kernel-fxtec-pro1x/net/sched/act_connmark.c
Toke Høiland-Jørgensen 9fd235ff00 sched: consistently handle layer3 header accesses in the presence of VLANs
[ Upstream commit d7bf2ebebc2bd61ab95e2a8e33541ef282f303d4 ]

There are a couple of places in net/sched/ that check skb->protocol and act
on the value there. However, in the presence of VLAN tags, the value stored
in skb->protocol can be inconsistent based on whether VLAN acceleration is
enabled. The commit quoted in the Fixes tag below fixed the users of
skb->protocol to use a helper that will always see the VLAN ethertype.

However, most of the callers don't actually handle the VLAN ethertype, but
expect to find the IP header type in the protocol field. This means that
things like changing the ECN field, or parsing diffserv values, stops
working if there's a VLAN tag, or if there are multiple nested VLAN
tags (QinQ).

To fix this, change the helper to take an argument that indicates whether
the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we
make sure to skip all of them, so behaviour is consistent even in QinQ
mode.

To make the helper usable from the ECN code, move it to if_vlan.h instead
of pkt_sched.h.

v3:
- Remove empty lines
- Move vlan variable definitions inside loop in skb_protocol()
- Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and
  bpf_skb_ecn_set_ce()

v2:
- Use eth_type_vlan() helper in skb_protocol()
- Also fix code that reads skb->protocol directly
- Change a couple of 'if/else if' statements to switch constructs to avoid
  calling the helper twice

Reported-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com>
Fixes: d8b9605d26 ("net: sched: fix skb->protocol use in case of accelerated vlan path")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-07-22 09:32:00 +02:00

250 lines
6.1 KiB
C

/*
* net/sched/act_connmark.c netfilter connmark retriever action
* skb mark is over-written
*
* Copyright (c) 2011 Felix Fietkau <nbd@openwrt.org>
*
* 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/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/pkt_cls.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/act_api.h>
#include <uapi/linux/tc_act/tc_connmark.h>
#include <net/tc_act/tc_connmark.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_core.h>
#include <net/netfilter/nf_conntrack_zones.h>
static unsigned int connmark_net_id;
static struct tc_action_ops act_connmark_ops;
static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
const struct nf_conntrack_tuple_hash *thash;
struct nf_conntrack_tuple tuple;
enum ip_conntrack_info ctinfo;
struct tcf_connmark_info *ca = to_connmark(a);
struct nf_conntrack_zone zone;
struct nf_conn *c;
int proto;
spin_lock(&ca->tcf_lock);
tcf_lastuse_update(&ca->tcf_tm);
bstats_update(&ca->tcf_bstats, skb);
switch (skb_protocol(skb, true)) {
case htons(ETH_P_IP):
if (skb->len < sizeof(struct iphdr))
goto out;
proto = NFPROTO_IPV4;
break;
case htons(ETH_P_IPV6):
if (skb->len < sizeof(struct ipv6hdr))
goto out;
proto = NFPROTO_IPV6;
break;
default:
goto out;
}
c = nf_ct_get(skb, &ctinfo);
if (c) {
skb->mark = c->mark;
/* using overlimits stats to count how many packets marked */
ca->tcf_qstats.overlimits++;
goto out;
}
if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
proto, ca->net, &tuple))
goto out;
zone.id = ca->zone;
zone.dir = NF_CT_DEFAULT_ZONE_DIR;
thash = nf_conntrack_find_get(ca->net, &zone, &tuple);
if (!thash)
goto out;
c = nf_ct_tuplehash_to_ctrack(thash);
/* using overlimits stats to count how many packets marked */
ca->tcf_qstats.overlimits++;
skb->mark = c->mark;
nf_ct_put(c);
out:
spin_unlock(&ca->tcf_lock);
return ca->tcf_action;
}
static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = {
[TCA_CONNMARK_PARMS] = { .len = sizeof(struct tc_connmark) },
};
static int tcf_connmark_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, connmark_net_id);
struct nlattr *tb[TCA_CONNMARK_MAX + 1];
struct tcf_connmark_info *ci;
struct tc_connmark *parm;
int ret = 0;
u32 index;
if (!nla)
return -EINVAL;
ret = nla_parse_nested(tb, TCA_CONNMARK_MAX, nla, connmark_policy,
NULL);
if (ret < 0)
return ret;
if (!tb[TCA_CONNMARK_PARMS])
return -EINVAL;
parm = nla_data(tb[TCA_CONNMARK_PARMS]);
index = parm->index;
ret = tcf_idr_check_alloc(tn, &index, a, bind);
if (!ret) {
ret = tcf_idr_create(tn, index, est, a,
&act_connmark_ops, bind, false);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
}
ci = to_connmark(*a);
ci->tcf_action = parm->action;
ci->net = net;
ci->zone = parm->zone;
tcf_idr_insert(tn, *a);
ret = ACT_P_CREATED;
} else if (ret > 0) {
ci = to_connmark(*a);
if (bind)
return 0;
if (!ovr) {
tcf_idr_release(*a, bind);
return -EEXIST;
}
/* replacing action and zone */
ci->tcf_action = parm->action;
ci->zone = parm->zone;
ret = 0;
}
return ret;
}
static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_connmark_info *ci = to_connmark(a);
struct tc_connmark opt = {
.index = ci->tcf_index,
.refcnt = refcount_read(&ci->tcf_refcnt) - ref,
.bindcnt = atomic_read(&ci->tcf_bindcnt) - bind,
.action = ci->tcf_action,
.zone = ci->zone,
};
struct tcf_t t;
if (nla_put(skb, TCA_CONNMARK_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
tcf_tm_dump(&t, &ci->tcf_tm);
if (nla_put_64bit(skb, TCA_CONNMARK_TM, sizeof(t), &t,
TCA_CONNMARK_PAD))
goto nla_put_failure;
return skb->len;
nla_put_failure:
nlmsg_trim(skb, b);
return -1;
}
static int tcf_connmark_walker(struct net *net, struct sk_buff *skb,
struct netlink_callback *cb, int type,
const struct tc_action_ops *ops,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, connmark_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, connmark_net_id);
return tcf_idr_search(tn, a, index);
}
static struct tc_action_ops act_connmark_ops = {
.kind = "connmark",
.type = TCA_ACT_CONNMARK,
.owner = THIS_MODULE,
.act = tcf_connmark_act,
.dump = tcf_connmark_dump,
.init = tcf_connmark_init,
.walk = tcf_connmark_walker,
.lookup = tcf_connmark_search,
.size = sizeof(struct tcf_connmark_info),
};
static __net_init int connmark_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, connmark_net_id);
return tc_action_net_init(net, tn, &act_connmark_ops);
}
static void __net_exit connmark_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, connmark_net_id);
}
static struct pernet_operations connmark_net_ops = {
.init = connmark_init_net,
.exit_batch = connmark_exit_net,
.id = &connmark_net_id,
.size = sizeof(struct tc_action_net),
};
static int __init connmark_init_module(void)
{
return tcf_register_action(&act_connmark_ops, &connmark_net_ops);
}
static void __exit connmark_cleanup_module(void)
{
tcf_unregister_action(&act_connmark_ops, &connmark_net_ops);
}
module_init(connmark_init_module);
module_exit(connmark_cleanup_module);
MODULE_AUTHOR("Felix Fietkau <nbd@openwrt.org>");
MODULE_DESCRIPTION("Connection tracking mark restoring");
MODULE_LICENSE("GPL");