linux/net/ipv4/ip_forward.c
Herbert Xu 35fc92a9de [NET]: Allow forwarding of ip_summed except CHECKSUM_COMPLETE
Right now Xen has a horrible hack that lets it forward packets with
partial checksums.  One of the reasons that CHECKSUM_PARTIAL and
CHECKSUM_COMPLETE were added is so that we can get rid of this hack
(where it creates two extra bits in the skbuff to essentially mirror
ip_summed without being destroyed by the forwarding code).

I had forgotten that I've already gone through all the deivce drivers
last time around to make sure that they're looking at ip_summed ==
CHECKSUM_PARTIAL rather than ip_summed != 0 on transmit.  In any case,
I've now done that again so it should definitely be safe.

Unfortunately nobody has yet added any code to update CHECKSUM_COMPLETE
values on forward so we I'm setting that to CHECKSUM_NONE.  This should
be safe to remove for bridging but I'd like to check that code path
first.

So here is the patch that lets us get rid of the hack by preserving
ip_summed (mostly) on forwarded packets.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-25 22:28:16 -07:00

131 lines
3.2 KiB
C

/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* The IP forwarding functionality.
*
* Version: $Id: ip_forward.c,v 1.48 2000/12/13 18:31:48 davem Exp $
*
* Authors: see ip.c
*
* Fixes:
* Many : Split from ip.c , see ip_input.c for
* history.
* Dave Gregorich : NULL ip_rt_put fix for multicast
* routing.
* Jos Vos : Add call_out_firewall before sending,
* use output device for accounting.
* Jos Vos : Call forward firewall after routing
* (always use output device).
* Mike McLagan : Routing by source
*/
#include <linux/types.h>
#include <linux/mm.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/icmp.h>
#include <linux/netdevice.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/tcp.h>
#include <net/udp.h>
#include <net/icmp.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/netfilter_ipv4.h>
#include <net/checksum.h>
#include <linux/route.h>
#include <net/route.h>
#include <net/xfrm.h>
static inline int ip_forward_finish(struct sk_buff *skb)
{
struct ip_options * opt = &(IPCB(skb)->opt);
IP_INC_STATS_BH(IPSTATS_MIB_OUTFORWDATAGRAMS);
if (unlikely(opt->optlen))
ip_forward_options(skb);
return dst_output(skb);
}
int ip_forward(struct sk_buff *skb)
{
struct iphdr *iph; /* Our header */
struct rtable *rt; /* Route we use */
struct ip_options * opt = &(IPCB(skb)->opt);
if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb))
goto drop;
if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
return NET_RX_SUCCESS;
if (skb->pkt_type != PACKET_HOST)
goto drop;
skb_forward_csum(skb);
/*
* According to the RFC, we must first decrease the TTL field. If
* that reaches zero, we must reply an ICMP control message telling
* that the packet's lifetime expired.
*/
if (ip_hdr(skb)->ttl <= 1)
goto too_many_hops;
if (!xfrm4_route_forward(skb))
goto drop;
rt = (struct rtable*)skb->dst;
if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
goto sr_failed;
if (unlikely(skb->len > dst_mtu(&rt->u.dst) &&
(ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
IP_INC_STATS(IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(dst_mtu(&rt->u.dst)));
goto drop;
}
/* We are about to mangle packet. Copy it! */
if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+rt->u.dst.header_len))
goto drop;
iph = ip_hdr(skb);
/* Decrease ttl after skb cow done */
ip_decrease_ttl(iph);
/*
* We now generate an ICMP HOST REDIRECT giving the route
* we calculated.
*/
if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr)
ip_rt_send_redirect(skb);
skb->priority = rt_tos2priority(iph->tos);
return NF_HOOK(PF_INET, NF_IP_FORWARD, skb, skb->dev, rt->u.dst.dev,
ip_forward_finish);
sr_failed:
/*
* Strict routing permits no gatewaying
*/
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0);
goto drop;
too_many_hops:
/* Tell the sender its packet died... */
IP_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}