1 files changed, 53 insertions, 33 deletions

diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index d620d4c53c6f..7799f4d16ce9 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -294,13 +294,16 @@ out:
  * bh passed here can be an inode block or a dir data block, depending
  * on the inode inline data flag.
  */
-static int ocfs2_check_dir_entry(struct inode * dir,
-				 struct ocfs2_dir_entry * de,
-				 struct buffer_head * bh,
+static int ocfs2_check_dir_entry(struct inode *dir,
+				 struct ocfs2_dir_entry *de,
+				 struct buffer_head *bh,
+				 char *buf,
+				 unsigned int size,
 				 unsigned long offset)
 {
 	const char *error_msg = NULL;
 	const int rlen = le16_to_cpu(de->rec_len);
+	const unsigned long next_offset = ((char *) de - buf) + rlen;
 
 	if (unlikely(rlen < OCFS2_DIR_REC_LEN(1)))
 		error_msg = "rec_len is smaller than minimal";
@@ -308,9 +311,11 @@ static int ocfs2_check_dir_entry(struct inode * dir,
 		error_msg = "rec_len % 4 != 0";
 	else if (unlikely(rlen < OCFS2_DIR_REC_LEN(de->name_len)))
 		error_msg = "rec_len is too small for name_len";
-	else if (unlikely(
-		 ((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize))
-		error_msg = "directory entry across blocks";
+	else if (unlikely(next_offset > size))
+		error_msg = "directory entry overrun";
+	else if (unlikely(next_offset > size - OCFS2_DIR_REC_LEN(1)) &&
+		 next_offset != size)
+		error_msg = "directory entry too close to end";
 
 	if (unlikely(error_msg != NULL))
 		mlog(ML_ERROR, "bad entry in directory #%llu: %s - "
@@ -352,16 +357,17 @@ static inline int ocfs2_search_dirblock(struct buffer_head *bh,
 	de_buf = first_de;
 	dlimit = de_buf + bytes;
 
-	while (de_buf < dlimit) {
+	while (de_buf < dlimit - OCFS2_DIR_MEMBER_LEN) {
 		/* this code is executed quadratically often */
 		/* do minimal checking `by hand' */
 
 		de = (struct ocfs2_dir_entry *) de_buf;
 
-		if (de_buf + namelen <= dlimit &&
+		if (de->name + namelen <= dlimit &&
 		    ocfs2_match(namelen, name, de)) {
 			/* found a match - just to be sure, do a full check */
-			if (!ocfs2_check_dir_entry(dir, de, bh, offset)) {
+			if (!ocfs2_check_dir_entry(dir, de, bh, first_de,
+						   bytes, offset)) {
 				ret = -1;
 				goto bail;
 			}
@@ -1059,26 +1065,39 @@ int ocfs2_find_entry(const char *name, int namelen,
 {
 	struct buffer_head *bh;
 	struct ocfs2_dir_entry *res_dir = NULL;
+	int ret = 0;
 
 	if (ocfs2_dir_indexed(dir))
 		return ocfs2_find_entry_dx(name, namelen, dir, lookup);
 
+	if (unlikely(i_size_read(dir) <= 0)) {
+		ret = -EFSCORRUPTED;
+		mlog_errno(ret);
+		goto out;
+	}
 	/*
 	 * The unindexed dir code only uses part of the lookup
 	 * structure, so there's no reason to push it down further
 	 * than this.
 	 */
-	if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+	if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		if (unlikely(i_size_read(dir) > dir->i_sb->s_blocksize)) {
+			ret = -EFSCORRUPTED;
+			mlog_errno(ret);
+			goto out;
+		}
 		bh = ocfs2_find_entry_id(name, namelen, dir, &res_dir);
-	else
+	} else {
 		bh = ocfs2_find_entry_el(name, namelen, dir, &res_dir);
+	}
 
 	if (bh == NULL)
 		return -ENOENT;
 
 	lookup->dl_leaf_bh = bh;
 	lookup->dl_entry = res_dir;
-	return 0;
+out:
+	return ret;
 }
 
 /*
@@ -1138,7 +1157,7 @@ static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir,
 	pde = NULL;
 	de = (struct ocfs2_dir_entry *) first_de;
 	while (i < bytes) {
-		if (!ocfs2_check_dir_entry(dir, de, bh, i)) {
+		if (!ocfs2_check_dir_entry(dir, de, bh, first_de, bytes, i)) {
 			status = -EIO;
 			mlog_errno(status);
 			goto bail;
@@ -1635,7 +1654,8 @@ int __ocfs2_add_entry(handle_t *handle,
 		/* These checks should've already been passed by the
 		 * prepare function, but I guess we can leave them
 		 * here anyway. */
-		if (!ocfs2_check_dir_entry(dir, de, insert_bh, offset)) {
+		if (!ocfs2_check_dir_entry(dir, de, insert_bh, data_start,
+					   size, offset)) {
 			retval = -ENOENT;
 			goto bail;
 		}
@@ -1774,7 +1794,8 @@ static int ocfs2_dir_foreach_blk_id(struct inode *inode,
 		}
 
 		de = (struct ocfs2_dir_entry *) (data->id_data + ctx->pos);
-		if (!ocfs2_check_dir_entry(inode, de, di_bh, ctx->pos)) {
+		if (!ocfs2_check_dir_entry(inode, de, di_bh, (char *)data->id_data,
+					   i_size_read(inode), ctx->pos)) {
 			/* On error, skip the f_pos to the end. */
 			ctx->pos = i_size_read(inode);
 			break;
@@ -1867,7 +1888,8 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode,
 		while (ctx->pos < i_size_read(inode)
 		       && offset < sb->s_blocksize) {
 			de = (struct ocfs2_dir_entry *) (bh->b_data + offset);
-			if (!ocfs2_check_dir_entry(inode, de, bh, offset)) {
+			if (!ocfs2_check_dir_entry(inode, de, bh, bh->b_data,
+						   sb->s_blocksize, offset)) {
 				/* On error, skip the f_pos to the
 				   next block. */
 				ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1;
@@ -1923,6 +1945,7 @@ int ocfs2_readdir(struct file *file, struct dir_context *ctx)
 {
 	int error = 0;
 	struct inode *inode = file_inode(file);
+	struct ocfs2_file_private *fp = file->private_data;
 	int lock_level = 0;
 
 	trace_ocfs2_readdir((unsigned long long)OCFS2_I(inode)->ip_blkno);
@@ -1943,7 +1966,7 @@ int ocfs2_readdir(struct file *file, struct dir_context *ctx)
 		goto bail_nolock;
 	}
 
-	error = ocfs2_dir_foreach_blk(inode, &file->f_version, ctx, false);
+	error = ocfs2_dir_foreach_blk(inode, &fp->cookie, ctx, false);
 
 	ocfs2_inode_unlock(inode, lock_level);
 	if (error)
@@ -2000,6 +2023,7 @@ int ocfs2_lookup_ino_from_name(struct inode *dir, const char *name,
  *
  * Return 0 if the name does not exist
  * Return -EEXIST if the directory contains the name
+ * Return -EFSCORRUPTED if found corruption
  *
  * Callers should have i_rwsem + a cluster lock on dir
  */
@@ -2013,9 +2037,12 @@ int ocfs2_check_dir_for_entry(struct inode *dir,
 	trace_ocfs2_check_dir_for_entry(
 		(unsigned long long)OCFS2_I(dir)->ip_blkno, namelen, name);
 
-	if (ocfs2_find_entry(name, namelen, dir, &lookup) == 0) {
+	ret = ocfs2_find_entry(name, namelen, dir, &lookup);
+	if (ret == 0) {
 		ret = -EEXIST;
 		mlog_errno(ret);
+	} else if (ret == -ENOENT) {
+		ret = 0;
 	}
 
 	ocfs2_free_dir_lookup_result(&lookup);
@@ -3339,7 +3366,7 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh,
 	struct super_block *sb = dir->i_sb;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 	struct ocfs2_dir_entry *de, *last_de = NULL;
-	char *de_buf, *limit;
+	char *first_de, *de_buf, *limit;
 	unsigned long offset = 0;
 	unsigned int rec_len, new_rec_len, free_space;
 
@@ -3352,14 +3379,16 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh,
 	else
 		free_space = dir->i_sb->s_blocksize - i_size_read(dir);
 
-	de_buf = di->id2.i_data.id_data;
+	first_de = di->id2.i_data.id_data;
+	de_buf = first_de;
 	limit = de_buf + i_size_read(dir);
 	rec_len = OCFS2_DIR_REC_LEN(namelen);
 
 	while (de_buf < limit) {
 		de = (struct ocfs2_dir_entry *)de_buf;
 
-		if (!ocfs2_check_dir_entry(dir, de, di_bh, offset)) {
+		if (!ocfs2_check_dir_entry(dir, de, di_bh, first_de,
+					   i_size_read(dir), offset)) {
 			ret = -ENOENT;
 			goto out;
 		}
@@ -3441,7 +3470,8 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name,
 			/* move to next block */
 			de = (struct ocfs2_dir_entry *) bh->b_data;
 		}
-		if (!ocfs2_check_dir_entry(dir, de, bh, offset)) {
+		if (!ocfs2_check_dir_entry(dir, de, bh, bh->b_data, blocksize,
+					   offset)) {
 			status = -ENOENT;
 			goto bail;
 		}
@@ -3499,16 +3529,6 @@ static int dx_leaf_sort_cmp(const void *a, const void *b)
 	return 0;
 }
 
-static void dx_leaf_sort_swap(void *a, void *b, int size)
-{
-	struct ocfs2_dx_entry *entry1 = a;
-	struct ocfs2_dx_entry *entry2 = b;
-
-	BUG_ON(size != sizeof(*entry1));
-
-	swap(*entry1, *entry2);
-}
-
 static int ocfs2_dx_leaf_same_major(struct ocfs2_dx_leaf *dx_leaf)
 {
 	struct ocfs2_dx_entry_list *dl_list = &dx_leaf->dl_list;
@@ -3769,7 +3789,7 @@ static int ocfs2_dx_dir_rebalance(struct ocfs2_super *osb, struct inode *dir,
 	 */
 	sort(dx_leaf->dl_list.de_entries, num_used,
 	     sizeof(struct ocfs2_dx_entry), dx_leaf_sort_cmp,
-	     dx_leaf_sort_swap);
+	     NULL);
 
 	ocfs2_journal_dirty(handle, dx_leaf_bh);