Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To:     linux-kernel@vger.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        stable@vger.kernel.org, Chuck Lever <chuck.lever@oracle.com>,
        Trond Myklebust <trond.myklebust@hammerspace.com>,
        Sasha Levin <sashal@kernel.org>
Subject: [PATCH 5.10 123/289] SUNRPC: Move fault injection call sites
Date:   Mon, 17 May 2021 16:00:48 +0200
Message-Id: <20210517140309.303881237@linuxfoundation.org>
In-Reply-To: <20210517140305.140529752@linuxfoundation.org>
References: <20210517140305.140529752@linuxfoundation.org>
User-Agent: quilt/0.66
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Precedence: bulk

From: Chuck Lever <chuck.lever@oracle.com>

[ Upstream commit 7638e0bfaed1b653d3ca663e560e9ffb44bb1030 ]

I've hit some crashes that occur in the xprt_rdma_inject_disconnect
path. It appears that, for some provides, rdma_disconnect() can
take so long that the transport can disconnect and release its
hardware resources while rdma_disconnect() is still running,
resulting in a UAF in the provider.

The transport's fault injection method may depend on the stability
of transport data structures. That means it needs to be invoked
only from contexts that hold the transport write lock.

Fixes: 4a0682583988 ("SUNRPC: Transport fault injection")
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/sunrpc/clnt.c               | 1 -
 net/sunrpc/xprt.c               | 6 ++++--
 net/sunrpc/xprtrdma/transport.c | 6 ++++--
 3 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 3259120462ed..69d8843a26e0 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1802,7 +1802,6 @@ call_allocate(struct rpc_task *task)
 
 	status = xprt->ops->buf_alloc(task);
 	trace_rpc_buf_alloc(task, status);
-	xprt_inject_disconnect(xprt);
 	if (status == 0)
 		return;
 	if (status != -ENOMEM) {
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 57f09ea3ef2a..99d07513237e 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1455,7 +1455,10 @@ bool xprt_prepare_transmit(struct rpc_task *task)
 
 void xprt_end_transmit(struct rpc_task *task)
 {
-	xprt_release_write(task->tk_rqstp->rq_xprt, task);
+	struct rpc_xprt	*xprt = task->tk_rqstp->rq_xprt;
+
+	xprt_inject_disconnect(xprt);
+	xprt_release_write(xprt, task);
 }
 
 /**
@@ -1857,7 +1860,6 @@ void xprt_release(struct rpc_task *task)
 	spin_unlock(&xprt->transport_lock);
 	if (req->rq_buffer)
 		xprt->ops->buf_free(task);
-	xprt_inject_disconnect(xprt);
 	xdr_free_bvec(&req->rq_rcv_buf);
 	xdr_free_bvec(&req->rq_snd_buf);
 	if (req->rq_cred != NULL)
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 035060c05fd5..f93ff4282bf4 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -262,8 +262,10 @@ xprt_rdma_connect_worker(struct work_struct *work)
  * xprt_rdma_inject_disconnect - inject a connection fault
  * @xprt: transport context
  *
- * If @xprt is connected, disconnect it to simulate spurious connection
- * loss.
+ * If @xprt is connected, disconnect it to simulate spurious
+ * connection loss. Caller must hold @xprt's send lock to
+ * ensure that data structures and hardware resources are
+ * stable during the rdma_disconnect() call.
  */
 static void
 xprt_rdma_inject_disconnect(struct rpc_xprt *xprt)
-- 
2.30.2