summaryrefslogtreecommitdiff
path: root/net/sched/act_skbmod.c
blob: cd0accaf844a18e4a6a626adba5fae05df66b0a3 (plain) (blame)
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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * net/sched/act_skbmod.c  skb data modifier
 *
 * Copyright (c) 2016 Jamal Hadi Salim <jhs@mojatatu.com>
*/

#include <linux/module.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <net/inet_ecn.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
#include <net/tc_wrapper.h>

#include <linux/tc_act/tc_skbmod.h>
#include <net/tc_act/tc_skbmod.h>

static struct tc_action_ops act_skbmod_ops;

TC_INDIRECT_SCOPE int tcf_skbmod_act(struct sk_buff *skb,
				     const struct tc_action *a,
				     struct tcf_result *res)
{
	struct tcf_skbmod *d = to_skbmod(a);
	int action, max_edit_len, err;
	struct tcf_skbmod_params *p;
	u64 flags;

	tcf_lastuse_update(&d->tcf_tm);
	bstats_update(this_cpu_ptr(d->common.cpu_bstats), skb);

	action = READ_ONCE(d->tcf_action);
	if (unlikely(action == TC_ACT_SHOT))
		goto drop;

	max_edit_len = skb_mac_header_len(skb);
	p = rcu_dereference_bh(d->skbmod_p);
	flags = p->flags;

	/* tcf_skbmod_init() guarantees "flags" to be one of the following:
	 *	1. a combination of SKBMOD_F_{DMAC,SMAC,ETYPE}
	 *	2. SKBMOD_F_SWAPMAC
	 *	3. SKBMOD_F_ECN
	 * SKBMOD_F_ECN only works with IP packets; all other flags only work with Ethernet
	 * packets.
	 */
	if (flags == SKBMOD_F_ECN) {
		switch (skb_protocol(skb, true)) {
		case cpu_to_be16(ETH_P_IP):
		case cpu_to_be16(ETH_P_IPV6):
			max_edit_len += skb_network_header_len(skb);
			break;
		default:
			goto out;
		}
	} else if (!skb->dev || skb->dev->type != ARPHRD_ETHER) {
		goto out;
	}

	err = skb_ensure_writable(skb, max_edit_len);
	if (unlikely(err)) /* best policy is to drop on the floor */
		goto drop;

	if (flags & SKBMOD_F_DMAC)
		ether_addr_copy(eth_hdr(skb)->h_dest, p->eth_dst);
	if (flags & SKBMOD_F_SMAC)
		ether_addr_copy(eth_hdr(skb)->h_source, p->eth_src);
	if (flags & SKBMOD_F_ETYPE)
		eth_hdr(skb)->h_proto = p->eth_type;

	if (flags & SKBMOD_F_SWAPMAC) {
		u16 tmpaddr[ETH_ALEN / 2]; /* ether_addr_copy() requirement */
		/*XXX: I am sure we can come up with more efficient swapping*/
		ether_addr_copy((u8 *)tmpaddr, eth_hdr(skb)->h_dest);
		ether_addr_copy(eth_hdr(skb)->h_dest, eth_hdr(skb)->h_source);
		ether_addr_copy(eth_hdr(skb)->h_source, (u8 *)tmpaddr);
	}

	if (flags & SKBMOD_F_ECN)
		INET_ECN_set_ce(skb);

out:
	return action;

drop:
	qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats));
	return TC_ACT_SHOT;
}

static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = {
	[TCA_SKBMOD_PARMS]		= { .len = sizeof(struct tc_skbmod) },
	[TCA_SKBMOD_DMAC]		= { .len = ETH_ALEN },
	[TCA_SKBMOD_SMAC]		= { .len = ETH_ALEN },
	[TCA_SKBMOD_ETYPE]		= { .type = NLA_U16 },
};

static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
			   struct nlattr *est, struct tc_action **a,
			   struct tcf_proto *tp, u32 flags,
			   struct netlink_ext_ack *extack)
{
	struct tc_action_net *tn = net_generic(net, act_skbmod_ops.net_id);
	bool ovr = flags & TCA_ACT_FLAGS_REPLACE;
	bool bind = flags & TCA_ACT_FLAGS_BIND;
	struct nlattr *tb[TCA_SKBMOD_MAX + 1];
	struct tcf_skbmod_params *p, *p_old;
	struct tcf_chain *goto_ch = NULL;
	struct tc_skbmod *parm;
	u32 lflags = 0, index;
	struct tcf_skbmod *d;
	bool exists = false;
	u8 *daddr = NULL;
	u8 *saddr = NULL;
	u16 eth_type = 0;
	int ret = 0, err;

	if (!nla)
		return -EINVAL;

	err = nla_parse_nested_deprecated(tb, TCA_SKBMOD_MAX, nla,
					  skbmod_policy, NULL);
	if (err < 0)
		return err;

	if (!tb[TCA_SKBMOD_PARMS])
		return -EINVAL;

	if (tb[TCA_SKBMOD_DMAC]) {
		daddr = nla_data(tb[TCA_SKBMOD_DMAC]);
		lflags |= SKBMOD_F_DMAC;
	}

	if (tb[TCA_SKBMOD_SMAC]) {
		saddr = nla_data(tb[TCA_SKBMOD_SMAC]);
		lflags |= SKBMOD_F_SMAC;
	}

	if (tb[TCA_SKBMOD_ETYPE]) {
		eth_type = nla_get_u16(tb[TCA_SKBMOD_ETYPE]);
		lflags |= SKBMOD_F_ETYPE;
	}

	parm = nla_data(tb[TCA_SKBMOD_PARMS]);
	index = parm->index;
	if (parm->flags & SKBMOD_F_SWAPMAC)
		lflags = SKBMOD_F_SWAPMAC;
	if (parm->flags & SKBMOD_F_ECN)
		lflags = SKBMOD_F_ECN;

	err = tcf_idr_check_alloc(tn, &index, a, bind);
	if (err < 0)
		return err;
	exists = err;
	if (exists && bind)
		return ACT_P_BOUND;

	if (!lflags) {
		if (exists)
			tcf_idr_release(*a, bind);
		else
			tcf_idr_cleanup(tn, index);
		return -EINVAL;
	}

	if (!exists) {
		ret = tcf_idr_create(tn, index, est, a,
				     &act_skbmod_ops, bind, true, flags);
		if (ret) {
			tcf_idr_cleanup(tn, index);
			return ret;
		}

		ret = ACT_P_CREATED;
	} else if (!ovr) {
		tcf_idr_release(*a, bind);
		return -EEXIST;
	}
	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
	if (err < 0)
		goto release_idr;

	d = to_skbmod(*a);

	p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL);
	if (unlikely(!p)) {
		err = -ENOMEM;
		goto put_chain;
	}

	p->flags = lflags;

	if (ovr)
		spin_lock_bh(&d->tcf_lock);
	/* Protected by tcf_lock if overwriting existing action. */
	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
	p_old = rcu_dereference_protected(d->skbmod_p, 1);

	if (lflags & SKBMOD_F_DMAC)
		ether_addr_copy(p->eth_dst, daddr);
	if (lflags & SKBMOD_F_SMAC)
		ether_addr_copy(p->eth_src, saddr);
	if (lflags & SKBMOD_F_ETYPE)
		p->eth_type = htons(eth_type);

	rcu_assign_pointer(d->skbmod_p, p);
	if (ovr)
		spin_unlock_bh(&d->tcf_lock);

	if (p_old)
		kfree_rcu(p_old, rcu);
	if (goto_ch)
		tcf_chain_put_by_act(goto_ch);

	return ret;
put_chain:
	if (goto_ch)
		tcf_chain_put_by_act(goto_ch);
release_idr:
	tcf_idr_release(*a, bind);
	return err;
}

static void tcf_skbmod_cleanup(struct tc_action *a)
{
	struct tcf_skbmod *d = to_skbmod(a);
	struct tcf_skbmod_params  *p;

	p = rcu_dereference_protected(d->skbmod_p, 1);
	if (p)
		kfree_rcu(p, rcu);
}

static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
			   int bind, int ref)
{
	struct tcf_skbmod *d = to_skbmod(a);
	unsigned char *b = skb_tail_pointer(skb);
	struct tcf_skbmod_params  *p;
	struct tc_skbmod opt;
	struct tcf_t t;

	memset(&opt, 0, sizeof(opt));
	opt.index   = d->tcf_index;
	opt.refcnt  = refcount_read(&d->tcf_refcnt) - ref,
	opt.bindcnt = atomic_read(&d->tcf_bindcnt) - bind;
	spin_lock_bh(&d->tcf_lock);
	opt.action = d->tcf_action;
	p = rcu_dereference_protected(d->skbmod_p,
				      lockdep_is_held(&d->tcf_lock));
	opt.flags  = p->flags;
	if (nla_put(skb, TCA_SKBMOD_PARMS, sizeof(opt), &opt))
		goto nla_put_failure;
	if ((p->flags & SKBMOD_F_DMAC) &&
	    nla_put(skb, TCA_SKBMOD_DMAC, ETH_ALEN, p->eth_dst))
		goto nla_put_failure;
	if ((p->flags & SKBMOD_F_SMAC) &&
	    nla_put(skb, TCA_SKBMOD_SMAC, ETH_ALEN, p->eth_src))
		goto nla_put_failure;
	if ((p->flags & SKBMOD_F_ETYPE) &&
	    nla_put_u16(skb, TCA_SKBMOD_ETYPE, ntohs(p->eth_type)))
		goto nla_put_failure;

	tcf_tm_dump(&t, &d->tcf_tm);
	if (nla_put_64bit(skb, TCA_SKBMOD_TM, sizeof(t), &t, TCA_SKBMOD_PAD))
		goto nla_put_failure;

	spin_unlock_bh(&d->tcf_lock);
	return skb->len;
nla_put_failure:
	spin_unlock_bh(&d->tcf_lock);
	nlmsg_trim(skb, b);
	return -1;
}

static struct tc_action_ops act_skbmod_ops = {
	.kind		=	"skbmod",
	.id		=	TCA_ACT_SKBMOD,
	.owner		=	THIS_MODULE,
	.act		=	tcf_skbmod_act,
	.dump		=	tcf_skbmod_dump,
	.init		=	tcf_skbmod_init,
	.cleanup	=	tcf_skbmod_cleanup,
	.size		=	sizeof(struct tcf_skbmod),
};
MODULE_ALIAS_NET_ACT("skbmod");

static __net_init int skbmod_init_net(struct net *net)
{
	struct tc_action_net *tn = net_generic(net, act_skbmod_ops.net_id);

	return tc_action_net_init(net, tn, &act_skbmod_ops);
}

static void __net_exit skbmod_exit_net(struct list_head *net_list)
{
	tc_action_net_exit(net_list, act_skbmod_ops.net_id);
}

static struct pernet_operations skbmod_net_ops = {
	.init = skbmod_init_net,
	.exit_batch = skbmod_exit_net,
	.id   = &act_skbmod_ops.net_id,
	.size = sizeof(struct tc_action_net),
};

MODULE_AUTHOR("Jamal Hadi Salim, <jhs@mojatatu.com>");
MODULE_DESCRIPTION("SKB data mod-ing");
MODULE_LICENSE("GPL");

static int __init skbmod_init_module(void)
{
	return tcf_register_action(&act_skbmod_ops, &skbmod_net_ops);
}

static void __exit skbmod_cleanup_module(void)
{
	tcf_unregister_action(&act_skbmod_ops, &skbmod_net_ops);
}

module_init(skbmod_init_module);
module_exit(skbmod_cleanup_module);