linux/net/sched/act_connmark.c

251 lines
6.2 KiB
C
Raw Normal View History

/*
* 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>
netns: make struct pernet_operations::id unsigned int Make struct pernet_operations::id unsigned. There are 2 reasons to do so: 1) This field is really an index into an zero based array and thus is unsigned entity. Using negative value is out-of-bound access by definition. 2) On x86_64 unsigned 32-bit data which are mixed with pointers via array indexing or offsets added or subtracted to pointers are preffered to signed 32-bit data. "int" being used as an array index needs to be sign-extended to 64-bit before being used. void f(long *p, int i) { g(p[i]); } roughly translates to movsx rsi, esi mov rdi, [rsi+...] call g MOVSX is 3 byte instruction which isn't necessary if the variable is unsigned because x86_64 is zero extending by default. Now, there is net_generic() function which, you guessed it right, uses "int" as an array index: static inline void *net_generic(const struct net *net, int id) { ... ptr = ng->ptr[id - 1]; ... } And this function is used a lot, so those sign extensions add up. Patch snipes ~1730 bytes on allyesconfig kernel (without all junk messing with code generation): add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) Unfortunately some functions actually grow bigger. This is a semmingly random artefact of code generation with register allocator being used differently. gcc decides that some variable needs to live in new r8+ registers and every access now requires REX prefix. Or it is shifted into r12, so [r12+0] addressing mode has to be used which is longer than [r8] However, overall balance is in negative direction: add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) function old new delta nfsd4_lock 3886 3959 +73 tipc_link_build_proto_msg 1096 1140 +44 mac80211_hwsim_new_radio 2776 2808 +32 tipc_mon_rcv 1032 1058 +26 svcauth_gss_legacy_init 1413 1429 +16 tipc_bcbase_select_primary 379 392 +13 nfsd4_exchange_id 1247 1260 +13 nfsd4_setclientid_confirm 782 793 +11 ... put_client_renew_locked 494 480 -14 ip_set_sockfn_get 730 716 -14 geneve_sock_add 829 813 -16 nfsd4_sequence_done 721 703 -18 nlmclnt_lookup_host 708 686 -22 nfsd4_lockt 1085 1063 -22 nfs_get_client 1077 1050 -27 tcf_bpf_init 1106 1076 -30 nfsd4_encode_fattr 5997 5930 -67 Total: Before=154856051, After=154854321, chg -0.00% Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-17 09:58:21 +08:00
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);
if (skb->protocol == htons(ETH_P_IP)) {
if (skb->len < sizeof(struct iphdr))
goto out;
proto = NFPROTO_IPV4;
} else if (skb->protocol == htons(ETH_P_IPV6)) {
if (skb->len < sizeof(struct ipv6hdr))
goto out;
proto = NFPROTO_IPV6;
} else {
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;
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;
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;
if (!nla)
return -EINVAL;
ret = nla_parse_nested(tb, TCA_CONNMARK_MAX, nla, connmark_policy,
NULL);
if (ret < 0)
return ret;
act_connmark: avoid crashing on malformed nlattrs with null parms tcf_connmark_init does not check in its configuration if TCA_CONNMARK_PARMS is set, resulting in a null pointer dereference when trying to access it. [501099.043007] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004 [501099.043039] IP: [<ffffffffc10c60fb>] tcf_connmark_init+0x8b/0x180 [act_connmark] ... [501099.044334] Call Trace: [501099.044345] [<ffffffffa47270e8>] ? tcf_action_init_1+0x198/0x1b0 [501099.044363] [<ffffffffa47271b0>] ? tcf_action_init+0xb0/0x120 [501099.044380] [<ffffffffa47250a4>] ? tcf_exts_validate+0xc4/0x110 [501099.044398] [<ffffffffc0f5fa97>] ? u32_set_parms+0xa7/0x270 [cls_u32] [501099.044417] [<ffffffffc0f60bf0>] ? u32_change+0x680/0x87b [cls_u32] [501099.044436] [<ffffffffa4725d1d>] ? tc_ctl_tfilter+0x4dd/0x8a0 [501099.044454] [<ffffffffa44a23a1>] ? security_capable+0x41/0x60 [501099.044471] [<ffffffffa470ca01>] ? rtnetlink_rcv_msg+0xe1/0x220 [501099.044490] [<ffffffffa470c920>] ? rtnl_newlink+0x870/0x870 [501099.044507] [<ffffffffa472cc61>] ? netlink_rcv_skb+0xa1/0xc0 [501099.044524] [<ffffffffa47073f4>] ? rtnetlink_rcv+0x24/0x30 [501099.044541] [<ffffffffa472c634>] ? netlink_unicast+0x184/0x230 [501099.044558] [<ffffffffa472c9d8>] ? netlink_sendmsg+0x2f8/0x3b0 [501099.044576] [<ffffffffa46d8880>] ? sock_sendmsg+0x30/0x40 [501099.044592] [<ffffffffa46d8e03>] ? SYSC_sendto+0xd3/0x150 [501099.044608] [<ffffffffa425fda1>] ? __do_page_fault+0x2d1/0x510 [501099.044626] [<ffffffffa47fbd7b>] ? system_call_fast_compare_end+0xc/0x9b Fixes: 22a5dc0e5e3e ("net: sched: Introduce connmark action") Signed-off-by: Étienne Noss <etienne.noss@wifirst.fr> Signed-off-by: Victorien Molle <victorien.molle@wifirst.fr> Acked-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-10 23:55:32 +08:00
if (!tb[TCA_CONNMARK_PARMS])
return -EINVAL;
parm = nla_data(tb[TCA_CONNMARK_PARMS]);
ret = tcf_idr_check_alloc(tn, &parm->index, a, bind);
if (!ret) {
ret = tcf_idr_create(tn, parm->index, est, a,
&act_connmark_ops, bind, false);
if (ret) {
tcf_idr_cleanup(tn, parm->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 */
spin_lock_bh(&ci->tcf_lock);
ci->tcf_action = parm->action;
ci->zone = parm->zone;
spin_unlock_bh(&ci->tcf_lock);
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,
};
struct tcf_t t;
spin_lock_bh(&ci->tcf_lock);
opt.action = ci->tcf_action;
opt.zone = ci->zone;
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;
spin_unlock_bh(&ci->tcf_lock);
return skb->len;
nla_put_failure:
spin_unlock_bh(&ci->tcf_lock);
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 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(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");