[PATCH] md: handle bypassing the read cache (assuming nothing fails)

Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 78 insertions, 0 deletions

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index b86ceba04f6f..269b7771a30b 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2633,6 +2633,84 @@ static int raid5_mergeable_bvec(request_queue_t *q, struct bio *bio, struct bio_
                 return max;
 }
 
+
+static int in_chunk_boundary(mddev_t *mddev, struct bio *bio)
+{
+        sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+        unsigned int chunk_sectors = mddev->chunk_size >> 9;
+        unsigned int bio_sectors = bio->bi_size >> 9;
+
+        return  chunk_sectors >=
+                ((sector & (chunk_sectors - 1)) + bio_sectors);
+}
+
+/*
+ *  The "raid5_align_endio" should check if the read succeeded and if it
+ *  did, call bio_endio on the original bio (having bio_put the new bio
+ *  first).
+ *  If the read failed..
+ */
+int raid5_align_endio(struct bio *bi, unsigned int bytes , int error)
+{
+        struct bio* raid_bi  = bi->bi_private;
+        if (bi->bi_size)
+                return 1;
+        bio_put(bi);
+        bio_endio(raid_bi, bytes, error);
+        return 0;
+}
+
+static int chunk_aligned_read(request_queue_t *q, struct bio * raid_bio)
+{
+        mddev_t *mddev = q->queuedata;
+        raid5_conf_t *conf = mddev_to_conf(mddev);
+        const unsigned int raid_disks = conf->raid_disks;
+        const unsigned int data_disks = raid_disks - 1;
+        unsigned int dd_idx, pd_idx;
+        struct bio* align_bi;
+        mdk_rdev_t *rdev;
+
+        if (!in_chunk_boundary(mddev, raid_bio)) {
+                printk("chunk_aligned_read : non aligned\n");
+                return 0;
+        }
+        /*
+         * use bio_clone to make a copy of the bio
+         */
+        align_bi = bio_clone(raid_bio, GFP_NOIO);
+        if (!align_bi)
+                return 0;
+        /*
+         *   set bi_end_io to a new function, and set bi_private to the
+         *     original bio.
+         */
+        align_bi->bi_end_io  = raid5_align_endio;
+        align_bi->bi_private = raid_bio;
+        /*
+         *      compute position
+         */
+        align_bi->bi_sector =  raid5_compute_sector(raid_bio->bi_sector,
+                                        raid_disks,
+                                        data_disks,
+                                        &dd_idx,
+                                        &pd_idx,
+                                        conf);
+
+        rcu_read_lock();
+        rdev = rcu_dereference(conf->disks[dd_idx].rdev);
+        if (rdev && test_bit(In_sync, &rdev->flags)) {
+                align_bi->bi_bdev =  rdev->bdev;
+                atomic_inc(&rdev->nr_pending);
+                rcu_read_unlock();
+                generic_make_request(align_bi);
+                return 1;
+        } else {
+                rcu_read_unlock();
+                return 0;
+        }
+}
+
+
 static int make_request(request_queue_t *q, struct bio * bi)
 {
         mddev_t *mddev = q->queuedata;