generic: net: tcp: backport tcp tx performance patches

An overall throughput gain of 22 % for heavy TCP use over a single TX queue.

Original patchset comment
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?h=v4.13&id=3f4888adae7c1619b990d98a9b967536f71822b8

Signed-off-by: Pavel Kubelun <be.dissent@gmail.com>

1 files changed, 48 insertions, 0 deletions

diff --git a/target/linux/generic/backport-4.9/024-2-tcp-tsq-remove-one-locked-operation-in-tcp_wfree.patch b/target/linux/generic/backport-4.9/024-2-tcp-tsq-remove-one-locked-operation-in-tcp_wfree.patch
new file mode 100644
index 0000000000..914be607e7
--- /dev/null
+++ b/target/linux/generic/backport-4.9/024-2-tcp-tsq-remove-one-locked-operation-in-tcp_wfree.patch
@@ -0,0 +1,48 @@
+From 408f0a6c21e124cc4f6c7aa370b38aa47e55428d Mon Sep 17 00:00:00 2001
+From: Eric Dumazet <edumazet@google.com>
+Date: Sat, 3 Dec 2016 11:14:51 -0800
+Subject: [PATCH 02/10] tcp: tsq: remove one locked operation in tcp_wfree()
+
+Instead of atomically clear TSQ_THROTTLED and atomically set TSQ_QUEUED
+bits, use one cmpxchg() to perform a single locked operation.
+
+Since the following patch will also set TCP_TSQ_DEFERRED here,
+this cmpxchg() will make this addition free.
+
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+ net/ipv4/tcp_output.c | 13 ++++++++++---
+ 1 file changed, 10 insertions(+), 3 deletions(-)
+
+--- a/net/ipv4/tcp_output.c
++++ b/net/ipv4/tcp_output.c
+@@ -860,6 +860,7 @@ void tcp_wfree(struct sk_buff *skb)
+ {
+ 	struct sock *sk = skb->sk;
+ 	struct tcp_sock *tp = tcp_sk(sk);
++	unsigned long flags, nval, oval;
+ 	int wmem;
+ 
+ 	/* Keep one reference on sk_wmem_alloc.
+@@ -877,11 +878,17 @@ void tcp_wfree(struct sk_buff *skb)
+ 	if (wmem >= SKB_TRUESIZE(1) && this_cpu_ksoftirqd() == current)
+ 		goto out;
+ 
+-	if (test_and_clear_bit(TSQ_THROTTLED, &tp->tsq_flags) &&
+-	    !test_and_set_bit(TSQ_QUEUED, &tp->tsq_flags)) {
+-		unsigned long flags;
++	for (oval = READ_ONCE(tp->tsq_flags);; oval = nval) {
+ 		struct tsq_tasklet *tsq;
+ 
++		if (!(oval & TSQF_THROTTLED) || (oval & TSQF_QUEUED))
++			goto out;
++
++		nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED;
++		nval = cmpxchg(&tp->tsq_flags, oval, nval);
++		if (nval != oval)
++			continue;
++
+ 		/* queue this socket to tasklet queue */
+ 		local_irq_save(flags);
+ 		tsq = this_cpu_ptr(&tsq_tasklet);