Merge branch 'work.write.end'

Matthew Wilcox (Oracle) <[email protected]> says:

On top of the ufs, minix, sysv and qnx6 directory handling patches, this
patch series converts us to using folios for write_begin and write_end.
That's the last mention of 'struct page' in several filesystems.

* work.write.end: (54 commits)
  buffer: Convert __block_write_begin() to take a folio
  ocfs2: Convert ocfs2_write_zero_page to use a folio
  fs: Convert aops->write_begin to take a folio
  fs: Convert aops->write_end to take a folio
  vboxsf: Use a folio in vboxsf_write_end()
  orangefs: Convert orangefs_write_begin() to use a folio
  orangefs: Convert orangefs_write_end() to use a folio
  jffs2: Convert jffs2_write_begin() to use a folio
  jffs2: Convert jffs2_write_end() to use a folio
  hostfs: Convert hostfs_write_end() to use a folio
  fuse: Convert fuse_write_begin() to use a folio
  fuse: Convert fuse_write_end() to use a folio
  f2fs: Convert f2fs_write_begin() to use a folio
  f2fs: Convert f2fs_write_end() to use a folio
  ecryptfs: Use a folio in ecryptfs_write_begin()
  ecryptfs: Convert ecryptfs_write_end() to use a folio
  buffer: Convert block_write_end() to take a folio
  ntfs3: Remove reset_log_file()
  nilfs2: Use a folio in nilfs_recover_dsync_blocks()
  buffer: Use a folio in generic_write_end()
  ...

Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Christian Brauner <[email protected]>

Author: brauner

Documentation/filesystems/locking.rst

@@ -251,10 +251,10 @@ prototypes::
 	void (*readahead)(struct readahead_control *);
 	int (*write_begin)(struct file *, struct address_space *mapping,
 				loff_t pos, unsigned len,
-				struct page **pagep, void **fsdata);
+				struct folio **foliop, void **fsdata);
 	int (*write_end)(struct file *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata);
+				struct folio *folio, void *fsdata);
 	sector_t (*bmap)(struct address_space *, sector_t);
 	void (*invalidate_folio) (struct folio *, size_t start, size_t len);
 	bool (*release_folio)(struct folio *, gfp_t);
@@ -280,7 +280,7 @@ read_folio:		yes, unlocks				shared
 writepages:
 dirty_folio:		maybe
 readahead:		yes, unlocks				shared
-write_begin:		locks the page		 exclusive
+write_begin:		locks the folio		 exclusive
 write_end:		yes, unlocks		 exclusive
 bmap:
 invalidate_folio:	yes					exclusive

Documentation/filesystems/vfs.rst

@@ -810,7 +810,7 @@ cache in your filesystem.  The following members are defined:
 				struct page **pagep, void **fsdata);
 		int (*write_end)(struct file *, struct address_space *mapping,
 				 loff_t pos, unsigned len, unsigned copied,
-				 struct page *page, void *fsdata);
+				 struct folio *folio, void *fsdata);
 		sector_t (*bmap)(struct address_space *, sector_t);
 		void (*invalidate_folio) (struct folio *, size_t start, size_t len);
 		bool (*release_folio)(struct folio *, gfp_t);
@@ -926,12 +926,12 @@ cache in your filesystem.  The following members are defined:
 	(if they haven't been read already) so that the updated blocks
 	can be written out properly.
 
-	The filesystem must return the locked pagecache page for the
-	specified offset, in ``*pagep``, for the caller to write into.
+	The filesystem must return the locked pagecache folio for the
+	specified offset, in ``*foliop``, for the caller to write into.
 
 	It must be able to cope with short writes (where the length
 	passed to write_begin is greater than the number of bytes copied
-	into the page).
+	into the folio).
 
 	A void * may be returned in fsdata, which then gets passed into
 	write_end.
@@ -944,8 +944,8 @@ cache in your filesystem.  The following members are defined:
 	called.  len is the original len passed to write_begin, and
 	copied is the amount that was able to be copied.
 
-	The filesystem must take care of unlocking the page and
-	releasing it refcount, and updating i_size.
+	The filesystem must take care of unlocking the folio,
+	decrementing its refcount, and updating i_size.
 
 	Returns < 0 on failure, otherwise the number of bytes (<=
 	'copied') that were able to be copied into pagecache.

block/fops.c

@@ -451,20 +451,20 @@ static void blkdev_readahead(struct readahead_control *rac)
 }
 
 static int blkdev_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct page **pagep, void **fsdata)
+		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
 {
-	return block_write_begin(mapping, pos, len, pagep, blkdev_get_block);
+	return block_write_begin(mapping, pos, len, foliop, blkdev_get_block);
 }
 
 static int blkdev_write_end(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned copied, struct page *page,
+		loff_t pos, unsigned len, unsigned copied, struct folio *folio,
 		void *fsdata)
 {
 	int ret;
-	ret = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+	ret = block_write_end(file, mapping, pos, len, copied, folio, fsdata);
 
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 
 	return ret;
 }

drivers/gpu/drm/i915/gem/i915_gem_shmem.c

@@ -424,7 +424,8 @@ shmem_pwrite(struct drm_i915_gem_object *obj,
 	struct address_space *mapping = obj->base.filp->f_mapping;
 	const struct address_space_operations *aops = mapping->a_ops;
 	char __user *user_data = u64_to_user_ptr(arg->data_ptr);
-	u64 remain, offset;
+	u64 remain;
+	loff_t pos;
 	unsigned int pg;
 
 	/* Caller already validated user args */
@@ -457,12 +458,12 @@ shmem_pwrite(struct drm_i915_gem_object *obj,
 	 */
 
 	remain = arg->size;
-	offset = arg->offset;
-	pg = offset_in_page(offset);
+	pos = arg->offset;
+	pg = offset_in_page(pos);
 
 	do {
 		unsigned int len, unwritten;
-		struct page *page;
+		struct folio *folio;
 		void *data, *vaddr;
 		int err;
 		char __maybe_unused c;
@@ -480,21 +481,19 @@ shmem_pwrite(struct drm_i915_gem_object *obj,
 		if (err)
 			return err;
 
-		err = aops->write_begin(obj->base.filp, mapping, offset, len,
-					&page, &data);
+		err = aops->write_begin(obj->base.filp, mapping, pos, len,
+					&folio, &data);
 		if (err < 0)
 			return err;
 
-		vaddr = kmap_local_page(page);
+		vaddr = kmap_local_folio(folio, offset_in_folio(folio, pos));
 		pagefault_disable();
-		unwritten = __copy_from_user_inatomic(vaddr + pg,
-						      user_data,
-						      len);
+		unwritten = __copy_from_user_inatomic(vaddr, user_data, len);
 		pagefault_enable();
 		kunmap_local(vaddr);
 
-		err = aops->write_end(obj->base.filp, mapping, offset, len,
-				      len - unwritten, page, data);
+		err = aops->write_end(obj->base.filp, mapping, pos, len,
+				      len - unwritten, folio, data);
 		if (err < 0)
 			return err;
 
@@ -504,7 +503,7 @@ shmem_pwrite(struct drm_i915_gem_object *obj,
 
 		remain -= len;
 		user_data += len;
-		offset += len;
+		pos += len;
 		pg = 0;
 	} while (remain);
 
@@ -660,7 +659,7 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915,
 	struct drm_i915_gem_object *obj;
 	struct file *file;
 	const struct address_space_operations *aops;
-	resource_size_t offset;
+	loff_t pos;
 	int err;
 
 	GEM_WARN_ON(IS_DGFX(i915));
@@ -672,29 +671,27 @@ i915_gem_object_create_shmem_from_data(struct drm_i915_private *i915,
 
 	file = obj->base.filp;
 	aops = file->f_mapping->a_ops;
-	offset = 0;
+	pos = 0;
 	do {
 		unsigned int len = min_t(typeof(size), size, PAGE_SIZE);
-		struct page *page;
-		void *pgdata, *vaddr;
+		struct folio *folio;
+		void *fsdata;
 
-		err = aops->write_begin(file, file->f_mapping, offset, len,
-					&page, &pgdata);
+		err = aops->write_begin(file, file->f_mapping, pos, len,
+					&folio, &fsdata);
 		if (err < 0)
 			goto fail;
 
-		vaddr = kmap(page);
-		memcpy(vaddr, data, len);
-		kunmap(page);
+		memcpy_to_folio(folio, offset_in_folio(folio, pos), data, len);
 
-		err = aops->write_end(file, file->f_mapping, offset, len, len,
-				      page, pgdata);
+		err = aops->write_end(file, file->f_mapping, pos, len, len,
+				      folio, fsdata);
 		if (err < 0)
 			goto fail;
 
 		size -= len;
 		data += len;
-		offset += len;
+		pos += len;
 	} while (size);
 
 	return obj;

fs/adfs/inode.c

@@ -55,12 +55,11 @@ static void adfs_write_failed(struct address_space *mapping, loff_t to)
 
 static int adfs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	*pagep = NULL;
-	ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata,
+	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
 				adfs_get_block,
 				&ADFS_I(mapping->host)->mmu_private);
 	if (unlikely(ret))

fs/affs/file.c

@@ -417,12 +417,11 @@ affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 
 static int affs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	*pagep = NULL;
-	ret = cont_write_begin(file, mapping, pos, len, pagep, fsdata,
+	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
 				affs_get_block,
 				&AFFS_I(mapping->host)->mmu_private);
 	if (unlikely(ret))
@@ -433,12 +432,12 @@ static int affs_write_begin(struct file *file, struct address_space *mapping,
 
 static int affs_write_end(struct file *file, struct address_space *mapping,
 			  loff_t pos, unsigned int len, unsigned int copied,
-			  struct page *page, void *fsdata)
+			  struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	int ret;
 
-	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
+	ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
 
 	/* Clear Archived bit on file writes, as AmigaOS would do */
 	if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) {
@@ -648,7 +647,7 @@ static int affs_read_folio_ofs(struct file *file, struct folio *folio)
 
 static int affs_write_begin_ofs(struct file *file, struct address_space *mapping,
 				loff_t pos, unsigned len,
-				struct page **pagep, void **fsdata)
+				struct folio **foliop, void **fsdata)
 {
 	struct inode *inode = mapping->host;
 	struct folio *folio;
@@ -671,7 +670,7 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping
 			mapping_gfp_mask(mapping));
 	if (IS_ERR(folio))
 		return PTR_ERR(folio);
-	*pagep = &folio->page;
+	*foliop = folio;
 
 	if (folio_test_uptodate(folio))
 		return 0;
@@ -687,9 +686,8 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping
 
 static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata)
+				struct folio *folio, void *fsdata)
 {
-	struct folio *folio = page_folio(page);
 	struct inode *inode = mapping->host;
 	struct super_block *sb = inode->i_sb;
 	struct buffer_head *bh, *prev_bh;
@@ -882,14 +880,14 @@ affs_truncate(struct inode *inode)
 
 	if (inode->i_size > AFFS_I(inode)->mmu_private) {
 		struct address_space *mapping = inode->i_mapping;
-		struct page *page;
+		struct folio *folio;
 		void *fsdata = NULL;
 		loff_t isize = inode->i_size;
 		int res;
 
-		res = mapping->a_ops->write_begin(NULL, mapping, isize, 0, &page, &fsdata);
+		res = mapping->a_ops->write_begin(NULL, mapping, isize, 0, &folio, &fsdata);
 		if (!res)
-			res = mapping->a_ops->write_end(NULL, mapping, isize, 0, 0, page, fsdata);
+			res = mapping->a_ops->write_end(NULL, mapping, isize, 0, 0, folio, fsdata);
 		else
 			inode->i_size = AFFS_I(inode)->mmu_private;
 		mark_inode_dirty(inode);

fs/bcachefs/fs-io-buffered.c

@@ -659,7 +659,7 @@ int bch2_writepages(struct address_space *mapping, struct writeback_control *wbc
 
 int bch2_write_begin(struct file *file, struct address_space *mapping,
 		     loff_t pos, unsigned len,
-		     struct page **pagep, void **fsdata)
+		     struct folio **foliop, void **fsdata)
 {
 	struct bch_inode_info *inode = to_bch_ei(mapping->host);
 	struct bch_fs *c = inode->v.i_sb->s_fs_info;
@@ -728,12 +728,11 @@ int bch2_write_begin(struct file *file, struct address_space *mapping,
 		goto err;
 	}
 
-	*pagep = &folio->page;
+	*foliop = folio;
 	return 0;
 err:
 	folio_unlock(folio);
 	folio_put(folio);
-	*pagep = NULL;
 err_unlock:
 	bch2_pagecache_add_put(inode);
 	kfree(res);
@@ -743,12 +742,11 @@ int bch2_write_begin(struct file *file, struct address_space *mapping,
 
 int bch2_write_end(struct file *file, struct address_space *mapping,
 		   loff_t pos, unsigned len, unsigned copied,
-		   struct page *page, void *fsdata)
+		   struct folio *folio, void *fsdata)
 {
 	struct bch_inode_info *inode = to_bch_ei(mapping->host);
 	struct bch_fs *c = inode->v.i_sb->s_fs_info;
 	struct bch2_folio_reservation *res = fsdata;
-	struct folio *folio = page_folio(page);
 	unsigned offset = pos - folio_pos(folio);
 
 	lockdep_assert_held(&inode->v.i_rwsem);

fs/bcachefs/fs-io-buffered.h

@@ -10,10 +10,10 @@ int bch2_read_folio(struct file *, struct folio *);
 int bch2_writepages(struct address_space *, struct writeback_control *);
 void bch2_readahead(struct readahead_control *);
 
-int bch2_write_begin(struct file *, struct address_space *, loff_t,
-		     unsigned, struct page **, void **);
+int bch2_write_begin(struct file *, struct address_space *, loff_t pos,
+		     unsigned len, struct folio **, void **);
 int bch2_write_end(struct file *, struct address_space *, loff_t,
-		   unsigned, unsigned, struct page *, void *);
+		   unsigned len, unsigned copied, struct folio *, void *);
 
 ssize_t bch2_write_iter(struct kiocb *, struct iov_iter *);
 

fs/bfs/file.c

@@ -172,11 +172,11 @@ static void bfs_write_failed(struct address_space *mapping, loff_t to)
 
 static int bfs_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata)
+			struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	ret = block_write_begin(mapping, pos, len, pagep, bfs_get_block);
+	ret = block_write_begin(mapping, pos, len, foliop, bfs_get_block);
 	if (unlikely(ret))
 		bfs_write_failed(mapping, pos + len);