openwrt-owl/target/linux/generic/backport-4.9/024-8-tcp-tsq-move-tsq_flags-close-to-sk_wmem_alloc.patch

From 7aa5470c2c09265902b5e4289afa82e4e7c2987e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 3 Dec 2016 11:14:57 -0800
Subject: [PATCH 08/10] tcp: tsq: move tsq_flags close to sk_wmem_alloc

tsq_flags being in the same cache line than sk_wmem_alloc
makes a lot of sense. Both fields are changed from tcp_wfree()
and more generally by various TSQ related functions.

Prior patch made room in struct sock and added sk_tsq_flags,
this patch deletes tsq_flags from struct tcp_sock.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h   |  1 -
 net/ipv4/tcp.c        |  4 ++--
 net/ipv4/tcp_ipv4.c   |  2 +-
 net/ipv4/tcp_output.c | 24 +++++++++++-------------
 net/ipv4/tcp_timer.c  |  4 ++--
 net/ipv6/tcp_ipv6.c   |  2 +-
 6 files changed, 17 insertions(+), 20 deletions(-)

--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -192,7 +192,6 @@ struct tcp_sock {
 	u32	tsoffset;	/* timestamp offset */
 
 	struct list_head tsq_node; /* anchor in tsq_tasklet.head list */
-	unsigned long	tsq_flags;
 
 	/* Data for direct copy to user */
 	struct {
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -665,9 +665,9 @@ static void tcp_push(struct sock *sk, in
 	if (tcp_should_autocork(sk, skb, size_goal)) {
 
 		/* avoid atomic op if TSQ_THROTTLED bit is already set */
-		if (!test_bit(TSQ_THROTTLED, &tp->tsq_flags)) {
+		if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) {
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING);
-			set_bit(TSQ_THROTTLED, &tp->tsq_flags);
+			set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
 		}
 		/* It is possible TX completion already happened
 		 * before we set TSQ_THROTTLED.
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -446,7 +446,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb
 			if (!sock_owned_by_user(sk)) {
 				tcp_v4_mtu_reduced(sk);
 			} else {
-				if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &tp->tsq_flags))
+				if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &sk->sk_tsq_flags))
 					sock_hold(sk);
 			}
 			goto out;
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -767,14 +767,15 @@ 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;
+		clear_bit(TSQ_QUEUED, &sk->sk_tsq_flags);
+
 		if (!sk->sk_lock.owned &&
-		    test_bit(TCP_TSQ_DEFERRED, &tp->tsq_flags)) {
+		    test_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) {
 			bh_lock_sock(sk);
 			if (!sock_owned_by_user(sk)) {
-				clear_bit(TCP_TSQ_DEFERRED, &tp->tsq_flags);
+				clear_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags);
 				tcp_tsq_handler(sk);
 			}
 			bh_unlock_sock(sk);
@@ -797,16 +798,15 @@ static void tcp_tasklet_func(unsigned lo
  */
 void tcp_release_cb(struct sock *sk)
 {
-	struct tcp_sock *tp = tcp_sk(sk);
 	unsigned long flags, nflags;
 
 	/* perform an atomic operation only if at least one flag is set */
 	do {
-		flags = tp->tsq_flags;
+		flags = sk->sk_tsq_flags;
 		if (!(flags & TCP_DEFERRED_ALL))
 			return;
 		nflags = flags & ~TCP_DEFERRED_ALL;
-	} while (cmpxchg(&tp->tsq_flags, flags, nflags) != flags);
+	} while (cmpxchg(&sk->sk_tsq_flags, flags, nflags) != flags);
 
 	if (flags & TCPF_TSQ_DEFERRED)
 		tcp_tsq_handler(sk);
@@ -878,7 +878,7 @@ void tcp_wfree(struct sk_buff *skb)
 	if (wmem >= SKB_TRUESIZE(1) && this_cpu_ksoftirqd() == current)
 		goto out;
 
-	for (oval = READ_ONCE(tp->tsq_flags);; oval = nval) {
+	for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) {
 		struct tsq_tasklet *tsq;
 		bool empty;
 
@@ -886,7 +886,7 @@ void tcp_wfree(struct sk_buff *skb)
 			goto out;
 
 		nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED | TCPF_TSQ_DEFERRED;
-		nval = cmpxchg(&tp->tsq_flags, oval, nval);
+		nval = cmpxchg(&sk->sk_tsq_flags, oval, nval);
 		if (nval != oval)
 			continue;
 
@@ -2093,7 +2093,7 @@ static bool tcp_small_queue_check(struct
 		    skb->prev == sk->sk_write_queue.next)
 			return false;
 
-		set_bit(TSQ_THROTTLED, &tcp_sk(sk)->tsq_flags);
+		set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
 		/* It is possible TX completion already happened
 		 * before we set TSQ_THROTTLED, so we must
 		 * test again the condition.
@@ -2191,8 +2191,8 @@ 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 (test_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags))
+			clear_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags);
 		if (tcp_small_queue_check(sk, skb, 0))
 			break;
 
@@ -3495,8 +3495,6 @@ void tcp_send_ack(struct sock *sk)
 	/* We do not want pure acks influencing TCP Small Queues or fq/pacing
 	 * too much.
 	 * SKB_TRUESIZE(max(1 .. 66, MAX_TCP_HEADER)) is unfortunately ~784
-	 * We also avoid tcp_wfree() overhead (cache line miss accessing
-	 * tp->tsq_flags) by using regular sock_wfree()
 	 */
 	skb_set_tcp_pure_ack(buff);
 
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -311,7 +311,7 @@ static void tcp_delack_timer(unsigned lo
 		inet_csk(sk)->icsk_ack.blocked = 1;
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
 		/* deleguate our work to tcp_release_cb() */
-		if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags))
+		if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags))
 			sock_hold(sk);
 	}
 	bh_unlock_sock(sk);
@@ -594,7 +594,7 @@ static void tcp_write_timer(unsigned lon
 		tcp_write_timer_handler(sk);
 	} else {
 		/* delegate our work to tcp_release_cb() */
-		if (!test_and_set_bit(TCP_WRITE_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags))
+		if (!test_and_set_bit(TCP_WRITE_TIMER_DEFERRED, &sk->sk_tsq_flags))
 			sock_hold(sk);
 	}
 	bh_unlock_sock(sk);
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -404,7 +404,7 @@ static void tcp_v6_err(struct sk_buff *s
 		if (!sock_owned_by_user(sk))
 			tcp_v6_mtu_reduced(sk);
 		else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED,
-					   &tp->tsq_flags))
+					   &sk->sk_tsq_flags))
 			sock_hold(sk);
 		goto out;
 	}