Merge tag 'folio-5.16' of git://git.infradead.org/users/willy/pagecache

Pull memory folios from Matthew Wilcox:
 "Add memory folios, a new type to represent either order-0 pages or the
  head page of a compound page. This should be enough infrastructure to
  support filesystems converting from pages to folios.

  The point of all this churn is to allow filesystems and the page cache
  to manage memory in larger chunks than PAGE_SIZE. The original plan
  was to use compound pages like THP does, but I ran into problems with
  some functions expecting only a head page while others expect the
  precise page containing a particular byte.

  The folio type allows a function to declare that it's expecting only a
  head page. Almost incidentally, this allows us to remove various calls
  to VM_BUG_ON(PageTail(page)) and compound_head().

  This converts just parts of the core MM and the page cache. For 5.17,
  we intend to convert various filesystems (XFS and AFS are ready; other
  filesystems may make it) and also convert more of the MM and page
  cache to folios. For 5.18, multi-page folios should be ready.

  The multi-page folios offer some improvement to some workloads. The
  80% win is real, but appears to be an artificial benchmark (postgres
  startup, which isn't a serious workload). Real workloads (eg building
  the kernel, running postgres in a steady state, etc) seem to benefit
  between 0-10%. I haven't heard of any performance losses as a result
  of this series. Nobody has done any serious performance tuning; I
  imagine that tweaking the readahead algorithm could provide some more
  interesting wins. There are also other places where we could choose to
  create large folios and currently do not, such as writes that are
  larger than PAGE_SIZE.

  I'd like to thank all my reviewers who've offered review/ack tags:
  Christoph Hellwig, David Howells, Jan Kara, Jeff Layton, Johannes
  Weiner, Kirill A. Shutemov, Michal Hocko, Mike Rapoport, Vlastimil
  Babka, William Kucharski, Yu Zhao and Zi Yan.

  I'd also like to thank those who gave feedback I incorporated but
  haven't offered up review tags for this part of the series: Nick
  Piggin, Mel Gorman, Ming Lei, Darrick Wong, Ted Ts'o, John Hubbard,
  Hugh Dickins, and probably a few others who I forget"

* tag 'folio-5.16' of git://git.infradead.org/users/willy/pagecache: (90 commits)
  mm/writeback: Add folio_write_one
  mm/filemap: Add FGP_STABLE
  mm/filemap: Add filemap_get_folio
  mm/filemap: Convert mapping_get_entry to return a folio
  mm/filemap: Add filemap_add_folio()
  mm/filemap: Add filemap_alloc_folio
  mm/page_alloc: Add folio allocation functions
  mm/lru: Add folio_add_lru()
  mm/lru: Convert __pagevec_lru_add_fn to take a folio
  mm: Add folio_evictable()
  mm/workingset: Convert workingset_refault() to take a folio
  mm/filemap: Add readahead_folio()
  mm/filemap: Add folio_mkwrite_check_truncate()
  mm/filemap: Add i_blocks_per_folio()
  mm/writeback: Add folio_redirty_for_writepage()
  mm/writeback: Add folio_account_redirty()
  mm/writeback: Add folio_clear_dirty_for_io()
  mm/writeback: Add folio_cancel_dirty()
  mm/writeback: Add folio_account_cleaned()
  mm/writeback: Add filemap_dirty_folio()
  ...

1 files changed, 67 insertions, 36 deletions

diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 355ea1ee32bd..e2ec68b0515c 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -6,27 +6,33 @@
 #include <linux/swap.h>
 
 /**
- * page_is_file_lru - should the page be on a file LRU or anon LRU?
- * @page: the page to test
- *
- * Returns 1 if @page is a regular filesystem backed page cache page or a lazily
- * freed anonymous page (e.g. via MADV_FREE).  Returns 0 if @page is a normal
- * anonymous page, a tmpfs page or otherwise ram or swap backed page.  Used by
- * functions that manipulate the LRU lists, to sort a page onto the right LRU
- * list.
+ * folio_is_file_lru - Should the folio be on a file LRU or anon LRU?
+ * @folio: The folio to test.
  *
  * We would like to get this info without a page flag, but the state
- * needs to survive until the page is last deleted from the LRU, which
+ * needs to survive until the folio is last deleted from the LRU, which
  * could be as far down as __page_cache_release.
+ *
+ * Return: An integer (not a boolean!) used to sort a folio onto the
+ * right LRU list and to account folios correctly.
+ * 1 if @folio is a regular filesystem backed page cache folio
+ * or a lazily freed anonymous folio (e.g. via MADV_FREE).
+ * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise
+ * ram or swap backed folio.
  */
+static inline int folio_is_file_lru(struct folio *folio)
+{
+	return !folio_test_swapbacked(folio);
+}
+
 static inline int page_is_file_lru(struct page *page)
 {
-	return !PageSwapBacked(page);
+	return folio_is_file_lru(page_folio(page));
 }
 
 static __always_inline void update_lru_size(struct lruvec *lruvec,
 				enum lru_list lru, enum zone_type zid,
-				int nr_pages)
+				long nr_pages)
 {
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 
@@ -39,69 +45,94 @@ static __always_inline void update_lru_size(struct lruvec *lruvec,
 }
 
 /**
- * __clear_page_lru_flags - clear page lru flags before releasing a page
- * @page: the page that was on lru and now has a zero reference
+ * __folio_clear_lru_flags - Clear page lru flags before releasing a page.
+ * @folio: The folio that was on lru and now has a zero reference.
  */
-static __always_inline void __clear_page_lru_flags(struct page *page)
+static __always_inline void __folio_clear_lru_flags(struct folio *folio)
 {
-	VM_BUG_ON_PAGE(!PageLRU(page), page);
+	VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio);
 
-	__ClearPageLRU(page);
+	__folio_clear_lru(folio);
 
 	/* this shouldn't happen, so leave the flags to bad_page() */
-	if (PageActive(page) && PageUnevictable(page))
+	if (folio_test_active(folio) && folio_test_unevictable(folio))
 		return;
 
-	__ClearPageActive(page);
-	__ClearPageUnevictable(page);
+	__folio_clear_active(folio);
+	__folio_clear_unevictable(folio);
+}
+
+static __always_inline void __clear_page_lru_flags(struct page *page)
+{
+	__folio_clear_lru_flags(page_folio(page));
 }
 
 /**
- * page_lru - which LRU list should a page be on?
- * @page: the page to test
+ * folio_lru_list - Which LRU list should a folio be on?
+ * @folio: The folio to test.
  *
- * Returns the LRU list a page should be on, as an index
+ * Return: The LRU list a folio should be on, as an index
  * into the array of LRU lists.
  */
-static __always_inline enum lru_list page_lru(struct page *page)
+static __always_inline enum lru_list folio_lru_list(struct folio *folio)
 {
 	enum lru_list lru;
 
-	VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page);
+	VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio);
 
-	if (PageUnevictable(page))
+	if (folio_test_unevictable(folio))
 		return LRU_UNEVICTABLE;
 
-	lru = page_is_file_lru(page) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON;
-	if (PageActive(page))
+	lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON;
+	if (folio_test_active(folio))
 		lru += LRU_ACTIVE;
 
 	return lru;
 }
 
+static __always_inline
+void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio)
+{
+	enum lru_list lru = folio_lru_list(folio);
+
+	update_lru_size(lruvec, lru, folio_zonenum(folio),
+			folio_nr_pages(folio));
+	list_add(&folio->lru, &lruvec->lists[lru]);
+}
+
 static __always_inline void add_page_to_lru_list(struct page *page,
 				struct lruvec *lruvec)
 {
-	enum lru_list lru = page_lru(page);
+	lruvec_add_folio(lruvec, page_folio(page));
+}
 
-	update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
-	list_add(&page->lru, &lruvec->lists[lru]);
+static __always_inline
+void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio)
+{
+	enum lru_list lru = folio_lru_list(folio);
+
+	update_lru_size(lruvec, lru, folio_zonenum(folio),
+			folio_nr_pages(folio));
+	list_add_tail(&folio->lru, &lruvec->lists[lru]);
 }
 
 static __always_inline void add_page_to_lru_list_tail(struct page *page,
 				struct lruvec *lruvec)
 {
-	enum lru_list lru = page_lru(page);
+	lruvec_add_folio_tail(lruvec, page_folio(page));
+}
 
-	update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
-	list_add_tail(&page->lru, &lruvec->lists[lru]);
+static __always_inline
+void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio)
+{
+	list_del(&folio->lru);
+	update_lru_size(lruvec, folio_lru_list(folio), folio_zonenum(folio),
+			-folio_nr_pages(folio));
 }
 
 static __always_inline void del_page_from_lru_list(struct page *page,
 				struct lruvec *lruvec)
 {
-	list_del(&page->lru);
-	update_lru_size(lruvec, page_lru(page), page_zonenum(page),
-			-thp_nr_pages(page));
+	lruvec_del_folio(lruvec, page_folio(page));
 }
 #endif