Merge tag 'vfs-6.19-rc1.iomap' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull iomap updates from Christian Brauner:
 "FUSE iomap Support for Buffered Reads:

    This adds iomap support for FUSE buffered reads and readahead. This
    enables granular uptodate tracking with large folios so only
    non-uptodate portions need to be read. Also fixes a race condition
    with large folios + writeback cache that could cause data corruption
    on partial writes followed by reads.

     - Refactored iomap read/readahead bio logic into helpers
     - Added caller-provided callbacks for read operations
     - Moved buffered IO bio logic into new file
     - FUSE now uses iomap for read_folio and readahead

  Zero Range Folio Batch Support:

    Add folio batch support for iomap_zero_range() to handle dirty
    folios over unwritten mappings. Fix raciness issues where dirty data
    could be lost during zero range operations.

     - filemap_get_folios_tag_range() helper for dirty folio lookup
     - Optional zero range dirty folio processing
     - XFS fills dirty folios on zero range of unwritten mappings
     - Removed old partial EOF zeroing optimization

  DIO Write Completions from Interrupt Context:

    Restore pre-iomap behavior where pure overwrite completions run
    inline rather than being deferred to workqueue. Reduces context
    switches for high-performance workloads like ScyllaDB.

     - Removed unused IOCB_DIO_CALLER_COMP code
     - Error completions always run in user context (fixes zonefs)
     - Reworked REQ_FUA selection logic
     - Inverted IOMAP_DIO_INLINE_COMP to IOMAP_DIO_OFFLOAD_COMP

  Buffered IO Cleanups:

    Some performance and code clarity improvements:

     - Replace manual bitmap scanning with find_next_bit()
     - Simplify read skip logic for writes
     - Optimize pending async writeback accounting
     - Better variable naming
     - Documentation for iomap_finish_folio_write() requirements

  Misaligned Vectors for Zoned XFS:

    Enables sub-block aligned vectors in XFS always-COW mode for zoned
    devices via new IOMAP_DIO_FSBLOCK_ALIGNED flag.

  Bug Fixes:

     - Allocate s_dio_done_wq for async reads (fixes syzbot report after
       error completion changes)
     - Fix iomap_read_end() for already uptodate folios (regression fix)"

* tag 'vfs-6.19-rc1.iomap' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (40 commits)
  iomap: allocate s_dio_done_wq for async reads as well
  iomap: fix iomap_read_end() for already uptodate folios
  iomap: invert the polarity of IOMAP_DIO_INLINE_COMP
  iomap: support write completions from interrupt context
  iomap: rework REQ_FUA selection
  iomap: always run error completions in user context
  fs, iomap: remove IOCB_DIO_CALLER_COMP
  iomap: use find_next_bit() for uptodate bitmap scanning
  iomap: use find_next_bit() for dirty bitmap scanning
  iomap: simplify when reads can be skipped for writes
  iomap: simplify ->read_folio_range() error handling for reads
  iomap: optimize pending async writeback accounting
  docs: document iomap writeback's iomap_finish_folio_write() requirement
  iomap: account for unaligned end offsets when truncating read range
  iomap: rename bytes_pending/bytes_accounted to bytes_submitted/bytes_not_submitted
  xfs: support sub-block aligned vectors in always COW mode
  iomap: add IOMAP_DIO_FSBLOCK_ALIGNED flag
  xfs: error tag to force zeroing on debug kernels
  iomap: remove old partial eof zeroing optimization
  xfs: fill dirty folios on zero range of unwritten mappings
  ...

29 files changed, 1093 insertions, 633 deletions

diff --git a/Documentation/filesystems/iomap/operations.rst b/Documentation/filesystems/iomap/operations.rst
index 387fd9cc72ca..da982ca7e413 100644
--- a/Documentation/filesystems/iomap/operations.rst
+++ b/Documentation/filesystems/iomap/operations.rst
@@ -135,6 +135,27 @@ These ``struct kiocb`` flags are significant for buffered I/O with iomap:
 
  * ``IOCB_DONTCACHE``: Turns on ``IOMAP_DONTCACHE``.
 
+``struct iomap_read_ops``
+--------------------------
+
+.. code-block:: c
+
+ struct iomap_read_ops {
+     int (*read_folio_range)(const struct iomap_iter *iter,
+                             struct iomap_read_folio_ctx *ctx, size_t len);
+     void (*submit_read)(struct iomap_read_folio_ctx *ctx);
+ };
+
+iomap calls these functions:
+
+  - ``read_folio_range``: Called to read in the range. This must be provided
+    by the caller. If this succeeds, iomap_finish_folio_read() must be called
+    after the range is read in, regardless of whether the read succeeded or
+    failed.
+
+  - ``submit_read``: Submit any pending read requests. This function is
+    optional.
+
 Internal per-Folio State
 ------------------------
 
@@ -182,6 +203,28 @@ The ``flags`` argument to ``->iomap_begin`` will be set to zero.
 The pagecache takes whatever locks it needs before calling the
 filesystem.
 
+Both ``iomap_readahead`` and ``iomap_read_folio`` pass in a ``struct
+iomap_read_folio_ctx``:
+
+.. code-block:: c
+
+ struct iomap_read_folio_ctx {
+    const struct iomap_read_ops *ops;
+    struct folio *cur_folio;
+    struct readahead_control *rac;
+    void *read_ctx;
+ };
+
+``iomap_readahead`` must set:
+ * ``ops->read_folio_range()`` and ``rac``
+
+``iomap_read_folio`` must set:
+ * ``ops->read_folio_range()`` and ``cur_folio``
+
+``ops->submit_read()`` and ``read_ctx`` are optional. ``read_ctx`` is used to
+pass in any custom data the caller needs accessible in the ops callbacks for
+fulfilling reads.
+
 Buffered Writes
 ---------------
 
@@ -317,6 +360,9 @@ The fields are as follows:
     delalloc reservations to avoid having delalloc reservations for
     clean pagecache.
     This function must be supplied by the filesystem.
+    If this succeeds, iomap_finish_folio_write() must be called once writeback
+    completes for the range, regardless of whether the writeback succeeded or
+    failed.
 
   - ``writeback_submit``: Submit the previous built writeback context.
     Block based file systems should use the iomap_ioend_writeback_submit
@@ -444,10 +490,6 @@ These ``struct kiocb`` flags are significant for direct I/O with iomap:
    Only meaningful for asynchronous I/O, and only if the entire I/O can
    be issued as a single ``struct bio``.
 
- * ``IOCB_DIO_CALLER_COMP``: Try to run I/O completion from the caller's
-   process context.
-   See ``linux/fs.h`` for more details.
-
 Filesystems should call ``iomap_dio_rw`` from ``->read_iter`` and
 ``->write_iter``, and set ``FMODE_CAN_ODIRECT`` in the ``->open``
 function for the file.
diff --git a/block/fops.c b/block/fops.c
index 5e3db9fead77..4dad9c2d5796 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -540,12 +540,13 @@ const struct address_space_operations def_blk_aops = {
 #else /* CONFIG_BUFFER_HEAD */
 static int blkdev_read_folio(struct file *file, struct folio *folio)
 {
-	return iomap_read_folio(folio, &blkdev_iomap_ops);
+	iomap_bio_read_folio(folio, &blkdev_iomap_ops);
+	return 0;
 }
 
 static void blkdev_readahead(struct readahead_control *rac)
 {
-	iomap_readahead(rac, &blkdev_iomap_ops);
+	iomap_bio_readahead(rac, &blkdev_iomap_ops);
 }
 
 static ssize_t blkdev_writeback_range(struct iomap_writepage_ctx *wpc,
diff --git a/fs/backing-file.c b/fs/backing-file.c
index 15a7f8031084..2a86bb6fcd13 100644
--- a/fs/backing-file.c
+++ b/fs/backing-file.c
@@ -227,12 +227,6 @@ ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter,
 	    !(file->f_mode & FMODE_CAN_ODIRECT))
 		return -EINVAL;
 
-	/*
-	 * Stacked filesystems don't support deferred completions, don't copy
-	 * this property in case it is set by the issuer.
-	 */
-	flags &= ~IOCB_DIO_CALLER_COMP;
-
 	old_cred = override_creds(ctx->cred);
 	if (is_sync_kiocb(iocb)) {
 		rwf_t rwf = iocb_to_rw_flags(flags);
diff --git a/fs/dax.c b/fs/dax.c
index 516f995a988c..38fae11ee419 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1507,7 +1507,7 @@ static int dax_zero_iter(struct iomap_iter *iter, bool *did_zero)
 
 	/* already zeroed?  we're done. */
 	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
-		return iomap_iter_advance(iter, &length);
+		return iomap_iter_advance(iter, length);
 
 	/*
 	 * invalidate the pages whose sharing state is to be changed
@@ -1536,10 +1536,10 @@ static int dax_zero_iter(struct iomap_iter *iter, bool *did_zero)
 		if (ret < 0)
 			return ret;
 
-		ret = iomap_iter_advance(iter, &length);
+		ret = iomap_iter_advance(iter, length);
 		if (ret)
 			return ret;
-	} while (length > 0);
+	} while ((length = iomap_length(iter)) > 0);
 
 	if (did_zero)
 		*did_zero = true;
@@ -1597,7 +1597,7 @@ static int dax_iomap_iter(struct iomap_iter *iomi, struct iov_iter *iter)
 
 		if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN) {
 			done = iov_iter_zero(min(length, end - pos), iter);
-			return iomap_iter_advance(iomi, &done);
+			return iomap_iter_advance(iomi, done);
 		}
 	}
 
@@ -1681,12 +1681,12 @@ static int dax_iomap_iter(struct iomap_iter *iomi, struct iov_iter *iter)
 			xfer = dax_copy_to_iter(dax_dev, pgoff, kaddr,
 					map_len, iter);
 
-		length = xfer;
-		ret = iomap_iter_advance(iomi, &length);
+		ret = iomap_iter_advance(iomi, xfer);
 		if (!ret && xfer == 0)
 			ret = -EFAULT;
 		if (xfer < map_len)
 			break;
+		length = iomap_length(iomi);
 	}
 	dax_read_unlock(id);
 
@@ -1919,10 +1919,8 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, unsigned long *pfnp,
 			ret |= VM_FAULT_MAJOR;
 		}
 
-		if (!(ret & VM_FAULT_ERROR)) {
-			u64 length = PAGE_SIZE;
-			iter.status = iomap_iter_advance(&iter, &length);
-		}
+		if (!(ret & VM_FAULT_ERROR))
+			iter.status = iomap_iter_advance(&iter, PAGE_SIZE);
 	}
 
 	if (iomap_errp)
@@ -2034,10 +2032,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, unsigned long *pfnp,
 			continue; /* actually breaks out of the loop */
 
 		ret = dax_fault_iter(vmf, &iter, pfnp, &xas, &entry, true);
-		if (ret != VM_FAULT_FALLBACK) {
-			u64 length = PMD_SIZE;
-			iter.status = iomap_iter_advance(&iter, &length);
-		}
+		if (ret != VM_FAULT_FALLBACK)
+			iter.status = iomap_iter_advance(&iter, PMD_SIZE);
 	}
 
 unlock_entry:
@@ -2163,7 +2159,6 @@ static int dax_range_compare_iter(struct iomap_iter *it_src,
 	const struct iomap *smap = &it_src->iomap;
 	const struct iomap *dmap = &it_dest->iomap;
 	loff_t pos1 = it_src->pos, pos2 = it_dest->pos;
-	u64 dest_len;
 	void *saddr, *daddr;
 	int id, ret;
 
@@ -2196,10 +2191,9 @@ static int dax_range_compare_iter(struct iomap_iter *it_src,
 	dax_read_unlock(id);
 
 advance:
-	dest_len = len;
-	ret = iomap_iter_advance(it_src, &len);
+	ret = iomap_iter_advance(it_src, len);
 	if (!ret)
-		ret = iomap_iter_advance(it_dest, &dest_len);
+		ret = iomap_iter_advance(it_dest, len);
 	return ret;
 
 out_unlock:
diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 8ca29962a3dd..bb13c4cb8455 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -371,7 +371,8 @@ static int erofs_read_folio(struct file *file, struct folio *folio)
 {
 	trace_erofs_read_folio(folio, true);
 
-	return iomap_read_folio(folio, &erofs_iomap_ops);
+	iomap_bio_read_folio(folio, &erofs_iomap_ops);
+	return 0;
 }
 
 static void erofs_readahead(struct readahead_control *rac)
@@ -379,7 +380,7 @@ static void erofs_readahead(struct readahead_control *rac)
 	trace_erofs_readahead(rac->mapping->host, readahead_index(rac),
 					readahead_count(rac), true);
 
-	return iomap_readahead(rac, &erofs_iomap_ops);
+	iomap_bio_readahead(rac, &erofs_iomap_ops);
 }
 
 static sector_t erofs_bmap(struct address_space *mapping, sector_t block)
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index ecaec0fea3a1..316922d5dd13 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1192,7 +1192,7 @@ static void fuse_fillattr(struct mnt_idmap *idmap, struct inode *inode,
 	if (attr->blksize != 0)
 		blkbits = ilog2(attr->blksize);
 	else
-		blkbits = fc->blkbits;
+		blkbits = inode->i_sb->s_blocksize_bits;
 
 	stat->blksize = 1 << blkbits;
 }
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index f1ef77a0be05..7bcb650a9f26 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -834,23 +834,142 @@ static int fuse_do_readfolio(struct file *file, struct folio *folio,
 	return 0;
 }
 
+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,
+};
+
+struct fuse_fill_read_data {
+	struct file *file;
+
+	/* Fields below are used if sending the read request asynchronously */
+	struct fuse_conn *fc;
+	struct fuse_io_args *ia;
+	unsigned int nr_bytes;
+};
+
+/* forward declarations */
+static bool fuse_folios_need_send(struct fuse_conn *fc, loff_t pos,
+				  unsigned len, struct fuse_args_pages *ap,
+				  unsigned cur_bytes, bool write);
+static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file,
+				unsigned int count, bool async);
+
+static int fuse_handle_readahead(struct folio *folio,
+				 struct readahead_control *rac,
+				 struct fuse_fill_read_data *data, loff_t pos,
+				 size_t len)
+{
+	struct fuse_io_args *ia = data->ia;
+	size_t off = offset_in_folio(folio, pos);
+	struct fuse_conn *fc = data->fc;
+	struct fuse_args_pages *ap;
+	unsigned int nr_pages;
+
+	if (ia && fuse_folios_need_send(fc, pos, len, &ia->ap, data->nr_bytes,
+					false)) {
+		fuse_send_readpages(ia, data->file, data->nr_bytes,
+				    fc->async_read);
+		data->nr_bytes = 0;
+		data->ia = NULL;
+		ia = NULL;
+	}
+	if (!ia) {
+		if (fc->num_background >= fc->congestion_threshold &&
+		    rac->ra->async_size >= readahead_count(rac))
+			/*
+			 * Congested and only async pages left, so skip the
+			 * rest.
+			 */
+			return -EAGAIN;
+
+		nr_pages = min(fc->max_pages, readahead_count(rac));
+		data->ia = fuse_io_alloc(NULL, nr_pages);
+		if (!data->ia)
+			return -ENOMEM;
+		ia = data->ia;
+	}
+	folio_get(folio);
+	ap = &ia->ap;
+	ap->folios[ap->num_folios] = folio;
+	ap->descs[ap->num_folios].offset = off;
+	ap->descs[ap->num_folios].length = len;
+	data->nr_bytes += len;
+	ap->num_folios++;
+
+	return 0;
+}
+
+static int fuse_iomap_read_folio_range_async(const struct iomap_iter *iter,
+					     struct iomap_read_folio_ctx *ctx,
+					     size_t len)
+{
+	struct fuse_fill_read_data *data = ctx->read_ctx;
+	struct folio *folio = ctx->cur_folio;
+	loff_t pos =  iter->pos;
+	size_t off = offset_in_folio(folio, pos);
+	struct file *file = data->file;
+	int ret;
+
+	if (ctx->rac) {
+		ret = fuse_handle_readahead(folio, ctx->rac, data, pos, len);
+	} else {
+		/*
+		 *  for non-readahead read requests, do reads synchronously
+		 *  since it's not guaranteed that the server can handle
+		 *  out-of-order reads
+		 */
+		ret = fuse_do_readfolio(file, folio, off, len);
+		if (!ret)
+			iomap_finish_folio_read(folio, off, len, ret);
+	}
+	return ret;
+}
+
+static void fuse_iomap_read_submit(struct iomap_read_folio_ctx *ctx)
+{
+	struct fuse_fill_read_data *data = ctx->read_ctx;
+
+	if (data->ia)
+		fuse_send_readpages(data->ia, data->file, data->nr_bytes,
+				    data->fc->async_read);
+}
+
+static const struct iomap_read_ops fuse_iomap_read_ops = {
+	.read_folio_range = fuse_iomap_read_folio_range_async,
+	.submit_read = fuse_iomap_read_submit,
+};
+
 static int fuse_read_folio(struct file *file, struct folio *folio)
 {
 	struct inode *inode = folio->mapping->host;
-	int err;
+	struct fuse_fill_read_data data = {
+		.file = file,
+	};
+	struct iomap_read_folio_ctx ctx = {
+		.cur_folio = folio,
+		.ops = &fuse_iomap_read_ops,
+		.read_ctx = &data,
 
-	err = -EIO;
-	if (fuse_is_bad(inode))
-		goto out;
+	};
 
-	err = fuse_do_readfolio(file, folio, 0, folio_size(folio));
-	if (!err)
-		folio_mark_uptodate(folio);
+	if (fuse_is_bad(inode)) {
+		folio_unlock(folio);
+		return -EIO;
+	}
 
+	iomap_read_folio(&fuse_iomap_ops, &ctx);
 	fuse_invalidate_atime(inode);
- out:
-	folio_unlock(folio);
-	return err;
+	return 0;
 }
 
 static int fuse_iomap_read_folio_range(const struct iomap_iter *iter,
@@ -887,7 +1006,8 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
 	fuse_invalidate_atime(inode);
 
 	for (i = 0; i < ap->num_folios; i++) {
-		folio_end_read(ap->folios[i], !err);
+		iomap_finish_folio_read(ap->folios[i], ap->descs[i].offset,
+					ap->descs[i].length, err);
 		folio_put(ap->folios[i]);
 	}
 	if (ia->ff)
@@ -897,7 +1017,7 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
 }
 
 static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file,
-				unsigned int count)
+				unsigned int count, bool async)
 {
 	struct fuse_file *ff = file->private_data;
 	struct fuse_mount *fm = ff->fm;
@@ -919,7 +1039,7 @@ static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file,
 
 	fuse_read_args_fill(ia, file, pos, count, FUSE_READ);
 	ia->read.attr_ver = fuse_get_attr_version(fm->fc);
-	if (fm->fc->async_read) {
+	if (async) {
 		ia->ff = fuse_file_get(ff);
 		ap->args.end = fuse_readpages_end;
 		err = fuse_simple_background(fm, &ap->args, GFP_KERNEL);
@@ -936,81 +1056,20 @@ static void fuse_readahead(struct readahead_control *rac)
 {
 	struct inode *inode = rac->mapping->host;
 	struct fuse_conn *fc = get_fuse_conn(inode);
-	unsigned int max_pages, nr_pages;
-	struct folio *folio = NULL;
+	struct fuse_fill_read_data data = {
+		.file = rac->file,
+		.fc = fc,
+	};
+	struct iomap_read_folio_ctx ctx = {
+		.ops = &fuse_iomap_read_ops,
+		.rac = rac,
+		.read_ctx = &data
+	};
 
 	if (fuse_is_bad(inode))
 		return;
 
-	max_pages = min_t(unsigned int, fc->max_pages,
-			fc->max_read / PAGE_SIZE);
-
-	/*
-	 * This is only accurate the first time through, since readahead_folio()
-	 * doesn't update readahead_count() from the previous folio until the
-	 * next call.  Grab nr_pages here so we know how many pages we're going
-	 * to have to process.  This means that we will exit here with
-	 * readahead_count() == folio_nr_pages(last_folio), but we will have
-	 * consumed all of the folios, and read_pages() will call
-	 * readahead_folio() again which will clean up the rac.
-	 */
-	nr_pages = readahead_count(rac);
-
-	while (nr_pages) {
-		struct fuse_io_args *ia;
-		struct fuse_args_pages *ap;
-		unsigned cur_pages = min(max_pages, nr_pages);
-		unsigned int pages = 0;
-
-		if (fc->num_background >= fc->congestion_threshold &&
-		    rac->ra->async_size >= readahead_count(rac))
-			/*
-			 * Congested and only async pages left, so skip the
-			 * rest.
-			 */
-			break;
-
-		ia = fuse_io_alloc(NULL, cur_pages);
-		if (!ia)
-			break;
-		ap = &ia->ap;
-
-		while (pages < cur_pages) {
-			unsigned int folio_pages;
-
-			/*
-			 * This returns a folio with a ref held on it.
-			 * The ref needs to be held until the request is
-			 * completed, since the splice case (see
-			 * fuse_try_move_page()) drops the ref after it's
-			 * replaced in the page cache.
-			 */
-			if (!folio)
-				folio =  __readahead_folio(rac);
-
-			folio_pages = folio_nr_pages(folio);
-			if (folio_pages > cur_pages - pages) {
-				/*
-				 * Large folios belonging to fuse will never
-				 * have more pages than max_pages.
-				 */
-				WARN_ON(!pages);
-				break;
-			}
-
-			ap->folios[ap->num_folios] = folio;
-			ap->descs[ap->num_folios].length = folio_size(folio);
-			ap->num_folios++;
-			pages += folio_pages;
-			folio = NULL;
-		}
-		fuse_send_readpages(ia, rac->file, pages << PAGE_SHIFT);
-		nr_pages -= pages;
-	}
-	if (folio) {
-		folio_end_read(folio, false);
-		folio_put(folio);
-	}
+	iomap_readahead(&fuse_iomap_ops, &ctx);
 }
 
 static ssize_t fuse_cache_read_iter(struct kiocb *iocb, struct iov_iter *to)
@@ -1397,20 +1456,6 @@ 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;
@@ -1834,7 +1879,8 @@ static void fuse_writepage_finish(struct fuse_writepage_args *wpa)
 		 * scope of the fi->lock alleviates xarray lock
 		 * contention and noticeably improves performance.
 		 */
-		iomap_finish_folio_write(inode, ap->folios[i], 1);
+		iomap_finish_folio_write(inode, ap->folios[i],
+					 ap->descs[i].length);
 
 	wake_up(&fi->page_waitq);
 }
@@ -2047,7 +2093,7 @@ struct fuse_fill_wb_data {
 	struct fuse_file *ff;
 	unsigned int max_folios;
 	/*
-	 * nr_bytes won't overflow since fuse_writepage_need_send() caps
+	 * nr_bytes won't overflow since fuse_folios_need_send() caps
 	 * wb requests to never exceed fc->max_pages (which has an upper bound
 	 * of U16_MAX).
 	 */
@@ -2092,14 +2138,15 @@ static void fuse_writepages_send(struct inode *inode,
 	spin_unlock(&fi->lock);
 }
 
-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)
+static bool fuse_folios_need_send(struct fuse_conn *fc, loff_t pos,
+				  unsigned len, struct fuse_args_pages *ap,
+				  unsigned cur_bytes, bool write)
 {
 	struct folio *prev_folio;
 	struct fuse_folio_desc prev_desc;
-	unsigned bytes = data->nr_bytes + len;
+	unsigned bytes = cur_bytes + len;
 	loff_t prev_pos;
+	size_t max_bytes = write ? fc->max_write : fc->max_read;
 
 	WARN_ON(!ap->num_folios);
 
@@ -2107,8 +2154,7 @@ static bool fuse_writepage_need_send(struct fuse_conn *fc, loff_t pos,
 	if ((bytes + PAGE_SIZE - 1) >> PAGE_SHIFT > fc->max_pages)
 		return true;
 
-	/* Reached max write bytes */
-	if (bytes > fc->max_write)
+	if (bytes > max_bytes)
 		return true;
 
 	/* Discontinuity */
@@ -2118,11 +2164,6 @@ static bool fuse_writepage_need_send(struct fuse_conn *fc, loff_t pos,
 	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, fc->max_pages))
-		return true;
-
 	return false;
 }
 
@@ -2146,10 +2187,24 @@ static ssize_t fuse_iomap_writeback_range(struct iomap_writepage_ctx *wpc,
 			return -EIO;
 	}
 
-	if (wpa && fuse_writepage_need_send(fc, pos, len, ap, data)) {
-		fuse_writepages_send(inode, data);
-		data->wpa = NULL;
-		data->nr_bytes = 0;
+	if (wpa) {
+		bool send = fuse_folios_need_send(fc, pos, len, ap,
+						  data->nr_bytes, true);
+
+		if (!send) {
+			/*
+			 * Need to grow the pages array?  If so, did the
+			 * expansion fail?
+			 */
+			send = (ap->num_folios == data->max_folios) &&
+				!fuse_pages_realloc(data, fc->max_pages);
+		}
+
+		if (send) {
+			fuse_writepages_send(inode, data);
+			data->wpa = NULL;
+			data->nr_bytes = 0;
+		}
 	}
 
 	if (data->wpa == NULL) {
@@ -2161,7 +2216,6 @@ static ssize_t fuse_iomap_writeback_range(struct iomap_writepage_ctx *wpc,
 		ap = &wpa->ia.ap;
 	}
 
-	iomap_start_folio_write(inode, folio, 1);
 	fuse_writepage_args_page_fill(wpa, folio, ap->num_folios,
 				      offset, len);
 	data->nr_bytes += len;
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index c2f2a48156d6..f616c1991fed 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -981,14 +981,6 @@ struct fuse_conn {
 		/* Request timeout (in jiffies). 0 = no timeout */
 		unsigned int req_timeout;
 	} timeout;
-
-	/*
-	 * This is a workaround until fuse uses iomap for reads.
-	 * For fuseblk servers, this represents the blocksize passed in at
-	 * mount time and for regular fuse servers, this is equivalent to
-	 * inode->i_blkbits.
-	 */
-	u8 blkbits;
 };
 
 /*
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index d1babf56f254..8ba29ca23244 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -291,7 +291,7 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
 	if (attr->blksize)
 		fi->cached_i_blkbits = ilog2(attr->blksize);
 	else
-		fi->cached_i_blkbits = fc->blkbits;
+		fi->cached_i_blkbits = inode->i_sb->s_blocksize_bits;
 
 	/*
 	 * Don't set the sticky bit in i_mode, unless we want the VFS
@@ -1838,22 +1838,11 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
 		err = -EINVAL;
 		if (!sb_set_blocksize(sb, ctx->blksize))
 			goto err;
-		/*
-		 * This is a workaround until fuse hooks into iomap for reads.
-		 * Use PAGE_SIZE for the blocksize else if the writeback cache
-		 * is enabled, buffered writes go through iomap and a read may
-		 * overwrite partially written data if blocksize < PAGE_SIZE
-		 */
-		fc->blkbits = sb->s_blocksize_bits;
-		if (ctx->blksize != PAGE_SIZE &&
-		    !sb_set_blocksize(sb, PAGE_SIZE))
-			goto err;
 #endif
 		fc->sync_fs = 1;
 	} else {
 		sb->s_blocksize = PAGE_SIZE;
 		sb->s_blocksize_bits = PAGE_SHIFT;
-		fc->blkbits = sb->s_blocksize_bits;
 	}
 
 	sb->s_subtype = ctx->subtype;
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 47d74afd63ac..38d4f343187a 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -424,11 +424,11 @@ static int gfs2_read_folio(struct file *file, struct folio *folio)
 	struct inode *inode = folio->mapping->host;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	int error;
+	int error = 0;
 
 	if (!gfs2_is_jdata(ip) ||
 	    (i_blocksize(inode) == PAGE_SIZE && !folio_buffers(folio))) {
-		error = iomap_read_folio(folio, &gfs2_iomap_ops);
+		iomap_bio_read_folio(folio, &gfs2_iomap_ops);
 	} else if (gfs2_is_stuffed(ip)) {
 		error = stuffed_read_folio(ip, folio);
 	} else {
@@ -503,7 +503,7 @@ static void gfs2_readahead(struct readahead_control *rac)
 	else if (gfs2_is_jdata(ip))
 		mpage_readahead(rac, gfs2_block_map);
 	else
-		iomap_readahead(rac, &gfs2_iomap_ops);
+		iomap_bio_readahead(rac, &gfs2_iomap_ops);
 }
 
 /**
diff --git a/fs/iomap/Makefile b/fs/iomap/Makefile
index f7e1c8534c46..a572b8808524 100644
--- a/fs/iomap/Makefile
+++ b/fs/iomap/Makefile
@@ -14,5 +14,6 @@ iomap-y				+= trace.o \
 iomap-$(CONFIG_BLOCK)		+= direct-io.o \
 				   ioend.o \
 				   fiemap.o \
-				   seek.o
+				   seek.o \
+				   bio.o
 iomap-$(CONFIG_SWAP)		+= swapfile.o
diff --git a/fs/iomap/bio.c b/fs/iomap/bio.c
new file mode 100644
index 000000000000..fc045f2e4c45
--- /dev/null
+++ b/fs/iomap/bio.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2010 Red Hat, Inc.
+ * Copyright (C) 2016-2023 Christoph Hellwig.
+ */
+#include <linux/iomap.h>
+#include <linux/pagemap.h>
+#include "internal.h"
+#include "trace.h"
+
+static void iomap_read_end_io(struct bio *bio)
+{
+	int error = blk_status_to_errno(bio->bi_status);
+	struct folio_iter fi;
+
+	bio_for_each_folio_all(fi, bio)
+		iomap_finish_folio_read(fi.folio, fi.offset, fi.length, error);
+	bio_put(bio);
+}
+
+static void iomap_bio_submit_read(struct iomap_read_folio_ctx *ctx)
+{
+	struct bio *bio = ctx->read_ctx;
+
+	if (bio)
+		submit_bio(bio);
+}
+
+static int iomap_bio_read_folio_range(const struct iomap_iter *iter,
+		struct iomap_read_folio_ctx *ctx, size_t plen)
+{
+	struct folio *folio = ctx->cur_folio;
+	const struct iomap *iomap = &iter->iomap;
+	loff_t pos = iter->pos;
+	size_t poff = offset_in_folio(folio, pos);
+	loff_t length = iomap_length(iter);