1 files changed, 32 insertions, 11 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 95544e4028c0..6e5617b9f9db 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -283,6 +283,8 @@
 
 int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
 
+int sysctl_tcp_min_tso_segs __read_mostly = 2;
+
 struct percpu_counter tcp_orphan_count;
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
 
@@ -410,10 +412,6 @@ void tcp_init_sock(struct sock *sk)
 
         icsk->icsk_sync_mss = tcp_sync_mss;
 
-        /* Presumed zeroed, in order of appearance:
-         *      cookie_in_always, cookie_out_never,
-         *      s_data_constant, s_data_in, s_data_out
-         */
         sk->sk_sndbuf = sysctl_tcp_wmem[1];
         sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
@@ -499,7 +497,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
                         mask |= POLLIN | POLLRDNORM;
 
                 if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
-                        if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) {
+                        if (sk_stream_is_writeable(sk)) {
                                 mask |= POLLOUT | POLLWRNORM;
                         } else {  /* send SIGIO later */
                                 set_bit(SOCK_ASYNC_NOSPACE,
@@ -510,7 +508,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
                                  * wspace test but before the flags are set,
                                  * IO signal will be lost.
                                  */
-                                if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk))
+                                if (sk_stream_is_writeable(sk))
                                         mask |= POLLOUT | POLLWRNORM;
                         }
                 } else
@@ -789,12 +787,28 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
         xmit_size_goal = mss_now;
 
         if (large_allowed && sk_can_gso(sk)) {
-                xmit_size_goal = ((sk->sk_gso_max_size - 1) -
-                                  inet_csk(sk)->icsk_af_ops->net_header_len -
-                                  inet_csk(sk)->icsk_ext_hdr_len -
-                                  tp->tcp_header_len);
+                u32 gso_size, hlen;
+
+                /* Maybe we should/could use sk->sk_prot->max_header here ? */
+                hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
+                       inet_csk(sk)->icsk_ext_hdr_len +
+                       tp->tcp_header_len;
+
+                /* Goal is to send at least one packet per ms,
+                 * not one big TSO packet every 100 ms.
+                 * This preserves ACK clocking and is consistent
+                 * with tcp_tso_should_defer() heuristic.
+                 */
+                gso_size = sk->sk_pacing_rate / (2 * MSEC_PER_SEC);
+                gso_size = max_t(u32, gso_size,
+                                 sysctl_tcp_min_tso_segs * mss_now);
 
-                /* TSQ : try to have two TSO segments in flight */
+                xmit_size_goal = min_t(u32, gso_size,
+                                       sk->sk_gso_max_size - 1 - hlen);
+
+                /* TSQ : try to have at least two segments in flight
+                 * (one in NIC TX ring, another in Qdisc)
+                 */
                 xmit_size_goal = min_t(u32, xmit_size_goal,
                                        sysctl_tcp_limit_output_bytes >> 1);
 
@@ -2639,6 +2653,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
                 else
                         tp->tsoffset = val - tcp_time_stamp;
                 break;
+        case TCP_NOTSENT_LOWAT:
+                tp->notsent_lowat = val;
+                sk->sk_write_space(sk);
+                break;
         default:
                 err = -ENOPROTOOPT;
                 break;
@@ -2855,6 +2873,9 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
         case TCP_TIMESTAMP:
                 val = tcp_time_stamp + tp->tsoffset;
                 break;
+        case TCP_NOTSENT_LOWAT:
+                val = tp->notsent_lowat;
+                break;
         default:
                 return -ENOPROTOOPT;
         }