#include <linux/ftrace_event.h>
#include <linux/memcontrol.h>
#include <linux/prefetch.h>
+#include <linux/page-debug-flags.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
unsigned long totalram_pages __read_mostly;
unsigned long totalreserve_pages __read_mostly;
+/*
+ * When calculating the number of globally allowed dirty pages, there
+ * is a certain number of per-zone reserves that should not be
+ * considered dirtyable memory. This is the sum of those reserves
+ * over all existing zones that contribute dirtyable memory.
+ */
+unsigned long dirty_balance_reserve __read_mostly;
+
int percpu_pagelist_fraction;
gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
saved_gfp_mask = gfp_allowed_mask;
gfp_allowed_mask &= ~GFP_IOFS;
}
+
+bool pm_suspended_storage(void)
+{
+ if ((gfp_allowed_mask & GFP_IOFS) == GFP_IOFS)
+ return false;
+ return true;
+}
#endif /* CONFIG_PM_SLEEP */
#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
clear_highpage(page + i);
}
+#ifdef CONFIG_DEBUG_PAGEALLOC
+unsigned int _debug_guardpage_minorder;
+
+static int __init debug_guardpage_minorder_setup(char *buf)
+{
+ unsigned long res;
+
+ if (kstrtoul(buf, 10, &res) < 0 || res > MAX_ORDER / 2) {
+ printk(KERN_ERR "Bad debug_guardpage_minorder value\n");
+ return 0;
+ }
+ _debug_guardpage_minorder = res;
+ printk(KERN_INFO "Setting debug_guardpage_minorder to %lu\n", res);
+ return 0;
+}
+__setup("debug_guardpage_minorder=", debug_guardpage_minorder_setup);
+
+static inline void set_page_guard_flag(struct page *page)
+{
+ __set_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+}
+
+static inline void clear_page_guard_flag(struct page *page)
+{
+ __clear_bit(PAGE_DEBUG_FLAG_GUARD, &page->debug_flags);
+}
+#else
+static inline void set_page_guard_flag(struct page *page) { }
+static inline void clear_page_guard_flag(struct page *page) { }
+#endif
+
static inline void set_page_order(struct page *page, int order)
{
set_page_private(page, order);
if (page_zone_id(page) != page_zone_id(buddy))
return 0;
+ if (page_is_guard(buddy) && page_order(buddy) == order) {
+ VM_BUG_ON(page_count(buddy) != 0);
+ return 1;
+ }
+
if (PageBuddy(buddy) && page_order(buddy) == order) {
VM_BUG_ON(page_count(buddy) != 0);
return 1;
buddy = page + (buddy_idx - page_idx);
if (!page_is_buddy(page, buddy, order))
break;
-
- /* Our buddy is free, merge with it and move up one order. */
- list_del(&buddy->lru);
- zone->free_area[order].nr_free--;
- rmv_page_order(buddy);
+ /*
+ * Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page,
+ * merge with it and move up one order.
+ */
+ if (page_is_guard(buddy)) {
+ clear_page_guard_flag(buddy);
+ set_page_private(page, 0);
+ __mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order);
+ } else {
+ list_del(&buddy->lru);
+ zone->free_area[order].nr_free--;
+ rmv_page_order(buddy);
+ }
combined_idx = buddy_idx & page_idx;
page = page + (combined_idx - page_idx);
page_idx = combined_idx;
int i;
int bad = 0;
+#ifdef CONFIG_XEN
+ if (PageForeign(page)) {
+ PageForeignDestructor(page, order);
+ return false;
+ }
+#endif
+
trace_mm_page_free(page, order);
kmemcheck_free_shadow(page, order);
unsigned long flags;
int wasMlocked = __TestClearPageMlocked(page);
+#ifdef CONFIG_XEN
+ WARN_ON(PageForeign(page) && wasMlocked);
+#endif
if (!free_pages_prepare(page, order))
return;
local_irq_restore(flags);
}
-/*
- * permit the bootmem allocator to evade page validation on high-order frees
- */
void __meminit __free_pages_bootmem(struct page *page, unsigned int order)
{
- if (order == 0) {
- __ClearPageReserved(page);
- set_page_count(page, 0);
- set_page_refcounted(page);
- __free_page(page);
- } else {
- int loop;
+ unsigned int nr_pages = 1 << order;
+ unsigned int loop;
- prefetchw(page);
- for (loop = 0; loop < (1 << order); loop++) {
- struct page *p = &page[loop];
-
- if (loop + 1 < (1 << order))
- prefetchw(p + 1);
- __ClearPageReserved(p);
- set_page_count(p, 0);
- }
+ prefetchw(page);
+ for (loop = 0; loop < nr_pages; loop++) {
+ struct page *p = &page[loop];
- set_page_refcounted(page);
- __free_pages(page, order);
+ if (loop + 1 < nr_pages)
+ prefetchw(p + 1);
+ __ClearPageReserved(p);
+ set_page_count(p, 0);
}
+
+ set_page_refcounted(page);
+ __free_pages(page, order);
}
high--;
size >>= 1;
VM_BUG_ON(bad_range(zone, &page[size]));
+
+#ifdef CONFIG_DEBUG_PAGEALLOC
+ if (high < debug_guardpage_minorder()) {
+ /*
+ * Mark as guard pages (or page), that will allow to
+ * merge back to allocator when buddy will be freed.
+ * Corresponding page table entries will not be touched,
+ * pages will stay not present in virtual address space
+ */
+ INIT_LIST_HEAD(&page[size].lru);
+ set_page_guard_flag(&page[size]);
+ set_page_private(&page[size], high);
+ /* Guard pages are not available for any usage */
+ __mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << high));
+ continue;
+ }
+#endif
list_add(&page[size].lru, &area->free_list[migratetype]);
area->nr_free++;
set_page_order(&page[size], high);
}
/*
- * Spill all the per-cpu pages from all CPUs back into the buddy allocator
+ * Spill all the per-cpu pages from all CPUs back into the buddy allocator.
+ *
+ * Note that this code is protected against sending an IPI to an offline
+ * CPU but does not guarantee sending an IPI to newly hotplugged CPUs:
+ * on_each_cpu_mask() blocks hotplug and won't talk to offlined CPUs but
+ * nothing keeps CPUs from showing up after we populated the cpumask and
+ * before the call to on_each_cpu_mask().
*/
void drain_all_pages(void)
{
- on_each_cpu(drain_local_pages, NULL, 1);
+ int cpu;
+ struct per_cpu_pageset *pcp;
+ struct zone *zone;
+
+ /*
+ * Allocate in the BSS so we wont require allocation in
+ * direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y
+ */
+ static cpumask_t cpus_with_pcps;
+
+ /*
+ * We don't care about racing with CPU hotplug event
+ * as offline notification will cause the notified
+ * cpu to drain that CPU pcps and on_each_cpu_mask
+ * disables preemption as part of its processing
+ */
+ for_each_online_cpu(cpu) {
+ bool has_pcps = false;
+ for_each_populated_zone(zone) {
+ pcp = per_cpu_ptr(zone->pageset, cpu);
+ if (pcp->pcp.count) {
+ has_pcps = true;
+ break;
+ }
+ }
+ if (has_pcps)
+ cpumask_set_cpu(cpu, &cpus_with_pcps);
+ else
+ cpumask_clear_cpu(cpu, &cpus_with_pcps);
+ }
+ on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1);
}
#ifdef CONFIG_HIBERNATION
int migratetype;
int wasMlocked = __TestClearPageMlocked(page);
+#ifdef CONFIG_XEN
+ WARN_ON(PageForeign(page) && wasMlocked);
+#endif
if (!free_pages_prepare(page, 0))
return;
long min = mark;
int o;
- free_pages -= (1 << order) + 1;
+ free_pages -= (1 << order) - 1;
if (alloc_flags & ALLOC_HIGH)
min -= min / 2;
if (alloc_flags & ALLOC_HARDER)
if ((alloc_flags & ALLOC_CPUSET) &&
!cpuset_zone_allowed_softwall(zone, gfp_mask))
continue;
+ /*
+ * When allocating a page cache page for writing, we
+ * want to get it from a zone that is within its dirty
+ * limit, such that no single zone holds more than its
+ * proportional share of globally allowed dirty pages.
+ * The dirty limits take into account the zone's
+ * lowmem reserves and high watermark so that kswapd
+ * should be able to balance it without having to
+ * write pages from its LRU list.
+ *
+ * This may look like it could increase pressure on
+ * lower zones by failing allocations in higher zones
+ * before they are full. But the pages that do spill
+ * over are limited as the lower zones are protected
+ * by this very same mechanism. It should not become
+ * a practical burden to them.
+ *
+ * XXX: For now, allow allocations to potentially
+ * exceed the per-zone dirty limit in the slowpath
+ * (ALLOC_WMARK_LOW unset) before going into reclaim,
+ * which is important when on a NUMA setup the allowed
+ * zones are together not big enough to reach the
+ * global limit. The proper fix for these situations
+ * will require awareness of zones in the
+ * dirty-throttling and the flusher threads.
+ */
+ if ((alloc_flags & ALLOC_WMARK_LOW) &&
+ (gfp_mask & __GFP_WRITE) && !zone_dirty_ok(zone))
+ goto this_zone_full;
BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
{
unsigned int filter = SHOW_MEM_FILTER_NODES;
- if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
+ if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs) ||
+ debug_guardpage_minorder() > 0)
return;
/*
va_end(args);
}
- pr_warn("%s: page allocation failure: order:%d, mode:0x%x\n",
+ if (!(gfp_mask & __GFP_WAIT)) {
+ pr_info("The following is only an harmless informational message.\n");
+ pr_info("Unless you get a _continuous_flood_ of these messages it means\n");
+ pr_info("everything is working fine. Allocations from irqs cannot be\n");
+ pr_info("perfectly reliable and the kernel is designed to handle that.\n");
+ }
+ pr_info("%s: page allocation failure. order:%d, mode:0x%x\n",
current->comm, order, gfp_mask);
dump_stack();
static inline int
should_alloc_retry(gfp_t gfp_mask, unsigned int order,
+ unsigned long did_some_progress,
unsigned long pages_reclaimed)
{
/* Do not loop if specifically requested */
if (gfp_mask & __GFP_NORETRY)
return 0;
+ /* Always retry if specifically requested */
+ if (gfp_mask & __GFP_NOFAIL)
+ return 1;
+
+ /*
+ * Suspend converts GFP_KERNEL to __GFP_WAIT which can prevent reclaim
+ * making forward progress without invoking OOM. Suspend also disables
+ * storage devices so kswapd will not help. Bail if we are suspending.
+ */
+ if (!did_some_progress && pm_suspended_storage())
+ return 0;
+
/*
* In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
* means __GFP_NOFAIL, but that may not be true in other
if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order))
return 1;
- /*
- * Don't let big-order allocations loop unless the caller
- * explicitly requests that.
- */
- if (gfp_mask & __GFP_NOFAIL)
- return 1;
-
return 0;
}
goto out;
}
/* Exhausted what can be done so it's blamo time */
- out_of_memory(zonelist, gfp_mask, order, nodemask);
+ out_of_memory(zonelist, gfp_mask, order, nodemask, false);
out:
clear_zonelist_oom(zonelist, gfp_mask);
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
- int migratetype, unsigned long *did_some_progress,
- bool sync_migration)
+ int migratetype, bool sync_migration,
+ bool *deferred_compaction,
+ unsigned long *did_some_progress)
{
struct page *page;
- if (!order || compaction_deferred(preferred_zone))
+ if (!order)
+ return NULL;
+
+ if (compaction_deferred(preferred_zone, order)) {
+ *deferred_compaction = true;
return NULL;
+ }
current->flags |= PF_MEMALLOC;
*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
if (page) {
preferred_zone->compact_considered = 0;
preferred_zone->compact_defer_shift = 0;
+ if (order >= preferred_zone->compact_order_failed)
+ preferred_zone->compact_order_failed = order + 1;
count_vm_event(COMPACTSUCCESS);
return page;
}
* but not enough to satisfy watermarks.
*/
count_vm_event(COMPACTFAIL);
- defer_compaction(preferred_zone);
+
+ /*
+ * As async compaction considers a subset of pageblocks, only
+ * defer if the failure was a sync compaction failure.
+ */
+ if (sync_migration)
+ defer_compaction(preferred_zone, order);
cond_resched();
}
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
struct zonelist *zonelist, enum zone_type high_zoneidx,
nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
- int migratetype, unsigned long *did_some_progress,
- bool sync_migration)
+ int migratetype, bool sync_migration,
+ bool *deferred_compaction,
+ unsigned long *did_some_progress)
{
return NULL;
}
unsigned long pages_reclaimed = 0;
unsigned long did_some_progress;
bool sync_migration = false;
+ bool deferred_compaction = false;
/*
* In the slowpath, we sanity check order to avoid ever trying to
zonelist, high_zoneidx,
nodemask,
alloc_flags, preferred_zone,
- migratetype, &did_some_progress,
- sync_migration);
+ migratetype, sync_migration,
+ &deferred_compaction,
+ &did_some_progress);
if (page)
goto got_pg;
sync_migration = true;
+ /*
+ * If compaction is deferred for high-order allocations, it is because
+ * sync compaction recently failed. In this is the case and the caller
+ * has requested the system not be heavily disrupted, fail the
+ * allocation now instead of entering direct reclaim
+ */
+ if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD))
+ goto nopage;
+
/* Try direct reclaim and then allocating */
page = __alloc_pages_direct_reclaim(gfp_mask, order,
zonelist, high_zoneidx,
if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
if (oom_killer_disabled)
goto nopage;
+ /* Coredumps can quickly deplete all memory reserves */
+ if ((current->flags & PF_DUMPCORE) &&
+ !(gfp_mask & __GFP_NOFAIL))
+ goto nopage;
page = __alloc_pages_may_oom(gfp_mask, order,
zonelist, high_zoneidx,
nodemask, preferred_zone,
/* Check if we should retry the allocation */
pages_reclaimed += did_some_progress;
- if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) {
+ if (should_alloc_retry(gfp_mask, order, did_some_progress,
+ pages_reclaimed)) {
/* Wait for some write requests to complete then retry */
wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
goto rebalance;
zonelist, high_zoneidx,
nodemask,
alloc_flags, preferred_zone,
- migratetype, &did_some_progress,
- sync_migration);
+ migratetype, sync_migration,
+ &deferred_compaction,
+ &did_some_progress);
if (page)
goto got_pg;
}
{
enum zone_type high_zoneidx = gfp_zone(gfp_mask);
struct zone *preferred_zone;
- struct page *page;
+ struct page *page = NULL;
int migratetype = allocflags_to_migratetype(gfp_mask);
+ unsigned int cpuset_mems_cookie;
gfp_mask &= gfp_allowed_mask;
if (unlikely(!zonelist->_zonerefs->zone))
return NULL;
- get_mems_allowed();
+retry_cpuset:
+ cpuset_mems_cookie = get_mems_allowed();
+
/* The preferred zone is used for statistics later */
first_zones_zonelist(zonelist, high_zoneidx,
nodemask ? : &cpuset_current_mems_allowed,
&preferred_zone);
- if (!preferred_zone) {
- put_mems_allowed();
- return NULL;
- }
+ if (!preferred_zone)
+ goto out;
/* First allocation attempt */
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
page = __alloc_pages_slowpath(gfp_mask, order,
zonelist, high_zoneidx, nodemask,
preferred_zone, migratetype);
- put_mems_allowed();
trace_mm_page_alloc(page, order, gfp_mask, migratetype);
+
+out:
+ /*
+ * When updating a task's mems_allowed, it is possible to race with
+ * parallel threads in such a way that an allocation can fail while
+ * the mask is being updated. If a page allocation is about to fail,
+ * check if the cpuset changed during allocation and if so, retry.
+ */
+ if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+ goto retry_cpuset;
+
return page;
}
EXPORT_SYMBOL(__alloc_pages_nodemask);
bool skip_free_areas_node(unsigned int flags, int nid)
{
bool ret = false;
+ unsigned int cpuset_mems_cookie;
if (!(flags & SHOW_MEM_FILTER_NODES))
goto out;
- get_mems_allowed();
- ret = !node_isset(nid, cpuset_current_mems_allowed);
- put_mems_allowed();
+ do {
+ cpuset_mems_cookie = get_mems_allowed();
+ ret = !node_isset(nid, cpuset_current_mems_allowed);
+ } while (!put_mems_allowed(cpuset_mems_cookie));
out:
return ret;
}
}
}
-int __init add_from_early_node_map(struct range *range, int az,
- int nr_range, int nid)
-{
- unsigned long start_pfn, end_pfn;
- int i;
-
- /* need to go over early_node_map to find out good range for node */
- for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL)
- nr_range = add_range(range, az, nr_range, start_pfn, end_pfn);
- return nr_range;
-}
-
/**
* sparse_memory_present_with_active_regions - Call memory_present for each active range
* @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used.
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = pgdat->node_zones + j;
unsigned long size, realsize, memmap_pages;
- enum lru_list l;
+ enum lru_list lru;
size = zone_spanned_pages_in_node(nid, j, zones_size);
realsize = size - zone_absent_pages_in_node(nid, j,
zone->zone_pgdat = pgdat;
zone_pcp_init(zone);
- for_each_lru(l)
- INIT_LIST_HEAD(&zone->lru[l].list);
+ for_each_lru(lru)
+ INIT_LIST_HEAD(&zone->lruvec.lists[lru]);
zone->reclaim_stat.recent_rotated[0] = 0;
zone->reclaim_stat.recent_rotated[1] = 0;
zone->reclaim_stat.recent_scanned[0] = 0;
* memory. When they don't, some nodes will have more kernelcore than
* others
*/
-static void __init find_zone_movable_pfns_for_nodes(unsigned long *movable_pfn)
+static void __init find_zone_movable_pfns_for_nodes(void)
{
int i, nid;
unsigned long usable_startpfn;
for (zone_type = 0; zone_type <= ZONE_NORMAL; zone_type++) {
struct zone *zone = &pgdat->node_zones[zone_type];
- if (zone->present_pages)
+ if (zone->present_pages) {
node_set_state(zone_to_nid(zone), N_NORMAL_MEMORY);
+ break;
+ }
}
#endif
}
/* Find the PFNs that ZONE_MOVABLE begins at in each node */
memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn));
- find_zone_movable_pfns_for_nodes(zone_movable_pfn);
+ find_zone_movable_pfns_for_nodes();
/* Print out the zone ranges */
printk("Zone PFN ranges:\n");
int cpu = (unsigned long)hcpu;
if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
+ lru_add_drain_cpu(cpu);
drain_pages(cpu);
/*
if (max > zone->present_pages)
max = zone->present_pages;
reserve_pages += max;
+ /*
+ * Lowmem reserves are not available to
+ * GFP_HIGHUSER page cache allocations and
+ * kswapd tries to balance zones to their high
+ * watermark. As a result, neither should be
+ * regarded as dirtyable memory, to prevent a
+ * situation where reclaim has to clean pages
+ * in order to balance the zones.
+ */
+ zone->dirty_balance_reserve = max;
}
}
+ dirty_balance_reserve = reserve_pages;
totalreserve_pages = reserve_pages;
}
spin_unlock_irqrestore(&zone->lock, flags);
}
+#ifdef CONFIG_XEN
+ for_each_populated_zone(zone) {
+ unsigned int cpu;
+
+ for_each_online_cpu(cpu) {
+ unsigned long high;
+
+ high = percpu_pagelist_fraction
+ ? zone->present_pages / percpu_pagelist_fraction
+ : 5 * zone_batchsize(zone);
+ setup_pagelist_highmark(
+ per_cpu_ptr(zone->pageset, cpu), high);
+ }
+ }
+#endif
+
/* update totalreserve_pages */
calculate_totalreserve_pages();
}
int ret;
ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
- if (!write || (ret == -EINVAL))
+ if (!write || (ret < 0))
return ret;
for_each_populated_zone(zone) {
for_each_possible_cpu(cpu) {
max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4;
do_div(max, bucketsize);
}
+ max = min(max, 0x80000000ULL);
if (numentries > max)
numentries = max;
bool is_pageblock_removable_nolock(struct page *page)
{
- struct zone *zone = page_zone(page);
+ struct zone *zone;
+ unsigned long pfn;
+
+ /*
+ * We have to be careful here because we are iterating over memory
+ * sections which are not zone aware so we might end up outside of
+ * the zone but still within the section.
+ * We have to take care about the node as well. If the node is offline
+ * its NODE_DATA will be NULL - see page_zone.
+ */
+ if (!node_online(page_to_nid(page)))
+ return false;
+
+ zone = page_zone(page);
+ pfn = page_to_pfn(page);
+ if (zone->zone_start_pfn > pfn ||
+ zone->zone_start_pfn + zone->spanned_pages <= pfn)
+ return false;
+
return __count_immobile_pages(zone, page, 0);
}