netfs: Simplify the writeback code

Use the new folio_queue structures to simplify the writeback code.  The
problem with referring to the i_pages xarray directly is that we may have
gaps in the sequence of folios we're writing from that we need to skip when
we're removing the writeback mark from the folios we're writing back from.

At the moment the code tries to deal with this by carefully tracking the
gaps in each writeback stream (eg. write to server and write to cache) and
divining when there's a gap that spans folios (something that's not helped
by folios not being a consistent size).

Instead, the folio_queue buffer contains pointers only the folios we're
dealing with, has them in ascending order and indicates a gap by placing
non-consequitive folios next to each other.  This makes it possible to
track where we need to clean up to by just keeping track of where we've
processed to on each stream and taking the minimum.

Note that the I/O iterator is always rounded up to the end of the folio,
even if that is beyond the EOF position, so that the cache can do DIO from
the page.  The excess space is cleared, though mmapped writes clobber it.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Link: https://lore.kernel.org/r/20240814203850.2240469-18-dhowells@redhat.com/ # v2
Signed-off-by: Christian Brauner <brauner@kernel.org>

1 files changed, 19 insertions, 17 deletions

diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index 9ead075962f0..25fb7e166cc0 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -107,7 +107,6 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping,
 	if (is_buffered && netfs_is_cache_enabled(ictx))
 		fscache_begin_write_operation(&wreq->cache_resources, netfs_i_cookie(ictx));
 
-	wreq->contiguity = wreq->start;
 	wreq->cleaned_to = wreq->start;
 
 	wreq->io_streams[0].stream_nr		= 0;
@@ -158,6 +157,7 @@ static void netfs_prepare_write(struct netfs_io_request *wreq,
 	subreq->source		= stream->source;
 	subreq->start		= start;
 	subreq->stream_nr	= stream->stream_nr;
+	subreq->io_iter		= wreq->io_iter;
 
 	_enter("R=%x[%x]", wreq->debug_id, subreq->debug_index);
 
@@ -213,22 +213,15 @@ static void netfs_prepare_write(struct netfs_io_request *wreq,
  * netfs_write_subrequest_terminated() when complete.
  */
 static void netfs_do_issue_write(struct netfs_io_stream *stream,
-				 struct netfs_io_subrequest *subreq,
-				 struct iov_iter *source)
+				 struct netfs_io_subrequest *subreq)
 {
 	struct netfs_io_request *wreq = subreq->rreq;
-	size_t size = subreq->len - subreq->transferred;
 
 	_enter("R=%x[%x],%zx", wreq->debug_id, subreq->debug_index, subreq->len);
 
 	if (test_bit(NETFS_SREQ_FAILED, &subreq->flags))
 		return netfs_write_subrequest_terminated(subreq, subreq->error, false);
 
-	// TODO: Use encrypted buffer
-	subreq->io_iter = *source;
-	iov_iter_advance(source, size);
-	iov_iter_truncate(&subreq->io_iter, size);
-
 	trace_netfs_sreq(subreq, netfs_sreq_trace_submit);
 	stream->issue_write(subreq);
 }
@@ -237,8 +230,15 @@ void netfs_reissue_write(struct netfs_io_stream *stream,
 			 struct netfs_io_subrequest *subreq,
 			 struct iov_iter *source)
 {
+	size_t size = subreq->len - subreq->transferred;
+
+	// TODO: Use encrypted buffer
+	subreq->io_iter = *source;
+	iov_iter_advance(source, size);
+	iov_iter_truncate(&subreq->io_iter, size);
+
 	__set_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
-	netfs_do_issue_write(stream, subreq, source);
+	netfs_do_issue_write(stream, subreq);
 }
 
 static void netfs_issue_write(struct netfs_io_request *wreq,
@@ -249,10 +249,8 @@ static void netfs_issue_write(struct netfs_io_request *wreq,
 	if (!subreq)
 		return;
 	stream->construct = NULL;
-
-	if (subreq->start + subreq->len > wreq->start + wreq->submitted)
-		WRITE_ONCE(wreq->submitted, subreq->start + subreq->len - wreq->start);
-	netfs_do_issue_write(stream, subreq, &wreq->io_iter);
+	subreq->io_iter.count = subreq->len;
+	netfs_do_issue_write(stream, subreq);
 }
 
 /*
@@ -464,10 +462,11 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
 		if (choose_s < 0)
 			break;
 		stream = &wreq->io_streams[choose_s];
+		wreq->io_iter.iov_offset = stream->submit_off;
 
+		atomic64_set(&wreq->issued_to, fpos + stream->submit_off);
 		part = netfs_advance_write(wreq, stream, fpos + stream->submit_off,
 					   stream->submit_len, to_eof);
-		atomic64_set(&wreq->issued_to, fpos + stream->submit_off);
 		stream->submit_off += part;
 		stream->submit_max_len -= part;
 		if (part > stream->submit_len)
@@ -478,6 +477,8 @@ static int netfs_write_folio(struct netfs_io_request *wreq,
 			debug = true;
 	}
 
+	wreq->io_iter.iov_offset = 0;
+	iov_iter_advance(&wreq->io_iter, fsize);
 	atomic64_set(&wreq->issued_to, fpos + fsize);
 
 	if (!debug)
@@ -526,10 +527,10 @@ int netfs_writepages(struct address_space *mapping,
 	netfs_stat(&netfs_n_wh_writepages);
 
 	do {
-		_debug("wbiter %lx %llx", folio->index, wreq->start + wreq->submitted);
+		_debug("wbiter %lx %llx", folio->index, atomic64_read(&wreq->issued_to));
 
 		/* It appears we don't have to handle cyclic writeback wrapping. */
-		WARN_ON_ONCE(wreq && folio_pos(folio) < wreq->start + wreq->submitted);
+		WARN_ON_ONCE(wreq && folio_pos(folio) < atomic64_read(&wreq->issued_to));
 
 		if (netfs_folio_group(folio) != NETFS_FOLIO_COPY_TO_CACHE &&
 		    unlikely(!test_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags))) {
@@ -673,6 +674,7 @@ int netfs_unbuffered_write(struct netfs_io_request *wreq, bool may_wait, size_t
 		part = netfs_advance_write(wreq, upload, start, len, false);
 		start += part;
 		len -= part;
+		iov_iter_advance(&wreq->io_iter, part);
 		if (test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) {
 			trace_netfs_rreq(wreq, netfs_rreq_trace_wait_pause);
 			wait_on_bit(&wreq->flags, NETFS_RREQ_PAUSE, TASK_UNINTERRUPTIBLE);