ar-error.c 5.76 KB
Newer Older
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
/* Error message handling (ICMP)
 *
 * 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"

/*
 * handle an error received on the local endpoint
 */
void rxrpc_UDP_error_report(struct sock *sk)
{
	struct sock_exterr_skb *serr;
	struct rxrpc_transport *trans;
	struct rxrpc_local *local = sk->sk_user_data;
	struct rxrpc_peer *peer;
	struct sk_buff *skb;
	__be32 addr;
	__be16 port;

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

	skb = skb_dequeue(&sk->sk_error_queue);
	if (!skb) {
		_leave("UDP socket errqueue empty");
		return;
	}

	rxrpc_new_skb(skb);

	serr = SKB_EXT_ERR(skb);
	addr = *(__be32 *)(skb_network_header(skb) + serr->addr_offset);
	port = serr->port;

52
	_net("Rx UDP Error from %pI4:%hu", &addr, ntohs(port));
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
	_debug("Msg l:%d d:%d", skb->len, skb->data_len);

	peer = rxrpc_find_peer(local, addr, port);
	if (IS_ERR(peer)) {
		rxrpc_free_skb(skb);
		_leave(" [no peer]");
		return;
	}

	trans = rxrpc_find_transport(local, peer);
	if (!trans) {
		rxrpc_put_peer(peer);
		rxrpc_free_skb(skb);
		_leave(" [no trans]");
		return;
	}

	if (serr->ee.ee_origin == SO_EE_ORIGIN_ICMP &&
	    serr->ee.ee_type == ICMP_DEST_UNREACH &&
	    serr->ee.ee_code == ICMP_FRAG_NEEDED
	    ) {
		u32 mtu = serr->ee.ee_info;

		_net("Rx Received 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);
		}

		/* ip_rt_frag_needed() may have eaten the info */
		if (mtu == 0)
			mtu = ntohs(icmp_hdr(skb)->un.frag.mtu);

		if (mtu == 0) {
			/* they didn't give us a size, estimate one */
			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) {
102
			spin_lock_bh(&peer->lock);
103 104
			peer->mtu = mtu;
			peer->maxdata = peer->mtu - peer->hdrsize;
105
			spin_unlock_bh(&peer->lock);
106 107 108 109 110 111 112 113 114
			_net("Net MTU %u (maxdata %u)",
			     peer->mtu, peer->maxdata);
		}
	}

	rxrpc_put_peer(peer);

	/* pass the transport ref to error_handler to release */
	skb_queue_tail(&trans->error_queue, skb);
115
	rxrpc_queue_work(&trans->error_handler);
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

	/* reset and regenerate socket error */
	spin_lock_bh(&sk->sk_error_queue.lock);
	sk->sk_err = 0;
	skb = skb_peek(&sk->sk_error_queue);
	if (skb) {
		sk->sk_err = SKB_EXT_ERR(skb)->ee.ee_errno;
		spin_unlock_bh(&sk->sk_error_queue.lock);
		sk->sk_error_report(sk);
	} else {
		spin_unlock_bh(&sk->sk_error_queue.lock);
	}

	_leave("");
}

/*
 * deal with UDP error messages
 */
void rxrpc_UDP_error_handler(struct work_struct *work)
{
	struct sock_extended_err *ee;
	struct sock_exterr_skb *serr;
	struct rxrpc_transport *trans =
		container_of(work, struct rxrpc_transport, error_handler);
	struct sk_buff *skb;
142
	int err;
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

	_enter("");

	skb = skb_dequeue(&trans->error_queue);
	if (!skb)
		return;

	serr = SKB_EXT_ERR(skb);
	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");
				err = ENETUNREACH;
				break;
			case ICMP_HOST_UNREACH:
				_net("Rx Received ICMP Host Unreachable");
				err = EHOSTUNREACH;
				break;
			case ICMP_PORT_UNREACH:
				_net("Rx Received ICMP Port Unreachable");
				err = ECONNREFUSED;
				break;
			case ICMP_FRAG_NEEDED:
				_net("Rx Received ICMP Fragmentation Needed (%d)",
				     ee->ee_info);
				err = 0; /* dealt with elsewhere */
				break;
			case ICMP_NET_UNKNOWN:
				_net("Rx Received ICMP Unknown Network");
				err = ENETUNREACH;
				break;
			case ICMP_HOST_UNKNOWN:
				_net("Rx Received ICMP Unknown Host");
				err = EHOSTUNREACH;
				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_LOCAL:
		_proto("Rx Received local error { error=%d }",
		       ee->ee_errno);
		break;

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

	/* terminate all the affected calls if there's an unrecoverable
	 * error */
	if (err) {
		struct rxrpc_call *call, *_n;

		_debug("ISSUE ERROR %d", err);

		spin_lock_bh(&trans->peer->lock);
		trans->peer->net_error = err;

		list_for_each_entry_safe(call, _n, &trans->peer->error_targets,
					 error_link) {
			write_lock(&call->state_lock);
			if (call->state != RXRPC_CALL_COMPLETE &&
			    call->state < RXRPC_CALL_NETWORK_ERROR) {
				call->state = RXRPC_CALL_NETWORK_ERROR;
				set_bit(RXRPC_CALL_RCVD_ERROR, &call->events);
236
				rxrpc_queue_call(call);
237 238 239 240 241 242 243 244 245
			}
			write_unlock(&call->state_lock);
			list_del_init(&call->error_link);
		}

		spin_unlock_bh(&trans->peer->lock);
	}

	if (!skb_queue_empty(&trans->error_queue))
246
		rxrpc_queue_work(&trans->error_handler);
247 248 249 250 251

	rxrpc_free_skb(skb);
	rxrpc_put_transport(trans);
	_leave("");
}