4 files changed, 272 insertions, 0 deletions

diff --git a/contrib/hyperv/tools/scripts/hyperv_vfattach b/contrib/hyperv/tools/scripts/hyperv_vfattach
new file mode 100644
index 000000000000..e1ed1849f98f
--- /dev/null
+++ b/contrib/hyperv/tools/scripts/hyperv_vfattach
@@ -0,0 +1,79 @@
+#!/bin/sh
+
+#
+# If transparent VF is enabled, don't do anything.
+#
+
+sysctl -n hw.hn.vf_transparent > /dev/null 2>&1
+if [ $? -ne 0 ]
+then
+	# Old kernel; no transparent VF.
+	vf_transparent=0
+else
+	vf_transparent=`sysctl -n hw.hn.vf_transparent`
+fi
+
+if [ $vf_transparent -ne 0 ]
+then
+	# Transparent VF; done!
+	exit 0
+fi
+
+iface=$1
+delay=$2
+
+if [ $delay -gt 0 ]
+then
+	#
+	# Delayed VF up.
+	#
+	sleep $delay
+	ifconfig $iface up
+	# Done!
+	exit $?
+fi
+
+#
+# Check to see whether $iface is a VF or not.
+# If $iface is a VF, bring it up now.
+#
+
+# for hyperv_vf_delay
+. /etc/rc.conf
+
+sysctl -n hw.hn.vflist > /dev/null 2>&1
+if [ $? -ne 0 ]
+then
+	# Old kernel; nothing could be done properly.
+	exit 0
+fi
+vf_list=`sysctl -n hw.hn.vflist`
+
+for vf in $vf_list
+do
+	if [ $vf = $iface ]
+	then
+		#
+		# Linger a little bit (at least 2 seconds) mainly to
+		# make sure that $iface is fully attached.
+		#
+		# NOTE:
+		# In Azure hyperv_vf_delay should be configured to a
+		# large value, e.g. 120 seconds, to avoid racing cloud
+		# agent goofs.
+		#
+		test $hyperv_vf_delay -ge 2 > /dev/null 2>&1
+		if [ $? -ne 0 ]
+		then
+			hyperv_vf_delay=2
+		fi
+		#
+		# NOTE:
+		# "(sleep ..; ifconfig .. up) > /dev/null 2>&1 &"
+		# does _not_ work.
+		#
+		daemon -f /usr/libexec/hyperv/hyperv_vfattach \
+		    $iface $hyperv_vf_delay
+		break
+	fi
+done
diff --git a/contrib/hyperv/tools/scripts/hyperv_vfup b/contrib/hyperv/tools/scripts/hyperv_vfup
new file mode 100644
index 000000000000..7a2bc595c212
--- /dev/null
+++ b/contrib/hyperv/tools/scripts/hyperv_vfup
@@ -0,0 +1,119 @@
+#!/bin/sh
+
+. /etc/rc.subr
+. /etc/network.subr
+
+load_rc_config netif
+
+#
+# Customized per-interface setup, e.g. hyperv_vfup.hn1
+#
+# NOTE-CUSTOMIZE:
+# Comment this out, if this script is used as template
+# for the customized per-interface setup.
+#
+if [ -f /usr/libexec/hyperv/hyperv_vfup.$1 ]
+then
+	/usr/libexec/hyperv/hyperv_vfup.$1
+	exit $?
+fi
+
+# NOTE-CUSTOMIZE:
+#hn=${0##*.}
+hn=$1
+hn_unit=`echo $hn | sed 's/[^0-9]*//g'`
+
+vf=`sysctl -n dev.hn.$hn_unit.vf`
+if [ ! $vf ]
+then
+	# Race happened; VF was removed, before we ran.
+	echo "$hn: VF was detached"
+	exit 0
+fi
+
+#
+# Create laggX for hnX.
+# Add VF and hnX to laggX.
+#
+
+lagg=lagg$hn_unit
+
+ifconfig $lagg > /dev/null 2>&1
+if [ $? -ne 0 ]
+then
+	#
+	# No laggX, create it now.
+	#
+	ifconfig $lagg create > /dev/null 2>&1
+	if [ $? -ne 0 ]
+	then
+		echo "$lagg creation failed"
+		exit 1
+	fi
+
+	#
+	# Configure laggX (failover), add hnX and VF to it.
+	#
+	ifconfig $lagg laggproto failover laggport $hn laggport $vf
+	ifconfig $lagg inet6 no_dad
+
+	#
+	# Stop dhclient on hnX, if any.
+	#
+	pidfile=/var/run/dhclient.$hn.pid
+	if [ -f $pidfile ]
+	then
+		kill -TERM `cat $pidfile`
+	fi
+
+	#
+	# Remove all configured IPv4 addresses on hnX, e.g.
+	# configured by dhclient.  laggX will take over the
+	# network operations.
+	#
+	while true
+	do
+		ifconfig $hn -alias > /dev/null 2>&1
+		if [ $? -ne 0 ]
+		then
+			break
+		fi
+	done
+
+	# TODO: Remove IPv6 addresses on hnX
+
+	#
+	# Use hnX's configuration for laggX
+	#
+	# NOTE-CUSTOMIZE:
+	# If this script is used as template for the customized
+	# per-interface setup, replace this with whatever you
+	# want to do with the laggX.
+	#
+	if dhcpif $hn;
+	then
+		ifconfig $lagg up
+		if syncdhcpif $hn;
+		then
+			dhclient $lagg
+		else
+			dhclient -b $lagg
+		fi
+	else
+		ifconfig_args=`ifconfig_getargs $hn`
+		if [ -n "$ifconfig_args" ]
+		then
+			ifconfig $lagg $ifconfig_args
+		fi
+	fi
+else
+	#
+	# laggX exists.  Check whether VF was there or not.
+	# If VF was not added to laggX, add it now.
+	#
+	ifconfig $lagg | grep "laggport: $vf" > /dev/null 2>&1
+	if [ $? -ne 0 ]
+	then
+		ifconfig $lagg laggport $vf
+	fi
+fi
diff --git a/etc/devd/hyperv.conf b/etc/devd/hyperv.conf
index 0abf284a9ce0..10a4e2b9e5ce 100644
--- a/etc/devd/hyperv.conf
+++ b/etc/devd/hyperv.conf
@@ -33,3 +33,76 @@ notify 11 {
 	match "cdev"		"hv_fsvss_dev";
 	action "pkill -x hv_vss_daemon";
 };
+
+#
+# Rules for non-transparent network VF.
+#
+# How network VF works with hn(4) on Hyper-V in non-transparent mode:
+#
+# - Each network VF has a cooresponding hn(4).
+# - The network VF and the it's cooresponding hn(4) have the same hardware
+#   address.
+# - Once the network VF is up, e.g. ifconfig VF up:
+#   o  All of the transmission should go through the network VF.
+#   o  Most of the reception goes through the network VF.
+#   o  Small amount of reception may go through the cooresponding hn(4).
+#      This reception will happen, even if the the cooresponding hn(4) is
+#      down.  The cooresponding hn(4) will change the reception interface
+#      to the network VF, so that network layer and application layer will
+#      be tricked into thinking that these packets were received by the
+#      network VF.
+#   o  The cooresponding hn(4) pretends the physical link is down.
+# - Once the network VF is down or detached:
+#   o  All of the transmission should go through the cooresponding hn(4).
+#   o  All of the reception goes through the cooresponding hn(4).
+#   o  The cooresponding hn(4) fallbacks to the original physical link
+#      detection logic.
+#
+# All these features are mainly used to help live migration, during which
+# the network VF will be detached, while the network communication to the
+# VM must not be cut off.  In order to reach this level of live migration
+# transparency, we use failover mode lagg(4) with the network VF and the
+# cooresponding hn(4) attached to it.
+#
+# To ease user configuration for both network VF and non-network VF, the
+# lagg(4) will be created by the following rules, and the configuration
+# of the cooresponding hn(4) will be applied to the lagg(4) automatically.
+#
+# NOTE:
+# If live migration is not needed at all, the following rules could be
+# commented out, and the network VF interface could be used exclusively.
+# Most often the cooresponding hn(4) could be completely ignored.
+#
+#
+# Default workflow for the network VF bringup:
+# 1) ETHERNET/IFATTACH -> VF interface up (delayed by rc.conf hyperv_vf_delay
+#    seconds).  This operation will trigger HYPERV_NIC_VF/VF_UP.
+# 2) HYPERV_NIC_VF/VF_UP:
+#    a) Create laggX coresponding to hnX.
+#    b) Add hnX and VF to laggX.
+#    c) Whack all previous network configuration on hnX, including stopping
+#       dhclient.
+#    d) Apply rc.conf ifconfig_hnX to laggX; i.e. including starting dhclient.
+#
+# NOTE:
+# HYPERV_NIC_VF/VF_UP action script could be customized per-interface by
+# adding /usr/libexec/hyperv/hyperv_vfup.hnX script.
+# /usr/libexec/hyperv/hyperv_vfup could be used as the template for the
+# customized per-interface script.
+#
+# NOTE:
+# For transparent network VF, hyperv_vfattach does nothing and
+# HYPERV_NIC_VF/VF_UP will not be triggered at all.
+#
+
+notify 10 {
+	match "system"		"HYPERV_NIC_VF";
+	match "type"		"VF_UP";
+	action "/usr/libexec/hyperv/hyperv_vfup $subsystem";
+};
+
+notify 10 {
+	match "system"		"ETHERNET";
+	match "type"		"IFATTACH";
+	action "/usr/libexec/hyperv/hyperv_vfattach $subsystem 0";
+};
diff --git a/libexec/hyperv/Makefile b/libexec/hyperv/Makefile
index a89b7435d2e5..6e251b24faa7 100644
--- a/libexec/hyperv/Makefile
+++ b/libexec/hyperv/Makefile
@@ -5,5 +5,6 @@
 BINDIR=		${LIBEXECDIR}/hyperv
 
 SCRIPTS=	hv_set_ifconfig hv_get_dns_info hv_get_dhcp_info
+SCRIPTS+=	hyperv_vfattach hyperv_vfup
 
 .include <bsd.prog.mk>