#!/bin/bash
#
# netboot - PXE-style boot for KVM on s390
#
# Sample script to build an initramfs image suitable for performing a
# PXELINUX-style boot for KVM guests from a DHCP/BOOTP Server.
# Has to be executed on the KVM host where it will be deployed and needs
# to be re-run after kernel updates on the host, unless the virtio
# drivers are statically built into the host kernel.
#
# The script requires a busybox install tree, e.g. resulting from a build
# from source, after make defconfig && make install
#
# To keep things simple, we don't include udev but use devtmpfs
# which means the host kernel must have been built with CONFIG_DEVTMPFS=y
#
# Sample invocation:
#
# ./mk-pxelinux-ramfs -b /downloads/busyboxdir pxelinux.initramfs
#
# Copyright IBM Corp. 2017
#
# s390-tools is free software; you can redistribute it and/or modify
# it under the terms of the MIT license. See LICENSE for details.

# Variables
cmd=$(basename $0)
busyboxdir=
builddir=
initramfs=
success=no

# Cleanup on exit
cleanup()
{
	if [ -n $builddir ]
	then
		rm -rf $builddir
	fi
}
trap cleanup EXIT

# Usage
usage()
{
cat <<-EOF
Usage: $cmd -b BUSYBOX_DIR [-k KERNEL_VERSION] INITRAMFS_FILE

Build a PXELINUX style boot initramfs INITRAMFS_FILE using a busybox installed
in BUSYBOX_DIR and kernel modules from the currently running kernel or from
the kernel version specified with the '-k KERNEL_VERSION' option.

OPTIONS
-b        Search installed busybox in directory BUSYBOX_DIR
-k        Use KERNEL_VERSION instead of currently running kernel
-h        Print this help, then exit
-v        Print version information, then exit
EOF
}

printversion()
{
	cat <<-EOD
	$cmd: version %S390_TOOLS_VERSION%
	Copyright IBM Corp. 2017
	EOD
}

# Get shared objects for binary
sharedobjs()
{
	ldd $1 | sed -e 's?[^/]*??' -e 's/(.*)//'
}

# Check args
args=$(getopt b:k:hv $*)
if [ $? = 0 ]
then
	set -- $args
	while [ -n $1 ]
	do
		case $1 in
			-b) busyboxdir=$2; shift 2;;
			-k) kernelversion=$2; shift 2;;
		        -h) usage; exit 0;;
		        -v) printversion; exit 0;;
		        --) shift; break;;
		        *) echo "$cmd: Unexpected argument $1, exiting..." >&2; exit 1;;
		esac
	done
fi

if [ $# != 1 -o "$busyboxdir" = "" ]
then
	usage >&2
	exit 1
fi

# Full output file path
initramfs=$(readlink -m $(dirname $1))/$(basename $1)

# Exit on error
set -e

# Module locations
if [ -n $kernelversion ]; then
	moddir=/lib/modules/$kernelversion
else
	moddir=/lib/modules/$(uname -r)
fi
netdir=$moddir/kernel/drivers/net
blkdir=$moddir/kernel/drivers/block

# Setup build directory
builddir=$(mktemp -d)
echo "$cmd: Building in $builddir"

ramfsdirs="/bin /dev /etc /lib64 /lib /mnt /proc /run /sbin /sys /tmp /usr /var"
for d in $ramfsdirs
do
	mkdir -p $builddir/$d
done

# Kexec
echo "$cmd: Copying kexec"

# Install both binary and required shared libraries
OLDPATH=$PATH
PATH=$OLDPATH:/sbin:/usr/sbin
kexec_bin=$(command -v kexec)
kexec_sos=$(sharedobjs $kexec_bin)
PATH=$OLDPATH

cp $kexec_bin $builddir/sbin
for so in $kexec_sos
do
	mkdir -p $builddir/$(dirname $so)
	cp $so $builddir/$(dirname $so)
done

# virtio module(s), if present
echo "$cmd: Copying virtio modules"

mkdir -p $builddir/$netdir
mkdir -p $builddir/$blkdir
set +e
cp $netdir/virtio_net.ko* $builddir/$netdir 2> /dev/null
cp $blkdir/virtio_blk.ko* $builddir/$blkdir 2> /dev/null
set -e

# Busybox (+ dependencies)
echo "$cmd: Copying busybox files"

cp -a $busyboxdir/* $builddir
busybox_sos=$(sharedobjs $busyboxdir/bin/busybox)
for so in $busybox_sos
do
	mkdir -p $builddir/$(dirname $so)
	cp $so $builddir/$(dirname $so)
done

# ad_packet module(s), if present
echo "$cmd: Copying af_packet modules"

packetdir=$moddir/kernel/net/packet
mkdir -p $builddir/$packetdir
set +e
cp $packetdir/* $builddir/$packetdir 2> /dev/null
set -e

# Init script
echo "$cmd: Making init script"

# --- begin init script
cat <<'EOF' > $builddir/init
#!/bin/sh
/bin/mount -t devtmpfs none /dev
/bin/mount -t proc none /proc
/bin/mount -t sysfs none /sys
/bin/mount -t tmpfs none /run

/sbin/modprobe virtio_net
/sbin/udhcpc -O pxeconffile -O pxepathprefix -x 93:001F &

/sbin/pxeboot.script
EOF
# --- end init script
chmod +x $builddir/init

# udhcpc script
echo "$cmd: Making DHCP script"

mkdir -p $builddir/usr/share/udhcpc
# -- begin dhcp script
cat <<'EOF' > $builddir/usr/share/udhcpc/default.script
#!/bin/sh
# Setup name resolution and PXE boot configuration
# called by udhcpc

RESOLVCONF="/etc/resolv.conf"
PXECONF="/etc/pxe.conf"

ccidr()
{
    # clumsy netmask to cidr transformation
    # with minimal sanity checking
    OLDIFS=$IFS
    IFS=.
    c=0
    n=4
    for i in $1
    do
	n=$(/usr/bin/expr $n - 1)
	case $i in
	    255) c=$(/usr/bin/expr $c + 8);;
	    254) c=$(/usr/bin/expr $c + 7); break;;
	    252) c=$(/usr/bin/expr $c + 6); break;;
	    248) c=$(/usr/bin/expr $c + 5); break;;
	    240) c=$(/usr/bin/expr $c + 4); break;;
	    224) c=$(/usr/bin/expr $c + 3); break;;
	    192) c=$(/usr/bin/expr $c + 2); break;;
	    128) c=$(/usr/bin/expr $c + 1); break;;
	    0) break;;
	    *) c=0; break;;
	esac
	if [ $n = 0 ]
	then
	    break
	fi
    done
    IFS=$OLDIFS
    echo $c
}

echo "DHCP response $1: "
case "$1" in
    deconfig)
	echo " interface: $interface"
	/sbin/ip route flush table all
	/sbin/ip addr flush $interface
	/sbin/ip link set $interface up
	/bin/rm -f $PXECONF $RESOLVCONF
	;;

    renew|bound)
	echo " interface: $interface $ip $subnet"
	echo " router: $router"
	echo " domain: $domain $dns"
	echo " tftp: $siaddr"
	echo " pxepathprefix: $pxepathprefix"
	# flush routes
	/sbin/ip route flush table all
	# setup if link
	/sbin/ip addr flush $interface
	/sbin/ip link set $interface up
	# setup if addr
	if [ -n "$subnet" ]
	then
	    maskedip="$ip"/$(ccidr $subnet)
	else
	    maskedip="ip"
	fi
	/sbin/ip addr add $maskedip broadcast $broadcast dev $interface
	# setup default routes
	if [ -n "$router" ]
	then
		/sbin/ip route add default via $router
	fi

	# setup resolv.conf
	if [ -n "$domain" ]
	then
	    echo "search $domain" > $RESOLVCONF
	    for i in $dns
	    do
		echo " nameserver $i" >> $RESOLVCONF
	    done
	fi

	# pxe control
	if [ -n  "$siaddr" ]
	then
	    echo "siaddr=$siaddr" > $PXECONF
	    echo "interface=$interface" >> $PXECONF
	    echo "ip=$ip" >> $PXECONF
	    echo "pxepathprefix=$pxepathprefix" >> $PXECONF
	fi
	;;

    nak)
	;;
    *)
	exit 1
	;;
esac

exit 0

EOF
# -- end dhcp script
chmod +x $builddir/usr/share/udhcpc/default.script

# pxeboot script
echo "$cmd: Making PXE boot script"

# -- begin pxeboot script
cat <<'EOF' > $builddir/sbin/pxeboot.script
#!/bin/sh
# Perform a PXE style boot using kexec
# Supports only super-simple config files

set -e

# Check if a valid pxe conf is available
# so far a non configurable 600 sec timeout
PXE_CONF=/etc/pxe.conf
TIMEOUT=600
WAITED=0
echo "waiting for pxe config from DHCP (max $TIMEOUT sec)"
while [ ! -f $PXE_CONF ]
do
    sleep 1
    WAITED=$(($WAITED + 1))
    if [ $WAITED -gt $TIMEOUT ]
    then
        echo Error waiting for PXE configuration from DHCP
        exit
    fi
done

# Source the DHCP-generated TFTP info
# Currently we are just looking for siaddr
. $PXE_CONF

# Retrieve the config (default only for now)
CONFIGS=""
if [ -n "$siaddr" ];
then
    # Enable UUID based config on s390
    if [ $(/bin/uname -m) = "s390x" ]
    then
	set +e
	uuid=$(/bin/grep UUID /proc/sysinfo | tail -1 | tr -d ' ' | cut -d ':' -f 2) 2> /dev/null
	set -e
    else
	# not caring for other arches right now
	uuid=""
    fi
    CONFIGS="$CONFIGS $uuid"

    # Enable MAC based config
    ifaddr=$(/bin/cat /sys/class/net/$interface/address | tr ':' '-')
    CONFIGS="$CONFIGS 01-$ifaddr"

    # Enable IP based config
    iphex=$(printf %02X $(echo $ip | tr '.' ' '))
    for i in 8 7 6 5 4 3 2 1
    do
	CONFIGS="$CONFIGS $(echo $iphex | cut -c 1-$i)"
    done

    # Finally enable default config
    CONFIGS="$CONFIGS default"

    set +e
    for c in $CONFIGS
    do
	echo "fetching config pxelinux.cfg/$c from $siaddr"
	if /usr/bin/tftp -g -l /tmp/config -r ${pxepathprefix}pxelinux.cfg/$c $siaddr
	then
	    break
	fi
    done
fi

if [ ! -f /tmp/config ]
then
    echo no config found
    exit
fi

# Simple config file parsing, only one entry allowed
kernel=$(/bin/grep -i "^[[:space:]]*kernel" /tmp/config | sed "s/^[[:space:]]*kernel[[:space:]]*//I")
initrd=$(/bin/grep -i "^[[:space:]]*initrd" /tmp/config | sed "s/^[[:space:]]*initrd[[:space:]]*//I")
append=$(/bin/grep -i "^[[:space:]]*append" /tmp/config | sed "s/^[[:space:]]*append[[:space:]]*//I")
ipappend=$(/bin/grep -i "^[[:space:]]*ipappend" /tmp/config | sed "s/^[[:space:]]*ipappend[[:space:]]*//I")

if [ -z "$kernel" ]
then
    echo no kernel statement found in config
    exit
else
    echo fetch kernel $kernel from $siaddr
    /usr/bin/tftp -g -l /tmp/kernel -r $pxepathprefix$kernel $siaddr
fi

if [ -n "$initrd" ]
then
    echo fetch initrd $initrd from $siaddr
    /usr/bin/tftp -g -l /tmp/initrd -r $pxepathprefix$initrd $siaddr
    INITRD="--initrd=/tmp/initrd"
else
    INITRD=""
fi

if [ -z "$append" ]; then
    echo "Kexec load: kexec -l /tmp/kernel $INITRD"
    kexec -l /tmp/kernel $INITRD
else
    if [ "$ipappend" = "2" ]; then
       $append="$append BOOTIF=01-$ifaddr"
    fi
    echo "Kexec load: kexec -l /tmp/kernel $INITRD --append=\"$append\""
    kexec -l /tmp/kernel $INITRD --append="$append"
fi
kexec -e
EOF
# -- end pxeboot script
chmod +x $builddir/sbin/pxeboot.script

# The final initramfs
echo Building initramfs

cd $builddir
find . | cpio -o -Hnewc | gzip - > $initramfs
cd $OLDPWD