> From: "Shmulik Ladkani" <shmulik.ladk...@gmail.com> > To: "Lance Richardson" <lrich...@redhat.com> > Cc: netdev@vger.kernel.org, f...@strlen.de, jtl...@redhat.com, > han...@stressinduktion.org > Sent: Friday, November 4, 2016 5:24:09 AM > Subject: Re: [PATCH net v3] ipv4: allow local fragmentation in > ip_finish_output_gso() > > Hi, > > On Thu, 3 Nov 2016 09:06:27 -0400 (EDT) Lance Richardson > <lrich...@redhat.com> wrote: > > I'm not sure what could be added that would help, was there something > > specific you had in mind? > > How about something like this (preliminary, feel free to massage): > > @@ -248,10 +248,16 @@ static int ip_finish_output_gso(struct net *net, struct > sock *sk, > > /* Slowpath - GSO segment length is exceeding the dst MTU. > * > - * This can happen in two cases: > - * 1) TCP GRO packet, DF bit not set > - * 2) skb arrived via virtio-net, we thus get TSO/GSO skbs directly > - * from host network stack. > + * This can happen in several cases: > + * - Forwarding of TCP GRO packet, DF bit not set > + * - Forwarding of skb arrived in a virtualization environment (from > + * virtio-net/vhost/tap) with TSO/GSO size set by other's network > + * stack > + * - Local GSO skb xmitted on an NETIF_F_TSO tunnel stacked over an > + * interface with a smaller mtu > + * - Arriving GRO skb (or GSO skb in a virtualized env) that gets L2 > + * bridged to a NETIF_F_TSO tunnel stacked over an interface with an > + * insufficent mtu > */ > features = netif_skb_features(skb); > BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET); >
Thanks, that looks good to me. I can send a follow-up patch with this change, if you like (there seems to be agreement that the original patch is OK). Lance