Merge branch 'tcp-fast-so_reuseport'

Craig Gallek says:

====================
Faster SO_REUSEPORT for TCP

This patch series complements an earlier series (6a5ef90c58da)
which added faster SO_REUSEPORT lookup for UDP sockets by
extending the feature to TCP sockets.  It uses the same
array-based data structure which allows for socket selection
after finding the first listening socket that matches an incoming
packet.  Prior to this feature, every socket in the reuseport
group needed to be found and examined before a selection could be
made.

With this series the SO_ATTACH_REUSEPORT_CBPF and
SO_ATTACH_REUSEPORT_EBPF socket options now work for TCP sockets
as well.  The test at the end of the series includes an example of
how to use these options to select a reuseport socket based on the
cpu core id handling the incoming packet.

There are several refactoring patches that precede the feature
implementation.  Only the last two patches in this series
should result in any behavioral changes.

v4
- Fix build issue when compiling IPv6 as a module.  This required
  moving the ipv6_rcv_saddr_equal into an object that is included as a
  built-in object.  I included this change in the second patch which
  adds inet6_hash since that is where ipv6_rcv_saddr_equal will
  later be called from non-module code.

v3:
- Another warning in the first patch caught by a build bot.  Return 0 in
  the no-op UDP hash function.

v2:
- In the first patched I missed a couple of hash functions that should now be
  returning int instead of void.  I missed these the first time through as it
  only generated a warning and not an error :\
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 15 insertions, 7 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 9b17c1792dce..c16a2e6273d9 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -24,6 +24,7 @@
 #include <net/tcp_states.h>
 #include <net/xfrm.h>
 #include <net/tcp.h>
+#include <net/sock_reuseport.h>
 
 #ifdef INET_CSK_DEBUG
 const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n";
@@ -67,7 +68,8 @@ int inet_csk_bind_conflict(const struct sock *sk,
 			if ((!reuse || !sk2->sk_reuse ||
 			    sk2->sk_state == TCP_LISTEN) &&
 			    (!reuseport || !sk2->sk_reuseport ||
-			    (sk2->sk_state != TCP_TIME_WAIT &&
+			     rcu_access_pointer(sk->sk_reuseport_cb) ||
+			     (sk2->sk_state != TCP_TIME_WAIT &&
 			     !uid_eq(uid, sock_i_uid(sk2))))) {
 
 				if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr ||
@@ -132,6 +134,7 @@ again:
 					      sk->sk_state != TCP_LISTEN) ||
 					     (tb->fastreuseport > 0 &&
 					      sk->sk_reuseport &&
+					      !rcu_access_pointer(sk->sk_reuseport_cb) &&
 					      uid_eq(tb->fastuid, uid))) &&
 					    (tb->num_owners < smallest_size || smallest_size == -1)) {
 						smallest_size = tb->num_owners;
@@ -193,15 +196,18 @@ tb_found:
 		if (((tb->fastreuse > 0 &&
 		      sk->sk_reuse && sk->sk_state != TCP_LISTEN) ||
 		     (tb->fastreuseport > 0 &&
-		      sk->sk_reuseport && uid_eq(tb->fastuid, uid))) &&
-		    smallest_size == -1) {
+		      sk->sk_reuseport &&
+		      !rcu_access_pointer(sk->sk_reuseport_cb) &&
+		      uid_eq(tb->fastuid, uid))) && smallest_size == -1) {
 			goto success;
 		} else {
 			ret = 1;
 			if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true)) {
 				if (((sk->sk_reuse && sk->sk_state != TCP_LISTEN) ||
 				     (tb->fastreuseport > 0 &&
-				      sk->sk_reuseport && uid_eq(tb->fastuid, uid))) &&
+				      sk->sk_reuseport &&
+				      !rcu_access_pointer(sk->sk_reuseport_cb) &&
+				      uid_eq(tb->fastuid, uid))) &&
 				    smallest_size != -1 && --attempts >= 0) {
 					spin_unlock(&head->lock);
 					goto again;
@@ -734,6 +740,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct inet_sock *inet = inet_sk(sk);
+	int err = -EADDRINUSE;
 
 	reqsk_queue_alloc(&icsk->icsk_accept_queue);
 
@@ -751,13 +758,14 @@ int inet_csk_listen_start(struct sock *sk, int backlog)
 		inet->inet_sport = htons(inet->inet_num);
 
 		sk_dst_reset(sk);
-		sk->sk_prot->hash(sk);
+		err = sk->sk_prot->hash(sk);
 
-		return 0;
+		if (likely(!err))
+			return 0;
 	}
 
 	sk->sk_state = TCP_CLOSE;
-	return -EADDRINUSE;
+	return err;
 }
 EXPORT_SYMBOL_GPL(inet_csk_listen_start);