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, 66 insertions, 45 deletions

diff --git a/mm/util.c b/mm/util.c
index bacabe446906..e58151a61255 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -654,81 +654,78 @@ void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
 }
 EXPORT_SYMBOL(kvrealloc);
 
-static inline void *__page_rmapping(struct page *page)
-{
-	unsigned long mapping;
-
-	mapping = (unsigned long)page->mapping;
-	mapping &= ~PAGE_MAPPING_FLAGS;
-
-	return (void *)mapping;
-}
-
 /* Neutral page->mapping pointer to address_space or anon_vma or other */
 void *page_rmapping(struct page *page)
 {
-	page = compound_head(page);
-	return __page_rmapping(page);
+	return folio_raw_mapping(page_folio(page));
 }
 
-/*
- * Return true if this page is mapped into pagetables.
- * For compound page it returns true if any subpage of compound page is mapped.
+/**
+ * folio_mapped - Is this folio mapped into userspace?
+ * @folio: The folio.
+ *
+ * Return: True if any page in this folio is referenced by user page tables.
  */
-bool page_mapped(struct page *page)
+bool folio_mapped(struct folio *folio)
 {
-	int i;
+	long i, nr;
 
-	if (likely(!PageCompound(page)))
-		return atomic_read(&page->_mapcount) >= 0;
-	page = compound_head(page);
-	if (atomic_read(compound_mapcount_ptr(page)) >= 0)
+	if (folio_test_single(folio))
+		return atomic_read(&folio->_mapcount) >= 0;
+	if (atomic_read(folio_mapcount_ptr(folio)) >= 0)
 		return true;
-	if (PageHuge(page))
+	if (folio_test_hugetlb(folio))
 		return false;
-	for (i = 0; i < compound_nr(page); i++) {
-		if (atomic_read(&page[i]._mapcount) >= 0)
+
+	nr = folio_nr_pages(folio);
+	for (i = 0; i < nr; i++) {
+		if (atomic_read(&folio_page(folio, i)->_mapcount) >= 0)
 			return true;
 	}
 	return false;
 }
-EXPORT_SYMBOL(page_mapped);
+EXPORT_SYMBOL(folio_mapped);
 
 struct anon_vma *page_anon_vma(struct page *page)
 {
-	unsigned long mapping;
+	struct folio *folio = page_folio(page);
+	unsigned long mapping = (unsigned long)folio->mapping;
 
-	page = compound_head(page);
-	mapping = (unsigned long)page->mapping;
 	if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
 		return NULL;
-	return __page_rmapping(page);
+	return (void *)(mapping - PAGE_MAPPING_ANON);
 }
 
-struct address_space *page_mapping(struct page *page)
+/**
+ * folio_mapping - Find the mapping where this folio is stored.
+ * @folio: The folio.
+ *
+ * For folios which are in the page cache, return the mapping that this
+ * page belongs to.  Folios in the swap cache return the swap mapping
+ * this page is stored in (which is different from the mapping for the
+ * swap file or swap device where the data is stored).
+ *
+ * You can call this for folios which aren't in the swap cache or page
+ * cache and it will return NULL.
+ */
+struct address_space *folio_mapping(struct folio *folio)
 {
 	struct address_space *mapping;
 
-	page = compound_head(page);
-
 	/* This happens if someone calls flush_dcache_page on slab page */
-	if (unlikely(PageSlab(page)))
+	if (unlikely(folio_test_slab(folio)))
 		return NULL;
 
-	if (unlikely(PageSwapCache(page))) {
-		swp_entry_t entry;
+	if (unlikely(folio_test_swapcache(folio)))
+		return swap_address_space(folio_swap_entry(folio));
 
-		entry.val = page_private(page);
-		return swap_address_space(entry);
-	}
-
-	mapping = page->mapping;
+	mapping = folio->mapping;
 	if ((unsigned long)mapping & PAGE_MAPPING_ANON)
 		return NULL;
 
 	return (void *)((unsigned long)mapping & ~PAGE_MAPPING_FLAGS);
 }
-EXPORT_SYMBOL(page_mapping);
+EXPORT_SYMBOL(folio_mapping);
 
 /* Slow path of page_mapcount() for compound pages */
 int __page_mapcount(struct page *page)
@@ -750,13 +747,26 @@ int __page_mapcount(struct page *page)
 }
 EXPORT_SYMBOL_GPL(__page_mapcount);
 
-void copy_huge_page(struct page *dst, struct page *src)
+/**
+ * folio_copy - Copy the contents of one folio to another.
+ * @dst: Folio to copy to.
+ * @src: Folio to copy from.
+ *
+ * The bytes in the folio represented by @src are copied to @dst.
+ * Assumes the caller has validated that @dst is at least as large as @src.
+ * Can be called in atomic context for order-0 folios, but if the folio is
+ * larger, it may sleep.
+ */
+void folio_copy(struct folio *dst, struct folio *src)
 {
-	unsigned i, nr = compound_nr(src);
+	long i = 0;
+	long nr = folio_nr_pages(src);
 
-	for (i = 0; i < nr; i++) {
+	for (;;) {
+		copy_highpage(folio_page(dst, i), folio_page(src, i));
+		if (++i == nr)
+			break;
 		cond_resched();
-		copy_highpage(nth_page(dst, i), nth_page(src, i));
 	}
 }
 
@@ -1079,3 +1089,14 @@ void page_offline_end(void)
 	up_write(&page_offline_rwsem);
 }
 EXPORT_SYMBOL(page_offline_end);
+
+#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
+void flush_dcache_folio(struct folio *folio)
+{
+	long i, nr = folio_nr_pages(folio);
+
+	for (i = 0; i < nr; i++)
+		flush_dcache_page(folio_page(folio, i));
+}
+EXPORT_SYMBOL(flush_dcache_folio);
+#endif