summaryrefslogtreecommitdiff
path: root/net/xfrm/xfrm_device.c
blob: 39bce5d764de5d28682368e4cbfa18f7c7f16e63 (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
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
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * xfrm_device.c - IPsec device offloading code.
 *
 * Copyright (c) 2015 secunet Security Networks AG
 *
 * Author:
 * Steffen Klassert <steffen.klassert@secunet.com>
 */

#include <linux/errno.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <net/dst.h>
#include <net/xfrm.h>
#include <linux/notifier.h>

#ifdef CONFIG_XFRM_OFFLOAD
static void __xfrm_transport_prep(struct xfrm_state *x, struct sk_buff *skb,
				  unsigned int hsize)
{
	struct xfrm_offload *xo = xfrm_offload(skb);

	skb_reset_mac_len(skb);
	if (xo->flags & XFRM_GSO_SEGMENT)
		skb->transport_header -= x->props.header_len;

	pskb_pull(skb, skb_transport_offset(skb) + x->props.header_len);
}

static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb,
				    unsigned int hsize)

{
	struct xfrm_offload *xo = xfrm_offload(skb);

	if (xo->flags & XFRM_GSO_SEGMENT)
		skb->transport_header = skb->network_header + hsize;

	skb_reset_mac_len(skb);
	pskb_pull(skb, skb->mac_len + x->props.header_len);
}

static void __xfrm_mode_beet_prep(struct xfrm_state *x, struct sk_buff *skb,
				  unsigned int hsize)
{
	struct xfrm_offload *xo = xfrm_offload(skb);
	int phlen = 0;

	if (xo->flags & XFRM_GSO_SEGMENT)
		skb->transport_header = skb->network_header + hsize;

	skb_reset_mac_len(skb);
	if (x->sel.family != AF_INET6) {
		phlen = IPV4_BEET_PHMAXLEN;
		if (x->outer_mode.family == AF_INET6)
			phlen += sizeof(struct ipv6hdr) - sizeof(struct iphdr);
	}

	pskb_pull(skb, skb->mac_len + hsize + (x->props.header_len - phlen));
}

/* Adjust pointers into the packet when IPsec is done at layer2 */
static void xfrm_outer_mode_prep(struct xfrm_state *x, struct sk_buff *skb)
{
	switch (x->outer_mode.encap) {
	case XFRM_MODE_TUNNEL:
		if (x->outer_mode.family == AF_INET)
			return __xfrm_mode_tunnel_prep(x, skb,
						       sizeof(struct iphdr));
		if (x->outer_mode.family == AF_INET6)
			return __xfrm_mode_tunnel_prep(x, skb,
						       sizeof(struct ipv6hdr));
		break;
	case XFRM_MODE_TRANSPORT:
		if (x->outer_mode.family == AF_INET)
			return __xfrm_transport_prep(x, skb,
						     sizeof(struct iphdr));
		if (x->outer_mode.family == AF_INET6)
			return __xfrm_transport_prep(x, skb,
						     sizeof(struct ipv6hdr));
		break;
	case XFRM_MODE_BEET:
		if (x->outer_mode.family == AF_INET)
			return __xfrm_mode_beet_prep(x, skb,
						     sizeof(struct iphdr));
		if (x->outer_mode.family == AF_INET6)
			return __xfrm_mode_beet_prep(x, skb,
						     sizeof(struct ipv6hdr));
		break;
	case XFRM_MODE_ROUTEOPTIMIZATION:
	case XFRM_MODE_IN_TRIGGER:
		break;
	}
}

struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again)
{
	int err;
	unsigned long flags;
	struct xfrm_state *x;
	struct softnet_data *sd;
	struct sk_buff *skb2, *nskb, *pskb = NULL;
	netdev_features_t esp_features = features;
	struct xfrm_offload *xo = xfrm_offload(skb);
	struct net_device *dev = skb->dev;
	struct sec_path *sp;

	if (!xo || (xo->flags & XFRM_XMIT))
		return skb;

	if (!(features & NETIF_F_HW_ESP))
		esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);

	sp = skb_sec_path(skb);
	x = sp->xvec[sp->len - 1];
	if (xo->flags & XFRM_GRO || x->xso.flags & XFRM_OFFLOAD_INBOUND)
		return skb;

	/* This skb was already validated on the upper/virtual dev */
	if ((x->xso.dev != dev) && (x->xso.real_dev == dev))
		return skb;

	local_irq_save(flags);
	sd = this_cpu_ptr(&softnet_data);
	err = !skb_queue_empty(&sd->xfrm_backlog);
	local_irq_restore(flags);

	if (err) {
		*again = true;
		return skb;
	}

	if (skb_is_gso(skb) && unlikely(x->xso.dev != dev)) {
		struct sk_buff *segs;

		/* Packet got rerouted, fixup features and segment it. */
		esp_features = esp_features & ~(NETIF_F_HW_ESP | NETIF_F_GSO_ESP);

		segs = skb_gso_segment(skb, esp_features);
		if (IS_ERR(segs)) {
			kfree_skb(skb);
			atomic_long_inc(&dev->tx_dropped);
			return NULL;
		} else {
			consume_skb(skb);
			skb = segs;
		}
	}

	if (!skb->next) {
		esp_features |= skb->dev->gso_partial_features;
		xfrm_outer_mode_prep(x, skb);

		xo->flags |= XFRM_DEV_RESUME;

		err = x->type_offload->xmit(x, skb, esp_features);
		if (err) {
			if (err == -EINPROGRESS)
				return NULL;

			XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR);
			kfree_skb(skb);
			return NULL;
		}

		skb_push(skb, skb->data - skb_mac_header(skb));

		return skb;
	}

	skb_list_walk_safe(skb, skb2, nskb) {
		esp_features |= skb->dev->gso_partial_features;
		skb_mark_not_on_list(skb2);

		xo = xfrm_offload(skb2);
		xo->flags |= XFRM_DEV_RESUME;

		xfrm_outer_mode_prep(x, skb2);

		err = x->type_offload->xmit(x, skb2, esp_features);
		if (!err) {
			skb2->next = nskb;
		} else if (err != -EINPROGRESS) {
			XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR);
			skb2->next = nskb;
			kfree_skb_list(skb2);
			return NULL;
		} else {
			if (skb == skb2)
				skb = nskb;
			else
				pskb->next = nskb;

			continue;
		}

		skb_push(skb2, skb2->data - skb_mac_header(skb2));
		pskb = skb2;
	}

	return skb;
}
EXPORT_SYMBOL_GPL(validate_xmit_xfrm);

int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
		       struct xfrm_user_offload *xuo)
{
	int err;
	struct dst_entry *dst;
	struct net_device *dev;
	struct xfrm_state_offload *xso = &x->xso;
	xfrm_address_t *saddr;
	xfrm_address_t *daddr;

	if (!x->type_offload)
		return -EINVAL;

	/* We don't yet support UDP encapsulation and TFC padding. */
	if (x->encap || x->tfcpad)
		return -EINVAL;

	if (xuo->flags & ~(XFRM_OFFLOAD_IPV6 | XFRM_OFFLOAD_INBOUND))
		return -EINVAL;

	dev = dev_get_by_index(net, xuo->ifindex);
	if (!dev) {
		if (!(xuo->flags & XFRM_OFFLOAD_INBOUND)) {
			saddr = &x->props.saddr;
			daddr = &x->id.daddr;
		} else {
			saddr = &x->id.daddr;
			daddr = &x->props.saddr;
		}

		dst = __xfrm_dst_lookup(net, 0, 0, saddr, daddr,
					x->props.family,
					xfrm_smark_get(0, x));
		if (IS_ERR(dst))
			return 0;

		dev = dst->dev;

		dev_hold(dev);
		dst_release(dst);
	}

	if (!dev->xfrmdev_ops || !dev->xfrmdev_ops->xdo_dev_state_add) {
		xso->dev = NULL;
		dev_put(dev);
		return 0;
	}

	if (x->props.flags & XFRM_STATE_ESN &&
	    !dev->xfrmdev_ops->xdo_dev_state_advance_esn) {
		xso->dev = NULL;
		dev_put(dev);
		return -EINVAL;
	}

	xso->dev = dev;
	netdev_tracker_alloc(dev, &xso->dev_tracker, GFP_ATOMIC);
	xso->real_dev = dev;
	xso->num_exthdrs = 1;
	/* Don't forward bit that is not implemented */
	xso->flags = xuo->flags & ~XFRM_OFFLOAD_IPV6;

	err = dev->xfrmdev_ops->xdo_dev_state_add(x);
	if (err) {
		xso->num_exthdrs = 0;
		xso->flags = 0;
		xso->dev = NULL;
		xso->real_dev = NULL;
		dev_put_track(dev, &xso->dev_tracker);

		if (err != -EOPNOTSUPP)
			return err;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(xfrm_dev_state_add);

bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
{
	int mtu;
	struct dst_entry *dst = skb_dst(skb);
	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
	struct net_device *dev = x->xso.dev;

	if (!x->type_offload || x->encap)
		return false;

	if ((!dev || (dev == xfrm_dst_path(dst)->dev)) &&
	    (!xdst->child->xfrm)) {
		mtu = xfrm_state_mtu(x, xdst->child_mtu_cached);
		if (skb->len <= mtu)
			goto ok;

		if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu))
			goto ok;
	}

	return false;

ok:
	if (dev && dev->xfrmdev_ops && dev->xfrmdev_ops->xdo_dev_offload_ok)
		return x->xso.dev->xfrmdev_ops->xdo_dev_offload_ok(skb, x);

	return true;
}
EXPORT_SYMBOL_GPL(xfrm_dev_offload_ok);

void xfrm_dev_resume(struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	int ret = NETDEV_TX_BUSY;
	struct netdev_queue *txq;
	struct softnet_data *sd;
	unsigned long flags;

	rcu_read_lock();
	txq = netdev_core_pick_tx(dev, skb, NULL);

	HARD_TX_LOCK(dev, txq, smp_processor_id());
	if (!netif_xmit_frozen_or_stopped(txq))
		skb = dev_hard_start_xmit(skb, dev, txq, &ret);
	HARD_TX_UNLOCK(dev, txq);

	if (!dev_xmit_complete(ret)) {
		local_irq_save(flags);
		sd = this_cpu_ptr(&softnet_data);
		skb_queue_tail(&sd->xfrm_backlog, skb);
		raise_softirq_irqoff(NET_TX_SOFTIRQ);
		local_irq_restore(flags);
	}
	rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(xfrm_dev_resume);

void xfrm_dev_backlog(struct softnet_data *sd)
{
	struct sk_buff_head *xfrm_backlog = &sd->xfrm_backlog;
	struct sk_buff_head list;
	struct sk_buff *skb;

	if (skb_queue_empty(xfrm_backlog))
		return;

	__skb_queue_head_init(&list);

	spin_lock(&xfrm_backlog->lock);
	skb_queue_splice_init(xfrm_backlog, &list);
	spin_unlock(&xfrm_backlog->lock);

	while (!skb_queue_empty(&list)) {
		skb = __skb_dequeue(&list);
		xfrm_dev_resume(skb);
	}

}
#endif

static int xfrm_api_check(struct net_device *dev)
{
#ifdef CONFIG_XFRM_OFFLOAD
	if ((dev->features & NETIF_F_HW_ESP_TX_CSUM) &&
	    !(dev->features & NETIF_F_HW_ESP))
		return NOTIFY_BAD;

	if ((dev->features & NETIF_F_HW_ESP) &&
	    (!(dev->xfrmdev_ops &&
	       dev->xfrmdev_ops->xdo_dev_state_add &&
	       dev->xfrmdev_ops->xdo_dev_state_delete)))
		return NOTIFY_BAD;
#else
	if (dev->features & (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM))
		return NOTIFY_BAD;
#endif

	return NOTIFY_DONE;
}

static int xfrm_dev_register(struct net_device *dev)
{
	return xfrm_api_check(dev);
}

static int xfrm_dev_feat_change(struct net_device *dev)
{
	return xfrm_api_check(dev);
}

static int xfrm_dev_down(struct net_device *dev)
{
	if (dev->features & NETIF_F_HW_ESP)
		xfrm_dev_state_flush(dev_net(dev), dev, true);

	return NOTIFY_DONE;
}

static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
	struct net_device *dev = netdev_notifier_info_to_dev(ptr);

	switch (event) {
	case NETDEV_REGISTER:
		return xfrm_dev_register(dev);

	case NETDEV_FEAT_CHANGE:
		return xfrm_dev_feat_change(dev);

	case NETDEV_DOWN:
	case NETDEV_UNREGISTER:
		return xfrm_dev_down(dev);
	}
	return NOTIFY_DONE;
}

static struct notifier_block xfrm_dev_notifier = {
	.notifier_call	= xfrm_dev_event,
};

void __init xfrm_dev_init(void)
{
	register_netdevice_notifier(&xfrm_dev_notifier);
}