mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-27 19:29:37 +00:00
![Florian Westphal](/assets/img/avatar_default.png)
Its possible that we have more than one packet with the same ct tuple
simultaneously, e.g. when an application emits n packets on same UDP
socket from multiple threads.
NAT rules might be applied to those packets. With the right set of rules,
n packets will be mapped to m destinations, where at least two packets end
up with the same destination.
When this happens, the existing clash resolution may merge the skb that
is processed after the first has been received with the identical tuple
already in hash table.
However, its possible that this identical tuple is a NAT_CLASH tuple.
In that case the second skb will be sent, but no reply can be received
since the reply that is processed first removes the NAT_CLASH tuple.
Do not auto-delete, this gives a 1 second window for replies to be passed
back to originator.
Packets that are coming later (udp stream case) will not be affected:
they match the original ct entry, not a NAT_CLASH one.
Also prevent NAT_CLASH entries from getting offloaded.
Fixes: 6a757c07e5
("netfilter: conntrack: allow insertion of clashing entries")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
289 lines
7 KiB
C
289 lines
7 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
#include <linux/kernel.h>
|
|
#include <linux/module.h>
|
|
#include <linux/init.h>
|
|
#include <linux/netlink.h>
|
|
#include <linux/netfilter.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/netfilter/nf_conntrack_common.h>
|
|
#include <linux/netfilter/nf_tables.h>
|
|
#include <net/ip.h> /* for ipv4 options. */
|
|
#include <net/netfilter/nf_tables.h>
|
|
#include <net/netfilter/nf_tables_core.h>
|
|
#include <net/netfilter/nf_conntrack_core.h>
|
|
#include <net/netfilter/nf_conntrack_extend.h>
|
|
#include <net/netfilter/nf_flow_table.h>
|
|
|
|
struct nft_flow_offload {
|
|
struct nft_flowtable *flowtable;
|
|
};
|
|
|
|
static int nft_flow_route(const struct nft_pktinfo *pkt,
|
|
const struct nf_conn *ct,
|
|
struct nf_flow_route *route,
|
|
enum ip_conntrack_dir dir)
|
|
{
|
|
struct dst_entry *this_dst = skb_dst(pkt->skb);
|
|
struct dst_entry *other_dst = NULL;
|
|
struct flowi fl;
|
|
|
|
memset(&fl, 0, sizeof(fl));
|
|
switch (nft_pf(pkt)) {
|
|
case NFPROTO_IPV4:
|
|
fl.u.ip4.daddr = ct->tuplehash[dir].tuple.src.u3.ip;
|
|
fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex;
|
|
break;
|
|
case NFPROTO_IPV6:
|
|
fl.u.ip6.daddr = ct->tuplehash[dir].tuple.src.u3.in6;
|
|
fl.u.ip6.flowi6_oif = nft_in(pkt)->ifindex;
|
|
break;
|
|
}
|
|
|
|
nf_route(nft_net(pkt), &other_dst, &fl, false, nft_pf(pkt));
|
|
if (!other_dst)
|
|
return -ENOENT;
|
|
|
|
route->tuple[dir].dst = this_dst;
|
|
route->tuple[!dir].dst = other_dst;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static bool nft_flow_offload_skip(struct sk_buff *skb, int family)
|
|
{
|
|
if (skb_sec_path(skb))
|
|
return true;
|
|
|
|
if (family == NFPROTO_IPV4) {
|
|
const struct ip_options *opt;
|
|
|
|
opt = &(IPCB(skb)->opt);
|
|
|
|
if (unlikely(opt->optlen))
|
|
return true;
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
static void nft_flow_offload_eval(const struct nft_expr *expr,
|
|
struct nft_regs *regs,
|
|
const struct nft_pktinfo *pkt)
|
|
{
|
|
struct nft_flow_offload *priv = nft_expr_priv(expr);
|
|
struct nf_flowtable *flowtable = &priv->flowtable->data;
|
|
struct tcphdr _tcph, *tcph = NULL;
|
|
enum ip_conntrack_info ctinfo;
|
|
struct nf_flow_route route;
|
|
struct flow_offload *flow;
|
|
enum ip_conntrack_dir dir;
|
|
struct nf_conn *ct;
|
|
int ret;
|
|
|
|
if (nft_flow_offload_skip(pkt->skb, nft_pf(pkt)))
|
|
goto out;
|
|
|
|
ct = nf_ct_get(pkt->skb, &ctinfo);
|
|
if (!ct)
|
|
goto out;
|
|
|
|
switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) {
|
|
case IPPROTO_TCP:
|
|
tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff,
|
|
sizeof(_tcph), &_tcph);
|
|
if (unlikely(!tcph || tcph->fin || tcph->rst))
|
|
goto out;
|
|
break;
|
|
case IPPROTO_UDP:
|
|
break;
|
|
default:
|
|
goto out;
|
|
}
|
|
|
|
if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) ||
|
|
ct->status & (IPS_SEQ_ADJUST | IPS_NAT_CLASH))
|
|
goto out;
|
|
|
|
if (!nf_ct_is_confirmed(ct))
|
|
goto out;
|
|
|
|
if (test_and_set_bit(IPS_OFFLOAD_BIT, &ct->status))
|
|
goto out;
|
|
|
|
dir = CTINFO2DIR(ctinfo);
|
|
if (nft_flow_route(pkt, ct, &route, dir) < 0)
|
|
goto err_flow_route;
|
|
|
|
flow = flow_offload_alloc(ct);
|
|
if (!flow)
|
|
goto err_flow_alloc;
|
|
|
|
if (flow_offload_route_init(flow, &route) < 0)
|
|
goto err_flow_add;
|
|
|
|
if (tcph) {
|
|
ct->proto.tcp.seen[0].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
|
|
ct->proto.tcp.seen[1].flags |= IP_CT_TCP_FLAG_BE_LIBERAL;
|
|
}
|
|
|
|
ret = flow_offload_add(flowtable, flow);
|
|
if (ret < 0)
|
|
goto err_flow_add;
|
|
|
|
dst_release(route.tuple[!dir].dst);
|
|
return;
|
|
|
|
err_flow_add:
|
|
flow_offload_free(flow);
|
|
err_flow_alloc:
|
|
dst_release(route.tuple[!dir].dst);
|
|
err_flow_route:
|
|
clear_bit(IPS_OFFLOAD_BIT, &ct->status);
|
|
out:
|
|
regs->verdict.code = NFT_BREAK;
|
|
}
|
|
|
|
static int nft_flow_offload_validate(const struct nft_ctx *ctx,
|
|
const struct nft_expr *expr,
|
|
const struct nft_data **data)
|
|
{
|
|
unsigned int hook_mask = (1 << NF_INET_FORWARD);
|
|
|
|
return nft_chain_validate_hooks(ctx->chain, hook_mask);
|
|
}
|
|
|
|
static const struct nla_policy nft_flow_offload_policy[NFTA_FLOW_MAX + 1] = {
|
|
[NFTA_FLOW_TABLE_NAME] = { .type = NLA_STRING,
|
|
.len = NFT_NAME_MAXLEN - 1 },
|
|
};
|
|
|
|
static int nft_flow_offload_init(const struct nft_ctx *ctx,
|
|
const struct nft_expr *expr,
|
|
const struct nlattr * const tb[])
|
|
{
|
|
struct nft_flow_offload *priv = nft_expr_priv(expr);
|
|
u8 genmask = nft_genmask_next(ctx->net);
|
|
struct nft_flowtable *flowtable;
|
|
|
|
if (!tb[NFTA_FLOW_TABLE_NAME])
|
|
return -EINVAL;
|
|
|
|
flowtable = nft_flowtable_lookup(ctx->table, tb[NFTA_FLOW_TABLE_NAME],
|
|
genmask);
|
|
if (IS_ERR(flowtable))
|
|
return PTR_ERR(flowtable);
|
|
|
|
priv->flowtable = flowtable;
|
|
flowtable->use++;
|
|
|
|
return nf_ct_netns_get(ctx->net, ctx->family);
|
|
}
|
|
|
|
static void nft_flow_offload_deactivate(const struct nft_ctx *ctx,
|
|
const struct nft_expr *expr,
|
|
enum nft_trans_phase phase)
|
|
{
|
|
struct nft_flow_offload *priv = nft_expr_priv(expr);
|
|
|
|
nf_tables_deactivate_flowtable(ctx, priv->flowtable, phase);
|
|
}
|
|
|
|
static void nft_flow_offload_activate(const struct nft_ctx *ctx,
|
|
const struct nft_expr *expr)
|
|
{
|
|
struct nft_flow_offload *priv = nft_expr_priv(expr);
|
|
|
|
priv->flowtable->use++;
|
|
}
|
|
|
|
static void nft_flow_offload_destroy(const struct nft_ctx *ctx,
|
|
const struct nft_expr *expr)
|
|
{
|
|
nf_ct_netns_put(ctx->net, ctx->family);
|
|
}
|
|
|
|
static int nft_flow_offload_dump(struct sk_buff *skb, const struct nft_expr *expr)
|
|
{
|
|
struct nft_flow_offload *priv = nft_expr_priv(expr);
|
|
|
|
if (nla_put_string(skb, NFTA_FLOW_TABLE_NAME, priv->flowtable->name))
|
|
goto nla_put_failure;
|
|
|
|
return 0;
|
|
|
|
nla_put_failure:
|
|
return -1;
|
|
}
|
|
|
|
static struct nft_expr_type nft_flow_offload_type;
|
|
static const struct nft_expr_ops nft_flow_offload_ops = {
|
|
.type = &nft_flow_offload_type,
|
|
.size = NFT_EXPR_SIZE(sizeof(struct nft_flow_offload)),
|
|
.eval = nft_flow_offload_eval,
|
|
.init = nft_flow_offload_init,
|
|
.activate = nft_flow_offload_activate,
|
|
.deactivate = nft_flow_offload_deactivate,
|
|
.destroy = nft_flow_offload_destroy,
|
|
.validate = nft_flow_offload_validate,
|
|
.dump = nft_flow_offload_dump,
|
|
};
|
|
|
|
static struct nft_expr_type nft_flow_offload_type __read_mostly = {
|
|
.name = "flow_offload",
|
|
.ops = &nft_flow_offload_ops,
|
|
.policy = nft_flow_offload_policy,
|
|
.maxattr = NFTA_FLOW_MAX,
|
|
.owner = THIS_MODULE,
|
|
};
|
|
|
|
static int flow_offload_netdev_event(struct notifier_block *this,
|
|
unsigned long event, void *ptr)
|
|
{
|
|
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
|
|
|
|
if (event != NETDEV_DOWN)
|
|
return NOTIFY_DONE;
|
|
|
|
nf_flow_table_cleanup(dev);
|
|
|
|
return NOTIFY_DONE;
|
|
}
|
|
|
|
static struct notifier_block flow_offload_netdev_notifier = {
|
|
.notifier_call = flow_offload_netdev_event,
|
|
};
|
|
|
|
static int __init nft_flow_offload_module_init(void)
|
|
{
|
|
int err;
|
|
|
|
err = register_netdevice_notifier(&flow_offload_netdev_notifier);
|
|
if (err)
|
|
goto err;
|
|
|
|
err = nft_register_expr(&nft_flow_offload_type);
|
|
if (err < 0)
|
|
goto register_expr;
|
|
|
|
return 0;
|
|
|
|
register_expr:
|
|
unregister_netdevice_notifier(&flow_offload_netdev_notifier);
|
|
err:
|
|
return err;
|
|
}
|
|
|
|
static void __exit nft_flow_offload_module_exit(void)
|
|
{
|
|
nft_unregister_expr(&nft_flow_offload_type);
|
|
unregister_netdevice_notifier(&flow_offload_netdev_notifier);
|
|
}
|
|
|
|
module_init(nft_flow_offload_module_init);
|
|
module_exit(nft_flow_offload_module_exit);
|
|
|
|
MODULE_LICENSE("GPL");
|
|
MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
|
|
MODULE_ALIAS_NFT_EXPR("flow_offload");
|
|
MODULE_DESCRIPTION("nftables hardware flow offload module");
|