// simavr "device" for the TSB bootloader: load the boot-linked ELF into the
// ATmega328P boot section, enter it (BOOTRST is not modelled, so PC is set to
// the boot base, exactly as simavr's own board_simduino does), and expose
// UART0 as a pty. A host client (Python pyserial, or the real tsbloader) then
// speaks the TSB protocol over that pty and actually flashes the device.
#include <array>
#include <csignal>
#include <cstdint>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <print>

#include <unistd.h>

// The parts headers (uart_pty.h) carry no C++ linkage guards of their own,
// unlike simavr's core headers - the block covers both harmlessly.
extern "C" {
#include "avr_uart.h"
#include "sim_avr.h"
#include "sim_elf.h"
#include "uart_pty.h"
}

namespace {

// What the loaders are built for: tsb/*.cpp's device clock and the chip's SPM
// page, which is also the config page sitting directly below the boot section.
constexpr std::uint32_t clock_hz = 16'000'000;
constexpr std::uint32_t page_bytes = 128;

avr_t *avr;
uart_pty_t uart_pty;

[[noreturn]] void finish(int)
{
	uart_pty_stop(&uart_pty);
	_exit(0);
}

} // namespace

int main(int argc, char *argv[])
{
	if (argc != 3) {
		std::println(stderr, "usage: {} <tsb.elf> <boot_base_hex>", argv[0]);
		return 2;
	}
	const auto boot_base = static_cast<std::uint32_t>(std::strtoul(argv[2], nullptr, 0));

	avr = avr_make_mcu_by_name("atmega328p");
	if (!avr) {
		std::println(stderr, "device: no ATmega328P core");
		return 1;
	}
	avr_init(avr);
	avr->frequency = clock_hz;
	// Real flash powers up erased (0xff); the app region must look erased
	// before the bootloader programs it.
	std::memset(avr->flash, 0xff, avr->flashend + 1);

	// simavr's ELF loader flattens the flash base to 0 (it expects an app at
	// 0x0), but it hands back the boot code in fw.flash, so it is placed at the
	// boot section base by hand.
	elf_firmware_t fw{};
	if (elf_read_firmware(argv[1], &fw) != 0) {
		std::println(stderr, "device: cannot read {}", argv[1]);
		return 1;
	}
	// An image that runs past flash end cannot execute on hardware, and a
	// naive copy of it would smash the heap beyond avr->flash - after which
	// the simulation misbehaves in ways that point everywhere but here.
	// Refuse it loudly instead.
	if (boot_base + fw.flashsize > avr->flashend + 1) {
		std::println(stderr, "device: {} B at {:#x} runs past flash end {:#x} - image does not fit its slot",
		             fw.flashsize, boot_base, avr->flashend);
		return 1;
	}
	std::memcpy(avr->flash + boot_base, fw.flash, fw.flashsize);
	avr->pc = boot_base;
	avr->codeend = avr->flashend;

	// Optional: seed the config page with a hex byte string, so the password
	// gate and emergency erase can be tested.
	// Layout: [appjump lo][appjump hi][timeout][password...][0xff].
	if (const char *cfg = std::getenv("TSB_CONFIG")) {
		const auto app_end = boot_base - page_bytes;
		for (int i = 0; cfg[i] && cfg[i + 1]; i += 2) {
			const std::array pair{cfg[i], cfg[i + 1], '\0'};
			avr->flash[app_end + i / 2] = static_cast<std::uint8_t>(std::strtoul(pair.data(), nullptr, 16));
		}
	}

	// POLL_SLEEP makes simavr usleep(1) on every status-register read while the
	// UART is idle - a host-CPU-saving hack that models no hardware and paces a
	// tight-polling loader (one that releases TX between bytes, as one-wire does)
	// in real time, distorting protocol timing. Clear it so the loader runs at
	// true cycle speed.
	std::uint32_t uflags = 0;
	avr_ioctl(avr, AVR_IOCTL_UART_GET_FLAGS('0'), &uflags);
	uflags &= ~AVR_UART_FLAG_POLL_SLEEP;
	avr_ioctl(avr, AVR_IOCTL_UART_SET_FLAGS('0'), &uflags);

	uart_pty_init(avr, &uart_pty);
	uart_pty_connect(&uart_pty, '0');
	std::println("TSB_PTY {}", uart_pty.pty.slavename);
	std::fflush(stdout);

	std::signal(SIGTERM, finish);
	std::signal(SIGINT, finish);

	for (;;) {
		const auto state = avr_run(avr);
		if (state == cpu_Done || state == cpu_Crashed) {
			break;
		}
	}
	finish(0);
}