forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathnfs4recover.c
1412 lines (1198 loc) · 32.1 KB
/
nfs4recover.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
/*
* Copyright (c) 2004 The Regents of the University of Michigan.
* Copyright (c) 2012 Jeff Layton <jlayton@redhat.com>
* All rights reserved.
*
* Andy Adamson <andros@citi.umich.edu>
*
* 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/file.h>
#include <linux/slab.h>
#include <linux/namei.h>
#include <linux/crypto.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/module.h>
#include <net/net_namespace.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
#include <linux/sunrpc/clnt.h>
#include <linux/nfsd/cld.h>
#include "nfsd.h"
#include "state.h"
#include "vfs.h"
#include "netns.h"
#define NFSDDBG_FACILITY NFSDDBG_PROC
/* Declarations */
struct nfsd4_client_tracking_ops {
int (*init)(struct net *);
void (*exit)(struct net *);
void (*create)(struct nfs4_client *);
void (*remove)(struct nfs4_client *);
int (*check)(struct nfs4_client *);
void (*grace_done)(struct nfsd_net *, time_t);
};
/* Globals */
static char user_recovery_dirname[PATH_MAX] = "/var/lib/nfs/v4recovery";
static int
nfs4_save_creds(const struct cred **original_creds)
{
struct cred *new;
new = prepare_creds();
if (!new)
return -ENOMEM;
new->fsuid = GLOBAL_ROOT_UID;
new->fsgid = GLOBAL_ROOT_GID;
*original_creds = override_creds(new);
put_cred(new);
return 0;
}
static void
nfs4_reset_creds(const struct cred *original)
{
revert_creds(original);
}
static void
md5_to_hex(char *out, char *md5)
{
int i;
for (i=0; i<16; i++) {
unsigned char c = md5[i];
*out++ = '0' + ((c&0xf0)>>4) + (c>=0xa0)*('a'-'9'-1);
*out++ = '0' + (c&0x0f) + ((c&0x0f)>=0x0a)*('a'-'9'-1);
}
*out = '\0';
}
static int
nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname)
{
struct xdr_netobj cksum;
struct hash_desc desc;
struct scatterlist sg;
int status;
dprintk("NFSD: nfs4_make_rec_clidname for %.*s\n",
clname->len, clname->data);
desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
desc.tfm = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
if (IS_ERR(desc.tfm)) {
status = PTR_ERR(desc.tfm);
goto out_no_tfm;
}
cksum.len = crypto_hash_digestsize(desc.tfm);
cksum.data = kmalloc(cksum.len, GFP_KERNEL);
if (cksum.data == NULL) {
status = -ENOMEM;
goto out;
}
sg_init_one(&sg, clname->data, clname->len);
status = crypto_hash_digest(&desc, &sg, sg.length, cksum.data);
if (status)
goto out;
md5_to_hex(dname, cksum.data);
status = 0;
out:
kfree(cksum.data);
crypto_free_hash(desc.tfm);
out_no_tfm:
return status;
}
/*
* If we had an error generating the recdir name for the legacy tracker
* then warn the admin. If the error doesn't appear to be transient,
* then disable recovery tracking.
*/
static void
legacy_recdir_name_error(struct nfs4_client *clp, int error)
{
printk(KERN_ERR "NFSD: unable to generate recoverydir "
"name (%d).\n", error);
/*
* if the algorithm just doesn't exist, then disable the recovery
* tracker altogether. The crypto libs will generally return this if
* FIPS is enabled as well.
*/
if (error == -ENOENT) {
printk(KERN_ERR "NFSD: disabling legacy clientid tracking. "
"Reboot recovery will not function correctly!\n");
nfsd4_client_tracking_exit(clp->net);
}
}
static void
nfsd4_create_clid_dir(struct nfs4_client *clp)
{
const struct cred *original_cred;
char dname[HEXDIR_LEN];
struct dentry *dir, *dentry;
struct nfs4_client_reclaim *crp;
int status;
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
dprintk("NFSD: nfsd4_create_clid_dir for \"%s\"\n", dname);
if (test_and_set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
return;
if (!nn->rec_file)
return;
status = nfs4_make_rec_clidname(dname, &clp->cl_name);
if (status)
return legacy_recdir_name_error(clp, status);
status = nfs4_save_creds(&original_cred);
if (status < 0)
return;
status = mnt_want_write_file(nn->rec_file);
if (status)
return;
dir = nn->rec_file->f_path.dentry;
/* lock the parent */
mutex_lock(&dir->d_inode->i_mutex);
dentry = lookup_one_len(dname, dir, HEXDIR_LEN-1);
if (IS_ERR(dentry)) {
status = PTR_ERR(dentry);
goto out_unlock;
}
if (dentry->d_inode)
/*
* In the 4.1 case, where we're called from
* reclaim_complete(), records from the previous reboot
* may still be left, so this is OK.
*
* In the 4.0 case, we should never get here; but we may
* as well be forgiving and just succeed silently.
*/
goto out_put;
status = vfs_mkdir(dir->d_inode, dentry, S_IRWXU);
out_put:
dput(dentry);
out_unlock:
mutex_unlock(&dir->d_inode->i_mutex);
if (status == 0) {
if (nn->in_grace) {
crp = nfs4_client_to_reclaim(dname, nn);
if (crp)
crp->cr_clp = clp;
}
vfs_fsync(nn->rec_file, 0);
} else {
printk(KERN_ERR "NFSD: failed to write recovery record"
" (err %d); please check that %s exists"
" and is writeable", status,
user_recovery_dirname);
}
mnt_drop_write_file(nn->rec_file);
nfs4_reset_creds(original_cred);
}
typedef int (recdir_func)(struct dentry *, struct dentry *, struct nfsd_net *);
struct name_list {
char name[HEXDIR_LEN];
struct list_head list;
};
static int
nfsd4_build_namelist(void *arg, const char *name, int namlen,
loff_t offset, u64 ino, unsigned int d_type)
{
struct list_head *names = arg;
struct name_list *entry;
if (namlen != HEXDIR_LEN - 1)
return 0;
entry = kmalloc(sizeof(struct name_list), GFP_KERNEL);
if (entry == NULL)
return -ENOMEM;
memcpy(entry->name, name, HEXDIR_LEN - 1);
entry->name[HEXDIR_LEN - 1] = '\0';
list_add(&entry->list, names);
return 0;
}
static int
nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn)
{
const struct cred *original_cred;
struct dentry *dir = nn->rec_file->f_path.dentry;
LIST_HEAD(names);
int status;
status = nfs4_save_creds(&original_cred);
if (status < 0)
return status;
status = vfs_llseek(nn->rec_file, 0, SEEK_SET);
if (status < 0) {
nfs4_reset_creds(original_cred);
return status;
}
status = vfs_readdir(nn->rec_file, nfsd4_build_namelist, &names);
mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
while (!list_empty(&names)) {
struct name_list *entry;
entry = list_entry(names.next, struct name_list, list);
if (!status) {
struct dentry *dentry;
dentry = lookup_one_len(entry->name, dir, HEXDIR_LEN-1);
if (IS_ERR(dentry)) {
status = PTR_ERR(dentry);
break;
}
status = f(dir, dentry, nn);
dput(dentry);
}
list_del(&entry->list);
kfree(entry);
}
mutex_unlock(&dir->d_inode->i_mutex);
nfs4_reset_creds(original_cred);
return status;
}
static int
nfsd4_unlink_clid_dir(char *name, int namlen, struct nfsd_net *nn)
{
struct dentry *dir, *dentry;
int status;
dprintk("NFSD: nfsd4_unlink_clid_dir. name %.*s\n", namlen, name);
dir = nn->rec_file->f_path.dentry;
mutex_lock_nested(&dir->d_inode->i_mutex, I_MUTEX_PARENT);
dentry = lookup_one_len(name, dir, namlen);
if (IS_ERR(dentry)) {
status = PTR_ERR(dentry);
goto out_unlock;
}
status = -ENOENT;
if (!dentry->d_inode)
goto out;
status = vfs_rmdir(dir->d_inode, dentry);
out:
dput(dentry);
out_unlock:
mutex_unlock(&dir->d_inode->i_mutex);
return status;
}
static void
nfsd4_remove_clid_dir(struct nfs4_client *clp)
{
const struct cred *original_cred;
struct nfs4_client_reclaim *crp;
char dname[HEXDIR_LEN];
int status;
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
if (!nn->rec_file || !test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
return;
status = nfs4_make_rec_clidname(dname, &clp->cl_name);
if (status)
return legacy_recdir_name_error(clp, status);
status = mnt_want_write_file(nn->rec_file);
if (status)
goto out;
clear_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
status = nfs4_save_creds(&original_cred);
if (status < 0)
goto out_drop_write;
status = nfsd4_unlink_clid_dir(dname, HEXDIR_LEN-1, nn);
nfs4_reset_creds(original_cred);
if (status == 0) {
vfs_fsync(nn->rec_file, 0);
if (nn->in_grace) {
/* remove reclaim record */
crp = nfsd4_find_reclaim_client(dname, nn);
if (crp)
nfs4_remove_reclaim_record(crp, nn);
}
}
out_drop_write:
mnt_drop_write_file(nn->rec_file);
out:
if (status)
printk("NFSD: Failed to remove expired client state directory"
" %.*s\n", HEXDIR_LEN, dname);
}
static int
purge_old(struct dentry *parent, struct dentry *child, struct nfsd_net *nn)
{
int status;
if (nfs4_has_reclaimed_state(child->d_name.name, nn))
return 0;
status = vfs_rmdir(parent->d_inode, child);
if (status)
printk("failed to remove client recovery directory %s\n",
child->d_name.name);
/* Keep trying, success or failure: */
return 0;
}
static void
nfsd4_recdir_purge_old(struct nfsd_net *nn, time_t boot_time)
{
int status;
nn->in_grace = false;
if (!nn->rec_file)
return;
status = mnt_want_write_file(nn->rec_file);
if (status)
goto out;
status = nfsd4_list_rec_dir(purge_old, nn);
if (status == 0)
vfs_fsync(nn->rec_file, 0);
mnt_drop_write_file(nn->rec_file);
out:
nfs4_release_reclaim(nn);
if (status)
printk("nfsd4: failed to purge old clients from recovery"
" directory %s\n", nn->rec_file->f_path.dentry->d_name.name);
}
static int
load_recdir(struct dentry *parent, struct dentry *child, struct nfsd_net *nn)
{
if (child->d_name.len != HEXDIR_LEN - 1) {
printk("nfsd4: illegal name %s in recovery directory\n",
child->d_name.name);
/* Keep trying; maybe the others are OK: */
return 0;
}
nfs4_client_to_reclaim(child->d_name.name, nn);
return 0;
}
static int
nfsd4_recdir_load(struct net *net) {
int status;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (!nn->rec_file)
return 0;
status = nfsd4_list_rec_dir(load_recdir, nn);
if (status)
printk("nfsd4: failed loading clients from recovery"
" directory %s\n", nn->rec_file->f_path.dentry->d_name.name);
return status;
}
/*
* Hold reference to the recovery directory.
*/
static int
nfsd4_init_recdir(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
const struct cred *original_cred;
int status;
printk("NFSD: Using %s as the NFSv4 state recovery directory\n",
user_recovery_dirname);
BUG_ON(nn->rec_file);
status = nfs4_save_creds(&original_cred);
if (status < 0) {
printk("NFSD: Unable to change credentials to find recovery"
" directory: error %d\n",
status);
return status;
}
nn->rec_file = filp_open(user_recovery_dirname, O_RDONLY | O_DIRECTORY, 0);
if (IS_ERR(nn->rec_file)) {
printk("NFSD: unable to find recovery directory %s\n",
user_recovery_dirname);
status = PTR_ERR(nn->rec_file);
nn->rec_file = NULL;
}
nfs4_reset_creds(original_cred);
if (!status)
nn->in_grace = true;
return status;
}
static int
nfs4_legacy_state_init(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
int i;
nn->reclaim_str_hashtbl = kmalloc(sizeof(struct list_head) *
CLIENT_HASH_SIZE, GFP_KERNEL);
if (!nn->reclaim_str_hashtbl)
return -ENOMEM;
for (i = 0; i < CLIENT_HASH_SIZE; i++)
INIT_LIST_HEAD(&nn->reclaim_str_hashtbl[i]);
nn->reclaim_str_hashtbl_size = 0;
return 0;
}
static void
nfs4_legacy_state_shutdown(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
kfree(nn->reclaim_str_hashtbl);
}
static int
nfsd4_load_reboot_recovery_data(struct net *net)
{
int status;
status = nfsd4_init_recdir(net);
if (!status)
status = nfsd4_recdir_load(net);
if (status)
printk(KERN_ERR "NFSD: Failure reading reboot recovery data\n");
return status;
}
static int
nfsd4_legacy_tracking_init(struct net *net)
{
int status;
/* XXX: The legacy code won't work in a container */
if (net != &init_net) {
WARN(1, KERN_ERR "NFSD: attempt to initialize legacy client "
"tracking in a container!\n");
return -EINVAL;
}
status = nfs4_legacy_state_init(net);
if (status)
return status;
status = nfsd4_load_reboot_recovery_data(net);
if (status)
goto err;
return 0;
err:
nfs4_legacy_state_shutdown(net);
return status;
}
static void
nfsd4_shutdown_recdir(struct nfsd_net *nn)
{
if (!nn->rec_file)
return;
fput(nn->rec_file);
nn->rec_file = NULL;
}
static void
nfsd4_legacy_tracking_exit(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
nfs4_release_reclaim(nn);
nfsd4_shutdown_recdir(nn);
nfs4_legacy_state_shutdown(net);
}
/*
* Change the NFSv4 recovery directory to recdir.
*/
int
nfs4_reset_recoverydir(char *recdir)
{
int status;
struct path path;
status = kern_path(recdir, LOOKUP_FOLLOW, &path);
if (status)
return status;
status = -ENOTDIR;
if (S_ISDIR(path.dentry->d_inode->i_mode)) {
strcpy(user_recovery_dirname, recdir);
status = 0;
}
path_put(&path);
return status;
}
char *
nfs4_recoverydir(void)
{
return user_recovery_dirname;
}
static int
nfsd4_check_legacy_client(struct nfs4_client *clp)
{
int status;
char dname[HEXDIR_LEN];
struct nfs4_client_reclaim *crp;
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
/* did we already find that this client is stable? */
if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
return 0;
status = nfs4_make_rec_clidname(dname, &clp->cl_name);
if (status) {
legacy_recdir_name_error(clp, status);
return status;
}
/* look for it in the reclaim hashtable otherwise */
crp = nfsd4_find_reclaim_client(dname, nn);
if (crp) {
set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
crp->cr_clp = clp;
return 0;
}
return -ENOENT;
}
static struct nfsd4_client_tracking_ops nfsd4_legacy_tracking_ops = {
.init = nfsd4_legacy_tracking_init,
.exit = nfsd4_legacy_tracking_exit,
.create = nfsd4_create_clid_dir,
.remove = nfsd4_remove_clid_dir,
.check = nfsd4_check_legacy_client,
.grace_done = nfsd4_recdir_purge_old,
};
/* Globals */
#define NFSD_PIPE_DIR "nfsd"
#define NFSD_CLD_PIPE "cld"
/* per-net-ns structure for holding cld upcall info */
struct cld_net {
struct rpc_pipe *cn_pipe;
spinlock_t cn_lock;
struct list_head cn_list;
unsigned int cn_xid;
};
struct cld_upcall {
struct list_head cu_list;
struct cld_net *cu_net;
struct task_struct *cu_task;
struct cld_msg cu_msg;
};
static int
__cld_pipe_upcall(struct rpc_pipe *pipe, struct cld_msg *cmsg)
{
int ret;
struct rpc_pipe_msg msg;
memset(&msg, 0, sizeof(msg));
msg.data = cmsg;
msg.len = sizeof(*cmsg);
/*
* Set task state before we queue the upcall. That prevents
* wake_up_process in the downcall from racing with schedule.
*/
set_current_state(TASK_UNINTERRUPTIBLE);
ret = rpc_queue_upcall(pipe, &msg);
if (ret < 0) {
set_current_state(TASK_RUNNING);
goto out;
}
schedule();
set_current_state(TASK_RUNNING);
if (msg.errno < 0)
ret = msg.errno;
out:
return ret;
}
static int
cld_pipe_upcall(struct rpc_pipe *pipe, struct cld_msg *cmsg)
{
int ret;
/*
* -EAGAIN occurs when pipe is closed and reopened while there are
* upcalls queued.
*/
do {
ret = __cld_pipe_upcall(pipe, cmsg);
} while (ret == -EAGAIN);
return ret;
}
static ssize_t
cld_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
{
struct cld_upcall *tmp, *cup;
struct cld_msg __user *cmsg = (struct cld_msg __user *)src;
uint32_t xid;
struct nfsd_net *nn = net_generic(filp->f_dentry->d_sb->s_fs_info,
nfsd_net_id);
struct cld_net *cn = nn->cld_net;
if (mlen != sizeof(*cmsg)) {
dprintk("%s: got %zu bytes, expected %zu\n", __func__, mlen,
sizeof(*cmsg));
return -EINVAL;
}
/* copy just the xid so we can try to find that */
if (copy_from_user(&xid, &cmsg->cm_xid, sizeof(xid)) != 0) {
dprintk("%s: error when copying xid from userspace", __func__);
return -EFAULT;
}
/* walk the list and find corresponding xid */
cup = NULL;
spin_lock(&cn->cn_lock);
list_for_each_entry(tmp, &cn->cn_list, cu_list) {
if (get_unaligned(&tmp->cu_msg.cm_xid) == xid) {
cup = tmp;
list_del_init(&cup->cu_list);
break;
}
}
spin_unlock(&cn->cn_lock);
/* couldn't find upcall? */
if (!cup) {
dprintk("%s: couldn't find upcall -- xid=%u\n", __func__, xid);
return -EINVAL;
}
if (copy_from_user(&cup->cu_msg, src, mlen) != 0)
return -EFAULT;
wake_up_process(cup->cu_task);
return mlen;
}
static void
cld_pipe_destroy_msg(struct rpc_pipe_msg *msg)
{
struct cld_msg *cmsg = msg->data;
struct cld_upcall *cup = container_of(cmsg, struct cld_upcall,
cu_msg);
/* errno >= 0 means we got a downcall */
if (msg->errno >= 0)
return;
wake_up_process(cup->cu_task);
}
static const struct rpc_pipe_ops cld_upcall_ops = {
.upcall = rpc_pipe_generic_upcall,
.downcall = cld_pipe_downcall,
.destroy_msg = cld_pipe_destroy_msg,
};
static struct dentry *
nfsd4_cld_register_sb(struct super_block *sb, struct rpc_pipe *pipe)
{
struct dentry *dir, *dentry;
dir = rpc_d_lookup_sb(sb, NFSD_PIPE_DIR);
if (dir == NULL)
return ERR_PTR(-ENOENT);
dentry = rpc_mkpipe_dentry(dir, NFSD_CLD_PIPE, NULL, pipe);
dput(dir);
return dentry;
}
static void
nfsd4_cld_unregister_sb(struct rpc_pipe *pipe)
{
if (pipe->dentry)
rpc_unlink(pipe->dentry);
}
static struct dentry *
nfsd4_cld_register_net(struct net *net, struct rpc_pipe *pipe)
{
struct super_block *sb;
struct dentry *dentry;
sb = rpc_get_sb_net(net);
if (!sb)
return NULL;
dentry = nfsd4_cld_register_sb(sb, pipe);
rpc_put_sb_net(net);
return dentry;
}
static void
nfsd4_cld_unregister_net(struct net *net, struct rpc_pipe *pipe)
{
struct super_block *sb;
sb = rpc_get_sb_net(net);
if (sb) {
nfsd4_cld_unregister_sb(pipe);
rpc_put_sb_net(net);
}
}
/* Initialize rpc_pipefs pipe for communication with client tracking daemon */
static int
nfsd4_init_cld_pipe(struct net *net)
{
int ret;
struct dentry *dentry;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
struct cld_net *cn;
if (nn->cld_net)
return 0;
cn = kzalloc(sizeof(*cn), GFP_KERNEL);
if (!cn) {
ret = -ENOMEM;
goto err;
}
cn->cn_pipe = rpc_mkpipe_data(&cld_upcall_ops, RPC_PIPE_WAIT_FOR_OPEN);
if (IS_ERR(cn->cn_pipe)) {
ret = PTR_ERR(cn->cn_pipe);
goto err;
}
spin_lock_init(&cn->cn_lock);
INIT_LIST_HEAD(&cn->cn_list);
dentry = nfsd4_cld_register_net(net, cn->cn_pipe);
if (IS_ERR(dentry)) {
ret = PTR_ERR(dentry);
goto err_destroy_data;
}
cn->cn_pipe->dentry = dentry;
nn->cld_net = cn;
return 0;
err_destroy_data:
rpc_destroy_pipe_data(cn->cn_pipe);
err:
kfree(cn);
printk(KERN_ERR "NFSD: unable to create nfsdcld upcall pipe (%d)\n",
ret);
return ret;
}
static void
nfsd4_remove_cld_pipe(struct net *net)
{
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
struct cld_net *cn = nn->cld_net;
nfsd4_cld_unregister_net(net, cn->cn_pipe);
rpc_destroy_pipe_data(cn->cn_pipe);
kfree(nn->cld_net);
nn->cld_net = NULL;
}
static struct cld_upcall *
alloc_cld_upcall(struct cld_net *cn)
{
struct cld_upcall *new, *tmp;
new = kzalloc(sizeof(*new), GFP_KERNEL);
if (!new)
return new;
/* FIXME: hard cap on number in flight? */
restart_search:
spin_lock(&cn->cn_lock);
list_for_each_entry(tmp, &cn->cn_list, cu_list) {
if (tmp->cu_msg.cm_xid == cn->cn_xid) {
cn->cn_xid++;
spin_unlock(&cn->cn_lock);
goto restart_search;
}
}
new->cu_task = current;
new->cu_msg.cm_vers = CLD_UPCALL_VERSION;
put_unaligned(cn->cn_xid++, &new->cu_msg.cm_xid);
new->cu_net = cn;
list_add(&new->cu_list, &cn->cn_list);
spin_unlock(&cn->cn_lock);
dprintk("%s: allocated xid %u\n", __func__, new->cu_msg.cm_xid);
return new;
}
static void
free_cld_upcall(struct cld_upcall *victim)
{
struct cld_net *cn = victim->cu_net;
spin_lock(&cn->cn_lock);
list_del(&victim->cu_list);
spin_unlock(&cn->cn_lock);
kfree(victim);
}
/* Ask daemon to create a new record */
static void
nfsd4_cld_create(struct nfs4_client *clp)
{
int ret;
struct cld_upcall *cup;
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
struct cld_net *cn = nn->cld_net;
/* Don't upcall if it's already stored */
if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
return;
cup = alloc_cld_upcall(cn);
if (!cup) {
ret = -ENOMEM;
goto out_err;
}
cup->cu_msg.cm_cmd = Cld_Create;
cup->cu_msg.cm_u.cm_name.cn_len = clp->cl_name.len;
memcpy(cup->cu_msg.cm_u.cm_name.cn_id, clp->cl_name.data,
clp->cl_name.len);
ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg);
if (!ret) {
ret = cup->cu_msg.cm_status;
set_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
}
free_cld_upcall(cup);
out_err:
if (ret)
printk(KERN_ERR "NFSD: Unable to create client "
"record on stable storage: %d\n", ret);
}
/* Ask daemon to create a new record */
static void
nfsd4_cld_remove(struct nfs4_client *clp)
{
int ret;
struct cld_upcall *cup;
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
struct cld_net *cn = nn->cld_net;
/* Don't upcall if it's already removed */
if (!test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
return;
cup = alloc_cld_upcall(cn);
if (!cup) {
ret = -ENOMEM;
goto out_err;
}
cup->cu_msg.cm_cmd = Cld_Remove;
cup->cu_msg.cm_u.cm_name.cn_len = clp->cl_name.len;
memcpy(cup->cu_msg.cm_u.cm_name.cn_id, clp->cl_name.data,
clp->cl_name.len);
ret = cld_pipe_upcall(cn->cn_pipe, &cup->cu_msg);
if (!ret) {
ret = cup->cu_msg.cm_status;
clear_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags);
}
free_cld_upcall(cup);
out_err:
if (ret)
printk(KERN_ERR "NFSD: Unable to remove client "
"record from stable storage: %d\n", ret);
}
/* Check for presence of a record, and update its timestamp */
static int
nfsd4_cld_check(struct nfs4_client *clp)
{
int ret;
struct cld_upcall *cup;
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
struct cld_net *cn = nn->cld_net;
/* Don't upcall if one was already stored during this grace pd */
if (test_bit(NFSD4_CLIENT_STABLE, &clp->cl_flags))
return 0;
cup = alloc_cld_upcall(cn);
if (!cup) {
printk(KERN_ERR "NFSD: Unable to check client record on "
"stable storage: %d\n", -ENOMEM);
return -ENOMEM;
}
cup->cu_msg.cm_cmd = Cld_Check;
cup->cu_msg.cm_u.cm_name.cn_len = clp->cl_name.len;
memcpy(cup->cu_msg.cm_u.cm_name.cn_id, clp->cl_name.data,
clp->cl_name.len);