xref: /kernel/linux/linux-5.10/net/dccp/dccp.h (revision 8c2ecf20)
1/* SPDX-License-Identifier: GPL-2.0-only */
2#ifndef _DCCP_H
3#define _DCCP_H
4/*
5 *  net/dccp/dccp.h
6 *
7 *  An implementation of the DCCP protocol
8 *  Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br>
9 *  Copyright (c) 2005-6 Ian McDonald <ian.mcdonald@jandi.co.nz>
10 */
11
12#include <linux/dccp.h>
13#include <linux/ktime.h>
14#include <net/snmp.h>
15#include <net/sock.h>
16#include <net/tcp.h>
17#include "ackvec.h"
18
19/*
20 * 	DCCP - specific warning and debugging macros.
21 */
22#define DCCP_WARN(fmt, ...)						\
23	net_warn_ratelimited("%s: " fmt, __func__, ##__VA_ARGS__)
24#define DCCP_CRIT(fmt, a...) printk(KERN_CRIT fmt " at %s:%d/%s()\n", ##a, \
25					 __FILE__, __LINE__, __func__)
26#define DCCP_BUG(a...)       do { DCCP_CRIT("BUG: " a); dump_stack(); } while(0)
27#define DCCP_BUG_ON(cond)    do { if (unlikely((cond) != 0))		   \
28				     DCCP_BUG("\"%s\" holds (exception!)", \
29					      __stringify(cond));          \
30			     } while (0)
31
32#define DCCP_PRINTK(enable, fmt, args...)	do { if (enable)	     \
33							printk(fmt, ##args); \
34						} while(0)
35#define DCCP_PR_DEBUG(enable, fmt, a...)	DCCP_PRINTK(enable, KERN_DEBUG \
36						  "%s: " fmt, __func__, ##a)
37
38#ifdef CONFIG_IP_DCCP_DEBUG
39extern bool dccp_debug;
40#define dccp_pr_debug(format, a...)	  DCCP_PR_DEBUG(dccp_debug, format, ##a)
41#define dccp_pr_debug_cat(format, a...)   DCCP_PRINTK(dccp_debug, format, ##a)
42#define dccp_debug(fmt, a...)		  dccp_pr_debug_cat(KERN_DEBUG fmt, ##a)
43#else
44#define dccp_pr_debug(format, a...)	  do {} while (0)
45#define dccp_pr_debug_cat(format, a...)	  do {} while (0)
46#define dccp_debug(format, a...)	  do {} while (0)
47#endif
48
49extern struct inet_hashinfo dccp_hashinfo;
50
51DECLARE_PER_CPU(unsigned int, dccp_orphan_count);
52
53void dccp_time_wait(struct sock *sk, int state, int timeo);
54
55/*
56 *  Set safe upper bounds for header and option length. Since Data Offset is 8
57 *  bits (RFC 4340, sec. 5.1), the total header length can never be more than
58 *  4 * 255 = 1020 bytes. The largest possible header length is 28 bytes (X=1):
59 *    - DCCP-Response with ACK Subheader and 4 bytes of Service code      OR
60 *    - DCCP-Reset    with ACK Subheader and 4 bytes of Reset Code fields
61 *  Hence a safe upper bound for the maximum option length is 1020-28 = 992
62 */
63#define MAX_DCCP_SPECIFIC_HEADER (255 * sizeof(uint32_t))
64#define DCCP_MAX_PACKET_HDR 28
65#define DCCP_MAX_OPT_LEN (MAX_DCCP_SPECIFIC_HEADER - DCCP_MAX_PACKET_HDR)
66#define MAX_DCCP_HEADER (MAX_DCCP_SPECIFIC_HEADER + MAX_HEADER)
67
68/* Upper bound for initial feature-negotiation overhead (padded to 32 bits) */
69#define DCCP_FEATNEG_OVERHEAD	 (32 * sizeof(uint32_t))
70
71#define DCCP_TIMEWAIT_LEN (60 * HZ) /* how long to wait to destroy TIME-WAIT
72				     * state, about 60 seconds */
73
74/* RFC 1122, 4.2.3.1 initial RTO value */
75#define DCCP_TIMEOUT_INIT ((unsigned int)(3 * HZ))
76
77/*
78 * The maximum back-off value for retransmissions. This is needed for
79 *  - retransmitting client-Requests (sec. 8.1.1),
80 *  - retransmitting Close/CloseReq when closing (sec. 8.3),
81 *  - feature-negotiation retransmission (sec. 6.6.3),
82 *  - Acks in client-PARTOPEN state (sec. 8.1.5).
83 */
84#define DCCP_RTO_MAX ((unsigned int)(64 * HZ))
85
86/*
87 * RTT sampling: sanity bounds and fallback RTT value from RFC 4340, section 3.4
88 */
89#define DCCP_SANE_RTT_MIN	100
90#define DCCP_FALLBACK_RTT	(USEC_PER_SEC / 5)
91#define DCCP_SANE_RTT_MAX	(3 * USEC_PER_SEC)
92
93/* sysctl variables for DCCP */
94extern int  sysctl_dccp_request_retries;
95extern int  sysctl_dccp_retries1;
96extern int  sysctl_dccp_retries2;
97extern int  sysctl_dccp_tx_qlen;
98extern int  sysctl_dccp_sync_ratelimit;
99
100/*
101 *	48-bit sequence number arithmetic (signed and unsigned)
102 */
103#define INT48_MIN	  0x800000000000LL		/* 2^47	    */
104#define UINT48_MAX	  0xFFFFFFFFFFFFLL		/* 2^48 - 1 */
105#define COMPLEMENT48(x)	 (0x1000000000000LL - (x))	/* 2^48 - x */
106#define TO_SIGNED48(x)	 (((x) < INT48_MIN)? (x) : -COMPLEMENT48( (x)))
107#define TO_UNSIGNED48(x) (((x) >= 0)?	     (x) :  COMPLEMENT48(-(x)))
108#define ADD48(a, b)	 (((a) + (b)) & UINT48_MAX)
109#define SUB48(a, b)	 ADD48((a), COMPLEMENT48(b))
110
111static inline void dccp_inc_seqno(u64 *seqno)
112{
113	*seqno = ADD48(*seqno, 1);
114}
115
116/* signed mod-2^48 distance: pos. if seqno1 < seqno2, neg. if seqno1 > seqno2 */
117static inline s64 dccp_delta_seqno(const u64 seqno1, const u64 seqno2)
118{
119	u64 delta = SUB48(seqno2, seqno1);
120
121	return TO_SIGNED48(delta);
122}
123
124/* is seq1 < seq2 ? */
125static inline int before48(const u64 seq1, const u64 seq2)
126{
127	return (s64)((seq2 << 16) - (seq1 << 16)) > 0;
128}
129
130/* is seq1 > seq2 ? */
131#define after48(seq1, seq2)	before48(seq2, seq1)
132
133/* is seq2 <= seq1 <= seq3 ? */
134static inline int between48(const u64 seq1, const u64 seq2, const u64 seq3)
135{
136	return (seq3 << 16) - (seq2 << 16) >= (seq1 << 16) - (seq2 << 16);
137}
138
139static inline u64 max48(const u64 seq1, const u64 seq2)
140{
141	return after48(seq1, seq2) ? seq1 : seq2;
142}
143
144/**
145 * dccp_loss_count - Approximate the number of lost data packets in a burst loss
146 * @s1:  last known sequence number before the loss ('hole')
147 * @s2:  first sequence number seen after the 'hole'
148 * @ndp: NDP count on packet with sequence number @s2
149 */
150static inline u64 dccp_loss_count(const u64 s1, const u64 s2, const u64 ndp)
151{
152	s64 delta = dccp_delta_seqno(s1, s2);
153
154	WARN_ON(delta < 0);
155	delta -= ndp + 1;
156
157	return delta > 0 ? delta : 0;
158}
159
160/**
161 * dccp_loss_free - Evaluate condition for data loss from RFC 4340, 7.7.1
162 */
163static inline bool dccp_loss_free(const u64 s1, const u64 s2, const u64 ndp)
164{
165	return dccp_loss_count(s1, s2, ndp) == 0;
166}
167
168enum {
169	DCCP_MIB_NUM = 0,
170	DCCP_MIB_ACTIVEOPENS,			/* ActiveOpens */
171	DCCP_MIB_ESTABRESETS,			/* EstabResets */
172	DCCP_MIB_CURRESTAB,			/* CurrEstab */
173	DCCP_MIB_OUTSEGS,			/* OutSegs */
174	DCCP_MIB_OUTRSTS,
175	DCCP_MIB_ABORTONTIMEOUT,
176	DCCP_MIB_TIMEOUTS,
177	DCCP_MIB_ABORTFAILED,
178	DCCP_MIB_PASSIVEOPENS,
179	DCCP_MIB_ATTEMPTFAILS,
180	DCCP_MIB_OUTDATAGRAMS,
181	DCCP_MIB_INERRS,
182	DCCP_MIB_OPTMANDATORYERROR,
183	DCCP_MIB_INVALIDOPT,
184	__DCCP_MIB_MAX
185};
186
187#define DCCP_MIB_MAX	__DCCP_MIB_MAX
188struct dccp_mib {
189	unsigned long	mibs[DCCP_MIB_MAX];
190};
191
192DECLARE_SNMP_STAT(struct dccp_mib, dccp_statistics);
193#define DCCP_INC_STATS(field)	SNMP_INC_STATS(dccp_statistics, field)
194#define __DCCP_INC_STATS(field)	__SNMP_INC_STATS(dccp_statistics, field)
195#define DCCP_DEC_STATS(field)	SNMP_DEC_STATS(dccp_statistics, field)
196
197/*
198 * 	Checksumming routines
199 */
200static inline unsigned int dccp_csum_coverage(const struct sk_buff *skb)
201{
202	const struct dccp_hdr* dh = dccp_hdr(skb);
203
204	if (dh->dccph_cscov == 0)
205		return skb->len;
206	return (dh->dccph_doff + dh->dccph_cscov - 1) * sizeof(u32);
207}
208
209static inline void dccp_csum_outgoing(struct sk_buff *skb)
210{
211	unsigned int cov = dccp_csum_coverage(skb);
212
213	if (cov >= skb->len)
214		dccp_hdr(skb)->dccph_cscov = 0;
215
216	skb->csum = skb_checksum(skb, 0, (cov > skb->len)? skb->len : cov, 0);
217}
218
219void dccp_v4_send_check(struct sock *sk, struct sk_buff *skb);
220
221int dccp_retransmit_skb(struct sock *sk);
222
223void dccp_send_ack(struct sock *sk);
224void dccp_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
225			 struct request_sock *rsk);
226
227void dccp_send_sync(struct sock *sk, const u64 seq,
228		    const enum dccp_pkt_type pkt_type);
229
230/*
231 * TX Packet Dequeueing Interface
232 */
233void dccp_qpolicy_push(struct sock *sk, struct sk_buff *skb);
234bool dccp_qpolicy_full(struct sock *sk);
235void dccp_qpolicy_drop(struct sock *sk, struct sk_buff *skb);
236struct sk_buff *dccp_qpolicy_top(struct sock *sk);
237struct sk_buff *dccp_qpolicy_pop(struct sock *sk);
238bool dccp_qpolicy_param_ok(struct sock *sk, __be32 param);
239
240/*
241 * TX Packet Output and TX Timers
242 */
243void dccp_write_xmit(struct sock *sk);
244void dccp_write_space(struct sock *sk);
245void dccp_flush_write_queue(struct sock *sk, long *time_budget);
246
247void dccp_init_xmit_timers(struct sock *sk);
248static inline void dccp_clear_xmit_timers(struct sock *sk)
249{
250	inet_csk_clear_xmit_timers(sk);
251}
252
253unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu);
254
255const char *dccp_packet_name(const int type);
256
257void dccp_set_state(struct sock *sk, const int state);
258void dccp_done(struct sock *sk);
259
260int dccp_reqsk_init(struct request_sock *rq, struct dccp_sock const *dp,
261		    struct sk_buff const *skb);
262
263int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
264
265struct sock *dccp_create_openreq_child(const struct sock *sk,
266				       const struct request_sock *req,
267				       const struct sk_buff *skb);
268
269int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb);
270
271struct sock *dccp_v4_request_recv_sock(const struct sock *sk, struct sk_buff *skb,
272				       struct request_sock *req,
273				       struct dst_entry *dst,
274				       struct request_sock *req_unhash,
275				       bool *own_req);
276struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
277			    struct request_sock *req);
278
279int dccp_child_process(struct sock *parent, struct sock *child,
280		       struct sk_buff *skb);
281int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
282			   struct dccp_hdr *dh, unsigned int len);
283int dccp_rcv_established(struct sock *sk, struct sk_buff *skb,
284			 const struct dccp_hdr *dh, const unsigned int len);
285
286void dccp_destruct_common(struct sock *sk);
287int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized);
288void dccp_destroy_sock(struct sock *sk);
289
290void dccp_close(struct sock *sk, long timeout);
291struct sk_buff *dccp_make_response(const struct sock *sk, struct dst_entry *dst,
292				   struct request_sock *req);
293
294int dccp_connect(struct sock *sk);
295int dccp_disconnect(struct sock *sk, int flags);
296int dccp_getsockopt(struct sock *sk, int level, int optname,
297		    char __user *optval, int __user *optlen);
298int dccp_setsockopt(struct sock *sk, int level, int optname,
299		    sockptr_t optval, unsigned int optlen);
300int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg);
301int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
302int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
303		 int flags, int *addr_len);
304void dccp_shutdown(struct sock *sk, int how);
305int inet_dccp_listen(struct socket *sock, int backlog);
306__poll_t dccp_poll(struct file *file, struct socket *sock,
307		       poll_table *wait);
308int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
309void dccp_req_err(struct sock *sk, u64 seq);
310
311struct sk_buff *dccp_ctl_make_reset(struct sock *sk, struct sk_buff *skb);
312int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code);
313void dccp_send_close(struct sock *sk, const int active);
314int dccp_invalid_packet(struct sk_buff *skb);
315u32 dccp_sample_rtt(struct sock *sk, long delta);
316
317static inline bool dccp_bad_service_code(const struct sock *sk,
318					const __be32 service)
319{
320	const struct dccp_sock *dp = dccp_sk(sk);
321
322	if (dp->dccps_service == service)
323		return false;
324	return !dccp_list_has_service(dp->dccps_service_list, service);
325}
326
327/**
328 * dccp_skb_cb  -  DCCP per-packet control information
329 * @dccpd_type: one of %dccp_pkt_type (or unknown)
330 * @dccpd_ccval: CCVal field (5.1), see e.g. RFC 4342, 8.1
331 * @dccpd_reset_code: one of %dccp_reset_codes
332 * @dccpd_reset_data: Data1..3 fields (depend on @dccpd_reset_code)
333 * @dccpd_opt_len: total length of all options (5.8) in the packet
334 * @dccpd_seq: sequence number
335 * @dccpd_ack_seq: acknowledgment number subheader field value
336 *
337 * This is used for transmission as well as for reception.
338 */
339struct dccp_skb_cb {
340	union {
341		struct inet_skb_parm	h4;
342#if IS_ENABLED(CONFIG_IPV6)
343		struct inet6_skb_parm	h6;
344#endif
345	} header;
346	__u8  dccpd_type:4;
347	__u8  dccpd_ccval:4;
348	__u8  dccpd_reset_code,
349	      dccpd_reset_data[3];
350	__u16 dccpd_opt_len;
351	__u64 dccpd_seq;
352	__u64 dccpd_ack_seq;
353};
354
355#define DCCP_SKB_CB(__skb) ((struct dccp_skb_cb *)&((__skb)->cb[0]))
356
357/* RFC 4340, sec. 7.7 */
358static inline int dccp_non_data_packet(const struct sk_buff *skb)
359{
360	const __u8 type = DCCP_SKB_CB(skb)->dccpd_type;
361
362	return type == DCCP_PKT_ACK	 ||
363	       type == DCCP_PKT_CLOSE	 ||
364	       type == DCCP_PKT_CLOSEREQ ||
365	       type == DCCP_PKT_RESET	 ||
366	       type == DCCP_PKT_SYNC	 ||
367	       type == DCCP_PKT_SYNCACK;
368}
369
370/* RFC 4340, sec. 7.7 */
371static inline int dccp_data_packet(const struct sk_buff *skb)
372{
373	const __u8 type = DCCP_SKB_CB(skb)->dccpd_type;
374
375	return type == DCCP_PKT_DATA	 ||
376	       type == DCCP_PKT_DATAACK  ||
377	       type == DCCP_PKT_REQUEST  ||
378	       type == DCCP_PKT_RESPONSE;
379}
380
381static inline int dccp_packet_without_ack(const struct sk_buff *skb)
382{
383	const __u8 type = DCCP_SKB_CB(skb)->dccpd_type;
384
385	return type == DCCP_PKT_DATA || type == DCCP_PKT_REQUEST;
386}
387
388#define DCCP_PKT_WITHOUT_ACK_SEQ (UINT48_MAX << 2)
389
390static inline void dccp_hdr_set_seq(struct dccp_hdr *dh, const u64 gss)
391{
392	struct dccp_hdr_ext *dhx = (struct dccp_hdr_ext *)((void *)dh +
393							   sizeof(*dh));
394	dh->dccph_seq2 = 0;
395	dh->dccph_seq = htons((gss >> 32) & 0xfffff);
396	dhx->dccph_seq_low = htonl(gss & 0xffffffff);
397}
398
399static inline void dccp_hdr_set_ack(struct dccp_hdr_ack_bits *dhack,
400				    const u64 gsr)
401{
402	dhack->dccph_reserved1 = 0;
403	dhack->dccph_ack_nr_high = htons(gsr >> 32);
404	dhack->dccph_ack_nr_low  = htonl(gsr & 0xffffffff);
405}
406
407static inline void dccp_update_gsr(struct sock *sk, u64 seq)
408{
409	struct dccp_sock *dp = dccp_sk(sk);
410
411	if (after48(seq, dp->dccps_gsr))
412		dp->dccps_gsr = seq;
413	/* Sequence validity window depends on remote Sequence Window (7.5.1) */
414	dp->dccps_swl = SUB48(ADD48(dp->dccps_gsr, 1), dp->dccps_r_seq_win / 4);
415	/*
416	 * Adjust SWL so that it is not below ISR. In contrast to RFC 4340,
417	 * 7.5.1 we perform this check beyond the initial handshake: W/W' are
418	 * always > 32, so for the first W/W' packets in the lifetime of a
419	 * connection we always have to adjust SWL.
420	 * A second reason why we are doing this is that the window depends on
421	 * the feature-remote value of Sequence Window: nothing stops the peer
422	 * from updating this value while we are busy adjusting SWL for the
423	 * first W packets (we would have to count from scratch again then).
424	 * Therefore it is safer to always make sure that the Sequence Window
425	 * is not artificially extended by a peer who grows SWL downwards by
426	 * continually updating the feature-remote Sequence-Window.
427	 * If sequence numbers wrap it is bad luck. But that will take a while
428	 * (48 bit), and this measure prevents Sequence-number attacks.
429	 */
430	if (before48(dp->dccps_swl, dp->dccps_isr))
431		dp->dccps_swl = dp->dccps_isr;
432	dp->dccps_swh = ADD48(dp->dccps_gsr, (3 * dp->dccps_r_seq_win) / 4);
433}
434
435static inline void dccp_update_gss(struct sock *sk, u64 seq)
436{
437	struct dccp_sock *dp = dccp_sk(sk);
438
439	dp->dccps_gss = seq;
440	/* Ack validity window depends on local Sequence Window value (7.5.1) */
441	dp->dccps_awl = SUB48(ADD48(dp->dccps_gss, 1), dp->dccps_l_seq_win);
442	/* Adjust AWL so that it is not below ISS - see comment above for SWL */
443	if (before48(dp->dccps_awl, dp->dccps_iss))
444		dp->dccps_awl = dp->dccps_iss;
445	dp->dccps_awh = dp->dccps_gss;
446}
447
448static inline int dccp_ackvec_pending(const struct sock *sk)
449{
450	return dccp_sk(sk)->dccps_hc_rx_ackvec != NULL &&
451	       !dccp_ackvec_is_empty(dccp_sk(sk)->dccps_hc_rx_ackvec);
452}
453
454static inline int dccp_ack_pending(const struct sock *sk)
455{
456	return dccp_ackvec_pending(sk) || inet_csk_ack_scheduled(sk);
457}
458
459int dccp_feat_signal_nn_change(struct sock *sk, u8 feat, u64 nn_val);
460int dccp_feat_finalise_settings(struct dccp_sock *dp);
461int dccp_feat_server_ccid_dependencies(struct dccp_request_sock *dreq);
462int dccp_feat_insert_opts(struct dccp_sock*, struct dccp_request_sock*,
463			  struct sk_buff *skb);
464int dccp_feat_activate_values(struct sock *sk, struct list_head *fn);
465void dccp_feat_list_purge(struct list_head *fn_list);
466
467int dccp_insert_options(struct sock *sk, struct sk_buff *skb);
468int dccp_insert_options_rsk(struct dccp_request_sock *, struct sk_buff *);
469u32 dccp_timestamp(void);
470void dccp_timestamping_init(void);
471int dccp_insert_option(struct sk_buff *skb, unsigned char option,
472		       const void *value, unsigned char len);
473
474#ifdef CONFIG_SYSCTL
475int dccp_sysctl_init(void);
476void dccp_sysctl_exit(void);
477#else
478static inline int dccp_sysctl_init(void)
479{
480	return 0;
481}
482
483static inline void dccp_sysctl_exit(void)
484{
485}
486#endif
487
488#endif /* _DCCP_H */
489