md/raid1,5,10: Disable WRITE SAME until a recovery strategy is in place

commit 5026d7a9b2f3eb1f9bda66c18ac6bc3036ec9020 upstream.

There are cases where the kernel will believe that the WRITE SAME
command is supported by a block device which does not, in fact,
support WRITE SAME.  This currently happens for SATA drivers behind a
SAS controller, but there are probably a hundred other ways that can
happen, including drive firmware bugs.

After receiving an error for WRITE SAME the block layer will retry the
request as a plain write of zeroes, but mdraid will consider the
failure as fatal and consider the drive failed.  This has the effect
that all the mirrors containing a specific set of data are each
offlined in very rapid succession resulting in data loss.

However, just bouncing the request back up to the block layer isn't
ideal either, because the whole initial request-retry sequence should
be inside the write bitmap fence, which probably means that md needs
to do its own conversion of WRITE SAME to write zero.

Until the failure scenario has been sorted out, disable WRITE SAME for
raid1, raid5, and raid10.

[neilb: added raid5]

This patch is appropriate for any -stable since 3.7 when write_same
support was added.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 8430c0d6cc8e479b9e6627230334937a12aef158..754f95fd9888691c8665d07d1d5aeb9ceb225291 100644 (file)
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -2837,8 +2837,8 @@ static int run(struct mddev *mddev)
                return PTR_ERR(conf);
 
        if (mddev->queue)
-               blk_queue_max_write_same_sectors(mddev->queue,
-                                                mddev->chunk_sectors);
+               blk_queue_max_write_same_sectors(mddev->queue, 0);
+
        rdev_for_each(rdev, mddev) {
                if (!mddev->gendisk)
                        continue;

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index bc5b444b683d580e7088a60078109fea66cb657f..f17cadd062d02351c337002828d63f054c89c020 100644 (file)
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3635,8 +3635,7 @@ 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_max_write_same_sectors(mddev->queue, 0);
                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);

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index f4e87bfc7567923944d2fce13da4c7d636479566..251ab6449cec571008ebcca8abccd080a793a31f 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5457,7 +5457,7 @@ static int run(struct mddev *mddev)
                if (mddev->major_version == 0 &&
                    mddev->minor_version > 90)
                        rdev->recovery_offset = reshape_offset;
-                       
+
                if (rdev->recovery_offset < reshape_offset) {
                        /* We need to check old and new layout */
                        if (!only_parity(rdev->raid_disk,
@@ -5580,6 +5580,8 @@ static int run(struct mddev *mddev)
                 */
                mddev->queue->limits.discard_zeroes_data = 0;
 
+               blk_queue_max_write_same_sectors(mddev->queue, 0);
+
                rdev_for_each(rdev, mddev) {
                        disk_stack_limits(mddev->gendisk, rdev->bdev,
                                          rdev->data_offset << 9);