net: No more expensive sock_hold()/sock_put() on each tx

One of the problem with sock memory accounting is it uses
a pair of sock_hold()/sock_put() for each transmitted packet.

This slows down bidirectional flows because the receive path
also needs to take a refcount on socket and might use a different
cpu than transmit path or transmit completion path. So these
two atomic operations also trigger cache line bounces.

We can see this in tx or tx/rx workloads (media gateways for example),
where sock_wfree() can be in top five functions in profiles.

We use this sock_hold()/sock_put() so that sock freeing
is delayed until all tx packets are completed.

As we also update sk_wmem_alloc, we could offset sk_wmem_alloc
by one unit at init time, until sk_free() is called.
Once sk_free() is called, we atomic_dec_and_test(sk_wmem_alloc)
to decrement initial offset and atomicaly check if any packets
are in flight.

skb_set_owner_w() doesnt call sock_hold() anymore

sock_wfree() doesnt call sock_put() anymore, but check if sk_wmem_alloc
reached 0 to perform the final freeing.

Drawback is that a skb->truesize error could lead to unfreeable sockets, or
even worse, prematurely calling __sk_free() on a live socket.

Nice speedups on SMP. tbench for example, going from 2691 MB/s to 2711 MB/s
on my 8 cpu dev machine, even if tbench was not really hitting sk_refcnt
contention point. 5 % speedup on a UDP transmit workload (depends
on number of flows), lowering TX completion cpu usage.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/sock.h

@@ -1217,9 +1217,13 @@ static inline int skb_copy_to_page(struct sock *sk, char __user *from,
 
 static inline void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
 {
-	sock_hold(sk);
 	skb->sk = sk;
 	skb->destructor = sock_wfree;
+	/*
+	 * We used to take a refcount on sk, but following operation
+	 * is enough to guarantee sk_free() wont free this sock until
+	 * all in-flight packets are completed
+	 */
 	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
 }
 

net/core/sock.c

@@ -1008,7 +1008,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 }
 EXPORT_SYMBOL(sk_alloc);
 
-void sk_free(struct sock *sk)
+static void __sk_free(struct sock *sk)
 {
 	struct sk_filter *filter;
 
@@ -1031,6 +1031,17 @@ void sk_free(struct sock *sk)
 	put_net(sock_net(sk));
 	sk_prot_free(sk->sk_prot_creator, sk);
 }
+
+void sk_free(struct sock *sk)
+{
+	/*
+	 * We substract one from sk_wmem_alloc and can know if
+	 * some packets are still in some tx queue.
+	 * If not null, sock_wfree() will call __sk_free(sk) later
+	 */
+	if (atomic_dec_and_test(&sk->sk_wmem_alloc))
+		__sk_free(sk);
+}
 EXPORT_SYMBOL(sk_free);
 
 /*
@@ -1071,7 +1082,10 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
 		newsk->sk_backlog.head	= newsk->sk_backlog.tail = NULL;
 
 		atomic_set(&newsk->sk_rmem_alloc, 0);
-		atomic_set(&newsk->sk_wmem_alloc, 0);
+		/*
+		 * sk_wmem_alloc set to one (see sk_free() and sock_wfree())
+		 */
+		atomic_set(&newsk->sk_wmem_alloc, 1);
 		atomic_set(&newsk->sk_omem_alloc, 0);
 		skb_queue_head_init(&newsk->sk_receive_queue);
 		skb_queue_head_init(&newsk->sk_write_queue);
@@ -1175,12 +1189,18 @@ void __init sk_init(void)
 void sock_wfree(struct sk_buff *skb)
 {
 	struct sock *sk = skb->sk;
+	int res;
 
 	/* In case it might be waiting for more memory. */
-	atomic_sub(skb->truesize, &sk->sk_wmem_alloc);
+	res = atomic_sub_return(skb->truesize, &sk->sk_wmem_alloc);
 	if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE))
 		sk->sk_write_space(sk);
-	sock_put(sk);
+	/*
+	 * if sk_wmem_alloc reached 0, we are last user and should
+	 * free this sock, as sk_free() call could not do it.
+	 */
+	if (res == 0)
+		__sk_free(sk);
 }
 EXPORT_SYMBOL(sock_wfree);
 
@@ -1819,6 +1839,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	sk->sk_stamp = ktime_set(-1L, 0);
 
 	atomic_set(&sk->sk_refcnt, 1);
+	atomic_set(&sk->sk_wmem_alloc, 1);
 	atomic_set(&sk->sk_drops, 0);
 }
 EXPORT_SYMBOL(sock_init_data);

net/ipv4/ip_output.c

@@ -498,7 +498,6 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 			BUG_ON(frag->sk);
 			if (skb->sk) {
-				sock_hold(skb->sk);
 				frag->sk = skb->sk;
 				frag->destructor = sock_wfree;
 				truesizes += frag->truesize;

net/ipv6/ip6_output.c

@@ -680,7 +680,6 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 
 			BUG_ON(frag->sk);
 			if (skb->sk) {
-				sock_hold(skb->sk);
 				frag->sk = skb->sk;
 				frag->destructor = sock_wfree;
 				truesizes += frag->truesize;