Received-SPF: pass (google.com: domain of linux-nfs-owner@vger.kernel.org designates 2620:137:e000::3:7 as permitted sender) client-ip=2620:137:e000::3:7;
From:   David Howells <dhowells@redhat.com>
To:     Jeff Layton <jlayton@kernel.org>, Steve French <smfrench@gmail.com>
Cc:     David Howells <dhowells@redhat.com>,
        Matthew Wilcox <willy@infradead.org>,
        Marc Dionne <marc.dionne@auristor.com>,
        Paulo Alcantara <pc@manguebit.com>,
        Shyam Prasad N <sprasad@microsoft.com>,
        Tom Talpey <tom@talpey.com>,
        Dominique Martinet <asmadeus@codewreck.org>,
        Ilya Dryomov <idryomov@gmail.com>,
        Christian Brauner <christian@brauner.io>,
        linux-afs@lists.infradead.org, linux-cifs@vger.kernel.org,
        linux-nfs@vger.kernel.org, ceph-devel@vger.kernel.org,
        v9fs@lists.linux.dev, linux-fsdevel@vger.kernel.org,
        linux-mm@kvack.org, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-cachefs@redhat.com
Subject: [RFC PATCH 25/53] netfs: Make netfs_read_folio() handle streaming-write pages
Date:   Fri, 13 Oct 2023 17:03:54 +0100
Message-ID: <20231013160423.2218093-26-dhowells@redhat.com>
In-Reply-To: <20231013160423.2218093-1-dhowells@redhat.com>
References: <20231013160423.2218093-1-dhowells@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

netfs_read_folio() needs to handle partially-valid pages that are marked
dirty, but not uptodate in the event that someone tries to read a page was
used to cache data by a streaming write.

In such a case, make netfs_read_folio() set up a bvec iterator that points
to the parts of the folio that need filling and to a sink page for the data
that should be discarded and use that instead of i_pages as the iterator to
be written to.

This requires netfs_rreq_unlock_folios() to convert the page into a normal
dirty uptodate page, getting rid of the partial write record and bumping
the group pointer over to folio->private.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
---
 fs/netfs/buffered_read.c     | 61 ++++++++++++++++++++++++++++++++++--
 include/trace/events/netfs.h |  2 ++
 2 files changed, 60 insertions(+), 3 deletions(-)

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index 2f06344bba21..374707df6575 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -16,6 +16,7 @@
 void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
 {
 	struct netfs_io_subrequest *subreq;
+	struct netfs_folio *finfo;
 	struct folio *folio;
 	pgoff_t start_page = rreq->start / PAGE_SIZE;
 	pgoff_t last_page = ((rreq->start + rreq->len) / PAGE_SIZE) - 1;
@@ -86,6 +87,15 @@ void netfs_rreq_unlock_folios(struct netfs_io_request *rreq)
 
 		if (!pg_failed) {
 			flush_dcache_folio(folio);
+			finfo = netfs_folio_info(folio);
+			if (finfo) {
+				trace_netfs_folio(folio, netfs_folio_trace_filled_gaps);
+				if (finfo->netfs_group)
+					folio_change_private(folio, finfo->netfs_group);
+				else
+					folio_detach_private(folio);
+				kfree(finfo);
+			}
 			folio_mark_uptodate(folio);
 		}
 
@@ -245,6 +255,7 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 	struct address_space *mapping = folio_file_mapping(folio);
 	struct netfs_io_request *rreq;
 	struct netfs_inode *ctx = netfs_inode(mapping->host);
+	struct folio *sink = NULL;
 	int ret;
 
 	_enter("%lx", folio_index(folio));
@@ -265,12 +276,56 @@ int netfs_read_folio(struct file *file, struct folio *folio)
 	trace_netfs_read(rreq, rreq->start, rreq->len, netfs_read_trace_readpage);
 
 	/* Set up the output buffer */
-	iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
-			rreq->start, rreq->len);
+	if (folio_test_dirty(folio)) {
+		/* Handle someone trying to read from an unflushed streaming
+		 * write.  We fiddle the buffer so that a gap at the beginning
+		 * and/or a gap at the end get copied to, but the middle is
+		 * discarded.
+		 */
+		struct netfs_folio *finfo = netfs_folio_info(folio);
+		struct bio_vec *bvec;
+		unsigned int from = finfo->dirty_offset;
+		unsigned int to = from + finfo->dirty_len;
+		unsigned int off = 0, i = 0;
+		size_t flen = folio_size(folio);
+		size_t nr_bvec = flen / PAGE_SIZE + 2;
+		size_t part;
+
+		ret = -ENOMEM;
+		bvec = kmalloc_array(nr_bvec, sizeof(*bvec), GFP_KERNEL);
+		if (!bvec)
+			goto discard;
+
+		sink = folio_alloc(GFP_KERNEL, 0);
+		if (!sink)
+			goto discard;
+
+		trace_netfs_folio(folio, netfs_folio_trace_read_gaps);
+
+		rreq->direct_bv = bvec;
+		rreq->direct_bv_count = nr_bvec;
+		if (from > 0) {
+			bvec_set_folio(&bvec[i++], folio, from, 0);
+			off = from;
+		}
+		while (off < to) {
+			part = min_t(size_t, to - off, PAGE_SIZE);
+			bvec_set_folio(&bvec[i++], sink, part, 0);
+			off += part;
+		}
+		if (to < flen)
+			bvec_set_folio(&bvec[i++], folio, flen - to, to);
+		iov_iter_bvec(&rreq->iter, ITER_DEST, bvec, i, rreq->len);
+	} else {
+		iov_iter_xarray(&rreq->iter, ITER_DEST, &mapping->i_pages,
+				rreq->start, rreq->len);
+	}
 
 	ret = netfs_begin_read(rreq, true);
+	if (sink)
+		folio_put(sink);
 	netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
-	return ret;
+	return ret < 0 ? ret : 0;
 
 discard:
 	netfs_put_request(rreq, false, netfs_rreq_trace_put_discard);
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 94793f842000..b7426f455086 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -115,9 +115,11 @@
 	EM(netfs_folio_trace_clear,		"clear")	\
 	EM(netfs_folio_trace_clear_s,		"clear-s")	\
 	EM(netfs_folio_trace_clear_g,		"clear-g")	\
+	EM(netfs_folio_trace_filled_gaps,	"filled-gaps")	\
 	EM(netfs_folio_trace_kill,		"kill")		\
 	EM(netfs_folio_trace_mkwrite,		"mkwrite")	\
 	EM(netfs_folio_trace_mkwrite_plus,	"mkwrite+")	\
+	EM(netfs_folio_trace_read_gaps,		"read-gaps")	\
 	EM(netfs_folio_trace_redirty,		"redirty")	\
 	EM(netfs_folio_trace_redirtied,		"redirtied")	\
 	EM(netfs_folio_trace_store,		"store")	\