forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
ore.c
1164 lines (997 loc) · 30.1 KB
/
ore.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) 2005, 2006
* Avishay Traeger ([email protected])
* Copyright (C) 2008, 2009
* Boaz Harrosh <[email protected]>
*
* This file is part of exofs.
*
* exofs is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation. Since it is based on ext2, and the only
* valid version of GPL for the Linux kernel is version 2, the only valid
* version of GPL for exofs is version 2.
*
* exofs is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with exofs; if not, write to the Free Software
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include <linux/slab.h>
#include <linux/module.h>
#include <asm/div64.h>
#include <linux/lcm.h>
#include "ore_raid.h"
MODULE_AUTHOR("Boaz Harrosh <[email protected]>");
MODULE_DESCRIPTION("Objects Raid Engine ore.ko");
MODULE_LICENSE("GPL");
/* ore_verify_layout does a couple of things:
* 1. Given a minimum number of needed parameters fixes up the rest of the
* members to be operatonals for the ore. The needed parameters are those
* that are defined by the pnfs-objects layout STD.
* 2. Check to see if the current ore code actually supports these parameters
* for example stripe_unit must be a multple of the system PAGE_SIZE,
* and etc...
* 3. Cache some havily used calculations that will be needed by users.
*/
enum { BIO_MAX_PAGES_KMALLOC =
(PAGE_SIZE - sizeof(struct bio)) / sizeof(struct bio_vec),};
int ore_verify_layout(unsigned total_comps, struct ore_layout *layout)
{
u64 stripe_length;
switch (layout->raid_algorithm) {
case PNFS_OSD_RAID_0:
layout->parity = 0;
break;
case PNFS_OSD_RAID_5:
layout->parity = 1;
break;
case PNFS_OSD_RAID_PQ:
layout->parity = 2;
break;
case PNFS_OSD_RAID_4:
default:
ORE_ERR("Only RAID_0/5/6 for now received-enum=%d\n",
layout->raid_algorithm);
return -EINVAL;
}
if (0 != (layout->stripe_unit & ~PAGE_MASK)) {
ORE_ERR("Stripe Unit(0x%llx)"
" must be Multples of PAGE_SIZE(0x%lx)\n",
_LLU(layout->stripe_unit), PAGE_SIZE);
return -EINVAL;
}
if (layout->group_width) {
if (!layout->group_depth) {
ORE_ERR("group_depth == 0 && group_width != 0\n");
return -EINVAL;
}
if (total_comps < (layout->group_width * layout->mirrors_p1)) {
ORE_ERR("Data Map wrong, "
"numdevs=%d < group_width=%d * mirrors=%d\n",
total_comps, layout->group_width,
layout->mirrors_p1);
return -EINVAL;
}
layout->group_count = total_comps / layout->mirrors_p1 /
layout->group_width;
} else {
if (layout->group_depth) {
printk(KERN_NOTICE "Warning: group_depth ignored "
"group_width == 0 && group_depth == %lld\n",
_LLU(layout->group_depth));
}
layout->group_width = total_comps / layout->mirrors_p1;
layout->group_depth = -1;
layout->group_count = 1;
}
stripe_length = (u64)layout->group_width * layout->stripe_unit;
if (stripe_length >= (1ULL << 32)) {
ORE_ERR("Stripe_length(0x%llx) >= 32bit is not supported\n",
_LLU(stripe_length));
return -EINVAL;
}
layout->max_io_length =
(BIO_MAX_PAGES_KMALLOC * PAGE_SIZE - layout->stripe_unit) *
(layout->group_width - layout->parity);
if (layout->parity) {
unsigned stripe_length =
(layout->group_width - layout->parity) *
layout->stripe_unit;
layout->max_io_length /= stripe_length;
layout->max_io_length *= stripe_length;
}
ORE_DBGMSG("max_io_length=0x%lx\n", layout->max_io_length);
return 0;
}
EXPORT_SYMBOL(ore_verify_layout);
static u8 *_ios_cred(struct ore_io_state *ios, unsigned index)
{
return ios->oc->comps[index & ios->oc->single_comp].cred;
}
static struct osd_obj_id *_ios_obj(struct ore_io_state *ios, unsigned index)
{
return &ios->oc->comps[index & ios->oc->single_comp].obj;
}
static struct osd_dev *_ios_od(struct ore_io_state *ios, unsigned index)
{
ORE_DBGMSG2("oc->first_dev=%d oc->numdevs=%d i=%d oc->ods=%p\n",
ios->oc->first_dev, ios->oc->numdevs, index,
ios->oc->ods);
return ore_comp_dev(ios->oc, index);
}
int _ore_get_io_state(struct ore_layout *layout,
struct ore_components *oc, unsigned numdevs,
unsigned sgs_per_dev, unsigned num_par_pages,
struct ore_io_state **pios)
{
struct ore_io_state *ios;
struct page **pages;
struct osd_sg_entry *sgilist;
struct __alloc_all_io_state {
struct ore_io_state ios;
struct ore_per_dev_state per_dev[numdevs];
union {
struct osd_sg_entry sglist[sgs_per_dev * numdevs];
struct page *pages[num_par_pages];
};
} *_aios;
if (likely(sizeof(*_aios) <= PAGE_SIZE)) {
_aios = kzalloc(sizeof(*_aios), GFP_KERNEL);
if (unlikely(!_aios)) {
ORE_DBGMSG("Failed kzalloc bytes=%zd\n",
sizeof(*_aios));
*pios = NULL;
return -ENOMEM;
}
pages = num_par_pages ? _aios->pages : NULL;
sgilist = sgs_per_dev ? _aios->sglist : NULL;
ios = &_aios->ios;
} else {
struct __alloc_small_io_state {
struct ore_io_state ios;
struct ore_per_dev_state per_dev[numdevs];
} *_aio_small;
union __extra_part {
struct osd_sg_entry sglist[sgs_per_dev * numdevs];
struct page *pages[num_par_pages];
} *extra_part;
_aio_small = kzalloc(sizeof(*_aio_small), GFP_KERNEL);
if (unlikely(!_aio_small)) {
ORE_DBGMSG("Failed alloc first part bytes=%zd\n",
sizeof(*_aio_small));
*pios = NULL;
return -ENOMEM;
}
extra_part = kzalloc(sizeof(*extra_part), GFP_KERNEL);
if (unlikely(!extra_part)) {
ORE_DBGMSG("Failed alloc second part bytes=%zd\n",
sizeof(*extra_part));
kfree(_aio_small);
*pios = NULL;
return -ENOMEM;
}
pages = num_par_pages ? extra_part->pages : NULL;
sgilist = sgs_per_dev ? extra_part->sglist : NULL;
/* In this case the per_dev[0].sgilist holds the pointer to
* be freed
*/
ios = &_aio_small->ios;
ios->extra_part_alloc = true;
}
if (pages) {
ios->parity_pages = pages;
ios->max_par_pages = num_par_pages;
}
if (sgilist) {
unsigned d;
for (d = 0; d < numdevs; ++d) {
ios->per_dev[d].sglist = sgilist;
sgilist += sgs_per_dev;
}
ios->sgs_per_dev = sgs_per_dev;
}
ios->layout = layout;
ios->oc = oc;
*pios = ios;
return 0;
}
/* Allocate an io_state for only a single group of devices
*
* If a user needs to call ore_read/write() this version must be used becase it
* allocates extra stuff for striping and raid.
* The ore might decide to only IO less then @length bytes do to alignmets
* and constrains as follows:
* - The IO cannot cross group boundary.
* - In raid5/6 The end of the IO must align at end of a stripe eg.
* (@offset + @length) % strip_size == 0. Or the complete range is within a
* single stripe.
* - Memory condition only permitted a shorter IO. (A user can use @length=~0
* And check the returned ios->length for max_io_size.)
*
* The caller must check returned ios->length (and/or ios->nr_pages) and
* re-issue these pages that fall outside of ios->length
*/
int ore_get_rw_state(struct ore_layout *layout, struct ore_components *oc,
bool is_reading, u64 offset, u64 length,
struct ore_io_state **pios)
{
struct ore_io_state *ios;
unsigned numdevs = layout->group_width * layout->mirrors_p1;
unsigned sgs_per_dev = 0, max_par_pages = 0;
int ret;
if (layout->parity && length) {
unsigned data_devs = layout->group_width - layout->parity;
unsigned stripe_size = layout->stripe_unit * data_devs;
unsigned pages_in_unit = layout->stripe_unit / PAGE_SIZE;
u32 remainder;
u64 num_stripes;
u64 num_raid_units;
num_stripes = div_u64_rem(length, stripe_size, &remainder);
if (remainder)
++num_stripes;
num_raid_units = num_stripes * layout->parity;
if (is_reading) {
/* For reads add per_dev sglist array */
/* TODO: Raid 6 we need twice more. Actually:
* num_stripes / LCMdP(W,P);
* if (W%P != 0) num_stripes *= parity;
*/
/* first/last seg is split */
num_raid_units += layout->group_width;
sgs_per_dev = div_u64(num_raid_units, data_devs) + 2;
} else {
/* For Writes add parity pages array. */
max_par_pages = num_raid_units * pages_in_unit *
sizeof(struct page *);
}
}
ret = _ore_get_io_state(layout, oc, numdevs, sgs_per_dev, max_par_pages,
pios);
if (unlikely(ret))
return ret;
ios = *pios;
ios->reading = is_reading;
ios->offset = offset;
if (length) {
ore_calc_stripe_info(layout, offset, length, &ios->si);
ios->length = ios->si.length;
ios->nr_pages = ((ios->offset & (PAGE_SIZE - 1)) +
ios->length + PAGE_SIZE - 1) / PAGE_SIZE;
if (layout->parity)
_ore_post_alloc_raid_stuff(ios);
}
return 0;
}
EXPORT_SYMBOL(ore_get_rw_state);
/* Allocate an io_state for all the devices in the comps array
*
* This version of io_state allocation is used mostly by create/remove
* and trunc where we currently need all the devices. The only wastful
* bit is the read/write_attributes with no IO. Those sites should
* be converted to use ore_get_rw_state() with length=0
*/
int ore_get_io_state(struct ore_layout *layout, struct ore_components *oc,
struct ore_io_state **pios)
{
return _ore_get_io_state(layout, oc, oc->numdevs, 0, 0, pios);
}
EXPORT_SYMBOL(ore_get_io_state);
void ore_put_io_state(struct ore_io_state *ios)
{
if (ios) {
unsigned i;
for (i = 0; i < ios->numdevs; i++) {
struct ore_per_dev_state *per_dev = &ios->per_dev[i];
if (per_dev->or)
osd_end_request(per_dev->or);
if (per_dev->bio)
bio_put(per_dev->bio);
}
_ore_free_raid_stuff(ios);
kfree(ios);
}
}
EXPORT_SYMBOL(ore_put_io_state);
static void _sync_done(struct ore_io_state *ios, void *p)
{
struct completion *waiting = p;
complete(waiting);
}
static void _last_io(struct kref *kref)
{
struct ore_io_state *ios = container_of(
kref, struct ore_io_state, kref);
ios->done(ios, ios->private);
}
static void _done_io(struct osd_request *or, void *p)
{
struct ore_io_state *ios = p;
kref_put(&ios->kref, _last_io);
}
int ore_io_execute(struct ore_io_state *ios)
{
DECLARE_COMPLETION_ONSTACK(wait);
bool sync = (ios->done == NULL);
int i, ret;
if (sync) {
ios->done = _sync_done;
ios->private = &wait;
}
for (i = 0; i < ios->numdevs; i++) {
struct osd_request *or = ios->per_dev[i].or;
if (unlikely(!or))
continue;
ret = osd_finalize_request(or, 0, _ios_cred(ios, i), NULL);
if (unlikely(ret)) {
ORE_DBGMSG("Failed to osd_finalize_request() => %d\n",
ret);
return ret;
}
}
kref_init(&ios->kref);
for (i = 0; i < ios->numdevs; i++) {
struct osd_request *or = ios->per_dev[i].or;
if (unlikely(!or))
continue;
kref_get(&ios->kref);
osd_execute_request_async(or, _done_io, ios);
}
kref_put(&ios->kref, _last_io);
ret = 0;
if (sync) {
wait_for_completion(&wait);
ret = ore_check_io(ios, NULL);
}
return ret;
}
static void _clear_bio(struct bio *bio)
{
struct bio_vec *bv;
unsigned i;
bio_for_each_segment_all(bv, bio, i) {
unsigned this_count = bv->bv_len;
if (likely(PAGE_SIZE == this_count))
clear_highpage(bv->bv_page);
else
zero_user(bv->bv_page, bv->bv_offset, this_count);
}
}
int ore_check_io(struct ore_io_state *ios, ore_on_dev_error on_dev_error)
{
enum osd_err_priority acumulated_osd_err = 0;
int acumulated_lin_err = 0;
int i;
for (i = 0; i < ios->numdevs; i++) {
struct osd_sense_info osi;
struct ore_per_dev_state *per_dev = &ios->per_dev[i];
struct osd_request *or = per_dev->or;
int ret;
if (unlikely(!or))
continue;
ret = osd_req_decode_sense(or, &osi);
if (likely(!ret))
continue;
if ((OSD_ERR_PRI_CLEAR_PAGES == osi.osd_err_pri) &&
per_dev->bio) {
/* start read offset passed endof file.
* Note: if we do not have bio it means read-attributes
* In this case we should return error to caller.
*/
_clear_bio(per_dev->bio);
ORE_DBGMSG("start read offset passed end of file "
"offset=0x%llx, length=0x%llx\n",
_LLU(per_dev->offset),
_LLU(per_dev->length));
continue; /* we recovered */
}
if (on_dev_error) {
u64 residual = ios->reading ?
or->in.residual : or->out.residual;
u64 offset = (ios->offset + ios->length) - residual;
unsigned dev = per_dev->dev - ios->oc->first_dev;
struct ore_dev *od = ios->oc->ods[dev];
on_dev_error(ios, od, dev, osi.osd_err_pri,
offset, residual);
}
if (osi.osd_err_pri >= acumulated_osd_err) {
acumulated_osd_err = osi.osd_err_pri;
acumulated_lin_err = ret;
}
}
return acumulated_lin_err;
}
EXPORT_SYMBOL(ore_check_io);
/*
* L - logical offset into the file
*
* D - number of Data devices
* D = group_width - parity
*
* U - The number of bytes in a stripe within a group
* U = stripe_unit * D
*
* T - The number of bytes striped within a group of component objects
* (before advancing to the next group)
* T = U * group_depth
*
* S - The number of bytes striped across all component objects
* before the pattern repeats
* S = T * group_count
*
* M - The "major" (i.e., across all components) cycle number
* M = L / S
*
* G - Counts the groups from the beginning of the major cycle
* G = (L - (M * S)) / T [or (L % S) / T]
*
* H - The byte offset within the group
* H = (L - (M * S)) % T [or (L % S) % T]
*
* N - The "minor" (i.e., across the group) stripe number
* N = H / U
*
* C - The component index coresponding to L
*
* C = (H - (N * U)) / stripe_unit + G * D
* [or (L % U) / stripe_unit + G * D]
*
* O - The component offset coresponding to L
* O = L % stripe_unit + N * stripe_unit + M * group_depth * stripe_unit
*
* LCMdP – Parity cycle: Lowest Common Multiple of group_width, parity
* divide by parity
* LCMdP = lcm(group_width, parity) / parity
*
* R - The parity Rotation stripe
* (Note parity cycle always starts at a group's boundary)
* R = N % LCMdP
*
* I = the first parity device index
* I = (group_width + group_width - R*parity - parity) % group_width
*
* Craid - The component index Rotated
* Craid = (group_width + C - R*parity) % group_width
* (We add the group_width to avoid negative numbers modulo math)
*/
void ore_calc_stripe_info(struct ore_layout *layout, u64 file_offset,
u64 length, struct ore_striping_info *si)
{
u32 stripe_unit = layout->stripe_unit;
u32 group_width = layout->group_width;
u64 group_depth = layout->group_depth;
u32 parity = layout->parity;
u32 D = group_width - parity;
u32 U = D * stripe_unit;
u64 T = U * group_depth;
u64 S = T * layout->group_count;
u64 M = div64_u64(file_offset, S);
/*
G = (L - (M * S)) / T
H = (L - (M * S)) % T
*/
u64 LmodS = file_offset - M * S;
u32 G = div64_u64(LmodS, T);
u64 H = LmodS - G * T;
u32 N = div_u64(H, U);
u32 Nlast;
/* "H - (N * U)" is just "H % U" so it's bound to u32 */
u32 C = (u32)(H - (N * U)) / stripe_unit + G * group_width;
u32 first_dev = C - C % group_width;
div_u64_rem(file_offset, stripe_unit, &si->unit_off);
si->obj_offset = si->unit_off + (N * stripe_unit) +
(M * group_depth * stripe_unit);
si->cur_comp = C - first_dev;
si->cur_pg = si->unit_off / PAGE_SIZE;
if (parity) {
u32 LCMdP = lcm(group_width, parity) / parity;
/* R = N % LCMdP; */
u32 RxP = (N % LCMdP) * parity;
si->par_dev = (group_width + group_width - parity - RxP) %
group_width + first_dev;
si->dev = (group_width + group_width + C - RxP) %
group_width + first_dev;
si->bytes_in_stripe = U;
si->first_stripe_start = M * S + G * T + N * U;
} else {
/* Make the math correct see _prepare_one_group */
si->par_dev = group_width;
si->dev = C;
}
si->dev *= layout->mirrors_p1;
si->par_dev *= layout->mirrors_p1;
si->offset = file_offset;
si->length = T - H;
if (si->length > length)
si->length = length;
Nlast = div_u64(H + si->length + U - 1, U);
si->maxdevUnits = Nlast - N;
si->M = M;
}
EXPORT_SYMBOL(ore_calc_stripe_info);
int _ore_add_stripe_unit(struct ore_io_state *ios, unsigned *cur_pg,
unsigned pgbase, struct page **pages,
struct ore_per_dev_state *per_dev, int cur_len)
{
unsigned pg = *cur_pg;
struct request_queue *q =
osd_request_queue(_ios_od(ios, per_dev->dev));
unsigned len = cur_len;
int ret;
if (per_dev->bio == NULL) {
unsigned bio_size;
if (!ios->reading) {
bio_size = ios->si.maxdevUnits;
} else {
bio_size = (ios->si.maxdevUnits + 1) *
(ios->layout->group_width - ios->layout->parity) /
ios->layout->group_width;
}
bio_size *= (ios->layout->stripe_unit / PAGE_SIZE);
per_dev->bio = bio_kmalloc(GFP_KERNEL, bio_size);
if (unlikely(!per_dev->bio)) {
ORE_DBGMSG("Failed to allocate BIO size=%u\n",
bio_size);
ret = -ENOMEM;
goto out;
}
}
while (cur_len > 0) {
unsigned pglen = min_t(unsigned, PAGE_SIZE - pgbase, cur_len);
unsigned added_len;
cur_len -= pglen;
added_len = bio_add_pc_page(q, per_dev->bio, pages[pg],
pglen, pgbase);
if (unlikely(pglen != added_len)) {
/* If bi_vcnt == bi_max then this is a SW BUG */
ORE_DBGMSG("Failed bio_add_pc_page bi_vcnt=0x%x "
"bi_max=0x%x BIO_MAX=0x%x cur_len=0x%x\n",
per_dev->bio->bi_vcnt,
per_dev->bio->bi_max_vecs,
BIO_MAX_PAGES_KMALLOC, cur_len);
ret = -ENOMEM;
goto out;
}
_add_stripe_page(ios->sp2d, &ios->si, pages[pg]);
pgbase = 0;
++pg;
}
BUG_ON(cur_len);
per_dev->length += len;
*cur_pg = pg;
ret = 0;
out: /* we fail the complete unit on an error eg don't advance
* per_dev->length and cur_pg. This means that we might have a bigger
* bio than the CDB requested length (per_dev->length). That's fine
* only the oposite is fatal.
*/
return ret;
}
static int _add_parity_units(struct ore_io_state *ios,
struct ore_striping_info *si,
unsigned dev, unsigned first_dev,
unsigned mirrors_p1, unsigned devs_in_group,
unsigned cur_len)
{
unsigned do_parity;
int ret = 0;
for (do_parity = ios->layout->parity; do_parity; --do_parity) {
struct ore_per_dev_state *per_dev;
per_dev = &ios->per_dev[dev - first_dev];
if (!per_dev->length && !per_dev->offset) {
/* Only/always the parity unit of the first
* stripe will be empty. So this is a chance to
* initialize the per_dev info.
*/
per_dev->dev = dev;
per_dev->offset = si->obj_offset - si->unit_off;
}
ret = _ore_add_parity_unit(ios, si, per_dev, cur_len,
do_parity == 1);
if (unlikely(ret))
break;
if (do_parity != 1) {
dev = ((dev + mirrors_p1) % devs_in_group) + first_dev;
si->cur_comp = (si->cur_comp + 1) %
ios->layout->group_width;
}
}
return ret;
}
static int _prepare_for_striping(struct ore_io_state *ios)
{
struct ore_striping_info *si = &ios->si;
unsigned stripe_unit = ios->layout->stripe_unit;
unsigned mirrors_p1 = ios->layout->mirrors_p1;
unsigned group_width = ios->layout->group_width;
unsigned devs_in_group = group_width * mirrors_p1;
unsigned dev = si->dev;
unsigned first_dev = dev - (dev % devs_in_group);
unsigned cur_pg = ios->pages_consumed;
u64 length = ios->length;
int ret = 0;
if (!ios->pages) {
ios->numdevs = ios->layout->mirrors_p1;
return 0;
}
BUG_ON(length > si->length);
while (length) {
struct ore_per_dev_state *per_dev =
&ios->per_dev[dev - first_dev];
unsigned cur_len, page_off = 0;
if (!per_dev->length && !per_dev->offset) {
/* First time initialize the per_dev info. */
per_dev->dev = dev;
if (dev == si->dev) {
WARN_ON(dev == si->par_dev);
per_dev->offset = si->obj_offset;
cur_len = stripe_unit - si->unit_off;
page_off = si->unit_off & ~PAGE_MASK;
BUG_ON(page_off && (page_off != ios->pgbase));
} else {
per_dev->offset = si->obj_offset - si->unit_off;
cur_len = stripe_unit;
}
} else {
cur_len = stripe_unit;
}
if (cur_len >= length)
cur_len = length;
ret = _ore_add_stripe_unit(ios, &cur_pg, page_off, ios->pages,
per_dev, cur_len);
if (unlikely(ret))
goto out;
length -= cur_len;
dev = ((dev + mirrors_p1) % devs_in_group) + first_dev;
si->cur_comp = (si->cur_comp + 1) % group_width;
if (unlikely((dev == si->par_dev) || (!length && ios->sp2d))) {
if (!length && ios->sp2d) {
/* If we are writing and this is the very last
* stripe. then operate on parity dev.
*/
dev = si->par_dev;
/* If last stripe operate on parity comp */
si->cur_comp = group_width - ios->layout->parity;
}
/* In writes cur_len just means if it's the
* last one. See _ore_add_parity_unit.
*/
ret = _add_parity_units(ios, si, dev, first_dev,
mirrors_p1, devs_in_group,
ios->sp2d ? length : cur_len);
if (unlikely(ret))
goto out;
/* Rotate next par_dev backwards with wraping */
si->par_dev = (devs_in_group + si->par_dev -
ios->layout->parity * mirrors_p1) %
devs_in_group + first_dev;
/* Next stripe, start fresh */
si->cur_comp = 0;
si->cur_pg = 0;
si->obj_offset += cur_len;
si->unit_off = 0;
}
}
out:
ios->numdevs = devs_in_group;
ios->pages_consumed = cur_pg;
return ret;
}
int ore_create(struct ore_io_state *ios)
{
int i, ret;
for (i = 0; i < ios->oc->numdevs; i++) {
struct osd_request *or;
or = osd_start_request(_ios_od(ios, i), GFP_KERNEL);
if (unlikely(!or)) {
ORE_ERR("%s: osd_start_request failed\n", __func__);
ret = -ENOMEM;
goto out;
}
ios->per_dev[i].or = or;
ios->numdevs++;
osd_req_create_object(or, _ios_obj(ios, i));
}
ret = ore_io_execute(ios);
out:
return ret;
}
EXPORT_SYMBOL(ore_create);
int ore_remove(struct ore_io_state *ios)
{
int i, ret;
for (i = 0; i < ios->oc->numdevs; i++) {
struct osd_request *or;
or = osd_start_request(_ios_od(ios, i), GFP_KERNEL);
if (unlikely(!or)) {
ORE_ERR("%s: osd_start_request failed\n", __func__);
ret = -ENOMEM;
goto out;
}
ios->per_dev[i].or = or;
ios->numdevs++;
osd_req_remove_object(or, _ios_obj(ios, i));
}
ret = ore_io_execute(ios);
out:
return ret;
}
EXPORT_SYMBOL(ore_remove);
static int _write_mirror(struct ore_io_state *ios, int cur_comp)
{
struct ore_per_dev_state *master_dev = &ios->per_dev[cur_comp];
unsigned dev = ios->per_dev[cur_comp].dev;
unsigned last_comp = cur_comp + ios->layout->mirrors_p1;
int ret = 0;
if (ios->pages && !master_dev->length)
return 0; /* Just an empty slot */
for (; cur_comp < last_comp; ++cur_comp, ++dev) {
struct ore_per_dev_state *per_dev = &ios->per_dev[cur_comp];
struct osd_request *or;
or = osd_start_request(_ios_od(ios, dev), GFP_KERNEL);
if (unlikely(!or)) {
ORE_ERR("%s: osd_start_request failed\n", __func__);
ret = -ENOMEM;
goto out;
}
per_dev->or = or;
if (ios->pages) {
struct bio *bio;
if (per_dev != master_dev) {
bio = bio_clone_kmalloc(master_dev->bio,
GFP_KERNEL);
if (unlikely(!bio)) {
ORE_DBGMSG(
"Failed to allocate BIO size=%u\n",
master_dev->bio->bi_max_vecs);
ret = -ENOMEM;
goto out;
}
bio->bi_bdev = NULL;
bio->bi_next = NULL;
per_dev->offset = master_dev->offset;
per_dev->length = master_dev->length;
per_dev->bio = bio;
per_dev->dev = dev;
} else {
bio = master_dev->bio;
/* FIXME: bio_set_dir() */
bio->bi_rw |= REQ_WRITE;
}
osd_req_write(or, _ios_obj(ios, cur_comp),
per_dev->offset, bio, per_dev->length);
ORE_DBGMSG("write(0x%llx) offset=0x%llx "
"length=0x%llx dev=%d\n",
_LLU(_ios_obj(ios, cur_comp)->id),
_LLU(per_dev->offset),
_LLU(per_dev->length), dev);
} else if (ios->kern_buff) {
per_dev->offset = ios->si.obj_offset;
per_dev->dev = ios->si.dev + dev;
/* no cross device without page array */
BUG_ON((ios->layout->group_width > 1) &&
(ios->si.unit_off + ios->length >
ios->layout->stripe_unit));
ret = osd_req_write_kern(or, _ios_obj(ios, cur_comp),
per_dev->offset,
ios->kern_buff, ios->length);
if (unlikely(ret))
goto out;
ORE_DBGMSG2("write_kern(0x%llx) offset=0x%llx "
"length=0x%llx dev=%d\n",
_LLU(_ios_obj(ios, cur_comp)->id),
_LLU(per_dev->offset),
_LLU(ios->length), per_dev->dev);
} else {
osd_req_set_attributes(or, _ios_obj(ios, cur_comp));
ORE_DBGMSG2("obj(0x%llx) set_attributes=%d dev=%d\n",
_LLU(_ios_obj(ios, cur_comp)->id),
ios->out_attr_len, dev);
}
if (ios->out_attr)
osd_req_add_set_attr_list(or, ios->out_attr,
ios->out_attr_len);
if (ios->in_attr)
osd_req_add_get_attr_list(or, ios->in_attr,
ios->in_attr_len);
}
out:
return ret;
}
int ore_write(struct ore_io_state *ios)
{
int i;
int ret;
if (unlikely(ios->sp2d && !ios->r4w)) {
/* A library is attempting a RAID-write without providing
* a pages lock interface.
*/
WARN_ON_ONCE(1);
return -ENOTSUPP;
}
ret = _prepare_for_striping(ios);
if (unlikely(ret))
return ret;
for (i = 0; i < ios->numdevs; i += ios->layout->mirrors_p1) {
ret = _write_mirror(ios, i);
if (unlikely(ret))
return ret;
}
ret = ore_io_execute(ios);
return ret;
}
EXPORT_SYMBOL(ore_write);
int _ore_read_mirror(struct ore_io_state *ios, unsigned cur_comp)
{
struct osd_request *or;
struct ore_per_dev_state *per_dev = &ios->per_dev[cur_comp];
struct osd_obj_id *obj = _ios_obj(ios, cur_comp);
unsigned first_dev = (unsigned)obj->id;
if (ios->pages && !per_dev->length)
return 0; /* Just an empty slot */
first_dev = per_dev->dev + first_dev % ios->layout->mirrors_p1;
or = osd_start_request(_ios_od(ios, first_dev), GFP_KERNEL);
if (unlikely(!or)) {
ORE_ERR("%s: osd_start_request failed\n", __func__);
return -ENOMEM;
}
per_dev->or = or;
if (ios->pages) {
if (per_dev->cur_sg) {
/* finalize the last sg_entry */
_ore_add_sg_seg(per_dev, 0, false);
if (unlikely(!per_dev->cur_sg))
return 0; /* Skip parity only device */
osd_req_read_sg(or, obj, per_dev->bio,
per_dev->sglist, per_dev->cur_sg);
} else {
/* The no raid case */
osd_req_read(or, obj, per_dev->offset,
per_dev->bio, per_dev->length);
}
ORE_DBGMSG("read(0x%llx) offset=0x%llx length=0x%llx"
" dev=%d sg_len=%d\n", _LLU(obj->id),
_LLU(per_dev->offset), _LLU(per_dev->length),
first_dev, per_dev->cur_sg);
} else {
BUG_ON(ios->kern_buff);
osd_req_get_attributes(or, obj);
ORE_DBGMSG2("obj(0x%llx) get_attributes=%d dev=%d\n",
_LLU(obj->id),