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, 90 insertions, 0 deletions

diff --git a/target/linux/generic/backport-4.9/024-1-tcp-tsq-add-tsq_flags-tsq_enum.patch b/target/linux/generic/backport-4.9/024-1-tcp-tsq-add-tsq_flags-tsq_enum.patch
new file mode 100644
index 0000000000..20311498aa
--- /dev/null
+++ b/target/linux/generic/backport-4.9/024-1-tcp-tsq-add-tsq_flags-tsq_enum.patch
@@ -0,0 +1,90 @@
+From 40fc3423b983b864bf70b03199191260ae9b2ea6 Mon Sep 17 00:00:00 2001
+From: Eric Dumazet <edumazet@google.com>
+Date: Sat, 3 Dec 2016 11:14:50 -0800
+Subject: [PATCH 01/10] tcp: tsq: add tsq_flags / tsq_enum
+
+This is a cleanup, to ease code review of following patches.
+
+Old 'enum tsq_flags' is renamed, and a new enumeration is added
+with the flags used in cmpxchg() operations as opposed to
+single bit operations.
+
+Signed-off-by: Eric Dumazet <edumazet@google.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+ include/linux/tcp.h   | 11 ++++++++++-
+ net/ipv4/tcp_output.c | 16 ++++++++--------
+ 2 files changed, 18 insertions(+), 9 deletions(-)
+
+--- a/include/linux/tcp.h
++++ b/include/linux/tcp.h
+@@ -367,7 +367,7 @@ struct tcp_sock {
+ 	u32	*saved_syn;
+ };
+ 
+-enum tsq_flags {
++enum tsq_enum {
+ 	TSQ_THROTTLED,
+ 	TSQ_QUEUED,
+ 	TCP_TSQ_DEFERRED,	   /* tcp_tasklet_func() found socket was owned */
+@@ -378,6 +378,15 @@ enum tsq_flags {
+ 				    */
+ };
+ 
++enum tsq_flags {
++	TSQF_THROTTLED			= (1UL << TSQ_THROTTLED),
++	TSQF_QUEUED			= (1UL << TSQ_QUEUED),
++	TCPF_TSQ_DEFERRED		= (1UL << TCP_TSQ_DEFERRED),
++	TCPF_WRITE_TIMER_DEFERRED	= (1UL << TCP_WRITE_TIMER_DEFERRED),
++	TCPF_DELACK_TIMER_DEFERRED	= (1UL << TCP_DELACK_TIMER_DEFERRED),
++	TCPF_MTU_REDUCED_DEFERRED	= (1UL << TCP_MTU_REDUCED_DEFERRED),
++};
++
+ static inline struct tcp_sock *tcp_sk(const struct sock *sk)
+ {
+ 	return (struct tcp_sock *)sk;
+--- a/net/ipv4/tcp_output.c
++++ b/net/ipv4/tcp_output.c
+@@ -784,10 +784,10 @@ static void tcp_tasklet_func(unsigned lo
+ 	}
+ }
+ 
+-#define TCP_DEFERRED_ALL ((1UL << TCP_TSQ_DEFERRED) |		\
+-			  (1UL << TCP_WRITE_TIMER_DEFERRED) |	\
+-			  (1UL << TCP_DELACK_TIMER_DEFERRED) |	\
+-			  (1UL << TCP_MTU_REDUCED_DEFERRED))
++#define TCP_DEFERRED_ALL (TCPF_TSQ_DEFERRED |		\
++			  TCPF_WRITE_TIMER_DEFERRED |	\
++			  TCPF_DELACK_TIMER_DEFERRED |	\
++			  TCPF_MTU_REDUCED_DEFERRED)
+ /**
+  * tcp_release_cb - tcp release_sock() callback
+  * @sk: socket
+@@ -808,7 +808,7 @@ void tcp_release_cb(struct sock *sk)
+ 		nflags = flags & ~TCP_DEFERRED_ALL;
+ 	} while (cmpxchg(&tp->tsq_flags, flags, nflags) != flags);
+ 
+-	if (flags & (1UL << TCP_TSQ_DEFERRED))
++	if (flags & TCPF_TSQ_DEFERRED)
+ 		tcp_tsq_handler(sk);
+ 
+ 	/* Here begins the tricky part :
+@@ -822,15 +822,15 @@ void tcp_release_cb(struct sock *sk)
+ 	 */
+ 	sock_release_ownership(sk);
+ 
+-	if (flags & (1UL << TCP_WRITE_TIMER_DEFERRED)) {
++	if (flags & TCPF_WRITE_TIMER_DEFERRED) {
+ 		tcp_write_timer_handler(sk);
+ 		__sock_put(sk);
+ 	}
+-	if (flags & (1UL << TCP_DELACK_TIMER_DEFERRED)) {
++	if (flags & TCPF_DELACK_TIMER_DEFERRED) {
+ 		tcp_delack_timer_handler(sk);
+ 		__sock_put(sk);
+ 	}
+-	if (flags & (1UL << TCP_MTU_REDUCED_DEFERRED)) {
++	if (flags & TCPF_MTU_REDUCED_DEFERRED) {
+ 		inet_csk(sk)->icsk_af_ops->mtu_reduced(sk);
+ 		__sock_put(sk);
+ 	}