Add 'discard' request handling

Some block devices benefit from a hint that they can forget the contents
of certain sectors. Add basic support for this to the block core, along
with a 'blkdev_issue_discard()' helper function which issues such
requests.

The caller doesn't get to provide an end_io functio, since
blkdev_issue_discard() will automatically split the request up into
multiple bios if appropriate. Neither does the function wait for
completion -- it's expected that callers won't care about when, or even
_if_, the request completes. It's only a hint to the device anyway. By
definition, the file system doesn't _care_ about these sectors any more.

[With feedback from OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> and
Jens Axboe <jens.axboe@oracle.com]

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

3 files changed, 24 insertions, 3 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 17f1fbdb31bf..1fdfc5621c83 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -149,6 +149,8 @@ struct bio {
  * bit 2 -- barrier
  * bit 3 -- fail fast, don't want low level driver retries
  * bit 4 -- synchronous I/O hint: the block layer will unplug immediately
+ * bit 5 -- metadata request
+ * bit 6 -- discard sectors
  */
 #define BIO_RW          0       /* Must match RW in req flags (blkdev.h) */
 #define BIO_RW_AHEAD    1       /* Must match FAILFAST in req flags */
@@ -156,6 +158,7 @@ struct bio {
 #define BIO_RW_FAILFAST 3
 #define BIO_RW_SYNC     4
 #define BIO_RW_META     5
+#define BIO_RW_DISCARD  6
 
 /*
  * upper 16 bits of bi_rw define the io priority of this bio
@@ -186,13 +189,14 @@ struct bio {
 #define bio_rw_ahead(bio)       ((bio)->bi_rw & (1 << BIO_RW_AHEAD))
 #define bio_rw_meta(bio)        ((bio)->bi_rw & (1 << BIO_RW_META))
 #define bio_empty_barrier(bio)  (bio_barrier(bio) && !bio_has_data(bio))
+#define bio_discard(bio)        ((bio)->bi_rw & (1 << BIO_RW_DISCARD))
 
 static inline unsigned int bio_cur_sectors(struct bio *bio)
 {
         if (bio->bi_vcnt)
                 return bio_iovec(bio)->bv_len >> 9;
-
-        return 0;
+        else /* dataless requests such as discard */
+                return bio->bi_size >> 9;
 }
 
 static inline void *bio_data(struct bio *bio)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index e0ba018f5e88..26ececbbebe2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -89,6 +89,7 @@ enum {
 enum rq_flag_bits {
         __REQ_RW,               /* not set, read. set, write */
         __REQ_FAILFAST,         /* no low level driver retries */
+        __REQ_DISCARD,          /* request to discard sectors */
         __REQ_SORTED,           /* elevator knows about this request */
         __REQ_SOFTBARRIER,      /* may not be passed by ioscheduler */
         __REQ_HARDBARRIER,      /* may not be passed by drive either */
@@ -111,6 +112,7 @@ enum rq_flag_bits {
 };
 
 #define REQ_RW          (1 << __REQ_RW)
+#define REQ_DISCARD     (1 << __REQ_DISCARD)
 #define REQ_FAILFAST    (1 << __REQ_FAILFAST)
 #define REQ_SORTED      (1 << __REQ_SORTED)
 #define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER)
@@ -252,6 +254,7 @@ typedef void (request_fn_proc) (struct request_queue *q);
 typedef int (make_request_fn) (struct request_queue *q, struct bio *bio);
 typedef int (prep_rq_fn) (struct request_queue *, struct request *);
 typedef void (unplug_fn) (struct request_queue *);
+typedef int (prepare_discard_fn) (struct request_queue *, struct request *);
 
 struct bio_vec;
 struct bvec_merge_data {
@@ -307,6 +310,7 @@ struct request_queue
         make_request_fn         *make_request_fn;
         prep_rq_fn              *prep_rq_fn;
         unplug_fn               *unplug_fn;
+        prepare_discard_fn      *prepare_discard_fn;
         merge_bvec_fn           *merge_bvec_fn;
         prepare_flush_fn        *prepare_flush_fn;
         softirq_done_fn         *softirq_done_fn;
@@ -546,6 +550,7 @@ enum {
 #define blk_sorted_rq(rq)       ((rq)->cmd_flags & REQ_SORTED)
 #define blk_barrier_rq(rq)      ((rq)->cmd_flags & REQ_HARDBARRIER)
 #define blk_fua_rq(rq)          ((rq)->cmd_flags & REQ_FUA)
+#define blk_discard_rq(rq)      ((rq)->cmd_flags & REQ_DISCARD)
 #define blk_bidi_rq(rq)         ((rq)->next_rq != NULL)
 #define blk_empty_barrier(rq)   (blk_barrier_rq(rq) && blk_fs_request(rq) && !(rq)->hard_nr_sectors)
 /* rq->queuelist of dequeued request must be list_empty() */
@@ -796,6 +801,7 @@ extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *);
 extern void blk_queue_dma_alignment(struct request_queue *, int);
 extern void blk_queue_update_dma_alignment(struct request_queue *, int);
 extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *);
+extern void blk_queue_set_discard(struct request_queue *, prepare_discard_fn *);
 extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev);
 extern int blk_queue_ordered(struct request_queue *, unsigned, prepare_flush_fn *);
 extern int blk_do_ordered(struct request_queue *, struct request **);
@@ -837,6 +843,16 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt,
 }
 
 extern int blkdev_issue_flush(struct block_device *, sector_t *);
+extern int blkdev_issue_discard(struct block_device *, sector_t sector,
+                                unsigned nr_sects);
+
+static inline int sb_issue_discard(struct super_block *sb,
+                                   sector_t block, unsigned nr_blocks)
+{
+        block <<= (sb->s_blocksize_bits - 9);
+        nr_blocks <<= (sb->s_blocksize_bits - 9);
+        return blkdev_issue_discard(sb->s_bdev, block, nr_blocks);
+}
 
 /*
 * command filter functions
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 580b513668fe..eb0131319134 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -86,7 +86,8 @@ extern int dir_notify_enable;
 #define READ_META       (READ | (1 << BIO_RW_META))
 #define WRITE_SYNC      (WRITE | (1 << BIO_RW_SYNC))
 #define SWRITE_SYNC     (SWRITE | (1 << BIO_RW_SYNC))
-#define WRITE_BARRIER   ((1 << BIO_RW) | (1 << BIO_RW_BARRIER))
+#define WRITE_BARRIER   (WRITE | (1 << BIO_RW_BARRIER))
+#define WRITE_DISCARD   (WRITE | (1 << BIO_RW_DISCARD))
 
 #define SEL_IN          1
 #define SEL_OUT         2