#include <linux/pagemap.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/topology.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
-#include <linux/vs_base.h>
+#include <linux/cpuset.h>
+#include <linux/memory_hotplug.h>
+#include <linux/nodemask.h>
+#include <linux/vmalloc.h>
+#include <linux/mempolicy.h>
#include <linux/vs_limit.h>
#include <asm/tlbflush.h>
+#include <asm/div64.h>
+#include "internal.h"
-DECLARE_BITMAP(node_online_map, MAX_NUMNODES);
-struct pglist_data *pgdat_list;
-unsigned long totalram_pages;
-unsigned long totalhigh_pages;
-int nr_swap_pages;
-int numnodes = 1;
-int sysctl_lower_zone_protection = 0;
+/*
+ * MCD - HACK: Find somewhere to initialize this EARLY, or make this
+ * initializer cleaner
+ */
+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);
+unsigned long totalram_pages __read_mostly;
+unsigned long totalhigh_pages __read_mostly;
+unsigned long totalreserve_pages __read_mostly;
+long nr_swap_pages;
+int percpu_pagelist_fraction;
+
+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] = { 256, 256, 32 };
EXPORT_SYMBOL(totalram_pages);
-EXPORT_SYMBOL(nr_swap_pages);
/*
* Used by page_zone() to look up the address of the struct zone whose
* id is encoded in the upper bits of page->flags
*/
-struct zone *zone_table[1 << (ZONES_SHIFT + NODES_SHIFT)];
+struct zone *zone_table[1 << ZONETABLE_SHIFT] __read_mostly;
EXPORT_SYMBOL(zone_table);
-static char *zone_names[MAX_NR_ZONES] = { "DMA", "Normal", "HighMem" };
+static char *zone_names[MAX_NR_ZONES] = { "DMA", "DMA32", "Normal", "HighMem" };
int min_free_kbytes = 1024;
+unsigned long __initdata nr_kernel_pages;
+unsigned long __initdata nr_all_pages;
+
+#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)
+{
+#ifdef CONFIG_HOLES_IN_ZONE
+ if (!pfn_valid(page_to_pfn(page)))
+ return 0;
+#endif
+ 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_to_pfn(page) >= zone->zone_start_pfn + zone->spanned_pages)
+ if (page_outside_zone_boundaries(zone, page))
return 1;
- if (page_to_pfn(page) < zone->zone_start_pfn)
- return 1;
- if (zone != page_zone(page))
+ 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(const char *function, struct page *page)
+static void bad_page(struct page *page)
{
- printk(KERN_EMERG "Bad page state at %s (in process '%s', page %p)\n",
- function, current->comm, page);
- printk(KERN_EMERG "flags:0x%08lx mapping:%p mapcount:%d count:%d\n",
+ printk(KERN_EMERG "Bad page state in process '%s'\n"
+ KERN_EMERG "page:%p flags:0x%0*lx mapping:%p mapcount:%d count:%d (%s)\n"
+ KERN_EMERG "Trying to fix it up, but a reboot is needed\n"
+ KERN_EMERG "Backtrace:\n",
+ current->comm, page, (int)(2*sizeof(unsigned long)),
(unsigned long)page->flags, page->mapping,
- (int)page->mapcount, page_count(page));
- printk(KERN_EMERG "Backtrace:\n");
+ page_mapcount(page), page_count(page), print_tainted());
dump_stack();
- printk(KERN_EMERG "Trying to fix it up, but a reboot is needed\n");
- page->flags &= ~(1 << PG_private |
+ page->flags &= ~(1 << PG_lru |
+ 1 << PG_private |
1 << PG_locked |
- 1 << PG_lru |
1 << PG_active |
1 << PG_dirty |
- 1 << PG_maplock |
- 1 << PG_anon |
+ 1 << PG_reclaim |
+ 1 << PG_slab |
1 << PG_swapcache |
- 1 << PG_writeback);
+ 1 << PG_writeback |
+ 1 << PG_buddy );
set_page_count(page, 0);
+ reset_page_mapcount(page);
page->mapping = NULL;
- page->mapcount = 0;
+ add_taint(TAINT_BAD_PAGE);
}
-#ifndef CONFIG_HUGETLB_PAGE
-#define prep_compound_page(page, order) do { } while (0)
-#define destroy_compound_page(page, order) do { } while (0)
-#else
/*
* Higher-order pages are called "compound pages". They are structured thusly:
*
* All pages have PG_compound set. All pages have their ->private pointing at
* the head page (even the head page has this).
*
- * The first tail page's ->mapping, if non-zero, holds the address of the
- * compound page's put_page() function.
- *
- * The order of the allocation is stored in the first tail page's ->index
- * This is only for debug at present. This usage means that zero-order pages
- * may not be compound.
+ * 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, (unsigned long)page[1].lru.prev);
+}
+
static void prep_compound_page(struct page *page, unsigned long order)
{
int i;
int nr_pages = 1 << order;
- page[1].mapping = 0;
- page[1].index = order;
+ page[1].lru.next = (void *)free_compound_page; /* set dtor */
+ page[1].lru.prev = (void *)order;
for (i = 0; i < nr_pages; i++) {
struct page *p = page + i;
- SetPageCompound(p);
- p->private = (unsigned long)page;
+ __SetPageCompound(p);
+ set_page_private(p, (unsigned long)page);
}
}
int i;
int nr_pages = 1 << order;
- if (!PageCompound(page))
- return;
-
- if (page[1].index != order)
- bad_page(__FUNCTION__, page);
+ if (unlikely((unsigned long)page[1].lru.prev != order))
+ bad_page(page);
for (i = 0; i < nr_pages; i++) {
struct page *p = page + i;
- if (!PageCompound(p))
- bad_page(__FUNCTION__, page);
- if (p->private != (unsigned long)page)
- bad_page(__FUNCTION__, page);
- ClearPageCompound(p);
+ if (unlikely(!PageCompound(p) |
+ (page_private(p) != (unsigned long)page)))
+ bad_page(page);
+ __ClearPageCompound(p);
}
}
-#endif /* CONFIG_HUGETLB_PAGE */
+
+static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
+{
+ int i;
+
+ 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.
+ */
+ BUG_ON((gfp_flags & __GFP_HIGHMEM) && in_interrupt());
+ for (i = 0; i < (1 << order); i++)
+ 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);
+ __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 contigious at least up to MAX_ORDER
+ */
+static inline struct page *
+__page_find_buddy(struct page *page, unsigned long page_idx, unsigned int order)
+{
+ unsigned long buddy_idx = page_idx ^ (1 << order);
+
+ return page + (buddy_idx - page_idx);
+}
+
+static inline unsigned long
+__find_combined_index(unsigned long page_idx, unsigned int order)
+{
+ return (page_idx & ~(1 << order));
+}
+
+/*
+ * This function checks whether a page is free && is the buddy
+ * we can do coalesce a page and its buddy if
+ * (a) the buddy is not in a hole &&
+ * (b) the buddy is in the buddy system &&
+ * (c) a page and its buddy have the same order.
+ *
+ * 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, int order)
+{
+#ifdef CONFIG_HOLES_IN_ZONE
+ if (!pfn_valid(page_to_pfn(page)))
+ return 0;
+#endif
+
+ if (PageBuddy(page) && page_order(page) == order) {
+ BUG_ON(page_count(page) != 0);
+ return 1;
+ }
+ return 0;
+}
/*
* Freeing function for a buddy system allocator.
* 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 one bit for each pair of blocks, which
- * is set to 1 iff only one of the pair is allocated. So when we
- * are allocating or freeing one, we can derive the state of the
+ * 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
* -- wli
*/
-static inline void __free_pages_bulk (struct page *page, struct page *base,
- struct zone *zone, struct free_area *area, unsigned long mask,
- unsigned int order)
+static inline void __free_one_page(struct page *page,
+ struct zone *zone, unsigned int order)
{
- unsigned long page_idx, index;
+ unsigned long page_idx;
+ int order_size = 1 << order;
- if (order)
+ if (unlikely(PageCompound(page)))
destroy_compound_page(page, order);
- page_idx = page - base;
- if (page_idx & ~mask)
- BUG();
- index = page_idx >> (1 + order);
-
- zone->free_pages -= mask;
- while (mask + (1 << (MAX_ORDER-1))) {
- struct page *buddy1, *buddy2;
- BUG_ON(area >= zone->free_area + MAX_ORDER);
- if (!__test_and_change_bit(index, area->map))
- /*
- * the buddy page is still allocated.
- */
- break;
- /*
- * Move the buddy up one level.
- * This code is taking advantage of the identity:
- * -mask = 1+~mask
- */
- buddy1 = base + (page_idx ^ -mask);
- buddy2 = base + page_idx;
- BUG_ON(bad_range(zone, buddy1));
- BUG_ON(bad_range(zone, buddy2));
- list_del(&buddy1->lru);
- mask <<= 1;
- area++;
- index >>= 1;
- page_idx &= mask;
+ page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);
+
+ BUG_ON(page_idx & (order_size - 1));
+ BUG_ON(bad_range(zone, page));
+
+ zone->free_pages += order_size;
+ while (order < MAX_ORDER-1) {
+ unsigned long combined_idx;
+ struct free_area *area;
+ struct page *buddy;
+
+ buddy = __page_find_buddy(page, page_idx, order);
+ if (!page_is_buddy(buddy, order))
+ break; /* Move the buddy up one level. */
+
+ list_del(&buddy->lru);
+ area = zone->free_area + order;
+ area->nr_free--;
+ rmv_page_order(buddy);
+ combined_idx = __find_combined_index(page_idx, order);
+ page = page + (combined_idx - page_idx);
+ page_idx = combined_idx;
+ order++;
}
- list_add(&(base + page_idx)->lru, &area->free_list);
+ set_page_order(page, order);
+ list_add(&page->lru, &zone->free_area[order].free_list);
+ zone->free_area[order].nr_free++;
}
-static inline void free_pages_check(const char *function, struct page *page)
+static inline int free_pages_check(struct page *page)
{
- if ( page_mapped(page) ||
- page->mapping != NULL ||
- page_count(page) != 0 ||
+ if (unlikely(page_mapcount(page) |
+ (page->mapping != NULL) |
+ (page_count(page) != 0) |
(page->flags & (
1 << PG_lru |
1 << PG_private |
1 << PG_active |
1 << PG_reclaim |
1 << PG_slab |
- 1 << PG_maplock |
- 1 << PG_anon |
1 << PG_swapcache |
- 1 << PG_writeback )))
- bad_page(function, page);
+ 1 << PG_writeback |
+ 1 << PG_reserved |
+ 1 << PG_buddy ))))
+ bad_page(page);
if (PageDirty(page))
- ClearPageDirty(page);
+ __ClearPageDirty(page);
+ /*
+ * For now, we report if PG_reserved was found set, but do not
+ * clear it, and do not free the page. But we shall soon need
+ * to do more, for when the ZERO_PAGE count wraps negative.
+ */
+ return PageReserved(page);
}
/*
* Frees a list of pages.
* Assumes all pages on list are in same zone, and of same order.
- * count is the number of pages to free, or 0 for all on the list.
+ * 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 int
-free_pages_bulk(struct zone *zone, int count,
- struct list_head *list, unsigned int order)
+static void free_pages_bulk(struct zone *zone, int count,
+ struct list_head *list, int order)
{
- unsigned long mask, flags;
- struct free_area *area;
- struct page *base, *page = NULL;
- int ret = 0;
-
- mask = (~0UL) << order;
- base = zone->zone_mem_map;
- area = zone->free_area + order;
- spin_lock_irqsave(&zone->lock, flags);
+ spin_lock(&zone->lock);
zone->all_unreclaimable = 0;
zone->pages_scanned = 0;
- while (!list_empty(list) && count--) {
+ while (count--) {
+ struct page *page;
+
+ BUG_ON(list_empty(list));
page = list_entry(list->prev, struct page, lru);
- /* have to delete it as __free_pages_bulk list manipulates */
+ /* have to delete it as __free_one_page list manipulates */
list_del(&page->lru);
- __free_pages_bulk(page, base, zone, area, mask, order);
- ret++;
+ __free_one_page(page, zone, order);
}
- spin_unlock_irqrestore(&zone->lock, flags);
- return ret;
+ spin_unlock(&zone->lock);
}
-void __free_pages_ok(struct page *page, unsigned int order)
+static void free_one_page(struct zone *zone, struct page *page, int order)
{
LIST_HEAD(list);
+ list_add(&page->lru, &list);
+ free_pages_bulk(zone, 1, &list, order);
+}
+
+static void __free_pages_ok(struct page *page, unsigned int order)
+{
+ unsigned long flags;
int i;
+ int reserved = 0;
+
+ arch_free_page(page, order);
+ if (!PageHighMem(page))
+ mutex_debug_check_no_locks_freed(page_address(page),
+ PAGE_SIZE<<order);
- mod_page_state(pgfree, 1 << order);
for (i = 0 ; i < (1 << order) ; ++i)
- free_pages_check(__FUNCTION__, page + i);
- list_add(&page->lru, &list);
- kernel_map_pages(page, 1<<order, 0);
- free_pages_bulk(page_zone(page), 1, &list, order);
+ reserved += free_pages_check(page + i);
+ if (reserved)
+ return;
+
+ kernel_map_pages(page, 1 << order, 0);
+ local_irq_save(flags);
+ __mod_page_state(pgfree, 1 << order);
+ free_one_page(page_zone(page), page, order);
+ local_irq_restore(flags);
}
-#define MARK_USED(index, order, area) \
- __change_bit((index) >> (1+(order)), (area)->map)
+/*
+ * permit the bootmem allocator to evade page validation on high-order frees
+ */
+void fastcall __init __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;
-static inline struct page *
-expand(struct zone *zone, struct page *page,
- unsigned long index, int low, int high, struct free_area *area)
+ 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)
{
unsigned long size = 1 << high;
while (high > low) {
- BUG_ON(bad_range(zone, page));
area--;
high--;
size >>= 1;
- list_add(&page->lru, &area->free_list);
- MARK_USED(index, high, area);
- index += size;
- page += size;
+ BUG_ON(bad_range(zone, &page[size]));
+ list_add(&page[size].lru, &area->free_list);
+ area->nr_free++;
+ set_page_order(&page[size], high);
}
- return page;
-}
-
-static inline void set_page_refs(struct page *page, int order)
-{
-#ifdef CONFIG_MMU
- set_page_count(page, 1);
-#else
- int i;
-
- /*
- * We need to reference all the pages for this order, otherwise if
- * anyone accesses one of the pages with (get/put) it will be freed.
- */
- for (i = 0; i < (1 << order); i++)
- set_page_count(page+i, 1);
-#endif /* CONFIG_MMU */
}
/*
* This page is about to be returned from the page allocator
*/
-static void prep_new_page(struct page *page, int order)
+static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
{
- if (page->mapping || page_mapped(page) ||
- (page->flags & (
+ if (unlikely(page_mapcount(page) |
+ (page->mapping != NULL) |
+ (page_count(page) != 0) |
+ (page->flags & (
+ 1 << PG_lru |
1 << PG_private |
1 << PG_locked |
- 1 << PG_lru |
1 << PG_active |
1 << PG_dirty |
1 << PG_reclaim |
- 1 << PG_maplock |
- 1 << PG_anon |
+ 1 << PG_slab |
1 << PG_swapcache |
- 1 << PG_writeback )))
- bad_page(__FUNCTION__, page);
+ 1 << PG_writeback |
+ 1 << PG_reserved |
+ 1 << PG_buddy ))))
+ bad_page(page);
+
+ /*
+ * For now, we report if PG_reserved was found set, but do not
+ * clear it, and do not allocate the page: as a safety net.
+ */
+ if (PageReserved(page))
+ return 1;
page->flags &= ~(1 << PG_uptodate | 1 << PG_error |
1 << PG_referenced | 1 << PG_arch_1 |
1 << PG_checked | 1 << PG_mappedtodisk);
- page->private = 0;
- set_page_refs(page, order);
+ set_page_private(page, 0);
+ set_page_refcounted(page);
+ 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;
}
/*
struct free_area * area;
unsigned int current_order;
struct page *page;
- unsigned int index;
for (current_order = order; current_order < MAX_ORDER; ++current_order) {
area = zone->free_area + current_order;
page = list_entry(area->free_list.next, struct page, lru);
list_del(&page->lru);
- index = page - zone->zone_mem_map;
- if (current_order != MAX_ORDER-1)
- MARK_USED(index, current_order, area);
+ rmv_page_order(page);
+ area->nr_free--;
zone->free_pages -= 1UL << order;
- return expand(zone, page, index, order, current_order, area);
+ expand(zone, page, order, current_order, area);
+ return page;
}
return NULL;
static int rmqueue_bulk(struct zone *zone, unsigned int order,
unsigned long count, struct list_head *list)
{
- unsigned long flags;
int i;
- int allocated = 0;
- struct page *page;
- spin_lock_irqsave(&zone->lock, flags);
+ spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
- page = __rmqueue(zone, order);
- if (page == NULL)
+ struct page *page = __rmqueue(zone, order);
+ if (unlikely(page == NULL))
break;
- allocated++;
list_add_tail(&page->lru, list);
}
- spin_unlock_irqrestore(&zone->lock, flags);
- return allocated;
+ spin_unlock(&zone->lock);
+ return i;
+}
+
+#ifdef CONFIG_NUMA
+/*
+ * Called from the slab reaper to drain pagesets on a particular node that
+ * belong to the currently executing processor.
+ * Note that this function must be called with the thread pinned to
+ * a single processor.
+ */
+void drain_node_pages(int nodeid)
+{
+ int i, z;
+ unsigned long flags;
+
+ for (z = 0; z < MAX_NR_ZONES; z++) {
+ struct zone *zone = NODE_DATA(nodeid)->node_zones + z;
+ struct per_cpu_pageset *pset;
+
+ pset = zone_pcp(zone, smp_processor_id());
+ for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
+ struct per_cpu_pages *pcp;
+
+ pcp = &pset->pcp[i];
+ if (pcp->count) {
+ local_irq_save(flags);
+ free_pages_bulk(zone, pcp->count, &pcp->list, 0);
+ pcp->count = 0;
+ local_irq_restore(flags);
+ }
+ }
+ }
}
+#endif
#if defined(CONFIG_PM) || defined(CONFIG_HOTPLUG_CPU)
static void __drain_pages(unsigned int cpu)
{
+ unsigned long flags;
struct zone *zone;
int i;
for_each_zone(zone) {
struct per_cpu_pageset *pset;
- pset = &zone->pageset[cpu];
+ pset = zone_pcp(zone, cpu);
for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
struct per_cpu_pages *pcp;
pcp = &pset->pcp[i];
- pcp->count -= free_pages_bulk(zone, pcp->count,
- &pcp->list, 0);
+ local_irq_save(flags);
+ free_pages_bulk(zone, pcp->count, &pcp->list, 0);
+ pcp->count = 0;
+ local_irq_restore(flags);
}
}
}
#endif /* CONFIG_PM || CONFIG_HOTPLUG_CPU */
#ifdef CONFIG_PM
-int is_head_of_free_region(struct page *page)
+
+void mark_free_pages(struct zone *zone)
{
- struct zone *zone = page_zone(page);
- unsigned long flags;
+ unsigned long zone_pfn, flags;
int order;
struct list_head *curr;
- /*
- * Should not matter as we need quiescent system for
- * suspend anyway, but...
- */
+ if (!zone->spanned_pages)
+ return;
+
spin_lock_irqsave(&zone->lock, flags);
+ for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
+ ClearPageNosaveFree(pfn_to_page(zone_pfn + zone->zone_start_pfn));
+
for (order = MAX_ORDER - 1; order >= 0; --order)
- list_for_each(curr, &zone->free_area[order].free_list)
- if (page == list_entry(curr, struct page, lru)) {
- spin_unlock_irqrestore(&zone->lock, flags);
- return 1 << order;
- }
+ list_for_each(curr, &zone->free_area[order].free_list) {
+ unsigned long start_pfn, i;
+
+ start_pfn = page_to_pfn(list_entry(curr, struct page, lru));
+
+ for (i=0; i < (1<<order); i++)
+ SetPageNosaveFree(pfn_to_page(start_pfn+i));
+ }
spin_unlock_irqrestore(&zone->lock, flags);
- return 0;
}
/*
}
#endif /* CONFIG_PM */
-static void zone_statistics(struct zonelist *zonelist, struct zone *z)
+static void zone_statistics(struct zonelist *zonelist, struct zone *z, int cpu)
{
#ifdef CONFIG_NUMA
- unsigned long flags;
- int cpu;
pg_data_t *pg = z->zone_pgdat;
pg_data_t *orig = zonelist->zones[0]->zone_pgdat;
struct per_cpu_pageset *p;
- local_irq_save(flags);
- cpu = smp_processor_id();
- p = &z->pageset[cpu];
+ p = zone_pcp(z, cpu);
if (pg == orig) {
- z->pageset[cpu].numa_hit++;
+ p->numa_hit++;
} else {
p->numa_miss++;
- zonelist->zones[0]->pageset[cpu].numa_foreign++;
+ zone_pcp(zonelist->zones[0], cpu)->numa_foreign++;
}
if (pg == NODE_DATA(numa_node_id()))
p->local_node++;
else
p->other_node++;
- local_irq_restore(flags);
#endif
}
/*
* Free a 0-order page
*/
-static void FASTCALL(free_hot_cold_page(struct page *page, int cold));
static void fastcall free_hot_cold_page(struct page *page, int cold)
{
struct zone *zone = page_zone(page);
struct per_cpu_pages *pcp;
unsigned long flags;
+ arch_free_page(page, 0);
+
+ if (PageAnon(page))
+ page->mapping = NULL;
+ if (free_pages_check(page))
+ return;
+
kernel_map_pages(page, 1, 0);
- inc_page_state(pgfree);
- free_pages_check(__FUNCTION__, page);
- pcp = &zone->pageset[get_cpu()].pcp[cold];
+
+ pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
local_irq_save(flags);
- if (pcp->count >= pcp->high)
- pcp->count -= free_pages_bulk(zone, pcp->batch, &pcp->list, 0);
+ __inc_page_state(pgfree);
list_add(&page->lru, &pcp->list);
pcp->count++;
+ if (pcp->count >= pcp->high) {
+ free_pages_bulk(zone, pcp->batch, &pcp->list, 0);
+ pcp->count -= pcp->batch;
+ } else if (zone->all_unreclaimable) {
+ spin_lock(&zone->lock);
+ zone->all_unreclaimable = 0;
+ zone->pages_scanned = 0;
+ spin_unlock(&zone->lock);
+ }
local_irq_restore(flags);
put_cpu();
}
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;
+
+ BUG_ON(PageCompound(page));
+ 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 *zone, int order, int gfp_flags)
+static struct page *buffered_rmqueue(struct zonelist *zonelist,
+ struct zone *zone, int order, gfp_t gfp_flags)
{
unsigned long flags;
- struct page *page = NULL;
+ struct page *page;
int cold = !!(gfp_flags & __GFP_COLD);
+ int cpu;
- if (order == 0) {
+again:
+ cpu = get_cpu();
+ if (likely(order == 0)) {
struct per_cpu_pages *pcp;
- pcp = &zone->pageset[get_cpu()].pcp[cold];
+ pcp = &zone_pcp(zone, cpu)->pcp[cold];
local_irq_save(flags);
- if (pcp->count <= pcp->low)
+ if (!pcp->count) {
pcp->count += rmqueue_bulk(zone, 0,
pcp->batch, &pcp->list);
- if (pcp->count) {
- page = list_entry(pcp->list.next, struct page, lru);
- list_del(&page->lru);
- pcp->count--;
+ if (unlikely(!pcp->count))
+ goto failed;
}
- local_irq_restore(flags);
- put_cpu();
- }
-
- if (page == NULL) {
+ 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);
- spin_unlock_irqrestore(&zone->lock, flags);
+ spin_unlock(&zone->lock);
+ if (!page)
+ goto failed;
}
- if (page != NULL) {
- BUG_ON(bad_range(zone, page));
- mod_page_state_zone(zone, pgalloc, 1 << order);
- prep_new_page(page, order);
- if (order && (gfp_flags & __GFP_COMP))
- prep_compound_page(page, order);
+ __mod_page_state_zone(zone, pgalloc, 1 << order);
+ zone_statistics(zonelist, zone, cpu);
+ local_irq_restore(flags);
+ put_cpu();
+
+ 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 */
+
+/*
+ * 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, free_pages = z->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;
+}
+
+/*
+ * get_page_from_freeliest goes through the zonelist trying to allocate
+ * a page.
+ */
+static struct page *
+get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
+ struct zonelist *zonelist, int alloc_flags)
+{
+ struct zone **z = zonelist->zones;
+ struct page *page = NULL;
+ int classzone_idx = zone_idx(*z);
+
+ /*
+ * Go through the zonelist once, looking for a zone with enough free.
+ * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
+ */
+ do {
+ if ((alloc_flags & ALLOC_CPUSET) &&
+ !cpuset_zone_allowed(*z, gfp_mask))
+ continue;
+
+ if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
+ unsigned long mark;
+ if (alloc_flags & ALLOC_WMARK_MIN)
+ mark = (*z)->pages_min;
+ else if (alloc_flags & ALLOC_WMARK_LOW)
+ mark = (*z)->pages_low;
+ else
+ mark = (*z)->pages_high;
+ if (!zone_watermark_ok(*z, order, mark,
+ classzone_idx, alloc_flags))
+ if (!zone_reclaim_mode ||
+ !zone_reclaim(*z, gfp_mask, order))
+ continue;
+ }
+
+ page = buffered_rmqueue(zonelist, *z, order, gfp_mask);
+ if (page) {
+ break;
+ }
+ } while (*(++z) != NULL);
return page;
}
/*
* This is the 'heart' of the zoned buddy allocator.
- *
- * Herein lies the mysterious "incremental min". That's the
- *
- * local_low = z->pages_low;
- * min += local_low;
- *
- * thing. The intent here is to provide additional protection to low zones for
- * allocation requests which _could_ use higher zones. So a GFP_HIGHMEM
- * request is not allowed to dip as deeply into the normal zone as a GFP_KERNEL
- * request. This preserves additional space in those lower zones for requests
- * which really do need memory from those zones. It means that on a decent
- * sized machine, GFP_HIGHMEM and GFP_KERNEL requests basically leave the DMA
- * zone untouched.
*/
struct page * fastcall
-__alloc_pages(unsigned int gfp_mask, unsigned int order,
+__alloc_pages(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist)
{
- const int wait = gfp_mask & __GFP_WAIT;
- unsigned long min;
- struct zone **zones;
+ const gfp_t wait = gfp_mask & __GFP_WAIT;
+ struct zone **z;
struct page *page;
struct reclaim_state reclaim_state;
struct task_struct *p = current;
- int i;
- int alloc_type;
int do_retry;
+ int alloc_flags;
+ int did_some_progress;
might_sleep_if(wait);
- zones = zonelist->zones; /* the list of zones suitable for gfp_mask */
- if (zones[0] == NULL) /* no zones in the zonelist */
- return NULL;
+restart:
+ z = zonelist->zones; /* the list of zones suitable for gfp_mask */
- alloc_type = zone_idx(zones[0]);
-
- /* Go through the zonelist once, looking for a zone with enough free */
- for (i = 0; zones[i] != NULL; i++) {
- struct zone *z = zones[i];
-
- min = (1<<order) + z->protection[alloc_type];
-
- /*
- * We let real-time tasks dip their real-time paws a little
- * deeper into reserves.
- */
- if (rt_task(p))
- min -= z->pages_low >> 1;
-
- if (z->free_pages >= min ||
- (!wait && z->free_pages >= z->pages_high)) {
- page = buffered_rmqueue(z, order, gfp_mask);
- if (page) {
- zone_statistics(zonelist, z);
- goto got_pg;
- }
- }
+ if (unlikely(*z == NULL)) {
+ /* Should this ever happen?? */
+ return NULL;
}
- /* we're somewhat low on memory, failed to find what we needed */
- for (i = 0; zones[i] != NULL; i++)
- wakeup_kswapd(zones[i]);
+ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
+ zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
+ if (page)
+ goto got_pg;
- /* Go through the zonelist again, taking __GFP_HIGH into account */
- for (i = 0; zones[i] != NULL; i++) {
- struct zone *z = zones[i];
+ do {
+ if (cpuset_zone_allowed(*z, gfp_mask|__GFP_HARDWALL))
+ wakeup_kswapd(*z, order);
+ } while (*(++z));
- min = (1<<order) + z->protection[alloc_type];
-
- if (gfp_mask & __GFP_HIGH)
- min -= z->pages_low >> 2;
- if (rt_task(p))
- min -= z->pages_low >> 1;
-
- if (z->free_pages >= min ||
- (!wait && z->free_pages >= z->pages_high)) {
- page = buffered_rmqueue(z, order, gfp_mask);
- if (page) {
- zone_statistics(zonelist, z);
- goto got_pg;
- }
- }
- }
-
- /* here we're in the low on memory slow path */
+ /*
+ * 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;
-rebalance:
- if ((p->flags & (PF_MEMALLOC | PF_MEMDIE)) && !in_interrupt()) {
- /* go through the zonelist yet again, ignoring mins */
- for (i = 0; zones[i] != NULL; i++) {
- struct zone *z = zones[i];
-
- page = buffered_rmqueue(z, order, gfp_mask);
- if (page) {
- zone_statistics(zonelist, z);
+ /*
+ * 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, order, zonelist, alloc_flags);
+ if (page)
+ goto got_pg;
+
+ /* This allocation should allow future memory freeing. */
+
+ 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, order,
+ zonelist, ALLOC_NO_WATERMARKS);
+ if (page)
goto got_pg;
+ if (gfp_mask & __GFP_NOFAIL) {
+ blk_congestion_wait(WRITE, HZ/50);
+ goto nofail_alloc;
}
}
goto nopage;
if (!wait)
goto nopage;
+rebalance:
+ cond_resched();
+
+ /* We now go into synchronous reclaim */
+ cpuset_memory_pressure_bump();
p->flags |= PF_MEMALLOC;
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
- try_to_free_pages(zones, gfp_mask, order);
+ did_some_progress = try_to_free_pages(zonelist->zones, gfp_mask);
p->reclaim_state = NULL;
p->flags &= ~PF_MEMALLOC;
- /* go through the zonelist yet one more time */
- for (i = 0; zones[i] != NULL; i++) {
- struct zone *z = zones[i];
+ cond_resched();
- min = (1UL << order) + z->protection[alloc_type];
+ if (likely(did_some_progress)) {
+ page = get_page_from_freelist(gfp_mask, order,
+ zonelist, alloc_flags);
+ if (page)
+ goto got_pg;
+ } else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
+ /*
+ * Go through the zonelist yet one more time, keep
+ * very high watermark here, this is only to catch
+ * a parallel oom killing, we must fail if we're still
+ * under heavy pressure.
+ */
+ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
+ zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
+ if (page)
+ goto got_pg;
- if (z->free_pages >= min ||
- (!wait && z->free_pages >= z->pages_high)) {
- page = buffered_rmqueue(z, order, gfp_mask);
- if (page) {
- zone_statistics(zonelist, z);
- goto got_pg;
- }
- }
+ out_of_memory(zonelist, gfp_mask, order);
+ 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, but that
- * may not be true in other implementations.
+ * In this implementation, __GFP_REPEAT means __GFP_NOFAIL for order
+ * <= 3, but that may not be true in other implementations.
*/
do_retry = 0;
if (!(gfp_mask & __GFP_NORETRY)) {
" order:%d, mode:0x%x\n",
p->comm, order, gfp_mask);
dump_stack();
+ show_mem();
}
- return NULL;
got_pg:
- kernel_map_pages(page, 1 << order, 1);
return page;
}
EXPORT_SYMBOL(__alloc_pages);
-#ifdef CONFIG_NUMA
-/* Early boot: Everything is done by one cpu, but the data structures will be
- * used by all cpus - spread them on all nodes.
- */
-static __init unsigned long get_boot_pages(unsigned int gfp_mask, unsigned int order)
-{
-static int nodenr;
- int i = nodenr;
- struct page *page;
-
- for (;;) {
- if (i > nodenr + numnodes)
- return 0;
- if (node_present_pages(i%numnodes)) {
- struct zone **z;
- /* The node contains memory. Check that there is
- * memory in the intended zonelist.
- */
- z = NODE_DATA(i%numnodes)->node_zonelists[gfp_mask & GFP_ZONEMASK].zones;
- while (*z) {
- if ( (*z)->free_pages > (1UL<<order))
- goto found_node;
- z++;
- }
- }
- i++;
- }
-found_node:
- nodenr = i+1;
- page = alloc_pages_node(i%numnodes, gfp_mask, order);
- if (!page)
- return 0;
- return (unsigned long) page_address(page);
-}
-#endif
-
/*
* Common helper functions.
*/
-fastcall unsigned long __get_free_pages(unsigned int gfp_mask, unsigned int order)
+fastcall unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
{
struct page * page;
-
-#ifdef CONFIG_NUMA
- if (unlikely(system_state == SYSTEM_BOOTING))
- return get_boot_pages(gfp_mask, order);
-#endif
page = alloc_pages(gfp_mask, order);
if (!page)
return 0;
EXPORT_SYMBOL(__get_free_pages);
-fastcall unsigned long get_zeroed_page(unsigned int gfp_mask)
+fastcall 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
*/
- BUG_ON(gfp_mask & __GFP_HIGHMEM);
+ BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0);
- page = alloc_pages(gfp_mask, 0);
- if (page) {
- void *address = page_address(page);
- clear_page(address);
- return (unsigned long) address;
- }
+ page = alloc_pages(gfp_mask | __GFP_ZERO, 0);
+ if (page)
+ return (unsigned long) page_address(page);
return 0;
}
fastcall void __free_pages(struct page *page, unsigned int order)
{
- if (!PageReserved(page) && put_page_testzero(page)) {
+ if (put_page_testzero(page)) {
if (order == 0)
free_hot_page(page);
else
fastcall void free_pages(unsigned long addr, unsigned int order)
{
if (addr != 0) {
- BUG_ON(!virt_addr_valid(addr));
- __free_pages(virt_to_page(addr), order);
+ BUG_ON(!virt_addr_valid((void *)addr));
+ __free_pages(virt_to_page((void *)addr), order);
}
}
EXPORT_SYMBOL(nr_free_pages);
-unsigned int nr_used_zone_pages(void)
-{
- unsigned int pages = 0;
- struct zone *zone;
-
- for_each_zone(zone)
- pages += zone->nr_active + zone->nr_inactive;
-
- return pages;
-}
-
#ifdef CONFIG_NUMA
unsigned int nr_free_pages_pgdat(pg_data_t *pgdat)
{
static unsigned int nr_free_zone_pages(int offset)
{
- pg_data_t *pgdat;
+ /* Just pick one node, since fallback list is circular */
+ pg_data_t *pgdat = NODE_DATA(numa_node_id());
unsigned int sum = 0;
- for_each_pgdat(pgdat) {
- struct zonelist *zonelist = pgdat->node_zonelists + offset;
- struct zone **zonep = zonelist->zones;
- struct zone *zone;
+ struct zonelist *zonelist = pgdat->node_zonelists + offset;
+ struct zone **zonep = zonelist->zones;
+ struct zone *zone;
- for (zone = *zonep++; zone; zone = *zonep++) {
- unsigned long size = zone->present_pages;
- unsigned long high = zone->pages_high;
- if (size > high)
- sum += size - high;
- }
+ for (zone = *zonep++; zone; zone = *zonep++) {
+ unsigned long size = zone->present_pages;
+ unsigned long high = zone->pages_high;
+ if (size > high)
+ sum += size - high;
}
return sum;
*/
unsigned int nr_free_buffer_pages(void)
{
- return nr_free_zone_pages(GFP_USER & GFP_ZONEMASK);
+ return nr_free_zone_pages(gfp_zone(GFP_USER));
}
/*
*/
unsigned int nr_free_pagecache_pages(void)
{
- return nr_free_zone_pages(GFP_HIGHUSER & GFP_ZONEMASK);
+ return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER));
}
#ifdef CONFIG_HIGHMEM
pg_data_t *pgdat;
unsigned int pages = 0;
- for_each_pgdat(pgdat)
+ for_each_online_pgdat(pgdat)
pages += pgdat->node_zones[ZONE_HIGHMEM].free_pages;
return pages;
* The result is unavoidably approximate - it can change
* during and after execution of this function.
*/
-DEFINE_PER_CPU(struct page_state, page_states) = {0};
-EXPORT_PER_CPU_SYMBOL(page_states);
+static DEFINE_PER_CPU(struct page_state, page_states) = {0};
atomic_t nr_pagecache = ATOMIC_INIT(0);
EXPORT_SYMBOL(nr_pagecache);
DEFINE_PER_CPU(long, nr_pagecache_local) = 0;
#endif
-void __get_page_state(struct page_state *ret, int nr)
+static void __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask)
{
- int cpu = 0;
+ unsigned cpu;
- memset(ret, 0, sizeof(*ret));
- while (cpu < NR_CPUS) {
- unsigned long *in, *out, off;
+ memset(ret, 0, nr * sizeof(unsigned long));
+ cpus_and(*cpumask, *cpumask, cpu_online_map);
- if (!cpu_possible(cpu)) {
- cpu++;
- continue;
- }
+ for_each_cpu_mask(cpu, *cpumask) {
+ unsigned long *in;
+ unsigned long *out;
+ unsigned off;
+ unsigned next_cpu;
in = (unsigned long *)&per_cpu(page_states, cpu);
- cpu++;
- if (cpu < NR_CPUS && cpu_possible(cpu))
- prefetch(&per_cpu(page_states, cpu));
+
+ next_cpu = next_cpu(cpu, *cpumask);
+ if (likely(next_cpu < NR_CPUS))
+ prefetch(&per_cpu(page_states, next_cpu));
+
out = (unsigned long *)ret;
for (off = 0; off < nr; off++)
*out++ += *in++;
}
}
+void get_page_state_node(struct page_state *ret, int node)
+{
+ int nr;
+ cpumask_t mask = node_to_cpumask(node);
+
+ nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
+ nr /= sizeof(unsigned long);
+
+ __get_page_state(ret, nr+1, &mask);
+}
+
void get_page_state(struct page_state *ret)
{
int nr;
+ cpumask_t mask = CPU_MASK_ALL;
nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
nr /= sizeof(unsigned long);
- __get_page_state(ret, nr + 1);
+ __get_page_state(ret, nr + 1, &mask);
}
void get_full_page_state(struct page_state *ret)
{
- __get_page_state(ret, sizeof(*ret) / sizeof(unsigned long));
+ cpumask_t mask = CPU_MASK_ALL;
+
+ __get_page_state(ret, sizeof(*ret) / sizeof(unsigned long), &mask);
}
-unsigned long __read_page_state(unsigned offset)
+unsigned long read_page_state_offset(unsigned long offset)
{
unsigned long ret = 0;
int cpu;
- for (cpu = 0; cpu < NR_CPUS; cpu++) {
+ for_each_online_cpu(cpu) {
unsigned long in;
- if (!cpu_possible(cpu))
- continue;
-
in = (unsigned long)&per_cpu(page_states, cpu) + offset;
ret += *((unsigned long *)in);
}
return ret;
}
+void __mod_page_state_offset(unsigned long offset, unsigned long delta)
+{
+ void *ptr;
+
+ ptr = &__get_cpu_var(page_states);
+ *(unsigned long *)(ptr + offset) += delta;
+}
+EXPORT_SYMBOL(__mod_page_state_offset);
+
+void mod_page_state_offset(unsigned long offset, unsigned long delta)
+{
+ unsigned long flags;
+ void *ptr;
+
+ local_irq_save(flags);
+ ptr = &__get_cpu_var(page_states);
+ *(unsigned long *)(ptr + offset) += delta;
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL(mod_page_state_offset);
+
+void __get_zone_counts(unsigned long *active, unsigned long *inactive,
+ unsigned long *free, struct pglist_data *pgdat)
+{
+ struct zone *zones = pgdat->node_zones;
+ int i;
+
+ *active = 0;
+ *inactive = 0;
+ *free = 0;
+ for (i = 0; i < MAX_NR_ZONES; i++) {
+ *active += zones[i].nr_active;
+ *inactive += zones[i].nr_inactive;
+ *free += zones[i].free_pages;
+ }
+}
+
void get_zone_counts(unsigned long *active,
unsigned long *inactive, unsigned long *free)
{
- struct zone *zone;
+ struct pglist_data *pgdat;
*active = 0;
*inactive = 0;
*free = 0;
- for_each_zone(zone) {
- *active += zone->nr_active;
- *inactive += zone->nr_inactive;
- *free += zone->free_pages;
+ for_each_online_pgdat(pgdat) {
+ unsigned long l, m, n;
+ __get_zone_counts(&l, &m, &n, pgdat);
+ *active += l;
+ *inactive += m;
+ *free += n;
}
}
val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].present_pages;
val->freehigh = pgdat->node_zones[ZONE_HIGHMEM].free_pages;
val->mem_unit = PAGE_SIZE;
+ if (vx_flags(VXF_VIRT_MEM, 0))
+ vx_vsi_meminfo(val);
}
#endif
show_node(zone);
printk("%s per-cpu:", zone->name);
- if (!zone->present_pages) {
+ if (!populated_zone(zone)) {
printk(" empty\n");
continue;
} else
printk("\n");
- for (cpu = 0; cpu < NR_CPUS; ++cpu) {
+ for_each_online_cpu(cpu) {
struct per_cpu_pageset *pageset;
- if (!cpu_possible(cpu))
- continue;
-
- pageset = zone->pageset + cpu;
+ pageset = zone_pcp(zone, cpu);
for (temperature = 0; temperature < 2; temperature++)
- printk("cpu %d %s: low %d, high %d, batch %d\n",
+ printk("cpu %d %s: high %d, batch %d used:%d\n",
cpu,
temperature ? "cold" : "hot",
- pageset->pcp[temperature].low,
pageset->pcp[temperature].high,
- pageset->pcp[temperature].batch);
+ pageset->pcp[temperature].batch,
+ pageset->pcp[temperature].count);
}
}
get_page_state(&ps);
get_zone_counts(&active, &inactive, &free);
- printk("\nFree pages: %11ukB (%ukB HighMem)\n",
+ printk("Free pages: %11ukB (%ukB HighMem)\n",
K(nr_free_pages()),
K(nr_free_highpages()));
" active:%lukB"
" inactive:%lukB"
" present:%lukB"
+ " pages_scanned:%lu"
+ " all_unreclaimable? %s"
"\n",
zone->name,
K(zone->free_pages),
K(zone->pages_high),
K(zone->nr_active),
K(zone->nr_inactive),
- K(zone->present_pages)
+ K(zone->present_pages),
+ zone->pages_scanned,
+ (zone->all_unreclaimable ? "yes" : "no")
);
- printk("protections[]:");
+ printk("lowmem_reserve[]:");
for (i = 0; i < MAX_NR_ZONES; i++)
- printk(" %lu", zone->protection[i]);
+ printk(" %lu", zone->lowmem_reserve[i]);
printk("\n");
}
for_each_zone(zone) {
- struct list_head *elem;
unsigned long nr, flags, order, total = 0;
show_node(zone);
printk("%s: ", zone->name);
- if (!zone->present_pages) {
+ if (!populated_zone(zone)) {
printk("empty\n");
continue;
}
spin_lock_irqsave(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
- nr = 0;
- list_for_each(elem, &zone->free_area[order].free_list)
- ++nr;
+ nr = zone->free_area[order].nr_free;
total += nr << order;
printk("%lu*%lukB ", nr, K(1UL) << order);
}
/*
* Builds allocation fallback zone lists.
+ *
+ * Add all populated zones of a node to the zonelist.
*/
-static int __init build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, int j, int k)
-{
- switch (k) {
- struct zone *zone;
- default:
- BUG();
- case ZONE_HIGHMEM:
- zone = pgdat->node_zones + ZONE_HIGHMEM;
- if (zone->present_pages) {
+static int __init build_zonelists_node(pg_data_t *pgdat,
+ struct zonelist *zonelist, int nr_zones, int zone_type)
+{
+ struct zone *zone;
+
+ BUG_ON(zone_type > ZONE_HIGHMEM);
+
+ do {
+ zone = pgdat->node_zones + zone_type;
+ if (populated_zone(zone)) {
#ifndef CONFIG_HIGHMEM
- BUG();
+ BUG_ON(zone_type > ZONE_NORMAL);
#endif
- zonelist->zones[j++] = zone;
+ zonelist->zones[nr_zones++] = zone;
+ check_highest_zone(zone_type);
}
- case ZONE_NORMAL:
- zone = pgdat->node_zones + ZONE_NORMAL;
- if (zone->present_pages)
- zonelist->zones[j++] = zone;
- case ZONE_DMA:
- zone = pgdat->node_zones + ZONE_DMA;
- if (zone->present_pages)
- zonelist->zones[j++] = zone;
- }
+ zone_type--;
- return j;
+ } while (zone_type >= 0);
+ return nr_zones;
+}
+
+static inline int highest_zone(int zone_bits)
+{
+ int res = ZONE_NORMAL;
+ if (zone_bits & (__force int)__GFP_HIGHMEM)
+ res = ZONE_HIGHMEM;
+ if (zone_bits & (__force int)__GFP_DMA32)
+ res = ZONE_DMA32;
+ if (zone_bits & (__force int)__GFP_DMA)
+ res = ZONE_DMA;
+ return res;
}
#ifdef CONFIG_NUMA
-#define MAX_NODE_LOAD (numnodes)
+#define MAX_NODE_LOAD (num_online_nodes())
static int __initdata node_load[MAX_NUMNODES];
/**
- * find_next_best_node - find the next node that should appear in a given
- * node's fallback list
+ * 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: pointer to the bitmap of already used nodes
+ * @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
* on them otherwise.
* It returns -1 if no node is found.
*/
-static int __init find_next_best_node(int node, void *used_node_mask)
+static int __init find_next_best_node(int node, nodemask_t *used_node_mask)
{
- int i, n, val;
+ int n, val;
int min_val = INT_MAX;
int best_node = -1;
- for (i = 0; i < numnodes; i++) {
- cpumask_t tmp;
+ /* Use the local node if we haven't already */
+ if (!node_isset(node, *used_node_mask)) {
+ node_set(node, *used_node_mask);
+ return node;
+ }
- /* Start from local node */
- n = (node+i)%numnodes;
+ for_each_online_node(n) {
+ cpumask_t tmp;
/* Don't want a node to appear more than once */
- if (test_bit(n, used_node_mask))
+ 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 = node_to_cpumask(n);
if (!cpus_empty(tmp))
}
if (best_node >= 0)
- set_bit(best_node, used_node_mask);
+ node_set(best_node, *used_node_mask);
return best_node;
}
int i, j, k, node, local_node;
int prev_node, load;
struct zonelist *zonelist;
- DECLARE_BITMAP(used_mask, MAX_NUMNODES);
+ nodemask_t used_mask;
/* initialize zonelists */
- for (i = 0; i < MAX_NR_ZONES; i++) {
+ for (i = 0; i < GFP_ZONETYPES; i++) {
zonelist = pgdat->node_zonelists + i;
- memset(zonelist, 0, sizeof(*zonelist));
zonelist->zones[0] = NULL;
}
/* NUMA-aware ordering of nodes */
local_node = pgdat->node_id;
- load = numnodes;
+ load = num_online_nodes();
prev_node = local_node;
- bitmap_zero(used_mask, MAX_NUMNODES);
- while ((node = find_next_best_node(local_node, used_mask)) >= 0) {
+ nodes_clear(used_mask);
+ 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 (node_distance(local_node, node) !=
- node_distance(local_node, prev_node))
+
+ if (distance != node_distance(local_node, prev_node))
node_load[node] += load;
prev_node = node;
load--;
- for (i = 0; i < MAX_NR_ZONES; i++) {
+ for (i = 0; i < GFP_ZONETYPES; i++) {
zonelist = pgdat->node_zonelists + i;
for (j = 0; zonelist->zones[j] != NULL; j++);
- k = ZONE_NORMAL;
- if (i & __GFP_HIGHMEM)
- k = ZONE_HIGHMEM;
- if (i & __GFP_DMA)
- k = ZONE_DMA;
+ k = highest_zone(i);
j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
zonelist->zones[j] = NULL;
int i, j, k, node, local_node;
local_node = pgdat->node_id;
- for (i = 0; i < MAX_NR_ZONES; i++) {
+ for (i = 0; i < GFP_ZONETYPES; i++) {
struct zonelist *zonelist;
zonelist = pgdat->node_zonelists + i;
- memset(zonelist, 0, sizeof(*zonelist));
j = 0;
- k = ZONE_NORMAL;
- if (i & __GFP_HIGHMEM)
- k = ZONE_HIGHMEM;
- if (i & __GFP_DMA)
- k = ZONE_DMA;
-
+ k = highest_zone(i);
j = build_zonelists_node(pgdat, zonelist, j, k);
/*
* Now we build the zonelist so that it contains the zones
* zones coming right after the local ones are those from
* node N+1 (modulo N)
*/
- for (node = local_node + 1; node < numnodes; node++)
- j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
- for (node = 0; node < local_node; node++)
- j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
-
+ for (node = local_node + 1; node < MAX_NUMNODES; node++) {
+ if (!node_online(node))
+ continue;
+ j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
+ }
+ for (node = 0; node < local_node; node++) {
+ if (!node_online(node))
+ continue;
+ j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
+ }
+
zonelist->zones[j] = NULL;
}
}
-#endif /* CONFIG_NUMA */
-
-void __init build_all_zonelists(void)
+#endif /* CONFIG_NUMA */
+
+void __init build_all_zonelists(void)
+{
+ int i;
+
+ for_each_online_node(i)
+ build_zonelists(NODE_DATA(i));
+ printk("Built %i zonelists\n", num_online_nodes());
+ cpuset_init_current_mems_allowed();
+}
+
+/*
+ * Helper functions to size the waitqueue hash table.
+ * Essentially these want to choose hash table sizes sufficiently
+ * large so that collisions trying to wait on pages are rare.
+ * But in fact, the number of active page waitqueues on typical
+ * systems is ridiculously low, less than 200. So this is even
+ * conservative, even though it seems large.
+ *
+ * The constant PAGES_PER_WAITQUEUE specifies the ratio of pages to
+ * waitqueues, i.e. the size of the waitq table given the number of pages.
+ */
+#define PAGES_PER_WAITQUEUE 256
+
+static inline unsigned long wait_table_size(unsigned long pages)
+{
+ unsigned long size = 1;
+
+ pages /= PAGES_PER_WAITQUEUE;
+
+ while (size < pages)
+ size <<= 1;
+
+ /*
+ * Once we have dozens or even hundreds of threads sleeping
+ * on IO we've got bigger problems than wait queue collision.
+ * Limit the size of the wait table to a reasonable size.
+ */
+ size = min(size, 4096UL);
+
+ return max(size, 4UL);
+}
+
+/*
+ * This is an integer logarithm so that shifts can be used later
+ * to extract the more random high bits from the multiplicative
+ * hash function before the remainder is taken.
+ */
+static inline unsigned long wait_table_bits(unsigned long size)
+{
+ return ffz(~size);
+}
+
+#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))
+
+static void __init calculate_zone_totalpages(struct pglist_data *pgdat,
+ unsigned long *zones_size, unsigned long *zholes_size)
+{
+ unsigned long realtotalpages, totalpages = 0;
+ int i;
+
+ for (i = 0; i < MAX_NR_ZONES; i++)
+ totalpages += zones_size[i];
+ pgdat->node_spanned_pages = totalpages;
+
+ realtotalpages = totalpages;
+ if (zholes_size)
+ for (i = 0; i < MAX_NR_ZONES; i++)
+ realtotalpages -= zholes_size[i];
+ pgdat->node_present_pages = realtotalpages;
+ printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages);
+}
+
+
+/*
+ * Initially all pages are reserved - free ones are freed
+ * up by free_all_bootmem() once the early boot process is
+ * done. Non-atomic initialization, single-pass.
+ */
+void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
+ unsigned long start_pfn)
+{
+ struct page *page;
+ unsigned long end_pfn = start_pfn + size;
+ unsigned long pfn;
+
+ for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+ if (!early_pfn_valid(pfn))
+ continue;
+ page = pfn_to_page(pfn);
+ set_page_links(page, zone, nid, pfn);
+ init_page_count(page);
+ reset_page_mapcount(page);
+ SetPageReserved(page);
+ INIT_LIST_HEAD(&page->lru);
+#ifdef WANT_PAGE_VIRTUAL
+ /* The shift won't overflow because ZONE_NORMAL is below 4G. */
+ if (!is_highmem_idx(zone))
+ set_page_address(page, __va(pfn << PAGE_SHIFT));
+#endif
+ }
+}
+
+void zone_init_free_lists(struct pglist_data *pgdat, struct zone *zone,
+ unsigned long size)
+{
+ int order;
+ for (order = 0; order < MAX_ORDER ; order++) {
+ INIT_LIST_HEAD(&zone->free_area[order].free_list);
+ zone->free_area[order].nr_free = 0;
+ }
+}
+
+#define ZONETABLE_INDEX(x, zone_nr) ((x << ZONES_SHIFT) | zone_nr)
+void zonetable_add(struct zone *zone, int nid, int zid, unsigned long pfn,
+ unsigned long size)
+{
+ unsigned long snum = pfn_to_section_nr(pfn);
+ unsigned long end = pfn_to_section_nr(pfn + size);
+
+ if (FLAGS_HAS_NODE)
+ zone_table[ZONETABLE_INDEX(nid, zid)] = zone;
+ else
+ for (; snum <= end; snum++)
+ zone_table[ZONETABLE_INDEX(snum, zid)] = zone;
+}
+
+#ifndef __HAVE_ARCH_MEMMAP_INIT
+#define memmap_init(size, nid, zone, start_pfn) \
+ memmap_init_zone((size), (nid), (zone), (start_pfn))
+#endif
+
+static int __cpuinit zone_batchsize(struct zone *zone)
+{
+ int batch;
+
+ /*
+ * The per-cpu-pages pools are set to around 1000th of the
+ * size of the zone. But no more than 1/2 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 = (1 << (fls(batch + batch/2)-1)) - 1;
+
+ return batch;
+}
+
+inline void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
+{
+ struct per_cpu_pages *pcp;
+
+ memset(p, 0, sizeof(*p));
+
+ pcp = &p->pcp[0]; /* hot */
+ 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);
+}
+
+/*
+ * 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[0]; /* hot list */
+ 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;
+
+ for_each_zone(zone) {
+
+ zone_pcp(zone, cpu) = kmalloc_node(sizeof(struct per_cpu_pageset),
+ GFP_KERNEL, cpu_to_node(cpu));
+ 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 (dzone == zone)
+ break;
+ kfree(zone_pcp(dzone, cpu));
+ zone_pcp(dzone, cpu) = NULL;
+ }
+ return -ENOMEM;
+}
+
+static inline void free_zone_pagesets(int cpu)
{
- int i;
+ struct zone *zone;
- for(i = 0 ; i < numnodes ; i++)
- build_zonelists(NODE_DATA(i));
- printk("Built %i zonelists\n", numnodes);
-}
+ for_each_zone(zone) {
+ struct per_cpu_pageset *pset = zone_pcp(zone, cpu);
-/*
- * 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
+ zone_pcp(zone, cpu) = NULL;
+ kfree(pset);
+ }
+}
-static inline unsigned long wait_table_size(unsigned long pages)
+static int pageset_cpuup_callback(struct notifier_block *nfb,
+ unsigned long action,
+ void *hcpu)
{
- 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);
+ int cpu = (long)hcpu;
+ int ret = NOTIFY_OK;
- return max(size, 4UL);
+ switch (action) {
+ case CPU_UP_PREPARE:
+ if (process_zones(cpu))
+ ret = NOTIFY_BAD;
+ break;
+ case CPU_UP_CANCELED:
+ case CPU_DEAD:
+ free_zone_pagesets(cpu);
+ break;
+ default:
+ break;
+ }
+ return ret;
}
-/*
- * 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)
+static struct notifier_block pageset_notifier =
+ { &pageset_cpuup_callback, NULL, 0 };
+
+void __init setup_per_cpu_pageset(void)
{
- return ffz(~size);
+ 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);
}
-#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))
+#endif
-static void __init calculate_zone_totalpages(struct pglist_data *pgdat,
- unsigned long *zones_size, unsigned long *zholes_size)
+static __meminit
+void zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
{
- unsigned long realtotalpages, totalpages = 0;
int i;
+ struct pglist_data *pgdat = zone->zone_pgdat;
- for (i = 0; i < MAX_NR_ZONES; i++)
- totalpages += zones_size[i];
- pgdat->node_spanned_pages = totalpages;
+ /*
+ * The per-page waitqueue mechanism uses hashed waitqueues
+ * per zone.
+ */
+ zone->wait_table_size = wait_table_size(zone_size_pages);
+ zone->wait_table_bits = wait_table_bits(zone->wait_table_size);
+ zone->wait_table = (wait_queue_head_t *)
+ alloc_bootmem_node(pgdat, zone->wait_table_size
+ * sizeof(wait_queue_head_t));
- realtotalpages = totalpages;
- if (zholes_size)
- for (i = 0; i < MAX_NR_ZONES; i++)
- realtotalpages -= zholes_size[i];
- pgdat->node_present_pages = realtotalpages;
- printk("On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages);
+ for(i = 0; i < zone->wait_table_size; ++i)
+ init_waitqueue_head(zone->wait_table + i);
}
-
-/*
- * Initially all pages are reserved - free ones are freed
- * up by free_all_bootmem() once the early boot process is
- * done. Non-atomic initialization, single-pass.
- */
-void __init memmap_init_zone(struct page *start, unsigned long size, int nid,
- unsigned long zone, unsigned long start_pfn)
+static __meminit void zone_pcp_init(struct zone *zone)
{
- struct page *page;
+ int cpu;
+ unsigned long batch = zone_batchsize(zone);
- for (page = start; page < (start + size); page++) {
- set_page_zone(page, NODEZONE(nid, zone));
- set_page_count(page, 0);
- SetPageReserved(page);
- INIT_LIST_HEAD(&page->lru);
-#ifdef WANT_PAGE_VIRTUAL
- /* The shift won't overflow because ZONE_NORMAL is below 4G. */
- if (zone != ZONE_HIGHMEM)
- set_page_address(page, __va(start_pfn << PAGE_SHIFT));
+ for (cpu = 0; cpu < NR_CPUS; cpu++) {
+#ifdef CONFIG_NUMA
+ /* Early boot. Slab allocator not functional yet */
+ zone_pcp(zone, cpu) = &boot_pageset[cpu];
+ setup_pageset(&boot_pageset[cpu],0);
+#else
+ setup_pageset(zone_pcp(zone,cpu), batch);
#endif
- start_pfn++;
}
+ if (zone->present_pages)
+ printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%lu\n",
+ zone->name, zone->present_pages, batch);
}
-#ifndef __HAVE_ARCH_MEMMAP_INIT
-#define memmap_init(start, size, nid, zone, start_pfn) \
- memmap_init_zone((start), (size), (nid), (zone), (start_pfn))
-#endif
+static __meminit void init_currently_empty_zone(struct zone *zone,
+ unsigned long zone_start_pfn, unsigned long size)
+{
+ struct pglist_data *pgdat = zone->zone_pgdat;
+
+ zone_wait_table_init(zone, size);
+ pgdat->nr_zones = zone_idx(zone) + 1;
+
+ 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);
+}
/*
* Set up the zone data structures:
static void __init free_area_init_core(struct pglist_data *pgdat,
unsigned long *zones_size, unsigned long *zholes_size)
{
- unsigned long i, j;
- const unsigned long zone_required_alignment = 1UL << (MAX_ORDER-1);
- int cpu, nid = pgdat->node_id;
- struct page *lmem_map = pgdat->node_mem_map;
+ unsigned long j;
+ int nid = pgdat->node_id;
unsigned long zone_start_pfn = pgdat->node_start_pfn;
+ pgdat_resize_init(pgdat);
pgdat->nr_zones = 0;
init_waitqueue_head(&pgdat->kswapd_wait);
+ pgdat->kswapd_max_order = 0;
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = pgdat->node_zones + j;
unsigned long size, realsize;
- unsigned long batch;
- zone_table[NODEZONE(nid, j)] = zone;
realsize = size = zones_size[j];
if (zholes_size)
realsize -= zholes_size[j];
+ if (j < ZONE_HIGHMEM)
+ nr_kernel_pages += realsize;
+ nr_all_pages += realsize;
+
zone->spanned_pages = size;
zone->present_pages = realsize;
zone->name = zone_names[j];
spin_lock_init(&zone->lock);
spin_lock_init(&zone->lru_lock);
+ zone_seqlock_init(zone);
zone->zone_pgdat = pgdat;
zone->free_pages = 0;
zone->temp_priority = zone->prev_priority = DEF_PRIORITY;
- /*
- * The per-cpu-pages pools are set to around 1000th of the
- * size of the zone. But no more than 1/4 of a meg - there's
- * no point in going beyond the size of L2 cache.
- *
- * OK, so we don't know how big the cache is. So guess.
- */
- batch = zone->present_pages / 1024;
- if (batch * PAGE_SIZE > 256 * 1024)
- batch = (256 * 1024) / PAGE_SIZE;
- batch /= 4; /* We effectively *= 4 below */
- if (batch < 1)
- batch = 1;
-
- for (cpu = 0; cpu < NR_CPUS; cpu++) {
- struct per_cpu_pages *pcp;
-
- pcp = &zone->pageset[cpu].pcp[0]; /* hot */
- pcp->count = 0;
- pcp->low = 2 * batch;
- pcp->high = 6 * batch;
- pcp->batch = 1 * batch;
- INIT_LIST_HEAD(&pcp->list);
-
- pcp = &zone->pageset[cpu].pcp[1]; /* cold */
- pcp->count = 0;
- pcp->low = 0;
- pcp->high = 2 * batch;
- pcp->batch = 1 * batch;
- INIT_LIST_HEAD(&pcp->list);
- }
- printk(" %s zone: %lu pages, LIFO batch:%lu\n",
- zone_names[j], realsize, batch);
+ zone_pcp_init(zone);
INIT_LIST_HEAD(&zone->active_list);
INIT_LIST_HEAD(&zone->inactive_list);
- atomic_set(&zone->nr_scan_active, 0);
- atomic_set(&zone->nr_scan_inactive, 0);
+ zone->nr_scan_active = 0;
+ zone->nr_scan_inactive = 0;
zone->nr_active = 0;
zone->nr_inactive = 0;
+ atomic_set(&zone->reclaim_in_progress, 0);
if (!size)
continue;
- /*
- * The per-page waitqueue mechanism uses hashed waitqueues
- * per zone.
- */
- zone->wait_table_size = wait_table_size(size);
- zone->wait_table_bits =
- wait_table_bits(zone->wait_table_size);
- zone->wait_table = (wait_queue_head_t *)
- alloc_bootmem_node(pgdat, zone->wait_table_size
- * sizeof(wait_queue_head_t));
-
- for(i = 0; i < zone->wait_table_size; ++i)
- init_waitqueue_head(zone->wait_table + i);
-
- pgdat->nr_zones = j+1;
-
- zone->zone_mem_map = lmem_map;
- zone->zone_start_pfn = zone_start_pfn;
-
- if ((zone_start_pfn) & (zone_required_alignment-1))
- printk("BUG: wrong zone alignment, it will crash\n");
-
- memmap_init(lmem_map, size, nid, j, zone_start_pfn);
-
+ zonetable_add(zone, nid, j, zone_start_pfn, size);
+ init_currently_empty_zone(zone, zone_start_pfn, size);
zone_start_pfn += size;
- lmem_map += size;
+ }
+}
- for (i = 0; ; i++) {
- unsigned long bitmap_size;
+static void __init alloc_node_mem_map(struct pglist_data *pgdat)
+{
+ /* Skip empty nodes */
+ if (!pgdat->node_spanned_pages)
+ return;
- INIT_LIST_HEAD(&zone->free_area[i].free_list);
- if (i == MAX_ORDER-1) {
- zone->free_area[i].map = NULL;
- break;
- }
+#ifdef CONFIG_FLAT_NODE_MEM_MAP
+ /* ia64 gets its own node_mem_map, before this, without bootmem */
+ if (!pgdat->node_mem_map) {
+ unsigned long size, start, end;
+ struct page *map;
- /*
- * Page buddy system uses "index >> (i+1)",
- * where "index" is at most "size-1".
- *
- * The extra "+3" is to round down to byte
- * size (8 bits per byte assumption). Thus
- * we get "(size-1) >> (i+4)" as the last byte
- * we can access.
- *
- * The "+1" is because we want to round the
- * byte allocation up rather than down. So
- * we should have had a "+7" before we shifted
- * down by three. Also, we have to add one as
- * we actually _use_ the last bit (it's [0,n]
- * inclusive, not [0,n[).
- *
- * So we actually had +7+1 before we shift
- * down by 3. But (n+8) >> 3 == (n >> 3) + 1
- * (modulo overflows, which we do not have).
- *
- * Finally, we LONG_ALIGN because all bitmap
- * operations are on longs.
- */
- bitmap_size = (size-1) >> (i+4);
- bitmap_size = LONG_ALIGN(bitmap_size+1);
- zone->free_area[i].map =
- (unsigned long *) alloc_bootmem_node(pgdat, bitmap_size);
- }
+ /*
+ * The zone's endpoints aren't required to be MAX_ORDER
+ * aligned but the node_mem_map endpoints must be in order
+ * for the buddy allocator to function correctly.
+ */
+ start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1);
+ end = pgdat->node_start_pfn + pgdat->node_spanned_pages;
+ end = ALIGN(end, MAX_ORDER_NR_PAGES);
+ size = (end - start) * sizeof(struct page);
+ map = alloc_remap(pgdat->node_id, size);
+ if (!map)
+ map = alloc_bootmem_node(pgdat, size);
+ pgdat->node_mem_map = map + (pgdat->node_start_pfn - start);
}
+#ifdef CONFIG_FLATMEM
+ /*
+ * With no DISCONTIG, the global mem_map is just set as node 0's
+ */
+ if (pgdat == NODE_DATA(0))
+ mem_map = NODE_DATA(0)->node_mem_map;
+#endif
+#endif /* CONFIG_FLAT_NODE_MEM_MAP */
}
void __init free_area_init_node(int nid, struct pglist_data *pgdat,
- struct page *node_mem_map, unsigned long *zones_size,
- unsigned long node_start_pfn, unsigned long *zholes_size)
+ unsigned long *zones_size, unsigned long node_start_pfn,
+ unsigned long *zholes_size)
{
- unsigned long size;
-
pgdat->node_id = nid;
pgdat->node_start_pfn = node_start_pfn;
calculate_zone_totalpages(pgdat, zones_size, zholes_size);
- if (!node_mem_map) {
- size = (pgdat->node_spanned_pages + 1) * sizeof(struct page);
- node_mem_map = alloc_bootmem_node(pgdat, size);
- }
- pgdat->node_mem_map = node_mem_map;
+
+ alloc_node_mem_map(pgdat);
free_area_init_core(pgdat, zones_size, zholes_size);
}
-#ifndef CONFIG_DISCONTIGMEM
+#ifndef CONFIG_NEED_MULTIPLE_NODES
static bootmem_data_t contig_bootmem_data;
struct pglist_data contig_page_data = { .bdata = &contig_bootmem_data };
EXPORT_SYMBOL(contig_page_data);
+#endif
void __init free_area_init(unsigned long *zones_size)
{
- free_area_init_node(0, &contig_page_data, NULL, zones_size,
+ free_area_init_node(0, NODE_DATA(0), zones_size,
__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
- mem_map = contig_page_data.node_mem_map;
}
-#endif
#ifdef CONFIG_PROC_FS
{
pg_data_t *pgdat;
loff_t node = *pos;
-
- for (pgdat = pgdat_list; pgdat && node; pgdat = pgdat->pgdat_next)
+ for (pgdat = first_online_pgdat();
+ pgdat && node;
+ pgdat = next_online_pgdat(pgdat))
--node;
return pgdat;
pg_data_t *pgdat = (pg_data_t *)arg;
(*pos)++;
- return pgdat->pgdat_next;
+ return next_online_pgdat(pgdat);
}
static void frag_stop(struct seq_file *m, void *arg)
}
/*
- * This walks the freelist for each zone. Whilst this is slow, I'd rather
- * be slow here than slow down the fast path by keeping stats - mjbligh
+ * This walks the free areas for each zone.
*/
static int frag_show(struct seq_file *m, void *arg)
{
int order;
for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
- if (!zone->present_pages)
+ if (!populated_zone(zone))
continue;
spin_lock_irqsave(&zone->lock, flags);
seq_printf(m, "Node %d, zone %8s ", pgdat->node_id, zone->name);
- for (order = 0; order < MAX_ORDER; ++order) {
- unsigned long nr_bufs = 0;
- struct list_head *elem;
-
- list_for_each(elem, &(zone->free_area[order].free_list))
- ++nr_bufs;
- seq_printf(m, "%6lu ", nr_bufs);
- }
+ for (order = 0; order < MAX_ORDER; ++order)
+ seq_printf(m, "%6lu ", zone->free_area[order].nr_free);
spin_unlock_irqrestore(&zone->lock, flags);
seq_putc(m, '\n');
}
.show = frag_show,
};
+/*
+ * Output information about zones in @pgdat.
+ */
+static int zoneinfo_show(struct seq_file *m, void *arg)
+{
+ pg_data_t *pgdat = arg;
+ struct zone *zone;
+ struct zone *node_zones = pgdat->node_zones;
+ unsigned long flags;
+
+ for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; zone++) {
+ int i;
+
+ if (!populated_zone(zone))
+ continue;
+
+ spin_lock_irqsave(&zone->lock, flags);
+ seq_printf(m, "Node %d, zone %8s", pgdat->node_id, zone->name);
+ seq_printf(m,
+ "\n pages free %lu"
+ "\n min %lu"
+ "\n low %lu"
+ "\n high %lu"
+ "\n active %lu"
+ "\n inactive %lu"
+ "\n scanned %lu (a: %lu i: %lu)"
+ "\n spanned %lu"
+ "\n present %lu",
+ zone->free_pages,
+ zone->pages_min,
+ zone->pages_low,
+ zone->pages_high,
+ zone->nr_active,
+ zone->nr_inactive,
+ zone->pages_scanned,
+ zone->nr_scan_active, zone->nr_scan_inactive,
+ zone->spanned_pages,
+ zone->present_pages);
+ seq_printf(m,
+ "\n protection: (%lu",
+ zone->lowmem_reserve[0]);
+ for (i = 1; i < ARRAY_SIZE(zone->lowmem_reserve); i++)
+ seq_printf(m, ", %lu", zone->lowmem_reserve[i]);
+ seq_printf(m,
+ ")"
+ "\n pagesets");
+ for_each_online_cpu(i) {
+ struct per_cpu_pageset *pageset;
+ int j;
+
+ pageset = zone_pcp(zone, i);
+ for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
+ if (pageset->pcp[j].count)
+ break;
+ }
+ if (j == ARRAY_SIZE(pageset->pcp))
+ continue;
+ for (j = 0; j < ARRAY_SIZE(pageset->pcp); j++) {
+ seq_printf(m,
+ "\n cpu: %i pcp: %i"
+ "\n count: %i"
+ "\n high: %i"
+ "\n batch: %i",
+ i, j,
+ pageset->pcp[j].count,
+ pageset->pcp[j].high,
+ pageset->pcp[j].batch);
+ }
+#ifdef CONFIG_NUMA
+ seq_printf(m,
+ "\n numa_hit: %lu"
+ "\n numa_miss: %lu"
+ "\n numa_foreign: %lu"
+ "\n interleave_hit: %lu"
+ "\n local_node: %lu"
+ "\n other_node: %lu",
+ pageset->numa_hit,
+ pageset->numa_miss,
+ pageset->numa_foreign,
+ pageset->interleave_hit,
+ pageset->local_node,
+ pageset->other_node);
+#endif
+ }
+ seq_printf(m,
+ "\n all_unreclaimable: %u"
+ "\n prev_priority: %i"
+ "\n temp_priority: %i"
+ "\n start_pfn: %lu",
+ zone->all_unreclaimable,
+ zone->prev_priority,
+ zone->temp_priority,
+ zone->zone_start_pfn);
+ spin_unlock_irqrestore(&zone->lock, flags);
+ seq_putc(m, '\n');
+ }
+ return 0;
+}
+
+struct seq_operations zoneinfo_op = {
+ .start = frag_start, /* iterate over all zones. The same as in
+ * fragmentation. */
+ .next = frag_next,
+ .stop = frag_stop,
+ .show = zoneinfo_show,
+};
+
static char *vmstat_text[] = {
"nr_dirty",
"nr_writeback",
"pgpgout",
"pswpin",
"pswpout",
- "pgalloc_high",
+ "pgalloc_high",
"pgalloc_normal",
+ "pgalloc_dma32",
"pgalloc_dma",
+
"pgfree",
"pgactivate",
"pgdeactivate",
"pgfault",
"pgmajfault",
+
"pgrefill_high",
"pgrefill_normal",
+ "pgrefill_dma32",
"pgrefill_dma",
"pgsteal_high",
"pgsteal_normal",
+ "pgsteal_dma32",
"pgsteal_dma",
+
"pgscan_kswapd_high",
"pgscan_kswapd_normal",
-
+ "pgscan_kswapd_dma32",
"pgscan_kswapd_dma",
+
"pgscan_direct_high",
"pgscan_direct_normal",
+ "pgscan_direct_dma32",
"pgscan_direct_dma",
- "pginodesteal",
+ "pginodesteal",
"slabs_scanned",
"kswapd_steal",
"kswapd_inodesteal",
"allocstall",
"pgrotated",
+ "nr_bounce",
};
static void *vmstat_start(struct seq_file *m, loff_t *pos)
{
int cpu = (unsigned long)hcpu;
long *count;
+ unsigned long *src, *dest;
if (action == CPU_DEAD) {
+ int i;
+
/* Drain local pagecache count. */
count = &per_cpu(nr_pagecache_local, cpu);
atomic_add(*count, &nr_pagecache);
*count = 0;
local_irq_disable();
__drain_pages(cpu);
+
+ /* Add dead cpu's page_states to our own. */
+ dest = (unsigned long *)&__get_cpu_var(page_states);
+ src = (unsigned long *)&per_cpu(page_states, cpu);
+
+ for (i = 0; i < sizeof(struct page_state)/sizeof(unsigned long);
+ i++) {
+ dest[i] += src[i];
+ src[i] = 0;
+ }
+
local_irq_enable();
}
return NOTIFY_OK;
hotcpu_notifier(page_alloc_cpu_notify, 0);
}
-static unsigned long higherzone_val(struct zone *z, int max_zone,
- int alloc_type)
+/*
+ * calculate_totalreserve_pages - called when sysctl_lower_zone_reserve_ratio
+ * or min_free_kbytes changes.
+ */
+static void calculate_totalreserve_pages(void)
{
- int z_idx = zone_idx(z);
- struct zone *higherzone;
- unsigned long pages;
-
- /* there is no higher zone to get a contribution from */
- if (z_idx == MAX_NR_ZONES-1)
- return 0;
+ struct pglist_data *pgdat;
+ unsigned long reserve_pages = 0;
+ int i, j;
- higherzone = &z->zone_pgdat->node_zones[z_idx+1];
+ for_each_online_pgdat(pgdat) {
+ for (i = 0; i < MAX_NR_ZONES; i++) {
+ struct zone *zone = pgdat->node_zones + i;
+ unsigned long max = 0;
- /* We always start with the higher zone's protection value */
- pages = higherzone->protection[alloc_type];
+ /* Find valid and maximum lowmem_reserve in the zone */
+ for (j = i; j < MAX_NR_ZONES; j++) {
+ if (zone->lowmem_reserve[j] > max)
+ max = zone->lowmem_reserve[j];
+ }
- /*
- * We get a lower-zone-protection contribution only if there are
- * pages in the higher zone and if we're not the highest zone
- * in the current zonelist. e.g., never happens for GFP_DMA. Happens
- * only for ZONE_DMA in a GFP_KERNEL allocation and happens for ZONE_DMA
- * and ZONE_NORMAL for a GFP_HIGHMEM allocation.
- */
- if (higherzone->present_pages && z_idx < alloc_type)
- pages += higherzone->pages_low * sysctl_lower_zone_protection;
+ /* we treat pages_high as reserved pages. */
+ max += zone->pages_high;
- return pages;
+ if (max > zone->present_pages)
+ max = zone->present_pages;
+ reserve_pages += max;
+ }
+ }
+ totalreserve_pages = reserve_pages;
}
/*
- * setup_per_zone_protection - called whenver min_free_kbytes or
- * sysctl_lower_zone_protection changes. Ensures that each zone
- * has a correct pages_protected value, so an adequate number of
+ * setup_per_zone_lowmem_reserve - called whenever
+ * sysctl_lower_zone_reserve_ratio changes. Ensures that each zone
+ * has a correct pages reserved value, so an adequate number of
* pages are left in the zone after a successful __alloc_pages().
- *
- * This algorithm is way confusing. I tries to keep the same behavior
- * as we had with the incremental min iterative algorithm.
*/
-static void setup_per_zone_protection(void)
+static void setup_per_zone_lowmem_reserve(void)
{
struct pglist_data *pgdat;
- struct zone *zones, *zone;
- int max_zone;
- int i, j;
+ int j, idx;
- for_each_pgdat(pgdat) {
- zones = pgdat->node_zones;
+ for_each_online_pgdat(pgdat) {
+ for (j = 0; j < MAX_NR_ZONES; j++) {
+ struct zone *zone = pgdat->node_zones + j;
+ unsigned long present_pages = zone->present_pages;
- for (i = 0, max_zone = 0; i < MAX_NR_ZONES; i++)
- if (zones[i].present_pages)
- max_zone = i;
+ zone->lowmem_reserve[j] = 0;
- /*
- * For each of the different allocation types:
- * GFP_DMA -> GFP_KERNEL -> GFP_HIGHMEM
- */
- for (i = 0; i < MAX_NR_ZONES; i++) {
- /*
- * For each of the zones:
- * ZONE_HIGHMEM -> ZONE_NORMAL -> ZONE_DMA
- */
- for (j = MAX_NR_ZONES-1; j >= 0; j--) {
- zone = &zones[j];
-
- /*
- * We never protect zones that don't have memory
- * in them (j>max_zone) or zones that aren't in
- * the zonelists for a certain type of
- * allocation (j>i). We have to assign these to
- * zero because the lower zones take
- * contributions from the higher zones.
- */
- if (j > max_zone || j > i) {
- zone->protection[i] = 0;
- continue;
- }
- /*
- * The contribution of the next higher zone
- */
- zone->protection[i] = higherzone_val(zone,
- max_zone, i);
- zone->protection[i] += zone->pages_low;
+ for (idx = j-1; idx >= 0; idx--) {
+ struct zone *lower_zone;
+
+ if (sysctl_lowmem_reserve_ratio[idx] < 1)
+ sysctl_lowmem_reserve_ratio[idx] = 1;
+
+ lower_zone = pgdat->node_zones + idx;
+ lower_zone->lowmem_reserve[j] = present_pages /
+ sysctl_lowmem_reserve_ratio[idx];
+ present_pages += lower_zone->present_pages;
}
}
}
+
+ /* update totalreserve_pages */
+ calculate_totalreserve_pages();
}
/*
* that the pages_{min,low,high} values for each zone are set correctly
* with respect to min_free_kbytes.
*/
-static void setup_per_zone_pages_min(void)
+void setup_per_zone_pages_min(void)
{
unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
unsigned long lowmem_pages = 0;
}
for_each_zone(zone) {
+ u64 tmp;
+
spin_lock_irqsave(&zone->lru_lock, flags);
+ tmp = (u64)pages_min * zone->present_pages;
+ do_div(tmp, lowmem_pages);
if (is_highmem(zone)) {
/*
- * Often, highmem doesn't need to reserve any pages.
- * But the pages_min/low/high values are also used for
- * batching up page reclaim activity so we need a
- * decent value here.
+ * __GFP_HIGH and PF_MEMALLOC allocations usually don't
+ * need highmem pages, so cap pages_min to a small
+ * value here.
+ *
+ * The (pages_high-pages_low) and (pages_low-pages_min)
+ * deltas controls asynch page reclaim, and so should
+ * not be capped for highmem.
*/
int min_pages;
min_pages = 128;
zone->pages_min = min_pages;
} else {
- /* if it's a lowmem zone, reserve a number of pages
+ /*
+ * If it's a lowmem zone, reserve a number of pages
* proportionate to the zone's size.
*/
- zone->pages_min = (pages_min * zone->present_pages) /
- lowmem_pages;
+ zone->pages_min = tmp;
}
- zone->pages_low = zone->pages_min * 2;
- zone->pages_high = zone->pages_min * 3;
+ zone->pages_low = zone->pages_min + (tmp >> 2);
+ zone->pages_high = zone->pages_min + (tmp >> 1);
spin_unlock_irqrestore(&zone->lru_lock, flags);
}
+
+ /* update totalreserve_pages */
+ calculate_totalreserve_pages();
}
/*
* Initialise min_free_kbytes.
*
* For small machines we want it small (128k min). For large machines
- * we want it large (16MB max). But it is not linear, because network
+ * we want it large (64MB max). But it is not linear, because network
* bandwidth does not increase linearly with machine size. We use
*
- * min_free_kbytes = sqrt(lowmem_kbytes)
+ * min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy:
+ * min_free_kbytes = sqrt(lowmem_kbytes * 16)
*
* which yields
*
- * 16MB: 128k
- * 32MB: 181k
- * 64MB: 256k
- * 128MB: 362k
- * 256MB: 512k
- * 512MB: 724k
- * 1024MB: 1024k
- * 2048MB: 1448k
- * 4096MB: 2048k
- * 8192MB: 2896k
- * 16384MB: 4096k
+ * 16MB: 512k
+ * 32MB: 724k
+ * 64MB: 1024k
+ * 128MB: 1448k
+ * 256MB: 2048k
+ * 512MB: 2896k
+ * 1024MB: 4096k
+ * 2048MB: 5792k
+ * 4096MB: 8192k
+ * 8192MB: 11584k
+ * 16384MB: 16384k
*/
static int __init init_per_zone_pages_min(void)
{
lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10);
- min_free_kbytes = int_sqrt(lowmem_kbytes);
+ min_free_kbytes = int_sqrt(lowmem_kbytes * 16);
if (min_free_kbytes < 128)
min_free_kbytes = 128;
- if (min_free_kbytes > 16384)
- min_free_kbytes = 16384;
+ if (min_free_kbytes > 65536)
+ min_free_kbytes = 65536;
setup_per_zone_pages_min();
- setup_per_zone_protection();
+ setup_per_zone_lowmem_reserve();
return 0;
}
module_init(init_per_zone_pages_min)
* changes.
*/
int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *length)
+ struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
- proc_dointvec(table, write, file, buffer, length);
+ proc_dointvec(table, write, file, buffer, length, ppos);
setup_per_zone_pages_min();
- setup_per_zone_protection();
return 0;
}
/*
- * lower_zone_protection_sysctl_handler - just a wrapper around
- * proc_dointvec() so that we can call setup_per_zone_protection()
- * whenever sysctl_lower_zone_protection changes.
+ * lowmem_reserve_ratio_sysctl_handler - just a wrapper around
+ * proc_dointvec() so that we can call setup_per_zone_lowmem_reserve()
+ * whenever sysctl_lowmem_reserve_ratio changes.
+ *
+ * The reserve ratio obviously has absolutely no relation with the
+ * pages_min watermarks. The lowmem reserve ratio can only make sense
+ * if in function of the boot time zone sizes.
+ */
+int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
+ struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+{
+ proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+ setup_per_zone_lowmem_reserve();
+ return 0;
+}
+
+/*
+ * percpu_pagelist_fraction - changes the pcp->high for each zone on each
+ * cpu. It is the fraction of total pages in each zone that a hot per cpu pagelist
+ * can have before it gets flushed back to buddy allocator.
*/
-int lower_zone_protection_sysctl_handler(ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *length)
+
+int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
+ struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
{
- proc_dointvec_minmax(table, write, file, buffer, length);
- setup_per_zone_protection();
+ struct zone *zone;
+ unsigned int cpu;
+ int ret;
+
+ ret = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+ if (!write || (ret == -EINVAL))
+ return ret;
+ for_each_zone(zone) {
+ for_each_online_cpu(cpu) {
+ unsigned long high;
+ high = zone->present_pages / percpu_pagelist_fraction;
+ setup_pagelist_highmark(zone_pcp(zone, cpu), high);
+ }
+ }
return 0;
}
+
+__initdata int hashdist = HASHDIST_DEFAULT;
+
+#ifdef CONFIG_NUMA
+static int __init set_hashdist(char *str)
+{
+ if (!str)
+ return 0;
+ hashdist = simple_strtoul(str, &str, 0);
+ return 1;
+}
+__setup("hashdist=", set_hashdist);
+#endif
+
+/*
+ * allocate a large system hash table from bootmem
+ * - it is assumed that the hash table must contain an exact power-of-2
+ * quantity of entries
+ * - limit is the number of hash buckets, not the total allocation size
+ */
+void *__init alloc_large_system_hash(const char *tablename,
+ unsigned long bucketsize,
+ unsigned long numentries,
+ int scale,
+ int flags,
+ unsigned int *_hash_shift,
+ unsigned int *_hash_mask,
+ unsigned long limit)
+{
+ unsigned long long max = limit;
+ unsigned long log2qty, size;
+ void *table = NULL;
+
+ /* allow the kernel cmdline to have a say */
+ if (!numentries) {
+ /* round applicable memory size up to nearest megabyte */
+ numentries = (flags & HASH_HIGHMEM) ? nr_all_pages : nr_kernel_pages;
+ numentries += (1UL << (20 - PAGE_SHIFT)) - 1;
+ numentries >>= 20 - PAGE_SHIFT;
+ numentries <<= 20 - PAGE_SHIFT;
+
+ /* limit to 1 bucket per 2^scale bytes of low memory */
+ if (scale > PAGE_SHIFT)
+ numentries >>= (scale - PAGE_SHIFT);
+ else
+ numentries <<= (PAGE_SHIFT - scale);
+ }
+ numentries = roundup_pow_of_two(numentries);
+
+ /* limit allocation size to 1/16 total memory by default */
+ if (max == 0) {
+ max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4;
+ do_div(max, bucketsize);
+ }
+
+ if (numentries > max)
+ numentries = max;
+
+ log2qty = long_log2(numentries);
+
+ do {
+ size = bucketsize << log2qty;
+ if (flags & HASH_EARLY)
+ table = alloc_bootmem(size);
+ else if (hashdist)
+ table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL);
+ else {
+ unsigned long order;
+ for (order = 0; ((1UL << order) << PAGE_SHIFT) < size; order++)
+ ;
+ table = (void*) __get_free_pages(GFP_ATOMIC, order);
+ }
+ } while (!table && size > PAGE_SIZE && --log2qty);
+
+ if (!table)
+ panic("Failed to allocate %s hash table\n", tablename);
+
+ printk("%s hash table entries: %d (order: %d, %lu bytes)\n",
+ tablename,
+ (1U << log2qty),
+ long_log2(size) - PAGE_SHIFT,
+ size);
+
+ if (_hash_shift)
+ *_hash_shift = log2qty;
+ if (_hash_mask)
+ *_hash_mask = (1 << log2qty) - 1;
+
+ return table;
+}
+
+#ifdef CONFIG_OUT_OF_LINE_PFN_TO_PAGE
+/*
+ * pfn <-> page translation. out-of-line version.
+ * (see asm-generic/memory_model.h)
+ */
+#if defined(CONFIG_FLATMEM)
+struct page *pfn_to_page(unsigned long pfn)
+{
+ return mem_map + (pfn - ARCH_PFN_OFFSET);
+}
+unsigned long page_to_pfn(struct page *page)
+{
+ return (page - mem_map) + ARCH_PFN_OFFSET;
+}
+#elif defined(CONFIG_DISCONTIGMEM)
+struct page *pfn_to_page(unsigned long pfn)
+{
+ int nid = arch_pfn_to_nid(pfn);
+ return NODE_DATA(nid)->node_mem_map + arch_local_page_offset(pfn,nid);
+}
+unsigned long page_to_pfn(struct page *page)
+{
+ struct pglist_data *pgdat = NODE_DATA(page_to_nid(page));
+ return (page - pgdat->node_mem_map) + pgdat->node_start_pfn;
+}
+#elif defined(CONFIG_SPARSEMEM)
+struct page *pfn_to_page(unsigned long pfn)
+{
+ return __section_mem_map_addr(__pfn_to_section(pfn)) + pfn;
+}
+
+unsigned long page_to_pfn(struct page *page)
+{
+ long section_id = page_to_section(page);
+ return page - __section_mem_map_addr(__nr_to_section(section_id));
+}
+#endif /* CONFIG_FLATMEM/DISCONTIGMME/SPARSEMEM */
+EXPORT_SYMBOL(pfn_to_page);
+EXPORT_SYMBOL(page_to_pfn);
+#endif /* CONFIG_OUT_OF_LINE_PFN_TO_PAGE */
git://git.onelab.eu / linux-2.6.git / blobdiff