summaryrefslogtreecommitdiffstats
path: root/fs/afs/rotate.c
blob: b00c739e0e63aaf03d288ad94096e0ab075ee9b4 (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
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
/* Handle fileserver selection and rotation.
 *
 * Copyright (C) 2017 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 Licence
 * as published by the Free Software Foundation; either version
 * 2 of the Licence, or (at your option) any later version.
 */

#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/sched.h>
#include <linux/delay.h>
#include <linux/sched/signal.h>
#include "internal.h"
#include "afs_fs.h"

/*
 * Begin an operation on the fileserver.
 *
 * Fileserver operations are serialised on the server by vnode, so we serialise
 * them here also using the io_lock.
 */
bool afs_begin_vnode_operation(struct afs_fs_cursor *fc, struct afs_vnode *vnode,
			       struct key *key, bool intr)
{
	memset(fc, 0, sizeof(*fc));
	fc->vnode = vnode;
	fc->key = key;
	fc->ac.error = SHRT_MAX;
	fc->error = -EDESTADDRREQ;

	if (intr) {
		fc->flags |= AFS_FS_CURSOR_INTR;
		if (mutex_lock_interruptible(&vnode->io_lock) < 0) {
			fc->error = -EINTR;
			fc->flags |= AFS_FS_CURSOR_STOP;
			return false;
		}
	} else {
		mutex_lock(&vnode->io_lock);
	}

	if (vnode->lock_state != AFS_VNODE_LOCK_NONE)
		fc->flags |= AFS_FS_CURSOR_CUR_ONLY;
	return true;
}

/*
 * Begin iteration through a server list, starting with the vnode's last used
 * server if possible, or the last recorded good server if not.
 */
static bool afs_start_fs_iteration(struct afs_fs_cursor *fc,
				   struct afs_vnode *vnode)
{
	struct afs_cb_interest *cbi;
	int i;

	read_lock(&vnode->volume->servers_lock);
	fc->server_list = afs_get_serverlist(vnode->volume->servers);
	read_unlock(&vnode->volume->servers_lock);

	fc->untried = (1UL << fc->server_list->nr_servers) - 1;
	fc->index = READ_ONCE(fc->server_list->preferred);

	cbi = rcu_dereference_protected(vnode->cb_interest,
					lockdep_is_held(&vnode->io_lock));
	if (cbi) {
		/* See if the vnode's preferred record is still available */
		for (i = 0; i < fc->server_list->nr_servers; i++) {
			if (fc->server_list->servers[i].cb_interest == cbi) {
				fc->index = i;
				goto found_interest;
			}
		}

		/* If we have a lock outstanding on a server that's no longer
		 * serving this vnode, then we can't switch to another server
		 * and have to return an error.
		 */
		if (fc->flags & AFS_FS_CURSOR_CUR_ONLY) {
			fc->error = -ESTALE;
			return false;
		}

		/* Note that the callback promise is effectively broken */
		write_seqlock(&vnode->cb_lock);
		ASSERTCMP(cbi, ==, rcu_access_pointer(vnode->cb_interest));
		rcu_assign_pointer(vnode->cb_interest, NULL);
		if (test_and_clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags))
			vnode->cb_break++;
		write_sequnlock(&vnode->cb_lock);

		afs_put_cb_interest(afs_v2net(vnode), cbi);
		cbi = NULL;
	}

found_interest:
	return true;
}

/*
 * Post volume busy note.
 */
static void afs_busy(struct afs_volume *volume, u32 abort_code)
{
	const char *m;

	switch (abort_code) {
	case VOFFLINE:		m = "offline";		break;
	case VRESTARTING:	m = "restarting";	break;
	case VSALVAGING:	m = "being salvaged";	break;
	default:		m = "busy";		break;
	}

	pr_notice("kAFS: Volume %llu '%s' is %s\n", volume->vid, volume->name, m);
}

/*
 * Sleep and retry the operation to the same fileserver.
 */
static bool afs_sleep_and_retry(struct afs_fs_cursor *fc)
{
	if (fc->flags & AFS_FS_CURSOR_INTR) {
		msleep_interruptible(1000);
		if (signal_pending(current)) {
			fc->error = -ERESTARTSYS;
			return false;
		}
	} else {
		msleep(1000);
	}

	return true;
}

/*
 * Select the fileserver to use.  May be called multiple times to rotate
 * through the fileservers.
 */
bool afs_select_fileserver(struct afs_fs_cursor *fc)
{
	struct afs_addr_list *alist;
	struct afs_server *server;
	struct afs_vnode *vnode = fc->vnode;
	struct afs_error e;
	u32 rtt;
	int error = fc->ac.error, i;

	_enter("%lx[%d],%lx[%d],%d,%d",
	       fc->untried, fc->index,
	       fc->ac.tried, fc->ac.index,
	       error, fc->ac.abort_code);

	if (fc->flags & AFS_FS_CURSOR_STOP) {
		_leave(" = f [stopped]");
		return false;
	}

	fc->nr_iterations++;

	/* Evaluate the result of the previous operation, if there was one. */
	switch (error) {
	case SHRT_MAX:
		goto start;

	case 0:
	default:
		/* Success or local failure.  Stop. */
		fc->error = error;
		fc->flags |= AFS_FS_CURSOR_STOP;
		_leave(" = f [okay/local %d]", error);
		return false;

	case -ECONNABORTED:
		/* The far side rejected the operation on some grounds.  This
		 * might involve the server being busy or the volume having been moved.
		 */
		switch (fc->ac.abort_code) {
		case VNOVOL:
			/* This fileserver doesn't know about the volume.
			 * - May indicate that the VL is wrong - retry once and compare
			 *   the results.
			 * - May indicate that the fileserver couldn't attach to the vol.
			 */
			if (fc->flags & AFS_FS_CURSOR_VNOVOL) {
				fc->error = -EREMOTEIO;
				goto next_server;
			}

			write_lock(&vnode->volume->servers_lock);
			fc->server_list->vnovol_mask |= 1 << fc->index;
			write_unlock(&vnode->volume->servers_lock);

			set_bit(AFS_VOLUME_NEEDS_UPDATE, &vnode->volume->flags);
			error = afs_check_volume_status(vnode->volume, fc->key);
			if (error < 0)
				goto failed_set_error;

			if (test_bit(AFS_VOLUME_DELETED, &vnode->volume->flags)) {
				fc->error = -ENOMEDIUM;
				goto failed;
			}

			/* If the server list didn't change, then assume that
			 * it's the fileserver having trouble.
			 */
			if (vnode->volume->servers == fc->server_list) {
				fc->error = -EREMOTEIO;
				goto next_server;
			}

			/* Try again */
			fc->flags |= AFS_FS_CURSOR_VNOVOL;
			_leave(" = t [vnovol]");
			return true;

		case VSALVAGE: /* TODO: Should this return an error or iterate? */
		case VVOLEXISTS:
		case VNOSERVICE:
		case VONLINE:
		case VDISKFULL:
		case VOVERQUOTA:
			fc->error = afs_abort_to_error(fc->ac.abort_code);
			goto next_server;

		case VOFFLINE:
			if (!test_and_set_bit(AFS_VOLUME_OFFLINE, &vnode->volume->flags)) {
				afs_busy(vnode->volume, fc->ac.abort_code);
				clear_bit(AFS_VOLUME_BUSY, &vnode->volume->flags);
			}
			if (fc->flags & AFS_FS_CURSOR_NO_VSLEEP) {
				fc->error = -EADV;
				goto failed;
			}
			if (fc->flags & AFS_FS_CURSOR_CUR_ONLY) {
				fc->error = -ESTALE;
				goto failed;
			}
			goto busy;

		case VSALVAGING:
		case VRESTARTING:
		case VBUSY:
			/* Retry after going round all the servers unless we
			 * have a file lock we need to maintain.
			 */
			if (fc->flags & AFS_FS_CURSOR_NO_VSLEEP) {
				fc->error = -EBUSY;
				goto failed;
			}
			if (!test_and_set_bit(AFS_VOLUME_BUSY, &vnode->volume->flags)) {
				afs_busy(vnode->volume, fc->ac.abort_code);
				clear_bit(AFS_VOLUME_OFFLINE, &vnode->volume->flags);
			}
		busy:
			if (fc->flags & AFS_FS_CURSOR_CUR_ONLY) {
				if (!afs_sleep_and_retry(fc))
					goto failed;

				 /* Retry with same server & address */
				_leave(" = t [vbusy]");
				return true;
			}

			fc->flags |= AFS_FS_CURSOR_VBUSY;
			goto next_server;

		case VMOVED:
			/* The volume migrated to another server.  We consider
			 * consider all locks and callbacks broken and request
			 * an update from the VLDB.
			 *
			 * We also limit the number of VMOVED hops we will
			 * honour, just in case someone sets up a loop.
			 */
			if (fc->flags & AFS_FS_CURSOR_VMOVED) {
				fc->error = -EREMOTEIO;
				goto failed;
			}
			fc->flags |= AFS_FS_CURSOR_VMOVED;

			set_bit(AFS_VOLUME_WAIT, &vnode->volume->flags);
			set_bit(AFS_VOLUME_NEEDS_UPDATE, &vnode->volume->flags);
			error = afs_check_volume_status(vnode->volume, fc->key);
			if (error < 0)
				goto failed_set_error;

			/* If the server list didn't change, then the VLDB is
			 * out of sync with the fileservers.  This is hopefully
			 * a temporary condition, however, so we don't want to
			 * permanently block access to the file.
			 *
			 * TODO: Try other fileservers if we can.
			 *
			 * TODO: Retry a few times with sleeps.
			 */
			if (vnode->volume->servers == fc->server_list) {
				fc->error = -ENOMEDIUM;
				goto failed;
			}

			goto restart_from_beginning;

		default:
			clear_bit(AFS_VOLUME_OFFLINE, &vnode->volume->flags);
			clear_bit(AFS_VOLUME_BUSY, &vnode->volume->flags);
			fc->error = afs_abort_to_error(fc->ac.abort_code);
			goto failed;
		}

	case -ETIMEDOUT:
	case -ETIME:
		if (fc->error != -EDESTADDRREQ)
			goto iterate_address;
		/* Fall through */
	case -ERFKILL:
	case -EADDRNOTAVAIL:
	case -ENETUNREACH:
	case -EHOSTUNREACH:
	case -EHOSTDOWN:
	case -ECONNREFUSED:
		_debug("no conn");
		fc->error = error;
		goto iterate_address;

	case -ECONNRESET:
		_debug("call reset");
		fc->error = error;
		goto failed;
	}

restart_from_beginning:
	_debug("restart");
	afs_end_cursor(&fc->ac);
	afs_put_cb_interest(afs_v2net(vnode), fc->cbi);
	fc->cbi = NULL;
	afs_put_serverlist(afs_v2net(vnode), fc->server_list);
	fc->server_list = NULL;
start:
	_debug("start");
	/* See if we need to do an update of the volume record.  Note that the
	 * volume may have moved or even have been deleted.
	 */
	error = afs_check_volume_status(vnode->volume, fc->key);
	if (error < 0)
		goto failed_set_error;

	if (!afs_start_fs_iteration(fc, vnode))
		goto failed;

	_debug("__ VOL %llx __", vnode->volume->vid);
	error = afs_probe_fileservers(afs_v2net(vnode), fc->key, fc->server_list);
	if (error < 0)
		goto failed_set_error;

pick_server:
	_debug("pick [%lx]", fc->untried);

	error = afs_wait_for_fs_probes(fc->server_list, fc->untried);
	if (error < 0)
		goto failed_set_error;

	/* Pick the untried server with the lowest RTT.  If we have outstanding
	 * callbacks, we stick with the server we're already using if we can.
	 */
	if (fc->cbi) {
		_debug("cbi %u", fc->index);
		if (test_bit(fc->index, &fc->untried))
			goto selected_server;
		afs_put_cb_interest(afs_v2net(vnode), fc->cbi);
		fc->cbi = NULL;
		_debug("nocbi");
	}

	fc->index = -1;
	rtt = U32_MAX;
	for (i = 0; i < fc->server_list->nr_servers; i++) {
		struct afs_server *s = fc->server_list->servers[i].server;

		if (!test_bit(i, &fc->untried) || !s->probe.responded)
			continue;
		if (s->probe.rtt < rtt) {
			fc->index = i;
			rtt = s->probe.rtt;
		}
	}

	if (fc->index == -1)
		goto no_more_servers;

selected_server:
	_debug("use %d", fc->index);
	__clear_bit(fc->index, &fc->untried);

	/* We're starting on a different fileserver from the list.  We need to
	 * check it, create a callback intercept, find its address list and
	 * probe its capabilities before we use it.
	 */
	ASSERTCMP(fc->ac.alist, ==, NULL);
	server = fc->server_list->servers[fc->index].server;

	if (!afs_check_server_record(fc, server))
		goto failed;

	_debug("USING SERVER: %pU", &server->uuid);

	/* Make sure we've got a callback interest record for this server.  We
	 * have to link it in before we send the request as we can be sent a
	 * break request before we've finished decoding the reply and
	 * installing the vnode.
	 */
	error = afs_register_server_cb_interest(vnode, fc->server_list,
						fc->index);
	if (error < 0)
		goto failed_set_error;

	fc->cbi = afs_get_cb_interest(
		rcu_dereference_protected(vnode->cb_interest,
					  lockdep_is_held(&vnode->io_lock)));

	read_lock(&server->fs_lock);
	alist = rcu_dereference_protected(server->addresses,
					  lockdep_is_held(&server->fs_lock));
	afs_get_addrlist(alist);
	read_unlock(&server->fs_lock);

	memset(&fc->ac, 0, sizeof(fc->ac));

	if (!fc->ac.alist)
		fc->ac.alist = alist;
	else
		afs_put_addrlist(alist);

	fc->ac.index = -1;

iterate_address:
	ASSERT(fc->ac.alist);
	/* Iterate over the current server's address list to try and find an
	 * address on which it will respond to us.
	 */
	if (!afs_iterate_addresses(&fc->ac))
		goto next_server;

	_debug("address [%u] %u/%u", fc->index, fc->ac.index, fc->ac.alist->nr_addrs);

	_leave(" = t");
	return true;

next_server:
	_debug("next");
	afs_end_cursor(&fc->ac);
	goto pick_server;

no_more_servers:
	/* That's all the servers poked to no good effect.  Try again if some
	 * of them were busy.
	 */
	if (fc->flags & AFS_FS_CURSOR_VBUSY)
		goto restart_from_beginning;

	e.error = -EDESTADDRREQ;
	e.responded = false;
	for (i = 0; i < fc->server_list->nr_servers; i++) {
		struct afs_server *s = fc->server_list->servers[i].server;

		afs_prioritise_error(&e, READ_ONCE(s->probe.error),
				     s->probe.abort_code);
	}

	error = e.error;

failed_set_error:
	fc->error = error;
failed:
	fc->flags |= AFS_FS_CURSOR_STOP;
	afs_end_cursor(&fc->ac);
	_leave(" = f [failed %d]", fc->error);
	return false;
}

/*
 * Select the same fileserver we used for a vnode before and only that
 * fileserver.  We use this when we have a lock on that file, which is backed
 * only by the fileserver we obtained it from.
 */
bool afs_select_current_fileserver(struct afs_fs_cursor *fc)
{
	struct afs_vnode *vnode = fc->vnode;
	struct afs_cb_interest *cbi;
	struct afs_addr_list *alist;
	int error = fc->ac.error;

	_enter("");

	cbi = rcu_dereference_protected(vnode->cb_interest,
					lockdep_is_held(&vnode->io_lock));

	switch (error) {
	case SHRT_MAX:
		if (!cbi) {
			fc->error = -ESTALE;
			fc->flags |= AFS_FS_CURSOR_STOP;
			return false;
		}

		fc->cbi = afs_get_cb_interest(cbi);

		read_lock(&cbi->server->fs_lock);
		alist = rcu_dereference_protected(cbi->server->addresses,
						  lockdep_is_held(&cbi->server->fs_lock));
		afs_get_addrlist(alist);
		read_unlock(&cbi->server->fs_lock);
		if (!alist) {
			fc->error = -ESTALE;
			fc->flags |= AFS_FS_CURSOR_STOP;
			return false;
		}

		memset(&fc->ac, 0, sizeof(fc->ac));
		fc->ac.alist = alist;
		fc->ac.index = -1;
		goto iterate_address;

	case 0:
	default:
		/* Success or local failure.  Stop. */
		fc->error = error;
		fc->flags |= AFS_FS_CURSOR_STOP;
		_leave(" = f [okay/local %d]", error);
		return false;

	case -ECONNABORTED:
		fc->error = afs_abort_to_error(fc->ac.abort_code);
		fc->flags |= AFS_FS_CURSOR_STOP;
		_leave(" = f [abort]");
		return false;

	case -ERFKILL:
	case -EADDRNOTAVAIL:
	case -ENETUNREACH:
	case -EHOSTUNREACH:
	case -EHOSTDOWN:
	case -ECONNREFUSED:
	case -ETIMEDOUT:
	case -ETIME:
		_debug("no conn");
		fc->error = error;
		goto iterate_address;
	}

iterate_address:
	/* Iterate over the current server's address list to try and find an
	 * address on which it will respond to us.
	 */
	if (afs_iterate_addresses(&fc->ac)) {
		_leave(" = t");
		return true;
	}

	afs_end_cursor(&fc->ac);
	return false;
}

/*
 * Dump cursor state in the case of the error being EDESTADDRREQ.
 */
static void afs_dump_edestaddrreq(const struct afs_fs_cursor *fc)
{
	static int count;
	int i;

	if (!IS_ENABLED(CONFIG_AFS_DEBUG_CURSOR) || count > 3)
		return;
	count++;

	rcu_read_lock();

	pr_notice("EDESTADDR occurred\n");
	pr_notice("FC: cbb=%x cbb2=%x fl=%hx err=%hd\n",
		  fc->cb_break, fc->cb_break_2, fc->flags, fc->error);
	pr_notice("FC: ut=%lx ix=%d ni=%u\n",
		  fc->untried, fc->index, fc->nr_iterations);

	if (fc->server_list) {
		const struct afs_server_list *sl = fc->server_list;
		pr_notice("FC: SL nr=%u pr=%u vnov=%hx\n",
			  sl->nr_servers, sl->preferred, sl->vnovol_mask);
		for (i = 0; i < sl->nr_servers; i++) {
			const struct afs_server *s = sl->servers[i].server;
			pr_notice("FC: server fl=%lx av=%u %pU\n",
				  s->flags, s->addr_version, &s->uuid);
			if (s->addresses) {
				const struct afs_addr_list *a =
					rcu_dereference(s->addresses);
				pr_notice("FC:  - av=%u nr=%u/%u/%u pr=%u\n",
					  a->version,
					  a->nr_ipv4, a->nr_addrs, a->max_addrs,
					  a->preferred);
				pr_notice("FC:  - pr=%lx R=%lx F=%lx\n",
					  a->probed, a->responded, a->failed);
				if (a == fc->ac.alist)
					pr_notice("FC:  - current\n");
			}
		}
	}

	pr_notice("AC: t=%lx ax=%u ac=%d er=%d r=%u ni=%u\n",
		  fc->ac.tried, fc->ac.index, fc->ac.abort_code, fc->ac.error,
		  fc->ac.responded, fc->ac.nr_iterations);
	rcu_read_unlock();
}

/*
 * Tidy up a filesystem cursor and unlock the vnode.
 */
int afs_end_vnode_operation(struct afs_fs_cursor *fc)
{
	struct afs_net *net = afs_v2net(fc->vnode);

	if (fc->error == -EDESTADDRREQ ||
	    fc->error == -EADDRNOTAVAIL ||
	    fc->error == -ENETUNREACH ||
	    fc->error == -EHOSTUNREACH)
		afs_dump_edestaddrreq(fc);

	mutex_unlock(&fc->vnode->io_lock);

	afs_end_cursor(&fc->ac);
	afs_put_cb_interest(net, fc->cbi);
	afs_put_serverlist(net, fc->server_list);

	if (fc->error == -ECONNABORTED)
		fc->error = afs_abort_to_error(fc->ac.abort_code);

	return fc->error;
}