1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
|
From 1bb0c3ec899827cfa4668bb63a08713a40744d21 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Sun, 9 Jul 2017 08:58:30 +0200
Subject: [PATCH] netfilter: conntrack: cache route for forwarded connections
... to avoid per-packet FIB lookup if possible.
The cached dst is re-used provided the input interface
is the same as that of the previous packet in the same direction.
If not, the cached dst is invalidated.
For ipv6 we also need to store sernum, else dst_check doesn't work,
pointed out by Eric Dumazet.
This should speed up forwarding when conntrack is already in use
anyway, especially when using reverse path filtering -- active RPF
enforces two FIB lookups for each packet.
Before the routing cache removal this didn't matter since RPF was performed
only when route cache didn't yield a result; but without route cache it
comes at higher price.
Julian Anastasov suggested to add NETDEV_UNREGISTER handler to
avoid holding on to dsts of 'frozen' conntracks.
Signed-off-by: Florian Westphal <fw@strlen.de>
---
include/net/netfilter/nf_conntrack_extend.h | 4 +
include/net/netfilter/nf_conntrack_rtcache.h | 34 +++
net/netfilter/Kconfig | 12 +
net/netfilter/Makefile | 3 +
net/netfilter/nf_conntrack_rtcache.c | 428 +++++++++++++++++++++++++++
5 files changed, 481 insertions(+)
create mode 100644 include/net/netfilter/nf_conntrack_rtcache.h
create mode 100644 net/netfilter/nf_conntrack_rtcache.c
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -28,6 +28,9 @@ enum nf_ct_ext_id {
#if IS_ENABLED(CONFIG_NETFILTER_SYNPROXY)
NF_CT_EXT_SYNPROXY,
#endif
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_RTCACHE)
+ NF_CT_EXT_RTCACHE,
+#endif
NF_CT_EXT_NUM,
};
@@ -40,6 +43,7 @@ enum nf_ct_ext_id {
#define NF_CT_EXT_TIMEOUT_TYPE struct nf_conn_timeout
#define NF_CT_EXT_LABELS_TYPE struct nf_conn_labels
#define NF_CT_EXT_SYNPROXY_TYPE struct nf_conn_synproxy
+#define NF_CT_EXT_RTCACHE_TYPE struct nf_conn_rtcache
/* Extensions: optional stuff which isn't permanently in struct. */
struct nf_ct_ext {
--- /dev/null
+++ b/include/net/netfilter/nf_conntrack_rtcache.h
@@ -0,0 +1,34 @@
+#include <linux/gfp.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_extend.h>
+
+struct dst_entry;
+
+struct nf_conn_dst_cache {
+ struct dst_entry *dst;
+ int iif;
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV6)
+ u32 cookie;
+#endif
+
+};
+
+struct nf_conn_rtcache {
+ struct nf_conn_dst_cache cached_dst[IP_CT_DIR_MAX];
+};
+
+static inline
+struct nf_conn_rtcache *nf_ct_rtcache_find(const struct nf_conn *ct)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_RTCACHE)
+ return nf_ct_ext_find(ct, NF_CT_EXT_RTCACHE);
+#else
+ return NULL;
+#endif
+}
+
+static inline int nf_conn_rtcache_iif_get(const struct nf_conn_rtcache *rtc,
+ enum ip_conntrack_dir dir)
+{
+ return rtc->cached_dst[dir].iif;
+}
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -135,6 +135,18 @@ config NF_CONNTRACK_EVENTS
If unsure, say `N'.
+config NF_CONNTRACK_RTCACHE
+ tristate "Cache route entries in conntrack objects"
+ depends on NETFILTER_ADVANCED
+ depends on NF_CONNTRACK
+ help
+ If this option is enabled, the connection tracking code will
+ cache routing information for each connection that is being
+ forwarded, at a cost of 32 bytes per conntrack object.
+
+ To compile it as a module, choose M here. If unsure, say N.
+ The module will be called nf_conntrack_rtcache.
+
config NF_CONNTRACK_TIMEOUT
bool 'Connection tracking timeout'
depends on NETFILTER_ADVANCED
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -25,6 +25,9 @@ obj-$(CONFIG_NETFILTER_NETLINK_OSF) += n
# connection tracking
obj-$(CONFIG_NF_CONNTRACK) += nf_conntrack.o
+# optional conntrack route cache extension
+obj-$(CONFIG_NF_CONNTRACK_RTCACHE) += nf_conntrack_rtcache.o
+
obj-$(CONFIG_NF_CT_PROTO_GRE) += nf_conntrack_proto_gre.o
# netlink interface for nf_conntrack
--- /dev/null
+++ b/net/netfilter/nf_conntrack_rtcache.c
@@ -0,0 +1,440 @@
+/* route cache for netfilter.
+ *
+ * (C) 2014 Red Hat GmbH
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/types.h>
+#include <linux/netfilter.h>
+#include <linux/skbuff.h>
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/export.h>
+#include <linux/module.h>
+
+#include <net/dst.h>
+
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_extend.h>
+#include <net/netfilter/nf_conntrack_rtcache.h>
+
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV6)
+#include <net/ip6_fib.h>
+#endif
+
+static void __nf_conn_rtcache_destroy(struct nf_conn_rtcache *rtc,
+ enum ip_conntrack_dir dir)
+{
+ struct dst_entry *dst = rtc->cached_dst[dir].dst;
+
+ dst_release(dst);
+}
+
+static void nf_conn_rtcache_destroy(struct nf_conn *ct)
+{
+ struct nf_conn_rtcache *rtc = nf_ct_rtcache_find(ct);
+
+ if (!rtc)
+ return;
+
+ __nf_conn_rtcache_destroy(rtc, IP_CT_DIR_ORIGINAL);
+ __nf_conn_rtcache_destroy(rtc, IP_CT_DIR_REPLY);
+}
+
+static void nf_ct_rtcache_ext_add(struct nf_conn *ct)
+{
+ struct nf_conn_rtcache *rtc;
+
+ rtc = nf_ct_ext_add(ct, NF_CT_EXT_RTCACHE, GFP_ATOMIC);
+ if (rtc) {
+ rtc->cached_dst[IP_CT_DIR_ORIGINAL].iif = -1;
+ rtc->cached_dst[IP_CT_DIR_ORIGINAL].dst = NULL;
+ rtc->cached_dst[IP_CT_DIR_REPLY].iif = -1;
+ rtc->cached_dst[IP_CT_DIR_REPLY].dst = NULL;
+ }
+}
+
+static struct nf_conn_rtcache *nf_ct_rtcache_find_usable(struct nf_conn *ct)
+{
+ return nf_ct_rtcache_find(ct);
+}
+
+static struct dst_entry *
+nf_conn_rtcache_dst_get(const struct nf_conn_rtcache *rtc,
+ enum ip_conntrack_dir dir)
+{
+ return rtc->cached_dst[dir].dst;
+}
+
+static u32 nf_rtcache_get_cookie(int pf, const struct dst_entry *dst)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV6)
+ if (pf == NFPROTO_IPV6) {
+ const struct rt6_info *rt = (const struct rt6_info *)dst;
+
+ if (rt->from && rt->from->fib6_node)
+ return (u32)rt->from->fib6_node->fn_sernum;
+ }
+#endif
+ return 0;
+}
+
+static void nf_conn_rtcache_dst_set(int pf,
+ struct nf_conn_rtcache *rtc,
+ struct dst_entry *dst,
+ enum ip_conntrack_dir dir, int iif)
+{
+ if (rtc->cached_dst[dir].iif != iif)
+ rtc->cached_dst[dir].iif = iif;
+
+ if (rtc->cached_dst[dir].dst != dst) {
+ struct dst_entry *old;
+
+ dst_hold(dst);
+
+ old = xchg(&rtc->cached_dst[dir].dst, dst);
+ dst_release(old);
+
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV6)
+ if (pf == NFPROTO_IPV6)
+ rtc->cached_dst[dir].cookie =
+ nf_rtcache_get_cookie(pf, dst);
+#endif
+ }
+}
+
+static void nf_conn_rtcache_dst_obsolete(struct nf_conn_rtcache *rtc,
+ enum ip_conntrack_dir dir)
+{
+ struct dst_entry *old;
+
+ pr_debug("Invalidate iif %d for dir %d on cache %p\n",
+ rtc->cached_dst[dir].iif, dir, rtc);
+
+ old = xchg(&rtc->cached_dst[dir].dst, NULL);
+ dst_release(old);
+ rtc->cached_dst[dir].iif = -1;
+}
+
+static unsigned int nf_rtcache_in(u_int8_t pf,
+ struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ struct nf_conn_rtcache *rtc;
+ enum ip_conntrack_info ctinfo;
+ enum ip_conntrack_dir dir;
+ struct dst_entry *dst;
+ struct nf_conn *ct;
+ int iif;
+ u32 cookie;
+
+ if (skb_dst(skb) || skb->sk)
+ return NF_ACCEPT;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (!ct)
+ return NF_ACCEPT;
+
+ rtc = nf_ct_rtcache_find_usable(ct);
+ if (!rtc)
+ return NF_ACCEPT;
+
+ /* if iif changes, don't use cache and let ip stack
+ * do route lookup.
+ *
+ * If rp_filter is enabled it might toss skb, so
+ * we don't want to avoid these checks.
+ */
+ dir = CTINFO2DIR(ctinfo);
+ iif = nf_conn_rtcache_iif_get(rtc, dir);
+ if (state->in->ifindex != iif) {
+ pr_debug("ct %p, iif %d, cached iif %d, skip cached entry\n",
+ ct, iif, state->in->ifindex);
+ return NF_ACCEPT;
+ }
+ dst = nf_conn_rtcache_dst_get(rtc, dir);
+ if (dst == NULL)
+ return NF_ACCEPT;
+
+ cookie = nf_rtcache_get_cookie(pf, dst);
+
+ dst = dst_check(dst, cookie);
+ pr_debug("obtained dst %p for skb %p, cookie %d\n", dst, skb, cookie);
+ if (likely(dst))
+ skb_dst_set_noref(skb, dst);
+ else
+ nf_conn_rtcache_dst_obsolete(rtc, dir);
+
+ return NF_ACCEPT;
+}
+
+static unsigned int nf_rtcache_forward(u_int8_t pf,
+ struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ struct nf_conn_rtcache *rtc;
+ enum ip_conntrack_info ctinfo;
+ enum ip_conntrack_dir dir;
+ struct nf_conn *ct;
+ struct dst_entry *dst = skb_dst(skb);
+ int iif;
+
+ ct = nf_ct_get(skb, &ctinfo);
+ if (!ct)
+ return NF_ACCEPT;
+
+ if (dst && dst_xfrm(dst))
+ return NF_ACCEPT;
+
+ if (!nf_ct_is_confirmed(ct)) {
+ if (WARN_ON(nf_ct_rtcache_find(ct)))
+ return NF_ACCEPT;
+ nf_ct_rtcache_ext_add(ct);
+ return NF_ACCEPT;
+ }
+
+ rtc = nf_ct_rtcache_find_usable(ct);
+ if (!rtc)
+ return NF_ACCEPT;
+
+ dir = CTINFO2DIR(ctinfo);
+ iif = nf_conn_rtcache_iif_get(rtc, dir);
+ pr_debug("ct %p, skb %p, dir %d, iif %d, cached iif %d\n",
+ ct, skb, dir, iif, state->in->ifindex);
+ if (likely(state->in->ifindex == iif))
+ return NF_ACCEPT;
+
+ nf_conn_rtcache_dst_set(pf, rtc, skb_dst(skb), dir, state->in->ifindex);
+ return NF_ACCEPT;
+}
+
+static unsigned int nf_rtcache_in4(void *priv,
+ struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ return nf_rtcache_in(NFPROTO_IPV4, skb, state);
+}
+
+static unsigned int nf_rtcache_forward4(void *priv,
+ struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ return nf_rtcache_forward(NFPROTO_IPV4, skb, state);
+}
+
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV6)
+static unsigned int nf_rtcache_in6(void *priv,
+ struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ return nf_rtcache_in(NFPROTO_IPV6, skb, state);
+}
+
+static unsigned int nf_rtcache_forward6(void *priv,
+ struct sk_buff *skb,
+ const struct nf_hook_state *state)
+{
+ return nf_rtcache_forward(NFPROTO_IPV6, skb, state);
+}
+#endif
+
+static int nf_rtcache_dst_remove(struct nf_conn *ct, void *data)
+{
+ struct nf_conn_rtcache *rtc = nf_ct_rtcache_find(ct);
+ struct net_device *dev = data;
+
+ if (!rtc)
+ return 0;
+
+ if (dev->ifindex == rtc->cached_dst[IP_CT_DIR_ORIGINAL].iif ||
+ dev->ifindex == rtc->cached_dst[IP_CT_DIR_REPLY].iif) {
+ nf_conn_rtcache_dst_obsolete(rtc, IP_CT_DIR_ORIGINAL);
+ nf_conn_rtcache_dst_obsolete(rtc, IP_CT_DIR_REPLY);
+ }
+
+ return 0;
+}
+
+static int nf_rtcache_netdev_event(struct notifier_block *this,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct net *net = dev_net(dev);
+
+ if (event == NETDEV_DOWN)
+ nf_ct_iterate_cleanup_net(net, nf_rtcache_dst_remove, dev, 0, 0);
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block nf_rtcache_notifier = {
+ .notifier_call = nf_rtcache_netdev_event,
+};
+
+static struct nf_hook_ops rtcache_ops[] = {
+ {
+ .hook = nf_rtcache_in4,
+ .pf = NFPROTO_IPV4,
+ .hooknum = NF_INET_PRE_ROUTING,
+ .priority = NF_IP_PRI_LAST,
+ },
+ {
+ .hook = nf_rtcache_forward4,
+ .pf = NFPROTO_IPV4,
+ .hooknum = NF_INET_FORWARD,
+ .priority = NF_IP_PRI_LAST,
+ },
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV6)
+ {
+ .hook = nf_rtcache_in6,
+ .pf = NFPROTO_IPV6,
+ .hooknum = NF_INET_PRE_ROUTING,
+ .priority = NF_IP_PRI_LAST,
+ },
+ {
+ .hook = nf_rtcache_forward6,
+ .pf = NFPROTO_IPV6,
+ .hooknum = NF_INET_FORWARD,
+ .priority = NF_IP_PRI_LAST,
+ },
+#endif
+};
+
+static struct nf_ct_ext_type rtcache_extend __read_mostly = {
+ .len = sizeof(struct nf_conn_rtcache),
+ .align = __alignof__(struct nf_conn_rtcache),
+ .id = NF_CT_EXT_RTCACHE,
+ .destroy = nf_conn_rtcache_destroy,
+};
+
+static int __net_init rtcache_net_init(struct net *net)
+{
+ return nf_register_net_hooks(net, rtcache_ops, ARRAY_SIZE(rtcache_ops));
+}
+
+static void __net_exit rtcache_net_exit(struct net *net)
+{
+ /* remove hooks so no new connections get rtcache extension */
+ nf_unregister_net_hooks(net, rtcache_ops, ARRAY_SIZE(rtcache_ops));
+}
+
+static struct pernet_operations rtcache_ops_net_ops = {
+ .init = rtcache_net_init,
+ .exit = rtcache_net_exit,
+};
+
+static int __init nf_conntrack_rtcache_init(void)
+{
+ int ret = nf_ct_extend_register(&rtcache_extend);
+
+ if (ret < 0) {
+ pr_err("nf_conntrack_rtcache: Unable to register extension\n");
+ return ret;
+ }
+
+ ret = register_pernet_subsys(&rtcache_ops_net_ops);
+ if (ret) {
+ nf_ct_extend_unregister(&rtcache_extend);
+ return ret;
+ }
+
+ ret = nf_register_net_hooks(&init_net, rtcache_ops,
+ ARRAY_SIZE(rtcache_ops));
+ if (ret < 0) {
+ nf_ct_extend_unregister(&rtcache_extend);
+ unregister_pernet_subsys(&rtcache_ops_net_ops);
+ return ret;
+ }
+
+ ret = register_netdevice_notifier(&nf_rtcache_notifier);
+ if (ret) {
+ nf_unregister_net_hooks(&init_net, rtcache_ops,
+ ARRAY_SIZE(rtcache_ops));
+ nf_ct_extend_unregister(&rtcache_extend);
+ unregister_pernet_subsys(&rtcache_ops_net_ops);
+ }
+
+ return ret;
+}
+
+static int nf_rtcache_ext_remove(struct nf_conn *ct, void *data)
+{
+ struct nf_conn_rtcache *rtc = nf_ct_rtcache_find(ct);
+
+ return rtc != NULL;
+}
+
+static bool __exit nf_conntrack_rtcache_wait_for_dying(struct net *net)
+{
+ bool wait = false;
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct nf_conntrack_tuple_hash *h;
+ struct hlist_nulls_node *n;
+ struct nf_conn *ct;
+ struct ct_pcpu *pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
+
+ rcu_read_lock();
+ spin_lock_bh(&pcpu->lock);
+
+ hlist_nulls_for_each_entry(h, n, &pcpu->dying, hnnode) {
+ ct = nf_ct_tuplehash_to_ctrack(h);
+ if (nf_ct_rtcache_find(ct) != NULL) {
+ wait = true;
+ break;
+ }
+ }
+ spin_unlock_bh(&pcpu->lock);
+ rcu_read_unlock();
+ }
+
+ return wait;
+}
+
+static void __exit nf_conntrack_rtcache_fini(void)
+{
+ struct net *net;
+ int count = 0;
+
+ synchronize_net();
+
+ unregister_netdevice_notifier(&nf_rtcache_notifier);
+ unregister_pernet_subsys(&rtcache_ops_net_ops);
+ for_each_net(net)
+ nf_unregister_net_hooks(net, rtcache_ops, ARRAY_SIZE(rtcache_ops));
+
+ synchronize_net();
+
+ rtnl_lock();
+
+ /* zap all conntracks with rtcache extension */
+ for_each_net(net)
+ nf_ct_iterate_cleanup_net(net, nf_rtcache_ext_remove, NULL, 0, 0);
+
+ for_each_net(net) {
+ /* .. and make sure they're gone from dying list, too */
+ while (nf_conntrack_rtcache_wait_for_dying(net)) {
+ msleep(200);
+ WARN_ONCE(++count > 25, "Waiting for all rtcache conntracks to go away\n");
+ }
+ }
+
+ rtnl_unlock();
+
+ synchronize_net();
+ nf_ct_extend_unregister(&rtcache_extend);
+}
+module_init(nf_conntrack_rtcache_init);
+module_exit(nf_conntrack_rtcache_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
+MODULE_DESCRIPTION("Conntrack route cache extension");
|