summaryrefslogtreecommitdiffstats
path: root/drivers/base/memory.c
blob: d5ffaab3cb61c95a194386e71a94910db1fb31b4 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Memory subsystem support
 *
 * Written by Matt Tolentino <matthew.e.tolentino@intel.com>
 *            Dave Hansen <haveblue@us.ibm.com>
 *
 * This file provides the necessary infrastructure to represent
 * a SPARSEMEM-memory-model system's physical memory in /sysfs.
 * All arch-independent code that assumes MEMORY_HOTPLUG requires
 * SPARSEMEM should be contained here, or in mm/memory_hotplug.c.
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/topology.h>
#include <linux/capability.h>
#include <linux/device.h>
#include <linux/memory.h>
#include <linux/memory_hotplug.h>
#include <linux/mm.h>
#include <linux/stat.h>
#include <linux/slab.h>
#include <linux/xarray.h>

#include <linux/atomic.h>
#include <linux/uaccess.h>

#define MEMORY_CLASS_NAME	"memory"

static const char *const online_type_to_str[] = {
	[MMOP_OFFLINE] = "offline",
	[MMOP_ONLINE] = "online",
	[MMOP_ONLINE_KERNEL] = "online_kernel",
	[MMOP_ONLINE_MOVABLE] = "online_movable",
};

int mhp_online_type_from_str(const char *str)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(online_type_to_str); i++) {
		if (sysfs_streq(str, online_type_to_str[i]))
			return i;
	}
	return -EINVAL;
}

#define to_memory_block(dev) container_of(dev, struct memory_block, dev)

static int sections_per_block;

static inline unsigned long memory_block_id(unsigned long section_nr)
{
	return section_nr / sections_per_block;
}

static inline unsigned long pfn_to_block_id(unsigned long pfn)
{
	return memory_block_id(pfn_to_section_nr(pfn));
}

static inline unsigned long phys_to_block_id(unsigned long phys)
{
	return pfn_to_block_id(PFN_DOWN(phys));
}

static int memory_subsys_online(struct device *dev);
static int memory_subsys_offline(struct device *dev);

static struct bus_type memory_subsys = {
	.name = MEMORY_CLASS_NAME,
	.dev_name = MEMORY_CLASS_NAME,
	.online = memory_subsys_online,
	.offline = memory_subsys_offline,
};

/*
 * Memory blocks are cached in a local radix tree to avoid
 * a costly linear search for the corresponding device on
 * the subsystem bus.
 */
static DEFINE_XARRAY(memory_blocks);

static BLOCKING_NOTIFIER_HEAD(memory_chain);

int register_memory_notifier(struct notifier_block *nb)
{
	return blocking_notifier_chain_register(&memory_chain, nb);
}
EXPORT_SYMBOL(register_memory_notifier);

void unregister_memory_notifier(struct notifier_block *nb)
{
	blocking_notifier_chain_unregister(&memory_chain, nb);
}
EXPORT_SYMBOL(unregister_memory_notifier);

static void memory_block_release(struct device *dev)
{
	struct memory_block *mem = to_memory_block(dev);

	kfree(mem);
}

unsigned long __weak memory_block_size_bytes(void)
{
	return MIN_MEMORY_BLOCK_SIZE;
}
EXPORT_SYMBOL_GPL(memory_block_size_bytes);

/*
 * Show the first physical section index (number) of this memory block.
 */
static ssize_t phys_index_show(struct device *dev,
			       struct device_attribute *attr, char *buf)
{
	struct memory_block *mem = to_memory_block(dev);
	unsigned long phys_index;

	phys_index = mem->start_section_nr / sections_per_block;

	return sysfs_emit(buf, "%08lx\n", phys_index);
}

/*
 * Legacy interface that we cannot remove. Always indicate "removable"
 * with CONFIG_MEMORY_HOTREMOVE - bad heuristic.
 */
static ssize_t removable_show(struct device *dev, struct device_attribute *attr,
			      char *buf)
{
	return sysfs_emit(buf, "%d\n", (int)IS_ENABLED(CONFIG_MEMORY_HOTREMOVE));
}

/*
 * online, offline, going offline, etc.
 */
static ssize_t state_show(struct device *dev, struct device_attribute *attr,
			  char *buf)
{
	struct memory_block *mem = to_memory_block(dev);
	const char *output;

	/*
	 * We can probably put these states in a nice little array
	 * so that they're not open-coded
	 */
	switch (mem->state) {
	case MEM_ONLINE:
		output = "online";
		break;
	case MEM_OFFLINE:
		output = "offline";
		break;
	case MEM_GOING_OFFLINE:
		output = "going-offline";
		break;
	default:
		WARN_ON(1);
		return sysfs_emit(buf, "ERROR-UNKNOWN-%ld\n", mem->state);
	}

	return sysfs_emit(buf, "%s\n", output);
}

int memory_notify(unsigned long val, void *v)
{
	return blocking_notifier_call_chain(&memory_chain, val, v);
}

static int memory_block_online(struct memory_block *mem)
{
	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
	unsigned long nr_vmemmap_pages = mem->nr_vmemmap_pages;
	struct zone *zone;
	int ret;

	zone = zone_for_pfn_range(mem->online_type, mem->nid, start_pfn, nr_pages);

	/*
	 * Although vmemmap pages have a different lifecycle than the pages
	 * they describe (they remain until the memory is unplugged), doing
	 * their initialization and accounting at memory onlining/offlining
	 * stage helps to keep accounting easier to follow - e.g vmemmaps
	 * belong to the same zone as the memory they backed.
	 */
	if (nr_vmemmap_pages) {
		ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone);
		if (ret)
			return ret;
	}

	ret = online_pages(start_pfn + nr_vmemmap_pages,
			   nr_pages - nr_vmemmap_pages, zone);
	if (ret) {
		if (nr_vmemmap_pages)
			mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);
		return ret;
	}

	/*
	 * Account once onlining succeeded. If the zone was unpopulated, it is
	 * now already properly populated.
	 */
	if (nr_vmemmap_pages)
		adjust_present_page_count(zone, nr_vmemmap_pages);

	return ret;
}

static int memory_block_offline(struct memory_block *mem)
{
	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
	unsigned long nr_vmemmap_pages = mem->nr_vmemmap_pages;
	struct zone *zone;
	int ret;

	/*
	 * Unaccount before offlining, such that unpopulated zone and kthreads
	 * can properly be torn down in offline_pages().
	 */
	if (nr_vmemmap_pages) {
		zone = page_zone(pfn_to_page(start_pfn));
		adjust_present_page_count(zone, -nr_vmemmap_pages);
	}

	ret = offline_pages(start_pfn + nr_vmemmap_pages,
			    nr_pages - nr_vmemmap_pages);
	if (ret) {
		/* offline_pages() failed. Account back. */
		if (nr_vmemmap_pages)
			adjust_present_page_count(zone, nr_vmemmap_pages);
		return ret;
	}

	if (nr_vmemmap_pages)
		mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages);

	return ret;
}

/*
 * MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is
 * OK to have direct references to sparsemem variables in here.
 */
static int
memory_block_action(struct memory_block *mem, unsigned long action)
{
	int ret;

	switch (action) {
	case MEM_ONLINE:
		ret = memory_block_online(mem);
		break;
	case MEM_OFFLINE:
		ret = memory_block_offline(mem);
		break;
	default:
		WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "
		     "%ld\n", __func__, mem->start_section_nr, action, action);
		ret = -EINVAL;
	}

	return ret;
}

static int memory_block_change_state(struct memory_block *mem,
		unsigned long to_state, unsigned long from_state_req)
{
	int ret = 0;

	if (mem->state != from_state_req)
		return -EINVAL;

	if (to_state == MEM_OFFLINE)
		mem->state = MEM_GOING_OFFLINE;

	ret = memory_block_action(mem, to_state);
	mem->state = ret ? from_state_req : to_state;

	return ret;
}

/* The device lock serializes operations on memory_subsys_[online|offline] */
static int memory_subsys_online(struct device *dev)
{
	struct memory_block *mem = to_memory_block(dev);
	int ret;

	if (mem->state == MEM_ONLINE)
		return 0;

	/*
	 * When called via device_online() without configuring the online_type,
	 * we want to default to MMOP_ONLINE.
	 */
	if (mem->online_type == MMOP_OFFLINE)
		mem->online_type = MMOP_ONLINE;

	ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
	mem->online_type = MMOP_OFFLINE;

	return ret;
}

static int memory_subsys_offline(struct device *dev)
{
	struct memory_block *mem = to_memory_block(dev);

	if (mem->state == MEM_OFFLINE)
		return 0;

	return memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
}

static ssize_t state_store(struct device *dev, struct device_attribute *attr,
			   const char *buf, size_t count)
{
	const int online_type = mhp_online_type_from_str(buf);
	struct memory_block *mem = to_memory_block(dev);
	int ret;

	if (online_type < 0)
		return -EINVAL;

	ret = lock_device_hotplug_sysfs();
	if (ret)
		return ret;

	switch (online_type) {
	case MMOP_ONLINE_KERNEL:
	case MMOP_ONLINE_MOVABLE:
	case MMOP_ONLINE:
		/* mem->online_type is protected by device_hotplug_lock */
		mem->online_type = online_type;
		ret = device_online(&mem->dev);
		break;
	case MMOP_OFFLINE:
		ret = device_offline(&mem->dev);
		break;
	default:
		ret = -EINVAL; /* should never happen */
	}

	unlock_device_hotplug();

	if (ret < 0)
		return ret;
	if (ret)
		return -EINVAL;

	return count;
}

/*
 * Legacy interface that we cannot remove: s390x exposes the storage increment
 * covered by a memory block, allowing for identifying which memory blocks
 * comprise a storage increment. Since a memory block spans complete
 * storage increments nowadays, this interface is basically unused. Other
 * archs never exposed != 0.
 */
static ssize_t phys_device_show(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	struct memory_block *mem = to_memory_block(dev);
	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);

	return sysfs_emit(buf, "%d\n",
			  arch_get_memory_phys_device(start_pfn));
}

#ifdef CONFIG_MEMORY_HOTREMOVE
static int print_allowed_zone(char *buf, int len, int nid,
			      unsigned long start_pfn, unsigned long nr_pages,
			      int online_type, struct zone *default_zone)
{
	struct zone *zone;

	zone = zone_for_pfn_range(online_type, nid, start_pfn, nr_pages);
	if (zone == default_zone)
		return 0;

	return sysfs_emit_at(buf, len, " %s", zone->name);
}

static ssize_t valid_zones_show(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	struct memory_block *mem = to_memory_block(dev);
	unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr);
	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
	struct zone *default_zone;
	int len = 0;
	int nid;

	/*
	 * Check the existing zone. Make sure that we do that only on the
	 * online nodes otherwise the page_zone is not reliable
	 */
	if (mem->state == MEM_ONLINE) {
		/*
		 * The block contains more than one zone can not be offlined.
		 * This can happen e.g. for ZONE_DMA and ZONE_DMA32
		 */
		default_zone = test_pages_in_a_zone(start_pfn,
						    start_pfn + nr_pages);
		if (!default_zone)
			return sysfs_emit(buf, "%s\n", "none");
		len += sysfs_emit_at(buf, len, "%s", default_zone->name);
		goto out;
	}

	nid = mem->nid;
	default_zone = zone_for_pfn_range(MMOP_ONLINE, nid, start_pfn,
					  nr_pages);

	len += sysfs_emit_at(buf, len, "%s", default_zone->name);
	len += print_allowed_zone(buf, len, nid, start_pfn, nr_pages,
				  MMOP_ONLINE_KERNEL, default_zone);
	len += print_allowed_zone(buf, len, nid, start_pfn, nr_pages,
				  MMOP_ONLINE_MOVABLE, default_zone);
out:
	len += sysfs_emit_at(buf, len, "\n");
	return len;
}
static DEVICE_ATTR_RO(valid_zones);
#endif

static DEVICE_ATTR_RO(phys_index);
static DEVICE_ATTR_RW(state);
static DEVICE_ATTR_RO(phys_device);
static DEVICE_ATTR_RO(removable);

/*
 * Show the memory block size (shared by all memory blocks).
 */
static ssize_t block_size_bytes_show(struct device *dev,
				     struct device_attribute *attr, char *buf)
{
	return sysfs_emit(buf, "%lx\n", memory_block_size_bytes());
}

static DEVICE_ATTR_RO(block_size_bytes);

/*
 * Memory auto online policy.
 */

static ssize_t auto_online_blocks_show(struct device *dev,
				       struct device_attribute *attr, char *buf)
{
	return sysfs_emit(buf, "%s\n",
			  online_type_to_str[mhp_default_online_type]);
}

static ssize_t auto_online_blocks_store(struct device *dev,
					struct device_attribute *attr,
					const char *buf, size_t count)
{
	const int online_type = mhp_online_type_from_str(buf);

	if (online_type < 0)
		return -EINVAL;

	mhp_default_online_type = online_type;
	return count;
}

static DEVICE_ATTR_RW(auto_online_blocks);

/*
 * Some architectures will have custom drivers to do this, and
 * will not need to do it from userspace.  The fake hot-add code
 * as well as ppc64 will do all of their discovery in userspace
 * and will require this interface.
 */
#ifdef CONFIG_ARCH_MEMORY_PROBE
static ssize_t probe_store(struct device *dev, struct device_attribute *attr,
			   const char *buf, size_t count)
{
	u64 phys_addr;
	int nid, ret;
	unsigned long pages_per_block = PAGES_PER_SECTION * sections_per_block;

	ret = kstrtoull(buf, 0, &phys_addr);
	if (ret)
		return ret;

	if (phys_addr & ((pages_per_block << PAGE_SHIFT) - 1))
		return -EINVAL;

	ret = lock_device_hotplug_sysfs();
	if (ret)
		return ret;

	nid = memory_add_physaddr_to_nid(phys_addr);
	ret = __add_memory(nid, phys_addr,
			   MIN_MEMORY_BLOCK_SIZE * sections_per_block,
			   MHP_NONE);

	if (ret)
		goto out;

	ret = count;
out:
	unlock_device_hotplug();
	return ret;
}

static DEVICE_ATTR_WO(probe);
#endif

#ifdef CONFIG_MEMORY_FAILURE
/*
 * Support for offlining pages of memory
 */

/* Soft offline a page */
static ssize_t soft_offline_page_store(struct device *dev,
				       struct device_attribute *attr,
				       const char *buf, size_t count)
{
	int ret;
	u64 pfn;
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (kstrtoull(buf, 0, &pfn) < 0)
		return -EINVAL;
	pfn >>= PAGE_SHIFT;
	ret = soft_offline_page(pfn, 0);
	return ret == 0 ? count : ret;
}

/* Forcibly offline a page, including killing processes. */
static ssize_t hard_offline_page_store(struct device *dev,
				       struct device_attribute *attr,
				       const char *buf, size_t count)
{
	int ret;
	u64 pfn;
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (kstrtoull(buf, 0, &pfn) < 0)
		return -EINVAL;
	pfn >>= PAGE_SHIFT;
	ret = memory_failure(pfn, 0);
	return ret ? ret : count;
}

static DEVICE_ATTR_WO(soft_offline_page);
static DEVICE_ATTR_WO(hard_offline_page);
#endif

/* See phys_device_show(). */
int __weak arch_get_memory_phys_device(unsigned long start_pfn)
{
	return 0;
}

/*
 * A reference for the returned memory block device is acquired.
 *
 * Called under device_hotplug_lock.
 */
static struct memory_block *find_memory_block_by_id(unsigned long block_id)
{
	struct memory_block *mem;

	mem = xa_load(&memory_blocks, block_id);
	if (mem)
		get_device(&mem->dev);
	return mem;
}

/*
 * Called under device_hotplug_lock.
 */
struct memory_block *find_memory_block(struct mem_section *section)
{
	unsigned long block_id = memory_block_id(__section_nr(section));

	return find_memory_block_by_id(block_id);
}

static struct attribute *memory_memblk_attrs[] = {
	&dev_attr_phys_index.attr,
	&dev_attr_state.attr,
	&dev_attr_phys_device.attr,
	&dev_attr_removable.attr,
#ifdef CONFIG_MEMORY_HOTREMOVE
	&dev_attr_valid_zones.attr,
#endif
	NULL
};

static struct attribute_group memory_memblk_attr_group = {
	.attrs = memory_memblk_attrs,
};

static const struct attribute_group *memory_memblk_attr_groups[] = {
	&memory_memblk_attr_group,
	NULL,
};

/*
 * register_memory - Setup a sysfs device for a memory block
 */
static
int register_memory(struct memory_block *memory)
{
	int ret;

	memory->dev.bus = &memory_subsys;
	memory->dev.id = memory->start_section_nr / sections_per_block;
	memory->dev.release = memory_block_release;
	memory->dev.groups = memory_memblk_attr_groups;
	memory->dev.offline = memory->state == MEM_OFFLINE;

	ret = device_register(&memory->dev);
	if (ret) {
		put_device(&memory->dev);
		return ret;
	}
	ret = xa_err(xa_store(&memory_blocks, memory->dev.id, memory,
			      GFP_KERNEL));
	if (ret) {
		put_device(&memory->dev);
		device_unregister(&memory->dev);
	}
	return ret;
}

static int init_memory_block(unsigned long block_id, unsigned long state,
			     unsigned long nr_vmemmap_pages)
{
	struct memory_block *mem;
	int ret = 0;

	mem = find_memory_block_by_id(block_id);
	if (mem) {
		put_device(&mem->dev);
		return -EEXIST;
	}
	mem = kzalloc(sizeof(*mem), GFP_KERNEL);
	if (!mem)
		return -ENOMEM;

	mem->start_section_nr = block_id * sections_per_block;
	mem->state = state;
	mem->nid = NUMA_NO_NODE;
	mem->nr_vmemmap_pages = nr_vmemmap_pages;

	ret = register_memory(mem);

	return ret;
}

static int add_memory_block(unsigned long base_section_nr)
{
	int section_count = 0;
	unsigned long nr;

	for (nr = base_section_nr; nr < base_section_nr + sections_per_block;
	     nr++)
		if (present_section_nr(nr))
			section_count++;

	if (section_count == 0)
		return 0;
	return init_memory_block(memory_block_id(base_section_nr),
				 MEM_ONLINE, 0);
}

static void unregister_memory(struct memory_block *memory)
{
	if (WARN_ON_ONCE(memory->dev.bus != &memory_subsys))
		return;

	WARN_ON(xa_erase(&memory_blocks, memory->dev.id) == NULL);

	/* drop the ref. we got via find_memory_block() */
	put_device(&memory->dev);
	device_unregister(&memory->dev);
}

/*
 * Create memory block devices for the given memory area. Start and size
 * have to be aligned to memory block granularity. Memory block devices
 * will be initialized as offline.
 *
 * Called under device_hotplug_lock.
 */
int create_memory_block_devices(unsigned long start, unsigned long size,
				unsigned long vmemmap_pages)
{
	const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start));
	unsigned long end_block_id = pfn_to_block_id(PFN_DOWN(start + size));
	struct memory_block *mem;
	unsigned long block_id;
	int ret = 0;

	if (WARN_ON_ONCE(!IS_ALIGNED(start, memory_block_size_bytes()) ||
			 !IS_ALIGNED(size, memory_block_size_bytes())))
		return -EINVAL;

	for (block_id = start_block_id; block_id != end_block_id; block_id++) {
		ret = init_memory_block(block_id, MEM_OFFLINE, vmemmap_pages);
		if (ret)
			break;
	}
	if (ret) {
		end_block_id = block_id;
		for (block_id = start_block_id; block_id != end_block_id;
		     block_id++) {
			mem = find_memory_block_by_id(block_id);
			if (WARN_ON_ONCE(!mem))
				continue;
			unregister_memory(mem);
		}
	}
	return ret;
}

/*
 * Remove memory block devices for the given memory area. Start and size
 * have to be aligned to memory block granularity. Memory block devices
 * have to be offline.
 *
 * Called under device_hotplug_lock.
 */
void remove_memory_block_devices(unsigned long start, unsigned long size)
{
	const unsigned long start_block_id = pfn_to_block_id(PFN_DOWN(start));
	const unsigned long end_block_id = pfn_to_block_id(PFN_DOWN(start + size));
	struct memory_block *mem;
	unsigned long block_id;

	if (WARN_ON_ONCE(!IS_ALIGNED(start, memory_block_size_bytes()) ||
			 !IS_ALIGNED(size, memory_block_size_bytes())))
		return;

	for (block_id = start_block_id; block_id != end_block_id; block_id++) {
		mem = find_memory_block_by_id(block_id);
		if (WARN_ON_ONCE(!mem))
			continue;
		unregister_memory_block_under_nodes(mem);
		unregister_memory(mem);
	}
}

/* return true if the memory block is offlined, otherwise, return false */
bool is_memblock_offlined(struct memory_block *mem)
{
	return mem->state == MEM_OFFLINE;
}

static struct attribute *memory_root_attrs[] = {
#ifdef CONFIG_ARCH_MEMORY_PROBE
	&dev_attr_probe.attr,
#endif

#ifdef CONFIG_MEMORY_FAILURE
	&dev_attr_soft_offline_page.attr,
	&dev_attr_hard_offline_page.attr,
#endif

	&dev_attr_block_size_bytes.attr,
	&dev_attr_auto_online_blocks.attr,
	NULL
};

static struct attribute_group memory_root_attr_group = {
	.attrs = memory_root_attrs,
};

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

/*
 * Initialize the sysfs support for memory devices. At the time this function
 * is called, we cannot have concurrent creation/deletion of memory block
 * devices, the device_hotplug_lock is not needed.
 */
void __init memory_dev_init(void)
{
	int ret;
	unsigned long block_sz, nr;

	/* Validate the configured memory block size */
	block_sz = memory_block_size_bytes();
	if (!is_power_of_2(block_sz) || block_sz < MIN_MEMORY_BLOCK_SIZE)
		panic("Memory block size not suitable: 0x%lx\n", block_sz);
	sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;

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

	/*
	 * Create entries for memory sections that were found
	 * during boot and have been initialized
	 */
	for (nr = 0; nr <= __highest_present_section_nr;
	     nr += sections_per_block) {
		ret = add_memory_block(nr);
		if (ret)
			panic("%s() failed to add memory block: %d\n", __func__,
			      ret);
	}
}

/**
 * walk_memory_blocks - walk through all present memory blocks overlapped
 *			by the range [start, start + size)
 *
 * @start: start address of the memory range
 * @size: size of the memory range
 * @arg: argument passed to func
 * @func: callback for each memory section walked
 *
 * This function walks through all present memory blocks overlapped by the
 * range [start, start + size), calling func on each memory block.
 *
 * In case func() returns an error, walking is aborted and the error is
 * returned.
 *
 * Called under device_hotplug_lock.
 */
int walk_memory_blocks(unsigned long start, unsigned long size,
		       void *arg, walk_memory_blocks_func_t func)
{
	const unsigned long start_block_id = phys_to_block_id(start);
	const unsigned long end_block_id = phys_to_block_id(start + size - 1);
	struct memory_block *mem;
	unsigned long block_id;
	int ret = 0;

	if (!size)
		return 0;

	for (block_id = start_block_id; block_id <= end_block_id; block_id++) {
		mem = find_memory_block_by_id(block_id);
		if (!mem)
			continue;

		ret = func(mem, arg);
		put_device(&mem->dev);
		if (ret)
			break;
	}
	return ret;
}

struct for_each_memory_block_cb_data {
	walk_memory_blocks_func_t func;
	void *arg;
};

static int for_each_memory_block_cb(struct device *dev, void *data)
{
	struct memory_block *mem = to_memory_block(dev);
	struct for_each_memory_block_cb_data *cb_data = data;

	return cb_data->func(mem, cb_data->arg);
}

/**
 * for_each_memory_block - walk through all present memory blocks
 *
 * @arg: argument passed to func
 * @func: callback for each memory block walked
 *
 * This function walks through all present memory blocks, calling func on
 * each memory block.
 *
 * In case func() returns an error, walking is aborted and the error is
 * returned.
 */
int for_each_memory_block(void *arg, walk_memory_blocks_func_t func)
{
	struct for_each_memory_block_cb_data cb_data = {
		.func = func,
		.arg = arg,
	};

	return bus_for_each_dev(&memory_subsys, NULL, &cb_data,
				for_each_memory_block_cb);
}