md: Allow devices to be re-added to a read-only array.

When assembling an array incrementally we might want to make
it device available when "enough" devices are present, but maybe
not "all" devices are present.
If the remaining devices appear before the array is actually used,
they should be added transparently.

We do this by using the "read-auto" mode where the array acts like
it is read-only until a write request arrives.

Current an add-device request switches a read-auto array to active.
This means that only one device can be added after the array is first
made read-auto.  This isn't a problem for RAID5, but is not ideal for
RAID6 or RAID10.
Also we don't really want to switch the array to read-auto at all
when re-adding a device as this doesn't really imply any change.

So:
 - remove the "md_update_sb()" call from add_new_disk().  This isn't
   really needed as just adding a disk doesn't require a metadata
   update.  Instead, just set MD_CHANGE_DEVS.  This will effect a
   metadata update soon enough, once the array is not read-only.

 - Allow the ADD_NEW_DISK ioctl to succeed without activating a
   read-auto array, providing the MD_DISK_SYNC flag is set.
   In this case, the device will be rejected if it cannot be added
   with the correct device number, or has an incorrect event count.

 - Teach remove_and_add_spares() to be careful about adding spares
   when the array is read-only (or read-mostly) - only add devices
   that are thought to be in-sync, and only do it if the array is
   in-sync itself.

 - In md_check_recovery, use remove_and_add_spares in the read-only
   case, rather than open coding just the 'remove' part of it.
Reported-by: Martin Wilck <mwilck@arcor.de>
Signed-off-by: NeilBrown <neilb@suse.de>

drivers/md/md.c

@@ -5816,7 +5816,7 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info)
 		else
 			sysfs_notify_dirent_safe(rdev->sysfs_state);
 
-		md_update_sb(mddev, 1);
+		set_bit(MD_CHANGE_DEVS, &mddev->flags);
 		if (mddev->degraded)
 			set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
@@ -6503,6 +6503,24 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 		err = hot_remove_disk(mddev, new_decode_dev(arg));
 		goto done_unlock;
 
+	case ADD_NEW_DISK:
+		/* We can support ADD_NEW_DISK on read-only arrays
+		 * on if we are re-adding a preexisting device.
+		 * So require mddev->pers and MD_DISK_SYNC.
+		 */
+		if (mddev->pers) {
+			mdu_disk_info_t info;
+			if (copy_from_user(&info, argp, sizeof(info)))
+				err = -EFAULT;
+			else if (!(info.state & (1<<MD_DISK_SYNC)))
+				/* Need to clear read-only for this */
+				break;
+			else
+				err = add_new_disk(mddev, &info);
+			goto done_unlock;
+		}
+		break;
+
 	case BLKROSET:
 		if (get_user(ro, (int __user *)(arg))) {
 			err = -EFAULT;
@@ -7685,9 +7703,29 @@ static int remove_and_add_spares(struct mddev *mddev,
 		    !test_bit(In_sync, &rdev->flags) &&
 		    !test_bit(Faulty, &rdev->flags))
 			spares++;
-		if (rdev->raid_disk < 0
-		    && !test_bit(Faulty, &rdev->flags)) {
+		if (rdev->raid_disk >= 0)
+			continue;
+		if (test_bit(Faulty, &rdev->flags))
+			continue;
+		if (mddev->ro &&
+		    rdev->saved_raid_disk < 0)
+			continue;
+
 		rdev->recovery_offset = 0;
+		if (rdev->saved_raid_disk >= 0 && mddev->in_sync) {
+			spin_lock_irq(&mddev->write_lock);
+			if (mddev->in_sync)
+				/* OK, this device, which is in_sync,
+				 * will definitely be noticed before
+				 * the next write, so recovery isn't
+				 * needed.
+				 */
+				rdev->recovery_offset = mddev->recovery_cp;
+			spin_unlock_irq(&mddev->write_lock);
+		}
+		if (mddev->ro && rdev->recovery_offset != MaxSector)
+			/* not safe to add this disk now */
+			continue;
 		if (mddev->pers->
 		    hot_add_disk(mddev, rdev) == 0) {
 			if (sysfs_link_rdev(mddev, rdev))
@@ -7697,7 +7735,6 @@ static int remove_and_add_spares(struct mddev *mddev,
 			set_bit(MD_CHANGE_DEVS, &mddev->flags);
 		}
 	}
-	}
 no_add:
 	if (removed)
 		set_bit(MD_CHANGE_DEVS, &mddev->flags);
@@ -7804,22 +7841,16 @@ void md_check_recovery(struct mddev *mddev)
 		int spares = 0;
 
 		if (mddev->ro) {
-			/* Only thing we do on a ro array is remove
-			 * failed devices.
+			/* On a read-only array we can:
+			 * - remove failed devices
+			 * - add already-in_sync devices if the array itself
+			 *   is in-sync.
+			 * As we only add devices that are already in-sync,
+			 * we can activate the spares immediately.
 			 */
-			struct md_rdev *rdev;
-			rdev_for_each(rdev, mddev)
-				if (rdev->raid_disk >= 0 &&
-				    !test_bit(Blocked, &rdev->flags) &&
-				    test_bit(Faulty, &rdev->flags) &&
-				    atomic_read(&rdev->nr_pending)==0) {
-					if (mddev->pers->hot_remove_disk(
-						    mddev, rdev) == 0) {
-						sysfs_unlink_rdev(mddev, rdev);
-						rdev->raid_disk = -1;
-					}
-				}
 			clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+			remove_and_add_spares(mddev, NULL);
+			mddev->pers->spare_active(mddev);
 			goto unlock;
 		}