net: Do not clear the sock TX queue in sk_set_socket()

Clearing the sock TX queue in sk_set_socket() might cause unexpected
out-of-order transmit when called from sock_orphan(), as outstanding
packets can pick a different TX queue and bypass the ones already queued.

This is undesired in general. More specifically, it breaks the in-order
scheduling property guarantee for device-offloaded TLS sockets.

Remove the call to sk_tx_queue_clear() in sk_set_socket(), and add it
explicitly only where needed.

Fixes: e022f0b4a03f ("net: Introduce sk_tx_queue_mapping")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/sock.h b/include/net/sock.h
index c53cc42b5ab92d0062519e60435b85c75564a967..3428619faae4340485b200f49d9cce4fb09086b3 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1848,7 +1848,6 @@ static inline int sk_rx_queue_get(const struct sock *sk)
 
 static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 {
-       sk_tx_queue_clear(sk);
        sk->sk_socket = sock;
 }
 

diff --git a/net/core/sock.c b/net/core/sock.c
index 94391da277544e12c8a9c9eb52c51b0678b46dc4..d832c650287c375cd9e99e40c09f3ec354487716 100644 (file)
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1767,6 +1767,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
                cgroup_sk_alloc(&sk->sk_cgrp_data);
                sock_update_classid(&sk->sk_cgrp_data);
                sock_update_netprioidx(&sk->sk_cgrp_data);
+               sk_tx_queue_clear(sk);
        }
 
        return sk;
@@ -1990,6 +1991,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
                 */
                sk_refcnt_debug_inc(newsk);
                sk_set_socket(newsk, NULL);
+               sk_tx_queue_clear(newsk);
                RCU_INIT_POINTER(newsk->sk_wq, NULL);
 
                if (newsk->sk_prot->sockets_allocated)