From: Trond Myklebust trond.myklebust@hammerspace.com
commit f00432063db1a0db484e85193eccc6845435b80e upstream.
We must ensure that all sockets are closed before we call xprt_free() and release the reference to the net namespace. The problem is that calling fput() will defer closing the socket until delayed_fput() gets called. Let's fix the situation by allowing rpciod and the transport teardown code (which runs on the system wq) to call __fput_sync(), and directly close the socket.
Reported-by: Felix Fu foyjog@gmail.com Acked-by: Al Viro viro@zeniv.linux.org.uk Fixes: a73881c96d73 ("SUNRPC: Fix an Oops in udp_poll()") Cc: stable@vger.kernel.org # 5.1.x: 3be232f11a3c: SUNRPC: Prevent immediate close+reconnect Cc: stable@vger.kernel.org # 5.1.x: 89f42494f92f: SUNRPC: Don't call connect() more than once on a TCP socket Cc: stable@vger.kernel.org # 5.1.x Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com [meenashanmugam: Fix merge conflict in xprt_connect] Signed-off-by: Meena Shanmugam meenashanmugam@google.com --- fs/file_table.c | 1 + net/sunrpc/xprt.c | 5 +---- net/sunrpc/xprtsock.c | 16 +++++++++++++--- 3 files changed, 15 insertions(+), 7 deletions(-)
diff --git a/fs/file_table.c b/fs/file_table.c index 30d55c9a1744..70e8fb68a171 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -375,6 +375,7 @@ void __fput_sync(struct file *file) }
EXPORT_SYMBOL(fput); +EXPORT_SYMBOL(__fput_sync);
void __init files_init(void) { diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 68d08dcba018..94ae95c57f78 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -868,10 +868,7 @@ void xprt_connect(struct rpc_task *task) if (!xprt_lock_write(xprt, task)) return;
- if (test_and_clear_bit(XPRT_CLOSE_WAIT, &xprt->state)) - xprt->ops->close(xprt); - - if (!xprt_connected(xprt)) { + if (!xprt_connected(xprt) && !test_bit(XPRT_CLOSE_WAIT, &xprt->state)) { task->tk_rqstp->rq_connect_cookie = xprt->connect_cookie; rpc_sleep_on_timeout(&xprt->pending, task, NULL, xprt_request_timeout(task->tk_rqstp)); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 29e9c54a89d3..81f0e03b71b6 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -989,7 +989,7 @@ static int xs_local_send_request(struct rpc_rqst *req)
/* Close the stream if the previous transmission was incomplete */ if (xs_send_request_was_aborted(transport, req)) { - xs_close(xprt); + xprt_force_disconnect(xprt); return -ENOTCONN; }
@@ -1027,7 +1027,7 @@ static int xs_local_send_request(struct rpc_rqst *req) -status); /* fall through */ case -EPIPE: - xs_close(xprt); + xprt_force_disconnect(xprt); status = -ENOTCONN; }
@@ -1303,6 +1303,16 @@ static void xs_reset_transport(struct sock_xprt *transport)
if (sk == NULL) return; + /* + * Make sure we're calling this in a context from which it is safe + * to call __fput_sync(). In practice that means rpciod and the + * system workqueue. + */ + if (!(current->flags & PF_WQ_WORKER)) { + WARN_ON_ONCE(1); + set_bit(XPRT_CLOSE_WAIT, &xprt->state); + return; + }
if (atomic_read(&transport->xprt.swapper)) sk_clear_memalloc(sk); @@ -1326,7 +1336,7 @@ static void xs_reset_transport(struct sock_xprt *transport) mutex_unlock(&transport->recv_mutex);
trace_rpc_socket_close(xprt, sock); - fput(filp); + __fput_sync(filp);
xprt_disconnect_done(xprt); }