#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/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/pfn.h>
#include <linux/backing-dev.h>
#include <linux/fault-inject.h>
+#include <linux/page-isolation.h>
+#include <linux/memcontrol.h>
+#include <linux/debugobjects.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#include "internal.h"
/*
- * MCD - HACK: Find somewhere to initialize this EARLY, or make this
- * initializer cleaner
+ * Array of node states.
*/
-nodemask_t node_online_map __read_mostly = { { [0] = 1UL } };
-EXPORT_SYMBOL(node_online_map);
-nodemask_t node_possible_map __read_mostly = NODE_MASK_ALL;
-EXPORT_SYMBOL(node_possible_map);
+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;
long nr_swap_pages;
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);
/*
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
/*
- * MAX_ACTIVE_REGIONS determines the maxmimum number of distinct
+ * 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
static unsigned long __meminitdata node_boundary_end_pfn[MAX_NUMNODES];
#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */
unsigned long __initdata required_kernelcore;
- unsigned long __initdata required_movablecore;
+ static unsigned long __initdata required_movablecore;
unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
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)
{
static void bad_page(struct page *page)
{
- printk(KERN_EMERG "Bad page state in process '%s'\n"
- KERN_EMERG "page:%p flags:0x%0*lx mapping:%p mapcount:%d count:%d\n"
- KERN_EMERG "Trying to fix it up, but a reboot is needed\n"
- KERN_EMERG "Backtrace:\n",
+ void *pc = page_get_page_cgroup(page);
+
+ printk(KERN_EMERG "Bad page state in process '%s'\n" KERN_EMERG
+ "page:%p flags:0x%0*lx mapping:%p mapcount:%d count:%d\n",
current->comm, page, (int)(2*sizeof(unsigned long)),
(unsigned long)page->flags, page->mapping,
page_mapcount(page), page_count(page));
+ if (pc) {
+ printk(KERN_EMERG "cgroup:%p\n", pc);
+ page_reset_bad_cgroup(page);
+ }
+ printk(KERN_EMERG "Trying to fix it up, but a reboot is needed\n"
+ KERN_EMERG "Backtrace:\n");
dump_stack();
- page->flags &= ~(1 << PG_lru |
- 1 << PG_private |
- 1 << PG_locked |
- 1 << PG_active |
- 1 << PG_dirty |
- 1 << PG_reclaim |
- 1 << PG_slab |
- 1 << PG_swapcache |
- 1 << PG_writeback |
- 1 << PG_buddy );
+ page->flags &= ~PAGE_FLAGS_CLEAR_WHEN_BAD;
set_page_count(page, 0);
reset_page_mapcount(page);
page->mapping = NULL;
{
int i;
- VM_BUG_ON((gfp_flags & (__GFP_WAIT | __GFP_HIGHMEM)) == __GFP_HIGHMEM);
/*
* clear_highpage() will use KM_USER0, so it's a bug to use __GFP_ZERO
* and __GFP_HIGHMEM from hard or soft interrupt context.
clear_highpage(page + i);
}
-/*
- * 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(page);
-}
-
static inline void set_page_order(struct page *page, int order)
{
set_page_private(page, order);
{
unsigned long page_idx;
int order_size = 1 << order;
+ int migratetype = get_pageblock_migratetype(page);
if (unlikely(PageCompound(page)))
destroy_compound_page(page, order);
__mod_zone_page_state(zone, NR_FREE_PAGES, order_size);
while (order < MAX_ORDER-1) {
unsigned long combined_idx;
- struct free_area *area;
struct page *buddy;
buddy = __page_find_buddy(page, page_idx, order);
break; /* Move the buddy up one level. */
list_del(&buddy->lru);
- area = zone->free_area + order;
- area->nr_free--;
+ zone->free_area[order].nr_free--;
rmv_page_order(buddy);
combined_idx = __find_combined_index(page_idx, order);
page = page + (combined_idx - page_idx);
order++;
}
set_page_order(page, order);
- list_add(&page->lru, &zone->free_area[order].free_list);
+ list_add(&page->lru,
+ &zone->free_area[order].free_list[migratetype]);
zone->free_area[order].nr_free++;
}
{
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
+ (page_get_page_cgroup(page) != NULL) |
(page_count(page) != 0) |
- (page->flags & (
- 1 << PG_lru |
- 1 << PG_private |
- 1 << PG_locked |
- 1 << PG_active |
- 1 << PG_slab |
- 1 << PG_swapcache |
- 1 << PG_writeback |
- 1 << PG_reserved |
- 1 << PG_buddy ))))
+ (page->flags & PAGE_FLAGS_CHECK_AT_FREE)))
bad_page(page);
if (PageDirty(page))
__ClearPageDirty(page);
struct list_head *list, int order)
{
spin_lock(&zone->lock);
- zone->all_unreclaimable = 0;
+ zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
zone->pages_scanned = 0;
while (count--) {
struct page *page;
static void free_one_page(struct zone *zone, struct page *page, int order)
{
spin_lock(&zone->lock);
- zone->all_unreclaimable = 0;
+ zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
zone->pages_scanned = 0;
__free_one_page(page, zone, order);
spin_unlock(&zone->lock);
if (reserved)
return;
- if (!PageHighMem(page))
+ 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);
/*
* permit the bootmem allocator to evade page validation on high-order frees
*/
-void fastcall __init __free_pages_bootmem(struct page *page, unsigned int order)
+void __free_pages_bootmem(struct page *page, unsigned int order)
{
if (order == 0) {
__ClearPageReserved(page);
* -- wli
*/
static inline void expand(struct zone *zone, struct page *page,
- int low, int high, struct free_area *area)
+ int low, int high, struct free_area *area,
+ int migratetype)
{
unsigned long size = 1 << high;
high--;
size >>= 1;
VM_BUG_ON(bad_range(zone, &page[size]));
- list_add(&page[size].lru, &area->free_list);
+ list_add(&page[size].lru, &area->free_list[migratetype]);
area->nr_free++;
set_page_order(&page[size], high);
}
{
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
+ (page_get_page_cgroup(page) != NULL) |
(page_count(page) != 0) |
- (page->flags & (
- 1 << PG_lru |
- 1 << PG_private |
- 1 << PG_locked |
- 1 << PG_active |
- 1 << PG_dirty |
- 1 << PG_slab |
- 1 << PG_swapcache |
- 1 << PG_writeback |
- 1 << PG_reserved |
- 1 << PG_buddy ))))
+ (page->flags & PAGE_FLAGS_CHECK_AT_PREP)))
bad_page(page);
/*
if (PageReserved(page))
return 1;
- page->flags &= ~(1 << PG_uptodate | 1 << PG_error | 1 << PG_readahead |
+ page->flags &= ~(1 << PG_uptodate | 1 << PG_error | 1 << PG_reclaim |
1 << PG_referenced | 1 << PG_arch_1 |
1 << PG_owner_priv_1 | 1 << PG_mappedtodisk);
set_page_private(page, 0);
return 0;
}
-/*
- * Do the hard work of removing an element from the buddy allocator.
- * Call me with the zone->lock already held.
+/*
+ * Go through the free lists for the given migratetype and remove
+ * the smallest available page from the freelists
*/
-static struct page *__rmqueue(struct zone *zone, unsigned int order)
+static struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
+ int migratetype)
{
- struct free_area * area;
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))
+ area = &(zone->free_area[current_order]);
+ if (list_empty(&area->free_list[migratetype]))
continue;
- page = list_entry(area->free_list.next, struct page, lru);
+ 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);
+ 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()
+ */
+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;) {
+ 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;
+}
+
+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)
+ 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);
+ struct page *page = __rmqueue(zone, order, migratetype);
if (unlikely(page == NULL))
break;
- list_add_tail(&page->lru, list);
+
+ /*
+ * 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;
}
#endif
-static void __drain_pages(unsigned int cpu)
+/*
+ * 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;
- int i;
for_each_zone(zone) {
struct per_cpu_pageset *pset;
+ struct per_cpu_pages *pcp;
if (!populated_zone(zone))
continue;
pset = zone_pcp(zone, cpu);
- for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
- struct per_cpu_pages *pcp;
-
- pcp = &pset->pcp[i];
- local_irq_save(flags);
- free_pages_bulk(zone, pcp->count, &pcp->list, 0);
- pcp->count = 0;
- local_irq_restore(flags);
- }
+
+ 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;
+ int order, t;
struct list_head *curr;
if (!zone->spanned_pages)
swsusp_unset_page_free(page);
}
- for (order = MAX_ORDER - 1; order >= 0; --order)
- list_for_each(curr, &zone->free_area[order].free_list) {
+ 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);
}
-
-/*
- * 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_HIBERNATION */
+#endif /* CONFIG_PM */
/*
* Free a 0-order page
*/
-static void fastcall free_hot_cold_page(struct page *page, int cold)
+static void free_hot_cold_page(struct page *page, int cold)
{
struct zone *zone = page_zone(page);
struct per_cpu_pages *pcp;
if (free_pages_check(page))
return;
- if (!PageHighMem(page))
+ 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[cold];
+ pcp = &zone_pcp(zone, get_cpu())->pcp;
local_irq_save(flags);
__count_vm_event(PGFREE);
- list_add(&page->lru, &pcp->list);
+ 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);
put_cpu();
}
-void fastcall free_hot_page(struct page *page)
+void free_hot_page(struct page *page)
{
free_hot_cold_page(page, 0);
}
-void fastcall free_cold_page(struct page *page)
+void free_cold_page(struct page *page)
{
free_hot_cold_page(page, 1);
}
* we cheat by calling it from here, in the order > 0 path. Saves a branch
* or two.
*/
-static struct page *buffered_rmqueue(struct zonelist *zonelist,
+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[cold];
+ pcp = &zone_pcp(zone, cpu)->pcp;
local_irq_save(flags);
if (!pcp->count) {
pcp->count = rmqueue_bulk(zone, 0,
- pcp->batch, &pcp->list);
+ pcp->batch, &pcp->list, migratetype);
if (unlikely(!pcp->count))
goto failed;
}
- page = list_entry(pcp->list.next, struct page, lru);
+
+ /* 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);
+ page = __rmqueue(zone, order, migratetype);
spin_unlock(&zone->lock);
if (!page)
goto failed;
}
__count_zone_vm_events(PGALLOC, zone, 1 << order);
- zone_statistics(zonelist, zone);
+ zone_statistics(preferred_zone, zone);
local_irq_restore(flags);
put_cpu();
* 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 alot of full or unallowed zones.
+ * 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_online_map.)
+ * 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 (!zlc)
return NULL;
- if (jiffies - zlc->last_full_zap > 1 * HZ) {
+ 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_online_map;
+ &node_states[N_HIGH_MEMORY];
return allowednodes;
}
* 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 zone **z,
+static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
nodemask_t *allowednodes)
{
struct zonelist_cache *zlc; /* cached zonelist speedup info */
if (!zlc)
return 1;
- i = z - zonelist->zones;
+ i = z - zonelist->_zonerefs;
n = zlc->z_to_n[i];
/* This zone is worth trying if it is allowed but not full */
* 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 zone **z)
+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 */
if (!zlc)
return;
- i = z - zonelist->zones;
+ i = z - zonelist->_zonerefs;
set_bit(i, zlc->fullzones);
}
return NULL;
}
-static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z,
+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 zone **z)
+static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
{
}
#endif /* CONFIG_NUMA */
* a page.
*/
static struct page *
-get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
- struct zonelist *zonelist, int alloc_flags)
+get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
+ struct zonelist *zonelist, int high_zoneidx, int alloc_flags)
{
- struct zone **z;
+ struct zoneref *z;
struct page *page = NULL;
- int classzone_idx = zone_idx(zonelist->zones[0]);
- struct zone *zone;
+ 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.
*/
- z = zonelist->zones;
-
- do {
+ for_each_zone_zonelist_nodemask(zone, z, zonelist,
+ high_zoneidx, nodemask) {
if (NUMA_BUILD && zlc_active &&
!zlc_zone_worth_trying(zonelist, z, allowednodes))
continue;
- zone = *z;
- if (unlikely(NUMA_BUILD && (gfp_mask & __GFP_THISNODE) &&
- zone->zone_pgdat != zonelist->zones[0]->zone_pgdat))
- break;
if ((alloc_flags & ALLOC_CPUSET) &&
!cpuset_zone_allowed_softwall(zone, gfp_mask))
goto try_next_zone;
}
}
- page = buffered_rmqueue(zonelist, zone, order, gfp_mask);
+ page = buffered_rmqueue(preferred_zone, zone, order, gfp_mask);
if (page)
break;
this_zone_full:
zlc_active = 1;
did_zlc_setup = 1;
}
- } while (*(++z) != NULL);
+ }
if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
/* Disable zlc cache for second zonelist scan */
/*
* This is the 'heart' of the zoned buddy allocator.
*/
-struct page * fastcall
-__alloc_pages(gfp_t gfp_mask, unsigned int order,
- struct zonelist *zonelist)
+static 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;
- struct zone **z;
+ 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;
- int did_some_progress;
+ unsigned long did_some_progress;
+ unsigned long pages_reclaimed = 0;
might_sleep_if(wait);
return NULL;
restart:
- z = zonelist->zones; /* the list of zones suitable for gfp_mask */
+ z = zonelist->_zonerefs; /* the list of zones suitable for gfp_mask */
- if (unlikely(*z == NULL)) {
- /* Should this ever happen?? */
+ 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, order,
- zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
+ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
+ zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET);
if (page)
goto got_pg;
if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
goto nopage;
- for (z = zonelist->zones; *z; z++)
- wakeup_kswapd(*z, order);
+ for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
+ wakeup_kswapd(zone, order);
/*
* OK, we're below the kswapd watermark and have kicked background
* 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, order, zonelist, alloc_flags);
+ page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
+ high_zoneidx, alloc_flags);
if (page)
goto got_pg;
if (!(gfp_mask & __GFP_NOMEMALLOC)) {
nofail_alloc:
/* go through the zonelist yet again, ignoring mins */
- page = get_page_from_freelist(gfp_mask, order,
- zonelist, ALLOC_NO_WATERMARKS);
+ 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) {
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
- did_some_progress = try_to_free_pages(zonelist->zones, order, gfp_mask);
+ did_some_progress = try_to_free_pages(zonelist, order, gfp_mask);
p->reclaim_state = NULL;
p->flags &= ~PF_MEMALLOC;
cond_resched();
+ if (order != 0)
+ drain_all_pages();
+
if (likely(did_some_progress)) {
- page = get_page_from_freelist(gfp_mask, order,
- zonelist, alloc_flags);
+ 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, order,
- zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
- if (page)
+ 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)
+ 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, __GFP_REPEAT means __GFP_NOFAIL for order
- * <= 3, but that may not be true in other implementations.
+ * 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) ||
- (gfp_mask & __GFP_REPEAT))
+ 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;
}
return page;
}
+struct page *
+__alloc_pages(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist)
+{
+ return __alloc_pages_internal(gfp_mask, order, zonelist, NULL);
+}
+
+struct page *
+__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist, nodemask_t *nodemask)
+{
+ return __alloc_pages_internal(gfp_mask, order, zonelist, nodemask);
+}
+
EXPORT_SYMBOL(__alloc_pages);
/*
* Common helper functions.
*/
-fastcall unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
+unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
{
struct page * page;
page = alloc_pages(gfp_mask, order);
EXPORT_SYMBOL(__get_free_pages);
-fastcall unsigned long get_zeroed_page(gfp_t gfp_mask)
+unsigned long get_zeroed_page(gfp_t gfp_mask)
{
struct page * page;
free_hot_cold_page(pvec->pages[i], pvec->cold);
}
-fastcall void __free_pages(struct page *page, unsigned int order)
+void __free_pages(struct page *page, unsigned int order)
{
if (put_page_testzero(page)) {
if (order == 0)
EXPORT_SYMBOL(__free_pages);
-fastcall void free_pages(unsigned long addr, unsigned int order)
+void free_pages(unsigned long addr, unsigned int order)
{
if (addr != 0) {
VM_BUG_ON(!virt_addr_valid((void *)addr));
static unsigned int nr_free_zone_pages(int offset)
{
+ struct zoneref *z;
+ struct zone *zone;
+
/* Just pick one node, since fallback list is circular */
- pg_data_t *pgdat = NODE_DATA(numa_node_id());
unsigned int sum = 0;
- struct zonelist *zonelist = pgdat->node_zonelists + offset;
- struct zone **zonep = zonelist->zones;
- struct zone *zone;
+ struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL);
- for (zone = *zonep++; zone; zone = *zonep++) {
+ for_each_zone_zonelist(zone, z, zonelist, offset) {
unsigned long size = zone->present_pages;
unsigned long high = zone->pages_high;
if (size > high)
pageset = zone_pcp(zone, cpu);
- printk("CPU %4d: Hot: hi:%5d, btch:%4d usd:%4d "
- "Cold: hi:%5d, btch:%4d usd:%4d\n",
- cpu, pageset->pcp[0].high,
- pageset->pcp[0].batch, pageset->pcp[0].count,
- pageset->pcp[1].high, pageset->pcp[1].batch,
- pageset->pcp[1].count);
+ printk("CPU %4d: hi:%5d, btch:%4d usd:%4d\n",
+ cpu, pageset->pcp.high,
+ pageset->pcp.batch, pageset->pcp.count);
}
}
K(zone_page_state(zone, NR_INACTIVE)),
K(zone->present_pages),
zone->pages_scanned,
- (zone->all_unreclaimable ? "yes" : "no")
+ (zone_is_all_unreclaimable(zone) ? "yes" : "no")
);
printk("lowmem_reserve[]:");
for (i = 0; i < MAX_NR_ZONES; i++)
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.
*
zone_type--;
zone = pgdat->node_zones + zone_type;
if (populated_zone(zone)) {
- zonelist->zones[nr_zones++] = zone;
+ zoneref_set_zone(zone,
+ &zonelist->_zonerefs[nr_zones++]);
check_highest_zone(zone_type);
}
int n, val;
int min_val = INT_MAX;
int best_node = -1;
+ node_to_cpumask_ptr(tmp, 0);
/* Use the local node if we haven't already */
if (!node_isset(node, *used_node_mask)) {
return node;
}
- for_each_online_node(n) {
- cpumask_t tmp;
+ 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))
val += (n < node);
/* Give preference to headless and unused nodes */
- tmp = node_to_cpumask(n);
- if (!cpus_empty(tmp))
+ node_to_cpumask_ptr_next(tmp, n);
+ if (!cpus_empty(*tmp))
val += PENALTY_FOR_NODE_WITH_CPUS;
/* Slight preference for less loaded node */
*/
static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
{
- enum zone_type i;
int j;
struct zonelist *zonelist;
- for (i = 0; i < MAX_NR_ZONES; i++) {
- zonelist = pgdat->node_zonelists + i;
- for (j = 0; zonelist->zones[j] != NULL; j++)
- ;
- j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
- zonelist->zones[j] = NULL;
- }
+ 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;
}
/*
static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes)
{
- enum zone_type i;
int pos, j, node;
int zone_type; /* needs to be signed */
struct zone *z;
struct zonelist *zonelist;
- for (i = 0; i < MAX_NR_ZONES; i++) {
- zonelist = pgdat->node_zonelists + i;
- pos = 0;
- for (zone_type = i; 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)) {
- zonelist->zones[pos++] = z;
- check_highest_zone(zone_type);
- }
+ 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->zones[pos] = NULL;
}
+ zonelist->_zonerefs[pos].zone = NULL;
+ zonelist->_zonerefs[pos].zone_idx = 0;
}
static int default_zonelist_order(void)
* 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 / (num_online_nodes() + 1);
+ average_size = total_size /
+ (nodes_weight(node_states[N_HIGH_MEMORY]) + 1);
for_each_online_node(nid) {
low_kmem_size = 0;
total_size = 0;
int order = current_zonelist_order;
/* initialize zonelists */
- for (i = 0; i < MAX_NR_ZONES; i++) {
+ for (i = 0; i < MAX_ZONELISTS; i++) {
zonelist = pgdat->node_zonelists + i;
- zonelist->zones[0] = NULL;
+ zonelist->_zonerefs[0].zone = NULL;
+ zonelist->_zonerefs[0].zone_idx = 0;
}
/* NUMA-aware ordering of nodes */
/* 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)
{
- int i;
-
- for (i = 0; i < MAX_NR_ZONES; i++) {
- struct zonelist *zonelist;
- struct zonelist_cache *zlc;
- struct zone **z;
+ struct zonelist *zonelist;
+ struct zonelist_cache *zlc;
+ struct zoneref *z;
- zonelist = pgdat->node_zonelists + i;
- zonelist->zlcache_ptr = zlc = &zonelist->zlcache;
- bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
- for (z = zonelist->zones; *z; z++)
- zlc->z_to_n[z - zonelist->zones] = zone_to_nid(*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);
}
static void build_zonelists(pg_data_t *pgdat)
{
int node, local_node;
- enum zone_type i,j;
+ enum zone_type j;
+ struct zonelist *zonelist;
local_node = pgdat->node_id;
- for (i = 0; i < MAX_NR_ZONES; i++) {
- struct zonelist *zonelist;
- zonelist = pgdat->node_zonelists + i;
+ zonelist = &pgdat->node_zonelists[0];
+ j = build_zonelists_node(pgdat, zonelist, 0, MAX_NR_ZONES - 1);
- j = build_zonelists_node(pgdat, zonelist, 0, i);
- /*
- * 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, i);
- }
- for (node = 0; node < local_node; node++) {
- if (!node_online(node))
- continue;
- j = build_zonelists_node(NODE_DATA(node), zonelist, j, i);
- }
-
- zonelist->zones[j] = NULL;
+ /*
+ * 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)
{
- int i;
-
- for (i = 0; i < MAX_NR_ZONES; i++)
- pgdat->node_zonelists[i].zlcache_ptr = NULL;
+ pgdat->node_zonelists[0].zlcache_ptr = NULL;
}
#endif /* CONFIG_NUMA */
int nid;
for_each_online_node(nid) {
- build_zonelists(NODE_DATA(nid));
- build_zonelist_cache(NODE_DATA(nid));
+ pg_data_t *pgdat = NODE_DATA(nid);
+
+ build_zonelists(pgdat);
+ build_zonelist_cache(pgdat);
}
return 0;
}
__build_all_zonelists(NULL);
cpuset_init_current_mems_allowed();
} else {
- /* we have to stop all cpus to guaranntee there is no user
+ /* we have to stop all cpus to guarantee there is no user
of zonelist */
stop_machine_run(__build_all_zonelists, NULL, NR_CPUS);
/* cpuset refresh routine should be here */
}
vm_total_pages = nr_free_pagecache_pages();
- printk("Built %i zonelists in %s order. Total pages: %ld\n",
+ /*
+ * 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]);
#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);
+
+ /* 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.
struct page *page;
unsigned long end_pfn = start_pfn + size;
unsigned long pfn;
+ struct zone *z;
+ 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
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. */
}
}
-static void __meminit zone_init_free_lists(struct pglist_data *pgdat,
- struct zone *zone, unsigned long size)
+static void __meminit zone_init_free_lists(struct zone *zone)
{
- int order;
- for (order = 0; order < MAX_ORDER ; order++) {
- INIT_LIST_HEAD(&zone->free_area[order].free_list);
+ 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;
}
}
memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY)
#endif
-static int __devinit zone_batchsize(struct zone *zone)
+static int zone_batchsize(struct zone *zone)
{
int batch;
memset(p, 0, sizeof(*p));
- pcp = &p->pcp[0]; /* hot */
+ pcp = &p->pcp;
pcp->count = 0;
pcp->high = 6 * batch;
pcp->batch = max(1UL, 1 * batch);
INIT_LIST_HEAD(&pcp->list);
-
- pcp = &p->pcp[1]; /* cold*/
- pcp->count = 0;
- pcp->high = 2 * batch;
- pcp->batch = max(1UL, batch/2);
- INIT_LIST_HEAD(&pcp->list);
}
/*
{
struct per_cpu_pages *pcp;
- pcp = &p->pcp[0]; /* hot list */
+ pcp = &p->pcp;
pcp->high = high;
pcp->batch = max(1UL, high/4);
if ((high/4) > (PAGE_SHIFT * 8))
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_zone(zone) {
continue;
zone_pcp(zone, cpu) = kmalloc_node(sizeof(struct per_cpu_pageset),
- GFP_KERNEL, cpu_to_node(cpu));
+ GFP_KERNEL, node);
if (!zone_pcp(zone, cpu))
goto bad;
return 0;
bad:
for_each_zone(dzone) {
+ if (!populated_zone(dzone))
+ continue;
if (dzone == zone)
break;
kfree(zone_pcp(dzone, cpu));
alloc_size = zone->wait_table_hash_nr_entries
* sizeof(wait_queue_head_t);
- if (system_state == SYSTEM_BOOTING) {
+ if (!slab_is_available()) {
zone->wait_table = (wait_queue_head_t *)
alloc_bootmem_node(pgdat, alloc_size);
} else {
* To use this new node's memory, further consideration will be
* necessary.
*/
- zone->wait_table = (wait_queue_head_t *)vmalloc(alloc_size);
+ zone->wait_table = vmalloc(alloc_size);
}
if (!zone->wait_table)
return -ENOMEM;
zone->zone_start_pfn = zone_start_pfn;
- memmap_init(size, pgdat->node_id, zone_idx(zone), zone_start_pfn);
-
- zone_init_free_lists(pgdat, zone, zone->spanned_pages);
+ zone_init_free_lists(zone);
return 0;
}
/*
* Basic iterator support. Return the next active range of PFNs for a node
- * Note: nid == MAX_NUMNODES returns next region regardles of node
+ * Note: nid == MAX_NUMNODES returns next region regardless of node
*/
static int __meminit next_active_region_index_in_nid(int index, int nid)
{
}
}
+void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data)
+{
+ int i;
+ int ret;
+
+ for_each_active_range_index_in_nid(i, nid) {
+ ret = work_fn(early_node_map[i].start_pfn,
+ early_node_map[i].end_pfn, data);
+ if (ret)
+ break;
+ }
+}
/**
* sparse_memory_present_with_active_regions - Call memory_present for each active range
* @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used.
*end_pfn = max(*end_pfn, early_node_map[i].end_pfn);
}
- if (*start_pfn == -1UL) {
- printk(KERN_WARNING "Node %u active with no memory\n", nid);
+ if (*start_pfn == -1UL)
*start_pfn = 0;
- }
/* Push the node boundaries out if requested */
account_node_boundary(nid, start_pfn, end_pfn);
realtotalpages);
}
+#ifndef CONFIG_SPARSEMEM
+/*
+ * Calculate the size of the zone->blockflags rounded to an unsigned long
+ * Start by making sure zonesize is a multiple of pageblock_order by rounding
+ * up. Then use 1 NR_PAGEBLOCK_BITS worth of bits per pageblock, finally
+ * round what is now in bits to nearest long in bits, then return it in
+ * bytes.
+ */
+static unsigned long __init usemap_size(unsigned long zonesize)
+{
+ unsigned long usemapsize;
+
+ usemapsize = roundup(zonesize, pageblock_nr_pages);
+ usemapsize = usemapsize >> pageblock_order;
+ usemapsize *= NR_PAGEBLOCK_BITS;
+ usemapsize = roundup(usemapsize, 8 * sizeof(unsigned long));
+
+ return usemapsize / 8;
+}
+
+static void __init setup_usemap(struct pglist_data *pgdat,
+ struct zone *zone, unsigned long zonesize)
+{
+ unsigned long usemapsize = usemap_size(zonesize);
+ zone->pageblock_flags = NULL;
+ if (usemapsize) {
+ zone->pageblock_flags = alloc_bootmem_node(pgdat, usemapsize);
+ memset(zone->pageblock_flags, 0, usemapsize);
+ }
+}
+#else
+static void inline setup_usemap(struct pglist_data *pgdat,
+ struct zone *zone, unsigned long zonesize) {}
+#endif /* CONFIG_SPARSEMEM */
+
+#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
+
+/* Return a sensible default order for the pageblock size. */
+static inline int pageblock_default_order(void)
+{
+ if (HPAGE_SHIFT > PAGE_SHIFT)
+ return HUGETLB_PAGE_ORDER;
+
+ return MAX_ORDER-1;
+}
+
+/* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
+static inline void __init set_pageblock_order(unsigned int order)
+{
+ /* Check that pageblock_nr_pages has not already been setup */
+ if (pageblock_order)
+ return;
+
+ /*
+ * Assume the largest contiguous order of interest is a huge page.
+ * This value may be variable depending on boot parameters on IA64
+ */
+ pageblock_order = order;
+}
+#else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
+
+/*
+ * When CONFIG_HUGETLB_PAGE_SIZE_VARIABLE is not set, set_pageblock_order()
+ * and pageblock_default_order() are unused as pageblock_order is set
+ * at compile-time. See include/linux/pageblock-flags.h for the values of
+ * pageblock_order based on the kernel config
+ */
+static inline int pageblock_default_order(unsigned int order)
+{
+ return MAX_ORDER-1;
+}
+#define set_pageblock_order(x) do {} while (0)
+
+#endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
+
/*
* Set up the zone data structures:
* - mark all pages reserved
* - mark all memory queues empty
* - clear the memory bitmaps
*/
-static void __meminit free_area_init_core(struct pglist_data *pgdat,
+static void __paginginit free_area_init_core(struct pglist_data *pgdat,
unsigned long *zones_size, unsigned long *zholes_size)
{
enum zone_type j;
* is used by this zone for memmap. This affects the watermark
* and per-cpu initialisations
*/
- memmap_pages = (size * sizeof(struct page)) >> PAGE_SHIFT;
+ memmap_pages =
+ PAGE_ALIGN(size * sizeof(struct page)) >> PAGE_SHIFT;
if (realsize >= memmap_pages) {
realsize -= memmap_pages;
printk(KERN_DEBUG
zone->nr_scan_active = 0;
zone->nr_scan_inactive = 0;
zap_zone_vm_stats(zone);
- atomic_set(&zone->reclaim_in_progress, 0);
+ zone->flags = 0;
if (!size)
continue;
+ set_pageblock_order(pageblock_default_order());
+ setup_usemap(pgdat, zone, size);
ret = init_currently_empty_zone(zone, zone_start_pfn,
size, MEMMAP_EARLY);
BUG_ON(ret);
+ memmap_init(size, nid, j, zone_start_pfn);
zone_start_pfn += size;
}
}
mem_map = NODE_DATA(0)->node_mem_map;
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
if (page_to_pfn(mem_map) != pgdat->node_start_pfn)
- mem_map -= pgdat->node_start_pfn;
+ mem_map -= (pgdat->node_start_pfn - ARCH_PFN_OFFSET);
#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
}
#endif
#endif /* CONFIG_FLAT_NODE_MEM_MAP */
}
-void __meminit free_area_init_node(int nid, struct pglist_data *pgdat,
+void __paginginit free_area_init_node(int nid, struct pglist_data *pgdat,
unsigned long *zones_size, unsigned long node_start_pfn,
unsigned long *zholes_size)
{
calculate_node_totalpages(pgdat, zones_size, zholes_size);
alloc_node_mem_map(pgdat);
+#ifdef CONFIG_FLAT_NODE_MEM_MAP
+ printk(KERN_DEBUG "free_area_init_node: node %d, pgdat %08lx, node_mem_map %08lx\n",
+ nid, (unsigned long)pgdat,
+ (unsigned long)pgdat->node_mem_map);
+#endif
free_area_init_core(pgdat, zones_size, zholes_size);
}
{
int i;
- printk(KERN_DEBUG "Entering add_active_range(%d, %lu, %lu) "
+ printk(KERN_DEBUG "Entering add_active_range(%d, %#lx, %#lx) "
"%d entries of %d used\n",
nid, start_pfn, end_pfn,
nr_nodemap_entries, MAX_ACTIVE_REGIONS);
}
/**
- * shrink_active_range - Shrink an existing registered range of PFNs
+ * remove_active_range - Shrink an existing registered range of PFNs
* @nid: The node id the range is on that should be shrunk
- * @old_end_pfn: The old end PFN of the range
- * @new_end_pfn: The new PFN of the range
+ * @start_pfn: The new PFN of the range
+ * @end_pfn: The new PFN of the range
*
* i386 with NUMA use alloc_remap() to store a node_mem_map on a local node.
- * The map is kept at the end physical page range that has already been
- * registered with add_active_range(). This function allows an arch to shrink
- * an existing registered range.
+ * The map is kept near the end physical page range that has already been
+ * registered. This function allows an arch to shrink an existing registered
+ * range.
*/
-void __init shrink_active_range(unsigned int nid, unsigned long old_end_pfn,
- unsigned long new_end_pfn)
+void __init remove_active_range(unsigned int nid, unsigned long start_pfn,
+ unsigned long end_pfn)
{
- int i;
+ int i, j;
+ int removed = 0;
+
+ printk(KERN_DEBUG "remove_active_range (%d, %lu, %lu)\n",
+ nid, start_pfn, end_pfn);
/* Find the old active region end and shrink */
- for_each_active_range_index_in_nid(i, nid)
- if (early_node_map[i].end_pfn == old_end_pfn) {
- early_node_map[i].end_pfn = new_end_pfn;
- break;
+ for_each_active_range_index_in_nid(i, nid) {
+ if (early_node_map[i].start_pfn >= start_pfn &&
+ early_node_map[i].end_pfn <= end_pfn) {
+ /* clear it */
+ early_node_map[i].start_pfn = 0;
+ early_node_map[i].end_pfn = 0;
+ removed = 1;
+ continue;
+ }
+ if (early_node_map[i].start_pfn < start_pfn &&
+ early_node_map[i].end_pfn > start_pfn) {
+ unsigned long temp_end_pfn = early_node_map[i].end_pfn;
+ early_node_map[i].end_pfn = start_pfn;
+ if (temp_end_pfn > end_pfn)
+ add_active_range(nid, end_pfn, temp_end_pfn);
+ continue;
}
+ if (early_node_map[i].start_pfn >= start_pfn &&
+ early_node_map[i].end_pfn > end_pfn &&
+ early_node_map[i].start_pfn < end_pfn) {
+ early_node_map[i].start_pfn = end_pfn;
+ continue;
+ }
+ }
+
+ if (!removed)
+ return;
+
+ /* remove the blank ones */
+ for (i = nr_nodemap_entries - 1; i > 0; i--) {
+ if (early_node_map[i].nid != nid)
+ continue;
+ if (early_node_map[i].end_pfn)
+ continue;
+ /* we found it, get rid of it */
+ for (j = i; j < nr_nodemap_entries - 1; j++)
+ memcpy(&early_node_map[j], &early_node_map[j+1],
+ sizeof(early_node_map[j]));
+ j = nr_nodemap_entries - 1;
+ memset(&early_node_map[j], 0, sizeof(early_node_map[j]));
+ nr_nodemap_entries--;
+ }
}
/**
}
/* Find the lowest pfn for a node */
-unsigned long __init find_min_pfn_for_node(unsigned long nid)
+unsigned long __init find_min_pfn_for_node(int nid)
{
int i;
unsigned long min_pfn = ULONG_MAX;
if (min_pfn == ULONG_MAX) {
printk(KERN_WARNING
- "Could not find start_pfn for node %lu\n", nid);
+ "Could not find start_pfn for node %d\n", nid);
return 0;
}
return max_pfn;
}
-unsigned long __init early_calculate_totalpages(void)
+/*
+ * early_calculate_totalpages()
+ * Sum pages in active regions for movable zone.
+ * Populate N_HIGH_MEMORY for calculating usable_nodes.
+ */
+static unsigned long __init early_calculate_totalpages(void)
{
int i;
unsigned long totalpages = 0;
- for (i = 0; i < nr_nodemap_entries; i++)
- totalpages += early_node_map[i].end_pfn -
+ for (i = 0; i < nr_nodemap_entries; i++) {
+ unsigned long pages = early_node_map[i].end_pfn -
early_node_map[i].start_pfn;
-
- return totalpages;
+ totalpages += pages;
+ if (pages)
+ node_set_state(early_node_map[i].nid, N_HIGH_MEMORY);
+ }
+ return totalpages;
}
/*
int i, nid;
unsigned long usable_startpfn;
unsigned long kernelcore_node, kernelcore_remaining;
- int usable_nodes = num_online_nodes();
+ unsigned long totalpages = early_calculate_totalpages();
+ int usable_nodes = nodes_weight(node_states[N_HIGH_MEMORY]);
/*
* If movablecore was specified, calculate what size of
* what movablecore would have allowed.
*/
if (required_movablecore) {
- unsigned long totalpages = early_calculate_totalpages();
unsigned long corepages;
/*
restart:
/* Spread kernelcore memory as evenly as possible throughout nodes */
kernelcore_node = required_kernelcore / usable_nodes;
- for_each_online_node(nid) {
+ for_each_node_state(nid, N_HIGH_MEMORY) {
/*
* Recalculate kernelcore_node if the division per node
* now exceeds what is necessary to satisfy the requested
roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES);
}
+/* Any regular memory on that node ? */
+static void check_for_regular_memory(pg_data_t *pgdat)
+{
+#ifdef CONFIG_HIGHMEM
+ enum zone_type zone_type;
+
+ for (zone_type = 0; zone_type <= ZONE_NORMAL; zone_type++) {
+ struct zone *zone = &pgdat->node_zones[zone_type];
+ if (zone->present_pages)
+ node_set_state(zone_to_nid(zone), N_NORMAL_MEMORY);
+ }
+#endif
+}
+
/**
* free_area_init_nodes - Initialise all pg_data_t and zone data
* @max_zone_pfn: an array of max PFNs for each zone
for (i = 0; i < MAX_NR_ZONES; i++) {
if (i == ZONE_MOVABLE)
continue;
- printk(" %-8s %8lu -> %8lu\n",
+ printk(" %-8s %0#10lx -> %0#10lx\n",
zone_names[i],
arch_zone_lowest_possible_pfn[i],
arch_zone_highest_possible_pfn[i]);
/* Print out the early_node_map[] */
printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries);
for (i = 0; i < nr_nodemap_entries; i++)
- printk(" %3d: %8lu -> %8lu\n", early_node_map[i].nid,
+ printk(" %3d: %0#10lx -> %0#10lx\n", early_node_map[i].nid,
early_node_map[i].start_pfn,
early_node_map[i].end_pfn);
pg_data_t *pgdat = NODE_DATA(nid);
free_area_init_node(nid, pgdat, NULL,
find_min_pfn_for_node(nid), NULL);
+
+ /* Any memory on that node */
+ if (pgdat->node_present_pages)
+ node_set_state(nid, N_HIGH_MEMORY);
+ check_for_regular_memory(pgdat);
}
}
int cpu = (unsigned long)hcpu;
if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
- local_irq_disable();
- __drain_pages(cpu);
+ drain_pages(cpu);
+
+ /*
+ * Spill the event counters of the dead processor
+ * into the current processors event counters.
+ * This artificially elevates the count of the current
+ * processor.
+ */
vm_events_fold_cpu(cpu);
- local_irq_enable();
+
+ /*
+ * Zero the differential counters of the dead processor
+ * so that the vm statistics are consistent.
+ *
+ * This is only okay since the processor is dead and cannot
+ * race with what we are doing.
+ */
refresh_cpu_vm_stats(cpu);
}
return NOTIFY_OK;
zone->pages_low = zone->pages_min + (tmp >> 2);
zone->pages_high = zone->pages_min + (tmp >> 1);
+ setup_zone_migrate_reserve(zone);
spin_unlock_irqrestore(&zone->lru_lock, flags);
}
else if (hashdist)
table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
else {
- unsigned long order;
- for (order = 0; ((1UL << order) << PAGE_SHIFT) < size; order++)
- ;
+ unsigned long order = get_order(size);
table = (void*) __get_free_pages(GFP_ATOMIC, order);
/*
* If bucketsize is not a power-of-two, we may free
EXPORT_SYMBOL(page_to_pfn);
#endif /* CONFIG_OUT_OF_LINE_PFN_TO_PAGE */
+/* Return a pointer to the bitmap storing bits affecting a block of pages */
+static inline unsigned long *get_pageblock_bitmap(struct zone *zone,
+ unsigned long pfn)
+{
+#ifdef CONFIG_SPARSEMEM
+ return __pfn_to_section(pfn)->pageblock_flags;
+#else
+ return zone->pageblock_flags;
+#endif /* CONFIG_SPARSEMEM */
+}
+
+static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn)
+{
+#ifdef CONFIG_SPARSEMEM
+ pfn &= (PAGES_PER_SECTION-1);
+ return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
+#else
+ pfn = pfn - zone->zone_start_pfn;
+ return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
+#endif /* CONFIG_SPARSEMEM */
+}
+
+/**
+ * get_pageblock_flags_group - Return the requested group of flags for the pageblock_nr_pages block of pages
+ * @page: The page within the block of interest
+ * @start_bitidx: The first bit of interest to retrieve
+ * @end_bitidx: The last bit of interest
+ * returns pageblock_bits flags
+ */
+unsigned long get_pageblock_flags_group(struct page *page,
+ int start_bitidx, int end_bitidx)
+{
+ struct zone *zone;
+ unsigned long *bitmap;
+ unsigned long pfn, bitidx;
+ unsigned long flags = 0;
+ unsigned long value = 1;
+
+ zone = page_zone(page);
+ pfn = page_to_pfn(page);
+ bitmap = get_pageblock_bitmap(zone, pfn);
+ bitidx = pfn_to_bitidx(zone, pfn);
+
+ for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
+ if (test_bit(bitidx + start_bitidx, bitmap))
+ flags |= value;
+
+ return flags;
+}
+/**
+ * set_pageblock_flags_group - Set the requested group of flags for a pageblock_nr_pages block of pages
+ * @page: The page within the block of interest
+ * @start_bitidx: The first bit of interest
+ * @end_bitidx: The last bit of interest
+ * @flags: The flags to set
+ */
+void set_pageblock_flags_group(struct page *page, unsigned long flags,
+ int start_bitidx, int end_bitidx)
+{
+ struct zone *zone;
+ unsigned long *bitmap;
+ unsigned long pfn, bitidx;
+ unsigned long value = 1;
+
+ zone = page_zone(page);
+ pfn = page_to_pfn(page);
+ bitmap = get_pageblock_bitmap(zone, pfn);
+ bitidx = pfn_to_bitidx(zone, pfn);
+ VM_BUG_ON(pfn < zone->zone_start_pfn);
+ VM_BUG_ON(pfn >= zone->zone_start_pfn + zone->spanned_pages);
+
+ for (; start_bitidx <= end_bitidx; start_bitidx++, value <<= 1)
+ if (flags & value)
+ __set_bit(bitidx + start_bitidx, bitmap);
+ else
+ __clear_bit(bitidx + start_bitidx, bitmap);
+}
+
+/*
+ * This is designed as sub function...plz see page_isolation.c also.
+ * set/clear page block's type to be ISOLATE.
+ * page allocater never alloc memory from ISOLATE block.
+ */
+
+int set_migratetype_isolate(struct page *page)
+{
+ struct zone *zone;
+ unsigned long flags;
+ int ret = -EBUSY;
+
+ zone = page_zone(page);
+ spin_lock_irqsave(&zone->lock, flags);
+ /*
+ * In future, more migrate types will be able to be isolation target.
+ */
+ if (get_pageblock_migratetype(page) != MIGRATE_MOVABLE)
+ goto out;
+ set_pageblock_migratetype(page, MIGRATE_ISOLATE);
+ move_freepages_block(zone, page, MIGRATE_ISOLATE);
+ ret = 0;
+out:
+ spin_unlock_irqrestore(&zone->lock, flags);
+ if (!ret)
+ drain_all_pages();
+ return ret;
+}
+
+void unset_migratetype_isolate(struct page *page)
+{
+ struct zone *zone;
+ unsigned long flags;
+ zone = page_zone(page);
+ spin_lock_irqsave(&zone->lock, flags);
+ if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE)
+ goto out;
+ set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+ move_freepages_block(zone, page, MIGRATE_MOVABLE);
+out:
+ spin_unlock_irqrestore(&zone->lock, flags);
+}
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+/*
+ * All pages in the range must be isolated before calling this.
+ */
+void
+__offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
+{
+ struct page *page;
+ struct zone *zone;
+ int order, i;
+ unsigned long pfn;
+ unsigned long flags;
+ /* find the first valid pfn */
+ for (pfn = start_pfn; pfn < end_pfn; pfn++)
+ if (pfn_valid(pfn))
+ break;
+ if (pfn == end_pfn)
+ return;
+ zone = page_zone(pfn_to_page(pfn));
+ spin_lock_irqsave(&zone->lock, flags);
+ pfn = start_pfn;
+ while (pfn < end_pfn) {
+ if (!pfn_valid(pfn)) {
+ pfn++;
+ continue;
+ }
+ page = pfn_to_page(pfn);
+ BUG_ON(page_count(page));
+ BUG_ON(!PageBuddy(page));
+ order = page_order(page);
+#ifdef CONFIG_DEBUG_VM
+ printk(KERN_INFO "remove from free list %lx %d %lx\n",
+ pfn, 1 << order, end_pfn);
+#endif
+ list_del(&page->lru);
+ rmv_page_order(page);
+ zone->free_area[order].nr_free--;
+ __mod_zone_page_state(zone, NR_FREE_PAGES,
+ - (1UL << order));
+ for (i = 0; i < (1 << order); i++)
+ SetPageReserved((page+i));
+ pfn += (1 << order);
+ }
+ spin_unlock_irqrestore(&zone->lock, flags);
+}
+#endif