Re: [PATCH net v2] L2TP:Adjust intf MTU,factor underlay L3,overlay L2
From: James Chapman
Date: Thu Sep 29 2016 - 11:28:59 EST
On 22/09/16 21:52, R. Parameswaran wrote:
> From ed585bdd6d3d2b3dec58d414f514cd764d89159d Mon Sep 17 00:00:00 2001
> From: "R. Parameswaran" <rparames@xxxxxxxxxxx>
> Date: Thu, 22 Sep 2016 13:19:25 -0700
> Subject: [PATCH] L2TP:Adjust intf MTU,factor underlay L3,overlay L2
>
> Take into account all of the tunnel encapsulation headers when setting
> up the MTU on the L2TP logical interface device. Otherwise, packets
> created by the applications on top of the L2TP layer are larger
> than they ought to be, relative to the underlay MTU, leading to
> needless fragmentation once the outer IP encap is added.
>
> Specifically, take into account the (outer, underlay) IP header
> imposed on the encapsulated L2TP packet, and the Layer 2 header
> imposed on the inner IP packet prior to L2TP encapsulation.
>
> Do not assume an Ethernet (non-jumbo) underlay. Use the PMTU mechanism
> and the dst entry in the L2TP tunnel socket to directly pull up
> the underlay MTU (as the baseline number on top of which the
> encapsulation headers are factored in). Fall back to Ethernet MTU
> if this fails.
>
> Signed-off-by: R. Parameswaran <rparames@xxxxxxxxxxx>
>
> Reviewed-by: "N. Prachanda" <nprachan@xxxxxxxxxxx>,
> Reviewed-by: "R. Shearman" <rshearma@xxxxxxxxxxx>,
> Reviewed-by: "D. Fawcus" <dfawcus@xxxxxxxxxxx>
> ---
> net/l2tp/l2tp_eth.c | 48 ++++++++++++++++++++++++++++++++++++++++++++----
> 1 file changed, 44 insertions(+), 4 deletions(-)
>
> diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
> index 57fc5a4..dbcd6bd 100644
> --- a/net/l2tp/l2tp_eth.c
> +++ b/net/l2tp/l2tp_eth.c
> @@ -30,6 +30,9 @@
> #include <net/xfrm.h>
> #include <net/net_namespace.h>
> #include <net/netns/generic.h>
> +#include <linux/ip.h>
> +#include <linux/ipv6.h>
> +#include <linux/udp.h>
>
> #include "l2tp_core.h"
>
> @@ -206,6 +209,46 @@ static void l2tp_eth_show(struct seq_file *m, void *arg)
> }
> #endif
>
> +static void l2tp_eth_adjust_mtu(struct l2tp_tunnel *tunnel,
> + struct l2tp_session *session,
> + struct net_device *dev)
> +{
> + unsigned int overhead = 0;
> + struct dst_entry *dst;
> +
> + if (session->mtu != 0) {
> + dev->mtu = session->mtu;
> + dev->needed_headroom += session->hdr_len;
> + if (tunnel->encap == L2TP_ENCAPTYPE_UDP)
> + dev->needed_headroom += sizeof(struct udphdr);
> + return;
> + }
> + overhead = session->hdr_len;
> + /* Adjust MTU, factor overhead - underlay L3 hdr, overlay L2 hdr*/
> + if (tunnel->sock->sk_family == AF_INET)
> + overhead += (ETH_HLEN + sizeof(struct iphdr));
> + else if (tunnel->sock->sk_family == AF_INET6)
> + overhead += (ETH_HLEN + sizeof(struct ipv6hdr));
What about options in the IP header? If certain options are set on the
socket, the IP header may be larger.
> + /* Additionally, if the encap is UDP, account for UDP header size */
> + if (tunnel->encap == L2TP_ENCAPTYPE_UDP)
> + overhead += sizeof(struct udphdr);
> + /* If PMTU discovery was enabled, use discovered MTU on L2TP device */
> + dst = sk_dst_get(tunnel->sock);
> + if (dst) {
> + u32 pmtu = dst_mtu(dst);
> +
> + if (pmtu != 0)
> + dev->mtu = pmtu;
> + dst_release(dst);
> + }
> + /* else (no PMTUD) L2TP dev MTU defaulted to Ethernet MTU in caller */
> + session->mtu = dev->mtu - overhead;
> + dev->mtu = session->mtu;
> + dev->needed_headroom += session->hdr_len;
> + if (tunnel->encap == L2TP_ENCAPTYPE_UDP)
> + dev->needed_headroom += sizeof(struct udphdr);
> +}
> +
> static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg)
> {
> struct net_device *dev;
> @@ -255,11 +298,8 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p
> }
>
> dev_net_set(dev, net);
> - if (session->mtu == 0)
> - session->mtu = dev->mtu - session->hdr_len;
> - dev->mtu = session->mtu;
> - dev->needed_headroom += session->hdr_len;
>
> + l2tp_eth_adjust_mtu(tunnel, session, dev);
> priv = netdev_priv(dev);
> priv->dev = dev;
> priv->session = session;