[Xen-devel] [PATCH 02/13 V6] remus: implement network buffering hotplug scripts

[Lai Jiangshan <laijs@xxxxxxxxxxxxxx>]

From: Shriram Rajagopalan <rshriram@xxxxxxxxx>

This patch introduces remus-netbuf-setup hotplug script responsible for
setting up and tearing down the necessary infrastructure required for
network output buffering in Remus.  This script is intended to be invoked
by libxl for each guest interface, when starting or stopping Remus.

Apart from returning success/failure indication via the usual hotplug
entries in xenstore, this script also writes to xenstore, the name of
the IFB device to be used to control the vif's network output.

The script relies on libnl3 command line utilities to perform various
setup/teardown functions. The script is confined to Linux platforms only
since NetBSD does not seem to have libnl3.

Signed-off-by: Shriram Rajagopalan <rshriram@xxxxxxxxx>
Signed-off-by: Lai Jiangshan <laijs@xxxxxxxxxxxxxx>
Reviewed-by: Wen Congyang <wency@xxxxxxxxxxxxxx>
---
 tools/hotplug/Linux/Makefile           |   1 +
 tools/hotplug/Linux/remus-netbuf-setup | 183 +++++++++++++++++++++++++++++++++
 2 files changed, 184 insertions(+)
 create mode 100644 tools/hotplug/Linux/remus-netbuf-setup

diff --git a/tools/hotplug/Linux/Makefile b/tools/hotplug/Linux/Makefile
index 47655f6..6139c1f 100644
--- a/tools/hotplug/Linux/Makefile
+++ b/tools/hotplug/Linux/Makefile
@@ -16,6 +16,7 @@ XEN_SCRIPTS += network-nat vif-nat
 XEN_SCRIPTS += vif-openvswitch
 XEN_SCRIPTS += vif2
 XEN_SCRIPTS += vif-setup
+XEN_SCRIPTS-$(CONFIG_REMUS_NETBUF) += remus-netbuf-setup
 XEN_SCRIPTS += block
 XEN_SCRIPTS += block-enbd block-nbd
 XEN_SCRIPTS-$(CONFIG_BLKTAP1) += blktap
diff --git a/tools/hotplug/Linux/remus-netbuf-setup 
b/tools/hotplug/Linux/remus-netbuf-setup
new file mode 100644
index 0000000..3467db2
--- /dev/null
+++ b/tools/hotplug/Linux/remus-netbuf-setup
@@ -0,0 +1,183 @@
+#!/bin/bash
+#============================================================================
+# ${XEN_SCRIPT_DIR}/remus-netbuf-setup
+#
+# Script for attaching a network buffer to the specified vif (in any mode).
+# The hotplugging system will call this script when starting remus via libxl
+# API, libxl_domain_remus_start.
+#
+# Usage:
+# remus-netbuf-setup (setup|teardown)
+#
+# Environment vars:
+# vifname     vif interface name (required).
+# XENBUS_PATH path in Xenstore, where the IFB device details will be stored
+#                      or read from (required).
+#             (libxl passes /libxl/<domid>/remus/netbuf/<devid>)
+# IFB         ifb interface to be cleaned up (required). [for teardown op only]
+
+# Written to the store: (setup operation)
+# XENBUS_PATH/ifb=<ifbdevName> the IFB device serving
+#  as the intermediate buffer through which the interface's network output
+#  can be controlled.
+#
+# To install a network buffer on a guest vif (vif1.0) using ifb (ifb0)
+# we need to do the following
+#
+#  ip link set dev ifb0 up
+#  tc qdisc add dev vif1.0 ingress
+#  tc filter add dev vif1.0 parent ffff: proto ip \
+#    prio 10 u32 match u32 0 0 action mirred egress redirect dev ifb0
+#  nl-qdisc-add --dev=ifb0 --parent root plug
+#  nl-qdisc-add --dev=ifb0 --parent root --update plug --limit=10000000
+#                                                (10MB limit on buffer)
+#
+# So order of operations when installing a network buffer on vif1.0
+# 1. find a free ifb and bring up the device
+# 2. redirect traffic from vif1.0 to ifb:
+#   2.1 add ingress qdisc to vif1.0 (to capture outgoing packets from guest)
+#   2.2 use tc filter command with actions mirred egress + redirect
+# 3. install plug_qdisc on ifb device, with which we can buffer/release
+#    guest's network output from vif1.0
+#
+#
+
+#============================================================================
+
+# Unlike other vif scripts, vif-common is not needed here as it executes vif
+#specific setup code such as renaming.
+dir=$(dirname "$0")
+. "$dir/xen-hotplug-common.sh"
+
+findCommand "$@"
+
+if [ "$command" != "setup" -a  "$command" != "teardown" ]
+then
+  echo "Invalid command: $command"
+  log err "Invalid command: $command"
+  exit 1
+fi
+
+evalVariables "$@"
+
+: ${vifname:?}
+: ${XENBUS_PATH:?}
+
+check_libnl_tools() {
+    if ! command -v nl-qdisc-list > /dev/null 2>&1; then
+        fatal "Unable to find nl-qdisc-list tool"
+    fi
+    if ! command -v nl-qdisc-add > /dev/null 2>&1; then
+        fatal "Unable to find nl-qdisc-add tool"
+    fi
+    if ! command -v nl-qdisc-delete > /dev/null 2>&1; then
+        fatal "Unable to find nl-qdisc-delete tool"
+    fi
+}
+
+# We only check for modules. We don't load them.
+# User/Admin is supposed to load ifb during boot time,
+# ensuring that there are enough free ifbs in the system.
+# Other modules will be loaded automatically by tc commands.
+check_modules() {
+    for m in ifb sch_plug sch_ingress act_mirred cls_u32
+    do
+        if ! modinfo $m > /dev/null 2>&1; then
+            fatal "Unable to find $m kernel module"
+        fi
+    done
+}
+
+setup_ifb() {
+
+    for ifb in `ifconfig -a -s|egrep ^ifb|cut -d ' ' -f1`
+    do
+        local installed=`nl-qdisc-list -d $ifb`
+        [ -n "$installed" ] && continue
+        IFB="$ifb"
+        break
+    done
+
+    if [ -z "$IFB" ]
+    then
+        fatal "Unable to find a free IFB device for $vifname"
+    fi
+
+    do_or_die ip link set dev "$IFB" up
+}
+
+redirect_vif_traffic() {
+    local vif=$1
+    local ifb=$2
+
+    do_or_die tc qdisc add dev "$vif" ingress
+
+    tc filter add dev "$vif" parent ffff: proto ip prio 10 \
+        u32 match u32 0 0 action mirred egress redirect dev "$ifb" >/dev/null 
2>&1
+
+    if [ $? -ne 0 ]
+    then
+        do_without_error tc qdisc del dev "$vif" ingress
+        fatal "Failed to redirect traffic from $vif to $ifb"
+    fi
+}
+
+add_plug_qdisc() {
+    local vif=$1
+    local ifb=$2
+
+    nl-qdisc-add --dev="$ifb" --parent root plug >/dev/null 2>&1
+    if [ $? -ne 0 ]
+    then
+        do_without_error tc qdisc del dev "$vif" ingress
+        fatal "Failed to add plug qdisc to $ifb"
+    fi
+
+    #set ifb buffering limit in bytes. Its okay if this command fails
+    nl-qdisc-add --dev="$ifb" --parent root \
+        --update plug --limit=10000000 >/dev/null 2>&1
+}
+
+teardown_netbuf() {
+    local vif=$1
+    local ifb=$2
+
+    if [ "$ifb" ]; then
+        do_without_error ip link set dev "$ifb" down
+        do_without_error nl-qdisc-delete --dev="$ifb" --parent root plug 
>/dev/null 2>&1
+        xenstore-rm -t "$XENBUS_PATH/ifb" 2>/dev/null || true
+    fi
+    do_without_error tc qdisc del dev "$vif" ingress
+    xenstore-rm -t "$XENBUS_PATH/hotplug-status" 2>/dev/null || true
+}
+
+xs_write_failed() {
+    local vif=$1
+    local ifb=$2
+    teardown_netbuf "$vifname" "$IFB"
+    fatal "failed to write ifb name to xenstore"
+}
+
+case "$command" in
+    setup)
+        check_libnl_tools
+        check_modules
+
+        claim_lock "pickifb"
+        setup_ifb
+        redirect_vif_traffic "$vifname" "$IFB"
+        add_plug_qdisc "$vifname" "$IFB"
+        release_lock "pickifb"
+
+        #not using xenstore_write that automatically exits on error
+        #because we need to cleanup
+        _xenstore_write "$XENBUS_PATH/ifb" "$IFB" || xs_write_failed 
"$vifname" "$IFB"
+        success
+        ;;
+    teardown)
+        : ${IFB:?}
+        teardown_netbuf "$vifname" "$IFB"
+        ;;
+esac
+
+log debug "Successful remus-netbuf-setup $command for $vifname, ifb $IFB."
-- 
1.8.4.2


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel