linux-kernel - Re: [PATCH v1] staging: exfat: fix multiple definition error of `rename

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <CAFd5g446ippuyNN5ej0hEiz1Rv9hqpke55pE0en15U=gG3zX0A@mail.gmail.com>
Date:   Thu, 5 Dec 2019 10:31:00 -0800
From:   Brendan Higgins <brendanhiggins@...gle.com>
To:     David Gow <davidgow@...gle.com>
Cc:     valdis.kletnieks@...edu,
        linux-fsdevel <linux-fsdevel@...r.kernel.org>,
        devel@...verdev.osuosl.org,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        Greg Kroah-Hartman <gregkh@...uxfoundation.org>
Subject: Re: [PATCH v1] staging: exfat: fix multiple definition error of `rename_file'

On Thu, Dec 5, 2019 at 9:51 AM David Gow <davidgow@...gle.com> wrote:
>
> On Wed, Dec 4, 2019 at 3:46 PM Brendan Higgins
> <brendanhiggins@...gle.com> wrote:
> >
> > `rename_file' was exported but not properly namespaced causing a
> > multiple definition error because `rename_file' is already defined in
> > fs/hostfs/hostfs_user.c:
> >
> > ld: drivers/staging/exfat/exfat_core.o: in function `rename_file':
> > drivers/staging/exfat/exfat_core.c:2327: multiple definition of
> > `rename_file'; fs/hostfs/hostfs_user.o:fs/hostfs/hostfs_user.c:350:
> > first defined here
> > make: *** [Makefile:1077: vmlinux] Error 1
> >
> > This error can be reproduced on ARCH=um by selecting:
> >
> > CONFIG_EXFAT_FS=y
> > CONFIG_HOSTFS=y
> >
> > Add a namespace prefix exfat_* to fix this error.
> >
> > Reported-by: Brendan Higgins <brendanhiggins@...gle.com>
> > Signed-off-by: Brendan Higgins <brendanhiggins@...gle.com>
> > Cc: Valdis Kletnieks <valdis.kletnieks@...edu>
> > Cc: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
>
> Tested-by: David Gow <davidgow@...gle.com>
> Reviewed-by: David Gow <davidgow@...gle.com>
>
> This works for me: I was able to reproduce the compile error without
> this patch, and successfully compile a UML kernel and mount an exfat
> fs after applying it.
>
> > ---
> >  drivers/staging/exfat/exfat.h       | 4 ++--
> >  drivers/staging/exfat/exfat_core.c  | 4 ++--
> >  drivers/staging/exfat/exfat_super.c | 4 ++--
> >  3 files changed, 6 insertions(+), 6 deletions(-)
> >
> > diff --git a/drivers/staging/exfat/exfat.h b/drivers/staging/exfat/exfat.h
> > index 2aac1e000977e..51c665a924b76 100644
> > --- a/drivers/staging/exfat/exfat.h
> > +++ b/drivers/staging/exfat/exfat.h
> > @@ -805,8 +805,8 @@ s32 create_dir(struct inode *inode, struct chain_t *p_dir,
> >  s32 create_file(struct inode *inode, struct chain_t *p_dir,
> >                 struct uni_name_t *p_uniname, u8 mode, struct file_id_t *fid);
> >  void remove_file(struct inode *inode, struct chain_t *p_dir, s32 entry);
> > -s32 rename_file(struct inode *inode, struct chain_t *p_dir, s32 old_entry,
> > -               struct uni_name_t *p_uniname, struct file_id_t *fid);
> > +s32 exfat_rename_file(struct inode *inode, struct chain_t *p_dir, s32 old_entry,
> > +                     struct uni_name_t *p_uniname, struct file_id_t *fid);
> >  s32 move_file(struct inode *inode, struct chain_t *p_olddir, s32 oldentry,
> >               struct chain_t *p_newdir, struct uni_name_t *p_uniname,
> >               struct file_id_t *fid);
>
> It seems a bit ugly to add the exfat_ prefix to just rename_file,
> rather than all of the above functions (e.g., create_dir, remove_file,
> etc). It doesn't look like any of the others are causing any issues
> though (while, for example, there is another remove_file in
> drivers/infiniband/hw/qib/qib_fs.c, it's static, so shouldn't be a
> problem).

Agreed; however, given that this is a fix, I didn't want to overreach
in the scope of this change since I want to make sure it gets accepted
in 5.5 and it probably won't make it in the merge window. I also
figured that, since this is in staging, this might be one of the
things that needs to happen before being promoted out of staging.

Nevertheless, I don't mind going through and adding the namespace
prefix to the other non-static functions if that's what Valdis and
Greg want.

Thanks!