md: raid1,10: Handle REQ_WRITE_SAME flag in write bios

Set mddev queue's max_write_same_sectors to its chunk_sector value (before
disk_stack_limits merges the underlying disk limits.)  With that in place,
be sure to handle writes coming down from the block layer that have the
REQ_WRITE_SAME flag set.  That flag needs to be copied into any newly cloned
write bio.

Signed-off-by: Joe Lawrence <joe.lawrence@stratus.com>
Acked-by: "Martin K. Petersen" <martin.petersen@oracle.com>
Signed-off-by: NeilBrown <neilb@suse.de>

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index d5bddfc..6e5d5a5 100644 (file)
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1000,6 +1000,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
        const unsigned long do_flush_fua = (bio->bi_rw & (REQ_FLUSH | REQ_FUA));
        const unsigned long do_discard = (bio->bi_rw
                                          & (REQ_DISCARD | REQ_SECURE));
+       const unsigned long do_same = (bio->bi_rw & REQ_WRITE_SAME);
        struct md_rdev *blocked_rdev;
        struct blk_plug_cb *cb;
        struct raid1_plug_cb *plug = NULL;
@@ -1301,7 +1302,8 @@ read_again:
                                   conf->mirrors[i].rdev->data_offset);
                mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
                mbio->bi_end_io = raid1_end_write_request;
-               mbio->bi_rw = WRITE | do_flush_fua | do_sync | do_discard;
+               mbio->bi_rw =
+                       WRITE | do_flush_fua | do_sync | do_discard | do_same;
                mbio->bi_private = r1_bio;
 
                atomic_inc(&r1_bio->remaining);
@@ -2818,6 +2820,9 @@ static int run(struct mddev *mddev)
        if (IS_ERR(conf))
                return PTR_ERR(conf);
 
+       if (mddev->queue)
+               blk_queue_max_write_same_sectors(mddev->queue,
+                                                mddev->chunk_sectors);
        rdev_for_each(rdev, mddev) {
                if (!mddev->gendisk)
                        continue;

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 64d4824..1a74c12 100644 (file)
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1105,6 +1105,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
        const unsigned long do_fua = (bio->bi_rw & REQ_FUA);
        const unsigned long do_discard = (bio->bi_rw
                                          & (REQ_DISCARD | REQ_SECURE));
+       const unsigned long do_same = (bio->bi_rw & REQ_WRITE_SAME);
        unsigned long flags;
        struct md_rdev *blocked_rdev;
        struct blk_plug_cb *cb;
@@ -1460,7 +1461,8 @@ retry_write:
                                                              rdev));
                        mbio->bi_bdev = rdev->bdev;
                        mbio->bi_end_io = raid10_end_write_request;
-                       mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
+                       mbio->bi_rw =
+                               WRITE | do_sync | do_fua | do_discard | do_same;
                        mbio->bi_private = r10_bio;
 
                        atomic_inc(&r10_bio->remaining);
@@ -1502,7 +1504,8 @@ retry_write:
                                                   r10_bio, rdev));
                        mbio->bi_bdev = rdev->bdev;
                        mbio->bi_end_io = raid10_end_write_request;
-                       mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
+                       mbio->bi_rw =
+                               WRITE | do_sync | do_fua | do_discard | do_same;
                        mbio->bi_private = r10_bio;
 
                        atomic_inc(&r10_bio->remaining);
@@ -3569,6 +3572,8 @@ static int run(struct mddev *mddev)
        if (mddev->queue) {
                blk_queue_max_discard_sectors(mddev->queue,
                                              mddev->chunk_sectors);
+               blk_queue_max_write_same_sectors(mddev->queue,
+                                                mddev->chunk_sectors);
                blk_queue_io_min(mddev->queue, chunk_size);
                if (conf->geo.raid_disks % conf->geo.near_copies)
                        blk_queue_io_opt(mddev->queue, chunk_size * conf->geo.raid_disks);