[PATCH v16 08/15] netfs: Change netfs_writeback_single() to not look inside the iterator

[David Howells <dhowells@redhat.com>]

Change netfs_writeback_single() so that it doesn't look around inside the
data buffer iterator it is given and doesn't try to submit the folios from
the list individually.  Instead, it treats it as a DIO write and pushes the
iterator directly, unsliced, to the cache (or the filesystem) to write
from.

There are also some changes of behaviour:

 (1) netfs_writeback_single() will make a single unbounded monolithic write
     to the cache.

 (2) When writing, sreq_max_len/segs are ignored as the "single" type
     mandates all the data be transferred in a single op.  Whilst this is
     not strictly necessary for the cache as the contract is really with
     the server, it simplifies things for now.

 (3) An explicit wait is added to the function to make sure that the write
     is concluded before returning as there's currently no mechanism to
     check if the write is completed as page flags aren't used.  This can
     be fixed later, but may require AFS's dir and symlink handling to
     check for write completion before allowing further changes be made.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Paulo Alcantara <pc@manguebit.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Christoph Hellwig <hch@infradead.org>
cc: linux-afs@lists.infradead.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
---
 fs/netfs/write_issue.c | 172 +++++++----------------------------------
 1 file changed, 28 insertions(+), 144 deletions(-)

diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
index e041023811ed..f084a6796667 100644
--- a/fs/netfs/write_issue.c
+++ b/fs/netfs/write_issue.c
@@ -625,133 +625,15 @@ int netfs_writepages(struct address_space *mapping,
 }
 EXPORT_SYMBOL(netfs_writepages);
 
-/*
- * Write some of a pending folio data back to the server and/or the cache.
- */
-static int netfs_write_folio_single(struct netfs_io_request *wreq,
-				    struct folio *folio)
-{
-	struct netfs_io_stream *upload = &wreq->io_streams[0];
-	struct netfs_io_stream *cache  = &wreq->io_streams[1];
-	struct netfs_io_stream *stream;
-	size_t iter_off = 0;
-	size_t fsize = folio_size(folio), flen;
-	uoff_t fpos = folio_pos(folio);
-	ssize_t ret;
-	bool to_eof = false;
-	bool no_debug = false;
-
-	_enter("");
-
-	flen = folio_size(folio);
-	if (flen > wreq->i_size - fpos) {
-		flen = wreq->i_size - fpos;
-		folio_zero_segment(folio, flen, fsize);
-		to_eof = true;
-	} else if (flen == wreq->i_size - fpos) {
-		to_eof = true;
-	}
-
-	_debug("folio %zx/%zx", flen, fsize);
-
-	if (!upload->avail && !cache->avail) {
-		trace_netfs_folio(folio, netfs_folio_trace_cancel_store);
-		return 0;
-	}
-
-	if (!upload->construct)
-		trace_netfs_folio(folio, netfs_folio_trace_store);
-	else
-		trace_netfs_folio(folio, netfs_folio_trace_store_plus);
-
-	/* Attach the folio to the rolling buffer. */
-	folio_get(folio);
-	ret = rolling_buffer_append(&wreq->buffer, folio, NETFS_ROLLBUF_PUT_MARK, wreq->gfp);
-	if (ret < 0) {
-		folio_put(folio);
-		return ret;
-	}
-
-	/* Move the submission point forward to allow for write-streaming data
-	 * not starting at the front of the page.  We don't do write-streaming
-	 * with the cache as the cache requires DIO alignment.
-	 *
-	 * Also skip uploading for data that's been read and just needs copying
-	 * to the cache.
-	 */
-	for (int s = 0; s < NR_IO_STREAMS; s++) {
-		stream = &wreq->io_streams[s];
-		stream->submit_off = 0;
-		stream->submit_len = flen;
-		if (!stream->avail) {
-			stream->submit_off = UINT_MAX;
-			stream->submit_len = 0;
-		}
-	}
-
-	/* Attach the folio to one or more subrequests.  For a big folio, we
-	 * could end up with thousands of subrequests if the wsize is small -
-	 * but we might need to wait during the creation of subrequests for
-	 * network resources (eg. SMB credits).
-	 */
-	for (;;) {
-		ssize_t part;
-		size_t lowest_off = ULONG_MAX;
-		int choose_s = -1;
-
-		/* Always add to the lowest-submitted stream first. */
-		for (int s = 0; s < NR_IO_STREAMS; s++) {
-			stream = &wreq->io_streams[s];
-			if (stream->submit_len > 0 &&
-			    stream->submit_off < lowest_off) {
-				lowest_off = stream->submit_off;
-				choose_s = s;
-			}
-		}
-
-		if (choose_s < 0)
-			break;
-		stream = &wreq->io_streams[choose_s];
-
-		/* Advance the iterator(s). */
-		if (stream->submit_off > iter_off) {
-			rolling_buffer_advance(&wreq->buffer, stream->submit_off - iter_off);
-			iter_off = stream->submit_off;
-		}
-
-		atomic64_set(&wreq->issued_to, fpos + stream->submit_off);
-		stream->submit_extendable_to = fsize - stream->submit_off;
-		part = netfs_advance_write(wreq, stream, fpos + stream->submit_off,
-					   stream->submit_len, to_eof);
-		stream->submit_off += part;
-		if (part > stream->submit_len)
-			stream->submit_len = 0;
-		else
-			stream->submit_len -= part;
-		if (part > 0)
-			no_debug = true;
-	}
-
-	wreq->buffer.iter.iov_offset = 0;
-	if (fsize > iter_off)
-		rolling_buffer_advance(&wreq->buffer, fsize - iter_off);
-	atomic64_set(&wreq->issued_to, fpos + fsize);
-
-	if (!no_debug)
-		kdebug("R=%x: No submit", wreq->debug_id);
-	_leave(" = 0");
-	return 0;
-}
-
 /**
- * netfs_writeback_single - Write back a monolithic payload
+ * netfs_writeback_single - Write back a monolithic payload to cache
  * @mapping: The mapping to write from
  * @wbc: Hints from the VM
- * @iter: Data buffer to write from, must be ITER_FOLIOQ.
+ * @iter: Data buffer to write from.
  * @len: Amount of data to write.
  *
- * Write a monolithic, non-pagecache object back to the server and/or
- * the cache.
+ * Write a monolithic, non-pagecache object back to the cache only.  The data
+ * is not written to the server.
  *
  * The data buffer may be bigger than @len (as set in @iter's count), and if
  * so, this function will use the extra as needed to provide padding into the
@@ -766,12 +648,8 @@ int netfs_writeback_single(struct address_space *mapping,
 {
 	struct netfs_io_request *wreq;
 	struct netfs_inode *ictx = netfs_inode(mapping->host);
-	struct folio_queue *fq;
-	size_t size = len;
 	int ret;
 
-	if (WARN_ON_ONCE(!iov_iter_is_folioq(iter)))
-		return -EIO;
 	if (WARN_ON_ONCE(iov_iter_count(iter) < len))
 		return -EIO;
 
@@ -787,36 +665,42 @@ int netfs_writeback_single(struct address_space *mapping,
 		goto couldnt_start;
 	}
 
+	wreq->buffer.iter = *iter;
+	wreq->len = len;
+	wreq->submitted = wreq->len;
+
 	__set_bit(NETFS_RREQ_OFFLOAD_COLLECTION, &wreq->flags);
 	trace_netfs_write(wreq, netfs_write_trace_writeback_single);
 	netfs_stat(&netfs_n_wh_writepages);
 
-	if (__test_and_set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags))
-		wreq->netfs_ops->begin_writeback(wreq);
+	for (int s = 0; s < NR_IO_STREAMS; s++) {
+		struct netfs_io_subrequest *subreq;
+		struct netfs_io_stream *stream = &wreq->io_streams[s];
+
+		if (!stream->avail)
+			continue;
 
-	for (fq = (struct folio_queue *)iter->folioq; fq; fq = fq->next) {
-		for (int slot = 0; slot < folioq_count(fq); slot++) {
-			struct folio *folio = folioq_folio(fq, slot);
-			size_t part = umin(folioq_folio_size(fq, slot), size);
+		netfs_prepare_write(wreq, stream, 0);
+		/* Allocation not allowed to fail in writeback. */
 
-			_debug("wbiter %lx %llx", folio->index, atomic64_read(&wreq->issued_to));
+		subreq = stream->construct;
+		subreq->len = wreq->len;
+		stream->submit_len = subreq->len;
+		stream->submit_extendable_to = iov_iter_count(iter) - len;
 
-			ret = netfs_write_folio_single(wreq, folio);
-			if (ret < 0)
-				goto stop;
-			size -= part;
-			if (size <= 0)
-				goto stop;
-		}
+		netfs_issue_write(wreq, stream);
 	}
 
-stop:
-	for (int s = 0; s < NR_IO_STREAMS; s++)
-		netfs_issue_write(wreq, &wreq->io_streams[s]);
 	netfs_all_subreqs_queued(wreq);
-
 	netfs_wake_collector(wreq);
 
+	/* TODO: Might want to be async here if WB_SYNC_NONE, but then need to
+	 * wait before modifying.
+	 */
+	ret = netfs_wait_for_write(wreq);
+	if (ret > 0)
+		ret = 0;
+
 	netfs_put_request(wreq, netfs_rreq_trace_put_return);
 	_leave(" = %d", ret);
 	return ret;