#!/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   : Boot the previous kernel and rebuild the new one's initramfs
# Source: https://jbtecwiz.com/support/lnx-kernel-panic-rootfs
#
# Run as     : GRUB menu, then shell
# Expect     : 30 minutes
# Risk       : low
# Reversible : yes
#
# WHEN THIS IS THE RIGHT FIX
#   It started after a kernel update and an older kernel is still
#   installed.
#
# HOW TO UNDO IT
#   Boot the older kernel again from GRUB -- it is untouched by this.
#
# 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 $n of 7"
  prose "$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 "  Boot the previous kernel and rebuild the new one'\''s initramfs"
echo
echo "  Risk: low   Reversible   30 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 'At the GRUB menu choose Advanced options and select the previous kernel. Hold Shift or press Esc during boot if the menu is hidden.' '' manual || true

if step 2 'Once booted, confirm which kernel you are on and which are installed.' '' cmd 'uname -r' 'ls /boot/vmlinuz-*'; then
  uname -r
  ls /boot/vmlinuz-*
  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 'Check the broken kernel'\''s initramfs exists and is a sensible size.' 'A zero-length or missing initramfs is a common result of a kernel update that ran out of space in /boot, and it produces exactly this panic.' cmd 'ls -lh /boot/initramfs-* /boot/initrd.img-* 2>/dev/null'; then
  ls -lh /boot/initramfs-* /boot/initrd.img-* 2>/dev/null
  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 'Check /boot has room, and clear old kernels if not.' '' cmd 'df -h /boot'; then
  df -h /boot
  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 it. On RHEL-family:' '' cmd 'sudo dracut -f /boot/initramfs-$(uname -r).img $(uname -r)'; then
  sudo dracut -f /boot/initramfs-$(uname -r).img $(uname -r)
  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:' '' cmd 'sudo update-initramfs -c -k all' 'sudo update-grub'; then
  sudo update-initramfs -c -k all
  sudo 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

step 7 'Reboot into the newer kernel.' '' manual || true

rule "  Confirm it worked"
prose 'The machine boots on the newest kernel.'
if [ "$DRYRUN" = "0" ]; then
  uname -r
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: Boot the older kernel again from GRUB -- it is untouched by this.'
rule