forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
nfs4state.c
4161 lines (3680 loc) · 109 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
/*
* linux/fs/nfsd/nfs4state.c
*
* Copyright (c) 2001 The Regents of the University of Michigan.
* All rights reserved.
*
* Kendrick Smith <[email protected]>
* Andy Adamson <[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.
*
*/
#include <linux/param.h>
#include <linux/major.h>
#include <linux/slab.h>
#include <linux/sunrpc/svc.h>
#include <linux/nfsd/nfsd.h>
#include <linux/nfsd/cache.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/workqueue.h>
#include <linux/smp_lock.h>
#include <linux/kthread.h>
#include <linux/nfs4.h>
#include <linux/nfsd/state.h>
#include <linux/nfsd/xdr4.h>
#include <linux/namei.h>
#include <linux/swap.h>
#include <linux/mutex.h>
#include <linux/lockd/bind.h>
#include <linux/module.h>
#include <linux/sunrpc/svcauth_gss.h>
#include <linux/sunrpc/clnt.h>
#define NFSDDBG_FACILITY NFSDDBG_PROC
/* Globals */
static time_t lease_time = 90; /* default lease time */
static time_t user_lease_time = 90;
static time_t boot_time;
static u32 current_ownerid = 1;
static u32 current_fileid = 1;
static u32 current_delegid = 1;
static u32 nfs4_init;
static stateid_t zerostateid; /* bits all 0 */
static stateid_t onestateid; /* bits all 1 */
static u64 current_sessionid = 1;
#define ZERO_STATEID(stateid) (!memcmp((stateid), &zerostateid, sizeof(stateid_t)))
#define ONE_STATEID(stateid) (!memcmp((stateid), &onestateid, sizeof(stateid_t)))
/* forward declarations */
static struct nfs4_stateid * find_stateid(stateid_t *stid, int flags);
static struct nfs4_delegation * find_delegation_stateid(struct inode *ino, stateid_t *stid);
static char user_recovery_dirname[PATH_MAX] = "/var/lib/nfs/v4recovery";
static void nfs4_set_recdir(char *recdir);
/* Locking: */
/* Currently used for almost all code touching nfsv4 state: */
static DEFINE_MUTEX(client_mutex);
/*
* Currently used for the del_recall_lru and file hash table. In an
* effort to decrease the scope of the client_mutex, this spinlock may
* eventually cover more:
*/
static DEFINE_SPINLOCK(recall_lock);
static struct kmem_cache *stateowner_slab = NULL;
static struct kmem_cache *file_slab = NULL;
static struct kmem_cache *stateid_slab = NULL;
static struct kmem_cache *deleg_slab = NULL;
void
nfs4_lock_state(void)
{
mutex_lock(&client_mutex);
}
void
nfs4_unlock_state(void)
{
mutex_unlock(&client_mutex);
}
static inline u32
opaque_hashval(const void *ptr, int nbytes)
{
unsigned char *cptr = (unsigned char *) ptr;
u32 x = 0;
while (nbytes--) {
x *= 37;
x += *cptr++;
}
return x;
}
static struct list_head del_recall_lru;
static inline void
put_nfs4_file(struct nfs4_file *fi)
{
if (atomic_dec_and_lock(&fi->fi_ref, &recall_lock)) {
list_del(&fi->fi_hash);
spin_unlock(&recall_lock);
iput(fi->fi_inode);
kmem_cache_free(file_slab, fi);
}
}
static inline void
get_nfs4_file(struct nfs4_file *fi)
{
atomic_inc(&fi->fi_ref);
}
static int num_delegations;
unsigned int max_delegations;
/*
* Open owner state (share locks)
*/
/* hash tables for nfs4_stateowner */
#define OWNER_HASH_BITS 8
#define OWNER_HASH_SIZE (1 << OWNER_HASH_BITS)
#define OWNER_HASH_MASK (OWNER_HASH_SIZE - 1)
#define ownerid_hashval(id) \
((id) & OWNER_HASH_MASK)
#define ownerstr_hashval(clientid, ownername) \
(((clientid) + opaque_hashval((ownername.data), (ownername.len))) & OWNER_HASH_MASK)
static struct list_head ownerid_hashtbl[OWNER_HASH_SIZE];
static struct list_head ownerstr_hashtbl[OWNER_HASH_SIZE];
/* hash table for nfs4_file */
#define FILE_HASH_BITS 8
#define FILE_HASH_SIZE (1 << FILE_HASH_BITS)
#define FILE_HASH_MASK (FILE_HASH_SIZE - 1)
/* hash table for (open)nfs4_stateid */
#define STATEID_HASH_BITS 10
#define STATEID_HASH_SIZE (1 << STATEID_HASH_BITS)
#define STATEID_HASH_MASK (STATEID_HASH_SIZE - 1)
#define file_hashval(x) \
hash_ptr(x, FILE_HASH_BITS)
#define stateid_hashval(owner_id, file_id) \
(((owner_id) + (file_id)) & STATEID_HASH_MASK)
static struct list_head file_hashtbl[FILE_HASH_SIZE];
static struct list_head stateid_hashtbl[STATEID_HASH_SIZE];
static struct nfs4_delegation *
alloc_init_deleg(struct nfs4_client *clp, struct nfs4_stateid *stp, struct svc_fh *current_fh, u32 type)
{
struct nfs4_delegation *dp;
struct nfs4_file *fp = stp->st_file;
struct nfs4_cb_conn *cb = &stp->st_stateowner->so_client->cl_cb_conn;
dprintk("NFSD alloc_init_deleg\n");
if (fp->fi_had_conflict)
return NULL;
if (num_delegations > max_delegations)
return NULL;
dp = kmem_cache_alloc(deleg_slab, GFP_KERNEL);
if (dp == NULL)
return dp;
num_delegations++;
INIT_LIST_HEAD(&dp->dl_perfile);
INIT_LIST_HEAD(&dp->dl_perclnt);
INIT_LIST_HEAD(&dp->dl_recall_lru);
dp->dl_client = clp;
get_nfs4_file(fp);
dp->dl_file = fp;
dp->dl_flock = NULL;
get_file(stp->st_vfs_file);
dp->dl_vfs_file = stp->st_vfs_file;
dp->dl_type = type;
dp->dl_ident = cb->cb_ident;
dp->dl_stateid.si_boot = get_seconds();
dp->dl_stateid.si_stateownerid = current_delegid++;
dp->dl_stateid.si_fileid = 0;
dp->dl_stateid.si_generation = 0;
fh_copy_shallow(&dp->dl_fh, ¤t_fh->fh_handle);
dp->dl_time = 0;
atomic_set(&dp->dl_count, 1);
list_add(&dp->dl_perfile, &fp->fi_delegations);
list_add(&dp->dl_perclnt, &clp->cl_delegations);
return dp;
}
void
nfs4_put_delegation(struct nfs4_delegation *dp)
{
if (atomic_dec_and_test(&dp->dl_count)) {
dprintk("NFSD: freeing dp %p\n",dp);
put_nfs4_file(dp->dl_file);
kmem_cache_free(deleg_slab, dp);
num_delegations--;
}
}
/* Remove the associated file_lock first, then remove the delegation.
* lease_modify() is called to remove the FS_LEASE file_lock from
* the i_flock list, eventually calling nfsd's lock_manager
* fl_release_callback.
*/
static void
nfs4_close_delegation(struct nfs4_delegation *dp)
{
struct file *filp = dp->dl_vfs_file;
dprintk("NFSD: close_delegation dp %p\n",dp);
dp->dl_vfs_file = NULL;
/* The following nfsd_close may not actually close the file,
* but we want to remove the lease in any case. */
if (dp->dl_flock)
vfs_setlease(filp, F_UNLCK, &dp->dl_flock);
nfsd_close(filp);
}
/* Called under the state lock. */
static void
unhash_delegation(struct nfs4_delegation *dp)
{
list_del_init(&dp->dl_perfile);
list_del_init(&dp->dl_perclnt);
spin_lock(&recall_lock);
list_del_init(&dp->dl_recall_lru);
spin_unlock(&recall_lock);
nfs4_close_delegation(dp);
nfs4_put_delegation(dp);
}
/*
* SETCLIENTID state
*/
/* Hash tables for nfs4_clientid state */
#define CLIENT_HASH_BITS 4
#define CLIENT_HASH_SIZE (1 << CLIENT_HASH_BITS)
#define CLIENT_HASH_MASK (CLIENT_HASH_SIZE - 1)
#define clientid_hashval(id) \
((id) & CLIENT_HASH_MASK)
#define clientstr_hashval(name) \
(opaque_hashval((name), 8) & CLIENT_HASH_MASK)
/*
* reclaim_str_hashtbl[] holds known client info from previous reset/reboot
* used in reboot/reset lease grace period processing
*
* conf_id_hashtbl[], and conf_str_hashtbl[] hold confirmed
* setclientid_confirmed info.
*
* unconf_str_hastbl[] and unconf_id_hashtbl[] hold unconfirmed
* setclientid info.
*
* client_lru holds client queue ordered by nfs4_client.cl_time
* for lease renewal.
*
* close_lru holds (open) stateowner queue ordered by nfs4_stateowner.so_time
* for last close replay.
*/
static struct list_head reclaim_str_hashtbl[CLIENT_HASH_SIZE];
static int reclaim_str_hashtbl_size = 0;
static struct list_head conf_id_hashtbl[CLIENT_HASH_SIZE];
static struct list_head conf_str_hashtbl[CLIENT_HASH_SIZE];
static struct list_head unconf_str_hashtbl[CLIENT_HASH_SIZE];
static struct list_head unconf_id_hashtbl[CLIENT_HASH_SIZE];
static struct list_head client_lru;
static struct list_head close_lru;
static void unhash_generic_stateid(struct nfs4_stateid *stp)
{
list_del(&stp->st_hash);
list_del(&stp->st_perfile);
list_del(&stp->st_perstateowner);
}
static void free_generic_stateid(struct nfs4_stateid *stp)
{
put_nfs4_file(stp->st_file);
kmem_cache_free(stateid_slab, stp);
}
static void release_lock_stateid(struct nfs4_stateid *stp)
{
unhash_generic_stateid(stp);
locks_remove_posix(stp->st_vfs_file, (fl_owner_t)stp->st_stateowner);
free_generic_stateid(stp);
}
static void unhash_lockowner(struct nfs4_stateowner *sop)
{
struct nfs4_stateid *stp;
list_del(&sop->so_idhash);
list_del(&sop->so_strhash);
list_del(&sop->so_perstateid);
while (!list_empty(&sop->so_stateids)) {
stp = list_first_entry(&sop->so_stateids,
struct nfs4_stateid, st_perstateowner);
release_lock_stateid(stp);
}
}
static void release_lockowner(struct nfs4_stateowner *sop)
{
unhash_lockowner(sop);
nfs4_put_stateowner(sop);
}
static void
release_stateid_lockowners(struct nfs4_stateid *open_stp)
{
struct nfs4_stateowner *lock_sop;
while (!list_empty(&open_stp->st_lockowners)) {
lock_sop = list_entry(open_stp->st_lockowners.next,
struct nfs4_stateowner, so_perstateid);
/* list_del(&open_stp->st_lockowners); */
BUG_ON(lock_sop->so_is_open_owner);
release_lockowner(lock_sop);
}
}
static void release_open_stateid(struct nfs4_stateid *stp)
{
unhash_generic_stateid(stp);
release_stateid_lockowners(stp);
nfsd_close(stp->st_vfs_file);
free_generic_stateid(stp);
}
static void unhash_openowner(struct nfs4_stateowner *sop)
{
struct nfs4_stateid *stp;
list_del(&sop->so_idhash);
list_del(&sop->so_strhash);
list_del(&sop->so_perclient);
list_del(&sop->so_perstateid); /* XXX: necessary? */
while (!list_empty(&sop->so_stateids)) {
stp = list_first_entry(&sop->so_stateids,
struct nfs4_stateid, st_perstateowner);
release_open_stateid(stp);
}
}
static void release_openowner(struct nfs4_stateowner *sop)
{
unhash_openowner(sop);
list_del(&sop->so_close_lru);
nfs4_put_stateowner(sop);
}
static DEFINE_SPINLOCK(sessionid_lock);
#define SESSION_HASH_SIZE 512
static struct list_head sessionid_hashtbl[SESSION_HASH_SIZE];
static inline int
hash_sessionid(struct nfs4_sessionid *sessionid)
{
struct nfsd4_sessionid *sid = (struct nfsd4_sessionid *)sessionid;
return sid->sequence % SESSION_HASH_SIZE;
}
static inline void
dump_sessionid(const char *fn, struct nfs4_sessionid *sessionid)
{
u32 *ptr = (u32 *)(&sessionid->data[0]);
dprintk("%s: %u:%u:%u:%u\n", fn, ptr[0], ptr[1], ptr[2], ptr[3]);
}
static void
gen_sessionid(struct nfsd4_session *ses)
{
struct nfs4_client *clp = ses->se_client;
struct nfsd4_sessionid *sid;
sid = (struct nfsd4_sessionid *)ses->se_sessionid.data;
sid->clientid = clp->cl_clientid;
sid->sequence = current_sessionid++;
sid->reserved = 0;
}
/*
* The protocol defines ca_maxresponssize_cached to include the size of
* the rpc header, but all we need to cache is the data starting after
* the end of the initial SEQUENCE operation--the rest we regenerate
* each time. Therefore we can advertise a ca_maxresponssize_cached
* value that is the number of bytes in our cache plus a few additional
* bytes. In order to stay on the safe side, and not promise more than
* we can cache, those additional bytes must be the minimum possible: 24
* bytes of rpc header (xid through accept state, with AUTH_NULL
* verifier), 12 for the compound header (with zero-length tag), and 44
* for the SEQUENCE op response:
*/
#define NFSD_MIN_HDR_SEQ_SZ (24 + 12 + 44)
/*
* Give the client the number of ca_maxresponsesize_cached slots it
* requests, of size bounded by NFSD_SLOT_CACHE_SIZE,
* NFSD_MAX_MEM_PER_SESSION, and nfsd_drc_max_mem. Do not allow more
* than NFSD_MAX_SLOTS_PER_SESSION.
*
* If we run out of reserved DRC memory we should (up to a point)
* re-negotiate active sessions and reduce their slot usage to make
* rooom for new connections. For now we just fail the create session.
*/
static int set_forechannel_drc_size(struct nfsd4_channel_attrs *fchan)
{
int mem, size = fchan->maxresp_cached;
if (fchan->maxreqs < 1)
return nfserr_inval;
if (size < NFSD_MIN_HDR_SEQ_SZ)
size = NFSD_MIN_HDR_SEQ_SZ;
size -= NFSD_MIN_HDR_SEQ_SZ;
if (size > NFSD_SLOT_CACHE_SIZE)
size = NFSD_SLOT_CACHE_SIZE;
/* bound the maxreqs by NFSD_MAX_MEM_PER_SESSION */
mem = fchan->maxreqs * size;
if (mem > NFSD_MAX_MEM_PER_SESSION) {
fchan->maxreqs = NFSD_MAX_MEM_PER_SESSION / size;
if (fchan->maxreqs > NFSD_MAX_SLOTS_PER_SESSION)
fchan->maxreqs = NFSD_MAX_SLOTS_PER_SESSION;
mem = fchan->maxreqs * size;
}
spin_lock(&nfsd_drc_lock);
/* bound the total session drc memory ussage */
if (mem + nfsd_drc_mem_used > nfsd_drc_max_mem) {
fchan->maxreqs = (nfsd_drc_max_mem - nfsd_drc_mem_used) / size;
mem = fchan->maxreqs * size;
}
nfsd_drc_mem_used += mem;
spin_unlock(&nfsd_drc_lock);
if (fchan->maxreqs == 0)
return nfserr_serverfault;
fchan->maxresp_cached = size + NFSD_MIN_HDR_SEQ_SZ;
return 0;
}
/*
* fchan holds the client values on input, and the server values on output
*/
static int init_forechannel_attrs(struct svc_rqst *rqstp,
struct nfsd4_channel_attrs *session_fchan,
struct nfsd4_channel_attrs *fchan)
{
int status = 0;
__u32 maxcount = svc_max_payload(rqstp);
/* headerpadsz set to zero in encode routine */
/* Use the client's max request and max response size if possible */
if (fchan->maxreq_sz > maxcount)
fchan->maxreq_sz = maxcount;
session_fchan->maxreq_sz = fchan->maxreq_sz;
if (fchan->maxresp_sz > maxcount)
fchan->maxresp_sz = maxcount;
session_fchan->maxresp_sz = fchan->maxresp_sz;
/* Use the client's maxops if possible */
if (fchan->maxops > NFSD_MAX_OPS_PER_COMPOUND)
fchan->maxops = NFSD_MAX_OPS_PER_COMPOUND;
session_fchan->maxops = fchan->maxops;
/* FIXME: Error means no more DRC pages so the server should
* recover pages from existing sessions. For now fail session
* creation.
*/
status = set_forechannel_drc_size(fchan);
session_fchan->maxresp_cached = fchan->maxresp_cached;
session_fchan->maxreqs = fchan->maxreqs;
dprintk("%s status %d\n", __func__, status);
return status;
}
static void
free_session_slots(struct nfsd4_session *ses)
{
int i;
for (i = 0; i < ses->se_fchannel.maxreqs; i++)
kfree(ses->se_slots[i]);
}
static int
alloc_init_session(struct svc_rqst *rqstp, struct nfs4_client *clp,
struct nfsd4_create_session *cses)
{
struct nfsd4_session *new, tmp;
struct nfsd4_slot *sp;
int idx, slotsize, cachesize, i;
int status;
memset(&tmp, 0, sizeof(tmp));
/* FIXME: For now, we just accept the client back channel attributes. */
tmp.se_bchannel = cses->back_channel;
status = init_forechannel_attrs(rqstp, &tmp.se_fchannel,
&cses->fore_channel);
if (status)
goto out;
BUILD_BUG_ON(NFSD_MAX_SLOTS_PER_SESSION * sizeof(struct nfsd4_slot)
+ sizeof(struct nfsd4_session) > PAGE_SIZE);
status = nfserr_serverfault;
/* allocate struct nfsd4_session and slot table pointers in one piece */
slotsize = tmp.se_fchannel.maxreqs * sizeof(struct nfsd4_slot *);
new = kzalloc(sizeof(*new) + slotsize, GFP_KERNEL);
if (!new)
goto out;
memcpy(new, &tmp, sizeof(*new));
/* allocate each struct nfsd4_slot and data cache in one piece */
cachesize = new->se_fchannel.maxresp_cached - NFSD_MIN_HDR_SEQ_SZ;
for (i = 0; i < new->se_fchannel.maxreqs; i++) {
sp = kzalloc(sizeof(*sp) + cachesize, GFP_KERNEL);
if (!sp)
goto out_free;
new->se_slots[i] = sp;
}
new->se_client = clp;
gen_sessionid(new);
idx = hash_sessionid(&new->se_sessionid);
memcpy(clp->cl_sessionid.data, new->se_sessionid.data,
NFS4_MAX_SESSIONID_LEN);
new->se_flags = cses->flags;
kref_init(&new->se_ref);
spin_lock(&sessionid_lock);
list_add(&new->se_hash, &sessionid_hashtbl[idx]);
list_add(&new->se_perclnt, &clp->cl_sessions);
spin_unlock(&sessionid_lock);
status = nfs_ok;
out:
return status;
out_free:
free_session_slots(new);
kfree(new);
goto out;
}
/* caller must hold sessionid_lock */
static struct nfsd4_session *
find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid)
{
struct nfsd4_session *elem;
int idx;
dump_sessionid(__func__, sessionid);
idx = hash_sessionid(sessionid);
dprintk("%s: idx is %d\n", __func__, idx);
/* Search in the appropriate list */
list_for_each_entry(elem, &sessionid_hashtbl[idx], se_hash) {
dump_sessionid("list traversal", &elem->se_sessionid);
if (!memcmp(elem->se_sessionid.data, sessionid->data,
NFS4_MAX_SESSIONID_LEN)) {
return elem;
}
}
dprintk("%s: session not found\n", __func__);
return NULL;
}
/* caller must hold sessionid_lock */
static void
unhash_session(struct nfsd4_session *ses)
{
list_del(&ses->se_hash);
list_del(&ses->se_perclnt);
}
static void
release_session(struct nfsd4_session *ses)
{
spin_lock(&sessionid_lock);
unhash_session(ses);
spin_unlock(&sessionid_lock);
nfsd4_put_session(ses);
}
void
free_session(struct kref *kref)
{
struct nfsd4_session *ses;
ses = container_of(kref, struct nfsd4_session, se_ref);
spin_lock(&nfsd_drc_lock);
nfsd_drc_mem_used -= ses->se_fchannel.maxreqs * NFSD_SLOT_CACHE_SIZE;
spin_unlock(&nfsd_drc_lock);
free_session_slots(ses);
kfree(ses);
}
static inline void
renew_client(struct nfs4_client *clp)
{
/*
* Move client to the end to the LRU list.
*/
dprintk("renewing client (clientid %08x/%08x)\n",
clp->cl_clientid.cl_boot,
clp->cl_clientid.cl_id);
list_move_tail(&clp->cl_lru, &client_lru);
clp->cl_time = get_seconds();
}
/* SETCLIENTID and SETCLIENTID_CONFIRM Helper functions */
static int
STALE_CLIENTID(clientid_t *clid)
{
if (clid->cl_boot == boot_time)
return 0;
dprintk("NFSD stale clientid (%08x/%08x) boot_time %08lx\n",
clid->cl_boot, clid->cl_id, boot_time);
return 1;
}
/*
* XXX Should we use a slab cache ?
* This type of memory management is somewhat inefficient, but we use it
* anyway since SETCLIENTID is not a common operation.
*/
static struct nfs4_client *alloc_client(struct xdr_netobj name)
{
struct nfs4_client *clp;
clp = kzalloc(sizeof(struct nfs4_client), GFP_KERNEL);
if (clp == NULL)
return NULL;
clp->cl_name.data = kmalloc(name.len, GFP_KERNEL);
if (clp->cl_name.data == NULL) {
kfree(clp);
return NULL;
}
memcpy(clp->cl_name.data, name.data, name.len);
clp->cl_name.len = name.len;
return clp;
}
static void
shutdown_callback_client(struct nfs4_client *clp)
{
struct rpc_clnt *clnt = clp->cl_cb_conn.cb_client;
if (clnt) {
/*
* Callback threads take a reference on the client, so there
* should be no outstanding callbacks at this point.
*/
clp->cl_cb_conn.cb_client = NULL;
rpc_shutdown_client(clnt);
}
}
static inline void
free_client(struct nfs4_client *clp)
{
shutdown_callback_client(clp);
if (clp->cl_cb_xprt)
svc_xprt_put(clp->cl_cb_xprt);
if (clp->cl_cred.cr_group_info)
put_group_info(clp->cl_cred.cr_group_info);
kfree(clp->cl_principal);
kfree(clp->cl_name.data);
kfree(clp);
}
void
put_nfs4_client(struct nfs4_client *clp)
{
if (atomic_dec_and_test(&clp->cl_count))
free_client(clp);
}
static void
expire_client(struct nfs4_client *clp)
{
struct nfs4_stateowner *sop;
struct nfs4_delegation *dp;
struct list_head reaplist;
dprintk("NFSD: expire_client cl_count %d\n",
atomic_read(&clp->cl_count));
INIT_LIST_HEAD(&reaplist);
spin_lock(&recall_lock);
while (!list_empty(&clp->cl_delegations)) {
dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt);
dprintk("NFSD: expire client. dp %p, fp %p\n", dp,
dp->dl_flock);
list_del_init(&dp->dl_perclnt);
list_move(&dp->dl_recall_lru, &reaplist);
}
spin_unlock(&recall_lock);
while (!list_empty(&reaplist)) {
dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru);
list_del_init(&dp->dl_recall_lru);
unhash_delegation(dp);
}
list_del(&clp->cl_idhash);
list_del(&clp->cl_strhash);
list_del(&clp->cl_lru);
while (!list_empty(&clp->cl_openowners)) {
sop = list_entry(clp->cl_openowners.next, struct nfs4_stateowner, so_perclient);
release_openowner(sop);
}
while (!list_empty(&clp->cl_sessions)) {
struct nfsd4_session *ses;
ses = list_entry(clp->cl_sessions.next, struct nfsd4_session,
se_perclnt);
release_session(ses);
}
put_nfs4_client(clp);
}
static void copy_verf(struct nfs4_client *target, nfs4_verifier *source)
{
memcpy(target->cl_verifier.data, source->data,
sizeof(target->cl_verifier.data));
}
static void copy_clid(struct nfs4_client *target, struct nfs4_client *source)
{
target->cl_clientid.cl_boot = source->cl_clientid.cl_boot;
target->cl_clientid.cl_id = source->cl_clientid.cl_id;
}
static void copy_cred(struct svc_cred *target, struct svc_cred *source)
{
target->cr_uid = source->cr_uid;
target->cr_gid = source->cr_gid;
target->cr_group_info = source->cr_group_info;
get_group_info(target->cr_group_info);
}
static int same_name(const char *n1, const char *n2)
{
return 0 == memcmp(n1, n2, HEXDIR_LEN);
}
static int
same_verf(nfs4_verifier *v1, nfs4_verifier *v2)
{
return 0 == memcmp(v1->data, v2->data, sizeof(v1->data));
}
static int
same_clid(clientid_t *cl1, clientid_t *cl2)
{
return (cl1->cl_boot == cl2->cl_boot) && (cl1->cl_id == cl2->cl_id);
}
/* XXX what about NGROUP */
static int
same_creds(struct svc_cred *cr1, struct svc_cred *cr2)
{
return cr1->cr_uid == cr2->cr_uid;
}
static void gen_clid(struct nfs4_client *clp)
{
static u32 current_clientid = 1;
clp->cl_clientid.cl_boot = boot_time;
clp->cl_clientid.cl_id = current_clientid++;
}
static void gen_confirm(struct nfs4_client *clp)
{
static u32 i;
u32 *p;
p = (u32 *)clp->cl_confirm.data;
*p++ = get_seconds();
*p++ = i++;
}
static struct nfs4_client *create_client(struct xdr_netobj name, char *recdir,
struct svc_rqst *rqstp, nfs4_verifier *verf)
{
struct nfs4_client *clp;
struct sockaddr *sa = svc_addr(rqstp);
char *princ;
clp = alloc_client(name);
if (clp == NULL)
return NULL;
princ = svc_gss_principal(rqstp);
if (princ) {
clp->cl_principal = kstrdup(princ, GFP_KERNEL);
if (clp->cl_principal == NULL) {
free_client(clp);
return NULL;
}
}
memcpy(clp->cl_recdir, recdir, HEXDIR_LEN);
atomic_set(&clp->cl_count, 1);
atomic_set(&clp->cl_cb_conn.cb_set, 0);
INIT_LIST_HEAD(&clp->cl_idhash);
INIT_LIST_HEAD(&clp->cl_strhash);
INIT_LIST_HEAD(&clp->cl_openowners);
INIT_LIST_HEAD(&clp->cl_delegations);
INIT_LIST_HEAD(&clp->cl_sessions);
INIT_LIST_HEAD(&clp->cl_lru);
clear_bit(0, &clp->cl_cb_slot_busy);
rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
copy_verf(clp, verf);
rpc_copy_addr((struct sockaddr *) &clp->cl_addr, sa);
clp->cl_flavor = rqstp->rq_flavor;
copy_cred(&clp->cl_cred, &rqstp->rq_cred);
gen_confirm(clp);
return clp;
}
static int check_name(struct xdr_netobj name)
{
if (name.len == 0)
return 0;
if (name.len > NFS4_OPAQUE_LIMIT) {
dprintk("NFSD: check_name: name too long(%d)!\n", name.len);
return 0;
}
return 1;
}
static void
add_to_unconfirmed(struct nfs4_client *clp, unsigned int strhashval)
{
unsigned int idhashval;
list_add(&clp->cl_strhash, &unconf_str_hashtbl[strhashval]);
idhashval = clientid_hashval(clp->cl_clientid.cl_id);
list_add(&clp->cl_idhash, &unconf_id_hashtbl[idhashval]);
list_add_tail(&clp->cl_lru, &client_lru);
clp->cl_time = get_seconds();
}
static void
move_to_confirmed(struct nfs4_client *clp)
{
unsigned int idhashval = clientid_hashval(clp->cl_clientid.cl_id);
unsigned int strhashval;
dprintk("NFSD: move_to_confirm nfs4_client %p\n", clp);
list_del_init(&clp->cl_strhash);
list_move(&clp->cl_idhash, &conf_id_hashtbl[idhashval]);
strhashval = clientstr_hashval(clp->cl_recdir);
list_add(&clp->cl_strhash, &conf_str_hashtbl[strhashval]);
renew_client(clp);
}
static struct nfs4_client *
find_confirmed_client(clientid_t *clid)
{
struct nfs4_client *clp;
unsigned int idhashval = clientid_hashval(clid->cl_id);
list_for_each_entry(clp, &conf_id_hashtbl[idhashval], cl_idhash) {
if (same_clid(&clp->cl_clientid, clid))
return clp;
}
return NULL;
}
static struct nfs4_client *
find_unconfirmed_client(clientid_t *clid)
{
struct nfs4_client *clp;
unsigned int idhashval = clientid_hashval(clid->cl_id);
list_for_each_entry(clp, &unconf_id_hashtbl[idhashval], cl_idhash) {
if (same_clid(&clp->cl_clientid, clid))
return clp;
}
return NULL;
}
/*
* Return 1 iff clp's clientid establishment method matches the use_exchange_id
* parameter. Matching is based on the fact the at least one of the
* EXCHGID4_FLAG_USE_{NON_PNFS,PNFS_MDS,PNFS_DS} flags must be set for v4.1
*
* FIXME: we need to unify the clientid namespaces for nfsv4.x
* and correctly deal with client upgrade/downgrade in EXCHANGE_ID
* and SET_CLIENTID{,_CONFIRM}
*/
static inline int
match_clientid_establishment(struct nfs4_client *clp, bool use_exchange_id)
{
bool has_exchange_flags = (clp->cl_exchange_flags != 0);
return use_exchange_id == has_exchange_flags;
}
static struct nfs4_client *
find_confirmed_client_by_str(const char *dname, unsigned int hashval,
bool use_exchange_id)
{
struct nfs4_client *clp;
list_for_each_entry(clp, &conf_str_hashtbl[hashval], cl_strhash) {
if (same_name(clp->cl_recdir, dname) &&
match_clientid_establishment(clp, use_exchange_id))
return clp;
}
return NULL;
}
static struct nfs4_client *
find_unconfirmed_client_by_str(const char *dname, unsigned int hashval,
bool use_exchange_id)
{
struct nfs4_client *clp;
list_for_each_entry(clp, &unconf_str_hashtbl[hashval], cl_strhash) {
if (same_name(clp->cl_recdir, dname) &&
match_clientid_establishment(clp, use_exchange_id))
return clp;
}
return NULL;
}
static void
gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, u32 scopeid)
{
struct nfs4_cb_conn *cb = &clp->cl_cb_conn;
unsigned short expected_family;
/* Currently, we only support tcp and tcp6 for the callback channel */
if (se->se_callback_netid_len == 3 &&
!memcmp(se->se_callback_netid_val, "tcp", 3))
expected_family = AF_INET;
else if (se->se_callback_netid_len == 4 &&
!memcmp(se->se_callback_netid_val, "tcp6", 4))
expected_family = AF_INET6;
else
goto out_err;
cb->cb_addrlen = rpc_uaddr2sockaddr(se->se_callback_addr_val,
se->se_callback_addr_len,
(struct sockaddr *) &cb->cb_addr,
sizeof(cb->cb_addr));
if (!cb->cb_addrlen || cb->cb_addr.ss_family != expected_family)
goto out_err;
if (cb->cb_addr.ss_family == AF_INET6)
((struct sockaddr_in6 *) &cb->cb_addr)->sin6_scope_id = scopeid;
cb->cb_minorversion = 0;
cb->cb_prog = se->se_callback_prog;
cb->cb_ident = se->se_callback_ident;