Merge tag 'folio-5.19' of git://git.infradead.org/users/willy/pagecache

Pull page cache updates from Matthew Wilcox:

 - Appoint myself page cache maintainer

 - Fix how scsicam uses the page cache

 - Use the memalloc_nofs_save() API to replace AOP_FLAG_NOFS

 - Remove the AOP flags entirely

 - Remove pagecache_write_begin() and pagecache_write_end()

 - Documentation updates

 - Convert several address_space operations to use folios:
     - is_dirty_writeback
     - readpage becomes read_folio
     - releasepage becomes release_folio
     - freepage becomes free_folio

 - Change filler_t to require a struct file pointer be the first
   argument like ->read_folio

* tag 'folio-5.19' of git://git.infradead.org/users/willy/pagecache: (107 commits)
  nilfs2: Fix some kernel-doc comments
  Appoint myself page cache maintainer
  fs: Remove aops->freepage
  secretmem: Convert to free_folio
  nfs: Convert to free_folio
  orangefs: Convert to free_folio
  fs: Add free_folio address space operation
  fs: Convert drop_buffers() to use a folio
  fs: Change try_to_free_buffers() to take a folio
  jbd2: Convert release_buffer_page() to use a folio
  jbd2: Convert jbd2_journal_try_to_free_buffers to take a folio
  reiserfs: Convert release_buffer_page() to use a folio
  fs: Remove last vestiges of releasepage
  ubifs: Convert to release_folio
  reiserfs: Convert to release_folio
  orangefs: Convert to release_folio
  ocfs2: Convert to release_folio
  nilfs2: Remove comment about releasepage
  nfs: Convert to release_folio
  jfs: Convert to release_folio
  ...

11 files changed, 80 insertions, 104 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 9a1eef6c5d35..fa0ca674450f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -225,12 +225,12 @@ void __filemap_remove_folio(struct folio *folio, void *shadow)
 
 void filemap_free_folio(struct address_space *mapping, struct folio *folio)
 {
-	void (*freepage)(struct page *);
+	void (*free_folio)(struct folio *);
 	int refs = 1;
 
-	freepage = mapping->a_ops->freepage;
-	if (freepage)
-		freepage(&folio->page);
+	free_folio = mapping->a_ops->free_folio;
+	if (free_folio)
+		free_folio(folio);
 
 	if (folio_test_large(folio) && !folio_test_hugetlb(folio))
 		refs = folio_nr_pages(folio);
@@ -807,7 +807,7 @@ void replace_page_cache_page(struct page *old, struct page *new)
 	struct folio *fold = page_folio(old);
 	struct folio *fnew = page_folio(new);
 	struct address_space *mapping = old->mapping;
-	void (*freepage)(struct page *) = mapping->a_ops->freepage;
+	void (*free_folio)(struct folio *) = mapping->a_ops->free_folio;
 	pgoff_t offset = old->index;
 	XA_STATE(xas, &mapping->i_pages, offset);
 
@@ -835,9 +835,9 @@ void replace_page_cache_page(struct page *old, struct page *new)
 	if (PageSwapBacked(new))
 		__inc_lruvec_page_state(new, NR_SHMEM);
 	xas_unlock_irq(&xas);
-	if (freepage)
-		freepage(old);
-	put_page(old);
+	if (free_folio)
+		free_folio(fold);
+	folio_put(fold);
 }
 EXPORT_SYMBOL_GPL(replace_page_cache_page);
 
@@ -2414,12 +2414,12 @@ static int filemap_read_folio(struct file *file, struct address_space *mapping,
 
 	/*
 	 * A previous I/O error may have been due to temporary failures,
-	 * eg. multipath errors.  PG_error will be set again if readpage
+	 * eg. multipath errors.  PG_error will be set again if read_folio
 	 * fails.
 	 */
 	folio_clear_error(folio);
 	/* Start the actual read. The read will unlock the page. */
-	error = mapping->a_ops->readpage(file, &folio->page);
+	error = mapping->a_ops->read_folio(file, folio);
 	if (error)
 		return error;
 
@@ -2636,7 +2636,7 @@ err:
  * @already_read: Number of bytes already read by the caller.
  *
  * Copies data from the page cache.  If the data is not currently present,
- * uses the readahead and readpage address_space operations to fetch it.
+ * uses the readahead and read_folio address_space operations to fetch it.
  *
  * Return: Total number of bytes copied, including those already read by
  * the caller.  If an error happens before any bytes are copied, returns
@@ -3447,7 +3447,7 @@ int generic_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct address_space *mapping = file->f_mapping;
 
-	if (!mapping->a_ops->readpage)
+	if (!mapping->a_ops->read_folio)
 		return -ENOEXEC;
 	file_accessed(file);
 	vma->vm_ops = &generic_file_vm_ops;
@@ -3483,10 +3483,13 @@ EXPORT_SYMBOL(generic_file_mmap);
 EXPORT_SYMBOL(generic_file_readonly_mmap);
 
 static struct folio *do_read_cache_folio(struct address_space *mapping,
-		pgoff_t index, filler_t filler, void *data, gfp_t gfp)
+		pgoff_t index, filler_t filler, struct file *file, gfp_t gfp)
 {
 	struct folio *folio;
 	int err;
+
+	if (!filler)
+		filler = mapping->a_ops->read_folio;
 repeat:
 	folio = filemap_get_folio(mapping, index);
 	if (!folio) {
@@ -3503,11 +3506,7 @@ repeat:
 		}
 
 filler:
-		if (filler)
-			err = filler(data, &folio->page);
-		else
-			err = mapping->a_ops->readpage(data, &folio->page);
-
+		err = filler(file, folio);
 		if (err < 0) {
 			folio_put(folio);
 			return ERR_PTR(err);
@@ -3557,44 +3556,44 @@ out:
 }
 
 /**
- * read_cache_folio - read into page cache, fill it if needed
- * @mapping:	the page's address_space
- * @index:	the page index
- * @filler:	function to perform the read
- * @data:	first arg to filler(data, page) function, often left as NULL
+ * read_cache_folio - Read into page cache, fill it if needed.
+ * @mapping: The address_space to read from.
+ * @index: The index to read.
+ * @filler: Function to perform the read, or NULL to use aops->read_folio().
+ * @file: Passed to filler function, may be NULL if not required.
  *
- * Read into the page cache. If a page already exists, and PageUptodate() is
- * not set, try to fill the page and wait for it to become unlocked.
+ * Read one page into the page cache.  If it succeeds, the folio returned
+ * will contain @index, but it may not be the first page of the folio.
  *
- * If the page does not get brought uptodate, return -EIO.
- *
- * The function expects mapping->invalidate_lock to be already held.
+ * If the filler function returns an error, it will be returned to the
+ * caller.
  *
- * Return: up to date page on success, ERR_PTR() on failure.
+ * Context: May sleep.  Expects mapping->invalidate_lock to be held.
+ * Return: An uptodate folio on success, ERR_PTR() on failure.
  */
 struct folio *read_cache_folio(struct address_space *mapping, pgoff_t index,
-		filler_t filler, void *data)
+		filler_t filler, struct file *file)
 {
-	return do_read_cache_folio(mapping, index, filler, data,
+	return do_read_cache_folio(mapping, index, filler, file,
 			mapping_gfp_mask(mapping));
 }
 EXPORT_SYMBOL(read_cache_folio);
 
 static struct page *do_read_cache_page(struct address_space *mapping,
-		pgoff_t index, filler_t *filler, void *data, gfp_t gfp)
+		pgoff_t index, filler_t *filler, struct file *file, gfp_t gfp)
 {
 	struct folio *folio;
 
-	folio = do_read_cache_folio(mapping, index, filler, data, gfp);
+	folio = do_read_cache_folio(mapping, index, filler, file, gfp);
 	if (IS_ERR(folio))
 		return &folio->page;
 	return folio_file_page(folio, index);
 }
 
 struct page *read_cache_page(struct address_space *mapping,
-				pgoff_t index, filler_t *filler, void *data)
+			pgoff_t index, filler_t *filler, struct file *file)
 {
-	return do_read_cache_page(mapping, index, filler, data,
+	return do_read_cache_page(mapping, index, filler, file,
 			mapping_gfp_mask(mapping));
 }
 EXPORT_SYMBOL(read_cache_page);
@@ -3622,27 +3621,6 @@ struct page *read_cache_page_gfp(struct address_space *mapping,
 }
 EXPORT_SYMBOL(read_cache_page_gfp);
 
-int pagecache_write_begin(struct file *file, struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned flags,
-				struct page **pagep, void **fsdata)
-{
-	const struct address_space_operations *aops = mapping->a_ops;
-
-	return aops->write_begin(file, mapping, pos, len, flags,
-							pagep, fsdata);
-}
-EXPORT_SYMBOL(pagecache_write_begin);
-
-int pagecache_write_end(struct file *file, struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata)
-{
-	const struct address_space_operations *aops = mapping->a_ops;
-
-	return aops->write_end(file, mapping, pos, len, copied, page, fsdata);
-}
-EXPORT_SYMBOL(pagecache_write_end);
-
 /*
  * Warn about a page cache invalidation failure during a direct I/O write.
  */
@@ -3754,7 +3732,6 @@ ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i)
 	const struct address_space_operations *a_ops = mapping->a_ops;
 	long status = 0;
 	ssize_t written = 0;
-	unsigned int flags = 0;
 
 	do {
 		struct page *page;
@@ -3784,7 +3761,7 @@ again:
 			break;
 		}
 
-		status = a_ops->write_begin(file, mapping, pos, bytes, flags,
+		status = a_ops->write_begin(file, mapping, pos, bytes,
 						&page, &fsdata);
 		if (unlikely(status < 0))
 			break;
@@ -3978,8 +3955,8 @@ bool filemap_release_folio(struct folio *folio, gfp_t gfp)
 	if (folio_test_writeback(folio))
 		return false;
 
-	if (mapping && mapping->a_ops->releasepage)
-		return mapping->a_ops->releasepage(&folio->page, gfp);
-	return try_to_free_buffers(&folio->page);
+	if (mapping && mapping->a_ops->release_folio)
+		return mapping->a_ops->release_folio(folio, gfp);
+	return try_to_free_buffers(folio);
 }
 EXPORT_SYMBOL(filemap_release_folio);
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index 46fa179e32fb..20bc15b57d93 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -131,12 +131,10 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
 EXPORT_SYMBOL(pagecache_get_page);
 
 struct page *grab_cache_page_write_begin(struct address_space *mapping,
-					pgoff_t index, unsigned flags)
+					pgoff_t index)
 {
 	unsigned fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
 
-	if (flags & AOP_FLAG_NOFS)
-		fgp_flags |= FGP_NOFS;
 	return pagecache_get_page(mapping, index, fgp_flags,
 			mapping_gfp_mask(mapping));
 }
diff --git a/mm/memory.c b/mm/memory.c
index 76e3af9639d9..2a12028a3749 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -555,11 +555,11 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
 		dump_page(page, "bad pte");
 	pr_alert("addr:%px vm_flags:%08lx anon_vma:%px mapping:%px index:%lx\n",
 		 (void *)addr, vma->vm_flags, vma->anon_vma, mapping, index);
-	pr_alert("file:%pD fault:%ps mmap:%ps readpage:%ps\n",
+	pr_alert("file:%pD fault:%ps mmap:%ps read_folio:%ps\n",
 		 vma->vm_file,
 		 vma->vm_ops ? vma->vm_ops->fault : NULL,
 		 vma->vm_file ? vma->vm_file->f_op->mmap : NULL,
-		 mapping ? mapping->a_ops->readpage : NULL);
+		 mapping ? mapping->a_ops->read_folio : NULL);
 	dump_stack();
 	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index 6c31ee1e1c9b..21d82636c291 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1013,7 +1013,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 	if (!page->mapping) {
 		VM_BUG_ON_PAGE(PageAnon(page), page);
 		if (page_has_private(page)) {
-			try_to_free_buffers(page);
+			try_to_free_buffers(folio);
 			goto out_unlock_both;
 		}
 	} else if (page_mapped(page)) {
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 7e2da284e427..fa1117db4610 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2602,10 +2602,12 @@ EXPORT_SYMBOL(folio_redirty_for_writepage);
  * folio_mark_dirty - Mark a folio as being modified.
  * @folio: The folio.
  *
- * For folios with a mapping this should be done with the folio lock held
- * for the benefit of asynchronous memory errors who prefer a consistent
- * dirty state. This rule can be broken in some special cases,
- * but should be better not to.
+ * The folio may not be truncated while this function is running.
+ * Holding the folio lock is sufficient to prevent truncation, but some
+ * callers cannot acquire a sleeping lock.  These callers instead hold
+ * the page table lock for a page table which contains at least one page
+ * in this folio.  Truncation will block on the page table lock as it
+ * unmaps pages before removing the folio from its mapping.
  *
  * Return: True if the folio was newly dirtied, false if it was already dirty.
  */
diff --git a/mm/page_io.c b/mm/page_io.c
index 3fbdab6a940e..a9444e67ec20 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -336,7 +336,7 @@ int swap_readpage(struct page *page, bool synchronous)
 		struct file *swap_file = sis->swap_file;
 		struct address_space *mapping = swap_file->f_mapping;
 
-		ret = mapping->a_ops->readpage(swap_file, page);
+		ret = mapping->a_ops->read_folio(swap_file, page_folio(page));
 		if (!ret)
 			count_vm_event(PSWPIN);
 		goto out;
diff --git a/mm/readahead.c b/mm/readahead.c
index 26bf74a6b2fe..b78921b54754 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -15,7 +15,7 @@
  * explicitly requested by the application.  Readahead only ever
  * attempts to read folios that are not yet in the page cache.  If a
  * folio is present but not up-to-date, readahead will not try to read
- * it. In that case a simple ->readpage() will be requested.
+ * it. In that case a simple ->read_folio() will be requested.
  *
  * Readahead is triggered when an application read request (whether a
  * system call or a page fault) finds that the requested folio is not in
@@ -78,7 +78,7 @@
  * address space operation, for which mpage_readahead() is a canonical
  * implementation.  ->readahead() should normally initiate reads on all
  * folios, but may fail to read any or all folios without causing an I/O
- * error.  The page cache reading code will issue a ->readpage() request
+ * error.  The page cache reading code will issue a ->read_folio() request
  * for any folio which ->readahead() did not read, and only an error
  * from this will be final.
  *
@@ -110,7 +110,7 @@
  * were not fetched with readahead_folio().  This will allow a
  * subsequent synchronous readahead request to try them again.  If they
  * are left in the page cache, then they will be read individually using
- * ->readpage() which may be less efficient.
+ * ->read_folio() which may be less efficient.
  */
 
 #include <linux/blkdev.h>
@@ -146,7 +146,7 @@ EXPORT_SYMBOL_GPL(file_ra_state_init);
 static void read_pages(struct readahead_control *rac)
 {
 	const struct address_space_operations *aops = rac->mapping->a_ops;
-	struct page *page;
+	struct folio *folio;
 	struct blk_plug plug;
 
 	if (!readahead_count(rac))
@@ -157,24 +157,23 @@ static void read_pages(struct readahead_control *rac)
 	if (aops->readahead) {
 		aops->readahead(rac);
 		/*
-		 * Clean up the remaining pages.  The sizes in ->ra
+		 * Clean up the remaining folios.  The sizes in ->ra
 		 * may be used to size the next readahead, so make sure
 		 * they accurately reflect what happened.
 		 */
-		while ((page = readahead_page(rac))) {
-			rac->ra->size -= 1;
-			if (rac->ra->async_size > 0) {
-				rac->ra->async_size -= 1;
-				delete_from_page_cache(page);
+		while ((folio = readahead_folio(rac)) != NULL) {
+			unsigned long nr = folio_nr_pages(folio);
+
+			rac->ra->size -= nr;
+			if (rac->ra->async_size >= nr) {
+				rac->ra->async_size -= nr;
+				filemap_remove_folio(folio);
 			}
-			unlock_page(page);
-			put_page(page);
+			folio_unlock(folio);
 		}
 	} else {
-		while ((page = readahead_page(rac))) {
-			aops->readpage(rac->file, page);
-			put_page(page);
-		}
+		while ((folio = readahead_folio(rac)) != NULL)
+			aops->read_folio(rac->file, folio);
 	}
 
 	blk_finish_plug(&plug);
@@ -255,8 +254,8 @@ void page_cache_ra_unbounded(struct readahead_control *ractl,
 	}
 
 	/*
-	 * Now start the IO.  We ignore I/O errors - if the page is not
-	 * uptodate then the caller will launch readpage again, and
+	 * Now start the IO.  We ignore I/O errors - if the folio is not
+	 * uptodate then the caller will launch read_folio again, and
 	 * will then handle the error.
 	 */
 	read_pages(ractl);
@@ -304,7 +303,7 @@ void force_page_cache_ra(struct readahead_control *ractl,
 	struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
 	unsigned long max_pages, index;
 
-	if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readahead))
+	if (unlikely(!mapping->a_ops->read_folio && !mapping->a_ops->readahead))
 		return;
 
 	/*
diff --git a/mm/secretmem.c b/mm/secretmem.c
index 3b3cf2892b6a..206ed6b40c1d 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -145,15 +145,15 @@ static int secretmem_migratepage(struct address_space *mapping,
 	return -EBUSY;
 }
 
-static void secretmem_freepage(struct page *page)
+static void secretmem_free_folio(struct folio *folio)
 {
-	set_direct_map_default_noflush(page);
-	clear_highpage(page);
+	set_direct_map_default_noflush(&folio->page);
+	folio_zero_segment(folio, 0, folio_size(folio));
 }
 
 const struct address_space_operations secretmem_aops = {
 	.dirty_folio	= noop_dirty_folio,
-	.freepage	= secretmem_freepage,
+	.free_folio	= secretmem_free_folio,
 	.migratepage	= secretmem_migratepage,
 	.isolate_page	= secretmem_isolate_page,
 };
diff --git a/mm/shmem.c b/mm/shmem.c
index 4b2fea33158e..f3e8de8ff75c 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2426,7 +2426,7 @@ static int shmem_initxattrs(struct inode *, const struct xattr *, void *);
 
 static int
 shmem_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
+			loff_t pos, unsigned len,
 			struct page **pagep, void **fsdata)
 {
 	struct inode *inode = mapping->host;
@@ -4162,7 +4162,7 @@ int shmem_zero_setup(struct vm_area_struct *vma)
  *
  * This behaves as a tmpfs "read_cache_page_gfp(mapping, index, gfp)",
  * with any new page allocations done using the specified allocation flags.
- * But read_cache_page_gfp() uses the ->readpage() method: which does not
+ * But read_cache_page_gfp() uses the ->read_folio() method: which does not
  * suit tmpfs, since it may have pages in swapcache, and needs to find those
  * for itself; although drivers/gpu/drm i915 and ttm rely upon this support.
  *
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 981a6e85c88e..6aec1b24f440 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3028,7 +3028,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	/*
 	 * Read the swap header.
 	 */
-	if (!mapping->a_ops->readpage) {
+	if (!mapping->a_ops->read_folio) {
 		error = -EINVAL;
 		goto bad_swap_unlock_inode;
 	}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1678802e03e7..edc89f26b738 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1181,7 +1181,7 @@ static pageout_t pageout(struct folio *folio, struct address_space *mapping)
 		 * folio->mapping == NULL while being dirty with clean buffers.
 		 */
 		if (folio_test_private(folio)) {
-			if (try_to_free_buffers(&folio->page)) {
+			if (try_to_free_buffers(folio)) {
 				folio_clear_dirty(folio);
 				pr_info("%s: orphaned folio\n", __func__);
 				return PAGE_CLEAN;
@@ -1282,9 +1282,9 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio,
 		xa_unlock_irq(&mapping->i_pages);
 		put_swap_page(&folio->page, swap);
 	} else {
-		void (*freepage)(struct page *);
+		void (*free_folio)(struct folio *);
 
-		freepage = mapping->a_ops->freepage;
+		free_folio = mapping->a_ops->free_folio;
 		/*
 		 * Remember a shadow entry for reclaimed file cache in
 		 * order to detect refaults, thus thrashing, later on.
@@ -1310,8 +1310,8 @@ static int __remove_mapping(struct address_space *mapping, struct folio *folio,
 			inode_add_lru(mapping->host);
 		spin_unlock(&mapping->host->i_lock);
 
-		if (freepage != NULL)
-			freepage(&folio->page);
+		if (free_folio)
+			free_folio(folio);
 	}
 
 	return 1;
@@ -1451,7 +1451,7 @@ static void folio_check_dirty_writeback(struct folio *folio,
 
 	mapping = folio_mapping(folio);
 	if (mapping && mapping->a_ops->is_dirty_writeback)
-		mapping->a_ops->is_dirty_writeback(&folio->page, dirty, writeback);
+		mapping->a_ops->is_dirty_writeback(folio, dirty, writeback);
 }
 
 static struct page *alloc_demote_page(struct page *page, unsigned long node)