vmscan.c

最新最稳定的Linux内存管理模块源代码

	 * OK, so we have swap space and a fair amount of page cache
	 * pages.  We use the recently rotated / recently scanned
	 * ratios to determine how valuable each cache is.
	 *
	 * Because workloads change over time (and to avoid overflow)
	 * we keep these statistics as a floating average, which ends
	 * up weighing recent references more than old ones.
	 *
	 * anon in [0], file in [1]
	 */
	if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
		spin_lock_irq(&zone->lru_lock);
		reclaim_stat->recent_scanned[0] /= 2;
		reclaim_stat->recent_rotated[0] /= 2;
		spin_unlock_irq(&zone->lru_lock);
	}

	if (unlikely(reclaim_stat->recent_scanned[1] > file / 4)) {
		spin_lock_irq(&zone->lru_lock);
		reclaim_stat->recent_scanned[1] /= 2;
		reclaim_stat->recent_rotated[1] /= 2;
		spin_unlock_irq(&zone->lru_lock);
	}

	/*
	 * With swappiness at 100, anonymous and file have the same priority.
	 * This scanning priority is essentially the inverse of IO cost.
	 */
	anon_prio = sc->swappiness;
	file_prio = 200 - sc->swappiness;

	/*
	 * The amount of pressure on anon vs file pages is inversely
	 * proportional to the fraction of recently scanned pages on
	 * each list that were recently referenced and in active use.
	 */
	ap = (anon_prio + 1) * (reclaim_stat->recent_scanned[0] + 1);
	ap /= reclaim_stat->recent_rotated[0] + 1;

	fp = (file_prio + 1) * (reclaim_stat->recent_scanned[1] + 1);
	fp /= reclaim_stat->recent_rotated[1] + 1;

	/* Normalize to percentages */
	percent[0] = 100 * ap / (ap + fp + 1);
	percent[1] = 100 - percent[0];
}


/*
 * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
 */
static void shrink_zone(int priority, struct zone *zone,
				struct scan_control *sc)
{
	unsigned long nr[NR_LRU_LISTS];
	unsigned long nr_to_scan;
	unsigned long percent[2];	/* anon @ 0; file @ 1 */
	enum lru_list l;
	unsigned long nr_reclaimed = sc->nr_reclaimed;
	unsigned long swap_cluster_max = sc->swap_cluster_max;

	get_scan_ratio(zone, sc, percent);

	for_each_evictable_lru(l) {
		int file = is_file_lru(l);
		int scan;

		scan = zone_nr_pages(zone, sc, l);
		if (priority) {
			scan >>= priority;
			scan = (scan * percent[file]) / 100;
		}
		if (scanning_global_lru(sc)) {
			zone->lru[l].nr_scan += scan;
			nr[l] = zone->lru[l].nr_scan;
			if (nr[l] >= swap_cluster_max)
				zone->lru[l].nr_scan = 0;
			else
				nr[l] = 0;
		} else
			nr[l] = scan;
	}

	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
					nr[LRU_INACTIVE_FILE]) {
		for_each_evictable_lru(l) {
			if (nr[l]) {
				nr_to_scan = min(nr[l], swap_cluster_max);
				nr[l] -= nr_to_scan;

				nr_reclaimed += shrink_list(l, nr_to_scan,
							    zone, sc, priority);
			}
		}
		/*
		 * On large memory systems, scan >> priority can become
		 * really large. This is fine for the starting priority;
		 * we want to put equal scanning pressure on each zone.
		 * However, if the VM has a harder time of freeing pages,
		 * with multiple processes reclaiming pages, the total
		 * freeing target can get unreasonably large.
		 */
		if (nr_reclaimed > swap_cluster_max &&
			priority < DEF_PRIORITY && !current_is_kswapd())
			break;
	}

	sc->nr_reclaimed = nr_reclaimed;

	/*
	 * Even if we did not try to evict anon pages at all, we want to
	 * rebalance the anon lru active/inactive ratio.
	 */
	if (inactive_anon_is_low(zone, sc))
		shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);

	throttle_vm_writeout(sc->gfp_mask);
}

/*
 * This is the direct reclaim path, for page-allocating processes.  We only
 * try to reclaim pages from zones which will satisfy the caller's allocation
 * request.
 *
 * We reclaim from a zone even if that zone is over pages_high.  Because:
 * a) The caller may be trying to free *extra* pages to satisfy a higher-order
 *    allocation or
 * b) The zones may be over pages_high but they must go *over* pages_high to
 *    satisfy the `incremental min' zone defense algorithm.
 *
 * If a zone is deemed to be full of pinned pages then just give it a light
 * scan then give up on it.
 */
static void shrink_zones(int priority, struct zonelist *zonelist,
					struct scan_control *sc)
{
	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
	struct zoneref *z;
	struct zone *zone;

	sc->all_unreclaimable = 1;
	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
		if (!populated_zone(zone))
			continue;
		/*
		 * Take care memory controller reclaiming has small influence
		 * to global LRU.
		 */
		if (scanning_global_lru(sc)) {
			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
				continue;
			note_zone_scanning_priority(zone, priority);

			if (zone_is_all_unreclaimable(zone) &&
						priority != DEF_PRIORITY)
				continue;	/* Let kswapd poll it */
			sc->all_unreclaimable = 0;
		} else {
			/*
			 * Ignore cpuset limitation here. We just want to reduce
			 * # of used pages by us regardless of memory shortage.
			 */
			sc->all_unreclaimable = 0;
			mem_cgroup_note_reclaim_priority(sc->mem_cgroup,
							priority);
		}

		shrink_zone(priority, zone, sc);
	}
}

/*
 * This is the main entry point to direct page reclaim.
 *
 * If a full scan of the inactive list fails to free enough memory then we
 * are "out of memory" and something needs to be killed.
 *
 * If the caller is !__GFP_FS then the probability of a failure is reasonably
 * high - the zone may be full of dirty or under-writeback pages, which this
 * 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.
 *
 * returns:	0, if no pages reclaimed
 * 		else, the number of pages reclaimed
 */
static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
					struct scan_control *sc)
{
	int priority;
	unsigned long ret = 0;
	unsigned long total_scanned = 0;
	struct reclaim_state *reclaim_state = current->reclaim_state;
	unsigned long lru_pages = 0;
	struct zoneref *z;
	struct zone *zone;
	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);

	delayacct_freepages_start();

	if (scanning_global_lru(sc))
		count_vm_event(ALLOCSTALL);
	/*
	 * mem_cgroup will not do shrink_slab.
	 */
	if (scanning_global_lru(sc)) {
		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {

			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
				continue;

			lru_pages += zone_lru_pages(zone);
		}
	}

	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
		sc->nr_scanned = 0;
		if (!priority)
			disable_swap_token();
		shrink_zones(priority, zonelist, sc);
		/*
		 * Don't shrink slabs when reclaiming memory from
		 * over limit cgroups
		 */
		if (scanning_global_lru(sc)) {
			shrink_slab(sc->nr_scanned, sc->gfp_mask, lru_pages);
			if (reclaim_state) {
				sc->nr_reclaimed += reclaim_state->reclaimed_slab;
				reclaim_state->reclaimed_slab = 0;
			}
		}
		total_scanned += sc->nr_scanned;
		if (sc->nr_reclaimed >= sc->swap_cluster_max) {
			ret = sc->nr_reclaimed;
			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)
			congestion_wait(WRITE, HZ/10);
	}
	/* top priority shrink_zones still had more to do? don't OOM, then */
	if (!sc->all_unreclaimable && scanning_global_lru(sc))
		ret = sc->nr_reclaimed;
out:
	/*
	 * Now that we've scanned all the zones at this priority level, note
	 * that level within the zone so that the next thread which performs
	 * scanning of this zone will immediately start out at this priority
	 * level.  This affects only the decision whether or not to bring
	 * mapped pages onto the inactive list.
	 */
	if (priority < 0)
		priority = 0;

	if (scanning_global_lru(sc)) {
		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {

			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
				continue;

			zone->prev_priority = priority;
		}
	} else
		mem_cgroup_record_reclaim_priority(sc->mem_cgroup, priority);

	delayacct_freepages_end();

	return ret;
}

unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
								gfp_t gfp_mask)
{
	struct scan_control sc = {
		.gfp_mask = gfp_mask,
		.may_writepage = !laptop_mode,
		.swap_cluster_max = SWAP_CLUSTER_MAX,
		.may_swap = 1,
		.swappiness = vm_swappiness,
		.order = order,
		.mem_cgroup = NULL,
		.isolate_pages = isolate_pages_global,
	};

	return do_try_to_free_pages(zonelist, &sc);
}

#ifdef CONFIG_CGROUP_MEM_RES_CTLR

unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
					   gfp_t gfp_mask,
					   bool noswap,
					   unsigned int swappiness)
{
	struct scan_control sc = {
		.may_writepage = !laptop_mode,
		.may_swap = 1,
		.swap_cluster_max = SWAP_CLUSTER_MAX,
		.swappiness = swappiness,
		.order = 0,
		.mem_cgroup = mem_cont,
		.isolate_pages = mem_cgroup_isolate_pages,
	};
	struct zonelist *zonelist;

	if (noswap)
		sc.may_swap = 0;

	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
	zonelist = NODE_DATA(numa_node_id())->node_zonelists;
	return do_try_to_free_pages(zonelist, &sc);
}
#endif

/*
 * For kswapd, balance_pgdat() will work across all this node's zones until
 * they are all at pages_high.
 *
 * 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 unsigned long balance_pgdat(pg_data_t *pgdat, int order)
{
	int all_zones_ok;
	int priority;
	int i;
	unsigned long total_scanned;
	struct reclaim_state *reclaim_state = current->reclaim_state;
	struct scan_control sc = {
		.gfp_mask = GFP_KERNEL,
		.may_swap = 1,
		.swap_cluster_max = SWAP_CLUSTER_MAX,
		.swappiness = vm_swappiness,
		.order = order,
		.mem_cgroup = NULL,
		.isolate_pages = isolate_pages_global,
	};
	/*
	 * temp_priority is used to remember the scanning priority at which
	 * this zone was successfully refilled to free_pages == pages_high.
	 */
	int temp_priority[MAX_NR_ZONES];

loop_again:
	total_scanned = 0;
	sc.nr_reclaimed = 0;
	sc.may_writepage = !laptop_mode;
	count_vm_event(PAGEOUTRUN);

	for (i = 0; i < pgdat->nr_zones; i++)
		temp_priority[i] = 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;

		/*
		 * 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_is_all_unreclaimable(zone) &&
			    priority != DEF_PRIORITY)
				continue;

			/*
			 * Do some background aging of the anon list, to give
			 * pages a chance to be referenced before reclaiming.
			 */
			if (inactive_anon_is_low(zone, &sc))
				shrink_active_list(SWAP_CLUSTER_MAX, zone,
							&sc, priority, 0);

			if (!zone_watermark_ok(zone, order, zone->pages_high,
					       0, 0)) {
				end_zone = i;
				break;
			}
		}
		if (i < 0)
			goto out;

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

			lru_pages += zone_lru_pages(zone);
		}

		/*
		 * 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_is_all_unreclaimable(zone) &&
					priority != DEF_PRIORITY)
				continue;

			if (!zone_watermark_ok(zone, order, zone->pages_high,
					       end_zone, 0))
				all_zones_ok = 0;
			temp_priority[i] = priority;
			sc.nr_scanned = 0;
			note_zone_scanning_priority(zone, priority);
			/*
			 * We put equal pressure on every zone, unless one
			 * zone has way too many pages free already.
			 */
			if (!zone_watermark_ok(zone, order, 8*zone->pages_high,
						end_zone, 0))
				shrink_zone(priority, zone, &sc);
			reclaim_state->reclaimed_slab = 0;
			nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
						lru_pages);
			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
			total_scanned += sc.nr_scanned;
			if (zone_is_all_unreclaimable(zone))