#!/usr/bin/env bash
#
# scripts/test-fault.sh — fault-diagnostics verification.
#
# Real hardware has no serial console, so a kernel crash previously left
# only a frozen screen ("unresponsive").  This test proves the fault-dump
# path: every CPU exception now prints a white-on-red band to the
# framebuffer *and* a parseable serial line (vector, error, RIP, CR2,
# task) before halting — so the next real-hardware failure identifies
# itself.  The `fault` command deliberately writes to an unmapped
# address; the machine must halt with a full dump, not triple-fault.
#
# Usage: ./scripts/test-fault.sh
# Env:   OVMF, QEMU (same defaults as other test scripts)
#
set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
PROJECT_DIR="$(dirname "$SCRIPT_DIR")"
cd "$PROJECT_DIR"

OVMF="${OVMF:-/usr/share/edk2/x64/OVMF.4m.fd}"
QEMU="${QEMU:-qemu-system-x86_64}"
ESP_DIR="$PROJECT_DIR/esp"
QPID=/tmp/rsdos-fault-qpid
SOCK=/tmp/rsdos-fault-qmon.sock
LOG=/tmp/rsdos-fault-serial.log
QLOG=/tmp/rsdos-fault-qemu.log

trap 'kill "$(cat "$QPID" 2>/dev/null)" 2>/dev/null || true' EXIT

fail() {
	echo "FAIL: $1"
	[ -f "$LOG" ] && tail -40 "$LOG"
	exit 1
}

wait_log() {
	local i=0
	while [ "$i" -lt $((${3:-60} * 10)) ]; do
		grep -q "$2" "$1" 2>/dev/null && return 0
		sleep 0.1
		i=$((i + 1))
	done
	return 1
}

echo "==> 1/5 build kernel (debug)"
cargo build --package rsdos --target x86_64-unknown-uefi

echo "==> 2/5 deploy to ESP"
mkdir -p "$ESP_DIR/EFI/BOOT"
cp target/x86_64-unknown-uefi/debug/rsdos.efi "$ESP_DIR/EFI/BOOT/BOOTX64.EFI"

echo "==> 3/6 boot QEMU (headless, + dedicated CRASHLOG stick)"
kill "$(cat "$QPID" 2>/dev/null)" 2>/dev/null || true
sleep 1
rm -f "$SOCK" "$LOG"
# A second FAT32 stick labeled CRASHLOG: crash reports must land here
# (label-selected by the kernel), not on the boot device.
CRASH_IMG=/tmp/rsdos-crash.img
"$SCRIPT_DIR/mkdisk.sh" --fresh --label CRASHLOG --no-seed "$CRASH_IMG" >/dev/null
"$QEMU" -bios "$OVMF" \
	-drive file=fat:rw:"$ESP_DIR",format=raw \
	-drive file="$CRASH_IMG",format=raw,if=none,id=crash \
	-device ide-hd,drive=crash,bus=ide.2 \
	-serial file:"$LOG" \
	-monitor unix:"$SOCK",server,nowait \
	-m 256M -machine q35 -cpu qemu64 -no-reboot -display none \
	>"$QLOG" 2>&1 &
echo $! >"$QPID"

wait_log "$LOG" "boot: entering shell" 90 || fail "kernel never reached the shell"

echo "==> 4/6 boot diagnostics present"
grep -aq "gop: fb base=" "$LOG" || fail "fb geometry diagnostic missing"
grep -aq "gop: mode .* selected" "$LOG" || fail "mode-selection diagnostic missing"
grep -aq "CRASHLOG" "$LOG" || fail "CRASHLOG stick not mounted"

echo "==> 5/6 inject a page fault (fault command)"
python3 "$SCRIPT_DIR/sendkeys.py" --sock "$SOCK" \
	"clear" \
	"fault"
sleep 2

# The dump must appear on serial: vector 14, the CR2 we wrote, RIP, and
# the shell task identity — then the machine halts (never triple-faults).
grep -aq "!!! page fault vec=14 .*rip=" "$LOG" || fail "page-fault dump line missing"
grep -aq "cr2=0x400000000000" "$LOG" || fail "CR2 not reported (faulting address)"
grep -aq "task=0 \"shell\"" "$LOG" || fail "faulting task not identified"
grep -aq "!!! halting" "$LOG" || fail "no halt message"

echo "==> 6/6 crash.log persisted on the CRASHLOG stick"
grep -aq "crashlog: vol .* (CRASHLOG)" "$LOG" || fail "crashlog did not target the CRASHLOG stick"
grep -aq "crashlog: wrote" "$LOG" || fail "crashlog write did not complete"
mdir -i "$CRASH_IMG" "::" 2>/dev/null | grep -aqi "crash" \
	|| fail "crash.log missing on the CRASHLOG stick"
# The boot ESP must NOT receive the crash log.
if [ -f "$ESP_DIR/crash.log" ]; then
	fail "crash.log landed on the boot ESP instead of the CRASHLOG stick"
fi

# The screen dump itself is exercised in-kernel (dump_lines); the serial
# path sharing the same format line is verified above.
echo ""
echo "PASS — fault dump + crash.log on the CRASHLOG stick"
echo "  every CPU exception halts with a diagnosable dump; the report"
echo "  survives reboot on the dedicated CRASHLOG volume"