soreuseport: TCP/IPv4 implementation

Allow multiple listener sockets to bind to the same port.

Motivation for soresuseport would be something like a web server
binding to port 80 running with multiple threads, where each thread
might have it's own listener socket.  This could be done as an
alternative to other models: 1) have one listener thread which
dispatches completed connections to workers. 2) accept on a single
listener socket from multiple threads.  In case #1 the listener thread
can easily become the bottleneck with high connection turn-over rate.
In case #2, the proportion of connections accepted per thread tends
to be uneven under high connection load (assuming simple event loop:
while (1) { accept(); process() }, wakeup does not promote fairness
among the sockets.  We have seen the  disproportion to be as high
as 3:1 ratio between thread accepting most connections and the one
accepting the fewest.  With so_reusport the distribution is
uniform.

Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 11 insertions, 3 deletions

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 67a8fa098e3a..7b2ae9d37076 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -81,7 +81,9 @@ struct inet_bind_bucket {
 	struct net		*ib_net;
 #endif
 	unsigned short		port;
-	signed short		fastreuse;
+	signed char		fastreuse;
+	signed char		fastreuseport;
+	kuid_t			fastuid;
 	int			num_owners;
 	struct hlist_node	node;
 	struct hlist_head	owners;
@@ -257,15 +259,19 @@ extern void inet_unhash(struct sock *sk);
 
 extern struct sock *__inet_lookup_listener(struct net *net,
 					   struct inet_hashinfo *hashinfo,
+					   const __be32 saddr,
+					   const __be16 sport,
 					   const __be32 daddr,
 					   const unsigned short hnum,
 					   const int dif);
 
 static inline struct sock *inet_lookup_listener(struct net *net,
 		struct inet_hashinfo *hashinfo,
+		__be32 saddr, __be16 sport,
 		__be32 daddr, __be16 dport, int dif)
 {
-	return __inet_lookup_listener(net, hashinfo, daddr, ntohs(dport), dif);
+	return __inet_lookup_listener(net, hashinfo, saddr, sport,
+				      daddr, ntohs(dport), dif);
 }
 
 /* Socket demux engine toys. */
@@ -358,7 +364,8 @@ static inline struct sock *__inet_lookup(struct net *net,
 	struct sock *sk = __inet_lookup_established(net, hashinfo,
 				saddr, sport, daddr, hnum, dif);
 
-	return sk ? : __inet_lookup_listener(net, hashinfo, daddr, hnum, dif);
+	return sk ? : __inet_lookup_listener(net, hashinfo, saddr, sport,
+					     daddr, hnum, dif);
 }
 
 static inline struct sock *inet_lookup(struct net *net,
diff --git a/include/net/netfilter/nf_tproxy_core.h b/include/net/netfilter/nf_tproxy_core.h
index 75ca9291cf2c..193796445642 100644
--- a/include/net/netfilter/nf_tproxy_core.h
+++ b/include/net/netfilter/nf_tproxy_core.h
@@ -82,6 +82,7 @@ nf_tproxy_get_sock_v4(struct net *net, const u8 protocol,
 			break;
 		case NFT_LOOKUP_LISTENER:
 			sk = inet_lookup_listener(net, &tcp_hashinfo,
+						    saddr, sport,
 						    daddr, dport,
 						    in->ifindex);