From c8dc9c654794a765ca61baed07f84ed8aaa7ca8c Mon Sep 17 00:00:00 2001 From: Joe Lawrence Date: Thu, 21 Feb 2013 13:28:09 +1100 Subject: 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 Acked-by: "Martin K. Petersen" Signed-off-by: NeilBrown --- drivers/md/raid1.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'drivers/md/raid1.c') diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index d5bddfc4010e..6e5d5a5f9cb4 100644 --- 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; -- cgit v1.2.3 From ee0b0244030434cdda26777bfb98962447e080cd Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 25 Feb 2013 12:38:29 +1100 Subject: md/raid1,raid10: fix deadlock with freeze_array() When raid1/raid10 needs to fix a read error, it first drains all pending requests by calling freeze_array(). This calls flush_pending_writes() if it needs to sleep, but some writes may be pending in a per-process plug rather than in the per-array request queue. When raid1{,0}_unplug() moves the request from the per-process plug to the per-array request queue (from which flush_pending_writes() can flush them), it needs to wake up freeze_array(), or freeze_array() will never flush them and so it will block forever. So add the requires wake_up() calls. This bug was introduced by commit f54a9d0e59c4bea3db733921ca9147612a6f292c for raid1 and a similar commit for RAID10, and so has been present since linux-3.6. As the bug causes a deadlock I believe this fix is suitable for -stable. Cc: stable@vger.kernel.org (3.6.y 3.7.y 3.8.y) Reported-by: Tregaron Bayly Tested-by: Tregaron Bayly Signed-off-by: NeilBrown --- drivers/md/raid1.c | 1 + drivers/md/raid10.c | 1 + 2 files changed, 2 insertions(+) (limited to 'drivers/md/raid1.c') diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 6e5d5a5f9cb4..fd86b372692d 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -967,6 +967,7 @@ static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule) bio_list_merge(&conf->pending_bio_list, &plug->pending); conf->pending_count += plug->pending_cnt; spin_unlock_irq(&conf->device_lock); + wake_up(&conf->wait_barrier); md_wakeup_thread(mddev->thread); kfree(plug); return; diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 61ed150bd0cf..77b562d18a90 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1119,6 +1119,7 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule) bio_list_merge(&conf->pending_bio_list, &plug->pending); conf->pending_count += plug->pending_cnt; spin_unlock_irq(&conf->device_lock); + wake_up(&conf->wait_barrier); md_wakeup_thread(mddev->thread); kfree(plug); return; -- cgit v1.2.3