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>

1 files changed, 69 insertions, 0 deletions

diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index a09ead19f9c5..273121c0eb80 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -315,3 +315,72 @@ int blkdev_issue_flush(struct block_device *bdev, sector_t *error_sector)
         return ret;
 }
 EXPORT_SYMBOL(blkdev_issue_flush);
+
+static void blkdev_discard_end_io(struct bio *bio, int err)
+{
+        if (err) {
+                if (err == -EOPNOTSUPP)
+                        set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
+                clear_bit(BIO_UPTODATE, &bio->bi_flags);
+        }
+
+        bio_put(bio);
+}
+
+/**
+ * blkdev_issue_discard - queue a discard
+ * @bdev:       blockdev to issue discard for
+ * @sector:     start sector
+ * @nr_sects:   number of sectors to discard
+ *
+ * Description:
+ *    Issue a discard request for the sectors in question. Does not wait.
+ */
+int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
+                         unsigned nr_sects)
+{
+        struct request_queue *q;
+        struct bio *bio;
+        int ret = 0;
+
+        if (bdev->bd_disk == NULL)
+                return -ENXIO;
+
+        q = bdev_get_queue(bdev);
+        if (!q)
+                return -ENXIO;
+
+        if (!q->prepare_discard_fn)
+                return -EOPNOTSUPP;
+
+        while (nr_sects && !ret) {
+                bio = bio_alloc(GFP_KERNEL, 0);
+                if (!bio)
+                        return -ENOMEM;
+
+                bio->bi_end_io = blkdev_discard_end_io;
+                bio->bi_bdev = bdev;
+
+                bio->bi_sector = sector;
+
+                if (nr_sects > q->max_hw_sectors) {
+                        bio->bi_size = q->max_hw_sectors << 9;
+                        nr_sects -= q->max_hw_sectors;
+                        sector += q->max_hw_sectors;
+                } else {
+                        bio->bi_size = nr_sects << 9;
+                        nr_sects = 0;
+                }
+                bio_get(bio);
+                submit_bio(WRITE_DISCARD, bio);
+
+                /* Check if it failed immediately */
+                if (bio_flagged(bio, BIO_EOPNOTSUPP))
+                        ret = -EOPNOTSUPP;
+                else if (!bio_flagged(bio, BIO_UPTODATE))
+                        ret = -EIO;
+                bio_put(bio);
+        }
+        return ret;
+}
+EXPORT_SYMBOL(blkdev_issue_discard);