1 files changed, 170 insertions, 32 deletions

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 4fd19b4d6675..c91babc6aa4b 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -21,12 +21,12 @@
 #include <linux/blkdev.h>
 #include <linux/list_sort.h>
 #include <linux/iversion.h>
+#include "ctree.h"
 #include "tree-log.h"
 #include "disk-io.h"
 #include "locking.h"
 #include "print-tree.h"
 #include "backref.h"
-#include "hash.h"
 #include "compression.h"
 #include "qgroup.h"
 #include "inode-map.h"
@@ -286,7 +286,7 @@ struct walk_control {
 	 * inside it
 	 */
 	int (*process_func)(struct btrfs_root *log, struct extent_buffer *eb,
-			    struct walk_control *wc, u64 gen);
+			    struct walk_control *wc, u64 gen, int level);
 };
 
 /*
@@ -294,7 +294,7 @@ struct walk_control {
  */
 static int process_one_buffer(struct btrfs_root *log,
 			      struct extent_buffer *eb,
-			      struct walk_control *wc, u64 gen)
+			      struct walk_control *wc, u64 gen, int level)
 {
 	struct btrfs_fs_info *fs_info = log->fs_info;
 	int ret = 0;
@@ -304,7 +304,7 @@ static int process_one_buffer(struct btrfs_root *log,
 	 * pin down any logged extents, so we have to read the block.
 	 */
 	if (btrfs_fs_incompat(fs_info, MIXED_GROUPS)) {
-		ret = btrfs_read_buffer(eb, gen);
+		ret = btrfs_read_buffer(eb, gen, level, NULL);
 		if (ret)
 			return ret;
 	}
@@ -853,7 +853,6 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans,
 				      struct btrfs_inode *dir,
 				      struct btrfs_dir_item *di)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct inode *inode;
 	char *name;
 	int name_len;
@@ -887,7 +886,7 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto out;
 	else
-		ret = btrfs_run_delayed_items(trans, fs_info);
+		ret = btrfs_run_delayed_items(trans);
 out:
 	kfree(name);
 	iput(inode);
@@ -967,7 +966,9 @@ static noinline int backref_in_log(struct btrfs_root *log,
 	ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
 
 	if (key->type == BTRFS_INODE_EXTREF_KEY) {
-		if (btrfs_find_name_in_ext_backref(path, ref_objectid,
+		if (btrfs_find_name_in_ext_backref(path->nodes[0],
+						   path->slots[0],
+						   ref_objectid,
 						   name, namelen, NULL))
 			match = 1;
 
@@ -1005,7 +1006,6 @@ static inline int __add_inode_ref(struct btrfs_trans_handle *trans,
 				  u64 ref_index, char *name, int namelen,
 				  int *search_done)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret;
 	char *victim_name;
 	int victim_name_len;
@@ -1063,7 +1063,7 @@ again:
 				kfree(victim_name);
 				if (ret)
 					return ret;
-				ret = btrfs_run_delayed_items(trans, fs_info);
+				ret = btrfs_run_delayed_items(trans);
 				if (ret)
 					return ret;
 				*search_done = 1;
@@ -1134,8 +1134,7 @@ again:
 							victim_name_len);
 					if (!ret)
 						ret = btrfs_run_delayed_items(
-								  trans,
-								  fs_info);
+								  trans);
 				}
 				iput(victim_parent);
 				kfree(victim_name);
@@ -1191,7 +1190,8 @@ static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
 	read_extent_buffer(eb, *name, (unsigned long)&extref->name,
 			   *namelen);
 
-	*index = btrfs_inode_extref_index(eb, extref);
+	if (index)
+		*index = btrfs_inode_extref_index(eb, extref);
 	if (parent_objectid)
 		*parent_objectid = btrfs_inode_extref_parent(eb, extref);
 
@@ -1212,12 +1212,102 @@ static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
 
 	read_extent_buffer(eb, *name, (unsigned long)(ref + 1), *namelen);
 
-	*index = btrfs_inode_ref_index(eb, ref);
+	if (index)
+		*index = btrfs_inode_ref_index(eb, ref);
 
 	return 0;
 }
 
 /*
+ * Take an inode reference item from the log tree and iterate all names from the
+ * inode reference item in the subvolume tree with the same key (if it exists).
+ * For any name that is not in the inode reference item from the log tree, do a
+ * proper unlink of that name (that is, remove its entry from the inode
+ * reference item and both dir index keys).
+ */
+static int unlink_old_inode_refs(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root,
+				 struct btrfs_path *path,
+				 struct btrfs_inode *inode,
+				 struct extent_buffer *log_eb,
+				 int log_slot,
+				 struct btrfs_key *key)
+{
+	int ret;
+	unsigned long ref_ptr;
+	unsigned long ref_end;
+	struct extent_buffer *eb;
+
+again:
+	btrfs_release_path(path);
+	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
+	if (ret > 0) {
+		ret = 0;
+		goto out;
+	}
+	if (ret < 0)
+		goto out;
+
+	eb = path->nodes[0];
+	ref_ptr = btrfs_item_ptr_offset(eb, path->slots[0]);
+	ref_end = ref_ptr + btrfs_item_size_nr(eb, path->slots[0]);
+	while (ref_ptr < ref_end) {
+		char *name = NULL;
+		int namelen;
+		u64 parent_id;
+
+		if (key->type == BTRFS_INODE_EXTREF_KEY) {
+			ret = extref_get_fields(eb, ref_ptr, &namelen, &name,
+						NULL, &parent_id);
+		} else {
+			parent_id = key->offset;
+			ret = ref_get_fields(eb, ref_ptr, &namelen, &name,
+					     NULL);
+		}
+		if (ret)
+			goto out;
+
+		if (key->type == BTRFS_INODE_EXTREF_KEY)
+			ret = btrfs_find_name_in_ext_backref(log_eb, log_slot,
+							     parent_id, name,
+							     namelen, NULL);
+		else
+			ret = btrfs_find_name_in_backref(log_eb, log_slot, name,
+							 namelen, NULL);
+
+		if (!ret) {
+			struct inode *dir;
+
+			btrfs_release_path(path);
+			dir = read_one_inode(root, parent_id);
+			if (!dir) {
+				ret = -ENOENT;
+				kfree(name);
+				goto out;
+			}
+			ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
+						 inode, name, namelen);
+			kfree(name);
+			iput(dir);
+			if (ret)
+				goto out;
+			goto again;
+		}
+
+		kfree(name);
+		ref_ptr += namelen;
+		if (key->type == BTRFS_INODE_EXTREF_KEY)
+			ref_ptr += sizeof(struct btrfs_inode_extref);
+		else
+			ref_ptr += sizeof(struct btrfs_inode_ref);
+	}
+	ret = 0;
+ out:
+	btrfs_release_path(path);
+	return ret;
+}
+
+/*
  * replay one inode back reference item found in the log tree.
  * eb, slot and key refer to the buffer and key found in the log tree.
  * root is the destination we are replaying into, and path is for temp
@@ -1345,6 +1435,19 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 		}
 	}
 
+	/*
+	 * Before we overwrite the inode reference item in the subvolume tree
+	 * with the item from the log tree, we must unlink all names from the
+	 * parent directory that are in the subvolume's tree inode reference
+	 * item, otherwise we end up with an inconsistent subvolume tree where
+	 * dir index entries exist for a name but there is no inode reference
+	 * item with the same name.
+	 */
+	ret = unlink_old_inode_refs(trans, root, path, BTRFS_I(inode), eb, slot,
+				    key);
+	if (ret)
+		goto out;
+
 	/* finally write the back reference in the inode */
 	ret = overwrite_item(trans, root, path, eb, slot, key);
 out:
@@ -1992,7 +2095,6 @@ static noinline int check_item_in_log(struct btrfs_trans_handle *trans,
 				      struct inode *dir,
 				      struct btrfs_key *dir_key)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret;
 	struct extent_buffer *eb;
 	int slot;
@@ -2056,7 +2158,7 @@ again:
 			ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
 					BTRFS_I(inode), name, name_len);
 			if (!ret)
-				ret = btrfs_run_delayed_items(trans, fs_info);
+				ret = btrfs_run_delayed_items(trans);
 			kfree(name);
 			iput(inode);
 			if (ret)
@@ -2304,17 +2406,16 @@ out:
  * back refs).
  */
 static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
-			     struct walk_control *wc, u64 gen)
+			     struct walk_control *wc, u64 gen, int level)
 {
 	int nritems;
 	struct btrfs_path *path;
 	struct btrfs_root *root = wc->replay_dest;
 	struct btrfs_key key;
-	int level;
 	int i;
 	int ret;
 
-	ret = btrfs_read_buffer(eb, gen);
+	ret = btrfs_read_buffer(eb, gen, level, NULL);
 	if (ret)
 		return ret;
 
@@ -2431,6 +2532,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 	WARN_ON(*level >= BTRFS_MAX_LEVEL);
 
 	while (*level > 0) {
+		struct btrfs_key first_key;
+
 		WARN_ON(*level < 0);
 		WARN_ON(*level >= BTRFS_MAX_LEVEL);
 		cur = path->nodes[*level];
@@ -2443,6 +2546,7 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 
 		bytenr = btrfs_node_blockptr(cur, path->slots[*level]);
 		ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]);
+		btrfs_node_key_to_cpu(cur, &first_key, path->slots[*level]);
 		blocksize = fs_info->nodesize;
 
 		parent = path->nodes[*level];
@@ -2453,7 +2557,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 			return PTR_ERR(next);
 
 		if (*level == 1) {
-			ret = wc->process_func(root, next, wc, ptr_gen);
+			ret = wc->process_func(root, next, wc, ptr_gen,
+					       *level - 1);
 			if (ret) {
 				free_extent_buffer(next);
 				return ret;
@@ -2461,7 +2566,8 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 
 			path->slots[*level]++;
 			if (wc->free) {
-				ret = btrfs_read_buffer(next, ptr_gen);
+				ret = btrfs_read_buffer(next, ptr_gen,
+							*level - 1, &first_key);
 				if (ret) {
 					free_extent_buffer(next);
 					return ret;
@@ -2491,7 +2597,7 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 			free_extent_buffer(next);
 			continue;
 		}
-		ret = btrfs_read_buffer(next, ptr_gen);
+		ret = btrfs_read_buffer(next, ptr_gen, *level - 1, &first_key);
 		if (ret) {
 			free_extent_buffer(next);
 			return ret;
@@ -2541,7 +2647,8 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans,
 
 			root_owner = btrfs_header_owner(parent);
 			ret = wc->process_func(root, path->nodes[*level], wc,
-				 btrfs_header_generation(path->nodes[*level]));
+				 btrfs_header_generation(path->nodes[*level]),
+				 *level);
 			if (ret)
 				return ret;
 
@@ -2623,7 +2730,8 @@ static int walk_log_tree(struct btrfs_trans_handle *trans,
 	/* was the root node processed? if not, catch it here */
 	if (path->nodes[orig_level]) {
 		ret = wc->process_func(log, path->nodes[orig_level], wc,
-			 btrfs_header_generation(path->nodes[orig_level]));
+			 btrfs_header_generation(path->nodes[orig_level]),
+			 orig_level);
 		if (ret)
 			goto out;
 		if (wc->free) {
@@ -3866,6 +3974,7 @@ fill_holes:
 			ASSERT(ret == 0);
 			src = src_path->nodes[0];
 			i = 0;
+			need_find_last_extent = true;
 		}
 
 		btrfs_item_key_to_cpu(src, &key, i);
@@ -3900,6 +4009,36 @@ fill_holes:
 			break;
 		*last_extent = extent_end;
 	}
+
+	/*
+	 * Check if there is a hole between the last extent found in our leaf
+	 * and the first extent in the next leaf. If there is one, we need to
+	 * log an explicit hole so that at replay time we can punch the hole.
+	 */
+	if (ret == 0 &&
+	    key.objectid == btrfs_ino(inode) &&
+	    key.type == BTRFS_EXTENT_DATA_KEY &&
+	    i == btrfs_header_nritems(src_path->nodes[0])) {
+		ret = btrfs_next_leaf(inode->root, src_path);
+		need_find_last_extent = true;
+		if (ret > 0) {
+			ret = 0;
+		} else if (ret == 0) {
+			btrfs_item_key_to_cpu(src_path->nodes[0], &key,
+					      src_path->slots[0]);
+			if (key.objectid == btrfs_ino(inode) &&
+			    key.type == BTRFS_EXTENT_DATA_KEY &&
+			    *last_extent < key.offset) {
+				const u64 len = key.offset - *last_extent;
+
+				ret = btrfs_insert_file_extent(trans, log,
+							       btrfs_ino(inode),
+							       *last_extent, 0,
+							       0, len, 0, len,
+							       0, 0, 0);
+			}
+		}
+	}
 	/*
 	 * Need to let the callers know we dropped the path so they should
 	 * re-search.
@@ -5411,7 +5550,6 @@ out:
  * the last committed transaction
  */
 static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
-				  struct btrfs_root *root,
 				  struct btrfs_inode *inode,
 				  struct dentry *parent,
 				  const loff_t start,
@@ -5419,6 +5557,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 				  int inode_only,
 				  struct btrfs_log_ctx *ctx)
 {
+	struct btrfs_root *root = inode->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct super_block *sb;
 	struct dentry *old_parent = NULL;
@@ -5444,7 +5583,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 		goto end_no_trans;
 	}
 
-	if (root != inode->root || btrfs_root_refs(&root->root_item) == 0) {
+	if (btrfs_root_refs(&root->root_item) == 0) {
 		ret = 1;
 		goto end_no_trans;
 	}
@@ -5576,7 +5715,7 @@ end_no_trans:
  * data on disk.
  */
 int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
-			  struct btrfs_root *root, struct dentry *dentry,
+			  struct dentry *dentry,
 			  const loff_t start,
 			  const loff_t end,
 			  struct btrfs_log_ctx *ctx)
@@ -5584,8 +5723,8 @@ int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
 	struct dentry *parent = dget_parent(dentry);
 	int ret;
 
-	ret = btrfs_log_inode_parent(trans, root, BTRFS_I(d_inode(dentry)),
-			parent, start, end, LOG_INODE_ALL, ctx);
+	ret = btrfs_log_inode_parent(trans, BTRFS_I(d_inode(dentry)), parent,
+				     start, end, LOG_INODE_ALL, ctx);
 	dput(parent);
 
 	return ret;
@@ -5847,13 +5986,12 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans,
 			struct dentry *parent)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
-	struct btrfs_root *root = inode->root;
 
 	/*
 	 * this will force the logging code to walk the dentry chain
 	 * up for the file
 	 */
-	if (S_ISREG(inode->vfs_inode.i_mode))
+	if (!S_ISDIR(inode->vfs_inode.i_mode))
 		inode->last_unlink_trans = trans->transid;
 
 	/*
@@ -5864,7 +6002,7 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans,
 	    (!old_dir || old_dir->logged_trans <= fs_info->last_trans_committed))
 		return 0;
 
-	return btrfs_log_inode_parent(trans, root, inode, parent, 0,
-				      LLONG_MAX, LOG_INODE_EXISTS, NULL);
+	return btrfs_log_inode_parent(trans, inode, parent, 0, LLONG_MAX,
+				      LOG_INODE_EXISTS, NULL);
 }