On Saturday 02 November 2024 20:33:31 Sasha Levin wrote: > This is a note to let you know that I've just added the patch titled > > cifs: Fix creating native symlinks pointing to current or parent directory > > to the 6.1-stable tree which can be found at: > http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary > > The filename of the patch is: > cifs-fix-creating-native-symlinks-pointing-to-curren.patch > and it can be found in the queue-6.1 subdirectory. > > If you, or anyone else, feels it should not be added to the stable tree, > please let <stable@xxxxxxxxxxxxxxx> know about it. > > > > commit 79461b2972a2357206773ebdcfe078f37297fa35 > Author: Pali Rohár <pali@xxxxxxxxxx> > Date: Sat Oct 5 16:02:56 2024 +0200 > > cifs: Fix creating native symlinks pointing to current or parent directory > > [ Upstream commit 63271b7d569fbe924bccc7dadc17d3d07a4e5f7a ] > > Calling 'ln -s . symlink' or 'ln -s .. symlink' creates symlink pointing to > some object name which ends with U+F029 unicode codepoint. This is because > trailing dot in the object name is replaced by non-ASCII unicode codepoint. > > So Linux SMB client currently is not able to create native symlink pointing > to current or parent directory on Windows SMB server which can be read by > either on local Windows server or by any other SMB client which does not > implement compatible-reverse character replacement. > > Fix this problem in cifsConvertToUTF16() function which is doing that > character replacement. Function comment already says that it does not need > to handle special cases '.' and '..', but after introduction of native > symlinks in reparse point form, this handling is needed. > > Note that this change depends on the previous change > "cifs: Improve creating native symlinks pointing to directory". > > Signed-off-by: Pali Rohár <pali@xxxxxxxxxx> > Signed-off-by: Steve French <stfrench@xxxxxxxxxxxxx> > Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx> Hello Sasha, this change alone in 6.1 would not work without the dependent change as mention in the commit message. So if you are not planning to include dependent change then please drop this change from 6.1 stable tree. > diff --git a/fs/smb/client/cifs_unicode.c b/fs/smb/client/cifs_unicode.c > index e7582dd791794..53f862a9c03cc 100644 > --- a/fs/smb/client/cifs_unicode.c > +++ b/fs/smb/client/cifs_unicode.c > @@ -485,10 +485,21 @@ cifsConvertToUTF16(__le16 *target, const char *source, int srclen, > /** > * Remap spaces and periods found at the end of every > * component of the path. The special cases of '.' and > - * '..' do not need to be dealt with explicitly because > - * they are addressed in namei.c:link_path_walk(). > + * '..' are need to be handled because of symlinks. > + * They are treated as non-end-of-string to avoid > + * remapping and breaking symlinks pointing to . or .. > **/ > - if ((i == srclen - 1) || (source[i+1] == '\\')) > + if ((i == 0 || source[i-1] == '\\') && > + source[i] == '.' && > + (i == srclen-1 || source[i+1] == '\\')) > + end_of_string = false; /* "." case */ > + else if (i >= 1 && > + (i == 1 || source[i-2] == '\\') && > + source[i-1] == '.' && > + source[i] == '.' && > + (i == srclen-1 || source[i+1] == '\\')) > + end_of_string = false; /* ".." case */ > + else if ((i == srclen - 1) || (source[i+1] == '\\')) > end_of_string = true; > else > end_of_string = false;
