block: add support for REQ_OP_WRITE_ZEROES

This adds a new block layer operation to zero out a range of
LBAs. This allows to implement zeroing for devices that don't use
either discard with a predictable zero pattern or WRITE SAME of zeroes.
The prominent example of that is NVMe with the Write Zeroes command,
but in the future, this should also help with improving the way
zeroing discards work. For this operation, suitable entry is exported in
sysfs which indicate the number of maximum bytes allowed in one
write zeroes operation by the device.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@hgst.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@fb.com>

3 files changed, 35 insertions, 11 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 70a7244f08a7..b15323934a29 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -76,7 +76,8 @@ static inline bool bio_has_data(struct bio *bio)
 	if (bio &&
 	    bio->bi_iter.bi_size &&
 	    bio_op(bio) != REQ_OP_DISCARD &&
-	    bio_op(bio) != REQ_OP_SECURE_ERASE)
+	    bio_op(bio) != REQ_OP_SECURE_ERASE &&
+	    bio_op(bio) != REQ_OP_WRITE_ZEROES)
 		return true;
 
 	return false;
@@ -86,7 +87,8 @@ static inline bool bio_no_advance_iter(struct bio *bio)
 {
 	return bio_op(bio) == REQ_OP_DISCARD ||
 	       bio_op(bio) == REQ_OP_SECURE_ERASE ||
-	       bio_op(bio) == REQ_OP_WRITE_SAME;
+	       bio_op(bio) == REQ_OP_WRITE_SAME ||
+	       bio_op(bio) == REQ_OP_WRITE_ZEROES;
 }
 
 static inline bool bio_mergeable(struct bio *bio)
@@ -188,18 +190,19 @@ static inline unsigned bio_segments(struct bio *bio)
 	struct bvec_iter iter;
 
 	/*
-	 * We special case discard/write same, because they interpret bi_size
-	 * differently:
+	 * We special case discard/write same/write zeroes, because they
+	 * interpret bi_size differently:
 	 */
 
-	if (bio_op(bio) == REQ_OP_DISCARD)
-		return 1;
-
-	if (bio_op(bio) == REQ_OP_SECURE_ERASE)
-		return 1;
-
-	if (bio_op(bio) == REQ_OP_WRITE_SAME)
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
+	case REQ_OP_WRITE_SAME:
+	case REQ_OP_WRITE_ZEROES:
 		return 1;
+	default:
+		break;
+	}
 
 	bio_for_each_segment(bv, bio, iter)
 		segs++;
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index f57458a6a93b..519ea2c9df61 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -159,6 +159,8 @@ enum req_opf {
 	REQ_OP_ZONE_RESET	= 6,
 	/* write the same sector many times */
 	REQ_OP_WRITE_SAME	= 7,
+	/* write the zero filled sector many times */
+	REQ_OP_WRITE_ZEROES	= 8,
 
 	REQ_OP_LAST,
 };
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 7e9d8a0895be..ebeef2b79c5a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -323,6 +323,7 @@ struct queue_limits {
 	unsigned int		max_discard_sectors;
 	unsigned int		max_hw_discard_sectors;
 	unsigned int		max_write_same_sectors;
+	unsigned int		max_write_zeroes_sectors;
 	unsigned int		discard_granularity;
 	unsigned int		discard_alignment;
 
@@ -774,6 +775,9 @@ static inline bool rq_mergeable(struct request *rq)
 	if (req_op(rq) == REQ_OP_FLUSH)
 		return false;
 
+	if (req_op(rq) == REQ_OP_WRITE_ZEROES)
+		return false;
+
 	if (rq->cmd_flags & REQ_NOMERGE_FLAGS)
 		return false;
 	if (rq->rq_flags & RQF_NOMERGE_FLAGS)
@@ -1004,6 +1008,9 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 	if (unlikely(op == REQ_OP_WRITE_SAME))
 		return q->limits.max_write_same_sectors;
 
+	if (unlikely(op == REQ_OP_WRITE_ZEROES))
+		return q->limits.max_write_zeroes_sectors;
+
 	return q->limits.max_sectors;
 }
 
@@ -1107,6 +1114,8 @@ extern void blk_queue_max_discard_sectors(struct request_queue *q,
 		unsigned int max_discard_sectors);
 extern void blk_queue_max_write_same_sectors(struct request_queue *q,
 		unsigned int max_write_same_sectors);
+extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
+		unsigned int max_write_same_sectors);
 extern void blk_queue_logical_block_size(struct request_queue *, unsigned short);
 extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
 extern void blk_queue_alignment_offset(struct request_queue *q,
@@ -1475,6 +1484,16 @@ static inline unsigned int bdev_write_same(struct block_device *bdev)
 	return 0;
 }
 
+static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev)
+{
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (q)
+		return q->limits.max_write_zeroes_sectors;
+
+	return 0;
+}
+
 static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);