~hc/RK356X_SDK_RELEASE.git

..	..	@@ -1,3 +1,4 @@
	1	+// SPDX-License-Identifier: GPL-2.0-or-later
1	2	/*
2	3	* UDP over IPv6
3	4	* Linux INET6 implementation
..	..	@@ -14,11 +15,6 @@
14	15	* a single port at the same time.
15	16	* Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data
16	17	* YOSHIFUJI Hideaki @USAGI: convert /proc/net/udp6 to seq_file.
17		- *
18		- * This program is free software; you can redistribute it and/or
19		- * modify it under the terms of the GNU General Public License
20		- * as published by the Free Software Foundation; either version
21		- * 2 of the License, or (at your option) any later version.
22	18	*/
23	19
24	20	#include <linux/errno.h>
..	..	@@ -36,6 +32,7 @@
36	32	#include <linux/skbuff.h>
37	33	#include <linux/slab.h>
38	34	#include <linux/uaccess.h>
	35	+#include <linux/indirect_call_wrapper.h>
39	36
40	37	#include <net/addrconf.h>
41	38	#include <net/ndisc.h>
..	..	@@ -45,6 +42,7 @@
45	42	#include <net/raw.h>
46	43	#include <net/tcp_states.h>
47	44	#include <net/ip6_checksum.h>
	45	+#include <net/ip6_tunnel.h>
48	46	#include <net/xfrm.h>
49	47	#include <net/inet_hashtables.h>
50	48	#include <net/inet6_hashtables.h>
..	..	@@ -56,14 +54,17 @@
56	54	#include <trace/events/skb.h>
57	55	#include "udp_impl.h"
58	56
59		-static bool udp6_lib_exact_dif_match(struct net net, struct sk_buff skb)
	57	+static void udpv6_destruct_sock(struct sock *sk)
60	58	{
61		-#if defined(CONFIG_NET_L3_MASTER_DEV)
62		- if (!net->ipv4.sysctl_udp_l3mdev_accept &&
63		- skb && ipv6_l3mdev_skb(IP6CB(skb)->flags))
64		- return true;
65		-#endif
66		- return false;
	59	+ udp_destruct_common(sk);
	60	+ inet6_sock_destruct(sk);
	61	+}
	62	+
	63	+int udpv6_init_sock(struct sock *sk)
	64	+{
	65	+ skb_queue_head_init(&udp_sk(sk)->reader_queue);
	66	+ sk->sk_destruct = udpv6_destruct_sock;
	67	+ return 0;
67	68	}
68	69
69	70	static u32 udp6_ehashfn(const struct net *net,
..	..	@@ -86,7 +87,7 @@
86	87	fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret);
87	88
88	89	return __inet6_ehashfn(lhash, lport, fhash, fport,
89		- udp_ipv6_hash_secret + net_hash_mix(net));
	90	+ udp6_ehash_secret + net_hash_mix(net));
90	91	}
91	92
92	93	int udp_v6_get_port(struct sock *sk, unsigned short snum)
..	..	@@ -101,7 +102,7 @@
101	102	return udp_lib_get_port(sk, snum, hash2_nulladdr);
102	103	}
103	104
104		-static void udp_v6_rehash(struct sock *sk)
	105	+void udp_v6_rehash(struct sock *sk)
105	106	{
106	107	u16 new_hash = ipv6_portaddr_hash(sock_net(sk),
107	108	&sk->sk_v6_rcv_saddr,
..	..	@@ -113,14 +114,18 @@
113	114	static int compute_score(struct sock sk, struct net net,
114	115	const struct in6_addr *saddr, __be16 sport,
115	116	const struct in6_addr *daddr, unsigned short hnum,
116		- int dif, int sdif, bool exact_dif)
	117	+ int dif, int sdif)
117	118	{
118	119	int score;
119	120	struct inet_sock *inet;
	121	+ bool dev_match;
120	122
121	123	if (!net_eq(sock_net(sk), net) \|\|
122	124	udp_sk(sk)->udp_port_hash != hnum \|\|
123	125	sk->sk_family != PF_INET6)
	126	+ return -1;
	127	+
	128	+ if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
124	129	return -1;
125	130
126	131	score = 0;
..	..	@@ -132,27 +137,17 @@
132	137	score++;
133	138	}
134	139
135		- if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
136		- if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
137		- return -1;
138		- score++;
139		- }
140		-
141	140	if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
142	141	if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
143	142	return -1;
144	143	score++;
145	144	}
146	145
147		- if (sk->sk_bound_dev_if \|\| exact_dif) {
148		- bool dev_match = (sk->sk_bound_dev_if == dif \|\|
149		- sk->sk_bound_dev_if == sdif);
150		-
151		- if (!dev_match)
152		- return -1;
153		- if (sk->sk_bound_dev_if)
154		- score++;
155		- }
	146	+ dev_match = udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif);
	147	+ if (!dev_match)
	148	+ return -1;
	149	+ if (sk->sk_bound_dev_if)
	150	+ score++;
156	151
157	152	if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
158	153	score++;
..	..	@@ -160,41 +155,85 @@
160	155	return score;
161	156	}
162	157
	158	+static struct sock lookup_reuseport(struct net net, struct sock *sk,
	159	+ struct sk_buff *skb,
	160	+ const struct in6_addr *saddr,
	161	+ __be16 sport,
	162	+ const struct in6_addr *daddr,
	163	+ unsigned int hnum)
	164	+{
	165	+ struct sock *reuse_sk = NULL;
	166	+ u32 hash;
	167	+
	168	+ if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) {
	169	+ hash = udp6_ehashfn(net, daddr, hnum, saddr, sport);
	170	+ reuse_sk = reuseport_select_sock(sk, hash, skb,
	171	+ sizeof(struct udphdr));
	172	+ }
	173	+ return reuse_sk;
	174	+}
	175	+
163	176	/* called with rcu_read_lock() */
164	177	static struct sock udp6_lib_lookup2(struct net net,
165	178	const struct in6_addr *saddr, __be16 sport,
166	179	const struct in6_addr *daddr, unsigned int hnum,
167		- int dif, int sdif, bool exact_dif,
168		- struct udp_hslot hslot2, struct sk_buff skb)
	180	+ int dif, int sdif, struct udp_hslot *hslot2,
	181	+ struct sk_buff *skb)
169	182	{
170		- struct sock sk, result, *reuseport_result;
	183	+ struct sock sk, result;
171	184	int score, badness;
172		- u32 hash = 0;
173	185
174	186	result = NULL;
175	187	badness = -1;
176	188	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
177	189	score = compute_score(sk, net, saddr, sport,
178		- daddr, hnum, dif, sdif, exact_dif);
	190	+ daddr, hnum, dif, sdif);
179	191	if (score > badness) {
180		- reuseport_result = NULL;
181		-
182		- if (sk->sk_reuseport &&
183		- sk->sk_state != TCP_ESTABLISHED) {
184		- hash = udp6_ehashfn(net, daddr, hnum,
185		- saddr, sport);
186		-
187		- reuseport_result = reuseport_select_sock(sk, hash, skb,
188		- sizeof(struct udphdr));
189		- if (reuseport_result && !reuseport_has_conns(sk, false))
190		- return reuseport_result;
	192	+ badness = score;
	193	+ result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
	194	+ if (!result) {
	195	+ result = sk;
	196	+ continue;
191	197	}
192	198
193		- result = reuseport_result ? : sk;
194		- badness = score;
	199	+ /* Fall back to scoring if group has connections */
	200	+ if (!reuseport_has_conns(sk))
	201	+ return result;
	202	+
	203	+ /* Reuseport logic returned an error, keep original score. */
	204	+ if (IS_ERR(result))
	205	+ continue;
	206	+
	207	+ badness = compute_score(sk, net, saddr, sport,
	208	+ daddr, hnum, dif, sdif);
195	209	}
196	210	}
197	211	return result;
	212	+}
	213	+
	214	+static inline struct sock udp6_lookup_run_bpf(struct net net,
	215	+ struct udp_table *udptable,
	216	+ struct sk_buff *skb,
	217	+ const struct in6_addr *saddr,
	218	+ __be16 sport,
	219	+ const struct in6_addr *daddr,
	220	+ u16 hnum)
	221	+{
	222	+ struct sock sk, reuse_sk;
	223	+ bool no_reuseport;
	224	+
	225	+ if (udptable != &udp_table)
	226	+ return NULL; /* only UDP is supported */
	227	+
	228	+ no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP,
	229	+ saddr, sport, daddr, hnum, &sk);
	230	+ if (no_reuseport \|\| IS_ERR_OR_NULL(sk))
	231	+ return sk;
	232	+
	233	+ reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
	234	+ if (reuse_sk)
	235	+ sk = reuse_sk;
	236	+ return sk;
198	237	}
199	238
200	239	/* rcu_read_lock() must be held */
..	..	@@ -204,66 +243,47 @@
204	243	int dif, int sdif, struct udp_table *udptable,
205	244	struct sk_buff *skb)
206	245	{
207		- struct sock sk, result;
208	246	unsigned short hnum = ntohs(dport);
209		- unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
210		- struct udp_hslot hslot2, hslot = &udptable->hash[slot];
211		- bool exact_dif = udp6_lib_exact_dif_match(net, skb);
212		- int score, badness;
213		- u32 hash = 0;
	247	+ unsigned int hash2, slot2;
	248	+ struct udp_hslot *hslot2;
	249	+ struct sock result, sk;
214	250
215		- if (hslot->count > 10) {
216		- hash2 = ipv6_portaddr_hash(net, daddr, hnum);
217		- slot2 = hash2 & udptable->mask;
218		- hslot2 = &udptable->hash2[slot2];
219		- if (hslot->count < hslot2->count)
220		- goto begin;
	251	+ hash2 = ipv6_portaddr_hash(net, daddr, hnum);
	252	+ slot2 = hash2 & udptable->mask;
	253	+ hslot2 = &udptable->hash2[slot2];
221	254
222		- result = udp6_lib_lookup2(net, saddr, sport,
223		- daddr, hnum, dif, sdif, exact_dif,
224		- hslot2, skb);
225		- if (!result) {
226		- unsigned int old_slot2 = slot2;
227		- hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
228		- slot2 = hash2 & udptable->mask;
229		- /* avoid searching the same slot again. */
230		- if (unlikely(slot2 == old_slot2))
231		- return result;
	255	+ /* Lookup connected or non-wildcard sockets */
	256	+ result = udp6_lib_lookup2(net, saddr, sport,
	257	+ daddr, hnum, dif, sdif,
	258	+ hslot2, skb);
	259	+ if (!IS_ERR_OR_NULL(result) && result->sk_state == TCP_ESTABLISHED)
	260	+ goto done;
232	261
233		- hslot2 = &udptable->hash2[slot2];
234		- if (hslot->count < hslot2->count)
235		- goto begin;
236		-
237		- result = udp6_lib_lookup2(net, saddr, sport,
238		- daddr, hnum, dif, sdif,
239		- exact_dif, hslot2,
240		- skb);
241		- }
242		- if (unlikely(IS_ERR(result)))
243		- return NULL;
244		- return result;
245		- }
246		-begin:
247		- result = NULL;
248		- badness = -1;
249		- sk_for_each_rcu(sk, &hslot->head) {
250		- score = compute_score(sk, net, saddr, sport, daddr, hnum, dif,
251		- sdif, exact_dif);
252		- if (score > badness) {
253		- if (sk->sk_reuseport) {
254		- hash = udp6_ehashfn(net, daddr, hnum,
255		- saddr, sport);
256		- result = reuseport_select_sock(sk, hash, skb,
257		- sizeof(struct udphdr));
258		- if (unlikely(IS_ERR(result)))
259		- return NULL;
260		- if (result)
261		- return result;
262		- }
	262	+ /* Lookup redirect from BPF */
	263	+ if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
	264	+ sk = udp6_lookup_run_bpf(net, udptable, skb,
	265	+ saddr, sport, daddr, hnum);
	266	+ if (sk) {
263	267	result = sk;
264		- badness = score;
	268	+ goto done;
265	269	}
266	270	}
	271	+
	272	+ /* Got non-wildcard socket or error on first lookup */
	273	+ if (result)
	274	+ goto done;
	275	+
	276	+ /* Lookup wildcard sockets */
	277	+ hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
	278	+ slot2 = hash2 & udptable->mask;
	279	+ hslot2 = &udptable->hash2[slot2];
	280	+
	281	+ result = udp6_lib_lookup2(net, saddr, sport,
	282	+ &in6addr_any, hnum, dif, sdif,
	283	+ hslot2, skb);
	284	+done:
	285	+ if (IS_ERR(result))
	286	+ return NULL;
267	287	return result;
268	288	}
269	289	EXPORT_SYMBOL_GPL(__udp6_lib_lookup);
..	..	@@ -329,9 +349,9 @@
329	349	struct inet_sock *inet = inet_sk(sk);
330	350	struct sk_buff *skb;
331	351	unsigned int ulen, copied;
332		- int peeked, peeking, off;
333		- int err;
	352	+ int off, err, peeking = flags & MSG_PEEK;
334	353	int is_udplite = IS_UDPLITE(sk);
	354	+ struct udp_mib __percpu *mib;
335	355	bool checksum_valid = false;
336	356	int is_udp4;
337	357
..	..	@@ -342,9 +362,8 @@
342	362	return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
343	363
344	364	try_again:
345		- peeking = flags & MSG_PEEK;
346	365	off = sk_peek_offset(sk, flags);
347		- skb = __skb_recv_udp(sk, flags, noblock, &peeked, &off, &err);
	366	+ skb = __skb_recv_udp(sk, flags, noblock, &off, &err);
348	367	if (!skb)
349	368	return err;
350	369
..	..	@@ -356,6 +375,7 @@
356	375	msg->msg_flags \|= MSG_TRUNC;
357	376
358	377	is_udp4 = (skb->protocol == htons(ETH_P_IP));
	378	+ mib = __UDPX_MIB(sk, is_udp4);
359	379
360	380	/*
361	381	* If checksum is needed at all, try to do it while copying the
..	..	@@ -382,26 +402,15 @@
382	402	goto csum_copy_err;
383	403	}
384	404	if (unlikely(err)) {
385		- if (!peeked) {
	405	+ if (!peeking) {
386	406	atomic_inc(&sk->sk_drops);
387		- if (is_udp4)
388		- UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS,
389		- is_udplite);
390		- else
391		- UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS,
392		- is_udplite);
	407	+ SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
393	408	}
394	409	kfree_skb(skb);
395	410	return err;
396	411	}
397		- if (!peeked) {
398		- if (is_udp4)
399		- UDP_INC_STATS(sock_net(sk), UDP_MIB_INDATAGRAMS,
400		- is_udplite);
401		- else
402		- UDP6_INC_STATS(sock_net(sk), UDP_MIB_INDATAGRAMS,
403		- is_udplite);
404		- }
	412	+ if (!peeking)
	413	+ SNMP_INC_STATS(mib, UDP_MIB_INDATAGRAMS);
405	414
406	415	sock_recv_ts_and_drops(msg, sk, skb);
407	416
..	..	@@ -429,6 +438,9 @@
429	438	(struct sockaddr *)sin6);
430	439	}
431	440
	441	+ if (udp_sk(sk)->gro_enabled)
	442	+ udp_cmsg_recv(msg, sk, skb);
	443	+
432	444	if (np->rxopt.all)
433	445	ip6_datagram_recv_common_ctl(sk, msg, skb);
434	446
..	..	@@ -451,17 +463,8 @@
451	463	csum_copy_err:
452	464	if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags,
453	465	udp_skb_destructor)) {
454		- if (is_udp4) {
455		- UDP_INC_STATS(sock_net(sk),
456		- UDP_MIB_CSUMERRORS, is_udplite);
457		- UDP_INC_STATS(sock_net(sk),
458		- UDP_MIB_INERRORS, is_udplite);
459		- } else {
460		- UDP6_INC_STATS(sock_net(sk),
461		- UDP_MIB_CSUMERRORS, is_udplite);
462		- UDP6_INC_STATS(sock_net(sk),
463		- UDP_MIB_INERRORS, is_udplite);
464		- }
	466	+ SNMP_INC_STATS(mib, UDP_MIB_CSUMERRORS);
	467	+ SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
465	468	}
466	469	kfree_skb(skb);
467	470
..	..	@@ -471,26 +474,133 @@
471	474	goto try_again;
472	475	}
473	476
474		-void __udp6_lib_err(struct sk_buff skb, struct inet6_skb_parm opt,
475		- u8 type, u8 code, int offset, __be32 info,
476		- struct udp_table *udptable)
	477	+DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
	478	+void udpv6_encap_enable(void)
	479	+{
	480	+ static_branch_inc(&udpv6_encap_needed_key);
	481	+}
	482	+EXPORT_SYMBOL(udpv6_encap_enable);
	483	+
	484	+/* Handler for tunnels with arbitrary destination ports: no socket lookup, go
	485	+ * through error handlers in encapsulations looking for a match.
	486	+ */
	487	+static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb,
	488	+ struct inet6_skb_parm *opt,
	489	+ u8 type, u8 code, int offset, __be32 info)
	490	+{
	491	+ int i;
	492	+
	493	+ for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
	494	+ int (handler)(struct sk_buff skb, struct inet6_skb_parm *opt,
	495	+ u8 type, u8 code, int offset, __be32 info);
	496	+ const struct ip6_tnl_encap_ops *encap;
	497	+
	498	+ encap = rcu_dereference(ip6tun_encaps[i]);
	499	+ if (!encap)
	500	+ continue;
	501	+ handler = encap->err_handler;
	502	+ if (handler && !handler(skb, opt, type, code, offset, info))
	503	+ return 0;
	504	+ }
	505	+
	506	+ return -ENOENT;
	507	+}
	508	+
	509	+/* Try to match ICMP errors to UDP tunnels by looking up a socket without
	510	+ * reversing source and destination port: this will match tunnels that force the
	511	+ * same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that
	512	+ * lwtunnels might actually break this assumption by being configured with
	513	+ * different destination ports on endpoints, in this case we won't be able to
	514	+ * trace ICMP messages back to them.
	515	+ *
	516	+ * If this doesn't match any socket, probe tunnels with arbitrary destination
	517	+ * ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port
	518	+ * we've sent packets to won't necessarily match the local destination port.
	519	+ *
	520	+ * Then ask the tunnel implementation to match the error against a valid
	521	+ * association.
	522	+ *
	523	+ * Return an error if we can't find a match, the socket if we need further
	524	+ * processing, zero otherwise.
	525	+ */
	526	+static struct sock __udp6_lib_err_encap(struct net net,
	527	+ const struct ipv6hdr *hdr, int offset,
	528	+ struct udphdr *uh,
	529	+ struct udp_table *udptable,
	530	+ struct sk_buff *skb,
	531	+ struct inet6_skb_parm *opt,
	532	+ u8 type, u8 code, __be32 info)
	533	+{
	534	+ int network_offset, transport_offset;
	535	+ struct sock *sk;
	536	+
	537	+ network_offset = skb_network_offset(skb);
	538	+ transport_offset = skb_transport_offset(skb);
	539	+
	540	+ /* Network header needs to point to the outer IPv6 header inside ICMP */
	541	+ skb_reset_network_header(skb);
	542	+
	543	+ /* Transport header needs to point to the UDP header */
	544	+ skb_set_transport_header(skb, offset);
	545	+
	546	+ sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source,
	547	+ &hdr->saddr, uh->dest,
	548	+ inet6_iif(skb), 0, udptable, skb);
	549	+ if (sk) {
	550	+ int (lookup)(struct sock sk, struct sk_buff *skb);
	551	+ struct udp_sock *up = udp_sk(sk);
	552	+
	553	+ lookup = READ_ONCE(up->encap_err_lookup);
	554	+ if (!lookup \|\| lookup(sk, skb))
	555	+ sk = NULL;
	556	+ }
	557	+
	558	+ if (!sk) {
	559	+ sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code,
	560	+ offset, info));
	561	+ }
	562	+
	563	+ skb_set_transport_header(skb, transport_offset);
	564	+ skb_set_network_header(skb, network_offset);
	565	+
	566	+ return sk;
	567	+}
	568	+
	569	+int __udp6_lib_err(struct sk_buff skb, struct inet6_skb_parm opt,
	570	+ u8 type, u8 code, int offset, __be32 info,
	571	+ struct udp_table *udptable)
477	572	{
478	573	struct ipv6_pinfo *np;
479	574	const struct ipv6hdr hdr = (const struct ipv6hdr )skb->data;
480	575	const struct in6_addr *saddr = &hdr->saddr;
481	576	const struct in6_addr *daddr = &hdr->daddr;
482	577	struct udphdr uh = (struct udphdr )(skb->data+offset);
	578	+ bool tunnel = false;
483	579	struct sock *sk;
484	580	int harderr;
485	581	int err;
486	582	struct net *net = dev_net(skb->dev);
487	583
488	584	sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
489		- inet6_iif(skb), 0, udptable, NULL);
	585	+ inet6_iif(skb), inet6_sdif(skb), udptable, NULL);
490	586	if (!sk) {
491		- __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
492		- ICMP6_MIB_INERRORS);
493		- return;
	587	+ /* No socket for error: try tunnels before discarding */
	588	+ sk = ERR_PTR(-ENOENT);
	589	+ if (static_branch_unlikely(&udpv6_encap_needed_key)) {
	590	+ sk = __udp6_lib_err_encap(net, hdr, offset, uh,
	591	+ udptable, skb,
	592	+ opt, type, code, info);
	593	+ if (!sk)
	594	+ return 0;
	595	+ }
	596	+
	597	+ if (IS_ERR(sk)) {
	598	+ __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
	599	+ ICMP6_MIB_INERRORS);
	600	+ return PTR_ERR(sk);
	601	+ }
	602	+
	603	+ tunnel = true;
494	604	}
495	605
496	606	harderr = icmpv6_err_convert(type, code, &err);
..	..	@@ -504,9 +614,18 @@
504	614	harderr = 1;
505	615	}
506	616	if (type == NDISC_REDIRECT) {
507		- ip6_sk_redirect(skb, sk);
	617	+ if (tunnel) {
	618	+ ip6_redirect(skb, sock_net(sk), inet6_iif(skb),
	619	+ sk->sk_mark, sk->sk_uid);
	620	+ } else {
	621	+ ip6_sk_redirect(skb, sk);
	622	+ }
508	623	goto out;
509	624	}
	625	+
	626	+ /* Tunnels don't have an application socket: don't pass errors back */
	627	+ if (tunnel)
	628	+ goto out;
510	629
511	630	if (!np->recverr) {
512	631	if (!harderr \|\| sk->sk_state != TCP_ESTABLISHED)
..	..	@@ -518,7 +637,7 @@
518	637	sk->sk_err = err;
519	638	sk->sk_error_report(sk);
520	639	out:
521		- return;
	640	+ return 0;
522	641	}
523	642
524	643	static int __udpv6_queue_rcv_skb(struct sock sk, struct sk_buff skb)
..	..	@@ -549,21 +668,14 @@
549	668	return 0;
550	669	}
551	670
552		-static __inline__ void udpv6_err(struct sk_buff *skb,
553		- struct inet6_skb_parm *opt, u8 type,
554		- u8 code, int offset, __be32 info)
	671	+static __inline__ int udpv6_err(struct sk_buff *skb,
	672	+ struct inet6_skb_parm *opt, u8 type,
	673	+ u8 code, int offset, __be32 info)
555	674	{
556		- __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
	675	+ return __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
557	676	}
558	677
559		-static DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
560		-void udpv6_encap_enable(void)
561		-{
562		- static_branch_enable(&udpv6_encap_needed_key);
563		-}
564		-EXPORT_SYMBOL(udpv6_encap_enable);
565		-
566		-static int udpv6_queue_rcv_skb(struct sock sk, struct sk_buff skb)
	678	+static int udpv6_queue_rcv_one_skb(struct sock sk, struct sk_buff skb)
567	679	{
568	680	struct udp_sock *up = udp_sk(sk);
569	681	int is_udplite = IS_UDPLITE(sk);
..	..	@@ -646,10 +758,31 @@
646	758	return -1;
647	759	}
648	760
	761	+static int udpv6_queue_rcv_skb(struct sock sk, struct sk_buff skb)
	762	+{
	763	+ struct sk_buff next, segs;
	764	+ int ret;
	765	+
	766	+ if (likely(!udp_unexpected_gso(sk, skb)))
	767	+ return udpv6_queue_rcv_one_skb(sk, skb);
	768	+
	769	+ __skb_push(skb, -skb_mac_offset(skb));
	770	+ segs = udp_rcv_segment(sk, skb, false);
	771	+ skb_list_walk_safe(segs, skb, next) {
	772	+ __skb_pull(skb, skb_transport_offset(skb));
	773	+
	774	+ ret = udpv6_queue_rcv_one_skb(sk, skb);
	775	+ if (ret > 0)
	776	+ ip6_protocol_deliver_rcu(dev_net(skb->dev), skb, ret,
	777	+ true);
	778	+ }
	779	+ return 0;
	780	+}
	781	+
649	782	static bool __udp_v6_is_mcast_sock(struct net net, struct sock sk,
650	783	__be16 loc_port, const struct in6_addr *loc_addr,
651	784	__be16 rmt_port, const struct in6_addr *rmt_addr,
652		- int dif, unsigned short hnum)
	785	+ int dif, int sdif, unsigned short hnum)
653	786	{
654	787	struct inet_sock *inet = inet_sk(sk);
655	788
..	..	@@ -661,7 +794,7 @@
661	794	(inet->inet_dport && inet->inet_dport != rmt_port) \|\|
662	795	(!ipv6_addr_any(&sk->sk_v6_daddr) &&
663	796	!ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) \|\|
664		- (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) \|\|
	797	+ !udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif) \|\|
665	798	(!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
666	799	!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
667	800	return false;
..	..	@@ -695,6 +828,7 @@
695	828	unsigned int offset = offsetof(typeof(*sk), sk_node);
696	829	unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
697	830	int dif = inet6_iif(skb);
	831	+ int sdif = inet6_sdif(skb);
698	832	struct hlist_node *node;
699	833	struct sk_buff *nskb;
700	834
..	..	@@ -709,7 +843,8 @@
709	843
710	844	sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) {
711	845	if (!__udp_v6_is_mcast_sock(net, sk, uh->dest, daddr,
712		- uh->source, saddr, dif, hnum))
	846	+ uh->source, saddr, dif, sdif,
	847	+ hnum))
713	848	continue;
714	849	/* If zero checksum and no_check is not on for
715	850	* the socket then skip it.
..	..	@@ -769,8 +904,7 @@
769	904	int ret;
770	905
771	906	if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
772		- skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check,
773		- ip6_compute_pseudo);
	907	+ skb_checksum_try_convert(skb, IPPROTO_UDP, ip6_compute_pseudo);
774	908
775	909	ret = udpv6_queue_rcv_skb(sk, skb);
776	910
..	..	@@ -787,6 +921,7 @@
787	921	struct net *net = dev_net(skb->dev);
788	922	struct udphdr *uh;
789	923	struct sock *sk;
	924	+ bool refcounted;
790	925	u32 ulen = 0;
791	926
792	927	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
..	..	@@ -823,21 +958,23 @@
823	958	goto csum_error;
824	959
825	960	/* Check if the socket is already available, e.g. due to early demux */
826		- sk = skb_steal_sock(skb);
	961	+ sk = skb_steal_sock(skb, &refcounted);
827	962	if (sk) {
828	963	struct dst_entry *dst = skb_dst(skb);
829	964	int ret;
830	965
831		- if (unlikely(sk->sk_rx_dst != dst))
	966	+ if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst))
832	967	udp6_sk_rx_dst_set(sk, dst);
833	968
834	969	if (!uh->check && !udp_sk(sk)->no_check6_rx) {
835		- sock_put(sk);
	970	+ if (refcounted)
	971	+ sock_put(sk);
836	972	goto report_csum_error;
837	973	}
838	974
839	975	ret = udp6_unicast_rcv_skb(sk, skb, uh);
840		- sock_put(sk);
	976	+ if (refcounted)
	977	+ sock_put(sk);
841	978	return ret;
842	979	}
843	980
..	..	@@ -904,7 +1041,7 @@
904	1041
905	1042	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
906	1043	if (sk->sk_state == TCP_ESTABLISHED &&
907		- INET6_MATCH(sk, net, rmt_addr, loc_addr, ports, dif, sdif))
	1044	+ inet6_match(net, sk, rmt_addr, loc_addr, ports, dif, sdif))
908	1045	return sk;
909	1046	/* Only check first socket in chain */
910	1047	break;
..	..	@@ -912,7 +1049,7 @@
912	1049	return NULL;
913	1050	}
914	1051
915		-static void udp_v6_early_demux(struct sk_buff *skb)
	1052	+void udp_v6_early_demux(struct sk_buff *skb)
916	1053	{
917	1054	struct net *net = dev_net(skb->dev);
918	1055	const struct udphdr *uh;
..	..	@@ -940,7 +1077,7 @@
940	1077
941	1078	skb->sk = sk;
942	1079	skb->destructor = sock_efree;
943		- dst = READ_ONCE(sk->sk_rx_dst);
	1080	+ dst = rcu_dereference(sk->sk_rx_dst);
944	1081
945	1082	if (dst)
946	1083	dst = dst_check(dst, inet6_sk(sk)->rx_dst_cookie);
..	..	@@ -953,7 +1090,7 @@
953	1090	}
954	1091	}
955	1092
956		-static __inline__ int udpv6_rcv(struct sk_buff *skb)
	1093	+INDIRECT_CALLABLE_SCOPE int udpv6_rcv(struct sk_buff *skb)
957	1094	{
958	1095	return __udp6_lib_rcv(skb, &udp_table, IPPROTO_UDP);
959	1096	}
..	..	@@ -977,6 +1114,8 @@
977	1114	static int udpv6_pre_connect(struct sock sk, struct sockaddr uaddr,
978	1115	int addr_len)
979	1116	{
	1117	+ if (addr_len < offsetofend(struct sockaddr, sa_family))
	1118	+ return -EINVAL;
980	1119	/* The following checks are replicated from __ip6_datagram_connect()
981	1120	* and intended to prevent BPF program called below from accessing
982	1121	* bytes that are out of the bound specified by user in addr_len.
..	..	@@ -998,6 +1137,9 @@
998	1137	* @sk: socket we are sending on
999	1138	* @skb: sk_buff containing the filled-in UDP header
1000	1139	* (checksum field must be zeroed out)
	1140	+ * @saddr: source address
	1141	+ * @daddr: destination address
	1142	+ * @len: length of packet
1001	1143	*/
1002	1144	static void udp6_hwcsum_outgoing(struct sock sk, struct sk_buff skb,
1003	1145	const struct in6_addr *saddr,
..	..	@@ -1177,6 +1319,7 @@
1177	1319	ipcm6_init(&ipc6);
1178	1320	ipc6.gso_size = READ_ONCE(up->gso_size);
1179	1321	ipc6.sockc.tsflags = sk->sk_tsflags;
	1322	+ ipc6.sockc.mark = sk->sk_mark;
1180	1323
1181	1324	/* destination address check */
1182	1325	if (sin6) {
..	..	@@ -1219,9 +1362,11 @@
1219	1362	msg->msg_name = &sin;
1220	1363	msg->msg_namelen = sizeof(sin);
1221	1364	do_udp_sendmsg:
1222		- if (__ipv6_only_sock(sk))
1223		- return -ENETUNREACH;
1224		- return udp_sendmsg(sk, msg, len);
	1365	+ err = __ipv6_only_sock(sk) ?
	1366	+ -ENETUNREACH : udp_sendmsg(sk, msg, len);
	1367	+ msg->msg_name = sin6;
	1368	+ msg->msg_namelen = addr_len;
	1369	+ return err;
1225	1370	}
1226	1371	}
1227	1372
..	..	@@ -1266,7 +1411,7 @@
1266	1411	fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
1267	1412	if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
1268	1413	flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
1269		- if (!flowlabel)
	1414	+ if (IS_ERR(flowlabel))
1270	1415	return -EINVAL;
1271	1416	}
1272	1417	}
..	..	@@ -1299,7 +1444,6 @@
1299	1444	if (!fl6.flowi6_oif)
1300	1445	fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;
1301	1446
1302		- fl6.flowi6_mark = sk->sk_mark;
1303	1447	fl6.flowi6_uid = sk->sk_uid;
1304	1448
1305	1449	if (msg->msg_controllen) {
..	..	@@ -1318,7 +1462,7 @@
1318	1462	}
1319	1463	if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
1320	1464	flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
1321		- if (!flowlabel)
	1465	+ if (IS_ERR(flowlabel))
1322	1466	return -EINVAL;
1323	1467	}
1324	1468	if (!(opt->opt_nflen\|opt->opt_flen))
..	..	@@ -1335,6 +1479,7 @@
1335	1479	ipc6.opt = opt;
1336	1480
1337	1481	fl6.flowi6_proto = sk->sk_protocol;
	1482	+ fl6.flowi6_mark = ipc6.sockc.mark;
1338	1483	fl6.daddr = *daddr;
1339	1484	if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr))
1340	1485	fl6.saddr = np->saddr;
..	..	@@ -1376,7 +1521,7 @@
1376	1521	} else if (!fl6.flowi6_oif)
1377	1522	fl6.flowi6_oif = np->ucast_oif;
1378	1523
1379		- security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
	1524	+ security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
1380	1525
1381	1526	if (ipc6.tclass < 0)
1382	1527	ipc6.tclass = np->tclass;
..	..	@@ -1482,38 +1627,32 @@
1482	1627	udp_v6_flush_pending_frames(sk);
1483	1628	release_sock(sk);
1484	1629
1485		- if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) {
1486		- void (encap_destroy)(struct sock sk);
1487		- encap_destroy = READ_ONCE(up->encap_destroy);
1488		- if (encap_destroy)
1489		- encap_destroy(sk);
	1630	+ if (static_branch_unlikely(&udpv6_encap_needed_key)) {
	1631	+ if (up->encap_type) {
	1632	+ void (encap_destroy)(struct sock sk);
	1633	+ encap_destroy = READ_ONCE(up->encap_destroy);
	1634	+ if (encap_destroy)
	1635	+ encap_destroy(sk);
	1636	+ }
	1637	+ if (up->encap_enabled) {
	1638	+ static_branch_dec(&udpv6_encap_needed_key);
	1639	+ udp_encap_disable();
	1640	+ }
1490	1641	}
1491		-
1492		- inet6_destroy_sock(sk);
1493	1642	}
1494	1643
1495	1644	/*
1496	1645	* Socket option code for UDP
1497	1646	*/
1498		-int udpv6_setsockopt(struct sock *sk, int level, int optname,
1499		- char __user *optval, unsigned int optlen)
	1647	+int udpv6_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
	1648	+ unsigned int optlen)
1500	1649	{
1501	1650	if (level == SOL_UDP \|\| level == SOL_UDPLITE)
1502		- return udp_lib_setsockopt(sk, level, optname, optval, optlen,
	1651	+ return udp_lib_setsockopt(sk, level, optname,
	1652	+ optval, optlen,
1503	1653	udp_v6_push_pending_frames);
1504	1654	return ipv6_setsockopt(sk, level, optname, optval, optlen);
1505	1655	}
1506		-
1507		-#ifdef CONFIG_COMPAT
1508		-int compat_udpv6_setsockopt(struct sock *sk, int level, int optname,
1509		- char __user *optval, unsigned int optlen)
1510		-{
1511		- if (level == SOL_UDP \|\| level == SOL_UDPLITE)
1512		- return udp_lib_setsockopt(sk, level, optname, optval, optlen,
1513		- udp_v6_push_pending_frames);
1514		- return compat_ipv6_setsockopt(sk, level, optname, optval, optlen);
1515		-}
1516		-#endif
1517	1656
1518	1657	int udpv6_getsockopt(struct sock *sk, int level, int optname,
1519	1658	char __user optval, int __user optlen)
..	..	@@ -1523,22 +1662,7 @@
1523	1662	return ipv6_getsockopt(sk, level, optname, optval, optlen);
1524	1663	}
1525	1664
1526		-#ifdef CONFIG_COMPAT
1527		-int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
1528		- char __user optval, int __user optlen)
1529		-{
1530		- if (level == SOL_UDP \|\| level == SOL_UDPLITE)
1531		- return udp_lib_getsockopt(sk, level, optname, optval, optlen);
1532		- return compat_ipv6_getsockopt(sk, level, optname, optval, optlen);
1533		-}
1534		-#endif
1535		-
1536		-/* thinking of making this const? Don't.
1537		- * early_demux can change based on sysctl.
1538		- */
1539		-static struct inet6_protocol udpv6_protocol = {
1540		- .early_demux = udp_v6_early_demux,
1541		- .early_demux_handler = udp_v6_early_demux,
	1665	+static const struct inet6_protocol udpv6_protocol = {
1542	1666	.handler = udpv6_rcv,
1543	1667	.err_handler = udpv6_err,
1544	1668	.flags = INET6_PROTO_NOPOLICY\|INET6_PROTO_FINAL,
..	..	@@ -1598,7 +1722,7 @@
1598	1722	.connect = ip6_datagram_connect,
1599	1723	.disconnect = udp_disconnect,
1600	1724	.ioctl = udp_ioctl,
1601		- .init = udp_init_sock,
	1725	+ .init = udpv6_init_sock,
1602	1726	.destroy = udpv6_destroy_sock,
1603	1727	.setsockopt = udpv6_setsockopt,
1604	1728	.getsockopt = udpv6_getsockopt,
..	..	@@ -1615,10 +1739,6 @@
1615	1739	.sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min),
1616	1740	.obj_size = sizeof(struct udp6_sock),
1617	1741	.h.udp_table = &udp_table,
1618		-#ifdef CONFIG_COMPAT
1619		- .compat_setsockopt = compat_udpv6_setsockopt,
1620		- .compat_getsockopt = compat_udpv6_getsockopt,
1621		-#endif
1622	1742	.diag_destroy = udp_abort,
1623	1743	};
1624	1744