block: Implement support for WRITE SAME

The WRITE SAME command supported on some SCSI devices allows the same
block to be efficiently replicated throughout a block range. Only a
single logical block is transferred from the host and the storage device
writes the same data to all blocks described by the I/O.

This patch implements support for WRITE SAME in the block layer. The
blkdev_issue_write_same() function can be used by filesystems and block
drivers to replicate a buffer across a block range. This can be used to
efficiently initialize software RAID devices, etc.

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

3 files changed, 36 insertions, 1 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index e54305cacc98..820e7aaad4fd 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -399,6 +399,9 @@ static inline bool bio_is_rw(struct bio *bio)
         if (!bio_has_data(bio))
                 return false;
 
+        if (bio->bi_rw & REQ_WRITE_SAME)
+                return false;
+
         return true;
 }
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 1b229664f573..cdf11191e645 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -147,6 +147,7 @@ enum rq_flag_bits {
         __REQ_PRIO,             /* boost priority in cfq */
         __REQ_DISCARD,          /* request to discard sectors */
         __REQ_SECURE,           /* secure discard (used with __REQ_DISCARD) */
+        __REQ_WRITE_SAME,       /* write same block many times */
 
         __REQ_NOIDLE,           /* don't anticipate more IO after this one */
         __REQ_FUA,              /* forced unit access */
@@ -185,13 +186,15 @@ enum rq_flag_bits {
 #define REQ_META                (1 << __REQ_META)
 #define REQ_PRIO                (1 << __REQ_PRIO)
 #define REQ_DISCARD             (1 << __REQ_DISCARD)
+#define REQ_WRITE_SAME          (1 << __REQ_WRITE_SAME)
 #define REQ_NOIDLE              (1 << __REQ_NOIDLE)
 
 #define REQ_FAILFAST_MASK \
         (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
 #define REQ_COMMON_MASK \
         (REQ_WRITE | REQ_FAILFAST_MASK | REQ_SYNC | REQ_META | REQ_PRIO | \
-         REQ_DISCARD | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | REQ_SECURE)
+         REQ_DISCARD | REQ_WRITE_SAME | REQ_NOIDLE | REQ_FLUSH | REQ_FUA | \
+         REQ_SECURE)
 #define REQ_CLONE_MASK          REQ_COMMON_MASK
 
 /* This mask is used for both bio and request merge checking */
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 90f7abe8f183..1756001210d2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -270,6 +270,7 @@ struct queue_limits {
         unsigned int            io_min;
         unsigned int            io_opt;
         unsigned int            max_discard_sectors;
+        unsigned int            max_write_same_sectors;
         unsigned int            discard_granularity;
         unsigned int            discard_alignment;
 
@@ -614,9 +615,20 @@ static inline bool blk_check_merge_flags(unsigned int flags1,
         if ((flags1 & REQ_SECURE) != (flags2 & REQ_SECURE))
                 return false;
 
+        if ((flags1 & REQ_WRITE_SAME) != (flags2 & REQ_WRITE_SAME))
+                return false;
+
         return true;
 }
 
+static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b)
+{
+        if (bio_data(a) == bio_data(b))
+                return true;
+
+        return false;
+}
+
 /*
  * q->prep_rq_fn return values
  */
@@ -818,6 +830,9 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
         if (unlikely(cmd_flags & REQ_DISCARD))
                 return q->limits.max_discard_sectors;
 
+        if (unlikely(cmd_flags & REQ_WRITE_SAME))
+                return q->limits.max_write_same_sectors;
+
         return q->limits.max_sectors;
 }
 
@@ -886,6 +901,8 @@ extern void blk_queue_max_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
 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_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,
@@ -1016,6 +1033,8 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
 extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *);
 extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
                 sector_t nr_sects, gfp_t gfp_mask, unsigned long flags);
+extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector,
+                sector_t nr_sects, gfp_t gfp_mask, struct page *page);
 extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
                         sector_t nr_sects, gfp_t gfp_mask);
 static inline int sb_issue_discard(struct super_block *sb, sector_t block,
@@ -1193,6 +1212,16 @@ static inline unsigned int bdev_discard_zeroes_data(struct block_device *bdev)
         return queue_discard_zeroes_data(bdev_get_queue(bdev));
 }
 
+static inline unsigned int bdev_write_same(struct block_device *bdev)
+{
+        struct request_queue *q = bdev_get_queue(bdev);
+
+        if (q)
+                return q->limits.max_write_same_sectors;
+
+        return 0;
+}
+
 static inline int queue_dma_alignment(struct request_queue *q)
 {
         return q ? q->dma_alignment : 511;