_warn("Kernel parameter elevator= does not have any effect anymore.\n"
+		"Please use sysfs to set IO scheduler for individual devices.\n");
+	return 1;
+}
+
+__setup("elevator=", elevator_setup);

block/ioctl.c

@@ -532,7 +532,10 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	case BLKREPORTZONE:
 		return blkdev_report_zones_ioctl(bdev, mode, cmd, arg);
 	case BLKRESETZONE:
-		return blkdev_reset_zones_ioctl(bdev, mode, cmd, arg);
+	case BLKOPENZONE:
+	case BLKCLOSEZONE:
+	case BLKFINISHZONE:
+		return blkdev_zone_mgmt_ioctl(bdev, mode, cmd, arg);
 	case BLKGETZONESZ:
 		return put_uint(arg, bdev_zone_sectors(bdev));
 	case BLKGETNRZONES:

block/opal_proto.h

@@ -76,7 +76,6 @@ enum opal_response_token {
  * Derived from: TCG_Storage_Architecture_Core_Spec_v2.01_r1.00
  * Section: 6.3 Assigned UIDs
  */
-#define OPAL_UID_LENGTH 8
 #define OPAL_METHOD_LENGTH 8
 #define OPAL_MSID_KEYLEN 15
 #define OPAL_UID_LENGTH_HALF 4
@@ -108,6 +107,7 @@ enum opal_uid {
 	OPAL_C_PIN_TABLE,
 	OPAL_LOCKING_INFO_TABLE,
 	OPAL_ENTERPRISE_LOCKING_INFO_TABLE,
+	OPAL_DATASTORE,
 	/* C_PIN_TABLE object ID's */
 	OPAL_C_PIN_MSID,
 	OPAL_C_PIN_SID,

block/t10-pi.c

@@ -235,16 +235,12 @@ static blk_status_t t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
 	return t10_pi_verify(iter, t10_pi_ip_fn, T10_PI_TYPE3_PROTECTION);
 }
 
-/**
- * Type 3 does not have a reference tag so no remapping is required.
- */
+/* Type 3 does not have a reference tag so no remapping is required. */
 static void t10_pi_type3_prepare(struct request *rq)
 {
 }
 
-/**
- * Type 3 does not have a reference tag so no remapping is required.
- */
+/* Type 3 does not have a reference tag so no remapping is required. */
 static void t10_pi_type3_complete(struct request *rq, unsigned int nr_bytes)
 {
 }

drivers/md/dm-zoned-metadata.c

@@ -1312,9 +1312,9 @@ static int dmz_reset_zone(struct dmz_metadata *zmd, struct dm_zone *zone)
 	if (!dmz_is_empty(zone) || dmz_seq_write_err(zone)) {
 		struct dmz_dev *dev = zmd->dev;
 
-		ret = blkdev_reset_zones(dev->bdev,
-					 dmz_start_sect(zmd, zone),
-					 dev->zone_nr_sectors, GFP_NOIO);
+		ret = blkdev_zone_mgmt(dev->bdev, REQ_OP_ZONE_RESET,
+				       dmz_start_sect(zmd, zone),
+				       dev->zone_nr_sectors, GFP_NOIO);
 		if (ret) {
 			dmz_dev_err(dev, "Reset zone %u failed %d",
 				    dmz_id(zmd, zone), ret);

fs/block_dev.c

@@ -1403,11 +1403,7 @@ static void flush_disk(struct block_device *bdev, bool kill_dirty)
 		       "resized disk %s\n",
 		       bdev->bd_disk ? bdev->bd_disk->disk_name : "");
 	}
-
-	if (!bdev->bd_disk)
-		return;
-	if (disk_part_scan_enabled(bdev->bd_disk))
-		bdev->bd_invalidated = 1;
+	bdev->bd_invalidated = 1;
 }
 
 /**
@@ -1512,6 +1508,19 @@ EXPORT_SYMBOL(bd_set_size);
 
 static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
+static void bdev_disk_changed(struct block_device *bdev, bool invalidate)
+{
+	if (disk_part_scan_enabled(bdev->bd_disk)) {
+		if (invalidate)
+			invalidate_partitions(bdev->bd_disk, bdev);
+		else
+			rescan_partitions(bdev->bd_disk, bdev);
+	} else {
+		check_disk_size_change(bdev->bd_disk, bdev, !invalidate);
+		bdev->bd_invalidated = 0;
+	}
+}
+
 /*
  * bd_mutex locking:
  *
@@ -1594,12 +1603,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			 * The latter is necessary to prevent ghost
 			 * partitions on a removed medium.
 			 */
-			if (bdev->bd_invalidated) {
-				if (!ret)
-					rescan_partitions(disk, bdev);
-				else if (ret == -ENOMEDIUM)
-					invalidate_partitions(disk, bdev);
-			}
+			if (bdev->bd_invalidated &&
+			    (!ret || ret == -ENOMEDIUM))
+				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 
 			if (ret)
 				goto out_clear;
@@ -1632,12 +1638,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			if (bdev->bd_disk->fops->open)
 				ret = bdev->bd_disk->fops->open(bdev, mode);
 			/* the same as first opener case, read comment there */
-			if (bdev->bd_invalidated) {
-				if (!ret)
-					rescan_partitions(bdev->bd_disk, bdev);
-				else if (ret == -ENOMEDIUM)
-					invalidate_partitions(bdev->bd_disk, bdev);
-			}
+			if (bdev->bd_invalidated &&
+			    (!ret || ret == -ENOMEDIUM))
+				bdev_disk_changed(bdev, ret == -ENOMEDIUM);
 			if (ret)
 				goto out_unlock_bdev;
 		}

fs/f2fs/segment.c

@@ -1771,7 +1771,8 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
 			return -EIO;
 		}
 		trace_f2fs_issue_reset_zone(bdev, blkstart);
-		return blkdev_reset_zones(bdev, sector, nr_sects, GFP_NOFS);
+		return blkdev_zone_mgmt(bdev, REQ_OP_ZONE_RESET,
+					sector, nr_sects, GFP_NOFS);
 	}
 
 	/* For conventional zones, use regular discard if supported */

fs/fcntl.c

@@ -261,7 +261,7 @@ static int f_getowner_uids(struct file *filp, unsigned long arg)
 static bool rw_hint_valid(enum rw_hint hint)
 {
 	switch (hint) {
-	case RWF_WRITE_LIFE_NOT_SET:
+	case RWH_WRITE_LIFE_NOT_SET:
 	case RWH_WRITE_LIFE_NONE:
 	case RWH_WRITE_LIFE_SHORT:
 	case RWH_WRITE_LIFE_MEDIUM:

include/linux/blk_types.h

@@ -153,10 +153,10 @@ struct bio {
 	unsigned short		bi_write_hint;
 	blk_status_t		bi_status;
 	u8			bi_partno;
+	atomic_t		__bi_remaining;
 
 	struct bvec_iter	bi_iter;
 
-	atomic_t		__bi_remaining;
 	bio_end_io_t		*bi_end_io;
 
 	void			*bi_private;
@@ -290,6 +290,12 @@ enum req_opf {
 	REQ_OP_ZONE_RESET_ALL	= 8,
 	/* write the zero filled sector many times */
 	REQ_OP_WRITE_ZEROES	= 9,
+	/* Open a zone */
+	REQ_OP_ZONE_OPEN	= 10,
+	/* Close a zone */
+	REQ_OP_ZONE_CLOSE	= 11,
+	/* Transition a zone to full */
+	REQ_OP_ZONE_FINISH	= 12,
 
 	/* SCSI passthrough using struct scsi_request */
 	REQ_OP_SCSI_IN		= 32,
@@ -417,6 +423,25 @@ static inline bool op_is_discard(unsigned int op)
 	return (op & REQ_OP_MASK) == REQ_OP_DISCARD;
 }
 
+/*
+ * Check if a bio or request operation is a zone management operation, with
+ * the exception of REQ_OP_ZONE_RESET_ALL which is treated as a special case
+ * due to its different handling in the block layer and device response in
+ * case of command failure.
+ */
+static inline bool op_is_zone_mgmt(enum req_opf op)
+{
+	switch (op & REQ_OP_MASK) {
+	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_OPEN:
+	case REQ_OP_ZONE_CLOSE:
+	case REQ_OP_ZONE_FINISH:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static inline int op_stat_group(unsigned int op)
 {
 	if (op_is_discard(op))

include/linux/blkdev.h

@@ -360,14 +360,15 @@ extern unsigned int blkdev_nr_zones(struct block_device *bdev);
 extern int blkdev_report_zones(struct block_device *bdev,
 			       sector_t sector, struct blk_zone *zones,
 			       unsigned int *nr_zones);
-extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors,
-			      sector_t nr_sectors, gfp_t gfp_mask);
+extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op,
+			    sector_t sectors, sector_t nr_sectors,
+			    gfp_t gfp_mask);
 extern int blk_revalidate_disk_zones(struct gendisk *disk);
 
 extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
 				     unsigned int cmd, unsigned long arg);
-extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode,
-				    unsigned int cmd, unsigned long arg);
+extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
+				  unsigned int cmd, unsigned long arg);
 
 #else /* CONFIG_BLK_DEV_ZONED */
 
@@ -388,9 +389,9 @@ static inline int blkdev_report_zones_ioctl(struct block_device *bdev,
 	return -ENOTTY;
 }
 
-static inline int blkdev_reset_zones_ioctl(struct block_device *bdev,
-					   fmode_t mode, unsigned int cmd,
-					   unsigned long arg)
+static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev,
+					 fmode_t mode, unsigned int cmd,
+					 unsigned long arg)
 {
 	return -ENOTTY;
 }
@@ -411,7 +412,6 @@ struct request_queue {
 
 	/* sw queues */
 	struct blk_mq_ctx __percpu	*queue_ctx;
-	unsigned int		nr_queues;
 
 	unsigned int		queue_depth;
 

include/linux/sed-opal.h

@@ -42,6 +42,7 @@ static inline bool is_sed_ioctl(unsigned int cmd)
 	case IOC_OPAL_PSID_REVERT_TPR:
 	case IOC_OPAL_MBR_DONE:
 	case IOC_OPAL_WRITE_SHADOW_MBR:
+	case IOC_OPAL_GENERIC_TABLE_RW:
 		return true;
 	}
 	return false;

include/trace/events/wbt.h

@@ -33,7 +33,8 @@ TRACE_EVENT(wbt_stat,
 	),
 
 	TP_fast_assign(
-		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		strlcpy(__entry->name, dev_name(bdi->dev),
+			ARRAY_SIZE(__entry->name));
 		__entry->rmean		= stat[0].mean;
 		__entry->rmin		= stat[0].min;
 		__entry->rmax		= stat[0].max;
@@ -67,7 +68,8 @@ TRACE_EVENT(wbt_lat,
 	),
 
 	TP_fast_assign(
-		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		strlcpy(__entry->name, dev_name(bdi->dev),
+			ARRAY_SIZE(__entry->name));
 		__entry->lat = div_u64(lat, 1000);
 	),
 
@@ -103,7 +105,8 @@ TRACE_EVENT(wbt_step,
 	),
 
 	TP_fast_assign(
-		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		strlcpy(__entry->name, dev_name(bdi->dev),
+			ARRAY_SIZE(__entry->name));
 		__entry->msg	= msg;
 		__entry->step	= step;
 		__entry->window	= div_u64(window, 1000);
@@ -138,7 +141,8 @@ TRACE_EVENT(wbt_timer,
 	),
 
 	TP_fast_assign(
-		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		strlcpy(__entry->name, dev_name(bdi->dev),
+			ARRAY_SIZE(__entry->name));
 		__entry->status		= status;
 		__entry->step		= step;
 		__entry->inflight	= inflight;

include/uapi/linux/blkzoned.h

@@ -120,9 +120,11 @@ struct blk_zone_report {
 };
 
 /**
- * struct blk_zone_range - BLKRESETZONE ioctl request
- * @sector: starting sector of the first zone to issue reset write pointer
- * @nr_sectors: Total number of sectors of 1 or more zones to reset
+ * struct blk_zone_range - BLKRESETZONE/BLKOPENZONE/
+ *                         BLKCLOSEZONE/BLKFINISHZONE ioctl
+ *                         requests
+ * @sector: Starting sector of the first zone to operate on.
+ * @nr_sectors: Total number of sectors of all zones to operate on.
  */
 struct blk_zone_range {
 	__u64		sector;
@@ -139,10 +141,19 @@ struct blk_zone_range {
  *                sector range. The sector range must be zone aligned.
  * @BLKGETZONESZ: Get the device zone size in number of 512 B sectors.
  * @BLKGETNRZONES: Get the total number of zones of the device.
+ * @BLKOPENZONE: Open the zones in the specified sector range.
+ *               The 512 B sector range must be zone aligned.
+ * @BLKCLOSEZONE: Close the zones in the specified sector range.
+ *                The 512 B sector range must be zone aligned.
+ * @BLKFINISHZONE: Mark the zones as full in the specified sector range.
+ *                 The 512 B sector range must be zone aligned.
  */
 #define BLKREPORTZONE	_IOWR(0x12, 130, struct blk_zone_report)
 #define BLKRESETZONE	_IOW(0x12, 131, struct blk_zone_range)
 #define BLKGETZONESZ	_IOR(0x12, 132, __u32)
 #define BLKGETNRZONES	_IOR(0x12, 133, __u32)
+#define BLKOPENZONE	_IOW(0x12, 134, struct blk_zone_range)
+#define BLKCLOSEZONE	_IOW(0x12, 135, struct blk_zone_range)
+#define BLKFINISHZONE	_IOW(0x12, 136, struct blk_zone_range)
 
 #endif /* _UAPI_BLKZONED_H */

include/uapi/linux/fcntl.h

@@ -58,13 +58,20 @@
  * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
  * used to clear any hints previously set.
  */
-#define RWF_WRITE_LIFE_NOT_SET	0
+#define RWH_WRITE_LIFE_NOT_SET	0
 #define RWH_WRITE_LIFE_NONE	1
 #define RWH_WRITE_LIFE_SHORT	2
 #define RWH_WRITE_LIFE_MEDIUM	3
 #define RWH_WRITE_LIFE_LONG	4
 #define RWH_WRITE_LIFE_EXTREME	5
 
+/*
+ * The originally introduced spelling is remained from the first
+ * versions of the patch set that introduced the feature, see commit
+ * v4.13-rc1~212^2~51.
+ */
+#define RWF_WRITE_LIFE_NOT_SET	RWH_WRITE_LIFE_NOT_SET
+
 /*
  * Types of directory notifications that may be requested.
  */

include/uapi/linux/sed-opal.h

@@ -113,6 +113,25 @@ struct opal_shadow_mbr {
 	__u64 size;
 };
 
+/* Opal table operations */
+enum opal_table_ops {
+	OPAL_READ_TABLE,
+	OPAL_WRITE_TABLE,
+};
+
+#define OPAL_UID_LENGTH 8
+struct opal_read_write_table {
+	struct opal_key key;
+	const __u64 data;
+	const __u8 table_uid[OPAL_UID_LENGTH];
+	__u64 offset;
+	__u64 size;
+#define OPAL_TABLE_READ (1 << OPAL_READ_TABLE)
+#define OPAL_TABLE_WRITE (1 << OPAL_WRITE_TABLE)
+	__u64 flags;
+	__u64 priv;
+};
+
 #define IOC_OPAL_SAVE		    _IOW('p', 220, struct opal_lock_unlock)
 #define IOC_OPAL_LOCK_UNLOCK	    _IOW('p', 221, struct opal_lock_unlock)
 #define IOC_OPAL_TAKE_OWNERSHIP	    _IOW('p', 222, struct opal_key)
@@ -128,5 +147,6 @@ struct opal_shadow_mbr {
 #define IOC_OPAL_PSID_REVERT_TPR    _IOW('p', 232, struct opal_key)
 #define IOC_OPAL_MBR_DONE           _IOW('p', 233, struct opal_mbr_done)
 #define IOC_OPAL_WRITE_SHADOW_MBR   _IOW('p', 234, struct opal_shadow_mbr)
+#define IOC_OPAL_GENERIC_TABLE_RW   _IOW('p', 235, struct opal_read_write_table)
 
 #endif /* _UAPI_SED_OPAL_H */

tools/include/uapi/linux/fcntl.h

@@ -58,13 +58,20 @@
  * Valid hint values for F_{GET,SET}_RW_HINT. 0 is "not set", or can be
  * used to clear any hints previously set.
  */
-#define RWF_WRITE_LIFE_NOT_SET	0
+#define RWH_WRITE_LIFE_NOT_SET	0
 #define RWH_WRITE_LIFE_NONE	1
 #define RWH_WRITE_LIFE_SHORT	2
 #define RWH_WRITE_LIFE_MEDIUM	3
 #define RWH_WRITE_LIFE_LONG	4
 #define RWH_WRITE_LIFE_EXTREME	5
 
+/*
+ * The originally introduced spelling is remained from the first
+ * versions of the patch set that introduced the feature, see commit
+ * v4.13-rc1~212^2~51.
+ */
+#define RWF_WRITE_LIFE_NOT_SET	RWH_WRITE_LIFE_NOT_SET
+
 /*
  * Types of directory notifications that may be requested.
  */