forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathbus.c
1466 lines (1219 loc) · 34.3 KB
/
bus.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
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2017-2018 Intel Corporation. All rights reserved. */
#include <linux/memremap.h>
#include <linux/device.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/dax.h>
#include <linux/io.h>
#include "dax-private.h"
#include "bus.h"
static struct class *dax_class;
static DEFINE_MUTEX(dax_bus_lock);
#define DAX_NAME_LEN 30
struct dax_id {
struct list_head list;
char dev_name[DAX_NAME_LEN];
};
static int dax_bus_uevent(struct device *dev, struct kobj_uevent_env *env)
{
/*
* We only ever expect to handle device-dax instances, i.e. the
* @type argument to MODULE_ALIAS_DAX_DEVICE() is always zero
*/
return add_uevent_var(env, "MODALIAS=" DAX_DEVICE_MODALIAS_FMT, 0);
}
static struct dax_device_driver *to_dax_drv(struct device_driver *drv)
{
return container_of(drv, struct dax_device_driver, drv);
}
static struct dax_id *__dax_match_id(struct dax_device_driver *dax_drv,
const char *dev_name)
{
struct dax_id *dax_id;
lockdep_assert_held(&dax_bus_lock);
list_for_each_entry(dax_id, &dax_drv->ids, list)
if (sysfs_streq(dax_id->dev_name, dev_name))
return dax_id;
return NULL;
}
static int dax_match_id(struct dax_device_driver *dax_drv, struct device *dev)
{
int match;
mutex_lock(&dax_bus_lock);
match = !!__dax_match_id(dax_drv, dev_name(dev));
mutex_unlock(&dax_bus_lock);
return match;
}
enum id_action {
ID_REMOVE,
ID_ADD,
};
static ssize_t do_id_store(struct device_driver *drv, const char *buf,
size_t count, enum id_action action)
{
struct dax_device_driver *dax_drv = to_dax_drv(drv);
unsigned int region_id, id;
char devname[DAX_NAME_LEN];
struct dax_id *dax_id;
ssize_t rc = count;
int fields;
fields = sscanf(buf, "dax%d.%d", ®ion_id, &id);
if (fields != 2)
return -EINVAL;
sprintf(devname, "dax%d.%d", region_id, id);
if (!sysfs_streq(buf, devname))
return -EINVAL;
mutex_lock(&dax_bus_lock);
dax_id = __dax_match_id(dax_drv, buf);
if (!dax_id) {
if (action == ID_ADD) {
dax_id = kzalloc(sizeof(*dax_id), GFP_KERNEL);
if (dax_id) {
strncpy(dax_id->dev_name, buf, DAX_NAME_LEN);
list_add(&dax_id->list, &dax_drv->ids);
} else
rc = -ENOMEM;
}
} else if (action == ID_REMOVE) {
list_del(&dax_id->list);
kfree(dax_id);
}
mutex_unlock(&dax_bus_lock);
if (rc < 0)
return rc;
if (action == ID_ADD)
rc = driver_attach(drv);
if (rc)
return rc;
return count;
}
static ssize_t new_id_store(struct device_driver *drv, const char *buf,
size_t count)
{
return do_id_store(drv, buf, count, ID_ADD);
}
static DRIVER_ATTR_WO(new_id);
static ssize_t remove_id_store(struct device_driver *drv, const char *buf,
size_t count)
{
return do_id_store(drv, buf, count, ID_REMOVE);
}
static DRIVER_ATTR_WO(remove_id);
static struct attribute *dax_drv_attrs[] = {
&driver_attr_new_id.attr,
&driver_attr_remove_id.attr,
NULL,
};
ATTRIBUTE_GROUPS(dax_drv);
static int dax_bus_match(struct device *dev, struct device_driver *drv);
static bool is_static(struct dax_region *dax_region)
{
return (dax_region->res.flags & IORESOURCE_DAX_STATIC) != 0;
}
static u64 dev_dax_size(struct dev_dax *dev_dax)
{
u64 size = 0;
int i;
device_lock_assert(&dev_dax->dev);
for (i = 0; i < dev_dax->nr_range; i++)
size += range_len(&dev_dax->ranges[i].range);
return size;
}
static int dax_bus_probe(struct device *dev)
{
struct dax_device_driver *dax_drv = to_dax_drv(dev->driver);
struct dev_dax *dev_dax = to_dev_dax(dev);
struct dax_region *dax_region = dev_dax->region;
int rc;
if (dev_dax_size(dev_dax) == 0 || dev_dax->id < 0)
return -ENXIO;
rc = dax_drv->probe(dev_dax);
if (rc || is_static(dax_region))
return rc;
/*
* Track new seed creation only after successful probe of the
* previous seed.
*/
if (dax_region->seed == dev)
dax_region->seed = NULL;
return 0;
}
static void dax_bus_remove(struct device *dev)
{
struct dax_device_driver *dax_drv = to_dax_drv(dev->driver);
struct dev_dax *dev_dax = to_dev_dax(dev);
if (dax_drv->remove)
dax_drv->remove(dev_dax);
}
static struct bus_type dax_bus_type = {
.name = "dax",
.uevent = dax_bus_uevent,
.match = dax_bus_match,
.probe = dax_bus_probe,
.remove = dax_bus_remove,
.drv_groups = dax_drv_groups,
};
static int dax_bus_match(struct device *dev, struct device_driver *drv)
{
struct dax_device_driver *dax_drv = to_dax_drv(drv);
/*
* All but the 'device-dax' driver, which has 'match_always'
* set, requires an exact id match.
*/
if (dax_drv->match_always)
return 1;
return dax_match_id(dax_drv, dev);
}
/*
* Rely on the fact that drvdata is set before the attributes are
* registered, and that the attributes are unregistered before drvdata
* is cleared to assume that drvdata is always valid.
*/
static ssize_t id_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dax_region *dax_region = dev_get_drvdata(dev);
return sprintf(buf, "%d\n", dax_region->id);
}
static DEVICE_ATTR_RO(id);
static ssize_t region_size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dax_region *dax_region = dev_get_drvdata(dev);
return sprintf(buf, "%llu\n", (unsigned long long)
resource_size(&dax_region->res));
}
static struct device_attribute dev_attr_region_size = __ATTR(size, 0444,
region_size_show, NULL);
static ssize_t region_align_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dax_region *dax_region = dev_get_drvdata(dev);
return sprintf(buf, "%u\n", dax_region->align);
}
static struct device_attribute dev_attr_region_align =
__ATTR(align, 0400, region_align_show, NULL);
#define for_each_dax_region_resource(dax_region, res) \
for (res = (dax_region)->res.child; res; res = res->sibling)
static unsigned long long dax_region_avail_size(struct dax_region *dax_region)
{
resource_size_t size = resource_size(&dax_region->res);
struct resource *res;
device_lock_assert(dax_region->dev);
for_each_dax_region_resource(dax_region, res)
size -= resource_size(res);
return size;
}
static ssize_t available_size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dax_region *dax_region = dev_get_drvdata(dev);
unsigned long long size;
device_lock(dev);
size = dax_region_avail_size(dax_region);
device_unlock(dev);
return sprintf(buf, "%llu\n", size);
}
static DEVICE_ATTR_RO(available_size);
static ssize_t seed_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dax_region *dax_region = dev_get_drvdata(dev);
struct device *seed;
ssize_t rc;
if (is_static(dax_region))
return -EINVAL;
device_lock(dev);
seed = dax_region->seed;
rc = sprintf(buf, "%s\n", seed ? dev_name(seed) : "");
device_unlock(dev);
return rc;
}
static DEVICE_ATTR_RO(seed);
static ssize_t create_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dax_region *dax_region = dev_get_drvdata(dev);
struct device *youngest;
ssize_t rc;
if (is_static(dax_region))
return -EINVAL;
device_lock(dev);
youngest = dax_region->youngest;
rc = sprintf(buf, "%s\n", youngest ? dev_name(youngest) : "");
device_unlock(dev);
return rc;
}
static ssize_t create_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t len)
{
struct dax_region *dax_region = dev_get_drvdata(dev);
unsigned long long avail;
ssize_t rc;
int val;
if (is_static(dax_region))
return -EINVAL;
rc = kstrtoint(buf, 0, &val);
if (rc)
return rc;
if (val != 1)
return -EINVAL;
device_lock(dev);
avail = dax_region_avail_size(dax_region);
if (avail == 0)
rc = -ENOSPC;
else {
struct dev_dax_data data = {
.dax_region = dax_region,
.size = 0,
.id = -1,
};
struct dev_dax *dev_dax = devm_create_dev_dax(&data);
if (IS_ERR(dev_dax))
rc = PTR_ERR(dev_dax);
else {
/*
* In support of crafting multiple new devices
* simultaneously multiple seeds can be created,
* but only the first one that has not been
* successfully bound is tracked as the region
* seed.
*/
if (!dax_region->seed)
dax_region->seed = &dev_dax->dev;
dax_region->youngest = &dev_dax->dev;
rc = len;
}
}
device_unlock(dev);
return rc;
}
static DEVICE_ATTR_RW(create);
void kill_dev_dax(struct dev_dax *dev_dax)
{
struct dax_device *dax_dev = dev_dax->dax_dev;
struct inode *inode = dax_inode(dax_dev);
kill_dax(dax_dev);
unmap_mapping_range(inode->i_mapping, 0, 0, 1);
}
EXPORT_SYMBOL_GPL(kill_dev_dax);
static void trim_dev_dax_range(struct dev_dax *dev_dax)
{
int i = dev_dax->nr_range - 1;
struct range *range = &dev_dax->ranges[i].range;
struct dax_region *dax_region = dev_dax->region;
device_lock_assert(dax_region->dev);
dev_dbg(&dev_dax->dev, "delete range[%d]: %#llx:%#llx\n", i,
(unsigned long long)range->start,
(unsigned long long)range->end);
__release_region(&dax_region->res, range->start, range_len(range));
if (--dev_dax->nr_range == 0) {
kfree(dev_dax->ranges);
dev_dax->ranges = NULL;
}
}
static void free_dev_dax_ranges(struct dev_dax *dev_dax)
{
while (dev_dax->nr_range)
trim_dev_dax_range(dev_dax);
}
static void unregister_dev_dax(void *dev)
{
struct dev_dax *dev_dax = to_dev_dax(dev);
dev_dbg(dev, "%s\n", __func__);
kill_dev_dax(dev_dax);
free_dev_dax_ranges(dev_dax);
device_del(dev);
put_device(dev);
}
/* a return value >= 0 indicates this invocation invalidated the id */
static int __free_dev_dax_id(struct dev_dax *dev_dax)
{
struct dax_region *dax_region = dev_dax->region;
struct device *dev = &dev_dax->dev;
int rc = dev_dax->id;
device_lock_assert(dev);
if (is_static(dax_region) || dev_dax->id < 0)
return -1;
ida_free(&dax_region->ida, dev_dax->id);
dev_dax->id = -1;
return rc;
}
static int free_dev_dax_id(struct dev_dax *dev_dax)
{
struct device *dev = &dev_dax->dev;
int rc;
device_lock(dev);
rc = __free_dev_dax_id(dev_dax);
device_unlock(dev);
return rc;
}
static ssize_t delete_store(struct device *dev, struct device_attribute *attr,
const char *buf, size_t len)
{
struct dax_region *dax_region = dev_get_drvdata(dev);
struct dev_dax *dev_dax;
struct device *victim;
bool do_del = false;
int rc;
if (is_static(dax_region))
return -EINVAL;
victim = device_find_child_by_name(dax_region->dev, buf);
if (!victim)
return -ENXIO;
device_lock(dev);
device_lock(victim);
dev_dax = to_dev_dax(victim);
if (victim->driver || dev_dax_size(dev_dax))
rc = -EBUSY;
else {
/*
* Invalidate the device so it does not become active
* again, but always preserve device-id-0 so that
* /sys/bus/dax/ is guaranteed to be populated while any
* dax_region is registered.
*/
if (dev_dax->id > 0) {
do_del = __free_dev_dax_id(dev_dax) >= 0;
rc = len;
if (dax_region->seed == victim)
dax_region->seed = NULL;
if (dax_region->youngest == victim)
dax_region->youngest = NULL;
} else
rc = -EBUSY;
}
device_unlock(victim);
/* won the race to invalidate the device, clean it up */
if (do_del)
devm_release_action(dev, unregister_dev_dax, victim);
device_unlock(dev);
put_device(victim);
return rc;
}
static DEVICE_ATTR_WO(delete);
static umode_t dax_region_visible(struct kobject *kobj, struct attribute *a,
int n)
{
struct device *dev = container_of(kobj, struct device, kobj);
struct dax_region *dax_region = dev_get_drvdata(dev);
if (is_static(dax_region))
if (a == &dev_attr_available_size.attr
|| a == &dev_attr_create.attr
|| a == &dev_attr_seed.attr
|| a == &dev_attr_delete.attr)
return 0;
return a->mode;
}
static struct attribute *dax_region_attributes[] = {
&dev_attr_available_size.attr,
&dev_attr_region_size.attr,
&dev_attr_region_align.attr,
&dev_attr_create.attr,
&dev_attr_seed.attr,
&dev_attr_delete.attr,
&dev_attr_id.attr,
NULL,
};
static const struct attribute_group dax_region_attribute_group = {
.name = "dax_region",
.attrs = dax_region_attributes,
.is_visible = dax_region_visible,
};
static const struct attribute_group *dax_region_attribute_groups[] = {
&dax_region_attribute_group,
NULL,
};
static void dax_region_free(struct kref *kref)
{
struct dax_region *dax_region;
dax_region = container_of(kref, struct dax_region, kref);
kfree(dax_region);
}
void dax_region_put(struct dax_region *dax_region)
{
kref_put(&dax_region->kref, dax_region_free);
}
EXPORT_SYMBOL_GPL(dax_region_put);
static void dax_region_unregister(void *region)
{
struct dax_region *dax_region = region;
sysfs_remove_groups(&dax_region->dev->kobj,
dax_region_attribute_groups);
dax_region_put(dax_region);
}
struct dax_region *alloc_dax_region(struct device *parent, int region_id,
struct range *range, int target_node, unsigned int align,
unsigned long flags)
{
struct dax_region *dax_region;
/*
* The DAX core assumes that it can store its private data in
* parent->driver_data. This WARN is a reminder / safeguard for
* developers of device-dax drivers.
*/
if (dev_get_drvdata(parent)) {
dev_WARN(parent, "dax core failed to setup private data\n");
return NULL;
}
if (!IS_ALIGNED(range->start, align)
|| !IS_ALIGNED(range_len(range), align))
return NULL;
dax_region = kzalloc(sizeof(*dax_region), GFP_KERNEL);
if (!dax_region)
return NULL;
dev_set_drvdata(parent, dax_region);
kref_init(&dax_region->kref);
dax_region->id = region_id;
dax_region->align = align;
dax_region->dev = parent;
dax_region->target_node = target_node;
ida_init(&dax_region->ida);
dax_region->res = (struct resource) {
.start = range->start,
.end = range->end,
.flags = IORESOURCE_MEM | flags,
};
if (sysfs_create_groups(&parent->kobj, dax_region_attribute_groups)) {
kfree(dax_region);
return NULL;
}
kref_get(&dax_region->kref);
if (devm_add_action_or_reset(parent, dax_region_unregister, dax_region))
return NULL;
return dax_region;
}
EXPORT_SYMBOL_GPL(alloc_dax_region);
static void dax_mapping_release(struct device *dev)
{
struct dax_mapping *mapping = to_dax_mapping(dev);
struct dev_dax *dev_dax = to_dev_dax(dev->parent);
ida_free(&dev_dax->ida, mapping->id);
kfree(mapping);
}
static void unregister_dax_mapping(void *data)
{
struct device *dev = data;
struct dax_mapping *mapping = to_dax_mapping(dev);
struct dev_dax *dev_dax = to_dev_dax(dev->parent);
struct dax_region *dax_region = dev_dax->region;
dev_dbg(dev, "%s\n", __func__);
device_lock_assert(dax_region->dev);
dev_dax->ranges[mapping->range_id].mapping = NULL;
mapping->range_id = -1;
device_del(dev);
put_device(dev);
}
static struct dev_dax_range *get_dax_range(struct device *dev)
{
struct dax_mapping *mapping = to_dax_mapping(dev);
struct dev_dax *dev_dax = to_dev_dax(dev->parent);
struct dax_region *dax_region = dev_dax->region;
device_lock(dax_region->dev);
if (mapping->range_id < 0) {
device_unlock(dax_region->dev);
return NULL;
}
return &dev_dax->ranges[mapping->range_id];
}
static void put_dax_range(struct dev_dax_range *dax_range)
{
struct dax_mapping *mapping = dax_range->mapping;
struct dev_dax *dev_dax = to_dev_dax(mapping->dev.parent);
struct dax_region *dax_region = dev_dax->region;
device_unlock(dax_region->dev);
}
static ssize_t start_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dev_dax_range *dax_range;
ssize_t rc;
dax_range = get_dax_range(dev);
if (!dax_range)
return -ENXIO;
rc = sprintf(buf, "%#llx\n", dax_range->range.start);
put_dax_range(dax_range);
return rc;
}
static DEVICE_ATTR(start, 0400, start_show, NULL);
static ssize_t end_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dev_dax_range *dax_range;
ssize_t rc;
dax_range = get_dax_range(dev);
if (!dax_range)
return -ENXIO;
rc = sprintf(buf, "%#llx\n", dax_range->range.end);
put_dax_range(dax_range);
return rc;
}
static DEVICE_ATTR(end, 0400, end_show, NULL);
static ssize_t pgoff_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dev_dax_range *dax_range;
ssize_t rc;
dax_range = get_dax_range(dev);
if (!dax_range)
return -ENXIO;
rc = sprintf(buf, "%#lx\n", dax_range->pgoff);
put_dax_range(dax_range);
return rc;
}
static DEVICE_ATTR(page_offset, 0400, pgoff_show, NULL);
static struct attribute *dax_mapping_attributes[] = {
&dev_attr_start.attr,
&dev_attr_end.attr,
&dev_attr_page_offset.attr,
NULL,
};
static const struct attribute_group dax_mapping_attribute_group = {
.attrs = dax_mapping_attributes,
};
static const struct attribute_group *dax_mapping_attribute_groups[] = {
&dax_mapping_attribute_group,
NULL,
};
static struct device_type dax_mapping_type = {
.release = dax_mapping_release,
.groups = dax_mapping_attribute_groups,
};
static int devm_register_dax_mapping(struct dev_dax *dev_dax, int range_id)
{
struct dax_region *dax_region = dev_dax->region;
struct dax_mapping *mapping;
struct device *dev;
int rc;
device_lock_assert(dax_region->dev);
if (dev_WARN_ONCE(&dev_dax->dev, !dax_region->dev->driver,
"region disabled\n"))
return -ENXIO;
mapping = kzalloc(sizeof(*mapping), GFP_KERNEL);
if (!mapping)
return -ENOMEM;
mapping->range_id = range_id;
mapping->id = ida_alloc(&dev_dax->ida, GFP_KERNEL);
if (mapping->id < 0) {
kfree(mapping);
return -ENOMEM;
}
dev_dax->ranges[range_id].mapping = mapping;
dev = &mapping->dev;
device_initialize(dev);
dev->parent = &dev_dax->dev;
dev->type = &dax_mapping_type;
dev_set_name(dev, "mapping%d", mapping->id);
rc = device_add(dev);
if (rc) {
put_device(dev);
return rc;
}
rc = devm_add_action_or_reset(dax_region->dev, unregister_dax_mapping,
dev);
if (rc)
return rc;
return 0;
}
static int alloc_dev_dax_range(struct dev_dax *dev_dax, u64 start,
resource_size_t size)
{
struct dax_region *dax_region = dev_dax->region;
struct resource *res = &dax_region->res;
struct device *dev = &dev_dax->dev;
struct dev_dax_range *ranges;
unsigned long pgoff = 0;
struct resource *alloc;
int i, rc;
device_lock_assert(dax_region->dev);
/* handle the seed alloc special case */
if (!size) {
if (dev_WARN_ONCE(dev, dev_dax->nr_range,
"0-size allocation must be first\n"))
return -EBUSY;
/* nr_range == 0 is elsewhere special cased as 0-size device */
return 0;
}
alloc = __request_region(res, start, size, dev_name(dev), 0);
if (!alloc)
return -ENOMEM;
ranges = krealloc(dev_dax->ranges, sizeof(*ranges)
* (dev_dax->nr_range + 1), GFP_KERNEL);
if (!ranges) {
__release_region(res, alloc->start, resource_size(alloc));
return -ENOMEM;
}
for (i = 0; i < dev_dax->nr_range; i++)
pgoff += PHYS_PFN(range_len(&ranges[i].range));
dev_dax->ranges = ranges;
ranges[dev_dax->nr_range++] = (struct dev_dax_range) {
.pgoff = pgoff,
.range = {
.start = alloc->start,
.end = alloc->end,
},
};
dev_dbg(dev, "alloc range[%d]: %pa:%pa\n", dev_dax->nr_range - 1,
&alloc->start, &alloc->end);
/*
* A dev_dax instance must be registered before mapping device
* children can be added. Defer to devm_create_dev_dax() to add
* the initial mapping device.
*/
if (!device_is_registered(&dev_dax->dev))
return 0;
rc = devm_register_dax_mapping(dev_dax, dev_dax->nr_range - 1);
if (rc)
trim_dev_dax_range(dev_dax);
return rc;
}
static int adjust_dev_dax_range(struct dev_dax *dev_dax, struct resource *res, resource_size_t size)
{
int last_range = dev_dax->nr_range - 1;
struct dev_dax_range *dax_range = &dev_dax->ranges[last_range];
struct dax_region *dax_region = dev_dax->region;
bool is_shrink = resource_size(res) > size;
struct range *range = &dax_range->range;
struct device *dev = &dev_dax->dev;
int rc;
device_lock_assert(dax_region->dev);
if (dev_WARN_ONCE(dev, !size, "deletion is handled by dev_dax_shrink\n"))
return -EINVAL;
rc = adjust_resource(res, range->start, size);
if (rc)
return rc;
*range = (struct range) {
.start = range->start,
.end = range->start + size - 1,
};
dev_dbg(dev, "%s range[%d]: %#llx:%#llx\n", is_shrink ? "shrink" : "extend",
last_range, (unsigned long long) range->start,
(unsigned long long) range->end);
return 0;
}
static ssize_t size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct dev_dax *dev_dax = to_dev_dax(dev);
unsigned long long size;
device_lock(dev);
size = dev_dax_size(dev_dax);
device_unlock(dev);
return sprintf(buf, "%llu\n", size);
}
static bool alloc_is_aligned(struct dev_dax *dev_dax, resource_size_t size)
{
/*
* The minimum mapping granularity for a device instance is a
* single subsection, unless the arch says otherwise.
*/
return IS_ALIGNED(size, max_t(unsigned long, dev_dax->align, memremap_compat_align()));
}
static int dev_dax_shrink(struct dev_dax *dev_dax, resource_size_t size)
{
resource_size_t to_shrink = dev_dax_size(dev_dax) - size;
struct dax_region *dax_region = dev_dax->region;
struct device *dev = &dev_dax->dev;
int i;
for (i = dev_dax->nr_range - 1; i >= 0; i--) {
struct range *range = &dev_dax->ranges[i].range;
struct dax_mapping *mapping = dev_dax->ranges[i].mapping;
struct resource *adjust = NULL, *res;
resource_size_t shrink;
shrink = min_t(u64, to_shrink, range_len(range));
if (shrink >= range_len(range)) {
devm_release_action(dax_region->dev,
unregister_dax_mapping, &mapping->dev);
trim_dev_dax_range(dev_dax);
to_shrink -= shrink;
if (!to_shrink)
break;
continue;
}
for_each_dax_region_resource(dax_region, res)
if (strcmp(res->name, dev_name(dev)) == 0
&& res->start == range->start) {
adjust = res;
break;
}
if (dev_WARN_ONCE(dev, !adjust || i != dev_dax->nr_range - 1,
"failed to find matching resource\n"))
return -ENXIO;
return adjust_dev_dax_range(dev_dax, adjust, range_len(range)
- shrink);
}
return 0;
}
/*
* Only allow adjustments that preserve the relative pgoff of existing
* allocations. I.e. the dev_dax->ranges array is ordered by increasing pgoff.
*/
static bool adjust_ok(struct dev_dax *dev_dax, struct resource *res)
{
struct dev_dax_range *last;
int i;
if (dev_dax->nr_range == 0)
return false;
if (strcmp(res->name, dev_name(&dev_dax->dev)) != 0)
return false;
last = &dev_dax->ranges[dev_dax->nr_range - 1];
if (last->range.start != res->start || last->range.end != res->end)
return false;
for (i = 0; i < dev_dax->nr_range - 1; i++) {
struct dev_dax_range *dax_range = &dev_dax->ranges[i];
if (dax_range->pgoff > last->pgoff)
return false;
}
return true;
}
static ssize_t dev_dax_resize(struct dax_region *dax_region,
struct dev_dax *dev_dax, resource_size_t size)
{
resource_size_t avail = dax_region_avail_size(dax_region), to_alloc;
resource_size_t dev_size = dev_dax_size(dev_dax);
struct resource *region_res = &dax_region->res;
struct device *dev = &dev_dax->dev;
struct resource *res, *first;
resource_size_t alloc = 0;
int rc;
if (dev->driver)
return -EBUSY;
if (size == dev_size)
return 0;
if (size > dev_size && size - dev_size > avail)
return -ENOSPC;
if (size < dev_size)
return dev_dax_shrink(dev_dax, size);
to_alloc = size - dev_size;
if (dev_WARN_ONCE(dev, !alloc_is_aligned(dev_dax, to_alloc),
"resize of %pa misaligned\n", &to_alloc))
return -ENXIO;
/*
* Expand the device into the unused portion of the region. This
* may involve adjusting the end of an existing resource, or
* allocating a new resource.
*/
retry:
first = region_res->child;
if (!first)
return alloc_dev_dax_range(dev_dax, dax_region->res.start, to_alloc);
rc = -ENOSPC;
for (res = first; res; res = res->sibling) {
struct resource *next = res->sibling;
/* space at the beginning of the region */
if (res == first && res->start > dax_region->res.start) {
alloc = min(res->start - dax_region->res.start, to_alloc);
rc = alloc_dev_dax_range(dev_dax, dax_region->res.start, alloc);
break;
}
alloc = 0;
/* space between allocations */
if (next && next->start > res->end + 1)
alloc = min(next->start - (res->end + 1), to_alloc);
/* space at the end of the region */
if (!alloc && !next && res->end < region_res->end)
alloc = min(region_res->end - res->end, to_alloc);
if (!alloc)
continue;
if (adjust_ok(dev_dax, res)) {
rc = adjust_dev_dax_range(dev_dax, res, resource_size(res) + alloc);
break;
}
rc = alloc_dev_dax_range(dev_dax, res->end + 1, alloc);
break;
}
if (rc)
return rc;
to_alloc -= alloc;
if (to_alloc)