15 files changed, 423 insertions, 238 deletions

diff --git a/block/blk-core.c b/block/blk-core.c
index d5e668ec751b..f0d82227a2fc 100644
--- a/block/blk-core.c
+++ b/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;
diff --git a/block/blk-exec.c b/block/blk-exec.c
index 1db44ca0f4a6..e20a852ae432 100644
--- a/block/blk-exec.c
+++ b/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
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 48e6725b32ee..f22cb6251d06 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -293,7 +293,7 @@ split:
 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;
 	}
diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c
index a0d3ce30fa08..062229395a50 100644
--- a/block/blk-mq-sysfs.c
+++ b/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 = {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ec791156e9cc..5c9adcaa27ac 100644
--- a/block/blk-mq.c
+++ b/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++) {
@@ -3271,10 +3256,6 @@ 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
 	 * updating the new sw to hw queue mappings.
@@ -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 @@ fallback:
 		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);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 32c62c64e6c2..eaaca8fc1c28 100644
--- a/block/blk-mq.h
+++ b/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)
 {
diff --git a/block/blk-stat.c b/block/blk-stat.c
index 940f15d600f8..7da302ff88d0 100644
--- a/block/blk-stat.c
+++ b/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();
 }
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 46f5198be017..fca9b158f4a0 100644
--- a/block/blk-sysfs.c
+++ b/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;
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 4bc5f260248a..481eaf7d04d4 100644
--- a/block/blk-zoned.c
+++ b/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,
diff --git a/block/blk.h b/block/blk.h
index 47fba9362e60..2bea40180b6f 100644
--- a/block/blk.h
+++ b/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)
diff --git a/block/elevator.c b/block/elevator.c
index 076ba7308e65..4eab3d70e880 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -832,3 +832,12 @@ 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);
diff --git a/block/ioctl.c b/block/ioctl.c
index 15a0eb80ada9..8756efb1419e 100644
--- a/block/ioctl.c
+++ b/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:
diff --git a/block/opal_proto.h b/block/opal_proto.h
index 5532412d567c..736e67c3e7c5 100644
--- a/block/opal_proto.h
+++ b/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,
diff --git a/block/sed-opal.c b/block/sed-opal.c
index b4c761973ac1..b2cacc9ddd11 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -149,6 +149,8 @@ static const u8 opaluid[][OPAL_UID_LENGTH] = {
 		{ 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x01 },
 	[OPAL_ENTERPRISE_LOCKING_INFO_TABLE] =
 		{ 0x00, 0x00, 0x08, 0x01, 0x00, 0x00, 0x00, 0x00 },
+	[OPAL_DATASTORE] =
+		{ 0x00, 0x00, 0x10, 0x01, 0x00, 0x00, 0x00, 0x00 },
 
 	/* C_PIN_TABLE object ID's */
 	[OPAL_C_PIN_MSID] =
@@ -1139,11 +1141,11 @@ static int generic_get_column(struct opal_dev *dev, const u8 *table,
  *
  * the result is provided in dev->resp->tok[4]
  */
-static int generic_get_table_info(struct opal_dev *dev, enum opal_uid table,
+static int generic_get_table_info(struct opal_dev *dev, const u8 *table_uid,
 				  u64 column)
 {
 	u8 uid[OPAL_UID_LENGTH];
-	const unsigned int half = OPAL_UID_LENGTH/2;
+	const unsigned int half = OPAL_UID_LENGTH_HALF;
 
 	/* sed-opal UIDs can be split in two halves:
 	 *  first:  actual table index
@@ -1152,7 +1154,7 @@ static int generic_get_table_info(struct opal_dev *dev, enum opal_uid table,
 	 * first part of the target table as relative index into that table
 	 */
 	memcpy(uid, opaluid[OPAL_TABLE_TABLE], half);
-	memcpy(uid+half, opaluid[table], half);
+	memcpy(uid + half, table_uid, half);
 
 	return generic_get_column(dev, uid, column);
 }
@@ -1221,6 +1223,75 @@ static int get_active_key(struct opal_dev *dev, void *data)
 	return get_active_key_cont(dev);
 }
 
+static int generic_table_write_data(struct opal_dev *dev, const u64 data,
+				    u64 offset, u64 size, const u8 *uid)
+{
+	const u8 __user *src = (u8 __user *)(uintptr_t)data;
+	u8 *dst;
+	u64 len;
+	size_t off = 0;
+	int err;
+
+	/* do we fit in the available space? */
+	err = generic_get_table_info(dev, uid, OPAL_TABLE_ROWS);
+	if (err) {
+		pr_debug("Couldn't get the table size\n");
+		return err;
+	}
+
+	len = response_get_u64(&dev->parsed, 4);
+	if (size > len || offset > len - size) {
+		pr_debug("Does not fit in the table (%llu vs. %llu)\n",
+			  offset + size, len);
+		return -ENOSPC;
+	}
+
+	/* do the actual transmission(s) */
+	while (off < size) {
+		err = cmd_start(dev, uid, opalmethod[OPAL_SET]);
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_WHERE);
+		add_token_u64(&err, dev, offset + off);
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_VALUES);
+
+		/*
+		 * The bytestring header is either 1 or 2 bytes, so assume 2.
+		 * There also needs to be enough space to accommodate the
+		 * trailing OPAL_ENDNAME (1 byte) and tokens added by
+		 * cmd_finalize.
+		 */
+		len = min(remaining_size(dev) - (2+1+CMD_FINALIZE_BYTES_NEEDED),
+			  (size_t)(size - off));
+		pr_debug("Write bytes %zu+%llu/%llu\n", off, len, size);
+
+		dst = add_bytestring_header(&err, dev, len);
+		if (!dst)
+			break;
+
+		if (copy_from_user(dst, src + off, len)) {
+			err = -EFAULT;
+			break;
+		}
+
+		dev->pos += len;
+
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+		if (err)
+			break;
+
+		err = finalize_and_send(dev, parse_and_check_status);
+		if (err)
+			break;
+
+		off += len;
+	}
+
+	return err;
+}
+
 static int generic_lr_enable_disable(struct opal_dev *dev,
 				     u8 *uid, bool rle, bool wle,
 				     bool rl, bool wl)
@@ -1583,68 +1654,9 @@ static int set_mbr_enable_disable(struct opal_dev *dev, void *data)
 static int write_shadow_mbr(struct opal_dev *dev, void *data)
 {
 	struct opal_shadow_mbr *shadow = data;
-	const u8 __user *src;
-	u8 *dst;
-	size_t off = 0;
-	u64 len;
-	int err = 0;
-
-	/* do we fit in the available shadow mbr space? */
-	err = generic_get_table_info(dev, OPAL_MBR, OPAL_TABLE_ROWS);
-	if (err) {
-		pr_debug("MBR: could not get shadow size\n");
-		return err;
-	}
-
-	len = response_get_u64(&dev->parsed, 4);
-	if (shadow->size > len || shadow->offset > len - shadow->size) {
-		pr_debug("MBR: does not fit in shadow (%llu vs. %llu)\n",
-			 shadow->offset + shadow->size, len);
-		return -ENOSPC;
-	}
-
-	/* do the actual transmission(s) */
-	src = (u8 __user *)(uintptr_t)shadow->data;
-	while (off < shadow->size) {
-		err = cmd_start(dev, opaluid[OPAL_MBR], opalmethod[OPAL_SET]);
-		add_token_u8(&err, dev, OPAL_STARTNAME);
-		add_token_u8(&err, dev, OPAL_WHERE);
-		add_token_u64(&err, dev, shadow->offset + off);
-		add_token_u8(&err, dev, OPAL_ENDNAME);
-
-		add_token_u8(&err, dev, OPAL_STARTNAME);
-		add_token_u8(&err, dev, OPAL_VALUES);
-
-		/*
-		 * The bytestring header is either 1 or 2 bytes, so assume 2.
-		 * There also needs to be enough space to accommodate the
-		 * trailing OPAL_ENDNAME (1 byte) and tokens added by
-		 * cmd_finalize.
-		 */
-		len = min(remaining_size(dev) - (2+1+CMD_FINALIZE_BYTES_NEEDED),
-			  (size_t)(shadow->size - off));
-		pr_debug("MBR: write bytes %zu+%llu/%llu\n",
-			 off, len, shadow->size);
-
-		dst = add_bytestring_header(&err, dev, len);
-		if (!dst)
-			break;
-		if (copy_from_user(dst, src + off, len))
-			err = -EFAULT;
-		dev->pos += len;
-
-		add_token_u8(&err, dev, OPAL_ENDNAME);
-		if (err)
-			break;
-
-		err = finalize_and_send(dev, parse_and_check_status);
-		if (err)
-			break;
-
-		off += len;
-	}
 
-	return err;
+	return generic_table_write_data(dev, shadow->data, shadow->offset,
+					shadow->size, opaluid[OPAL_MBR]);
 }
 
 static int generic_pw_cmd(u8 *key, size_t key_len, u8 *cpin_uid,
@@ -1957,6 +1969,113 @@ static int get_msid_cpin_pin(struct opal_dev *dev, void *data)
 	return 0;
 }
 
+static int write_table_data(struct opal_dev *dev, void *data)
+{
+	struct opal_read_write_table *write_tbl = data;
+
+	return generic_table_write_data(dev, write_tbl->data, write_tbl->offset,
+					write_tbl->size, write_tbl->table_uid);
+}
+
+static int read_table_data_cont(struct opal_dev *dev)
+{
+	int err;
+	const char *data_read;
+
+	err = parse_and_check_status(dev);
+	if (err)
+		return err;
+
+	dev->prev_d_len = response_get_string(&dev->parsed, 1, &data_read);
+	dev->prev_data = (void *)data_read;
+	if (!dev->prev_data) {
+		pr_debug("%s: Couldn't read data from the table.\n", __func__);
+		return OPAL_INVAL_PARAM;
+	}
+
+	return 0;
+}
+
+/*
+ * IO_BUFFER_LENGTH = 2048
+ * sizeof(header) = 56
+ * No. of Token Bytes in the Response = 11
+ * MAX size of data that can be carried in response buffer
+ * at a time is : 2048 - (56 + 11) = 1981 = 0x7BD.
+ */
+#define OPAL_MAX_READ_TABLE (0x7BD)
+
+static int read_table_data(struct opal_dev *dev, void *data)
+{
+	struct opal_read_write_table *read_tbl = data;
+	int err;
+	size_t off = 0, max_read_size = OPAL_MAX_READ_TABLE;
+	u64 table_len, len;
+	u64 offset = read_tbl->offset, read_size = read_tbl->size - 1;
+	u8 __user *dst;
+
+	err = generic_get_table_info(dev, read_tbl->table_uid, OPAL_TABLE_ROWS);
+	if (err) {
+		pr_debug("Couldn't get the table size\n");
+		return err;
+	}
+
+	table_len = response_get_u64(&dev->parsed, 4);
+
+	/* Check if the user is trying to read from the table limits */
+	if (read_size > table_len || offset > table_len - read_size) {
+		pr_debug("Read size exceeds the Table size limits (%llu vs. %llu)\n",
+			  offset + read_size, table_len);
+		return -EINVAL;
+	}
+
+	while (off < read_size) {
+		err = cmd_start(dev, read_tbl->table_uid, opalmethod[OPAL_GET]);
+
+		add_token_u8(&err, dev, OPAL_STARTLIST);
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_STARTROW);
+		add_token_u64(&err, dev, offset + off); /* start row value */
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+
+		add_token_u8(&err, dev, OPAL_STARTNAME);
+		add_token_u8(&err, dev, OPAL_ENDROW);
+
+		len = min(max_read_size, (size_t)(read_size - off));
+		add_token_u64(&err, dev, offset + off + len); /* end row value
+							       */
+		add_token_u8(&err, dev, OPAL_ENDNAME);
+		add_token_u8(&err, dev, OPAL_ENDLIST);
+
+		if (err) {
+			pr_debug("Error building read table data command.\n");
+			break;
+		}
+
+		err = finalize_and_send(dev, read_table_data_cont);
+		if (err)
+			break;
+
+		/* len+1: This includes the NULL terminator at the end*/
+		if (dev->prev_d_len > len + 1) {
+			err = -EOVERFLOW;
+			break;
+		}
+
+		dst = (u8 __user *)(uintptr_t)read_tbl->data;
+		if (copy_to_user(dst + off, dev->prev_data, dev->prev_d_len)) {
+			pr_debug("Error copying data to userspace\n");
+			err = -EFAULT;
+			break;
+		}
+		dev->prev_data = NULL;
+
+		off += len;
+	}
+
+	return err;
+}
+
 static int end_opal_session(struct opal_dev *dev, void *data)
 {
 	int err = 0;
@@ -2443,6 +2562,68 @@ bool opal_unlock_from_suspend(struct opal_dev *dev)
 }
 EXPORT_SYMBOL(opal_unlock_from_suspend);
 
+static int opal_read_table(struct opal_dev *dev,
+			   struct opal_read_write_table *rw_tbl)
+{
+	const struct opal_step read_table_steps[] = {
+		{ start_admin1LSP_opal_session, &rw_tbl->key },
+		{ read_table_data, rw_tbl },
+		{ end_opal_session, }
+	};
+	int ret = 0;
+
+	if (!rw_tbl->size)
+		return ret;
+
+	return execute_steps(dev, read_table_steps,
+			     ARRAY_SIZE(read_table_steps));
+}
+
+static int opal_write_table(struct opal_dev *dev,
+			    struct opal_read_write_table *rw_tbl)
+{
+	const struct opal_step write_table_steps[] = {
+		{ start_admin1LSP_opal_session, &rw_tbl->key },
+		{ write_table_data, rw_tbl },
+		{ end_opal_session, }
+	};
+	int ret = 0;
+
+	if (!rw_tbl->size)
+		return ret;
+
+	return execute_steps(dev, write_table_steps,
+			     ARRAY_SIZE(write_table_steps));
+}
+
+static int opal_generic_read_write_table(struct opal_dev *dev,
+					 struct opal_read_write_table *rw_tbl)
+{
+	int ret, bit_set;
+
+	mutex_lock(&dev->dev_lock);
+	setup_opal_dev(dev);
+
+	bit_set = fls64(rw_tbl->flags) - 1;
+	switch (bit_set) {
+	case OPAL_READ_TABLE:
+		ret = opal_read_table(dev, rw_tbl);
+		break;
+	case OPAL_WRITE_TABLE:
+		ret = opal_write_table(dev, rw_tbl);
+		break;
+	default:
+		pr_debug("Invalid bit set in the flag (%016llx).\n",
+			 rw_tbl->flags);
+		ret = -EINVAL;
+		break;
+	}
+
+	mutex_unlock(&dev->dev_lock);
+
+	return ret;
+}
+
 int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg)
 {
 	void *p;
@@ -2505,6 +2686,9 @@ int sed_ioctl(struct opal_dev *dev, unsigned int cmd, void __user *arg)
 	case IOC_OPAL_PSID_REVERT_TPR:
 		ret = opal_reverttper(dev, p, true);
 		break;
+	case IOC_OPAL_GENERIC_TABLE_RW:
+		ret = opal_generic_read_write_table(dev, p);
+		break;
 	default:
 		break;
 	}
diff --git a/block/t10-pi.c b/block/t10-pi.c
index 9803c7e0376e..f4907d941f03 100644
--- a/block/t10-pi.c
+++ b/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)
 {
 }