Hi,

mvs@ has completed the final bits to make socket buffer MP safe for
UDP packets.  This means that we can run UDP input on multiple
threads.  Diff below activates this.

Usually IP processing runs on multiple softnet threads with shared
net lock.  From there local packets are queued and processed by one
thread with exclusive net lock.  If the PR_MPINPUT flag is set,
protocol input is called directly from IP input on multiple threads,
shared net lock and no additional queueing.

Note that you need kernel sources from at least Sun Jul 21.  Then
apply this diff and test UDP local delivery to sockets.  To see an
performance effect, you need multiple CPUs and network interfaces
that support multiqueue.  These are bnxt, igc, ix, ixl, ngbe, vmx.

Please test!

bluhm

Index: netinet/in_proto.c
===================================================================
RCS file: /data/mirror/openbsd/cvs/src/sys/netinet/in_proto.c,v
diff -u -p -r1.106 in_proto.c
--- netinet/in_proto.c	13 Jul 2024 12:00:11 -0000	1.106
+++ netinet/in_proto.c	22 Jul 2024 11:40:55 -0000
@@ -185,7 +185,7 @@ const struct protosw inetsw[] = {
   .pr_type	= SOCK_DGRAM,
   .pr_domain	= &inetdomain,
   .pr_protocol	= IPPROTO_UDP,
-  .pr_flags	= PR_ATOMIC|PR_ADDR|PR_SPLICE|PR_MPSOCKET,
+  .pr_flags	= PR_ATOMIC|PR_ADDR|PR_SPLICE|PR_MPINPUT|PR_MPSOCKET,
   .pr_input	= udp_input,
   .pr_ctlinput	= udp_ctlinput,
   .pr_ctloutput	= ip_ctloutput,
Index: netinet6/in6_proto.c
===================================================================
RCS file: /data/mirror/openbsd/cvs/src/sys/netinet6/in6_proto.c,v
diff -u -p -r1.116 in6_proto.c
--- netinet6/in6_proto.c	19 Jul 2024 16:58:32 -0000	1.116
+++ netinet6/in6_proto.c	22 Jul 2024 11:40:55 -0000
@@ -136,7 +136,7 @@ const struct protosw inet6sw[] = {
   .pr_type	= SOCK_DGRAM,
   .pr_domain	= &inet6domain,
   .pr_protocol	= IPPROTO_UDP,
-  .pr_flags	= PR_ATOMIC|PR_ADDR|PR_SPLICE|PR_MPSOCKET,
+  .pr_flags	= PR_ATOMIC|PR_ADDR|PR_SPLICE|PR_MPINPUT|PR_MPSOCKET,
   .pr_input	= udp_input,
   .pr_ctlinput	= udp6_ctlinput,
   .pr_ctloutput	= ip6_ctloutput,