vmscan.c

ARM 嵌入式 系统 设计与实例开发 实验教材 二源码

		 */
		if (unlikely(TryLockPage(page))) {
			if (PageLaunder(page) && (gfp_mask & __GFP_FS)) {
				page_cache_get(page);
				spin_unlock(&pagemap_lru_lock);
				wait_on_page(page);
				page_cache_release(page);
				spin_lock(&pagemap_lru_lock);
			}
			continue;
		}

		if (PageDirty(page) && is_page_cache_freeable(page) && page->mapping) {
			/*
			 * It is not critical here to write it only if
			 * the page is unmapped beause any direct writer
			 * like O_DIRECT would set the PG_dirty bitflag
			 * on the phisical page after having successfully
			 * pinned it and after the I/O to the page is finished,
			 * so the direct writes to the page cannot get lost.
			 */
			int (*writepage)(struct page *);

			writepage = page->mapping->a_ops->writepage;
			if ((gfp_mask & __GFP_FS) && writepage) {
				ClearPageDirty(page);
				SetPageLaunder(page);
				page_cache_get(page);
				spin_unlock(&pagemap_lru_lock);

				writepage(page);
				page_cache_release(page);

				spin_lock(&pagemap_lru_lock);
				continue;
			}
		}

		/*
		 * If the page has buffers, try to free the buffer mappings
		 * associated with this page. If we succeed we try to free
		 * the page as well.
		 */
		if (page->buffers) {
			spin_unlock(&pagemap_lru_lock);

			/* avoid to free a locked page */
			page_cache_get(page);

			if (try_to_release_page(page, gfp_mask)) {
				if (!page->mapping) {
					/*
					 * We must not allow an anon page
					 * with no buffers to be visible on
					 * the LRU, so we unlock the page after
					 * taking the lru lock
					 */
					spin_lock(&pagemap_lru_lock);
					UnlockPage(page);
					__lru_cache_del(page);

					/* effectively free the page here */
					page_cache_release(page);

					if (--nr_pages)
						continue;
					break;
				} else {
					/*
					 * The page is still in pagecache so undo the stuff
					 * before the try_to_release_page since we've not
					 * finished and we can now try the next step.
					 */
					page_cache_release(page);

					spin_lock(&pagemap_lru_lock);
				}
			} else {
				/* failed to drop the buffers so stop here */
				UnlockPage(page);
				page_cache_release(page);

				spin_lock(&pagemap_lru_lock);
				continue;
			}
		}

		spin_lock(&pagecache_lock);

		/*
		 * this is the non-racy check for busy page.
		 */
		if (!page->mapping || !is_page_cache_freeable(page)) {
			spin_unlock(&pagecache_lock);
			UnlockPage(page);
page_mapped:
			if (--max_mapped >= 0)
				continue;

			/*
			 * Alert! We've found too many mapped pages on the
			 * inactive list, so we start swapping out now!
			 */
			spin_unlock(&pagemap_lru_lock);
			swap_out(priority, gfp_mask, classzone);
			return nr_pages;
		}

		/*
		 * It is critical to check PageDirty _after_ we made sure
		 * the page is freeable* so not in use by anybody.
		 */
		if (PageDirty(page)) {
			spin_unlock(&pagecache_lock);
			UnlockPage(page);
			continue;
		}

		/* point of no return */
		if (likely(!PageSwapCache(page))) {
			__remove_inode_page(page);
			spin_unlock(&pagecache_lock);
		} else {
			swp_entry_t swap;
			swap.val = page->index;
			__delete_from_swap_cache(page);
			spin_unlock(&pagecache_lock);
			swap_free(swap);
		}

		__lru_cache_del(page);
		UnlockPage(page);

		/* effectively free the page here */
		page_cache_release(page);

		if (--nr_pages)
			continue;
		break;
	}
	spin_unlock(&pagemap_lru_lock);

	return nr_pages;
}

/*
 * This moves pages from the active list to
 * the inactive list.
 *
 * We move them the other way when we see the
 * reference bit on the page.
 */
static void refill_inactive(int nr_pages)
{
	struct list_head * entry;

	spin_lock(&pagemap_lru_lock);
	entry = active_list.prev;
	while (nr_pages && entry != &active_list) {
		struct page * page;

		page = list_entry(entry, struct page, lru);
		entry = entry->prev;
		if (PageTestandClearReferenced(page)) {
			list_del(&page->lru);
			list_add(&page->lru, &active_list);
			continue;
		}

		nr_pages--;

		del_page_from_active_list(page);
		add_page_to_inactive_list(page);
		SetPageReferenced(page);
	}
	spin_unlock(&pagemap_lru_lock);
}

static int FASTCALL(shrink_caches(zone_t * classzone, int priority, unsigned int gfp_mask, int nr_pages));
static int shrink_caches(zone_t * classzone, int priority, unsigned int gfp_mask, int nr_pages)
{
	int chunk_size = nr_pages;
	unsigned long ratio;

	nr_pages -= kmem_cache_reap(gfp_mask);
	if (nr_pages <= 0)
		return 0;

	nr_pages = chunk_size;
	/* try to keep the active list 2/3 of the size of the cache */
	ratio = (unsigned long) nr_pages * nr_active_pages / ((nr_inactive_pages + 1) * 2);
	refill_inactive(ratio);

	nr_pages = shrink_cache(nr_pages, classzone, gfp_mask, priority);
	if (nr_pages <= 0)
		return 0;

	shrink_dcache_memory(priority, gfp_mask);
	shrink_icache_memory(priority, gfp_mask);
#ifdef CONFIG_QUOTA
	shrink_dqcache_memory(DEF_PRIORITY, gfp_mask);
#endif

	return nr_pages;
}

int try_to_free_pages(zone_t *classzone, unsigned int gfp_mask, unsigned int order)
{
	int priority = DEF_PRIORITY;
	int nr_pages = SWAP_CLUSTER_MAX;

	gfp_mask = pf_gfp_mask(gfp_mask);
	do {
		nr_pages = shrink_caches(classzone, priority, gfp_mask, nr_pages);
		if (nr_pages <= 0)
			return 1;
	} while (--priority);

	/*
	 * Hmm.. Cache shrink failed - time to kill something?
	 * Mhwahahhaha! This is the part I really like. Giggle.
	 */
#ifndef CONFIG_NO_OOM_KILLER
	out_of_memory();
#endif
	return 0;
}

DECLARE_WAIT_QUEUE_HEAD(kswapd_wait);

static int check_classzone_need_balance(zone_t * classzone)
{
	zone_t * first_classzone;

	first_classzone = classzone->zone_pgdat->node_zones;
	while (classzone >= first_classzone) {
		if (classzone->free_pages > classzone->pages_high)
			return 0;
		classzone--;
	}
	return 1;
}

static int kswapd_balance_pgdat(pg_data_t * pgdat)
{
	int need_more_balance = 0, i;
	zone_t * zone;

	for (i = pgdat->nr_zones-1; i >= 0; i--) {
		zone = pgdat->node_zones + i;
		if (unlikely(current->need_resched))
			schedule();
		if (!zone->need_balance)
			continue;
		if (!try_to_free_pages(zone, GFP_KSWAPD, 0)) {
			zone->need_balance = 0;
			__set_current_state(TASK_INTERRUPTIBLE);
			schedule_timeout(HZ);
			continue;
		}
		if (check_classzone_need_balance(zone))
			need_more_balance = 1;
		else
			zone->need_balance = 0;
	}

	return need_more_balance;
}

static void kswapd_balance(void)
{
	int need_more_balance;
	pg_data_t * pgdat;

	do {
		need_more_balance = 0;
		pgdat = pgdat_list;
		do
			need_more_balance |= kswapd_balance_pgdat(pgdat);
		while ((pgdat = pgdat->node_next));
	} while (need_more_balance);
}

static int kswapd_can_sleep_pgdat(pg_data_t * pgdat)
{
	zone_t * zone;
	int i;

	for (i = pgdat->nr_zones-1; i >= 0; i--) {
		zone = pgdat->node_zones + i;
		if (!zone->need_balance)
			continue;
		return 0;
	}

	return 1;
}

static int kswapd_can_sleep(void)
{
	pg_data_t * pgdat;

	pgdat = pgdat_list;
	do {
		if (kswapd_can_sleep_pgdat(pgdat))
			continue;
		return 0;
	} while ((pgdat = pgdat->node_next));

	return 1;
}

/*
 * 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.
 */
int kswapd(void *unused)
{
	struct task_struct *tsk = current;
	DECLARE_WAITQUEUE(wait, tsk);

	daemonize();
	strcpy(tsk->comm, "kswapd");
	sigfillset(&tsk->blocked);
	
	/*
	 * 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;

	/*
	 * Kswapd main loop.
	 */
	for (;;) {
		__set_current_state(TASK_INTERRUPTIBLE);
		add_wait_queue(&kswapd_wait, &wait);

		mb();
		if (kswapd_can_sleep())
			schedule();

		__set_current_state(TASK_RUNNING);
		remove_wait_queue(&kswapd_wait, &wait);

		/*
		 * If we actually get into a low-memory situation,
		 * the processes needing more memory will wake us
		 * up on a more timely basis.
		 */
		kswapd_balance();
		run_task_queue(&tq_disk);
	}
}

static int __init kswapd_init(void)
{
	printk("Starting kswapd\n");
	swap_setup();
	kernel_thread(kswapd, NULL, CLONE_FS | CLONE_FILES | CLONE_SIGNAL);
	return 0;
}

module_init(kswapd_init)