page_alloc.c 61.1 KB
Newer Older
L
Linus Torvalds 已提交
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
/*
 *  linux/mm/page_alloc.c
 *
 *  Manages the free list, the system allocates free pages here.
 *  Note that kmalloc() lives in slab.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *  Swap reorganised 29.12.95, Stephen Tweedie
 *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
 *  Reshaped it to be a zoned allocator, Ingo Molnar, Red Hat, 1999
 *  Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
 *  Zone balancing, Kanoj Sarcar, SGI, Jan 2000
 *  Per cpu hot/cold page lists, bulk allocation, Martin J. Bligh, Sept 2002
 *          (lots of bits borrowed from Ingo Molnar & Andrew Morton)
 */

#include <linux/config.h>
#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/suspend.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/notifier.h>
#include <linux/topology.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/nodemask.h>
#include <linux/vmalloc.h>

#include <asm/tlbflush.h>
#include "internal.h"

/*
 * MCD - HACK: Find somewhere to initialize this EARLY, or make this
 * initializer cleaner
 */
nodemask_t node_online_map = { { [0] = 1UL } };
46
EXPORT_SYMBOL(node_online_map);
L
Linus Torvalds 已提交
47
nodemask_t node_possible_map = NODE_MASK_ALL;
48
EXPORT_SYMBOL(node_possible_map);
L
Linus Torvalds 已提交
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
struct pglist_data *pgdat_list;
unsigned long totalram_pages;
unsigned long totalhigh_pages;
long nr_swap_pages;

/*
 * results with 256, 32 in the lowmem_reserve sysctl:
 *	1G machine -> (16M dma, 800M-16M normal, 1G-800M high)
 *	1G machine -> (16M dma, 784M normal, 224M high)
 *	NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA
 *	HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL
 *	HIGHMEM allocation will (224M+784M)/256 of ram reserved in ZONE_DMA
 */
int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = { 256, 32 };

EXPORT_SYMBOL(totalram_pages);
EXPORT_SYMBOL(nr_swap_pages);

/*
 * Used by page_zone() to look up the address of the struct zone whose
 * id is encoded in the upper bits of page->flags
 */
struct zone *zone_table[1 << (ZONES_SHIFT + NODES_SHIFT)];
EXPORT_SYMBOL(zone_table);

74 75 76 77 78
#ifdef CONFIG_NUMA
static struct per_cpu_pageset
	pageset_table[MAX_NR_ZONES*MAX_NUMNODES*NR_CPUS] __initdata;
#endif

L
Linus Torvalds 已提交
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
static char *zone_names[MAX_NR_ZONES] = { "DMA", "Normal", "HighMem" };
int min_free_kbytes = 1024;

unsigned long __initdata nr_kernel_pages;
unsigned long __initdata nr_all_pages;

/*
 * Temporary debugging check for pages not lying within a given zone.
 */
static int bad_range(struct zone *zone, struct page *page)
{
	if (page_to_pfn(page) >= zone->zone_start_pfn + zone->spanned_pages)
		return 1;
	if (page_to_pfn(page) < zone->zone_start_pfn)
		return 1;
#ifdef CONFIG_HOLES_IN_ZONE
	if (!pfn_valid(page_to_pfn(page)))
		return 1;
#endif
	if (zone != page_zone(page))
		return 1;
	return 0;
}

static void bad_page(const char *function, struct page *page)
{
	printk(KERN_EMERG "Bad page state at %s (in process '%s', page %p)\n",
		function, current->comm, page);
	printk(KERN_EMERG "flags:0x%0*lx mapping:%p mapcount:%d count:%d\n",
		(int)(2*sizeof(page_flags_t)), (unsigned long)page->flags,
		page->mapping, page_mapcount(page), page_count(page));
	printk(KERN_EMERG "Backtrace:\n");
	dump_stack();
	printk(KERN_EMERG "Trying to fix it up, but a reboot is needed\n");
	page->flags &= ~(1 << PG_private	|
			1 << PG_locked	|
			1 << PG_lru	|
			1 << PG_active	|
			1 << PG_dirty	|
			1 << PG_swapcache |
			1 << PG_writeback);
	set_page_count(page, 0);
	reset_page_mapcount(page);
	page->mapping = NULL;
	tainted |= TAINT_BAD_PAGE;
}

#ifndef CONFIG_HUGETLB_PAGE
#define prep_compound_page(page, order) do { } while (0)
#define destroy_compound_page(page, order) do { } while (0)
#else
/*
 * Higher-order pages are called "compound pages".  They are structured thusly:
 *
 * The first PAGE_SIZE page is called the "head page".
 *
 * The remaining PAGE_SIZE pages are called "tail pages".
 *
 * All pages have PG_compound set.  All pages have their ->private pointing at
 * the head page (even the head page has this).
 *
 * The first tail page's ->mapping, if non-zero, holds the address of the
 * compound page's put_page() function.
 *
 * The order of the allocation is stored in the first tail page's ->index
 * This is only for debug at present.  This usage means that zero-order pages
 * may not be compound.
 */
static void prep_compound_page(struct page *page, unsigned long order)
{
	int i;
	int nr_pages = 1 << order;

	page[1].mapping = NULL;
	page[1].index = order;
	for (i = 0; i < nr_pages; i++) {
		struct page *p = page + i;

		SetPageCompound(p);
		p->private = (unsigned long)page;
	}
}

static void destroy_compound_page(struct page *page, unsigned long order)
{
	int i;
	int nr_pages = 1 << order;

	if (!PageCompound(page))
		return;

	if (page[1].index != order)
		bad_page(__FUNCTION__, page);

	for (i = 0; i < nr_pages; i++) {
		struct page *p = page + i;

		if (!PageCompound(p))
			bad_page(__FUNCTION__, page);
		if (p->private != (unsigned long)page)
			bad_page(__FUNCTION__, page);
		ClearPageCompound(p);
	}
}
#endif		/* CONFIG_HUGETLB_PAGE */

/*
 * function for dealing with page's order in buddy system.
 * zone->lock is already acquired when we use these.
 * So, we don't need atomic page->flags operations here.
 */
static inline unsigned long page_order(struct page *page) {
	return page->private;
}

static inline void set_page_order(struct page *page, int order) {
	page->private = order;
	__SetPagePrivate(page);
}

static inline void rmv_page_order(struct page *page)
{
	__ClearPagePrivate(page);
	page->private = 0;
}

/*
 * Locate the struct page for both the matching buddy in our
 * pair (buddy1) and the combined O(n+1) page they form (page).
 *
 * 1) Any buddy B1 will have an order O twin B2 which satisfies
 * the following equation:
 *     B2 = B1 ^ (1 << O)
 * For example, if the starting buddy (buddy2) is #8 its order
 * 1 buddy is #10:
 *     B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10
 *
 * 2) Any buddy B will have an order O+1 parent P which
 * satisfies the following equation:
 *     P = B & ~(1 << O)
 *
 * Assumption: *_mem_map is contigious at least up to MAX_ORDER
 */
static inline struct page *
__page_find_buddy(struct page *page, unsigned long page_idx, unsigned int order)
{
	unsigned long buddy_idx = page_idx ^ (1 << order);

	return page + (buddy_idx - page_idx);
}

static inline unsigned long
__find_combined_index(unsigned long page_idx, unsigned int order)
{
	return (page_idx & ~(1 << order));
}

/*
 * This function checks whether a page is free && is the buddy
 * we can do coalesce a page and its buddy if
 * (a) the buddy is free &&
 * (b) the buddy is on the buddy system &&
 * (c) a page and its buddy have the same order.
 * for recording page's order, we use page->private and PG_private.
 *
 */
static inline int page_is_buddy(struct page *page, int order)
{
       if (PagePrivate(page)           &&
           (page_order(page) == order) &&
           !PageReserved(page)         &&
            page_count(page) == 0)
               return 1;
       return 0;
}

/*
 * Freeing function for a buddy system allocator.
 *
 * The concept of a buddy system is to maintain direct-mapped table
 * (containing bit values) for memory blocks of various "orders".
 * The bottom level table contains the map for the smallest allocatable
 * units of memory (here, pages), and each level above it describes
 * pairs of units from the levels below, hence, "buddies".
 * At a high level, all that happens here is marking the table entry
 * at the bottom level available, and propagating the changes upward
 * as necessary, plus some accounting needed to play nicely with other
 * parts of the VM system.
 * At each level, we keep a list of pages, which are heads of continuous
 * free pages of length of (1 << order) and marked with PG_Private.Page's
 * order is recorded in page->private field.
 * So when we are allocating or freeing one, we can derive the state of the
 * other.  That is, if we allocate a small block, and both were   
 * free, the remainder of the region must be split into blocks.   
 * If a block is freed, and its buddy is also free, then this
 * triggers coalescing into a block of larger size.            
 *
 * -- wli
 */

static inline void __free_pages_bulk (struct page *page,
		struct zone *zone, unsigned int order)
{
	unsigned long page_idx;
	int order_size = 1 << order;

	if (unlikely(order))
		destroy_compound_page(page, order);

	page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);

	BUG_ON(page_idx & (order_size - 1));
	BUG_ON(bad_range(zone, page));

	zone->free_pages += order_size;
	while (order < MAX_ORDER-1) {
		unsigned long combined_idx;
		struct free_area *area;
		struct page *buddy;

		combined_idx = __find_combined_index(page_idx, order);
		buddy = __page_find_buddy(page, page_idx, order);

		if (bad_range(zone, buddy))
			break;
		if (!page_is_buddy(buddy, order))
			break;		/* Move the buddy up one level. */
		list_del(&buddy->lru);
		area = zone->free_area + order;
		area->nr_free--;
		rmv_page_order(buddy);
		page = page + (combined_idx - page_idx);
		page_idx = combined_idx;
		order++;
	}
	set_page_order(page, order);
	list_add(&page->lru, &zone->free_area[order].free_list);
	zone->free_area[order].nr_free++;
}

static inline void free_pages_check(const char *function, struct page *page)
{
	if (	page_mapcount(page) ||
		page->mapping != NULL ||
		page_count(page) != 0 ||
		(page->flags & (
			1 << PG_lru	|
			1 << PG_private |
			1 << PG_locked	|
			1 << PG_active	|
			1 << PG_reclaim	|
			1 << PG_slab	|
			1 << PG_swapcache |
			1 << PG_writeback )))
		bad_page(function, page);
	if (PageDirty(page))
		ClearPageDirty(page);
}

/*
 * Frees a list of pages. 
 * Assumes all pages on list are in same zone, and of same order.
 * count is the number of pages to free, or 0 for all on the list.
 *
 * If the zone was previously in an "all pages pinned" state then look to
 * see if this freeing clears that state.
 *
 * And clear the zone's pages_scanned counter, to hold off the "all pages are
 * pinned" detection logic.
 */
static int
free_pages_bulk(struct zone *zone, int count,
		struct list_head *list, unsigned int order)
{
	unsigned long flags;
	struct page *page = NULL;
	int ret = 0;

	spin_lock_irqsave(&zone->lock, flags);
	zone->all_unreclaimable = 0;
	zone->pages_scanned = 0;
	while (!list_empty(list) && count--) {
		page = list_entry(list->prev, struct page, lru);
		/* have to delete it as __free_pages_bulk list manipulates */
		list_del(&page->lru);
		__free_pages_bulk(page, zone, order);
		ret++;
	}
	spin_unlock_irqrestore(&zone->lock, flags);
	return ret;
}

void __free_pages_ok(struct page *page, unsigned int order)
{
	LIST_HEAD(list);
	int i;

	arch_free_page(page, order);

	mod_page_state(pgfree, 1 << order);

#ifndef CONFIG_MMU
	if (order > 0)
		for (i = 1 ; i < (1 << order) ; ++i)
			__put_page(page + i);
#endif

	for (i = 0 ; i < (1 << order) ; ++i)
		free_pages_check(__FUNCTION__, page + i);
	list_add(&page->lru, &list);
	kernel_map_pages(page, 1<<order, 0);
	free_pages_bulk(page_zone(page), 1, &list, order);
}


/*
 * The order of subdivision here is critical for the IO subsystem.
 * Please do not alter this order without good reasons and regression
 * testing. Specifically, as large blocks of memory are subdivided,
 * the order in which smaller blocks are delivered depends on the order
 * they're subdivided in this function. This is the primary factor
 * influencing the order in which pages are delivered to the IO
 * subsystem according to empirical testing, and this is also justified
 * by considering the behavior of a buddy system containing a single
 * large block of memory acted on by a series of small allocations.
 * This behavior is a critical factor in sglist merging's success.
 *
 * -- wli
 */
static inline struct page *
expand(struct zone *zone, struct page *page,
 	int low, int high, struct free_area *area)
{
	unsigned long size = 1 << high;

	while (high > low) {
		area--;
		high--;
		size >>= 1;
		BUG_ON(bad_range(zone, &page[size]));
		list_add(&page[size].lru, &area->free_list);
		area->nr_free++;
		set_page_order(&page[size], high);
	}
	return page;
}

void set_page_refs(struct page *page, int order)
{
#ifdef CONFIG_MMU
	set_page_count(page, 1);
#else
	int i;

	/*
	 * We need to reference all the pages for this order, otherwise if
	 * anyone accesses one of the pages with (get/put) it will be freed.
	 * - eg: access_process_vm()
	 */
	for (i = 0; i < (1 << order); i++)
		set_page_count(page + i, 1);
#endif /* CONFIG_MMU */
}

/*
 * This page is about to be returned from the page allocator
 */
static void prep_new_page(struct page *page, int order)
{
	if (page->mapping || page_mapcount(page) ||
	    (page->flags & (
			1 << PG_private	|
			1 << PG_locked	|
			1 << PG_lru	|
			1 << PG_active	|
			1 << PG_dirty	|
			1 << PG_reclaim	|
			1 << PG_swapcache |
			1 << PG_writeback )))
		bad_page(__FUNCTION__, page);

	page->flags &= ~(1 << PG_uptodate | 1 << PG_error |
			1 << PG_referenced | 1 << PG_arch_1 |
			1 << PG_checked | 1 << PG_mappedtodisk);
	page->private = 0;
	set_page_refs(page, order);
	kernel_map_pages(page, 1 << order, 1);
}

/* 
 * Do the hard work of removing an element from the buddy allocator.
 * Call me with the zone->lock already held.
 */
static struct page *__rmqueue(struct zone *zone, unsigned int order)
{
	struct free_area * area;
	unsigned int current_order;
	struct page *page;

	for (current_order = order; current_order < MAX_ORDER; ++current_order) {
		area = zone->free_area + current_order;
		if (list_empty(&area->free_list))
			continue;

		page = list_entry(area->free_list.next, struct page, lru);
		list_del(&page->lru);
		rmv_page_order(page);
		area->nr_free--;
		zone->free_pages -= 1UL << order;
		return expand(zone, page, order, current_order, area);
	}

	return NULL;
}

/* 
 * Obtain a specified number of elements from the buddy allocator, all under
 * a single hold of the lock, for efficiency.  Add them to the supplied list.
 * Returns the number of new pages which were placed at *list.
 */
static int rmqueue_bulk(struct zone *zone, unsigned int order, 
			unsigned long count, struct list_head *list)
{
	unsigned long flags;
	int i;
	int allocated = 0;
	struct page *page;
	
	spin_lock_irqsave(&zone->lock, flags);
	for (i = 0; i < count; ++i) {
		page = __rmqueue(zone, order);
		if (page == NULL)
			break;
		allocated++;
		list_add_tail(&page->lru, list);
	}
	spin_unlock_irqrestore(&zone->lock, flags);
	return allocated;
}

#if defined(CONFIG_PM) || defined(CONFIG_HOTPLUG_CPU)
static void __drain_pages(unsigned int cpu)
{
	struct zone *zone;
	int i;

	for_each_zone(zone) {
		struct per_cpu_pageset *pset;

528
		pset = zone_pcp(zone, cpu);
L
Linus Torvalds 已提交
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
		for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
			struct per_cpu_pages *pcp;

			pcp = &pset->pcp[i];
			pcp->count -= free_pages_bulk(zone, pcp->count,
						&pcp->list, 0);
		}
	}
}
#endif /* CONFIG_PM || CONFIG_HOTPLUG_CPU */

#ifdef CONFIG_PM

void mark_free_pages(struct zone *zone)
{
	unsigned long zone_pfn, flags;
	int order;
	struct list_head *curr;

	if (!zone->spanned_pages)
		return;

	spin_lock_irqsave(&zone->lock, flags);
	for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
		ClearPageNosaveFree(pfn_to_page(zone_pfn + zone->zone_start_pfn));

	for (order = MAX_ORDER - 1; order >= 0; --order)
		list_for_each(curr, &zone->free_area[order].free_list) {
			unsigned long start_pfn, i;

			start_pfn = page_to_pfn(list_entry(curr, struct page, lru));

			for (i=0; i < (1<<order); i++)
				SetPageNosaveFree(pfn_to_page(start_pfn+i));
	}
	spin_unlock_irqrestore(&zone->lock, flags);
}

/*
 * Spill all of this CPU's per-cpu pages back into the buddy allocator.
 */
void drain_local_pages(void)
{
	unsigned long flags;

	local_irq_save(flags);	
	__drain_pages(smp_processor_id());
	local_irq_restore(flags);	
}
#endif /* CONFIG_PM */

static void zone_statistics(struct zonelist *zonelist, struct zone *z)
{
#ifdef CONFIG_NUMA
	unsigned long flags;
	int cpu;
	pg_data_t *pg = z->zone_pgdat;
	pg_data_t *orig = zonelist->zones[0]->zone_pgdat;
	struct per_cpu_pageset *p;

	local_irq_save(flags);
	cpu = smp_processor_id();
591
	p = zone_pcp(z,cpu);
L
Linus Torvalds 已提交
592
	if (pg == orig) {
593
		p->numa_hit++;
L
Linus Torvalds 已提交
594 595
	} else {
		p->numa_miss++;
596
		zone_pcp(zonelist->zones[0], cpu)->numa_foreign++;
L
Linus Torvalds 已提交
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
	}
	if (pg == NODE_DATA(numa_node_id()))
		p->local_node++;
	else
		p->other_node++;
	local_irq_restore(flags);
#endif
}

/*
 * Free a 0-order page
 */
static void FASTCALL(free_hot_cold_page(struct page *page, int cold));
static void fastcall free_hot_cold_page(struct page *page, int cold)
{
	struct zone *zone = page_zone(page);
	struct per_cpu_pages *pcp;
	unsigned long flags;

	arch_free_page(page, 0);

	kernel_map_pages(page, 1, 0);
	inc_page_state(pgfree);
	if (PageAnon(page))
		page->mapping = NULL;
	free_pages_check(__FUNCTION__, page);
623
	pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
L
Linus Torvalds 已提交
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
	local_irq_save(flags);
	if (pcp->count >= pcp->high)
		pcp->count -= free_pages_bulk(zone, pcp->batch, &pcp->list, 0);
	list_add(&page->lru, &pcp->list);
	pcp->count++;
	local_irq_restore(flags);
	put_cpu();
}

void fastcall free_hot_page(struct page *page)
{
	free_hot_cold_page(page, 0);
}
	
void fastcall free_cold_page(struct page *page)
{
	free_hot_cold_page(page, 1);
}

static inline void prep_zero_page(struct page *page, int order, unsigned int __nocast gfp_flags)
{
	int i;

	BUG_ON((gfp_flags & (__GFP_WAIT | __GFP_HIGHMEM)) == __GFP_HIGHMEM);
	for(i = 0; i < (1 << order); i++)
		clear_highpage(page + i);
}

/*
 * Really, prep_compound_page() should be called from __rmqueue_bulk().  But
 * we cheat by calling it from here, in the order > 0 path.  Saves a branch
 * or two.
 */
static struct page *
buffered_rmqueue(struct zone *zone, int order, unsigned int __nocast gfp_flags)
{
	unsigned long flags;
	struct page *page = NULL;
	int cold = !!(gfp_flags & __GFP_COLD);

	if (order == 0) {
		struct per_cpu_pages *pcp;

667
		pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
L
Linus Torvalds 已提交
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
		local_irq_save(flags);
		if (pcp->count <= pcp->low)
			pcp->count += rmqueue_bulk(zone, 0,
						pcp->batch, &pcp->list);
		if (pcp->count) {
			page = list_entry(pcp->list.next, struct page, lru);
			list_del(&page->lru);
			pcp->count--;
		}
		local_irq_restore(flags);
		put_cpu();
	}

	if (page == NULL) {
		spin_lock_irqsave(&zone->lock, flags);
		page = __rmqueue(zone, order);
		spin_unlock_irqrestore(&zone->lock, flags);
	}

	if (page != NULL) {
		BUG_ON(bad_range(zone, page));
		mod_page_state_zone(zone, pgalloc, 1 << order);
		prep_new_page(page, order);

		if (gfp_flags & __GFP_ZERO)
			prep_zero_page(page, order, gfp_flags);

		if (order && (gfp_flags & __GFP_COMP))
			prep_compound_page(page, order);
	}
	return page;
}

/*
 * Return 1 if free pages are above 'mark'. This takes into account the order
 * of the allocation.
 */
int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
		      int classzone_idx, int can_try_harder, int gfp_high)
{
	/* free_pages my go negative - that's OK */
	long min = mark, free_pages = z->free_pages - (1 << order) + 1;
	int o;

	if (gfp_high)
		min -= min / 2;
	if (can_try_harder)
		min -= min / 4;

	if (free_pages <= min + z->lowmem_reserve[classzone_idx])
		return 0;
	for (o = 0; o < order; o++) {
		/* At the next order, this order's pages become unavailable */
		free_pages -= z->free_area[o].nr_free << o;

		/* Require fewer higher order pages to be free */
		min >>= 1;

		if (free_pages <= min)
			return 0;
	}
	return 1;
}

M
Martin Hicks 已提交
732 733 734 735 736
static inline int
should_reclaim_zone(struct zone *z, unsigned int gfp_mask)
{
	if (!z->reclaim_pages)
		return 0;
M
Martin Hicks 已提交
737 738
	if (gfp_mask & __GFP_NORECLAIM)
		return 0;
M
Martin Hicks 已提交
739 740 741
	return 1;
}

L
Linus Torvalds 已提交
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
/*
 * This is the 'heart' of the zoned buddy allocator.
 */
struct page * fastcall
__alloc_pages(unsigned int __nocast gfp_mask, unsigned int order,
		struct zonelist *zonelist)
{
	const int wait = gfp_mask & __GFP_WAIT;
	struct zone **zones, *z;
	struct page *page;
	struct reclaim_state reclaim_state;
	struct task_struct *p = current;
	int i;
	int classzone_idx;
	int do_retry;
	int can_try_harder;
	int did_some_progress;

	might_sleep_if(wait);

	/*
	 * The caller may dip into page reserves a bit more if the caller
	 * cannot run direct reclaim, or is the caller has realtime scheduling
	 * policy
	 */
	can_try_harder = (unlikely(rt_task(p)) && !in_interrupt()) || !wait;

	zones = zonelist->zones;  /* the list of zones suitable for gfp_mask */

	if (unlikely(zones[0] == NULL)) {
		/* Should this ever happen?? */
		return NULL;
	}

	classzone_idx = zone_idx(zones[0]);

M
Martin Hicks 已提交
778
restart:
L
Linus Torvalds 已提交
779 780
	/* Go through the zonelist once, looking for a zone with enough free */
	for (i = 0; (z = zones[i]) != NULL; i++) {
M
Martin Hicks 已提交
781
		int do_reclaim = should_reclaim_zone(z, gfp_mask);
L
Linus Torvalds 已提交
782 783 784 785

		if (!cpuset_zone_allowed(z))
			continue;

M
Martin Hicks 已提交
786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803
		/*
		 * If the zone is to attempt early page reclaim then this loop
		 * will try to reclaim pages and check the watermark a second
		 * time before giving up and falling back to the next zone.
		 */
zone_reclaim_retry:
		if (!zone_watermark_ok(z, order, z->pages_low,
				       classzone_idx, 0, 0)) {
			if (!do_reclaim)
				continue;
			else {
				zone_reclaim(z, gfp_mask, order);
				/* Only try reclaim once */
				do_reclaim = 0;
				goto zone_reclaim_retry;
			}
		}

L
Linus Torvalds 已提交
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
		page = buffered_rmqueue(z, order, gfp_mask);
		if (page)
			goto got_pg;
	}

	for (i = 0; (z = zones[i]) != NULL; i++)
		wakeup_kswapd(z, order);

	/*
	 * Go through the zonelist again. Let __GFP_HIGH and allocations
	 * coming from realtime tasks to go deeper into reserves
	 *
	 * This is the last chance, in general, before the goto nopage.
	 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
	 */
	for (i = 0; (z = zones[i]) != NULL; i++) {
		if (!zone_watermark_ok(z, order, z->pages_min,
				       classzone_idx, can_try_harder,
				       gfp_mask & __GFP_HIGH))
			continue;

		if (wait && !cpuset_zone_allowed(z))
			continue;

		page = buffered_rmqueue(z, order, gfp_mask);
		if (page)
			goto got_pg;
	}

	/* This allocation should allow future memory freeing. */
834 835 836 837 838 839 840 841 842 843 844 845

	if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
			&& !in_interrupt()) {
		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
			/* go through the zonelist yet again, ignoring mins */
			for (i = 0; (z = zones[i]) != NULL; i++) {
				if (!cpuset_zone_allowed(z))
					continue;
				page = buffered_rmqueue(z, order, gfp_mask);
				if (page)
					goto got_pg;
			}
L
Linus Torvalds 已提交
846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861
		}
		goto nopage;
	}

	/* Atomic allocations - we can't balance anything */
	if (!wait)
		goto nopage;

rebalance:
	cond_resched();

	/* We now go into synchronous reclaim */
	p->flags |= PF_MEMALLOC;
	reclaim_state.reclaimed_slab = 0;
	p->reclaim_state = &reclaim_state;

862
	did_some_progress = try_to_free_pages(zones, gfp_mask);
L
Linus Torvalds 已提交
863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269

	p->reclaim_state = NULL;
	p->flags &= ~PF_MEMALLOC;

	cond_resched();

	if (likely(did_some_progress)) {
		/*
		 * Go through the zonelist yet one more time, keep
		 * very high watermark here, this is only to catch
		 * a parallel oom killing, we must fail if we're still
		 * under heavy pressure.
		 */
		for (i = 0; (z = zones[i]) != NULL; i++) {
			if (!zone_watermark_ok(z, order, z->pages_min,
					       classzone_idx, can_try_harder,
					       gfp_mask & __GFP_HIGH))
				continue;

			if (!cpuset_zone_allowed(z))
				continue;

			page = buffered_rmqueue(z, order, gfp_mask);
			if (page)
				goto got_pg;
		}
	} else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
		/*
		 * Go through the zonelist yet one more time, keep
		 * very high watermark here, this is only to catch
		 * a parallel oom killing, we must fail if we're still
		 * under heavy pressure.
		 */
		for (i = 0; (z = zones[i]) != NULL; i++) {
			if (!zone_watermark_ok(z, order, z->pages_high,
					       classzone_idx, 0, 0))
				continue;

			if (!cpuset_zone_allowed(z))
				continue;

			page = buffered_rmqueue(z, order, gfp_mask);
			if (page)
				goto got_pg;
		}

		out_of_memory(gfp_mask);
		goto restart;
	}

	/*
	 * Don't let big-order allocations loop unless the caller explicitly
	 * requests that.  Wait for some write requests to complete then retry.
	 *
	 * In this implementation, __GFP_REPEAT means __GFP_NOFAIL for order
	 * <= 3, but that may not be true in other implementations.
	 */
	do_retry = 0;
	if (!(gfp_mask & __GFP_NORETRY)) {
		if ((order <= 3) || (gfp_mask & __GFP_REPEAT))
			do_retry = 1;
		if (gfp_mask & __GFP_NOFAIL)
			do_retry = 1;
	}
	if (do_retry) {
		blk_congestion_wait(WRITE, HZ/50);
		goto rebalance;
	}

nopage:
	if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) {
		printk(KERN_WARNING "%s: page allocation failure."
			" order:%d, mode:0x%x\n",
			p->comm, order, gfp_mask);
		dump_stack();
	}
	return NULL;
got_pg:
	zone_statistics(zonelist, z);
	return page;
}

EXPORT_SYMBOL(__alloc_pages);

/*
 * Common helper functions.
 */
fastcall unsigned long __get_free_pages(unsigned int __nocast gfp_mask, unsigned int order)
{
	struct page * page;
	page = alloc_pages(gfp_mask, order);
	if (!page)
		return 0;
	return (unsigned long) page_address(page);
}

EXPORT_SYMBOL(__get_free_pages);

fastcall unsigned long get_zeroed_page(unsigned int __nocast gfp_mask)
{
	struct page * page;

	/*
	 * get_zeroed_page() returns a 32-bit address, which cannot represent
	 * a highmem page
	 */
	BUG_ON(gfp_mask & __GFP_HIGHMEM);

	page = alloc_pages(gfp_mask | __GFP_ZERO, 0);
	if (page)
		return (unsigned long) page_address(page);
	return 0;
}

EXPORT_SYMBOL(get_zeroed_page);

void __pagevec_free(struct pagevec *pvec)
{
	int i = pagevec_count(pvec);

	while (--i >= 0)
		free_hot_cold_page(pvec->pages[i], pvec->cold);
}

fastcall void __free_pages(struct page *page, unsigned int order)
{
	if (!PageReserved(page) && put_page_testzero(page)) {
		if (order == 0)
			free_hot_page(page);
		else
			__free_pages_ok(page, order);
	}
}

EXPORT_SYMBOL(__free_pages);

fastcall void free_pages(unsigned long addr, unsigned int order)
{
	if (addr != 0) {
		BUG_ON(!virt_addr_valid((void *)addr));
		__free_pages(virt_to_page((void *)addr), order);
	}
}

EXPORT_SYMBOL(free_pages);

/*
 * Total amount of free (allocatable) RAM:
 */
unsigned int nr_free_pages(void)
{
	unsigned int sum = 0;
	struct zone *zone;

	for_each_zone(zone)
		sum += zone->free_pages;

	return sum;
}

EXPORT_SYMBOL(nr_free_pages);

#ifdef CONFIG_NUMA
unsigned int nr_free_pages_pgdat(pg_data_t *pgdat)
{
	unsigned int i, sum = 0;

	for (i = 0; i < MAX_NR_ZONES; i++)
		sum += pgdat->node_zones[i].free_pages;

	return sum;
}
#endif

static unsigned int nr_free_zone_pages(int offset)
{
	pg_data_t *pgdat;
	unsigned int sum = 0;

	for_each_pgdat(pgdat) {
		struct zonelist *zonelist = pgdat->node_zonelists + offset;
		struct zone **zonep = zonelist->zones;
		struct zone *zone;

		for (zone = *zonep++; zone; zone = *zonep++) {
			unsigned long size = zone->present_pages;
			unsigned long high = zone->pages_high;
			if (size > high)
				sum += size - high;
		}
	}

	return sum;
}

/*
 * Amount of free RAM allocatable within ZONE_DMA and ZONE_NORMAL
 */
unsigned int nr_free_buffer_pages(void)
{
	return nr_free_zone_pages(GFP_USER & GFP_ZONEMASK);
}

/*
 * Amount of free RAM allocatable within all zones
 */
unsigned int nr_free_pagecache_pages(void)
{
	return nr_free_zone_pages(GFP_HIGHUSER & GFP_ZONEMASK);
}

#ifdef CONFIG_HIGHMEM
unsigned int nr_free_highpages (void)
{
	pg_data_t *pgdat;
	unsigned int pages = 0;

	for_each_pgdat(pgdat)
		pages += pgdat->node_zones[ZONE_HIGHMEM].free_pages;

	return pages;
}
#endif

#ifdef CONFIG_NUMA
static void show_node(struct zone *zone)
{
	printk("Node %d ", zone->zone_pgdat->node_id);
}
#else
#define show_node(zone)	do { } while (0)
#endif

/*
 * Accumulate the page_state information across all CPUs.
 * The result is unavoidably approximate - it can change
 * during and after execution of this function.
 */
static DEFINE_PER_CPU(struct page_state, page_states) = {0};

atomic_t nr_pagecache = ATOMIC_INIT(0);
EXPORT_SYMBOL(nr_pagecache);
#ifdef CONFIG_SMP
DEFINE_PER_CPU(long, nr_pagecache_local) = 0;
#endif

void __get_page_state(struct page_state *ret, int nr)
{
	int cpu = 0;

	memset(ret, 0, sizeof(*ret));

	cpu = first_cpu(cpu_online_map);
	while (cpu < NR_CPUS) {
		unsigned long *in, *out, off;

		in = (unsigned long *)&per_cpu(page_states, cpu);

		cpu = next_cpu(cpu, cpu_online_map);

		if (cpu < NR_CPUS)
			prefetch(&per_cpu(page_states, cpu));

		out = (unsigned long *)ret;
		for (off = 0; off < nr; off++)
			*out++ += *in++;
	}
}

void get_page_state(struct page_state *ret)
{
	int nr;

	nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
	nr /= sizeof(unsigned long);

	__get_page_state(ret, nr + 1);
}

void get_full_page_state(struct page_state *ret)
{
	__get_page_state(ret, sizeof(*ret) / sizeof(unsigned long));
}

unsigned long __read_page_state(unsigned offset)
{
	unsigned long ret = 0;
	int cpu;

	for_each_online_cpu(cpu) {
		unsigned long in;

		in = (unsigned long)&per_cpu(page_states, cpu) + offset;
		ret += *((unsigned long *)in);
	}
	return ret;
}

void __mod_page_state(unsigned offset, unsigned long delta)
{
	unsigned long flags;
	void* ptr;

	local_irq_save(flags);
	ptr = &__get_cpu_var(page_states);
	*(unsigned long*)(ptr + offset) += delta;
	local_irq_restore(flags);
}

EXPORT_SYMBOL(__mod_page_state);

void __get_zone_counts(unsigned long *active, unsigned long *inactive,
			unsigned long *free, struct pglist_data *pgdat)
{
	struct zone *zones = pgdat->node_zones;
	int i;

	*active = 0;
	*inactive = 0;
	*free = 0;
	for (i = 0; i < MAX_NR_ZONES; i++) {
		*active += zones[i].nr_active;
		*inactive += zones[i].nr_inactive;
		*free += zones[i].free_pages;
	}
}

void get_zone_counts(unsigned long *active,
		unsigned long *inactive, unsigned long *free)
{
	struct pglist_data *pgdat;

	*active = 0;
	*inactive = 0;
	*free = 0;
	for_each_pgdat(pgdat) {
		unsigned long l, m, n;
		__get_zone_counts(&l, &m, &n, pgdat);
		*active += l;
		*inactive += m;
		*free += n;
	}
}

void si_meminfo(struct sysinfo *val)
{
	val->totalram = totalram_pages;
	val->sharedram = 0;
	val->freeram = nr_free_pages();
	val->bufferram = nr_blockdev_pages();
#ifdef CONFIG_HIGHMEM
	val->totalhigh = totalhigh_pages;
	val->freehigh = nr_free_highpages();
#else
	val->totalhigh = 0;
	val->freehigh = 0;
#endif
	val->mem_unit = PAGE_SIZE;
}

EXPORT_SYMBOL(si_meminfo);

#ifdef CONFIG_NUMA
void si_meminfo_node(struct sysinfo *val, int nid)
{
	pg_data_t *pgdat = NODE_DATA(nid);

	val->totalram = pgdat->node_present_pages;
	val->freeram = nr_free_pages_pgdat(pgdat);
	val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].present_pages;
	val->freehigh = pgdat->node_zones[ZONE_HIGHMEM].free_pages;
	val->mem_unit = PAGE_SIZE;
}
#endif

#define K(x) ((x) << (PAGE_SHIFT-10))

/*
 * Show free area list (used inside shift_scroll-lock stuff)
 * We also calculate the percentage fragmentation. We do this by counting the
 * memory on each free list with the exception of the first item on the list.
 */
void show_free_areas(void)
{
	struct page_state ps;
	int cpu, temperature;
	unsigned long active;
	unsigned long inactive;
	unsigned long free;
	struct zone *zone;

	for_each_zone(zone) {
		show_node(zone);
		printk("%s per-cpu:", zone->name);

		if (!zone->present_pages) {
			printk(" empty\n");
			continue;
		} else
			printk("\n");

		for (cpu = 0; cpu < NR_CPUS; ++cpu) {
			struct per_cpu_pageset *pageset;

			if (!cpu_possible(cpu))
				continue;

1270
			pageset = zone_pcp(zone, cpu);
L
Linus Torvalds 已提交
1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389

			for (temperature = 0; temperature < 2; temperature++)
				printk("cpu %d %s: low %d, high %d, batch %d\n",
					cpu,
					temperature ? "cold" : "hot",
					pageset->pcp[temperature].low,
					pageset->pcp[temperature].high,
					pageset->pcp[temperature].batch);
		}
	}

	get_page_state(&ps);
	get_zone_counts(&active, &inactive, &free);

	printk("\nFree pages: %11ukB (%ukB HighMem)\n",
		K(nr_free_pages()),
		K(nr_free_highpages()));

	printk("Active:%lu inactive:%lu dirty:%lu writeback:%lu "
		"unstable:%lu free:%u slab:%lu mapped:%lu pagetables:%lu\n",
		active,
		inactive,
		ps.nr_dirty,
		ps.nr_writeback,
		ps.nr_unstable,
		nr_free_pages(),
		ps.nr_slab,
		ps.nr_mapped,
		ps.nr_page_table_pages);

	for_each_zone(zone) {
		int i;

		show_node(zone);
		printk("%s"
			" free:%lukB"
			" min:%lukB"
			" low:%lukB"
			" high:%lukB"
			" active:%lukB"
			" inactive:%lukB"
			" present:%lukB"
			" pages_scanned:%lu"
			" all_unreclaimable? %s"
			"\n",
			zone->name,
			K(zone->free_pages),
			K(zone->pages_min),
			K(zone->pages_low),
			K(zone->pages_high),
			K(zone->nr_active),
			K(zone->nr_inactive),
			K(zone->present_pages),
			zone->pages_scanned,
			(zone->all_unreclaimable ? "yes" : "no")
			);
		printk("lowmem_reserve[]:");
		for (i = 0; i < MAX_NR_ZONES; i++)
			printk(" %lu", zone->lowmem_reserve[i]);
		printk("\n");
	}

	for_each_zone(zone) {
 		unsigned long nr, flags, order, total = 0;

		show_node(zone);
		printk("%s: ", zone->name);
		if (!zone->present_pages) {
			printk("empty\n");
			continue;
		}

		spin_lock_irqsave(&zone->lock, flags);
		for (order = 0; order < MAX_ORDER; order++) {
			nr = zone->free_area[order].nr_free;
			total += nr << order;
			printk("%lu*%lukB ", nr, K(1UL) << order);
		}
		spin_unlock_irqrestore(&zone->lock, flags);
		printk("= %lukB\n", K(total));
	}

	show_swap_cache_info();
}

/*
 * Builds allocation fallback zone lists.
 */
static int __init build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, int j, int k)
{
	switch (k) {
		struct zone *zone;
	default:
		BUG();
	case ZONE_HIGHMEM:
		zone = pgdat->node_zones + ZONE_HIGHMEM;
		if (zone->present_pages) {
#ifndef CONFIG_HIGHMEM
			BUG();
#endif
			zonelist->zones[j++] = zone;
		}
	case ZONE_NORMAL:
		zone = pgdat->node_zones + ZONE_NORMAL;
		if (zone->present_pages)
			zonelist->zones[j++] = zone;
	case ZONE_DMA:
		zone = pgdat->node_zones + ZONE_DMA;
		if (zone->present_pages)
			zonelist->zones[j++] = zone;
	}

	return j;
}

#ifdef CONFIG_NUMA
#define MAX_NODE_LOAD (num_online_nodes())
static int __initdata node_load[MAX_NUMNODES];
/**
1390
 * find_next_best_node - find the next node that should appear in a given node's fallback list
L
Linus Torvalds 已提交
1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652
 * @node: node whose fallback list we're appending
 * @used_node_mask: nodemask_t of already used nodes
 *
 * We use a number of factors to determine which is the next node that should
 * appear on a given node's fallback list.  The node should not have appeared
 * already in @node's fallback list, and it should be the next closest node
 * according to the distance array (which contains arbitrary distance values
 * from each node to each node in the system), and should also prefer nodes
 * with no CPUs, since presumably they'll have very little allocation pressure
 * on them otherwise.
 * It returns -1 if no node is found.
 */
static int __init find_next_best_node(int node, nodemask_t *used_node_mask)
{
	int i, n, val;
	int min_val = INT_MAX;
	int best_node = -1;

	for_each_online_node(i) {
		cpumask_t tmp;

		/* Start from local node */
		n = (node+i) % num_online_nodes();

		/* Don't want a node to appear more than once */
		if (node_isset(n, *used_node_mask))
			continue;

		/* Use the local node if we haven't already */
		if (!node_isset(node, *used_node_mask)) {
			best_node = node;
			break;
		}

		/* Use the distance array to find the distance */
		val = node_distance(node, n);

		/* Give preference to headless and unused nodes */
		tmp = node_to_cpumask(n);
		if (!cpus_empty(tmp))
			val += PENALTY_FOR_NODE_WITH_CPUS;

		/* Slight preference for less loaded node */
		val *= (MAX_NODE_LOAD*MAX_NUMNODES);
		val += node_load[n];

		if (val < min_val) {
			min_val = val;
			best_node = n;
		}
	}

	if (best_node >= 0)
		node_set(best_node, *used_node_mask);

	return best_node;
}

static void __init build_zonelists(pg_data_t *pgdat)
{
	int i, j, k, node, local_node;
	int prev_node, load;
	struct zonelist *zonelist;
	nodemask_t used_mask;

	/* initialize zonelists */
	for (i = 0; i < GFP_ZONETYPES; i++) {
		zonelist = pgdat->node_zonelists + i;
		zonelist->zones[0] = NULL;
	}

	/* NUMA-aware ordering of nodes */
	local_node = pgdat->node_id;
	load = num_online_nodes();
	prev_node = local_node;
	nodes_clear(used_mask);
	while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
		/*
		 * We don't want to pressure a particular node.
		 * So adding penalty to the first node in same
		 * distance group to make it round-robin.
		 */
		if (node_distance(local_node, node) !=
				node_distance(local_node, prev_node))
			node_load[node] += load;
		prev_node = node;
		load--;
		for (i = 0; i < GFP_ZONETYPES; i++) {
			zonelist = pgdat->node_zonelists + i;
			for (j = 0; zonelist->zones[j] != NULL; j++);

			k = ZONE_NORMAL;
			if (i & __GFP_HIGHMEM)
				k = ZONE_HIGHMEM;
			if (i & __GFP_DMA)
				k = ZONE_DMA;

	 		j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
			zonelist->zones[j] = NULL;
		}
	}
}

#else	/* CONFIG_NUMA */

static void __init build_zonelists(pg_data_t *pgdat)
{
	int i, j, k, node, local_node;

	local_node = pgdat->node_id;
	for (i = 0; i < GFP_ZONETYPES; i++) {
		struct zonelist *zonelist;

		zonelist = pgdat->node_zonelists + i;

		j = 0;
		k = ZONE_NORMAL;
		if (i & __GFP_HIGHMEM)
			k = ZONE_HIGHMEM;
		if (i & __GFP_DMA)
			k = ZONE_DMA;

 		j = build_zonelists_node(pgdat, zonelist, j, k);
 		/*
 		 * Now we build the zonelist so that it contains the zones
 		 * of all the other nodes.
 		 * We don't want to pressure a particular node, so when
 		 * building the zones for node N, we make sure that the
 		 * zones coming right after the local ones are those from
 		 * node N+1 (modulo N)
 		 */
		for (node = local_node + 1; node < MAX_NUMNODES; node++) {
			if (!node_online(node))
				continue;
			j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
		}
		for (node = 0; node < local_node; node++) {
			if (!node_online(node))
				continue;
			j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
		}

		zonelist->zones[j] = NULL;
	}
}

#endif	/* CONFIG_NUMA */

void __init build_all_zonelists(void)
{
	int i;

	for_each_online_node(i)
		build_zonelists(NODE_DATA(i));
	printk("Built %i zonelists\n", num_online_nodes());
	cpuset_init_current_mems_allowed();
}

/*
 * Helper functions to size the waitqueue hash table.
 * Essentially these want to choose hash table sizes sufficiently
 * large so that collisions trying to wait on pages are rare.
 * But in fact, the number of active page waitqueues on typical
 * systems is ridiculously low, less than 200. So this is even
 * conservative, even though it seems large.
 *
 * The constant PAGES_PER_WAITQUEUE specifies the ratio of pages to
 * waitqueues, i.e. the size of the waitq table given the number of pages.
 */
#define PAGES_PER_WAITQUEUE	256

static inline unsigned long wait_table_size(unsigned long pages)
{
	unsigned long size = 1;

	pages /= PAGES_PER_WAITQUEUE;

	while (size < pages)
		size <<= 1;

	/*
	 * Once we have dozens or even hundreds of threads sleeping
	 * on IO we've got bigger problems than wait queue collision.
	 * Limit the size of the wait table to a reasonable size.
	 */
	size = min(size, 4096UL);

	return max(size, 4UL);
}

/*
 * This is an integer logarithm so that shifts can be used later
 * to extract the more random high bits from the multiplicative
 * hash function before the remainder is taken.
 */
static inline unsigned long wait_table_bits(unsigned long size)
{
	return ffz(~size);
}

#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))

static void __init calculate_zone_totalpages(struct pglist_data *pgdat,
		unsigned long *zones_size, unsigned long *zholes_size)
{
	unsigned long realtotalpages, totalpages = 0;
	int i;

	for (i = 0; i < MAX_NR_ZONES; i++)
		totalpages += zones_size[i];
	pgdat->node_spanned_pages = totalpages;

	realtotalpages = totalpages;
	if (zholes_size)
		for (i = 0; i < MAX_NR_ZONES; i++)
			realtotalpages -= zholes_size[i];
	pgdat->node_present_pages = realtotalpages;
	printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages);
}


/*
 * Initially all pages are reserved - free ones are freed
 * up by free_all_bootmem() once the early boot process is
 * done. Non-atomic initialization, single-pass.
 */
void __init memmap_init_zone(unsigned long size, int nid, unsigned long zone,
		unsigned long start_pfn)
{
	struct page *start = pfn_to_page(start_pfn);
	struct page *page;

	for (page = start; page < (start + size); page++) {
		set_page_zone(page, NODEZONE(nid, zone));
		set_page_count(page, 0);
		reset_page_mapcount(page);
		SetPageReserved(page);
		INIT_LIST_HEAD(&page->lru);
#ifdef WANT_PAGE_VIRTUAL
		/* The shift won't overflow because ZONE_NORMAL is below 4G. */
		if (!is_highmem_idx(zone))
			set_page_address(page, __va(start_pfn << PAGE_SHIFT));
#endif
		start_pfn++;
	}
}

void zone_init_free_lists(struct pglist_data *pgdat, struct zone *zone,
				unsigned long size)
{
	int order;
	for (order = 0; order < MAX_ORDER ; order++) {
		INIT_LIST_HEAD(&zone->free_area[order].free_list);
		zone->free_area[order].nr_free = 0;
	}
}

#ifndef __HAVE_ARCH_MEMMAP_INIT
#define memmap_init(size, nid, zone, start_pfn) \
	memmap_init_zone((size), (nid), (zone), (start_pfn))
#endif

1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803
static int __devinit zone_batchsize(struct zone *zone)
{
	int batch;

	/*
	 * The per-cpu-pages pools are set to around 1000th of the
	 * size of the zone.  But no more than 1/4 of a meg - there's
	 * no point in going beyond the size of L2 cache.
	 *
	 * OK, so we don't know how big the cache is.  So guess.
	 */
	batch = zone->present_pages / 1024;
	if (batch * PAGE_SIZE > 256 * 1024)
		batch = (256 * 1024) / PAGE_SIZE;
	batch /= 4;		/* We effectively *= 4 below */
	if (batch < 1)
		batch = 1;

	/*
	 * Clamp the batch to a 2^n - 1 value. Having a power
	 * of 2 value was found to be more likely to have
	 * suboptimal cache aliasing properties in some cases.
	 *
	 * For example if 2 tasks are alternately allocating
	 * batches of pages, one task can end up with a lot
	 * of pages of one half of the possible page colors
	 * and the other with pages of the other colors.
	 */
	batch = (1 << fls(batch + batch/2)) - 1;
	return batch;
}

#ifdef CONFIG_NUMA
/*
 * Dynamicaly allocate memory for the
 * per cpu pageset array in struct zone.
 */
static int __devinit process_zones(int cpu)
{
	struct zone *zone, *dzone;
	int i;

	for_each_zone(zone) {
		struct per_cpu_pageset *npageset = NULL;

		npageset = kmalloc_node(sizeof(struct per_cpu_pageset),
					 GFP_KERNEL, cpu_to_node(cpu));
		if (!npageset) {
			zone->pageset[cpu] = NULL;
			goto bad;
		}

		if (zone->pageset[cpu]) {
			memcpy(npageset, zone->pageset[cpu],
					sizeof(struct per_cpu_pageset));

			/* Relocate lists */
			for (i = 0; i < 2; i++) {
				INIT_LIST_HEAD(&npageset->pcp[i].list);
				list_splice(&zone->pageset[cpu]->pcp[i].list,
					&npageset->pcp[i].list);
			}
 		} else {
			struct per_cpu_pages *pcp;
			unsigned long batch;

			batch = zone_batchsize(zone);

			pcp = &npageset->pcp[0];		/* hot */
			pcp->count = 0;
			pcp->low = 2 * batch;
			pcp->high = 6 * batch;
			pcp->batch = 1 * batch;
			INIT_LIST_HEAD(&pcp->list);

			pcp = &npageset->pcp[1];		/* cold*/
			pcp->count = 0;
			pcp->low = 0;
			pcp->high = 2 * batch;
			pcp->batch = 1 * batch;
			INIT_LIST_HEAD(&pcp->list);
		}
		zone->pageset[cpu] = npageset;
	}

	return 0;
bad:
	for_each_zone(dzone) {
		if (dzone == zone)
			break;
		kfree(dzone->pageset[cpu]);
		dzone->pageset[cpu] = NULL;
	}
	return -ENOMEM;
}

static inline void free_zone_pagesets(int cpu)
{
#ifdef CONFIG_NUMA
	struct zone *zone;

	for_each_zone(zone) {
		struct per_cpu_pageset *pset = zone_pcp(zone, cpu);

		zone_pcp(zone, cpu) = NULL;
		kfree(pset);
	}
#endif
}

static int __devinit pageset_cpuup_callback(struct notifier_block *nfb,
		unsigned long action,
		void *hcpu)
{
	int cpu = (long)hcpu;
	int ret = NOTIFY_OK;

	switch (action) {
		case CPU_UP_PREPARE:
			if (process_zones(cpu))
				ret = NOTIFY_BAD;
			break;
#ifdef CONFIG_HOTPLUG_CPU
		case CPU_DEAD:
			free_zone_pagesets(cpu);
			break;
#endif
		default:
			break;
	}
	return ret;
}

static struct notifier_block pageset_notifier =
	{ &pageset_cpuup_callback, NULL, 0 };

void __init setup_per_cpu_pageset()
{
	int err;

	/* Initialize per_cpu_pageset for cpu 0.
	 * A cpuup callback will do this for every cpu
	 * as it comes online
	 */
	err = process_zones(smp_processor_id());
	BUG_ON(err);
	register_cpu_notifier(&pageset_notifier);
}

#endif

L
Linus Torvalds 已提交
1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845
/*
 * Set up the zone data structures:
 *   - mark all pages reserved
 *   - mark all memory queues empty
 *   - clear the memory bitmaps
 */
static void __init free_area_init_core(struct pglist_data *pgdat,
		unsigned long *zones_size, unsigned long *zholes_size)
{
	unsigned long i, j;
	const unsigned long zone_required_alignment = 1UL << (MAX_ORDER-1);
	int cpu, nid = pgdat->node_id;
	unsigned long zone_start_pfn = pgdat->node_start_pfn;

	pgdat->nr_zones = 0;
	init_waitqueue_head(&pgdat->kswapd_wait);
	pgdat->kswapd_max_order = 0;
	
	for (j = 0; j < MAX_NR_ZONES; j++) {
		struct zone *zone = pgdat->node_zones + j;
		unsigned long size, realsize;
		unsigned long batch;

		zone_table[NODEZONE(nid, j)] = zone;
		realsize = size = zones_size[j];
		if (zholes_size)
			realsize -= zholes_size[j];

		if (j == ZONE_DMA || j == ZONE_NORMAL)
			nr_kernel_pages += realsize;
		nr_all_pages += realsize;

		zone->spanned_pages = size;
		zone->present_pages = realsize;
		zone->name = zone_names[j];
		spin_lock_init(&zone->lock);
		spin_lock_init(&zone->lru_lock);
		zone->zone_pgdat = pgdat;
		zone->free_pages = 0;

		zone->temp_priority = zone->prev_priority = DEF_PRIORITY;

1846
		batch = zone_batchsize(zone);
1847

L
Linus Torvalds 已提交
1848 1849
		for (cpu = 0; cpu < NR_CPUS; cpu++) {
			struct per_cpu_pages *pcp;
1850 1851 1852 1853 1854 1855 1856 1857 1858
#ifdef CONFIG_NUMA
			struct per_cpu_pageset *pgset;
			pgset = &pageset_table[nid*MAX_NR_ZONES*NR_CPUS +
					(j * NR_CPUS) + cpu];

			zone->pageset[cpu] = pgset;
#else
			struct per_cpu_pageset *pgset = zone_pcp(zone, cpu);
#endif
L
Linus Torvalds 已提交
1859

1860
			pcp = &pgset->pcp[0];			/* hot */
L
Linus Torvalds 已提交
1861 1862 1863 1864 1865 1866
			pcp->count = 0;
			pcp->low = 2 * batch;
			pcp->high = 6 * batch;
			pcp->batch = 1 * batch;
			INIT_LIST_HEAD(&pcp->list);

1867
			pcp = &pgset->pcp[1];			/* cold */
L
Linus Torvalds 已提交
1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881
			pcp->count = 0;
			pcp->low = 0;
			pcp->high = 2 * batch;
			pcp->batch = 1 * batch;
			INIT_LIST_HEAD(&pcp->list);
		}
		printk(KERN_DEBUG "  %s zone: %lu pages, LIFO batch:%lu\n",
				zone_names[j], realsize, batch);
		INIT_LIST_HEAD(&zone->active_list);
		INIT_LIST_HEAD(&zone->inactive_list);
		zone->nr_scan_active = 0;
		zone->nr_scan_inactive = 0;
		zone->nr_active = 0;
		zone->nr_inactive = 0;
1882
		atomic_set(&zone->reclaim_in_progress, -1);
L
Linus Torvalds 已提交
1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022
		if (!size)
			continue;

		/*
		 * The per-page waitqueue mechanism uses hashed waitqueues
		 * per zone.
		 */
		zone->wait_table_size = wait_table_size(size);
		zone->wait_table_bits =
			wait_table_bits(zone->wait_table_size);
		zone->wait_table = (wait_queue_head_t *)
			alloc_bootmem_node(pgdat, zone->wait_table_size
						* sizeof(wait_queue_head_t));

		for(i = 0; i < zone->wait_table_size; ++i)
			init_waitqueue_head(zone->wait_table + i);

		pgdat->nr_zones = j+1;

		zone->zone_mem_map = pfn_to_page(zone_start_pfn);
		zone->zone_start_pfn = zone_start_pfn;

		if ((zone_start_pfn) & (zone_required_alignment-1))
			printk(KERN_CRIT "BUG: wrong zone alignment, it will crash\n");

		memmap_init(size, nid, j, zone_start_pfn);

		zone_start_pfn += size;

		zone_init_free_lists(pgdat, zone, zone->spanned_pages);
	}
}

static void __init alloc_node_mem_map(struct pglist_data *pgdat)
{
	unsigned long size;

	/* Skip empty nodes */
	if (!pgdat->node_spanned_pages)
		return;

	/* ia64 gets its own node_mem_map, before this, without bootmem */
	if (!pgdat->node_mem_map) {
		size = (pgdat->node_spanned_pages + 1) * sizeof(struct page);
		pgdat->node_mem_map = alloc_bootmem_node(pgdat, size);
	}
#ifndef CONFIG_DISCONTIGMEM
	/*
	 * With no DISCONTIG, the global mem_map is just set as node 0's
	 */
	if (pgdat == NODE_DATA(0))
		mem_map = NODE_DATA(0)->node_mem_map;
#endif
}

void __init free_area_init_node(int nid, struct pglist_data *pgdat,
		unsigned long *zones_size, unsigned long node_start_pfn,
		unsigned long *zholes_size)
{
	pgdat->node_id = nid;
	pgdat->node_start_pfn = node_start_pfn;
	calculate_zone_totalpages(pgdat, zones_size, zholes_size);

	alloc_node_mem_map(pgdat);

	free_area_init_core(pgdat, zones_size, zholes_size);
}

#ifndef CONFIG_DISCONTIGMEM
static bootmem_data_t contig_bootmem_data;
struct pglist_data contig_page_data = { .bdata = &contig_bootmem_data };

EXPORT_SYMBOL(contig_page_data);

void __init free_area_init(unsigned long *zones_size)
{
	free_area_init_node(0, &contig_page_data, zones_size,
			__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
}
#endif

#ifdef CONFIG_PROC_FS

#include <linux/seq_file.h>

static void *frag_start(struct seq_file *m, loff_t *pos)
{
	pg_data_t *pgdat;
	loff_t node = *pos;

	for (pgdat = pgdat_list; pgdat && node; pgdat = pgdat->pgdat_next)
		--node;

	return pgdat;
}

static void *frag_next(struct seq_file *m, void *arg, loff_t *pos)
{
	pg_data_t *pgdat = (pg_data_t *)arg;

	(*pos)++;
	return pgdat->pgdat_next;
}

static void frag_stop(struct seq_file *m, void *arg)
{
}

/* 
 * This walks the free areas for each zone.
 */
static int frag_show(struct seq_file *m, void *arg)
{
	pg_data_t *pgdat = (pg_data_t *)arg;
	struct zone *zone;
	struct zone *node_zones = pgdat->node_zones;
	unsigned long flags;
	int order;

	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
		if (!zone->present_pages)
			continue;

		spin_lock_irqsave(&zone->lock, flags);
		seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
		for (order = 0; order < MAX_ORDER; ++order)
			seq_printf(m, "%6lu ", zone->free_area[order].nr_free);
		spin_unlock_irqrestore(&zone->lock, flags);
		seq_putc(m, '\n');
	}
	return 0;
}

struct seq_operations fragmentation_op = {
	.start	= frag_start,
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= frag_show,
};

N
Nikita Danilov 已提交
2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072
/*
 * Output information about zones in @pgdat.
 */
static int zoneinfo_show(struct seq_file *m, void *arg)
{
	pg_data_t *pgdat = arg;
	struct zone *zone;
	struct zone *node_zones = pgdat->node_zones;
	unsigned long flags;

	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; zone++) {
		int i;

		if (!zone->present_pages)
			continue;

		spin_lock_irqsave(&zone->lock, flags);
		seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name);
		seq_printf(m,
			   "\n  pages free     %lu"
			   "\n        min      %lu"
			   "\n        low      %lu"
			   "\n        high     %lu"
			   "\n        active   %lu"
			   "\n        inactive %lu"
			   "\n        scanned  %lu (a: %lu i: %lu)"
			   "\n        spanned  %lu"
			   "\n        present  %lu",
			   zone->free_pages,
			   zone->pages_min,
			   zone->pages_low,
			   zone->pages_high,
			   zone->nr_active,
			   zone->nr_inactive,
			   zone->pages_scanned,
			   zone->nr_scan_active, zone->nr_scan_inactive,
			   zone->spanned_pages,
			   zone->present_pages);
		seq_printf(m,
			   "\n        protection: (%lu",
			   zone->lowmem_reserve[0]);
		for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++)
			seq_printf(m, ", %lu", zone->lowmem_reserve[i]);
		seq_printf(m,
			   ")"
			   "\n  pagesets");
		for (i = 0; i < ARRAY_SIZE(zone->pageset); i++) {
			struct per_cpu_pageset *pageset;
			int j;

2073
			pageset = zone_pcp(zone, i);
N
Nikita Danilov 已提交
2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131
			for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
				if (pageset->pcp[j].count)
					break;
			}
			if (j == ARRAY_SIZE(pageset->pcp))
				continue;
			for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
				seq_printf(m,
					   "\n    cpu: %i pcp: %i"
					   "\n              count: %i"
					   "\n              low:   %i"
					   "\n              high:  %i"
					   "\n              batch: %i",
					   i, j,
					   pageset->pcp[j].count,
					   pageset->pcp[j].low,
					   pageset->pcp[j].high,
					   pageset->pcp[j].batch);
			}
#ifdef CONFIG_NUMA
			seq_printf(m,
				   "\n            numa_hit:       %lu"
				   "\n            numa_miss:      %lu"
				   "\n            numa_foreign:   %lu"
				   "\n            interleave_hit: %lu"
				   "\n            local_node:     %lu"
				   "\n            other_node:     %lu",
				   pageset->numa_hit,
				   pageset->numa_miss,
				   pageset->numa_foreign,
				   pageset->interleave_hit,
				   pageset->local_node,
				   pageset->other_node);
#endif
		}
		seq_printf(m,
			   "\n  all_unreclaimable: %u"
			   "\n  prev_priority:     %i"
			   "\n  temp_priority:     %i"
			   "\n  start_pfn:         %lu",
			   zone->all_unreclaimable,
			   zone->prev_priority,
			   zone->temp_priority,
			   zone->zone_start_pfn);
		spin_unlock_irqrestore(&zone->lock, flags);
		seq_putc(m, '\n');
	}
	return 0;
}

struct seq_operations zoneinfo_op = {
	.start	= frag_start, /* iterate over all zones. The same as in
			       * fragmentation. */
	.next	= frag_next,
	.stop	= frag_stop,
	.show	= zoneinfo_show,
};

L
Linus Torvalds 已提交
2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176
static char *vmstat_text[] = {
	"nr_dirty",
	"nr_writeback",
	"nr_unstable",
	"nr_page_table_pages",
	"nr_mapped",
	"nr_slab",

	"pgpgin",
	"pgpgout",
	"pswpin",
	"pswpout",
	"pgalloc_high",

	"pgalloc_normal",
	"pgalloc_dma",
	"pgfree",
	"pgactivate",
	"pgdeactivate",

	"pgfault",
	"pgmajfault",
	"pgrefill_high",
	"pgrefill_normal",
	"pgrefill_dma",

	"pgsteal_high",
	"pgsteal_normal",
	"pgsteal_dma",
	"pgscan_kswapd_high",
	"pgscan_kswapd_normal",

	"pgscan_kswapd_dma",
	"pgscan_direct_high",
	"pgscan_direct_normal",
	"pgscan_direct_dma",
	"pginodesteal",

	"slabs_scanned",
	"kswapd_steal",
	"kswapd_inodesteal",
	"pageoutrun",
	"allocstall",

	"pgrotated",
2177
	"nr_bounce",
L
Linus Torvalds 已提交
2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336
};

static void *vmstat_start(struct seq_file *m, loff_t *pos)
{
	struct page_state *ps;

	if (*pos >= ARRAY_SIZE(vmstat_text))
		return NULL;

	ps = kmalloc(sizeof(*ps), GFP_KERNEL);
	m->private = ps;
	if (!ps)
		return ERR_PTR(-ENOMEM);
	get_full_page_state(ps);
	ps->pgpgin /= 2;		/* sectors -> kbytes */
	ps->pgpgout /= 2;
	return (unsigned long *)ps + *pos;
}

static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos)
{
	(*pos)++;
	if (*pos >= ARRAY_SIZE(vmstat_text))
		return NULL;
	return (unsigned long *)m->private + *pos;
}

static int vmstat_show(struct seq_file *m, void *arg)
{
	unsigned long *l = arg;
	unsigned long off = l - (unsigned long *)m->private;

	seq_printf(m, "%s %lu\n", vmstat_text[off], *l);
	return 0;
}

static void vmstat_stop(struct seq_file *m, void *arg)
{
	kfree(m->private);
	m->private = NULL;
}

struct seq_operations vmstat_op = {
	.start	= vmstat_start,
	.next	= vmstat_next,
	.stop	= vmstat_stop,
	.show	= vmstat_show,
};

#endif /* CONFIG_PROC_FS */

#ifdef CONFIG_HOTPLUG_CPU
static int page_alloc_cpu_notify(struct notifier_block *self,
				 unsigned long action, void *hcpu)
{
	int cpu = (unsigned long)hcpu;
	long *count;
	unsigned long *src, *dest;

	if (action == CPU_DEAD) {
		int i;

		/* Drain local pagecache count. */
		count = &per_cpu(nr_pagecache_local, cpu);
		atomic_add(*count, &nr_pagecache);
		*count = 0;
		local_irq_disable();
		__drain_pages(cpu);

		/* Add dead cpu's page_states to our own. */
		dest = (unsigned long *)&__get_cpu_var(page_states);
		src = (unsigned long *)&per_cpu(page_states, cpu);

		for (i = 0; i < sizeof(struct page_state)/sizeof(unsigned long);
				i++) {
			dest[i] += src[i];
			src[i] = 0;
		}

		local_irq_enable();
	}
	return NOTIFY_OK;
}
#endif /* CONFIG_HOTPLUG_CPU */

void __init page_alloc_init(void)
{
	hotcpu_notifier(page_alloc_cpu_notify, 0);
}

/*
 * setup_per_zone_lowmem_reserve - called whenever
 *	sysctl_lower_zone_reserve_ratio changes.  Ensures that each zone
 *	has a correct pages reserved value, so an adequate number of
 *	pages are left in the zone after a successful __alloc_pages().
 */
static void setup_per_zone_lowmem_reserve(void)
{
	struct pglist_data *pgdat;
	int j, idx;

	for_each_pgdat(pgdat) {
		for (j = 0; j < MAX_NR_ZONES; j++) {
			struct zone *zone = pgdat->node_zones + j;
			unsigned long present_pages = zone->present_pages;

			zone->lowmem_reserve[j] = 0;

			for (idx = j-1; idx >= 0; idx--) {
				struct zone *lower_zone;

				if (sysctl_lowmem_reserve_ratio[idx] < 1)
					sysctl_lowmem_reserve_ratio[idx] = 1;

				lower_zone = pgdat->node_zones + idx;
				lower_zone->lowmem_reserve[j] = present_pages /
					sysctl_lowmem_reserve_ratio[idx];
				present_pages += lower_zone->present_pages;
			}
		}
	}
}

/*
 * setup_per_zone_pages_min - called when min_free_kbytes changes.  Ensures 
 *	that the pages_{min,low,high} values for each zone are set correctly 
 *	with respect to min_free_kbytes.
 */
static void setup_per_zone_pages_min(void)
{
	unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
	unsigned long lowmem_pages = 0;
	struct zone *zone;
	unsigned long flags;

	/* Calculate total number of !ZONE_HIGHMEM pages */
	for_each_zone(zone) {
		if (!is_highmem(zone))
			lowmem_pages += zone->present_pages;
	}

	for_each_zone(zone) {
		spin_lock_irqsave(&zone->lru_lock, flags);
		if (is_highmem(zone)) {
			/*
			 * Often, highmem doesn't need to reserve any pages.
			 * But the pages_min/low/high values are also used for
			 * batching up page reclaim activity so we need a
			 * decent value here.
			 */
			int min_pages;

			min_pages = zone->present_pages / 1024;
			if (min_pages < SWAP_CLUSTER_MAX)
				min_pages = SWAP_CLUSTER_MAX;
			if (min_pages > 128)
				min_pages = 128;
			zone->pages_min = min_pages;
		} else {
N
Nikita Danilov 已提交
2337
			/* if it's a lowmem zone, reserve a number of pages
L
Linus Torvalds 已提交
2338 2339
			 * proportionate to the zone's size.
			 */
N
Nikita Danilov 已提交
2340
			zone->pages_min = (pages_min * zone->present_pages) /
L
Linus Torvalds 已提交
2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514
			                   lowmem_pages;
		}

		/*
		 * When interpreting these watermarks, just keep in mind that:
		 * zone->pages_min == (zone->pages_min * 4) / 4;
		 */
		zone->pages_low   = (zone->pages_min * 5) / 4;
		zone->pages_high  = (zone->pages_min * 6) / 4;
		spin_unlock_irqrestore(&zone->lru_lock, flags);
	}
}

/*
 * Initialise min_free_kbytes.
 *
 * For small machines we want it small (128k min).  For large machines
 * we want it large (64MB max).  But it is not linear, because network
 * bandwidth does not increase linearly with machine size.  We use
 *
 * 	min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy:
 *	min_free_kbytes = sqrt(lowmem_kbytes * 16)
 *
 * which yields
 *
 * 16MB:	512k
 * 32MB:	724k
 * 64MB:	1024k
 * 128MB:	1448k
 * 256MB:	2048k
 * 512MB:	2896k
 * 1024MB:	4096k
 * 2048MB:	5792k
 * 4096MB:	8192k
 * 8192MB:	11584k
 * 16384MB:	16384k
 */
static int __init init_per_zone_pages_min(void)
{
	unsigned long lowmem_kbytes;

	lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10);

	min_free_kbytes = int_sqrt(lowmem_kbytes * 16);
	if (min_free_kbytes < 128)
		min_free_kbytes = 128;
	if (min_free_kbytes > 65536)
		min_free_kbytes = 65536;
	setup_per_zone_pages_min();
	setup_per_zone_lowmem_reserve();
	return 0;
}
module_init(init_per_zone_pages_min)

/*
 * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so 
 *	that we can call two helper functions whenever min_free_kbytes
 *	changes.
 */
int min_free_kbytes_sysctl_handler(ctl_table *table, int write, 
	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
	proc_dointvec(table, write, file, buffer, length, ppos);
	setup_per_zone_pages_min();
	return 0;
}

/*
 * lowmem_reserve_ratio_sysctl_handler - just a wrapper around
 *	proc_dointvec() so that we can call setup_per_zone_lowmem_reserve()
 *	whenever sysctl_lowmem_reserve_ratio changes.
 *
 * The reserve ratio obviously has absolutely no relation with the
 * pages_min watermarks. The lowmem reserve ratio can only make sense
 * if in function of the boot time zone sizes.
 */
int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
	proc_dointvec_minmax(table, write, file, buffer, length, ppos);
	setup_per_zone_lowmem_reserve();
	return 0;
}

__initdata int hashdist = HASHDIST_DEFAULT;

#ifdef CONFIG_NUMA
static int __init set_hashdist(char *str)
{
	if (!str)
		return 0;
	hashdist = simple_strtoul(str, &str, 0);
	return 1;
}
__setup("hashdist=", set_hashdist);
#endif

/*
 * allocate a large system hash table from bootmem
 * - it is assumed that the hash table must contain an exact power-of-2
 *   quantity of entries
 * - limit is the number of hash buckets, not the total allocation size
 */
void *__init alloc_large_system_hash(const char *tablename,
				     unsigned long bucketsize,
				     unsigned long numentries,
				     int scale,
				     int flags,
				     unsigned int *_hash_shift,
				     unsigned int *_hash_mask,
				     unsigned long limit)
{
	unsigned long long max = limit;
	unsigned long log2qty, size;
	void *table = NULL;

	/* allow the kernel cmdline to have a say */
	if (!numentries) {
		/* round applicable memory size up to nearest megabyte */
		numentries = (flags & HASH_HIGHMEM) ? nr_all_pages : nr_kernel_pages;
		numentries += (1UL << (20 - PAGE_SHIFT)) - 1;
		numentries >>= 20 - PAGE_SHIFT;
		numentries <<= 20 - PAGE_SHIFT;

		/* limit to 1 bucket per 2^scale bytes of low memory */
		if (scale > PAGE_SHIFT)
			numentries >>= (scale - PAGE_SHIFT);
		else
			numentries <<= (PAGE_SHIFT - scale);
	}
	/* rounded up to nearest power of 2 in size */
	numentries = 1UL << (long_log2(numentries) + 1);

	/* limit allocation size to 1/16 total memory by default */
	if (max == 0) {
		max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4;
		do_div(max, bucketsize);
	}

	if (numentries > max)
		numentries = max;

	log2qty = long_log2(numentries);

	do {
		size = bucketsize << log2qty;
		if (flags & HASH_EARLY)
			table = alloc_bootmem(size);
		else if (hashdist)
			table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
		else {
			unsigned long order;
			for (order = 0; ((1UL << order) << PAGE_SHIFT) < size; order++)
				;
			table = (void*) __get_free_pages(GFP_ATOMIC, order);
		}
	} while (!table && size > PAGE_SIZE && --log2qty);

	if (!table)
		panic("Failed to allocate %s hash table\n", tablename);

	printk("%s hash table entries: %d (order: %d, %lu bytes)\n",
	       tablename,
	       (1U << log2qty),
	       long_log2(size) - PAGE_SHIFT,
	       size);

	if (_hash_shift)
		*_hash_shift = log2qty;
	if (_hash_mask)
		*_hash_mask = (1 << log2qty) - 1;

	return table;
}