xref: /kernel/linux/linux-5.10/net/ipv6/ip6_offload.c (revision 8c2ecf20)
1// SPDX-License-Identifier: GPL-2.0-or-later
2/*
3 *	IPV6 GSO/GRO offload support
4 *	Linux INET6 implementation
5 */
6
7#include <linux/kernel.h>
8#include <linux/socket.h>
9#include <linux/netdevice.h>
10#include <linux/skbuff.h>
11#include <linux/printk.h>
12
13#include <net/protocol.h>
14#include <net/ipv6.h>
15#include <net/inet_common.h>
16#include <net/tcp.h>
17#include <net/udp.h>
18
19#include "ip6_offload.h"
20
21/* All GRO functions are always builtin, except UDP over ipv6, which lays in
22 * ipv6 module, as it depends on UDPv6 lookup function, so we need special care
23 * when ipv6 is built as a module
24 */
25#if IS_BUILTIN(CONFIG_IPV6)
26#define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__)
27#else
28#define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__)
29#endif
30
31#define indirect_call_gro_receive_l4(f2, f1, cb, head, skb)	\
32({								\
33	unlikely(gro_recursion_inc_test(skb)) ?			\
34		NAPI_GRO_CB(skb)->flush |= 1, NULL :		\
35		INDIRECT_CALL_L4(cb, f2, f1, head, skb);	\
36})
37
38static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto)
39{
40	const struct net_offload *ops = NULL;
41
42	for (;;) {
43		struct ipv6_opt_hdr *opth;
44		int len;
45
46		if (proto != NEXTHDR_HOP) {
47			ops = rcu_dereference(inet6_offloads[proto]);
48
49			if (unlikely(!ops))
50				break;
51
52			if (!(ops->flags & INET6_PROTO_GSO_EXTHDR))
53				break;
54		}
55
56		if (unlikely(!pskb_may_pull(skb, 8)))
57			break;
58
59		opth = (void *)skb->data;
60		len = ipv6_optlen(opth);
61
62		if (unlikely(!pskb_may_pull(skb, len)))
63			break;
64
65		opth = (void *)skb->data;
66		proto = opth->nexthdr;
67		__skb_pull(skb, len);
68	}
69
70	return proto;
71}
72
73static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
74	netdev_features_t features)
75{
76	struct sk_buff *segs = ERR_PTR(-EINVAL);
77	struct ipv6hdr *ipv6h;
78	const struct net_offload *ops;
79	int proto;
80	struct frag_hdr *fptr;
81	unsigned int payload_len;
82	u8 *prevhdr;
83	int offset = 0;
84	bool encap, udpfrag;
85	int nhoff;
86	bool gso_partial;
87
88	skb_reset_network_header(skb);
89	nhoff = skb_network_header(skb) - skb_mac_header(skb);
90	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
91		goto out;
92
93	encap = SKB_GSO_CB(skb)->encap_level > 0;
94	if (encap)
95		features &= skb->dev->hw_enc_features;
96	SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h);
97
98	ipv6h = ipv6_hdr(skb);
99	__skb_pull(skb, sizeof(*ipv6h));
100	segs = ERR_PTR(-EPROTONOSUPPORT);
101
102	proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
103
104	if (skb->encapsulation &&
105	    skb_shinfo(skb)->gso_type & (SKB_GSO_IPXIP4 | SKB_GSO_IPXIP6))
106		udpfrag = proto == IPPROTO_UDP && encap &&
107			  (skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
108	else
109		udpfrag = proto == IPPROTO_UDP && !skb->encapsulation &&
110			  (skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
111
112	ops = rcu_dereference(inet6_offloads[proto]);
113	if (likely(ops && ops->callbacks.gso_segment)) {
114		skb_reset_transport_header(skb);
115		segs = ops->callbacks.gso_segment(skb, features);
116		if (!segs)
117			skb->network_header = skb_mac_header(skb) + nhoff - skb->head;
118	}
119
120	if (IS_ERR_OR_NULL(segs))
121		goto out;
122
123	gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
124
125	for (skb = segs; skb; skb = skb->next) {
126		ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
127		if (gso_partial && skb_is_gso(skb))
128			payload_len = skb_shinfo(skb)->gso_size +
129				      SKB_GSO_CB(skb)->data_offset +
130				      skb->head - (unsigned char *)(ipv6h + 1);
131		else
132			payload_len = skb->len - nhoff - sizeof(*ipv6h);
133		ipv6h->payload_len = htons(payload_len);
134		skb->network_header = (u8 *)ipv6h - skb->head;
135		skb_reset_mac_len(skb);
136
137		if (udpfrag) {
138			int err = ip6_find_1stfragopt(skb, &prevhdr);
139			if (err < 0) {
140				kfree_skb_list(segs);
141				return ERR_PTR(err);
142			}
143			fptr = (struct frag_hdr *)((u8 *)ipv6h + err);
144			fptr->frag_off = htons(offset);
145			if (skb->next)
146				fptr->frag_off |= htons(IP6_MF);
147			offset += (ntohs(ipv6h->payload_len) -
148				   sizeof(struct frag_hdr));
149		}
150		if (encap)
151			skb_reset_inner_headers(skb);
152	}
153
154out:
155	return segs;
156}
157
158/* Return the total length of all the extension hdrs, following the same
159 * logic in ipv6_gso_pull_exthdrs() when parsing ext-hdrs.
160 */
161static int ipv6_exthdrs_len(struct ipv6hdr *iph,
162			    const struct net_offload **opps)
163{
164	struct ipv6_opt_hdr *opth = (void *)iph;
165	int len = 0, proto, optlen = sizeof(*iph);
166
167	proto = iph->nexthdr;
168	for (;;) {
169		if (proto != NEXTHDR_HOP) {
170			*opps = rcu_dereference(inet6_offloads[proto]);
171			if (unlikely(!(*opps)))
172				break;
173			if (!((*opps)->flags & INET6_PROTO_GSO_EXTHDR))
174				break;
175		}
176		opth = (void *)opth + optlen;
177		optlen = ipv6_optlen(opth);
178		len += optlen;
179		proto = opth->nexthdr;
180	}
181	return len;
182}
183
184INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
185							 struct sk_buff *skb)
186{
187	const struct net_offload *ops;
188	struct sk_buff *pp = NULL;
189	struct sk_buff *p;
190	struct ipv6hdr *iph;
191	unsigned int nlen;
192	unsigned int hlen;
193	unsigned int off;
194	u16 flush = 1;
195	int proto;
196
197	off = skb_gro_offset(skb);
198	hlen = off + sizeof(*iph);
199	iph = skb_gro_header_fast(skb, off);
200	if (skb_gro_header_hard(skb, hlen)) {
201		iph = skb_gro_header_slow(skb, hlen, off);
202		if (unlikely(!iph))
203			goto out;
204	}
205
206	skb_set_network_header(skb, off);
207	skb_gro_pull(skb, sizeof(*iph));
208	skb_set_transport_header(skb, skb_gro_offset(skb));
209
210	flush += ntohs(iph->payload_len) != skb_gro_len(skb);
211
212	rcu_read_lock();
213	proto = iph->nexthdr;
214	ops = rcu_dereference(inet6_offloads[proto]);
215	if (!ops || !ops->callbacks.gro_receive) {
216		__pskb_pull(skb, skb_gro_offset(skb));
217		skb_gro_frag0_invalidate(skb);
218		proto = ipv6_gso_pull_exthdrs(skb, proto);
219		skb_gro_pull(skb, -skb_transport_offset(skb));
220		skb_reset_transport_header(skb);
221		__skb_push(skb, skb_gro_offset(skb));
222
223		ops = rcu_dereference(inet6_offloads[proto]);
224		if (!ops || !ops->callbacks.gro_receive)
225			goto out_unlock;
226
227		iph = ipv6_hdr(skb);
228	}
229
230	NAPI_GRO_CB(skb)->proto = proto;
231
232	flush--;
233	nlen = skb_network_header_len(skb);
234
235	list_for_each_entry(p, head, list) {
236		const struct ipv6hdr *iph2;
237		__be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */
238
239		if (!NAPI_GRO_CB(p)->same_flow)
240			continue;
241
242		iph2 = (struct ipv6hdr *)(p->data + off);
243		first_word = *(__be32 *)iph ^ *(__be32 *)iph2;
244
245		/* All fields must match except length and Traffic Class.
246		 * XXX skbs on the gro_list have all been parsed and pulled
247		 * already so we don't need to compare nlen
248		 * (nlen != (sizeof(*iph2) + ipv6_exthdrs_len(iph2, &ops)))
249		 * memcmp() alone below is sufficient, right?
250		 */
251		 if ((first_word & htonl(0xF00FFFFF)) ||
252		    !ipv6_addr_equal(&iph->saddr, &iph2->saddr) ||
253		    !ipv6_addr_equal(&iph->daddr, &iph2->daddr) ||
254		    *(u16 *)&iph->nexthdr != *(u16 *)&iph2->nexthdr) {
255not_same_flow:
256			NAPI_GRO_CB(p)->same_flow = 0;
257			continue;
258		}
259		if (unlikely(nlen > sizeof(struct ipv6hdr))) {
260			if (memcmp(iph + 1, iph2 + 1,
261				   nlen - sizeof(struct ipv6hdr)))
262				goto not_same_flow;
263		}
264		/* flush if Traffic Class fields are different */
265		NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000));
266		NAPI_GRO_CB(p)->flush |= flush;
267
268		/* If the previous IP ID value was based on an atomic
269		 * datagram we can overwrite the value and ignore it.
270		 */
271		if (NAPI_GRO_CB(skb)->is_atomic)
272			NAPI_GRO_CB(p)->flush_id = 0;
273	}
274
275	NAPI_GRO_CB(skb)->is_atomic = true;
276	NAPI_GRO_CB(skb)->flush |= flush;
277
278	skb_gro_postpull_rcsum(skb, iph, nlen);
279
280	pp = indirect_call_gro_receive_l4(tcp6_gro_receive, udp6_gro_receive,
281					 ops->callbacks.gro_receive, head, skb);
282
283out_unlock:
284	rcu_read_unlock();
285
286out:
287	skb_gro_flush_final(skb, pp, flush);
288
289	return pp;
290}
291
292static struct sk_buff *sit_ip6ip6_gro_receive(struct list_head *head,
293					      struct sk_buff *skb)
294{
295	/* Common GRO receive for SIT and IP6IP6 */
296
297	if (NAPI_GRO_CB(skb)->encap_mark) {
298		NAPI_GRO_CB(skb)->flush = 1;
299		return NULL;
300	}
301
302	NAPI_GRO_CB(skb)->encap_mark = 1;
303
304	return ipv6_gro_receive(head, skb);
305}
306
307static struct sk_buff *ip4ip6_gro_receive(struct list_head *head,
308					  struct sk_buff *skb)
309{
310	/* Common GRO receive for SIT and IP6IP6 */
311
312	if (NAPI_GRO_CB(skb)->encap_mark) {
313		NAPI_GRO_CB(skb)->flush = 1;
314		return NULL;
315	}
316
317	NAPI_GRO_CB(skb)->encap_mark = 1;
318
319	return inet_gro_receive(head, skb);
320}
321
322INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
323{
324	const struct net_offload *ops;
325	struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff);
326	int err = -ENOSYS;
327
328	if (skb->encapsulation) {
329		skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6));
330		skb_set_inner_network_header(skb, nhoff);
331	}
332
333	iph->payload_len = htons(skb->len - nhoff - sizeof(*iph));
334
335	rcu_read_lock();
336
337	nhoff += sizeof(*iph) + ipv6_exthdrs_len(iph, &ops);
338	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
339		goto out_unlock;
340
341	err = INDIRECT_CALL_L4(ops->callbacks.gro_complete, tcp6_gro_complete,
342			       udp6_gro_complete, skb, nhoff);
343
344out_unlock:
345	rcu_read_unlock();
346
347	return err;
348}
349
350static int sit_gro_complete(struct sk_buff *skb, int nhoff)
351{
352	skb->encapsulation = 1;
353	skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4;
354	return ipv6_gro_complete(skb, nhoff);
355}
356
357static int ip6ip6_gro_complete(struct sk_buff *skb, int nhoff)
358{
359	skb->encapsulation = 1;
360	skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6;
361	return ipv6_gro_complete(skb, nhoff);
362}
363
364static int ip4ip6_gro_complete(struct sk_buff *skb, int nhoff)
365{
366	skb->encapsulation = 1;
367	skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6;
368	return inet_gro_complete(skb, nhoff);
369}
370
371static struct packet_offload ipv6_packet_offload __read_mostly = {
372	.type = cpu_to_be16(ETH_P_IPV6),
373	.callbacks = {
374		.gso_segment = ipv6_gso_segment,
375		.gro_receive = ipv6_gro_receive,
376		.gro_complete = ipv6_gro_complete,
377	},
378};
379
380static struct sk_buff *sit_gso_segment(struct sk_buff *skb,
381				       netdev_features_t features)
382{
383	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP4))
384		return ERR_PTR(-EINVAL);
385
386	return ipv6_gso_segment(skb, features);
387}
388
389static struct sk_buff *ip4ip6_gso_segment(struct sk_buff *skb,
390					  netdev_features_t features)
391{
392	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP6))
393		return ERR_PTR(-EINVAL);
394
395	return inet_gso_segment(skb, features);
396}
397
398static struct sk_buff *ip6ip6_gso_segment(struct sk_buff *skb,
399					  netdev_features_t features)
400{
401	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP6))
402		return ERR_PTR(-EINVAL);
403
404	return ipv6_gso_segment(skb, features);
405}
406
407static const struct net_offload sit_offload = {
408	.callbacks = {
409		.gso_segment	= sit_gso_segment,
410		.gro_receive    = sit_ip6ip6_gro_receive,
411		.gro_complete   = sit_gro_complete,
412	},
413};
414
415static const struct net_offload ip4ip6_offload = {
416	.callbacks = {
417		.gso_segment	= ip4ip6_gso_segment,
418		.gro_receive    = ip4ip6_gro_receive,
419		.gro_complete   = ip4ip6_gro_complete,
420	},
421};
422
423static const struct net_offload ip6ip6_offload = {
424	.callbacks = {
425		.gso_segment	= ip6ip6_gso_segment,
426		.gro_receive    = sit_ip6ip6_gro_receive,
427		.gro_complete   = ip6ip6_gro_complete,
428	},
429};
430static int __init ipv6_offload_init(void)
431{
432
433	if (tcpv6_offload_init() < 0)
434		pr_crit("%s: Cannot add TCP protocol offload\n", __func__);
435	if (ipv6_exthdrs_offload_init() < 0)
436		pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__);
437
438	dev_add_offload(&ipv6_packet_offload);
439
440	inet_add_offload(&sit_offload, IPPROTO_IPV6);
441	inet6_add_offload(&ip6ip6_offload, IPPROTO_IPV6);
442	inet6_add_offload(&ip4ip6_offload, IPPROTO_IPIP);
443
444	return 0;
445}
446
447fs_initcall(ipv6_offload_init);
448