2019-05-27 14:55:01 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-or-later
|
2015-01-19 05:35:14 +08:00
|
|
|
/*
|
|
|
|
|
* net/sched/act_connmark.c netfilter connmark retriever action
|
|
|
|
|
* skb mark is over-written
|
|
|
|
|
*
|
|
|
|
|
* Copyright (c) 2011 Felix Fietkau <nbd@openwrt.org>
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
#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>
|
2019-03-20 22:00:05 +08:00
|
|
|
#include <net/pkt_cls.h>
|
2015-01-19 05:35:14 +08:00
|
|
|
#include <uapi/linux/tc_act/tc_connmark.h>
|
|
|
|
|
#include <net/tc_act/tc_connmark.h>
|
2022-12-06 21:55:12 +08:00
|
|
|
#include <net/tc_wrapper.h>
|
2015-01-19 05:35:14 +08:00
|
|
|
|
|
|
|
|
#include <net/netfilter/nf_conntrack.h>
|
|
|
|
|
#include <net/netfilter/nf_conntrack_core.h>
|
|
|
|
|
#include <net/netfilter/nf_conntrack_zones.h>
|
|
|
|
|
|
2016-07-26 07:09:41 +08:00
|
|
|
static struct tc_action_ops act_connmark_ops;
|
2016-02-23 07:57:53 +08:00
|
|
|
|
2022-12-06 21:55:12 +08:00
|
|
|
TC_INDIRECT_SCOPE int tcf_connmark_act(struct sk_buff *skb,
|
|
|
|
|
const struct tc_action *a,
|
|
|
|
|
struct tcf_result *res)
|
2015-01-19 05:35:14 +08:00
|
|
|
{
|
|
|
|
|
const struct nf_conntrack_tuple_hash *thash;
|
|
|
|
|
struct nf_conntrack_tuple tuple;
|
|
|
|
|
enum ip_conntrack_info ctinfo;
|
2016-07-26 07:09:41 +08:00
|
|
|
struct tcf_connmark_info *ca = to_connmark(a);
|
2023-02-15 05:15:32 +08:00
|
|
|
struct tcf_connmark_parms *parms;
|
2015-08-09 03:40:01 +08:00
|
|
|
struct nf_conntrack_zone zone;
|
2015-01-19 05:35:14 +08:00
|
|
|
struct nf_conn *c;
|
|
|
|
|
int proto;
|
|
|
|
|
|
2016-06-06 18:32:53 +08:00
|
|
|
tcf_lastuse_update(&ca->tcf_tm);
|
2023-02-15 05:15:32 +08:00
|
|
|
tcf_action_update_bstats(&ca->common, skb);
|
|
|
|
|
|
|
|
|
|
parms = rcu_dereference_bh(ca->parms);
|
2015-01-19 05:35:14 +08:00
|
|
|
|
sched: consistently handle layer3 header accesses in the presence of VLANs
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: d8b9605d2697 ("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>
2020-07-04 04:26:43 +08:00
|
|
|
switch (skb_protocol(skb, true)) {
|
|
|
|
|
case htons(ETH_P_IP):
|
2015-01-19 05:35:14 +08:00
|
|
|
if (skb->len < sizeof(struct iphdr))
|
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
|
|
proto = NFPROTO_IPV4;
|
sched: consistently handle layer3 header accesses in the presence of VLANs
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: d8b9605d2697 ("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>
2020-07-04 04:26:43 +08:00
|
|
|
break;
|
|
|
|
|
case htons(ETH_P_IPV6):
|
2015-01-19 05:35:14 +08:00
|
|
|
if (skb->len < sizeof(struct ipv6hdr))
|
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
|
|
proto = NFPROTO_IPV6;
|
sched: consistently handle layer3 header accesses in the presence of VLANs
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: d8b9605d2697 ("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>
2020-07-04 04:26:43 +08:00
|
|
|
break;
|
|
|
|
|
default:
|
2015-01-19 05:35:14 +08:00
|
|
|
goto out;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
c = nf_ct_get(skb, &ctinfo);
|
|
|
|
|
if (c) {
|
2022-11-10 03:39:07 +08:00
|
|
|
skb->mark = READ_ONCE(c->mark);
|
2023-02-15 05:15:32 +08:00
|
|
|
goto count;
|
2015-01-19 05:35:14 +08:00
|
|
|
}
|
|
|
|
|
|
2023-02-15 05:15:32 +08:00
|
|
|
if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, parms->net,
|
|
|
|
|
&tuple))
|
2015-01-19 05:35:14 +08:00
|
|
|
goto out;
|
|
|
|
|
|
2023-02-15 05:15:32 +08:00
|
|
|
zone.id = parms->zone;
|
netfilter: nf_conntrack: add direction support for zones
This work adds a direction parameter to netfilter zones, so identity
separation can be performed only in original/reply or both directions
(default). This basically opens up the possibility of doing NAT with
conflicting IP address/port tuples from multiple, isolated tenants
on a host (e.g. from a netns) without requiring each tenant to NAT
twice resp. to use its own dedicated IP address to SNAT to, meaning
overlapping tuples can be made unique with the zone identifier in
original direction, where the NAT engine will then allocate a unique
tuple in the commonly shared default zone for the reply direction.
In some restricted, local DNAT cases, also port redirection could be
used for making the reply traffic unique w/o requiring SNAT.
The consensus we've reached and discussed at NFWS and since the initial
implementation [1] was to directly integrate the direction meta data
into the existing zones infrastructure, as opposed to the ct->mark
approach we proposed initially.
As we pass the nf_conntrack_zone object directly around, we don't have
to touch all call-sites, but only those, that contain equality checks
of zones. Thus, based on the current direction (original or reply),
we either return the actual id, or the default NF_CT_DEFAULT_ZONE_ID.
CT expectations are direction-agnostic entities when expectations are
being compared among themselves, so we can only use the identifier
in this case.
Note that zone identifiers can not be included into the hash mix
anymore as they don't contain a "stable" value that would be equal
for both directions at all times, f.e. if only zone->id would
unconditionally be xor'ed into the table slot hash, then replies won't
find the corresponding conntracking entry anymore.
If no particular direction is specified when configuring zones, the
behaviour is exactly as we expect currently (both directions).
Support has been added for the CT netlink interface as well as the
x_tables raw CT target, which both already offer existing interfaces
to user space for the configuration of zones.
Below a minimal, simplified collision example (script in [2]) with
netperf sessions:
+--- tenant-1 ---+ mark := 1
| netperf |--+
+----------------+ | CT zone := mark [ORIGINAL]
[ip,sport] := X +--------------+ +--- gateway ---+
| mark routing |--| SNAT |-- ... +
+--------------+ +---------------+ |
+--- tenant-2 ---+ | ~~~|~~~
| netperf |--+ +-----------+ |
+----------------+ mark := 2 | netserver |------ ... +
[ip,sport] := X +-----------+
[ip,port] := Y
On the gateway netns, example:
iptables -t raw -A PREROUTING -j CT --zone mark --zone-dir ORIGINAL
iptables -t nat -A POSTROUTING -o <dev> -j SNAT --to-source <ip> --random-fully
iptables -t mangle -A PREROUTING -m conntrack --ctdir ORIGINAL -j CONNMARK --save-mark
iptables -t mangle -A POSTROUTING -m conntrack --ctdir REPLY -j CONNMARK --restore-mark
conntrack dump from gateway netns:
netperf -H 10.1.1.2 -t TCP_STREAM -l60 -p12865,5555 from each tenant netns
tcp 6 431995 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865 zone-orig=1
src=10.1.1.2 dst=10.1.1.1 sport=12865 dport=1024
[ASSURED] mark=1 secctx=system_u:object_r:unlabeled_t:s0 use=1
tcp 6 431994 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=5555 dport=12865 zone-orig=2
src=10.1.1.2 dst=10.1.1.1 sport=12865 dport=5555
[ASSURED] mark=2 secctx=system_u:object_r:unlabeled_t:s0 use=1
tcp 6 299 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=39438 dport=33768 zone-orig=1
src=10.1.1.2 dst=10.1.1.1 sport=33768 dport=39438
[ASSURED] mark=1 secctx=system_u:object_r:unlabeled_t:s0 use=1
tcp 6 300 ESTABLISHED src=40.1.1.1 dst=10.1.1.2 sport=32889 dport=40206 zone-orig=2
src=10.1.1.2 dst=10.1.1.1 sport=40206 dport=32889
[ASSURED] mark=2 secctx=system_u:object_r:unlabeled_t:s0 use=2
Taking this further, test script in [2] creates 200 tenants and runs
original-tuple colliding netperf sessions each. A conntrack -L dump in
the gateway netns also confirms 200 overlapping entries, all in ESTABLISHED
state as expected.
I also did run various other tests with some permutations of the script,
to mention some: SNAT in random/random-fully/persistent mode, no zones (no
overlaps), static zones (original, reply, both directions), etc.
[1] http://thread.gmane.org/gmane.comp.security.firewalls.netfilter.devel/57412/
[2] https://paste.fedoraproject.org/242835/65657871/
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
2015-08-14 22:03:39 +08:00
|
|
|
zone.dir = NF_CT_DEFAULT_ZONE_DIR;
|
2015-08-09 03:40:01 +08:00
|
|
|
|
2023-02-15 05:15:32 +08:00
|
|
|
thash = nf_conntrack_find_get(parms->net, &zone, &tuple);
|
2015-01-19 05:35:14 +08:00
|
|
|
if (!thash)
|
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
|
|
c = nf_ct_tuplehash_to_ctrack(thash);
|
2022-11-10 03:39:07 +08:00
|
|
|
skb->mark = READ_ONCE(c->mark);
|
2015-01-19 05:35:14 +08:00
|
|
|
nf_ct_put(c);
|
|
|
|
|
|
2023-02-15 05:15:32 +08:00
|
|
|
count:
|
|
|
|
|
/* using overlimits stats to count how many packets marked */
|
|
|
|
|
tcf_action_inc_overlimit_qstats(&ca->common);
|
2015-01-19 05:35:14 +08:00
|
|
|
out:
|
2023-02-15 05:15:32 +08:00
|
|
|
return READ_ONCE(ca->tcf_action);
|
2015-01-19 05:35:14 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
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,
|
2016-07-26 07:09:41 +08:00
|
|
|
struct nlattr *est, struct tc_action **a,
|
2019-10-30 22:09:05 +08:00
|
|
|
struct tcf_proto *tp, u32 flags,
|
2018-02-15 23:54:56 +08:00
|
|
|
struct netlink_ext_ack *extack)
|
2015-01-19 05:35:14 +08:00
|
|
|
{
|
2022-09-08 12:14:33 +08:00
|
|
|
struct tc_action_net *tn = net_generic(net, act_connmark_ops.net_id);
|
2023-02-15 05:15:32 +08:00
|
|
|
struct tcf_connmark_parms *nparms, *oparms;
|
2015-01-19 05:35:14 +08:00
|
|
|
struct nlattr *tb[TCA_CONNMARK_MAX + 1];
|
2021-07-30 07:12:14 +08:00
|
|
|
bool bind = flags & TCA_ACT_FLAGS_BIND;
|
2019-03-20 22:00:05 +08:00
|
|
|
struct tcf_chain *goto_ch = NULL;
|
2015-01-19 05:35:14 +08:00
|
|
|
struct tcf_connmark_info *ci;
|
|
|
|
|
struct tc_connmark *parm;
|
2019-03-20 22:00:05 +08:00
|
|
|
int ret = 0, err;
|
2019-08-01 21:02:51 +08:00
|
|
|
u32 index;
|
2015-01-19 05:35:14 +08:00
|
|
|
|
|
|
|
|
if (!nla)
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
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>
2019-04-26 20:07:28 +08:00
|
|
|
ret = nla_parse_nested_deprecated(tb, TCA_CONNMARK_MAX, nla,
|
|
|
|
|
connmark_policy, NULL);
|
2015-01-19 05:35:14 +08:00
|
|
|
if (ret < 0)
|
|
|
|
|
return ret;
|
|
|
|
|
|
2017-03-10 23:55:32 +08:00
|
|
|
if (!tb[TCA_CONNMARK_PARMS])
|
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
2023-02-15 05:15:32 +08:00
|
|
|
nparms = kzalloc(sizeof(*nparms), GFP_KERNEL);
|
|
|
|
|
if (!nparms)
|
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
2015-01-19 05:35:14 +08:00
|
|
|
parm = nla_data(tb[TCA_CONNMARK_PARMS]);
|
2019-08-01 21:02:51 +08:00
|
|
|
index = parm->index;
|
|
|
|
|
ret = tcf_idr_check_alloc(tn, &index, a, bind);
|
2018-07-05 22:24:32 +08:00
|
|
|
if (!ret) {
|
2023-02-15 05:15:32 +08:00
|
|
|
ret = tcf_idr_create_from_flags(tn, index, est, a,
|
|
|
|
|
&act_connmark_ops, bind, flags);
|
2018-07-05 22:24:32 +08:00
|
|
|
if (ret) {
|
2019-08-01 21:02:51 +08:00
|
|
|
tcf_idr_cleanup(tn, index);
|
2023-02-15 05:15:32 +08:00
|
|
|
err = ret;
|
|
|
|
|
goto out_free;
|
2018-07-05 22:24:32 +08:00
|
|
|
}
|
2015-01-19 05:35:14 +08:00
|
|
|
|
2016-07-26 07:09:41 +08:00
|
|
|
ci = to_connmark(*a);
|
2023-02-15 05:15:32 +08:00
|
|
|
|
|
|
|
|
nparms->net = net;
|
|
|
|
|
nparms->zone = parm->zone;
|
2015-01-19 05:35:14 +08:00
|
|
|
|
|
|
|
|
ret = ACT_P_CREATED;
|
2018-07-05 22:24:32 +08:00
|
|
|
} else if (ret > 0) {
|
2016-07-26 07:09:41 +08:00
|
|
|
ci = to_connmark(*a);
|
2023-02-15 05:15:32 +08:00
|
|
|
if (bind) {
|
|
|
|
|
err = 0;
|
|
|
|
|
goto out_free;
|
2018-07-05 22:24:30 +08:00
|
|
|
}
|
2023-02-15 05:15:32 +08:00
|
|
|
if (!(flags & TCA_ACT_FLAGS_REPLACE)) {
|
|
|
|
|
err = -EEXIST;
|
2019-03-20 22:00:05 +08:00
|
|
|
goto release_idr;
|
2023-02-15 05:15:32 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
nparms->net = rtnl_dereference(ci->parms)->net;
|
|
|
|
|
nparms->zone = parm->zone;
|
|
|
|
|
|
2018-07-05 22:24:32 +08:00
|
|
|
ret = 0;
|
2023-02-27 23:23:52 +08:00
|
|
|
} else {
|
|
|
|
|
err = ret;
|
|
|
|
|
goto out_free;
|
2015-01-19 05:35:14 +08:00
|
|
|
}
|
|
|
|
|
|
2023-02-15 05:15:32 +08:00
|
|
|
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
|
|
|
|
|
if (err < 0)
|
|
|
|
|
goto release_idr;
|
|
|
|
|
|
|
|
|
|
spin_lock_bh(&ci->tcf_lock);
|
|
|
|
|
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
|
|
|
|
|
oparms = rcu_replace_pointer(ci->parms, nparms, lockdep_is_held(&ci->tcf_lock));
|
|
|
|
|
spin_unlock_bh(&ci->tcf_lock);
|
|
|
|
|
|
|
|
|
|
if (goto_ch)
|
|
|
|
|
tcf_chain_put_by_act(goto_ch);
|
|
|
|
|
|
|
|
|
|
if (oparms)
|
|
|
|
|
kfree_rcu(oparms, rcu);
|
|
|
|
|
|
2015-01-19 05:35:14 +08:00
|
|
|
return ret;
|
2023-02-15 05:15:32 +08:00
|
|
|
|
2019-03-20 22:00:05 +08:00
|
|
|
release_idr:
|
|
|
|
|
tcf_idr_release(*a, bind);
|
2023-02-15 05:15:32 +08:00
|
|
|
out_free:
|
|
|
|
|
kfree(nparms);
|
2019-03-20 22:00:05 +08:00
|
|
|
return err;
|
2015-01-19 05:35:14 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
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);
|
2016-07-26 07:09:41 +08:00
|
|
|
struct tcf_connmark_info *ci = to_connmark(a);
|
2015-01-19 05:35:14 +08:00
|
|
|
struct tc_connmark opt = {
|
|
|
|
|
.index = ci->tcf_index,
|
2018-07-05 22:24:24 +08:00
|
|
|
.refcnt = refcount_read(&ci->tcf_refcnt) - ref,
|
|
|
|
|
.bindcnt = atomic_read(&ci->tcf_bindcnt) - bind,
|
2015-01-19 05:35:14 +08:00
|
|
|
};
|
2023-02-15 05:15:32 +08:00
|
|
|
struct tcf_connmark_parms *parms;
|
2015-01-19 05:35:14 +08:00
|
|
|
struct tcf_t t;
|
|
|
|
|
|
2018-08-30 01:15:36 +08:00
|
|
|
spin_lock_bh(&ci->tcf_lock);
|
2023-02-15 05:15:32 +08:00
|
|
|
parms = rcu_dereference_protected(ci->parms, lockdep_is_held(&ci->tcf_lock));
|
|
|
|
|
|
2018-08-30 01:15:36 +08:00
|
|
|
opt.action = ci->tcf_action;
|
2023-02-15 05:15:32 +08:00
|
|
|
opt.zone = parms->zone;
|
2015-01-19 05:35:14 +08:00
|
|
|
if (nla_put(skb, TCA_CONNMARK_PARMS, sizeof(opt), &opt))
|
|
|
|
|
goto nla_put_failure;
|
|
|
|
|
|
2016-06-06 18:32:55 +08:00
|
|
|
tcf_tm_dump(&t, &ci->tcf_tm);
|
2016-04-26 16:06:18 +08:00
|
|
|
if (nla_put_64bit(skb, TCA_CONNMARK_TM, sizeof(t), &t,
|
|
|
|
|
TCA_CONNMARK_PAD))
|
2015-01-19 05:35:14 +08:00
|
|
|
goto nla_put_failure;
|
2018-08-30 01:15:36 +08:00
|
|
|
spin_unlock_bh(&ci->tcf_lock);
|
2015-01-19 05:35:14 +08:00
|
|
|
|
|
|
|
|
return skb->len;
|
2018-08-30 01:15:36 +08:00
|
|
|
|
2015-01-19 05:35:14 +08:00
|
|
|
nla_put_failure:
|
2018-08-30 01:15:36 +08:00
|
|
|
spin_unlock_bh(&ci->tcf_lock);
|
2015-01-19 05:35:14 +08:00
|
|
|
nlmsg_trim(skb, b);
|
|
|
|
|
return -1;
|
|
|
|
|
}
|
|
|
|
|
|
2023-02-15 05:15:32 +08:00
|
|
|
static void tcf_connmark_cleanup(struct tc_action *a)
|
|
|
|
|
{
|
|
|
|
|
struct tcf_connmark_info *ci = to_connmark(a);
|
|
|
|
|
struct tcf_connmark_parms *parms;
|
|
|
|
|
|
|
|
|
|
parms = rcu_dereference_protected(ci->parms, 1);
|
|
|
|
|
if (parms)
|
|
|
|
|
kfree_rcu(parms, rcu);
|
|
|
|
|
}
|
|
|
|
|
|
2015-01-19 05:35:14 +08:00
|
|
|
static struct tc_action_ops act_connmark_ops = {
|
|
|
|
|
.kind = "connmark",
|
2019-02-10 20:25:00 +08:00
|
|
|
.id = TCA_ID_CONNMARK,
|
2015-01-19 05:35:14 +08:00
|
|
|
.owner = THIS_MODULE,
|
2018-08-12 21:34:49 +08:00
|
|
|
.act = tcf_connmark_act,
|
2015-01-19 05:35:14 +08:00
|
|
|
.dump = tcf_connmark_dump,
|
|
|
|
|
.init = tcf_connmark_init,
|
2023-02-15 05:15:32 +08:00
|
|
|
.cleanup = tcf_connmark_cleanup,
|
2016-07-26 07:09:41 +08:00
|
|
|
.size = sizeof(struct tcf_connmark_info),
|
2016-02-23 07:57:53 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static __net_init int connmark_init_net(struct net *net)
|
|
|
|
|
{
|
2022-09-08 12:14:33 +08:00
|
|
|
struct tc_action_net *tn = net_generic(net, act_connmark_ops.net_id);
|
2016-02-23 07:57:53 +08:00
|
|
|
|
2019-08-26 01:01:32 +08:00
|
|
|
return tc_action_net_init(net, tn, &act_connmark_ops);
|
2016-02-23 07:57:53 +08:00
|
|
|
}
|
|
|
|
|
|
2017-12-12 07:35:03 +08:00
|
|
|
static void __net_exit connmark_exit_net(struct list_head *net_list)
|
2016-02-23 07:57:53 +08:00
|
|
|
{
|
2022-09-08 12:14:33 +08:00
|
|
|
tc_action_net_exit(net_list, act_connmark_ops.net_id);
|
2016-02-23 07:57:53 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static struct pernet_operations connmark_net_ops = {
|
|
|
|
|
.init = connmark_init_net,
|
2017-12-12 07:35:03 +08:00
|
|
|
.exit_batch = connmark_exit_net,
|
2022-09-08 12:14:33 +08:00
|
|
|
.id = &act_connmark_ops.net_id,
|
2016-02-23 07:57:53 +08:00
|
|
|
.size = sizeof(struct tc_action_net),
|
2015-01-19 05:35:14 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
|
|
static int __init connmark_init_module(void)
|
|
|
|
|
{
|
2016-02-23 07:57:53 +08:00
|
|
|
return tcf_register_action(&act_connmark_ops, &connmark_net_ops);
|
2015-01-19 05:35:14 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static void __exit connmark_cleanup_module(void)
|
|
|
|
|
{
|
2016-02-23 07:57:53 +08:00
|
|
|
tcf_unregister_action(&act_connmark_ops, &connmark_net_ops);
|
2015-01-19 05:35:14 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
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");
|