[CIFS] fix small memory leak in an error path in new posix mkdir (5a07cdf8) · Commits · 戴 / test

There is a small memory leak in fs/cifs/inode.c::cifs_mkdir(). Storage for 'pInfo' is allocated with kzalloc(), but if the call to CIFSPOSIXCreate(...) happens to return 0 and pInfo->Type == -1, then we'll jump to the 'mkdir_get_info' label without freeing the storage allocated for 'pInfo'. This patch adds a kfree() call to free the storage just before jumping to the label, thus getting rid of the leak. Signed-off-by:

Jesper Juhl <jesper.juhl@gmail.com> Signed-off-by:

Steve French <sfrench@us.ibm.com>

fs/cifs/inode.c

+6 −2

Original line number	Diff line number	Diff line
		@@ -930,8 +930,10 @@ int cifs_mkdir(struct inode inode, struct dentry direntry, int mode)
		d_drop(direntry);
		} else {
		int obj_type;
		if (pInfo->Type == -1) /* no return info - go query */
		if (pInfo->Type == -1) /* no return info - go query */ {
		kfree(pInfo);
		goto mkdir_get_info;
		}
		/*BB check (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID ) to see if need
		to set uid/gid */
		inc_nlink(inode);
		@@ -941,8 +943,10 @@ int cifs_mkdir(struct inode inode, struct dentry direntry, int mode)
		direntry->d_op = &cifs_dentry_ops;

		newinode = new_inode(inode->i_sb);
		if (newinode == NULL)
		if (newinode == NULL) {
		kfree(pInfo);
		goto mkdir_get_info;
		}
		/* Is an i_ino of zero legal? */
		/* Are there sanity checks we can use to ensure that
		the server is really filling in that field? */

Admin message