// 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, a jump
// — and everything composite (verify, erase, reset-vector surgery, updating
// the loader itself) lives in the host tool. Protocol reference: README.md
// next to this file.
//
// The image is position-independent: control flow is PC-relative, the write
// and read paths take wire addresses, the write guard refuses the 512-byte
// slot the code is *running* in (taken from the runtime return address), the
// info block is read relative to that same anchor, and the application jump
// is an indirect call to an absolute entry. The identical binary therefore
// runs from any 512-byte slot with every command intact: flashed one slot
// below the resident loader it becomes the staging loader that rewrites the
// resident — how pureboot updates itself, host-driven, with no other
// firmware involved.
//
// 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 per awaited knock byte ("pb"); an idle line
// boots the application. A session then stays in the command loop until 'J'
// jumps away 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: the clocks the dogfood boards run (16 MHz crystal on
// the mega, calibrated RC on the tinies). The device signature comes straight
// from the chip database (avr::hw::db.signature) — compile-time data is the
// only universal source, since 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;
}

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

// Geometry: the resident loader owns the top 512 bytes of flash; the word
// below it is the trampoline (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 window, in seconds, is a compile-time constant (the build
// may override it): the whole EEPROM belongs to the application, and
// re-timing the loader is a bootloader self-update with a re-timed binary.
#if !defined(PUREBOOT_TIMEOUT)
#define PUREBOOT_TIMEOUT 8
#endif
constexpr std::uint8_t timeout_seconds = PUREBOOT_TIMEOUT;

// 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
    avr::hw::db.signature[0],
    avr::hw::db.signature[1],
    avr::hw::db.signature[2],
    static_cast<std::uint8_t>(page),
    base & 0xff,
    base >> 8, // app flash ends here; resident 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; drain() holds until
// the last transmitted frame is fully on the wire (the jump hand-over must
// not let the target's re-init clip the ack).
template <avr::hertz_t C>
consteval std::int16_t rxc_field()
{
	return avr::hw::db.field_index("UCSR0A", "RXC0");
}

template <avr::hertz_t C>
consteval std::int16_t txc_field()
{
	return avr::hw::db.field_index("UCSR0A", "TXC0");
}

template <avr::hertz_t C>
consteval std::int16_t status_reg()
{
	return avr::hw::db.reg_index("UCSR0A");
}

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

	// The compiled idle poll: lds UCSR0A (2), sbrc skipping the exit (2),
	// sbiw + sbci + sbci + brne (6).
	static constexpr std::uint8_t poll_cycles = 10;

	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);
	}

	static void drain()
	{
		// write() leaves the byte draining behind it. Clear a stale TXC0
		// first (W1C by writing the sampled status back — the store a hand
		// assembler writes, keeping U2X0), then wait for the fresh
		// completion; with a byte still ahead in the shifter TXC0 cannot
		// re-set until the last pending byte has fully left.
		using status = avr::hw::reg_impl<status_reg<C>()>;
		status::write(status::read());
		while (!avr::hw::field_impl<txc_field<C>()>::test()) {
		}
	}
};

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>;

	// The compiled idle poll: sbis skipping the exit (2), sbiw + sbci +
	// sbci + brne (6).
	static constexpr std::uint8_t poll_cycles = 8;

	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);
	}

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

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

// The application's entry, an absolute address the linker pins (--defsym in
// CMakeLists.txt): 0x0000 on the mega (word 0 stays the application's own
// vector — BOOTRST re-vectors a reset into the loader in hardware) and the
// trampoline word at base - 2 on the tinies. Reaching it must not depend on
// where this copy runs, so the jump goes through a pointer: [[gnu::noipa]]
// keeps the constant from folding back into a PC-relative call.
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);
}

// One activation window is a single 32-bit poll countdown. The divisor is
// the backend's counted poll-loop cycles (its own comment reads them off the
// compiled loop); whole-second precision is all the window promises, so the
// nearest cycle count is plenty.
consteval std::uint32_t window_polls()
{
	return timeout_seconds * static_cast<std::uint32_t>(dev::clock.hz / link::poll_cycles);
}

bool pending_before_deadline()
{
	std::uint32_t polls = window_polls();
	do {
		if (link::pending())
			return true;
	} while (--polls);
	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()
{
	if (!pending_before_deadline())
		run_app();
	return link::rx();
}

std::uint16_t rx16()
{
	std::uint16_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.
// send_flash stays out of line: its two callers ('b' and 'R') otherwise each
// inline a private copy of the loop.
[[gnu::noinline]] 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 — except the 512-byte slot this code runs
// in, which is drained but never programmed, so a copy can never erase
// itself. `slot_high` is the high byte of that running slot's base (run()
// derives it); a broken host thus cannot brick the running loader, and a
// copy flashed one slot lower may rewrite the slot above it — how pureboot
// updates itself. On the mega the RWW section is re-enabled so reads work
// immediately.
void program_flash(std::uint16_t address, std::uint8_t slot_high)
{
	// A buffer word cannot be loaded twice without an erase (§26.2.1), so a
	// refused page's drained data must not linger for the next write:
	// discard the buffer up front — CTPB on the tinies; on the mega writing
	// RWWSRE aborts a pending load (§26.2.2).
	if constexpr (boot_section)
		spm::rww_enable<off>();
	else
		spm::clear_buffer<off>();
	// The address is the loop's only state: pages are aligned, so the walk
	// ends when the offset bits wrap back to zero.
	do {
		std::uint8_t low = link::rx();
		std::uint8_t high = link::rx();
		spm::fill<off>(address, static_cast<std::uint16_t>(low | (high << 8)));
		address += 2;
	} while (static_cast<std::uint8_t>(address) & (page - 1));
	address -= 2; // back inside the page — erase and write ignore the word bits
	const std::uint8_t page_high = static_cast<std::uint8_t>(address >> 8) & 0xfe;
	if (page_high != slot_high) {
		// The tinies halt the CPU through the erase and the write, so only
		// the mega — running on while its RWW section programs — waits.
		spm::erase_page<off>(address);
		if constexpr (boot_section)
			spm::wait();
		spm::write_page<off>(address);
		if constexpr (boot_section) {
			spm::wait();
			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()
{
	std::uint8_t which = 0;
	do
		link::tx(spm::read_fuse<off>(static_cast<spm::fuse>(which)));
	while (++which & 3);
}

[[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();

	// The high byte of the 512-byte-aligned base this copy runs at: the word
	// return address's high byte is the byte address >> 9 (the slot index),
	// doubled back into address terms. program_flash refuses this one slot
	// and the info block is addressed from it, so both follow wherever the
	// code was flashed.
	const std::uint8_t slot_high =
	    static_cast<std::uint8_t>((reinterpret_cast<std::uint16_t>(__builtin_return_address(0)) >> 8) << 1);

	// 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() != 'p' || rx_deadline() != '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);
		const std::uint8_t command = link::rx();
		switch (command) {
		case 'b': { // info block, read relative to the running slot
			// The block sits in the image's first 256 bytes (the build lint
			// asserts it), and slots are 512-aligned — so the low byte of its
			// link address is its offset in any slot, and the high byte of
			// its runtime address is the running slot's. Built as a byte
			// pair so no absolute 16-bit address is ever materialized.
			const std::uint8_t low = static_cast<std::uint8_t>(reinterpret_cast<std::uint16_t>(info::storage.data()));
			send_flash(std::bit_cast<std::uint16_t>(std::array{low, slot_high}), info::size());
			break;
		}
		case 'J': { // jump to a wire word address: hand-over and staging transfer
			auto target = reinterpret_cast<void (*)()>(rx16());
			link::tx(ack);
			link::drain();
			jump(target);
		}
		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
			std::uint16_t address = rx16();
			std::uint8_t count = link::rx();
			if (command == 'R')
				send_flash(address, count);
			else if (command == 'r')
				send_eeprom(address, count);
			else
				store_eeprom(address, count);
			break;
		}
		case 'W': // program one flash page: addr16, page bytes
			program_flash(rx16(), slot_high);
			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>;