forked from grate-driver/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
pnfs.c
2697 lines (2383 loc) · 71.8 KB
/
pnfs.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
/*
* pNFS functions to call and manage layout drivers.
*
* Copyright (c) 2002 [year of first publication]
* The Regents of the University of Michigan
* All Rights Reserved
*
* Dean Hildebrand <dhildebz@umich.edu>
*
* Permission is granted to use, copy, create derivative works, and
* redistribute this software and such derivative works for any purpose,
* so long as the name of the University of Michigan is not used in
* any advertising or publicity pertaining to the use or distribution
* of this software without specific, written prior authorization. If
* the above copyright notice or any other identification of the
* University of Michigan is included in any copy of any portion of
* this software, then the disclaimer below must also be included.
*
* This software is provided as is, without representation or warranty
* of any kind either express or implied, including without limitation
* the implied warranties of merchantability, fitness for a particular
* purpose, or noninfringement. The Regents of the University of
* Michigan shall not be liable for any damages, including special,
* indirect, incidental, or consequential damages, with respect to any
* claim arising out of or in connection with the use of the software,
* even if it has been or is hereafter advised of the possibility of
* such damages.
*/
#include <linux/nfs_fs.h>
#include <linux/nfs_page.h>
#include <linux/module.h>
#include <linux/sort.h>
#include "internal.h"
#include "pnfs.h"
#include "iostat.h"
#include "nfs4trace.h"
#include "delegation.h"
#include "nfs42.h"
#define NFSDBG_FACILITY NFSDBG_PNFS
#define PNFS_LAYOUTGET_RETRY_TIMEOUT (120*HZ)
/* Locking:
*
* pnfs_spinlock:
* protects pnfs_modules_tbl.
*/
static DEFINE_SPINLOCK(pnfs_spinlock);
/*
* pnfs_modules_tbl holds all pnfs modules
*/
static LIST_HEAD(pnfs_modules_tbl);
static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo);
static void pnfs_free_returned_lsegs(struct pnfs_layout_hdr *lo,
struct list_head *free_me,
const struct pnfs_layout_range *range,
u32 seq);
static bool pnfs_lseg_dec_and_remove_zero(struct pnfs_layout_segment *lseg,
struct list_head *tmp_list);
/* Return the registered pnfs layout driver module matching given id */
static struct pnfs_layoutdriver_type *
find_pnfs_driver_locked(u32 id)
{
struct pnfs_layoutdriver_type *local;
list_for_each_entry(local, &pnfs_modules_tbl, pnfs_tblid)
if (local->id == id)
goto out;
local = NULL;
out:
dprintk("%s: Searching for id %u, found %p\n", __func__, id, local);
return local;
}
static struct pnfs_layoutdriver_type *
find_pnfs_driver(u32 id)
{
struct pnfs_layoutdriver_type *local;
spin_lock(&pnfs_spinlock);
local = find_pnfs_driver_locked(id);
if (local != NULL && !try_module_get(local->owner)) {
dprintk("%s: Could not grab reference on module\n", __func__);
local = NULL;
}
spin_unlock(&pnfs_spinlock);
return local;
}
void
unset_pnfs_layoutdriver(struct nfs_server *nfss)
{
if (nfss->pnfs_curr_ld) {
if (nfss->pnfs_curr_ld->clear_layoutdriver)
nfss->pnfs_curr_ld->clear_layoutdriver(nfss);
/* Decrement the MDS count. Purge the deviceid cache if zero */
if (atomic_dec_and_test(&nfss->nfs_client->cl_mds_count))
nfs4_deviceid_purge_client(nfss->nfs_client);
module_put(nfss->pnfs_curr_ld->owner);
}
nfss->pnfs_curr_ld = NULL;
}
/*
* When the server sends a list of layout types, we choose one in the order
* given in the list below.
*
* FIXME: should this list be configurable in some fashion? module param?
* mount option? something else?
*/
static const u32 ld_prefs[] = {
LAYOUT_SCSI,
LAYOUT_BLOCK_VOLUME,
LAYOUT_OSD2_OBJECTS,
LAYOUT_FLEX_FILES,
LAYOUT_NFSV4_1_FILES,
0
};
static int
ld_cmp(const void *e1, const void *e2)
{
u32 ld1 = *((u32 *)e1);
u32 ld2 = *((u32 *)e2);
int i;
for (i = 0; ld_prefs[i] != 0; i++) {
if (ld1 == ld_prefs[i])
return -1;
if (ld2 == ld_prefs[i])
return 1;
}
return 0;
}
/*
* Try to set the server's pnfs module to the pnfs layout type specified by id.
* Currently only one pNFS layout driver per filesystem is supported.
*
* @ids array of layout types supported by MDS.
*/
void
set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh,
struct nfs_fsinfo *fsinfo)
{
struct pnfs_layoutdriver_type *ld_type = NULL;
u32 id;
int i;
if (fsinfo->nlayouttypes == 0)
goto out_no_driver;
if (!(server->nfs_client->cl_exchange_flags &
(EXCHGID4_FLAG_USE_NON_PNFS | EXCHGID4_FLAG_USE_PNFS_MDS))) {
printk(KERN_ERR "NFS: %s: cl_exchange_flags 0x%x\n",
__func__, server->nfs_client->cl_exchange_flags);
goto out_no_driver;
}
sort(fsinfo->layouttype, fsinfo->nlayouttypes,
sizeof(*fsinfo->layouttype), ld_cmp, NULL);
for (i = 0; i < fsinfo->nlayouttypes; i++) {
id = fsinfo->layouttype[i];
ld_type = find_pnfs_driver(id);
if (!ld_type) {
request_module("%s-%u", LAYOUT_NFSV4_1_MODULE_PREFIX,
id);
ld_type = find_pnfs_driver(id);
}
if (ld_type)
break;
}
if (!ld_type) {
dprintk("%s: No pNFS module found!\n", __func__);
goto out_no_driver;
}
server->pnfs_curr_ld = ld_type;
if (ld_type->set_layoutdriver
&& ld_type->set_layoutdriver(server, mntfh)) {
printk(KERN_ERR "NFS: %s: Error initializing pNFS layout "
"driver %u.\n", __func__, id);
module_put(ld_type->owner);
goto out_no_driver;
}
/* Bump the MDS count */
atomic_inc(&server->nfs_client->cl_mds_count);
dprintk("%s: pNFS module for %u set\n", __func__, id);
return;
out_no_driver:
dprintk("%s: Using NFSv4 I/O\n", __func__);
server->pnfs_curr_ld = NULL;
}
int
pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *ld_type)
{
int status = -EINVAL;
struct pnfs_layoutdriver_type *tmp;
if (ld_type->id == 0) {
printk(KERN_ERR "NFS: %s id 0 is reserved\n", __func__);
return status;
}
if (!ld_type->alloc_lseg || !ld_type->free_lseg) {
printk(KERN_ERR "NFS: %s Layout driver must provide "
"alloc_lseg and free_lseg.\n", __func__);
return status;
}
spin_lock(&pnfs_spinlock);
tmp = find_pnfs_driver_locked(ld_type->id);
if (!tmp) {
list_add(&ld_type->pnfs_tblid, &pnfs_modules_tbl);
status = 0;
dprintk("%s Registering id:%u name:%s\n", __func__, ld_type->id,
ld_type->name);
} else {
printk(KERN_ERR "NFS: %s Module with id %d already loaded!\n",
__func__, ld_type->id);
}
spin_unlock(&pnfs_spinlock);
return status;
}
EXPORT_SYMBOL_GPL(pnfs_register_layoutdriver);
void
pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *ld_type)
{
dprintk("%s Deregistering id:%u\n", __func__, ld_type->id);
spin_lock(&pnfs_spinlock);
list_del(&ld_type->pnfs_tblid);
spin_unlock(&pnfs_spinlock);
}
EXPORT_SYMBOL_GPL(pnfs_unregister_layoutdriver);
/*
* pNFS client layout cache
*/
/* Need to hold i_lock if caller does not already hold reference */
void
pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo)
{
atomic_inc(&lo->plh_refcount);
}
static struct pnfs_layout_hdr *
pnfs_alloc_layout_hdr(struct inode *ino, gfp_t gfp_flags)
{
struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld;
return ld->alloc_layout_hdr(ino, gfp_flags);
}
static void
pnfs_free_layout_hdr(struct pnfs_layout_hdr *lo)
{
struct nfs_server *server = NFS_SERVER(lo->plh_inode);
struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
if (!list_empty(&lo->plh_layouts)) {
struct nfs_client *clp = server->nfs_client;
spin_lock(&clp->cl_lock);
list_del_init(&lo->plh_layouts);
spin_unlock(&clp->cl_lock);
}
put_rpccred(lo->plh_lc_cred);
return ld->free_layout_hdr(lo);
}
static void
pnfs_detach_layout_hdr(struct pnfs_layout_hdr *lo)
{
struct nfs_inode *nfsi = NFS_I(lo->plh_inode);
dprintk("%s: freeing layout cache %p\n", __func__, lo);
nfsi->layout = NULL;
/* Reset MDS Threshold I/O counters */
nfsi->write_io = 0;
nfsi->read_io = 0;
}
void
pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
{
struct inode *inode = lo->plh_inode;
pnfs_layoutreturn_before_put_layout_hdr(lo);
if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) {
if (!list_empty(&lo->plh_segs))
WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n");
pnfs_detach_layout_hdr(lo);
spin_unlock(&inode->i_lock);
pnfs_free_layout_hdr(lo);
}
}
static void
pnfs_set_plh_return_info(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode,
u32 seq)
{
if (lo->plh_return_iomode != 0 && lo->plh_return_iomode != iomode)
iomode = IOMODE_ANY;
lo->plh_return_iomode = iomode;
set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
if (seq != 0) {
WARN_ON_ONCE(lo->plh_return_seq != 0 && lo->plh_return_seq != seq);
lo->plh_return_seq = seq;
}
}
static void
pnfs_clear_layoutreturn_info(struct pnfs_layout_hdr *lo)
{
lo->plh_return_iomode = 0;
lo->plh_return_seq = 0;
clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
}
static void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo)
{
clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags);
clear_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags);
smp_mb__after_atomic();
wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN);
rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
}
static void
pnfs_clear_lseg_state(struct pnfs_layout_segment *lseg,
struct list_head *free_me)
{
clear_bit(NFS_LSEG_ROC, &lseg->pls_flags);
clear_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags);
if (test_and_clear_bit(NFS_LSEG_VALID, &lseg->pls_flags))
pnfs_lseg_dec_and_remove_zero(lseg, free_me);
if (test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
pnfs_lseg_dec_and_remove_zero(lseg, free_me);
}
/*
* Mark a pnfs_layout_hdr and all associated layout segments as invalid
*
* In order to continue using the pnfs_layout_hdr, a full recovery
* is required.
* Note that caller must hold inode->i_lock.
*/
int
pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo,
struct list_head *lseg_list)
{
struct pnfs_layout_range range = {
.iomode = IOMODE_ANY,
.offset = 0,
.length = NFS4_MAX_UINT64,
};
struct pnfs_layout_segment *lseg, *next;
set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
pnfs_clear_layoutreturn_info(lo);
list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
pnfs_clear_lseg_state(lseg, lseg_list);
pnfs_free_returned_lsegs(lo, lseg_list, &range, 0);
if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags) &&
!test_and_set_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags))
pnfs_clear_layoutreturn_waitbit(lo);
return !list_empty(&lo->plh_segs);
}
static int
pnfs_iomode_to_fail_bit(u32 iomode)
{
return iomode == IOMODE_RW ?
NFS_LAYOUT_RW_FAILED : NFS_LAYOUT_RO_FAILED;
}
static void
pnfs_layout_set_fail_bit(struct pnfs_layout_hdr *lo, int fail_bit)
{
lo->plh_retry_timestamp = jiffies;
if (!test_and_set_bit(fail_bit, &lo->plh_flags))
atomic_inc(&lo->plh_refcount);
}
static void
pnfs_layout_clear_fail_bit(struct pnfs_layout_hdr *lo, int fail_bit)
{
if (test_and_clear_bit(fail_bit, &lo->plh_flags))
atomic_dec(&lo->plh_refcount);
}
static void
pnfs_layout_io_set_failed(struct pnfs_layout_hdr *lo, u32 iomode)
{
struct inode *inode = lo->plh_inode;
struct pnfs_layout_range range = {
.iomode = iomode,
.offset = 0,
.length = NFS4_MAX_UINT64,
};
LIST_HEAD(head);
spin_lock(&inode->i_lock);
pnfs_layout_set_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
pnfs_mark_matching_lsegs_invalid(lo, &head, &range, 0);
spin_unlock(&inode->i_lock);
pnfs_free_lseg_list(&head);
dprintk("%s Setting layout IOMODE_%s fail bit\n", __func__,
iomode == IOMODE_RW ? "RW" : "READ");
}
static bool
pnfs_layout_io_test_failed(struct pnfs_layout_hdr *lo, u32 iomode)
{
unsigned long start, end;
int fail_bit = pnfs_iomode_to_fail_bit(iomode);
if (test_bit(fail_bit, &lo->plh_flags) == 0)
return false;
end = jiffies;
start = end - PNFS_LAYOUTGET_RETRY_TIMEOUT;
if (!time_in_range(lo->plh_retry_timestamp, start, end)) {
/* It is time to retry the failed layoutgets */
pnfs_layout_clear_fail_bit(lo, fail_bit);
return false;
}
return true;
}
static void
pnfs_init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg,
const struct pnfs_layout_range *range,
const nfs4_stateid *stateid)
{
INIT_LIST_HEAD(&lseg->pls_list);
INIT_LIST_HEAD(&lseg->pls_lc_list);
atomic_set(&lseg->pls_refcount, 1);
set_bit(NFS_LSEG_VALID, &lseg->pls_flags);
lseg->pls_layout = lo;
lseg->pls_range = *range;
lseg->pls_seq = be32_to_cpu(stateid->seqid);
}
static void pnfs_free_lseg(struct pnfs_layout_segment *lseg)
{
if (lseg != NULL) {
struct inode *inode = lseg->pls_layout->plh_inode;
NFS_SERVER(inode)->pnfs_curr_ld->free_lseg(lseg);
}
}
static void
pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo,
struct pnfs_layout_segment *lseg)
{
WARN_ON(test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
list_del_init(&lseg->pls_list);
/* Matched by pnfs_get_layout_hdr in pnfs_layout_insert_lseg */
atomic_dec(&lo->plh_refcount);
if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
return;
if (list_empty(&lo->plh_segs) &&
!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags) &&
!test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
if (atomic_read(&lo->plh_outstanding) == 0)
set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
}
}
static bool
pnfs_cache_lseg_for_layoutreturn(struct pnfs_layout_hdr *lo,
struct pnfs_layout_segment *lseg)
{
if (test_and_clear_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags) &&
pnfs_layout_is_valid(lo)) {
pnfs_set_plh_return_info(lo, lseg->pls_range.iomode, 0);
list_move_tail(&lseg->pls_list, &lo->plh_return_segs);
return true;
}
return false;
}
void
pnfs_put_lseg(struct pnfs_layout_segment *lseg)
{
struct pnfs_layout_hdr *lo;
struct inode *inode;
if (!lseg)
return;
dprintk("%s: lseg %p ref %d valid %d\n", __func__, lseg,
atomic_read(&lseg->pls_refcount),
test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
lo = lseg->pls_layout;
inode = lo->plh_inode;
if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) {
if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) {
spin_unlock(&inode->i_lock);
return;
}
pnfs_get_layout_hdr(lo);
pnfs_layout_remove_lseg(lo, lseg);
if (pnfs_cache_lseg_for_layoutreturn(lo, lseg))
lseg = NULL;
spin_unlock(&inode->i_lock);
pnfs_free_lseg(lseg);
pnfs_put_layout_hdr(lo);
}
}
EXPORT_SYMBOL_GPL(pnfs_put_lseg);
static void pnfs_free_lseg_async_work(struct work_struct *work)
{
struct pnfs_layout_segment *lseg;
struct pnfs_layout_hdr *lo;
lseg = container_of(work, struct pnfs_layout_segment, pls_work);
lo = lseg->pls_layout;
pnfs_free_lseg(lseg);
pnfs_put_layout_hdr(lo);
}
static void pnfs_free_lseg_async(struct pnfs_layout_segment *lseg)
{
INIT_WORK(&lseg->pls_work, pnfs_free_lseg_async_work);
schedule_work(&lseg->pls_work);
}
void
pnfs_put_lseg_locked(struct pnfs_layout_segment *lseg)
{
if (!lseg)
return;
assert_spin_locked(&lseg->pls_layout->plh_inode->i_lock);
dprintk("%s: lseg %p ref %d valid %d\n", __func__, lseg,
atomic_read(&lseg->pls_refcount),
test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
if (atomic_dec_and_test(&lseg->pls_refcount)) {
struct pnfs_layout_hdr *lo = lseg->pls_layout;
if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags))
return;
pnfs_layout_remove_lseg(lo, lseg);
if (!pnfs_cache_lseg_for_layoutreturn(lo, lseg)) {
pnfs_get_layout_hdr(lo);
pnfs_free_lseg_async(lseg);
}
}
}
EXPORT_SYMBOL_GPL(pnfs_put_lseg_locked);
/*
* is l2 fully contained in l1?
* start1 end1
* [----------------------------------)
* start2 end2
* [----------------)
*/
static bool
pnfs_lseg_range_contained(const struct pnfs_layout_range *l1,
const struct pnfs_layout_range *l2)
{
u64 start1 = l1->offset;
u64 end1 = pnfs_end_offset(start1, l1->length);
u64 start2 = l2->offset;
u64 end2 = pnfs_end_offset(start2, l2->length);
return (start1 <= start2) && (end1 >= end2);
}
static bool pnfs_lseg_dec_and_remove_zero(struct pnfs_layout_segment *lseg,
struct list_head *tmp_list)
{
if (!atomic_dec_and_test(&lseg->pls_refcount))
return false;
pnfs_layout_remove_lseg(lseg->pls_layout, lseg);
list_add(&lseg->pls_list, tmp_list);
return true;
}
/* Returns 1 if lseg is removed from list, 0 otherwise */
static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
struct list_head *tmp_list)
{
int rv = 0;
if (test_and_clear_bit(NFS_LSEG_VALID, &lseg->pls_flags)) {
/* Remove the reference keeping the lseg in the
* list. It will now be removed when all
* outstanding io is finished.
*/
dprintk("%s: lseg %p ref %d\n", __func__, lseg,
atomic_read(&lseg->pls_refcount));
if (pnfs_lseg_dec_and_remove_zero(lseg, tmp_list))
rv = 1;
}
return rv;
}
/*
* Compare 2 layout stateid sequence ids, to see which is newer,
* taking into account wraparound issues.
*/
static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
{
return (s32)(s1 - s2) > 0;
}
static bool
pnfs_should_free_range(const struct pnfs_layout_range *lseg_range,
const struct pnfs_layout_range *recall_range)
{
return (recall_range->iomode == IOMODE_ANY ||
lseg_range->iomode == recall_range->iomode) &&
pnfs_lseg_range_intersecting(lseg_range, recall_range);
}
static bool
pnfs_match_lseg_recall(const struct pnfs_layout_segment *lseg,
const struct pnfs_layout_range *recall_range,
u32 seq)
{
if (seq != 0 && pnfs_seqid_is_newer(lseg->pls_seq, seq))
return false;
if (recall_range == NULL)
return true;
return pnfs_should_free_range(&lseg->pls_range, recall_range);
}
/**
* pnfs_mark_matching_lsegs_invalid - tear down lsegs or mark them for later
* @lo: layout header containing the lsegs
* @tmp_list: list head where doomed lsegs should go
* @recall_range: optional recall range argument to match (may be NULL)
* @seq: only invalidate lsegs obtained prior to this sequence (may be 0)
*
* Walk the list of lsegs in the layout header, and tear down any that should
* be destroyed. If "recall_range" is specified then the segment must match
* that range. If "seq" is non-zero, then only match segments that were handed
* out at or before that sequence.
*
* Returns number of matching invalid lsegs remaining in list after scanning
* it and purging them.
*/
int
pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
struct list_head *tmp_list,
const struct pnfs_layout_range *recall_range,
u32 seq)
{
struct pnfs_layout_segment *lseg, *next;
int remaining = 0;
dprintk("%s:Begin lo %p\n", __func__, lo);
if (list_empty(&lo->plh_segs))
return 0;
list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
if (pnfs_match_lseg_recall(lseg, recall_range, seq)) {
dprintk("%s: freeing lseg %p iomode %d seq %u"
"offset %llu length %llu\n", __func__,
lseg, lseg->pls_range.iomode, lseg->pls_seq,
lseg->pls_range.offset, lseg->pls_range.length);
if (!mark_lseg_invalid(lseg, tmp_list))
remaining++;
}
dprintk("%s:Return %i\n", __func__, remaining);
return remaining;
}
static void
pnfs_free_returned_lsegs(struct pnfs_layout_hdr *lo,
struct list_head *free_me,
const struct pnfs_layout_range *range,
u32 seq)
{
struct pnfs_layout_segment *lseg, *next;
list_for_each_entry_safe(lseg, next, &lo->plh_return_segs, pls_list) {
if (pnfs_match_lseg_recall(lseg, range, seq))
list_move_tail(&lseg->pls_list, free_me);
}
}
/* note free_me must contain lsegs from a single layout_hdr */
void
pnfs_free_lseg_list(struct list_head *free_me)
{
struct pnfs_layout_segment *lseg, *tmp;
if (list_empty(free_me))
return;
list_for_each_entry_safe(lseg, tmp, free_me, pls_list) {
list_del(&lseg->pls_list);
pnfs_free_lseg(lseg);
}
}
void
pnfs_destroy_layout(struct nfs_inode *nfsi)
{
struct pnfs_layout_hdr *lo;
LIST_HEAD(tmp_list);
spin_lock(&nfsi->vfs_inode.i_lock);
lo = nfsi->layout;
if (lo) {
pnfs_get_layout_hdr(lo);
pnfs_mark_layout_stateid_invalid(lo, &tmp_list);
pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED);
pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED);
spin_unlock(&nfsi->vfs_inode.i_lock);
pnfs_free_lseg_list(&tmp_list);
pnfs_put_layout_hdr(lo);
} else
spin_unlock(&nfsi->vfs_inode.i_lock);
}
EXPORT_SYMBOL_GPL(pnfs_destroy_layout);
static bool
pnfs_layout_add_bulk_destroy_list(struct inode *inode,
struct list_head *layout_list)
{
struct pnfs_layout_hdr *lo;
bool ret = false;
spin_lock(&inode->i_lock);
lo = NFS_I(inode)->layout;
if (lo != NULL && list_empty(&lo->plh_bulk_destroy)) {
pnfs_get_layout_hdr(lo);
list_add(&lo->plh_bulk_destroy, layout_list);
ret = true;
}
spin_unlock(&inode->i_lock);
return ret;
}
/* Caller must hold rcu_read_lock and clp->cl_lock */
static int
pnfs_layout_bulk_destroy_byserver_locked(struct nfs_client *clp,
struct nfs_server *server,
struct list_head *layout_list)
{
struct pnfs_layout_hdr *lo, *next;
struct inode *inode;
list_for_each_entry_safe(lo, next, &server->layouts, plh_layouts) {
if (test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags))
continue;
inode = igrab(lo->plh_inode);
if (inode == NULL)
continue;
list_del_init(&lo->plh_layouts);
if (pnfs_layout_add_bulk_destroy_list(inode, layout_list))
continue;
rcu_read_unlock();
spin_unlock(&clp->cl_lock);
iput(inode);
spin_lock(&clp->cl_lock);
rcu_read_lock();
return -EAGAIN;
}
return 0;
}
static int
pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list,
bool is_bulk_recall)
{
struct pnfs_layout_hdr *lo;
struct inode *inode;
LIST_HEAD(lseg_list);
int ret = 0;
while (!list_empty(layout_list)) {
lo = list_entry(layout_list->next, struct pnfs_layout_hdr,
plh_bulk_destroy);
dprintk("%s freeing layout for inode %lu\n", __func__,
lo->plh_inode->i_ino);
inode = lo->plh_inode;
pnfs_layoutcommit_inode(inode, false);
spin_lock(&inode->i_lock);
list_del_init(&lo->plh_bulk_destroy);
if (pnfs_mark_layout_stateid_invalid(lo, &lseg_list)) {
if (is_bulk_recall)
set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
ret = -EAGAIN;
}
spin_unlock(&inode->i_lock);
pnfs_free_lseg_list(&lseg_list);
/* Free all lsegs that are attached to commit buckets */
nfs_commit_inode(inode, 0);
pnfs_put_layout_hdr(lo);
iput(inode);
}
return ret;
}
int
pnfs_destroy_layouts_byfsid(struct nfs_client *clp,
struct nfs_fsid *fsid,
bool is_recall)
{
struct nfs_server *server;
LIST_HEAD(layout_list);
spin_lock(&clp->cl_lock);
rcu_read_lock();
restart:
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
if (memcmp(&server->fsid, fsid, sizeof(*fsid)) != 0)
continue;
if (pnfs_layout_bulk_destroy_byserver_locked(clp,
server,
&layout_list) != 0)
goto restart;
}
rcu_read_unlock();
spin_unlock(&clp->cl_lock);
if (list_empty(&layout_list))
return 0;
return pnfs_layout_free_bulk_destroy_list(&layout_list, is_recall);
}
int
pnfs_destroy_layouts_byclid(struct nfs_client *clp,
bool is_recall)
{
struct nfs_server *server;
LIST_HEAD(layout_list);
spin_lock(&clp->cl_lock);
rcu_read_lock();
restart:
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
if (pnfs_layout_bulk_destroy_byserver_locked(clp,
server,
&layout_list) != 0)
goto restart;
}
rcu_read_unlock();
spin_unlock(&clp->cl_lock);
if (list_empty(&layout_list))
return 0;
return pnfs_layout_free_bulk_destroy_list(&layout_list, is_recall);
}
/*
* Called by the state manger to remove all layouts established under an
* expired lease.
*/
void
pnfs_destroy_all_layouts(struct nfs_client *clp)
{
nfs4_deviceid_mark_client_invalid(clp);
nfs4_deviceid_purge_client(clp);
pnfs_destroy_layouts_byclid(clp, false);
}
/* update lo->plh_stateid with new if is more recent */
void
pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
bool update_barrier)
{
u32 oldseq, newseq, new_barrier = 0;
oldseq = be32_to_cpu(lo->plh_stateid.seqid);
newseq = be32_to_cpu(new->seqid);
if (!pnfs_layout_is_valid(lo)) {
nfs4_stateid_copy(&lo->plh_stateid, new);
lo->plh_barrier = newseq;
pnfs_clear_layoutreturn_info(lo);
clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
return;
}
if (pnfs_seqid_is_newer(newseq, oldseq)) {
nfs4_stateid_copy(&lo->plh_stateid, new);
/*
* Because of wraparound, we want to keep the barrier
* "close" to the current seqids.
*/
new_barrier = newseq - atomic_read(&lo->plh_outstanding);
}
if (update_barrier)
new_barrier = be32_to_cpu(new->seqid);
else if (new_barrier == 0)
return;
if (pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
lo->plh_barrier = new_barrier;
}
static bool
pnfs_layout_stateid_blocked(const struct pnfs_layout_hdr *lo,
const nfs4_stateid *stateid)
{
u32 seqid = be32_to_cpu(stateid->seqid);
return !pnfs_seqid_is_newer(seqid, lo->plh_barrier);
}
/* lget is set to 1 if called from inside send_layoutget call chain */
static bool
pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo)
{
return lo->plh_block_lgets ||
test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
}
/*
* Get layout from server.
* for now, assume that whole file layouts are requested.
* arg->offset: 0
* arg->length: all ones
*/
static struct pnfs_layout_segment *
send_layoutget(struct pnfs_layout_hdr *lo,
struct nfs_open_context *ctx,
nfs4_stateid *stateid,
const struct pnfs_layout_range *range,
long *timeout, gfp_t gfp_flags)
{
struct inode *ino = lo->plh_inode;
struct nfs_server *server = NFS_SERVER(ino);
struct nfs4_layoutget *lgp;
loff_t i_size;
dprintk("--> %s\n", __func__);
/*
* Synchronously retrieve layout information from server and
* store in lseg. If we race with a concurrent seqid morphing
* op, then re-send the LAYOUTGET.
*/
lgp = kzalloc(sizeof(*lgp), gfp_flags);
if (lgp == NULL)
return ERR_PTR(-ENOMEM);
i_size = i_size_read(ino);
lgp->args.minlength = PAGE_SIZE;
if (lgp->args.minlength > range->length)
lgp->args.minlength = range->length;
if (range->iomode == IOMODE_READ) {
if (range->offset >= i_size)
lgp->args.minlength = 0;
else if (i_size - range->offset < lgp->args.minlength)
lgp->args.minlength = i_size - range->offset;
}
lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
pnfs_copy_range(&lgp->args.range, range);
lgp->args.type = server->pnfs_curr_ld->id;
lgp->args.inode = ino;
lgp->args.ctx = get_nfs_open_context(ctx);
nfs4_stateid_copy(&lgp->args.stateid, stateid);
lgp->gfp_flags = gfp_flags;
lgp->cred = lo->plh_lc_cred;
return nfs4_proc_layoutget(lgp, timeout, gfp_flags);
}
static void pnfs_clear_layoutcommit(struct inode *inode,
struct list_head *head)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct pnfs_layout_segment *lseg, *tmp;
if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags))
return;
list_for_each_entry_safe(lseg, tmp, &nfsi->layout->plh_segs, pls_list) {
if (!test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
continue;
pnfs_lseg_dec_and_remove_zero(lseg, head);
}
}
void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo,
const nfs4_stateid *arg_stateid,