Merge tag 'folio-5.17' of git://git.infradead.org/users/willy/pagecache

Pull folio conversion updates from Matthew Wilcox:
 "Convert much of the page cache to use folios

  This stops just short of actually enabling large folios. It converts
  everything that I noticed needs to be converted, but there may still
  be places I've overlooked which still have page size assumptions.

  The big change here is using large entries in the page cache XArray
  instead of many small entries. That only affects shmem for now, but
  it's a pretty big change for shmem since it changes where memory needs
  to be allocated (at split time instead of insertion)"

* tag 'folio-5.17' of git://git.infradead.org/users/willy/pagecache: (49 commits)
  mm: Use multi-index entries in the page cache
  XArray: Add xas_advance()
  truncate,shmem: Handle truncates that split large folios
  truncate: Convert invalidate_inode_pages2_range to folios
  fs: Convert vfs_dedupe_file_range_compare to folios
  mm: Remove pagevec_remove_exceptionals()
  mm: Convert find_lock_entries() to use a folio_batch
  filemap: Return only folios from find_get_entries()
  filemap: Convert filemap_get_read_batch() to use a folio_batch
  filemap: Convert filemap_read() to use a folio
  truncate: Add invalidate_complete_folio2()
  truncate: Convert invalidate_inode_pages2_range() to use a folio
  truncate: Skip known-truncated indices
  truncate,shmem: Add truncate_inode_folio()
  shmem: Convert part of shmem_undo_range() to use a folio
  mm: Add unmap_mapping_folio()
  truncate: Add truncate_cleanup_folio()
  filemap: Add filemap_release_folio()
  filemap: Use a folio in filemap_page_mkwrite
  filemap: Use a folio in filemap_map_pages
  ...

8 files changed, 177 insertions, 101 deletions

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index f280f33ff223..e4c18ba8d3bf 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -274,6 +274,15 @@ static inline int thp_nr_pages(struct page *page)
 	return 1;
 }
 
+/**
+ * folio_test_pmd_mappable - Can we map this folio with a PMD?
+ * @folio: The folio to test
+ */
+static inline bool folio_test_pmd_mappable(struct folio *folio)
+{
+	return folio_order(folio) >= HPAGE_PMD_ORDER;
+}
+
 struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
 		pmd_t *pmd, int flags, struct dev_pagemap **pgmap);
 struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
@@ -339,6 +348,11 @@ static inline int thp_nr_pages(struct page *page)
 	return 1;
 }
 
+static inline bool folio_test_pmd_mappable(struct folio *folio)
+{
+	return false;
+}
+
 static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma)
 {
 	return false;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index de103949860f..c768a7c81b0b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -714,6 +714,27 @@ int vma_is_stack_for_current(struct vm_area_struct *vma);
 struct mmu_gather;
 struct inode;
 
+static inline unsigned int compound_order(struct page *page)
+{
+	if (!PageHead(page))
+		return 0;
+	return page[1].compound_order;
+}
+
+/**
+ * folio_order - The allocation order of a folio.
+ * @folio: The folio.
+ *
+ * A folio is composed of 2^order pages.  See get_order() for the definition
+ * of order.
+ *
+ * Return: The order of the folio.
+ */
+static inline unsigned int folio_order(struct folio *folio)
+{
+	return compound_order(&folio->page);
+}
+
 #include <linux/huge_mm.h>
 
 /*
@@ -913,27 +934,6 @@ static inline void destroy_compound_page(struct page *page)
 	compound_page_dtors[page[1].compound_dtor](page);
 }
 
-static inline unsigned int compound_order(struct page *page)
-{
-	if (!PageHead(page))
-		return 0;
-	return page[1].compound_order;
-}
-
-/**
- * folio_order - The allocation order of a folio.
- * @folio: The folio.
- *
- * A folio is composed of 2^order pages.  See get_order() for the definition
- * of order.
- *
- * Return: The order of the folio.
- */
-static inline unsigned int folio_order(struct folio *folio)
-{
-	return compound_order(&folio->page);
-}
-
 static inline bool hpage_pincount_available(struct page *page)
 {
 	/*
@@ -1837,28 +1837,6 @@ static inline bool can_do_mlock(void) { return false; }
 extern int user_shm_lock(size_t, struct ucounts *);
 extern void user_shm_unlock(size_t, struct ucounts *);
 
-/*
- * Parameter block passed down to zap_pte_range in exceptional cases.
- */
-struct zap_details {
-	struct address_space *zap_mapping;	/* Check page->mapping if set */
-	struct page *single_page;		/* Locked page to be unmapped */
-};
-
-/*
- * We set details->zap_mappings when we want to unmap shared but keep private
- * pages. Return true if skip zapping this page, false otherwise.
- */
-static inline bool
-zap_skip_check_mapping(struct zap_details *details, struct page *page)
-{
-	if (!details || !page)
-		return false;
-
-	return details->zap_mapping &&
-	    (details->zap_mapping != page_rmapping(page));
-}
-
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 			     pte_t pte);
 struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
@@ -1893,7 +1871,6 @@ extern void truncate_pagecache(struct inode *inode, loff_t new);
 extern void truncate_setsize(struct inode *inode, loff_t newsize);
 void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to);
 void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
-int truncate_inode_page(struct address_space *mapping, struct page *page);
 int generic_error_remove_page(struct address_space *mapping, struct page *page);
 int invalidate_inode_page(struct page *page);
 
@@ -1904,7 +1881,6 @@ extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
 extern int fixup_user_fault(struct mm_struct *mm,
 			    unsigned long address, unsigned int fault_flags,
 			    bool *unlocked);
-void unmap_mapping_page(struct page *page);
 void unmap_mapping_pages(struct address_space *mapping,
 		pgoff_t start, pgoff_t nr, bool even_cows);
 void unmap_mapping_range(struct address_space *mapping,
@@ -1925,7 +1901,6 @@ static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address,
 	BUG();
 	return -EFAULT;
 }
-static inline void unmap_mapping_page(struct page *page) { }
 static inline void unmap_mapping_pages(struct address_space *mapping,
 		pgoff_t start, pgoff_t nr, bool even_cows) { }
 static inline void unmap_mapping_range(struct address_space *mapping,
@@ -1982,7 +1957,6 @@ int get_kernel_pages(const struct kvec *iov, int nr_pages, int write,
 			struct page **pages);
 struct page *get_dump_page(unsigned long addr);
 
-extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
 extern void do_invalidatepage(struct page *page, unsigned int offset,
 			      unsigned int length);
 
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index b5f14d581113..b3d353d537e2 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -68,9 +68,6 @@
  * might lose their PG_swapbacked flag when they simply can be dropped (e.g. as
  * a result of MADV_FREE).
  *
- * PG_uptodate tells whether the page's contents is valid.  When a read
- * completes, the page becomes uptodate, unless a disk I/O error happened.
- *
  * PG_referenced, PG_reclaim are used for page reclaim for anonymous and
  * file-backed pagecache (see mm/vmscan.c).
  *
@@ -615,6 +612,16 @@ TESTPAGEFLAG_FALSE(Ksm, ksm)
 
 u64 stable_page_flags(struct page *page);
 
+/**
+ * folio_test_uptodate - Is this folio up to date?
+ * @folio: The folio.
+ *
+ * The uptodate flag is set on a folio when every byte in the folio is
+ * at least as new as the corresponding bytes on storage.  Anonymous
+ * and CoW folios are always uptodate.  If the folio is not uptodate,
+ * some of the bytes in it may be; see the is_partially_uptodate()
+ * address_space operation.
+ */
 static inline bool folio_test_uptodate(struct folio *folio)
 {
 	bool ret = test_bit(PG_uptodate, folio_flags(folio, 0));
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 422bdf9f4e76..270bf5136c34 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -16,7 +16,7 @@
 #include <linux/hardirq.h> /* for in_interrupt() */
 #include <linux/hugetlb_inline.h>
 
-struct pagevec;
+struct folio_batch;
 
 static inline bool mapping_empty(struct address_space *mapping)
 {
@@ -511,15 +511,6 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping,
 			mapping_gfp_mask(mapping));
 }
 
-/* Does this page contain this index? */
-static inline bool thp_contains(struct page *head, pgoff_t index)
-{
-	/* HugeTLBfs indexes the page cache in units of hpage_size */
-	if (PageHuge(head))
-		return head->index == index;
-	return page_index(head) == (index & ~(thp_nr_pages(head) - 1UL));
-}
-
 #define swapcache_index(folio)	__page_file_index(&(folio)->page)
 
 /**
@@ -600,8 +591,6 @@ static inline struct page *find_subpage(struct page *head, pgoff_t index)
 	return head + (index & (thp_nr_pages(head) - 1));
 }
 
-unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
-		pgoff_t end, struct pagevec *pvec, pgoff_t *indices);
 unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
 			pgoff_t end, unsigned int nr_pages,
 			struct page **pages);
@@ -637,8 +626,10 @@ static inline struct page *grab_cache_page(struct address_space *mapping,
 	return find_or_create_page(mapping, index, mapping_gfp_mask(mapping));
 }
 
-extern struct page * read_cache_page(struct address_space *mapping,
-				pgoff_t index, filler_t *filler, void *data);
+struct folio *read_cache_folio(struct address_space *, pgoff_t index,
+		filler_t *filler, void *data);
+struct page *read_cache_page(struct address_space *, pgoff_t index,
+		filler_t *filler, void *data);
 extern struct page * read_cache_page_gfp(struct address_space *mapping,
 				pgoff_t index, gfp_t gfp_mask);
 extern int read_cache_pages(struct address_space *mapping,
@@ -650,6 +641,12 @@ static inline struct page *read_mapping_page(struct address_space *mapping,
 	return read_cache_page(mapping, index, NULL, data);
 }
 
+static inline struct folio *read_mapping_folio(struct address_space *mapping,
+				pgoff_t index, void *data)
+{
+	return read_cache_folio(mapping, index, NULL, data);
+}
+
 /*
  * Get index of the page within radix-tree (but not for hugetlb pages).
  * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE)
@@ -867,7 +864,7 @@ static inline int wait_on_page_locked_killable(struct page *page)
 	return folio_wait_locked_killable(page_folio(page));
 }
 
-int put_and_wait_on_page_locked(struct page *page, int state);
+int folio_put_wait_locked(struct folio *folio, int state);
 void wait_on_page_writeback(struct page *page);
 void folio_wait_writeback(struct folio *folio);
 int folio_wait_writeback_killable(struct folio *folio);
@@ -883,11 +880,6 @@ static inline void __set_page_dirty(struct page *page,
 }
 void folio_account_cleaned(struct folio *folio, struct address_space *mapping,
 			  struct bdi_writeback *wb);
-static inline void account_page_cleaned(struct page *page,
-		struct address_space *mapping, struct bdi_writeback *wb)
-{
-	return folio_account_cleaned(page_folio(page), mapping, wb);
-}
 void __folio_cancel_dirty(struct folio *folio);
 static inline void folio_cancel_dirty(struct folio *folio)
 {
@@ -934,11 +926,18 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 		pgoff_t index, gfp_t gfp);
 int filemap_add_folio(struct address_space *mapping, struct folio *folio,
 		pgoff_t index, gfp_t gfp);
-extern void delete_from_page_cache(struct page *page);
-extern void __delete_from_page_cache(struct page *page, void *shadow);
+void filemap_remove_folio(struct folio *folio);
+void delete_from_page_cache(struct page *page);
+void __filemap_remove_folio(struct folio *folio, void *shadow);
+static inline void __delete_from_page_cache(struct page *page, void *shadow)
+{
+	__filemap_remove_folio(page_folio(page), shadow);
+}
 void replace_page_cache_page(struct page *old, struct page *new);
 void delete_from_page_cache_batch(struct address_space *mapping,
-				  struct pagevec *pvec);
+				  struct folio_batch *fbatch);
+int try_to_release_page(struct page *page, gfp_t gfp);
+bool filemap_release_folio(struct folio *folio, gfp_t gfp);
 loff_t mapping_seek_hole_data(struct address_space *, loff_t start, loff_t end,
 		int whence);
 
@@ -1030,7 +1029,7 @@ struct readahead_control {
 void page_cache_ra_unbounded(struct readahead_control *,
 		unsigned long nr_to_read, unsigned long lookahead_count);
 void page_cache_sync_ra(struct readahead_control *, unsigned long req_count);
-void page_cache_async_ra(struct readahead_control *, struct page *,
+void page_cache_async_ra(struct readahead_control *, struct folio *,
 		unsigned long req_count);
 void readahead_expand(struct readahead_control *ractl,
 		      loff_t new_start, size_t new_len);
@@ -1077,7 +1076,7 @@ void page_cache_async_readahead(struct address_space *mapping,
 		struct page *page, pgoff_t index, unsigned long req_count)
 {
 	DEFINE_READAHEAD(ractl, file, ra, mapping, index);
-	page_cache_async_ra(&ractl, page, req_count);
+	page_cache_async_ra(&ractl, page_folio(page), req_count);
 }
 
 static inline struct folio *__readahead_folio(struct readahead_control *ractl)
@@ -1154,16 +1153,6 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac,
 		VM_BUG_ON_PAGE(PageTail(page), page);
 		array[i++] = page;
 		rac->_batch_count += thp_nr_pages(page);
-
-		/*
-		 * The page cache isn't using multi-index entries yet,
-		 * so the xas cursor needs to be manually moved to the
-		 * next index.  This can be removed once the page cache
-		 * is converted.
-		 */
-		if (PageHead(page))
-			xas_set(&xas, rac->_index + rac->_batch_count);
-
 		if (i == array_sz)
 			break;
 	}
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index 7f3f19065a9f..dda8d5868c81 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -15,8 +15,10 @@
 #define PAGEVEC_SIZE	15
 
 struct page;
+struct folio;
 struct address_space;
 
+/* Layout must match folio_batch */
 struct pagevec {
 	unsigned char nr;
 	bool percpu_pvec_drained;
@@ -25,7 +27,6 @@ struct pagevec {
 
 void __pagevec_release(struct pagevec *pvec);
 void __pagevec_lru_add(struct pagevec *pvec);
-void pagevec_remove_exceptionals(struct pagevec *pvec);
 unsigned pagevec_lookup_range(struct pagevec *pvec,
 			      struct address_space *mapping,
 			      pgoff_t *start, pgoff_t end);
@@ -81,4 +82,68 @@ static inline void pagevec_release(struct pagevec *pvec)
 		__pagevec_release(pvec);
 }
 
+/**
+ * struct folio_batch - A collection of folios.
+ *
+ * The folio_batch is used to amortise the cost of retrieving and
+ * operating on a set of folios.  The order of folios in the batch may be
+ * significant (eg delete_from_page_cache_batch()).  Some users of the
+ * folio_batch store "exceptional" entries in it which can be removed
+ * by calling folio_batch_remove_exceptionals().
+ */
+struct folio_batch {
+	unsigned char nr;
+	bool percpu_pvec_drained;
+	struct folio *folios[PAGEVEC_SIZE];
+};
+
+/* Layout must match pagevec */
+static_assert(sizeof(struct pagevec) == sizeof(struct folio_batch));
+static_assert(offsetof(struct pagevec, pages) ==
+		offsetof(struct folio_batch, folios));
+
+/**
+ * folio_batch_init() - Initialise a batch of folios
+ * @fbatch: The folio batch.
+ *
+ * A freshly initialised folio_batch contains zero folios.
+ */
+static inline void folio_batch_init(struct folio_batch *fbatch)
+{
+	fbatch->nr = 0;
+}
+
+static inline unsigned int folio_batch_count(struct folio_batch *fbatch)
+{
+	return fbatch->nr;
+}
+
+static inline unsigned int fbatch_space(struct folio_batch *fbatch)
+{
+	return PAGEVEC_SIZE - fbatch->nr;
+}
+
+/**
+ * folio_batch_add() - Add a folio to a batch.
+ * @fbatch: The folio batch.
+ * @folio: The folio to add.
+ *
+ * The folio is added to the end of the batch.
+ * The batch must have previously been initialised using folio_batch_init().
+ *
+ * Return: The number of slots still available.
+ */
+static inline unsigned folio_batch_add(struct folio_batch *fbatch,
+		struct folio *folio)
+{
+	fbatch->folios[fbatch->nr++] = folio;
+	return fbatch_space(fbatch);
+}
+
+static inline void folio_batch_release(struct folio_batch *fbatch)
+{
+	pagevec_release((struct pagevec *)fbatch);
+}
+
+void folio_batch_remove_exceptionals(struct folio_batch *fbatch);
 #endif /* _LINUX_PAGEVEC_H */
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 6350354f97e9..43321dbebba8 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -7,6 +7,7 @@
 
 #include <linux/kernel.h>
 #include <linux/thread_info.h>
+#include <linux/mm_types.h>
 #include <uapi/linux/uio.h>
 
 struct page;
@@ -146,6 +147,12 @@ size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
 size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i);
 size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i);
 
+static inline size_t copy_folio_to_iter(struct folio *folio, size_t offset,
+		size_t bytes, struct iov_iter *i)
+{
+	return copy_page_to_iter(&folio->page, offset, bytes, i);
+}
+
 static __always_inline __must_check
 size_t copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i)
 {
diff --git a/include/linux/xarray.h b/include/linux/xarray.h
index a91e3d90df8a..d6d5da6ed735 100644
--- a/include/linux/xarray.h
+++ b/include/linux/xarray.h
@@ -1581,6 +1581,24 @@ static inline void xas_set(struct xa_state *xas, unsigned long index)
 }
 
 /**
+ * xas_advance() - Skip over sibling entries.
+ * @xas: XArray operation state.
+ * @index: Index of last sibling entry.
+ *
+ * Move the operation state to refer to the last sibling entry.
+ * This is useful for loops that normally want to see sibling
+ * entries but sometimes want to skip them.  Use xas_set() if you
+ * want to move to an index which is not part of this entry.
+ */
+static inline void xas_advance(struct xa_state *xas, unsigned long index)
+{
+	unsigned char shift = xas_is_node(xas) ? xas->xa_node->shift : 0;
+
+	xas->xa_index = index;
+	xas->xa_offset = (index >> shift) & XA_CHUNK_MASK;
+}
+
+/**
  * xas_set_order() - Set up XArray operation state for a multislot entry.
  * @xas: XArray operation state.
  * @index: Target of the operation.
diff --git a/include/trace/events/filemap.h b/include/trace/events/filemap.h
index c47b63db124e..46c89c1e460c 100644
--- a/include/trace/events/filemap.h
+++ b/include/trace/events/filemap.h
@@ -15,43 +15,45 @@
 
 DECLARE_EVENT_CLASS(mm_filemap_op_page_cache,
 
-	TP_PROTO(struct page *page),
+	TP_PROTO(struct folio *folio),
 
-	TP_ARGS(page),
+	TP_ARGS(folio),
 
 	TP_STRUCT__entry(
 		__field(unsigned long, pfn)
 		__field(unsigned long, i_ino)
 		__field(unsigned long, index)
 		__field(dev_t, s_dev)
+		__field(unsigned char, order)
 	),
 
 	TP_fast_assign(
-		__entry->pfn = page_to_pfn(page);
-		__entry->i_ino = page->mapping->host->i_ino;
-		__entry->index = page->index;
-		if (page->mapping->host->i_sb)
-			__entry->s_dev = page->mapping->host->i_sb->s_dev;
+		__entry->pfn = folio_pfn(folio);
+		__entry->i_ino = folio->mapping->host->i_ino;
+		__entry->index = folio->index;
+		if (folio->mapping->host->i_sb)
+			__entry->s_dev = folio->mapping->host->i_sb->s_dev;
 		else
-			__entry->s_dev = page->mapping->host->i_rdev;
+			__entry->s_dev = folio->mapping->host->i_rdev;
+		__entry->order = folio_order(folio);
 	),
 
-	TP_printk("dev %d:%d ino %lx page=%p pfn=0x%lx ofs=%lu",
+	TP_printk("dev %d:%d ino %lx pfn=0x%lx ofs=%lu order=%u",
 		MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
 		__entry->i_ino,
-		pfn_to_page(__entry->pfn),
 		__entry->pfn,
-		__entry->index << PAGE_SHIFT)
+		__entry->index << PAGE_SHIFT,
+		__entry->order)
 );
 
 DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_delete_from_page_cache,
-	TP_PROTO(struct page *page),
-	TP_ARGS(page)
+	TP_PROTO(struct folio *folio),
+	TP_ARGS(folio)
 	);
 
 DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_add_to_page_cache,
-	TP_PROTO(struct page *page),
-	TP_ARGS(page)
+	TP_PROTO(struct folio *folio),
+	TP_ARGS(folio)
 	);
 
 TRACE_EVENT(filemap_set_wb_err,