blob: 480907cc28beb83494308544e777a30300b06da2 [file] [log] [blame]
/*
* 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/stddef.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/jiffies.h>
#include <linux/bootmem.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/suspend.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/oom.h>
#include <linux/notifier.h>
#include <linux/topology.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/memory_hotplug.h>
#include <linux/nodemask.h>
#include <linux/vmalloc.h>
#include <linux/mempolicy.h>
#include <linux/stop_machine.h>
#include <linux/sort.h>
#include <linux/pfn.h>
#include <linux/backing-dev.h>
#include <linux/fault-inject.h>
#include <linux/page-isolation.h>
#include <linux/page_cgroup.h>
#include <linux/debugobjects.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include "internal.h"
/*
* Array of node states.
*/
nodemask_t node_states[NR_NODE_STATES] __read_mostly = {
[N_POSSIBLE] = NODE_MASK_ALL,
[N_ONLINE] = { { [0] = 1UL } },
#ifndef CONFIG_NUMA
[N_NORMAL_MEMORY] = { { [0] = 1UL } },
#ifdef CONFIG_HIGHMEM
[N_HIGH_MEMORY] = { { [0] = 1UL } },
#endif
[N_CPU] = { { [0] = 1UL } },
#endif /* NUMA */
};
EXPORT_SYMBOL(node_states);
unsigned long totalram_pages __read_mostly;
unsigned long totalreserve_pages __read_mostly;
unsigned long highest_memmap_pfn __read_mostly;
int percpu_pagelist_fraction;
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
int pageblock_order __read_mostly;
#endif
static void __free_pages_ok(struct page *page, unsigned int order);
/*
* 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
*
* TBD: should special case ZONE_DMA32 machines here - in those we normally
* don't need any ZONE_NORMAL reservation
*/
int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = {
#ifdef CONFIG_ZONE_DMA
256,
#endif
#ifdef CONFIG_ZONE_DMA32
256,
#endif
#ifdef CONFIG_HIGHMEM
32,
#endif
32,
};
EXPORT_SYMBOL(totalram_pages);
static char * const zone_names[MAX_NR_ZONES] = {
#ifdef CONFIG_ZONE_DMA
"DMA",
#endif
#ifdef CONFIG_ZONE_DMA32
"DMA32",
#endif
"Normal",
#ifdef CONFIG_HIGHMEM
"HighMem",
#endif
"Movable",
};
int min_free_kbytes = 1024;
unsigned long __meminitdata nr_kernel_pages;
unsigned long __meminitdata nr_all_pages;
static unsigned long __meminitdata dma_reserve;
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
/*
* MAX_ACTIVE_REGIONS determines the maximum number of distinct
* ranges of memory (RAM) that may be registered with add_active_range().
* Ranges passed to add_active_range() will be merged if possible
* so the number of times add_active_range() can be called is
* related to the number of nodes and the number of holes
*/
#ifdef CONFIG_MAX_ACTIVE_REGIONS
/* Allow an architecture to set MAX_ACTIVE_REGIONS to save memory */
#define MAX_ACTIVE_REGIONS CONFIG_MAX_ACTIVE_REGIONS
#else
#if MAX_NUMNODES >= 32
/* If there can be many nodes, allow up to 50 holes per node */
#define MAX_ACTIVE_REGIONS (MAX_NUMNODES*50)
#else
/* By default, allow up to 256 distinct regions */
#define MAX_ACTIVE_REGIONS 256
#endif
#endif
static struct node_active_region __meminitdata early_node_map[MAX_ACTIVE_REGIONS];
static int __meminitdata nr_nodemap_entries;
static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE
static unsigned long __meminitdata node_boundary_start_pfn[MAX_NUMNODES];
static unsigned long __meminitdata node_boundary_end_pfn[MAX_NUMNODES];
#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
static unsigned long __initdata required_kernelcore;
static unsigned long __initdata required_movablecore;
static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
int movable_zone;
EXPORT_SYMBOL(movable_zone);
#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
#if MAX_NUMNODES > 1
int nr_node_ids __read_mostly = MAX_NUMNODES;
EXPORT_SYMBOL(nr_node_ids);
#endif
int page_group_by_mobility_disabled __read_mostly;
static void set_pageblock_migratetype(struct page *page, int migratetype)
{
set_pageblock_flags_group(page, (unsigned long)migratetype,
PB_migrate, PB_migrate_end);
}
#ifdef CONFIG_DEBUG_VM
static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
{
int ret = 0;
unsigned seq;
unsigned long pfn = page_to_pfn(page);
do {
seq = zone_span_seqbegin(zone);
if (pfn >= zone->zone_start_pfn + zone->spanned_pages)
ret = 1;
else if (pfn < zone->zone_start_pfn)
ret = 1;
} while (zone_span_seqretry(zone, seq));
return ret;
}
static int page_is_consistent(struct zone *zone, struct page *page)
{
if (!pfn_valid_within(page_to_pfn(page)))
return 0;
if (zone != page_zone(page))
return 0;
return 1;
}
/*
* Temporary debugging check for pages not lying within a given zone.
*/
static int bad_range(struct zone *zone, struct page *page)
{
if (page_outside_zone_boundaries(zone, page))
return 1;
if (!page_is_consistent(zone, page))
return 1;
return 0;
}
#else
static inline int bad_range(struct zone *zone, struct page *page)
{
return 0;
}
#endif
static void bad_page(struct page *page)
{
static unsigned long resume;
static unsigned long nr_shown;
static unsigned long nr_unshown;
/*
* Allow a burst of 60 reports, then keep quiet for that minute;
* or allow a steady drip of one report per second.
*/
if (nr_shown == 60) {
if (time_before(jiffies, resume)) {
nr_unshown++;
goto out;
}
if (nr_unshown) {
printk(KERN_ALERT
"BUG: Bad page state: %lu messages suppressed\n",
nr_unshown);
nr_unshown = 0;
}
nr_shown = 0;
}
if (nr_shown++ == 0)
resume = jiffies + 60 * HZ;
printk(KERN_ALERT "BUG: Bad page state in process %s pfn:%05lx\n",
current->comm, page_to_pfn(page));
printk(KERN_ALERT
"page:%p flags:%p count:%d mapcount:%d mapping:%p index:%lx\n",
page, (void *)page->flags, page_count(page),
page_mapcount(page), page->mapping, page->index);
dump_stack();
out:
/* Leave bad fields for debug, except PageBuddy could make trouble */
__ClearPageBuddy(page);
add_taint(TAINT_BAD_PAGE);
}
/*
* 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 ->lru.next holds the address of the compound page's
* put_page() function. Its ->lru.prev holds the order of allocation.
* This usage means that zero-order pages may not be compound.
*/
static void free_compound_page(struct page *page)
{
__free_pages_ok(page, compound_order(page));
}
void prep_compound_page(struct page *page, unsigned long order)
{
int i;
int nr_pages = 1 << order;
set_compound_page_dtor(page, free_compound_page);
set_compound_order(page, order);
__SetPageHead(page);
for (i = 1; i < nr_pages; i++) {
struct page *p = page + i;
__SetPageTail(p);
p->first_page = page;
}
}
#ifdef CONFIG_HUGETLBFS
void prep_compound_gigantic_page(struct page *page, unsigned long order)
{
int i;
int nr_pages = 1 << order;
struct page *p = page + 1;
set_compound_page_dtor(page, free_compound_page);
set_compound_order(page, order);
__SetPageHead(page);
for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
__SetPageTail(p);
p->first_page = page;
}
}
#endif
static int destroy_compound_page(struct page *page, unsigned long order)
{
int i;
int nr_pages = 1 << order;
int bad = 0;
if (unlikely(compound_order(page) != order) ||
unlikely(!PageHead(page))) {
bad_page(page);
bad++;
}
__ClearPageHead(page);
for (i = 1; i < nr_pages; i++) {
struct page *p = page + i;
if (unlikely(!PageTail(p) || (p->first_page != page))) {
bad_page(page);
bad++;
}
__ClearPageTail(p);
}
return bad;
}
static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
{
int i;
/*
* clear_highpage() will use KM_USER0, so it's a bug to use __GFP_ZERO
* and __GFP_HIGHMEM from hard or soft interrupt context.
*/
VM_BUG_ON((gfp_flags & __GFP_HIGHMEM) && in_interrupt());
for (i = 0; i < (1 << order); i++)
clear_highpage(page + i);
}
static inline void set_page_order(struct page *page, int order)
{
set_page_private(page, order);
__SetPageBuddy(page);
}
static inline void rmv_page_order(struct page *page)
{
__ClearPageBuddy(page);
set_page_private(page, 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 contiguous 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 not in a hole &&
* (b) the buddy is in the buddy system &&
* (c) a page and its buddy have the same order &&
* (d) a page and its buddy are in the same zone.
*
* For recording whether a page is in the buddy system, we use PG_buddy.
* Setting, clearing, and testing PG_buddy is serialized by zone->lock.
*
* For recording page's order, we use page_private(page).
*/
static inline int page_is_buddy(struct page *page, struct page *buddy,
int order)
{
if (!pfn_valid_within(page_to_pfn(buddy)))
return 0;
if (page_zone_id(page) != page_zone_id(buddy))
return 0;
if (PageBuddy(buddy) && page_order(buddy) == order) {
BUG_ON(page_count(buddy) != 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_buddy. Page's
* order is recorded in page_private(page) 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_one_page(struct page *page,
struct zone *zone, unsigned int order)
{
unsigned long page_idx;
int order_size = 1 << order;
int migratetype = get_pageblock_migratetype(page);
if (unlikely(PageCompound(page)))
if (unlikely(destroy_compound_page(page, order)))
return;
page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);
VM_BUG_ON(page_idx & (order_size - 1));
VM_BUG_ON(bad_range(zone, page));
__mod_zone_page_state(zone, NR_FREE_PAGES, order_size);
while (order < MAX_ORDER-1) {
unsigned long combined_idx;
struct page *buddy;
buddy = __page_find_buddy(page, page_idx, order);
if (!page_is_buddy(page, buddy, order))
break;
/* Our buddy is free, merge with it and move up one order. */
list_del(&buddy->lru);
zone->free_area[order].nr_free--;
rmv_page_order(buddy);
combined_idx = __find_combined_index(page_idx, order);
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[migratetype]);
zone->free_area[order].nr_free++;
}
static inline int free_pages_check(struct page *page)
{
free_page_mlock(page);
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
(page_count(page) != 0) |
(page->flags & PAGE_FLAGS_CHECK_AT_FREE))) {
bad_page(page);
return 1;
}
if (page->flags & PAGE_FLAGS_CHECK_AT_PREP)
page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
return 0;
}
/*
* 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.
*
* 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 void free_pages_bulk(struct zone *zone, int count,
struct list_head *list, int order)
{
spin_lock(&zone->lock);
zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
zone->pages_scanned = 0;
while (count--) {
struct page *page;
VM_BUG_ON(list_empty(list));
page = list_entry(list->prev, struct page, lru);
/* have to delete it as __free_one_page list manipulates */
list_del(&page->lru);
__free_one_page(page, zone, order);
}
spin_unlock(&zone->lock);
}
static void free_one_page(struct zone *zone, struct page *page, int order)
{
spin_lock(&zone->lock);
zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
zone->pages_scanned = 0;
__free_one_page(page, zone, order);
spin_unlock(&zone->lock);
}
static void __free_pages_ok(struct page *page, unsigned int order)
{
unsigned long flags;
int i;
int bad = 0;
for (i = 0 ; i < (1 << order) ; ++i)
bad += free_pages_check(page + i);
if (bad)
return;
if (!PageHighMem(page)) {
debug_check_no_locks_freed(page_address(page),PAGE_SIZE<<order);
debug_check_no_obj_freed(page_address(page),
PAGE_SIZE << order);
}
arch_free_page(page, order);
kernel_map_pages(page, 1 << order, 0);
local_irq_save(flags);
__count_vm_events(PGFREE, 1 << order);
free_one_page(page_zone(page), page, order);
local_irq_restore(flags);
}
/*
* permit the bootmem allocator to evade page validation on high-order frees
*/
void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
{
if (order == 0) {
__ClearPageReserved(page);
set_page_count(page, 0);
set_page_refcounted(page);
__free_page(page);
} else {
int loop;
prefetchw(page);
for (loop = 0; loop < BITS_PER_LONG; loop++) {
struct page *p = &page[loop];
if (loop + 1 < BITS_PER_LONG)
prefetchw(p + 1);
__ClearPageReserved(p);
set_page_count(p, 0);
}
set_page_refcounted(page);
__free_pages(page, 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 void expand(struct zone *zone, struct page *page,
int low, int high, struct free_area *area,
int migratetype)
{
unsigned long size = 1 << high;
while (high > low) {
area--;
high--;
size >>= 1;
VM_BUG_ON(bad_range(zone, &page[size]));
list_add(&page[size].lru, &area->free_list[migratetype]);
area->nr_free++;
set_page_order(&page[size], high);
}
}
/*
* This page is about to be returned from the page allocator
*/
static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
{
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
(page_count(page) != 0) |
(page->flags & PAGE_FLAGS_CHECK_AT_PREP))) {
bad_page(page);
return 1;
}
set_page_private(page, 0);
set_page_refcounted(page);
arch_alloc_page(page, order);
kernel_map_pages(page, 1 << order, 1);
if (gfp_flags & __GFP_ZERO)
prep_zero_page(page, order, gfp_flags);
if (order && (gfp_flags & __GFP_COMP))
prep_compound_page(page, order);
return 0;
}
/*
* Go through the free lists for the given migratetype and remove
* the smallest available page from the freelists
*/
static struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
int migratetype)
{
unsigned int current_order;
struct free_area * area;
struct page *page;
/* Find a page of the appropriate size in the preferred list */
for (current_order = order; current_order < MAX_ORDER; ++current_order) {
area = &(zone->free_area[current_order]);
if (list_empty(&area->free_list[migratetype]))
continue;
page = list_entry(area->free_list[migratetype].next,
struct page, lru);
list_del(&page->lru);
rmv_page_order(page);
area->nr_free--;
__mod_zone_page_state(zone, NR_FREE_PAGES, - (1UL << order));
expand(zone, page, order, current_order, area, migratetype);
return page;
}
return NULL;
}
/*
* This array describes the order lists are fallen back to when
* the free lists for the desirable migrate type are depleted
*/
static int fallbacks[MIGRATE_TYPES][MIGRATE_TYPES-1] = {
[MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE },
[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE },
[MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE },
[MIGRATE_RESERVE] = { MIGRATE_RESERVE, MIGRATE_RESERVE, MIGRATE_RESERVE }, /* Never used */
};
/*
* Move the free pages in a range to the free lists of the requested type.
* Note that start_page and end_pages are not aligned on a pageblock
* boundary. If alignment is required, use move_freepages_block()
*/
static int move_freepages(struct zone *zone,
struct page *start_page, struct page *end_page,
int migratetype)
{
struct page *page;
unsigned long order;
int pages_moved = 0;
#ifndef CONFIG_HOLES_IN_ZONE
/*
* page_zone is not safe to call in this context when
* CONFIG_HOLES_IN_ZONE is set. This bug check is probably redundant
* anyway as we check zone boundaries in move_freepages_block().
* Remove at a later date when no bug reports exist related to
* grouping pages by mobility
*/
BUG_ON(page_zone(start_page) != page_zone(end_page));
#endif
for (page = start_page; page <= end_page;) {
/* Make sure we are not inadvertently changing nodes */
VM_BUG_ON(page_to_nid(page) != zone_to_nid(zone));
if (!pfn_valid_within(page_to_pfn(page))) {
page++;
continue;
}
if (!PageBuddy(page)) {
page++;
continue;
}
order = page_order(page);
list_del(&page->lru);
list_add(&page->lru,
&zone->free_area[order].free_list[migratetype]);
page += 1 << order;
pages_moved += 1 << order;
}
return pages_moved;
}
static int move_freepages_block(struct zone *zone, struct page *page,
int migratetype)
{
unsigned long start_pfn, end_pfn;
struct page *start_page, *end_page;
start_pfn = page_to_pfn(page);
start_pfn = start_pfn & ~(pageblock_nr_pages-1);
start_page = pfn_to_page(start_pfn);
end_page = start_page + pageblock_nr_pages - 1;
end_pfn = start_pfn + pageblock_nr_pages - 1;
/* Do not cross zone boundaries */
if (start_pfn < zone->zone_start_pfn)
start_page = page;
if (end_pfn >= zone->zone_start_pfn + zone->spanned_pages)
return 0;
return move_freepages(zone, start_page, end_page, migratetype);
}
/* Remove an element from the buddy allocator from the fallback list */
static struct page *__rmqueue_fallback(struct zone *zone, int order,
int start_migratetype)
{
struct free_area * area;
int current_order;
struct page *page;
int migratetype, i;
/* Find the largest possible block of pages in the other list */
for (current_order = MAX_ORDER-1; current_order >= order;
--current_order) {
for (i = 0; i < MIGRATE_TYPES - 1; i++) {
migratetype = fallbacks[start_migratetype][i];
/* MIGRATE_RESERVE handled later if necessary */
if (migratetype == MIGRATE_RESERVE)
continue;
area = &(zone->free_area[current_order]);
if (list_empty(&area->free_list[migratetype]))
continue;
page = list_entry(area->free_list[migratetype].next,
struct page, lru);
area->nr_free--;
/*
* If breaking a large block of pages, move all free
* pages to the preferred allocation list. If falling
* back for a reclaimable kernel allocation, be more
* agressive about taking ownership of free pages
*/
if (unlikely(current_order >= (pageblock_order >> 1)) ||
start_migratetype == MIGRATE_RECLAIMABLE) {
unsigned long pages;
pages = move_freepages_block(zone, page,
start_migratetype);
/* Claim the whole block if over half of it is free */
if (pages >= (1 << (pageblock_order-1)))
set_pageblock_migratetype(page,
start_migratetype);
migratetype = start_migratetype;
}
/* Remove the page from the freelists */
list_del(&page->lru);
rmv_page_order(page);
__mod_zone_page_state(zone, NR_FREE_PAGES,
-(1UL << order));
if (current_order == pageblock_order)
set_pageblock_migratetype(page,
start_migratetype);
expand(zone, page, order, current_order, area, migratetype);
return page;
}
}
/* Use MIGRATE_RESERVE rather than fail an allocation */
return __rmqueue_smallest(zone, order, MIGRATE_RESERVE);
}
/*
* 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,
int migratetype)
{
struct page *page;
page = __rmqueue_smallest(zone, order, migratetype);
if (unlikely(!page))
page = __rmqueue_fallback(zone, order, migratetype);
return page;
}
/*
* 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,
int migratetype)
{
int i;
spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
struct page *page = __rmqueue(zone, order, migratetype);
if (unlikely(page == NULL))
break;
/*
* Split buddy pages returned by expand() are received here
* in physical page order. The page is added to the callers and
* list and the list head then moves forward. From the callers
* perspective, the linked list is ordered by page number in
* some conditions. This is useful for IO devices that can
* merge IO requests if the physical pages are ordered
* properly.
*/
list_add(&page->lru, list);
set_page_private(page, migratetype);
list = &page->lru;
}
spin_unlock(&zone->lock);
return i;
}
#ifdef CONFIG_NUMA
/*
* Called from the vmstat counter updater to drain pagesets of this
* currently executing processor on remote nodes after they have
* expired.
*
* Note that this function must be called with the thread pinned to
* a single processor.
*/
void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
{
unsigned long flags;
int to_drain;
local_irq_save(flags);
if (pcp->count >= pcp->batch)
to_drain = pcp->batch;
else
to_drain = pcp->count;
free_pages_bulk(zone, to_drain, &pcp->list, 0);
pcp->count -= to_drain;
local_irq_restore(flags);
}
#endif
/*
* Drain pages of the indicated processor.
*
* The processor must either be the current processor and the
* thread pinned to the current processor or a processor that
* is not online.
*/
static void drain_pages(unsigned int cpu)
{
unsigned long flags;
struct zone *zone;
for_each_populated_zone(zone) {
struct per_cpu_pageset *pset;
struct per_cpu_pages *pcp;
pset = zone_pcp(zone, cpu);
pcp = &pset->pcp;
local_irq_save(flags);
free_pages_bulk(zone, pcp->count, &pcp->list, 0);
pcp->count = 0;
local_irq_restore(flags);
}
}
/*
* Spill all of this CPU's per-cpu pages back into the buddy allocator.
*/
void drain_local_pages(void *arg)
{
drain_pages(smp_processor_id());
}
/*
* Spill all the per-cpu pages from all CPUs back into the buddy allocator
*/
void drain_all_pages(void)
{
on_each_cpu(drain_local_pages, NULL, 1);
}
#ifdef CONFIG_HIBERNATION
void mark_free_pages(struct zone *zone)
{
unsigned long pfn, max_zone_pfn;
unsigned long flags;
int order, t;
struct list_head *curr;
if (!zone->spanned_pages)
return;
spin_lock_irqsave(&zone->lock, flags);
max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
if (pfn_valid(pfn)) {
struct page *page = pfn_to_page(pfn);
if (!swsusp_page_is_forbidden(page))
swsusp_unset_page_free(page);
}
for_each_migratetype_order(order, t) {
list_for_each(curr, &zone->free_area[order].free_list[t]) {
unsigned long i;
pfn = page_to_pfn(list_entry(curr, struct page, lru));
for (i = 0; i < (1UL << order); i++)
swsusp_set_page_free(pfn_to_page(pfn + i));
}
}
spin_unlock_irqrestore(&zone->lock, flags);
}
#endif /* CONFIG_PM */
/*
* Free a 0-order page
*/
static void free_hot_cold_page(struct page *page, int cold)
{
struct zone *zone = page_zone(page);
struct per_cpu_pages *pcp;
unsigned long flags;
if (PageAnon(page))
page->mapping = NULL;
if (free_pages_check(page))
return;
if (!PageHighMem(page)) {
debug_check_no_locks_freed(page_address(page), PAGE_SIZE);
debug_check_no_obj_freed(page_address(page), PAGE_SIZE);
}
arch_free_page(page, 0);
kernel_map_pages(page, 1, 0);
pcp = &zone_pcp(zone, get_cpu())->pcp;
local_irq_save(flags);
__count_vm_event(PGFREE);
if (cold)
list_add_tail(&page->lru, &pcp->list);
else
list_add(&page->lru, &pcp->list);
set_page_private(page, get_pageblock_migratetype(page));
pcp->count++;
if (pcp->count >= pcp->high) {
free_pages_bulk(zone, pcp->batch, &pcp->list, 0);
pcp->count -= pcp->batch;
}
local_irq_restore(flags);
put_cpu();
}
void free_hot_page(struct page *page)
{
free_hot_cold_page(page, 0);
}
void free_cold_page(struct page *page)
{
free_hot_cold_page(page, 1);
}
/*
* split_page takes a non-compound higher-order page, and splits it into
* n (1<<order) sub-pages: page[0..n]
* Each sub-page must be freed individually.
*
* Note: this is probably too low level an operation for use in drivers.
* Please consult with lkml before using this in your driver.
*/
void split_page(struct page *page, unsigned int order)
{
int i;
VM_BUG_ON(PageCompound(page));
VM_BUG_ON(!page_count(page));
for (i = 1; i < (1 << order); i++)
set_page_refcounted(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 *preferred_zone,
struct zone *zone, int order, gfp_t gfp_flags)
{
unsigned long flags;
struct page *page;
int cold = !!(gfp_flags & __GFP_COLD);
int cpu;
int migratetype = allocflags_to_migratetype(gfp_flags);
again:
cpu = get_cpu();
if (likely(order == 0)) {
struct per_cpu_pages *pcp;
pcp = &zone_pcp(zone, cpu)->pcp;
local_irq_save(flags);
if (!pcp->count) {
pcp->count = rmqueue_bulk(zone, 0,
pcp->batch, &pcp->list, migratetype);
if (unlikely(!pcp->count))
goto failed;
}
/* Find a page of the appropriate migrate type */
if (cold) {
list_for_each_entry_reverse(page, &pcp->list, lru)
if (page_private(page) == migratetype)
break;
} else {
list_for_each_entry(page, &pcp->list, lru)
if (page_private(page) == migratetype)
break;
}
/* Allocate more to the pcp list if necessary */
if (unlikely(&page->lru == &pcp->list)) {
pcp->count += rmqueue_bulk(zone, 0,
pcp->batch, &pcp->list, migratetype);
page = list_entry(pcp->list.next, struct page, lru);
}
list_del(&page->lru);
pcp->count--;
} else {
spin_lock_irqsave(&zone->lock, flags);
page = __rmqueue(zone, order, migratetype);
spin_unlock(&zone->lock);
if (!page)
goto failed;
}
__count_zone_vm_events(PGALLOC, zone, 1 << order);
zone_statistics(preferred_zone, zone);
local_irq_restore(flags);
put_cpu();
VM_BUG_ON(bad_range(zone, page));
if (prep_new_page(page, order, gfp_flags))
goto again;
return page;
failed:
local_irq_restore(flags);
put_cpu();
return NULL;
}
#define ALLOC_NO_WATERMARKS 0x01 /* don't check watermarks at all */
#define ALLOC_WMARK_MIN 0x02 /* use pages_min watermark */
#define ALLOC_WMARK_LOW 0x04 /* use pages_low watermark */
#define ALLOC_WMARK_HIGH 0x08 /* use pages_high watermark */
#define ALLOC_HARDER 0x10 /* try to alloc harder */
#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */
#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
#ifdef CONFIG_FAIL_PAGE_ALLOC
static struct fail_page_alloc_attr {
struct fault_attr attr;
u32 ignore_gfp_highmem;
u32 ignore_gfp_wait;
u32 min_order;
#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
struct dentry *ignore_gfp_highmem_file;
struct dentry *ignore_gfp_wait_file;
struct dentry *min_order_file;
#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
} fail_page_alloc = {
.attr = FAULT_ATTR_INITIALIZER,
.ignore_gfp_wait = 1,
.ignore_gfp_highmem = 1,
.min_order = 1,
};
static int __init setup_fail_page_alloc(char *str)
{
return setup_fault_attr(&fail_page_alloc.attr, str);
}
__setup("fail_page_alloc=", setup_fail_page_alloc);
static int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
if (order < fail_page_alloc.min_order)
return 0;
if (gfp_mask & __GFP_NOFAIL)
return 0;
if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM))
return 0;
if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT))
return 0;
return should_fail(&fail_page_alloc.attr, 1 << order);
}
#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
static int __init fail_page_alloc_debugfs(void)
{
mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
struct dentry *dir;
int err;
err = init_fault_attr_dentries(&fail_page_alloc.attr,
"fail_page_alloc");
if (err)
return err;
dir = fail_page_alloc.attr.dentries.dir;
fail_page_alloc.ignore_gfp_wait_file =
debugfs_create_bool("ignore-gfp-wait", mode, dir,
&fail_page_alloc.ignore_gfp_wait);
fail_page_alloc.ignore_gfp_highmem_file =
debugfs_create_bool("ignore-gfp-highmem", mode, dir,
&fail_page_alloc.ignore_gfp_highmem);
fail_page_alloc.min_order_file =
debugfs_create_u32("min-order", mode, dir,
&fail_page_alloc.min_order);
if (!fail_page_alloc.ignore_gfp_wait_file ||
!fail_page_alloc.ignore_gfp_highmem_file ||
!fail_page_alloc.min_order_file) {
err = -ENOMEM;
debugfs_remove(fail_page_alloc.ignore_gfp_wait_file);
debugfs_remove(fail_page_alloc.ignore_gfp_highmem_file);
debugfs_remove(fail_page_alloc.min_order_file);
cleanup_fault_attr_dentries(&fail_page_alloc.attr);
}
return err;
}
late_initcall(fail_page_alloc_debugfs);
#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
#else /* CONFIG_FAIL_PAGE_ALLOC */
static inline int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
return 0;
}
#endif /* CONFIG_FAIL_PAGE_ALLOC */
/*
* 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 alloc_flags)
{
/* free_pages my go negative - that's OK */
long min = mark;
long free_pages = zone_page_state(z, NR_FREE_PAGES) - (1 << order) + 1;
int o;
if (alloc_flags & ALLOC_HIGH)
min -= min / 2;
if (alloc_flags & ALLOC_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;
}
#ifdef CONFIG_NUMA
/*
* zlc_setup - Setup for "zonelist cache". Uses cached zone data to
* skip over zones that are not allowed by the cpuset, or that have
* been recently (in last second) found to be nearly full. See further
* comments in mmzone.h. Reduces cache footprint of zonelist scans
* that have to skip over a lot of full or unallowed zones.
*
* If the zonelist cache is present in the passed in zonelist, then
* returns a pointer to the allowed node mask (either the current
* tasks mems_allowed, or node_states[N_HIGH_MEMORY].)
*
* If the zonelist cache is not available for this zonelist, does
* nothing and returns NULL.
*
* If the fullzones BITMAP in the zonelist cache is stale (more than
* a second since last zap'd) then we zap it out (clear its bits.)
*
* We hold off even calling zlc_setup, until after we've checked the
* first zone in the zonelist, on the theory that most allocations will
* be satisfied from that first zone, so best to examine that zone as
* quickly as we can.
*/
static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
{
struct zonelist_cache *zlc; /* cached zonelist speedup info */
nodemask_t *allowednodes; /* zonelist_cache approximation */
zlc = zonelist->zlcache_ptr;
if (!zlc)
return NULL;
if (time_after(jiffies, zlc->last_full_zap + HZ)) {
bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
zlc->last_full_zap = jiffies;
}
allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ?
&cpuset_current_mems_allowed :
&node_states[N_HIGH_MEMORY];
return allowednodes;
}
/*
* Given 'z' scanning a zonelist, run a couple of quick checks to see
* if it is worth looking at further for free memory:
* 1) Check that the zone isn't thought to be full (doesn't have its
* bit set in the zonelist_cache fullzones BITMAP).
* 2) Check that the zones node (obtained from the zonelist_cache
* z_to_n[] mapping) is allowed in the passed in allowednodes mask.
* Return true (non-zero) if zone is worth looking at further, or
* else return false (zero) if it is not.
*
* This check -ignores- the distinction between various watermarks,
* such as GFP_HIGH, GFP_ATOMIC, PF_MEMALLOC, ... If a zone is
* found to be full for any variation of these watermarks, it will
* be considered full for up to one second by all requests, unless
* we are so low on memory on all allowed nodes that we are forced
* into the second scan of the zonelist.
*
* In the second scan we ignore this zonelist cache and exactly
* apply the watermarks to all zones, even it is slower to do so.
* We are low on memory in the second scan, and should leave no stone
* unturned looking for a free page.
*/
static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
nodemask_t *allowednodes)
{
struct zonelist_cache *zlc; /* cached zonelist speedup info */
int i; /* index of *z in zonelist zones */
int n; /* node that zone *z is on */
zlc = zonelist->zlcache_ptr;
if (!zlc)
return 1;
i = z - zonelist->_zonerefs;
n = zlc->z_to_n[i];
/* This zone is worth trying if it is allowed but not full */
return node_isset(n, *allowednodes) && !test_bit(i, zlc->fullzones);
}
/*
* Given 'z' scanning a zonelist, set the corresponding bit in
* zlc->fullzones, so that subsequent attempts to allocate a page
* from that zone don't waste time re-examining it.
*/
static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
{
struct zonelist_cache *zlc; /* cached zonelist speedup info */
int i; /* index of *z in zonelist zones */
zlc = zonelist->zlcache_ptr;
if (!zlc)
return;
i = z - zonelist->_zonerefs;
set_bit(i, zlc->fullzones);
}
#else /* CONFIG_NUMA */
static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
{
return NULL;
}
static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
nodemask_t *allowednodes)
{
return 1;
}
static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
{
}
#endif /* CONFIG_NUMA */
/*
* get_page_from_freelist goes through the zonelist trying to allocate
* a page.
*/
static struct page *
get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
struct zonelist *zonelist, int high_zoneidx, int alloc_flags)
{
struct zoneref *z;
struct page *page = NULL;
int classzone_idx;
struct zone *zone, *preferred_zone;
nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
int zlc_active = 0; /* set if using zonelist_cache */
int did_zlc_setup = 0; /* just call zlc_setup() one time */
(void)first_zones_zonelist(zonelist, high_zoneidx, nodemask,
&preferred_zone);
if (!preferred_zone)
return NULL;
classzone_idx = zone_idx(preferred_zone);
zonelist_scan:
/*
* Scan zonelist, looking for a zone with enough free.
* See also cpuset_zone_allowed() comment in kernel/cpuset.c.
*/
for_each_zone_zonelist_nodemask(zone, z, zonelist,
high_zoneidx, nodemask) {
if (NUMA_BUILD && zlc_active &&
!zlc_zone_worth_trying(zonelist, z, allowednodes))
continue;
if ((alloc_flags & ALLOC_CPUSET) &&
!cpuset_zone_allowed_softwall(zone, gfp_mask))
goto try_next_zone;
if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
unsigned long mark;
int ret;
if (alloc_flags & ALLOC_WMARK_MIN)
mark = zone->pages_min;
else if (alloc_flags & ALLOC_WMARK_LOW)
mark = zone->pages_low;
else
mark = zone->pages_high;
if (zone_watermark_ok(zone, order, mark,
classzone_idx, alloc_flags))
goto try_this_zone;
if (zone_reclaim_mode == 0)
goto this_zone_full;
ret = zone_reclaim(zone, gfp_mask, order);
switch (ret) {
case ZONE_RECLAIM_NOSCAN:
/* did not scan */
goto try_next_zone;
case ZONE_RECLAIM_FULL:
/* scanned but unreclaimable */
goto this_zone_full;
default:
/* did we reclaim enough */
if (!zone_watermark_ok(zone, order, mark,
classzone_idx, alloc_flags))
goto this_zone_full;
}
}
try_this_zone:
page = buffered_rmqueue(preferred_zone, zone, order, gfp_mask);
if (page)
break;
this_zone_full:
if (NUMA_BUILD)
zlc_mark_zone_full(zonelist, z);
try_next_zone:
if (NUMA_BUILD && !did_zlc_setup) {
/* we do zlc_setup after the first zone is tried */
allowednodes = zlc_setup(zonelist, alloc_flags);
zlc_active = 1;
did_zlc_setup = 1;
}
}
if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
/* Disable zlc cache for second zonelist scan */
zlc_active = 0;
goto zonelist_scan;
}
return page;
}
/*
* This is the 'heart' of the zoned buddy allocator.
*/
struct page *
__alloc_pages_internal(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, nodemask_t *nodemask)
{
const gfp_t wait = gfp_mask & __GFP_WAIT;
enum zone_type high_zoneidx = gfp_zone(gfp_mask);
struct zoneref *z;
struct zone *zone;
struct page *page;
struct reclaim_state reclaim_state;
struct task_struct *p = current;
int do_retry;
int alloc_flags;
unsigned long did_some_progress;
unsigned long pages_reclaimed = 0;
lockdep_trace_alloc(gfp_mask);
might_sleep_if(wait);
if (should_fail_alloc_page(gfp_mask, order))
return NULL;
restart:
z = zonelist->_zonerefs; /* the list of zones suitable for gfp_mask */
if (unlikely(!z->zone)) {
/*
* Happens if we have an empty zonelist as a result of
* GFP_THISNODE being used on a memoryless node
*/
return NULL;
}
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET);
if (page)
goto got_pg;
/*
* GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and
* __GFP_NOWARN set) should not cause reclaim since the subsystem
* (f.e. slab) using GFP_THISNODE may choose to trigger reclaim
* using a larger set of nodes after it has established that the
* allowed per node queues are empty and that nodes are
* over allocated.
*/
if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
goto nopage;
for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
wakeup_kswapd(zone, order);
/*
* OK, we're below the kswapd watermark and have kicked background
* reclaim. Now things get more complex, so set up alloc_flags according
* to how we want to proceed.
*
* The caller may dip into page reserves a bit more if the caller
* cannot run direct reclaim, or if the caller has realtime scheduling
* policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will
* set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
*/
alloc_flags = ALLOC_WMARK_MIN;
if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait)
alloc_flags |= ALLOC_HARDER;
if (gfp_mask & __GFP_HIGH)
alloc_flags |= ALLOC_HIGH;
if (wait)
alloc_flags |= ALLOC_CPUSET;
/*
* Go through the zonelist again. Let __GFP_HIGH and allocations
* coming from realtime tasks 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.
* See also cpuset_zone_allowed() comment in kernel/cpuset.c.
*/
page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
high_zoneidx, alloc_flags);
if (page)
goto got_pg;
/* This allocation should allow future memory freeing. */
rebalance:
if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
&& !in_interrupt()) {
if (!(gfp_mask & __GFP_NOMEMALLOC)) {
nofail_alloc:
/* go through the zonelist yet again, ignoring mins */
page = get_page_from_freelist(gfp_mask, nodemask, order,
zonelist, high_zoneidx, ALLOC_NO_WATERMARKS);
if (page)
goto got_pg;
if (gfp_mask & __GFP_NOFAIL) {
congestion_wait(WRITE, HZ/50);
goto nofail_alloc;
}
}
goto nopage;
}
/* Atomic allocations - we can't balance anything */
if (!wait)
goto nopage;
cond_resched();
/* We now go into synchronous reclaim */
cpuset_memory_pressure_bump();
/*
* The task's cpuset might have expanded its set of allowable nodes
*/
cpuset_update_task_memory_state();
p->flags |= PF_MEMALLOC;
lockdep_set_current_reclaim_state(gfp_mask);
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
did_some_progress = try_to_free_pages(zonelist, order,
gfp_mask, nodemask);
p->reclaim_state = NULL;
lockdep_clear_current_reclaim_state();
p->flags &= ~PF_MEMALLOC;
cond_resched();
if (order != 0)
drain_all_pages();
if (likely(did_some_progress)) {
page = get_page_from_freelist(gfp_mask, nodemask, order,
zonelist, high_zoneidx, alloc_flags);
if (page)
goto got_pg;
} else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
if (!try_set_zone_oom(zonelist, gfp_mask)) {
schedule_timeout_uninterruptible(1);
goto restart;
}
/*
* 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.
*/
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask,
order, zonelist, high_zoneidx,
ALLOC_WMARK_HIGH|ALLOC_CPUSET);
if (page) {
clear_zonelist_oom(zonelist, gfp_mask);
goto got_pg;
}
/* The OOM killer will not help higher order allocs so fail */
if (order > PAGE_ALLOC_COSTLY_ORDER) {
clear_zonelist_oom(zonelist, gfp_mask);
goto nopage;
}
out_of_memory(zonelist, gfp_mask, order);
clear_zonelist_oom(zonelist, 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, order <= PAGE_ALLOC_COSTLY_ORDER
* means __GFP_NOFAIL, but that may not be true in other
* implementations.
*
* For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is
* specified, then we retry until we no longer reclaim any pages
* (above), or we've reclaimed an order of pages at least as
* large as the allocation's order. In both cases, if the
* allocation still fails, we stop retrying.
*/
pages_reclaimed += did_some_progress;
do_retry = 0;
if (!(gfp_mask & __GFP_NORETRY)) {
if (order <= PAGE_ALLOC_COSTLY_ORDER) {
do_retry = 1;
} else {
if (gfp_mask & __GFP_REPEAT &&
pages_reclaimed < (1 << order))
do_retry = 1;
}
if (gfp_mask & __GFP_NOFAIL)
do_retry = 1;
}
if (do_retry) {
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();
show_mem();
}
got_pg:
return page;
}
EXPORT_SYMBOL(__alloc_pages_internal);
/*
* Common helper functions.
*/
unsigned long __get_free_pages(gfp_t 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);
unsigned long get_zeroed_page(gfp_t gfp_mask)
{
struct page * page;
/*
* get_zeroed_page() returns a 32-bit address, which cannot represent
* a highmem page
*/
VM_BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0);
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);
}
void __free_pages(struct page *page, unsigned int order)
{
if (put_page_testzero(page)) {
if (order == 0)
free_hot_page(page);
else
__free_pages_ok(page, order);
}
}
EXPORT_SYMBOL(__free_pages);
void free_pages(unsigned long addr, unsigned int order)
{
if (addr != 0) {
VM_BUG_ON(!virt_addr_valid((void *)addr));
__free_pages(virt_to_page((void *)addr), order);
}
}
EXPORT_SYMBOL(free_pages);
/**
* alloc_pages_exact - allocate an exact number physically-contiguous pages.
* @size: the number of bytes to allocate
* @gfp_mask: GFP flags for the allocation
*
* This function is similar to alloc_pages(), except that it allocates the
* minimum number of pages to satisfy the request. alloc_pages() can only
* allocate memory in power-of-two pages.
*
* This function is also limited by MAX_ORDER.
*
* Memory allocated by this function must be released by free_pages_exact().
*/
void *alloc_pages_exact(size_t size, gfp_t gfp_mask)
{
unsigned int order = get_order(size);
unsigned long addr;
addr = __get_free_pages(gfp_mask, order);
if (addr) {
unsigned long alloc_end = addr + (PAGE_SIZE << order);
unsigned long used = addr + PAGE_ALIGN(size);
split_page(virt_to_page(addr), order);
while (used < alloc_end) {
free_page(used);
used += PAGE_SIZE;
}
}
return (void *)addr;
}
EXPORT_SYMBOL(alloc_pages_exact);
/**
* free_pages_exact - release memory allocated via alloc_pages_exact()
* @virt: the value returned by alloc_pages_exact.
* @size: size of allocation, same value as passed to alloc_pages_exact().
*
* Release the memory allocated by a previous call to alloc_pages_exact.
*/
void free_pages_exact(void *virt, size_t size)
{
unsigned long addr = (unsigned long)virt;
unsigned long end = addr + PAGE_ALIGN(size);
while (addr < end) {
free_page(addr);
addr += PAGE_SIZE;
}
}
EXPORT_SYMBOL(free_pages_exact);
static unsigned int nr_free_zone_pages(int offset)
{
struct zoneref *z;
struct zone *zone;
/* Just pick one node, since fallback list is circular */
unsigned int sum = 0;
struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL);
for_each_zone_zonelist(zone, z, zonelist, offset) {
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_zone(GFP_USER));
}
EXPORT_SYMBOL_GPL(nr_free_buffer_pages);
/*
* Amount of free RAM allocatable within all zones
*/
unsigned int nr_free_pagecache_pages(void)
{
return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE));
}
static inline void show_node(struct zone *zone)
{
if (NUMA_BUILD)
printk("Node %d ", zone_to_nid(zone));
}
void si_meminfo(struct sysinfo *val)
{
val->totalram = totalram_pages;
val->sharedram = 0;
val->freeram = global_page_state(NR_FREE_PAGES);
val->bufferram = nr_blockdev_pages();
val->totalhigh = totalhigh_pages;
val->freehigh = nr_free_highpages();
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 = node_page_state(nid, NR_FREE_PAGES);
#ifdef CONFIG_HIGHMEM
val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].present_pages;
val->freehigh = zone_page_state(&pgdat->node_zones[ZONE_HIGHMEM],
NR_FREE_PAGES);
#else
val->totalhigh = 0;
val->freehigh = 0;
#endif
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)
{
int cpu;
struct zone *zone;
for_each_populated_zone(zone) {
show_node(zone);
printk("%s per-cpu:\n", zone->name);
for_each_online_cpu(cpu) {
struct per_cpu_pageset *pageset;
pageset = zone_pcp(zone, cpu);
printk("CPU %4d: hi:%5d, btch:%4d usd:%4d\n",
cpu, pageset->pcp.high,
pageset->pcp.batch, pageset->pcp.count);
}
}
printk("Active_anon:%lu active_file:%lu inactive_anon:%lu\n"
" inactive_file:%lu"
//TODO: check/adjust line lengths
#ifdef CONFIG_UNEVICTABLE_LRU
" unevictable:%lu"
#endif
" dirty:%lu writeback:%lu unstable:%lu\n"
" free:%lu slab:%lu mapped:%lu pagetables:%lu bounce:%lu\n",
global_page_state(NR_ACTIVE_ANON),
global_page_state(NR_ACTIVE_FILE),
global_page_state(NR_INACTIVE_ANON),
global_page_state(NR_INACTIVE_FILE),
#ifdef CONFIG_UNEVICTABLE_LRU
global_page_state(NR_UNEVICTABLE),
#endif
global_page_state(NR_FILE_DIRTY),
global_page_state(NR_WRITEBACK),
global_page_state(NR_UNSTABLE_NFS),
global_page_state(NR_FREE_PAGES),
global_page_state(NR_SLAB_RECLAIMABLE) +
global_page_state(NR_SLAB_UNRECLAIMABLE),
global_page_state(NR_FILE_MAPPED),
global_page_state(NR_PAGETABLE),
global_page_state(NR_BOUNCE));
for_each_populated_zone(zone) {
int i;
show_node(zone);
printk("%s"
" free:%lukB"
" min:%lukB"
" low:%lukB"
" high:%lukB"
" active_anon:%lukB"
" inactive_anon:%lukB"
" active_file:%lukB"
" inactive_file:%lukB"
#ifdef CONFIG_UNEVICTABLE_LRU
" unevictable:%lukB"
#endif
" present:%lukB"
" pages_scanned:%lu"
" all_unreclaimable? %s"
"\n",
zone->name,
K(zone_page_state(zone, NR_FREE_PAGES)),
K(zone->pages_min),
K(zone->pages_low),
K(zone->pages_high),
K(zone_page_state(zone, NR_ACTIVE_ANON)),
K(zone_page_state(zone, NR_INACTIVE_ANON)),
K(zone_page_state(zone, NR_ACTIVE_FILE)),
K(zone_page_state(zone, NR_INACTIVE_FILE)),
#ifdef CONFIG_UNEVICTABLE_LRU
K(zone_page_state(zone, NR_UNEVICTABLE)),
#endif
K(zone->present_pages),
zone->pages_scanned,
(zone_is_all_unreclaimable(zone) ? "yes" : "no")
);
printk("lowmem_reserve[]:");
for (i = 0; i < MAX_NR_ZONES; i++)
printk(" %lu", zone->lowmem_reserve[i]);
printk("\n");
}
for_each_populated_zone(zone) {
unsigned long nr[MAX_ORDER], flags, order, total = 0;
show_node(zone);
printk("%s: ", zone->name);
spin_lock_irqsave(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
nr[order] = zone->free_area[order].nr_free;
total += nr[order] << order;
}
spin_unlock_irqrestore(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++)
printk("%lu*%lukB ", nr[order], K(1UL) << order);
printk("= %lukB\n", K(total));
}
printk("%ld total pagecache pages\n", global_page_state(NR_FILE_PAGES));
show_swap_cache_info();
}
static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
{
zoneref->zone = zone;
zoneref->zone_idx = zone_idx(zone);
}
/*
* Builds allocation fallback zone lists.
*
* Add all populated zones of a node to the zonelist.
*/
static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
int nr_zones, enum zone_type zone_type)
{
struct zone *zone;
BUG_ON(zone_type >= MAX_NR_ZONES);
zone_type++;
do {
zone_type--;
zone = pgdat->node_zones + zone_type;
if (populated_zone(zone)) {
zoneref_set_zone(zone,
&zonelist->_zonerefs[nr_zones++]);
check_highest_zone(zone_type);
}
} while (zone_type);
return nr_zones;
}
/*
* zonelist_order:
* 0 = automatic detection of better ordering.
* 1 = order by ([node] distance, -zonetype)
* 2 = order by (-zonetype, [node] distance)
*
* If not NUMA, ZONELIST_ORDER_ZONE and ZONELIST_ORDER_NODE will create
* the same zonelist. So only NUMA can configure this param.
*/
#define ZONELIST_ORDER_DEFAULT 0
#define ZONELIST_ORDER_NODE 1
#define ZONELIST_ORDER_ZONE 2
/* zonelist order in the kernel.
* set_zonelist_order() will set this to NODE or ZONE.
*/
static int current_zonelist_order = ZONELIST_ORDER_DEFAULT;
static char zonelist_order_name[3][8] = {"Default", "Node", "Zone"};
#ifdef CONFIG_NUMA
/* The value user specified ....changed by config */
static int user_zonelist_order = ZONELIST_ORDER_DEFAULT;
/* string for sysctl */
#define NUMA_ZONELIST_ORDER_LEN 16
char numa_zonelist_order[16] = "default";
/*
* interface for configure zonelist ordering.
* command line option "numa_zonelist_order"
* = "[dD]efault - default, automatic configuration.
* = "[nN]ode - order by node locality, then by zone within node
* = "[zZ]one - order by zone, then by locality within zone
*/
static int __parse_numa_zonelist_order(char *s)
{
if (*s == 'd' || *s == 'D') {
user_zonelist_order = ZONELIST_ORDER_DEFAULT;
} else if (*s == 'n' || *s == 'N') {
user_zonelist_order = ZONELIST_ORDER_NODE;
} else if (*s == 'z' || *s == 'Z') {
user_zonelist_order = ZONELIST_ORDER_ZONE;
} else {
printk(KERN_WARNING
"Ignoring invalid numa_zonelist_order value: "
"%s\n", s);
return -EINVAL;
}
return 0;
}
static __init int setup_numa_zonelist_order(char *s)
{
if (s)
return __parse_numa_zonelist_order(s);
return 0;
}
early_param("numa_zonelist_order", setup_numa_zonelist_order);
/*
* sysctl handler for numa_zonelist_order
*/
int numa_zonelist_order_handler(ctl_table *table, int write,
struct file *file, void __user *buffer, size_t *length,
loff_t *ppos)
{
char saved_string[NUMA_ZONELIST_ORDER_LEN];
int ret;
if (write)
strncpy(saved_string, (char*)table->data,
NUMA_ZONELIST_ORDER_LEN);
ret = proc_dostring(table, write, file, buffer, length, ppos);
if (ret)
return ret;
if (write) {
int oldval = user_zonelist_order;
if (__parse_numa_zonelist_order((char*)table->data)) {
/*
* bogus value. restore saved string
*/
strncpy((char*)table->data, saved_string,
NUMA_ZONELIST_ORDER_LEN);
user_zonelist_order = oldval;
} else if (oldval != user_zonelist_order)
build_all_zonelists();
}
return 0;
}
#define MAX_NODE_LOAD (num_online_nodes())
static int node_load[MAX_NUMNODES];
/**
* find_next_best_node - find the next node that should appear in a given node's fallback list
* @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 find_next_best_node(int node, nodemask_t *used_node_mask)
{
int n, val;
int min_val = INT_MAX;
int best_node = -1;
const struct cpumask *tmp = cpumask_of_node(0);
/* Use the local node if we haven't already */
if (!node_isset(node, *used_node_mask)) {
node_set(node, *used_node_mask);
return node;
}
for_each_node_state(n, N_HIGH_MEMORY) {
/* Don't want a node to appear more than once */
if (node_isset(n, *used_node_mask))
continue;
/* Use the distance array to find the distance */
val = node_distance(node, n);
/* Penalize nodes under us ("prefer the next node") */
val += (n < node);
/* Give preference to headless and unused nodes */
tmp = cpumask_of_node(n);
if (!cpumask_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;
}
/*
* Build zonelists ordered by node and zones within node.
* This results in maximum locality--normal zone overflows into local
* DMA zone, if any--but risks exhausting DMA zone.
*/
static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
{
int j;
struct zonelist *zonelist;
zonelist = &pgdat->node_zonelists[0];
for (j = 0; zonelist->_zonerefs[j].zone != NULL; j++)
;
j = build_zonelists_node(NODE_DATA(node), zonelist, j,
MAX_NR_ZONES - 1);
zonelist->_zonerefs[j].zone = NULL;
zonelist->_zonerefs[j].zone_idx = 0;
}
/*
* Build gfp_thisnode zonelists
*/
static void build_thisnode_zonelists(pg_data_t *pgdat)
{
int j;
struct zonelist *zonelist;
zonelist = &pgdat->node_zonelists[1];
j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1);
zonelist->_zonerefs[j].zone = NULL;
zonelist->_zonerefs[j].zone_idx = 0;
}
/*
* Build zonelists ordered by zone and nodes within zones.
* This results in conserving DMA zone[s] until all Normal memory is
* exhausted, but results in overflowing to remote node while memory
* may still exist in local DMA zone.
*/
static int node_order[MAX_NUMNODES];
static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes)
{
int pos, j, node;
int zone_type; /* needs to be signed */
struct zone *z;
struct zonelist *zonelist;
zonelist = &pgdat->node_zonelists[0];
pos = 0;
for (zone_type = MAX_NR_ZONES - 1; zone_type >= 0; zone_type--) {
for (j = 0; j < nr_nodes; j++) {
node = node_order[j];
z = &NODE_DATA(node)->node_zones[zone_type];
if (populated_zone(z)) {
zoneref_set_zone(z,
&zonelist->_zonerefs[pos++]);
check_highest_zone(zone_type);
}
}
}
zonelist->_zonerefs[pos].zone = NULL;
zonelist->_zonerefs[pos].zone_idx = 0;
}
static int default_zonelist_order(void)
{
int nid, zone_type;
unsigned long low_kmem_size,total_size;
struct zone *z;
int average_size;
/*
* ZONE_DMA and ZONE_DMA32 can be very small area in the sytem.
* If they are really small and used heavily, the system can fall
* into OOM very easily.
* This function detect ZONE_DMA/DMA32 size and confgigures zone order.
*/
/* Is there ZONE_NORMAL ? (ex. ppc has only DMA zone..) */
low_kmem_size = 0;
total_size = 0;
for_each_online_node(nid) {
for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
z = &NODE_DATA(nid)->node_zones[zone_type];
if (populated_zone(z)) {
if (zone_type < ZONE_NORMAL)
low_kmem_size += z->present_pages;
total_size += z->present_pages;
}
}
}
if (!low_kmem_size || /* there are no DMA area. */
low_kmem_size > total_size/2) /* DMA/DMA32 is big. */
return ZONELIST_ORDER_NODE;
/*
* look into each node's config.
* If there is a node whose DMA/DMA32 memory is very big area on
* local memory, NODE_ORDER may be suitable.
*/
average_size = total_size /
(nodes_weight(node_states[N_HIGH_MEMORY]) + 1);
for_each_online_node(nid) {
low_kmem_size = 0;
total_size = 0;
for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
z = &NODE_DATA(nid)->node_zones[zone_type];
if (populated_zone(z)) {
if (zone_type < ZONE_NORMAL)
low_kmem_size += z->present_pages;
total_size += z->present_pages;
}
}
if (low_kmem_size &&
total_size > average_size && /* ignore small node */
low_kmem_size > total_size * 70/100)
return ZONELIST_ORDER_NODE;
}
return ZONELIST_ORDER_ZONE;
}
static void set_zonelist_order(void)
{
if (user_zonelist_order == ZONELIST_ORDER_DEFAULT)
current_zonelist_order = default_zonelist_order();
else
current_zonelist_order = user_zonelist_order;
}
static void build_zonelists(pg_data_t *pgdat)
{
int j, node, load;
enum zone_type i;
nodemask_t used_mask;
int local_node, prev_node;
struct zonelist *zonelist;
int order = current_zonelist_order;
/* initialize zonelists */
for (i = 0; i < MAX_ZONELISTS; i++) {
zonelist = pgdat->node_zonelists + i;
zonelist->_zonerefs[0].zone = NULL;
zonelist->_zonerefs[0].zone_idx = 0;
}
/* NUMA-aware ordering of nodes */
local_node = pgdat->node_id;
load = num_online_nodes();
prev_node = local_node;
nodes_clear(used_mask);
memset(node_load, 0, sizeof(node_load));
memset(node_order, 0, sizeof(node_order));
j = 0;
while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
int distance = node_distance(local_node, node);
/*
* If another node is sufficiently far away then it is better
* to reclaim pages in a zone before going off node.
*/
if (distance > RECLAIM_DISTANCE)
zone_reclaim_mode = 1;
/*
* 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 (distance != node_distance(local_node, prev_node))
node_load[node] = load;
prev_node = node;
load--;
if (order == ZONELIST_ORDER_NODE)
build_zonelists_in_node_order(pgdat, node);
else
node_order[j++] = node; /* remember order */
}
if (order == ZONELIST_ORDER_ZONE) {
/* calculate node order -- i.e., DMA last! */
build_zonelists_in_zone_order(pgdat, j);
}
build_thisnode_zonelists(pgdat);
}
/* Construct the zonelist performance cache - see further mmzone.h */
static void build_zonelist_cache(pg_data_t *pgdat)
{
struct zonelist *zonelist;
struct zonelist_cache *zlc;
struct zoneref *z;
zonelist = &pgdat->node_zonelists[0];
zonelist->zlcache_ptr = zlc = &zonelist->zlcache;
bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
for (z = zonelist->_zonerefs; z->zone; z++)
zlc->z_to_n[z - zonelist->_zonerefs] = zonelist_node_idx(z);
}
#else /* CONFIG_NUMA */
static void set_zonelist_order(void)
{
current_zonelist_order = ZONELIST_ORDER_ZONE;
}
static void build_zonelists(pg_data_t *pgdat)
{
int node, local_node;
enum zone_type j;
struct zonelist *zonelist;
local_node = pgdat->node_id;
zonelist = &pgdat->node_zonelists[0];
j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1);
/*
* 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,
MAX_NR_ZONES - 1);
}
for (node = 0; node < local_node; node++) {
if (!node_online(node))
continue;
j = build_zonelists_node(NODE_DATA(node), zonelist, j,
MAX_NR_ZONES - 1);
}
zonelist->_zonerefs[j].zone = NULL;
zonelist->_zonerefs[j].zone_idx = 0;
}
/* non-NUMA variant of zonelist performance cache - just NULL zlcache_ptr */
static void build_zonelist_cache(pg_data_t *pgdat)
{
pgdat->node_zonelists[0].zlcache_ptr = NULL;
}
#endif /* CONFIG_NUMA */
/* return values int ....just for stop_machine() */
static int __build_all_zonelists(void *dummy)
{
int nid;
for_each_online_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
build_zonelists(pgdat);
build_zonelist_cache(pgdat);
}
return 0;
}
void build_all_zonelists(void)
{
set_zonelist_order();
if (system_state == SYSTEM_BOOTING) {
__build_all_zonelists(NULL);
mminit_verify_zonelist();
cpuset_init_current_mems_allowed();
} else {
/* we have to stop all cpus to guarantee there is no user
of zonelist */
stop_machine(__build_all_zonelists, NULL, NULL);
/* cpuset refresh routine should be here */
}
vm_total_pages = nr_free_pagecache_pages();
/*
* Disable grouping by mobility if the number of pages in the
* system is too low to allow the mechanism to work. It would be
* more accurate, but expensive to check per-zone. This check is
* made on memory-hotadd so a system can start with mobility
* disabled and enable it later
*/
if (vm_total_pages < (pageblock_nr_pages * MIGRATE_TYPES))
page_group_by_mobility_disabled = 1;
else
page_group_by_mobility_disabled = 0;
printk("Built %i zonelists in %s order, mobility grouping %s. "
"Total pages: %ld\n",
num_online_nodes(),
zonelist_order_name[current_zonelist_order],
page_group_by_mobility_disabled ? "off" : "on",
vm_total_pages);
#ifdef CONFIG_NUMA
printk("Policy zone: %s\n", zone_names[policy_zone]);
#endif
}
/*
* 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
#ifndef CONFIG_MEMORY_HOTPLUG
static inline unsigned long wait_table_hash_nr_entries(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);
}
#else
/*
* A zone's size might be changed by hot-add, so it is not possible to determine
* a suitable size for its wait_table. So we use the maximum size now.
*
* The max wait table size = 4096 x sizeof(wait_queue_head_t). ie:
*
* i386 (preemption config) : 4096 x 16 = 64Kbyte.
* ia64, x86-64 (no preemption): 4096 x 20 = 80Kbyte.
* ia64, x86-64 (preemption) : 4096 x 24 = 96Kbyte.
*
* The maximum entries are prepared when a zone's memory is (512K + 256) pages
* or more by the traditional way. (See above). It equals:
*
* i386, x86-64, powerpc(4K page size) : = ( 2G + 1M)byte.
* ia64(16K page size) : = ( 8G + 4M)byte.
* powerpc (64K page size) : = (32G +16M)byte.
*/
static inline unsigned long wait_table_hash_nr_entries(unsigned long pages)
{
return 4096UL;
}
#endif
/*
* 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))
/*
* Mark a number of pageblocks as MIGRATE_RESERVE. The number
* of blocks reserved is based on zone->pages_min. The memory within the
* reserve will tend to store contiguous free pages. Setting min_free_kbytes
* higher will lead to a bigger reserve which will get freed as contiguous
* blocks as reclaim kicks in
*/
static void setup_zone_migrate_reserve(struct zone *zone)
{
unsigned long start_pfn, pfn, end_pfn;
struct page *page;
unsigned long reserve, block_migratetype;
/* Get the start pfn, end pfn and the number of blocks to reserve */
start_pfn = zone->zone_start_pfn;
end_pfn = start_pfn + zone->spanned_pages;
reserve = roundup(zone->pages_min, pageblock_nr_pages) >>
pageblock_order;
for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
if (!pfn_valid(pfn))
continue;
page = pfn_to_page(pfn);
/* Watch out for overlapping nodes */
if (page_to_nid(page) != zone_to_nid(zone))
continue;
/* Blocks with reserved pages will never free, skip them. */
if (PageReserved(page))
continue;
block_migratetype = get_pageblock_migratetype(page);
/* If this block is reserved, account for it */
if (reserve > 0 && block_migratetype == MIGRATE_RESERVE) {
reserve--;
continue;
}
/* Suitable for reserving if this block is movable */
if (reserve > 0 && block_migratetype == MIGRATE_MOVABLE) {
set_pageblock_migratetype(page, MIGRATE_RESERVE);
move_freepages_block(zone, page, MIGRATE_RESERVE);
reserve--;
continue;
}
/*
* If the reserve is met and this is a previous reserved block,
* take it back
*/
if (block_migratetype == MIGRATE_RESERVE) {
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
move_freepages_block(zone, page, MIGRATE_MOVABLE);
}
}
}
/*
* 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 __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
unsigned long start_pfn, enum memmap_context context)
{
struct page *page;
unsigned long end_pfn = start_pfn + size;
unsigned long pfn;
struct zone *z;
if (highest_memmap_pfn < end_pfn - 1)
highest_memmap_pfn = end_pfn - 1;
z = &NODE_DATA(nid)->node_zones[zone];
for (pfn = start_pfn; pfn < end_pfn; pfn++) {
/*
* There can be holes in boot-time mem_map[]s
* handed to this function. They do not
* exist on hotplugged memory.
*/
if (context == MEMMAP_EARLY) {
if (!early_pfn_valid(pfn))
continue;
if (!early_pfn_in_nid(pfn, nid))
continue;
}
page = pfn_to_page(pfn);
set_page_links(page, zone, nid, pfn);
mminit_verify_page_links(page, zone, nid, pfn);
init_page_count(page);
reset_page_mapcount(page);
SetPageReserved(page);
/*
* Mark the block movable so that blocks are reserved for
* movable at startup. This will force kernel allocations
* to reserve their blocks rather than leaking throughout
* the address space during boot when many long-lived
* kernel allocations are made. Later some blocks near
* the start are marked MIGRATE_RESERVE by
* setup_zone_migrate_reserve()
*
* bitmap is created for zone's valid pfn range. but memmap
* can be created for invalid pages (for alignment)
* check here not to call set_pageblock_migratetype() against
* pfn out of zone.
*/
if ((z->zone_start_pfn <= pfn)
&& (pfn < z->zone_start_pfn + z->spanned_pages)
&& !(pfn & (pageblock_nr_pages - 1)))
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
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(pfn << PAGE_SHIFT));
#endif
}
}
static void __meminit zone_init_free_lists(struct zone *zone)
{
int order, t;
for_each_migratetype_order(order, t) {
INIT_LIST_HEAD(&zone->free_area[order].free_list[t]);
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), MEMMAP_EARLY)
#endif
static int zone_batchsize(struct zone *zone)
{
#ifdef CONFIG_MMU
int batch;
/*
* The per-cpu-pages pools are set to around 1000th of the
* size of the zone. But no more than 1/2 of a meg.
*
* OK, so we don't know how big the cache is. So guess.
*/
batch = zone->present_pages / 1024;
if (batch * PAGE_SIZE > 512 * 1024)
batch = (512 * 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 = rounddown_pow_of_two(batch + batch/2) - 1;
return batch;
#else
/* The deferral and batching of frees should be suppressed under NOMMU
* conditions.
*
* The problem is that NOMMU needs to be able to allocate large chunks
* of contiguous memory as there's no hardware page translation to
* assemble apparent contiguous memory from discontiguous pages.
*
* Queueing large contiguous runs of pages for batching, however,
* causes the pages to actually be freed in smaller chunks. As there
* can be a significant delay between the individual batches being
* recycled, this leads to the once large chunks of space being
* fragmented and becoming unavailable for high-order allocations.
*/
return 0;
#endif
}
static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
{
struct per_cpu_pages *pcp;
memset(p, 0, sizeof(*p));
pcp = &p->pcp;
pcp->count = 0;
pcp->high = 6 * batch;
pcp->batch = max(1UL, 1 * batch);
INIT_LIST_HEAD(&pcp->list);
}
/*
* setup_pagelist_highmark() sets the high water mark for hot per_cpu_pagelist
* to the value high for the pageset p.
*/
static void setup_pagelist_highmark(struct per_cpu_pageset *p,
unsigned long high)
{
struct per_cpu_pages *pcp;
pcp = &p->pcp;
pcp->high = high;
pcp->batch = max(1UL, high/4);
if ((high/4) > (PAGE_SHIFT * 8))
pcp->batch = PAGE_SHIFT * 8;
}
#ifdef CONFIG_NUMA
/*
* Boot pageset table. One per cpu which is going to be used for all
* zones and all nodes. The parameters will be set in such a way
* that an item put on a list will immediately be handed over to
* the buddy list. This is safe since pageset manipulation is done
* with interrupts disabled.
*
* Some NUMA counter updates may also be caught by the boot pagesets.
*
* The boot_pagesets must be kept even after bootup is complete for
* unused processors and/or zones. They do play a role for bootstrapping
* hotplugged processors.
*
* zoneinfo_show() and maybe other functions do
* not check if the processor is online before following the pageset pointer.
* Other parts of the kernel may not check if the zone is available.
*/
static struct per_cpu_pageset boot_pageset[NR_CPUS];
/*
* Dynamically allocate memory for the
* per cpu pageset array in struct zone.
*/
static int __cpuinit process_zones(int cpu)
{
struct zone *zone, *dzone;
int node = cpu_to_node(cpu);
node_set_state(node, N_CPU); /* this node has a cpu */
for_each_populated_zone(zone) {
zone_pcp(zone, cpu) = kmalloc_node(sizeof(struct per_cpu_pageset),
GFP_KERNEL, node);
if (!zone_pcp(zone, cpu))
goto bad;
setup_pageset(zone_pcp(zone, cpu), zone_batchsize(zone));
if (percpu_pagelist_fraction)
setup_pagelist_highmark(zone_pcp(zone, cpu),
(zone->present_pages / percpu_pagelist_fraction));
}
return 0;
bad:
for_each_zone(dzone) {
if (!populated_zone(dzone))
continue;
if (dzone == zone)
break;
kfree(zone_pcp(dzone, cpu));
zone_pcp(dzone, cpu) = &boot_pageset[cpu];
}
return -ENOMEM;
}
static inline void free_zone_pagesets(int cpu)
{
struct zone *zone;
for_each_zone(zone) {
struct per_cpu_pageset *pset = zone_pcp(zone, cpu);
/* Free per_cpu_pageset if it is slab allocated */
if (pset != &boot_pageset[cpu])
kfree(pset);
zone_pcp(zone, cpu) = &boot_pageset[cpu];
}
}
static int __cpuinit 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:
case CPU_UP_PREPARE_FROZEN:
if (process_zones(cpu))
ret = NOTIFY_BAD;
break;
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
case CPU_DEAD:
case CPU_DEAD_FROZEN:
free_zone_pagesets(cpu);
break;
default:
break;
}
return ret;
}
static struct notifier_block __cpuinitdata pageset_notifier =
{ &pageset_cpuup_callback, NULL, 0 };
void __init setup_per_cpu_pageset(void)
{
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
static noinline __init_refok
int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
{