tcp: remove prequeue support

prequeue is a tcp receive optimization that moves part of rx processing
from bh to process context.

This only works if the socket being processed belongs to a process that
is blocked in recv on that socket.

In practice, this doesn't happen anymore that often because nowadays
servers tend to use an event driven (epoll) model.

Even normal client applications (web browsers) commonly use many tcp
connections in parallel.

This has measureable impact only in netperf (which uses plain recv and
thus allows prequeue use) from host to locally running vm (~4%), however,
there were no changes when using netperf between two physical hosts with
ixgbe interfaces.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 1 insertions, 60 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 3a19ea28339f..a68eb4577d36 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1541,61 +1541,6 @@ void tcp_v4_early_demux(struct sk_buff *skb)
         }
 }
 
-/* Packet is added to VJ-style prequeue for processing in process
- * context, if a reader task is waiting. Apparently, this exciting
- * idea (VJ's mail "Re: query about TCP header on tcp-ip" of 07 Sep 93)
- * failed somewhere. Latency? Burstiness? Well, at least now we will
- * see, why it failed. 8)8)                               --ANK
- *
- */
-bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
-{
-        struct tcp_sock *tp = tcp_sk(sk);
-
-        if (sysctl_tcp_low_latency || !tp->ucopy.task)
-                return false;
-
-        if (skb->len <= tcp_hdrlen(skb) &&
-            skb_queue_len(&tp->ucopy.prequeue) == 0)
-                return false;
-
-        /* Before escaping RCU protected region, we need to take care of skb
-         * dst. Prequeue is only enabled for established sockets.
-         * For such sockets, we might need the skb dst only to set sk->sk_rx_dst
-         * Instead of doing full sk_rx_dst validity here, let's perform
-         * an optimistic check.
-         */
-        if (likely(sk->sk_rx_dst))
-                skb_dst_drop(skb);
-        else
-                skb_dst_force_safe(skb);
-
-        __skb_queue_tail(&tp->ucopy.prequeue, skb);
-        tp->ucopy.memory += skb->truesize;
-        if (skb_queue_len(&tp->ucopy.prequeue) >= 32 ||
-            tp->ucopy.memory + atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) {
-                struct sk_buff *skb1;
-
-                BUG_ON(sock_owned_by_user(sk));
-                __NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPPREQUEUEDROPPED,
-                                skb_queue_len(&tp->ucopy.prequeue));
-
-                while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
-                        sk_backlog_rcv(sk, skb1);
-
-                tp->ucopy.memory = 0;
-        } else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
-                wake_up_interruptible_sync_poll(sk_sleep(sk),
-                                           POLLIN | POLLRDNORM | POLLRDBAND);
-                if (!inet_csk_ack_scheduled(sk))
-                        inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
-                                                  (3 * tcp_rto_min(sk)) / 4,
-                                                  TCP_RTO_MAX);
-        }
-        return true;
-}
-EXPORT_SYMBOL(tcp_prequeue);
-
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
         u32 limit = sk->sk_rcvbuf + sk->sk_sndbuf;
@@ -1770,8 +1715,7 @@ process:
         tcp_segs_in(tcp_sk(sk), skb);
         ret = 0;
         if (!sock_owned_by_user(sk)) {
-                if (!tcp_prequeue(sk, skb))
-                        ret = tcp_v4_do_rcv(sk, skb);
+                ret = tcp_v4_do_rcv(sk, skb);
         } else if (tcp_add_backlog(sk, skb)) {
                 goto discard_and_relse;
         }
@@ -1936,9 +1880,6 @@ void tcp_v4_destroy_sock(struct sock *sk)
         }
 #endif
 
-        /* Clean prequeue, it must be empty really */
-        __skb_queue_purge(&tp->ucopy.prequeue);
-
         /* Clean up a referenced TCP bind bucket. */
         if (inet_csk(sk)->icsk_bind_hash)
                 inet_put_port(sk);