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 #include <net/gro.h>
19 
20 #include "ip6_offload.h"
21 
22 /* All GRO functions are always builtin, except UDP over ipv6, which lays in
23  * ipv6 module, as it depends on UDPv6 lookup function, so we need special care
24  * when ipv6 is built as a module
25  */
26 #if IS_BUILTIN(CONFIG_IPV6)
27 #define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__)
28 #else
29 #define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__)
30 #endif
31 
32 #define indirect_call_gro_receive_l4(f2, f1, cb, head, skb)	\
33 ({								\
34 	unlikely(gro_recursion_inc_test(skb)) ?			\
35 		NAPI_GRO_CB(skb)->flush |= 1, NULL :		\
36 		INDIRECT_CALL_L4(cb, f2, f1, head, skb);	\
37 })
38 
ipv6_gso_pull_exthdrs(struct sk_buff * skb,int proto)39 static int ipv6_gso_pull_exthdrs(struct sk_buff *skb, int proto)
40 {
41 	const struct net_offload *ops = NULL;
42 
43 	for (;;) {
44 		struct ipv6_opt_hdr *opth;
45 		int len;
46 
47 		if (proto != NEXTHDR_HOP) {
48 			ops = rcu_dereference(inet6_offloads[proto]);
49 
50 			if (unlikely(!ops))
51 				break;
52 
53 			if (!(ops->flags & INET6_PROTO_GSO_EXTHDR))
54 				break;
55 		}
56 
57 		if (unlikely(!pskb_may_pull(skb, 8)))
58 			break;
59 
60 		opth = (void *)skb->data;
61 		len = ipv6_optlen(opth);
62 
63 		if (unlikely(!pskb_may_pull(skb, len)))
64 			break;
65 
66 		opth = (void *)skb->data;
67 		proto = opth->nexthdr;
68 		__skb_pull(skb, len);
69 	}
70 
71 	return proto;
72 }
73 
ipv6_gso_segment(struct sk_buff * skb,netdev_features_t features)74 static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
75 	netdev_features_t features)
76 {
77 	struct sk_buff *segs = ERR_PTR(-EINVAL);
78 	struct ipv6hdr *ipv6h;
79 	const struct net_offload *ops;
80 	int proto, err;
81 	struct frag_hdr *fptr;
82 	unsigned int payload_len;
83 	u8 *prevhdr;
84 	int offset = 0;
85 	bool encap, udpfrag;
86 	int nhoff;
87 	bool gso_partial;
88 
89 	skb_reset_network_header(skb);
90 	err = ipv6_hopopt_jumbo_remove(skb);
91 	if (err)
92 		return ERR_PTR(err);
93 	nhoff = skb_network_header(skb) - skb_mac_header(skb);
94 	if (unlikely(!pskb_may_pull(skb, sizeof(*ipv6h))))
95 		goto out;
96 
97 	encap = SKB_GSO_CB(skb)->encap_level > 0;
98 	if (encap)
99 		features &= skb->dev->hw_enc_features;
100 	SKB_GSO_CB(skb)->encap_level += sizeof(*ipv6h);
101 
102 	ipv6h = ipv6_hdr(skb);
103 	__skb_pull(skb, sizeof(*ipv6h));
104 	segs = ERR_PTR(-EPROTONOSUPPORT);
105 
106 	proto = ipv6_gso_pull_exthdrs(skb, ipv6h->nexthdr);
107 
108 	if (skb->encapsulation &&
109 	    skb_shinfo(skb)->gso_type & (SKB_GSO_IPXIP4 | SKB_GSO_IPXIP6))
110 		udpfrag = proto == IPPROTO_UDP && encap &&
111 			  (skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
112 	else
113 		udpfrag = proto == IPPROTO_UDP && !skb->encapsulation &&
114 			  (skb_shinfo(skb)->gso_type & SKB_GSO_UDP);
115 
116 	ops = rcu_dereference(inet6_offloads[proto]);
117 	if (likely(ops && ops->callbacks.gso_segment)) {
118 		skb_reset_transport_header(skb);
119 		segs = ops->callbacks.gso_segment(skb, features);
120 		if (!segs)
121 			skb->network_header = skb_mac_header(skb) + nhoff - skb->head;
122 	}
123 
124 	if (IS_ERR_OR_NULL(segs))
125 		goto out;
126 
127 	gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
128 
129 	for (skb = segs; skb; skb = skb->next) {
130 		ipv6h = (struct ipv6hdr *)(skb_mac_header(skb) + nhoff);
131 		if (gso_partial && skb_is_gso(skb))
132 			payload_len = skb_shinfo(skb)->gso_size +
133 				      SKB_GSO_CB(skb)->data_offset +
134 				      skb->head - (unsigned char *)(ipv6h + 1);
135 		else
136 			payload_len = skb->len - nhoff - sizeof(*ipv6h);
137 		ipv6h->payload_len = htons(payload_len);
138 		skb->network_header = (u8 *)ipv6h - skb->head;
139 		skb_reset_mac_len(skb);
140 
141 		if (udpfrag) {
142 			int err = ip6_find_1stfragopt(skb, &prevhdr);
143 			if (err < 0) {
144 				kfree_skb_list(segs);
145 				return ERR_PTR(err);
146 			}
147 			fptr = (struct frag_hdr *)((u8 *)ipv6h + err);
148 			fptr->frag_off = htons(offset);
149 			if (skb->next)
150 				fptr->frag_off |= htons(IP6_MF);
151 			offset += (ntohs(ipv6h->payload_len) -
152 				   sizeof(struct frag_hdr));
153 		}
154 		if (encap)
155 			skb_reset_inner_headers(skb);
156 	}
157 
158 out:
159 	return segs;
160 }
161 
162 /* Return the total length of all the extension hdrs, following the same
163  * logic in ipv6_gso_pull_exthdrs() when parsing ext-hdrs.
164  */
ipv6_exthdrs_len(struct ipv6hdr * iph,const struct net_offload ** opps)165 static int ipv6_exthdrs_len(struct ipv6hdr *iph,
166 			    const struct net_offload **opps)
167 {
168 	struct ipv6_opt_hdr *opth = (void *)iph;
169 	int len = 0, proto, optlen = sizeof(*iph);
170 
171 	proto = iph->nexthdr;
172 	for (;;) {
173 		if (proto != NEXTHDR_HOP) {
174 			*opps = rcu_dereference(inet6_offloads[proto]);
175 			if (unlikely(!(*opps)))
176 				break;
177 			if (!((*opps)->flags & INET6_PROTO_GSO_EXTHDR))
178 				break;
179 		}
180 		opth = (void *)opth + optlen;
181 		optlen = ipv6_optlen(opth);
182 		len += optlen;
183 		proto = opth->nexthdr;
184 	}
185 	return len;
186 }
187 
ipv6_gro_receive(struct list_head * head,struct sk_buff * skb)188 INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
189 							 struct sk_buff *skb)
190 {
191 	const struct net_offload *ops;
192 	struct sk_buff *pp = NULL;
193 	struct sk_buff *p;
194 	struct ipv6hdr *iph;
195 	unsigned int nlen;
196 	unsigned int hlen;
197 	unsigned int off;
198 	u16 flush = 1;
199 	int proto;
200 
201 	off = skb_gro_offset(skb);
202 	hlen = off + sizeof(*iph);
203 	iph = skb_gro_header(skb, hlen, off);
204 	if (unlikely(!iph))
205 		goto out;
206 
207 	skb_set_network_header(skb, off);
208 	skb_gro_pull(skb, sizeof(*iph));
209 	skb_set_transport_header(skb, skb_gro_offset(skb));
210 
211 	flush += ntohs(iph->payload_len) != skb_gro_len(skb);
212 
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;
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 		     iph->nexthdr != iph2->nexthdr) {
255 not_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 			(__force __be32)(iph->hop_limit ^ iph2->hop_limit));
267 		NAPI_GRO_CB(p)->flush |= flush;
268 
269 		/* If the previous IP ID value was based on an atomic
270 		 * datagram we can overwrite the value and ignore it.
271 		 */
272 		if (NAPI_GRO_CB(skb)->is_atomic)
273 			NAPI_GRO_CB(p)->flush_id = 0;
274 	}
275 
276 	NAPI_GRO_CB(skb)->is_atomic = true;
277 	NAPI_GRO_CB(skb)->flush |= flush;
278 
279 	skb_gro_postpull_rcsum(skb, iph, nlen);
280 
281 	pp = indirect_call_gro_receive_l4(tcp6_gro_receive, udp6_gro_receive,
282 					 ops->callbacks.gro_receive, head, skb);
283 
284 out:
285 	skb_gro_flush_final(skb, pp, flush);
286 
287 	return pp;
288 }
289 
sit_ip6ip6_gro_receive(struct list_head * head,struct sk_buff * skb)290 static struct sk_buff *sit_ip6ip6_gro_receive(struct list_head *head,
291 					      struct sk_buff *skb)
292 {
293 	/* Common GRO receive for SIT and IP6IP6 */
294 
295 	if (NAPI_GRO_CB(skb)->encap_mark) {
296 		NAPI_GRO_CB(skb)->flush = 1;
297 		return NULL;
298 	}
299 
300 	NAPI_GRO_CB(skb)->encap_mark = 1;
301 
302 	return ipv6_gro_receive(head, skb);
303 }
304 
ip4ip6_gro_receive(struct list_head * head,struct sk_buff * skb)305 static struct sk_buff *ip4ip6_gro_receive(struct list_head *head,
306 					  struct sk_buff *skb)
307 {
308 	/* Common GRO receive for SIT and IP6IP6 */
309 
310 	if (NAPI_GRO_CB(skb)->encap_mark) {
311 		NAPI_GRO_CB(skb)->flush = 1;
312 		return NULL;
313 	}
314 
315 	NAPI_GRO_CB(skb)->encap_mark = 1;
316 
317 	return inet_gro_receive(head, skb);
318 }
319 
ipv6_gro_complete(struct sk_buff * skb,int nhoff)320 INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
321 {
322 	const struct net_offload *ops;
323 	struct ipv6hdr *iph;
324 	int err = -ENOSYS;
325 	u32 payload_len;
326 
327 	if (skb->encapsulation) {
328 		skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6));
329 		skb_set_inner_network_header(skb, nhoff);
330 	}
331 
332 	payload_len = skb->len - nhoff - sizeof(*iph);
333 	if (unlikely(payload_len > IPV6_MAXPLEN)) {
334 		struct hop_jumbo_hdr *hop_jumbo;
335 		int hoplen = sizeof(*hop_jumbo);
336 
337 		/* Move network header left */
338 		memmove(skb_mac_header(skb) - hoplen, skb_mac_header(skb),
339 			skb->transport_header - skb->mac_header);
340 		skb->data -= hoplen;
341 		skb->len += hoplen;
342 		skb->mac_header -= hoplen;
343 		skb->network_header -= hoplen;
344 		iph = (struct ipv6hdr *)(skb->data + nhoff);
345 		hop_jumbo = (struct hop_jumbo_hdr *)(iph + 1);
346 
347 		/* Build hop-by-hop options */
348 		hop_jumbo->nexthdr = iph->nexthdr;
349 		hop_jumbo->hdrlen = 0;
350 		hop_jumbo->tlv_type = IPV6_TLV_JUMBO;
351 		hop_jumbo->tlv_len = 4;
352 		hop_jumbo->jumbo_payload_len = htonl(payload_len + hoplen);
353 
354 		iph->nexthdr = NEXTHDR_HOP;
355 		iph->payload_len = 0;
356 	} else {
357 		iph = (struct ipv6hdr *)(skb->data + nhoff);
358 		iph->payload_len = htons(payload_len);
359 	}
360 
361 	nhoff += sizeof(*iph) + ipv6_exthdrs_len(iph, &ops);
362 	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
363 		goto out;
364 
365 	err = INDIRECT_CALL_L4(ops->callbacks.gro_complete, tcp6_gro_complete,
366 			       udp6_gro_complete, skb, nhoff);
367 
368 out:
369 	return err;
370 }
371 
sit_gro_complete(struct sk_buff * skb,int nhoff)372 static int sit_gro_complete(struct sk_buff *skb, int nhoff)
373 {
374 	skb->encapsulation = 1;
375 	skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP4;
376 	return ipv6_gro_complete(skb, nhoff);
377 }
378 
ip6ip6_gro_complete(struct sk_buff * skb,int nhoff)379 static int ip6ip6_gro_complete(struct sk_buff *skb, int nhoff)
380 {
381 	skb->encapsulation = 1;
382 	skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6;
383 	return ipv6_gro_complete(skb, nhoff);
384 }
385 
ip4ip6_gro_complete(struct sk_buff * skb,int nhoff)386 static int ip4ip6_gro_complete(struct sk_buff *skb, int nhoff)
387 {
388 	skb->encapsulation = 1;
389 	skb_shinfo(skb)->gso_type |= SKB_GSO_IPXIP6;
390 	return inet_gro_complete(skb, nhoff);
391 }
392 
393 static struct packet_offload ipv6_packet_offload __read_mostly = {
394 	.type = cpu_to_be16(ETH_P_IPV6),
395 	.callbacks = {
396 		.gso_segment = ipv6_gso_segment,
397 		.gro_receive = ipv6_gro_receive,
398 		.gro_complete = ipv6_gro_complete,
399 	},
400 };
401 
sit_gso_segment(struct sk_buff * skb,netdev_features_t features)402 static struct sk_buff *sit_gso_segment(struct sk_buff *skb,
403 				       netdev_features_t features)
404 {
405 	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP4))
406 		return ERR_PTR(-EINVAL);
407 
408 	return ipv6_gso_segment(skb, features);
409 }
410 
ip4ip6_gso_segment(struct sk_buff * skb,netdev_features_t features)411 static struct sk_buff *ip4ip6_gso_segment(struct sk_buff *skb,
412 					  netdev_features_t features)
413 {
414 	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP6))
415 		return ERR_PTR(-EINVAL);
416 
417 	return inet_gso_segment(skb, features);
418 }
419 
ip6ip6_gso_segment(struct sk_buff * skb,netdev_features_t features)420 static struct sk_buff *ip6ip6_gso_segment(struct sk_buff *skb,
421 					  netdev_features_t features)
422 {
423 	if (!(skb_shinfo(skb)->gso_type & SKB_GSO_IPXIP6))
424 		return ERR_PTR(-EINVAL);
425 
426 	return ipv6_gso_segment(skb, features);
427 }
428 
429 static const struct net_offload sit_offload = {
430 	.callbacks = {
431 		.gso_segment	= sit_gso_segment,
432 		.gro_receive    = sit_ip6ip6_gro_receive,
433 		.gro_complete   = sit_gro_complete,
434 	},
435 };
436 
437 static const struct net_offload ip4ip6_offload = {
438 	.callbacks = {
439 		.gso_segment	= ip4ip6_gso_segment,
440 		.gro_receive    = ip4ip6_gro_receive,
441 		.gro_complete   = ip4ip6_gro_complete,
442 	},
443 };
444 
445 static const struct net_offload ip6ip6_offload = {
446 	.callbacks = {
447 		.gso_segment	= ip6ip6_gso_segment,
448 		.gro_receive    = sit_ip6ip6_gro_receive,
449 		.gro_complete   = ip6ip6_gro_complete,
450 	},
451 };
ipv6_offload_init(void)452 static int __init ipv6_offload_init(void)
453 {
454 
455 	if (tcpv6_offload_init() < 0)
456 		pr_crit("%s: Cannot add TCP protocol offload\n", __func__);
457 	if (ipv6_exthdrs_offload_init() < 0)
458 		pr_crit("%s: Cannot add EXTHDRS protocol offload\n", __func__);
459 
460 	dev_add_offload(&ipv6_packet_offload);
461 
462 	inet_add_offload(&sit_offload, IPPROTO_IPV6);
463 	inet6_add_offload(&ip6ip6_offload, IPPROTO_IPV6);
464 	inet6_add_offload(&ip4ip6_offload, IPPROTO_IPIP);
465 
466 	return 0;
467 }
468 
469 fs_initcall(ipv6_offload_init);
470