From: Martin Brandenburg Date: Fri, 8 Apr 2016 17:33:21 +0000 (-0400) Subject: orangefs: strncpy -> strscpy X-Git-Tag: v4.9.8~2334^2~2 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=2eacea74cc465edc23ce5a4dd5c2213008ac3a05;p=platform%2Fkernel%2Flinux-rpi3.git orangefs: strncpy -> strscpy It would have been possible for a rogue client-core to send in a symlink target which is not NUL terminated. This returns EIO if the client-core gives us corrupt data. Leave debugfs and superblock code as is for now. Other dcache.c and namei.c strncpy instances are safe because ORANGEFS_NAME_MAX = NAME_MAX + 1; there is always enough space for a name plus a NUL byte. Signed-off-by: Martin Brandenburg Signed-off-by: Mike Marshall --- diff --git a/fs/orangefs/orangefs-utils.c b/fs/orangefs/orangefs-utils.c index 40f5163..f392a6a 100644 --- a/fs/orangefs/orangefs-utils.c +++ b/fs/orangefs/orangefs-utils.c @@ -315,9 +315,13 @@ int orangefs_inode_getattr(struct inode *inode, int new, int size) inode->i_size = (loff_t)strlen(new_op-> downcall.resp.getattr.link_target); orangefs_inode->blksize = (1 << inode->i_blkbits); - strlcpy(orangefs_inode->link_target, + ret = strscpy(orangefs_inode->link_target, new_op->downcall.resp.getattr.link_target, ORANGEFS_NAME_MAX); + if (ret == -E2BIG) { + ret = -EIO; + goto out; + } inode->i_link = orangefs_inode->link_target; } break;