Re: [PATCH] smb: client: fix possible double free in smb2_set_ea()

[Su Hui]

On 2024/10/14 20:53, Dan Carpenter wrote:

> On Mon, Oct 14, 2024 at 07:34:17PM +0800, Su Hui wrote:
> > Clang static checker(scan-build) warning：
> > fs/smb/client/smb2ops.c:1304:2: Attempt to free released memory.
> >   1304 |         kfree(ea);
> >        |         ^~~~~~~~~
> >
> > There is a double free in such case:
> > 'ea is initialized to NULL' -> 'first successful memory allocation for
> > ea' -> 'something failed, goto sea_exit' -> 'first memory release for ea'
> > -> 'goto replay_again' -> 'second goto sea_exit before allocate memory
> > for ea' -> 'second memory release for ea resulted in double free'.
> >
> > Assign NULL value to 'ea' after 'kfree(ea)', it can fix this double free
> > problem.
> >
> > Fixes: 4f1fffa23769 ("cifs: commands that are retried should have replay flag set")
> > Signed-off-by: Su Hui <suhui@xxxxxxxxxxxx>
> > ---
> >   fs/smb/client/smb2ops.c | 1 +
> >   1 file changed, 1 insertion(+)
> >
> > diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
> > index 6b385fce3f2a..5b42b352b703 100644
> > --- a/fs/smb/client/smb2ops.c
> > +++ b/fs/smb/client/smb2ops.c
> > @@ -1302,6 +1302,7 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
> >   
> >    sea_exit:
> >   	kfree(ea);
> > +	ea = NULL;
> That's very clever.  But I think that it would be better to do the "ea = NULL"
> near to the replay_again label.  There are some lines where we re-initialize
> resp_buftype[], utf16_path and vars etc.
>
> 	ea = NULL;
> 	resp_buftype[0] = resp_buftype[1] = resp_buftype[2] = CIFS_NO_BUFFER;

Yes, it's better! Thanks for your suggestions. I will send v2 patch soon.

Su Hui