xref: /kernel/linux/linux-5.10/net/ethernet/eth.c (revision 8c2ecf20) 
1// SPDX-License-Identifier: GPL-2.0-or-later
2/*
3 * INET		An implementation of the TCP/IP protocol suite for the LINUX
4 *		operating system.  INET is implemented using the  BSD Socket
5 *		interface as the means of communication with the user level.
6 *
7 *		Ethernet-type device handling.
8 *
9 * Version:	@(#)eth.c	1.0.7	05/25/93
10 *
11 * Authors:	Ross Biro
12 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
13 *		Mark Evans, <evansmp@uhura.aston.ac.uk>
14 *		Florian  La Roche, <rzsfl@rz.uni-sb.de>
15 *		Alan Cox, <gw4pts@gw4pts.ampr.org>
16 *
17 * Fixes:
18 *		Mr Linux	: Arp problems
19 *		Alan Cox	: Generic queue tidyup (very tiny here)
20 *		Alan Cox	: eth_header ntohs should be htons
21 *		Alan Cox	: eth_rebuild_header missing an htons and
22 *				  minor other things.
23 *		Tegge		: Arp bug fixes.
24 *		Florian		: Removed many unnecessary functions, code cleanup
25 *				  and changes for new arp and skbuff.
26 *		Alan Cox	: Redid header building to reflect new format.
27 *		Alan Cox	: ARP only when compiled with CONFIG_INET
28 *		Greg Page	: 802.2 and SNAP stuff.
29 *		Alan Cox	: MAC layer pointers/new format.
30 *		Paul Gortmaker	: eth_copy_and_sum shouldn't csum padding.
31 *		Alan Cox	: Protect against forwarding explosions with
32 *				  older network drivers and IFF_ALLMULTI.
33 *	Christer Weinigel	: Better rebuild header message.
34 *             Andrew Morton    : 26Feb01: kill ether_setup() - use netdev_boot_setup().
35 */
36#include <linux/module.h>
37#include <linux/types.h>
38#include <linux/kernel.h>
39#include <linux/string.h>
40#include <linux/mm.h>
41#include <linux/socket.h>
42#include <linux/in.h>
43#include <linux/inet.h>
44#include <linux/ip.h>
45#include <linux/netdevice.h>
46#include <linux/nvmem-consumer.h>
47#include <linux/etherdevice.h>
48#include <linux/skbuff.h>
49#include <linux/errno.h>
50#include <linux/init.h>
51#include <linux/if_ether.h>
52#include <linux/of_net.h>
53#include <linux/pci.h>
54#include <net/dst.h>
55#include <net/arp.h>
56#include <net/sock.h>
57#include <net/ipv6.h>
58#include <net/ip.h>
59#include <net/dsa.h>
60#include <net/flow_dissector.h>
61#include <linux/uaccess.h>
62#include <net/pkt_sched.h>
63
64__setup("ether=", netdev_boot_setup);
65
66/**
67 * eth_header - create the Ethernet header
68 * @skb:	buffer to alter
69 * @dev:	source device
70 * @type:	Ethernet type field
71 * @daddr: destination address (NULL leave destination address)
72 * @saddr: source address (NULL use device source address)
73 * @len:   packet length (<= skb->len)
74 *
75 *
76 * Set the protocol type. For a packet of type ETH_P_802_3/2 we put the length
77 * in here instead.
78 */
79int eth_header(struct sk_buff *skb, struct net_device *dev,
80	       unsigned short type,
81	       const void *daddr, const void *saddr, unsigned int len)
82{
83	struct ethhdr *eth = skb_push(skb, ETH_HLEN);
84
85	if (type != ETH_P_802_3 && type != ETH_P_802_2)
86		eth->h_proto = htons(type);
87	else
88		eth->h_proto = htons(len);
89
90	/*
91	 *      Set the source hardware address.
92	 */
93
94	if (!saddr)
95		saddr = dev->dev_addr;
96	memcpy(eth->h_source, saddr, ETH_ALEN);
97
98	if (daddr) {
99		memcpy(eth->h_dest, daddr, ETH_ALEN);
100		return ETH_HLEN;
101	}
102
103	/*
104	 *      Anyway, the loopback-device should never use this function...
105	 */
106
107	if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) {
108		eth_zero_addr(eth->h_dest);
109		return ETH_HLEN;
110	}
111
112	return -ETH_HLEN;
113}
114EXPORT_SYMBOL(eth_header);
115
116/**
117 * eth_get_headlen - determine the length of header for an ethernet frame
118 * @dev: pointer to network device
119 * @data: pointer to start of frame
120 * @len: total length of frame
121 *
122 * Make a best effort attempt to pull the length for all of the headers for
123 * a given frame in a linear buffer.
124 */
125u32 eth_get_headlen(const struct net_device *dev, void *data, unsigned int len)
126{
127	const unsigned int flags = FLOW_DISSECTOR_F_PARSE_1ST_FRAG;
128	const struct ethhdr *eth = (const struct ethhdr *)data;
129	struct flow_keys_basic keys;
130
131	/* this should never happen, but better safe than sorry */
132	if (unlikely(len < sizeof(*eth)))
133		return len;
134
135	/* parse any remaining L2/L3 headers, check for L4 */
136	if (!skb_flow_dissect_flow_keys_basic(dev_net(dev), NULL, &keys, data,
137					      eth->h_proto, sizeof(*eth),
138					      len, flags))
139		return max_t(u32, keys.control.thoff, sizeof(*eth));
140
141	/* parse for any L4 headers */
142	return min_t(u32, __skb_get_poff(NULL, data, &keys, len), len);
143}
144EXPORT_SYMBOL(eth_get_headlen);
145
146/**
147 * eth_type_trans - determine the packet's protocol ID.
148 * @skb: received socket data
149 * @dev: receiving network device
150 *
151 * The rule here is that we
152 * assume 802.3 if the type field is short enough to be a length.
153 * This is normal practice and works for any 'now in use' protocol.
154 */
155__be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev)
156{
157	unsigned short _service_access_point;
158	const unsigned short *sap;
159	const struct ethhdr *eth;
160
161	skb->dev = dev;
162	skb_reset_mac_header(skb);
163
164	eth = (struct ethhdr *)skb->data;
165	skb_pull_inline(skb, ETH_HLEN);
166
167	if (unlikely(!ether_addr_equal_64bits(eth->h_dest,
168					      dev->dev_addr))) {
169		if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) {
170			if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast))
171				skb->pkt_type = PACKET_BROADCAST;
172			else
173				skb->pkt_type = PACKET_MULTICAST;
174		} else {
175			skb->pkt_type = PACKET_OTHERHOST;
176		}
177	}
178
179	/*
180	 * Some variants of DSA tagging don't have an ethertype field
181	 * at all, so we check here whether one of those tagging
182	 * variants has been configured on the receiving interface,
183	 * and if so, set skb->protocol without looking at the packet.
184	 * The DSA tagging protocol may be able to decode some but not all
185	 * traffic (for example only for management). In that case give it the
186	 * option to filter the packets from which it can decode source port
187	 * information.
188	 */
189	if (unlikely(netdev_uses_dsa(dev)) && dsa_can_decode(skb, dev))
190		return htons(ETH_P_XDSA);
191
192	if (likely(eth_proto_is_802_3(eth->h_proto)))
193		return eth->h_proto;
194
195	/*
196	 *      This is a magic hack to spot IPX packets. Older Novell breaks
197	 *      the protocol design and runs IPX over 802.3 without an 802.2 LLC
198	 *      layer. We look for FFFF which isn't a used 802.2 SSAP/DSAP. This
199	 *      won't work for fault tolerant netware but does for the rest.
200	 */
201	sap = skb_header_pointer(skb, 0, sizeof(*sap), &_service_access_point);
202	if (sap && *sap == 0xFFFF)
203		return htons(ETH_P_802_3);
204
205	/*
206	 *      Real 802.2 LLC
207	 */
208	return htons(ETH_P_802_2);
209}
210EXPORT_SYMBOL(eth_type_trans);
211
212/**
213 * eth_header_parse - extract hardware address from packet
214 * @skb: packet to extract header from
215 * @haddr: destination buffer
216 */
217int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr)
218{
219	const struct ethhdr *eth = eth_hdr(skb);
220	memcpy(haddr, eth->h_source, ETH_ALEN);
221	return ETH_ALEN;
222}
223EXPORT_SYMBOL(eth_header_parse);
224
225/**
226 * eth_header_cache - fill cache entry from neighbour
227 * @neigh: source neighbour
228 * @hh: destination cache entry
229 * @type: Ethernet type field
230 *
231 * Create an Ethernet header template from the neighbour.
232 */
233int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type)
234{
235	struct ethhdr *eth;
236	const struct net_device *dev = neigh->dev;
237
238	eth = (struct ethhdr *)
239	    (((u8 *) hh->hh_data) + (HH_DATA_OFF(sizeof(*eth))));
240
241	if (type == htons(ETH_P_802_3))
242		return -1;
243
244	eth->h_proto = type;
245	memcpy(eth->h_source, dev->dev_addr, ETH_ALEN);
246	memcpy(eth->h_dest, neigh->ha, ETH_ALEN);
247
248	/* Pairs with READ_ONCE() in neigh_resolve_output(),
249	 * neigh_hh_output() and neigh_update_hhs().
250	 */
251	smp_store_release(&hh->hh_len, ETH_HLEN);
252
253	return 0;
254}
255EXPORT_SYMBOL(eth_header_cache);
256
257/**
258 * eth_header_cache_update - update cache entry
259 * @hh: destination cache entry
260 * @dev: network device
261 * @haddr: new hardware address
262 *
263 * Called by Address Resolution module to notify changes in address.
264 */
265void eth_header_cache_update(struct hh_cache *hh,
266			     const struct net_device *dev,
267			     const unsigned char *haddr)
268{
269	memcpy(((u8 *) hh->hh_data) + HH_DATA_OFF(sizeof(struct ethhdr)),
270	       haddr, ETH_ALEN);
271}
272EXPORT_SYMBOL(eth_header_cache_update);
273
274/**
275 * eth_header_parser_protocol - extract protocol from L2 header
276 * @skb: packet to extract protocol from
277 */
278__be16 eth_header_parse_protocol(const struct sk_buff *skb)
279{
280	const struct ethhdr *eth = eth_hdr(skb);
281
282	return eth->h_proto;
283}
284EXPORT_SYMBOL(eth_header_parse_protocol);
285
286/**
287 * eth_prepare_mac_addr_change - prepare for mac change
288 * @dev: network device
289 * @p: socket address
290 */
291int eth_prepare_mac_addr_change(struct net_device *dev, void *p)
292{
293	struct sockaddr *addr = p;
294
295	if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev))
296		return -EBUSY;
297	if (!is_valid_ether_addr(addr->sa_data))
298		return -EADDRNOTAVAIL;
299	return 0;
300}
301EXPORT_SYMBOL(eth_prepare_mac_addr_change);
302
303/**
304 * eth_commit_mac_addr_change - commit mac change
305 * @dev: network device
306 * @p: socket address
307 */
308void eth_commit_mac_addr_change(struct net_device *dev, void *p)
309{
310	struct sockaddr *addr = p;
311
312	memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
313}
314EXPORT_SYMBOL(eth_commit_mac_addr_change);
315
316/**
317 * eth_mac_addr - set new Ethernet hardware address
318 * @dev: network device
319 * @p: socket address
320 *
321 * Change hardware address of device.
322 *
323 * This doesn't change hardware matching, so needs to be overridden
324 * for most real devices.
325 */
326int eth_mac_addr(struct net_device *dev, void *p)
327{
328	int ret;
329
330	ret = eth_prepare_mac_addr_change(dev, p);
331	if (ret < 0)
332		return ret;
333	eth_commit_mac_addr_change(dev, p);
334	return 0;
335}
336EXPORT_SYMBOL(eth_mac_addr);
337
338int eth_validate_addr(struct net_device *dev)
339{
340	if (!is_valid_ether_addr(dev->dev_addr))
341		return -EADDRNOTAVAIL;
342
343	return 0;
344}
345EXPORT_SYMBOL(eth_validate_addr);
346
347const struct header_ops eth_header_ops ____cacheline_aligned = {
348	.create		= eth_header,
349	.parse		= eth_header_parse,
350	.cache		= eth_header_cache,
351	.cache_update	= eth_header_cache_update,
352	.parse_protocol	= eth_header_parse_protocol,
353};
354
355/**
356 * ether_setup - setup Ethernet network device
357 * @dev: network device
358 *
359 * Fill in the fields of the device structure with Ethernet-generic values.
360 */
361void ether_setup(struct net_device *dev)
362{
363	dev->header_ops		= &eth_header_ops;
364	dev->type		= ARPHRD_ETHER;
365	dev->hard_header_len 	= ETH_HLEN;
366	dev->min_header_len	= ETH_HLEN;
367	dev->mtu		= ETH_DATA_LEN;
368	dev->min_mtu		= ETH_MIN_MTU;
369	dev->max_mtu		= ETH_DATA_LEN;
370	dev->addr_len		= ETH_ALEN;
371	dev->tx_queue_len	= DEFAULT_TX_QUEUE_LEN;
372	dev->flags		= IFF_BROADCAST|IFF_MULTICAST;
373	dev->priv_flags		|= IFF_TX_SKB_SHARING;
374
375	eth_broadcast_addr(dev->broadcast);
376
377}
378EXPORT_SYMBOL(ether_setup);
379
380/**
381 * alloc_etherdev_mqs - Allocates and sets up an Ethernet device
382 * @sizeof_priv: Size of additional driver-private structure to be allocated
383 *	for this Ethernet device
384 * @txqs: The number of TX queues this device has.
385 * @rxqs: The number of RX queues this device has.
386 *
387 * Fill in the fields of the device structure with Ethernet-generic
388 * values. Basically does everything except registering the device.
389 *
390 * Constructs a new net device, complete with a private data area of
391 * size (sizeof_priv).  A 32-byte (not bit) alignment is enforced for
392 * this private data area.
393 */
394
395struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs,
396				      unsigned int rxqs)
397{
398	return alloc_netdev_mqs(sizeof_priv, "eth%d", NET_NAME_UNKNOWN,
399				ether_setup, txqs, rxqs);
400}
401EXPORT_SYMBOL(alloc_etherdev_mqs);
402
403ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len)
404{
405	return scnprintf(buf, PAGE_SIZE, "%*phC\n", len, addr);
406}
407EXPORT_SYMBOL(sysfs_format_mac);
408
409struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb)
410{
411	const struct packet_offload *ptype;
412	unsigned int hlen, off_eth;
413	struct sk_buff *pp = NULL;
414	struct ethhdr *eh, *eh2;
415	struct sk_buff *p;
416	__be16 type;
417	int flush = 1;
418
419	off_eth = skb_gro_offset(skb);
420	hlen = off_eth + sizeof(*eh);
421	eh = skb_gro_header_fast(skb, off_eth);
422	if (skb_gro_header_hard(skb, hlen)) {
423		eh = skb_gro_header_slow(skb, hlen, off_eth);
424		if (unlikely(!eh))
425			goto out;
426	}
427
428	flush = 0;
429
430	list_for_each_entry(p, head, list) {
431		if (!NAPI_GRO_CB(p)->same_flow)
432			continue;
433
434		eh2 = (struct ethhdr *)(p->data + off_eth);
435		if (compare_ether_header(eh, eh2)) {
436			NAPI_GRO_CB(p)->same_flow = 0;
437			continue;
438		}
439	}
440
441	type = eh->h_proto;
442
443	rcu_read_lock();
444	ptype = gro_find_receive_by_type(type);
445	if (ptype == NULL) {
446		flush = 1;
447		goto out_unlock;
448	}
449
450	skb_gro_pull(skb, sizeof(*eh));
451	skb_gro_postpull_rcsum(skb, eh, sizeof(*eh));
452	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
453
454out_unlock:
455	rcu_read_unlock();
456out:
457	skb_gro_flush_final(skb, pp, flush);
458
459	return pp;
460}
461EXPORT_SYMBOL(eth_gro_receive);
462
463int eth_gro_complete(struct sk_buff *skb, int nhoff)
464{
465	struct ethhdr *eh = (struct ethhdr *)(skb->data + nhoff);
466	__be16 type = eh->h_proto;
467	struct packet_offload *ptype;
468	int err = -ENOSYS;
469
470	if (skb->encapsulation)
471		skb_set_inner_mac_header(skb, nhoff);
472
473	rcu_read_lock();
474	ptype = gro_find_complete_by_type(type);
475	if (ptype != NULL)
476		err = ptype->callbacks.gro_complete(skb, nhoff +
477						    sizeof(struct ethhdr));
478
479	rcu_read_unlock();
480	return err;
481}
482EXPORT_SYMBOL(eth_gro_complete);
483
484static struct packet_offload eth_packet_offload __read_mostly = {
485	.type = cpu_to_be16(ETH_P_TEB),
486	.priority = 10,
487	.callbacks = {
488		.gro_receive = eth_gro_receive,
489		.gro_complete = eth_gro_complete,
490	},
491};
492
493static int __init eth_offload_init(void)
494{
495	dev_add_offload(&eth_packet_offload);
496
497	return 0;
498}
499
500fs_initcall(eth_offload_init);
501
502unsigned char * __weak arch_get_platform_mac_address(void)
503{
504	return NULL;
505}
506
507int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr)
508{
509	const unsigned char *addr = NULL;
510
511	if (dev->of_node)
512		addr = of_get_mac_address(dev->of_node);
513	if (IS_ERR_OR_NULL(addr))
514		addr = arch_get_platform_mac_address();
515
516	if (!addr)
517		return -ENODEV;
518
519	ether_addr_copy(mac_addr, addr);
520
521	return 0;
522}
523EXPORT_SYMBOL(eth_platform_get_mac_address);
524
525/**
526 * Obtain the MAC address from an nvmem cell named 'mac-address' associated
527 * with given device.
528 *
529 * @dev:	Device with which the mac-address cell is associated.
530 * @addrbuf:	Buffer to which the MAC address will be copied on success.
531 *
532 * Returns 0 on success or a negative error number on failure.
533 */
534int nvmem_get_mac_address(struct device *dev, void *addrbuf)
535{
536	struct nvmem_cell *cell;
537	const void *mac;
538	size_t len;
539
540	cell = nvmem_cell_get(dev, "mac-address");
541	if (IS_ERR(cell))
542		return PTR_ERR(cell);
543
544	mac = nvmem_cell_read(cell, &len);
545	nvmem_cell_put(cell);
546
547	if (IS_ERR(mac))
548		return PTR_ERR(mac);
549
550	if (len != ETH_ALEN || !is_valid_ether_addr(mac)) {
551		kfree(mac);
552		return -EINVAL;
553	}
554
555	ether_addr_copy(addrbuf, mac);
556	kfree(mac);
557
558	return 0;
559}
560EXPORT_SYMBOL(nvmem_get_mac_address);
561