forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
null_blk_main.c
2012 lines (1658 loc) · 48.4 KB
/
null_blk_main.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-only
/*
* Add configfs and memory store: Kyungchan Koh <[email protected]> and
* Shaohua Li <[email protected]>
*/
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/init.h>
#include "null_blk.h"
#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT)
#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT)
#define SECTOR_MASK (PAGE_SECTORS - 1)
#define FREE_BATCH 16
#define TICKS_PER_SEC 50ULL
#define TIMER_INTERVAL (NSEC_PER_SEC / TICKS_PER_SEC)
#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
static DECLARE_FAULT_ATTR(null_timeout_attr);
static DECLARE_FAULT_ATTR(null_requeue_attr);
static DECLARE_FAULT_ATTR(null_init_hctx_attr);
#endif
static inline u64 mb_per_tick(int mbps)
{
return (1 << 20) / TICKS_PER_SEC * ((u64) mbps);
}
/*
* Status flags for nullb_device.
*
* CONFIGURED: Device has been configured and turned on. Cannot reconfigure.
* UP: Device is currently on and visible in userspace.
* THROTTLED: Device is being throttled.
* CACHE: Device is using a write-back cache.
*/
enum nullb_device_flags {
NULLB_DEV_FL_CONFIGURED = 0,
NULLB_DEV_FL_UP = 1,
NULLB_DEV_FL_THROTTLED = 2,
NULLB_DEV_FL_CACHE = 3,
};
#define MAP_SZ ((PAGE_SIZE >> SECTOR_SHIFT) + 2)
/*
* nullb_page is a page in memory for nullb devices.
*
* @page: The page holding the data.
* @bitmap: The bitmap represents which sector in the page has data.
* Each bit represents one block size. For example, sector 8
* will use the 7th bit
* The highest 2 bits of bitmap are for special purpose. LOCK means the cache
* page is being flushing to storage. FREE means the cache page is freed and
* should be skipped from flushing to storage. Please see
* null_make_cache_space
*/
struct nullb_page {
struct page *page;
DECLARE_BITMAP(bitmap, MAP_SZ);
};
#define NULLB_PAGE_LOCK (MAP_SZ - 1)
#define NULLB_PAGE_FREE (MAP_SZ - 2)
static LIST_HEAD(nullb_list);
static struct mutex lock;
static int null_major;
static DEFINE_IDA(nullb_indexes);
static struct blk_mq_tag_set tag_set;
enum {
NULL_IRQ_NONE = 0,
NULL_IRQ_SOFTIRQ = 1,
NULL_IRQ_TIMER = 2,
};
enum {
NULL_Q_BIO = 0,
NULL_Q_RQ = 1,
NULL_Q_MQ = 2,
};
static int g_no_sched;
module_param_named(no_sched, g_no_sched, int, 0444);
MODULE_PARM_DESC(no_sched, "No io scheduler");
static int g_submit_queues = 1;
module_param_named(submit_queues, g_submit_queues, int, 0444);
MODULE_PARM_DESC(submit_queues, "Number of submission queues");
static int g_home_node = NUMA_NO_NODE;
module_param_named(home_node, g_home_node, int, 0444);
MODULE_PARM_DESC(home_node, "Home node for the device");
#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
/*
* For more details about fault injection, please refer to
* Documentation/fault-injection/fault-injection.rst.
*/
static char g_timeout_str[80];
module_param_string(timeout, g_timeout_str, sizeof(g_timeout_str), 0444);
MODULE_PARM_DESC(timeout, "Fault injection. timeout=<interval>,<probability>,<space>,<times>");
static char g_requeue_str[80];
module_param_string(requeue, g_requeue_str, sizeof(g_requeue_str), 0444);
MODULE_PARM_DESC(requeue, "Fault injection. requeue=<interval>,<probability>,<space>,<times>");
static char g_init_hctx_str[80];
module_param_string(init_hctx, g_init_hctx_str, sizeof(g_init_hctx_str), 0444);
MODULE_PARM_DESC(init_hctx, "Fault injection to fail hctx init. init_hctx=<interval>,<probability>,<space>,<times>");
#endif
static int g_queue_mode = NULL_Q_MQ;
static int null_param_store_val(const char *str, int *val, int min, int max)
{
int ret, new_val;
ret = kstrtoint(str, 10, &new_val);
if (ret)
return -EINVAL;
if (new_val < min || new_val > max)
return -EINVAL;
*val = new_val;
return 0;
}
static int null_set_queue_mode(const char *str, const struct kernel_param *kp)
{
return null_param_store_val(str, &g_queue_mode, NULL_Q_BIO, NULL_Q_MQ);
}
static const struct kernel_param_ops null_queue_mode_param_ops = {
.set = null_set_queue_mode,
.get = param_get_int,
};
device_param_cb(queue_mode, &null_queue_mode_param_ops, &g_queue_mode, 0444);
MODULE_PARM_DESC(queue_mode, "Block interface to use (0=bio,1=rq,2=multiqueue)");
static int g_gb = 250;
module_param_named(gb, g_gb, int, 0444);
MODULE_PARM_DESC(gb, "Size in GB");
static int g_bs = 512;
module_param_named(bs, g_bs, int, 0444);
MODULE_PARM_DESC(bs, "Block size (in bytes)");
static unsigned int nr_devices = 1;
module_param(nr_devices, uint, 0444);
MODULE_PARM_DESC(nr_devices, "Number of devices to register");
static bool g_blocking;
module_param_named(blocking, g_blocking, bool, 0444);
MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device");
static bool shared_tags;
module_param(shared_tags, bool, 0444);
MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq");
static bool g_shared_tag_bitmap;
module_param_named(shared_tag_bitmap, g_shared_tag_bitmap, bool, 0444);
MODULE_PARM_DESC(shared_tag_bitmap, "Use shared tag bitmap for all submission queues for blk-mq");
static int g_irqmode = NULL_IRQ_SOFTIRQ;
static int null_set_irqmode(const char *str, const struct kernel_param *kp)
{
return null_param_store_val(str, &g_irqmode, NULL_IRQ_NONE,
NULL_IRQ_TIMER);
}
static const struct kernel_param_ops null_irqmode_param_ops = {
.set = null_set_irqmode,
.get = param_get_int,
};
device_param_cb(irqmode, &null_irqmode_param_ops, &g_irqmode, 0444);
MODULE_PARM_DESC(irqmode, "IRQ completion handler. 0-none, 1-softirq, 2-timer");
static unsigned long g_completion_nsec = 10000;
module_param_named(completion_nsec, g_completion_nsec, ulong, 0444);
MODULE_PARM_DESC(completion_nsec, "Time in ns to complete a request in hardware. Default: 10,000ns");
static int g_hw_queue_depth = 64;
module_param_named(hw_queue_depth, g_hw_queue_depth, int, 0444);
MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 64");
static bool g_use_per_node_hctx;
module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, 0444);
MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false");
static bool g_zoned;
module_param_named(zoned, g_zoned, bool, S_IRUGO);
MODULE_PARM_DESC(zoned, "Make device as a host-managed zoned block device. Default: false");
static unsigned long g_zone_size = 256;
module_param_named(zone_size, g_zone_size, ulong, S_IRUGO);
MODULE_PARM_DESC(zone_size, "Zone size in MB when block device is zoned. Must be power-of-two: Default: 256");
static unsigned long g_zone_capacity;
module_param_named(zone_capacity, g_zone_capacity, ulong, 0444);
MODULE_PARM_DESC(zone_capacity, "Zone capacity in MB when block device is zoned. Can be less than or equal to zone size. Default: Zone size");
static unsigned int g_zone_nr_conv;
module_param_named(zone_nr_conv, g_zone_nr_conv, uint, 0444);
MODULE_PARM_DESC(zone_nr_conv, "Number of conventional zones when block device is zoned. Default: 0");
static unsigned int g_zone_max_open;
module_param_named(zone_max_open, g_zone_max_open, uint, 0444);
MODULE_PARM_DESC(zone_max_open, "Maximum number of open zones when block device is zoned. Default: 0 (no limit)");
static unsigned int g_zone_max_active;
module_param_named(zone_max_active, g_zone_max_active, uint, 0444);
MODULE_PARM_DESC(zone_max_active, "Maximum number of active zones when block device is zoned. Default: 0 (no limit)");
static struct nullb_device *null_alloc_dev(void);
static void null_free_dev(struct nullb_device *dev);
static void null_del_dev(struct nullb *nullb);
static int null_add_dev(struct nullb_device *dev);
static void null_free_device_storage(struct nullb_device *dev, bool is_cache);
static inline struct nullb_device *to_nullb_device(struct config_item *item)
{
return item ? container_of(item, struct nullb_device, item) : NULL;
}
static inline ssize_t nullb_device_uint_attr_show(unsigned int val, char *page)
{
return snprintf(page, PAGE_SIZE, "%u\n", val);
}
static inline ssize_t nullb_device_ulong_attr_show(unsigned long val,
char *page)
{
return snprintf(page, PAGE_SIZE, "%lu\n", val);
}
static inline ssize_t nullb_device_bool_attr_show(bool val, char *page)
{
return snprintf(page, PAGE_SIZE, "%u\n", val);
}
static ssize_t nullb_device_uint_attr_store(unsigned int *val,
const char *page, size_t count)
{
unsigned int tmp;
int result;
result = kstrtouint(page, 0, &tmp);
if (result < 0)
return result;
*val = tmp;
return count;
}
static ssize_t nullb_device_ulong_attr_store(unsigned long *val,
const char *page, size_t count)
{
int result;
unsigned long tmp;
result = kstrtoul(page, 0, &tmp);
if (result < 0)
return result;
*val = tmp;
return count;
}
static ssize_t nullb_device_bool_attr_store(bool *val, const char *page,
size_t count)
{
bool tmp;
int result;
result = kstrtobool(page, &tmp);
if (result < 0)
return result;
*val = tmp;
return count;
}
/* The following macro should only be used with TYPE = {uint, ulong, bool}. */
#define NULLB_DEVICE_ATTR(NAME, TYPE, APPLY) \
static ssize_t \
nullb_device_##NAME##_show(struct config_item *item, char *page) \
{ \
return nullb_device_##TYPE##_attr_show( \
to_nullb_device(item)->NAME, page); \
} \
static ssize_t \
nullb_device_##NAME##_store(struct config_item *item, const char *page, \
size_t count) \
{ \
int (*apply_fn)(struct nullb_device *dev, TYPE new_value) = APPLY;\
struct nullb_device *dev = to_nullb_device(item); \
TYPE new_value = 0; \
int ret; \
\
ret = nullb_device_##TYPE##_attr_store(&new_value, page, count);\
if (ret < 0) \
return ret; \
if (apply_fn) \
ret = apply_fn(dev, new_value); \
else if (test_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags)) \
ret = -EBUSY; \
if (ret < 0) \
return ret; \
dev->NAME = new_value; \
return count; \
} \
CONFIGFS_ATTR(nullb_device_, NAME);
static int nullb_apply_submit_queues(struct nullb_device *dev,
unsigned int submit_queues)
{
struct nullb *nullb = dev->nullb;
struct blk_mq_tag_set *set;
if (!nullb)
return 0;
/*
* Make sure that null_init_hctx() does not access nullb->queues[] past
* the end of that array.
*/
if (submit_queues > nr_cpu_ids)
return -EINVAL;
set = nullb->tag_set;
blk_mq_update_nr_hw_queues(set, submit_queues);
return set->nr_hw_queues == submit_queues ? 0 : -ENOMEM;
}
NULLB_DEVICE_ATTR(size, ulong, NULL);
NULLB_DEVICE_ATTR(completion_nsec, ulong, NULL);
NULLB_DEVICE_ATTR(submit_queues, uint, nullb_apply_submit_queues);
NULLB_DEVICE_ATTR(home_node, uint, NULL);
NULLB_DEVICE_ATTR(queue_mode, uint, NULL);
NULLB_DEVICE_ATTR(blocksize, uint, NULL);
NULLB_DEVICE_ATTR(irqmode, uint, NULL);
NULLB_DEVICE_ATTR(hw_queue_depth, uint, NULL);
NULLB_DEVICE_ATTR(index, uint, NULL);
NULLB_DEVICE_ATTR(blocking, bool, NULL);
NULLB_DEVICE_ATTR(use_per_node_hctx, bool, NULL);
NULLB_DEVICE_ATTR(memory_backed, bool, NULL);
NULLB_DEVICE_ATTR(discard, bool, NULL);
NULLB_DEVICE_ATTR(mbps, uint, NULL);
NULLB_DEVICE_ATTR(cache_size, ulong, NULL);
NULLB_DEVICE_ATTR(zoned, bool, NULL);
NULLB_DEVICE_ATTR(zone_size, ulong, NULL);
NULLB_DEVICE_ATTR(zone_capacity, ulong, NULL);
NULLB_DEVICE_ATTR(zone_nr_conv, uint, NULL);
NULLB_DEVICE_ATTR(zone_max_open, uint, NULL);
NULLB_DEVICE_ATTR(zone_max_active, uint, NULL);
static ssize_t nullb_device_power_show(struct config_item *item, char *page)
{
return nullb_device_bool_attr_show(to_nullb_device(item)->power, page);
}
static ssize_t nullb_device_power_store(struct config_item *item,
const char *page, size_t count)
{
struct nullb_device *dev = to_nullb_device(item);
bool newp = false;
ssize_t ret;
ret = nullb_device_bool_attr_store(&newp, page, count);
if (ret < 0)
return ret;
if (!dev->power && newp) {
if (test_and_set_bit(NULLB_DEV_FL_UP, &dev->flags))
return count;
if (null_add_dev(dev)) {
clear_bit(NULLB_DEV_FL_UP, &dev->flags);
return -ENOMEM;
}
set_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
dev->power = newp;
} else if (dev->power && !newp) {
if (test_and_clear_bit(NULLB_DEV_FL_UP, &dev->flags)) {
mutex_lock(&lock);
dev->power = newp;
null_del_dev(dev->nullb);
mutex_unlock(&lock);
}
clear_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
}
return count;
}
CONFIGFS_ATTR(nullb_device_, power);
static ssize_t nullb_device_badblocks_show(struct config_item *item, char *page)
{
struct nullb_device *t_dev = to_nullb_device(item);
return badblocks_show(&t_dev->badblocks, page, 0);
}
static ssize_t nullb_device_badblocks_store(struct config_item *item,
const char *page, size_t count)
{
struct nullb_device *t_dev = to_nullb_device(item);
char *orig, *buf, *tmp;
u64 start, end;
int ret;
orig = kstrndup(page, count, GFP_KERNEL);
if (!orig)
return -ENOMEM;
buf = strstrip(orig);
ret = -EINVAL;
if (buf[0] != '+' && buf[0] != '-')
goto out;
tmp = strchr(&buf[1], '-');
if (!tmp)
goto out;
*tmp = '\0';
ret = kstrtoull(buf + 1, 0, &start);
if (ret)
goto out;
ret = kstrtoull(tmp + 1, 0, &end);
if (ret)
goto out;
ret = -EINVAL;
if (start > end)
goto out;
/* enable badblocks */
cmpxchg(&t_dev->badblocks.shift, -1, 0);
if (buf[0] == '+')
ret = badblocks_set(&t_dev->badblocks, start,
end - start + 1, 1);
else
ret = badblocks_clear(&t_dev->badblocks, start,
end - start + 1);
if (ret == 0)
ret = count;
out:
kfree(orig);
return ret;
}
CONFIGFS_ATTR(nullb_device_, badblocks);
static struct configfs_attribute *nullb_device_attrs[] = {
&nullb_device_attr_size,
&nullb_device_attr_completion_nsec,
&nullb_device_attr_submit_queues,
&nullb_device_attr_home_node,
&nullb_device_attr_queue_mode,
&nullb_device_attr_blocksize,
&nullb_device_attr_irqmode,
&nullb_device_attr_hw_queue_depth,
&nullb_device_attr_index,
&nullb_device_attr_blocking,
&nullb_device_attr_use_per_node_hctx,
&nullb_device_attr_power,
&nullb_device_attr_memory_backed,
&nullb_device_attr_discard,
&nullb_device_attr_mbps,
&nullb_device_attr_cache_size,
&nullb_device_attr_badblocks,
&nullb_device_attr_zoned,
&nullb_device_attr_zone_size,
&nullb_device_attr_zone_capacity,
&nullb_device_attr_zone_nr_conv,
&nullb_device_attr_zone_max_open,
&nullb_device_attr_zone_max_active,
NULL,
};
static void nullb_device_release(struct config_item *item)
{
struct nullb_device *dev = to_nullb_device(item);
null_free_device_storage(dev, false);
null_free_dev(dev);
}
static struct configfs_item_operations nullb_device_ops = {
.release = nullb_device_release,
};
static const struct config_item_type nullb_device_type = {
.ct_item_ops = &nullb_device_ops,
.ct_attrs = nullb_device_attrs,
.ct_owner = THIS_MODULE,
};
static struct
config_item *nullb_group_make_item(struct config_group *group, const char *name)
{
struct nullb_device *dev;
dev = null_alloc_dev();
if (!dev)
return ERR_PTR(-ENOMEM);
config_item_init_type_name(&dev->item, name, &nullb_device_type);
return &dev->item;
}
static void
nullb_group_drop_item(struct config_group *group, struct config_item *item)
{
struct nullb_device *dev = to_nullb_device(item);
if (test_and_clear_bit(NULLB_DEV_FL_UP, &dev->flags)) {
mutex_lock(&lock);
dev->power = false;
null_del_dev(dev->nullb);
mutex_unlock(&lock);
}
config_item_put(item);
}
static ssize_t memb_group_features_show(struct config_item *item, char *page)
{
return snprintf(page, PAGE_SIZE,
"memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size,zone_capacity,zone_nr_conv,zone_max_open,zone_max_active\n");
}
CONFIGFS_ATTR_RO(memb_group_, features);
static struct configfs_attribute *nullb_group_attrs[] = {
&memb_group_attr_features,
NULL,
};
static struct configfs_group_operations nullb_group_ops = {
.make_item = nullb_group_make_item,
.drop_item = nullb_group_drop_item,
};
static const struct config_item_type nullb_group_type = {
.ct_group_ops = &nullb_group_ops,
.ct_attrs = nullb_group_attrs,
.ct_owner = THIS_MODULE,
};
static struct configfs_subsystem nullb_subsys = {
.su_group = {
.cg_item = {
.ci_namebuf = "nullb",
.ci_type = &nullb_group_type,
},
},
};
static inline int null_cache_active(struct nullb *nullb)
{
return test_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags);
}
static struct nullb_device *null_alloc_dev(void)
{
struct nullb_device *dev;
dev = kzalloc(sizeof(*dev), GFP_KERNEL);
if (!dev)
return NULL;
INIT_RADIX_TREE(&dev->data, GFP_ATOMIC);
INIT_RADIX_TREE(&dev->cache, GFP_ATOMIC);
if (badblocks_init(&dev->badblocks, 0)) {
kfree(dev);
return NULL;
}
dev->size = g_gb * 1024;
dev->completion_nsec = g_completion_nsec;
dev->submit_queues = g_submit_queues;
dev->home_node = g_home_node;
dev->queue_mode = g_queue_mode;
dev->blocksize = g_bs;
dev->irqmode = g_irqmode;
dev->hw_queue_depth = g_hw_queue_depth;
dev->blocking = g_blocking;
dev->use_per_node_hctx = g_use_per_node_hctx;
dev->zoned = g_zoned;
dev->zone_size = g_zone_size;
dev->zone_capacity = g_zone_capacity;
dev->zone_nr_conv = g_zone_nr_conv;
dev->zone_max_open = g_zone_max_open;
dev->zone_max_active = g_zone_max_active;
return dev;
}
static void null_free_dev(struct nullb_device *dev)
{
if (!dev)
return;
null_free_zoned_dev(dev);
badblocks_exit(&dev->badblocks);
kfree(dev);
}
static void put_tag(struct nullb_queue *nq, unsigned int tag)
{
clear_bit_unlock(tag, nq->tag_map);
if (waitqueue_active(&nq->wait))
wake_up(&nq->wait);
}
static unsigned int get_tag(struct nullb_queue *nq)
{
unsigned int tag;
do {
tag = find_first_zero_bit(nq->tag_map, nq->queue_depth);
if (tag >= nq->queue_depth)
return -1U;
} while (test_and_set_bit_lock(tag, nq->tag_map));
return tag;
}
static void free_cmd(struct nullb_cmd *cmd)
{
put_tag(cmd->nq, cmd->tag);
}
static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer);
static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq)
{
struct nullb_cmd *cmd;
unsigned int tag;
tag = get_tag(nq);
if (tag != -1U) {
cmd = &nq->cmds[tag];
cmd->tag = tag;
cmd->error = BLK_STS_OK;
cmd->nq = nq;
if (nq->dev->irqmode == NULL_IRQ_TIMER) {
hrtimer_init(&cmd->timer, CLOCK_MONOTONIC,
HRTIMER_MODE_REL);
cmd->timer.function = null_cmd_timer_expired;
}
return cmd;
}
return NULL;
}
static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, int can_wait)
{
struct nullb_cmd *cmd;
DEFINE_WAIT(wait);
cmd = __alloc_cmd(nq);
if (cmd || !can_wait)
return cmd;
do {
prepare_to_wait(&nq->wait, &wait, TASK_UNINTERRUPTIBLE);
cmd = __alloc_cmd(nq);
if (cmd)
break;
io_schedule();
} while (1);
finish_wait(&nq->wait, &wait);
return cmd;
}
static void end_cmd(struct nullb_cmd *cmd)
{
int queue_mode = cmd->nq->dev->queue_mode;
switch (queue_mode) {
case NULL_Q_MQ:
blk_mq_end_request(cmd->rq, cmd->error);
return;
case NULL_Q_BIO:
cmd->bio->bi_status = cmd->error;
bio_endio(cmd->bio);
break;
}
free_cmd(cmd);
}
static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
{
end_cmd(container_of(timer, struct nullb_cmd, timer));
return HRTIMER_NORESTART;
}
static void null_cmd_end_timer(struct nullb_cmd *cmd)
{
ktime_t kt = cmd->nq->dev->completion_nsec;
hrtimer_start(&cmd->timer, kt, HRTIMER_MODE_REL);
}
static void null_complete_rq(struct request *rq)
{
end_cmd(blk_mq_rq_to_pdu(rq));
}
static struct nullb_page *null_alloc_page(gfp_t gfp_flags)
{
struct nullb_page *t_page;
t_page = kmalloc(sizeof(struct nullb_page), gfp_flags);
if (!t_page)
goto out;
t_page->page = alloc_pages(gfp_flags, 0);
if (!t_page->page)
goto out_freepage;
memset(t_page->bitmap, 0, sizeof(t_page->bitmap));
return t_page;
out_freepage:
kfree(t_page);
out:
return NULL;
}
static void null_free_page(struct nullb_page *t_page)
{
__set_bit(NULLB_PAGE_FREE, t_page->bitmap);
if (test_bit(NULLB_PAGE_LOCK, t_page->bitmap))
return;
__free_page(t_page->page);
kfree(t_page);
}
static bool null_page_empty(struct nullb_page *page)
{
int size = MAP_SZ - 2;
return find_first_bit(page->bitmap, size) == size;
}
static void null_free_sector(struct nullb *nullb, sector_t sector,
bool is_cache)
{
unsigned int sector_bit;
u64 idx;
struct nullb_page *t_page, *ret;
struct radix_tree_root *root;
root = is_cache ? &nullb->dev->cache : &nullb->dev->data;
idx = sector >> PAGE_SECTORS_SHIFT;
sector_bit = (sector & SECTOR_MASK);
t_page = radix_tree_lookup(root, idx);
if (t_page) {
__clear_bit(sector_bit, t_page->bitmap);
if (null_page_empty(t_page)) {
ret = radix_tree_delete_item(root, idx, t_page);
WARN_ON(ret != t_page);
null_free_page(ret);
if (is_cache)
nullb->dev->curr_cache -= PAGE_SIZE;
}
}
}
static struct nullb_page *null_radix_tree_insert(struct nullb *nullb, u64 idx,
struct nullb_page *t_page, bool is_cache)
{
struct radix_tree_root *root;
root = is_cache ? &nullb->dev->cache : &nullb->dev->data;
if (radix_tree_insert(root, idx, t_page)) {
null_free_page(t_page);
t_page = radix_tree_lookup(root, idx);
WARN_ON(!t_page || t_page->page->index != idx);
} else if (is_cache)
nullb->dev->curr_cache += PAGE_SIZE;
return t_page;
}
static void null_free_device_storage(struct nullb_device *dev, bool is_cache)
{
unsigned long pos = 0;
int nr_pages;
struct nullb_page *ret, *t_pages[FREE_BATCH];
struct radix_tree_root *root;
root = is_cache ? &dev->cache : &dev->data;
do {
int i;
nr_pages = radix_tree_gang_lookup(root,
(void **)t_pages, pos, FREE_BATCH);
for (i = 0; i < nr_pages; i++) {
pos = t_pages[i]->page->index;
ret = radix_tree_delete_item(root, pos, t_pages[i]);
WARN_ON(ret != t_pages[i]);
null_free_page(ret);
}
pos++;
} while (nr_pages == FREE_BATCH);
if (is_cache)
dev->curr_cache = 0;
}
static struct nullb_page *__null_lookup_page(struct nullb *nullb,
sector_t sector, bool for_write, bool is_cache)
{
unsigned int sector_bit;
u64 idx;
struct nullb_page *t_page;
struct radix_tree_root *root;
idx = sector >> PAGE_SECTORS_SHIFT;
sector_bit = (sector & SECTOR_MASK);
root = is_cache ? &nullb->dev->cache : &nullb->dev->data;
t_page = radix_tree_lookup(root, idx);
WARN_ON(t_page && t_page->page->index != idx);
if (t_page && (for_write || test_bit(sector_bit, t_page->bitmap)))
return t_page;
return NULL;
}
static struct nullb_page *null_lookup_page(struct nullb *nullb,
sector_t sector, bool for_write, bool ignore_cache)
{
struct nullb_page *page = NULL;
if (!ignore_cache)
page = __null_lookup_page(nullb, sector, for_write, true);
if (page)
return page;
return __null_lookup_page(nullb, sector, for_write, false);
}
static struct nullb_page *null_insert_page(struct nullb *nullb,
sector_t sector, bool ignore_cache)
__releases(&nullb->lock)
__acquires(&nullb->lock)
{
u64 idx;
struct nullb_page *t_page;
t_page = null_lookup_page(nullb, sector, true, ignore_cache);
if (t_page)
return t_page;
spin_unlock_irq(&nullb->lock);
t_page = null_alloc_page(GFP_NOIO);
if (!t_page)
goto out_lock;
if (radix_tree_preload(GFP_NOIO))
goto out_freepage;
spin_lock_irq(&nullb->lock);
idx = sector >> PAGE_SECTORS_SHIFT;
t_page->page->index = idx;
t_page = null_radix_tree_insert(nullb, idx, t_page, !ignore_cache);
radix_tree_preload_end();
return t_page;
out_freepage:
null_free_page(t_page);
out_lock:
spin_lock_irq(&nullb->lock);
return null_lookup_page(nullb, sector, true, ignore_cache);
}
static int null_flush_cache_page(struct nullb *nullb, struct nullb_page *c_page)
{
int i;
unsigned int offset;
u64 idx;
struct nullb_page *t_page, *ret;
void *dst, *src;
idx = c_page->page->index;
t_page = null_insert_page(nullb, idx << PAGE_SECTORS_SHIFT, true);
__clear_bit(NULLB_PAGE_LOCK, c_page->bitmap);
if (test_bit(NULLB_PAGE_FREE, c_page->bitmap)) {
null_free_page(c_page);
if (t_page && null_page_empty(t_page)) {
ret = radix_tree_delete_item(&nullb->dev->data,
idx, t_page);
null_free_page(t_page);
}
return 0;
}
if (!t_page)
return -ENOMEM;
src = kmap_atomic(c_page->page);
dst = kmap_atomic(t_page->page);
for (i = 0; i < PAGE_SECTORS;
i += (nullb->dev->blocksize >> SECTOR_SHIFT)) {
if (test_bit(i, c_page->bitmap)) {
offset = (i << SECTOR_SHIFT);
memcpy(dst + offset, src + offset,
nullb->dev->blocksize);
__set_bit(i, t_page->bitmap);
}
}
kunmap_atomic(dst);
kunmap_atomic(src);
ret = radix_tree_delete_item(&nullb->dev->cache, idx, c_page);
null_free_page(ret);
nullb->dev->curr_cache -= PAGE_SIZE;
return 0;
}
static int null_make_cache_space(struct nullb *nullb, unsigned long n)
{
int i, err, nr_pages;
struct nullb_page *c_pages[FREE_BATCH];
unsigned long flushed = 0, one_round;
again:
if ((nullb->dev->cache_size * 1024 * 1024) >
nullb->dev->curr_cache + n || nullb->dev->curr_cache == 0)
return 0;
nr_pages = radix_tree_gang_lookup(&nullb->dev->cache,
(void **)c_pages, nullb->cache_flush_pos, FREE_BATCH);
/*
* nullb_flush_cache_page could unlock before using the c_pages. To
* avoid race, we don't allow page free
*/
for (i = 0; i < nr_pages; i++) {
nullb->cache_flush_pos = c_pages[i]->page->index;
/*
* We found the page which is being flushed to disk by other
* threads
*/
if (test_bit(NULLB_PAGE_LOCK, c_pages[i]->bitmap))
c_pages[i] = NULL;
else
__set_bit(NULLB_PAGE_LOCK, c_pages[i]->bitmap);
}
one_round = 0;
for (i = 0; i < nr_pages; i++) {
if (c_pages[i] == NULL)
continue;
err = null_flush_cache_page(nullb, c_pages[i]);
if (err)
return err;
one_round++;
}
flushed += one_round << PAGE_SHIFT;
if (n > flushed) {
if (nr_pages == 0)
nullb->cache_flush_pos = 0;
if (one_round == 0) {
/* give other threads a chance */
spin_unlock_irq(&nullb->lock);
spin_lock_irq(&nullb->lock);
}
goto again;
}
return 0;
}
static int copy_to_nullb(struct nullb *nullb, struct page *source,