summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorHerbert Xu <herbert@gondor.apana.org.au>2011-03-01 02:36:48 +0000
committerDavid S. Miller <davem@davemloft.net>2011-03-01 12:35:42 -0800
commit903ab86d195cca295379699299c5fc10beba31c7 (patch)
tree2b73fe727bf843bf0a0629dce044da61dc9cb166
parentf6b9664f8b711cf4fd53e70aa0d21f72d5bf806c (diff)
udp: Add lockless transmit path
The UDP transmit path has been running under the socket lock for a long time because of the corking feature. This means that transmitting to the same socket in multiple threads does not scale at all. However, as most users don't actually use corking, the locking can be removed in the common case. This patch creates a lockless fast path where corking is not used. Please note that this does create a slight inaccuracy in the enforcement of socket send buffer limits. In particular, we may exceed the socket limit by up to (number of CPUs) * (packet size) because of the way the limit is computed. As the primary purpose of socket buffers is to indicate congestion, this should not be a great problem for now. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r--net/ipv4/udp.c15
1 files changed, 14 insertions, 1 deletions
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 61c22ee7d4ba..8155d6eda376 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -802,6 +802,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
int err, is_udplite = IS_UDPLITE(sk);
int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
+ struct sk_buff *skb;
if (len > 0xFFFF)
return -EMSGSIZE;
@@ -816,6 +817,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
ipc.opt = NULL;
ipc.tx_flags = 0;
+ getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
+
if (up->pending) {
/*
* There are pending frames.
@@ -940,6 +943,17 @@ back_from_confirm:
if (!ipc.addr)
daddr = ipc.addr = rt->rt_dst;
+ /* Lockless fast path for the non-corking case. */
+ if (!corkreq) {
+ skb = ip_make_skb(sk, getfrag, msg->msg_iov, ulen,
+ sizeof(struct udphdr), &ipc, &rt,
+ msg->msg_flags);
+ err = PTR_ERR(skb);
+ if (skb && !IS_ERR(skb))
+ err = udp_send_skb(skb, daddr, dport);
+ goto out;
+ }
+
lock_sock(sk);
if (unlikely(up->pending)) {
/* The socket is already corked while preparing it. */
@@ -961,7 +975,6 @@ back_from_confirm:
do_append_data:
up->len += ulen;
- getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
err = ip_append_data(sk, getfrag, msg->msg_iov, ulen,
sizeof(struct udphdr), &ipc, &rt,
corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);