On Tue, Apr 7, 2015 at 8:45 AM, Hannes Frederic Sowa
<hannes@xxxxxxxxxxxxxxxxxxx> wrote:
> On Mo, 2015-04-06 at 23:02 -0700, Tom Herbert wrote:
>> On Sun, Apr 5, 2015 at 7:19 PM, David Miller <davem@xxxxxxxxxxxxx> wrote:
>> >
>> > That was we can make sure the output path of ipv4/ipv6 operate on
>> > the UDP socket rather than whatever random thing happens to be in
>> > skb->sk.
>> >
>> > Based upon a patch by Jiri Pirko.
>> >
>> > Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
>> > ---
>> > drivers/net/vxlan.c | 14 ++++++++------
>> > include/net/ip6_tunnel.h | 5 +++--
>> > include/net/ipv6.h | 1 +
>> > include/net/udp_tunnel.h | 5 +++--
>> > include/net/vxlan.h | 2 +-
>> > net/ipv4/geneve.c | 2 +-
>> > net/ipv4/udp_tunnel.c | 4 ++--
>> > net/ipv6/ip6_gre.c | 2 +-
>> > net/ipv6/ip6_tunnel.c | 2 +-
>> > net/ipv6/ip6_udp_tunnel.c | 5 +++--
>> > net/ipv6/output_core.c | 21 ++++++++++++++++-----
>> > net/openvswitch/vport-vxlan.c | 5 +++--
>> > net/tipc/udp_media.c | 6 ++++--
>> > 13 files changed, 47 insertions(+), 27 deletions(-)
>> >
>> > diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
>> > index b5fecb4..51baac7 100644
>> > --- a/drivers/net/vxlan.c
>> > +++ b/drivers/net/vxlan.c
>> > @@ -1672,7 +1672,8 @@ static void vxlan_build_gbp_hdr(struct vxlanhdr *vxh, u32 vxflags,
>> > }
>> >
>> > #if IS_ENABLED(CONFIG_IPV6)
>> > -static int vxlan6_xmit_skb(struct dst_entry *dst, struct sk_buff *skb,
>> > +static int vxlan6_xmit_skb(struct dst_entry *dst, struct sock *sk,
>> > + struct sk_buff *skb,
>> > struct net_device *dev, struct in6_addr *saddr,
>> > struct in6_addr *daddr, __u8 prio, __u8 ttl,
>> > __be16 src_port, __be16 dst_port,
>> > @@ -1748,7 +1749,7 @@ static int vxlan6_xmit_skb(struct dst_entry *dst, struct sk_buff *skb,
>> >
>> > skb_set_inner_protocol(skb, htons(ETH_P_TEB));
>> >
>> > - udp_tunnel6_xmit_skb(dst, skb, dev, saddr, daddr, prio,
>> > + udp_tunnel6_xmit_skb(dst, sk, skb, dev, saddr, daddr, prio,
>> > ttl, src_port, dst_port,
>> > !!(vxflags & VXLAN_F_UDP_ZERO_CSUM6_TX));
>> > return 0;
>> > @@ -1758,7 +1759,7 @@ err:
>> > }
>> > #endif
>> >
>> > -int vxlan_xmit_skb(struct rtable *rt, struct sk_buff *skb,
>> > +int vxlan_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
>> > __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
>> > __be16 src_port, __be16 dst_port,
>> > struct vxlan_metadata *md, bool xnet, u32 vxflags)
>> > @@ -1827,7 +1828,7 @@ int vxlan_xmit_skb(struct rtable *rt, struct sk_buff *skb,
>> >
>> > skb_set_inner_protocol(skb, htons(ETH_P_TEB));
>> >
>> > - return udp_tunnel_xmit_skb(rt, skb, src, dst, tos,
>> > + return udp_tunnel_xmit_skb(rt, sk, skb, src, dst, tos,
>> > ttl, df, src_port, dst_port, xnet,
>> > !(vxflags & VXLAN_F_UDP_CSUM));
>> > }
>> > @@ -1882,6 +1883,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
>> > struct vxlan_rdst *rdst, bool did_rsc)
>> > {
>> > struct vxlan_dev *vxlan = netdev_priv(dev);
>> > + struct sock *sk = vxlan->vn_sock->sock->sk;
>> > struct rtable *rt = NULL;
>> > const struct iphdr *old_iph;
>> > struct flowi4 fl4;
>> > @@ -1961,7 +1963,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
>> > md.vni = htonl(vni << 8);
>> > md.gbp = skb->mark;
>> >
>> > - err = vxlan_xmit_skb(rt, skb, fl4.saddr,
>> > + err = vxlan_xmit_skb(rt, sk, skb, fl4.saddr,
>> > dst->sin.sin_addr.s_addr, tos, ttl, df,
>> > src_port, dst_port, &md,
>> > !net_eq(vxlan->net, dev_net(vxlan->dev)),
>> > @@ -2021,7 +2023,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
>> > md.vni = htonl(vni << 8);
>> > md.gbp = skb->mark;
>> >
>> > - err = vxlan6_xmit_skb(ndst, skb, dev, &fl6.saddr, &fl6.daddr,
>> > + err = vxlan6_xmit_skb(ndst, sk, skb, dev, &fl6.saddr, &fl6.daddr,
>> > 0, ttl, src_port, dst_port, &md,
>> > !net_eq(vxlan->net, dev_net(vxlan->dev)),
>> > vxlan->flags);
>> > diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
>> > index 1668be5..b8529aa 100644
>> > --- a/include/net/ip6_tunnel.h
>> > +++ b/include/net/ip6_tunnel.h
>> > @@ -73,13 +73,14 @@ __u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr,
>> > struct net *ip6_tnl_get_link_net(const struct net_device *dev);
>> > int ip6_tnl_get_iflink(const struct net_device *dev);
>> >
>> > -static inline void ip6tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
>> > +static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
>> > + struct net_device *dev)
>> > {
>> > struct net_device_stats *stats = &dev->stats;
>> > int pkt_len, err;
>> >
>> > pkt_len = skb->len;
>> > - err = ip6_local_out(skb);
>> > + err = ip6_local_out_sk(sk, skb);
>> >
>> > if (net_xmit_eval(err) == 0) {
>> > struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
>> > diff --git a/include/net/ipv6.h b/include/net/ipv6.h
>> > index b6ae959..27470cd 100644
>> > --- a/include/net/ipv6.h
>> > +++ b/include/net/ipv6.h
>> > @@ -827,6 +827,7 @@ int ip6_input(struct sk_buff *skb);
>> > int ip6_mc_input(struct sk_buff *skb);
>> >
>> > int __ip6_local_out(struct sk_buff *skb);
>> > +int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb);
>> > int ip6_local_out(struct sk_buff *skb);
>> >
>> > /*
>> > diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
>> > index 1a20d33..c491c12 100644
>> > --- a/include/net/udp_tunnel.h
>> > +++ b/include/net/udp_tunnel.h
>> > @@ -77,13 +77,14 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
>> > struct udp_tunnel_sock_cfg *sock_cfg);
>> >
>> > /* Transmit the skb using UDP encapsulation. */
>> > -int udp_tunnel_xmit_skb(struct rtable *rt, struct sk_buff *skb,
>> > +int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
>> > __be32 src, __be32 dst, __u8 tos, __u8 ttl,
>> > __be16 df, __be16 src_port, __be16 dst_port,
>> > bool xnet, bool nocheck);
>> >
>> > #if IS_ENABLED(CONFIG_IPV6)
>> > -int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sk_buff *skb,
>> > +int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk,
>> > + struct sk_buff *skb,
>> > struct net_device *dev, struct in6_addr *saddr,
>> > struct in6_addr *daddr,
>> > __u8 prio, __u8 ttl, __be16 src_port,
>> > diff --git a/include/net/vxlan.h b/include/net/vxlan.h
>> > index 756e463..0082b5d 100644
>> > --- a/include/net/vxlan.h
>> > +++ b/include/net/vxlan.h
>> > @@ -145,7 +145,7 @@ struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
>> >
>> > void vxlan_sock_release(struct vxlan_sock *vs);
>> >
>> > -int vxlan_xmit_skb(struct rtable *rt, struct sk_buff *skb,
>> > +int vxlan_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
>> > __be32 src, __be32 dst, __u8 tos, __u8 ttl, __be16 df,
>> > __be16 src_port, __be16 dst_port, struct vxlan_metadata *md,
>> > bool xnet, u32 vxflags);
>> > diff --git a/net/ipv4/geneve.c b/net/ipv4/geneve.c
>> > index e64f8e9..b77f5e8 100644
>> > --- a/net/ipv4/geneve.c
>> > +++ b/net/ipv4/geneve.c
>> > @@ -136,7 +136,7 @@ int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt,
>> >
>> > skb_set_inner_protocol(skb, htons(ETH_P_TEB));
>> >
>> > - return udp_tunnel_xmit_skb(rt, skb, src, dst,
>> > + return udp_tunnel_xmit_skb(rt, gs->sock->sk, skb, src, dst,
>> > tos, ttl, df, src_port, dst_port, xnet,
>> > !csum);
>> > }
>> > diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
>> > index c83b354..6bb98cc 100644
>> > --- a/net/ipv4/udp_tunnel.c
>> > +++ b/net/ipv4/udp_tunnel.c
>> > @@ -75,7 +75,7 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
>> > }
>> > EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
>> >
>> > -int udp_tunnel_xmit_skb(struct rtable *rt, struct sk_buff *skb,
>> > +int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
>> > __be32 src, __be32 dst, __u8 tos, __u8 ttl,
>> > __be16 df, __be16 src_port, __be16 dst_port,
>> > bool xnet, bool nocheck)
>> > @@ -92,7 +92,7 @@ int udp_tunnel_xmit_skb(struct rtable *rt, struct sk_buff *skb,
>> >
>> > udp_set_csum(nocheck, skb, src, dst, skb->len);
>> >
>> > - return iptunnel_xmit(skb->sk, rt, skb, src, dst, IPPROTO_UDP,
>> > + return iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP,
>> > tos, ttl, df, xnet);
>> > }
>> > EXPORT_SYMBOL_GPL(udp_tunnel_xmit_skb);
>> > diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
>> > index f724329..b5e6cc1 100644
>> > --- a/net/ipv6/ip6_gre.c
>> > +++ b/net/ipv6/ip6_gre.c
>> > @@ -760,7 +760,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
>> >
>> > skb_set_inner_protocol(skb, protocol);
>> >
>> > - ip6tunnel_xmit(skb, dev);
>> > + ip6tunnel_xmit(NULL, skb, dev);
>> > if (ndst)
>> > ip6_tnl_dst_store(tunnel, ndst);
>> > return 0;
>> > diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
>> > index b6a211a..5cafd92 100644
>> > --- a/net/ipv6/ip6_tunnel.c
>> > +++ b/net/ipv6/ip6_tunnel.c
>> > @@ -1100,7 +1100,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
>> > ipv6h->nexthdr = proto;
>> > ipv6h->saddr = fl6->saddr;
>> > ipv6h->daddr = fl6->daddr;
>> > - ip6tunnel_xmit(skb, dev);
>> > + ip6tunnel_xmit(NULL, skb, dev);
>>
>> By same should logic iptunnel_xmit call in ip_tunnel_xmit should take
>> NULL arg for socket?
>
> Sure!
>
Actually, for consistency amongst all the IP encapsulation protocols
and given Dave's comments on how this is supposed to work, maybe for
the v4 and v6 tunnels we could have a raw AF_INET{6} socket opened for
all the tunnels to use when ip_tunnel_xmit is called. If it makes a
difference for UDP encapsulation, a UDP socket could also be opened.
Tom
> Thanks, otherwise the patches look good!
>
> Acked-by: Hannes Frederic Sowa <hannes@xxxxxxxxxxxxxxxxxxx>
>
>
>
--
To unsubscribe from this list: send the line "unsubscribe netfilter-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
