iomap: Add done_before argument to iomap_dio_rw

Add a done_before argument to iomap_dio_rw that indicates how much of
the request has already been transferred.  When the request succeeds, we
report that done_before additional bytes were tranferred.  This is
useful for finishing a request asynchronously when part of the request
has already been completed synchronously.

We'll use that to allow iomap_dio_rw to be used with page faults
disabled: when a page fault occurs while submitting a request, we
synchronously complete the part of the request that has already been
submitted.  The caller can then take care of the page fault and call
iomap_dio_rw again for the rest of the request, passing in the number of
bytes already tranferred.

Signed-off-by: Andreas Gruenbacher <[email protected]>
Reviewed-by: Darrick J. Wong <[email protected]>

Author: Andreas Gruenbacher

fs/btrfs/file.c

@@ -1957,7 +1957,7 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	}
 
 	dio = __iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
-			     0);
+			     0, 0);
 
 	btrfs_inode_unlock(inode, ilock_flags);
 
@@ -3658,7 +3658,8 @@ static ssize_t btrfs_direct_read(struct kiocb *iocb, struct iov_iter *to)
 		return 0;
 
 	btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED);
-	ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dio_ops, 0);
+	ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
+			   0, 0);
 	btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
 	return ret;
 }

fs/erofs/data.c

@@ -287,7 +287,7 @@ static ssize_t erofs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 		if (!err)
 			return iomap_dio_rw(iocb, to, &erofs_iomap_ops,
-					    NULL, 0);
+					    NULL, 0, 0);
 		if (err < 0)
 			return err;
 	}

fs/ext4/file.c

@@ -74,7 +74,7 @@ static ssize_t ext4_dio_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		return generic_file_read_iter(iocb, to);
 	}
 
-	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0);
+	ret = iomap_dio_rw(iocb, to, &ext4_iomap_ops, NULL, 0, 0);
 	inode_unlock_shared(inode);
 
 	file_accessed(iocb->ki_filp);
@@ -566,7 +566,8 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ilock_shared)
 		iomap_ops = &ext4_iomap_overwrite_ops;
 	ret = iomap_dio_rw(iocb, from, iomap_ops, &ext4_dio_write_ops,
-			   (unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0);
+			   (unaligned_io || extend) ? IOMAP_DIO_FORCE_WAIT : 0,
+			   0);
 	if (ret == -ENOTBLK)
 		ret = 0;
 

fs/gfs2/file.c

@@ -822,7 +822,7 @@ static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to,
 	if (ret)
 		goto out_uninit;
 
-	ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL, 0);
+	ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL, 0, 0);
 	gfs2_glock_dq(gh);
 out_uninit:
 	gfs2_holder_uninit(gh);
@@ -856,7 +856,7 @@ static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from,
 	if (offset + len > i_size_read(&ip->i_inode))
 		goto out;
 
-	ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL, 0);
+	ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL, 0, 0);
 	if (ret == -ENOTBLK)
 		ret = 0;
 out:

fs/iomap/direct-io.c

@@ -31,6 +31,7 @@ struct iomap_dio {
 	atomic_t		ref;
 	unsigned		flags;
 	int			error;
+	size_t			done_before;
 	bool			wait_for_completion;
 
 	union {
@@ -124,6 +125,9 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	if (ret > 0 && (dio->flags & IOMAP_DIO_NEED_SYNC))
 		ret = generic_write_sync(iocb, ret);
 
+	if (ret > 0)
+		ret += dio->done_before;
+
 	kfree(dio);
 
 	return ret;
@@ -450,13 +454,21 @@ static loff_t iomap_dio_iter(const struct iomap_iter *iter,
  * may be pure data writes. In that case, we still need to do a full data sync
  * completion.
  *
+ * When page faults are disabled and @dio_flags includes IOMAP_DIO_PARTIAL,
+ * __iomap_dio_rw can return a partial result if it encounters a non-resident
+ * page in @iter after preparing a transfer.  In that case, the non-resident
+ * pages can be faulted in and the request resumed with @done_before set to the
+ * number of bytes previously transferred.  The request will then complete with
+ * the correct total number of bytes transferred; this is essential for
+ * completing partial requests asynchronously.
+ *
  * Returns -ENOTBLK In case of a page invalidation invalidation failure for
  * writes.  The callers needs to fall back to buffered I/O in this case.
  */
 struct iomap_dio *
 __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags)
+		unsigned int dio_flags, size_t done_before)
 {
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = file_inode(iocb->ki_filp);
@@ -486,6 +498,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->dops = dops;
 	dio->error = 0;
 	dio->flags = 0;
+	dio->done_before = done_before;
 
 	dio->submit.iter = iter;
 	dio->submit.waiter = current;
@@ -652,11 +665,11 @@ EXPORT_SYMBOL_GPL(__iomap_dio_rw);
 ssize_t
 iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags)
+		unsigned int dio_flags, size_t done_before)
 {
 	struct iomap_dio *dio;
 
-	dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags);
+	dio = __iomap_dio_rw(iocb, iter, ops, dops, dio_flags, done_before);
 	if (IS_ERR_OR_NULL(dio))
 		return PTR_ERR_OR_ZERO(dio);
 	return iomap_dio_complete(dio);

fs/xfs/xfs_file.c

@@ -259,7 +259,7 @@ xfs_file_dio_read(
 	ret = xfs_ilock_iocb(iocb, XFS_IOLOCK_SHARED);
 	if (ret)
 		return ret;
-	ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0);
+	ret = iomap_dio_rw(iocb, to, &xfs_read_iomap_ops, NULL, 0, 0);
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
 	return ret;
@@ -569,7 +569,7 @@ xfs_file_dio_write_aligned(
 	}
 	trace_xfs_file_direct_write(iocb, from);
 	ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops,
-			   &xfs_dio_write_ops, 0);
+			   &xfs_dio_write_ops, 0, 0);
 out_unlock:
 	if (iolock)
 		xfs_iunlock(ip, iolock);
@@ -647,7 +647,7 @@ xfs_file_dio_write_unaligned(
 
 	trace_xfs_file_direct_write(iocb, from);
 	ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops,
-			   &xfs_dio_write_ops, flags);
+			   &xfs_dio_write_ops, flags, 0);
 
 	/*
 	 * Retry unaligned I/O with exclusive blocking semantics if the DIO

fs/zonefs/super.c

@@ -852,7 +852,7 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from)
 		ret = zonefs_file_dio_append(iocb, from);
 	else
 		ret = iomap_dio_rw(iocb, from, &zonefs_iomap_ops,
-				   &zonefs_write_dio_ops, 0);
+				   &zonefs_write_dio_ops, 0, 0);
 	if (zi->i_ztype == ZONEFS_ZTYPE_SEQ &&
 	    (ret > 0 || ret == -EIOCBQUEUED)) {
 		if (ret > 0)
@@ -987,7 +987,7 @@ static ssize_t zonefs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 		}
 		file_accessed(iocb->ki_filp);
 		ret = iomap_dio_rw(iocb, to, &zonefs_iomap_ops,
-				   &zonefs_read_dio_ops, 0);
+				   &zonefs_read_dio_ops, 0, 0);
 	} else {
 		ret = generic_file_read_iter(iocb, to);
 		if (ret == -EIO)

include/linux/iomap.h

@@ -339,10 +339,10 @@ struct iomap_dio_ops {
 
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags);
+		unsigned int dio_flags, size_t done_before);
 struct iomap_dio *__iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
-		unsigned int dio_flags);
+		unsigned int dio_flags, size_t done_before);
 ssize_t iomap_dio_complete(struct iomap_dio *dio);
 int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);