md/raid10: always set reshape_safe when initializing reshape_position.

'reshape_position' tracks where in the reshape we have reached.
'reshape_safe' tracks where in the reshape we have safely recorded
in the metadata.

These are compared to determine when to update the metadata.
So it is important that reshape_safe is initialised properly.
Currently it isn't.  When starting a reshape from the beginning
it usually has the correct value by luck.  But when reducing the
number of devices in a RAID10, it has the wrong value and this leads
to the metadata not being updated correctly.
This can lead to corruption if the reshape is not allowed to complete.

This patch is suitable for any -stable kernel which supports RAID10
reshape, which is 3.5 and later.

Fixes: 3ea7daa5d7fd ("md/raid10: add reshape support")
Cc: stable@vger.kernel.org (v3.5+ please wait for -final to be out for 2 weeks)
Signed-off-by: NeilBrown <neilb@suse.com>

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 940f2f3654617918d8eef951262c3ca120ab83ce..38c58e19cfce3d7bdea554b26474080a88e02cca 100644 (file)
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3556,6 +3556,7 @@ static struct r10conf *setup_conf(struct mddev *mddev)
                        /* far_copies must be 1 */
                        conf->prev.stride = conf->dev_sectors;
        }
+       conf->reshape_safe = conf->reshape_progress;
        spin_lock_init(&conf->device_lock);
        INIT_LIST_HEAD(&conf->retry_list);
 
@@ -3760,7 +3761,6 @@ static int run(struct mddev *mddev)
                }
                conf->offset_diff = min_offset_diff;
 
-               conf->reshape_safe = conf->reshape_progress;
                clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
                clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
                set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
@@ -4103,6 +4103,7 @@ static int raid10_start_reshape(struct mddev *mddev)
                conf->reshape_progress = size;
        } else
                conf->reshape_progress = 0;
+       conf->reshape_safe = conf->reshape_progress;
        spin_unlock_irq(&conf->device_lock);
 
        if (mddev->delta_disks && mddev->bitmap) {
@@ -4170,6 +4171,7 @@ abort:
                rdev->new_data_offset = rdev->data_offset;
        smp_wmb();
        conf->reshape_progress = MaxSector;
+       conf->reshape_safe = MaxSector;
        mddev->reshape_position = MaxSector;
        spin_unlock_irq(&conf->device_lock);
        return ret;
@@ -4524,6 +4526,7 @@ static void end_reshape(struct r10conf *conf)
        md_finish_reshape(conf->mddev);
        smp_wmb();
        conf->reshape_progress = MaxSector;
+       conf->reshape_safe = MaxSector;
        spin_unlock_irq(&conf->device_lock);
 
        /* read-ahead size must cover two whole stripes, which is