kernel_optimize_test/net/ipv4/xfrm4_output.c
Eric W. Biederman 29a26a5680 netfilter: Pass struct net into the netfilter hooks
Pass a network namespace parameter into the netfilter hooks.  At the
call site of the netfilter hooks the path a packet is taking through
the network stack is well known which allows the network namespace to
be easily and reliabily.

This allows the replacement of magic code like
"dev_net(state->in?:state->out)" that appears at the start of most
netfilter hooks with "state->net".

In almost all cases the network namespace passed in is derived
from the first network device passed in, guaranteeing those
paths will not see any changes in practice.

The exceptions are:
xfrm/xfrm_output.c:xfrm_output_resume()         xs_net(skb_dst(skb)->xfrm)
ipvs/ip_vs_xmit.c:ip_vs_nat_send_or_cont()      ip_vs_conn_net(cp)
ipvs/ip_vs_xmit.c:ip_vs_send_or_cont()          ip_vs_conn_net(cp)
ipv4/raw.c:raw_send_hdrinc()                    sock_net(sk)
ipv6/ip6_output.c:ip6_xmit()			sock_net(sk)
ipv6/ndisc.c:ndisc_send_skb()                   dev_net(skb->dev) not dev_net(dst->dev)
ipv6/raw.c:raw6_send_hdrinc()                   sock_net(sk)
br_netfilter_hooks.c:br_nf_pre_routing_finish() dev_net(skb->dev) before skb->dev is set to nf_bridge->physindev

In all cases these exceptions seem to be a better expression for the
network namespace the packet is being processed in then the historic
"dev_net(in?in:out)".  I am documenting them in case something odd
pops up and someone starts trying to track down what happened.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-17 17:18:37 -07:00

114 lines
2.6 KiB
C

/*
* xfrm4_output.c - Common IPsec encapsulation code for IPv4.
* Copyright (c) 2004 Herbert Xu <herbert@gondor.apana.org.au>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/if_ether.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/netfilter_ipv4.h>
#include <net/dst.h>
#include <net/ip.h>
#include <net/xfrm.h>
#include <net/icmp.h>
static int xfrm4_tunnel_check_size(struct sk_buff *skb)
{
int mtu, ret = 0;
if (IPCB(skb)->flags & IPSKB_XFRM_TUNNEL_SIZE)
goto out;
if (!(ip_hdr(skb)->frag_off & htons(IP_DF)) || skb->ignore_df)
goto out;
mtu = dst_mtu(skb_dst(skb));
if (skb->len > mtu) {
if (skb->sk)
xfrm_local_error(skb, mtu);
else
icmp_send(skb, ICMP_DEST_UNREACH,
ICMP_FRAG_NEEDED, htonl(mtu));
ret = -EMSGSIZE;
}
out:
return ret;
}
int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb)
{
int err;
err = xfrm4_tunnel_check_size(skb);
if (err)
return err;
XFRM_MODE_SKB_CB(skb)->protocol = ip_hdr(skb)->protocol;
return xfrm4_extract_header(skb);
}
int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
{
int err;
err = xfrm_inner_extract_output(x, skb);
if (err)
return err;
IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
skb->protocol = htons(ETH_P_IP);
return x->outer_mode->output2(x, skb);
}
EXPORT_SYMBOL(xfrm4_prepare_output);
int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb)
{
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
#ifdef CONFIG_NETFILTER
IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
#endif
return xfrm_output(sk, skb);
}
static int __xfrm4_output(struct sock *sk, struct sk_buff *skb)
{
struct xfrm_state *x = skb_dst(skb)->xfrm;
#ifdef CONFIG_NETFILTER
if (!x) {
IPCB(skb)->flags |= IPSKB_REROUTED;
return dst_output(sk, skb);
}
#endif
return x->outer_mode->afinfo->output_finish(sk, skb);
}
int xfrm4_output(struct sock *sk, struct sk_buff *skb)
{
struct net *net = dev_net(skb_dst(skb)->dev);
return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
net, sk, skb, NULL, skb_dst(skb)->dev,
__xfrm4_output,
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
void xfrm4_local_error(struct sk_buff *skb, u32 mtu)
{
struct iphdr *hdr;
hdr = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb);
ip_local_error(skb->sk, EMSGSIZE, hdr->daddr,
inet_sk(skb->sk)->inet_dport, mtu);
}