From:   Trond Myklebust <trondmy@gmail.com>
To:     linux-nfs@vger.kernel.org
Subject: [PATCH] SUNRPC: Use poll() to fix up the socket requeue races
Date:   Tue, 19 Feb 2019 09:06:16 -0500
Message-Id: <20190219140616.123141-1-trond.myklebust@hammerspace.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-nfs-owner@vger.kernel.org
Precedence: bulk

Because we clear XPRT_SOCK_DATA_READY before reading, we can end up
with a situation where new data arrives, causing xs_data_ready() to
queue up a second receive worker job for the same socket, which then
immediately gets stuck waiting on the transport receive mutex.
The fix is to only clear XPRT_SOCK_DATA_READY once we're done reading,
and then to use poll() to check if we might need to queue up a new
job in order to deal with any new data.

Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 net/sunrpc/xprtsock.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index f5d7dcd9e8d9..a721c843d5d3 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -656,13 +656,25 @@ xs_read_stream(struct sock_xprt *transport, int flags)
 	return ret != 0 ? ret : -ESHUTDOWN;
 }
 
+static void xs_poll_check_readable(struct sock_xprt *transport)
+{
+	struct socket *sock = transport->sock;
+	__poll_t events;
+
+	clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state);
+	events = sock->ops->poll(NULL, sock, NULL);
+	if (!(events & (EPOLLIN | EPOLLRDNORM)) || events & EPOLLRDHUP)
+		return;
+	if (!test_and_set_bit(XPRT_SOCK_DATA_READY, &transport->sock_state))
+		queue_work(xprtiod_workqueue, &transport->recv_worker);
+}
+
 static void xs_stream_data_receive(struct sock_xprt *transport)
 {
 	size_t read = 0;
 	ssize_t ret = 0;
 
 	mutex_lock(&transport->recv_mutex);
-	clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state);
 	if (transport->sock == NULL)
 		goto out;
 	for (;;) {
@@ -672,6 +684,7 @@ static void xs_stream_data_receive(struct sock_xprt *transport)
 		read += ret;
 		cond_resched();
 	}
+	xs_poll_check_readable(transport);
 out:
 	mutex_unlock(&transport->recv_mutex);
 	trace_xs_stream_read_data(&transport->xprt, ret, read);
@@ -1362,7 +1375,6 @@ static void xs_udp_data_receive(struct sock_xprt *transport)
 	int err;
 
 	mutex_lock(&transport->recv_mutex);
-	clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state);
 	sk = transport->inet;
 	if (sk == NULL)
 		goto out;
@@ -1374,6 +1386,7 @@ static void xs_udp_data_receive(struct sock_xprt *transport)
 		consume_skb(skb);
 		cond_resched();
 	}
+	xs_poll_check_readable(transport);
 out:
 	mutex_unlock(&transport->recv_mutex);
 }
-- 
2.20.1