threadx/scripts/check_clang.sh

#!/bin/bash
##############################################################################
# Copyright (C) 2026 Eclipse ThreadX contributors
#
# This program and the accompanying materials are made available under the
# terms of the MIT License which is available at
# https://opensource.org/licenses/MIT.
#
# AI Disclosure: This file was largely AI-generated by Claude Code (Opus 5).
# The AI-generated portions may be considered public domain (CC0-1.0)
# and not subject to the project's licence. The human contributor has
# reviewed and verified that the code is correct.
#
# SPDX-License-Identifier: MIT and CC0-1.0
##############################################################################

# Builds the Arm ports with an LLVM based toolchain: every assembly source of
# every Arm gnu port, and the common C sources for one core per architecture
# profile. Compilation only, no linking, so no target C library is required
# profile, then links the example builds that have a script driver.
#
#     scripts/check_clang.sh                       # clang from PATH
#     scripts/check_clang.sh --clang /path/to/clang
#     CLANG=/path/to/clang scripts/check_clang.sh
#
# Options:
#     --clang <path>   Compiler to use; defaults to $CLANG then to clang.
#     --asm-only       Skip the C sources and the example builds.
#     --no-examples    Skip the example builds.
#     --quiet          Print only failures and the summary.
#
# Exit status is 0 when everything builds and 1 otherwise.
#
# Why this exists: the gnu ports are only ever built with GNU tooling, and GNU
# as accepts several non-canonical forms that LLVM's assembler rejects. Those
# forms accumulated unnoticed. This check also covers Arm Toolchain for
# Embedded, which is LLVM based and is the successor to Arm Compiler 6, so the
# ac6 code paths are exercised here as well.
#
# Arm Toolchain for Embedded releases:
#     https://github.com/arm/arm-toolchain/releases

set -u

cd "$(dirname "$(realpath "$0")")/.."

CC="${CLANG:-clang}"
asm_only=0
no_examples=0
quiet=0

while [ "$#" -gt 0 ]; do
    case "$1" in
        --clang) [ "$#" -ge 2 ] || { echo "Error: --clang needs a path" >&2; exit 2; }; CC="$2"; shift 2 ;;
        --asm-only) asm_only=1; no_examples=1; shift ;;
        --no-examples) no_examples=1; shift ;;
        --quiet)    quiet=1; shift ;;
        -h|--help)  sed -n '17,33p' "$0"; exit 0 ;;
        *) echo "Error: unknown option '$1'" >&2; exit 2 ;;
    esac
done

say()  { [ "$quiet" -eq 1 ] || echo "$@"; }
fail() { echo "  FAIL: $*"; }

if ! command -v "$CC" >/dev/null 2>&1 && [ ! -x "$CC" ]; then
    echo "Error: compiler '$CC' not found."
    echo "Pass --clang <path>, set CLANG, or install Arm Toolchain for Embedded:"
    echo "  https://github.com/arm/arm-toolchain/releases"
    exit 1
fi

# Resolve to an absolute path. The example stage runs the build scripts from
# inside their own directories, so a relative compiler path would stop
# resolving there.
if [ -e "$CC" ]; then
    CC="$(realpath "$CC")"
else
    CC="$(command -v "$CC")"
fi

say ""
say "Using: $CC"
say "       $("$CC" --version | head -1)"

# Each port directory is mapped explicitly to a target triple and CPU. Do not
# replace this with prefix matching: cortex_a5* also matches cortex_a53 and
# cortex_a55, which are AArch64, and assembling those as ARM32 produces a flood
# of misleading errors.
declare -A PORT_TARGET=(
 [cortex_m0]="arm-none-eabi cortex-m0 -mthumb"
 [cortex_m0+]="arm-none-eabi cortex-m0plus -mthumb"
 [cortex_m3]="arm-none-eabi cortex-m3 -mthumb"
 [cortex_m4]="arm-none-eabi cortex-m4 -mthumb"
 [cortex_m7]="arm-none-eabi cortex-m7 -mthumb"
 [cortex_m23]="arm-none-eabi cortex-m23 -mthumb"
 [cortex_m33]="arm-none-eabi cortex-m33 -mthumb"
 [cortex_m55]="arm-none-eabi cortex-m55 -mthumb -mfloat-abi=hard"
 [cortex_m85]="arm-none-eabi cortex-m85 -mthumb -mfloat-abi=hard"
 [cortex_a5]="arm-none-eabi cortex-a5"
 [cortex_a7]="arm-none-eabi cortex-a7"
 [cortex_a8]="arm-none-eabi cortex-a8"
 [cortex_a9]="arm-none-eabi cortex-a9"
 [cortex_a12]="arm-none-eabi cortex-a12"
 [cortex_a15]="arm-none-eabi cortex-a15"
 [cortex_a17]="arm-none-eabi cortex-a17"
 [cortex_a5_smp]="arm-none-eabi cortex-a5"
 [cortex_a7_smp]="arm-none-eabi cortex-a7"
 [cortex_a9_smp]="arm-none-eabi cortex-a9"
 [cortex_r4]="arm-none-eabi cortex-r4"
 [cortex_r5]="arm-none-eabi cortex-r5"
 [cortex_r52]="arm-none-eabi cortex-r52"
 [cortex_a34]="aarch64-none-elf cortex-a34"
 [cortex_a35]="aarch64-none-elf cortex-a35"
 [cortex_a53]="aarch64-none-elf cortex-a53"
 [cortex_a55]="aarch64-none-elf cortex-a55"
 [cortex_a57]="aarch64-none-elf cortex-a57"
 [cortex_a65]="aarch64-none-elf cortex-a65"
 [cortex_a65ae]="aarch64-none-elf cortex-a65ae"
 [cortex_a72]="aarch64-none-elf cortex-a72"
 [cortex_a73]="aarch64-none-elf cortex-a73"
 [cortex_a75]="aarch64-none-elf cortex-a75"
 [cortex_a76]="aarch64-none-elf cortex-a76"
 [cortex_a76ae]="aarch64-none-elf cortex-a76ae"
 [cortex_a77]="aarch64-none-elf cortex-a77"
 [cortex_a34_smp]="aarch64-none-elf cortex-a34"
 [cortex_a35_smp]="aarch64-none-elf cortex-a35"
 [cortex_a53_smp]="aarch64-none-elf cortex-a53"
 [cortex_a55_smp]="aarch64-none-elf cortex-a55"
 [cortex_a57_smp]="aarch64-none-elf cortex-a57"
 [cortex_a65_smp]="aarch64-none-elf cortex-a65"
 [cortex_a65ae_smp]="aarch64-none-elf cortex-a65ae"
 [cortex_a72_smp]="aarch64-none-elf cortex-a72"
 [cortex_a73_smp]="aarch64-none-elf cortex-a73"
 [cortex_a75_smp]="aarch64-none-elf cortex-a75"
 [cortex_a76_smp]="aarch64-none-elf cortex-a76"
 [cortex_a76ae_smp]="aarch64-none-elf cortex-a76ae"
 [cortex_a77_smp]="aarch64-none-elf cortex-a77"
 [cortex_a78_smp]="aarch64-none-elf cortex-a78"
)

# One core per architecture profile for the C sources. Compiling all of them
# for every core would multiply the run time without adding coverage, since the
# port headers differ by profile rather than by core.
C_CORES="cortex_m0 cortex_m4 cortex_m23 cortex_m33 cortex_m55 cortex_a7 cortex_a53 cortex_r5"

# Example builds that are not expected to link, with the reason. Listed
# explicitly rather than silently skipped, so the gaps stay visible.
#
# These fail with the GNU toolchain too, so they are not LLVM problems:
#   cortex_m0            cortexm0_crt0.S references __text_load_start__,
#                        __text_start__ and __text_end__, which its linker
#                        script never defines. The Cortex-M4 script defines the
#                        equivalents, so this is a gap in that one example.
#   arm9 arm11           need newlib multilib variants for those CPUs, which are
#   cortex_r4 cortex_r5  not present in every GNU toolchain packaging.
#
# This one is specific to LLVM:
#   cortex_a12 a15 a17   their link line omits -nostartfiles, so the toolchain's
#                        own crt0 is linked, and it needs picolibc's
#                        __data_start, __data_source, __data_size and __bss_size,
#                        which the example's linker script does not define.
EXAMPLES_EXPECTED_TO_FAIL="arm9 arm11 cortex_m0 cortex_r4 cortex_r5 cortex_a12 cortex_a15 cortex_a17"

failures=0
skipped=""

# --------------------------------------------------------------------------
say ""
say "== Assembly sources of every Arm gnu port =="

total=0
for dir in ports/*/gnu/src ports_smp/*/gnu/src ports_module/*/gnu/src; do
    [ -d "$dir" ] || continue
    core="$(echo "$dir" | cut -d/ -f2)"
    spec="${PORT_TARGET[$core]:-}"
    if [ -z "$spec" ]; then
        skipped="$skipped $core"
        continue
    fi
    # shellcheck disable=SC2086
    set -- $spec
    target="$1"; cpu="$2"; shift 2; extra="$*"

    for src in "$dir"/*.S "$dir"/*.s; do
        [ -f "$src" ] || continue
        total=$((total + 1))
        output="$("$CC" --target="$target" -mcpu="$cpu" $extra -c "$src" -o /dev/null 2>&1)"
        if [ -n "$output" ]; then
            fail "$src"
            echo "$output" | sed 's/^/        /'
            failures=$((failures + 1))
        fi
    done
done
say "  $((total - failures)) of $total assembled"
if [ -n "$skipped" ]; then
    say "  not Arm, skipped:$(echo $skipped | tr ' ' '\n' | sort -u | tr '\n' ' ')"
fi

# --------------------------------------------------------------------------
if [ "$asm_only" -eq 0 ]; then
    say ""
    say "== Common C sources, one core per architecture profile =="

    for core in $C_CORES; do
        spec="${PORT_TARGET[$core]:-}"
        [ -n "$spec" ] || continue
        # shellcheck disable=SC2086
        set -- $spec
        target="$1"; cpu="$2"; shift 2; extra="$*"

        count=0; bad=0
        for src in common/src/*.c; do
            count=$((count + 1))
            output="$("$CC" --target="$target" -mcpu="$cpu" $extra \
                      -Iports/"$core"/gnu/inc -Icommon/inc -c "$src" -o /dev/null 2>&1)"
            if [ -n "$output" ]; then
                fail "$core: $src"
                echo "$output" | grep "error:" | head -3 | sed 's/^/        /'
                bad=$((bad + 1)); failures=$((failures + 1))
            fi
        done
        say "  $core: $((count - bad)) of $count compiled"
    done
fi


# --------------------------------------------------------------------------
if [ "$no_examples" -eq 0 ]; then
    say ""
    say "== Example builds, linked with lld =="

    example_ok=0
    example_total=0
    example_known=""
    for dir in ports/*/gnu/example_build; do
        [ -f "$dir/build_threadx.sh" ] && [ -f "$dir/build_threadx_sample.sh" ] || continue
        core="$(echo "$dir" | cut -d/ -f2)"
        case " $EXAMPLES_EXPECTED_TO_FAIL " in
            *" $core "*) example_known="$example_known $core"; continue ;;
        esac
        example_total=$((example_total + 1))

        rm -f "$dir"/*.o "$dir"/*.a "$dir"/*.out "$dir"/*.map 2>/dev/null || true
        log="$(cd "$dir" && TOOLCHAIN=atfe ATFE_CLANG="$CC" ./build_threadx.sh 2>&1 && \
                             TOOLCHAIN=atfe ATFE_CLANG="$CC" ./build_threadx_sample.sh 2>&1)" || true

        if [ -f "$dir/sample_threadx.out" ]; then
            example_ok=$((example_ok + 1))
        else
            fail "$core: example build produced no image"
            # Not filtered on "error": a missing tool reports "command not
            # found" or "Permission denied", and filtering hid exactly that.
            echo "$log" | tail -6 | sed 's/^/        /'
            failures=$((failures + 1))
        fi
        rm -f "$dir"/*.o "$dir"/*.a "$dir"/*.out "$dir"/*.map 2>/dev/null || true
    done
    say "  $example_ok of $example_total example builds linked"
    if [ -n "$example_known" ]; then
        say "  known not to link, see the list at the top of this script:$example_known"
    fi
fi
# --------------------------------------------------------------------------
say ""
if [ "$failures" -eq 0 ]; then
    say "All LLVM toolchain checks passed."
    exit 0
fi

echo "$failures LLVM toolchain check(s) failed."
exit 1