Re: [PATCH net] sfc: fix potential memleak in __ef100_hard_start_xmit()

[Leon Romanovsky]

On Fri, Nov 18, 2022 at 09:15:43AM +0000, Martin Habets wrote:
> On Thu, Nov 17, 2022 at 03:05:27PM +0200, Leon Romanovsky wrote:
> > On Thu, Nov 17, 2022 at 08:41:52PM +0800, Zhang Changzhong wrote:
> > > 
> > > 
> > > On 2022/11/17 19:36, Leon Romanovsky wrote:
> > > > On Thu, Nov 17, 2022 at 03:50:09PM +0800, Zhang Changzhong wrote:
> > > >> The __ef100_hard_start_xmit() returns NETDEV_TX_OK without freeing skb
> > > >> in error handling case, add dev_kfree_skb_any() to fix it.
> > > >>
> > > >> Fixes: 51b35a454efd ("sfc: skeleton EF100 PF driver")
> > > >> Signed-off-by: Zhang Changzhong <zhangchangzhong@xxxxxxxxxx>
> > > >> ---
> > > >>  drivers/net/ethernet/sfc/ef100_netdev.c | 1 +
> > > >>  1 file changed, 1 insertion(+)
> > > >>
> > > >> diff --git a/drivers/net/ethernet/sfc/ef100_netdev.c b/drivers/net/ethernet/sfc/ef100_netdev.c
> > > >> index 88fa295..ddcc325 100644
> > > >> --- a/drivers/net/ethernet/sfc/ef100_netdev.c
> > > >> +++ b/drivers/net/ethernet/sfc/ef100_netdev.c
> > > >> @@ -218,6 +218,7 @@ netdev_tx_t __ef100_hard_start_xmit(struct sk_buff *skb,
> > > >>  		   skb->len, skb->data_len, channel->channel);
> > > >>  	if (!efx->n_channels || !efx->n_tx_channels || !channel) {
> > > >>  		netif_stop_queue(net_dev);
> > > >> +		dev_kfree_skb_any(skb);
> > > >>  		goto err;
> > > >>  	}
> > > > 
> > > > ef100 doesn't release in __ef100_enqueue_skb() either. SKB shouldn't be
> > > > NULL or ERR at this stage.
> > > 
> > > SKB shouldn't be NULL or ERR, so it can be freed. But this code looks weird.
> > 
> > Please take a look __ef100_enqueue_skb() and see if it frees SKB on
> > error or not. If not, please fix it.
> 
> That function looks ok to me, but I appreciate the extra eyes on it.

__ef100_enqueue_skb() has the following check in error path:

  498 err:
  499         efx_enqueue_unwind(tx_queue, old_insert_count);
  500         if (!IS_ERR_OR_NULL(skb))
  501                 dev_kfree_skb_any(skb);
  502

The issue is that skb is never error or null here and this "if" is
actually always true and can be deleted.

Thanks