summaryrefslogtreecommitdiffstats
path: root/fs/afs/inode.c
blob: d6eed332507f0231d849f706b3079b9e6f5b1047 (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
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
/*
 * Copyright (c) 2002 Red Hat, Inc. All rights reserved.
 *
 * This software may be freely redistributed under the terms of the
 * GNU General Public License.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 *
 * Authors: David Woodhouse <dwmw2@infradead.org>
 *          David Howells <dhowells@redhat.com>
 *
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/sched.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/iversion.h>
#include "internal.h"
#include "afs_fs.h"

static const struct inode_operations afs_symlink_inode_operations = {
	.get_link	= page_get_link,
};

static noinline void dump_vnode(struct afs_vnode *vnode, struct afs_vnode *parent_vnode)
{
	static unsigned long once_only;

	pr_warn("kAFS: AFS vnode with undefined type %u\n", vnode->status.type);
	pr_warn("kAFS: A=%d m=%o s=%llx v=%llx\n",
		vnode->status.abort_code,
		vnode->status.mode,
		vnode->status.size,
		vnode->status.data_version);
	pr_warn("kAFS: vnode %llx:%llx:%x\n",
		vnode->fid.vid,
		vnode->fid.vnode,
		vnode->fid.unique);
	if (parent_vnode)
		pr_warn("kAFS: dir %llx:%llx:%x\n",
			parent_vnode->fid.vid,
			parent_vnode->fid.vnode,
			parent_vnode->fid.unique);

	if (!test_and_set_bit(0, &once_only))
		dump_stack();
}

/*
 * Set parameters for the netfs library
 */
static void afs_set_netfs_context(struct afs_vnode *vnode)
{
	netfs_inode_init(&vnode->netfs, &afs_req_ops);
}

/*
 * Initialise an inode from the vnode status.
 */
static int afs_inode_init_from_status(struct afs_operation *op,
				      struct afs_vnode_param *vp,
				      struct afs_vnode *vnode)
{
	struct afs_file_status *status = &vp->scb.status;
	struct inode *inode = AFS_VNODE_TO_I(vnode);
	struct timespec64 t;

	_enter("{%llx:%llu.%u} %s",
	       vp->fid.vid, vp->fid.vnode, vp->fid.unique,
	       op->type ? op->type->name : "???");

	_debug("FS: ft=%d lk=%d sz=%llu ver=%Lu mod=%hu",
	       status->type,
	       status->nlink,
	       (unsigned long long) status->size,
	       status->data_version,
	       status->mode);

	write_seqlock(&vnode->cb_lock);

	vnode->cb_v_break = op->cb_v_break;
	vnode->cb_s_break = op->cb_s_break;
	vnode->status = *status;

	t = status->mtime_client;
	inode_set_ctime_to_ts(inode, t);
	inode_set_mtime_to_ts(inode, t);
	inode_set_atime_to_ts(inode, t);
	inode->i_flags |= S_NOATIME;
	inode->i_uid = make_kuid(&init_user_ns, status->owner);
	inode->i_gid = make_kgid(&init_user_ns, status->group);
	set_nlink(&vnode->netfs.inode, status->nlink);

	switch (status->type) {
	case AFS_FTYPE_FILE:
		inode->i_mode	= S_IFREG | (status->mode & S_IALLUGO);
		inode->i_op	= &afs_file_inode_operations;
		inode->i_fop	= &afs_file_operations;
		inode->i_mapping->a_ops	= &afs_file_aops;
		mapping_set_large_folios(inode->i_mapping);
		break;
	case AFS_FTYPE_DIR:
		inode->i_mode	= S_IFDIR |  (status->mode & S_IALLUGO);
		inode->i_op	= &afs_dir_inode_operations;
		inode->i_fop	= &afs_dir_file_operations;
		inode->i_mapping->a_ops	= &afs_dir_aops;
		mapping_set_large_folios(inode->i_mapping);
		break;
	case AFS_FTYPE_SYMLINK:
		/* Symlinks with a mode of 0644 are actually mountpoints. */
		if ((status->mode & 0777) == 0644) {
			inode->i_flags |= S_AUTOMOUNT;

			set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);

			inode->i_mode	= S_IFDIR | 0555;
			inode->i_op	= &afs_mntpt_inode_operations;
			inode->i_fop	= &afs_mntpt_file_operations;
			inode->i_mapping->a_ops	= &afs_symlink_aops;
		} else {
			inode->i_mode	= S_IFLNK | status->mode;
			inode->i_op	= &afs_symlink_inode_operations;
			inode->i_mapping->a_ops	= &afs_symlink_aops;
		}
		inode_nohighmem(inode);
		break;
	default:
		dump_vnode(vnode, op->file[0].vnode != vnode ? op->file[0].vnode : NULL);
		write_sequnlock(&vnode->cb_lock);
		return afs_protocol_error(NULL, afs_eproto_file_type);
	}

	afs_set_i_size(vnode, status->size);
	afs_set_netfs_context(vnode);

	vnode->invalid_before	= status->data_version;
	inode_set_iversion_raw(&vnode->netfs.inode, status->data_version);

	if (!vp->scb.have_cb) {
		/* it's a symlink we just created (the fileserver
		 * didn't give us a callback) */
		vnode->cb_expires_at = ktime_get_real_seconds();
	} else {
		vnode->cb_expires_at = vp->scb.callback.expires_at;
		vnode->cb_server = op->server;
		set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
	}

	write_sequnlock(&vnode->cb_lock);
	return 0;
}

/*
 * Update the core inode struct from a returned status record.
 */
static void afs_apply_status(struct afs_operation *op,
			     struct afs_vnode_param *vp)
{
	struct afs_file_status *status = &vp->scb.status;
	struct afs_vnode *vnode = vp->vnode;
	struct inode *inode = &vnode->netfs.inode;
	struct timespec64 t;
	umode_t mode;
	bool data_changed = false;
	bool change_size = vp->set_size;

	_enter("{%llx:%llu.%u} %s",
	       vp->fid.vid, vp->fid.vnode, vp->fid.unique,
	       op->type ? op->type->name : "???");

	BUG_ON(test_bit(AFS_VNODE_UNSET, &vnode->flags));

	if (status->type != vnode->status.type) {
		pr_warn("Vnode %llx:%llx:%x changed type %u to %u\n",
			vnode->fid.vid,
			vnode->fid.vnode,
			vnode->fid.unique,
			status->type, vnode->status.type);
		afs_protocol_error(NULL, afs_eproto_bad_status);
		return;
	}

	if (status->nlink != vnode->status.nlink)
		set_nlink(inode, status->nlink);

	if (status->owner != vnode->status.owner)
		inode->i_uid = make_kuid(&init_user_ns, status->owner);

	if (status->group != vnode->status.group)
		inode->i_gid = make_kgid(&init_user_ns, status->group);

	if (status->mode != vnode->status.mode) {
		mode = inode->i_mode;
		mode &= ~S_IALLUGO;
		mode |= status->mode & S_IALLUGO;
		WRITE_ONCE(inode->i_mode, mode);
	}

	t = status->mtime_client;
	inode_set_mtime_to_ts(inode, t);
	if (vp->update_ctime)
		inode_set_ctime_to_ts(inode, op->ctime);

	if (vnode->status.data_version != status->data_version)
		data_changed = true;

	vnode->status = *status;

	if (vp->dv_before + vp->dv_delta != status->data_version) {
		if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags))
			pr_warn("kAFS: vnode modified {%llx:%llu} %llx->%llx %s (op=%x)\n",
				vnode->fid.vid, vnode->fid.vnode,
				(unsigned long long)vp->dv_before + vp->dv_delta,
				(unsigned long long)status->data_version,
				op->type ? op->type->name : "???",
				op->debug_id);

		vnode->invalid_before = status->data_version;
		if (vnode->status.type == AFS_FTYPE_DIR) {
			if (test_and_clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags))
				afs_stat_v(vnode, n_inval);
		} else {
			set_bit(AFS_VNODE_ZAP_DATA, &vnode->flags);
		}
		change_size = true;
		data_changed = true;
	} else if (vnode->status.type == AFS_FTYPE_DIR) {
		/* Expected directory change is handled elsewhere so
		 * that we can locally edit the directory and save on a
		 * download.
		 */
		if (test_bit(AFS_VNODE_DIR_VALID, &vnode->flags))
			data_changed = false;
		change_size = true;
	}

	if (data_changed) {
		inode_set_iversion_raw(inode, status->data_version);

		/* Only update the size if the data version jumped.  If the
		 * file is being modified locally, then we might have our own
		 * idea of what the size should be that's not the same as
		 * what's on the server.
		 */
		vnode->netfs.remote_i_size = status->size;
		if (change_size) {
			afs_set_i_size(vnode, status->size);
			inode_set_ctime_to_ts(inode, t);
			inode_set_atime_to_ts(inode, t);
		}
	}
}

/*
 * Apply a callback to a vnode.
 */
static void afs_apply_callback(struct afs_operation *op,
			       struct afs_vnode_param *vp)
{
	struct afs_callback *cb = &vp->scb.callback;
	struct afs_vnode *vnode = vp->vnode;

	if (!afs_cb_is_broken(vp->cb_break_before, vnode)) {
		vnode->cb_expires_at	= cb->expires_at;
		vnode->cb_server	= op->server;
		set_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
	}
}

/*
 * Apply the received status and callback to an inode all in the same critical
 * section to avoid races with afs_validate().
 */
void afs_vnode_commit_status(struct afs_operation *op, struct afs_vnode_param *vp)
{
	struct afs_vnode *vnode = vp->vnode;

	_enter("");

	write_seqlock(&vnode->cb_lock);

	if (vp->scb.have_error) {
		/* A YFS server will return this from RemoveFile2 and AFS and
		 * YFS will return this from InlineBulkStatus.
		 */
		if (vp->scb.status.abort_code == VNOVNODE) {
			set_bit(AFS_VNODE_DELETED, &vnode->flags);
			clear_nlink(&vnode->netfs.inode);
			__afs_break_callback(vnode, afs_cb_break_for_deleted);
			op->flags &= ~AFS_OPERATION_DIR_CONFLICT;
		}
	} else if (vp->scb.have_status) {
		if (vp->speculative &&
		    (test_bit(AFS_VNODE_MODIFYING, &vnode->flags) ||
		     vp->dv_before != vnode->status.data_version))
			/* Ignore the result of a speculative bulk status fetch
			 * if it splits around a modification op, thereby
			 * appearing to regress the data version.
			 */
			goto out;
		afs_apply_status(op, vp);
		if (vp->scb.have_cb)
			afs_apply_callback(op, vp);
	} else if (vp->op_unlinked && !(op->flags & AFS_OPERATION_DIR_CONFLICT)) {
		drop_nlink(&vnode->netfs.inode);
		if (vnode->netfs.inode.i_nlink == 0) {
			set_bit(AFS_VNODE_DELETED, &vnode->flags);
			__afs_break_callback(vnode, afs_cb_break_for_deleted);
		}
	}

out:
	write_sequnlock(&vnode->cb_lock);

	if (vp->scb.have_status)
		afs_cache_permit(vnode, op->key, vp->cb_break_before, &vp->scb);
}

static void afs_fetch_status_success(struct afs_operation *op)
{
	struct afs_vnode_param *vp = &op->file[op->fetch_status.which];
	struct afs_vnode *vnode = vp->vnode;
	int ret;

	if (vnode->netfs.inode.i_state & I_NEW) {
		ret = afs_inode_init_from_status(op, vp, vnode);
		afs_op_set_error(op, ret);
		if (ret == 0)
			afs_cache_permit(vnode, op->key, vp->cb_break_before, &vp->scb);
	} else {
		afs_vnode_commit_status(op, vp);
	}
}

const struct afs_operation_ops afs_fetch_status_operation = {
	.issue_afs_rpc	= afs_fs_fetch_status,
	.issue_yfs_rpc	= yfs_fs_fetch_status,
	.success	= afs_fetch_status_success,
	.aborted	= afs_check_for_remote_deletion,
};

/*
 * Fetch file status from the volume.
 */
int afs_fetch_status(struct afs_vnode *vnode, struct key *key, bool is_new,
		     afs_access_t *_caller_access)
{
	struct afs_operation *op;

	_enter("%s,{%llx:%llu.%u,S=%lx}",
	       vnode->volume->name,
	       vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique,
	       vnode->flags);

	op = afs_alloc_operation(key, vnode->volume);
	if (IS_ERR(op))
		return PTR_ERR(op);

	afs_op_set_vnode(op, 0, vnode);

	op->nr_files	= 1;
	op->ops		= &afs_fetch_status_operation;
	afs_begin_vnode_operation(op);
	afs_wait_for_operation(op);

	if (_caller_access)
		*_caller_access = op->file[0].scb.status.caller_access;
	return afs_put_operation(op);
}

/*
 * ilookup() comparator
 */
int afs_ilookup5_test_by_fid(struct inode *inode, void *opaque)
{
	struct afs_vnode *vnode = AFS_FS_I(inode);
	struct afs_fid *fid = opaque;

	return (fid->vnode == vnode->fid.vnode &&
		fid->vnode_hi == vnode->fid.vnode_hi &&
		fid->unique == vnode->fid.unique);
}

/*
 * iget5() comparator
 */
static int afs_iget5_test(struct inode *inode, void *opaque)
{
	struct afs_vnode_param *vp = opaque;
	//struct afs_vnode *vnode = AFS_FS_I(inode);

	return afs_ilookup5_test_by_fid(inode, &vp->fid);
}

/*
 * iget5() inode initialiser
 */
static int afs_iget5_set(struct inode *inode, void *opaque)
{
	struct afs_vnode_param *vp = opaque;
	struct afs_super_info *as = AFS_FS_S(inode->i_sb);
	struct afs_vnode *vnode = AFS_FS_I(inode);

	vnode->volume		= as->volume;
	vnode->fid		= vp->fid;

	/* YFS supports 96-bit vnode IDs, but Linux only supports
	 * 64-bit inode numbers.
	 */
	inode->i_ino		= vnode->fid.vnode;
	inode->i_generation	= vnode->fid.unique;
	return 0;
}

/*
 * Get a cache cookie for an inode.
 */
static void afs_get_inode_cache(struct afs_vnode *vnode)
{
#ifdef CONFIG_AFS_FSCACHE
	struct {
		__be32 vnode_id;
		__be32 unique;
		__be32 vnode_id_ext[2];	/* Allow for a 96-bit key */
	} __packed key;
	struct afs_vnode_cache_aux aux;

	if (vnode->status.type != AFS_FTYPE_FILE) {
		vnode->netfs.cache = NULL;
		return;
	}

	key.vnode_id		= htonl(vnode->fid.vnode);
	key.unique		= htonl(vnode->fid.unique);
	key.vnode_id_ext[0]	= htonl(vnode->fid.vnode >> 32);
	key.vnode_id_ext[1]	= htonl(vnode->fid.vnode_hi);
	afs_set_cache_aux(vnode, &aux);

	afs_vnode_set_cache(vnode,
			    fscache_acquire_cookie(
				    vnode->volume->cache,
				    vnode->status.type == AFS_FTYPE_FILE ?
				    0 : FSCACHE_ADV_SINGLE_CHUNK,
				    &key, sizeof(key),
				    &aux, sizeof(aux),
				    i_size_read(&vnode->netfs.inode)));
#endif
}

/*
 * inode retrieval
 */
struct inode *afs_iget(struct afs_operation *op, struct afs_vnode_param *vp)
{
	struct afs_vnode_param *dvp = &op->file[0];
	struct super_block *sb = dvp->vnode->netfs.inode.i_sb;
	struct afs_vnode *vnode;
	struct inode *inode;
	int ret;

	_enter(",{%llx:%llu.%u},,", vp->fid.vid, vp->fid.vnode, vp->fid.unique);

	inode = iget5_locked(sb, vp->fid.vnode, afs_iget5_test, afs_iget5_set, vp);
	if (!inode) {
		_leave(" = -ENOMEM");
		return ERR_PTR(-ENOMEM);
	}

	vnode = AFS_FS_I(inode);

	_debug("GOT INODE %p { vl=%llx vn=%llx, u=%x }",
	       inode, vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique);

	/* deal with an existing inode */
	if (!(inode->i_state & I_NEW)) {
		_leave(" = %p", inode);
		return inode;
	}

	ret = afs_inode_init_from_status(op, vp, vnode);
	if (ret < 0)
		goto bad_inode;

	afs_get_inode_cache(vnode);

	/* success */
	clear_bit(AFS_VNODE_UNSET, &vnode->flags);
	unlock_new_inode(inode);
	_leave(" = %p", inode);
	return inode;

	/* failure */
bad_inode:
	iget_failed(inode);
	_leave(" = %d [bad]", ret);
	return ERR_PTR(ret);
}

static int afs_iget5_set_root(struct inode *inode, void *opaque)
{
	struct afs_super_info *as = AFS_FS_S(inode->i_sb);
	struct afs_vnode *vnode = AFS_FS_I(inode);

	vnode->volume		= as->volume;
	vnode->fid.vid		= as->volume->vid,
	vnode->fid.vnode	= 1;
	vnode->fid.unique	= 1;
	inode->i_ino		= 1;
	inode->i_generation	= 1;
	return 0;
}

/*
 * Set up the root inode for a volume.  This is always vnode 1, unique 1 within
 * the volume.
 */
struct inode *afs_root_iget(struct super_block *sb, struct key *key)
{
	struct afs_super_info *as = AFS_FS_S(sb);
	struct afs_operation *op;
	struct afs_vnode *vnode;
	struct inode *inode;
	int ret;

	_enter(",{%llx},,", as->volume->vid);

	inode = iget5_locked(sb, 1, NULL, afs_iget5_set_root, NULL);
	if (!inode) {
		_leave(" = -ENOMEM");
		return ERR_PTR(-ENOMEM);
	}

	_debug("GOT ROOT INODE %p { vl=%llx }", inode, as->volume->vid);

	BUG_ON(!(inode->i_state & I_NEW));

	vnode = AFS_FS_I(inode);
	vnode->cb_v_break = as->volume->cb_v_break,
	afs_set_netfs_context(vnode);

	op = afs_alloc_operation(key, as->volume);
	if (IS_ERR(op)) {
		ret = PTR_ERR(op);
		goto error;
	}

	afs_op_set_vnode(op, 0, vnode);

	op->nr_files	= 1;
	op->ops		= &afs_fetch_status_operation;
	ret = afs_do_sync_operation(op);
	if (ret < 0)
		goto error;

	afs_get_inode_cache(vnode);

	clear_bit(AFS_VNODE_UNSET, &vnode->flags);
	unlock_new_inode(inode);
	_leave(" = %p", inode);
	return inode;

error:
	iget_failed(inode);
	_leave(" = %d [bad]", ret);
	return ERR_PTR(ret);
}

/*
 * 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);
}

/*
 * Check to see if we have a server currently serving this volume and that it
 * hasn't been reinitialised or dropped from the list.
 */
static bool afs_check_server_good(struct afs_vnode *vnode)
{
	struct afs_server_list *slist;
	struct afs_server *server;
	bool good;
	int i;

	if (vnode->cb_fs_s_break == atomic_read(&vnode->volume->cell->fs_s_break))
		return true;

	rcu_read_lock();

	slist = rcu_dereference(vnode->volume->servers);
	for (i = 0; i < slist->nr_servers; i++) {
		server = slist->servers[i].server;
		if (server == vnode->cb_server) {
			good = (vnode->cb_s_break == server->cb_s_break);
			rcu_read_unlock();
			return good;
		}
	}

	rcu_read_unlock();
	return false;
}

/*
 * Check the validity of a vnode/inode.
 */
bool afs_check_validity(struct afs_vnode *vnode)
{
	enum afs_cb_break_reason need_clear = afs_cb_break_no_break;
	time64_t now = ktime_get_real_seconds();
	unsigned int cb_break;
	int seq = 0;

	do {
		read_seqbegin_or_lock(&vnode->cb_lock, &seq);
		cb_break = vnode->cb_break;

		if (test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
			if (vnode->cb_v_break != vnode->volume->cb_v_break)
				need_clear = afs_cb_break_for_v_break;
			else if (!afs_check_server_good(vnode))
				need_clear = afs_cb_break_for_s_reinit;
			else if (test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags))
				need_clear = afs_cb_break_for_zap;
			else if (vnode->cb_expires_at - 10 <= now)
				need_clear = afs_cb_break_for_lapsed;
		} else if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
			;
		} else {
			need_clear = afs_cb_break_no_promise;
		}

	} while (need_seqretry(&vnode->cb_lock, seq));

	done_seqretry(&vnode->cb_lock, seq);

	if (need_clear == afs_cb_break_no_break)
		return true;

	write_seqlock(&vnode->cb_lock);
	if (need_clear == afs_cb_break_no_promise)
		vnode->cb_v_break = vnode->volume->cb_v_break;
	else if (cb_break == vnode->cb_break)
		__afs_break_callback(vnode, need_clear);
	else
		trace_afs_cb_miss(&vnode->fid, need_clear);
	write_sequnlock(&vnode->cb_lock);
	return false;
}

/*
 * Returns true if the pagecache is still valid.  Does not sleep.
 */
bool afs_pagecache_valid(struct afs_vnode *vnode)
{
	if (unlikely(test_bit(AFS_VNODE_DELETED, &vnode->flags))) {
		if (vnode->netfs.inode.i_nlink)
			clear_nlink(&vnode->netfs.inode);
		return true;
	}

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

	return false;
}

/*
 * 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)
{
	int ret;

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

	if (afs_pagecache_valid(vnode))
		goto valid;

	down_write(&vnode->validate_lock);

	/* if the promise has expired, we need to check the server again to get
	 * a new promise - note that if the (parent) directory's metadata was
	 * changed then the security may be different and we may no longer have
	 * access */
	if (!test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
		_debug("not promised");
		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);
	}

	if (test_bit(AFS_VNODE_DELETED, &vnode->flags)) {
		_debug("file already deleted");
		ret = -ESTALE;
		goto error_unlock;
	}

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

error_unlock:
	up_write(&vnode->validate_lock);
	_leave(" = %d", ret);
	return ret;
}

/*
 * read the attributes of an inode
 */
int afs_getattr(struct mnt_idmap *idmap, const struct path *path,
		struct kstat *stat, u32 request_mask, unsigned int query_flags)
{
	struct inode *inode = d_inode(path->dentry);
	struct afs_vnode *vnode = AFS_FS_I(inode);
	struct key *key;
	int ret, seq = 0;

	_enter("{ ino=%lu v=%u }", inode->i_ino, inode->i_generation);

	if (vnode->volume &&
	    !(query_flags & AT_STATX_DONT_SYNC) &&
	    !test_bit(AFS_VNODE_CB_PROMISED, &vnode->flags)) {
		key = afs_request_key(vnode->volume->cell);
		if (IS_ERR(key))
			return PTR_ERR(key);
		ret = afs_validate(vnode, key);
		key_put(key);
		if (ret < 0)
			return ret;
	}

	do {
		read_seqbegin_or_lock(&vnode->cb_lock, &seq);
		generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat);
		if (test_bit(AFS_VNODE_SILLY_DELETED, &vnode->flags) &&
		    stat->nlink > 0)
			stat->nlink -= 1;

		/* Lie about the size of directories.  We maintain a locally
		 * edited copy and may make different allocation decisions on
		 * it, but we need to give userspace the server's size.
		 */
		if (S_ISDIR(inode->i_mode))
			stat->size = vnode->netfs.remote_i_size;
	} while (need_seqretry(&vnode->cb_lock, seq));

	done_seqretry(&vnode->cb_lock, seq);
	return 0;
}

/*
 * discard an AFS inode
 */
int afs_drop_inode(struct inode *inode)
{
	_enter("");

	if (test_bit(AFS_VNODE_PSEUDODIR, &AFS_FS_I(inode)->flags))
		return generic_delete_inode(inode);
	else
		return generic_drop_inode(inode);
}

/*
 * clear an AFS inode
 */
void afs_evict_inode(struct inode *inode)
{
	struct afs_vnode_cache_aux aux;
	struct afs_vnode *vnode = AFS_FS_I(inode);

	_enter("{%llx:%llu.%d}",
	       vnode->fid.vid,
	       vnode->fid.vnode,
	       vnode->fid.unique);

	_debug("CLEAR INODE %p", inode);

	ASSERTCMP(inode->i_ino, ==, vnode->fid.vnode);

	truncate_inode_pages_final(&inode->i_data);

	afs_set_cache_aux(vnode, &aux);
	fscache_clear_inode_writeback(afs_vnode_cache(vnode), inode, &aux);
	clear_inode(inode);

	while (!list_empty(&vnode->wb_keys)) {
		struct afs_wb_key *wbk = list_entry(vnode->wb_keys.next,
						    struct afs_wb_key, vnode_link);
		list_del(&wbk->vnode_link);
		afs_put_wb_key(wbk);
	}

	fscache_relinquish_cookie(afs_vnode_cache(vnode),
				  test_bit(AFS_VNODE_DELETED, &vnode->flags));

	afs_prune_wb_keys(vnode);
	afs_put_permits(rcu_access_pointer(vnode->permit_cache));
	key_put(vnode->silly_key);
	vnode->silly_key = NULL;
	key_put(vnode->lock_key);
	vnode->lock_key = NULL;
	_leave("");
}

static void afs_setattr_success(struct afs_operation *op)
{
	struct afs_vnode_param *vp = &op->file[0];
	struct inode *inode = &vp->vnode->netfs.inode;
	loff_t old_i_size = i_size_read(inode);

	op->setattr.old_i_size = old_i_size;
	afs_vnode_commit_status(op, vp);
	/* inode->i_size has now been changed. */

	if (op->setattr.attr->ia_valid & ATTR_SIZE) {
		loff_t size = op->setattr.attr->ia_size;
		if (size > old_i_size)
			pagecache_isize_extended(inode, old_i_size, size);
	}
}

static void afs_setattr_edit_file(struct afs_operation *op)
{
	struct afs_vnode_param *vp = &op->file[0];
	struct inode *inode = &vp->vnode->netfs.inode;

	if (op->setattr.attr->ia_valid & ATTR_SIZE) {
		loff_t size = op->setattr.attr->ia_size;
		loff_t i_size = op->setattr.old_i_size;

		if (size < i_size)
			truncate_pagecache(inode, size);
		if (size != i_size)
			fscache_resize_cookie(afs_vnode_cache(vp->vnode),
					      vp->scb.status.size);
	}
}

static const struct afs_operation_ops afs_setattr_operation = {
	.issue_afs_rpc	= afs_fs_setattr,
	.issue_yfs_rpc	= yfs_fs_setattr,
	.success	= afs_setattr_success,
	.edit_dir	= afs_setattr_edit_file,
};

/*
 * set the attributes of an inode
 */
int afs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
		struct iattr *attr)
{
	const unsigned int supported =
		ATTR_SIZE | ATTR_MODE | ATTR_UID | ATTR_GID |
		ATTR_MTIME | ATTR_MTIME_SET | ATTR_TIMES_SET | ATTR_TOUCH;
	struct afs_operation *op;
	struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
	struct inode *inode = &vnode->netfs.inode;
	loff_t i_size;
	int ret;

	_enter("{%llx:%llu},{n=%pd},%x",
	       vnode->fid.vid, vnode->fid.vnode, dentry,
	       attr->ia_valid);

	if (!(attr->ia_valid & supported)) {
		_leave(" = 0 [unsupported]");
		return 0;
	}

	i_size = i_size_read(inode);
	if (attr->ia_valid & ATTR_SIZE) {
		if (!S_ISREG(inode->i_mode))
			return -EISDIR;

		ret = inode_newsize_ok(inode, attr->ia_size);
		if (ret)
			return ret;

		if (attr->ia_size == i_size)
			attr->ia_valid &= ~ATTR_SIZE;
	}

	fscache_use_cookie(afs_vnode_cache(vnode), true);

	/* Prevent any new writebacks from starting whilst we do this. */
	down_write(&vnode->validate_lock);

	if ((attr->ia_valid & ATTR_SIZE) && S_ISREG(inode->i_mode)) {
		loff_t size = attr->ia_size;

		/* Wait for any outstanding writes to the server to complete */
		loff_t from = min(size, i_size);
		loff_t to = max(size, i_size);
		ret = filemap_fdatawait_range(inode->i_mapping, from, to);
		if (ret < 0)
			goto out_unlock;

		/* Don't talk to the server if we're just shortening in-memory
		 * writes that haven't gone to the server yet.
		 */
		if (!(attr->ia_valid & (supported & ~ATTR_SIZE & ~ATTR_MTIME)) &&
		    attr->ia_size < i_size &&
		    attr->ia_size > vnode->status.size) {
			truncate_pagecache(inode, attr->ia_size);
			fscache_resize_cookie(afs_vnode_cache(vnode),
					      attr->ia_size);
			i_size_write(inode, attr->ia_size);
			ret = 0;
			goto out_unlock;
		}
	}

	op = afs_alloc_operation(((attr->ia_valid & ATTR_FILE) ?
				  afs_file_key(attr->ia_file) : NULL),
				 vnode->volume);
	if (IS_ERR(op)) {
		ret = PTR_ERR(op);
		goto out_unlock;
	}

	afs_op_set_vnode(op, 0, vnode);
	op->setattr.attr = attr;

	if (attr->ia_valid & ATTR_SIZE) {
		op->file[0].dv_delta = 1;
		op->file[0].set_size = true;
	}
	op->ctime = attr->ia_ctime;
	op->file[0].update_ctime = 1;
	op->file[0].modification = true;

	op->ops = &afs_setattr_operation;
	ret = afs_do_sync_operation(op);

out_unlock:
	up_write(&vnode->validate_lock);
	fscache_unuse_cookie(afs_vnode_cache(vnode), NULL, NULL);
	_leave(" = %d", ret);
	return ret;
}