filemap.c

最新最稳定的Linux内存管理模块源代码

EXPORT_SYMBOL(add_to_page_cache_locked);

int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
				pgoff_t offset, gfp_t gfp_mask)
{
	int ret;

	/*
	 * Splice_read and readahead add shmem/tmpfs pages into the page cache
	 * before shmem_readpage has a chance to mark them as SwapBacked: they
	 * need to go on the active_anon lru below, and mem_cgroup_cache_charge
	 * (called in add_to_page_cache) needs to know where they're going too.
	 */
	if (mapping_cap_swap_backed(mapping))
		SetPageSwapBacked(page);

	ret = add_to_page_cache(page, mapping, offset, gfp_mask);
	if (ret == 0) {
		if (page_is_file_cache(page))
			lru_cache_add_file(page);
		else
			lru_cache_add_active_anon(page);
	}
	return ret;
}

#ifdef CONFIG_NUMA
struct page *__page_cache_alloc(gfp_t gfp)
{
	if (cpuset_do_page_mem_spread()) {
		int n = cpuset_mem_spread_node();
		return alloc_pages_node(n, gfp, 0);
	}
	return alloc_pages(gfp, 0);
}
EXPORT_SYMBOL(__page_cache_alloc);
#endif

static int __sleep_on_page_lock(void *word)
{
	io_schedule();
	return 0;
}

/*
 * In order to wait for pages to become available there must be
 * waitqueues associated with pages. By using a hash table of
 * waitqueues where the bucket discipline is to maintain all
 * waiters on the same queue and wake all when any of the pages
 * become available, and for the woken contexts to check to be
 * sure the appropriate page became available, this saves space
 * at a cost of "thundering herd" phenomena during rare hash
 * collisions.
 */
static wait_queue_head_t *page_waitqueue(struct page *page)
{
	const struct zone *zone = page_zone(page);

	return &zone->wait_table[hash_ptr(page, zone->wait_table_bits)];
}

static inline void wake_up_page(struct page *page, int bit)
{
	__wake_up_bit(page_waitqueue(page), &page->flags, bit);
}

void wait_on_page_bit(struct page *page, int bit_nr)
{
	DEFINE_WAIT_BIT(wait, &page->flags, bit_nr);

	if (test_bit(bit_nr, &page->flags))
		__wait_on_bit(page_waitqueue(page), &wait, sync_page,
							TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_on_page_bit);

/**
 * unlock_page - unlock a locked page
 * @page: the page
 *
 * Unlocks the page and wakes up sleepers in ___wait_on_page_locked().
 * Also wakes sleepers in wait_on_page_writeback() because the wakeup
 * mechananism between PageLocked pages and PageWriteback pages is shared.
 * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
 *
 * The mb is necessary to enforce ordering between the clear_bit and the read
 * of the waitqueue (to avoid SMP races with a parallel wait_on_page_locked()).
 */
void unlock_page(struct page *page)
{
	VM_BUG_ON(!PageLocked(page));
	clear_bit_unlock(PG_locked, &page->flags);
	smp_mb__after_clear_bit();
	wake_up_page(page, PG_locked);
}
EXPORT_SYMBOL(unlock_page);

/**
 * end_page_writeback - end writeback against a page
 * @page: the page
 */
void end_page_writeback(struct page *page)
{
	if (TestClearPageReclaim(page))
		rotate_reclaimable_page(page);

	if (!test_clear_page_writeback(page))
		BUG();

	smp_mb__after_clear_bit();
	wake_up_page(page, PG_writeback);
}
EXPORT_SYMBOL(end_page_writeback);

/**
 * __lock_page - get a lock on the page, assuming we need to sleep to get it
 * @page: the page to lock
 *
 * Ugly. Running sync_page() in state TASK_UNINTERRUPTIBLE is scary.  If some
 * random driver's requestfn sets TASK_RUNNING, we could busywait.  However
 * chances are that on the second loop, the block layer's plug list is empty,
 * so sync_page() will then return in state TASK_UNINTERRUPTIBLE.
 */
void __lock_page(struct page *page)
{
	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);

	__wait_on_bit_lock(page_waitqueue(page), &wait, sync_page,
							TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(__lock_page);

int __lock_page_killable(struct page *page)
{
	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);

	return __wait_on_bit_lock(page_waitqueue(page), &wait,
					sync_page_killable, TASK_KILLABLE);
}

/**
 * __lock_page_nosync - get a lock on the page, without calling sync_page()
 * @page: the page to lock
 *
 * Variant of lock_page that does not require the caller to hold a reference
 * on the page's mapping.
 */
void __lock_page_nosync(struct page *page)
{
	DEFINE_WAIT_BIT(wait, &page->flags, PG_locked);
	__wait_on_bit_lock(page_waitqueue(page), &wait, __sleep_on_page_lock,
							TASK_UNINTERRUPTIBLE);
}

/**
 * find_get_page - find and get a page reference
 * @mapping: the address_space to search
 * @offset: the page index
 *
 * Is there a pagecache struct page at the given (mapping, offset) tuple?
 * If yes, increment its refcount and return it; if no, return NULL.
 */
struct page *find_get_page(struct address_space *mapping, pgoff_t offset)
{
	void **pagep;
	struct page *page;

	rcu_read_lock();
repeat:
	page = NULL;
	pagep = radix_tree_lookup_slot(&mapping->page_tree, offset);
	if (pagep) {
		page = radix_tree_deref_slot(pagep);
		if (unlikely(!page || page == RADIX_TREE_RETRY))
			goto repeat;

		if (!page_cache_get_speculative(page))
			goto repeat;

		/*
		 * Has the page moved?
		 * This is part of the lockless pagecache protocol. See
		 * include/linux/pagemap.h for details.
		 */
		if (unlikely(page != *pagep)) {
			page_cache_release(page);
			goto repeat;
		}
	}
	rcu_read_unlock();

	return page;
}
EXPORT_SYMBOL(find_get_page);

/**
 * find_lock_page - locate, pin and lock a pagecache page
 * @mapping: the address_space to search
 * @offset: the page index
 *
 * Locates the desired pagecache page, locks it, increments its reference
 * count and returns its address.
 *
 * Returns zero if the page was not present. find_lock_page() may sleep.
 */
struct page *find_lock_page(struct address_space *mapping, pgoff_t offset)
{
	struct page *page;

repeat:
	page = find_get_page(mapping, offset);
	if (page) {
		lock_page(page);
		/* Has the page been truncated? */
		if (unlikely(page->mapping != mapping)) {
			unlock_page(page);
			page_cache_release(page);
			goto repeat;
		}
		VM_BUG_ON(page->index != offset);
	}
	return page;
}
EXPORT_SYMBOL(find_lock_page);

/**
 * find_or_create_page - locate or add a pagecache page
 * @mapping: the page's address_space
 * @index: the page's index into the mapping
 * @gfp_mask: page allocation mode
 *
 * Locates a page in the pagecache.  If the page is not present, a new page
 * is allocated using @gfp_mask and is added to the pagecache and to the VM's
 * LRU list.  The returned page is locked and has its reference count
 * incremented.
 *
 * find_or_create_page() may sleep, even if @gfp_flags specifies an atomic
 * allocation!
 *
 * find_or_create_page() returns the desired page's address, or zero on
 * memory exhaustion.
 */
struct page *find_or_create_page(struct address_space *mapping,
		pgoff_t index, gfp_t gfp_mask)
{
	struct page *page;
	int err;
repeat:
	page = find_lock_page(mapping, index);
	if (!page) {
		page = __page_cache_alloc(gfp_mask);
		if (!page)
			return NULL;
		/*
		 * We want a regular kernel memory (not highmem or DMA etc)
		 * allocation for the radix tree nodes, but we need to honour
		 * the context-specific requirements the caller has asked for.
		 * GFP_RECLAIM_MASK collects those requirements.
		 */
		err = add_to_page_cache_lru(page, mapping, index,
			(gfp_mask & GFP_RECLAIM_MASK));
		if (unlikely(err)) {
			page_cache_release(page);
			page = NULL;
			if (err == -EEXIST)
				goto repeat;
		}
	}
	return page;
}
EXPORT_SYMBOL(find_or_create_page);

/**
 * find_get_pages - gang pagecache lookup
 * @mapping:	The address_space to search
 * @start:	The starting page index
 * @nr_pages:	The maximum number of pages
 * @pages:	Where the resulting pages are placed
 *
 * find_get_pages() will search for and return a group of up to
 * @nr_pages pages in the mapping.  The pages are placed at @pages.
 * find_get_pages() takes a reference against the returned pages.
 *
 * The search returns a group of mapping-contiguous pages with ascending
 * indexes.  There may be holes in the indices due to not-present pages.
 *
 * find_get_pages() returns the number of pages which were found.
 */
unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
			    unsigned int nr_pages, struct page **pages)
{
	unsigned int i;
	unsigned int ret;
	unsigned int nr_found;

	rcu_read_lock();
restart:
	nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree,
				(void ***)pages, start, nr_pages);
	ret = 0;
	for (i = 0; i < nr_found; i++) {
		struct page *page;
repeat:
		page = radix_tree_deref_slot((void **)pages[i]);
		if (unlikely(!page))
			continue;
		/*
		 * this can only trigger if nr_found == 1, making livelock
		 * a non issue.
		 */
		if (unlikely(page == RADIX_TREE_RETRY))
			goto restart;

		if (!page_cache_get_speculative(page))
			goto repeat;

		/* Has the page moved? */
		if (unlikely(page != *((void **)pages[i]))) {
			page_cache_release(page);
			goto repeat;
		}

		pages[ret] = page;
		ret++;
	}
	rcu_read_unlock();
	return ret;
}

/**
 * find_get_pages_contig - gang contiguous pagecache lookup
 * @mapping:	The address_space to search
 * @index:	The starting page index
 * @nr_pages:	The maximum number of pages
 * @pages:	Where the resulting pages are placed
 *
 * find_get_pages_contig() works exactly like find_get_pages(), except
 * that the returned number of pages are guaranteed to be contiguous.
 *
 * find_get_pages_contig() returns the number of pages which were found.
 */
unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
			       unsigned int nr_pages, struct page **pages)
{
	unsigned int i;
	unsigned int ret;
	unsigned int nr_found;

	rcu_read_lock();
restart:
	nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree,
				(void ***)pages, index, nr_pages);
	ret = 0;
	for (i = 0; i < nr_found; i++) {
		struct page *page;
repeat:
		page = radix_tree_deref_slot((void **)pages[i]);
		if (unlikely(!page))
			continue;
		/*
		 * this can only trigger if nr_found == 1, making livelock
		 * a non issue.
		 */
		if (unlikely(page == RADIX_TREE_RETRY))
			goto restart;

		if (page->mapping == NULL || page->index != index)
			break;

		if (!page_cache_get_speculative(page))
			goto repeat;

		/* Has the page moved? */
		if (unlikely(page != *((void **)pages[i]))) {
			page_cache_release(page);
			goto repeat;
		}

		pages[ret] = page;
		ret++;
		index++;
	}
	rcu_read_unlock();
	return ret;
}
EXPORT_SYMBOL(find_get_pages_contig);

/**
 * find_get_pages_tag - find and return pages that match @tag
 * @mapping:	the address_space to search
 * @index:	the starting page index
 * @tag:	the tag index
 * @nr_pages:	the maximum number of pages
 * @pages:	where the resulting pages are placed
 *
 * Like find_get_pages, except we only return pages which are tagged with
 * @tag.   We update @index to index the next page for the traversal.
 */
unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
			int tag, unsigned int nr_pages, struct page **pages)
{
	unsigned int i;
	unsigned int ret;
	unsigned int nr_found;

	rcu_read_lock();
restart:
	nr_found = radix_tree_gang_lookup_tag_slot(&mapping->page_tree,
				(void ***)pages, *index, nr_pages, tag);
	ret = 0;
	for (i = 0; i < nr_found; i++) {
		struct page *page;
repeat:
		page = radix_tree_deref_slot((void **)pages[i]);
		if (unlikely(!page))
			continue;
		/*
		 * this can only trigger if nr_found == 1, making livelock
		 * a non issue.
		 */
		if (unlikely(page == RADIX_TREE_RETRY))
			goto restart;

		if (!page_cache_get_speculative(page))
			goto repeat;

		/* Has the page moved? */
		if (unlikely(page != *((void **)pages[i]))) {
			page_cache_release(page);
			goto repeat;
		}

		pages[ret] = page;
		ret++;
	}
	rcu_read_unlock();

	if (ret)
		*index = pages[ret - 1]->index + 1;

	return ret;
}
EXPORT_SYMBOL(find_get_pages_tag);

/**
 * grab_cache_page_nowait - returns locked page at given index in given cache
 * @mapping: target address_space
 * @index: the page index
 *
 * Same as grab_cache_page(), but do not wait if the page is unavailable.
 * This is intended for speculative data generators, where the data can
 * be regenerated if the page couldn't be grabbed.  This routine should
 * be safe to call while holding the lock for another page.
 *
 * Clear __GFP_FS when allocating the page to avoid recursion into the fs
 * and deadlock against the caller's locked page.
 */
struct page *
grab_cache_page_nowait(struct address_space *mapping, pgoff_t index)
{
	struct page *page = find_get_page(mapping, index);

	if (page) {
		if (trylock_page(page))
			return page;
		page_cache_release(page);
		return NULL;
	}
	page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS);
	if (page && add_to_page_cache_lru(page, mapping, index, GFP_NOFS)) {
		page_cache_release(page);
		page = NULL;
	}
	return page;
}
EXPORT_SYMBOL(grab_cache_page_nowait);

/*
 * CD/DVDs are error prone. When a medium error occurs, the driver may fail
 * a _large_ part of the i/o request. Imagine the worst scenario:
 *
 *      ---R__________________________________________B__________
 *         ^ reading here                             ^ bad block(assume 4k)
 *
 * read(R) => miss => readahead(R...B) => media error => frustrating retries
 * => failing the whole request => read(R) => read(R+1) =>
 * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) =>
 * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) =>
 * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ......
 *