2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-15 16:53:54 +08:00
linux-next/net/xfrm/xfrm_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

237 lines
4.8 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 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);
}
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;
}
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);
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)
{
while (likely((err = xfrm_output_one(skb, err)) == 0)) {
nf_reset(skb);
err = skb_dst(skb)->ops->local_out(skb);
if (unlikely(err != 1))
goto out;
if (!skb_dst(skb)->xfrm)
return dst_output(skb);
err = nf_hook(skb_dst(skb)->ops->family,
NF_INET_POST_ROUTING, 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 sock *sk, struct sk_buff *skb)
{
return xfrm_output_resume(skb, 1);
}
static int xfrm_output_gso(struct sock *sk, struct sk_buff *skb)
{
struct sk_buff *segs;
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(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);
int err;
if (skb_is_gso(skb))
return xfrm_output_gso(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;
}
}
return xfrm_output2(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)
return;
afinfo->local_error(skb, mtu);
xfrm_state_put_afinfo(afinfo);
}
EXPORT_SYMBOL_GPL(xfrm_local_error);