#!/bin/sh
# Cero3 Shaper
# A 3 bin tc_codel and ipv6 enabled shaping script for
# ethernet gateways

# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
#
#       Copyright (C) 2012-4 Michael D. Taht, Toke Høiland-Jørgensen, Sebastian Moeller

# Compared to the complexity that debloat had become
# this cleanly shows a means of going from diffserv marking
# to prioritization using the current tools (ip(6)tables
# and tc. I note that the complexity of debloat exists for
# a reason, and it is expected that script is run first
# to setup various other parameters such as BQL and ethtool.
# (And that the debloat script has setup the other interfaces)

# You need to jiggle these parameters. Note limits are tuned towards a <10Mbit uplink <60Mbup down

. /usr/lib/sqm/functions.sh

ipt_setup() {

ipt -t mangle -N QOS_MARK_${IFACE}

ipt -t mangle -A QOS_MARK_${IFACE} -j MARK --set-mark 0x2${IPT_MASK_STRING}
# You can go further with classification but...
ipt -t mangle -A QOS_MARK_${IFACE} -m dscp --dscp-class CS1 -j MARK --set-mark 0x3${IPT_MASK_STRING}
ipt -t mangle -A QOS_MARK_${IFACE} -m dscp --dscp-class CS6 -j MARK --set-mark 0x1${IPT_MASK_STRING}
ipt -t mangle -A QOS_MARK_${IFACE} -m dscp --dscp-class EF -j MARK --set-mark 0x1${IPT_MASK_STRING}
ipt -t mangle -A QOS_MARK_${IFACE} -m dscp --dscp-class AF42 -j MARK --set-mark 0x1${IPT_MASK_STRING}
ipt -t mangle -A QOS_MARK_${IFACE} -m tos  --tos Minimize-Delay -j MARK --set-mark 0x1${IPT_MASK_STRING}

# and it might be a good idea to do it for udp tunnels too

# Turn it on. Preserve classification if already performed

#sm: is it correct to do this in $IFACE? Should ingress not be on $DEV? since HTB acts on $DEV?
#	SQUASH also does not work on $DEV (that is the IFB will still see the incoming ToS bits whether we squash or not)
#	SQUASH is still useful to protect internal machines...
if [ "$SQUASH_DSCP" = "1" ]
then
sqm_logger "Squashing differentiated services code points (DSCP) from ingress."
ipt -t mangle -I PREROUTING -i $IFACE -m dscp ! --dscp 0 -j DSCP --set-dscp-class be
else
sqm_logger "Keeping differentiated services code points (DSCP) from ingress."
ipt -t mangle -A PREROUTING -i $IFACE -m mark --mark 0x00${IPT_MASK_STRING} -g QOS_MARK_${IFACE} 
fi

ipt -t mangle -A POSTROUTING -o $IFACE -m mark --mark 0x00${IPT_MASK_STRING} -g QOS_MARK_${IFACE} 

# The Syn optimization was nice but fq_codel does it for us
# ipt -t mangle -A PREROUTING -i s+ -p tcp -m tcp --tcp-flags SYN,RST,ACK SYN -j MARK --set-mark 0x01
# Not sure if this will work. Encapsulation is a problem period

ipt -t mangle -I PREROUTING -i vtun+ -p tcp -j MARK --set-mark 0x2${IPT_MASK_STRING} # tcp tunnels need ordering

# Emanating from router, do a little more optimization
# but don't bother with it too much. 

ipt -t mangle -A OUTPUT -p udp -m multiport --ports 123,53 -j DSCP --set-dscp-class AF42

#Not clear if the second line is needed
#ipt -t mangle -A OUTPUT -o $IFACE -g QOS_MARK_${IFACE}

}


# TC rules

egress() {

CEIL=${UPLINK}
PRIO_RATE=`expr $CEIL / 3` # Ceiling for prioirty
BE_RATE=`expr $CEIL / 6`   # Min for best effort
BK_RATE=`expr $CEIL / 6`   # Min for background
BE_CEIL=`expr $CEIL - 16`  # A little slop at the top

LQ="quantum `get_mtu $IFACE $CEIL`"

$TC qdisc del dev $IFACE root 2> /dev/null
$TC qdisc add dev $IFACE root handle 1: `get_stab_string` htb default 12
$TC class add dev $IFACE parent 1: classid 1:1 htb $LQ rate ${CEIL}kbit ceil ${CEIL}kbit `get_htb_adsll_string`
$TC class add dev $IFACE parent 1:1 classid 1:10 htb $LQ rate ${CEIL}kbit ceil ${CEIL}kbit prio 0 `get_htb_adsll_string`
$TC class add dev $IFACE parent 1:1 classid 1:11 htb $LQ rate 128kbit ceil ${PRIO_RATE}kbit prio 1 `get_htb_adsll_string`
$TC class add dev $IFACE parent 1:1 classid 1:12 htb $LQ rate ${BE_RATE}kbit ceil ${BE_CEIL}kbit prio 2 `get_htb_adsll_string`
$TC class add dev $IFACE parent 1:1 classid 1:13 htb $LQ rate ${BK_RATE}kbit ceil ${BE_CEIL}kbit prio 3 `get_htb_adsll_string`

$TC qdisc add dev $IFACE parent 1:11 handle 110: $QDISC `get_limit ${ELIMIT}` `get_target "${ETARGET}" ${UPLINK}` `get_ecn ${EECN}` `get_quantum 300` `get_flows ${PRIO_RATE}` ${EQDISC_OPTS}
$TC qdisc add dev $IFACE parent 1:12 handle 120: $QDISC `get_limit ${ELIMIT}` `get_target "${ETARGET}" ${UPLINK}` `get_ecn ${EECN}` `get_quantum 300` `get_flows ${BE_RATE}` ${EQDISC_OPTS}
$TC qdisc add dev $IFACE parent 1:13 handle 130: $QDISC `get_limit ${ELIMIT}` `get_target "${ETARGET}" ${UPLINK}` `get_ecn ${EECN}` `get_quantum 300` `get_flows ${BK_RATE}` ${EQDISC_OPTS}


# Need a catchall rule

$TC filter add dev $IFACE parent 1:0 protocol all prio 999 u32 \
        match ip protocol 0 0x00 flowid 1:12  

# FIXME should probably change the filter here to do pre-nat
        
$TC filter add dev $IFACE parent 1:0 protocol ip prio 1 handle 1 fw classid 1:11
$TC filter add dev $IFACE parent 1:0 protocol ip prio 2 handle 2 fw classid 1:12
$TC filter add dev $IFACE parent 1:0 protocol ip prio 3 handle 3 fw classid 1:13

# ipv6 support. Note that the handle indicates the fw mark bucket that is looked for

$TC filter add dev $IFACE parent 1:0 protocol ipv6 prio 4 handle 1 fw classid 1:11
$TC filter add dev $IFACE parent 1:0 protocol ipv6 prio 5 handle 2 fw classid 1:12
$TC filter add dev $IFACE parent 1:0 protocol ipv6 prio 6 handle 3 fw classid 1:13

# Arp traffic

$TC filter add dev $IFACE parent 1:0 protocol arp prio 7 handle 1 fw classid 1:11

# ICMP traffic - Don't impress your friends. Deoptimize to manage ping floods
# better instead

$TC filter add dev $IFACE parent 1:0 protocol ip prio 8 \
	 u32 match ip protocol 1 0xff flowid 1:13

$TC filter add dev $IFACE parent 1:0 protocol ipv6 prio 9 \
	 u32 match ip protocol 1 0xff flowid 1:13

#diffserv $IFACE

}

ingress() {

CEIL=$DOWNLINK
PRIO_RATE=`expr $CEIL / 3` # Ceiling for prioirty
BE_RATE=`expr $CEIL / 6`   # Min for best effort
BK_RATE=`expr $CEIL / 6`   # Min for background
BE_CEIL=`expr $CEIL - 16`  # A little slop at the top

LQ="quantum `get_mtu $IFACE $CEIL`"

$TC qdisc del dev $IFACE handle ffff: ingress 2> /dev/null
$TC qdisc add dev $IFACE handle ffff: ingress

$TC qdisc del dev $DEV root  2> /dev/null

if [ "$SQUASH_INGRESS" = "1" ]
then
sqm_logger "Do not perform DSCP based filtering on ingress. (1-tier classification)"
# Revert to no dscp based filtering
$TC qdisc del dev $DEV root 2>/dev/null
$TC qdisc add dev $DEV root handle 1: `get_stab_string` htb default 10
$TC class add dev $DEV parent 1: classid 1:1 htb $LQ rate ${DOWNLINK}kbit ceil ${DOWNLINK}kbit `get_htb_adsll_string`
$TC class add dev $DEV parent 1:1 classid 1:10 htb $LQ rate ${DOWNLINK}kbit ceil ${DOWNLINK}kbit prio 0 `get_htb_adsll_string`
$TC qdisc add dev $DEV parent 1:10 handle 110: $QDISC `get_limit ${ILIMIT}` `get_target "${ITARGET}" ${DOWNLINK}` `get_ecn ${IECN}` `get_flows ${DOWNLINK}` ${IQDISC_OPTS}

else
sqm_logger "Perform DSCP based filtering on ingress. (3-tier classification)"
$TC qdisc add dev $DEV root handle 1: `get_stab_string` htb default 12
$TC class add dev $DEV parent 1: classid 1:1 htb $LQ rate ${CEIL}kbit ceil ${CEIL}kbit `get_htb_adsll_string`
$TC class add dev $DEV parent 1:1 classid 1:10 htb $LQ rate ${CEIL}kbit ceil ${CEIL}kbit prio 0 `get_htb_adsll_string`
$TC class add dev $DEV parent 1:1 classid 1:11 htb $LQ rate 32kbit ceil ${PRIO_RATE}kbit prio 1 `get_htb_adsll_string`
$TC class add dev $DEV parent 1:1 classid 1:12 htb $LQ rate ${BE_RATE}kbit ceil ${BE_CEIL}kbit prio 2 `get_htb_adsll_string`
$TC class add dev $DEV parent 1:1 classid 1:13 htb $LQ rate ${BK_RATE}kbit ceil ${BE_CEIL}kbit prio 3 `get_htb_adsll_string`

# I'd prefer to use a pre-nat filter but that causes permutation...

$TC qdisc add dev $DEV parent 1:11 handle 110: $QDISC `get_limit ${ILIMIT}` `get_target "${ITARGET}" ${DOWNLINK}` `get_ecn ${IECN}` `get_quantum 500` `get_flows ${PRIO_RATE}` ${IQDISC_OPTS}
$TC qdisc add dev $DEV parent 1:12 handle 120: $QDISC `get_limit ${ILIMIT}` `get_target "${ITARGET}" ${DOWNLINK}` `get_ecn ${IECN}` `get_quantum 1500` `get_flows ${BE_RATE}` ${IQDISC_OPTS}
$TC qdisc add dev $DEV parent 1:13 handle 130: $QDISC `get_limit ${ILIMIT}` `get_target "${ITARGET}" ${DOWNLINK}` `get_ecn ${IECN}` `get_quantum 300` `get_flows ${BK_RATE}` ${IQDISC_OPTS}

diffserv $DEV

fi

ifconfig $DEV up

# redirect all IP packets arriving in $IFACE to ifb0 

$TC filter add dev $IFACE parent ffff: protocol all prio 10 u32 \
  match u32 0 0 flowid 1:1 action mirred egress redirect dev $DEV

}

do_modules
ipt_setup

if [ "$UPLINK" -ne 0 ];
then
	egress
	sqm_logger "egress shaping activated"
else
	sqm_logger "egress shaping deactivated"
	tc qdisc del dev $IFACE root 2> /dev/null
fi
if [ "$DOWNLINK" -ne 0 ];
then
	ingress
	sqm_logger "ingress shaping activated"
else
	sqm_logger "ingress shaping deactivated"
	tc qdisc del dev $DEV root 2> /dev/null
	tc qdisc del dev $IFACE ingress 2> /dev/null
fi



# References:
# This alternate shaper attempts to go for 1/u performance in a clever way
# http://git.coverfire.com/?p=linux-qos-scripts.git;a=blob;f=src-3tos.sh;hb=HEAD

# Comments
# This does the right thing with ipv6 traffic.
# It also tries to leverage diffserv to some sane extent. In particular,
# the 'priority' queue is limited to 33% of the total, so EF, and IMM traffic
# cannot starve other types. The rfc suggested 30%. 30% is probably
# a lot in today's world.

# Flaws
# Many!