Commit 421b3885 authored by Shawn Bohrer's avatar Shawn Bohrer Committed by David S. Miller

udp: ipv4: Add udp early demux

The removal of the routing cache introduced a performance regression for
some UDP workloads since a dst lookup must be done for each packet.
This change caches the dst per socket in a similar manner to what we do
for TCP by implementing early_demux.

For UDP multicast we can only cache the dst if there is only one
receiving socket on the host.  Since caching only works when there is
one receiving socket we do the multicast socket lookup using RCU.

For UDP unicast we only demux sockets with an exact match in order to
not break forwarding setups.  Additionally since the hash chains may be
long we only check the first socket to see if it is a match and not
waste extra time searching the whole chain when we might not find an
exact match.

Benchmark results from a netperf UDP_RR test:
Before 87961.22 transactions/s
After  89789.68 transactions/s

Benchmark results from a fio 1 byte UDP multicast pingpong test
(Multicast one way unicast response):
Before 12.97us RTT
After  12.63us RTT
Signed-off-by: default avatarShawn Bohrer <sbohrer@rgmadvisors.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 005ec974
...@@ -218,7 +218,7 @@ struct cg_proto; ...@@ -218,7 +218,7 @@ struct cg_proto;
* @sk_lock: synchronizer * @sk_lock: synchronizer
* @sk_rcvbuf: size of receive buffer in bytes * @sk_rcvbuf: size of receive buffer in bytes
* @sk_wq: sock wait queue and async head * @sk_wq: sock wait queue and async head
* @sk_rx_dst: receive input route used by early tcp demux * @sk_rx_dst: receive input route used by early demux
* @sk_dst_cache: destination cache * @sk_dst_cache: destination cache
* @sk_dst_lock: destination cache lock * @sk_dst_lock: destination cache lock
* @sk_policy: flow policy * @sk_policy: flow policy
......
...@@ -175,6 +175,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, ...@@ -175,6 +175,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
unsigned int hash2_nulladdr); unsigned int hash2_nulladdr);
/* net/ipv4/udp.c */ /* net/ipv4/udp.c */
void udp_v4_early_demux(struct sk_buff *skb);
int udp_get_port(struct sock *sk, unsigned short snum, int udp_get_port(struct sock *sk, unsigned short snum,
int (*saddr_cmp)(const struct sock *, int (*saddr_cmp)(const struct sock *,
const struct sock *)); const struct sock *));
......
...@@ -1546,6 +1546,7 @@ static const struct net_protocol tcp_protocol = { ...@@ -1546,6 +1546,7 @@ static const struct net_protocol tcp_protocol = {
}; };
static const struct net_protocol udp_protocol = { static const struct net_protocol udp_protocol = {
.early_demux = udp_v4_early_demux,
.handler = udp_rcv, .handler = udp_rcv,
.err_handler = udp_err, .err_handler = udp_err,
.no_policy = 1, .no_policy = 1,
......
...@@ -103,6 +103,7 @@ ...@@ -103,6 +103,7 @@
#include <linux/seq_file.h> #include <linux/seq_file.h>
#include <net/net_namespace.h> #include <net/net_namespace.h>
#include <net/icmp.h> #include <net/icmp.h>
#include <net/inet_hashtables.h>
#include <net/route.h> #include <net/route.h>
#include <net/checksum.h> #include <net/checksum.h>
#include <net/xfrm.h> #include <net/xfrm.h>
...@@ -565,6 +566,26 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, ...@@ -565,6 +566,26 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
} }
EXPORT_SYMBOL_GPL(udp4_lib_lookup); EXPORT_SYMBOL_GPL(udp4_lib_lookup);
static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
__be16 loc_port, __be32 loc_addr,
__be16 rmt_port, __be32 rmt_addr,
int dif, unsigned short hnum)
{
struct inet_sock *inet = inet_sk(sk);
if (!net_eq(sock_net(sk), net) ||
udp_sk(sk)->udp_port_hash != hnum ||
(inet->inet_daddr && inet->inet_daddr != rmt_addr) ||
(inet->inet_dport != rmt_port && inet->inet_dport) ||
(inet->inet_rcv_saddr && inet->inet_rcv_saddr != loc_addr) ||
ipv6_only_sock(sk) ||
(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif))
return false;
if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif))
return false;
return true;
}
static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk, static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk,
__be16 loc_port, __be32 loc_addr, __be16 loc_port, __be32 loc_addr,
__be16 rmt_port, __be32 rmt_addr, __be16 rmt_port, __be32 rmt_addr,
...@@ -575,20 +596,11 @@ static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk, ...@@ -575,20 +596,11 @@ static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk,
unsigned short hnum = ntohs(loc_port); unsigned short hnum = ntohs(loc_port);
sk_nulls_for_each_from(s, node) { sk_nulls_for_each_from(s, node) {
struct inet_sock *inet = inet_sk(s); if (__udp_is_mcast_sock(net, s,
loc_port, loc_addr,
if (!net_eq(sock_net(s), net) || rmt_port, rmt_addr,
udp_sk(s)->udp_port_hash != hnum || dif, hnum))
(inet->inet_daddr && inet->inet_daddr != rmt_addr) || goto found;
(inet->inet_dport != rmt_port && inet->inet_dport) ||
(inet->inet_rcv_saddr &&
inet->inet_rcv_saddr != loc_addr) ||
ipv6_only_sock(s) ||
(s->sk_bound_dev_if && s->sk_bound_dev_if != dif))
continue;
if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif))
continue;
goto found;
} }
s = NULL; s = NULL;
found: found:
...@@ -1581,6 +1593,14 @@ static void flush_stack(struct sock **stack, unsigned int count, ...@@ -1581,6 +1593,14 @@ static void flush_stack(struct sock **stack, unsigned int count,
kfree_skb(skb1); kfree_skb(skb1);
} }
static void udp_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
dst_hold(dst);
sk->sk_rx_dst = dst;
}
/* /*
* Multicasts and broadcasts go to each listener. * Multicasts and broadcasts go to each listener.
* *
...@@ -1709,11 +1729,28 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, ...@@ -1709,11 +1729,28 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
if (udp4_csum_init(skb, uh, proto)) if (udp4_csum_init(skb, uh, proto))
goto csum_error; goto csum_error;
if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) if (skb->sk) {
return __udp4_lib_mcast_deliver(net, skb, uh, int ret;
saddr, daddr, udptable); sk = skb->sk;
sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (unlikely(sk->sk_rx_dst == NULL))
udp_sk_rx_dst_set(sk, skb);
ret = udp_queue_rcv_skb(sk, skb);
/* a return value > 0 means to resubmit the input, but
* it wants the return to be -protocol, or 0
*/
if (ret > 0)
return -ret;
return 0;
} else {
if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
return __udp4_lib_mcast_deliver(net, skb, uh,
saddr, daddr, udptable);
sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
}
if (sk != NULL) { if (sk != NULL) {
int ret; int ret;
...@@ -1771,6 +1808,135 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, ...@@ -1771,6 +1808,135 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
return 0; return 0;
} }
/* We can only early demux multicast if there is a single matching socket.
* If more than one socket found returns NULL
*/
static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
__be16 loc_port, __be32 loc_addr,
__be16 rmt_port, __be32 rmt_addr,
int dif)
{
struct sock *sk, *result;
struct hlist_nulls_node *node;
unsigned short hnum = ntohs(loc_port);
unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask);
struct udp_hslot *hslot = &udp_table.hash[slot];
rcu_read_lock();
begin:
count = 0;
result = NULL;
sk_nulls_for_each_rcu(sk, node, &hslot->head) {
if (__udp_is_mcast_sock(net, sk,
loc_port, loc_addr,
rmt_port, rmt_addr,
dif, hnum)) {
result = sk;
++count;
}
}
/*
* 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) != slot)
goto begin;
if (result) {
if (count != 1 ||
unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
result = NULL;
else if (unlikely(!__udp_is_mcast_sock(net, sk,
loc_port, loc_addr,
rmt_port, rmt_addr,
dif, hnum))) {
sock_put(result);
result = NULL;
}
}
rcu_read_unlock();
return result;
}
/* For unicast we should only early demux connected sockets or we can
* break forwarding setups. The chains here can be long so only check
* if the first socket is an exact match and if not move on.
*/
static struct sock *__udp4_lib_demux_lookup(struct net *net,
__be16 loc_port, __be32 loc_addr,
__be16 rmt_port, __be32 rmt_addr,
int dif)
{
struct sock *sk, *result;
struct hlist_nulls_node *node;
unsigned short hnum = ntohs(loc_port);
unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum);
unsigned int slot2 = hash2 & udp_table.mask;
struct udp_hslot *hslot2 = &udp_table.hash2[slot2];
INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr)
const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum);
rcu_read_lock();
result = NULL;
udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) {
if (INET_MATCH(sk, net, acookie,
rmt_addr, loc_addr, ports, dif))
result = sk;
/* Only check first socket in chain */
break;
}
if (result) {
if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2)))
result = NULL;
else if (unlikely(!INET_MATCH(sk, net, acookie,
rmt_addr, loc_addr,
ports, dif))) {
sock_put(result);
result = NULL;
}
}
rcu_read_unlock();
return result;
}
void udp_v4_early_demux(struct sk_buff *skb)
{
const struct iphdr *iph = ip_hdr(skb);
const struct udphdr *uh = udp_hdr(skb);
struct sock *sk;
struct dst_entry *dst;
struct net *net = dev_net(skb->dev);
int dif = skb->dev->ifindex;
/* validate the packet */
if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
return;
if (skb->pkt_type == PACKET_BROADCAST ||
skb->pkt_type == PACKET_MULTICAST)
sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
uh->source, iph->saddr, dif);
else if (skb->pkt_type == PACKET_HOST)
sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
uh->source, iph->saddr, dif);
else
return;
if (!sk)
return;
skb->sk = sk;
skb->destructor = sock_edemux;
dst = sk->sk_rx_dst;
if (dst)
dst = dst_check(dst, 0);
if (dst)
skb_dst_set_noref(skb, dst);
}
int udp_rcv(struct sk_buff *skb) int udp_rcv(struct sk_buff *skb)
{ {
return __udp4_lib_rcv(skb, &udp_table, IPPROTO_UDP); return __udp4_lib_rcv(skb, &udp_table, IPPROTO_UDP);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment