On Tue, Oct 6, 2020 at 9:03 AM Jesper Dangaard Brouer <brouer@xxxxxxxxxx> wrote:
>
> The BPF-helpers for FIB lookup (bpf_xdp_fib_lookup and bpf_skb_fib_lookup)
> can perform MTU check and return BPF_FIB_LKUP_RET_FRAG_NEEDED. The BPF-prog
> don't know the MTU value that caused this rejection.
>
> If the BPF-prog wants to implement PMTU (Path MTU Discovery) (rfc1191) it
> need to know this MTU value for the ICMP packet.
>
> Patch change lookup and result struct bpf_fib_lookup, to contain this MTU
> value as output via a union with 'tot_len' as this is the value used for
> the MTU lookup.
>
> Signed-off-by: Jesper Dangaard Brouer <brouer@xxxxxxxxxx>
> ---
> include/uapi/linux/bpf.h | 11 +++++++++--
> net/core/filter.c | 17 ++++++++++++-----
> 2 files changed, 21 insertions(+), 7 deletions(-)
>
> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
> index c446394135be..50ce65e37b16 100644
> --- a/include/uapi/linux/bpf.h
> +++ b/include/uapi/linux/bpf.h
> @@ -2216,6 +2216,9 @@ union bpf_attr {
> * * > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
> * packet is not forwarded or needs assist from full stack
> *
> + * If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU
> + * was exceeded and result params->mtu contains the MTU.
> + *
> * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
> * Description
> * Add an entry to, or update a sockhash *map* referencing sockets.
> @@ -4844,9 +4847,13 @@ struct bpf_fib_lookup {
> __be16 sport;
> __be16 dport;
>
> - /* total length of packet from network header - used for MTU check */
> - __u16 tot_len;
> + union { /* used for MTU check */
> + /* input to lookup */
> + __u16 tot_len; /* total length of packet from network hdr */
>
> + /* output: MTU value (if requested check_mtu) */
> + __u16 mtu;
> + };
> /* input: L3 device index for lookup
> * output: device index from FIB lookup
> */
> diff --git a/net/core/filter.c b/net/core/filter.c
> index fed239e77bdc..d84723f347c0 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -5185,13 +5185,14 @@ static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = {
> #if IS_ENABLED(CONFIG_INET) || IS_ENABLED(CONFIG_IPV6)
> static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
> const struct neighbour *neigh,
> - const struct net_device *dev)
> + const struct net_device *dev, u32 mtu)
> {
> memcpy(params->dmac, neigh->ha, ETH_ALEN);
> memcpy(params->smac, dev->dev_addr, ETH_ALEN);
> params->h_vlan_TCI = 0;
> params->h_vlan_proto = 0;
> params->ifindex = dev->ifindex;
> + params->mtu = mtu;
>
> return 0;
> }
> @@ -5275,8 +5276,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
>
> if (check_mtu) {
> mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst);
> - if (params->tot_len > mtu)
> + if (params->tot_len > mtu) {
> + params->mtu = mtu; /* union with tot_len */
> return BPF_FIB_LKUP_RET_FRAG_NEEDED;
> + }
> }
>
> nhc = res.nhc;
> @@ -5309,7 +5312,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
> if (!neigh)
> return BPF_FIB_LKUP_RET_NO_NEIGH;
>
> - return bpf_fib_set_fwd_params(params, neigh, dev);
> + return bpf_fib_set_fwd_params(params, neigh, dev, mtu);
> }
> #endif
>
> @@ -5401,8 +5404,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
>
> if (check_mtu) {
> mtu = ipv6_stub->ip6_mtu_from_fib6(&res, dst, src);
> - if (params->tot_len > mtu)
> + if (params->tot_len > mtu) {
> + params->mtu = mtu; /* union with tot_len */
> return BPF_FIB_LKUP_RET_FRAG_NEEDED;
> + }
> }
>
> if (res.nh->fib_nh_lws)
> @@ -5421,7 +5426,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
> if (!neigh)
> return BPF_FIB_LKUP_RET_NO_NEIGH;
>
> - return bpf_fib_set_fwd_params(params, neigh, dev);
> + return bpf_fib_set_fwd_params(params, neigh, dev, mtu);
> }
> #endif
>
> @@ -5490,6 +5495,8 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
> dev = dev_get_by_index_rcu(net, params->ifindex);
> if (!is_skb_forwardable(dev, skb))
> rc = BPF_FIB_LKUP_RET_FRAG_NEEDED;
> +
> + params->mtu = dev->mtu; /* union with tot_len */
> }
>
> return rc;
>
>
It would be beneficial to be able to fetch the route advmss, initcwnd,
etc as well...
But I take it the struct can't be extended?
