net: TCP thin dupack

This patch enables fast retransmissions after one dupACK for
TCP if the stream is identified as thin. This will reduce
latencies for thin streams that are not able to trigger fast
retransmissions due to high packet interarrival time. This
mechanism is only active if enabled by iocontrol or syscontrol
and the stream is identified as thin.

Signed-off-by: Andreas Petlund <apetlund@simula.no>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 42 insertions, 1 deletions

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index f147310d9af4..2571a62d923e 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -499,6 +499,18 @@ tcp_thin_linear_timeouts - BOOLEAN
         Documentation/networking/tcp-thin.txt
         Default: 0
 
+tcp_thin_dupack - BOOLEAN
+        Enable dynamic triggering of retransmissions after one dupACK
+        for thin streams. If set, a check is performed upon reception
+        of a dupACK to determine if the stream is thin (less than 4
+        packets in flight). As long as the stream is found to be thin,
+        data is retransmitted on the first received dupACK. This
+        improves retransmission latency for non-aggressive thin
+        streams, often found to be time-dependent.
+        For more information on thin streams, see
+        Documentation/networking/tcp-thin.txt
+        Default: 0
+
 UDP variables:
 
 udp_mem - vector of 3 INTEGERs: min, pressure, max
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 3ba8b074612f..a778ee024590 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -104,6 +104,7 @@ enum {
 #define TCP_MD5SIG              14      /* TCP MD5 Signature (RFC2385) */
 #define TCP_COOKIE_TRANSACTIONS 15      /* TCP Cookie Transactions */
 #define TCP_THIN_LINEAR_TIMEOUTS 16      /* Use linear timeouts for thin streams*/
+#define TCP_THIN_DUPACK         17      /* Fast retrans. after 1 dupack */
 
 /* for TCP_INFO socket option */
 #define TCPI_OPT_TIMESTAMPS     1
@@ -343,7 +344,8 @@ struct tcp_sock {
         u8      frto_counter;   /* Number of new acks after RTO */
         u8      nonagle     : 4,/* Disable Nagle algorithm?             */
                 thin_lto    : 1,/* Use linear timeouts for thin streams */
-                unused      : 3;
+                thin_dupack : 1,/* Fast retransmit on first dupack      */
+                unused      : 2;
 
 /* RTT measurement */
         u32     srtt;           /* smoothed round trip time << 3        */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6278fc734abd..56f0aec40ed6 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -245,6 +245,7 @@ extern int sysctl_tcp_slow_start_after_idle;
 extern int sysctl_tcp_max_ssthresh;
 extern int sysctl_tcp_cookie_size;
 extern int sysctl_tcp_thin_linear_timeouts;
+extern int sysctl_tcp_thin_dupack;
 
 extern atomic_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index e6a2460587d4..c1bc074f61b7 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -582,6 +582,13 @@ static struct ctl_table ipv4_table[] = {
                 .mode           = 0644,
                 .proc_handler   = proc_dointvec
         },
+        {
+                .procname       = "tcp_thin_dupack",
+                .data           = &sysctl_tcp_thin_dupack,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = proc_dointvec
+        },
         {
                 .procname       = "udp_mem",
                 .data           = &sysctl_udp_mem,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 21bae9afefea..5901010fad55 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2236,6 +2236,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
                         tp->thin_lto = val;
                 break;
 
+        case TCP_THIN_DUPACK:
+                if (val < 0 || val > 1)
+                        err = -EINVAL;
+                else
+                        tp->thin_dupack = val;
+                break;
+
         case TCP_CORK:
                 /* When set indicates to always queue non-full frames.
                  * Later the user clears this option and we transmit
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 3fddc69ccccc..788851ca8c5d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -89,6 +89,8 @@ int sysctl_tcp_frto __read_mostly = 2;
 int sysctl_tcp_frto_response __read_mostly;
 int sysctl_tcp_nometrics_save __read_mostly;
 
+int sysctl_tcp_thin_dupack __read_mostly;
+
 int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
 int sysctl_tcp_abc __read_mostly;
 
@@ -2447,6 +2449,16 @@ static int tcp_time_to_recover(struct sock *sk)
                 return 1;
         }
 
+        /* If a thin stream is detected, retransmit after first
+         * received dupack. Employ only if SACK is supported in order
+         * to avoid possible corner-case series of spurious retransmissions
+         * Use only if there are no unsent data.
+         */
+        if ((tp->thin_dupack || sysctl_tcp_thin_dupack) &&
+            tcp_stream_is_thin(tp) && tcp_dupack_heuristics(tp) > 1 &&
+            tcp_is_sack(tp) && !tcp_send_head(sk))
+                return 1;
+
         return 0;
 }