summaryrefslogtreecommitdiff
path: root/net/rxrpc/output.c
blob: db01fbb70d23cbd7ad4c237336bd31ce002155a5 (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
/* RxRPC packet transmission
 *
 * 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.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/net.h>
#include <linux/gfp.h>
#include <linux/skbuff.h>
#include <linux/export.h>
#include <net/sock.h>
#include <net/af_rxrpc.h>
#include "ar-internal.h"

struct rxrpc_pkt_buffer {
	struct rxrpc_wire_header whdr;
	union {
		struct {
			struct rxrpc_ackpacket ack;
			u8 acks[255];
			u8 pad[3];
		};
		__be32 abort_code;
	};
	struct rxrpc_ackinfo ackinfo;
};

/*
 * Fill out an ACK packet.
 */
static size_t rxrpc_fill_out_ack(struct rxrpc_call *call,
				 struct rxrpc_pkt_buffer *pkt)
{
	rxrpc_serial_t serial;
	rxrpc_seq_t hard_ack, top, seq;
	int ix;
	u32 mtu, jmax;
	u8 *ackp = pkt->acks;

	/* Barrier against rxrpc_input_data(). */
	serial = call->ackr_serial;
	hard_ack = READ_ONCE(call->rx_hard_ack);
	top = smp_load_acquire(&call->rx_top);

	pkt->ack.bufferSpace	= htons(8);
	pkt->ack.maxSkew	= htons(call->ackr_skew);
	pkt->ack.firstPacket	= htonl(hard_ack + 1);
	pkt->ack.previousPacket	= htonl(call->ackr_prev_seq);
	pkt->ack.serial		= htonl(serial);
	pkt->ack.reason		= call->ackr_reason;
	pkt->ack.nAcks		= top - hard_ack;

	if (pkt->ack.reason == RXRPC_ACK_PING)
		pkt->whdr.flags |= RXRPC_REQUEST_ACK;

	if (after(top, hard_ack)) {
		seq = hard_ack + 1;
		do {
			ix = seq & RXRPC_RXTX_BUFF_MASK;
			if (call->rxtx_buffer[ix])
				*ackp++ = RXRPC_ACK_TYPE_ACK;
			else
				*ackp++ = RXRPC_ACK_TYPE_NACK;
			seq++;
		} while (before_eq(seq, top));
	}

	mtu = call->conn->params.peer->if_mtu;
	mtu -= call->conn->params.peer->hdrsize;
	jmax = (call->nr_jumbo_bad > 3) ? 1 : rxrpc_rx_jumbo_max;
	pkt->ackinfo.rxMTU	= htonl(rxrpc_rx_mtu);
	pkt->ackinfo.maxMTU	= htonl(mtu);
	pkt->ackinfo.rwind	= htonl(call->rx_winsize);
	pkt->ackinfo.jumbo_max	= htonl(jmax);

	trace_rxrpc_tx_ack(call, hard_ack + 1, serial, call->ackr_reason,
			   top - hard_ack);

	*ackp++ = 0;
	*ackp++ = 0;
	*ackp++ = 0;
	return top - hard_ack + 3;
}

/*
 * Send an ACK or ABORT call packet.
 */
int rxrpc_send_call_packet(struct rxrpc_call *call, u8 type)
{
	struct rxrpc_connection *conn = NULL;
	struct rxrpc_pkt_buffer *pkt;
	struct msghdr msg;
	struct kvec iov[2];
	rxrpc_serial_t serial;
	size_t len, n;
	bool ping = false;
	int ioc, ret;
	u32 abort_code;

	_enter("%u,%s", call->debug_id, rxrpc_pkts[type]);

	spin_lock_bh(&call->lock);
	if (call->conn)
		conn = rxrpc_get_connection_maybe(call->conn);
	spin_unlock_bh(&call->lock);
	if (!conn)
		return -ECONNRESET;

	pkt = kzalloc(sizeof(*pkt), GFP_KERNEL);
	if (!pkt) {
		rxrpc_put_connection(conn);
		return -ENOMEM;
	}

	serial = atomic_inc_return(&conn->serial);

	msg.msg_name	= &call->peer->srx.transport;
	msg.msg_namelen	= call->peer->srx.transport_len;
	msg.msg_control	= NULL;
	msg.msg_controllen = 0;
	msg.msg_flags	= 0;

	pkt->whdr.epoch		= htonl(conn->proto.epoch);
	pkt->whdr.cid		= htonl(call->cid);
	pkt->whdr.callNumber	= htonl(call->call_id);
	pkt->whdr.seq		= 0;
	pkt->whdr.serial	= htonl(serial);
	pkt->whdr.type		= type;
	pkt->whdr.flags		= conn->out_clientflag;
	pkt->whdr.userStatus	= 0;
	pkt->whdr.securityIndex	= call->security_ix;
	pkt->whdr._rsvd		= 0;
	pkt->whdr.serviceId	= htons(call->service_id);

	iov[0].iov_base	= pkt;
	iov[0].iov_len	= sizeof(pkt->whdr);
	len = sizeof(pkt->whdr);

	switch (type) {
	case RXRPC_PACKET_TYPE_ACK:
		spin_lock_bh(&call->lock);
		if (!call->ackr_reason) {
			spin_unlock_bh(&call->lock);
			ret = 0;
			goto out;
		}
		ping = (call->ackr_reason == RXRPC_ACK_PING);
		n = rxrpc_fill_out_ack(call, pkt);
		call->ackr_reason = 0;

		spin_unlock_bh(&call->lock);

		_proto("Tx ACK %%%u { m=%hu f=#%u p=#%u s=%%%u r=%s n=%u }",
		       serial,
		       ntohs(pkt->ack.maxSkew),
		       ntohl(pkt->ack.firstPacket),
		       ntohl(pkt->ack.previousPacket),
		       ntohl(pkt->ack.serial),
		       rxrpc_acks(pkt->ack.reason),
		       pkt->ack.nAcks);

		iov[0].iov_len += sizeof(pkt->ack) + n;
		iov[1].iov_base = &pkt->ackinfo;
		iov[1].iov_len	= sizeof(pkt->ackinfo);
		len += sizeof(pkt->ack) + n + sizeof(pkt->ackinfo);
		ioc = 2;
		break;

	case RXRPC_PACKET_TYPE_ABORT:
		abort_code = call->abort_code;
		pkt->abort_code = htonl(abort_code);
		_proto("Tx ABORT %%%u { %d }", serial, abort_code);
		iov[0].iov_len += sizeof(pkt->abort_code);
		len += sizeof(pkt->abort_code);
		ioc = 1;
		break;

	default:
		BUG();
		ret = -ENOANO;
		goto out;
	}

	if (ping) {
		call->ackr_ping = serial;
		smp_wmb();
		/* We need to stick a time in before we send the packet in case
		 * the reply gets back before kernel_sendmsg() completes - but
		 * asking UDP to send the packet can take a relatively long
		 * time, so we update the time after, on the assumption that
		 * the packet transmission is more likely to happen towards the
		 * end of the kernel_sendmsg() call.
		 */
		call->ackr_ping_time = ktime_get_real();
		set_bit(RXRPC_CALL_PINGING, &call->flags);
		trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_ping, serial);
	}
	ret = kernel_sendmsg(conn->params.local->socket,
			     &msg, iov, ioc, len);
	if (ping)
		call->ackr_ping_time = ktime_get_real();

	if (ret < 0 && call->state < RXRPC_CALL_COMPLETE) {
		switch (type) {
		case RXRPC_PACKET_TYPE_ACK:
			clear_bit(RXRPC_CALL_PINGING, &call->flags);
			rxrpc_propose_ACK(call, pkt->ack.reason,
					  ntohs(pkt->ack.maxSkew),
					  ntohl(pkt->ack.serial),
					  true, true);
			break;
		case RXRPC_PACKET_TYPE_ABORT:
			break;
		}
	}

out:
	rxrpc_put_connection(conn);
	kfree(pkt);
	return ret;
}

/*
 * send a packet through the transport endpoint
 */
int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb)
{
	struct rxrpc_connection *conn = call->conn;
	struct rxrpc_wire_header whdr;
	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
	struct msghdr msg;
	struct kvec iov[2];
	rxrpc_serial_t serial;
	size_t len;
	int ret, opt;

	_enter(",{%d}", skb->len);

	/* Each transmission of a Tx packet needs a new serial number */
	serial = atomic_inc_return(&conn->serial);

	whdr.epoch	= htonl(conn->proto.epoch);
	whdr.cid	= htonl(call->cid);
	whdr.callNumber	= htonl(call->call_id);
	whdr.seq	= htonl(sp->hdr.seq);
	whdr.serial	= htonl(serial);
	whdr.type	= RXRPC_PACKET_TYPE_DATA;
	whdr.flags	= sp->hdr.flags;
	whdr.userStatus	= 0;
	whdr.securityIndex = call->security_ix;
	whdr._rsvd	= htons(sp->hdr._rsvd);
	whdr.serviceId	= htons(call->service_id);

	iov[0].iov_base = &whdr;
	iov[0].iov_len = sizeof(whdr);
	iov[1].iov_base = skb->head;
	iov[1].iov_len = skb->len;
	len = iov[0].iov_len + iov[1].iov_len;

	msg.msg_name = &call->peer->srx.transport;
	msg.msg_namelen = call->peer->srx.transport_len;
	msg.msg_control = NULL;
	msg.msg_controllen = 0;
	msg.msg_flags = 0;

	if (IS_ENABLED(CONFIG_AF_RXRPC_INJECT_LOSS)) {
		static int lose;
		if ((lose++ & 7) == 7) {
			rxrpc_lose_skb(skb, rxrpc_skb_tx_lost);
			_leave(" = 0 [lose]");
			return 0;
		}
	}

	_proto("Tx DATA %%%u { #%u }", serial, sp->hdr.seq);

	/* send the packet with the don't fragment bit set if we currently
	 * think it's small enough */
	if (iov[1].iov_len >= call->peer->maxdata)
		goto send_fragmentable;

	down_read(&conn->params.local->defrag_sem);
	/* send the packet by UDP
	 * - returns -EMSGSIZE if UDP would have to fragment the packet
	 *   to go out of the interface
	 *   - in which case, we'll have processed the ICMP error
	 *     message and update the peer record
	 */
	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);

	up_read(&conn->params.local->defrag_sem);
	if (ret == -EMSGSIZE)
		goto send_fragmentable;

done:
	if (ret >= 0) {
		skb->tstamp = ktime_get_real();
		smp_wmb();
		sp->hdr.serial = serial;
		if (whdr.flags & RXRPC_REQUEST_ACK)
			trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial);
	}
	_leave(" = %d [%u]", ret, call->peer->maxdata);
	return ret;

send_fragmentable:
	/* attempt to send this message with fragmentation enabled */
	_debug("send fragment");

	down_write(&conn->params.local->defrag_sem);

	switch (conn->params.local->srx.transport.family) {
	case AF_INET:
		opt = IP_PMTUDISC_DONT;
		ret = kernel_setsockopt(conn->params.local->socket,
					SOL_IP, IP_MTU_DISCOVER,
					(char *)&opt, sizeof(opt));
		if (ret == 0) {
			ret = kernel_sendmsg(conn->params.local->socket, &msg,
					     iov, 2, len);

			opt = IP_PMTUDISC_DO;
			kernel_setsockopt(conn->params.local->socket, SOL_IP,
					  IP_MTU_DISCOVER,
					  (char *)&opt, sizeof(opt));
		}
		break;

#ifdef CONFIG_AF_RXRPC_IPV6
	case AF_INET6:
		opt = IPV6_PMTUDISC_DONT;
		ret = kernel_setsockopt(conn->params.local->socket,
					SOL_IPV6, IPV6_MTU_DISCOVER,
					(char *)&opt, sizeof(opt));
		if (ret == 0) {
			ret = kernel_sendmsg(conn->params.local->socket, &msg,
					     iov, 1, iov[0].iov_len);

			opt = IPV6_PMTUDISC_DO;
			kernel_setsockopt(conn->params.local->socket,
					  SOL_IPV6, IPV6_MTU_DISCOVER,
					  (char *)&opt, sizeof(opt));
		}
		break;
#endif
	}

	up_write(&conn->params.local->defrag_sem);
	goto done;
}

/*
 * reject packets through the local endpoint
 */
void rxrpc_reject_packets(struct rxrpc_local *local)
{
	struct sockaddr_rxrpc srx;
	struct rxrpc_skb_priv *sp;
	struct rxrpc_wire_header whdr;
	struct sk_buff *skb;
	struct msghdr msg;
	struct kvec iov[2];
	size_t size;
	__be32 code;

	_enter("%d", local->debug_id);

	iov[0].iov_base = &whdr;
	iov[0].iov_len = sizeof(whdr);
	iov[1].iov_base = &code;
	iov[1].iov_len = sizeof(code);
	size = sizeof(whdr) + sizeof(code);

	msg.msg_name = &srx.transport;
	msg.msg_control = NULL;
	msg.msg_controllen = 0;
	msg.msg_flags = 0;

	memset(&whdr, 0, sizeof(whdr));
	whdr.type = RXRPC_PACKET_TYPE_ABORT;

	while ((skb = skb_dequeue(&local->reject_queue))) {
		rxrpc_see_skb(skb, rxrpc_skb_rx_seen);
		sp = rxrpc_skb(skb);

		if (rxrpc_extract_addr_from_skb(&srx, skb) == 0) {
			msg.msg_namelen = srx.transport_len;

			code = htonl(skb->priority);

			whdr.epoch	= htonl(sp->hdr.epoch);
			whdr.cid	= htonl(sp->hdr.cid);
			whdr.callNumber	= htonl(sp->hdr.callNumber);
			whdr.serviceId	= htons(sp->hdr.serviceId);
			whdr.flags	= sp->hdr.flags;
			whdr.flags	^= RXRPC_CLIENT_INITIATED;
			whdr.flags	&= RXRPC_CLIENT_INITIATED;

			kernel_sendmsg(local->socket, &msg, iov, 2, size);
		}

		rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
	}

	_leave("");
}