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
  ...

Author: torvalds

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.

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,

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);

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:

fs/erofs/data.c

@@ -371,15 +371,16 @@ 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)
 {
 	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)

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;
 }