net: Add rtnetlink init_rcvwnd to set the TCP initial receive window

Add rtnetlink init_rcvwnd to set the TCP initial receive window size
advertised by passive and active TCP connections.
The current Linux TCP implementation limits the advertised TCP initial
receive window to the one prescribed by slow start. For short lived
TCP connections used for transaction type of traffic (i.e. http
requests), bounding the advertised TCP initial receive window results
in increased latency to complete the transaction.
Support for setting initial congestion window is already supported
using rtnetlink init_cwnd, but the feature is useless without the
ability to set a larger TCP initial receive window.
The rtnetlink init_rcvwnd allows increasing the TCP initial receive
window, allowing TCP connection to advertise larger TCP receive window
than the ones bounded by slow start.

Signed-off-by: Laurent Chavey <chavey@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 21 insertions, 9 deletions

diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 05330fc5b436..9590364fe8b5 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -362,6 +362,8 @@ enum {
 #define RTAX_FEATURES RTAX_FEATURES
         RTAX_RTO_MIN,
 #define RTAX_RTO_MIN RTAX_RTO_MIN
+        RTAX_INITRWND,
+#define RTAX_INITRWND RTAX_INITRWND
         __RTAX_MAX
 };
 
diff --git a/include/net/dst.h b/include/net/dst.h
index 39c4a5963e12..ce078cda6b74 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -83,8 +83,6 @@ struct dst_entry {
          * (L1_CACHE_SIZE would be too much)
          */
 #ifdef CONFIG_64BIT
-        long                    __pad_to_align_refcnt[2];
-#else
         long                    __pad_to_align_refcnt[1];
 #endif
         /*
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 185e22baecb1..788c99f98597 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -965,7 +965,8 @@ static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
 /* Determine a window scaling and initial window to offer. */
 extern void tcp_select_initial_window(int __space, __u32 mss,
                                       __u32 *rcv_wnd, __u32 *window_clamp,
-                                      int wscale_ok, __u8 *rcv_wscale);
+                                      int wscale_ok, __u8 *rcv_wscale,
+                                      __u32 init_rcv_wnd);
 
 static inline int tcp_win_from_space(int space)
 {
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 66fd80ef2473..5c24db4a3c91 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -358,7 +358,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 
         tcp_select_initial_window(tcp_full_space(sk), req->mss,
                                   &req->rcv_wnd, &req->window_clamp,
-                                  ireq->wscale_ok, &rcv_wscale);
+                                  ireq->wscale_ok, &rcv_wscale,
+                                  dst_metric(&rt->u.dst, RTAX_INITRWND));
 
         ireq->rcv_wscale  = rcv_wscale;
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 12b2af36eab8..4a1605d3f909 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -183,7 +183,8 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
  */
 void tcp_select_initial_window(int __space, __u32 mss,
                                __u32 *rcv_wnd, __u32 *window_clamp,
-                               int wscale_ok, __u8 *rcv_wscale)
+                               int wscale_ok, __u8 *rcv_wscale,
+                               __u32 init_rcv_wnd)
 {
         unsigned int space = (__space < 0 ? 0 : __space);
 
@@ -232,7 +233,13 @@ void tcp_select_initial_window(int __space, __u32 mss,
                         init_cwnd = 2;
                 else if (mss > 1460)
                         init_cwnd = 3;
-                if (*rcv_wnd > init_cwnd * mss)
+                /* when initializing use the value from init_rcv_wnd
+                 * rather than the default from above
+                 */
+                if (init_rcv_wnd &&
+                    (*rcv_wnd > init_rcv_wnd * mss))
+                        *rcv_wnd = init_rcv_wnd * mss;
+                else if (*rcv_wnd > init_cwnd * mss)
                         *rcv_wnd = init_cwnd * mss;
         }
 
@@ -2417,7 +2424,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
                         &req->rcv_wnd,
                         &req->window_clamp,
                         ireq->wscale_ok,
-                        &rcv_wscale);
+                        &rcv_wscale,
+                        dst_metric(dst, RTAX_INITRWND));
                 ireq->rcv_wscale = rcv_wscale;
         }
 
@@ -2544,7 +2552,8 @@ static void tcp_connect_init(struct sock *sk)
                                   &tp->rcv_wnd,
                                   &tp->window_clamp,
                                   sysctl_tcp_window_scaling,
-                                  &rcv_wscale);
+                                  &rcv_wscale,
+                                  dst_metric(dst, RTAX_INITRWND));
 
         tp->rx_opt.rcv_wscale = rcv_wscale;
         tp->rcv_ssthresh = tp->rcv_wnd;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 7208a06576c6..34d1f0690d7e 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -269,7 +269,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
         req->window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
         tcp_select_initial_window(tcp_full_space(sk), req->mss,
                                   &req->rcv_wnd, &req->window_clamp,
-                                  ireq->wscale_ok, &rcv_wscale);
+                                  ireq->wscale_ok, &rcv_wscale,
+                                  dst_metric(dst, RTAX_INITRWND));
 
         ireq->rcv_wscale = rcv_wscale;