Files
bootloader/test/pbautobaud.py
BlackMark 7702c6b700 test: gate autobaud's logic floor, and say what an RC oscillator costs
The ATtiny13A run left autobaud's low-clock lock looking unreliable: 1/5 at
19200 on a 1.2 MHz RC part. The simulator does not reproduce it. At an exact
clock the calibration is solid down to ~36 cycles a bit and fails outright by
~31 — a sharp edge, not a fraying one — where the real part was already 1 in 5
by ~59. So the effect is the oscillator's own jitter and not backend logic, and
the two floors are different quantities about a factor of two apart.

Both are worth having. pureboot.autobaud gates a tight-bit point, since its two
existing clock points both sat near 100 cycles a bit and would not notice the
floor moving. The README carries the other half: both floors side by side, the
per-clock envelope measured on silicon, and the reason budgeting the logic's ~36
on an RC part is wrong.

It also carries the trap that produced the confusion. On a patched-vector chip an
erased application region walks back up into the loader, so every expired window
opens another and the host's retries eventually catch the pulse — 5/5 where the
same part with an application resident gives 1/5. Measure with an application in
place, or the fixture flatters the backend.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-27 16:44:21 +02:00

187 lines
9.8 KiB
Python

#!/usr/bin/env python3
"""End-to-end autobaud test: drive an autobaud loader in simavr through the
calibration handshake and a flash + EEPROM + fuse round-trip, cross-checked
against the simulator's ground-truth memory — then repeat at a second F_CPU with
the *same* loader binary, which is the property autobaud exists for: one
clock-agnostic image that locks onto whatever rate the host sends.
Usage: pbautobaud.py <device_bin> <loader_elf> <mcu> <base_hex> <page>
<app_bin> <app_hz> <app_baud> <tool_py> <workdir>
The loader is a software-serial build on PB0/PB1 (pureboot_add_autobaud's
default), so the runner drives it over the GPIO⇄pty bridge (-l sw:B0,B1). The
app fixture is built for (app_hz, app_baud); the hand-over is checked at that
point, and a second point at half the clock proves the lock is measured, not
baked in.
"""
import os
import sys
import time
def fail(message):
print(f"FAIL: {message}")
sys.exit(1)
def main():
(device_bin, elf, mcu, base_hex, page, app_bin, app_hz, app_baud, tool, workdir) = sys.argv[1:]
base, page, app_hz, app_baud = int(base_hex, 0), int(page), int(app_hz), int(app_baud)
sys.path.insert(0, os.path.dirname(os.path.abspath(tool)))
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
import pbsim
import pureboot as pb
os.makedirs(workdir, exist_ok=True)
ee_image = bytes(range(0xA0, 0xB0))
ee_path = os.path.join(workdir, "ee.bin")
open(ee_path, "wb").write(ee_image)
# The geometry the surgery planner needs, from the chip class the runner is
# told — the same derivation pbtest.py makes: the boot-sectioned megas need
# no vector surgery, the tinies and the boot-section-less m48s do, and the
# large chips speak word addresses.
mega = mcu.startswith("atmega")
patch = not mega or mcu.startswith("atmega48")
word_flash = base + pb.SLOT > 0x10000
wire_base = base // 2 if word_flash else base
flags = (1 if patch else 0) | (2 if word_flash else 0)
ground_truth = pb.Info(bytes([ord("P"), ord("B"), pb.NEWEST_LOADER, 0, 0, 0, page & 0xFF,
wire_base & 0xFF, wire_base >> 8, 0, 0, flags]))
def round_trip(hz, baud, label, hand_over):
"""One clock point: reset, calibrate + knock, program, verify against the
simulator's own flash, and (at the app's point) hand over to the fixture."""
dump = os.path.join(workdir, f"flash_{label}.bin")
device = pbsim.Device(device_bin, elf, mcu, str(hz), base_hex, page, baud, dump, link="sw:B0,B1")
try:
# The host tool, in autobaud mode, sends the 0xC0 calibration pulse
# and a single knock at `baud`; the loader locks to it.
out = pbsim.run_tool(tool, device.pty, baud, "--autobaud", "--info", "--fuses",
"--flash", app_bin, "--eeprom", ee_path, "--stay")
for needed in ("version", "signature", "fuses", "verify:", "stays"):
if needed not in out:
fail(f"{label}: session output lacks {needed!r}\n{out}")
# Read both memories back over the locked link and check them.
read_flash = os.path.join(workdir, f"rf_{label}.bin")
read_eeprom = os.path.join(workdir, f"re_{label}.bin")
out = pbsim.run_tool(tool, device.pty, baud, "--autobaud", "--verify-flash", app_bin,
"--verify-eeprom", ee_path, "--read-flash", read_flash,
"--read-eeprom", read_eeprom, "--stay")
if out.count("verify:") != 2:
fail(f"{label}: did not verify both memories\n{out}")
if open(read_eeprom, "rb").read()[: len(ee_image)] != ee_image:
fail(f"{label}: EEPROM read-back mismatch")
if hand_over:
# Regression: a calibration pulse with no knock behind it must
# not wedge the loader. The knock's edge wait used to be
# unbudgeted, so one stray low pulse — EMI, or a host that opens
# the port and never knocks — held the loader forever and the
# application never ran. The whole activation is bounded now, so
# the window closes and the app boots; the banner is the proof.
# (The pause lets the loader reach its measurement loop, so the
# pulse is genuinely seen and the test cannot pass vacuously.)
device.reset()
port = pb.Port(device.pty, baud)
try:
time.sleep(0.2)
port.write(bytes((pb.CALIBRATE,)))
# Accumulate rather than match exactly: the reset leaves the
# idle line a framing artefact ahead of the banner, which is
# noise here — the question is only whether the app ran.
seen = b""
deadline = time.monotonic() + 180.0
while b"APP" not in seen and time.monotonic() < deadline:
seen += port.read_available(1.0)
if b"APP" not in seen:
fail(f"{label}: lone calibration pulse wedged the loader — app never bannered, saw {seen!r}")
print(f" {label}: lone calibration pulse does not wedge the loader")
finally:
port.close()
device.reset()
port = pb.Port(device.pty, baud)
try:
loader = pb.Loader(port)
live = loader.connect_autobaud(15)
if not pb.OLDEST_LOADER <= live.version <= pb.NEWEST_LOADER:
fail(f"{label}: loader reports pureboot {live.version}")
if loader.unified:
# pureboot 5's data space. 0x0200 is clear of the
# loader's own .noinit unit at the bottom of SRAM and of
# the stack at the top. Reading it back over the same
# locked link proves both directions of the new space.
probe = bytes(range(0x30, 0x40))
loader.write_ram(0x0200, probe)
if loader.read_ram(0x0200, len(probe)) != probe:
fail(f"{label}: RAM round-trip mismatch")
# The register file and the I/O space share the data
# address space on AVR, so the same command reaches a
# peripheral register. SPMCSR reads back as idle here.
verbose_ram = loader.read_ram(0x0200, 4)
print(f" {label}: RAM read/write ok ({verbose_ram.hex()})")
loader.run_application()
banner = port.read_exact(3, 5.0)
if banner != b"APP":
fail(f"{label}: application banner was {banner!r}")
finally:
port.close()
finally:
device.stop()
# Ground truth (read after the runner exits and writes its dump): what
# the tool programmed must be what the simulator actually holds.
pages = pb.plan_flash(open(app_bin, "rb").read(), ground_truth)
flash_true = open(dump, "rb").read()
for address, data in pages.items():
if flash_true[address : address + page] != data:
fail(f"{label}: simulator flash differs from the programmed image at {address:#06x}")
print(f" {label}: locked at {hz} Hz / {baud} Bd, flash+EEPROM verified"
+ (", hand-over ok" if hand_over else ""))
def must_lock(hz, baud, label):
"""The calibration alone, at a tight bit period. Nothing is programmed —
the question is only whether the loader can still measure the pulse."""
dump = os.path.join(workdir, f"flash_{label}.bin")
device = pbsim.Device(device_bin, elf, mcu, str(hz), base_hex, page, baud, dump,
link="sw:B0,B1")
try:
port = pb.Port(device.pty, baud)
try:
live = pb.Loader(port).connect_autobaud(15)
if live.version != pb.NEWEST_LOADER:
fail(f"{label}: loader reports pureboot {live.version}")
finally:
port.close()
finally:
device.stop()
print(f" {label}: locked at {hz} Hz / {baud} Bd ({hz / baud:.0f} cycles a bit)")
# The app fixture is built for one clock; the hand-over banners there. A
# second point at double that clock, same loader binary, proves the lock is
# measured, not baked in — the whole point of autobaud. (Doubling keeps the
# bit period healthy; halving would drop it below the software UART's floor.)
round_trip(app_hz, app_baud, "clock-a", hand_over=True)
round_trip(app_hz * 2, app_baud, "clock-b", hand_over=False)
# Both points above sit near 100 cycles a bit, which is comfortable. The
# calibration's real floor is far tighter, and it is worth a gate: measured
# here, the lock is solid down to ~36 cycles a bit and fails outright by ~31
# — a sharp edge, not a fraying one. This pins the tightest standard rate the
# fixture's clock reaches, so a change that raises the floor is caught.
#
# It does *not* bound what a real deployment can use. On silicon the
# oscillator's own jitter costs roughly a factor of two: an ATtiny13A on its
# factory RC trim was reliable at ~118 cycles a bit and already locking only
# 1 attempt in 5 by ~59, which no exact-clock simulation can show. The
# deployable envelope is a README matter; this is the logic's floor.
must_lock(app_hz, app_baud * 2, "tight-bit")
print("pbautobaud: calibration lock and flash/EEPROM/fuse round-trip pass at both clocks, "
"and the tight bit period still locks")
if __name__ == "__main__":
main()