aboutsummaryrefslogtreecommitdiffstats
path: root/fs/afs/volume.c
blob: c82e1bb4f2dd366042b5a37409ca07d72c011f07 (plain) (blame)
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
/* AFS volume management
 *
 * Copyright (C) 2002 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/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include "volume.h"
#include "vnode.h"
#include "cell.h"
#include "cache.h"
#include "cmservice.h"
#include "fsclient.h"
#include "vlclient.h"
#include "internal.h"

#ifdef __KDEBUG
static const char *afs_voltypes[] = { "R/W", "R/O", "BAK" };
#endif

#ifdef AFS_CACHING_SUPPORT
static cachefs_match_val_t afs_volume_cache_match(void *target,
						  const void *entry);
static void afs_volume_cache_update(void *source, void *entry);

struct cachefs_index_def afs_volume_cache_index_def = {
	.name		= "volume",
	.data_size	= sizeof(struct afs_cache_vhash),
	.keys[0]	= { CACHEFS_INDEX_KEYS_BIN, 1 },
	.keys[1]	= { CACHEFS_INDEX_KEYS_BIN, 1 },
	.match		= afs_volume_cache_match,
	.update		= afs_volume_cache_update,
};
#endif

/*
 * lookup a volume by name
 * - this can be one of the following:
 *	"%[cell:]volume[.]"		R/W volume
 *	"#[cell:]volume[.]"		R/O or R/W volume (rwparent=0),
 *					 or R/W (rwparent=1) volume
 *	"%[cell:]volume.readonly"	R/O volume
 *	"#[cell:]volume.readonly"	R/O volume
 *	"%[cell:]volume.backup"		Backup volume
 *	"#[cell:]volume.backup"		Backup volume
 *
 * The cell name is optional, and defaults to the current cell.
 *
 * See "The Rules of Mount Point Traversal" in Chapter 5 of the AFS SysAdmin
 * Guide
 * - Rule 1: Explicit type suffix forces access of that type or nothing
 *           (no suffix, then use Rule 2 & 3)
 * - Rule 2: If parent volume is R/O, then mount R/O volume by preference, R/W
 *           if not available
 * - Rule 3: If parent volume is R/W, then only mount R/W volume unless
 *           explicitly told otherwise
 */
int afs_volume_lookup(const char *name, struct afs_cell *cell, int rwpath,
		      struct afs_volume **_volume)
{
	struct afs_vlocation *vlocation = NULL;
	struct afs_volume *volume = NULL;
	afs_voltype_t type;
	const char *cellname, *volname, *suffix;
	char srvtmask;
	int force, ret, loop, cellnamesz, volnamesz;

	_enter("%s,,%d,", name, rwpath);

	if (!name || (name[0] != '%' && name[0] != '#') || !name[1]) {
		printk("kAFS: unparsable volume name\n");
		return -EINVAL;
	}

	/* determine the type of volume we're looking for */
	force = 0;
	type = AFSVL_ROVOL;

	if (rwpath || name[0] == '%') {
		type = AFSVL_RWVOL;
		force = 1;
	}

	suffix = strrchr(name, '.');
	if (suffix) {
		if (strcmp(suffix, ".readonly") == 0) {
			type = AFSVL_ROVOL;
			force = 1;
		} else if (strcmp(suffix, ".backup") == 0) {
			type = AFSVL_BACKVOL;
			force = 1;
		} else if (suffix[1] == 0) {
		} else {
			suffix = NULL;
		}
	}

	/* split the cell and volume names */
	name++;
	volname = strchr(name, ':');
	if (volname) {
		cellname = name;
		cellnamesz = volname - name;
		volname++;
	} else {
		volname = name;
		cellname = NULL;
		cellnamesz = 0;
	}

	volnamesz = suffix ? suffix - volname : strlen(volname);

	_debug("CELL:%*.*s [%p] VOLUME:%*.*s SUFFIX:%s TYPE:%d%s",
	       cellnamesz, cellnamesz, cellname ?: "", cell,
	       volnamesz, volnamesz, volname, suffix ?: "-",
	       type,
	       force ? " FORCE" : "");

	/* lookup the cell record */
	if (cellname || !cell) {
		ret = afs_cell_lookup(cellname, cellnamesz, &cell);
		if (ret<0) {
			printk("kAFS: unable to lookup cell '%s'\n",
			       cellname ?: "");
			goto error;
		}
	} else {
		afs_get_cell(cell);
	}

	/* lookup the volume location record */
	ret = afs_vlocation_lookup(cell, volname, volnamesz, &vlocation);
	if (ret < 0)
		goto error;

	/* make the final decision on the type we want */
	ret = -ENOMEDIUM;
	if (force && !(vlocation->vldb.vidmask & (1 << type)))
		goto error;

	srvtmask = 0;
	for (loop = 0; loop < vlocation->vldb.nservers; loop++)
		srvtmask |= vlocation->vldb.srvtmask[loop];

	if (force) {
		if (!(srvtmask & (1 << type)))
			goto error;
	} else if (srvtmask & AFS_VOL_VTM_RO) {
		type = AFSVL_ROVOL;
	} else if (srvtmask & AFS_VOL_VTM_RW) {
		type = AFSVL_RWVOL;
	} else {
		goto error;
	}

	down_write(&cell->vl_sem);

	/* is the volume already active? */
	if (vlocation->vols[type]) {
		/* yes - re-use it */
		volume = vlocation->vols[type];
		afs_get_volume(volume);
		goto success;
	}

	/* create a new volume record */
	_debug("creating new volume record");

	ret = -ENOMEM;
	volume = kzalloc(sizeof(struct afs_volume), GFP_KERNEL);
	if (!volume)
		goto error_up;

	atomic_set(&volume->usage, 1);
	volume->type		= type;
	volume->type_force	= force;
	volume->cell		= cell;
	volume->vid		= vlocation->vldb.vid[type];

	init_rwsem(&volume->server_sem);

	/* look up all the applicable server records */
	for (loop = 0; loop < 8; loop++) {
		if (vlocation->vldb.srvtmask[loop] & (1 << volume->type)) {
			ret = afs_server_lookup(
				volume->cell,
				&vlocation->vldb.servers[loop],
				&volume->servers[volume->nservers]);
			if (ret < 0)
				goto error_discard;

			volume->nservers++;
		}
	}

	/* attach the cache and volume location */
#ifdef AFS_CACHING_SUPPORT
	cachefs_acquire_cookie(vlocation->cache,
			       &afs_vnode_cache_index_def,
			       volume,
			       &volume->cache);
#endif

	afs_get_vlocation(vlocation);
	volume->vlocation = vlocation;

	vlocation->vols[type] = volume;

success:
	_debug("kAFS selected %s volume %08x",
	       afs_voltypes[volume->type], volume->vid);
	*_volume = volume;
	ret = 0;

	/* clean up */
error_up:
	up_write(&cell->vl_sem);
error:
	afs_put_vlocation(vlocation);
	afs_put_cell(cell);

	_leave(" = %d (%p)", ret, volume);
	return ret;

error_discard:
	up_write(&cell->vl_sem);

	for (loop = volume->nservers - 1; loop >= 0; loop--)
		afs_put_server(volume->servers[loop]);

	kfree(volume);
	goto error;
}

/*
 * destroy a volume record
 */
void afs_put_volume(struct afs_volume *volume)
{
	struct afs_vlocation *vlocation;
	int loop;

	if (!volume)
		return;

	_enter("%p", volume);

	vlocation = volume->vlocation;

	/* sanity check */
	BUG_ON(atomic_read(&volume->usage) <= 0);

	/* to prevent a race, the decrement and the dequeue must be effectively
	 * atomic */
	down_write(&vlocation->cell->vl_sem);

	if (likely(!atomic_dec_and_test(&volume->usage))) {
		up_write(&vlocation->cell->vl_sem);
		_leave("");
		return;
	}

	vlocation->vols[volume->type] = NULL;

	up_write(&vlocation->cell->vl_sem);

	/* finish cleaning up the volume */
#ifdef AFS_CACHING_SUPPORT
	cachefs_relinquish_cookie(volume->cache, 0);
#endif
	afs_put_vlocation(vlocation);

	for (loop = volume->nservers - 1; loop >= 0; loop--)
		afs_put_server(volume->servers[loop]);

	kfree(volume);

	_leave(" [destroyed]");
}

/*
 * pick a server to use to try accessing this volume
 * - returns with an elevated usage count on the server chosen
 */
int afs_volume_pick_fileserver(struct afs_volume *volume,
			       struct afs_server **_server)
{
	struct afs_server *server;
	int ret, state, loop;

	_enter("%s", volume->vlocation->vldb.name);

	down_read(&volume->server_sem);

	/* handle the no-server case */
	if (volume->nservers == 0) {
		ret = volume->rjservers ? -ENOMEDIUM : -ESTALE;
		up_read(&volume->server_sem);
		_leave(" = %d [no servers]", ret);
		return ret;
	}

	/* basically, just search the list for the first live server and use
	 * that */
	ret = 0;
	for (loop = 0; loop < volume->nservers; loop++) {
		server = volume->servers[loop];
		state = server->fs_state;

		switch (state) {
			/* found an apparently healthy server */
		case 0:
			afs_get_server(server);
			up_read(&volume->server_sem);
			*_server = server;
			_leave(" = 0 (picked %08x)",
			       ntohl(server->addr.s_addr));
			return 0;

		case -ENETUNREACH:
			if (ret == 0)
				ret = state;
			break;

		case -EHOSTUNREACH:
			if (ret == 0 ||
			    ret == -ENETUNREACH)
				ret = state;
			break;

		case -ECONNREFUSED:
			if (ret == 0 ||
			    ret == -ENETUNREACH ||
			    ret == -EHOSTUNREACH)
				ret = state;
			break;

		default:
		case -EREMOTEIO:
			if (ret == 0 ||
			    ret == -ENETUNREACH ||
			    ret == -EHOSTUNREACH ||
			    ret == -ECONNREFUSED)
				ret = state;
			break;
		}
	}

	/* no available servers
	 * - TODO: handle the no active servers case better
	 */
	up_read(&volume->server_sem);
	_leave(" = %d", ret);
	return ret;
}

/*
 * release a server after use
 * - releases the ref on the server struct that was acquired by picking
 * - records result of using a particular server to access a volume
 * - return 0 to try again, 1 if okay or to issue error
 */
int afs_volume_release_fileserver(struct afs_volume *volume,
				  struct afs_server *server,
				  int result)
{
	unsigned loop;

	_enter("%s,%08x,%d",
	       volume->vlocation->vldb.name, ntohl(server->addr.s_addr),
	       result);

	switch (result) {
		/* success */
	case 0:
		server->fs_act_jif = jiffies;
		break;

		/* the fileserver denied all knowledge of the volume */
	case -ENOMEDIUM:
		server->fs_act_jif = jiffies;
		down_write(&volume->server_sem);

		/* first, find where the server is in the active list (if it
		 * is) */
		for (loop = 0; loop < volume->nservers; loop++)
			if (volume->servers[loop] == server)
				goto present;

		/* no longer there - may have been discarded by another op */
		goto try_next_server_upw;

	present:
		volume->nservers--;
		memmove(&volume->servers[loop],
			&volume->servers[loop + 1],
			sizeof(volume->servers[loop]) *
			(volume->nservers - loop));
		volume->servers[volume->nservers] = NULL;
		afs_put_server(server);
		volume->rjservers++;

		if (volume->nservers > 0)
			/* another server might acknowledge its existence */
			goto try_next_server_upw;

		/* handle the case where all the fileservers have rejected the
		 * volume
		 * - TODO: try asking the fileservers for volume information
		 * - TODO: contact the VL server again to see if the volume is
		 *         no longer registered
		 */
		up_write(&volume->server_sem);
		afs_put_server(server);
		_leave(" [completely rejected]");
		return 1;

		/* problem reaching the server */
	case -ENETUNREACH:
	case -EHOSTUNREACH:
	case -ECONNREFUSED:
	case -ETIMEDOUT:
	case -EREMOTEIO:
		/* mark the server as dead
		 * TODO: vary dead timeout depending on error
		 */
		spin_lock(&server->fs_lock);
		if (!server->fs_state) {
			server->fs_dead_jif = jiffies + HZ * 10;
			server->fs_state = result;
			printk("kAFS: SERVER DEAD state=%d\n", result);
		}
		spin_unlock(&server->fs_lock);
		goto try_next_server;

		/* miscellaneous error */
	default:
		server->fs_act_jif = jiffies;
	case -ENOMEM:
	case -ENONET:
		break;
	}

	/* tell the caller to accept the result */
	afs_put_server(server);
	_leave("");
	return 1;

	/* tell the caller to loop around and try the next server */
try_next_server_upw:
	up_write(&volume->server_sem);
try_next_server:
	afs_put_server(server);
	_leave(" [try next server]");
	return 0;
}

/*
 * match a volume hash record stored in the cache
 */
#ifdef AFS_CACHING_SUPPORT
static cachefs_match_val_t afs_volume_cache_match(void *target,
						  const void *entry)
{
	const struct afs_cache_vhash *vhash = entry;
	struct afs_volume *volume = target;

	_enter("{%u},{%u}", volume->type, vhash->vtype);

	if (volume->type == vhash->vtype) {
		_leave(" = SUCCESS");
		return CACHEFS_MATCH_SUCCESS;
	}

	_leave(" = FAILED");
	return CACHEFS_MATCH_FAILED;
}
#endif

/*
 * update a volume hash record stored in the cache
 */
#ifdef AFS_CACHING_SUPPORT
static void afs_volume_cache_update(void *source, void *entry)
{
	struct afs_cache_vhash *vhash = entry;
	struct afs_volume *volume = source;

	_enter("");

	vhash->vtype = volume->type;
}
#endif