[RFC PATCH v3 04/18] iomap: Add async buffered write support

[Stefan Roesch <shr@fb.com>]

This adds async buffered write support to iomap. The support is focused
on the changes necessary to support XFS with iomap.

Support for other filesystems might require additional changes.

Signed-off-by: Stefan Roesch <shr@fb.com>
---
 fs/iomap/buffered-io.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 6b06fd358958..b029e2b10e07 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -580,12 +580,18 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
 	size_t from = offset_in_folio(folio, pos), to = from + len;
 	size_t poff, plen;
 	gfp_t  gfp = GFP_NOFS | __GFP_NOFAIL;
+	bool no_wait = (iter->flags & IOMAP_NOWAIT);
+
+	if (no_wait)
+		gfp = GFP_NOWAIT;
 
 	if (folio_test_uptodate(folio))
 		return 0;
 	folio_clear_error(folio);
 
 	iop = iomap_page_create_gfp(iter->inode, folio, nr_blocks, gfp);
+	if (no_wait && !iop)
+		return -EAGAIN;
 
 	do {
 		iomap_adjust_read_range(iter->inode, folio, &block_start,
@@ -602,6 +608,8 @@ static int __iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
 			if (WARN_ON_ONCE(iter->flags & IOMAP_UNSHARE))
 				return -EIO;
 			folio_zero_segments(folio, poff, from, to, poff + plen);
+		} else if (no_wait) {
+			return -EAGAIN;
 		} else {
 			int status = iomap_read_folio_sync(block_start, folio,
 					poff, plen, srcmap);
@@ -632,6 +640,9 @@ static int iomap_write_begin(const struct iomap_iter *iter, loff_t pos,
 	unsigned fgp = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE | FGP_NOFS;
 	int status = 0;
 
+	if (iter->flags & IOMAP_NOWAIT)
+		fgp |= FGP_NOWAIT;
+
 	BUG_ON(pos + len > iter->iomap.offset + iter->iomap.length);
 	if (srcmap != &iter->iomap)
 		BUG_ON(pos + len > srcmap->offset + srcmap->length);
@@ -789,6 +800,10 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 		 * Otherwise there's a nasty deadlock on copying from the
 		 * same page as we're writing to, without it being marked
 		 * up-to-date.
+		 *
+		 * For async buffered writes the assumption is that the user
+		 * page has already been faulted in. This can be optimized by
+		 * faulting the user page in the prepare phase of io-uring.
 		 */
 		if (unlikely(fault_in_iov_iter_readable(i, bytes) == bytes)) {
 			status = -EFAULT;
@@ -844,6 +859,9 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i,
 	};
 	int ret;
 
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		iter.flags |= IOMAP_NOWAIT;
+
 	while ((ret = iomap_iter(&iter, ops)) > 0)
 		iter.processed = iomap_write_iter(&iter, i);
 	if (iter.pos == iocb->ki_pos)
-- 
2.30.2