net: speedup udp receive path
Since commit 95766fff ([UDP]: Add memory accounting.),
each received packet needs one extra sock_lock()/sock_release() pair.
This added latency because of possible backlog handling. Then later,
ticket spinlocks added yet another latency source in case of DDOS.
This patch introduces lock_sock_bh() and unlock_sock_bh()
synchronization primitives, avoiding one atomic operation and backlog
processing.
skb_free_datagram_locked() uses them instead of full blown
lock_sock()/release_sock(). skb is orphaned inside locked section for
proper socket memory reclaim, and finally freed outside of it.
UDP receive path now take the socket spinlock only once.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 3ead20a..91c60f0 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -424,7 +424,7 @@
return err;
csum_copy_err:
- lock_sock(sk);
+ lock_sock_bh(sk);
if (!skb_kill_datagram(sk, skb, flags)) {
if (is_udp4)
UDP_INC_STATS_USER(sock_net(sk),
@@ -433,7 +433,7 @@
UDP6_INC_STATS_USER(sock_net(sk),
UDP_MIB_INERRORS, is_udplite);
}
- release_sock(sk);
+ unlock_sock_bh(sk);
if (flags & MSG_DONTWAIT)
return -EAGAIN;