From: Eric Dumazet <eric.dumazet@gmail.com>
To: "David S. Miller" <davem@davemloft.net>
Cc: Linux Netdev List <netdev@vger.kernel.org>,
Lucian Adrian Grijincu <lgrijincu@ixiacom.com>,
Octavian Purdila <opurdila@ixiacom.com>
Subject: [PATCH 5/8] ipv6: udp: optimize unicast RX path
Date: Sun, 08 Nov 2009 21:18:30 +0100 [thread overview]
Message-ID: <4AF72796.3090209@gmail.com> (raw)
We first locate the (local port) hash chain head
If few sockets are in this chain, we proceed with previous lookup algo.
If too many sockets are listed, we take a look at the secondary
(port, address) hash chain.
We choose the shortest chain and proceed with a RCU lookup on the elected chain.
But, if we chose (port, address) chain, and fail to find a socket on given address,
we must try another lookup on (port, in6addr_any) chain to find sockets not bound
to a particular IP.
-> No extra cost for typical setups, where the first lookup will probabbly
be performed.
RCU lookups everywhere, we dont acquire spinlock.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
net/ipv6/udp.c | 112 +++++++++++++++++++++++++++++++++++++++++++++--
1 files changed, 109 insertions(+), 3 deletions(-)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1e5fadd..c5b0451 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -146,6 +146,88 @@ static inline int compute_score(struct sock *sk, struct net *net,
return score;
}
+#define SCORE2_MAX (1 + 1 + 1)
+static inline int compute_score2(struct sock *sk, struct net *net,
+ const struct in6_addr *saddr, __be16 sport,
+ const struct in6_addr *daddr, unsigned short hnum,
+ int dif)
+{
+ int score = -1;
+
+ if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum &&
+ sk->sk_family == PF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct inet_sock *inet = inet_sk(sk);
+
+ if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
+ return -1;
+ score = 0;
+ if (inet->inet_dport) {
+ if (inet->inet_dport != sport)
+ return -1;
+ score++;
+ }
+ if (!ipv6_addr_any(&np->daddr)) {
+ if (!ipv6_addr_equal(&np->daddr, saddr))
+ return -1;
+ score++;
+ }
+ if (sk->sk_bound_dev_if) {
+ if (sk->sk_bound_dev_if != dif)
+ return -1;
+ score++;
+ }
+ }
+ return score;
+}
+
+#define udp_portaddr_for_each_entry_rcu(__sk, node, list) \
+ hlist_nulls_for_each_entry_rcu(__sk, node, list, __sk_common.skc_portaddr_node)
+
+/* called with read_rcu_lock() */
+static struct sock *udp6_lib_lookup2(struct net *net,
+ const struct in6_addr *saddr, __be16 sport,
+ const struct in6_addr *daddr, unsigned int hnum, int dif,
+ struct udp_hslot *hslot2, unsigned int slot2)
+{
+ struct sock *sk, *result;
+ struct hlist_nulls_node *node;
+ int score, badness;
+
+begin:
+ result = NULL;
+ badness = -1;
+ udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) {
+ score = compute_score2(sk, net, saddr, sport,
+ daddr, hnum, dif);
+ if (score > badness) {
+ result = sk;
+ badness = score;
+ if (score == SCORE2_MAX)
+ goto exact_match;
+ }
+ }
+ /*
+ * if the nulls value we got at the end of this lookup is
+ * not the expected one, we must restart lookup.
+ * We probably met an item that was moved to another chain.
+ */
+ if (get_nulls_value(node) != slot2)
+ goto begin;
+
+ if (result) {
+exact_match:
+ if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt)))
+ result = NULL;
+ else if (unlikely(compute_score2(result, net, saddr, sport,
+ daddr, hnum, dif) < badness)) {
+ sock_put(result);
+ goto begin;
+ }
+ }
+ return result;
+}
+
static struct sock *__udp6_lib_lookup(struct net *net,
struct in6_addr *saddr, __be16 sport,
struct in6_addr *daddr, __be16 dport,
@@ -154,11 +236,35 @@ static struct sock *__udp6_lib_lookup(struct net *net,
struct sock *sk, *result;
struct hlist_nulls_node *node;
unsigned short hnum = ntohs(dport);
- unsigned int hash = udp_hashfn(net, hnum, udptable->mask);
- struct udp_hslot *hslot = &udptable->hash[hash];
+ unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
+ struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
int score, badness;
rcu_read_lock();
+ if (hslot->count > 10) {
+ hash2 = udp6_portaddr_hash(net, daddr, hnum);
+ slot2 = hash2 & udptable->mask;
+ hslot2 = &udptable->hash2[slot2];
+ if (hslot->count < hslot2->count)
+ goto begin;
+
+ result = udp6_lib_lookup2(net, saddr, sport,
+ daddr, hnum, dif,
+ hslot2, slot2);
+ if (!result) {
+ hash2 = udp6_portaddr_hash(net, &in6addr_any, hnum);
+ slot2 = hash2 & udptable->mask;
+ hslot2 = &udptable->hash2[slot2];
+ if (hslot->count < hslot2->count)
+ goto begin;
+
+ result = udp6_lib_lookup2(net, &in6addr_any, sport,
+ daddr, hnum, dif,
+ hslot2, slot2);
+ }
+ rcu_read_unlock();
+ return result;
+ }
begin:
result = NULL;
badness = -1;
@@ -174,7 +280,7 @@ begin:
* not the expected one, we must restart lookup.
* We probably met an item that was moved to another chain.
*/
- if (get_nulls_value(node) != hash)
+ if (get_nulls_value(node) != slot)
goto begin;
if (result) {
reply other threads:[~2009-11-08 20:18 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4AF72796.3090209@gmail.com \
--to=eric.dumazet@gmail.com \
--cc=davem@davemloft.net \
--cc=lgrijincu@ixiacom.com \
--cc=netdev@vger.kernel.org \
--cc=opurdila@ixiacom.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).