Re: [PATCH net RFC] net: Clear IFF_TX_SKB_SHARING for all Ethernet devices using skb_padto
From: Xie He
Date: Thu Oct 22 2020 - 21:56:54 EST
On Thu, Oct 22, 2020 at 5:44 PM Jakub Kicinski <kuba@xxxxxxxxxx> wrote:
>
> On Thu, 22 Oct 2020 12:59:45 -0700 Xie He wrote:
> >
> > But I also see some drivers that want to pad the skb to a strange
> > length, and don't set their special min_mtu to match this length. For
> > example:
> >
> > drivers/net/ethernet/packetengines/yellowfin.c wants to pad the skb to
> > a dynamically calculated value.
> >
> > drivers/net/ethernet/ti/cpsw.c, cpsw_new.c and tlan.c want to pad the
> > skb to macro defined values.
> >
> > drivers/net/ethernet/intel/iavf/iavf_txrx.c wants to pad the skb to
> > IAVF_MIN_TX_LEN (17).
> >
> > drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c wants to pad the skb to 17.
>
> Hm, I see, that would be a slight loss of functionality if we started
> requiring 64B, for example, while the driver could in practice xmit
> 17B frames (would matter only to VFs, but nonetheless).
I think requiring the length to be at least some value won't solve the
problem for all drivers. For example:
drivers/net/ethernet/packetengines/yellowfin.c pads the skb to 32-byte
boundaries in the memory (no matter how long the length is).
drivers/net/ethernet/adaptec/starfire.c pads the skb so that the
length is multiples of 4.
drivers/net/ethernet/sun/cassini.c pads the skb to cp->min_frame_size,
which may be 255, 60, or 97.
> > Another solution I can think of is to add a "skb_shared" check to
> > "__skb_pad", so that if __skb_pad encounters a shared skb, it just
> > returns an error. The driver would think this is a memory allocation
> > failure. This way we can ensure shared skbs are not modified.
>
> I'm not sure if we want to be adding checks to __skb_pad() to handle
> what's effectively a pktgen specific condition.
>
> We could create a new field in struct netdevice for min_frame_len, but I
> think your patch is the simplest solution. Let's see if anyone objects.
>
> BTW it seems like there is more drivers which will need the flag
> cleared, e.g. drivers/net/ethernet/broadcom/bnxt/bnxt.c?
My patch isn't complete. Because there are so many drivers with this
problem, I feel it's hard to solve them all at once. So I only grepped
"skb_padto" under "drivers/net/ethernet". There are other drivers
under "ethernet" using "skb_pad", "skb_put_padto" or "eth_skb_pad".
There are also (fake) Ethernet drivers under "drivers/net/wireless". I
feel it'd take a long time and also be error-prone to solve them all,
so I feel it'd be the best if there are other solutions.