forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
nfs4state.c
2533 lines (2266 loc) · 65.9 KB
/
nfs4state.c
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
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* fs/nfs/nfs4state.c
*
* Client-side XDR for NFSv4.
*
* Copyright (c) 2002 The Regents of the University of Michigan.
* All rights reserved.
*
* Kendrick Smith <[email protected]>
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of the University nor the names of its
* contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
* BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
* LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
* NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
* Implementation of the NFSv4 state model. For the time being,
* this is minimal, but will be made much more complex in a
* subsequent patch.
*/
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/nfs_fs.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/ratelimit.h>
#include <linux/workqueue.h>
#include <linux/bitops.h>
#include <linux/jiffies.h>
#include <linux/sunrpc/clnt.h>
#include "nfs4_fs.h"
#include "callback.h"
#include "delegation.h"
#include "internal.h"
#include "nfs4idmap.h"
#include "nfs4session.h"
#include "pnfs.h"
#include "netns.h"
#define NFSDBG_FACILITY NFSDBG_STATE
#define OPENOWNER_POOL_SIZE 8
const nfs4_stateid zero_stateid = {
{ .data = { 0 } },
.type = NFS4_SPECIAL_STATEID_TYPE,
};
static DEFINE_MUTEX(nfs_clid_init_mutex);
int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
{
struct nfs4_setclientid_res clid = {
.clientid = clp->cl_clientid,
.confirm = clp->cl_confirm,
};
unsigned short port;
int status;
struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
if (test_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state))
goto do_confirm;
port = nn->nfs_callback_tcpport;
if (clp->cl_addr.ss_family == AF_INET6)
port = nn->nfs_callback_tcpport6;
status = nfs4_proc_setclientid(clp, NFS4_CALLBACK, port, cred, &clid);
if (status != 0)
goto out;
clp->cl_clientid = clid.clientid;
clp->cl_confirm = clid.confirm;
set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
do_confirm:
status = nfs4_proc_setclientid_confirm(clp, &clid, cred);
if (status != 0)
goto out;
clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
nfs4_schedule_state_renewal(clp);
out:
return status;
}
/**
* nfs40_discover_server_trunking - Detect server IP address trunking (mv0)
*
* @clp: nfs_client under test
* @result: OUT: found nfs_client, or clp
* @cred: credential to use for trunking test
*
* Returns zero, a negative errno, or a negative NFS4ERR status.
* If zero is returned, an nfs_client pointer is planted in
* "result".
*
* Note: The returned client may not yet be marked ready.
*/
int nfs40_discover_server_trunking(struct nfs_client *clp,
struct nfs_client **result,
struct rpc_cred *cred)
{
struct nfs4_setclientid_res clid = {
.clientid = clp->cl_clientid,
.confirm = clp->cl_confirm,
};
struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
unsigned short port;
int status;
port = nn->nfs_callback_tcpport;
if (clp->cl_addr.ss_family == AF_INET6)
port = nn->nfs_callback_tcpport6;
status = nfs4_proc_setclientid(clp, NFS4_CALLBACK, port, cred, &clid);
if (status != 0)
goto out;
clp->cl_clientid = clid.clientid;
clp->cl_confirm = clid.confirm;
status = nfs40_walk_client_list(clp, result, cred);
if (status == 0) {
/* Sustain the lease, even if it's empty. If the clientid4
* goes stale it's of no use for trunking discovery. */
nfs4_schedule_state_renewal(*result);
}
out:
return status;
}
struct rpc_cred *nfs4_get_machine_cred_locked(struct nfs_client *clp)
{
struct rpc_cred *cred = NULL;
if (clp->cl_machine_cred != NULL)
cred = get_rpccred(clp->cl_machine_cred);
return cred;
}
static void nfs4_root_machine_cred(struct nfs_client *clp)
{
struct rpc_cred *cred, *new;
new = rpc_lookup_machine_cred(NULL);
spin_lock(&clp->cl_lock);
cred = clp->cl_machine_cred;
clp->cl_machine_cred = new;
spin_unlock(&clp->cl_lock);
if (cred != NULL)
put_rpccred(cred);
}
static struct rpc_cred *
nfs4_get_renew_cred_server_locked(struct nfs_server *server)
{
struct rpc_cred *cred = NULL;
struct nfs4_state_owner *sp;
struct rb_node *pos;
for (pos = rb_first(&server->state_owners);
pos != NULL;
pos = rb_next(pos)) {
sp = rb_entry(pos, struct nfs4_state_owner, so_server_node);
if (list_empty(&sp->so_states))
continue;
cred = get_rpccred(sp->so_cred);
break;
}
return cred;
}
/**
* nfs4_get_renew_cred_locked - Acquire credential for a renew operation
* @clp: client state handle
*
* Returns an rpc_cred with reference count bumped, or NULL.
* Caller must hold clp->cl_lock.
*/
struct rpc_cred *nfs4_get_renew_cred_locked(struct nfs_client *clp)
{
struct rpc_cred *cred = NULL;
struct nfs_server *server;
/* Use machine credentials if available */
cred = nfs4_get_machine_cred_locked(clp);
if (cred != NULL)
goto out;
rcu_read_lock();
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
cred = nfs4_get_renew_cred_server_locked(server);
if (cred != NULL)
break;
}
rcu_read_unlock();
out:
return cred;
}
static void nfs4_end_drain_slot_table(struct nfs4_slot_table *tbl)
{
if (test_and_clear_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state)) {
spin_lock(&tbl->slot_tbl_lock);
nfs41_wake_slot_table(tbl);
spin_unlock(&tbl->slot_tbl_lock);
}
}
static void nfs4_end_drain_session(struct nfs_client *clp)
{
struct nfs4_session *ses = clp->cl_session;
if (clp->cl_slot_tbl) {
nfs4_end_drain_slot_table(clp->cl_slot_tbl);
return;
}
if (ses != NULL) {
nfs4_end_drain_slot_table(&ses->bc_slot_table);
nfs4_end_drain_slot_table(&ses->fc_slot_table);
}
}
static int nfs4_drain_slot_tbl(struct nfs4_slot_table *tbl)
{
set_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state);
spin_lock(&tbl->slot_tbl_lock);
if (tbl->highest_used_slotid != NFS4_NO_SLOT) {
reinit_completion(&tbl->complete);
spin_unlock(&tbl->slot_tbl_lock);
return wait_for_completion_interruptible(&tbl->complete);
}
spin_unlock(&tbl->slot_tbl_lock);
return 0;
}
static int nfs4_begin_drain_session(struct nfs_client *clp)
{
struct nfs4_session *ses = clp->cl_session;
int ret = 0;
if (clp->cl_slot_tbl)
return nfs4_drain_slot_tbl(clp->cl_slot_tbl);
/* back channel */
ret = nfs4_drain_slot_tbl(&ses->bc_slot_table);
if (ret)
return ret;
/* fore channel */
return nfs4_drain_slot_tbl(&ses->fc_slot_table);
}
#if defined(CONFIG_NFS_V4_1)
static int nfs41_setup_state_renewal(struct nfs_client *clp)
{
int status;
struct nfs_fsinfo fsinfo;
unsigned long now;
if (!test_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state)) {
nfs4_schedule_state_renewal(clp);
return 0;
}
now = jiffies;
status = nfs4_proc_get_lease_time(clp, &fsinfo);
if (status == 0) {
nfs4_set_lease_period(clp, fsinfo.lease_time * HZ, now);
nfs4_schedule_state_renewal(clp);
}
return status;
}
static void nfs41_finish_session_reset(struct nfs_client *clp)
{
clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
/* create_session negotiated new slot table */
clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, &clp->cl_state);
nfs41_setup_state_renewal(clp);
}
int nfs41_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
{
int status;
if (test_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state))
goto do_confirm;
status = nfs4_proc_exchange_id(clp, cred);
if (status != 0)
goto out;
set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
do_confirm:
status = nfs4_proc_create_session(clp, cred);
if (status != 0)
goto out;
nfs41_finish_session_reset(clp);
nfs_mark_client_ready(clp, NFS_CS_READY);
out:
return status;
}
/**
* nfs41_discover_server_trunking - Detect server IP address trunking (mv1)
*
* @clp: nfs_client under test
* @result: OUT: found nfs_client, or clp
* @cred: credential to use for trunking test
*
* Returns NFS4_OK, a negative errno, or a negative NFS4ERR status.
* If NFS4_OK is returned, an nfs_client pointer is planted in
* "result".
*
* Note: The returned client may not yet be marked ready.
*/
int nfs41_discover_server_trunking(struct nfs_client *clp,
struct nfs_client **result,
struct rpc_cred *cred)
{
int status;
status = nfs4_proc_exchange_id(clp, cred);
if (status != NFS4_OK)
return status;
status = nfs41_walk_client_list(clp, result, cred);
if (status < 0)
return status;
if (clp != *result)
return 0;
/* Purge state if the client id was established in a prior instance */
if (clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R)
set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
else
set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
nfs4_schedule_state_manager(clp);
status = nfs_wait_client_init_complete(clp);
if (status < 0)
nfs_put_client(clp);
return status;
}
#endif /* CONFIG_NFS_V4_1 */
/**
* nfs4_get_clid_cred - Acquire credential for a setclientid operation
* @clp: client state handle
*
* Returns an rpc_cred with reference count bumped, or NULL.
*/
struct rpc_cred *nfs4_get_clid_cred(struct nfs_client *clp)
{
struct rpc_cred *cred;
spin_lock(&clp->cl_lock);
cred = nfs4_get_machine_cred_locked(clp);
spin_unlock(&clp->cl_lock);
return cred;
}
static struct nfs4_state_owner *
nfs4_find_state_owner_locked(struct nfs_server *server, struct rpc_cred *cred)
{
struct rb_node **p = &server->state_owners.rb_node,
*parent = NULL;
struct nfs4_state_owner *sp;
while (*p != NULL) {
parent = *p;
sp = rb_entry(parent, struct nfs4_state_owner, so_server_node);
if (cred < sp->so_cred)
p = &parent->rb_left;
else if (cred > sp->so_cred)
p = &parent->rb_right;
else {
if (!list_empty(&sp->so_lru))
list_del_init(&sp->so_lru);
atomic_inc(&sp->so_count);
return sp;
}
}
return NULL;
}
static struct nfs4_state_owner *
nfs4_insert_state_owner_locked(struct nfs4_state_owner *new)
{
struct nfs_server *server = new->so_server;
struct rb_node **p = &server->state_owners.rb_node,
*parent = NULL;
struct nfs4_state_owner *sp;
int err;
while (*p != NULL) {
parent = *p;
sp = rb_entry(parent, struct nfs4_state_owner, so_server_node);
if (new->so_cred < sp->so_cred)
p = &parent->rb_left;
else if (new->so_cred > sp->so_cred)
p = &parent->rb_right;
else {
if (!list_empty(&sp->so_lru))
list_del_init(&sp->so_lru);
atomic_inc(&sp->so_count);
return sp;
}
}
err = ida_get_new(&server->openowner_id, &new->so_seqid.owner_id);
if (err)
return ERR_PTR(err);
rb_link_node(&new->so_server_node, parent, p);
rb_insert_color(&new->so_server_node, &server->state_owners);
return new;
}
static void
nfs4_remove_state_owner_locked(struct nfs4_state_owner *sp)
{
struct nfs_server *server = sp->so_server;
if (!RB_EMPTY_NODE(&sp->so_server_node))
rb_erase(&sp->so_server_node, &server->state_owners);
ida_remove(&server->openowner_id, sp->so_seqid.owner_id);
}
static void
nfs4_init_seqid_counter(struct nfs_seqid_counter *sc)
{
sc->create_time = ktime_get();
sc->flags = 0;
sc->counter = 0;
spin_lock_init(&sc->lock);
INIT_LIST_HEAD(&sc->list);
rpc_init_wait_queue(&sc->wait, "Seqid_waitqueue");
}
static void
nfs4_destroy_seqid_counter(struct nfs_seqid_counter *sc)
{
rpc_destroy_wait_queue(&sc->wait);
}
/*
* nfs4_alloc_state_owner(): this is called on the OPEN or CREATE path to
* create a new state_owner.
*
*/
static struct nfs4_state_owner *
nfs4_alloc_state_owner(struct nfs_server *server,
struct rpc_cred *cred,
gfp_t gfp_flags)
{
struct nfs4_state_owner *sp;
sp = kzalloc(sizeof(*sp), gfp_flags);
if (!sp)
return NULL;
sp->so_server = server;
sp->so_cred = get_rpccred(cred);
spin_lock_init(&sp->so_lock);
INIT_LIST_HEAD(&sp->so_states);
nfs4_init_seqid_counter(&sp->so_seqid);
atomic_set(&sp->so_count, 1);
INIT_LIST_HEAD(&sp->so_lru);
seqcount_init(&sp->so_reclaim_seqcount);
mutex_init(&sp->so_delegreturn_mutex);
return sp;
}
static void
nfs4_reset_state_owner(struct nfs4_state_owner *sp)
{
/* This state_owner is no longer usable, but must
* remain in place so that state recovery can find it
* and the opens associated with it.
* It may also be used for new 'open' request to
* return a delegation to the server.
* So update the 'create_time' so that it looks like
* a new state_owner. This will cause the server to
* request an OPEN_CONFIRM to start a new sequence.
*/
sp->so_seqid.create_time = ktime_get();
}
static void nfs4_free_state_owner(struct nfs4_state_owner *sp)
{
nfs4_destroy_seqid_counter(&sp->so_seqid);
put_rpccred(sp->so_cred);
kfree(sp);
}
static void nfs4_gc_state_owners(struct nfs_server *server)
{
struct nfs_client *clp = server->nfs_client;
struct nfs4_state_owner *sp, *tmp;
unsigned long time_min, time_max;
LIST_HEAD(doomed);
spin_lock(&clp->cl_lock);
time_max = jiffies;
time_min = (long)time_max - (long)clp->cl_lease_time;
list_for_each_entry_safe(sp, tmp, &server->state_owners_lru, so_lru) {
/* NB: LRU is sorted so that oldest is at the head */
if (time_in_range(sp->so_expires, time_min, time_max))
break;
list_move(&sp->so_lru, &doomed);
nfs4_remove_state_owner_locked(sp);
}
spin_unlock(&clp->cl_lock);
list_for_each_entry_safe(sp, tmp, &doomed, so_lru) {
list_del(&sp->so_lru);
nfs4_free_state_owner(sp);
}
}
/**
* nfs4_get_state_owner - Look up a state owner given a credential
* @server: nfs_server to search
* @cred: RPC credential to match
*
* Returns a pointer to an instantiated nfs4_state_owner struct, or NULL.
*/
struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *server,
struct rpc_cred *cred,
gfp_t gfp_flags)
{
struct nfs_client *clp = server->nfs_client;
struct nfs4_state_owner *sp, *new;
spin_lock(&clp->cl_lock);
sp = nfs4_find_state_owner_locked(server, cred);
spin_unlock(&clp->cl_lock);
if (sp != NULL)
goto out;
new = nfs4_alloc_state_owner(server, cred, gfp_flags);
if (new == NULL)
goto out;
do {
if (ida_pre_get(&server->openowner_id, gfp_flags) == 0)
break;
spin_lock(&clp->cl_lock);
sp = nfs4_insert_state_owner_locked(new);
spin_unlock(&clp->cl_lock);
} while (sp == ERR_PTR(-EAGAIN));
if (sp != new)
nfs4_free_state_owner(new);
out:
nfs4_gc_state_owners(server);
return sp;
}
/**
* nfs4_put_state_owner - Release a nfs4_state_owner
* @sp: state owner data to release
*
* Note that we keep released state owners on an LRU
* list.
* This caches valid state owners so that they can be
* reused, to avoid the OPEN_CONFIRM on minor version 0.
* It also pins the uniquifier of dropped state owners for
* a while, to ensure that those state owner names are
* never reused.
*/
void nfs4_put_state_owner(struct nfs4_state_owner *sp)
{
struct nfs_server *server = sp->so_server;
struct nfs_client *clp = server->nfs_client;
if (!atomic_dec_and_lock(&sp->so_count, &clp->cl_lock))
return;
sp->so_expires = jiffies;
list_add_tail(&sp->so_lru, &server->state_owners_lru);
spin_unlock(&clp->cl_lock);
}
/**
* nfs4_purge_state_owners - Release all cached state owners
* @server: nfs_server with cached state owners to release
*
* Called at umount time. Remaining state owners will be on
* the LRU with ref count of zero.
*/
void nfs4_purge_state_owners(struct nfs_server *server)
{
struct nfs_client *clp = server->nfs_client;
struct nfs4_state_owner *sp, *tmp;
LIST_HEAD(doomed);
spin_lock(&clp->cl_lock);
list_for_each_entry_safe(sp, tmp, &server->state_owners_lru, so_lru) {
list_move(&sp->so_lru, &doomed);
nfs4_remove_state_owner_locked(sp);
}
spin_unlock(&clp->cl_lock);
list_for_each_entry_safe(sp, tmp, &doomed, so_lru) {
list_del(&sp->so_lru);
nfs4_free_state_owner(sp);
}
}
static struct nfs4_state *
nfs4_alloc_open_state(void)
{
struct nfs4_state *state;
state = kzalloc(sizeof(*state), GFP_NOFS);
if (!state)
return NULL;
atomic_set(&state->count, 1);
INIT_LIST_HEAD(&state->lock_states);
spin_lock_init(&state->state_lock);
seqlock_init(&state->seqlock);
return state;
}
void
nfs4_state_set_mode_locked(struct nfs4_state *state, fmode_t fmode)
{
if (state->state == fmode)
return;
/* NB! List reordering - see the reclaim code for why. */
if ((fmode & FMODE_WRITE) != (state->state & FMODE_WRITE)) {
if (fmode & FMODE_WRITE)
list_move(&state->open_states, &state->owner->so_states);
else
list_move_tail(&state->open_states, &state->owner->so_states);
}
state->state = fmode;
}
static struct nfs4_state *
__nfs4_find_state_byowner(struct inode *inode, struct nfs4_state_owner *owner)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs4_state *state;
list_for_each_entry(state, &nfsi->open_states, inode_states) {
if (state->owner != owner)
continue;
if (!nfs4_valid_open_stateid(state))
continue;
if (atomic_inc_not_zero(&state->count))
return state;
}
return NULL;
}
static void
nfs4_free_open_state(struct nfs4_state *state)
{
kfree(state);
}
struct nfs4_state *
nfs4_get_open_state(struct inode *inode, struct nfs4_state_owner *owner)
{
struct nfs4_state *state, *new;
struct nfs_inode *nfsi = NFS_I(inode);
spin_lock(&inode->i_lock);
state = __nfs4_find_state_byowner(inode, owner);
spin_unlock(&inode->i_lock);
if (state)
goto out;
new = nfs4_alloc_open_state();
spin_lock(&owner->so_lock);
spin_lock(&inode->i_lock);
state = __nfs4_find_state_byowner(inode, owner);
if (state == NULL && new != NULL) {
state = new;
state->owner = owner;
atomic_inc(&owner->so_count);
list_add(&state->inode_states, &nfsi->open_states);
ihold(inode);
state->inode = inode;
spin_unlock(&inode->i_lock);
/* Note: The reclaim code dictates that we add stateless
* and read-only stateids to the end of the list */
list_add_tail(&state->open_states, &owner->so_states);
spin_unlock(&owner->so_lock);
} else {
spin_unlock(&inode->i_lock);
spin_unlock(&owner->so_lock);
if (new)
nfs4_free_open_state(new);
}
out:
return state;
}
void nfs4_put_open_state(struct nfs4_state *state)
{
struct inode *inode = state->inode;
struct nfs4_state_owner *owner = state->owner;
if (!atomic_dec_and_lock(&state->count, &owner->so_lock))
return;
spin_lock(&inode->i_lock);
list_del(&state->inode_states);
list_del(&state->open_states);
spin_unlock(&inode->i_lock);
spin_unlock(&owner->so_lock);
iput(inode);
nfs4_free_open_state(state);
nfs4_put_state_owner(owner);
}
/*
* Close the current file.
*/
static void __nfs4_close(struct nfs4_state *state,
fmode_t fmode, gfp_t gfp_mask, int wait)
{
struct nfs4_state_owner *owner = state->owner;
int call_close = 0;
fmode_t newstate;
atomic_inc(&owner->so_count);
/* Protect against nfs4_find_state() */
spin_lock(&owner->so_lock);
switch (fmode & (FMODE_READ | FMODE_WRITE)) {
case FMODE_READ:
state->n_rdonly--;
break;
case FMODE_WRITE:
state->n_wronly--;
break;
case FMODE_READ|FMODE_WRITE:
state->n_rdwr--;
}
newstate = FMODE_READ|FMODE_WRITE;
if (state->n_rdwr == 0) {
if (state->n_rdonly == 0) {
newstate &= ~FMODE_READ;
call_close |= test_bit(NFS_O_RDONLY_STATE, &state->flags);
call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags);
}
if (state->n_wronly == 0) {
newstate &= ~FMODE_WRITE;
call_close |= test_bit(NFS_O_WRONLY_STATE, &state->flags);
call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags);
}
if (newstate == 0)
clear_bit(NFS_DELEGATED_STATE, &state->flags);
}
nfs4_state_set_mode_locked(state, newstate);
spin_unlock(&owner->so_lock);
if (!call_close) {
nfs4_put_open_state(state);
nfs4_put_state_owner(owner);
} else
nfs4_do_close(state, gfp_mask, wait);
}
void nfs4_close_state(struct nfs4_state *state, fmode_t fmode)
{
__nfs4_close(state, fmode, GFP_NOFS, 0);
}
void nfs4_close_sync(struct nfs4_state *state, fmode_t fmode)
{
__nfs4_close(state, fmode, GFP_KERNEL, 1);
}
/*
* Search the state->lock_states for an existing lock_owner
* that is compatible with either of the given owners.
* If the second is non-zero, then the first refers to a Posix-lock
* owner (current->files) and the second refers to a flock/OFD
* owner (struct file*). In that case, prefer a match for the first
* owner.
* If both sorts of locks are held on the one file we cannot know
* which stateid was intended to be used, so a "correct" choice cannot
* be made. Failing that, a "consistent" choice is preferable. The
* consistent choice we make is to prefer the first owner, that of a
* Posix lock.
*/
static struct nfs4_lock_state *
__nfs4_find_lock_state(struct nfs4_state *state,
fl_owner_t fl_owner, fl_owner_t fl_owner2)
{
struct nfs4_lock_state *pos, *ret = NULL;
list_for_each_entry(pos, &state->lock_states, ls_locks) {
if (pos->ls_owner == fl_owner) {
ret = pos;
break;
}
if (pos->ls_owner == fl_owner2)
ret = pos;
}
if (ret)
atomic_inc(&ret->ls_count);
return ret;
}
/*
* Return a compatible lock_state. If no initialized lock_state structure
* exists, return an uninitialized one.
*
*/
static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
{
struct nfs4_lock_state *lsp;
struct nfs_server *server = state->owner->so_server;
lsp = kzalloc(sizeof(*lsp), GFP_NOFS);
if (lsp == NULL)
return NULL;
nfs4_init_seqid_counter(&lsp->ls_seqid);
atomic_set(&lsp->ls_count, 1);
lsp->ls_state = state;
lsp->ls_owner = fl_owner;
lsp->ls_seqid.owner_id = ida_simple_get(&server->lockowner_id, 0, 0, GFP_NOFS);
if (lsp->ls_seqid.owner_id < 0)
goto out_free;
INIT_LIST_HEAD(&lsp->ls_locks);
return lsp;
out_free:
kfree(lsp);
return NULL;
}
void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp)
{
ida_simple_remove(&server->lockowner_id, lsp->ls_seqid.owner_id);
nfs4_destroy_seqid_counter(&lsp->ls_seqid);
kfree(lsp);
}
/*
* Return a compatible lock_state. If no initialized lock_state structure
* exists, return an uninitialized one.
*
*/
static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_owner_t owner)
{
struct nfs4_lock_state *lsp, *new = NULL;
for(;;) {
spin_lock(&state->state_lock);
lsp = __nfs4_find_lock_state(state, owner, NULL);
if (lsp != NULL)
break;
if (new != NULL) {
list_add(&new->ls_locks, &state->lock_states);
set_bit(LK_STATE_IN_USE, &state->flags);
lsp = new;
new = NULL;
break;
}
spin_unlock(&state->state_lock);
new = nfs4_alloc_lock_state(state, owner);
if (new == NULL)
return NULL;
}
spin_unlock(&state->state_lock);
if (new != NULL)
nfs4_free_lock_state(state->owner->so_server, new);
return lsp;
}
/*
* Release reference to lock_state, and free it if we see that
* it is no longer in use
*/
void nfs4_put_lock_state(struct nfs4_lock_state *lsp)
{
struct nfs_server *server;
struct nfs4_state *state;
if (lsp == NULL)
return;
state = lsp->ls_state;
if (!atomic_dec_and_lock(&lsp->ls_count, &state->state_lock))
return;
list_del(&lsp->ls_locks);
if (list_empty(&state->lock_states))
clear_bit(LK_STATE_IN_USE, &state->flags);
spin_unlock(&state->state_lock);
server = state->owner->so_server;
if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags)) {
struct nfs_client *clp = server->nfs_client;
clp->cl_mvops->free_lock_state(server, lsp);
} else
nfs4_free_lock_state(server, lsp);
}
static void nfs4_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
{
struct nfs4_lock_state *lsp = src->fl_u.nfs4_fl.owner;
dst->fl_u.nfs4_fl.owner = lsp;
atomic_inc(&lsp->ls_count);
}
static void nfs4_fl_release_lock(struct file_lock *fl)
{
nfs4_put_lock_state(fl->fl_u.nfs4_fl.owner);
}
static const struct file_lock_operations nfs4_fl_lock_ops = {
.fl_copy_lock = nfs4_fl_copy_lock,
.fl_release_private = nfs4_fl_release_lock,
};
int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl)
{
struct nfs4_lock_state *lsp;
if (fl->fl_ops != NULL)
return 0;
lsp = nfs4_get_lock_state(state, fl->fl_owner);
if (lsp == NULL)
return -ENOMEM;
fl->fl_u.nfs4_fl.owner = lsp;
fl->fl_ops = &nfs4_fl_lock_ops;
return 0;
}
static int nfs4_copy_lock_stateid(nfs4_stateid *dst,
struct nfs4_state *state,
const struct nfs_lock_context *l_ctx)
{
struct nfs4_lock_state *lsp;
fl_owner_t fl_owner, fl_flock_owner;
int ret = -ENOENT;
if (l_ctx == NULL)
goto out;
if (test_bit(LK_STATE_IN_USE, &state->flags) == 0)
goto out;
fl_owner = l_ctx->lockowner;
fl_flock_owner = l_ctx->open_context->flock_owner;
spin_lock(&state->state_lock);
lsp = __nfs4_find_lock_state(state, fl_owner, fl_flock_owner);
if (lsp && test_bit(NFS_LOCK_LOST, &lsp->ls_flags))
ret = -EIO;
else if (lsp != NULL && test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) != 0) {
nfs4_stateid_copy(dst, &lsp->ls_stateid);
ret = 0;
}
spin_unlock(&state->state_lock);
nfs4_put_lock_state(lsp);
out:
return ret;
}
static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
{
const nfs4_stateid *src;
int seq;
do {
src = &zero_stateid;
seq = read_seqbegin(&state->seqlock);
if (test_bit(NFS_OPEN_STATE, &state->flags))
src = &state->open_stateid;
nfs4_stateid_copy(dst, src);
} while (read_seqretry(&state->seqlock, seq));
}
/*
* Byte-range lock aware utility to initialize the stateid of read/write
* requests.
*/
int nfs4_select_rw_stateid(struct nfs4_state *state,