summaryrefslogtreecommitdiff
path: root/include/net/udp.h
blob: 909ecf447e0fb2abaedf4d8954d2824c746fb251 (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
/* 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.
 *
 *		Definitions for the UDP module.
 *
 * Version:	@(#)udp.h	1.0.2	05/07/93
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *
 * Fixes:
 *		Alan Cox	: Turned on udp checksums. I don't want to
 *				  chase 'memory corruption' bugs that aren't!
 */
#ifndef _UDP_H
#define _UDP_H

#include <linux/list.h>
#include <linux/bug.h>
#include <net/inet_sock.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ip.h>
#include <linux/ipv6.h>
#include <linux/seq_file.h>
#include <linux/poll.h>
#include <linux/indirect_call_wrapper.h>

/**
 *	struct udp_skb_cb  -  UDP(-Lite) private variables
 *
 *	@header:      private variables used by IPv4/IPv6
 *	@cscov:       checksum coverage length (UDP-Lite only)
 *	@partial_cov: if set indicates partial csum coverage
 */
struct udp_skb_cb {
	union {
		struct inet_skb_parm	h4;
#if IS_ENABLED(CONFIG_IPV6)
		struct inet6_skb_parm	h6;
#endif
	} header;
	__u16		cscov;
	__u8		partial_cov;
};
#define UDP_SKB_CB(__skb)	((struct udp_skb_cb *)((__skb)->cb))

/**
 *	struct udp_hslot - UDP hash slot
 *
 *	@head:	head of list of sockets
 *	@count:	number of sockets in 'head' list
 *	@lock:	spinlock protecting changes to head/count
 */
struct udp_hslot {
	struct hlist_head	head;
	int			count;
	spinlock_t		lock;
} __attribute__((aligned(2 * sizeof(long))));

/**
 *	struct udp_table - UDP table
 *
 *	@hash:	hash table, sockets are hashed on (local port)
 *	@hash2:	hash table, sockets are hashed on (local port, local address)
 *	@mask:	number of slots in hash tables, minus 1
 *	@log:	log2(number of slots in hash table)
 */
struct udp_table {
	struct udp_hslot	*hash;
	struct udp_hslot	*hash2;
	unsigned int		mask;
	unsigned int		log;
};
extern struct udp_table udp_table;
void udp_table_init(struct udp_table *, const char *);
static inline struct udp_hslot *udp_hashslot(struct udp_table *table,
					     struct net *net, unsigned int num)
{
	return &table->hash[udp_hashfn(net, num, table->mask)];
}
/*
 * For secondary hash, net_hash_mix() is performed before calling
 * udp_hashslot2(), this explains difference with udp_hashslot()
 */
static inline struct udp_hslot *udp_hashslot2(struct udp_table *table,
					      unsigned int hash)
{
	return &table->hash2[hash & table->mask];
}

extern struct proto udp_prot;

extern atomic_long_t udp_memory_allocated;

/* sysctl variables for udp */
extern long sysctl_udp_mem[3];
extern int sysctl_udp_rmem_min;
extern int sysctl_udp_wmem_min;

struct sk_buff;

/*
 *	Generic checksumming routines for UDP(-Lite) v4 and v6
 */
static inline __sum16 __udp_lib_checksum_complete(struct sk_buff *skb)
{
	return (UDP_SKB_CB(skb)->cscov == skb->len ?
		__skb_checksum_complete(skb) :
		__skb_checksum_complete_head(skb, UDP_SKB_CB(skb)->cscov));
}

static inline int udp_lib_checksum_complete(struct sk_buff *skb)
{
	return !skb_csum_unnecessary(skb) &&
		__udp_lib_checksum_complete(skb);
}

/**
 * 	udp_csum_outgoing  -  compute UDPv4/v6 checksum over fragments
 * 	@sk: 	socket we are writing to
 * 	@skb: 	sk_buff containing the filled-in UDP header
 * 	        (checksum field must be zeroed out)
 */
static inline __wsum udp_csum_outgoing(struct sock *sk, struct sk_buff *skb)
{
	__wsum csum = csum_partial(skb_transport_header(skb),
				   sizeof(struct udphdr), 0);
	skb_queue_walk(&sk->sk_write_queue, skb) {
		csum = csum_add(csum, skb->csum);
	}
	return csum;
}

static inline __wsum udp_csum(struct sk_buff *skb)
{
	__wsum csum = csum_partial(skb_transport_header(skb),
				   sizeof(struct udphdr), skb->csum);

	for (skb = skb_shinfo(skb)->frag_list; skb; skb = skb->next) {
		csum = csum_add(csum, skb->csum);
	}
	return csum;
}

static inline __sum16 udp_v4_check(int len, __be32 saddr,
				   __be32 daddr, __wsum base)
{
	return csum_tcpudp_magic(saddr, daddr, len, IPPROTO_UDP, base);
}

void udp_set_csum(bool nocheck, struct sk_buff *skb,
		  __be32 saddr, __be32 daddr, int len);

static inline void udp_csum_pull_header(struct sk_buff *skb)
{
	if (!skb->csum_valid && skb->ip_summed == CHECKSUM_NONE)
		skb->csum = csum_partial(skb->data, sizeof(struct udphdr),
					 skb->csum);
	skb_pull_rcsum(skb, sizeof(struct udphdr));
	UDP_SKB_CB(skb)->cscov -= sizeof(struct udphdr);
}

typedef struct sock *(*udp_lookup_t)(const struct sk_buff *skb, __be16 sport,
				     __be16 dport);

INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *,
							   struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int));
INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *,
							   struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int));
INDIRECT_CALLABLE_DECLARE(void udp_v6_early_demux(struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *));

struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
				struct udphdr *uh, struct sock *sk);
int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup);

struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
				  netdev_features_t features, bool is_ipv6);

static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb)
{
	struct udphdr *uh;
	unsigned int hlen, off;

	off  = skb_gro_offset(skb);
	hlen = off + sizeof(*uh);
	uh   = skb_gro_header_fast(skb, off);
	if (skb_gro_header_hard(skb, hlen))
		uh = skb_gro_header_slow(skb, hlen, off);

	return uh;
}

/* hash routines shared between UDPv4/6 and UDP-Litev4/6 */
static inline int udp_lib_hash(struct sock *sk)
{
	BUG();
	return 0;
}

void udp_lib_unhash(struct sock *sk);
void udp_lib_rehash(struct sock *sk, u16 new_hash);

static inline void udp_lib_close(struct sock *sk, long timeout)
{
	sk_common_release(sk);
}

int udp_lib_get_port(struct sock *sk, unsigned short snum,
		     unsigned int hash2_nulladdr);

u32 udp_flow_hashrnd(void);

static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb,
				       int min, int max, bool use_eth)
{
	u32 hash;

	if (min >= max) {
		/* Use default range */
		inet_get_local_port_range(net, &min, &max);
	}

	hash = skb_get_hash(skb);
	if (unlikely(!hash)) {
		if (use_eth) {
			/* Can't find a normal hash, caller has indicated an
			 * Ethernet packet so use that to compute a hash.
			 */
			hash = jhash(skb->data, 2 * ETH_ALEN,
				     (__force u32) skb->protocol);
		} else {
			/* Can't derive any sort of hash for the packet, set
			 * to some consistent random value.
			 */
			hash = udp_flow_hashrnd();
		}
	}

	/* Since this is being sent on the wire obfuscate hash a bit
	 * to minimize possbility that any useful information to an
	 * attacker is leaked. Only upper 16 bits are relevant in the
	 * computation for 16 bit port value.
	 */
	hash ^= hash << 16;

	return htons((((u64) hash * (max - min)) >> 32) + min);
}

static inline int udp_rqueue_get(struct sock *sk)
{
	return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit);
}

static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if,
				       int dif, int sdif)
{
#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
	return inet_bound_dev_eq(!!net->ipv4.sysctl_udp_l3mdev_accept,
				 bound_dev_if, dif, sdif);
#else
	return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
#endif
}

/* net/ipv4/udp.c */
void udp_destruct_sock(struct sock *sk);
void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len);
int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb);
void udp_skb_destructor(struct sock *sk, struct sk_buff *skb);
struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
			       int noblock, int *off, int *err);
static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags,
					   int noblock, int *err)
{
	int off = 0;

	return __skb_recv_udp(sk, flags, noblock, &off, err);
}

int udp_v4_early_demux(struct sk_buff *skb);
bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst);
int udp_get_port(struct sock *sk, unsigned short snum,
		 int (*saddr_cmp)(const struct sock *,
				  const struct sock *));
int udp_err(struct sk_buff *, u32);
int udp_abort(struct sock *sk, int err);
int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len);
int udp_push_pending_frames(struct sock *sk);
void udp_flush_pending_frames(struct sock *sk);
int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size);
void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst);
int udp_rcv(struct sk_buff *skb);
int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
int udp_init_sock(struct sock *sk);
int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
int __udp_disconnect(struct sock *sk, int flags);
int udp_disconnect(struct sock *sk, int flags);
__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait);
struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb,
				       netdev_features_t features,
				       bool is_ipv6);
int udp_lib_getsockopt(struct sock *sk, int level, int optname,
		       char __user *optval, int __user *optlen);
int udp_lib_setsockopt(struct sock *sk, int level, int optname,
		       sockptr_t optval, unsigned int optlen,
		       int (*push_pending_frames)(struct sock *));
struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
			     __be32 daddr, __be16 dport, int dif);
struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
			       __be32 daddr, __be16 dport, int dif, int sdif,
			       struct udp_table *tbl, struct sk_buff *skb);
struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
				 __be16 sport, __be16 dport);
struct sock *udp6_lib_lookup(struct net *net,
			     const struct in6_addr *saddr, __be16 sport,
			     const struct in6_addr *daddr, __be16 dport,
			     int dif);
struct sock *__udp6_lib_lookup(struct net *net,
			       const struct in6_addr *saddr, __be16 sport,
			       const struct in6_addr *daddr, __be16 dport,
			       int dif, int sdif, struct udp_table *tbl,
			       struct sk_buff *skb);
struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
				 __be16 sport, __be16 dport);
int udp_read_sock(struct sock *sk, read_descriptor_t *desc,
		  sk_read_actor_t recv_actor);

/* UDP uses skb->dev_scratch to cache as much information as possible and avoid
 * possibly multiple cache miss on dequeue()
 */
struct udp_dev_scratch {
	/* skb->truesize and the stateless bit are embedded in a single field;
	 * do not use a bitfield since the compiler emits better/smaller code
	 * this way
	 */
	u32 _tsize_state;

#if BITS_PER_LONG == 64
	/* len and the bit needed to compute skb_csum_unnecessary
	 * will be on cold cache lines at recvmsg time.
	 * skb->len can be stored on 16 bits since the udp header has been
	 * already validated and pulled.
	 */
	u16 len;
	bool is_linear;
	bool csum_unnecessary;
#endif
};

static inline struct udp_dev_scratch *udp_skb_scratch(struct sk_buff *skb)
{
	return (struct udp_dev_scratch *)&skb->dev_scratch;
}

#if BITS_PER_LONG == 64
static inline unsigned int udp_skb_len(struct sk_buff *skb)
{
	return udp_skb_scratch(skb)->len;
}

static inline bool udp_skb_csum_unnecessary(struct sk_buff *skb)
{
	return udp_skb_scratch(skb)->csum_unnecessary;
}

static inline bool udp_skb_is_linear(struct sk_buff *skb)
{
	return udp_skb_scratch(skb)->is_linear;
}

#else
static inline unsigned int udp_skb_len(struct sk_buff *skb)
{
	return skb->len;
}

static inline bool udp_skb_csum_unnecessary(struct sk_buff *skb)
{
	return skb_csum_unnecessary(skb);
}

static inline bool udp_skb_is_linear(struct sk_buff *skb)
{
	return !skb_is_nonlinear(skb);
}
#endif

static inline int copy_linear_skb(struct sk_buff *skb, int len, int off,
				  struct iov_iter *to)
{
	int n;

	n = copy_to_iter(skb->data + off, len, to);
	if (n == len)
		return 0;

	iov_iter_revert(to, n);
	return -EFAULT;
}

/*
 * 	SNMP statistics for UDP and UDP-Lite
 */
#define UDP_INC_STATS(net, field, is_udplite)		      do { \
	if (is_udplite) SNMP_INC_STATS((net)->mib.udplite_statistics, field);       \
	else		SNMP_INC_STATS((net)->mib.udp_statistics, field);  }  while(0)
#define __UDP_INC_STATS(net, field, is_udplite) 	      do { \
	if (is_udplite) __SNMP_INC_STATS((net)->mib.udplite_statistics, field);         \
	else		__SNMP_INC_STATS((net)->mib.udp_statistics, field);    }  while(0)

#define __UDP6_INC_STATS(net, field, is_udplite)	    do { \
	if (is_udplite) __SNMP_INC_STATS((net)->mib.udplite_stats_in6, field);\
	else		__SNMP_INC_STATS((net)->mib.udp_stats_in6, field);  \
} while(0)
#define UDP6_INC_STATS(net, field, __lite)		    do { \
	if (__lite) SNMP_INC_STATS((net)->mib.udplite_stats_in6, field);  \
	else	    SNMP_INC_STATS((net)->mib.udp_stats_in6, field);      \
} while(0)

#if IS_ENABLED(CONFIG_IPV6)
#define __UDPX_MIB(sk, ipv4)						\
({									\
	ipv4 ? (IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics :	\
				 sock_net(sk)->mib.udp_statistics) :	\
		(IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_stats_in6 :	\
				 sock_net(sk)->mib.udp_stats_in6);	\
})
#else
#define __UDPX_MIB(sk, ipv4)						\
({									\
	IS_UDPLITE(sk) ? sock_net(sk)->mib.udplite_statistics :		\
			 sock_net(sk)->mib.udp_statistics;		\
})
#endif

#define __UDPX_INC_STATS(sk, field) \
	__SNMP_INC_STATS(__UDPX_MIB(sk, (sk)->sk_family == AF_INET), field)

#ifdef CONFIG_PROC_FS
struct udp_seq_afinfo {
	sa_family_t			family;
	struct udp_table		*udp_table;
};

struct udp_iter_state {
	struct seq_net_private  p;
	int			bucket;
	struct udp_seq_afinfo	*bpf_seq_afinfo;
};

void *udp_seq_start(struct seq_file *seq, loff_t *pos);
void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos);
void udp_seq_stop(struct seq_file *seq, void *v);

extern const struct seq_operations udp_seq_ops;
extern const struct seq_operations udp6_seq_ops;

int udp4_proc_init(void);
void udp4_proc_exit(void);
#endif /* CONFIG_PROC_FS */

int udpv4_offload_init(void);

void udp_init(void);

DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key);
void udp_encap_enable(void);
void udp_encap_disable(void);
#if IS_ENABLED(CONFIG_IPV6)
DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
void udpv6_encap_enable(void);
#endif

static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
					      struct sk_buff *skb, bool ipv4)
{
	netdev_features_t features = NETIF_F_SG;
	struct sk_buff *segs;

	/* Avoid csum recalculation by skb_segment unless userspace explicitly
	 * asks for the final checksum values
	 */
	if (!inet_get_convert_csum(sk))
		features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;

	/* UDP segmentation expects packets of type CHECKSUM_PARTIAL or
	 * CHECKSUM_NONE in __udp_gso_segment. UDP GRO indeed builds partial
	 * packets in udp_gro_complete_segment. As does UDP GSO, verified by
	 * udp_send_skb. But when those packets are looped in dev_loopback_xmit
	 * their ip_summed CHECKSUM_NONE is changed to CHECKSUM_UNNECESSARY.
	 * Reset in this specific case, where PARTIAL is both correct and
	 * required.
	 */
	if (skb->pkt_type == PACKET_LOOPBACK)
		skb->ip_summed = CHECKSUM_PARTIAL;

	/* the GSO CB lays after the UDP one, no need to save and restore any
	 * CB fragment
	 */
	segs = __skb_gso_segment(skb, features, false);
	if (IS_ERR_OR_NULL(segs)) {
		int segs_nr = skb_shinfo(skb)->gso_segs;

		atomic_add(segs_nr, &sk->sk_drops);
		SNMP_ADD_STATS(__UDPX_MIB(sk, ipv4), UDP_MIB_INERRORS, segs_nr);
		kfree_skb(skb);
		return NULL;
	}

	consume_skb(skb);
	return segs;
}

static inline void udp_post_segment_fix_csum(struct sk_buff *skb)
{
	/* UDP-lite can't land here - no GRO */
	WARN_ON_ONCE(UDP_SKB_CB(skb)->partial_cov);

	/* UDP packets generated with UDP_SEGMENT and traversing:
	 *
	 * UDP tunnel(xmit) -> veth (segmentation) -> veth (gro) -> UDP tunnel (rx)
	 *
	 * can reach an UDP socket with CHECKSUM_NONE, because
	 * __iptunnel_pull_header() converts CHECKSUM_PARTIAL into NONE.
	 * SKB_GSO_UDP_L4 or SKB_GSO_FRAGLIST packets with no UDP tunnel will
	 * have a valid checksum, as the GRO engine validates the UDP csum
	 * before the aggregation and nobody strips such info in between.
	 * Instead of adding another check in the tunnel fastpath, we can force
	 * a valid csum after the segmentation.
	 * Additionally fixup the UDP CB.
	 */
	UDP_SKB_CB(skb)->cscov = skb->len;
	if (skb->ip_summed == CHECKSUM_NONE && !skb->csum_valid)
		skb->csum_valid = 1;
}

#ifdef CONFIG_BPF_SYSCALL
struct sk_psock;
struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock);
int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
#endif

#endif	/* _UDP_H */