kernel: backport an upstream fix to improve TCP performance for wifi drivers

Signed-off-by: Felix Fietkau <nbd@openwrt.org>
SVN-Revision: 38810

diff --git a/target/linux/generic/patches-3.10/010-tsq_queueing_minimum.patch b/target/linux/generic/patches-3.10/010-tsq_queueing_minimum.patch
new file mode 100644 (file)
index 0000000..2d2dafc
--- /dev/null
+++ b/target/linux/generic/patches-3.10/010-tsq_queueing_minimum.patch
@@ -0,0 +1,80 @@
+From 98e09386c0ef4dfd48af7ba60ff908f0d525cdee Mon Sep 17 00:00:00 2001
+From: Eric Dumazet <edumazet@google.com>
+Date: Wed, 13 Nov 2013 14:32:54 +0000
+Subject: tcp: tsq: restore minimal amount of queueing
+
+After commit c9eeec26e32e ("tcp: TSQ can use a dynamic limit"), several
+users reported throughput regressions, notably on mvneta and wifi
+adapters.
+
+802.11 AMPDU requires a fair amount of queueing to be effective.
+
+This patch partially reverts the change done in tcp_write_xmit()
+so that the minimal amount is sysctl_tcp_limit_output_bytes.
+
+It also remove the use of this sysctl while building skb stored
+in write queue, as TSO autosizing does the right thing anyway.
+
+Users with well behaving NICS and correct qdisc (like sch_fq),
+can then lower the default sysctl_tcp_limit_output_bytes value from
+128KB to 8KB.
+
+This new usage of sysctl_tcp_limit_output_bytes permits each driver
+authors to check how their driver performs when/if the value is set
+to a minimum of 4KB.
+
+Normally, line rate for a single TCP flow should be possible,
+but some drivers rely on timers to perform TX completion and
+too long TX completion delays prevent reaching full throughput.
+
+Fixes: c9eeec26e32e ("tcp: TSQ can use a dynamic limit")
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Reported-by: Sujith Manoharan <sujith@msujith.org>
+Reported-by: Arnaud Ebalard <arno@natisbad.org>
+Tested-by: Sujith Manoharan <sujith@msujith.org>
+Cc: Felix Fietkau <nbd@openwrt.org>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+--- a/Documentation/networking/ip-sysctl.txt
++++ b/Documentation/networking/ip-sysctl.txt
+@@ -571,9 +571,6 @@ tcp_limit_output_bytes - INTEGER
+       typical pfifo_fast qdiscs.
+       tcp_limit_output_bytes limits the number of bytes on qdisc
+       or device to reduce artificial RTT/cwnd and reduce bufferbloat.
+-      Note: For GSO/TSO enabled flows, we try to have at least two
+-      packets in flight. Reducing tcp_limit_output_bytes might also
+-      reduce the size of individual GSO packet (64KB being the max)
+       Default: 131072
+ 
+ tcp_challenge_ack_limit - INTEGER
+--- a/net/ipv4/tcp.c
++++ b/net/ipv4/tcp.c
+@@ -807,12 +807,6 @@ static unsigned int tcp_xmit_size_goal(s
+               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);
+-
+               xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal);
+ 
+               /* We try hard to avoid divides here */
+--- a/net/ipv4/tcp_output.c
++++ b/net/ipv4/tcp_output.c
+@@ -1866,8 +1866,12 @@ static bool tcp_write_xmit(struct sock *
+                *  - better RTT estimation and ACK scheduling
+                *  - faster recovery
+                *  - high rates
++               * Alas, some drivers / subsystems require a fair amount
++               * of queued bytes to ensure line rate.
++               * One example is wifi aggregation (802.11 AMPDU)
+                */
+-              limit = max(skb->truesize, sk->sk_pacing_rate >> 10);
++              limit = max_t(unsigned int, sysctl_tcp_limit_output_bytes,
++                            sk->sk_pacing_rate >> 10);
+ 
+               if (atomic_read(&sk->sk_wmem_alloc) > limit) {
+                       set_bit(TSQ_THROTTLED, &tp->tsq_flags);