page-writeback.c

最新最稳定的Linux内存管理模块源代码

	done_index = index;
	while (!done && (index <= end)) {
		int i;

		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
			      PAGECACHE_TAG_DIRTY,
			      min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
		if (nr_pages == 0)
			break;

		for (i = 0; i < nr_pages; i++) {
			struct page *page = pvec.pages[i];

			/*
			 * At this point, the page may be truncated or
			 * invalidated (changing page->mapping to NULL), or
			 * even swizzled back from swapper_space to tmpfs file
			 * mapping. However, page->index will not change
			 * because we have a reference on the page.
			 */
			if (page->index > end) {
				/*
				 * can't be range_cyclic (1st pass) because
				 * end == -1 in that case.
				 */
				done = 1;
				break;
			}

			done_index = page->index + 1;

			lock_page(page);

			/*
			 * Page truncated or invalidated. We can freely skip it
			 * then, even for data integrity operations: the page
			 * has disappeared concurrently, so there could be no
			 * real expectation of this data interity operation
			 * even if there is now a new, dirty page at the same
			 * pagecache address.
			 */
			if (unlikely(page->mapping != mapping)) {
continue_unlock:
				unlock_page(page);
				continue;
			}

			if (!PageDirty(page)) {
				/* someone wrote it for us */
				goto continue_unlock;
			}

			if (PageWriteback(page)) {
				if (wbc->sync_mode != WB_SYNC_NONE)
					wait_on_page_writeback(page);
				else
					goto continue_unlock;
			}

			BUG_ON(PageWriteback(page));
			if (!clear_page_dirty_for_io(page))
				goto continue_unlock;

			ret = (*writepage)(page, wbc, data);
			if (unlikely(ret)) {
				if (ret == AOP_WRITEPAGE_ACTIVATE) {
					unlock_page(page);
					ret = 0;
				} else {
					/*
					 * done_index is set past this page,
					 * so media errors will not choke
					 * background writeout for the entire
					 * file. This has consequences for
					 * range_cyclic semantics (ie. it may
					 * not be suitable for data integrity
					 * writeout).
					 */
					done = 1;
					break;
				}
 			}

			if (nr_to_write > 0) {
				nr_to_write--;
				if (nr_to_write == 0 &&
				    wbc->sync_mode == WB_SYNC_NONE) {
					/*
					 * We stop writing back only if we are
					 * not doing integrity sync. In case of
					 * integrity sync we have to keep going
					 * because someone may be concurrently
					 * dirtying pages, and we might have
					 * synced a lot of newly appeared dirty
					 * pages, but have not synced all of the
					 * old dirty pages.
					 */
					done = 1;
					break;
				}
			}

			if (wbc->nonblocking && bdi_write_congested(bdi)) {
				wbc->encountered_congestion = 1;
				done = 1;
				break;
			}
		}
		pagevec_release(&pvec);
		cond_resched();
	}
	if (!cycled && !done) {
		/*
		 * range_cyclic:
		 * We hit the last page and there is more work to be done: wrap
		 * back to the start of the file
		 */
		cycled = 1;
		index = 0;
		end = writeback_index - 1;
		goto retry;
	}
	if (!wbc->no_nrwrite_index_update) {
		if (wbc->range_cyclic || (range_whole && nr_to_write > 0))
			mapping->writeback_index = done_index;
		wbc->nr_to_write = nr_to_write;
	}

	return ret;
}
EXPORT_SYMBOL(write_cache_pages);

/*
 * Function used by generic_writepages to call the real writepage
 * function and set the mapping flags on error
 */
static int __writepage(struct page *page, struct writeback_control *wbc,
		       void *data)
{
	struct address_space *mapping = data;
	int ret = mapping->a_ops->writepage(page, wbc);
	mapping_set_error(mapping, ret);
	return ret;
}

/**
 * generic_writepages - walk the list of dirty pages of the given address space and writepage() all of them.
 * @mapping: address space structure to write
 * @wbc: subtract the number of written pages from *@wbc->nr_to_write
 *
 * This is a library function, which implements the writepages()
 * address_space_operation.
 */
int generic_writepages(struct address_space *mapping,
		       struct writeback_control *wbc)
{
	/* deal with chardevs and other special file */
	if (!mapping->a_ops->writepage)
		return 0;

	return write_cache_pages(mapping, wbc, __writepage, mapping);
}

EXPORT_SYMBOL(generic_writepages);

int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
	int ret;

	if (wbc->nr_to_write <= 0)
		return 0;
	wbc->for_writepages = 1;
	if (mapping->a_ops->writepages)
		ret = mapping->a_ops->writepages(mapping, wbc);
	else
		ret = generic_writepages(mapping, wbc);
	wbc->for_writepages = 0;
	return ret;
}

/**
 * write_one_page - write out a single page and optionally wait on I/O
 * @page: the page to write
 * @wait: if true, wait on writeout
 *
 * The page must be locked by the caller and will be unlocked upon return.
 *
 * write_one_page() returns a negative error code if I/O failed.
 */
int write_one_page(struct page *page, int wait)
{
	struct address_space *mapping = page->mapping;
	int ret = 0;
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_ALL,
		.nr_to_write = 1,
	};

	BUG_ON(!PageLocked(page));

	if (wait)
		wait_on_page_writeback(page);

	if (clear_page_dirty_for_io(page)) {
		page_cache_get(page);
		ret = mapping->a_ops->writepage(page, &wbc);
		if (ret == 0 && wait) {
			wait_on_page_writeback(page);
			if (PageError(page))
				ret = -EIO;
		}
		page_cache_release(page);
	} else {
		unlock_page(page);
	}
	return ret;
}
EXPORT_SYMBOL(write_one_page);

/*
 * For address_spaces which do not use buffers nor write back.
 */
int __set_page_dirty_no_writeback(struct page *page)
{
	if (!PageDirty(page))
		SetPageDirty(page);
	return 0;
}

/*
 * For address_spaces which do not use buffers.  Just tag the page as dirty in
 * its radix tree.
 *
 * This is also used when a single buffer is being dirtied: we want to set the
 * page dirty in that case, but not all the buffers.  This is a "bottom-up"
 * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
 *
 * Most callers have locked the page, which pins the address_space in memory.
 * But zap_pte_range() does not lock the page, however in that case the
 * mapping is pinned by the vma's ->vm_file reference.
 *
 * We take care to handle the case where the page was truncated from the
 * mapping by re-checking page_mapping() inside tree_lock.
 */
int __set_page_dirty_nobuffers(struct page *page)
{
	if (!TestSetPageDirty(page)) {
		struct address_space *mapping = page_mapping(page);
		struct address_space *mapping2;

		if (!mapping)
			return 1;

		spin_lock_irq(&mapping->tree_lock);
		mapping2 = page_mapping(page);
		if (mapping2) { /* Race with truncate? */
			BUG_ON(mapping2 != mapping);
			WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
			if (mapping_cap_account_dirty(mapping)) {
				__inc_zone_page_state(page, NR_FILE_DIRTY);
				__inc_bdi_stat(mapping->backing_dev_info,
						BDI_RECLAIMABLE);
				task_dirty_inc(current);
				task_io_account_write(PAGE_CACHE_SIZE);
			}
			radix_tree_tag_set(&mapping->page_tree,
				page_index(page), PAGECACHE_TAG_DIRTY);
		}
		spin_unlock_irq(&mapping->tree_lock);
		if (mapping->host) {
			/* !PageAnon && !swapper_space */
			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
		}
		return 1;
	}
	return 0;
}
EXPORT_SYMBOL(__set_page_dirty_nobuffers);

/*
 * When a writepage implementation decides that it doesn't want to write this
 * page for some reason, it should redirty the locked page via
 * redirty_page_for_writepage() and it should then unlock the page and return 0
 */
int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
{
	wbc->pages_skipped++;
	return __set_page_dirty_nobuffers(page);
}
EXPORT_SYMBOL(redirty_page_for_writepage);

/*
 * If the mapping doesn't provide a set_page_dirty a_op, then
 * just fall through and assume that it wants buffer_heads.
 */
int set_page_dirty(struct page *page)
{
	struct address_space *mapping = page_mapping(page);

	if (likely(mapping)) {
		int (*spd)(struct page *) = mapping->a_ops->set_page_dirty;
#ifdef CONFIG_BLOCK
		if (!spd)
			spd = __set_page_dirty_buffers;
#endif
		return (*spd)(page);
	}
	if (!PageDirty(page)) {
		if (!TestSetPageDirty(page))
			return 1;
	}
	return 0;
}
EXPORT_SYMBOL(set_page_dirty);

/*
 * set_page_dirty() is racy if the caller has no reference against
 * page->mapping->host, and if the page is unlocked.  This is because another
 * CPU could truncate the page off the mapping and then free the mapping.
 *
 * Usually, the page _is_ locked, or the caller is a user-space process which
 * holds a reference on the inode by having an open file.
 *
 * In other cases, the page should be locked before running set_page_dirty().
 */
int set_page_dirty_lock(struct page *page)
{
	int ret;

	lock_page_nosync(page);
	ret = set_page_dirty(page);
	unlock_page(page);
	return ret;
}
EXPORT_SYMBOL(set_page_dirty_lock);

/*
 * Clear a page's dirty flag, while caring for dirty memory accounting.
 * Returns true if the page was previously dirty.
 *
 * This is for preparing to put the page under writeout.  We leave the page
 * tagged as dirty in the radix tree so that a concurrent write-for-sync
 * can discover it via a PAGECACHE_TAG_DIRTY walk.  The ->writepage
 * implementation will run either set_page_writeback() or set_page_dirty(),
 * at which stage we bring the page's dirty flag and radix-tree dirty tag
 * back into sync.
 *
 * This incoherency between the page's dirty flag and radix-tree tag is
 * unfortunate, but it only exists while the page is locked.
 */
int clear_page_dirty_for_io(struct page *page)
{
	struct address_space *mapping = page_mapping(page);

	BUG_ON(!PageLocked(page));

	ClearPageReclaim(page);
	if (mapping && mapping_cap_account_dirty(mapping)) {
		/*
		 * Yes, Virginia, this is indeed insane.
		 *
		 * We use this sequence to make sure that
		 *  (a) we account for dirty stats properly
		 *  (b) we tell the low-level filesystem to
		 *      mark the whole page dirty if it was
		 *      dirty in a pagetable. Only to then
		 *  (c) clean the page again and return 1 to
		 *      cause the writeback.
		 *
		 * This way we avoid all nasty races with the
		 * dirty bit in multiple places and clearing
		 * them concurrently from different threads.
		 *
		 * Note! Normally the "set_page_dirty(page)"
		 * has no effect on the actual dirty bit - since
		 * that will already usually be set. But we
		 * need the side effects, and it can help us
		 * avoid races.
		 *
		 * We basically use the page "master dirty bit"
		 * as a serialization point for all the different
		 * threads doing their things.
		 */
		if (page_mkclean(page))
			set_page_dirty(page);
		/*
		 * We carefully synchronise fault handlers against
		 * installing a dirty pte and marking the page dirty
		 * at this point. We do this by having them hold the
		 * page lock at some point after installing their
		 * pte, but before marking the page dirty.
		 * Pages are always locked coming in here, so we get
		 * the desired exclusion. See mm/memory.c:do_wp_page()
		 * for more comments.
		 */
		if (TestClearPageDirty(page)) {
			dec_zone_page_state(page, NR_FILE_DIRTY);
			dec_bdi_stat(mapping->backing_dev_info,
					BDI_RECLAIMABLE);
			return 1;
		}
		return 0;
	}
	return TestClearPageDirty(page);
}
EXPORT_SYMBOL(clear_page_dirty_for_io);

int test_clear_page_writeback(struct page *page)
{
	struct address_space *mapping = page_mapping(page);
	int ret;

	if (mapping) {
		struct backing_dev_info *bdi = mapping->backing_dev_info;
		unsigned long flags;

		spin_lock_irqsave(&mapping->tree_lock, flags);
		ret = TestClearPageWriteback(page);
		if (ret) {
			radix_tree_tag_clear(&mapping->page_tree,
						page_index(page),
						PAGECACHE_TAG_WRITEBACK);
			if (bdi_cap_account_writeback(bdi)) {
				__dec_bdi_stat(bdi, BDI_WRITEBACK);
				__bdi_writeout_inc(bdi);
			}
		}
		spin_unlock_irqrestore(&mapping->tree_lock, flags);
	} else {
		ret = TestClearPageWriteback(page);
	}
	if (ret)
		dec_zone_page_state(page, NR_WRITEBACK);
	return ret;
}

int test_set_page_writeback(struct page *page)
{
	struct address_space *mapping = page_mapping(page);
	int ret;

	if (mapping) {
		struct backing_dev_info *bdi = mapping->backing_dev_info;
		unsigned long flags;

		spin_lock_irqsave(&mapping->tree_lock, flags);
		ret = TestSetPageWriteback(page);
		if (!ret) {
			radix_tree_tag_set(&mapping->page_tree,
						page_index(page),
						PAGECACHE_TAG_WRITEBACK);
			if (bdi_cap_account_writeback(bdi))
				__inc_bdi_stat(bdi, BDI_WRITEBACK);
		}
		if (!PageDirty(page))
			radix_tree_tag_clear(&mapping->page_tree,
						page_index(page),
						PAGECACHE_TAG_DIRTY);
		spin_unlock_irqrestore(&mapping->tree_lock, flags);
	} else {
		ret = TestSetPageWriteback(page);
	}
	if (!ret)
		inc_zone_page_state(page, NR_WRITEBACK);
	return ret;

}
EXPORT_SYMBOL(test_set_page_writeback);

/*
 * Return true if any of the pages in the mapping are marked with the
 * passed tag.
 */
int mapping_tagged(struct address_space *mapping, int tag)
{
	int ret;
	rcu_read_lock();
	ret = radix_tree_tagged(&mapping->page_tree, tag);
	rcu_read_unlock();
	return ret;
}
EXPORT_SYMBOL(mapping_tagged);