[NET]: Keep sk_backlog near sk_lock

sk_backlog is a critical field of struct sock. (known famous words)

It is (ab)used in hot paths, in particular in release_sock(), tcp_recvmsg(),
tcp_v4_rcv(), sk_receive_skb().

It really makes sense to place it next to sk_lock, because sk_backlog is only
used after sk_lock locked (and thus memory cache line in L1 cache). This
should reduce cache misses and sk_lock acquisition time.

(In theory, we could only move the head pointer near sk_lock, and leaving tail
far away, because 'tail' is normally not so hot, but keep it simple :) )

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 10 insertions, 10 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index 2c7d60c..a3366c3 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -202,6 +202,15 @@ struct sock {
 	unsigned short		sk_type;
 	int			sk_rcvbuf;
 	socket_lock_t		sk_lock;
+	/*
+	 * The backlog queue is special, it is always used with
+	 * the per-socket spinlock held and requires low latency
+	 * access. Therefore we special case it's implementation.
+	 */
+	struct {
+		struct sk_buff *head;
+		struct sk_buff *tail;
+	} sk_backlog;
 	wait_queue_head_t	*sk_sleep;
 	struct dst_entry	*sk_dst_cache;
 	struct xfrm_policy	*sk_policy[2];
@@ -221,15 +230,6 @@ struct sock {
 	int			sk_rcvlowat;
 	unsigned long 		sk_flags;
 	unsigned long	        sk_lingertime;
-	/*
-	 * The backlog queue is special, it is always used with
-	 * the per-socket spinlock held and requires low latency
-	 * access. Therefore we special case it's implementation.
-	 */
-	struct {
-		struct sk_buff *head;
-		struct sk_buff *tail;
-	} sk_backlog;
 	struct sk_buff_head	sk_error_queue;
 	struct proto		*sk_prot_creator;
 	rwlock_t		sk_callback_lock;
diff --git a/net/core/sock.c b/net/core/sock.c
index 27c4f62..6d35d57 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -904,6 +904,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
 		sk_node_init(&newsk->sk_node);
 		sock_lock_init(newsk);
 		bh_lock_sock(newsk);
+		newsk->sk_backlog.head	= newsk->sk_backlog.tail = NULL;
 
 		atomic_set(&newsk->sk_rmem_alloc, 0);
 		atomic_set(&newsk->sk_wmem_alloc, 0);
@@ -923,7 +924,6 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
 		newsk->sk_wmem_queued	= 0;
 		newsk->sk_forward_alloc = 0;
 		newsk->sk_send_head	= NULL;
-		newsk->sk_backlog.head	= newsk->sk_backlog.tail = NULL;
 		newsk->sk_userlocks	= sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;
 
 		sock_reset_flag(newsk, SOCK_DONE);