#!/usr/bin/env bash
#
# JbTecWiz Support Centre -- generated fix script
#
# Fault : Boot drops to emergency mode after an fstab change
# Fix   : Make a network mount safe at boot
# Source: https://jbtecwiz.com/support/lnx-fstab-emergency
#
# Run as     : Emergency shell, then normal shell
# Expect     : 20 minutes
# Risk       : low
# Reversible : yes
#
# WHEN THIS IS THE RIGHT FIX
#   An NFS or CIFS entry is stalling or failing the boot.
#
# HOW TO UNDO IT
#   Comment the line out and reboot.
#
# 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 $n of 5"
  prose "$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 "  Boot drops to emergency mode after an fstab change"
echo "  Make a network mount safe at boot"
echo
echo "  Risk: low   Reversible   20 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

if step 1 'Get to a writable root as above.' '' cmd 'mount -o remount,rw /'; then
  mount -o remount,rw /
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 1 failed. The rest of the fix may depend on it." >&2
  fi
fi

if step 2 'Add the options that tell systemd this mount needs the network and must not be fatal.' '' cmd 'vi /etc/fstab'; then
  vi /etc/fstab
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 2 failed. The rest of the fix may depend on it." >&2
  fi
fi

step 3 'The options to use are _netdev,nofail plus a timeout -- for example: `//fs01/share /mnt/share cifs credentials=/etc/smb-creds,_netdev,nofail,x-systemd.device-timeout=10 0 0`' '_netdev orders the mount after the network is up. Without it systemd tries to mount before there is a route and the failure is fatal.' manual || true

step 4 'Consider x-systemd.automount so the share is mounted on first access rather than at boot.' 'This decouples the boot from the file server entirely -- the machine comes up whether or not the share is reachable.' manual || true

if step 5 'Reload and test without rebooting.' '' cmd 'systemctl daemon-reload' 'mount -a'; then
  systemctl daemon-reload
  mount -a
  if [ $? -ne 0 ]; then
    failed=$((failed+1))
    echo "  Step 5 failed. The rest of the fix may depend on it." >&2
  fi
fi

rule "  Confirm it worked"
prose 'The system boots and the share mounts, or is absent without blocking anything.'
if [ "$DRYRUN" = "0" ]; then
  findmnt /mnt/share; 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-fstab-emergency"
else
  echo "  Finished."
fi
echo
prose 'To undo: Comment the line out and reboot.'
rule