[Fix] (IntegrationTest): gate private split logs and repair control red-checks

.github/workflows/test.yml

@@ -1043,9 +1043,9 @@ jobs:
       # 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 is the one Split entry
+      # selects InProcess, and the DirectGLES.Split.PersistentMapArm. entry retains its private
-      # with a MOBILEGL_LOG_FILE_PATH of its own (nothing else writes it, so the grep means what it
+      # counting log (all Split entries now have private paths; nothing else writes this file).
-      # says). The line is written during bring-up, before any scenario decides to skip, so this
+      # 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
@@ -1106,7 +1106,9 @@ jobs:
         uses: actions/upload-artifact@v7
         with:
           name: integration-split-logs
-          path: build-split/MobileGL/MG_IntegrationTest/*.log*
+          path: |
+            build-split/MobileGL/MG_IntegrationTest/*.log*
+            build-split/MobileGL/MG_IntegrationTest/split-logs/*.log
           if-no-files-found: warn
 
       - name: Upload core dumps

MobileGL/MG_IntegrationTest/CMakeLists.txt

@@ -1950,7 +1950,6 @@ if (MOBILEGL_BUILD_DISAGGREGATED)
 
     gtest_discover_tests(MobileGLIntegrationTest
         TEST_PREFIX "DirectGLES.Split.PersistentMapArm."
-        TEST_LIST MGL_SPLIT_ARM_TESTS
         TEST_FILTER "PersistentCoherentMapScenario.TheMapLandsInTheArmItsLaneDeclares"
         DISCOVERY_TIMEOUT 30
         PROPERTIES
@@ -1984,8 +1983,9 @@ if (MOBILEGL_BUILD_DISAGGREGATED)
         "MGITEST_SMALL_RING_LANE=1" "MOBILEGL_IPC_RING_MB=1" "MOBILEGL_IPC_STAGE_MB=1"
         ${MGL_ITEST_CAPABILITY_ENV} ${MGL_ITEST_COMMON_ENV})
 
-    foreach(mglItestSmallRingScenario ClearThenReadPixelsScenario TriangleScenario
+    set(MGL_SPLIT_SMALL_RING_SCENARIOS ClearThenReadPixelsScenario TriangleScenario
                                       PersistentCoherentMapScenario)
+    foreach(mglItestSmallRingScenario IN LISTS MGL_SPLIT_SMALL_RING_SCENARIOS)
         gtest_discover_tests(MobileGLIntegrationTest
             TEST_PREFIX "DirectGLES.Split.SmallRing."
             TEST_LIST "MGL_SPLIT_SMALL_${mglItestSmallRingScenario}_TESTS"
@@ -2001,9 +2001,12 @@ if (MOBILEGL_BUILD_DISAGGREGATED)
     configure_file(Harness/SplitLogPaths.cmake.in SplitLogPaths.cmake @ONLY)
     set_property(DIRECTORY APPEND PROPERTY TEST_INCLUDE_FILES
         "${CMAKE_CURRENT_BINARY_DIR}/SplitLogPaths.cmake")
+    # Python is mandatory for this split integration gate (also used by the CI controls).
+    # Do not silently omit the ownership check when the interpreter is unavailable.
     find_package(Python3 REQUIRED COMPONENTS Interpreter)
     add_test(NAME SplitLogPaths.PrivateAndDistinct
         COMMAND "${Python3_EXECUTABLE}"
             "${CMAKE_CURRENT_SOURCE_DIR}/Harness/split_log_paths.py"
             check "${CMAKE_CTEST_COMMAND}" "${CMAKE_BINARY_DIR}")
+    set_tests_properties(SplitLogPaths.PrivateAndDistinct PROPERTIES LABELS "integration-split")
 endif()

MobileGL/MG_IntegrationTest/Harness/SplitLogPaths.cmake.in

@@ -5,7 +5,7 @@ foreach(entry IN LISTS MGL_SPLIT_CLEAR_TESTS MGL_SPLIT_TRIANGLE_TESTS MGL_SPLIT_
     set_tests_properties("${entry}" PROPERTIES ENVIRONMENT
         "MOBILEGL_LOG_FILE_PATH=@CMAKE_CURRENT_BINARY_DIR@/split-logs/${entry}.log")
 endforeach()
-foreach(scenario ClearThenReadPixelsScenario TriangleScenario PersistentCoherentMapScenario)
+foreach(scenario @MGL_SPLIT_SMALL_RING_SCENARIOS@)
     foreach(entry IN LISTS MGL_SPLIT_SMALL_${scenario}_TESTS)
         set_tests_properties("${entry}" PROPERTIES ENVIRONMENT
             "MOBILEGL_LOG_FILE_PATH=@CMAKE_CURRENT_BINARY_DIR@/split-logs/${entry}.log")

MobileGL/MG_IntegrationTest/Harness/split_log_paths.py

@@ -14,7 +14,7 @@ def paths(document):
         props = {p["name"]: p["value"] for p in test.get("properties", [])}
         values = [v.split("=", 1)[1] for v in props.get("ENVIRONMENT", [])
                   if v.startswith("MOBILEGL_LOG_FILE_PATH=")]
-        is_split = "integration-split" in props.get("LABELS", [])
+        is_split = test["name"].startswith("DirectGLES.Split.")
         if is_split and (len(values) != 1 or not values[0]):
             raise ValueError(f"{test['name']}: requires exactly one nonempty MOBILEGL_LOG_FILE_PATH")
         for value in values:

scripts/ci/control_smoke_test.sh

@@ -19,7 +19,7 @@
 set -u
 
 HERE="$(cd "$(dirname "$0")" && pwd)"
-WORK="$(mktemp -d)"
+WORK="$(mktemp -d)" || exit 1
 trap 'rm -rf "${WORK}"' EXIT
 
 STUB_DIR="${WORK}/stub"
@@ -99,6 +99,10 @@ expect FAILED "a pull library passed the split retrace"      -- run_retrace retr
 
 echo
 echo "smoke test: ${passes} passed, ${failures} failed"
+# Keep the private-file cases on the entry point used by CI and the local gate.
+if ! bash "${HERE}/testdata/split_private_log_smoke.sh"; then
+  failures=$((failures + 1))
+fi
 if [ "${failures}" -gt 0 ]; then
   echo "CONTROL_SMOKE_TEST_FAILED"
   exit 1

scripts/ci/redcheck_control_smoke_test.sh

@@ -5,13 +5,13 @@
 # X = revert the message check in each control, i.e. put the controls back in the state ID-46
 #     finding 8 found them in: a non-zero ctest exit is accepted whatever the failure was.
 #
-# The smoke test must then FAIL, and it must fail on the two cases that exist for this defect -
+# The smoke test must then FAIL on the cases that exist for this defect -
 # "unrelated failure with a non-empty selection" and "red without the transport-resolution
-# message" - and not merely somewhere. A smoke test that goes red for any other reason when the
+# message", plus the missing private-file Fatal - and not merely somewhere. A smoke test that goes
-# evidence check is removed would not be pinning the evidence check.
+# red for any other reason when the evidence check is removed would not be pinning the evidence check.
 set -u
 HERE="$(cd "$(dirname "$0")" && pwd)"
-WORK="$(mktemp -d)"
+WORK="$(mktemp -d)" || exit 1
 trap 'cp "${WORK}/split.orig" "${HERE}/split_negative_controls.sh"; cp "${WORK}/retrace.orig" "${HERE}/retrace_pull_library_control.sh"; rm -rf "${WORK}"' EXIT
 
 cp "${HERE}/split_negative_controls.sh" "${WORK}/split.orig"
@@ -27,27 +27,35 @@ tail -1 "${WORK}/before.log"
 
 echo
 echo "=== perturbation: remove the evidence check from both controls"
-python3 - "${HERE}/split_negative_controls.sh" "${HERE}/retrace_pull_library_control.sh" <<'PY'
+python3 - "${HERE}/split_negative_controls.sh" "${HERE}/retrace_pull_library_control.sh" <<'PY' || exit 1
 import sys
+import re
 split, retrace = sys.argv[1], sys.argv[2]
 for path, needle in ((split, 'grep -qE "${evidence}"'), (retrace, 'grep -qF "${EVIDENCE}"')):
     text = open(path).read()
+    if path == split:
+        text, count = re.subn(
+            r'(?m)^    python3 "\$\{log_helper\}" evidence[^\n]*\n[^\n]*\|\| exit 1\n',
+            '    : "private-file evidence check removed by red-check"\n', text)
+        if count != 1:
+            raise SystemExit(f"expected exactly one private-file evidence check in {path}, found {count}")
     out, hit = [], 0
     for line in text.splitlines(keepends=True):
-        if needle in line and line.lstrip().startswith('if ! '):
+        if needle in line and line.lstrip().startswith(('if ! ', 'elif ! ')):
             indent = line[:len(line) - len(line.lstrip())]
-            out.append(f"{indent}if false; then\n")
+            keyword = 'elif' if line.lstrip().startswith('elif ') else 'if'
+            out.append(f"{indent}{keyword} false; then\n")
             hit += 1
         else:
             out.append(line)
     if hit != 1:
         raise SystemExit(f"expected exactly one evidence check in {path}, found {hit}")
     open(path, 'w').write(''.join(out))
-print("both evidence checks reverted to 'any non-zero ctest exit is accepted'")
+print("E1 private-file, E3(a) and retrace evidence checks reverted to 'any non-zero ctest exit is accepted'")
 PY
 
 echo
-echo "=== the smoke test on the reverted controls (it MUST be red, on those two cases)"
+echo "=== the smoke test on the reverted controls (it MUST be red on the pinned cases)"
 bash "${HERE}/control_smoke_test.sh" > "${WORK}/after.log" 2>&1
 rc=$?
 cat "${WORK}/after.log"
@@ -61,11 +69,12 @@ fi
 missed=0
 grep -q "NOT OK   unrelated failure with a non-empty selection" "${WORK}/after.log" || missed=1
 grep -q "NOT OK   red without the transport-resolution message" "${WORK}/after.log" || missed=1
+grep -qF "NOT OK missing-fatal: control must report FAILED for its own reason" "${WORK}/after.log" || missed=1
 if [ "${missed}" -ne 0 ]; then
   echo
-  echo "RED-CHECK FAILED: the smoke test went red, but not on the two cases the evidence check exists for."
+  echo "RED-CHECK FAILED: the smoke test went red, but not on the unrelated split, unrelated retrace and missing private-Fatal cases."
   exit 1
 fi
 
 echo
-echo "P5_T1_CONTROL_SMOKE_REDCHECK_OK - removing the evidence check reds exactly the two cases that pin it"
+echo "P5_T1_CONTROL_SMOKE_REDCHECK_OK - removing the evidence checks reds the unrelated split, unrelated retrace and missing private-Fatal cases"

scripts/ci/split_negative_controls.sh

@@ -42,8 +42,7 @@
 set -u
 
 if [ "${1:-}" = "--self-test" ]; then
-  bash "$(dirname "$0")/control_smoke_test.sh" &&
+  bash "$(dirname "$0")/control_smoke_test.sh"
-    bash "$(dirname "$0")/testdata/split_private_log_smoke.sh"
   exit $?
 fi
 
@@ -65,7 +64,8 @@ python3 "${log_helper}" check "${CTEST}" "$PWD" || exit 1
 # runtime fact inside each test process (MG_Config::Transport, ClientSession::Active(),
 # ImplementedVerbCount(), read by Harness/SplitRuntimePeek), so the only honest way to ask it from a
 # shell is to look at what the entries DID.
-"${CTEST}" -L integration-split -j 4 --no-tests=error --output-junit "${junit}"
+# The metadata ownership test shares the label but cannot arm runtime controls.
+"${CTEST}" -L integration-split -R '^DirectGLES\.Split\.' -j 4 --no-tests=error --output-junit "${junit}"
 baseline_rc=$?
 
 if [ ! -f "${junit}" ]; then
@@ -136,7 +136,9 @@ run_control() {
   echo "${name} turned ${matched} selected entries red, and the red carries the scenario's own diagnostic, as it must"
 }
 
-# E1: c1 ClientSession::Post emits MGLOG_F Fatal{BarrierViolation, "<slot>"}.
+# E1: c1 ClientSession::EmitAndWait emits MGLOG_F Fatal{BarrierViolation, "<slot>"}.
+# This asserts an observed overlap with the applier, which is timing-dependent.
+# Without that Fatal in a fresh selected file E1 fails; pixel/status fallbacks do not count.
 # Keep the ID-53-approved SmallRing selection as well as the default lane.
 run_control "negative control E1 (MOBILEGL_IPC_VERB_BARRIER=0)" \
   'DirectGLES\.Split\.(SmallRing\.)?(Triangle|ClearThenReadPixels)' \

scripts/ci/testdata/split_private_log_smoke.sh

@@ -16,6 +16,9 @@ for mode in missing-fatal stdout-fatal stale-fatal evidence e3-unrelated; do
     [ "${rc}" = 0 ] && grep -q "negative control E3(a).*scenario's own diagnostic" "${WORK}/${mode}.out" || {
       cat "${WORK}/${mode}.out"; echo "NOT OK private-file Fatal must PASS"; exit 1;
     }
+    grep -qFx "private-log evidence: DirectGLES.Split.ClearThenReadPixelsScenario.ClearWithNoDrawIsVisibleToDefaultFramebufferReadPixels: ${WORK}/${mode}/entry.log" "${WORK}/${mode}.out" || {
+      cat "${WORK}/${mode}.out"; echo "NOT OK private-file evidence line must name the selected entry and path"; exit 1;
+    }
   else
     message='E1 FAILED: selected private logs lack expected Fatal'
     [ "${mode}" != e3-unrelated ] || message='FAILED: red lacks its persistent-map push diagnostic'