Re: [PATCH net] rds: MP-RDS may use an invalid c_path

[David Miller]

From: Ka-Cheong Poon 
Date: Wed, 11 Apr 2018 00:57:25 -0700

> rds_sendmsg() calls rds_send_mprds_hash() to find a c_path to use to
> send a message.  Suppose the RDS connection is not yet up.  In
> rds_send_mprds_hash(), it does
> 
>   if (conn->c_npaths == 0)
>   wait_event_interruptible(conn->c_hs_waitq,
>(conn->c_npaths != 0));
> 
> If it is interrupted before the connection is set up,
> rds_send_mprds_hash() will return a non-zero hash value.  Hence
> rds_sendmsg() will use a non-zero c_path to send the message.  But if
> the RDS connection ends up to be non-MP capable, the message will be
> lost as only the zero c_path can be used.
> 
> Signed-off-by: Ka-Cheong Poon 

Applied and queued up for -stable, thanks.

Re: [PATCH net] rds: MP-RDS may use an invalid c_path

[santosh.shilim...@oracle.com]

On 4/11/18 12:57 AM, Ka-Cheong Poon wrote:

rds_sendmsg() calls rds_send_mprds_hash() to find a c_path to use to
send a message.  Suppose the RDS connection is not yet up.  In
rds_send_mprds_hash(), it does

if (conn->c_npaths == 0)
wait_event_interruptible(conn->c_hs_waitq,
 (conn->c_npaths != 0));

If it is interrupted before the connection is set up,
rds_send_mprds_hash() will return a non-zero hash value.  Hence
rds_sendmsg() will use a non-zero c_path to send the message.  But if
the RDS connection ends up to be non-MP capable, the message will be
lost as only the zero c_path can be used.

Signed-off-by: Ka-Cheong Poon 
---

Thanks for posting the fix upstream as well.

Acked-by: Santosh Shilimkar 

[PATCH net] rds: MP-RDS may use an invalid c_path

[Ka-Cheong Poon]

rds_sendmsg() calls rds_send_mprds_hash() to find a c_path to use to
send a message.  Suppose the RDS connection is not yet up.  In
rds_send_mprds_hash(), it does

if (conn->c_npaths == 0)
wait_event_interruptible(conn->c_hs_waitq,
 (conn->c_npaths != 0));

If it is interrupted before the connection is set up,
rds_send_mprds_hash() will return a non-zero hash value.  Hence
rds_sendmsg() will use a non-zero c_path to send the message.  But if
the RDS connection ends up to be non-MP capable, the message will be
lost as only the zero c_path can be used.

Signed-off-by: Ka-Cheong Poon 
---
 net/rds/send.c | 15 ++-
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/rds/send.c b/net/rds/send.c
index acad042..94c7f74 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -1017,10 +1017,15 @@ static int rds_send_mprds_hash(struct rds_sock *rs, 
struct rds_connection *conn)
if (conn->c_npaths == 0 && hash != 0) {
rds_send_ping(conn, 0);
 
-   if (conn->c_npaths == 0) {
-   wait_event_interruptible(conn->c_hs_waitq,
-(conn->c_npaths != 0));
-   }
+   /* The underlying connection is not up yet.  Need to wait
+* until it is up to be sure that the non-zero c_path can be
+* used.  But if we are interrupted, we have to use the zero
+* c_path in case the connection ends up being non-MP capable.
+*/
+   if (conn->c_npaths == 0)
+   if (wait_event_interruptible(conn->c_hs_waitq,
+conn->c_npaths != 0))
+   hash = 0;
if (conn->c_npaths == 1)
hash = 0;
}
-- 
1.8.3.1