kernel-ark/net/ipv4/xfrm4_output.c
David Miller 7026b1ddb6 netfilter: Pass socket pointer down through okfn().
On the output paths in particular, we have to sometimes deal with two
socket contexts.  First, and usually skb->sk, is the local socket that
generated the frame.

And second, is potentially the socket used to control a tunneling
socket, such as one the encapsulates using UDP.

We do not want to disassociate skb->sk when encapsulating in order
to fix this, because that would break socket memory accounting.

The most extreme case where this can cause huge problems is an
AF_PACKET socket transmitting over a vxlan device.  We hit code
paths doing checks that assume they are dealing with an ipv4
socket, but are actually operating upon the AF_PACKET one.

Signed-off-by: David S. Miller <davem@davemloft.net>
2015-04-07 15:25:55 -04:00

112 lines
2.5 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(sk, skb);
}
#endif
return x->outer_mode->afinfo->output_finish(sk, skb);
}
int xfrm4_output(struct sock *sk, struct sk_buff *skb)
{
return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, 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);
}