summaryrefslogtreecommitdiffstats
path: root/fs/afs/validation.c
blob: 32a53fc8dfb26b292c0817155a7c9d387d66064d (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
// SPDX-License-Identifier: GPL-2.0-or-later
/* vnode and volume validity verification.
 *
 * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include "internal.h"

/*
 * Data validation is managed through a number of mechanisms from the server:
 *
 *  (1) On first contact with a server (such as if it has just been rebooted),
 *      the server sends us a CB.InitCallBackState* request.
 *
 *  (2) On a RW volume, in response to certain vnode (inode)-accessing RPC
 *      calls, the server maintains a time-limited per-vnode promise that it
 *      will send us a CB.CallBack request if a third party alters the vnodes
 *      accessed.
 *
 *      Note that a vnode-level callbacks may also be sent for other reasons,
 *      such as filelock release.
 *
 *  (3) On a RO (or Backup) volume, in response to certain vnode-accessing RPC
 *      calls, each server maintains a time-limited per-volume promise that it
 *      will send us a CB.CallBack request if the RO volume is updated to a
 *      snapshot of the RW volume ("vos release").  This is an atomic event
 *      that cuts over all instances of the RO volume across multiple servers
 *      simultaneously.
 *
 *	Note that a volume-level callbacks may also be sent for other reasons,
 *	such as the volumeserver taking over control of the volume from the
 *	fileserver.
 *
 *	Note also that each server maintains an independent time limit on an
 *	independent callback.
 *
 *  (4) Certain RPC calls include a volume information record "VolSync" in
 *      their reply.  This contains a creation date for the volume that should
 *      remain unchanged for a RW volume (but will be changed if the volume is
 *      restored from backup) or will be bumped to the time of snapshotting
 *      when a RO volume is released.
 *
 * In order to track this events, the following are provided:
 *
 *	->cb_v_break.  A counter of events that might mean that the contents of
 *	a volume have been altered since we last checked a vnode.
 *
 *	->cb_v_check.  A counter of the number of events that we've sent a
 *	query to the server for.  Everything's up to date if this equals
 *	cb_v_break.
 *
 *	->cb_scrub.  A counter of the number of regression events for which we
 *	have to completely wipe the cache.
 *
 *	->cb_ro_snapshot.  A counter of the number of times that we've
 *      recognised that a RO volume has been updated.
 *
 *	->cb_break.  A counter of events that might mean that the contents of a
 *      vnode have been altered.
 *
 *	->cb_expires_at.  The time at which the callback promise expires or
 *      AFS_NO_CB_PROMISE if we have no promise.
 *
 * The way we manage things is:
 *
 *  (1) When a volume-level CB.CallBack occurs, we increment ->cb_v_break on
 *      the volume and reset ->cb_expires_at (ie. set AFS_NO_CB_PROMISE) on the
 *      volume and volume's server record.
 *
 *  (2) When a CB.InitCallBackState occurs, we treat this as a volume-level
 *	callback break on all the volumes that have been using that volume
 *	(ie. increment ->cb_v_break and reset ->cb_expires_at).
 *
 *  (3) When a vnode-level CB.CallBack occurs, we increment ->cb_break on the
 *	vnode and reset its ->cb_expires_at.  If the vnode is mmapped, we also
 *	dispatch a work item to unmap all PTEs to the vnode's pagecache to
 *	force reentry to the filesystem for revalidation.
 *
 *  (4) When entering the filesystem, we call afs_validate() to check the
 *	validity of a vnode.  This first checks to see if ->cb_v_check and
 *	->cb_v_break match, and if they don't, we lock volume->cb_check_lock
 *	exclusively and perform an FS.FetchStatus on the vnode.
 *
 *	After checking the volume, we check the vnode.  If there's a mismatch
 *	between the volume counters and the vnode's mirrors of those counters,
 *	we lock vnode->validate_lock and issue an FS.FetchStatus on the vnode.
 *
 *  (5) When the reply from FS.FetchStatus arrives, the VolSync record is
 *      parsed:
 *
 *	(A) If the Creation timestamp has changed on a RW volume or regressed
 *	    on a RO volume, we try to increment ->cb_scrub; if it advances on a
 *	    RO volume, we assume "vos release" happened and try to increment
 *	    ->cb_ro_snapshot.
 *
 *      (B) If the Update timestamp has regressed, we try to increment
 *	    ->cb_scrub.
 *
 *      Note that in both of these cases, we only do the increment if we can
 *      cmpxchg the value of the timestamp from the value we noted before the
 *      op.  This tries to prevent parallel ops from fighting one another.
 *
 *	volume->cb_v_check is then set to ->cb_v_break.
 *
 *  (6) The AFSCallBack record included in the FS.FetchStatus reply is also
 *	parsed and used to set the promise in ->cb_expires_at for the vnode,
 *	the volume and the volume's server record.
 *
 *  (7) If ->cb_scrub is seen to have advanced, we invalidate the pagecache for
 *      the vnode.
 */

/*
 * Check the validity of a vnode/inode and its parent volume.
 */
bool afs_check_validity(const struct afs_vnode *vnode)
{
	const struct afs_volume *volume = vnode->volume;
	time64_t deadline = ktime_get_real_seconds() + 10;

	if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
		return true;

	if (atomic_read(&volume->cb_v_check) != atomic_read(&volume->cb_v_break) ||
	    atomic64_read(&vnode->cb_expires_at)  <= deadline ||
	    volume->cb_expires_at <= deadline ||
	    vnode->cb_ro_snapshot != atomic_read(&volume->cb_ro_snapshot) ||
	    vnode->cb_scrub	  != atomic_read(&volume->cb_scrub) ||
	    test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) {
		_debug("inval");
		return false;
	}

	return true;
}

/*
 * See if the server we've just talked to is currently excluded.
 */
static bool __afs_is_server_excluded(struct afs_operation *op, struct afs_volume *volume)
{
	const struct afs_server_entry *se;
	const struct afs_server_list *slist;
	bool is_excluded = true;
	int i;

	rcu_read_lock();

	slist = rcu_dereference(volume->servers);
	for (i = 0; i < slist->nr_servers; i++) {
		se = &slist->servers[i];
		if (op->server == se->server) {
			is_excluded = test_bit(AFS_SE_EXCLUDED, &se->flags);
			break;
		}
	}

	rcu_read_unlock();
	return is_excluded;
}

/*
 * Update the volume's server list when the creation time changes and see if
 * the server we've just talked to is currently excluded.
 */
static int afs_is_server_excluded(struct afs_operation *op, struct afs_volume *volume)
{
	int ret;

	if (__afs_is_server_excluded(op, volume))
		return 1;

	set_bit(AFS_VOLUME_NEEDS_UPDATE, &volume->flags);
	ret = afs_check_volume_status(op->volume, op);
	if (ret < 0)
		return ret;

	return __afs_is_server_excluded(op, volume);
}

/*
 * Handle a change to the volume creation time in the VolSync record.
 */
static int afs_update_volume_creation_time(struct afs_operation *op, struct afs_volume *volume)
{
	unsigned int snap;
	time64_t cur = volume->creation_time;
	time64_t old = op->pre_volsync.creation;
	time64_t new = op->volsync.creation;
	int ret;

	_enter("%llx,%llx,%llx->%llx", volume->vid, cur, old, new);

	if (cur == TIME64_MIN) {
		volume->creation_time = new;
		return 0;
	}

	if (new == cur)
		return 0;

	/* Try to advance the creation timestamp from what we had before the
	 * operation to what we got back from the server.  This should
	 * hopefully ensure that in a race between multiple operations only one
	 * of them will do this.
	 */
	if (cur != old)
		return 0;

	/* If the creation time changes in an unexpected way, we need to scrub
	 * our caches.  For a RW vol, this will only change if the volume is
	 * restored from a backup; for a RO/Backup vol, this will advance when
	 * the volume is updated to a new snapshot (eg. "vos release").
	 */
	if (volume->type == AFSVL_RWVOL)
		goto regressed;
	if (volume->type == AFSVL_BACKVOL) {
		if (new < old)
			goto regressed;
		goto advance;
	}

	/* We have an RO volume, we need to query the VL server and look at the
	 * server flags to see if RW->RO replication is in progress.
	 */
	ret = afs_is_server_excluded(op, volume);
	if (ret < 0)
		return ret;
	if (ret > 0) {
		snap = atomic_read(&volume->cb_ro_snapshot);
		trace_afs_cb_v_break(volume->vid, snap, afs_cb_break_volume_excluded);
		return ret;
	}

advance:
	snap = atomic_inc_return(&volume->cb_ro_snapshot);
	trace_afs_cb_v_break(volume->vid, snap, afs_cb_break_for_vos_release);
	volume->creation_time = new;
	return 0;

regressed:
	atomic_inc(&volume->cb_scrub);
	trace_afs_cb_v_break(volume->vid, 0, afs_cb_break_for_creation_regress);
	volume->creation_time = new;
	return 0;
}

/*
 * Handle a change to the volume update time in the VolSync record.
 */
static void afs_update_volume_update_time(struct afs_operation *op, struct afs_volume *volume)
{
	enum afs_cb_break_reason reason = afs_cb_break_no_break;
	time64_t cur = volume->update_time;
	time64_t old = op->pre_volsync.update;
	time64_t new = op->volsync.update;

	_enter("%llx,%llx,%llx->%llx", volume->vid, cur, old, new);

	if (cur == TIME64_MIN) {
		volume->update_time = new;
		return;
	}

	if (new == cur)
		return;

	/* If the volume update time changes in an unexpected way, we need to
	 * scrub our caches.  For a RW vol, this will advance on every
	 * modification op; for a RO/Backup vol, this will advance when the
	 * volume is updated to a new snapshot (eg. "vos release").
	 */
	if (new < old)
		reason = afs_cb_break_for_update_regress;

	/* Try to advance the update timestamp from what we had before the
	 * operation to what we got back from the server.  This should
	 * hopefully ensure that in a race between multiple operations only one
	 * of them will do this.
	 */
	if (cur == old) {
		if (reason == afs_cb_break_for_update_regress) {
			atomic_inc(&volume->cb_scrub);
			trace_afs_cb_v_break(volume->vid, 0, reason);
		}
		volume->update_time = new;
	}
}

static int afs_update_volume_times(struct afs_operation *op, struct afs_volume *volume)
{
	int ret = 0;

	if (likely(op->volsync.creation == volume->creation_time &&
		   op->volsync.update == volume->update_time))
		return 0;

	mutex_lock(&volume->volsync_lock);
	if (op->volsync.creation != volume->creation_time) {
		ret = afs_update_volume_creation_time(op, volume);
		if (ret < 0)
			goto out;
	}
	if (op->volsync.update != volume->update_time)
		afs_update_volume_update_time(op, volume);
out:
	mutex_unlock(&volume->volsync_lock);
	return ret;
}

/*
 * Update the state of a volume, including recording the expiration time of the
 * callback promise.  Returns 1 to redo the operation from the start.
 */
int afs_update_volume_state(struct afs_operation *op)
{
	struct afs_server_list *slist = op->server_list;
	struct afs_server_entry *se = &slist->servers[op->server_index];
	struct afs_callback *cb = &op->file[0].scb.callback;
	struct afs_volume *volume = op->volume;
	unsigned int cb_v_break = atomic_read(&volume->cb_v_break);
	unsigned int cb_v_check = atomic_read(&volume->cb_v_check);
	int ret;

	_enter("%llx", op->volume->vid);

	if (op->volsync.creation != TIME64_MIN || op->volsync.update != TIME64_MIN) {
		ret = afs_update_volume_times(op, volume);
		if (ret != 0) {
			_leave(" = %d", ret);
			return ret;
		}
	}

	if (op->cb_v_break == cb_v_break &&
	    (op->file[0].scb.have_cb || op->file[1].scb.have_cb)) {
		time64_t expires_at = cb->expires_at;

		if (!op->file[0].scb.have_cb)
			expires_at = op->file[1].scb.callback.expires_at;

		se->cb_expires_at = expires_at;
		volume->cb_expires_at = expires_at;
	}
	if (cb_v_check < op->cb_v_break)
		atomic_cmpxchg(&volume->cb_v_check, cb_v_check, op->cb_v_break);
	return 0;
}

/*
 * mark the data attached to an inode as obsolete due to a write on the server
 * - might also want to ditch all the outstanding writes and dirty pages
 */
static void afs_zap_data(struct afs_vnode *vnode)
{
	_enter("{%llx:%llu}", vnode->fid.vid, vnode->fid.vnode);

	afs_invalidate_cache(vnode, 0);

	/* nuke all the non-dirty pages that aren't locked, mapped or being
	 * written back in a regular file and completely discard the pages in a
	 * directory or symlink */
	if (S_ISREG(vnode->netfs.inode.i_mode))
		invalidate_remote_inode(&vnode->netfs.inode);
	else
		invalidate_inode_pages2(vnode->netfs.inode.i_mapping);
}

/*
 * validate a vnode/inode
 * - there are several things we need to check
 *   - parent dir data changes (rm, rmdir, rename, mkdir, create, link,
 *     symlink)
 *   - parent dir metadata changed (security changes)
 *   - dentry data changed (write, truncate)
 *   - dentry metadata changed (security changes)
 */
int afs_validate(struct afs_vnode *vnode, struct key *key)
{
	struct afs_volume *volume = vnode->volume;
	unsigned int cb_ro_snapshot, cb_scrub;
	time64_t deadline = ktime_get_real_seconds() + 10;
	bool zap = false, locked_vol = false;
	int ret;

	_enter("{v={%llx:%llu} fl=%lx},%x",
	       vnode->fid.vid, vnode->fid.vnode, vnode->flags,
	       key_serial(key));

	if (afs_check_validity(vnode))
		return test_bit(AFS_VNODE_DELETED, &vnode->flags) ? -ESTALE : 0;

	ret = down_write_killable(&vnode->validate_lock);
	if (ret < 0)
		goto error;

	if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
		ret = -ESTALE;
		goto error_unlock;
	}

	/* Validate a volume after the v_break has changed or the volume
	 * callback expired.  We only want to do this once per volume per
	 * v_break change.  The actual work will be done when parsing the
	 * status fetch reply.
	 */
	if (volume->cb_expires_at <= deadline ||
	    atomic_read(&volume->cb_v_check) != atomic_read(&volume->cb_v_break)) {
		ret = mutex_lock_interruptible(&volume->cb_check_lock);
		if (ret < 0)
			goto error_unlock;
		locked_vol = true;
	}

	cb_ro_snapshot = atomic_read(&volume->cb_ro_snapshot);
	cb_scrub = atomic_read(&volume->cb_scrub);
	if (vnode->cb_ro_snapshot != cb_ro_snapshot ||
	    vnode->cb_scrub	  != cb_scrub)
		unmap_mapping_pages(vnode->netfs.inode.i_mapping, 0, 0, false);

	if (vnode->cb_ro_snapshot != cb_ro_snapshot ||
	    vnode->cb_scrub	  != cb_scrub ||
	    volume->cb_expires_at <= deadline ||
	    atomic_read(&volume->cb_v_check) != atomic_read(&volume->cb_v_break) ||
	    atomic64_read(&vnode->cb_expires_at) <= deadline
	    ) {
		ret = afs_fetch_status(vnode, key, false, NULL);
		if (ret < 0) {
			if (ret == -ENOENT) {
				set_bit(AFS_VNODE_DELETED, &vnode->flags);
				ret = -ESTALE;
			}
			goto error_unlock;
		}

		_debug("new promise [fl=%lx]", vnode->flags);
	}

	/* We can drop the volume lock now as. */
	if (locked_vol) {
		mutex_unlock(&volume->cb_check_lock);
		locked_vol = false;
	}

	cb_ro_snapshot = atomic_read(&volume->cb_ro_snapshot);
	cb_scrub = atomic_read(&volume->cb_scrub);
	_debug("vnode inval %x==%x %x==%x",
	       vnode->cb_ro_snapshot, cb_ro_snapshot,
	       vnode->cb_scrub, cb_scrub);
	if (vnode->cb_scrub != cb_scrub)
		zap = true;
	vnode->cb_ro_snapshot = cb_ro_snapshot;
	vnode->cb_scrub = cb_scrub;

	/* if the vnode's data version number changed then its contents are
	 * different */
	zap |= test_and_clear_bit(AFS_VNODE_ZAP_DATA, &vnode->flags);
	if (zap)
		afs_zap_data(vnode);
	up_write(&vnode->validate_lock);
	_leave(" = 0");
	return 0;

error_unlock:
	if (locked_vol)
		mutex_unlock(&volume->cb_check_lock);
	up_write(&vnode->validate_lock);
error:
	_leave(" = %d", ret);
	return ret;
}