inetpeer: Optimize inet_getid()

While investigating for network latencies, I found inet_getid() was a
contention point for some workloads, as inet_peer_idlock is shared
by all inet_getid() users regardless of peers.

One way to fix this is to make ip_id_count an atomic_t instead
of __u16, and use atomic_add_return().

In order to keep sizeof(struct inet_peer) = 64 on 64bit arches
tcp_ts_stamp is also converted to __u32 instead of "unsigned long".

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 35ad7b9..87b1df0 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -17,15 +17,15 @@
 	/* group together avl_left,avl_right,v4daddr to speedup lookups */
 	struct inet_peer	*avl_left, *avl_right;
 	__be32			v4daddr;	/* peer's address */
-	__u16			avl_height;
-	__u16			ip_id_count;	/* IP ID for the next packet */
+	__u32			avl_height;
 	struct list_head	unused;
 	__u32			dtime;		/* the time of last use of not
 						 * referenced entries */
 	atomic_t		refcnt;
 	atomic_t		rid;		/* Frag reception counter */
+	atomic_t		ip_id_count;	/* IP ID for the next packet */
 	__u32			tcp_ts;
-	unsigned long		tcp_ts_stamp;
+	__u32			tcp_ts_stamp;
 };
 
 void			inet_initpeers(void) __init;
@@ -36,17 +36,11 @@
 /* can be called from BH context or outside */
 extern void inet_putpeer(struct inet_peer *p);
 
-extern spinlock_t inet_peer_idlock;
 /* can be called with or without local BH being disabled */
 static inline __u16	inet_getid(struct inet_peer *p, int more)
 {
-	__u16 id;
-
-	spin_lock_bh(&inet_peer_idlock);
-	id = p->ip_id_count;
-	p->ip_id_count += 1 + more;
-	spin_unlock_bh(&inet_peer_idlock);
-	return id;
+	more++;
+	return atomic_add_return(more, &p->ip_id_count) - more;
 }
 
 #endif /* _NET_INETPEER_H */