linux/net/xfrm/xfrm_output.c

910 lines
21 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* xfrm_output.c - Common IPsec encapsulation code.
*
* Copyright (c) 2007 Herbert Xu <herbert@gondor.apana.org.au>
*/
#include <linux/errno.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/netfilter.h>
#include <linux/skbuff.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <net/dst.h>
#include <net/icmp.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ip6_route.h>
#include <net/ipv6_stubs.h>
#endif
#include "xfrm_inout.h"
static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb);
static int xfrm_inner_extract_output(struct xfrm_state *x, 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(xfrm_dst_child(skb_dst(skb)));
skb_dst_drop(skb);
return child;
}
/* Add encapsulation header.
*
* The IP header will be moved forward to make space for the encapsulation
* header.
*/
static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct iphdr *iph = ip_hdr(skb);
int ihl = iph->ihl * 4;
skb_set_inner_transport_header(skb, skb_transport_offset(skb));
skb_set_network_header(skb, -x->props.header_len);
skb->mac_header = skb->network_header +
offsetof(struct iphdr, protocol);
skb->transport_header = skb->network_header + ihl;
__skb_pull(skb, ihl);
memmove(skb_network_header(skb), iph, ihl);
return 0;
}
#if IS_ENABLED(CONFIG_IPV6_MIP6)
static int mip6_rthdr_offset(struct sk_buff *skb, u8 **nexthdr, int type)
{
const unsigned char *nh = skb_network_header(skb);
unsigned int offset = sizeof(struct ipv6hdr);
unsigned int packet_len;
int found_rhdr = 0;
packet_len = skb_tail_pointer(skb) - nh;
*nexthdr = &ipv6_hdr(skb)->nexthdr;
while (offset <= packet_len) {
struct ipv6_opt_hdr *exthdr;
switch (**nexthdr) {
case NEXTHDR_HOP:
break;
case NEXTHDR_ROUTING:
if (type == IPPROTO_ROUTING && offset + 3 <= packet_len) {
struct ipv6_rt_hdr *rt;
rt = (struct ipv6_rt_hdr *)(nh + offset);
if (rt->type != 0)
return offset;
}
found_rhdr = 1;
break;
case NEXTHDR_DEST:
/* HAO MUST NOT appear more than once.
* XXX: It is better to try to find by the end of
* XXX: packet if HAO exists.
*/
if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0) {
net_dbg_ratelimited("mip6: hao exists already, override\n");
return offset;
}
if (found_rhdr)
return offset;
break;
default:
return offset;
}
if (offset + sizeof(struct ipv6_opt_hdr) > packet_len)
return -EINVAL;
exthdr = (struct ipv6_opt_hdr *)(skb_network_header(skb) +
offset);
offset += ipv6_optlen(exthdr);
if (offset > IPV6_MAXPLEN)
return -EINVAL;
*nexthdr = &exthdr->nexthdr;
}
return -EINVAL;
}
#endif
#if IS_ENABLED(CONFIG_IPV6)
static int xfrm6_hdr_offset(struct xfrm_state *x, struct sk_buff *skb, u8 **prevhdr)
{
switch (x->type->proto) {
#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPPROTO_DSTOPTS:
case IPPROTO_ROUTING:
return mip6_rthdr_offset(skb, prevhdr, x->type->proto);
#endif
default:
break;
}
return ip6_find_1stfragopt(skb, prevhdr);
}
#endif
/* Add encapsulation header.
*
* The IP header and mutable extension headers will be moved forward to make
* space for the encapsulation header.
*/
static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_IPV6)
struct ipv6hdr *iph;
u8 *prevhdr;
int hdr_len;
iph = ipv6_hdr(skb);
skb_set_inner_transport_header(skb, skb_transport_offset(skb));
hdr_len = xfrm6_hdr_offset(x, skb, &prevhdr);
if (hdr_len < 0)
return hdr_len;
skb_set_mac_header(skb,
(prevhdr - x->props.header_len) - skb->data);
skb_set_network_header(skb, -x->props.header_len);
skb->transport_header = skb->network_header + hdr_len;
__skb_pull(skb, hdr_len);
memmove(ipv6_hdr(skb), iph, hdr_len);
return 0;
#else
WARN_ON_ONCE(1);
return -EAFNOSUPPORT;
#endif
}
/* Add route optimization header space.
*
* The IP header and mutable extension headers will be moved forward to make
* space for the route optimization header.
*/
static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_IPV6)
struct ipv6hdr *iph;
u8 *prevhdr;
int hdr_len;
iph = ipv6_hdr(skb);
hdr_len = xfrm6_hdr_offset(x, skb, &prevhdr);
if (hdr_len < 0)
return hdr_len;
skb_set_mac_header(skb,
(prevhdr - x->props.header_len) - skb->data);
skb_set_network_header(skb, -x->props.header_len);
skb->transport_header = skb->network_header + hdr_len;
__skb_pull(skb, hdr_len);
memmove(ipv6_hdr(skb), iph, hdr_len);
x->lastused = ktime_get_real_seconds();
return 0;
#else
WARN_ON_ONCE(1);
return -EAFNOSUPPORT;
#endif
}
/* Add encapsulation header.
*
* The top IP header will be constructed per draft-nikander-esp-beet-mode-06.txt.
*/
static int xfrm4_beet_encap_add(struct xfrm_state *x, struct sk_buff *skb)
{
struct ip_beet_phdr *ph;
struct iphdr *top_iph;
int hdrlen, optlen;
hdrlen = 0;
optlen = XFRM_MODE_SKB_CB(skb)->optlen;
if (unlikely(optlen))
hdrlen += IPV4_BEET_PHMAXLEN - (optlen & 4);
skb_set_network_header(skb, -x->props.header_len - hdrlen +
(XFRM_MODE_SKB_CB(skb)->ihl - sizeof(*top_iph)));
if (x->sel.family != AF_INET6)
skb->network_header += IPV4_BEET_PHMAXLEN;
skb->mac_header = skb->network_header +
offsetof(struct iphdr, protocol);
skb->transport_header = skb->network_header + sizeof(*top_iph);
xfrm4_beet_make_header(skb);
ph = __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdrlen);
top_iph = ip_hdr(skb);
if (unlikely(optlen)) {
if (WARN_ON(optlen < 0))
return -EINVAL;
ph->padlen = 4 - (optlen & 4);
ph->hdrlen = optlen / 8;
ph->nexthdr = top_iph->protocol;
if (ph->padlen)
memset(ph + 1, IPOPT_NOP, ph->padlen);
top_iph->protocol = IPPROTO_BEETPH;
top_iph->ihl = sizeof(struct iphdr) / 4;
}
top_iph->saddr = x->props.saddr.a4;
top_iph->daddr = x->id.daddr.a4;
return 0;
}
/* Add encapsulation header.
*
* The top IP header will be constructed per RFC 2401.
*/
static int xfrm4_tunnel_encap_add(struct xfrm_state *x, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct iphdr *top_iph;
int flags;
skb_set_inner_network_header(skb, skb_network_offset(skb));
skb_set_inner_transport_header(skb, skb_transport_offset(skb));
skb_set_network_header(skb, -x->props.header_len);
skb->mac_header = skb->network_header +
offsetof(struct iphdr, protocol);
skb->transport_header = skb->network_header + sizeof(*top_iph);
top_iph = ip_hdr(skb);
top_iph->ihl = 5;
top_iph->version = 4;
top_iph->protocol = xfrm_af2proto(skb_dst(skb)->ops->family);
/* DS disclosing depends on XFRM_SA_XFLAG_DONT_ENCAP_DSCP */
if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP)
top_iph->tos = 0;
else
top_iph->tos = XFRM_MODE_SKB_CB(skb)->tos;
top_iph->tos = INET_ECN_encapsulate(top_iph->tos,
XFRM_MODE_SKB_CB(skb)->tos);
flags = x->props.flags;
if (flags & XFRM_STATE_NOECN)
IP_ECN_clear(top_iph);
top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ?
0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF));
top_iph->ttl = ip4_dst_hoplimit(xfrm_dst_child(dst));
top_iph->saddr = x->props.saddr.a4;
top_iph->daddr = x->id.daddr.a4;
ip_select_ident(dev_net(dst->dev), skb, NULL);
return 0;
}
#if IS_ENABLED(CONFIG_IPV6)
static int xfrm6_tunnel_encap_add(struct xfrm_state *x, struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *top_iph;
int dsfield;
skb_set_inner_network_header(skb, skb_network_offset(skb));
skb_set_inner_transport_header(skb, skb_transport_offset(skb));
skb_set_network_header(skb, -x->props.header_len);
skb->mac_header = skb->network_header +
offsetof(struct ipv6hdr, nexthdr);
skb->transport_header = skb->network_header + sizeof(*top_iph);
top_iph = ipv6_hdr(skb);
top_iph->version = 6;
memcpy(top_iph->flow_lbl, XFRM_MODE_SKB_CB(skb)->flow_lbl,
sizeof(top_iph->flow_lbl));
top_iph->nexthdr = xfrm_af2proto(skb_dst(skb)->ops->family);
if (x->props.extra_flags & XFRM_SA_XFLAG_DONT_ENCAP_DSCP)
dsfield = 0;
else
dsfield = XFRM_MODE_SKB_CB(skb)->tos;
dsfield = INET_ECN_encapsulate(dsfield, XFRM_MODE_SKB_CB(skb)->tos);
if (x->props.flags & XFRM_STATE_NOECN)
dsfield &= ~INET_ECN_MASK;
ipv6_change_dsfield(top_iph, 0, dsfield);
top_iph->hop_limit = ip6_dst_hoplimit(xfrm_dst_child(dst));
top_iph->saddr = *(struct in6_addr *)&x->props.saddr;
top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
return 0;
}
static int xfrm6_beet_encap_add(struct xfrm_state *x, struct sk_buff *skb)
{
struct ipv6hdr *top_iph;
struct ip_beet_phdr *ph;
int optlen, hdr_len;
hdr_len = 0;
optlen = XFRM_MODE_SKB_CB(skb)->optlen;
if (unlikely(optlen))
hdr_len += IPV4_BEET_PHMAXLEN - (optlen & 4);
skb_set_network_header(skb, -x->props.header_len - hdr_len);
if (x->sel.family != AF_INET6)
skb->network_header += IPV4_BEET_PHMAXLEN;
skb->mac_header = skb->network_header +
offsetof(struct ipv6hdr, nexthdr);
skb->transport_header = skb->network_header + sizeof(*top_iph);
ph = __skb_pull(skb, XFRM_MODE_SKB_CB(skb)->ihl - hdr_len);
xfrm6_beet_make_header(skb);
top_iph = ipv6_hdr(skb);
if (unlikely(optlen)) {
if (WARN_ON(optlen < 0))
return -EINVAL;
ph->padlen = 4 - (optlen & 4);
ph->hdrlen = optlen / 8;
ph->nexthdr = top_iph->nexthdr;
if (ph->padlen)
memset(ph + 1, IPOPT_NOP, ph->padlen);
top_iph->nexthdr = IPPROTO_BEETPH;
}
top_iph->saddr = *(struct in6_addr *)&x->props.saddr;
top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
return 0;
}
#endif
/* Add encapsulation header.
*
* On exit, the transport header will be set to the start of the
* encapsulation header to be filled in by x->type->output and the mac
* header will be set to the nextheader (protocol for IPv4) field of the
* extension header directly preceding the encapsulation header, or in
* its absence, that of the top IP header.
* The value of the network header will always point to the top IP header
* while skb->data will point to the payload.
*/
static 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);
switch (x->outer_mode.encap) {
case XFRM_MODE_BEET:
return xfrm4_beet_encap_add(x, skb);
case XFRM_MODE_TUNNEL:
return xfrm4_tunnel_encap_add(x, skb);
}
WARN_ON_ONCE(1);
return -EOPNOTSUPP;
}
static int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_IPV6)
int err;
err = xfrm_inner_extract_output(x, skb);
if (err)
return err;
skb->ignore_df = 1;
skb->protocol = htons(ETH_P_IPV6);
switch (x->outer_mode.encap) {
case XFRM_MODE_BEET:
return xfrm6_beet_encap_add(x, skb);
case XFRM_MODE_TUNNEL:
return xfrm6_tunnel_encap_add(x, skb);
default:
WARN_ON_ONCE(1);
return -EOPNOTSUPP;
}
#endif
WARN_ON_ONCE(1);
return -EAFNOSUPPORT;
}
static int xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb)
{
switch (x->outer_mode.encap) {
case XFRM_MODE_BEET:
case XFRM_MODE_TUNNEL:
if (x->outer_mode.family == AF_INET)
return xfrm4_prepare_output(x, skb);
if (x->outer_mode.family == AF_INET6)
return xfrm6_prepare_output(x, skb);
break;
case XFRM_MODE_TRANSPORT:
if (x->outer_mode.family == AF_INET)
return xfrm4_transport_output(x, skb);
if (x->outer_mode.family == AF_INET6)
return xfrm6_transport_output(x, skb);
break;
case XFRM_MODE_ROUTEOPTIMIZATION:
if (x->outer_mode.family == AF_INET6)
return xfrm6_ro_output(x, skb);
WARN_ON_ONCE(1);
break;
default:
WARN_ON_ONCE(1);
break;
}
return -EOPNOTSUPP;
}
#if IS_ENABLED(CONFIG_NET_PKTGEN)
int pktgen_xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb)
{
return xfrm_outer_mode_output(x, skb);
}
EXPORT_SYMBOL_GPL(pktgen_xfrm_outer_mode_output);
#endif
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;
}
skb->mark = xfrm_smark_get(skb->mark, x);
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>
2017-08-10 17:11:33 +00:00
err = xfrm_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 = xfrm_replay_overflow(x, skb);
if (err) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATESEQERROR);
goto error;
}
x->curlft.bytes += skb->len;
x->curlft.packets++;
x->curlft.use_time = ktime_get_real_seconds();
spin_unlock_bh(&x->lock);
skb_dst_force(skb);
if (!skb_dst(skb)) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
err = -EHOSTUNREACH;
goto error_nolock;
}
if (xfrm_offload(skb)) {
x->type_offload->encap(x, skb);
} else {
/* Inner headers are invalid now. */
skb->encapsulation = 0;
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;
}
2021-03-01 19:00:04 +00:00
int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err)
{
2015-09-16 01:04:16 +00:00
struct net *net = xs_net(skb_dst(skb)->xfrm);
while (likely((err = xfrm_output_one(skb, err)) == 0)) {
nf_reset_ct(skb);
2021-03-01 19:00:04 +00:00
err = skb_dst(skb)->ops->local_out(net, sk, skb);
if (unlikely(err != 1))
goto out;
if (!skb_dst(skb)->xfrm)
2021-03-01 19:00:04 +00:00
return dst_output(net, sk, skb);
err = nf_hook(skb_dst(skb)->ops->family,
2021-03-01 19:00:04 +00:00
NF_INET_POST_ROUTING, net, 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)
{
2021-03-01 19:00:04 +00:00
return xfrm_output_resume(sk, skb, 1);
}
static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct sk_buff *segs, *nskb;
BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_GSO_CB_OFFSET);
BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_GSO_CB_OFFSET);
segs = skb_gso_segment(skb, 0);
kfree_skb(skb);
if (IS_ERR(segs))
return PTR_ERR(segs);
if (segs == NULL)
return -EINVAL;
skb_list_walk_safe(segs, segs, nskb) {
int err;
skb_mark_not_on_list(segs);
err = xfrm_output2(net, sk, segs);
if (unlikely(err)) {
kfree_skb_list(nskb);
return err;
}
}
return 0;
}
/* For partial checksum offload, the outer header checksum is calculated
* by software and the inner header checksum is calculated by hardware.
* This requires hardware to know the inner packet type to calculate
* the inner header checksum. Save inner ip protocol here to avoid
* traversing the packet in the vendor's xmit code.
* For IPsec tunnel mode save the ip protocol from the IP header of the
* plain text packet. Otherwise If the encap type is IPIP, just save
* skb->inner_ipproto in any other case get the ip protocol from the IP
* header.
*/
static void xfrm_get_inner_ipproto(struct sk_buff *skb, struct xfrm_state *x)
{
struct xfrm_offload *xo = xfrm_offload(skb);
const struct ethhdr *eth;
if (!xo)
return;
if (x->outer_mode.encap == XFRM_MODE_TUNNEL) {
switch (x->outer_mode.family) {
case AF_INET:
xo->inner_ipproto = ip_hdr(skb)->protocol;
break;
case AF_INET6:
xo->inner_ipproto = ipv6_hdr(skb)->nexthdr;
break;
default:
break;
}
return;
}
/* non-Tunnel Mode */
if (!skb->encapsulation)
return;
if (skb->inner_protocol_type == ENCAP_TYPE_IPPROTO) {
xo->inner_ipproto = skb->inner_ipproto;
return;
}
if (skb->inner_protocol_type != ENCAP_TYPE_ETHER)
return;
eth = (struct ethhdr *)skb_inner_mac_header(skb);
switch (ntohs(eth->h_proto)) {
case ETH_P_IPV6:
xo->inner_ipproto = inner_ipv6_hdr(skb)->nexthdr;
break;
case ETH_P_IP:
xo->inner_ipproto = inner_ip_hdr(skb)->protocol;
break;
}
}
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;
switch (x->outer_mode.family) {
case AF_INET:
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED;
break;
case AF_INET6:
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED;
break;
}
secpath_reset(skb);
if (xfrm_dev_offload_ok(skb, x)) {
struct sec_path *sp;
sp = secpath_set(skb);
if (!sp) {
XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
kfree_skb(skb);
return -ENOMEM;
}
sp->olen++;
sp->xvec[sp->len++] = x;
xfrm_state_hold(x);
xfrm_get_inner_ipproto(skb, x);
skb->encapsulation = 1;
if (skb_is_gso(skb)) {
xfrm: call xfrm_output_gso when inner_protocol is set in xfrm_output An use-after-free crash can be triggered when sending big packets over vxlan over esp with esp offload enabled: [] BUG: KASAN: use-after-free in ipv6_gso_pull_exthdrs.part.8+0x32c/0x4e0 [] Call Trace: [] dump_stack+0x75/0xa0 [] kasan_report+0x37/0x50 [] ipv6_gso_pull_exthdrs.part.8+0x32c/0x4e0 [] ipv6_gso_segment+0x2c8/0x13c0 [] skb_mac_gso_segment+0x1cb/0x420 [] skb_udp_tunnel_segment+0x6b5/0x1c90 [] inet_gso_segment+0x440/0x1380 [] skb_mac_gso_segment+0x1cb/0x420 [] esp4_gso_segment+0xae8/0x1709 [esp4_offload] [] inet_gso_segment+0x440/0x1380 [] skb_mac_gso_segment+0x1cb/0x420 [] __skb_gso_segment+0x2d7/0x5f0 [] validate_xmit_skb+0x527/0xb10 [] __dev_queue_xmit+0x10f8/0x2320 <--- [] ip_finish_output2+0xa2e/0x1b50 [] ip_output+0x1a8/0x2f0 [] xfrm_output_resume+0x110e/0x15f0 [] __xfrm4_output+0xe1/0x1b0 [] xfrm4_output+0xa0/0x200 [] iptunnel_xmit+0x5a7/0x920 [] vxlan_xmit_one+0x1658/0x37a0 [vxlan] [] vxlan_xmit+0x5e4/0x3ec8 [vxlan] [] dev_hard_start_xmit+0x125/0x540 [] __dev_queue_xmit+0x17bd/0x2320 <--- [] ip6_finish_output2+0xb20/0x1b80 [] ip6_output+0x1b3/0x390 [] ip6_xmit+0xb82/0x17e0 [] inet6_csk_xmit+0x225/0x3d0 [] __tcp_transmit_skb+0x1763/0x3520 [] tcp_write_xmit+0xd64/0x5fe0 [] __tcp_push_pending_frames+0x8c/0x320 [] tcp_sendmsg_locked+0x2245/0x3500 [] tcp_sendmsg+0x27/0x40 As on the tx path of vxlan over esp, skb->inner_network_header would be set on vxlan_xmit() and xfrm4_tunnel_encap_add(), and the later one can overwrite the former one. It causes skb_udp_tunnel_segment() to use a wrong skb->inner_network_header, then the issue occurs. This patch is to fix it by calling xfrm_output_gso() instead when the inner_protocol is set, in which gso_segment of inner_protocol will be done first. While at it, also improve some code around. Fixes: 7862b4058b9f ("esp: Add gso handlers for esp4 and esp6") Reported-by: Xiumei Mu <xmu@redhat.com> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2020-04-20 13:51:09 +00:00
if (skb->inner_protocol)
return xfrm_output_gso(net, sk, skb);
xfrm: call xfrm_output_gso when inner_protocol is set in xfrm_output An use-after-free crash can be triggered when sending big packets over vxlan over esp with esp offload enabled: [] BUG: KASAN: use-after-free in ipv6_gso_pull_exthdrs.part.8+0x32c/0x4e0 [] Call Trace: [] dump_stack+0x75/0xa0 [] kasan_report+0x37/0x50 [] ipv6_gso_pull_exthdrs.part.8+0x32c/0x4e0 [] ipv6_gso_segment+0x2c8/0x13c0 [] skb_mac_gso_segment+0x1cb/0x420 [] skb_udp_tunnel_segment+0x6b5/0x1c90 [] inet_gso_segment+0x440/0x1380 [] skb_mac_gso_segment+0x1cb/0x420 [] esp4_gso_segment+0xae8/0x1709 [esp4_offload] [] inet_gso_segment+0x440/0x1380 [] skb_mac_gso_segment+0x1cb/0x420 [] __skb_gso_segment+0x2d7/0x5f0 [] validate_xmit_skb+0x527/0xb10 [] __dev_queue_xmit+0x10f8/0x2320 <--- [] ip_finish_output2+0xa2e/0x1b50 [] ip_output+0x1a8/0x2f0 [] xfrm_output_resume+0x110e/0x15f0 [] __xfrm4_output+0xe1/0x1b0 [] xfrm4_output+0xa0/0x200 [] iptunnel_xmit+0x5a7/0x920 [] vxlan_xmit_one+0x1658/0x37a0 [vxlan] [] vxlan_xmit+0x5e4/0x3ec8 [vxlan] [] dev_hard_start_xmit+0x125/0x540 [] __dev_queue_xmit+0x17bd/0x2320 <--- [] ip6_finish_output2+0xb20/0x1b80 [] ip6_output+0x1b3/0x390 [] ip6_xmit+0xb82/0x17e0 [] inet6_csk_xmit+0x225/0x3d0 [] __tcp_transmit_skb+0x1763/0x3520 [] tcp_write_xmit+0xd64/0x5fe0 [] __tcp_push_pending_frames+0x8c/0x320 [] tcp_sendmsg_locked+0x2245/0x3500 [] tcp_sendmsg+0x27/0x40 As on the tx path of vxlan over esp, skb->inner_network_header would be set on vxlan_xmit() and xfrm4_tunnel_encap_add(), and the later one can overwrite the former one. It causes skb_udp_tunnel_segment() to use a wrong skb->inner_network_header, then the issue occurs. This patch is to fix it by calling xfrm_output_gso() instead when the inner_protocol is set, in which gso_segment of inner_protocol will be done first. While at it, also improve some code around. Fixes: 7862b4058b9f ("esp: Add gso handlers for esp4 and esp6") Reported-by: Xiumei Mu <xmu@redhat.com> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2020-04-20 13:51:09 +00:00
skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;
goto out;
}
if (x->xso.dev && x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM)
goto out;
xfrm: call xfrm_output_gso when inner_protocol is set in xfrm_output An use-after-free crash can be triggered when sending big packets over vxlan over esp with esp offload enabled: [] BUG: KASAN: use-after-free in ipv6_gso_pull_exthdrs.part.8+0x32c/0x4e0 [] Call Trace: [] dump_stack+0x75/0xa0 [] kasan_report+0x37/0x50 [] ipv6_gso_pull_exthdrs.part.8+0x32c/0x4e0 [] ipv6_gso_segment+0x2c8/0x13c0 [] skb_mac_gso_segment+0x1cb/0x420 [] skb_udp_tunnel_segment+0x6b5/0x1c90 [] inet_gso_segment+0x440/0x1380 [] skb_mac_gso_segment+0x1cb/0x420 [] esp4_gso_segment+0xae8/0x1709 [esp4_offload] [] inet_gso_segment+0x440/0x1380 [] skb_mac_gso_segment+0x1cb/0x420 [] __skb_gso_segment+0x2d7/0x5f0 [] validate_xmit_skb+0x527/0xb10 [] __dev_queue_xmit+0x10f8/0x2320 <--- [] ip_finish_output2+0xa2e/0x1b50 [] ip_output+0x1a8/0x2f0 [] xfrm_output_resume+0x110e/0x15f0 [] __xfrm4_output+0xe1/0x1b0 [] xfrm4_output+0xa0/0x200 [] iptunnel_xmit+0x5a7/0x920 [] vxlan_xmit_one+0x1658/0x37a0 [vxlan] [] vxlan_xmit+0x5e4/0x3ec8 [vxlan] [] dev_hard_start_xmit+0x125/0x540 [] __dev_queue_xmit+0x17bd/0x2320 <--- [] ip6_finish_output2+0xb20/0x1b80 [] ip6_output+0x1b3/0x390 [] ip6_xmit+0xb82/0x17e0 [] inet6_csk_xmit+0x225/0x3d0 [] __tcp_transmit_skb+0x1763/0x3520 [] tcp_write_xmit+0xd64/0x5fe0 [] __tcp_push_pending_frames+0x8c/0x320 [] tcp_sendmsg_locked+0x2245/0x3500 [] tcp_sendmsg+0x27/0x40 As on the tx path of vxlan over esp, skb->inner_network_header would be set on vxlan_xmit() and xfrm4_tunnel_encap_add(), and the later one can overwrite the former one. It causes skb_udp_tunnel_segment() to use a wrong skb->inner_network_header, then the issue occurs. This patch is to fix it by calling xfrm_output_gso() instead when the inner_protocol is set, in which gso_segment of inner_protocol will be done first. While at it, also improve some code around. Fixes: 7862b4058b9f ("esp: Add gso handlers for esp4 and esp6") Reported-by: Xiumei Mu <xmu@redhat.com> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2020-04-20 13:51:09 +00:00
} else {
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);
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_is_gso(skb) && skb->len > mtu) ||
(skb_is_gso(skb) &&
!skb_gso_validate_network_len(skb, ip_skb_dst_mtu(skb->sk, skb)))) {
skb->protocol = htons(ETH_P_IP);
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;
}
static int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb)
{
int err;
if (x->outer_mode.encap == XFRM_MODE_BEET &&
ip_is_fragment(ip_hdr(skb))) {
net_warn_ratelimited("BEET mode doesn't support inner IPv4 fragments\n");
return -EAFNOSUPPORT;
}
err = xfrm4_tunnel_check_size(skb);
if (err)
return err;
XFRM_MODE_SKB_CB(skb)->protocol = ip_hdr(skb)->protocol;
xfrm4_extract_header(skb);
return 0;
}
#if IS_ENABLED(CONFIG_IPV6)
static int xfrm6_tunnel_check_size(struct sk_buff *skb)
{
int mtu, ret = 0;
struct dst_entry *dst = skb_dst(skb);
if (skb->ignore_df)
goto out;
mtu = dst_mtu(dst);
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
if ((!skb_is_gso(skb) && skb->len > mtu) ||
(skb_is_gso(skb) &&
!skb_gso_validate_network_len(skb, ip6_skb_dst_mtu(skb)))) {
skb->dev = dst->dev;
skb->protocol = htons(ETH_P_IPV6);
if (xfrm6_local_dontfrag(skb->sk))
ipv6_stub->xfrm6_local_rxpmtu(skb, mtu);
else if (skb->sk)
xfrm_local_error(skb, mtu);
else
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
ret = -EMSGSIZE;
}
out:
return ret;
}
#endif
static int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb)
{
#if IS_ENABLED(CONFIG_IPV6)
int err;
err = xfrm6_tunnel_check_size(skb);
if (err)
return err;
XFRM_MODE_SKB_CB(skb)->protocol = ipv6_hdr(skb)->nexthdr;
xfrm6_extract_header(skb);
return 0;
#else
WARN_ON_ONCE(1);
return -EAFNOSUPPORT;
#endif
}
static int xfrm_inner_extract_output(struct xfrm_state *x, struct sk_buff *skb)
{
const 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;
switch (inner_mode->family) {
case AF_INET:
return xfrm4_extract_output(x, skb);
case AF_INET6:
return xfrm6_extract_output(x, skb);
}
return -EAFNOSUPPORT;
}
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;
xfrm: fix a NULL-ptr deref in xfrm_local_error This patch is to fix a crash: [ ] kasan: GPF could be caused by NULL-ptr deref or user memory access [ ] general protection fault: 0000 [#1] SMP KASAN PTI [ ] RIP: 0010:ipv6_local_error+0xac/0x7a0 [ ] Call Trace: [ ] xfrm6_local_error+0x1eb/0x300 [ ] xfrm_local_error+0x95/0x130 [ ] __xfrm6_output+0x65f/0xb50 [ ] xfrm6_output+0x106/0x46f [ ] udp_tunnel6_xmit_skb+0x618/0xbf0 [ip6_udp_tunnel] [ ] vxlan_xmit_one+0xbc6/0x2c60 [vxlan] [ ] vxlan_xmit+0x6a0/0x4276 [vxlan] [ ] dev_hard_start_xmit+0x165/0x820 [ ] __dev_queue_xmit+0x1ff0/0x2b90 [ ] ip_finish_output2+0xd3e/0x1480 [ ] ip_do_fragment+0x182d/0x2210 [ ] ip_output+0x1d0/0x510 [ ] ip_send_skb+0x37/0xa0 [ ] raw_sendmsg+0x1b4c/0x2b80 [ ] sock_sendmsg+0xc0/0x110 This occurred when sending a v4 skb over vxlan6 over ipsec, in which case skb->protocol == htons(ETH_P_IPV6) while skb->sk->sk_family == AF_INET in xfrm_local_error(). Then it will go to xfrm6_local_error() where it tries to get ipv6 info from a ipv4 sk. This issue was actually fixed by Commit 628e341f319f ("xfrm: make local error reporting more robust"), but brought back by Commit 844d48746e4b ("xfrm: choose protocol family by skb protocol"). So to fix it, we should call xfrm6_local_error() only when skb->protocol is htons(ETH_P_IPV6) and skb->sk->sk_family is AF_INET6. Fixes: 844d48746e4b ("xfrm: choose protocol family by skb protocol") Reported-by: Xiumei Mu <xmu@redhat.com> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2020-05-26 09:41:46 +00:00
else if (skb->protocol == htons(ETH_P_IPV6) &&
skb->sk->sk_family == AF_INET6)
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);