Re: [PATCH] 9p/xen: do not memcpy header into req->rc

[Stefano Stabellini]

On Tue, 22 Nov 2022, Dominique Martinet wrote:
> while 'h' is packed and can be assumed to match the request payload,
> req->rc is a struct p9_fcall which is not packed and that memcpy
> could be wrong.
> 
> Fix this by copying each fields individually instead.
> 
> Reported-by: Christian Schoenebeck <linux_oss@xxxxxxxxxxxxx>
> Suggested-by: Stefano Stabellini <sstabellini@xxxxxxxxxx>
> Link: https://lkml.kernel.org/r/alpine.DEB.2.22.394.2211211454540.1049131@ubuntu-linux-20-04-desktop
> Signed-off-by: Dominique Martinet <asmadeus@xxxxxxxxxxxxx>

Reviewed-by: Stefano Stabellini <sstabellini@xxxxxxxxxx>


> ---
> Follow up from the previous xen patch's review.
> 
> This isn't an immediate fix so I don't think this one should be rushed
> in with the rest of the overflow fixes -- I'll let this sit a bit in
> -next after reviews.
> 
>  net/9p/trans_xen.c | 4 +++-
>  1 file changed, 3 insertions(+), 1 deletion(-)
> 
> diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c
> index 4665215bc98b..e8e3f54a837e 100644
> --- a/net/9p/trans_xen.c
> +++ b/net/9p/trans_xen.c
> @@ -216,7 +216,9 @@ static void p9_xen_response(struct work_struct *work)
>  			goto recv_error;
>  		}
>  
> -		memcpy(&req->rc, &h, sizeof(h));
> +		req->rc.size = h.size;
> +		req->rc.id = h.id;
> +		req->rc.tag = h.tag;
>  		req->rc.offset = 0;
>  
>  		masked_cons = xen_9pfs_mask(cons, XEN_9PFS_RING_SIZE(ring));
> -- 
> 2.35.1
>