Merge patch series "fuse: use iomap for buffered writes + writeback"

Joanne Koong <joannelkoong@gmail.com> says:

This series adds fuse iomap support for buffered writes and dirty folio
writeback. This is needed so that granular uptodate and dirty tracking can
be used in fuse when large folios are enabled. This has two big advantages.
For writes, instead of the entire folio needing to be read into the page
cache, only the relevant portions need to be. For writeback, only the
dirty portions need to be written back instead of the entire folio.

Please note that this patchset does not enable large folios yet. That will be
sent out in a separate future patchset.

* patches from https://lore.kernel.org/20250715202122.2282532-1-joannelkoong@gmail.com:
  fuse: refactor writeback to use iomap_writepage_ctx inode
  fuse: hook into iomap for invalidating and checking partial uptodateness
  fuse: use iomap for folio laundering
  fuse: use iomap for writeback
  fuse: use iomap for buffered writes

Link: https://lore.kernel.org/20250715202122.2282532-1-joannelkoong@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>

2 files changed, 154 insertions, 192 deletions

diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig
index ca215a3cba3e..a774166264de 100644
--- a/fs/fuse/Kconfig
+++ b/fs/fuse/Kconfig
@@ -2,6 +2,7 @@
 config FUSE_FS
 	tristate "FUSE (Filesystem in Userspace) support"
 	select FS_POSIX_ACL
+	select FS_IOMAP
 	help
 	  With FUSE it is possible to implement a fully functional filesystem
 	  in a userspace program.
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index f102afc03359..f16426fd2bf5 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -21,6 +21,7 @@
 #include <linux/filelock.h>
 #include <linux/splice.h>
 #include <linux/task_io_accounting_ops.h>
+#include <linux/iomap.h>
 
 static int fuse_send_open(struct fuse_mount *fm, u64 nodeid,
 			  unsigned int open_flags, int opcode,
@@ -788,12 +789,16 @@ static void fuse_short_read(struct inode *inode, u64 attr_ver, size_t num_read,
 	}
 }
 
-static int fuse_do_readfolio(struct file *file, struct folio *folio)
+static int fuse_do_readfolio(struct file *file, struct folio *folio,
+			     size_t off, size_t len)
 {
 	struct inode *inode = folio->mapping->host;
 	struct fuse_mount *fm = get_fuse_mount(inode);
-	loff_t pos = folio_pos(folio);
-	struct fuse_folio_desc desc = { .length = folio_size(folio) };
+	loff_t pos = folio_pos(folio) + off;
+	struct fuse_folio_desc desc = {
+		.offset = off,
+		.length = len,
+	};
 	struct fuse_io_args ia = {
 		.ap.args.page_zeroing = true,
 		.ap.args.out_pages = true,
@@ -820,8 +825,6 @@ static int fuse_do_readfolio(struct file *file, struct folio *folio)
 	if (res < desc.length)
 		fuse_short_read(inode, attr_ver, res, &ia.ap);
 
-	folio_mark_uptodate(folio);
-
 	return 0;
 }
 
@@ -834,13 +837,26 @@ static int fuse_read_folio(struct file *file, struct folio *folio)
 	if (fuse_is_bad(inode))
 		goto out;
 
-	err = fuse_do_readfolio(file, folio);
+	err = fuse_do_readfolio(file, folio, 0, folio_size(folio));
+	if (!err)
+		folio_mark_uptodate(folio);
+
 	fuse_invalidate_atime(inode);
  out:
 	folio_unlock(folio);
 	return err;
 }
 
+static int fuse_iomap_read_folio_range(const struct iomap_iter *iter,
+				       struct folio *folio, loff_t pos,
+				       size_t len)
+{
+	struct file *file = iter->private;
+	size_t off = offset_in_folio(folio, pos);
+
+	return fuse_do_readfolio(file, folio, off, len);
+}
+
 static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
 			       int err)
 {
@@ -1375,6 +1391,24 @@ static void fuse_dio_unlock(struct kiocb *iocb, bool exclusive)
 	}
 }
 
+static const struct iomap_write_ops fuse_iomap_write_ops = {
+	.read_folio_range = fuse_iomap_read_folio_range,
+};
+
+static int fuse_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+			    unsigned int flags, struct iomap *iomap,
+			    struct iomap *srcmap)
+{
+	iomap->type = IOMAP_MAPPED;
+	iomap->length = length;
+	iomap->offset = offset;
+	return 0;
+}
+
+static const struct iomap_ops fuse_iomap_ops = {
+	.iomap_begin	= fuse_iomap_begin,
+};
+
 static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
@@ -1384,6 +1418,7 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct inode *inode = mapping->host;
 	ssize_t err, count;
 	struct fuse_conn *fc = get_fuse_conn(inode);
+	bool writeback = false;
 
 	if (fc->writeback_cache) {
 		/* Update size (EOF optimization) and mode (SUID clearing) */
@@ -1392,16 +1427,11 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		if (err)
 			return err;
 
-		if (fc->handle_killpriv_v2 &&
-		    setattr_should_drop_suidgid(idmap,
-						file_inode(file))) {
-			goto writethrough;
-		}
-
-		return generic_file_write_iter(iocb, from);
+		if (!fc->handle_killpriv_v2 ||
+		    !setattr_should_drop_suidgid(idmap, file_inode(file)))
+			writeback = true;
 	}
 
-writethrough:
 	inode_lock(inode);
 
 	err = count = generic_write_checks(iocb, from);
@@ -1420,6 +1450,15 @@ writethrough:
 			goto out;
 		written = direct_write_fallback(iocb, from, written,
 				fuse_perform_write(iocb, from));
+	} else if (writeback) {
+		/*
+		 * Use iomap so that we can do granular uptodate reads
+		 * and granular dirty tracking for large folios.
+		 */
+		written = iomap_file_buffered_write(iocb, from,
+						    &fuse_iomap_ops,
+						    &fuse_iomap_write_ops,
+						    file);
 	} else {
 		written = fuse_perform_write(iocb, from);
 	}
@@ -1794,7 +1833,7 @@ static void fuse_writepage_finish(struct fuse_writepage_args *wpa)
 		 * scope of the fi->lock alleviates xarray lock
 		 * contention and noticeably improves performance.
 		 */
-		folio_end_writeback(ap->folios[i]);
+		iomap_finish_folio_write(inode, ap->folios[i], 1);
 		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
 		wb_writeout_inc(&bdi->wb);
 	}
@@ -1981,19 +2020,20 @@ static void fuse_writepage_add_to_bucket(struct fuse_conn *fc,
 }
 
 static void fuse_writepage_args_page_fill(struct fuse_writepage_args *wpa, struct folio *folio,
-					  uint32_t folio_index)
+					  uint32_t folio_index, loff_t offset, unsigned len)
 {
 	struct inode *inode = folio->mapping->host;
 	struct fuse_args_pages *ap = &wpa->ia.ap;
 
 	ap->folios[folio_index] = folio;
-	ap->descs[folio_index].offset = 0;
-	ap->descs[folio_index].length = folio_size(folio);
+	ap->descs[folio_index].offset = offset;
+	ap->descs[folio_index].length = len;
 
 	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
 }
 
 static struct fuse_writepage_args *fuse_writepage_args_setup(struct folio *folio,
+							     size_t offset,
 							     struct fuse_file *ff)
 {
 	struct inode *inode = folio->mapping->host;
@@ -2006,7 +2046,7 @@ static struct fuse_writepage_args *fuse_writepage_args_setup(struct folio *folio
 		return NULL;
 
 	fuse_writepage_add_to_bucket(fc, wpa);
-	fuse_write_args_fill(&wpa->ia, ff, folio_pos(folio), 0);
+	fuse_write_args_fill(&wpa->ia, ff, folio_pos(folio) + offset, 0);
 	wpa->ia.write.in.write_flags |= FUSE_WRITE_CACHE;
 	wpa->inode = inode;
 	wpa->ia.ff = ff;
@@ -2018,63 +2058,28 @@ static struct fuse_writepage_args *fuse_writepage_args_setup(struct folio *folio
 	return wpa;
 }
 
-static int fuse_writepage_locked(struct folio *folio)
-{
-	struct address_space *mapping = folio->mapping;
-	struct inode *inode = mapping->host;
-	struct fuse_inode *fi = get_fuse_inode(inode);
-	struct fuse_writepage_args *wpa;
-	struct fuse_args_pages *ap;
-	struct fuse_file *ff;
-	int error = -EIO;
-
-	ff = fuse_write_file_get(fi);
-	if (!ff)
-		goto err;
-
-	wpa = fuse_writepage_args_setup(folio, ff);
-	error = -ENOMEM;
-	if (!wpa)
-		goto err_writepage_args;
-
-	ap = &wpa->ia.ap;
-	ap->num_folios = 1;
-
-	folio_start_writeback(folio);
-	fuse_writepage_args_page_fill(wpa, folio, 0);
-
-	spin_lock(&fi->lock);
-	list_add_tail(&wpa->queue_entry, &fi->queued_writes);
-	fuse_flush_writepages(inode);
-	spin_unlock(&fi->lock);
-
-	return 0;
-
-err_writepage_args:
-	fuse_file_put(ff, false);
-err:
-	mapping_set_error(folio->mapping, error);
-	return error;
-}
-
 struct fuse_fill_wb_data {
 	struct fuse_writepage_args *wpa;
 	struct fuse_file *ff;
-	struct inode *inode;
 	unsigned int max_folios;
-	unsigned int nr_pages;
+	/*
+	 * nr_bytes won't overflow since fuse_writepage_need_send() caps
+	 * wb requests to never exceed fc->max_pages (which has an upper bound
+	 * of U16_MAX).
+	 */
+	unsigned int nr_bytes;
 };
 
-static bool fuse_pages_realloc(struct fuse_fill_wb_data *data)
+static bool fuse_pages_realloc(struct fuse_fill_wb_data *data,
+			       unsigned int max_pages)
 {
 	struct fuse_args_pages *ap = &data->wpa->ia.ap;
-	struct fuse_conn *fc = get_fuse_conn(data->inode);
 	struct folio **folios;
 	struct fuse_folio_desc *descs;
 	unsigned int nfolios = min_t(unsigned int,
 				     max_t(unsigned int, data->max_folios * 2,
 					   FUSE_DEFAULT_MAX_PAGES_PER_REQ),
-				    fc->max_pages);
+				    max_pages);
 	WARN_ON(nfolios <= data->max_folios);
 
 	folios = fuse_folios_alloc(nfolios, GFP_NOFS, &descs);
@@ -2091,10 +2096,10 @@ static bool fuse_pages_realloc(struct fuse_fill_wb_data *data)
 	return true;
 }
 
-static void fuse_writepages_send(struct fuse_fill_wb_data *data)
+static void fuse_writepages_send(struct inode *inode,
+				 struct fuse_fill_wb_data *data)
 {
 	struct fuse_writepage_args *wpa = data->wpa;
-	struct inode *inode = data->inode;
 	struct fuse_inode *fi = get_fuse_inode(inode);
 
 	spin_lock(&fi->lock);
@@ -2103,195 +2108,150 @@ static void fuse_writepages_send(struct fuse_fill_wb_data *data)
 	spin_unlock(&fi->lock);
 }
 
-static bool fuse_writepage_need_send(struct fuse_conn *fc, struct folio *folio,
-				     struct fuse_args_pages *ap,
+static bool fuse_writepage_need_send(struct fuse_conn *fc, loff_t pos,
+				     unsigned len, struct fuse_args_pages *ap,
 				     struct fuse_fill_wb_data *data)
 {
+	struct folio *prev_folio;
+	struct fuse_folio_desc prev_desc;
+	unsigned bytes = data->nr_bytes + len;
+	loff_t prev_pos;
+
 	WARN_ON(!ap->num_folios);
 
 	/* Reached max pages */
-	if (data->nr_pages + folio_nr_pages(folio) > fc->max_pages)
+	if ((bytes + PAGE_SIZE - 1) >> PAGE_SHIFT > fc->max_pages)
 		return true;
 
 	/* Reached max write bytes */
-	if ((data->nr_pages * PAGE_SIZE) + folio_size(folio) > fc->max_write)
+	if (bytes > fc->max_write)
 		return true;
 
 	/* Discontinuity */
-	if (folio_next_index(ap->folios[ap->num_folios - 1]) != folio->index)
+	prev_folio = ap->folios[ap->num_folios - 1];
+	prev_desc = ap->descs[ap->num_folios - 1];
+	prev_pos = folio_pos(prev_folio) + prev_desc.offset + prev_desc.length;
+	if (prev_pos != pos)
 		return true;
 
 	/* Need to grow the pages array?  If so, did the expansion fail? */
-	if (ap->num_folios == data->max_folios && !fuse_pages_realloc(data))
+	if (ap->num_folios == data->max_folios &&
+	    !fuse_pages_realloc(data, fc->max_pages))
 		return true;
 
 	return false;
 }
 
-static int fuse_writepages_fill(struct folio *folio,
-		struct writeback_control *wbc, void *_data)
+static ssize_t fuse_iomap_writeback_range(struct iomap_writepage_ctx *wpc,
+					  struct folio *folio, u64 pos,
+					  unsigned len, u64 end_pos)
 {
-	struct fuse_fill_wb_data *data = _data;
+	struct fuse_fill_wb_data *data = wpc->wb_ctx;
 	struct fuse_writepage_args *wpa = data->wpa;
 	struct fuse_args_pages *ap = &wpa->ia.ap;
-	struct inode *inode = data->inode;
+	struct inode *inode = wpc->inode;
 	struct fuse_inode *fi = get_fuse_inode(inode);
 	struct fuse_conn *fc = get_fuse_conn(inode);
-	int err;
+	loff_t offset = offset_in_folio(folio, pos);
+
+	WARN_ON_ONCE(!data);
+	/* len will always be page aligned */
+	WARN_ON_ONCE(len & (PAGE_SIZE - 1));
 
 	if (!data->ff) {
-		err = -EIO;
 		data->ff = fuse_write_file_get(fi);
 		if (!data->ff)
-			goto out_unlock;
+			return -EIO;
 	}
 
-	if (wpa && fuse_writepage_need_send(fc, folio, ap, data)) {
-		fuse_writepages_send(data);
+	if (wpa && fuse_writepage_need_send(fc, pos, len, ap, data)) {
+		fuse_writepages_send(inode, data);
 		data->wpa = NULL;
-		data->nr_pages = 0;
+		data->nr_bytes = 0;
 	}
 
 	if (data->wpa == NULL) {
-		err = -ENOMEM;
-		wpa = fuse_writepage_args_setup(folio, data->ff);
+		wpa = fuse_writepage_args_setup(folio, offset, data->ff);
 		if (!wpa)
-			goto out_unlock;
+			return -ENOMEM;
 		fuse_file_get(wpa->ia.ff);
 		data->max_folios = 1;
 		ap = &wpa->ia.ap;
 	}
-	folio_start_writeback(folio);
 
-	fuse_writepage_args_page_fill(wpa, folio, ap->num_folios);
-	data->nr_pages += folio_nr_pages(folio);
+	iomap_start_folio_write(inode, folio, 1);
+	fuse_writepage_args_page_fill(wpa, folio, ap->num_folios,
+				      offset, len);
+	data->nr_bytes += len;
 
-	err = 0;
 	ap->num_folios++;
 	if (!data->wpa)
 		data->wpa = wpa;
-out_unlock:
-	folio_unlock(folio);
 
-	return err;
+	return len;
 }
 
-static int fuse_writepages(struct address_space *mapping,
-			   struct writeback_control *wbc)
+static int fuse_iomap_writeback_submit(struct iomap_writepage_ctx *wpc,
+				       int error)
 {
-	struct inode *inode = mapping->host;
-	struct fuse_conn *fc = get_fuse_conn(inode);
-	struct fuse_fill_wb_data data;
-	int err;
+	struct fuse_fill_wb_data *data = wpc->wb_ctx;
 
-	err = -EIO;
-	if (fuse_is_bad(inode))
-		goto out;
-
-	if (wbc->sync_mode == WB_SYNC_NONE &&
-	    fc->num_background >= fc->congestion_threshold)
-		return 0;
+	WARN_ON_ONCE(!data);
 
-	data.inode = inode;
-	data.wpa = NULL;
-	data.ff = NULL;
-	data.nr_pages = 0;
-
-	err = write_cache_pages(mapping, wbc, fuse_writepages_fill, &data);
-	if (data.wpa) {
-		WARN_ON(!data.wpa->ia.ap.num_folios);
-		fuse_writepages_send(&data);
+	if (data->wpa) {
+		WARN_ON(!data->wpa->ia.ap.num_folios);
+		fuse_writepages_send(wpc->inode, data);
 	}
-	if (data.ff)
-		fuse_file_put(data.ff, false);
 
-out:
-	return err;
-}
-
-/*
- * It's worthy to make sure that space is reserved on disk for the write,
- * but how to implement it without killing performance need more thinking.
- */
-static int fuse_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
-{
-	pgoff_t index = pos >> PAGE_SHIFT;
-	struct fuse_conn *fc = get_fuse_conn(file_inode(file));
-	struct folio *folio;
-	loff_t fsize;
-	int err = -ENOMEM;
-
-	WARN_ON(!fc->writeback_cache);
-
-	folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN,
-			mapping_gfp_mask(mapping));
-	if (IS_ERR(folio))
-		goto error;
-
-	if (folio_test_uptodate(folio) || len >= folio_size(folio))
-		goto success;
-	/*
-	 * Check if the start of this folio comes after the end of file,
-	 * in which case the readpage can be optimized away.
-	 */
-	fsize = i_size_read(mapping->host);
-	if (fsize <= folio_pos(folio)) {
-		size_t off = offset_in_folio(folio, pos);
-		if (off)
-			folio_zero_segment(folio, 0, off);
-		goto success;
-	}
-	err = fuse_do_readfolio(file, folio);
-	if (err)
-		goto cleanup;
-success:
-	*foliop = folio;
-	return 0;
+	if (data->ff)
+		fuse_file_put(data->ff, false);
 
-cleanup:
-	folio_unlock(folio);
-	folio_put(folio);
-error:
-	return err;
+	return error;
 }
 
-static int fuse_write_end(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned copied,
-		struct folio *folio, void *fsdata)
-{
-	struct inode *inode = folio->mapping->host;
-
-	/* Haven't copied anything?  Skip zeroing, size extending, dirtying. */
-	if (!copied)
-		goto unlock;
-
-	pos += copied;
-	if (!folio_test_uptodate(folio)) {
-		/* Zero any unwritten bytes at the end of the page */
-		size_t endoff = pos & ~PAGE_MASK;
-		if (endoff)
-			folio_zero_segment(folio, endoff, PAGE_SIZE);
-		folio_mark_uptodate(folio);
-	}
+static const struct iomap_writeback_ops fuse_writeback_ops = {
+	.writeback_range	= fuse_iomap_writeback_range,
+	.writeback_submit	= fuse_iomap_writeback_submit,
+};
 
-	if (pos > inode->i_size)
-		i_size_write(inode, pos);
+static int fuse_writepages(struct address_space *mapping,
+			   struct writeback_control *wbc)
+{
+	struct inode *inode = mapping->host;
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	struct fuse_fill_wb_data data = {};
+	struct iomap_writepage_ctx wpc = {
+		.inode = inode,
+		.iomap.type = IOMAP_MAPPED,
+		.wbc = wbc,
+		.ops = &fuse_writeback_ops,
+		.wb_ctx	= &data,
+	};
 
-	folio_mark_dirty(folio);
+	if (fuse_is_bad(inode))
+		return -EIO;
 
-unlock:
-	folio_unlock(folio);
-	folio_put(folio);
+	if (wbc->sync_mode == WB_SYNC_NONE &&
+	    fc->num_background >= fc->congestion_threshold)
+		return 0;
 
-	return copied;
+	return iomap_writepages(&wpc);
 }
 
 static int fuse_launder_folio(struct folio *folio)
 {
 	int err = 0;
+	struct fuse_fill_wb_data data = {};
+	struct iomap_writepage_ctx wpc = {
+		.inode = folio->mapping->host,
+		.iomap.type = IOMAP_MAPPED,
+		.ops = &fuse_writeback_ops,
+		.wb_ctx	= &data,
+	};
+
 	if (folio_clear_dirty_for_io(folio)) {
-		err = fuse_writepage_locked(folio);
+		err = iomap_writeback_folio(&wpc, folio);
+		err = fuse_iomap_writeback_submit(&wpc, err);
 		if (!err)
 			folio_wait_writeback(folio);
 	}
@@ -3144,12 +3104,13 @@ static const struct address_space_operations fuse_file_aops  = {
 	.readahead	= fuse_readahead,
 	.writepages	= fuse_writepages,
 	.launder_folio	= fuse_launder_folio,
-	.dirty_folio	= filemap_dirty_folio,
+	.dirty_folio	= iomap_dirty_folio,
+	.release_folio	= iomap_release_folio,
+	.invalidate_folio = iomap_invalidate_folio,
+	.is_partially_uptodate = iomap_is_partially_uptodate,
 	.migrate_folio	= filemap_migrate_folio,
 	.bmap		= fuse_bmap,
 	.direct_IO	= fuse_direct_IO,
-	.write_begin	= fuse_write_begin,
-	.write_end	= fuse_write_end,
 };
 
 void fuse_init_file_inode(struct inode *inode, unsigned int flags)