peer_event.c 8.3 KB
Newer Older
1
/* Peer event handling, typically ICMP messages.
2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24
 *
 * 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"

25 26
static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);

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
/*
 * 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 sock_exterr_skb *serr = SKB_EXT_ERR(skb);
	struct sockaddr_rxrpc srx;

	_enter("");

	memset(&srx, 0, sizeof(srx));
	srx.transport_type = local->srx.transport_type;
	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.sin.sin_port = serr->port;
		srx.transport_len = sizeof(struct sockaddr_in);
		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;

69
#ifdef CONFIG_AF_RXRPC_IPV6
D
David Howells 已提交
70 71 72 73 74 75 76 77 78 79 80 81
	case AF_INET6:
		srx.transport.sin6.sin6_port = serr->port;
		srx.transport_len = sizeof(struct sockaddr_in6);
		switch (serr->ee.ee_origin) {
		case SO_EE_ORIGIN_ICMP6:
			_net("Rx ICMP6");
			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");
82
			memcpy(srx.transport.sin6.sin6_addr.s6_addr + 12,
D
David Howells 已提交
83 84 85 86 87 88 89 90 91 92
			       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;
93
#endif
D
David Howells 已提交
94

95 96 97 98 99 100 101
	default:
		BUG();
	}

	return rxrpc_lookup_peer_rcu(local, &srx);
}

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
/*
 * 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);
	}
}

141
/*
142
 * Handle an error received on the local endpoint.
143
 */
144
void rxrpc_error_report(struct sock *sk)
145 146 147 148 149 150 151 152
{
	struct sock_exterr_skb *serr;
	struct rxrpc_local *local = sk->sk_user_data;
	struct rxrpc_peer *peer;
	struct sk_buff *skb;

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

153
	skb = sock_dequeue_err_skb(sk);
154 155 156 157
	if (!skb) {
		_leave("UDP socket errqueue empty");
		return;
	}
D
David Howells 已提交
158
	rxrpc_new_skb(skb, rxrpc_skb_rx_received);
159 160
	serr = SKB_EXT_ERR(skb);
	if (!skb->len && serr->ee.ee_origin == SO_EE_ORIGIN_TIMESTAMPING) {
161
		_leave("UDP empty message");
D
David Howells 已提交
162
		rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
163 164
		return;
	}
165

166 167 168 169 170 171
	rcu_read_lock();
	peer = rxrpc_lookup_peer_icmp_rcu(local, skb);
	if (peer && !rxrpc_get_peer_maybe(peer))
		peer = NULL;
	if (!peer) {
		rcu_read_unlock();
D
David Howells 已提交
172
		rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
173 174 175 176
		_leave(" [no peer]");
		return;
	}

177 178 179 180
	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);
181
		rcu_read_unlock();
D
David Howells 已提交
182
		rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
183 184 185
		rxrpc_put_peer(peer);
		_leave(" [MTU update]");
		return;
186 187
	}

188
	rxrpc_store_error(peer, serr);
189
	rcu_read_unlock();
D
David Howells 已提交
190
	rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
191

192 193
	/* The ref we obtained is passed off to the work item */
	rxrpc_queue_work(&peer->error_distributor);
194 195 196 197
	_leave("");
}

/*
198
 * Map an error report to error codes on the peer record.
199
 */
200 201
static void rxrpc_store_error(struct rxrpc_peer *peer,
			      struct sock_exterr_skb *serr)
202 203
{
	struct sock_extended_err *ee;
204
	int err;
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

	_enter("");

	ee = &serr->ee;

	_net("Rx Error o=%d t=%d c=%d e=%d",
	     ee->ee_origin, ee->ee_type, ee->ee_code, ee->ee_errno);

	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;

253
	case SO_EE_ORIGIN_NONE:
254
	case SO_EE_ORIGIN_LOCAL:
255
		_proto("Rx Received local error { error=%d }", err);
256
		err += RXRPC_LOCAL_ERROR_OFFSET;
257 258 259 260
		break;

	case SO_EE_ORIGIN_ICMP6:
	default:
261
		_proto("Rx Received error report { orig=%u }", ee->ee_origin);
262 263 264
		break;
	}

265 266 267 268 269 270 271 272 273 274 275
	peer->error_report = err;
}

/*
 * Distribute an error that occurred on a peer
 */
void rxrpc_peer_error_distributor(struct work_struct *work)
{
	struct rxrpc_peer *peer =
		container_of(work, struct rxrpc_peer, error_distributor);
	struct rxrpc_call *call;
276 277
	enum rxrpc_call_completion compl;
	int error;
278 279

	_enter("");
280

281 282 283 284 285 286 287
	error = READ_ONCE(peer->error_report);
	if (error < RXRPC_LOCAL_ERROR_OFFSET) {
		compl = RXRPC_CALL_NETWORK_ERROR;
	} else {
		compl = RXRPC_CALL_LOCAL_ERROR;
		error -= RXRPC_LOCAL_ERROR_OFFSET;
	}
288

289
	_debug("ISSUE ERROR %s %d", rxrpc_call_completions[compl], error);
290

291
	spin_lock_bh(&peer->lock);
292

293 294 295 296
	while (!hlist_empty(&peer->error_targets)) {
		call = hlist_entry(peer->error_targets.first,
				   struct rxrpc_call, error_link);
		hlist_del_init(&call->error_link);
D
David Howells 已提交
297
		rxrpc_see_call(call);
298

299 300
		if (rxrpc_set_call_completion(call, compl, 0, error))
			rxrpc_notify_socket(call);
301 302
	}

303
	spin_unlock_bh(&peer->lock);
304

305
	rxrpc_put_peer(peer);
306 307
	_leave("");
}
D
David Howells 已提交
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

/*
 * 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);
}