[PATCHv6,13/37] mm: make write_cache_pages() work on huge pages

Commit Message

Kirill A . Shutemov Jan. 26, 2017, 11:57 a.m. UTC

We writeback whole huge page a time. Let's adjust iteration this way.

Signed-off-by: Kirill A. Shutemov <[e-mail]>
---
 include/linux/mm.h      |  1 +
 include/linux/pagemap.h |  1 +
 mm/page-writeback.c     | 17 ++++++++++++-----
 3 files changed, 14 insertions(+), 5 deletions(-)

Comments

Matthew Wilcox Feb. 10, 2017, 5:46 p.m. UTC | #1

On Thu, Jan 26, 2017 at 02:57:55PM +0300, Kirill A. Shutemov wrote:
> We writeback whole huge page a time. Let's adjust iteration this way.
> 
> Signed-off-by: Kirill A. Shutemov <[e-mail]>

I think a lot of the complexity in this patch is from pagevec_lookup_tag
giving you subpages rather than head pages...

> @@ -2268,7 +2273,8 @@ int write_cache_pages(struct address_space *mapping,
>  					 * not be suitable for data integrity
>  					 * writeout).
>  					 */
> -					done_index = page->index + 1;
> +					done_index = compound_head(page)->index
> +						+ hpage_nr_pages(page);
>  					done = 1;
>  					break;
>  				}

you'd still need this line, but it'd only be:

					done_index = page->index +
						(1 << compound_order(page));

I think we want:

#define	nr_pages(page)	(1 << compound_order(page))

because we seem to be repeating that idiom quite a lot in these patches.

					done_index = page->index +
								nr_pages(page);

Still doesn't quite fit on one line, but it's closer, and it's the
ridiculous indentation in that function that's the real problem.

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index b84615b0f64c..9e87155af456 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1045,6 +1045,7 @@  extern pgoff_t __page_file_index(struct page *page);
  */
 static inline pgoff_t page_index(struct page *page)
 {
+	page = compound_head(page);
 	if (unlikely(PageSwapCache(page)))
 		return __page_file_index(page);
 	return page->index;
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 9a93b9c3d662..e3eb6dc03286 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -545,6 +545,7 @@  static inline int wait_on_page_locked_killable(struct page *page)
  */
 static inline void wait_on_page_writeback(struct page *page)
 {
+	page = compound_head(page);
 	if (PageWriteback(page))
 		wait_on_page_bit(page, PG_writeback);
 }
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 290e8b7d3181..47d5b12c460e 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2209,7 +2209,7 @@  int write_cache_pages(struct address_space *mapping,
 			 * mapping. However, page->index will not change
 			 * because we have a reference on the page.
 			 */
-			if (page->index > end) {
+			if (page_to_pgoff(page) > end) {
 				/*
 				 * can't be range_cyclic (1st pass) because
 				 * end == -1 in that case.
@@ -2218,7 +2218,12 @@  int write_cache_pages(struct address_space *mapping,
 				break;
 			}
 
-			done_index = page->index;
+			done_index = page_to_pgoff(page);
+			if (PageTransCompound(page)) {
+				index = round_up(index + 1, HPAGE_PMD_NR);
+				i += HPAGE_PMD_NR -
+					done_index % HPAGE_PMD_NR - 1;
+			}
 
 			lock_page(page);
 
@@ -2230,7 +2235,7 @@  int write_cache_pages(struct address_space *mapping,
 			 * even if there is now a new, dirty page at the same
 			 * pagecache address.
 			 */
-			if (unlikely(page->mapping != mapping)) {
+			if (unlikely(page_mapping(page) != mapping)) {
 continue_unlock:
 				unlock_page(page);
 				continue;
@@ -2268,7 +2273,8 @@  int write_cache_pages(struct address_space *mapping,
 					 * not be suitable for data integrity
 					 * writeout).
 					 */
-					done_index = page->index + 1;
+					done_index = compound_head(page)->index
+						+ hpage_nr_pages(page);
 					done = 1;
 					break;
 				}
@@ -2280,7 +2286,8 @@  int write_cache_pages(struct address_space *mapping,
 			 * keep going until we have written all the pages
 			 * we tagged for writeback prior to entering this loop.
 			 */
-			if (--wbc->nr_to_write <= 0 &&
+			wbc->nr_to_write -= hpage_nr_pages(page);
+			if (wbc->nr_to_write <= 0 &&
 			    wbc->sync_mode == WB_SYNC_NONE) {
 				done = 1;
 				break;