The second pass concluded the 168 B tricks->asm gap was per-call ABI
cost. Most of it was structure. Rebuilt around the oracle's own shape —
argless noinline primitives over a whole-loader call-saved register
protocol (g_addr in Y, count r16, window r7, direction latch r6), a
top-down erase_below whose loop tests against zero and hands callers
g_addr = 0 for free, bounded rx everywhere (a silent host unwinds to
the app from any state, as the oracle does), and a named tsb_app entry
that --pmem-wrap-around=32k relaxes to the wrapped rjmp:
tsb_asm 510 B in the 512 B section (oracle: 500), C++ except rx
and the page-store loop — the two routines whose remaining
cost is the calling convention itself (~30 asm lines, was
~280)
tsb_tricks 526 B, no assembly at all (was 666)
tsb_pure 836 B, still one readable function per command (was 842)
Every g_* update placement works around a GCC 16.1 wrong-code bug
(stores into global register variables deleted when only callees read
them — repro and rules in libavr dev/lessons.md). Also fixes two
latent hardware bugs all earlier tiers carried, masked by simavr's
zeroed register file: the crt-less entries never established
__zero_reg__ = 0, and the direction latch was read before written —
power-on registers are undefined.
All tiers full oracle feature parity, protocol tests green in both
libavr modes, .text byte-identical across modes.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
387 lines
13 KiB
C++
387 lines
13 KiB
C++
// TinySafeBoot on libavr — tier 3: full feature parity in the 512-byte boot
|
||
// section, in C++ except where the C ABI itself is the cost.
|
||
//
|
||
// The complete TinySafeBoot feature set — watchdog-reset bail, one-wire
|
||
// half-duplex UART, a config-page activation timeout, the password gate,
|
||
// emergency erase, and config/flash/EEPROM read-write — at 510 bytes in the
|
||
// 512-byte BOOTSZ=11 section the hand-written oracle occupies (500 B). This tier used to be one
|
||
// monolithic inline-asm routine; it is now the tricks tier's C++ (same
|
||
// register protocol, same structure — see tsb_tricks.cpp, including the
|
||
// global-register miscompile rules) with exactly two routines kept in
|
||
// assembly, the two whose remaining cost *is* the calling convention:
|
||
//
|
||
// rx the bounded receive: C++ must re-floor the timeout window on every
|
||
// call (the global-register-store miscompile) and split it across
|
||
// call-saved registers; the asm keeps the oracle's X-register nested
|
||
// countdown.
|
||
// store the page-store loop: C++ cannot hold the receive byte pair and the
|
||
// walked Z pointer across the rx calls without call-saved staging
|
||
// (push/pop + a Y→Z copy per word); the asm calls rx knowing exactly
|
||
// which registers it touches and walks Z live across the whole page.
|
||
//
|
||
// Everything else — bring-up, activation, password gate, emergency erase,
|
||
// dispatch, every SPM/EEPROM/flash primitive, every geometry/baud/info
|
||
// constant — is C++ on libavr, and the two asm routines splice into the same
|
||
// global-register protocol the C++ uses (g_addr in Y, g_cnt in r16, g_window
|
||
// in r7, g_receiving in r6), so calls cross the boundary with no marshalling.
|
||
//
|
||
// The wire protocol is strict request/response, which is what makes the shared
|
||
// line safe: the device drives it only between a received command and its
|
||
// reply, and releases it (RXEN0 only) whenever it waits.
|
||
|
||
#include <libavr/libavr.hpp>
|
||
|
||
#include <avr/io.h> // SP / RAMEND for the crt-free boot entry, SFR addresses for the asm routines
|
||
|
||
using namespace avr::literals;
|
||
namespace spm = avr::spm;
|
||
namespace ee = avr::eeprom;
|
||
namespace hw = avr::hw;
|
||
|
||
namespace tsb {
|
||
namespace {
|
||
|
||
// The loader is purely polled — it never enables interrupts — so every SPM and
|
||
// EEPROM lock folds to nothing under this posture.
|
||
constexpr auto off = avr::irq::guard_policy::unused;
|
||
|
||
constexpr std::uint8_t confirm = '!';
|
||
constexpr std::uint8_t request = '?';
|
||
constexpr std::uint8_t knock = '@';
|
||
|
||
// Boot geometry for the 512 B boot section (BOOTSZ=11); the page size and the
|
||
// flash/EEPROM extents are the chip database's to know. app_end is the config
|
||
// page (TSB's LASTPAGE), one page below the boot section.
|
||
constexpr std::uint16_t page = spm::page_bytes;
|
||
constexpr std::uint16_t boot_bytes = 512;
|
||
constexpr std::uint16_t app_end = spm::flash_bytes - boot_bytes - page;
|
||
constexpr std::uint16_t eeprom_end = avr::hw::db.mem.eeprom_size - 1;
|
||
|
||
// Lockout-proof floor for the activation window (the oracle's F_CPU/1MHz).
|
||
constexpr std::uint8_t act_min = 16;
|
||
// Post-activation window: the host gets seconds, not milliseconds, mid-session.
|
||
constexpr std::uint8_t comm_window = 200;
|
||
|
||
constexpr std::uint16_t build_date = 26 * 512 + 7 * 32 + 20;
|
||
|
||
// Fixed 115200 8N1; the library solves UBRR + U2X from clock and baud.
|
||
constexpr auto baud = avr::uart::detail::solve_baud(16_MHz, 115200_Bd);
|
||
|
||
// The 16-byte device-info block, streamed out on activation.
|
||
// clang-format off
|
||
[[gnu::progmem]] constexpr std::uint8_t info[16] = {
|
||
'T', 'S', 'B',
|
||
build_date & 0xFF, build_date >> 8,
|
||
0xF3, // status: native-UART fixed-baud lineage
|
||
0x1E, 0x95, 0x0F, // ATmega328P signature
|
||
page / 2, // page size in words
|
||
(app_end / 2) & 0xFF, (app_end / 2) >> 8,
|
||
eeprom_end & 0xFF, eeprom_end >> 8,
|
||
0xAA, 0xAA,
|
||
};
|
||
// clang-format on
|
||
|
||
register std::uint16_t g_addr asm("r28");
|
||
register std::uint8_t g_cnt asm("r16");
|
||
register std::uint8_t g_window asm("r7");
|
||
register std::uint8_t g_receiving asm("r6");
|
||
|
||
const std::uint8_t *flash_ptr(std::uint16_t addr)
|
||
{
|
||
return reinterpret_cast<const std::uint8_t *>(addr);
|
||
}
|
||
|
||
// Bounded byte receive (asm 1 of 2): release the one-wire line on a direction
|
||
// change, poll RXC0 under the oracle's nested X-register countdown seeded from
|
||
// g_window (floored against lockout), byte or 0-on-silence in r24. Z survives
|
||
// — the property the store's word loop rides on.
|
||
[[gnu::noinline, gnu::noclone]] std::uint8_t rx()
|
||
{
|
||
std::uint8_t byte;
|
||
asm volatile(" tst %[dir] \n\t" // already receiving? keep the line released
|
||
" brne 1f \n\t"
|
||
" ldi %[b], 0x10 \n\t" // RXEN0 alone: release the line and listen
|
||
" sts %[ucsr0b], %[b] \n\t"
|
||
" ser %[b] \n\t"
|
||
" mov %[dir], %[b] \n\t"
|
||
"1: mov r27, %[to] \n\t" // outer countdown high byte = window
|
||
" ori r27, %[actmin] \n\t" // lockout-proof floor
|
||
" clr r26 \n\t"
|
||
"2: ser %[b] \n\t"
|
||
"3: lds %[b], %[ucsr0a] \n\t"
|
||
" sbrc %[b], 7 \n\t" // RXC0
|
||
" rjmp 4f \n\t"
|
||
" dec %[b] \n\t"
|
||
" brne 3b \n\t"
|
||
" sbiw r26, 1 \n\t"
|
||
" brcc 2b \n\t"
|
||
" clr %[b] \n\t" // silence → 0, which no compare accepts
|
||
" rjmp 5f \n\t"
|
||
"4: lds %[b], %[udr0] \n\t"
|
||
"5: \n\t"
|
||
: [b] "=&d"(byte), [dir] "+r"(g_receiving)
|
||
: [to] "r"(g_window), [actmin] "M"(act_min), [ucsr0a] "n"(_SFR_MEM_ADDR(UCSR0A)),
|
||
[ucsr0b] "n"(_SFR_MEM_ADDR(UCSR0B)), [udr0] "n"(_SFR_MEM_ADDR(UDR0))
|
||
: "r26", "r27", "cc");
|
||
return byte;
|
||
}
|
||
|
||
// One-wire transmit: take the line (TXEN0 alone) on a direction change with a
|
||
// turn-around guard, put the byte out, hold the line until the whole frame is
|
||
// out (TXC0, not UDRE0), W1C TXC0 by storing the sampled status back (keeps
|
||
// U2X0). Plain C++ — it compiles *smaller* than the oracle's routine.
|
||
[[gnu::noinline, gnu::noclone]] void tx(std::uint8_t byte)
|
||
{
|
||
if (g_receiving) {
|
||
g_receiving = 0;
|
||
hw::ucsr0b::write(hw::ucsr0b::txen0(1));
|
||
for (std::uint8_t guard = 46; guard; --guard)
|
||
;
|
||
}
|
||
hw::udr0::write(byte);
|
||
std::uint8_t status;
|
||
do {
|
||
status = hw::ucsr0a::read();
|
||
} while (!(status & hw::ucsr0a::txc0(1).value));
|
||
hw::ucsr0a::write(status);
|
||
}
|
||
|
||
// '?', then hand back the host's reply for the callers' one-byte compare.
|
||
[[gnu::noinline, gnu::noclone]] std::uint8_t rcnf()
|
||
{
|
||
tx(request);
|
||
return rx();
|
||
}
|
||
|
||
// One flash byte ← [g_addr++] (the advance right before ret — the
|
||
// global-register rule, see tsb_tricks.cpp).
|
||
[[gnu::noinline, gnu::noclone]] std::uint8_t sflash()
|
||
{
|
||
std::uint8_t byte = avr::flash_load(flash_ptr(g_addr));
|
||
++g_addr;
|
||
return byte;
|
||
}
|
||
|
||
// One EEPROM byte ← [g_addr++].
|
||
[[gnu::noinline, gnu::noclone]] std::uint8_t eerd()
|
||
{
|
||
std::uint8_t byte = ee::read(g_addr);
|
||
++g_addr;
|
||
return byte;
|
||
}
|
||
|
||
// One EEPROM byte → [g_addr++].
|
||
[[gnu::noinline, gnu::noclone]] void eewr(std::uint8_t byte)
|
||
{
|
||
ee::write<off>(g_addr, byte);
|
||
++g_addr;
|
||
}
|
||
|
||
// Stream g_cnt flash bytes from g_addr to the host.
|
||
[[gnu::noinline, gnu::noclone]] void sendf()
|
||
{
|
||
do {
|
||
tx(sflash());
|
||
} while (--g_cnt);
|
||
}
|
||
|
||
// Wait out a running SPM op, then re-open the RWW section — after every page
|
||
// op and before handing over, as the oracle does.
|
||
[[gnu::noinline, gnu::noclone]] void settle()
|
||
{
|
||
spm::wait();
|
||
spm::rww_enable<off>();
|
||
}
|
||
|
||
extern "C" [[noreturn]] void tsb_app(); // the application's reset vector: --defsym=tsb_app=0
|
||
|
||
[[noreturn]] void appjump()
|
||
{
|
||
settle();
|
||
tsb_app();
|
||
}
|
||
|
||
// Step g_addr one page down and erase that page (the decrement lives here —
|
||
// the global-register rule).
|
||
[[gnu::noinline, gnu::noclone]] void erase_below()
|
||
{
|
||
g_addr -= page;
|
||
spm::erase_page<off>(g_addr);
|
||
settle();
|
||
}
|
||
|
||
// Erase the whole application, top-down like the oracle: the loop bound is a
|
||
// compare with zero, and g_addr = 0 is handed back for free.
|
||
[[gnu::noinline, gnu::noclone]] void erase_application()
|
||
{
|
||
g_addr = app_end;
|
||
do {
|
||
erase_below();
|
||
} while (g_addr != 0);
|
||
}
|
||
|
||
// Stream one host page into the erased flash page at g_addr (asm 2 of 2): the
|
||
// word pair stages in r0:r1 straight from rx (whose register set is known —
|
||
// the cross-call liveness C++ cannot express), Z walks the page and PGWRT
|
||
// programs it. g_addr is left at the next page base.
|
||
[[gnu::noinline, gnu::noclone]] void store_flash()
|
||
{
|
||
asm volatile(" movw r30, r28 \n\t" // Z = page base; rx leaves Z live
|
||
" ldi r20, %[words] \n\t"
|
||
"1: rcall %x[rx] \n\t"
|
||
" mov r0, r24 \n\t" // word low byte
|
||
" rcall %x[rx] \n\t"
|
||
" mov r1, r24 \n\t" // word high byte
|
||
" ldi r24, 0x01 \n\t" // SPMEN: buffer the word at Z
|
||
" out %[spmcsr], r24 \n\t"
|
||
" spm \n\t"
|
||
" clr r1 \n\t"
|
||
" adiw r30, 2 \n\t"
|
||
" dec r20 \n\t"
|
||
" brne 1b \n\t"
|
||
" movw %[base], r30 \n\t" // g_addr = the next page base
|
||
" subi r30, %[pagelo] \n\t" // Z back to this page's base
|
||
" sbci r31, %[pagehi] \n\t"
|
||
" ldi r24, 0x05 \n\t" // PGWRT | SPMEN: program the page
|
||
" out %[spmcsr], r24 \n\t"
|
||
" spm \n\t"
|
||
: [base] "+r"(g_addr)
|
||
: [rx] "i"(&rx), [spmcsr] "I"(_SFR_IO_ADDR(SPMCSR)), [words] "M"(page / 2), [pagelo] "M"(page & 0xff),
|
||
[pagehi] "M"(page >> 8)
|
||
: "r0", "r1", "r20", "r24", "r26", "r27", "r30", "r31", "cc", "memory");
|
||
settle();
|
||
}
|
||
|
||
[[noreturn, gnu::noinline]] void run()
|
||
{
|
||
// A watchdog reset hands straight back to the application, as the
|
||
// reference loader does, rather than re-entering the bootloader.
|
||
if (hw::mcusr::wdrf.test())
|
||
appjump();
|
||
|
||
// Lean bring-up from reset state: UCSR0C already reads 8N1, UBRR0H reads
|
||
// 0, and rx()/tx() raise RXEN0/TXEN0 on first use — only the divisor low
|
||
// byte and U2X0 need a store. The library still does the datasheet work.
|
||
static_assert(baud.u2x && baud.ubrr < 256, "lean bring-up writes UBRR0L only, with U2X0");
|
||
hw::reg<"UBRR0">::write(static_cast<std::uint8_t>(baud.ubrr));
|
||
hw::ucsr0a::write(hw::ucsr0a::u2x0(1));
|
||
// General-purpose registers are undefined at power-on (no crt zeroes them);
|
||
// the direction latch must start "not receiving" so the first rx() enables
|
||
// the receiver. The reference loader clears its shadow register for the
|
||
// same reason.
|
||
g_receiving = 0;
|
||
|
||
// Activation: 3×'@', each inside the config page's timeout window (rx
|
||
// floors it so a corrupt page cannot lock the loader out); anything else —
|
||
// including silence — hands over.
|
||
g_window = avr::flash_load(flash_ptr(app_end + 2));
|
||
for (std::uint8_t k = 3; k; --k)
|
||
if (rx() != knock)
|
||
appjump();
|
||
g_window = comm_window;
|
||
|
||
// Password gate (config page from app_end+3, 0xff-terminated; a blank
|
||
// page is no password). A wrong byte blanks the comparison and drains the
|
||
// line forever, so a wrong password can never fall through; a 0 requests
|
||
// emergency erase behind two confirms. On pass the info block goes out;
|
||
// the emergency path skips it and drops into the command loop.
|
||
g_addr = app_end + 3;
|
||
std::uint8_t mask = 0xff;
|
||
for (;;) {
|
||
std::uint8_t expected = avr::flash_load(flash_ptr(g_addr)) & mask;
|
||
++g_addr;
|
||
if (expected == 0xff) {
|
||
g_addr = reinterpret_cast<std::uint16_t>(&info[0]);
|
||
g_cnt = sizeof(info);
|
||
sendf();
|
||
break;
|
||
}
|
||
std::uint8_t got = rx();
|
||
if (got == 0) {
|
||
if (mask == 0)
|
||
continue;
|
||
if (rcnf() != confirm || rcnf() != confirm)
|
||
appjump();
|
||
erase_application(); // leaves g_addr = 0 for the EEPROM walk
|
||
do {
|
||
eewr(0xff);
|
||
} while (g_addr <= eeprom_end);
|
||
g_addr = app_end + page;
|
||
erase_below();
|
||
break;
|
||
}
|
||
if (got != expected)
|
||
mask = 0;
|
||
}
|
||
|
||
for (;;) {
|
||
tx(confirm); // Mainloop ready
|
||
g_addr = 0;
|
||
switch (rx()) {
|
||
case 'f': // read application flash, one page per host '!'
|
||
for (;;) {
|
||
if (rx() != confirm)
|
||
break;
|
||
g_cnt = page;
|
||
sendf();
|
||
if (g_addr >= app_end)
|
||
break;
|
||
}
|
||
break;
|
||
case 'F': // erase the application, then take pages behind '?'
|
||
erase_application(); // leaves g_addr = 0, the write start
|
||
while (rcnf() == confirm)
|
||
store_flash();
|
||
break;
|
||
case 'e': // read EEPROM, one page per host '!', until the host stops
|
||
for (;;) {
|
||
if (rx() != confirm)
|
||
break;
|
||
g_cnt = page;
|
||
do {
|
||
tx(eerd());
|
||
} while (--g_cnt);
|
||
}
|
||
break;
|
||
case 'E': // take EEPROM pages behind '?'
|
||
while (rcnf() == confirm) {
|
||
g_cnt = page;
|
||
do {
|
||
eewr(rx());
|
||
} while (--g_cnt);
|
||
}
|
||
break;
|
||
case 'c': // read the config page
|
||
read_config:
|
||
g_addr = app_end;
|
||
g_cnt = page;
|
||
sendf();
|
||
break;
|
||
case 'C': // replace the config page, then echo it back to verify
|
||
if (rcnf() != confirm)
|
||
break;
|
||
g_addr = app_end + page;
|
||
erase_below(); // leaves g_addr = app_end, the store target
|
||
store_flash();
|
||
goto read_config;
|
||
default: // 'q' or any other byte runs the application
|
||
appjump();
|
||
}
|
||
}
|
||
}
|
||
|
||
} // namespace
|
||
} // namespace tsb
|
||
|
||
// Reset lands here: BOOTRST vectors to the boot section base and .vectors is
|
||
// laid first, so this is the first instruction executed. No crt ran, so set
|
||
// the stack pointer before anything is called.
|
||
extern "C" [[gnu::naked, gnu::used, gnu::section(".vectors")]] void __boot_entry()
|
||
{
|
||
SP = RAMEND;
|
||
// The one line of crt this loader needs: compiled code assumes
|
||
// __zero_reg__ (r1) is 0, and power-on registers are undefined.
|
||
asm volatile("clr __zero_reg__");
|
||
tsb::run();
|
||
}
|