forked from beagleboard/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
namespace_devs.c
2000 lines (1684 loc) · 49.1 KB
/
namespace_devs.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) 2013-2015 Intel Corporation. All rights reserved.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of version 2 of the GNU General Public License as
* published by the Free Software Foundation.
*
* This program 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.
*/
#include <linux/module.h>
#include <linux/device.h>
#include <linux/slab.h>
#include <linux/pmem.h>
#include <linux/nd.h>
#include "nd-core.h"
#include "nd.h"
static void namespace_io_release(struct device *dev)
{
struct nd_namespace_io *nsio = to_nd_namespace_io(dev);
kfree(nsio);
}
static void namespace_pmem_release(struct device *dev)
{
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
kfree(nspm->alt_name);
kfree(nspm->uuid);
kfree(nspm);
}
static void namespace_blk_release(struct device *dev)
{
struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
struct nd_region *nd_region = to_nd_region(dev->parent);
if (nsblk->id >= 0)
ida_simple_remove(&nd_region->ns_ida, nsblk->id);
kfree(nsblk->alt_name);
kfree(nsblk->uuid);
kfree(nsblk->res);
kfree(nsblk);
}
static struct device_type namespace_io_device_type = {
.name = "nd_namespace_io",
.release = namespace_io_release,
};
static struct device_type namespace_pmem_device_type = {
.name = "nd_namespace_pmem",
.release = namespace_pmem_release,
};
static struct device_type namespace_blk_device_type = {
.name = "nd_namespace_blk",
.release = namespace_blk_release,
};
static bool is_namespace_pmem(struct device *dev)
{
return dev ? dev->type == &namespace_pmem_device_type : false;
}
static bool is_namespace_blk(struct device *dev)
{
return dev ? dev->type == &namespace_blk_device_type : false;
}
static bool is_namespace_io(struct device *dev)
{
return dev ? dev->type == &namespace_io_device_type : false;
}
static int is_uuid_busy(struct device *dev, void *data)
{
u8 *uuid1 = data, *uuid2 = NULL;
if (is_namespace_pmem(dev)) {
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
uuid2 = nspm->uuid;
} else if (is_namespace_blk(dev)) {
struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
uuid2 = nsblk->uuid;
} else if (is_nd_btt(dev)) {
struct nd_btt *nd_btt = to_nd_btt(dev);
uuid2 = nd_btt->uuid;
} else if (is_nd_pfn(dev)) {
struct nd_pfn *nd_pfn = to_nd_pfn(dev);
uuid2 = nd_pfn->uuid;
}
if (uuid2 && memcmp(uuid1, uuid2, NSLABEL_UUID_LEN) == 0)
return -EBUSY;
return 0;
}
static int is_namespace_uuid_busy(struct device *dev, void *data)
{
if (is_nd_pmem(dev) || is_nd_blk(dev))
return device_for_each_child(dev, data, is_uuid_busy);
return 0;
}
/**
* nd_is_uuid_unique - verify that no other namespace has @uuid
* @dev: any device on a nvdimm_bus
* @uuid: uuid to check
*/
bool nd_is_uuid_unique(struct device *dev, u8 *uuid)
{
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
if (!nvdimm_bus)
return false;
WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm_bus->dev));
if (device_for_each_child(&nvdimm_bus->dev, uuid,
is_namespace_uuid_busy) != 0)
return false;
return true;
}
bool pmem_should_map_pages(struct device *dev)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
if (!IS_ENABLED(CONFIG_ZONE_DEVICE))
return false;
if (!test_bit(ND_REGION_PAGEMAP, &nd_region->flags))
return false;
if (is_nd_pfn(dev) || is_nd_btt(dev))
return false;
#ifdef ARCH_MEMREMAP_PMEM
return ARCH_MEMREMAP_PMEM == MEMREMAP_WB;
#else
return false;
#endif
}
EXPORT_SYMBOL(pmem_should_map_pages);
const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
char *name)
{
struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
const char *suffix = NULL;
if (ndns->claim) {
if (is_nd_btt(ndns->claim))
suffix = "s";
else if (is_nd_pfn(ndns->claim))
suffix = "m";
else
dev_WARN_ONCE(&ndns->dev, 1,
"unknown claim type by %s\n",
dev_name(ndns->claim));
}
if (is_namespace_pmem(&ndns->dev) || is_namespace_io(&ndns->dev)) {
if (!suffix && pmem_should_map_pages(&ndns->dev))
suffix = "m";
sprintf(name, "pmem%d%s", nd_region->id, suffix ? suffix : "");
} else if (is_namespace_blk(&ndns->dev)) {
struct nd_namespace_blk *nsblk;
nsblk = to_nd_namespace_blk(&ndns->dev);
sprintf(name, "ndblk%d.%d%s", nd_region->id, nsblk->id,
suffix ? suffix : "");
} else {
return NULL;
}
return name;
}
EXPORT_SYMBOL(nvdimm_namespace_disk_name);
const u8 *nd_dev_to_uuid(struct device *dev)
{
static const u8 null_uuid[16];
if (!dev)
return null_uuid;
if (is_namespace_pmem(dev)) {
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
return nspm->uuid;
} else if (is_namespace_blk(dev)) {
struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
return nsblk->uuid;
} else
return null_uuid;
}
EXPORT_SYMBOL(nd_dev_to_uuid);
static ssize_t nstype_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
return sprintf(buf, "%d\n", nd_region_to_nstype(nd_region));
}
static DEVICE_ATTR_RO(nstype);
static ssize_t __alt_name_store(struct device *dev, const char *buf,
const size_t len)
{
char *input, *pos, *alt_name, **ns_altname;
ssize_t rc;
if (is_namespace_pmem(dev)) {
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
ns_altname = &nspm->alt_name;
} else if (is_namespace_blk(dev)) {
struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
ns_altname = &nsblk->alt_name;
} else
return -ENXIO;
if (dev->driver || to_ndns(dev)->claim)
return -EBUSY;
input = kmemdup(buf, len + 1, GFP_KERNEL);
if (!input)
return -ENOMEM;
input[len] = '\0';
pos = strim(input);
if (strlen(pos) + 1 > NSLABEL_NAME_LEN) {
rc = -EINVAL;
goto out;
}
alt_name = kzalloc(NSLABEL_NAME_LEN, GFP_KERNEL);
if (!alt_name) {
rc = -ENOMEM;
goto out;
}
kfree(*ns_altname);
*ns_altname = alt_name;
sprintf(*ns_altname, "%s", pos);
rc = len;
out:
kfree(input);
return rc;
}
static resource_size_t nd_namespace_blk_size(struct nd_namespace_blk *nsblk)
{
struct nd_region *nd_region = to_nd_region(nsblk->common.dev.parent);
struct nd_mapping *nd_mapping = &nd_region->mapping[0];
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
struct nd_label_id label_id;
resource_size_t size = 0;
struct resource *res;
if (!nsblk->uuid)
return 0;
nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL);
for_each_dpa_resource(ndd, res)
if (strcmp(res->name, label_id.id) == 0)
size += resource_size(res);
return size;
}
static bool __nd_namespace_blk_validate(struct nd_namespace_blk *nsblk)
{
struct nd_region *nd_region = to_nd_region(nsblk->common.dev.parent);
struct nd_mapping *nd_mapping = &nd_region->mapping[0];
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
struct nd_label_id label_id;
struct resource *res;
int count, i;
if (!nsblk->uuid || !nsblk->lbasize || !ndd)
return false;
count = 0;
nd_label_gen_id(&label_id, nsblk->uuid, NSLABEL_FLAG_LOCAL);
for_each_dpa_resource(ndd, res) {
if (strcmp(res->name, label_id.id) != 0)
continue;
/*
* Resources with unacknoweldged adjustments indicate a
* failure to update labels
*/
if (res->flags & DPA_RESOURCE_ADJUSTED)
return false;
count++;
}
/* These values match after a successful label update */
if (count != nsblk->num_resources)
return false;
for (i = 0; i < nsblk->num_resources; i++) {
struct resource *found = NULL;
for_each_dpa_resource(ndd, res)
if (res == nsblk->res[i]) {
found = res;
break;
}
/* stale resource */
if (!found)
return false;
}
return true;
}
resource_size_t nd_namespace_blk_validate(struct nd_namespace_blk *nsblk)
{
resource_size_t size;
nvdimm_bus_lock(&nsblk->common.dev);
size = __nd_namespace_blk_validate(nsblk);
nvdimm_bus_unlock(&nsblk->common.dev);
return size;
}
EXPORT_SYMBOL(nd_namespace_blk_validate);
static int nd_namespace_label_update(struct nd_region *nd_region,
struct device *dev)
{
dev_WARN_ONCE(dev, dev->driver || to_ndns(dev)->claim,
"namespace must be idle during label update\n");
if (dev->driver || to_ndns(dev)->claim)
return 0;
/*
* Only allow label writes that will result in a valid namespace
* or deletion of an existing namespace.
*/
if (is_namespace_pmem(dev)) {
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
resource_size_t size = resource_size(&nspm->nsio.res);
if (size == 0 && nspm->uuid)
/* delete allocation */;
else if (!nspm->uuid)
return 0;
return nd_pmem_namespace_label_update(nd_region, nspm, size);
} else if (is_namespace_blk(dev)) {
struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
resource_size_t size = nd_namespace_blk_size(nsblk);
if (size == 0 && nsblk->uuid)
/* delete allocation */;
else if (!nsblk->uuid || !nsblk->lbasize)
return 0;
return nd_blk_namespace_label_update(nd_region, nsblk, size);
} else
return -ENXIO;
}
static ssize_t alt_name_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
ssize_t rc;
device_lock(dev);
nvdimm_bus_lock(dev);
wait_nvdimm_bus_probe_idle(dev);
rc = __alt_name_store(dev, buf, len);
if (rc >= 0)
rc = nd_namespace_label_update(nd_region, dev);
dev_dbg(dev, "%s: %s(%zd)\n", __func__, rc < 0 ? "fail " : "", rc);
nvdimm_bus_unlock(dev);
device_unlock(dev);
return rc < 0 ? rc : len;
}
static ssize_t alt_name_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
char *ns_altname;
if (is_namespace_pmem(dev)) {
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
ns_altname = nspm->alt_name;
} else if (is_namespace_blk(dev)) {
struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
ns_altname = nsblk->alt_name;
} else
return -ENXIO;
return sprintf(buf, "%s\n", ns_altname ? ns_altname : "");
}
static DEVICE_ATTR_RW(alt_name);
static int scan_free(struct nd_region *nd_region,
struct nd_mapping *nd_mapping, struct nd_label_id *label_id,
resource_size_t n)
{
bool is_blk = strncmp(label_id->id, "blk", 3) == 0;
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
int rc = 0;
while (n) {
struct resource *res, *last;
resource_size_t new_start;
last = NULL;
for_each_dpa_resource(ndd, res)
if (strcmp(res->name, label_id->id) == 0)
last = res;
res = last;
if (!res)
return 0;
if (n >= resource_size(res)) {
n -= resource_size(res);
nd_dbg_dpa(nd_region, ndd, res, "delete %d\n", rc);
nvdimm_free_dpa(ndd, res);
/* retry with last resource deleted */
continue;
}
/*
* Keep BLK allocations relegated to high DPA as much as
* possible
*/
if (is_blk)
new_start = res->start + n;
else
new_start = res->start;
rc = adjust_resource(res, new_start, resource_size(res) - n);
if (rc == 0)
res->flags |= DPA_RESOURCE_ADJUSTED;
nd_dbg_dpa(nd_region, ndd, res, "shrink %d\n", rc);
break;
}
return rc;
}
/**
* shrink_dpa_allocation - for each dimm in region free n bytes for label_id
* @nd_region: the set of dimms to reclaim @n bytes from
* @label_id: unique identifier for the namespace consuming this dpa range
* @n: number of bytes per-dimm to release
*
* Assumes resources are ordered. Starting from the end try to
* adjust_resource() the allocation to @n, but if @n is larger than the
* allocation delete it and find the 'new' last allocation in the label
* set.
*/
static int shrink_dpa_allocation(struct nd_region *nd_region,
struct nd_label_id *label_id, resource_size_t n)
{
int i;
for (i = 0; i < nd_region->ndr_mappings; i++) {
struct nd_mapping *nd_mapping = &nd_region->mapping[i];
int rc;
rc = scan_free(nd_region, nd_mapping, label_id, n);
if (rc)
return rc;
}
return 0;
}
static resource_size_t init_dpa_allocation(struct nd_label_id *label_id,
struct nd_region *nd_region, struct nd_mapping *nd_mapping,
resource_size_t n)
{
bool is_blk = strncmp(label_id->id, "blk", 3) == 0;
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
resource_size_t first_dpa;
struct resource *res;
int rc = 0;
/* allocate blk from highest dpa first */
if (is_blk)
first_dpa = nd_mapping->start + nd_mapping->size - n;
else
first_dpa = nd_mapping->start;
/* first resource allocation for this label-id or dimm */
res = nvdimm_allocate_dpa(ndd, label_id, first_dpa, n);
if (!res)
rc = -EBUSY;
nd_dbg_dpa(nd_region, ndd, res, "init %d\n", rc);
return rc ? n : 0;
}
static bool space_valid(bool is_pmem, bool is_reserve,
struct nd_label_id *label_id, struct resource *res)
{
/*
* For BLK-space any space is valid, for PMEM-space, it must be
* contiguous with an existing allocation unless we are
* reserving pmem.
*/
if (is_reserve || !is_pmem)
return true;
if (!res || strcmp(res->name, label_id->id) == 0)
return true;
return false;
}
enum alloc_loc {
ALLOC_ERR = 0, ALLOC_BEFORE, ALLOC_MID, ALLOC_AFTER,
};
static resource_size_t scan_allocate(struct nd_region *nd_region,
struct nd_mapping *nd_mapping, struct nd_label_id *label_id,
resource_size_t n)
{
resource_size_t mapping_end = nd_mapping->start + nd_mapping->size - 1;
bool is_reserve = strcmp(label_id->id, "pmem-reserve") == 0;
bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0;
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
const resource_size_t to_allocate = n;
struct resource *res;
int first;
retry:
first = 0;
for_each_dpa_resource(ndd, res) {
resource_size_t allocate, available = 0, free_start, free_end;
struct resource *next = res->sibling, *new_res = NULL;
enum alloc_loc loc = ALLOC_ERR;
const char *action;
int rc = 0;
/* ignore resources outside this nd_mapping */
if (res->start > mapping_end)
continue;
if (res->end < nd_mapping->start)
continue;
/* space at the beginning of the mapping */
if (!first++ && res->start > nd_mapping->start) {
free_start = nd_mapping->start;
available = res->start - free_start;
if (space_valid(is_pmem, is_reserve, label_id, NULL))
loc = ALLOC_BEFORE;
}
/* space between allocations */
if (!loc && next) {
free_start = res->start + resource_size(res);
free_end = min(mapping_end, next->start - 1);
if (space_valid(is_pmem, is_reserve, label_id, res)
&& free_start < free_end) {
available = free_end + 1 - free_start;
loc = ALLOC_MID;
}
}
/* space at the end of the mapping */
if (!loc && !next) {
free_start = res->start + resource_size(res);
free_end = mapping_end;
if (space_valid(is_pmem, is_reserve, label_id, res)
&& free_start < free_end) {
available = free_end + 1 - free_start;
loc = ALLOC_AFTER;
}
}
if (!loc || !available)
continue;
allocate = min(available, n);
switch (loc) {
case ALLOC_BEFORE:
if (strcmp(res->name, label_id->id) == 0) {
/* adjust current resource up */
if (is_pmem && !is_reserve)
return n;
rc = adjust_resource(res, res->start - allocate,
resource_size(res) + allocate);
action = "cur grow up";
} else
action = "allocate";
break;
case ALLOC_MID:
if (strcmp(next->name, label_id->id) == 0) {
/* adjust next resource up */
if (is_pmem && !is_reserve)
return n;
rc = adjust_resource(next, next->start
- allocate, resource_size(next)
+ allocate);
new_res = next;
action = "next grow up";
} else if (strcmp(res->name, label_id->id) == 0) {
action = "grow down";
} else
action = "allocate";
break;
case ALLOC_AFTER:
if (strcmp(res->name, label_id->id) == 0)
action = "grow down";
else
action = "allocate";
break;
default:
return n;
}
if (strcmp(action, "allocate") == 0) {
/* BLK allocate bottom up */
if (!is_pmem)
free_start += available - allocate;
else if (!is_reserve && free_start != nd_mapping->start)
return n;
new_res = nvdimm_allocate_dpa(ndd, label_id,
free_start, allocate);
if (!new_res)
rc = -EBUSY;
} else if (strcmp(action, "grow down") == 0) {
/* adjust current resource down */
rc = adjust_resource(res, res->start, resource_size(res)
+ allocate);
if (rc == 0)
res->flags |= DPA_RESOURCE_ADJUSTED;
}
if (!new_res)
new_res = res;
nd_dbg_dpa(nd_region, ndd, new_res, "%s(%d) %d\n",
action, loc, rc);
if (rc)
return n;
n -= allocate;
if (n) {
/*
* Retry scan with newly inserted resources.
* For example, if we did an ALLOC_BEFORE
* insertion there may also have been space
* available for an ALLOC_AFTER insertion, so we
* need to check this same resource again
*/
goto retry;
} else
return 0;
}
/*
* If we allocated nothing in the BLK case it may be because we are in
* an initial "pmem-reserve pass". Only do an initial BLK allocation
* when none of the DPA space is reserved.
*/
if ((is_pmem || !ndd->dpa.child) && n == to_allocate)
return init_dpa_allocation(label_id, nd_region, nd_mapping, n);
return n;
}
static int merge_dpa(struct nd_region *nd_region,
struct nd_mapping *nd_mapping, struct nd_label_id *label_id)
{
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
struct resource *res;
if (strncmp("pmem", label_id->id, 4) == 0)
return 0;
retry:
for_each_dpa_resource(ndd, res) {
int rc;
struct resource *next = res->sibling;
resource_size_t end = res->start + resource_size(res);
if (!next || strcmp(res->name, label_id->id) != 0
|| strcmp(next->name, label_id->id) != 0
|| end != next->start)
continue;
end += resource_size(next);
nvdimm_free_dpa(ndd, next);
rc = adjust_resource(res, res->start, end - res->start);
nd_dbg_dpa(nd_region, ndd, res, "merge %d\n", rc);
if (rc)
return rc;
res->flags |= DPA_RESOURCE_ADJUSTED;
goto retry;
}
return 0;
}
static int __reserve_free_pmem(struct device *dev, void *data)
{
struct nvdimm *nvdimm = data;
struct nd_region *nd_region;
struct nd_label_id label_id;
int i;
if (!is_nd_pmem(dev))
return 0;
nd_region = to_nd_region(dev);
if (nd_region->ndr_mappings == 0)
return 0;
memset(&label_id, 0, sizeof(label_id));
strcat(label_id.id, "pmem-reserve");
for (i = 0; i < nd_region->ndr_mappings; i++) {
struct nd_mapping *nd_mapping = &nd_region->mapping[i];
resource_size_t n, rem = 0;
if (nd_mapping->nvdimm != nvdimm)
continue;
n = nd_pmem_available_dpa(nd_region, nd_mapping, &rem);
if (n == 0)
return 0;
rem = scan_allocate(nd_region, nd_mapping, &label_id, n);
dev_WARN_ONCE(&nd_region->dev, rem,
"pmem reserve underrun: %#llx of %#llx bytes\n",
(unsigned long long) n - rem,
(unsigned long long) n);
return rem ? -ENXIO : 0;
}
return 0;
}
static void release_free_pmem(struct nvdimm_bus *nvdimm_bus,
struct nd_mapping *nd_mapping)
{
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
struct resource *res, *_res;
for_each_dpa_resource_safe(ndd, res, _res)
if (strcmp(res->name, "pmem-reserve") == 0)
nvdimm_free_dpa(ndd, res);
}
static int reserve_free_pmem(struct nvdimm_bus *nvdimm_bus,
struct nd_mapping *nd_mapping)
{
struct nvdimm *nvdimm = nd_mapping->nvdimm;
int rc;
rc = device_for_each_child(&nvdimm_bus->dev, nvdimm,
__reserve_free_pmem);
if (rc)
release_free_pmem(nvdimm_bus, nd_mapping);
return rc;
}
/**
* grow_dpa_allocation - for each dimm allocate n bytes for @label_id
* @nd_region: the set of dimms to allocate @n more bytes from
* @label_id: unique identifier for the namespace consuming this dpa range
* @n: number of bytes per-dimm to add to the existing allocation
*
* Assumes resources are ordered. For BLK regions, first consume
* BLK-only available DPA free space, then consume PMEM-aliased DPA
* space starting at the highest DPA. For PMEM regions start
* allocations from the start of an interleave set and end at the first
* BLK allocation or the end of the interleave set, whichever comes
* first.
*/
static int grow_dpa_allocation(struct nd_region *nd_region,
struct nd_label_id *label_id, resource_size_t n)
{
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0;
int i;
for (i = 0; i < nd_region->ndr_mappings; i++) {
struct nd_mapping *nd_mapping = &nd_region->mapping[i];
resource_size_t rem = n;
int rc, j;
/*
* In the BLK case try once with all unallocated PMEM
* reserved, and once without
*/
for (j = is_pmem; j < 2; j++) {
bool blk_only = j == 0;
if (blk_only) {
rc = reserve_free_pmem(nvdimm_bus, nd_mapping);
if (rc)
return rc;
}
rem = scan_allocate(nd_region, nd_mapping,
label_id, rem);
if (blk_only)
release_free_pmem(nvdimm_bus, nd_mapping);
/* try again and allow encroachments into PMEM */
if (rem == 0)
break;
}
dev_WARN_ONCE(&nd_region->dev, rem,
"allocation underrun: %#llx of %#llx bytes\n",
(unsigned long long) n - rem,
(unsigned long long) n);
if (rem)
return -ENXIO;
rc = merge_dpa(nd_region, nd_mapping, label_id);
if (rc)
return rc;
}
return 0;
}
static void nd_namespace_pmem_set_size(struct nd_region *nd_region,
struct nd_namespace_pmem *nspm, resource_size_t size)
{
struct resource *res = &nspm->nsio.res;
res->start = nd_region->ndr_start;
res->end = nd_region->ndr_start + size - 1;
}
static ssize_t __size_store(struct device *dev, unsigned long long val)
{
resource_size_t allocated = 0, available = 0;
struct nd_region *nd_region = to_nd_region(dev->parent);
struct nd_mapping *nd_mapping;
struct nvdimm_drvdata *ndd;
struct nd_label_id label_id;
u32 flags = 0, remainder;
u8 *uuid = NULL;
int rc, i;
if (dev->driver || to_ndns(dev)->claim)
return -EBUSY;
if (is_namespace_pmem(dev)) {
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
uuid = nspm->uuid;
} else if (is_namespace_blk(dev)) {
struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
uuid = nsblk->uuid;
flags = NSLABEL_FLAG_LOCAL;
}
/*
* We need a uuid for the allocation-label and dimm(s) on which
* to store the label.
*/
if (!uuid || nd_region->ndr_mappings == 0)
return -ENXIO;
div_u64_rem(val, SZ_4K * nd_region->ndr_mappings, &remainder);
if (remainder) {
dev_dbg(dev, "%llu is not %dK aligned\n", val,
(SZ_4K * nd_region->ndr_mappings) / SZ_1K);
return -EINVAL;
}
nd_label_gen_id(&label_id, uuid, flags);
for (i = 0; i < nd_region->ndr_mappings; i++) {
nd_mapping = &nd_region->mapping[i];
ndd = to_ndd(nd_mapping);
/*
* All dimms in an interleave set, or the base dimm for a blk
* region, need to be enabled for the size to be changed.
*/
if (!ndd)
return -ENXIO;
allocated += nvdimm_allocated_dpa(ndd, &label_id);
}
available = nd_region_available_dpa(nd_region);
if (val > available + allocated)
return -ENOSPC;
if (val == allocated)
return 0;
val = div_u64(val, nd_region->ndr_mappings);
allocated = div_u64(allocated, nd_region->ndr_mappings);
if (val < allocated)
rc = shrink_dpa_allocation(nd_region, &label_id,
allocated - val);
else
rc = grow_dpa_allocation(nd_region, &label_id, val - allocated);
if (rc)
return rc;
if (is_namespace_pmem(dev)) {
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
nd_namespace_pmem_set_size(nd_region, nspm,
val * nd_region->ndr_mappings);
} else if (is_namespace_blk(dev)) {
struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
/*
* Try to delete the namespace if we deleted all of its
* allocation, this is not the seed device for the
* region, and it is not actively claimed by a btt
* instance.
*/
if (val == 0 && nd_region->ns_seed != dev
&& !nsblk->common.claim)
nd_device_unregister(dev, ND_ASYNC);
}
return rc;
}
static ssize_t size_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
unsigned long long val;
u8 **uuid = NULL;
int rc;
rc = kstrtoull(buf, 0, &val);
if (rc)
return rc;
device_lock(dev);
nvdimm_bus_lock(dev);
wait_nvdimm_bus_probe_idle(dev);
rc = __size_store(dev, val);
if (rc >= 0)
rc = nd_namespace_label_update(nd_region, dev);
if (is_namespace_pmem(dev)) {
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
uuid = &nspm->uuid;
} else if (is_namespace_blk(dev)) {
struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
uuid = &nsblk->uuid;
}
if (rc == 0 && val == 0 && uuid) {
/* setting size zero == 'delete namespace' */
kfree(*uuid);
*uuid = NULL;
}
dev_dbg(dev, "%s: %llx %s (%d)\n", __func__, val, rc < 0
? "fail" : "success", rc);
nvdimm_bus_unlock(dev);
device_unlock(dev);
return rc < 0 ? rc : len;
}
resource_size_t __nvdimm_namespace_capacity(struct nd_namespace_common *ndns)
{
struct device *dev = &ndns->dev;
if (is_namespace_pmem(dev)) {
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
return resource_size(&nspm->nsio.res);
} else if (is_namespace_blk(dev)) {
return nd_namespace_blk_size(to_nd_namespace_blk(dev));
} else if (is_namespace_io(dev)) {
struct nd_namespace_io *nsio = to_nd_namespace_io(dev);
return resource_size(&nsio->res);
} else
WARN_ONCE(1, "unknown namespace type\n");