Re: [PATCH net-next 1/6] tcp: do not assume TCP code is non preemptible

[Eric Dumazet]

On Wed, 2016-04-27 at 22:25 -0700, Eric Dumazet wrote:
> We want to to make TCP stack preemptible, as draining prequeue
> and backlog queues can take lot of time.
> 
> Many SNMP updates were assuming that BH (and preemption) was disabled.
> 
> Need to convert some __NET_INC_STATS() calls to NET_INC_STATS()
> and some __TCP_INC_STATS() to TCP_INC_STATS()
> 
> Before using this_cpu_ptr(net->ipv4.tcp_sk) in tcp_v4_send_reset()
> and tcp_v4_send_ack(), we add an explicit preempt disabled section.
> 
> Signed-off-by: Eric Dumazet <eduma...@google.com>
> ---

I'll send a V2 including following changes I missed :

I'll also include the sendmsg() latency breaker.

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0509a685d90c..25d527922b18 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2698,7 +2698,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff 
*skb, int segs)
                        tp->retrans_stamp = tcp_skb_timestamp(skb);
 
        } else if (err != -EBUSY) {
-               __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
+               NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
        }
 
        if (tp->undo_retrans < 0)
@@ -2822,7 +2822,7 @@ begin_fwd:
                if (tcp_retransmit_skb(sk, skb, segs))
                        return;
 
-               __NET_INC_STATS(sock_net(sk), mib_idx);
+               NET_INC_STATS(sock_net(sk), mib_idx);
 
                if (tcp_in_cwnd_reduction(sk))
                        tp->prr_out += tcp_skb_pcount(skb);