aboutsummaryrefslogtreecommitdiff
path: root/net/netfilter/nf_queue.c
blob: d812c1235b30372b35f7b2866b113a9878b27147 (plain)
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
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/skbuff.h>
#include <linux/netfilter.h>
#include <linux/seq_file.h>
#include <linux/rcupdate.h>
#include <net/protocol.h>
#include <net/netfilter/nf_queue.h>
#include <net/dst.h>

#include "nf_internals.h"

/*
 * Hook for nfnetlink_queue to register its queue handler.
 * We do this so that most of the NFQUEUE code can be modular.
 *
 * Once the queue is registered it must reinject all packets it
 * receives, no matter what.
 */
static const struct nf_queue_handler __rcu *queue_handler __read_mostly;

/* return EBUSY when somebody else is registered, return EEXIST if the
 * same handler is registered, return 0 in case of success. */
void nf_register_queue_handler(const struct nf_queue_handler *qh)
{
	/* should never happen, we only have one queueing backend in kernel */
	WARN_ON(rcu_access_pointer(queue_handler));
	rcu_assign_pointer(queue_handler, qh);
}
EXPORT_SYMBOL(nf_register_queue_handler);

/* The caller must flush their queue before this */
void nf_unregister_queue_handler(void)
{
	RCU_INIT_POINTER(queue_handler, NULL);
	synchronize_rcu();
}
EXPORT_SYMBOL(nf_unregister_queue_handler);

static void nf_queue_entry_release_refs(struct nf_queue_entry *entry)
{
	/* Release those devices we held, or Alexey will kill me. */
	if (entry->indev)
		dev_put(entry->indev);
	if (entry->outdev)
		dev_put(entry->outdev);
#ifdef CONFIG_BRIDGE_NETFILTER
	if (entry->skb->nf_bridge) {
		struct nf_bridge_info *nf_bridge = entry->skb->nf_bridge;

		if (nf_bridge->physindev)
			dev_put(nf_bridge->physindev);
		if (nf_bridge->physoutdev)
			dev_put(nf_bridge->physoutdev);
	}
#endif
	/* Drop reference to owner of hook which queued us. */
	module_put(entry->elem->owner);
}

/*
 * Any packet that leaves via this function must come back
 * through nf_reinject().
 */
static int __nf_queue(struct sk_buff *skb,
		      struct nf_hook_ops *elem,
		      u_int8_t pf, unsigned int hook,
		      struct net_device *indev,
		      struct net_device *outdev,
		      int (*okfn)(struct sk_buff *),
		      unsigned int queuenum)
{
	int status = -ENOENT;
	struct nf_queue_entry *entry = NULL;
#ifdef CONFIG_BRIDGE_NETFILTER
	struct net_device *physindev;
	struct net_device *physoutdev;
#endif
	const struct nf_afinfo *afinfo;
	const struct nf_queue_handler *qh;

	/* QUEUE == DROP if no one is waiting, to be safe. */
	rcu_read_lock();

	qh = rcu_dereference(queue_handler);
	if (!qh) {
		status = -ESRCH;
		goto err_unlock;
	}

	afinfo = nf_get_afinfo(pf);
	if (!afinfo)
		goto err_unlock;

	entry = kmalloc(sizeof(*entry) + afinfo->route_key_size, GFP_ATOMIC);
	if (!entry) {
		status = -ENOMEM;
		goto err_unlock;
	}

	*entry = (struct nf_queue_entry) {
		.skb	= skb,
		.elem	= elem,
		.pf	= pf,
		.hook	= hook,
		.indev	= indev,
		.outdev	= outdev,
		.okfn	= okfn,
	};

	/* If it's going away, ignore hook. */
	if (!try_module_get(entry->elem->owner)) {
		status = -ECANCELED;
		goto err_unlock;
	}
	/* Bump dev refs so they don't vanish while packet is out */
	if (indev)
		dev_hold(indev);
	if (outdev)
		dev_hold(outdev);
#ifdef CONFIG_BRIDGE_NETFILTER
	if (skb->nf_bridge) {
		physindev = skb->nf_bridge->physindev;
		if (physindev)
			dev_hold(physindev);
		physoutdev = skb->nf_bridge->physoutdev;
		if (physoutdev)
			dev_hold(physoutdev);
	}
#endif
	skb_dst_force(skb);
	afinfo->saveroute(skb, entry);
	status = qh->outfn(entry, queuenum);

	rcu_read_unlock();

	if (status < 0) {
		nf_queue_entry_release_refs(entry);
		goto err;
	}

	return 0;

err_unlock:
	rcu_read_unlock();
err:
	kfree(entry);
	return status;
}

#ifdef CONFIG_BRIDGE_NETFILTER
/* When called from bridge netfilter, skb->data must point to MAC header
 * before calling skb_gso_segment(). Else, original MAC header is lost
 * and segmented skbs will be sent to wrong destination.
 */
static void nf_bridge_adjust_skb_data(struct sk_buff *skb)
{
	if (skb->nf_bridge)
		__skb_push(skb, skb->network_header - skb->mac_header);
}

static void nf_bridge_adjust_segmented_data(struct sk_buff *skb)
{
	if (skb->nf_bridge)
		__skb_pull(skb, skb->network_header - skb->mac_header);
}
#else
#define nf_bridge_adjust_skb_data(s) do {} while (0)
#define nf_bridge_adjust_segmented_data(s) do {} while (0)
#endif

int nf_queue(struct sk_buff *skb,
	     struct nf_hook_ops *elem,
	     u_int8_t pf, unsigned int hook,
	     struct net_device *indev,
	     struct net_device *outdev,
	     int (*okfn)(struct sk_buff *),
	     unsigned int queuenum)
{
	struct sk_buff *segs;
	int err = -EINVAL;
	unsigned int queued;

	if (!skb_is_gso(skb))
		return __nf_queue(skb, elem, pf, hook, indev, outdev, okfn,
				  queuenum);

	switch (pf) {
	case NFPROTO_IPV4:
		skb->protocol = htons(ETH_P_IP);
		break;
	case NFPROTO_IPV6:
		skb->protocol = htons(ETH_P_IPV6);
		break;
	}

	nf_bridge_adjust_skb_data(skb);
	segs = skb_gso_segment(skb, 0);
	/* Does not use PTR_ERR to limit the number of error codes that can be
	 * returned by nf_queue.  For instance, callers rely on -ECANCELED to mean
	 * 'ignore this hook'.
	 */
	if (IS_ERR(segs))
		goto out_err;
	queued = 0;
	err = 0;
	do {
		struct sk_buff *nskb = segs->next;

		segs->next = NULL;
		if (err == 0) {
			nf_bridge_adjust_segmented_data(segs);
			err = __nf_queue(segs, elem, pf, hook, indev,
					   outdev, okfn, queuenum);
		}
		if (err == 0)
			queued++;
		else
			kfree_skb(segs);
		segs = nskb;
	} while (segs);

	if (queued) {
		kfree_skb(skb);
		return 0;
	}
  out_err:
	nf_bridge_adjust_segmented_data(skb);
	return err;
}

void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict)
{
	struct sk_buff *skb = entry->skb;
	struct nf_hook_ops *elem = entry->elem;
	const struct nf_afinfo *afinfo;
	int err;

	rcu_read_lock();

	nf_queue_entry_release_refs(entry);

	/* Continue traversal iff userspace said ok... */
	if (verdict == NF_REPEAT) {
		elem = list_entry(elem->list.prev, struct nf_hook_ops, list);
		verdict = NF_ACCEPT;
	}

	if (verdict == NF_ACCEPT) {
		afinfo = nf_get_afinfo(entry->pf);
		if (!afinfo || afinfo->reroute(skb, entry) < 0)
			verdict = NF_DROP;
	}

	if (verdict == NF_ACCEPT) {
	next_hook:
		verdict = nf_iterate(&nf_hooks[entry->pf][entry->hook],
				     skb, entry->hook,
				     entry->indev, entry->outdev, &elem,
				     entry->okfn, INT_MIN);
	}

	switch (verdict & NF_VERDICT_MASK) {
	case NF_ACCEPT:
	case NF_STOP:
		local_bh_disable();
		entry->okfn(skb);
		local_bh_enable();
		break;
	case NF_QUEUE:
		err = __nf_queue(skb, elem, entry->pf, entry->hook,
				 entry->indev, entry->outdev, entry->okfn,
				 verdict >> NF_VERDICT_QBITS);
		if (err < 0) {
			if (err == -ECANCELED)
				goto next_hook;
			if (err == -ESRCH &&
			   (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS))
				goto next_hook;
			kfree_skb(skb);
		}
		break;
	case NF_STOLEN:
		break;
	default:
		kfree_skb(skb);
	}
	rcu_read_unlock();
	kfree(entry);
}
EXPORT_SYMBOL(nf_reinject);