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

[Geert Uytterhoeven <geert@xxxxxxxxxxxxxx>]

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;

Gr{oetje,eeting}s,

                        Geert

-- 
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@xxxxxxxxxxxxxx

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
                                -- Linus Torvalds