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, 71 insertions, 0 deletions

diff --git a/target/linux/generic/backport-4.9/024-3-tcp-tsq-add-shortcut-in-tcp_tasklet_func.patch b/target/linux/generic/backport-4.9/024-3-tcp-tsq-add-shortcut-in-tcp_tasklet_func.patch
new file mode 100644
index 0000000000..8f45c23e3f
--- /dev/null
+++ b/target/linux/generic/backport-4.9/024-3-tcp-tsq-add-shortcut-in-tcp_tasklet_func.patch
@@ -0,0 +1,71 @@
+From b223feb9de2a65c533ff95c08e834fa732906ea5 Mon Sep 17 00:00:00 2001
+From: Eric Dumazet <edumazet@google.com>
+Date: Sat, 3 Dec 2016 11:14:52 -0800
+Subject: [PATCH 03/10] tcp: tsq: add shortcut in tcp_tasklet_func()
+
+Under high stress, I've seen tcp_tasklet_func() consuming
+~700 usec, handling ~150 tcp sockets.
+
+By setting TCP_TSQ_DEFERRED in tcp_wfree(), we give a chance
+for other cpus/threads entering tcp_write_xmit() to grab it,
+allowing tcp_tasklet_func() to skip sockets that already did
+an xmit cycle.
+
+In the future, we might give to ACK processing an increased
+budget to reduce even more tcp_tasklet_func() amount of work.
+
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+ net/ipv4/tcp_output.c | 22 ++++++++++++----------
+ 1 file changed, 12 insertions(+), 10 deletions(-)
+
+--- a/net/ipv4/tcp_output.c
++++ b/net/ipv4/tcp_output.c
+@@ -767,19 +767,19 @@ static void tcp_tasklet_func(unsigned lo
+ 	list_for_each_safe(q, n, &list) {
+ 		tp = list_entry(q, struct tcp_sock, tsq_node);
+ 		list_del(&tp->tsq_node);
++		clear_bit(TSQ_QUEUED, &tp->tsq_flags);
+ 
+ 		sk = (struct sock *)tp;
+-		bh_lock_sock(sk);
+-
+-		if (!sock_owned_by_user(sk)) {
+-			tcp_tsq_handler(sk);
+-		} else {
+-			/* defer the work to tcp_release_cb() */
+-			set_bit(TCP_TSQ_DEFERRED, &tp->tsq_flags);
++		if (!sk->sk_lock.owned &&
++		    test_bit(TCP_TSQ_DEFERRED, &tp->tsq_flags)) {
++			bh_lock_sock(sk);
++			if (!sock_owned_by_user(sk)) {
++				clear_bit(TCP_TSQ_DEFERRED, &tp->tsq_flags);
++				tcp_tsq_handler(sk);
++			}
++			bh_unlock_sock(sk);
+ 		}
+-		bh_unlock_sock(sk);
+ 
+-		clear_bit(TSQ_QUEUED, &tp->tsq_flags);
+ 		sk_free(sk);
+ 	}
+ }
+@@ -884,7 +884,7 @@ void tcp_wfree(struct sk_buff *skb)
+ 		if (!(oval & TSQF_THROTTLED) || (oval & TSQF_QUEUED))
+ 			goto out;
+ 
+-		nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED;
++		nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED | TCPF_TSQ_DEFERRED;
+ 		nval = cmpxchg(&tp->tsq_flags, oval, nval);
+ 		if (nval != oval)
+ 			continue;
+@@ -2179,6 +2179,8 @@ static bool tcp_write_xmit(struct sock *
+ 		    unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
+ 			break;
+ 
++		if (test_bit(TCP_TSQ_DEFERRED, &tp->tsq_flags))
++			clear_bit(TCP_TSQ_DEFERRED, &tp->tsq_flags);
+ 		if (tcp_small_queue_check(sk, skb, 0))
+ 			break;
+