#include <linux/nodemask.h>
#include <linux/vmalloc.h>
#include <linux/mempolicy.h>
+#include <linux/stop_machine.h>
#include <asm/tlbflush.h>
+#include <asm/div64.h>
#include "internal.h"
/*
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 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;
+unsigned long __meminitdata nr_kernel_pages;
+unsigned long __meminitdata nr_all_pages;
#ifdef CONFIG_DEBUG_VM
static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
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;
* 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) {
+static inline unsigned long page_order(struct page *page)
+{
return page_private(page);
}
-static inline void set_page_order(struct page *page, int order) {
+static inline void set_page_order(struct page *page, int order)
+{
set_page_private(page, order);
- __SetPagePrivate(page);
+ __SetPageBuddy(page);
}
static inline void rmv_page_order(struct page *page)
{
- __ClearPagePrivate(page);
+ __ClearPageBuddy(page);
set_page_private(page, 0);
}
* 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 free &&
- * (c) the buddy is on the buddy system &&
- * (d) a page and its buddy have the same order.
- * for recording page's order, we use page_private(page) and PG_private.
+ * (b) the buddy is in the buddy system &&
+ * (c) a page and its buddy have the same order &&
+ * (d) a page and its buddy are in the same zone.
*
+ * For recording whether a page is in the buddy system, we use PG_buddy.
+ * Setting, clearing, and testing PG_buddy is serialized by zone->lock.
+ *
+ * For recording page's order, we use page_private(page).
*/
-static inline int page_is_buddy(struct page *page, int order)
+static inline int page_is_buddy(struct page *page, struct page *buddy,
+ int order)
{
#ifdef CONFIG_HOLES_IN_ZONE
- if (!pfn_valid(page_to_pfn(page)))
+ if (!pfn_valid(page_to_pfn(buddy)))
return 0;
#endif
- if (PagePrivate(page) &&
- (page_order(page) == order) &&
- page_count(page) == 0)
- return 1;
- return 0;
+ if (page_zone_id(page) != page_zone_id(buddy))
+ return 0;
+
+ if (PageBuddy(buddy) && page_order(buddy) == order) {
+ BUG_ON(page_count(buddy) != 0);
+ return 1;
+ }
+ return 0;
}
/*
* as necessary, plus some accounting needed to play nicely with other
* parts of the VM system.
* At each level, we keep a list of pages, which are heads of continuous
- * free pages of length of (1 << order) and marked with PG_Private.Page's
+ * 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
struct page *buddy;
buddy = __page_find_buddy(page, page_idx, order);
- if (!page_is_buddy(buddy, order))
+ if (!page_is_buddy(page, buddy, order))
break; /* Move the buddy up one level. */
list_del(&buddy->lru);
1 << PG_slab |
1 << PG_swapcache |
1 << PG_writeback |
- 1 << PG_reserved ))))
+ 1 << PG_reserved |
+ 1 << PG_buddy ))))
bad_page(page);
if (PageDirty(page))
__ClearPageDirty(page);
1 << PG_slab |
1 << PG_swapcache |
1 << PG_writeback |
- 1 << PG_reserved ))))
+ 1 << PG_reserved |
+ 1 << PG_buddy ))))
bad_page(page);
/*
goto got_pg;
do {
- if (cpuset_zone_allowed(*z, gfp_mask))
- wakeup_kswapd(*z, order);
+ wakeup_kswapd(*z, order);
} while (*(++z));
/*
alloc_flags |= ALLOC_HARDER;
if (gfp_mask & __GFP_HIGH)
alloc_flags |= ALLOC_HIGH;
- alloc_flags |= ALLOC_CPUSET;
+ if (wait)
+ alloc_flags |= ALLOC_CPUSET;
/*
* Go through the zonelist again. Let __GFP_HIGH and allocations
}
for_each_zone(zone) {
- unsigned long nr, flags, order, total = 0;
+ unsigned long nr[MAX_ORDER], flags, order, total = 0;
show_node(zone);
printk("%s: ", zone->name);
spin_lock_irqsave(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
- nr = zone->free_area[order].nr_free;
- total += nr << order;
- printk("%lu*%lukB ", nr, K(1UL) << order);
+ nr[order] = zone->free_area[order].nr_free;
+ total += nr[order] << order;
}
spin_unlock_irqrestore(&zone->lock, flags);
+ for (order = 0; order < MAX_ORDER; order++)
+ printk("%lu*%lukB ", nr[order], K(1UL) << order);
printk("= %lukB\n", K(total));
}
*
* Add all populated zones of a node to the zonelist.
*/
-static int __init build_zonelists_node(pg_data_t *pgdat,
+static int __meminit build_zonelists_node(pg_data_t *pgdat,
struct zonelist *zonelist, int nr_zones, int zone_type)
{
struct zone *zone;
#ifdef CONFIG_NUMA
#define MAX_NODE_LOAD (num_online_nodes())
-static int __initdata node_load[MAX_NUMNODES];
+static int __meminitdata node_load[MAX_NUMNODES];
/**
* find_next_best_node - find the next node that should appear in a given node's fallback list
* @node: node whose fallback list we're appending
* on them otherwise.
* It returns -1 if no node is found.
*/
-static int __init find_next_best_node(int node, nodemask_t *used_node_mask)
+static int __meminit find_next_best_node(int node, nodemask_t *used_node_mask)
{
int n, val;
int min_val = INT_MAX;
return best_node;
}
-static void __init build_zonelists(pg_data_t *pgdat)
+static void __meminit build_zonelists(pg_data_t *pgdat)
{
int i, j, k, node, local_node;
int prev_node, load;
#else /* CONFIG_NUMA */
-static void __init build_zonelists(pg_data_t *pgdat)
+static void __meminit build_zonelists(pg_data_t *pgdat)
{
int i, j, k, node, local_node;
#endif /* CONFIG_NUMA */
-void __init build_all_zonelists(void)
+/* return values int ....just for stop_machine_run() */
+static int __meminit __build_all_zonelists(void *dummy)
{
- int i;
+ int nid;
+ for_each_online_node(nid)
+ build_zonelists(NODE_DATA(nid));
+ return 0;
+}
- for_each_online_node(i)
- build_zonelists(NODE_DATA(i));
- printk("Built %i zonelists\n", num_online_nodes());
- cpuset_init_current_mems_allowed();
+void __meminit build_all_zonelists(void)
+{
+ if (system_state == SYSTEM_BOOTING) {
+ __build_all_zonelists(0);
+ cpuset_init_current_mems_allowed();
+ } else {
+ /* we have to stop all cpus to guaranntee 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. Total pages: %ld\n",
+ num_online_nodes(), vm_total_pages);
}
/*
*/
#define PAGES_PER_WAITQUEUE 256
-static inline unsigned long wait_table_size(unsigned long pages)
+#ifndef CONFIG_MEMORY_HOTPLUG
+static inline unsigned long wait_table_hash_nr_entries(unsigned long pages)
{
unsigned long size = 1;
return max(size, 4UL);
}
+#else
+/*
+ * A zone's size might be changed by hot-add, so it is not possible to determine
+ * a suitable size for its wait_table. So we use the maximum size now.
+ *
+ * The max wait table size = 4096 x sizeof(wait_queue_head_t). ie:
+ *
+ * i386 (preemption config) : 4096 x 16 = 64Kbyte.
+ * ia64, x86-64 (no preemption): 4096 x 20 = 80Kbyte.
+ * ia64, x86-64 (preemption) : 4096 x 24 = 96Kbyte.
+ *
+ * The maximum entries are prepared when a zone's memory is (512K + 256) pages
+ * or more by the traditional way. (See above). It equals:
+ *
+ * i386, x86-64, powerpc(4K page size) : = ( 2G + 1M)byte.
+ * ia64(16K page size) : = ( 8G + 4M)byte.
+ * powerpc (64K page size) : = (32G +16M)byte.
+ */
+static inline unsigned long wait_table_hash_nr_entries(unsigned long pages)
+{
+ return 4096UL;
+}
+#endif
/*
* This is an integer logarithm so that shifts can be used later
}
}
-static int __cpuinit pageset_cpuup_callback(struct notifier_block *nfb,
+static int pageset_cpuup_callback(struct notifier_block *nfb,
unsigned long action,
void *hcpu)
{
#endif
static __meminit
-void zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
+int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
{
int i;
struct pglist_data *pgdat = zone->zone_pgdat;
+ size_t alloc_size;
/*
* 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));
+ zone->wait_table_hash_nr_entries =
+ wait_table_hash_nr_entries(zone_size_pages);
+ zone->wait_table_bits =
+ wait_table_bits(zone->wait_table_hash_nr_entries);
+ alloc_size = zone->wait_table_hash_nr_entries
+ * sizeof(wait_queue_head_t);
+
+ if (system_state == SYSTEM_BOOTING) {
+ zone->wait_table = (wait_queue_head_t *)
+ alloc_bootmem_node(pgdat, alloc_size);
+ } else {
+ /*
+ * This case means that a zone whose size was 0 gets new memory
+ * via memory hot-add.
+ * But it may be the case that a new node was hot-added. In
+ * this case vmalloc() will not be able to use this new node's
+ * memory - this wait_table must be initialized to use this new
+ * node itself as well.
+ * To use this new node's memory, further consideration will be
+ * necessary.
+ */
+ zone->wait_table = (wait_queue_head_t *)vmalloc(alloc_size);
+ }
+ if (!zone->wait_table)
+ return -ENOMEM;
- for(i = 0; i < zone->wait_table_size; ++i)
+ for(i = 0; i < zone->wait_table_hash_nr_entries; ++i)
init_waitqueue_head(zone->wait_table + i);
+
+ return 0;
}
static __meminit void zone_pcp_init(struct zone *zone)
zone->name, zone->present_pages, batch);
}
-static __meminit void init_currently_empty_zone(struct zone *zone,
- unsigned long zone_start_pfn, unsigned long size)
+__meminit int 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);
+ int ret;
+ ret = zone_wait_table_init(zone, size);
+ if (ret)
+ return ret;
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);
+
+ return 0;
}
/*
* - mark all memory queues empty
* - clear the memory bitmaps
*/
-static void __init free_area_init_core(struct pglist_data *pgdat,
+static void __meminit free_area_init_core(struct pglist_data *pgdat,
unsigned long *zones_size, unsigned long *zholes_size)
{
unsigned long j;
int nid = pgdat->node_id;
unsigned long zone_start_pfn = pgdat->node_start_pfn;
+ int ret;
pgdat_resize_init(pgdat);
pgdat->nr_zones = 0;
continue;
zonetable_add(zone, nid, j, zone_start_pfn, size);
- init_currently_empty_zone(zone, zone_start_pfn, size);
+ ret = init_currently_empty_zone(zone, zone_start_pfn, size);
+ BUG_ON(ret);
zone_start_pfn += size;
}
}
#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;
+ unsigned long size, start, end;
struct page *map;
- size = (pgdat->node_spanned_pages + 1) * sizeof(struct page);
+ /*
+ * 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_mem_map = map + (pgdat->node_start_pfn - start);
}
#ifdef CONFIG_FLATMEM
/*
#endif /* CONFIG_FLAT_NODE_MEM_MAP */
}
-void __init free_area_init_node(int nid, struct pglist_data *pgdat,
+void __meminit free_area_init_node(int nid, struct pglist_data *pgdat,
unsigned long *zones_size, unsigned long node_start_pfn,
unsigned long *zholes_size)
{
hotcpu_notifier(page_alloc_cpu_notify, 0);
}
+/*
+ * calculate_totalreserve_pages - called when sysctl_lower_zone_reserve_ratio
+ * or min_free_kbytes changes.
+ */
+static void calculate_totalreserve_pages(void)
+{
+ struct pglist_data *pgdat;
+ unsigned long reserve_pages = 0;
+ int i, j;
+
+ for_each_online_pgdat(pgdat) {
+ for (i = 0; i < MAX_NR_ZONES; i++) {
+ struct zone *zone = pgdat->node_zones + i;
+ unsigned long max = 0;
+
+ /* 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 treat pages_high as reserved pages. */
+ max += zone->pages_high;
+
+ if (max > zone->present_pages)
+ max = zone->present_pages;
+ reserve_pages += max;
+ }
+ }
+ totalreserve_pages = reserve_pages;
+}
+
/*
* setup_per_zone_lowmem_reserve - called whenever
* sysctl_lower_zone_reserve_ratio changes. Ensures that each zone
}
}
}
+
+ /* update totalreserve_pages */
+ calculate_totalreserve_pages();
}
/*
}
for_each_zone(zone) {
- unsigned long tmp;
+ u64 tmp;
+
spin_lock_irqsave(&zone->lru_lock, flags);
- tmp = (pages_min * zone->present_pages) / lowmem_pages;
+ tmp = (u64)pages_min * zone->present_pages;
+ do_div(tmp, lowmem_pages);
if (is_highmem(zone)) {
/*
* __GFP_HIGH and PF_MEMALLOC allocations usually don't
zone->pages_min = tmp;
}
- zone->pages_low = zone->pages_min + tmp / 4;
- zone->pages_high = zone->pages_min + tmp / 2;
+ 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();
}
/*
}
#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);
+ return __pfn_to_page(pfn);
}
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));
+ return __page_to_pfn(page);
}
-#endif /* CONFIG_FLATMEM/DISCONTIGMME/SPARSEMEM */
EXPORT_SYMBOL(pfn_to_page);
EXPORT_SYMBOL(page_to_pfn);
#endif /* CONFIG_OUT_OF_LINE_PFN_TO_PAGE */