summaryrefslogtreecommitdiffstats
path: root/drivers/base/node.c
blob: ec8bb24a5a227a80173c58d299da925bd48010d6 (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
// SPDX-License-Identifier: GPL-2.0
/*
 * Basic Node interface support
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/memory.h>
#include <linux/vmstat.h>
#include <linux/notifier.h>
#include <linux/node.h>
#include <linux/hugetlb.h>
#include <linux/compaction.h>
#include <linux/cpumask.h>
#include <linux/topology.h>
#include <linux/nodemask.h>
#include <linux/cpu.h>
#include <linux/device.h>
#include <linux/pm_runtime.h>
#include <linux/swap.h>
#include <linux/slab.h>

static struct bus_type node_subsys = {
	.name = "node",
	.dev_name = "node",
};

static inline ssize_t cpumap_read(struct file *file, struct kobject *kobj,
				  struct bin_attribute *attr, char *buf,
				  loff_t off, size_t count)
{
	struct device *dev = kobj_to_dev(kobj);
	struct node *node_dev = to_node(dev);
	cpumask_var_t mask;
	ssize_t n;

	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
		return 0;

	cpumask_and(mask, cpumask_of_node(node_dev->dev.id), cpu_online_mask);
	n = cpumap_print_bitmask_to_buf(buf, mask, off, count);
	free_cpumask_var(mask);

	return n;
}

static BIN_ATTR_RO(cpumap, 0);

static inline ssize_t cpulist_read(struct file *file, struct kobject *kobj,
				   struct bin_attribute *attr, char *buf,
				   loff_t off, size_t count)
{
	struct device *dev = kobj_to_dev(kobj);
	struct node *node_dev = to_node(dev);
	cpumask_var_t mask;
	ssize_t n;

	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
		return 0;

	cpumask_and(mask, cpumask_of_node(node_dev->dev.id), cpu_online_mask);
	n = cpumap_print_list_to_buf(buf, mask, off, count);
	free_cpumask_var(mask);

	return n;
}

static BIN_ATTR_RO(cpulist, 0);

/**
 * struct node_access_nodes - Access class device to hold user visible
 * 			      relationships to other nodes.
 * @dev:	Device for this memory access class
 * @list_node:	List element in the node's access list
 * @access:	The access class rank
 * @hmem_attrs: Heterogeneous memory performance attributes
 */
struct node_access_nodes {
	struct device		dev;
	struct list_head	list_node;
	unsigned int		access;
#ifdef CONFIG_HMEM_REPORTING
	struct node_hmem_attrs	hmem_attrs;
#endif
};
#define to_access_nodes(dev) container_of(dev, struct node_access_nodes, dev)

static struct attribute *node_init_access_node_attrs[] = {
	NULL,
};

static struct attribute *node_targ_access_node_attrs[] = {
	NULL,
};

static const struct attribute_group initiators = {
	.name	= "initiators",
	.attrs	= node_init_access_node_attrs,
};

static const struct attribute_group targets = {
	.name	= "targets",
	.attrs	= node_targ_access_node_attrs,
};

static const struct attribute_group *node_access_node_groups[] = {
	&initiators,
	&targets,
	NULL,
};

static void node_remove_accesses(struct node *node)
{
	struct node_access_nodes *c, *cnext;

	list_for_each_entry_safe(c, cnext, &node->access_list, list_node) {
		list_del(&c->list_node);
		device_unregister(&c->dev);
	}
}

static void node_access_release(struct device *dev)
{
	kfree(to_access_nodes(dev));
}

static struct node_access_nodes *node_init_node_access(struct node *node,
						       unsigned int access)
{
	struct node_access_nodes *access_node;
	struct device *dev;

	list_for_each_entry(access_node, &node->access_list, list_node)
		if (access_node->access == access)
			return access_node;

	access_node = kzalloc(sizeof(*access_node), GFP_KERNEL);
	if (!access_node)
		return NULL;

	access_node->access = access;
	dev = &access_node->dev;
	dev->parent = &node->dev;
	dev->release = node_access_release;
	dev->groups = node_access_node_groups;
	if (dev_set_name(dev, "access%u", access))
		goto free;

	if (device_register(dev))
		goto free_name;

	pm_runtime_no_callbacks(dev);
	list_add_tail(&access_node->list_node, &node->access_list);
	return access_node;
free_name:
	kfree_const(dev->kobj.name);
free:
	kfree(access_node);
	return NULL;
}

#ifdef CONFIG_HMEM_REPORTING
#define ACCESS_ATTR(name)						\
static ssize_t name##_show(struct device *dev,				\
			   struct device_attribute *attr,		\
			   char *buf)					\
{									\
	return sysfs_emit(buf, "%u\n",					\
			  to_access_nodes(dev)->hmem_attrs.name);	\
}									\
static DEVICE_ATTR_RO(name)

ACCESS_ATTR(read_bandwidth);
ACCESS_ATTR(read_latency);
ACCESS_ATTR(write_bandwidth);
ACCESS_ATTR(write_latency);

static struct attribute *access_attrs[] = {
	&dev_attr_read_bandwidth.attr,
	&dev_attr_read_latency.attr,
	&dev_attr_write_bandwidth.attr,
	&dev_attr_write_latency.attr,
	NULL,
};

/**
 * node_set_perf_attrs - Set the performance values for given access class
 * @nid: Node identifier to be set
 * @hmem_attrs: Heterogeneous memory performance attributes
 * @access: The access class the for the given attributes
 */
void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
			 unsigned int access)
{
	struct node_access_nodes *c;
	struct node *node;
	int i;

	if (WARN_ON_ONCE(!node_online(nid)))
		return;

	node = node_devices[nid];
	c = node_init_node_access(node, access);
	if (!c)
		return;

	c->hmem_attrs = *hmem_attrs;
	for (i = 0; access_attrs[i] != NULL; i++) {
		if (sysfs_add_file_to_group(&c->dev.kobj, access_attrs[i],
					    "initiators")) {
			pr_info("failed to add performance attribute to node %d\n",
				nid);
			break;
		}
	}
}

/**
 * struct node_cache_info - Internal tracking for memory node caches
 * @dev:	Device represeting the cache level
 * @node:	List element for tracking in the node
 * @cache_attrs:Attributes for this cache level
 */
struct node_cache_info {
	struct device dev;
	struct list_head node;
	struct node_cache_attrs cache_attrs;
};
#define to_cache_info(device) container_of(device, struct node_cache_info, dev)

#define CACHE_ATTR(name, fmt) 						\
static ssize_t name##_show(struct device *dev,				\
			   struct device_attribute *attr,		\
			   char *buf)					\
{									\
	return sysfs_emit(buf, fmt "\n",				\
			  to_cache_info(dev)->cache_attrs.name);	\
}									\
static DEVICE_ATTR_RO(name);

CACHE_ATTR(size, "%llu")
CACHE_ATTR(line_size, "%u")
CACHE_ATTR(indexing, "%u")
CACHE_ATTR(write_policy, "%u")

static struct attribute *cache_attrs[] = {
	&dev_attr_indexing.attr,
	&dev_attr_size.attr,
	&dev_attr_line_size.attr,
	&dev_attr_write_policy.attr,
	NULL,
};
ATTRIBUTE_GROUPS(cache);

static void node_cache_release(struct device *dev)
{
	kfree(dev);
}

static void node_cacheinfo_release(struct device *dev)
{
	struct node_cache_info *info = to_cache_info(dev);
	kfree(info);
}

static void node_init_cache_dev(struct node *node)
{
	struct device *dev;

	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
	if (!dev)
		return;

	device_initialize(dev);
	dev->parent = &node->dev;
	dev->release = node_cache_release;
	if (dev_set_name(dev, "memory_side_cache"))
		goto put_device;

	if (device_add(dev))
		goto put_device;

	pm_runtime_no_callbacks(dev);
	node->cache_dev = dev;
	return;
put_device:
	put_device(dev);
}

/**
 * node_add_cache() - add cache attribute to a memory node
 * @nid: Node identifier that has new cache attributes
 * @cache_attrs: Attributes for the cache being added
 */
void node_add_cache(unsigned int nid, struct node_cache_attrs *cache_attrs)
{
	struct node_cache_info *info;
	struct device *dev;
	struct node *node;

	if (!node_online(nid) || !node_devices[nid])
		return;

	node = node_devices[nid];
	list_for_each_entry(info, &node->cache_attrs, node) {
		if (info->cache_attrs.level == cache_attrs->level) {
			dev_warn(&node->dev,
				"attempt to add duplicate cache level:%d\n",
				cache_attrs->level);
			return;
		}
	}

	if (!node->cache_dev)
		node_init_cache_dev(node);
	if (!node->cache_dev)
		return;

	info = kzalloc(sizeof(*info), GFP_KERNEL);
	if (!info)
		return;

	dev = &info->dev;
	device_initialize(dev);
	dev->parent = node->cache_dev;
	dev->release = node_cacheinfo_release;
	dev->groups = cache_groups;
	if (dev_set_name(dev, "index%d", cache_attrs->level))
		goto put_device;

	info->cache_attrs = *cache_attrs;
	if (device_add(dev)) {
		dev_warn(&node->dev, "failed to add cache level:%d\n",
			 cache_attrs->level);
		goto put_device;
	}
	pm_runtime_no_callbacks(dev);
	list_add_tail(&info->node, &node->cache_attrs);
	return;
put_device:
	put_device(dev);
}

static void node_remove_caches(struct node *node)
{
	struct node_cache_info *info, *next;

	if (!node->cache_dev)
		return;

	list_for_each_entry_safe(info, next, &node->cache_attrs, node) {
		list_del(&info->node);
		device_unregister(&info->dev);
	}
	device_unregister(node->cache_dev);
}

static void node_init_caches(unsigned int nid)
{
	INIT_LIST_HEAD(&node_devices[nid]->cache_attrs);
}
#else
static void node_init_caches(unsigned int nid) { }
static void node_remove_caches(struct node *node) { }
#endif

#define K(x) ((x) << (PAGE_SHIFT - 10))
static ssize_t node_read_meminfo(struct device *dev,
			struct device_attribute *attr, char *buf)
{
	int len = 0;
	int nid = dev->id;
	struct pglist_data *pgdat = NODE_DATA(nid);
	struct sysinfo i;
	unsigned long sreclaimable, sunreclaimable;
	unsigned long swapcached = 0;

	si_meminfo_node(&i, nid);
	sreclaimable = node_page_state_pages(pgdat, NR_SLAB_RECLAIMABLE_B);
	sunreclaimable = node_page_state_pages(pgdat, NR_SLAB_UNRECLAIMABLE_B);
#ifdef CONFIG_SWAP
	swapcached = node_page_state_pages(pgdat, NR_SWAPCACHE);
#endif
	len = sysfs_emit_at(buf, len,
			    "Node %d MemTotal:       %8lu kB\n"
			    "Node %d MemFree:        %8lu kB\n"
			    "Node %d MemUsed:        %8lu kB\n"
			    "Node %d SwapCached:     %8lu kB\n"
			    "Node %d Active:         %8lu kB\n"
			    "Node %d Inactive:       %8lu kB\n"
			    "Node %d Active(anon):   %8lu kB\n"
			    "Node %d Inactive(anon): %8lu kB\n"
			    "Node %d Active(file):   %8lu kB\n"
			    "Node %d Inactive(file): %8lu kB\n"
			    "Node %d Unevictable:    %8lu kB\n"
			    "Node %d Mlocked:        %8lu kB\n",
			    nid, K(i.totalram),
			    nid, K(i.freeram),
			    nid, K(i.totalram - i.freeram),
			    nid, K(swapcached),
			    nid, K(node_page_state(pgdat, NR_ACTIVE_ANON) +
				   node_page_state(pgdat, NR_ACTIVE_FILE)),
			    nid, K(node_page_state(pgdat, NR_INACTIVE_ANON) +
				   node_page_state(pgdat, NR_INACTIVE_FILE)),
			    nid, K(node_page_state(pgdat, NR_ACTIVE_ANON)),
			    nid, K(node_page_state(pgdat, NR_INACTIVE_ANON)),
			    nid, K(node_page_state(pgdat, NR_ACTIVE_FILE)),
			    nid, K(node_page_state(pgdat, NR_INACTIVE_FILE)),
			    nid, K(node_page_state(pgdat, NR_UNEVICTABLE)),
			    nid, K(sum_zone_node_page_state(nid, NR_MLOCK)));

#ifdef CONFIG_HIGHMEM
	len += sysfs_emit_at(buf, len,
			     "Node %d HighTotal:      %8lu kB\n"
			     "Node %d HighFree:       %8lu kB\n"
			     "Node %d LowTotal:       %8lu kB\n"
			     "Node %d LowFree:        %8lu kB\n",
			     nid, K(i.totalhigh),
			     nid, K(i.freehigh),
			     nid, K(i.totalram - i.totalhigh),
			     nid, K(i.freeram - i.freehigh));
#endif
	len += sysfs_emit_at(buf, len,
			     "Node %d Dirty:          %8lu kB\n"
			     "Node %d Writeback:      %8lu kB\n"
			     "Node %d FilePages:      %8lu kB\n"
			     "Node %d Mapped:         %8lu kB\n"
			     "Node %d AnonPages:      %8lu kB\n"
			     "Node %d Shmem:          %8lu kB\n"
			     "Node %d KernelStack:    %8lu kB\n"
#ifdef CONFIG_SHADOW_CALL_STACK
			     "Node %d ShadowCallStack:%8lu kB\n"
#endif
			     "Node %d PageTables:     %8lu kB\n"
			     "Node %d NFS_Unstable:   %8lu kB\n"
			     "Node %d Bounce:         %8lu kB\n"
			     "Node %d WritebackTmp:   %8lu kB\n"
			     "Node %d KReclaimable:   %8lu kB\n"
			     "Node %d Slab:           %8lu kB\n"
			     "Node %d SReclaimable:   %8lu kB\n"
			     "Node %d SUnreclaim:     %8lu kB\n"
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
			     "Node %d AnonHugePages:  %8lu kB\n"
			     "Node %d ShmemHugePages: %8lu kB\n"
			     "Node %d ShmemPmdMapped: %8lu kB\n"
			     "Node %d FileHugePages: %8lu kB\n"
			     "Node %d FilePmdMapped: %8lu kB\n"
#endif
			     ,
			     nid, K(node_page_state(pgdat, NR_FILE_DIRTY)),
			     nid, K(node_page_state(pgdat, NR_WRITEBACK)),
			     nid, K(node_page_state(pgdat, NR_FILE_PAGES)),
			     nid, K(node_page_state(pgdat, NR_FILE_MAPPED)),
			     nid, K(node_page_state(pgdat, NR_ANON_MAPPED)),
			     nid, K(i.sharedram),
			     nid, node_page_state(pgdat, NR_KERNEL_STACK_KB),
#ifdef CONFIG_SHADOW_CALL_STACK
			     nid, node_page_state(pgdat, NR_KERNEL_SCS_KB),
#endif
			     nid, K(node_page_state(pgdat, NR_PAGETABLE)),
			     nid, 0UL,
			     nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
			     nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
			     nid, K(sreclaimable +
				    node_page_state(pgdat, NR_KERNEL_MISC_RECLAIMABLE)),
			     nid, K(sreclaimable + sunreclaimable),
			     nid, K(sreclaimable),
			     nid, K(sunreclaimable)
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
			     ,
			     nid, K(node_page_state(pgdat, NR_ANON_THPS)),
			     nid, K(node_page_state(pgdat, NR_SHMEM_THPS)),
			     nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)),
			     nid, K(node_page_state(pgdat, NR_FILE_THPS)),
			     nid, K(node_page_state(pgdat, NR_FILE_PMDMAPPED))
#endif
			    );
	len += hugetlb_report_node_meminfo(buf, len, nid);
	return len;
}

#undef K
static DEVICE_ATTR(meminfo, 0444, node_read_meminfo, NULL);

static ssize_t node_read_numastat(struct device *dev,
				  struct device_attribute *attr, char *buf)
{
	fold_vm_numa_events();
	return sysfs_emit(buf,
			  "numa_hit %lu\n"
			  "numa_miss %lu\n"
			  "numa_foreign %lu\n"
			  "interleave_hit %lu\n"
			  "local_node %lu\n"
			  "other_node %lu\n",
			  sum_zone_numa_event_state(dev->id, NUMA_HIT),
			  sum_zone_numa_event_state(dev->id, NUMA_MISS),
			  sum_zone_numa_event_state(dev->id, NUMA_FOREIGN),
			  sum_zone_numa_event_state(dev->id, NUMA_INTERLEAVE_HIT),
			  sum_zone_numa_event_state(dev->id, NUMA_LOCAL),
			  sum_zone_numa_event_state(dev->id, NUMA_OTHER));
}
static DEVICE_ATTR(numastat, 0444, node_read_numastat, NULL);

static ssize_t node_read_vmstat(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	int nid = dev->id;
	struct pglist_data *pgdat = NODE_DATA(nid);
	int i;
	int len = 0;

	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
		len += sysfs_emit_at(buf, len, "%s %lu\n",
				     zone_stat_name(i),
				     sum_zone_node_page_state(nid, i));

#ifdef CONFIG_NUMA
	fold_vm_numa_events();
	for (i = 0; i < NR_VM_NUMA_EVENT_ITEMS; i++)
		len += sysfs_emit_at(buf, len, "%s %lu\n",
				     numa_stat_name(i),
				     sum_zone_numa_event_state(nid, i));

#endif
	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
		unsigned long pages = node_page_state_pages(pgdat, i);

		if (vmstat_item_print_in_thp(i))
			pages /= HPAGE_PMD_NR;
		len += sysfs_emit_at(buf, len, "%s %lu\n", node_stat_name(i),
				     pages);
	}

	return len;
}
static DEVICE_ATTR(vmstat, 0444, node_read_vmstat, NULL);

static ssize_t node_read_distance(struct device *dev,
				  struct device_attribute *attr, char *buf)
{
	int nid = dev->id;
	int len = 0;
	int i;

	/*
	 * buf is currently PAGE_SIZE in length and each node needs 4 chars
	 * at the most (distance + space or newline).
	 */
	BUILD_BUG_ON(MAX_NUMNODES * 4 > PAGE_SIZE);

	for_each_online_node(i) {
		len += sysfs_emit_at(buf, len, "%s%d",
				     i ? " " : "", node_distance(nid, i));
	}

	len += sysfs_emit_at(buf, len, "\n");
	return len;
}
static DEVICE_ATTR(distance, 0444, node_read_distance, NULL);

static struct attribute *node_dev_attrs[] = {
	&dev_attr_meminfo.attr,
	&dev_attr_numastat.attr,
	&dev_attr_distance.attr,
	&dev_attr_vmstat.attr,
	NULL
};

static struct bin_attribute *node_dev_bin_attrs[] = {
	&bin_attr_cpumap,
	&bin_attr_cpulist,
	NULL
};

static const struct attribute_group node_dev_group = {
	.attrs = node_dev_attrs,
	.bin_attrs = node_dev_bin_attrs
};

static const struct attribute_group *node_dev_groups[] = {
	&node_dev_group,
#ifdef CONFIG_HAVE_ARCH_NODE_DEV_GROUP
	&arch_node_dev_group,
#endif
	NULL
};

#ifdef CONFIG_HUGETLBFS
/*
 * hugetlbfs per node attributes registration interface:
 * When/if hugetlb[fs] subsystem initializes [sometime after this module],
 * it will register its per node attributes for all online nodes with
 * memory.  It will also call register_hugetlbfs_with_node(), below, to
 * register its attribute registration functions with this node driver.
 * Once these hooks have been initialized, the node driver will call into
 * the hugetlb module to [un]register attributes for hot-plugged nodes.
 */
static node_registration_func_t __hugetlb_register_node;
static node_registration_func_t __hugetlb_unregister_node;

static inline bool hugetlb_register_node(struct node *node)
{
	if (__hugetlb_register_node &&
			node_state(node->dev.id, N_MEMORY)) {
		__hugetlb_register_node(node);
		return true;
	}
	return false;
}

static inline void hugetlb_unregister_node(struct node *node)
{
	if (__hugetlb_unregister_node)
		__hugetlb_unregister_node(node);
}

void register_hugetlbfs_with_node(node_registration_func_t doregister,
				  node_registration_func_t unregister)
{
	__hugetlb_register_node   = doregister;
	__hugetlb_unregister_node = unregister;
}
#else
static inline void hugetlb_register_node(struct node *node) {}

static inline void hugetlb_unregister_node(struct node *node) {}
#endif

static void node_device_release(struct device *dev)
{
	struct node *node = to_node(dev);

#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_HUGETLBFS)
	/*
	 * We schedule the work only when a memory section is
	 * onlined/offlined on this node. When we come here,
	 * all the memory on this node has been offlined,
	 * so we won't enqueue new work to this work.
	 *
	 * The work is using node->node_work, so we should
	 * flush work before freeing the memory.
	 */
	flush_work(&node->node_work);
#endif
	kfree(node);
}

/*
 * register_node - Setup a sysfs device for a node.
 * @num - Node number to use when creating the device.
 *
 * Initialize and register the node device.
 */
static int register_node(struct node *node, int num)
{
	int error;

	node->dev.id = num;
	node->dev.bus = &node_subsys;
	node->dev.release = node_device_release;
	node->dev.groups = node_dev_groups;
	error = device_register(&node->dev);

	if (error)
		put_device(&node->dev);
	else {
		hugetlb_register_node(node);

		compaction_register_node(node);
	}
	return error;
}

/**
 * unregister_node - unregister a node device
 * @node: node going away
 *
 * Unregisters a node device @node.  All the devices on the node must be
 * unregistered before calling this function.
 */
void unregister_node(struct node *node)
{
	hugetlb_unregister_node(node);		/* no-op, if memoryless node */
	node_remove_accesses(node);
	node_remove_caches(node);
	device_unregister(&node->dev);
}

struct node *node_devices[MAX_NUMNODES];

/*
 * register cpu under node
 */
int register_cpu_under_node(unsigned int cpu, unsigned int nid)
{
	int ret;
	struct device *obj;

	if (!node_online(nid))
		return 0;

	obj = get_cpu_device(cpu);
	if (!obj)
		return 0;

	ret = sysfs_create_link(&node_devices[nid]->dev.kobj,
				&obj->kobj,
				kobject_name(&obj->kobj));
	if (ret)
		return ret;

	return sysfs_create_link(&obj->kobj,
				 &node_devices[nid]->dev.kobj,
				 kobject_name(&node_devices[nid]->dev.kobj));
}

/**
 * register_memory_node_under_compute_node - link memory node to its compute
 *					     node for a given access class.
 * @mem_nid:	Memory node number
 * @cpu_nid:	Cpu  node number
 * @access:	Access class to register
 *
 * Description:
 * 	For use with platforms that may have separate memory and compute nodes.
 * 	This function will export node relationships linking which memory
 * 	initiator nodes can access memory targets at a given ranked access
 * 	class.
 */
int register_memory_node_under_compute_node(unsigned int mem_nid,
					    unsigned int cpu_nid,
					    unsigned int access)
{
	struct node *init_node, *targ_node;
	struct node_access_nodes *initiator, *target;
	int ret;

	if (!node_online(cpu_nid) || !node_online(mem_nid))
		return -ENODEV;

	init_node = node_devices[cpu_nid];
	targ_node = node_devices[mem_nid];
	initiator = node_init_node_access(init_node, access);
	target = node_init_node_access(targ_node, access);
	if (!initiator || !target)
		return -ENOMEM;

	ret = sysfs_add_link_to_group(&initiator->dev.kobj, "targets",
				      &targ_node->dev.kobj,
				      dev_name(&targ_node->dev));
	if (ret)
		return ret;

	ret = sysfs_add_link_to_group(&target->dev.kobj, "initiators",
				      &init_node->dev.kobj,
				      dev_name(&init_node->dev));
	if (ret)
		goto err;

	return 0;
 err:
	sysfs_remove_link_from_group(&initiator->dev.kobj, "targets",
				     dev_name(&targ_node->dev));
	return ret;
}

int unregister_cpu_under_node(unsigned int cpu, unsigned int nid)
{
	struct device *obj;

	if (!node_online(nid))
		return 0;

	obj = get_cpu_device(cpu);
	if (!obj)
		return 0;

	sysfs_remove_link(&node_devices[nid]->dev.kobj,
			  kobject_name(&obj->kobj));
	sysfs_remove_link(&obj->kobj,
			  kobject_name(&node_devices[nid]->dev.kobj));

	return 0;
}

#ifdef CONFIG_MEMORY_HOTPLUG
static int __ref get_nid_for_pfn(unsigned long pfn)
{
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
	if (system_state < SYSTEM_RUNNING)
		return early_pfn_to_nid(pfn);
#endif
	return pfn_to_nid(pfn);
}

static void do_register_memory_block_under_node(int nid,
						struct memory_block *mem_blk,
						enum meminit_context context)
{
	int ret;

	memory_block_add_nid(mem_blk, nid, context);

	ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
				       &mem_blk->dev.kobj,
				       kobject_name(&mem_blk->dev.kobj));
	if (ret && ret != -EEXIST)
		dev_err_ratelimited(&node_devices[nid]->dev,
				    "can't create link to %s in sysfs (%d)\n",
				    kobject_name(&mem_blk->dev.kobj), ret);

	ret = sysfs_create_link_nowarn(&mem_blk->dev.kobj,
				&node_devices[nid]->dev.kobj,
				kobject_name(&node_devices[nid]->dev.kobj));
	if (ret && ret != -EEXIST)
		dev_err_ratelimited(&mem_blk->dev,
				    "can't create link to %s in sysfs (%d)\n",
				    kobject_name(&node_devices[nid]->dev.kobj),
				    ret);
}

/* register memory section under specified node if it spans that node */
static int register_mem_block_under_node_early(struct memory_block *mem_blk,
					       void *arg)
{
	unsigned long memory_block_pfns = memory_block_size_bytes() / PAGE_SIZE;
	unsigned long start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
	unsigned long end_pfn = start_pfn + memory_block_pfns - 1;
	int nid = *(int *)arg;
	unsigned long pfn;

	for (pfn = start_pfn; pfn <= end_pfn; pfn++) {
		int page_nid;

		/*
		 * memory block could have several absent sections from start.
		 * skip pfn range from absent section
		 */
		if (!pfn_in_present_section(pfn)) {
			pfn = round_down(pfn + PAGES_PER_SECTION,
					 PAGES_PER_SECTION) - 1;
			continue;
		}

		/*
		 * We need to check if page belongs to nid only at the boot
		 * case because node's ranges can be interleaved.
		 */
		page_nid = get_nid_for_pfn(pfn);
		if (page_nid < 0)
			continue;
		if (page_nid != nid)
			continue;

		do_register_memory_block_under_node(nid, mem_blk, MEMINIT_EARLY);
		return 0;
	}
	/* mem section does not span the specified node */
	return 0;
}

/*
 * During hotplug we know that all pages in the memory block belong to the same
 * node.
 */
static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk,
						 void *arg)
{
	int nid = *(int *)arg;

	do_register_memory_block_under_node(nid, mem_blk, MEMINIT_HOTPLUG);
	return 0;
}

/*
 * Unregister a memory block device under the node it spans. Memory blocks
 * with multiple nodes cannot be offlined and therefore also never be removed.
 */
void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
{
	if (mem_blk->nid == NUMA_NO_NODE)
		return;

	sysfs_remove_link(&node_devices[mem_blk->nid]->dev.kobj,
			  kobject_name(&mem_blk->dev.kobj));
	sysfs_remove_link(&mem_blk->dev.kobj,
			  kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
}

void register_memory_blocks_under_node(int nid, unsigned long start_pfn,
				       unsigned long end_pfn,
				       enum meminit_context context)
{
	walk_memory_blocks_func_t func;

	if (context == MEMINIT_HOTPLUG)
		func = register_mem_block_under_node_hotplug;
	else
		func = register_mem_block_under_node_early;

	walk_memory_blocks(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn),
			   (void *)&nid, func);
	return;
}

#ifdef CONFIG_HUGETLBFS
/*
 * Handle per node hstate attribute [un]registration on transistions
 * to/from memoryless state.
 */
static void node_hugetlb_work(struct work_struct *work)
{
	struct node *node = container_of(work, struct node, node_work);

	/*
	 * We only get here when a node transitions to/from memoryless state.
	 * We can detect which transition occurred by examining whether the
	 * node has memory now.  hugetlb_register_node() already check this
	 * so we try to register the attributes.  If that fails, then the
	 * node has transitioned to memoryless, try to unregister the
	 * attributes.
	 */
	if (!hugetlb_register_node(node))
		hugetlb_unregister_node(node);
}

static void init_node_hugetlb_work(int nid)
{
	INIT_WORK(&node_devices[nid]->node_work, node_hugetlb_work);
}

static int node_memory_callback(struct notifier_block *self,
				unsigned long action, void *arg)
{
	struct memory_notify *mnb = arg;
	int nid = mnb->status_change_nid;

	switch (action) {
	case MEM_ONLINE:
	case MEM_OFFLINE:
		/*
		 * offload per node hstate [un]registration to a work thread
		 * when transitioning to/from memoryless state.
		 */
		if (nid != NUMA_NO_NODE)
			schedule_work(&node_devices[nid]->node_work);
		break;

	case MEM_GOING_ONLINE:
	case MEM_GOING_OFFLINE:
	case MEM_CANCEL_ONLINE:
	case MEM_CANCEL_OFFLINE:
	default:
		break;
	}

	return NOTIFY_OK;
}
#endif	/* CONFIG_HUGETLBFS */
#endif /* CONFIG_MEMORY_HOTPLUG */

#if !defined(CONFIG_MEMORY_HOTPLUG) || !defined(CONFIG_HUGETLBFS)
static inline int node_memory_callback(struct notifier_block *self,
				unsigned long action, void *arg)
{
	return NOTIFY_OK;
}

static void init_node_hugetlb_work(int nid) { }

#endif

int __register_one_node(int nid)
{
	int error;
	int cpu;

	node_devices[nid] = kzalloc(sizeof(struct node), GFP_KERNEL);
	if (!node_devices[nid])
		return -ENOMEM;

	error = register_node(node_devices[nid], nid);

	/* link cpu under this node */
	for_each_present_cpu(cpu) {
		if (cpu_to_node(cpu) == nid)
			register_cpu_under_node(cpu, nid);
	}

	INIT_LIST_HEAD(&node_devices[nid]->access_list);
	/* initialize work queue for memory hot plug */
	init_node_hugetlb_work(nid);
	node_init_caches(nid);

	return error;
}

void unregister_one_node(int nid)
{
	if (!node_devices[nid])
		return;

	unregister_node(node_devices[nid]);
	node_devices[nid] = NULL;
}

/*
 * node states attributes
 */

struct node_attr {
	struct device_attribute attr;
	enum node_states state;
};

static ssize_t show_node_state(struct device *dev,
			       struct device_attribute *attr, char *buf)
{
	struct node_attr *na = container_of(attr, struct node_attr, attr);

	return sysfs_emit(buf, "%*pbl\n",
			  nodemask_pr_args(&node_states[na->state]));
}

#define _NODE_ATTR(name, state) \
	{ __ATTR(name, 0444, show_node_state, NULL), state }

static struct node_attr node_state_attr[] = {
	[N_POSSIBLE] = _NODE_ATTR(possible, N_POSSIBLE),
	[N_ONLINE] = _NODE_ATTR(online, N_ONLINE),
	[N_NORMAL_MEMORY] = _NODE_ATTR(has_normal_memory, N_NORMAL_MEMORY),
#ifdef CONFIG_HIGHMEM
	[N_HIGH_MEMORY] = _NODE_ATTR(has_high_memory, N_HIGH_MEMORY),
#endif
	[N_MEMORY] = _NODE_ATTR(has_memory, N_MEMORY),
	[N_CPU] = _NODE_ATTR(has_cpu, N_CPU),
	[N_GENERIC_INITIATOR] = _NODE_ATTR(has_generic_initiator,
					   N_GENERIC_INITIATOR),
};

static struct attribute *node_state_attrs[] = {
	&node_state_attr[N_POSSIBLE].attr.attr,
	&node_state_attr[N_ONLINE].attr.attr,
	&node_state_attr[N_NORMAL_MEMORY].attr.attr,
#ifdef CONFIG_HIGHMEM
	&node_state_attr[N_HIGH_MEMORY].attr.attr,
#endif
	&node_state_attr[N_MEMORY].attr.attr,
	&node_state_attr[N_CPU].attr.attr,
	&node_state_attr[N_GENERIC_INITIATOR].attr.attr,
	NULL
};

static const struct attribute_group memory_root_attr_group = {
	.attrs = node_state_attrs,
};

static const struct attribute_group *cpu_root_attr_groups[] = {
	&memory_root_attr_group,
	NULL,
};

#define NODE_CALLBACK_PRI	2	/* lower than SLAB */
void __init node_dev_init(void)
{
	static struct notifier_block node_memory_callback_nb = {
		.notifier_call = node_memory_callback,
		.priority = NODE_CALLBACK_PRI,
	};
	int ret, i;

 	BUILD_BUG_ON(ARRAY_SIZE(node_state_attr) != NR_NODE_STATES);
 	BUILD_BUG_ON(ARRAY_SIZE(node_state_attrs)-1 != NR_NODE_STATES);

	ret = subsys_system_register(&node_subsys, cpu_root_attr_groups);
	if (ret)
		panic("%s() failed to register subsystem: %d\n", __func__, ret);

	register_hotmemory_notifier(&node_memory_callback_nb);

	/*
	 * Create all node devices, which will properly link the node
	 * to applicable memory block devices and already created cpu devices.
	 */
	for_each_online_node(i) {
		ret = register_one_node(i);
		if (ret)
			panic("%s() failed to add node: %d\n", __func__, ret);
	}
}