md: fix handling of array level takeover that re-arranges devices.

Most array level changes leave the list of devices largely unchanged,
possibly causing one at the end to become redundant.
However conversions between RAID0 and RAID10 need to renumber
all devices (except 0).

This renumbering is currently being done in the ->run method when the
new personality takes over.  However this is too late as the common
code in md.c might already have invalidated some of the devices if
they had a ->raid_disk number that appeared to high.

Moving it into the ->takeover method is too early as the array is
still active at that time and wrong ->raid_disk numbers could cause
confusion.

So add a ->new_raid_disk field to mdk_rdev_s and use it to communicate
the new raid_disk number.
Now the common code knows exactly which devices need to be renumbered,
and which can be invalidated, and can do it all at a convenient time
when the array is suspend.
It can also update some symlinks in sysfs which previously were not be
updated correctly.

Reported-by: Maciej Trela <maciej.trela@intel.com>
Signed-off-by: NeilBrown <neilb@suse.de>

1 files changed, 30 insertions, 5 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4edcda8f4869..4869128bf742 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -3001,6 +3001,9 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
                 return -EINVAL;
         }
 
+        list_for_each_entry(rdev, &mddev->disks, same_set)
+                rdev->new_raid_disk = rdev->raid_disk;
+
         /* ->takeover must set new_* and/or delta_disks
          * if it succeeds, and may set them when it fails.
          */
@@ -3051,13 +3054,35 @@ level_store(mddev_t *mddev, const char *buf, size_t len)
                 mddev->safemode = 0;
         }
 
-        module_put(mddev->pers->owner);
-        /* Invalidate devices that are now superfluous */
-        list_for_each_entry(rdev, &mddev->disks, same_set)
-                if (rdev->raid_disk >= mddev->raid_disks) {
-                        rdev->raid_disk = -1;
+        list_for_each_entry(rdev, &mddev->disks, same_set) {
+                char nm[20];
+                if (rdev->raid_disk < 0)
+                        continue;
+                if (rdev->new_raid_disk > mddev->raid_disks)
+                        rdev->new_raid_disk = -1;
+                if (rdev->new_raid_disk == rdev->raid_disk)
+                        continue;
+                sprintf(nm, "rd%d", rdev->raid_disk);
+                sysfs_remove_link(&mddev->kobj, nm);
+        }
+        list_for_each_entry(rdev, &mddev->disks, same_set) {
+                if (rdev->raid_disk < 0)
+                        continue;
+                if (rdev->new_raid_disk == rdev->raid_disk)
+                        continue;
+                rdev->raid_disk = rdev->new_raid_disk;
+                if (rdev->raid_disk < 0)
                         clear_bit(In_sync, &rdev->flags);
+                else {
+                        char nm[20];
+                        sprintf(nm, "rd%d", rdev->raid_disk);
+                        if(sysfs_create_link(&mddev->kobj, &rdev->kobj, nm))
+                                printk("md: cannot register %s for %s after level change\n",
+                                       nm, mdname(mddev));
                 }
+        }
+
+        module_put(mddev->pers->owner);
         mddev->pers = pers;
         mddev->private = priv;
         strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));