Re: [PATCH net] net: ethernet: rtsn: fix potential memory leak in rtsn_start_xmit()

[Eric Dumazet]

On Tue, Oct 15, 2024 at 8:58 AM Geert Uytterhoeven <geert@xxxxxxxxxxxxxx> wrote:
>
> Hi Wang,
>
> On Mon, Oct 14, 2024 at 4:43 PM Wang Hai <wanghai38@xxxxxxxxxx> wrote:
> > The rtsn_start_xmit() returns NETDEV_TX_OK without freeing skb
> > in case of skb->len being too long, add dev_kfree_skb_any() to fix it.
> >
> > Fixes: b0d3969d2b4d ("net: ethernet: rtsn: Add support for Renesas Ethernet-TSN")
> > Signed-off-by: Wang Hai <wanghai38@xxxxxxxxxx>
>
> Thanks for your patch!
>
> > --- a/drivers/net/ethernet/renesas/rtsn.c
> > +++ b/drivers/net/ethernet/renesas/rtsn.c
> > @@ -1057,6 +1057,7 @@ static netdev_tx_t rtsn_start_xmit(struct sk_buff *skb, struct net_device *ndev)
> >         if (skb->len >= TX_DS) {
> >                 priv->stats.tx_dropped++;
> >                 priv->stats.tx_errors++;
> > +               dev_kfree_skb_any(skb);
> >                 goto out;
> >         }
>
> Does the same apply to the skb_put_padto() failure path below?
>
> drivers/net/ethernet/renesas/rtsn.c-    if (skb_put_padto(skb, ETH_ZLEN))
> drivers/net/ethernet/renesas/rtsn.c-            goto out;

In case of error, skb_put_padto() frees the skb.

/**
 * skb_put_padto - increase size and pad an skbuff up to a minimal size
 * @skb: buffer to pad
 * @len: minimal length
 *
 * Pads up a buffer to ensure the trailing bytes exist and are
 * blanked. If the buffer already contains sufficient data it
 * is untouched. Otherwise it is extended. Returns zero on
 * success. The skb is freed on error.
 */
static inline int __must_check skb_put_padto(struct sk_buff *skb,
unsigned int len)
{
return __skb_put_padto(skb, len, true);
}