name: Test on: push: branches: - dev - Feat/Backend-Direct-GLES - Feat/Backend-Direct-Vulkan # TEMPORARY, remove before merging the MGPipe work into dev: the disaggregation # branch runs the full lane on every push so a phase's landing is not gated on # someone remembering to dispatch the workflow by hand. - feat/disaggregated workflow_dispatch: inputs: baseline_sha: description: >- The commit monolith-symbol-report compares this tree against. P1's G1 says the pull build is byte-identical to feat/disaggregated@087685d1, and that is what the default names. The trigger set is unchanged: this job runs on workflow_dispatch only. required: false default: "087685d1" jobs: build-linux: runs-on: ubuntu-latest permissions: actions: write contents: read env: BUILD_DIR: build-linux CCACHE_BASEDIR: ${{ github.workspace }} CCACHE_COMPRESS: "true" CCACHE_DIR: ${{ github.workspace }}/.ccache CCACHE_MAXSIZE: 4G CCACHE_NOHASHDIR: "true" steps: - name: Set Swap Space uses: pierotofy/set-swap-space@v1.0 with: swap-size-gb: 32 - name: Checkout repo uses: actions/checkout@v6 with: submodules: recursive - name: Get CMake uses: lukka/get-cmake@v4.3.3 - name: Restore ccache uses: actions/cache/restore@v5 with: path: .ccache key: ${{ runner.os }}-test-${{ github.job }}-ccache-v1 restore-keys: | ${{ runner.os }}-test-${{ github.job }}-ccache- - name: Prepare Vulkan SDK uses: humbletim/setup-vulkan-sdk@v1.2.1 with: vulkan-query-version: 1.4.304.1 vulkan-components: Vulkan-Headers, Vulkan-Loader vulkan-use-cache: true - name: Update glslang external sources working-directory: 3rdparty/glslang run: python update_glslang_sources.py - name: Install build dependencies run: | sudo apt-get update sudo apt-get install -y ccache clang-20 clang++-20 lld-20 libc++-20-dev libc++abi-20-dev libvulkan-dev libegl1-mesa-dev libgles2-mesa-dev libgl1-mesa-dri mesa-vulkan-drivers ninja-build - name: Show installed toolchain run: | ccache --version clang-20 --version clang++-20 --version ld.lld-20 --version || ld.lld --version || true dpkg -l 'libc++*' 'libegl*' 'libgles*' 'mesa*' 'vulkan*' || true - name: Configure CMake run: | if [ "${{ secrets.ACTIONS_STEP_DEBUG }}" = "true" ]; then BUILD_TYPE=Debug else BUILD_TYPE=Release fi cmake -S . -B "${BUILD_DIR}" -G Ninja \ -DCMAKE_C_COMPILER=clang-20 \ -DCMAKE_CXX_COMPILER=clang++-20 \ -DCMAKE_C_COMPILER_LAUNCHER=ccache \ -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \ -DCMAKE_BUILD_TYPE="${BUILD_TYPE}" \ -DMOBILEGL_LOG_ACTIVE_LEVEL=MOBILEGL_LOG_LEVEL_INFO \ -DMOBILEGL_BUILD_TEST=ON \ -DMOBILEGL_BUILD_BENCHMARK=ON \ -DMOBILEGL_BUILD_INTEGRATION_TEST=ON \ -DMOBILEGL_ITEST_VK_ICD=/usr/share/vulkan/icd.d/lvp_icd.json \ -DMOBILEGL_BUILD_TRACE_REPLAY=OFF \ -DBENCHMARK_DOWNLOAD_DEPENDENCIES=ON \ -DBENCHMARK_ENABLE_TESTING=OFF \ -DCMAKE_POLICY_VERSION_MINIMUM=3.5 - name: Build run: cmake --build "${BUILD_DIR}" --parallel "$(nproc)" - name: Show ccache stats if: always() run: ccache --show-stats # Rewrite one rolling entry per job on the default branch. The upload stays # cumulative - it carries every object restored at the top of this run plus # the few TUs that actually changed - but Actions cache keys are immutable, # so the superseded blob has to be released before the same key can be # re-uploaded. Running after the build means a failed build leaves the # existing entry untouched. The other trigger branches restore this entry # rather than each writing one of their own. - name: Release superseded ccache entry if: github.ref_name == github.event.repository.default_branch env: GH_TOKEN: ${{ github.token }} CACHE_KEY: ${{ runner.os }}-test-${{ github.job }}-ccache-v1 run: gh cache delete "${CACHE_KEY}" || true - name: Save ccache if: github.ref_name == github.event.repository.default_branch continue-on-error: true uses: actions/cache/save@v5 with: path: .ccache key: ${{ runner.os }}-test-${{ github.job }}-ccache-v1 - name: Package Linux runtime run: | mkdir -p ci-artifacts mapfile -t SHARED_LIBS < <(find "${BUILD_DIR}" -type f \( -name '*.so' -o -name '*.so.*' \) -print | sort) tar \ --exclude='*/CMakeFiles' \ --exclude='*.o' \ --exclude='*.a' \ --exclude='*.ninja*' \ --exclude='build.ninja' \ --exclude='cmake_install.cmake' \ -czf ci-artifacts/mobilegl-linux-runtime.tgz \ "${BUILD_DIR}/CTestTestfile.cmake" \ "${BUILD_DIR}/MobileGL/MG_Test" \ "${BUILD_DIR}/MobileGL/MG_Benchmark" \ "${BUILD_DIR}/MobileGL/MG_IntegrationTest" \ "${SHARED_LIBS[@]}" - name: Upload Linux runtime uses: actions/upload-artifact@v7 with: name: mobilegl-linux-runtime path: ci-artifacts/mobilegl-linux-runtime.tgz if-no-files-found: error test: runs-on: ubuntu-latest needs: build-linux steps: - name: Checkout repo uses: actions/checkout@v6 - name: Get CMake uses: lukka/get-cmake@v4.3.3 - name: Install runtime dependencies run: | sudo apt-get update sudo apt-get install -y libvulkan1 libegl1 libgles2 libgl1-mesa-dri mesa-vulkan-drivers - name: Download Linux runtime uses: actions/download-artifact@v8 with: name: mobilegl-linux-runtime path: . - name: Unpack Linux runtime run: tar -xzf mobilegl-linux-runtime.tgz - name: Normalize CTest command paths run: | python - <<'PY' from pathlib import Path import re for path in Path('build-linux').rglob('CTestTestfile.cmake'): text = path.read_text() text = re.sub(r'"[^"]*/cmake-[^"]*/bin/cmake"', '"cmake"', text) path.write_text(text) PY - name: Test working-directory: build-linux run: | ulimit -c unlimited sudo sysctl -w kernel.core_pattern='/tmp/core.%e.%p' if [ "${{ secrets.ACTIONS_STEP_DEBUG }}" = "true" ]; then ctest -V -L unit --no-tests=error else ctest --output-on-failure -L unit --no-tests=error fi - name: Upload core dumps if: failure() uses: actions/upload-artifact@v7 with: name: unit-core-dumps path: /tmp/core.* if-no-files-found: ignore integration: runs-on: ubuntu-latest needs: build-linux steps: - name: Checkout repo uses: actions/checkout@v6 - name: Get CMake uses: lukka/get-cmake@v4.3.3 - name: Install runtime dependencies # Same set as the benchmark job, for the same reason: the scenarios bring # up real headless EGL (llvmpipe) and Vulkan (lavapipe) contexts, and # libegl-mesa0 - the EGL vendor library behind glvnd's libegl1 dispatch - # only arrives as a Recommends. run: | sudo apt-get update sudo apt-get install -y libvulkan1 libegl1 libegl-mesa0 libgles2 libgl1-mesa-dri mesa-vulkan-drivers - name: Download Linux runtime uses: actions/download-artifact@v8 with: name: mobilegl-linux-runtime path: . - name: Unpack Linux runtime run: tar -xzf mobilegl-linux-runtime.tgz - name: Normalize CTest command paths run: | python - <<'PY' from pathlib import Path import re for path in Path('build-linux').rglob('CTestTestfile.cmake'): text = path.read_text() text = re.sub(r'"[^"]*/cmake-[^"]*/bin/cmake"', '"cmake"', text) path.write_text(text) PY - name: Integration scenarios working-directory: build-linux # REQUIRE_GPU makes a driverless runner FAIL instead of skipping every # scenario - an all-skip run is otherwise indistinguishable from a pass, # which is how a five-month-old draw-dropping bug survived unseen until # this lane existed. # # The lavapipe ICD pin lives in the build-linux configure # (-DMOBILEGL_ITEST_VK_ICD), NOT here: the configure bakes it into each # test's ctest ENVIRONMENT property, and a property entry OVERRIDES the # job environment - a VK_ICD_FILENAMES exported here would be silently # ignored while looking like it works. This lane runs on lavapipe # deterministically, not on whichever of the eight Mesa ICDs a GPU-less # runner enumerates first. # # Cores are armed so that any crash - the harness pre-flight child's # included - leaves /tmp/core.*, which the failure-only step below ships # as an artifact. Analyzing a downloaded core against the runtime # artifact's binary in an ubuntu-24.04 userspace reproduces the exact # crash stack without burning a CI round on an in-workflow debugger. env: MOBILEGL_ITEST_REQUIRE_GPU: "1" MOBILEGL_MAGMA_FIX_ITERATIONRP_SUBGROUP_SCRATCH: "1" MOBILEGL_MAGMA_DERIVE_NUM_SUBGROUPS: "1" MOBILEGL_MAGMA_ITERATIONRP_FIX_BARRIER: "1" run: | ulimit -c unlimited sudo sysctl -w kernel.core_pattern='/tmp/core.%e.%p' # Second, filtered pass: with the range-invalidating map flush disabled, # the buffer scenarios run on the upload ring's staged-copy tier - which # the default pass never reaches (the map tier absorbs every flush on # Mesa), so without this the Mali fallback tier would have zero CI # coverage. The flag is NOT baked into the ctest ENVIRONMENT properties, # so an inline env reaches the test processes (unlike the ICD pin above). if [ "${{ secrets.ACTIONS_STEP_DEBUG }}" = "true" ]; then ctest -V -L integration-gpu --no-tests=error MOBILEGL_ESPRYT_DISABLE_INVALIDATE_FLUSH=1 ctest -V -L integration-gpu \ -R 'Buffer|Readback|Atomic|Ssbo|Arena' --no-tests=error else ctest --output-on-failure -L integration-gpu --no-tests=error MOBILEGL_ESPRYT_DISABLE_INVALIDATE_FLUSH=1 ctest --output-on-failure -L integration-gpu \ -R 'Buffer|Readback|Atomic|Ssbo|Arena' --no-tests=error fi - name: Upload core dumps if: failure() uses: actions/upload-artifact@v7 with: name: integration-core-dumps path: /tmp/core.* if-no-files-found: ignore # THE THIRD CI MODE (ARCHITECTURE.md 13.2-(2)): the same library, built with the PipeInputs # comparator compiled in, running the integration suite and a trace subset with two state models # in one address space. It is a second build rather than a flag on the first because # MOBILEGL_PIPE_VERIFY is a compile-time option - the snapshot, the entry compare and the # compare-at-read hook do not exist in the shipped library, and are never meant to. build-linux-verify: runs-on: ubuntu-latest timeout-minutes: 120 permissions: actions: write contents: read env: BUILD_DIR: build-verify CCACHE_BASEDIR: ${{ github.workspace }} CCACHE_COMPRESS: "true" CCACHE_DIR: ${{ github.workspace }}/.ccache CCACHE_MAXSIZE: 4G CCACHE_NOHASHDIR: "true" steps: - name: Set Swap Space uses: pierotofy/set-swap-space@v1.0 with: swap-size-gb: 32 - name: Checkout repo uses: actions/checkout@v6 with: submodules: recursive - name: Get CMake uses: lukka/get-cmake@v4.3.3 - name: Restore ccache uses: actions/cache/restore@v5 with: path: .ccache key: ${{ runner.os }}-test-${{ github.job }}-ccache-v1 restore-keys: | ${{ runner.os }}-test-${{ github.job }}-ccache- - name: Prepare Vulkan SDK uses: humbletim/setup-vulkan-sdk@v1.2.1 with: vulkan-query-version: 1.4.304.1 vulkan-components: Vulkan-Headers, Vulkan-Loader vulkan-use-cache: true - name: Update glslang external sources working-directory: 3rdparty/glslang run: python update_glslang_sources.py - name: Install build dependencies run: | sudo apt-get update sudo apt-get install -y ccache clang-20 clang++-20 lld-20 libc++-20-dev libc++abi-20-dev libvulkan-dev libegl1-mesa-dev libgles2-mesa-dev libgl1-mesa-dri mesa-vulkan-drivers ninja-build - name: Show installed toolchain run: | ccache --version clang-20 --version clang++-20 --version ld.lld-20 --version || ld.lld --version || true dpkg -l 'libc++*' 'libegl*' 'libgles*' 'mesa*' 'vulkan*' || true - name: Configure CMake # Release/INFO like the shipped build on purpose. The poison arms in this configuration # through MOBILEGL_PIPE_VERIFY (PipeInputs.h derives MOBILEGL_PIPE_POISON from it), so this # job needs neither a Debug log level nor MOBILEGL_BUILD_DISAGGREGATED - and a Debug build # would compare a different library from the one the other lanes measure. (build-linux # switches to Debug under ACTIONS_STEP_DEBUG; this job deliberately does not - a Debug # build flips CXX_VISIBILITY_PRESET and arms MOBILEGL_PIPE_POISON through a second, unrelated # arm of its #if, so the debug switch would change what the lane is measuring.) run: | cmake -S . -B "${BUILD_DIR}" -G Ninja \ -DCMAKE_C_COMPILER=clang-20 \ -DCMAKE_CXX_COMPILER=clang++-20 \ -DCMAKE_C_COMPILER_LAUNCHER=ccache \ -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \ -DCMAKE_BUILD_TYPE=Release \ -DMOBILEGL_LOG_ACTIVE_LEVEL=MOBILEGL_LOG_LEVEL_INFO \ -DMOBILEGL_BUILD_TEST=ON \ -DMOBILEGL_BUILD_BENCHMARK=OFF \ -DMOBILEGL_BUILD_INTEGRATION_TEST=ON \ -DMOBILEGL_ITEST_VK_ICD=/usr/share/vulkan/icd.d/lvp_icd.json \ -DMOBILEGL_BUILD_TRACE_REPLAY=OFF \ -DMOBILEGL_PIPE_VERIFY=ON \ -DCMAKE_POLICY_VERSION_MINIMUM=3.5 - name: Build run: cmake --build "${BUILD_DIR}" --parallel "$(nproc)" # The lane is worthless if the option silently did not take, and that is a one-character # mistake away at all times (a typo'd -D is not an error in CMake). Two checks, both cheap: # the comparator's entry point must be in the library, and the fill entry point with it. # # `nm` and NOT `nm -D`. The library is built CXX_VISIBILITY_PRESET hidden in every non-Debug # configuration (CMakeLists.txt:600-604) and the MGPipe entry points are plain namespace # functions with no export attribute, so not one of them appears in the DYNAMIC table: on a # perfectly healthy verify build `nm -D --defined-only ... | grep -c MGPipe` answers 0 out of # ~11900 exported symbols, and a gate spelled that way is red forever for a reason that has # nothing to do with what it claims to test. The static symbol table has them as local `t` # entries, this artifact is never stripped, and `No MG_Remote in the pull build` below already # uses this spelling. The symbol count guards the remaining hole: a stripped library would # make both greps fail for a third, silent reason. - name: The verify library really carries the comparator run: | test -f "${BUILD_DIR}/libMobileGL.so" defined=$(nm --defined-only "${BUILD_DIR}/libMobileGL.so" | wc -l) if [ "${defined}" -lt 1000 ]; then echo "::error::nm --defined-only sees only ${defined} symbols in ${BUILD_DIR}/libMobileGL.so - it looks stripped, so the two checks below could not have failed honestly" exit 1 fi if ! nm --defined-only "${BUILD_DIR}/libMobileGL.so" | grep -q "MGPipeVerifyInputs"; then echo "::error::libMobileGL.so defines no MGPipeVerifyInputs: -DMOBILEGL_PIPE_VERIFY=ON did not take, and every lane that consumes this artifact would run the comparator-free library and pass having compared nothing" exit 1 fi # The per-verb entry point, under EITHER of its two names. P2 renames # MGPipeFillForVerb to MGPipeValidateForVerb (the body becomes the tracker's walk and # the fill is one of its five steps), so this check has to accept both or it goes red on # the rename for a reason that has nothing to do with what it tests. What it tests is # unchanged: that the library HAS a per-verb entry point compiled in. if ! nm --defined-only "${BUILD_DIR}/libMobileGL.so" | grep -qE "MGPipeValidateForVerb|MGPipeFillForVerb"; then echo "::error::libMobileGL.so defines neither MGPipeValidateForVerb nor MGPipeFillForVerb: there is no per-verb entry point in this artifact, so nothing fills the block the comparator compares" exit 1 fi echo "libMobileGL.so defines MGPipeVerifyInputs and a per-verb entry point (${defined} defined symbols)" - name: Show ccache stats if: always() run: ccache --show-stats - name: Release superseded ccache entry if: github.ref_name == github.event.repository.default_branch env: GH_TOKEN: ${{ github.token }} CACHE_KEY: ${{ runner.os }}-test-${{ github.job }}-ccache-v1 run: gh cache delete "${CACHE_KEY}" || true - name: Save ccache if: github.ref_name == github.event.repository.default_branch continue-on-error: true uses: actions/cache/save@v5 with: path: .ccache key: ${{ runner.os }}-test-${{ github.job }}-ccache-v1 - name: Package Linux verify runtime run: | mkdir -p ci-artifacts mapfile -t SHARED_LIBS < <(find "${BUILD_DIR}" -type f \( -name '*.so' -o -name '*.so.*' \) -print | sort) tar \ --exclude='*/CMakeFiles' \ --exclude='*.o' \ --exclude='*.a' \ --exclude='*.ninja*' \ --exclude='build.ninja' \ --exclude='cmake_install.cmake' \ -czf ci-artifacts/mobilegl-linux-runtime-verify.tgz \ "${BUILD_DIR}/CTestTestfile.cmake" \ "${BUILD_DIR}/MobileGL/MG_Test" \ "${BUILD_DIR}/MobileGL/MG_IntegrationTest" \ "${SHARED_LIBS[@]}" - name: Upload Linux verify runtime uses: actions/upload-artifact@v7 with: name: mobilegl-linux-runtime-verify path: ci-artifacts/mobilegl-linux-runtime-verify.tgz if-no-files-found: error # The verify lane itself, plus the two negative controls that keep it falsifiable. The controls # are ALWAYS-ON steps, not a manual exercise: a gate that can only be shown to work by someone # remembering to break it on purpose is a gate that has already stopped working. integration-verify: runs-on: ubuntu-latest timeout-minutes: 180 needs: build-linux-verify steps: - name: Checkout repo uses: actions/checkout@v6 - name: Get CMake uses: lukka/get-cmake@v4.3.3 - name: Install runtime dependencies run: | sudo apt-get update sudo apt-get install -y libvulkan1 libegl1 libegl-mesa0 libgles2 libgl1-mesa-dri mesa-vulkan-drivers - name: Download Linux verify runtime uses: actions/download-artifact@v8 with: name: mobilegl-linux-runtime-verify path: . - name: Unpack Linux verify runtime run: | tar -xzf mobilegl-linux-runtime-verify.tgz test -f build-verify/libMobileGL.so - name: Normalize CTest command paths run: | python - <<'PY' from pathlib import Path import re for path in Path('build-verify').rglob('CTestTestfile.cmake'): text = path.read_text() text = re.sub(r'"[^"]*/cmake-[^"]*/bin/cmake"', '"cmake"', text) path.write_text(text) PY - name: Integration scenarios under MOBILEGL_PIPE_VERIFY working-directory: build-verify # --no-tests=error is half the gate: the verify entries only exist when the library was # configured with -DMOBILEGL_PIPE_VERIFY=ON, so a build that lost the option matches no # tests and reds here instead of reporting a green run of nothing. The other half is # PipeVerifyArmingScenario.Armed, which fails when the library never printed its arming # line - the failure mode a bare `MOBILEGL_PIPE_VERIFY=1` cannot detect by itself. # # SCOPE, stated so nobody reads more into a green than is there: this is every integration # ENTRY under the comparator, not every integration CONFIGURATION. The `integration` job # runs a second, filtered pass with MOBILEGL_ESPRYT_DISABLE_INVALIDATE_FLUSH=1 for the # upload ring's staged-copy tier; that pass is 186 entries here and, at the 5-10x the # comparator costs, is not affordable inside this job's budget. The tier is covered by # `integration`, unverified, and P2 can take it once the comparator's cost is known. env: MOBILEGL_ITEST_REQUIRE_GPU: "1" MOBILEGL_MAGMA_FIX_ITERATIONRP_SUBGROUP_SCRATCH: "1" MOBILEGL_MAGMA_DERIVE_NUM_SUBGROUPS: "1" MOBILEGL_MAGMA_ITERATIONRP_FIX_BARRIER: "1" run: | ulimit -c unlimited sudo sysctl -w kernel.core_pattern='/tmp/core.%e.%p' if [ "${{ secrets.ACTIONS_STEP_DEBUG }}" = "true" ]; then ctest -V -L integration-verify --no-tests=error else ctest --output-on-failure -L integration-verify --no-tests=error fi # The push-only unit tests, on the verify runtime. # # WHY HERE AND NOT IN `test`. The entries themselves are registered in EVERY build - they # have to be, or `ctest -N` would stop matching name-for-name between the pull and the push # build (gate G2). What is push-only is what they assert about: MGPipeRenderStateSpans.cpp # and PipeApply.cpp are appended to SOURCE_FILES inside the `if (MOBILEGL_PIPE_PUSH)` block, # which is exactly how the pull build stays symbol-identical, so in a pull build each case # opens with `#if !MOBILEGL_PIPE_PUSH GTEST_SKIP() << "push not compiled in"`. The `test` # job therefore runs G6's chunk-table walk and G10's residual assertions as a column of # skips: CI executes the NAMES and never one of the assertions. This job unpacks a build # that compiled them, so it is the first place in CI where they actually run. # # This artifact already carries them - the packaging step above tars # ${BUILD_DIR}/MobileGL/MG_Test whole - so the whole cost is the run, which is ~14 s for # ~1490 entries. --no-tests=error, because a packaging change that stopped shipping the # unit binaries would otherwise report a green run of nothing. - name: Unit tests on the verify runtime (G6, G10) working-directory: build-verify run: ctest --output-on-failure -L unit --no-tests=error -j "$(nproc)" # The always-on P2 and P3a negative controls (G8, G10, G12), which are labelled # integration-gpu and not integration-verify - they are about the handle key, the subsystem # switch and the map-persistent counter, not about the comparator - so the lane above does # not reach them. They are run HERE because this is the only CI job that unpacks a # MOBILEGL_PIPE_PUSH build: every one of them reads a counter out of the library's summary # line, and both the counters and their brackets are #if MOBILEGL_PIPE_PUSH, so in the pull # `integration` job the entries exist (gate G2 requires the same names in both builds) but # have nothing to assert. # # An arm whose subsystem has not landed on this tree SKIPS with the reason (never absent, # never a green that asserted nothing), so this step is green through the P2 and P3a landing # orders and starts asserting as each package arrives. # # The environment is the sibling step's, deliberately and in full: these entries run the # same DirectVulkan binary through the same runner, so the three MOBILEGL_MAGMA_* fixes it # needs apply here too, and a crash here has to leave a core for the same black-box flow. # The step above is the only reason those lines exist in this job; a control that crashed # without one would be the hardest failure in the job to diagnose. # # THE -R ALTERNATIVES ARE TEST-NAME PREFIXES, NOT LANE LABELS, and each one is deliberately # the SHORTEST string that still selects only what it means to. `ResourceSubsystem` (not # `ResourceSubsystemControl`) is what reaches the eight # DirectGLES.ResourceSubsystemOn./Off.LargeArenaAdoptionScenario.* entries - the A/B lanes # whose entire purpose is that the handle path and the legacy BufferBackendOps path must # agree about an adopted store - as well as the two ResourceSubsystemControl. entries. # `MapPersistentRoundtrip` is singular because LargeArenaAdoptionScenario's case is # `AnAdoptionCostsExactlyOneMapPersistentRoundtrip`; the plural matched only the lane PREFIX # of the other one. Both mistakes were silent: this is the only CI job that unpacks a push # build, so an entry the filter misses is either never run under the P3a bits at all or runs # only in the pull `integration` job, where a MOBILEGL_PIPE_PUSH value steers nothing # (Config.h declares the field inside the push guard) and both arms are the same legacy path. # A lane that cannot go red where it is installed is not a gate (ROADMAP.md:7). # P4a ADDS THREE ALTERNATIVES, and each one is here because this is the only CI job that # unpacks a push build: # * `ObjectSubsystem` reaches the three DirectGLES.ObjectSubsystemControl. entries - the # 0x1fff-vs-0x1ff A/B and the 0x9ff dependency refusal (G12). `ResourceSubsystem` does # NOT match it: the two families are named apart on purpose, because they are different # phases' switches and a filter that merged them would hide one behind the other. # * `TextureParamsWithoutASamplerView` reaches G9's four cases, the scenario ROADMAP.md:20 # names by hand. It runs in the ambient lanes, which the label already selects - but this # step is where those cases run against a PUSH library, and G9's whole claim is about the # push path. All four cases are green on the contract commit - including the one D-E3 # expected to be red, for the reason the scenario's header records - so this row is green # from the day it lands and goes red only if a reachability path stops syncing texture # parameters at all, which is the coupling ARCHITECTURE.md:100 exists to remove. # * `TextureUploadShape` is RECORDED, not gated (D-D4): it asserts that the two upload-shape # counters could be read and that they agree, and prints the shape for MEASUREMENTS.md. It # is in the filter so that the number is actually collected on every run - an unmeasured # shape is not a recorded one - and because its own assertions can go red. # As with the four before them, each alternative is the SHORTEST string that selects only what # it means to. - name: The handle-ABA, CSO, subsystem and texture-parameter controls (G8, G8b, G9, G10, G12) working-directory: build-verify env: MOBILEGL_ITEST_REQUIRE_GPU: "1" MOBILEGL_MAGMA_FIX_ITERATIONRP_SUBGROUP_SCRATCH: "1" MOBILEGL_MAGMA_DERIVE_NUM_SUBGROUPS: "1" MOBILEGL_MAGMA_ITERATIONRP_FIX_BARRIER: "1" run: | ulimit -c unlimited sudo sysctl -w kernel.core_pattern='/tmp/core.%e.%p' ctest --output-on-failure -L integration-gpu \ -R 'HandleRecycle|CsoContentAddressing|ResourceSubsystem|MapPersistentRoundtrip|ObjectSubsystem|TextureParamsWithoutASamplerView|TextureUploadShape' \ --no-tests=error -j 4 # The arming lanes' logs, and ONLY those. Each lane shares one MOBILEGL_LOG_FILE_PATH and the # library opens it fopen(path, "w"), so after an ambient lane of 400-odd processes the file # holds the LAST one - grepping it would say nothing about the other 405 and would red a # healthy lane whenever the last entry happened not to issue a verb (which is what the # PoisonOmissionScenario parent, the last ambient entry, does by construction: it forks, # execve()s and reads files). The DirectGLES.VerifyArming. / DirectVulkan.VerifyArming. # entries are one process each on a log path nothing else writes, so this grep means exactly # what it says. # # What it proves: arming is a property of (this library, this environment), and these two # processes ran the same library with the same MOBILEGL_PIPE_VERIFY=1 as their ~400 ambient # siblings. It is not, and cannot be, a per-process census - the shared log cannot support one. # It catches the case ctest cannot: an arming entry that SKIPPED still reports green. - name: The verify lanes armed the comparator working-directory: build-verify run: | shopt -s nullglob logs=(MobileGL/MG_IntegrationTest/pipe-verify-arming-*.log) if [ ${#logs[@]} -lt 2 ]; then echo "::error::found ${#logs[@]} pipe-verify-arming-*.log (expected one per backend). The VerifyArming. entries did not run, so nothing in this job establishes that the comparator was ever armed." exit 1 fi for log in "${logs[@]}"; do if ! grep -q "MGPipe: verify armed" "${log}"; then echo "::error::${log} carries no arming line: that lane's process ran the whole scenario without the comparator, so every green entry beside it is green for no reason" exit 1 fi done echo "arming line present in all ${#logs[@]} arming-lane log(s)" # NEGATIVE CONTROL A (gate G4). The knob perturbs one field in the snapshot arm before the # entry compare, so a working comparator must abort the run. This step passes when ctest # FAILS - `if ctest ...; then error` - which is the only shape that can catch a comparator # that silently compares nothing. # # The knob reaches the test process through the JOB environment: no ctest ENVIRONMENT # property on the ambient Verify. entries names it (MG_IntegrationTest/CMakeLists.txt says # so out loud), and a property entry would otherwise override this and the control would # prove nothing. Same precedent as MOBILEGL_ESPRYT_DISABLE_INVALIDATE_FLUSH in `integration`. - name: Negative control A - a corrupted snapshot field must turn the lane red working-directory: build-verify env: MOBILEGL_ITEST_REQUIRE_GPU: "1" MOBILEGL_PIPE_VERIFY_CORRUPT: GetRenderStateParameters run: | FILTER='DirectGLES\.Verify\..*ClearThenReadPixels' # An empty selection would ALSO make ctest exit non-zero (--no-tests=error), and this # step reads non-zero as "the control worked" - so the selection is counted first. A # control that passes because it ran nothing is worse than no control. matched=$(ctest -N -L integration-verify -R "${FILTER}" | grep -cE '^ *Test *#[0-9]+:') if [ "${matched}" -lt 1 ]; then echo "::error::negative control A selected ${matched} tests; its filter no longer matches anything" exit 1 fi if ctest --output-on-failure -L integration-verify -R "${FILTER}" --no-tests=error; then echo "::error::MOBILEGL_PIPE_VERIFY_CORRUPT=GetRenderStateParameters left ${matched} verify entries GREEN. The comparator is not comparing, so every green entry above is green for no reason." exit 1 fi echo "the corrupted field turned ${matched} selected entries red, as it must" # NEGATIVE CONTROL B (gate G5). The omission skips the STAMP of one field for one verb while # still copying its value - indistinguishable from a fill row nobody wrote - so the poison # must abort the glGenerateMipmap. Again: this step passes when ctest fails. # # The entry it targets is PoisonOmissionScenario.WithoutOmissionCompletes, which is green in # the ambient lane above and is the ONLY integration entry in the tree that calls # glGenerateMipmap at all. It deliberately does not skip itself when the knob is set, exactly # so that this control has something to turn red. - name: Negative control B - an omitted fill point must turn the lane red on that verb working-directory: build-verify env: MOBILEGL_ITEST_REQUIRE_GPU: "1" MOBILEGL_PIPE_POISON_OMIT: GenerateMipmap:GetActiveTextureUnit run: | FILTER='DirectGLES\.Verify\.PoisonOmissionScenario\.WithoutOmissionCompletes' matched=$(ctest -N -L integration-verify -R "${FILTER}" | grep -cE '^ *Test *#[0-9]+:') if [ "${matched}" -lt 1 ]; then echo "::error::negative control B selected ${matched} tests; its filter no longer matches anything" exit 1 fi if ctest --output-on-failure -L integration-verify -R "${FILTER}" --no-tests=error; then echo "::error::MOBILEGL_PIPE_POISON_OMIT=GenerateMipmap:GetActiveTextureUnit left the verify lane GREEN. The per-verb poison is not armed, so a forgotten fill row would ship silently." exit 1 fi echo "the omitted fill point turned the lane red, as it must" - name: Upload verify lane logs if: always() uses: actions/upload-artifact@v7 with: name: integration-verify-logs path: build-verify/MobileGL/MG_IntegrationTest/pipe-*.log* if-no-files-found: warn - name: Upload core dumps if: failure() uses: actions/upload-artifact@v7 with: name: integration-verify-core-dumps path: /tmp/core.* if-no-files-found: ignore # P5's split build. The verify pair cloned, because the problem is the same one: a third # configuration of the same sources whose whole value depends on the option having taken. # # IT CANNOT RIDE ON build-linux'S ARTIFACT. build-linux passes no -DMOBILEGL_PIPE_PUSH, so it is # a PULL build; MOBILEGL_BUILD_DISAGGREGATED implies MOBILEGL_PIPE_PUSH (the split path decodes # into the MGPipe applier and PIPE_PUSH is what compiles the applier), so the split arm needs a # build of its own exactly as the verify arm does. # # THE `nm` STEP IS THE POINT OF THIS JOB. In a build without the option, MG_Remote is not # compiled at all and MOBILEGL_TRANSPORT's parser does not exist - so the variable is accepted by # the environment and silently ignored (CONTRACT-P5 5). Every downstream lane would then run # monolith and go green under a name that says split. CMake will not complain about a typo'd -D, # so the build-level assertion is the only guard, and its absence is precisely what would make # the whole split arm meaningless. build-linux-split: runs-on: ubuntu-latest timeout-minutes: 120 permissions: actions: write contents: read env: BUILD_DIR: build-split CCACHE_BASEDIR: ${{ github.workspace }} CCACHE_COMPRESS: "true" CCACHE_DIR: ${{ github.workspace }}/.ccache CCACHE_MAXSIZE: 4G CCACHE_NOHASHDIR: "true" steps: - name: Set Swap Space uses: pierotofy/set-swap-space@v1.0 with: swap-size-gb: 32 - name: Checkout repo uses: actions/checkout@v6 with: # recursive, and load-bearing here beyond the usual: MOBILEGL_BUILD_DISAGGREGATED # SHADOWS ITSELF BACK TO OFF when 3rdparty/flatbuffers/include is missing # (CMakeLists.txt:471-486, a normal variable rather than a cache force, deliberately). # A shallow checkout would therefore configure cleanly, build a monolith library, and # be caught only by the nm step below. submodules: recursive - name: Get CMake uses: lukka/get-cmake@v4.3.3 - name: Restore ccache uses: actions/cache/restore@v5 with: path: .ccache key: ${{ runner.os }}-test-${{ github.job }}-ccache-v1 restore-keys: | ${{ runner.os }}-test-${{ github.job }}-ccache- - name: Prepare Vulkan SDK uses: humbletim/setup-vulkan-sdk@v1.2.1 with: vulkan-query-version: 1.4.304.1 vulkan-components: Vulkan-Headers, Vulkan-Loader vulkan-use-cache: true - name: Update glslang external sources working-directory: 3rdparty/glslang run: python update_glslang_sources.py - name: Install build dependencies run: | sudo apt-get update sudo apt-get install -y ccache clang-20 clang++-20 lld-20 libc++-20-dev libc++abi-20-dev libvulkan-dev libegl1-mesa-dev libgles2-mesa-dev libgl1-mesa-dri mesa-vulkan-drivers ninja-build - name: Show installed toolchain run: | ccache --version clang-20 --version clang++-20 --version dpkg -l 'libc++*' 'libegl*' 'libgles*' 'mesa*' 'vulkan*' || true - name: Configure CMake # Release/INFO like the shipped build, for the same reason build-linux-verify gives. # INFO specifically matters here: ConfigLoader logs the resolved transport at INFO and # that line is what run_trace_case.cmake and the integration-split lane read back as # proof the transport resolved in THIS process. # # _INPROC implies _DISAGGREGATED implies _PIPE_PUSH; all three are passed anyway, because # an implication that is asserted in two places is an implication nobody has to remember. run: | cmake -S . -B "${BUILD_DIR}" -G Ninja \ -DCMAKE_C_COMPILER=clang-20 \ -DCMAKE_CXX_COMPILER=clang++-20 \ -DCMAKE_C_COMPILER_LAUNCHER=ccache \ -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \ -DCMAKE_BUILD_TYPE=Release \ -DMOBILEGL_LOG_ACTIVE_LEVEL=MOBILEGL_LOG_LEVEL_INFO \ -DMOBILEGL_BUILD_TEST=ON \ -DMOBILEGL_BUILD_BENCHMARK=OFF \ -DMOBILEGL_BUILD_INTEGRATION_TEST=ON \ -DMOBILEGL_ITEST_VK_ICD=/usr/share/vulkan/icd.d/lvp_icd.json \ -DMOBILEGL_BUILD_TRACE_REPLAY=OFF \ -DMOBILEGL_PIPE_PUSH=ON \ -DMOBILEGL_BUILD_DISAGGREGATED=ON \ -DMOBILEGL_BUILD_DISAGGREGATED_INPROC=ON \ -DCMAKE_POLICY_VERSION_MINIMUM=3.5 - name: Build run: cmake --build "${BUILD_DIR}" --parallel "$(nproc)" # `nm` and NOT `nm -D`, for the reason build-linux-verify spells out: everything under # MG_Remote is a plain namespace symbol in a CXX_VISIBILITY_PRESET=hidden Release build and # none of it reaches the dynamic table. The symbol count guards the remaining hole - a # stripped library would make the grep fail for a third, silent reason. # # The mirror of this assertion already exists and is the G1 control: monolith-symbol-report # asserts that a -DMOBILEGL_BUILD_DISAGGREGATED=OFF library defines NO MG_Remote symbol. The # two together are ARCHITECTURE.md:524's surviving byte-level equality, in both directions. - name: The split library really carries MG_Remote run: | test -f "${BUILD_DIR}/libMobileGL.so" defined=$(nm --defined-only "${BUILD_DIR}/libMobileGL.so" | wc -l) if [ "${defined}" -lt 1000 ]; then echo "::error::nm --defined-only sees only ${defined} symbols in ${BUILD_DIR}/libMobileGL.so - it looks stripped, so the checks below could not have failed honestly" exit 1 fi remote=$(nm --defined-only "${BUILD_DIR}/libMobileGL.so" | grep -c -i "MG_Remote" || true) if [ "${remote}" -lt 1 ]; then echo "::error::libMobileGL.so defines no MG_Remote symbol: -DMOBILEGL_BUILD_DISAGGREGATED=ON did not take (a typo'd -D is not a CMake error, and the option shadows itself OFF when 3rdparty/flatbuffers/include is missing). Every lane that consumes this artifact would run MONOLITH while claiming to run split, because the MOBILEGL_TRANSPORT parser does not exist in such a build and the variable is accepted and ignored." exit 1 fi # The transport parser itself, which is the symbol the runtime evidence depends on. if ! nm --defined-only "${BUILD_DIR}/libMobileGL.so" | grep -q "MGPipeApply"; then echo "::error::libMobileGL.so defines no MGPipeApply* entry point, so MOBILEGL_PIPE_PUSH did not take either and there is no applier for the split path to decode into" exit 1 fi echo "libMobileGL.so defines ${remote} MG_Remote symbol(s) and the MGPipe applier (${defined} defined symbols)" - name: Show ccache stats if: always() run: ccache --show-stats - name: Release superseded ccache entry if: github.ref_name == github.event.repository.default_branch env: GH_TOKEN: ${{ github.token }} CACHE_KEY: ${{ runner.os }}-test-${{ github.job }}-ccache-v1 run: gh cache delete "${CACHE_KEY}" || true - name: Save ccache if: github.ref_name == github.event.repository.default_branch continue-on-error: true uses: actions/cache/save@v5 with: path: .ccache key: ${{ runner.os }}-test-${{ github.job }}-ccache-v1 - name: Package Linux split runtime run: | mkdir -p ci-artifacts mapfile -t SHARED_LIBS < <(find "${BUILD_DIR}" -type f \( -name '*.so' -o -name '*.so.*' \) -print | sort) tar \ --exclude='*/CMakeFiles' \ --exclude='*.o' \ --exclude='*.a' \ --exclude='*.ninja*' \ --exclude='build.ninja' \ --exclude='cmake_install.cmake' \ -czf ci-artifacts/mobilegl-linux-runtime-split.tgz \ "${BUILD_DIR}/CTestTestfile.cmake" \ "${BUILD_DIR}/MobileGL/MG_Test" \ "${BUILD_DIR}/MobileGL/MG_IntegrationTest" \ "${SHARED_LIBS[@]}" - name: Upload Linux split runtime uses: actions/upload-artifact@v7 with: name: mobilegl-linux-runtime-split path: ci-artifacts/mobilegl-linux-runtime-split.tgz if-no-files-found: error # The split lane itself: the three-arm shape ARCHITECTURE.md:521 asks for verbatim, plus the # first real run of the five MG_Test/Wire suites, plus P5's two exit-gate negative controls. integration-split: runs-on: ubuntu-latest timeout-minutes: 120 needs: build-linux-split steps: - name: Checkout repo uses: actions/checkout@v6 - name: Get CMake uses: lukka/get-cmake@v4.3.3 - name: Install runtime dependencies run: | sudo apt-get update sudo apt-get install -y libvulkan1 libegl1 libegl-mesa0 libgles2 libgl1-mesa-dri mesa-vulkan-drivers - name: Download Linux split runtime uses: actions/download-artifact@v8 with: name: mobilegl-linux-runtime-split path: . - name: Unpack Linux split runtime run: | tar -xzf mobilegl-linux-runtime-split.tgz test -f build-split/libMobileGL.so - name: Normalize CTest command paths run: | python - <<'PY' from pathlib import Path import re for path in Path('build-split').rglob('CTestTestfile.cmake'): text = path.read_text() text = re.sub(r'"[^"]*/cmake-[^"]*/bin/cmake"', '"cmake"', text) path.write_text(text) PY # THE FIRST REAL RUN OF MG_Test/Wire. Those five suites - Framing, Ring, InProcessTransport, # ProtocolSmoke and FdPassing - are registered only under MOBILEGL_BUILD_DISAGGREGATED # (MG_Test/CMakeLists.txt), and before this job existed NO cmake invocation anywhere in this # workflow passed that option. They had never been compiled by CI, let alone run. - name: Unit tests on the split runtime working-directory: build-split run: ctest --output-on-failure -L unit --no-tests=error -j "$(nproc)" # --no-tests=error is half the gate, exactly as in integration-verify: the integration-split # entries exist only when the library was configured with -DMOBILEGL_BUILD_DISAGGREGATED=ON, # so a build that lost the option matches nothing and reds here instead of reporting a green # run of nothing. The other half is the transport-resolution check below. # # An entry whose owning package (c1 client, s1 session, v1 server) has not landed SKIPS with # the reason and never goes green - MG_IntegrationTest/CMakeLists.txt probes MG_Remote for # c0's signature stubs and disarms the lane while any remain. - name: Split scenarios under MOBILEGL_TRANSPORT=inproc working-directory: build-split env: MOBILEGL_ITEST_REQUIRE_GPU: "1" run: | ulimit -c unlimited sudo sysctl -w kernel.core_pattern='/tmp/core.%e.%p' ctest --output-on-failure -L integration-split --no-tests=error -j 4 # ARCHITECTURE.md:521 asks for `ctest -L integration-gpu` to be name-for-name identical # between the monolith and the split arm of the SAME build - the G2 shape extended to a # third arm. The knob goes in the JOB environment rather than in a ctest property, for the # reason the MOBILEGL_ESPRYT_DISABLE_INVALIDATE_FLUSH precedent in `integration` gives: a # property would override it and the arm would not be an arm. # # The entries that name MOBILEGL_TRANSPORT in their OWN property (the Split. lanes) keep # their value in both passes, which is correct: they are the split family in both arms and # the comparison is about the other 1100. - name: The same integration entries under monolith and under inproc working-directory: build-split env: MOBILEGL_ITEST_REQUIRE_GPU: "1" MOBILEGL_MAGMA_FIX_ITERATIONRP_SUBGROUP_SCRATCH: "1" MOBILEGL_MAGMA_DERIVE_NUM_SUBGROUPS: "1" MOBILEGL_MAGMA_ITERATIONRP_FIX_BARRIER: "1" run: | ulimit -c unlimited sudo sysctl -w kernel.core_pattern='/tmp/core.%e.%p' count=$(ctest -N -L integration-gpu | grep -cE '^ *Test *#[0-9]+:') if [ "${count}" -lt 1 ]; then echo "::error::the split runtime registers ${count} integration-gpu entries" exit 1 fi echo "integration-gpu entries in the split build: ${count}" MOBILEGL_TRANSPORT=monolith ctest --output-on-failure -L integration-gpu --no-tests=error -j 4 --output-junit "${RUNNER_TEMP}/arm-monolith.xml" MOBILEGL_TRANSPORT=inproc ctest --output-on-failure -L integration-gpu --no-tests=error -j 4 --output-junit "${RUNNER_TEMP}/arm-inproc.xml" # NAME **AND STATUS**, and it is the comparison this step claimed to make and did not # (review finding N-3): the first version wrote a names file and never read it, and # `--output-on-failure` treats a SKIPPED test as not-a-failure - so the very failure # ARCHITECTURE.md:521 is about, "an inproc arm that skipped forty entries the monolith arm # ran", was invisible here and caught only by the local gate. `ctest -N` cannot see it # either: this is one build directory, so the two arms have identical name lists by # construction and the difference is entirely in what each entry DID. python3 - "${RUNNER_TEMP}/arm-monolith.xml" "${RUNNER_TEMP}/arm-inproc.xml" <<'PY' import sys, xml.etree.ElementTree as ET def rows(path): out = {} for case in ET.parse(path).getroot().iter('testcase'): status = 'passed' if case.find('failure') is not None or case.find('error') is not None: status = 'failed' elif case.find('skipped') is not None or case.get('status') in ('notrun', 'disabled'): status = 'skipped' out[case.get('name')] = status return out a, b = rows(sys.argv[1]), rows(sys.argv[2]) diff = sorted(set(a) ^ set(b)) + sorted(n for n in set(a) & set(b) if a[n] != b[n]) if diff: for name in diff[:40]: print(f"::error::{name}: monolith={a.get(name, '')} inproc={b.get(name, '')}") print(f"::error::the monolith and inproc arms of ctest -L integration-gpu differ on " f"{len(diff)} entries. ARCHITECTURE.md:521 requires them identical name for name " f"AND status; an entry that SKIPPED on one arm and ran on the other is the " f"failure this compares for, and it is not a failure to --output-on-failure.") raise SystemExit(1) print(f"the two arms agree on all {len(a)} entries, name and status") PY # THE RUNTIME HALF OF "THIS IS REALLY A SPLIT BUILD". The build-level nm check in # build-linux-split proves the library CARRIES MG_Remote; this proves the transport # RESOLVED in a process of this lane. ConfigLoader::InitTransport logs one INFO line when it # selects InProcess, and the DirectGLES.Split.PersistentMapArm. entry retains its private # counting log (all Split entries now have private paths; nothing else writes this file). # The line is written during bring-up, before any scenario decides to skip, so this # check is live from the day the lanes land rather than from the day they stop skipping. - name: The split lane really resolved the transport working-directory: build-split run: | log=MobileGL/MG_IntegrationTest/persistent-map-arm-split-DirectGLES.log if [ ! -f "${log}" ]; then echo "::error::${log} does not exist: the DirectGLES.Split.PersistentMapArm. entry never ran, so nothing in this job establishes that MOBILEGL_TRANSPORT ever resolved to inproc in a live process" exit 1 fi # THE DISTINCTIVE PART OF THE INFO LINE, not the bare KEY=VALUE (review finding M-5): # ConfigLoader logs `Config: Accepted env variable: MOBILEGL_TRANSPORT=inproc` for the # env dump too, unconditionally and in a PULL build, and at DEBUG that line is live. if ! grep -q "MOBILEGL_TRANSPORT=inproc - the MGPipe record stream" "${log}"; then echo "::error::${log} carries no transport-resolution line. ConfigLoader::InitTransport logs it at INFO when it selects InProcess, and that code exists only in a MOBILEGL_BUILD_DISAGGREGATED build - so this lane ran a monolith library while claiming to be the split lane. (A bare MOBILEGL_TRANSPORT=inproc substring is NOT accepted: the env dump prints one in every build.)" exit 1 fi echo "the split lane resolved MOBILEGL_TRANSPORT=inproc" # EXIT GATE E1's NEGATIVE CONTROL and EXIT GATE E3(a)'s, in one step because they have the # same two-state shape and the same reason for it. # # Both controls turn a knob that MUST make a split scenario red: MOBILEGL_IPC_VERB_BARRIER=0 # removes the lockstep fence R-1 rests on, and MOBILEGL_IPC_PERSISTENT_BLOCK_KB=0 turns the # persistent-map push off. A control of the verify lane's shape - "this step passes when # ctest FAILS" - cannot be written yet, because while packages c1/s1/v1 are landing the # Split entries SKIP and ctest reports green whatever the knob says, so an unconditional # control would be red for the whole of P5 for a reason that is not a defect. # # So the expected state is DERIVED FROM BEHAVIOUR rather than assumed. The first version read # MGITEST_REMOTE_CLIENT_PRESENT out of the generated *_tests.cmake, which was a restatement of # the CMake source probe review finding M-1 falsified; the arming condition is a runtime fact # inside each test process (MG_Config::Transport, ClientSession::Active() and # ImplementedVerbCount(), read by Harness/SplitRuntimePeek), so the only honest way to ask it # from a shell is to look at what the entries DID. When entries passed, the controls MUST # fire; when every one of them skipped, the step says so loudly and does not pretend. # # THE BODY OF THIS STEP IS scripts/ci/split_negative_controls.sh, and the move is the point # rather than tidiness. A `run:` block executes nowhere but on a runner, so these lines were # unreviewable and untestable: when the wave-1 cross-family review said they were broken, # CONFIRMING it needed a hand-made copy of them (wave1-codex-verify.md 8), and a copy is not # the thing. scripts/ci/control_smoke_test.sh now drives the very file this step runs. # # What that smoke test pins, and what ID-46 finding 8 found missing: each control asserts its # OWN failure reason. A non-zero ctest exit used to be enough, so a timeout, a setup abort or # any unrelated assertion printed "turned N selected entries red, as it must" and this step # went green. The arming run's `|| true` had the matching defect - it counted a case that ran # and FAILED as evidence the lane was live, so the controls could be measured against a # baseline that was already red. - name: Negative controls - the verb barrier and the persistent-map push must be load-bearing working-directory: build-split env: MOBILEGL_ITEST_REQUIRE_GPU: "1" CONTROL_TMPDIR: ${{ runner.temp }} run: bash "${GITHUB_WORKSPACE}/scripts/ci/split_negative_controls.sh" - name: Upload split lane logs if: always() uses: actions/upload-artifact@v7 with: name: integration-split-logs path: | build-split/MobileGL/MG_IntegrationTest/*.log* build-split/MobileGL/MG_IntegrationTest/split-logs/*.log if-no-files-found: warn - name: Upload core dumps if: failure() uses: actions/upload-artifact@v7 with: name: integration-split-core-dumps path: /tmp/core.* if-no-files-found: ignore # MobileGL/MG_Remote/Protocol/generated/protocol_generated.h is COMMITTED, and # flatc is deliberately absent from the default build graph (a codegen step in # the graph is how the earlier branch ended up cross-compiling an arm64 flatc # and trying to run it on the host). This job is what keeps the committed # header honest: build the pinned flatc, regenerate, and fail on any diff. # It needs no MobileGL build, so it does not depend on build-linux. flatc-check: runs-on: ubuntu-latest steps: - name: Checkout repo uses: actions/checkout@v6 - name: Get CMake uses: lukka/get-cmake@v4.3.3 - name: Check out the FlatBuffers submodule only # Just this one: the schema check has nothing to do with glslang, # SPIRV-Cross or the trace fixtures. run: git submodule update --init 3rdparty/flatbuffers - name: Regenerate protocol_generated.h run: python3 scripts/gen_protocol.py --build-dir "${{ runner.temp }}/flatc-build" - name: Fail if the committed header is stale run: git diff --exit-code -- MobileGL/MG_Remote/Protocol/generated/protocol_generated.h # P0.5 interface-purity gate A (ARCHITECTURE.md:501): the two extracted headers' include closure, # asserted on `-H` output because `nm --undefined-only` is blind to "included but not called" - # a header whose types are never named leaves no symbol behind, and "included at all" is exactly # the coupling P1 and P7 have to sever. Needs a preprocessor and three header submodules, no # CMake configure and no glslang sources, so like pipe-gates it does not depend on build-linux. # The script's own --self-test is always on: a negative control that stopped tripping fails the # job, because a gate that cannot go red is not a gate (ROADMAP.md:7). include-graph-check: name: Include-closure purity gate runs-on: ubuntu-latest steps: - name: Checkout repo uses: actions/checkout@v6 - name: Check out the three header submodules the closure needs # ska/flat_hash_map.hpp, xxhash.h and vulkan/vulkan.h are the only submodule headers # Includes.h reaches; glslang and spirv_cross are vendored under include/. run: git submodule update --init include/ska 3rdparty/xxHash 3rdparty/Vulkan-Headers - name: Install clang and the X11 headers vulkan.h pulls on Linux # Includes.h defines VK_USE_PLATFORM_XLIB_KHR before , which then # includes ; without libx11-dev every clang-mode probe dies in the # preprocessor and the gate reports 5 problems that have nothing to do with purity. run: sudo apt-get update && sudo apt-get install -y clang-20 libx11-dev - name: Include-closure assertions and negative control # --expect-probes 4 (contract-v2.md 7.6): an exit code cannot tell four probes from none, # so a --probe typo or a manifest edit that selected nothing would run zero probes and # exit 0 - the second half of the finding that added the flag. The count is the length of # scripts/check_include_closure.py's PROBES list and changing one means changing the other. # # --compiler stays clang++-20, which is what the step above installs (Debian's clang-20 # package ships /usr/bin/clang++-20). It is deliberately NOT the bare `clang++` the local # campaign gate spells: that spelling exists because the WSL box has no clang++-20, and # copying it here would trade a version-pinned compiler for whatever the runner has. run: python3 scripts/check_include_closure.py --mode both --compiler clang++-20 --self-test --require-all --expect-probes 4 benchmark: runs-on: ubuntu-latest needs: build-linux steps: - name: Checkout repo uses: actions/checkout@v6 - name: Get CMake uses: lukka/get-cmake@v4.3.3 - name: Install runtime dependencies # libegl-mesa0 is the EGL vendor library itself: DriverBench brings up a # real GL context, and libegl1 is only glvnd's dispatch. It normally # arrives as a Recommends of libegl1, which is too quiet a dependency for # the one job that needs a working driver. run: | sudo apt-get update sudo apt-get install -y libvulkan1 libegl1 libegl-mesa0 libgles2 libgl1-mesa-dri mesa-vulkan-drivers - name: Download Linux runtime uses: actions/download-artifact@v8 with: name: mobilegl-linux-runtime path: . - name: Unpack Linux runtime run: tar -xzf mobilegl-linux-runtime.tgz - name: Normalize CTest command paths run: | python - <<'PY' from pathlib import Path import re for path in Path('build-linux').rglob('CTestTestfile.cmake'): text = path.read_text() text = re.sub(r'"[^"]*/cmake-[^"]*/bin/cmake"', '"cmake"', text) path.write_text(text) PY - name: Benchmark working-directory: build-linux run: | ulimit -c unlimited sudo sysctl -w kernel.core_pattern='/tmp/core.%e.%p' ctest -V -C Release -L benchmark --no-tests=error - name: Upload core dumps if: failure() uses: actions/upload-artifact@v7 with: name: benchmark-core-dumps path: /tmp/core.* if-no-files-found: ignore build-retrace: runs-on: ubuntu-latest needs: - build-linux - test - benchmark - integration permissions: actions: write contents: read env: BUILD_DIR: build-retrace CCACHE_BASEDIR: ${{ github.workspace }} CCACHE_COMPRESS: "true" CCACHE_DIR: ${{ github.workspace }}/.ccache CCACHE_MAXSIZE: 4G CCACHE_NOHASHDIR: "true" MOBILEGL_LIBRARY: ${{ github.workspace }}/build-linux/libMobileGL.so steps: - name: Set Swap Space uses: pierotofy/set-swap-space@v1.0 with: swap-size-gb: 32 - name: Checkout repo uses: actions/checkout@v6 with: submodules: recursive - name: Get CMake uses: lukka/get-cmake@v4.3.3 - name: Restore ccache uses: actions/cache/restore@v5 with: path: .ccache key: ${{ runner.os }}-test-${{ github.job }}-ccache-v1 restore-keys: | ${{ runner.os }}-test-${{ github.job }}-ccache- - name: Prepare Vulkan SDK uses: humbletim/setup-vulkan-sdk@v1.2.1 with: vulkan-query-version: 1.4.304.1 vulkan-components: Vulkan-Headers, Vulkan-Loader vulkan-use-cache: true - name: Update glslang external sources working-directory: 3rdparty/glslang run: python update_glslang_sources.py - name: Install dependencies run: | sudo apt-get update sudo apt-get install -y ccache clang-20 clang++-20 lld-20 libc++-20-dev libc++abi-20-dev libvulkan-dev libegl1-mesa-dev libgles2-mesa-dev libgl1-mesa-dri mesa-vulkan-drivers ninja-build - name: Show installed toolchain run: | ccache --version clang-20 --version clang++-20 --version ld.lld-20 --version || ld.lld --version || true dpkg -l 'libc++*' 'libegl*' 'libgles*' 'mesa*' 'vulkan*' || true - name: Download Linux runtime uses: actions/download-artifact@v8 with: name: mobilegl-linux-runtime path: . - name: Unpack Linux runtime run: | tar -xzf mobilegl-linux-runtime.tgz test -f "${MOBILEGL_LIBRARY}" - name: Configure CMake run: | if [ "${{ secrets.ACTIONS_STEP_DEBUG }}" = "true" ]; then BUILD_TYPE=Debug else BUILD_TYPE=Release fi cmake -S . -B "${BUILD_DIR}" -G Ninja \ -DCMAKE_C_COMPILER=clang-20 \ -DCMAKE_CXX_COMPILER=clang++-20 \ -DCMAKE_C_COMPILER_LAUNCHER=ccache \ -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \ -DCMAKE_BUILD_TYPE="${BUILD_TYPE}" \ -DMOBILEGL_LOG_ACTIVE_LEVEL=MOBILEGL_LOG_LEVEL_INFO \ -DMOBILEGL_BUILD_TEST=OFF \ -DMOBILEGL_BUILD_BENCHMARK=OFF \ -DMOBILEGL_BUILD_TRACE_REPLAY=ON \ -DMOBILEGL_TRACE_REPLAY_MOBILEGL_LIBRARY="${MOBILEGL_LIBRARY}" \ -DCMAKE_POLICY_VERSION_MINIMUM=3.5 - name: Build trace replay run: cmake --build "${BUILD_DIR}" --target mobilegl_trace_replay --parallel "$(nproc)" - name: Show ccache stats if: always() run: ccache --show-stats - name: Release superseded ccache entry if: github.ref_name == github.event.repository.default_branch env: GH_TOKEN: ${{ github.token }} CACHE_KEY: ${{ runner.os }}-test-${{ github.job }}-ccache-v1 run: gh cache delete "${CACHE_KEY}" || true - name: Save ccache if: github.ref_name == github.event.repository.default_branch continue-on-error: true uses: actions/cache/save@v5 with: path: .ccache key: ${{ runner.os }}-test-${{ github.job }}-ccache-v1 - name: Normalize CTest command paths run: | python - <<'PY' from pathlib import Path import re for path in Path('build-retrace').rglob('CTestTestfile.cmake'): text = path.read_text() text = re.sub(r'"[^"]*/cmake-[^"]*/bin/cmake"', '"cmake"', text) path.write_text(text) PY - name: Package trace replay run: | mkdir -p ci-artifacts tar -czf ci-artifacts/mobilegl-trace-replay.tgz \ build-retrace/tools/trace_replay/mobilegl_trace_replay \ build-retrace/tools/trace_replay/CTestTestfile.cmake - name: Upload trace replay uses: actions/upload-artifact@v7 with: name: mobilegl-trace-replay path: ci-artifacts/mobilegl-trace-replay.tgz if-no-files-found: error trace-cases: name: trace case matrix runs-on: ubuntu-latest needs: - test - benchmark - integration outputs: matrix: ${{ steps.trace-cases.outputs.matrix }} names: ${{ steps.trace-cases.outputs.names }} verify-matrix: ${{ steps.trace-cases.outputs.verify-matrix }} split-matrix: ${{ steps.trace-cases.outputs.split-matrix }} steps: - name: Checkout repo uses: actions/checkout@v6 - name: Load trace cases id: trace-cases run: | echo "matrix=$(python3 tools/trace_replay/trace_cases.py --ci --format github-test-matrix)" >> "$GITHUB_OUTPUT" echo "names=$(python3 tools/trace_replay/trace_cases.py --ci --format names)" >> "$GITHUB_OUTPUT" # The subset the verify build retraces ("verify": true in trace_cases.json). It is a # SUBSET of the matrix above, so retrace-verify needs no fixtures of its own. echo "verify-matrix=$(python3 tools/trace_replay/trace_cases.py --ci --format github-verify-matrix)" >> "$GITHUB_OUTPUT" # P5's split subset ("split": true, DirectGLES only). Also a SUBSET of the matrix above, # so retrace-split needs no fixtures of its own either. It is one case today - OpenRA, # which is what the phase gate names - and trace_cases.py refuses a `split` case that is # not in CI or does not run DirectGLES, so the subset cannot silently become empty. SPLIT_MATRIX=$(python3 tools/trace_replay/trace_cases.py --ci --format github-split-matrix) # AND IT MUST NOT BE EMPTY. An empty `include` is not an error to GitHub - it skips the # whole retrace-split job with no red anywhere - so the one way this subset can vanish # silently is guarded here. trace_cases.py now also rejects an unknown manifest key, which # was the hole: `"splitt": true` loaded clean and emptied the subset (review N-4). if [ "$(printf '%s' "${SPLIT_MATRIX}" | python3 -c 'import json,sys; print(len(json.load(sys.stdin)["include"]))')" -lt 1 ]; then echo "::error::the split retrace subset is EMPTY. No case in trace_cases.json carries \"split\": true, so retrace-split would be skipped with no red. Exit gate E2 names OpenRA." exit 1 fi echo "split-matrix=${SPLIT_MATRIX}" >> "$GITHUB_OUTPUT" trace-fixtures: name: trace fixture (${{ matrix.case }}) runs-on: ubuntu-latest needs: trace-cases strategy: fail-fast: false max-parallel: 4 matrix: case: ${{ fromJSON(needs.trace-cases.outputs.names) }} steps: - name: Checkout repo uses: actions/checkout@v6 - name: Derive trace fixture cache key id: fixture-key run: bash .github/scripts/trace-fixture-cache.sh key '${{ matrix.case }}' - name: Restore trace fixture cache id: fixture-cache if: steps.fixture-key.outputs.cacheable == 'true' uses: actions/cache/restore@v5 with: path: ${{ steps.fixture-key.outputs.paths }} key: ${{ steps.fixture-key.outputs.key }} - name: Verify restored trace fixture id: fixture-verify if: steps.fixture-cache.outputs.cache-hit == 'true' run: | if bash .github/scripts/trace-fixture-cache.sh verify '${{ matrix.case }}'; then echo "ok=true" >> "$GITHUB_OUTPUT" else echo "ok=false" >> "$GITHUB_OUTPUT" echo "::warning::Cached fixture for ${{ matrix.case }} failed verification; falling back to the download path" bash .github/scripts/trace-fixture-cache.sh reset '${{ matrix.case }}' fi - name: Fetch trace fixture if: steps.fixture-verify.outputs.ok != 'true' run: bash .github/scripts/fetch-trace-fixture-lfs.sh '${{ matrix.case }}' - name: Save trace fixture cache if: steps.fixture-key.outputs.cacheable == 'true' && steps.fixture-cache.outputs.cache-hit != 'true' uses: actions/cache/save@v5 with: path: ${{ steps.fixture-key.outputs.paths }} key: ${{ steps.fixture-key.outputs.key }} - name: Stage trace fixture run: | safe_case="$(printf '%s' '${{ matrix.case }}' | sed 's/[^A-Za-z0-9._-]/_/g')" stage_dir="trace-fixtures/${safe_case}" mkdir -p "${stage_dir}" python3 tools/trace_replay/trace_cases.py --format fixture-files --case '${{ matrix.case }}' | while IFS= read -r file; do cp "${file}" "${stage_dir}/" done - name: Upload trace fixture uses: actions/upload-artifact@v7 with: name: trace-fixture-${{ matrix.case }} path: trace-fixtures/** if-no-files-found: error retrace: name: retrace (${{ matrix.backend }}, ${{ matrix.case }}) runs-on: ubuntu-latest needs: - build-linux - build-retrace - trace-cases - trace-fixtures if: ${{ always() && needs.build-linux.result == 'success' && needs.build-retrace.result == 'success' && needs.trace-cases.result == 'success' }} strategy: fail-fast: false max-parallel: 4 matrix: ${{ fromJSON(needs.trace-cases.outputs.matrix) }} steps: - name: Set Swap Space uses: pierotofy/set-swap-space@v1.0 with: swap-size-gb: 16 - name: Checkout repo uses: actions/checkout@v6 - name: Download trace fixture uses: actions/download-artifact@v8 with: name: trace-fixture-${{ matrix.case }} path: trace-fixture-download - name: Install trace fixture run: | mkdir -p tools/trace_replay/fixtures find trace-fixture-download -type f -exec cp {} tools/trace_replay/fixtures/ \; - name: Get CMake uses: lukka/get-cmake@v4.3.3 - name: Install runtime dependencies run: | sudo apt-get update sudo apt-get install -y libvulkan1 libegl1-mesa-dev libgles2-mesa-dev libgl1-mesa-dri mesa-vulkan-drivers test -e /usr/lib/x86_64-linux-gnu/libEGL.so test -e /usr/lib/x86_64-linux-gnu/libGLESv2.so - name: Download Linux runtime uses: actions/download-artifact@v8 with: name: mobilegl-linux-runtime path: . - name: Download trace replay uses: actions/download-artifact@v8 with: name: mobilegl-trace-replay path: . - name: Unpack retrace runtime run: | tar -xzf mobilegl-linux-runtime.tgz tar -xzf mobilegl-trace-replay.tgz test -f build-linux/libMobileGL.so test -f build-retrace/tools/trace_replay/mobilegl_trace_replay - name: Retrace and validate working-directory: build-retrace/tools/trace_replay run: | ulimit -c unlimited sudo sysctl -w kernel.core_pattern='/tmp/core.%e.%p' if [ '${{ matrix.backend }}' = 'DirectVulkan' ]; then export MOBILEGL_MAGMA_R11G11B10F_FALLBACK=1 fi if [ '${{ matrix.backend }}' = 'DirectVulkan' ] \ && [ '${{ matrix.case }}' = 'minecraft-1.21.4-fabric-iris-iterationrp-in-world' ]; then export MOBILEGL_MAGMA_FIX_ITERATIONRP_SUBGROUP_SCRATCH=1 export MOBILEGL_MAGMA_DERIVE_NUM_SUBGROUPS=1 export MOBILEGL_MAGMA_ITERATIONRP_FIX_BARRIER=1 fi # The blended depth-write quirk auto-enables only on Qualcomm, which no CI # runner has, so force it on for the OIT case it exists to fix. ForceOn # bypasses only the vendor gate, so this exercises the real strip on # lavapipe. The Android AVD lane deliberately leaves it off, keeping the # unstripped path covered for the same trace. if [ '${{ matrix.backend }}' = 'DirectVulkan' ] \ && [ '${{ matrix.case }}' = 'improved-transparency-minecraft-26.3' ]; then export MOBILEGL_MAGMA_DISABLE_BLENDED_DEPTH_WRITE=1 fi ctest -V --no-tests=error -R '^MobileGLTraceReplay\.${{ matrix.case }}\.${{ matrix.backend }}$' - name: Upload core dumps if: failure() uses: actions/upload-artifact@v7 with: name: retrace-core-dumps-${{ matrix.backend }}-${{ matrix.case }} path: /tmp/core.* if-no-files-found: ignore - name: Upload actual image if: always() uses: actions/upload-artifact@v7 with: name: retrace-result-${{ matrix.backend }}-${{ matrix.case }} path: | build-retrace/tools/trace_replay/${{ matrix.case }}/actual-images/** build-retrace/tools/trace_replay/${{ matrix.case }}/${{ matrix.backend }}/output/** if-no-files-found: warn retrace-summary: name: retrace summary runs-on: ubuntu-latest needs: retrace if: ${{ always() && needs.retrace.result != 'skipped' }} steps: - name: Checkout repo uses: actions/checkout@v6 - name: Set artifact metadata run: | echo "date_today=$(date +'%Y-%m-%d')" >> "$GITHUB_ENV" - name: Set up Node.js uses: actions/setup-node@v7 with: node-version: '22' - name: Download retrace results uses: actions/download-artifact@v8 with: pattern: retrace-result-* path: retrace-artifacts - name: Render retrace summary run: | node tools/trace_replay/render_retrace_summary.mjs \ --input retrace-artifacts \ --output-dir retrace-summary \ --title "MobileGL Linux retrace overview" \ --group-label "Linux" \ --html mobilegl-linux-retrace-overview.html - name: Upload retrace summary uses: actions/upload-artifact@v7 with: path: retrace-summary/mobilegl-linux-retrace-overview.html archive: false if-no-files-found: error # The trace half of the third CI mode. Same replay, same goldens, but the library underneath is # the verify build and MOBILEGL_PIPE_VERIFY=1 is in the environment, so every backend read of # frontend state is checked against a snapshot taken at the verb boundary. Eight cases rather # than the full lane's 40 (tools/trace_replay/trace_cases.json, "verify": true): the comparator # is budgeted at 5-10x, and the full sweep is a phase-exit / workflow_dispatch run. retrace-verify: name: retrace verify (${{ matrix.backend }}, ${{ matrix.case }}) runs-on: ubuntu-latest timeout-minutes: 240 needs: - build-linux-verify - build-retrace - trace-cases - trace-fixtures if: ${{ always() && needs.build-linux-verify.result == 'success' && needs.build-retrace.result == 'success' && needs.trace-cases.result == 'success' }} strategy: fail-fast: false max-parallel: 4 matrix: ${{ fromJSON(needs.trace-cases.outputs.verify-matrix) }} steps: - name: Set Swap Space uses: pierotofy/set-swap-space@v1.0 with: swap-size-gb: 16 - name: Checkout repo uses: actions/checkout@v6 - name: Download trace fixture uses: actions/download-artifact@v8 with: name: trace-fixture-${{ matrix.case }} path: trace-fixture-download - name: Install trace fixture run: | mkdir -p tools/trace_replay/fixtures find trace-fixture-download -type f -exec cp {} tools/trace_replay/fixtures/ \; - name: Get CMake uses: lukka/get-cmake@v4.3.3 - name: Install runtime dependencies run: | sudo apt-get update sudo apt-get install -y libvulkan1 libegl1-mesa-dev libgles2-mesa-dev libgl1-mesa-dri mesa-vulkan-drivers test -e /usr/lib/x86_64-linux-gnu/libEGL.so test -e /usr/lib/x86_64-linux-gnu/libGLESv2.so - name: Download Linux verify runtime uses: actions/download-artifact@v8 with: name: mobilegl-linux-runtime-verify path: . - name: Download trace replay uses: actions/download-artifact@v8 with: name: mobilegl-trace-replay path: . - name: Unpack the VERIFY runtime as the library under test # build-retrace's CTestTestfile.cmake has the absolute path # /build-linux/libMobileGL.so frozen into every case, so the swap happens here # rather than through a variable: the verify .so is put where that path points. The nm # check is what makes the swap falsifiable - a run against the ordinary library would # carry no comparator, ignore MOBILEGL_PIPE_VERIFY entirely, and match its golden. # # `nm`, not `nm -D`, for the reason spelled out in build-linux-verify: everything MGPipe is # hidden-visibility in a Release build and the dynamic table has none of it. run: | tar -xzf mobilegl-linux-runtime-verify.tgz tar -xzf mobilegl-trace-replay.tgz test -f build-verify/libMobileGL.so test -f build-retrace/tools/trace_replay/mobilegl_trace_replay mkdir -p build-linux cp build-verify/libMobileGL.so build-linux/libMobileGL.so if ! nm --defined-only build-linux/libMobileGL.so | grep -q MGPipeVerifyInputs; then echo "::error::the library unpacked at build-linux/libMobileGL.so defines no MGPipeVerifyInputs, so this retrace would replay against a comparator-free build and pass on its golden having verified nothing" exit 1 fi echo "the library at build-linux/libMobileGL.so is the verify build" - name: Retrace and validate under MOBILEGL_PIPE_VERIFY working-directory: build-retrace/tools/trace_replay # run_trace_case.cmake turns MOBILEGL_PIPE_VERIFY into three assertions of its own (the # arming line, no Fatal{PipeVerifyDiffer, no Fatal{UnmigratedPipeInput), so a case that # somehow ran the wrong library reds here instead of passing on its golden. # --timeout 10800: the 1800s cases run 5-10x slower with both comparator arms live, which # is well past ctest's 1500s default. run: | ulimit -c unlimited sudo sysctl -w kernel.core_pattern='/tmp/core.%e.%p' export MOBILEGL_PIPE_VERIFY=1 if [ '${{ matrix.backend }}' = 'DirectVulkan' ]; then export MOBILEGL_MAGMA_R11G11B10F_FALLBACK=1 fi if [ '${{ matrix.backend }}' = 'DirectVulkan' ] \ && [ '${{ matrix.case }}' = 'improved-transparency-minecraft-26.3' ]; then export MOBILEGL_MAGMA_DISABLE_BLENDED_DEPTH_WRITE=1 fi ctest -V --no-tests=error --timeout 10800 \ -R '^MobileGLTraceReplay\.${{ matrix.case }}\.${{ matrix.backend }}$' # The retrace lane's own always-on negative control, on one case so it costs one short trace: # with a snapshot field corrupted, the SAME replay must fail. Without it, "40 traces, zero # divergences" would be a statement about a comparator nobody watched. # # The rerun replays into the SAME case directory, so the verified run's images are put aside # first and restored before the verdict: "Upload actual image" below runs `if: always()` and # would otherwise ship the deliberately corrupted run's output under the name of the good one. # The restore happens whichever way the control goes, which is why the ctest exit status is # captured rather than tested inline. - name: Negative control - a corrupted snapshot field must red this retrace if: ${{ matrix.case == 'OpenRA' && matrix.backend == 'DirectGLES' }} working-directory: build-retrace/tools/trace_replay run: | export MOBILEGL_PIPE_VERIFY=1 export MOBILEGL_PIPE_VERIFY_CORRUPT=GetRenderStateParameters GOOD_OUTPUT="${RUNNER_TEMP}/openra-verified-output" rm -rf "${GOOD_OUTPUT}" if [ -d OpenRA ]; then cp -a OpenRA "${GOOD_OUTPUT}" fi set +e ctest -V --no-tests=error --timeout 10800 \ -R '^MobileGLTraceReplay\.OpenRA\.DirectGLES$' control_rc=$? set -e if [ -d "${GOOD_OUTPUT}" ]; then rm -rf OpenRA mv "${GOOD_OUTPUT}" OpenRA echo "restored the verified run's OpenRA output over the corrupted rerun's" fi if [ "${control_rc}" -eq 0 ]; then echo "::error::MOBILEGL_PIPE_VERIFY_CORRUPT=GetRenderStateParameters left the OpenRA retrace GREEN, so the comparator is not comparing and the whole verify retrace lane proves nothing." exit 1 fi echo "the corrupted field turned the retrace red, as it must (ctest exit ${control_rc})" - name: Upload core dumps if: failure() uses: actions/upload-artifact@v7 with: name: retrace-verify-core-dumps-${{ matrix.backend }}-${{ matrix.case }} path: /tmp/core.* if-no-files-found: ignore - name: Upload actual image if: always() uses: actions/upload-artifact@v7 with: name: retrace-verify-result-${{ matrix.backend }}-${{ matrix.case }} path: | build-retrace/tools/trace_replay/${{ matrix.case }}/actual-images/** build-retrace/tools/trace_replay/${{ matrix.case }}/${{ matrix.backend }}/output/** if-no-files-found: warn # P5's retrace arm: retrace-verify with MOBILEGL_PIPE_VERIFY=1 swapped for # MOBILEGL_TRANSPORT=inproc and the comparator's symbol swapped for an MG_Remote one. Exit gate # E2 is one row - OpenRA at SSIM >= 0.99 - and trace_cases.json's `split: true` is where that # subset lives. # # IT RUNS THE UNCHANGED CTEST NAMES with the transport exported in the JOB environment, rather # than the SPLIT-suffixed variant entries. build-retrace configures without # -DMOBILEGL_BUILD_DISAGGREGATED, so the variant entries are deliberately not registered there # (a name that says SPLIT in a build that cannot be one is worse than no name), and the # unchanged names are what retrace-verify already proves this shape works with. The variant # entries exist for a build that DOES configure the option - a local build-split with trace # replay on - where `ctest -L retrace-split` is self-describing and needs no environment ritual. # # WHAT MAKES IT FALSIFIABLE is not the SSIM. A monolith run of OpenRA also scores 1.000: measured # on this branch, a pull library under MOBILEGL_TRANSPORT=inproc produced ssim=1.0 and was caught # only by run_trace_case.cmake's transport-resolution assertion. So there are two guards, and the # SSIM is neither of them: the nm check below (this library carries MG_Remote) and the # transport-resolution line in the library's own log (this PROCESS resolved inproc). retrace-split: name: retrace split (${{ matrix.backend }}, ${{ matrix.case }}) runs-on: ubuntu-latest timeout-minutes: 240 needs: - build-linux - build-linux-split - build-retrace - trace-cases - trace-fixtures # build-linux is needed for the negative control ONLY: its pull library is what the control # swaps in to prove the transport-resolution assertion is load-bearing. if: ${{ always() && needs.build-linux.result == 'success' && needs.build-linux-split.result == 'success' && needs.build-retrace.result == 'success' && needs.trace-cases.result == 'success' }} strategy: fail-fast: false max-parallel: 4 matrix: ${{ fromJSON(needs.trace-cases.outputs.split-matrix) }} steps: - name: Set Swap Space uses: pierotofy/set-swap-space@v1.0 with: swap-size-gb: 16 - name: Checkout repo uses: actions/checkout@v6 - name: Download trace fixture uses: actions/download-artifact@v8 with: name: trace-fixture-${{ matrix.case }} path: trace-fixture-download - name: Install trace fixture run: | mkdir -p tools/trace_replay/fixtures find trace-fixture-download -type f -exec cp {} tools/trace_replay/fixtures/ \; - name: Get CMake uses: lukka/get-cmake@v4.3.3 - name: Install runtime dependencies run: | sudo apt-get update sudo apt-get install -y libvulkan1 libegl1-mesa-dev libgles2-mesa-dev libgl1-mesa-dri mesa-vulkan-drivers test -e /usr/lib/x86_64-linux-gnu/libEGL.so test -e /usr/lib/x86_64-linux-gnu/libGLESv2.so - name: Download Linux split runtime uses: actions/download-artifact@v8 with: name: mobilegl-linux-runtime-split path: . - name: Download trace replay uses: actions/download-artifact@v8 with: name: mobilegl-trace-replay path: . # The PULL runtime, for the negative control at the end of this job and for nothing else. - name: Download Linux pull runtime (negative control) uses: actions/download-artifact@v8 with: name: mobilegl-linux-runtime path: pull-runtime - name: Unpack the pull runtime (negative control) run: | tar -xzf pull-runtime/mobilegl-linux-runtime.tgz -C pull-runtime test -f pull-runtime/build-linux/libMobileGL.so - name: Unpack the SPLIT runtime as the library under test # build-retrace's CTestTestfile.cmake has the absolute path # /build-linux/libMobileGL.so frozen into every case, so the swap happens here # rather than through a variable, exactly as in retrace-verify. `nm`, not `nm -D`. run: | tar -xzf mobilegl-linux-runtime-split.tgz tar -xzf mobilegl-trace-replay.tgz test -f build-split/libMobileGL.so test -f build-retrace/tools/trace_replay/mobilegl_trace_replay mkdir -p build-linux cp build-split/libMobileGL.so build-linux/libMobileGL.so if ! nm --defined-only build-linux/libMobileGL.so | grep -q -i MG_Remote; then echo "::error::the library unpacked at build-linux/libMobileGL.so defines no MG_Remote symbol, so this retrace would replay against a monolith build, ignore MOBILEGL_TRANSPORT entirely and match its golden having split nothing" exit 1 fi echo "the library at build-linux/libMobileGL.so is the split build" - name: Retrace and validate under MOBILEGL_TRANSPORT=inproc working-directory: build-retrace/tools/trace_replay # run_trace_case.cmake turns MOBILEGL_TRANSPORT into assertions of its own - the library # must have RESOLVED the transport in this process, and its log must carry no Fatal{ - so a # case that somehow ran the wrong library reds here instead of passing on its golden. That # log is also the only valid refusal census: the console sink is compiled out of this # configuration, so a `ctest -V` transcript reports a false zero for Fatal{ lines. run: | ulimit -c unlimited sudo sysctl -w kernel.core_pattern='/tmp/core.%e.%p' export MOBILEGL_TRANSPORT=inproc ctest -V --no-tests=error --timeout 10800 \ -R '^MobileGLTraceReplay\.${{ matrix.case }}\.${{ matrix.backend }}$' # THE RETRACE LANE'S OWN ALWAYS-ON NEGATIVE CONTROL, and its absence was review finding M-6: # this job was a clone of retrace-verify with the one step removed that makes the lane mean # anything. retrace-verify carries "a corrupted snapshot field must red this retrace" so that # "79 traces, zero divergences" is not a statement about a comparator nobody watched; the # same sentence applies here word for word. # # The control swaps the PULL library into the frozen path and requires the SAME replay to # fail. It is the sharpest one available, because OpenRA scores ssim 1.000000 either way - # measured - so this step fails if and only if run_trace_case.cmake's transport-resolution # assertion has stopped working, which is the single thing standing between this job and a # green that ran monolith end to end. # # NOT the control BRIEF 7 E2 names ("patch the Clear emitter to drop one emission; SSIM must # fall below threshold"). That one needs an emitter, i.e. package c1, and it is carried as an # explicit debt in t1-v1.md rather than silently substituted - which is what the first # version of this package did. # # The rerun replays into the same case directory, so the good run's images are put aside and # restored whichever way the control goes; "Upload actual image" below runs `if: always()` # and would otherwise ship the deliberately-wrong run's output under the good run's name. # THE BODY OF THIS STEP IS scripts/ci/retrace_pull_library_control.sh, for the reason the # split lane's control gives: a `run:` block cannot be executed off a runner, so these lines # could not be tested until they ran in CI. scripts/ci/control_smoke_test.sh drives that file. # # Two holes ID-46 finding 8(b) found in this block, both CONFIRMED against the REAL ctest in a # REAL build tree, both closed in the script: it had NO selection guard at all - unlike the # split lane's run_control - so a case/backend regex matching nothing exited 8 through # `--no-tests=error` and was read as "the pull library turned it red"; and only "non-zero # ctest" was checked after the nm identity check, so a loader failure, a missing fixture or a # timeout passed it. The red must now carry run_trace_case.cmake's own sentence. - name: Negative control - the PULL library must red this split retrace working-directory: build-retrace/tools/trace_replay env: CONTROL_TMPDIR: ${{ runner.temp }} PULL_LIBRARY: ${{ github.workspace }}/pull-runtime/build-linux/libMobileGL.so FROZEN_LIBRARY: ${{ github.workspace }}/build-linux/libMobileGL.so run: >- bash "${GITHUB_WORKSPACE}/scripts/ci/retrace_pull_library_control.sh" '${{ matrix.case }}' '${{ matrix.backend }}' # The refusal census, recorded rather than gated. run_trace_case.cmake already REDS the case # on any Fatal{, so reaching here means the count is zero - but the number and the distinct # slot names are what MEASUREMENTS wants from every split run, and reading them out of the # library's own log is the only way to get them (ctest -V's transcript is a false zero). - name: Refusal census from the library log if: always() working-directory: build-retrace/tools/trace_replay run: | log="${{ matrix.case }}/${{ matrix.backend }}/output/mobilegl.log" if [ ! -f "${log}" ]; then echo "no ${log} - the replay wrote no library log" exit 0 fi echo "Fatal{ lines: $(grep -c 'Fatal{' "${log}" || true)" grep -o 'Fatal{[A-Za-z]*, "[^"]*"' "${log}" | sort | uniq -c | sort -rn | head -20 || true grep -m1 "MOBILEGL_TRANSPORT=" "${log}" || echo "no transport line in ${log}" - name: Upload core dumps if: failure() uses: actions/upload-artifact@v7 with: name: retrace-split-core-dumps-${{ matrix.backend }}-${{ matrix.case }} path: /tmp/core.* if-no-files-found: ignore - name: Upload actual image if: always() uses: actions/upload-artifact@v7 with: name: retrace-split-result-${{ matrix.backend }}-${{ matrix.case }} path: | build-retrace/tools/trace_replay/${{ matrix.case }}/actual-images/** build-retrace/tools/trace_replay/${{ matrix.case }}/${{ matrix.backend }}/output/** if-no-files-found: warn # G1's own job: the pull build must be the tree before P1, symbol for symbol and byte for byte. # workflow_dispatch only - it builds the library twice from scratch, and its answer is about a # BASELINE rather than about this push, so a per-push run would be measuring the wrong pair. monolith-symbol-report: name: monolith symbol report runs-on: ubuntu-latest timeout-minutes: 180 if: ${{ github.event_name == 'workflow_dispatch' }} env: CCACHE_BASEDIR: ${{ github.workspace }} CCACHE_COMPRESS: "true" CCACHE_DIR: ${{ github.workspace }}/.ccache CCACHE_MAXSIZE: 4G CCACHE_NOHASHDIR: "true" steps: - name: Set Swap Space uses: pierotofy/set-swap-space@v1.0 with: swap-size-gb: 32 - name: Checkout repo uses: actions/checkout@v6 with: submodules: recursive fetch-depth: 0 - name: Get CMake uses: lukka/get-cmake@v4.3.3 - name: Restore ccache uses: actions/cache/restore@v5 with: path: .ccache key: ${{ runner.os }}-test-${{ github.job }}-ccache-v1 restore-keys: | ${{ runner.os }}-test-${{ github.job }}-ccache- - name: Prepare Vulkan SDK uses: humbletim/setup-vulkan-sdk@v1.2.1 with: vulkan-query-version: 1.4.304.1 vulkan-components: Vulkan-Headers, Vulkan-Loader vulkan-use-cache: true - name: Install build dependencies run: | sudo apt-get update sudo apt-get install -y ccache clang-20 clang++-20 lld-20 libc++-20-dev libc++abi-20-dev libvulkan-dev libegl1-mesa-dev libgles2-mesa-dev libgl1-mesa-dri mesa-vulkan-drivers ninja-build binutils # Both sides with IDENTICAL flags, LTO off, the same compiler and the same standard library: # symbol_report.py's guard rails (scripts/symbol_report.py) say a mismatched pair "adds" # thousands of symbols and the comparison then means nothing. The library alone - no tests, # no benchmark, no integration test, no trace replay - because those targets do not ship. - name: Build the baseline library (${{ inputs.baseline_sha }}) run: | git worktree add ../baseline "${{ inputs.baseline_sha }}" cd ../baseline git submodule update --init --recursive (cd 3rdparty/glslang && python update_glslang_sources.py) cmake -S . -B build-sym-base -G Ninja \ -DCMAKE_C_COMPILER=clang-20 -DCMAKE_CXX_COMPILER=clang++-20 \ -DCMAKE_C_COMPILER_LAUNCHER=ccache -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \ -DCMAKE_BUILD_TYPE=Release \ -DMOBILEGL_LOG_ACTIVE_LEVEL=MOBILEGL_LOG_LEVEL_INFO \ -DMOBILEGL_BUILD_TEST=OFF -DMOBILEGL_BUILD_BENCHMARK=OFF \ -DMOBILEGL_BUILD_INTEGRATION_TEST=OFF -DMOBILEGL_BUILD_TRACE_REPLAY=OFF \ -DMOBILEGL_BUILD_DISAGGREGATED=OFF \ -DMOBILEGL_PIPE_PUSH=OFF -DMOBILEGL_PIPE_VERIFY=OFF \ -DMOBILEGL_ENABLE_LTO=OFF \ -DCMAKE_POLICY_VERSION_MINIMUM=3.5 cmake --build build-sym-base --parallel "$(nproc)" cp build-sym-base/libMobileGL.so "${GITHUB_WORKSPACE}/libMobileGL-baseline.so" - name: Build the head library run: | (cd 3rdparty/glslang && python update_glslang_sources.py) cmake -S . -B build-sym-head -G Ninja \ -DCMAKE_C_COMPILER=clang-20 -DCMAKE_CXX_COMPILER=clang++-20 \ -DCMAKE_C_COMPILER_LAUNCHER=ccache -DCMAKE_CXX_COMPILER_LAUNCHER=ccache \ -DCMAKE_BUILD_TYPE=Release \ -DMOBILEGL_LOG_ACTIVE_LEVEL=MOBILEGL_LOG_LEVEL_INFO \ -DMOBILEGL_BUILD_TEST=OFF -DMOBILEGL_BUILD_BENCHMARK=OFF \ -DMOBILEGL_BUILD_INTEGRATION_TEST=OFF -DMOBILEGL_BUILD_TRACE_REPLAY=OFF \ -DMOBILEGL_BUILD_DISAGGREGATED=OFF \ -DMOBILEGL_PIPE_PUSH=OFF -DMOBILEGL_PIPE_VERIFY=OFF \ -DMOBILEGL_ENABLE_LTO=OFF \ -DCMAKE_POLICY_VERSION_MINIMUM=3.5 cmake --build build-sym-head --parallel "$(nproc)" # The monolith must not have grown a remote half. ARCHITECTURE.md:506: MG_Remote lives behind # MOBILEGL_BUILD_DISAGGREGATED and nothing of it may reach a shipped pull build. - name: No MG_Remote in the pull build run: | if nm --defined-only build-sym-head/libMobileGL.so | grep -q MG_Remote; then echo "::error::the pull build defines MG_Remote symbols; the disaggregated half leaked into the monolith" nm --defined-only build-sym-head/libMobileGL.so | grep MG_Remote | head -20 exit 1 fi echo "no MG_Remote symbols in the pull build" - name: Symbol report (G1) run: | python3 scripts/symbol_report.py \ --before libMobileGL-baseline.so \ --after build-sym-head/libMobileGL.so \ --threshold 0 \ --fail-on-symbol-set-change \ --fail-on-added-bytes 0 \ --markdown symbol-report.md \ --json symbol-report.json - name: Upload the symbol report if: always() uses: actions/upload-artifact@v7 with: name: monolith-symbol-report path: | symbol-report.md symbol-report.json if-no-files-found: error remove-artifact-clutter: name: remove artifact clutter runs-on: ubuntu-latest # (d) retrace-verify too: this job deletes the trace-fixture-* artifacts, and the verify # retraces download the same ones. needs: - retrace-summary - retrace-verify if: always() permissions: actions: write steps: - name: Delete intermediate Linux retrace artifacts env: GH_TOKEN: ${{ github.token }} run: | # Both retrace lanes, not just the pull one: `retrace verify (backend, case)` downloads # the same trace-fixture- artifact, and a failed verify retrace is exactly when # someone needs that fixture to reproduce locally. The two prefixes are stripped in # order, longest first, because "retrace (" is not a prefix of "retrace verify (". declare -A failed_cases=() while IFS= read -r job_name; do case_name="${job_name#retrace verify (*, }" case_name="${case_name#retrace (*, }" case_name="${case_name%)}" failed_cases["${case_name}"]=1 done < <( gh api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/jobs?per_page=100" \ --jq '.jobs[] | select((.name | startswith("retrace (")) or (.name | startswith("retrace verify ("))) | select(.conclusion == "failure" or .conclusion == "cancelled" or .conclusion == "timed_out" or .conclusion == "action_required") | .name' ) if ((${#failed_cases[@]})); then echo "Retaining fixtures for failed retrace case(s):" printf ' %s\n' "${!failed_cases[@]}" else echo "All retrace jobs succeeded; no fixtures need to be retained." fi deleted=0 retained=0 while IFS=$'\t' read -r artifact_id artifact_name; do if [[ "${artifact_name}" == trace-fixture-* ]]; then case_name="${artifact_name#trace-fixture-}" if [[ -v "failed_cases[${case_name}]" ]]; then echo "Retaining ${artifact_name} (${artifact_id}) for failed retrace." ((retained += 1)) continue fi fi echo "Deleting ${artifact_name} (${artifact_id})" gh api --method DELETE "repos/${GITHUB_REPOSITORY}/actions/artifacts/${artifact_id}" ((deleted += 1)) done < <( gh api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/artifacts?per_page=100" \ --jq '.artifacts[] | select(.name | startswith("trace-fixture-") or startswith("retrace-result-")) | [.id, .name] | @tsv' ) echo "Deleted ${deleted} intermediate Linux artifact(s); retained ${retained} failed-retrace fixture(s)." pipe-gates: name: MGPipe generators and hygiene gates runs-on: ubuntu-latest # Deliberately independent of build-linux: these are source-level gates, they take # seconds, and a broken build must not hide a drifted interface. env: # THE CURRENT PHASE's base ref, for the two G5 region gates below. It is 37da3c3a - P4a's # base ref, INTEGRATOR-DECISIONS ID-1 - and NOT the workflow's baseline_sha input: that input # is the SYMBOL baseline (087685d1, P1's G1 reading) and it is empty on a push, whereas these # gates ask "did the do-not-touch list move since the phase started". # # IT MOVED FROM P3a's 44c2b5cf TO P4a's 37da3c3a WITH THE PHASE, and that is a deliberate # narrowing rather than a loss: P3a's eleven functions were compared against 44c2b5cf at P3a's # own exit and were byte-identical there, so 37da3c3a carries the same bodies (measured: the # eleven shas at 37da3c3a are the eleven shas at 44c2b5cf, and FlushPendingRangesFrom's is # still the sha pinned in the script at 3e298c9a). What the two gates now both answer is "did # anything on the list move during P4a", which is the question this phase can act on. BASELINE: "37da3c3a" steps: - name: Checkout repo uses: actions/checkout@v6 with: # The G5 gate reads Managers.cpp at BASELINE with `git show`, which a depth-1 checkout # does not have. Nothing else in this job needs history. fetch-depth: 0 # The seven generators all read MG_Pipe/*.def, so regenerating and diffing is what # keeps the two interface tables, the wire records, the verify comparators, the # PipeInputs field ids, the read-inventory coverage and the render-state member list # from drifting apart from the catalogue. The generated files are committed # deliberately: the build must not depend on python. - name: Regenerate the MGPipe interface (G1-G7) run: | python3 scripts/gen_pipe.py git diff --exit-code -- MobileGL/MG_Pipe/generated # The generators' own negative controls: canned inputs that MUST trip each structural check # (a field list that does not cover its struct's members, a verb set that is not the function # table's). Regenerating and diffing above cannot see a check that silently stopped # checking - a broken gate and a clean tree produce the same green. - name: The MGPipe generators' checks can still fail run: python3 scripts/gen_pipe.py --self-test # The same question for the symbol tool the P1 gate is written in terms of. - name: The symbol report's buckets and gates can still fail run: python3 scripts/symbol_report.py --self-test # Per-draw fprintf/printf instrumentation has repeatedly been committed by accident, # once inside a mutex critical section. Nothing under these two trees prints to a # stdio stream today - MGLOG_D compiles out in INFO builds and is the only channel # they are allowed to use - so this gate starts with no exceptions, and any addition # to it needs a reason in the pull request rather than a quiet whitelist entry. The # alternation names every stdio spelling, not just the two that were committed: # fprintf to either stream, printf, puts, and the iostream pair. - name: No stdio instrumentation in MG_Backend or MG_State run: | if grep -rnE 'fprintf[[:space:]]*\((stderr|stdout)|(^|[^[:alnum:]_>.])printf[[:space:]]*\(|(^|[^[:alnum:]_>.:])puts[[:space:]]*\(|std::(cout|cerr)' \ MobileGL/MG_Backend MobileGL/MG_State; then echo "::error::stdio instrumentation found; use MGLOG_D (compiled out in INFO builds)" exit 1 fi echo "no fprintf(stderr/stdout / printf( / puts( / std::cout|cerr under MobileGL/MG_Backend or MobileGL/MG_State" # A GATE as of P2, which is when MG_Pipe/DirtySurface.def exists to diff the scan against # (ROADMAP.md:18 puts the first mapping round in P2). --check fails BOTH directions: a # mutator the scanner finds with no row in the def, and a row naming a mutator the scan no # longer finds - so a deleted mutator cannot leave a stale row behind claiming coverage. # # --self-test is the half that keeps --check honest, and it is not optional. A completeness # check that silently stopped checking produces exactly the same green as a complete # mapping; the self-test feeds it two canned negative controls (a mutator withheld from the # def, a row naming a function that does not exist) and fails if either fails to trip. Same # shape as gen_pipe.py --self-test and check_include_closure.py above. # # What this gate does NOT cover is written into DirtySurface.def's header rather than left # implicit: the scanner attributes a mutation inside a lambda to the enclosing function, # reads a mutation published through a helper as deferred, and scans only MG_Impl/GLImpl - # so the four MGP_NOTE_MUTATION sites in MG_State are outside it entirely. This is a # completeness gate over what the scanner can see; the semantic proof is the verify lane. - name: MGPipe dirty-surface mapping is complete (G9) run: | python3 scripts/gen_pipe_dirty_surface.py --check python3 scripts/gen_pipe_dirty_surface.py --self-test # A GATE as of P5 (R-7.1, CONTRACT-P5.md table 2). The eighth generator, and the only one # whose output the step above cannot cover: `gen_pipe.py` does not write # PipeFieldOwnership.inc, so regenerating the seven and diffing MG_Pipe/generated leaves a # drifted ownership table green. The build-level static_assert only catches an # UNCLASSIFIED row; a hand edit that CHANGES a class compiles clean, and --check is the # only thing in the tree that catches it. # # NO BRANCH GUARD, deliberately, unlike the two G5 steps below: this asks "does the # committed table still follow from the .def files", which is a question every branch can # answer and every branch wants answered. The table outlives feat/disaggregated. # # --self-test is not optional, for the reason the two gates above give and for one this # generator learned the hard way: its first version counted eleven trips when one control # was a silent duplicate of another, because the harness asked "did something exit" rather # than "did THIS exit". Every control now asserts its own message, and a harness control # asserts that the harness still rejects someone else's exit. - name: MGPipe PipeInputs field-ownership table is complete (R-7.1, table 2) run: | python3 scripts/gen_pipe_field_ownership.py --check python3 scripts/gen_pipe_field_ownership.py --self-test # R-16 APPLIED TO THE NEGATIVE CONTROLS THEMSELVES. The split lane's E1/E3(a) controls and the # retrace lane's pull-library control are gates, and until ID-46 finding 8 neither could be # made red by anyone: their bodies were `run:` blocks, which execute only on a runner. Both # bodies now live in scripts/ci/, and this step runs them against a stubbed ctest that # reproduces the finding - a NON-EMPTY selection failing with UNRELATED_CONTROL_FAILURE, and a # case/backend regex matching no tests - and requires each control to report FAILED. The same # stub, failing with the diagnostics the scenarios really emit, must make them report PASSED. # # NO BRANCH GUARD: this asks "do the negative controls still reject a red that is not theirs", # which is a question every branch can answer and none of which depends on the TEMPORARY # feat/disaggregated trigger at the top of this file. It costs a couple of seconds and needs # no build. - name: The split and retrace negative controls still reject a red that is not theirs (R-16) run: bash scripts/ci/control_smoke_test.sh # A GATE as of P3a (G5). "pool 与延迟释放原样搬" (ROADMAP.md:19) is meant literally: the # buffer pool, the deferred-release drain and the three persistently mapped rings move # VERBATIM, and ARCHITECTURE.md:515 says why - their retire happens only inside Present, so # a batching or ordering change there starves them, and nothing else in this workflow can # see it. P3a rewrites the rest of Managers.cpp by design, so a file diff says nothing; the # script extracts the ELEVEN named bodies and compares their hashes on their own. # # Eleven and not ten (ID-15): Managers.cpp carries the three-tier flush drain TWICE, once # per preprocessor arm, and a push build compiles only FlushPendingRangesFrom while the # untouched FlushPendingRangesNow lives in the `#else`. Hashing the pull name alone would # protect text no shipping build compiles, so both are hashed - the pull ladder against # BASELINE, the push ladder against a sha pinned in the script at 3dadd4c1 (ID-41), because # that one was born in P3a and is compared against the reviewed body rather than against the # base ref. # # Scoped to the disaggregation branch and to a manual dispatch, deliberately: the question # is "did these eleven move since P3a started", and BASELINE is P3a's base ref. On dev, # where unrelated buffer fixes land on their own schedule, the same comparison would be # asking a question nobody posed - it belongs with the TEMPORARY trigger lines at the top # of this file and retires with them. # # --self-test is the half that keeps it honest, and it is not optional: a comparison that # silently stopped comparing produces exactly the same green as eleven untouched bodies. It # runs eight canned controls - eleven bodies extracted, an untouched copy compared equal, an # edit OUTSIDE them ignored, each of the three perturbation targets (ClearBufferPool and BOTH # flush ladders) reported BY NAME, plus the pin-precedence control and a one-token edit to the # pinned ladder compared against the pin - and fails if any of them does not answer. # Same shape as gen_pipe.py --self-test above. - name: The buffer pool, the deferred-release drain and the rings did not move (G5) if: ${{ github.ref == 'refs/heads/feat/disaggregated' || github.event_name == 'workflow_dispatch' }} run: bash scripts/p3a_untouched_regions.sh "${BASELINE}" HEAD - name: The untouched-region gate can still fail (G5) if: ${{ github.ref == 'refs/heads/feat/disaggregated' || github.event_name == 'workflow_dispatch' }} run: bash scripts/p3a_untouched_regions.sh --self-test # A GATE AS OF P4a (G5), and a SECOND script rather than an edit to the one above. P4a extends # the same claim to the rest of ARCHITECTURE.md:318's do-not-touch list - the unpack PBO ring's # staging repack and its two helpers, the attachment permutation, the D24S8 sampling-emulation # core and the format-caveat handler - which is SEVENTEEN regions across THREE files # (BRIEF-P4A.md D-N: P3a's eleven, which P4a must not touch either, plus P4a's six). The # parent's SOURCE_PATH is a single file, so the extension needed a per-region source path and # a region KIND (DepthStencilSamplingReadImpl is a namespace, not a function); everything else # about the extraction is its parent's, verbatim. # # Both scripts run. The parent keeps answering its own question against its own eleven, so a # regression in either half names itself, and neither gate can be silenced by editing the # other's list. # # Same feat/disaggregated-or-dispatch guard as the P3a step, for the same reason: the question # is "did these move since the phase started", and on dev - where unrelated buffer and texture # fixes land on their own schedule - it would be a question nobody posed. It belongs with the # TEMPORARY trigger lines at the top of this file and retires with them. # # --self-test is the half that keeps it honest and is not optional: a comparison that silently # stopped comparing produces exactly the same green as seventeen untouched regions. It runs # three positive controls (seventeen regions extracted, an untouched copy compared equal, an # edit OUTSIDE them invisible in all three files) and NINE negative ones - ClearBufferPool, # FlushPendingRangesNow, RecomputeBackendColorSlots and StageBlocksIntoUnpackRing, each # perturbed at its HEAD and at its TAIL and each required to be named BY NAME, plus a # one-token edit to the pinned FlushPendingRangesFrom body compared against the pin - and # fails if any of them does not answer. - name: The unpack ring, the attachment permutation, the D24S8 core and the format caveat did not move (G5) if: ${{ github.ref == 'refs/heads/feat/disaggregated' || github.event_name == 'workflow_dispatch' }} run: bash scripts/p4a_untouched_regions.sh "${BASELINE}" HEAD - name: The P4a untouched-region gate can still fail (G5) if: ${{ github.ref == 'refs/heads/feat/disaggregated' || github.event_name == 'workflow_dispatch' }} run: bash scripts/p4a_untouched_regions.sh --self-test # Warning only for now: the disaggregation documents are still being written, and a # lint that fails a rewrite in progress teaches people to ignore it. It becomes # --strict when the documents settle. - name: Documentation citation lint run: | shopt -s nullglob documents=(docs/Disaggregated/*.md) if [ ${#documents[@]} -eq 0 ]; then echo "no disaggregation documents to check" exit 0 fi python3 scripts/check_doc_citations.py "${documents[@]}" || true