1 files changed, 228 insertions, 5 deletions

diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 4a0243cb9d97..3a9c1e046ebe 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -21,6 +21,8 @@
 #include "rcu-string.h"
 #include "dev-replace.h"
 #include "sysfs.h"
+#include "zoned.h"
+#include "block-group.h"
 
 /*
  * Device replace overview
@@ -91,6 +93,17 @@ int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
 	ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0);
 	if (ret) {
 no_valid_dev_replace_entry_found:
+		/*
+		 * We don't have a replace item or it's corrupted.  If there is
+		 * a replace target, fail the mount.
+		 */
+		if (btrfs_find_device(fs_info->fs_devices,
+				      BTRFS_DEV_REPLACE_DEVID, NULL, NULL)) {
+			btrfs_err(fs_info,
+			"found replace target device without a valid replace item");
+			ret = -EUCLEAN;
+			goto out;
+		}
 		ret = 0;
 		dev_replace->replace_state =
 			BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED;
@@ -143,16 +156,27 @@ no_valid_dev_replace_entry_found:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
-		dev_replace->srcdev = NULL;
-		dev_replace->tgtdev = NULL;
+		/*
+		 * We don't have an active replace item but if there is a
+		 * replace target, fail the mount.
+		 */
+		if (btrfs_find_device(fs_info->fs_devices,
+				      BTRFS_DEV_REPLACE_DEVID, NULL, NULL)) {
+			btrfs_err(fs_info,
+			"replace devid present without an active replace item");
+			ret = -EUCLEAN;
+		} else {
+			dev_replace->srcdev = NULL;
+			dev_replace->tgtdev = NULL;
+		}
 		break;
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
 		dev_replace->srcdev = btrfs_find_device(fs_info->fs_devices,
-						src_devid, NULL, NULL, true);
+						src_devid, NULL, NULL);
 		dev_replace->tgtdev = btrfs_find_device(fs_info->fs_devices,
 							BTRFS_DEV_REPLACE_DEVID,
-							NULL, NULL, true);
+							NULL, NULL);
 		/*
 		 * allow 'btrfs dev replace_cancel' if src/tgt device is
 		 * missing
@@ -237,6 +261,13 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 		return PTR_ERR(bdev);
 	}
 
+	if (!btrfs_check_device_zone_type(fs_info, bdev)) {
+		btrfs_err(fs_info,
+		"dev-replace: zoned type of target device mismatch with filesystem");
+		ret = -EINVAL;
+		goto error;
+	}
+
 	sync_blockdev(bdev);
 
 	list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) {
@@ -291,6 +322,10 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 	set_blocksize(device->bdev, BTRFS_BDEV_BLOCKSIZE);
 	device->fs_devices = fs_info->fs_devices;
 
+	ret = btrfs_get_dev_zone_info(device);
+	if (ret)
+		goto error;
+
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
 	list_add(&device->dev_list, &fs_info->fs_devices->devices);
 	fs_info->fs_devices->num_devices++;
@@ -425,6 +460,185 @@ static char* btrfs_dev_name(struct btrfs_device *device)
 		return rcu_str_deref(device->name);
 }
 
+static int mark_block_group_to_copy(struct btrfs_fs_info *fs_info,
+				    struct btrfs_device *src_dev)
+{
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	struct btrfs_key found_key;
+	struct btrfs_root *root = fs_info->dev_root;
+	struct btrfs_dev_extent *dev_extent = NULL;
+	struct btrfs_block_group *cache;
+	struct btrfs_trans_handle *trans;
+	int ret = 0;
+	u64 chunk_offset;
+
+	/* Do not use "to_copy" on non zoned filesystem for now */
+	if (!btrfs_is_zoned(fs_info))
+		return 0;
+
+	mutex_lock(&fs_info->chunk_mutex);
+
+	/* Ensure we don't have pending new block group */
+	spin_lock(&fs_info->trans_lock);
+	while (fs_info->running_transaction &&
+	       !list_empty(&fs_info->running_transaction->dev_update_list)) {
+		spin_unlock(&fs_info->trans_lock);
+		mutex_unlock(&fs_info->chunk_mutex);
+		trans = btrfs_attach_transaction(root);
+		if (IS_ERR(trans)) {
+			ret = PTR_ERR(trans);
+			mutex_lock(&fs_info->chunk_mutex);
+			if (ret == -ENOENT) {
+				spin_lock(&fs_info->trans_lock);
+				continue;
+			} else {
+				goto unlock;
+			}
+		}
+
+		ret = btrfs_commit_transaction(trans);
+		mutex_lock(&fs_info->chunk_mutex);
+		if (ret)
+			goto unlock;
+
+		spin_lock(&fs_info->trans_lock);
+	}
+	spin_unlock(&fs_info->trans_lock);
+
+	path = btrfs_alloc_path();
+	if (!path) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
+	path->reada = READA_FORWARD;
+	path->search_commit_root = 1;
+	path->skip_locking = 1;
+
+	key.objectid = src_dev->devid;
+	key.type = BTRFS_DEV_EXTENT_KEY;
+	key.offset = 0;
+
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		goto free_path;
+	if (ret > 0) {
+		if (path->slots[0] >=
+		    btrfs_header_nritems(path->nodes[0])) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				goto free_path;
+			if (ret > 0) {
+				ret = 0;
+				goto free_path;
+			}
+		} else {
+			ret = 0;
+		}
+	}
+
+	while (1) {
+		struct extent_buffer *leaf = path->nodes[0];
+		int slot = path->slots[0];
+
+		btrfs_item_key_to_cpu(leaf, &found_key, slot);
+
+		if (found_key.objectid != src_dev->devid)
+			break;
+
+		if (found_key.type != BTRFS_DEV_EXTENT_KEY)
+			break;
+
+		if (found_key.offset < key.offset)
+			break;
+
+		dev_extent = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent);
+
+		chunk_offset = btrfs_dev_extent_chunk_offset(leaf, dev_extent);
+
+		cache = btrfs_lookup_block_group(fs_info, chunk_offset);
+		if (!cache)
+			goto skip;
+
+		spin_lock(&cache->lock);
+		cache->to_copy = 1;
+		spin_unlock(&cache->lock);
+
+		btrfs_put_block_group(cache);
+
+skip:
+		ret = btrfs_next_item(root, path);
+		if (ret != 0) {
+			if (ret > 0)
+				ret = 0;
+			break;
+		}
+	}
+
+free_path:
+	btrfs_free_path(path);
+unlock:
+	mutex_unlock(&fs_info->chunk_mutex);
+
+	return ret;
+}
+
+bool btrfs_finish_block_group_to_copy(struct btrfs_device *srcdev,
+				      struct btrfs_block_group *cache,
+				      u64 physical)
+{
+	struct btrfs_fs_info *fs_info = cache->fs_info;
+	struct extent_map *em;
+	struct map_lookup *map;
+	u64 chunk_offset = cache->start;
+	int num_extents, cur_extent;
+	int i;
+
+	/* Do not use "to_copy" on non zoned filesystem for now */
+	if (!btrfs_is_zoned(fs_info))
+		return true;
+
+	spin_lock(&cache->lock);
+	if (cache->removed) {
+		spin_unlock(&cache->lock);
+		return true;
+	}
+	spin_unlock(&cache->lock);
+
+	em = btrfs_get_chunk_map(fs_info, chunk_offset, 1);
+	ASSERT(!IS_ERR(em));
+	map = em->map_lookup;
+
+	num_extents = cur_extent = 0;
+	for (i = 0; i < map->num_stripes; i++) {
+		/* We have more device extent to copy */
+		if (srcdev != map->stripes[i].dev)
+			continue;
+
+		num_extents++;
+		if (physical == map->stripes[i].physical)
+			cur_extent = i;
+	}
+
+	free_extent_map(em);
+
+	if (num_extents > 1 && cur_extent < num_extents - 1) {
+		/*
+		 * Has more stripes on this device. Keep this block group
+		 * readonly until we finish all the stripes.
+		 */
+		return false;
+	}
+
+	/* Last stripe on this device */
+	spin_lock(&cache->lock);
+	cache->to_copy = 0;
+	spin_unlock(&cache->lock);
+
+	return true;
+}
+
 static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 		const char *tgtdev_name, u64 srcdevid, const char *srcdev_name,
 		int read_src)
@@ -466,6 +680,10 @@ static int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 	if (ret)
 		return ret;
 
+	ret = mark_block_group_to_copy(fs_info, src_device);
+	if (ret)
+		return ret;
+
 	down_write(&dev_replace->rwsem);
 	switch (dev_replace->replace_state) {
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
@@ -681,13 +899,16 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	 * flush all outstanding I/O and inode extent mappings before the
 	 * copy operation is declared as being finished
 	 */
-	ret = btrfs_start_delalloc_roots(fs_info, U64_MAX);
+	ret = btrfs_start_delalloc_roots(fs_info, LONG_MAX, false);
 	if (ret) {
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 		return ret;
 	}
 	btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
 
+	if (!scrub_ret)
+		btrfs_reada_remove_dev(src_device);
+
 	/*
 	 * We have to use this loop approach because at this point src_device
 	 * has to be available for transaction commit to complete, yet new
@@ -696,6 +917,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	while (1) {
 		trans = btrfs_start_transaction(root, 0);
 		if (IS_ERR(trans)) {
+			btrfs_reada_undo_remove_dev(src_device);
 			mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 			return PTR_ERR(trans);
 		}
@@ -746,6 +968,7 @@ error:
 		up_write(&dev_replace->rwsem);
 		mutex_unlock(&fs_info->chunk_mutex);
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+		btrfs_reada_undo_remove_dev(src_device);
 		btrfs_rm_dev_replace_blocked(fs_info);
 		if (tgt_device)
 			btrfs_destroy_dev_replace_tgtdev(tgt_device);