Writes in sequential write required zones must happen at the write
pointer. Even if the submitter of the write commands (e.g. a filesystem)
submits writes for sequential write required zones in order, the block
layer or the storage controller may reorder these write commands.
The zone locking mechanism in the mq-deadline I/O scheduler serializes
write commands for sequential zones. Some but not all storage controllers
require this serialization. Introduce a new request queue limit member
variable to allow block drivers to indicate that they preserve the order
of write commands and thus do not require serialization of writes per
zone.
Cc: Damien Le Moal <dlemoal@xxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Ming Lei <ming.lei@xxxxxxxxxx>
Signed-off-by: Bart Van Assche <bvanassche@xxxxxxx>
---
block/blk-settings.c | 6 ++++++
include/linux/blkdev.h | 1 +
2 files changed, 7 insertions(+)
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 0046b447268f..b75c97971860 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -56,6 +56,7 @@ void blk_set_default_limits(struct queue_limits *lim)
lim->alignment_offset = 0;
lim->io_opt = 0;
lim->misaligned = 0;
+ lim->use_zone_write_lock = true;
lim->zoned = BLK_ZONED_NONE;
lim->zone_write_granularity = 0;
lim->dma_alignment = 511;
@@ -685,6 +686,11 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
b->max_secure_erase_sectors);
t->zone_write_granularity = max(t->zone_write_granularity,
b->zone_write_granularity);
+ /*
+ * Whether or not the zone write lock should be used depends on the
+ * bottom driver only.
+ */
+ t->use_zone_write_lock = b->use_zone_write_lock;
t->zoned = max(t->zoned, b->zoned);
return ret;
}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2f5371b8482c..deffa1f13444 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -316,6 +316,7 @@ struct queue_limits {
unsigned char misaligned;
unsigned char discard_misaligned;
unsigned char raid_partial_stripes_expensive;
+ bool use_zone_write_lock;
enum blk_zoned_model zoned;
/*
