vmscan.c

最新最稳定的Linux内存管理模块源代码

				nr_taken++;
				scan++;
				break;

			case -EBUSY:
				/* else it is being freed elsewhere */
				list_move(&cursor_page->lru, src);
			default:
				break;	/* ! on LRU or wrong list */
			}
		}
	}

	*scanned = scan;
	return nr_taken;
}

static unsigned long isolate_pages_global(unsigned long nr,
					struct list_head *dst,
					unsigned long *scanned, int order,
					int mode, struct zone *z,
					struct mem_cgroup *mem_cont,
					int active, int file)
{
	int lru = LRU_BASE;
	if (active)
		lru += LRU_ACTIVE;
	if (file)
		lru += LRU_FILE;
	return isolate_lru_pages(nr, &z->lru[lru].list, dst, scanned, order,
								mode, !!file);
}

/*
 * clear_active_flags() is a helper for shrink_active_list(), clearing
 * any active bits from the pages in the list.
 */
static unsigned long clear_active_flags(struct list_head *page_list,
					unsigned int *count)
{
	int nr_active = 0;
	int lru;
	struct page *page;

	list_for_each_entry(page, page_list, lru) {
		lru = page_is_file_cache(page);
		if (PageActive(page)) {
			lru += LRU_ACTIVE;
			ClearPageActive(page);
			nr_active++;
		}
		count[lru]++;
	}

	return nr_active;
}

/**
 * isolate_lru_page - tries to isolate a page from its LRU list
 * @page: page to isolate from its LRU list
 *
 * Isolates a @page from an LRU list, clears PageLRU and adjusts the
 * vmstat statistic corresponding to whatever LRU list the page was on.
 *
 * Returns 0 if the page was removed from an LRU list.
 * Returns -EBUSY if the page was not on an LRU list.
 *
 * The returned page will have PageLRU() cleared.  If it was found on
 * the active list, it will have PageActive set.  If it was found on
 * the unevictable list, it will have the PageUnevictable bit set. That flag
 * may need to be cleared by the caller before letting the page go.
 *
 * The vmstat statistic corresponding to the list on which the page was
 * found will be decremented.
 *
 * Restrictions:
 * (1) Must be called with an elevated refcount on the page. This is a
 *     fundamentnal difference from isolate_lru_pages (which is called
 *     without a stable reference).
 * (2) the lru_lock must not be held.
 * (3) interrupts must be enabled.
 */
int isolate_lru_page(struct page *page)
{
	int ret = -EBUSY;

	if (PageLRU(page)) {
		struct zone *zone = page_zone(page);

		spin_lock_irq(&zone->lru_lock);
		if (PageLRU(page) && get_page_unless_zero(page)) {
			int lru = page_lru(page);
			ret = 0;
			ClearPageLRU(page);

			del_page_from_lru_list(zone, page, lru);
		}
		spin_unlock_irq(&zone->lru_lock);
	}
	return ret;
}

/*
 * shrink_inactive_list() is a helper for shrink_zone().  It returns the number
 * of reclaimed pages
 */
static unsigned long shrink_inactive_list(unsigned long max_scan,
			struct zone *zone, struct scan_control *sc,
			int priority, int file)
{
	LIST_HEAD(page_list);
	struct pagevec pvec;
	unsigned long nr_scanned = 0;
	unsigned long nr_reclaimed = 0;
	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);

	pagevec_init(&pvec, 1);

	lru_add_drain();
	spin_lock_irq(&zone->lru_lock);
	do {
		struct page *page;
		unsigned long nr_taken;
		unsigned long nr_scan;
		unsigned long nr_freed;
		unsigned long nr_active;
		unsigned int count[NR_LRU_LISTS] = { 0, };
		int mode = ISOLATE_INACTIVE;

		/*
		 * If we need a large contiguous chunk of memory, or have
		 * trouble getting a small set of contiguous pages, we
		 * will reclaim both active and inactive pages.
		 *
		 * We use the same threshold as pageout congestion_wait below.
		 */
		if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
			mode = ISOLATE_BOTH;
		else if (sc->order && priority < DEF_PRIORITY - 2)
			mode = ISOLATE_BOTH;

		nr_taken = sc->isolate_pages(sc->swap_cluster_max,
			     &page_list, &nr_scan, sc->order, mode,
				zone, sc->mem_cgroup, 0, file);
		nr_active = clear_active_flags(&page_list, count);
		__count_vm_events(PGDEACTIVATE, nr_active);

		__mod_zone_page_state(zone, NR_ACTIVE_FILE,
						-count[LRU_ACTIVE_FILE]);
		__mod_zone_page_state(zone, NR_INACTIVE_FILE,
						-count[LRU_INACTIVE_FILE]);
		__mod_zone_page_state(zone, NR_ACTIVE_ANON,
						-count[LRU_ACTIVE_ANON]);
		__mod_zone_page_state(zone, NR_INACTIVE_ANON,
						-count[LRU_INACTIVE_ANON]);

		if (scanning_global_lru(sc))
			zone->pages_scanned += nr_scan;

		reclaim_stat->recent_scanned[0] += count[LRU_INACTIVE_ANON];
		reclaim_stat->recent_scanned[0] += count[LRU_ACTIVE_ANON];
		reclaim_stat->recent_scanned[1] += count[LRU_INACTIVE_FILE];
		reclaim_stat->recent_scanned[1] += count[LRU_ACTIVE_FILE];

		spin_unlock_irq(&zone->lru_lock);

		nr_scanned += nr_scan;
		nr_freed = shrink_page_list(&page_list, sc, PAGEOUT_IO_ASYNC);

		/*
		 * If we are direct reclaiming for contiguous pages and we do
		 * not reclaim everything in the list, try again and wait
		 * for IO to complete. This will stall high-order allocations
		 * but that should be acceptable to the caller
		 */
		if (nr_freed < nr_taken && !current_is_kswapd() &&
					sc->order > PAGE_ALLOC_COSTLY_ORDER) {
			congestion_wait(WRITE, HZ/10);

			/*
			 * The attempt at page out may have made some
			 * of the pages active, mark them inactive again.
			 */
			nr_active = clear_active_flags(&page_list, count);
			count_vm_events(PGDEACTIVATE, nr_active);

			nr_freed += shrink_page_list(&page_list, sc,
							PAGEOUT_IO_SYNC);
		}

		nr_reclaimed += nr_freed;
		local_irq_disable();
		if (current_is_kswapd()) {
			__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scan);
			__count_vm_events(KSWAPD_STEAL, nr_freed);
		} else if (scanning_global_lru(sc))
			__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);

		__count_zone_vm_events(PGSTEAL, zone, nr_freed);

		if (nr_taken == 0)
			goto done;

		spin_lock(&zone->lru_lock);
		/*
		 * Put back any unfreeable pages.
		 */
		while (!list_empty(&page_list)) {
			int lru;
			page = lru_to_page(&page_list);
			VM_BUG_ON(PageLRU(page));
			list_del(&page->lru);
			if (unlikely(!page_evictable(page, NULL))) {
				spin_unlock_irq(&zone->lru_lock);
				putback_lru_page(page);
				spin_lock_irq(&zone->lru_lock);
				continue;
			}
			SetPageLRU(page);
			lru = page_lru(page);
			add_page_to_lru_list(zone, page, lru);
			if (PageActive(page)) {
				int file = !!page_is_file_cache(page);
				reclaim_stat->recent_rotated[file]++;
			}
			if (!pagevec_add(&pvec, page)) {
				spin_unlock_irq(&zone->lru_lock);
				__pagevec_release(&pvec);
				spin_lock_irq(&zone->lru_lock);
			}
		}
  	} while (nr_scanned < max_scan);
	spin_unlock(&zone->lru_lock);
done:
	local_irq_enable();
	pagevec_release(&pvec);
	return nr_reclaimed;
}

/*
 * We are about to scan this zone at a certain priority level.  If that priority
 * level is smaller (ie: more urgent) than the previous priority, then note
 * that priority level within the zone.  This is done so that when the next
 * process comes in to scan this zone, it will immediately start out at this
 * priority level rather than having to build up its own scanning priority.
 * Here, this priority affects only the reclaim-mapped threshold.
 */
static inline void note_zone_scanning_priority(struct zone *zone, int priority)
{
	if (priority < zone->prev_priority)
		zone->prev_priority = priority;
}

/*
 * This moves pages from the active list to the inactive list.
 *
 * We move them the other way if the page is referenced by one or more
 * processes, from rmap.
 *
 * If the pages are mostly unmapped, the processing is fast and it is
 * appropriate to hold zone->lru_lock across the whole operation.  But if
 * the pages are mapped, the processing is slow (page_referenced()) so we
 * should drop zone->lru_lock around each page.  It's impossible to balance
 * this, so instead we remove the pages from the LRU while processing them.
 * It is safe to rely on PG_active against the non-LRU pages in here because
 * nobody will play with that bit on a non-LRU page.
 *
 * The downside is that we have to touch page->_count against each page.
 * But we had to alter page->flags anyway.
 */


static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
			struct scan_control *sc, int priority, int file)
{
	unsigned long pgmoved;
	int pgdeactivate = 0;
	unsigned long pgscanned;
	LIST_HEAD(l_hold);	/* The pages which were snipped off */
	LIST_HEAD(l_inactive);
	struct page *page;
	struct pagevec pvec;
	enum lru_list lru;
	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);

	lru_add_drain();
	spin_lock_irq(&zone->lru_lock);
	pgmoved = sc->isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order,
					ISOLATE_ACTIVE, zone,
					sc->mem_cgroup, 1, file);
	/*
	 * zone->pages_scanned is used for detect zone's oom
	 * mem_cgroup remembers nr_scan by itself.
	 */
	if (scanning_global_lru(sc)) {
		zone->pages_scanned += pgscanned;
	}
	reclaim_stat->recent_scanned[!!file] += pgmoved;

	if (file)
		__mod_zone_page_state(zone, NR_ACTIVE_FILE, -pgmoved);
	else
		__mod_zone_page_state(zone, NR_ACTIVE_ANON, -pgmoved);
	spin_unlock_irq(&zone->lru_lock);

	pgmoved = 0;
	while (!list_empty(&l_hold)) {
		cond_resched();
		page = lru_to_page(&l_hold);
		list_del(&page->lru);

		if (unlikely(!page_evictable(page, NULL))) {
			putback_lru_page(page);
			continue;
		}

		/* page_referenced clears PageReferenced */
		if (page_mapping_inuse(page) &&
		    page_referenced(page, 0, sc->mem_cgroup))
			pgmoved++;

		list_add(&page->lru, &l_inactive);
	}

	/*
	 * Move the pages to the [file or anon] inactive list.
	 */
	pagevec_init(&pvec, 1);
	lru = LRU_BASE + file * LRU_FILE;

	spin_lock_irq(&zone->lru_lock);
	/*
	 * Count referenced pages from currently used mappings as
	 * rotated, even though they are moved to the inactive list.
	 * This helps balance scan pressure between file and anonymous
	 * pages in get_scan_ratio.
	 */
	reclaim_stat->recent_rotated[!!file] += pgmoved;

	pgmoved = 0;
	while (!list_empty(&l_inactive)) {
		page = lru_to_page(&l_inactive);
		prefetchw_prev_lru_page(page, &l_inactive, flags);
		VM_BUG_ON(PageLRU(page));
		SetPageLRU(page);
		VM_BUG_ON(!PageActive(page));
		ClearPageActive(page);

		list_move(&page->lru, &zone->lru[lru].list);
		mem_cgroup_add_lru_list(page, lru);
		pgmoved++;
		if (!pagevec_add(&pvec, page)) {
			__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
			spin_unlock_irq(&zone->lru_lock);
			pgdeactivate += pgmoved;
			pgmoved = 0;
			if (buffer_heads_over_limit)
				pagevec_strip(&pvec);
			__pagevec_release(&pvec);
			spin_lock_irq(&zone->lru_lock);
		}
	}
	__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
	pgdeactivate += pgmoved;
	if (buffer_heads_over_limit) {
		spin_unlock_irq(&zone->lru_lock);
		pagevec_strip(&pvec);
		spin_lock_irq(&zone->lru_lock);
	}
	__count_zone_vm_events(PGREFILL, zone, pgscanned);
	__count_vm_events(PGDEACTIVATE, pgdeactivate);
	spin_unlock_irq(&zone->lru_lock);
	if (vm_swap_full())
		pagevec_swap_free(&pvec);

	pagevec_release(&pvec);
}

static int inactive_anon_is_low_global(struct zone *zone)
{
	unsigned long active, inactive;

	active = zone_page_state(zone, NR_ACTIVE_ANON);
	inactive = zone_page_state(zone, NR_INACTIVE_ANON);

	if (inactive * zone->inactive_ratio < active)
		return 1;

	return 0;
}

/**
 * inactive_anon_is_low - check if anonymous pages need to be deactivated
 * @zone: zone to check
 * @sc:   scan control of this context
 *
 * Returns true if the zone does not have enough inactive anon pages,
 * meaning some active anon pages need to be deactivated.
 */
static int inactive_anon_is_low(struct zone *zone, struct scan_control *sc)
{
	int low;

	if (scanning_global_lru(sc))
		low = inactive_anon_is_low_global(zone);
	else
		low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup);
	return low;
}

static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
	struct zone *zone, struct scan_control *sc, int priority)
{
	int file = is_file_lru(lru);

	if (lru == LRU_ACTIVE_FILE) {
		shrink_active_list(nr_to_scan, zone, sc, priority, file);
		return 0;
	}

	if (lru == LRU_ACTIVE_ANON && inactive_anon_is_low(zone, sc)) {
		shrink_active_list(nr_to_scan, zone, sc, priority, file);
		return 0;
	}
	return shrink_inactive_list(nr_to_scan, zone, sc, priority, file);
}

/*
 * Determine how aggressively the anon and file LRU lists should be
 * scanned.  The relative value of each set of LRU lists is determined
 * by looking at the fraction of the pages scanned we did rotate back
 * onto the active list instead of evict.
 *
 * percent[0] specifies how much pressure to put on ram/swap backed
 * memory, while percent[1] determines pressure on the file LRUs.
 */
static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
					unsigned long *percent)
{
	unsigned long anon, file, free;
	unsigned long anon_prio, file_prio;
	unsigned long ap, fp;
	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);

	/* If we have no swap space, do not bother scanning anon pages. */
	if (nr_swap_pages <= 0) {
		percent[0] = 0;
		percent[1] = 100;
		return;
	}

	anon  = zone_nr_pages(zone, sc, LRU_ACTIVE_ANON) +
		zone_nr_pages(zone, sc, LRU_INACTIVE_ANON);
	file  = zone_nr_pages(zone, sc, LRU_ACTIVE_FILE) +
		zone_nr_pages(zone, sc, LRU_INACTIVE_FILE);

	if (scanning_global_lru(sc)) {
		free  = zone_page_state(zone, NR_FREE_PAGES);
		/* If we have very few page cache pages,
		   force-scan anon pages. */
		if (unlikely(file + free <= zone->pages_high)) {
			percent[0] = 100;
			percent[1] = 0;
			return;
		}
	}

	/*