BlackMark
74d8b92885
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>
96 lines
4.6 KiB
CMake
96 lines
4.6 KiB
CMake
cmake_minimum_required(VERSION 3.28)
|
|
|
|
project(tsb_libavr LANGUAGES CXX)
|
|
|
|
# libavr from a local checkout (LIBAVR_ROOT) or the forge; the toolchain file
|
|
# comes from the same checkout via CMakePresets.json.
|
|
include(FetchContent)
|
|
if(NOT LIBAVR_ROOT AND DEFINED ENV{LIBAVR_ROOT})
|
|
set(LIBAVR_ROOT $ENV{LIBAVR_ROOT})
|
|
endif()
|
|
if(LIBAVR_ROOT)
|
|
FetchContent_Declare(libavr SOURCE_DIR ${LIBAVR_ROOT})
|
|
else()
|
|
FetchContent_Declare(libavr GIT_REPOSITORY git@git.blackmark.me:avr/libavr.git GIT_TAG main)
|
|
endif()
|
|
FetchContent_MakeAvailable(libavr)
|
|
|
|
if(PROJECT_IS_TOP_LEVEL)
|
|
add_compile_options(-Werror) # warnings are errors for the port's own code
|
|
enable_testing()
|
|
|
|
# The behavioral test drives the real TinySafeBoot wire protocol over a
|
|
# simavr pty (as the host tools do) and actually flashes the device. The
|
|
# runner is a host program built at configure time against libsimavr; if it
|
|
# or Python is missing, only the size tests run.
|
|
find_program(_host_cc NAMES cc gcc)
|
|
find_package(Python3 COMPONENTS Interpreter)
|
|
if(_host_cc AND Python3_FOUND)
|
|
set(TSB_DEVICE ${CMAKE_BINARY_DIR}/tsb_device)
|
|
execute_process(
|
|
COMMAND ${_host_cc} -O2 -I/usr/include/simavr -I/usr/include/simavr/parts
|
|
-o ${TSB_DEVICE} ${CMAKE_CURRENT_SOURCE_DIR}/test/device.c
|
|
-lsimavr -lsimavrparts -lelf
|
|
RESULT_VARIABLE _dev_res ERROR_VARIABLE _dev_err)
|
|
if(NOT _dev_res EQUAL 0)
|
|
message(STATUS "tsb_device not built (${_dev_err}) — protocol tests skipped")
|
|
unset(TSB_DEVICE)
|
|
endif()
|
|
endif()
|
|
endif()
|
|
|
|
# The TinySafeBoot protocol reimplemented on libavr in three variants that trade
|
|
# clarity for size. Each links into the ATmega328P boot section (BOOTSZ selects
|
|
# its size; BOOTRST vectors a reset to its base) with -nostartfiles — a polled
|
|
# loader has no use for the crt or the vector table. The naked entry sits in
|
|
# .vectors, laid first, and runs. The boot base is FLASHEND+1 minus the section
|
|
# size; the linker section-start and the source's boot_bytes agree. tsb_app is
|
|
# the application's reset vector, pinned to 0 here so the loaders jump to a
|
|
# named function; --pmem-wrap-around lets relaxation turn that absolute jump
|
|
# into the wrapped rjmp AVR's modulo-flash PC actually executes.
|
|
# All three implement the full oracle feature set (see oracle/README.md):
|
|
# watchdog bail, one-wire half-duplex, config-page activation timeout, password
|
|
# gate, emergency erase, config/flash/EEPROM read-write. They differ only in how,
|
|
# and the size gradient is the cost of that "how" — see dev/lessons.md.
|
|
# tsb_asm — the tricks tier's C++ with exactly two routines in asm (the
|
|
# bounded rx and the page-store loop — the two whose remaining
|
|
# cost is the C ABI itself): 510 B in the 512 B section the
|
|
# hand-written 500 B oracle occupies. Everything else, from
|
|
# bring-up to dispatch, is C++ on libavr.
|
|
# tsb_tricks — no asm at all: the whole-loader register allocation lives in
|
|
# global register variables (Y walks the page pointer), every
|
|
# helper is a tiny noinline primitive placed by the
|
|
# global-register store rules, pages stream straight to
|
|
# SPM/EEPROM, and the bring-up is the two reset-non-default
|
|
# registers only. 526 B in the 1 KB section (BOOTSZ=10) — 14
|
|
# over the oracle's section, from 168 over at this tier's first
|
|
# floor.
|
|
# tsb_pure — pure idiomatic libavr, one function per command, TU-local
|
|
# (internal linkage), streaming (no SRAM page buffer): 836 B in
|
|
# the 1 KB section.
|
|
#
|
|
# add_tsb_variant(<name> <boot-section-bytes>)
|
|
function(add_tsb_variant name bytes)
|
|
math(EXPR base_dec "32768 - ${bytes}")
|
|
math(EXPR base_hex "${base_dec}" OUTPUT_FORMAT HEXADECIMAL)
|
|
add_executable(${name} tsb/${name}.cpp)
|
|
target_link_libraries(${name} PRIVATE libavr)
|
|
target_link_options(${name} PRIVATE -nostartfiles -Wl,--section-start=.text=${base_hex}
|
|
-Wl,--defsym=tsb_app=0 -Wl,--pmem-wrap-around=32k)
|
|
add_custom_command(TARGET ${name} POST_BUILD COMMAND ${CMAKE_SIZE} $<TARGET_FILE:${name}>)
|
|
if(PROJECT_IS_TOP_LEVEL)
|
|
add_test(NAME ${name}.size
|
|
COMMAND ${CMAKE_COMMAND} -DSIZE_TOOL=${CMAKE_SIZE} -DELF=$<TARGET_FILE:${name}>
|
|
-DLIMIT=${bytes} -P ${CMAKE_CURRENT_SOURCE_DIR}/test/check_size.cmake)
|
|
if(DEFINED TSB_DEVICE)
|
|
add_test(NAME ${name}.protocol
|
|
COMMAND ${Python3_EXECUTABLE} ${CMAKE_CURRENT_SOURCE_DIR}/test/tsbtest.py
|
|
${TSB_DEVICE} $<TARGET_FILE:${name}> ${base_hex})
|
|
endif()
|
|
endif()
|
|
endfunction()
|
|
|
|
add_tsb_variant(tsb_asm 512)
|
|
add_tsb_variant(tsb_pure 1024)
|
|
add_tsb_variant(tsb_tricks 1024)
|