vmscan.c

最新最稳定的Linux内存管理模块源代码

				continue;
			if (nr_slab == 0 && zone->pages_scanned >=
						(zone_lru_pages(zone) * 6))
					zone_set_flag(zone,
						      ZONE_ALL_UNRECLAIMABLE);
			/*
			 * 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 > sc.nr_reclaimed + sc.nr_reclaimed / 2)
				sc.may_writepage = 1;
		}
		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)
			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 (sc.nr_reclaimed >= SWAP_CLUSTER_MAX)
			break;
	}
out:
	/*
	 * Note within each zone the priority level at which this zone was
	 * brought into a happy state.  So that the next thread which scans this
	 * zone will start out at that priority level.
	 */
	for (i = 0; i < pgdat->nr_zones; i++) {
		struct zone *zone = pgdat->node_zones + i;

		zone->prev_priority = temp_priority[i];
	}
	if (!all_zones_ok) {
		cond_resched();

		try_to_freeze();

		/*
		 * Fragmentation may mean that the system cannot be
		 * rebalanced for high-order allocations in all zones.
		 * At this point, if nr_reclaimed < SWAP_CLUSTER_MAX,
		 * it means the zones have been fully scanned and are still
		 * not balanced. For high-order allocations, there is
		 * little point trying all over again as kswapd may
		 * infinite loop.
		 *
		 * Instead, recheck all watermarks at order-0 as they
		 * are the most important. If watermarks are ok, kswapd will go
		 * back to sleep. High-order users can still perform direct
		 * reclaim if they wish.
		 */
		if (sc.nr_reclaimed < SWAP_CLUSTER_MAX)
			order = sc.order = 0;

		goto loop_again;
	}

	return sc.nr_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,
	};
	node_to_cpumask_ptr(cpumask, pgdat->node_id);

	if (!cpumask_empty(cpumask))
		set_cpus_allowed_ptr(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_SWAPWRITE | PF_KSWAPD;
	set_freezable();

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

		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 {
			if (!freezing(current))
				schedule();

			order = pgdat->kswapd_max_order;
		}
		finish_wait(&pgdat->kswapd_wait, &wait);

		if (!try_to_freeze()) {
			/* We can speed up thawing tasks if we don't call
			 * balance_pgdat after returning from the refrigerator
			 */
			balance_pgdat(pgdat, 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_hardwall(zone, GFP_KERNEL))
		return;
	if (!waitqueue_active(&pgdat->kswapd_wait))
		return;
	wake_up_interruptible(&pgdat->kswapd_wait);
}

unsigned long global_lru_pages(void)
{
	return global_page_state(NR_ACTIVE_ANON)
		+ global_page_state(NR_ACTIVE_FILE)
		+ global_page_state(NR_INACTIVE_ANON)
		+ global_page_state(NR_INACTIVE_FILE);
}

#ifdef CONFIG_PM
/*
 * Helper function for shrink_all_memory().  Tries to reclaim 'nr_pages' pages
 * from LRU lists system-wide, for given pass and priority, and returns the
 * number of reclaimed pages
 *
 * For pass > 3 we also try to shrink the LRU lists that contain a few pages
 */
static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
				      int pass, struct scan_control *sc)
{
	struct zone *zone;
	unsigned long ret = 0;

	for_each_zone(zone) {
		enum lru_list l;

		if (!populated_zone(zone))
			continue;
		if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY)
			continue;

		for_each_evictable_lru(l) {
			enum zone_stat_item ls = NR_LRU_BASE + l;
			unsigned long lru_pages = zone_page_state(zone, ls);

			/* For pass = 0, we don't shrink the active list */
			if (pass == 0 && (l == LRU_ACTIVE_ANON ||
						l == LRU_ACTIVE_FILE))
				continue;

			zone->lru[l].nr_scan += (lru_pages >> prio) + 1;
			if (zone->lru[l].nr_scan >= nr_pages || pass > 3) {
				unsigned long nr_to_scan;

				zone->lru[l].nr_scan = 0;
				nr_to_scan = min(nr_pages, lru_pages);
				ret += shrink_list(l, nr_to_scan, zone,
								sc, prio);
				if (ret >= nr_pages)
					return ret;
			}
		}
	}
	return ret;
}

/*
 * Try to free `nr_pages' of memory, system-wide, and return the number of
 * freed pages.
 *
 * Rather than trying to age LRUs the aim is to preserve the overall
 * LRU order by reclaiming preferentially
 * inactive > active > active referenced > active mapped
 */
unsigned long shrink_all_memory(unsigned long nr_pages)
{
	unsigned long lru_pages, nr_slab;
	unsigned long ret = 0;
	int pass;
	struct reclaim_state reclaim_state;
	struct scan_control sc = {
		.gfp_mask = GFP_KERNEL,
		.may_swap = 0,
		.swap_cluster_max = nr_pages,
		.may_writepage = 1,
		.isolate_pages = isolate_pages_global,
	};

	current->reclaim_state = &reclaim_state;

	lru_pages = global_lru_pages();
	nr_slab = global_page_state(NR_SLAB_RECLAIMABLE);
	/* If slab caches are huge, it's better to hit them first */
	while (nr_slab >= lru_pages) {
		reclaim_state.reclaimed_slab = 0;
		shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
		if (!reclaim_state.reclaimed_slab)
			break;

		ret += reclaim_state.reclaimed_slab;
		if (ret >= nr_pages)
			goto out;

		nr_slab -= reclaim_state.reclaimed_slab;
	}

	/*
	 * We try to shrink LRUs in 5 passes:
	 * 0 = Reclaim from inactive_list only
	 * 1 = Reclaim from active list but don't reclaim mapped
	 * 2 = 2nd pass of type 1
	 * 3 = Reclaim mapped (normal reclaim)
	 * 4 = 2nd pass of type 3
	 */
	for (pass = 0; pass < 5; pass++) {
		int prio;

		/* Force reclaiming mapped pages in the passes #3 and #4 */
		if (pass > 2)
			sc.may_swap = 1;

		for (prio = DEF_PRIORITY; prio >= 0; prio--) {
			unsigned long nr_to_scan = nr_pages - ret;

			sc.nr_scanned = 0;
			ret += shrink_all_zones(nr_to_scan, prio, pass, &sc);
			if (ret >= nr_pages)
				goto out;

			reclaim_state.reclaimed_slab = 0;
			shrink_slab(sc.nr_scanned, sc.gfp_mask,
					global_lru_pages());
			ret += reclaim_state.reclaimed_slab;
			if (ret >= nr_pages)
				goto out;

			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
				congestion_wait(WRITE, HZ / 10);
		}
	}

	/*
	 * If ret = 0, we could not shrink LRUs, but there may be something
	 * in slab caches
	 */
	if (!ret) {
		do {
			reclaim_state.reclaimed_slab = 0;
			shrink_slab(nr_pages, sc.gfp_mask, global_lru_pages());
			ret += reclaim_state.reclaimed_slab;
		} while (ret < nr_pages && reclaim_state.reclaimed_slab > 0);
	}

out:
	current->reclaim_state = NULL;

	return ret;
}
#endif

/* 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);
			node_to_cpumask_ptr(mask, 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;
}

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;

/*
 * 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_swap = !!(zone_reclaim_mode & RECLAIM_SWAP),
		.swap_cluster_max = max_t(unsigned long, nr_pages,
					SWAP_CLUSTER_MAX),
		.gfp_mask = gfp_mask,
		.swappiness = vm_swappiness,
		.isolate_pages = isolate_pages_global,
	};
	unsigned long slab_reclaimable;

	disable_swap_token();
	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;
	reclaim_state.reclaimed_slab = 0;
	p->reclaim_state = &reclaim_state;

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

	slab_reclaimable = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
	if (slab_reclaimable > 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