vmscan.c

 * caller can't do much about.  We kick pdflush and take explicit naps in the
 * hope that some of these pages can be written.  But if the allocating task
 * holds filesystem locks which prevent writeout this might not work, and the
 * allocation attempt will fail.
 */
int try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
{
	int priority;
	int ret = 0;
	int total_scanned = 0, total_reclaimed = 0;
	struct reclaim_state *reclaim_state = current->reclaim_state;
	struct scan_control sc;
	unsigned long lru_pages = 0;
	int i;

	sc.gfp_mask = gfp_mask;
	sc.may_writepage = 0;

	inc_page_state(allocstall);

	for (i = 0; zones[i] != NULL; i++) {
		struct zone *zone = zones[i];

		if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
			continue;

		zone->temp_priority = DEF_PRIORITY;
		lru_pages += zone->nr_active + zone->nr_inactive;
	}

	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
		sc.nr_mapped = read_page_state(nr_mapped);
		sc.nr_scanned = 0;
		sc.nr_reclaimed = 0;
		sc.priority = priority;
		sc.swap_cluster_max = SWAP_CLUSTER_MAX;
		if (!priority)
			disable_swap_token();
		shrink_caches(zones, &sc);
		shrink_slab(sc.nr_scanned, gfp_mask, lru_pages);
		if (reclaim_state) {
			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
			reclaim_state->reclaimed_slab = 0;
		}
		total_scanned += sc.nr_scanned;
		total_reclaimed += sc.nr_reclaimed;
		if (total_reclaimed >= sc.swap_cluster_max) {
			ret = 1;
			goto out;
		}

		/*
		 * Try to write back as many pages as we just scanned.  This
		 * tends to cause slow streaming writers to write data to the
		 * disk smoothly, at the dirtying rate, which is nice.   But
		 * that's undesirable in laptop mode, where we *want* lumpy
		 * writeout.  So in laptop mode, write out the whole world.
		 */
		if (total_scanned > sc.swap_cluster_max + sc.swap_cluster_max/2) {
			wakeup_pdflush(laptop_mode ? 0 : total_scanned);
			sc.may_writepage = 1;
		}

		/* Take a nap, wait for some writeback to complete */
		if (sc.nr_scanned && priority < DEF_PRIORITY - 2)
			blk_congestion_wait(WRITE, HZ/10);
	}
out:
	for (i = 0; zones[i] != 0; i++) {
		struct zone *zone = zones[i];

		if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
			continue;

		zone->prev_priority = zone->temp_priority;
	}
	return ret;
}

/*
 * For kswapd, balance_pgdat() will work across all this node's zones until
 * they are all at pages_high.
 *
 * If `nr_pages' is non-zero then it is the number of pages which are to be
 * reclaimed, regardless of the zone occupancies.  This is a software suspend
 * special.
 *
 * Returns the number of pages which were actually freed.
 *
 * There is special handling here for zones which are full of pinned pages.
 * This can happen if the pages are all mlocked, or if they are all used by
 * device drivers (say, ZONE_DMA).  Or if they are all in use by hugetlb.
 * What we do is to detect the case where all pages in the zone have been
 * scanned twice and there has been zero successful reclaim.  Mark the zone as
 * dead and from now on, only perform a short scan.  Basically we're polling
 * the zone for when the problem goes away.
 *
 * kswapd scans the zones in the highmem->normal->dma direction.  It skips
 * zones which have free_pages > pages_high, but once a zone is found to have
 * free_pages <= pages_high, we scan that zone and the lower zones regardless
 * of the number of free pages in the lower zones.  This interoperates with
 * the page allocator fallback scheme to ensure that aging of pages is balanced
 * across the zones.
 */
static int balance_pgdat(pg_data_t *pgdat, int nr_pages, int order)
{
	int to_free = nr_pages;
	int all_zones_ok;
	int priority;
	int i;
	int total_scanned, total_reclaimed;
	struct reclaim_state *reclaim_state = current->reclaim_state;
	struct scan_control sc;

loop_again:
	total_scanned = 0;
	total_reclaimed = 0;
	sc.gfp_mask = GFP_KERNEL;
	sc.may_writepage = 0;
	sc.nr_mapped = read_page_state(nr_mapped);

	inc_page_state(pageoutrun);

	for (i = 0; i < pgdat->nr_zones; i++) {
		struct zone *zone = pgdat->node_zones + i;

		zone->temp_priority = DEF_PRIORITY;
	}

	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
		int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
		unsigned long lru_pages = 0;

		/* The swap token gets in the way of swapout... */
		if (!priority)
			disable_swap_token();

		all_zones_ok = 1;

		if (nr_pages == 0) {
			/*
			 * Scan in the highmem->dma direction for the highest
			 * zone which needs scanning
			 */
			for (i = pgdat->nr_zones - 1; i >= 0; i--) {
				struct zone *zone = pgdat->node_zones + i;

				if (!populated_zone(zone))
					continue;

				if (zone->all_unreclaimable &&
						priority != DEF_PRIORITY)
					continue;

				if (!zone_watermark_ok(zone, order,
						zone->pages_high, 0, 0)) {
					end_zone = i;
					goto scan;
				}
			}
			goto out;
		} else {
			end_zone = pgdat->nr_zones - 1;
		}
scan:
		for (i = 0; i <= end_zone; i++) {
			struct zone *zone = pgdat->node_zones + i;

			lru_pages += zone->nr_active + zone->nr_inactive;
		}

		/*
		 * Now scan the zone in the dma->highmem direction, stopping
		 * at the last zone which needs scanning.
		 *
		 * We do this because the page allocator works in the opposite
		 * direction.  This prevents the page allocator from allocating
		 * pages behind kswapd's direction of progress, which would
		 * cause too much scanning of the lower zones.
		 */
		for (i = 0; i <= end_zone; i++) {
			struct zone *zone = pgdat->node_zones + i;
			int nr_slab;

			if (!populated_zone(zone))
				continue;

			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
				continue;

			if (nr_pages == 0) {	/* Not software suspend */
				if (!zone_watermark_ok(zone, order,
						zone->pages_high, end_zone, 0))
					all_zones_ok = 0;
			}
			zone->temp_priority = priority;
			if (zone->prev_priority > priority)
				zone->prev_priority = priority;
			sc.nr_scanned = 0;
			sc.nr_reclaimed = 0;
			sc.priority = priority;
			sc.swap_cluster_max = nr_pages? nr_pages : SWAP_CLUSTER_MAX;
			atomic_inc(&zone->reclaim_in_progress);
			shrink_zone(zone, &sc);
			atomic_dec(&zone->reclaim_in_progress);
			reclaim_state->reclaimed_slab = 0;
			nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
						lru_pages);
			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
			total_reclaimed += sc.nr_reclaimed;
			total_scanned += sc.nr_scanned;
			if (zone->all_unreclaimable)
				continue;
			if (nr_slab == 0 && zone->pages_scanned >=
				    (zone->nr_active + zone->nr_inactive) * 4)
				zone->all_unreclaimable = 1;
			/*
			 * If we've done a decent amount of scanning and
			 * the reclaim ratio is low, start doing writepage
			 * even in laptop mode
			 */
			if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
			    total_scanned > total_reclaimed+total_reclaimed/2)
				sc.may_writepage = 1;
		}
		if (nr_pages && to_free > total_reclaimed)
			continue;	/* swsusp: need to do more work */
		if (all_zones_ok)
			break;		/* kswapd: all done */
		/*
		 * OK, kswapd is getting into trouble.  Take a nap, then take
		 * another pass across the zones.
		 */
		if (total_scanned && priority < DEF_PRIORITY - 2)
			blk_congestion_wait(WRITE, HZ/10);

		/*
		 * We do this so kswapd doesn't build up large priorities for
		 * example when it is freeing in parallel with allocators. It
		 * matches the direct reclaim path behaviour in terms of impact
		 * on zone->*_priority.
		 */
		if ((total_reclaimed >= SWAP_CLUSTER_MAX) && (!nr_pages))
			break;
	}
out:
	for (i = 0; i < pgdat->nr_zones; i++) {
		struct zone *zone = pgdat->node_zones + i;

		zone->prev_priority = zone->temp_priority;
	}
	if (!all_zones_ok) {
		cond_resched();
		goto loop_again;
	}

	return total_reclaimed;
}

/*
 * The background pageout daemon, started as a kernel thread
 * from the init process. 
 *
 * This basically trickles out pages so that we have _some_
 * free memory available even if there is no other activity
 * that frees anything up. This is needed for things like routing
 * etc, where we otherwise might have all activity going on in
 * asynchronous contexts that cannot page things out.
 *
 * If there are applications that are active memory-allocators
 * (most normal use), this basically shouldn't matter.
 */
static int kswapd(void *p)
{
	unsigned long order;
	pg_data_t *pgdat = (pg_data_t*)p;
	struct task_struct *tsk = current;
	DEFINE_WAIT(wait);
	struct reclaim_state reclaim_state = {
		.reclaimed_slab = 0,
	};
	cpumask_t cpumask;

	daemonize("kswapd%d", pgdat->node_id);
	cpumask = node_to_cpumask(pgdat->node_id);
	if (!cpus_empty(cpumask))
		set_cpus_allowed(tsk, cpumask);
	current->reclaim_state = &reclaim_state;

	/*
	 * Tell the memory management that we're a "memory allocator",
	 * and that if we need more memory we should get access to it
	 * regardless (see "__alloc_pages()"). "kswapd" should
	 * never get caught in the normal page freeing logic.
	 *
	 * (Kswapd normally doesn't need memory anyway, but sometimes
	 * you need a small amount of memory in order to be able to
	 * page out something else, and this flag essentially protects
	 * us from recursively trying to free more memory as we're
	 * trying to free the first piece of memory in the first place).
	 */
	tsk->flags |= PF_MEMALLOC|PF_KSWAPD;

	order = 0;
	for ( ; ; ) {
		unsigned long new_order;

		try_to_freeze();

		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
		new_order = pgdat->kswapd_max_order;
		pgdat->kswapd_max_order = 0;
		if (order < new_order) {
			/*
			 * Don't sleep if someone wants a larger 'order'
			 * allocation
			 */
			order = new_order;
		} else {
			schedule();
			order = pgdat->kswapd_max_order;
		}
		finish_wait(&pgdat->kswapd_wait, &wait);

		balance_pgdat(pgdat, 0, order);
	}
	return 0;
}

/*
 * A zone is low on free memory, so wake its kswapd task to service it.
 */
void wakeup_kswapd(struct zone *zone, int order)
{
	pg_data_t *pgdat;

	if (!populated_zone(zone))
		return;

	pgdat = zone->zone_pgdat;
	if (zone_watermark_ok(zone, order, zone->pages_low, 0, 0))
		return;
	if (pgdat->kswapd_max_order < order)
		pgdat->kswapd_max_order = order;
	if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
		return;
	if (!waitqueue_active(&pgdat->kswapd_wait))
		return;
	wake_up_interruptible(&pgdat->kswapd_wait);
}

#ifdef CONFIG_PM
/*
 * Try to free `nr_pages' of memory, system-wide.  Returns the number of freed
 * pages.
 */
int shrink_all_memory(int nr_pages)
{
	pg_data_t *pgdat;
	int nr_to_free = nr_pages;
	int ret = 0;
	struct reclaim_state reclaim_state = {
		.reclaimed_slab = 0,
	};

	current->reclaim_state = &reclaim_state;
	for_each_pgdat(pgdat) {
		int freed;
		freed = balance_pgdat(pgdat, nr_to_free, 0);
		ret += freed;
		nr_to_free -= freed;
		if (nr_to_free <= 0)
			break;
	}
	current->reclaim_state = NULL;
	return ret;
}
#endif

#ifdef CONFIG_HOTPLUG_CPU
/* 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)
{
	pg_data_t *pgdat;
	cpumask_t mask;

	if (action == CPU_ONLINE) {
		for_each_pgdat(pgdat) {
			mask = node_to_cpumask(pgdat->node_id);
			if (any_online_cpu(mask) != NR_CPUS)
				/* One of our CPUs online: restore mask */
				set_cpus_allowed(pgdat->kswapd, mask);
		}
	}
	return NOTIFY_OK;
}
#endif /* CONFIG_HOTPLUG_CPU */

static int __init kswapd_init(void)
{
	pg_data_t *pgdat;
	swap_setup();
	for_each_pgdat(pgdat)
		pgdat->kswapd
		= find_task_by_pid(kernel_thread(kswapd, pgdat, CLONE_KERNEL));
	total_memory = nr_free_pagecache_pages();
	hotcpu_notifier(cpu_callback, 0);
	return 0;
}

module_init(kswapd_init)