forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
flexfilelayout.c
2414 lines (2071 loc) · 62.4 KB
/
flexfilelayout.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
/*
* Module for pnfs flexfile layout driver.
*
* Copyright (c) 2014, Primary Data, Inc. All rights reserved.
*
* Tao Peng <[email protected]>
*/
#include <linux/nfs_fs.h>
#include <linux/nfs_page.h>
#include <linux/module.h>
#include <linux/sunrpc/metrics.h>
#include "flexfilelayout.h"
#include "../nfs4session.h"
#include "../nfs4idmap.h"
#include "../internal.h"
#include "../delegation.h"
#include "../nfs4trace.h"
#include "../iostat.h"
#include "../nfs.h"
#include "../nfs42.h"
#define NFSDBG_FACILITY NFSDBG_PNFS_LD
#define FF_LAYOUT_POLL_RETRY_MAX (15*HZ)
#define FF_LAYOUTRETURN_MAXERR 20
static struct group_info *ff_zero_group;
static void ff_layout_read_record_layoutstats_done(struct rpc_task *task,
struct nfs_pgio_header *hdr);
static int ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo,
struct nfs42_layoutstat_devinfo *devinfo,
int dev_limit);
static void ff_layout_encode_ff_layoutupdate(struct xdr_stream *xdr,
const struct nfs42_layoutstat_devinfo *devinfo,
struct nfs4_ff_layout_mirror *mirror);
static struct pnfs_layout_hdr *
ff_layout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
{
struct nfs4_flexfile_layout *ffl;
ffl = kzalloc(sizeof(*ffl), gfp_flags);
if (ffl) {
INIT_LIST_HEAD(&ffl->error_list);
INIT_LIST_HEAD(&ffl->mirrors);
ffl->last_report_time = ktime_get();
return &ffl->generic_hdr;
} else
return NULL;
}
static void
ff_layout_free_layout_hdr(struct pnfs_layout_hdr *lo)
{
struct nfs4_ff_layout_ds_err *err, *n;
list_for_each_entry_safe(err, n, &FF_LAYOUT_FROM_HDR(lo)->error_list,
list) {
list_del(&err->list);
kfree(err);
}
kfree(FF_LAYOUT_FROM_HDR(lo));
}
static int decode_pnfs_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
{
__be32 *p;
p = xdr_inline_decode(xdr, NFS4_STATEID_SIZE);
if (unlikely(p == NULL))
return -ENOBUFS;
stateid->type = NFS4_PNFS_DS_STATEID_TYPE;
memcpy(stateid->data, p, NFS4_STATEID_SIZE);
dprintk("%s: stateid id= [%x%x%x%x]\n", __func__,
p[0], p[1], p[2], p[3]);
return 0;
}
static int decode_deviceid(struct xdr_stream *xdr, struct nfs4_deviceid *devid)
{
__be32 *p;
p = xdr_inline_decode(xdr, NFS4_DEVICEID4_SIZE);
if (unlikely(!p))
return -ENOBUFS;
memcpy(devid, p, NFS4_DEVICEID4_SIZE);
nfs4_print_deviceid(devid);
return 0;
}
static int decode_nfs_fh(struct xdr_stream *xdr, struct nfs_fh *fh)
{
__be32 *p;
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
return -ENOBUFS;
fh->size = be32_to_cpup(p++);
if (fh->size > sizeof(struct nfs_fh)) {
printk(KERN_ERR "NFS flexfiles: Too big fh received %d\n",
fh->size);
return -EOVERFLOW;
}
/* fh.data */
p = xdr_inline_decode(xdr, fh->size);
if (unlikely(!p))
return -ENOBUFS;
memcpy(&fh->data, p, fh->size);
dprintk("%s: fh len %d\n", __func__, fh->size);
return 0;
}
/*
* Currently only stringified uids and gids are accepted.
* I.e., kerberos is not supported to the DSes, so no pricipals.
*
* That means that one common function will suffice, but when
* principals are added, this should be split to accomodate
* calls to both nfs_map_name_to_uid() and nfs_map_group_to_gid().
*/
static int
decode_name(struct xdr_stream *xdr, u32 *id)
{
__be32 *p;
int len;
/* opaque_length(4)*/
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
return -ENOBUFS;
len = be32_to_cpup(p++);
if (len < 0)
return -EINVAL;
dprintk("%s: len %u\n", __func__, len);
/* opaque body */
p = xdr_inline_decode(xdr, len);
if (unlikely(!p))
return -ENOBUFS;
if (!nfs_map_string_to_numeric((char *)p, len, id))
return -EINVAL;
return 0;
}
static bool ff_mirror_match_fh(const struct nfs4_ff_layout_mirror *m1,
const struct nfs4_ff_layout_mirror *m2)
{
int i, j;
if (m1->fh_versions_cnt != m2->fh_versions_cnt)
return false;
for (i = 0; i < m1->fh_versions_cnt; i++) {
bool found_fh = false;
for (j = 0; j < m2->fh_versions_cnt; j++) {
if (nfs_compare_fh(&m1->fh_versions[i],
&m2->fh_versions[j]) == 0) {
found_fh = true;
break;
}
}
if (!found_fh)
return false;
}
return true;
}
static struct nfs4_ff_layout_mirror *
ff_layout_add_mirror(struct pnfs_layout_hdr *lo,
struct nfs4_ff_layout_mirror *mirror)
{
struct nfs4_flexfile_layout *ff_layout = FF_LAYOUT_FROM_HDR(lo);
struct nfs4_ff_layout_mirror *pos;
struct inode *inode = lo->plh_inode;
spin_lock(&inode->i_lock);
list_for_each_entry(pos, &ff_layout->mirrors, mirrors) {
if (memcmp(&mirror->devid, &pos->devid, sizeof(pos->devid)) != 0)
continue;
if (!ff_mirror_match_fh(mirror, pos))
continue;
if (refcount_inc_not_zero(&pos->ref)) {
spin_unlock(&inode->i_lock);
return pos;
}
}
list_add(&mirror->mirrors, &ff_layout->mirrors);
mirror->layout = lo;
spin_unlock(&inode->i_lock);
return mirror;
}
static void
ff_layout_remove_mirror(struct nfs4_ff_layout_mirror *mirror)
{
struct inode *inode;
if (mirror->layout == NULL)
return;
inode = mirror->layout->plh_inode;
spin_lock(&inode->i_lock);
list_del(&mirror->mirrors);
spin_unlock(&inode->i_lock);
mirror->layout = NULL;
}
static struct nfs4_ff_layout_mirror *ff_layout_alloc_mirror(gfp_t gfp_flags)
{
struct nfs4_ff_layout_mirror *mirror;
mirror = kzalloc(sizeof(*mirror), gfp_flags);
if (mirror != NULL) {
spin_lock_init(&mirror->lock);
refcount_set(&mirror->ref, 1);
INIT_LIST_HEAD(&mirror->mirrors);
}
return mirror;
}
static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror)
{
struct rpc_cred *cred;
ff_layout_remove_mirror(mirror);
kfree(mirror->fh_versions);
cred = rcu_access_pointer(mirror->ro_cred);
if (cred)
put_rpccred(cred);
cred = rcu_access_pointer(mirror->rw_cred);
if (cred)
put_rpccred(cred);
nfs4_ff_layout_put_deviceid(mirror->mirror_ds);
kfree(mirror);
}
static void ff_layout_put_mirror(struct nfs4_ff_layout_mirror *mirror)
{
if (mirror != NULL && refcount_dec_and_test(&mirror->ref))
ff_layout_free_mirror(mirror);
}
static void ff_layout_free_mirror_array(struct nfs4_ff_layout_segment *fls)
{
int i;
if (fls->mirror_array) {
for (i = 0; i < fls->mirror_array_cnt; i++) {
/* normally mirror_ds is freed in
* .free_deviceid_node but we still do it here
* for .alloc_lseg error path */
ff_layout_put_mirror(fls->mirror_array[i]);
}
kfree(fls->mirror_array);
fls->mirror_array = NULL;
}
}
static int ff_layout_check_layout(struct nfs4_layoutget_res *lgr)
{
int ret = 0;
dprintk("--> %s\n", __func__);
/* FIXME: remove this check when layout segment support is added */
if (lgr->range.offset != 0 ||
lgr->range.length != NFS4_MAX_UINT64) {
dprintk("%s Only whole file layouts supported. Use MDS i/o\n",
__func__);
ret = -EINVAL;
}
dprintk("--> %s returns %d\n", __func__, ret);
return ret;
}
static void _ff_layout_free_lseg(struct nfs4_ff_layout_segment *fls)
{
if (fls) {
ff_layout_free_mirror_array(fls);
kfree(fls);
}
}
static bool
ff_lseg_range_is_after(const struct pnfs_layout_range *l1,
const struct pnfs_layout_range *l2)
{
u64 end1, end2;
if (l1->iomode != l2->iomode)
return l1->iomode != IOMODE_READ;
end1 = pnfs_calc_offset_end(l1->offset, l1->length);
end2 = pnfs_calc_offset_end(l2->offset, l2->length);
if (end1 < l2->offset)
return false;
if (end2 < l1->offset)
return true;
return l2->offset <= l1->offset;
}
static bool
ff_lseg_merge(struct pnfs_layout_segment *new,
struct pnfs_layout_segment *old)
{
u64 new_end, old_end;
if (test_bit(NFS_LSEG_LAYOUTRETURN, &old->pls_flags))
return false;
if (new->pls_range.iomode != old->pls_range.iomode)
return false;
old_end = pnfs_calc_offset_end(old->pls_range.offset,
old->pls_range.length);
if (old_end < new->pls_range.offset)
return false;
new_end = pnfs_calc_offset_end(new->pls_range.offset,
new->pls_range.length);
if (new_end < old->pls_range.offset)
return false;
/* Mergeable: copy info from 'old' to 'new' */
if (new_end < old_end)
new_end = old_end;
if (new->pls_range.offset < old->pls_range.offset)
new->pls_range.offset = old->pls_range.offset;
new->pls_range.length = pnfs_calc_offset_length(new->pls_range.offset,
new_end);
if (test_bit(NFS_LSEG_ROC, &old->pls_flags))
set_bit(NFS_LSEG_ROC, &new->pls_flags);
return true;
}
static void
ff_layout_add_lseg(struct pnfs_layout_hdr *lo,
struct pnfs_layout_segment *lseg,
struct list_head *free_me)
{
pnfs_generic_layout_insert_lseg(lo, lseg,
ff_lseg_range_is_after,
ff_lseg_merge,
free_me);
}
static void ff_layout_sort_mirrors(struct nfs4_ff_layout_segment *fls)
{
int i, j;
for (i = 0; i < fls->mirror_array_cnt - 1; i++) {
for (j = i + 1; j < fls->mirror_array_cnt; j++)
if (fls->mirror_array[i]->efficiency <
fls->mirror_array[j]->efficiency)
swap(fls->mirror_array[i],
fls->mirror_array[j]);
}
}
static struct pnfs_layout_segment *
ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
struct nfs4_layoutget_res *lgr,
gfp_t gfp_flags)
{
struct pnfs_layout_segment *ret;
struct nfs4_ff_layout_segment *fls = NULL;
struct xdr_stream stream;
struct xdr_buf buf;
struct page *scratch;
u64 stripe_unit;
u32 mirror_array_cnt;
__be32 *p;
int i, rc;
dprintk("--> %s\n", __func__);
scratch = alloc_page(gfp_flags);
if (!scratch)
return ERR_PTR(-ENOMEM);
xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages,
lgr->layoutp->len);
xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
/* stripe unit and mirror_array_cnt */
rc = -EIO;
p = xdr_inline_decode(&stream, 8 + 4);
if (!p)
goto out_err_free;
p = xdr_decode_hyper(p, &stripe_unit);
mirror_array_cnt = be32_to_cpup(p++);
dprintk("%s: stripe_unit=%llu mirror_array_cnt=%u\n", __func__,
stripe_unit, mirror_array_cnt);
if (mirror_array_cnt > NFS4_FLEXFILE_LAYOUT_MAX_MIRROR_CNT ||
mirror_array_cnt == 0)
goto out_err_free;
rc = -ENOMEM;
fls = kzalloc(sizeof(*fls), gfp_flags);
if (!fls)
goto out_err_free;
fls->mirror_array_cnt = mirror_array_cnt;
fls->stripe_unit = stripe_unit;
fls->mirror_array = kcalloc(fls->mirror_array_cnt,
sizeof(fls->mirror_array[0]), gfp_flags);
if (fls->mirror_array == NULL)
goto out_err_free;
for (i = 0; i < fls->mirror_array_cnt; i++) {
struct nfs4_ff_layout_mirror *mirror;
struct auth_cred acred = { .group_info = ff_zero_group };
struct rpc_cred __rcu *cred;
u32 ds_count, fh_count, id;
int j;
rc = -EIO;
p = xdr_inline_decode(&stream, 4);
if (!p)
goto out_err_free;
ds_count = be32_to_cpup(p);
/* FIXME: allow for striping? */
if (ds_count != 1)
goto out_err_free;
fls->mirror_array[i] = ff_layout_alloc_mirror(gfp_flags);
if (fls->mirror_array[i] == NULL) {
rc = -ENOMEM;
goto out_err_free;
}
fls->mirror_array[i]->ds_count = ds_count;
/* deviceid */
rc = decode_deviceid(&stream, &fls->mirror_array[i]->devid);
if (rc)
goto out_err_free;
/* efficiency */
rc = -EIO;
p = xdr_inline_decode(&stream, 4);
if (!p)
goto out_err_free;
fls->mirror_array[i]->efficiency = be32_to_cpup(p);
/* stateid */
rc = decode_pnfs_stateid(&stream, &fls->mirror_array[i]->stateid);
if (rc)
goto out_err_free;
/* fh */
rc = -EIO;
p = xdr_inline_decode(&stream, 4);
if (!p)
goto out_err_free;
fh_count = be32_to_cpup(p);
fls->mirror_array[i]->fh_versions =
kcalloc(fh_count, sizeof(struct nfs_fh),
gfp_flags);
if (fls->mirror_array[i]->fh_versions == NULL) {
rc = -ENOMEM;
goto out_err_free;
}
for (j = 0; j < fh_count; j++) {
rc = decode_nfs_fh(&stream,
&fls->mirror_array[i]->fh_versions[j]);
if (rc)
goto out_err_free;
}
fls->mirror_array[i]->fh_versions_cnt = fh_count;
/* user */
rc = decode_name(&stream, &id);
if (rc)
goto out_err_free;
acred.uid = make_kuid(&init_user_ns, id);
/* group */
rc = decode_name(&stream, &id);
if (rc)
goto out_err_free;
acred.gid = make_kgid(&init_user_ns, id);
/* find the cred for it */
rcu_assign_pointer(cred, rpc_lookup_generic_cred(&acred, 0, gfp_flags));
if (IS_ERR(cred)) {
rc = PTR_ERR(cred);
goto out_err_free;
}
if (lgr->range.iomode == IOMODE_READ)
rcu_assign_pointer(fls->mirror_array[i]->ro_cred, cred);
else
rcu_assign_pointer(fls->mirror_array[i]->rw_cred, cred);
mirror = ff_layout_add_mirror(lh, fls->mirror_array[i]);
if (mirror != fls->mirror_array[i]) {
/* swap cred ptrs so free_mirror will clean up old */
if (lgr->range.iomode == IOMODE_READ) {
cred = xchg(&mirror->ro_cred, cred);
rcu_assign_pointer(fls->mirror_array[i]->ro_cred, cred);
} else {
cred = xchg(&mirror->rw_cred, cred);
rcu_assign_pointer(fls->mirror_array[i]->rw_cred, cred);
}
ff_layout_free_mirror(fls->mirror_array[i]);
fls->mirror_array[i] = mirror;
}
dprintk("%s: iomode %s uid %u gid %u\n", __func__,
lgr->range.iomode == IOMODE_READ ? "READ" : "RW",
from_kuid(&init_user_ns, acred.uid),
from_kgid(&init_user_ns, acred.gid));
}
p = xdr_inline_decode(&stream, 4);
if (!p)
goto out_sort_mirrors;
fls->flags = be32_to_cpup(p);
p = xdr_inline_decode(&stream, 4);
if (!p)
goto out_sort_mirrors;
for (i=0; i < fls->mirror_array_cnt; i++)
fls->mirror_array[i]->report_interval = be32_to_cpup(p);
out_sort_mirrors:
ff_layout_sort_mirrors(fls);
rc = ff_layout_check_layout(lgr);
if (rc)
goto out_err_free;
ret = &fls->generic_hdr;
dprintk("<-- %s (success)\n", __func__);
out_free_page:
__free_page(scratch);
return ret;
out_err_free:
_ff_layout_free_lseg(fls);
ret = ERR_PTR(rc);
dprintk("<-- %s (%d)\n", __func__, rc);
goto out_free_page;
}
static bool ff_layout_has_rw_segments(struct pnfs_layout_hdr *layout)
{
struct pnfs_layout_segment *lseg;
list_for_each_entry(lseg, &layout->plh_segs, pls_list)
if (lseg->pls_range.iomode == IOMODE_RW)
return true;
return false;
}
static void
ff_layout_free_lseg(struct pnfs_layout_segment *lseg)
{
struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
dprintk("--> %s\n", __func__);
if (lseg->pls_range.iomode == IOMODE_RW) {
struct nfs4_flexfile_layout *ffl;
struct inode *inode;
ffl = FF_LAYOUT_FROM_HDR(lseg->pls_layout);
inode = ffl->generic_hdr.plh_inode;
spin_lock(&inode->i_lock);
if (!ff_layout_has_rw_segments(lseg->pls_layout)) {
ffl->commit_info.nbuckets = 0;
kfree(ffl->commit_info.buckets);
ffl->commit_info.buckets = NULL;
}
spin_unlock(&inode->i_lock);
}
_ff_layout_free_lseg(fls);
}
/* Return 1 until we have multiple lsegs support */
static int
ff_layout_get_lseg_count(struct nfs4_ff_layout_segment *fls)
{
return 1;
}
static void
nfs4_ff_start_busy_timer(struct nfs4_ff_busy_timer *timer, ktime_t now)
{
/* first IO request? */
if (atomic_inc_return(&timer->n_ops) == 1) {
timer->start_time = now;
}
}
static ktime_t
nfs4_ff_end_busy_timer(struct nfs4_ff_busy_timer *timer, ktime_t now)
{
ktime_t start;
if (atomic_dec_return(&timer->n_ops) < 0)
WARN_ON_ONCE(1);
start = timer->start_time;
timer->start_time = now;
return ktime_sub(now, start);
}
static bool
nfs4_ff_layoutstat_start_io(struct nfs4_ff_layout_mirror *mirror,
struct nfs4_ff_layoutstat *layoutstat,
ktime_t now)
{
s64 report_interval = FF_LAYOUTSTATS_REPORT_INTERVAL;
struct nfs4_flexfile_layout *ffl = FF_LAYOUT_FROM_HDR(mirror->layout);
nfs4_ff_start_busy_timer(&layoutstat->busy_timer, now);
if (!mirror->start_time)
mirror->start_time = now;
if (mirror->report_interval != 0)
report_interval = (s64)mirror->report_interval * 1000LL;
else if (layoutstats_timer != 0)
report_interval = (s64)layoutstats_timer * 1000LL;
if (ktime_to_ms(ktime_sub(now, ffl->last_report_time)) >=
report_interval) {
ffl->last_report_time = now;
return true;
}
return false;
}
static void
nfs4_ff_layout_stat_io_update_requested(struct nfs4_ff_layoutstat *layoutstat,
__u64 requested)
{
struct nfs4_ff_io_stat *iostat = &layoutstat->io_stat;
iostat->ops_requested++;
iostat->bytes_requested += requested;
}
static void
nfs4_ff_layout_stat_io_update_completed(struct nfs4_ff_layoutstat *layoutstat,
__u64 requested,
__u64 completed,
ktime_t time_completed,
ktime_t time_started)
{
struct nfs4_ff_io_stat *iostat = &layoutstat->io_stat;
ktime_t completion_time = ktime_sub(time_completed, time_started);
ktime_t timer;
iostat->ops_completed++;
iostat->bytes_completed += completed;
iostat->bytes_not_delivered += requested - completed;
timer = nfs4_ff_end_busy_timer(&layoutstat->busy_timer, time_completed);
iostat->total_busy_time =
ktime_add(iostat->total_busy_time, timer);
iostat->aggregate_completion_time =
ktime_add(iostat->aggregate_completion_time,
completion_time);
}
static void
nfs4_ff_layout_stat_io_start_read(struct inode *inode,
struct nfs4_ff_layout_mirror *mirror,
__u64 requested, ktime_t now)
{
bool report;
spin_lock(&mirror->lock);
report = nfs4_ff_layoutstat_start_io(mirror, &mirror->read_stat, now);
nfs4_ff_layout_stat_io_update_requested(&mirror->read_stat, requested);
set_bit(NFS4_FF_MIRROR_STAT_AVAIL, &mirror->flags);
spin_unlock(&mirror->lock);
if (report)
pnfs_report_layoutstat(inode, GFP_KERNEL);
}
static void
nfs4_ff_layout_stat_io_end_read(struct rpc_task *task,
struct nfs4_ff_layout_mirror *mirror,
__u64 requested,
__u64 completed)
{
spin_lock(&mirror->lock);
nfs4_ff_layout_stat_io_update_completed(&mirror->read_stat,
requested, completed,
ktime_get(), task->tk_start);
set_bit(NFS4_FF_MIRROR_STAT_AVAIL, &mirror->flags);
spin_unlock(&mirror->lock);
}
static void
nfs4_ff_layout_stat_io_start_write(struct inode *inode,
struct nfs4_ff_layout_mirror *mirror,
__u64 requested, ktime_t now)
{
bool report;
spin_lock(&mirror->lock);
report = nfs4_ff_layoutstat_start_io(mirror , &mirror->write_stat, now);
nfs4_ff_layout_stat_io_update_requested(&mirror->write_stat, requested);
set_bit(NFS4_FF_MIRROR_STAT_AVAIL, &mirror->flags);
spin_unlock(&mirror->lock);
if (report)
pnfs_report_layoutstat(inode, GFP_NOIO);
}
static void
nfs4_ff_layout_stat_io_end_write(struct rpc_task *task,
struct nfs4_ff_layout_mirror *mirror,
__u64 requested,
__u64 completed,
enum nfs3_stable_how committed)
{
if (committed == NFS_UNSTABLE)
requested = completed = 0;
spin_lock(&mirror->lock);
nfs4_ff_layout_stat_io_update_completed(&mirror->write_stat,
requested, completed, ktime_get(), task->tk_start);
set_bit(NFS4_FF_MIRROR_STAT_AVAIL, &mirror->flags);
spin_unlock(&mirror->lock);
}
static int
ff_layout_alloc_commit_info(struct pnfs_layout_segment *lseg,
struct nfs_commit_info *cinfo,
gfp_t gfp_flags)
{
struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
struct pnfs_commit_bucket *buckets;
int size;
if (cinfo->ds->nbuckets != 0) {
/* This assumes there is only one RW lseg per file.
* To support multiple lseg per file, we need to
* change struct pnfs_commit_bucket to allow dynamic
* increasing nbuckets.
*/
return 0;
}
size = ff_layout_get_lseg_count(fls) * FF_LAYOUT_MIRROR_COUNT(lseg);
buckets = kcalloc(size, sizeof(struct pnfs_commit_bucket),
gfp_flags);
if (!buckets)
return -ENOMEM;
else {
int i;
spin_lock(&cinfo->inode->i_lock);
if (cinfo->ds->nbuckets != 0)
kfree(buckets);
else {
cinfo->ds->buckets = buckets;
cinfo->ds->nbuckets = size;
for (i = 0; i < size; i++) {
INIT_LIST_HEAD(&buckets[i].written);
INIT_LIST_HEAD(&buckets[i].committing);
/* mark direct verifier as unset */
buckets[i].direct_verf.committed =
NFS_INVALID_STABLE_HOW;
}
}
spin_unlock(&cinfo->inode->i_lock);
return 0;
}
}
static struct nfs4_pnfs_ds *
ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
int start_idx,
int *best_idx)
{
struct nfs4_ff_layout_segment *fls = FF_LAYOUT_LSEG(lseg);
struct nfs4_pnfs_ds *ds;
bool fail_return = false;
int idx;
/* mirrors are sorted by efficiency */
for (idx = start_idx; idx < fls->mirror_array_cnt; idx++) {
if (idx+1 == fls->mirror_array_cnt)
fail_return = true;
ds = nfs4_ff_layout_prepare_ds(lseg, idx, fail_return);
if (ds) {
*best_idx = idx;
return ds;
}
}
return NULL;
}
static void
ff_layout_pg_get_read(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req,
bool strict_iomode)
{
retry_strict:
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
req->wb_context,
0,
NFS4_MAX_UINT64,
IOMODE_READ,
strict_iomode,
GFP_KERNEL);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
pgio->pg_lseg = NULL;
}
/* If we don't have checking, do get a IOMODE_RW
* segment, and the server wants to avoid READs
* there, then retry!
*/
if (pgio->pg_lseg && !strict_iomode &&
ff_layout_avoid_read_on_rw(pgio->pg_lseg)) {
strict_iomode = true;
goto retry_strict;
}
}
static void
ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req)
{
struct nfs_pgio_mirror *pgm;
struct nfs4_ff_layout_mirror *mirror;
struct nfs4_pnfs_ds *ds;
int ds_idx;
retry:
pnfs_generic_pg_check_layout(pgio);
/* Use full layout for now */
if (!pgio->pg_lseg)
ff_layout_pg_get_read(pgio, req, false);
else if (ff_layout_avoid_read_on_rw(pgio->pg_lseg))
ff_layout_pg_get_read(pgio, req, true);
/* If no lseg, fall back to read through mds */
if (pgio->pg_lseg == NULL)
goto out_mds;
ds = ff_layout_choose_best_ds_for_read(pgio->pg_lseg, 0, &ds_idx);
if (!ds) {
if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
goto out_mds;
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
/* Sleep for 1 second before retrying */
ssleep(1);
goto retry;
}
mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx);
pgio->pg_mirror_idx = ds_idx;
/* read always uses only one mirror - idx 0 for pgio layer */
pgm = &pgio->pg_mirrors[0];
pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize;
return;
out_mds:
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
nfs_pageio_reset_read_mds(pgio);
}
static void
ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req)
{
struct nfs4_ff_layout_mirror *mirror;
struct nfs_pgio_mirror *pgm;
struct nfs_commit_info cinfo;
struct nfs4_pnfs_ds *ds;
int i;
int status;
retry:
pnfs_generic_pg_check_layout(pgio);
if (!pgio->pg_lseg) {
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
req->wb_context,
0,
NFS4_MAX_UINT64,
IOMODE_RW,
false,
GFP_NOFS);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
pgio->pg_lseg = NULL;
return;
}
}
/* If no lseg, fall back to write through mds */
if (pgio->pg_lseg == NULL)
goto out_mds;
nfs_init_cinfo(&cinfo, pgio->pg_inode, pgio->pg_dreq);
status = ff_layout_alloc_commit_info(pgio->pg_lseg, &cinfo, GFP_NOFS);
if (status < 0)
goto out_mds;
/* Use a direct mapping of ds_idx to pgio mirror_idx */
if (WARN_ON_ONCE(pgio->pg_mirror_count !=
FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg)))
goto out_mds;
for (i = 0; i < pgio->pg_mirror_count; i++) {
ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, i, true);
if (!ds) {
if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg))
goto out_mds;
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
/* Sleep for 1 second before retrying */
ssleep(1);
goto retry;
}
pgm = &pgio->pg_mirrors[i];
mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].wsize;
}
return;
out_mds:
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
nfs_pageio_reset_write_mds(pgio);
}
static unsigned int
ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req)
{
if (!pgio->pg_lseg) {
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
req->wb_context,
0,
NFS4_MAX_UINT64,
IOMODE_RW,
false,
GFP_NOFS);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
pgio->pg_lseg = NULL;
goto out;
}
}
if (pgio->pg_lseg)
return FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg);
/* no lseg means that pnfs is not in use, so no mirroring here */
nfs_pageio_reset_write_mds(pgio);
out:
return 1;
}
static const struct nfs_pageio_ops ff_layout_pg_read_ops = {
.pg_init = ff_layout_pg_init_read,
.pg_test = pnfs_generic_pg_test,
.pg_doio = pnfs_generic_pg_readpages,
.pg_cleanup = pnfs_generic_pg_cleanup,
};
static const struct nfs_pageio_ops ff_layout_pg_write_ops = {
.pg_init = ff_layout_pg_init_write,
.pg_test = pnfs_generic_pg_test,
.pg_doio = pnfs_generic_pg_writepages,
.pg_get_mirror_count = ff_layout_pg_get_mirror_count_write,
.pg_cleanup = pnfs_generic_pg_cleanup,
};
static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs)
{
struct rpc_task *task = &hdr->task;
pnfs_layoutcommit_inode(hdr->inode, false);
if (retry_pnfs) {