linux_dsm_epyc7002/net/ipv6/xfrm6_input.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

146 lines
3.0 KiB
C

/*
* xfrm6_input.c: based on net/ipv4/xfrm4_input.c
*
* Authors:
* Mitsuru KANDA @USAGI
* Kazunori MIYAZAWA @USAGI
* Kunihiro Ishiguro <kunihiro@ipinfusion.com>
* YOSHIFUJI Hideaki @USAGI
* IPv6 support
*/
#include <linux/module.h>
#include <linux/string.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
#include <net/ipv6.h>
#include <net/xfrm.h>
int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb)
{
return xfrm6_extract_header(skb);
}
int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi)
{
XFRM_SPI_SKB_CB(skb)->family = AF_INET6;
XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct ipv6hdr, daddr);
return xfrm_input(skb, nexthdr, spi, 0);
}
EXPORT_SYMBOL(xfrm6_rcv_spi);
int xfrm6_transport_finish(struct sk_buff *skb, int async)
{
skb_network_header(skb)[IP6CB(skb)->nhoff] =
XFRM_MODE_SKB_CB(skb)->protocol;
#ifndef CONFIG_NETFILTER
if (!async)
return 1;
#endif
ipv6_hdr(skb)->payload_len = htons(skb->len);
__skb_push(skb, skb->data - skb_network_header(skb));
NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
dev_net(skb->dev), NULL, skb, skb->dev, NULL,
ip6_rcv_finish);
return -1;
}
int xfrm6_rcv(struct sk_buff *skb)
{
return xfrm6_rcv_spi(skb, skb_network_header(skb)[IP6CB(skb)->nhoff],
0);
}
EXPORT_SYMBOL(xfrm6_rcv);
int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr,
xfrm_address_t *saddr, u8 proto)
{
struct net *net = dev_net(skb->dev);
struct xfrm_state *x = NULL;
int i = 0;
/* Allocate new secpath or COW existing one. */
if (!skb->sp || atomic_read(&skb->sp->refcnt) != 1) {
struct sec_path *sp;
sp = secpath_dup(skb->sp);
if (!sp) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR);
goto drop;
}
if (skb->sp)
secpath_put(skb->sp);
skb->sp = sp;
}
if (1 + skb->sp->len == XFRM_MAX_DEPTH) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
goto drop;
}
for (i = 0; i < 3; i++) {
xfrm_address_t *dst, *src;
switch (i) {
case 0:
dst = daddr;
src = saddr;
break;
case 1:
/* lookup state with wild-card source address */
dst = daddr;
src = (xfrm_address_t *)&in6addr_any;
break;
default:
/* lookup state with wild-card addresses */
dst = (xfrm_address_t *)&in6addr_any;
src = (xfrm_address_t *)&in6addr_any;
break;
}
x = xfrm_state_lookup_byaddr(net, skb->mark, dst, src, proto, AF_INET6);
if (!x)
continue;
spin_lock(&x->lock);
if ((!i || (x->props.flags & XFRM_STATE_WILDRECV)) &&
likely(x->km.state == XFRM_STATE_VALID) &&
!xfrm_state_check_expire(x)) {
spin_unlock(&x->lock);
if (x->type->input(x, skb) > 0) {
/* found a valid state */
break;
}
} else
spin_unlock(&x->lock);
xfrm_state_put(x);
x = NULL;
}
if (!x) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES);
xfrm_audit_state_notfound_simple(skb, AF_INET6);
goto drop;
}
skb->sp->xvec[skb->sp->len++] = x;
spin_lock(&x->lock);
x->curlft.bytes += skb->len;
x->curlft.packets++;
spin_unlock(&x->lock);
return 1;
drop:
return -1;
}
EXPORT_SYMBOL(xfrm6_input_addr);