Re: [PATCH RFC 2/2] veth: propagate bridge GSO to peer

[Stephen Hemminger <stephen@networkplumber.org>]

On Thu, 30 Nov 2017 09:26:39 -0800
Eric Dumazet <eric.dumazet@gmail.com> wrote:

> On Thu, 2017-11-30 at 09:10 -0800, Stephen Hemminger wrote:
> > 
> > 
> > The problem goes back into the core GSO networking code.
> > Something like this is needed.
> > 
> > static inline bool netif_needs_gso(struct sk_buff *skb,
> > 				   const struct net_device *dev,
> > 				   netdev_features_t features)
> > {
> > 	return skb_is_gso(skb) &&
> > 		(!skb_gso_ok(skb, features) ||
> > 		 unlikely(skb_shinfo(skb)->gso_segs > dev-  
> > >gso_max_segs) ||  << new  
> > 		 unlikely(skb_shinfo(skb)->gso_size > dev-  
> > >gso_max_size) ||  << new  
> > 		 unlikely((skb->ip_summed != CHECKSUM_PARTIAL) &&
> > 			  (skb->ip_summed != CHECKSUM_UNNECESSARY)));
> > }
> > 
> > What that will do is split up the monster GSO packets if they ever
> > bleed
> > across from one device to another through the twisty mazes of packet
> > processing paths.  
> 
> 
> Since very few drivers have these gso_max_segs / gso_max_size, check
> could be done in their ndo_features_check()

Agreed, we could do it there.