ip6_vti: adjust vti mtu according to mtu of lower device

[ Upstream commit 53c81e95df1793933f87748d36070a721f6cb287 ]

LTP/udp6_ipsec_vti tests fail when sending large UDP datagrams over
ip6_vti that require fragmentation and the underlying device has an
MTU smaller than 1500 plus some extra space for headers. This happens
because ip6_vti, by default, sets MTU to ETH_DATA_LEN and not updating
it depending on a destination address or link parameter. Further
attempts to send UDP packets may succeed because pmtu gets updated on
ICMPV6_PKT_TOOBIG in vti6_err().

In case the lower device has larger MTU size, e.g. 9000, ip6_vti works
but not using the possible maximum size, output packets have 1500 limit.

The above cases require manual MTU setup after ip6_vti creation. However
ip_vti already updates MTU based on lower device with ip_tunnel_bind_dev().

Here is the example when the lower device MTU is set to 9000:

  # ip a sh ltp_ns_veth2
      ltp_ns_veth2@if7: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 9000 ...
        inet 10.0.0.2/24 scope global ltp_ns_veth2
        inet6 fd00::2/64 scope global

  # ip li add vti6 type vti6 local fd00::2 remote fd00::1
  # ip li show vti6
      vti6@NONE: <POINTOPOINT,NOARP> mtu 1500 ...
        link/tunnel6 fd00::2 peer fd00::1

After the patch:
  # ip li add vti6 type vti6 local fd00::2 remote fd00::1
  # ip li show vti6
      vti6@NONE: <POINTOPOINT,NOARP> mtu 8832 ...
        link/tunnel6 fd00::2 peer fd00::1

Reported-by: Petr Vorel <pvorel@suse.cz>
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index bcdc2d557de13914b5046dece683614eb5f8f8c8..413f01be0c9b9d2a577fd5b815b0e2e76f561ea0 100644 (file)
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -626,6 +626,7 @@ static void vti6_link_config(struct ip6_tnl *t)
 {
        struct net_device *dev = t->dev;
        struct __ip6_tnl_parm *p = &t->parms;
+       struct net_device *tdev = NULL;
 
        memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
        memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));
@@ -638,6 +639,25 @@ static void vti6_link_config(struct ip6_tnl *t)
                dev->flags |= IFF_POINTOPOINT;
        else
                dev->flags &= ~IFF_POINTOPOINT;
+
+       if (p->flags & IP6_TNL_F_CAP_XMIT) {
+               int strict = (ipv6_addr_type(&p->raddr) &
+                             (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
+               struct rt6_info *rt = rt6_lookup(t->net,
+                                                &p->raddr, &p->laddr,
+                                                p->link, strict);
+
+               if (rt)
+                       tdev = rt->dst.dev;
+               ip6_rt_put(rt);
+       }
+
+       if (!tdev && p->link)
+               tdev = __dev_get_by_index(t->net, p->link);
+
+       if (tdev)
+               dev->mtu = max_t(int, tdev->mtu - dev->hard_header_len,
+                                IPV6_MIN_MTU);
 }
 
 /**