X-Git-Url: http://git.cascardo.eti.br/?a=blobdiff_plain;f=fs%2Fbtrfs%2Frelocation.c;h=27480ef9813cd4af9a3713b1ed6fcd64157147bd;hb=62b99540a1d91e46422f0e04de50fc723812c421;hp=08ef890deca69fdce7a35d26bcf5ae45d9f67d8b;hpb=84bf51ea9d3495119244b62cc3d07fe4d7bdc1e9;p=cascardo%2Flinux.git

diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 08ef890deca6..27480ef9813c 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -31,6 +31,7 @@
 #include "async-thread.h"
 #include "free-space-cache.h"
 #include "inode-map.h"
+#include "qgroup.h"
 
 /*
  * backref_node, mapping_node and tree_block start with this
@@ -235,12 +236,12 @@ static void backref_cache_cleanup(struct backref_cache *cache)
 	cache->last_trans = 0;
 
 	for (i = 0; i < BTRFS_MAX_LEVEL; i++)
-		BUG_ON(!list_empty(&cache->pending[i]));
-	BUG_ON(!list_empty(&cache->changed));
-	BUG_ON(!list_empty(&cache->detached));
-	BUG_ON(!RB_EMPTY_ROOT(&cache->rb_root));
-	BUG_ON(cache->nr_nodes);
-	BUG_ON(cache->nr_edges);
+		ASSERT(list_empty(&cache->pending[i]));
+	ASSERT(list_empty(&cache->changed));
+	ASSERT(list_empty(&cache->detached));
+	ASSERT(RB_EMPTY_ROOT(&cache->rb_root));
+	ASSERT(!cache->nr_nodes);
+	ASSERT(!cache->nr_edges);
 }
 
 static struct backref_node *alloc_backref_node(struct backref_cache *cache)
@@ -668,8 +669,8 @@ int find_inline_backref(struct extent_buffer *leaf, int slot,
  * roots of b-trees that reference the tree block.
  *
  * the basic idea of this function is check backrefs of a given block
- * to find upper level blocks that refernece the block, and then check
- * bakcrefs of these upper level blocks recursively. the recursion stop
+ * to find upper level blocks that reference the block, and then check
+ * backrefs of these upper level blocks recursively. the recursion stop
  * when tree root is reached or backrefs for the block is cached.
  *
  * NOTE: if we find backrefs for a block are cached, we know backrefs
@@ -1160,7 +1161,7 @@ out:
 			if (!RB_EMPTY_NODE(&upper->rb_node))
 				continue;
 
-			/* Add this guy's upper edges to the list to proces */
+			/* Add this guy's upper edges to the list to process */
 			list_for_each_entry(edge, &upper->upper, list[LOWER])
 				list_add_tail(&edge->list[UPPER], &list);
 			if (list_empty(&upper->upper))
@@ -1171,8 +1172,12 @@ out:
 			lower = list_entry(useless.next,
 					   struct backref_node, list);
 			list_del_init(&lower->list);
+			if (lower == node)
+				node = NULL;
 			free_backref_node(cache, lower);
 		}
+
+		free_backref_node(cache, node);
 		return ERR_PTR(err);
 	}
 	ASSERT(!node || !node->detached);
@@ -1719,7 +1724,7 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 					   btrfs_header_owner(leaf),
 					   key.objectid, key.offset);
 		if (ret) {
-			btrfs_abort_transaction(trans, root, ret);
+			btrfs_abort_transaction(trans, ret);
 			break;
 		}
 
@@ -1727,7 +1732,7 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 					parent, btrfs_header_owner(leaf),
 					key.objectid, key.offset);
 		if (ret) {
-			btrfs_abort_transaction(trans, root, ret);
+			btrfs_abort_transaction(trans, ret);
 			break;
 		}
 	}
@@ -2396,7 +2401,7 @@ again:
 		}
 
 		/*
-		 * we keep the old last snapshod transid in rtranid when we
+		 * we keep the old last snapshot transid in rtranid when we
 		 * created the relocation tree.
 		 */
 		last_snap = btrfs_root_rtransid(&reloc_root->root_item);
@@ -2418,7 +2423,7 @@ again:
 	}
 out:
 	if (ret) {
-		btrfs_std_error(root->fs_info, ret, NULL);
+		btrfs_handle_fs_error(root->fs_info, ret, NULL);
 		if (!list_empty(&reloc_roots))
 			free_reloc_roots(&reloc_roots);
 
@@ -2604,25 +2609,28 @@ static int reserve_metadata_space(struct btrfs_trans_handle *trans,
 
 	trans->block_rsv = rc->block_rsv;
 	rc->reserved_bytes += num_bytes;
+
+	/*
+	 * We are under a transaction here so we can only do limited flushing.
+	 * If we get an enospc just kick back -EAGAIN so we know to drop the
+	 * transaction and try to refill when we can flush all the things.
+	 */
 	ret = btrfs_block_rsv_refill(root, rc->block_rsv, num_bytes,
-				BTRFS_RESERVE_FLUSH_ALL);
+				BTRFS_RESERVE_FLUSH_LIMIT);
 	if (ret) {
-		if (ret == -EAGAIN) {
-			tmp = rc->extent_root->nodesize *
-				RELOCATION_RESERVED_NODES;
-			while (tmp <= rc->reserved_bytes)
-				tmp <<= 1;
-			/*
-			 * only one thread can access block_rsv at this point,
-			 * so we don't need hold lock to protect block_rsv.
-			 * we expand more reservation size here to allow enough
-			 * space for relocation and we will return eailer in
-			 * enospc case.
-			 */
-			rc->block_rsv->size = tmp + rc->extent_root->nodesize *
-					      RELOCATION_RESERVED_NODES;
-		}
-		return ret;
+		tmp = rc->extent_root->nodesize * RELOCATION_RESERVED_NODES;
+		while (tmp <= rc->reserved_bytes)
+			tmp <<= 1;
+		/*
+		 * only one thread can access block_rsv at this point,
+		 * so we don't need hold lock to protect block_rsv.
+		 * we expand more reservation size here to allow enough
+		 * space for relocation and we will return eailer in
+		 * enospc case.
+		 */
+		rc->block_rsv->size = tmp + rc->extent_root->nodesize *
+			RELOCATION_RESERVED_NODES;
+		return -EAGAIN;
 	}
 
 	return 0;
@@ -2814,7 +2822,7 @@ static void mark_block_processed(struct reloc_control *rc,
 				 u64 bytenr, u32 blocksize)
 {
 	set_extent_bits(&rc->processed_blocks, bytenr, bytenr + blocksize - 1,
-			EXTENT_DIRTY, GFP_NOFS);
+			EXTENT_DIRTY);
 }
 
 static void __mark_block_processed(struct reloc_control *rc,
@@ -3182,7 +3190,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 		    page_start + offset == cluster->boundary[nr]) {
 			set_extent_bits(&BTRFS_I(inode)->io_tree,
 					page_start, page_end,
-					EXTENT_BOUNDARY, GFP_NOFS);
+					EXTENT_BOUNDARY);
 			nr++;
 		}
 
@@ -3871,6 +3879,7 @@ static noinline_for_stack
 int prepare_to_relocate(struct reloc_control *rc)
 {
 	struct btrfs_trans_handle *trans;
+	int ret;
 
 	rc->block_rsv = btrfs_alloc_block_rsv(rc->extent_root,
 					      BTRFS_BLOCK_RSV_TEMP);
@@ -3885,6 +3894,11 @@ int prepare_to_relocate(struct reloc_control *rc)
 	rc->reserved_bytes = 0;
 	rc->block_rsv->size = rc->extent_root->nodesize *
 			      RELOCATION_RESERVED_NODES;
+	ret = btrfs_block_rsv_refill(rc->extent_root,
+				     rc->block_rsv, rc->block_rsv->size,
+				     BTRFS_RESERVE_FLUSH_ALL);
+	if (ret)
+		return ret;
 
 	rc->create_reloc_tree = 1;
 	set_reloc_control(rc);
@@ -3903,6 +3917,90 @@ int prepare_to_relocate(struct reloc_control *rc)
 	return 0;
 }
 
+/*
+ * Qgroup fixer for data chunk relocation.
+ * The data relocation is done in the following steps
+ * 1) Copy data extents into data reloc tree
+ * 2) Create tree reloc tree(special snapshot) for related subvolumes
+ * 3) Modify file extents in tree reloc tree
+ * 4) Merge tree reloc tree with original fs tree, by swapping tree blocks
+ *
+ * The problem is, data and tree reloc tree are not accounted to qgroup,
+ * and 4) will only info qgroup to track tree blocks change, not file extents
+ * in the tree blocks.
+ *
+ * The good news is, related data extents are all in data reloc tree, so we
+ * only need to info qgroup to track all file extents in data reloc tree
+ * before commit trans.
+ */
+static int qgroup_fix_relocated_data_extents(struct btrfs_trans_handle *trans,
+					     struct reloc_control *rc)
+{
+	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
+	struct inode *inode = rc->data_inode;
+	struct btrfs_root *data_reloc_root = BTRFS_I(inode)->root;
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	int ret = 0;
+
+	if (!fs_info->quota_enabled)
+		return 0;
+
+	/*
+	 * Only for stage where we update data pointers the qgroup fix is
+	 * valid.
+	 * For MOVING_DATA stage, we will miss the timing of swapping tree
+	 * blocks, and won't fix it.
+	 */
+	if (!(rc->stage == UPDATE_DATA_PTRS && rc->extents_found))
+		return 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+	key.objectid = btrfs_ino(inode);
+	key.type = BTRFS_EXTENT_DATA_KEY;
+	key.offset = 0;
+
+	ret = btrfs_search_slot(NULL, data_reloc_root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+
+	lock_extent(&BTRFS_I(inode)->io_tree, 0, (u64)-1);
+	while (1) {
+		struct btrfs_file_extent_item *fi;
+
+		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
+		if (key.objectid > btrfs_ino(inode))
+			break;
+		if (key.type != BTRFS_EXTENT_DATA_KEY)
+			goto next;
+		fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
+				    struct btrfs_file_extent_item);
+		if (btrfs_file_extent_type(path->nodes[0], fi) !=
+				BTRFS_FILE_EXTENT_REG)
+			goto next;
+		ret = btrfs_qgroup_insert_dirty_extent(trans, fs_info,
+			btrfs_file_extent_disk_bytenr(path->nodes[0], fi),
+			btrfs_file_extent_disk_num_bytes(path->nodes[0], fi),
+			GFP_NOFS);
+		if (ret < 0)
+			break;
+next:
+		ret = btrfs_next_item(data_reloc_root, path);
+		if (ret < 0)
+			break;
+		if (ret > 0) {
+			ret = 0;
+			break;
+		}
+	}
+	unlock_extent(&BTRFS_I(inode)->io_tree, 0 , (u64)-1);
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
 static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
 {
 	struct rb_root blocks = RB_ROOT;
@@ -4059,8 +4157,7 @@ restart:
 	}
 
 	btrfs_release_path(path);
-	clear_extent_bits(&rc->processed_blocks, 0, (u64)-1, EXTENT_DIRTY,
-			  GFP_NOFS);
+	clear_extent_bits(&rc->processed_blocks, 0, (u64)-1, EXTENT_DIRTY);
 
 	if (trans) {
 		btrfs_end_transaction_throttle(trans, rc->extent_root);
@@ -4090,10 +4187,16 @@ restart:
 
 	/* get rid of pinned extents */
 	trans = btrfs_join_transaction(rc->extent_root);
-	if (IS_ERR(trans))
+	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
-	else
-		btrfs_commit_transaction(trans, rc->extent_root);
+		goto out_free;
+	}
+	err = qgroup_fix_relocated_data_extents(trans, rc);
+	if (err < 0) {
+		btrfs_abort_transaction(trans, err);
+		goto out_free;
+	}
+	btrfs_commit_transaction(trans, rc->extent_root);
 out_free:
 	btrfs_free_block_rsv(rc->extent_root, rc->block_rsv);
 	btrfs_free_path(path);
@@ -4254,12 +4357,11 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start)
 	btrfs_info(extent_root->fs_info, "relocating block group %llu flags %llu",
 	       rc->block_group->key.objectid, rc->block_group->flags);
 
-	ret = btrfs_start_delalloc_roots(fs_info, 0, -1);
-	if (ret < 0) {
-		err = ret;
-		goto out;
-	}
-	btrfs_wait_ordered_roots(fs_info, -1);
+	btrfs_wait_block_group_reservations(rc->block_group);
+	btrfs_wait_nocow_writers(rc->block_group);
+	btrfs_wait_ordered_roots(fs_info, -1,
+				 rc->block_group->key.objectid,
+				 rc->block_group->key.offset);
 
 	while (1) {
 		mutex_lock(&fs_info->cleaner_mutex);
@@ -4457,10 +4559,16 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 	unset_reloc_control(rc);
 
 	trans = btrfs_join_transaction(rc->extent_root);
-	if (IS_ERR(trans))
+	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
-	else
-		err = btrfs_commit_transaction(trans, rc->extent_root);
+		goto out_free;
+	}
+	err = qgroup_fix_relocated_data_extents(trans, rc);
+	if (err < 0) {
+		btrfs_abort_transaction(trans, err);
+		goto out_free;
+	}
+	err = btrfs_commit_transaction(trans, rc->extent_root);
 out_free:
 	kfree(rc);
 out:
@@ -4592,7 +4700,7 @@ int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
 
 /*
  * called before creating snapshot. it calculates metadata reservation
- * requried for relocating tree blocks in the snapshot
+ * required for relocating tree blocks in the snapshot
  */
 void btrfs_reloc_pre_snapshot(struct btrfs_pending_snapshot *pending,
 			      u64 *bytes_to_reserve)
@@ -4645,7 +4753,7 @@ int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans,
 	if (rc->merge_reloc_tree) {
 		ret = btrfs_block_rsv_migrate(&pending->block_rsv,
 					      rc->block_rsv,
-					      rc->nodes_relocated);
+					      rc->nodes_relocated, 1);
 		if (ret)
 			return ret;
 	}