memory_hotplug.c 53.8 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12
/*
 *  linux/mm/memory_hotplug.c
 *
 *  Copyright (C)
 */

#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/compiler.h>
13
#include <linux/export.h>
14
#include <linux/pagevec.h>
15
#include <linux/writeback.h>
16 17 18 19
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/memory.h>
20
#include <linux/memremap.h>
21 22 23
#include <linux/memory_hotplug.h>
#include <linux/highmem.h>
#include <linux/vmalloc.h>
24
#include <linux/ioport.h>
K
KAMEZAWA Hiroyuki 已提交
25 26 27
#include <linux/delay.h>
#include <linux/migrate.h>
#include <linux/page-isolation.h>
28
#include <linux/pfn.h>
29
#include <linux/suspend.h>
30
#include <linux/mm_inline.h>
31
#include <linux/firmware-map.h>
32
#include <linux/stop_machine.h>
33
#include <linux/hugetlb.h>
34
#include <linux/memblock.h>
35
#include <linux/bootmem.h>
36
#include <linux/compaction.h>
37 38 39

#include <asm/tlbflush.h>

40 41
#include "internal.h"

42 43 44 45 46 47 48 49 50 51
/*
 * online_page_callback contains pointer to current page onlining function.
 * Initially it is generic_online_page(). If it is required it could be
 * changed by calling set_online_page_callback() for callback registration
 * and restore_online_page_callback() for generic callback restore.
 */

static void generic_online_page(struct page *page);

static online_page_callback_t online_page_callback = generic_online_page;
52
static DEFINE_MUTEX(online_page_callback_lock);
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
/* The same as the cpu_hotplug lock, but for memory hotplug. */
static struct {
	struct task_struct *active_writer;
	struct mutex lock; /* Synchronizes accesses to refcount, */
	/*
	 * Also blocks the new readers during
	 * an ongoing mem hotplug operation.
	 */
	int refcount;

#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct lockdep_map dep_map;
#endif
} mem_hotplug = {
	.active_writer = NULL,
	.lock = __MUTEX_INITIALIZER(mem_hotplug.lock),
	.refcount = 0,
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	.dep_map = {.name = "mem_hotplug.lock" },
#endif
};

/* Lockdep annotations for get/put_online_mems() and mem_hotplug_begin/end() */
#define memhp_lock_acquire_read() lock_map_acquire_read(&mem_hotplug.dep_map)
#define memhp_lock_acquire()      lock_map_acquire(&mem_hotplug.dep_map)
#define memhp_lock_release()      lock_map_release(&mem_hotplug.dep_map)

81 82 83
bool memhp_auto_online;
EXPORT_SYMBOL_GPL(memhp_auto_online);

84 85 86 87 88 89 90 91 92 93 94
void get_online_mems(void)
{
	might_sleep();
	if (mem_hotplug.active_writer == current)
		return;
	memhp_lock_acquire_read();
	mutex_lock(&mem_hotplug.lock);
	mem_hotplug.refcount++;
	mutex_unlock(&mem_hotplug.lock);

}
95

96
void put_online_mems(void)
97
{
98 99 100 101 102 103 104 105 106 107 108 109
	if (mem_hotplug.active_writer == current)
		return;
	mutex_lock(&mem_hotplug.lock);

	if (WARN_ON(!mem_hotplug.refcount))
		mem_hotplug.refcount++; /* try to fix things up */

	if (!--mem_hotplug.refcount && unlikely(mem_hotplug.active_writer))
		wake_up_process(mem_hotplug.active_writer);
	mutex_unlock(&mem_hotplug.lock);
	memhp_lock_release();

110 111
}

112
void mem_hotplug_begin(void)
113
{
114 115 116 117 118 119 120 121 122 123 124
	mem_hotplug.active_writer = current;

	memhp_lock_acquire();
	for (;;) {
		mutex_lock(&mem_hotplug.lock);
		if (likely(!mem_hotplug.refcount))
			break;
		__set_current_state(TASK_UNINTERRUPTIBLE);
		mutex_unlock(&mem_hotplug.lock);
		schedule();
	}
125 126
}

127
void mem_hotplug_done(void)
128 129 130 131 132
{
	mem_hotplug.active_writer = NULL;
	mutex_unlock(&mem_hotplug.lock);
	memhp_lock_release();
}
133

134 135 136 137 138
/* add this memory to iomem resource */
static struct resource *register_memory_resource(u64 start, u64 size)
{
	struct resource *res;
	res = kzalloc(sizeof(struct resource), GFP_KERNEL);
139 140
	if (!res)
		return ERR_PTR(-ENOMEM);
141 142 143 144

	res->name = "System RAM";
	res->start = start;
	res->end = start + size - 1;
145
	res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
146
	if (request_resource(&iomem_resource, res) < 0) {
147
		pr_debug("System RAM resource %pR cannot be added\n", res);
148
		kfree(res);
149
		return ERR_PTR(-EEXIST);
150 151 152 153 154 155 156 157 158 159 160 161 162
	}
	return res;
}

static void release_memory_resource(struct resource *res)
{
	if (!res)
		return;
	release_resource(res);
	kfree(res);
	return;
}

163
#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
164 165
void get_page_bootmem(unsigned long info,  struct page *page,
		      unsigned long type)
166
{
A
Andrea Arcangeli 已提交
167
	page->lru.next = (struct list_head *) type;
168 169 170 171 172
	SetPagePrivate(page);
	set_page_private(page, info);
	atomic_inc(&page->_count);
}

173
void put_page_bootmem(struct page *page)
174
{
A
Andrea Arcangeli 已提交
175
	unsigned long type;
176

A
Andrea Arcangeli 已提交
177 178 179
	type = (unsigned long) page->lru.next;
	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
	       type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
180 181 182 183

	if (atomic_dec_return(&page->_count) == 1) {
		ClearPagePrivate(page);
		set_page_private(page, 0);
A
Andrea Arcangeli 已提交
184
		INIT_LIST_HEAD(&page->lru);
185
		free_reserved_page(page);
186 187 188
	}
}

189 190
#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
#ifndef CONFIG_SPARSEMEM_VMEMMAP
191
static void register_page_bootmem_info_section(unsigned long start_pfn)
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
{
	unsigned long *usemap, mapsize, section_nr, i;
	struct mem_section *ms;
	struct page *page, *memmap;

	section_nr = pfn_to_section_nr(start_pfn);
	ms = __nr_to_section(section_nr);

	/* Get section's memmap address */
	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);

	/*
	 * Get page for the memmap's phys address
	 * XXX: need more consideration for sparse_vmemmap...
	 */
	page = virt_to_page(memmap);
	mapsize = sizeof(struct page) * PAGES_PER_SECTION;
	mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT;

	/* remember memmap's page */
	for (i = 0; i < mapsize; i++, page++)
		get_page_bootmem(section_nr, page, SECTION_INFO);

	usemap = __nr_to_section(section_nr)->pageblock_flags;
	page = virt_to_page(usemap);

	mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;

	for (i = 0; i < mapsize; i++, page++)
221
		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
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
#else /* CONFIG_SPARSEMEM_VMEMMAP */
static void register_page_bootmem_info_section(unsigned long start_pfn)
{
	unsigned long *usemap, mapsize, section_nr, i;
	struct mem_section *ms;
	struct page *page, *memmap;

	if (!pfn_valid(start_pfn))
		return;

	section_nr = pfn_to_section_nr(start_pfn);
	ms = __nr_to_section(section_nr);

	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);

	register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);

	usemap = __nr_to_section(section_nr)->pageblock_flags;
	page = virt_to_page(usemap);

	mapsize = PAGE_ALIGN(usemap_size()) >> PAGE_SHIFT;

	for (i = 0; i < mapsize; i++, page++)
		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
}
#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265

void register_page_bootmem_info_node(struct pglist_data *pgdat)
{
	unsigned long i, pfn, end_pfn, nr_pages;
	int node = pgdat->node_id;
	struct page *page;
	struct zone *zone;

	nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT;
	page = virt_to_page(pgdat);

	for (i = 0; i < nr_pages; i++, page++)
		get_page_bootmem(node, page, NODE_INFO);

	zone = &pgdat->node_zones[0];
	for (; zone < pgdat->node_zones + MAX_NR_ZONES - 1; zone++) {
266
		if (zone_is_initialized(zone)) {
267 268 269 270 271 272 273 274 275 276 277
			nr_pages = zone->wait_table_hash_nr_entries
				* sizeof(wait_queue_head_t);
			nr_pages = PAGE_ALIGN(nr_pages) >> PAGE_SHIFT;
			page = virt_to_page(zone->wait_table);

			for (i = 0; i < nr_pages; i++, page++)
				get_page_bootmem(node, page, NODE_INFO);
		}
	}

	pfn = pgdat->node_start_pfn;
278
	end_pfn = pgdat_end_pfn(pgdat);
279

280
	/* register section info */
281 282 283 284 285
	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
		/*
		 * Some platforms can assign the same pfn to multiple nodes - on
		 * node0 as well as nodeN.  To avoid registering a pfn against
		 * multiple nodes we check that this pfn does not already
286
		 * reside in some other nodes.
287 288 289 290
		 */
		if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node))
			register_page_bootmem_info_section(pfn);
	}
291
}
292
#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */
293

294 295
static void __meminit grow_zone_span(struct zone *zone, unsigned long start_pfn,
				     unsigned long end_pfn)
296 297 298 299 300
{
	unsigned long old_zone_end_pfn;

	zone_span_writelock(zone);

301
	old_zone_end_pfn = zone_end_pfn(zone);
302
	if (zone_is_empty(zone) || start_pfn < zone->zone_start_pfn)
303 304 305 306 307 308 309 310
		zone->zone_start_pfn = start_pfn;

	zone->spanned_pages = max(old_zone_end_pfn, end_pfn) -
				zone->zone_start_pfn;

	zone_span_writeunlock(zone);
}

311 312 313 314 315
static void resize_zone(struct zone *zone, unsigned long start_pfn,
		unsigned long end_pfn)
{
	zone_span_writelock(zone);

316 317 318 319 320 321 322 323 324 325 326
	if (end_pfn - start_pfn) {
		zone->zone_start_pfn = start_pfn;
		zone->spanned_pages = end_pfn - start_pfn;
	} else {
		/*
		 * make it consist as free_area_init_core(),
		 * if spanned_pages = 0, then keep start_pfn = 0
		 */
		zone->zone_start_pfn = 0;
		zone->spanned_pages = 0;
	}
327 328 329 330 331 332 333 334 335 336 337 338 339 340 341

	zone_span_writeunlock(zone);
}

static void fix_zone_id(struct zone *zone, unsigned long start_pfn,
		unsigned long end_pfn)
{
	enum zone_type zid = zone_idx(zone);
	int nid = zone->zone_pgdat->node_id;
	unsigned long pfn;

	for (pfn = start_pfn; pfn < end_pfn; pfn++)
		set_page_links(pfn_to_page(pfn), zid, nid, pfn);
}

342
/* Can fail with -ENOMEM from allocating a wait table with vmalloc() or
343
 * alloc_bootmem_node_nopanic()/memblock_virt_alloc_node_nopanic() */
344 345 346 347
static int __ref ensure_zone_is_initialized(struct zone *zone,
			unsigned long start_pfn, unsigned long num_pages)
{
	if (!zone_is_initialized(zone))
348 349
		return init_currently_empty_zone(zone, start_pfn, num_pages);

350 351 352
	return 0;
}

353
static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2,
354 355
		unsigned long start_pfn, unsigned long end_pfn)
{
356
	int ret;
357
	unsigned long flags;
358 359
	unsigned long z1_start_pfn;

360 361 362
	ret = ensure_zone_is_initialized(z1, start_pfn, end_pfn - start_pfn);
	if (ret)
		return ret;
363 364 365 366

	pgdat_resize_lock(z1->zone_pgdat, &flags);

	/* can't move pfns which are higher than @z2 */
367
	if (end_pfn > zone_end_pfn(z2))
368
		goto out_fail;
369
	/* the move out part must be at the left most of @z2 */
370 371 372 373 374 375
	if (start_pfn > z2->zone_start_pfn)
		goto out_fail;
	/* must included/overlap */
	if (end_pfn <= z2->zone_start_pfn)
		goto out_fail;

376
	/* use start_pfn for z1's start_pfn if z1 is empty */
377
	if (!zone_is_empty(z1))
378 379 380 381 382
		z1_start_pfn = z1->zone_start_pfn;
	else
		z1_start_pfn = start_pfn;

	resize_zone(z1, z1_start_pfn, end_pfn);
383
	resize_zone(z2, end_pfn, zone_end_pfn(z2));
384 385 386 387 388 389 390 391 392 393 394

	pgdat_resize_unlock(z1->zone_pgdat, &flags);

	fix_zone_id(z1, start_pfn, end_pfn);

	return 0;
out_fail:
	pgdat_resize_unlock(z1->zone_pgdat, &flags);
	return -1;
}

395
static int __meminit move_pfn_range_right(struct zone *z1, struct zone *z2,
396 397
		unsigned long start_pfn, unsigned long end_pfn)
{
398
	int ret;
399
	unsigned long flags;
400 401
	unsigned long z2_end_pfn;

402 403 404
	ret = ensure_zone_is_initialized(z2, start_pfn, end_pfn - start_pfn);
	if (ret)
		return ret;
405 406 407 408 409 410 411

	pgdat_resize_lock(z1->zone_pgdat, &flags);

	/* can't move pfns which are lower than @z1 */
	if (z1->zone_start_pfn > start_pfn)
		goto out_fail;
	/* the move out part mast at the right most of @z1 */
412
	if (zone_end_pfn(z1) >  end_pfn)
413 414
		goto out_fail;
	/* must included/overlap */
415
	if (start_pfn >= zone_end_pfn(z1))
416 417
		goto out_fail;

418
	/* use end_pfn for z2's end_pfn if z2 is empty */
419
	if (!zone_is_empty(z2))
420
		z2_end_pfn = zone_end_pfn(z2);
421 422 423
	else
		z2_end_pfn = end_pfn;

424
	resize_zone(z1, z1->zone_start_pfn, start_pfn);
425
	resize_zone(z2, start_pfn, z2_end_pfn);
426 427 428 429 430 431 432 433 434 435 436

	pgdat_resize_unlock(z1->zone_pgdat, &flags);

	fix_zone_id(z2, start_pfn, end_pfn);

	return 0;
out_fail:
	pgdat_resize_unlock(z1->zone_pgdat, &flags);
	return -1;
}

437 438
static void __meminit grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn,
				      unsigned long end_pfn)
439
{
440
	unsigned long old_pgdat_end_pfn = pgdat_end_pfn(pgdat);
441

442
	if (!pgdat->node_spanned_pages || start_pfn < pgdat->node_start_pfn)
443 444 445 446 447 448
		pgdat->node_start_pfn = start_pfn;

	pgdat->node_spanned_pages = max(old_pgdat_end_pfn, end_pfn) -
					pgdat->node_start_pfn;
}

A
Al Viro 已提交
449
static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
450 451 452 453 454
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	int nr_pages = PAGES_PER_SECTION;
	int nid = pgdat->node_id;
	int zone_type;
455
	unsigned long flags, pfn;
456
	int ret;
457 458

	zone_type = zone - pgdat->node_zones;
459 460 461
	ret = ensure_zone_is_initialized(zone, phys_start_pfn, nr_pages);
	if (ret)
		return ret;
462 463 464 465 466 467

	pgdat_resize_lock(zone->zone_pgdat, &flags);
	grow_zone_span(zone, phys_start_pfn, phys_start_pfn + nr_pages);
	grow_pgdat_span(zone->zone_pgdat, phys_start_pfn,
			phys_start_pfn + nr_pages);
	pgdat_resize_unlock(zone->zone_pgdat, &flags);
D
Dave Hansen 已提交
468 469
	memmap_init_zone(nr_pages, nid, zone_type,
			 phys_start_pfn, MEMMAP_HOTPLUG);
470 471 472 473 474 475 476 477

	/* online_page_range is called later and expects pages reserved */
	for (pfn = phys_start_pfn; pfn < phys_start_pfn + nr_pages; pfn++) {
		if (!pfn_valid(pfn))
			continue;

		SetPageReserved(pfn_to_page(pfn));
	}
478
	return 0;
479 480
}

481 482
static int __meminit __add_section(int nid, struct zone *zone,
					unsigned long phys_start_pfn)
483 484 485
{
	int ret;

486 487 488
	if (pfn_valid(phys_start_pfn))
		return -EEXIST;

489
	ret = sparse_add_one_section(zone, phys_start_pfn);
490 491 492 493

	if (ret < 0)
		return ret;

494 495 496 497 498
	ret = __add_zone(zone, phys_start_pfn);

	if (ret < 0)
		return ret;

499
	return register_new_memory(nid, __pfn_to_section(phys_start_pfn));
500 501
}

502 503 504 505 506 507 508 509 510 511 512 513
/*
 * Reasonably generic function for adding memory.  It is
 * expected that archs that support memory hotplug will
 * call this function after deciding the zone to which to
 * add the new pages.
 */
int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
			unsigned long nr_pages)
{
	unsigned long i;
	int err = 0;
	int start_sec, end_sec;
514 515
	struct vmem_altmap *altmap;

516 517
	clear_zone_contiguous(zone);

518 519 520 521
	/* during initialize mem_map, align hot-added range to section */
	start_sec = pfn_to_section_nr(phys_start_pfn);
	end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1);

522 523 524 525 526 527 528 529
	altmap = to_vmem_altmap((unsigned long) pfn_to_page(phys_start_pfn));
	if (altmap) {
		/*
		 * Validate altmap is within bounds of the total request
		 */
		if (altmap->base_pfn != phys_start_pfn
				|| vmem_altmap_offset(altmap) > nr_pages) {
			pr_warn_once("memory add fail, invalid altmap\n");
530 531
			err = -EINVAL;
			goto out;
532 533 534 535
		}
		altmap->alloc = 0;
	}

536
	for (i = start_sec; i <= end_sec; i++) {
537
		err = __add_section(nid, zone, section_nr_to_pfn(i));
538 539 540 541 542 543 544 545 546 547

		/*
		 * EEXIST is finally dealt with by ioresource collision
		 * check. see add_memory() => register_memory_resource()
		 * Warning will be printed if there is collision.
		 */
		if (err && (err != -EEXIST))
			break;
		err = 0;
	}
548
	vmemmap_populate_print_last();
549 550
out:
	set_zone_contiguous(zone);
551 552 553 554 555
	return err;
}
EXPORT_SYMBOL_GPL(__add_pages);

#ifdef CONFIG_MEMORY_HOTREMOVE
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
/* find the smallest valid pfn in the range [start_pfn, end_pfn) */
static int find_smallest_section_pfn(int nid, struct zone *zone,
				     unsigned long start_pfn,
				     unsigned long end_pfn)
{
	struct mem_section *ms;

	for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SECTION) {
		ms = __pfn_to_section(start_pfn);

		if (unlikely(!valid_section(ms)))
			continue;

		if (unlikely(pfn_to_nid(start_pfn) != nid))
			continue;

		if (zone && zone != page_zone(pfn_to_page(start_pfn)))
			continue;

		return start_pfn;
	}

	return 0;
}

/* find the biggest valid pfn in the range [start_pfn, end_pfn). */
static int find_biggest_section_pfn(int nid, struct zone *zone,
				    unsigned long start_pfn,
				    unsigned long end_pfn)
{
	struct mem_section *ms;
	unsigned long pfn;

	/* pfn is the end pfn of a memory section. */
	pfn = end_pfn - 1;
	for (; pfn >= start_pfn; pfn -= PAGES_PER_SECTION) {
		ms = __pfn_to_section(pfn);

		if (unlikely(!valid_section(ms)))
			continue;

		if (unlikely(pfn_to_nid(pfn) != nid))
			continue;

		if (zone && zone != page_zone(pfn_to_page(pfn)))
			continue;

		return pfn;
	}

	return 0;
}

static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
			     unsigned long end_pfn)
{
612 613 614
	unsigned long zone_start_pfn = zone->zone_start_pfn;
	unsigned long z = zone_end_pfn(zone); /* zone_end_pfn namespace clash */
	unsigned long zone_end_pfn = z;
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
	unsigned long pfn;
	struct mem_section *ms;
	int nid = zone_to_nid(zone);

	zone_span_writelock(zone);
	if (zone_start_pfn == start_pfn) {
		/*
		 * If the section is smallest section in the zone, it need
		 * shrink zone->zone_start_pfn and zone->zone_spanned_pages.
		 * In this case, we find second smallest valid mem_section
		 * for shrinking zone.
		 */
		pfn = find_smallest_section_pfn(nid, zone, end_pfn,
						zone_end_pfn);
		if (pfn) {
			zone->zone_start_pfn = pfn;
			zone->spanned_pages = zone_end_pfn - pfn;
		}
	} else if (zone_end_pfn == end_pfn) {
		/*
		 * If the section is biggest section in the zone, it need
		 * shrink zone->spanned_pages.
		 * In this case, we find second biggest valid mem_section for
		 * shrinking zone.
		 */
		pfn = find_biggest_section_pfn(nid, zone, zone_start_pfn,
					       start_pfn);
		if (pfn)
			zone->spanned_pages = pfn - zone_start_pfn + 1;
	}

	/*
	 * The section is not biggest or smallest mem_section in the zone, it
	 * only creates a hole in the zone. So in this case, we need not
	 * change the zone. But perhaps, the zone has only hole data. Thus
	 * it check the zone has only hole or not.
	 */
	pfn = zone_start_pfn;
	for (; pfn < zone_end_pfn; pfn += PAGES_PER_SECTION) {
		ms = __pfn_to_section(pfn);

		if (unlikely(!valid_section(ms)))
			continue;

		if (page_zone(pfn_to_page(pfn)) != zone)
			continue;

		 /* If the section is current section, it continues the loop */
		if (start_pfn == pfn)
			continue;

		/* If we find valid section, we have nothing to do */
		zone_span_writeunlock(zone);
		return;
	}

	/* The zone has no valid section */
	zone->zone_start_pfn = 0;
	zone->spanned_pages = 0;
	zone_span_writeunlock(zone);
}

static void shrink_pgdat_span(struct pglist_data *pgdat,
			      unsigned long start_pfn, unsigned long end_pfn)
{
680 681 682
	unsigned long pgdat_start_pfn = pgdat->node_start_pfn;
	unsigned long p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */
	unsigned long pgdat_end_pfn = p;
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
	unsigned long pfn;
	struct mem_section *ms;
	int nid = pgdat->node_id;

	if (pgdat_start_pfn == start_pfn) {
		/*
		 * If the section is smallest section in the pgdat, it need
		 * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages.
		 * In this case, we find second smallest valid mem_section
		 * for shrinking zone.
		 */
		pfn = find_smallest_section_pfn(nid, NULL, end_pfn,
						pgdat_end_pfn);
		if (pfn) {
			pgdat->node_start_pfn = pfn;
			pgdat->node_spanned_pages = pgdat_end_pfn - pfn;
		}
	} else if (pgdat_end_pfn == end_pfn) {
		/*
		 * If the section is biggest section in the pgdat, it need
		 * shrink pgdat->node_spanned_pages.
		 * In this case, we find second biggest valid mem_section for
		 * shrinking zone.
		 */
		pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn,
					       start_pfn);
		if (pfn)
			pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1;
	}

	/*
	 * If the section is not biggest or smallest mem_section in the pgdat,
	 * it only creates a hole in the pgdat. So in this case, we need not
	 * change the pgdat.
	 * But perhaps, the pgdat has only hole data. Thus it check the pgdat
	 * has only hole or not.
	 */
	pfn = pgdat_start_pfn;
	for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SECTION) {
		ms = __pfn_to_section(pfn);

		if (unlikely(!valid_section(ms)))
			continue;

		if (pfn_to_nid(pfn) != nid)
			continue;

		 /* If the section is current section, it continues the loop */
		if (start_pfn == pfn)
			continue;

		/* If we find valid section, we have nothing to do */
		return;
	}

	/* The pgdat has no valid section */
	pgdat->node_start_pfn = 0;
	pgdat->node_spanned_pages = 0;
}

static void __remove_zone(struct zone *zone, unsigned long start_pfn)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	int nr_pages = PAGES_PER_SECTION;
	int zone_type;
	unsigned long flags;

	zone_type = zone - pgdat->node_zones;

	pgdat_resize_lock(zone->zone_pgdat, &flags);
	shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
	shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages);
	pgdat_resize_unlock(zone->zone_pgdat, &flags);
}

758 759
static int __remove_section(struct zone *zone, struct mem_section *ms,
		unsigned long map_offset)
760
{
761 762
	unsigned long start_pfn;
	int scn_nr;
763 764 765 766 767 768 769 770 771
	int ret = -EINVAL;

	if (!valid_section(ms))
		return ret;

	ret = unregister_memory_section(ms);
	if (ret)
		return ret;

772 773 774 775
	scn_nr = __section_nr(ms);
	start_pfn = section_nr_to_pfn(scn_nr);
	__remove_zone(zone, start_pfn);

776
	sparse_remove_one_section(zone, ms, map_offset);
777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793
	return 0;
}

/**
 * __remove_pages() - remove sections of pages from a zone
 * @zone: zone from which pages need to be removed
 * @phys_start_pfn: starting pageframe (must be aligned to start of a section)
 * @nr_pages: number of pages to remove (must be multiple of section size)
 *
 * Generic helper function to remove section mappings and sysfs entries
 * for the section of the memory we are removing. Caller needs to make
 * sure that pages are marked reserved and zones are adjust properly by
 * calling offline_pages().
 */
int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
		 unsigned long nr_pages)
{
794
	unsigned long i;
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
	unsigned long map_offset = 0;
	int sections_to_remove, ret = 0;

	/* In the ZONE_DEVICE case device driver owns the memory region */
	if (is_dev_zone(zone)) {
		struct page *page = pfn_to_page(phys_start_pfn);
		struct vmem_altmap *altmap;

		altmap = to_vmem_altmap((unsigned long) page);
		if (altmap)
			map_offset = vmem_altmap_offset(altmap);
	} else {
		resource_size_t start, size;

		start = phys_start_pfn << PAGE_SHIFT;
		size = nr_pages * PAGE_SIZE;

		ret = release_mem_region_adjustable(&iomem_resource, start,
					size);
		if (ret) {
			resource_size_t endres = start + size - 1;

			pr_warn("Unable to release resource <%pa-%pa> (%d)\n",
					&start, &endres, ret);
		}
	}
821

822 823
	clear_zone_contiguous(zone);

824 825 826 827 828 829 830 831 832
	/*
	 * We can only remove entire sections
	 */
	BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK);
	BUG_ON(nr_pages % PAGES_PER_SECTION);

	sections_to_remove = nr_pages / PAGES_PER_SECTION;
	for (i = 0; i < sections_to_remove; i++) {
		unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION;
833 834 835

		ret = __remove_section(zone, __pfn_to_section(pfn), map_offset);
		map_offset = 0;
836 837 838
		if (ret)
			break;
	}
839 840 841

	set_zone_contiguous(zone);

842 843 844
	return ret;
}
EXPORT_SYMBOL_GPL(__remove_pages);
845
#endif /* CONFIG_MEMORY_HOTREMOVE */
846

847 848 849 850
int set_online_page_callback(online_page_callback_t callback)
{
	int rc = -EINVAL;

851 852
	get_online_mems();
	mutex_lock(&online_page_callback_lock);
853 854 855 856 857 858

	if (online_page_callback == generic_online_page) {
		online_page_callback = callback;
		rc = 0;
	}

859 860
	mutex_unlock(&online_page_callback_lock);
	put_online_mems();
861 862 863 864 865 866 867 868 869

	return rc;
}
EXPORT_SYMBOL_GPL(set_online_page_callback);

int restore_online_page_callback(online_page_callback_t callback)
{
	int rc = -EINVAL;

870 871
	get_online_mems();
	mutex_lock(&online_page_callback_lock);
872 873 874 875 876 877

	if (online_page_callback == callback) {
		online_page_callback = generic_online_page;
		rc = 0;
	}

878 879
	mutex_unlock(&online_page_callback_lock);
	put_online_mems();
880 881 882 883 884 885

	return rc;
}
EXPORT_SYMBOL_GPL(restore_online_page_callback);

void __online_page_set_limits(struct page *page)
886
{
887 888 889 890 891
}
EXPORT_SYMBOL_GPL(__online_page_set_limits);

void __online_page_increment_counters(struct page *page)
{
892
	adjust_managed_page_count(page, 1);
893 894
}
EXPORT_SYMBOL_GPL(__online_page_increment_counters);
895

896 897
void __online_page_free(struct page *page)
{
898
	__free_reserved_page(page);
899
}
900 901 902 903 904 905 906 907
EXPORT_SYMBOL_GPL(__online_page_free);

static void generic_online_page(struct page *page)
{
	__online_page_set_limits(page);
	__online_page_increment_counters(page);
	__online_page_free(page);
}
908

909 910
static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
			void *arg)
911 912
{
	unsigned long i;
913 914 915 916 917
	unsigned long onlined_pages = *(unsigned long *)arg;
	struct page *page;
	if (PageReserved(pfn_to_page(start_pfn)))
		for (i = 0; i < nr_pages; i++) {
			page = pfn_to_page(start_pfn + i);
918
			(*online_page_callback)(page);
919 920 921 922 923 924
			onlined_pages++;
		}
	*(unsigned long *)arg = onlined_pages;
	return 0;
}

925
#ifdef CONFIG_MOVABLE_NODE
T
Tang Chen 已提交
926 927 928 929
/*
 * When CONFIG_MOVABLE_NODE, we permit onlining of a node which doesn't have
 * normal memory.
 */
930 931 932 933
static bool can_online_high_movable(struct zone *zone)
{
	return true;
}
T
Tang Chen 已提交
934
#else /* CONFIG_MOVABLE_NODE */
935 936 937 938 939
/* ensure every online node has NORMAL memory */
static bool can_online_high_movable(struct zone *zone)
{
	return node_state(zone_to_nid(zone), N_NORMAL_MEMORY);
}
T
Tang Chen 已提交
940
#endif /* CONFIG_MOVABLE_NODE */
941

942 943 944 945 946 947 948 949
/* check which state of node_states will be changed when online memory */
static void node_states_check_changes_online(unsigned long nr_pages,
	struct zone *zone, struct memory_notify *arg)
{
	int nid = zone_to_nid(zone);
	enum zone_type zone_last = ZONE_NORMAL;

	/*
950 951 952
	 * If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY]
	 * contains nodes which have zones of 0...ZONE_NORMAL,
	 * set zone_last to ZONE_NORMAL.
953
	 *
954 955 956
	 * If we don't have HIGHMEM nor movable node,
	 * node_states[N_NORMAL_MEMORY] contains nodes which have zones of
	 * 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
957
	 */
958
	if (N_MEMORY == N_NORMAL_MEMORY)
959 960 961 962 963 964 965 966 967 968 969 970 971
		zone_last = ZONE_MOVABLE;

	/*
	 * if the memory to be online is in a zone of 0...zone_last, and
	 * the zones of 0...zone_last don't have memory before online, we will
	 * need to set the node to node_states[N_NORMAL_MEMORY] after
	 * the memory is online.
	 */
	if (zone_idx(zone) <= zone_last && !node_state(nid, N_NORMAL_MEMORY))
		arg->status_change_nid_normal = nid;
	else
		arg->status_change_nid_normal = -1;

972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993
#ifdef CONFIG_HIGHMEM
	/*
	 * If we have movable node, node_states[N_HIGH_MEMORY]
	 * contains nodes which have zones of 0...ZONE_HIGHMEM,
	 * set zone_last to ZONE_HIGHMEM.
	 *
	 * If we don't have movable node, node_states[N_NORMAL_MEMORY]
	 * contains nodes which have zones of 0...ZONE_MOVABLE,
	 * set zone_last to ZONE_MOVABLE.
	 */
	zone_last = ZONE_HIGHMEM;
	if (N_MEMORY == N_HIGH_MEMORY)
		zone_last = ZONE_MOVABLE;

	if (zone_idx(zone) <= zone_last && !node_state(nid, N_HIGH_MEMORY))
		arg->status_change_nid_high = nid;
	else
		arg->status_change_nid_high = -1;
#else
	arg->status_change_nid_high = arg->status_change_nid_normal;
#endif

994 995
	/*
	 * if the node don't have memory befor online, we will need to
996
	 * set the node to node_states[N_MEMORY] after the memory
997 998
	 * is online.
	 */
999
	if (!node_state(nid, N_MEMORY))
1000 1001 1002 1003 1004 1005 1006 1007 1008 1009
		arg->status_change_nid = nid;
	else
		arg->status_change_nid = -1;
}

static void node_states_set_node(int node, struct memory_notify *arg)
{
	if (arg->status_change_nid_normal >= 0)
		node_set_state(node, N_NORMAL_MEMORY);

1010 1011 1012 1013
	if (arg->status_change_nid_high >= 0)
		node_set_state(node, N_HIGH_MEMORY);

	node_set_state(node, N_MEMORY);
1014 1015
}

1016

1017
/* Must be protected by mem_hotplug_begin() */
1018
int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type)
1019
{
1020
	unsigned long flags;
1021 1022
	unsigned long onlined_pages = 0;
	struct zone *zone;
1023
	int need_zonelists_rebuild = 0;
1024 1025 1026 1027
	int nid;
	int ret;
	struct memory_notify arg;

1028 1029 1030 1031 1032 1033 1034
	/*
	 * This doesn't need a lock to do pfn_to_page().
	 * The section can't be removed here because of the
	 * memory_block->state_mutex.
	 */
	zone = page_zone(pfn_to_page(pfn));

1035 1036
	if ((zone_idx(zone) > ZONE_NORMAL ||
	    online_type == MMOP_ONLINE_MOVABLE) &&
1037
	    !can_online_high_movable(zone))
1038
		return -EINVAL;
1039

1040 1041
	if (online_type == MMOP_ONLINE_KERNEL &&
	    zone_idx(zone) == ZONE_MOVABLE) {
1042
		if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages))
1043
			return -EINVAL;
1044
	}
1045 1046
	if (online_type == MMOP_ONLINE_MOVABLE &&
	    zone_idx(zone) == ZONE_MOVABLE - 1) {
1047
		if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages))
1048
			return -EINVAL;
1049 1050 1051 1052 1053
	}

	/* Previous code may changed the zone of the pfn range */
	zone = page_zone(pfn_to_page(pfn));

1054 1055
	arg.start_pfn = pfn;
	arg.nr_pages = nr_pages;
1056
	node_states_check_changes_online(nr_pages, zone, &arg);
1057

1058
	nid = zone_to_nid(zone);
1059

1060 1061 1062 1063
	ret = memory_notify(MEM_GOING_ONLINE, &arg);
	ret = notifier_to_errno(ret);
	if (ret) {
		memory_notify(MEM_CANCEL_ONLINE, &arg);
1064
		return ret;
1065
	}
1066 1067 1068 1069 1070
	/*
	 * If this zone is not populated, then it is not in zonelist.
	 * This means the page allocator ignores this zone.
	 * So, zonelist must be updated after online.
	 */
1071
	mutex_lock(&zonelists_mutex);
1072
	if (!populated_zone(zone)) {
1073
		need_zonelists_rebuild = 1;
1074 1075
		build_all_zonelists(NULL, zone);
	}
1076

K
KAMEZAWA Hiroyuki 已提交
1077
	ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
1078
		online_pages_range);
1079
	if (ret) {
1080 1081
		if (need_zonelists_rebuild)
			zone_pcp_reset(zone);
1082
		mutex_unlock(&zonelists_mutex);
1083 1084 1085 1086
		printk(KERN_DEBUG "online_pages [mem %#010llx-%#010llx] failed\n",
		       (unsigned long long) pfn << PAGE_SHIFT,
		       (((unsigned long long) pfn + nr_pages)
			    << PAGE_SHIFT) - 1);
1087
		memory_notify(MEM_CANCEL_ONLINE, &arg);
1088
		return ret;
1089 1090
	}

1091
	zone->present_pages += onlined_pages;
1092 1093

	pgdat_resize_lock(zone->zone_pgdat, &flags);
1094
	zone->zone_pgdat->node_present_pages += onlined_pages;
1095 1096
	pgdat_resize_unlock(zone->zone_pgdat, &flags);

1097
	if (onlined_pages) {
1098
		node_states_set_node(nid, &arg);
1099
		if (need_zonelists_rebuild)
1100
			build_all_zonelists(NULL, NULL);
1101 1102 1103
		else
			zone_pcp_update(zone);
	}
1104

1105
	mutex_unlock(&zonelists_mutex);
1106 1107 1108

	init_per_zone_wmark_min();

1109
	if (onlined_pages) {
1110
		kswapd_run(nid);
1111 1112
		kcompactd_run(nid);
	}
1113

1114
	vm_total_pages = nr_free_pagecache_pages();
1115

1116
	writeback_set_ratelimit();
1117 1118 1119

	if (onlined_pages)
		memory_notify(MEM_ONLINE, &arg);
1120
	return 0;
1121
}
1122
#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
1123

1124 1125 1126 1127 1128 1129 1130 1131 1132 1133
static void reset_node_present_pages(pg_data_t *pgdat)
{
	struct zone *z;

	for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
		z->present_pages = 0;

	pgdat->node_present_pages = 0;
}

1134 1135
/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start)
1136 1137 1138 1139
{
	struct pglist_data *pgdat;
	unsigned long zones_size[MAX_NR_ZONES] = {0};
	unsigned long zholes_size[MAX_NR_ZONES] = {0};
1140
	unsigned long start_pfn = PFN_DOWN(start);
1141

1142 1143 1144 1145 1146
	pgdat = NODE_DATA(nid);
	if (!pgdat) {
		pgdat = arch_alloc_nodedata(nid);
		if (!pgdat)
			return NULL;
1147

1148
		arch_refresh_nodedata(nid, pgdat);
1149 1150 1151 1152
	} else {
		/* Reset the nr_zones and classzone_idx to 0 before reuse */
		pgdat->nr_zones = 0;
		pgdat->classzone_idx = 0;
1153
	}
1154 1155 1156 1157

	/* we can use NODE_DATA(nid) from here */

	/* init node's zones as empty zones, we don't have any present pages.*/
1158
	free_area_init_node(nid, zones_size, start_pfn, zholes_size);
1159

1160 1161 1162 1163
	/*
	 * The node we allocated has no zone fallback lists. For avoiding
	 * to access not-initialized zonelist, build here.
	 */
1164
	mutex_lock(&zonelists_mutex);
1165
	build_all_zonelists(pgdat, NULL);
1166
	mutex_unlock(&zonelists_mutex);
1167

1168 1169 1170 1171 1172 1173 1174 1175
	/*
	 * zone->managed_pages is set to an approximate value in
	 * free_area_init_core(), which will cause
	 * /sys/device/system/node/nodeX/meminfo has wrong data.
	 * So reset it to 0 before any memory is onlined.
	 */
	reset_node_managed_pages(pgdat);

1176 1177 1178 1179 1180 1181 1182
	/*
	 * When memory is hot-added, all the memory is in offline state. So
	 * clear all zones' present_pages because they will be updated in
	 * online_pages() and offline_pages().
	 */
	reset_node_present_pages(pgdat);

1183 1184 1185 1186 1187 1188 1189 1190 1191 1192
	return pgdat;
}

static void rollback_node_hotadd(int nid, pg_data_t *pgdat)
{
	arch_refresh_nodedata(nid, NULL);
	arch_free_nodedata(pgdat);
	return;
}

1193

1194 1195 1196
/**
 * try_online_node - online a node if offlined
 *
1197 1198
 * called by cpu_up() to online a node without onlined memory.
 */
1199
int try_online_node(int nid)
1200 1201 1202 1203
{
	pg_data_t	*pgdat;
	int	ret;

1204 1205 1206
	if (node_online(nid))
		return 0;

1207
	mem_hotplug_begin();
1208
	pgdat = hotadd_new_pgdat(nid, 0);
1209
	if (!pgdat) {
1210
		pr_err("Cannot online node %d due to NULL pgdat\n", nid);
1211 1212 1213 1214 1215 1216 1217
		ret = -ENOMEM;
		goto out;
	}
	node_set_online(nid);
	ret = register_one_node(nid);
	BUG_ON(ret);

1218 1219 1220 1221 1222 1223
	if (pgdat->node_zonelists->_zonerefs->zone == NULL) {
		mutex_lock(&zonelists_mutex);
		build_all_zonelists(NULL, NULL);
		mutex_unlock(&zonelists_mutex);
	}

1224
out:
1225
	mem_hotplug_done();
1226 1227 1228
	return ret;
}

1229 1230
static int check_hotplug_memory_range(u64 start, u64 size)
{
1231
	u64 start_pfn = PFN_DOWN(start);
1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245
	u64 nr_pages = size >> PAGE_SHIFT;

	/* Memory range must be aligned with section */
	if ((start_pfn & ~PAGE_SECTION_MASK) ||
	    (nr_pages % PAGES_PER_SECTION) || (!nr_pages)) {
		pr_err("Section-unaligned hotplug range: start 0x%llx, size 0x%llx\n",
				(unsigned long long)start,
				(unsigned long long)size);
		return -EINVAL;
	}

	return 0;
}

1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265
/*
 * If movable zone has already been setup, newly added memory should be check.
 * If its address is higher than movable zone, it should be added as movable.
 * Without this check, movable zone may overlap with other zone.
 */
static int should_add_memory_movable(int nid, u64 start, u64 size)
{
	unsigned long start_pfn = start >> PAGE_SHIFT;
	pg_data_t *pgdat = NODE_DATA(nid);
	struct zone *movable_zone = pgdat->node_zones + ZONE_MOVABLE;

	if (zone_is_empty(movable_zone))
		return 0;

	if (movable_zone->zone_start_pfn <= start_pfn)
		return 1;

	return 0;
}

1266 1267
int zone_for_memory(int nid, u64 start, u64 size, int zone_default,
		bool for_device)
1268
{
1269 1270 1271 1272
#ifdef CONFIG_ZONE_DEVICE
	if (for_device)
		return ZONE_DEVICE;
#endif
1273 1274 1275 1276 1277 1278
	if (should_add_memory_movable(nid, start, size))
		return ZONE_MOVABLE;

	return zone_default;
}

1279 1280 1281 1282 1283
static int online_memory_block(struct memory_block *mem, void *arg)
{
	return memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE);
}

A
Al Viro 已提交
1284
/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
1285
int __ref add_memory_resource(int nid, struct resource *res, bool online)
1286
{
1287
	u64 start, size;
1288
	pg_data_t *pgdat = NULL;
1289 1290
	bool new_pgdat;
	bool new_node;
1291 1292
	int ret;

1293 1294 1295
	start = res->start;
	size = resource_size(res);

1296 1297 1298 1299
	ret = check_hotplug_memory_range(start, size);
	if (ret)
		return ret;

1300 1301 1302 1303
	{	/* Stupid hack to suppress address-never-null warning */
		void *p = NODE_DATA(nid);
		new_pgdat = !p;
	}
1304

1305
	mem_hotplug_begin();
1306

1307 1308 1309 1310 1311 1312 1313 1314
	/*
	 * Add new range to memblock so that when hotadd_new_pgdat() is called
	 * to allocate new pgdat, get_pfn_range_for_nid() will be able to find
	 * this new range and calculate total pages correctly.  The range will
	 * be removed at hot-remove time.
	 */
	memblock_add_node(start, size, nid);

1315 1316
	new_node = !node_online(nid);
	if (new_node) {
1317
		pgdat = hotadd_new_pgdat(nid, start);
1318
		ret = -ENOMEM;
1319
		if (!pgdat)
1320
			goto error;
1321 1322
	}

1323
	/* call arch's memory hotadd */
1324
	ret = arch_add_memory(nid, start, size, false);
1325

1326 1327 1328
	if (ret < 0)
		goto error;

1329
	/* we online node here. we can't roll back from here. */
1330 1331
	node_set_online(nid);

1332
	if (new_node) {
1333 1334 1335 1336 1337 1338 1339 1340 1341
		ret = register_one_node(nid);
		/*
		 * If sysfs file of new node can't create, cpu on the node
		 * can't be hot-added. There is no rollback way now.
		 * So, check by BUG_ON() to catch it reluctantly..
		 */
		BUG_ON(ret);
	}

1342 1343 1344
	/* create new memmap entry */
	firmware_map_add_hotplug(start, start + size, "System RAM");

1345 1346 1347 1348 1349
	/* online pages if requested */
	if (online)
		walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1),
				  NULL, online_memory_block);

1350 1351
	goto out;

1352 1353 1354 1355
error:
	/* rollback pgdat allocation and others */
	if (new_pgdat)
		rollback_node_hotadd(nid, pgdat);
1356
	memblock_remove(start, size);
1357

1358
out:
1359
	mem_hotplug_done();
1360 1361
	return ret;
}
1362 1363 1364 1365 1366 1367 1368 1369
EXPORT_SYMBOL_GPL(add_memory_resource);

int __ref add_memory(int nid, u64 start, u64 size)
{
	struct resource *res;
	int ret;

	res = register_memory_resource(start, size);
1370 1371
	if (IS_ERR(res))
		return PTR_ERR(res);
1372

1373
	ret = add_memory_resource(nid, res, memhp_auto_online);
1374 1375 1376 1377
	if (ret < 0)
		release_memory_resource(res);
	return ret;
}
1378
EXPORT_SYMBOL_GPL(add_memory);
K
KAMEZAWA Hiroyuki 已提交
1379 1380

#ifdef CONFIG_MEMORY_HOTREMOVE
1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399
/*
 * A free page on the buddy free lists (not the per-cpu lists) has PageBuddy
 * set and the size of the free page is given by page_order(). Using this,
 * the function determines if the pageblock contains only free pages.
 * Due to buddy contraints, a free page at least the size of a pageblock will
 * be located at the start of the pageblock
 */
static inline int pageblock_free(struct page *page)
{
	return PageBuddy(page) && page_order(page) >= pageblock_order;
}

/* Return the start of the next active pageblock after a given page */
static struct page *next_active_pageblock(struct page *page)
{
	/* Ensure the starting page is pageblock-aligned */
	BUG_ON(page_to_pfn(page) & (pageblock_nr_pages - 1));

	/* If the entire pageblock is free, move to the end of free page */
1400 1401 1402 1403 1404 1405 1406
	if (pageblock_free(page)) {
		int order;
		/* be careful. we don't have locks, page_order can be changed.*/
		order = page_order(page);
		if ((order < MAX_ORDER) && (order >= pageblock_order))
			return page + (1 << order);
	}
1407

1408
	return page + pageblock_nr_pages;
1409 1410 1411 1412 1413 1414 1415 1416 1417 1418
}

/* Checks if this range of memory is likely to be hot-removable. */
int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
{
	struct page *page = pfn_to_page(start_pfn);
	struct page *end_page = page + nr_pages;

	/* Check the starting page of each pageblock within the range */
	for (; page < end_page; page = next_active_pageblock(page)) {
1419
		if (!is_pageblock_removable_nolock(page))
1420
			return 0;
1421
		cond_resched();
1422 1423 1424 1425 1426 1427
	}

	/* All pageblocks in the memory block are likely to be hot-removable */
	return 1;
}

K
KAMEZAWA Hiroyuki 已提交
1428 1429 1430
/*
 * Confirm all pages in a range [start, end) is belongs to the same zone.
 */
1431
int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
K
KAMEZAWA Hiroyuki 已提交
1432
{
1433
	unsigned long pfn, sec_end_pfn;
K
KAMEZAWA Hiroyuki 已提交
1434 1435 1436
	struct zone *zone = NULL;
	struct page *page;
	int i;
1437
	for (pfn = start_pfn, sec_end_pfn = SECTION_ALIGN_UP(start_pfn);
K
KAMEZAWA Hiroyuki 已提交
1438
	     pfn < end_pfn;
1439 1440 1441
	     pfn = sec_end_pfn + 1, sec_end_pfn += PAGES_PER_SECTION) {
		/* Make sure the memory section is present first */
		if (!present_section_nr(pfn_to_section_nr(pfn)))
K
KAMEZAWA Hiroyuki 已提交
1442
			continue;
1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456
		for (; pfn < sec_end_pfn && pfn < end_pfn;
		     pfn += MAX_ORDER_NR_PAGES) {
			i = 0;
			/* This is just a CONFIG_HOLES_IN_ZONE check.*/
			while ((i < MAX_ORDER_NR_PAGES) &&
				!pfn_valid_within(pfn + i))
				i++;
			if (i == MAX_ORDER_NR_PAGES)
				continue;
			page = pfn_to_page(pfn + i);
			if (zone && page_zone(page) != zone)
				return 0;
			zone = page_zone(page);
		}
K
KAMEZAWA Hiroyuki 已提交
1457 1458 1459 1460 1461
	}
	return 1;
}

/*
1462 1463 1464 1465
 * Scan pfn range [start,end) to find movable/migratable pages (LRU pages
 * and hugepages). We scan pfn because it's much easier than scanning over
 * linked list. This function returns the pfn of the first found movable
 * page if it's found, otherwise 0.
K
KAMEZAWA Hiroyuki 已提交
1466
 */
1467
static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
K
KAMEZAWA Hiroyuki 已提交
1468 1469 1470 1471 1472 1473 1474 1475
{
	unsigned long pfn;
	struct page *page;
	for (pfn = start; pfn < end; pfn++) {
		if (pfn_valid(pfn)) {
			page = pfn_to_page(pfn);
			if (PageLRU(page))
				return pfn;
1476
			if (PageHuge(page)) {
1477
				if (page_huge_active(page))
1478 1479 1480 1481 1482
					return pfn;
				else
					pfn = round_up(pfn + 1,
						1 << compound_order(page)) - 1;
			}
K
KAMEZAWA Hiroyuki 已提交
1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502
		}
	}
	return 0;
}

#define NR_OFFLINE_AT_ONCE_PAGES	(256)
static int
do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned long pfn;
	struct page *page;
	int move_pages = NR_OFFLINE_AT_ONCE_PAGES;
	int not_managed = 0;
	int ret = 0;
	LIST_HEAD(source);

	for (pfn = start_pfn; pfn < end_pfn && move_pages > 0; pfn++) {
		if (!pfn_valid(pfn))
			continue;
		page = pfn_to_page(pfn);
1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515

		if (PageHuge(page)) {
			struct page *head = compound_head(page);
			pfn = page_to_pfn(head) + (1<<compound_order(head)) - 1;
			if (compound_order(head) > PFN_SECTION_SHIFT) {
				ret = -EBUSY;
				break;
			}
			if (isolate_huge_page(page, &source))
				move_pages -= 1 << compound_order(head);
			continue;
		}

1516
		if (!get_page_unless_zero(page))
K
KAMEZAWA Hiroyuki 已提交
1517 1518 1519 1520 1521
			continue;
		/*
		 * We can skip free pages. And we can only deal with pages on
		 * LRU.
		 */
1522
		ret = isolate_lru_page(page);
K
KAMEZAWA Hiroyuki 已提交
1523
		if (!ret) { /* Success */
1524
			put_page(page);
1525
			list_add_tail(&page->lru, &source);
K
KAMEZAWA Hiroyuki 已提交
1526
			move_pages--;
1527 1528 1529
			inc_zone_page_state(page, NR_ISOLATED_ANON +
					    page_is_file_cache(page));

K
KAMEZAWA Hiroyuki 已提交
1530 1531
		} else {
#ifdef CONFIG_DEBUG_VM
1532 1533
			printk(KERN_ALERT "removing pfn %lx from LRU failed\n",
			       pfn);
1534
			dump_page(page, "failed to remove from LRU");
K
KAMEZAWA Hiroyuki 已提交
1535
#endif
1536
			put_page(page);
L
Lucas De Marchi 已提交
1537
			/* Because we don't have big zone->lock. we should
1538 1539 1540
			   check this again here. */
			if (page_count(page)) {
				not_managed++;
1541
				ret = -EBUSY;
1542 1543
				break;
			}
K
KAMEZAWA Hiroyuki 已提交
1544 1545
		}
	}
1546 1547
	if (!list_empty(&source)) {
		if (not_managed) {
1548
			putback_movable_pages(&source);
1549 1550
			goto out;
		}
1551 1552 1553 1554 1555

		/*
		 * alloc_migrate_target should be improooooved!!
		 * migrate_pages returns # of failed pages.
		 */
1556
		ret = migrate_pages(&source, alloc_migrate_target, NULL, 0,
1557
					MIGRATE_SYNC, MR_MEMORY_HOTPLUG);
1558
		if (ret)
1559
			putback_movable_pages(&source);
K
KAMEZAWA Hiroyuki 已提交
1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578
	}
out:
	return ret;
}

/*
 * remove from free_area[] and mark all as Reserved.
 */
static int
offline_isolated_pages_cb(unsigned long start, unsigned long nr_pages,
			void *data)
{
	__offline_isolated_pages(start, start + nr_pages);
	return 0;
}

static void
offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
{
K
KAMEZAWA Hiroyuki 已提交
1579
	walk_system_ram_range(start_pfn, end_pfn - start_pfn, NULL,
K
KAMEZAWA Hiroyuki 已提交
1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591
				offline_isolated_pages_cb);
}

/*
 * Check all pages in range, recoreded as memory resource, are isolated.
 */
static int
check_pages_isolated_cb(unsigned long start_pfn, unsigned long nr_pages,
			void *data)
{
	int ret;
	long offlined = *(long *)data;
1592
	ret = test_pages_isolated(start_pfn, start_pfn + nr_pages, true);
K
KAMEZAWA Hiroyuki 已提交
1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604
	offlined = nr_pages;
	if (!ret)
		*(long *)data += offlined;
	return ret;
}

static long
check_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
{
	long offlined = 0;
	int ret;

K
KAMEZAWA Hiroyuki 已提交
1605
	ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn, &offlined,
K
KAMEZAWA Hiroyuki 已提交
1606 1607 1608 1609 1610 1611
			check_pages_isolated_cb);
	if (ret < 0)
		offlined = (long)ret;
	return offlined;
}

1612
#ifdef CONFIG_MOVABLE_NODE
T
Tang Chen 已提交
1613 1614 1615 1616
/*
 * When CONFIG_MOVABLE_NODE, we permit offlining of a node which doesn't have
 * normal memory.
 */
1617 1618 1619 1620
static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
{
	return true;
}
T
Tang Chen 已提交
1621
#else /* CONFIG_MOVABLE_NODE */
1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644
/* ensure the node has NORMAL memory if it is still online */
static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	unsigned long present_pages = 0;
	enum zone_type zt;

	for (zt = 0; zt <= ZONE_NORMAL; zt++)
		present_pages += pgdat->node_zones[zt].present_pages;

	if (present_pages > nr_pages)
		return true;

	present_pages = 0;
	for (; zt <= ZONE_MOVABLE; zt++)
		present_pages += pgdat->node_zones[zt].present_pages;

	/*
	 * we can't offline the last normal memory until all
	 * higher memory is offlined.
	 */
	return present_pages == 0;
}
T
Tang Chen 已提交
1645
#endif /* CONFIG_MOVABLE_NODE */
1646

1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669
static int __init cmdline_parse_movable_node(char *p)
{
#ifdef CONFIG_MOVABLE_NODE
	/*
	 * Memory used by the kernel cannot be hot-removed because Linux
	 * cannot migrate the kernel pages. When memory hotplug is
	 * enabled, we should prevent memblock from allocating memory
	 * for the kernel.
	 *
	 * ACPI SRAT records all hotpluggable memory ranges. But before
	 * SRAT is parsed, we don't know about it.
	 *
	 * The kernel image is loaded into memory at very early time. We
	 * cannot prevent this anyway. So on NUMA system, we set any
	 * node the kernel resides in as un-hotpluggable.
	 *
	 * Since on modern servers, one node could have double-digit
	 * gigabytes memory, we can assume the memory around the kernel
	 * image is also un-hotpluggable. So before SRAT is parsed, just
	 * allocate memory near the kernel image to try the best to keep
	 * the kernel away from hotpluggable memory.
	 */
	memblock_set_bottom_up(true);
1670
	movable_node_enabled = true;
1671 1672 1673 1674 1675 1676 1677
#else
	pr_warn("movable_node option not supported\n");
#endif
	return 0;
}
early_param("movable_node", cmdline_parse_movable_node);

1678 1679 1680 1681 1682 1683 1684 1685 1686
/* check which state of node_states will be changed when offline memory */
static void node_states_check_changes_offline(unsigned long nr_pages,
		struct zone *zone, struct memory_notify *arg)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	unsigned long present_pages = 0;
	enum zone_type zt, zone_last = ZONE_NORMAL;

	/*
1687 1688 1689
	 * If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY]
	 * contains nodes which have zones of 0...ZONE_NORMAL,
	 * set zone_last to ZONE_NORMAL.
1690
	 *
1691 1692 1693
	 * If we don't have HIGHMEM nor movable node,
	 * node_states[N_NORMAL_MEMORY] contains nodes which have zones of
	 * 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
1694
	 */
1695
	if (N_MEMORY == N_NORMAL_MEMORY)
1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711
		zone_last = ZONE_MOVABLE;

	/*
	 * check whether node_states[N_NORMAL_MEMORY] will be changed.
	 * If the memory to be offline is in a zone of 0...zone_last,
	 * and it is the last present memory, 0...zone_last will
	 * become empty after offline , thus we can determind we will
	 * need to clear the node from node_states[N_NORMAL_MEMORY].
	 */
	for (zt = 0; zt <= zone_last; zt++)
		present_pages += pgdat->node_zones[zt].present_pages;
	if (zone_idx(zone) <= zone_last && nr_pages >= present_pages)
		arg->status_change_nid_normal = zone_to_nid(zone);
	else
		arg->status_change_nid_normal = -1;

1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735
#ifdef CONFIG_HIGHMEM
	/*
	 * If we have movable node, node_states[N_HIGH_MEMORY]
	 * contains nodes which have zones of 0...ZONE_HIGHMEM,
	 * set zone_last to ZONE_HIGHMEM.
	 *
	 * If we don't have movable node, node_states[N_NORMAL_MEMORY]
	 * contains nodes which have zones of 0...ZONE_MOVABLE,
	 * set zone_last to ZONE_MOVABLE.
	 */
	zone_last = ZONE_HIGHMEM;
	if (N_MEMORY == N_HIGH_MEMORY)
		zone_last = ZONE_MOVABLE;

	for (; zt <= zone_last; zt++)
		present_pages += pgdat->node_zones[zt].present_pages;
	if (zone_idx(zone) <= zone_last && nr_pages >= present_pages)
		arg->status_change_nid_high = zone_to_nid(zone);
	else
		arg->status_change_nid_high = -1;
#else
	arg->status_change_nid_high = arg->status_change_nid_normal;
#endif

1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759
	/*
	 * node_states[N_HIGH_MEMORY] contains nodes which have 0...ZONE_MOVABLE
	 */
	zone_last = ZONE_MOVABLE;

	/*
	 * check whether node_states[N_HIGH_MEMORY] will be changed
	 * If we try to offline the last present @nr_pages from the node,
	 * we can determind we will need to clear the node from
	 * node_states[N_HIGH_MEMORY].
	 */
	for (; zt <= zone_last; zt++)
		present_pages += pgdat->node_zones[zt].present_pages;
	if (nr_pages >= present_pages)
		arg->status_change_nid = zone_to_nid(zone);
	else
		arg->status_change_nid = -1;
}

static void node_states_clear_node(int node, struct memory_notify *arg)
{
	if (arg->status_change_nid_normal >= 0)
		node_clear_state(node, N_NORMAL_MEMORY);

1760 1761
	if ((N_MEMORY != N_NORMAL_MEMORY) &&
	    (arg->status_change_nid_high >= 0))
1762
		node_clear_state(node, N_HIGH_MEMORY);
1763 1764 1765 1766

	if ((N_MEMORY != N_HIGH_MEMORY) &&
	    (arg->status_change_nid >= 0))
		node_clear_state(node, N_MEMORY);
1767 1768
}

1769
static int __ref __offline_pages(unsigned long start_pfn,
K
KAMEZAWA Hiroyuki 已提交
1770 1771 1772 1773
		  unsigned long end_pfn, unsigned long timeout)
{
	unsigned long pfn, nr_pages, expire;
	long offlined_pages;
1774
	int ret, drain, retry_max, node;
1775
	unsigned long flags;
K
KAMEZAWA Hiroyuki 已提交
1776
	struct zone *zone;
1777
	struct memory_notify arg;
K
KAMEZAWA Hiroyuki 已提交
1778 1779 1780 1781 1782 1783 1784 1785 1786 1787

	/* at least, alignment against pageblock is necessary */
	if (!IS_ALIGNED(start_pfn, pageblock_nr_pages))
		return -EINVAL;
	if (!IS_ALIGNED(end_pfn, pageblock_nr_pages))
		return -EINVAL;
	/* This makes hotplug much easier...and readable.
	   we assume this for now. .*/
	if (!test_pages_in_a_zone(start_pfn, end_pfn))
		return -EINVAL;
1788 1789 1790 1791 1792

	zone = page_zone(pfn_to_page(start_pfn));
	node = zone_to_nid(zone);
	nr_pages = end_pfn - start_pfn;

1793
	if (zone_idx(zone) <= ZONE_NORMAL && !can_offline_normal(zone, nr_pages))
1794
		return -EINVAL;
1795

K
KAMEZAWA Hiroyuki 已提交
1796
	/* set above range as isolated */
1797 1798
	ret = start_isolate_page_range(start_pfn, end_pfn,
				       MIGRATE_MOVABLE, true);
K
KAMEZAWA Hiroyuki 已提交
1799
	if (ret)
1800
		return ret;
1801 1802 1803

	arg.start_pfn = start_pfn;
	arg.nr_pages = nr_pages;
1804
	node_states_check_changes_offline(nr_pages, zone, &arg);
1805 1806 1807 1808 1809 1810

	ret = memory_notify(MEM_GOING_OFFLINE, &arg);
	ret = notifier_to_errno(ret);
	if (ret)
		goto failed_removal;

K
KAMEZAWA Hiroyuki 已提交
1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826
	pfn = start_pfn;
	expire = jiffies + timeout;
	drain = 0;
	retry_max = 5;
repeat:
	/* start memory hot removal */
	ret = -EAGAIN;
	if (time_after(jiffies, expire))
		goto failed_removal;
	ret = -EINTR;
	if (signal_pending(current))
		goto failed_removal;
	ret = 0;
	if (drain) {
		lru_add_drain_all();
		cond_resched();
1827
		drain_all_pages(zone);
K
KAMEZAWA Hiroyuki 已提交
1828 1829
	}

1830 1831
	pfn = scan_movable_pages(start_pfn, end_pfn);
	if (pfn) { /* We have movable pages */
K
KAMEZAWA Hiroyuki 已提交
1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844
		ret = do_migrate_range(pfn, end_pfn);
		if (!ret) {
			drain = 1;
			goto repeat;
		} else {
			if (ret < 0)
				if (--retry_max == 0)
					goto failed_removal;
			yield();
			drain = 1;
			goto repeat;
		}
	}
1845
	/* drain all zone's lru pagevec, this is asynchronous... */
K
KAMEZAWA Hiroyuki 已提交
1846 1847
	lru_add_drain_all();
	yield();
1848
	/* drain pcp pages, this is synchronous. */
1849
	drain_all_pages(zone);
1850 1851 1852 1853 1854
	/*
	 * dissolve free hugepages in the memory block before doing offlining
	 * actually in order to make hugetlbfs's object counting consistent.
	 */
	dissolve_free_huge_pages(start_pfn, end_pfn);
K
KAMEZAWA Hiroyuki 已提交
1855 1856 1857 1858 1859 1860 1861
	/* check again */
	offlined_pages = check_pages_isolated(start_pfn, end_pfn);
	if (offlined_pages < 0) {
		ret = -EBUSY;
		goto failed_removal;
	}
	printk(KERN_INFO "Offlined Pages %ld\n", offlined_pages);
1862
	/* Ok, all of our target is isolated.
K
KAMEZAWA Hiroyuki 已提交
1863 1864
	   We cannot do rollback at this point. */
	offline_isolated_pages(start_pfn, end_pfn);
1865
	/* reset pagetype flags and makes migrate type to be MOVABLE */
1866
	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
K
KAMEZAWA Hiroyuki 已提交
1867
	/* removal success */
1868
	adjust_managed_page_count(pfn_to_page(start_pfn), -offlined_pages);
K
KAMEZAWA Hiroyuki 已提交
1869
	zone->present_pages -= offlined_pages;
1870 1871

	pgdat_resize_lock(zone->zone_pgdat, &flags);
K
KAMEZAWA Hiroyuki 已提交
1872
	zone->zone_pgdat->node_present_pages -= offlined_pages;
1873
	pgdat_resize_unlock(zone->zone_pgdat, &flags);
1874

1875 1876
	init_per_zone_wmark_min();

1877
	if (!populated_zone(zone)) {
1878
		zone_pcp_reset(zone);
1879 1880 1881 1882 1883
		mutex_lock(&zonelists_mutex);
		build_all_zonelists(NULL, NULL);
		mutex_unlock(&zonelists_mutex);
	} else
		zone_pcp_update(zone);
1884

1885
	node_states_clear_node(node, &arg);
1886
	if (arg.status_change_nid >= 0) {
1887
		kswapd_stop(node);
1888 1889
		kcompactd_stop(node);
	}
1890

K
KAMEZAWA Hiroyuki 已提交
1891 1892
	vm_total_pages = nr_free_pagecache_pages();
	writeback_set_ratelimit();
1893 1894

	memory_notify(MEM_OFFLINE, &arg);
K
KAMEZAWA Hiroyuki 已提交
1895 1896 1897
	return 0;

failed_removal:
1898 1899 1900
	printk(KERN_INFO "memory offlining [mem %#010llx-%#010llx] failed\n",
	       (unsigned long long) start_pfn << PAGE_SHIFT,
	       ((unsigned long long) end_pfn << PAGE_SHIFT) - 1);
1901
	memory_notify(MEM_CANCEL_OFFLINE, &arg);
K
KAMEZAWA Hiroyuki 已提交
1902
	/* pushback to free area */
1903
	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
K
KAMEZAWA Hiroyuki 已提交
1904 1905
	return ret;
}
1906

1907
/* Must be protected by mem_hotplug_begin() */
1908 1909 1910 1911
int offline_pages(unsigned long start_pfn, unsigned long nr_pages)
{
	return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ);
}
1912
#endif /* CONFIG_MEMORY_HOTREMOVE */
1913

1914 1915 1916
/**
 * walk_memory_range - walks through all mem sections in [start_pfn, end_pfn)
 * @start_pfn: start pfn of the memory range
1917
 * @end_pfn: end pfn of the memory range
1918 1919 1920 1921 1922 1923 1924 1925
 * @arg: argument passed to func
 * @func: callback for each memory section walked
 *
 * This function walks through all present mem sections in range
 * [start_pfn, end_pfn) and call func on each mem section.
 *
 * Returns the return value of func.
 */
1926
int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
1927
		void *arg, int (*func)(struct memory_block *, void *))
1928
{
1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949
	struct memory_block *mem = NULL;
	struct mem_section *section;
	unsigned long pfn, section_nr;
	int ret;

	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
		section_nr = pfn_to_section_nr(pfn);
		if (!present_section_nr(section_nr))
			continue;

		section = __nr_to_section(section_nr);
		/* same memblock? */
		if (mem)
			if ((section_nr >= mem->start_section_nr) &&
			    (section_nr <= mem->end_section_nr))
				continue;

		mem = find_memory_block_hinted(section, mem);
		if (!mem)
			continue;

1950
		ret = func(mem, arg);
1951
		if (ret) {
1952 1953
			kobject_put(&mem->dev.kobj);
			return ret;
1954 1955 1956 1957 1958 1959
		}
	}

	if (mem)
		kobject_put(&mem->dev.kobj);

1960 1961 1962
	return 0;
}

1963
#ifdef CONFIG_MEMORY_HOTREMOVE
1964
static int check_memblock_offlined_cb(struct memory_block *mem, void *arg)
1965 1966 1967
{
	int ret = !is_memblock_offlined(mem);

1968 1969 1970 1971 1972
	if (unlikely(ret)) {
		phys_addr_t beginpa, endpa;

		beginpa = PFN_PHYS(section_nr_to_pfn(mem->start_section_nr));
		endpa = PFN_PHYS(section_nr_to_pfn(mem->end_section_nr + 1))-1;
1973
		pr_warn("removing memory fails, because memory "
1974 1975 1976
			"[%pa-%pa] is onlined\n",
			&beginpa, &endpa);
	}
1977 1978 1979 1980

	return ret;
}

1981
static int check_cpu_on_node(pg_data_t *pgdat)
1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996
{
	int cpu;

	for_each_present_cpu(cpu) {
		if (cpu_to_node(cpu) == pgdat->node_id)
			/*
			 * the cpu on this node isn't removed, and we can't
			 * offline this node.
			 */
			return -EBUSY;
	}

	return 0;
}

1997
static void unmap_cpu_on_node(pg_data_t *pgdat)
1998 1999 2000 2001 2002 2003 2004 2005 2006 2007
{
#ifdef CONFIG_ACPI_NUMA
	int cpu;

	for_each_possible_cpu(cpu)
		if (cpu_to_node(cpu) == pgdat->node_id)
			numa_clear_node(cpu);
#endif
}

2008
static int check_and_unmap_cpu_on_node(pg_data_t *pgdat)
2009
{
2010
	int ret;
2011

2012
	ret = check_cpu_on_node(pgdat);
2013 2014 2015 2016 2017 2018 2019 2020
	if (ret)
		return ret;

	/*
	 * the node will be offlined when we come here, so we can clear
	 * the cpu_to_node() now.
	 */

2021
	unmap_cpu_on_node(pgdat);
2022 2023 2024
	return 0;
}

2025 2026 2027 2028 2029 2030 2031 2032
/**
 * try_offline_node
 *
 * Offline a node if all memory sections and cpus of the node are removed.
 *
 * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
 * and online/offline operations before this call.
 */
2033
void try_offline_node(int nid)
2034
{
2035 2036 2037
	pg_data_t *pgdat = NODE_DATA(nid);
	unsigned long start_pfn = pgdat->node_start_pfn;
	unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
2038
	unsigned long pfn;
2039
	int i;
2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056

	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
		unsigned long section_nr = pfn_to_section_nr(pfn);

		if (!present_section_nr(section_nr))
			continue;

		if (pfn_to_nid(pfn) != nid)
			continue;

		/*
		 * some memory sections of this node are not removed, and we
		 * can't offline node now.
		 */
		return;
	}

2057
	if (check_and_unmap_cpu_on_node(pgdat))
2058 2059 2060 2061 2062 2063 2064 2065
		return;

	/*
	 * all memory/cpu of this node are removed, we can offline this
	 * node now.
	 */
	node_set_offline(nid);
	unregister_one_node(nid);
2066 2067 2068 2069 2070

	/* free waittable in each zone */
	for (i = 0; i < MAX_NR_ZONES; i++) {
		struct zone *zone = pgdat->node_zones + i;

2071 2072 2073 2074
		/*
		 * wait_table may be allocated from boot memory,
		 * here only free if it's allocated by vmalloc.
		 */
2075
		if (is_vmalloc_addr(zone->wait_table)) {
2076
			vfree(zone->wait_table);
2077 2078
			zone->wait_table = NULL;
		}
2079
	}
2080
}
2081
EXPORT_SYMBOL(try_offline_node);
2082

2083 2084 2085 2086 2087 2088 2089
/**
 * remove_memory
 *
 * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
 * and online/offline operations before this call, as required by
 * try_offline_node().
 */
2090
void __ref remove_memory(int nid, u64 start, u64 size)
2091
{
2092
	int ret;
2093

2094 2095
	BUG_ON(check_hotplug_memory_range(start, size));

2096
	mem_hotplug_begin();
2097 2098

	/*
2099 2100 2101
	 * All memory blocks must be offlined before removing memory.  Check
	 * whether all memory blocks in question are offline and trigger a BUG()
	 * if this is not the case.
2102
	 */
2103
	ret = walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL,
2104
				check_memblock_offlined_cb);
2105
	if (ret)
2106
		BUG();
2107

2108 2109
	/* remove memmap entry */
	firmware_map_remove(start, start + size, "System RAM");
2110 2111
	memblock_free(start, size);
	memblock_remove(start, size);
2112

2113 2114
	arch_remove_memory(start, size);

2115 2116
	try_offline_node(nid);

2117
	mem_hotplug_done();
2118 2119
}
EXPORT_SYMBOL_GPL(remove_memory);
2120
#endif /* CONFIG_MEMORY_HOTREMOVE */