linux-stable/net/xfrm/xfrm_output.c
Lorenzo Colitti 077fbac405 net: xfrm: support setting an output mark.
On systems that use mark-based routing it may be necessary for
routing lookups to use marks in order for packets to be routed
correctly. An example of such a system is Android, which uses
socket marks to route packets via different networks.

Currently, routing lookups in tunnel mode always use a mark of
zero, making routing incorrect on such systems.

This patch adds a new output_mark element to the xfrm state and
a corresponding XFRMA_OUTPUT_MARK netlink attribute. The output
mark differs from the existing xfrm mark in two ways:

1. The xfrm mark is used to match xfrm policies and states, while
   the xfrm output mark is used to set the mark (and influence
   the routing) of the packets emitted by those states.
2. The existing mark is constrained to be a subset of the bits of
   the originating socket or transformed packet, but the output
   mark is arbitrary and depends only on the state.

The use of a separate mark provides additional flexibility. For
example:

- A packet subject to two transforms (e.g., transport mode inside
  tunnel mode) can have two different output marks applied to it,
  one for the transport mode SA and one for the tunnel mode SA.
- On a system where socket marks determine routing, the packets
  emitted by an IPsec tunnel can be routed based on a mark that
  is determined by the tunnel, not by the marks of the
  unencrypted packets.
- Support for setting the output marks can be introduced without
  breaking any existing setups that employ both mark-based
  routing and xfrm tunnel mode. Simply changing the code to use
  the xfrm mark for routing output packets could xfrm mark could
  change behaviour in a way that breaks these setups.

If the output mark is unspecified or set to zero, the mark is not
set or changed.

Tested: make allyesconfig; make -j64
Tested: https://android-review.googlesource.com/452776
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2017-08-11 07:03:00 +02:00

290 lines
6.1 KiB
C

/*
* xfrm_output.c - Common IPsec encapsulation code.
*
* Copyright (c) 2007 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/errno.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/netfilter.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <net/dst.h>
#include <net/xfrm.h>
static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb);
static int xfrm_skb_check_space(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
int nhead = dst->header_len + LL_RESERVED_SPACE(dst->dev)
- skb_headroom(skb);
int ntail = dst->dev->needed_tailroom - skb_tailroom(skb);
if (nhead <= 0) {
if (ntail <= 0)
return 0;
nhead = 0;
} else if (ntail < 0)
ntail = 0;
return pskb_expand_head(skb, nhead, ntail, GFP_ATOMIC);
}
/* Children define the path of the packet through the
* Linux networking. Thus, destinations are stackable.
*/
static struct dst_entry *skb_dst_pop(struct sk_buff *skb)
{
struct dst_entry *child = dst_clone(skb_dst(skb)->child);
skb_dst_drop(skb);
return child;
}
static int xfrm_output_one(struct sk_buff *skb, int err)
{
struct dst_entry *dst = skb_dst(skb);
struct xfrm_state *x = dst->xfrm;
struct net *net = xs_net(x);
if (err <= 0)
goto resume;
do {
err = xfrm_skb_check_space(skb);
if (err) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
goto error_nolock;
}
if (x->props.output_mark)
skb->mark = x->props.output_mark;
err = x->outer_mode->output(x, skb);
if (err) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEMODEERROR);
goto error_nolock;
}
spin_lock_bh(&x->lock);
if (unlikely(x->km.state != XFRM_STATE_VALID)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEINVALID);
err = -EINVAL;
goto error;
}
err = xfrm_state_check_expire(x);
if (err) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEEXPIRED);
goto error;
}
err = x->repl->overflow(x, skb);
if (err) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR);
goto error;
}
x->curlft.bytes += skb->len;
x->curlft.packets++;
spin_unlock_bh(&x->lock);
skb_dst_force(skb);
if (xfrm_offload(skb)) {
x->type_offload->encap(x, skb);
} else {
err = x->type->output(x, skb);
if (err == -EINPROGRESS)
goto out;
}
resume:
if (err) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEPROTOERROR);
goto error_nolock;
}
dst = skb_dst_pop(skb);
if (!dst) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
err = -EHOSTUNREACH;
goto error_nolock;
}
skb_dst_set(skb, dst);
x = dst->xfrm;
} while (x && !(x->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL));
return 0;
error:
spin_unlock_bh(&x->lock);
error_nolock:
kfree_skb(skb);
out:
return err;
}
int xfrm_output_resume(struct sk_buff *skb, int err)
{
struct net *net = xs_net(skb_dst(skb)->xfrm);
while (likely((err = xfrm_output_one(skb, err)) == 0)) {
nf_reset(skb);
err = skb_dst(skb)->ops->local_out(net, skb->sk, skb);
if (unlikely(err != 1))
goto out;
if (!skb_dst(skb)->xfrm)
return dst_output(net, skb->sk, skb);
err = nf_hook(skb_dst(skb)->ops->family,
NF_INET_POST_ROUTING, net, skb->sk, skb,
NULL, skb_dst(skb)->dev, xfrm_output2);
if (unlikely(err != 1))
goto out;
}
if (err == -EINPROGRESS)
err = 0;
out:
return err;
}
EXPORT_SYMBOL_GPL(xfrm_output_resume);
static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
{
return xfrm_output_resume(skb, 1);
}
static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct sk_buff *segs;
BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET);
segs = skb_gso_segment(skb, 0);
kfree_skb(skb);
if (IS_ERR(segs))
return PTR_ERR(segs);
if (segs == NULL)
return -EINVAL;
do {
struct sk_buff *nskb = segs->next;
int err;
segs->next = NULL;
err = xfrm_output2(net, sk, segs);
if (unlikely(err)) {
kfree_skb_list(nskb);
return err;
}
segs = nskb;
} while (segs);
return 0;
}
int xfrm_output(struct sock *sk, struct sk_buff *skb)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct xfrm_state *x = skb_dst(skb)->xfrm;
int err;
secpath_reset(skb);
skb->encapsulation = 0;
if (xfrm_dev_offload_ok(skb, x)) {
struct sec_path *sp;
sp = secpath_dup(skb->sp);
if (!sp) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
kfree_skb(skb);
return -ENOMEM;
}
if (skb->sp)
secpath_put(skb->sp);
skb->sp = sp;
skb->encapsulation = 1;
sp->olen++;
sp->xvec[skb->sp->len++] = x;
xfrm_state_hold(x);
if (skb_is_gso(skb)) {
skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;
return xfrm_output2(net, sk, skb);
}
if (x->xso.dev && x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM)
goto out;
}
if (skb_is_gso(skb))
return xfrm_output_gso(net, sk, skb);
if (skb->ip_summed == CHECKSUM_PARTIAL) {
err = skb_checksum_help(skb);
if (err) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
kfree_skb(skb);
return err;
}
}
out:
return xfrm_output2(net, sk, skb);
}
EXPORT_SYMBOL_GPL(xfrm_output);
int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct xfrm_mode *inner_mode;
if (x->sel.family == AF_UNSPEC)
inner_mode = xfrm_ip2inner_mode(x,
xfrm_af2proto(skb_dst(skb)->ops->family));
else
inner_mode = x->inner_mode;
if (inner_mode == NULL)
return -EAFNOSUPPORT;
return inner_mode->afinfo->extract_output(x, skb);
}
EXPORT_SYMBOL_GPL(xfrm_inner_extract_output);
void xfrm_local_error(struct sk_buff *skb, int mtu)
{
unsigned int proto;
struct xfrm_state_afinfo *afinfo;
if (skb->protocol == htons(ETH_P_IP))
proto = AF_INET;
else if (skb->protocol == htons(ETH_P_IPV6))
proto = AF_INET6;
else
return;
afinfo = xfrm_state_get_afinfo(proto);
if (afinfo)
afinfo->local_error(skb, mtu);
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(xfrm_local_error);