// SUPERSEDED — kept for the record, not built. With the activation hang fixed
// (a lone calibration pulse used to wedge the loader, see autobaud.md) this
// version is 530 B on the 1284P against a 512 B slot. Its 4 B of margin was
// never spare capacity; it was the space the missing fix should have occupied.
// pureboot_autobaud_uni.cpp replaces it at 464 B with more features.
//
// pureboot autobaud — the software-serial variant that measures the host's bit
// timing at runtime, so one binary runs at any F_CPU: the image carries no
// clock. THE PURE VERSION — no inline assembly, no global register variables,
// exactly the constraints the fixed-baud loader keeps.
//
// Two source files exist for review (autobaud.md):
// this one, pure, and pureboot_autobaud_reg.cpp, which keeps the running-slot
// write guard at the cost of one global register variable. They differ only in
// where the measured unit lives and whether the guard is present.
//
// What this version trades to fit 512 B in pure C++ (the 1284 at 508), each
// licensed by "the host guarantees safety" (README.md) and the owner's approval
// to simplify the info block:
//   - the measured per-bit unit lives in the two general-purpose I/O scratch
//     registers (GPIOR) where the chip has them, in a static otherwise —
//     reached through libavr's named register surface, so no asm and no global
//     register variable; the loader stays pure;
//   - the info block is slimmed to the version and the signature — the chip's
//     identity — from which the host derives page size, loader base, EEPROM
//     size and the addressing flags via its own chip database;
//   - no running-slot write guard: the host never programs the loader's own
//     slot, and a broken host bricking the target is the host's bug;
//   - a single-byte activation knock: the calibration pulse already proves a
//     host is present.
//
// Position independence is kept and is in fact total here: control flow is
// PC-relative, the wire carries addresses, and with the slimmed info block and
// no write guard nothing anchors on the runtime address at all.

#include <libavr/libavr.hpp>

#include <util/delay_basic.h>

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

namespace pureboot {
namespace {

// Purely polled: every interrupt guard folds to nothing.
constexpr auto off = avr::irq::guard_policy::unused;

constexpr std::uint8_t ack = '+';

// Autobaud carries no clock, so PUREBOOT_CLOCK_HZ / PUREBOOT_BAUD are not
// consulted; only the software-UART pins are a deployment parameter.
#if !defined(PUREBOOT_RX)
#define PUREBOOT_RX pb0
#endif
#if !defined(PUREBOOT_TX)
#define PUREBOOT_TX pb1
#endif

// The watchdog reset flag's home: MCUSR, or the classic megas' MCUCSR.
consteval std::int16_t wdrf_field()
{
	auto reg = std::string_view{hw::db.regs[static_cast<std::size_t>(avr::power::detail::reset_reg())].name};
	return hw::db.field_index(reg, "WDRF");
}

// The loader owns the top 512 bytes; a staging copy goes in the slot below.
constexpr std::uint16_t slot_bytes = 512;
constexpr std::uint32_t base = spm::flash_bytes - slot_bytes;
constexpr std::uint16_t page = spm::page_bytes;
constexpr bool boot_section = hw::curated::has_boot_section();

// Past 64 KiB a byte address no longer fits the wire's 16 bits, so flash
// addresses there are word addresses ('J' always was one).
constexpr bool word_flash = spm::flash_bytes > 65536;

// The loader's one identity number (README.md); the slimmed info block carries
// it and the signature, and the host maps a version to its protocol.
constexpr std::uint8_t version = 4;

// The activation window as a fixed poll budget: with no clock, whole seconds
// cannot be timed. A __uint24 (AVR's three-byte type) holds it — a fourth byte
// would cost two words at each countdown step for range never used.
#if !defined(PUREBOOT_AUTOBAUD_POLLS)
#define PUREBOOT_AUTOBAUD_POLLS 4000000
#endif
constexpr __uint24 autobaud_budget = PUREBOOT_AUTOBAUD_POLLS;

// The measured per-bit delay (in _delay_loop_2 four-cycle iterations). It lives
// in the two adjacent general-purpose I/O scratch registers (GPIOR1:GPIOR2)
// where the chip has them — in/out reach them in one word where a static's
// lds/sts take two, and there is no .bss to clear — and in a plain static
// otherwise (the t13, m8 and m16/32 have no GPIOR). Both are pure: the named
// register surface, no inline asm, no global register variable.
constexpr bool have_gpior = hw::db.reg_index("GPIOR1") >= 0 && hw::db.reg_index("GPIOR2") >= 0;

std::uint16_t unit_backing;

template <bool Gpior = have_gpior>
[[gnu::always_inline]] inline std::uint16_t get_unit()
{
	if constexpr (Gpior)
		return static_cast<std::uint16_t>(hw::reg_impl<hw::db.reg_index("GPIOR1")>::read() |
		                                  (hw::reg_impl<hw::db.reg_index("GPIOR2")>::read() << 8));
	else
		return unit_backing;
}

template <bool Gpior = have_gpior>
[[gnu::always_inline]] inline void put_unit(std::uint16_t u)
{
	if constexpr (Gpior) {
		hw::reg_impl<hw::db.reg_index("GPIOR1")>::write(static_cast<std::uint8_t>(u));
		hw::reg_impl<hw::db.reg_index("GPIOR2")>::write(static_cast<std::uint8_t>(u >> 8));
	} else
		unit_backing = u;
}

// The autobaud software link: bit-banged with cycle-counted delays like the
// fixed-baud software backend, but the per-bit delay is the measured unit, not
// a consteval constant. rx/tx load the unit once into a local, so each bit
// spins from a register with no per-bit reload.
struct link {
	using in_t = avr::io::input<avr::PUREBOOT_RX, avr::io::pull::up>;
	using out_t = avr::io::output<avr::PUREBOOT_TX>;

	static void init()
	{
		avr::init<in_t, out_t>();
		out_t::set(); // idle high
	}

	// Time the calibration pulse into the unit. The host sends 0xC0 — a start
	// bit plus six zero data bits are one low pulse of seven bit-times — and the
	// counted poll loop is seven cycles an iteration, so the count is the pulse
	// length in cycles ÷ 7 × 7 = one bit period in cycles, and count >> 2 is that
	// period in _delay_loop_2's four-cycle iterations. Waits for the start edge
	// under the poll budget; 0 (returned, and stored) means the budget expired.
	static std::uint16_t measure(__uint24 budget)
	{
		while (in_t::read())
			if (!--budget)
				return 0;
		std::uint16_t count = 0;
		while (!in_t::read())
			++count;
		const std::uint16_t u = static_cast<std::uint16_t>(count >> 2);
		put_unit(u);
		return u;
	}

	// The eight data bits, entered just past the falling edge of the start bit.
	// Split out of rx() so the activation path can wait for that edge under a
	// budget while the command loop waits for it indefinitely.
	static std::uint8_t sample()
	{
		const std::uint16_t unit = get_unit();
		_delay_loop_2(static_cast<std::uint16_t>(unit + (unit >> 1))); // 1.5 bits to the LSB centre
		std::uint8_t value = 0;
		for (std::uint8_t bit = 0; bit < 8; ++bit) {
			value >>= 1;
			if (in_t::read())
				value |= 0x80;
			_delay_loop_2(unit);
		}
		return value;
	}

	static std::uint8_t rx()
	{
		while (in_t::read()) // await the start edge
			;
		return sample();
	}

	// A byte under the poll budget, for the activation knock. An expired budget
	// returns 0, which is not the knock, so the caller falls back into the
	// budgeted measure() — and a line that stays idle boots the application
	// there. Without this the knock's edge wait was unbounded, so a single
	// spurious calibration pulse (EMI, or a host that opens the port and never
	// knocks) wedged the loader and the application never ran.
	static std::uint8_t rx_bounded(__uint24 budget)
	{
		while (in_t::read())
			if (!--budget)
				return 0;
		return sample();
	}

	static void tx(std::uint8_t value)
	{
		const std::uint16_t unit = get_unit();
		out_t::clear(); // start bit
		_delay_loop_2(unit);
		for (std::uint8_t bit = 0; bit < 8; ++bit) {
			out_t::write(value & 1);
			value >>= 1;
			_delay_loop_2(unit);
		}
		out_t::set(); // stop bit
		_delay_loop_2(unit);
	}

	static void drain()
	{
		// The software transmitter returns only after the stop bit.
	}
};

extern "C" [[noreturn]] void pureboot_app();

[[gnu::noipa, noreturn]] void jump(void (*target)())
{
	target();
	__builtin_unreachable();
}

[[gnu::noinline, noreturn]] void run_app()
{
	jump(pureboot_app);
}

// Inlined: read across a call, the first byte strands in a call-saved register
// the caller has to push and pop.
[[gnu::always_inline]] inline std::uint16_t rx16()
{
	std::uint16_t low = link::rx();
	return static_cast<std::uint16_t>(low | (link::rx() << 8));
}

[[gnu::always_inline]] inline std::uint16_t word_of(std::array<std::uint8_t, 2> pair)
{
	return std::bit_cast<std::uint16_t>(pair);
}

[[maybe_unused, gnu::always_inline]] inline void send_flash_near(std::uint16_t address, std::uint8_t count)
{
	do
		link::tx(avr::flash_load(reinterpret_cast<const std::uint8_t *>(address++)));
	while (--count);
}

[[maybe_unused, gnu::always_inline]] inline void send_flash_far(std::uint16_t address, std::uint8_t count)
{
	std::uint8_t rampz = static_cast<std::uint8_t>(address >> 15);
	std::uint16_t z = static_cast<std::uint16_t>(address << 1);
	do {
		link::tx(avr::flash_load_far<std::uint8_t>((static_cast<std::uint32_t>(rampz) << 16) | z));
		if (++z == 0)
			++rampz;
	} while (--count);
}

[[gnu::always_inline]] inline void send_flash(std::uint16_t address, std::uint8_t count)
{
	if constexpr (word_flash)
		send_flash_far(address, count);
	else
		send_flash_near(address, count);
}

[[gnu::noinline]] void tx_ack()
{
	link::tx(ack);
}

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

void store_eeprom(std::uint16_t address, std::uint8_t count)
{
	do {
		ee::write<off>(address++, link::rx());
		tx_ack();
	} while (--count);
}

// One page into the SPM buffer, then erase and program. No running-slot write
// guard: the host guarantees it never targets the loader's own slot (the pure
// version's one dropped safety net, licensed — README.md).
void program_flash(std::uint16_t wire_address)
{
	spm::flash_address_t address;
	if constexpr (word_flash) {
		const std::uint8_t rampz = static_cast<std::uint8_t>(wire_address >> 15);
		const std::uint16_t z0 = static_cast<std::uint16_t>(wire_address << 1) & ~static_cast<std::uint16_t>(page - 1);
		std::uint16_t z = z0;
		do {
			std::uint8_t low = link::rx();
			std::uint8_t high = link::rx();
			spm::fill<off>((static_cast<spm::flash_address_t>(rampz) << 16) | z, word_of({low, high}));
			z += 2;
		} while (static_cast<std::uint8_t>(z));
		address = (static_cast<spm::flash_address_t>(rampz) << 16) | z0;
	} else {
		address = static_cast<spm::flash_address_t>(wire_address & ~static_cast<std::uint16_t>(page - 1));
		do {
			std::uint8_t low = link::rx();
			std::uint8_t high = link::rx();
			spm::fill<off>(address, word_of({low, high}));
			address += 2;
		} while (static_cast<std::uint8_t>(address) & (page - 1));
		address -= 2; // back inside the page — erase and write ignore the word bits
	}
	spm::erase_page<off>(address);
	if constexpr (boot_section)
		spm::wait();
	spm::write_page<off>(address);
	if constexpr (boot_section)
		spm::wait();
	if constexpr (boot_section)
		spm::rww_enable<off>();
}

void send_fuses()
{
	std::uint8_t which = 0;
	do
		link::tx(spm::read_fuse<off>(static_cast<spm::fuse>(which)));
	while (++which != 4);
}

[[noreturn]] void run()
{
	if (hw::field_impl<wdrf_field()>::test())
		run_app();

	link::init();

	// Measure the calibration pulse into the unit, then take one 'p' knock. An
	// expired budget (no host) boots the application; a pulse that decodes to
	// anything but 'p' re-measures.
	for (;;) {
		if (link::measure(autobaud_budget) == 0)
			run_app();
		if (link::rx_bounded(autobaud_budget) == 'p')
			break;
	}

	for (;;) {
		ee::wait();
		tx_ack();
		const std::uint8_t command = link::rx();
		switch (command) {
		case 'J': { // jump to a wire word address: hand-over and staging transfer
			auto target = reinterpret_cast<void (*)()>(rx16());
			tx_ack();
			link::drain();
			jump(target);
		}
		case 'b': // chip identity: version then the three signature bytes
			link::tx(version);
			link::tx(hw::db.signature[0]);
			link::tx(hw::db.signature[1]);
			link::tx(hw::db.signature[2]);
			break;
		case 'R':   // read flash: addr16, n8 (0 = 256)
		case 'r':   // read EEPROM: addr16, n8
		case 'w': { // write EEPROM: addr16, n8, then n bytes each acked
			// One address-and-count path for the three, so the flash streamer
			// keeps a single call site and inlines into this never-returning
			// loop — its cursor then lives in the loop's own call-saved
			// registers instead of being saved and restored around a call
			// (the call-site-count lesson, autobaud.md).
			const std::uint16_t address = rx16();
			const std::uint8_t count = link::rx();
			if (command == 'r')
				send_eeprom(address, count);
			else if (command == 'w')
				store_eeprom(address, count);
			else
				send_flash(address, count);
			break;
		}
		case 'W': // program one flash page: addr16, page bytes
			program_flash(rx16());
			break;
		case 'F': // fuse and lock bytes
			send_fuses();
			break;
		default: // unknown bytes are ignored; the loop re-acks
			break;
		}
	}
}

} // namespace
} // namespace pureboot

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