summaryrefslogtreecommitdiffstats
path: root/net/ethernet/eth.c
blob: 9ea45aae04ee4604b396453192e8aa7a746c0673 (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
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
622
623
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Ethernet-type device handling.
 *
 * Version:	@(#)eth.c	1.0.7	05/25/93
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Mark Evans, <evansmp@uhura.aston.ac.uk>
 *		Florian  La Roche, <rzsfl@rz.uni-sb.de>
 *		Alan Cox, <gw4pts@gw4pts.ampr.org>
 *
 * Fixes:
 *		Mr Linux	: Arp problems
 *		Alan Cox	: Generic queue tidyup (very tiny here)
 *		Alan Cox	: eth_header ntohs should be htons
 *		Alan Cox	: eth_rebuild_header missing an htons and
 *				  minor other things.
 *		Tegge		: Arp bug fixes.
 *		Florian		: Removed many unnecessary functions, code cleanup
 *				  and changes for new arp and skbuff.
 *		Alan Cox	: Redid header building to reflect new format.
 *		Alan Cox	: ARP only when compiled with CONFIG_INET
 *		Greg Page	: 802.2 and SNAP stuff.
 *		Alan Cox	: MAC layer pointers/new format.
 *		Paul Gortmaker	: eth_copy_and_sum shouldn't csum padding.
 *		Alan Cox	: Protect against forwarding explosions with
 *				  older network drivers and IFF_ALLMULTI.
 *	Christer Weinigel	: Better rebuild header message.
 *             Andrew Morton    : 26Feb01: kill ether_setup() - use netdev_boot_setup().
 */
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/mm.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/ip.h>
#include <linux/netdevice.h>
#include <linux/nvmem-consumer.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/if_ether.h>
#include <linux/of_net.h>
#include <linux/pci.h>
#include <linux/property.h>
#include <net/dst.h>
#include <net/arp.h>
#include <net/sock.h>
#include <net/ipv6.h>
#include <net/ip.h>
#include <net/dsa.h>
#include <net/flow_dissector.h>
#include <net/gro.h>
#include <linux/uaccess.h>
#include <net/pkt_sched.h>

/**
 * eth_header - create the Ethernet header
 * @skb:	buffer to alter
 * @dev:	source device
 * @type:	Ethernet type field
 * @daddr: destination address (NULL leave destination address)
 * @saddr: source address (NULL use device source address)
 * @len:   packet length (<= skb->len)
 *
 *
 * Set the protocol type. For a packet of type ETH_P_802_3/2 we put the length
 * in here instead.
 */
int eth_header(struct sk_buff *skb, struct net_device *dev,
	       unsigned short type,
	       const void *daddr, const void *saddr, unsigned int len)
{
	struct ethhdr *eth = skb_push(skb, ETH_HLEN);

	if (type != ETH_P_802_3 && type != ETH_P_802_2)
		eth->h_proto = htons(type);
	else
		eth->h_proto = htons(len);

	/*
	 *      Set the source hardware address.
	 */

	if (!saddr)
		saddr = dev->dev_addr;
	memcpy(eth->h_source, saddr, ETH_ALEN);

	if (daddr) {
		memcpy(eth->h_dest, daddr, ETH_ALEN);
		return ETH_HLEN;
	}

	/*
	 *      Anyway, the loopback-device should never use this function...
	 */

	if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) {
		eth_zero_addr(eth->h_dest);
		return ETH_HLEN;
	}

	return -ETH_HLEN;
}
EXPORT_SYMBOL(eth_header);

/**
 * eth_get_headlen - determine the length of header for an ethernet frame
 * @dev: pointer to network device
 * @data: pointer to start of frame
 * @len: total length of frame
 *
 * Make a best effort attempt to pull the length for all of the headers for
 * a given frame in a linear buffer.
 */
u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len)
{
	const unsigned int flags = FLOW_DISSECTOR_F_PARSE_1ST_FRAG;
	const struct ethhdr *eth = (const struct ethhdr *)data;
	struct flow_keys_basic keys;

	/* this should never happen, but better safe than sorry */
	if (unlikely(len < sizeof(*eth)))
		return len;

	/* parse any remaining L2/L3 headers, check for L4 */
	if (!skb_flow_dissect_flow_keys_basic(dev_net(dev), NULL, &keys, data,
					      eth->h_proto, sizeof(*eth),
					      len, flags))
		return max_t(u32, keys.control.thoff, sizeof(*eth));

	/* parse for any L4 headers */
	return min_t(u32, __skb_get_poff(NULL, data, &keys, len), len);
}
EXPORT_SYMBOL(eth_get_headlen);

/**
 * eth_type_trans - determine the packet's protocol ID.
 * @skb: received socket data
 * @dev: receiving network device
 *
 * The rule here is that we
 * assume 802.3 if the type field is short enough to be a length.
 * This is normal practice and works for any 'now in use' protocol.
 */
__be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
{
	unsigned short _service_access_point;
	const unsigned short *sap;
	const struct ethhdr *eth;

	skb->dev = dev;
	skb_reset_mac_header(skb);

	eth = (struct ethhdr *)skb->data;
	skb_pull_inline(skb, ETH_HLEN);

	if (unlikely(!ether_addr_equal_64bits(eth->h_dest,
					      dev->dev_addr))) {
		if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) {
			if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast))
				skb->pkt_type = PACKET_BROADCAST;
			else
				skb->pkt_type = PACKET_MULTICAST;
		} else {
			skb->pkt_type = PACKET_OTHERHOST;
		}
	}

	/*
	 * Some variants of DSA tagging don't have an ethertype field
	 * at all, so we check here whether one of those tagging
	 * variants has been configured on the receiving interface,
	 * and if so, set skb->protocol without looking at the packet.
	 */
	if (unlikely(netdev_uses_dsa(dev)))
		return htons(ETH_P_XDSA);

	if (likely(eth_proto_is_802_3(eth->h_proto)))
		return eth->h_proto;

	/*
	 *      This is a magic hack to spot IPX packets. Older Novell breaks
	 *      the protocol design and runs IPX over 802.3 without an 802.2 LLC
	 *      layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This
	 *      won't work for fault tolerant netware but does for the rest.
	 */
	sap = skb_header_pointer(skb, 0, sizeof(*sap), &_service_access_point);
	if (sap && *sap == 0xFFFF)
		return htons(ETH_P_802_3);

	/*
	 *      Real 802.2 LLC
	 */
	return htons(ETH_P_802_2);
}
EXPORT_SYMBOL(eth_type_trans);

/**
 * eth_header_parse - extract hardware address from packet
 * @skb: packet to extract header from
 * @haddr: destination buffer
 */
int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr)
{
	const struct ethhdr *eth = eth_hdr(skb);
	memcpy(haddr, eth->h_source, ETH_ALEN);
	return ETH_ALEN;
}
EXPORT_SYMBOL(eth_header_parse);

/**
 * eth_header_cache - fill cache entry from neighbour
 * @neigh: source neighbour
 * @hh: destination cache entry
 * @type: Ethernet type field
 *
 * Create an Ethernet header template from the neighbour.
 */
int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type)
{
	struct ethhdr *eth;
	const struct net_device *dev = neigh->dev;

	eth = (struct ethhdr *)
	    (((u8 *) hh->hh_data) + (HH_DATA_OFF(sizeof(*eth))));

	if (type == htons(ETH_P_802_3))
		return -1;

	eth->h_proto = type;
	memcpy(eth->h_source, dev->dev_addr, ETH_ALEN);
	memcpy(eth->h_dest, neigh->ha, ETH_ALEN);

	/* Pairs with READ_ONCE() in neigh_resolve_output(),
	 * neigh_hh_output() and neigh_update_hhs().
	 */
	smp_store_release(&hh->hh_len, ETH_HLEN);

	return 0;
}
EXPORT_SYMBOL(eth_header_cache);

/**
 * eth_header_cache_update - update cache entry
 * @hh: destination cache entry
 * @dev: network device
 * @haddr: new hardware address
 *
 * Called by Address Resolution module to notify changes in address.
 */
void eth_header_cache_update(struct hh_cache *hh,
			     const struct net_device *dev,
			     const unsigned char *haddr)
{
	memcpy(((u8 *) hh->hh_data) + HH_DATA_OFF(sizeof(struct ethhdr)),
	       haddr, ETH_ALEN);
}
EXPORT_SYMBOL(eth_header_cache_update);

/**
 * eth_header_parse_protocol - extract protocol from L2 header
 * @skb: packet to extract protocol from
 */
__be16 eth_header_parse_protocol(const struct sk_buff *skb)
{
	const struct ethhdr *eth = eth_hdr(skb);

	return eth->h_proto;
}
EXPORT_SYMBOL(eth_header_parse_protocol);

/**
 * eth_prepare_mac_addr_change - prepare for mac change
 * @dev: network device
 * @p: socket address
 */
int eth_prepare_mac_addr_change(struct net_device *dev, void *p)
{
	struct sockaddr *addr = p;

	if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev))
		return -EBUSY;
	if (!is_valid_ether_addr(addr->sa_data))
		return -EADDRNOTAVAIL;
	return 0;
}
EXPORT_SYMBOL(eth_prepare_mac_addr_change);

/**
 * eth_commit_mac_addr_change - commit mac change
 * @dev: network device
 * @p: socket address
 */
void eth_commit_mac_addr_change(struct net_device *dev, void *p)
{
	struct sockaddr *addr = p;

	eth_hw_addr_set(dev, addr->sa_data);
}
EXPORT_SYMBOL(eth_commit_mac_addr_change);

/**
 * eth_mac_addr - set new Ethernet hardware address
 * @dev: network device
 * @p: socket address
 *
 * Change hardware address of device.
 *
 * This doesn't change hardware matching, so needs to be overridden
 * for most real devices.
 */
int eth_mac_addr(struct net_device *dev, void *p)
{
	int ret;

	ret = eth_prepare_mac_addr_change(dev, p);
	if (ret < 0)
		return ret;
	eth_commit_mac_addr_change(dev, p);
	return 0;
}
EXPORT_SYMBOL(eth_mac_addr);

int eth_validate_addr(struct net_device *dev)
{
	if (!is_valid_ether_addr(dev->dev_addr))
		return -EADDRNOTAVAIL;

	return 0;
}
EXPORT_SYMBOL(eth_validate_addr);

const struct header_ops eth_header_ops ____cacheline_aligned = {
	.create		= eth_header,
	.parse		= eth_header_parse,
	.cache		= eth_header_cache,
	.cache_update	= eth_header_cache_update,
	.parse_protocol	= eth_header_parse_protocol,
};

/**
 * ether_setup - setup Ethernet network device
 * @dev: network device
 *
 * Fill in the fields of the device structure with Ethernet-generic values.
 */
void ether_setup(struct net_device *dev)
{
	dev->header_ops		= &eth_header_ops;
	dev->type		= ARPHRD_ETHER;
	dev->hard_header_len 	= ETH_HLEN;
	dev->min_header_len	= ETH_HLEN;
	dev->mtu		= ETH_DATA_LEN;
	dev->min_mtu		= ETH_MIN_MTU;
	dev->max_mtu		= ETH_DATA_LEN;
	dev->addr_len		= ETH_ALEN;
	dev->tx_queue_len	= DEFAULT_TX_QUEUE_LEN;
	dev->flags		= IFF_BROADCAST|IFF_MULTICAST;
	dev->priv_flags		|= IFF_TX_SKB_SHARING;

	eth_broadcast_addr(dev->broadcast);

}
EXPORT_SYMBOL(ether_setup);

/**
 * alloc_etherdev_mqs - Allocates and sets up an Ethernet device
 * @sizeof_priv: Size of additional driver-private structure to be allocated
 *	for this Ethernet device
 * @txqs: The number of TX queues this device has.
 * @rxqs: The number of RX queues this device has.
 *
 * Fill in the fields of the device structure with Ethernet-generic
 * values. Basically does everything except registering the device.
 *
 * Constructs a new net device, complete with a private data area of
 * size (sizeof_priv).  A 32-byte (not bit) alignment is enforced for
 * this private data area.
 */

struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs,
				      unsigned int rxqs)
{
	return alloc_netdev_mqs(sizeof_priv, "eth%d", NET_NAME_UNKNOWN,
				ether_setup, txqs, rxqs);
}
EXPORT_SYMBOL(alloc_etherdev_mqs);

ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len)
{
	return scnprintf(buf, PAGE_SIZE, "%*phC\n", len, addr);
}
EXPORT_SYMBOL(sysfs_format_mac);

struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb)
{
	const struct packet_offload *ptype;
	unsigned int hlen, off_eth;
	struct sk_buff *pp = NULL;
	struct ethhdr *eh, *eh2;
	struct sk_buff *p;
	__be16 type;
	int flush = 1;

	off_eth = skb_gro_offset(skb);
	hlen = off_eth + sizeof(*eh);
	eh = skb_gro_header_fast(skb, off_eth);
	if (skb_gro_header_hard(skb, hlen)) {
		eh = skb_gro_header_slow(skb, hlen, off_eth);
		if (unlikely(!eh))
			goto out;
	}

	flush = 0;

	list_for_each_entry(p, head, list) {
		if (!NAPI_GRO_CB(p)->same_flow)
			continue;

		eh2 = (struct ethhdr *)(p->data + off_eth);
		if (compare_ether_header(eh, eh2)) {
			NAPI_GRO_CB(p)->same_flow = 0;
			continue;
		}
	}

	type = eh->h_proto;

	rcu_read_lock();
	ptype = gro_find_receive_by_type(type);
	if (ptype == NULL) {
		flush = 1;
		goto out_unlock;
	}

	skb_gro_pull(skb, sizeof(*eh));
	skb_gro_postpull_rcsum(skb, eh, sizeof(*eh));

	pp = indirect_call_gro_receive_inet(ptype->callbacks.gro_receive,
					    ipv6_gro_receive, inet_gro_receive,
					    head, skb);

out_unlock:
	rcu_read_unlock();
out:
	skb_gro_flush_final(skb, pp, flush);

	return pp;
}
EXPORT_SYMBOL(eth_gro_receive);

int eth_gro_complete(struct sk_buff *skb, int nhoff)
{
	struct ethhdr *eh = (struct ethhdr *)(skb->data + nhoff);
	__be16 type = eh->h_proto;
	struct packet_offload *ptype;
	int err = -ENOSYS;

	if (skb->encapsulation)
		skb_set_inner_mac_header(skb, nhoff);

	rcu_read_lock();
	ptype = gro_find_complete_by_type(type);
	if (ptype != NULL)
		err = INDIRECT_CALL_INET(ptype->callbacks.gro_complete,
					 ipv6_gro_complete, inet_gro_complete,
					 skb, nhoff + sizeof(*eh));

	rcu_read_unlock();
	return err;
}
EXPORT_SYMBOL(eth_gro_complete);

static struct packet_offload eth_packet_offload __read_mostly = {
	.type = cpu_to_be16(ETH_P_TEB),
	.priority = 10,
	.callbacks = {
		.gro_receive = eth_gro_receive,
		.gro_complete = eth_gro_complete,
	},
};

static int __init eth_offload_init(void)
{
	dev_add_offload(&eth_packet_offload);

	return 0;
}

fs_initcall(eth_offload_init);

unsigned char * __weak arch_get_platform_mac_address(void)
{
	return NULL;
}

int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr)
{
	unsigned char *addr;
	int ret;

	ret = of_get_mac_address(dev->of_node, mac_addr);
	if (!ret)
		return 0;

	addr = arch_get_platform_mac_address();
	if (!addr)
		return -ENODEV;

	ether_addr_copy(mac_addr, addr);

	return 0;
}
EXPORT_SYMBOL(eth_platform_get_mac_address);

/**
 * nvmem_get_mac_address - Obtain the MAC address from an nvmem cell named
 * 'mac-address' associated with given device.
 *
 * @dev:	Device with which the mac-address cell is associated.
 * @addrbuf:	Buffer to which the MAC address will be copied on success.
 *
 * Returns 0 on success or a negative error number on failure.
 */
int nvmem_get_mac_address(struct device *dev, void *addrbuf)
{
	struct nvmem_cell *cell;
	const void *mac;
	size_t len;

	cell = nvmem_cell_get(dev, "mac-address");
	if (IS_ERR(cell))
		return PTR_ERR(cell);

	mac = nvmem_cell_read(cell, &len);
	nvmem_cell_put(cell);

	if (IS_ERR(mac))
		return PTR_ERR(mac);

	if (len != ETH_ALEN || !is_valid_ether_addr(mac)) {
		kfree(mac);
		return -EINVAL;
	}

	ether_addr_copy(addrbuf, mac);
	kfree(mac);

	return 0;
}
EXPORT_SYMBOL(nvmem_get_mac_address);

static void *fwnode_get_mac_addr(struct fwnode_handle *fwnode,
				 const char *name, char *addr,
				 int alen)
{
	int ret = fwnode_property_read_u8_array(fwnode, name, addr, alen);

	if (ret == 0 && alen == ETH_ALEN && is_valid_ether_addr(addr))
		return addr;
	return NULL;
}

/**
 * fwnode_get_mac_address - Get the MAC from the firmware node
 * @fwnode:	Pointer to the firmware node
 * @addr:	Address of buffer to store the MAC in
 * @alen:	Length of the buffer pointed to by addr, should be ETH_ALEN
 *
 * Search the firmware node for the best MAC address to use.  'mac-address' is
 * checked first, because that is supposed to contain to "most recent" MAC
 * address. If that isn't set, then 'local-mac-address' is checked next,
 * because that is the default address.  If that isn't set, then the obsolete
 * 'address' is checked, just in case we're using an old device tree.
 *
 * Note that the 'address' property is supposed to contain a virtual address of
 * the register set, but some DTS files have redefined that property to be the
 * MAC address.
 *
 * All-zero MAC addresses are rejected, because those could be properties that
 * exist in the firmware tables, but were not updated by the firmware.  For
 * example, the DTS could define 'mac-address' and 'local-mac-address', with
 * zero MAC addresses.  Some older U-Boots only initialized 'local-mac-address'.
 * In this case, the real MAC is in 'local-mac-address', and 'mac-address'
 * exists but is all zeros.
 */
void *fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr, int alen)
{
	char *res;

	res = fwnode_get_mac_addr(fwnode, "mac-address", addr, alen);
	if (res)
		return res;

	res = fwnode_get_mac_addr(fwnode, "local-mac-address", addr, alen);
	if (res)
		return res;

	return fwnode_get_mac_addr(fwnode, "address", addr, alen);
}
EXPORT_SYMBOL(fwnode_get_mac_address);

/**
 * device_get_mac_address - Get the MAC for a given device
 * @dev:	Pointer to the device
 * @addr:	Address of buffer to store the MAC in
 * @alen:	Length of the buffer pointed to by addr, should be ETH_ALEN
 */
void *device_get_mac_address(struct device *dev, char *addr, int alen)
{
	return fwnode_get_mac_address(dev_fwnode(dev), addr, alen);
}
EXPORT_SYMBOL(device_get_mac_address);