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>
diff --git a/include/net/sock.h b/include/net/sock.h
index 4bb1ff9..010e14a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1217,9 +1217,13 @@
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);
}
diff --git a/net/core/sock.c b/net/core/sock.c
index 04e35eb..06e26b7 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1008,7 +1008,7 @@
}
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 @@
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 @@
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 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 @@
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);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 9248d28..2470262 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -498,7 +498,6 @@
BUG_ON(frag->sk);
if (skb->sk) {
- sock_hold(skb->sk);
frag->sk = skb->sk;
frag->destructor = sock_wfree;
truesizes += frag->truesize;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index db6c722..7c76e3d 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -680,7 +680,6 @@
BUG_ON(frag->sk);
if (skb->sk) {
- sock_hold(skb->sk);
frag->sk = skb->sk;
frag->destructor = sock_wfree;
truesizes += frag->truesize;