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
|
/*
* net/sched/ipt.c iptables target interface
*
*TODO: Add other tables. For now we only support the ipv4 table targets
*
* 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.
*
* Copyright: Jamal Hadi Salim (2002-4)
*/
#include <asm/uaccess.h>
#include <asm/system.h>
#include <asm/bitops.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/proc_fs.h>
#include <linux/kmod.h>
#include <net/sock.h>
#include <net/pkt_sched.h>
#include <linux/tc_act/tc_ipt.h>
#include <net/tc_act/tc_ipt.h>
#include <linux/netfilter_ipv4/ip_tables.h>
#define IPT_TAB_MASK 15
static struct tcf_common *tcf_ipt_ht[IPT_TAB_MASK + 1];
static u32 ipt_idx_gen;
static DEFINE_RWLOCK(ipt_lock);
static struct tcf_hashinfo ipt_hash_info = {
.htab = tcf_ipt_ht,
.hmask = IPT_TAB_MASK,
.lock = &ipt_lock,
};
static int ipt_init_target(struct ipt_entry_target *t, char *table, unsigned int hook)
{
struct xt_target *target;
int ret = 0;
target = xt_request_find_target(AF_INET, t->u.user.name,
t->u.user.revision);
if (!target)
return -ENOENT;
t->u.kernel.target = target;
ret = xt_check_target(target, AF_INET, t->u.target_size - sizeof(*t),
table, hook, 0, 0);
if (ret) {
module_put(t->u.kernel.target->me);
return ret;
}
if (t->u.kernel.target->checkentry
&& !t->u.kernel.target->checkentry(table, NULL,
t->u.kernel.target, t->data,
hook)) {
module_put(t->u.kernel.target->me);
ret = -EINVAL;
}
return ret;
}
static void ipt_destroy_target(struct ipt_entry_target *t)
{
if (t->u.kernel.target->destroy)
t->u.kernel.target->destroy(t->u.kernel.target, t->data);
module_put(t->u.kernel.target->me);
}
static int tcf_ipt_release(struct tcf_ipt *ipt, int bind)
{
int ret = 0;
if (ipt) {
if (bind)
ipt->tcf_bindcnt--;
ipt->tcf_refcnt--;
if (ipt->tcf_bindcnt <= 0 && ipt->tcf_refcnt <= 0) {
ipt_destroy_target(ipt->tcfi_t);
kfree(ipt->tcfi_tname);
kfree(ipt->tcfi_t);
tcf_hash_destroy(&ipt->common, &ipt_hash_info);
ret = ACT_P_DELETED;
}
}
return ret;
}
static int tcf_ipt_init(struct rtattr *rta, struct rtattr *est,
struct tc_action *a, int ovr, int bind)
{
struct rtattr *tb[TCA_IPT_MAX];
struct tcf_ipt *ipt;
struct tcf_common *pc;
struct ipt_entry_target *td, *t;
char *tname;
int ret = 0, err;
u32 hook = 0;
u32 index = 0;
if (rta == NULL || rtattr_parse_nested(tb, TCA_IPT_MAX, rta) < 0)
return -EINVAL;
if (tb[TCA_IPT_HOOK-1] == NULL ||
RTA_PAYLOAD(tb[TCA_IPT_HOOK-1]) < sizeof(u32))
return -EINVAL;
if (tb[TCA_IPT_TARG-1] == NULL ||
RTA_PAYLOAD(tb[TCA_IPT_TARG-1]) < sizeof(*t))
return -EINVAL;
td = (struct ipt_entry_target *)RTA_DATA(tb[TCA_IPT_TARG-1]);
if (RTA_PAYLOAD(tb[TCA_IPT_TARG-1]) < td->u.target_size)
return -EINVAL;
if (tb[TCA_IPT_INDEX-1] != NULL &&
RTA_PAYLOAD(tb[TCA_IPT_INDEX-1]) >= sizeof(u32))
index = *(u32 *)RTA_DATA(tb[TCA_IPT_INDEX-1]);
pc = tcf_hash_check(index, a, bind, &ipt_hash_info);
if (!pc) {
pc = tcf_hash_create(index, est, a, sizeof(*ipt), bind,
&ipt_idx_gen, &ipt_hash_info);
if (unlikely(!pc))
return -ENOMEM;
ret = ACT_P_CREATED;
} else {
if (!ovr) {
tcf_ipt_release(to_ipt(pc), bind);
return -EEXIST;
}
}
ipt = to_ipt(pc);
hook = *(u32 *)RTA_DATA(tb[TCA_IPT_HOOK-1]);
err = -ENOMEM;
tname = kmalloc(IFNAMSIZ, GFP_KERNEL);
if (unlikely(!tname))
goto err1;
if (tb[TCA_IPT_TABLE - 1] == NULL ||
rtattr_strlcpy(tname, tb[TCA_IPT_TABLE-1], IFNAMSIZ) >= IFNAMSIZ)
strcpy(tname, "mangle");
t = kmemdup(td, td->u.target_size, GFP_KERNEL);
if (unlikely(!t))
goto err2;
if ((err = ipt_init_target(t, tname, hook)) < 0)
goto err3;
spin_lock_bh(&ipt->tcf_lock);
if (ret != ACT_P_CREATED) {
ipt_destroy_target(ipt->tcfi_t);
kfree(ipt->tcfi_tname);
kfree(ipt->tcfi_t);
}
ipt->tcfi_tname = tname;
ipt->tcfi_t = t;
ipt->tcfi_hook = hook;
spin_unlock_bh(&ipt->tcf_lock);
if (ret == ACT_P_CREATED)
tcf_hash_insert(pc, &ipt_hash_info);
return ret;
err3:
kfree(t);
err2:
kfree(tname);
err1:
kfree(pc);
return err;
}
static int tcf_ipt_cleanup(struct tc_action *a, int bind)
{
struct tcf_ipt *ipt = a->priv;
return tcf_ipt_release(ipt, bind);
}
static int tcf_ipt(struct sk_buff *skb, struct tc_action *a,
struct tcf_result *res)
{
int ret = 0, result = 0;
struct tcf_ipt *ipt = a->priv;
if (skb_cloned(skb)) {
if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
return TC_ACT_UNSPEC;
}
spin_lock(&ipt->tcf_lock);
ipt->tcf_tm.lastuse = jiffies;
ipt->tcf_bstats.bytes += skb->len;
ipt->tcf_bstats.packets++;
/* yes, we have to worry about both in and out dev
worry later - danger - this API seems to have changed
from earlier kernels */
/* iptables targets take a double skb pointer in case the skb
* needs to be replaced. We don't own the skb, so this must not
* happen. The pskb_expand_head above should make sure of this */
ret = ipt->tcfi_t->u.kernel.target->target(&skb, skb->dev, NULL,
ipt->tcfi_hook,
ipt->tcfi_t->u.kernel.target,
ipt->tcfi_t->data);
switch (ret) {
case NF_ACCEPT:
result = TC_ACT_OK;
break;
case NF_DROP:
result = TC_ACT_SHOT;
ipt->tcf_qstats.drops++;
break;
case IPT_CONTINUE:
result = TC_ACT_PIPE;
break;
default:
if (net_ratelimit())
printk("Bogus netfilter code %d assume ACCEPT\n", ret);
result = TC_POLICE_OK;
break;
}
spin_unlock(&ipt->tcf_lock);
return result;
}
static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_ipt *ipt = a->priv;
struct ipt_entry_target *t;
|