fs_probe.c 11.9 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0-or-later
2 3
/* AFS fileserver probing
 *
4
 * Copyright (C) 2018, 2020 Red Hat, Inc. All Rights Reserved.
5 6 7 8 9 10 11
 * Written by David Howells (dhowells@redhat.com)
 */

#include <linux/sched.h>
#include <linux/slab.h>
#include "afs_fs.h"
#include "internal.h"
12
#include "protocol_afs.h"
13 14
#include "protocol_yfs.h"

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
static unsigned int afs_fs_probe_fast_poll_interval = 30 * HZ;
static unsigned int afs_fs_probe_slow_poll_interval = 5 * 60 * HZ;

/*
 * Start the probe polling timer.  We have to supply it with an inc on the
 * outstanding server count.
 */
static void afs_schedule_fs_probe(struct afs_net *net,
				  struct afs_server *server, bool fast)
{
	unsigned long atj;

	if (!net->live)
		return;

	atj = server->probed_at;
	atj += fast ? afs_fs_probe_fast_poll_interval : afs_fs_probe_slow_poll_interval;

	afs_inc_servers_outstanding(net);
	if (timer_reduce(&net->fs_probe_timer, atj))
		afs_dec_servers_outstanding(net);
}

/*
 * Handle the completion of a set of probes.
 */
static void afs_finished_fs_probe(struct afs_net *net, struct afs_server *server)
{
	bool responded = server->probe.responded;

	write_seqlock(&net->fs_lock);
46
	if (responded) {
47
		list_add_tail(&server->probe_link, &net->fs_probe_slow);
48 49 50
	} else {
		server->rtt = UINT_MAX;
		clear_bit(AFS_SERVER_FL_RESPONDING, &server->flags);
51
		list_add_tail(&server->probe_link, &net->fs_probe_fast);
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
	write_sequnlock(&net->fs_lock);

	afs_schedule_fs_probe(net, server, !responded);
}

/*
 * Handle the completion of a probe.
 */
static void afs_done_one_fs_probe(struct afs_net *net, struct afs_server *server)
{
	_enter("");

	if (atomic_dec_and_test(&server->probe_outstanding))
		afs_finished_fs_probe(net, server);

	wake_up_all(&server->probe_wq);
}

/*
 * Handle inability to send a probe due to ENOMEM when trying to allocate a
 * call struct.
 */
static void afs_fs_probe_not_done(struct afs_net *net,
				  struct afs_server *server,
				  struct afs_addr_cursor *ac)
78
{
79 80 81 82
	struct afs_addr_list *alist = ac->alist;
	unsigned int index = ac->index;

	_enter("");
83

84 85 86 87 88 89 90 91 92 93 94
	trace_afs_io_error(0, -ENOMEM, afs_io_error_fs_probe_fail);
	spin_lock(&server->probe_lock);

	server->probe.local_failure = true;
	if (server->probe.error == 0)
		server->probe.error = -ENOMEM;

	set_bit(index, &alist->failed);

	spin_unlock(&server->probe_lock);
	return afs_done_one_fs_probe(net, server);
95 96 97 98 99 100 101 102 103
}

/*
 * Process the result of probing a fileserver.  This is called after successful
 * or failed delivery of an FS.GetCapabilities operation.
 */
void afs_fileserver_probe_result(struct afs_call *call)
{
	struct afs_addr_list *alist = call->alist;
104
	struct afs_server *server = call->server;
105
	unsigned int index = call->addr_ix;
106
	unsigned int rtt_us = 0, cap0;
107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124
	int ret = call->error;

	_enter("%pU,%u", &server->uuid, index);

	spin_lock(&server->probe_lock);

	switch (ret) {
	case 0:
		server->probe.error = 0;
		goto responded;
	case -ECONNABORTED:
		if (!server->probe.responded) {
			server->probe.abort_code = call->abort_code;
			server->probe.error = ret;
		}
		goto responded;
	case -ENOMEM:
	case -ENONET:
125
		clear_bit(index, &alist->responded);
126
		server->probe.local_failure = true;
127
		trace_afs_io_error(call->debug_id, ret, afs_io_error_fs_probe_fail);
128 129
		goto out;
	case -ECONNRESET: /* Responded, but call expired. */
130 131
	case -ERFKILL:
	case -EADDRNOTAVAIL:
132 133
	case -ENETUNREACH:
	case -EHOSTUNREACH:
134
	case -EHOSTDOWN:
135 136 137 138 139 140 141 142 143 144 145
	case -ECONNREFUSED:
	case -ETIMEDOUT:
	case -ETIME:
	default:
		clear_bit(index, &alist->responded);
		set_bit(index, &alist->failed);
		if (!server->probe.responded &&
		    (server->probe.error == 0 ||
		     server->probe.error == -ETIMEDOUT ||
		     server->probe.error == -ETIME))
			server->probe.error = ret;
146
		trace_afs_io_error(call->debug_id, ret, afs_io_error_fs_probe_fail);
147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162
		goto out;
	}

responded:
	clear_bit(index, &alist->failed);

	if (call->service_id == YFS_FS_SERVICE) {
		server->probe.is_yfs = true;
		set_bit(AFS_SERVER_FL_IS_YFS, &server->flags);
		alist->addrs[index].srx_service = call->service_id;
	} else {
		server->probe.not_yfs = true;
		if (!server->probe.is_yfs) {
			clear_bit(AFS_SERVER_FL_IS_YFS, &server->flags);
			alist->addrs[index].srx_service = call->service_id;
		}
163 164 165 166 167
		cap0 = ntohl(call->tmp);
		if (cap0 & AFS3_VICED_CAPABILITY_64BITFILES)
			set_bit(AFS_SERVER_FL_HAS_FS64, &server->flags);
		else
			clear_bit(AFS_SERVER_FL_HAS_FS64, &server->flags);
168 169
	}

170 171
	rxrpc_kernel_get_srtt(call->net->socket, call->rxcall, &rtt_us);
	if (rtt_us < server->probe.rtt) {
172
		server->probe.rtt = rtt_us;
173
		server->rtt = rtt_us;
174 175 176 177 178
		alist->preferred = index;
	}

	smp_wmb(); /* Set rtt before responded. */
	server->probe.responded = true;
179
	set_bit(index, &alist->responded);
180
	set_bit(AFS_SERVER_FL_RESPONDING, &server->flags);
181 182 183
out:
	spin_unlock(&server->probe_lock);

184 185 186
	_debug("probe %pU [%u] %pISpc rtt=%u ret=%d",
	       &server->uuid, index, &alist->addrs[index].transport,
	       rtt_us, ret);
187

188
	return afs_done_one_fs_probe(call->net, server);
189 190 191
}

/*
192 193
 * Probe one or all of a fileserver's addresses to find out the best route and
 * to query its capabilities.
194
 */
195 196
void afs_fs_probe_fileserver(struct afs_net *net, struct afs_server *server,
			     struct key *key, bool all)
197 198 199 200 201 202 203 204 205 206
{
	struct afs_addr_cursor ac = {
		.index = 0,
	};

	_enter("%pU", &server->uuid);

	read_lock(&server->fs_lock);
	ac.alist = rcu_dereference_protected(server->addresses,
					     lockdep_is_held(&server->fs_lock));
207
	afs_get_addrlist(ac.alist);
208 209
	read_unlock(&server->fs_lock);

210 211
	server->probed_at = jiffies;
	atomic_set(&server->probe_outstanding, all ? ac.alist->nr_addrs : 1);
212 213 214
	memset(&server->probe, 0, sizeof(server->probe));
	server->probe.rtt = UINT_MAX;

215 216 217
	ac.index = ac.alist->preferred;
	if (ac.index < 0 || ac.index >= ac.alist->nr_addrs)
		all = true;
218

219 220 221 222 223 224 225
	if (all) {
		for (ac.index = 0; ac.index < ac.alist->nr_addrs; ac.index++)
			if (!afs_fs_get_capabilities(net, server, &ac, key))
				afs_fs_probe_not_done(net, server, &ac);
	} else {
		if (!afs_fs_get_capabilities(net, server, &ac, key))
			afs_fs_probe_not_done(net, server, &ac);
226 227
	}

228
	afs_put_addrlist(ac.alist);
229 230 231 232 233 234 235 236 237
}

/*
 * Wait for the first as-yet untried fileserver to respond.
 */
int afs_wait_for_fs_probes(struct afs_server_list *slist, unsigned long untried)
{
	struct wait_queue_entry *waits;
	struct afs_server *server;
238
	unsigned int rtt = UINT_MAX, rtt_s;
239 240 241 242 243 244 245 246 247
	bool have_responders = false;
	int pref = -1, i;

	_enter("%u,%lx", slist->nr_servers, untried);

	/* Only wait for servers that have a probe outstanding. */
	for (i = 0; i < slist->nr_servers; i++) {
		if (test_bit(i, &untried)) {
			server = slist->servers[i].server;
248
			if (!atomic_read(&server->probe_outstanding))
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
				__clear_bit(i, &untried);
			if (server->probe.responded)
				have_responders = true;
		}
	}
	if (have_responders || !untried)
		return 0;

	waits = kmalloc(array_size(slist->nr_servers, sizeof(*waits)), GFP_KERNEL);
	if (!waits)
		return -ENOMEM;

	for (i = 0; i < slist->nr_servers; i++) {
		if (test_bit(i, &untried)) {
			server = slist->servers[i].server;
			init_waitqueue_entry(&waits[i], current);
			add_wait_queue(&server->probe_wq, &waits[i]);
		}
	}

	for (;;) {
		bool still_probing = false;

		set_current_state(TASK_INTERRUPTIBLE);
		for (i = 0; i < slist->nr_servers; i++) {
			if (test_bit(i, &untried)) {
				server = slist->servers[i].server;
				if (server->probe.responded)
					goto stop;
278
				if (atomic_read(&server->probe_outstanding))
279 280 281 282
					still_probing = true;
			}
		}

283
		if (!still_probing || signal_pending(current))
284 285 286 287 288 289 290 291 292 293
			goto stop;
		schedule();
	}

stop:
	set_current_state(TASK_RUNNING);

	for (i = 0; i < slist->nr_servers; i++) {
		if (test_bit(i, &untried)) {
			server = slist->servers[i].server;
294 295 296
			rtt_s = READ_ONCE(server->rtt);
			if (test_bit(AFS_SERVER_FL_RESPONDING, &server->flags) &&
			    rtt_s < rtt) {
297
				pref = i;
298
				rtt = rtt_s;
299 300 301 302 303 304 305 306 307 308 309 310 311 312 313
			}

			remove_wait_queue(&server->probe_wq, &waits[i]);
		}
	}

	kfree(waits);

	if (pref == -1 && signal_pending(current))
		return -ERESTARTSYS;

	if (pref >= 0)
		slist->preferred = pref;
	return 0;
}
314 315 316 317 318 319 320 321 322

/*
 * Probe timer.  We have an increment on fs_outstanding that we need to pass
 * along to the work item.
 */
void afs_fs_probe_timer(struct timer_list *timer)
{
	struct afs_net *net = container_of(timer, struct afs_net, fs_probe_timer);

323
	if (!net->live || !queue_work(afs_wq, &net->fs_prober))
324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346
		afs_dec_servers_outstanding(net);
}

/*
 * Dispatch a probe to a server.
 */
static void afs_dispatch_fs_probe(struct afs_net *net, struct afs_server *server, bool all)
	__releases(&net->fs_lock)
{
	struct key *key = NULL;

	/* We remove it from the queues here - it will be added back to
	 * one of the queues on the completion of the probe.
	 */
	list_del_init(&server->probe_link);

	afs_get_server(server, afs_server_trace_get_probe);
	write_sequnlock(&net->fs_lock);

	afs_fs_probe_fileserver(net, server, key, all);
	afs_put_server(net, server, afs_server_trace_put_probe);
}

347 348 349 350 351 352 353 354 355 356 357 358
/*
 * Probe a server immediately without waiting for its due time to come
 * round.  This is used when all of the addresses have been tried.
 */
void afs_probe_fileserver(struct afs_net *net, struct afs_server *server)
{
	write_seqlock(&net->fs_lock);
	if (!list_empty(&server->probe_link))
		return afs_dispatch_fs_probe(net, server, true);
	write_sequnlock(&net->fs_lock);
}

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
/*
 * Probe dispatcher to regularly dispatch probes to keep NAT alive.
 */
void afs_fs_probe_dispatcher(struct work_struct *work)
{
	struct afs_net *net = container_of(work, struct afs_net, fs_prober);
	struct afs_server *fast, *slow, *server;
	unsigned long nowj, timer_at, poll_at;
	bool first_pass = true, set_timer = false;

	if (!net->live)
		return;

	_enter("");

	if (list_empty(&net->fs_probe_fast) && list_empty(&net->fs_probe_slow)) {
		_leave(" [none]");
		return;
	}

again:
	write_seqlock(&net->fs_lock);

	fast = slow = server = NULL;
	nowj = jiffies;
	timer_at = nowj + MAX_JIFFY_OFFSET;

	if (!list_empty(&net->fs_probe_fast)) {
		fast = list_first_entry(&net->fs_probe_fast, struct afs_server, probe_link);
		poll_at = fast->probed_at + afs_fs_probe_fast_poll_interval;
		if (time_before(nowj, poll_at)) {
			timer_at = poll_at;
			set_timer = true;
			fast = NULL;
		}
	}

	if (!list_empty(&net->fs_probe_slow)) {
		slow = list_first_entry(&net->fs_probe_slow, struct afs_server, probe_link);
		poll_at = slow->probed_at + afs_fs_probe_slow_poll_interval;
		if (time_before(nowj, poll_at)) {
			if (time_before(poll_at, timer_at))
			    timer_at = poll_at;
			set_timer = true;
			slow = NULL;
		}
	}

	server = fast ?: slow;
	if (server)
		_debug("probe %pU", &server->uuid);

	if (server && (first_pass || !need_resched())) {
		afs_dispatch_fs_probe(net, server, server == fast);
		first_pass = false;
		goto again;
	}

	write_sequnlock(&net->fs_lock);

	if (server) {
		if (!queue_work(afs_wq, &net->fs_prober))
			afs_dec_servers_outstanding(net);
		_leave(" [requeue]");
	} else if (set_timer) {
		if (timer_reduce(&net->fs_probe_timer, timer_at))
			afs_dec_servers_outstanding(net);
		_leave(" [timer]");
	} else {
		afs_dec_servers_outstanding(net);
		_leave(" [quiesce]");
	}
}
432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466

/*
 * Wait for a probe on a particular fileserver to complete for 2s.
 */
int afs_wait_for_one_fs_probe(struct afs_server *server, bool is_intr)
{
	struct wait_queue_entry wait;
	unsigned long timo = 2 * HZ;

	if (atomic_read(&server->probe_outstanding) == 0)
		goto dont_wait;

	init_wait_entry(&wait, 0);
	for (;;) {
		prepare_to_wait_event(&server->probe_wq, &wait,
				      is_intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
		if (timo == 0 ||
		    server->probe.responded ||
		    atomic_read(&server->probe_outstanding) == 0 ||
		    (is_intr && signal_pending(current)))
			break;
		timo = schedule_timeout(timo);
	}

	finish_wait(&server->probe_wq, &wait);

dont_wait:
	if (server->probe.responded)
		return 0;
	if (is_intr && signal_pending(current))
		return -ERESTARTSYS;
	if (timo == 0)
		return -ETIME;
	return -EDESTADDRREQ;
}
467 468 469 470 471 472 473 474 475

/*
 * Clean up the probing when the namespace is killed off.
 */
void afs_fs_probe_cleanup(struct afs_net *net)
{
	if (del_timer_sync(&net->fs_probe_timer))
		afs_dec_servers_outstanding(net);
}