#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
+#include <linux/jiffies.h>
#include <linux/bootmem.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
+#include <linux/oom.h>
#include <linux/notifier.h>
#include <linux/topology.h>
#include <linux/sysctl.h>
#include <linux/backing-dev.h>
#include <linux/fault-inject.h>
#include <linux/page-isolation.h>
+#include <linux/memcontrol.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
/*
- * MAX_ACTIVE_REGIONS determines the maxmimum number of distinct
+ * MAX_ACTIVE_REGIONS determines the maximum number of distinct
* ranges of memory (RAM) that may be registered with add_active_range().
* Ranges passed to add_active_range() will be merged if possible
* so the number of times add_active_range() can be called is
static void bad_page(struct page *page)
{
- printk(KERN_EMERG "Bad page state in process '%s'\n"
- KERN_EMERG "page:%p flags:0x%0*lx mapping:%p mapcount:%d count:%d\n"
- KERN_EMERG "Trying to fix it up, but a reboot is needed\n"
- KERN_EMERG "Backtrace:\n",
+ void *pc = page_get_page_cgroup(page);
+
+ printk(KERN_EMERG "Bad page state in process '%s'\n" KERN_EMERG
+ "page:%p flags:0x%0*lx mapping:%p mapcount:%d count:%d\n",
current->comm, page, (int)(2*sizeof(unsigned long)),
(unsigned long)page->flags, page->mapping,
page_mapcount(page), page_count(page));
+ if (pc) {
+ printk(KERN_EMERG "cgroup:%p\n", pc);
+ page_reset_bad_cgroup(page);
+ }
+ printk(KERN_EMERG "Trying to fix it up, but a reboot is needed\n"
+ KERN_EMERG "Backtrace:\n");
dump_stack();
page->flags &= ~(1 << PG_lru |
1 << PG_private |
{
int i;
- VM_BUG_ON((gfp_flags & (__GFP_WAIT | __GFP_HIGHMEM)) == __GFP_HIGHMEM);
/*
* clear_highpage() will use KM_USER0, so it's a bug to use __GFP_ZERO
* and __GFP_HIGHMEM from hard or soft interrupt context.
{
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
+ (page_get_page_cgroup(page) != NULL) |
(page_count(page) != 0) |
(page->flags & (
1 << PG_lru |
struct list_head *list, int order)
{
spin_lock(&zone->lock);
- zone->all_unreclaimable = 0;
+ zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
zone->pages_scanned = 0;
while (count--) {
struct page *page;
static void free_one_page(struct zone *zone, struct page *page, int order)
{
spin_lock(&zone->lock);
- zone->all_unreclaimable = 0;
+ zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
zone->pages_scanned = 0;
__free_one_page(page, zone, order);
spin_unlock(&zone->lock);
/*
* permit the bootmem allocator to evade page validation on high-order frees
*/
-void fastcall __init __free_pages_bootmem(struct page *page, unsigned int order)
+void __init __free_pages_bootmem(struct page *page, unsigned int order)
{
if (order == 0) {
__ClearPageReserved(page);
{
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
+ (page_get_page_cgroup(page) != NULL) |
(page_count(page) != 0) |
(page->flags & (
1 << PG_lru |
return move_freepages(zone, start_page, end_page, migratetype);
}
-/* Return the page with the lowest PFN in the list */
-static struct page *min_page(struct list_head *list)
-{
- unsigned long min_pfn = -1UL;
- struct page *min_page = NULL, *page;;
-
- list_for_each_entry(page, list, lru) {
- unsigned long pfn = page_to_pfn(page);
- if (pfn < min_pfn) {
- min_pfn = pfn;
- min_page = page;
- }
- }
-
- return min_page;
-}
-
/* Remove an element from the buddy allocator from the fallback list */
static struct page *__rmqueue_fallback(struct zone *zone, int order,
int start_migratetype)
if (list_empty(&area->free_list[migratetype]))
continue;
- /* Bias kernel allocations towards low pfns */
page = list_entry(area->free_list[migratetype].next,
struct page, lru);
- if (unlikely(start_migratetype != MIGRATE_MOVABLE))
- page = min_page(&area->free_list[migratetype]);
area->nr_free--;
/*
struct page *page = __rmqueue(zone, order, migratetype);
if (unlikely(page == NULL))
break;
+
+ /*
+ * Split buddy pages returned by expand() are received here
+ * in physical page order. The page is added to the callers and
+ * list and the list head then moves forward. From the callers
+ * perspective, the linked list is ordered by page number in
+ * some conditions. This is useful for IO devices that can
+ * merge IO requests if the physical pages are ordered
+ * properly.
+ */
list_add(&page->lru, list);
set_page_private(page, migratetype);
+ list = &page->lru;
}
spin_unlock(&zone->lock);
return i;
}
#endif
-static void __drain_pages(unsigned int cpu)
+/*
+ * Drain pages of the indicated processor.
+ *
+ * The processor must either be the current processor and the
+ * thread pinned to the current processor or a processor that
+ * is not online.
+ */
+static void drain_pages(unsigned int cpu)
{
unsigned long flags;
struct zone *zone;
- int i;
for_each_zone(zone) {
struct per_cpu_pageset *pset;
+ struct per_cpu_pages *pcp;
if (!populated_zone(zone))
continue;
pset = zone_pcp(zone, cpu);
- for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
- struct per_cpu_pages *pcp;
-
- pcp = &pset->pcp[i];
- local_irq_save(flags);
- free_pages_bulk(zone, pcp->count, &pcp->list, 0);
- pcp->count = 0;
- local_irq_restore(flags);
- }
+
+ pcp = &pset->pcp;
+ local_irq_save(flags);
+ free_pages_bulk(zone, pcp->count, &pcp->list, 0);
+ pcp->count = 0;
+ local_irq_restore(flags);
}
}
+/*
+ * Spill all of this CPU's per-cpu pages back into the buddy allocator.
+ */
+void drain_local_pages(void *arg)
+{
+ drain_pages(smp_processor_id());
+}
+
+/*
+ * Spill all the per-cpu pages from all CPUs back into the buddy allocator
+ */
+void drain_all_pages(void)
+{
+ on_each_cpu(drain_local_pages, NULL, 0, 1);
+}
+
#ifdef CONFIG_HIBERNATION
void mark_free_pages(struct zone *zone)
}
#endif /* CONFIG_PM */
-/*
- * Spill all of this CPU's per-cpu pages back into the buddy allocator.
- */
-void drain_local_pages(void)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- __drain_pages(smp_processor_id());
- local_irq_restore(flags);
-}
-
-void smp_drain_local_pages(void *arg)
-{
- drain_local_pages();
-}
-
-/*
- * Spill all the per-cpu pages from all CPUs back into the buddy allocator
- */
-void drain_all_local_pages(void)
-{
- unsigned long flags;
-
- local_irq_save(flags);
- __drain_pages(smp_processor_id());
- local_irq_restore(flags);
-
- smp_call_function(smp_drain_local_pages, NULL, 0, 1);
-}
-
/*
* Free a 0-order page
*/
-static void fastcall free_hot_cold_page(struct page *page, int cold)
+static void free_hot_cold_page(struct page *page, int cold)
{
struct zone *zone = page_zone(page);
struct per_cpu_pages *pcp;
arch_free_page(page, 0);
kernel_map_pages(page, 1, 0);
- pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
+ pcp = &zone_pcp(zone, get_cpu())->pcp;
local_irq_save(flags);
__count_vm_event(PGFREE);
- list_add(&page->lru, &pcp->list);
+ if (cold)
+ list_add_tail(&page->lru, &pcp->list);
+ else
+ list_add(&page->lru, &pcp->list);
set_page_private(page, get_pageblock_migratetype(page));
pcp->count++;
if (pcp->count >= pcp->high) {
put_cpu();
}
-void fastcall free_hot_page(struct page *page)
+void free_hot_page(struct page *page)
{
free_hot_cold_page(page, 0);
}
-void fastcall free_cold_page(struct page *page)
+void free_cold_page(struct page *page)
{
free_hot_cold_page(page, 1);
}
if (likely(order == 0)) {
struct per_cpu_pages *pcp;
- pcp = &zone_pcp(zone, cpu)->pcp[cold];
+ pcp = &zone_pcp(zone, cpu)->pcp;
local_irq_save(flags);
if (!pcp->count) {
pcp->count = rmqueue_bulk(zone, 0,
}
/* Find a page of the appropriate migrate type */
- list_for_each_entry(page, &pcp->list, lru)
- if (page_private(page) == migratetype)
- break;
+ if (cold) {
+ list_for_each_entry_reverse(page, &pcp->list, lru)
+ if (page_private(page) == migratetype)
+ break;
+ } else {
+ list_for_each_entry(page, &pcp->list, lru)
+ if (page_private(page) == migratetype)
+ break;
+ }
/* Allocate more to the pcp list if necessary */
if (unlikely(&page->lru == &pcp->list)) {
* skip over zones that are not allowed by the cpuset, or that have
* been recently (in last second) found to be nearly full. See further
* comments in mmzone.h. Reduces cache footprint of zonelist scans
- * that have to skip over alot of full or unallowed zones.
+ * that have to skip over a lot of full or unallowed zones.
*
* If the zonelist cache is present in the passed in zonelist, then
* returns a pointer to the allowed node mask (either the current
if (!zlc)
return NULL;
- if (jiffies - zlc->last_full_zap > 1 * HZ) {
+ if (time_after(jiffies, zlc->last_full_zap + HZ)) {
bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
zlc->last_full_zap = jiffies;
}
/*
* This is the 'heart' of the zoned buddy allocator.
*/
-struct page * fastcall
+struct page *
__alloc_pages(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist)
{
reclaim_state.reclaimed_slab = 0;
p->reclaim_state = &reclaim_state;
- did_some_progress = try_to_free_pages(zonelist->zones, order, gfp_mask);
+ did_some_progress = try_to_free_pages(zonelist, order, gfp_mask);
p->reclaim_state = NULL;
p->flags &= ~PF_MEMALLOC;
cond_resched();
if (order != 0)
- drain_all_local_pages();
+ drain_all_pages();
if (likely(did_some_progress)) {
page = get_page_from_freelist(gfp_mask, order,
if (page)
goto got_pg;
} else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
+ if (!try_set_zone_oom(zonelist)) {
+ schedule_timeout_uninterruptible(1);
+ goto restart;
+ }
+
/*
* Go through the zonelist yet one more time, keep
* very high watermark here, this is only to catch
*/
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
- if (page)
+ if (page) {
+ clear_zonelist_oom(zonelist);
goto got_pg;
+ }
/* The OOM killer will not help higher order allocs so fail */
- if (order > PAGE_ALLOC_COSTLY_ORDER)
+ if (order > PAGE_ALLOC_COSTLY_ORDER) {
+ clear_zonelist_oom(zonelist);
goto nopage;
+ }
out_of_memory(zonelist, gfp_mask, order);
+ clear_zonelist_oom(zonelist);
goto restart;
}
/*
* Common helper functions.
*/
-fastcall unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
+unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
{
struct page * page;
page = alloc_pages(gfp_mask, order);
EXPORT_SYMBOL(__get_free_pages);
-fastcall unsigned long get_zeroed_page(gfp_t gfp_mask)
+unsigned long get_zeroed_page(gfp_t gfp_mask)
{
struct page * page;
free_hot_cold_page(pvec->pages[i], pvec->cold);
}
-fastcall void __free_pages(struct page *page, unsigned int order)
+void __free_pages(struct page *page, unsigned int order)
{
if (put_page_testzero(page)) {
if (order == 0)
EXPORT_SYMBOL(__free_pages);
-fastcall void free_pages(unsigned long addr, unsigned int order)
+void free_pages(unsigned long addr, unsigned int order)
{
if (addr != 0) {
VM_BUG_ON(!virt_addr_valid((void *)addr));
static unsigned int nr_free_zone_pages(int offset)
{
/* Just pick one node, since fallback list is circular */
- pg_data_t *pgdat = NODE_DATA(numa_node_id());
unsigned int sum = 0;
- struct zonelist *zonelist = pgdat->node_zonelists + offset;
+ struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL);
struct zone **zonep = zonelist->zones;
struct zone *zone;
pageset = zone_pcp(zone, cpu);
- printk("CPU %4d: Hot: hi:%5d, btch:%4d usd:%4d "
- "Cold: hi:%5d, btch:%4d usd:%4d\n",
- cpu, pageset->pcp[0].high,
- pageset->pcp[0].batch, pageset->pcp[0].count,
- pageset->pcp[1].high, pageset->pcp[1].batch,
- pageset->pcp[1].count);
+ printk("CPU %4d: hi:%5d, btch:%4d usd:%4d\n",
+ cpu, pageset->pcp.high,
+ pageset->pcp.batch, pageset->pcp.count);
}
}
K(zone_page_state(zone, NR_INACTIVE)),
K(zone->present_pages),
zone->pages_scanned,
- (zone->all_unreclaimable ? "yes" : "no")
+ (zone_is_all_unreclaimable(zone) ? "yes" : "no")
);
printk("lowmem_reserve[]:");
for (i = 0; i < MAX_NR_ZONES; i++)
printk("= %lukB\n", K(total));
}
+ printk("%ld total pagecache pages\n", global_page_state(NR_FILE_PAGES));
+
show_swap_cache_info();
}
int n, val;
int min_val = INT_MAX;
int best_node = -1;
+ node_to_cpumask_ptr(tmp, 0);
/* Use the local node if we haven't already */
if (!node_isset(node, *used_node_mask)) {
}
for_each_node_state(n, N_HIGH_MEMORY) {
- cpumask_t tmp;
/* Don't want a node to appear more than once */
if (node_isset(n, *used_node_mask))
val += (n < node);
/* Give preference to headless and unused nodes */
- tmp = node_to_cpumask(n);
- if (!cpus_empty(tmp))
+ node_to_cpumask_ptr_next(tmp, n);
+ if (!cpus_empty(*tmp))
val += PENALTY_FOR_NODE_WITH_CPUS;
/* Slight preference for less loaded node */
__build_all_zonelists(NULL);
cpuset_init_current_mems_allowed();
} else {
- /* we have to stop all cpus to guaranntee there is no user
+ /* we have to stop all cpus to guarantee there is no user
of zonelist */
stop_machine_run(__build_all_zonelists, NULL, NR_CPUS);
/* cpuset refresh routine should be here */
}
}
-static void __meminit zone_init_free_lists(struct pglist_data *pgdat,
- struct zone *zone, unsigned long size)
+static void __meminit zone_init_free_lists(struct zone *zone)
{
int order, t;
for_each_migratetype_order(order, t) {
memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY)
#endif
-static int __devinit zone_batchsize(struct zone *zone)
+static int zone_batchsize(struct zone *zone)
{
int batch;
memset(p, 0, sizeof(*p));
- pcp = &p->pcp[0]; /* hot */
+ pcp = &p->pcp;
pcp->count = 0;
pcp->high = 6 * batch;
pcp->batch = max(1UL, 1 * batch);
INIT_LIST_HEAD(&pcp->list);
-
- pcp = &p->pcp[1]; /* cold*/
- pcp->count = 0;
- pcp->high = 2 * batch;
- pcp->batch = max(1UL, batch/2);
- INIT_LIST_HEAD(&pcp->list);
}
/*
{
struct per_cpu_pages *pcp;
- pcp = &p->pcp[0]; /* hot list */
+ pcp = &p->pcp;
pcp->high = high;
pcp->batch = max(1UL, high/4);
if ((high/4) > (PAGE_SHIFT * 8))
memmap_init(size, pgdat->node_id, zone_idx(zone), zone_start_pfn);
- zone_init_free_lists(pgdat, zone, zone->spanned_pages);
+ zone_init_free_lists(zone);
return 0;
}
/*
* Basic iterator support. Return the next active range of PFNs for a node
- * Note: nid == MAX_NUMNODES returns next region regardles of node
+ * Note: nid == MAX_NUMNODES returns next region regardless of node
*/
static int __meminit next_active_region_index_in_nid(int index, int nid)
{
#endif /* CONFIG_SPARSEMEM */
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
+
+/* Return a sensible default order for the pageblock size. */
+static inline int pageblock_default_order(void)
+{
+ if (HPAGE_SHIFT > PAGE_SHIFT)
+ return HUGETLB_PAGE_ORDER;
+
+ return MAX_ORDER-1;
+}
+
/* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
static inline void __init set_pageblock_order(unsigned int order)
{
}
#else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
-/* Defined this way to avoid accidently referencing HUGETLB_PAGE_ORDER */
+/*
+ * When CONFIG_HUGETLB_PAGE_SIZE_VARIABLE is not set, set_pageblock_order()
+ * and pageblock_default_order() are unused as pageblock_order is set
+ * at compile-time. See include/linux/pageblock-flags.h for the values of
+ * pageblock_order based on the kernel config
+ */
+static inline int pageblock_default_order(unsigned int order)
+{
+ return MAX_ORDER-1;
+}
#define set_pageblock_order(x) do {} while (0)
#endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
* - mark all memory queues empty
* - clear the memory bitmaps
*/
-static void __meminit free_area_init_core(struct pglist_data *pgdat,
+static void __paginginit free_area_init_core(struct pglist_data *pgdat,
unsigned long *zones_size, unsigned long *zholes_size)
{
enum zone_type j;
zone->nr_scan_active = 0;
zone->nr_scan_inactive = 0;
zap_zone_vm_stats(zone);
- atomic_set(&zone->reclaim_in_progress, 0);
+ zone->flags = 0;
if (!size)
continue;
- set_pageblock_order(HUGETLB_PAGE_ORDER);
+ set_pageblock_order(pageblock_default_order());
setup_usemap(pgdat, zone, size);
ret = init_currently_empty_zone(zone, zone_start_pfn,
size, MEMMAP_EARLY);
mem_map = NODE_DATA(0)->node_mem_map;
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
if (page_to_pfn(mem_map) != pgdat->node_start_pfn)
- mem_map -= pgdat->node_start_pfn;
+ mem_map -= (pgdat->node_start_pfn - ARCH_PFN_OFFSET);
#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
}
#endif
#endif /* CONFIG_FLAT_NODE_MEM_MAP */
}
-void __meminit free_area_init_node(int nid, struct pglist_data *pgdat,
+void __paginginit free_area_init_node(int nid, struct pglist_data *pgdat,
unsigned long *zones_size, unsigned long node_start_pfn,
unsigned long *zholes_size)
{
int cpu = (unsigned long)hcpu;
if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
- local_irq_disable();
- __drain_pages(cpu);
+ drain_pages(cpu);
+
+ /*
+ * Spill the event counters of the dead processor
+ * into the current processors event counters.
+ * This artificially elevates the count of the current
+ * processor.
+ */
vm_events_fold_cpu(cpu);
- local_irq_enable();
+
+ /*
+ * Zero the differential counters of the dead processor
+ * so that the vm statistics are consistent.
+ *
+ * This is only okay since the processor is dead and cannot
+ * race with what we are doing.
+ */
refresh_cpu_vm_stats(cpu);
}
return NOTIFY_OK;
out:
spin_unlock_irqrestore(&zone->lock, flags);
if (!ret)
- drain_all_local_pages();
+ drain_all_pages();
return ret;
}