// pureboot — a serial bootloader on libavr, pure by constraint: one C++
// source with no inline assembly and no global register variables, built for
// every chip libavr targets, 512 bytes on each. The device speaks primitives
// — read/program flash, read/write EEPROM, fuse bytes, an info block, run —
// and everything composite (verify, erase, reset-vector surgery on the
// tinies, timeout configuration) lives in the host tool. Protocol reference:
// README.md next to this file.
//
// Entry: reset lands in avr::startup::entry below (BOOTRST on the mega; the
// patched reset vector — or erased flash walking up into the loader — on the
// tinies). A watchdog reset hands straight to the application. Otherwise the
// host has one activation window — EEPROM's last cell, in seconds — to knock
// ("pb"); an idle line boots the application. A session then stays in the
// command loop until 'G' hands over or the chip resets.

#include <libavr/libavr.hpp>

using namespace avr::literals;
namespace spm = avr::spm;
namespace ee = avr::eeprom;

namespace pureboot {
namespace {

// Purely polled — interrupts stay off, every guard folds to nothing.
constexpr auto off = avr::irq::guard_policy::unused;

constexpr std::uint8_t ack = '+';

// Per-chip personality, from the chip database: the clocks the dogfood
// boards run (16 MHz crystal on the mega, calibrated RC on the tinies) and
// the device signature (compile-time data — the tiny13A cannot even read its
// signature row from code).
consteval avr::hertz_t clock()
{
	if (avr::hw::db.name == "ATtiny13A")
		return 9.6_MHz;
	if (avr::hw::db.name == "ATtiny85")
		return 8_MHz;
	return 16_MHz;
}

consteval std::array<std::uint8_t, 3> signature()
{
	if (avr::hw::db.name == "ATtiny13A")
		return {0x1e, 0x90, 0x07};
	if (avr::hw::db.name == "ATtiny85")
		return {0x1e, 0x93, 0x0b};
	return {0x1e, 0x95, 0x0f};
}

using dev = avr::device<{.clock = clock()}>;

// Geometry: the loader owns the top 512 bytes of flash; the byte below it is
// the trampoline word (the application's relocated reset vector) on chips
// without a hardware boot section. The RWWSRE bit marks a separate boot
// section — on classic AVR the two capabilities coincide.
constexpr std::uint16_t boot_bytes = 512;
constexpr std::uint16_t base = static_cast<std::uint16_t>(spm::flash_bytes - boot_bytes);
constexpr std::uint16_t page = spm::page_bytes;
constexpr bool boot_section = avr::hw::db.field_index("SPMCSR", "RWWSRE") >= 0;

// The activation timeout lives in EEPROM's last cell, in seconds; the host
// rewrites it with the ordinary EEPROM-write command. An unprogrammed cell —
// 0x00 or the erased 0xff — means the 4 s default: a stray value can never
// floor the window to nothing and lock the loader out, and erasing the whole
// EEPROM resets the timeout instead of maxing it to 255 s.
constexpr std::uint16_t timeout_cell = avr::hw::db.mem.eeprom_size - 1;
constexpr std::uint8_t default_seconds = 4;

// The 12-byte info block the host reads with the 'b' command; flash-resident
// (there is no crt to copy a .data image).
inline constexpr std::array<std::uint8_t, 12> info_data = {
    'P',
    'B',
    1, // magic, protocol version
    signature()[0],
    signature()[1],
    signature()[2],
    static_cast<std::uint8_t>(page),
    base & 0xff,
    base >> 8, // app flash ends here; loader base
    avr::hw::db.mem.eeprom_size & 0xff,
    avr::hw::db.mem.eeprom_size >> 8,
    boot_section ? 0 : 1, // bit 0: host must patch the reset vector (no hardware boot section)
};
using info = avr::flash_table<info_data>;

// The serial link: the hardware USART where the chip has one, the polled
// software UART (no vector — the table belongs to the application) on PB0/PB1
// elsewhere. Both are class templates on the clock so only the selected
// backend is ever instantiated. pending() is the cheap line test the
// activation window polls; rx() then picks the byte up.
template <avr::hertz_t C>
consteval std::int16_t rxc_field()
{
	return avr::hw::db.field_index("UCSR0A", "RXC0");
}

template <avr::hertz_t C>
struct hardware_link {
	using uart = avr::uart::usart0<C, {.baud = 115200_Bd, .max_baud_error = 2.5_pct}>;

	static void init()
	{
		avr::init<uart>();
	}

	static bool pending()
	{
		return avr::hw::field_impl<rxc_field<C>()>::test();
	}

	static std::uint8_t rx()
	{
		return uart::read_blocking();
	}

	static void tx(std::uint8_t byte)
	{
		uart::write(byte);
	}
};

template <avr::hertz_t C>
struct software_link {
	using rx_t = avr::uart::software_rx_polled<C, avr::pb0, 57600_Bd>;
	using tx_t = avr::uart::software_tx<C, avr::pb1, 57600_Bd>;

	static void init()
	{
		avr::init<rx_t, tx_t>();
	}

	static bool pending()
	{
		return !avr::io::input<avr::pb0>::read(); // a start bit has begun
	}

	static std::uint8_t rx()
	{
		return rx_t::template read_blocking<off>();
	}

	static void tx(std::uint8_t byte)
	{
		tx_t::template write<off>(byte);
	}
};

using link = std::conditional_t<avr::hw::db.has_reg("UDR0"), hardware_link<dev::clock>, software_link<dev::clock>>;

// The application's entry: the linker pins pureboot_app to 0x0000 on the
// mega (reset re-vectors here through BOOTRST, so address 0 stays the
// application's own vector) and to the trampoline word at base - 2 on the
// tinies (--defsym in CMakeLists.txt).
extern "C" [[noreturn]] void pureboot_app();

[[noreturn]] void run_app()
{
	pureboot_app();
}

// One activation tick is 65536 pending() polls — a pin (or flag) test plus a
// 16-bit countdown, about 8 cycles. Whole-second precision is all the
// timeout cell promises; the seconds count stays a loop bound (a runtime
// multiply would drag libgcc's __mulhi3 into the MUL-less tinies).
consteval std::uint16_t ticks_per_second()
{
	return static_cast<std::uint16_t>(dev::clock.hz / (65536ull * 8u));
}
static_assert(ticks_per_second() >= 1);

bool pending_before(std::uint8_t seconds)
{
	do {
		std::uint16_t ticks = ticks_per_second();
		do {
			std::uint16_t spins = 0; // wraps first, so 65536 polls per tick
			do {
				if (link::pending())
					return true;
			} while (--spins);
		} while (--ticks);
	} while (--seconds);
	return false;
}

// A knock byte under the activation deadline: an idle line means no host is
// there, and the application runs.
std::uint8_t rx_deadline(std::uint8_t seconds)
{
	if (!pending_before(seconds))
		run_app();
	return link::rx();
}

std::uint16_t rx16()
{
	std::uint8_t low = link::rx();
	return static_cast<std::uint16_t>(low | (link::rx() << 8));
}

const std::uint8_t *flash_ptr(std::uint16_t address)
{
	return reinterpret_cast<const std::uint8_t *>(address);
}

// The streamers take the count in the wire's 8-bit form: 0 means 256.
void send_flash(std::uint16_t address, std::uint8_t count)
{
	do
		link::tx(avr::flash_load(flash_ptr(address++)));
	while (--count);
}

void send_eeprom(std::uint16_t address, std::uint8_t count)
{
	do
		link::tx(ee::read(address++));
	while (--count);
}

// EEPROM write, host-paced: each ack goes out once the byte's write has
// begun, so the next byte arrives while it completes and the following
// write's own ready-wait sees an idle line. Nothing is ever missed, on
// either serial backend, without a buffer.
void store_eeprom(std::uint16_t address, std::uint8_t count)
{
	do {
		ee::write<off>(address++, link::rx());
		link::tx(ack);
	} while (--count);
}

// One flash page: stream the bytes into the SPM buffer as little-endian
// words, then erase and program. Addresses in the loader's own 512 bytes
// are drained but never programmed — a broken host cannot brick the chip.
// On the mega the RWW section is re-enabled so reads work immediately.
void program_flash(std::uint16_t address)
{
	for (std::uint16_t i = 0; i < page; i += 2) {
		std::uint8_t low = link::rx();
		std::uint8_t high = link::rx();
		spm::fill<off>(address + i, static_cast<std::uint16_t>(low | (high << 8)));
	}
	if (address < base) {
		spm::erase_page<off>(address);
		spm::wait();
		spm::write_page<off>(address);
		spm::wait();
		if constexpr (boot_section)
			spm::rww_enable<off>();
	}
}

// The four fuse/lock bytes in the hardware's own Z order: low, lock,
// extended, high. Writing fuses is not a thing self-programming can do on
// AVR — SPM reaches flash (and boot lock bits) only.
void send_fuses()
{
	for (std::uint8_t which = 0; which < 4; ++which)
		link::tx(spm::read_fuse<off>(static_cast<spm::fuse>(which)));
}

[[noreturn]] void run()
{
	// A watchdog reset belongs to the application (whose watchdog stays
	// forced on until it clears WDRF) — no activation window in its way.
	if (avr::hw::mcusr::wdrf.test())
		run_app();

	link::init();

	std::uint8_t seconds = ee::read(timeout_cell);
	if (seconds == 0 || seconds == 0xff)
		seconds = default_seconds;

	// The knock: 'p' then 'b', each under a fresh window; any other byte is
	// line noise and waits again. Falling out of a window runs the app.
	while (rx_deadline(seconds) != 'p' || rx_deadline(seconds) != 'b') {
	}

	for (;;) {
		// No prompt while an EEPROM write runs: a pending write blocks SPM
		// and fuse reads (§26.2.1), and the ack tells the host all is done.
		ee::wait();
		link::tx(ack);
		switch (link::rx()) {
		case 'b': // info block
			send_flash(reinterpret_cast<std::uint16_t>(info::storage.data()), info::size());
			break;
		case 'R': { // read flash: addr16, n8 (0 = 256)
			std::uint16_t address = rx16();
			send_flash(address, link::rx());
			break;
		}
		case 'W': // program one flash page: addr16, page bytes
			program_flash(rx16());
			break;
		case 'r': { // read EEPROM: addr16, n8
			std::uint16_t address = rx16();
			send_eeprom(address, link::rx());
			break;
		}
		case 'w': { // write EEPROM: addr16, n8, then n bytes each acked
			std::uint16_t address = rx16();
			store_eeprom(address, link::rx());
			break;
		}
		case 'F': // fuse and lock bytes
			send_fuses();
			break;
		case 'G': // hand over to the application
			link::tx(ack);
			run_app();
		default: // unknown bytes are ignored; the loop re-acks
			break;
		}
	}
}

} // namespace
} // namespace pureboot

template struct avr::startup::entry<pureboot::run>;