md: fix problem when adding device to read-only array with bitmap.

If an array is started degraded, and then the missing device
is found it can be re-added and a minimal bitmap-based recovery
will bring it fully up-to-date.

If the array is read-only a recovery would not be allowed.
But also if the array is read-only and the missing device was
present very recently, then there could be no need for any
recovery at all, so we simply include the device in the read-only
array without any recovery.

However... if the missing device was removed a little longer ago
it could be missing some updates, but if a bitmap is present it will
be conditionally accepted pending a bitmap-based update.  We don't
currently detect this case properly and will include that old
device into the read-only array with no recovery even though it really
needs a recovery.

This patch keeps track of whether a bitmap-based-recovery is really
needed or not in the new Bitmap_sync rdev flag.  If that is set,
then the device will not be added to a read-only array.

Cc: Andrei Warkentin <andreiw@vmware.com>
Fixes: d70ed2e4fafdbef0800e73942482bb075c21578b
Cc: stable@vger.kernel.org (3.2+)
Signed-off-by: NeilBrown <neilb@suse.de>

2 files changed, 18 insertions, 3 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index e60cebf3f519..2a456a5d59a8 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1087,6 +1087,7 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
         rdev->raid_disk = -1;
         clear_bit(Faulty, &rdev->flags);
         clear_bit(In_sync, &rdev->flags);
+        clear_bit(Bitmap_sync, &rdev->flags);
         clear_bit(WriteMostly, &rdev->flags);
 
         if (mddev->raid_disks == 0) {
@@ -1165,6 +1166,8 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev)
                  */
                 if (ev1 < mddev->bitmap->events_cleared)
                         return 0;
+                if (ev1 < mddev->events)
+                        set_bit(Bitmap_sync, &rdev->flags);
         } else {
                 if (ev1 < mddev->events)
                         /* just a hot-add of a new device, leave raid_disk at -1 */
@@ -1573,6 +1576,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
         rdev->raid_disk = -1;
         clear_bit(Faulty, &rdev->flags);
         clear_bit(In_sync, &rdev->flags);
+        clear_bit(Bitmap_sync, &rdev->flags);
         clear_bit(WriteMostly, &rdev->flags);
 
         if (mddev->raid_disks == 0) {
@@ -1655,6 +1659,8 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev)
                  */
                 if (ev1 < mddev->bitmap->events_cleared)
                         return 0;
+                if (ev1 < mddev->events)
+                        set_bit(Bitmap_sync, &rdev->flags);
         } else {
                 if (ev1 < mddev->events)
                         /* just a hot-add of a new device, leave raid_disk at -1 */
@@ -2798,6 +2804,7 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len)
                 else
                         rdev->saved_raid_disk = -1;
                 clear_bit(In_sync, &rdev->flags);
+                clear_bit(Bitmap_sync, &rdev->flags);
                 err = rdev->mddev->pers->
                         hot_add_disk(rdev->mddev, rdev);
                 if (err) {
@@ -5770,6 +5777,7 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info)
                             info->raid_disk < mddev->raid_disks) {
                                 rdev->raid_disk = info->raid_disk;
                                 set_bit(In_sync, &rdev->flags);
+                                clear_bit(Bitmap_sync, &rdev->flags);
                         } else
                                 rdev->raid_disk = -1;
                 } else
@@ -7716,7 +7724,8 @@ static int remove_and_add_spares(struct mddev *mddev,
                 if (test_bit(Faulty, &rdev->flags))
                         continue;
                 if (mddev->ro &&
-                    rdev->saved_raid_disk < 0)
+                    ! (rdev->saved_raid_disk >= 0 &&
+                       !test_bit(Bitmap_sync, &rdev->flags)))
                         continue;
 
                 rdev->recovery_offset = 0;
@@ -7797,9 +7806,12 @@ void md_check_recovery(struct mddev *mddev)
                          * As we only add devices that are already in-sync,
                          * we can activate the spares immediately.
                          */
-                        clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
                         remove_and_add_spares(mddev, NULL);
-                        mddev->pers->spare_active(mddev);
+                        /* There is no thread, but we need to call
+                         * ->spare_active and clear saved_raid_disk
+                         */
+                        md_reap_sync_thread(mddev);
+                        clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
                         goto unlock;
                 }
 
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 2f5cc8a7ef3e..0095ec84ffc7 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -129,6 +129,9 @@ struct md_rdev {
 enum flag_bits {
         Faulty,                 /* device is known to have a fault */
         In_sync,                /* device is in_sync with rest of array */
+        Bitmap_sync,            /* ..actually, not quite In_sync.  Need a
+                                 * bitmap-based recovery to get fully in sync
+                                 */
         Unmerged,               /* device is being added to array and should
                                  * be considerred for bvec_merge_fn but not
                                  * yet for actual IO