vmscan.c

	p->flags |= PF_MEMALLOC;
	lockdep_set_current_reclaim_state(sc.gfp_mask);
	reclaim_state.reclaimed_slab = 0;
	p->reclaim_state = &reclaim_state;

	nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);

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

	return nr_reclaimed;
}
#endif /* CONFIG_HIBERNATION */

/* It's optimal to keep kswapds on the same CPUs as their memory, but
   not required for correctness.  So if the last cpu in a node goes
   away, we get changed to run anywhere: as the first one comes back,
   restore their cpu bindings. */
static int __devinit cpu_callback(struct notifier_block *nfb,
				  unsigned long action, void *hcpu)
{
	int nid;

	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
		for_each_node_state(nid, N_HIGH_MEMORY) {
			pg_data_t *pgdat = NODE_DATA(nid);
			const struct cpumask *mask;

			mask = cpumask_of_node(pgdat->node_id);

			if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
				/* One of our CPUs online: restore mask */
				set_cpus_allowed_ptr(pgdat->kswapd, mask);
		}
	}
	return NOTIFY_OK;
}

/*
 * This kswapd start function will be called by init and node-hot-add.
 * On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added.
 */
int kswapd_run(int nid)
{
	pg_data_t *pgdat = NODE_DATA(nid);
	int ret = 0;

	if (pgdat->kswapd)
		return 0;

	pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
	if (IS_ERR(pgdat->kswapd)) {
		/* failure at boot is fatal */
		BUG_ON(system_state == SYSTEM_BOOTING);
		printk("Failed to start kswapd on node %d\n",nid);
		ret = -1;
	}
	return ret;
}

/*
 * Called by memory hotplug when all memory in a node is offlined.
 */
void kswapd_stop(int nid)
{
	struct task_struct *kswapd = NODE_DATA(nid)->kswapd;

	if (kswapd)
		kthread_stop(kswapd);
}

static int __init kswapd_init(void)
{
	int nid;

	swap_setup();
	for_each_node_state(nid, N_HIGH_MEMORY)
 		kswapd_run(nid);
	hotcpu_notifier(cpu_callback, 0);
	return 0;
}

module_init(kswapd_init)

#ifdef CONFIG_NUMA
/*
 * Zone reclaim mode
 *
 * If non-zero call zone_reclaim when the number of free pages falls below
 * the watermarks.
 */
int zone_reclaim_mode __read_mostly;

#define RECLAIM_OFF 0
#define RECLAIM_ZONE (1<<0)	/* Run shrink_inactive_list on the zone */
#define RECLAIM_WRITE (1<<1)	/* Writeout pages during reclaim */
#define RECLAIM_SWAP (1<<2)	/* Swap pages out during reclaim */

/*
 * Priority for ZONE_RECLAIM. This determines the fraction of pages
 * of a node considered for each zone_reclaim. 4 scans 1/16th of
 * a zone.
 */
#define ZONE_RECLAIM_PRIORITY 4

/*
 * Percentage of pages in a zone that must be unmapped for zone_reclaim to
 * occur.
 */
int sysctl_min_unmapped_ratio = 1;

/*
 * If the number of slab pages in a zone grows beyond this percentage then
 * slab reclaim needs to occur.
 */
int sysctl_min_slab_ratio = 5;

static inline unsigned long zone_unmapped_file_pages(struct zone *zone)
{
	unsigned long file_mapped = zone_page_state(zone, NR_FILE_MAPPED);
	unsigned long file_lru = zone_page_state(zone, NR_INACTIVE_FILE) +
		zone_page_state(zone, NR_ACTIVE_FILE);

	/*
	 * It's possible for there to be more file mapped pages than
	 * accounted for by the pages on the file LRU lists because
	 * tmpfs pages accounted for as ANON can also be FILE_MAPPED
	 */
	return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0;
}

/* Work out how many page cache pages we can reclaim in this reclaim_mode */
static long zone_pagecache_reclaimable(struct zone *zone)
{
	long nr_pagecache_reclaimable;
	long delta = 0;

	/*
	 * If RECLAIM_SWAP is set, then all file pages are considered
	 * potentially reclaimable. Otherwise, we have to worry about
	 * pages like swapcache and zone_unmapped_file_pages() provides
	 * a better estimate
	 */
	if (zone_reclaim_mode & RECLAIM_SWAP)
		nr_pagecache_reclaimable = zone_page_state(zone, NR_FILE_PAGES);
	else
		nr_pagecache_reclaimable = zone_unmapped_file_pages(zone);

	/* If we can't clean pages, remove dirty pages from consideration */
	if (!(zone_reclaim_mode & RECLAIM_WRITE))
		delta += zone_page_state(zone, NR_FILE_DIRTY);

	/* Watch for any possible underflows due to delta */
	if (unlikely(delta > nr_pagecache_reclaimable))
		delta = nr_pagecache_reclaimable;

	return nr_pagecache_reclaimable - delta;
}

/*
 * Try to free up some pages from this zone through reclaim.
 */
static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
{
	/* Minimum pages needed in order to stay on node */
	const unsigned long nr_pages = 1 << order;
	struct task_struct *p = current;
	struct reclaim_state reclaim_state;
	int priority;
	struct scan_control sc = {
		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
		.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
		.may_swap = 1,
		.nr_to_reclaim = max_t(unsigned long, nr_pages,
				       SWAP_CLUSTER_MAX),
		.gfp_mask = gfp_mask,
		.order = order,
	};
	struct shrink_control shrink = {
		.gfp_mask = sc.gfp_mask,
	};
	unsigned long nr_slab_pages0, nr_slab_pages1;

	cond_resched();
	/*
	 * We need to be able to allocate from the reserves for RECLAIM_SWAP
	 * and we also need to be able to write out pages for RECLAIM_WRITE
	 * and RECLAIM_SWAP.
	 */
	p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
	lockdep_set_current_reclaim_state(gfp_mask);
	reclaim_state.reclaimed_slab = 0;
	p->reclaim_state = &reclaim_state;

	if (zone_pagecache_reclaimable(zone) > zone->min_unmapped_pages) {
		/*
		 * Free memory by calling shrink zone with increasing
		 * priorities until we have enough memory freed.
		 */
		priority = ZONE_RECLAIM_PRIORITY;
		do {
			shrink_zone(priority, zone, &sc);
			priority--;
		} while (priority >= 0 && sc.nr_reclaimed < nr_pages);
	}

	nr_slab_pages0 = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
	if (nr_slab_pages0 > zone->min_slab_pages) {
		/*
		 * shrink_slab() does not currently allow us to determine how
		 * many pages were freed in this zone. So we take the current
		 * number of slab pages and shake the slab until it is reduced
		 * by the same nr_pages that we used for reclaiming unmapped
		 * pages.
		 *
		 * Note that shrink_slab will free memory on all zones and may
		 * take a long time.
		 */
		for (;;) {
			unsigned long lru_pages = zone_reclaimable_pages(zone);

			/* No reclaimable slab or very low memory pressure */
			if (!shrink_slab(&shrink, sc.nr_scanned, lru_pages))
				break;

			/* Freed enough memory */
			nr_slab_pages1 = zone_page_state(zone,
							NR_SLAB_RECLAIMABLE);
			if (nr_slab_pages1 + nr_pages <= nr_slab_pages0)
				break;
		}

		/*
		 * Update nr_reclaimed by the number of slab pages we
		 * reclaimed from this zone.
		 */
		nr_slab_pages1 = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
		if (nr_slab_pages1 < nr_slab_pages0)
			sc.nr_reclaimed += nr_slab_pages0 - nr_slab_pages1;
	}

	p->reclaim_state = NULL;
	current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
	lockdep_clear_current_reclaim_state();
	return sc.nr_reclaimed >= nr_pages;
}

int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
{
	int node_id;
	int ret;

	/*
	 * Zone reclaim reclaims unmapped file backed pages and
	 * slab pages if we are over the defined limits.
	 *
	 * A small portion of unmapped file backed pages is needed for
	 * file I/O otherwise pages read by file I/O will be immediately
	 * thrown out if the zone is overallocated. So we do not reclaim
	 * if less than a specified percentage of the zone is used by
	 * unmapped file backed pages.
	 */
	if (zone_pagecache_reclaimable(zone) <= zone->min_unmapped_pages &&
	    zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
		return ZONE_RECLAIM_FULL;

	if (zone->all_unreclaimable)
		return ZONE_RECLAIM_FULL;

	/*
	 * Do not scan if the allocation should not be delayed.
	 */
	if (!(gfp_mask & __GFP_WAIT) || (current->flags & PF_MEMALLOC))
		return ZONE_RECLAIM_NOSCAN;

	/*
	 * Only run zone reclaim on the local zone or on zones that do not
	 * have associated processors. This will favor the local processor
	 * over remote processors and spread off node memory allocations
	 * as wide as possible.
	 */
	node_id = zone_to_nid(zone);
	if (node_state(node_id, N_CPU) && node_id != numa_node_id())
		return ZONE_RECLAIM_NOSCAN;

	if (zone_test_and_set_flag(zone, ZONE_RECLAIM_LOCKED))
		return ZONE_RECLAIM_NOSCAN;

	ret = __zone_reclaim(zone, gfp_mask, order);
	zone_clear_flag(zone, ZONE_RECLAIM_LOCKED);

	if (!ret)
		count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);

	return ret;
}
#endif

/*
 * page_evictable - test whether a page is evictable
 * @page: the page to test
 * @vma: the VMA in which the page is or will be mapped, may be NULL
 *
 * Test whether page is evictable--i.e., should be placed on active/inactive
 * lists vs unevictable list.  The vma argument is !NULL when called from the
 * fault path to determine how to instantate a new page.
 *
 * Reasons page might not be evictable:
 * (1) page's mapping marked unevictable
 * (2) page is part of an mlocked VMA
 *
 */
int page_evictable(struct page *page, struct vm_area_struct *vma)
{

	if (mapping_unevictable(page_mapping(page)))
		return 0;

	if (PageMlocked(page) || (vma && is_mlocked_vma(vma, page)))
		return 0;

	return 1;
}

/**
 * check_move_unevictable_page - check page for evictability and move to appropriate zone lru list
 * @page: page to check evictability and move to appropriate lru list
 * @zone: zone page is in
 *
 * Checks a page for evictability and moves the page to the appropriate
 * zone lru list.
 *
 * Restrictions: zone->lru_lock must be held, page must be on LRU and must
 * have PageUnevictable set.
 */
static void check_move_unevictable_page(struct page *page, struct zone *zone)
{
	VM_BUG_ON(PageActive(page));

retry:
	ClearPageUnevictable(page);
	if (page_evictable(page, NULL)) {
		enum lru_list l = page_lru_base_type(page);

		__dec_zone_state(zone, NR_UNEVICTABLE);
		list_move(&page->lru, &zone->lru[l].list);
		mem_cgroup_move_lists(page, LRU_UNEVICTABLE, l);
		__inc_zone_state(zone, NR_INACTIVE_ANON + l);
		__count_vm_event(UNEVICTABLE_PGRESCUED);
	} else {
		/*
		 * rotate unevictable list
		 */
		SetPageUnevictable(page);
		list_move(&page->lru, &zone->lru[LRU_UNEVICTABLE].list);
		mem_cgroup_rotate_lru_list(page, LRU_UNEVICTABLE);
		if (page_evictable(page, NULL))
			goto retry;
	}
}

/**
 * scan_mapping_unevictable_pages - scan an address space for evictable pages
 * @mapping: struct address_space to scan for evictable pages
 *
 * Scan all pages in mapping.  Check unevictable pages for
 * evictability and move them to the appropriate zone lru list.
 */
void scan_mapping_unevictable_pages(struct address_space *mapping)
{
	pgoff_t next = 0;
	pgoff_t end   = (i_size_read(mapping->host) + PAGE_CACHE_SIZE - 1) >>
			 PAGE_CACHE_SHIFT;
	struct zone *zone;
	struct pagevec pvec;

	if (mapping->nrpages == 0)
		return;

	pagevec_init(&pvec, 0);
	while (next < end &&
		pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
		int i;
		int pg_scanned = 0;

		zone = NULL;

		for (i = 0; i < pagevec_count(&pvec); i++) {
			struct page *page = pvec.pages[i];
			pgoff_t page_index = page->index;
			struct zone *pagezone = page_zone(page);

			pg_scanned++;
			if (page_index > next)
				next = page_index;
			next++;

			if (pagezone != zone) {
				if (zone)
					spin_unlock_irq(&zone->lru_lock);
				zone = pagezone;
				spin_lock_irq(&zone->lru_lock);
			}

			if (PageLRU(page) && PageUnevictable(page))
				check_move_unevictable_page(page, zone);
		}
		if (zone)
			spin_unlock_irq(&zone->lru_lock);
		pagevec_release(&pvec);

		count_vm_events(UNEVICTABLE_PGSCANNED, pg_scanned);
	}

}

/**
 * scan_zone_unevictable_pages - check unevictable list for evictable pages
 * @zone - zone of which to scan the unevictable list
 *
 * Scan @zone's unevictable LRU lists to check for pages that have become
 * evictable.  Move those that have to @zone's inactive list where they
 * become candidates for reclaim, unless shrink_inactive_zone() decides
 * to reactivate them.  Pages that are still unevictable are rotated
 * back onto @zone's unevictable list.
 */
#define SCAN_UNEVICTABLE_BATCH_SIZE 16UL /* arbitrary lock hold batch size */
static void scan_zone_unevictable_pages(struct zone *zone)
{
	struct list_head *l_unevictable = &zone->lru[LRU_UNEVICTABLE].list;
	unsigned long scan;
	unsigned long nr_to_scan = zone_page_state(zone, NR_UNEVICTABLE);

	while (nr_to_scan > 0) {
		unsigned long batch_size = min(nr_to_scan,
						SCAN_UNEVICTABLE_BATCH_SIZE);

		spin_lock_irq(&zone->lru_lock);
		for (scan = 0;  scan < batch_size; scan++) {
			struct page *page = lru_to_page(l_unevictable);

			if (!trylock_page(page))
				continue;

			prefetchw_prev_lru_page(page, l_unevictable, flags);

			if (likely(PageLRU(page) && PageUnevictable(page)))
				check_move_unevictable_page(page, zone);

			unlock_page(page);
		}
		spin_unlock_irq(&zone->lru_lock);

		nr_to_scan -= batch_size;
	}
}


/**
 * scan_all_zones_unevictable_pages - scan all unevictable lists for evictable pages
 *
 * A really big hammer:  scan all zones' unevictable LRU lists to check for
 * pages that have become evictable.  Move those back to the zones'
 * inactive list where they become candidates for reclaim.
 * This occurs when, e.g., we have unswappable pages on the unevictable lists,
 * and we add swap to the system.  As such, it runs in the context of a task
 * that has possibly/probably made some previously unevictable pages
 * evictable.
 */
static void scan_all_zones_unevictable_pages(void)
{
	struct zone *zone;

	for_each_zone(zone) {
		scan_zone_unevictable_pages(zone);
	}
}

/*
 * scan_unevictable_pages [vm] sysctl handler.  On demand re-scan of
 * all nodes' unevictable lists for evictable pages
 */
unsigned long scan_unevictable_pages;

int scan_unevictable_handler(struct ctl_table *table, int write,
			   void __user *buffer,
			   size_t *length, loff_t *ppos)
{
	proc_doulongvec_minmax(table, write, buffer, length, ppos);

	if (write && *(unsigned long *)table->data)
		scan_all_zones_unevictable_pages();

	scan_unevictable_pages = 0;
	return 0;
}

#ifdef CONFIG_NUMA
/*
 * per node 'scan_unevictable_pages' attribute.  On demand re-scan of
 * a specified node's per zone unevictable lists for evictable pages.
 */

static ssize_t read_scan_unevictable_node(struct sys_device *dev,
					  struct sysdev_attribute *attr,
					  char *buf)
{
	return sprintf(buf, "0\n");	/* always zero; should fit... */
}

static ssize_t write_scan_unevictable_node(struct sys_device *dev,
					   struct sysdev_attribute *attr,
					const char *buf, size_t count)
{
	struct zone *node_zones = NODE_DATA(dev->id)->node_zones;
	struct zone *zone;
	unsigned long res;
	unsigned long req = strict_strtoul(buf, 10, &res);

	if (!req)
		return 1;	/* zero is no-op */

	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
		if (!populated_zone(zone))
			continue;
		scan_zone_unevictable_pages(zone);
	}
	return 1;
}


static SYSDEV_ATTR(scan_unevictable_pages, S_IRUGO | S_IWUSR,
			read_scan_unevictable_node,
			write_scan_unevictable_node);

int scan_unevictable_register_node(struct node *node)
{
	return sysdev_create_file(&node->sysdev, &attr_scan_unevictable_pages);
}

void scan_unevictable_unregister_node(struct node *node)
{
	sysdev_remove_file(&node->sysdev, &attr_scan_unevictable_pages);
}
#endif