#!/usr/bin/env bash
#
# JbTecWiz Support Centre -- generated fix script
#
# Fault : Kernel panic -- "VFS: Unable to mount root fs on unknown-block(0,0)"
# Fix   : Rebuild the initramfs with all drivers from a rescue environment
# Source: https://jbtecwiz.com/support/lnx-kernel-panic-rootfs
#
# Run as     : Rescue/live media with chroot
# Expect     : 45-90 minutes
# Risk       : medium
# Reversible : yes
#
# WHEN THIS IS THE RIGHT FIX
#   Hardware or the virtual platform changed, so the initramfs lacks the
#   driver for the new controller.
#
# HOW TO UNDO IT
#   The old initramfs files are still in /boot under their own kernel
#   versions -- select one from the GRUB menu.
#
# Walks the fix one step at a time and asks before each. Steps with no
# command are yours to do -- it prints those and waits. DRYRUN=1 prints
# without executing; UNATTENDED=1 does not ask.
#
# --------------------------------------------------------------------
# NO WARRANTY - USE AT YOUR OWN RISK
#
# This script is provided by JbTecWiz as-is and with no warranty of any
# kind, express or implied. You run it entirely at your own risk.
#
# JbTecWiz accepts no liability for any loss or damage arising from its
# use, including but not limited to data loss, downtime, or configuration
# changes that turn out to be wrong for your system.
#
# You are responsible for reading this script before running it, for
# satisfying yourself that it suits the machine in front of you, and for
# having a working backup first. Some steps cannot be undone.
# --------------------------------------------------------------------

set -uo pipefail
DRYRUN="${DRYRUN:-0}"
UNATTENDED="${UNATTENDED:-0}"
failed=0

rule() { printf "\n%s\n" "$(printf '-%.0s' $(seq 1 70))"; if [ $# -gt 0 ]; then echo "$1"; fi; }
prose() { echo "$1" | fold -s -w 74 | sed "s/^/  /"; }

# Returns 0 when the caller should run the command, 1 when it should not.
# A manual step always returns 1 -- there is nothing for the caller to run.
step() {  # step <n> <do> <why> <manual|cmd> [command lines...]
  local n="$1" dotext="$2" why="$3" mode="$4"; shift 4
  rule "  Step $n of 8"
  prose "$dotext"
  if [ -n "$why" ]; then echo; prose "$why"; fi
  if [ "$mode" = "manual" ]; then
    echo; echo "  -> Do this yourself, then press Enter to carry on."
    if [ "$UNATTENDED" = "0" ] && [ "$DRYRUN" = "0" ]; then read -r _; fi
    return 1
  fi
  echo; printf "    %s\n" "$@"; echo
  if [ "$DRYRUN" = "1" ]; then echo "  (dry run -- not executed)"; return 1; fi
  if [ "$UNATTENDED" = "0" ]; then
    read -r -p "  Run this step? [Y]es / [S]kip / [Q]uit " a
    case "$a" in
      [Qq]*) echo "  Stopped at your request."; exit 0 ;;
      [Ss]*) echo "  Skipped."; return 1 ;;
    esac
  fi
  return 0
}

rule
echo "  Kernel panic -- "VFS: Unable to mount root fs on unknown-block(0,0)""
echo "  Rebuild the initramfs with all drivers from a rescue environment"
echo
echo "  Risk: medium   Reversible   45-90 minutes"
echo
prose 'No warranty. Use at your own risk - JbTecWiz accepts no liability. Read it before you run it, and have a backup.'
rule
echo
if [ "$UNATTENDED" = "0" ] && [ "$DRYRUN" = "0" ]; then
  read -r -p "  Ready? [y/N] " go
  case "$go" in [Yy]*) ;; *) echo "  Nothing was changed."; exit 0;; esac
fi

step 1 'Boot rescue media matching the distribution and version.' '' manual || true

if step 2 'Find and mount the root filesystem, activating LVM first if it is used.' '' cmd 'lsblk -f' 'sudo vgchange -ay' 'sudo mount /dev/mapper/vg-root /mnt'; then
  lsblk -f
  sudo vgchange -ay
  sudo mount /dev/mapper/vg-root /mnt
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 2 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 3 'Mount /boot and the EFI partition if separate.' '' cmd 'sudo mount /dev/sda1 /mnt/boot' 'sudo mount /dev/sda2 /mnt/boot/efi'; then
  sudo mount /dev/sda1 /mnt/boot
  sudo mount /dev/sda2 /mnt/boot/efi
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 3 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 4 'Bind the virtual filesystems and chroot in.' '' cmd 'for d in dev proc sys run; do sudo mount --bind /$d /mnt/$d; done' 'sudo chroot /mnt /bin/bash'; then
  for d in dev proc sys run; do sudo mount --bind /$d /mnt/$d; done
  sudo chroot /mnt /bin/bash
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 4 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 5 'Rebuild the initramfs with every driver rather than the host-only subset.' '--no-hostonly builds a generic initramfs that carries drivers for hardware this machine does not currently have. It is larger and it boots on platforms the host-only build cannot see.' cmd 'dracut -f --no-hostonly --add-drivers '\''virtio_blk virtio_scsi virtio_pci ahci nvme'\'' /boot/initramfs-$(ls /lib/modules | tail -1).img $(ls /lib/modules | tail -1)'; then
  dracut -f --no-hostonly --add-drivers 'virtio_blk virtio_scsi virtio_pci ahci nvme' /boot/initramfs-$(ls /lib/modules | tail -1).img $(ls /lib/modules | tail -1)
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 5 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 6 'On Debian-family, set MODULES=most in /etc/initramfs-tools/initramfs.conf, then rebuild.' '' cmd 'update-initramfs -c -k all && update-grub'; then
  update-initramfs -c -k all && update-grub
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 6 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 7 'Confirm root= in the GRUB config matches a device that exists.' '' cmd 'grep -E '\''linux|root='\'' /boot/grub2/grub.cfg | head' 'blkid'; then
  grep -E 'linux|root=' /boot/grub2/grub.cfg | head
  blkid
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 7 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 8 'Exit, unmount and reboot.' '' cmd 'exit' 'sudo umount -R /mnt' 'sudo reboot'; then
  exit
  sudo umount -R /mnt
  sudo reboot
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 8 failed. The rest of the fix may depend on it." >&2
  fi
fi

rule "  Confirm it worked"
prose 'The system boots to a login prompt.'
if [ "$DRYRUN" = "0" ]; then
  systemctl is-system-running
fi

rule
if [ "$failed" -gt 0 ]; then
  echo "  Finished with $failed failed step(s)."
  echo "  Read the full write-up at https://jbtecwiz.com/support/lnx-kernel-panic-rootfs"
else
  echo "  Finished."
fi
echo
prose 'To undo: The old initramfs files are still in /boot under their own kernel versions -- select one from the GRUB menu.'
rule