1 files changed, 144 insertions, 112 deletions

diff --git a/drivers/md/md.c b/drivers/md/md.c
index aeceedfc530..681d1099a2d 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -72,6 +72,9 @@ static DECLARE_WAIT_QUEUE_HEAD(resync_wait);
 static struct workqueue_struct *md_wq;
 static struct workqueue_struct *md_misc_wq;
 
+static int remove_and_add_spares(struct mddev *mddev,
+				 struct md_rdev *this);
+
 #define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); }
 
 /*
@@ -194,21 +197,12 @@ void md_trim_bio(struct bio *bio, int offset, int size)
 	if (offset == 0 && size == bio->bi_size)
 		return;
 
-	bio->bi_sector += offset;
-	bio->bi_size = size;
-	offset <<= 9;
 	clear_bit(BIO_SEG_VALID, &bio->bi_flags);
 
-	while (bio->bi_idx < bio->bi_vcnt &&
-	       bio->bi_io_vec[bio->bi_idx].bv_len <= offset) {
-		/* remove this whole bio_vec */
-		offset -= bio->bi_io_vec[bio->bi_idx].bv_len;
-		bio->bi_idx++;
-	}
-	if (bio->bi_idx < bio->bi_vcnt) {
-		bio->bi_io_vec[bio->bi_idx].bv_offset += offset;
-		bio->bi_io_vec[bio->bi_idx].bv_len -= offset;
-	}
+	bio_advance(bio, offset << 9);
+
+	bio->bi_size = size;
+
 	/* avoid any complications with bi_idx being non-zero*/
 	if (bio->bi_idx) {
 		memmove(bio->bi_io_vec, bio->bi_io_vec+bio->bi_idx,
@@ -1564,8 +1558,8 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_
 					     sector, count, 1) == 0)
 				return -EINVAL;
 		}
-	} else if (sb->bblog_offset == 0)
-		rdev->badblocks.shift = -1;
+	} else if (sb->bblog_offset != 0)
+		rdev->badblocks.shift = 0;
 
 	if (!refdev) {
 		ret = 1;
@@ -2411,6 +2405,11 @@ static void md_update_sb(struct mddev * mddev, int force_change)
 	int nospares = 0;
 	int any_badblocks_changed = 0;
 
+	if (mddev->ro) {
+		if (force_change)
+			set_bit(MD_CHANGE_DEVS, &mddev->flags);
+		return;
+	}
 repeat:
 	/* First make sure individual recovery_offsets are correct */
 	rdev_for_each(rdev, mddev) {
@@ -2800,12 +2799,10 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len)
 		/* personality does all needed checks */
 		if (rdev->mddev->pers->hot_remove_disk == NULL)
 			return -EINVAL;
-		err = rdev->mddev->pers->
-			hot_remove_disk(rdev->mddev, rdev);
-		if (err)
-			return err;
-		sysfs_unlink_rdev(rdev->mddev, rdev);
-		rdev->raid_disk = -1;
+		clear_bit(Blocked, &rdev->flags);
+		remove_and_add_spares(rdev->mddev, rdev);
+		if (rdev->raid_disk >= 0)
+			return -EBUSY;
 		set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery);
 		md_wakeup_thread(rdev->mddev->thread);
 	} else if (rdev->mddev->pers) {
@@ -3221,7 +3218,7 @@ int md_rdev_init(struct md_rdev *rdev)
 	 * be used - I wonder if that matters
 	 */
 	rdev->badblocks.count = 0;
-	rdev->badblocks.shift = 0;
+	rdev->badblocks.shift = -1; /* disabled until explicitly enabled */
 	rdev->badblocks.page = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	seqlock_init(&rdev->badblocks.lock);
 	if (rdev->badblocks.page == NULL)
@@ -3293,9 +3290,6 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe
 			goto abort_free;
 		}
 	}
-	if (super_format == -1)
-		/* hot-add for 0.90, or non-persistent: so no badblocks */
-		rdev->badblocks.shift = -1;
 
 	return rdev;
 
@@ -4225,8 +4219,6 @@ action_show(struct mddev *mddev, char *page)
 	return sprintf(page, "%s\n", type);
 }
 
-static void reap_sync_thread(struct mddev *mddev);
-
 static ssize_t
 action_store(struct mddev *mddev, const char *page, size_t len)
 {
@@ -4241,7 +4233,7 @@ action_store(struct mddev *mddev, const char *page, size_t len)
 	if (cmd_match(page, "idle") || cmd_match(page, "frozen")) {
 		if (mddev->sync_thread) {
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-			reap_sync_thread(mddev);
+			md_reap_sync_thread(mddev);
 		}
 	} else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
 		   test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))
@@ -5279,7 +5271,7 @@ static void __md_stop_writes(struct mddev *mddev)
 	if (mddev->sync_thread) {
 		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
-		reap_sync_thread(mddev);
+		md_reap_sync_thread(mddev);
 	}
 
 	del_timer_sync(&mddev->safemode_timer);
@@ -5287,7 +5279,8 @@ static void __md_stop_writes(struct mddev *mddev)
 	bitmap_flush(mddev);
 	md_super_wait(mddev);
 
-	if (!mddev->in_sync || mddev->flags) {
+	if (mddev->ro == 0 &&
+	    (!mddev->in_sync || mddev->flags)) {
 		/* mark array as shutdown cleanly */
 		mddev->in_sync = 1;
 		md_update_sb(mddev, 1);
@@ -5810,7 +5803,7 @@ 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);
@@ -5877,6 +5870,9 @@ static int hot_remove_disk(struct mddev * mddev, dev_t dev)
 	if (!rdev)
 		return -ENXIO;
 
+	clear_bit(Blocked, &rdev->flags);
+	remove_and_add_spares(mddev, rdev);
+
 	if (rdev->raid_disk >= 0)
 		goto busy;
 
@@ -6490,6 +6486,28 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 		err = md_set_readonly(mddev, bdev);
 		goto done_unlock;
 
+	case HOT_REMOVE_DISK:
+		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;
@@ -6560,10 +6578,6 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode,
 		goto done_unlock;
 	}
 
-	case HOT_REMOVE_DISK:
-		err = hot_remove_disk(mddev, new_decode_dev(arg));
-		goto done_unlock;
-
 	case HOT_ADD_DISK:
 		err = hot_add_disk(mddev, new_decode_dev(arg));
 		goto done_unlock;
@@ -6651,15 +6665,13 @@ static int md_open(struct block_device *bdev, fmode_t mode)
 	return err;
 }
 
-static int md_release(struct gendisk *disk, fmode_t mode)
+static void md_release(struct gendisk *disk, fmode_t mode)
 {
  	struct mddev *mddev = disk->private_data;
 
 	BUG_ON(!mddev);
 	atomic_dec(&mddev->openers);
 	mddev_put(mddev);
-
-	return 0;
 }
 
 static int md_media_changed(struct gendisk *disk)
@@ -7644,14 +7656,16 @@ void md_do_sync(struct md_thread *thread)
 }
 EXPORT_SYMBOL_GPL(md_do_sync);
 
-static int remove_and_add_spares(struct mddev *mddev)
+static int remove_and_add_spares(struct mddev *mddev,
+				 struct md_rdev *this)
 {
 	struct md_rdev *rdev;
 	int spares = 0;
 	int removed = 0;
 
 	rdev_for_each(rdev, mddev)
-		if (rdev->raid_disk >= 0 &&
+		if ((this == NULL || rdev == this) &&
+		    rdev->raid_disk >= 0 &&
 		    !test_bit(Blocked, &rdev->flags) &&
 		    (test_bit(Faulty, &rdev->flags) ||
 		     ! test_bit(In_sync, &rdev->flags)) &&
@@ -7666,74 +7680,52 @@ static int remove_and_add_spares(struct mddev *mddev)
 	if (removed && mddev->kobj.sd)
 		sysfs_notify(&mddev->kobj, NULL, "degraded");
 
+	if (this)
+		goto no_add;
+
 	rdev_for_each(rdev, mddev) {
 		if (rdev->raid_disk >= 0 &&
 		    !test_bit(In_sync, &rdev->flags) &&
 		    !test_bit(Faulty, &rdev->flags))
 			spares++;
-		if (rdev->raid_disk < 0
-		    && !test_bit(Faulty, &rdev->flags)) {
-			rdev->recovery_offset = 0;
-			if (mddev->pers->
-			    hot_add_disk(mddev, rdev) == 0) {
-				if (sysfs_link_rdev(mddev, rdev))
-					/* failure here is OK */;
-				spares++;
-				md_new_event(mddev);
-				set_bit(MD_CHANGE_DEVS, &mddev->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))
+				/* failure here is OK */;
+			spares++;
+			md_new_event(mddev);
+			set_bit(MD_CHANGE_DEVS, &mddev->flags);
 		}
 	}
+no_add:
 	if (removed)
 		set_bit(MD_CHANGE_DEVS, &mddev->flags);
 	return spares;
 }
 
-static void reap_sync_thread(struct mddev *mddev)
-{
-	struct md_rdev *rdev;
-
-	/* resync has finished, collect result */
-	md_unregister_thread(&mddev->sync_thread);
-	if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
-	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
-		/* success...*/
-		/* activate any spares */
-		if (mddev->pers->spare_active(mddev)) {
-			sysfs_notify(&mddev->kobj, NULL,
-				     "degraded");
-			set_bit(MD_CHANGE_DEVS, &mddev->flags);
-		}
-	}
-	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
-	    mddev->pers->finish_reshape)
-		mddev->pers->finish_reshape(mddev);
-
-	/* If array is no-longer degraded, then any saved_raid_disk
-	 * information must be scrapped.  Also if any device is now
-	 * In_sync we must scrape the saved_raid_disk for that device
-	 * do the superblock for an incrementally recovered device
-	 * written out.
-	 */
-	rdev_for_each(rdev, mddev)
-		if (!mddev->degraded ||
-		    test_bit(In_sync, &rdev->flags))
-			rdev->saved_raid_disk = -1;
-
-	md_update_sb(mddev, 1);
-	clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
-	clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
-	clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
-	clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
-	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
-	/* flag recovery needed just to double check */
-	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-	sysfs_notify_dirent_safe(mddev->sysfs_action);
-	md_new_event(mddev);
-	if (mddev->event_work.func)
-		queue_work(md_misc_wq, &mddev->event_work);
-}
-
 /*
  * This routine is regularly called by all per-raid-array threads to
  * deal with generic issues like resync and super-block update.
@@ -7789,22 +7781,16 @@ 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;
 		}
 
@@ -7836,7 +7822,7 @@ void md_check_recovery(struct mddev *mddev)
 			goto unlock;
 		}
 		if (mddev->sync_thread) {
-			reap_sync_thread(mddev);
+			md_reap_sync_thread(mddev);
 			goto unlock;
 		}
 		/* Set RUNNING before clearing NEEDED to avoid
@@ -7867,7 +7853,7 @@ void md_check_recovery(struct mddev *mddev)
 				goto unlock;
 			set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
 			clear_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
-		} else if ((spares = remove_and_add_spares(mddev))) {
+		} else if ((spares = remove_and_add_spares(mddev, NULL))) {
 			clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 			clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 			clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
@@ -7917,6 +7903,51 @@ void md_check_recovery(struct mddev *mddev)
 	}
 }
 
+void md_reap_sync_thread(struct mddev *mddev)
+{
+	struct md_rdev *rdev;
+
+	/* resync has finished, collect result */
+	md_unregister_thread(&mddev->sync_thread);
+	if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery) &&
+	    !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
+		/* success...*/
+		/* activate any spares */
+		if (mddev->pers->spare_active(mddev)) {
+			sysfs_notify(&mddev->kobj, NULL,
+				     "degraded");
+			set_bit(MD_CHANGE_DEVS, &mddev->flags);
+		}
+	}
+	if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
+	    mddev->pers->finish_reshape)
+		mddev->pers->finish_reshape(mddev);
+
+	/* If array is no-longer degraded, then any saved_raid_disk
+	 * information must be scrapped.  Also if any device is now
+	 * In_sync we must scrape the saved_raid_disk for that device
+	 * do the superblock for an incrementally recovered device
+	 * written out.
+	 */
+	rdev_for_each(rdev, mddev)
+		if (!mddev->degraded ||
+		    test_bit(In_sync, &rdev->flags))
+			rdev->saved_raid_disk = -1;
+
+	md_update_sb(mddev, 1);
+	clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
+	clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
+	clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
+	clear_bit(MD_RECOVERY_REQUESTED, &mddev->recovery);
+	clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
+	/* flag recovery needed just to double check */
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	sysfs_notify_dirent_safe(mddev->sysfs_action);
+	md_new_event(mddev);
+	if (mddev->event_work.func)
+		queue_work(md_misc_wq, &mddev->event_work);
+}
+
 void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev)
 {
 	sysfs_notify_dirent_safe(rdev->sysfs_state);
@@ -8642,6 +8673,7 @@ EXPORT_SYMBOL(md_register_thread);
 EXPORT_SYMBOL(md_unregister_thread);
 EXPORT_SYMBOL(md_wakeup_thread);
 EXPORT_SYMBOL(md_check_recovery);
+EXPORT_SYMBOL(md_reap_sync_thread);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MD RAID framework");
 MODULE_ALIAS("md");