1 files changed, 396 insertions, 335 deletions

diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 8c8f69d8ba48..b2b9b89d6967 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -22,14 +22,18 @@
 
 struct queue_sysfs_entry {
 	struct attribute attr;
-	ssize_t (*show)(struct request_queue *, char *);
-	ssize_t (*store)(struct request_queue *, const char *, size_t);
+	ssize_t (*show)(struct gendisk *disk, char *page);
+	ssize_t (*show_limit)(struct gendisk *disk, char *page);
+
+	ssize_t (*store)(struct gendisk *disk, const char *page, size_t count);
+	int (*store_limit)(struct gendisk *disk, const char *page,
+			size_t count, struct queue_limits *lim);
 };
 
 static ssize_t
 queue_var_show(unsigned long var, char *page)
 {
-	return sprintf(page, "%lu\n", var);
+	return sysfs_emit(page, "%lu\n", var);
 }
 
 static ssize_t
@@ -47,16 +51,23 @@ queue_var_store(unsigned long *var, const char *page, size_t count)
 	return count;
 }
 
-static ssize_t queue_requests_show(struct request_queue *q, char *page)
+static ssize_t queue_requests_show(struct gendisk *disk, char *page)
 {
-	return queue_var_show(q->nr_requests, page);
+	ssize_t ret;
+
+	mutex_lock(&disk->queue->elevator_lock);
+	ret = queue_var_show(disk->queue->nr_requests, page);
+	mutex_unlock(&disk->queue->elevator_lock);
+	return ret;
 }
 
 static ssize_t
-queue_requests_store(struct request_queue *q, const char *page, size_t count)
+queue_requests_store(struct gendisk *disk, const char *page, size_t count)
 {
 	unsigned long nr;
 	int ret, err;
+	unsigned int memflags;
+	struct request_queue *q = disk->queue;
 
 	if (!queue_is_mq(q))
 		return -EINVAL;
@@ -65,307 +76,294 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count)
 	if (ret < 0)
 		return ret;
 
+	memflags = blk_mq_freeze_queue(q);
+	mutex_lock(&q->elevator_lock);
 	if (nr < BLKDEV_MIN_RQ)
 		nr = BLKDEV_MIN_RQ;
 
-	err = blk_mq_update_nr_requests(q, nr);
+	err = blk_mq_update_nr_requests(disk->queue, nr);
 	if (err)
-		return err;
-
+		ret = err;
+	mutex_unlock(&q->elevator_lock);
+	blk_mq_unfreeze_queue(q, memflags);
 	return ret;
 }
 
-static ssize_t queue_ra_show(struct request_queue *q, char *page)
+static ssize_t queue_ra_show(struct gendisk *disk, char *page)
 {
-	unsigned long ra_kb;
+	ssize_t ret;
 
-	if (!q->disk)
-		return -EINVAL;
-	ra_kb = q->disk->bdi->ra_pages << (PAGE_SHIFT - 10);
-	return queue_var_show(ra_kb, page);
+	mutex_lock(&disk->queue->limits_lock);
+	ret = queue_var_show(disk->bdi->ra_pages << (PAGE_SHIFT - 10), page);
+	mutex_unlock(&disk->queue->limits_lock);
+
+	return ret;
 }
 
 static ssize_t
-queue_ra_store(struct request_queue *q, const char *page, size_t count)
+queue_ra_store(struct gendisk *disk, const char *page, size_t count)
 {
 	unsigned long ra_kb;
 	ssize_t ret;
+	unsigned int memflags;
+	struct request_queue *q = disk->queue;
 
-	if (!q->disk)
-		return -EINVAL;
 	ret = queue_var_store(&ra_kb, page, count);
 	if (ret < 0)
 		return ret;
-	q->disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10);
-	return ret;
-}
-
-static ssize_t queue_max_sectors_show(struct request_queue *q, char *page)
-{
-	int max_sectors_kb = queue_max_sectors(q) >> 1;
-
-	return queue_var_show(max_sectors_kb, page);
-}
-
-static ssize_t queue_max_segments_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_max_segments(q), page);
-}
-
-static ssize_t queue_max_discard_segments_show(struct request_queue *q,
-		char *page)
-{
-	return queue_var_show(queue_max_discard_segments(q), page);
-}
-
-static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(q->limits.max_integrity_segments, page);
-}
-
-static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_max_segment_size(q), page);
-}
-
-static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_logical_block_size(q), page);
-}
-
-static ssize_t queue_physical_block_size_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_physical_block_size(q), page);
-}
+	/*
+	 * ->ra_pages is protected by ->limits_lock because it is usually
+	 * calculated from the queue limits by queue_limits_commit_update.
+	 */
+	mutex_lock(&q->limits_lock);
+	memflags = blk_mq_freeze_queue(q);
+	disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10);
+	mutex_unlock(&q->limits_lock);
+	blk_mq_unfreeze_queue(q, memflags);
 
-static ssize_t queue_chunk_sectors_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(q->limits.chunk_sectors, page);
+	return ret;
 }
 
-static ssize_t queue_io_min_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_io_min(q), page);
+#define QUEUE_SYSFS_LIMIT_SHOW(_field)					\
+static ssize_t queue_##_field##_show(struct gendisk *disk, char *page)	\
+{									\
+	return queue_var_show(disk->queue->limits._field, page);	\
+}
+
+QUEUE_SYSFS_LIMIT_SHOW(max_segments)
+QUEUE_SYSFS_LIMIT_SHOW(max_discard_segments)
+QUEUE_SYSFS_LIMIT_SHOW(max_integrity_segments)
+QUEUE_SYSFS_LIMIT_SHOW(max_segment_size)
+QUEUE_SYSFS_LIMIT_SHOW(max_write_streams)
+QUEUE_SYSFS_LIMIT_SHOW(write_stream_granularity)
+QUEUE_SYSFS_LIMIT_SHOW(logical_block_size)
+QUEUE_SYSFS_LIMIT_SHOW(physical_block_size)
+QUEUE_SYSFS_LIMIT_SHOW(chunk_sectors)
+QUEUE_SYSFS_LIMIT_SHOW(io_min)
+QUEUE_SYSFS_LIMIT_SHOW(io_opt)
+QUEUE_SYSFS_LIMIT_SHOW(discard_granularity)
+QUEUE_SYSFS_LIMIT_SHOW(zone_write_granularity)
+QUEUE_SYSFS_LIMIT_SHOW(virt_boundary_mask)
+QUEUE_SYSFS_LIMIT_SHOW(dma_alignment)
+QUEUE_SYSFS_LIMIT_SHOW(max_open_zones)
+QUEUE_SYSFS_LIMIT_SHOW(max_active_zones)
+QUEUE_SYSFS_LIMIT_SHOW(atomic_write_unit_min)
+QUEUE_SYSFS_LIMIT_SHOW(atomic_write_unit_max)
+
+#define QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(_field)			\
+static ssize_t queue_##_field##_show(struct gendisk *disk, char *page)	\
+{									\
+	return sysfs_emit(page, "%llu\n",				\
+		(unsigned long long)disk->queue->limits._field <<	\
+			SECTOR_SHIFT);					\
 }
 
-static ssize_t queue_io_opt_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_io_opt(q), page);
-}
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_discard_sectors)
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_hw_discard_sectors)
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_write_zeroes_sectors)
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(atomic_write_max_sectors)
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(atomic_write_boundary_sectors)
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_zone_append_sectors)
 
-static ssize_t queue_discard_granularity_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(q->limits.discard_granularity, page);
+#define QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(_field)			\
+static ssize_t queue_##_field##_show(struct gendisk *disk, char *page)	\
+{									\
+	return queue_var_show(disk->queue->limits._field >> 1, page);	\
 }
 
-static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page)
-{
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(max_sectors)
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(max_hw_sectors)
 
-	return sprintf(page, "%llu\n",
-		(unsigned long long)q->limits.max_hw_discard_sectors << 9);
+#define QUEUE_SYSFS_SHOW_CONST(_name, _val)				\
+static ssize_t queue_##_name##_show(struct gendisk *disk, char *page)	\
+{									\
+	return sysfs_emit(page, "%d\n", _val);				\
 }
 
-static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
-{
-	return sprintf(page, "%llu\n",
-		       (unsigned long long)q->limits.max_discard_sectors << 9);
-}
+/* deprecated fields */
+QUEUE_SYSFS_SHOW_CONST(discard_zeroes_data, 0)
+QUEUE_SYSFS_SHOW_CONST(write_same_max, 0)
+QUEUE_SYSFS_SHOW_CONST(poll_delay, -1)
 
-static ssize_t queue_discard_max_store(struct request_queue *q,
-				       const char *page, size_t count)
+static int queue_max_discard_sectors_store(struct gendisk *disk,
+		const char *page, size_t count, struct queue_limits *lim)
 {
 	unsigned long max_discard_bytes;
-	struct queue_limits lim;
 	ssize_t ret;
-	int err;
 
 	ret = queue_var_store(&max_discard_bytes, page, count);
 	if (ret < 0)
 		return ret;
 
-	if (max_discard_bytes & (q->limits.discard_granularity - 1))
+	if (max_discard_bytes & (disk->queue->limits.discard_granularity - 1))
 		return -EINVAL;
 
 	if ((max_discard_bytes >> SECTOR_SHIFT) > UINT_MAX)
 		return -EINVAL;
 
-	blk_mq_freeze_queue(q);
-	lim = queue_limits_start_update(q);
-	lim.max_user_discard_sectors = max_discard_bytes >> SECTOR_SHIFT;
-	err = queue_limits_commit_update(q, &lim);
-	blk_mq_unfreeze_queue(q);
-
-	if (err)
-		return err;
-	return ret;
-}
-
-static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(0, page);
-}
-
-static ssize_t queue_write_same_max_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(0, page);
-}
-
-static ssize_t queue_write_zeroes_max_show(struct request_queue *q, char *page)
-{
-	return sprintf(page, "%llu\n",
-		(unsigned long long)q->limits.max_write_zeroes_sectors << 9);
-}
-
-static ssize_t queue_zone_write_granularity_show(struct request_queue *q,
-						 char *page)
-{
-	return queue_var_show(queue_zone_write_granularity(q), page);
-}
-
-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;
-
-	return sprintf(page, "%llu\n", max_sectors << SECTOR_SHIFT);
+	lim->max_user_discard_sectors = max_discard_bytes >> SECTOR_SHIFT;
+	return 0;
 }
 
-static ssize_t
-queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
+static int
+queue_max_sectors_store(struct gendisk *disk, const char *page, size_t count,
+		struct queue_limits *lim)
 {
 	unsigned long max_sectors_kb;
-	struct queue_limits lim;
 	ssize_t ret;
-	int err;
 
 	ret = queue_var_store(&max_sectors_kb, page, count);
 	if (ret < 0)
 		return ret;
 
-	blk_mq_freeze_queue(q);
-	lim = queue_limits_start_update(q);
-	lim.max_user_sectors = max_sectors_kb << 1;
-	err = queue_limits_commit_update(q, &lim);
-	blk_mq_unfreeze_queue(q);
-	if (err)
-		return err;
-	return ret;
+	lim->max_user_sectors = max_sectors_kb << 1;
+	return 0;
 }
 
-static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
+static ssize_t queue_feature_store(struct gendisk *disk, const char *page,
+		size_t count, struct queue_limits *lim, blk_features_t feature)
 {
-	int max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1;
-
-	return queue_var_show(max_hw_sectors_kb, page);
-}
+	unsigned long val;
+	ssize_t ret;
 
-static ssize_t queue_virt_boundary_mask_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(q->limits.virt_boundary_mask, page);
-}
+	ret = queue_var_store(&val, page, count);
+	if (ret < 0)
+		return ret;
 
-static ssize_t queue_dma_alignment_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_dma_alignment(q), page);
+	if (val)
+		lim->features |= feature;
+	else
+		lim->features &= ~feature;
+	return 0;
 }
 
-#define QUEUE_SYSFS_BIT_FNS(name, flag, neg)				\
-static ssize_t								\
-queue_##name##_show(struct request_queue *q, char *page)		\
+#define QUEUE_SYSFS_FEATURE(_name, _feature)				\
+static ssize_t queue_##_name##_show(struct gendisk *disk, char *page)	\
 {									\
-	int bit;							\
-	bit = test_bit(QUEUE_FLAG_##flag, &q->queue_flags);		\
-	return queue_var_show(neg ? !bit : bit, page);			\
+	return sysfs_emit(page, "%u\n",					\
+		!!(disk->queue->limits.features & _feature));		\
 }									\
-static ssize_t								\
-queue_##name##_store(struct request_queue *q, const char *page, size_t count) \
+static int queue_##_name##_store(struct gendisk *disk,			\
+		const char *page, size_t count, struct queue_limits *lim) \
+{									\
+	return queue_feature_store(disk, page, count, lim, _feature);	\
+}
+
+QUEUE_SYSFS_FEATURE(rotational, BLK_FEAT_ROTATIONAL)
+QUEUE_SYSFS_FEATURE(add_random, BLK_FEAT_ADD_RANDOM)
+QUEUE_SYSFS_FEATURE(iostats, BLK_FEAT_IO_STAT)
+QUEUE_SYSFS_FEATURE(stable_writes, BLK_FEAT_STABLE_WRITES);
+
+#define QUEUE_SYSFS_FEATURE_SHOW(_name, _feature)			\
+static ssize_t queue_##_name##_show(struct gendisk *disk, char *page)	\
 {									\
-	unsigned long val;						\
-	ssize_t ret;							\
-	ret = queue_var_store(&val, page, count);			\
-	if (ret < 0)							\
-		 return ret;						\
-	if (neg)							\
-		val = !val;						\
-									\
-	if (val)							\
-		blk_queue_flag_set(QUEUE_FLAG_##flag, q);		\
-	else								\
-		blk_queue_flag_clear(QUEUE_FLAG_##flag, q);		\
-	return ret;							\
+	return sysfs_emit(page, "%u\n",					\
+		!!(disk->queue->limits.features & _feature));		\
 }
 
-QUEUE_SYSFS_BIT_FNS(nonrot, NONROT, 1);
-QUEUE_SYSFS_BIT_FNS(random, ADD_RANDOM, 0);
-QUEUE_SYSFS_BIT_FNS(iostats, IO_STAT, 0);
-QUEUE_SYSFS_BIT_FNS(stable_writes, STABLE_WRITES, 0);
-#undef QUEUE_SYSFS_BIT_FNS
+QUEUE_SYSFS_FEATURE_SHOW(fua, BLK_FEAT_FUA);
+QUEUE_SYSFS_FEATURE_SHOW(dax, BLK_FEAT_DAX);
+
+static ssize_t queue_poll_show(struct gendisk *disk, char *page)
+{
+	if (queue_is_mq(disk->queue))
+		return sysfs_emit(page, "%u\n", blk_mq_can_poll(disk->queue));
+
+	return sysfs_emit(page, "%u\n",
+			!!(disk->queue->limits.features & BLK_FEAT_POLL));
+}
 
-static ssize_t queue_zoned_show(struct request_queue *q, char *page)
+static ssize_t queue_zoned_show(struct gendisk *disk, char *page)
 {
-	if (blk_queue_is_zoned(q))
-		return sprintf(page, "host-managed\n");
-	return sprintf(page, "none\n");
+	if (blk_queue_is_zoned(disk->queue))
+		return sysfs_emit(page, "host-managed\n");
+	return sysfs_emit(page, "none\n");
 }
 
-static ssize_t queue_nr_zones_show(struct request_queue *q, char *page)
+static ssize_t queue_nr_zones_show(struct gendisk *disk, char *page)
 {
-	return queue_var_show(disk_nr_zones(q->disk), page);
+	return queue_var_show(disk_nr_zones(disk), page);
 }
 
-static ssize_t queue_max_open_zones_show(struct request_queue *q, char *page)
+static ssize_t queue_iostats_passthrough_show(struct gendisk *disk, char *page)
 {
-	return queue_var_show(bdev_max_open_zones(q->disk->part0), page);
+	return queue_var_show(!!blk_queue_passthrough_stat(disk->queue), page);
 }
 
-static ssize_t queue_max_active_zones_show(struct request_queue *q, char *page)
+static int queue_iostats_passthrough_store(struct gendisk *disk,
+		const char *page, size_t count, struct queue_limits *lim)
 {
-	return queue_var_show(bdev_max_active_zones(q->disk->part0), page);
+	unsigned long ios;
+	ssize_t ret;
+
+	ret = queue_var_store(&ios, page, count);
+	if (ret < 0)
+		return ret;
+
+	if (ios)
+		lim->flags |= BLK_FLAG_IOSTATS_PASSTHROUGH;
+	else
+		lim->flags &= ~BLK_FLAG_IOSTATS_PASSTHROUGH;
+	return 0;
 }
 
-static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
+static ssize_t queue_nomerges_show(struct gendisk *disk, char *page)
 {
-	return queue_var_show((blk_queue_nomerges(q) << 1) |
-			       blk_queue_noxmerges(q), page);
+	return queue_var_show((blk_queue_nomerges(disk->queue) << 1) |
+			       blk_queue_noxmerges(disk->queue), page);
 }
 
-static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
+static ssize_t queue_nomerges_store(struct gendisk *disk, const char *page,
 				    size_t count)
 {
 	unsigned long nm;
+	unsigned int memflags;
+	struct request_queue *q = disk->queue;
 	ssize_t ret = queue_var_store(&nm, page, count);
 
 	if (ret < 0)
 		return ret;
 
+	memflags = blk_mq_freeze_queue(q);
 	blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, q);
 	blk_queue_flag_clear(QUEUE_FLAG_NOXMERGES, q);
 	if (nm == 2)
 		blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q);
 	else if (nm)
 		blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
+	blk_mq_unfreeze_queue(q, memflags);
 
 	return ret;
 }
 
-static ssize_t queue_rq_affinity_show(struct request_queue *q, char *page)
+static ssize_t queue_rq_affinity_show(struct gendisk *disk, char *page)
 {
-	bool set = test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags);
-	bool force = test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags);
+	bool set = test_bit(QUEUE_FLAG_SAME_COMP, &disk->queue->queue_flags);
+	bool force = test_bit(QUEUE_FLAG_SAME_FORCE, &disk->queue->queue_flags);
 
 	return queue_var_show(set << force, page);
 }
 
 static ssize_t
-queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
+queue_rq_affinity_store(struct gendisk *disk, const char *page, size_t count)
 {
 	ssize_t ret = -EINVAL;
 #ifdef CONFIG_SMP
+	struct request_queue *q = disk->queue;
 	unsigned long val;
+	unsigned int memflags;
 
 	ret = queue_var_store(&val, page, count);
 	if (ret < 0)
 		return ret;
 
+	/*
+	 * Here we update two queue flags each using atomic bitops, although
+	 * updating two flags isn't atomic it should be harmless as those flags
+	 * are accessed individually using atomic test_bit operation. So we
+	 * don't grab any lock while updating these flags.
+	 */
+	memflags = blk_mq_freeze_queue(q);
 	if (val == 2) {
 		blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, q);
 		blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, q);
@@ -376,89 +374,87 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
 		blk_queue_flag_clear(QUEUE_FLAG_SAME_COMP, q);
 		blk_queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q);
 	}
+	blk_mq_unfreeze_queue(q, memflags);
 #endif
 	return ret;
 }
 
-static ssize_t queue_poll_delay_show(struct request_queue *q, char *page)
-{
-	return sprintf(page, "%d\n", -1);
-}
-
-static ssize_t queue_poll_delay_store(struct request_queue *q, const char *page,
+static ssize_t queue_poll_delay_store(struct gendisk *disk, const char *page,
 				size_t count)
 {
 	return count;
 }
 
-static ssize_t queue_poll_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(test_bit(QUEUE_FLAG_POLL, &q->queue_flags), page);
-}
-
-static ssize_t queue_poll_store(struct request_queue *q, const char *page,
+static ssize_t queue_poll_store(struct gendisk *disk, const char *page,
 				size_t count)
 {
-	if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
-		return -EINVAL;
+	unsigned int memflags;
+	ssize_t ret = count;
+	struct request_queue *q = disk->queue;
+
+	memflags = blk_mq_freeze_queue(q);
+	if (!(q->limits.features & BLK_FEAT_POLL)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	pr_info_ratelimited("writes to the poll attribute are ignored.\n");
 	pr_info_ratelimited("please use driver specific parameters instead.\n");
-	return count;
+out:
+	blk_mq_unfreeze_queue(q, memflags);
+	return ret;
 }
 
-static ssize_t queue_io_timeout_show(struct request_queue *q, char *page)
+static ssize_t queue_io_timeout_show(struct gendisk *disk, char *page)
 {
-	return sprintf(page, "%u\n", jiffies_to_msecs(q->rq_timeout));
+	return sysfs_emit(page, "%u\n",
+			jiffies_to_msecs(READ_ONCE(disk->queue->rq_timeout)));
 }
 
-static ssize_t queue_io_timeout_store(struct request_queue *q, const char *page,
+static ssize_t queue_io_timeout_store(struct gendisk *disk, const char *page,
 				  size_t count)
 {
-	unsigned int val;
+	unsigned int val, memflags;
 	int err;
+	struct request_queue *q = disk->queue;
 
 	err = kstrtou32(page, 10, &val);
 	if (err || val == 0)
 		return -EINVAL;
 
+	memflags = blk_mq_freeze_queue(q);
 	blk_queue_rq_timeout(q, msecs_to_jiffies(val));
+	blk_mq_unfreeze_queue(q, memflags);
 
 	return count;
 }
 
-static ssize_t queue_wc_show(struct request_queue *q, char *page)
+static ssize_t queue_wc_show(struct gendisk *disk, char *page)
 {
-	if (test_bit(QUEUE_FLAG_WC, &q->queue_flags))
-		return sprintf(page, "write back\n");
-
-	return sprintf(page, "write through\n");
+	if (blk_queue_write_cache(disk->queue))
+		return sysfs_emit(page, "write back\n");
+	return sysfs_emit(page, "write through\n");
 }
 
-static ssize_t queue_wc_store(struct request_queue *q, const char *page,
-			      size_t count)
+static int queue_wc_store(struct gendisk *disk, const char *page,
+		size_t count, struct queue_limits *lim)
 {
+	bool disable;
+
 	if (!strncmp(page, "write back", 10)) {
-		if (!test_bit(QUEUE_FLAG_HW_WC, &q->queue_flags))
-			return -EINVAL;
-		blk_queue_flag_set(QUEUE_FLAG_WC, q);
+		disable = false;
 	} else if (!strncmp(page, "write through", 13) ||
-		 !strncmp(page, "none", 4)) {
-		blk_queue_flag_clear(QUEUE_FLAG_WC, q);
+		   !strncmp(page, "none", 4)) {
+		disable = true;
 	} else {
 		return -EINVAL;
 	}
 
-	return count;
-}
-
-static ssize_t queue_fua_show(struct request_queue *q, char *page)
-{
-	return sprintf(page, "%u\n", test_bit(QUEUE_FLAG_FUA, &q->queue_flags));
-}
-
-static ssize_t queue_dax_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(blk_queue_dax(q), page);
+	if (disable)
+		lim->flags |= BLK_FLAG_WRITE_CACHE_DISABLED;
+	else
+		lim->flags &= ~BLK_FLAG_WRITE_CACHE_DISABLED;
+	return 0;
 }
 
 #define QUEUE_RO_ENTRY(_prefix, _name)			\
@@ -474,62 +470,80 @@ static struct queue_sysfs_entry _prefix##_entry = {	\
 	.store	= _prefix##_store,			\
 };
 
+#define QUEUE_LIM_RO_ENTRY(_prefix, _name)			\
+static struct queue_sysfs_entry _prefix##_entry = {	\
+	.attr		= { .name = _name, .mode = 0444 },	\
+	.show_limit	= _prefix##_show,			\
+}
+
+#define QUEUE_LIM_RW_ENTRY(_prefix, _name)			\
+static struct queue_sysfs_entry _prefix##_entry = {	\
+	.attr		= { .name = _name, .mode = 0644 },	\
+	.show_limit	= _prefix##_show,			\
+	.store_limit	= _prefix##_store,			\
+}
+
 QUEUE_RW_ENTRY(queue_requests, "nr_requests");
 QUEUE_RW_ENTRY(queue_ra, "read_ahead_kb");
-QUEUE_RW_ENTRY(queue_max_sectors, "max_sectors_kb");
-QUEUE_RO_ENTRY(queue_max_hw_sectors, "max_hw_sectors_kb");
-QUEUE_RO_ENTRY(queue_max_segments, "max_segments");
-QUEUE_RO_ENTRY(queue_max_integrity_segments, "max_integrity_segments");
-QUEUE_RO_ENTRY(queue_max_segment_size, "max_segment_size");
+QUEUE_LIM_RW_ENTRY(queue_max_sectors, "max_sectors_kb");
+QUEUE_LIM_RO_ENTRY(queue_max_hw_sectors, "max_hw_sectors_kb");
+QUEUE_LIM_RO_ENTRY(queue_max_segments, "max_segments");
+QUEUE_LIM_RO_ENTRY(queue_max_integrity_segments, "max_integrity_segments");
+QUEUE_LIM_RO_ENTRY(queue_max_segment_size, "max_segment_size");
+QUEUE_LIM_RO_ENTRY(queue_max_write_streams, "max_write_streams");
+QUEUE_LIM_RO_ENTRY(queue_write_stream_granularity, "write_stream_granularity");
 QUEUE_RW_ENTRY(elv_iosched, "scheduler");
 
-QUEUE_RO_ENTRY(queue_logical_block_size, "logical_block_size");
-QUEUE_RO_ENTRY(queue_physical_block_size, "physical_block_size");
-QUEUE_RO_ENTRY(queue_chunk_sectors, "chunk_sectors");
-QUEUE_RO_ENTRY(queue_io_min, "minimum_io_size");
-QUEUE_RO_ENTRY(queue_io_opt, "optimal_io_size");
+QUEUE_LIM_RO_ENTRY(queue_logical_block_size, "logical_block_size");
+QUEUE_LIM_RO_ENTRY(queue_physical_block_size, "physical_block_size");
+QUEUE_LIM_RO_ENTRY(queue_chunk_sectors, "chunk_sectors");
+QUEUE_LIM_RO_ENTRY(queue_io_min, "minimum_io_size");
+QUEUE_LIM_RO_ENTRY(queue_io_opt, "optimal_io_size");
 
-QUEUE_RO_ENTRY(queue_max_discard_segments, "max_discard_segments");
-QUEUE_RO_ENTRY(queue_discard_granularity, "discard_granularity");
-QUEUE_RO_ENTRY(queue_discard_max_hw, "discard_max_hw_bytes");
-QUEUE_RW_ENTRY(queue_discard_max, "discard_max_bytes");
+QUEUE_LIM_RO_ENTRY(queue_max_discard_segments, "max_discard_segments");
+QUEUE_LIM_RO_ENTRY(queue_discard_granularity, "discard_granularity");
+QUEUE_LIM_RO_ENTRY(queue_max_hw_discard_sectors, "discard_max_hw_bytes");
+QUEUE_LIM_RW_ENTRY(queue_max_discard_sectors, "discard_max_bytes");
 QUEUE_RO_ENTRY(queue_discard_zeroes_data, "discard_zeroes_data");
 
+QUEUE_LIM_RO_ENTRY(queue_atomic_write_max_sectors, "atomic_write_max_bytes");
+QUEUE_LIM_RO_ENTRY(queue_atomic_write_boundary_sectors,
+		"atomic_write_boundary_bytes");
+QUEUE_LIM_RO_ENTRY(queue_atomic_write_unit_max, "atomic_write_unit_max_bytes");
+QUEUE_LIM_RO_ENTRY(queue_atomic_write_unit_min, "atomic_write_unit_min_bytes");
+
 QUEUE_RO_ENTRY(queue_write_same_max, "write_same_max_bytes");
-QUEUE_RO_ENTRY(queue_write_zeroes_max, "write_zeroes_max_bytes");
-QUEUE_RO_ENTRY(queue_zone_append_max, "zone_append_max_bytes");
-QUEUE_RO_ENTRY(queue_zone_write_granularity, "zone_write_granularity");
+QUEUE_LIM_RO_ENTRY(queue_max_write_zeroes_sectors, "write_zeroes_max_bytes");
+QUEUE_LIM_RO_ENTRY(queue_max_zone_append_sectors, "zone_append_max_bytes");
+QUEUE_LIM_RO_ENTRY(queue_zone_write_granularity, "zone_write_granularity");
 
-QUEUE_RO_ENTRY(queue_zoned, "zoned");
+QUEUE_LIM_RO_ENTRY(queue_zoned, "zoned");
 QUEUE_RO_ENTRY(queue_nr_zones, "nr_zones");
-QUEUE_RO_ENTRY(queue_max_open_zones, "max_open_zones");
-QUEUE_RO_ENTRY(queue_max_active_zones, "max_active_zones");
+QUEUE_LIM_RO_ENTRY(queue_max_open_zones, "max_open_zones");
+QUEUE_LIM_RO_ENTRY(queue_max_active_zones, "max_active_zones");
 
 QUEUE_RW_ENTRY(queue_nomerges, "nomerges");
+QUEUE_LIM_RW_ENTRY(queue_iostats_passthrough, "iostats_passthrough");
 QUEUE_RW_ENTRY(queue_rq_affinity, "rq_affinity");
 QUEUE_RW_ENTRY(queue_poll, "io_poll");
 QUEUE_RW_ENTRY(queue_poll_delay, "io_poll_delay");
-QUEUE_RW_ENTRY(queue_wc, "write_cache");
-QUEUE_RO_ENTRY(queue_fua, "fua");
-QUEUE_RO_ENTRY(queue_dax, "dax");
+QUEUE_LIM_RW_ENTRY(queue_wc, "write_cache");
+QUEUE_LIM_RO_ENTRY(queue_fua, "fua");
+QUEUE_LIM_RO_ENTRY(queue_dax, "dax");
 QUEUE_RW_ENTRY(queue_io_timeout, "io_timeout");
-QUEUE_RO_ENTRY(queue_virt_boundary_mask, "virt_boundary_mask");
-QUEUE_RO_ENTRY(queue_dma_alignment, "dma_alignment");
-
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-QUEUE_RW_ENTRY(blk_throtl_sample_time, "throttle_sample_time");
-#endif
+QUEUE_LIM_RO_ENTRY(queue_virt_boundary_mask, "virt_boundary_mask");
+QUEUE_LIM_RO_ENTRY(queue_dma_alignment, "dma_alignment");
 
 /* legacy alias for logical_block_size: */
 static struct queue_sysfs_entry queue_hw_sector_size_entry = {
-	.attr = {.name = "hw_sector_size", .mode = 0444 },
-	.show = queue_logical_block_size_show,
+	.attr		= {.name = "hw_sector_size", .mode = 0444 },
+	.show_limit	= queue_logical_block_size_show,
 };
 
-QUEUE_RW_ENTRY(queue_nonrot, "rotational");
-QUEUE_RW_ENTRY(queue_iostats, "iostats");
-QUEUE_RW_ENTRY(queue_random, "add_random");
-QUEUE_RW_ENTRY(queue_stable_writes, "stable_writes");
+QUEUE_LIM_RW_ENTRY(queue_rotational, "rotational");
+QUEUE_LIM_RW_ENTRY(queue_iostats, "iostats");
+QUEUE_LIM_RW_ENTRY(queue_add_random, "add_random");
+QUEUE_LIM_RW_ENTRY(queue_stable_writes, "stable_writes");
 
 #ifdef CONFIG_BLK_WBT
 static ssize_t queue_var_store64(s64 *var, const char *page)
@@ -545,23 +559,36 @@ static ssize_t queue_var_store64(s64 *var, const char *page)
 	return 0;
 }
 
-static ssize_t queue_wb_lat_show(struct request_queue *q, char *page)
+static ssize_t queue_wb_lat_show(struct gendisk *disk, char *page)
 {
-	if (!wbt_rq_qos(q))
-		return -EINVAL;
+	ssize_t ret;
+	struct request_queue *q = disk->queue;
 
-	if (wbt_disabled(q))
-		return sprintf(page, "0\n");
+	mutex_lock(&disk->rqos_state_mutex);
+	if (!wbt_rq_qos(q)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (wbt_disabled(q)) {
+		ret = sysfs_emit(page, "0\n");
+		goto out;
+	}
 
-	return sprintf(page, "%llu\n", div_u64(wbt_get_min_lat(q), 1000));
+	ret = sysfs_emit(page, "%llu\n", div_u64(wbt_get_min_lat(q), 1000));
+out:
+	mutex_unlock(&disk->rqos_state_mutex);
+	return ret;
 }
 
-static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
+static ssize_t queue_wb_lat_store(struct gendisk *disk, const char *page,
 				  size_t count)
 {
+	struct request_queue *q = disk->queue;
 	struct rq_qos *rqos;
 	ssize_t ret;
 	s64 val;
+	unsigned int memflags;
 
 	ret = queue_var_store64(&val, page);
 	if (ret < 0)
@@ -569,35 +596,40 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 	if (val < -1)
 		return -EINVAL;
 
+	memflags = blk_mq_freeze_queue(q);
+
 	rqos = wbt_rq_qos(q);
 	if (!rqos) {
-		ret = wbt_init(q->disk);
+		ret = wbt_init(disk);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
+	ret = count;
 	if (val == -1)
 		val = wbt_default_latency_nsec(q);
 	else if (val >= 0)
 		val *= 1000ULL;
 
 	if (wbt_get_min_lat(q) == val)
-		return count;
+		goto out;
 
 	/*
 	 * Ensure that the queue is idled, in case the latency update
 	 * ends up either enabling or disabling wbt completely. We can't
 	 * have IO inflight if that happens.
 	 */
-	blk_mq_freeze_queue(q);
 	blk_mq_quiesce_queue(q);
 
+	mutex_lock(&disk->rqos_state_mutex);
 	wbt_set_min_lat(q, val);
+	mutex_unlock(&disk->rqos_state_mutex);
 
 	blk_mq_unquiesce_queue(q);
-	blk_mq_unfreeze_queue(q);
+out:
+	blk_mq_unfreeze_queue(q, memflags);
 
-	return count;
+	return ret;
 }
 
 QUEUE_RW_ENTRY(queue_wb_lat, "wbt_lat_usec");
@@ -605,13 +637,17 @@ QUEUE_RW_ENTRY(queue_wb_lat, "wbt_lat_usec");
 
 /* Common attributes for bio-based and request-based queues. */
 static struct attribute *queue_attrs[] = {
-	&queue_ra_entry.attr,
+	/*
+	 * Attributes which are protected with q->limits_lock.
+	 */
 	&queue_max_hw_sectors_entry.attr,
 	&queue_max_sectors_entry.attr,
 	&queue_max_segments_entry.attr,
 	&queue_max_discard_segments_entry.attr,
 	&queue_max_integrity_segments_entry.attr,
 	&queue_max_segment_size_entry.attr,
+	&queue_max_write_streams_entry.attr,
+	&queue_write_stream_granularity_entry.attr,
 	&queue_hw_sector_size_entry.attr,
 	&queue_logical_block_size_entry.attr,
 	&queue_physical_block_size_entry.attr,
@@ -619,44 +655,60 @@ static struct attribute *queue_attrs[] = {
 	&queue_io_min_entry.attr,
 	&queue_io_opt_entry.attr,
 	&queue_discard_granularity_entry.attr,
-	&queue_discard_max_entry.attr,
-	&queue_discard_max_hw_entry.attr,
-	&queue_discard_zeroes_data_entry.attr,
-	&queue_write_same_max_entry.attr,
-	&queue_write_zeroes_max_entry.attr,
-	&queue_zone_append_max_entry.attr,
+	&queue_max_discard_sectors_entry.attr,
+	&queue_max_hw_discard_sectors_entry.attr,
+	&queue_atomic_write_max_sectors_entry.attr,
+	&queue_atomic_write_boundary_sectors_entry.attr,
+	&queue_atomic_write_unit_min_entry.attr,
+	&queue_atomic_write_unit_max_entry.attr,
+	&queue_max_write_zeroes_sectors_entry.attr,
+	&queue_max_zone_append_sectors_entry.attr,
 	&queue_zone_write_granularity_entry.attr,
-	&queue_nonrot_entry.attr,
+	&queue_rotational_entry.attr,
 	&queue_zoned_entry.attr,
-	&queue_nr_zones_entry.attr,
 	&queue_max_open_zones_entry.attr,
 	&queue_max_active_zones_entry.attr,
-	&queue_nomerges_entry.attr,
+	&queue_iostats_passthrough_entry.attr,
 	&queue_iostats_entry.attr,
 	&queue_stable_writes_entry.attr,
-	&queue_random_entry.attr,
-	&queue_poll_entry.attr,
+	&queue_add_random_entry.attr,
 	&queue_wc_entry.attr,
 	&queue_fua_entry.attr,
 	&queue_dax_entry.attr,
-	&queue_poll_delay_entry.attr,
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-	&blk_throtl_sample_time_entry.attr,
-#endif
 	&queue_virt_boundary_mask_entry.attr,
 	&queue_dma_alignment_entry.attr,
+	&queue_ra_entry.attr,
+
+	/*
+	 * Attributes which don't require locking.
+	 */
+	&queue_discard_zeroes_data_entry.attr,
+	&queue_write_same_max_entry.attr,
+	&queue_nr_zones_entry.attr,
+	&queue_nomerges_entry.attr,
+	&queue_poll_entry.attr,
+	&queue_poll_delay_entry.attr,
+
 	NULL,
 };
 
 /* Request-based queue attributes that are not relevant for bio-based queues. */
 static struct attribute *blk_mq_queue_attrs[] = {
-	&queue_requests_entry.attr,
+	/*
+	 * Attributes which require some form of locking other than
+	 * q->sysfs_lock.
+	 */
 	&elv_iosched_entry.attr,
-	&queue_rq_affinity_entry.attr,
-	&queue_io_timeout_entry.attr,
+	&queue_requests_entry.attr,
 #ifdef CONFIG_BLK_WBT
 	&queue_wb_lat_entry.attr,
 #endif
+	/*
+	 * Attributes which don't require locking.
+	 */
+	&queue_rq_affinity_entry.attr,
+	&queue_io_timeout_entry.attr,
+
 	NULL,
 };
 
@@ -706,15 +758,20 @@ queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 {
 	struct queue_sysfs_entry *entry = to_queue(attr);
 	struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj);
-	struct request_queue *q = disk->queue;
-	ssize_t res;
 
-	if (!entry->show)
+	if (!entry->show && !entry->show_limit)
 		return -EIO;
-	mutex_lock(&q->sysfs_lock);
-	res = entry->show(q, page);
-	mutex_unlock(&q->sysfs_lock);
-	return res;
+
+	if (entry->show_limit) {
+		ssize_t res;
+
+		mutex_lock(&disk->queue->limits_lock);
+		res = entry->show_limit(disk, page);
+		mutex_unlock(&disk->queue->limits_lock);
+		return res;
+	}
+
+	return entry->show(disk, page);
 }
 
 static ssize_t
@@ -724,15 +781,28 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,
 	struct queue_sysfs_entry *entry = to_queue(attr);
 	struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj);
 	struct request_queue *q = disk->queue;
-	ssize_t res;
 
-	if (!entry->store)
+	if (!entry->store_limit && !entry->store)
 		return -EIO;
 
-	mutex_lock(&q->sysfs_lock);
-	res = entry->store(q, page, length);
-	mutex_unlock(&q->sysfs_lock);
-	return res;
+	if (entry->store_limit) {
+		ssize_t res;
+
+		struct queue_limits lim = queue_limits_start_update(q);
+
+		res = entry->store_limit(disk, page, length, &lim);
+		if (res < 0) {
+			queue_limits_cancel_update(q);
+			return res;
+		}
+
+		res = queue_limits_commit_update_frozen(q, &lim);
+		if (res)
+			return res;
+		return length;
+	}
+
+	return entry->store(disk, page, length);
 }
 
 static const struct sysfs_ops queue_sysfs_ops = {
@@ -779,7 +849,6 @@ int blk_register_queue(struct gendisk *disk)
 	struct request_queue *q = disk->queue;
 	int ret;
 
-	mutex_lock(&q->sysfs_dir_lock);
 	kobject_init(&disk->queue_kobj, &blk_queue_ktype);
 	ret = kobject_add(&disk->queue_kobj, &disk_to_dev(disk)->kobj, "queue");
 	if (ret < 0)
@@ -802,26 +871,21 @@ int blk_register_queue(struct gendisk *disk)
 	if (ret)
 		goto out_debugfs_remove;
 
-	if (q->elevator) {
-		ret = elv_register_queue(q, false);
-		if (ret)
-			goto out_unregister_ia_ranges;
-	}
-
 	ret = blk_crypto_sysfs_register(disk);
 	if (ret)
-		goto out_elv_unregister;
+		goto out_unregister_ia_ranges;
 
-	blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
+	if (queue_is_mq(q))
+		elevator_set_default(q);
 	wbt_enable_default(disk);
-	blk_throtl_register(disk);
+
+	blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
 
 	/* Now everything is ready and send out KOBJ_ADD uevent */
 	kobject_uevent(&disk->queue_kobj, KOBJ_ADD);
 	if (q->elevator)
 		kobject_uevent(&q->elevator->kobj, KOBJ_ADD);
 	mutex_unlock(&q->sysfs_lock);
-	mutex_unlock(&q->sysfs_dir_lock);
 
 	/*
 	 * SCSI probing may synchronously create and destroy a lot of
@@ -832,23 +896,20 @@ int blk_register_queue(struct gendisk *disk)
 	 * faster to shut down and is made fully functional here as
 	 * request_queues for non-existent devices never get registered.
 	 */
-	if (!blk_queue_init_done(q)) {
-		blk_queue_flag_set(QUEUE_FLAG_INIT_DONE, q);
-		percpu_ref_switch_to_percpu(&q->q_usage_counter);
-	}
+	blk_queue_flag_set(QUEUE_FLAG_INIT_DONE, q);
+	percpu_ref_switch_to_percpu(&q->q_usage_counter);
 
 	return ret;
 
-out_elv_unregister:
-	elv_unregister_queue(q);
 out_unregister_ia_ranges:
 	disk_unregister_independent_access_ranges(disk);
 out_debugfs_remove:
 	blk_debugfs_remove(disk);
 	mutex_unlock(&q->sysfs_lock);
+	if (queue_is_mq(q))
+		blk_mq_sysfs_unregister(disk);
 out_put_queue_kobj:
 	kobject_put(&disk->queue_kobj);
-	mutex_unlock(&q->sysfs_dir_lock);
 	return ret;
 }
 
@@ -879,7 +940,6 @@ void blk_unregister_queue(struct gendisk *disk)
 	blk_queue_flag_clear(QUEUE_FLAG_REGISTERED, q);
 	mutex_unlock(&q->sysfs_lock);
 
-	mutex_lock(&q->sysfs_dir_lock);
 	/*
 	 * Remove the sysfs attributes before unregistering the queue data
 	 * structures that can be modified through sysfs.
@@ -889,14 +949,15 @@ void blk_unregister_queue(struct gendisk *disk)
 	blk_crypto_sysfs_unregister(disk);
 
 	mutex_lock(&q->sysfs_lock);
-	elv_unregister_queue(q);
 	disk_unregister_independent_access_ranges(disk);
 	mutex_unlock(&q->sysfs_lock);
 
 	/* Now that we've deleted all child objects, we can delete the queue. */
 	kobject_uevent(&disk->queue_kobj, KOBJ_REMOVE);
 	kobject_del(&disk->queue_kobj);
-	mutex_unlock(&q->sysfs_dir_lock);
+
+	if (queue_is_mq(q))
+		elevator_set_none(q);
 
 	blk_debugfs_remove(disk);
 }