page_alloc.c

static int rmqueue_bulk(struct zone *zone, unsigned int order, 
			unsigned long count, struct list_head *list,
			int migratetype, int cold)
{
	int i;
	
	spin_lock(&zone->lock);
	for (i = 0; i < count; ++i) {
		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.
		 */
		if (likely(cold == 0))
			list_add(&page->lru, list);
		else
			list_add_tail(&page->lru, list);
		set_page_private(page, migratetype);
		list = &page->lru;
	}
	__mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order));
	spin_unlock(&zone->lock);
	return i;
}

#ifdef CONFIG_NUMA
/*
 * Called from the vmstat counter updater to drain pagesets of this
 * currently executing processor on remote nodes after they have
 * expired.
 *
 * Note that this function must be called with the thread pinned to
 * a single processor.
 */
void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
{
	unsigned long flags;
	int to_drain;

	local_irq_save(flags);
	if (pcp->count >= pcp->batch)
		to_drain = pcp->batch;
	else
		to_drain = pcp->count;
	free_pcppages_bulk(zone, to_drain, pcp);
	pcp->count -= to_drain;
	local_irq_restore(flags);
}
#endif

/*
 * 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;

	for_each_populated_zone(zone) {
		struct per_cpu_pageset *pset;
		struct per_cpu_pages *pcp;

		local_irq_save(flags);
		pset = per_cpu_ptr(zone->pageset, cpu);

		pcp = &pset->pcp;
		if (pcp->count) {
			free_pcppages_bulk(zone, pcp->count, pcp);
			pcp->count = 0;
		}
		local_irq_restore(flags);
	}
}

/*
 * Spill all of this CPU's per-cpu pages back into the buddy allocator.
 */
void drain_local_pages(void *arg)
{
	drain_pages(smp_processor_id());
}

/*
 * Spill all the per-cpu pages from all CPUs back into the buddy allocator
 */
void drain_all_pages(void)
{
	on_each_cpu(drain_local_pages, NULL, 1);
}

#ifdef CONFIG_HIBERNATION

void mark_free_pages(struct zone *zone)
{
	unsigned long pfn, max_zone_pfn;
	unsigned long flags;
	int order, t;
	struct list_head *curr;

	if (!zone->spanned_pages)
		return;

	spin_lock_irqsave(&zone->lock, flags);

	max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
	for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
		if (pfn_valid(pfn)) {
			struct page *page = pfn_to_page(pfn);

			if (!swsusp_page_is_forbidden(page))
				swsusp_unset_page_free(page);
		}

	for_each_migratetype_order(order, t) {
		list_for_each(curr, &zone->free_area[order].free_list[t]) {
			unsigned long i;

			pfn = page_to_pfn(list_entry(curr, struct page, lru));
			for (i = 0; i < (1UL << order); i++)
				swsusp_set_page_free(pfn_to_page(pfn + i));
		}
	}
	spin_unlock_irqrestore(&zone->lock, flags);
}
#endif /* CONFIG_PM */

/*
 * Free a 0-order page
 * cold == 1 ? free a cold page : free a hot page
 */
void free_hot_cold_page(struct page *page, int cold)
{
	struct zone *zone = page_zone(page);
	struct per_cpu_pages *pcp;
	unsigned long flags;
	int migratetype;
	int wasMlocked = __TestClearPageMlocked(page);

	if (!free_pages_prepare(page, 0))
		return;

	migratetype = get_pageblock_migratetype(page);
	set_page_private(page, migratetype);
	local_irq_save(flags);
	if (unlikely(wasMlocked))
		free_page_mlock(page);
	__count_vm_event(PGFREE);

	/*
	 * We only track unmovable, reclaimable and movable on pcp lists.
	 * Free ISOLATE pages back to the allocator because they are being
	 * offlined but treat RESERVE as movable pages so we can get those
	 * areas back if necessary. Otherwise, we may have to free
	 * excessively into the page allocator
	 */
	if (migratetype >= MIGRATE_PCPTYPES) {
		if (unlikely(migratetype == MIGRATE_ISOLATE)) {
			free_one_page(zone, page, 0, migratetype);
			goto out;
		}
		migratetype = MIGRATE_MOVABLE;
	}

	pcp = &this_cpu_ptr(zone->pageset)->pcp;
	if (cold)
		list_add_tail(&page->lru, &pcp->lists[migratetype]);
	else
		list_add(&page->lru, &pcp->lists[migratetype]);
	pcp->count++;
	if (pcp->count >= pcp->high) {
		free_pcppages_bulk(zone, pcp->batch, pcp);
		pcp->count -= pcp->batch;
	}

out:
	local_irq_restore(flags);
}

/*
 * Free a list of 0-order pages
 */
void free_hot_cold_page_list(struct list_head *list, int cold)
{
	struct page *page, *next;

	list_for_each_entry_safe(page, next, list, lru) {
		trace_mm_page_free_batched(page, cold);
		free_hot_cold_page(page, cold);
	}
}

/*
 * 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;

	VM_BUG_ON(PageCompound(page));
	VM_BUG_ON(!page_count(page));

#ifdef CONFIG_KMEMCHECK
	/*
	 * Split shadow pages too, because free(page[0]) would
	 * otherwise free the whole shadow.
	 */
	if (kmemcheck_page_is_tracked(page))
		split_page(virt_to_page(page[0].shadow), order);
#endif

	for (i = 1; i < (1 << order); i++)
		set_page_refcounted(page + i);
}

/*
 * Similar to split_page except the page is already free. As this is only
 * being used for migration, the migratetype of the block also changes.
 * As this is called with interrupts disabled, the caller is responsible
 * for calling arch_alloc_page() and kernel_map_page() after interrupts
 * are enabled.
 *
 * Note: this is probably too low level an operation for use in drivers.
 * Please consult with lkml before using this in your driver.
 */
int split_free_page(struct page *page)
{
	unsigned int order;
	unsigned long watermark;
	struct zone *zone;

	BUG_ON(!PageBuddy(page));

	zone = page_zone(page);
	order = page_order(page);

	/* Obey watermarks as if the page was being allocated */
	watermark = low_wmark_pages(zone) + (1 << order);
	if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
		return 0;

	/* Remove page from free list */
	list_del(&page->lru);
	zone->free_area[order].nr_free--;
	rmv_page_order(page);
	__mod_zone_page_state(zone, NR_FREE_PAGES, -(1UL << order));

	/* Split into individual pages */
	set_page_refcounted(page);
	split_page(page, order);

	if (order >= pageblock_order - 1) {
		struct page *endpage = page + (1 << order) - 1;
		for (; page < endpage; page += pageblock_nr_pages)
			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
	}

	return 1 << order;
}

/*
 * 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 inline
struct page *buffered_rmqueue(struct zone *preferred_zone,
			struct zone *zone, int order, gfp_t gfp_flags,
			int migratetype)
{
	unsigned long flags;
	struct page *page;
	int cold = !!(gfp_flags & __GFP_COLD);

again:
	if (likely(order == 0)) {
		struct per_cpu_pages *pcp;
		struct list_head *list;

		local_irq_save(flags);
		pcp = &this_cpu_ptr(zone->pageset)->pcp;
		list = &pcp->lists[migratetype];
		if (list_empty(list)) {
			pcp->count += rmqueue_bulk(zone, 0,
					pcp->batch, list,
					migratetype, cold);
			if (unlikely(list_empty(list)))
				goto failed;
		}

		if (cold)
			page = list_entry(list->prev, struct page, lru);
		else
			page = list_entry(list->next, struct page, lru);

		list_del(&page->lru);
		pcp->count--;
	} else {
		if (unlikely(gfp_flags & __GFP_NOFAIL)) {
			/*
			 * __GFP_NOFAIL is not to be used in new code.
			 *
			 * All __GFP_NOFAIL callers should be fixed so that they
			 * properly detect and handle allocation failures.
			 *
			 * We most definitely don't want callers attempting to
			 * allocate greater than order-1 page units with
			 * __GFP_NOFAIL.
			 */
			WARN_ON_ONCE(order > 1);
		}
		spin_lock_irqsave(&zone->lock, flags);
		page = __rmqueue(zone, order, migratetype);
		spin_unlock(&zone->lock);
		if (!page)
			goto failed;
		__mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order));
	}

	__count_zone_vm_events(PGALLOC, zone, 1 << order);
	zone_statistics(preferred_zone, zone, gfp_flags);
	local_irq_restore(flags);

	VM_BUG_ON(bad_range(zone, page));
	if (prep_new_page(page, order, gfp_flags))
		goto again;
	return page;

failed:
	local_irq_restore(flags);
	return NULL;
}

/* The ALLOC_WMARK bits are used as an index to zone->watermark */
#define ALLOC_WMARK_MIN		WMARK_MIN
#define ALLOC_WMARK_LOW		WMARK_LOW
#define ALLOC_WMARK_HIGH	WMARK_HIGH
#define ALLOC_NO_WATERMARKS	0x04 /* don't check watermarks at all */

/* Mask to get the watermark bits */
#define ALLOC_WMARK_MASK	(ALLOC_NO_WATERMARKS-1)

#define ALLOC_HARDER		0x10 /* try to alloc harder */
#define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
#define ALLOC_CPUSET		0x40 /* check for correct cpuset */

#ifdef CONFIG_FAIL_PAGE_ALLOC

static struct {
	struct fault_attr attr;

	u32 ignore_gfp_highmem;
	u32 ignore_gfp_wait;
	u32 min_order;
} fail_page_alloc = {
	.attr = FAULT_ATTR_INITIALIZER,
	.ignore_gfp_wait = 1,
	.ignore_gfp_highmem = 1,
	.min_order = 1,
};

static int __init setup_fail_page_alloc(char *str)
{
	return setup_fault_attr(&fail_page_alloc.attr, str);
}
__setup("fail_page_alloc=", setup_fail_page_alloc);

static int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
	if (order < fail_page_alloc.min_order)
		return 0;
	if (gfp_mask & __GFP_NOFAIL)
		return 0;
	if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM))
		return 0;
	if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT))
		return 0;

	return should_fail(&fail_page_alloc.attr, 1 << order);
}

#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS

static int __init fail_page_alloc_debugfs(void)
{
	umode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
	struct dentry *dir;

	dir = fault_create_debugfs_attr("fail_page_alloc", NULL,
					&fail_page_alloc.attr);
	if (IS_ERR(dir))
		return PTR_ERR(dir);

	if (!debugfs_create_bool("ignore-gfp-wait", mode, dir,
				&fail_page_alloc.ignore_gfp_wait))
		goto fail;
	if (!debugfs_create_bool("ignore-gfp-highmem", mode, dir,
				&fail_page_alloc.ignore_gfp_highmem))
		goto fail;
	if (!debugfs_create_u32("min-order", mode, dir,
				&fail_page_alloc.min_order))
		goto fail;

	return 0;
fail:
	debugfs_remove_recursive(dir);

	return -ENOMEM;
}

late_initcall(fail_page_alloc_debugfs);

#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */

#else /* CONFIG_FAIL_PAGE_ALLOC */

static inline int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
	return 0;
}

#endif /* CONFIG_FAIL_PAGE_ALLOC */

/*
 * Return true if free pages are above 'mark'. This takes into account the order
 * of the allocation.
 */
static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
		      int classzone_idx, int alloc_flags, long free_pages)
{
	/* free_pages my go negative - that's OK */
	long min = mark;
	int o;

	free_pages -= (1 << order) + 1;
	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 false;
	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 false;
	}
	return true;
}

bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
		      int classzone_idx, int alloc_flags)
{
	return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
					zone_page_state(z, NR_FREE_PAGES));
}

bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
		      int classzone_idx, int alloc_flags)
{
	long free_pages = zone_page_state(z, NR_FREE_PAGES);

	if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
		free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);

	return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
								free_pages);
}

#ifdef CONFIG_NUMA
/*
 * zlc_setup - Setup for "zonelist cache".  Uses cached zone data to
 * 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 a lot of full or unallowed zones.
 *
 * If the zonelist cache is present in the passed in zonelist, then
 * returns a pointer to the allowed node mask (either the current
 * tasks mems_allowed, or node_states[N_HIGH_MEMORY].)
 *
 * If the zonelist cache is not available for this zonelist, does
 * nothing and returns NULL.
 *
 * If the fullzones BITMAP in the zonelist cache is stale (more than
 * a second since last zap'd) then we zap it out (clear its bits.)
 *
 * We hold off even calling zlc_setup, until after we've checked the
 * first zone in the zonelist, on the theory that most allocations will
 * be satisfied from that first zone, so best to examine that zone as
 * quickly as we can.
 */
static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
{
	struct zonelist_cache *zlc;	/* cached zonelist speedup info */
	nodemask_t *allowednodes;	/* zonelist_cache approximation */

	zlc = zonelist->zlcache_ptr;
	if (!zlc)
		return NULL;

	if (time_after(jiffies, zlc->last_full_zap + HZ)) {
		bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
		zlc->last_full_zap = jiffies;
	}

	allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ?
					&cpuset_current_mems_allowed :
					&node_states[N_HIGH_MEMORY];
	return allowednodes;
}

/*
 * Given 'z' scanning a zonelist, run a couple of quick checks to see
 * if it is worth looking at further for free memory:
 *  1) Check that the zone isn't thought to be full (doesn't have its
 *     bit set in the zonelist_cache fullzones BITMAP).
 *  2) Check that the zones node (obtained from the zonelist_cache
 *     z_to_n[] mapping) is allowed in the passed in allowednodes mask.
 * Return true (non-zero) if zone is worth looking at further, or
 * else return false (zero) if it is not.
 *
 * This check -ignores- the distinction between various watermarks,
 * such as GFP_HIGH, GFP_ATOMIC, PF_MEMALLOC, ...  If a zone is
 * found to be full for any variation of these watermarks, it will
 * be considered full for up to one second by all requests, unless
 * we are so low on memory on all allowed nodes that we are forced
 * into the second scan of the zonelist.
 *
 * In the second scan we ignore this zonelist cache and exactly
 * apply the watermarks to all zones, even it is slower to do so.
 * We are low on memory in the second scan, and should leave no stone
 * unturned looking for a free page.
 */
static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
						nodemask_t *allowednodes)
{
	struct zonelist_cache *zlc;	/* cached zonelist speedup info */
	int i;				/* index of *z in zonelist zones */
	int n;				/* node that zone *z is on */

	zlc = zonelist->zlcache_ptr;
	if (!zlc)
		return 1;

	i = z - zonelist->_zonerefs;
	n = zlc->z_to_n[i];

	/* This zone is worth trying if it is allowed but not full */
	return node_isset(n, *allowednodes) && !test_bit(i, zlc->fullzones);
}

/*
 * Given 'z' scanning a zonelist, set the corresponding bit in
 * zlc->fullzones, so that subsequent attempts to allocate a page
 * from that zone don't waste time re-examining it.
 */
static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
{
	struct zonelist_cache *zlc;	/* cached zonelist speedup info */
	int i;				/* index of *z in zonelist zones */

	zlc = zonelist->zlcache_ptr;
	if (!zlc)
		return;

	i = z - zonelist->_zonerefs;

	set_bit(i, zlc->fullzones);
}

/*
 * clear all zones full, called after direct reclaim makes progress so that
 * a zone that was recently full is not skipped over for up to a second
 */
static void zlc_clear_zones_full(struct zonelist *zonelist)
{
	struct zonelist_cache *zlc;	/* cached zonelist speedup info */

	zlc = zonelist->zlcache_ptr;
	if (!zlc)
		return;

	bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
}

#else	/* CONFIG_NUMA */

static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
{
	return NULL;
}

static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
				nodemask_t *allowednodes)
{
	return 1;
}

static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
{
}

static void zlc_clear_zones_full(struct zonelist *zonelist)
{
}
#endif	/* CONFIG_NUMA */

/*
 * get_page_from_freelist goes through the zonelist trying to allocate
 * a page.
 */
static struct page *
get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order,
		struct zonelist *zonelist, int high_zoneidx, int alloc_flags,
		struct zone *preferred_zone, int migratetype)
{
	struct zoneref *z;
	struct page *page = NULL;
	int classzone_idx;
	struct zone *zone;
	nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
	int zlc_active = 0;		/* set if using zonelist_cache */
	int did_zlc_setup = 0;		/* just call zlc_setup() one time */

	classzone_idx = zone_idx(preferred_zone);
zonelist_scan:
	/*
	 * Scan zonelist, looking for a zone with enough free.
	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
	 */
	for_each_zone_zonelist_nodemask(zone, z, zonelist,
						high_zoneidx, nodemask) {
		if (NUMA_BUILD && zlc_active &&
			!zlc_zone_worth_trying(zonelist, z, allowednodes))
				continue;
		if ((alloc_flags & ALLOC_CPUSET) &&
			!cpuset_zone_allowed_softwall(zone, gfp_mask))
				continue;

		BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
		if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
			unsigned long mark;
			int ret;

			mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK];
			if (zone_watermark_ok(zone, order, mark,
				    classzone_idx, alloc_flags))
				goto try_this_zone;

			if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) {
				/*
				 * we do zlc_setup if there are multiple nodes
				 * and before considering the first zone allowed
				 * by the cpuset.
				 */
				allowednodes = zlc_setup(zonelist, alloc_flags);
				zlc_active = 1;
				did_zlc_setup = 1;
			}

			if (zone_reclaim_mode == 0)
				goto this_zone_full;

			/*
			 * As we may have just activated ZLC, check if the first
			 * eligible zone has failed zone_reclaim recently.
			 */
			if (NUMA_BUILD && zlc_active &&
				!zlc_zone_worth_trying(zonelist, z, allowednodes))
				continue;

			ret = zone_reclaim(zone, gfp_mask, order);
			switch (ret) {
			case ZONE_RECLAIM_NOSCAN:
				/* did not scan */
				continue;
			case ZONE_RECLAIM_FULL:
				/* scanned but unreclaimable */
				continue;
			default:
				/* did we reclaim enough */
				if (!zone_watermark_ok(zone, order, mark,
						classzone_idx, alloc_flags))
					goto this_zone_full;
			}
		}

try_this_zone:
		page = buffered_rmqueue(preferred_zone, zone, order,
						gfp_mask, migratetype);
		if (page)
			break;
this_zone_full:
		if (NUMA_BUILD)
			zlc_mark_zone_full(zonelist, z);
	}

	if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
		/* Disable zlc cache for second zonelist scan */
		zlc_active = 0;
		goto zonelist_scan;
	}
	return page;
}

/*
 * Large machines with many possible nodes should not always dump per-node
 * meminfo in irq context.
 */
static inline bool should_suppress_show_mem(void)
{
	bool ret = false;

#if NODES_SHIFT > 8
	ret = in_interrupt();
#endif
	return ret;
}

static DEFINE_RATELIMIT_STATE(nopage_rs,
		DEFAULT_RATELIMIT_INTERVAL,
		DEFAULT_RATELIMIT_BURST);

void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
{
	unsigned int filter = SHOW_MEM_FILTER_NODES;

	if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
		return;

	/*
	 * This documents exceptions given to allocations in certain
	 * contexts that are allowed to allocate outside current's set
	 * of allowed nodes.
	 */
	if (!(gfp_mask & __GFP_NOMEMALLOC))
		if (test_thread_flag(TIF_MEMDIE) ||
		    (current->flags & (PF_MEMALLOC | PF_EXITING)))
			filter &= ~SHOW_MEM_FILTER_NODES;
	if (in_interrupt() || !(gfp_mask & __GFP_WAIT))
		filter &= ~SHOW_MEM_FILTER_NODES;

	if (fmt) {
		struct va_format vaf;
		va_list args;

		va_start(args, fmt);

		vaf.fmt = fmt;
		vaf.va = &args;

		pr_warn("%pV", &vaf);

		va_end(args);
	}

	pr_warn("%s: page allocation failure: order:%d, mode:0x%x\n",
		current->comm, order, gfp_mask);

	dump_stack();
	if (!should_suppress_show_mem())
		show_mem(filter);
}

static inline int
should_alloc_retry(gfp_t gfp_mask, unsigned int order,
				unsigned long pages_reclaimed)
{
	/* Do not loop if specifically requested */
	if (gfp_mask & __GFP_NORETRY)
		return 0;

	/*
	 * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER
	 * means __GFP_NOFAIL, but that may not be true in other
	 * implementations.
	 */
	if (order <= PAGE_ALLOC_COSTLY_ORDER)
		return 1;

	/*
	 * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is
	 * specified, then we retry until we no longer reclaim any pages
	 * (above), or we've reclaimed an order of pages at least as
	 * large as the allocation's order. In both cases, if the
	 * allocation still fails, we stop retrying.
	 */
	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;
}

static inline struct page *
__alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
	struct zonelist *zonelist, enum zone_type high_zoneidx,
	nodemask_t *nodemask, struct zone *preferred_zone,
	int migratetype)
{
	struct page *page;

	/* Acquire the OOM killer lock for the zones in zonelist */
	if (!try_set_zonelist_oom(zonelist, gfp_mask)) {
		schedule_timeout_uninterruptible(1);
		return NULL;
	}

	/*
	 * 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, nodemask,
		order, zonelist, high_zoneidx,
		ALLOC_WMARK_HIGH|ALLOC_CPUSET,
		preferred_zone, migratetype);
	if (page)
		goto out;

	if (!(gfp_mask & __GFP_NOFAIL)) {
		/* The OOM killer will not help higher order allocs */
		if (order > PAGE_ALLOC_COSTLY_ORDER)
			goto out;
		/* The OOM killer does not needlessly kill tasks for lowmem */
		if (high_zoneidx < ZONE_NORMAL)
			goto out;
		/*
		 * GFP_THISNODE contains __GFP_NORETRY and we never hit this.
		 * Sanity check for bare calls of __GFP_THISNODE, not real OOM.
		 * The caller should handle page allocation failure by itself if
		 * it specifies __GFP_THISNODE.
		 * Note: Hugepage uses it but will hit PAGE_ALLOC_COSTLY_ORDER.
		 */
		if (gfp_mask & __GFP_THISNODE)
			goto out;
	}
	/* Exhausted what can be done so it's blamo time */
	out_of_memory(zonelist, gfp_mask, order, nodemask);

out:
	clear_zonelist_oom(zonelist, gfp_mask);
	return page;
}

#ifdef CONFIG_COMPACTION
/* Try memory compaction for high-order allocations before reclaim */
static struct page *
__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)
{
	struct page *page;

	if (!order || compaction_deferred(preferred_zone))
		return NULL;

	current->flags |= PF_MEMALLOC;
	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
						nodemask, sync_migration);
	current->flags &= ~PF_MEMALLOC;
	if (*did_some_progress != COMPACT_SKIPPED) {

		/* Page migration frees to the PCP lists but we want merging */
		drain_pages(get_cpu());
		put_cpu();

		page = get_page_from_freelist(gfp_mask, nodemask,
				order, zonelist, high_zoneidx,
				alloc_flags, preferred_zone,
				migratetype);
		if (page) {
			preferred_zone->compact_considered = 0;
			preferred_zone->compact_defer_shift = 0;
			count_vm_event(COMPACTSUCCESS);
			return page;
		}

		/*
		 * It's bad if compaction run occurs and fails.
		 * The most likely reason is that pages exist,
		 * but not enough to satisfy watermarks.
		 */
		count_vm_event(COMPACTFAIL);
		defer_compaction(preferred_zone);

		cond_resched();
	}

	return NULL;
}
#else
static inline struct page *
__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)
{
	return NULL;
}
#endif /* CONFIG_COMPACTION */

/* The really slow allocator path where we enter direct reclaim */
static inline struct page *
__alloc_pages_direct_reclaim(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)
{
	struct page *page = NULL;
	struct reclaim_state reclaim_state;
	bool drained = false;

	cond_resched();

	/* We now go into synchronous reclaim */
	cpuset_memory_pressure_bump();
	current->flags |= PF_MEMALLOC;
	lockdep_set_current_reclaim_state(gfp_mask);
	reclaim_state.reclaimed_slab = 0;
	current->reclaim_state = &reclaim_state;

	*did_some_progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask);

	current->reclaim_state = NULL;
	lockdep_clear_current_reclaim_state();
	current->flags &= ~PF_MEMALLOC;

	cond_resched();

	if (unlikely(!(*did_some_progress)))
		return NULL;

	/* After successful reclaim, reconsider all zones for allocation */
	if (NUMA_BUILD)
		zlc_clear_zones_full(zonelist);

retry:
	page = get_page_from_freelist(gfp_mask, nodemask, order,
					zonelist, high_zoneidx,
					alloc_flags, preferred_zone,
					migratetype);

	/*
	 * If an allocation failed after direct reclaim, it could be because
	 * pages are pinned on the per-cpu lists. Drain them and try again
	 */
	if (!page && !drained) {
		drain_all_pages();
		drained = true;
		goto retry;
	}

	return page;
}

/*
 * This is called in the allocator slow-path if the allocation request is of
 * sufficient urgency to ignore watermarks and take other desperate measures
 */
static inline struct page *
__alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
	struct zonelist *zonelist, enum zone_type high_zoneidx,
	nodemask_t *nodemask, struct zone *preferred_zone,
	int migratetype)
{
	struct page *page;

	do {