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

[Dan Carpenter]

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;

regards,
dan carpenter