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
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
|
/*
* ip_vs_app.c: Application module support for IPVS
*
* Authors: Wensong Zhang <wensong@linuxvirtualserver.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.
*
* Most code here is taken from ip_masq_app.c in kernel 2.2. The difference
* is that ip_vs_app module handles the reverse direction (incoming requests
* and outgoing responses).
*
* IP_MASQ_APP application masquerading module
*
* Author: Juan Jose Ciarlante, <jjciarla@raiz.uncu.edu.ar>
*
*/
#define KMSG_COMPONENT "IPVS"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/netfilter.h>
#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/protocol.h>
#include <net/tcp.h>
#include <linux/stat.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/mutex.h>
#include <net/ip_vs.h>
EXPORT_SYMBOL(register_ip_vs_app);
EXPORT_SYMBOL(unregister_ip_vs_app);
EXPORT_SYMBOL(register_ip_vs_app_inc);
static DEFINE_MUTEX(__ip_vs_app_mutex);
/*
* Get an ip_vs_app object
*/
static inline int ip_vs_app_get(struct ip_vs_app *app)
{
return try_module_get(app->module);
}
static inline void ip_vs_app_put(struct ip_vs_app *app)
{
module_put(app->module);
}
static void ip_vs_app_inc_destroy(struct ip_vs_app *inc)
{
kfree(inc->timeout_table);
kfree(inc);
}
static void ip_vs_app_inc_rcu_free(struct rcu_head *head)
{
struct ip_vs_app *inc = container_of(head, struct ip_vs_app, rcu_head);
ip_vs_app_inc_destroy(inc);
}
/*
* Allocate/initialize app incarnation and register it in proto apps.
*/
static int
ip_vs_app_inc_new(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 proto,
__u16 port)
{
struct ip_vs_protocol *pp;
struct ip_vs_app *inc;
int ret;
if (!(pp = ip_vs_proto_get(proto)))
return -EPROTONOSUPPORT;
if (!pp->unregister_app)
return -EOPNOTSUPP;
inc = kmemdup(app, sizeof(*inc), GFP_KERNEL);
if (!inc)
return -ENOMEM;
INIT_LIST_HEAD(&inc->p_list);
INIT_LIST_HEAD(&inc->incs_list);
inc->app = app;
inc->port = htons(port);
atomic_set(&inc->usecnt, 0);
if (app->timeouts) {
inc->timeout_table =
ip_vs_create_timeout_table(app->timeouts,
app->timeouts_size);
if (!inc->timeout_table) {
ret = -ENOMEM;
goto out;
}
}
ret = pp->register_app(ipvs, inc);
if (ret)
goto out;
list_add(&inc->a_list, &app->incs_list);
IP_VS_DBG(9, "%s App %s:%u registered\n",
pp->name, inc->name, ntohs(inc->port));
return 0;
out:
ip_vs_app_inc_destroy(inc);
return ret;
}
/*
* Release app incarnation
*/
static void
ip_vs_app_inc_release(struct netns_ipvs *ipvs, struct ip_vs_app *inc)
{
struct ip_vs_protocol *pp;
if (!(pp = ip_vs_proto_get(inc->protocol)))
return;
if (pp->unregister_app)
pp->unregister_app(ipvs, inc);
IP_VS_DBG(9, "%s App %s:%u unregistered\n",
pp->name, inc->name, ntohs(inc->port));
list_del(&inc->a_list);
call_rcu(&inc->rcu_head, ip_vs_app_inc_rcu_free);
}
/*
* Get reference to app inc (only called from softirq)
*
*/
int ip_vs_app_inc_get(struct ip_vs_app *inc)
{
int result;
result = ip_vs_app_get(inc->app);
if (result)
atomic_inc(&inc->usecnt);
return result;
}
/*
* Put the app inc (only called from timer or net softirq)
*/
void ip_vs_app_inc_put(struct ip_vs_app *inc)
{
atomic_dec(&inc->usecnt);
ip_vs_app_put(inc->app);
}
/*
* Register an application incarnation in protocol applications
*/
int
register_ip_vs_app_inc(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 proto,
__u16 port)
{
int result;
mutex_lock(&__ip_vs_app_mutex);
result = ip_vs_app_inc_new(ipvs, app, proto, port);
mutex_unlock(&__ip_vs_app_mutex);
return result;
}
/* Register application for netns */
struct ip_vs_app *register_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app)
{
struct ip_vs_app *a;
int err = 0;
mutex_lock(&__ip_vs_app_mutex);
list_for_each_entry(a, &ipvs->app_list, a_list) {
if (!strcmp(app->name, a->name)) {
err = -EEXIST;
goto out_unlock;
}
}
a = kmemdup(app, sizeof(*app), GFP_KERNEL);
if (!a) {
err = -ENOMEM;
goto out_unlock;
}
INIT_LIST_HEAD(&a->incs_list);
list_add(&a->a_list, &ipvs->app_list);
/* increase the module use count */
ip_vs_use_count_inc();
out_unlock:
mutex_unlock(&__ip_vs_app_mutex);
return err ? ERR_PTR(err) : a;
}
/*
* ip_vs_app unregistration routine
* We are sure there are no app incarnations attached to services
* Caller should use synchronize_rcu() or rcu_barrier()
*/
void unregister_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app)
{
struct ip_vs_app *a, *anxt, *inc, *nxt;
mutex_lock(&__ip_vs_app_mutex);
list_for_each_entry_safe(a, anxt, &ipvs->app_list, a_list) {
if (app && strcmp(app->name, a->name))
continue;
list_for_each_entry_safe(inc, nxt, &a->incs_list, a_list) {
ip_vs_app_inc_release(ipvs, inc);
}
list_del(&a->a_list);
kfree(a);
/* decrease the module use count */
ip_vs_use_count_dec();
}
mutex_unlock(&__ip_vs_app_mutex);
}
/*
* Bind ip_vs_conn to its ip_vs_app (called by cp constructor)
*/
int ip_vs_bind_app(struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
return pp->app_conn_bind(cp);
}
/*
* Unbind cp from application incarnation (called by cp destructor)
*/
void ip_vs_unbind_app(struct ip_vs_conn *cp)
{
struct ip_vs_app *inc = cp->app;
if (!inc)
return;
if (inc->unbind_conn)
inc->unbind_conn(inc, cp);
if (inc->done_conn)
inc->done_conn(inc, cp);
ip_vs_app_inc_put(inc);
cp->app = NULL;
}
/*
* Fixes th->seq based on ip_vs_seq info.
*/
static inline void vs_fix_seq(const struct ip_vs_seq *vseq, struct tcphdr *th)
{
__u32 seq = ntohl(th->seq);
/*
* Adjust seq with delta-offset for all packets after
* the most recent resized pkt seq and with previous_delta offset
* for all packets before most recent resized pkt seq.
*/
if (vseq->delta || vseq->previous_delta) {
if(after(seq, vseq->init_seq)) {
th->seq = htonl(seq + vseq->delta);
IP_VS_DBG(9, "%s(): added delta (%d) to seq\n",
__func__, vseq->delta);
} else {
th->seq = htonl(seq + vseq->previous_delta);
IP_VS_DBG(9, "%s(): added previous_delta (%d) to seq\n",
__func__, vseq->previous_delta);
}
}
}
/*
* Fixes th->ack_seq based on ip_vs_seq info.
*/
static inline void
vs_fix_ack_seq(const struct ip_vs_seq *vseq, struct tcphdr *th)
{
__u32 ack_seq = ntohl(th->ack_seq);
/*
* Adjust ack_seq with delta-offset for
* the packets AFTER most recent resized pkt has caused a shift
* for packets before most recent resized pkt, use previous_delta
*/
if (vseq->delta || vseq->previous_delta) {
/* since ack_seq is the number of octet that is expected
to receive next, so compare it with init_seq+delta */
if(after(ack_seq, vseq->init_seq+vseq->delta)) {
th->ack_seq = htonl(ack_seq - vseq->delta);
IP_VS_DBG(9, "%s(): subtracted delta "
"(%d) from ack_seq\n", __func__, vseq->delta);
} else {
th->ack_seq = htonl(ack_seq - vseq->previous_delta);
IP_VS_DBG(9, "%s(): subtracted "
"previous_delta (%d) from ack_seq\n",
__func__, vseq->previous_delta);
}
}
}
/*
* Updates ip_vs_seq if pkt has been resized
* Assumes already checked proto==IPPROTO_TCP and diff!=0.
*/
static inline void vs_seq_update(struct ip_vs_conn *cp, struct ip_vs_seq *vseq,
unsigned int flag, __u32 seq, int diff)
{
/* spinlock is to keep updating cp->flags atomic */
spin_lock_bh(&cp->lock);
if (!(cp->flags & flag) || after(seq, vseq->init_seq)) {
vseq->previous_delta = vseq->delta;
vseq->delta += diff;
vseq->init_seq = seq;
cp->flags |= flag;
}
spin_unlock_bh(&cp->lock);
}
static inline int app_tcp_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb,
struct ip_vs_app *app)
{
int diff;
const unsigned int tcp_offset = ip_hdrlen(skb);
struct tcphdr *th;
__u32 seq;
if (!skb_make_writable(skb, tcp_offset + sizeof(*th)))
return 0;
th = (struct tcphdr *)(skb_network_header(skb) + tcp_offset);
/*
* Remember seq number in case this pkt gets resized
*/
seq = ntohl(th->seq);
/*
* Fix seq stuff if flagged as so.
*/
if (cp->flags & IP_VS_CONN_F_OUT_SEQ)
vs_fix_seq(&cp->out_seq, th);
if (cp->flags & IP_VS_CONN_F_IN_SEQ)
vs_fix_ack_seq(&cp->in_seq, th);
/*
* Call private output hook function
*/
if (app->pkt_out == NULL)
return 1;
if (!app->pkt_out(app, cp, skb, &diff))
return 0;
/*
* Update ip_vs seq stuff if len has changed.
*/
if (diff != 0)
vs_seq_update(cp, &cp->out_seq,
IP_VS_CONN_F_OUT_SEQ, seq, diff);
return 1;
}
/*
* Output pkt hook. Will call bound ip_vs_app specific function
* called by ipvs packet handler, assumes previously checked cp!=NULL
* returns false if it can't handle packet (oom)
*/
int ip_vs_app_pkt_out(struct ip_vs_conn *cp, struct sk_buff *skb)
{
struct ip_vs_app *app;
/*
* check if application module is bound to
* this ip_vs_conn.
*/
if ((app = cp->app) == NULL)
return 1;
/* TCP is complicated */
if (cp->protocol == IPPROTO_TCP)
return app_tcp_pkt_out(cp, skb, app);
/*
* Call private output hook function
*/
if (app->pkt_out == NULL)
return 1;
return app->pkt_out(app, cp, skb, NULL);
}
static inline int app_tcp_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb,
struct ip_vs_app *app)
{
int diff;
const unsigned int tcp_offset = ip_hdrlen(skb);
struct tcphdr *th;
__u32 seq;
if (!skb_make_writable(skb, tcp_offset + sizeof(*th)))
return 0;
th = (struct tcphdr *)(skb_network_header(skb) + tcp_offset);
/*
* Remember seq number in case this pkt gets resized
*/
seq = ntohl(th->seq);
/*
* Fix seq stuff if flagged as so.
*/
if (cp->flags & IP_VS_CONN_F_IN_SEQ)
vs_fix_seq(&cp->in_seq, th);
if (cp->flags & IP_VS_CONN_F_OUT_SEQ)
vs_fix_ack_seq(&cp->out_seq, th);
/*
* Call private input hook function
*/
if (app->pkt_in == NULL)
return 1;
if (!app->pkt_in(app, cp, skb, &diff))
return 0;
/*
* Update ip_vs seq stuff if len has changed.
*/
if (diff != 0)
vs_seq_update(cp, &cp->in_seq,
IP_VS_CONN_F_IN_SEQ, seq, diff);
return 1;
}
/*
* Input pkt hook. Will call bound ip_vs_app specific function
* called by ipvs packet handler, assumes previously checked cp!=NULL.
* returns false if can't handle packet (oom).
*/
int ip_vs_app_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb)
{
struct ip_vs_app *app;
/*
* check if application module is bound to
* this ip_vs_conn.
*/
if ((app = cp->app) == NULL)
return 1;
/* TCP is complicated */
if (cp->protocol == IPPROTO_TCP)
return app_tcp_pkt_in(cp, skb, app);
/*
* Call private input hook function
*/
if (app->pkt_in == NULL)
return 1;
return app->pkt_in(app, cp, skb, NULL);
}
#ifdef CONFIG_PROC_FS
/*
* /proc/net/ip_vs_app entry function
*/
static struct ip_vs_app *ip_vs_app_idx(struct netns_ipvs *ipvs, loff_t pos)
{
struct ip_vs_app *app, *inc;
list_for_each_entry(app, &ipvs->app_list, a_list) {
list_for_each_entry(inc, &app->incs_list, a_list) {
if (pos-- == 0)
return inc;
}
}
return NULL;
}
static void *ip_vs_app_seq_start(struct seq_file *seq, loff_t *pos)
{
struct net *net = seq_file_net(seq);
struct netns_ipvs *ipvs = net_ipvs(net);
mutex_lock(&__ip_vs_app_mutex);
return *pos ? ip_vs_app_idx(ipvs, *pos - 1) : SEQ_START_TOKEN;
}
static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct ip_vs_app *inc, *app;
struct list_head *e;
struct net *net = seq_file_net(seq);
struct netns_ipvs *ipvs = net_ipvs(net);
++*pos;
if (v == SEQ_START_TOKEN)
return ip_vs_app_idx(ipvs, 0);
inc = v;
app = inc->app;
if ((e = inc->a_list.next) != &app->incs_list)
return list_entry(e, struct ip_vs_app, a_list);
/* go on to next application */
for (e = app->a_list.next; e != &ipvs->app_list; e = e->next) {
app = list_entry(e, struct ip_vs_app, a_list);
list_for_each_entry(inc, &app->incs_list, a_list) {
return inc;
}
}
return NULL;
}
static void ip_vs_app_seq_stop(struct seq_file *seq, void *v)
{
mutex_unlock(&__ip_vs_app_mutex);
}
static int ip_vs_app_seq_show(struct seq_file *seq, void *v)
{
if (v == SEQ_START_TOKEN)
seq_puts(seq, "prot port usecnt name\n");
else {
const struct ip_vs_app *inc = v;
seq_printf(seq, "%-3s %-7u %-6d %-17s\n",
ip_vs_proto_name(inc->protocol),
ntohs(inc->port),
atomic_read(&inc->usecnt),
inc->name);
}
return 0;
}
static const struct seq_operations ip_vs_app_seq_ops = {
.start = ip_vs_app_seq_start,
.next = ip_vs_app_seq_next,
.stop = ip_vs_app_seq_stop,
.show = ip_vs_app_seq_show,
};
static int ip_vs_app_open(struct inode *inode, struct file *file)
{
return seq_open_net(inode, file, &ip_vs_app_seq_ops,
sizeof(struct seq_net_private));
}
static const struct file_operations ip_vs_app_fops = {
.owner = THIS_MODULE,
.open = ip_vs_app_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_net,
};
#endif
int __net_init ip_vs_app_net_init(struct net *net)
{
struct netns_ipvs *ipvs = net_ipvs(net);
INIT_LIST_HEAD(&ipvs->app_list);
proc_create("ip_vs_app", 0, net->proc_net, &ip_vs_app_fops);
return 0;
}
void __net_exit ip_vs_app_net_cleanup(struct net *net)
{
struct netns_ipvs *ipvs = net_ipvs(net);
unregister_ip_vs_app(ipvs, NULL /* all */);
remove_proc_entry("ip_vs_app", net->proc_net);
}
|