pxe-server/playbook/blancco-init.sh

#!/bin/sh
# Blancco PXE Loader - init script for custom initramfs
# Boot chain: iPXE -> GRUB EFI -> Ubuntu kernel + this initramfs -> switch_root to Blancco
#
# Blancco's own kernel freezes on Dell Precision towers during PXE boot.
# Workaround: boot Ubuntu kernel, download Blancco rootfs (squashfs), mount
# overlay filesystem, and switch_root into Blancco's userspace.

export PATH=/bin:/sbin

echo ""
echo "============================================"
echo "  Blancco PXE loader"
echo "============================================"
echo ""

mount -t proc proc /proc
mount -t sysfs sysfs /sys
mount -t devtmpfs devtmpfs /dev 2>/dev/null
mkdir -p /tmp /run

echo "[1/4] Loading NIC drivers..."
echo "  Kernel: $(uname -r)"
echo "  Interfaces before driver load: $(ls /sys/class/net/ 2>/dev/null)"

# Dependency modules first. insmod does not resolve deps; main NIC
# drivers like igb need dca + i2c-algo-bit, atlantic needs macsec,
# some Intel drivers need libeth/libie. Load helpers first so the
# main driver module has its required symbols available.
for mod in /lib/modules/libeth.ko /lib/modules/libie*.ko /lib/modules/dca.ko \
           /lib/modules/i2c-algo-bit.ko /lib/modules/macsec.ko \
           /lib/modules/mii.ko /lib/modules/ssb.ko /lib/modules/libphy.ko \
           /lib/modules/mdio*.ko /lib/modules/phy*.ko /lib/modules/ptp*.ko; do
    [ -f "$mod" ] || continue
    insmod "$mod" 2>&1 | grep -v '^$' | head -1 || true
done

# Main NIC drivers (everything else in /lib/modules/ that is not a helper
# or the overlay/squashfs modules). Errors are now VISIBLE so if a
# driver fails to load we can see why.
for mod in /lib/modules/*.ko; do
    base=$(basename "$mod")
    case "$base" in
        libeth.ko|libie*.ko|dca.ko|i2c-algo-bit.ko|macsec.ko|mii.ko|ssb.ko|libphy.ko|overlay.ko|squashfs.ko|mdio*.ko|phy*.ko|ptp*.ko)
            continue ;;
    esac
    echo "  insmod $base"
    insmod "$mod" 2>&1 | head -1 || true
done
sleep 5

echo "  Interfaces after driver load: $(ls /sys/class/net/ 2>/dev/null)"
echo "  Kernel messages mentioning NIC driver activity:"
dmesg 2>/dev/null | grep -iE "eth|igc|igb|bnxt|tg3|r8169|atlantic|e1000|ixgbe|i40e|eno|ens|enp" | tail -20

echo "  Waiting for network interface..."
IFACE=""
COUNT=0
while [ $COUNT -lt 60 ]; do
    for i in /sys/class/net/*; do
        ifname="${i##*/}"
        if [ "$ifname" != "lo" ] && [ -d "$i" ]; then
            IFACE=$ifname
            break 2
        fi
    done
    COUNT=$((COUNT + 1))
    sleep 1
    echo -n "."
done
echo ""

if [ -z "$IFACE" ]; then
    echo ""
    echo "ERROR: No network interface found after 60s."
    echo "  /sys/class/net/: $(ls /sys/class/net/ 2>/dev/null)"
    echo "  Last 40 lines of dmesg (look for probe failures):"
    dmesg 2>/dev/null | tail -40
    echo ""
    echo "  Dropping to busybox shell for manual debug. reboot with 'reboot -f'."
    exec sh
fi

echo "  Interface: $IFACE"
ip link set $IFACE up
sleep 2

SERVER=10.9.100.1
ifconfig $IFACE 10.9.100.250 netmask 255.255.255.0 up
sleep 1
echo "  IP: 10.9.100.250"

echo "[2/4] Downloading Blancco rootfs (666MB)..."
wget -O /tmp/airootfs.sfs http://$SERVER/blancco/arch/x86_64/airootfs.sfs 2>&1
if [ ! -s /tmp/airootfs.sfs ]; then
    echo "ERROR: Failed to download rootfs!"
    exec sh
fi
echo "  OK ($(wc -c < /tmp/airootfs.sfs) bytes)"

echo "[3/4] Mounting rootfs..."
mkdir -p /run/lower /run/upper /run/work /run/newroot

losetup /dev/loop0 /tmp/airootfs.sfs
mount -t squashfs -o ro /dev/loop0 /run/lower
if [ $? -ne 0 ]; then
    echo "ERROR: squashfs mount failed!"
    exec sh
fi

insmod /lib/modules/overlay.ko 2>/dev/null
mount -t tmpfs -o size=50% tmpfs /run/upper
mkdir -p /run/upper/upper /run/upper/work

mount -t overlay overlay -o lowerdir=/run/lower,upperdir=/run/upper/upper,workdir=/run/upper/work /run/newroot
if [ $? -ne 0 ]; then
    echo "ERROR: overlay mount failed!"
    exec sh
fi

echo "[4/5] Installing kernel modules (132MB)..."
wget -O /tmp/kmod.tar.gz http://$SERVER/blancco/kmod.tar.gz 2>&1
if [ -s /tmp/kmod.tar.gz ]; then
    cd /run/newroot
    gunzip -c /tmp/kmod.tar.gz | tar xf -
    rm -f /tmp/kmod.tar.gz
    cd /
    echo "  OK"
else
    echo "  WARNING: Failed to download kernel modules"
fi

echo "[5/6] Switching root to Blancco..."
mkdir -p /run/newroot/run /run/newroot/proc /run/newroot/sys /run/newroot/dev /run/newroot/tmp

echo "[6/6] Downloading Blancco config..."
wget -O /run/newroot/albus/config.xml http://$SERVER/blancco/config-clean.xml 2>&1
wget -O /run/newroot/albus/preferences.xml http://$SERVER/blancco/preferences.xml 2>&1
if [ -s /run/newroot/albus/config.xml ]; then
    echo "  config.xml: $(wc -c < /run/newroot/albus/config.xml) bytes"
else
    echo "  WARNING: Failed to download config.xml"
fi
if [ -s /run/newroot/albus/preferences.xml ]; then
    cp -f /run/newroot/albus/preferences.xml /run/newroot/albus/preferences.save
    echo "  preferences.xml: $(wc -c < /run/newroot/albus/preferences.xml) bytes"
else
    echo "  WARNING: Failed to download preferences.xml"
fi

# Pre-configure X.org to use modesetting driver (generic KMS, works with all GPUs)
mkdir -p /run/newroot/etc/X11/xorg.conf.d
echo "  X.org: forcing modesetting driver"
cat > /run/newroot/etc/X11/xorg.conf.d/20-failsafeDriver.conf << 'XEOF'
Section "Device"
    Identifier "Failsafe Video Device"
    Driver "modesetting"
EndSection
XEOF

# Enable SSH for remote debugging
echo "  Enabling SSH (root:blancco)..."
if [ -f /run/newroot/etc/ssh/sshd_config ]; then
    sed 's/^#*PermitRootLogin.*/PermitRootLogin yes/' /run/newroot/etc/ssh/sshd_config > /run/newroot/etc/ssh/sshd_config.new || true
    mv /run/newroot/etc/ssh/sshd_config.new /run/newroot/etc/ssh/sshd_config || true
fi

cat > /run/newroot/etc/rc.local << 'RCEOF'
#!/bin/bash
echo 'root:blancco' | chpasswd
ssh-keygen -A 2>/dev/null
/usr/bin/sshd 2>/dev/null
RCEOF
chmod +x /run/newroot/etc/rc.local

cat > /run/newroot/etc/systemd/system/pxe-debug.service << 'SVCEOF'
[Unit]
Description=PXE Debug SSH
After=network.target

[Service]
Type=oneshot
RemainAfterExit=yes
ExecStart=/etc/rc.local

[Install]
WantedBy=multi-user.target
SVCEOF
ln -sf /etc/systemd/system/pxe-debug.service /run/newroot/etc/systemd/system/multi-user.target.wants/pxe-debug.service 2>/dev/null

mount --move /proc /run/newroot/proc
mount --move /sys /run/newroot/sys
mount --move /dev /run/newroot/dev

echo "  Starting Blancco..."
exec switch_root /run/newroot /sbin/init