renegade-project/linux-next
2
0
Fork 0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-27 14:43:58 +08:00
Code
425aa0e1d0
linux-next/net/ipv4/ip_tunnel_core.c
Johannes Berg 8cb081746c netlink: make validation more configurable for future strictness 
We currently have two levels of strict validation:

 1) liberal (default)
     - undefined (type >= max) & NLA_UNSPEC attributes accepted
     - attribute length >= expected accepted
     - garbage at end of message accepted
 2) strict (opt-in)
     - NLA_UNSPEC attributes accepted
     - attribute length >= expected accepted

Split out parsing strictness into four different options:
 * TRAILING     - check that there's no trailing data after parsing
                  attributes (in message or nested)
 * MAXTYPE      - reject attrs > max known type
 * UNSPEC       - reject attributes with NLA_UNSPEC policy entries
 * STRICT_ATTRS - strictly validate attribute size

The default for future things should be *everything*.
The current *_strict() is a combination of TRAILING and MAXTYPE,
and is renamed to _deprecated_strict().
The current regular parsing has none of this, and is renamed to
*_parse_deprecated().

Additionally it allows us to selectively set one of the new flags
even on old policies. Notably, the UNSPEC flag could be useful in
this case, since it can be arranged (by filling in the policy) to
not be an incompatible userspace ABI change, but would then going
forward prevent forgetting attribute entries. Similar can apply
to the POLICY flag.

We end up with the following renames:
 * nla_parse           -> nla_parse_deprecated
 * nla_parse_strict    -> nla_parse_deprecated_strict
 * nlmsg_parse         -> nlmsg_parse_deprecated
 * nlmsg_parse_strict  -> nlmsg_parse_deprecated_strict
 * nla_parse_nested    -> nla_parse_nested_deprecated
 * nla_validate_nested -> nla_validate_nested_deprecated

Using spatch, of course:
    @@
    expression TB, MAX, HEAD, LEN, POL, EXT;
    @@
    -nla_parse(TB, MAX, HEAD, LEN, POL, EXT)
    +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT)

    @@
    expression NLH, HDRLEN, TB, MAX, POL, EXT;
    @@
    -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT)
    +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT)

    @@
    expression NLH, HDRLEN, TB, MAX, POL, EXT;
    @@
    -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT)
    +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT)

    @@
    expression TB, MAX, NLA, POL, EXT;
    @@
    -nla_parse_nested(TB, MAX, NLA, POL, EXT)
    +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT)

    @@
    expression START, MAX, POL, EXT;
    @@
    -nla_validate_nested(START, MAX, POL, EXT)
    +nla_validate_nested_deprecated(START, MAX, POL, EXT)

    @@
    expression NLH, HDRLEN, MAX, POL, EXT;
    @@
    -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT)
    +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT)

For this patch, don't actually add the strict, non-renamed versions
yet so that it breaks compile if I get it wrong.

Also, while at it, make nla_validate and nla_parse go down to a
common __nla_validate_parse() function to avoid code duplication.

Ultimately, this allows us to have very strict validation for every
new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the
next patch, while existing things will continue to work as is.

In effect then, this adds fully strict validation for any new command.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-27 17:07:21 -04:00

459 lines
12 KiB
C
Raw Blame History

/*
* Copyright (c) 2013 Nicira, Inc.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of version 2 of the GNU General Public
* License as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
* 02110-1301, USA
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/in6.h>
#include <linux/inetdevice.h>
#include <linux/netfilter_ipv4.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <linux/if_vlan.h>
#include <linux/static_key.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/ip_tunnels.h>
#include <net/ip6_tunnel.h>
#include <net/arp.h>
#include <net/checksum.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#include <net/dst_metadata.h>
const struct ip_tunnel_encap_ops __rcu *
iptun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
EXPORT_SYMBOL(iptun_encaps);
const struct ip6_tnl_encap_ops __rcu *
ip6tun_encaps[MAX_IPTUN_ENCAP_OPS] __read_mostly;
EXPORT_SYMBOL(ip6tun_encaps);
void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
__be32 src, __be32 dst, __u8 proto,
__u8 tos, __u8 ttl, __be16 df, bool xnet)
{
int pkt_len = skb->len - skb_inner_network_offset(skb);
struct net *net = dev_net(rt->dst.dev);
struct net_device *dev = skb->dev;
struct iphdr *iph;
int err;
skb_scrub_packet(skb, xnet);
skb_clear_hash_if_not_l4(skb);
skb_dst_set(skb, &rt->dst);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
/* Push down and install the IP header. */
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = ip_mtu_locked(&rt->dst) ? 0 : df;
iph->protocol = proto;
iph->tos = tos;
iph->daddr = dst;
iph->saddr = src;
iph->ttl = ttl;
__ip_select_ident(net, iph, skb_shinfo(skb)->gso_segs ?: 1);
err = ip_local_out(net, sk, skb);
if (unlikely(net_xmit_eval(err)))
pkt_len = 0;
iptunnel_xmit_stats(dev, pkt_len);
}
EXPORT_SYMBOL_GPL(iptunnel_xmit);
int __iptunnel_pull_header(struct sk_buff *skb, int hdr_len,
__be16 inner_proto, bool raw_proto, bool xnet)
{
if (unlikely(!pskb_may_pull(skb, hdr_len)))
return -ENOMEM;
skb_pull_rcsum(skb, hdr_len);
if (!raw_proto && inner_proto == htons(ETH_P_TEB)) {
struct ethhdr *eh;
if (unlikely(!pskb_may_pull(skb, ETH_HLEN)))
return -ENOMEM;
eh = (struct ethhdr *)skb->data;
if (likely(eth_proto_is_802_3(eh->h_proto)))
skb->protocol = eh->h_proto;
else
skb->protocol = htons(ETH_P_802_2);
} else {
skb->protocol = inner_proto;
}
skb_clear_hash_if_not_l4(skb);
__vlan_hwaccel_clear_tag(skb);
skb_set_queue_mapping(skb, 0);
skb_scrub_packet(skb, xnet);
return iptunnel_pull_offloads(skb);
}
EXPORT_SYMBOL_GPL(__iptunnel_pull_header);
struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md,
gfp_t flags)
{
struct metadata_dst *res;
struct ip_tunnel_info *dst, *src;
if (!md || md->type != METADATA_IP_TUNNEL ||
md->u.tun_info.mode & IP_TUNNEL_INFO_TX)
return NULL;
res = metadata_dst_alloc(0, METADATA_IP_TUNNEL, flags);
if (!res)
return NULL;
dst = &res->u.tun_info;
src = &md->u.tun_info;
dst->key.tun_id = src->key.tun_id;
if (src->mode & IP_TUNNEL_INFO_IPV6)
memcpy(&dst->key.u.ipv6.dst, &src->key.u.ipv6.src,
sizeof(struct in6_addr));
else
dst->key.u.ipv4.dst = src->key.u.ipv4.src;
dst->key.tun_flags = src->key.tun_flags;
dst->mode = src->mode | IP_TUNNEL_INFO_TX;
return res;
}
EXPORT_SYMBOL_GPL(iptunnel_metadata_reply);
int iptunnel_handle_offloads(struct sk_buff *skb,
int gso_type_mask)
{
int err;
if (likely(!skb->encapsulation)) {
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
}
if (skb_is_gso(skb)) {
err = skb_header_unclone(skb, GFP_ATOMIC);
if (unlikely(err))
return err;
skb_shinfo(skb)->gso_type |= gso_type_mask;
return 0;
}
if (skb->ip_summed != CHECKSUM_PARTIAL) {
skb->ip_summed = CHECKSUM_NONE;
/* We clear encapsulation here to prevent badly-written
* drivers potentially deciding to offload an inner checksum
* if we set CHECKSUM_PARTIAL on the outer header.
* This should go away when the drivers are all fixed.
*/
skb->encapsulation = 0;
}
return 0;
}
EXPORT_SYMBOL_GPL(iptunnel_handle_offloads);
/* Often modified stats are per cpu, other are shared (netdev->stats) */
void ip_tunnel_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *tot)
{
int i;
netdev_stats_to_stats64(tot, &dev->stats);
for_each_possible_cpu(i) {
const struct pcpu_sw_netstats *tstats =
per_cpu_ptr(dev->tstats, i);
u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
unsigned int start;
do {
start = u64_stats_fetch_begin_irq(&tstats->syncp);
rx_packets = tstats->rx_packets;
tx_packets = tstats->tx_packets;
rx_bytes = tstats->rx_bytes;
tx_bytes = tstats->tx_bytes;
} while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
tot->rx_packets += rx_packets;
tot->tx_packets += tx_packets;
tot->rx_bytes += rx_bytes;
tot->tx_bytes += tx_bytes;
}
}
EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = {
[LWTUNNEL_IP_ID] = { .type = NLA_U64 },
[LWTUNNEL_IP_DST] = { .type = NLA_U32 },
[LWTUNNEL_IP_SRC] = { .type = NLA_U32 },
[LWTUNNEL_IP_TTL] = { .type = NLA_U8 },
[LWTUNNEL_IP_TOS] = { .type = NLA_U8 },
[LWTUNNEL_IP_FLAGS] = { .type = NLA_U16 },
};
static int ip_tun_build_state(struct nlattr *attr,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts,
struct netlink_ext_ack *extack)
{
struct ip_tunnel_info *tun_info;
struct lwtunnel_state *new_state;
struct nlattr *tb[LWTUNNEL_IP_MAX + 1];
int err;
err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP_MAX, attr,
ip_tun_policy, extack);
if (err < 0)
return err;
new_state = lwtunnel_state_alloc(sizeof(*tun_info));
if (!new_state)
return -ENOMEM;
new_state->type = LWTUNNEL_ENCAP_IP;
tun_info = lwt_tun_info(new_state);
#ifdef CONFIG_DST_CACHE
err = dst_cache_init(&tun_info->dst_cache, GFP_KERNEL);
if (err) {
lwtstate_free(new_state);
return err;
}
#endif
if (tb[LWTUNNEL_IP_ID])
tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP_ID]);
if (tb[LWTUNNEL_IP_DST])
tun_info->key.u.ipv4.dst = nla_get_in_addr(tb[LWTUNNEL_IP_DST]);
if (tb[LWTUNNEL_IP_SRC])
tun_info->key.u.ipv4.src = nla_get_in_addr(tb[LWTUNNEL_IP_SRC]);
if (tb[LWTUNNEL_IP_TTL])
tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP_TTL]);
if (tb[LWTUNNEL_IP_TOS])
tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]);
if (tb[LWTUNNEL_IP_FLAGS])
tun_info->key.tun_flags = nla_get_be16(tb[LWTUNNEL_IP_FLAGS]);
tun_info->mode = IP_TUNNEL_INFO_TX;
tun_info->options_len = 0;
*ts = new_state;
return 0;
}
static void ip_tun_destroy_state(struct lwtunnel_state *lwtstate)
{
#ifdef CONFIG_DST_CACHE
struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate);
dst_cache_destroy(&tun_info->dst_cache);
#endif
}
static int ip_tun_fill_encap_info(struct sk_buff *skb,
struct lwtunnel_state *lwtstate)
{
struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate);
if (nla_put_be64(skb, LWTUNNEL_IP_ID, tun_info->key.tun_id,
LWTUNNEL_IP_PAD) ||
nla_put_in_addr(skb, LWTUNNEL_IP_DST, tun_info->key.u.ipv4.dst) ||
nla_put_in_addr(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) ||
nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) ||
nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) ||
nla_put_be16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags))
return -ENOMEM;
return 0;
}
static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
{
return nla_total_size_64bit(8) /* LWTUNNEL_IP_ID */
+ nla_total_size(4) /* LWTUNNEL_IP_DST */
+ nla_total_size(4) /* LWTUNNEL_IP_SRC */
+ nla_total_size(1) /* LWTUNNEL_IP_TOS */
+ nla_total_size(1) /* LWTUNNEL_IP_TTL */
+ nla_total_size(2); /* LWTUNNEL_IP_FLAGS */
}
static int ip_tun_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b)
{
return memcmp(lwt_tun_info(a), lwt_tun_info(b),
sizeof(struct ip_tunnel_info));
}
static const struct lwtunnel_encap_ops ip_tun_lwt_ops = {
.build_state = ip_tun_build_state,
.destroy_state = ip_tun_destroy_state,
.fill_encap = ip_tun_fill_encap_info,
.get_encap_size = ip_tun_encap_nlsize,
.cmp_encap = ip_tun_cmp_encap,
.owner = THIS_MODULE,
};
static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = {
[LWTUNNEL_IP6_ID] = { .type = NLA_U64 },
[LWTUNNEL_IP6_DST] = { .len = sizeof(struct in6_addr) },
[LWTUNNEL_IP6_SRC] = { .len = sizeof(struct in6_addr) },
[LWTUNNEL_IP6_HOPLIMIT] = { .type = NLA_U8 },
[LWTUNNEL_IP6_TC] = { .type = NLA_U8 },
[LWTUNNEL_IP6_FLAGS] = { .type = NLA_U16 },
};
static int ip6_tun_build_state(struct nlattr *attr,
unsigned int family, const void *cfg,
struct lwtunnel_state **ts,
struct netlink_ext_ack *extack)
{
struct ip_tunnel_info *tun_info;
struct lwtunnel_state *new_state;
struct nlattr *tb[LWTUNNEL_IP6_MAX + 1];
int err;
err = nla_parse_nested_deprecated(tb, LWTUNNEL_IP6_MAX, attr,
ip6_tun_policy, extack);
if (err < 0)
return err;
new_state = lwtunnel_state_alloc(sizeof(*tun_info));
if (!new_state)
return -ENOMEM;
new_state->type = LWTUNNEL_ENCAP_IP6;
tun_info = lwt_tun_info(new_state);
if (tb[LWTUNNEL_IP6_ID])
tun_info->key.tun_id = nla_get_be64(tb[LWTUNNEL_IP6_ID]);
if (tb[LWTUNNEL_IP6_DST])
tun_info->key.u.ipv6.dst = nla_get_in6_addr(tb[LWTUNNEL_IP6_DST]);
if (tb[LWTUNNEL_IP6_SRC])
tun_info->key.u.ipv6.src = nla_get_in6_addr(tb[LWTUNNEL_IP6_SRC]);
if (tb[LWTUNNEL_IP6_HOPLIMIT])
tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP6_HOPLIMIT]);
if (tb[LWTUNNEL_IP6_TC])
tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]);
if (tb[LWTUNNEL_IP6_FLAGS])
tun_info->key.tun_flags = nla_get_be16(tb[LWTUNNEL_IP6_FLAGS]);
tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6;
tun_info->options_len = 0;
*ts = new_state;
return 0;
}
static int ip6_tun_fill_encap_info(struct sk_buff *skb,
struct lwtunnel_state *lwtstate)
{
struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate);
if (nla_put_be64(skb, LWTUNNEL_IP6_ID, tun_info->key.tun_id,
LWTUNNEL_IP6_PAD) ||
nla_put_in6_addr(skb, LWTUNNEL_IP6_DST, &tun_info->key.u.ipv6.dst) ||
nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) ||
nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.tos) ||
nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.ttl) ||
nla_put_be16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags))
return -ENOMEM;
return 0;
}
static int ip6_tun_encap_nlsize(struct lwtunnel_state *lwtstate)
{
return nla_total_size_64bit(8) /* LWTUNNEL_IP6_ID */
+ nla_total_size(16) /* LWTUNNEL_IP6_DST */
+ nla_total_size(16) /* LWTUNNEL_IP6_SRC */
+ nla_total_size(1) /* LWTUNNEL_IP6_HOPLIMIT */
+ nla_total_size(1) /* LWTUNNEL_IP6_TC */
+ nla_total_size(2); /* LWTUNNEL_IP6_FLAGS */
}
static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = {
.build_state = ip6_tun_build_state,
.fill_encap = ip6_tun_fill_encap_info,
.get_encap_size = ip6_tun_encap_nlsize,
.cmp_encap = ip_tun_cmp_encap,
.owner = THIS_MODULE,
};
void __init ip_tunnel_core_init(void)
{
/* If you land here, make sure whether increasing ip_tunnel_info's
* options_len is a reasonable choice with its usage in front ends
* (f.e., it's part of flow keys, etc).
*/
BUILD_BUG_ON(IP_TUNNEL_OPTS_MAX != 255);
lwtunnel_encap_add_ops(&ip_tun_lwt_ops, LWTUNNEL_ENCAP_IP);
lwtunnel_encap_add_ops(&ip6_tun_lwt_ops, LWTUNNEL_ENCAP_IP6);
}
DEFINE_STATIC_KEY_FALSE(ip_tunnel_metadata_cnt);
EXPORT_SYMBOL(ip_tunnel_metadata_cnt);
void ip_tunnel_need_metadata(void)
{
static_branch_inc(&ip_tunnel_metadata_cnt);
}
EXPORT_SYMBOL_GPL(ip_tunnel_need_metadata);
void ip_tunnel_unneed_metadata(void)
{
static_branch_dec(&ip_tunnel_metadata_cnt);
}
EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata);
View Git Blame Copy Permalink