Free Electrons

Embedded Linux Experts

  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
/*
 * 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/kobject.h>
#include <linux/memory_hotplug.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/stat.h>
#include <linux/slab.h>

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

static DEFINE_MUTEX(mem_sysfs_mutex);

#define MEMORY_CLASS_NAME	"memory"

static int sections_per_block;

static inline int base_memory_block_id(int section_nr)
{
	return section_nr / sections_per_block;
}

static struct bus_type memory_subsys = {
	.name = MEMORY_CLASS_NAME,
	.dev_name = MEMORY_CLASS_NAME,
};

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 ATOMIC_NOTIFIER_HEAD(memory_isolate_chain);

int register_memory_isolate_notifier(struct notifier_block *nb)
{
	return atomic_notifier_chain_register(&memory_isolate_chain, nb);
}
EXPORT_SYMBOL(register_memory_isolate_notifier);

void unregister_memory_isolate_notifier(struct notifier_block *nb)
{
	atomic_notifier_chain_unregister(&memory_isolate_chain, nb);
}
EXPORT_SYMBOL(unregister_memory_isolate_notifier);

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

	memory->dev.bus = &memory_subsys;
	memory->dev.id = memory->start_section_nr / sections_per_block;

	error = device_register(&memory->dev);
	return error;
}

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

	/* drop the ref. we got in remove_memory_block() */
	kobject_put(&memory->dev.kobj);
	device_unregister(&memory->dev);
}

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

static unsigned long get_memory_block_size(void)
{
	unsigned long block_sz;

	block_sz = memory_block_size_bytes();

	/* Validate blk_sz is a power of 2 and not less than section size */
	if ((block_sz & (block_sz - 1)) || (block_sz < MIN_MEMORY_BLOCK_SIZE)) {
		WARN_ON(1);
		block_sz = MIN_MEMORY_BLOCK_SIZE;
	}

	return block_sz;
}

/*
 * use this as the physical section index that this memsection
 * uses.
 */

static ssize_t show_mem_start_phys_index(struct device *dev,
			struct device_attribute *attr, char *buf)
{
	struct memory_block *mem =
		container_of(dev, struct memory_block, dev);
	unsigned long phys_index;

	phys_index = mem->start_section_nr / sections_per_block;
	return sprintf(buf, "%08lx\n", phys_index);
}

static ssize_t show_mem_end_phys_index(struct device *dev,
			struct device_attribute *attr, char *buf)
{
	struct memory_block *mem =
		container_of(dev, struct memory_block, dev);
	unsigned long phys_index;

	phys_index = mem->end_section_nr / sections_per_block;
	return sprintf(buf, "%08lx\n", phys_index);
}

/*
 * Show whether the section of memory is likely to be hot-removable
 */
static ssize_t show_mem_removable(struct device *dev,
			struct device_attribute *attr, char *buf)
{
	unsigned long i, pfn;
	int ret = 1;
	struct memory_block *mem =
		container_of(dev, struct memory_block, dev);

	for (i = 0; i < sections_per_block; i++) {
		pfn = section_nr_to_pfn(mem->start_section_nr + i);
		ret &= is_mem_section_removable(pfn, PAGES_PER_SECTION);
	}

	return sprintf(buf, "%d\n", ret);
}

/*
 * online, offline, going offline, etc.
 */
static ssize_t show_mem_state(struct device *dev,
			struct device_attribute *attr, char *buf)
{
	struct memory_block *mem =
		container_of(dev, struct memory_block, dev);
	ssize_t len = 0;

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

	return len;
}

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

int memory_isolate_notify(unsigned long val, void *v)
{
	return atomic_notifier_call_chain(&memory_isolate_chain, val, v);
}

/*
 * The probe routines leave the pages reserved, just as the bootmem code does.
 * Make sure they're still that way.
 */
static bool pages_correctly_reserved(unsigned long start_pfn,
					unsigned long nr_pages)
{
	int i, j;
	struct page *page;
	unsigned long pfn = start_pfn;

	/*
	 * memmap between sections is not contiguous except with
	 * SPARSEMEM_VMEMMAP. We lookup the page once per section
	 * and assume memmap is contiguous within each section
	 */
	for (i = 0; i < sections_per_block; i++, pfn += PAGES_PER_SECTION) {
		if (WARN_ON_ONCE(!pfn_valid(pfn)))
			return false;
		page = pfn_to_page(pfn);

		for (j = 0; j < PAGES_PER_SECTION; j++) {
			if (PageReserved(page + j))
				continue;

			printk(KERN_WARNING "section number %ld page number %d "
				"not reserved, was it already online?\n",
				pfn_to_section_nr(pfn), j);

			return false;
		}
	}

	return true;
}

/*
 * 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(unsigned long phys_index, unsigned long action)
{
	unsigned long start_pfn, start_paddr;
	unsigned long nr_pages = PAGES_PER_SECTION * sections_per_block;
	struct page *first_page;
	int ret;

	first_page = pfn_to_page(phys_index << PFN_SECTION_SHIFT);

	switch (action) {
		case MEM_ONLINE:
			start_pfn = page_to_pfn(first_page);

			if (!pages_correctly_reserved(start_pfn, nr_pages))
				return -EBUSY;

			ret = online_pages(start_pfn, nr_pages);
			break;
		case MEM_OFFLINE:
			start_paddr = page_to_pfn(first_page) << PAGE_SHIFT;
			ret = remove_memory(start_paddr,
					    nr_pages << PAGE_SHIFT);
			break;
		default:
			WARN(1, KERN_WARNING "%s(%ld, %ld) unknown action: "
			     "%ld\n", __func__, phys_index, 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;

	mutex_lock(&mem->state_mutex);

	if (mem->state != from_state_req) {
		ret = -EINVAL;
		goto out;
	}

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

	ret = memory_block_action(mem->start_section_nr, to_state);

	if (ret) {
		mem->state = from_state_req;
		goto out;
	}

	mem->state = to_state;
	switch (mem->state) {
	case MEM_OFFLINE:
		kobject_uevent(&mem->dev.kobj, KOBJ_OFFLINE);
		break;
	case MEM_ONLINE:
		kobject_uevent(&mem->dev.kobj, KOBJ_ONLINE);
		break;
	default:
		break;
	}
out:
	mutex_unlock(&mem->state_mutex);
	return ret;
}

static ssize_t
store_mem_state(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t count)
{
	struct memory_block *mem;
	int ret = -EINVAL;

	mem = container_of(dev, struct memory_block, dev);

	if (!strncmp(buf, "online", min((int)count, 6)))
		ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
	else if(!strncmp(buf, "offline", min((int)count, 7)))
		ret = memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);

	if (ret)
		return ret;
	return count;
}

/*
 * phys_device is a bad name for this.  What I really want
 * is a way to differentiate between memory ranges that
 * are part of physical devices that constitute
 * a complete removable unit or fru.
 * i.e. do these ranges belong to the same physical device,
 * s.t. if I offline all of these sections I can then
 * remove the physical device?
 */
static ssize_t show_phys_device(struct device *dev,
				struct device_attribute *attr, char *buf)
{
	struct memory_block *mem =
		container_of(dev, struct memory_block, dev);
	return sprintf(buf, "%d\n", mem->phys_device);
}

static DEVICE_ATTR(phys_index, 0444, show_mem_start_phys_index, NULL);
static DEVICE_ATTR(end_phys_index, 0444, show_mem_end_phys_index, NULL);
static DEVICE_ATTR(state, 0644, show_mem_state, store_mem_state);
static DEVICE_ATTR(phys_device, 0444, show_phys_device, NULL);
static DEVICE_ATTR(removable, 0444, show_mem_removable, NULL);

#define mem_create_simple_file(mem, attr_name)	\
	device_create_file(&mem->dev, &dev_attr_##attr_name)
#define mem_remove_simple_file(mem, attr_name)	\
	device_remove_file(&mem->dev, &dev_attr_##attr_name)

/*
 * Block size attribute stuff
 */
static ssize_t
print_block_size(struct device *dev, struct device_attribute *attr,
		 char *buf)
{
	return sprintf(buf, "%lx\n", get_memory_block_size());
}

static DEVICE_ATTR(block_size_bytes, 0444, print_block_size, NULL);

static int block_size_init(void)
{
	return device_create_file(memory_subsys.dev_root,
				  &dev_attr_block_size_bytes);
}

/*
 * 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
memory_probe_store(struct device *dev, struct device_attribute *attr,
		   const char *buf, size_t count)
{
	u64 phys_addr;
	int nid;
	int i, ret;
	unsigned long pages_per_block = PAGES_PER_SECTION * sections_per_block;

	phys_addr = simple_strtoull(buf, NULL, 0);

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

	for (i = 0; i < sections_per_block; i++) {
		nid = memory_add_physaddr_to_nid(phys_addr);
		ret = add_memory(nid, phys_addr,
				 PAGES_PER_SECTION << PAGE_SHIFT);
		if (ret)
			goto out;

		phys_addr += MIN_MEMORY_BLOCK_SIZE;
	}

	ret = count;
out:
	return ret;
}
static DEVICE_ATTR(probe, S_IWUSR, NULL, memory_probe_store);

static int memory_probe_init(void)
{
	return device_create_file(memory_subsys.dev_root, &dev_attr_probe);
}
#else
static inline int memory_probe_init(void)
{
	return 0;
}
#endif

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

/* Soft offline a page */
static ssize_t
store_soft_offline_page(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 (strict_strtoull(buf, 0, &pfn) < 0)
		return -EINVAL;
	pfn >>= PAGE_SHIFT;
	if (!pfn_valid(pfn))
		return -ENXIO;
	ret = soft_offline_page(pfn_to_page(pfn), 0);
	return ret == 0 ? count : ret;
}

/* Forcibly offline a page, including killing processes. */
static ssize_t
store_hard_offline_page(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 (strict_strtoull(buf, 0, &pfn) < 0)
		return -EINVAL;
	pfn >>= PAGE_SHIFT;
	ret = memory_failure(pfn, 0, 0);
	return ret ? ret : count;
}

static DEVICE_ATTR(soft_offline_page, 0644, NULL, store_soft_offline_page);
static DEVICE_ATTR(hard_offline_page, 0644, NULL, store_hard_offline_page);

static __init int memory_fail_init(void)
{
	int err;

	err = device_create_file(memory_subsys.dev_root,
				&dev_attr_soft_offline_page);
	if (!err)
		err = device_create_file(memory_subsys.dev_root,
				&dev_attr_hard_offline_page);
	return err;
}
#else
static inline int memory_fail_init(void)
{
	return 0;
}
#endif

/*
 * Note that phys_device is optional.  It is here to allow for
 * differentiation between which *physical* devices each
 * section belongs to...
 */
int __weak arch_get_memory_phys_device(unsigned long start_pfn)
{
	return 0;
}

/*
 * A reference for the returned object is held and the reference for the
 * hinted object is released.
 */
struct memory_block *find_memory_block_hinted(struct mem_section *section,
					      struct memory_block *hint)
{
	int block_id = base_memory_block_id(__section_nr(section));
	struct device *hintdev = hint ? &hint->dev : NULL;
	struct device *dev;

	dev = subsys_find_device_by_id(&memory_subsys, block_id, hintdev);
	if (hint)
		put_device(&hint->dev);
	if (!dev)
		return NULL;
	return container_of(dev, struct memory_block, dev);
}

/*
 * For now, we have a linear search to go find the appropriate
 * memory_block corresponding to a particular phys_index. If
 * this gets to be a real problem, we can always use a radix
 * tree or something here.
 *
 * This could be made generic for all device subsystems.
 */
struct memory_block *find_memory_block(struct mem_section *section)
{
	return find_memory_block_hinted(section, NULL);
}

static int init_memory_block(struct memory_block **memory,
			     struct mem_section *section, unsigned long state)
{
	struct memory_block *mem;
	unsigned long start_pfn;
	int scn_nr;
	int ret = 0;

	mem = kzalloc(sizeof(*mem), GFP_KERNEL);
	if (!mem)
		return -ENOMEM;

	scn_nr = __section_nr(section);
	mem->start_section_nr =
			base_memory_block_id(scn_nr) * sections_per_block;
	mem->end_section_nr = mem->start_section_nr + sections_per_block - 1;
	mem->state = state;
	mem->section_count++;
	mutex_init(&mem->state_mutex);
	start_pfn = section_nr_to_pfn(mem->start_section_nr);
	mem->phys_device = arch_get_memory_phys_device(start_pfn);

	ret = register_memory(mem);
	if (!ret)
		ret = mem_create_simple_file(mem, phys_index);
	if (!ret)
		ret = mem_create_simple_file(mem, end_phys_index);
	if (!ret)
		ret = mem_create_simple_file(mem, state);
	if (!ret)
		ret = mem_create_simple_file(mem, phys_device);
	if (!ret)
		ret = mem_create_simple_file(mem, removable);

	*memory = mem;
	return ret;
}

static int add_memory_section(int nid, struct mem_section *section,
			struct memory_block **mem_p,
			unsigned long state, enum mem_add_context context)
{
	struct memory_block *mem = NULL;
	int scn_nr = __section_nr(section);
	int ret = 0;

	mutex_lock(&mem_sysfs_mutex);

	if (context == BOOT) {
		/* same memory block ? */
		if (mem_p && *mem_p)
			if (scn_nr >= (*mem_p)->start_section_nr &&
			    scn_nr <= (*mem_p)->end_section_nr) {
				mem = *mem_p;
				kobject_get(&mem->dev.kobj);
			}
	} else
		mem = find_memory_block(section);

	if (mem) {
		mem->section_count++;
		kobject_put(&mem->dev.kobj);
	} else {
		ret = init_memory_block(&mem, section, state);
		/* store memory_block pointer for next loop */
		if (!ret && context == BOOT)
			if (mem_p)
				*mem_p = mem;
	}

	if (!ret) {
		if (context == HOTPLUG &&
		    mem->section_count == sections_per_block)
			ret = register_mem_sect_under_node(mem, nid);
	}

	mutex_unlock(&mem_sysfs_mutex);
	return ret;
}

int remove_memory_block(unsigned long node_id, struct mem_section *section,
		int phys_device)
{
	struct memory_block *mem;

	mutex_lock(&mem_sysfs_mutex);
	mem = find_memory_block(section);
	unregister_mem_sect_under_nodes(mem, __section_nr(section));

	mem->section_count--;
	if (mem->section_count == 0) {
		mem_remove_simple_file(mem, phys_index);
		mem_remove_simple_file(mem, end_phys_index);
		mem_remove_simple_file(mem, state);
		mem_remove_simple_file(mem, phys_device);
		mem_remove_simple_file(mem, removable);
		unregister_memory(mem);
		kfree(mem);
	} else
		kobject_put(&mem->dev.kobj);

	mutex_unlock(&mem_sysfs_mutex);
	return 0;
}

/*
 * need an interface for the VM to add new memory regions,
 * but without onlining it.
 */
int register_new_memory(int nid, struct mem_section *section)
{
	return add_memory_section(nid, section, NULL, MEM_OFFLINE, HOTPLUG);
}

int unregister_memory_section(struct mem_section *section)
{
	if (!present_section(section))
		return -EINVAL;

	return remove_memory_block(0, section, 0);
}

/*
 * Initialize the sysfs support for memory devices...
 */
int __init memory_dev_init(void)
{
	unsigned int i;
	int ret;
	int err;
	unsigned long block_sz;
	struct memory_block *mem = NULL;

	ret = subsys_system_register(&memory_subsys, NULL);
	if (ret)
		goto out;

	block_sz = get_memory_block_size();
	sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;

	/*
	 * Create entries for memory sections that were found
	 * during boot and have been initialized
	 */
	for (i = 0; i < NR_MEM_SECTIONS; i++) {
		if (!present_section_nr(i))
			continue;
		/* don't need to reuse memory_block if only one per block */
		err = add_memory_section(0, __nr_to_section(i),
				 (sections_per_block == 1) ? NULL : &mem,
					 MEM_ONLINE,
					 BOOT);
		if (!ret)
			ret = err;
	}

	err = memory_probe_init();
	if (!ret)
		ret = err;
	err = memory_fail_init();
	if (!ret)
		ret = err;
	err = block_size_init();
	if (!ret)
		ret = err;
out:
	if (ret)
		printk(KERN_ERR "%s() failed: %d\n", __func__, ret);
	return ret;
}