aboutsummaryrefslogtreecommitdiff
path: root/net/rxrpc/peer_event.c
blob: 81a7869325a625c9c1ba45fed77e25ee23fe738a (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
/* Peer event handling, typically ICMP messages.
 *
 * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 */

#include <linux/module.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/errqueue.h>
#include <linux/udp.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/icmp.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include <net/ip.h>
#include "ar-internal.h"

static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
static void rxrpc_distribute_error(struct rxrpc_peer *, int,
				   enum rxrpc_call_completion);

/*
 * Find the peer associated with an ICMP packet.
 */
static struct rxrpc_peer *rxrpc_lookup_peer_icmp_rcu(struct rxrpc_local *local,
						     const struct sk_buff *skb,
						     struct sockaddr_rxrpc *srx)
{
	struct sock_exterr_skb *serr = SKB_EXT_ERR(skb);

	_enter("");

	memset(srx, 0, sizeof(*srx));
	srx->transport_type = local->srx.transport_type;
	srx->transport_len = local->srx.transport_len;
	srx->transport.family = local->srx.transport.family;

	/* Can we see an ICMP4 packet on an ICMP6 listening socket?  and vice
	 * versa?
	 */
	switch (srx->transport.family) {
	case AF_INET:
		srx->transport_len = sizeof(srx->transport.sin);
		srx->transport.family = AF_INET;
		srx->transport.sin.sin_port = serr->port;
		switch (serr->ee.ee_origin) {
		case SO_EE_ORIGIN_ICMP:
			_net("Rx ICMP");
			memcpy(&srx->transport.sin.sin_addr,
			       skb_network_header(skb) + serr->addr_offset,
			       sizeof(struct in_addr));
			break;
		case SO_EE_ORIGIN_ICMP6:
			_net("Rx ICMP6 on v4 sock");
			memcpy(&srx->transport.sin.sin_addr,
			       skb_network_header(skb) + serr->addr_offset + 12,
			       sizeof(struct in_addr));
			break;
		default:
			memcpy(&srx->transport.sin.sin_addr, &ip_hdr(skb)->saddr,
			       sizeof(struct in_addr));
			break;
		}
		break;

#ifdef CONFIG_AF_RXRPC_IPV6
	case AF_INET6:
		switch (serr->ee.ee_origin) {
		case SO_EE_ORIGIN_ICMP6:
			_net("Rx ICMP6");
			srx->transport.sin6.sin6_port = serr->port;
			memcpy(&srx->transport.sin6.sin6_addr,
			       skb_network_header(skb) + serr->addr_offset,
			       sizeof(struct in6_addr));
			break;
		case SO_EE_ORIGIN_ICMP:
			_net("Rx ICMP on v6 sock");
			srx->transport_len = sizeof(srx->transport.sin);
			srx->transport.family = AF_INET;
			srx->transport.sin.sin_port = serr->port;
			memcpy(&srx->transport.sin.sin_addr,
			       skb_network_header(skb) + serr->addr_offset,
			       sizeof(struct in_addr));
			break;
		default:
			memcpy(&srx->transport.sin6.sin6_addr,
			       &ipv6_hdr(skb)->saddr,
			       sizeof(struct in6_addr));
			break;
		}
		break;
#endif

	default:
		BUG();
	}

	return rxrpc_lookup_peer_rcu(local, srx);
}

/*
 * Handle an MTU/fragmentation problem.
 */
static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, struct sock_exterr_skb *serr)
{
	u32 mtu = serr->ee.ee_info;

	_net("Rx ICMP Fragmentation Needed (%d)", mtu);

	/* wind down the local interface MTU */
	if (mtu > 0 && peer->if_mtu == 65535 && mtu < peer->if_mtu) {
		peer->if_mtu = mtu;
		_net("I/F MTU %u", mtu);
	}

	if (mtu == 0) {
		/* they didn't give us a size, estimate one */
		mtu = peer->if_mtu;
		if (mtu > 1500) {
			mtu >>= 1;
			if (mtu < 1500)
				mtu = 1500;
		} else {
			mtu -= 100;
			if (mtu < peer->hdrsize)
				mtu = peer->hdrsize + 4;
		}
	}

	if (mtu < peer->mtu) {
		spin_lock_bh(&peer->lock);
		peer->mtu = mtu;
		peer->maxdata = peer->mtu - peer->hdrsize;
		spin_unlock_bh(&peer->lock);
		_net("Net MTU %u (maxdata %u)",
		     peer->mtu, peer->maxdata);
	}
}

/*
 * Handle an error received on the local endpoint.
 */
void rxrpc_error_report(struct sock *sk)
{
	struct sock_exterr_skb *serr;
	struct sockaddr_rxrpc srx;
	struct rxrpc_local *local = sk->sk_user_data;
	struct rxrpc_peer *peer;
	struct sk_buff *skb;

	_enter("%p{%d}", sk, local->debug_id);

	skb = sock_dequeue_err_skb(sk);
	if (!skb) {
		_leave("UDP socket errqueue empty");
		return;
	}
	rxrpc_new_skb(skb, rxrpc_skb_rx_received);
	serr = SKB_EXT_ERR(skb);
	if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
		_leave("UDP empty message");
		rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
		return;
	}

	rcu_read_lock();
	peer = rxrpc_lookup_peer_icmp_rcu(local, skb, &srx);
	if (peer && !rxrpc_get_peer_maybe(peer))
		peer = NULL;
	if (!peer) {
		rcu_read_unlock();
		rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
		_leave(" [no peer]");
		return;
	}

	trace_rxrpc_rx_icmp(peer, &serr->ee, &srx);

	if ((serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
	     serr->ee.ee_type == ICMP_DEST_UNREACH &&
	     serr->ee.ee_code == ICMP_FRAG_NEEDED)) {
		rxrpc_adjust_mtu(peer, serr);
		rcu_read_unlock();
		rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
		rxrpc_put_peer(peer);
		_leave(" [MTU update]");
		return;
	}

	rxrpc_store_error(peer, serr);
	rcu_read_unlock();
	rxrpc_free_skb(skb, rxrpc_skb_rx_freed);

	_leave("");
}

/*
 * Map an error report to error codes on the peer record.
 */
static void rxrpc_store_error(struct rxrpc_peer *peer,
			      struct sock_exterr_skb *serr)
{
	enum rxrpc_call_completion compl = RXRPC_CALL_NETWORK_ERROR;
	struct sock_extended_err *ee;
	int err;

	_enter("");

	ee = &serr->ee;

	err = ee->ee_errno;

	switch (ee->ee_origin) {
	case SO_EE_ORIGIN_ICMP:
		switch (ee->ee_type) {
		case ICMP_DEST_UNREACH:
			switch (ee->ee_code) {
			case ICMP_NET_UNREACH:
				_net("Rx Received ICMP Network Unreachable");
				break;
			case ICMP_HOST_UNREACH:
				_net("Rx Received ICMP Host Unreachable");
				break;
			case ICMP_PORT_UNREACH:
				_net("Rx Received ICMP Port Unreachable");
				break;
			case ICMP_NET_UNKNOWN:
				_net("Rx Received ICMP Unknown Network");
				break;
			case ICMP_HOST_UNKNOWN:
				_net("Rx Received ICMP Unknown Host");
				break;
			default:
				_net("Rx Received ICMP DestUnreach code=%u",
				     ee->ee_code);
				break;
			}
			break;

		case ICMP_TIME_EXCEEDED:
			_net("Rx Received ICMP TTL Exceeded");
			break;

		default:
			_proto("Rx Received ICMP error { type=%u code=%u }",
			       ee->ee_type, ee->ee_code);
			break;
		}
		break;

	case SO_EE_ORIGIN_NONE:
	case SO_EE_ORIGIN_LOCAL:
		_proto("Rx Received local error { error=%d }", err);
		compl = RXRPC_CALL_LOCAL_ERROR;
		break;

	case SO_EE_ORIGIN_ICMP6:
	default:
		_proto("Rx Received error report { orig=%u }", ee->ee_origin);
		break;
	}

	rxrpc_distribute_error(peer, err, compl);
}

/*
 * Distribute an error that occurred on a peer.
 */
static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error,
				   enum rxrpc_call_completion compl)
{
	struct rxrpc_call *call;

	hlist_for_each_entry_rcu(call, &peer->error_targets, error_link) {
		rxrpc_see_call(call);
		if (call->state < RXRPC_CALL_COMPLETE &&
		    rxrpc_set_call_completion(call, compl, 0, -error))
			rxrpc_notify_socket(call);
	}
}

/*
 * Add RTT information to cache.  This is called in softirq mode and has
 * exclusive access to the peer RTT data.
 */
void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why,
			rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial,
			ktime_t send_time, ktime_t resp_time)
{
	struct rxrpc_peer *peer = call->peer;
	s64 rtt;
	u64 sum = peer->rtt_sum, avg;
	u8 cursor = peer->rtt_cursor, usage = peer->rtt_usage;

	rtt = ktime_to_ns(ktime_sub(resp_time, send_time));
	if (rtt < 0)
		return;

	/* Replace the oldest datum in the RTT buffer */
	sum -= peer->rtt_cache[cursor];
	sum += rtt;
	peer->rtt_cache[cursor] = rtt;
	peer->rtt_cursor = (cursor + 1) & (RXRPC_RTT_CACHE_SIZE - 1);
	peer->rtt_sum = sum;
	if (usage < RXRPC_RTT_CACHE_SIZE) {
		usage++;
		peer->rtt_usage = usage;
	}

	/* Now recalculate the average */
	if (usage == RXRPC_RTT_CACHE_SIZE) {
		avg = sum / RXRPC_RTT_CACHE_SIZE;
	} else {
		avg = sum;
		do_div(avg, usage);
	}

	peer->rtt = avg;
	trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, rtt,
			   usage, avg);
}

/*
 * Perform keep-alive pings.
 */
static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet,
					  struct list_head *collector,
					  time64_t base,
					  u8 cursor)
{
	struct rxrpc_peer *peer;
	const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
	time64_t keepalive_at;
	int slot;

	spin_lock_bh(&rxnet->peer_hash_lock);

	while (!list_empty(collector)) {
		peer = list_entry(collector->next,
				  struct rxrpc_peer, keepalive_link);

		list_del_init(&peer->keepalive_link);
		if (!rxrpc_get_peer_maybe(peer))
			continue;

		spin_unlock_bh(&rxnet->peer_hash_lock);

		keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME;
		slot = keepalive_at - base;
		_debug("%02x peer %u t=%d {%pISp}",
		       cursor, peer->debug_id, slot, &peer->srx.transport);

		if (keepalive_at <= base ||
		    keepalive_at > base + RXRPC_KEEPALIVE_TIME) {
			rxrpc_send_keepalive(peer);
			slot = RXRPC_KEEPALIVE_TIME;
		}

		/* A transmission to this peer occurred since last we examined
		 * it so put it into the appropriate future bucket.
		 */
		slot += cursor;
		slot &= mask;
		spin_lock_bh(&rxnet->peer_hash_lock);
		list_add_tail(&peer->keepalive_link,
			      &rxnet->peer_keepalive[slot & mask]);
		rxrpc_put_peer(peer);
	}

	spin_unlock_bh(&rxnet->peer_hash_lock);
}

/*
 * Perform keep-alive pings with VERSION packets to keep any NAT alive.
 */
void rxrpc_peer_keepalive_worker(struct work_struct *work)
{
	struct rxrpc_net *rxnet =
		container_of(work, struct rxrpc_net, peer_keepalive_work);
	const u8 mask = ARRAY_SIZE(rxnet->peer_keepalive) - 1;
	time64_t base, now, delay;
	u8 cursor, stop;
	LIST_HEAD(collector);

	now = ktime_get_seconds();
	base = rxnet->peer_keepalive_base;
	cursor = rxnet->peer_keepalive_cursor;
	_enter("%lld,%u", base - now, cursor);

	if (!rxnet->live)
		return;

	/* Remove to a temporary list all the peers that are currently lodged
	 * in expired buckets plus all new peers.
	 *
	 * Everything in the bucket at the cursor is processed this
	 * second; the bucket at cursor + 1 goes at now + 1s and so
	 * on...
	 */
	spin_lock_bh(&rxnet->peer_hash_lock);
	list_splice_init(&rxnet->peer_keepalive_new, &collector);

	stop = cursor + ARRAY_SIZE(rxnet->peer_keepalive);
	while (base <= now && (s8)(cursor - stop) < 0) {
		list_splice_tail_init(&rxnet->peer_keepalive[cursor & mask],
				      &collector);
		base++;
		cursor++;
	}

	base = now;
	spin_unlock_bh(&rxnet->peer_hash_lock);

	rxnet->peer_keepalive_base = base;
	rxnet->peer_keepalive_cursor = cursor;
	rxrpc_peer_keepalive_dispatch(rxnet, &collector, base, cursor);
	ASSERT(list_empty(&collector));

	/* Schedule the timer for the next occupied timeslot. */
	cursor = rxnet->peer_keepalive_cursor;
	stop = cursor + RXRPC_KEEPALIVE_TIME - 1;
	for (; (s8)(cursor - stop) < 0; cursor++) {
		if (!list_empty(&rxnet->peer_keepalive[cursor & mask]))
			break;
		base++;
	}

	now = ktime_get_seconds();
	delay = base - now;
	if (delay < 1)
		delay = 1;
	delay *= HZ;
	if (rxnet->live)
		timer_reduce(&rxnet->peer_keepalive_timer, jiffies + delay);

	_leave("");
}