[Fix] (MG_Backend/DirectVulkan, ShaderTranspiler, MG_Test, TraceReplay): make iterationRP retrace pass on 64-lane Vulkan devices with subgroup-width emulation and format-aware readback

.github/scripts/fetch-trace-fixture-lfs.sh

@@ -1,10 +1,6 @@
 #!/usr/bin/env bash
 set -euo pipefail
 
-script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-# shellcheck source=trace-fixture-lib.sh
-. "${script_dir}/trace-fixture-lib.sh"
-
 if [ "$#" -lt 1 ] || [ "$#" -gt 2 ]; then
   echo "usage: $0 <trace-case> [fixture-dir]" >&2
   exit 2
@@ -13,23 +9,7 @@ fi
 case_name="$1"
 fixture_dir="${2:-tools/trace_replay/fixtures}"
 python_bin="${PYTHON:-python3}"
-# Fixture mirrors, tried in order before falling back to Git LFS. Override the
-# whole list with MOBILEGL_TRACE_FIXTURE_MIRROR_BASES (whitespace separated);
-# MOBILEGL_TRACE_FIXTURE_MIRROR_BASE still works and is tried first.
-default_mirror_bases=(
-  "https://git.hit.moe/swung0x48/MobileGL/media/branch/dev/tools/trace_replay/fixtures"
-  "https://repo.miawa.cn/mgl/tools/trace_replay/fixtures"
-)
-if [ -n "${MOBILEGL_TRACE_FIXTURE_MIRROR_BASES:-}" ]; then
-  read -r -a mirror_bases <<< "${MOBILEGL_TRACE_FIXTURE_MIRROR_BASES}"
-else
-  mirror_bases=("${default_mirror_bases[@]}")
-fi
-if [ -n "${MOBILEGL_TRACE_FIXTURE_MIRROR_BASE:-}" ]; then
-  mirror_bases=("${MOBILEGL_TRACE_FIXTURE_MIRROR_BASE}" "${mirror_bases[@]}")
-fi
-# Optional bearer token for mirrors that require authentication (private Gitea).
-mirror_token="${MOBILEGL_TRACE_FIXTURE_MIRROR_TOKEN:-}"
+mirror_base="${MOBILEGL_TRACE_FIXTURE_MIRROR_BASE:-https://repo.miawa.cn/mgl/tools/trace_replay/fixtures}"
 download_attempts="${MOBILEGL_TRACE_FIXTURE_DOWNLOAD_ATTEMPTS:-5}"
 retry_delay="${MOBILEGL_TRACE_FIXTURE_RETRY_DELAY:-2}"
 
@@ -50,8 +30,7 @@ fixture_list="$("${python_bin}" tools/trace_replay/trace_cases.py \
   --format fixture-files \
   --case "${case_name}" \
   --fixture-root "${fixture_dir}")"
-# Strip CR so the script also works when python emits CRLF (Git Bash on Windows).
-mapfile -t files < <(printf '%s\n' "${fixture_list}" | tr -d '\r')
+mapfile -t files <<< "${fixture_list}"
 
 include="$(IFS=,; echo "${files[*]}")"
 if [ "${case_name}" = "OpenRA" ]; then
@@ -66,6 +45,57 @@ if [ "${case_name}" = "OpenRA" ]; then
   exit 0
 fi
 
+get_lfs_metadata() {
+  local file="$1"
+  local pointer
+  local expected_oid
+  local expected_size
+
+  if ! pointer="$(git show "HEAD:${file}" 2>/dev/null)"; then
+    echo "failed to read tracked fixture metadata: ${file}" >&2
+    return 1
+  fi
+  if ! grep -q '^version https://git-lfs.github.com/spec/v1$' <<< "${pointer}"; then
+    echo "tracked fixture is not a Git LFS pointer: ${file}" >&2
+    return 1
+  fi
+
+  expected_oid="$(awk '$1 == "oid" && $2 ~ /^sha256:/ { sub(/^sha256:/, "", $2); print $2 }' <<< "${pointer}")"
+  expected_size="$(awk '$1 == "size" { print $2 }' <<< "${pointer}")"
+  if ! [[ "${expected_oid}" =~ ^[0-9a-f]{64}$ ]] || ! [[ "${expected_size}" =~ ^[0-9]+$ ]]; then
+    echo "invalid Git LFS pointer metadata: ${file}" >&2
+    return 1
+  fi
+
+  printf '%s %s\n' "${expected_oid}" "${expected_size}"
+}
+
+verify_fixture_file() {
+  local downloaded_file="$1"
+  local display_name="$2"
+  local expected_oid="$3"
+  local expected_size="$4"
+  local actual_oid
+  local actual_size
+
+  if [ ! -f "${downloaded_file}" ]; then
+    echo "fixture file is missing: ${display_name}" >&2
+    return 1
+  fi
+
+  actual_size="$(wc -c < "${downloaded_file}" | tr -d '[:space:]')"
+  if [ "${actual_size}" != "${expected_size}" ]; then
+    echo "fixture size mismatch for ${display_name}: expected ${expected_size}, got ${actual_size}" >&2
+    return 1
+  fi
+
+  actual_oid="$(sha256sum "${downloaded_file}" | awk '{ print $1 }')"
+  if [ "${actual_oid}" != "${expected_oid}" ]; then
+    echo "fixture SHA-256 mismatch for ${display_name}: expected ${expected_oid}, got ${actual_oid}" >&2
+    return 1
+  fi
+}
+
 fetch_file_from_mirror() {
   local file="$1"
   local url="$2"
@@ -76,7 +106,6 @@ fetch_file_from_mirror() {
   local attempt
   local partial_size
   local curl_status
-  local curl_auth
 
   metadata="$(get_lfs_metadata "${file}")" || return 1
   read -r expected_oid expected_size <<< "${metadata}"
@@ -107,11 +136,7 @@ fetch_file_from_mirror() {
       echo "Starting mirror download for ${file} (attempt ${attempt}/${download_attempts})"
     fi
 
-    curl_auth=()
-    if [ -n "${mirror_token}" ]; then
-      curl_auth=(--header "Authorization: token ${mirror_token}")
-    fi
-    if curl -L --fail --show-error --continue-at - "${curl_auth[@]}" --output "${tmp_file}" "${url}"; then
+    if curl -L --fail --show-error --continue-at - --output "${tmp_file}" "${url}"; then
       if verify_fixture_file "${tmp_file}" "${file}" "${expected_oid}" "${expected_size}"; then
         mv "${tmp_file}" "${file}"
         return 0
@@ -154,42 +179,26 @@ fetch_file_from_mirror() {
   return 1
 }
 
-# Files no mirror could serve, even after retrying every mirror. Only these fall
-# back to Git LFS, so a mirror that served the rest of the case still spares
-# GitHub the bandwidth for those files.
-mirror_failures=()
-
 fetch_from_mirror() {
   mkdir -p "${fixture_dir}"
   for file in "${files[@]}"; do
     local name
     local url
-    local base
-    local fetched=0
     name="$(basename "${file}")"
-    for base in "${mirror_bases[@]}"; do
-      url="${base%/}/${name}"
-      echo "Fetching trace fixture from mirror: ${url}"
-      if fetch_file_from_mirror "${file}" "${url}"; then
-        fetched=1
-        break
-      fi
-      echo "Mirror did not serve ${name}; trying the next mirror" >&2
-    done
-    if [ "${fetched}" -ne 1 ]; then
-      mirror_failures+=("${file}")
+    url="${mirror_base%/}/${name}"
+    echo "Fetching trace fixture from mirror: ${url}"
+    if ! fetch_file_from_mirror "${file}" "${url}"; then
+      return 1
     fi
   done
-  [ "${#mirror_failures[@]}" -eq 0 ]
 }
 
 if fetch_from_mirror; then
   echo "Fetched trace fixture files for ${case_name} from mirror: ${include}"
 else
-  fallback_include="$(IFS=,; echo "${mirror_failures[*]}")"
-  echo "All mirrors failed for ${#mirror_failures[@]} of ${#files[@]} file(s) of ${case_name}; falling back to Git LFS: ${fallback_include}"
+  echo "Mirror fetch failed for ${case_name}; falling back to Git LFS: ${include}"
   git lfs install --local
-  git lfs pull --include="${fallback_include}" --exclude=""
+  git lfs pull --include="${include}" --exclude=""
 fi
 
 for file in "${files[@]}"; do

.github/scripts/trace-fixture-cache.sh

@@ -1,117 +0,0 @@
-#!/usr/bin/env bash
-# Cache-side helper for trace fixtures.
-#
-#   key <case> [fixture-dir]     derive the actions/cache key and path list
-#   verify <case> [fixture-dir]  check restored fixtures against their pointers
-#   reset <case> [fixture-dir]   drop restored fixtures, leaving the pointers
-#
-# The cache key is content-addressed on the Git LFS pointer oids tracked at
-# HEAD, which are readable from a plain checkout without smudging. Fixture
-# content therefore maps 1:1 onto a key: unchanged content hits, changed
-# content is a new key and thus a miss, and the download path handles it. The
-# key deliberately carries no restore-keys prefix in the workflow - a fixture
-# that does not match the pointer exactly must never be restored.
-set -euo pipefail
-
-script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-# shellcheck source=trace-fixture-lib.sh
-. "${script_dir}/trace-fixture-lib.sh"
-
-# Bump when the key derivation changes in a way that must invalidate old
-# entries; the content digest alone would not notice a format change.
-key_schema="v1"
-
-if [ "$#" -lt 2 ] || [ "$#" -gt 3 ]; then
-  echo "usage: $0 <key|verify|reset> <trace-case> [fixture-dir]" >&2
-  exit 2
-fi
-
-command_name="$1"
-case_name="$2"
-fixture_dir="${3:-tools/trace_replay/fixtures}"
-python_bin="${PYTHON:-python3}"
-
-if ! command -v "${python_bin}" >/dev/null 2>&1 && command -v python >/dev/null 2>&1; then
-  python_bin=python
-fi
-
-mapfile -t files < <(trace_fixture_files "${case_name}" "${fixture_dir}" "${python_bin}")
-if [ "${#files[@]}" -eq 0 ]; then
-  echo "no fixture files declared for trace case: ${case_name}" >&2
-  exit 1
-fi
-
-# Writes "name=value" to $GITHUB_OUTPUT when running under Actions, and to
-# stdout otherwise so the script stays runnable (and testable) off-CI.
-emit_output() {
-  local name="$1"
-  local value="$2"
-  if [ -n "${GITHUB_OUTPUT:-}" ]; then
-    if [[ "${value}" == *$'\n'* ]]; then
-      local delimiter="ghadelim_$(date +%s%N)_$$"
-      {
-        printf '%s<<%s\n' "${name}" "${delimiter}"
-        printf '%s\n' "${value}"
-        printf '%s\n' "${delimiter}"
-      } >> "${GITHUB_OUTPUT}"
-    else
-      printf '%s=%s\n' "${name}" "${value}" >> "${GITHUB_OUTPUT}"
-    fi
-  fi
-  printf '%s=%s\n' "${name}" "${value}"
-}
-
-sanitize_case() {
-  printf '%s' "$1" | sed 's/[^A-Za-z0-9._-]/_/g'
-}
-
-case "${command_name}" in
-  key)
-    manifest=""
-    for file in "${files[@]}"; do
-      # A case whose fixtures are committed directly rather than through Git LFS
-      # (OpenRA) has no pointer oid to key on, and nothing to download either.
-      # Report it as uncacheable so the workflow skips the cache entirely.
-      if ! metadata="$(get_lfs_metadata "${file}" 2>/dev/null)"; then
-        echo "trace case ${case_name} is not stored in Git LFS; skipping fixture cache" >&2
-        emit_output "cacheable" "false"
-        emit_output "key" ""
-        exit 0
-      fi
-      read -r expected_oid expected_size <<< "${metadata}"
-      manifest+="$(basename "${file}") ${expected_oid} ${expected_size}"$'\n'
-    done
-
-    digest="$(printf '%s' "${manifest}" | sha256sum | awk '{ print substr($1, 1, 16) }')"
-    safe_case="$(sanitize_case "${case_name}")"
-
-    emit_output "cacheable" "true"
-    emit_output "key" "trace-fixture-${key_schema}-${safe_case}-${digest}"
-    emit_output "paths" "$(printf '%s\n' "${files[@]}")"
-    ;;
-
-  verify)
-    for file in "${files[@]}"; do
-      metadata="$(get_lfs_metadata "${file}")"
-      read -r expected_oid expected_size <<< "${metadata}"
-      verify_fixture_file "${file}" "${file}" "${expected_oid}" "${expected_size}"
-    done
-    echo "Verified ${#files[@]} fixture file(s) for ${case_name} against the tracked Git LFS pointers."
-    ;;
-
-  reset)
-    # Put the working tree back to the pointer files a fresh checkout would
-    # have, so that a rejected cache entry falls through to exactly the same
-    # download path a cache miss takes.
-    for file in "${files[@]}"; do
-      rm -f "${file}" "${file}.tmp"
-    done
-    git checkout -- "${files[@]}"
-    echo "Reset ${#files[@]} fixture file(s) for ${case_name} to their tracked Git LFS pointers."
-    ;;
-
-  *)
-    echo "unknown command: ${command_name}" >&2
-    exit 2
-    ;;
-esac

.github/scripts/trace-fixture-lib.sh

@@ -1,73 +0,0 @@
-#!/usr/bin/env bash
-# Shared helpers for trace-fixture handling: reading the in-tree Git LFS pointer
-# metadata and verifying a fixture file against it. Sourced by
-# fetch-trace-fixture-lfs.sh (verify after download) and by
-# trace-fixture-cache.sh (cache key derivation and verify after cache restore),
-# so both paths agree on what a valid fixture is.
-
-# Reads the Git LFS pointer tracked at HEAD for a fixture path and prints
-# "<oid> <size>". Fails if the tracked blob is not a well-formed LFS pointer.
-get_lfs_metadata() {
-  local file="$1"
-  local pointer
-  local expected_oid
-  local expected_size
-
-  if ! pointer="$(git show "HEAD:${file}" 2>/dev/null)"; then
-    echo "failed to read tracked fixture metadata: ${file}" >&2
-    return 1
-  fi
-  if ! grep -q '^version https://git-lfs.github.com/spec/v1$' <<< "${pointer}"; then
-    echo "tracked fixture is not a Git LFS pointer: ${file}" >&2
-    return 1
-  fi
-
-  expected_oid="$(awk '$1 == "oid" && $2 ~ /^sha256:/ { sub(/^sha256:/, "", $2); print $2 }' <<< "${pointer}")"
-  expected_size="$(awk '$1 == "size" { print $2 }' <<< "${pointer}")"
-  if ! [[ "${expected_oid}" =~ ^[0-9a-f]{64}$ ]] || ! [[ "${expected_size}" =~ ^[0-9]+$ ]]; then
-    echo "invalid Git LFS pointer metadata: ${file}" >&2
-    return 1
-  fi
-
-  printf '%s %s\n' "${expected_oid}" "${expected_size}"
-}
-
-# Checks an on-disk fixture against the size and SHA-256 from its LFS pointer.
-verify_fixture_file() {
-  local downloaded_file="$1"
-  local display_name="$2"
-  local expected_oid="$3"
-  local expected_size="$4"
-  local actual_oid
-  local actual_size
-
-  if [ ! -f "${downloaded_file}" ]; then
-    echo "fixture file is missing: ${display_name}" >&2
-    return 1
-  fi
-
-  actual_size="$(wc -c < "${downloaded_file}" | tr -d '[:space:]')"
-  if [ "${actual_size}" != "${expected_size}" ]; then
-    echo "fixture size mismatch for ${display_name}: expected ${expected_size}, got ${actual_size}" >&2
-    return 1
-  fi
-
-  actual_oid="$(sha256sum "${downloaded_file}" | awk '{ print $1 }')"
-  if [ "${actual_oid}" != "${expected_oid}" ]; then
-    echo "fixture SHA-256 mismatch for ${display_name}: expected ${expected_oid}, got ${actual_oid}" >&2
-    return 1
-  fi
-}
-
-# Prints the fixture file paths of a trace case, one per line. Strips CR so the
-# result is usable when python emits CRLF (Git Bash on Windows).
-trace_fixture_files() {
-  local case_name="$1"
-  local fixture_dir="$2"
-  local python_bin="${3:-python3}"
-
-  "${python_bin}" tools/trace_replay/trace_cases.py \
-    --format fixture-files \
-    --case "${case_name}" \
-    --fixture-root "${fixture_dir}" | tr -d '\r'
-}

.github/scripts/validate-plugin-apks.sh

@@ -44,12 +44,12 @@ require 'key:MOBILEGL_BACKEND_TYPE' "$plugin_resource_text" 'V2 backend variable
 require 'defaultValue:DirectGLES' "$plugin_resource_text" 'V2 DirectGLES default'
 require 'DirectVulkan' "$plugin_resource_text" 'V2 DirectVulkan option'
 require 'key:MOBILEGL_DISABLE_TIMERQUERY' "$plugin_resource_text" 'V2 timer-query toggle'
-require 'key:MOBILEGL_MAGMA_DISABLE_SUBGROUP' "$plugin_resource_text" 'V2 Vulkan subgroup toggle'
+require 'key:MOBILEGL_DISABLE_SUBGROUP' "$plugin_resource_text" 'V2 Vulkan subgroup toggle'
 require 'key:MOBILEGL_MAGMA_R11G11B10F_FALLBACK' "$plugin_resource_text" 'V2 Magma format fallback toggle'
 require 'key:MOBILEGL_MAGMA_FRAMESINFLIGHT' "$plugin_resource_text" 'V2 Magma frames-in-flight setting'
-require 'key:MOBILEGL_ESPRYT_AVOID_SAMPLER_MIPMAP_MIN_FILTER' "$plugin_resource_text" 'V2 sampler workaround toggle'
+require 'key:MOBILEGL_AVOID_SAMPLER_MIPMAP_MIN_FILTER' "$plugin_resource_text" 'V2 sampler workaround toggle'
 require 'key:MOBILEGL_COHERENT_AS_FLUSH' "$plugin_resource_text" 'V2 coherent-as-flush toggle'
-require 'key:MOBILEGL_ESPRYT_USE_ANGLE' "$plugin_resource_text" 'V2 ANGLE toggle'
+require 'key:MOBILEGL_USE_ANGLE' "$plugin_resource_text" 'V2 ANGLE toggle'
 
 if [[ $(grep -Fc 'fclPlugin_V2' <<<"$plugin_manifest") -ne 1 ]]; then
   echo '::error::Plugin manifest must expose exactly one V2 descriptor' >&2

.github/workflows/apk.yml

@@ -6,30 +6,11 @@ on:
       - 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
-      - codex/fix-github-ci
-    # A docs-only push builds nothing this workflow tests (231 emulator legs per run). The Test
-    # workflow keeps running for docs: it hosts the doc citation lint.
-    paths-ignore:
-      - 'docs/**'
-      - '**/*.md'
   workflow_dispatch:
 
-# ONE LIVE RUN PER BRANCH, as in test.yml: a superseded push is cancelled rather than left queued
-# behind its successor; a manual dispatch gets a group of its own; dev queues rather than cancels.
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event_name == 'workflow_dispatch' && github.run_id || github.ref }}
-  cancel-in-progress: ${{ github.event_name == 'push' && github.ref != 'refs/heads/dev' }}
-
 jobs:
   build:
     runs-on: ubuntu-latest
-    permissions:
-      actions: write
-      contents: read
     env:
       CCACHE_BASEDIR: ${{ github.workspace }}
       CCACHE_COMPRESS: "true"
@@ -37,7 +18,6 @@ jobs:
       CCACHE_MAXSIZE: 4G
       CCACHE_NOHASHDIR: "true"
       MOBILEGL_CMAKE_COMPILER_LAUNCHER: ccache
-      MOBILEGL_CI_DISAGGREGATED: ${{ (github.ref_name == 'feat/disaggregated' || github.ref_name == 'codex/fix-github-ci') && 'ON' || 'OFF' }}
 
     steps:
       - name: Checkout repo
@@ -55,20 +35,18 @@ jobs:
           distribution: zulu
           java-version: '17'
 
-      - name: Android replay lifecycle regression
-        run: python3 tools/trace_replay/test_android_lifecycle.py
-
       - name: Setup Gradle
         uses: gradle/actions/setup-gradle@v6
         with:
           gradle-version: 8.10.2
 
       - name: Restore ccache
-        uses: actions/cache/restore@v5
+        uses: actions/cache@v5
         with:
           path: .ccache
-          key: ${{ runner.os }}-apk-${{ github.job }}-ccache-v1
+          key: ${{ runner.os }}-apk-${{ github.job }}-ccache-${{ github.ref_name }}-${{ github.run_id }}
           restore-keys: |
+            ${{ runner.os }}-apk-${{ github.job }}-ccache-${{ github.ref_name }}-
             ${{ runner.os }}-apk-${{ github.job }}-ccache-
 
       - name: Install ccache
@@ -81,8 +59,6 @@ jobs:
         uses: android-actions/setup-android@v4
         with:
           accept-android-sdk-licenses: false
-          packages: platform-tools
-          cmdline-tools-version: 13114758
 
       - name: Accept Android SDK licenses
         run: yes | sdkmanager --licenses >/dev/null
@@ -97,13 +73,7 @@ jobs:
         run: python update_glslang_sources.py
 
       - name: Build plugin APK
-        run: >-
-          gradle --no-daemon -p android-plugin :app:assemblePluginRelease
-          -Pmobilegl.apkSuffix="${GITHUB_SHA}" -Pmobilegl.logLevel=MOBILEGL_LOG_LEVEL_INFO
-          -Pmobilegl.buildDisaggregated="${MOBILEGL_CI_DISAGGREGATED}"
-          -Pmobilegl.buildDisaggregatedInproc="${MOBILEGL_CI_DISAGGREGATED}"
-          -Pmobilegl.pipePush="${MOBILEGL_CI_DISAGGREGATED}"
-          --parallel --max-workers "$(nproc)"
+        run: gradle --no-daemon -p android-plugin :app:assemblePluginRelease -Pmobilegl.apkSuffix="${GITHUB_SHA}" -Pmobilegl.logLevel=MOBILEGL_LOG_LEVEL_INFO --parallel --max-workers "$(nproc)"
         env:
           SIGNING_STORE_PASSWORD: ${{ secrets.SIGNING_STORE_PASSWORD }}
           SIGNING_KEY_ALIAS: ${{ secrets.SIGNING_KEY_ALIAS }}
@@ -145,14 +115,7 @@ jobs:
             66fdc867e552192d553d59095ea2e3cef4829de65c356f1fd826027b1905972e
 
       - name: Build retrace APK
-        run: >-
-          gradle --no-daemon -p android-plugin :app:assembleTraceRelease
-          -Pmobilegl.apkSuffix="${GITHUB_SHA}" -Pmobilegl.abis=all
-          -Pmobilegl.debuggableRelease=true -Pmobilegl.logLevel=MOBILEGL_LOG_LEVEL_INFO
-          -Pmobilegl.buildDisaggregated="${MOBILEGL_CI_DISAGGREGATED}"
-          -Pmobilegl.buildDisaggregatedInproc="${MOBILEGL_CI_DISAGGREGATED}"
-          -Pmobilegl.pipePush="${MOBILEGL_CI_DISAGGREGATED}"
-          --parallel --max-workers "$(nproc)"
+        run: gradle --no-daemon -p android-plugin :app:assembleTraceRelease -Pmobilegl.apkSuffix="${GITHUB_SHA}" -Pmobilegl.abis=all -Pmobilegl.debuggableRelease=true -Pmobilegl.logLevel=MOBILEGL_LOG_LEVEL_INFO --parallel --max-workers "$(nproc)"
         env:
           SIGNING_STORE_PASSWORD: ${{ secrets.SIGNING_STORE_PASSWORD }}
           SIGNING_KEY_ALIAS: ${{ secrets.SIGNING_KEY_ALIAS }}
@@ -162,28 +125,6 @@ jobs:
         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 a ~4 GB 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: ${{ runner.os }}-apk-${{ 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: ${{ runner.os }}-apk-${{ github.job }}-ccache-v1
-
       - name: Verify APK metadata and packaging
         run: |
           AAPT2="$(find "$ANDROID_HOME/build-tools" -name aapt2 -type f | sort -V | tail -n 1)"
@@ -234,8 +175,6 @@ jobs:
     name: trace case matrix
     runs-on: ubuntu-latest
     needs: build
-    env:
-      MOBILEGL_CI_DISAGGREGATED: ${{ (github.ref_name == 'feat/disaggregated' || github.ref_name == 'codex/fix-github-ci') && 'ON' || 'OFF' }}
     outputs:
       android: ${{ steps.trace-cases.outputs.android }}
       names: ${{ steps.trace-cases.outputs.names }}
@@ -246,12 +185,7 @@ jobs:
       - name: Load trace cases
         id: trace-cases
         run: |
-          python3 tools/trace_replay/trace_cases.py --self-test-transport-matrices
-          matrix_format=github-apk-matrix
-          if [ "${MOBILEGL_CI_DISAGGREGATED}" = "ON" ]; then
-            matrix_format=github-apk-transport-matrix
-          fi
-          echo "android=$(python3 tools/trace_replay/trace_cases.py --ci --format "${matrix_format}")" >> "$GITHUB_OUTPUT"
+          echo "android=$(python3 tools/trace_replay/trace_cases.py --ci --format github-apk)" >> "$GITHUB_OUTPUT"
           echo "names=$(python3 tools/trace_replay/trace_cases.py --ci --format names)" >> "$GITHUB_OUTPUT"
 
   trace-fixtures:
@@ -267,41 +201,9 @@ jobs:
       - 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')"
@@ -335,8 +237,6 @@ jobs:
         uses: android-actions/setup-android@v4
         with:
           accept-android-sdk-licenses: false
-          packages: platform-tools
-          cmdline-tools-version: 13114758
 
       - name: Accept Android SDK licenses
         run: yes | sdkmanager --licenses >/dev/null
@@ -364,7 +264,7 @@ jobs:
             --avd-name "${AVD_NAME}"
 
   retrace:
-    name: retrace (${{ matrix.backend.name }} / ${{ matrix.transport || 'monolith' }}, ${{ matrix.case.name }})
+    name: retrace (${{ matrix.backend.name }}, ${{ matrix.case.name }})
     runs-on: ubuntu-latest
     needs:
       - build
@@ -374,8 +274,6 @@ jobs:
     if: ${{ always() && needs.build.result == 'success' && needs.android-avd.result == 'success' && needs.trace-cases.result == 'success' }}
     timeout-minutes: 75
     env:
-      MOBILEGL_CI_TRANSPORT: ${{ matrix.transport || 'monolith' }}
-      MOBILEGL_CI_LANE: ${{ matrix.lane || 'monolith-control' }}
       AVD_NAME: mobilegl-ci
       ANDROID_AVD_HOME: ${{ github.workspace }}/.android/avd
       ANDROID_HOME: ${{ github.workspace }}/.android/sdk
@@ -383,9 +281,15 @@ jobs:
     strategy:
       fail-fast: false
       max-parallel: 4
-      matrix: ${{ fromJSON(needs.trace-cases.outputs.android) }}
+      matrix:
+        backend:
+          - name: DirectGLES
+            gpu: software
+          - name: DirectVulkan
+            gpu: lavapipe
+        case: ${{ fromJSON(needs.trace-cases.outputs.android) }}
     steps:
-      - name: Set swap space
+      - name: Set Swap Space
         uses: pierotofy/set-swap-space@v1.0
         with:
           swap-size-gb: 8
@@ -414,8 +318,6 @@ jobs:
         uses: android-actions/setup-android@v4
         with:
           accept-android-sdk-licenses: false
-          packages: platform-tools
-          cmdline-tools-version: 13114758
 
       - name: Accept Android SDK licenses
         run: yes | sdkmanager --licenses >/dev/null
@@ -454,7 +356,7 @@ jobs:
             --profile pixel_6 \
             --avd-name "${AVD_NAME}"
 
-      - name: Launch emulator
+      - name: Launch Emulator
         run: |
           sh android-plugin/run-avd-ci.sh start \
             --avd-name "${AVD_NAME}" \
@@ -465,49 +367,18 @@ jobs:
 
       - name: Retrace and validate
         env:
-          MOBILEGL_ESPRYT_USE_ANGLE: ${{ matrix.backend.name == 'DirectGLES' && '1' || '0' }}
+          MOBILEGL_USE_ANGLE: ${{ matrix.backend.name == 'DirectGLES' && '1' || '0' }}
           MOBILEGL_TRACE_ANGLE_VARIANT: ${{ matrix.case.name == 'minecraft-1.21.4-fabric-iris-bliss-in-world' && '90a62123d794' || 'ec889e6ea831' }}
           MOBILEGL_MAGMA_R11G11B10F_FALLBACK: ${{ matrix.backend.name == 'DirectVulkan' && '1' || '0' }}
-          MOBILEGL_MAGMA_FIX_ITERATIONRP_SUBGROUP_SCRATCH: ${{ matrix.backend.name == 'DirectVulkan' && matrix.case.name == 'minecraft-1.21.4-fabric-iris-iterationrp-in-world' && '1' || '0' }}
-          MOBILEGL_MAGMA_DERIVE_NUM_SUBGROUPS: ${{ matrix.backend.name == 'DirectVulkan' && matrix.case.name == 'minecraft-1.21.4-fabric-iris-iterationrp-in-world' && '1' || '0' }}
-          MOBILEGL_MAGMA_ITERATIONRP_FIX_BARRIER: ${{ matrix.backend.name == 'DirectVulkan' && matrix.case.name == 'minecraft-1.21.4-fabric-iris-iterationrp-in-world' && '1' || '0' }}
         run: |
           apk_file="android-retrace-apks/MobileGL-plugin-trace-release-${GITHUB_SHA}.apk"
           test -f "${apk_file}"
           extra_retrace_args=()
-          if [ "${MOBILEGL_CI_TRANSPORT}" = "inproc" ]; then
-            extra_retrace_args+=(
-              --env "MOBILEGL_TRANSPORT=inproc;MOBILEGL_IPC_ROLE_SPLIT_STATE=1;MOBILEGL_IPC_STRICT_ERRORS=1;MOBILEGL_IPC_RUN_AHEAD=1"
-              --require-inproc
-            )
-          elif [ "${MOBILEGL_CI_TRANSPORT}" = "spawn" ]; then
-            # THE SAME CLIENT KNOBS AS inproc, so the two acceptance lanes differ in exactly one
-            # thing: which PROCESS the server role runs in. They are scrubbed out of the CHILD's
-            # environment by the launcher and read by the client, which is where they belong.
-            #
-            # MOBILEGL_IPC_SERVER_PATH IS DELIBERATELY ABSENT. nativeLibraryDir carries an
-            # install-time hash, so nothing off the device can spell it; TraceReplayActivity
-            # resolves it from getApplicationInfo() when the env asks for spawn, and an explicit
-            # value would override that. --use-pbuffer is NOT optional here: until P12 a spawned
-            # server cannot be handed a window at all, because an ANativeWindow* is a pointer
-            # into the CLIENT's process and SetWindowHandle is refused on the way across with
-            # Fatal{UnmigratedSurface, "AndroidNativeWindow@P12"} (Rule H).
-            extra_retrace_args+=(
-              --env "MOBILEGL_TRANSPORT=spawn;MOBILEGL_IPC_ROLE_SPLIT_STATE=1;MOBILEGL_IPC_STRICT_ERRORS=1;MOBILEGL_IPC_RUN_AHEAD=1"
-              --use-pbuffer
-              --require-spawn
-            )
-          else
-            extra_retrace_args+=(--env "MOBILEGL_TRANSPORT=monolith")
-          fi
           # Bliss needs the newer signed ANGLE variant plus sampler mipmap
           # min-filter downgrading on ANGLE llvmpipe.
           if [ "${{ matrix.backend.name }}" = "DirectGLES" ] && [ "${{ matrix.case.name }}" = "minecraft-1.21.4-fabric-iris-bliss-in-world" ]; then
             extra_retrace_args+=(--avoid-angle-llvmpipe-sampler-mipmap-min-filter)
           fi
-          if [ "${{ matrix.backend.name }}" = "DirectGLES" ] && [ "${{ matrix.case.avoid_angle_llvmpipe_explicit_lod_bias || false }}" = "true" ]; then
-            extra_retrace_args+=(--avoid-angle-llvmpipe-explicit-lod-bias)
-          fi
           if [ "${{ matrix.case.coherent_as_flush || false }}" = "true" ]; then
             extra_retrace_args+=(--coherent-as-flush)
           fi
@@ -540,24 +411,6 @@ jobs:
           run_retrace || retrace_status=$?
           if [ "${retrace_status}" -eq 75 ]; then
             echo "::warning::Android emulator infrastructure failed; restarting it and retrying this retrace once."
-            # Surface-lost is retried rather than failed, so it would otherwise
-            # be invisible. Report it per job - a healthy run prints nothing and
-            # a rate spike shows up as a row per affected case.
-            reason_file="android-retrace-result/infrastructure-failure-reason.txt"
-            surface_lost_retries=0
-            if [ -f "${reason_file}" ]; then
-              surface_lost_retries="$(grep -c 'angle-surface-lost' "${reason_file}" || true)"
-            fi
-            if [ "${surface_lost_retries}" -gt 0 ]; then
-              echo "surface-lost retries: ${surface_lost_retries} (${{ matrix.backend.name }}, ${{ matrix.case.name }})" \
-                >> "${GITHUB_STEP_SUMMARY}"
-            fi
-            # The restart truncates EMULATOR_LOG, and the attempt that lost the
-            # emulator is the one worth reading - the retry usually only shows
-            # the wreckage. Keep the first attempt's log before it is clobbered.
-            if [ -f "${EMULATOR_LOG}" ]; then
-              cp "${EMULATOR_LOG}" "${EMULATOR_LOG}.first-attempt" || true
-            fi
             sh android-plugin/run-avd-ci.sh stop \
               --avd-name "${AVD_NAME}" \
               --emulator-log "${EMULATOR_LOG}" \
@@ -581,12 +434,6 @@ jobs:
           safe_case="$(printf '%s' '${{ matrix.case.name }}' | sed 's/[^A-Za-z0-9._-]/_/g')"
           result_dir="android-retrace-result/${safe_case}-${{ matrix.backend.name }}"
           mkdir -p "${result_dir}"
-          python3 - "${result_dir}/lane.json" <<'PY'
-          import json, os, sys
-          from pathlib import Path
-          Path(sys.argv[1]).write_text(json.dumps({"lane": os.environ["MOBILEGL_CI_LANE"],
-              "transport": os.environ["MOBILEGL_CI_TRANSPORT"]}, indent=2))
-          PY
           if [ -s "${{ matrix.case.golden }}" ]; then
             cp "${{ matrix.case.golden }}" "${result_dir}/${safe_case}-${{ matrix.backend.name }}-golden.png"
           fi
@@ -603,15 +450,8 @@ jobs:
           if [ -f "${EMULATOR_LOG}" ]; then
             cp "${EMULATOR_LOG}" android-retrace-result/diagnostics/emulator.log
           fi
-          if [ -f "${EMULATOR_LOG}.first-attempt" ]; then
-            cp "${EMULATOR_LOG}.first-attempt" android-retrace-result/diagnostics/emulator-first-attempt.log
-          fi
-          # A vanished emulator looks identical whether the host OOM killer took
-          # qemu or the renderer faulted. These two say which.
-          free -h > android-retrace-result/diagnostics/host-memory.txt 2>&1 || true
-          sudo dmesg -T 2>/dev/null | tail -300 > android-retrace-result/diagnostics/host-dmesg.txt || true
 
-      - name: Stop emulator
+      - name: Stop Emulator
         if: always()
         run: |
           sh android-plugin/run-avd-ci.sh stop \
@@ -623,7 +463,7 @@ jobs:
         if: always()
         uses: actions/upload-artifact@v7
         with:
-          name: MobileGL-android-retrace-result-${{ matrix.lane || 'monolith-control' }}-${{ matrix.transport || 'monolith' }}-${{ env.date_today }}-${{ github.sha }}-${{ matrix.backend.name }}-${{ matrix.case.name }}
+          name: MobileGL-android-retrace-result-${{ env.date_today }}-${{ github.sha }}-${{ matrix.backend.name }}-${{ matrix.case.name }}
           path: android-retrace-result/**
           if-no-files-found: warn
 
@@ -632,8 +472,6 @@ jobs:
     runs-on: ubuntu-latest
     needs: retrace
     if: always()
-    env:
-      MOBILEGL_CI_DISAGGREGATED: ${{ (github.ref_name == 'feat/disaggregated' || github.ref_name == 'codex/fix-github-ci') && 'ON' || 'OFF' }}
 
     steps:
       - name: Checkout repo
@@ -648,73 +486,25 @@ jobs:
         with:
           node-version: '22'
 
-      - name: Download Android monolith control results
+      - name: Download Android retrace results
         uses: actions/download-artifact@v8
         with:
-          pattern: MobileGL-android-retrace-result-monolith-control-monolith-*
-          path: retrace-artifacts/monolith-control
+          pattern: MobileGL-android-retrace-result-*
+          path: retrace-artifacts
 
-      - name: Download Android inproc acceptance results
-        if: env.MOBILEGL_CI_DISAGGREGATED == 'ON'
-        uses: actions/download-artifact@v8
-        with:
-          pattern: MobileGL-android-retrace-result-inproc-acceptance-inproc-*
-          path: retrace-artifacts/inproc-acceptance
-
-      - name: Download Android spawn acceptance results
-        if: env.MOBILEGL_CI_DISAGGREGATED == 'ON'
-        uses: actions/download-artifact@v8
-        with:
-          pattern: MobileGL-android-retrace-result-spawn-acceptance-spawn-*
-          path: retrace-artifacts/spawn-acceptance
-
-      - name: Render monolith control summary
+      - name: Render retrace summary
         run: |
           node tools/trace_replay/render_retrace_summary.mjs \
-            --input retrace-artifacts/monolith-control \
-            --output-dir android-retrace-summary/monolith-control \
-            --title "MobileGL Android monolith control" \
-            --group-label "Android Emulator / monolith control" \
-            --html mobilegl-android-monolith-control.html
+            --input retrace-artifacts \
+            --output-dir android-retrace-summary \
+            --title "MobileGL Android retrace overview" \
+            --group-label "Android Emulator" \
+            --html mobilegl-android-retrace-overview.html
 
-      - name: Render inproc acceptance summary
-        if: env.MOBILEGL_CI_DISAGGREGATED == 'ON'
-        run: |
-          node tools/trace_replay/render_retrace_summary.mjs \
-            --input retrace-artifacts/inproc-acceptance \
-            --output-dir android-retrace-summary/inproc-acceptance \
-            --title "MobileGL Android inproc acceptance" \
-            --group-label "Android Emulator / inproc acceptance" \
-            --html mobilegl-android-inproc-acceptance.html
-
-      - name: Render spawn acceptance summary
-        if: env.MOBILEGL_CI_DISAGGREGATED == 'ON'
-        run: |
-          node tools/trace_replay/render_retrace_summary.mjs             --input retrace-artifacts/spawn-acceptance             --output-dir android-retrace-summary/spawn-acceptance             --title "MobileGL Android spawn acceptance"             --group-label "Android Emulator / spawn acceptance"             --html mobilegl-android-spawn-acceptance.html
-
-      - name: Upload Android monolith control summary
+      - name: Upload Android retrace summary
         uses: actions/upload-artifact@v7
         with:
-          name: MobileGL-android-monolith-control-summary-${{ github.sha }}
-          path: android-retrace-summary/monolith-control/mobilegl-android-monolith-control.html
-          archive: false
-          if-no-files-found: error
-
-      - name: Upload Android inproc acceptance summary
-        if: env.MOBILEGL_CI_DISAGGREGATED == 'ON'
-        uses: actions/upload-artifact@v7
-        with:
-          name: MobileGL-android-inproc-acceptance-summary-${{ github.sha }}
-          path: android-retrace-summary/inproc-acceptance/mobilegl-android-inproc-acceptance.html
-          archive: false
-          if-no-files-found: error
-
-      - name: Upload Android spawn acceptance summary
-        if: env.MOBILEGL_CI_DISAGGREGATED == 'ON'
-        uses: actions/upload-artifact@v7
-        with:
-          name: MobileGL-android-spawn-acceptance-summary-${{ github.sha }}
-          path: android-retrace-summary/spawn-acceptance/mobilegl-android-spawn-acceptance.html
+          path: android-retrace-summary/mobilegl-android-retrace-overview.html
           archive: false
           if-no-files-found: error
 
@@ -730,61 +520,41 @@ jobs:
         env:
           GH_TOKEN: ${{ github.token }}
         run: |
-          # Fail before deletion if either paginated inventory cannot be read.
-          gh api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/jobs?per_page=100" \
-            --jq '.jobs[] | select(.name | startswith("retrace (")) | select(.conclusion == "failure" or .conclusion == "cancelled" or .conclusion == "timed_out" or .conclusion == "action_required") | .name' \
-            > "${RUNNER_TEMP}/cleanup-jobs.txt"
-          gh api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/artifacts?per_page=100" \
-            --jq '.artifacts[] | select(.name | startswith("MobileGL-trace-fixture-") or startswith("MobileGL-android-retrace-result-") or startswith("trace-fixture-") or startswith("retrace-result-")) | [.id, .name] | @tsv' \
-            > "${RUNNER_TEMP}/cleanup-artifacts.txt"
           declare -A failed_cases=()
           while IFS= read -r job_name; do
             case_name="${job_name#retrace (*, }"
             case_name="${case_name%)}"
             failed_cases["${case_name}"]=1
-          done < "${RUNNER_TEMP}/cleanup-jobs.txt"
+          done < <(
+            gh api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/jobs?per_page=100" \
+              --jq '.jobs[] | select(.name | startswith("retrace (")) | select(.conclusion == "failure" or .conclusion == "cancelled" or .conclusion == "timed_out" or .conclusion == "action_required") | .name'
+          )
 
           if ((${#failed_cases[@]})); then
-            echo "Retaining fixtures and results for failed retrace case(s):"
+            echo "Retaining fixtures for failed retrace case(s):"
             printf '  %s\n' "${!failed_cases[@]}"
           else
-            echo "All retrace jobs succeeded; nothing needs to be retained."
+            echo "All retrace jobs succeeded; no fixtures need to be retained."
           fi
 
           deleted=0
           retained=0
           while IFS=$'\t' read -r artifact_id artifact_name; do
-            keep=0
             if [[ "${artifact_name}" == MobileGL-trace-fixture-* ]]; then
               case_name="${artifact_name#MobileGL-trace-fixture-}"
               if [[ -v "failed_cases[${case_name}]" ]]; then
-                keep=1
+                echo "Retaining ${artifact_name} (${artifact_id}) for failed retrace."
+                ((retained += 1))
+                continue
               fi
-            elif [[ "${artifact_name}" == MobileGL-android-retrace-result-* ]]; then
-              # The result artifact carries mobilegl.log, retrace.log, logcat,
-              # the emulator log and the actual/diff images - the only record of
-              # why a retrace failed. Its name ends in -<backend>-<case>, so a
-              # suffix match on the case name keeps both backends' results for a
-              # case that failed on either of them, which is what a comparison
-              # needs. The match is anchored at the end, so a case name that is a
-              # prefix of a longer one does not retain the longer one's results.
-              for case_name in "${!failed_cases[@]}"; do
-                if [[ "${artifact_name}" == *-"${case_name}" ]]; then
-                  keep=1
-                  break
-                fi
-              done
-            fi
-
-            if ((keep)); then
-              echo "Retaining ${artifact_name} (${artifact_id}) for failed retrace."
-              ((retained += 1))
-              continue
             fi
 
             echo "Deleting ${artifact_name} (${artifact_id})"
             gh api --method DELETE "repos/${GITHUB_REPOSITORY}/actions/artifacts/${artifact_id}"
             ((deleted += 1))
-          done < "${RUNNER_TEMP}/cleanup-artifacts.txt"
+          done < <(
+            gh api --paginate "repos/${GITHUB_REPOSITORY}/actions/runs/${GITHUB_RUN_ID}/artifacts?per_page=100" \
+              --jq '.artifacts[] | select(.name | startswith("MobileGL-trace-fixture-") or startswith("MobileGL-android-retrace-result-") or startswith("trace-fixture-") or startswith("retrace-result-")) | [.id, .name] | @tsv'
+          )
 
           echo "Deleted ${deleted} intermediate Android artifact(s); retained ${retained} failed-retrace fixture(s)."

.gitignore

@@ -25,6 +25,3 @@ MobileGL/MG*/cmake-build*
 /android-plugin/app/src/trace/jniLibs
 /android-plugin/local.properties
 tools/trace_replay/work/
-__pycache__/
-*.py[cod]
-/.gradle

.gitmodules

@@ -7,6 +7,9 @@
 [submodule "3rdparty/SPIRV-Cross"]
 	path = 3rdparty/SPIRV-Cross
 	url = https://github.com/KhronosGroup/SPIRV-Cross.git
+[submodule "include/FastSTL"]
+	path = include/FastSTL
+	url = https://github.com/MobileGL-Dev/FastSTL.git
 [submodule "3rdparty/tracy"]
 	path = 3rdparty/tracy
 	url = https://github.com/wolfpld/tracy.git
@@ -28,12 +31,3 @@
 [submodule "3rdparty/apitrace"]
 	path = 3rdparty/apitrace
 	url = https://github.com/MobileGL-Dev/apitrace.git
-[submodule "3rdparty/asio"]
-	path = 3rdparty/asio
-	url = https://github.com/chriskohlhoff/asio.git
-[submodule "include/ska"]
-	path = include/ska
-	url = https://github.com/MobileGL-Dev/flat_hash_map.git
-[submodule "3rdparty/flatbuffers"]
-	path = 3rdparty/flatbuffers
-	url = https://github.com/google/flatbuffers.git

CMakeLists.txt

@@ -4,129 +4,20 @@ project("MobileGL")
 
 option(MOBILEGL_BUILD_TEST        "Build MobileGL tests"                             ON )
 option(MOBILEGL_BUILD_BENCHMARK   "Build MobileGL benchmarks"                        ON )
-# Headless end-to-end GPU scenarios (MobileGL/MG_IntegrationTest). They need a
-# real GPU/ICD to do anything, so they are off by default for CI; every scenario
-# skips cleanly where there is none. Registered under the `integration-gpu`
-# ctest label so a run can select or exclude them.
-option(MOBILEGL_BUILD_INTEGRATION_TEST "Build MobileGL headless GPU integration tests" OFF)
 option(MOBILEGL_FORCE_RELEASE_OPT "Enable Release optimization flags in Debug build" ON )
 option(MOBILEGL_ENABLE_TRACY      "Enable tracy for profiling"                       OFF)
 option(MOBILEGL_BUILD_TRACE_REPLAY "Build desktop apitrace replay runner"            OFF)
 option(MOBILEGL_TRACE_ANGLE_VARIANTS "Enable signed trace-APK ANGLE variant loading" OFF)
 option(MOBILEGL_IOS               "Build MobileGL for iOS instead of macOS when APPLE is set" OFF)
-# The disaggregated (two-process) shape. OFF is the shipping default and OFF
-# must stay byte-comparable to a tree without MG_Remote at all: nothing under
-# MobileGL/MG_Remote/ is compiled, no include path is added, and no library is
-# linked, so `nm --defined-only libMobileGL.so | grep -i MG_Remote` is empty.
-# That emptiness is one of the two byte-level equalities the plan's validation
-# gates keep (section 10.3).
-option(MOBILEGL_BUILD_DISAGGREGATED "Build the MG_Remote transport layer (two-process shape)" OFF)
-# The CI / debugging shape (ARCHITECTURE.md:581): both roles in ONE process, talking over the
-# same SEG_CMD ring and the same G3 codec a spawned server would use. It IMPLIES
-# MOBILEGL_BUILD_DISAGGREGATED (below) and additionally admits the role-isolation shims that
-# only make sense when the two roles share an address space. It is a SUPERSET, never a
-# substitute: MOBILEGL_TRANSPORT=inproc is what selects the shape at run time, and this option
-# only decides whether the shims are compiled in.
-option(MOBILEGL_BUILD_DISAGGREGATED_INPROC "Compile the in-process (one-process, two-role) split shims; implies MOBILEGL_BUILD_DISAGGREGATED" OFF)
-option(MOBILEGL_BUILD_SERVER_SPIKE "Build the P0 spike-A MobileGLServer delivery-chain executable (Android only)" OFF)
-# The PipeInputs strangler (ARCHITECTURE.md 9.2). OFF is the pull build and must stay
-# byte-identical to a tree without either option: MGB_CTX is the live GLContext, no
-# MGPipe/PipeInputs source is compiled, every MGP_FILL is ((void)0).
-option(MOBILEGL_PIPE_PUSH "Backends read frontend state through the MGPipe PipeInputs block instead of MG_State::pGLContext (ARCHITECTURE.md 9.2 phase A)" OFF)
-option(MOBILEGL_PIPE_VERIFY "Compile SnapshotFromGLContext() and the G4 per-verb shadow comparator; implies MOBILEGL_PIPE_PUSH; never shipped" OFF)
-# Track H's old-versus-new arm (ARCHITECTURE.md 9.6). With a MOBILEGL_PIPE_PUSH bit clear
-# the backend would still run the RE-KEYED memo code, so the bitmask alone stops being a
-# valid A/B the moment a handle wave lands: this option compiles the pre-handle arm - the
-# registries, OwnerEquals, the TwinLookupMemos, g_fbSlotCache, ComputePipelineStateHash,
-# the address-keyed VaoDrawMemo - beside it, behind the same PipeInputs interface. ON for
-# the whole migration window; it retires with the pull path itself at P13.
-option(MOBILEGL_PIPE_LEGACY_MEMOS "Compile the pre-handle memo arm beside the {slot, gen} arm so Track H has a real A/B (ARCHITECTURE.md 9.6)" ON)
 set(MOBILEGL_LOG_ACTIVE_LEVEL "MOBILEGL_LOG_LEVEL_INFO" CACHE STRING "MobileGL active log level macro")
 set(MOBILEGL_VULKAN_LIBRARY "" CACHE FILEPATH "Vulkan loader/MoltenVK library to link for iOS builds")
 
 if (ANDROID)
     set(MOBILEGL_BUILD_TEST       OFF CACHE BOOL "Build MobileGL tests"      FORCE)
     set(MOBILEGL_BUILD_BENCHMARK  OFF CACHE BOOL "Build MobileGL benchmarks" FORCE)
-
-    # ------- Android API level policy: minimum 26, decided here and only here -------
-    # MobileGL ships against API 26: the codebase must not use any API introduced
-    # after 26. That usage constraint is enforced where it is real - the shipping
-    # gradle build compiles at minSdk 26, where a newer API is simply undeclared
-    # and fails to compile. Configuring at a HIGHER level is therefore allowed
-    # (nothing in the tree may rely on it), but a LOWER level would change the
-    # libc contract underneath the shipped library and is refused.
-    #
-    # This has to live at configure time because the level cannot be corrected
-    # from a source header. A `#define __ANDROID_API__ 26` in a common header
-    # only rewrites the macro for the bionic headers that happen to be included
-    # after it; any libc++ header pulled in earlier has already latched its
-    # feature macros at the real configure-time level. libc++ and bionic then
-    # disagree about which symbols exist - libc++ calls e.g.
-    # pthread_cond_clockwait while bionic, re-read at the lowered level, has
-    # hidden its declaration. MobileGL/Defines.h carried exactly that pin from
-    # the first commit until it was removed; this guard is what replaces it.
-    #
-    # Read the level back from the compiler target triple first. Its trailing
-    # number (aarch64-none-linux-android26) is precisely what clang turns into
-    # __ANDROID_API__, so it cannot disagree with the compile itself, and it is
-    # already past every NDK normalisation step - codename aliases, "latest",
-    # and per-ABI minimum pull-ups. ANDROID_PLATFORM_LEVEL is the fallback for
-    # generators/languages where the triple variable is not populated.
-    #
-    # Note CMAKE_SYSTEM_VERSION is deliberately NOT consulted: it holds the API
-    # level only under the NDK's newer toolchain path, and is a meaningless 1
-    # when ANDROID_USE_LEGACY_TOOLCHAIN_FILE is on (which is what AGP has been
-    # defaulting to). Reading it would fail every legacy-mode build.
-    set(MOBILEGL_ANDROID_API_LEVEL 26)
-
-    set(_mobilegl_android_api "")
-    foreach (_mobilegl_api_triple "${CMAKE_CXX_COMPILER_TARGET}"
-                                  "${CMAKE_C_COMPILER_TARGET}")
-        if (NOT _mobilegl_android_api AND
-            _mobilegl_api_triple MATCHES "-android([0-9]+)$")
-            set(_mobilegl_android_api "${CMAKE_MATCH_1}")
-        endif()
-    endforeach()
-
-    foreach (_mobilegl_api_var ANDROID_PLATFORM_LEVEL ANDROID_NATIVE_API_LEVEL
-                               ANDROID_PLATFORM)
-        if (NOT _mobilegl_android_api AND ${_mobilegl_api_var})
-            string(REGEX REPLACE "^android-" ""
-                   _mobilegl_android_api "${${_mobilegl_api_var}}")
-        endif()
-    endforeach()
-
-    if (NOT _mobilegl_android_api MATCHES "^[0-9]+$")
-        message(FATAL_ERROR
-            "MobileGL: could not determine the Android API level (got "
-            "\"${_mobilegl_android_api}\"). Configure with the NDK toolchain "
-            "file and -DANDROID_PLATFORM=android-${MOBILEGL_ANDROID_API_LEVEL}.")
-    elseif (_mobilegl_android_api LESS MOBILEGL_ANDROID_API_LEVEL)
-        message(FATAL_ERROR
-            "MobileGL requires at least Android API ${MOBILEGL_ANDROID_API_LEVEL}, "
-            "but this build resolved to API ${_mobilegl_android_api}.\n"
-            "Configure with -DANDROID_PLATFORM=android-${MOBILEGL_ANDROID_API_LEVEL} "
-            "(gradle builds get this from minSdk ${MOBILEGL_ANDROID_API_LEVEL}, so "
-            "check that minSdk instead of adding an override).")
-    elseif (_mobilegl_android_api GREATER MOBILEGL_ANDROID_API_LEVEL)
-        message(STATUS
-            "MobileGL: configuring at Android API ${_mobilegl_android_api} "
-            "(> shipping minimum ${MOBILEGL_ANDROID_API_LEVEL}). Allowed, but the "
-            "tree must not use post-${MOBILEGL_ANDROID_API_LEVEL} APIs - the "
-            "minSdk-${MOBILEGL_ANDROID_API_LEVEL} gradle build is the enforcing "
-            "compile.")
-    endif()
-
-    message(STATUS "MobileGL: Android API level ${_mobilegl_android_api}")
-
-    unset(_mobilegl_android_api)
-    unset(_mobilegl_api_var)
-    unset(_mobilegl_api_triple)
 endif()
 
-option(MOBILEGL_ENABLE_LTO "Build with ThinLTO/IPO" OFF)
-
-if ((NOT CMAKE_BUILD_TYPE STREQUAL "Debug" OR MOBILEGL_FORCE_RELEASE_OPT) AND MOBILEGL_ENABLE_LTO)
+if (NOT CMAKE_BUILD_TYPE STREQUAL "Debug" OR MOBILEGL_FORCE_RELEASE_OPT)
     # Check if ThinLTO or LTO is suppported
     include(CheckIPOSupported)
     include(CheckCCompilerFlag)
@@ -185,61 +76,15 @@ if (MSVC)
 endif()
 
 # Generate MGGitHash.h
-#
-# RESULT_VARIABLE, WHICH THIS CALL DID NOT HAVE (CONTRACT-P6 4.2). Without it a failed
-# `git rev-parse` yields "" and nothing says so. Verified live: building this worktree from WSL
-# produces an EMPTY hash, because the worktree's `.git` is a file holding a WINDOWS path that
-# WSL's git cannot resolve - so two builds from different commits got IDENTICAL ABI
-# fingerprints and the stamp silently stopped doing its documented job.
 execute_process(
     COMMAND git rev-parse HEAD
     WORKING_DIRECTORY ${CMAKE_SOURCE_DIR}
     OUTPUT_VARIABLE GIT_COMMIT_HASH_FULL
     OUTPUT_STRIP_TRAILING_WHITESPACE
-    RESULT_VARIABLE MOBILEGL_GIT_STAMP_RESULT
-    ERROR_QUIET
 )
 
 string(SUBSTRING "${GIT_COMMIT_HASH_FULL}" 0 7 GIT_COMMIT_HASH_SHORT)
 
-# --- the BUILD STAMP, and why it is a second pair rather than a fix to the first -------------
-#
-# GIT_COMMIT_HASH_SHORT MAY NOT MOVE. It is baked into glGetString(GL_VERSION)
-# (MG_Impl/GLImpl/Getter/GL_Getter.cpp), so redefining it changes an APPLICATION-VISIBLE GL
-# string and the pull build's .rodata - a behaviour leak and a G1 break at once. The handshake
-# gets its own pair instead, consumed only by the ABI fingerprint, which no pull build compiles.
-#
-# PRESENT IS A FIRST-CLASS INPUT, not the emptiness of VALUE. "this build has no stamp" and
-# "this build's stamp is the empty string" are different claims, and a fingerprint that could
-# not tell them apart is how two unrelated builds agreed in the first place.
-#
-# -DMOBILEGL_BUILD_STAMP=<anything> (or the environment variable) overrides, because a tree git
-# cannot read is not always a tree whose commit is unknown - CI has ${GITHUB_SHA} in hand.
-set(MOBILEGL_BUILD_STAMP "" CACHE STRING "Explicit ABI-fingerprint build stamp when git cannot be read")
-set(MOBILEGL_BUILD_STAMP_VALUE "")
-if(NOT "${MOBILEGL_BUILD_STAMP}" STREQUAL "")
-    set(MOBILEGL_BUILD_STAMP_VALUE "${MOBILEGL_BUILD_STAMP}")
-elseif(NOT "$ENV{MOBILEGL_BUILD_STAMP}" STREQUAL "")
-    set(MOBILEGL_BUILD_STAMP_VALUE "$ENV{MOBILEGL_BUILD_STAMP}")
-elseif(MOBILEGL_GIT_STAMP_RESULT EQUAL 0 AND NOT "${GIT_COMMIT_HASH_FULL}" STREQUAL "")
-    set(MOBILEGL_BUILD_STAMP_VALUE "${GIT_COMMIT_HASH_FULL}")
-endif()
-
-if("${MOBILEGL_BUILD_STAMP_VALUE}" STREQUAL "")
-    set(MOBILEGL_BUILD_STAMP_PRESENT 0)
-    # A WARNING AND NOT A FATAL: a build with no stamp is still a usable build, it just cannot
-    # prove that a peer was built from the same tree. Saying so once at configure time is the
-    # difference between a known limitation and the silent one 4.2 found.
-    message(WARNING
-        "MobileGL: no build stamp. `git rev-parse HEAD` failed (result "
-        "'${MOBILEGL_GIT_STAMP_RESULT}') and MOBILEGL_BUILD_STAMP was not set, so the ABI "
-        "fingerprint cannot distinguish two builds of the same sizes from different commits - "
-        "which is exactly what a stale MOBILEGL_IPC_SERVER_PATH looks like. Pass "
-        "-DMOBILEGL_BUILD_STAMP=<commit> to restore it.")
-else()
-    set(MOBILEGL_BUILD_STAMP_PRESENT 1)
-endif()
-
 configure_file(
     ${CMAKE_SOURCE_DIR}/MobileGL/MG_Util/Miscellany/MGGitHash.h.in
     ${CMAKE_BINARY_DIR}/generated/MGGitHash.h
@@ -255,7 +100,6 @@ set(ENABLE_SPVREMAPPER         OFF CACHE BOOL "Enable SPVRemapper" FORCE)
 set(ENABLE_OPT                 ON  CACHE BOOL "Enable SPIRV-Tools opt usage in glslang" FORCE)
 set(BUILD_EXTERNAL             ON  CACHE BOOL "Build external deps in External/" FORCE)
 set(ENABLE_GLSLANG_INSTALL     OFF CACHE BOOL "Install glslang targets" FORCE)
-set(SPIRV_SKIP_EXECUTABLES     ON  CACHE BOOL "Skip building SPIRV-Tools executables" FORCE)
 
 set(SPIRV_CROSS_C_API          ON  CACHE BOOL "Enable C API" FORCE)
 set(SPIRV_CROSS_ENABLE_GLSL    ON  CACHE BOOL "Enable GLSL backend" FORCE)
@@ -303,16 +147,11 @@ set(SOURCE_FILES
 
     MobileGL/MG_Util/Debug/Log.cpp
 
-    MobileGL/MG_Util/Async/JobNode.cpp
-    MobileGL/MG_Util/Async/ShaderCompilePool.cpp
-
     MobileGL/MG_Util/Math/VectorTypes.cpp
     MobileGL/MG_Util/Metrics/TextureMetrics.cpp
 
     MobileGL/MG_Util/Metrics/BufferMetrics.cpp
 
-    MobileGL/MG_Util/Metrics/PipeStats.cpp
-
     MobileGL/MG_Util/Converters/GLToStr/GLEnumConverter.cpp
     MobileGL/MG_Util/Converters/EGLToStr/EGLEnumConverter.cpp
     MobileGL/MG_Util/Converters/MGToStr/DataTypeConverter.cpp
@@ -341,63 +180,27 @@ set(SOURCE_FILES
 
     MobileGL/MG_Util/Classifiers/TextureEnumClassifier.cpp
 
-    MobileGL/MG_Util/ShaderTranspiler/CompileEnv.cpp
     MobileGL/MG_Util/ShaderTranspiler/ShaderCompiler.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpvcSession.cpp
     MobileGL/MG_Util/ShaderTranspiler/ShaderSourceProcessor.cpp
-    MobileGL/MG_Util/ShaderTranspiler/TranslationCache.cpp
     MobileGL/MG_Util/ShaderTranspiler/glslang/TMglGlslIoResolver.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FlattenInterfaceStructPass.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/EliminateFloatEqualsZeroPass.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/RenameSamplerFunctionParameterPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/RenameBuiltinShadowingFunctionsPass.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DecomposeWorkgroupVec3Pass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DecoratePositionInvariantPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DemoteFloat64Pass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FlattenFloat64StorageBlockPass.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LowerDrawParametersPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LowerViewportIndexPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/PackDoubleVertexInputsPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FlattenXfbInterfaceBlocksPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/UniquifyIoBlockNamesPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/StripIoBlockLocationsPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/SplitArrayVertexInputsPass.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/RebaseInstanceIndexPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/ZeroBaseVertexPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DeriveNumSubgroupsPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FixIterationRPBarrierPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FixIterationRPSubgroupScratchPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/EmulateSubgroupsPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/NormalizeRectCoordinatesPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/Lower1DArrayImagesPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/Lower1DSampledImagesPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/BakeImageFormatsPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/WidenImageFormatsPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/ClampMultisampleFetchPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/PrivateToEntryLocalPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/StripUniformLocationsPass.cpp
     MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/StripUboMemberRelaxedPrecisionPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/StripNoPerspectivePass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/EmulateNoPerspectivePass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LegalizeFragmentOutputIndexPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/LegalizeResourceArrayIndexPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/FlattenAtomicCounterBlockPass.cpp
-    MobileGL/MG_Util/ShaderTranspiler/SpirvPasses/DemotePointSizePass.cpp
 
     MobileGL/MG_Util/BackendLoaders/OpenGL/Loader.cpp
     MobileGL/MG_Util/BackendLoaders/Vulkan/Loader.cpp
 
-    MobileGL/MG_Util/SelfTest/DriverBugProbes.cpp
-    MobileGL/MG_Util/SelfTest/PersistentBufferOrderingProbe.cpp
     MobileGL/MG_Util/SelfTest/DriverPost.cpp
-    MobileGL/MG_Util/SelfTest/DriverPostIterationRPWitness.cpp
-    MobileGL/MG_Util/SelfTest/PrimitivesGeneratedNoXfbProbe.cpp
 
     MobileGL/MG_Util/Texture/PixelStoreProcessor.cpp
     MobileGL/MG_Util/Texture/TextureFormatProcessor.cpp
 
     MobileGL/MG_Impl/GLXImpl/Exporting/Definitions.cpp
-    MobileGL/MG_Impl/GLXImpl/GLXImpl.cpp
     MobileGL/MG_Impl/GLXImpl/LookUp/LookUp.cpp
 
     MobileGL/MG_Impl/EGLImpl/Exporting/Definitions.cpp
@@ -411,10 +214,7 @@ set(SOURCE_FILES
     MobileGL/MG_Impl/GLImpl/Framebuffer/Validators.cpp
     MobileGL/MG_Impl/GLImpl/Framebuffer/GL_Framebuffer.cpp
     MobileGL/MG_Impl/GLImpl/Program/GL_Program.cpp
-    MobileGL/MG_Impl/GLImpl/Program/ProgramInterface.cpp
-    MobileGL/MG_Impl/GLImpl/Program/GL_ProgramPipeline.cpp
     MobileGL/MG_Impl/GLImpl/Texture/GL_Texture.cpp
-    MobileGL/MG_Impl/GLImpl/Debug/GL_Debug.cpp
     MobileGL/MG_Impl/GLImpl/Texture/Validators.cpp
     MobileGL/MG_Impl/GLImpl/Texture/ProxyTexture.cpp
     MobileGL/MG_Impl/GLImpl/VertexArray/GL_VertexArray.cpp
@@ -436,7 +236,6 @@ set(SOURCE_FILES
     MobileGL/MG_Backend/DirectGLES/BackendObject_DirectGLES.cpp
     MobileGL/MG_Backend/DirectGLES/Utils.cpp
     MobileGL/MG_Backend/DirectGLES/Managers.cpp
-    MobileGL/MG_Backend/DirectGLES/MultiDraw.cpp
 
     MobileGL/MG_Backend/DirectVulkan/DirectVulkan.cpp
     MobileGL/MG_Backend/DirectVulkan/BackendObject_DirectVulkan.cpp
@@ -472,17 +271,10 @@ set(SOURCE_FILES
     MobileGL/MG_State/GLState/TextureState/TextureObject2DCube.cpp
     MobileGL/MG_State/GLState/TextureState/TextureObject3D.cpp
     MobileGL/MG_State/GLState/TextureState/TextureObjectBuffer.cpp
-    MobileGL/MG_State/GLState/TextureState/TextureObjectView.cpp
     MobileGL/MG_State/GLState/TextureState/TextureUnit.cpp
     MobileGL/MG_State/GLState/TextureState/TextureState.cpp
     MobileGL/MG_State/GLState/ProgramState/ProgramObject.cpp
-    MobileGL/MG_State/GLState/ProgramState/ProgramLinkTask.cpp
-    MobileGL/MG_State/GLState/ProgramState/ProgramTranslationCache.cpp
-    MobileGL/MG_State/GLState/ProgramState/ProgramSpirvTask.cpp
-    MobileGL/MG_State/GLState/ProgramState/ShaderCompileTask.cpp
     MobileGL/MG_State/GLState/ProgramState/ShaderObject.cpp
-    MobileGL/MG_State/GLState/ProgramState/ShaderPreprocessCache.cpp
-    MobileGL/MG_State/GLState/ProgramState/ShaderCompileAdoptionMap.cpp
     MobileGL/MG_State/GLState/ProgramState/ProgramState.cpp
     MobileGL/MG_State/GLState/RenderState/RenderState.cpp
     MobileGL/MG_State/GLState/FramebufferState/FramebufferObject.cpp
@@ -493,180 +285,6 @@ set(SOURCE_FILES
     MobileGL/MG_State/GLState/RenderbufferState/RenderbufferState.cpp
 )
 
-# ---------------------------------------------------------------------------
-# MG_Remote (disaggregated transport). Everything below is gated: with the
-# option OFF not one file here is compiled and no include path is added.
-# ---------------------------------------------------------------------------
-
-# MOBILEGL_BUILD_DISAGGREGATED_INPROC implies MOBILEGL_BUILD_DISAGGREGATED. A normal
-# variable, not a forced cache write, for the reason the two implications below give: an
-# operator's cache entry stays theirs and only this configure is shadowed. Ordered BEFORE the
-# flatbuffers guard so that a missing submodule turns BOTH off together - an INPROC build
-# with the transport shadowed off would compile a role-isolation shim over no roles.
-if (MOBILEGL_BUILD_DISAGGREGATED_INPROC AND NOT MOBILEGL_BUILD_DISAGGREGATED)
-    message(STATUS "MobileGL: MOBILEGL_BUILD_DISAGGREGATED_INPROC=ON forces "
-                   "MOBILEGL_BUILD_DISAGGREGATED ON for this configure")
-    set(MOBILEGL_BUILD_DISAGGREGATED ON)
-endif()
-
-# FlatBuffers is a submodule and its runtime is header-only. Guard both ways:
-# a checkout without the submodule must configure and build, just without the
-# disaggregated shape, rather than fail with a missing-header error a hundred
-# lines later. Note this only checks for the RUNTIME headers - flatc is never
-# built here (see scripts/gen_protocol.py).
-if (MOBILEGL_BUILD_DISAGGREGATED AND
-    NOT EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/3rdparty/flatbuffers/include/flatbuffers/flatbuffers.h")
-    message(WARNING
-        "MOBILEGL_BUILD_DISAGGREGATED=ON but 3rdparty/flatbuffers/include is missing. "
-        "Run `git submodule update --init 3rdparty/flatbuffers`. Building without the "
-        "disaggregated shape for this configure; the cached ON takes effect once the "
-        "submodule is present.")
-    # A NORMAL variable, deliberately not `CACHE BOOL ... FORCE`: forcing OFF into the cache
-    # made the plain re-configure after `git submodule update` stay OFF with no message at
-    # all. Shadowing the cache entry for this configure only keeps the operator's ON where it
-    # was, so the next configure - with the submodule there - honours it.
-    set(MOBILEGL_BUILD_DISAGGREGATED OFF)
-    # And with it the shim option, or the `-DMOBILEGL_BUILD_DISAGGREGATED_INPROC=1` below
-    # would still be defined over a build with no MG_Remote in it at all.
-    set(MOBILEGL_BUILD_DISAGGREGATED_INPROC OFF)
-endif()
-
-# MOBILEGL_BUILD_DISAGGREGATED implies MOBILEGL_PIPE_PUSH (P5 c0). The split path IS the
-# pushed path: MG_Remote's server decodes records into the MGPipeApply* entry points, which
-# live in MG_Pipe/PipeApply.cpp, which the PIPE_PUSH block below is what compiles. Without
-# this, `-DMOBILEGL_BUILD_DISAGGREGATED=ON` alone configures and then fails to link the
-# applier - and the shape it fails in (MG_Remote compiled, no applier) is indistinguishable
-# at the CMake level from a legitimate transport-only build, which is why it is stated here
-# rather than left to whoever hits the link error. Same normal-variable form as the two
-# implications above.
-if (MOBILEGL_BUILD_DISAGGREGATED AND NOT MOBILEGL_PIPE_PUSH)
-    message(STATUS "MobileGL: MOBILEGL_BUILD_DISAGGREGATED=ON forces MOBILEGL_PIPE_PUSH ON for "
-                   "this configure: the split path decodes into the MGPipe applier, and the "
-                   "applier is what MOBILEGL_PIPE_PUSH compiles")
-    set(MOBILEGL_PIPE_PUSH ON)
-endif()
-
-# MOBILEGL_PIPE_VERIFY implies MOBILEGL_PIPE_PUSH: the comparator compares the pushed block
-# against a snapshot, so there has to be a pushed block. A normal variable, not a forced
-# cache write, for the same reason as the disaggregated fallback above.
-if (MOBILEGL_PIPE_VERIFY AND NOT MOBILEGL_PIPE_PUSH)
-    message(STATUS "MobileGL: MOBILEGL_PIPE_VERIFY=ON forces MOBILEGL_PIPE_PUSH ON for this configure")
-    set(MOBILEGL_PIPE_PUSH ON)
-endif()
-
-# In a pull build the legacy arm is the ONLY arm, so the option cannot be off there.
-# A normal variable, not a forced cache write, for the same reason as the two above.
-if (NOT MOBILEGL_PIPE_PUSH AND NOT MOBILEGL_PIPE_LEGACY_MEMOS)
-    message(STATUS "MobileGL: MOBILEGL_PIPE_PUSH=OFF forces MOBILEGL_PIPE_LEGACY_MEMOS ON for this "
-                   "configure: with nothing pushed it is the only arm there is")
-    set(MOBILEGL_PIPE_LEGACY_MEMOS ON)
-endif()
-
-if (MOBILEGL_PIPE_PUSH)
-    message(STATUS "MobileGL: PipeInputs push ON, appending the MGPipe fill sources")
-    list(APPEND SOURCE_FILES
-        MobileGL/MG_Backend/MGPipe/PipeInputs.cpp
-        MobileGL/MG_Impl/Pipe/PipeFill.cpp
-        # P2's contract: the chunk table and its subset hash, the in-process applier, and
-        # the client's {slot, gen} allocator. All three are push-only, which is how the
-        # pull build gains no symbol from P2 (G1) - a declaration emits nothing.
-        MobileGL/MG_Pipe/MGPipeRenderStateSpans.cpp
-        MobileGL/MG_Pipe/PipeApply.cpp
-        MobileGL/MG_Impl/Pipe/SlotAllocator.cpp
-        # P4a's contract: the reflection-archive serializer over ProgramArtifacts.h's
-        # VisitFields tables. Push-only for the same G1 reason as the three above - in
-        # monolith the archive never crosses (create_shader_state hands the two structs over
-        # by pointer beside the record), so the codec is live code only in the VERIFY lane,
-        # where the applier serialises, deserialises and field-compares before storing.
-        MobileGL/MG_State/GLState/ProgramState/ProgramArtifactsCodec.cpp
-        # P5's contract (integrator ruling R-17, package c1): the MONOLITH arm of the
-        # client->wire routing - the thirty-seven adapters that install gMGPipeScreen /
-        # gMGPipeContext over the MGPipeApply* entry points, and the reply mailbox the four
-        # acceptance rows answer through. Push-only for the same G1 reason as the five above:
-        # the two tables are inline variables that are zero in a pull build and nothing there
-        # can reach a thunk.
-        MobileGL/MG_Pipe/PipeRoute.cpp
-    )
-endif()
-
-if (MOBILEGL_BUILD_DISAGGREGATED)
-    message(STATUS "MobileGL: disaggregated transport ON, appending MG_Remote sources")
-    list(APPEND SOURCE_FILES
-        MobileGL/MG_Remote/Transport/ShmLink.cpp
-        MobileGL/MG_Remote/Transport/LinkMetrics.cpp
-        MobileGL/MG_Remote/Transport/StreamLink.cpp
-        MobileGL/MG_Remote/Transport/Ring.cpp
-        MobileGL/MG_Remote/Transport/Doorbell.cpp
-        MobileGL/MG_Remote/Transport/ShmSegment.cpp
-        # Both platform halves are listed unconditionally and each is empty on
-        # the other OS, so neither can rot behind an `if (WIN32)` nobody
-        # configures.
-        MobileGL/MG_Remote/Transport/ShmSegmentPosix.cpp
-        MobileGL/MG_Remote/Transport/ShmSegmentWin32.cpp
-        MobileGL/MG_Remote/Transport/FdPassing.cpp
-        MobileGL/MG_Remote/Transport/InProcessTransport.cpp
-        MobileGL/MG_Remote/Transport/SocketTransport.cpp
-        MobileGL/MG_Remote/Transport/ControlInbox.cpp
-        # Keeps MG_Util/Debug/Log.h - and through it the GL frontend's
-        # umbrella header - out of the header-only wire code (WireLog.h).
-        MobileGL/MG_Remote/Transport/WireLog.cpp
-        # ---- P5: the three new directories ------------------------------
-        # Wire/   the G3 codec: MGPWireRec_* in and out of SEG_CMD, blobs and
-        #         var-tails in and out of SEG_STAGE.                    [w1]
-        # Client/ the emitting role: session, the 69-slot emit table, the
-        #         caps mirror.                                          [c1]
-        # Server/ the applying role: session, the applier bridge onto the
-        #         existing MGPipeApply* free functions, the apply thread. [v1]
-        #
-        # Every file below lands in P5 as a HEADER plus a .cpp of named
-        # Fatal stubs, so that all seven P5 packages compile and link on day
-        # one against signatures that cannot then move under them. A stub is
-        # MGLOG_F + std::abort, never a silent no-op: an unimplemented
-        # emitter that returns quietly is how a split lane runs monolith and
-        # goes green (ARCHITECTURE.md 10.3).
-        MobileGL/MG_Remote/CapsCodec.cpp
-        # P6 dl: the one place a session dies - Session::Fail's funnel (Fatal-family aware,
-        # publishes SessionFault, one telemetry point).
-        MobileGL/MG_Remote/FatalFunnel.cpp
-        MobileGL/MG_Remote/Wire/PipeWireCodec.cpp
-        MobileGL/MG_Remote/Client/ClientSession.cpp
-        MobileGL/MG_Remote/Client/EmitTables.cpp
-        MobileGL/MG_Remote/Client/CapsMirror.cpp
-        # P5 c1: the client role's BackendObject. pActiveBackendObject holds one of these
-        # under split (table 3); the hook that installs it is v1's, in MG_Backend/Init.cpp.
-        MobileGL/MG_Remote/Client/BackendObject_Remote.cpp
-        # P5 c1, ruling R-17: the ENCODE TWIN of gMGPipeWireRecordApply - the thirty-seven
-        # emitters installed over the two generated tables, which is what stops every
-        # resource/CSO/texture/program record executing synchronously on the GL thread under
-        # inproc. The monolith arm of the same routing is MG_Pipe/PipeRoute.cpp, in the
-        # PIPE_PUSH list above, because it must exist in a push build that has no MG_Remote.
-        MobileGL/MG_Remote/Client/WireTables.cpp
-        # P5 b1's two: the conservative GPU-write set the client must build because all six
-        # MarkGpuWritten producers are on the server's side of the line, and the
-        # block-granularity persistent-map push that tier T2 makes mandatory.
-        MobileGL/MG_Remote/Client/GpuWritePending.cpp
-        MobileGL/MG_Remote/Client/PersistentMapTracker.cpp
-        MobileGL/MG_Remote/Server/ServerSession.cpp
-        MobileGL/MG_Remote/Server/PipeApplier.cpp
-        MobileGL/MG_Remote/Server/ServerLoop.cpp
-        MobileGL/MG_Remote/Server/ServerMain.cpp
-        MobileGL/MG_Remote/Server/ServerSpawn.cpp
-        # P5f fc: the value frame that replaced the control mailbox's function-pointer payload,
-        # and its codec against protocol.fbs's SurfaceOp/SurfaceReply (the spawn arm's seam).
-        MobileGL/MG_Remote/Server/SurfaceControlFrame.cpp
-        MobileGL/MG_Remote/Protocol/SurfaceOpCodec.cpp
-        # P12 (on-screen server window): the process-wide holder of the server's own window
-        # (the display Activity's SurfaceView on Android; nobody installs one on the host, so a
-        # ServerOwned request is refused by name there).
-        MobileGL/MG_Remote/Server/ServerDisplay.cpp
-        # P7 gate 5 (g5-msprobe): the Magma wire arm's two multisample depth/stencil resolve
-        # arms and the probe that measures the first against the second, shared by the
-        # renderer's bring-up and the Vulkan POST. Wire-only - the monolith records neither arm -
-        # so it stays out of the pull build (gate G1).
-        MobileGL/MG_Backend/DirectVulkan/Renderer/WireDepthResolveProbe.cpp
-    )
-endif()
-
 if (APPLE AND NOT MOBILEGL_IOS)
     list(APPEND SOURCE_FILES
         MobileGL/MG_Impl/CGLImpl/CGLImpl.cpp
@@ -679,30 +297,9 @@ endif()
 if (ANDROID)
     list(APPEND SOURCE_FILES
         MobileGL/MG_Util/SelfTest/DriverPostJni.cpp
-        MobileGL/MG_Util/SelfTest/DriverBenchJni.cpp
-    )
-    if (MOBILEGL_BUILD_DISAGGREGATED)
-        # P12 (on-screen server window): the trace APK's MobileGLDisplayActivity - the in-process
-        # display server's thread, its SurfaceView's ANativeWindow in and out of ServerDisplay, and
-        # the geometry up-call. Split build only: nothing else has an in-process server to drive.
-        list(APPEND SOURCE_FILES
-            MobileGL/MG_Remote/Server/DisplayServerJni.cpp
-        )
-    endif()
-endif()
-
-if (WIN32)
-    list(APPEND SOURCE_FILES
-        MobileGL/MG_Impl/WGLImpl/WGLImpl.cpp
-        MobileGL/MG_Impl/WGLImpl/Exporting/Definitions.cpp
     )
 endif()
 
-# The shader-compile pool runs standalone Asio on real threads. This host's glibc (>= 2.34)
-# merged pthread into libc, so it links without asking, but the NDK and musl are not
-# guaranteed to be as forgiving - ask for it explicitly rather than rely on the accident.
-find_package(Threads REQUIRED)
-
 set(MOBILEGL_LINK_LIBRARIES
         glslang::glslang
         spirv-cross-c
@@ -712,71 +309,29 @@ set(MOBILEGL_LINK_LIBRARIES
         GPUOpen::VulkanMemoryAllocator
         Vulkan::UtilityHeaders
         spirv-reflect-static
-        Threads::Threads
 )
 
 set(MOBILEGL_COMPILE_DEF
         -DVMA_STATIC_VULKAN_FUNCTIONS=0
         -DVMA_DYNAMIC_VULKAN_FUNCTIONS=1
         -DVMA_VULKAN_VERSION=1001000
-        # Header-only Asio, no Boost, no deprecated interfaces. Set on the definition list
-        # rather than per-target so the shared library and the _s static target agree.
-        -DASIO_STANDALONE
-        -DASIO_NO_DEPRECATED
 )
 
-if (MOBILEGL_BUILD_DISAGGREGATED)
-    list(APPEND MOBILEGL_COMPILE_DEF -DMOBILEGL_BUILD_DISAGGREGATED=1)
-endif()
-
-if (MOBILEGL_PIPE_PUSH)
-    list(APPEND MOBILEGL_COMPILE_DEF -DMOBILEGL_PIPE_PUSH=1)
-endif()
-if (MOBILEGL_PIPE_VERIFY)
-    list(APPEND MOBILEGL_COMPILE_DEF -DMOBILEGL_PIPE_VERIFY=1)
-endif()
-if (MOBILEGL_PIPE_LEGACY_MEMOS)
-    list(APPEND MOBILEGL_COMPILE_DEF -DMOBILEGL_PIPE_LEGACY_MEMOS=1)
-endif()
-
 message(STATUS "MOBILEGL_COMPILE_DEF=${MOBILEGL_COMPILE_DEF}")
 
 set(MOBILEGL_INCLUDE_DIR
         ${CMAKE_SOURCE_DIR}/include
         ${CMAKE_SOURCE_DIR}/MobileGL
-        # The MGPipe boundary headers. They are reachable as <MG_Pipe/MGPipe.h> through the
-        # line above too; this entry lets the client, the backends and MG_Remote spell them
-        # as <MGPipe.h> once MG_Pipe stops being a leaf of the frontend tree.
-        ${CMAKE_SOURCE_DIR}/MobileGL/MG_Pipe
         ${spirv-tools_SOURCE_DIR}
         ${spirv-tools_SOURCE_DIR}/include
         ${spirv-tools_BINARY_DIR}
         ${SPIRV-Headers_SOURCE_DIR}/include
-        # Header-only submodule: no add_subdirectory, no link target. Only
-        # MG_Util/Async/ShaderCompilePool.cpp includes it, and it stays behind that file's
-        # pimpl so no consumer target needs this path.
-        ${CMAKE_SOURCE_DIR}/3rdparty/asio/include
 )
 
-if (MOBILEGL_BUILD_DISAGGREGATED)
-    # Header-only runtime: an include path, no add_subdirectory, no link
-    # target, and above all no flatc in the build graph. protocol_generated.h
-    # is committed and regenerated by scripts/gen_protocol.py.
-    list(APPEND MOBILEGL_INCLUDE_DIR ${CMAKE_SOURCE_DIR}/3rdparty/flatbuffers/include)
-endif()
-
-add_library(${CMAKE_PROJECT_NAME} SHARED
+add_library(${CMAKE_PROJECT_NAME} SHARED 
     ${SOURCE_FILES}
 )
 
-if (WIN32)
-    # The wgl* entry points are exported via .def (see the comment in wgl.def);
-    # only the shared library links it.
-    target_sources(${CMAKE_PROJECT_NAME} PRIVATE
-        MobileGL/MG_Impl/WGLImpl/Exporting/wgl.def
-    )
-endif()
-
 if (CMAKE_BUILD_TYPE STREQUAL "Debug")
     set_target_properties(${CMAKE_PROJECT_NAME} PROPERTIES
         C_VISIBILITY_PRESET default
@@ -819,18 +374,6 @@ if(UNIX AND NOT APPLE AND NOT ANDROID)
     endforeach()
 endif()
 
-if(WIN32)
-    # Drop-in for the classic GL loader path: a copy named opengl32.dll placed
-    # next to a host executable is what LoadLibrary("opengl32.dll") and gdi32's
-    # pixel-format forwarding will resolve.
-    add_custom_command(TARGET ${CMAKE_PROJECT_NAME} POST_BUILD
-        COMMAND ${CMAKE_COMMAND} -E copy_if_different
-                "$<TARGET_FILE:${CMAKE_PROJECT_NAME}>"
-                "$<TARGET_FILE_DIR:${CMAKE_PROJECT_NAME}>/opengl32.dll"
-        COMMENT "Creating opengl32.dll drop-in copy"
-    )
-endif()
-
 if(NOT ANDROID)
     add_library(${CMAKE_PROJECT_NAME}_s STATIC 
         ${SOURCE_FILES}
@@ -882,21 +425,8 @@ if (ANDROID)
 endif()
 
 if (APPLE AND NOT MOBILEGL_IOS)
-    # MobileGL statically embeds glslang, SPIRV-Tools, and SPIRV-Cross. When
-    # this dylib is injected with DYLD_INSERT_LIBRARIES, exporting those C++
-    # symbols interposes incompatible copies embedded by host libraries such
-    # as shaderc. Keep only the public GL/EGL/CGL loader surface globally
-    # visible; GetProcAddress can still return pointers to hidden internals.
-    set(MOBILEGL_MACOS_EXPORTED_SYMBOLS
-        "${CMAKE_CURRENT_SOURCE_DIR}/MobileGL/MG_Impl/DyldInterpose/ExportedSymbols.txt")
-    target_link_options(${CMAKE_PROJECT_NAME} PRIVATE
-        "LINKER:-exported_symbols_list,${MOBILEGL_MACOS_EXPORTED_SYMBOLS}")
-    set_property(TARGET ${CMAKE_PROJECT_NAME} APPEND PROPERTY
-        LINK_DEPENDS "${MOBILEGL_MACOS_EXPORTED_SYMBOLS}")
-
     target_link_libraries(${CMAKE_PROJECT_NAME} PUBLIC
         "-framework Cocoa"
-        "-framework CoreVideo"
         "-framework QuartzCore"
         "-framework Foundation"
         "-framework OpenGL"
@@ -904,7 +434,6 @@ if (APPLE AND NOT MOBILEGL_IOS)
     if(TARGET ${CMAKE_PROJECT_NAME}_s)
         target_link_libraries(${CMAKE_PROJECT_NAME}_s PUBLIC
             "-framework Cocoa"
-            "-framework CoreVideo"
             "-framework QuartzCore"
             "-framework Foundation"
             "-framework OpenGL"
@@ -960,12 +489,6 @@ if (NOT ANDROID)
         add_subdirectory(MobileGL/MG_Test)
     endif()
 
-    # After MG_Test so googletest is already available when the unit tests are
-    # built; the module fetches its own copy when they are not.
-    if (MOBILEGL_BUILD_INTEGRATION_TEST)
-        add_subdirectory(MobileGL/MG_IntegrationTest)
-    endif()
-
     if (MOBILEGL_BUILD_BENCHMARK)
         add_subdirectory(MobileGL/MG_Benchmark)
     endif()
@@ -974,119 +497,3 @@ if (NOT ANDROID)
         add_subdirectory(tools/trace_replay)
     endif()
 endif()
-
-# The integration binary is also useful as a standalone adb-shell executable.
-# Android cannot use the desktop-only MobileGL_s target, so its CMake module
-# links libMobileGL.so and creates an AImageReader-backed window instead.
-if (ANDROID AND MOBILEGL_BUILD_INTEGRATION_TEST)
-    add_subdirectory(MobileGL/MG_IntegrationTest)
-endif()
-
-# ---------------------------------------------------------------------------
-# P0 spike A: the Android delivery chain for a second native executable.
-#
-# The disaggregated design needs a server process on Android (PLAN-B.md §8.1,
-# inheriting PLAN.md §11.1-§11.6). An APK's only exec-able install location is
-# lib/<abi>/, and the packager only puts a file there if it is named lib*.so -
-# so a second executable has to be built with an .so name and exec'd out of
-# getApplicationInfo().nativeLibraryDir. This target is the stub that proves the
-# chain end to end: it is packaged like a library, exec'd from the app's own
-# untrusted_app process, and writes a marker the parent reads back.
-#
-# Off by default and ANDROID-only, so no shipping configuration builds it. The
-# trace flavour of the plugin APK turns it on (android-plugin/build.gradle).
-# ---------------------------------------------------------------------------
-# ---------------------------------------------------------------------------
-# P6 `sm`: the REAL server image. Unlike MOBILEGL_BUILD_SERVER_SPIKE below - the
-# P0 spike, which links no MobileGL library and exists only to prove the Android
-# delivery chain - this one links the library and runs mobilegl_server_main.
-#
-# ARCHITECTURE.md:496 called for a ~30-line stub that dlopen's libMobileGL.so and
-# dlsym's the entry point, so one shared library serves both roles. On a desktop
-# configure we link it directly instead: there is no APK packaging rule to satisfy
-# and a direct link is what makes an undefined symbol a BUILD error rather than a
-# runtime dlsym failure in a child whose stderr is /dev/null.
-#
-# Android keeps the lib*.so naming and the nativeLibraryDir output the spike
-# proved is the only exec-able location in an APK.
-if (MOBILEGL_BUILD_DISAGGREGATED AND NOT WIN32)
-    add_executable(MobileGLServer
-        ${CMAKE_CURRENT_SOURCE_DIR}/MobileGL/MG_Remote/Server/ServerEntry.cpp)
-
-    target_include_directories(MobileGLServer PRIVATE
-        ${MOBILEGL_INCLUDE_DIR})
-
-    target_link_libraries(MobileGLServer PRIVATE ${CMAKE_PROJECT_NAME})
-
-    set_target_properties(MobileGLServer PROPERTIES
-        POSITION_INDEPENDENT_CODE ON)
-    target_compile_options(MobileGLServer PRIVATE -fPIE)
-    target_link_options(MobileGLServer PRIVATE -pie)
-
-    # $ORIGIN, OR THE SERVER CANNOT START AT ALL ON ANDROID.
-    #
-    # This executable links libMobileGL.so, and it is EXEC'd rather than dlopen'd - so it gets a
-    # fresh linker namespace with the default search path, not the app's. An APK's lib/<abi>/ is
-    # not on that path, and the failure is the bluntest one there is:
-    #
-    #   F linker: CANNOT LINK EXECUTABLE ".../lib/arm64/libMobileGLServer.so":
-    #             library "libMobileGL.so" not found: needed by main executable
-    #
-    # It cost a device run to find because it is invisible on desktop: CMake gives build-tree
-    # targets an absolute RPATH automatically, so the WSL server resolved its dependency through a
-    # path that does not exist on a phone. $ORIGIN says "beside me", which is true in the APK, true
-    # in the build tree, and true wherever somebody copies the pair - and it is what makes a
-    # deployment that is NOT a build tree work at all, which the end state is.
-    # THE PROPERTIES, NOT target_link_options. A raw `-Wl,-rpath,$ORIGIN` reaches the generator
-    # unquoted and the SHELL expands $ORIGIN to nothing - measured on device, where the linker
-    # said `normalize_path - invalid input: "$"` and then failed to find libMobileGL.so anyway.
-    # BUILD_RPATH / INSTALL_RPATH are the supported spelling and CMake escapes them correctly.
-    set_target_properties(MobileGLServer PROPERTIES
-        BUILD_RPATH "$ORIGIN"
-        INSTALL_RPATH "$ORIGIN"
-        BUILD_WITH_INSTALL_RPATH TRUE)
-
-    if (ANDROID)
-        # An APK's only exec-able install location is lib/<abi>/, and the packager
-        # only puts a file there if it is named lib*.so. P0 spike A proved this
-        # works from the app's own untrusted_app domain on two devices.
-        set_target_properties(MobileGLServer PROPERTIES
-            PREFIX "lib" SUFFIX ".so" OUTPUT_NAME "MobileGLServer")
-        if (CMAKE_LIBRARY_OUTPUT_DIRECTORY)
-            set_target_properties(MobileGLServer PROPERTIES
-                RUNTIME_OUTPUT_DIRECTORY "${CMAKE_LIBRARY_OUTPUT_DIRECTORY}")
-        endif()
-    else()
-        # Desktop: the name the dladdr fallback looks for beside libMobileGL.so.
-        set_target_properties(MobileGLServer PROPERTIES
-            PREFIX "lib" SUFFIX ".so" OUTPUT_NAME "MobileGLServer"
-            RUNTIME_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}")
-    endif()
-endif()
-
-if (ANDROID AND MOBILEGL_BUILD_SERVER_SPIKE)
-    # Renamed by P6 sm: the real server took the name it had been holding.
-    add_executable(MobileGLServerSpike
-        ${CMAKE_CURRENT_SOURCE_DIR}/tools/spikes/server_stub/main.cpp)
-
-    # An executable that is named like a shared library still has to be a real
-    # PIE executable: Android has refused non-PIE executables since API 21, and
-    # the name alone does not change what the loader demands of the file.
-    set_target_properties(MobileGLServerSpike PROPERTIES
-        PREFIX "lib"
-        SUFFIX ".so"
-        OUTPUT_NAME "MobileGLServerSpike"
-        POSITION_INDEPENDENT_CODE ON)
-    target_compile_options(MobileGLServerSpike PRIVATE -fPIE)
-    target_link_options(MobileGLServerSpike PRIVATE -pie)
-
-    # AGP packages what the external native build drops into the per-ABI output
-    # directory, and it selects by the .so extension. CMake puts executables in
-    # CMAKE_RUNTIME_OUTPUT_DIRECTORY, which is not the directory AGP hands to
-    # CMAKE_LIBRARY_OUTPUT_DIRECTORY, so point this target's runtime output at
-    # the library directory when the generator gave us one.
-    if (CMAKE_LIBRARY_OUTPUT_DIRECTORY)
-        set_target_properties(MobileGLServerSpike PROPERTIES
-            RUNTIME_OUTPUT_DIRECTORY "${CMAKE_LIBRARY_OUTPUT_DIRECTORY}")
-    endif()
-endif()

MobileGL/Config.h

@@ -14,48 +14,12 @@ namespace MobileGL::MG_Config {
     inline const String ProjectName = "MobileGL";
     inline const String CoreName = "MobileGL Core";
     inline const String CoreVendor = "MobileGL-Dev (BZLZHH, Swung0x48, Tungsten)";
-    inline const Version CoreVersion = {26, 9, 0, "-dev", VersionType::Development};
+    inline const Version CoreVersion = {26, 7, 0, "-dev", VersionType::Development};
     inline const VersionStringFormatAttrib DefaultVersionStringFormatAttrib = {2, 2, 0, true, true};
     inline const Uint64 CacheVersion = 0;
 
     extern BackendType ActiveBackendType;
 
-    // Tri-state override for device-specific quirks: Auto lets the detected device decide,
-    // ForceOn/ForceOff bypass the detection in either direction. ForceOn only bypasses the
-    // device gate - each quirk keeps its structural safety checks.
-    enum class QuirkOverride : Uint8 {
-        Auto = 0,
-        ForceOn,
-        ForceOff,
-    };
-
-    // Preferred DirectVulkan dispatch tier for the glMultiDraw* families. A preference,
-    // never a demand: the renderer clamps it to what the device supports at device
-    // creation, falling down the chain ext -> indirect -> unroll with one log line.
-    enum class MultiDrawMode : Uint8 {
-        Auto = 0, // unset: best supported tier
-        Ext,      // VK_EXT_multi_draw: one vkCmdDrawMultiEXT / vkCmdDrawMultiIndexedEXT
-        Indirect, // multiDrawIndirect feature: one vkCmdDraw*Indirect over a transient command array
-        Unroll,   // one vkCmdDraw* per sub-draw
-    };
-
-    // Preferred DirectGLES emulation tier for glMultiDrawElements(BaseVertex). GLES has no
-    // such entry point in core, so every tier below is an emulation; they differ only in
-    // which driver capability they lean on and how many driver calls a batch costs. Like
-    // the Magma knob this is a preference, clamped at resolution time to what the ES
-    // driver actually supports, with one log line when it falls back.
-    enum class GLESMultiDrawMode : Uint8 {
-        Auto = 0,      // unset: best supported tier
-        Ext,           // one glMultiDrawElementsBaseVertexEXT
-        MultiIndirect, // one glMultiDrawElementsIndirectEXT over a scratch command buffer
-        Indirect,      // one glDrawElementsIndirect per sub-draw over that same buffer
-        BaseVertex,    // one glDrawElementsBaseVertex per sub-draw
-        DrawElements,  // baseVertex folded into a scratch index buffer on the CPU, then plain
-                       // glDrawElements per sub-draw (for drivers with no base-vertex draw at all)
-        Compute,       // a compute shader flattens every sub-draw into one rebased index buffer,
-                       // drawn by a single glDrawElements
-    };
-
     // Feature toggles parsed once from environment variables in MG_ConfigLoader::Init()
     // (ConfigLoader.cpp), before the accepted-env map is destroyed. All Bool fields share
     // one truthy rule: the variable is set, non-empty, not "0", and not "false"
@@ -69,102 +33,21 @@ namespace MobileGL::MG_Config {
     struct FeaturesTable {
         // MOBILEGL_DISABLE_TIMERQUERY: do not advertise or use GPU timer queries.
         Bool DisableTimerQuery = false;
-        // MOBILEGL_ESPRYT_ENABLE_TEXTURE_VIEW: advertise GL_ARB_texture_view on DirectGLES when
-        // the host ES driver has EXT/OES_texture_view. Off by default: the host extension is
-        // present on Adreno 830 and the functional half of KHR-GL4{2,3}.texture_view still fails
-        // there, because the view's ES internalformat is normalized independently of the storage
-        // it aliases (see BackendObject_DirectGLES::BuildAdvertisedExtensions). The flag exists
-        // so that work can be done without editing the gate.
-        Bool EsprytEnableTextureView = false;
-        // MOBILEGL_ENABLE_SPIRV_VALIDATION: validate generated and transformed SPIR-V.
-        // Disabled by default because validation is a diagnostics-only cost.
-        Bool EnableSpirvValidation = false;
-        // MOBILEGL_ESPRYT_USE_ANGLE: load ANGLE EGL/GLES libraries.
-        Bool EsprytUseAngle = false;
+        // MOBILEGL_USE_ANGLE: load ANGLE EGL/GLES libraries.
+        Bool UseAngle = false;
 #if defined(MOBILEGL_TRACE_ANGLE_VARIANTS)
         // MOBILEGL_TRACE_ANGLE_VARIANT: signed trace-APK ANGLE build short hash.
         String TraceAngleVariant;
 #endif
-        // MOBILEGL_MAGMA_DISABLE_SUBGROUP: force-disable Vulkan shader subgroup support,
-        // including the opt-in emulated compute path below.
-        Bool MagmaDisableSubgroup = false;
-        // MOBILEGL_MAGMA_EMULATE_SUBGROUP: implement GL_KHR_shader_subgroup's compute
-        // stage on a 32-lane VIRTUAL subgroup lowered to workgroup-shared memory
-        // (ShaderTranspiler::EmulateSubgroupsPass). Strictly a last resort: it only ever
-        // engages when this flag is set AND the device has no native subgroup support at
-        // all - a device with real subgroup operations always uses them natively,
-        // whatever their width (the known iterationRP defect is patched by
-        // MagmaFixIterationRPSubgroupScratch below instead). Off by default.
-        Bool MagmaEmulateSubgroup = false;
-        // MOBILEGL_MAGMA_FIX_ITERATIONRP_SUBGROUP_SCRATCH: patch iterationRP's own bug - the
-        // pack declares `shared vec2 prefixSumCache[32]` for a 512-invocation exposure
-        // reduction and indexes it by gl_SubgroupID, so any device with sub-16-lane
-        // subgroups (8-lane lavapipe -> 64 subgroups) writes shared memory out of
-        // bounds. The pass grows that one array to what the device's topology needs and
-        // touches nothing else; it only rewrites modules positively matching the pack's
-        // reduction fingerprint (ShaderTranspiler::FixIterationRPSubgroupScratchPass),
-        // so every other shader passes through byte-identical - as does iterationRP
-        // itself on >= 16-lane devices. Auto is ON; ForceOff replays the pack's bug
-        // verbatim.
-        QuirkOverride MagmaFixIterationRPSubgroupScratch = QuirkOverride::Auto;
-        // MOBILEGL_MAGMA_ITERATIONRP_FIX_BARRIER: repair Program 203's missing workgroup
-        // rendezvous between its two reductions over prefixSumCache. Off by default and
-        // fingerprint-gated by FixIterationRPBarrierPass when enabled.
-        Bool MagmaIterationRPFixBarrier = false;
-        // MOBILEGL_MAGMA_DERIVE_NUM_SUBGROUPS: replace compute gl_NumSubgroups loads with
-        // ceil(workgroup invocations / gl_SubgroupSize) on the NATIVE subgroup path
-        // (ShaderTranspiler::DeriveNumSubgroupsPass). Auto is ON: GL requires
-        // gl_SubgroupID < gl_NumSubgroups, Adreno's builtin reports 1 while the same
-        // dispatch emits IDs 0..7, and the derived value is the one Vulkan guarantees
-        // whenever the pipeline can request REQUIRE_FULL_SUBGROUPS (which the renderer
-        // does whenever local_size_x is a multiple of the native width). ForceOff returns
-        // to the raw driver builtin.
-        QuirkOverride MagmaDeriveNumSubgroups = QuirkOverride::Auto;
-        // MOBILEGL_ADVERTISE_FP64: add GL_ARB_gpu_shader_fp64 to the advertised extension
-        // string. `double` in a shader always WORKS - it is narrowed to 32 bits before any
-        // module reaches a backend (ShaderTranspiler::DemoteFloat64Pass) - but the extension
-        // promises 64-bit precision, and that is the one thing the narrowing cannot deliver.
-        // Off by default so an application that checks the string before using doubles keeps
-        // its float path; on for measuring what the conformance suite makes of the demoted
-        // precision. See the DemoteFloat64Pass header and the "fp64" POST row.
-        Bool AdvertiseFp64 = false;
+        // MOBILEGL_DISABLE_SUBGROUP: force-disable Vulkan shader subgroup support.
+        Bool DisableSubgroup = false;
         // MOBILEGL_MAGMA_R11G11B10F_FALLBACK: use fallback format for R11G11B10F on Vulkan.
         Bool MagmaR11G11B10FFallback = false;
         // MOBILEGL_MAGMA_FRAMESINFLIGHT: requested Magma frames in flight, defaulting to 3.
         Uint32 MagmaFramesInFlight = 3;
-        // MOBILEGL_ESPRYT_AVOID_SAMPLER_MIPMAP_MIN_FILTER: avoid mipmap min filters in samplers,
+        // MOBILEGL_AVOID_SAMPLER_MIPMAP_MIN_FILTER: avoid mipmap min filters in samplers,
         // resolves certain rendering bugs on ANGLE + llvmpipe.
-        Bool EsprytAvoidSamplerMipmapMinFilter = false;
-        // MOBILEGL_ESPRYT_AVOID_EXPLICIT_LOD_BIAS: leave an already-explicit LOD argument alone when
-        // emulating GL_TEXTURE_LOD_BIAS, instead of adding the bias uniform to it. Injecting
-        // the uniform turns a compile-time-constant LOD into a runtime expression, which
-        // sends ANGLE + llvmpipe down a mip-selection path that dereferences a NULL
-        // descriptor and kills the process. Deviates from spec (Vulkan adds the bias to
-        // OpImageSampleExplicitLod), so it is an avoidance for that stack only.
-        Bool EsprytAvoidExplicitLodBias = false;
-        // MOBILEGL_ESPRYT_UNLOCATED_IO_BLOCKS: emit a tessellation/geometry program's
-        // inter-stage interface blocks WITHOUT their layout(location=) qualifier, letting ES
-        // match them by block name and member sequence instead. The Mali ES driver delivers
-        // nothing at all through a located block once a tessellation or geometry stage is in
-        // the pipeline; the driver POST measures that and turns this on by itself, so Auto is
-        // the right setting everywhere. ForceOn exists so the emulation can be exercised on a
-        // healthy driver - which is what the integration lane does, since llvmpipe and
-        // lavapipe carry a located block correctly and would otherwise never run this code -
-        // and ForceOff is the negative control. See StripIoBlockLocationsPass.
-        QuirkOverride EsprytUnlocatedIoBlocks = QuirkOverride::Auto;
-        // MOBILEGL_POINT_SIZE_DEMOTION: demote gl_PointSize out of tessellation/geometry
-        // stages into an ordinary varying (ShaderCompiler::
-        // DemoteTessellationGeometryPointSizeForProgram) instead of declining such programs
-        // on a device that advertises neither EXT/OES_tessellation_point_size /
-        // geometry_point_size (DirectGLES) nor shaderTessellationAndGeometryPointSize
-        // (DirectVulkan). Auto arms it exactly where the detection says the capability is
-        // absent, which is the right setting everywhere. ForceOn exists so the demotion can
-        // be exercised on a healthy driver - llvmpipe and lavapipe host the built-in
-        // natively and would otherwise never run this code, which is what the pinned
-        // integration lane uses - and ForceOff restores the plain declines (escape hatch /
-        // negative control). Cross-backend by design: the demotion runs in the shared
-        // phase-B chain, so one switch covers both. See DemotePointSizePass.
-        QuirkOverride PointSizeDemotion = QuirkOverride::Auto;
+        Bool AvoidSamplerMipmapMinFilter = false;
         // MOBILEGL_COHERENT_AS_FLUSH: app-compat for engines (e.g. Flywheel) that write
         // GPU-read data through persistent GL_MAP_FLUSH_EXPLICIT_BIT maps they never
         // flush. Persistent FLUSH_EXPLICIT map requests are rewritten to coherent
@@ -174,525 +57,16 @@ namespace MobileGL::MG_Config {
         Bool CoherentAsFlush = false;
         // MOBILEGL_TRACE_SKIP_AUTODESTROY: skip teardown in the ELF destructor (Init.cpp).
         Bool TraceSkipAutodestroy = false;
-        // MOBILEGL_ESPRYT_DISABLE_UBO_RING: force the DirectGLES global-UBO upload back to the
+        // MOBILEGL_DISABLE_UBO_RING: force the DirectGLES global-UBO upload back to the
         // per-draw glBufferSubData path instead of the persistent-mapped ring allocator
         // (negative control / driver-bug escape hatch).
-        Bool EsprytDisableUboRing = false;
-        // MOBILEGL_ESPRYT_DISABLE_UNPACK_RING: force DirectGLES texture uploads back to
-        // glTexSubImage from the client pointer instead of staging them through the
-        // persistent-mapped unpack-PBO ring (negative control / driver-bug escape
-        // hatch).
-        Bool EsprytDisableUnpackRing = false;
-        // MOBILEGL_ESPRYT_DISABLE_UPLOAD_RING: force DirectGLES app buffer updates
-        // (glBufferSubData / map flushes) back to the immediate driver upload instead
-        // of queueing them for the staged-copy flush through the persistent-mapped
-        // upload ring (negative control / driver-bug escape hatch; the immediate
-        // upload stalls on drivers that resolve the WAR hazard on the CPU, e.g. Mali).
-        Bool EsprytDisableUploadRing = false;
-        // MOBILEGL_ESPRYT_DISABLE_INVALIDATE_FLUSH: skip the glMapBufferRange(WRITE |
-        // INVALIDATE_RANGE) tier of the DirectGLES pending-range flush and go straight
-        // to the upload ring's staged glCopyBufferSubData (negative control / escape
-        // hatch for a driver whose range-invalidating map misbehaves). The map tier is
-        // what keeps a partial write into a large in-flight buffer priced by the RANGE:
-        // on Mali both the immediate glBufferSubData and a staged copy into a busy
-        // mutable store ghost the whole destination on the CPU.
-        Bool EsprytDisableInvalidateFlush = false;
-        // MOBILEGL_DISABLE_LARGE_BUFFER_ADOPTION: keep mesh-arena-sized buffer stores
-        // (>= 16MiB) on the CPU-shadow model instead of backing them with the backend's
-        // persistently+coherently mapped storage at definition time (negative control /
-        // escape hatch). Frontend-scoped: it engages only where the active backend
-        // provides AcquirePersistentMap. With adoption on, an app SubData into a busy
-        // 128MB arena is a plain memcpy into GPU-visible memory; every driver-mediated
-        // route for the same write stalls the thread or ghost-copies the whole arena on
-        // this class of Mali driver, and the arena stops costing its size again in RAM.
-        Bool DisableLargeBufferAdoption = false;
-        // MOBILEGL_ESPRYT_FORCE_DS_READBACK_EMULATION: make DirectGLES skip the native ES
-        // depth/stencil reads and always go through the shader-sampling emulation. Core GL
-        // ES has no depth or stencil readback, but some drivers accept it anyway (Mesa does,
-        // Adreno does not), which means the emulation is dead code on exactly the stack the
-        // headless suite runs on. This forces it live so the scenarios and the CTS can
-        // exercise the path, and gives the device an A/B lever over the same choice.
-        Bool EsprytForceDepthStencilReadbackEmulation = false;
+        Bool DisableUboRing = false;
         // MOBILEGL_RELAXED_SEMANTICS: relax strict core-profile rules (e.g. VAO-0 draws,
         // texture-name reuse after delete) even on contexts that explicitly requested a core
         // profile. Without it, relaxed semantics still apply to every context that did not
         // explicitly request a core profile via EGL_CONTEXT_OPENGL_PROFILE_MASK / a >=3.1
         // version request.
         Bool RelaxedSemantics = false;
-        // MOBILEGL_MAGMA_DISABLE_BLENDED_DEPTH_WRITE: overrides the DirectVulkan quirk that
-        // strips depth writes from accumulation-blended pipelines (MIN/MAX or additive
-        // ONE+ONE - the multi-pass depth-equality signature) on drivers without
-        // cross-pipeline vertex position invariance. Sorted-transparency "over" blends,
-        // gl_FragDepth writers, and fully color-masked attachments are exempt (see
-        // PipelineFactory::ShouldSuppressDepthWrite). Auto detects Qualcomm.
-        QuirkOverride MagmaDisableBlendedDepthWriteQuirk = QuirkOverride::Auto;
-        // MOBILEGL_MAGMA_DISABLE_ROBUST_BUFFER_ACCESS: leave the Vulkan robustBufferAccess device
-        // feature off. It is enabled by default to match GL's defined out-of-range fetch
-        // behavior; this escape hatch exists to measure or dodge its GPU cost on a device.
-        Bool MagmaDisableRobustBufferAccess = false;
-        // MOBILEGL_MAGMA_MULTIDRAW_MODE: preferred DirectVulkan multi-draw dispatch tier
-        // ("ext" | "indirect" | "unroll", see MultiDrawMode). Clamped to device support;
-        // unset picks the best supported tier.
-        MultiDrawMode MagmaMultiDrawMode = MultiDrawMode::Auto;
-        // MOBILEGL_ESPRYT_MULTIDRAW_MODE: preferred DirectGLES glMultiDrawElements emulation
-        // tier ("ext" | "multiindirect" | "indirect" | "basevertex" | "drawelements" |
-        // "compute", see GLESMultiDrawMode). Clamped to driver support; unset picks the best
-        // supported tier, which never includes "compute" - see the note on its resolution.
-        GLESMultiDrawMode EsprytMultiDrawMode = GLESMultiDrawMode::Auto;
-        // MOBILEGL_ASYNC_SHADER_COMPILE: overrides asynchronous shader compilation. Unset
-        // keeps the built-in default (MG_Util::Async::kAsyncShaderCompileDefault); falsy
-        // forces every glCompileShader/glLinkProgram to run synchronously on the calling
-        // thread AND withdraws GL_KHR_parallel_shader_compile, so the single switch reverts
-        // both the threading and the application-visible behaviour change.
-        QuirkOverride AsyncShaderCompile = QuirkOverride::Auto;
-        // MOBILEGL_ASYNC_SHADER_COMPILE_THREADS: shader-compile worker count. 0 (unset) means
-        // auto, which is min(4, big cores); an explicit value is honoured as given.
-        Uint32 AsyncShaderCompileThreads = 0;
-        // MOBILEGL_ASYNC_OPTIMISTIC_SHADER_STATUS: while a compile job is still in flight,
-        // glGetShaderiv(GL_COMPILE_STATUS) answers GL_TRUE and the shader info log reads
-        // empty, WITHOUT joining the job (latched per compile - see
-        // ShaderObject::TakeOptimisticCompileAnswer). A deliberate, bounded spec violation:
-        // a real failure still fails the program link with the compile log quoted. It
-        // exists for applications that compile hundreds of shaders serially and read the
-        // status right after each glCompileShader - Iris's shader-pack load - where those
-        // per-shader joins are what serializes the batch on its main path (Iris's gbuffer
-        // phase issues no program-level query between programs; program-level LINK_STATUS
-        // and the program info log still join truthfully, so paths that check each link
-        // immediately stay serial by their own construction). Off by default; never
-        // advertise it.
-        QuirkOverride AsyncOptimisticShaderStatus = QuirkOverride::Auto;
-        // MOBILEGL_SHADER_CACHE: the three-level, in-memory shader translation memo
-        // (MG_Util/ShaderTranspiler/TranslationCache.h). The levels follow the GL
-        // entry points - L1c memoizes one glCompileShader's PARSE VERDICT, L1 a
-        // linked program's whole front end, L2 DirectGLES's emitted ESSL. Auto is
-        // ON; ForceOff turns ALL THREE off and makes every translation run from
-        // scratch. The escape hatch exists because a wrong cache hit is a silently
-        // miscompiled shader: if a device ever renders differently with the cache
-        // on, one run with this falsy says so.
-        QuirkOverride ShaderTranslationCache = QuirkOverride::Auto;
-        // MOBILEGL_ESPRYT_FORCE_VIEWPORT_ARRAY_EMULATION: DirectGLES' gl_ViewportIndex routing
-        // emulation - the builtin becomes a flat varying, the fragment stage gets a
-        // per-pass gate, and a routed draw is REPLAYED once per distinct viewport state
-        // with the real glViewport/glScissor/glDepthRangef set for it. Auto is ON, and
-        // it is ON even where the driver advertises GL_OES_viewport_array, because that
-        // extension only ever gave the SHADER a compilable name: MobileGL has never
-        // programmed a driver's INDEXED viewport state (SyncRenderState pushes index 0
-        // and nothing else), so on an extension-capable driver every index rasterized as
-        // index 0 exactly as it did without one. ForceOff returns to that behaviour -
-        // the pre-emulation path, extension passthrough where it exists and
-        // LowerViewportIndexPass' demote-to-a-plain-global where it does not - and is
-        // the negative control the emulation is measured against.
-        QuirkOverride EsprytViewportArrayEmulation = QuirkOverride::Auto;
-        // MOBILEGL_ESPRYT_WIDEN_PACKED16_STORAGE: DirectGLES stores GL_RGB565/GL_RGB5(A1)/GL_RGBA4
-        // images as 8-bit-per-channel ES storage (GL_RGB8/GL_RGBA8) instead of the driver's
-        // native 16-bit packed formats. Auto defers to a POST driver-bug probe
-        // (SelfTest::CopyImageMirrorsPacked16FieldOrder): some Mali drivers store SOME
-        // packed16 allocations with a MIRRORED field order (allocation-scoped and
-        // shape/context dependent - the failing 30x30x12 GL_TEXTURE_2D_ARRAYs are mirrored
-        // at every level), so glCopyImageSubData - a raw texel-block move - lands R/G/B/A
-        // reversed whenever exactly one endpoint sits in a mirrored allocation
-        // (KHR-GL4x.copy_image.functional rgb5/rgb5_a1/rgba4 x every *2d_array* pair).
-        // With no 16-bit packed ES image left there is no field order to disagree about; the
-        // client word still round-trips exactly, because the canonical shadow is already
-        // UNorm8 and an n-bit field encodes to UNorm8 and back losslessly for n <= 8.
-        // ForceOn widens on any driver (the llvmpipe suites use it to exercise the widened
-        // path); ForceOff keeps the native narrow storage even where the probe fires - the
-        // negative control that replays the corruption. Costs 2x the memory of the affected
-        // formats where it engages, which is why Auto is probe-gated rather than always-on.
-        QuirkOverride EsprytWidenPacked16Storage = QuirkOverride::Auto;
-        // MOBILEGL_MAGMA_PRIMGEN_QUERY_REROUTE: DirectVulkan's GL_PRIMITIVES_GENERATED
-        // reroute for draws made while transform feedback is INACTIVE. The stream query
-        // (VK_QUERY_TYPE_TRANSFORM_FEEDBACK_STREAM_EXT primitivesNeeded) is defined to count
-        // them, but a Mali driver - and Mesa lavapipe - answers 0 unless a capture span is
-        // open, which is exactly the shape the CTS uses to measure the tessellator, so ~29
-        // tessellation tests per tree size a capture buffer from the 0 and die on the
-        // zero-length map. Auto defers to a device probe at renderer bring-up
-        // (SelfTest::RunPrimitivesGeneratedNoXfbProbe), which measures two substitutes on
-        // the same capture-less draws and arms the best proven one: the dedicated
-        // VK_EXT_primitives_generated_query (exact semantics by definition; lavapipe passes
-        // it, rasterizer discard included), else a clipping-invocations pipeline-statistics
-        // pool (see the verdict vocabulary for its rasterizer-discard split). ForceOn pins
-        // the reroute structurally wherever a pool can exist (the arming-observable lane,
-        // immune to the probe's verdict moving), and ForceOff is the negative control that
-        // replays the driver's silence.
-        QuirkOverride MagmaPrimGenQueryReroute = QuirkOverride::Auto;
-        // --- MGPipe (the disaggregation plan's explicit frontend/backend boundary) ---
-        // MOBILEGL_PIPE_PUSH: per-subsystem bitmask selecting which state the frontend
-        // PUSHES over MGPipe instead of leaving the backend to pull it out of GLContext.
-        // 0 - the only shipped value until the migration lands - is "pull everything",
-        // i.e. exactly today's behaviour, and is the default of a PULL build, where the
-        // knob is meaningless anyway. A PUSH build defaults to every subsystem migrated so
-        // far (MG_Pipe::kMGPipeSubsystemsMigratedAtP5e = 0x3fff), so MOBILEGL_PIPE_PUSH=0 in
-        // the environment is the all-pull control and 0x1fff (kMGPipeSubsystemsMigratedAtP4a)
-        // is the "everything before P5e" control P5e's A/B is run against - each phase's
-        // constant survives as the next phase's control, which is why none of them is ever
-        // edited. Accepts decimal or 0x-prefixed hex, and operators pass it as hex, so the
-        // bits are listed here (MG_Pipe/MGPipe.h owns them):
-        //   0x01 render state (create/bind_render_state + set_dynamic_state)
-        //   0x02 pixel pack        0x04 patch state      0x08 vertex attrib defaults
-        //   0x10 residual values   0x20 Espryt slots     0x40 Magma vertex input
-        //   0x80 resources (the resource_* family: the seven BufferBackendOps hooks)
-        //   0x100 vertex input (vertex elements / vertex buffers / index buffer)
-        //   0x200 framebuffer (set_framebuffer_state)              - requires 0x400
-        //   0x400 texture resources (texture + renderbuffer resource_*,
-        //         set_texture_params)                              - requires 0x80 AND 0x800
-        //         (the built-in sampler CSO a set_texture_params record names is minted by
-        //         the sampler family alone, ID-15; the four rows are MG_Impl/Pipe/PipeFill.cpp's
-        //         kMGPipeP4aFamilyDependencies, mirrored bit for bit by Espryt's resolvers)
-        //   0x800 samplers (sampler CSO, sampler view, set_sampler_views /
-        //         bind_sampler_states / set_shader_images)         - requires 0x400
-        //   0x1000 programs (shader CSO, set_draw/dispatch_program, global constants)
-        //   0x2000 buffer binding points (set_shader_buffers, the three indexed binding-point
-        //         classes and the dirty bits 15/16/17)             - requires 0x80
-        //         (every MGPBufferRange::Res names a Buffer handle; P5e)
-        //   A dependency that is not met is REFUSED with one ERROR naming both bits and the
-        //   family runs its legacy arm; it is never half-run.
-        //   1<<63 NOT a subsystem, a BEHAVIOUR: turn OFF client-side content addressing of
-        //         CSOs, so every pipeline-version change mints a fresh CSO and the map is
-        //         never probed. The negative control the CSO design is measured against.
-        Uint64 PipePush = 0;
-        // MOBILEGL_PIPE_VERIFY: per-draw, per-FIELD shadow comparison of the pushed state
-        // against a snapshot taken from GLContext the old way, printing the first field
-        // that differs and the draw serial. Roughly 5-10x slower and never shipped; it is
-        // the semantic gate that replaces byte identity, and it catches the dangerous
-        // direction - a dirty bit that fires too RARELY - which no purity gate can see.
-        Bool PipeVerify = false;
-#if MOBILEGL_PIPE_PUSH
-        // The three knobs of the MOBILEGL_PIPE_VERIFY build (P1 brief D2). Compiled only
-        // under MOBILEGL_PIPE_PUSH so the pull build's FeaturesTable does not change size.
-        // MOBILEGL_PIPE_VERIFY_FATAL: the first divergence aborts (default). 0 logs and
-        // counts instead, for triage and for the lane that must survive to read its own
-        // log. Tri-state parse like PipeLegacyMemos: only an explicit falsy value turns it
-        // off.
-        Bool PipeVerifyFatal = true;
-        // MOBILEGL_PIPE_VERIFY_CORRUPT: a field name from kMGPipeInputFieldNames[]; the
-        // comparator perturbs that field in the SNAPSHOT arm before the entry compare, so a
-        // green verify run goes red naming it (negative control A). Unknown name is
-        // Fatal{PipeVerifyBadKnob}.
-        String PipeVerifyCorrupt;
-        // MOBILEGL_PIPE_POISON_OMIT: <Verb>:<FieldName>; the filler skips the STAMP (not
-        // the value) of that field for that verb, an omission indistinguishable from a
-        // forgotten FillPoints.def row, so that verb's read of it is
-        // Fatal{UnmigratedPipeInput} (negative control B). Unknown name is
-        // Fatal{PipeVerifyBadKnob}.
-        String PipePoisonOmit;
-        // MOBILEGL_PIPE_HANDLE_ABA_CONTROL (negative control C, P2 brief D18): replace the
-        // OBJECT IDENTITY in every DirectVulkan vertex-input memo key with a constant, on
-        // whichever arm the run is on - the pre-handle (address, lifetime id) pair AND the
-        // handle arm's {slot, gen} generation - so a replacement object inherits its dead
-        // predecessor's resolved vertex bindings and HandleRecycleScenario.AbaControl asserts
-        // the WRONG pixels. That is what proves the reproducer still reproduces. D18 wrote
-        // this as "hash the raw BufferObject* instead of its lifetime id"; measured, the heap
-        // block is never handed back, so that spelling collided with nothing and the control
-        // went vacuous - see MagmaPipeArms.h's MagmaPipeAbaControlDefeatsIdentity for the
-        // measurement and for what the control still leaves standing. Under
-        // MOBILEGL_PIPE_PUSH only, so it cannot exist in a shipping pull build.
-        Bool PipeHandleAbaControl = false;
-#endif
-        // MOBILEGL_PIPE_STATS: dump the boundary counters (bytes, calls, roundtrips,
-        // texture pulls, upload shapes, residual-block bytes, index mirror bytes).
-        Bool PipeStats = false;
-        // MOBILEGL_PIPE_LEGACY_MEMOS: keep the pre-handle registries and TwinLookupMemos
-        // alive so the first handle waves have a real old-versus-new arm to be compared
-        // against. ON by default for the whole migration window, deleted with the pull
-        // path itself.
-        Bool PipeLegacyMemos = true;
-        // MOBILEGL_PIPE_TEXEL_RETAIN_MB: LRU budget for texels retained against a
-        // server-initiated texture re-send. Default 0, i.e. OFF: MipmapStorage already
-        // holds a complete CPU shadow, so this cache buys latency, never correctness.
-        Uint32 PipeTexelRetainMb = 0;
-        // MOBILEGL_PIPE_INDEX_MIRROR_MB: budget for the server-side index host mirror,
-        // which is what lets primitive-restart rewriting and multi-draw flattening stay on
-        // the server without shipping index bytes per draw. Over budget it degrades to
-        // per-draw staging, counted separately in the stats.
-        Uint32 PipeIndexMirrorMb = 64;
-        // MOBILEGL_PIPE_STATS_PERIOD: frames per boundary-counter summary line. 120 is the
-        // steady-state cadence; the device retrace harness never reaches the teardown dump
-        // and a trimmed fixture (create-indirect) is shorter than 120 frames, so a run that
-        // needs its numbers at all sets this low enough to land at least one window.
-        Uint32 PipeStatsPeriod = 120;
-        // MOBILEGL_PIPE_STATS_FILE: where the boundary counters' teardown JSON dump goes.
-        // Empty (the default) means no dump; the per-120-frame summary line still goes to
-        // the log whenever PipeStats is on, so a device run needs no writable path.
-        String PipeStatsFile;
     };
     extern FeaturesTable Features;
-
-    // ---------------------------------------------------------------------------------
-    // P5: the transport selector and the MOBILEGL_IPC_* family (ARCHITECTURE.md 16, 附 A)
-    // ---------------------------------------------------------------------------------
-    //
-    // MOBILEGL_TRANSPORT = monolith | inproc | spawn | unix:<path> | pipe:<name>.
-    //
-    // WHY `Transport` IS NOT A FeaturesTable MEMBER. ARCHITECTURE.md:580 requires that with
-    // MOBILEGL_BUILD_DISAGGREGATED=OFF it be a `constexpr Monolith`, so that the single hook
-    // in MG_Backend/Init.cpp compiles away entirely rather than becoming a branch nobody can
-    // take. A FeaturesTable member is a runtime field in every build, which is the opposite
-    // of that; it would also resize MG_Config::Features and break G1 (the pull build's
-    // symbol set must not move) for the same reason the MOBILEGL_PIPE_VERIFY knobs above sit
-    // behind their own #if.
-    //
-    // ONE CONSEQUENCE, STATED SO IT IS NOT REDISCOVERED: in a build without the option,
-    // MOBILEGL_TRANSPORT=inproc is ACCEPTED BY THE ENVIRONMENT AND SILENTLY IGNORED - the
-    // parser below does not exist to complain about it, and putting a complaint in the
-    // unconditional part of ConfigLoader would move a pull-build symbol. That is the exact
-    // shape of "the split lane ran monolith and went green", so the gate against it is a
-    // BUILD-level check, not a runtime one: `nm --defined-only libMobileGL.so | grep -i
-    // MG_Remote` must be non-empty in build-split (CONTRACT-P5.md table 3, and the CI job
-    // P5 adds beside build-linux-verify).
-    enum class TransportMode : Uint8 {
-        Monolith = 0,  // today's in-library backend; no MG_Remote object is constructed
-        InProcess = 1, // P5: a real apply thread in this process, over the same G3 codec
-        Spawn = 2,     // P6: fork/exec MobileGLServer, socketpair
-        UnixSocket = 3,// P6: connect to an existing AF_UNIX endpoint (Endpoint = <path>)
-        NamedPipe = 4, // P6: Windows named pipe (Endpoint = <name>)
-    };
-
-#if MOBILEGL_BUILD_DISAGGREGATED
-    // Parsed once by MG_ConfigLoader::Init(). Defaults to Monolith even here: building the
-    // transport in is not the same as using it, and every existing lane of a build-split
-    // must keep running monolith unless it is asked for one.
-    extern TransportMode Transport;
-    // The <path> of `unix:` / the <name> of `pipe:`. Empty for the other three modes.
-    extern String TransportEndpoint;
-
-    // P7 F1. DID **THIS PROCESS'S OWN CONFIGURATION** ASK FOR A SPLIT TRANSPORT.
-    //
-    // `Transport` alone cannot answer that, and the difference is exactly the one the F1 gate
-    // turns on. A unit fixture assigns `Transport` by hand to put the code under test on its
-    // split arm (ServerLoopTest's main does, and says why) while building no client at all; a
-    // real run gets it from MG_ConfigLoader::Init(), and that run WILL bring a client half up.
-    // Only the second may be held to "never decide a record family's fate from a placeholder
-    // caps mirror" - in the first there is no handshake, no mirror to adopt and nothing the
-    // rule could mean.
-    //
-    // Written once, by InitTransport(), and never cleared: a process does not stop having been
-    // configured. Read by MG_Remote::Client::CapsMirror::RequireFirstSnapshot.
-    extern Bool SplitTransportRequestedByConfig;
-
-    // The MOBILEGL_IPC_* family. A separate table rather than more FeaturesTable members,
-    // for the G1 reason above and because every field here is meaningless without the
-    // transport: a build that cannot reach the MG_Remote code cannot honour one of them.
-    //
-    // P5 lands exactly the knobs P5's own packages read. A later phase's knob is added HERE,
-    // through the integrator, and not invented at its call site - ARCHITECTURE.md:615 holds
-    // the full planned inventory (PRESENT_CREDIT, POLL_ESCALATE, SHADOW_SHM,
-    // INLINE_PAYLOADS, TRACE, ATTACH, RESPAWN, IDLE_EXIT_S), and every one of those belongs
-    // to P6 or later.
-    //
-    // P12 (on-screen server window): MOBILEGL_IPC_SURFACE's two values. See IpcTable::Surface.
-    enum class IpcSurface : Uint8 {
-        Offscreen = 0, // a window surface is the client's own window, as before (the default)
-        Server = 1,    // a window surface is the SERVER's window: WindowKind::ServerOwned
-    };
-    struct IpcTable {
-        // MOBILEGL_IPC_SERVER_PATH: where to find libMobileGLServer. P6 consumes it; P5
-        // lands the parse because t1's ctest ENVIRONMENT blocks and add_trace_replay_test's
-        // SPLIT variant already carry it, and an environment variable that nothing parses is
-        // indistinguishable from one that is parsed and ignored.
-        String ServerPath;
-        // Control endpoint and data-plane selection are independent of topology.
-        String Control = "fork"; // fork | unix:<path> | tcp://host:port
-        String Data = "auto";    // auto | shm | stream
-        // MOBILEGL_IPC_RING_MB: SEG_CMD size. A RECORD MAY BE AT MOST HALF OF THIS
-        // (RingProducer::MaxRecordBytes), so 8 MiB caps one record at 4 MiB; R-10 makes the
-        // codec publish a max-record-bytes counter rather than assume that is enough.
-        Uint32 RingMb = 8;
-        // MOBILEGL_IPC_STAGE_MB: SEG_STAGE size. Every blob and every var-tail's bytes live
-        // here ONE BLOB AT A TIME: a row whose content can outgrow the segment cuts it at the
-        // stage chunk budget (MGPipeStageChunkBytes, a quarter of this), and a record type with
-        // no cut is Fatal{RingOverrun, "SEG_STAGE"} rather than allowed to exceed it.
-        Uint32 StageMb = 32;
-        // MOBILEGL_IPC_WIRE_DEFERRED_MB (P7 wave 4 M2, ID-P7-32): the SERVER's budget, in MiB,
-        // for orphaned wire buffer stores - the old VkBuffer every glBufferData that crosses the
-        // wire leaves behind - that a GPU command recorded but not yet retired may still name.
-        // Stores no command names are destroyed at once and stores whose last submission has
-        // retired are destroyed at the next park; this bounds the REST. When the parked bytes
-        // exceed it after a sweep, the server flushes what it has recorded and waits for it
-        // (WaitForWireBufferHostAccess's sync point, mid-frame), which retires every one. It is
-        // not a frame count because a frame is not bounded: a snapshot-exiting pbuffer replay
-        // delivers one present for 1.3 M calls. The same sync point also fires above a fixed
-        // 1024 parked stores (VkBufferManager::kWireDeferredCountCeiling), because small
-        // orphans never reach a byte budget. 0 IS THE NEGATIVE CONTROL for both, not "unlimited
-        // by design": no forced sync, so a one-frame respecify-and-draw loop grows without bound
-        // and MagmaWireReclaimScenario's watermark cases must go red.
-        Uint32 WireDeferredMb = 64;
-        // MOBILEGL_IPC_SPIN_US: spin before parking on a doorbell, either direction.
-        Uint32 SpinUs = 50;
-        // MOBILEGL_IPC_EVENT_WAIT_MS (PH-6, ID-P7-2): the SERVER's patience, in ms, for ONE
-        // reverse-channel event that finds SEG_EVENT full under run-ahead. The apply thread
-        // publishes, rings the client and parks until the client drains enough room; a client
-        // that has not made room when this runs out - it stopped draining (NotDraining) or it
-        // drains a slot at a time (TooSlow) - FORFEITS the reverse channel: that event and every
-        // later one is dropped and counted (eventDropped), and the session stops by the ordinary
-        // stop path rather than by Fatal{EventRingOverflow}. A peer that goes away (PeerGone) or
-        // a session that is stopped (Stopped) ends the wait at once instead, so the knob may
-        // exceed ServerLoop::Stop()'s 5000 ms join. It bounds the whole reservation, not one
-        // park, so a trickling peer cannot stretch it - nor can a shm peer that writes the
-        // (peer-writable) eventRingFull latch to 0 itself, though that one keeps the apply
-        // thread spinning rather than parked until the budget runs out. Was a 30000 ms constant
-        // spent twice. Read by the server only (ServerSpawn.cpp passes it to a spawned child);
-        // the lockstep arm (no kCapRunAheadApply, i.e. Magma) never waits and keeps P5C's Fatal.
-        Uint32 EventWaitMs = 2000;
-        // MOBILEGL_IPC_PERSISTENT_BLOCK_KB: block granularity of the persistent-map push.
-        // 0 IS A NEGATIVE CONTROL, NOT "unlimited": it disables the push, and
-        // PersistentCoherentMapScenario must go RED under it (exit gate E3(a)).
-        Uint32 PersistentBlockKb = 64;
-        // MOBILEGL_IPC_PERSISTENT_HASH_SUPPRESS: 1 = the persistent-map push ships only
-        // blocks whose xxHash64 changed since the last push, instead of the whole mapped
-        // range every verb. 0 restores the whole-range push (A/B control).
-        Uint32 PersistentHashSuppress = 1;
-        // MOBILEGL_IPC_BATCH_WAITS: 1 = value-class records (kCtxState / kCtxCso / kCtxObject
-        // with no reply slot) are published without waiting for their own apply; the barrier
-        // is taken at the next pull-reading verb (kCtxVerb syncs, queries, screen rows, and
-        // every reply-slot row), which is the only place BARRIER-PULLED fields are read. 0
-        // restores the per-record barrier of R-1.
-        Uint32 BatchWaits = 1;
-        // MOBILEGL_IPC_CREATE_WINDOW: how many RESOURCE_CREATE answers may be outstanding before the
-        // client waits for one. 1 = every create waits (the shape R-5 shipped with); N > 1 = up to N
-        // creates go out fire-and-forget, their caller reads a PROVISIONAL accept, and the oldest
-        // answer is taken when the window fills.
-        //
-        // DEFAULT 2, AND IT TOOK THREE THINGS TO GET HERE. The deferral was inert for two
-        // measured reasons and one structural one, in the order they were found:
-        //   1. the reply buffer was a ring of the last 8 answers, and between two creates this
-        //      client emits on the order of a thousand records - so the answer was always gone
-        //      (`want=310` on every miss while the ring spanned [1175..1504]);
-        //   2. a residency budget that tried to take answers back early could not help, because
-        //      what displaces an answer is what the SERVER sends, not what the client emits;
-        //   3. and so the fix was RETENTION - a link keeps a declared answer until its reader
-        //      takes it (Transport/ILink.h's RetainsReplies, StreamLink's declared-answer store).
-        //
-        // MEASURED ON THE DEVICE, load frame, both ends rebuilt (create 4,536, records 103,097,
-        // frame-sent identical per op throughout):
-        //     window 1    4,536 blocking takes   28.66 s   (the shape R-5 shipped)
-        //     window 2      2,500               17.27 s
-        //     window 4      1,644               11.02 s
-        // and the round trip does NOT grow as the window deepens (5,285 / 4,082 us against 5,672
-        // at 1), which is the measurement that says the ~5 ms is a WAKEUP the server batches away
-        // rather than its apply throughput - so amortising four creates per wakeup is a real 2.6x.
-        //
-        // 6 IS THE DEFAULT, AND IT IS WHERE THE CURVE FLATTENS - the sweep that says so is the
-        // one the paragraph above asked for, and it moved the ceiling too (kCreateWindowMax is 8
-        // now; the old 4 was derived from a reply pool the window does not run on). Three
-        // interleaved runs per arm on one binary, load frame, create 4,536 sent in every arm:
-        //
-        //     window 4   1,503 blocking takes   13.23 s median   (spread 11.37-16.29)
-        //     window 5   1,277                  11.31 s          (10.61-12.12)
-        //     window 6   1,155                  10.79 s          ( 9.69-10.81)
-        //     window 8     859                  10.96 s          ( 8.92-11.03)
-        //
-        // 4->5 buys 1.92 s, 5->6 buys 0.53 s, 6->8 buys NOTHING (-0.18 s, inside a session noise
-        // of ~1.5-2 s) - so 6 is the smallest window on the flat part and the extra answers a
-        // deeper one holds buy no time. AND PAST THIS POINT THE FRAME IS NOT WAIT-BOUND ANY MORE:
-        // window 8 pays 296 fewer blocking takes than window 6 and the wall clock does not move.
-        // The store is not the constraint either - its peak is logged as it crosses (StreamLink's
-        // P12 line) and reads 6..11 against a cap of 24 at every arm from 5 up. What is left is
-        // the constant ~350-400 creates that block for a reason depth does not reach, and the
-        // 101 MB / 103k records the SERVER has to apply. NOTE THE PREDICATE the whole mechanism rests
-        // on: an answer is retained because the wire DECLARED it will be read - NOT because its
-        // caller was fire-and-forget. The window's own creates are fire-and-forget AND read, so a
-        // flag keyed on wantReply would disable the very mechanism it exists to enable
-        // (docs/Disaggregated/notes/p12/CREATE-WINDOW-MEASURED.md sections 7-11).
-        Uint32 CreateWindow = 10;
-        // MOBILEGL_IPC_ADOPT_TIER: 2 = emulate (client keeps the shadow and pushes), which
-        // is the only tier P5 implements and the reason persistent-map-push can be non-zero
-        // at all (R-6). 0 and 1 parse and are Fatal at use with "P11"; they exist now so the
-        // negative control has a spelling the day P11 writes it.
-        Uint32 AdoptTier = 2;
-        // MOBILEGL_IPC_VERB_BARRIER: 1 = the client blocks at every verb boundary until
-        // appliedSeq reaches its emitSeq (R-1). 0 is the negative control: it is EXPECTED to
-        // be red, because 31 of the 63 PipeInputs fields are still pulled from a live
-        // GLContext by the client's residual fill and a free-running queue lets the server
-        // read a FUTURE value of them.
-        Uint32 VerbBarrier = 1;
-        // MOBILEGL_IPC_RUN_AHEAD (P5e, MG_Remote/CONTRACT-P5E.md §1): 1 = after publishing an
-        // UNBARRIERED record the client returns immediately instead of waiting for its apply.
-        // It is one half of a conjunction and never a switch on its own - the client arms
-        // run-ahead only when the server also publishes kCapRunAheadApply, so on Magma, and on
-        // Espryt before the P5e integration commit, 1 means exactly what 0 means and logs once
-        // saying so.
-        //
-        // 0 IS THE A/B CONTROL AND NOT A NEGATIVE ONE: the server code, the fill decision and
-        // every record are identical on both arms, and the only difference is whether the
-        // client waits. That is what makes "is the picture the same" a question about the wait
-        // rule alone. MOBILEGL_IPC_VERB_BARRIER=0 keeps its own meaning and stays the
-        // lockstep arm's negative control; under run-ahead it is the one that must go red, at
-        // the first barriered row's stale pull.
-        //
-        // Forced to 0 by MOBILEGL_PIPE_VERIFY, beside BatchWaits: the comparator needs a
-        // client-filled gPipeInputs block for every verb, and run-ahead is precisely the
-        // arm that stops filling it.
-        Uint32 RunAhead = 1;
-        // MOBILEGL_IPC_PRESENT_CREDIT (P5e, ruling 4 / ID-92): how many presents the client may
-        // have in flight before it waits for a swap to come back. 1 = the client publishes
-        // frame N+1's records while the server applies and swaps frame N - one frame of
-        // overlap, at most one frame of added latency - and the CREDIT, never the ring's bytes,
-        // is what paces a run-ahead client. 2 is a device MEASUREMENT arm: it buys no CPU on a
-        // client that is already CPU-bound and costs a frame of latency, which is why the
-        // default is 1 and not "as deep as the ring".
-        Uint32 PresentCredit = 1;
-        // MOBILEGL_IPC_CONTROL_TIMEOUT_MS (CONTRACT-P6 §5.4 D5b): how long a spawn/tcp client
-        // waits for the SurfaceReply to one surface-control op (eglCreate*Surface, MakeCurrent,
-        // ...) once the server's backend is up. Its expiry is NOT fatal: the doorbell's death
-        // latch decides dead (device lost) from alive-but-silent (a named diagnostic). The
-        // contract named this knob from P6 on; the client hard-coded its default until P7.
-        Uint32 ControlTimeoutMs = 5000;
-        // MOBILEGL_IPC_COLD_START_MS (P7): the same wait for the three ops a server may bring its
-        // NATIVE backend up inside - CreatePbufferSurface, CreateWindowSurface, MakeCurrent -
-        // until the session's first MakeCurrent is answered ok. The bring-up is lazy (Espryt's
-        // eglInitialize, Magma's Vulkan instance and device), ~100 ms on a workstation and more
-        // than the steady 5 s on a loaded CI runner (retrace-split spawn legs, runs 35671704873
-        // and 35706183230). Never shorter than CONTROL_TIMEOUT_MS; its expiry is the same
-        // non-fatal named answer. The default is the spawn connect budget, for the same reason:
-        // "the server has to create a backend, and a cold software rasteriser is not fast".
-        Uint32 ColdStartMs = 20000;
-        // MOBILEGL_IPC_STRICT_ERRORS: promote a BARRIER-PULLED field read - and, in a split
-        // build, the seven sticky forwards that are otherwise exempt - from "count it in
-        // rsp" to Fatal (R-7.3).
-        Bool StrictErrors = false;
-        // MOBILEGL_IPC_ROLE_SPLIT_STATE (P5f f1, P5F-WIRE-COMPLETENESS.md §4): the dual-block
-        // rehearsal. 1 = the client's residual fill writes a CLIENT-ROLE PipeInputs block and
-        // the backend/applier keep reading the SERVER-ROLE one, so every path that today works
-        // only because the two roles share one object turns into a named
-        // Fatal{UnmigratedPipeInput, "<field>@<verb>"} instead of a silent cross-role read.
-        // Meaningless under monolith transport (the two roles are one thread there, so the
-        // selection folds to the single shared block) and forced off by MOBILEGL_PIPE_VERIFY
-        // (the comparator owns the one fill block it compares against). 0 is not merely the
-        // default, it is the negative control: the lane's distinctness case must go red
-        // without it (P5F §6).
-        Bool RoleSplitState = false;
-        // MOBILEGL_IPC_AUDIT: after a record retires, the server fills the SEG_STAGE bytes
-        // it referenced with 0xDD (R-2.5). This is the ONLY mechanical control that an
-        // inproc implementation did not quietly keep using a pointer past its lifetime.
-        Bool Audit = false;
-        // MOBILEGL_IPC_SERVER_AFFINITY: `auto` (the default, big-core detection borrowed
-        // from ShaderCompilePool), `off`, or an explicit CPU mask. Kept as the raw string
-        // because the resolved mask is logged by whoever starts the apply thread, and the
-        // string is what an operator typed.
-        String ServerAffinity = "auto";
-        // MOBILEGL_IPC_SURFACE (P12, on-screen server window) = offscreen | server. `server` makes
-        // the client a HEADLESS one: eglCreateWindowSurface / eglCreatePlatformWindowSurface accept
-        // any native window including NULL, send ONE CreateWindowSurface naming
-        // WindowKind::ServerOwned (token 0, the size from EGL_WIDTH/EGL_HEIGHT, 0/0 = the server's
-        // own) and no SetWindowHandle, and take the surface's real geometry back from the server.
-        // Meaningful only when this client talks to a remote server (MOBILEGL_TRANSPORT=spawn, the
-        // fork or tcp:// control); under monolith / inproc it is parsed, logged as ignored, and
-        // changes nothing. `offscreen` (the default) is today's behaviour byte for byte.
-        // Pbuffers stay pbuffers in both modes (D4: one mode per session, decided by the first).
-        IpcSurface Surface = IpcSurface::Offscreen;
-    };
-    extern IpcTable Ipc;
-
-    // P12: the one predicate every client-side consumer of MOBILEGL_IPC_SURFACE asks - a window
-    // surface is the server's when the knob says so AND there is a remote server to own it.
-    inline Bool ServerOwnedWindowSurfaces() {
-        return Transport == TransportMode::Spawn && Ipc.Surface == IpcSurface::Server;
-    }
-#else
-    // The whole point: in a build without MG_Remote this folds at compile time, so
-    // `if (MG_Config::Transport != MG_Config::TransportMode::Monolith)` in Init.cpp is a
-    // discarded statement and the pull build gains no symbol, no branch and no byte.
-    inline constexpr TransportMode Transport = TransportMode::Monolith;
-#endif
 } // namespace MobileGL::MG_Config

MobileGL/ConfigLoader.cpp

@@ -7,20 +7,9 @@
 // End of Source File Header
 
 #include "Config.h"
-#if MOBILEGL_PIPE_PUSH
-// For kMGPipeSubsystemsMigratedAtP5e, the push build's PipePush default (the P2, P3a and P4a
-// constants beside it are the phase-by-phase controls, not the default). Push-only, so the
-// pull build's translation unit is unchanged.
-#include <MG_Pipe/MGPipe.h>
-#endif
 
 #include <cerrno>
 #include <cstdlib>
-#if MOBILEGL_BUILD_DISAGGREGATED
-// std::strcmp, for InitIpc's server-role check (P12). Split-only, so the pull build's TU is
-// unchanged (G1).
-#include <cstring>
-#endif
 
 #ifndef _WIN32
 extern char** environ;
@@ -30,16 +19,6 @@ namespace MobileGL::MG_Config {
     // Zero/default-initialized at static-init time (all fields have constexpr-friendly
     // defaults), so it is safe to read even if MG_ConfigLoader::Init has not run yet.
     FeaturesTable Features;
-#if MOBILEGL_BUILD_DISAGGREGATED
-    // Same contract, and for the same reason: MG_Backend::Init() reads Transport, and a
-    // build order that put it before MG_ConfigLoader::Init() must see Monolith rather than
-    // a torn enum. Defined only here - in a pull build Config.h makes Transport a constexpr
-    // and there is nothing to define.
-    TransportMode Transport = TransportMode::Monolith;
-    String TransportEndpoint;
-    Bool SplitTransportRequestedByConfig = false;
-    IpcTable Ipc;
-#endif
 } // namespace MobileGL::MG_Config
 
 namespace MobileGL::MG_ConfigLoader {
@@ -107,58 +86,6 @@ namespace MobileGL::MG_ConfigLoader {
         return it != acceptedEnvVariablesMap->end() && IsTruthyValue(it->second);
     }
 
-    // Quirk overrides are tri-state: an unset variable keeps device auto-detection, a truthy
-    // value forces the quirk on, anything else set ("0", "false", "") forces it off.
-    inline MG_Config::QuirkOverride QueryEnvQuirkOverride(const String& key) {
-        auto it = acceptedEnvVariablesMap->find(key);
-        if (it == acceptedEnvVariablesMap->end()) {
-            return MG_Config::QuirkOverride::Auto;
-        }
-        return IsTruthyValue(it->second) ? MG_Config::QuirkOverride::ForceOn
-                                         : MG_Config::QuirkOverride::ForceOff;
-    }
-
-    // Multi-draw mode is a named-value preference: unset keeps Auto (best supported tier),
-    // a recognized name selects that tier as the ceiling, anything else warns and keeps Auto.
-    inline MG_Config::MultiDrawMode QueryEnvMultiDrawMode(const String& key) {
-        auto it = acceptedEnvVariablesMap->find(key);
-        if (it == acceptedEnvVariablesMap->end()) {
-            return MG_Config::MultiDrawMode::Auto;
-        }
-        String lowered = it->second;
-        std::transform(lowered.begin(), lowered.end(), lowered.begin(),
-                       [](unsigned char c) { return static_cast<char>(std::tolower(c)); });
-        if (lowered == "ext") return MG_Config::MultiDrawMode::Ext;
-        if (lowered == "indirect") return MG_Config::MultiDrawMode::Indirect;
-        if (lowered == "unroll") return MG_Config::MultiDrawMode::Unroll;
-        if (lowered.empty() || lowered == "auto") return MG_Config::MultiDrawMode::Auto;
-        MGLOG_W("Config: Ignoring invalid env variable %s='%s'; expected ext|indirect|unroll|auto, using auto",
-                key.c_str(), it->second.c_str());
-        return MG_Config::MultiDrawMode::Auto;
-    }
-
-    // Same contract as QueryEnvMultiDrawMode, over the DirectGLES tier names.
-    inline MG_Config::GLESMultiDrawMode QueryEnvGLESMultiDrawMode(const String& key) {
-        auto it = acceptedEnvVariablesMap->find(key);
-        if (it == acceptedEnvVariablesMap->end()) {
-            return MG_Config::GLESMultiDrawMode::Auto;
-        }
-        String lowered = it->second;
-        std::transform(lowered.begin(), lowered.end(), lowered.begin(),
-                       [](unsigned char c) { return static_cast<char>(std::tolower(c)); });
-        if (lowered == "ext") return MG_Config::GLESMultiDrawMode::Ext;
-        if (lowered == "multiindirect") return MG_Config::GLESMultiDrawMode::MultiIndirect;
-        if (lowered == "indirect") return MG_Config::GLESMultiDrawMode::Indirect;
-        if (lowered == "basevertex") return MG_Config::GLESMultiDrawMode::BaseVertex;
-        if (lowered == "drawelements") return MG_Config::GLESMultiDrawMode::DrawElements;
-        if (lowered == "compute") return MG_Config::GLESMultiDrawMode::Compute;
-        if (lowered.empty() || lowered == "auto") return MG_Config::GLESMultiDrawMode::Auto;
-        MGLOG_W("Config: Ignoring invalid env variable %s='%s'; expected "
-                "ext|multiindirect|indirect|basevertex|drawelements|compute|auto, using auto",
-                key.c_str(), it->second.c_str());
-        return MG_Config::GLESMultiDrawMode::Auto;
-    }
-
     inline Uint32 QueryEnvUint32(const String& key, Uint32 defaultValue, Uint32 minValue, Uint32 maxValue) {
         auto it = acceptedEnvVariablesMap->find(key);
         if (it == acceptedEnvVariablesMap->end()) {
@@ -180,120 +107,22 @@ namespace MobileGL::MG_ConfigLoader {
         return static_cast<Uint32>(parsedValue);
     }
 
-    // Same contract as QueryEnvUint32, over 64 bits and accepting an explicit 0x prefix: the
-    // one consumer is a subsystem BITMASK, and a bitmask written in decimal is unreadable.
-    // Decimal otherwise - never strtoull's base 0, whose "leading zero means octal" rule
-    // silently read MOBILEGL_PIPE_PUSH=010 as 8 - and a '-' anywhere is rejected rather than
-    // wrapped, which strtoull would otherwise do without complaint (-1 -> every bit set).
-    inline Uint64 QueryEnvUint64(const String& key, Uint64 defaultValue) {
-        auto it = acceptedEnvVariablesMap->find(key);
-        if (it == acceptedEnvVariablesMap->end()) {
-            return defaultValue;
-        }
-
-        const String& value = it->second;
-        const char* text = value.c_str();
-        int base = 10;
-        if (value.size() > 2 && text[0] == '0' && (text[1] == 'x' || text[1] == 'X')) {
-            text += 2;
-            base = 16;
-        }
-        char* parseEnd = nullptr;
-        errno = 0;
-        const bool negative = value.find('-') != String::npos;
-        const unsigned long long parsedValue = negative ? 0 : std::strtoull(text, &parseEnd, base);
-        if (negative || parseEnd == text || *parseEnd != '\0' || errno == ERANGE) {
-            MGLOG_W("Config: Ignoring invalid env variable %s='%s'; expected a non-negative integer "
-                    "(decimal, or 0x-prefixed hexadecimal), using default %llu",
-                    key.c_str(), value.c_str(), static_cast<unsigned long long>(defaultValue));
-            return defaultValue;
-        }
-
-        return static_cast<Uint64>(parsedValue);
-    }
-
     inline void InitFeatures() {
         auto& features = MG_Config::Features;
         features.DisableTimerQuery = QueryEnvFlag("MOBILEGL_DISABLE_TIMERQUERY");
-        features.EsprytEnableTextureView = QueryEnvFlag("MOBILEGL_ESPRYT_ENABLE_TEXTURE_VIEW");
-        features.EnableSpirvValidation = QueryEnvFlag("MOBILEGL_ENABLE_SPIRV_VALIDATION");
-        features.EsprytUseAngle = QueryEnvFlag("MOBILEGL_ESPRYT_USE_ANGLE");
+        features.UseAngle = QueryEnvFlag("MOBILEGL_USE_ANGLE");
 #if defined(MOBILEGL_TRACE_ANGLE_VARIANTS)
         QueryEnvVariable("MOBILEGL_TRACE_ANGLE_VARIANT", features.TraceAngleVariant, "");
 #endif
-        features.MagmaDisableSubgroup = QueryEnvFlag("MOBILEGL_MAGMA_DISABLE_SUBGROUP");
-        features.MagmaEmulateSubgroup = QueryEnvFlag("MOBILEGL_MAGMA_EMULATE_SUBGROUP");
-        features.MagmaFixIterationRPSubgroupScratch =
-            QueryEnvQuirkOverride("MOBILEGL_MAGMA_FIX_ITERATIONRP_SUBGROUP_SCRATCH");
-        features.MagmaIterationRPFixBarrier = QueryEnvFlag("MOBILEGL_MAGMA_ITERATIONRP_FIX_BARRIER");
-        features.MagmaDeriveNumSubgroups = QueryEnvQuirkOverride("MOBILEGL_MAGMA_DERIVE_NUM_SUBGROUPS");
-        features.AdvertiseFp64 = QueryEnvFlag("MOBILEGL_ADVERTISE_FP64");
+        features.DisableSubgroup = QueryEnvFlag("MOBILEGL_DISABLE_SUBGROUP");
         features.MagmaR11G11B10FFallback = QueryEnvFlag("MOBILEGL_MAGMA_R11G11B10F_FALLBACK");
         features.MagmaFramesInFlight = QueryEnvUint32("MOBILEGL_MAGMA_FRAMESINFLIGHT", 3, 1, 64);
-        features.EsprytAvoidSamplerMipmapMinFilter =
-            QueryEnvFlag("MOBILEGL_ESPRYT_AVOID_SAMPLER_MIPMAP_MIN_FILTER");
-        features.EsprytAvoidExplicitLodBias = QueryEnvFlag("MOBILEGL_ESPRYT_AVOID_EXPLICIT_LOD_BIAS");
-        features.EsprytUnlocatedIoBlocks = QueryEnvQuirkOverride("MOBILEGL_ESPRYT_UNLOCATED_IO_BLOCKS");
-        features.PointSizeDemotion = QueryEnvQuirkOverride("MOBILEGL_POINT_SIZE_DEMOTION");
+        features.AvoidSamplerMipmapMinFilter =
+            QueryEnvFlag("MOBILEGL_AVOID_SAMPLER_MIPMAP_MIN_FILTER");
         features.CoherentAsFlush = QueryEnvFlag("MOBILEGL_COHERENT_AS_FLUSH");
         features.TraceSkipAutodestroy = QueryEnvFlag("MOBILEGL_TRACE_SKIP_AUTODESTROY");
-        features.EsprytDisableUboRing = QueryEnvFlag("MOBILEGL_ESPRYT_DISABLE_UBO_RING");
-        features.EsprytDisableUnpackRing = QueryEnvFlag("MOBILEGL_ESPRYT_DISABLE_UNPACK_RING");
-        features.EsprytDisableUploadRing = QueryEnvFlag("MOBILEGL_ESPRYT_DISABLE_UPLOAD_RING");
-        features.EsprytDisableInvalidateFlush = QueryEnvFlag("MOBILEGL_ESPRYT_DISABLE_INVALIDATE_FLUSH");
-        features.DisableLargeBufferAdoption = QueryEnvFlag("MOBILEGL_DISABLE_LARGE_BUFFER_ADOPTION");
-        features.EsprytForceDepthStencilReadbackEmulation =
-            QueryEnvFlag("MOBILEGL_ESPRYT_FORCE_DS_READBACK_EMULATION");
+        features.DisableUboRing = QueryEnvFlag("MOBILEGL_DISABLE_UBO_RING");
         features.RelaxedSemantics = QueryEnvFlag("MOBILEGL_RELAXED_SEMANTICS");
-        features.MagmaDisableBlendedDepthWriteQuirk =
-            QueryEnvQuirkOverride("MOBILEGL_MAGMA_DISABLE_BLENDED_DEPTH_WRITE");
-        features.MagmaDisableRobustBufferAccess = QueryEnvFlag("MOBILEGL_MAGMA_DISABLE_ROBUST_BUFFER_ACCESS");
-        features.MagmaMultiDrawMode = QueryEnvMultiDrawMode("MOBILEGL_MAGMA_MULTIDRAW_MODE");
-        features.EsprytMultiDrawMode = QueryEnvGLESMultiDrawMode("MOBILEGL_ESPRYT_MULTIDRAW_MODE");
-        features.AsyncShaderCompile = QueryEnvQuirkOverride("MOBILEGL_ASYNC_SHADER_COMPILE");
-        features.AsyncShaderCompileThreads = QueryEnvUint32("MOBILEGL_ASYNC_SHADER_COMPILE_THREADS", 0, 0, 64);
-        features.AsyncOptimisticShaderStatus =
-            QueryEnvQuirkOverride("MOBILEGL_ASYNC_OPTIMISTIC_SHADER_STATUS");
-        features.ShaderTranslationCache = QueryEnvQuirkOverride("MOBILEGL_SHADER_CACHE");
-        features.EsprytViewportArrayEmulation =
-            QueryEnvQuirkOverride("MOBILEGL_ESPRYT_FORCE_VIEWPORT_ARRAY_EMULATION");
-        features.EsprytWidenPacked16Storage =
-            QueryEnvQuirkOverride("MOBILEGL_ESPRYT_WIDEN_PACKED16_STORAGE");
-        features.MagmaPrimGenQueryReroute = QueryEnvQuirkOverride("MOBILEGL_MAGMA_PRIMGEN_QUERY_REROUTE");
-        // MGPipe. Nothing here needs adding to an allow-list: InitializeAcceptedEnvVariables
-        // accepts every MOBILEGL_ / LIBGL_ prefixed variable in the environment, so a name
-        // that starts with MOBILEGL_ is visible to these queries by construction.
-#if MOBILEGL_PIPE_PUSH
-        // A push build with the knob unset runs every subsystem migrated so far, so the
-        // shipped path is the one the gates measure; MOBILEGL_PIPE_PUSH=0 in the
-        // environment is the all-subsystems-pull control that reproduces P1 exactly, and
-        // kMGPipeSubsystemsMigratedAtP3a (0x1ff) is the phase-by-phase control - P4a's four
-        // subsystems off, everything P3a landed still on.
-        features.PipePush = QueryEnvUint64("MOBILEGL_PIPE_PUSH", MG_Pipe::kMGPipeSubsystemsMigratedAtP5e);
-#else
-        // Meaningless in a pull build: there is nothing to push. Config.h documents 0 as
-        // "pull everything" and that stays literally true.
-        features.PipePush = QueryEnvUint64("MOBILEGL_PIPE_PUSH", 0);
-#endif
-        features.PipeVerify = QueryEnvFlag("MOBILEGL_PIPE_VERIFY");
-#if MOBILEGL_PIPE_PUSH
-        // Defaults ON: read as a tri-state so only an explicitly falsy value turns it off.
-        features.PipeVerifyFatal =
-            QueryEnvQuirkOverride("MOBILEGL_PIPE_VERIFY_FATAL") != MG_Config::QuirkOverride::ForceOff;
-        QueryEnvVariable("MOBILEGL_PIPE_VERIFY_CORRUPT", features.PipeVerifyCorrupt, "");
-        QueryEnvVariable("MOBILEGL_PIPE_POISON_OMIT", features.PipePoisonOmit, "");
-        features.PipeHandleAbaControl = QueryEnvFlag("MOBILEGL_PIPE_HANDLE_ABA_CONTROL");
-#endif
-        features.PipeStats = QueryEnvFlag("MOBILEGL_PIPE_STATS");
-        // Defaults ON, so the flag has to be read as a tri-state rather than as a plain
-        // truthy check: unset must keep the memos, and only an explicitly falsy value may
-        // drop them.
-        features.PipeLegacyMemos =
-            QueryEnvQuirkOverride("MOBILEGL_PIPE_LEGACY_MEMOS") != MG_Config::QuirkOverride::ForceOff;
-        features.PipeTexelRetainMb = QueryEnvUint32("MOBILEGL_PIPE_TEXEL_RETAIN_MB", 0, 0, 4096);
-        features.PipeIndexMirrorMb = QueryEnvUint32("MOBILEGL_PIPE_INDEX_MIRROR_MB", 64, 0, 4096);
-        features.PipeStatsPeriod = QueryEnvUint32("MOBILEGL_PIPE_STATS_PERIOD", 120, 1, 1000000);
-        QueryEnvVariable("MOBILEGL_PIPE_STATS_FILE", features.PipeStatsFile, "");
     }
 
     inline void InitBackendType() {
@@ -312,254 +141,12 @@ namespace MobileGL::MG_ConfigLoader {
 #undef ENTRY
     }
 
-#if MOBILEGL_BUILD_DISAGGREGATED
-    // MOBILEGL_TRANSPORT = monolith | inproc | spawn | unix:<path> | pipe:<name>
-    // (ARCHITECTURE.md:583). Shaped after InitBackendType above: an exact-name table, then
-    // one fallback that names what it did instead. The two prefixed forms are the only
-    // reason this is not literally that function's ENTRY macro.
-    //
-    // spawn / unix: / pipe: PARSE AND THEN REFUSE. They are P6's, and the refusal is NAMED
-    // rather than silent, because the failure this avoids is a P6 lane that set
-    // MOBILEGL_TRANSPORT=spawn, fell back to monolith, and went green on the wrong arm.
-    // The mode is left at Monolith so nothing half-initializes.
-    inline void InitTransport() {
-        String value;
-        QueryEnvVariable("MOBILEGL_TRANSPORT", value, "monolith");
-        String lowered = value;
-        std::transform(lowered.begin(), lowered.end(), lowered.begin(),
-                       [](unsigned char c) { return static_cast<char>(std::tolower(c)); });
-
-        MG_Config::TransportEndpoint.clear();
-        if (lowered.empty() || lowered == "monolith") {
-            MG_Config::Transport = MG_Config::TransportMode::Monolith;
-            return;
-        }
-        if (lowered == "inproc") {
-            MG_Config::Transport = MG_Config::TransportMode::InProcess;
-            // P7 F1: see Config.h. Set beside the mode, on the two arms that actually resolve
-            // one, and NOT on the two that name a transport and then stay monolith - a process
-            // that was refused its transport brings no client half up either.
-            MG_Config::SplitTransportRequestedByConfig = true;
-            MGLOG_I("Config: MOBILEGL_TRANSPORT=inproc - the MGPipe record stream crosses a real "
-                    "ring to an apply thread");
-            return;
-        }
-        // The three P6 forms. Recognised precisely, so the diagnostic can say "not yet"
-        // rather than "unknown", which are different bugs on the operator's side.
-        // P6 `sm`/`cp`: spawn is IMPLEMENTED. It launches a server process on a
-        // rendezvous of its own and connects to it - the two processes are
-        // independent, so this is `Dial = Connect` with a launcher attached
-        // rather than the fork-coupled shape ARCHITECTURE.md:488 described.
-        if (lowered == "spawn") {
-            MG_Config::Transport = MG_Config::TransportMode::Spawn;
-            MG_Config::SplitTransportRequestedByConfig = true; // P7 F1, as above.
-            // THE SAME SHAPE AS THE inproc LINE ABOVE, AND FOR THE SAME REASON.
-            // run_trace_case.cmake asserts on a distinctive sentence from this
-            // function rather than on `MOBILEGL_TRANSPORT=spawn` alone, because
-            // ConfigLoader logs an `Accepted env variable: KEY=VALUE` line for
-            // every MOBILEGL_* in EVERY build including the pull one - so the
-            // bare KEY=VALUE is satisfied by a monolith library that parsed
-            // nothing (review M-5). A spawn arm with no line of its own could
-            // only have been asserted with the inproc marker, which spawn never
-            // emits: the arm would have been red for a missing sentence rather
-            // than green for a working transport.
-            MGLOG_I("Config: MOBILEGL_TRANSPORT=spawn - the MGPipe record stream crosses a real "
-                    "ring to an apply thread in ANOTHER PROCESS");
-            return;
-        }
-        if (lowered.compare(0, 5, "unix:") == 0 || lowered.compare(0, 5, "pipe:") == 0) {
-            // unix: and pipe: remain P6+ - connecting to an endpoint SOMEBODY
-            // ELSE is listening on needs the server lifecycle to be somebody
-            // else's too, which is P12's. Named, never a silent degrade.
-            MGLOG_E("Config: MOBILEGL_TRANSPORT='%s' names a transport P6 does not implement yet; "
-                    "staying on monolith. This run is NOT a split run.",
-                    value.c_str());
-            MG_Config::Transport = MG_Config::TransportMode::Monolith;
-            return;
-        }
-        MGLOG_W("Config: Ignoring invalid env variable MOBILEGL_TRANSPORT='%s'; expected "
-                "monolith|inproc|spawn|unix:<path>|pipe:<name>, using monolith",
-                value.c_str());
-        MG_Config::Transport = MG_Config::TransportMode::Monolith;
-    }
-
-    // The MOBILEGL_IPC_* family (Config.h IpcTable). Parsed unconditionally rather than only
-    // when Transport != Monolith: a knob that silently means nothing on one arm of an A/B is
-    // how an A/B stops being one, and the ranges below are the diagnostics.
-    inline void InitIpc() {
-        auto& ipc = MG_Config::Ipc;
-        QueryEnvVariable("MOBILEGL_IPC_SERVER_PATH", ipc.ServerPath, "");
-        QueryEnvVariable("MOBILEGL_IPC_CONTROL", ipc.Control, "fork");
-        QueryEnvVariable("MOBILEGL_IPC_DATA", ipc.Data, "auto");
-        // Both ring floors are 1 MiB, not 0: a ring caps ONE record at half its size, and
-        // the catalogue's largest fixed payload (MGPFramebufferState, 304 bytes) plus a
-        // create_shader_state archive already needs far more than a toy ring. The ceilings
-        // are sanity, not policy.
-        ipc.RingMb = QueryEnvUint32("MOBILEGL_IPC_RING_MB", 8, 1, 1024);
-        ipc.StageMb = QueryEnvUint32("MOBILEGL_IPC_STAGE_MB", 32, 1, 4096);
-        // P7 wave 4 M2 (Config.h has the semantics). 0 is admitted ON PURPOSE as the negative
-        // control: no forced sync, and MagmaWireReclaimScenario's watermark case must go red.
-        ipc.WireDeferredMb = QueryEnvUint32("MOBILEGL_IPC_WIRE_DEFERRED_MB", 64, 0, 65536);
-        ipc.SpinUs = QueryEnvUint32("MOBILEGL_IPC_SPIN_US", 50, 0, 1000000);
-        // PH-6 (ID-P7-2; Config.h has the semantics). 0 is NOT admitted: a server with no
-        // patience at all would forfeit a healthy run-ahead client the first time its ring
-        // filled between two of the client's drains, which is an ordinary backlog.
-        ipc.EventWaitMs = QueryEnvUint32("MOBILEGL_IPC_EVENT_WAIT_MS", 2000, 1, 600000);
-        // 0 is admitted ON PURPOSE and is the negative control of exit gate E3(a): it turns
-        // the persistent-map push OFF, and PersistentCoherentMapScenario must go red.
-        ipc.PersistentBlockKb = QueryEnvUint32("MOBILEGL_IPC_PERSISTENT_BLOCK_KB", 64, 0, 65536);
-        // Whole-range push is the 0 arm; with it on (default) only blocks whose
-        // xxHash64 changed since the last push are shipped.
-        ipc.PersistentHashSuppress = QueryEnvUint32("MOBILEGL_IPC_PERSISTENT_HASH_SUPPRESS", 1, 0, 1);
-        ipc.BatchWaits = QueryEnvUint32("MOBILEGL_IPC_BATCH_WAITS", 1, 0, 1);
-        // The create window. DEFAULT 6, and it works because a link that declares RetainsReplies
-        // keeps a declared answer until its reader takes it - Config.h carries the three reasons it
-        // was inert before, the device numbers, and the sweep that put the default at 6 rather
-        // than 4 or 8 (the curve flattens at 6: 4->5 buys 1.92 s, 5->6 0.53 s, 6->8 nothing).
-        // Capped at 8: the retained set is bounded by the window's own depth, the store holds 24
-        // declared answers, and the device sweep showed the wall clock still falling at the old
-        // cap of 4 (see WireTables.cpp's kCreateWindowMax). WireTables.cpp's static_assert and
-        // StreamLink's crossing log are the checks on this number.
-        ipc.CreateWindow = QueryEnvUint32("MOBILEGL_IPC_CREATE_WINDOW", 10, 1, 12);
-        // The verify harness compares the pushed block against the applier per verb; a
-        // batched queue lets the comparer read a supplied field mid-apply, which is a
-        // torn read rather than a divergence. The batch is therefore off whenever the
-        // shadow comparer is armed.
-        if (MG_Config::Features.PipeVerify) ipc.BatchWaits = 0;
-        // 2 is the only tier P5 implements (R-6). 0 and 1 parse here and are refused at the
-        // point of use, which is where the "P11" in the message belongs.
-        ipc.AdoptTier = QueryEnvUint32("MOBILEGL_IPC_ADOPT_TIER", 2, 0, 2);
-        ipc.VerbBarrier = QueryEnvUint32("MOBILEGL_IPC_VERB_BARRIER", 1, 0, 1);
-        // P5e (MG_Remote/CONTRACT-P5E.md §1). The wait rule's A/B, parsed here like every
-        // other IPC knob and armed only where the server publishes kCapRunAheadApply.
-        ipc.RunAhead = QueryEnvUint32("MOBILEGL_IPC_RUN_AHEAD", 1, 0, 1);
-        // ... and forced OFF by the verify harness for BatchWaits' reason, one step further:
-        // run-ahead's whole point is that the client stops filling gPipeInputs for an
-        // unbarriered record, and the comparator has nothing left to compare when it does.
-        if (MG_Config::Features.PipeVerify) ipc.RunAhead = 0;
-        // The present credit (ruling 4). 1 is one frame of overlap; 8 is the ceiling because a
-        // deeper queue buys nothing on a CPU-bound client and pays for it in latency. 0 is NOT
-        // admitted: a credit of zero would mean "publish no present at all".
-        ipc.PresentCredit = QueryEnvUint32("MOBILEGL_IPC_PRESENT_CREDIT", 1, 1, 8);
-        // CONTRACT-P6 D5b's reply bound and P7's cold-start budget (Config.h has the semantics).
-        // Both are floored at 100 ms: a zero bound would declare every live server silent.
-        ipc.ControlTimeoutMs = QueryEnvUint32("MOBILEGL_IPC_CONTROL_TIMEOUT_MS", 5000, 100, 600000);
-        ipc.ColdStartMs = QueryEnvUint32("MOBILEGL_IPC_COLD_START_MS", 20000, 100, 600000);
-        ipc.StrictErrors = QueryEnvFlag("MOBILEGL_IPC_STRICT_ERRORS");
-        ipc.Audit = QueryEnvFlag("MOBILEGL_IPC_AUDIT");
-        QueryEnvVariable("MOBILEGL_IPC_SERVER_AFFINITY", ipc.ServerAffinity, "auto");
-        // P5f f1: the dual-block rehearsal (P5F-WIRE-COMPLETENESS.md §4). Forced OFF by the
-        // verify harness: the comparator's entry compare and compare-at-read hook are built on
-        // there being ONE filled block (the hook pins itself to &gPipeInputs,
-        // PipeFill.cpp's MGPipeVerifyReadHook), which is exactly what the rehearsal splits.
-        ipc.RoleSplitState = QueryEnvFlag("MOBILEGL_IPC_ROLE_SPLIT_STATE");
-        if (MG_Config::Features.PipeVerify && ipc.RoleSplitState) {
-            MGLOG_W("Config: MOBILEGL_IPC_ROLE_SPLIT_STATE=1 is incompatible with "
-                    "MOBILEGL_PIPE_VERIFY (the comparator owns the single fill block); "
-                    "the dual-block rehearsal is OFF for this run");
-            ipc.RoleSplitState = false;
-        }
-
-        // P6 `dl` (CONTRACT-P6 5.3): MOBILEGL_IPC_RESPAWN IS A NAMED REFUSAL, NOT A NO-OP.
-        //
-        // The device-lost latch is deliberately one-way - a session whose server died has
-        // nothing to recover into, because every handle the client minted names an object in a
-        // process that no longer exists. Re-pushing the world onto a fresh server is the work
-        // this knob would turn on, and no stage has written it.
-        //
-        // Refused BY NAME rather than parsed and ignored, for the reason Config.h gives about
-        // the whole IPC family: an environment variable nothing consumes is indistinguishable
-        // from one that is consumed and does nothing, and an operator who set this one would
-        // otherwise conclude that recovery had been tried and had not helped.
-        {
-            String respawn;
-            QueryEnvVariable("MOBILEGL_IPC_RESPAWN", respawn, "");
-            if (!respawn.empty() && respawn != "0") {
-                MGLOG_E("Config: MOBILEGL_IPC_RESPAWN='%s' names a recovery NO STAGE HAS "
-                        "IMPLEMENTED. The device-lost latch is one-way on purpose: every handle "
-                        "this client minted names an object inside the server process, so a new "
-                        "server would have to be re-pushed the entire world before a single verb "
-                        "could land. This run will latch device-lost and stay there.",
-                        respawn.c_str());
-            }
-        }
-
-        // P12 (on-screen server window): MOBILEGL_IPC_SURFACE = offscreen | server (Config.h has
-        // the semantics). An unknown value is named and read as the default, like every knob here.
-        {
-            String surface;
-            QueryEnvVariable("MOBILEGL_IPC_SURFACE", surface, "offscreen");
-            std::transform(surface.begin(), surface.end(), surface.begin(),
-                           [](unsigned char c) { return static_cast<char>(std::tolower(c)); });
-            if (surface.empty() || surface == "offscreen") {
-                ipc.Surface = MG_Config::IpcSurface::Offscreen;
-            } else if (surface == "server") {
-                ipc.Surface = MG_Config::IpcSurface::Server;
-            } else {
-                MGLOG_W("Config: Ignoring invalid env variable MOBILEGL_IPC_SURFACE='%s'; expected "
-                        "offscreen|server, using offscreen",
-                        surface.c_str());
-                ipc.Surface = MG_Config::IpcSurface::Offscreen;
-            }
-            // (Not said by a server process: a spawned server inherits the client's environment,
-            // parses this before RunSession sets its own transport, and has no client half anyway.)
-            const char* role = std::getenv("MOBILEGL_IPC_ROLE");
-            const Bool serverProcess = role != nullptr && std::strcmp(role, "server") == 0;
-            if (ipc.Surface == MG_Config::IpcSurface::Server && !serverProcess &&
-                MG_Config::Transport != MG_Config::TransportMode::Spawn) {
-                // Said, not silently honoured: there is no remote server here to own a window.
-                MGLOG_W("Config: MOBILEGL_IPC_SURFACE=server is IGNORED - it asks a remote server "
-                        "(MOBILEGL_TRANSPORT=spawn, a fork or tcp:// control) to own the window surface, "
-                        "and this run has none. Window surfaces stay the client's own");
-            }
-        }
-
-        if (MG_Config::Transport == MG_Config::TransportMode::Monolith) return;
-        // One line, on the arm where these numbers decide behaviour, because every one of
-        // them is a number a bug report has to quote.
-        // CREATE-WINDOW IS IN THIS LINE BECAUSE A RUN HAS TO SAY WHICH WINDOW IT USED. It was
-        // missing while the value was a number nobody varied, and the moment it became one that
-        // changes the wall clock by seconds (the P12 sweep: 28.3 s at 1 down to 10.8 s at 6) a
-        // log that does not name it makes every run ambiguous about its own configuration.
-        MGLOG_I("Config: IPC ring=%uMiB stage=%uMiB wire-deferred=%uMiB spin=%uus event-wait=%ums "
-                "persistent-block=%uKiB create-window=%u "
-                "adopt-tier=%u verb-barrier=%u run-ahead=%u present-credit=%u control-timeout=%ums "
-                "cold-start=%ums strict=%d audit=%d role-split-state=%d affinity='%s' surface=%s",
-                ipc.RingMb, ipc.StageMb, ipc.WireDeferredMb, ipc.SpinUs, ipc.EventWaitMs,
-                ipc.PersistentBlockKb, ipc.CreateWindow, ipc.AdoptTier,
-                ipc.VerbBarrier, ipc.RunAhead, ipc.PresentCredit, ipc.ControlTimeoutMs, ipc.ColdStartMs,
-                static_cast<int>(ipc.StrictErrors), static_cast<int>(ipc.Audit),
-                static_cast<int>(ipc.RoleSplitState), ipc.ServerAffinity.c_str(),
-                MG_Config::ServerOwnedWindowSurfaces() ? "server" : "offscreen");
-        if (ipc.VerbBarrier == 0) {
-            MGLOG_W("Config: MOBILEGL_IPC_VERB_BARRIER=0 is the R-1 NEGATIVE CONTROL and is "
-                    "expected to fail: the client still pulls 31 of 63 PipeInputs fields from a "
-                    "live GLContext, so an unbarriered queue lets the server read future values");
-        }
-        if (ipc.WireDeferredMb == 0) {
-            MGLOG_W("Config: MOBILEGL_IPC_WIRE_DEFERRED_MB=0 is the M2 NEGATIVE CONTROL: the "
-                    "server never forces a sync for orphaned wire buffer stores, so a long frame "
-                    "that respecifies and draws holds every one of them until the frame ends");
-        }
-        if (ipc.PersistentBlockKb == 0) {
-            MGLOG_W("Config: MOBILEGL_IPC_PERSISTENT_BLOCK_KB=0 is the E3(a) NEGATIVE CONTROL: "
-                    "the persistent-map push is OFF and a coherent-map scenario must go red");
-        }
-    }
-#endif
-
     void Init() {
         MGLOG_D("Loading configuration from environment variables...");
         InitializeAcceptedEnvVariables();
 
         InitBackendType();
         InitFeatures();
-#if MOBILEGL_BUILD_DISAGGREGATED
-        // After InitFeatures, so the one line InitIpc logs is the last word on this run's
-        // configuration, and before the accepted-env map is destroyed just below.
-        InitTransport();
-        InitIpc();
-#endif
 
         // Destroy the map since we won't need it anymore
         acceptedEnvVariablesMap.reset();

MobileGL/Defines.h

@@ -9,20 +9,10 @@
 #pragma once
 
 // ============== Platform-specific definitions and macros ============== //
-// No __ANDROID_API__ pin here on purpose. The effective API level is owned by
-// the build system (gradle minSdk 26 -> -DANDROID_PLATFORM=android-26, enforced
-// by the configure-time guard in CMakeLists.txt), not by a macro.
-//
-// History: this used to `#define __ANDROID_API__ 26` to *raise* the level back
-// when the build configured something lower, so that pthread_getname_np (which
-// bionic guards with __INTRODUCED_IN(26)) would be declared. Once a later
-// change added an `#undef` in front of it, the same line started *lowering* the
-// level whenever the build configured higher than 26 - and that is an
-// include-order split-brain, not a compatibility knob: a TU that includes any
-// libc++ header before Includes.h latches libc++'s feature macros at the
-// configure-time level, and only the bionic headers pulled in afterwards see
-// the lowered value. The two halves then disagree (e.g. libc++ believes
-// pthread_cond_clockwait exists while bionic has since hidden its declaration).
+#ifdef __ANDROID__
+#undef __ANDROID_API__
+#define __ANDROID_API__ 26 // force Android API level to 26 for compatibility
+#endif
 
 #ifdef _WIN32
 #ifndef NOMINMAX
@@ -44,26 +34,8 @@
 #define MOBILEGL_EGL_API MOBILEGL_API
 #define MOBILEGL_CGL_API MOBILEGL_API
 #define MOBILEGL_NSOPENGL_API MOBILEGL_API
-#define MOBILEGL_WGL_API MOBILEGL_API
 
 // ====================== MobileGL configurations ======================= //
-// The numeric log levels live here, not only in Log.h: MOBILEGL_ASSERT below compares
-// MOBILEGL_LOG_ACTIVE_LEVEL against MOBILEGL_LOG_LEVEL_DEBUG, and in a translation unit
-// that includes Defines.h without Log.h both tokens would silently evaluate to 0 in the
-// preprocessor conditional - enabling the assert in exactly the INFO-level builds it is
-// documented to be compiled out of. Log.h redefines them identically, which is legal.
-//
-// Severity order, ascending: DEBUG < INFO < WARN < ERROR < FATAL. MOBILEGL_LOG_ACTIVE_LEVEL
-// names the lowest severity compiled in, so the production default INFO keeps I/W/E/F and
-// drops only D. Any edit here must be mirrored in Log.h.
-#ifndef MOBILEGL_LOG_LEVEL_DEBUG
-#define MOBILEGL_LOG_LEVEL_DEBUG 0
-#define MOBILEGL_LOG_LEVEL_INFO 1
-#define MOBILEGL_LOG_LEVEL_WARN 2
-#define MOBILEGL_LOG_LEVEL_ERROR 3
-#define MOBILEGL_LOG_LEVEL_FATAL 4
-#endif
-
 #ifndef MOBILEGL_LOG_ACTIVE_LEVEL
 #define MOBILEGL_LOG_ACTIVE_LEVEL MOBILEGL_LOG_LEVEL_INFO
 #endif
@@ -95,12 +67,6 @@
 #endif
 
 // =============================== Utils ================================ //
-// Asserts are live in exactly the builds where MGLOG_D is live, i.e. DEBUG builds only;
-// an INFO build (the production default) compiles them out. DEBUG is the lowest severity
-// in the ordering above, so "ACTIVE <= DEBUG" is true only for ACTIVE == DEBUG - the same
-// gate MGLOG_D uses in Log.h. That equivalence is what makes this gate survive the
-// 2026-08-13 renumbering unchanged; the contract is and stays
-// "INFO builds: asserts OFF; DEBUG builds: asserts ON".
 #if MOBILEGL_LOG_ACTIVE_LEVEL <= MOBILEGL_LOG_LEVEL_DEBUG
     #define MOBILEGL_ASSERT(condition, ...)                                                                                \
         do {                                                                                                               \

MobileGL/GlobalObjects.cpp

@@ -14,13 +14,7 @@ namespace MobileGL {
     } // namespace MG_Config
 
     namespace MG_Backend {
-        // Leak-at-exit storage: the UniquePtr itself lives on the heap and is
-        // never destroyed by the runtime, so process exit runs no backend
-        // destructors (static destruction order across TUs is undefined).
-        // Deterministic teardown happens inside the EGL lifecycle instead:
-        // the last eglTerminate calls MobileGL::Destroy(), which .reset()s
-        // these singletons while the process is still healthy.
-        UniquePtr<BackendObject>& pActiveBackendObject = *new UniquePtr<BackendObject>();
+        UniquePtr<BackendObject> pActiveBackendObject;
         GlobalBackendFunctionsTable gBackendFunctionsTable;
     } // namespace MG_Backend
 } // namespace MobileGL

MobileGL/Includes.h

@@ -49,8 +49,8 @@
 #include <stacktrace>
 #endif
 
-// Include ska::flat_hash_map
-#include <ska/flat_hash_map.hpp>
+// Include FastSTL
+#include <FastSTL/UnorderedMap.h>
 
 // Include xxHash
 #include <xxhash.h>

MobileGL/Init.cpp

@@ -9,34 +9,14 @@
 #include "Init.h"
 #include "Config.h"
 #include <MG_Backend/BackendObjects.h>
-#include <MG_Backend/DirectVulkan/DirectVulkan.h>
 #include <MG_State/GLState/Core.h>
 #include <MG_State/EGLState/Core.h>
 #include <MG_Impl/GLImpl/Texture/ProxyTexture.h>
 #include <MG_Impl/GLImpl/Framebuffer/GL_Framebuffer.h>
-#include <MG_Impl/GLImpl/Sync/GL_Sync.h>
-#include <MG_Impl/GLImpl/Query/GL_Query.h>
-#include <MG_Util/Async/ShaderCompilePool.h>
-#include <MG_Util/Metrics/PipeStats.h>
-#include <MG_Util/ShaderTranspiler/ShaderCompiler.h>
-#include <MG_State/GLState/ProgramState/ProgramTranslationCache.h>
-#include <MG_Util/ShaderTranspiler/TranslationCache.h>
-#if MOBILEGL_PIPE_VERIFY
-#include <MG_Backend/MGPipe/PipeInputs.h> // MGPipeVerifyFlushSummary, before Debug::Close in DestroyImpl
-#endif
-
-#include <atomic>
-#include <mutex>
 
 namespace MobileGL {
     namespace {
-        std::atomic<Bool> g_isInitialized = false;
-        thread_local Bool tl_initializing = false;
-
-        std::mutex& InitMutex() {
-            static std::mutex mutex;
-            return mutex;
-        }
+        Bool g_isInitialized = false;
 
         void DestroyImpl(Bool logLifecycle) {
             if (!g_isInitialized) {
@@ -46,70 +26,14 @@ namespace MobileGL {
             if (logLifecycle) {
                 MGLOG_I("MobileGL closing...");
             }
-#if MOBILEGL_BUILD_DISAGGREGATED
-            // P5: the split roles come down FIRST - ARCHITECTURE.md:537's order puts the whole
-            // of it before MobileGL::Destroy(), and this function IS MobileGL::Destroy. A no-op
-            // in a monolith RUN; absent from a monolith BUILD, because G1 admits no new pull
-            // symbol and no resized one (the first version called it unconditionally and moved
-            // DestroyImpl by 32 bytes). See BackendObjects.h for why the position rather than
-            // the call is the load-bearing part.
-            MG_Backend::ShutdownSplitRoles();
-#endif
-            // Before any subsystem the counters name goes away, and before the last frame's
-            // numbers can be lost: emits the final summary line and, when
-            // MOBILEGL_PIPE_STATS_FILE is set, the JSON dump. A no-op when the counters are
-            // off, and idempotent.
-            MG_Util::PipeStats::Shutdown();
-            // First, before anything else is torn down. In-flight compile/link jobs own
-            // their own inputs and are safe against everything below EXCEPT glslang's
-            // process globals and the TShader/TProgram objects hanging off pGLContext,
-            // both of which this function is about to destroy. This is the one
-            // cancellation path in the whole design that waits.
-            MG_Util::Async::ShaderCompilePool::Get().StopAndDrain();
-            // GL syncs die with their contexts, and every context is gone by the
-            // time full teardown runs: drain the live-sync registry while the
-            // backend function table can still release the backend handles (and
-            // before a re-initialized library could pair them with the wrong
-            // backend's DeleteSync).
-            MG_Impl::GLImpl::DestroyAllSyncObjects();
-            // Queries die with their contexts for the same reason, and their registry
-            // is the same shape of process-global map: drain it here too, while the
-            // function table can still pair each backend handle with the backend that
-            // minted it.
-            MG_Impl::GLImpl::DestroyAllQueryObjects();
+            glslang::FinalizeProcess();
             MG_Backend::pActiveBackendObject.reset();
             MG_State::pGLContext.reset();
             MG_State::pEGLContext.reset();
             MG_Impl::GLImpl::TextureImpl::pProxyTextureManager.reset();
             MG_Impl::GLImpl::FramebufferImpl::pDefaultFramebufferInfo.reset();
-            // Must run AFTER pGLContext.reset(). FinalizeProcess -> ShFinalize deletes
-            // glslang's process-wide pool allocator and every cached built-in symbol table,
-            // while the TShader/TProgram objects owned by the shader and program objects
-            // still reference levels adopted from those tables. Finalizing first left live
-            // glslang objects pointing at freed memory for the rest of the teardown.
-            glslang::FinalizeProcess();
-            // Immediately after, and never apart from it: FinalizeProcess just deleted the
-            // built-in symbol tables the prewarm latch stands for, so leaving it set would
-            // make the next Initialize() skip a prewarm it genuinely needs.
-            MG_Util::ShaderTranspiler::ShaderCompiler::ResetPrewarmLatch();
-            // The two-level translation memo. Nothing in it references a glslang object -
-            // both levels hold plain bytes - so this is RSS hygiene rather than a lifetime
-            // requirement, and it is safe either side of FinalizeProcess. Stats first: an
-            // fordebug build gets one line per level saying how the run went.
-            MG_Util::ShaderTranspiler::LogShaderTranslationCacheStats();
-            MG_Util::ShaderTranspiler::ClearShaderTranslationCaches();
-            MG_State::GLState::LogProgramTranslationCacheStats();
-            MG_State::GLState::ClearProgramTranslationCache();
             MG_Backend::gBackendFunctionsTable = {};
             g_isInitialized = false;
-#if MOBILEGL_PIPE_VERIFY
-            // BEFORE Close, and from here rather than from a static destructor (V1 fix round 2):
-            // Close() nulls the role's sink and Log.cpp's next write reopens it with "w", so the
-            // FATAL=0 summary the comparator used to write from __run_exit_handlers truncated the
-            // client half of every such run to that one line. Verify builds only - the guard is
-            // the compile definition, not a runtime knob, and the pull build gains no byte (G1).
-            MG_Pipe::MGPipeVerifyFlushSummary();
-#endif
             if (logLifecycle) {
                 MG_Util::Debug::Close();
             }
@@ -128,107 +52,52 @@ namespace MobileGL {
         MGLOG_I("Initializing MobileGL...");
         MG_ConfigLoader::Init();
         MGLOG_I("Config loaded");
-        // Immediately after the config load and before anything can count: the MGPipe
-        // boundary counters latch their enable flag here, so every counting site in the
-        // two backends is a load of an already-settled global for the rest of the run.
-        MG_Util::PipeStats::Init();
-#if MOBILEGL_BUILD_DISAGGREGATED
-        // F1 (P7 wave 2). THE WIRE COMES UP BEFORE THE FIRST FRONTEND OBJECT IS BORN, and the
-        // ORDER is the fix - not a wait, and not a friendlier default mask.
-        //
-        // MG_State::Init() constructs GLContext, and GLContext's TextureState constructor
-        // materialises one default texture object per target (GL 3.3 core 3.8,
-        // TextureState.cpp:62-71). TextureObjectBase's constructor emits resource_create for
-        // every one of them (TextureState/TextureObject.cpp:168-169), and that emission is
-        // gated, through PipeFill's FamilyIsLive, on
-        // CapsMirror::ServerConsumes(kMGPipeSubsystemTextureResources). In the old order the
-        // mirror was still GENERATION 0 when it was asked - it had no snapshot because the
-        // session had not been started yet, MG_Backend::Init() being what starts it - so it
-        // answered from the placeholder, every one of those creates was withheld, and the log
-        // said so once and then never again:
-        //
-        //     MG_Remote client: the server does not consume MGPipe subsystem 0x400 - this
-        //     family emits NOTHING and the legacy pull path runs for it (R-8). callMask=0x0,
-        //     caps generation 0
-        //
-        // That is not a race and it never was one: the line reproduces byte-for-byte on
-        // lavapipe and on an Adreno 830, because the two Init calls are two statements in one
-        // thread. And "the legacy pull path runs for it" is false under split - the client has
-        // no pull path to fall back to - so the records are simply lost, and only a later
-        // respecify's self-healing create (TextureEmit.h:872) ever brings one back.
-        //
-        // A BOUNDED WAIT INSIDE ServerConsumes CANNOT FIX THIS AND WOULD DEADLOCK: during
-        // MG_State::Init() no handshake is in flight, and the one that will land is started
-        // LATER BY THIS SAME THREAD. The only correct answer is to have already brought it up,
-        // which is what this hook does. ServerConsumes now REFUSES to answer from a
-        // placeholder (CapsMirror.cpp), so a regression of this order is a named Fatal rather
-        // than a whole family of silently dropped records.
-        //
-        // In a build without MOBILEGL_BUILD_DISAGGREGATED this statement does not exist, so
-        // the pull build gains no symbol, no branch and no byte - which is what G1 measures.
-        const Bool splitBackendIsUp = MG_Backend::InitSplitRolesBeforeState();
-#endif
         MG_State::Init();
         MGLOG_D("MG_State initialized");
-#if MOBILEGL_BUILD_DISAGGREGATED
-        if (!splitBackendIsUp)
-#endif
-        {
-            MG_Backend::Init();
-        }
+        MG_Backend::Init();
         MGLOG_D("MG_Backend initialized");
         MG_Impl::Init();
         MGLOG_D("MG_Impl initialized");
         glslang::InitializeProcess();
-        // On the GL thread, before any worker can exist. glslang builds its built-in symbol
-        // tables lazily under a process-wide lock held for the whole build, so without this
-        // the first concurrent compiles of a shaderpack all serialize behind the very first
-        // parse and asynchronous compilation looks like it is doing nothing.
-        //
-        // Gated on the flag, because the problem it solves only exists when there are
-        // workers: with compilation synchronous, nothing ever contends for that lock and the
-        // three throwaway parses buy nothing - they just add to every eglInitialize. Read the
-        // flag here rather than inside PrewarmBuiltins so ShaderCompiler keeps no dependency
-        // on the async subsystem (ProgramUtilTest compiles that file without it).
-        if (MG_Util::Async::AsyncShaderCompileEnabled()) {
-            MG_Util::ShaderTranspiler::ShaderCompiler::PrewarmBuiltins();
-        }
         MGLOG_D("glslang initialized");
         g_isInitialized = true;
         MGLOG_I("MobileGL initialized");
     }
 
-    void EnsureInitialized() {
-        if (g_isInitialized.load(std::memory_order_acquire)) {
-            return;
-        }
-        // Re-entrant call while this thread is already inside Initialize()
-        // (e.g. an init step routing back through a public entry point).
-        if (tl_initializing) {
-            return;
-        }
-        const std::lock_guard<std::mutex> lock(InitMutex());
-        if (g_isInitialized.load(std::memory_order_acquire)) {
-            return;
-        }
-        tl_initializing = true;
-        Initialize();
-        tl_initializing = false;
-    }
-
     void Destroy() {
         DestroyImpl(true);
     }
 
-    // MobileGL's lifecycle is owned entirely by the host-API layers
-    // (EGL/WGL/CGL): initialization happens lazily on the first entry point
-    // via EnsureInitialized(), and full teardown happens deterministically
-    // when the last EGL display is terminated with nothing current (EGLImpl
-    // calls Destroy()). There is intentionally no backend-initializing static
-    // constructor, no static destructor, and no DllMain: the global singletons
-    // use leak-at-exit storage (see GlobalObjects.cpp), so a process that exits
-    // without eglTerminate simply leaks them to the OS instead of running
-    // backend destructors during static teardown. macOS has a lightweight
-    // dyld constructor that installs NSOpenGL dispatch hooks only; full backend
-    // initialization still enters here from the first hooked CGL context.
+#if defined(__linux__) || defined(__APPLE__)
+    __attribute__((constructor)) static void AutoInit() {
+        Initialize();
+    }
+
+    __attribute__((destructor)) static void AutoDestroy() {
+        if (MG_Config::Features.TraceSkipAutodestroy) {
+            return;
+        }
+#if defined(__APPLE__)
+        // macOS injected dylibs can run destructors after logging/backend static state is already torn down.
+        return;
+#else
+        DestroyImpl(false);
+#endif
+    }
+#endif
+
+#ifdef _WIN32
+    BOOL WINAPI DllMain(HMODULE hModule, DWORD ul_reason_for_call, LPVOID lpReserved) {
+        switch (ul_reason_for_call) {
+        case DLL_PROCESS_ATTACH:
+            Initialize();
+            break;
+
+        case DLL_PROCESS_DETACH:
+            Destroy();
+            break;
+        }
+        return TRUE;
+    }
+#endif
 } // namespace MobileGL

MobileGL/Init.h

@@ -11,13 +11,6 @@
 
 namespace MobileGL {
     void Initialize();
-    // Thread-safe, idempotent, and re-entrant wrapper around Initialize().
-    // Host layers (EGL/WGL/CGL entry points) call this lazily on first use so
-    // full backend initialization never depends on ELF/DLL static constructors,
-    // and so a fresh init can follow a full Destroy() (e.g. after the last
-    // eglTerminate). The macOS dyld bootstrap installs only lightweight
-    // NSOpenGL method hooks.
-    void EnsureInitialized();
     void Destroy();
 
     namespace MG_Util::Debug {

MobileGL/MG_Backend/BackendObject.h

@@ -9,15 +9,11 @@
 #pragma once
 #include <Includes.h>
 #include "MG_State/GLState/TextureState/TextureEnum.h"
-#if MOBILEGL_BUILD_DISAGGREGATED
-#include <MG_Pipe/MGPipeHandles.h>
-#endif
 
 namespace MobileGL {
     namespace MG_State::GLState {
         class FramebufferObject;
         class ITextureObject;
-        class RenderbufferObject;
     }
 
     enum class BackendType {
@@ -28,34 +24,6 @@ namespace MobileGL {
     };
 
     namespace MG_Backend {
-        // One endpoint of a glCopyImageSubData. GL 4.6 core 18.3.2 accepts GL_RENDERBUFFER
-        // alongside the ten whole-image texture targets, and a renderbuffer name lives in a
-        // namespace of its own - so an endpoint is a sum type, not an ITextureObject. At most
-        // one of the two pointers is set; neither is set when the name named nothing, which is
-        // the INVALID_VALUE the frontend validator reports.
-        struct CopyImageEndpoint {
-            SharedPtr<MG_State::GLState::ITextureObject> Texture;
-            SharedPtr<MG_State::GLState::RenderbufferObject> Renderbuffer;
-#if MOBILEGL_BUILD_DISAGGREGATED
-            MG_Pipe::MGPipeHandle TextureHandle = MG_Pipe::kMGPipeNullHandle;
-            MG_Pipe::MGPipeHandle RenderbufferHandle = MG_Pipe::kMGPipeNullHandle;
-#endif
-
-            Bool IsRenderbuffer() const {
-#if MOBILEGL_BUILD_DISAGGREGATED
-                if (!MG_Pipe::MGPipeHandleIsNull(RenderbufferHandle)) return true;
-#endif
-                return Renderbuffer != nullptr;
-            }
-            Bool Exists() const {
-#if MOBILEGL_BUILD_DISAGGREGATED
-                if (!MG_Pipe::MGPipeHandleIsNull(TextureHandle)) return true;
-                if (!MG_Pipe::MGPipeHandleIsNull(RenderbufferHandle)) return true;
-#endif
-                return Texture != nullptr || Renderbuffer != nullptr;
-            }
-        };
-
         enum class FormatCapability : Uint64 {
             Creatable = 1ull << 0,
 
@@ -177,10 +145,6 @@ namespace MobileGL {
                                             GLenum buffer, GLint drawbuffer, const GLfloat* value);
             void (*ClearNamedFramebufferfi)(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
                                             GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
-            void (*ClearNamedFramebufferiv)(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
-                                            GLenum buffer, GLint drawbuffer, const GLint* value);
-            void (*ClearNamedFramebufferuiv)(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
-                                             GLenum buffer, GLint drawbuffer, const GLuint* value);
             void (*BlitFramebuffer)(GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1, GLint dstX0, GLint dstY0,
                                     GLint dstX1, GLint dstY1, GLbitfield mask, GLenum filter);
             void (*BlitNamedFramebuffer)(const SharedPtr<MG_State::GLState::FramebufferObject>& readFramebuffer,
@@ -192,9 +156,9 @@ namespace MobileGL {
                                    GLsizei height, GLint border);
             void (*CopyTexSubImage2D)(GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y,
                                       GLsizei width, GLsizei height);
-            void (*CopyImageSubData)(const CopyImageEndpoint& src,
+            void (*CopyImageSubData)(const SharedPtr<MG_State::GLState::ITextureObject>& srcTexture,
                                      GLenum srcTarget, GLint srcLevel, GLint srcX, GLint srcY, GLint srcZ,
-                                     const CopyImageEndpoint& dst,
+                                     const SharedPtr<MG_State::GLState::ITextureObject>& dstTexture,
                                      GLenum dstTarget, GLint dstLevel, GLint dstX, GLint dstY, GLint dstZ,
                                      GLsizei srcWidth, GLsizei srcHeight, GLsizei srcDepth);
             void (*GenerateMipmap)(GLenum target);
@@ -210,35 +174,18 @@ namespace MobileGL {
             void (*MemoryBarrierByRegion)(GLbitfield barriers);
             void (*BindImageTexture)(GLuint unit, GLuint texture, GLint level, GLboolean layered, GLint layer,
                                      GLenum access, GLenum format);
-            // The ONLY indexed query that is genuinely a backend one, and only for the pnames
-            // MG_Impl/GLImpl/Getter/GL_Getter.cpp does not already own. Every indexed pname that
-            // names FRONTEND state - the indexed buffer bindings, the per-unit texture/sampler
-            // bindings, the image-unit bindings, the viewport rectangles, the indexed capabilities
-            // - is answered in GL_Getter::GetIntegeri_v and never reaches this entry; the
-            // 64-bit and float/double widths are derived there from the same answer, which is why
-            // no GetInteger64i_v/GetFloati_v/GetDoublei_v table entry exists. In practice this
-            // leaves GL_MAX_COMPUTE_WORK_GROUP_COUNT / _SIZE (also asked directly by
-            // MG_Util/ShaderTranspiler/CompileEnv.cpp) plus whatever pname the frontend has no
-            // case for at all.
             void (*GetIntegeri_v)(GLenum target, GLuint index, GLint* data);
-            // There is deliberately NO GetProgramiv entry: glGetProgramiv describes the program
-            // the APPLICATION wrote - link status, the transform-feedback mode, the compute local
-            // size - all of which are frontend link artifacts on ProgramObject, and
-            // MG_Impl/GLImpl/Program/GL_Program.cpp answers every one of them from there. Asking a
-            // backend would mean asking about a DIFFERENT program (a SPIRV-Cross-generated ESSL
-            // one, or a SPIR-V module), in a namespace the application never sees.
-            // The GL program interface (glGetProgramInterfaceiv / glGetProgramResource*) is NOT
-            // a backend query: it describes the program the application wrote, in the
-            // application's namespace, which neither backend program is in. It is answered
-            // entirely by MG_Impl/GLImpl/Program/ProgramInterface from the frontend reflection.
-            // Takes the block's GL NAME, not glShaderStorageBlockBinding's index. The index
-            // the application passes is the frontend interface-query enumeration's, and no
-            // backend shares that index space: DirectVulkan enumerates SPIR-V descriptor
-            // bindings and DirectGLES asks a real driver about SPIRV-Cross-generated ESSL.
-            // The name is the one coordinate all three agree on, so the frontend resolves the
-            // index against its own enumeration and each backend maps the name to its own.
-            void (*ShaderStorageBlockBinding)(GLuint program, const GLchar* storageBlockName,
-                                              GLuint storageBlockBinding);
+            void (*GetInteger64i_v)(GLenum target, GLuint index, GLint64* data);
+            void (*GetProgramiv)(GLuint program, GLenum pname, GLint* params);
+            void (*GetProgramInterfaceiv)(GLuint program, GLenum programInterface, GLenum pname, GLint* params);
+            GLuint (*GetProgramResourceIndex)(GLuint program, GLenum programInterface, const GLchar* name);
+            void (*GetProgramResourceName)(GLuint program, GLenum programInterface, GLuint index, GLsizei bufSize,
+                                           GLsizei* length, GLchar* name);
+            void (*GetProgramResourceiv)(GLuint program, GLenum programInterface, GLuint index, GLsizei propCount,
+                                         const GLenum* props, GLsizei bufSize, GLsizei* length, GLint* params);
+            GLint (*GetProgramResourceLocation)(GLuint program, GLenum programInterface, const GLchar* name);
+            GLint (*GetProgramResourceLocationIndex)(GLuint program, GLenum programInterface, const GLchar* name);
+            void (*ShaderStorageBlockBinding)(GLuint program, GLuint storageBlockIndex, GLuint storageBlockBinding);
             // GL fence sync objects. All entries are optional (may be null); the
             // frontend then falls back to always-signaled sync semantics.
             // FenceSync may itself return null when the backend cannot create a
@@ -273,39 +220,6 @@ namespace MobileGL {
             // and leave the query readable later.
             Bool (*GetQueryResult64)(BackendQueryHandle query, Bool wait, Uint64* outNanoseconds);
             void (*DeleteBackendQuery)(BackendQueryHandle query);
-            // GL_SAMPLES_PASSED occlusion queries (optional; null = unsupported,
-            // the frontend then rejects the target). Results/deletion flow through
-            // GetQueryResult64 / DeleteBackendQuery like timer queries.
-            BackendQueryHandle (*BeginOcclusionQuery)();
-            void (*EndOcclusionQuery)(BackendQueryHandle query);
-            // Transform feedback primitive queries backed by real GPU query pools
-            // (optional; null = frontend falls back to CPU accounting).
-            BackendQueryHandle (*BeginXfbPrimitivesQuery)(Bool generated);
-            void (*EndXfbPrimitivesQuery)(BackendQueryHandle query);
-            // Whether GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN should be answered from the
-            // frontend's own accounting wherever that accounting is exact - a capture with no
-            // geometry stage - instead of from the query above. Set by DirectGLES, whose result
-            // is whatever the ES driver's PRIMITIVES_WRITTEN counter says: Adreno reports twice
-            // the written count for a vertex-only capture that follows a large render pass,
-            // where the desktop-exact answer is the one the frontend already computed. Defaults
-            // to false, so a backend that never sets it keeps using its GPU result.
-            Bool PrefersCpuXfbPrimitiveAccounting = false;
-            // Transform feedback capture spans, for backends whose own GL/ES driver
-            // performs the capture (DirectGLES). Both optional; null means the backend
-            // drives capture from its draw recording instead (DirectVulkan). End is
-            // called while the frontend capture state is still active, so the backend
-            // can still see the capture program and buffer bindings.
-            // GL_PATCH_VERTICES; ES 3.2 spells it the same way.
-            void (*PatchParameteri)(GLenum pname, GLint value);
-            void (*BeginTransformFeedback)(GLenum primitiveMode);
-            void (*EndTransformFeedback)();
-            // ARB_transform_feedback2. A backend that leaves these null keeps the single
-            // implicit capture span the frontend has always modelled; the frontend state
-            // (paused flag, per-object bindings) is tracked either way.
-            void (*PauseTransformFeedback)();
-            void (*ResumeTransformFeedback)();
-            void (*BindTransformFeedback)(GLuint name);
-            void (*DeleteTransformFeedback)(GLuint name);
             Int64 (*GetGpuTimestampNs)(); // glGetInteger64v(GL_TIMESTAMP); 0 if unsupported
         };
         struct GlobalBackendFunctionsTable {
@@ -316,29 +230,8 @@ namespace MobileGL {
             void (*SetSwapInterval)(Int interval);
         };
 
-        // Coarse GPU vendor identity for gating device-specific quirks. Detected from the
-        // Vulkan physical-device vendorID or the GLES GL_VENDOR/GL_RENDERER strings; stays
-        // Unknown when detection is inconclusive, in which case auto-gated quirks stay off.
-        enum class GpuVendorKind : Uint8 {
-            Unknown = 0,
-            Qualcomm,
-            Arm,
-            Nvidia,
-            Amd,
-            Intel,
-            ImgTec,
-            // Software rasterizers (llvmpipe/lavapipe, SwiftShader).
-            Software,
-        };
-
         struct DynamicBackendParameters {
-            Uint64 UniformBufferOffsetAlignment = 256;
-            // GL_SHADER_STORAGE_BUFFER_OFFSET_ALIGNMENT, which is a SEPARATE limit from the
-            // uniform one and is routinely larger: Adreno 830 reports 32 for uniform buffers and
-            // 64 for storage buffers. Answering the storage query with the uniform value let an
-            // application bind a storage range at an offset the driver cannot address, which it
-            // accepted without error and then wrote somewhere else entirely.
-            Uint64 ShaderStorageBufferOffsetAlignment = 256;
+            SizeT UniformBufferOffsetAlignment = 256;
             // GL_MAX_TEXTURE_MAX_ANISOTROPY_EXT. 1.0 means the backend cannot filter anisotropically,
             // which is also why the extension is not advertised in that case.
             Float MaxTextureMaxAnisotropy = 1.0f;
@@ -364,13 +257,6 @@ namespace MobileGL {
             Int MaxIntegerSamples = 1;
             Int MaxSamples = 1;
             Int MaxSampleMaskWords = 1;
-            // Tessellation limits; defaults are the GL 4.0 core minimums.
-            Int MaxPatchVertices = 32;
-            Int MaxTessGenLevel = 64;
-            // GL_MIN/MAX_PROGRAM_TEXTURE_GATHER_OFFSET. Defaults are the GL 4.0 core
-            // minimums, which every ES 3.1 driver also guarantees.
-            Int MinProgramTextureGatherOffset = -8;
-            Int MaxProgramTextureGatherOffset = 7;
             Int MaxTextureImageUnits = 32;
             Int MaxVertexTextureImageUnits = 32;
             Int MaxComputeTextureImageUnits = 32;
@@ -378,41 +264,10 @@ namespace MobileGL {
             Int MaxVertexAttribs = 16;
             Int MaxComputeShaderStorageBlocks = 8;
             Int MaxCombinedShaderStorageBlocks = 32;
-            // Per-stage GL_MAX_*_SHADER_STORAGE_BLOCKS. Zero is a legal answer for the four
-            // non-compute, non-fragment stages and these defaults are the spec minimums, not
-            // placeholders: GL 4.6 table 23.64 and ES 3.2 table 21.44 both set the minimum for
-            // vertex, tessellation control, tessellation evaluation and geometry at 0, and only
-            // fragment (8 in GL, 4 in ES) and compute are guaranteed to have any. Every real ARM
-            // GLES driver takes that allowance - a Mali-G925 reports 0 for all four - so a
-            // backend that cannot honour a graphics-stage storage block MUST report 0 here
-            // rather than a hopeful number. Advertising a non-zero count the driver will refuse
-            // does not make the block work; it only moves the failure from an honest
-            // "unsupported" at query time to a backend link error the frontend never surfaces,
-            // after which every draw with that program silently renders nothing.
-            Int MaxVertexShaderStorageBlocks = 0;
-            Int MaxTessControlShaderStorageBlocks = 0;
-            Int MaxTessEvaluationShaderStorageBlocks = 0;
-            Int MaxGeometryShaderStorageBlocks = 0;
-            Int MaxFragmentShaderStorageBlocks = 8;
             Int MaxComputeUniformBlocks = 12;
             Int MaxComputeWorkGroupInvocations = 128;
-            // GL_MAX_COMPUTE_WORK_GROUP_COUNT / GL_MAX_COMPUTE_WORK_GROUP_SIZE, one value per
-            // axis. These six, with the invocations limit above, are the only indexed limits a
-            // backend genuinely OWNS - the device answers them (glGetIntegeri_v on DirectGLES,
-            // VkPhysicalDeviceLimits::maxComputeWorkGroupCount/Size on DirectVulkan) - and so
-            // the only ones that survive the retirement of the GetIntegeri_v table entry: they
-            // cross the MGPipe boundary inside MGPCaps, by inclusion of this struct (plan B
-            // section 4.4.1). Every other indexed pname names frontend state. RAW driver
-            // answers, like the invocations limit: GL_Getter and the compile environment floor
-            // them at the shared MIN_COMPUTE_WORK_GROUP_* minimums themselves. The defaults are
-            // the GL 4.3 core minimums (table 23.60) and describe the no-backend case, as
-            // MaxClipDistances' does.
-            Int MaxComputeWorkGroupCount[3] = {65535, 65535, 65535};
-            Int MaxComputeWorkGroupSize[3] = {1024, 1024, 64};
             Int MaxShaderStorageBufferBindings = 8;
             Int MaxTextureBufferSize = 65536;
-            // GL_TEXTURE_BUFFER_OFFSET_ALIGNMENT; 1 means the offset is unconstrained.
-            Int TextureBufferOffsetAlignment = 1;
             Int MaxUniformBufferBindings = 24;
             Int MaxUniformBlockSize = 16384;
             Int MaxImageUnits = 8;
@@ -423,155 +278,26 @@ namespace MobileGL {
             Int MaxComputeImageUniforms = 8;
             Int MaxDrawBuffers = 8;
             Int MaxColorAttachments = 8;
-            // GL_MAX_CLIP_DISTANCES. Zero is a legal answer here, not a placeholder, and a
-            // backend that cannot host a clip distance MUST report it: advertising eight the
-            // backend will refuse does not make gl_ClipDistance work, it only moves the failure
-            // from an honest "unsupported" at query time to a backend shader-compile error the
-            // frontend never surfaces, after which every draw with that program silently renders
-            // nothing. DirectGLES fills it from GL_EXT_clip_cull_distance, DirectVulkan from the
-            // shaderClipDistance device feature. The DEFAULT stays at the GL 4.3 core minimum
-            // because it describes the no-backend case (standalone shader compiles, unit tests),
-            // where there is no device to be honest about and BuildTBuiltInResource still has to
-            // hand glslang a workable gl_MaxClipDistances.
             Int MaxClipDistances = 8;
-            // GL_MAX_CULL_DISTANCES and GL_MAX_COMBINED_CLIP_AND_CULL_DISTANCES, under exactly
-            // the contract stated for MaxClipDistances above: ZERO IS A LEGAL ANSWER and a
-            // backend that cannot host a cull distance MUST report it. The failure this prevents
-            // is worse than the clip one, because cull distance discards the whole primitive:
-            // glslang bounds gl_CullDistance[i] against maxCullDistances and expands
-            // gl_MaxCullDistances from it, SPIRV-Cross then emits
-            // `#extension GL_EXT_clip_cull_distance : require` into the ESSL, and a host driver
-            // without that extension rejects the program in an info log nobody surfaces. These
-            // used to be bare 8s inside BuildTBuiltInResource with no backend consulted at all.
-            // The DEFAULTS are the GL 4.5 core minimums for the same reason MaxClipDistances'
-            // is: they describe the no-backend case (standalone compiles, unit tests).
-            Int MaxCullDistances = 8;
-            Int MaxCombinedClipAndCullDistances = 8;
             Int MaxViewports = 16;
-            // GL_LAYER_PROVOKING_VERTEX / GL_VIEWPORT_INDEX_PROVOKING_VERTEX: which vertex of a
-            // primitive supplies gl_Layer and gl_ViewportIndex. GL 4.6 table 23.65 makes
-            // GL_UNDEFINED_VERTEX a legal answer for both, and it is the honest default - naming
-            // a convention is a statement about behaviour, so a backend that does not pin one
-            // must not claim it does. DirectGLES fills the layer one from the ES 3.2 query and
-            // the viewport one from GL_OES_viewport_array, and leaves UNDEFINED where the
-            // capability is absent: without the viewport array extension only viewport 0 is ever
-            // rasterized, so no convention selects anything. DirectVulkan keeps UNDEFINED for
-            // both - which vertex provokes is decided per pipeline by
-            // VulkanRenderer::SelectProvokingVertexMode out of VK_EXT_provoking_vertex,
-            // provokingVertexModePerPipeline and the topology, so no single convention is true
-            // of the backend.
-            Uint32 LayerProvokingVertex = GL_UNDEFINED_VERTEX;
-            Uint32 ViewportIndexProvokingVertex = GL_UNDEFINED_VERTEX;
             Int MaxViewportWidth = 16384;
             Int MaxViewportHeight = 16384;
             Float ViewportBoundsRangeMin = 0.0f;
             Float ViewportBoundsRangeMax = 0.0f;
             Int ViewportSubpixelBits = 0;
-            // GL 4.x fragment-interpolation offset limits. These defaults are the
-            // core minimums and are replaced by live GLES/Vulkan device limits.
-            Float MinFragmentInterpolationOffset = -0.5f;
-            // For four fractional bits the greatest required legal offset is
-            // 0.5 - 2^-4 = 0.4375 (GL 4.6 table 23.70).
-            Float MaxFragmentInterpolationOffset = 0.4375f;
-            Int FragmentInterpolationOffsetBits = 4;
             Bool SupportsWideLines = false;
-            // Whether a framebuffer whose depth and stencil attachments are distinct
-            // images can be rendered to. GL only requires support when both refer to the
-            // same image and lets an implementation answer GL_FRAMEBUFFER_UNSUPPORTED
-            // otherwise, which is what DirectVulkan (one combined attachment) and the
-            // real ES drivers behind DirectGLES both do. Defaults to true so a backend
-            // that never sets it keeps the permissive behaviour.
-            Bool SupportsDistinctDepthStencilAttachments = true;
-            // Whether attaching a single layer of a 3D or array texture to a framebuffer actually
-            // renders to that layer. DirectGLES hands the layer straight to
-            // glFramebufferTextureLayer, so it does; DirectVulkan maps a GL layer onto a Vulkan
-            // array layer with no notion of a 3D depth slice, so it does not yet. Defaults to false
-            // so a backend that never sets it gets the conservative answer.
-            // Which layered texture targets this backend can attach ONE layer of to a framebuffer
-            // and then really clear, render and read back that layer. Bit (1u << TextureTarget) is
-            // set for each supported target. Deliberately per target rather than one flag: the three
-            // ways a GL layer maps onto Vulkan are independent capabilities. A 2D or 2D multisample
-            // array layer IS a VkImage array layer and needs nothing extra; a 3D texture's layer is
-            // a z slice, which needs a 2D-array-compatible image and a per-slice clear that
-            // vkCmdClearColorImage cannot express; a cube map array needs an image shape and the
-            // imageCubeArray feature before it can be attached at any layer at all. Defaults to 0 so
-            // a backend that never sets it gets the conservative answer.
-            Uint32 PerLayerFramebufferAttachmentTargets = 0;
-
-            static constexpr Uint32 PerLayerFramebufferAttachmentBit(TextureTarget target) {
-                return (static_cast<Int>(target) >= 0 &&
-                        static_cast<Int>(target) < static_cast<Int>(TextureTarget::TextureTargetCount))
-                           ? (1u << static_cast<Uint32>(target))
-                           : 0u;
-            }
-
-            Bool SupportsPerLayerFramebufferAttachment(TextureTarget target) const {
-                const Uint32 bit = PerLayerFramebufferAttachmentBit(target);
-                return bit != 0 && (PerLayerFramebufferAttachmentTargets & bit) != 0;
-            }
-            // Whether this backend can CONSUME a shader module that still declares 64-bit floats,
-            // i.e. whether `double` survives the transpile instead of being narrowed to `float`
-            // (ShaderTranspiler::DemoteFloat64Pass). Detected, never assumed:
-            //   * DirectVulkan sets it from VkPhysicalDeviceFeatures::shaderFloat64, the feature
-            //     VUID-VkShaderModuleCreateInfo-pCode-08740 requires before a module declaring
-            //     OpCapability Float64 may be created at all. lavapipe has it; Adreno and Mali
-            //     both report VK_FALSE, so no real mobile device does.
-            //   * DirectGLES can NEVER have it. GLSL ES has no 64-bit float type in any version
-            //     or extension, so SPIRV-Cross cannot emit one ("FP64 not supported in ES
-            //     profile") and the demotion there is mathematically mandatory, always.
-            // Defaults to false so a backend that never sets it - and the no-backend case, which
-            // is what standalone shader compiles and the unit tests run under - keeps the
-            // demotion, which is the behaviour that works everywhere.
-            Bool SupportsShaderFloat64 = false;
-            // Whether glVertexAttribLFormat / glVertexArrayAttribLFormat can be honoured, i.e.
-            // whether a 64-bit vertex attribute can actually reach a shader unconverted. Detected,
-            // never assumed: DirectVulkan needs VkPhysicalDeviceFeatures::shaderFloat64 (the
-            // attribute travels as its 32-bit word pair, so no VK_FORMAT_R64* is required, but the
-            // bitcast result is Float64); DirectGLES can never have it, ESSL having no fp64 type at
-            // all. Defaults to false so a backend that never sets it gets the conservative answer.
-            //
-            // INDEPENDENT of SupportsShaderFloat64, and it has to be: this flag decides a VkFormat
-            // from the VAO ATTRIBUTE alone, which does not know what type the shader declared, and
-            // glVertexAttribFormat(GL_DOUBLE) feeding a plain `in vec4` is both legal and common
-            // (KHR-GL43.vertex_attrib_binding.basic-input-case4/5, advanced-bindingUpdate). A
-            // backend with native fp64 that still cannot FETCH 64 bits keeps this false and relies
-            // on the per-MODULE rule in ShaderCompiler::SanitizeAndOptimizeBinary instead: a vertex
-            // module that declares a 64-bit float INPUT is demoted whole, so the two shader-side
-            // halves (PackDoubleVertexInputsPass and VertexInputStateFactory::ToVkVertexFormat)
-            // still see one consistent world.
-            Bool SupportsFloat64VertexAttributes = false;
-            // Whether a TESSELLATION stage of this backend may access gl_PointSize - i.e.
-            // whether a module declaring OpCapability TessellationPointSize can reach the
-            // driver at all. DirectVulkan sets both this and the geometry twin from the one
-            // shaderTessellationAndGeometryPointSize feature; DirectGLES sets them
-            // independently from the EXT/OES_tessellation_point_size /
-            // geometry_point_size extension pairs (PointSizeTier), which really do come
-            // separately. When absent, ProgramSpirvTask demotes the built-in to an ordinary
-            // varying program-wide (ShaderCompiler::
-            // DemoteTessellationGeometryPointSizeForProgram); MOBILEGL_POINT_SIZE_DEMOTION
-            // overrides the detection in either direction at backend init.
-            //
-            // Defaults TRUE, deliberately against the house "assume absent" rule: false
-            // ARMS a rewrite, so the conservative no-backend answer (standalone compiles,
-            // unit tests) is the one that leaves modules untouched. A backend that never
-            // sets it gets standard modules and, at worst, the old honest declines.
-            Bool SupportsTessellationPointSize = true;
-            // The geometry-stage twin (OpCapability GeometryPointSize).
-            Bool SupportsGeometryPointSize = true;
-            Uint64 MaxShaderStorageBlockSize = 128 * 1024 * 1024;
+            SizeT MaxShaderStorageBlockSize = 128 * 1024 * 1024;
             Uint32 SubgroupSize = 0;
             Uint32 SubgroupSupportedStages = 0;
             Uint32 SubgroupSupportedFeatures = 0;
             Bool SubgroupQuadOperationsInAllStages = false;
-            GpuVendorKind GpuVendor = GpuVendorKind::Unknown;
         };
 
         enum class WindowBackend {
             Android,
             X11,
             MetalLayer,
-            Win32, // Handle is an HWND
-            // TODO: Wayland, etc.
+            // TODO: Wayland, Windows, etc.
             WindowBackendCount,
             Unknown = -1
         };

MobileGL/MG_Backend/BackendObjects.h

@@ -13,47 +13,6 @@
 #include "DirectVulkan/BackendObject_DirectVulkan.h"
 
 namespace MobileGL::MG_Backend {
-    extern UniquePtr<BackendObject>& pActiveBackendObject;
+    extern UniquePtr<BackendObject> pActiveBackendObject;
     extern GlobalBackendFunctionsTable gBackendFunctionsTable;
-
-#if MOBILEGL_BUILD_DISAGGREGATED
-    // P5 v1. The counterpart of Init()'s single split hook, and a NO-OP in every run that is
-    // not split. It exists ONLY in a split build: G1 admits no new symbol in the pull build,
-    // so MobileGL/Init.cpp's call sits under the same #if rather than calling a no-op.
-    //
-    // IT MUST RUN FIRST, BEFORE ANYTHING ELSE IN DestroyImpl. ARCHITECTURE.md:537's order is
-    // publish -> the server drains and acks -> stop the apply thread (Kill, then join) -> close
-    // the transport -> the client drains the compile pool -> MobileGL::Destroy() -> release the
-    // sync/query handles; DestroyImpl IS MobileGL::Destroy, so everything before that arrow has
-    // to happen at its top. Two consequences are load-bearing rather than tidy:
-    //
-    //   * the apply thread is JOINED before PipeStats::Shutdown() dumps, so nothing is writing
-    //     a counter while the final line is produced;
-    //   * the apply thread is joined before pActiveBackendObject.reset(), so the server's own
-    //     BackendObject - which is NOT that global (table 3) - is destroyed on the thread that
-    //     owns the context, by ServerLoop::Stop, rather than on the app thread.
-    //
-    // The sync/query registries stay where they are, drained at MobileGL/Init.cpp:62 and :67
-    // BEFORE pActiveBackendObject.reset(). ARCHITECTURE.md:537 puts them after
-    // MobileGL::Destroy(); the two are only reconcilable if a split sync handle is
-    // client-minted and needs no backend call, which is P10's. CONTRACT-P5 4 flags this as a
-    // KNOWN OPEN ITEM and asks v1 to record which way it went: P5 keeps today's order.
-    void ShutdownSplitRoles();
-
-    // F1 (P7 wave 2). Init()'s SPLIT ARM, run BEFORE MG_State::Init() rather than after it.
-    //
-    // Returns true when this process took the split path - whether the bring-up succeeded or
-    // was refused by name - and the caller must then NOT call Init() a second time. Returns
-    // false under MG_Config::TransportMode::Monolith, where there is nothing to bring up and
-    // Init() keeps its own place after MG_State::Init().
-    //
-    // WHY IT EXISTS AT ALL, rather than MobileGL::Initialize simply calling Init() earlier:
-    // the monolith arm of Init() must keep running after MG_State::Init(), because
-    // BackendObject_DirectGLES::Initialize() is the tree's own order for it and moving it is a
-    // pull-build change G1 forbids. So the split arm - and only the split arm - moves.
-    //
-    // It exists ONLY in a split build, for the reason InitServerRoleForSpawn states: a
-    // definition guarded only on the inside still emits a symbol, and G1 measured that.
-    Bool InitSplitRolesBeforeState();
-#endif
 } // namespace MobileGL::MG_Backend

MobileGL/MG_Backend/DirectGLES/BackendObject_DirectGLES.h

@@ -18,16 +18,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
                                     const MG_External::GLESCapabilities& capabilities,
                                     FormatCapabilityCache& cache);
 
-    // Clamps a requested sample count down to what the ES driver can really deliver for this
-    // format on this format-capability target: the probed per-format list when there is one, the
-    // driver's per-class GL_MAX_*_SAMPLES otherwise. The frontend deliberately validates against
-    // the count MobileGL advertises instead (GL_Getter's GetAdvertisedMaxSamples), which on a
-    // driver reporting GL_MAX_INTEGER_SAMPLES 1 is higher than the driver accepts, so every ES
-    // allocation call has to come through here. The shadow state keeps the requested count, so
-    // GL_TEXTURE_SAMPLES and framebuffer completeness still answer what the application asked for.
-    Int ClampSamplesToBackendSupport(SizeT targetIndex, TextureInternalFormat logicalFormat, GLenum imageFormat,
-                                     Int samples);
-
     class BackendObject_DirectGLES : public BackendObject {
     public:
         ~BackendObject_DirectGLES() override;
@@ -77,13 +67,9 @@ namespace MobileGL::MG_Backend::DirectGLES {
     const RendererInfo& GetRendererIdentity();
 
     // The full OpenGL extension list Espryt advertises (glGetString(GL_EXTENSIONS))
-    // for a device whose timer queries / anisotropic filtering / native indirect draws /
-    // non-zero indirect baseInstance semantics / EXT-OES texture views are (or are not) usable.
+    // for a device whose timer queries / anisotropic filtering are (or are not) usable.
     // The MOBILEGL_DISABLE_TIMERQUERY escape hatch is applied inside.
-    Vector<GLExtension> BuildAdvertisedExtensions(Bool timerQueriesSupported, Bool anisotropicFilteringSupported,
-                                                  Bool drawIndirectSupported,
-                                                  Bool nonZeroIndirectBaseInstanceSupported,
-                                                  Bool textureViewSupported, Bool cubeMapArraySupported);
+    Vector<GLExtension> BuildAdvertisedExtensions(Bool timerQueriesSupported, Bool anisotropicFilteringSupported);
 
     // Format: <OpenGL ES Renderer>, OpenGL ES <Major>.<Minor> — the exact string an
     // initialized backend returns from GetBackendAPIVersionString (and that ends up

MobileGL/MG_Backend/DirectGLES/ContextEpoch.h

@@ -1,23 +0,0 @@
-// MobileGL - DirectGLES context-owned static state identities (P5f fs).
-#pragma once
-
-#if MOBILEGL_BUILD_DISAGGREGATED
-#include <Config.h>
-#include <MG_Pipe/PipeApply.h>
-
-namespace MobileGL::MG_Backend::DirectGLES {
-    extern Uint g_backendContextGeneration;
-
-    struct ContextEpoch {
-        Uint Native = 0;
-        Uint64 Served = 0;
-        Bool Server = false;
-        Bool operator==(const ContextEpoch&) const = default;
-    };
-
-    inline ContextEpoch CurrentContextEpoch() {
-        const Bool server = MG_Config::Transport != MG_Config::TransportMode::Monolith;
-        return {g_backendContextGeneration, server ? MG_Pipe::MGPipeApplierContextSerial() : 0, server};
-    }
-}
-#endif

MobileGL/MG_Backend/DirectGLES/DirectGLES.h

@@ -23,16 +23,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
     // Content uploads use scratch bindings, so draws and dispatches call this after
     // texture synchronization.
     void BindCurrentTextures();
-#if MOBILEGL_BUILD_DISAGGREGATED
-    Bool ReadTextureImageWire(const MG_Pipe::MGPReadbackInfo& info, Vector<Uint8>& bytes);
-    // Native/server-only color level readback. Returns tightly packed, owned
-    // bytes in the requested pair; never consults a frontend texture or PACK/PBO.
-    // The caller resolves identity/extent from its resource record and supplies
-    // whether the SOURCE allocation already uses an image carrier.
-    Bool ReadTextureLevelTight(GLuint texture, TextureTarget target, TextureUploadTarget uploadTarget,
-                               TextureInternalFormat logicalFormat, GLint level, const IntVec3& logicalExtent,
-                               Bool sourceUsesImageCarrier, GLenum format, GLenum type, Vector<Uint8>& bytes);
-#endif
     void ClearBufferfi(GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
     void ClearBufferfv(GLenum buffer, GLint drawbuffer, const GLfloat* value);
     void ClearBufferuiv(GLenum buffer, GLint drawbuffer, const GLuint* value);
@@ -50,8 +40,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
     void MultiDrawElementsIndirectCount(GLenum mode, GLenum type, const void* indirect, GLintptr drawcount,
                                         GLsizei maxdrawcount, GLsizei stride);
     void MultiDrawArraysIndirect(GLenum mode, const void* indirect, GLsizei drawcount, GLsizei stride);
-    void MultiDrawArraysIndirectCount(GLenum mode, const void* indirect, GLintptr drawcount, GLsizei maxdrawcount,
-                                      GLsizei stride);
     void DrawRangeElementsBaseVertex(GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type,
                                      const void* indices, GLint basevertex);
     void DrawRangeElements(GLenum mode, GLuint start, GLuint end, GLsizei count, GLenum type, const void* indices);
@@ -71,10 +59,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
                                  GLenum buffer, GLint drawbuffer, const GLfloat* value);
     void ClearNamedFramebufferfi(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
                                  GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
-    void ClearNamedFramebufferiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
-                                 GLenum buffer, GLint drawbuffer, const GLint* value);
-    void ClearNamedFramebufferuiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer,
-                                  GLenum buffer, GLint drawbuffer, const GLuint* value);
     void BlitFramebuffer(GLint srcX0, GLint srcY0, GLint srcX1, GLint srcY1, GLint dstX0, GLint dstY0, GLint dstX1,
                          GLint dstY1, GLbitfield mask, GLenum filter);
     void BlitNamedFramebuffer(const SharedPtr<MG_State::GLState::FramebufferObject>& readFramebuffer,
@@ -86,9 +70,9 @@ namespace MobileGL::MG_Backend::DirectGLES {
                         GLsizei height, GLint border);
     void CopyTexSubImage2D(GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y, GLsizei width,
                            GLsizei height);
-    void CopyImageSubData(const CopyImageEndpoint& src,
+    void CopyImageSubData(const SharedPtr<MG_State::GLState::ITextureObject>& srcTexture,
                           GLenum srcTarget, GLint srcLevel, GLint srcX, GLint srcY, GLint srcZ,
-                          const CopyImageEndpoint& dst,
+                          const SharedPtr<MG_State::GLState::ITextureObject>& dstTexture,
                           GLenum dstTarget, GLint dstLevel, GLint dstX, GLint dstY, GLint dstZ,
                           GLsizei srcWidth, GLsizei srcHeight, GLsizei srcDepth);
     void GenerateMipmap(GLenum target);
@@ -102,7 +86,17 @@ namespace MobileGL::MG_Backend::DirectGLES {
     void BindImageTexture(GLuint unit, GLuint texture, GLint level, GLboolean layered, GLint layer, GLenum access,
                           GLenum format);
     void GetIntegeri_v(GLenum target, GLuint index, GLint* data);
-    void ShaderStorageBlockBinding(GLuint program, const GLchar* storageBlockName, GLuint storageBlockBinding);
+    void GetInteger64i_v(GLenum target, GLuint index, GLint64* data);
+    void GetProgramiv(GLuint program, GLenum pname, GLint* params);
+    void GetProgramInterfaceiv(GLuint program, GLenum programInterface, GLenum pname, GLint* params);
+    GLuint GetProgramResourceIndex(GLuint program, GLenum programInterface, const GLchar* name);
+    void GetProgramResourceName(GLuint program, GLenum programInterface, GLuint index, GLsizei bufSize, GLsizei* length,
+                                GLchar* name);
+    void GetProgramResourceiv(GLuint program, GLenum programInterface, GLuint index, GLsizei propCount,
+                              const GLenum* props, GLsizei bufSize, GLsizei* length, GLint* params);
+    GLint GetProgramResourceLocation(GLuint program, GLenum programInterface, const GLchar* name);
+    GLint GetProgramResourceLocationIndex(GLuint program, GLenum programInterface, const GLchar* name);
+    void ShaderStorageBlockBinding(GLuint program, GLuint storageBlockIndex, GLuint storageBlockBinding);
     Bool InitWindowSurface(NativeWindowType window);
     Bool InitPbufferSurface(EGLint width, EGLint height);
     Bool MakeCurrent();
@@ -127,24 +121,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
     // capability read needs no current ES context, and it stays false until
     // the ES capabilities have been filled in.
     Bool AreTimerQueriesSupported();
-    // True when the host ES driver can back a GL_TEXTURE_BUFFER at all - ES 3.2 core, or
-    // EXT/OES_texture_buffer, with glTexBuffer resolved. Desktop GL has had buffer textures as
-    // core since 3.1, so the frontend advertises them unconditionally and an app may call
-    // glTexBuffer whenever it likes; this is the only thing standing between that call and a
-    // null entry point. False also means every shader declaring a samplerBuffer is
-    // uncompilable on this driver, which the program build reports by name.
-    Bool AreBufferTexturesSupported();
-    // Human-readable name of the buffer-texture tier for diagnostics and the driver POST:
-    // "core (ES 3.2)", "GL_EXT_texture_buffer", "GL_OES_texture_buffer" or "unsupported".
-    const char* GetBufferTextureTierName();
-    // glTexBuffer / glTexBufferRange through whichever spelling this driver's buffer-texture
-    // support actually ships: the unsuffixed names are ES 3.2 core, while an EXT/OES driver
-    // exports glTexBuffer{,Range}EXT / OES. Callers must have checked
-    // AreBufferTexturesSupported() first. CallTexBufferRange reports whether it could honour
-    // the range - no tier is required to expose the range form, and the whole-buffer form is
-    // the documented fallback.
-    void CallTexBuffer(GLenum target, GLenum internalFormat, GLuint buffer);
-    Bool CallTexBufferRange(GLenum target, GLenum internalFormat, GLuint buffer, GLintptr offset, GLsizeiptr size);
     // GL timer-query objects, backed by GL_EXT_disjoint_timer_query. The
     // creators return null (the frontend then falls back to an immediately
     // available zero result) when the calling thread does not own the ES
@@ -154,16 +130,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
     BackendQueryHandle BeginTimeElapsedQuery();
     void EndTimeElapsedQuery(BackendQueryHandle query);
     BackendQueryHandle QueryCounterTimestamp();
-    // GL_ANY_SAMPLES_PASSED(_CONSERVATIVE) occlusion queries: core ES3, independent of
-    // GL_EXT_disjoint_timer_query and of MOBILEGL_DISABLE_TIMERQUERY. Results/deletion
-    // flow through GetQueryResult64/DeleteBackendQuery like the timer queries above.
-    BackendQueryHandle BeginOcclusionQuery();
-    void EndOcclusionQuery(BackendQueryHandle query);
-    // GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN / GL_PRIMITIVES_GENERATED, also core ES
-    // (GL_PRIMITIVES_GENERATED from ES 3.2 on). Null when the target is unavailable, in
-    // which case the frontend falls back to counting primitives from the draw calls.
-    BackendQueryHandle BeginXfbPrimitivesQuery(Bool generated);
-    void EndXfbPrimitivesQuery(BackendQueryHandle query);
     Bool IsQueryResultAvailable(BackendQueryHandle query);
     // Returns true when a final value landed in *outNanoseconds (a zero for
     // null or stale-generation handles IS final: the frontend may cache it
@@ -180,69 +146,14 @@ namespace MobileGL::MG_Backend::DirectGLES {
     // A buffer retired during frame N is safe to recycle once CompletedFrameSerial() >= N.
     Uint64 CurrentFrameSerial();
     Uint64 CompletedFrameSerial();
-    // Block (up to timeoutNs) until the given frame serial provably retired on the
-    // GPU, using the per-frame fence ring. False when no usable fence covers the
-    // serial (fence-less context, foreign thread, or the slot was recycled);
-    // completion state is untouched in that case.
-    Bool WaitForFrameSerialCompleted(Uint64 serial, Uint64 timeoutNs);
     // Applies (or defers until the window surface exists) the app-requested
     // eglSwapInterval on the native EGL surface.
     void SetSwapInterval(Int interval);
-#if MOBILEGL_BUILD_DISAGGREGATED
-    // P12 review fix: the swap interval an ended server session asked for is not the next one's.
-    // The request outlives the context on purpose (a surface re-created mid-session re-applies it),
-    // so the in-process display server's session end forgets it: the next session starts at the
-    // driver's default until it asks (BackendObject_DirectGLES's destructor under a transport).
-    void ForgetRequestedSwapInterval();
-#endif
     void SetEGLFuncsTable(const MG_External::EGLFunctionsTable& eglFuncs);
     void SetGLESFuncsTable(const MG_External::GLESFunctionsTable& glesFuncs);
     void SetGLESCapabilities(const MG_External::GLESCapabilities& capabilities);
     void DestroyEGLContext();
 
-    // Transform feedback capture spans, performed by the real ES driver. The
-    // capture set is declared on the backend program at link time; the driver-side
-    // begin is deferred to the first draw of the span (ES needs the capturing
-    // program current and the capture buffers bound), and the end also mirrors the
-    // captured bytes back into the frontend buffer shadows.
-    void PatchParameteri(GLenum pname, GLint value);
-
-    namespace XfbImpl {
-        Bool AreTransformFeedbacksSupported();
-        // True while a capture span is open on the current transform feedback object
-        // (frontend Begin seen and not paused), whether or not the deferred driver-side
-        // Begin has been issued yet. Draw paths that would restructure the primitive
-        // stream, or that need to dispatch compute mid-draw, decline while it is set.
-        Bool IsCaptureSpanOpen();
-        void BeginTransformFeedback(GLenum primitiveMode);
-        void EndTransformFeedback();
-        void PauseTransformFeedback();
-        void ResumeTransformFeedback();
-        void BindTransformFeedback(GLuint name);
-        void DeleteTransformFeedback(GLuint name);
-        void OnBackendContextDestroyed();
-    } // namespace XfbImpl
-
-    namespace RenderStateImpl {
-        // Pushes the frontend's render-state block to the ES driver, diffed against what was
-        // last pushed.
-        //
-        // `forColorClear` names the CALLER, and the only thing it changes is the colour write
-        // mask handed to the driver. A draw into a colour attachment the backend widened from
-        // three channels to four gets that buffer's alpha channel masked OFF, so nothing can
-        // move the stored alpha away from the 1.0 the application's three-channel format
-        // implies (see FramebufferImpl::g_alphaWidenedDrawBufferMask). A CLEAR is how that 1.0
-        // gets there in the first place, so it must be allowed to write alpha - hence the flag
-        // rather than an unconditional doctoring. It is part of the sync memo, so a clear
-        // followed by a draw re-pushes the mask instead of early-outing on an unchanged
-        // frontend version.
-        //
-        // The application's own colour mask is never modified: glGet(GL_COLOR_WRITEMASK)
-        // answers from the frontend state, which this function only reads.
-        void SyncRenderState(Bool forColorClear = false);
-        void InvalidateSyncedRenderState();
-    } // namespace RenderStateImpl
-
     extern MG_External::EGLFunctionsTable g_EGLFuncs;
     extern MG_External::GLESFunctionsTable g_GLESFuncs;
     extern MG_External::GLESCapabilities g_GLESCapabilities;

MobileGL/MG_Backend/DirectGLES/MultiDraw.h

@@ -1,64 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectGLES/MultiDraw.h
-// Copyright (c) 2025-2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-
-#pragma once
-#include <Includes.h>
-#include <Config.h>
-#include "DirectGLES.h"
-
-// Emulation of the desktop glMultiDrawElements / glMultiDrawElementsBaseVertex entry
-// points on OpenGL ES, which has neither in core.
-//
-// Every strategy below is an emulation; they differ only in which driver capability
-// they lean on and in how many driver entries a batch of N sub-draws costs. The design
-// follows MobileGlues (MobileGL-Dev/MobileGlues, gl/multidraw.cpp) tier for tier, plus
-// the native GL_EXT_multi_draw_arrays interaction that MobileGL already had:
-//
-//   Ext           one glMultiDrawElementsBaseVertexEXT           1 driver entry
-//   MultiIndirect one glMultiDrawElementsIndirectEXT             1 driver entry + 1 upload
-//   Indirect      N x glDrawElementsIndirect                     N + 1 upload
-//   BaseVertex    N x glDrawElementsBaseVertex                   N
-//   DrawElements  N x glDrawElements over CPU-rebased indices    N + 1 upload
-//   Compute       1 x glDrawElements over a GPU-flattened,       1 dispatch + 1 entry
-//                 rebased index stream
-//
-// Which one runs is resolved once per ES context from the driver's capabilities,
-// capped by MOBILEGL_ESPRYT_MULTIDRAW_MODE, and can additionally be demoted per batch
-// when the batch's own shape rules a tier out (see ResolveTierForBatch in the .cpp).
-namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
-    // The tier this ES context resolved to, computed on first use and stable after.
-    MG_Config::GLESMultiDrawMode ResolvedTier();
-    // "multiindirect", "compute", ... - stable identifiers, also used by the POST row.
-    const char* TierName(MG_Config::GLESMultiDrawMode tier);
-    // One line naming the resolved tier, the tiers the driver can support, and the env
-    // clamp if one applied. For DriverPost and the startup log.
-    String DescribeTierResolution();
-
-    // The resolution itself, as a pure function of a capability set: the backend feeds
-    // it the live ES context's capabilities, DriverPost feeds it the ones it probed
-    // standalone, and both therefore report the same tier. `explanation`, when non-null,
-    // receives the "requested -> resolved (driver supports: ...)" line.
-    MG_Config::GLESMultiDrawMode ResolveTier(const MG_External::GLESCapabilities& caps,
-                                             const MG_External::GLESFunctionsTable& funcs,
-                                             MG_Config::GLESMultiDrawMode requested, String* explanation);
-    // Whether one tier is runnable on the given capability set, for per-row POST output.
-    Bool IsTierSupported(const MG_External::GLESCapabilities& caps, const MG_External::GLESFunctionsTable& funcs,
-                         MG_Config::GLESMultiDrawMode tier);
-
-    // Runs `drawcount` indexed sub-draws as one glMultiDrawElements(BaseVertex) call
-    // would. `basevertex` is null for the plain glMultiDrawElements entry point (every
-    // base vertex is 0). Owns the whole draw, preparation included: callers must not
-    // have run PrepareForDraw, because the compute tier has to dispatch before the
-    // draw state is established.
-    void DrawElementsBatch(GLenum mode, const GLsizei* count, GLenum type, const GLvoid* const* indices,
-                           GLsizei drawcount, const GLint* basevertex);
-
-    // The ES context is gone: every scratch buffer and the compute program belonged to
-    // it, so drop the names without deleting them (the dead context reclaims them).
-    void OnBackendContextDestroyed();
-} // namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl

MobileGL/MG_Backend/DirectGLES/SlotTables.h

@@ -1,785 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectGLES/SlotTables.h
-// Copyright (c) 2025-2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-
-#pragma once
-#include <Includes.h>
-
-#include <MG_Pipe/MGPipeHandles.h>
-
-#if MOBILEGL_PIPE_PUSH
-#include <MG_Impl/Pipe/SlotAllocator.h>
-#endif
-#if MOBILEGL_BUILD_DISAGGREGATED
-#include <MG_Pipe/PipeSessionFail.h>
-#endif
-
-// Espryt 0b, the first Track H slice: the DENSE, {slot, gen}-keyed twin table that replaces
-// StateBackendObjectRegistry's UnorderedMap<StateObject*, Entry>.
-//
-// What changes, and why each of them is the point:
-//
-//  * The KEY stops being a frontend heap address. It is MGPipeHandle{Slot, Gen}, minted by the
-//    client's MGPipeSlotAllocator off the frontend object's GetLifetimeId(). A recycled heap
-//    address cannot reproduce a handle, so the weak_ptr the registry carried per entry purely
-//    to catch that (its Entry::stateRef, used as an IDENTITY test) stops being an identity
-//    mechanism, and OwnerEquals / TwinLookupMemo x3 / UnitSamplerLookupMemo's owner compare all
-//    lose their reason to exist.
-//  * The lookup stops being a hash probe into an open-addressed map and becomes one bounds
-//    check plus one array index, so a returned BackendPtr* is NOT invalidated by the next Find
-//    on the table. That kills the hazard Managers.h documents at length, and with it the
-//    by-value copy plus second Find that SyncTextureObjectToBackend paid to survive it.
-//  * Slots are dense per kind, which is what lets the server side (ARCHITECTURE.md 10.1,
-//    MG_Remote/Server/PipeObjectTables) be an array rather than an object graph.
-//
-// Death is ANNOUNCED, and that is what lets this table have no garbage collector - the
-// deliverable ROADMAP.md:18 spells "GC" in and the one D13 makes a precondition of the switch-
-// over. All six re-keyed object classes raise MG_State::GLState::NotifyStateObjectDestroyed()
-// from their destructor (BufferBackendOps' shape, one entry point for six kinds), the backend
-// consumes it in Managers.cpp, and OnFrontendObjectDestroyed() below drops the twin in EVERY
-// table of the kind and returns the slot, at the moment the frontend object's last SharedPtr
-// goes. So:
-//   * there is NO draw-path tick, NO creation tick and NO sweep of any kind on this arm. The
-//     seven CollectGarbageIfNeeded call sites in DirectGLES.cpp drive the LEGACY registry only;
-//   * a twin, and the driver storage it owns, is freed when the application lets go of the
-//     object rather than up to 64 creations or 1024 draw ticks later. That is what
-//     Managers.h's "dead gigabytes" note asked for.
-//
-// EVERY HOLDER OF THE KIND, not one. Two live tables of one kind is a real configuration - the
-// ScopedDirectGLESTextureBindings fixture keeps a by-value copy of the Texture registry for the
-// length of a test, and a context reset does the same in reverse - and the slot allocator
-// erases its lifetimeId -> slot mapping on Free, so a notice delivered to one holder and
-// resolved again by the next would find nothing to resolve. Every table therefore links itself
-// into a per-table-type list at construction and out at destruction, and one notice resolves
-// the handle ONCE, drops the twin in each holder BY HANDLE, and frees the slot once, last. No
-// holder can be left naming a live entry for a dead object, and there is nothing a sweep could
-// still find. (The list is per table TYPE; the kind is the type's template parameter, and each
-// of the six kinds has exactly one table type in this backend. Magma's subsystem-4 table mints
-// out of its own per-renderer allocator, not MGPipeSlots(), so it is not a holder here.)
-//
-// The weak_ptr per entry survives as the MONOLITH-GLUE half of the table's identity: the
-// minting GetOrCreate stores it, NoteStateForHandle/StateForHandle read it, and the legacy
-// death notice walks it. It is never an identity test - that is what Gen is for - and it is
-// never read to decide whether an entry is dead: a destructor that runs after exit() has begun
-// has its notice dropped by InProcessTeardown(), and that twin is then a DELIBERATE leak (the
-// process is exiting, the driver reclaims the object, and a twin destructor must not call into
-// a driver that may already be unloaded), not something to be collected later.
-//
-// P5e (id, CONTRACT-P5E §4.1): ForEachLive() NO LONGER HANDS IT OUT. It answers
-// fn(MGPipeHandle, const BackendPtr&), because a walk that produced a frontend SharedPtr out
-// of server memory was the last place the server could hold one across records - and a caller
-// that still needs the object (the detach walk) asks StateForHandle for it BY HANDLE, inside
-// the scope that names the debt, so the read is one greppable site rather than a property of
-// the iteration.
-//
-// P3+ DEBT, recorded rather than hidden: this header is under MG_Backend/ and it MINTS
-// handles (MGPipeSlots().Acquire below) off a frontend SharedPtr's GetLifetimeId().
-// MGPipeHandles.h:13-16 says a handle is minted by the CLIENT and never by the server, and
-// under a real split neither the frontend object nor its lifetime id exists on this side of
-// the wire. This is monolith glue: the minting and the lifetimeId -> handle resolution both
-// belong on the client, and the backend should receive the handle in the verb payload. It is
-// NOT part of "Track H done" and check_include_closure.py does not probe MG_Backend headers,
-// so nothing catches it automatically.
-//
-// P5c (hd, CONTRACT-P5C §3.1) is what gives the debt teeth: with an active transport the
-// minting GetOrCreate, HandleOf and OnFrontendObjectDestroyed raise
-// Fatal{RoleViolation, "MGPipeSlots"} when reached from the apply thread (the same check the
-// allocator's own three entries carry, repeated here so the refusal names this surface), and
-// the split paths resolve through GetOrCreate(handle) / ReleaseByHandle instead.
-//
-// P5f (fr): the frontend-keyed half survives only as MONOLITH GLUE. HandleOf,
-// GetOrCreate(StatePtr), NoteStateForHandle and StateForHandle refuse EVERY transport
-// apply before touching a frontend object, with or without a barrier or named scope.
-// Find(StateObject*) delegates to HandleOf; handle-only iteration never reads stateRef.
-// The registry guard is independent of Magma's legacy allocator debt scope.
-namespace MobileGL::MG_Backend::DirectGLES {
-
-#if MOBILEGL_PIPE_PUSH
-
-    // Declared in Managers.h as well; repeated here because this header is included from it
-    // before that declaration, and the table below is the arming site on this arm (D13: "the
-    // arming site moves to the slot table's first insertion").
-    void EnsureProcessTeardownSentinel();
-
-    // What the two knobs add up to. Split out as a PURE function of them so a test can drive
-    // every combination without needing a process per combination.
-    enum class EsprytSlotArmVerdict {
-        Handles, // kMGPipeSubsystemEsprytSlots is set: the {slot, gen} tables run.
-        Legacy,  // the bit is clear and the legacy address-keyed registry is reachable.
-        NoArm,   // the bit is clear AND MOBILEGL_PIPE_LEGACY_MEMOS=0 made the legacy arm
-                 // unreachable, so the operator asked for a configuration with no arm at all.
-    };
-
-    EsprytSlotArmVerdict ClassifyEsprytSlotArm(Bool subsystemBitSet, Bool legacyMemosEnabled);
-
-    // This process's verdict, read off MG_Config::Features. Latches nothing and stops nothing.
-    EsprytSlotArmVerdict CurrentEsprytSlotArmVerdict();
-
-    // Says, at backend bring-up, that the knobs leave no arm - and does NOT stop.
-    //
-    // The stop cannot live here, and that is the whole point of the split. Backend context
-    // creation runs inside eglMakeCurrent, and the integration harness pre-flights exactly that
-    // sequence in a FORKED CHILD (MG_IntegrationTest/Harness/HeadlessGL.cpp): a child that dies
-    // on a signal is reported as "no usable GPU/display/ICD" and every scenario in the lane is
-    // SKIPPED - i.e. the lane goes green having run nothing, on the very pair of env vars the
-    // D14/D18 A/B is driven with, which is what ROADMAP.md:7 forbids. So bring-up only
-    // DIAGNOSES; the stop is raised by ResolveEsprytSlotTablesArm() at the first twin lookup,
-    // which happens in the test body where the harness reports it as a failure.
-    //
-    // The CALL SITE (InitDisplayAndContext in DirectGLES.cpp) is pinned by
-    // DirectGLESSlotTable.EglBringUpUnderTheArmlessKnobPairReturnsInsteadOfStopping, which runs
-    // the real bring-up entry point under the pair in a forked child: edit that site back to
-    // ResolveEsprytSlotTablesArm() and the case fails naming both knobs.
-    void DiagnoseEsprytSlotArm();
-
-    // Reads the config, logs, installs the death-notice consumer, and STOPS when the operator
-    // left no arm at all. Cold: called exactly once per process, from the latch below - i.e. at
-    // the first twin lookup, which is the first moment an arm is actually needed. A process
-    // that never twins anything needs no arm and is not stopped.
-    Bool ResolveEsprytSlotTablesArm();
-
-    // True when this process runs the {slot, gen} arm. Fixed for the life of the process: the
-    // two arms hold their twins in different containers, so flipping mid-run would strand them.
-    //
-    // INLINE on purpose. Every Find / GetOrCreate / HandleOf / ForEachLive on the twin tables
-    // consults it, i.e. it is on the per-draw path several times per draw. As an out-of-line
-    // function in Managers.cpp (no LTO in any shipped configuration) that was a call through
-    // the PLT per lookup; here the caller sees a guard-variable load and a perfectly-predicted
-    // branch, and the arm dispatch folds into the caller.
-    inline Bool EsprytSlotTablesEnabled() {
-        static const Bool enabled = ResolveEsprytSlotTablesArm();
-        return enabled;
-    }
-
-    template <typename StateObject, typename BackendObject, MG_Pipe::MGPipeKind kKind>
-    class BackendSlotTable {
-    public:
-        using StatePtr = SharedPtr<StateObject>;
-        using StateWeakPtr = std::weak_ptr<StateObject>;
-        using BackendPtr = SharedPtr<BackendObject>;
-
-        // The largest slot index this table will grow to for a handle that ARRIVED in a call's
-        // payload. Slots are dense and allocated per kind, so a million of one kind is already
-        // far past any application's live object count; the cap is here because the alternative
-        // is letting a corrupt 32-bit slot decide a vector resize. See GetOrCreate(MGPipeHandle).
-        static constexpr Uint32 kMaxHandleSlot = 1u << 20;
-
-        // P5e (id), CONTRACT-P5E §4.3: THE COMPOSITE BAND, and it is a P5e PREREQUISITE rather
-        // than a follow-up. ShaderCso's top 1/16 of slot space (from
-        // kMGPipeShaderCsoCompositeSlotBase = 983040) is the program-pipeline composites'
-        // (MGPipeHandles.h); EntryAt below indexes m_slots BY SLOT and resizes to it, so a
-        // single composite used to grow g_backendProgramObjects to ~983k entries of ~40 B -
-        // ~40 MB for one program pipeline. Today that is reachable only through
-        // GetOrCreate(StatePtr) for a composite program; after the rekey the by-handle
-        // resolution IS the ordinary path, so every composite bind would pay it.
-        //
-        // A SECOND VECTOR RATHER THAN MORE OF THE FIRST, exactly as the allocator
-        // (SlotAllocator.h's KindState::BandSlots) and the applier (PipeApply.h's
-        // CompositeShaderCsos) already do, and for the same reason: both spaces stay dense
-        // against their own high-water mark, which is the property that lets the server index
-        // rather than hash. The band is EMPTY for every kind but ShaderCso and costs those
-        // kinds one empty Vector per table.
-        static constexpr Bool kHasCompositeBand = (kKind == MG_Pipe::MGPipeKind::ShaderCso);
-        static constexpr SizeT kMaxBandSlots =
-            MG_Pipe::kMGPipeShaderCsoSlotLimit - MG_Pipe::kMGPipeShaderCsoCompositeSlotBase;
-
-        struct Entry {
-            BackendPtr backend;
-            // THE MONOLITH-GLUE HALF of the entry (P5e, CONTRACT-P5E §4.1): written by the
-            // minting GetOrCreate and by NoteStateForHandle, read only by StateForHandle and
-            // the legacy death notice. Never compared against another object to decide identity
-            // - that is what Gen is for - never dereferenced for its address, and never read to
-            // decide whether the slot is dead: death is announced, not discovered. ForEachLive
-            // stopped reading it at P5e: a walk that handed a frontend SharedPtr out of server
-            // memory on every step was the last place the server could hold one across records.
-            StateWeakPtr stateRef;
-            // The generation this entry's twin was built for. An entry whose Gen no longer
-            // matches the allocator's is a twin of the slot's PREVIOUS owner.
-            Uint32 Gen = 0;
-            Bool Live = false;
-        };
-
-        // Every constructor links the table into the per-type holder list and the destructor
-        // unlinks it, so a by-value copy (the ScopedDirectGLESTextureBindings fixture's saved
-        // registry) is a holder for exactly as long as it exists. Copy and move carry the
-        // ENTRIES and the memo; the links are the table's own and are never copied.
-        BackendSlotTable() { LinkHolder(); }
-        BackendSlotTable(const BackendSlotTable& other):
-            m_slots(other.m_slots),
-            m_band(other.m_band),
-            m_nullTwin(other.m_nullTwin),
-            m_memoLifetimeId(other.m_memoLifetimeId),
-            m_memoHandle(other.m_memoHandle) {
-            LinkHolder();
-        }
-        BackendSlotTable(BackendSlotTable&& other) noexcept:
-            m_slots(std::move(other.m_slots)),
-            m_band(std::move(other.m_band)),
-            m_nullTwin(std::move(other.m_nullTwin)),
-            m_memoLifetimeId(other.m_memoLifetimeId),
-            m_memoHandle(other.m_memoHandle) {
-            other.m_slots.clear();
-            other.m_band.clear();
-            other.ForgetHandle();
-            LinkHolder();
-        }
-        BackendSlotTable& operator=(const BackendSlotTable& other) {
-            if (this != &other) {
-                m_slots = other.m_slots;
-                m_band = other.m_band;
-                m_nullTwin = other.m_nullTwin;
-                m_memoLifetimeId = other.m_memoLifetimeId;
-                m_memoHandle = other.m_memoHandle;
-            }
-            return *this;
-        }
-        BackendSlotTable& operator=(BackendSlotTable&& other) noexcept {
-            if (this != &other) {
-                m_slots = std::move(other.m_slots);
-                m_band = std::move(other.m_band);
-                m_nullTwin = std::move(other.m_nullTwin);
-                m_memoLifetimeId = other.m_memoLifetimeId;
-                m_memoHandle = other.m_memoHandle;
-                other.m_slots.clear();
-                other.m_band.clear();
-                other.ForgetHandle();
-            }
-            return *this;
-        }
-        ~BackendSlotTable() { UnlinkHolder(); }
-
-        // Resolve-or-create. The handle comes from the client allocator keyed on the frontend
-        // object's lifetime id, so two calls for the same live object always land on the same
-        // slot, and a successor object at the same heap address never does.
-        BackendPtr& GetOrCreate(const StatePtr& stateObj) {
-            // No assert on null here, unlike the map arm: null is TOLERATED, so a DEBUG build
-            // must not trap where the release build quietly does the documented thing.
-            if (stateObj == nullptr) {
-                // The registry this replaces inserted a null KEY and handed back that entry's
-                // twin (DirectGLES.cpp's SyncTextureObjectToBackend documents relying on
-                // exactly that tolerance), so a release build never dereferenced null here.
-                // Keep the shape exactly, INCLUDING across calls: the map kept its null-keyed
-                // entry, so a second null call was handed the same twin the first one got.
-                // Resetting here instead would have destroyed it - an arm difference in the one
-                // path that documents relying on this. One per-table parking slot, never live,
-                // never handed a handle, because a null object has no identity and
-                // therefore cannot have a {slot, gen}.
-                return m_nullTwin;
-            }
-
-            // D13: the teardown sentinel is armed by the slot table's first insertion. Twin
-            // creation is the moment a driver-owned id starts needing a guarded destructor;
-            // this is the cold path, so the once-guard costs nothing per draw. On the legacy
-            // arm StateBackendObjectRegistry::GetOrCreate arms it itself.
-            EnsureProcessTeardownSentinel();
-
-#if MOBILEGL_BUILD_DISAGGREGATED
-            // This overload mints from frontend identity and is monolith-only. Refuse
-            // before either the client object or allocator is touched, even when a
-            // legacy named scope is open and the current record is barriered.
-            MG_Pipe::MGPipeRefuseFrontendKeyedRegistryFromApplyThread("GetOrCreate(StatePtr)");
-#endif
-
-            const MG_Pipe::MGPipeHandle handle =
-                MG_Pipe::MGPipeSlots().Acquire(kKind, stateObj->GetLifetimeId());
-            MOBILEGL_ASSERT(!MG_Pipe::MGPipeHandleIsNull(handle),
-                            "MGPipe slot space of kind %u is exhausted",
-                            static_cast<Uint32>(kKind));
-            Entry& entry = EntryAt(handle.Slot);
-            if (entry.Live && entry.Gen != handle.Gen) {
-                // The slot was reclaimed and handed to a new object: the twin at it describes
-                // driver ids the new state object never made.
-                entry.backend.reset();
-            }
-            entry.Gen = handle.Gen;
-            entry.Live = true;
-            entry.stateRef = stateObj;
-            // No creation tick and no sweep here. The registry this replaces needed both,
-            // because nothing told it a texture or a renderbuffer had been DELETED and object
-            // CHURN rather than draw count is what made that urgent. Every one of the six kinds
-            // now announces its own death from its destructor, so a dead twin's slot is already
-            // back before the next creation asks for one.
-            RememberHandle(stateObj->GetLifetimeId(), handle);
-            return entry.backend;
-        }
-
-        // P3a: resolve-or-create BY HANDLE, and it is the shape that discharges the debt this
-        // header records against itself at the top of the file.
-        //
-        // The overload above mints - it calls MGPipeSlots().Acquire off a frontend object's
-        // lifetime id, from inside MG_Backend - which is monolith glue: a handle is minted by
-        // the CLIENT, and under a real split neither the object nor its lifetime id exists on
-        // this side. This overload never touches the allocator at all. The handle ARRIVED, in
-        // the call's payload, already minted by the side that owns minting; all this does is
-        // index the slot, notice a generation that no longer matches (the slot was recycled,
-        // so the twin at it describes driver ids the new resource never made) and hand back
-        // the twin pointer. FindByHandle beside it is the same shape and already existed.
-        //
-        // No StatePtr, therefore no Entry::stateRef unless a caller that holds the object notes
-        // it (NoteStateForHandle): a handle-keyed entry has no frontend object to weakly hold
-        // by itself. P5e (§4.1) makes that stop mattering for the iteration - ForEachLive keys
-        // on Live && backend, so such an entry is VISIBLE to the walk and it is StateForHandle,
-        // asked by the one caller that needs the object, that answers null for it. Which is the
-        // same set the old stateRef-locking walk produced, decided at one site instead of in
-        // the loop.
-        //
-        // Death stays ANNOUNCED, as it is on the other overload: for a handle-keyed kind the
-        // announcement is the family's own destroy call, not the shared death notice, and the
-        // slot is freed by the CLIENT after that call returns.
-        //
-        // UNUSED AT THE CONTRACT COMMIT, deliberately: it is a member of a class template, so
-        // an uninstantiated one costs nothing anywhere, and the backend package is what gives
-        // it its first caller.
-        BackendPtr& GetOrCreate(MG_Pipe::MGPipeHandle handle) {
-            MOBILEGL_ASSERT(!MG_Pipe::MGPipeHandleIsNull(handle),
-                            "GetOrCreate(handle) named the reserved null handle");
-            if (MG_Pipe::MGPipeHandleIsNull(handle)) return m_nullTwin;
-
-            // A slot index that ARRIVED in a payload indexes a vector this call would RESIZE,
-            // and nothing between the payload and here bounds it: the applier's blob gates sit
-            // in front of the vertex-input family, not in front of the resource family, which
-            // dispatches ops->Create(record.Res, ...) straight through. There is no allocator
-            // constant to check against on this side - the allocator is the client's - so this
-            // is a sanity cap and is documented as one: kMaxHandleSlot entries of one kind is
-            // already orders of magnitude past any real GL object count, while a corrupt 32-bit
-            // slot asks for a four-billion-entry resize.
-            if (handle.Slot >= kMaxHandleSlot) {
-#if MOBILEGL_BUILD_DISAGGREGATED
-                // PH-2: handle.Slot is peer supplied on the disaggregated arm. Release builds
-                // must publish a named protocol fault instead of silently returning m_nullTwin.
-                MG_Pipe::MGPipeSessionFail( // @Ph-declined (ID-P7-1): PH-2 stays Fatal, CONTRACT-P7 §12
-                    MG_Pipe::MGPipeFatalFamily::ProtocolCorruption,
-                    "MGPipe: Fatal{ProtocolCorruption, \"BackendSlotTable.HandleSlot\"} - "
-                    "GetOrCreate(handle) named slot %u, past this table's %u bound",
-                    handle.Slot, kMaxHandleSlot);
-#else
-                MOBILEGL_ASSERT(false, "GetOrCreate(handle) named slot %u, past this table's %u bound",
-                                handle.Slot, kMaxHandleSlot);
-                return m_nullTwin;
-#endif
-            }
-
-            // Same arming as the minting overload, and for the same reason: twin creation is
-            // the moment a driver-owned id starts needing a guarded destructor.
-            EnsureProcessTeardownSentinel();
-
-            // THE TWO DIRECTIONS ARE NOT SYMMETRIC HERE, where they are on the minting overload.
-            // There the handle comes straight out of MGPipeSlots().Acquire and can never be
-            // BEHIND the entry, so a bare `!=` only ever means "the slot was recycled forward".
-            // Here the handle arrived in a payload, so `handle.Gen < entry.Gen` is a reachable
-            // input, and adopting it would destroy the INCUMBENT LIVE twin - a driver buffer id,
-            // a persistent map, a pooled store, released by a defaulted destructor that issues
-            // no glDeleteBuffers and no pool enrolment - and then stamp the slot back to the
-            // dead resource's generation, after which the incumbent's own FindByHandle refuses
-            // it and it is silently handed a fresh, empty twin. That is a leak AND a resource
-            // that loses its storage with no diagnostic, i.e. the shape commit d7655247 fixed
-            // and the thing MGPipeHandle::Gen exists to prevent. So: forward is a recycle and
-            // resets the twin, BACKWARD is refused - which is the same answer FindByHandle
-            // below already gives the same input.
-            Entry& entry = EntryAt(handle.Slot);
-            if (entry.Live && entry.Gen > handle.Gen) {
-#if MOBILEGL_BUILD_DISAGGREGATED
-                // PH-2: a stale peer generation must not silently shed the incumbent twin in a
-                // release server. The funnel names the exact identity fault and notifies the peer.
-                MG_Pipe::MGPipeSessionFail( // @Ph-declined (ID-P7-1): PH-2 stays Fatal, CONTRACT-P7 §12
-                    MG_Pipe::MGPipeFatalFamily::ProtocolCorruption,
-                    "MGPipe: Fatal{ProtocolCorruption, \"BackendSlotTable.Generation\"} - "
-                    "GetOrCreate(handle) named generation %u at slot %u, behind live generation %u",
-                    handle.Gen, handle.Slot, entry.Gen);
-#else
-                MOBILEGL_ASSERT(false,
-                                "GetOrCreate(handle) named generation %u at slot %u, which is BEHIND "
-                                "the live entry's %u - refusing rather than destroying the incumbent",
-                                handle.Gen, handle.Slot, entry.Gen);
-                return m_nullTwin;
-#endif
-            }
-            if (entry.Live && entry.Gen != handle.Gen) entry.backend.reset();
-            entry.Gen = handle.Gen;
-            entry.Live = true;
-            return entry.backend;
-        }
-
-        // The generation of the LIVE entry at this slot, or 0 when the slot is out of range or
-        // holds no live entry. It exists so a caller can DIAGNOSE - in a release build, where
-        // MOBILEGL_ASSERT is inert - the refusal GetOrCreate(handle) above performs silently.
-        Uint32 LiveGenAt(Uint32 slot) const {
-            const Entry* const entry = EntryOrNull(slot);
-            if (entry == nullptr) return 0;
-            return entry->Live ? entry->Gen : 0;
-        }
-
-        // Remember/read the frontend object last used by the monolith sync path.
-        // Handles supplied to the server never need this weak state. Neither method
-        // touches the allocator, so each carries its own unconditional apply guard.
-        void NoteStateForHandle(MG_Pipe::MGPipeHandle handle, const StatePtr& stateObj) {
-#if MOBILEGL_BUILD_DISAGGREGATED
-            MG_Pipe::MGPipeRefuseFrontendKeyedRegistryFromApplyThread("NoteStateForHandle");
-#endif
-            if (MG_Pipe::MGPipeHandleIsNull(handle)) return;
-            Entry* const entry = EntryOrNull(handle.Slot);
-            if (entry == nullptr || !entry->Live || entry->Gen != handle.Gen) return;
-            entry->stateRef = stateObj;
-        }
-
-        // The frontend object noted for this handle, or null. The handle answers identity;
-        // this answers only "which object was this twin last synced from".
-        StatePtr StateForHandle(MG_Pipe::MGPipeHandle handle) const {
-#if MOBILEGL_BUILD_DISAGGREGATED
-            MG_Pipe::MGPipeRefuseFrontendKeyedRegistryFromApplyThread("StateForHandle");
-#endif
-            if (MG_Pipe::MGPipeHandleIsNull(handle)) return nullptr;
-            const Entry* const entry = EntryOrNull(handle.Slot);
-            if (entry == nullptr || !entry->Live || entry->Gen != handle.Gen) return nullptr;
-            return entry->stateRef.lock();
-        }
-
-        // P3a: the death half of the overload above, for a kind whose announcement is its own
-        // destroy CALL rather than the shared death notice (D-L). Hands the twin OUT rather
-        // than destroying it in place, because the caller may still have to decide what
-        // happens to the driver id it owns - Espryt pools it, deletes it, or parks it on the
-        // deferred-release list when no context is current on this thread - and every one of
-        // those outcomes has to be reached with the entry already retired, so a re-entrant
-        // GetOrCreate from a twin destructor cannot resurrect it.
-        //
-        // The slot itself is NOT freed here: it belongs to the kind, and for a handle-keyed
-        // kind the CLIENT frees it after the destroy call returns (SlotAllocator.h:60 - the
-        // Gen bump rides the next handout, so a double free cannot skip a generation). An
-        // entry whose Gen no longer matches is a twin of the slot's previous owner and is
-        // left alone: the successor's own GetOrCreate resets it.
-        BackendPtr ReleaseByHandle(MG_Pipe::MGPipeHandle handle) {
-            if (MG_Pipe::MGPipeHandleIsNull(handle)) return BackendPtr{};
-            if (m_memoHandle.Slot == handle.Slot) ForgetHandle();
-            Entry* const entry = EntryOrNull(handle.Slot);
-            if (entry == nullptr || !entry->Live || entry->Gen != handle.Gen) return BackendPtr{};
-            BackendPtr dead = std::move(entry->backend);
-            entry->backend.reset();
-            entry->stateRef.reset();
-            entry->Live = false;
-            return dead;
-        }
-
-        // Null when no live twin of this object exists. Unlike the registry's Find this NEVER
-        // mutates the table, so the returned pointer survives any later Find on it; only a
-        // GetOrCreate that grows the vector can move it, and callers that hold one across a
-        // possible insertion still copy the BackendPtr out.
-        BackendPtr* Find(StateObject* stateObj) {
-            if (stateObj == nullptr) return nullptr;
-            return FindByHandle(HandleOf(stateObj));
-        }
-
-        const BackendPtr* Find(StateObject* stateObj) const {
-            return const_cast<BackendSlotTable*>(this)->Find(stateObj);
-        }
-
-        BackendPtr* FindByHandle(MG_Pipe::MGPipeHandle handle) {
-            if (MG_Pipe::MGPipeHandleIsNull(handle)) return nullptr;
-            Entry* const entry = EntryOrNull(handle.Slot);
-            if (entry == nullptr || !entry->Live || entry->Gen != handle.Gen) return nullptr;
-            return &entry->backend;
-        }
-
-        // The handle this object's twin is keyed on, or the null handle. This is what a backend
-        // memo stores instead of a raw pointer, a GL name or a bare lifetime id.
-        //
-        // A NULL answer is never memoised. The memo is per table and the allocator is per
-        // kind, so with two holders of one kind the OTHER table can be the one that acquires;
-        // a cached "no handle" here would then outlive the twin's creation over there, and
-        // nothing on this table's own acquire path would ever refresh it. A miss costs the
-        // allocator probe it always cost; a hit is refreshed the moment anyone acquires.
-        MG_Pipe::MGPipeHandle HandleOf(const StateObject* stateObj) const {
-            if (stateObj == nullptr) return MG_Pipe::kMGPipeNullHandle;
-#if MOBILEGL_BUILD_DISAGGREGATED
-            // Resolve frontend identity only in the monolith path. A cache hit is
-            // subject to the same guard as a fresh allocator lookup.
-            MG_Pipe::MGPipeRefuseFrontendKeyedRegistryFromApplyThread("HandleOf");
-#endif
-            const Uint64 lifetimeId = stateObj->GetLifetimeId();
-            if (lifetimeId == m_memoLifetimeId) return m_memoHandle;
-            const MG_Pipe::MGPipeHandle handle =
-                MG_Pipe::MGPipeSlots().FindByLifetimeId(kKind, lifetimeId);
-            if (!MG_Pipe::MGPipeHandleIsNull(handle)) RememberHandle(lifetimeId, handle);
-            return handle;
-        }
-
-        // P2 step e2's backend half. The frontend object with this lifetime id has just been
-        // DESTROYED: resolve its handle ONCE, drop its twin in EVERY table of this type, and
-        // return the slot to the allocator - in that order, because the allocator forgets the
-        // lifetime id on Free and a holder told second could no longer resolve it.
-        //
-        // The slot is returned whether or not any holder still had a twin at it: the lifetime
-        // id is dead and MG_State never hands one out twice, so nothing can acquire it again,
-        // and a slot minted for it that no table holds (a table reset with `= {}` drops its
-        // entries without freeing) would otherwise stay allocated for the life of the process.
-        //
-        // STATIC, and deliberately so: a notice is about an object, not about a table, and
-        // "which table holds it" is exactly the question that produced the two-holder leak.
-        // Returns whether the object had a slot of this kind, i.e. whether anything was freed;
-        // a second call for the same id answers false because the allocator no longer maps it.
-        static Bool OnFrontendObjectDestroyed(Uint64 lifetimeId) {
-#if MOBILEGL_BUILD_DISAGGREGATED
-            // P5c (hd): the Find/Free pair below is monolith-only with an active transport -
-            // a frontend death is announced to the server by the object_death record (ct),
-            // and a direct call from the apply thread is Fatal{RoleViolation, "MGPipeSlots"}.
-            MG_Pipe::MGPipeRefuseAllocatorFromApplyThread("OnFrontendObjectDestroyed");
-#endif
-            const MG_Pipe::MGPipeHandle handle =
-                MG_Pipe::MGPipeSlots().FindByLifetimeId(kKind, lifetimeId);
-            if (MG_Pipe::MGPipeHandleIsNull(handle)) return false;
-            for (BackendSlotTable* holder = s_firstHolder; holder != nullptr;) {
-                // The successor is read BEFORE the release: ReleaseTwinAt runs the twin's
-                // destructor, which is a driver call, and nothing that outlives it may be a
-                // reference into this holder.
-                BackendSlotTable* const next = holder->m_nextHolder;
-                holder->ReleaseTwinAt(handle);
-                holder = next;
-            }
-            MG_Pipe::MGPipeSlots().Free(kKind, handle);
-            return true;
-        }
-
-        // P5c (ct), CONTRACT-P5C.md §5.2: the handle-keyed half of the above, for a death that
-        // arrived AS A WIRE RECORD (object_death) rather than as the shared notice. The
-        // handle IS the resolution - it crossed in the record's payload - so the client's
-        // allocator is never asked: under an active transport MGPipeSlots() is a client-only
-        // surface (rule E, §3.1) and this function runs on the apply thread. Every holder
-        // lets go exactly as the notice arm does, in the same successor-first order. What
-        // does NOT happen here is the allocator Free: the slot's owner - the client -
-        // returned it itself after the record went out (PipeFill.cpp's NotifyAndFree), and a
-        // double Free would be refused by generation anyway. Idempotent against the kind's
-        // own delete opcode, exactly as the notice arm is: a twin the delete already released
-        // fails ReleaseTwinAt's generation check and the walk moves on.
-        static Bool ReleaseTwinByHandle(MG_Pipe::MGPipeHandle handle) {
-            if (MG_Pipe::MGPipeHandleIsNull(handle)) return false;
-            Bool released = false;
-            for (BackendSlotTable* holder = s_firstHolder; holder != nullptr;) {
-                BackendSlotTable* const next = holder->m_nextHolder;
-                released = holder->ReleaseTwinAt(handle) || released;
-                holder = next;
-            }
-            return released;
-        }
-
-        // How many tables of this type exist right now. For the tests that pin the holder
-        // list; nothing on a shipping path asks.
-        static Uint32 HolderCount() {
-            Uint32 count = 0;
-            for (const BackendSlotTable* holder = s_firstHolder; holder != nullptr;
-                 holder = holder->m_nextHolder) {
-                ++count;
-            }
-            return count;
-        }
-
-        // P5e (id), CONTRACT-P5E §4.1: fn(MGPipeHandle, const BackendPtr& twin) over every
-        // live, twinned entry. Replaces the registry's begin()/end(), whose iterator exposed
-        // the raw frontend address as the map key - the one place the backend read an identity
-        // it must not have - and replaces P3a's own fn(StatePtr, BackendPtr), which handed a
-        // frontend SharedPtr OUT OF SERVER MEMORY on every step.
-        //
-        // WHAT THE CALLER LOST AND HOW IT GETS IT BACK, because the two are not the same thing.
-        // The walk no longer locks Entry::stateRef, so a caller that needs the frontend object
-        // asks StateForHandle(handle) for it - which is the same weak reference, read at one
-        // named site inside the scope that owns the debt, instead of at every step of an
-        // iteration. Coverage is UNCHANGED by construction: an entry ForEachLive used to skip
-        // because its stateRef did not lock is one whose StateForHandle answers null, and the
-        // caller skips it there instead.
-        //
-        // The handle is the entry's own {slot, gen}, band-aware: a composite ShaderCso's slot
-        // is reported as kMGPipeShaderCsoCompositeSlotBase + its band index, i.e. the slot the
-        // client minted, never the index into m_band.
-        template <typename Fn>
-        void ForEachLive(Fn&& fn) const {
-            // Index loop and a COPIED twin, not a range-for over references: fn is arbitrary
-            // backend code, and a nested GetOrCreate on this table would resize m_slots and
-            // invalidate both the iterator and any reference into the vector that outlives the
-            // call. The one caller today happens not to insert; that is not a property the
-            // walk should depend on.
-            for (SizeT index = 0; index < m_slots.size(); ++index) {
-                const Entry& entry = m_slots[index];
-                if (!entry.Live || !entry.backend) continue;
-                const BackendPtr twin = entry.backend;
-                fn(MG_Pipe::MGPipeHandle{static_cast<Uint32>(index), entry.Gen}, twin);
-            }
-            for (SizeT index = 0; index < m_band.size(); ++index) {
-                const Entry& entry = m_band[index];
-                if (!entry.Live || !entry.backend) continue;
-                const BackendPtr twin = entry.backend;
-                fn(MG_Pipe::MGPipeHandle{
-                       static_cast<Uint32>(index) + MG_Pipe::kMGPipeShaderCsoCompositeSlotBase,
-                       entry.Gen},
-                   twin);
-            }
-        }
-
-        Uint32 LiveCount() const {
-            Uint32 count = 0;
-            for (const Entry& entry : m_slots) {
-                if (entry.Live) ++count;
-            }
-            for (const Entry& entry : m_band) {
-                if (entry.Live) ++count;
-            }
-            return count;
-        }
-
-        // The band's own live count, so a case can tell "the composite is twinned" from "the
-        // ordinary table grew to reach it" - which is the whole assertion the band exists for
-        // and is untestable from LiveCount alone.
-        Uint32 CompositeLiveCount() const {
-            Uint32 count = 0;
-            for (const Entry& entry : m_band) {
-                if (entry.Live) ++count;
-            }
-            return count;
-        }
-
-        // How many entries each space has ALLOCATED, live or not. A leak case asserts on these
-        // rather than on LiveCount: growth is what the band prevents, and a dense table that
-        // never shrinks is invisible to a liveness count.
-        SizeT OrdinaryCapacityForTest() const { return m_slots.size(); }
-        SizeT CompositeCapacityForTest() const { return m_band.size(); }
-
-    private:
-        // Drop the twin at `handle` if THIS table holds it. Frees nothing: the slot belongs to
-        // the kind, not to the table, and OnFrontendObjectDestroyed returns it once, after
-        // every holder has let go.
-        Bool ReleaseTwinAt(MG_Pipe::MGPipeHandle handle) {
-            // Forget the memo whenever it names this slot, even if this table has no entry
-            // there: a memo can be a handle learned from the allocator for an object another
-            // holder twinned, and it must not survive the slot's next handout.
-            if (m_memoHandle.Slot == handle.Slot) ForgetHandle();
-            // The twin's destructor is a driver call and could, in principle, re-enter
-            // GetOrCreate on this table and resize m_slots. So NOTHING that outlives the
-            // destructor may be a reference into m_slots: the twin is moved out into a local,
-            // the entry is finished with, and only then is the local released.
-            BackendPtr dead;
-            {
-                Entry* const entry = EntryOrNull(handle.Slot);
-                if (entry == nullptr || !entry->Live || entry->Gen != handle.Gen) return false;
-                dead = std::move(entry->backend);
-                entry->backend.reset();
-                entry->stateRef.reset();
-                entry->Live = false;
-            }
-            dead.reset();
-            return true;
-        }
-
-        // ---- P5e (id): the two slot spaces, resolved in ONE place ---------------------------
-        //
-        // Every reader and writer below goes through these three, so a caller that forgot the
-        // band cannot exist - the shape MGPipeSlotAllocator::EntryOf already uses one level
-        // out. kHasCompositeBand folds to `false` at compile time for the five non-ShaderCso
-        // instantiations, so their band is dead code and an empty Vector.
-        static constexpr Bool SlotIsBanded(Uint32 slot) {
-            return kHasCompositeBand && MG_Pipe::MGPipeIsCompositeShaderSlot(slot);
-        }
-        static constexpr SizeT IndexOfSlot(Uint32 slot) {
-            return SlotIsBanded(slot)
-                       ? static_cast<SizeT>(slot - MG_Pipe::kMGPipeShaderCsoCompositeSlotBase)
-                       : static_cast<SizeT>(slot);
-        }
-
-        // The entry a slot names, or null when its space has never grown that far. NEVER grows:
-        // a lookup that resized would turn every miss into an allocation, which is the hazard
-        // Find documents.
-        Entry* EntryOrNull(Uint32 slot) {
-            Vector<Entry>& table = SlotIsBanded(slot) ? m_band : m_slots;
-            const SizeT index = IndexOfSlot(slot);
-            if (index >= table.size()) return nullptr;
-            return &table[index];
-        }
-        const Entry* EntryOrNull(Uint32 slot) const {
-            return const_cast<BackendSlotTable*>(this)->EntryOrNull(slot);
-        }
-
-        // Grows the right space to hold `slot`. Every caller bounds `slot` first - the minting
-        // overload because the allocator produced it, the handle overload against
-        // kMaxHandleSlot - because this is the one place a client-supplied number decides an
-        // allocation size. A composite slot grows m_band by (slot - base) + 1, so the ordinary
-        // table never learns the band exists.
-        Entry& EntryAt(Uint32 slot) {
-            Vector<Entry>& table = SlotIsBanded(slot) ? m_band : m_slots;
-            const SizeT index = IndexOfSlot(slot);
-            if (index >= table.size()) table.resize(index + 1);
-            return table[index];
-        }
-
-        void RememberHandle(Uint64 lifetimeId, MG_Pipe::MGPipeHandle handle) const {
-            m_memoLifetimeId = lifetimeId;
-            m_memoHandle = handle;
-        }
-        void ForgetHandle() const {
-            m_memoLifetimeId = 0;
-            m_memoHandle = MG_Pipe::kMGPipeNullHandle;
-        }
-
-        // The holder list: intrusive and doubly linked, so registering and unregistering are
-        // two pointer writes with no allocation, and its head is a constant-initialised
-        // static - which is what lets the process-lifetime registry globals in Managers.cpp
-        // link themselves in from their own constructors with no initialisation-order
-        // question to answer. Single-threaded, like every table it links (the tables live and
-        // die on the context thread, as the notice they answer does).
-        void LinkHolder() {
-            m_prevHolder = nullptr;
-            m_nextHolder = s_firstHolder;
-            if (s_firstHolder != nullptr) s_firstHolder->m_prevHolder = this;
-            s_firstHolder = this;
-        }
-        void UnlinkHolder() {
-            if (m_prevHolder != nullptr) {
-                m_prevHolder->m_nextHolder = m_nextHolder;
-            } else {
-                s_firstHolder = m_nextHolder;
-            }
-            if (m_nextHolder != nullptr) m_nextHolder->m_prevHolder = m_prevHolder;
-            m_prevHolder = nullptr;
-            m_nextHolder = nullptr;
-        }
-
-        static inline BackendSlotTable* s_firstHolder = nullptr;
-        BackendSlotTable* m_prevHolder = nullptr;
-        BackendSlotTable* m_nextHolder = nullptr;
-
-        // Indexed by MGPipeHandle::Slot; [0] is the reserved slot and is never live.
-        Vector<Entry> m_slots;
-        // P5e (id): the ShaderCso COMPOSITE band, indexed by (slot -
-        // kMGPipeShaderCsoCompositeSlotBase) and EMPTY for every other kind. See
-        // kHasCompositeBand above for why it is a second vector and not more of the first.
-        Vector<Entry> m_band;
-        // Handed back by GetOrCreate for a null state object. Never live, never handed a handle.
-        BackendPtr m_nullTwin;
-
-        // ONE-entry resolution memo, lifetimeId -> handle. It exists because without it every
-        // resolution goes through the allocator's ByLifetimeId hash, which the deleted
-        // TwinLookupMemos existed to avoid and which D13 promises to replace with "direct slot
-        // indexing".
-        //
-        // It is one entry and therefore only helps a caller that asks for the SAME object twice
-        // running - ResolveVaoTwin and SyncCurrentProgram do, once per draw each. Two callers
-        // it does NOT help, recorded rather than claimed away: BindCurrentFBO resolves BOTH
-        // targets in a frame, and ResolveUnitSamplerBackend asks for a different sampler per
-        // texture unit, so both thrash a single-entry memo and pay the probe P1 did not (P1 had
-        // a per-unit memo and a direct-mapped 6-slot array there). Making the memo per-unit /
-        // per-target is the fix, and G11 - the device-side gate that would price it - is owed.
-        //
-        // It cannot serve a stale answer, by three independent arguments:
-        //   * the key is a lifetime id, which MG_State never hands out twice, so a recycled
-        //     heap address cannot hit this memo the way it could hit an address-keyed one;
-        //   * a null answer is never stored, so another holder's acquire cannot be hidden by
-        //     a "no handle" this table remembered earlier; and
-        //   * even a hit for a slot that has since been freed and re-handed is caught, because
-        //     the caller resolves the handle through FindByHandle, which compares Gen.
-        // Cleared anyway when a death notice names the memoised slot. 0 is never a live
-        // lifetime id (MG_State's counters start at 1), so a zeroed memo is a guaranteed miss.
-        mutable Uint64 m_memoLifetimeId = 0;
-        mutable MG_Pipe::MGPipeHandle m_memoHandle = MG_Pipe::kMGPipeNullHandle;
-    };
-
-#endif // MOBILEGL_PIPE_PUSH
-} // namespace MobileGL::MG_Backend::DirectGLES

MobileGL/MG_Backend/DirectGLES/Utils.h

@@ -9,23 +9,8 @@
 #pragma once
 #include <Includes.h>
 #include <MG_State/GLState/Core.h>
-#include <MG_Util/BackendLoaders/OpenGL/Loader.h>
-#include <MG_Util/Texture/TextureFormatProcessor.h>
 
 namespace MobileGL::MG_Backend::DirectGLES {
-#if MOBILEGL_BUILD_DISAGGREGATED
-    // C6 / ID-52 / CONTRACT-P5 table 3's pActiveBackendObject row. The format-capability cache of
-    // THIS ROLE's backend. Under an active transport the server's own private
-    // BackendObject_DirectGLES owns the context on the apply thread, so a backend-internal format
-    // lookup must read ITS probed cache - not pActiveBackendObject's, which under split is the
-    // CLIENT's BackendObject_Remote mirror (a caps snapshot, generation-lagged, and on an
-    // independent server not usable at all). Monolith build/transport: pActiveBackendObject, so a
-    // pull build never sees this symbol. Null when no backend is up. The seven table-3 reads
-    // (five in Utils.cpp, ClampSamplesToBackendSupport in BackendObject_DirectGLES.cpp) go through
-    // this instead of dereferencing pActiveBackendObject directly.
-    const FormatCapabilityCache* ActiveBackendFormatCaps();
-#endif
-
     namespace DebugImpl {
         class ErrorLopper {
         public:
@@ -49,148 +34,13 @@ namespace MobileGL::MG_Backend::DirectGLES {
     } // namespace VertexArrayImpl
 
     namespace TextureImpl {
-        // Whether images on this format-capability target can back a colour attachment, and so
-        // need a colour-renderable storage format even when the frontend asked for a
-        // three-channel one ES never renders to. Shared by the capability probe (which passes the
-        // capabilities it has just queried, before the globals are published) and by the
-        // allocation path (which reads the active backend's), so the format the cache was probed
-        // with is always the format the image is created with.
-        Bool TargetRequiresRenderableFormat(SizeT targetIndex);
-        Flags<PixelFormatNormalizeOptionBit> GetRenderTargetNormalizeOptions(
-            const MG_External::GLESCapabilities& capabilities, SizeT targetIndex);
-
-        // Whether this format's ES storage is widened to 8-bit-per-channel because the
-        // driver stores some packed16 allocations with a mirrored field order
-        // (PixelFormatNormalizeOptionBit::WidenPacked16Norm). True only for
-        // GL_RGB565/GL_RGB5(_A1)/GL_RGBA4, and only where the POST probe measured the
-        // divergence (or MOBILEGL_ESPRYT_WIDEN_PACKED16_STORAGE forces it). The transfer paths
-        // consult it too: the packed-norm re-upload leg must stand down when the ES storage
-        // is no longer 16-bit packed.
-        Bool UsesWidenedPacked16NormStorage(TextureInternalFormat internalFormat);
-
         void GenerateTextureFormatInfo(TextureInternalFormat internalFormat, GLenum* outInternalFormat,
                                        GLenum* outFormat, GLenum* outType,
                                        TextureTarget target = TextureTarget::Unknown);
         void GenerateRenderbufferFormatInfo(TextureInternalFormat internalFormat, GLenum* outInternalFormat,
                                             GLenum* outFormat, GLenum* outType);
         Bool ShouldUseCaveatTextureFormat(TextureInternalFormat internalFormat, TextureTarget target);
-
-        // True when the format the image is actually created with has an alpha channel the
-        // frontend format does not (the three-channel colour-renderable widening). GL reads such
-        // a channel back as 1.0, so any swizzle source of ALPHA has to be answered with ONE and
-        // any readback of the image has to overwrite the alpha the draw happened to leave there.
-        Bool BackendTextureFormatAddsAlpha(TextureInternalFormat internalFormat, TextureTarget target);
-        Bool BackendRenderbufferFormatAddsAlpha(TextureInternalFormat internalFormat);
         Bool ShouldUseCaveatRenderbufferFormat(TextureInternalFormat internalFormat);
-
-        // The CHANNEL WIDENING an image-bindable texture's ES storage takes, so that a format
-        // GLSL ES cannot spell as an image is carried by one it can.
-        //
-        // GL has forty image formats, GLSL ES core has thirteen, and no test device advertises
-        // GL_NV_image_formats - so a shader declaring one of the other twenty-six has no legal
-        // ESSL at all and glBindImageTexture rejects the narrow format outright for most of them
-        // (GL_INVALID_VALUE for nineteen of twenty-six on Adreno, twenty-five on both Malis).
-        // Seventeen have a core format of the SAME per-channel width and component type,
-        // differing only in channel count, and in one of those the emulation is EXACT: GL already
-        // defines an imageLoad from a narrower format as (r, 0, 0, 1) and an imageStore as
-        // dropping the components the format does not have, so the carrier's surplus channels
-        // hold values GL has already named. WidenImageFormatsPass pins them in the shader; this
-        // is the storage half, and DirectGLES::TextureImpl::SyncImageTextureBinding the bind
-        // half. All three ask WidenedCoreEsslImageFormat, so they cannot pick different carriers.
-        //
-        // Reports nothing (InternalFormat == GL_UNKNOWN_MGL) for a format that is core already,
-        // for the nine with no exact carrier (r11f_g11f_b10f, rgb10_a2, rgb10_a2ui, rgba16, rg16,
-        // r16, rgba16_snorm, rg16_snorm, r16_snorm - those keep the honest "no GLSL ES spelling"
-        // diagnostic rather than a silent approximation), and on a driver that HAS
-        // GL_NV_image_formats, where the shader keeps the declared format and no widening may
-        // happen behind it.
-        //
-        // The widened triple REPLACES what GenerateTextureFormatInfo chose, including any
-        // renderability substitution: an image that cannot be image-bound is useless whatever its
-        // attachment behaviour, so the image constraint wins. In practice that only bites
-        // RG8_SNORM/R8_SNORM on a driver without EXT_render_snorm, where the storage stays
-        // signed-normalized instead of becoming the half float that fallback would have picked -
-        // so an image-bound texture in one of those two formats is no longer attachable, and
-        // glGetTexImage on it falls through to the CPU shadow, which a shader-side imageStore
-        // does not update. Accepted deliberately: before the widening, an image binding in either
-        // format was refused outright by every driver tested and the stage that declared it never
-        // compiled at all, so nothing that works today is being given up.
-        //
-        // KNOWN GAP, for the same "all three layers move together" reason: a widened texture that
-        // is ALSO an FBO colour attachment gains one to three writable channels, and a draw into
-        // it can leave values in channels GL says are 0 and 1. Sampling and imageLoad are covered
-        // (the swizzle composition in SyncTextureParamsToBackend and the shader-side mask), but a
-        // glReadPixels/glGetTexImage that asks for more channels than the frontend format has
-        // would see them. Closing it needs the per-draw-buffer colour mask the three-channel
-        // widening already carries (FramebufferImpl::g_alphaWidenedDrawBufferMask) generalized
-        // from "alpha" to a channel count, which is its own change.
-        // How the FRONTEND's CPU shadow for a widened format is laid out relative to the carrier's
-        // transfer, i.e. what the upload has to do to it. Almost every entry is `Components`: the
-        // shadow already holds SourceChannels components of exactly the carrier's own type, so
-        // padding it out to four is the whole conversion. The packed entries do not - their shadow
-        // is ONE 32-bit word per texel - and reading such a word as components of the carrier's
-        // type takes twelve or sixteen bytes out of four and shears the level.
-        enum class ImageWidenSourceEncoding : Uint8 {
-            Components = 0,
-            // r11f_g11f_b10f: GL_UNSIGNED_INT_10F_11F_11F_REV -> four GL_FLOATs of an rgba16f.
-            PackedFloat11f11f10f,
-            // rgb10_a2 and rgb10_a2ui: GL_UNSIGNED_INT_2_10_10_10_REV -> four GL_UNSIGNED_SHORT
-            // channel CODES of an rgba16ui. The same split serves both: the two formats differ
-            // only in what the codes MEAN, which is the shader's business and not the transfer's.
-            PackedInt2101010Rev,
-        };
-
-        struct ImageBindableStorageWidening {
-            GLenum InternalFormat = GL_UNKNOWN_MGL;
-            GLenum Format = GL_UNKNOWN_MGL;
-            GLenum Type = GL_UNKNOWN_MGL;
-            // Channels the FRONTEND format has, i.e. how many of the carrier's four the client
-            // data fills. The rest are uploaded as 0, and the fourth as the format's implied 1.
-            Uint SourceChannels = 0;
-            // Whether that implied 1 is the integer one or a saturated normalized field - the
-            // transfer type cannot tell the two apart (GL_UNSIGNED_BYTE serves both RG8 and
-            // RG8UI), so the carrier decides.
-            Bool IntegerData = false;
-            // What the upload has to do to the frontend shadow before it describes the level to
-            // the driver (PrepareImageWidenedUpload).
-            ImageWidenSourceEncoding SourceEncoding = ImageWidenSourceEncoding::Components;
-            // Non-zero when the carrier holds this format's channels as the INTEGER CODES of a
-            // NORMALIZED value - the seven 16-bit and 10-bit normalized formats, which core ESSL
-            // has no image format of any width for and which a float carrier would requantise.
-            // Each entry is the largest code that channel can hold, i.e. the denominator of GL 4.6
-            // 2.3.5; SignedNormalized picks which of the two conversions it is the denominator of.
-            //
-            // Two things depend on it, both because the ES storage no longer shares the frontend
-            // format's component class: the upload pads a missing alpha with ChannelMax[3] instead
-            // of the transfer type's own "one" (through a uint carrier the saturated field IS the
-            // one), and glGetTexImage divides the codes back out into the floats the application
-            // is still owed.
-            Uint ChannelMax[4] = {0u, 0u, 0u, 0u};
-            Bool SignedNormalized = false;
-
-            Bool CarriesNormalizedCodes() const { return ChannelMax[0] != 0u; }
-            explicit operator Bool() const { return InternalFormat != GL_UNKNOWN_MGL; }
-        };
-        ImageBindableStorageWidening GetImageBindableStorageWidening(TextureInternalFormat internalFormat);
-
-        // The single-channel core format an image-bindable BUFFER texture's view is SPLIT into, or
-        // GL_UNKNOWN_MGL for a format that needs no split (or has no core base).
-        //
-        // A buffer texture cannot be widened: its texels are the application's buffer object, at
-        // the size and layout the application gave it, and it is usually also a vertex, index or
-        // storage buffer whose bytes are not ours to restride. But an rg32f view of N texels and
-        // an r32f view of 2N texels describe exactly the SAME bytes, so the split changes only
-        // how the shader subscripts them - component j of texel i is texel 2i + j of the base
-        // view - which WidenImageFormatsPass rewrites every access to do. The same rule as the
-        // widening decides WHETHER: a driver that can spell rg32f for an imageBuffer needs
-        // nothing.
-        //
-        // KNOWN GAP, and the reason this is not applied to a texture that is merely sampled: a
-        // buffer texture that is BOTH image-bound and read through a samplerBuffer would have its
-        // sampled view split too, and the sampler side is not rewritten. Accepted for the same
-        // reason the storage widening's gaps are - on a driver where the split applies at all
-        // there is no legal ESSL for the image declaration, so such a program did not compile.
-        GLenum GetImageBindableBufferSplitFormat(TextureInternalFormat internalFormat);
     } // namespace TextureImpl
 
     namespace FramebufferImpl {} // namespace FramebufferImpl
@@ -238,24 +88,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
         // bytes, dst receives width * GetReadbackDstPixelSize(mapping, type) bytes.
         void ConvertWideReadbackRow(const Uint8* src, Uint8* dst, SizeT width, GLenum wideType,
                                     const ReadbackChannelMapping& mapping, GLenum type);
-
-        // Stores wide RGBA(_INTEGER) rows into the client pointer or the bound PACK pixel buffer,
-        // honoring the client-side PACK pixel-store parameters (row length, alignment, skips,
-        // swap-bytes, and - when applyPackImageParams - image height/skip images). Shared by the
-        // DirectGLES and DirectVulkan readback conversion paths.
-        Bool StoreWideRowsToClient(const Uint8* wide, GLenum wideType, GLsizei width, GLsizei sliceHeight,
-                                   GLsizei sliceCount, const ReadbackChannelMapping& mapping, GLenum type,
-                                   void* pixels, Bool applyPackImageParams);
-
-        // Stores packed 32-bit source words verbatim, with the same destination addressing, PACK
-        // parameters and pixel-pack-buffer handling as StoreWideRowsToClient. For the sources whose
-        // storage word already IS the client word (MG_Util::IsRawPackedPixelTransfer): routing those
-        // through the wide float intermediate re-encodes them, and the RGB9_E5 encoder canonicalizes
-        // the shared exponent, so glGetTexImage would answer with different bits than were stored.
-        // `srcWords` holds sliceHeight * sliceCount tightly stacked rows of `width` 32-bit words.
-        // False when `type` is not a 4-byte packed type.
-        Bool StorePackedWordsToClient(const Uint8* srcWords, GLsizei width, GLsizei sliceHeight, GLsizei sliceCount,
-                                      GLenum type, void* pixels, Bool applyPackImageParams);
     } // namespace ReadbackImpl
 
     namespace PrgramImpl {
@@ -264,289 +96,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
         String ClampNormFallbackOutputs(String glslCode, GLenum shaderType, Uint32 snormOutputMask,
                                         Uint32 unormOutputMask);
         String ForceFlatIntegerVaryings(const String& glslCode, GLenum shaderType);
-        // Legacy GLSL's gl_FragColor is broadcast to every enabled draw buffer (GL 4.6
-        // 15.2.3), but ShaderSourceProcessor lowers it to the single output mg_FragColor,
-        // which only ever reaches draw buffer 0. Replicates it across `drawBufferCount`
-        // outputs and copies the value into them at the end of main. A no-op for
-        // drawBufferCount <= 1, i.e. for everything but a framebuffer that actually
-        // enables several draw buffers, so the ordinary single-target shader is untouched.
-        String BroadcastLegacyFragColor(String glslCode, GLenum shaderType, Uint drawBufferCount);
-        // SPIRV-Cross emits `#extension GL_EXT_texture_buffer : require` for every buffer-texture
-        // sampler when it targets ESSL below 320, and offers no way to ask for the OES spelling.
-        // On a driver that advertises only GL_OES_texture_buffer that directive is a compile
-        // error, so the name is retargeted in the emitted source. A no-op on every other tier:
-        // ES 3.2 needs no directive at all and an EXT driver already has the right one.
-        String RetargetTextureBufferExtension(String glslCode,
-                                              MG_External::GLESCapabilities::TextureBufferTier tier);
-        // Adds `#extension GL_NV_image_formats : require` when the shader carries an image
-        // format qualifier GLSL ES has no core spelling for. SPIRV-Cross prints the format and
-        // asks for nothing, so the request has to be made here. `needed` is the caller's answer,
-        // because only it knows which formats are in play AND whether the driver advertises the
-        // extension - requesting an unadvertised extension is itself a compile error, so this is
-        // never emitted speculatively. A no-op when not needed or already present.
-        String RequestExtendedImageFormats(String glslCode, Bool needed);
-        // Adds `#extension GL_OES_viewport_array : require` when the emitted ESSL names
-        // gl_ViewportIndex. SPIRV-Cross prints that identifier and asks for nothing (unlike
-        // gl_Layer, which it backs with GL_NV_viewport_array2 on ES) and ESSL has no core
-        // spelling for it at any version, so the request has to be made here or the stage does
-        // not compile - which loses the whole program, not just the multi-viewport routing.
-        // `needed` is the caller's answer for the same reason as above: only it knows whether the
-        // driver advertises the extension, and requesting an unadvertised one is itself a compile
-        // error, so this is never emitted speculatively. A no-op when not needed or already
-        // present.
-        String RequestViewportArrayExtension(String glslCode, Bool needed);
-        // Adds `#extension <extensionName> : require` when a TESSELLATION or GEOMETRY stage's
-        // emitted ESSL names gl_PointSize. Desktop GL has that built-in in gl_PerVertex for every
-        // vertex-processing stage; ESSL does NOT have it in those two at any version - not even
-        // 320, where the stages themselves are core - until EXT/OES_tessellation_point_size resp.
-        // EXT/OES_geometry_point_size is requested. SPIRV-Cross prints the identifier bare and
-        // asks for nothing, exactly as it does for gl_ViewportIndex, so without this the stage
-        // fails to compile with "`gl_PointSize' undeclared" and the WHOLE program is replaced by
-        // program 0 - the draw renders nothing and any transform-feedback capture it was carrying
-        // is rejected outright. `extensionName` is the caller's answer, nullptr when the driver
-        // advertises neither spelling, because requesting an unadvertised extension is itself a
-        // compile error. A no-op when nullptr or already present.
-        String RequestPointSizeExtension(String glslCode, const char* extensionName);
-        // The extension name RequestPointSizeExtension should be given for `tier`, or nullptr for
-        // PointSizeTier::None. `tessellation` picks the tessellation spellings over the geometry
-        // ones; the two extensions are separate and neither implies the other.
-        const char* PointSizeExtensionName(MG_External::GLESCapabilities::PointSizeTier tier, Bool tessellation);
-        // Writes a format layout qualifier into the image declarations named in
-        // `esslFormatByUniformName` that still have none. The completion half of the image-format
-        // bake, and ONLY that: the SPIR-V pass (BakeImageFormatsPass) is what normally puts the
-        // format in, but SPIRV-Cross throws rather than printing the formats it calls
-        // desktop-only when it targets ESSL - r8ui among them, which is what the stencil half of
-        // KHR-GL4x.packed_depth_stencil.stencil_texturing binds - and a throw loses the whole
-        // stage. So those formats stay out of the module and are spelled here instead, on the
-        // emitted text, where nothing can refuse them.
-        //
-        // Declarations that already carry a format are left exactly as they are, whoever wrote
-        // it. Must run before RemoveLayoutBinding, which is where an image's layout qualifier
-        // stops being safe to edit by hand.
-        String BakeImageFormatQualifiers(String glslCode, const UnorderedMap<String, String>& esslFormatByUniformName);
         String RemoveLayoutBinding(const String& glslCode);
-        // Prefix of the per-element scalar declarations RemapImageArrayElementUnits splits an
-        // image array into; the suffix is the array's own name and the element's index.
-        constexpr const char* IMAGE_ARRAY_ELEMENT_PREFIX = "mg_imageElem_";
-        // One image ARRAY whose elements the application pointed at units that are not
-        // consecutive-from-element-zero.
-        struct ImageArrayUnitPlan {
-            String name;       // the array's name, exactly as the emitted ESSL declares it
-            Vector<Int> units; // the frontend image unit element k has to reach
-        };
-        // Desktop GL lets an application give each element of an image array an ARBITRARY unit
-        // (glUniform1i per element). ES has no such call at all - "ES image units come
-        // exclusively from the layout(binding=N) qualifier" - and one declaration carries one
-        // binding, so ESSL nails an array's elements to the CONSECUTIVE units N, N+1, N+2, ...
-        // MobileGL used to stamp element [0]'s unit as the binding and let the rest fall where
-        // they fell: KHR-GL4x.shader_image_load_store.advanced-sso-simple assigns 0,2,4,6 and
-        // 1,3,5,7, so its two programs actually addressed 0,1,2,3 and 1,2,3,4 - one layer got the
-        // wrong value and three were never written, with no GL error and no link log. The same
-        // defect for SAMPLER arrays was fixed API-side (SubscriptUniformNameForElement); an image
-        // array has no API side to fix, because ES makes glUniform1i on an image uniform an
-        // INVALID_OPERATION.
-        //
-        // Repaired by SPLITTING the array into one SCALAR image uniform per element, each with
-        // its own layout(binding = N), and rewriting `name[k]` to the scalar declared for
-        // element k. One declaration carries one binding, so one declaration per unit is the
-        // only spelling that reaches an arbitrary set of them.
-        //
-        // That rewrite needs every k in the emitted text to be a LITERAL, and it is:
-        // LegalizeResourceArrayIndexingForEssl has already folded or lowered every dynamic
-        // image-array subscript in the module, because ESSL forbids one outright ("image arrays
-        // indexed with non-constant expressions are forbidden in GLSL ES", Mesa 26.1.4 at
-        // ES 3.2, on a raw GLES probe with no MobileGL in the loop). The earlier shape here -
-        // widening the array to cover the whole span of units and routing each subscript through
-        // a `const highp int` offset table - was written before that pass covered images, and
-        // the table lookup was itself one of the non-constant expressions the same probe refuses.
-        // The split also costs exactly the image uniforms the application declared, where the
-        // widening cost the whole SPAN (seven for the four elements of
-        // KHR-GL42.shader_image_load_store.advanced-sso-simple), so there is no budget for it to
-        // fail to fit in.
-        //
-        // Declines - leaving the array exactly as it was, and naming it in `outDeclined` for the
-        // caller to report - when the emitted extent disagrees with the reflection, when the
-        // array is reached by anything other than a subscript, or when a subscript is not a
-        // literal element index. Silence was the whole defect here, so a decline must be audible.
-        //
-        // Must run AFTER RebindImageUniformsToFrontendUnits and BakeImageFormatQualifiers (both
-        // key on the GL uniform name and on a binding already being stamped) and BEFORE
-        // SplitReadWriteImageUniforms (so each element that is both read and written is split
-        // with its own binding already on it) and RemoveLayoutBinding (which is what preserves
-        // image bindings). Like them, it is downstream of the L2 shader-translation memo, so the
-        // per-program units it reads need no entry in BuildEsslTranslationKey.
-        String RemapImageArrayElementUnits(const String& glslCode, const Vector<ImageArrayUnitPlan>& plans,
-                                           Vector<String>* outDeclined = nullptr);
-        // The member list of a `gl_PerVertex { ... }` redeclaration in already-emitted ESSL -
-        // the text between the braces, verbatim - or nullopt when the shader does not redeclare
-        // the block in that direction. `input` selects the `in gl_PerVertex` form over the
-        // `out` one.
-        //
-        // Exists so BuildPassthroughTessControlEssl can MIRROR the stages it has to sit between
-        // rather than guess at them. Whether SPIRV-Cross redeclares the built-in block, and with
-        // which members, depends on what the application's shader touched; a synthesized stage
-        // that redeclares a different shape than its neighbours is an ES link error against a
-        // program that has no other problem.
-        std::optional<String> ExtractPerVertexBlockMembers(const String& essl, Bool input);
-        // The pass-through tessellation control stage GL 4.6 core 11.2.2 describes: "the input
-        // patch is passed through unmodified", the output patch has PATCH_VERTICES vertices, and
-        // the levels come from the PATCH_DEFAULT_OUTER_LEVEL / PATCH_DEFAULT_INNER_LEVEL state.
-        //
-        // Desktop GL makes the control stage OPTIONAL. OpenGL ES 3.2 does not: it has no
-        // PATCH_DEFAULT_*_LEVEL state at all (only glPatchParameteri, for PATCH_VERTICES) and
-        // rejects a program that has an evaluation stage without a control stage - with an EMPTY
-        // info log, verified on an Adreno 830 with no MobileGL in the process. MobileGL's own
-        // frontend link succeeds, so the program reports GL_LINK_STATUS = TRUE, program 0 is
-        // bound in its place, and every draw silently renders nothing.
-        //
-        // `inPerVertexMembers` / `outPerVertexMembers` are the member lists to redeclare gl_in
-        // and gl_out with - normally taken from the neighbouring stages' own emitted ESSL via
-        // ExtractPerVertexBlockMembers, and empty to leave the driver's built-in declaration
-        // alone, which is what matching a neighbour that did not redeclare requires.
-        //
-        // All four outer levels and both inner levels are written unconditionally: writing a
-        // level the evaluation stage's domain does not use is legal and ignored, and it saves
-        // this from having to know the domain. They are the GL_PATCH_DEFAULT_OUTER_LEVEL /
-        // GL_PATCH_DEFAULT_INNER_LEVEL state, baked in as literals - ES has no such state and no
-        // glPatchParameterfv to forward to, so compiling them in is the only way to honour them.
-        // That makes them part of what a built program is stale against, exactly as PATCH_VERTICES
-        // is: see the staleness clause in DirectGLES.cpp's SyncCurrentProgram, which compares both.
-        //
-        // The same stage, for the same reason, that DirectVulkan synthesizes in
-        // ProgramFactory::BuildPassthroughTessControlSource - Vulkan likewise requires both
-        // tessellation stages. Kept as two generators rather than one because the two targets
-        // disagree on everything but the algorithm: desktop GLSL 450 against ESSL, a fixed
-        // gl_PerVertex shape that Vulkan matches structurally against a mirrored one, and a
-        // VkShaderModule against a driver shader object.
-        String BuildPassthroughTessControlEssl(Uint esslVersion, Uint patchVertices,
-                                               const String& inPerVertexMembers,
-                                               const String& outPerVertexMembers,
-                                               const FloatVec4& defaultOuterLevel,
-                                               const FloatVec2& defaultInnerLevel);
-        // Prefix of the writeonly half a read+write image uniform is split into (see
-        // SplitReadWriteImageUniforms); the suffix is the image's own (already access-tagged) name.
-        constexpr const char* IMAGE_WRITE_ALIAS_PREFIX = "mg_imageWrite_";
-        // The three names SplitReadWriteImageUniforms renames a rewritten image declaration
-        // under, one per REPAIR it can apply. Which one a stage picks is decided by that stage's
-        // own accesses, so two stages that use an image the same way arrive at the SAME name and
-        // two that use it differently arrive at different ones - which is exactly the property
-        // the rename exists for, at no cost to the stages that agree. Exposed for the tests.
-        constexpr const char* IMAGE_READONLY_ALIAS_PREFIX = "mg_imageRo_";
-        constexpr const char* IMAGE_WRITEONLY_ALIAS_PREFIX = "mg_imageWo_";
-        constexpr const char* IMAGE_SPLIT_READ_ALIAS_PREFIX = "mg_imageRw_";
-        // ESSL refuses an image variable that carries a format qualifier other than r32f /
-        // r32i / r32ui unless it also carries `readonly` or `writeonly` (GLSL ES 3.10 4.9 /
-        // 3.20 4.10; glslang enforces it verbatim in ParseHelper.cpp's layoutObjectCheck).
-        // SPIRV-Cross emits NEITHER for an image the shader both reads and writes: it
-        // speculatively decorates every storage image NonWritable+NonReadable
-        // (fixup_image_load_store_access), then OpImageRead clears NonReadable and
-        // OpImageWrite clears NonWritable, and to_qualifiers_glsl only prints `readonly`
-        // from NonWritable and `writeonly` from NonReadable. Desktop GLSL is happy with the
-        // bare declaration, so the frontend raises no error and the illegal ESSL only shows
-        // up as a device compile failure - and then as a silently no-op draw.
-        //
-        // Restores a legal declaration, and RENAMES it after the repair it applied while doing so:
-        //  * loaded only            -> add `readonly`, rename under IMAGE_READONLY_ALIAS_PREFIX
-        //  * stored only            -> add `writeonly`, rename under IMAGE_WRITEONLY_ALIAS_PREFIX
-        //  * both                   -> emit TWO declarations on the same binding and of the
-        //                              same type, `coherent readonly
-        //                              <IMAGE_SPLIT_READ_ALIAS_PREFIX><name>` and `coherent
-        //                              writeonly <IMAGE_WRITE_ALIAS_PREFIX><that name>`, point
-        //                              every imageStore at the second one, and follow each of
-        //                              those stores with `memoryBarrierImage();`. Several image
-        //                              variables may share an image unit as long as they have
-        //                              the same type and format, which is exactly what the pair
-        //                              is.
-        //
-        // The rename is the other half of the repair and applies to all three cases. The qualifier
-        // chosen above is a decision about ONE STAGE's accesses, and GLSL requires a uniform
-        // declared in two stages to be declared identically - so a shader that stores an image from
-        // the vertex stage and loads it from the fragment stage came out of here `writeonly` in one
-        // and `readonly` in the other. Adreno merges the two same-named declarations and silently
-        // drops the vertex-stage STORES: no GL error, no link log, LINK_STATUS = 1, and the image
-        // still reads back its initial contents
-        // (KHR-GL4x.shader_image_load_store.advanced-memory-dependentInvocation; a raw-ES probe
-        // isolated the trigger to the same-name/mismatched-qualifier pair, and only when both
-        // carry `coherent`). Renaming leaves no cross-stage variable to merge.
-        //
-        // The name is keyed on the REPAIR, not on the stage, and that distinction is the whole
-        // point: two stages that use an image the same way emit byte-identical declarations, so
-        // letting them keep one shared name costs nothing and merging them is correct, while two
-        // stages that use it differently land on different prefixes and cannot be merged at all.
-        // A per-STAGE tag also satisfied the first requirement but violated the second: it made
-        // the SAME image a distinct uniform in every stage that named it, and Adreno allocates
-        // image LOCATIONS per distinct uniform. KHR-GL43.shading_language_420pack.
-        // binding_images_texture_type_* declares three read+write images in each of its five
-        // stages; merged that is 6 image uniforms, per-stage-tagged it is 30, and the Adreno 830
-        // linker answered "Error: Image Image location or component exceeds max allowed. Error:
-        // Linking failed." - which, the frontend having already published LINK_STATUS = TRUE from
-        // glslang's link, surfaced only as every draw silently doing nothing and the images
-        // reading back zero. Mali and Mesa link the same text, so nothing but a device gate
-        // catches this.
-        //
-        // A declaration SPIRV-Cross already tagged `readonly` or `writeonly` needs no qualifier
-        // repair, but it is NOT stage-independent: that tag is derived from the accesses of the
-        // stage being emitted, so an image stored in the vertex stage and loaded in the fragment
-        // stage arrives here as `coherent writeonly g_image` and `coherent readonly g_image` -
-        // one name, two spellings, which is exactly the pair Adreno merges. Those declarations
-        // are therefore renamed too, keyed on the qualifier they already carry (readonly ->
-        // IMAGE_READONLY_ALIAS_PREFIX, writeonly -> IMAGE_WRITEONLY_ALIAS_PREFIX) and with
-        // nothing but the identifier changed. Stages that agree still reach the same alias and
-        // stay merged, so this costs no shader an extra image uniform.
-        //
-        // The declarations this pass still leaves untouched keep their names: one carrying BOTH
-        // readonly and writeonly (a spelling no access analysis produces, so it came from the
-        // application and is identical everywhere), and one carrying NEITHER, which is legal only
-        // for the r32f/r32i/r32ui formats and is likewise spelled the same in every stage.
-        //
-        // The `coherent` on both halves of the pair is load-bearing, not decoration: GLSL only
-        // guarantees a write through one image variable is visible to a read through a DIFFERENT
-        // one when both are coherent, and the split is what makes a same-variable
-        // read-after-write cross-variable. The single-declaration repairs above do not get it -
-        // nothing aliases them.
-        //
-        // The barrier is the other half of the same problem, and coherent alone did not cover it:
-        // visibility is not ORDER. Within one invocation the ES compiler sees a write to one
-        // variable and a read of another it has no reason to believe alias, and is free to serve
-        // the read from before the write - which is what advanced-memory-order's store/load/
-        // compare loop measured on Adreno. memoryBarrierImage() orders exactly those two, is core
-        // GLSL ES 3.10 in every stage, and is not an execution barrier, so it is legal in
-        // non-uniform control flow. It costs something in a shader that stores to a read+write
-        // image in a loop, which is why it is confined to the split pair.
-        //
-        // Budget note: the split DOUBLES the image-uniform count of the stage it fires in, so
-        // a driver advertising a tight GL_MAX_{FRAGMENT,VERTEX,...}_IMAGE_UNIFORMS can turn a
-        // shader that used to compile into a link failure. ES only guarantees 4 fragment image
-        // uniforms, so a shader with more than half the limit in read+write images is the case
-        // to watch.
-        //
-        // Runs on the transpiled ESSL, so it must see the bindings the frontend units were
-        // already rewritten to and must run before those bindings are stripped - see the call
-        // site in Managers.cpp. Its output is a function of the emitted text alone - it needs no
-        // stage and no per-program state - so it adds nothing to BuildEsslTranslationKey either.
-        //
-        // `outSplitCount`, when given, receives the number of declarations that were actually
-        // doubled - i.e. exactly how many image uniforms this stage gained over what the
-        // application declared. Zero for every shader but a handful, and the only number the
-        // budget note above can be reported with.
-        String SplitReadWriteImageUniforms(const String& glslCode, Uint* outSplitCount = nullptr);
-        // Prefix of the per-sampler float uniform that carries GL_TEXTURE_LOD_BIAS into
-        // the shader (see EmulateTextureLodBias); the suffix is the sampler's own name.
-        constexpr const char* LOD_BIAS_UNIFORM_PREFIX = "mg_lodBias_";
-        // ES has no per-texture/sampler LOD bias at all (GL_TEXTURE_LOD_BIAS is desktop
-        // only; Vulkan spells it VkSamplerCreateInfo::mipLodBias), so it has to reach the
-        // shader as a uniform and be folded into every lookup's level of detail. Declares
-        // one `uniform highp float mg_lodBias_<sampler>;` per mip-capable sampler and adds
-        // it to the bias / explicit-LOD argument of every lookup that takes one. Draws push
-        // the bound texture's (or sampler object's) value into it; a shader whose samplers
-        // all have a zero bias is therefore unaffected. Returns the source unchanged when
-        // there is nothing to rewrite.
-        //
-        // avoidExplicitLodBias leaves lookups that already carry an explicit LOD untouched,
-        // so their constant level stays constant; only the implicit-LOD forms take the bias.
-        // Off by default and only ever set on ANGLE + llvmpipe, where injecting the uniform
-        // into a constant LOD crashes the driver (MOBILEGL_ESPRYT_AVOID_EXPLICIT_LOD_BIAS).
-        String EmulateTextureLodBias(const String& glslCode, Bool avoidExplicitLodBias = false);
     } // namespace PrgramImpl
 
     namespace Utils {

MobileGL/MG_Backend/DirectGLES/WireTextureReadback.inc

@@ -1,309 +0,0 @@
-// Included in DirectGLES.cpp after the native packed-word readback helper.
-// The server needs owned tight rows for a storage promotion, not client PACK
-// layout or a fallback into a frontend texture's potentially stale shadow.
-    class ScopedWireTextureReadLevel {
-    public:
-        ScopedWireTextureReadLevel(GLuint texture, GLenum target, GLint level)
-            : m_texture(texture), m_target(target) {
-            switch (target) {
-            case GL_TEXTURE_2D: m_binding = GL_TEXTURE_BINDING_2D; break;
-            case GL_TEXTURE_3D: m_binding = GL_TEXTURE_BINDING_3D; break;
-            case GL_TEXTURE_2D_ARRAY: m_binding = GL_TEXTURE_BINDING_2D_ARRAY; break;
-            case GL_TEXTURE_CUBE_MAP: m_binding = GL_TEXTURE_BINDING_CUBE_MAP; break;
-            case GL_TEXTURE_CUBE_MAP_ARRAY: m_binding = GL_TEXTURE_BINDING_CUBE_MAP_ARRAY; break;
-            default: return;
-            }
-            GLint previous = 0;
-            DrainESErrors();
-            g_GLESFuncs.glGetIntegerv(m_binding, &previous);
-            g_GLESFuncs.glBindTexture(m_target, m_texture);
-            g_GLESFuncs.glGetTexParameteriv(m_target, GL_TEXTURE_BASE_LEVEL, &m_baseLevel);
-            g_GLESFuncs.glGetTexParameteriv(m_target, GL_TEXTURE_MAX_LEVEL, &m_maxLevel);
-            m_saved = g_GLESFuncs.glGetError() == GL_NO_ERROR;
-            if (m_saved) {
-                // ES framebuffer completeness can reject a defined level whose
-                // base level or intervening mip chain is missing/inconsistent.
-                // Read this existing native image as the sole base level. The
-                // logical GL parameters and every cached copy remain unchanged.
-                g_GLESFuncs.glTexParameteri(m_target, GL_TEXTURE_BASE_LEVEL, level);
-                g_GLESFuncs.glTexParameteri(m_target, GL_TEXTURE_MAX_LEVEL, level);
-                m_valid = g_GLESFuncs.glGetError() == GL_NO_ERROR;
-            }
-            g_GLESFuncs.glBindTexture(m_target, static_cast<GLuint>(previous));
-        }
-
-        ~ScopedWireTextureReadLevel() {
-            if (!m_saved) return;
-            // The packed-word path can use its own texture scratch binding.
-            // Save the binding at restoration time too; do not assume an active
-            // texture unit or make the backend's binding cache forget a bind.
-            GLint previous = 0;
-            g_GLESFuncs.glGetIntegerv(m_binding, &previous);
-            g_GLESFuncs.glBindTexture(m_target, m_texture);
-            g_GLESFuncs.glTexParameteri(m_target, GL_TEXTURE_BASE_LEVEL, m_baseLevel);
-            g_GLESFuncs.glTexParameteri(m_target, GL_TEXTURE_MAX_LEVEL, m_maxLevel);
-            g_GLESFuncs.glBindTexture(m_target, static_cast<GLuint>(previous));
-        }
-
-        Bool Valid() const { return m_valid; }
-
-    private:
-        GLuint m_texture;
-        GLenum m_target;
-        GLenum m_binding = GL_NONE;
-        GLint m_baseLevel = 0, m_maxLevel = 0;
-        Bool m_saved = false, m_valid = false;
-    };
-
-    static Bool ReadWireColorRowsTight(GLsizei width, GLsizei height, GLenum format, GLenum type,
-                                      Bool forceOpaqueAlpha, const NormalizedImageCarrierRead& carrier,
-                                      Vector<Uint8>& bytes) {
-        ReadbackChannelMapping mapping{};
-        if (!GetReadbackChannelMapping(format, mapping)) return false;
-        const SizeT pixelBytes = GetReadbackDstPixelSize(mapping, type);
-        if (!pixelBytes || width <= 0 || height <= 0) return false;
-        const GLenum componentType = QueryReadAttachmentComponentType();
-        const Bool integerAttachment = componentType == GL_INT || componentType == GL_UNSIGNED_INT;
-        if (carrier.Active() ? (mapping.isInteger || !integerAttachment)
-                             : mapping.isInteger != integerAttachment) return false;
-
-        GLint implFormat = 0, implType = 0;
-        g_GLESFuncs.glGetIntegerv(GL_IMPLEMENTATION_COLOR_READ_FORMAT, &implFormat);
-        g_GLESFuncs.glGetIntegerv(GL_IMPLEMENTATION_COLOR_READ_TYPE, &implType);
-        struct Candidate { GLenum format, type; };
-        Vector<Candidate> candidates;
-        if (carrier.Active()) {
-            candidates.push_back({GL_RGBA_INTEGER, GL_UNSIGNED_INT});
-        } else if (mapping.isInteger) {
-            if (GetWideReadChannelCount(implFormat) > 0 && IsIntegerReadFormat(implFormat) &&
-                (implType == GL_INT || implType == GL_UNSIGNED_INT))
-                candidates.push_back({static_cast<GLenum>(implFormat), static_cast<GLenum>(implType)});
-            candidates.push_back({GL_RGBA_INTEGER, componentType == GL_INT ? GLenum(GL_INT) : GLenum(GL_UNSIGNED_INT)});
-        } else {
-            if (GetWideReadChannelCount(implFormat) > 0 && !IsIntegerReadFormat(implFormat) &&
-                (CanDecodeWideSourceType(implType) ||
-                 (implFormat == GL_RGBA && implType == GL_UNSIGNED_INT_2_10_10_10_REV)))
-                candidates.push_back({static_cast<GLenum>(implFormat), static_cast<GLenum>(implType)});
-            if (componentType == GL_FLOAT) candidates.push_back({GL_RGBA, GL_FLOAT});
-            if (componentType == GL_SIGNED_NORMALIZED) {
-                candidates.push_back({GL_RGBA, GL_SHORT});
-                candidates.push_back({GL_RGBA, GL_BYTE});
-            } else candidates.push_back({GL_RGBA, GL_UNSIGNED_BYTE});
-        }
-        ScopedPixelPackBuffer packBuffer(0);
-        ScopedPackState packState(PixelStoreImpl::PackState{1, 0, 0, 0});
-        const SizeT pixels = static_cast<SizeT>(width) * static_cast<SizeT>(height);
-        Vector<Uint8> wide;
-        GLenum wideType = GL_NONE;
-        Int channels = 0;
-        DrainESErrors();
-        for (const auto candidate : candidates) {
-            channels = GetWideReadChannelCount(candidate.format);
-            wide.resize(pixels * static_cast<SizeT>(channels) * GetReadbackComponentSize(candidate.type));
-            g_GLESFuncs.glReadPixels(0, 0, width, height, candidate.format, candidate.type, wide.data());
-            if (g_GLESFuncs.glGetError() == GL_NO_ERROR) { wideType = candidate.type; break; }
-        }
-        if (wideType == GL_NONE) return false;
-
-        if (carrier.Active()) {
-            Vector<Uint8> decoded(pixels * 4 * sizeof(Float));
-            auto* dst = reinterpret_cast<Float*>(decoded.data());
-            const auto* src = reinterpret_cast<const Uint32*>(wide.data());
-            for (SizeT i = 0; i < pixels; ++i) {
-                for (SizeT c = 0; c < 4; ++c) {
-                    const Float divisor = static_cast<Float>(carrier.ChannelMax[c]);
-                    dst[i * 4 + c] = carrier.SignedNormalized
-                        ? std::max(static_cast<Float>(static_cast<Int16>(static_cast<Uint16>(src[i * 4 + c]))) / divisor, -1.0f)
-                        : static_cast<Float>(src[i * 4 + c]) / divisor;
-                }
-            }
-            wide = Move(decoded); wideType = GL_FLOAT; channels = 4;
-        } else if (wideType == GL_UNSIGNED_INT_2_10_10_10_REV) {
-            Vector<Uint8> decoded(pixels * 4 * sizeof(Float));
-            auto* dst = reinterpret_cast<Float*>(decoded.data());
-            for (SizeT i = 0; i < pixels; ++i) {
-                Uint32 word = 0;
-                Memcpy(&word, wide.data() + i * sizeof(word), sizeof(word));
-                dst[i * 4] = static_cast<Float>(word & 1023u) / 1023.0f;
-                dst[i * 4 + 1] = static_cast<Float>((word >> 10) & 1023u) / 1023.0f;
-                dst[i * 4 + 2] = static_cast<Float>((word >> 20) & 1023u) / 1023.0f;
-                dst[i * 4 + 3] = static_cast<Float>((word >> 30) & 3u) / 3.0f;
-            }
-            wide = Move(decoded); wideType = GL_FLOAT; channels = 4;
-        }
-        if (channels < 4) ExpandNarrowWideRead(wide, pixels, channels, wideType);
-        if (forceOpaqueAlpha) ForceWideReadAlphaToOne(wide, pixels, wideType);
-        Vector<Uint8> converted(pixels * pixelBytes);
-        const SizeT sourceRowBytes = static_cast<SizeT>(width) * 4 * GetReadbackComponentSize(wideType);
-        for (GLsizei row = 0; row < height; ++row)
-            ReadbackImpl::ConvertWideReadbackRow(wide.data() + static_cast<SizeT>(row) * sourceRowBytes,
-                converted.data() + static_cast<SizeT>(row) * width * pixelBytes, width, wideType, mapping, type);
-        bytes = Move(converted);
-        return true;
-    }
-
-    static Bool ReadWireDepthStencilLevelTight(GLuint texture, TextureTarget target,
-                                               TextureUploadTarget uploadTarget, GLint level,
-                                               const IntVec3& extent, GLenum format, GLenum type,
-                                               Vector<Uint8>& bytes) {
-        const SizeT pixelBytes = MG_Util::GetInputBytesPerPixel(
-            MG_Util::ConvertGLEnumToTextureInputFormat(format), MG_Util::ConvertGLEnumToTexturePixelDataType(type));
-        if (!pixelBytes) return false;
-        const Bool needDepth = format == GL_DEPTH_COMPONENT || format == GL_DEPTH_STENCIL;
-        const Bool needStencil = format == GL_STENCIL_INDEX || format == GL_DEPTH_STENCIL;
-        ScopedFramebufferBinding bindings(true, false);
-        GLuint fbo = 0;
-        g_GLESFuncs.glGenFramebuffers(1, &fbo);
-        struct DeleteFbo { GLuint id; ~DeleteFbo() { g_GLESFuncs.glDeleteFramebuffers(1, &id); } } cleanup{fbo};
-        FramebufferImpl::BindFramebufferId(GL_READ_FRAMEBUFFER, fbo);
-        ScopedPixelPackBuffer packBuffer(0);
-        ScopedPackState packState(PixelStoreImpl::PackState{1, 0, 0, 0});
-        const GLenum nativeTarget = TextureImpl::ConvertTextureTargetToBackendGLEnum(target);
-        const GLenum point = needDepth ? (needStencil ? GL_DEPTH_STENCIL_ATTACHMENT : GL_DEPTH_ATTACHMENT)
-                                      : GL_STENCIL_ATTACHMENT;
-        const SizeT count = static_cast<SizeT>(extent.x()) * extent.y();
-        Vector<Uint8> result(count * extent.z() * pixelBytes);
-        if (g_GLESFuncs.glMemoryBarrier) g_GLESFuncs.glMemoryBarrier(GL_ALL_BARRIER_BITS);
-        g_GLESFuncs.glFinish();
-        for (GLint z = 0; z < extent.z(); ++z) {
-            if (nativeTarget == GL_TEXTURE_3D || nativeTarget == GL_TEXTURE_2D_ARRAY ||
-                nativeTarget == GL_TEXTURE_CUBE_MAP_ARRAY)
-                g_GLESFuncs.glFramebufferTextureLayer(GL_READ_FRAMEBUFFER, point, texture, level, z);
-            else
-                g_GLESFuncs.glFramebufferTexture2D(GL_READ_FRAMEBUFFER, point,
-                    TextureImpl::ConvertTextureUploadTargetToBackendGLEnum(uploadTarget), texture, level);
-            g_GLESFuncs.glReadBuffer(GL_NONE);
-            if (g_GLESFuncs.glCheckFramebufferStatus(GL_READ_FRAMEBUFFER) != GL_FRAMEBUFFER_COMPLETE) return false;
-            Vector<Float> depth;
-            Vector<Uint8> stencil;
-            if (needDepth && !ReadDepthValuesNative(0, 0, extent.x(), extent.y(), depth)) return false;
-            if (needStencil && !ReadStencilBytesNative(0, 0, extent.x(), extent.y(), stencil)) return false;
-            auto* dst = result.data() + count * z * pixelBytes;
-            for (SizeT i = 0; i < count; ++i) {
-                if (format == GL_DEPTH_STENCIL) {
-                    const Uint32 s = stencil[i];
-                    if (type == GL_UNSIGNED_INT_24_8) {
-                        const Uint32 packed = (NormalizedDepthToUnsigned(depth[i], 16777215.0) << 8) | s;
-                        Memcpy(dst + i * pixelBytes, &packed, sizeof(packed));
-                    } else if (type == GL_FLOAT_32_UNSIGNED_INT_24_8_REV) {
-                        Memcpy(dst + i * pixelBytes, &depth[i], sizeof(Float));
-                        Memcpy(dst + i * pixelBytes + sizeof(Float), &s, sizeof(s));
-                    } else return false;
-                } else if (type == GL_FLOAT) {
-                    const Float value = needDepth ? depth[i] : static_cast<Float>(stencil[i]);
-                    Memcpy(dst + i * pixelBytes, &value, sizeof(value));
-                } else if (type == GL_HALF_FLOAT) {
-                    const Uint16 value = MG_Util::EncodeFloatToHalfBits(
-                        needDepth ? depth[i] : static_cast<Float>(stencil[i]));
-                    Memcpy(dst + i * pixelBytes, &value, sizeof(value));
-                } else {
-                    const Bool signedType = type == GL_BYTE || type == GL_SHORT || type == GL_INT;
-                    const Double maximum = signedType
-                        ? (pixelBytes == 1 ? 127.0 : pixelBytes == 2 ? 32767.0 : 2147483647.0)
-                        : (pixelBytes == 1 ? 255.0 : pixelBytes == 2 ? 65535.0 : 4294967295.0);
-                    const Uint32 value = needDepth ? NormalizedDepthToUnsigned(depth[i], maximum) : stencil[i];
-                    if (pixelBytes == 1) dst[i] = static_cast<Uint8>(value);
-                    else if (pixelBytes == 2) { const Uint16 v = static_cast<Uint16>(value); Memcpy(dst + i * 2, &v, 2); }
-                    else if (pixelBytes == 4) Memcpy(dst + i * 4, &value, 4);
-                    else return false;
-                }
-            }
-        }
-        bytes = Move(result);
-        return true;
-    }
-
-    Bool ReadTextureLevelTight(GLuint texture, TextureTarget target, TextureUploadTarget uploadTarget,
-                               TextureInternalFormat logicalFormat, GLint level, const IntVec3& logicalExtent,
-                               Bool sourceUsesImageCarrier, GLenum format, GLenum type, Vector<Uint8>& bytes) {
-        if (!texture || level < 0 || TextureImpl::IsMultisampleTextureTarget(target)) return false;
-        const IntVec3 extent = TextureImpl::GetBackendUploadSize(target, logicalExtent);
-        const GLenum nativeTarget = TextureImpl::ConvertTextureTargetToBackendGLEnum(target);
-        ScopedWireTextureReadLevel readLevel(texture, nativeTarget, level);
-        if (!readLevel.Valid()) return false;
-        if (format == GL_DEPTH_COMPONENT || format == GL_DEPTH_STENCIL || format == GL_STENCIL_INDEX)
-            return ReadWireDepthStencilLevelTight(texture, target, uploadTarget, level, extent, format, type, bytes);
-        ReadbackChannelMapping mapping{};
-        if (!GetReadbackChannelMapping(format, mapping)) return false;
-        const SizeT pixelBytes = GetReadbackDstPixelSize(mapping, type);
-        if (!pixelBytes || extent.x() <= 0 || extent.y() <= 0 || extent.z() <= 0) return false;
-        const GLenum faceTarget = TextureImpl::ConvertTextureUploadTargetToBackendGLEnum(uploadTarget);
-        const auto widening = sourceUsesImageCarrier
-            ? TextureImpl::GetImageBindableStorageWidening(logicalFormat) : TextureImpl::ImageBindableStorageWidening{};
-        const SizeT sliceBytes = static_cast<SizeT>(extent.x()) * extent.y() * pixelBytes;
-        Vector<Uint8> result(sliceBytes * static_cast<SizeT>(extent.z()));
-        if (g_GLESFuncs.glMemoryBarrier) g_GLESFuncs.glMemoryBarrier(GL_ALL_BARRIER_BITS);
-        g_GLESFuncs.glFinish();
-
-        // A raw packed word may have redundant encodings or NaN payloads. Read
-        // it through R32UI when the source really still uses that native layout.
-        const Bool rawPacked = !widening && MG_Util::PixelStoreProcessor::IsRawPackedPixelTransfer(
-            logicalFormat, MG_Util::ConvertGLEnumToTextureInputFormat(format),
-            MG_Util::ConvertGLEnumToTexturePixelDataType(type));
-        if (rawPacked && pixelBytes == sizeof(Uint32)) {
-            const GLint face = uploadTarget >= TextureUploadTarget::CubeMapPositiveX &&
-                               uploadTarget <= TextureUploadTarget::CubeMapNegativeZ
-                ? static_cast<GLint>(uploadTarget) - static_cast<GLint>(TextureUploadTarget::CubeMapPositiveX) : 0;
-            for (GLint layer = 0; layer < extent.z(); ++layer)
-                if (!ReadPackedLevelWordsViaScratch(texture, nativeTarget, level, face + layer, extent.x(), extent.y(),
-                        reinterpret_cast<Uint32*>(result.data() + static_cast<SizeT>(layer) * sliceBytes))) return false;
-            bytes = Move(result);
-            return true;
-        }
-
-        NormalizedImageCarrierRead carrier{};
-        if (widening && widening.CarriesNormalizedCodes()) {
-            for (SizeT c = 0; c < 4; ++c) carrier.ChannelMax[c] = widening.ChannelMax[c];
-            carrier.SignedNormalized = widening.SignedNormalized;
-        }
-        TempFBOBinder binder(true);
-        auto& framebuffer = binder.Framebuffer();
-        for (GLint layer = 0; layer < extent.z(); ++layer) {
-            if (nativeTarget == GL_TEXTURE_3D || nativeTarget == GL_TEXTURE_2D_ARRAY || nativeTarget == GL_TEXTURE_CUBE_MAP_ARRAY)
-                ScratchFBOImpl::EnsureColorAttachmentLayer(framebuffer, GL_READ_FRAMEBUFFER, texture, level, layer);
-            else
-                ScratchFBOImpl::EnsureColorAttachment2D(framebuffer, GL_READ_FRAMEBUFFER, texture, faceTarget, level);
-            ScratchFBOImpl::EnsureReadBuffer(framebuffer, GL_COLOR_ATTACHMENT0);
-            const GLenum status = g_GLESFuncs.glCheckFramebufferStatus(GL_READ_FRAMEBUFFER);
-            if (status != GL_FRAMEBUFFER_COMPLETE) {
-                MGLOG_E_ONCE("Espryt wire texture readback: framebuffer status=0x%x texture=%u level=%d target=0x%x",
-                            status, texture, level, nativeTarget);
-                return false;
-            }
-            Vector<Uint8> slice;
-            if (!ReadWireColorRowsTight(extent.x(), extent.y(), format, type,
-                    TextureImpl::BackendTextureFormatAddsAlpha(logicalFormat, target), carrier, slice) ||
-                slice.size() != sliceBytes) return false;
-            Memcpy(result.data() + static_cast<SizeT>(layer) * sliceBytes, slice.data(), sliceBytes);
-        }
-        bytes = Move(result);
-        return true;
-    }
-
-    Bool ReadTextureImageWire(const MG_Pipe::MGPReadbackInfo& info, Vector<Uint8>& bytes) {
-        const auto* record = PipeTextureRecordForHandle(info.Res);
-        if (!record) return false;
-        TextureTarget target = TextureTarget::Unknown;
-        for (Int i = 0; i < static_cast<Int>(TextureTarget::TextureTargetCount); ++i)
-            if (MG_Pipe::MGPipeResourceTargetForTextureTarget(static_cast<TextureTarget>(i)) == record->Desc.Target)
-                target = static_cast<TextureTarget>(i);
-        if (target == TextureTarget::Unknown) return false;
-        const auto twin = TextureImpl::SyncTextureToBackendByHandle(info.Res);
-        if (!twin) return false;
-        const Bool wholeCube = info.Target == GL_TEXTURE_CUBE_MAP;
-        const IntVec3 extent{static_cast<Int>(info.Box.W), static_cast<Int>(info.Box.H),
-                            wholeCube ? 1 : static_cast<Int>(info.Box.D)};
-        Vector<Uint8> result;
-        for (Int face = 0; face < (wholeCube ? 6 : 1); ++face) {
-            const auto uploadTarget = wholeCube
-                ? static_cast<TextureUploadTarget>(static_cast<Int>(TextureUploadTarget::CubeMapPositiveX) + face)
-                : MG_Util::ConvertGLEnumToTextureUploadTarget(info.Target);
-            Vector<Uint8> slice;
-            if (!ReadTextureLevelTight(twin->GetBackendTextureId(), target, uploadTarget,
-                    static_cast<TextureInternalFormat>(record->Desc.InternalFormat), info.Level, extent,
-                    twin->RequiresImageBindableStorage(), info.Format, info.Type, slice)) return false;
-            result.insert(result.end(), slice.begin(), slice.end());
-        }
-        bytes = Move(result);
-        return true;
-    }

MobileGL/MG_Backend/DirectVulkan/BackendObject_DirectVulkan.cpp

@@ -9,20 +9,15 @@
 #include "BackendObject_DirectVulkan.h"
 #include "MG_Backend/BackendObject.h"
 #include "DirectVulkan.h"
-#include "SubgroupSupportPolicy.h"
 #include "MG_State/GLState/FramebufferState/FramebufferObject.h"
-#include "MG_State/GLState/Core.h"
-#include <MG_Pipe/PipeInputsSwitch.h>
 #include "MG_State/GLState/TextureState/TextureState.h"
 #include "MG_Util/Classifiers/TextureEnumClassifier.h"
 #include "MG_Util/Converters/MGToGL/TextureEnumConverter.h"
 #include "MG_Util/Converters/MGToStr/TextureEnumConverter.h"
 #include "MG_Util/Converters/MGToVk/TextureEnumConverter.h"
 #include "MG_Util/Texture/TextureFormatProcessor.h"
-#include "MG_Util/Async/ShaderCompilePool.h"
 
 #include <Config.h>
-#include <cmath>
 #include <cstdlib>
 #include <cstring>
 
@@ -45,11 +40,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Bool IsLayeredTarget(TextureTarget target) {
             return target == TextureTarget::Texture3D || target == TextureTarget::Texture1DArray ||
                    target == TextureTarget::Texture2DArray || target == TextureTarget::TextureCubeMap ||
-                   target == TextureTarget::TextureCubeMapArray || target == TextureTarget::Texture2DMultisampleArray;
+                   target == TextureTarget::TextureCubeMapArray ||
+                   target == TextureTarget::Texture2DMultisampleArray;
         }
 
         Bool IsMultisampleTarget(TextureTarget target) {
-            return target == TextureTarget::Texture2DMultisample || target == TextureTarget::Texture2DMultisampleArray;
+            return target == TextureTarget::Texture2DMultisample ||
+                   target == TextureTarget::Texture2DMultisampleArray;
         }
 
         Bool IsTextureBufferTarget(TextureTarget target) {
@@ -61,8 +58,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             GLenum normalizedInternalFormat = glFormat;
             GLenum imageFormat = GL_RGBA;
             GLenum imageType = GL_UNSIGNED_BYTE;
-            MG_Util::TextureFormatProcessor::NormalizePixelFormat(glFormat, PixelFormatNormalizeOptionBit::None,
-                                                                  &normalizedInternalFormat, &imageFormat, &imageType);
+            MG_Util::TextureFormatProcessor::NormalizePixelFormat(
+                glFormat, PixelFormatNormalizeOptionBit::None, &normalizedInternalFormat, &imageFormat, &imageType);
             return imageFormat == GL_RED_INTEGER || imageFormat == GL_RG_INTEGER || imageFormat == GL_RGB_INTEGER ||
                    imageFormat == GL_RGBA_INTEGER;
         }
@@ -83,7 +80,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return caps;
         }
 
-        FormatCapabilityFlags BuildVulkanCaps(TextureInternalFormat logicalFormat, TextureTarget target,
+        FormatCapabilityFlags BuildVulkanCaps(TextureInternalFormat logicalFormat,
+                                              TextureTarget target,
                                               VkFormatFeatureFlags features) {
             FormatCapabilityFlags caps;
             const Bool isDepth = MG_Util::IsDepthFormatInternalFormat(logicalFormat);
@@ -102,7 +100,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             const Bool sampled = (features & VK_FORMAT_FEATURE_SAMPLED_IMAGE_BIT) != 0;
             const Bool linearFilter = (features & VK_FORMAT_FEATURE_SAMPLED_IMAGE_FILTER_LINEAR_BIT) != 0;
             const Bool colorRenderable = (features & VK_FORMAT_FEATURE_COLOR_ATTACHMENT_BIT) != 0;
-            const Bool depthStencilRenderable = (features & VK_FORMAT_FEATURE_DEPTH_STENCIL_ATTACHMENT_BIT) != 0;
+            const Bool depthStencilRenderable =
+                (features & VK_FORMAT_FEATURE_DEPTH_STENCIL_ATTACHMENT_BIT) != 0;
             const Bool renderable = (isDepth || isStencil) ? depthStencilRenderable : colorRenderable;
 
             if (sampled || renderable) {
@@ -141,20 +140,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             case TextureInternalFormat::RGB:
             case TextureInternalFormat::RGB8:
                 return TextureInternalFormat::RGBA8;
-            // Legacy low-bit-depth formats with no (or rarely supported) native Vulkan
-            // encoding; a wider normalized fallback keeps at least the required precision.
-            case TextureInternalFormat::R3G3B2:
-            case TextureInternalFormat::RGB4:
-            case TextureInternalFormat::RGB5:
-            case TextureInternalFormat::RGBA2:
-            case TextureInternalFormat::RGBA4:
-            case TextureInternalFormat::RGB5A1:
-                return TextureInternalFormat::RGBA8;
-            case TextureInternalFormat::RGB10:
-                return TextureInternalFormat::RGB10A2;
-            case TextureInternalFormat::RGB12:
-            case TextureInternalFormat::RGBA12:
-                return TextureInternalFormat::RGBA16;
             case TextureInternalFormat::SRGB8:
                 return TextureInternalFormat::SRGB8Alpha8;
             case TextureInternalFormat::RGB8Snorm:
@@ -199,20 +184,21 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         Bool HasNewCaveatFormatCaps(FormatCapabilityFlags nativeCaps, FormatCapabilityFlags fallbackCaps) {
             for (FormatCapability capability : kReportedFormatCapabilities) {
-                if (HasFormatCapability(fallbackCaps, capability) && !HasFormatCapability(nativeCaps, capability)) {
+                if (HasFormatCapability(fallbackCaps, capability) &&
+                    !HasFormatCapability(nativeCaps, capability)) {
                     return true;
                 }
             }
             return false;
         }
 
-        void LogVulkanFormatCaveat(TextureInternalFormat logicalFormat, SizeT targetIndex,
+        void LogVulkanFormatCaveat(TextureInternalFormat logicalFormat,
+                                   SizeT targetIndex,
                                    TextureInternalFormat fallbackFormat) {
-            MGLOG_D(
-                "Caveat: %s %s not fully supported. Reason: native Vulkan format is not fully supported. Fallback: %s",
-                GetFormatCapabilityTargetName(targetIndex).c_str(),
-                MG_Util::ConvertTextureInternalFormatToString(logicalFormat).c_str(),
-                MG_Util::ConvertTextureInternalFormatToString(fallbackFormat).c_str());
+            MGLOG_D("Caveat: %s %s not fully supported. Reason: native Vulkan format is not fully supported. Fallback: %s",
+                    GetFormatCapabilityTargetName(targetIndex).c_str(),
+                    MG_Util::ConvertTextureInternalFormatToString(logicalFormat).c_str(),
+                    MG_Util::ConvertTextureInternalFormatToString(fallbackFormat).c_str());
         }
 
         Vector<Int> BuildSampleCounts(Int maxSamples) {
@@ -256,15 +242,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
                 for (SizeT targetIndex = 0; targetIndex < kFormatCapabilityTextureTargetCount; ++targetIndex) {
                     const auto target = static_cast<TextureTarget>(targetIndex);
-                    const VkFormatFeatureFlags nativeFeatures = IsTextureBufferTarget(target)
-                                                                    ? nativeProperties.bufferFeatures
-                                                                    : nativeProperties.optimalTilingFeatures;
+                    const VkFormatFeatureFlags nativeFeatures =
+                        IsTextureBufferTarget(target) ? nativeProperties.bufferFeatures
+                                                      : nativeProperties.optimalTilingFeatures;
                     FormatCapabilityFlags nativeCaps = BuildVulkanCaps(logicalFormat, target, nativeFeatures);
                     cache.FullCaps[targetIndex][formatIndex] |= nativeCaps;
 
-                    const VkFormatFeatureFlags fallbackFeatures = IsTextureBufferTarget(target)
-                                                                      ? fallbackProperties.bufferFeatures
-                                                                      : fallbackProperties.optimalTilingFeatures;
+                    const VkFormatFeatureFlags fallbackFeatures =
+                        IsTextureBufferTarget(target) ? fallbackProperties.bufferFeatures
+                                                      : fallbackProperties.optimalTilingFeatures;
                     FormatCapabilityFlags fallbackCaps = BuildVulkanCaps(logicalFormat, target, fallbackFeatures);
                     if (fallbackFormat != VK_FORMAT_UNDEFINED && fallbackFormat != nativeFormat) {
                         cache.CaveatCaps[targetIndex][formatIndex] |= fallbackCaps;
@@ -299,8 +285,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 cache.FullCaps[renderbufferTargetIndex][formatIndex] |= renderbufferCaps;
 
                 if (fallbackFormat != VK_FORMAT_UNDEFINED && fallbackFormat != nativeFormat) {
-                    FormatCapabilityFlags fallbackRenderbufferCaps = BuildVulkanCaps(
-                        logicalFormat, TextureTarget::Texture2D, fallbackProperties.optimalTilingFeatures);
+                    FormatCapabilityFlags fallbackRenderbufferCaps =
+                        BuildVulkanCaps(logicalFormat, TextureTarget::Texture2D,
+                                        fallbackProperties.optimalTilingFeatures);
                     fallbackRenderbufferCaps &= FormatCapability::Creatable;
                     if ((fallbackProperties.optimalTilingFeatures &
                          (VK_FORMAT_FEATURE_COLOR_ATTACHMENT_BIT | VK_FORMAT_FEATURE_DEPTH_STENCIL_ATTACHMENT_BIT)) !=
@@ -309,7 +296,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                         fallbackRenderbufferCaps |= FormatCapability::MultisampleRenderbuffer;
                     }
                     cache.CaveatCaps[renderbufferTargetIndex][formatIndex] |= fallbackRenderbufferCaps;
-                    if (fallbackLogicalFormat && HasNewCaveatFormatCaps(renderbufferCaps, fallbackRenderbufferCaps)) {
+                    if (fallbackLogicalFormat &&
+                        HasNewCaveatFormatCaps(renderbufferCaps, fallbackRenderbufferCaps)) {
                         LogVulkanFormatCaveat(logicalFormat, renderbufferTargetIndex, *fallbackLogicalFormat);
                     }
                 }
@@ -326,31 +314,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
     void PopulateFormatCapabilities(VkPhysicalDevice physicalDevice,
                                     PFN_vkGetPhysicalDeviceFormatProperties getFormatProperties,
-                                    const MG_External::VulkanCapabilities& capabilities, FormatCapabilityCache& cache) {
+                                    const MG_External::VulkanCapabilities& capabilities,
+                                    FormatCapabilityCache& cache) {
         PopulateFormatCapabilitiesImpl(physicalDevice, getFormatProperties, capabilities, cache);
     }
 
-#if MOBILEGL_BUILD_DISAGGREGATED
-    BackendObject_DirectVulkan::~BackendObject_DirectVulkan() {
-        // P12 review fix: A SERVER SESSION THAT ENDS WITHOUT A CLEAN TEARDOWN LEAVES NO RENDERER ON
-        // THE WINDOW. The renderer - swapchain and VkSurfaceKHR on the window - is a process global
-        // that only ReleaseEGLResources / a released surface drops, and a client that went away
-        // without eglTerminate (a crash, a kill, a dropped connection) sends neither. Under a
-        // transport this object is the server's and its destruction is the session's end (ServerLoop's
-        // apply thread, after the final drain, before the display lease ends), so the renderer goes
-        // here: nothing of the ended session keeps presenting into, or holding a surface on, the
-        // server's window once its lease is over. Monolith keeps its renderer.
-        if (MG_Config::Transport != MG_Config::TransportMode::Monolith && pVulkanRenderer != nullptr) {
-            BumpRendererGeneration();
-            pVulkanRenderer.reset();
-            ClearProgramResourceCaches();
-        }
-    }
-#else
     BackendObject_DirectVulkan::~BackendObject_DirectVulkan() = default;
-#endif
 
-    BackendObject_DirectVulkan::BackendObject_DirectVulkan() : m_rendererInfo{GetRendererIdentity()} {}
+    BackendObject_DirectVulkan::BackendObject_DirectVulkan(): m_rendererInfo{GetRendererIdentity()} {}
 
     Bool BackendObject_DirectVulkan::InitWindowSurface() {
         if (!m_windowHandle.Handle) {
@@ -383,18 +354,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     }
 
     void BackendObject_DirectVulkan::Initialize() {
-#if MOBILEGL_BUILD_DISAGGREGATED
-        VkBufferManager::RegisterWireResourceOps();
-#if MOBILEGL_PIPE_PUSH
-        // P7 wave 2 package C (CONTRACT-P7 §5.5). BESIDE the resource ops and for the same
-        // reason: this is the one place both Magma server roles pass through - the inproc
-        // role and the spawn/TCP session child - and ServerLoop::CreateBackend calls it at
-        // step 1 of InitServerRoleCommon, before the client session exists and therefore
-        // before any frontend object can die unheard. A per-transport install is how one of
-        // the two roles ends up without it.
-        InstallStateObjectDeathOps();
-#endif
-#endif
         m_initialized = true;
     }
 
@@ -416,9 +375,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
         UpdateDynamicBackendParameters();
         UpdateAdvertisedExtensions();
-        if (MGB_CTX_LIVE) {
-            MGB_CTX->InvalidateCompileEnv();
-        }
         PopulateFormatCapabilities(physicalDevice.handle, vkGetPhysicalDeviceFormatProperties, m_vulkanCaps,
                                    MutableFormatCapabilities());
         PrintFormatCapabilities(GetFormatCapabilities());
@@ -439,9 +395,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             MGLOG_E("DirectVulkan backend not initialized");
             return false;
         }
-        if (!handle.Handle || (handle.Backend != WindowBackend::Android && handle.Backend != WindowBackend::X11 &&
-                               handle.Backend != WindowBackend::MetalLayer && handle.Backend != WindowBackend::Win32)) {
-            MGLOG_E("DirectVulkan backend only supports Android, X11, CAMetalLayer, and Win32 native windows");
+        if (!handle.Handle || (handle.Backend != WindowBackend::Android &&
+                               handle.Backend != WindowBackend::X11 &&
+                               handle.Backend != WindowBackend::MetalLayer)) {
+            MGLOG_E("DirectVulkan backend only supports Android, X11, and CAMetalLayer native windows");
             return false;
         }
 
@@ -497,9 +454,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // treat them as signaled/available with zero results from here on.
         BumpRendererGeneration();
         pVulkanRenderer.reset();
-        // The reflection cache is file-scope, not renderer-owned; without this the
-        // deleted programs' reflection strings survive full context teardown.
-        ClearProgramResourceCaches();
         BackendObject::ReleaseEGLResources();
     }
 
@@ -509,9 +463,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // treat them as signaled/available with zero results from here on.
         BumpRendererGeneration();
         pVulkanRenderer.reset();
-        // The reflection cache is file-scope, not renderer-owned; without this the
-        // deleted programs' reflection strings survive full context teardown.
-        ClearProgramResourceCaches();
     }
 
     const RendererInfo& BackendObject_DirectVulkan::GetRendererInfo() const {
@@ -531,158 +482,35 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             .RendererName = "Magma",
             .BackendName = "Direct (Vulkan)",
             .ExtraVendor = Nullopt,
-            .RendererGLInfo = {.TargetGLVersion = {4, 6, 0},
-                               .TargetGLSLVersion = {4, 6, 0},
-                               // Baseline advertisement (no runtime-gated capabilities); a live
-                               // backend reconciles its copy in UpdateAdvertisedExtensions.
-                               .Extensions = BuildAdvertisedExtensions(false, false, false, false, false),
-                               .IsCompatibilityProfile = false},
+            .RendererGLInfo =
+                {
+                    .TargetGLVersion = {3, 3, 0},
+                    .TargetGLSLVersion = {4, 6, 0},
+                    // Baseline advertisement (no shader subgroup, no timer queries); a
+                    // live backend reconciles its copy in UpdateAdvertisedExtensions.
+                    .Extensions = BuildAdvertisedExtensions(false, false, false),
+                    .IsCompatibilityProfile = false
+                },
             .StaticBackendCapability = {.AllowVSOnlyPrograms = false}};
         return rendererInfo;
     }
 
     Vector<GLExtension> BuildAdvertisedExtensions(Bool shaderSubgroupSupported, Bool timerQueriesSupported,
-                                                  Bool anisotropicFilteringSupported,
-                                                  Bool nonZeroIndirectBaseInstanceSupported,
-                                                  Bool cubeMapArraySupported) {
-        Vector<GLExtension> extensions = {
-            // The version tokens have to reach the version the backend actually claims:
-            // TargetGLVersion is {4,6,0}, and a list that stopped at OpenGL40 told an
-            // application feature-detecting off these tokens the opposite of what
-            // GL_MAJOR_VERSION / GL_MINOR_VERSION told it.
-            V_OpenGL30, V_OpenGL31, V_OpenGL32, V_OpenGL33, V_OpenGL40, V_OpenGL41, V_OpenGL42, V_OpenGL43,
-            V_OpenGL44, V_OpenGL45, V_OpenGL46,
-            E_GL_ARB_draw_buffers_blend,
-            E_GL_ARB_compute_shader, E_GL_ARB_shader_storage_buffer_object, E_GL_ARB_shader_image_load_store,
-            E_GL_ARB_clear_buffer_object, E_GL_ARB_program_interface_query, E_GL_ARB_framebuffer_object, E_GL_ARB_draw_indirect,
-            E_GL_ARB_multi_draw_indirect,
-            E_GL_ARB_indirect_parameters, E_GL_EXT_framebuffer_object, E_GL_ARB_depth_texture, E_GL_ARB_buffer_storage,
-            E_GL_ARB_texture_storage, E_GL_ARB_texture_storage_multisample, E_GL_ARB_texture_multisample,
-            E_GL_ARB_clear_texture, E_GL_ARB_direct_state_access, E_GL_ARB_shader_draw_parameters,
-            E_GL_ARB_gpu_shader_int64, E_GL_KHR_debug, E_GL_ARB_gpu_shader5, E_GL_ARB_multi_bind,
-            E_GL_ARB_shading_language_420pack, E_GL_ARB_vertex_attrib_binding, E_GL_ARB_shader_image_size,
-            E_GL_ARB_explicit_attrib_location,
-            // Core since GL 3.1 and implemented for every version advertised here. The string
-            // matters because applications gate the ENTRY POINTS on it rather than on the
-            // version: a caller that finds the extension missing never resolves
-            // glGetUniformBlockIndex / glUniformBlockBinding, and one that then uses uniform
-            // blocks anyway calls through a null pointer.
-            E_GL_ARB_uniform_buffer_object,
-            // Sampling the stencil aspect through DEPTH_STENCIL_TEXTURE_MODE. Core from 4.3,
-            // so on a 4.0 context the string is the only way to reach it.
-            E_GL_ARB_stencil_texturing,
-            // Unconditional, unlike DirectGLES: a GL texture view is a second set of VkImageViews
-            // over the same VkImage with a sub-range and possibly a reinterpreted VkFormat, which
-            // is core Vulkan on every device MobileGL runs on. Format-reinterpreting views need
-            // VK_IMAGE_CREATE_MUTABLE_FORMAT_BIT on the image, which SyncTextureResource sets for
-            // every immutable-storage texture (see the comment there).
-            E_GL_ARB_texture_view,
-            // Core since 3.2 and implemented here on both backends - glDrawElementsBaseVertex,
-            // glDrawRangeElementsBaseVertex, glDrawElementsInstancedBaseVertex and
-            // glMultiDrawElementsBaseVertex all reach real per-draw vertex rebasing. The string
-            // was simply never emitted, which left KHR-GL4*.draw_elements_base_vertex_tests
-            // NotSupported on a feature that works.
-            E_GL_ARB_draw_elements_base_vertex,
-            // The whole sync-object family is real and core since 3.2: glFenceSync, glIsSync,
-            // glDeleteSync, glClientWaitSync, glWaitSync and glGetSynciv all live in GLImpl over a
-            // backend fence (a VkFence here, an EGLSync/GLsync on DirectGLES), and glGetInteger64v
-            // answers GL_MAX_SERVER_WAIT_TIMEOUT. The string matters for the same reason
-            // ARB_uniform_buffer_object's does: LWJGL builds GLCapabilities from the extension
-            // list, and a caller that finds GL_ARB_sync missing never resolves the entry points -
-            // then calls through null if it uses fences anyway. Nothing in the CTS gates on this
-            // string, so it is advertised on the strength of the implementation, not a test unlock.
-            E_GL_ARB_sync,
-            // Atomic counters, core since 4.2. glGetActiveAtomicCounterBufferiv and the whole
-            // GL_ATOMIC_COUNTER_BUFFER_* query family are real in GLImpl, and the counter buffer
-            // now reaches the shader on BOTH backends - Magma resolves the lowered
-            // gl_AtomicCounterBlock_<N> from the atomic-counter binding points rather than the
-            // shader-storage ones (see ResolveStorageBufferDescriptor). Withheld here until that
-            // landed, because the counter silently read whatever was bound as SSBO N instead.
-            E_GL_ARB_shader_atomic_counters,
-            // glVertexAttribDivisor, core since 3.3 and real on both backends. Applications
-            // (Better Clouds' GLCompat among them) accept the extension string as an
-            // ALTERNATIVE to a 3.3 context when deciding whether instanced rendering is
-            // available, so withholding it makes MobileGL look less capable than it is.
-            E_GL_ARB_instanced_arrays,
-            // Core GL 3.0-4.3 plumbing that has been real here for as long as the backend has
-            // existed, and that was simply never named. None of these unlocks a single CTS case -
-            // the conformance suite reaches all of them through the version - so they are
-            // advertised for the OTHER consumer of this list: LWJGL builds GLCapabilities from the
-            // string set, and an application that gates its ENTRY POINTS on the string rather than
-            // on the version never resolves them and then calls through null. Each is backed by
-            // the entry points named beside it. Kept identical to the DirectGLES block so the two
-            // backends do not disagree about what MobileGL is.
-            //
-            // glBindVertexArray / glGenVertexArrays / glDeleteVertexArrays / glIsVertexArray.
-            E_GL_ARB_vertex_array_object,
-            // The 14 glSamplerParameter* / glGetSamplerParameter* entry points, including the
-            // integer-valued Iiv/Iuiv forms.
-            E_GL_ARB_sampler_objects,
-            // glMapBufferRange + glFlushMappedBufferRange, which ARB_buffer_storage's persistent
-            // maps are already built on top of.
-            E_GL_ARB_map_buffer_range,
-            // glCopyBufferSubData plus the GL_COPY_READ_BUFFER / GL_COPY_WRITE_BUFFER targets.
-            E_GL_ARB_copy_buffer,
-            // glCopyImageSubData, wired to a real backend hook on both backends.
-            E_GL_ARB_copy_image,
-            // GL_TEXTURE_SWIZZLE_{R,G,B,A,RGBA}, which map onto a VkImageView's component swizzle.
-            E_GL_ARB_texture_swizzle,
-            // GL_INT_2_10_10_10_REV / GL_UNSIGNED_INT_2_10_10_10_REV on glVertexAttribPointer plus
-            // the eight glVertexAttribP* entry points.
-            E_GL_ARB_vertex_type_2_10_10_10_rev,
-            // The R/RG internal formats. Named separately from the float ones because an
-            // application may check either.
-            E_GL_ARB_texture_rg,
-            // GL_DEPTH_COMPONENT32F and GL_DEPTH32F_STENCIL8.
-            E_GL_ARB_depth_buffer_float,
-            // The floating-point colour formats. Unlike the rest of this block this string DOES
-            // gate CTS cases - KHR-GL4*.internalformat.texture2d.*{16f,32f} is keyed on it with no
-            // core-version fallback, so eight cases per version list were NotSupported on formats
-            // the backend has always had.
-            E_GL_ARB_texture_float,
-            // glViewportArrayv / glViewportIndexedf{,v} / glScissorArrayv / glScissorIndexed{,v} /
-            // glDepthRangeArrayv / glDepthRangeIndexed / glGetFloati_v / glGetDoublei_v, over the
-            // 16 viewports GL_MAX_VIEWPORTS reports.
-            E_GL_ARB_viewport_array,
-            // Advertised with GL_NUM_PROGRAM_BINARY_FORMATS = 0, which the
-            // extension explicitly permits. It is also the only thing that
-            // exposes glProgramParameteri before GL 4.1.
-            E_GL_ARB_get_program_binary};
-        // Vulkan's drawIndirectFirstInstance feature is optional. Direct base-instance calls work
-        // without it, but ARB_base_instance also promises non-zero firstInstance in GPU indirect
-        // commands; the renderer supplies true only when that word is legal and gl_InstanceID can
-        // be rebased to OpenGL's zero-based semantics.
-        if (nonZeroIndirectBaseInstanceSupported) {
-            extensions.push_back(E_GL_ARB_base_instance);
-        }
-        if (shaderSubgroupSupported && !MG_Config::Features.MagmaDisableSubgroup) {
+                                                  Bool anisotropicFilteringSupported) {
+        Vector<GLExtension> extensions = {V_OpenGL30, V_OpenGL31, V_OpenGL32,
+                                          V_OpenGL33, E_GL_ARB_draw_buffers_blend, E_GL_ARB_compute_shader,
+                                          E_GL_ARB_shader_storage_buffer_object, E_GL_ARB_shader_image_load_store,
+                                          E_GL_ARB_program_interface_query, E_GL_ARB_framebuffer_object,
+                                          E_GL_ARB_multi_draw_indirect, E_GL_ARB_indirect_parameters,
+                                          E_GL_EXT_framebuffer_object, E_GL_ARB_depth_texture, E_GL_ARB_buffer_storage,
+                                          E_GL_ARB_texture_storage, E_GL_ARB_texture_storage_multisample,
+                                          E_GL_ARB_clear_texture, E_GL_ARB_direct_state_access,
+                                          E_GL_ARB_shader_draw_parameters, E_GL_ARB_gpu_shader_int64, E_GL_KHR_debug,
+                                          E_GL_ARB_gpu_shader5, E_GL_ARB_multi_bind, E_GL_ARB_shading_language_420pack,
+                                          E_GL_ARB_vertex_attrib_binding, E_GL_ARB_shader_image_size};
+        if (shaderSubgroupSupported && !MG_Config::Features.DisableSubgroup) {
             extensions.push_back(E_GL_KHR_shader_subgroup);
         }
-        // GL_KHR_parallel_shader_compile is MobileGL's own capability, not the Vulkan
-        // device's: the compiler threads belong to MobileGL's shader pool and
-        // glCompileShader/glLinkProgram are serviced entirely inside the frontend, so there
-        // is no device feature to condition this on.
-        //
-        // Gated on the async flag deliberately, and this is the whole reason the gate
-        // exists. Advertising the string is the one part of asynchronous compilation that a
-        // recorded trace can never cover: Iris and Sodium change their SUBMISSION SCHEDULE
-        // the moment they see it - they enqueue whole pipeline batches and poll
-        // GL_COMPLETION_STATUS_KHR instead of compiling one program at a time - so
-        // MOBILEGL_ASYNC_SHADER_COMPILE=0 has to withdraw the application-visible behaviour
-        // change as well as the threading, or the kill switch would only be half a switch.
-        if (MG_Util::Async::AsyncShaderCompileEnabled()) {
-            extensions.push_back(E_GL_KHR_parallel_shader_compile);
-        }
-        // GL_ARB_gpu_shader_fp64 is opt-in (MOBILEGL_ADVERTISE_FP64), and stays opt-in even on a
-        // device that HAS shaderFloat64. Every `double` in a shader compiles and runs either way
-        // - narrowed to 32 bits where the device has no 64-bit floats, kept whole where it does -
-        // so an application that simply uses doubles needs nothing advertised. What the extension
-        // additionally promises is the whole GL_ARB_gpu_shader_fp64 SURFACE (glUniform*d
-        // conformance, the fp64 built-ins, the state queries), and turning the string on is a
-        // decision about all of it rather than about the shader path alone.
-        if (MG_Config::Features.AdvertiseFp64) {
-            extensions.push_back(E_GL_ARB_gpu_shader_fp64);
-        }
         // GL_ARB_timer_query gates MC's F3 GPU% (LWJGL checks the extension string);
         // only advertised when the device actually supports timestamp queries and the
         // MOBILEGL_DISABLE_TIMERQUERY escape hatch is off.
@@ -696,18 +524,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             extensions.push_back(E_GL_EXT_texture_filter_anisotropic);
             extensions.push_back(E_GL_ARB_texture_filter_anisotropic);
         }
-        // A cube map array is a 6n-layer VkImage viewed as VK_IMAGE_VIEW_TYPE_CUBE_ARRAY, and that
-        // view type cannot be created without the imageCubeArray device feature - so the string
-        // follows the feature, not the version, exactly as the per-layer attachment bit does.
-        //
-        // Named for the application's benefit rather than the suite's: measured on Adreno 830,
-        // KHR-GL43.texture_gather.plain-gather-*-cube-array already passed without the string, so
-        // this unlocks no conformance case. It is advertised because the feature is real and
-        // because an application that feature-detects cube map arrays off the string (rather than
-        // off the 4.0 version) would otherwise decline a path this backend serves.
-        if (cubeMapArraySupported) {
-            extensions.push_back(E_GL_ARB_texture_cube_map_array);
-        }
         return extensions;
     }
 
@@ -754,8 +570,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             funcsTable.GL.ClearBufferiv = ClearBufferiv;
             funcsTable.GL.ClearNamedFramebufferfv = ClearNamedFramebufferfv;
             funcsTable.GL.ClearNamedFramebufferfi = ClearNamedFramebufferfi;
-            funcsTable.GL.ClearNamedFramebufferiv = ClearNamedFramebufferiv;
-            funcsTable.GL.ClearNamedFramebufferuiv = ClearNamedFramebufferuiv;
             funcsTable.GL.BlitFramebuffer = BlitFramebuffer;
             funcsTable.GL.BlitNamedFramebuffer = BlitNamedFramebuffer;
             funcsTable.GL.CopyTexImage2D = CopyTexImage2D;
@@ -771,6 +585,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             funcsTable.GL.MemoryBarrierByRegion = MemoryBarrierByRegion;
             funcsTable.GL.BindImageTexture = BindImageTexture;
             funcsTable.GL.GetIntegeri_v = GetIntegeri_v;
+            funcsTable.GL.GetInteger64i_v = GetInteger64i_v;
+            funcsTable.GL.GetProgramiv = GetProgramiv;
+            funcsTable.GL.GetProgramInterfaceiv = GetProgramInterfaceiv;
+            funcsTable.GL.GetProgramResourceIndex = GetProgramResourceIndex;
+            funcsTable.GL.GetProgramResourceName = GetProgramResourceName;
+            funcsTable.GL.GetProgramResourceiv = GetProgramResourceiv;
+            funcsTable.GL.GetProgramResourceLocation = GetProgramResourceLocation;
+            funcsTable.GL.GetProgramResourceLocationIndex = GetProgramResourceLocationIndex;
             funcsTable.GL.ShaderStorageBlockBinding = ShaderStorageBlockBinding;
             funcsTable.GL.FenceSync = FenceSync;
             funcsTable.GL.ClientWaitSync = ClientWaitSync;
@@ -791,15 +613,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 funcsTable.GL.DeleteBackendQuery = DeleteBackendQuery;
                 funcsTable.GL.GetGpuTimestampNs = GetGpuTimestampNs;
             }
-            // Occlusion queries share the handle-based result/delete entries, which must
-            // exist even when timer queries are disabled.
-            funcsTable.GL.BeginOcclusionQuery = BeginOcclusionQuery;
-            funcsTable.GL.EndOcclusionQuery = EndOcclusionQuery;
-            funcsTable.GL.BeginXfbPrimitivesQuery = BeginXfbPrimitivesQuery;
-            funcsTable.GL.EndXfbPrimitivesQuery = EndXfbPrimitivesQuery;
-            funcsTable.GL.IsQueryResultAvailable = IsQueryResultAvailable;
-            funcsTable.GL.GetQueryResult64 = GetQueryResult64;
-            funcsTable.GL.DeleteBackendQuery = DeleteBackendQuery;
             funcsTableInitialized = true;
         }
         return funcsTable;
@@ -814,9 +627,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_vulkanCaps = capabilities;
         UpdateDynamicBackendParameters();
         UpdateAdvertisedExtensions();
-        if (MGB_CTX_LIVE) {
-            MGB_CTX->InvalidateCompileEnv();
-        }
         MutableFormatCapabilities().Clear();
     }
 
@@ -827,17 +637,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // real device timestamp support. ApplyVulkanCapabilitiesForTesting may
         // run without a renderer; no timer query is advertised then. Rebuilding
         // the whole list keeps re-runs idempotent.
-        // The opt-in emulated compute path (SubgroupSupportPolicy.h) carries the
-        // extension by itself on devices with no native subgroup support at all; a
-        // device with native subgroups always advertises - and uses - those.
-        const Bool subgroupSupportAdvertised =
-            m_vulkanCaps.SupportsShaderSubgroup ||
-            ShouldEmulateSubgroups(m_vulkanCaps.SupportsShaderSubgroup);
         m_rendererInfo.RendererGLInfo.Extensions = BuildAdvertisedExtensions(
-            subgroupSupportAdvertised, pVulkanRenderer && pVulkanRenderer->IsTimerQuerySupported(),
-            pVulkanRenderer && pVulkanRenderer->IsSamplerAnisotropySupported(),
-            pVulkanRenderer && pVulkanRenderer->IsNonZeroIndirectBaseInstanceSupported(),
-            m_vulkanCaps.SupportsImageCubeArray);
+            m_vulkanCaps.SupportsShaderSubgroup, pVulkanRenderer && pVulkanRenderer->IsTimerQuerySupported(),
+            pVulkanRenderer && pVulkanRenderer->IsSamplerAnisotropySupported());
     }
 
     void BackendObject_DirectVulkan::UpdateDynamicBackendParameters() {
@@ -885,14 +687,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         static constexpr SizeT kMaxAdvertisedShaderStorageBlockSize = 512ull * 1024ull * 1024ull;
         m_dynamicParameters.UniformBufferOffsetAlignment = m_vulkanCaps.UniformBufferOffsetAlignment;
-        m_dynamicParameters.ShaderStorageBufferOffsetAlignment = m_vulkanCaps.ShaderStorageBufferOffsetAlignment;
         m_dynamicParameters.AliasedLineWidthRangeMin = m_vulkanCaps.AliasedLineWidthRangeMin;
         m_dynamicParameters.AliasedLineWidthRangeMax = m_vulkanCaps.AliasedLineWidthRangeMax;
         // Without the samplerAnisotropy feature the limit is unusable, so report 1.0 (no anisotropy)
         // rather than a maximum the sampler manager will never apply.
         m_dynamicParameters.MaxTextureMaxAnisotropy =
             (pVulkanRenderer && pVulkanRenderer->IsSamplerAnisotropySupported()) ? m_vulkanCaps.MaxSamplerAnisotropy
-                                                                                 : 1.0f;
+                                                                                : 1.0f;
         m_dynamicParameters.SmoothLineWidthRangeMin = m_vulkanCaps.SmoothLineWidthRangeMin;
         m_dynamicParameters.SmoothLineWidthRangeMax = m_vulkanCaps.SmoothLineWidthRangeMax;
         m_dynamicParameters.SmoothLineWidthGranularity = m_vulkanCaps.SmoothLineWidthGranularity;
@@ -913,7 +714,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_dynamicParameters.MaxIntegerSamples = m_vulkanCaps.MaxIntegerSamples;
         m_dynamicParameters.MaxSamples = m_vulkanCaps.MaxSamples;
         m_dynamicParameters.MaxSampleMaskWords = m_vulkanCaps.MaxSampleMaskWords;
-        const Int maxSupportedTextureUnits = static_cast<Int>(MG_State::GLState::TextureState::MAX_TEXTURE_IMAGE_UNITS);
+        const Int maxSupportedTextureUnits =
+            static_cast<Int>(MG_State::GLState::TextureState::MAX_TEXTURE_IMAGE_UNITS);
         // GL_MAX_TEXTURE_IMAGE_UNITS is a *per-stage* sampler limit. Adreno/Qualcomm report a huge
         // maxPerStageDescriptorSampledImages (descriptor-indexing scale), so clamping it only to our
         // combined array capacity (192) still advertises 192 per stage. Host code treats this value as
@@ -923,7 +725,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // limits while keeping the combined limit at our texture-unit array capacity.
         constexpr Int maxPerStageTextureUnits =
             static_cast<Int>(MG_State::GLState::TextureState::MAX_PER_STAGE_TEXTURE_IMAGE_UNITS);
-        m_dynamicParameters.MaxTextureImageUnits = std::min(m_vulkanCaps.MaxTextureImageUnits, maxPerStageTextureUnits);
+        m_dynamicParameters.MaxTextureImageUnits =
+            std::min(m_vulkanCaps.MaxTextureImageUnits, maxPerStageTextureUnits);
         m_dynamicParameters.MaxVertexTextureImageUnits =
             std::min(m_vulkanCaps.MaxVertexTextureImageUnits, maxPerStageTextureUnits);
         m_dynamicParameters.MaxComputeTextureImageUnits =
@@ -932,93 +735,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             std::min(m_vulkanCaps.MaxCombinedTextureImageUnits, maxSupportedTextureUnits);
         // Never advertise more attributes than the state layer can store: the current-value array and
         // the Uint32 attribute masks the draw path passes around are both bounded by MAX_VERTEX_ATTRIBS.
-        m_dynamicParameters.MaxVertexAttribs = std::min(
-            m_vulkanCaps.MaxVertexAttribs, static_cast<Int>(MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS));
-        // Vulkan descriptor limits are not GL limits, and a GL application reads an advertised
-        // limit as an amount it may actually USE. Adreno answers the per-stage/per-set descriptor
-        // queries at descriptor-indexing scale - the same driver whose
-        // GL_MAX_SHADER_STORAGE_BLOCK_SIZE is clamped from 2147483647 further down - so
-        // KHR-GL44.multi_bind.dispatch_bind_buffers_base read GL_MAX_COMPUTE_UNIFORM_BLOCKS,
-        // created that many buffers and spliced that many UBO declarations into a single compute
-        // shader: ~14 s of allocation, then death on std::bad_alloc. Its sibling
-        // dispatch_bind_buffers_range hard-codes 4 buffers and passes, which is the clean
-        // discriminator. Every ceiling below is far above what any desktop driver advertises for
-        // these (84-96 for the binding families) and far below a descriptor-indexing count, so it
-        // can only lower a limit that was never usable in the first place. The zero floor is not
-        // decoration: a driver reporting UINT32_MAX used to arrive here as -1.
-        const auto clampLimit = [](const char* name, Int reported, Int ceiling) {
-            const Int clamped = std::min(std::max(reported, 0), ceiling);
-            if (clamped != reported) {
-                MGLOG_I("DirectVulkan: clamped %s from %d to %d", name, reported, clamped);
-            }
-            return clamped;
-        };
-        // GL 4.6 required minimums, for the record: MAX_COMPUTE_UNIFORM_BLOCKS 12,
-        // MAX_COMPUTE/COMBINED_SHADER_STORAGE_BLOCKS 8, MAX_SHADER_STORAGE_BUFFER_BINDINGS 8,
-        // MAX_UNIFORM_BUFFER_BINDINGS 84, MAX_TEXTURE_BUFFER_SIZE 65536.
-        constexpr Int kMaxAdvertisedBufferBlocks = 256;
-        constexpr Int kMaxAdvertisedTextureBufferSize = 1 << 27; // texels; what desktop GL reports
-        m_dynamicParameters.MaxComputeShaderStorageBlocks =
-            clampLimit("GL_MAX_COMPUTE_SHADER_STORAGE_BLOCKS", m_vulkanCaps.MaxComputeShaderStorageBlocks,
-                       kMaxAdvertisedBufferBlocks);
-        m_dynamicParameters.MaxCombinedShaderStorageBlocks =
-            clampLimit("GL_MAX_COMBINED_SHADER_STORAGE_BLOCKS", m_vulkanCaps.MaxCombinedShaderStorageBlocks,
-                       kMaxAdvertisedBufferBlocks);
-        m_dynamicParameters.MaxComputeUniformBlocks =
-            clampLimit("GL_MAX_COMPUTE_UNIFORM_BLOCKS", m_vulkanCaps.MaxComputeUniformBlocks,
-                       kMaxAdvertisedBufferBlocks);
+        m_dynamicParameters.MaxVertexAttribs =
+            std::min(m_vulkanCaps.MaxVertexAttribs,
+                     static_cast<Int>(MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS));
+        m_dynamicParameters.MaxComputeShaderStorageBlocks = m_vulkanCaps.MaxComputeShaderStorageBlocks;
+        m_dynamicParameters.MaxCombinedShaderStorageBlocks = m_vulkanCaps.MaxCombinedShaderStorageBlocks;
+        m_dynamicParameters.MaxComputeUniformBlocks = m_vulkanCaps.MaxComputeUniformBlocks;
         m_dynamicParameters.MaxComputeWorkGroupInvocations = m_vulkanCaps.MaxComputeWorkGroupInvocations;
-        // The six per-axis compute limits, from the same VkPhysicalDeviceLimits fields
-        // GLFunctionsTable::GetIntegeri_v (DirectVulkan.cpp) reads live. Carried here so that
-        // MGPCaps has them once the table entry retires (plan B section 4.4.1); GL_Getter floors
-        // them. Not clamped: unlike the block counts these are not amounts an application
-        // allocates, and the frontend already raises them to the GL minimum.
-        for (SizeT axis = 0; axis < 3; ++axis) {
-            m_dynamicParameters.MaxComputeWorkGroupCount[axis] = m_vulkanCaps.MaxComputeWorkGroupCount[axis];
-            m_dynamicParameters.MaxComputeWorkGroupSize[axis] = m_vulkanCaps.MaxComputeWorkGroupSize[axis];
-        }
-        m_dynamicParameters.MaxShaderStorageBufferBindings =
-            clampLimit("GL_MAX_SHADER_STORAGE_BUFFER_BINDINGS", m_vulkanCaps.MaxShaderStorageBufferBindings,
-                       kMaxAdvertisedBufferBlocks);
-        // Per-stage GL_MAX_*_SHADER_STORAGE_BLOCKS. Vulkan has one descriptor limit for every
-        // stage (maxPerStageDescriptorStorageBuffers, which is what MaxComputeShaderStorageBlocks
-        // carries), so the stage limits differ only by whether the stage can have blocks at all.
-        //
-        // Deliberately NOT gated on vertexPipelineStoresAndAtomics, unlike the per-stage image
-        // uniforms below. That gate reads as the obvious one and is wrong here in practice: a
-        // Mali-G925-Immortalis reports vertexPipelineStoresAndAtomics=false (supported AND
-        // enabled) and yet runs all 433 KHR-GL43.constant_expressions.*_tess_* cases correctly
-        // through this backend - those write their result through a storage block declared in a
-        // tessellation stage. Gating would report 0 and turn 433 passing cases into
-        // "unsupported", removing function that demonstrably works.
-        //
-        // The asymmetry with DirectGLES is real and is the point. There, 0 prevents a program
-        // the driver refuses outright at link time; the honest limit converts a silent
-        // wrong-render into a capability an application can route around. Here there is no such
-        // failure to prevent, so the limit stays at what the device can address. If a Vulkan
-        // device is ever found that genuinely rejects such a pipeline, the gate belongs at
-        // pipeline creation where the rejection is observable, not on a feature bit this driver
-        // reports inaccurately.
-        {
-            const Int maxPerStageStorageBlocks =
-                std::min(std::max(m_dynamicParameters.MaxComputeShaderStorageBlocks, 0),
-                         std::min(std::max(m_dynamicParameters.MaxCombinedShaderStorageBlocks, 0),
-                                  std::max(m_dynamicParameters.MaxShaderStorageBufferBindings, 0)));
-            m_dynamicParameters.MaxVertexShaderStorageBlocks = maxPerStageStorageBlocks;
-            m_dynamicParameters.MaxTessControlShaderStorageBlocks = maxPerStageStorageBlocks;
-            m_dynamicParameters.MaxTessEvaluationShaderStorageBlocks = maxPerStageStorageBlocks;
-            // The one hard capability in the set: no geometry stage means no blocks in it.
-            m_dynamicParameters.MaxGeometryShaderStorageBlocks =
-                m_vulkanCaps.SupportsGeometryShader ? maxPerStageStorageBlocks : 0;
-            m_dynamicParameters.MaxFragmentShaderStorageBlocks = maxPerStageStorageBlocks;
-        }
-        m_dynamicParameters.MaxTextureBufferSize = clampLimit(
-            "GL_MAX_TEXTURE_BUFFER_SIZE", m_vulkanCaps.MaxTextureBufferSize, kMaxAdvertisedTextureBufferSize);
-        m_dynamicParameters.TextureBufferOffsetAlignment = m_vulkanCaps.TextureBufferOffsetAlignment;
-        m_dynamicParameters.MaxUniformBufferBindings = clampLimit(
-            "GL_MAX_UNIFORM_BUFFER_BINDINGS", m_vulkanCaps.MaxUniformBufferBindings, kMaxAdvertisedBufferBlocks);
+        m_dynamicParameters.MaxShaderStorageBufferBindings = m_vulkanCaps.MaxShaderStorageBufferBindings;
+        m_dynamicParameters.MaxTextureBufferSize = m_vulkanCaps.MaxTextureBufferSize;
+        m_dynamicParameters.MaxUniformBufferBindings = m_vulkanCaps.MaxUniformBufferBindings;
         m_dynamicParameters.MaxUniformBlockSize = m_vulkanCaps.MaxUniformBlockSize;
-        m_dynamicParameters.MaxImageUnits = std::max(std::min(m_vulkanCaps.MaxImageUnits, maxSupportedTextureUnits), 0);
+        m_dynamicParameters.MaxImageUnits =
+            std::max(std::min(m_vulkanCaps.MaxImageUnits, maxSupportedTextureUnits), 0);
         m_dynamicParameters.MaxCombinedImageUniforms = std::max(m_vulkanCaps.MaxCombinedImageUniforms, 0);
         const Int maxPerStageImageUniforms =
             std::min(m_dynamicParameters.MaxImageUnits, m_dynamicParameters.MaxCombinedImageUniforms);
@@ -1035,156 +764,25 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             m_vulkanCaps.SupportsFragmentStoresAndAtomics ? maxPerStageImageUniforms : 0;
         m_dynamicParameters.MaxComputeImageUniforms =
             std::min(std::max(m_vulkanCaps.MaxComputeImageUniforms, 0), maxPerStageImageUniforms);
-        const Int maxSupportedDrawBuffers = static_cast<Int>(MG_State::GLState::FramebufferObject::MAX_DRAW_BUFFERS);
+        const Int maxSupportedDrawBuffers =
+            static_cast<Int>(MG_State::GLState::FramebufferObject::MAX_DRAW_BUFFERS);
         m_dynamicParameters.MaxDrawBuffers = std::min(m_vulkanCaps.MaxDrawBuffers, maxSupportedDrawBuffers);
         m_dynamicParameters.MaxColorAttachments = std::min(m_vulkanCaps.MaxColorAttachments, maxSupportedDrawBuffers);
-        // Same shape as the image-uniform limits three lines above: maxClipDistances is reported
-        // by every device, but declaring ClipDistance in a module needs the shaderClipDistance
-        // FEATURE, which VulkanRenderer enables exactly where the physical device has it. Without
-        // it the limit describes a capacity no shader may use, so report none.
-        m_dynamicParameters.MaxClipDistances =
-            m_vulkanCaps.SupportsShaderClipDistance ? std::max(m_vulkanCaps.MaxClipDistances, 0) : 0;
-        // The cull pair, gated on its own feature. shaderCullDistance is separate from
-        // shaderClipDistance and VulkanRenderer enables it independently, so it gets its own
-        // gate rather than riding on the clip one.
-        m_dynamicParameters.MaxCullDistances =
-            m_vulkanCaps.SupportsShaderCullDistance ? std::max(m_vulkanCaps.MaxCullDistances, 0) : 0;
-        // GL 4.6 core 11.1.3.10: the combined limit is at least as large as either half. A device
-        // with only one of the two features must not report a combined capacity that implies the
-        // other, so the gate is "either feature" and the value never drops below what is enabled.
-        m_dynamicParameters.MaxCombinedClipAndCullDistances =
-            (m_vulkanCaps.SupportsShaderClipDistance || m_vulkanCaps.SupportsShaderCullDistance)
-                ? std::max({m_vulkanCaps.MaxCombinedClipAndCullDistances, m_dynamicParameters.MaxClipDistances,
-                            m_dynamicParameters.MaxCullDistances})
-                : 0;
+        m_dynamicParameters.MaxClipDistances = m_vulkanCaps.MaxClipDistances;
         m_dynamicParameters.MaxViewports = m_vulkanCaps.MaxViewports;
-        // Assigned explicitly rather than left to the struct's defaults, like every other
-        // parameter here, so a second fill cannot inherit a stale value. GL_UNDEFINED_VERTEX is
-        // the truthful answer for DirectVulkan and a legal one (GL 4.6 table 23.65): which vertex
-        // provokes is chosen per pipeline by VulkanRenderer::SelectProvokingVertexMode out of
-        // VK_EXT_provoking_vertex, provokingVertexModePerPipeline and the topology, so there is no
-        // one convention to name. Vulkan's own default is FIRST, which is the opposite of the
-        // GL_LAST_VERTEX_CONVENTION this used to claim unconditionally.
-        m_dynamicParameters.LayerProvokingVertex = GL_UNDEFINED_VERTEX;
-        m_dynamicParameters.ViewportIndexProvokingVertex = GL_UNDEFINED_VERTEX;
         m_dynamicParameters.MaxViewportWidth = m_vulkanCaps.MaxViewportWidth;
         m_dynamicParameters.MaxViewportHeight = m_vulkanCaps.MaxViewportHeight;
         m_dynamicParameters.ViewportBoundsRangeMin = m_vulkanCaps.ViewportBoundsRangeMin;
         m_dynamicParameters.ViewportBoundsRangeMax = m_vulkanCaps.ViewportBoundsRangeMax;
         m_dynamicParameters.ViewportSubpixelBits = m_vulkanCaps.ViewportSubpixelBits;
-        m_dynamicParameters.MinFragmentInterpolationOffset =
-            std::isfinite(m_vulkanCaps.MinFragmentInterpolationOffset) &&
-                    m_vulkanCaps.MinFragmentInterpolationOffset <= -0.5f
-                ? m_vulkanCaps.MinFragmentInterpolationOffset
-                : -0.5f;
-        m_dynamicParameters.MaxFragmentInterpolationOffset = 0.4375f;
-        m_dynamicParameters.FragmentInterpolationOffsetBits = 4;
-        if (m_vulkanCaps.FragmentInterpolationOffsetBits >= 4 &&
-            std::isfinite(m_vulkanCaps.MaxFragmentInterpolationOffset)) {
-            const Float requiredMaxOffset = 0.5f - std::ldexp(1.0f, -m_vulkanCaps.FragmentInterpolationOffsetBits);
-            if (m_vulkanCaps.MaxFragmentInterpolationOffset >= requiredMaxOffset) {
-                m_dynamicParameters.MaxFragmentInterpolationOffset = m_vulkanCaps.MaxFragmentInterpolationOffset;
-                m_dynamicParameters.FragmentInterpolationOffsetBits = m_vulkanCaps.FragmentInterpolationOffsetBits;
-            }
-        }
         m_dynamicParameters.SupportsWideLines = m_vulkanCaps.SupportsWideLines;
-        // A 2D or 2D multisample array texture is a VK_IMAGE_TYPE_2D image whose GL depth IS its
-        // arrayLayers, so a GL layer is a Vulkan array layer with nothing to translate.
-        // ResolveAttachmentBaseArrayLayer already passes the attachment's layer through. The other
-        // layered targets are declared separately as their own machinery lands.
-        {
-            using DynParams = MG_Backend::DynamicBackendParameters;
-            m_dynamicParameters.PerLayerFramebufferAttachmentTargets |=
-                DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture2DArray) |
-                DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture2DMultisampleArray);
-            // A cube map array is one 2D image with arrayLayers = 6 * cubeCount, so a GL layer is a
-            // Vulkan array layer here too - but the image cannot be created without imageCubeArray.
-            // A 3D texture's GL layer is a z slice, which only a 2D view over a 2D-array-compatible
-            // image can name. Optimistic: a format that refuses the flag is caught at image creation
-            // and declines the slice view there, which the clear path handles as a soft miss.
-            if (m_vulkanCaps.Supports2DArrayCompatible3DImages) {
-                m_dynamicParameters.PerLayerFramebufferAttachmentTargets |=
-                    DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::Texture3D);
-            }
-            if (m_vulkanCaps.SupportsImageCubeArray) {
-                m_dynamicParameters.PerLayerFramebufferAttachmentTargets |=
-                    DynParams::PerLayerFramebufferAttachmentBit(TextureTarget::TextureCubeMapArray);
-            }
-        }
-        // The device feature the whole fp64 story hangs off. With it, a module keeps its
-        // OpCapability Float64 and real doubles reach the driver; without it the transpile
-        // narrows every 64-bit float to 32 (ShaderTranspiler::DemoteFloat64Pass), because
-        // VUID-VkShaderModuleCreateInfo-pCode-08740 forbids the capability outright and no
-        // pipeline could be built from such a module. lavapipe reports it; Adreno and Mali both
-        // report VK_FALSE, so on every real mobile device this is false and the demotion runs
-        // exactly as it always has.
-        m_dynamicParameters.SupportsShaderFloat64 = m_vulkanCaps.SupportsShaderFloat64;
-        // shaderTessellationAndGeometryPointSize, both stage families from the one feature.
-        // False arms the shared phase-B point-size demotion, whose modules then carry no
-        // TessellationPointSize/GeometryPointSize capability and build without the feature.
-        // MOBILEGL_POINT_SIZE_DEMOTION=1 pretends it is absent so the demotion can be
-        // exercised on a healthy driver (lavapipe advertises the feature); =0 restores the
-        // detected answer's declines.
-        {
-            Bool supportsStagePointSize = m_vulkanCaps.SupportsTessellationAndGeometryPointSize;
-            switch (MG_Config::Features.PointSizeDemotion) {
-            case MG_Config::QuirkOverride::ForceOn:
-                MGLOG_I("DirectVulkan: MOBILEGL_POINT_SIZE_DEMOTION=1 - treating tessellation/geometry "
-                        "gl_PointSize as unhosted so the demotion runs on this driver");
-                supportsStagePointSize = false;
-                break;
-            case MG_Config::QuirkOverride::ForceOff:
-                MGLOG_I("DirectVulkan: MOBILEGL_POINT_SIZE_DEMOTION=0 - keeping the built-in and the "
-                        "plain declines regardless of the device feature");
-                supportsStagePointSize = true;
-                break;
-            case MG_Config::QuirkOverride::Auto:
-                break;
-            }
-            m_dynamicParameters.SupportsTessellationPointSize = supportsStagePointSize;
-            m_dynamicParameters.SupportsGeometryPointSize = supportsStagePointSize;
-        }
-        // Never, on any device, and DELIBERATELY NOT COUPLED to the line above even though it
-        // once tracked the same feature. It used to, because a `dvec` input needed Float64 to
-        // exist in the module at all; a 64-bit vertex FETCH was already impossible
-        // (VK_FORMAT_R64*_SFLOAT is optional and lavapipe reports zero bufferFeatures for all
-        // four), so the attribute arrived as its 32-bit word pair and PackDoubleVertexInputsPass
-        // bitcast it back.
-        //
-        // Re-coupling it does not work, and the reason is worth recording because it is not
-        // obvious: this flag decides the VkFormat from the VAO ATTRIBUTE alone, and the attribute
-        // does not know what the shader declared. glVertexAttribFormat(GL_DOUBLE) against a plain
-        // `in vec4` is not only legal but the common case
-        // (KHR-GL43.vertex_attrib_binding.basic-input-case4 does exactly that, and case5 adds
-        // normalized=GL_TRUE), and advanced-bindingUpdate feeds a dvec3 the same way - GL defines
-        // all of them as "doubles in memory, converted to float". Turning the flag on turns the
-        // narrowing OFF for every one of them and the attributes come back unfetched.
-        //
-        // What keeps the two halves honest instead is a per-MODULE decision: a vertex module that
-        // declares a 64-bit float INPUT is demoted whole, even where the backend has native fp64,
-        // so `dvec` inputs are `vec` inputs on this backend exactly as they always were. See
-        // ShaderCompiler::SanitizeAndOptimizeBinary.
-        m_dynamicParameters.SupportsFloat64VertexAttributes = false;
         m_dynamicParameters.MaxShaderStorageBlockSize =
             std::min(m_vulkanCaps.MaxShaderStorageBlockSize, kMaxAdvertisedShaderStorageBlockSize);
         if (m_vulkanCaps.SupportsShaderSubgroup) {
             m_dynamicParameters.SubgroupSize = m_vulkanCaps.SubgroupSize;
             m_dynamicParameters.SubgroupSupportedStages = mapShaderStages(m_vulkanCaps.SubgroupSupportedStages);
-            m_dynamicParameters.SubgroupSupportedFeatures =
-                mapSubgroupFeatures(m_vulkanCaps.SubgroupSupportedOperations);
+            m_dynamicParameters.SubgroupSupportedFeatures = mapSubgroupFeatures(m_vulkanCaps.SubgroupSupportedOperations);
             m_dynamicParameters.SubgroupQuadOperationsInAllStages = m_vulkanCaps.SubgroupQuadOperationsInAllStages;
-        } else if (ShouldEmulateSubgroups(m_vulkanCaps.SupportsShaderSubgroup)) {
-            // MOBILEGL_MAGMA_EMULATE_SUBGROUP on a device with no native subgroups: the
-            // advertised values describe the 32-lane virtual subgroup the compute
-            // lowering implements (SubgroupSupportPolicy.h / EmulateSubgroupsPass).
-            // GL requires the advertisement and the execution to agree, and on this
-            // path the emulation is what executes; only the compute stage is offered.
-            m_dynamicParameters.SubgroupSize = kEmulatedSubgroupSize;
-            m_dynamicParameters.SubgroupSupportedStages = kEmulatedSubgroupStages;
-            m_dynamicParameters.SubgroupSupportedFeatures = kEmulatedSubgroupFeatures;
-            m_dynamicParameters.SubgroupQuadOperationsInAllStages = false;
-            MGLOG_I("DirectVulkan: emulating 32-lane compute subgroups "
-                    "(MOBILEGL_MAGMA_EMULATE_SUBGROUP, no native subgroup support)");
         } else {
             m_dynamicParameters.SubgroupSize = 0;
             m_dynamicParameters.SubgroupSupportedStages = 0;
@@ -1193,34 +791,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
         if (m_dynamicParameters.MaxShaderStorageBlockSize != m_vulkanCaps.MaxShaderStorageBlockSize) {
             MGLOG_I("DirectVulkan: clamped GL_MAX_SHADER_STORAGE_BLOCK_SIZE from %zu to %zu",
-                    m_vulkanCaps.MaxShaderStorageBlockSize, m_dynamicParameters.MaxShaderStorageBlockSize);
-        }
-        switch (m_vulkanCaps.VendorId) {
-        case 0x5143u: // VK_VENDOR_ID: Qualcomm
-            m_dynamicParameters.GpuVendor = GpuVendorKind::Qualcomm;
-            break;
-        case 0x13B5u: // ARM
-            m_dynamicParameters.GpuVendor = GpuVendorKind::Arm;
-            break;
-        case 0x10DEu: // NVIDIA
-            m_dynamicParameters.GpuVendor = GpuVendorKind::Nvidia;
-            break;
-        case 0x1002u: // AMD
-            m_dynamicParameters.GpuVendor = GpuVendorKind::Amd;
-            break;
-        case 0x8086u: // Intel
-            m_dynamicParameters.GpuVendor = GpuVendorKind::Intel;
-            break;
-        case 0x1010u: // Imagination
-            m_dynamicParameters.GpuVendor = GpuVendorKind::ImgTec;
-            break;
-        case 0x10005u: // Mesa software (lavapipe)
-        case 0x1AE0u:  // Google (SwiftShader)
-            m_dynamicParameters.GpuVendor = GpuVendorKind::Software;
-            break;
-        default:
-            m_dynamicParameters.GpuVendor = GpuVendorKind::Unknown;
-            break;
+                    m_vulkanCaps.MaxShaderStorageBlockSize,
+                    m_dynamicParameters.MaxShaderStorageBlockSize);
         }
     }
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/BackendObject_DirectVulkan.h

@@ -62,21 +62,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     // POST screen shows.
 
     // Static identity of the Magma renderer (renderer/backend names, target GL/GLSL
-    // versions, ExtraVendor) with the baseline extension advertisement (no runtime-gated
-    // capabilities). A live backend copies this in its constructor and
+    // versions, ExtraVendor) with the baseline extension advertisement (no shader
+    // subgroup, no timer queries). A live backend copies this in its constructor and
     // reconciles the Extensions in UpdateAdvertisedExtensions once real capabilities
     // exist; callers that need the advertised list for a known capability set must
     // use BuildAdvertisedExtensions instead.
     const RendererInfo& GetRendererIdentity();
 
     // The full OpenGL extension list Magma advertises (glGetString(GL_EXTENSIONS)) for
-    // a device with the given raw capabilities. The MOBILEGL_MAGMA_DISABLE_SUBGROUP and
+    // a device with the given raw capabilities. The MOBILEGL_DISABLE_SUBGROUP and
     // MOBILEGL_DISABLE_TIMERQUERY escape hatches are applied inside, so callers pass
     // the detected device support (passing an already-gated value is harmless).
     Vector<GLExtension> BuildAdvertisedExtensions(Bool shaderSubgroupSupported, Bool timerQueriesSupported,
-                                                  Bool anisotropicFilteringSupported,
-                                                  Bool nonZeroIndirectBaseInstanceSupported,
-                                                  Bool cubeMapArraySupported);
+                                                  Bool anisotropicFilteringSupported);
 
     // Format: <GPU Name>, Vulkan <Vulkan Version>, Driver <Driver Version> — the exact
     // string an initialized backend returns from GetBackendAPIVersionString (and that

MobileGL/MG_Backend/DirectVulkan/DirectVulkan.h

@@ -12,7 +12,7 @@
 #include "Renderer/VulkanRenderer.h"
 
 namespace MobileGL::MG_Backend::DirectVulkan {
-    extern UniquePtr<VulkanRenderer>& pVulkanRenderer;
+    extern UniquePtr<VulkanRenderer> pVulkanRenderer;
 
     // Generation of the live VulkanRenderer instance, mirroring DirectGLES's
     // g_syncContextGeneration. BackendObject_DirectVulkan bumps it wherever
@@ -23,34 +23,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     Uint64 GetRendererGeneration();
     void BumpRendererGeneration();
 
-#if MOBILEGL_BUILD_DISAGGREGATED && MOBILEGL_PIPE_PUSH
-    // P7 wave 2 package C (CONTRACT-P7 §5.5). Magma's StateObjectDeathOps table, installed
-    // from BackendObject_DirectVulkan::Initialize() so that GetStateObjectDeathOps() is
-    // non-null on every Magma role that owns a backend. See the definition for what the one
-    // arm does and for the inproc gap it closes. Push-only and disaggregated-only: a pull
-    // build declares no notice at all (StateObjectDeathNotice.h) and has nothing to emit.
-    void InstallStateObjectDeathOps();
-    // True when the notice currently installed is this backend's. Read by MG_Test so the
-    // install can be asserted without a death having to happen first.
-    Bool StateObjectDeathOpsInstalled();
-#endif
-
-    // Drops every cached program-resource reflection entry (CPU-side strings/vectors
-    // only, no Vulkan handles). Called at EGL teardown next to the renderer reset;
-    // safe because GL calls are serialized in this codebase, and any still-live
-    // program rebuilds its entry from the retained generated SPIR-V on demand.
-    void ClearProgramResourceCaches();
-
     void ClearBufferfi(GLenum buffer, GLint drawbuffer, GLfloat depth, GLint stencil);
     void ClearBufferfv(GLenum buffer, GLint drawbuffer, const GLfloat* value);
     void ClearBufferuiv(GLenum buffer, GLint drawbuffer, const GLuint* value);
     void ClearBufferiv(GLenum buffer, GLint drawbuffer, const GLint* value);
     void ClearNamedFramebufferfv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
                                  GLint drawbuffer, const GLfloat* value);
-    void ClearNamedFramebufferiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
-                                 GLint drawbuffer, const GLint* value);
-    void ClearNamedFramebufferuiv(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
-                                  GLint drawbuffer, const GLuint* value);
     void ClearNamedFramebufferfi(const SharedPtr<MG_State::GLState::FramebufferObject>& framebuffer, GLenum buffer,
                                  GLint drawbuffer, GLfloat depth, GLint stencil);
     void Clear(GLbitfield mask);
@@ -94,9 +72,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                         GLsizei height, GLint border);
     void CopyTexSubImage2D(GLenum target, GLint level, GLint xoffset, GLint yoffset, GLint x, GLint y, GLsizei width,
                            GLsizei height);
-    void CopyImageSubData(const CopyImageEndpoint& src,
+    void CopyImageSubData(const SharedPtr<MG_State::GLState::ITextureObject>& srcTexture,
                           GLenum srcTarget, GLint srcLevel, GLint srcX, GLint srcY, GLint srcZ,
-                          const CopyImageEndpoint& dst,
+                          const SharedPtr<MG_State::GLState::ITextureObject>& dstTexture,
                           GLenum dstTarget, GLint dstLevel, GLint dstX, GLint dstY, GLint dstZ,
                           GLsizei srcWidth, GLsizei srcHeight, GLsizei srcDepth);
     void GenerateMipmap(GLenum target);
@@ -107,7 +85,17 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     void BindImageTexture(GLuint unit, GLuint texture, GLint level, GLboolean layered, GLint layer, GLenum access,
                           GLenum format);
     void GetIntegeri_v(GLenum target, GLuint index, GLint* data);
-    void ShaderStorageBlockBinding(GLuint program, const GLchar* storageBlockName, GLuint storageBlockBinding);
+    void GetInteger64i_v(GLenum target, GLuint index, GLint64* data);
+    void GetProgramiv(GLuint program, GLenum pname, GLint* params);
+    void GetProgramInterfaceiv(GLuint program, GLenum programInterface, GLenum pname, GLint* params);
+    GLuint GetProgramResourceIndex(GLuint program, GLenum programInterface, const GLchar* name);
+    void GetProgramResourceName(GLuint program, GLenum programInterface, GLuint index, GLsizei bufSize,
+                                GLsizei* length, GLchar* name);
+    void GetProgramResourceiv(GLuint program, GLenum programInterface, GLuint index, GLsizei propCount,
+                              const GLenum* props, GLsizei bufSize, GLsizei* length, GLint* params);
+    GLint GetProgramResourceLocation(GLuint program, GLenum programInterface, const GLchar* name);
+    GLint GetProgramResourceLocationIndex(GLuint program, GLenum programInterface, const GLchar* name);
+    void ShaderStorageBlockBinding(GLuint program, GLuint storageBlockIndex, GLuint storageBlockBinding);
     void ReadPixels(GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, void* pixels);
     void GetTexImage(GLenum target, GLint level, GLenum format, GLenum type, GLvoid* pixels);
     void GetTextureImage(const SharedPtr<MG_State::GLState::ITextureObject>& texture, TextureUploadTarget uploadTarget,
@@ -129,10 +117,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     // only while a live renderer exists whose device can actually time.
     Bool IsTimerQuerySupported();
     BackendQueryHandle BeginTimeElapsedQuery();
-    BackendQueryHandle BeginXfbPrimitivesQuery(Bool generated);
-    void EndXfbPrimitivesQuery(BackendQueryHandle query);
-    BackendQueryHandle BeginOcclusionQuery();
-    void EndOcclusionQuery(BackendQueryHandle query);
     void EndTimeElapsedQuery(BackendQueryHandle query);
     BackendQueryHandle QueryCounterTimestamp();
     Bool IsQueryResultAvailable(BackendQueryHandle query);

MobileGL/MG_Backend/DirectVulkan/Renderer/BufferArena.cpp

@@ -7,9 +7,6 @@
 // End of Source File Header
 
 #include "BufferArena.h"
-#if MOBILEGL_BUILD_DISAGGREGATED
-#include <Config.h>
-#endif
 
 namespace MobileGL::MG_Backend::DirectVulkan {
     Bool BufferArena::Initialize(const BufferArenaDesc& desc) {
@@ -114,11 +111,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
 
         if (buffer.IsValid()) {
-            // Outgrown, not dead: every BufferSlice handed out from this frame's arena so far
-            // still names it, and those slices stay in service until the frame slot is rewound
-            // (VkBufferResource::transientSlice, the converted-vertex-stream cache, the draw
-            // memos). The release therefore has to survive every mid-frame reclaim and land on
-            // the next ResetFrame of this slot - see VkBufferManager::CollectAllDeferredReleases.
             m_deferredReleases[frameIndex].push_back(std::move(buffer));
         }
 
@@ -128,14 +120,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         bufferDesc.usage = m_desc.usage;
         bufferDesc.memoryUsage = m_desc.memoryUsage;
         bufferDesc.allocationFlags = m_desc.allocationFlags;
-#if MOBILEGL_BUILD_DISAGGREGATED
-        // Split staging may also be the destination of a GPU UBO range copy.
-        // Persistent host writes must be coherent: Upload deliberately writes
-        // the mapped pointer without a per-range VMA flush.
-        if (MG_Config::Transport != MG_Config::TransportMode::Monolith && m_desc.persistentlyMapped) {
-            bufferDesc.requiredFlags = VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT | VK_MEMORY_PROPERTY_HOST_COHERENT_BIT;
-        }
-#endif
         if (!buffer.Create(bufferDesc)) {
             return false;
         }

MobileGL/MG_Backend/DirectVulkan/Renderer/FrameContext.cpp

@@ -7,9 +7,6 @@
 // End of Source File Header
 
 #include "FrameContext.h"
-#if MOBILEGL_BUILD_DISAGGREGATED
-#include <Config.h>
-#endif
 
 namespace MobileGL::MG_Backend::DirectVulkan {
     VkResult FrameContext::Initialize(VkDevice device, VkCommandPool commandPool, Uint32 frameCount) {
@@ -19,19 +16,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_device = device;
         m_commandPool = commandPool;
 
-        Vector<VkCommandBuffer> commandBuffers(frameCount * 2, VK_NULL_HANDLE);
+        Vector<VkCommandBuffer> commandBuffers(frameCount, VK_NULL_HANDLE);
         VkCommandBufferAllocateInfo allocInfo{};
         allocInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
         allocInfo.commandPool = commandPool;
         allocInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
-        allocInfo.commandBufferCount = frameCount * 2;
+        allocInfo.commandBufferCount = frameCount;
         VkResult result = vkAllocateCommandBuffers(device, &allocInfo, commandBuffers.data());
         if (result != VK_SUCCESS) {
             return result;
         }
         for (Uint32 i = 0; i < frameCount; ++i) {
             m_frames[i].commandBuffer = commandBuffers[i];
-            m_frames[i].preCommandBuffer = commandBuffers[frameCount + i];
         }
 
         VkSemaphoreCreateInfo semaphoreInfo{VK_STRUCTURE_TYPE_SEMAPHORE_CREATE_INFO};
@@ -51,10 +47,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
     void FrameContext::Destroy(VkDevice device, VkCommandPool commandPool) {
         const Uint32 frameCount = static_cast<Uint32>(m_frames.size());
-        Vector<VkCommandBuffer> commandBuffers(frameCount * 2, VK_NULL_HANDLE);
+        Vector<VkCommandBuffer> commandBuffers(frameCount, VK_NULL_HANDLE);
         for (Uint32 i = 0; i < frameCount; ++i) {
             commandBuffers[i] = m_frames[i].commandBuffer;
-            commandBuffers[frameCount + i] = m_frames[i].preCommandBuffer;
         }
 
         for (Uint32 i = 0; i < frameCount; ++i) {
@@ -65,7 +60,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             for (auto& frame : m_frames) {
                 FreeRetiredCommandBuffers(frame);
             }
-            vkFreeCommandBuffers(device, commandPool, frameCount * 2, commandBuffers.data());
+            vkFreeCommandBuffers(device, commandPool, frameCount, commandBuffers.data());
         }
         m_frames.clear();
         currentFrameIndex = 0;
@@ -92,8 +87,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         currentFrameIndex = (currentFrameIndex + 1) % static_cast<Uint32>(m_frames.size());
         GetCurrent().isCommandRecording = false;
         GetCurrent().hasCommandBufferRecorded = false;
-        GetCurrent().isPreCommandRecording = false;
-        GetCurrent().hasPreCommandBufferRecorded = false;
     }
 
     VkCommandBuffer& FrameContext::BeginCommandRecording(VkCommandBufferUsageFlags flags,
@@ -125,41 +118,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         frame.hasCommandBufferRecorded = true;
     }
 
-    VkCommandBuffer FrameContext::BeginPreCommandRecording() {
-        auto& frame = GetCurrent();
-        if (frame.isPreCommandRecording) {
-            return frame.preCommandBuffer;
-        }
-        MOBILEGL_ASSERT(!frame.hasPreCommandBufferRecorded,
-                        "BeginPreCommandRecording: a recorded pre stream is still awaiting submission");
-        VK_VERIFY(vkResetCommandBuffer(frame.preCommandBuffer, 0), "BeginPreCommandRecording, vkResetCommandBuffer");
-        VkCommandBufferBeginInfo beginInfo{};
-        beginInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO;
-        VK_VERIFY(vkBeginCommandBuffer(frame.preCommandBuffer, &beginInfo),
-                  "BeginPreCommandRecording, vkBeginCommandBuffer");
-        frame.isPreCommandRecording = true;
-        return frame.preCommandBuffer;
-    }
-
-    void FrameContext::EndPreCommandRecordingIfOpen() {
-        auto& frame = GetCurrent();
-        if (!frame.isPreCommandRecording) {
-            return;
-        }
-        VK_VERIFY(vkEndCommandBuffer(frame.preCommandBuffer), "EndPreCommandRecordingIfOpen, vkEndCommandBuffer");
-        frame.isPreCommandRecording = false;
-        frame.hasPreCommandBufferRecorded = true;
-    }
-
-    void FrameContext::AbandonPreCommandRecording() {
-        auto& frame = GetCurrent();
-        if (frame.isPreCommandRecording) {
-            VK_VERIFY(vkEndCommandBuffer(frame.preCommandBuffer), "AbandonPreCommandRecording, vkEndCommandBuffer");
-        }
-        frame.isPreCommandRecording = false;
-        frame.hasPreCommandBufferRecorded = false;
-    }
-
     VkResult FrameContext::InitializeSwapchainSemaphores(VkDevice device, Uint32 swapchainImageCount) {
         DestroySwapchainSemaphores(device);
         if (swapchainImageCount == 0) {
@@ -192,41 +150,16 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
     Bool FrameContext::TransitionToPresent(VkImage image, VkImageLayout oldLayout, VkImageLayout presentLayout) {
         auto& frame = GetCurrent();
-        if (oldLayout == presentLayout || oldLayout == VK_IMAGE_LAYOUT_SHARED_PRESENT_KHR) {
+        if (frame.hasCommandBufferRecorded || frame.isCommandRecording || oldLayout == presentLayout ||
+            oldLayout == VK_IMAGE_LAYOUT_SHARED_PRESENT_KHR) {
             return false;
         }
 
-        // The barrier belongs in the frame's own recording. Bailing out because
-        // something was already recorded (the previous behaviour) dropped the
-        // transition entirely for every frame that never ran a default-framebuffer
-        // render pass - the only other thing that carries the image to
-        // PRESENT_SRC_KHR, via that pass's finalLayout - so the swapchain image was
-        // handed to the WSI still in the layout it was acquired in.
-        // A closed-but-unsubmitted buffer can only come from a submit that already
-        // failed (SubmitPendingCommandBuffer leaves the flag set on error), and
-        // appending to it is illegal while reopening would reset the frame's own
-        // commands away. The device is gone on that path anyway - stay silent-safe
-        // rather than trade a lost device for a barrier into a closed buffer.
-        if (frame.hasCommandBufferRecorded) {
-            MGLOG_E_ONCE("TransitionToPresent: command buffer already closed; skipping the present barrier");
-            return false;
-        }
-
-        // Reopening a recording here would vkResetCommandBuffer this frame's own
-        // commands away, so append to the open one and let the caller close it.
-        const Bool openedRecording = !frame.isCommandRecording;
-        VkCommandBuffer commandBuffer = openedRecording ? BeginCommandRecording() : frame.commandBuffer;
+        auto& commandBuffer = BeginCommandRecording();
 
         VkImageMemoryBarrier presentBarrier{};
         presentBarrier.sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER;
         presentBarrier.srcAccessMask = 0;
-#if MOBILEGL_BUILD_DISAGGREGATED
-        // A layout transition writes the image too. Order it after the wire
-        // render pass's storeOp, clears and copies instead of relying on the old
-        // per-draw queue-idle path. This applies even when contents are discarded.
-        if (MG_Config::Transport != MG_Config::TransportMode::Monolith)
-            presentBarrier.srcAccessMask = VK_ACCESS_MEMORY_WRITE_BIT;
-#endif
         presentBarrier.dstAccessMask = 0;
         presentBarrier.oldLayout = oldLayout;
         presentBarrier.newLayout = presentLayout;
@@ -238,19 +171,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         presentBarrier.subresourceRange.levelCount = 1;
         presentBarrier.subresourceRange.baseArrayLayer = 0;
         presentBarrier.subresourceRange.layerCount = 1;
-        vkCmdPipelineBarrier(commandBuffer,
-#if MOBILEGL_BUILD_DISAGGREGATED
-                             MG_Config::Transport != MG_Config::TransportMode::Monolith
-                                 ? VK_PIPELINE_STAGE_ALL_COMMANDS_BIT : VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT,
-#else
-                             VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT,
-#endif
-                             VK_PIPELINE_STAGE_BOTTOM_OF_PIPE_BIT, 0, 0,
+        vkCmdPipelineBarrier(commandBuffer, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT, VK_PIPELINE_STAGE_BOTTOM_OF_PIPE_BIT, 0, 0,
                              nullptr, 0, nullptr, 1, &presentBarrier);
 
-        if (openedRecording) {
-            EndCommandRecording();
-        }
+        EndCommandRecording();
         return true;
     }
 
@@ -258,27 +182,17 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                                                                Uint32 swapchainImageIndex) const {
         const auto& frame = GetCurrent();
         MOBILEGL_ASSERT(!frame.isCommandRecording, "GetSubmitInfo called while command buffer recording is still active");
-        MOBILEGL_ASSERT(!frame.isPreCommandRecording,
-                        "GetSubmitInfo called while the pre-pass stream is still recording");
         AssertValidSwapchainImageIndex(swapchainImageIndex);
         SubmitInfoPacket packet{};
         packet.waitSemaphore = frame.imageAvailableSemaphore;
         packet.signalSemaphore = m_swapchainImageRenderFinishedSemaphores[swapchainImageIndex];
-
-        Uint32 commandBufferCount = 0;
-        // The pre-pass stream executes strictly before the frame's commands.
-        if (frame.hasPreCommandBufferRecorded) {
-            packet.commandBuffers[commandBufferCount++] = frame.preCommandBuffer;
-        }
-        if (shouldSubmitCommandBuffer) {
-            packet.commandBuffers[commandBufferCount++] = frame.commandBuffer;
-        }
+        packet.commandBuffer = frame.commandBuffer;
 
         packet.submitInfo.waitSemaphoreCount = frame.imageAvailableSemaphoreConsumed ? 0U : 1U;
         packet.submitInfo.pWaitSemaphores = frame.imageAvailableSemaphoreConsumed ? nullptr : &packet.waitSemaphore;
         packet.submitInfo.pWaitDstStageMask = frame.imageAvailableSemaphoreConsumed ? nullptr : &packet.waitDstStageMask;
-        packet.submitInfo.commandBufferCount = commandBufferCount;
-        packet.submitInfo.pCommandBuffers = commandBufferCount > 0 ? packet.commandBuffers : nullptr;
+        packet.submitInfo.commandBufferCount = shouldSubmitCommandBuffer ? 1U : 0U;
+        packet.submitInfo.pCommandBuffers = shouldSubmitCommandBuffer ? &packet.commandBuffer : nullptr;
         packet.submitInfo.signalSemaphoreCount = 1;
         packet.submitInfo.pSignalSemaphores = &packet.signalSemaphore;
         return packet;
@@ -307,29 +221,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         if (result != VK_SUCCESS) {
             return result;
         }
-        // Under disaggregation VulkanRenderer waits every registered fence
-        // through this slot's last submit before calling here. That aggregate
-        // proof covers mid-frame pooled-fence flushes too; the slot fence alone
-        // would not. Initialize's first acquire has no prior submissions.
+        // The slot's fence has been waited: every command buffer this slot
+        // submitted (including mid-frame flushes) has finished executing.
         FreeRetiredCommandBuffers(frame);
 
         result = vkAcquireNextImageKHR(device, swapchain, timeout, frame.imageAvailableSemaphore, acquireFence,
                                        &outImageIndex);
-        // VK_SUBOPTIMAL_KHR is a success code: an image *was* acquired and
-        // imageAvailableSemaphore *will* be signaled. Bailing out on it skipped both
-        // the consumed-flag reset (leaving a stale "already consumed", so the next
-        // submit never waited on the pending signal) and the fence reset (leaving
-        // the slot's fence signaled for the next submit to reuse). Only a genuine
-        // failure - VK_ERROR_OUT_OF_DATE_KHR and friends, where nothing is acquired
-        // and nothing is signaled - skips the bookkeeping.
-        if (result != VK_SUCCESS && result != VK_SUBOPTIMAL_KHR) {
+        if (result != VK_SUCCESS) {
             return result;
         }
 
         frame.imageAvailableSemaphoreConsumed = false;
-        const VkResult resetResult = vkResetFences(device, 1, &frame.imageInFlightFence);
-        // Hand the acquire's own code back so the caller can schedule a rebuild.
-        return resetResult == VK_SUCCESS ? result : resetResult;
+        return vkResetFences(device, 1, &frame.imageInFlightFence);
     }
 
     Uint32 FrameContext::GetCurrentFrameIndex() const {
@@ -344,14 +247,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_recordingObserver = observer;
     }
 
-    VkResult FrameContext::RetireCurrentCommandBuffer(Bool retirePreCommandBuffer) {
+    VkResult FrameContext::RetireCurrentCommandBuffer() {
         MOBILEGL_ASSERT(m_device != VK_NULL_HANDLE && m_commandPool != VK_NULL_HANDLE,
                         "RetireCurrentCommandBuffer requires an initialized FrameContext");
         auto& frame = GetCurrent();
         MOBILEGL_ASSERT(!frame.isCommandRecording,
                         "RetireCurrentCommandBuffer called while the command buffer is still recording");
-        MOBILEGL_ASSERT(!frame.isPreCommandRecording,
-                        "RetireCurrentCommandBuffer called while the pre-pass stream is still recording");
 
         VkCommandBufferAllocateInfo allocInfo{};
         allocInfo.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO;
@@ -359,23 +260,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         allocInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
         allocInfo.commandBufferCount = 1;
         VkCommandBuffer replacement = VK_NULL_HANDLE;
-        VkResult result = vkAllocateCommandBuffers(m_device, &allocInfo, &replacement);
+        const VkResult result = vkAllocateCommandBuffers(m_device, &allocInfo, &replacement);
         if (result != VK_SUCCESS) {
             return result;
         }
-        if (retirePreCommandBuffer) {
-            VkCommandBuffer preReplacement = VK_NULL_HANDLE;
-            result = vkAllocateCommandBuffers(m_device, &allocInfo, &preReplacement);
-            if (result != VK_SUCCESS) {
-                vkFreeCommandBuffers(m_device, m_commandPool, 1, &replacement);
-                return result;
-            }
-            frame.retiredCommandBuffers.push_back({frame.preCommandBuffer, frame.lastSubmitIndex});
-            frame.preCommandBuffer = preReplacement;
-        }
-        // lastSubmitIndex was just written by the renderer for the submission
-        // that carried this command buffer.
-        frame.retiredCommandBuffers.push_back({frame.commandBuffer, frame.lastSubmitIndex});
+        frame.retiredCommandBuffers.push_back(frame.commandBuffer);
         frame.commandBuffer = replacement;
         return VK_SUCCESS;
     }
@@ -385,40 +274,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return;
         }
         if (m_device != VK_NULL_HANDLE && m_commandPool != VK_NULL_HANDLE) {
-            for (const auto& retired : frame.retiredCommandBuffers) {
-                vkFreeCommandBuffers(m_device, m_commandPool, 1, &retired.commandBuffer);
-            }
+            vkFreeCommandBuffers(m_device, m_commandPool, static_cast<Uint32>(frame.retiredCommandBuffers.size()),
+                                 frame.retiredCommandBuffers.data());
         }
         frame.retiredCommandBuffers.clear();
     }
 
-    void FrameContext::FreeRetiredCommandBuffersCompletedUpTo(Uint64 completedSubmitIndex) {
-        if (m_device == VK_NULL_HANDLE || m_commandPool == VK_NULL_HANDLE) {
-            return;
-        }
-        for (auto& frame : m_frames) {
-            // Retired buffers are appended in submit order, so the completed
-            // ones form a prefix.
-            SizeT completedCount = 0;
-            while (completedCount < frame.retiredCommandBuffers.size() &&
-                   frame.retiredCommandBuffers[completedCount].submitIndex <= completedSubmitIndex) {
-                vkFreeCommandBuffers(m_device, m_commandPool, 1,
-                                     &frame.retiredCommandBuffers[completedCount].commandBuffer);
-                ++completedCount;
-            }
-            if (completedCount > 0) {
-                frame.retiredCommandBuffers.erase(frame.retiredCommandBuffers.begin(),
-                                                  frame.retiredCommandBuffers.begin() + completedCount);
-            }
-        }
-    }
-
-    void FrameContext::FreeAllRetiredCommandBuffers() {
-        for (auto& frame : m_frames) {
-            FreeRetiredCommandBuffers(frame);
-        }
-    }
-
     void FrameContext::AssertValidFrameIndex(Uint32 frameIndex) const {
         MOBILEGL_ASSERT(frameIndex < m_frames.size(), "FrameContext index out of range");
     }

MobileGL/MG_Backend/DirectVulkan/Renderer/FrameContext.h

@@ -29,9 +29,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             VkPipelineStageFlags waitDstStageMask = VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT;
             VkSemaphore waitSemaphore = VK_NULL_HANDLE;
             VkSemaphore signalSemaphore = VK_NULL_HANDLE;
-            // [0] = pre-pass command buffer (when recorded), then the frame
-            // command buffer; submitInfo.pCommandBuffers points here.
-            VkCommandBuffer commandBuffers[2] = {VK_NULL_HANDLE, VK_NULL_HANDLE};
+            VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
             VkSubmitInfo submitInfo{VK_STRUCTURE_TYPE_SUBMIT_INFO};
         };
 
@@ -42,35 +40,17 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             VkPresentInfoKHR presentInfo{VK_STRUCTURE_TYPE_PRESENT_INFO_KHR};
         };
 
-        // A command buffer submitted mid-frame (FlushPendingCommands), tagged
-        // with the submit-tracker index it was submitted under so it can be
-        // freed as soon as that submission is observed complete - without
-        // waiting for the slot's fence to be waited again (present-less flush
-        // loops never wait it).
-        struct RetiredCommandBuffer {
-            VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
-            Uint64 submitIndex = 0;
-        };
-
         struct FrameData {
             VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
-            // Pre-pass work stream: out-of-pass commands (deferred clear
-            // materialization, sampled-layout transitions) for resources the
-            // frame's recording has not touched yet. Submitted immediately
-            // BEFORE commandBuffer in the same vkQueueSubmit, so recording
-            // into it never has to split the frame's active render pass.
-            VkCommandBuffer preCommandBuffer = VK_NULL_HANDLE;
             VkSemaphore imageAvailableSemaphore = VK_NULL_HANDLE;
             VkFence imageInFlightFence = VK_NULL_HANDLE;
             Bool isCommandRecording = false;
             Bool hasCommandBufferRecorded = false;
-            Bool isPreCommandRecording = false;
-            Bool hasPreCommandBufferRecorded = false;
             Bool imageAvailableSemaphoreConsumed = false;
-            // Command buffers submitted mid-frame (FlushPendingCommands),
-            // appended in submit order; freed once their submission is known
-            // complete (fence wait or completion poll).
-            Vector<RetiredCommandBuffer> retiredCommandBuffers;
+            // Command buffers submitted mid-frame (FlushPendingCommands) whose
+            // execution is only known complete once this slot's fence has been
+            // waited again; freed at that point.
+            Vector<VkCommandBuffer> retiredCommandBuffers;
             // Submit-tracker index of this slot's most recent queue submission
             // (written by the renderer at submit time).
             Uint64 lastSubmitIndex = 0;
@@ -87,14 +67,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkCommandBuffer& BeginCommandRecording(VkCommandBufferUsageFlags flags = 0,
                                                const VkCommandBufferInheritanceInfo* pInheritanceInfo = nullptr);
         void EndCommandRecording();
-        // Lazily opens the pre-pass work stream (see FrameData::preCommandBuffer).
-        VkCommandBuffer BeginPreCommandRecording();
-        // Closes the pre stream if open, marking it for submission ahead of the
-        // frame command buffer. Safe to call when it never opened.
-        void EndPreCommandRecordingIfOpen();
-        // Drops an in-progress or recorded-but-unsubmitted pre stream (dropped
-        // frame recordings, swapchain recreation).
-        void AbandonPreCommandRecording();
         VkResult InitializeSwapchainSemaphores(VkDevice device, Uint32 swapchainImageCount);
         void DestroySwapchainSemaphores(VkDevice device);
         Bool TransitionToPresent(VkImage image, VkImageLayout oldLayout,
@@ -107,18 +79,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // Parks the current (already ended and submitted) command buffer on the
         // slot's retired list and installs a freshly allocated one, so recording
         // can restart while the submitted buffer is still executing. Retired
-        // buffers are freed after the slot's fence is next waited, or as soon
-        // as their submission is observed complete.
-        VkResult RetireCurrentCommandBuffer(Bool retirePreCommandBuffer = false);
-
-        // Frees every retired command buffer whose tagged submission index is
-        // known complete. Driven by the renderer's submit tracker on completion
-        // events (fence waits and non-blocking polls), so present-less flush
-        // loops reclaim their buffers without any extra wait.
-        void FreeRetiredCommandBuffersCompletedUpTo(Uint64 completedSubmitIndex);
-        // Frees every slot's retired command buffers. Only valid when the
-        // caller has proven every queue submission complete.
-        void FreeAllRetiredCommandBuffers();
+        // buffers are freed after the slot's fence is next waited.
+        VkResult RetireCurrentCommandBuffer();
 
         Uint32 GetCurrentFrameIndex() const;
         Uint32 GetFrameCount() const;

MobileGL/MG_Backend/DirectVulkan/Renderer/MagmaPipeArms.h

@@ -1,611 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/MagmaPipeArms.h
-// Copyright (c) 2025-2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-
-#pragma once
-#include <Includes.h>
-
-#include <Config.h>
-#if MOBILEGL_PIPE_PUSH
-// kMGPipeSubsystem* - the runtime bitmask's named bits - and MGPipeHandle itself. Both are
-// header-only constant/POD declarations, and both are push-only, so the pull build's include
-// graph is unchanged (G1).
-#include <MG_Pipe/MGPipe.h>
-#include <MG_Pipe/MGPipeHandles.h>
-#endif
-
-#include <cstdlib>
-
-// Magma's arm selector for the P2 Track H / render-state re-keys (P2 brief D14), and the
-// {slot, gen} mint the re-keyed sites are written against.
-//
-// Two switches decide which arm a re-keyed site runs, and they are NOT the same switch:
-//
-//   MOBILEGL_PIPE_PUSH (compile)          - is the pushed state there to be keyed on at all
-//   Features.PipePush  (runtime bitmask)  - is THIS subsystem migrated in THIS run
-//   MOBILEGL_PIPE_LEGACY_MEMOS (compile)  - is the pre-handle arm compiled beside it
-//   Features.PipeLegacyMemos (runtime)    - may the pre-handle arm be ENTERED in this run
-//
-// ARCHITECTURE.md 9.6's point: once a handle wave lands, a clear MOBILEGL_PIPE_PUSH bit is
-// only a valid A/B while the legacy arm is still compiled, because with the bit clear the
-// backend would otherwise still run the re-keyed code. So a clear bit selects the legacy
-// arm, and a run that has explicitly disabled the legacy arm may not fall into it.
-//
-// D14 spends that last sentence at STARTUP, not per draw: "a Track-H subsystem whose bit is
-// clear is a startup Fatal{PipeLegacyMemosDisabled}". Nothing in the draw path aborts, and
-// nothing outside Track H consults the legacy-memo lever at all - see
-// MagmaPipeValidateSubsystemConfiguration below for both halves of that rule.
-//
-// The whole header is inert in a pull build: MOBILEGL_PIPE_PUSH is 0 there, every helper
-// below is behind it, and the pull build's translation units are byte-identical (G1).
-namespace MobileGL::MG_Backend::DirectVulkan {
-
-#if MOBILEGL_PIPE_PUSH
-    // Is `subsystemBit` (MG_Pipe/MGPipe.h's kMGPipeSubsystem*) migrated in this run?
-    inline Bool MagmaPipeSubsystemOn(Uint64 subsystemBit) {
-        return (MG_Config::Features.PipePush & subsystemBit) != 0;
-    }
-
-    // ---------------------------------------------------------------------------------
-    // D14's startup gate
-    // ---------------------------------------------------------------------------------
-    //
-    // Called once from VulkanRenderer::Initialize(), i.e. only when Magma is the backend
-    // that is actually running. It answers exactly one question and it answers it before the
-    // first draw: is there an arm for Magma's Track-H subsystem in this configuration?
-    //
-    // Three deliberate boundaries, each of which the per-draw shape this replaces got wrong:
-    //
-    //  * ONLY Magma's own Track-H bit is checked. Espryt's bit 5 is Espryt's business (a
-    //    DirectVulkan run does not execute one line of DirectGLES' re-key), so
-    //    MOBILEGL_PIPE_PUSH=0x20 must not kill a Magma run, and MOBILEGL_PIPE_PUSH=0x40 must
-    //    not kill an Espryt one.
-    //  * bit 0 (kMGPipeSubsystemRenderState) is NOT Track H and is NOT fatal. It is not a
-    //    memo re-key at all: it decides where the pipeline memo's STATE KEY comes from, and
-    //    a clear bit there simply means the client is not pushing render-state CSOs in this
-    //    run, which GetOrCreatePipeline answers with its own state hash. D14 labels bits 5
-    //    and 6 "Track H" and labels bit 0 nothing of the sort.
-    //  * it is Fatal at STARTUP, once, not on a draw. A per-draw abort inside
-    //    GetOrCreatePipeline turns a configuration mistake into a mid-frame crash and puts a
-    //    branch nobody needs on the hottest path in the backend.
-    //
-    // [declared deviation from D14, review v2 minor 2] D14's runtime row reads "false: the
-    // legacy arm is never entered", and D14's compile-switch row names ComputePipelineStateHash
-    // as part of the pre-handle arm. Those two together would make MOBILEGL_PIPE_LEGACY_MEMOS=0
-    // with bit 0 CLEAR a contradiction: the pipeline memo has no CSO handle to key on, so it
-    // keys on a state hash, and in a build that compiles the pre-handle arm that hash IS
-    // ComputePipelineStateHash. Magma does not make that fatal - bit 0 is not Track H, and
-    // there is a correct answer (the state hash) where for bits 5/6 there is none - but it no
-    // longer does it SILENTLY: the combination is named once, at startup, right here.
-    inline void MagmaPipeValidateSubsystemConfiguration() {
-        if (!MG_Config::Features.PipeLegacyMemos &&
-            !MagmaPipeSubsystemOn(MG_Pipe::kMGPipeSubsystemRenderState)) {
-            MGLOG_W("MGPipe: MOBILEGL_PIPE_LEGACY_MEMOS=0 with kMGPipeSubsystemRenderState (bit 0 "
-                    "of MOBILEGL_PIPE_PUSH) clear - Magma's pipeline memo has no CSO handle to key "
-                    "on, so every draw whose pipeline-state version moved runs the pre-handle STATE "
-                    "HASH instead. That is not a Track-H subsystem and not fatal, but it is not the "
-                    "handle arm either: set bit 0 (MOBILEGL_PIPE_PUSH=0x%llx) if this run was meant "
-                    "to measure it.",
-                    static_cast<unsigned long long>(MG_Config::Features.PipePush |
-                                                    MG_Pipe::kMGPipeSubsystemRenderState));
-        }
-#if MOBILEGL_PIPE_LEGACY_MEMOS
-        // The pre-handle arm is compiled AND the operator has not forbidden entering it, so a
-        // clear bit is an ordinary, valid A/B: the site takes the legacy arm.
-        if (MG_Config::Features.PipeLegacyMemos) return;
-#endif
-        if (MagmaPipeSubsystemOn(MG_Pipe::kMGPipeSubsystemMagmaVertexInput)) return;
-#if MOBILEGL_PIPE_LEGACY_MEMOS
-        const char* const why = "this run has MOBILEGL_PIPE_LEGACY_MEMOS=0";
-#else
-        const char* const why =
-            "this build has cmake -DMOBILEGL_PIPE_LEGACY_MEMOS=OFF, which compiles no such arm";
-#endif
-        MGLOG_F("MGPipe: Fatal{PipeLegacyMemosDisabled} Magma's Track-H subsystem "
-                "(kMGPipeSubsystemMagmaVertexInput, bit 6 of MOBILEGL_PIPE_PUSH) is clear, so the "
-                "vertex-input cache and the VAO draw memo want the pre-handle arm - but %s. Set "
-                "bit 6 (MOBILEGL_PIPE_PUSH=0x%llx, or the default 0x%llx), or allow the legacy arm.",
-                why,
-                static_cast<unsigned long long>(MG_Config::Features.PipePush |
-                                                MG_Pipe::kMGPipeSubsystemMagmaVertexInput),
-                static_cast<unsigned long long>(MG_Pipe::kMGPipeSubsystemsMigratedAtP2));
-        std::abort();
-    }
-
-    // "Does this Track-H site run the handle arm?" - the ONE question every re-keyed Track-H
-    // site asks, so that they cannot disagree with each other or with the startup gate.
-    inline Bool MagmaPipeTrackHArmIsHandles(Uint64 trackHBit) {
-#if MOBILEGL_PIPE_LEGACY_MEMOS
-        return MagmaPipeSubsystemOn(trackHBit);
-#else
-        // No pre-handle arm exists in this build, and MagmaPipeValidateSubsystemConfiguration
-        // has already made a clear bit a startup Fatal, so the handle arm is the only arm a
-        // running process can be on.
-        (void)trackHBit;
-        return true;
-#endif
-    }
-
-    // ---------------------------------------------------------------------------------
-    // Negative control C (P2 brief D18): MOBILEGL_PIPE_HANDLE_ABA_CONTROL
-    // ---------------------------------------------------------------------------------
-    //
-    // "Is the object-identity half of every vertex-input memo key deliberately defeated in
-    // this run?" - the ONE question the control's sites ask, for the same reason
-    // MagmaPipeTrackHArmIsHandles exists: three sites deciding separately could disagree,
-    // and a control that defeats two of three guards proves nothing.
-    //
-    // WHAT IT DEFEATS, AND WHY IT IS SPELLED AS "REPLACE THE IDENTITY WITH A CONSTANT"
-    // RATHER THAN "USE THE HEAP ADDRESS".
-    //
-    // D18 wrote the control as "hash attr.Buffer.get() instead of GetLifetimeId(), and skip
-    // the vaoLifetimeId compare", on the theory that a deleted object's replacement lands at
-    // the freed heap block and so reproduces the key. Measured, it does not: in
-    // HandleRecycleScenario the GL NAMES come back (glGen* hands the deleted name straight
-    // out) but the C++ heap blocks do not - a VertexArrayObject is 3920 bytes, too large for
-    // glibc's tcache, so its chunk goes to the unsorted bin and is split by the very next
-    // allocation the replacement path makes. Four create/delete cycles in one run produced
-    // four distinct addresses, ~1 MiB apart. With no address reuse there is nothing for
-    // "hash the address" to collide with: the replacement hashes differently, indexes a
-    // different memo slot, and inherits nothing - so the arm asserted stale pixels and saw
-    // fresh ones, which is a FAILING negative control that had stopped controlling anything.
-    //
-    // So the control no longer asks the allocator for the collision; it manufactures it. On
-    // both arms the object identity is replaced by a constant, which is the strongest form of
-    // "the allocator handed the block back" and is deterministic. That covers strictly more
-    // than D18's spelling, and in particular it reaches the arm P2 SHIPS: on the handle arm
-    // the constant defeats the OBJECT IDENTITY THAT SELECTS THE SLOT - the key the handle arm
-    // ships - so the replacement VAO is handed the dead one's memo entry and its content hash.
-    // Defeating only the retired lifetime-id/address guards would leave that key untested,
-    // which is exactly the vacuity this control exists to catch.
-    //
-    // WHAT IT DOES NOT COVER, AND WHY NO REPRODUCER OF THIS SHAPE CAN [fix-aba review v1,
-    // MAJOR 1]. It does NOT exercise the GENERATION half of {slot, gen}:
-    //
-    //   * THIS MINT still has no death notification, and that is now a narrower statement than
-    //     it was. P7 wave 2 package C gives DirectVulkan a StateObjectDeathOps table
-    //     (DirectVulkan.cpp's g_magmaStateObjectDeathOps, CONTRACT-P7 §5.5), so
-    //     NotifyStateObjectDestroyed DOES have a consumer on this backend - but that consumer's
-    //     one job is to emit the `object_death` RECORD so the server drops its twin, and it
-    //     never touches these per-renderer identity tables: they are the SERVER-side renderer's
-    //     own, the notice is raised on the CLIENT thread, and an Acquire/retire from the wrong
-    //     side is precisely the cross-role read CONTRACT-P5C §3.1 forbids. So a slot here still
-    //     returns to the free list only through OnFrameBoundary's age sweep (kSweepInterval
-    //     256, kRetireAgeBoundaries 1024, below), and everything the two bullets below derive
-    //     from that is unchanged;
-    //   * HandleRecycleScenario issues five frame boundaries, so the free list is empty when
-    //     the replacement VAO acquires and it gets a BRAND-NEW slot at Gen 1 (measured:
-    //     redVao slot=2 gen=1, greenVao slot=3 gen=1). The knob-off FRESH verdict there is
-    //     decided by the SLOT alone, and deleting the ++Gen below leaves all four arms green;
-    //   * a genuine slot REUSE needs >= 1024 idle boundaries after the dead object's last
-    //     draw, which necessarily puts the two draws in different frames - and the only memo
-    //     that carries a GPU slice rather than a layout, ResolvedVertexBindings, declines
-    //     across frames by design. The two requirements are mutually exclusive, so the
-    //     generation is out of reach of any same-frame pixel reproducer for this memo.
-    //
-    // The generation is covered where it IS expressible, over this mint and the claim rule
-    // MagmaPipeClaimSlotMemos below: MG_Test/Pipe/MagmaPipeIdentityTest.cpp drives a real
-    // retire -> reuse and asserts that a memo stamped at {slot, gen=N} is not served at
-    // {slot, gen=N+1} with the knob off and IS served with it on. Deleting the ++Gen reds that
-    // suite; it is the only place in the tree where that deletion is caught.
-    //
-    // Everything the control does NOT defeat is as load-bearing as what it does. It never
-    // touches a guard that is not an IDENTITY guard: the resolved-bindings memo's frame
-    // serial, its slice-epoch compares and its host-map check all stay in force, so a green
-    // AbaControl arm still means "a replacement object was handed its dead predecessor's
-    // resolved vertex bindings because the identity halves of the keys were defeated", not
-    // "every safety net was switched off until something broke".
-    //
-    // Off by default (Config.h), set only by the HandleRecycle AbaControl ctest lanes, and
-    // #if MOBILEGL_PIPE_PUSH throughout, so no shipping pull build can even parse it.
-    // P4a (BRIEF-P4A.md D-I2, G8): WHICH KINDS THIS ANSWER COVERS, and it is not "all of them".
-    //
-    // P4a mints six more client-side kinds - Texture, Renderbuffer, Framebuffer, SamplerCso,
-    // SamplerViewCso and ShaderCso - and requires the ABA control to defeat "the identity half
-    // of P4a's memo keys as well", because a control that only defeats the guards a phase
-    // RETIRED says nothing about the key that phase SHIPS.
-    //
-    // On Magma there is no such key to defeat, and that is a fact about the roadmap rather than
-    // an omission here. MagmaPipeIdentityTables below mints exactly TWO kinds,
-    // VertexElementsCso and Buffer; a texture, a framebuffer, a sampler, a view and a program
-    // are all still reached from their frontend objects on this backend, and moving them onto
-    // handles is P7's work (ROADMAP.md:24 - "Magma anything"; P4a leaves MG_Backend/DirectVulkan
-    // untouched apart from this file). So the honest statement is per KIND, and it is spelled as
-    // code rather than as a comment so that a caller cannot read the blanket answer above and
-    // conclude the knob covers its kind:
-    //
-    //   * for the two kinds this backend really keys on {slot, gen}, the knob defeats the
-    //     identity exactly as it always has (MagmaPipeClaimSlotMemos);
-    //   * for P4a's six there is nothing here to defeat, so the answer is FALSE - and
-    //     MG_IntegrationTest's HandleRecycleScenario reads that through its own build probe and
-    //     makes those cases' AbaControl arm assert the CORRECT pixels while SAYING that it is
-    //     not controlling anything for that kind. It does not assert a corruption that no code
-    //     on this tree can produce, which would be a permanently red always-on lane.
-    //
-    // WHAT MAKES IT TRUE LATER, in one sentence, so the next reader does not have to derive it:
-    // when a backend grows a Features.PipeHandleAbaControl consumer over its P4a object slot
-    // tables - one `if` in GetOrCreate / FindByHandle, the shape MagmaPipeClaimSlotMemos already
-    // has for vertex input - this function's per-kind answer becomes that consumer's, the
-    // integration probe finds the consumer, and the six cases flip to expecting the corruption.
-    inline Bool MagmaPipeAbaControlDefeatsIdentity() {
-        return MG_Config::Features.PipeHandleAbaControl;
-    }
-
-    // WHICH KINDS THIS BACKEND ACTUALLY KEYS ON {slot, gen}, and therefore which kinds the knob
-    // above has an identity to defeat at all. `kind` is MG_Pipe::MGPipeKind.
-    //
-    // EXHAUSTIVE, WITH NO `default:`, for MG_IntegrationTest/Harness/PipeSlotPeek.cpp's reason:
-    // a kind added to MGPipeKind without a decision here must be a -Wswitch warning in this
-    // file rather than a row that silently inherits somebody else's answer. Being wrong in the
-    // "covered" direction is the expensive one - a control asserting a corruption nobody can
-    // produce is a permanently red always-on lane - so an undecided kind must never read true,
-    // and with no `default:` there is no arm for it to read true from.
-    //
-    // constexpr AND PINNED BY static_assert BELOW, which is what stops it rotting the way a
-    // predicate with no caller does: MagmaPipeIdentityTables mints exactly two kinds, the
-    // asserts say so in both directions, and the file no longer compiles if the tables and this
-    // statement of them ever part company. (Review F-m5: the earlier form had no caller at all
-    // and could not make anything red or green.)
-    inline constexpr Bool MagmaPipeAbaControlKindIsRekeyedHere(MG_Pipe::MGPipeKind kind) {
-        switch (kind) {
-            // The two MagmaPipeIdentityTables really mints.
-            case MG_Pipe::MGPipeKind::VertexElementsCso:
-            case MG_Pipe::MGPipeKind::Buffer:
-                return true;
-            // P4a's six object classes: still reached from their frontend objects on this
-            // backend (Magma's object paths are P7, ROADMAP.md:24), so there is no key here for
-            // the knob to defeat.
-            case MG_Pipe::MGPipeKind::Texture:
-            case MG_Pipe::MGPipeKind::Renderbuffer:
-            case MG_Pipe::MGPipeKind::Framebuffer:
-            case MG_Pipe::MGPipeKind::SamplerCso:
-            case MG_Pipe::MGPipeKind::SamplerViewCso:
-            case MG_Pipe::MGPipeKind::ShaderCso:
-            // ...and everything else this backend does not mint a handle for.
-            case MG_Pipe::MGPipeKind::None:
-            case MG_Pipe::MGPipeKind::Xfb:
-            case MG_Pipe::MGPipeKind::RenderStateCso:
-            case MG_Pipe::MGPipeKind::Fence:
-            case MG_Pipe::MGPipeKind::Query:
-            case MG_Pipe::MGPipeKind::Context:
-            case MG_Pipe::MGPipeKind::KindCount:
-                return false;
-        }
-        return false;
-    }
-
-    static_assert(MagmaPipeAbaControlKindIsRekeyedHere(MG_Pipe::MGPipeKind::VertexElementsCso),
-                  "MagmaPipeIdentityTables mints VertexElementsCso: the knob has an identity to "
-                  "defeat for it");
-    static_assert(MagmaPipeAbaControlKindIsRekeyedHere(MG_Pipe::MGPipeKind::Buffer),
-                  "MagmaPipeIdentityTables mints Buffer: the knob has an identity to defeat for it");
-    static_assert(!MagmaPipeAbaControlKindIsRekeyedHere(MG_Pipe::MGPipeKind::Texture) &&
-                      !MagmaPipeAbaControlKindIsRekeyedHere(MG_Pipe::MGPipeKind::Renderbuffer) &&
-                      !MagmaPipeAbaControlKindIsRekeyedHere(MG_Pipe::MGPipeKind::Framebuffer) &&
-                      !MagmaPipeAbaControlKindIsRekeyedHere(MG_Pipe::MGPipeKind::SamplerCso) &&
-                      !MagmaPipeAbaControlKindIsRekeyedHere(MG_Pipe::MGPipeKind::SamplerViewCso) &&
-                      !MagmaPipeAbaControlKindIsRekeyedHere(MG_Pipe::MGPipeKind::ShaderCso),
-                  "P4a's six object classes are not keyed on {slot, gen} on this backend, so "
-                  "HandleRecycleScenario's six AbaControl arms must NOT expect a corruption here. "
-                  "Wiring one of them is what flips this assert, this predicate and that arm - and "
-                  "MG_IntegrationTest's two-symbol probe over MG_Backend/DirectVulkan is what "
-                  "carries the answer into the lane");
-
-    // THERE IS DELIBERATELY NO PER-KIND WRAPPER HERE, and review F-v2-m3 is why. An earlier
-    // round carried `MagmaPipeAbaControlCoversKind(kind)` - the conjunction of the two
-    // statements above - and it had no caller anywhere in the tree: the knob's only two
-    // consumers (VulkanRenderer.cpp's VAO draw memo and VertexInputStateFactory.cpp's pipeline
-    // key) each hold ONE kind, VertexElementsCso, by construction, so the kind is not a
-    // variable at either site. A conjunction no build ever evaluates cannot be pinned the way
-    // the predicate above is pinned - it is not constexpr, because it reads MG_Config::Features,
-    // so no static_assert can reach it - which makes it exactly the rot F-m5 was raised about,
-    // one level up: an `&&` whose operands could be inverted or dropped with nothing to say so.
-    //
-    // The two pieces stand alone instead, and each is pinned by something that runs:
-    // MagmaPipeAbaControlKindIsRekeyedHere is constexpr and asserted in BOTH directions by the
-    // three static_asserts above, which compile in every Magma build; MagmaPipeAbaControlDefeats
-    // Identity is the knob, and its two consumers are what make it true or false. A call site
-    // that ever does hold a variable kind writes the `&&` there, where a build will run it.
-
-    // The single consumer-table entry every VAO collapses onto while the control is on. Slot
-    // 0 is a real, ordinary entry of both tables (MagmaPipeSlotIndex maps the first allocatable
-    // handle onto it), so nothing about the tables changes shape for the control's sake.
-    inline constexpr Uint32 kMagmaPipeAbaControlSlotIndex = 0;
-
-    // ---------------------------------------------------------------------------------
-    // The {slot, gen} mint
-    // ---------------------------------------------------------------------------------
-    //
-    // Maps a frontend object's never-reused lifetime id to a dense {slot, gen}. Three
-    // properties, and the third is the one review v2 got wrong:
-    //
-    //   1. exact identity - Gen moves whenever a slot changes owner, so a stale handle can
-    //      never match a live object even if the allocator hands back the same heap address
-    //      (the ABA HandleRecycleScenario reproduces);
-    //   2. dense slots - the slot IS an index, so a consumer's per-slot table needs no hash,
-    //      no probe and no mix;
-    //   3. NO CAPACITY CLIFF. A live object's handle never changes while the object is being
-    //      drawn, whatever the working set size.
-    //
-    // Property 3 is why this is not the fixed 2-way set-associative LRU the previous round
-    // shipped. That structure evicted a LIVE object once the working set passed its capacity,
-    // and every consumer memo keyed on the handle died with it: measured on a verbatim
-    // transcription, 54% of uses lost their handle at 2500 live VAOs against 2048 entries, and
-    // 20% at 1024 live VAOs once the lifetime ids are sparse (an app that creates and destroys
-    // VAOs, which is the Minecraft chunk shape this exists for). Two of the three memos it
-    // fed - the content-hash memo and the resolved-state memo - had NO capacity before this
-    // package: they were unbounded mutable fields on VertexArrayObject. Introducing eviction
-    // there turns one ComputeHash per VAO reconfiguration into one per DRAW, and, once the
-    // buffer table thrashes too, makes the vertex-input content hash a per-draw value that
-    // inserts a fresh heap-allocated BackendVertexInputState into an unbounded map on every
-    // draw. That is a worse leak than the one it was introduced to avoid.
-    //
-    // So: grow on demand, and reclaim by AGE instead of by capacity.
-    //
-    //   * Acquire hits an UnorderedMap<lifetimeId, slotIndex>, in front of which sits a
-    //     one-entry memo. Every re-keyed site in a draw asks about the SAME VAO, so the memo
-    //     turns the five-or-six acquisitions a draw makes into one map probe plus five Uint64
-    //     compares - less than the address multiply plus two-way probe the pre-handle arm ran.
-    //   * OnFrameBoundary retires slots whose object has not been drawn for
-    //     kRetireAgeBoundaries boundaries and returns them to a free list, so the table's
-    //     footprint tracks the LIVE DRAWN working set, not objects ever created. That is the
-    //     property MG_Impl/Pipe/SlotAllocator cannot have here: nothing in P2 can call its
-    //     Free (the tracker emits no object-class state, BufferBackendOps::OnDestroy is handed
-    //     a BackendBufferResource rather than the BufferObject, and VertexArrayObject has no
-    //     death hook at all - adding one is D13's explicit-destroy work, which covers Espryt's
-    //     six kinds, not VertexElementsCso), so an allocator here would grow by one SlotState
-    //     plus one map node per object EVER created, for the life of the process, on a
-    //     platform with an LMK. Age-based reclamation is the stand-in for the death
-    //     notification, and it is exactly as ABA-proof, because reuse bumps Gen.
-    //   * A retire costs at most one memo recompute if the object is drawn again - the same
-    //     price a cache miss costs - and it is charged only to objects that went idle for
-    //     ~1024 frames, never to a hot one.
-    //
-    // Memory: one map node plus one 24-byte Entry per live object, i.e. tens of bytes against
-    // the kilobyte a VertexArrayObject or a BufferObject already costs the frontend. There is
-    // no capacity to size off a device measurement because there is no capacity; what the
-    // device run in D.4.2 can still want is the number itself, so the high-water mark is
-    // logged at MGLOG_D on the allocate-a-new-slot branch (once per new object, never on a
-    // draw - ROADMAP.md:7).
-    //
-    // Single-threaded, like the rest of the renderer. Owned per VulkanRenderer (see
-    // MagmaPipeIdentityTables): a process-global would share one table, and one reclamation
-    // clock, across two live contexts.
-    class MagmaPipeIdentityTable {
-    public:
-        explicit MagmaPipeIdentityTable(const char* kindName) : m_kindName(kindName) {}
-
-        // Slots ever minted. A consumer table indexed by MagmaPipeSlotIndex() needs this many
-        // entries; MagmaPipeSlotTable below grows itself, so nobody has to ask.
-        Uint32 Count() const { return static_cast<Uint32>(m_entries.size()); }
-        // Objects currently holding a slot - the live working set this table tracks.
-        Uint32 LiveCount() const { return static_cast<Uint32>(m_index.size()); }
-
-        MG_Pipe::MGPipeHandle Acquire(Uint64 lifetimeId) {
-            // Unreachable: MG_State hands out lifetime ids from 1 precisely so that a
-            // zero-initialised memo slot cannot carry a live object's id. Guarded anyway so
-            // that a zero can never be minted into a slot and then indexed with.
-            if (lifetimeId == 0) return MG_Pipe::kMGPipeNullHandle;
-            // The one-entry front memo. Cleared by any retire, so it can never serve a slot
-            // that has been handed back to the free list.
-            if (lifetimeId == m_lastLifetimeId) {
-                m_entries[m_lastIndex].LastUse = m_boundary;
-                return m_lastHandle;
-            }
-            Uint32 index = 0;
-            const auto it = m_index.find(lifetimeId);
-            if (it != m_index.end()) {
-                index = it->second;
-            } else {
-                index = ClaimSlot();
-                m_entries[index].LifetimeId = lifetimeId;
-                m_index.emplace(lifetimeId, index);
-            }
-            Entry& entry = m_entries[index];
-            entry.LastUse = m_boundary;
-            m_lastLifetimeId = lifetimeId;
-            m_lastIndex = index;
-            m_lastHandle = MG_Pipe::MGPipeHandle{index + MG_Pipe::kMGPipeFirstAllocatableSlot,
-                                                 entry.Gen};
-            return m_lastHandle;
-        }
-
-        // Ages the table and returns idle slots to the free list. Same shape and the same
-        // self-gating as VertexInputStateFactory::OnFrameBoundary, which is what the reclaimed
-        // slots' consumers use.
-        void OnFrameBoundary() {
-            ++m_boundary;
-            if ((m_boundary % kSweepInterval) != 0) return;
-            SizeT retired = 0;
-            for (auto it = m_index.begin(); it != m_index.end();) {
-                Entry& entry = m_entries[it->second];
-                if ((m_boundary - entry.LastUse) > kRetireAgeBoundaries) {
-                    entry.LifetimeId = 0;
-                    m_freeSlots.push_back(it->second);
-                    it = m_index.erase(it);
-                    ++retired;
-                } else {
-                    ++it;
-                }
-            }
-            if (retired != 0) {
-                // A retired slot's Gen has not moved yet - it moves when the slot is reused -
-                // so a front memo pointing at one would still hand out a handle the consumer
-                // tables would accept. Drop it.
-                m_lastLifetimeId = 0;
-                m_lastHandle = MG_Pipe::kMGPipeNullHandle;
-                MGLOG_D("MagmaPipeIdentityTable(%s): retired %zu idle slots, %u live of %u minted",
-                        m_kindName, retired, LiveCount(), Count());
-            }
-        }
-
-    private:
-        // Sweep cadence and retirement age, deliberately the same numbers
-        // VertexInputStateFactory::OnFrameBoundary uses for the entries these slots key: a slot
-        // retired earlier than its cache entry would mint a new handle for an object whose
-        // entry is still live and still correct, which is a pure waste.
-        static constexpr Uint64 kSweepInterval = 256;
-        static constexpr Uint64 kRetireAgeBoundaries = 1024;
-
-        struct Entry {
-            Uint64 LifetimeId = 0;
-            Uint64 LastUse = 0;
-            // Moves ONLY on slot reuse, never on respecify: an object that keeps its slot keeps
-            // its generation, which is what makes a memo survive a reconfiguration.
-            Uint32 Gen = 0;
-        };
-
-        Uint32 ClaimSlot() {
-            while (!m_freeSlots.empty()) {
-                const Uint32 index = m_freeSlots.back();
-                m_freeSlots.pop_back();
-                // MGPipeHandles.h:52-58 defends the Gen wrap only in a debug allocator, and
-                // MOBILEGL_ASSERT is compiled out of every build P2 runs (Defines.h: asserts are
-                // live only at MOBILEGL_LOG_ACTIVE_LEVEL == DEBUG). So the wrap is handled on the
-                // RELEASE path instead of asserted: a slot that has been reused 2^32 times is
-                // permanently retired rather than wrapped, because a wrapped Gen would let a
-                // stale handle match a live object. It costs one slot.
-                if (m_entries[index].Gen == ~Uint32{0}) {
-                    MGLOG_W("MagmaPipeIdentityTable(%s): slot %u reached generation 2^32-1 and is "
-                            "retired for good; {slot, gen} stays unique",
-                            m_kindName, index + MG_Pipe::kMGPipeFirstAllocatableSlot);
-                    continue;
-                }
-                ++m_entries[index].Gen;
-                return index;
-            }
-            const Uint32 index = static_cast<Uint32>(m_entries.size());
-            m_entries.push_back(Entry{});
-            m_entries[index].Gen = 1;
-            // The high-water mark, at powers of two from 1024 up: at most a handful of lines
-            // for a whole session, emitted from the allocate-a-NEW-slot branch, i.e. once per
-            // object this backend has ever seen and never on a draw (ROADMAP.md:7).
-            //
-            // [narrow, declared deviation from D20's "MGLOG_D for anything non-critical"] This
-            // one is I, not D, because D is compiled out of every build that ships and of every
-            // build P2 measures, and this line IS the measurement review v2's MAJOR 1 asks for:
-            // the live-object high-water mark of minecraft-1.21.4-in-world and
-            // ...-sodium-in-world, which nothing on desktop reaches and no gate here can see.
-            // The structure no longer has a capacity to size off it, so the number is evidence
-            // rather than a tuning input - but D.4.2 should still read it out of the device log,
-            // and it cannot read a line that was compiled away.
-            const SizeT minted = m_entries.size();
-            if (minted >= 1024 && (minted & (minted - 1)) == 0) {
-                MGLOG_I("MagmaPipeIdentityTable(%s): high-water %zu slots minted, %u live",
-                        m_kindName, minted, LiveCount());
-            }
-            return index;
-        }
-
-        const char* m_kindName = "";
-        Uint64 m_boundary = 0;
-        Vector<Entry> m_entries;
-        Vector<Uint32> m_freeSlots;
-        UnorderedMap<Uint64, Uint32> m_index;
-        // One-entry front memo (see Acquire). m_lastLifetimeId == 0 means "empty": a live
-        // object's lifetime id is never 0.
-        Uint64 m_lastLifetimeId = 0;
-        Uint32 m_lastIndex = 0;
-        MG_Pipe::MGPipeHandle m_lastHandle = MG_Pipe::kMGPipeNullHandle;
-    };
-
-    // The two mints one renderer owns. Per renderer, NOT process-global: two live contexts (or
-    // a context recreation, which destroys and rebuilds the renderer) would otherwise share one
-    // table and one reclamation clock, and both consumer tables are per-instance already.
-    class MagmaPipeIdentityTables {
-    public:
-        // A VAO is kind VertexElementsCso: that is the gallium-shaped CSO a vertex array
-        // resolves to, and the only kind in MGPipeKind that names vertex-input state.
-        MG_Pipe::MGPipeHandle HandleOf(MG_Pipe::MGPipeKind kind, Uint64 lifetimeId) {
-            return kind == MG_Pipe::MGPipeKind::Buffer ? m_buffers.Acquire(lifetimeId)
-                                                       : m_vaos.Acquire(lifetimeId);
-        }
-        void OnFrameBoundary() {
-            m_vaos.OnFrameBoundary();
-            m_buffers.OnFrameBoundary();
-        }
-        const MagmaPipeIdentityTable& Vaos() const { return m_vaos; }
-        const MagmaPipeIdentityTable& Buffers() const { return m_buffers; }
-
-    private:
-        MagmaPipeIdentityTable m_vaos{"VertexElementsCso"};
-        MagmaPipeIdentityTable m_buffers{"Buffer"};
-    };
-
-    // The table entry a handle names. Every per-slot table Magma keeps is indexed by this.
-    //
-    // A null handle has no slot, and it is unreachable here: both lifetime-id sources start at
-    // 1 (VertexArrayObject.cpp, BufferObject.cpp), so Acquire's zero guard never fires. The
-    // ternary, not the assertion, is what has effect in a shipped build (Defines.h compiles
-    // MOBILEGL_ASSERT out at INFO), and slot 0 of a consumer table is a real entry that a null
-    // handle can never match, because MGPipeHandleIsNull is also what the consumers compare.
-    inline Uint32 MagmaPipeSlotIndex(const MG_Pipe::MGPipeHandle& handle) {
-        MOBILEGL_ASSERT(!MG_Pipe::MGPipeHandleIsNull(handle),
-                        "a null MGPipeHandle has no slot to index a per-slot table with");
-        return MG_Pipe::MGPipeHandleIsNull(handle)
-                   ? 0u
-                   : handle.Slot - MG_Pipe::kMGPipeFirstAllocatableSlot;
-    }
-
-    // A grow-on-demand per-slot table whose ENTRY ADDRESSES NEVER MOVE.
-    //
-    // D12.4 asks for a grow-on-demand Vector, and with an unbounded mint that is what a
-    // consumer needs - but a Vector that grows relocates its elements, and the draw path holds
-    // references into these entries across nested calls. Chunks of kChunkEntries are appended
-    // instead: the Vector of owning pointers reallocates, the chunks never do, so an entry
-    // reference is valid for the life of the table. That is the same guarantee the fixed table
-    // it replaces gave, without the fixed capacity.
-    template <typename T, Uint32 kChunkEntries = 256>
-    class MagmaPipeSlotTable {
-    public:
-        T& operator[](Uint32 index) {
-            const Uint32 chunk = index / kChunkEntries;
-            while (m_chunks.size() <= chunk) {
-                m_chunks.push_back(MakeUnique<Chunk>());
-            }
-            return m_chunks[chunk]->Entries[index % kChunkEntries];
-        }
-        SizeT Capacity() const { return m_chunks.size() * kChunkEntries; }
-
-    private:
-        struct Chunk {
-            T Entries[kChunkEntries] = {};
-        };
-        Vector<UniquePtr<Chunk>> m_chunks;
-    };
-
-    // The claim rule every per-slot memo table uses, in one place so that the rule and the
-    // negative control that defeats it cannot drift apart between consumers - and so that the
-    // unit suite which drives a REAL slot reuse (MG_Test/Pipe/MagmaPipeIdentityTest.cpp) tests
-    // this code rather than a copy of it.
-    //
-    // The SLOT picks the entry; the WHOLE handle - Gen included - decides whether the entry is
-    // this object's. A slot the mint recycled for a different object comes back with a moved
-    // Gen, so the compare fails and the entry is cleared rather than inherited. That is the
-    // half HandleRecycleScenario cannot reach (see MagmaPipeAbaControlDefeatsIdentity).
-    //
-    // With negative control C on, every object collapses onto one entry and the entry is handed
-    // back UNCLEARED and UNCLAIMED - at once "the replacement reproduced its predecessor's
-    // slot" and "the slot was reused and Gen did not move".
-    //
-    // `Memos` needs a MG_Pipe::MGPipeHandle member named Owner and a default constructor that
-    // means "empty"; VertexInputStateFactory::VaoBackendMemos is the one production instance.
-    template <typename Memos, Uint32 kChunkEntries>
-    inline Memos& MagmaPipeClaimSlotMemos(MagmaPipeSlotTable<Memos, kChunkEntries>& table,
-                                          const MG_Pipe::MGPipeHandle& handle) {
-        if (MagmaPipeAbaControlDefeatsIdentity()) {
-            return table[kMagmaPipeAbaControlSlotIndex];
-        }
-        Memos& memos = table[MagmaPipeSlotIndex(handle)];
-        if (!(memos.Owner == handle)) {
-            memos = Memos{};
-            memos.Owner = handle;
-        }
-        return memos;
-    }
-#endif // MOBILEGL_PIPE_PUSH
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/MagmaProgramSource.h

@@ -1,224 +0,0 @@
-// MobileGL - server-owned program input for Magma (P5f fm).
-#pragma once
-
-#include <MG_State/GLState/ProgramState/ProgramObject.h>
-
-#if MOBILEGL_BUILD_DISAGGREGATED
-#include <MG_Pipe/PipeApply.h>
-#include <MG_State/GLState/ProgramState/ProgramArtifactsCodec.h>
-#include "../DirectVulkanResourceState.h"
-// P7 wave 2 package C, OQ-8: spirv_reflect.h is GONE from this header, and its absence is the
-// gate. Everything this class needed it for - the storage-block index space - now travels in
-// the archive (LinkArtifacts::storageBlocks), so the SPIR-V reflector is off the Magma wire
-// draw path entirely. A future edit that re-adds the include is re-adding a per-draw reflect,
-// because a MagmaProgramSource is constructed once per draw and can memoise nothing.
-#endif
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-#if MOBILEGL_BUILD_DISAGGREGATED
-    // A borrowed view, valid only while its frontend object or server record lives.
-    // It never constructs a ProgramObject on the server. Post-link mutable values
-    // come from the record tails, not from the archive's link-time defaults.
-    class MagmaProgramSource {
-    public:
-        using Program = MG_State::GLState::ProgramObject;
-        MagmaProgramSource(const Program& program) : m_frontend(&program) {}
-        MagmaProgramSource(MG_Pipe::MGPipeHandle handle, const MG_Pipe::MGPipeShaderCsoRecord& record)
-            : m_handle(handle), m_record(&record) {
-            MOBILEGL_ASSERT(record.Archive != nullptr, "Magma program record has no archive");
-        }
-
-        Bool IsWire() const { return m_record != nullptr; }
-        MG_Pipe::MGPipeHandle Handle() const { return m_handle; }
-        const Program* Frontend() const { return m_frontend; }
-        Uint GetExternalIndex() const { return IsWire() ? m_handle.Slot : m_frontend->GetExternalIndex(); }
-        Uint64 GetLifetimeId() const {
-            return IsWire() ? (Uint64(m_handle.Gen) << 32) | m_handle.Slot : m_frontend->GetLifetimeId();
-        }
-        Bool GetLinkStatus() const { return IsWire() ? m_record->Desc.LinkStatus != 0 : m_frontend->GetLinkStatus(); }
-        Bool GetSpirvStatus() const { return IsWire() ? m_record->Desc.SpirvStatus != 0 : m_frontend->GetSpirvStatus(); }
-        Bool PointSizeDemoted() const { return IsWire() ? m_record->Desc.PointSizeDemoted != 0 : m_frontend->PointSizeDemoted(); }
-        Bool GetSpirvValidationEnabled() const {
-            return IsWire() ? m_record->Desc.EnableSpirvValidation != 0 : m_frontend->GetSpirvValidationEnabled();
-        }
-        const Vector<Vector<Uint>>& GetGeneratedSpirv() const {
-            return IsWire() ? m_record->Archive->Spirv.generatedSpirv : m_frontend->GetGeneratedSpirv();
-        }
-        Vector<ShaderStage> GetLinkedShaderStages() const {
-            if (!IsWire()) return m_frontend->GetLinkedShaderStages();
-            Vector<ShaderStage> result;
-            for (const auto stage : m_record->Archive->LinkedStages) result.push_back(static_cast<ShaderStage>(stage));
-            return result;
-        }
-        Bool HasLinkedShaderStage(ShaderStage stage) const {
-            if (!IsWire()) return m_frontend->HasLinkedShaderStage(stage);
-            const auto& stages = m_record->Archive->LinkedStages;
-            return std::find(stages.begin(), stages.end(), static_cast<Uint32>(stage)) != stages.end();
-        }
-        Bool GetBackendHashMemo(Uint flags, Uint64& hash) const {
-            // A view has no lifetime in which a memo can safely persist. The server
-            // factory's content cache still owns compiled programs; hash from current
-            // archive + binding tails rather than borrowing the client's mutable memo.
-            return !IsWire() && m_frontend->GetBackendHashMemo(flags, hash);
-        }
-        void SetBackendHashMemo(Uint flags, Uint64 hash) const {
-            if (!IsWire()) m_frontend->SetBackendHashMemo(flags, hash);
-        }
-        Uint64 GetBackendStateVersion() const { return IsWire() ? m_record->Serial : m_frontend->GetBackendStateVersion(); }
-        Uint64 GetBlockBindingVersion() const { return IsWire() ? m_record->BindingsSerial : m_frontend->GetBlockBindingVersion(); }
-        Uint64 GetImageUnitVersion() const { return IsWire() ? m_record->BindingsSerial : m_frontend->GetImageUnitVersion(); }
-        Uint64 GetLinkVersion() const { return IsWire() ? m_record->Serial : m_frontend->GetLinkVersion(); }
-
-        const void* GetUBOData() const { return IsWire() ? m_record->GlobalConstants.data() : m_frontend->GetUBOData(); }
-        Uint GetUBOSize() const { return IsWire() ? static_cast<Uint>(m_record->GlobalConstants.size()) : m_frontend->GetUBOSize(); }
-        Uint32 GetUBOContentVersion() const { return IsWire() ? m_record->GlobalConstantsVersion : m_frontend->GetUBOContentVersion(); }
-        Int GetActiveUniformBlocksCount() const {
-            return IsWire() ? static_cast<Int>(Link().glBlockIndexToTProgram.size()) : m_frontend->GetActiveUniformBlocksCount();
-        }
-        Uint GetUniformBlockIndex(const char* name) const {
-            if (!IsWire()) return m_frontend->GetUniformBlockIndex(name);
-            auto found = Link().uniformBlockIndexByName.find(name);
-            if (found == Link().uniformBlockIndexByName.end()) found = Link().uniformBlockIndexByName.find(String(name) + "[0]");
-            return found == Link().uniformBlockIndexByName.end() ? GL_INVALID_INDEX : found->second;
-        }
-        Uint GetUniformBlockBinding(Uint index) const {
-            if (!IsWire()) return m_frontend->GetUniformBlockBinding(index);
-            return index < m_record->BlockBindings.size() ? static_cast<Uint>(m_record->BlockBindings[index]) : 0;
-        }
-        const String& GetUniformBlockName(Uint index) const {
-            if (!IsWire()) return m_frontend->GetUniformBlockName(index);
-            const auto* block = Block(index);
-            static const String empty;
-            return block ? block->name : empty;
-        }
-        Uint GetUBOSizeAt(Uint index) const {
-            if (!IsWire()) return m_frontend->GetUBOSizeAt(index);
-            const auto* block = Block(index);
-            return block ? (static_cast<Uint>(block->size) + 15u) & ~15u : 0;
-        }
-        Bool IsValidUniformLocation(Int location) const {
-            return IsWire() ? Program::IsValidUniformLocation(Link(), location) : m_frontend->IsValidUniformLocation(location);
-        }
-        Bool UniformLocationsAliasSameUniform(Int a, Int b) const {
-            if (!IsWire()) return m_frontend->UniformLocationsAliasSameUniform(a, b);
-            return IsValidUniformLocation(a) && IsValidUniformLocation(b) &&
-                Link().uniformIndexInTProgram[a] == Link().uniformIndexInTProgram[b];
-        }
-        GLenum GetUniformType(Uint location) const {
-            if (!IsWire()) return m_frontend->GetUniformType(location);
-            return IsValidUniformLocation(static_cast<Int>(location))
-                ? Program::UniformAtIn(Link(), Link().uniformIndexInTProgram[location]).glDefineType : 0;
-        }
-        Int GetUniformSamplerOrImageUnitIndex(Uint location) const {
-            if (!IsWire()) return m_frontend->GetUniformSamplerOrImageUnitIndex(location);
-            const auto& units = m_record->SamplerUnits;
-            const auto found = std::lower_bound(units.begin(), units.end(), location,
-                [](const MG_Pipe::MGPProgramSamplerUnit& unit, Uint value) { return unit.Location < value; });
-            return found != units.end() && found->Location == location ? found->Unit : -1;
-        }
-        Int GetUniformLocation(const String& name) const {
-            if (!IsWire()) return m_frontend->GetUniformLocation(name);
-            const auto& locations = Link().uniformLocations;
-            auto found = locations.find(name);
-            if (found != locations.end()) return static_cast<Int>(found->second);
-            if (name.empty()) return -1;
-            found = locations.find(name + "[0]");
-            if (found != locations.end()) return static_cast<Int>(found->second);
-            if (name.back() != ']' || name.size() < 4) return -1;
-            const SizeT bracket = name.rfind('[');
-            if (bracket == String::npos || bracket + 1 >= name.size() - 1) return -1;
-            Uint element = 0;
-            for (SizeT i = bracket + 1; i < name.size() - 1; ++i) {
-                if (name[i] < '0' || name[i] > '9') return -1;
-                element = element * 10 + static_cast<Uint>(name[i] - '0');
-                if (element > 0x0fffffffu) return -1;
-            }
-            found = locations.find(name.substr(0, bracket) + "[0]");
-            if (found == locations.end()) found = locations.find(name.substr(0, bracket));
-            if (found == locations.end()) return -1;
-            const Int base = static_cast<Int>(found->second);
-            if (!IsValidUniformLocation(base)) return -1;
-            const Int tIndex = Link().uniformIndexInTProgram[base];
-            if (!Program::UniformAtIn(Link(), tIndex).type.isArray ||
-                static_cast<GLint>(element) >= Program::GetUniformArraySizeByTIndex(Link(), tIndex)) return -1;
-            const Int location = base + static_cast<Int>(element);
-            return UniformLocationsAliasSameUniform(base, location) ? location : -1;
-        }
-
-        SizeT GetTransformFeedbackVaryingCount() const { return IsWire() ? Link().xfbVaryings.size() : m_frontend->GetTransformFeedbackVaryingCount(); }
-        const Vector<MG_State::GLState::XfbVarying>& GetTransformFeedbackVaryings() const {
-            return IsWire() ? Link().xfbVaryings : m_frontend->GetTransformFeedbackVaryings();
-        }
-        SizeT GetTransformFeedbackBufferCount() const { return IsWire() ? Link().xfbStrides.size() : m_frontend->GetTransformFeedbackBufferCount(); }
-        Uint32 GetTransformFeedbackStride(Uint index) const {
-            if (!IsWire()) return m_frontend->GetTransformFeedbackStride(index);
-            return index < Link().xfbStrides.size() ? Link().xfbStrides[index] : 0;
-        }
-        GLenum GetTransformFeedbackBufferMode() const {
-            return IsWire() ? Link().xfbBufferMode : m_frontend->GetTransformFeedbackBufferMode();
-        }
-        // P7 wave 2 package C, OQ-8 (CONTRACT-P7 §5.3): READ OUT OF THE ARCHIVE.
-        //
-        // What stood here re-ran spvReflectCreateShaderModule over EVERY stage module of the
-        // program, and it did so PER DRAW: a MagmaProgramSource is a borrowed view that
-        // WireDraw.inc's WireProgramSource constructs afresh for each wire draw, so the lazy
-        // `m_storageBlocksReady` latch could never outlive one. The list it rebuilt is a pure
-        // function of the linked program, so it is now built once at link time and travels in
-        // the archive (LinkArtifacts::storageBlocks), which takes the SPIR-V reflector off the
-        // wire draw path entirely - this header no longer includes spirv_reflect.h at all.
-        Uint GetShaderStorageBlockIndex(const String& name) const {
-            if (!IsWire()) return DirectVulkan::GetShaderStorageBlockIndex(*m_frontend, name);
-            const auto& blocks = Link().storageBlocks;
-            // The archive carries NORMALISED names (the array subscript stripped), because
-            // that is the spelling SPIRV-Reflect's type_name gives and the spelling
-            // ProgramFactory::ReflectLayout looks up. A caller that still holds a GL-style
-            // "Foo[2]" gets the same second chance it always had.
-            const auto find = [&blocks](const String& key) {
-                return std::find_if(blocks.begin(), blocks.end(),
-                    [&](const MG_State::GLState::StorageBlockReflection& block) {
-                        return block.name == key;
-                    });
-            };
-            auto found = find(name);
-            if (found == blocks.end() && !name.empty() && name.back() == ']') {
-                const auto bracket = name.rfind('[');
-                if (bracket != String::npos) found = find(name.substr(0, bracket));
-            }
-            return found == blocks.end() ? GL_INVALID_INDEX
-                                         : static_cast<Uint>(found - blocks.begin());
-        }
-        Uint GetShaderStorageBlockBinding(Uint index) const {
-            if (!IsWire()) return DirectVulkan::GetShaderStorageBlockBinding(*m_frontend, index);
-            const auto& blocks = Link().storageBlocks;
-            if (index >= blocks.size()) return 0;
-            const auto& block = blocks[index];
-            // THE OVERRIDE STILL WINS, and it still comes off the RECORD rather than the
-            // archive: glShaderStorageBlockBinding is a post-link mutable and the archive
-            // carries link-time defaults only (rule on MagmaProgramSource, and the reason
-            // StorageBlockReflection::binding is documented as the DECLARED binding).
-            for (const auto& override : m_record->StorageOverrides) {
-                if (override.Name == block.name) return override.Binding;
-            }
-            return block.binding;
-        }
-
-    private:
-        const MG_State::GLState::LinkArtifacts& Link() const { return m_record->Archive->Link; }
-        const MG_State::GLState::BlockReflection* Block(Uint index) const {
-            if (index >= Link().glBlockIndexToTProgram.size()) return nullptr;
-            const Int tIndex = Link().glBlockIndexToTProgram[index];
-            return tIndex >= 0 && static_cast<SizeT>(tIndex) < Link().blockReflection.size()
-                ? &Link().blockReflection[tIndex] : nullptr;
-        }
-        const Program* m_frontend = nullptr;
-        MG_Pipe::MGPipeHandle m_handle = MG_Pipe::kMGPipeNullHandle;
-        const MG_Pipe::MGPipeShaderCsoRecord* m_record = nullptr;
-        // P7 OQ-8: the two mutables that memoised the per-draw reflect are gone with it. They
-        // were `mutable` precisely because this class is a borrowed const view - and that is
-        // also why they never helped: a view lives for one draw, so the latch was cold every
-        // time it was read.
-    };
-#else
-    using MagmaProgramSource = MG_State::GLState::ProgramObject;
-#endif
-}

MobileGL/MG_Backend/DirectVulkan/Renderer/PipelineFactory.cpp

@@ -8,8 +8,6 @@
 
 #include "PipelineFactory.h"
 
-#include <algorithm>
-
 namespace MobileGL::MG_Backend::DirectVulkan {
     static const char* PrimitiveTopologyToString(VkPrimitiveTopology topology) {
         switch (topology) {
@@ -110,81 +108,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                   "vkCreatePipelineCache");
     }
 
-    // Must be called once, before any pipeline is created: the flag is not part of the
-    // pipeline hash, so flipping it mid-life would serve cached pipelines built under the
-    // old value.
-    void PipelineFactory::SetSuppressBlendedDepthWrite(Bool enabled) {
-        s_suppressBlendedDepthWrite = enabled;
-    }
-
-    Bool PipelineFactory::ShouldSuppressBlendedDepthWriteForDevice(MG_Config::QuirkOverride quirkOverride,
-                                                                   Uint32 vendorId) {
-        static constexpr Uint32 kVendorIdQualcomm = 0x5143;
-        switch (quirkOverride) {
-        case MG_Config::QuirkOverride::ForceOn:
-            return true;
-        case MG_Config::QuirkOverride::ForceOff:
-            return false;
-        case MG_Config::QuirkOverride::Auto:
-        default:
-            return vendorId == kVendorIdQualcomm;
-        }
-    }
-
-    namespace {
-        // MIN/MAX extremum blending: the signature of a depth-bounds accumulation pass
-        // (MC 26.3 OIT writes vec4(-linD, linD, deviceZ, 0) under GL_MAX while writing
-        // depth for its equality chain). MIN/MAX ignore blend factors per the Vulkan spec.
-        //
-        // Deliberately the ONLY shape stripped. A quirk should touch as little unrelated
-        // content as possible, and a trace sweep of every fixture showed the wider
-        // alternatives all cost more than they fix:
-        //   - additive ONE+ONE with a depth write matched zero draws of the 26.3 chain
-        //     (its transmittance/accumulate passes disable depth writes themselves) - the
-        //     only real content it caught was harmless additive glow effects (Create);
-        //   - sorted-transparency "over" blends (SRC_ALPHA-style) are order-dependent,
-        //     drawn once per surface, and rely on their depth writes for occlusion;
-        //   - separate-alpha accumulation over an over-blending color channel has no
-        //     known pairing with a depth-equality chain (color channel only, see tests).
-        // If a future workload pairs another blend shape with an equality chain, widen
-        // this with that evidence in hand rather than pre-emptively.
-        Bool IsAccumulationBlend(const VkPipelineColorBlendAttachmentState& attachment) {
-            return attachment.colorBlendOp == VK_BLEND_OP_MIN ||
-                   attachment.colorBlendOp == VK_BLEND_OP_MAX;
-        }
-    } // namespace
-
-    Bool PipelineFactory::ShouldSuppressDepthWrite(const PipelineCreatePayload& payload) {
-        if (!payload.depthWriteEnable) {
-            return false;
-        }
-        // A shader that assigns gl_FragDepth supplies depth itself rather than taking the
-        // pipeline's interpolated Z, so a driver that varies the vertex position math
-        // between pipelines cannot desynchronize it. (A gl_FragDepth = gl_FragCoord.z
-        // passthrough is the exception that stays exposed; no known content pairs one with
-        // an equality chain, and 26.3's composite is a genuine computed-depth writer.)
-        if (payload.fragmentReplacesDepth) {
-            return false;
-        }
-        for (Uint32 i = 0; i < payload.colorAttachmentCount; ++i) {
-            const VkPipelineColorBlendAttachmentState& attachment = payload.colorBlendAttachments[i];
-            if (attachment.blendEnable != VK_TRUE) {
-                continue;
-            }
-            // All color writes masked: blending is moot (depth-prepass pattern that left
-            // GL_BLEND enabled); stripping the depth write would delete the whole prepass.
-            if (attachment.colorWriteMask == 0) {
-                continue;
-            }
-            // Any attachment qualifies, not just attachment 0: the 26.3 transmittance pass
-            // accumulates into a 2-target MRT and must stay stripped.
-            if (IsAccumulationBlend(attachment)) {
-                return true;
-            }
-        }
-        return false;
-    }
-
     PipelineFactory::~PipelineFactory() {
         DestroyAll();
         if (m_pipelineCache != VK_NULL_HANDLE) {
@@ -198,35 +121,16 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.programHash, sizeof(payload.programHash)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.vertexInputHash, sizeof(payload.vertexInputHash)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.pipelineLayout, sizeof(payload.pipelineLayout)));
-#if MOBILEGL_BUILD_DISAGGREGATED
-        if (payload.wireRenderPassCompatibilityId != 0) {
-            constexpr Uint64 wireDomain = 0x5749524552504b59ull;
-            XXHASH_VERIFY(XXH64_update(m_hashState, &wireDomain, sizeof(wireDomain)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &payload.wireRenderPassCompatibilityId,
-                                      sizeof(payload.wireRenderPassCompatibilityId)));
-        } else
-#endif
-        {
-            XXHASH_VERIFY(XXH64_update(m_hashState, &payload.renderPass, sizeof(payload.renderPass)));
-        }
+        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.renderPass, sizeof(payload.renderPass)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.colorAttachmentCount, sizeof(payload.colorAttachmentCount)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.rasterizationSamples, sizeof(payload.rasterizationSamples)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.sampleShadingEnable, sizeof(payload.sampleShadingEnable)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.minSampleShading, sizeof(payload.minSampleShading)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.sampleMask, sizeof(payload.sampleMask)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.subpass, sizeof(payload.subpass)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.topology, sizeof(payload.topology)));
         XXHASH_VERIFY(
             XXH64_update(m_hashState, &payload.primitiveRestartEnable, sizeof(payload.primitiveRestartEnable)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.patchControlPoints, sizeof(payload.patchControlPoints)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.passthroughTessControlKey,
-                                   sizeof(payload.passthroughTessControlKey)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &payload.viewportCount, sizeof(payload.viewportCount)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.polygonMode, sizeof(payload.polygonMode)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.cullMode, sizeof(payload.cullMode)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.frontFace, sizeof(payload.frontFace)));
-        XXHASH_VERIFY(
-            XXH64_update(m_hashState, &payload.provokingVertexMode, sizeof(payload.provokingVertexMode)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.depthTestEnable, sizeof(payload.depthTestEnable)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.depthWriteEnable, sizeof(payload.depthWriteEnable)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &payload.depthBiasEnable, sizeof(payload.depthBiasEnable)));
@@ -248,8 +152,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             XXH64_update(m_hashState, &payload.backStencilDepthFailOp, sizeof(payload.backStencilDepthFailOp)));
         XXHASH_VERIFY(
             XXH64_update(m_hashState, &payload.backStencilCompareOp, sizeof(payload.backStencilCompareOp)));
-        XXHASH_VERIFY(
-            XXH64_update(m_hashState, &payload.fragmentReplacesDepth, sizeof(payload.fragmentReplacesDepth)));
         if (payload.colorAttachmentCount > 0) {
             XXHASH_VERIFY(XXH64_update(
                 m_hashState,
@@ -263,132 +165,23 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         const HashType hash = ComputeHash(payload);
         auto it = m_cache.find(hash);
         if (it != m_cache.end()) {
-            it->second.lastUsedFrame = m_frameCounter;
-            return it->second.pipeline;
+            return it->second;
         }
 
         VkPipeline pipeline = CreatePipeline(payload);
-        // A failed creation must never be memoized. Caching VK_NULL_HANDLE served the null back for
-        // the rest of the process, so one transient driver rejection turned every later draw with
-        // the same state into a vkCmdBindPipeline(VK_NULL_HANDLE) - the SIGSEGV behind 9 of the 15
-        // CTS process deaths. Retrying costs one failed vkCreateGraphicsPipelines per draw, which
-        // is the correct price for a broken pipeline and is bounded by the draw itself being
-        // skipped.
-        if (pipeline == VK_NULL_HANDLE) {
-            // Unlatched, like the CreatePipeline report it accompanies: a pipeline MobileGL
-            // assembled and the driver refused is a broken invariant, not an expected failure,
-            // so it stays loud for as long as it is reachable. Raised from MGLOG_I once the
-            // Log.h ordering fix made MGLOG_E live in INFO builds.
-            MGLOG_E("PipelineFactory::GetOrCreatePipeline: creation failed for hash=0x%llx "
-                    "programHash=0x%llx; not caching the failure",
-                    static_cast<unsigned long long>(hash),
-                    static_cast<unsigned long long>(payload.programHash));
-            return VK_NULL_HANDLE;
-        }
-        m_cache.emplace(hash, PipelineCacheEntry{pipeline, payload.programHash,
-#if MOBILEGL_BUILD_DISAGGREGATED
-                                                 // Wire pipelines outlive their creator pass and
-                                                 // may serve another compatible pass in flight.
-                                                 // Never evict them by a recycled native handle.
-                                                 payload.wireRenderPassCompatibilityId != 0 ? VK_NULL_HANDLE :
-#endif
-                                                 payload.renderPass,
-                                                 m_frameCounter});
+        m_cache.emplace(hash, pipeline);
         return pipeline;
     }
 
     void PipelineFactory::DestroyAll() {
         for (auto& pair : m_cache) {
-            if (pair.second.pipeline != VK_NULL_HANDLE) {
-                vkDestroyPipeline(m_device, pair.second.pipeline, nullptr);
+            if (pair.second != VK_NULL_HANDLE) {
+                vkDestroyPipeline(m_device, pair.second, nullptr);
             }
         }
         m_cache.clear();
     }
 
-    Uint32 PipelineFactory::OnFrameBoundary() {
-        ++m_frameCounter;
-
-        // Sweep cadence and retire age mirror VkRenderPassManager::OnPresent: an entry
-        // idle for more than kRetireAgeFrames frame boundaries cannot be referenced by
-        // any in-flight command buffer (frames-in-flight <= MOBILEGL_MAGMA_FRAMESINFLIGHT),
-        // so immediate vkDestroyPipeline is safe. The caller must drop its "last
-        // pipeline" memo when this returns non-zero: the memo can return a cached
-        // handle without touching this cache, so an evicted pipeline may still be
-        // memoized (present-less flush loops never reset the memo per frame).
-        constexpr Uint64 kSweepInterval = 256;
-        constexpr Uint64 kRetireAgeFrames = 1024;
-        if ((m_frameCounter % kSweepInterval) != 0) {
-            return 0;
-        }
-
-        Uint32 evicted = 0;
-        for (auto it = m_cache.begin(); it != m_cache.end();) {
-            if (m_frameCounter - it->second.lastUsedFrame > kRetireAgeFrames) {
-                if (it->second.pipeline != VK_NULL_HANDLE) {
-                    vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
-                }
-                it = m_cache.erase(it);
-                ++evicted;
-            } else {
-                ++it;
-            }
-        }
-        if (evicted > 0) {
-            MGLOG_D("PipelineFactory::OnFrameBoundary: evicted %u idle pipelines (%zu remain)", evicted,
-                    m_cache.size());
-        }
-        return evicted;
-    }
-
-    Uint32 PipelineFactory::EvictByRenderPasses(const Vector<VkRenderPass>& renderPasses) {
-        if (renderPasses.empty() || m_cache.empty()) {
-            return 0;
-        }
-        // Sorted-batch membership test keeps a mass eviction (shader-pack switch,
-        // dimension exit) at one O(cache * log batch) scan instead of one full scan
-        // per dying pass.
-        Vector<VkRenderPass> sortedPasses = renderPasses;
-        std::sort(sortedPasses.begin(), sortedPasses.end());
-        Uint32 evicted = 0;
-        for (auto it = m_cache.begin(); it != m_cache.end();) {
-            if (std::binary_search(sortedPasses.begin(), sortedPasses.end(), it->second.renderPass)) {
-                if (it->second.pipeline != VK_NULL_HANDLE) {
-                    vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
-                }
-                it = m_cache.erase(it);
-                ++evicted;
-            } else {
-                ++it;
-            }
-        }
-        if (evicted > 0) {
-            MGLOG_D("PipelineFactory::EvictByRenderPasses: evicted %u pipelines for %zu destroyed render passes",
-                    evicted, sortedPasses.size());
-        }
-        return evicted;
-    }
-
-    Uint32 PipelineFactory::EvictByProgramHash(HashType programHash) {
-        Uint32 evicted = 0;
-        for (auto it = m_cache.begin(); it != m_cache.end();) {
-            if (it->second.programHash == programHash) {
-                if (it->second.pipeline != VK_NULL_HANDLE) {
-                    vkDestroyPipeline(m_device, it->second.pipeline, nullptr);
-                }
-                it = m_cache.erase(it);
-                ++evicted;
-            } else {
-                ++it;
-            }
-        }
-        if (evicted > 0) {
-            MGLOG_D("PipelineFactory::EvictByProgramHash: evicted %u pipelines for program hash 0x%llx",
-                    evicted, static_cast<unsigned long long>(programHash));
-        }
-        return evicted;
-    }
-
     VkPipeline PipelineFactory::CreatePipeline(const PipelineCreatePayload& payload) const {
         MOBILEGL_ASSERT(payload.stages != nullptr && !payload.stages->empty(), "PipelineFactory: stages are empty");
         MOBILEGL_ASSERT(payload.vertexInputState != nullptr, "PipelineFactory: vertexInputState is null");
@@ -423,18 +216,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         ia.topology = payload.topology;
         ia.primitiveRestartEnable = payload.primitiveRestartEnable ? VK_TRUE : VK_FALSE;
 
-        // Only a patch topology has a tessellation stage to configure; leaving the pointer null
-        // otherwise is what the spec expects.
-        VkPipelineTessellationStateCreateInfo tessellation{VK_STRUCTURE_TYPE_PIPELINE_TESSELLATION_STATE_CREATE_INFO};
-        tessellation.patchControlPoints = payload.patchControlPoints;
-
         VkPipelineViewportStateCreateInfo vpci{VK_STRUCTURE_TYPE_PIPELINE_VIEWPORT_STATE_CREATE_INFO};
-        // Both counts move together: GL has one scissor rectangle per viewport, and Vulkan
-        // requires viewportCount == scissorCount whenever both are dynamic
-        // (VUID-VkPipelineViewportStateCreateInfo-scissorCount-04136). The caller has already
-        // clamped this to the device's multiViewport capability.
-        vpci.viewportCount = std::max<Uint32>(payload.viewportCount, 1u);
-        vpci.scissorCount = vpci.viewportCount;
+        vpci.viewportCount = 1;
+        vpci.scissorCount = 1;
 
         VkPipelineRasterizationStateCreateInfo raster{VK_STRUCTURE_TYPE_PIPELINE_RASTERIZATION_STATE_CREATE_INFO};
         raster.polygonMode = payload.polygonMode;
@@ -443,28 +227,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         raster.depthBiasEnable = payload.depthBiasEnable ? VK_TRUE : VK_FALSE;
         raster.rasterizerDiscardEnable = payload.rasterizerDiscardEnable ? VK_TRUE : VK_FALSE;
         raster.lineWidth = 1.0f;
-        // Only chain the struct when the mode is not Vulkan's implicit default: a device without
-        // VK_EXT_provoking_vertex enabled must never see this pNext entry, and the renderer's
-        // selector already collapses to FIRST in exactly that case - so a device without the
-        // extension produces a byte-identical VkGraphicsPipelineCreateInfo to before.
-        VkPipelineRasterizationProvokingVertexStateCreateInfoEXT provokingVertexState{
-            VK_STRUCTURE_TYPE_PIPELINE_RASTERIZATION_PROVOKING_VERTEX_STATE_CREATE_INFO_EXT};
-        if (payload.provokingVertexMode != VK_PROVOKING_VERTEX_MODE_FIRST_VERTEX_EXT) {
-            provokingVertexState.provokingVertexMode = payload.provokingVertexMode;
-            provokingVertexState.pNext = raster.pNext;
-            raster.pNext = &provokingVertexState;
-        }
 
         VkPipelineMultisampleStateCreateInfo ms{VK_STRUCTURE_TYPE_PIPELINE_MULTISAMPLE_STATE_CREATE_INFO};
         ms.rasterizationSamples = payload.rasterizationSamples;
-        ms.sampleShadingEnable = payload.sampleShadingEnable ? VK_TRUE : VK_FALSE;
-        // Ignored by Vulkan unless sampleShadingEnable is set, but written unconditionally so the
-        // struct's bytes match the hash the payload was keyed by.
-        ms.minSampleShading = payload.minSampleShading;
-        // GL_SAMPLE_MASK / glSampleMaski. Left at nullptr - which Vulkan reads as all-ones - until
-        // now, so glSampleMaski was a silent no-op on this backend while DirectGLES forwarded it.
-        // The pointer has to outlive the vkCreateGraphicsPipelines call, which the payload does.
-        ms.pSampleMask = payload.sampleMask;
 
         VkPipelineDepthStencilStateCreateInfo depthStencil{VK_STRUCTURE_TYPE_PIPELINE_DEPTH_STENCIL_STATE_CREATE_INFO};
         depthStencil.depthTestEnable = payload.depthTestEnable ? VK_TRUE : VK_FALSE;
@@ -493,77 +258,17 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         for (Uint32 i = 0; i < payload.colorAttachmentCount; ++i) {
             colorAttachments[i] = payload.colorBlendAttachments[i];
         }
-        // Suppress depth writes on accumulation-blended pipelines when the active driver
-        // cannot keep vertex positions invariant across the pipelines of a multi-pass
-        // depth-equality chain (see SetSuppressBlendedDepthWrite). The decision is narrowed
-        // in ShouldSuppressDepthWrite: sorted-transparency "over" blends (vanilla MC water),
-        // gl_FragDepth writers, and masked-out attachments keep their depth writes.
-        // This bakes the decision into the pipeline, which only works because depth write is
-        // static state here - adding VK_DYNAMIC_STATE_DEPTH_WRITE_ENABLE to kDynamicStates
-        // would let the record-time value override it and silently disable the quirk.
-        if (s_suppressBlendedDepthWrite && ShouldSuppressDepthWrite(payload)) {
-            depthStencil.depthWriteEnable = VK_FALSE;
-        }
         VkPipelineColorBlendStateCreateInfo blend{VK_STRUCTURE_TYPE_PIPELINE_COLOR_BLEND_STATE_CREATE_INFO};
         blend.logicOpEnable = payload.logicOpEnable ? VK_TRUE : VK_FALSE;
         blend.logicOp = payload.logicOp;
         blend.attachmentCount = payload.colorAttachmentCount;
         blend.pAttachments = colorAttachments.empty() ? nullptr : colorAttachments.data();
 
-        // A GL program may have a tessellation EVALUATION stage and no CONTROL stage: GL 4.6 core
-        // 11.2.2 gives it a fixed-function pass-through instead. Vulkan has no such stage, and
-        // VUID-VkGraphicsPipelineCreateInfo-pStages-00730 requires both tessellation stages or
-        // neither - so the renderer synthesizes the pass-through GL describes and hands it in
-        // here (see ProgramFactory::GetOrCreatePassthroughTessControlStage).
-        //
-        // The refusal below is what keeps the half-tessellated shape away from the driver when
-        // there is no synthesized stage to add - because Mali does not reject it, it dereferences
-        // null INSIDE vkCreateGraphicsPipelines and takes the process down (SIGSEGV, fault addr
-        // 0x34, on Mali-G715/r54p2 and Mali-G925/r49p1 alike; Adreno and lavapipe merely render
-        // wrong). Returning VK_NULL_HANDLE routes this through the same path a driver rejection
-        // takes: the draw is skipped, nothing is memoised, and the process survives.
-        const Vector<VkPipelineShaderStageCreateInfo>* effectiveStages = payload.stages;
-        Vector<VkPipelineShaderStageCreateInfo> stagesWithPassthrough;
-        if (payload.passthroughTessControlStage.module != VK_NULL_HANDLE) {
-            stagesWithPassthrough = *payload.stages;
-            stagesWithPassthrough.push_back(payload.passthroughTessControlStage);
-            effectiveStages = &stagesWithPassthrough;
-        }
-        {
-            VkShaderStageFlags stagesPresent = 0;
-            for (const auto& stageInfo : *effectiveStages) {
-                stagesPresent |= stageInfo.stage;
-            }
-            const Bool hasTessControl = (stagesPresent & VK_SHADER_STAGE_TESSELLATION_CONTROL_BIT) != 0;
-            const Bool hasTessEval = (stagesPresent & VK_SHADER_STAGE_TESSELLATION_EVALUATION_BIT) != 0;
-            if (hasTessControl != hasTessEval) {
-                // Latched, and the latch is the point: a failed creation is deliberately never
-                // memoised (see GetOrCreatePipeline), so a program in this state re-enters here
-                // once per draw, every frame - and a refusal diagnostic that repeats per draw is
-                // noise, not a diagnostic. One line names the program; the draws it explains are
-                // all the same draw.
-                static Bool s_warnedHalfTessellatedPipeline = false;
-                if (!s_warnedHalfTessellatedPipeline) {
-                    s_warnedHalfTessellatedPipeline = true;
-                    MGLOG_E_ONCE("PipelineFactory::CreatePipeline: refusing a pipeline with %s tessellation stage and "
-                            "no %s stage (VUID-VkGraphicsPipelineCreateInfo-pStages-00730). programHash=0x%llx "
-                            "patchControlPoints=%u. Its draws are skipped; logged once.",
-                            hasTessEval ? "an evaluation" : "a control",
-                            hasTessEval ? "control" : "evaluation",
-                            static_cast<unsigned long long>(payload.programHash),
-                            payload.patchControlPoints);
-                }
-                return VK_NULL_HANDLE;
-            }
-        }
-
         VkGraphicsPipelineCreateInfo gpi{VK_STRUCTURE_TYPE_GRAPHICS_PIPELINE_CREATE_INFO};
-        gpi.stageCount = static_cast<Uint32>(effectiveStages->size());
-        gpi.pStages = effectiveStages->data();
+        gpi.stageCount = static_cast<Uint32>(payload.stages->size());
+        gpi.pStages = payload.stages->data();
         gpi.pVertexInputState = payload.vertexInputState;
         gpi.pInputAssemblyState = &ia;
-        gpi.pTessellationState =
-            payload.topology == VK_PRIMITIVE_TOPOLOGY_PATCH_LIST ? &tessellation : nullptr;
         gpi.pViewportState = &vpci;
         gpi.pRasterizationState = &raster;
         gpi.pMultisampleState = &ms;
@@ -576,13 +281,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         VkPipeline pipeline = VK_NULL_HANDLE;
         const VkResult result = vkCreateGraphicsPipelines(m_device, m_pipelineCache, 1, &gpi, nullptr, &pipeline);
-        // Loud, at MGLOG_F, and deliberately NOT latched. vkCreateGraphicsPipelines refusing a
-        // pipeline MobileGL assembled is a should-never-happen state, and the driver's own
-        // answer is VK_ERROR_UNKNOWN - no information at all - so this dump is the entire
-        // diagnosis. It is not an expected failure mode, so the one-shot rule that quiets W/E
-        // does not apply: while this is reachable it should keep saying so on every draw.
-        // GetOrCreatePipeline deliberately does not cache the failure, which is what makes that
-        // repetition happen; if the repetition ever needs to stop, fix the pipeline, not the log.
         if (result != VK_SUCCESS) {
             MGLOG_F("PipelineFactory::CreatePipeline failed: result=%s (%d) programHash=0x%llx vertexInputHash=0x%llx stageCount=%u topology=%s(%d) colorAttachmentCount=%u samples=%s(%d) subpass=%u",
                     VkResultToString(result),
@@ -613,36 +311,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             MGLOG_F("PipelineFactory::CreatePipeline vertex input: bindingCount=%u attributeCount=%u",
                     payload.vertexInputState->vertexBindingDescriptionCount,
                     payload.vertexInputState->vertexAttributeDescriptionCount);
-            // The driver's own answer is VK_ERROR_UNKNOWN, i.e. no information at all, so the only
-            // way to work out WHICH shader it choked on (the open sampler-array-in-struct
-            // investigation) is to name the modules. MGLOG_I, not _D: this is part of a
-            // should-never-happen report and must survive in the INFO-level builds that CTS
-            // actually runs against, alongside the MGLOG_F lines above.
-            if (payload.stageSpirvDigests) {
-                for (SizeT i = 0; i < payload.stageSpirvDigests->size(); ++i) {
-                    const auto& digest = (*payload.stageSpirvDigests)[i];
-                    MGLOG_I("PipelineFactory::CreatePipeline spirv[%zu]: stage=0x%x words=%u bytes=%zu "
-                            "hash=0x%llx",
-                            i, digest.stage, digest.wordCount,
-                            static_cast<SizeT>(digest.wordCount) * sizeof(Uint32),
-                            static_cast<unsigned long long>(digest.hash));
-                }
-            } else {
-                MGLOG_I("PipelineFactory::CreatePipeline: no SPIR-V digests attached to the payload");
-            }
-            if (payload.stages) {
-                for (SizeT i = 0; i < payload.stages->size(); ++i) {
-                    const auto& stage = (*payload.stages)[i];
-                    // VkShaderModule is a non-dispatchable handle: a pointer on 64-bit but a
-                    // plain uint64_t on 32-bit ABIs, where a cast to const void* is ill-formed
-                    // (broke the armeabi-v7a build). Print it as the 64-bit value it is.
-                    MGLOG_I("PipelineFactory::CreatePipeline stage[%zu]: stage=0x%x module=0x%llx entry=%s "
-                            "specialization=%d",
-                            i, static_cast<Uint32>(stage.stage),
-                            static_cast<unsigned long long>(reinterpret_cast<Uint64>(stage.module)),
-                            stage.pName ? stage.pName : "(null)", stage.pSpecializationInfo ? 1 : 0);
-                }
-            }
             for (Uint32 i = 0; i < payload.colorAttachmentCount; ++i) {
                 const auto& attachment = payload.colorBlendAttachments[i];
                 MGLOG_F("PipelineFactory::CreatePipeline colorAttachment[%u]: blend=%d colorWriteMask=0x%x srcColor=%d dstColor=%d colorOp=%d srcAlpha=%d dstAlpha=%d alphaOp=%d",

MobileGL/MG_Backend/DirectVulkan/Renderer/PipelineFactory.h

@@ -14,16 +14,6 @@
 #include <Includes.h>
 
 namespace MobileGL::MG_Backend::DirectVulkan {
-    // Enough of a fingerprint to identify the exact module the driver rejected without keeping the
-    // SPIR-V alive for every program in the cache: a driver that answers VK_ERROR_UNKNOWN tells us
-    // nothing, so the log has to carry the shader's identity itself. Diagnostic only - never part
-    // of any pipeline or program hash.
-    struct ShaderStageSpirvDigest {
-        Uint32 stage = 0; // VkShaderStageFlagBits
-        Uint32 wordCount = 0;
-        Uint64 hash = 0;
-    };
-
     class PipelineFactory {
     public:
         using HashType = Uint64;
@@ -35,62 +25,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             HashType vertexInputHash = 0;
             VkPipelineLayout pipelineLayout = VK_NULL_HANDLE;
             VkRenderPass renderPass = VK_NULL_HANDLE;
-#if MOBILEGL_BUILD_DISAGGREGATED
-            // Nonzero is an exact, renderer-lifetime compatibility identity.
-            // renderPass remains the valid creation handle, not the cache key.
-            Uint64 wireRenderPassCompatibilityId = 0;
-#endif
             Uint32 colorAttachmentCount = 1;
             VkSampleCountFlagBits rasterizationSamples = VK_SAMPLE_COUNT_1_BIT;
-            // glEnable(GL_SAMPLE_SHADING) + glMinSampleShading, which Vulkan bakes into the
-            // pipeline rather than exposing as dynamic state - so both are part of the pipeline's
-            // identity and both are hashed. The renderer leaves the enable false unless the
-            // device's sampleRateShading feature was enabled
-            // (VUID-VkPipelineMultisampleStateCreateInfo-sampleShadingEnable-00784).
-            Bool sampleShadingEnable = false;
-            Float minSampleShading = 0.0f;
-            // glEnable(GL_SAMPLE_MASK) + glSampleMaski, the fixed-function coverage mask, already
-            // reduced to what GL says this draw gets (VulkanRenderer::ResolveEffectiveSampleMask:
-            // all-ones unless the target is genuinely multisampled). Pipeline state like the two
-            // above - Vulkan has no dynamic sample mask before VK_EXT_extended_dynamic_state3 -
-            // so it is hashed with them, and all-ones has to keep producing the pipeline a null
-            // pSampleMask always did.
-            //
-            // TWO words, though GL only ever fills the first. GL_MAX_SAMPLE_MASK_WORDS is clamped
-            // to 1 on both backends, so glSampleMaski writes index 0 and nothing else - but the
-            // count Vulkan READS is ceil(rasterizationSamples / 32), which is 2 on a 64-sample
-            // target, and GetAdvertisedMaxSamples does not cap the driver's sample count. A
-            // single Uint32 here let such a pipeline read one word past the member (the next
-            // struct field). The second word is all-ones: full coverage for samples 32..63, which
-            // is the only honest answer when GL has no state describing them.
-            Uint32 sampleMask[2] = {0xffffffffu, 0xffffffffu};
             Uint32 subpass = 0;
             VkPrimitiveTopology topology = VK_PRIMITIVE_TOPOLOGY_TRIANGLE_LIST;
             Bool primitiveRestartEnable = false;
-            // GL_PATCH_VERTICES; only read for a PATCH_LIST topology.
-            Uint32 patchControlPoints = 3;
-            // ProgramFactory::ComputePassthroughTessControlKey of the synthesized pass-through
-            // tessellation control stage below, or 0 when this pipeline has none. Hashed, because
-            // the levels glPatchParameterfv set are compiled INTO that module and are not a
-            // function of the program or of patchControlPoints - see the note on
-            // passthroughTessControlStage.
-            Uint64 passthroughTessControlKey = 0;
-            // How many of ARB_viewport_array's viewports this pipeline rasterizes into. 1 for
-            // every program that never assigns gl_ViewportIndex, which is all of them outside the
-            // conformance suite - the wide shape costs a longer vkCmdSetViewport/Scissor per state
-            // change and can cost hardware fast paths, so it is opt-in per program. Baked into the
-            // pipeline (viewportCount is not dynamic without VK_EXT_extended_dynamic_state) and
-            // therefore hashed; the DYNAMIC viewport/scissor arrays the draw pushes must have
-            // exactly this many elements (VUID-vkCmdDraw-viewportCount-03417/-03418).
-            Uint32 viewportCount = 1;
             VkPolygonMode polygonMode = VK_POLYGON_MODE_FILL;
             VkCullModeFlags cullMode = VK_CULL_MODE_BACK_BIT;
             VkFrontFace frontFace = VK_FRONT_FACE_CLOCKWISE;
-            // GL's provoking vertex, baked into the pipeline (VK_EXT_provoking_vertex). It selects
-            // which vertex a flat varying takes AND the vertex order transform feedback records for
-            // strips/fans, so it is part of the pipeline's identity, not dynamic state. Defaults to
-            // Vulkan's own convention, which is what a device without the extension gets.
-            VkProvokingVertexModeEXT provokingVertexMode = VK_PROVOKING_VERTEX_MODE_FIRST_VERTEX_EXT;
             Bool depthTestEnable = false;
             Bool depthWriteEnable = false;
             Bool depthBiasEnable = false;
@@ -107,26 +49,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             VkStencilOp backStencilPassOp = VK_STENCIL_OP_KEEP;
             VkStencilOp backStencilDepthFailOp = VK_STENCIL_OP_KEEP;
             VkCompareOp backStencilCompareOp = VK_COMPARE_OP_ALWAYS;
-            // The fragment module writes gl_FragDepth (SPIR-V DepthReplacing); exempts the
-            // pipeline from the blended depth-write quirk (see ShouldSuppressDepthWrite).
-            Bool fragmentReplacesDepth = false;
             Array<VkPipelineColorBlendAttachmentState, kMaxColorAttachments> colorBlendAttachments{};
             const Vector<VkPipelineShaderStageCreateInfo>* stages = nullptr;
-            // The tessellation control stage this renderer synthesized for a program that has
-            // an evaluation stage and none of its own (GL 4.6 core 11.2.2 gives such a program a
-            // fixed-function pass-through; Vulkan has no such thing and
-            // VUID-VkGraphicsPipelineCreateInfo-pStages-00730 forbids the half-tessellated
-            // pipeline outright). Appended to `stages` at creation. A null module means the
-            // renderer could not build one, and CreatePipeline refuses the pipeline - the same
-            // refusal it applies when `stages` itself is half-tessellated.
-            //
-            // NOT hashed directly: it is a pure function of the program, of patchControlPoints and
-            // of the default tessellation levels - the first two of which ComputeHash already
-            // mixes in, and the third of which arrives through passthroughTessControlKey above.
-            VkPipelineShaderStageCreateInfo passthroughTessControlStage{};
             const VkPipelineVertexInputStateCreateInfo* vertexInputState = nullptr;
-            // Diagnostic only; may be null. Read solely from the pipeline-creation failure path.
-            const Vector<ShaderStageSpirvDigest>* stageSpirvDigests = nullptr;
         };
 
         explicit PipelineFactory(VkDevice device, const VulkanRendererConfig& config);
@@ -137,69 +62,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkPipeline GetOrCreatePipeline(const PipelineCreatePayload& payload);
         void DestroyAll();
 
-        // Frame boundary hook: ages the pipeline cache and destroys long-unused entries
-        // (their command buffers retired many frames ago), mirroring
-        // VkRenderPassManager::OnPresent's sweep. Returns the number of pipelines
-        // destroyed so the caller can drop any memoized VkPipeline handle.
-        Uint32 OnFrameBoundary();
-        // Destroys every cached pipeline hashed on one of `renderPasses`. Only safe
-        // when the caller guarantees GPU idleness for them - the render-pass manager
-        // calls this (via the renderer) for passes its own >1024-boundary-idle sweep
-        // just evicted, and a pipeline hashed on those handles is only ever bound by
-        // draws that also hit the render-pass entries. Also closes the handle-recycling
-        // hazard: a recycled VkRenderPass value must never serve a stale pipeline.
-        // Batched: one cache scan regardless of how many passes died in the sweep.
-        // Returns the number destroyed (callers invalidate memos when non-zero).
-        Uint32 EvictByRenderPasses(const Vector<VkRenderPass>& renderPasses);
-        // Destroys every cached pipeline built from the program with content hash
-        // `programHash`. Called from the ProgramFactory eviction path, which proves the
-        // same >1024-boundary idleness (the program's pipelines are only bound by draws
-        // that stamp its factory entry). Returns the number destroyed.
-        Uint32 EvictByProgramHash(HashType programHash);
-
-        // Driver quirk: suppress depth writes on accumulation-blended pipelines. Multi-pass
-        // depth-equality rendering (a blended prepass writes depth that later passes re-test
-        // with an equality-inclusive compare on the re-rasterized geometry) requires
-        // cross-pipeline position invariance that some mobile compilers do not provide, even
-        // with the SPIR-V Invariant decoration; whole primitives then drop out of the later
-        // passes. Only MIN/MAX extremum blends are stripped - the signature of such a
-        // chain's depth-bounds pass (MC 26.3 OIT), and per a fixture-wide trace sweep the
-        // only depth-writing shape the chain actually uses - so every other blend
-        // (sorted-transparency "over" like vanilla MC water, additive glows, ...) keeps
-        // its depth writes. Set at renderer initialization based on the active driver.
-        static void SetSuppressBlendedDepthWrite(Bool enabled);
-        static Bool IsSuppressBlendedDepthWriteEnabled() { return s_suppressBlendedDepthWrite; }
-        // Device gate for the quirk: ForceOn/ForceOff bypass detection, Auto enables it on
-        // the known-affected vendor (Qualcomm).
-        static Bool ShouldSuppressBlendedDepthWriteForDevice(MG_Config::QuirkOverride quirkOverride,
-                                                             Uint32 vendorId);
-        // Pure per-pipeline strip decision (exempts gl_FragDepth writers, masked-out and
-        // non-accumulation blends); combined with the device flag in CreatePipeline. Static
-        // and payload-only so tests can pin the contract without a VkDevice.
-        static Bool ShouldSuppressDepthWrite(const PipelineCreatePayload& payload);
-
     private:
-        struct PipelineCacheEntry {
-            VkPipeline pipeline = VK_NULL_HANDLE;
-            // The hashed inputs the eviction paths key on: programHash ties the entry to
-            // its ProgramFactory entry, renderPass records the exact handle the hash
-            // folded in (the hash is one-way, so targeted eviction needs them verbatim).
-            HashType programHash = 0;
-            VkRenderPass renderPass = VK_NULL_HANDLE;
-            // Frame-boundary counter value of the last GetOrCreatePipeline hit; drives
-            // cache eviction (see OnFrameBoundary).
-            Uint64 lastUsedFrame = 0;
-        };
-
         VkPipeline CreatePipeline(const PipelineCreatePayload& payload) const;
 
         VkDevice m_device = VK_NULL_HANDLE;
         const VulkanRendererConfig& m_config;
         VkPipelineCache m_pipelineCache = VK_NULL_HANDLE;
-        UnorderedMap<HashType, PipelineCacheEntry> m_cache;
-        // Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
-        Uint64 m_frameCounter = 0;
+        UnorderedMap<HashType, VkPipeline> m_cache;
         static inline XXH64_state_t* m_hashState = XXH64_createState();
-        static inline Bool s_suppressBlendedDepthWrite = false;
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/ProgramFactory.h

@@ -9,8 +9,7 @@
 #pragma once
 
 #include "../VkIncludes.h"
-#include "PipelineFactory.h"
-#include "MagmaProgramSource.h"
+#include "MG_State/GLState/ProgramState/ProgramObject.h"
 #include "MG_State/GLState/ProgramState/ShaderObject.h"
 #include "MG_State/GLState/TextureState/TextureEnum.h"
 
@@ -33,13 +32,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             CombinedImageSampler,
             UniformTexelBuffer,
             StorageBuffer,
-            StorageImage,
-            // GLSL `imageBuffer` - a buffer texture reached through an IMAGE unit rather than a
-            // texture unit. Vulkan spells it VK_DESCRIPTOR_TYPE_STORAGE_TEXEL_BUFFER, which is a
-            // VkBufferView like UniformTexelBuffer and not a VkImageView like StorageImage: it is
-            // the one image uniform whose descriptor is a buffer. Appended, never inserted -
-            // DescriptorKeyHash mixes the enumerator's value.
-            StorageTexelBuffer
+            StorageImage
         };
 
         enum class CompileOptionBit : Uint {
@@ -49,129 +42,31 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             SurfaceRotate90 = 1 << 2,
             SurfaceRotate180 = 1 << 3,
             SurfaceRotate270 = 1 << 4,
-            // Rewrites the fragment stage's implicit-LOD image samples to explicit LOD 0.
-            // Only ever set for a draw whose every sampler binding is clamped to a single mip
-            // level, which makes the two forms produce identical texels (the implicit lambda is
-            // clamped into [minLod, maxLod] = [0, 0] regardless of derivatives or bias).
-            ExplicitLod0Sampling = 1 << 5,
-            // Decorates the last vertex-processing stage's captured varyings with
-            // XfbBuffer/XfbStride/Offset (VK_EXT_transform_feedback). Set only for draws
-            // recorded while GL transform feedback is active, so plain draws keep the
-            // undecorated variant.
-            XfbCapture = 1 << 6,
-            // Rewrites the fragment stage's gl_FragCoord reads to GL's bottom-left window
-            // origin. Vulkan's gl_FragCoord.y IS the framebuffer row being written, and the
-            // default framebuffer's image is stored in display (top-left) order, so a shader
-            // that reads gl_FragCoord there sees `height - y_GL`. Set together with
-            // PositionYFlip (the two are the same fact about the same draws) except under a
-            // quarter turn, which this renderer does not convert rectangles for either.
-            FragCoordYFlip = 1 << 7,
-            // Replaces the vertex stage's gl_BaseVertex reads with zero. GL defines the builtin
-            // as zero for every drawing command that has no baseVertex parameter - all the
-            // DrawArrays forms - while Vulkan's BaseVertex reports firstVertex there. Set only
-            // for a non-indexed draw whose program actually reads the builtin, so nothing else
-            // acquires a second program/pipeline variant. See ZeroBaseVertexPass.
-            ZeroBaseVertex = 1 << 8,
         };
         using CompileOptionFlags = Flags<CompileOptionBit>;
         using HashType = Uint64;
 
-        // The gl_PerVertex members a pass-through tessellation control stage may have to carry,
-        // in the order glslang declares them - which is the order a redeclaration must use.
-        // Which of them exist is a function of the neighbouring stage's GLSL VERSION
-        // (gl_CullDistance joins the block at #version 450), so the mask is read off that
-        // stage's SPIR-V rather than assumed. See ReflectPerVertexInputMembers.
-        enum class PerVertexMemberBit : Uint32 {
-            Position = 1u << 0,
-            PointSize = 1u << 1,
-            ClipDistance = 1u << 2,
-            CullDistance = 1u << 3,
-        };
-        // What a program parsed below #version 450 carries, and the fallback when a module's
-        // block cannot be read.
-        static constexpr Uint32 kDefaultPerVertexMembers =
-            static_cast<Uint32>(PerVertexMemberBit::Position) | static_cast<Uint32>(PerVertexMemberBit::PointSize) |
-            static_cast<Uint32>(PerVertexMemberBit::ClipDistance);
-
-        struct UpdateAfterBindLimits {
-            Bool enabled = false;
-            Uint32 maxPerStageSamplers = 0;
-            Uint32 maxPerStageUniformBuffers = 0;
-            Uint32 maxPerStageStorageBuffers = 0;
-            Uint32 maxPerStageSampledImages = 0;
-            Uint32 maxPerStageStorageImages = 0;
-            Uint32 maxPerStageResources = 0;
-            Uint32 maxSetSamplers = 0;
-            Uint32 maxSetUniformBuffers = 0;
-            Uint32 maxSetUniformBuffersDynamic = 0;
-            Uint32 maxSetStorageBuffers = 0;
-            Uint32 maxSetStorageBuffersDynamic = 0;
-            Uint32 maxSetSampledImages = 0;
-            Uint32 maxSetStorageImages = 0;
-        };
-
         struct VkProgramObject {
             static constexpr Uint32 kMaxVertexInputLocations = 32;
 
             HashType hash = 0;
             Vector<VkPipelineShaderStageCreateInfo> stages;
             Vector<VkShaderModule> modules;
-            // Parallel to stages; identifies the exact module bytes handed to the driver when a
-            // pipeline creation fails. Sixteen bytes per stage instead of keeping the SPIR-V.
-            Vector<ShaderStageSpirvDigest> stageSpirvDigests;
 
             // Layout data (previously in separate VkProgramLayout)
             VkDescriptorSetLayout descriptorSetLayout = VK_NULL_HANDLE;
-            // True only when this layout passed every descriptor-indexing feature and
-            // update-after-bind limit gate at reflection time. It controls both the
-            // layout/binding flags and the pool class used by UniformManager.
-            Bool usesUpdateAfterBind = false;
             VkPipelineLayout pipelineLayout = VK_NULL_HANDLE;
             Vector<DescriptorBindingKind> bindingKinds;
-            // The bindings this program actually declares, ascending. bindingKinds is sized to the
-            // 256-binding cap while a real GL program uses 1-8, so the per-draw descriptor walk was
-            // scanning 256 slots to find a handful. MUST stay ascending: Vulkan consumes
-            // pDynamicOffsets in binding order and the writer pushes them in iteration order, so an
-            // unordered list would silently mis-pair dynamic offsets with their uniform blocks.
-            Vector<Uint32> activeBindings;
             Vector<Uint32> dynamicBindings;
             Vector<Int> uniformBlockIndexByBinding;
-            // Descriptor count per binding (1 except for a descriptor ARRAY - a UBO or storage
-            // block instance array, an image uniform array or a sampler uniform array - each of
-            // which occupies one binding with descriptorCount = N).
-            Vector<Uint16> bindingDescriptorCounts;
-            // Per-element GL uniform block indices for arrayed UBO bindings (count > 1);
-            // element 0 of a non-arrayed binding stays in uniformBlockIndexByBinding.
-            UnorderedMap<Uint32, Vector<Int>> arrayedUniformBlockIndicesByBinding;
             Vector<String> samplerNameByBinding;
             Vector<Int> samplerUniformLocationByBinding;
             Vector<TextureTarget> samplerTextureTargetByBinding;
             Vector<SamplerNumericDomain> samplerNumericDomainByBinding;
-            // Shared by StorageImage and StorageTexelBuffer bindings: a binding is one kind or
-            // the other, never both, and both need exactly the same thing - the format the
-            // shader declared, so the per-draw resolve can tell a typed declaration from a
-            // formatless one. Kept as one pair rather than two so the move operations below
-            // cannot drift out of sync with a field that only one kind populates.
             Vector<VkFormat> storageImageFormatByBinding;
             Vector<Bool> storageImageUsesBindingFormatByBinding;
             Vector<String> storageBlockNameByBinding;
             Vector<Int> storageBlockIndexByBinding;
-            // Set once during ReflectLayout so the per-draw path can skip the whole
-            // storage-image preparation for the overwhelming majority of programs.
-            Bool hasStorageImages = false;
-            // Something about this program's descriptors could not be resolved - an opaque
-            // uniform array whose elements have no addressable uniform locations (the
-            // multi-dimensional case), or a binding remap that failed outright. The binding
-            // STAYS DECLARED in the descriptor set layout; declining is done here, by refusing
-            // every draw, and BindProgramUniformBuffers returns false so the draw setup skips
-            // the draw exactly as it does for any other bind failure.
-            //
-            // Keeping the layout intact is the load-bearing half. Shrinking it instead - which
-            // is what the first cut of this did - leaves the shader reading a descriptor the
-            // layout never declared, and lavapipe segfaults on that inside PIPELINE CREATION,
-            // in a JIT worker thread, before any draw runs where a refusal could help. The
-            // reason was logged once at MGLOG_I when the descriptor was declined.
-            Bool declinedDescriptors = false;
             Int globalUboBinding = -1;
             Uint32 activeVertexInputLocationMask = 0;
             Array<GLenum, kMaxVertexInputLocations> vertexInputTypes{};
@@ -180,76 +75,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             ShaderStage rasterizationProducerStage = ShaderStage::Unknown;
             Uint32 producerOutputComponentCount = 0;
             Uint32 fragmentInputComponentCount = 0;
-            // The fragment module declares the DepthReplacing execution mode (writes
-            // gl_FragDepth); shader-computed depth is immune to the cross-pipeline
-            // position-invariance quirk (see PipelineFactory::ShouldSuppressDepthWrite).
-            Bool fragmentReplacesDepth = false;
-            // The vertex module declares the BaseVertex builtin. Selects the ZeroBaseVertex
-            // program variant for non-indexed draws, and is deliberately a property of the
-            // PROGRAM rather than of the variant: the zeroed variant leaves the variable
-            // declared, so both variants answer the same and the draw path can ask either.
-            Bool readsBaseVertexBuiltin = false;
-            // Some pre-rasterization stage assigns gl_ViewportIndex. Its pipeline declares
-            // viewportCount = the renderer's rasterizable viewport count instead of 1, and its
-            // draws push the whole viewport/scissor array; every other program keeps the
-            // single-viewport fast path untouched. Part of the program's identity (folded into
-            // the pipeline hash through programHash), so no memo can serve the wrong shape.
-            Bool writesViewportIndexBuiltin = false;
-            // This program has a tessellation EVALUATION stage and no tessellation CONTROL
-            // stage. GL allows that (4.6 core 11.2.2: with no control shader the input patch
-            // is passed through unmodified, the output patch size is PATCH_VERTICES, and the
-            // levels come from the PATCH_DEFAULT_*_LEVEL state); Vulkan does not - either both
-            // tessellation stages are present or neither
-            // (VUID-VkGraphicsPipelineCreateInfo-pStages-00730). So the draw path has to supply
-            // the pass-through stage GL describes; see GetOrCreatePassthroughTessControlStage.
-            // True when this program was built AS a transform-feedback capture variant but its
-            // last pre-rasterization module does NOT carry the Xfb execution mode - so the
-            // renderer must decline the capture span instead of issuing
-            // vkCmdBeginTransformFeedbackEXT against it
-            // (VUID-vkCmdBeginTransformFeedbackEXT-None-04128).
-            //
-            // Two ways to get here, and neither is visible from GL state, which is all
-            // BeginXfbCaptureForDraw otherwise consults: the clip/XFB validation backstop had to
-            // rewind past the capture decoration, or XfbCaptureDecoratePass resolved none of the
-            // requested varyings and returned without changing anything (its own MGLOG_E path)
-            // while its runner still reported success. Both used to ship a non-Xfb module under
-            // an Xfb-flagged cache entry - the flag and the layout are part of the program cache
-            // key, so it was sticky for every later captured draw of the program, not a glitch.
-            Bool xfbCaptureDeclined = false;
-            // The program has a tessellation or geometry module declaring TessellationPointSize /
-            // GeometryPointSize on a device whose shaderTessellationAndGeometryPointSize feature
-            // is off, so a pipeline built from it is invalid usage
-            // (VUID-RuntimeSpirv-PointSize-06439). Its draws are refused in SetupDraw rather than
-            // handed to the driver - the same contract PipelineFactory's half-tessellated refusal
-            // implements one level up, and the counterpart of the DirectGLES arm that reports a
-            // driver with neither point-size extension by name.
-            //
-            // Sticky by construction, which is what makes ONE log line honest: the flag lives on
-            // the cache entry, so every later draw of the same program variant reads the same
-            // answer instead of re-deciding it.
-            Bool pointSizeCapabilityUnsupported = false;
-            Bool needsPassthroughTessControl = false;
-            // ...and the pass-through this renderer can synthesize carries gl_Position and
-            // nothing else, so it is only correct when the evaluation stage's inputs are
-            // built-ins. A user-defined varying would arrive at the evaluation stage
-            // UNWRITTEN once a control stage sits between it and the vertex stage, which is
-            // silently wrong pixels rather than a crash - so those programs are declined
-            // instead (PipelineFactory::CreatePipeline refuses the pipeline and the draw is
-            // skipped). See ReflectPassthroughTessControlNeed.
-            Bool passthroughTessControlEmulatable = false;
-            // Which gl_PerVertex members the evaluation stage's `in gl_PerVertex gl_in[]` block
-            // actually carries, as a PerVertexMemberBit mask read off its SPIR-V. The synthesized
-            // control stage has to redeclare the SAME shape: glslang appends gl_CullDistance to
-            // that block from #version 450 upward, so a 450/460 program - and every ESSL program,
-            // which the source processor rewrites to "#version 460 core" - carries four members
-            // where a 430 program carries three. A fixed three-member pass-through fed the
-            // evaluation stage a differently-shaped block, which is the black-frame-no-error case
-            // this whole family is written around.
-            Uint32 passthroughPerVertexMembers = 0;
-            // Frame-boundary counter value of the last GetOrCreateProgram hit; drives
-            // cache eviction (see OnFrameBoundary). Mutable: the draw snapshot's memoised
-            // entry pointer re-stamps use through a const reference (StampProgramUse).
-            mutable Uint64 lastUsedFrame = 0;
 
             static inline VkDevice s_device = VK_NULL_HANDLE;
 
@@ -260,23 +85,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 hash = other.hash;
                 stages = std::move(other.stages);
                 modules = std::move(other.modules);
-                // Must travel with `modules`: these digests name the SPIR-V those exact
-                // shader modules were built from, and the pipeline-failure diagnostics
-                // print the two together. Leaving it behind used to merely lose the
-                // digests on a rehash; now that the cache is a robin-hood table, insertion
-                // SWAPS two entries, and a field that no move touches stays behind in the
-                // slot - pairing one program's modules with another program's digests, so
-                // a pipeline failure would be reported against the wrong SPIR-V.
-                stageSpirvDigests = std::move(other.stageSpirvDigests);
                 descriptorSetLayout = other.descriptorSetLayout;
-                usesUpdateAfterBind = other.usesUpdateAfterBind;
                 pipelineLayout = other.pipelineLayout;
                 bindingKinds = std::move(other.bindingKinds);
-                activeBindings = std::move(other.activeBindings);
                 dynamicBindings = std::move(other.dynamicBindings);
                 uniformBlockIndexByBinding = std::move(other.uniformBlockIndexByBinding);
-                bindingDescriptorCounts = std::move(other.bindingDescriptorCounts);
-                arrayedUniformBlockIndicesByBinding = std::move(other.arrayedUniformBlockIndicesByBinding);
                 samplerNameByBinding = std::move(other.samplerNameByBinding);
                 samplerUniformLocationByBinding = std::move(other.samplerUniformLocationByBinding);
                 samplerTextureTargetByBinding = std::move(other.samplerTextureTargetByBinding);
@@ -286,8 +99,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                     std::move(other.storageImageUsesBindingFormatByBinding);
                 storageBlockNameByBinding = std::move(other.storageBlockNameByBinding);
                 storageBlockIndexByBinding = std::move(other.storageBlockIndexByBinding);
-                hasStorageImages = other.hasStorageImages;
-                declinedDescriptors = other.declinedDescriptors;
                 globalUboBinding = other.globalUboBinding;
                 activeVertexInputLocationMask = other.activeVertexInputLocationMask;
                 vertexInputTypes = other.vertexInputTypes;
@@ -296,32 +107,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 rasterizationProducerStage = other.rasterizationProducerStage;
                 producerOutputComponentCount = other.producerOutputComponentCount;
                 fragmentInputComponentCount = other.fragmentInputComponentCount;
-                fragmentReplacesDepth = other.fragmentReplacesDepth;
-                readsBaseVertexBuiltin = other.readsBaseVertexBuiltin;
-                writesViewportIndexBuiltin = other.writesViewportIndexBuiltin;
-                needsPassthroughTessControl = other.needsPassthroughTessControl;
-                passthroughTessControlEmulatable = other.passthroughTessControlEmulatable;
-                passthroughPerVertexMembers = other.passthroughPerVertexMembers;
-                lastUsedFrame = other.lastUsedFrame;
                 other.hash = 0;
                 other.descriptorSetLayout = VK_NULL_HANDLE;
-                other.usesUpdateAfterBind = false;
                 other.pipelineLayout = VK_NULL_HANDLE;
-                other.hasStorageImages = false;
-                other.declinedDescriptors = false;
                 other.globalUboBinding = -1;
                 other.activeVertexInputLocationMask = 0;
                 other.activeFragmentOutputLocationMask = 0;
                 other.rasterizationProducerStage = ShaderStage::Unknown;
                 other.producerOutputComponentCount = 0;
                 other.fragmentInputComponentCount = 0;
-                other.fragmentReplacesDepth = false;
-                other.readsBaseVertexBuiltin = false;
-                other.writesViewportIndexBuiltin = false;
-                other.needsPassthroughTessControl = false;
-                other.passthroughTessControlEmulatable = false;
-                other.passthroughPerVertexMembers = 0;
-                other.lastUsedFrame = 0;
             }
             VkProgramObject& operator=(VkProgramObject&& other) noexcept {
                 if (this == &other) {
@@ -331,16 +125,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 hash = other.hash;
                 stages = std::move(other.stages);
                 modules = std::move(other.modules);
-                stageSpirvDigests = std::move(other.stageSpirvDigests); // travels with `modules` - see the move ctor
                 descriptorSetLayout = other.descriptorSetLayout;
-                usesUpdateAfterBind = other.usesUpdateAfterBind;
                 pipelineLayout = other.pipelineLayout;
                 bindingKinds = std::move(other.bindingKinds);
-                activeBindings = std::move(other.activeBindings);
                 dynamicBindings = std::move(other.dynamicBindings);
                 uniformBlockIndexByBinding = std::move(other.uniformBlockIndexByBinding);
-                bindingDescriptorCounts = std::move(other.bindingDescriptorCounts);
-                arrayedUniformBlockIndicesByBinding = std::move(other.arrayedUniformBlockIndicesByBinding);
                 samplerNameByBinding = std::move(other.samplerNameByBinding);
                 samplerUniformLocationByBinding = std::move(other.samplerUniformLocationByBinding);
                 samplerTextureTargetByBinding = std::move(other.samplerTextureTargetByBinding);
@@ -350,8 +139,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                     std::move(other.storageImageUsesBindingFormatByBinding);
                 storageBlockNameByBinding = std::move(other.storageBlockNameByBinding);
                 storageBlockIndexByBinding = std::move(other.storageBlockIndexByBinding);
-                hasStorageImages = other.hasStorageImages;
-                declinedDescriptors = other.declinedDescriptors;
                 globalUboBinding = other.globalUboBinding;
                 activeVertexInputLocationMask = other.activeVertexInputLocationMask;
                 vertexInputTypes = other.vertexInputTypes;
@@ -360,32 +147,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 rasterizationProducerStage = other.rasterizationProducerStage;
                 producerOutputComponentCount = other.producerOutputComponentCount;
                 fragmentInputComponentCount = other.fragmentInputComponentCount;
-                fragmentReplacesDepth = other.fragmentReplacesDepth;
-                readsBaseVertexBuiltin = other.readsBaseVertexBuiltin;
-                writesViewportIndexBuiltin = other.writesViewportIndexBuiltin;
-                needsPassthroughTessControl = other.needsPassthroughTessControl;
-                passthroughTessControlEmulatable = other.passthroughTessControlEmulatable;
-                passthroughPerVertexMembers = other.passthroughPerVertexMembers;
-                lastUsedFrame = other.lastUsedFrame;
                 other.hash = 0;
                 other.descriptorSetLayout = VK_NULL_HANDLE;
-                other.usesUpdateAfterBind = false;
                 other.pipelineLayout = VK_NULL_HANDLE;
-                other.hasStorageImages = false;
-                other.declinedDescriptors = false;
                 other.globalUboBinding = -1;
                 other.activeVertexInputLocationMask = 0;
                 other.activeFragmentOutputLocationMask = 0;
                 other.rasterizationProducerStage = ShaderStage::Unknown;
                 other.producerOutputComponentCount = 0;
                 other.fragmentInputComponentCount = 0;
-                other.fragmentReplacesDepth = false;
-                other.readsBaseVertexBuiltin = false;
-                other.writesViewportIndexBuiltin = false;
-                other.needsPassthroughTessControl = false;
-                other.passthroughTessControlEmulatable = false;
-                other.passthroughPerVertexMembers = 0;
-                other.lastUsedFrame = 0;
                 return *this;
             }
 
@@ -412,171 +182,27 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 }
                 modules.clear();
                 stages.clear();
-                stageSpirvDigests.clear(); // the modules they describe are gone
             }
         };
 
-        // Notified when the OnFrameBoundary sweep destroys an aged-out cache entry,
-        // carrying the entry's content hash and the VkDescriptorSetLayout it owned.
-        // Dependent caches (compute pipelines, PipelineFactory entries, UniformManager's
-        // per-layout descriptor sets) must purge in the same step: after vkDestroy the
-        // layout handle value may be recycled for an unrelated layout, and the program
-        // hash may be re-inserted by a later rebuild of the same content.
-        class IEvictionObserver {
-        public:
-            virtual ~IEvictionObserver() = default;
-            virtual void OnProgramEvicted(HashType programHash, VkDescriptorSetLayout descriptorSetLayout) = 0;
-        };
-
-        // How this factory's compute modules implement GL_KHR_shader_subgroup. Computed
-        // once at renderer initialization (SubgroupSupportPolicy.h + the device's
-        // subgroup properties) so lowering can never disagree with the advertised
-        // capabilities. Native subgroup operations always execute natively; the two
-        // repair passes patch modules AROUND them, and the emulation only replaces them
-        // on opted-in devices with no subgroup support at all.
-        struct SubgroupLoweringPolicy {
-            Bool emulateSubgroups = false;      // MOBILEGL_MAGMA_EMULATE_SUBGROUP, no-native-support devices
-            Bool fixIterationRPSubgroupScratch = false; // patch iterationRP's under-declared scratch
-            Bool fixIterationRPBarrier = false; // repair Program 203's shared-scratch race
-            Bool deriveNumSubgroups = false;    // repair the NumSubgroups builtin
-            Bool requireFullSubgroups = false;  // computeFullSubgroups enabled on the device
-            Uint32 nativeSubgroupSize = 0;
-            // Full-subgroup launches are bounded by this device limit; a dispatch whose
-            // workgroup needs more subgroups than this cannot request the flag.
-            Uint32 maxComputeWorkgroupSubgroups = 0;
-            // VkPhysicalDeviceLimits::maxComputeSharedMemorySize; bounds the scratch the
-            // emulation pass may add (0 falls back to the Vulkan minimum, 16384).
-            Uint32 maxComputeSharedMemoryBytes = 0;
-        };
-
-        explicit ProgramFactory(VkDevice device, const VulkanRendererConfig& config, Uint32 maxBindings,
-                                Bool shaderDrawParametersEnabled,
-                                Bool unformattedFloatStorageImagesEnabled,
-                                Bool tessellationAndGeometryPointSizeEnabled,
-                                Bool enableSpirvValidation,
-                                UpdateAfterBindLimits updateAfterBindLimits,
-                                SubgroupLoweringPolicy subgroupPolicy)
+        explicit ProgramFactory(VkDevice device, const VulkanRendererConfig& config, Uint32 maxBindings = 16,
+                                Bool shaderDrawParametersEnabled = false,
+                                Bool unformattedFloatStorageImagesEnabled = false)
             : m_device(device), m_maxBindings(maxBindings), m_config(config),
               m_shaderDrawParametersEnabled(shaderDrawParametersEnabled),
-              m_unformattedFloatStorageImagesEnabled(unformattedFloatStorageImagesEnabled),
-              m_tessellationAndGeometryPointSizeEnabled(tessellationAndGeometryPointSizeEnabled),
-              m_enableSpirvValidation(enableSpirvValidation),
-              m_updateAfterBindLimits(updateAfterBindLimits),
-              m_subgroupPolicy(subgroupPolicy) {
+              m_unformattedFloatStorageImagesEnabled(unformattedFloatStorageImagesEnabled) {
             VkProgramObject::s_device = device;
         }
-        // Destroys the pass-through tessellation control modules. Runs while the device is
-        // still alive for the same reason ~VkProgramObject's does: this factory outlives
-        // nothing that owns the device.
-        ~ProgramFactory();
+        ~ProgramFactory() = default;
         ProgramFactory(const ProgramFactory&) = delete;
 
-        HashType ComputeHash(const MagmaProgramSource& program, CompileOptionFlags flags) const;
+        HashType ComputeHash(const MG_State::GLState::ProgramObject& program, CompileOptionFlags flags) const;
         const VkProgramObject& GetOrCreateProgram(
-            const MagmaProgramSource& program, CompileOptionFlags flags);
-
-        // The default framebuffer's current image height, baked as a literal into every
-        // FragCoordYFlip variant (there is no push-constant or specialization channel here, and
-        // adding one for a value that changes only on swapchain recreation would cost the draw
-        // path more than a recompile costs a resize). It is therefore part of those variants'
-        // identity: ComputeHash mixes it in when the bit is set, so a height change re-keys them
-        // and leaves every other program's hash untouched. Setting a NEW height also bumps the
-        // cache-structure epoch, because a caller holding a memoised VkProgramObject* would
-        // otherwise keep using a module compiled against the old height.
-        void SetDefaultFramebufferHeight(Uint32 height);
-        Uint32 GetDefaultFramebufferHeight() const { return m_defaultFramebufferHeight; }
-
-        // Bumped whenever m_cache's STRUCTURE changes (any insert or erase): the cache is
-        // an open-addressing map holding entries by value, so both moves existing entries.
-        // A caller that memoised a VkProgramObject* may keep dereferencing it only while
-        // this is unchanged; on a bump it must re-run GetOrCreateProgram.
-        Uint64 GetCacheStructureEpoch() const { return m_cacheStructureEpoch; }
-        // A memoised entry pointer bypasses GetOrCreateProgram, whose per-lookup stamp is
-        // what keeps an in-use entry out of OnFrameBoundary's idle sweep - so such a
-        // caller must re-stamp the entry itself, at least once per frame boundary.
-        void StampProgramUse(const VkProgramObject& entry) const { entry.lastUsedFrame = m_frameCounter; }
-
-        // Observer may be null (no notifications). Not owned.
-        void SetEvictionObserver(IEvictionObserver* observer) { m_evictionObserver = observer; }
-        // Frame boundary hook: ages the program cache and evicts long-unused entries
-        // (their command buffers retired many frames ago), mirroring
-        // VkRenderPassManager::OnPresent's sweep.
-        void OnFrameBoundary();
+            const MG_State::GLState::ProgramObject& program, CompileOptionFlags flags);
 
         static VkShaderStageFlagBits ToVkStage(ShaderStage stage);
         static VkFormat ConvertSpirvImageFormatToVkFormat(SpvImageFormat format);
         static SamplerNumericDomain UniformTypeToSamplerNumericDomain(GLenum glType);
-        // The same question for an IMAGE uniform (`image2D`, `uimageBuffer`, ...), which the
-        // sampler form above deliberately does not answer. Kept separate rather than folded in
-        // because the two are asked in different places for different reasons: a sampler's domain
-        // decides a sampled VIEW format, an image's decides what a placeholder descriptor for an
-        // UNBOUND image unit must be (see UniformManager::AcquireUnboundTexelBufferView and
-        // GetUnboundStorageImageTexture) - a formatless `writeonly` declaration reflects no
-        // format at all, and the numeric domain is then the only thing that constrains it.
-        static SamplerNumericDomain UniformTypeToImageNumericDomain(GLenum glType);
-        // True when any entry point declares the DepthReplacing execution mode, i.e. the
-        // shader assigns gl_FragDepth. Exposed so the blended depth-write quirk's exemption
-        // can be pinned by tests. A false negative loses the exemption, so such a shader is
-        // stripped conservatively and forfeits its depth write.
-        static Bool ReflectedFragmentReplacesDepth(const SpvReflectShaderModule& reflectModule);
-        // True when an entry point reads the InstanceIndex builtin. Only gates a diagnostic:
-        // without shaderDrawParameters such a shader cannot have gl_InstanceID rebased.
-        static Bool ReflectedReadsInstanceIndexBuiltin(const SpvReflectShaderModule& reflectModule);
-        // True when an entry point declares the BaseVertex builtin, i.e. when a non-indexed
-        // draw with this program has to take the ZeroBaseVertex variant.
-        static Bool ReflectedReadsBaseVertexBuiltin(const SpvReflectShaderModule& reflectModule);
-        // Shared by the two above: does any entry point list an input variable decorated with
-        // this builtin?
-        static Bool ReflectedDeclaresInputBuiltin(const SpvReflectShaderModule& reflectModule, SpvBuiltIn builtin);
-        // True when an entry point writes the ViewportIndex builtin (gl_ViewportIndex), i.e. when
-        // the program can route primitives to a viewport other than 0 and its pipeline therefore
-        // has to declare more than one. Asks about OUTPUT variables because that is the direction
-        // a pre-rasterization stage declares it in.
-        static Bool ReflectedWritesViewportIndexBuiltin(const SpvReflectShaderModule& reflectModule);
-        static Bool ReflectedDeclaresOutputBuiltin(const SpvReflectShaderModule& reflectModule, SpvBuiltIn builtin);
-
-        // The pass-through tessellation control stage GL 4.6 core 11.2.2 describes for a
-        // program that has an evaluation stage and no control stage, for an input patch of
-        // `patchVertices` control points. Returned BY VALUE (a stage description is a POD, and
-        // the cache below is a rehashing map, so a pointer into it would not survive the next
-        // distinct patch size). `.module == VK_NULL_HANDLE` means the stage could not be built:
-        // the caller then has no control stage to inject, and CreatePipeline refuses the
-        // pipeline rather than handing the driver a half-tessellated one.
-        //
-        // Keyed on the patch size, the six default tessellation levels AND the gl_PerVertex
-        // member set, because all three decide what the generator emits. The size comes from
-        // PATCH_VERTICES and the levels from PATCH_DEFAULT_OUTER_LEVEL / PATCH_DEFAULT_INNER_LEVEL
-        // - draw state rather than link state, and the CTS case that motivated this links at the
-        // default 3 and draws at 4. The member set comes from the neighbouring evaluation stage's
-        // own SPIR-V, so two programs at different GLSL versions need different modules. The
-        // pipeline cache re-keys on the same inputs, so the module a pipeline was built with is
-        // part of that pipeline's identity. Compiling is bounded by the number of distinct
-        // (size, levels, members) combinations a program draws with - one or two in practice -
-        // and only ever happens for the rare program that has no control stage at all.
-        VkPipelineShaderStageCreateInfo GetOrCreatePassthroughTessControlStage(Uint32 patchVertices,
-                                                                              const FloatVec4& defaultOuterLevel,
-                                                                              const FloatVec2& defaultInnerLevel,
-                                                                              Uint32 perVertexMembers);
-
-        // Source of the module above. Exposed for tests: the generated GLSL is the whole
-        // contract with the evaluation stage, so it is worth pinning independently of a device.
-        static String BuildPassthroughTessControlSource(Uint32 patchVertices, const FloatVec4& defaultOuterLevel,
-                                                        const FloatVec2& defaultInnerLevel, Uint32 perVertexMembers);
-
-        // The identity of one such module: everything the generator bakes in, folded into a
-        // 64-bit key over the raw bits (so -0.0 and +0.0 key apart, which is harmless, and NaN
-        // keys to itself, which is what matters). Shared with PipelineFactory, which mixes the
-        // same value into the pipeline hash so a pipeline can never be handed a module built for
-        // different levels or a different block shape.
-        static Uint64 ComputePassthroughTessControlKey(Uint32 patchVertices, const FloatVec4& defaultOuterLevel,
-                                                       const FloatVec2& defaultInnerLevel, Uint32 perVertexMembers);
-
-        // The PerVertexMemberBit mask of the INPUT per-vertex block a module declares, read
-        // straight out of its SPIR-V (OpMemberDecorate ... BuiltIn on the struct behind the one
-        // Input variable that is an array of a Block-decorated struct). Zero when the module has
-        // no such block. Exposed for tests, which is the only way to pin the shape agreement
-        // without a device.
-        static Uint32 ReflectPerVertexInputMembers(const Vector<Uint>& spirv);
 
     private:
         struct ProgramLookupCache {
@@ -587,27 +213,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         };
 
         static TextureTarget UniformTypeToTextureTarget(GLenum glType);
-        // `stages` is ALWAYS ProgramObject::GetLinkedShaderStages() - one entry per module of
-        // `spirv`, at the same index. Taking the stages rather than the shader objects is what
-        // keeps the program's live attach list, which is a longer and differently-indexed list
-        // the moment a glAttachShader lands after the link, from being passed here by mistake.
-        void ReflectVertexInputs(const Vector<ShaderStage>& stages,
+        void ReflectVertexInputs(const Vector<SharedPtr<MG_State::GLState::ShaderObject>>& shaders,
                      const Vector<Vector<Uint>>& spirv,
                      VkProgramObject& entry) const;
-        void ReflectViewportIndexUsage(const Vector<ShaderStage>& stages,
-                                       const Vector<Vector<Uint>>& spirv,
-                                       VkProgramObject& entry) const;
-        void ReflectFragmentOutputs(const Vector<ShaderStage>& stages,
+        void ReflectFragmentOutputs(const Vector<SharedPtr<MG_State::GLState::ShaderObject>>& shaders,
                         const Vector<Vector<Uint>>& spirv,
                         VkProgramObject& entry) const;
-        void ReflectLayout(const MagmaProgramSource& program, const Vector<Vector<Uint>>& spirv,
+        void ReflectLayout(const MG_State::GLState::ProgramObject& program, const Vector<Vector<Uint>>& spirv,
                            VkProgramObject& entry) const;
-        // Fills needsPassthroughTessControl / passthroughTessControlEmulatable off the linked
-        // modules. Const and reflection-only: it decides nothing about the pipeline, it only
-        // records what the evaluation stage's input interface is made of.
-        void ReflectPassthroughTessControlNeed(const Vector<ShaderStage>& stages,
-                                               const Vector<Vector<Uint>>& spirv,
-                                               VkProgramObject& entry) const;
 
         VkDevice m_device = VK_NULL_HANDLE;
         Uint32 m_maxBindings = 0;
@@ -619,42 +232,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // True only when the logical device enabled both
         // shaderStorageImageReadWithoutFormat and shaderStorageImageWriteWithoutFormat.
         Bool m_unformattedFloatStorageImagesEnabled = false;
-        // True when the logical device enabled shaderTessellationAndGeometryPointSize. When it is
-        // FALSE a program whose tessellation or geometry module declares TessellationPointSize /
-        // GeometryPointSize is refused at build time (see VkProgramObject::
-        // pointSizeCapabilityUnsupported) instead of being handed to the driver as invalid usage.
-        Bool m_tessellationAndGeometryPointSizeEnabled = false;
-        // Startup snapshot used only by internally synthesized shader modules, which do not
-        // originate from a ProgramLinkTask.
-        Bool m_enableSpirvValidation = false;
-        // Device feature and limit gate resolved before vkCreateDevice. Keeping it in
-        // the factory lets each reflected layout choose ordinary descriptors when its
-        // own counts would exceed the update-after-bind budget.
-        UpdateAfterBindLimits m_updateAfterBindLimits{};
-        SubgroupLoweringPolicy m_subgroupPolicy{};
-        // See SetDefaultFramebufferHeight. 0 means "not known yet"; the FragCoordYFlip bit is
-        // never set before the swapchain exists, so no variant can be compiled against it.
-        Uint32 m_defaultFramebufferHeight = 0;
         mutable ProgramLookupCache m_lastLookup;
-        // Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
-        Uint64 m_frameCounter = 0;
-        // See GetCacheStructureEpoch(). Starts at 1 so a zero-initialized memo can never match.
-        Uint64 m_cacheStructureEpoch = 1;
-        IEvictionObserver* m_evictionObserver = nullptr;
-        // Pass-through tessellation control stages by the identity of what was compiled into
-        // them - the input patch size and the six default tessellation levels, folded into one
-        // 64-bit key by ComputePassthroughTessControlKey (the levels are float state, so the map
-        // cannot simply be keyed on the patch size any more). A failed build is cached as
-        // VK_NULL_HANDLE so a broken generator costs one compile, not one per draw.
-        //
-        // Hard-capped, because the key is application-controlled: glPatchParameterfv clamps
-        // nothing, so an application that recomputes a level per frame mints a new key per frame.
-        // Reaching the cap destroys every module and starts over (see the flush in
-        // GetOrCreatePassthroughTessControlStage); the cap is far above what any program that
-        // holds its levels still will ever need. The gl_PerVertex member set is in the key too
-        // and adds only a handful of values, so it does not move the cap in practice.
-        static constexpr SizeT kMaxPassthroughTessControlStages = 64;
-        UnorderedMap<Uint64, VkPipelineShaderStageCreateInfo> m_passthroughTessControlStages;
         static inline XXH64_state_t* m_hashState = XXH64_createState();
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/SubmitFencePrefix.h

@@ -1,41 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/SubmitFencePrefix.h
-// Copyright (c) 2025-2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-
-#pragma once
-
-#include <cstdint>
-#include <vector>
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-
-// Collect every fence in the ordered submission prefix. Waiting on only the last matching
-// frame-serial record is insufficient: the same serial may have an earlier in-flight submit.
-template <typename Records, typename Fence>
-bool CollectSubmitFencePrefix(const Records& records, std::uint64_t submitIndex,
-                              Fence nullFence, std::vector<Fence>& fences) {
-    fences.clear();
-    bool foundTarget = false;
-    for (const auto& record : records) {
-        if (record.submitIndex > submitIndex) {
-            break;
-        }
-        if (record.fence == nullFence) {
-            fences.clear();
-            return false;
-        }
-        fences.push_back(record.fence);
-        foundTarget = foundTarget || record.submitIndex == submitIndex;
-    }
-    if (!foundTarget) {
-        fences.clear();
-        return false;
-    }
-    return true;
-}
-
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/SwapchainObject.cpp

@@ -11,11 +11,6 @@
 #include "MG_Impl/GLImpl/Framebuffer/GL_Framebuffer.h"
 #include "MG_State/GLState/TextureState/TextureObject2D.h"
 
-#if MOBILEGL_PIPE_PUSH
-// P5c ev: the surface-changed event's producer callback, installed by the server session.
-#include <MG_Pipe/MGPipeCallbacks.h>
-#endif
-
 #if defined(__has_include)
 #if __has_include(<vulkan/vk_enum_string_helper.h>)
 #include <vulkan/vk_enum_string_helper.h>
@@ -162,7 +157,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         MGLOG_I("Got %d surface formats:", swapchainCapabilities.surfaceFormats.size());
         for (const auto& sf : swapchainCapabilities.surfaceFormats) {
-            MGLOG_D("    [%s, %s]", string_VkFormat(sf.format), string_VkColorSpaceKHR(sf.colorSpace));
+            MGLOG_I("    [%s, %s]", string_VkFormat(sf.format), string_VkColorSpaceKHR(sf.colorSpace));
         }
 
         const auto pickedSurfaceFormat = ChooseSwapchainSurfaceFormat(swapchainCapabilities.surfaceFormats);
@@ -171,7 +166,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         MGLOG_I("Got %d present modes:", swapchainCapabilities.presentModes.size());
         for (const auto& pm : swapchainCapabilities.presentModes) {
-            MGLOG_D("    %s", string_VkPresentModeKHR(pm));
+            MGLOG_I("    %s", string_VkPresentModeKHR(pm));
         }
 
         const auto presentMode = ChooseSwapchainPresentMode(swapchainCapabilities.presentModes);
@@ -252,11 +247,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         m_surfaceFormat = {createInfo.imageFormat, createInfo.imageColorSpace};
         m_extent = createInfo.imageExtent;
-        // The surface-space extent this swapchain was built from, i.e. before the
-        // quarter-turn swap above. Out-of-date checks must compare in THIS space: comparing a
-        // freshly queried currentExtent against the swapped m_extent flips axes every rotation
-        // and makes the comparison alternate forever.
-        m_surfaceExtent = defaultFramebufferExtent;
         m_preTransform = createInfo.preTransform;
 
         VK_VERIFY(vkCreateSwapchainKHR(device, &createInfo, nullptr, &m_swapchain));
@@ -267,9 +257,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_images.resize(imageCount, VK_NULL_HANDLE);
         VK_VERIFY(vkGetSwapchainImagesKHR(device, m_swapchain, &imageCount, m_images.data()));
         m_imageLayouts.assign(imageCount, VK_IMAGE_LAYOUT_UNDEFINED);
-        // Fresh swapchain images hold garbage until a render pass stores into them.
-        m_imageContentDefined.assign(imageCount, false);
-        m_depthStencilContentDefined.assign(imageCount, false);
 
         CreateImageViews(device);
         CreateDepthStencilResources(device, physicalDevice);
@@ -285,6 +272,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             static_cast<SizeT>(defaultFramebufferExtent.width) *
             static_cast<SizeT>(defaultFramebufferExtent.height) * 4;
 
+        auto* colorTex = static_cast<MG_State::GLState::TextureObject2D*>(defaultFBOInfo->colorAttachment.get());
+        colorTex->AllocateStorage(
+            TextureUploadTarget::Texture2D, 0, {
+                {extentWidth, extentHeight, 1},
+                defaultAttachmentByteSize}); // TODO: 4 is format size
         TextureInternalFormat depthFormat = TextureInternalFormat::Depth24Stencil8;
         switch (m_depthStencilFormat) {
             case VK_FORMAT_D24_UNORM_S8_UINT:
@@ -300,6 +292,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 depthFormat = TextureInternalFormat::Depth24Stencil8;
                 break;
         }
+        auto* depthTex = static_cast<MG_State::GLState::TextureObject2D*>(defaultFBOInfo->depthAttachment.get());
+        depthTex->SetInternalFormat(depthFormat);
+        depthTex->AllocateStorage(TextureUploadTarget::Texture2D, 0, {
+            {extentWidth, extentHeight, 1},
+            defaultAttachmentByteSize}); // TODO: 4 is format size
 
         // The default FBO's stencil attachment must track the swapchain extent:
         // FramebufferObject::CheckCompleteness requires every valid attachment
@@ -319,44 +316,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 stencilFormat = depthFormat;
                 break;
         }
-
-#if MOBILEGL_PIPE_PUSH
-        if (MG_Pipe::gMGPipeCallbacks.OnSurfaceChanged != nullptr) {
-            // P5c ev (CONTRACT-P5C §4.2): with an active transport the default FBO's
-            // attachments are CLIENT memory and this thread may not write them - the backend
-            // fills MGPSurfaceInfo and posts, and the client's consumer replays exactly the
-            // allocate/format writes of the monolith arm below on the GL thread. The two
-            // formats are always equal by the switches above, so one InternalFormat carries
-            // both. The callback's presence IS the transport probe - the server session
-            // installs it at Accept, and under monolith nobody ever does.
-            MG_Pipe::MGPSurfaceInfo info{};
-            info.Width = defaultFramebufferExtent.width;
-            info.Height = defaultFramebufferExtent.height;
-            info.InternalFormat = static_cast<Uint32>(depthFormat);
-            info.Samples = 1;
-            info.Layers = 1;
-            info.IsDefault = 1;
-            MG_Pipe::gMGPipeCallbacks.OnSurfaceChanged(&info);
-        } else
-#endif
-        {
-            auto* colorTex = static_cast<MG_State::GLState::TextureObject2D*>(defaultFBOInfo->colorAttachment.get());
-            colorTex->AllocateStorage(
-                TextureUploadTarget::Texture2D, 0, {
-                    {extentWidth, extentHeight, 1},
-                    defaultAttachmentByteSize}); // TODO: 4 is format size
-            auto* depthTex = static_cast<MG_State::GLState::TextureObject2D*>(defaultFBOInfo->depthAttachment.get());
-            depthTex->SetInternalFormat(depthFormat);
-            depthTex->AllocateStorage(TextureUploadTarget::Texture2D, 0, {
-                {extentWidth, extentHeight, 1},
-                defaultAttachmentByteSize}); // TODO: 4 is format size
-
-            auto* stencilTex = static_cast<MG_State::GLState::TextureObject2D*>(defaultFBOInfo->stencilAttachment.get());
-            stencilTex->SetInternalFormat(stencilFormat);
-            stencilTex->AllocateStorage(TextureUploadTarget::Texture2D, 0, {
-                {extentWidth, extentHeight, 1},
-                defaultAttachmentByteSize}); // TODO: 4 is format size
-        }
+        auto* stencilTex = static_cast<MG_State::GLState::TextureObject2D*>(defaultFBOInfo->stencilAttachment.get());
+        stencilTex->SetInternalFormat(stencilFormat);
+        stencilTex->AllocateStorage(TextureUploadTarget::Texture2D, 0, {
+            {extentWidth, extentHeight, 1},
+            defaultAttachmentByteSize}); // TODO: 4 is format size
 
     }
 
@@ -464,39 +428,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         m_images.clear();
         m_imageLayouts.clear();
-        m_imageContentDefined.clear();
-        m_depthStencilContentDefined.clear();
         m_preTransform = VK_SURFACE_TRANSFORM_IDENTITY_BIT_KHR;
     }
 
-    Bool SwapchainObject::IsImageContentDefined(Uint32 index) const {
-        MOBILEGL_ASSERT(index < m_imageContentDefined.size(), "Swapchain image content index out of range");
-        return m_imageContentDefined[index];
-    }
-
-    void SwapchainObject::SetImageContentDefined(Uint32 index, Bool defined) {
-        MOBILEGL_ASSERT(index < m_imageContentDefined.size(), "Swapchain image content index out of range");
-        m_imageContentDefined[index] = defined;
-    }
-
-    Bool SwapchainObject::IsDepthStencilContentDefined(Uint32 index) const {
-        MOBILEGL_ASSERT(index < m_depthStencilContentDefined.size(),
-                        "Swapchain depth/stencil content index out of range");
-        return m_depthStencilContentDefined[index];
-    }
-
-    void SwapchainObject::SetDepthStencilContentDefined(Uint32 index, Bool defined) {
-        MOBILEGL_ASSERT(index < m_depthStencilContentDefined.size(),
-                        "Swapchain depth/stencil content index out of range");
-        m_depthStencilContentDefined[index] = defined;
-    }
-
-    void SwapchainObject::SetAllDepthStencilContentUndefined() {
-        for (SizeT i = 0; i < m_depthStencilContentDefined.size(); ++i) {
-            m_depthStencilContentDefined[i] = false;
-        }
-    }
-
     VkImage SwapchainObject::GetImage(Uint32 index) const {
         MOBILEGL_ASSERT(index < m_images.size(), "Swapchain image index out of range");
         return m_images[index];

MobileGL/MG_Backend/DirectVulkan/Renderer/SwapchainObject.h

@@ -35,9 +35,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkSwapchainKHR GetHandle() const { return m_swapchain; }
         const VkSurfaceFormatKHR& GetSurfaceFormat() const { return m_surfaceFormat; }
         VkExtent2D GetExtent() const { return m_extent; }
-        // Surface-space extent (before the pre-rotation quarter-turn swap) this swapchain was
-        // created from - the value to compare a freshly queried currentExtent against.
-        VkExtent2D GetSurfaceExtent() const { return m_surfaceExtent; }
         VkSurfaceTransformFlagBitsKHR GetPreTransform() const { return m_preTransform; }
         const Vector<VkImage>& GetImages() const { return m_images; }
         const Vector<VkImageView>& GetImageViews() const { return m_imageViews; }
@@ -52,21 +49,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         void SetImageLayout(Uint32 index, VkImageLayout layout);
         SizeT GetImageCount() const { return m_images.size(); }
 
-        // EGL content-validity tracking for the default framebuffer. A color
-        // buffer's content is undefined once its image has been presented
-        // (EGL_BUFFER_DESTROYED swap behaviour, the implementation default),
-        // and every ancillary (depth/stencil) buffer's content is undefined
-        // after ANY swap regardless of swap behaviour (EGL 1.5 §3.10.1). The
-        // render-pass manager turns an undefined attachment's tile load into
-        // LOAD_OP_DONT_CARE. Flags start false (a fresh swapchain image holds
-        // garbage) and a render pass storing into an attachment sets it back
-        // to defined.
-        Bool IsImageContentDefined(Uint32 index) const;
-        void SetImageContentDefined(Uint32 index, Bool defined);
-        Bool IsDepthStencilContentDefined(Uint32 index) const;
-        void SetDepthStencilContentDefined(Uint32 index, Bool defined);
-        void SetAllDepthStencilContentUndefined();
-
     private:
         void CreateImageViews(VkDevice device);
         void CreateDepthStencilResources(VkDevice device, VkPhysicalDevice physicalDevice);
@@ -81,7 +63,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkSwapchainKHR m_swapchain = VK_NULL_HANDLE;
         VkSurfaceFormatKHR m_surfaceFormat{};
         VkExtent2D m_extent{};
-        VkExtent2D m_surfaceExtent{};
         VkSurfaceTransformFlagBitsKHR m_preTransform = VK_SURFACE_TRANSFORM_IDENTITY_BIT_KHR;
         Vector<VkImage> m_images;
         Vector<VkImageView> m_imageViews;
@@ -92,7 +73,5 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Vector<VkDeviceMemory> m_depthStencilImageMemories;
         Vector<VkImageView> m_depthStencilImageViews;
         Vector<VkImageLayout> m_depthStencilImageLayouts;
-        Vector<Bool> m_imageContentDefined;
-        Vector<Bool> m_depthStencilContentDefined;
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/UniformManager.h

@@ -9,11 +9,9 @@
 #pragma once
 
 #include "ProgramFactory.h"
-#include "MagmaProgramSource.h"
 #include "VkBufferManager.h"
 #include "VkSamplerManager.h"
 #include "VkTextureManager.h"
-#include "WirePlaceholderKey.h"
 #include "../VkIncludes.h"
 #include <Includes.h>
 
@@ -28,26 +26,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     public:
         struct SamplerBindingOverride {
             Uint32 binding = 0;
-            Uint32 element = 0;
             MG_State::GLState::ITextureObject* texture = nullptr;
             const MG_State::GLState::SamplerObject* sampler = nullptr;
             VkImageView imageView = VK_NULL_HANDLE;
-            VkImageLayout imageLayout = VK_IMAGE_LAYOUT_UNDEFINED;
-            Bool forceNearestFiltering = false;
         };
 
-        struct SamplerImageFeedbackBinding {
-            Uint32 samplerBinding = 0;
-            Uint32 samplerElement = 0;
-            MG_State::GLState::ITextureObject* texture = nullptr;
-            const MG_State::GLState::SamplerObject* sampler = nullptr;
-            SamplerNumericDomain numericDomain = SamplerNumericDomain::Unknown;
-        };
-
-        // `physicalDevice` is only ever asked for format properties: a placeholder descriptor for
-        // an unbound texel-buffer binding has to be built from a format the DEVICE accepts as a
-        // texel buffer, and there is no other route to that answer from here.
-        Bool Initialize(VkDevice device, VkPhysicalDevice physicalDevice, VkBufferManager* bufferManager,
+        Bool Initialize(VkDevice device, VkBufferManager* bufferManager,
                         ProgramFactory* programFactory,
                         VkDeviceSize minUniformBufferOffsetAlignment, Uint32 frameCount,
                         Uint32 maxBindings = 16, Uint32 setsPerFrame = 64,
@@ -55,92 +39,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         void Shutdown();
 
         void BeginFrame(Uint32 frameIndex);
-#if MOBILEGL_BUILD_DISAGGREGATED
-        // A present-less wire frame may run arbitrarily many draws. Before its
-        // descriptor cursor reaches this budget, the renderer retires the
-        // submission that last used the sets and rewinds every layout cursor.
-        static constexpr Uint32 kWireDescriptorSetBudget = 2048;
-        Bool WireDescriptorSetBudgetReached(Uint32 frameIndex) const;
-        SizeT RewindWireDescriptorSets(Uint32 frameIndex);
-        // How the wire arm answers a STORAGE image unit that GL 4.6 core 8.26 makes invalid (no
-        // texture, or a (level, layer) its texture lacks): a load returns zero, a store and an
-        // atomic are discarded. `deviceNullDescriptor` is the renderer's enablement of
-        // VK_EXT_robustness2's nullDescriptor at device creation. With it the unit binds a NULL
-        // storage-image descriptor, which is exactly that rule. Without it (or under
-        // MGITEST_MAGMA_FORCE_PRIVATE_IMAGE_PLACEHOLDER=1, the host lanes' way onto this arm) the
-        // unit binds a placeholder PRIVATE to its unit (per shape), cleared before each use, so no
-        // two units ever alias; what that cannot give is a load of the SAME unit after its own
-        // store inside one pass reading zero, nor privacy past kWirePrivateStoragePlaceholderCap
-        // placeholders (CONTRACT-P7 §12). Called after Initialize.
-        void SetWireInvalidStorageImageArm(Bool deviceNullDescriptor);
-#endif
-        // A command buffer (re)began recording: descriptor bindings recorded into
-        // the previous buffer do not carry over, so drop the bind-dedup shadow.
-        void OnCommandBufferBoundary() { m_lastBindValid = false; }
-        // A ProgramFactory eviction just destroyed this layout: purge every frame
-        // slot's cached descriptor sets for it, so a recycled handle value can never
-        // stale-hit sets written for the dead layout's bindings. The sets are
-        // vkFreeDescriptorSets'd back to their pools (created with
-        // FREE_DESCRIPTOR_SET_BIT) and the pool accounting is credited, so program
-        // churn recycles pool capacity instead of abandoning it. GPU-safe: the layout
-        // only dies after >1024 idle frame boundaries, so no in-flight command buffer
-        // references its sets. This is the only eviction path for the per-layout
-        // caches - a live layout's entry must never be purged (its sets would be
-        // unreachable pool slots), so there is deliberately no age-based sweep here.
-        void OnDescriptorSetLayoutDestroyed(VkDescriptorSetLayout descriptorSetLayout);
-        // One record per visited CombinedImageSampler DESCRIPTOR (post fallback substitution,
-        // in binding order, and within a binding in array-element order): the resolved texture
-        // and effective sampler, as never-reused lifetime ids so a freed-and-reallocated object
-        // at the same heap address can only MISS a comparison, never false-hit it (same ABA
-        // rule as SamplerResolveMemo). An arrayed binding contributes one record per element -
-        // element granularity is required, or swapping the textures of two elements of the same
-        // array would leave the record list identical and the fast path would keep a stale set.
-        struct SampledBindingRecord {
-            Uint64 textureLifetimeId = 0;
-            Uint64 samplerLifetimeId = 0;
-        };
-        Bool CollectSampledTextures(const MagmaProgramSource& program,
+        Bool CollectSampledTextures(const MG_State::GLState::ProgramObject& program,
                                     const ProgramFactory::VkProgramObject& programObj,
-                                    Vector<MG_State::GLState::ITextureObject*>& outTextures,
-                                    Vector<SampledBindingRecord>* outBindingRecords = nullptr);
-        // Shadow-compare for the SetupDraw fast path: re-runs the CollectSampledTextures
-        // walk and reports whether every visited binding still resolves to the recorded
-        // (texture, effective sampler) pair. A texture bind generation bump alone (e.g. a
-        // redundant glBindSampler, which always bumps it) does not prove the sampled set
-        // moved; this walk does, without rebuilding the set or falling off the fast path.
-        Bool SampledBindingsUnchanged(const MagmaProgramSource& program,
-                                      const ProgramFactory::VkProgramObject& programObj,
-                                      const Vector<SampledBindingRecord>& previousRecords) const;
-        Bool CollectStorageImageTextures(const MagmaProgramSource& program,
+                                    Vector<MG_State::GLState::ITextureObject*>& outTextures);
+        Bool CollectStorageImageTextures(const MG_State::GLState::ProgramObject& program,
                                          const ProgramFactory::VkProgramObject& programObj,
                                          Vector<MG_State::GLState::ITextureObject*>& outTextures) const;
-        Bool CollectSamplerImageFeedback(
-            const MagmaProgramSource& program,
-            const ProgramFactory::VkProgramObject& programObj,
-            Vector<SamplerImageFeedbackBinding>& outBindings) const;
-        static Bool SamplerOverlapsWritableImageSubresource(Int samplerBaseLevel, Int samplerMaxLevel,
-                                                             GLint imageLevel, GLenum imageAccess);
-#if MOBILEGL_BUILD_DISAGGREGATED
-        // Resolve lazy texture uploads/promotions before the caller captures the
-        // command buffer passed to BindProgramUniformBuffers. Preparation may
-        // submit older work, but descriptor recording must never rotate it.
-        Bool PrepareWireTextureResources(const MagmaProgramSource& program,
-                                          const ProgramFactory::VkProgramObject& programObj);
-#endif
-        // samplerDescriptorsUnchangedHint: the caller (SetupDraw fast path) proved that
-        // every input of every combined-image-sampler resolution is unchanged since the
-        // previous draw's resolve - same (texture, sampler) per binding, texture params
-        // sum, sampling-resolution generation (sampler params + texture shape), image
-        // epochs AND per-resource layout values - so the per-binding cached
-        // VkDescriptorImageInfo may be reused without re-running the resolve chain.
         Bool BindProgramUniformBuffers(VkCommandBuffer commandBuffer,
-                                       const MagmaProgramSource& program,
+                                       const MG_State::GLState::ProgramObject& program,
                                        const ProgramFactory::VkProgramObject& programObj,
                                        Uint32 frameIndex,
                                        VkPipelineBindPoint bindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS,
-                                       const SamplerBindingOverride* samplerBindingOverride = nullptr,
-                                       Bool samplerDescriptorsUnchangedHint = false,
-                                       const Vector<SamplerBindingOverride>* samplerBindingOverrides = nullptr);
+                                       const SamplerBindingOverride* samplerBindingOverride = nullptr);
 
         // Pure format-policy helper kept public for host regression tests. Formatted storage
         // images use their shader qualifier; transformed float images use glBindImageTexture's
@@ -148,219 +58,52 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         static VkFormat ResolveStorageImageViewFormat(VkFormat reflectedFormat, GLenum bindingFormat,
                                                       VkFormat resourceFormat, Bool useBindingFormat);
 
-        // True when the program reads at least one sampler and every one of them is bound to a
-        // texture whose GL level range is a single level. Such a sampler resolves to
-        // minLod = maxLod = 0 (see VkSamplerManager::GetOrCreateSampler), so an implicit-LOD sample
-        // and an explicit LOD 0 sample must read the same texel - which is what makes the
-        // ExplicitLod0Sampling SPIR-V rewrite safe to request. Deliberately conservative: it reads
-        // only GL state, so a texture that ends up single-level for another reason (one uploaded
-        // level under a wide level range) merely misses the rewrite.
-        static Bool ProgramSamplesOnlySingleLevelTextures(const MagmaProgramSource& program,
-                                                          const ProgramFactory::VkProgramObject& programObj);
-
     private:
         struct DescriptorPoolBucket {
             VkDescriptorPool handle = VK_NULL_HANDLE;
             Uint32 maxSets = 0;
             Uint32 allocatedSets = 0;
-            Bool updateAfterBind = false;
-        };
-
-        // A cached descriptor set together with the pool it was allocated from, so a
-        // layout-destroyed purge can vkFreeDescriptorSets it back and credit the
-        // owning bucket's accounting.
-        struct CachedDescriptorSet {
-            VkDescriptorSet set = VK_NULL_HANDLE;
-            VkDescriptorPool pool = VK_NULL_HANDLE;
         };
 
         struct DescriptorSetCacheEntry {
-            Vector<CachedDescriptorSet> sets;
+            Vector<VkDescriptorSet> sets;
             Uint32 cursor = 0;
         };
 
-#if MOBILEGL_BUILD_DISAGGREGATED
-        // ResolveWireImageDescriptor emits no pNext chain. Key every view-create
-        // value explicitly: hash collisions must never alias different windows,
-        // formats or swizzles. The root handle and allocation epoch also prevent
-        // a recycled native image handle from reviving an older view.
-        struct WireImageViewKey {
-            MG_Pipe::MGPipeHandle root{};
-            VkImage image = VK_NULL_HANDLE;
-            Uint64 imageEpoch = 0;
-            VkImageViewCreateFlags flags = 0;
-            VkImageViewType type = VK_IMAGE_VIEW_TYPE_2D;
-            VkFormat format = VK_FORMAT_UNDEFINED;
-            VkComponentMapping components{};
-            VkImageSubresourceRange range{};
-
-            Bool operator==(const WireImageViewKey& other) const {
-                return root == other.root && image == other.image && imageEpoch == other.imageEpoch &&
-                       flags == other.flags && type == other.type && format == other.format &&
-                       components.r == other.components.r && components.g == other.components.g &&
-                       components.b == other.components.b && components.a == other.components.a &&
-                       range.aspectMask == other.range.aspectMask && range.baseMipLevel == other.range.baseMipLevel &&
-                       range.levelCount == other.range.levelCount && range.baseArrayLayer == other.range.baseArrayLayer &&
-                       range.layerCount == other.range.layerCount;
-            }
-        };
-
-        struct WireImageViewKeyHash {
-            SizeT operator()(const WireImageViewKey& key) const;
-        };
-
-        struct WirePlaceholderImage {
-            VkImage image = VK_NULL_HANDLE;
-            VkDeviceMemory memory = VK_NULL_HANDLE;
-            VkImageView view = VK_NULL_HANDLE;
-            VkSampler sampler = VK_NULL_HANDLE;
-            VkRenderPass clearPass = VK_NULL_HANDLE;
-            VkFramebuffer clearFramebuffer = VK_NULL_HANDLE;
-            VkFormat format = VK_FORMAT_UNDEFINED;
-            VkImageAspectFlags aspect = VK_IMAGE_ASPECT_COLOR_BIT;
-            VkSampleCountFlagBits samples = VK_SAMPLE_COUNT_1_BIT;
-            VkImageLayout layout = VK_IMAGE_LAYOUT_UNDEFINED;
-            Uint32 layers = 1;
-        };
-        // Keyed by shape, and a storage placeholder on the arm without a null descriptor by its
-        // image unit too (WirePlaceholderKey.h: ChooseWirePlaceholderKey, and its cap).
-        mutable UnorderedMap<WirePlaceholderKey, WirePlaceholderImage, WirePlaceholderKeyHash> m_wirePlaceholderImages;
-        // How many of those are private to a unit (against kWirePrivateStoragePlaceholderCap).
-        mutable SizeT m_wirePrivateStoragePlaceholders = 0;
-        // See SetWireInvalidStorageImageArm.
-        Bool m_wireInvalidStorageImagesBindNull = false;
-        // boundStorageFormat: for a storage binding with no reflected format, the format the
-        // unit's glBindImageTexture named, when the unit holds a texture it cannot address
-        // (GL 4.6 core 8.26); UNDEFINED keeps the numeric-domain R32 default. `unit` is the image
-        // unit of a storage binding (what its private placeholder is private to); unused for a sampler.
-        Bool ResolveWirePlaceholderImage(VkCommandBuffer commandBuffer, const MagmaProgramSource& program,
-            const ProgramFactory::VkProgramObject& programObj, Uint32 binding, Bool storage,
-            VkDescriptorImageInfo& out, VkFormat boundStorageFormat = VK_FORMAT_UNDEFINED, Uint32 unit = ~0u) const;
-        void DestroyWirePlaceholderImage(WirePlaceholderImage& image) const;
-#endif
-
         struct FrameResources {
             Vector<DescriptorPoolBucket> descriptorPools;
             UnorderedMap<VkDescriptorSetLayout, DescriptorSetCacheEntry> descriptorSetCacheByLayout;
             Vector<VkBufferView> texelBufferViews;
-#if MOBILEGL_BUILD_DISAGGREGATED
-            mutable Vector<VkImageView> wireImageViews;
-            // Own views in the vector above until this slot's fence/idle proof.
-            // Cache hits preserve the handle, enabling descriptor-content reuse.
-            mutable UnorderedMap<WireImageViewKey, VkImageView, WireImageViewKeyHash> wireImageViewCache;
-#endif
             Uint32 activeDescriptorPoolIndex = 0;
             Uint32 allocatedSetsThisFrame = 0;
             Uint32 peakAllocatedSetsThisFrame = 0;
         };
 
-        static Bool ResolveSamplerTexture(const MagmaProgramSource& program,
+        static Bool ResolveSamplerTexture(const MG_State::GLState::ProgramObject& program,
                                    const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
                                    SharedPtr<MG_State::GLState::ITextureObject>& outTexture);
-        // Shared per-binding resolution for CollectSampledTextures and
-        // SampledBindingsUnchanged, so membership and comparison can never diverge:
-        // texture after the fallback substitution (may still be null when no fallback
-        // exists), effective sampler = unit override else the texture's own sampler.
-        // False = the binding is skipped (unbound with a non-2D fallback target).
-        // `element` indexes a sampler array inside the binding; see ResolveSamplerDescriptor.
-        Bool ResolveSampledBinding(const MagmaProgramSource& program,
-                                   const ProgramFactory::VkProgramObject& programObj, Uint32 binding, Uint32 element,
-                                   MG_State::GLState::ITextureObject*& outTexture,
-                                   const MG_State::GLState::SamplerObject*& outSampler) const;
         // Raw-pointer variant for the per-draw sampled-texture walk (CollectSampledTextures):
         // the bound texture stays alive through the draw via GL binding state, so callers that
         // only need the pointer skip the SharedPtr copy's atomic refcount churn.
         static MG_State::GLState::ITextureObject* ResolveSamplerTextureRaw(
-            const MagmaProgramSource& program,
-            const ProgramFactory::VkProgramObject& programObj, Uint32 binding, Uint32 element);
-        // `numericDomain` is the sampler's class, and it matters only for the multisample arm -
-        // see GetFallbackMultisampleTexture for why the single-sampled fallback can ignore it.
-        SharedPtr<MG_State::GLState::ITextureObject> GetFallbackTexture(
-            TextureTarget target, SamplerNumericDomain numericDomain) const;
-        // The multisample arm of GetFallbackTexture. One object per (target, numeric domain) and
-        // no upload path: a multisample image cannot be written by a transfer, so its texels stay
-        // undefined - which is what GL promises for a texelFetch on an incomplete multisample
-        // texture - and it cannot carry MUTABLE_FORMAT, so its format has to match the sampler's
-        // class outright rather than being reinterpreted at view time.
-        SharedPtr<MG_State::GLState::ITextureObject> GetFallbackMultisampleTexture(
-            TextureTarget target, SamplerNumericDomain numericDomain) const;
-        // ---- placeholders for UNBOUND image-backed descriptors -------------------------
-        // GL lets a program declare `samplerBuffer`, `imageBuffer` or `image2D` and bind nothing
-        // to the unit it names: the fetch is then undefined (GL 4.6 core 8.9 for an incomplete
-        // buffer texture, 8.26 for an image unit with no texture) - undefined VALUES, not a
-        // dropped draw. Vulkan has no unwritten descriptor, so something valid has to sit in the
-        // set or the whole draw or dispatch is lost, which is what these two build. Same shape as
-        // VkBufferManager::AcquireUnboundStorageDescriptor, one level up: per FORMAT rather than
-        // one shared object, because a descriptor whose format disagrees with the shader's
-        // declaration is invalid Vulkan even when nothing ever reads it.
-        //
-        // `declaredFormat` is the format the SHADER declared (VK_FORMAT_UNDEFINED for a sampled
-        // texel buffer, which never carries one, or for a formatless `writeonly` image);
-        // `numericDomain` decides the format when there is no declaration and is the fallback
-        // class when the device cannot use the declared one as a texel buffer.
-        VkBufferView AcquireUnboundTexelBufferView(VkFormat declaredFormat, SamplerNumericDomain numericDomain,
-                                                   Bool storage);
-        // A 1x1 (x1 layer, or 6 faces for a cube) texture of `format`, shaped for `target` so the
-        // view the descriptor gets has the view type the shader's image declaration demands.
-        // Null for a target with no single-sampled placeholder shape - multisample images, whose
-        // descriptor needs a multisample view that this cannot stand in for.
-        SharedPtr<MG_State::GLState::ITextureObject> GetUnboundStorageImageTexture(TextureTarget target,
-                                                                                    VkFormat format) const;
-        // The (target, format) pair a storage-image binding's placeholder is keyed by, resolved
-        // from reflection alone. False when the binding has no placeholder shape.
-        Bool ResolveUnboundStorageImagePlaceholder(const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                                   TextureTarget& outTarget, VkFormat& outFormat) const;
-        // `element` indexes a sampler ARRAY inside one binding; each element carries its own
-        // independently assigned GL texture unit, so it selects the texture, the sampler
-        // override and the fallback separately from its neighbours.
-        //
-        // trustUnchangedHint: reuse this binding's cached VkDescriptorImageInfo outright
-        // (see BindProgramUniformBuffers' samplerDescriptorsUnchangedHint for the proof
-        // obligations the caller carries). The cache is keyed by binding alone, so it is
-        // used ONLY for single-descriptor bindings - see m_samplerResolveMemo.
-        Bool ResolveSamplerDescriptor(VkCommandBuffer commandBuffer, const MagmaProgramSource& program,
+            const MG_State::GLState::ProgramObject& program,
+            const ProgramFactory::VkProgramObject& programObj, Uint32 binding);
+        SharedPtr<MG_State::GLState::ITextureObject> GetFallbackTexture(TextureTarget target) const;
+        Bool ResolveSamplerDescriptor(VkCommandBuffer commandBuffer, const MG_State::GLState::ProgramObject& program,
                                       const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                      Uint32 element, VkDescriptorImageInfo& outImageInfo,
-                                      Bool trustUnchangedHint = false) const;
-#if MOBILEGL_BUILD_DISAGGREGATED
-        Bool ResolveWireImageDescriptor(VkCommandBuffer commandBuffer, const MagmaProgramSource& program,
-                                       const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                       Uint32 element, Bool storage, VkDescriptorImageInfo& out) const;
-        Bool ResolveWireTexelBufferDescriptor(const MagmaProgramSource& program,
-                                             const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                             Uint32 frameIndex, Bool storage, VkBufferView& out);
-        Uint32 m_wireFrameIndex = 0;
-        VkDeviceSize m_wireStorageOffsetAlignment = 1;
-        VkDeviceSize m_wireTexelOffsetAlignment = 1;
-        VkDeviceSize m_wireMaxUniformRange = ~VkDeviceSize{0};
-        VkDeviceSize m_wireMaxStorageRange = ~VkDeviceSize{0};
-        Uint32 m_wireMaxTexelElements = ~Uint32{0};
-#endif
+                                      VkDescriptorImageInfo& outImageInfo) const;
         Bool ResolveSamplerDescriptorOverride(const SamplerBindingOverride& samplerBindingOverride,
                                               VkDescriptorImageInfo& outImageInfo) const;
-        Bool ResolveTexelBufferDescriptor(const MagmaProgramSource& program,
+        Bool ResolveTexelBufferDescriptor(const MG_State::GLState::ProgramObject& program,
                                           const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
                                           Uint32 frameIndex, VkBufferView& outBufferView);
-        // GLSL `imageBuffer`: the same VkBufferView descriptor as the sampled texel buffer above,
-        // but resolved from an IMAGE unit (glBindImageTexture) rather than a texture unit, and
-        // made GPU-resident-writable because the shader may store to it. No `element` parameter:
-        // an imageBuffer ARRAY is refused at program creation, so a binding is always one
-        // descriptor (see the array gate in RemapDescriptorBindingsForVulkan).
-        Bool ResolveStorageTexelBufferDescriptor(const MagmaProgramSource& program,
-                                                 const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                                 Uint32 frameIndex, VkBufferView& outBufferView);
-        // `element` indexes a block INSTANCE array's descriptors; it is 0 for every ordinary
-        // block. Each element resolves through its own GL storage block, and so its own GL
-        // binding point, buffer and glBindBufferRange window.
-        Bool ResolveStorageBufferDescriptor(const MagmaProgramSource& program,
+        Bool ResolveStorageBufferDescriptor(const MG_State::GLState::ProgramObject& program,
                                             const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                            Uint32 element, VkDescriptorBufferInfo& outBufferInfo) const;
-        // `element` indexes an image ARRAY inside one binding; each element carries its own
-        // independently assigned GL image unit.
+                                            VkDescriptorBufferInfo& outBufferInfo) const;
         Bool ResolveStorageImageDescriptor(VkCommandBuffer commandBuffer,
-                                           const MagmaProgramSource& program,
+                                           const MG_State::GLState::ProgramObject& program,
                                            const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                           Uint32 element, VkDescriptorImageInfo& outImageInfo) const;
+                                           VkDescriptorImageInfo& outImageInfo) const;
         // Result of resolving a UBO binding: either a zero-copy direct bind to the app's resident
         // VkBuffer (the GLES backend's approach - no per-draw copy) or the CPU payload to upload.
         struct UboBindResult {
@@ -371,30 +114,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             const void* payload = nullptr;  // fallback UploadTransient path
             VkDeviceSize payloadSize = 0;
         };
-#if MOBILEGL_BUILD_DISAGGREGATED
-        Bool ResolveWireUniformBufferPayload(const MagmaProgramSource& program, Uint32 blockIndex,
-                                             Uint32 bindingPoint, UboBindResult& out) const;
-#endif
-        Bool ResolveUniformBufferPayload(const MagmaProgramSource& program,
+        Bool ResolveUniformBufferPayload(const MG_State::GLState::ProgramObject& program,
                                          const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                         Uint32 arrayElement, UboBindResult& out) const;
-        // Shared resolution of one dynamic-UBO binding element into the
-        // (buffer, range, dynamicOffset) triple the descriptor consumes: direct
-        // bind, global-slice reuse, or transient upload. Used by the full walk
-        // and by the dynamic-offset-only rebind (see FastRebindMemo).
-        Bool ResolveDynamicUboDescriptor(const MagmaProgramSource& program,
-                                         const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
-                                         Uint32 arrayElement, Uint32 frameIndex, VkBuffer& outBuffer,
-                                         VkDeviceSize& outRange, Uint32& outDynamicOffset);
-        // The vkCmdBindDescriptorSets tail shared by the full walk and the
-        // dynamic-offset-only rebind: skips the driver call when this exact
-        // binding is already live on the command buffer (see the bind-dedup
-        // shadow below), otherwise binds and refreshes the shadow.
-        void BindDescriptorSetDeduped(VkCommandBuffer commandBuffer, VkPipelineBindPoint bindPoint,
-                                      VkPipelineLayout pipelineLayout, VkDescriptorSet descriptorSet,
-                                      const Vector<Uint32>& dynamicOffsets);
-        Bool CreateDescriptorPool(Uint32 maxSets, Bool updateAfterBind, VkDescriptorPool& outPool) const;
-        Bool GrowFrameDescriptorPool(FrameResources& frame, Uint32 frameIndex, Bool updateAfterBind);
+                                         UboBindResult& out) const;
+        Bool CreateDescriptorPool(Uint32 maxSets, VkDescriptorPool& outPool) const;
+        Bool GrowFrameDescriptorPool(FrameResources& frame, Uint32 frameIndex);
         VkResult AllocateDescriptorSetsFromActivePool(
             Uint32 frameIndex, const ProgramFactory::VkProgramObject& programObj, VkDescriptorSet& outDescriptorSet);
         VkResult AcquireDescriptorSet(Uint32 frameIndex,
@@ -402,7 +126,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                                       VkDescriptorSet& outDescriptorSet);
 
         VkDevice m_device = VK_NULL_HANDLE;
-        VkPhysicalDevice m_physicalDevice = VK_NULL_HANDLE;
         VkBufferManager* m_bufferManager = nullptr;
         ProgramFactory* m_programFactory = nullptr;
         Vector<FrameResources> m_frames;
@@ -415,18 +138,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VkTextureManager* m_textureManager = nullptr;
         VkSamplerManager* m_samplerManager = nullptr;
         mutable SharedPtr<MG_State::GLState::ITextureObject> m_fallbackTexture2D;
-        // Keyed by (arrayed, numeric domain); see GetFallbackMultisampleTexture. Lazily populated,
-        // never evicted - at most six tiny 1x1 images - and torn down with the manager.
-        mutable UnorderedMap<Uint32, SharedPtr<MG_State::GLState::ITextureObject>> m_fallbackMultisampleTextures;
-        // See AcquireUnboundTexelBufferView / GetUnboundStorageImageTexture. Both are lazily
-        // populated, never evicted (a program's declared formats are a fixed, tiny set) and torn
-        // down with the manager. The texel views are keyed by format AND by storage-vs-sampled
-        // because the two descriptor kinds demand different format FEATURES of the device, so one
-        // format can be usable for one and not the other. Deliberately NOT the per-frame
-        // texelBufferViews list: those are destroyed at every frame boundary, and these must
-        // outlive it or the placeholder would be rebuilt for every unbound binding every frame.
-        UnorderedMap<Uint64, VkBufferView> m_unboundTexelBufferViews;
-        mutable UnorderedMap<Uint64, SharedPtr<MG_State::GLState::ITextureObject>> m_unboundStorageImageTextures;
 
         // Per-draw scratch buffers for BindProgramUniformBuffers: reused (clear keeps
         // capacity) so the descriptor-write path stops allocating on every draw.
@@ -436,94 +147,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Vector<VkBufferView> m_texelBufferViewsScratch;
         Vector<Uint32> m_dynamicOffsetsScratch;
 
-        // Descriptor-set reuse across recent draws (see BindProgramUniformBuffers).
-        // When a draw's resolved descriptor content is byte-identical to one memoized
-        // earlier, reuse that VkDescriptorSet and skip AcquireDescriptorSet +
-        // vkUpdateDescriptorSets - only the bind-time dynamic offsets differ. Four
-        // entries with round-robin replacement rather than one: draws alternating
-        // between two programs (MC's chunk<->entity ping-pong) would thrash a single
-        // slot into a full re-allocate+write every draw. Reset each frame in BeginFrame
-        // because the frame's descriptor sets are recycled there.
-        struct DescriptorReuseEntry {
-            Uint64 signature = 0;
-            VkDescriptorSet set = VK_NULL_HANDLE;
-            Bool valid = false;
-        };
-        static constexpr Uint32 kDescriptorReuseMemoSize = 4;
-        DescriptorReuseEntry m_descriptorReuseMemo[kDescriptorReuseMemoSize];
-        Uint32 m_descriptorReuseMemoNext = 0;
-
-        // Dynamic-offset-only rebind (see BindProgramUniformBuffers): records the
-        // descriptor set selected by the last cacheable full walk of a program
-        // whose active bindings are exactly one dynamic UBO (single descriptor)
-        // plus combined-image samplers. When the next call proves every sampler
-        // descriptor input unchanged (samplerDescriptorsUnchangedHint) and the
-        // UBO re-resolves to the SAME VkBuffer+range - only the dynamic offset
-        // moved, the per-draw glUniform case - the walk collapses to: resolve one
-        // offset, rebind the recorded set with new pDynamicOffsets (Vulkan allows
-        // rebinding the same set with different dynamic offsets).
-        // Invalidation inventory: BeginFrame clears it (the frame's sets are
-        // recycled) and the frameIndex field guards cross-frame confusion on top;
-        // OnDescriptorSetLayoutDestroyed clears it (the set may be freed); a
-        // sampler-override walk clears it (mirrors m_descriptorReuseMemo); a
-        // program relink bumps the backend state version and thus programObj.hash
-        // so the key misses; the program lifetime id is never reused, so a
-        // deleted-and-recreated program misses; a texture/sampler/binding change
-        // drops the hint upstream; an arena wrap or growth resolves a different
-        // VkBuffer and misses. AcquireDescriptorSet's per-frame cursor only
-        // advances, so the recorded set is never re-written within its frame.
-        // P7 M2 round 2 (ID-P7-43): a WIRE store can die MID-FRAME on the reclaim
-        // path (VkBufferManager::DeferredWireRelease), and the next mint can hand
-        // its VkBuffer handle value back - a heap pointer under lavapipe - so "the
-        // same VkBuffer+range" is no longer proof of the same store. The memo
-        // therefore records VkBufferManager::GetWireStoreDestroyEpoch() and misses
-        // once any wire store has been destroyed since; the descriptor-reuse
-        // signature below folds the same epoch in. On the wire arm this memo is
-        // never consulted (SetupWireDraw passes no sampler hint), so the field is
-        // the defensive half; the signature is the half the wire arm reaches.
-        struct FastRebindMemo {
-            Bool valid = false;
-            Uint32 frameIndex = 0;
-            Uint64 programLifetimeId = 0;
-            ProgramFactory::HashType programHash = 0;
-            Uint32 uboBinding = 0;
-            VkBuffer uboBuffer = VK_NULL_HANDLE;
-            VkDeviceSize uboRange = 0;
-            VkDescriptorSet set = VK_NULL_HANDLE;
-#if MOBILEGL_BUILD_DISAGGREGATED
-            Uint64 wireStoreDestroyEpoch = 0;
-#endif
-        };
-        FastRebindMemo m_fastRebindMemo;
-
-        // vkCmdBindDescriptorSets dedup: consecutive draws with a static uniform
-        // block resolve to the same set AND the same dynamic offsets, so the
-        // driver call can be skipped outright. Command-buffer-scope state; reset
-        // via OnCommandBufferBoundary whenever a recording (re)begins. Keyed on
-        // layout+bind point, so a pipeline-layout switch always rebinds.
-        static constexpr Uint32 kMaxShadowedDynamicOffsets = 8;
-        Bool m_lastBindValid = false;
-        VkDescriptorSet m_lastBindSet = VK_NULL_HANDLE;
-        VkPipelineLayout m_lastBindLayout = VK_NULL_HANDLE;
-        VkPipelineBindPoint m_lastBindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS;
-        Uint32 m_lastBindOffsetCount = 0;
-        Uint32 m_lastBindOffsets[kMaxShadowedDynamicOffsets] = {};
-
-        // Global-UBO transient-slice reuse: MC leaves the default uniform block
-        // untouched across long GUI/terrain runs, so the per-draw re-upload of
-        // the same bytes can reuse the slice uploaded earlier THIS frame (frame
-        // serial guards arena recycling; the content version guards writes).
-        struct GlobalUboSliceMemo {
-            Uint64 programLifetimeId = 0;
-            Uint64 frameSerial = 0;
-            Uint32 uboContentVersion = 0;
-            VkBuffer buffer = VK_NULL_HANDLE;
-            VkDeviceSize offset = 0;
-            VkDeviceSize range = 0;
-        };
-        static constexpr Uint32 kGlobalUboMemoSize = 4;
-        GlobalUboSliceMemo m_globalUboMemo[kGlobalUboMemoSize];
-        Uint32 m_globalUboMemoNext = 0;
+        // Descriptor-set reuse across consecutive draws (see BindProgramUniformBuffers).
+        // When a draw's resolved descriptor content is byte-identical to the previous
+        // draw's, reuse the same VkDescriptorSet and skip AcquireDescriptorSet +
+        // vkUpdateDescriptorSets - only the bind-time dynamic offsets differ. Reset each
+        // frame in BeginFrame because the frame's descriptor sets are recycled there.
+        VkDescriptorSet m_lastBoundDescriptorSet = VK_NULL_HANDLE;
+        Uint64 m_lastDescriptorSignature = 0;
+        Bool m_hasLastDescriptor = false;
 
         // Per-binding fast path over VkSamplerManager's content-hashed sampler cache, which
         // stays the source of truth: its key hashes all sampler+texture state, so two distinct
@@ -536,56 +167,16 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // lifetime id, so a freed-and-reallocated sampler or texture at the same heap address
         // always gets a fresh id and misses (a raw pointer would false-hit that ABA) - so a
         // stale guess can only miss and fall through to the hash, never resolve wrong. Still
-        // reset each frame alongside the descriptor-set cache. Indexed by binding, but the
-        // whole-descriptor entry is additionally keyed by program lifetime: Vulkan binding
-        // numbers are layout-local and unrelated programs routinely reuse binding 0/1.
+        // reset each frame alongside the descriptor-set cache. Indexed by binding.
         struct SamplerResolveMemo {
-            Uint64 infoProgramLifetimeId = 0;
             Uint64 samplerLifetimeId = 0;
             Uint64 textureLifetimeId = 0;
             VkSampler sampler = VK_NULL_HANDLE;
-            Uint32 viewLevelCount = 0;
             Uint16 samplerVersion = 0;
             Uint16 textureParamsVersion = 0;
             Bool forceNearestFiltering = false;
             Bool valid = false;
-            // ResolveSampledImageViewFormat is pure in (image format, numeric domain), but a
-            // domain mismatch walks a ~184-entry format table. Memo the resolution per binding
-            // so a reinterpreted sampler pays that scan once, not once per draw.
-            VkFormat viewFormatSource = VK_FORMAT_UNDEFINED;
-            SamplerNumericDomain viewFormatDomain = SamplerNumericDomain::Unknown;
-            VkFormat viewFormat = VK_FORMAT_UNDEFINED;
-            Bool viewFormatValid = false;
-            // Whole resolved descriptor from this binding's last full resolve. Reused
-            // ONLY under ResolveSamplerDescriptor's trustUnchangedHint, whose caller
-            // proves every resolve input unchanged; cleared with the per-frame reset
-            // (the cached VkSampler outlives a frame only via a fresh resolve, which
-            // also re-stamps it against VkSamplerManager's frame-boundary sweep).
-            //
-            // This one field is keyed by binding but describes ONE descriptor, so it is
-            // written and read only for single-descriptor bindings. A sampler ARRAY's
-            // elements share the binding and would overwrite each other here - the last
-            // element resolved would then be handed to element 0 on the next hinted draw.
-            // Every other field above is self-validating (each compares its full key
-            // before reuse, and the view-format entry is a pure function of format and
-            // numeric domain), so an arrayed binding may keep using those.
-            VkDescriptorImageInfo info{};
-            Bool infoValid = false;
         };
         mutable Vector<SamplerResolveMemo> m_samplerResolveMemo;
-        // Exclusive upper bound on the entries of m_samplerResolveMemo that any resolve
-        // has ever written. The vector is sized to the DEVICE binding cap (256 on desktop
-        // NVIDIA), but a program declares 1-8 bindings, so the per-frame reset below was
-        // memsetting ~22 KB of never-touched entries every frame - a measurable slice of
-        // the per-frame fixed cost on draw-light frames. Every site that can turn any of
-        // an entry's *Valid flags on raises this mark first, so entries at or above it are
-        // provably still in their constructed (all-invalid) state and clearing them is a
-        // no-op. Never lowered except by Initialize/Shutdown, which rebuild the vector.
-        mutable Uint32 m_samplerResolveMemoHighWater = 0;
-        void NoteSamplerResolveMemoTouched(Uint32 binding) const {
-            if (binding >= m_samplerResolveMemoHighWater) {
-                m_samplerResolveMemoHighWater = binding + 1;
-            }
-        }
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateFactory.cpp

@@ -7,13 +7,7 @@
 // End of Source File Header
 
 #include "VertexInputStateFactory.h"
-#include "MagmaPipeArms.h"
 #include "MG_Util/Converters/MGToStr/DataTypeConverter.h"
-#include <MG_Backend/BackendObjects.h>
-#if MOBILEGL_BUILD_DISAGGREGATED
-#include <Config.h>
-#include <MG_Remote/Server/ServerLoop.h>
-#endif
 #include <utility>
 
 namespace MobileGL::MG_Backend::DirectVulkan {
@@ -35,192 +29,36 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Stride, sizeof(attr.Stride)));
             XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Offset, sizeof(attr.Offset)));
             XXHASH_VERIFY(XXH64_update(m_hashState, &attr.IsInteger, sizeof(attr.IsInteger)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attr.IsLong, sizeof(attr.IsLong)));
             XXHASH_VERIFY(XXH64_update(m_hashState, &attr.IsBgra, sizeof(attr.IsBgra)));
             XXHASH_VERIFY(XXH64_update(m_hashState, &attr.Divisor, sizeof(attr.Divisor)));
 
-            // The bound buffer's IDENTITY is a component of the key, and it has to be the
-            // buffer's never-reused lifetime id - NOT its heap address, which this used to
-            // hash. An address is recycled by the allocator, so a deleted-and-recreated
-            // buffer reproduces it; combined with a byte-identical attribute layout that
-            // reproduces the WHOLE content hash, and the hash is what
-            // TryBindResolvedVertexBindings accepts as proof that a memoised binding still
-            // reads the buffer it was resolved from. It did not: a destroyed buffer's GPU
-            // slice was bound for its successor's draw, which is how a transform-feedback
-            // capture came back holding a dead VAO's vertex data (0,0,0,1 - the previous
-            // test's positions) instead of its own.
-            // Zero for client memory (no buffer), which is a distinct identity of its own.
-            //
-            // P2 D12.4 / ARCHITECTURE.md 9.5: under the handle arm the identity is the
-            // buffer's {slot, gen} rather than its lifetime id - "lifetimeId -> gen mixed
-            // into every server-side content hash". The two are equally ABA-proof (the
-            // allocator maps one onto the other and bumps Gen only on slot REUSE); what
-            // changes is that the key is now the identity the SERVER will be handed once
-            // buffers travel as handles, instead of a number only the client can mint.
-            Uint64 bufferKey = attr.Buffer ? attr.Buffer->GetLifetimeId() : 0;
-#if MOBILEGL_PIPE_PUSH
-            if (attr.Buffer) {
-                // The SAME arm question the other four re-keyed sites ask, through the same
-                // helper: a site that decided for itself could silently key on the pre-handle
-                // identity while its neighbours keyed on the handle.
-                if (MagmaPipeTrackHArmIsHandles(MG_Pipe::kMGPipeSubsystemMagmaVertexInput)) {
-                    const MG_Pipe::MGPipeHandle handle =
-                        m_identity->HandleOf(MG_Pipe::MGPipeKind::Buffer, attr.Buffer->GetLifetimeId());
-                    bufferKey = static_cast<Uint64>(handle.Slot) | (static_cast<Uint64>(handle.Gen) << 32);
-                }
-                if (MagmaPipeAbaControlDefeatsIdentity()) {
-                    // Negative control C (P2 brief D18), on WHICHEVER arm this run is on - the
-                    // pre-handle lifetime id and the handle's {slot, gen} are the same guard
-                    // wearing two hats, and a control that defeated only the retired one would
-                    // say nothing about the key P2 ships.
-                    //
-                    // The identity is replaced by a constant rather than by the raw
-                    // BufferObject*, because the address is not recycled in practice and so
-                    // never collides (see MagmaPipeAbaControlDefeatsIdentity). Zero is what a
-                    // key with NO buffer identity in it looks like - the exact defect this
-                    // hash was fixed for: "the hash is what TryBindResolvedVertexBindings
-                    // accepts as proof that a memoised binding still reads the buffer it was
-                    // resolved from", and with the identity gone it accepts a binding resolved
-                    // from a different buffer. HandleRecycleScenario.AbaControl then draws a
-                    // replacement VAO and gets its dead predecessor's vertex data.
-                    bufferKey = 0;
-                }
-            }
-#endif
+            const SizeT bufferKey = reinterpret_cast<SizeT>(attr.Buffer.get());
             XXHASH_VERIFY(XXH64_update(m_hashState, &bufferKey, sizeof(bufferKey)));
         }
 
         return XXH64_digest(m_hashState);
     }
 
-#if MOBILEGL_PIPE_PUSH
-    VertexInputStateFactory::VaoBackendMemos& VertexInputStateFactory::MemosFor(
-        const MG_State::GLState::VertexArrayObject& vao) const {
-        const MG_Pipe::MGPipeHandle handle =
-            m_identity->HandleOf(MG_Pipe::MGPipeKind::VertexElementsCso, vao.GetLifetimeId());
-        // One entry per mintable slot, grown on demand: the mint has no capacity, so neither
-        // does this, and no two live VAOs can share an entry however large the working set is.
-        // There is no probe in front of it because the mint itself is one - a one-entry memo
-        // hit for every acquisition after this draw's first, and a hash probe otherwise.
-        //
-        // The claim rule - the slot picks the entry, the whole handle (Gen included) decides
-        // whose it is - and negative control C's defeat of it are MagmaPipeArms.h's
-        // MagmaPipeClaimSlotMemos, so that the unit suite which drives a REAL slot reuse
-        // (MG_Test/Pipe/MagmaPipeIdentityTest.cpp) exercises this code and not a copy of it.
-        // What the control defeats HERE is the identity that SELECTS the entry: every VAO
-        // collapses onto one, handed back uncleared, so the replacement inherits the dead
-        // VAO's content hash and its resolved-entry pointer. The GENERATION half is the unit
-        // suite's business, for the reason MagmaPipeAbaControlDefeatsIdentity spells out.
-        return MagmaPipeClaimSlotMemos(m_vaoMemos, handle);
-    }
-#endif
-
-#if MOBILEGL_PIPE_PUSH
-    Bool VertexInputStateFactory::TryGetMemoizedHash(const MG_State::GLState::VertexArrayObject& vao,
-                                                     Uint64& outHash) const {
-        if (MagmaPipeTrackHArmIsHandles(MG_Pipe::kMGPipeSubsystemMagmaVertexInput)) {
-            const VaoBackendMemos& memos = MemosFor(vao);
-            if (memos.HashConfigVersion != vao.GetConfigVersion()) return false;
-            outHash = memos.Hash;
-            return true;
-        }
-#if MOBILEGL_PIPE_LEGACY_MEMOS
-        return vao.GetBackendHashMemo(outHash);
-#else
-        return false;
-#endif
-    }
-#endif
-
     VertexInputStateFactory::HashType VertexInputStateFactory::GetOrComputeHash(
         const MG_State::GLState::VertexArrayObject& vao) const {
         HashType hash = 0;
-#if MOBILEGL_PIPE_PUSH
-        // P2 D12.5: the same memo, on the backend's side of the boundary.
-        if (MagmaPipeTrackHArmIsHandles(MG_Pipe::kMGPipeSubsystemMagmaVertexInput)) {
-            VaoBackendMemos& memos = MemosFor(vao);
-            if (memos.HashConfigVersion == vao.GetConfigVersion()) {
-                return memos.Hash;
-            }
-            hash = ComputeHash(vao);
-            memos.Hash = hash;
-            memos.HashConfigVersion = vao.GetConfigVersion();
-            return hash;
-        }
-#endif
-#if MOBILEGL_PIPE_LEGACY_MEMOS
         if (!vao.GetBackendHashMemo(hash)) {
             hash = ComputeHash(vao);
             vao.SetBackendHashMemo(hash);
         }
-#endif
         return hash;
     }
 
     const VertexInputStateFactory::BackendVertexInputState& VertexInputStateFactory::GetOrCreateVertexInputState(
         const MG_State::GLState::VertexArrayObject& vao) {
-#if MOBILEGL_PIPE_PUSH
-        // P2 D12.5: the same per-draw fast path, but the resolved-entry pointer lives in this
-        // factory's slot-indexed table instead of on the frontend VAO. The eviction epoch
-        // survives the move and is still what stops a stale pointer being dereferenced: the
-        // POINTEE is a cache entry this factory can erase at a frame boundary, and moving the
-        // memo does not change that.
-        if (MagmaPipeTrackHArmIsHandles(MG_Pipe::kMGPipeSubsystemMagmaVertexInput)) {
-            VaoBackendMemos& memos = MemosFor(vao);
-            if (memos.StateConfigVersion == vao.GetConfigVersion() && memos.State != nullptr &&
-                memos.StateEpoch == m_evictionEpoch) {
-                const auto* memoEntry = static_cast<const BackendVertexInputState*>(memos.State);
-                memoEntry->lastUsedFrameBoundary = m_frameBoundaryCounter;
-                return *memoEntry;
-            }
-            const BackendVertexInputState& resolved =
-                GetOrCreateVertexInputState(vao, GetOrComputeHash(vao));
-            // MemosFor is re-taken rather than kept live across GetOrCreateVertexInputState:
-            // the reference is not worth holding across a call that can resize the table.
-            VaoBackendMemos& stamp = MemosFor(vao);
-            stamp.State = &resolved;
-            stamp.StateEpoch = m_evictionEpoch;
-            stamp.StateConfigVersion = vao.GetConfigVersion();
-            // The AUX memo is deliberately NOT stamped here: its two words already live in
-            // VulkanRenderer::VaoDrawMemo (layoutHash / layoutAuxMasks) and its getter has no
-            // live reader anywhere, so the handle arm retires it rather than moving it.
-            return resolved;
-        }
-#endif
-#if !MOBILEGL_PIPE_LEGACY_MEMOS
-        // Unreachable: with no legacy arm compiled MagmaPipeTrackHArmIsHandles is a compile-
-        // time true, so the handle arm above always returns. Written out rather than left to
-        // fall off the end so the function still has a return on every path a compiler sees.
         return GetOrCreateVertexInputState(vao, GetOrComputeHash(vao));
-#else
-        // Per-draw fast path: the VAO carries a pointer to its resolved entry,
-        // valid while its config version and the cache's eviction epoch both
-        // match - no re-hash, no map lookup.
-        const void* memoState = nullptr;
-        Uint64 memoEpoch = 0;
-        if (vao.GetBackendStateMemo(memoState, memoEpoch) && memoEpoch == m_evictionEpoch) {
-            const auto* entry = static_cast<const BackendVertexInputState*>(memoState);
-            entry->lastUsedFrameBoundary = m_frameBoundaryCounter;
-            return *entry;
-        }
-        const BackendVertexInputState& entry = GetOrCreateVertexInputState(vao, GetOrComputeHash(vao));
-        vao.SetBackendStateMemo(&entry, m_evictionEpoch);
-        // Also mirror the layout identity and the two per-draw masks into the VAO's aux
-        // memo (pure VALUES derived from the VAO configuration, so config-version
-        // guarding alone is sound). The draw fast path reads them from the VAO object it
-        // already touched instead of chasing into this entry - see PackVertexInputAuxMemo.
-        vao.SetBackendAuxMemo(entry.layoutHash,
-                              PackVertexInputAuxMasks(entry.unsupportedAttribMask, entry.attributeLocationMask));
-        return entry;
-#endif // MOBILEGL_PIPE_LEGACY_MEMOS
     }
 
     const VertexInputStateFactory::BackendVertexInputState& VertexInputStateFactory::GetOrCreateVertexInputState(
         const MG_State::GLState::VertexArrayObject& vao, HashType hash) {
         auto it = m_cache.find(hash);
         if (it != m_cache.end()) {
-            it->second->lastUsedFrameBoundary = m_frameBoundaryCounter;
-            return *it->second;
+            return it->second;
         }
 
         VertexInputStateBuilder builder;
@@ -229,7 +67,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Vector<Uint32> bindingAttributeLocations;
         Vector<Bool> bindingUsesClientMemory;
         Vector<VertexStreamConversion> bindingConversions;
-        Vector<VkVertexInputBindingDivisorDescriptionEXT> bindingDivisors;
         Uint32 unsupportedAttribMask = 0;
 
         for (Uint32 location = 0; location < MG_State::GLState::VertexArrayObject::MAX_VERTEX_ATTRIBS; ++location) {
@@ -238,46 +75,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 continue;
             }
 
-            VkFormat sourceVkFormat =
-                ToVkVertexFormat(attr.Type, attr.Size, attr.Normalized, attr.IsInteger, attr.IsBgra, attr.IsLong);
-            VertexStreamConversion conversion = VertexStreamConversion::None;
-            // Gated on the SAME flag ToVkVertexFormat gates its 64-bit path on, and that is
-            // load-bearing rather than belt-and-braces: the narrowing is only correct because the
-            // shader's `dvec` input is a `vec` by the time the pipeline is built, and what
-            // guarantees that is the flag being clear. It is clear on every backend today, and a
-            // program with a 64-bit float vertex input is demoted WHOLE for the same reason even
-            // where the device has native fp64 (ProgramSpirvTask::GenerateSpirv). With the flag
-            // set, a dvec3/dvec4 would be declined by ToVkVertexFormat AND left 64-bit in the
-            // module, so a float32 stream would be fed to a Float64 input.
-            const Bool narrowFloat64Arrays =
-#if MOBILEGL_BUILD_DISAGGREGATED
-                // P5c (hd, CONTRACT-P5C §3.7): with an active transport the answer is the
-                // SERVER's own backend's - the client caps mirror is client memory (rule E).
-                MG_Config::Transport != MG_Config::TransportMode::Monolith
-                    ? (MG_Remote::Server::ServerLoopInstance().Backend() == nullptr ||
-                       !MG_Remote::Server::ServerLoopInstance().Backend()
-                            ->GetDynamicParameters()
-                            .SupportsFloat64VertexAttributes)
-                    :
-#endif
-                MG_Backend::pActiveBackendObject == nullptr ||
-                !MG_Backend::pActiveBackendObject->GetDynamicParameters().SupportsFloat64VertexAttributes;
-            if (sourceVkFormat == VK_FORMAT_UNDEFINED && attr.Type == DataType::Float64 && narrowFloat64Arrays) {
-                // No native 64-bit fetch here (see ToVkVertexFormat's Float64 case), but the
-                // source bytes are ordinary IEEE-754 doubles and DemoteFloat64Pass has already
-                // narrowed every dvec input to a vec, so the array is narrowed to match rather
-                // than dropped. Mirrors what DirectGLES does for the same state.
-                const VkFormat narrowedFormat = ToFloat32VertexFormat(attr.Size);
-                if (narrowedFormat != VK_FORMAT_UNDEFINED && SupportsVertexBufferFormat(narrowedFormat)) {
-                    sourceVkFormat = narrowedFormat;
-                    conversion = VertexStreamConversion::Float64ToFloat32;
-                    MGLOG_W_ONCE("Vertex attribute location=%u is a 64-bit (GL_DOUBLE) array; fetching it at "
-                            "float32 precision through format=%d (size=%d long=%s)",
-                            location, static_cast<Int>(narrowedFormat), attr.Size, attr.IsLong ? "true" : "false");
-                }
-            }
+            const VkFormat sourceVkFormat =
+                ToVkVertexFormat(attr.Type, attr.Size, attr.Normalized, attr.IsInteger, attr.IsBgra);
             if (sourceVkFormat == VK_FORMAT_UNDEFINED) {
-                MGLOG_E_ONCE("Unsupported vertex attribute layout (location=%u, type=%s, size=%d): the array is "
+                MGLOG_E("Unsupported vertex attribute layout (location=%u, type=%s, size=%d): the array is "
                         "enabled but cannot be mapped to a VkFormat",
                         location, MG_Util::ConvertDataTypeToString(attr.Type).c_str(), attr.Size);
                 unsupportedAttribMask |= (1u << location);
@@ -285,13 +86,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             }
 
             VkFormat vkFormat = sourceVkFormat;
-            if (conversion == VertexStreamConversion::None && !SupportsVertexBufferFormat(vkFormat)) {
+            VertexStreamConversion conversion = VertexStreamConversion::None;
+            if (!SupportsVertexBufferFormat(vkFormat)) {
                 if (IsScaledIntegerVertexFormat(vkFormat)) {
                     const VkFormat fallbackFormat = ToFloat32VertexFormat(attr.Size);
                     if (fallbackFormat != VK_FORMAT_UNDEFINED && SupportsVertexBufferFormat(fallbackFormat)) {
                         vkFormat = fallbackFormat;
                         conversion = VertexStreamConversion::ScaledIntegerToFloat32;
-                        MGLOG_W_ONCE("Vertex attribute location=%u format=%d lacks "
+                        MGLOG_W("Vertex attribute location=%u format=%d lacks "
                                 "VK_FORMAT_FEATURE_VERTEX_BUFFER_BIT; using float32 stream format=%d "
                                 "(type=%s size=%d normalized=%s integer=%s)",
                                 location, static_cast<Int>(sourceVkFormat), static_cast<Int>(vkFormat),
@@ -301,7 +103,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                 }
 
                 if (conversion == VertexStreamConversion::None) {
-                    MGLOG_E_ONCE("Unsupported Vulkan vertex format (location=%u, format=%d, type=%s, size=%d): "
+                    MGLOG_E("Unsupported Vulkan vertex format (location=%u, format=%d, type=%s, size=%d): "
                             "VK_FORMAT_FEATURE_VERTEX_BUFFER_BIT is unavailable and no semantic fallback exists",
                             location, static_cast<Int>(sourceVkFormat),
                             MG_Util::ConvertDataTypeToString(attr.Type).c_str(), attr.Size);
@@ -312,52 +114,34 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
             const SizeT attribByteSize = GetAttributeByteSize(attr.Type, attr.Size, attr.IsBgra);
             if (attribByteSize == 0) {
-                MGLOG_E_ONCE("Vertex attribute with unknown component size (location=%u, type=%s): the array is "
+                MGLOG_E("Vertex attribute with unknown component size (location=%u, type=%s): the array is "
                         "enabled but cannot be sized",
                         location, MG_Util::ConvertDataTypeToString(attr.Type).c_str());
                 unsupportedAttribMask |= (1u << location);
                 continue;
             }
 
-            // Verbatim, zero included. The frontend already resolved a pointer call's
-            // "tightly packed" stride 0 into the element size (see VertexAttribute::Stride),
-            // so a zero here is the binding model's stride 0 - every vertex reads the same
-            // element - which is exactly what a zero VkVertexInputBindingDescription::stride
-            // means. Substituting the element size fetched a fresh element per vertex and ran
-            // off the end of the buffer (KHR-GL43.vertex_attrib_binding.basic-input-case7/8).
-            // Client-memory arrays cannot reach zero: they only exist on the pointer path.
-            const Uint32 sourceStride = static_cast<Uint32>(attr.Stride);
+            const Uint32 sourceStride =
+                attr.Stride > 0 ? static_cast<Uint32>(attr.Stride) : static_cast<Uint32>(attribByteSize);
             const Bool packedAttribute = attr.Type == DataType::Int2101010Rev ||
                                          attr.Type == DataType::Uint2101010Rev;
             const SizeT requiredAlignment = packedAttribute ? attribByteSize : GetComponentSize(attr.Type);
-            // For a client-memory array attr.Offset holds the raw client pointer, and the
-            // draw path re-uploads the data to a 16-aligned transient slice with attribute
-            // offset 0, so only the stride can violate Vulkan's fetch alignment there.
-            const Bool clientMemoryAttribute = attr.Buffer == nullptr;
             if (conversion == VertexStreamConversion::None && requiredAlignment > 1 &&
-                ((sourceStride % requiredAlignment) != 0 ||
-                 (!clientMemoryAttribute && (attr.Offset % requiredAlignment) != 0))) {
+                ((sourceStride % requiredAlignment) != 0 || (attr.Offset % requiredAlignment) != 0)) {
                 // GL accepts arbitrary byte strides and offsets. Core Vulkan vertex fetches do not
                 // unless VK_EXT_legacy_vertex_attributes is available, so deinterleave this one
                 // attribute into a tightly packed transient stream without changing its format.
                 conversion = VertexStreamConversion::Repack;
-                MGLOG_W_ONCE("Vertex attribute location=%u uses Vulkan-incompatible alignment "
+                MGLOG_W("Vertex attribute location=%u uses Vulkan-incompatible alignment "
                         "(offset=%zu stride=%u required=%zu); using a tightly packed stream",
                         location, attr.Offset, sourceStride, requiredAlignment);
             }
 
             Uint32 stride = sourceStride;
-            // A converted stream is tightly packed, so its stride is the converted element
-            // size - unless the source stride is zero, which does not describe a packing at
-            // all but "never advance". That survives the conversion unchanged: the draw path
-            // converts exactly one element and every vertex reads it.
-            if (sourceStride != 0) {
-                if (conversion == VertexStreamConversion::Repack) {
-                    stride = static_cast<Uint32>(attribByteSize);
-                } else if (conversion == VertexStreamConversion::ScaledIntegerToFloat32 ||
-                           conversion == VertexStreamConversion::Float64ToFloat32) {
-                    stride = static_cast<Uint32>(attr.Size * static_cast<Int>(sizeof(Float)));
-                }
+            if (conversion == VertexStreamConversion::Repack) {
+                stride = static_cast<Uint32>(attribByteSize);
+            } else if (conversion == VertexStreamConversion::ScaledIntegerToFloat32) {
+                stride = static_cast<Uint32>(attr.Size * static_cast<Int>(sizeof(Float)));
             }
             const VkVertexInputRate inputRate =
                 (attr.Divisor == 0) ? VK_VERTEX_INPUT_RATE_VERTEX : VK_VERTEX_INPUT_RATE_INSTANCE;
@@ -371,51 +155,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             bindingConversions.push_back(conversion);
             builder.AddBinding(binding, stride, inputRate);
             builder.AddAttribute(location, binding, vkFormat, 0);
-            // Divisor 1 is what VK_VERTEX_INPUT_RATE_INSTANCE already means; only anything
-            // else needs the extension to say it.
-            if (inputRate == VK_VERTEX_INPUT_RATE_INSTANCE && attr.Divisor != 1) {
-                bindingDivisors.push_back({binding, static_cast<Uint32>(attr.Divisor)});
-            }
         }
 
         const auto& state = builder.Build();
 
-        auto& slot = m_cache[hash];
-        if (!slot) {
-            slot = MakeUnique<BackendVertexInputState>();
-        }
-        BackendVertexInputState& entry = *slot;
+        auto& entry = m_cache[hash];
         entry.hash = hash;
-        entry.lastUsedFrameBoundary = m_frameBoundaryCounter;
-        entry.bindingDivisors = Move(bindingDivisors);
         entry.bindings = builder.GetBindings();
         entry.attributes = builder.GetAttributes();
-        // See the layoutHash declaration: hash only the resolved layout, never
-        // buffer identities, so identical layouts across VAOs/buffers agree.
-        XXHASH_VERIFY(XXH64_reset(m_hashState, 0));
-        for (const auto& binding : entry.bindings) {
-            XXHASH_VERIFY(XXH64_update(m_hashState, &binding.binding, sizeof(binding.binding)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &binding.stride, sizeof(binding.stride)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &binding.inputRate, sizeof(binding.inputRate)));
-        }
-        for (const auto& attribute : entry.attributes) {
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attribute.location, sizeof(attribute.location)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attribute.binding, sizeof(attribute.binding)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attribute.format, sizeof(attribute.format)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &attribute.offset, sizeof(attribute.offset)));
-        }
-        for (const auto& divisor : entry.bindingDivisors) {
-            XXHASH_VERIFY(XXH64_update(m_hashState, &divisor.binding, sizeof(divisor.binding)));
-            XXHASH_VERIFY(XXH64_update(m_hashState, &divisor.divisor, sizeof(divisor.divisor)));
-        }
-        XXHASH_VERIFY(XXH64_update(m_hashState, &unsupportedAttribMask, sizeof(unsupportedAttribMask)));
-        entry.layoutHash = XXH64_digest(m_hashState);
-        entry.attributeLocationMask = 0;
-        for (const auto& attribute : entry.attributes) {
-            if (attribute.location < 32u) {
-                entry.attributeLocationMask |= (1u << attribute.location);
-            }
-        }
         entry.bindingBufferKeys = std::move(bindingBufferKeys);
         entry.bindingBaseOffsets = std::move(bindingBaseOffsets);
         entry.bindingAttributeLocations = std::move(bindingAttributeLocations);
@@ -425,193 +172,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         entry.state = state;
         entry.state.pVertexBindingDescriptions = entry.bindings.empty() ? nullptr : entry.bindings.data();
         entry.state.pVertexAttributeDescriptions = entry.attributes.empty() ? nullptr : entry.attributes.data();
-        if (!entry.bindingDivisors.empty()) {
-            entry.divisorState.vertexBindingDivisorCount = static_cast<Uint32>(entry.bindingDivisors.size());
-            entry.divisorState.pVertexBindingDivisors = entry.bindingDivisors.data();
-            entry.state.pNext = &entry.divisorState;
-        } else {
-            entry.state.pNext = nullptr;
-        }
         return entry;
     }
 
-#if MOBILEGL_BUILD_DISAGGREGATED
-    Bool VertexInputStateFactory::BuildWireVertexInput(const MG_Pipe::MGPipeVertexElementsRecord& elements,
-            const MG_Pipe::MGPipeApplierState& state, Uint32 activeMask, BackendVertexInputState& out) const {
-        out = BackendVertexInputState{};
-        for (Uint32 location = 0; location < elements.AttributeCount; ++location) {
-            const auto& attr = elements.Attributes[location];
-            if (!attr.Enabled || !(activeMask & (1u << location))) continue;
-            // P7 wave 2 package C, CONTRACT-P7 §3.2 `vertex-layout`: THE ONE STRING BECAME TWO
-            // VERDICTS, and the split is by what the reason is ABOUT rather than by severity.
-            //
-            // Every reason here used to return false, and the single caller answered that with
-            // one P7-marked MagmaWireFatal - an abort, bypassing Session::Fail, invisible
-            // to the census gate and with no equivalent on the monolith arm at all. But the
-            // reasons are not one kind of thing:
-            //
-            //   * `buffer-window` is a statement about the RECORD: an enabled attribute the
-            //     program reads names a slot outside the window set_vertex_buffers published.
-            //     Nothing about the device or the format is involved; the two halves of the
-            //     protocol disagree about what crossed. It stays a named Fatal through the hook
-            //     (see the caller), and it is load-bearing rather than defensive - it is what
-            //     caught the Redmi VAO hash collision fixed in 376c04be.
-            //
-            //   * every other reason is a statement about what VULKAN CAN EXPRESS on this
-            //     device: a GL type with no VkFormat, a format without
-            //     VK_FORMAT_FEATURE_VERTEX_BUFFER_BIT, a component size we cannot compute, an
-            //     offset sum that does not fit. The monolith arm has had an answer for these
-            //     since it was written, and it is not an abort: mask the attribute out of the
-            //     vertex input state and carry on (the `unsupportedAttribMask |= ...; continue;`
-            //     sites in GetOrCreateVertexInputState above). The draw path then decides,
-            //     loudly and once, whether the masked attribute was one the program actually
-            //     reads. This arm now does exactly that, which is what "same observable as the
-            //     monolith lane" means for this row.
-            //
-            // THE COUNT: the contract says "the other six"; there are SEVEN return sites below
-            // it, because `offset-overflow` was added after the audit's count and is an
-            // arithmetic guard rather than a shape one. It is masked with the rest: an
-            // attribute whose base offsets cannot be added is one Vulkan cannot fetch, the
-            // monolith arm never computes that sum at all, and masking is strictly safer than
-            // a Fatal for a number no application can reach on purpose. Recorded in
-            // notes/p7/magma-c.md rather than silently reconciled.
-            const auto describe = [&](const char* reason, VkFormat format) {
-                MGLOG_E_ONCE("Magma wire vertex layout: %s location=%u type=%u size=%u normalized=%u integer=%u long=%u bgra=%u stride=%d offset=%llu format=%d bufferWindow=%u+%u activeMask=0x%x",
-                    reason, location, attr.Type, static_cast<Uint32>(attr.Size), static_cast<Uint32>(attr.Normalized),
-                    static_cast<Uint32>(attr.IsInteger), static_cast<Uint32>(attr.IsLong), static_cast<Uint32>(attr.IsBgra),
-                    attr.Stride, static_cast<unsigned long long>(attr.Offset), static_cast<Int>(format),
-                    state.VertexBufferStart, state.VertexBufferCount, activeMask);
-            };
-            // The protocol verdict: the caller turns a false into the named Fatal.
-            const auto reject = [&](const char* reason, VkFormat format = VK_FORMAT_UNDEFINED) {
-                describe(reason, format);
-                return false;
-            };
-            // The device verdict: MGLOG_E_ONCE + mask + continue, the monolith arm's shape.
-            // MGLOG_E_ONCE and not MGLOG_E, also the monolith arm's: an unmappable attribute is
-            // a property of the VAO and the device, so it repeats every draw, and the per-draw
-            // line is what made the old abort look preferable to whoever wrote it.
-            const auto maskOut = [&](const char* reason, VkFormat format = VK_FORMAT_UNDEFINED) {
-                describe(reason, format);
-                out.unsupportedAttribMask |= 1u << location;
-            };
-            // set_vertex_buffers is flattened PER ATTRIBUTE (VertexInputEmit.h), not
-            // indexed by the original ARB binding point in attr.BindingIndex.
-            if (location < state.VertexBufferStart ||
-                location - state.VertexBufferStart >= state.VertexBufferCount) return reject("buffer-window");
-            const auto& buffer = state.VertexBuffers[location];
-            const auto type = static_cast<DataType>(attr.Type);
-            if (attr.Stride < 0 || attr.Size < 1 || attr.Size > 4) { maskOut("attribute-shape"); continue; }
-            VkFormat format = ToVkVertexFormat(type, attr.Size, attr.Normalized, attr.IsInteger,
-                                               attr.IsBgra, attr.IsLong);
-            auto conversion = VertexStreamConversion::None;
-            if (format == VK_FORMAT_UNDEFINED && type == DataType::Float64) {
-                const auto* backend = MG_Remote::Server::ServerLoopInstance().Backend();
-                if (backend && backend->GetDynamicParameters().SupportsFloat64VertexAttributes) {
-                    // Exactly the monolith arm's answer for the same state: with native fp64
-                    // the module KEPT its 64-bit inputs (DemoteFloat64Pass did not run), so
-                    // narrowing the stream would feed float32 to a Float64 input - and the
-                    // monolith build therefore leaves sourceVkFormat UNDEFINED and falls into
-                    // its own mask-out below. Same place, same mask.
-                    maskOut("native-fp64-format");
-                    continue;
-                }
-                format = ToFloat32VertexFormat(attr.Size);
-                conversion = VertexStreamConversion::Float64ToFloat32;
-            }
-            if (format == VK_FORMAT_UNDEFINED) { maskOut("format-map"); continue; }
-            if (!SupportsVertexBufferFormat(format)) {
-                if (!IsScaledIntegerVertexFormat(format)) { maskOut("native-format-feature", format); continue; }
-                format = ToFloat32VertexFormat(attr.Size);
-                conversion = VertexStreamConversion::ScaledIntegerToFloat32;
-                if (!SupportsVertexBufferFormat(format)) { maskOut("converted-format-feature", format); continue; }
-            }
-            const SizeT elementSize = GetAttributeByteSize(type, attr.Size, attr.IsBgra);
-            if (!elementSize) { maskOut("element-size", format); continue; }
-            const Uint64 offset = attr.Offset + buffer.Offset;
-            if (offset < attr.Offset) { maskOut("offset-overflow", format); continue; }
-            const SizeT alignment = (type == DataType::Int2101010Rev || type == DataType::Uint2101010Rev)
-                ? elementSize : GetComponentSize(type);
-            if (conversion == VertexStreamConversion::None && alignment > 1 &&
-                (offset % alignment || static_cast<Uint32>(attr.Stride) % alignment))
-                conversion = VertexStreamConversion::Repack;
-            Uint32 stride = static_cast<Uint32>(attr.Stride);
-            if (stride && conversion != VertexStreamConversion::None)
-                stride = conversion == VertexStreamConversion::Repack ? static_cast<Uint32>(elementSize)
-                    : static_cast<Uint32>(attr.Size) * sizeof(Float);
-            const Uint32 binding = static_cast<Uint32>(out.bindings.size());
-            out.bindings.push_back({binding, stride,
-                buffer.Divisor ? VK_VERTEX_INPUT_RATE_INSTANCE : VK_VERTEX_INPUT_RATE_VERTEX});
-            out.attributes.push_back({location, binding, format, 0});
-            out.bindingAttributeLocations.push_back(location);
-            out.bindingBaseOffsets.push_back(static_cast<SizeT>(offset));
-            out.bindingConversions.push_back(conversion);
-            if (buffer.Divisor > 1) out.bindingDivisors.push_back({binding, buffer.Divisor});
-            out.attributeLocationMask |= 1u << location;
-        }
-        // Native handles/offsets do not decide the pipeline layout. Include only the
-        // resolved binding/attribute/divisor values, including a legal zero stride.
-        Uint64 hash = XXH64(out.bindings.data(), out.bindings.size() * sizeof(out.bindings[0]), 0);
-        hash = XXH64(out.attributes.data(), out.attributes.size() * sizeof(out.attributes[0]), hash);
-        hash = XXH64(out.bindingDivisors.data(),
-            out.bindingDivisors.size() * sizeof(out.bindingDivisors[0]), hash);
-        // THE MASK IS PART OF THE LAYOUT NOW, for the same reason the monolith entry's hash
-        // carries it (the XXH64_update over unsupportedAttribMask in GetOrCreateVertexInputState
-        // above). Before this package the mask was always zero here, so leaving it out of the
-        // hash was free; now two VAOs can produce the SAME bindings, attributes and divisors
-        // and differ only in which enabled attribute was masked out, and a hash blind to that
-        // would serve one of them the other's pipeline.
-        out.layoutHash = XXH64(&out.unsupportedAttribMask, sizeof(out.unsupportedAttribMask), hash);
-        out.state.vertexBindingDescriptionCount = static_cast<Uint32>(out.bindings.size());
-        out.state.pVertexBindingDescriptions = out.bindings.data();
-        out.state.vertexAttributeDescriptionCount = static_cast<Uint32>(out.attributes.size());
-        out.state.pVertexAttributeDescriptions = out.attributes.data();
-        if (!out.bindingDivisors.empty()) {
-            out.divisorState.vertexBindingDivisorCount = static_cast<Uint32>(out.bindingDivisors.size());
-            out.divisorState.pVertexBindingDivisors = out.bindingDivisors.data();
-            out.state.pNext = &out.divisorState;
-        }
-        return true;
-    }
-#endif
-
-    void VertexInputStateFactory::OnFrameBoundary() {
-        ++m_frameBoundaryCounter;
-
-        // Sweep occasionally; evict entries whose last hit is far in the past.
-        // Erasure happens only here, never mid-frame: the draw path holds a
-        // reference into the current entry across its setup, and unordered_map
-        // erase would invalidate it. Entries are CPU-side only, so no GPU-idle
-        // proof is needed; an evicted entry that is used again is simply rebuilt
-        // from the VAO state (same hash, same content).
-        constexpr Uint64 kSweepInterval = 256;
-        constexpr Uint64 kRetireAgeBoundaries = 1024;
-        if ((m_frameBoundaryCounter % kSweepInterval) != 0) {
-            return;
-        }
-
-        for (auto it = m_cache.begin(); it != m_cache.end();) {
-            if (m_frameBoundaryCounter - it->second->lastUsedFrameBoundary > kRetireAgeBoundaries) {
-                it = m_cache.erase(it);
-                // Invalidate every VAO's state-pointer memo: the erased node's
-                // address may be reused by a future insert. Advance through the
-                // process-wide source so the value stays unique across factory
-                // instances (see the member comment). With no legacy arm the memos
-                // live in this factory and die with it, so a per-instance bump is
-                // enough - P2 D12.5.
-#if MOBILEGL_PIPE_LEGACY_MEMOS
-                m_evictionEpoch = ++s_evictionEpochSource;
-#else
-                ++m_evictionEpoch;
-#endif
-            } else {
-                ++it;
-            }
-        }
-    }
-
     VkFormat VertexInputStateFactory::ToVkVertexFormat(DataType type, Int size, Bool normalized, Bool isInteger,
-                                                       Bool isBgra, Bool isLong) {
+                                                       Bool isBgra) {
         if (isBgra) {
             // GL_BGRA: four reversed-order components, always normalized (enforced at validation), only
             // legal with GL_UNSIGNED_BYTE or a 2_10_10_10 type. The reversed VkFormats put the
@@ -636,46 +201,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         case DataType::Int2101010Rev:
             if (isInteger || size != 4) return VK_FORMAT_UNDEFINED;
             return normalized ? VK_FORMAT_A2B10G10R10_SNORM_PACK32 : VK_FORMAT_A2B10G10R10_SSCALED_PACK32;
-        case DataType::Float64:
-            // A 64-bit attribute is fetched as its 32-bit word pair and bitcast back to double in the
-            // shader (PackDoubleVertexInputsPass does the shader half). That is bit-exact and, unlike
-            // VK_FORMAT_R64*_SFLOAT, needs no format capability: lavapipe reports bufferFeatures = 0
-            // for every R64 float format, so a native 64-bit vertex fetch is simply unavailable there
-            // while shaderFloat64 is not. Both halves key off nothing but the attribute being long,
-            // so they always agree without extra plumbing.
-            //
-            // ... as long as the shader half still runs. It does not when the backend has declared
-            // no 64-bit vertex attribute support: DemoteFloat64Pass has already narrowed every
-            // `dvec` input to a `vec` by then, so PackDoubleVertexInputsPass finds nothing to pack
-            // and a UINT-formatted attribute would be fed to a float input - garbage with no
-            // diagnostic anywhere. Declining here hands the attribute to the caller's
-            // Float64ToFloat32 fallback instead, which narrows the source doubles to match the
-            // demoted `vec` input - the same thing DirectGLES does for the same state. The
-            // frontend RECORDS the format either way, so this gate is the only thing standing
-            // between a legal glVertexAttribLFormat and a mismatched pipeline.
-            if (
-#if MOBILEGL_BUILD_DISAGGREGATED
-                // P5c (hd, CONTRACT-P5C §3.7): see the narrowFloat64Arrays site above.
-                MG_Config::Transport != MG_Config::TransportMode::Monolith
-                    ? (MG_Remote::Server::ServerLoopInstance().Backend() == nullptr ||
-                       !MG_Remote::Server::ServerLoopInstance().Backend()
-                            ->GetDynamicParameters()
-                            .SupportsFloat64VertexAttributes)
-                    :
-#endif
-                MG_Backend::pActiveBackendObject == nullptr ||
-                !MG_Backend::pActiveBackendObject->GetDynamicParameters().SupportsFloat64VertexAttributes) {
-                return VK_FORMAT_UNDEFINED;
-            }
-            if (!isLong || isInteger || normalized) return VK_FORMAT_UNDEFINED;
-            switch (size) {
-            case 1: return VK_FORMAT_R32G32_UINT;
-            case 2: return VK_FORMAT_R32G32B32A32_UINT;
-            // A dvec3/dvec4 input is 6/8 uint32 components: no single VkFormat, and GL spreads it
-            // over two attribute locations, which the location-per-VAO-index model here does not
-            // express. Declined rather than fetched wrong.
-            default: return VK_FORMAT_UNDEFINED;
-            }
         case DataType::Float32:
             switch (size) {
             case 1: return VK_FORMAT_R32_SFLOAT;
@@ -847,17 +372,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         if (m_physicalDevice == VK_NULL_HANDLE || format == VK_FORMAT_UNDEFINED) {
             return false;
         }
-#if MOBILEGL_BUILD_DISAGGREGATED
-        if (MG_Config::Transport != MG_Config::TransportMode::Monolith) {
-            const auto found = m_wireVertexFormatSupport.find(format);
-            if (found != m_wireVertexFormatSupport.end()) return found->second;
-            VkFormatProperties properties{};
-            vkGetPhysicalDeviceFormatProperties(m_physicalDevice, format, &properties);
-            const Bool supported = (properties.bufferFeatures & VK_FORMAT_FEATURE_VERTEX_BUFFER_BIT) != 0;
-            m_wireVertexFormatSupport.emplace(format, supported);
-            return supported;
-        }
-#endif
         VkFormatProperties properties{};
         vkGetPhysicalDeviceFormatProperties(m_physicalDevice, format, &properties);
         return (properties.bufferFeatures & VK_FORMAT_FEATURE_VERTEX_BUFFER_BIT) != 0;

MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateFactory.h

@@ -7,15 +7,8 @@
 // End of Source File Header
 
 #pragma once
-// MG_Pipe::MGPipeHandle for the P2 D12.5 memo table below. A header of constexpr constants,
-// so the pull build gains nothing from it.
-#include <MG_Pipe/MGPipeHandles.h>
-#if MOBILEGL_BUILD_DISAGGREGATED
-#include <MG_Pipe/PipeApply.h>
-#endif
 
 #include "Config.h"
-#include "MagmaPipeArms.h"
 #include "VertexInputStateBuilder.h"
 #include "MG_State/GLState/VertexArrayState/VertexArrayObject.h"
 #include <Includes.h>
@@ -30,26 +23,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             None = 0,
             Repack,
             ScaledIntegerToFloat32,
-            // GL_DOUBLE source data narrowed to a tightly packed float32 stream: the fetch half
-            // of the fp64 demotion the shader side already does unconditionally.
-            Float64ToFloat32,
         };
 
         struct BackendVertexInputState {
             HashType hash = 0;
-            // Hash of the resolved Vulkan vertex layout only (bindings, attributes,
-            // unsupported mask) - NO buffer identities. `hash` mixes each bound
-            // buffer's never-reused LIFETIME ID, so per-chunk VBOs mint a fresh
-            // identity per buffer; keying pipelines on that minted one VkPipeline per
-            // chunk section for an identical layout, defeating pipeline reuse and the
-            // per-draw memo. Pipelines depend only on the layout, so they key on this
-            // instead.
-            HashType layoutHash = 0;
-            // Frame boundary of the last cache hit; entries idle past the
-            // OnFrameBoundary retirement age are evicted (CPU heap only).
-            // Mutable: the VAO's state-pointer memo fast path stamps it through
-            // a const entry reference.
-            mutable Uint64 lastUsedFrameBoundary = 0;
             Vector<VkVertexInputBindingDescription> bindings;
             Vector<VkVertexInputAttributeDescription> attributes;
             Vector<SizeT> bindingBufferKeys;
@@ -61,167 +38,38 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             // absent from `attributes`, so without this mask the draw path cannot tell them apart from
             // a genuinely disabled array and would silently feed the shader the current attribute value.
             Uint32 unsupportedAttribMask = 0;
-            // Bitmask of `attributes[i].location` - the draw path needs it up to
-            // three times per draw, so it is baked once at build time.
-            Uint32 attributeLocationMask = 0;
-            // Per-binding glVertexAttribDivisor values other than 1. Vulkan's instance input
-            // rate advances once per instance and nothing else, so anything else has to be
-            // stated through VK_EXT_vertex_attribute_divisor. Empty when every instanced
-            // binding uses divisor 1, which is what the plain input rate already means.
-            Vector<VkVertexInputBindingDivisorDescriptionEXT> bindingDivisors;
-            VkPipelineVertexInputDivisorStateCreateInfoEXT divisorState{
-                VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_DIVISOR_STATE_CREATE_INFO_EXT
-            };
             VkPipelineVertexInputStateCreateInfo state{
                 VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_STATE_CREATE_INFO
             };
         };
 
-#if MOBILEGL_PIPE_PUSH
-        // The mint is the RENDERER's (MagmaPipeIdentityTables), not a process-global and not
-        // this factory's: VulkanRenderer::LookupVaoDrawMemo has to derive the same {slot, gen}
-        // for the same VAO, and a table that outlived the context it was minted for would share
-        // one reclamation clock across two live contexts (review v2 minor 4).
-        VertexInputStateFactory(const VulkanRendererConfig& config, VkPhysicalDevice physicalDevice,
-                                MagmaPipeIdentityTables& identity):
-            m_config(config), m_physicalDevice(physicalDevice), m_identity(&identity) {}
-#else
         VertexInputStateFactory(const VulkanRendererConfig& config, VkPhysicalDevice physicalDevice):
             m_config(config), m_physicalDevice(physicalDevice) {}
-#endif
         ~VertexInputStateFactory() = default;
         VertexInputStateFactory(const VertexInputStateFactory&) = delete;
 
-        // The VAO aux-memo payload GetOrCreateVertexInputState(vao) stamps: aux0 is the
-        // entry's layoutHash, aux1 packs (unsupportedAttribMask << 32) | attributeLocationMask.
-        // Readers that find the aux memo valid can use these without resolving the entry.
-        static Uint64 PackVertexInputAuxMasks(Uint32 unsupportedAttribMask, Uint32 attributeLocationMask) {
-            return (static_cast<Uint64>(unsupportedAttribMask) << 32) | attributeLocationMask;
-        }
-
         HashType ComputeHash(const MG_State::GLState::VertexArrayObject& vao) const;
         // Memoized ComputeHash: reuses the VAO's cached hash while its config version
         // is unchanged. Use this on per-draw paths.
         HashType GetOrComputeHash(const MG_State::GLState::VertexArrayObject& vao) const;
-#if MOBILEGL_PIPE_PUSH
-        // The VAO's content hash IF it has already been memoized, without computing one.
-        // P2 D12.5: the three draw-path readers that used to ask the VAO object this
-        // question ask the factory instead, because that is where the memo lives once the
-        // frontend object stops carrying the backend's state.
-        Bool TryGetMemoizedHash(const MG_State::GLState::VertexArrayObject& vao, Uint64& outHash) const;
-#endif
         const BackendVertexInputState& GetOrCreateVertexInputState(
             const MG_State::GLState::VertexArrayObject& vao, HashType hash);
         const BackendVertexInputState& GetOrCreateVertexInputState(const MG_State::GLState::VertexArrayObject& vao);
-        // Frame boundary hook: ages the cache and evicts entries not hit for many
-        // frames. The key mixes each bound buffer's never-reused lifetime id, so
-        // buffer/VAO churn keeps minting fresh keys - and does so by construction,
-        // not by luck: a recreated buffer can no longer land back on its dead
-        // predecessor's key. Without eviction the map grows for the whole session.
-        // Entries hold no Vulkan handles (pipeline creation copies the descriptions)
-        // and the draw path's entry reference never spans a frame boundary, so
-        // eviction here needs no GPU-idle proof. Self-gated: one counter bump and
-        // compare except on sweep boundaries.
-        void OnFrameBoundary();
         static SizeT GetComponentSize(DataType type);
         // Tightly-packed byte size of one vertex element for this attribute: componentSize * size for
         // normal types, and 4 (one packed word) for the 2_10_10_10 types and GL_BGRA. Returns 0 for
         // an unknown/unsupported type.
         static SizeT GetAttributeByteSize(DataType type, Int size, Bool isBgra);
-#if MOBILEGL_BUILD_DISAGGREGATED
-        // A wire VAO is a layout record plus a separate per-attribute buffer window.
-        // No frontend VAO identity, address or memo participates in this layout.
-        Bool BuildWireVertexInput(const MG_Pipe::MGPipeVertexElementsRecord& elements,
-                                  const MG_Pipe::MGPipeApplierState& state, Uint32 activeMask,
-                                  BackendVertexInputState& out) const;
-#endif
 
     private:
-        static VkFormat ToVkVertexFormat(DataType type, Int size, Bool normalized, Bool isInteger, Bool isBgra = false,
-                                         Bool isLong = false);
+        static VkFormat ToVkVertexFormat(DataType type, Int size, Bool normalized, Bool isInteger, Bool isBgra = false);
         static Bool IsScaledIntegerVertexFormat(VkFormat format);
         static VkFormat ToFloat32VertexFormat(Int componentCount);
         Bool SupportsVertexBufferFormat(VkFormat format) const;
 
-#if MOBILEGL_PIPE_PUSH
-        // ---- P2 D12.5: the backend's memos, off the frontend VAO and into the backend ----
-        //
-        // The two facts that used to live as `mutable` fields on VertexArrayObject
-        // (Get/SetBackendHashMemo and Get/SetBackendStateMemo), kept here instead, keyed on
-        // the VAO's {slot, gen} and guarded by exactly the same config version. A frontend
-        // state object holding the backend's raw pointer is what P2 retires: under split the
-        // backend is in another process and its cache entry has no address a client could
-        // store, so the memo has to live on the side that owns the pointee.
-        //
-        // The AUX memo is not carried over: its two words moved into VaoDrawMemo::layoutHash
-        // and layoutAuxMasks long ago and its getter has no live reader anywhere in the tree,
-        // so the handle arm simply stops writing it (D12.5 says delete rather than move).
-        struct VaoBackendMemos {
-            // Whose memos these are. The identity table can recycle a slot for a different
-            // VAO under LRU pressure, and the handle compare - Gen included - is what says
-            // the contents are this object's and not its predecessor's.
-            MG_Pipe::MGPipeHandle Owner = MG_Pipe::kMGPipeNullHandle;
-            Uint64 Hash = 0;
-            Uint32 HashConfigVersion = ~0u;
-            const void* State = nullptr;
-            Uint64 StateEpoch = 0;
-            Uint32 StateConfigVersion = ~0u;
-        };
-        // Grow-on-demand (D12.4), one entry per slot the renderer's mint has ever handed
-        // out, and NO CAPACITY: these two memos had none before this package either - they
-        // were unbounded mutable fields on the VertexArrayObject itself - and re-introducing
-        // eviction here is what review v2 rejected. MagmaPipeSlotTable grows in chunks so an
-        // entry reference stays valid across the nested GetOrCreateVertexInputState call.
-        // 48 B per live VAO, reclaimed with the slot when the object goes idle.
-        mutable MagmaPipeSlotTable<VaoBackendMemos> m_vaoMemos;
-        // The renderer's {slot, gen} mint (see the constructor). Never null under push.
-        MagmaPipeIdentityTables* m_identity = nullptr;
-        // The entry belonging to `vao`, claimed (and cleared) if the slot currently holds
-        // someone else's.
-        VaoBackendMemos& MemosFor(const MG_State::GLState::VertexArrayObject& vao) const;
-#endif
-
         const VulkanRendererConfig& m_config;
         VkPhysicalDevice m_physicalDevice = VK_NULL_HANDLE;
-#if MOBILEGL_BUILD_DISAGGREGATED
-        // Physical-device format capabilities never change during this factory's
-        // lifetime. The wire path rebuilds layouts without the legacy VAO memo.
-        mutable UnorderedMap<VkFormat, Bool> m_wireVertexFormatSupport;
-#endif
-        // Values are heap-allocated: UnorderedMap is open-addressing, so INSERT
-        // invalidates references to stored values - and so does ERASE, which shifts
-        // the rest of the probe cluster into the hole and therefore moves entries
-        // other than the erased one. The draw path (and the VAOs' state-pointer
-        // memos) hold entry pointers across both; only the unique_ptr cell moves,
-        // never the pointee.
-        UnorderedMap<HashType, UniquePtr<BackendVertexInputState>> m_cache;
-        // Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
-        Uint64 m_frameBoundaryCounter = 0;
-        // Bumped whenever any cache entry is erased. VAOs memo a raw pointer to
-        // their heap-allocated entry (stable across map insert/rehash by
-        // construction); a memo is honored only while its recorded epoch
-        // matches, so an evicted entry can never be dereferenced through a
-        // stale memo.
-        //
-        // Drawn from a process-wide source, never a per-instance counter: the VAO
-        // memos outlive this factory (they live on the frontend context's VAOs, the renderer
-        // is destroyed and recreated on EGL surface release/re-create), so a fresh
-        // factory restarting at a dead factory's epoch value would honor its
-        // dangling entry pointers. The constructor takes a value strictly greater
-        // than anything a predecessor ever stamped, so a dead factory's memo can
-        // never compare equal here - the same never-reused idiom as the lifetime ids.
-        // Single-threaded like the rest of the factory (renderer-thread only).
-        //
-        // P2 D12.5: the process-wide source is the LEGACY arm's need. It exists because the
-        // memos live on the frontend VAOs and therefore outlive the factory. The handle arm's
-        // memo table is owned by this factory and dies with it, so a per-instance counter is
-        // enough there and the epoch shrinks back to what it looks like it should be.
-#if MOBILEGL_PIPE_LEGACY_MEMOS
-        static inline Uint64 s_evictionEpochSource = 0;
-        Uint64 m_evictionEpoch = ++s_evictionEpochSource;
-#else
-        Uint64 m_evictionEpoch = 1;
-#endif
+        UnorderedMap<HashType, BackendVertexInputState> m_cache;
         static inline XXH64_state_t* m_hashState = XXH64_createState();
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferManager.h

@@ -13,10 +13,6 @@
 #include "../VkIncludes.h"
 #include <Includes.h>
 #include <vk_mem_alloc.h>
-#if MOBILEGL_BUILD_DISAGGREGATED
-#include "MG_Pipe/MGPipeTypes.h"
-#include <unordered_map>
-#endif
 
 namespace MobileGL::MG_Backend::DirectVulkan {
     enum class BufferKind : Uint8 {
@@ -35,9 +31,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         VmaMemoryUsage transientMemoryUsage = VMA_MEMORY_USAGE_AUTO;
         VmaAllocationCreateFlags transientAllocationFlags = VMA_ALLOCATION_CREATE_HOST_ACCESS_SEQUENTIAL_WRITE_BIT;
         Bool transientPersistentMapping = false;
-        // VK_EXT_transform_feedback is enabled: persistent-map storage additionally
-        // carries the transform feedback usage so capture targets can bind directly.
-        Bool transformFeedbackUsageEnabled = false;
     };
 
     // The DirectVulkan storage behind one frontend buffer (pipe_resource analogue).
@@ -61,33 +54,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // never orphaned or recreated. Draw-time acquire binds it directly, no re-upload.
         Bool persistentMapped = false;
 
-        // Bumped from a manager-wide counter every time anything that decides which
-        // BufferSlice an Acquire*Slice call hands back changes: storage created or
-        // released, a full re-upload becoming due, a promotion/demotion between
-        // resident and streamed storage, or a new per-frame arena slice. Callers that
-        // memoise a resolved slice compare this to prove the memo still describes the
-        // buffer. The counter is manager-wide (never per-resource) so a freshly
-        // created resource - including one that replaces a destroyed resource at the
-        // same address - can never reproduce a value some memo already holds. 0 means
-        // "no slice has ever been handed out", which no memo can match.
-        Uint64 sliceEpoch = 0;
-
         // Cached transient (streaming) slice for the current frame.
         BufferSlice transientSlice{};
         Uint64 transientFrameSerial = 0;
         Uint64 transientChangeSerial = 0;
         VkDeviceSize transientSize = 0;
-
-        // Streaming re-copies the whole store into the per-frame arena on every
-        // frame, which is right for genuinely per-frame data but pure waste for a
-        // Dynamic-hinted buffer the app stopped touching. After the content
-        // survives kStreamedPromotionStreak frame boundaries unchanged it is
-        // promoted to resident storage (one final upload, then zero per-frame
-        // cost); the first content change demotes it back to streaming, and the
-        // streaming path's existing downgrade releases the resident store.
-        Uint32 unchangedStreak = 0;
-        Bool promotedResident = false;
-        Uint64 promotedChangeSerial = 0;
     };
 
     // Supplies a command buffer that is recording and outside any render pass,
@@ -103,48 +74,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Bool Initialize(const VkBufferManagerInitInfo& initInfo);
         void Shutdown();
 
-#if MOBILEGL_BUILD_DISAGGREGATED
-        // Registered before caps publication; the initialized renderer owns the storage.
-        static void RegisterWireResourceOps();
-        // Transport resources are owned by their complete wire handle, never by a
-        // frontend BufferObject. Acquires expose the full GPU store, without a CPU
-        // pointer: CPU consumers must use ReadWireBuffer for ordered, current bytes.
-        Bool AcquireWireSlice(BufferKind kind, MG_Pipe::MGPipeHandle res, BufferSlice& outSlice);
-        Bool ReadWireBuffer(MG_Pipe::MGPipeHandle res, Uint64 offset, Uint64 size, void* dst);
-        Bool CopyWireBufferRangeToSlice(MG_Pipe::MGPipeHandle res, Uint64 offset, Uint64 size,
-                                        const BufferSlice& dst);
-        // P7 A.1, the sub-word half of the one above: the same copy for a window whose start
-        // or end does not land on a four-byte boundary. The read of the APPLICATION's store is
-        // rounded OUT to whole words and clamped to the store's end, so the widened window can
-        // never touch a byte the application does not own; it lands in a transient staging
-        // slice, and only the staging -> dst shift is sub-word - inside our own arena, where an
-        // unaligned region cannot alias anything else. vkCmdCopyBuffer places no alignment rule
-        // on a region's offsets or size (unlike vkCmdUpdateBuffer / vkCmdFillBuffer), so the
-        // shift is a plain legal copy. `dstSkip` is the byte inside `dst` the window starts at.
-        // This retires `uniform-buffer-byte-tail`.
-        Bool CopyWireBufferSubWordRangeToSlice(MG_Pipe::MGPipeHandle res, Uint64 offset, Uint64 size,
-                                               Uint32 frameIndex, const BufferSlice& dst, Uint64 dstSkip);
-        void MarkWireBufferGpuWritten(MG_Pipe::MGPipeHandle res, Uint64 offset, Uint64 size);
-
-        // Resource-op entry points. All run on the server apply owner.
-        void CreateWireBuffer(MG_Pipe::MGPipeHandle res, const MG_Pipe::MGPResourceDesc& desc);
-        void RespecifyWireBuffer(MG_Pipe::MGPipeHandle res, const MG_Pipe::MGPResourceDesc& desc,
-                                 const void* initialBytes);
-        void WriteWireBuffer(MG_Pipe::MGPipeHandle res, Uint64 offset, Uint64 size, const void* bytes);
-        void FlushWireBuffer(MG_Pipe::MGPipeHandle res, Uint64 offset, Uint64 size, const void* bytes);
-        void ReadbackWireBuffer(MG_Pipe::MGPipeHandle res, Uint64 offset, Uint64 size);
-        void DestroyWireBuffer(MG_Pipe::MGPipeHandle res);
-#endif
-
         // Recreate all per-frame transient arenas
         Bool RecreateTransientArenas(Uint32 frameCount);
         void BeginFrame(Uint32 frameIndex);
-        // Drains every frame slot's deferred buffer/resource releases. Only valid when
-        // the caller has proven every queue submission complete; used by the present-less
-        // frame-boundary drain. Deliberately does NOT touch the transient arena's parked
-        // superseded blocks: those are still named by this frame's slices (see the
-        // definition), and only a frame rewind retires them.
-        void CollectAllDeferredReleases();
         // All previously submitted GPU work has completed (vkDeviceWaitIdle).
         void NotifyDeviceIdle();
         // A frame slot's submission fence has been waited: every serial up to
@@ -157,27 +89,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Bool UploadTransient(BufferKind kind, Uint32 frameIndex, const void* data, VkDeviceSize size,
                              VkDeviceSize alignment, BufferSlice& outSlice);
 
-        // The descriptor a shader storage block gets when the program declares it and the
-        // application bound no buffer at its GL binding point. GL 4.6 core 7.8 makes that a
-        // legal state - the block simply has no store, so reads are undefined and writes go
-        // nowhere - whereas Vulkan has no such thing as an unwritten descriptor, so something
-        // real has to sit in the set or the whole draw/dispatch is lost. One zero-filled
-        // buffer, created once and shared by every unbound binding: bindings that are only
-        // declared (the case this exists for) never touch it, and one that is actually read
-        // sees zeros, which is inside GL's "undefined". robustBufferAccess bounds anything
-        // that indexes past it.
-        BufferSlice AcquireUnboundStorageDescriptor();
-
-        // The store a texel-buffer descriptor - `samplerBuffer` or `imageBuffer` - gets when the
-        // unit the program's uniform names has no buffer texture on it, or the buffer texture on
-        // it has no GL buffer attached. Both are legal GL states that make a fetch return
-        // undefined values (GL 4.6 core 8.9: a buffer texture with no attached buffer object is
-        // incomplete, and sampling an incomplete texture is undefined - not a lost draw), and both
-        // used to take the whole draw or dispatch with them. The VIEW over this - one per format,
-        // and the descriptor is a VkBufferView, not a buffer - is built by
-        // UniformManager::AcquireUnboundTexelBufferView.
-        BufferSlice AcquireUnboundTexelBufferDescriptor();
-
         // Draw-time acquire for resident (device-storage) buffers: ensures the
         // resource exists and is fully uploaded, marks it used this frame.
         Bool AcquireResidentSlice(BufferKind kind, const SharedPtr<MG_State::GLState::BufferObject>& bufferObject,
@@ -197,24 +108,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // Immediate ops, dispatched from the frontend BufferBackendOps table.
         void OnRespecify(MG_State::GLState::BufferObject& bufferObject);
         void OnSubData(MG_State::GLState::BufferObject& bufferObject, SizeT offset, SizeT size);
-        void OnResidentSubData(MG_State::GLState::BufferObject& bufferObject, SizeT offset, DataPtr data);
         void OnFlushMappedRange(MG_State::GLState::BufferObject& bufferObject, Range1D range,
                                 Flags<BufferMappingAccessBit> appAccess);
         void OnResourceDestroyed(SharedPtr<MG_State::GLState::BackendBufferResource>&& resource);
 
         Uint64 GetFrameSerial() const { return m_frameSerial; }
-        // Highest value handed to any VkBufferResource::sliceEpoch. Unchanged since a
-        // memo was taken means no buffer this manager owns changed which slice it hands
-        // back, and none was persistently mapped, in between - so a memo of resolved
-        // slices needs no per-buffer re-check. See AcquirePersistentMap for the mapping half.
-        Uint64 GetSliceEpochCounter() const { return m_sliceEpochCounter; }
-#if MOBILEGL_BUILD_DISAGGREGATED
-        // Bumped every time this manager destroys a WIRE store's VkBuffer (see
-        // m_wireStoreDestroyEpoch). Unchanged since a memo was taken means no VkBuffer handle
-        // that memo names can have been freed and re-minted in between, which is the one
-        // fact a handle-keyed memo of wire descriptors needs and cannot read off the handle.
-        Uint64 GetWireStoreDestroyEpoch() const { return m_wireStoreDestroyEpoch; }
-#endif
         // Highest frame serial whose GPU work is known complete; serials at or
         // below it may be considered signaled. Drives IsResourceBusy and the
         // backend GL fence objects.
@@ -222,121 +120,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // Busy = potentially referenced by GPU work that has not been fenced yet
         // (including commands recorded for the current, unsubmitted frame).
         Bool IsResourceBusy(const VkBufferResource& resource) const;
-        // Hand the manager a buffer to destroy once the frame that recorded commands
-        // naming it has completed. The renderer's blit path needs a device-local
-        // scratch store for one recorded operation, which cannot be a stack local:
-        // the glBlitFramebuffer that records the commands returns long before the
-        // command buffer is submitted.
-        void DeferRelease(VkBufferObject&& buffer);
 
     private:
-#if MOBILEGL_BUILD_DISAGGREGATED
-        struct WireBufferResource {
-            VkBufferObject buffer;
-            Uint64 size = 0;
-            Uint64 lastUseSerial = 0;
-            // P7 wave 2 package B3: the submission expected to carry the most recent GPU use
-            // of this buffer - the busy predicate's DEFENCE term, not its guarantee (see
-            // WriteWireBuffer). IsSubmitIndexComplete polls the real fence and reports an
-            // unsubmitted index as incomplete, but the stamp is taken before the draw is
-            // recorded and a mid-draw flush can submit it without the draw.
-            Uint64 lastUseSubmitIndex = 0;
-            Bool gpuWritesPending = false;
-            // Only ranges actually submitted by resource_subdata are covered. No
-            // shadow is retained: flush cannot replay stale bytes over GPU writes.
-            Vector<Range1D> stagedCoverage;
-        };
-        static Uint64 WireBufferKey(MG_Pipe::MGPipeHandle res) {
-            return (static_cast<Uint64>(res.Gen) << 32) | res.Slot;
-        }
-        WireBufferResource* FindWireBuffer(MG_Pipe::MGPipeHandle res);
-        Bool WaitForWireBufferHostAccess(WireBufferResource& resource);
-
-        // P7 wave 4 (M2), ID-P7-27: THE WIRE ARM'S ORPHANS NEED A RECLAIM THAT IS NOT A FRAME
-        // BOUNDARY.
-        //
-        // RespecifyWireBuffer - which is every glBufferData that crosses the wire - orphans the
-        // old store unconditionally, because unlike OnRespecify it has no shadow to upload in
-        // place from and no cheap way to know the client is re-sending the same size. The orphan
-        // is legitimate (M1 measured the conditional-orphan mirror: 6701 live against 6702).
-        // What was missing is the RECLAIM. DeferRelease parks into m_deferredBufferReleases,
-        // whose only sweep is CollectDeferredReleases from a frame boundary, and on a pbuffer
-        // replay the server sees ONE present record for the whole run - so on
-        // minecraft-1.21.4-fabric-iris-bsl-esc-menu-854 the buckets held 25,923 dead stores
-        // against 28 live wire buffers, one memfd mapping each, and the server died in scudo's
-        // secondary allocator.
-        //
-        // So a wire store is parked HERE instead, with the facts that say when it is dead, and
-        // THE DEFER PATH ITSELF RECLAIMS - every park sweeps, and the frame boundary is only one
-        // more sweep point (CollectDeferredReleases), never the one this depends on:
-        //
-        //   * `lastUseSerial == 0` - read BEFORE RespecifyWireBuffer zeroes it. Zero means no
-        //     GPU command has named the store since it was minted or since the last host-access
-        //     wait proved every recorded command complete (WaitForWireBufferHostAccess); every
-        //     path that hands the store to the GPU stamps m_frameSerial, which starts at 1. Such
-        //     a store is destroyed at the park and never enters the list.
-        //   * `submitIndex` - the renderer's GetSyncPointSubmitIndex() at park time, which is by
-        //     construction the LAST submission that can name this store: every command that
-        //     names it was recorded before the park (the record left behind a bumped slice
-        //     epoch, so no memo can hand it out again), and a recorded command is either already
-        //     submitted (<= m_submitCounter) or in the batch that becomes m_submitCounter + 1.
-        //     IsSubmitIndexComplete(submitIndex) is a fence observation, so this is the gate
-        //     that empties the set MID-FRAME - the shape CollectWireObjects already uses for
-        //     the wire image/view tables.
-        //   * THE RENDERER IS IDLE - IsSubmitIndexComplete(GetSyncPointSubmitIndex()): nothing
-        //     is recorded and every submission has retired. Then every parked store is dead,
-        //     including one tagged for a batch that was abandoned rather than submitted (a
-        //     minimized Present drops its recording), whose own index may never complete.
-        //
-        // THE FRAME-SERIAL FLOOR IS DELIBERATELY NOT A PROOF HERE. It cannot move inside a
-        // frame (NotifyFrameSerialComplete refuses the current serial), so it frees nothing in
-        // the one-present replay this exists for; the submit index above is the fact that CAN
-        // move mid-frame, and it is a fence observation rather than a count.
-        //
-        // AND EVERY DESTROY HERE HAPPENS MID-FRAME, which the memos above this manager were not
-        // written for. UniformManager's descriptor memos are keyed on the VkBuffer HANDLE, and
-        // before M2 a wire store only ever died at the same boundary that clears those memos
-        // (UniformManager::BeginFrame, from Present or a drain). A store destroyed here can
-        // have its handle value re-minted by the next Create - a heap pointer under lavapipe -
-        // while a memo still maps that handle to a descriptor set baked to the dead store's
-        // memory: silent wrong bytes, no Fatal (ID-P7-43). m_wireStoreDestroyEpoch is the
-        // fact the memos fold in: every wire-store destroy bumps it, so a memo taken before
-        // the destroy cannot match after it. Deliberately NOT m_sliceEpochCounter, which every
-        // WriteWireBuffer bumps and which would defeat the memo on every glBufferSubData.
-        struct DeferredWireRelease {
-            VkBufferObject buffer;
-            Uint64 lastUseSerial = 0;
-            Uint64 submitIndex = 0;
-            // Cached: GetSize() is gone once the object is destroyed, and the watermark's
-            // running total has to stay exact as entries leave.
-            Uint64 bytes = 0;
-        };
-        // Park a wire store, sweep, then hold the watermark. `lastUseSerial` is the releasing
-        // resource's, captured before the caller resets it.
-        void DeferWireRelease(VkBufferObject&& buffer, Uint64 lastUseSerial);
-        // Destroy every parked store proven dead by the rules above. Returns how many.
-        SizeT SweepDeferredWireReleases();
-        // MOBILEGL_IPC_WIRE_DEFERRED_MB (Config.h has the semantics): when the parked bytes
-        // still exceed the budget after a sweep, take the sync point WaitForWireBufferHostAccess
-        // takes - flush what is recorded, wait for it - and sweep again, which retires every
-        // parked store, because none can be tagged past the sync point it just waited out.
-        void EnforceWireDeferredWatermark();
-        // ...and the same sync point when more than this many stores are parked, whatever their
-        // bytes (see the definition for the measurement). Not a knob: it bounds an object count
-        // the byte budget cannot see, and MOBILEGL_IPC_WIRE_DEFERRED_MB=0 disables it too.
-        static constexpr SizeT kWireDeferredCountCeiling = 1024;
-        // Teardown: the caller has proven the device idle (Shutdown / RecreateTransientArenas).
-        void DestroyAllDeferredWireReleases();
-        // THE one Fatal{ResourceUnavailable, "buffer-write-sync"} site (rule I: no second abort
-        // for the census to count), shared by the host write that cannot wait for the GPU and
-        // the watermark that cannot. `site` says which.
-        [[noreturn]] static void WireBufferSyncFatal(const char* site);
-        // The wbuf[] gauges (PipeStats.h, Gauge::WireBuffers..WireDeferredSyncs). The peaks are
-        // taken at the two points the numbers can rise - a park and a mint - and published when
-        // the stats channel is on; MagmaWireReclaimScenario reads them off the server's line.
-        void NoteWireStorePeaks();
-        void PublishWireReclaimGauges();
-#endif
         Bool InitializeTransientArenas();
         static VkBufferUsageFlags GetVkBufferUsage(BufferKind kind);
         VkBufferResource* GetOrCreateResource(const SharedPtr<MG_State::GLState::BufferObject>& bufferObject);
@@ -347,57 +132,22 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Bool SwapStorageAndUploadAll(VkBufferResource& resource, MG_State::GLState::BufferObject& bufferObject);
         // Record a staging-slice copy into the resident storage, ordered against
         // in-flight and already-recorded GPU work.
-        Bool StagedRangeCopy(VkBufferResource& resource, const void* data,
+        Bool StagedRangeCopy(VkBufferResource& resource, MG_State::GLState::BufferObject& bufferObject,
                              SizeT offset, SizeT size);
-#if MOBILEGL_BUILD_DISAGGREGATED
-        Bool StagedWireRangeCopy(WireBufferResource& resource, const void* data, SizeT offset, SizeT size);
-#endif
+        void DeferRelease(VkBufferObject&& buffer);
         void CollectDeferredReleases(Uint32 frameIndex);
         void DestroyAllDeferredReleases();
         void TrackLiveResource(const SharedPtr<VkBufferResource>& resource);
         void ReleaseAllLiveResources();
-        // See VkBufferResource::sliceEpoch.
-        void BumpSliceEpoch(VkBufferResource& resource) { resource.sliceEpoch = ++m_sliceEpochCounter; }
 
         VkBufferManagerInitInfo m_initInfo{};
         BufferArena m_transientUploadArena;
-        // See AcquireUnboundStorageDescriptor. Lazily created, never re-created, torn down
-        // with the manager.
-        VkBufferObject m_unboundStorageBuffer;
-        // See AcquireUnboundTexelBufferDescriptor. Same lifetime rules.
-        VkBufferObject m_unboundTexelBuffer;
         IBufferCopyCommandProvider* m_copyProvider = nullptr;
         Vector<Vector<VkBufferObject>> m_deferredBufferReleases;
         Vector<Vector<SharedPtr<VkBufferResource>>> m_deferredResourceReleases;
         Vector<WeakPtr<VkBufferResource>> m_liveResources;
-#if MOBILEGL_BUILD_DISAGGREGATED
-        std::unordered_map<Uint64, WireBufferResource> m_wireBuffers;
-        // See DeferredWireRelease. ONE FLAT LIST rather than the per-frame-slot buckets above:
-        // the whole point is that these entries do not wait for a frame slot to come round.
-        Vector<DeferredWireRelease> m_deferredWireReleases;
-        // Bytes currently parked in that list, kept exact so the watermark needs no walk.
-        Uint64 m_deferredWireBytes = 0;
-        // Live VkBuffers this arm owns: the stores held by m_wireBuffers plus the parked ones.
-        // Maintained rather than counted, because the publish runs on every park.
-        Uint64 m_wireStoreCount = 0;
-        // Run maxima of the two numbers above and the watermark's sync count, for the gauges.
-        Uint64 m_wireStoreCountPeak = 0;
-        Uint64 m_deferredWireBytesPeak = 0;
-        Uint64 m_wireDeferredSyncs = 0;
-        // See GetWireStoreDestroyEpoch and the DeferredWireRelease comment. Bumped on every
-        // path that destroys a wire store's VkBuffer, and never reset (not even by Shutdown),
-        // for m_sliceEpochCounter's reason: a memo taken before a re-initialize must not match
-        // a handle minted after it.
-        Uint64 m_wireStoreDestroyEpoch = 0;
-#endif
-    // Size m_liveResources had just after the last sweep; the next sweep waits for it to double.
-    SizeT m_liveResourcesLastPruned = 0;
         Uint32 m_currentFrameIndex = 0;
         Uint64 m_frameSerial = 1;
         Uint64 m_completedSerialFloor = 0;
-        // Never reset (not even by Shutdown): a value handed to a resource must stay
-        // unique for the process, or a memo taken before a re-initialize could match
-        // a different resource's state after it.
-        Uint64 m_sliceEpochCounter = 0;
     };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferObject.cpp

@@ -76,7 +76,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         const VkResult result =
             vmaCreateBuffer(m_allocator, &bufferInfo, &allocationInfo, &m_buffer, &m_allocation, nullptr);
         if (result != VK_SUCCESS) {
-            MGLOG_E_ONCE("VkBufferObject::Create failed: vmaCreateBuffer returned %d", result);
+            MGLOG_E("VkBufferObject::Create failed: vmaCreateBuffer returned %d", result);
             m_allocator = nullptr;
             m_buffer = VK_NULL_HANDLE;
             m_allocation = nullptr;
@@ -108,7 +108,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         const VkResult mapResult = vmaMapMemory(m_allocator, m_allocation, &m_mappedData);
         if (mapResult != VK_SUCCESS || m_mappedData == nullptr) {
-            MGLOG_E_ONCE("VkBufferObject::Map failed: vmaMapMemory returned %d", mapResult);
+            MGLOG_E("VkBufferObject::Map failed: vmaMapMemory returned %d", mapResult);
             m_mappedData = nullptr;
             return nullptr;
         }
@@ -138,14 +138,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         const Bool wasMapped = IsMapped();
         void* mapped = wasMapped ? m_mappedData : Map();
         if (mapped == nullptr) {
-            MGLOG_E_ONCE("VkBufferObject::Upload failed: unable to map buffer");
+            MGLOG_E("VkBufferObject::Upload failed: unable to map buffer");
             return false;
         }
 
         Memcpy(static_cast<Uint8*>(mapped) + offset, data, static_cast<SizeT>(size));
         const VkResult flushResult = vmaFlushAllocation(m_allocator, m_allocation, offset, size);
         if (flushResult != VK_SUCCESS) {
-            MGLOG_E_ONCE("VkBufferObject::Upload failed: vmaFlushAllocation returned %d", flushResult);
+            MGLOG_E("VkBufferObject::Upload failed: vmaFlushAllocation returned %d", flushResult);
             if (!wasMapped) {
                 Unmap();
             }
@@ -170,10 +170,22 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         const VkResult result = vmaInvalidateAllocation(m_allocator, m_allocation, offset, resolvedSize);
         if (result != VK_SUCCESS) {
-            MGLOG_E_ONCE("VkBufferObject::Invalidate failed: vmaInvalidateAllocation returned %d", result);
+            MGLOG_E("VkBufferObject::Invalidate failed: vmaInvalidateAllocation returned %d", result);
             return false;
         }
         return true;
     }
 
+    BufferSlice VkBufferObject::GetSlice(VkDeviceSize offset, VkDeviceSize size) const {
+        MOBILEGL_ASSERT(offset <= m_size, "VkBufferObject::GetSlice offset out of range");
+        const VkDeviceSize resolvedSize = (size == VK_WHOLE_SIZE) ? (m_size - offset) : size;
+        MOBILEGL_ASSERT(offset + resolvedSize <= m_size, "VkBufferObject::GetSlice range out of bounds");
+
+        BufferSlice slice{};
+        slice.buffer = m_buffer;
+        slice.offset = offset;
+        slice.size = resolvedSize;
+        slice.mapped = (m_mappedData != nullptr) ? static_cast<Uint8*>(m_mappedData) + offset : nullptr;
+        return slice;
+    }
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferObject.h

@@ -48,20 +48,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         VkBuffer GetHandle() const { return m_buffer; }
         VkDeviceSize GetSize() const { return m_size; }
-        // Inline: runs on the per-draw acquire path (a resident buffer bind is a
-        // GetSlice per binding), where an out-of-line call was measurable.
-        BufferSlice GetSlice(VkDeviceSize offset = 0, VkDeviceSize size = VK_WHOLE_SIZE) const {
-            MOBILEGL_ASSERT(offset <= m_size, "VkBufferObject::GetSlice offset out of range");
-            const VkDeviceSize resolvedSize = (size == VK_WHOLE_SIZE) ? (m_size - offset) : size;
-            MOBILEGL_ASSERT(offset + resolvedSize <= m_size, "VkBufferObject::GetSlice range out of bounds");
-
-            BufferSlice slice{};
-            slice.buffer = m_buffer;
-            slice.offset = offset;
-            slice.size = resolvedSize;
-            slice.mapped = (m_mappedData != nullptr) ? static_cast<Uint8*>(m_mappedData) + offset : nullptr;
-            return slice;
-        }
+        BufferSlice GetSlice(VkDeviceSize offset = 0, VkDeviceSize size = VK_WHOLE_SIZE) const;
         void* GetMappedData() const { return m_mappedData; }
         Bool IsMapped() const { return m_mappedData != nullptr; }
         Bool IsValid() const { return m_allocator != nullptr && m_buffer != VK_NULL_HANDLE && m_allocation != nullptr; }

MobileGL/MG_Backend/DirectVulkan/Renderer/VkClearManager.cpp

@@ -8,80 +8,15 @@
 
 #include "VkClearManager.h"
 
-// For the shared ResolveAttachmentLayerCount (and the ToVulkanLevelExtent it is built on): the
-// clear key's layer span has to be the same one the render pass builds its attachment view from.
-#include "VkTextureManager.h"
-
-#include "MG_State/GLState/Core.h"
-#include <MG_Pipe/PipeInputsSwitch.h>
 #include "MG_Util/Converters/MGToStr/FramebufferEnumConverter.h"
 #include "MG_Util/Converters/MGToStr/TextureEnumConverter.h"
 
-#include <algorithm>
-#include <cmath>
-
 namespace MobileGL::MG_Backend::DirectVulkan {
     static Bool IsCubeMapFaceUploadTarget(TextureUploadTarget target) {
         return target >= TextureUploadTarget::CubeMapPositiveX &&
                target <= TextureUploadTarget::CubeMapNegativeZ;
     }
 
-    VkClearColorValue MakeVkClearColorValue(const ClearAttachmentPayload& payload, Bool formatLacksAlpha) {
-        VkClearColorValue clearValue{};
-        switch (payload.colorEncoding) {
-        case ClearColorEncoding::Int:
-            clearValue.int32[0] = payload.colorInt.x();
-            clearValue.int32[1] = payload.colorInt.y();
-            clearValue.int32[2] = payload.colorInt.z();
-            clearValue.int32[3] = formatLacksAlpha ? 1 : payload.colorInt.w();
-            break;
-        case ClearColorEncoding::Uint:
-            clearValue.uint32[0] = payload.colorUint.x();
-            clearValue.uint32[1] = payload.colorUint.y();
-            clearValue.uint32[2] = payload.colorUint.z();
-            clearValue.uint32[3] = formatLacksAlpha ? 1u : payload.colorUint.w();
-            break;
-        case ClearColorEncoding::Float:
-            clearValue.float32[0] = payload.color.x();
-            clearValue.float32[1] = payload.color.y();
-            clearValue.float32[2] = payload.color.z();
-            clearValue.float32[3] = formatLacksAlpha ? 1.0f : payload.color.w();
-            break;
-        }
-        return clearValue;
-    }
-
-    void PreCompensateSrgbClearColor(ClearAttachmentPayload& payload, VkFormat destinationFormat) {
-        if (payload.colorEncoding != ClearColorEncoding::Float) return;
-        // With GL_FRAMEBUFFER_SRGB enabled GL performs the encoding itself, so the driver doing it
-        // is exactly right and there is nothing to undo.
-        if (MGB_CTX->IsCapabilityEnabled(MobileGL::CapabilityInput::FramebufferSrgb)) return;
-        if (ResolveSrgbAttachmentWriteFormat(destinationFormat, false) == destinationFormat) return;
-
-        // sRGB -> linear (GL 4.6 core 8.24), applied to the colour channels only: alpha is stored
-        // linearly in an sRGB format and must pass through untouched.
-        const auto toLinear = [](Float encoded) {
-            const Float value = std::clamp(encoded, 0.0f, 1.0f);
-            return value <= 0.04045f ? value / 12.92f : std::pow((value + 0.055f) / 1.055f, 2.4f);
-        };
-        payload.color = FloatVec4(toLinear(payload.color.x()), toLinear(payload.color.y()),
-                                  toLinear(payload.color.z()), payload.color.w());
-    }
-
-    void ForceOpaqueClearAlpha(ClearAttachmentPayload& payload) {
-        switch (payload.colorEncoding) {
-        case ClearColorEncoding::Int:
-            payload.colorInt = IntVec4(payload.colorInt.x(), payload.colorInt.y(), payload.colorInt.z(), 1);
-            break;
-        case ClearColorEncoding::Uint:
-            payload.colorUint = UintVec4(payload.colorUint.x(), payload.colorUint.y(), payload.colorUint.z(), 1u);
-            break;
-        case ClearColorEncoding::Float:
-            payload.color = FloatVec4(payload.color.x(), payload.color.y(), payload.color.z(), 1.0f);
-            break;
-        }
-    }
-
     static Bool PendingClearMatchesTextureIdentity(const PendingClearKey& key, const TextureIdentity& identity) {
         return key.texture == identity.texture && key.textureLifetimeId == identity.lifetimeId;
     }
@@ -105,13 +40,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         return ResolveAttachmentBaseArrayLayer(uploadTarget);
     }
 
-    // ResolveAttachmentLayerCount used to be duplicated here, reading attachment.GetSize().z()
-    // raw - no ToVulkanLevelExtent remap for a 1D array, no six-faces arm for a cube map. That is
-    // not a cosmetic difference: the count below is not key-only, it is written straight into
-    // VkImageSubresourceRange::layerCount by MaterializePendingClearForTexture, which then POPS
-    // the entry - so a layered cube map's glClear reached one face and the other five were lost
-    // for good, while the very same queued clear cleared all six through the render pass's
-    // LOAD_OP_CLEAR. The helper now lives once, in VkTextureManager.h beside ToVulkanLevelExtent.
+    static Uint32 ResolveAttachmentLayerCount(
+        const MG_State::GLState::FramebufferAttachmentObject& attachment) {
+        if (attachment.IsLayered()) {
+            return static_cast<Uint32>(std::max(attachment.GetSize().z(), 1));
+        }
+        return 1u;
+    }
 
     static const MG_State::GLState::FramebufferAttachmentObject* GetClearableAttachment(
         const MG_State::GLState::FramebufferObject& drawFbo, FramebufferAttachmentType attachmentType) {
@@ -127,30 +62,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         return &attachment;
     }
 
-    // The texture a pending clear is actually ABOUT. A clear issued through a GL texture view
-    // (ARB_texture_view) targets the storage it views, so it must queue against - and be found
-    // by - the storage texture; keying it on the view instead left the clear invisible to every
-    // materialisation done through the parent's name (and vice versa), so the image stayed in
-    // VK_IMAGE_LAYOUT_UNDEFINED and the readback was dropped as unreadable.
-    static MG_State::GLState::ITextureObject* ClearStorageTextureOf(MG_State::GLState::ITextureObject* texture) {
-        if (texture == nullptr) {
-            return nullptr;
-        }
-        const auto& storageOwner = texture->GetViewStorageOwner();
-        return storageOwner ? storageOwner.get() : texture;
-    }
-
-    PendingClearKey VkClearManager::MakePendingClearKey(MG_State::GLState::ITextureObject* rawTexture, Uint32 mipLevel,
+    PendingClearKey VkClearManager::MakePendingClearKey(MG_State::GLState::ITextureObject* texture, Uint32 mipLevel,
                                                         Uint32 baseArrayLayer, Uint32 layerCount) {
-        MG_State::GLState::ITextureObject* texture = ClearStorageTextureOf(rawTexture);
-        if (rawTexture != nullptr && texture != rawTexture) {
-            // The caller named a level and a layer of the VIEW; the key describes the STORAGE, so
-            // both have to be shifted into its numbering (GL 4.6 core 8.18). Without this a clear
-            // of a view's level 0 would collide with a clear of the storage's level 0 even when
-            // the view opened onto level 1.
-            mipLevel += static_cast<Uint32>(rawTexture->GetViewMinLevel());
-            baseArrayLayer += static_cast<Uint32>(rawTexture->GetViewMinLayer());
-        }
         return PendingClearKey {
             .texture = texture,
             .textureLifetimeId = texture ? texture->GetLifetimeId() : 0,
@@ -180,19 +93,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         const std::lock_guard<std::mutex> lock(m_mutex);
         m_pendingClears.clear();
         m_aliveObjects.clear();
-        m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
     }
 
     TextureIdentity VkClearManager::MakeTextureIdentity(MG_State::GLState::ITextureObject* texture) {
-        // Same rule as VkTextureManager::MakeTextureIdentity: a GL texture view is identified by
-        // the storage it views. A clear posted against a view and one posted against its parent
-        // target the same image, so they have to coalesce rather than queue independently.
-        if (texture != nullptr) {
-            const auto& storageOwner = texture->GetViewStorageOwner();
-            if (storageOwner) {
-                texture = storageOwner.get();
-            }
-        }
         return TextureIdentity {
             .texture = texture,
             .lifetimeId = texture ? texture->GetLifetimeId() : 0,
@@ -202,15 +105,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     void VkClearManager::MergeClearPayload(ClearAttachmentPayload& dst, const ClearAttachmentPayload& src) {
         dst.mask |= src.mask;
         if ((src.mask & GL_COLOR_BUFFER_BIT) != 0) {
-            // The whole colour story travels together (same rule as
-            // VkRenderPassManager::QueueRenderbufferClear): a glClearBufferiv/uiv
-            // payload carries its value in colorInt/colorUint and its branch selector
-            // in colorEncoding - dropping them here would leave the pending clear
-            // reading as an all-zero float one.
             dst.color = src.color;
-            dst.colorEncoding = src.colorEncoding;
-            dst.colorInt = src.colorInt;
-            dst.colorUint = src.colorUint;
         }
         if ((src.mask & GL_DEPTH_BUFFER_BIT) != 0) {
             dst.depth = src.depth;
@@ -232,7 +127,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             m_pendingClears.erase(key);
         }
         m_aliveObjects.erase(identity);
-        m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
     }
 
     Bool VkClearManager::LockTextureIdentityLocked(const TextureIdentity& identity,
@@ -322,14 +216,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return;
         }
 
-        const auto& storageOwner = texture->GetViewStorageOwner();
-        const SharedPtr<MG_State::GLState::ITextureObject>& storageTexture = storageOwner ? storageOwner : texture;
-        const PendingClearKey key = MakePendingClearKey(storageTexture.get());
+        const PendingClearKey key = MakePendingClearKey(texture.get());
         const std::lock_guard<std::mutex> lock(m_mutex);
-        m_aliveObjects[MakeTextureIdentity(storageTexture.get())] = storageTexture;
+        m_aliveObjects[MakeTextureIdentity(texture.get())] = texture;
         auto& pending = m_pendingClears[key];
         MergeClearPayload(pending, clearPayload);
-        m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
     }
 
     void VkClearManager::QueueClear(const ClearAttachmentPayload& clearPayload,
@@ -343,17 +234,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
 
         const PendingClearKey key = MakePendingClearKey(attachment);
-        // The alive entry must hold the STORAGE object, because the key names it:
-        // LockTextureIdentityLocked cross-checks the two, and registering a view here under its
-        // storage's identity made every lookup of this clear fail that check and silently report
-        // "nothing pending" - which is how a clear issued through a view's framebuffer vanished.
-        const auto& storageOwner = texture->GetViewStorageOwner();
-        const SharedPtr<MG_State::GLState::ITextureObject>& storageTexture = storageOwner ? storageOwner : texture;
         const std::lock_guard<std::mutex> lock(m_mutex);
-        m_aliveObjects[MakeTextureIdentity(storageTexture.get())] = storageTexture;
+        m_aliveObjects[MakeTextureIdentity(texture.get())] = texture;
         auto& pending = m_pendingClears[key];
         MergeClearPayload(pending, clearPayload);
-        m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
     }
 
     Bool VkClearManager::HasPendingClear(MG_State::GLState::ITextureObject* texture) {
@@ -361,11 +245,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return false;
         }
 
-        if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
-            return false;  // per-draw hot path: nothing pending anywhere
-        }
-
-        texture = ClearStorageTextureOf(texture);
         const Uint64 lifetimeId = texture->GetLifetimeId();
         const std::lock_guard<std::mutex> lock(m_mutex);
         for (auto it = m_pendingClears.begin(); it != m_pendingClears.end(); ++it) {
@@ -381,9 +260,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         if (key.texture == nullptr) {
             return false;
         }
-        if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
-            return false;  // per-draw hot path: nothing pending anywhere
-        }
 
         const std::lock_guard<std::mutex> lock(m_mutex);
         if (m_pendingClears.find(key) == m_pendingClears.end()) {
@@ -411,9 +287,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         if (key.texture == nullptr) {
             return false;
         }
-        if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
-            return false;  // per-draw hot path: nothing pending anywhere
-        }
 
         const std::lock_guard<std::mutex> lock(m_mutex);
         if (!LockTextureLocked(key, outTexture)) {
@@ -452,11 +325,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         if (texture == nullptr) {
             return false;
         }
-        if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
-            return false;  // per-draw hot path: nothing pending anywhere
-        }
 
-        texture = ClearStorageTextureOf(texture);
         const Uint64 lifetimeId = texture->GetLifetimeId();
         const std::lock_guard<std::mutex> lock(m_mutex);
         SharedPtr<MG_State::GLState::ITextureObject> liveTexture;
@@ -476,9 +345,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return;
         }
 
-        if (m_pendingCount.load(std::memory_order_relaxed) == 0) {
-            return;  // per-draw hot path: nothing pending anywhere
-        }
         const TextureIdentity identity = MakeTextureIdentity(texture);
         MGLOG_D("%s: Pop all pending clears for texture %d", __func__, texture->GetExternalIndex());
         const std::lock_guard<std::mutex> lock(m_mutex);
@@ -495,7 +361,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             auto it = m_pendingClears.find(key);
             if (it != m_pendingClears.end()) {
                 m_pendingClears.erase(it);
-            m_pendingCount.store(static_cast<Uint32>(m_pendingClears.size()), std::memory_order_relaxed);
             }
         }
 

MobileGL/MG_Backend/DirectVulkan/Renderer/VkClearManager.h

@@ -14,7 +14,6 @@
 #include "MG_Util/Math/VectorTypes.h"
 
 #include <Includes.h>
-#include <atomic>
 #include <unordered_map>
 
 namespace MobileGL::MG_Backend::DirectVulkan {
@@ -24,41 +23,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         Uint32 stencil{};
     };
 
-    // A colour clear reaches us from one of glClear/ClearBufferfv, ClearBufferiv or
-    // ClearBufferuiv, and Vulkan reads VkClearColorValue's union according to the destination
-    // image's format rather than converting between the members - a float written where an
-    // integer format is expected is reinterpreted bit for bit, not rounded. Remember which entry
-    // point supplied the value so the member written when the clear is materialized matches.
-    enum class ClearColorEncoding : Uint8 { Float, Int, Uint };
-
     struct ClearAttachmentPayload {
         GLbitfield mask = 0;
         FloatVec4 color = FloatVec4(0.0f, 0.0f, 0.0f, 0.0f);
-        ClearColorEncoding colorEncoding = ClearColorEncoding::Float;
-        IntVec4 colorInt = IntVec4(0, 0, 0, 0);
-        UintVec4 colorUint = UintVec4(0u, 0u, 0u, 0u);
         Float depth = 1.0f;
         Uint32 stencil = 0;
     };
 
-    // Builds the clear value for `payload` in the union member its encoding calls for.
-    // `formatLacksAlpha` applies GL's rule that a format without an alpha channel reads as one,
-    // expressed in whichever type matches (GL 4.6 core 15.2.3).
-    VkClearColorValue MakeVkClearColorValue(const ClearAttachmentPayload& payload, Bool formatLacksAlpha);
-
-    // Applies that same rule in place, for the paths that have to bake it into the payload before
-    // the destination is known.
-    void ForceOpaqueClearAlpha(ClearAttachmentPayload& payload);
-
-    // vkCmdClearColorImage names the image, so the driver applies the destination format's transfer
-    // function to whatever value it is handed. Every other write path in this backend goes through
-    // the UNORM twin view while GL_FRAMEBUFFER_SRGB is off (ResolveSrgbAttachmentWriteFormat) and
-    // therefore stores the raw value GL asked for. Rewrites `payload` to the linear colour whose
-    // encoding is that raw value, so a direct image clear of an sRGB destination agrees with them.
-    // A no-op for every other format, for integer clear encodings, and when GL is doing the
-    // encoding itself.
-    void PreCompensateSrgbClearColor(ClearAttachmentPayload& payload, VkFormat destinationFormat);
-
     struct PendingClearKey {
         MG_State::GLState::ITextureObject* texture = nullptr;
         Uint64 textureLifetimeId = 0;
@@ -114,8 +85,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     class VkClearManager {
     public:
         static PendingClearKey MakePendingClearKey(const MG_State::GLState::FramebufferAttachmentObject& attachment);
-        // Resolves a GL texture view to the storage it views before keying; see the definition.
-        static PendingClearKey MakePendingClearKey(MG_State::GLState::ITextureObject* rawTexture, Uint32 mipLevel = 0,
+        static PendingClearKey MakePendingClearKey(MG_State::GLState::ITextureObject* texture, Uint32 mipLevel = 0,
                                                    Uint32 baseArrayLayer = 0, Uint32 layerCount = 1);
 
         Bool Initialize();
@@ -150,19 +120,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
                                SharedPtr<MG_State::GLState::ITextureObject>& outTexture);
 
         Uint8 m_gcCounter = 0;
-    public:
-        // Lock-free probe for the consecutive-draw fast path: any pending clear
-        // forces the full SetupDraw path (which materializes/consumes it).
-        Bool HasAnyPendingClears() const { return m_pendingCount.load(std::memory_order_relaxed) != 0; }
-
-    private:
         mutable std::mutex m_mutex;
-        // Lock-free mirror of m_pendingClears.size(), maintained under m_mutex
-        // by every mutation. The per-draw probes (HasPendingClear/GetPending*)
-        // read it before taking the lock: during draw batches the pending set
-        // is almost always empty, so this turns several locked map probes per
-        // draw into one relaxed load.
-        std::atomic<Uint32> m_pendingCount{0};
         std::unordered_map<PendingClearKey, ClearAttachmentPayload, PendingClearKeyHash> m_pendingClears;
         std::unordered_map<TextureIdentity, WeakPtr<MG_State::GLState::ITextureObject>, TextureIdentityHash> m_aliveObjects;
     };

MobileGL/MG_Backend/DirectVulkan/Renderer/VkRenderPassManager.h

@@ -16,7 +16,6 @@
 #include "MG_State/GLState/FramebufferState/FramebufferObject.h"
 
 #include <Includes.h>
-#include <unordered_map>
 #include <vk_mem_alloc.h>
 
 namespace MobileGL::MG_Backend::DirectVulkan {
@@ -43,11 +42,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     struct TrackedAttachmentLayoutInfo {
         TrackedAttachmentTarget target = TrackedAttachmentTarget::Texture;
         WeakPtr<MG_State::GLState::ITextureObject> texture;
-        // Identity-compare shortcut for the per-draw "does the active pass use
-        // this sampled texture" probe: comparing this against a LIVE texture's
-        // address needs no weak_ptr::lock (two refcount atomics per probe).
-        // May dangle once the texture dies - compare only, never dereference.
-        MG_State::GLState::ITextureObject* textureRaw = nullptr;
         WeakPtr<MG_State::GLState::RenderbufferObject> renderbuffer;
         Uint32 textureMipLevel = 0;
         Uint32 swapchainImageIndex = 0;
@@ -101,42 +95,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             std::swap(layers, that.layers);
             std::swap(lastUsedFrame, that.lastUsedFrame);
         }
-        // Move ASSIGNMENT, not just construction. The move constructor above and the
-        // destructor below each independently suppress the implicit one, which left the
-        // type move-constructible but not move-assignable - and therefore not swappable,
-        // which std::swap(pair&, pair&) requires. That was invisible while UnorderedMap
-        // only ever move-CONSTRUCTED an element into a fresh slot. ska::flat_hash_map
-        // probes robin-hood: inserting swaps the entry being placed against the one
-        // already sitting in the slot whenever it has travelled further from its desired
-        // position, so the mapped type has to be swappable or the table fails to
-        // instantiate at all.
-        //
-        // SWAP SEMANTICS, exactly like the move constructor: this does not release the
-        // destination's handles, it parks them in `that`, which destroys them when it
-        // dies. That is correct for the only caller - std::swap, whose temporary expires
-        // immediately - and it is what keeps the three-move sequence from destroying a
-        // live render pass. It is NOT correct for a hand-written `a = std::move(b)` where
-        // `a` held live handles and `b` outlives the statement: those handles would then
-        // survive until `b` dies. There is no such caller; add a destroy-then-steal
-        // assignment before writing one.
-        RenderPassEntry& operator=(RenderPassEntry&& that) noexcept {
-            if (this != &that) {
-                std::swap(hash, that.hash);
-                std::swap(renderPass, that.renderPass);
-                std::swap(framebuffer, that.framebuffer);
-                std::swap(compatibilityHash, that.compatibilityHash);
-                std::swap(pendingClearAttachments, that.pendingClearAttachments);
-                std::swap(trackedAttachmentLayouts, that.trackedAttachmentLayouts);
-                std::swap(attachmentCount, that.attachmentCount);
-                std::swap(colorAttachmentCount, that.colorAttachmentCount);
-                std::swap(hasDepthStencilAttachment, that.hasDepthStencilAttachment);
-                std::swap(sampleCount, that.sampleCount);
-                std::swap(extent, that.extent);
-                std::swap(layers, that.layers);
-                std::swap(lastUsedFrame, that.lastUsedFrame);
-            }
-            return *this;
-        }
         RenderPassEntry(
             Uint64 hash,
             VkRenderPass renderpass,
@@ -199,68 +157,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     class VkRenderPassManager {
     public:
         using HashType = Uint64;
-
-        // Notified once per OnPresent sweep with every aged-out entry's VkRenderPass
-        // value: pipelines are hashed on the raw handle, and once destroyed the value
-        // may be recycled for an incompatible pass, so dependent caches must purge
-        // everything keyed on them before any new pass can be created (the sweep and
-        // the notification run back-to-back with no creation in between; observers
-        // compare the values, never dereference them). Batched so a mass-idle cohort
-        // (shader-pack switch, dimension exit) costs the observer one pipeline-cache
-        // scan, not one per dying pass. The wholesale paths
-        // (Shutdown/RecreateSwapchain) do not notify - their callers already drop
-        // every pipeline outright.
-        class IEvictionObserver {
-        public:
-            virtual ~IEvictionObserver() = default;
-            virtual void OnRenderPassesDestroyed(const Vector<VkRenderPass>& renderPasses) = 0;
-        };
-
         VkRenderPassManager(VkDevice device,
             VkPhysicalDevice physicalDevice, VmaAllocator allocator, const VulkanRendererConfig& config,
             VkClearManager& clearManager, VkTextureManager& textureManager, SwapchainObject& swapchainObject);
         ~VkRenderPassManager();
 
-        // Observer may be null (no notifications). Not owned.
-        void SetEvictionObserver(IEvictionObserver* observer) { m_evictionObserver = observer; }
-
         Bool Initialize();
         void Shutdown();
 
         HashType ComputeHash(
             const MG_State::GLState::FramebufferObject& fbo,
             Uint32 swapchainImageIndex,
-            Bool includePendingClear = true,
-            Bool includeDefaultFboDepthStencil = true);
-        // drawUsesDepthStencil: whether the operation about to run inside the pass
-        // reads or writes the depth/stencil buffer (depth test or stencil test
-        // enabled, or a depth/stencil clear). Only consulted for the DEFAULT
-        // framebuffer: EGL undefines its ancillary buffers at every swap, so a
-        // default-FBO pass whose draws provably never touch depth/stencil is
-        // created WITHOUT the depth attachment - on a tiler that skips the whole
-        // depth tile load AND store. The flavor only escalates: once a pass with
-        // depth is active, later depth-less draws keep using it, and a depth-using
-        // draw against a depth-less active pass resolves to a new (incompatible)
-        // entry, which the caller's compatibility check turns into a pass split;
-        // the new pass's depth loads DONT_CARE (content was undefined all along).
-        //
-        // Returns NULLPTR when this framebuffer cannot be represented as a Vulkan render pass at
-        // all - a texture the texture manager declined to back (an unsupported format or sample
-        // count), or an attachment view it cannot construct (a layer span the image has no room
-        // for, a 3D image whose format was refused 2D-array compatibility). This used to be
-        // unrepresentable: the function returned a reference, so the only thing the two fallible
-        // calls it builds on could do was trip a MOBILEGL_ASSERT - which is compiled out of every
-        // INFO build - and then dereference the null resource, or hand VK_NULL_HANDLE to
-        // vkCreateFramebuffer. That took the whole process down (51 lost CTS records over 21
-        // bodies, one runner restart each) where a declined draw is merely a wrong picture.
-        //
-        // EVERY caller must handle nullptr by dropping the operation, exactly as the draw path
-        // already drops a draw whose sampler descriptor could not be resolved
-        // (UniformManager::BindProgramUniformBuffers). The failure paths log MGLOG_E_ONCE
-        // themselves, so a caller needs no message of its own.
-        [[nodiscard]] RenderPassEntry* GetOrCreateRenderPass(const MG_State::GLState::FramebufferObject& fbo,
-                                                             Uint32 swapchainImageIndex,
-                                                             Bool drawUsesDepthStencil = true);
+            Bool includePendingClear = true);
+        RenderPassEntry& GetOrCreateRenderPass(const MG_State::GLState::FramebufferObject& fbo, Uint32 swapchainImageIndex);
         void QueueRenderbufferClear(GLbitfield mask, const ClearFramebufferPayload& clearPayload,
                                     const MG_State::GLState::FramebufferObject& drawFbo);
         void QueueRenderbufferClear(const ClearAttachmentPayload& clearPayload,
@@ -283,20 +192,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         UnorderedMap<Uint64, RenderPassEntry> m_renderPasses;
         // Monotonic frame counter (bumped in OnPresent) for render-pass cache aging.
         Uint64 m_frameCounter = 0;
-        IEvictionObserver* m_evictionObserver = nullptr;
 
         // Bumped whenever a renderbuffer VkImage is (re)created; together with the texture
         // manager's image epoch this invalidates the render-pass fast path on any attachment
         // image recreation.
         Uint64 m_renderbufferImageEpoch = 1;
 
-    public:
-        // Bumped whenever a renderbuffer backing is (re)created; consecutive-draw
-        // snapshots include it so an attachment respecify forces a re-resolve.
-        Uint64 GetRenderbufferImageEpoch() const { return m_renderbufferImageEpoch; }
-
-    private:
-
         // Per-draw fast-path memo for GetOrCreateRenderPass (dirty-flag state tracking): when the
         // framebuffer state is provably unchanged since the last resolution, the active render pass
         // is reused WITHOUT recomputing the expensive per-draw hash. Invalidated by FBO switch /
@@ -304,36 +205,17 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         // or a pending clear. Portable to Vulkan 1.1 (no dynamic_rendering / imageless FB needed).
         Bool m_rpFastValid = false;
         const MG_State::GLState::FramebufferObject* m_rpFastFbo = nullptr;
-        // The FBO's never-reused lifetime id joins the raw pointer + Uint16 version:
-        // a deleted FBO reallocated at the same address whose fresh setup performed
-        // the same number of version bumps would otherwise compare equal (both count
-        // from 0), serving the dead framebuffer's pass to the new object.
-        Uint64 m_rpFastFboLifetimeId = 0;
         Uint16 m_rpFastFboVersion = 0;
         Uint32 m_rpFastSwapchainIndex = 0;
         Uint64 m_rpFastTexEpoch = 0;
         Uint64 m_rpFastRbEpoch = 0;
         Uint64 m_rpFastRenderPassHash = 0;
-        // Whether the memoized entry carries a depth/stencil attachment; a
-        // default-FBO resolution whose effective depth request differs must
-        // miss the memo (the depth-less/depth-full flavors hash differently).
-        Bool m_rpFastHadDepthStencil = false;
 
-    public:
         struct RenderbufferResource {
-            // deadSinceFrame sentinel: the owning weak reference has not been observed
-            // expired. Dead resources age past every in-flight frame before Destroy
-            // (see CollectRenderbufferGarbage); the GPU may still reference the image
-            // for frames-in-flight frames after the GL object dies.
-            static constexpr Uint64 kNeverObservedDead = UINT64_MAX;
-
             WeakPtr<MG_State::GLState::RenderbufferObject> renderbuffer;
             VkImage image = VK_NULL_HANDLE;
             VmaAllocation allocation = nullptr;
             VkImageView view = VK_NULL_HANDLE;
-            // UNORM reinterpretation of an sRGB image, used as the attachment view while
-            // GL_FRAMEBUFFER_SRGB is disabled (raw writes). Null for non-sRGB formats.
-            VkImageView unormTwinView = VK_NULL_HANDLE;
             VkImageLayout layout = VK_IMAGE_LAYOUT_UNDEFINED;
             VkFormat format = VK_FORMAT_UNDEFINED;
             VkImageAspectFlags aspect = VK_IMAGE_ASPECT_NONE;
@@ -341,75 +223,25 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             VkSampleCountFlagBits sampleCount = VK_SAMPLE_COUNT_1_BIT;
             TextureInternalFormat internalFormat = TextureInternalFormat::Unknown;
             Int samples = 0;
-            // m_frameCounter value at which the weak reference was first seen expired.
-            Uint64 deadSinceFrame = kNeverObservedDead;
 
             void Destroy(VkDevice device, VmaAllocator allocator);
         };
 
-        // Public so the renderer's blit/copy/readback bindings can source renderbuffer
-        // attachments the same way texture attachments go through the texture manager.
-        RenderbufferResource* GetOrCreateRenderbufferResource(
-            const SharedPtr<MG_State::GLState::RenderbufferObject>& renderbuffer);
-        Bool GetPendingRenderbufferClear(MG_State::GLState::RenderbufferObject* renderbuffer,
-                                         ClearAttachmentPayload& outPayload) const;
-
-    private:
         struct PendingRenderbufferClear {
             WeakPtr<MG_State::GLState::RenderbufferObject> renderbuffer;
             ClearAttachmentPayload payload{};
         };
 
-        // A superseded renderbuffer backing (glRenderbufferStorage respecify) parked
-        // until enough frame boundaries have passed that no in-flight command buffer
-        // can still reference it; destroyed in OnPresent (see RetireAgeFrames).
-        struct DeferredRenderbufferRelease {
-            VkImage image = VK_NULL_HANDLE;
-            VmaAllocation allocation = nullptr;
-            VkImageView view = VK_NULL_HANDLE;
-            VkImageView unormTwinView = VK_NULL_HANDLE;
-            Uint64 deferredAtFrame = 0;
-        };
-
-        // Node-based std::unordered_map, deliberately NOT the open-addressing UnorderedMap:
-        // callers cache a RenderbufferResource* - or a bare &resource->layout - and then make further
-        // calls that touch this map. BlitFramebuffer is the one that bit: it resolves the source and
-        // destination colour bindings (ResolveColorBlitBinding caches &rbResource->layout), then
-        // materializes the source's pending clear, which looks that same resource up again. Growing
-        // an open-addressed table relocates every element, so the cached pointer went on to name
-        // freed storage still holding the pre-clear VK_IMAGE_LAYOUT_UNDEFINED; BlitFramebuffer bailed
-        // out at "source image layout is undefined", silently dropping the blit -
-        // renderbuffers_storage_multisample read back zero instead of the clear colour on exactly the
-        // iterations that grew the table.
-        //
-        // Reordering the materialize ahead of the resolves - the fix ReadPixels got - does not cover
-        // this: the destination resolve still runs after the source pointer is taken. The depth blit,
-        // GetOrCreateRenderPass's depthRenderbufferResource and ReadDepthStencilPixels cache the same
-        // kind of pointer, so the invariant belongs in the container rather than in a per-call-site
-        // ordering rule. m_textureResources is node-based for the same reason.
-        //
-        // The case for keeping this node-based got STRONGER with ska::flat_hash_map, so do not read
-        // the paragraph above as merely historical: ska erases by shifting the rest of the probe
-        // cluster backwards into the hole, so erasing one renderbuffer relocates OTHER renderbuffers'
-        // entries - a cached pointer can now be invalidated by a key it has nothing to do with, which
-        // no call-site ordering rule can defend against. (What did change: ska's operator[] returns on
-        // a hit before it runs its grow check, so a plain lookup of a PRESENT key no longer relocates.
-        // That narrows the insert hazard; it does not touch the erase one.)
-        std::unordered_map<MG_State::GLState::RenderbufferObject*, RenderbufferResource> m_renderbufferResources;
+        UnorderedMap<MG_State::GLState::RenderbufferObject*, RenderbufferResource> m_renderbufferResources;
         UnorderedMap<MG_State::GLState::RenderbufferObject*, PendingRenderbufferClear> m_pendingRenderbufferClears;
-        Vector<DeferredRenderbufferRelease> m_deferredRenderbufferReleases;
-        // Supported sample counts per attachment format, so per-draw resource lookups
-        // do not repeat vkGetPhysicalDeviceImageFormatProperties.
-        UnorderedMap<VkFormat, VkSampleCountFlags> m_attachmentSampleCountsByFormat;
 
+        RenderbufferResource* GetOrCreateRenderbufferResource(
+            const SharedPtr<MG_State::GLState::RenderbufferObject>& renderbuffer);
+        Bool GetPendingRenderbufferClear(MG_State::GLState::RenderbufferObject* renderbuffer,
+                                         ClearAttachmentPayload& outPayload) const;
         Bool HasPendingRenderbufferClear(
             const MG_State::GLState::FramebufferAttachmentObject& attachment) const;
         void CollectRenderbufferGarbage();
-        // Frame-boundary margin after which a resource last referenced by a retired
-        // GL object (or superseded backing) is provably past every in-flight frame.
-        Uint64 RetireAgeFrames() const;
-        void DeferRenderbufferBackingRelease(RenderbufferResource& resource);
-        void CollectDeferredRenderbufferReleases(Bool destroyAll);
 
         static inline XXH64_state_t* m_hashState = XXH64_createState();
         static inline ActiveRenderPassInfo s_activeRenderPass{};

MobileGL/MG_Backend/DirectVulkan/Renderer/VkSamplerManager.cpp

@@ -15,192 +15,12 @@
 
 namespace MobileGL::MG_Backend::DirectVulkan {
     namespace {
-#if MOBILEGL_BUILD_DISAGGREGATED
-        // An accessor view over the wire's POD values, not a GL object with constructor,
-        // lifetime ID, allocator hooks or mutation callbacks. Both sources below use
-        // one sampler policy, including format-sensitive border-color conversion.
-        struct SamplerParametersSource {
-            const SamplerParameters& Params;
-            SamplerWrapMode GetWrapS() const { return Params.wrapS; }
-            SamplerWrapMode GetWrapT() const { return Params.wrapT; }
-            SamplerWrapMode GetWrapR() const { return Params.wrapR; }
-            SamplerFilterMode GetMinFilter() const { return Params.minFilter; }
-            SamplerFilterMode GetMagFilter() const { return Params.magFilter; }
-            SamplerMipmapMode GetMipmapMode() const { return Params.mipmapMode; }
-            Float GetMinLod() const { return Params.minLod; }
-            Float GetMaxLod() const { return Params.maxLod; }
-            Float GetLodBias() const { return Params.lodBias; }
-            Float GetMaxAnisotropy() const { return Params.maxAnisotropy; }
-            SamplerCompareMode GetCompareMode() const { return Params.compareMode; }
-            SamplerCompareFunc GetSamplerCompareFunc() const { return Params.compareFunc; }
-            const FloatVec4& GetBorderColor() const { return Params.borderColor; }
-            const IntVec4& GetBorderColorI() const { return Params.borderColorI; }
-            const UintVec4& GetBorderColorUI() const { return Params.borderColorUI; }
-            // Cache identity is entirely content-based; these fields are diagnostics.
-            Uint GetExternalIndex() const { return 0; }
-            Uint16 GetVersion() const { return 0; }
-        };
-
-        template <class SamplerSource>
-        Bool UsesBorderColor(const SamplerSource& sampler) {
-#else
         Bool UsesBorderColor(const MG_State::GLState::SamplerObject& sampler) {
-#endif
             return sampler.GetWrapS() == SamplerWrapMode::ClampToBorder ||
                    sampler.GetWrapT() == SamplerWrapMode::ClampToBorder ||
                    sampler.GetWrapR() == SamplerWrapMode::ClampToBorder;
         }
 
-        // The numeric domain the texture is SAMPLED in. Vulkan splits VkBorderColor into a float
-        // family and an integer family and requires the sampler's choice to match the image view's
-        // format (a float border on an integer view, or the reverse, is undefined) - so the domain
-        // comes from the TEXTURE, while the value comes from whichever GL entry point wrote it.
-        enum class BorderColorDomain {
-            Float,
-            SignedInteger,
-            UnsignedInteger
-        };
-
-        BorderColorDomain ResolveBorderColorDomain(TextureInternalFormat format) {
-            switch (format) {
-            case TextureInternalFormat::R8I:
-            case TextureInternalFormat::R16I:
-            case TextureInternalFormat::R32I:
-            case TextureInternalFormat::RG8I:
-            case TextureInternalFormat::RG16I:
-            case TextureInternalFormat::RG32I:
-            case TextureInternalFormat::RGB8I:
-            case TextureInternalFormat::RGB16I:
-            case TextureInternalFormat::RGB32I:
-            case TextureInternalFormat::RGBA8I:
-            case TextureInternalFormat::RGBA16I:
-            case TextureInternalFormat::RGBA32I:
-                return BorderColorDomain::SignedInteger;
-            case TextureInternalFormat::R8UI:
-            case TextureInternalFormat::R16UI:
-            case TextureInternalFormat::R32UI:
-            case TextureInternalFormat::RG8UI:
-            case TextureInternalFormat::RG16UI:
-            case TextureInternalFormat::RG32UI:
-            case TextureInternalFormat::RGB8UI:
-            case TextureInternalFormat::RGB16UI:
-            case TextureInternalFormat::RGB32UI:
-            case TextureInternalFormat::RGBA8UI:
-            case TextureInternalFormat::RGBA16UI:
-            case TextureInternalFormat::RGBA32UI:
-            case TextureInternalFormat::RGB10A2UI:
-                return BorderColorDomain::UnsignedInteger;
-            default:
-                return BorderColorDomain::Float;
-            }
-        }
-
-        Bool IsSignedNormalizedFormat(TextureInternalFormat format) {
-            switch (format) {
-            case TextureInternalFormat::R8Snorm:
-            case TextureInternalFormat::R16Snorm:
-            case TextureInternalFormat::RG8Snorm:
-            case TextureInternalFormat::RG16Snorm:
-            case TextureInternalFormat::RGB8Snorm:
-            case TextureInternalFormat::RGB16Snorm:
-            case TextureInternalFormat::RGBA8Snorm:
-            case TextureInternalFormat::RGBA16Snorm:
-                return true;
-            default:
-                return false;
-            }
-        }
-
-        // GL 4.6 core 8.14.2: "The border values are clamped before they are used, according to the
-        // format in which texture components are stored. For signed and unsigned normalized
-        // fixed-point formats, border values are clamped to [-1,1] and [0,1] respectively. For
-        // floating-point and integer formats, border values are clamped to the representable range of
-        // the format." Every clause of that sentence is a real case here - the clamp is not just the
-        // normalized one.
-        //
-        // Only the 32-bit float formats are genuinely unclamped: every finite float is representable
-        // in them. Half-float has a finite maximum, and the two packed "float" formats are UNSIGNED,
-        // so a negative border on them must come back as 0 rather than as a negative number the
-        // driver delivers verbatim through VK_BORDER_COLOR_FLOAT_CUSTOM_EXT.
-        struct FloatBorderRange {
-            Bool clamped = true;
-            Float minValue = 0.0f;
-            Float maxValue = 1.0f;
-        };
-
-        FloatBorderRange ResolveFloatBorderRange(TextureInternalFormat format, Bool isSignedNormalized) {
-            switch (format) {
-            case TextureInternalFormat::R32F:
-            case TextureInternalFormat::RG32F:
-            case TextureInternalFormat::RGB32F:
-            case TextureInternalFormat::RGBA32F:
-                return {false, 0.0f, 0.0f};
-            case TextureInternalFormat::R16F:
-            case TextureInternalFormat::RG16F:
-            case TextureInternalFormat::RGB16F:
-            case TextureInternalFormat::RGBA16F:
-                return {true, -65504.0f, 65504.0f};
-            // Unsigned packed floats: no sign bit at all. 65024 is the largest 11-bit float; the
-            // 10-bit blue channel tops out lower (64512) and RGB9E5 higher (65408), but the bound
-            // that matters for correctness is the lower one, and a single conservative upper bound
-            // costs nothing a real border colour will ever notice.
-            case TextureInternalFormat::R11FG11FB10F:
-                return {true, 0.0f, 64512.0f};
-            case TextureInternalFormat::RGB9E5:
-                return {true, 0.0f, 65408.0f};
-            default:
-                return {true, isSignedNormalized ? -1.0f : 0.0f, 1.0f};
-            }
-        }
-
-        // Per-component representable range of an integer texture format, as Int64 so that the whole
-        // signed and unsigned 32-bit ranges are expressible in one type and the clamp can be written
-        // once for both domains. Alpha is carried separately because RGB10_A2UI is the one format
-        // whose alpha is narrower than its colour channels.
-        struct IntegerBorderRange {
-            Int64 rgbMin = 0;
-            Int64 rgbMax = 0;
-            Int64 alphaMin = 0;
-            Int64 alphaMax = 0;
-        };
-
-        IntegerBorderRange ResolveIntegerBorderRange(TextureInternalFormat format) {
-            const auto uniform = [](Int64 low, Int64 high) { return IntegerBorderRange{low, high, low, high}; };
-            switch (format) {
-            case TextureInternalFormat::R8I:
-            case TextureInternalFormat::RG8I:
-            case TextureInternalFormat::RGB8I:
-            case TextureInternalFormat::RGBA8I:
-                return uniform(-128, 127);
-            case TextureInternalFormat::R16I:
-            case TextureInternalFormat::RG16I:
-            case TextureInternalFormat::RGB16I:
-            case TextureInternalFormat::RGBA16I:
-                return uniform(-32768, 32767);
-            case TextureInternalFormat::R8UI:
-            case TextureInternalFormat::RG8UI:
-            case TextureInternalFormat::RGB8UI:
-            case TextureInternalFormat::RGBA8UI:
-                return uniform(0, 255);
-            case TextureInternalFormat::R16UI:
-            case TextureInternalFormat::RG16UI:
-            case TextureInternalFormat::RGB16UI:
-            case TextureInternalFormat::RGBA16UI:
-                return uniform(0, 65535);
-            case TextureInternalFormat::R32UI:
-            case TextureInternalFormat::RG32UI:
-            case TextureInternalFormat::RGB32UI:
-            case TextureInternalFormat::RGBA32UI:
-                return uniform(0, 4294967295LL);
-            case TextureInternalFormat::RGB10A2UI:
-                return {0, 1023, 0, 3};
-            default:
-                // The signed 32-bit formats, and anything unexpected: the full int32 range, i.e. a
-                // clamp that cannot alter a value the GL entry points could have carried.
-                return uniform(-2147483648LL, 2147483647LL);
-            }
-        }
-
         Bool IsDepthTextureFormat(TextureInternalFormat format) {
             switch (format) {
             case TextureInternalFormat::DepthComponent:
@@ -221,43 +41,16 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             return std::fabs(lhs - rhs) <= 1e-6f;
         }
 
-#if MOBILEGL_BUILD_DISAGGREGATED
-        template <class SamplerSource>
-        Float ResolveEffectiveMaxLod(const SamplerSource& sampler) {
-#else
         Float ResolveEffectiveMaxLod(const MG_State::GLState::SamplerObject& sampler) {
-#endif
             if (sampler.GetMipmapMode() == SamplerMipmapMode::None) {
                 return 0.0f;
             }
             return sampler.GetMaxLod();
         }
 
-#if MOBILEGL_BUILD_DISAGGREGATED
-        template <class SamplerSource>
-        Float ResolveEffectiveMinLod(const SamplerSource& sampler, Float effectiveMaxLod) {
-#else
         Float ResolveEffectiveMinLod(const MG_State::GLState::SamplerObject& sampler, Float effectiveMaxLod) {
-#endif
             return std::min(sampler.GetMinLod(), effectiveMaxLod);
         }
-
-        // A single-level view can only ever deliver the base level, but the LOD clamp must not be
-        // collapsed to exactly 0: both GL and Vulkan pick magFilter over minFilter from the
-        // *clamped* lambda, so maxLod = 0 would make every fragment magnify and quietly retire the
-        // min filter. 0.25 is the value VkSamplerCreateInfo's own note prescribes for emulating
-        // GL's non-mipmapped minification - large enough for lambda to stay positive, small enough
-        // that a NEAREST mip mode still rounds down to level 0. Clamped rather than assigned, so a
-        // texture whose GL_TEXTURE_MAX_LOD really is 0 keeps magnifying as GL says it must.
-#if MOBILEGL_BUILD_DISAGGREGATED
-        template <class SamplerSource>
-        Float ResolveSingleLevelMaxLod(const SamplerSource& sampler, Bool singleLevelView) {
-#else
-        Float ResolveSingleLevelMaxLod(const MG_State::GLState::SamplerObject& sampler, Bool singleLevelView) {
-#endif
-            const Float maxLod = ResolveEffectiveMaxLod(sampler);
-            return singleLevelView ? std::min(maxLod, 0.25f) : maxLod;
-        }
     } // namespace
 
     Bool VkSamplerManager::Initialize(const InitInfo& initInfo) {
@@ -267,20 +60,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         m_config = initInfo.config;
         m_samplerAnisotropySupported = initInfo.samplerAnisotropySupported;
         m_maxSamplerAnisotropy = std::max(initInfo.maxSamplerAnisotropy, 1.0f);
-        m_customBorderColorSupported = initInfo.customBorderColorSupported;
-        m_maxCustomBorderColorSamplers = initInfo.maxCustomBorderColorSamplers;
-        m_customBorderColorSamplerCount = 0;
         MOBILEGL_ASSERT(m_device != VK_NULL_HANDLE && m_config != nullptr,
                         "VkSamplerManager::Initialize failed: invalid initialization info");
         return true;
     }
 
-#if MOBILEGL_BUILD_DISAGGREGATED
-    template <class SamplerSource>
-    Float VkSamplerManager::ResolveEffectiveMaxAnisotropy(const SamplerSource& sampler,
-#else
     Float VkSamplerManager::ResolveEffectiveMaxAnisotropy(const MG_State::GLState::SamplerObject& sampler,
-#endif
                                                            Bool forceNearestFiltering) const {
         if (!m_samplerAnisotropySupported) return 1.0f;
         if (forceNearestFiltering) return 1.0f;
@@ -304,54 +89,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
 
         m_device = VK_NULL_HANDLE;
         m_config = nullptr;
-        m_frameBoundaryCounter = 0;
-        m_customBorderColorSupported = false;
-        m_maxCustomBorderColorSamplers = 0;
-        m_customBorderColorSamplerCount = 0;
     }
 
-    void VkSamplerManager::OnFrameBoundary() {
-        ++m_frameBoundaryCounter;
-
-        // Sweep occasionally; destroy samplers whose last use is far past every
-        // in-flight frame. Destroy and erase must stay atomic, or Shutdown would
-        // double-free the handle; an evicted key that recurs simply re-creates
-        // its sampler on the next miss.
-        constexpr Uint64 kSweepInterval = 256;
-        constexpr Uint64 kRetireAgeBoundaries = 1024;
-        if ((m_frameBoundaryCounter % kSweepInterval) != 0) {
-            return;
-        }
-
-        for (auto it = m_samplers.begin(); it != m_samplers.end();) {
-            auto& entry = it->second;
-            if (m_frameBoundaryCounter - entry.lastUsedFrameBoundary > kRetireAgeBoundaries) {
-                if (m_device != VK_NULL_HANDLE && entry.handle != VK_NULL_HANDLE) {
-                    vkDestroySampler(m_device, entry.handle, nullptr);
-                }
-                if (entry.usesCustomBorderColor && m_customBorderColorSamplerCount > 0) {
-                    --m_customBorderColorSamplerCount;
-                }
-                it = m_samplers.erase(it);
-            } else {
-                ++it;
-            }
-        }
-    }
-
-#if MOBILEGL_BUILD_DISAGGREGATED
-    template <class SamplerSource>
-    Uint64 VkSamplerManager::BuildSamplerKey(const SamplerSource& sampler,
-#else
     Uint64 VkSamplerManager::BuildSamplerKey(const MG_State::GLState::SamplerObject& sampler,
-#endif
-                                             Bool forceNearestFiltering, Bool singleLevelView,
-                                             const ResolvedBorderColor& borderColor) const {
+                                             const MG_State::GLState::ITextureObject& texture,
+                                             Bool forceNearestFiltering) const {
         MOBILEGL_ASSERT(m_config != nullptr, "VkSamplerManager::BuildSamplerKey: m_config is null");
         XXHASH_VERIFY(XXH64_reset(m_hashState, m_config->CacheVersion));
 
         XXHASH_VERIFY(XXH64_update(m_hashState, &forceNearestFiltering, sizeof(forceNearestFiltering)));
-        XXHASH_VERIFY(XXH64_update(m_hashState, &singleLevelView, sizeof(singleLevelView)));
 
         const auto minFilter = sampler.GetMinFilter();
         XXHASH_VERIFY(XXH64_update(m_hashState, &minFilter, sizeof(minFilter)));
@@ -365,7 +111,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         XXHASH_VERIFY(XXH64_update(m_hashState, &wrapT, sizeof(wrapT)));
         const auto wrapR = sampler.GetWrapR();
         XXHASH_VERIFY(XXH64_update(m_hashState, &wrapR, sizeof(wrapR)));
-        const auto maxLod = ResolveSingleLevelMaxLod(sampler, singleLevelView);
+        const auto maxLod = ResolveEffectiveMaxLod(sampler);
         const auto minLod = ResolveEffectiveMinLod(sampler, maxLod);
         XXHASH_VERIFY(XXH64_update(m_hashState, &minLod, sizeof(minLod)));
         XXHASH_VERIFY(XXH64_update(m_hashState, &maxLod, sizeof(maxLod)));
@@ -378,46 +124,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         XXHASH_VERIFY(XXH64_update(m_hashState, &maxAnisotropy, sizeof(maxAnisotropy)));
         const auto compareMode = sampler.GetCompareMode();
         XXHASH_VERIFY(XXH64_update(m_hashState, &compareMode, sizeof(compareMode)));
-        const auto compareFunc = sampler.GetSamplerCompareFunc();
+        const auto compareFunc = ResolveCompareFunc(sampler, texture);
         XXHASH_VERIFY(XXH64_update(m_hashState, &compareFunc, sizeof(compareFunc)));
-        // The resolved enum AND, when it is one of the *_CUSTOM_EXT values, the sixteen bytes of the
-        // colour itself: two samplers that differ only in a custom border colour carry the same enum
-        // and would otherwise collide onto whichever one was created first.
-        XXHASH_VERIFY(XXH64_update(m_hashState, &borderColor.color, sizeof(borderColor.color)));
-        if (borderColor.isCustom) {
-            XXHASH_VERIFY(XXH64_update(m_hashState, &borderColor.customValue, sizeof(borderColor.customValue)));
-        }
+        const auto borderColor = ResolveVkBorderColor(sampler, texture);
+        XXHASH_VERIFY(XXH64_update(m_hashState, &borderColor, sizeof(borderColor)));
         return XXH64_digest(m_hashState);
     }
 
-#if MOBILEGL_BUILD_DISAGGREGATED
-    template <class SamplerSource>
-    VkSampler VkSamplerManager::GetOrCreateSamplerImpl(const SamplerSource& sampler,
-                                                       TextureInternalFormat format,
-#else
     VkSampler VkSamplerManager::GetOrCreateSampler(const MG_State::GLState::SamplerObject& sampler,
                                                    const MG_State::GLState::ITextureObject& texture,
-#endif
-                                                   Bool forceNearestFiltering, Uint32 viewLevelCount) {
-        // A view that exposes a single mip level has no second level to blend with, so GL's
-        // *_MIPMAP_* minification filters degenerate to plain filtering on the base level -
-        // sampling is unchanged by pinning the Vulkan sampler to NEAREST mip mode at LOD 0.
-        // It is not cosmetic: MobileGL backs such a view with a fully allocated mip chain whose
-        // tail is never written, and a LINEAR mip mode lets the texture unit issue the level+1
-        // fetch anyway. On Adreno that fetch lands in uninitialized UBWC pages (or past the
-        // allocation for a genuinely single-level image) and faults the GPU - the same failure
-        // the default-framebuffer blit shader had to work around with an explicit-LOD sample.
-        const Bool singleLevelView = viewLevelCount == 1;
-        // Resolved once and used for both the key and the create-info; see ResolvedBorderColor.
-#if MOBILEGL_BUILD_DISAGGREGATED
-        const ResolvedBorderColor borderColor = ResolveBorderColor(sampler, format);
-#else
-        const ResolvedBorderColor borderColor = ResolveBorderColor(sampler, texture);
-#endif
-        const Uint64 key = BuildSamplerKey(sampler, forceNearestFiltering, singleLevelView, borderColor);
+                                                   Bool forceNearestFiltering) {
+        const Uint64 key = BuildSamplerKey(sampler, texture, forceNearestFiltering);
         auto it = m_samplers.find(key);
         if (it != m_samplers.end()) {
-            it->second.lastUsedFrameBoundary = m_frameBoundaryCounter;
             return it->second.handle;
         }
 
@@ -425,9 +144,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         samplerInfo.sType = VK_STRUCTURE_TYPE_SAMPLER_CREATE_INFO;
         samplerInfo.magFilter = forceNearestFiltering ? VK_FILTER_NEAREST : ToVkFilter(sampler.GetMagFilter());
         samplerInfo.minFilter = forceNearestFiltering ? VK_FILTER_NEAREST : ToVkFilter(sampler.GetMinFilter());
-        samplerInfo.mipmapMode = (forceNearestFiltering || singleLevelView)
-                                     ? VK_SAMPLER_MIPMAP_MODE_NEAREST
-                                     : ToVkMipmapMode(sampler.GetMipmapMode());
+        samplerInfo.mipmapMode = forceNearestFiltering ? VK_SAMPLER_MIPMAP_MODE_NEAREST
+                                                       : ToVkMipmapMode(sampler.GetMipmapMode());
         samplerInfo.addressModeU = ToVkAddressMode(sampler.GetWrapS());
         samplerInfo.addressModeV = ToVkAddressMode(sampler.GetWrapT());
         samplerInfo.addressModeW = ToVkAddressMode(sampler.GetWrapR());
@@ -438,25 +156,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         samplerInfo.anisotropyEnable = maxAnisotropy > 1.0f ? VK_TRUE : VK_FALSE;
         samplerInfo.maxAnisotropy = maxAnisotropy;
         samplerInfo.compareEnable = sampler.GetCompareMode() == SamplerCompareMode::CompareToTexture ? VK_TRUE : VK_FALSE;
-        samplerInfo.compareOp = ToVkCompareOp(sampler.GetSamplerCompareFunc());
-        // Must match BuildSamplerKey's resolution exactly.
-        samplerInfo.maxLod = ResolveSingleLevelMaxLod(sampler, singleLevelView);
+        samplerInfo.compareOp = ToVkCompareOp(ResolveCompareFunc(sampler, texture));
+        samplerInfo.maxLod = ResolveEffectiveMaxLod(sampler);
         samplerInfo.minLod = ResolveEffectiveMinLod(sampler, samplerInfo.maxLod);
-        samplerInfo.borderColor = borderColor.color;
+        samplerInfo.borderColor = ResolveVkBorderColor(sampler, texture);
         samplerInfo.unnormalizedCoordinates = VK_FALSE;
 
-        // VK_EXT_custom_border_color. `format` stays UNDEFINED, which is legal only because
-        // customBorderColorWithoutFormat was required alongside customBorderColors at device
-        // creation - a GL sampler object has no idea which texture it will be paired with.
-        VkSamplerCustomBorderColorCreateInfoEXT customBorderColorInfo{};
-        if (borderColor.isCustom) {
-            customBorderColorInfo.sType = VK_STRUCTURE_TYPE_SAMPLER_CUSTOM_BORDER_COLOR_CREATE_INFO_EXT;
-            customBorderColorInfo.customBorderColor = borderColor.customValue;
-            customBorderColorInfo.format = VK_FORMAT_UNDEFINED;
-            customBorderColorInfo.pNext = samplerInfo.pNext;
-            samplerInfo.pNext = &customBorderColorInfo;
-        }
-
         VkSampler vkSampler = VK_NULL_HANDLE;
         VK_VERIFY(vkCreateSampler(m_device, &samplerInfo, nullptr, &vkSampler), "vkCreateSampler(texture)");
 
@@ -464,29 +169,10 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         entry.handle = vkSampler;
         entry.externalIndex = sampler.GetExternalIndex();
         entry.version = sampler.GetVersion();
-        entry.lastUsedFrameBoundary = m_frameBoundaryCounter;
-        entry.usesCustomBorderColor = borderColor.isCustom;
-        if (entry.usesCustomBorderColor) {
-            ++m_customBorderColorSamplerCount;
-        }
         m_samplers[key] = entry;
         return vkSampler;
     }
 
-#if MOBILEGL_BUILD_DISAGGREGATED
-    VkSampler VkSamplerManager::GetOrCreateSampler(const MG_State::GLState::SamplerObject& sampler,
-                                                   const MG_State::GLState::ITextureObject& texture,
-                                                   Bool forceNearestFiltering, Uint32 viewLevelCount) {
-        return GetOrCreateSamplerImpl(sampler, texture.GetFormat(), forceNearestFiltering, viewLevelCount);
-    }
-
-    VkSampler VkSamplerManager::GetOrCreateSamplerFromParameters(const SamplerParameters& parameters,
-        TextureInternalFormat format, Bool forceNearestFiltering, Uint32 viewLevelCount) {
-        return GetOrCreateSamplerImpl(SamplerParametersSource{parameters}, format,
-                                       forceNearestFiltering, viewLevelCount);
-    }
-#endif
-
     VkFilter VkSamplerManager::ToVkFilter(SamplerFilterMode mode) {
         return mode == SamplerFilterMode::Nearest ? VK_FILTER_NEAREST : VK_FILTER_LINEAR;
     }
@@ -542,156 +228,48 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         }
     }
 
-#if MOBILEGL_BUILD_DISAGGREGATED
-    template <class SamplerSource>
-    VkSamplerManager::ResolvedBorderColor VkSamplerManager::ResolveBorderColor(
-        const SamplerSource& sampler, TextureInternalFormat format) const {
-#else
-    VkSamplerManager::ResolvedBorderColor VkSamplerManager::ResolveBorderColor(
-        const MG_State::GLState::SamplerObject& sampler, const MG_State::GLState::ITextureObject& texture) const {
-#endif
-        ResolvedBorderColor resolved{};
+    SamplerCompareFunc VkSamplerManager::ResolveCompareFunc(const MG_State::GLState::SamplerObject& sampler,
+                                                            const MG_State::GLState::ITextureObject& texture) {
+        const auto compareFunc = sampler.GetSamplerCompareFunc();
+        if (sampler.GetCompareMode() == SamplerCompareMode::CompareToTexture &&
+            IsDepthTextureFormat(texture.GetFormat()) && compareFunc == SamplerCompareFunc::Always) {
+            return SamplerCompareFunc::LessEqual;
+        }
+
+        return compareFunc;
+    }
+
+    VkBorderColor VkSamplerManager::ResolveVkBorderColor(const MG_State::GLState::SamplerObject& sampler,
+                                                         const MG_State::GLState::ITextureObject& texture) {
         if (!UsesBorderColor(sampler)) {
-            return resolved; // FLOAT_TRANSPARENT_BLACK, never sampled
+            return VK_BORDER_COLOR_FLOAT_TRANSPARENT_BLACK;
         }
 
-        // Border colour is sampler state: a bound sampler object supplies its own, and a texture
-        // with none reaches the very same value through the sampler object it owns.
-#if !MOBILEGL_BUILD_DISAGGREGATED
-        const auto format = texture.GetFormat();
-#endif
-        const auto domain = ResolveBorderColorDomain(format);
-        const Bool canUseCustom = m_customBorderColorSupported && m_maxCustomBorderColorSamplers > 0 &&
-                                  m_customBorderColorSamplerCount < m_maxCustomBorderColorSamplers;
+        const auto& borderColor = texture.GetBorderColor();
+        const Bool isDepthTexture = IsDepthTextureFormat(texture.GetFormat());
 
-        if (domain != BorderColorDomain::Float) {
-            // An integer image view REQUIRES an integer border colour, whatever the value is - even
-            // (0,0,0,1). The value itself is whichever integer form the application wrote; a float
-            // border on an integer texture is nonsense GL leaves undefined, so the derived integer
-            // representation (a plain cast) is as good an answer as any.
-            //
-            // Clamped to the format's representable range FIRST, per GL 4.6 core 8.14.2, and read
-            // through Int64 so the whole signed and unsigned 32-bit ranges are expressible at once.
-            //
-            // Which representation to start from is the TEXTURE's domain, not the entry-point form
-            // the application used. GL 4.6 core 8.10 stores an "I"-form border colour unmodified with
-            // an integer internal data type and does not define a sign conversion between the two
-            // integer forms, so the stored bits are reinterpreted in the sampled format's own
-            // signedness. Measured, not assumed: a border of -1 written with glTexParameterIiv
-            // against a GL_R8UI texture samples as 255 on the ES driver, i.e. as 0xFFFFFFFF clamped
-            // to the format's maximum - see the IntegerBorderColorScenario case that pins it. Picking
-            // the representation by the FORM instead would answer 0 here, which is a defensible
-            // reading of the same spec text but puts DirectVulkan at odds with DirectGLES - and
-            // DirectGLES cannot deviate, it forwards the value to the driver verbatim. Cross-backend
-            // agreement decides it.
-            const auto range = ResolveIntegerBorderRange(format);
-            const auto& borderColorI = sampler.GetBorderColorI();
-            const auto& borderColorUI = sampler.GetBorderColorUI();
-            const Bool startFromUnsigned = domain == BorderColorDomain::UnsignedInteger;
-            Int64 clamped[4];
-            for (SizeT channel = 0; channel < 4; ++channel) {
-                const Int64 raw = startFromUnsigned ? static_cast<Int64>(borderColorUI[channel])
-                                                    : static_cast<Int64>(borderColorI[channel]);
-                const Int64 low = channel == 3 ? range.alphaMin : range.rgbMin;
-                const Int64 high = channel == 3 ? range.alphaMax : range.rgbMax;
-                clamped[channel] = std::clamp(raw, low, high);
-            }
-
-            // Matched against the CLAMPED value, so a border the format cannot hold still lands on
-            // the palette entry it clamps to rather than missing every one of them.
-            const Bool allZeroRgb = clamped[0] == 0 && clamped[1] == 0 && clamped[2] == 0;
-            if (allZeroRgb && clamped[3] == 0) {
-                resolved.color = VK_BORDER_COLOR_INT_TRANSPARENT_BLACK;
-                return resolved;
-            }
-            if (allZeroRgb && clamped[3] == 1) {
-                resolved.color = VK_BORDER_COLOR_INT_OPAQUE_BLACK;
-                return resolved;
-            }
-            if (clamped[0] == 1 && clamped[1] == 1 && clamped[2] == 1 && clamped[3] == 1) {
-                resolved.color = VK_BORDER_COLOR_INT_OPAQUE_WHITE;
-                return resolved;
-            }
-            if (canUseCustom) {
-                resolved.color = VK_BORDER_COLOR_INT_CUSTOM_EXT;
-                resolved.isCustom = true;
-                for (SizeT channel = 0; channel < 4; ++channel) {
-                    if (domain == BorderColorDomain::UnsignedInteger) {
-                        resolved.customValue.uint32[channel] = static_cast<Uint32>(clamped[channel]);
-                    } else {
-                        resolved.customValue.int32[channel] = static_cast<Int32>(clamped[channel]);
-                    }
-                }
-                return resolved;
-            }
-            // No custom colour available: pick the nearest of the three integer palette entries
-            // rather than always answering transparent black, which is what turned an integer border
-            // of (-1,-1,-1,-1) into 0 and broke the CTS's clamped-texel detection outright.
-            const Bool opaque = clamped[3] != 0;
-            const Bool bright = clamped[0] != 0 || clamped[1] != 0 || clamped[2] != 0;
-            resolved.color = !opaque ? VK_BORDER_COLOR_INT_TRANSPARENT_BLACK
-                                     : (bright ? VK_BORDER_COLOR_INT_OPAQUE_WHITE : VK_BORDER_COLOR_INT_OPAQUE_BLACK);
-            return resolved;
-        }
-
-        // Float domain. GL 4.6 core 8.14.2/8.23: the border colour is interpreted in the texture's
-        // format, so it is clamped to that format's representable range first. Without the clamp the
-        // CTS's border of (255,255,255,255) on a GL_RGBA8 texture matched none of the palette entries
-        // and fell through to transparent black - every border texel sampled 0 where the test wanted
-        // 255. The range is per format class, not just the normalized [0,1] / [-1,1] pair: only the
-        // 32-bit float formats are unclamped.
-        FloatVec4 borderColor = sampler.GetBorderColor();
-        if (const auto range = ResolveFloatBorderRange(format, IsSignedNormalizedFormat(format)); range.clamped) {
-            borderColor = FloatVec4(std::clamp(borderColor.x(), range.minValue, range.maxValue),
-                                    std::clamp(borderColor.y(), range.minValue, range.maxValue),
-                                    std::clamp(borderColor.z(), range.minValue, range.maxValue),
-                                    std::clamp(borderColor.w(), range.minValue, range.maxValue));
-        }
-
-        // A depth texture samples one component, so only x decides - and its alpha reads as 1.
-        if (IsDepthTextureFormat(format)) {
+        if (isDepthTexture) {
             if (NearlyEqual(borderColor.x(), 1.0f)) {
-                resolved.color = VK_BORDER_COLOR_FLOAT_OPAQUE_WHITE;
-                return resolved;
+                return VK_BORDER_COLOR_FLOAT_OPAQUE_WHITE;
             }
             if (NearlyEqual(borderColor.x(), 0.0f)) {
-                resolved.color = VK_BORDER_COLOR_FLOAT_OPAQUE_BLACK;
-                return resolved;
+                return VK_BORDER_COLOR_FLOAT_OPAQUE_BLACK;
             }
         }
 
         const Bool rgbZero = NearlyEqual(borderColor.x(), 0.0f) && NearlyEqual(borderColor.y(), 0.0f) &&
                              NearlyEqual(borderColor.z(), 0.0f);
         if (rgbZero && NearlyEqual(borderColor.w(), 0.0f)) {
-            resolved.color = VK_BORDER_COLOR_FLOAT_TRANSPARENT_BLACK;
-            return resolved;
+            return VK_BORDER_COLOR_FLOAT_TRANSPARENT_BLACK;
         }
         if (rgbZero && NearlyEqual(borderColor.w(), 1.0f)) {
-            resolved.color = VK_BORDER_COLOR_FLOAT_OPAQUE_BLACK;
-            return resolved;
+            return VK_BORDER_COLOR_FLOAT_OPAQUE_BLACK;
         }
         if (NearlyEqual(borderColor.x(), 1.0f) && NearlyEqual(borderColor.y(), 1.0f) &&
             NearlyEqual(borderColor.z(), 1.0f) && NearlyEqual(borderColor.w(), 1.0f)) {
-            resolved.color = VK_BORDER_COLOR_FLOAT_OPAQUE_WHITE;
-            return resolved;
+            return VK_BORDER_COLOR_FLOAT_OPAQUE_WHITE;
         }
 
-        if (canUseCustom) {
-            resolved.color = VK_BORDER_COLOR_FLOAT_CUSTOM_EXT;
-            resolved.isCustom = true;
-            resolved.customValue.float32[0] = borderColor.x();
-            resolved.customValue.float32[1] = borderColor.y();
-            resolved.customValue.float32[2] = borderColor.z();
-            resolved.customValue.float32[3] = borderColor.w();
-            return resolved;
-        }
-
-        // Nearest of the three float palette entries. Transparent black stays the answer for a
-        // transparent border, which is what the old unconditional fallback got right by accident.
-        const Bool opaque = borderColor.w() >= 0.5f;
-        const Bool bright = (borderColor.x() + borderColor.y() + borderColor.z()) >= 1.5f;
-        resolved.color = !opaque ? VK_BORDER_COLOR_FLOAT_TRANSPARENT_BLACK
-                                 : (bright ? VK_BORDER_COLOR_FLOAT_OPAQUE_WHITE : VK_BORDER_COLOR_FLOAT_OPAQUE_BLACK);
-        return resolved;
+        return VK_BORDER_COLOR_FLOAT_TRANSPARENT_BLACK;
     }
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkSamplerManager.h

@@ -28,116 +28,45 @@ public:
         Bool samplerAnisotropySupported = false;
         // VkPhysicalDeviceLimits::maxSamplerAnisotropy.
         Float maxSamplerAnisotropy = 1.0f;
-        // VK_EXT_custom_border_color was enabled with BOTH customBorderColors and
-        // customBorderColorWithoutFormat; see VulkanRenderer::m_customBorderColorFeatureEnabled.
-        Bool customBorderColorSupported = false;
-        // VkPhysicalDeviceCustomBorderColorPropertiesEXT::maxCustomBorderColorSamplers. A hard device
-        // limit on how many LIVE samplers may carry a custom border colour, so the cache counts them
-        // and falls back to the snapped predefined value once it is reached.
-        Uint32 maxCustomBorderColorSamplers = 0;
     };
 
     Bool Initialize(const InitInfo& initInfo);
     void Shutdown();
 
-    // viewLevelCount is the mip-level count of the image view this sampler will be paired
-    // with; 0 means "unknown, do not narrow". See GetOrCreateSampler for why it matters.
     VkSampler GetOrCreateSampler(const MG_State::GLState::SamplerObject& sampler,
                                  const MG_State::GLState::ITextureObject& texture,
-                                 Bool forceNearestFiltering = false,
-                                 Uint32 viewLevelCount = 0);
-#if MOBILEGL_BUILD_DISAGGREGATED
-    // The applier owns these values: effective bound/builtin sampler parameters and
-    // the sampled texture view's format/range. No frontend object is constructed.
-    VkSampler GetOrCreateSamplerFromParameters(const SamplerParameters& parameters,
-        TextureInternalFormat format, Bool forceNearestFiltering = false, Uint32 viewLevelCount = 0);
-#endif
-    // Frame boundary hook: ages the sampler cache and destroys samplers not used
-    // for many frames. The key hashes continuous float state (lodBias, LOD clamps,
-    // anisotropy), so an app animating those would otherwise mint an unbounded
-    // stream of never-destroyed VkSamplers and eventually exhaust the device's
-    // maxSamplerAllocationCount. A sampler idle for over a thousand frame
-    // boundaries cannot be referenced by any in-flight command buffer (frames in
-    // flight are single digits), and every descriptor set the GPU consumes is
-    // written that same frame with live handles (the per-binding resolve memo and
-    // descriptor-set reuse are both frame-reset), so destruction here needs no
-    // fence wait. Self-gated: one counter bump and compare except on sweep
-    // boundaries.
-    void OnFrameBoundary();
-
-    // What GL_TEXTURE_BORDER_COLOR resolves to for one (sampler, texture) pair. `color` is always a
-    // legal VkBorderColor; when `isCustom` it is one of the *_CUSTOM_EXT values and `customValue`
-    // carries the actual components in a VkSamplerCustomBorderColorCreateInfoEXT.
-    //
-    // Resolved ONCE per GetOrCreateSampler call and threaded into both the cache key and the
-    // create-info, so the two cannot disagree - the same discipline the resolved anisotropy needs,
-    // and here it also makes the maxCustomBorderColorSamplers fallback deterministic: whether a
-    // custom colour was affordable is decided before the key is built, not twice with a budget
-    // change in between.
-    struct ResolvedBorderColor {
-        VkBorderColor color = VK_BORDER_COLOR_FLOAT_TRANSPARENT_BLACK;
-        VkClearColorValue customValue{};
-        Bool isCustom = false;
-    };
+                                 Bool forceNearestFiltering = false);
 
 private:
     struct SamplerCacheEntry {
         VkSampler handle = VK_NULL_HANDLE;
         Uint externalIndex = 0;
         Uint16 version = 0;
-        // Frame boundary of the last cache hit; entries idle past the
-        // OnFrameBoundary retirement age have their VkSampler destroyed.
-        Uint64 lastUsedFrameBoundary = 0;
-        // Counted against maxCustomBorderColorSamplers for as long as this entry lives.
-        Bool usesCustomBorderColor = false;
     };
 
-#if MOBILEGL_BUILD_DISAGGREGATED
-    template <class SamplerSource>
-    VkSampler GetOrCreateSamplerImpl(const SamplerSource& sampler, TextureInternalFormat format,
-                                     Bool forceNearestFiltering, Uint32 viewLevelCount);
-    template <class SamplerSource>
-    Uint64 BuildSamplerKey(const SamplerSource& sampler, Bool forceNearestFiltering,
-#else
-    Uint64 BuildSamplerKey(const MG_State::GLState::SamplerObject& sampler, Bool forceNearestFiltering,
-#endif
-                           Bool singleLevelView, const ResolvedBorderColor& borderColor) const;
+    Uint64 BuildSamplerKey(const MG_State::GLState::SamplerObject& sampler,
+                           const MG_State::GLState::ITextureObject& texture,
+                           Bool forceNearestFiltering) const;
     static VkFilter ToVkFilter(SamplerFilterMode mode);
     static VkSamplerMipmapMode ToVkMipmapMode(SamplerMipmapMode mode);
     static VkSamplerAddressMode ToVkAddressMode(SamplerWrapMode mode);
     static VkCompareOp ToVkCompareOp(SamplerCompareFunc func);
-#if MOBILEGL_BUILD_DISAGGREGATED
-    template <class SamplerSource>
-    ResolvedBorderColor ResolveBorderColor(const SamplerSource& sampler, TextureInternalFormat format) const;
-#else
-    ResolvedBorderColor ResolveBorderColor(const MG_State::GLState::SamplerObject& sampler,
-                                           const MG_State::GLState::ITextureObject& texture) const;
-#endif
+    static SamplerCompareFunc ResolveCompareFunc(const MG_State::GLState::SamplerObject& sampler,
+                                                 const MG_State::GLState::ITextureObject& texture);
+    static VkBorderColor ResolveVkBorderColor(const MG_State::GLState::SamplerObject& sampler,
+                                              const MG_State::GLState::ITextureObject& texture);
     // The anisotropy Vulkan will actually apply: 1.0 (i.e. disabled) unless the feature is on and
     // the sampler filters linearly both ways, otherwise the GL request clamped to the device limit.
     // GL happily carries GL_TEXTURE_MAX_ANISOTROPY on a NEAREST sampler (Blaze3D's blocks do exactly
     // that) while Vulkan forbids anisotropyEnable there, so the GL value must never be forwarded raw.
-#if MOBILEGL_BUILD_DISAGGREGATED
-    template <class SamplerSource>
-    Float ResolveEffectiveMaxAnisotropy(const SamplerSource& sampler,
-#else
     Float ResolveEffectiveMaxAnisotropy(const MG_State::GLState::SamplerObject& sampler,
-#endif
                                         Bool forceNearestFiltering) const;
 
     VkDevice m_device = VK_NULL_HANDLE;
     const VulkanRendererConfig* m_config = nullptr;
     Bool m_samplerAnisotropySupported = false;
     Float m_maxSamplerAnisotropy = 1.0f;
-    Bool m_customBorderColorSupported = false;
-    Uint32 m_maxCustomBorderColorSamplers = 0;
-    // Live cache entries carrying a custom border colour. Kept in step with the entries themselves
-    // in exactly the three places one can appear or disappear: creation, the OnFrameBoundary sweep,
-    // and Shutdown.
-    Uint32 m_customBorderColorSamplerCount = 0;
     UnorderedMap<Uint64, SamplerCacheEntry> m_samplers;
-    // Monotonic frame-boundary counter (bumped in OnFrameBoundary) for cache aging.
-    Uint64 m_frameBoundaryCounter = 0;
     static inline XXH64_state_t* m_hashState = XXH64_createState();
 };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkTextureManager.h

@@ -10,137 +10,23 @@
 
 #include "../VkIncludes.h"
 #include <Includes.h>
-#include <MG_State/GLState/FramebufferState/FramebufferObject.h>
 #include <MG_State/GLState/TextureState/TextureObject.h>
 #include <vk_mem_alloc.h>
-#include <algorithm>
 #include <unordered_map>
-#include <unordered_set>
-
-#include <Config.h>
-#if MOBILEGL_BUILD_DISAGGREGATED
-// The handle-keyed arm's key type. Header-only POD, disagg-only, exactly the shape
-// MagmaPipeArms.h already gives this directory.
-#include <MG_Pipe/MGPipeHandles.h>
-#endif
 
 namespace MobileGL::MG_State::GLState {
 class ITextureObject;
 }
-#if MOBILEGL_BUILD_DISAGGREGATED
-namespace MobileGL::MG_Pipe {
-struct MGPipeResourceRecord;
-}
-#endif
 
 namespace MobileGL::MG_Backend::DirectVulkan {
 enum class SamplerNumericDomain : Uint8;
 
-// What VkFormat a GL internal format is BACKED with, and how a shadow upload has to be reshaped to
-// fit it. This is not the same question as "is there an exact VkFormat for this GL format", which is
-// what ConvertTextureInternalFormatToVkEnum answers: several GL formats have no Vulkan twin at all
-// (RGBA2, RGBA12) and several three-channel ones are deliberately widened to their four-channel twin
-// because Vulkan devices rarely support the 3-channel layouts.
-//
-// SHARED, and it must stay the only answer to that question. A renderbuffer and a texture of the
-// same GL format have to resolve to the SAME VkFormat or every blit, resolve and glCopyImageSubData
-// between them crosses a size-incompatible pair, which vkCmdCopyImage leaves undefined
-// (VUID-vkCmdCopyImage-srcImage-01548). The renderbuffer path used to carry a hand-maintained second
-// copy of this table that was missing four rows - RGBA2, RGBA4, RGB5A1 and RGBA12 - so those four
-// renderbuffer formats either got no image at all or a 16-bit-packed one facing a 32-bit texture.
-struct TextureFormatInfo {
-    VkFormat format = VK_FORMAT_UNDEFINED;
-    // The GL format has three channels and is carried in a four-channel image; a shadow upload has
-    // to be expanded, inserting `alphaBytes` after every `componentByteCount * 3` source bytes.
-    Bool expandRgbToRgba = false;
-    Uint32 componentByteCount = 0;
-    Array<Uint8, 4> alphaBytes = {0, 0, 0, 0};
-};
-
-// Callers that only need the backing VkFormat (a renderbuffer has no shadow upload to reshape) take
-// `.format` and ignore the rest.
-TextureFormatInfo ResolveTextureFormatInfo(TextureInternalFormat format);
-
-// A GL 1D-ARRAY level keeps its LAYER COUNT in the state-side HEIGHT: that is what
-// glTexImage2D(GL_TEXTURE_1D_ARRAY, width, layers) means, and the frontend records the level
-// as {width, layers, 1} (see GL_Texture.cpp's AllocateStorage and the completeness walk in
-// TextureObject.cpp, which shrinks only x down the chain). Vulkan packs it the other way: a
-// 1D array is a VK_IMAGE_TYPE_1D image whose extent.height MUST be 1 and whose layers live in
-// arrayLayers - i.e. in the slot this backend reads out of z. So every place that turns a GL
-// level size into Vulkan image geometry has to move the count across first, and every GL-space
-// sub-box that rides along with it has to move its y the same way. DirectGLES performs the
-// identical remap onto the ES 2D array it maps 1D arrays to (GetBackendUploadSize).
-//
-// Applied to nothing else: a 2D array, a cube array and a 3D texture all already carry their
-// depth/layer count in z, which is where the Vulkan side expects it.
-inline IntVec3 ToVulkanLevelExtent(TextureTarget stateTarget, const IntVec3& glTexelSize) {
-    if (stateTarget == TextureTarget::Texture1DArray) {
-        return {glTexelSize.x(), 1, glTexelSize.y()};
-    }
-    return glTexelSize;
-}
-
-// How many Vulkan array layers (or, for a 3D image, z slices) a GL framebuffer attachment spans.
-//
-// THE ONE COPY, deliberately. This used to exist twice - privately in VkRenderPassManager.cpp and
-// again in VkClearManager.cpp - and the two are not independent: the render pass builds the
-// attachment view and VkFramebufferCreateInfo::layers from one, while the CLEAR key built from the
-// other is written verbatim into VkImageSubresourceRange::layerCount when a queued glClear is
-// materialised outside a render pass (MaterializePendingClearForTexture). They are two consumers
-// of the same GL clear, so any disagreement means the same glClear produces two different pictures
-// depending only on which path happens to consume it first - and the materialise path then POPS
-// the entry, so the other one never runs. Fixing one copy and leaving the other is exactly how
-// that split gets introduced; keep them the same function.
-//
-// Two shapes make this more than `size.z()`:
-//   * GL_TEXTURE_1D_ARRAY keeps its layer count in the state-side HEIGHT (see ToVulkanLevelExtent
-//     just above), so z reads 1 and every layer above the first was silently dropped.
-//   * GL_TEXTURE_CUBE_MAP is attached layered as its REPRESENTATIVE upload target, the +X face
-//     (ResolveRepresentableFramebufferTextureUploadTarget), and one face's level size has z = 1 -
-//     but a layered cube attachment names all six faces (GL 4.6 core 9.2.8), which are the image's
-//     six array layers. A cube ARRAY needs no such arm: its representative target carries 6n in z.
-inline Uint32 ResolveAttachmentLayerCount(const MG_State::GLState::FramebufferAttachmentObject& attachment) {
-    if (!attachment.IsLayered()) {
-        return 1u;
-    }
-    const auto& texture = attachment.GetTexture();
-    const TextureTarget target = texture != nullptr ? texture->GetTarget() : TextureTarget::Unknown;
-    if (target == TextureTarget::TextureCubeMap) {
-        return 6u;
-    }
-    return static_cast<Uint32>(std::max(ToVulkanLevelExtent(target, attachment.GetSize()).z(), 1));
-}
-
-// A GL framebuffer attachment's level/layer, and a GL image unit's, are relative to the texture
-// the application NAMED. When that texture was created by glTextureView (ARB_texture_view) they
-// are relative to the VIEW, and have to be shifted into the storage image's numbering before they
-// can index a Vulkan subresource - DirectVulkan gives a view no image of its own, it shares the
-// storage texture's (VkTextureManager::StorageTextureOf).
-//
-// Apply EXACTLY ONCE, at the boundary where a GL level/layer becomes a subresource index. Every
-// GetOrCreate*View entry point below expects values that have already been through here, and so
-// does everything that reads or copies an attachment directly. Both are identity on a plain
-// texture (TEXTURE_VIEW_MIN_LEVEL / MIN_LAYER are 0 there), so the conversion is unconditional
-// and there is no second, view-only code path to keep in step.
-inline Uint32 ToStorageMipLevel(const MG_State::GLState::ITextureObject* texture, Int glLevel) {
-    const Uint32 level = static_cast<Uint32>(glLevel > 0 ? glLevel : 0);
-    return texture != nullptr ? level + static_cast<Uint32>(texture->GetViewMinLevel()) : level;
-}
-
-inline Uint32 ToStorageArrayLayer(const MG_State::GLState::ITextureObject* texture, Int glLayer) {
-    const Uint32 layer = static_cast<Uint32>(glLayer > 0 ? glLayer : 0);
-    return texture != nullptr ? layer + static_cast<Uint32>(texture->GetViewMinLayer()) : layer;
-}
-
 class VkTextureManager {
 public:
     // Monotonic epoch bumped whenever a texture VkImage is (re)created. The render-pass
     // manager keys its per-draw fast path on this so an attachment's image recreation
     // invalidates the cached render pass (dirty-flag tracking; portable to Vulkan 1.1).
     Uint64 GetTextureImageEpoch() const { return m_textureImageEpoch; }
-    // Bumped whenever any tracked texture resource is erased; cached
-    // TextureResource pointers are valid only while this is unchanged.
-    Uint64 GetResourceEraseEpoch() const { return m_resourceEraseEpoch; }
 
     struct TextureIdentity {
         MG_State::GLState::ITextureObject* texture = nullptr;
@@ -166,20 +52,6 @@ public:
         VkCommandPool commandPool = VK_NULL_HANDLE;
         VkQueue graphicsQueue = VK_NULL_HANDLE;
         Uint32 frameCount = 0;
-        // VK_KHR_image_format_list is enabled: MUTABLE_FORMAT images can name the exact set of
-        // formats they will be viewed as, which is what lets a tiler keep them compressed.
-        Bool imageFormatListSupported = false;
-        // Union of shader stages sampled-read barriers may name on this device; the renderer
-        // builds it from the enabled features because geometry/tessellation stage bits are
-        // invalid in a barrier when their feature is off.
-        VkPipelineStageFlags sampledReadStageMask = VK_PIPELINE_STAGE_VERTEX_SHADER_BIT |
-                                                    VK_PIPELINE_STAGE_FRAGMENT_SHADER_BIT |
-                                                    VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT;
-        // Family of `graphicsQueue`; the manager creates its own command pool
-        // on it for the recycled upload-batch command buffers, so their parked
-        // allocations never sit in (and fragment) the renderer's shared pool
-        // that frame command buffers churn through every frame.
-        Uint32 graphicsQueueFamilyIndex = 0;
     };
 
     struct TextureResource {
@@ -188,16 +60,12 @@ public:
             Uint32 baseArrayLayer = 0;
             Uint32 layerCount = 1;
             VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
-            // May differ from the image format: sRGB images attach through their UNORM
-            // twin while GL_FRAMEBUFFER_SRGB is disabled.
-            VkFormat viewFormat = VK_FORMAT_UNDEFINED;
 
             Bool operator==(const AttachmentViewKey& other) const {
                 return mipLevel == other.mipLevel &&
                        baseArrayLayer == other.baseArrayLayer &&
                        layerCount == other.layerCount &&
-                       viewType == other.viewType &&
-                       viewFormat == other.viewFormat;
+                       viewType == other.viewType;
             }
         };
 
@@ -208,8 +76,6 @@ public:
                 hash ^= std::hash<Uint32>{}(key.layerCount) + 0x9e3779b9u + (hash << 6) + (hash >> 2);
                 hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.viewType)) +
                         0x9e3779b9u + (hash << 6) + (hash >> 2);
-                hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.viewFormat)) +
-                        0x9e3779b9u + (hash << 6) + (hash >> 2);
                 return hash;
             }
         };
@@ -230,35 +96,17 @@ public:
             }
         };
 
-        // Layer range and aspect join the key because a GL texture view (ARB_texture_view) can
-        // differ from its storage on either: the Better Clouds shape samples ONE D24S8 image
-        // through two GL names in one draw, the parent with the stencil aspect and the view with
-        // the depth aspect, and a layer-sliced view of an array texture names a sub-range of the
-        // same image. Without these two fields those views would alias each other in the cache.
         struct SampledImageViewKey {
             Uint32 baseMipLevel = 0;
             Uint32 levelCount = 1;
-            Uint32 baseArrayLayer = 0;
-            Uint32 layerCount = 1;
             VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
             VkFormat format = VK_FORMAT_UNDEFINED;
-            VkImageAspectFlags aspect = VK_IMAGE_ASPECT_COLOR_BIT;
-            // GL_TEXTURE_SWIZZLE_* is per-texture state, so two views over one storage with the
-            // same window but different swizzles are different views. Baked into the key because
-            // a GL texture view's ONLY sampled view lives in this cache: unlike the storage
-            // texture's own sampledView, which SyncTextureViews rebuilds whenever the params
-            // version moves, nothing else would ever notice a swizzle change on a view.
-            Uint32 componentSwizzle = 0;
 
             Bool operator==(const SampledImageViewKey& other) const {
                 return baseMipLevel == other.baseMipLevel &&
                        levelCount == other.levelCount &&
-                       baseArrayLayer == other.baseArrayLayer &&
-                       layerCount == other.layerCount &&
                        viewType == other.viewType &&
-                       format == other.format &&
-                       aspect == other.aspect &&
-                       componentSwizzle == other.componentSwizzle;
+                       format == other.format;
             }
         };
 
@@ -266,15 +114,10 @@ public:
             SizeT operator()(const SampledImageViewKey& key) const {
                 SizeT hash = std::hash<Uint32>{}(key.baseMipLevel);
                 hash ^= std::hash<Uint32>{}(key.levelCount) + 0x9e3779b9u + (hash << 6) + (hash >> 2);
-                hash ^= std::hash<Uint32>{}(key.baseArrayLayer) + 0x9e3779b9u + (hash << 6) + (hash >> 2);
-                hash ^= std::hash<Uint32>{}(key.layerCount) + 0x9e3779b9u + (hash << 6) + (hash >> 2);
                 hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.viewType)) +
                         0x9e3779b9u + (hash << 6) + (hash >> 2);
                 hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.format)) +
                         0x9e3779b9u + (hash << 6) + (hash >> 2);
-                hash ^= std::hash<Uint32>{}(static_cast<Uint32>(key.aspect)) +
-                        0x9e3779b9u + (hash << 6) + (hash >> 2);
-                hash ^= std::hash<Uint32>{}(key.componentSwizzle) + 0x9e3779b9u + (hash << 6) + (hash >> 2);
                 return hash;
             }
         };
@@ -313,25 +156,7 @@ public:
         VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
         VkSampleCountFlagBits sampleCount = VK_SAMPLE_COUNT_1_BIT;
         VkImageCreateFlags imageCreateFlags = 0;
-        // Usage the live image was created with. STORAGE is only requested for textures that
-        // have actually been bound to a GL image unit, because on Adreno a storage-capable
-        // image loses UBWC bandwidth compression; a later image binding upgrades the usage
-        // and recreates the image, so the resolved usage has to be part of the compatibility
-        // check that decides whether the existing image can be kept.
-        VkImageUsageFlags usageFlags = 0;
-        // True once this image was (re)resolved while the texture was already marked as an
-        // image-unit texture. Distinguishes "not upgraded yet" from "cannot be upgraded"
-        // (a format whose optimalTilingFeatures lack STORAGE_IMAGE never gains the bit), so
-        // NeedsStorageImagePreparation cannot ask for a recreate that will never happen.
-        Bool storageUsageResolved = false;
         Uint16 syncedTextureParamsVersion = 0;
-        // Recording generation (VkTextureManager::GetRecordingGeneration) of the last
-        // command referencing this image that was recorded into the CURRENT frame
-        // command buffer. An image untouched by the open recording may have its
-        // out-of-pass work (deferred clears, sampled-layout transitions) recorded
-        // into the frame's PRE command buffer - which executes strictly before the
-        // frame's commands - instead of splitting the active render pass.
-        Uint64 lastRecordingGeneration = 0;
         // Snapshot of ITextureObject::GetContentVersion() at the last successful sync;
         // lets SyncTexture skip the whole re-check/re-upload when content is unchanged.
         Uint64 syncedContentVersion = 0;
@@ -339,19 +164,6 @@ public:
         // as defense-in-depth: any path that grows the level set (which resizes the sampled view)
         // busts the skip even if it failed to bump the content version.
         Uint32 syncedMipLevelCount = 0;
-        // Snapshot of ITextureObject::GetShapeVersion() at the last successful sync. The content
-        // version alone does NOT cover a re-specification: glTexImage2D(..., nullptr) on an
-        // already-defined level changes its size or format and dirties no texel, so it moves the
-        // shape version and nothing else. Without this in the early-out key the image, its views
-        // and therefore imageSize() all keep answering with the texture's PREVIOUS shape.
-        Uint64 syncedShapeVersion = 0;
-        // The handle-keyed arm's (P5f fm) early-out key: the applier record's server-owned
-        // Serial at the last successful sync. 0 also means "this resource has only ever been
-        // synced by the frontend arm" - a wire record's Serial starts at 0 on a create and moves
-        // on every mutation, so the first handle sync of a fresh image always re-checks.
-#if MOBILEGL_BUILD_DISAGGREGATED
-        Uint64 syncedWireSerial = 0;
-#endif
 
         TextureResource() = default;
         TextureResource(const TextureResource&) = delete;
@@ -377,16 +189,9 @@ public:
             std::swap(this->viewType, that.viewType);
             std::swap(this->sampleCount, that.sampleCount);
             std::swap(this->imageCreateFlags, that.imageCreateFlags);
-            std::swap(this->usageFlags, that.usageFlags);
-            std::swap(this->storageUsageResolved, that.storageUsageResolved);
             std::swap(this->syncedTextureParamsVersion, that.syncedTextureParamsVersion);
-            std::swap(this->lastRecordingGeneration, that.lastRecordingGeneration);
             std::swap(this->syncedContentVersion, that.syncedContentVersion);
             std::swap(this->syncedMipLevelCount, that.syncedMipLevelCount);
-            std::swap(this->syncedShapeVersion, that.syncedShapeVersion);
-#if MOBILEGL_BUILD_DISAGGREGATED
-            std::swap(this->syncedWireSerial, that.syncedWireSerial);
-#endif
         }
 
         void Reset() {
@@ -445,15 +250,9 @@ public:
             viewType = VK_IMAGE_VIEW_TYPE_2D;
             sampleCount = VK_SAMPLE_COUNT_1_BIT;
             imageCreateFlags = 0;
-            usageFlags = 0;
-            storageUsageResolved = false;
             syncedTextureParamsVersion = 0;
             syncedContentVersion = 0;
             syncedMipLevelCount = 0;
-            syncedShapeVersion = 0;
-#if MOBILEGL_BUILD_DISAGGREGATED
-            syncedWireSerial = 0;
-#endif
         }
 
         ~TextureResource() {
@@ -464,128 +263,12 @@ public:
         static inline VmaAllocator s_allocator = VK_NULL_HANDLE;
     };
 
-    struct SampledTextureSnapshot {
-        VkImageView imageView = VK_NULL_HANDLE;
-        VkImageLayout layout = VK_IMAGE_LAYOUT_UNDEFINED;
-    };
-
     Bool Initialize(const InitInfo& initInfo);
     void Shutdown();
     void BeginFrame(Uint32 frameIndex);
-    // Submits the accumulated texture-upload batch (one command buffer, one
-    // vkQueueSubmit, one pooled fence) if any uploads are pending. MUST run
-    // before any other vkQueueSubmit on the shared graphics queue whose
-    // commands may consume an image the batch writes - the frame command
-    // buffer submit (mid-frame flush, readback, Present) and the
-    // preserve-on-recreate copy are the existing callers. No-op when the
-    // batch is empty.
-    void FlushPendingUploads();
-#if MOBILEGL_BUILD_DISAGGREGATED
-    // Non-blocking idle proof for wire-object retirement. Independent texture
-    // submissions are not represented by VulkanRenderer's submit counter.
-    Bool WireUploadsAreIdle();
-#endif
-
-    // Drains every frame slot's deferred image/view releases. Only valid when
-    // the caller has proven every queue submission complete; used by the
-    // present-less frame-boundary drain.
-    void CollectAllDeferredReleases();
-
-    // ---- GL texture views (ARB_texture_view / GL 4.6 core 8.18) ----
-    // The GL texture whose STORAGE backs the given one: itself, or - for a texture created by
-    // glTextureView - the texture it views. Every image-scoped question (which VkImage, its
-    // LAYOUT, its uploads, its extent, its usage) must be asked of this object, because a view
-    // has none of its own; only the VkImageViews differ per GL texture object. Sharing one
-    // TextureResource is not an optimisation, it is the only correct arrangement: layout is a
-    // property of the image, and VulkanRenderer caches raw pointers straight to the resource's
-    // layout field, so a second resource aliasing the same image would desynchronise the moment
-    // either of them transitioned it.
-    static MG_State::GLState::ITextureObject& StorageTextureOf(MG_State::GLState::ITextureObject& texture);
-
-    // The window a GL texture object opens onto its storage image. For a plain texture this is
-    // the resource's own full extent; for a view it is the sub-range, format and aspect
-    // glTextureView gave it. Views built from a non-default window must live in the KEYED caches
-    // (attachmentViews / alternateSampledViews), never in the per-mip vectors, which belong to
-    // the storage texture's own defaults.
-    struct TextureViewWindow {
-        Uint32 baseMipLevel = 0;
-        Uint32 levelCount = 1;
-        Uint32 baseArrayLayer = 0;
-        Uint32 layerCount = 1;
-        VkFormat format = VK_FORMAT_UNDEFINED;
-        VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
-        VkImageAspectFlags sampledAspect = VK_IMAGE_ASPECT_COLOR_BIT;
-        VkComponentMapping components{VK_COMPONENT_SWIZZLE_R, VK_COMPONENT_SWIZZLE_G, VK_COMPONENT_SWIZZLE_B,
-                                      VK_COMPONENT_SWIZZLE_A};
-        Bool isTextureView = false;
-    };
-
-    // The four component swizzles packed into one value, for the sampled-view cache key.
-    static Uint32 PackComponentSwizzle(const VkComponentMapping& components) {
-        return (static_cast<Uint32>(components.r) & 0xFFu) | ((static_cast<Uint32>(components.g) & 0xFFu) << 8) |
-               ((static_cast<Uint32>(components.b) & 0xFFu) << 16) |
-               ((static_cast<Uint32>(components.a) & 0xFFu) << 24);
-    }
-    TextureViewWindow ResolveTextureViewWindow(MG_State::GLState::ITextureObject& texture,
-                                               const TextureResource& resource) const;
-    // Records what a GL texture view needs of the image it views, so the next sync of the
-    // STORAGE texture creates (or recreates and copies forward) an image the view can be built
-    // over. See m_viewRequestedImageFlags for why this is lazy rather than unconditional.
-    void NoteTextureViewImageRequirements(MG_State::GLState::ITextureObject& viewTexture,
-                                          MG_State::GLState::ITextureObject& storageTexture);
-    VkImageCreateFlags GetViewRequestedImageFlags(const MG_State::GLState::ITextureObject& storageTexture) const;
-    // Appends every format a GL texture view reinterprets this storage as, for the narrowed
-    // VkImageFormatListCreateInfo the image is created with.
-    void AppendViewRequestedFormats(const MG_State::GLState::ITextureObject& storageTexture,
-                                    Vector<VkFormat>& outFormats) const;
-    // Builds (and caches, keyed by the whole window) one sampled VkImageView over a storage
-    // image. Shared back end of every GL-texture-view sampled path.
-    VkImageView GetOrCreateWindowedSampledView(MG_State::GLState::ITextureObject& texture,
-                                               TextureResource& resource, const TextureViewWindow& window);
 
     TextureResource* SyncTextureAndGetDescriptor(
         MG_State::GLState::ITextureObject& texture);
-#if MOBILEGL_BUILD_DISAGGREGATED
-    // P5f (fm): THE HANDLE-KEYED ARM of SyncTextureAndGetDescriptor. Under an active transport
-    // the apply thread may not name the client's ITextureObject (rule E), so the clear / blit /
-    // readback / mipmap verbs resolve their attachment textures from the wire handle the
-    // framebuffer or mip record carried: shape from the applier's resource record
-    // (MGPipeApplier().TextureResources), texels from the server's staged-texture store
-    // (P5c tx), pending-upload bookkeeping consumed from the same record. Returns null - never
-    // a frontend fallback - when the record or the shape does not resolve; the caller declines
-    // loudly, which is the honest answer a missing record deserves.
-    //
-    // The resource lives in m_wireTextureResources keyed by StagedTextureStore::KeyForHandle -
-    // a NAMESPACE THE FRONTEND-KEYED m_textureResources NEVER MEETS, so a recycled {slot, gen}
-    // can never inherit its predecessor's image. Texture views resolve the storage owner from
-    // Desc.ViewOf and the window from ViewCso; buffer-backed textures remain P7's buffer arm.
-    Bool ReadUnbackedWireLevel(MG_Pipe::MGPipeHandle handle, TextureUploadTarget target, Uint32 level,
-                               const IntVec3& extent, VkFormat& format, Vector<Uint8>& bytes);
-    TextureResource* SyncTextureResourceByHandle(MG_Pipe::MGPipeHandle handle, Bool renderbuffer = false,
-                                                 Bool requireStorage = false);
-    // Map a texture/view-relative subresource to its live storage owner. layerCount, when
-    // supplied, receives the number of accessible layers starting at the input layer.
-    // viewFormat is UNDEFINED for an ordinary texture, or the outer view's format.
-    // outsideWindow, when supplied, says WHY a null came back: true only when every record on
-    // the way was live and consistent and the (level, layer) simply is not there - past the
-    // owner's levels or layers, or past a view's own window. A dead record, a missing or stale
-    // view CSO and an unresolvable view format leave it false.
-    MG_Pipe::MGPipeHandle ResolveWireTextureStorage(MG_Pipe::MGPipeHandle handle, Uint32& level,
-        Uint32& layer, VkFormat* viewFormat = nullptr, Uint32* layerCount = nullptr,
-        Bool* outsideWindow = nullptr);
-    // Grows the live image of a handle-keyed resource to `requiredMipLevels`, carrying the
-    // existing levels' content across with an in-command-buffer copy. The caller
-    // (GenerateMipmap's record arm) has flushed every pending submission first, so the old
-    // image is GPU-idle and the copy may be recorded into `commandBuffer` directly; the old
-    // image goes to the deferred-release ring. False when the chain cannot grow (the resource
-    // stays as it was).
-    Bool GrowWireTextureMipChain(MG_Pipe::MGPipeHandle handle, Uint32 requiredMipLevels,
-                                 VkCommandBuffer commandBuffer);
-    // Records that GPU writes superseded the staged CPU snapshot of this level. Layer
-    // ranges select cube faces; array and 3D levels share one staged level shadow.
-    void MarkWireTextureGpuWritten(MG_Pipe::MGPipeHandle handle, Uint32 mipLevel,
-                                    Uint32 baseArrayLayer = 0, Uint32 layerCount = 1);
-#endif
     VkImageView GetOrCreateViewAtMipLevel(MG_State::GLState::ITextureObject& texture, Uint32 mipLevel);
     VkImageView GetOrCreateAttachmentViewAtMipLevel(MG_State::GLState::ITextureObject& texture, Uint32 mipLevel,
                                                     Uint32 baseArrayLayer, Uint32 layerCount,
@@ -601,76 +284,18 @@ public:
                                                       VkImageLayout newLayout);
     Bool TransitionTextureForSampling(VkCommandBuffer commandBuffer, MG_State::GLState::ITextureObject& texture);
     Bool TransitionTextureForStorageImage(VkCommandBuffer commandBuffer, MG_State::GLState::ITextureObject& texture);
-    // Copies the complete sampler-visible mip range into a transient sampled image. The source is
-    // restored to its prior layout, so image-store descriptors continue to name the original image.
-    // The transient ownership is tied to the current frame slot and is safe through its submission.
-    Bool SnapshotTextureForSampling(VkCommandBuffer commandBuffer, MG_State::GLState::ITextureObject& texture,
-                                    SamplerNumericDomain numericDomain,
-                                    VkPipelineStageFlags consumerShaderStageMask,
-                                    SampledTextureSnapshot& outSnapshot);
 
-    // Recording-generation bookkeeping for the pre-pass command stream. The
-    // generation advances every time the frame command buffer (re)begins
-    // recording; a resource whose stamp does not match was not referenced by
-    // any command in the open recording, so its out-of-pass work may safely
-    // execute ahead of the whole recording (in the pre command buffer).
-    void AdvanceRecordingGeneration() { ++m_recordingGeneration; }
-    void StampResourceRecordingUse(TextureResource& resource) const {
-        resource.lastRecordingGeneration = m_recordingGeneration;
-    }
-    // Map-lookup variant for callers that only hold the GL texture object.
-    void StampTextureRecordingUse(MG_State::GLState::ITextureObject* texture);
-    Bool WasTouchedThisRecording(const TextureResource& resource) const {
-        return resource.lastRecordingGeneration == m_recordingGeneration;
-    }
-    // Records that this texture is bound to a GL image unit, so its image must carry
-    // VK_IMAGE_USAGE_STORAGE_BIT. Must be called before NeedsStorageImagePreparation, and
-    // therefore before the render pass is committed: an image that has to be upgraded is
-    // recreated, which is illegal inside a render pass. Sticky for the texture's lifetime -
-    // GL lets an image binding come and go, and re-creating the image every time it does
-    // would cost far more than the compression it wins back.
-    void MarkStorageImageTexture(MG_State::GLState::ITextureObject& texture);
-    // True when this texture is marked but its live image predates the mark, i.e. the next sync
-    // will recreate it with STORAGE usage and copy the old contents forward. Callers use this to
-    // submit their pending recording first, so that copy cannot read pre-flush content.
-    Bool NeedsStorageUsageUpgrade(MG_State::GLState::ITextureObject& texture) const;
-    // The same ordering question for the other recreate-and-preserve trigger: true when this
-    // texture's live image carries a shorter mip chain than a full one, so defining the missing
-    // levels recreates it and copies the old contents forward.
-    Bool NeedsMipChainGrowth(MG_State::GLState::ITextureObject& texture) const;
-    // Non-mutating probe for the per-draw storage-image fast path: true when preparing this
-    // texture as a storage image may need work that is illegal inside a render pass (resource
-    // creation, dirty-content upload, or a layout transition to GENERAL). Unknown state reports
-    // true - a false positive merely ends the render pass, a false negative would skip a barrier.
-    Bool NeedsStorageImagePreparation(MG_State::GLState::ITextureObject& texture) const;
-
-    // `depthStencilTextureMode` is the texture's GL_DEPTH_STENCIL_TEXTURE_MODE; it only decides
-    // anything for an image that carries both aspects. Defaulted so the call sites that have no
-    // texture in hand keep the depth-aspect answer they have always given.
-    static VkImageAspectFlags ResolveSampledImageViewAspectMask(VkImageAspectFlags imageAspect,
-                                                                GLenum depthStencilTextureMode = GL_DEPTH_COMPONENT);
+    static VkImageAspectFlags ResolveSampledImageViewAspectMask(VkImageAspectFlags imageAspect);
     static VkFormat ResolveSampledImageViewFormat(VkFormat imageFormat, SamplerNumericDomain numericDomain);
     static Bool AreSampledImageViewFormatsCompatible(VkFormat imageFormat, VkFormat viewFormat);
     static Bool AreStorageImageViewFormatsCompatible(VkFormat imageFormat, VkFormat viewFormat);
 
-    // Moves `image` to `newLayout` and writes the new layout back through `trackedLayout`.
-    //
-    // The barrier covers EVERY array layer of the image, and there is deliberately no layer
-    // parameter to say otherwise: layout here is tracked per IMAGE (one `TextureResource::layout`,
-    // or one caller-owned variable), so a barrier narrower than the image would leave the layers it
-    // skipped in the old layout while the tracker claims they moved. Every transfer against a
-    // framebuffer attachment above layer 0 - glReadPixels, glBlitFramebuffer, glCopyTexSubImage,
-    // glCopyImageSubData - then ran its copy on a layer no barrier had transitioned.
-    //
-    // The mip range IS a parameter, because mip levels really are transitioned piecewise (see
-    // UpdateTrackedImageLayoutAfterAttachmentWrite and the mipmap generation loops): those callers
-    // move the complement of the level they wrote so the whole image converges on one layout again.
-    // Nothing does, or can, do that per layer.
     static Bool TransitionImageLayout(VkCommandBuffer commandBuffer, VkImage image, VkImageLayout& trackedLayout,
                                VkImageLayout newLayout, VkPipelineStageFlags srcStageMask,
                                VkPipelineStageFlags dstStageMask, VkAccessFlags srcAccessMask,
                                VkAccessFlags dstAccessMask, VkImageAspectFlags aspectMask,
-                               Uint32 baseMipLevel = 0, Uint32 levelCount = 1);
+                               Uint32 baseMipLevel = 0, Uint32 levelCount = 1,
+                               Uint32 layerCount = 1);
 
     SizeT CollectGarbage();
 
@@ -700,9 +325,6 @@ public:
 private:
     // Bumped in SyncTextureResource right after vmaCreateImage(texture). See GetTextureImageEpoch().
     Uint64 m_textureImageEpoch = 1;
-    // See AdvanceRecordingGeneration. Starts above every resource's default
-    // stamp of 0 so a fresh resource counts as untouched.
-    Uint64 m_recordingGeneration = 1;
 
     Bool SyncTexture(MG_State::GLState::ITextureObject &texture,
                      TextureResource &outResource);
@@ -733,47 +355,18 @@ private:
     void DeferViewRelease(VkImageView view);
     void CollectDeferredReleases(Uint32 frameIndex);
     void DestroyDeferredReleases();
-    // Frees the fence/command buffer/staging buffer of every in-flight texture
-    // upload whose fence has signaled (submission order = completion order on
-    // the single queue, so the scan stops at the first still-pending entry).
-    // waitAll blocks on every entry - Shutdown's drain.
-    void ReclaimCompletedUploads(Bool waitAll = false);
     static TextureIdentity MakeTextureIdentity(MG_State::GLState::ITextureObject* texture);
     void EraseTrackedTexture(const TextureIdentity& identity);
     void PruneStaleTextureAliases(MG_State::GLState::ITextureObject* texture);
-    SizeT PruneDeadTextures();
-#if MOBILEGL_BUILD_DISAGGREGATED
-    // The two halves of SyncTextureResourceByHandle: shape from the resource record's
-    // descriptor (create / recreate / compatibility), then the pending-upload walk against the
-    // server's staged store. UploadPendingWireLevels mutates the applier's record (consumed
-    // entries are dropped), which is why the record is a non-const reference.
-    Bool SyncWireTextureShape(const MG_Pipe::MGPipeResourceRecord& record, TextureResource& resource,
-                              Bool requireStorage);
-    Bool UploadPendingWireLevels(MG_Pipe::MGPipeHandle handle, MG_Pipe::MGPipeResourceRecord& record,
-                                 TextureResource& resource);
-    // The handle-keyed twin of m_textureResources, keyed by StagedTextureStore::KeyForHandle.
-    // Node-based for the same reason m_renderbufferResources is: callers hold TextureResource*
-    // across map-touching calls.
-    std::unordered_map<Uint64, TextureResource> m_wireTextureResources;
-    // Handles are per-kind; a renderbuffer and texture may have identical slot/gen.
-    std::unordered_map<Uint64, TextureResource> m_wireRenderbufferResources;
-#endif
 
     VkDevice m_device = VK_NULL_HANDLE;
     VkPhysicalDevice m_physicalDevice = VK_NULL_HANDLE;
     VmaAllocator m_allocator = nullptr;
     VkCommandPool m_commandPool = VK_NULL_HANDLE;
-    // Dedicated pool for the recycled upload-batch command buffers (see
-    // InitInfo::graphicsQueueFamilyIndex).
-    VkCommandPool m_uploadCommandPool = VK_NULL_HANDLE;
     VkQueue m_graphicsQueue = VK_NULL_HANDLE;
-    Bool m_imageFormatListSupported = false;
     Uint32 m_currentFrameIndex = 0;
 
     Uint8 m_gcCounter = 0;
-    // Frame-boundary GC gate: counts BeginFrame calls, not draws, so texture churn
-    // through non-draw paths (FBO clears, readbacks) still reaches the prune.
-    Uint32 m_gcFrameCounter = 0;
     // Active only between BeginDrawSyncScope/EndDrawSyncScope; identities of
     // textures already fully synced in the current draw (small N -> flat scan).
     Bool m_drawSyncScopeActive = false;
@@ -786,105 +379,9 @@ private:
         TextureResource* resource = nullptr;
     };
     Vector<DrawSyncedTexture> m_drawSyncedThisDraw;
-    // Cross-draw sampled-texture memo: the same few textures (atlas, lightmap)
-    // are resolved on every draw, so cache their resource pointers and skip the
-    // alive/resource map lookups. Node-based std::unordered_map keeps the
-    // pointees stable across inserts; erases bump m_resourceEraseEpoch, which
-    // every memo entry must match. SyncTexture still runs on memo hits, so
-    // content/param freshness is unaffected. A dead-then-reused texture address
-    // cannot false-hit: the new object carries a new lifetime id.
-    struct SyncedTextureMemoEntry {
-        const MG_State::GLState::ITextureObject* texture = nullptr;
-        Uint64 lifetimeId = 0;
-        Uint64 eraseEpoch = 0;
-        TextureResource* resource = nullptr;
-    };
-    static constexpr Uint32 kSyncedTextureMemoSize = 8;
-    SyncedTextureMemoEntry m_syncedTextureMemo[kSyncedTextureMemoSize];
-    Uint32 m_syncedTextureMemoNext = 0;
-    Uint64 m_resourceEraseEpoch = 1;
-    // Formats whose mutable-image probe failed on this device; their images are created
-    // without MUTABLE_FORMAT_BIT so repeat syncs neither re-probe nor flag-mismatch.
-    std::unordered_set<VkFormat> m_mutableFormatUnsupported;
-    // Formats whose 3D images refused VK_IMAGE_CREATE_2D_ARRAY_COMPATIBLE_BIT. Per format+usage,
-    // exactly like the mutable-format verdict above, so it is answered at image creation and
-    // remembered rather than probed once globally.
-    std::unordered_set<VkFormat> m_2dArrayCompatibleUnsupported;
     std::unordered_map<TextureIdentity, WeakPtr<MG_State::GLState::ITextureObject>, TextureIdentityHash> m_aliveObjects;
     std::unordered_map<TextureIdentity, TextureResource, TextureIdentityHash> m_textureResources;
-    // Textures that have been bound to a GL image unit (see MarkStorageImageTexture).
-    std::unordered_set<TextureIdentity, TextureIdentityHash> m_storageImageTextures;
-    // Extra VkImageCreateFlags a GL texture view needs on the storage image it views, keyed by
-    // the STORAGE texture's identity. Requested lazily, exactly like STORAGE usage above and for
-    // the same reason: VK_IMAGE_CREATE_MUTABLE_FORMAT_BIT costs bandwidth compression on tilers
-    // (it is what VK_KHR_image_format_list exists to claw back), so setting it on every
-    // immutable-storage texture would tax every glTexStorage2D render target in a game for a
-    // feature almost none of them use. A SAME-format view - which is the common case, and the
-    // Better Clouds case - needs no flag at all and therefore costs nothing.
-    std::unordered_map<TextureIdentity, VkImageCreateFlags, TextureIdentityHash> m_viewRequestedImageFlags;
-    // Every VkFormat a GL texture view has asked to reinterpret this storage as. The narrowed
-    // VkImageFormatListCreateInfo the image is created with must name them: the list is a promise
-    // that NO other format will ever be viewed, and building a view outside it is
-    // VUID-VkImageViewCreateInfo-pNext-01585. Keyed, like the flags above, by the STORAGE texture.
-    std::unordered_map<TextureIdentity, std::unordered_set<VkFormat>, TextureIdentityHash> m_viewRequestedFormats;
-    // Supported multisample counts per format, so repeat texture syncs do not
-    // re-query vkGetPhysicalDeviceImageFormatProperties.
-    std::unordered_map<VkFormat, VkSampleCountFlags> m_multisampleCountsByFormat;
     Vector<Vector<TextureResource>> m_deferredReleases;
     Vector<Vector<VkImageView>> m_deferredViewReleases;
-
-    // --- Batched upload machinery ---
-    // Uploads within a frame are recorded into ONE shared command buffer and
-    // submitted with ONE vkQueueSubmit at FlushPendingUploads (the renderer
-    // flushes before every frame-command-buffer submit). Staging memory comes
-    // from a pool of persistently-mapped, reusable blocks instead of a
-    // vmaCreateBuffer per upload.
-    struct UploadStagingBlock {
-        VkBuffer buffer = VK_NULL_HANDLE;
-        VmaAllocation allocation = nullptr;
-        Uint8* mapped = nullptr; // persistently mapped for the block's lifetime
-        VkDeviceSize capacity = 0;
-        VkDeviceSize cursor = 0; // bump cursor while the block backs the open batch
-    };
-    // Opens the batch command buffer lazily (allocates/reuses + begins recording).
-    VkCommandBuffer EnsureUploadBatchOpen();
-    // Bump-allocates `size` staging bytes for the open batch, growing onto a
-    // new/pooled block when the current one cannot fit. Returns the write
-    // pointer; outBuffer/outBaseOffset locate the space for copy commands.
-    Uint8* AcquireUploadStagingSpace(VkDeviceSize size, VkBuffer& outBuffer, VkDeviceSize& outBaseOffset);
-    void RecycleUploadStagingBlock(UploadStagingBlock&& block);
-    // Drops a recorded-but-unsubmitted batch on the floor. Shutdown only: the
-    // device is being torn down, so the lost texel data is unobservable.
-    void DiscardPendingUploadBatch();
-    void DestroyUploadPools();
-
-    Vector<UploadStagingBlock> m_freeUploadStagingBlocks;
-    VkDeviceSize m_freeUploadStagingBytes = 0;
-    Vector<VkCommandBuffer> m_freeUploadCommandBuffers;
-    Vector<VkFence> m_freeUploadFences;
-    Bool m_uploadBatchOpen = false;
-    VkCommandBuffer m_uploadBatchCommandBuffer = VK_NULL_HANDLE;
-    // Blocks whose staging bytes the open batch's copies reference (last =
-    // the block the bump cursor is currently allocating from).
-    Vector<UploadStagingBlock> m_uploadBatchBlocks;
-    // Images the open batch writes; consulted for the rare re-upload-after-
-    // draw flush and by DeferResourceRelease (an unsubmitted command buffer
-    // referencing a deferred-released image would escape every fence-based
-    // destruction proof, so the batch is flushed before the image is parked).
-    Vector<VkImage> m_uploadBatchImages;
-    VkDeviceSize m_uploadBatchStagingBytes = 0;
-
-    // Texture uploads are submitted out-of-band but NOT waited on (waiting
-    // behind the queue serialized the CPU against the previous frame's GPU
-    // work every time an animated atlas re-uploaded). Each flushed batch's
-    // transients are parked here and RECYCLED (fence reset to the fence pool,
-    // command buffer reset to the CB pool, staging blocks back to the block
-    // pool) once the batch fence signals.
-    struct PendingUploadReclaim {
-        VkFence fence = VK_NULL_HANDLE;
-        VkCommandBuffer commandBuffer = VK_NULL_HANDLE;
-        Vector<UploadStagingBlock> stagingBlocks;
-    };
-    Vector<PendingUploadReclaim> m_pendingUploadReclaims;
 };
 } // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/VkTimerQueryManager.cpp

@@ -15,7 +15,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         MOBILEGL_ASSERT(initInfo.device != VK_NULL_HANDLE, "VkTimerQueryManager::Initialize requires valid VkDevice");
         MOBILEGL_ASSERT(initInfo.frameCount > 0, "VkTimerQueryManager::Initialize requires non-zero frame count");
         if (initInfo.timestampValidBits == 0 || initInfo.timestampPeriodNs <= 0.0f || initInfo.slotsPerPool == 0) {
-            MGLOG_W_ONCE("VkTimerQueryManager: timestamps unsupported (validBits=%u, period=%f, slots=%u)",
+            MGLOG_W("VkTimerQueryManager: timestamps unsupported (validBits=%u, period=%f, slots=%u)",
                     initInfo.timestampValidBits, initInfo.timestampPeriodNs, initInfo.slotsPerPool);
             return false;
         }
@@ -35,7 +35,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         for (auto& poolState : m_pools) {
             const VkResult result = vkCreateQueryPool(m_device, &poolInfo, nullptr, &poolState.pool);
             if (result != VK_SUCCESS) {
-                MGLOG_E_ONCE("VkTimerQueryManager: vkCreateQueryPool failed with %s", VkResultToString(result));
+                MGLOG_E("VkTimerQueryManager: vkCreateQueryPool failed with %s", VkResultToString(result));
                 Shutdown();
                 return false;
             }
@@ -90,7 +90,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
         auto& poolState = m_pools[frameIndex];
         if (poolState.cursor >= m_slotsPerPool) {
             if (!poolState.exhaustionWarned) {
-                MGLOG_W_ONCE("VkTimerQueryManager: frame %u timestamp pool exhausted (%u slots); further timer queries "
+                MGLOG_W("VkTimerQueryManager: frame %u timestamp pool exhausted (%u slots); further timer queries "
                         "this frame fall back to the frontend path",
                         frameIndex, m_slotsPerPool);
                 poolState.exhaustionWarned = true;
@@ -120,7 +120,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
             m_device, m_pools[record.poolIndex].pool, record.slot, 1, sizeof(resultWithAvailability),
             resultWithAvailability, sizeof(Uint64), VK_QUERY_RESULT_64_BIT | VK_QUERY_RESULT_WITH_AVAILABILITY_BIT);
         if (result != VK_SUCCESS && result != VK_NOT_READY) {
-            MGLOG_E_ONCE("VkTimerQueryManager: vkGetQueryPoolResults failed with %s", VkResultToString(result));
+            MGLOG_E("VkTimerQueryManager: vkGetQueryPoolResults failed with %s", VkResultToString(result));
             return false;
         }
         if (resultWithAvailability[1] == 0) {

MobileGL/MG_Backend/DirectVulkan/Renderer/WireColorBlit.frag

@@ -1,13 +0,0 @@
-#version 450
-layout(set = 0, binding = 0) uniform sampler2D sourceImage;
-layout(location = 0) in vec2 texCoord;
-layout(location = 0) out vec4 outColor;
-
-void main() {
-    // Source framebuffer clipping preserves the original scale, rather than
-    // extending the edge texels into pixels outside the source framebuffer.
-    if (any(lessThan(texCoord, vec2(0.0))) || any(greaterThan(texCoord, vec2(1.0)))) discard;
-    // Explicit LOD is required on Adreno 650: implicit LOD through a rotated
-    // single-mip UBWC render target can read outside its allocation.
-    outColor = textureLod(sourceImage, texCoord, 0.0);
-}

MobileGL/MG_Backend/DirectVulkan/Renderer/WireColorBlit.inc

@@ -1,407 +0,0 @@
-// Included by VulkanRenderer.cpp inside the backend namespace, after WireFramebuffer.inc.
-// The native blit owns no frontend object and never invokes the GL shader compiler.
-#if MOBILEGL_BUILD_DISAGGREGATED
-#include "WireColorBlitSpirv.h"
-
-    struct VulkanRenderer::WireColorBlitResources {
-        struct Target {
-            VkFormat format = VK_FORMAT_UNDEFINED;
-            VkImageLayout layout = VK_IMAGE_LAYOUT_UNDEFINED;
-            VkRenderPass renderPass = VK_NULL_HANDLE;
-            VkPipeline pipeline = VK_NULL_HANDLE;
-        };
-        VkShaderModule vertex = VK_NULL_HANDLE, fragment = VK_NULL_HANDLE;
-        VkDescriptorSetLayout descriptorLayout = VK_NULL_HANDLE;
-        VkPipelineLayout pipelineLayout = VK_NULL_HANDLE;
-        VkSampler nearest = VK_NULL_HANDLE, linear = VK_NULL_HANDLE;
-        Vector<Target> targets;
-    };
-
-    void VulkanRenderer::DestroyWireColorBlitResources() {
-        if (!m_wireColorBlitResources) return;
-        // Shutdown calls this after vkDeviceWaitIdle and after all per-submit
-        // descriptor pools/framebuffers/views have been collected.
-        auto& cache = *m_wireColorBlitResources;
-        for (const auto& target : cache.targets) {
-            vkDestroyPipeline(m_device, target.pipeline, nullptr);
-            vkDestroyRenderPass(m_device, target.renderPass, nullptr);
-        }
-        vkDestroySampler(m_device, cache.nearest, nullptr);
-        vkDestroySampler(m_device, cache.linear, nullptr);
-        vkDestroyPipelineLayout(m_device, cache.pipelineLayout, nullptr);
-        vkDestroyDescriptorSetLayout(m_device, cache.descriptorLayout, nullptr);
-        vkDestroyShaderModule(m_device, cache.vertex, nullptr);
-        vkDestroyShaderModule(m_device, cache.fragment, nullptr);
-        delete m_wireColorBlitResources;
-        m_wireColorBlitResources = nullptr;
-    }
-
-    Bool VulkanRenderer::BlitWireColorToDefault(WireImage source, WireImage destination,
-        GLint sx0, GLint sy0, GLint sx1, GLint sy1,
-        GLint dx0, GLint dy0, GLint dx1, GLint dy1, GLenum filter) {
-        if (!destination.isDefault) return false;
-        return BlitWireColorImage(source, destination, sx0, sy0, sx1, sy1, dx0, dy0, dx1, dy1, filter, false);
-    }
-
-    // P7 wave 2-B (CONTRACT-P7 §3.2, `default-color-blit-shape`). The shader blit below can only
-    // SAMPLE its source: sampler2D, a float result, and one of two 2D view types. A framebuffer
-    // whose colour attachment is RGBA8UI, or a layer of a 3D texture, is none of those, and on a
-    // rotated Android surface there is no other arm - an axis-aligned vkCmdBlitImage cannot
-    // express a quarter turn. So the source region becomes an owned 2D image first, through
-    // vkCmdCopyImage, which cares about the texel BLOCK SIZE and not about how the block is
-    // interpreted; the scratch then takes the shader blit as an ordinary 2D float source.
-    //
-    // REINTERPRETATION IS THE POINT FOR THE INTEGER CASE, and GL agrees: glBlitFramebuffer
-    // between an integer and a normalized format is INVALID_OPERATION (GL 4.6 core 18.3.1), so
-    // there is no defined result to be wrong about - only a shape that used to end the session
-    // and now produces the source's bits. For a float source of the wrong VIEW TYPE the copy is
-    // a plain slice extraction and the result is exactly right.
-    Bool VulkanRenderer::BlitWireColorToDefaultThroughScratch(WireImage source, WireImage destination,
-        GLint sx0, GLint sy0, GLint sx1, GLint sy1,
-        GLint dx0, GLint dy0, GLint dx1, GLint dy1, GLenum filter) {
-        if (!destination.isDefault || source.isDefault) return false;
-        if (source.samples != VK_SAMPLE_COUNT_1_BIT || destination.samples != VK_SAMPLE_COUNT_1_BIT)
-            return false;
-        if (!source.image || !destination.image || source.image == destination.image) return false;
-        const Int64 width = std::abs(static_cast<Int64>(sx1) - sx0);
-        const Int64 height = std::abs(static_cast<Int64>(sy1) - sy0);
-        if (!width || !height || dx0 == dx1 || dy0 == dy1) return true;
-        if (std::min(sx0, sx1) < 0 || std::min(sy0, sy1) < 0 ||
-            static_cast<Uint64>(std::max(sx0, sx1)) > source.extent.width ||
-            static_cast<Uint64>(std::max(sy0, sy1)) > source.extent.height) return false;
-        // A compressed source cannot be a colour attachment, so it cannot be a framebuffer blit's
-        // source either - but the block arithmetic below would silently produce nonsense for one,
-        // and "cannot happen" is the reason the guards this package retires were written as
-        // asserts. The size-compatibility classes are Vulkan's own (VkFormat texel block size);
-        // the destination format is whatever the swapchain uses and is always sampled-float.
-        if (vkuFormatIsCompressed(source.format)) return false;
-        VkFormat scratchFormat = VK_FORMAT_UNDEFINED;
-        switch (vkuFormatTexelBlockSize(source.format)) {
-        case 1: scratchFormat = VK_FORMAT_R8_UNORM; break;
-        case 2: scratchFormat = VK_FORMAT_R8G8_UNORM; break;
-        case 4: scratchFormat = VK_FORMAT_R8G8B8A8_UNORM; break;
-        case 8: scratchFormat = VK_FORMAT_R16G16B16A16_SFLOAT; break;
-        case 16: scratchFormat = VK_FORMAT_R32G32B32A32_SFLOAT; break;
-        default: return false;
-        }
-        VkFormatProperties scratchProperties{};
-        vkGetPhysicalDeviceFormatProperties(m_physicalDevice.handle, scratchFormat, &scratchProperties);
-        const VkFormatFeatureFlags scratchRequired = VK_FORMAT_FEATURE_SAMPLED_IMAGE_BIT |
-            (filter == GL_LINEAR ? VK_FORMAT_FEATURE_SAMPLED_IMAGE_FILTER_LINEAR_BIT : 0);
-        if ((scratchProperties.optimalTilingFeatures & scratchRequired) != scratchRequired) return false;
-
-        auto scratch = MakeUnique<VkTextureManager::TextureResource>();
-        VkImageCreateInfo info{VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO};
-        info.imageType = VK_IMAGE_TYPE_2D;
-        info.format = scratchFormat;
-        info.extent = {static_cast<Uint32>(width), static_cast<Uint32>(height), 1};
-        info.mipLevels = info.arrayLayers = 1;
-        info.samples = VK_SAMPLE_COUNT_1_BIT;
-        info.tiling = VK_IMAGE_TILING_OPTIMAL;
-        info.usage = VK_IMAGE_USAGE_TRANSFER_DST_BIT | VK_IMAGE_USAGE_SAMPLED_BIT;
-        info.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
-        VmaAllocationCreateInfo allocation{};
-        allocation.usage = VMA_MEMORY_USAGE_AUTO_PREFER_DEVICE;
-        allocation.requiredFlags = VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT;
-        if (vmaCreateImage(m_allocator, &info, &allocation, &scratch->image, &scratch->allocation,
-                           nullptr) != VK_SUCCESS)
-            return false;
-        scratch->format = scratchFormat;
-        scratch->extent = {info.extent.width, info.extent.height};
-        scratch->mipLevels = scratch->arrayLayers = scratch->depth = 1;
-        scratch->aspect = VK_IMAGE_ASPECT_COLOR_BIT;
-        WireImage staged{};
-        staged.image = scratch->image;
-        staged.format = scratchFormat;
-        staged.aspect = VK_IMAGE_ASPECT_COLOR_BIT;
-        staged.extent = scratch->extent;
-        staged.trackedLayout = &scratch->layout;
-
-        m_textureManager->FlushPendingUploads();
-        TransitionWireImage(source, VK_IMAGE_LAYOUT_TRANSFER_SRC_OPTIMAL);
-        TransitionWireImage(staged, VK_IMAGE_LAYOUT_TRANSFER_DST_OPTIMAL);
-        VkImageCopy copy{};
-        // A 3D source carries its slice on z and always names layer 0; every other source
-        // carries it on the layer axis, which is the same split ResolveWireImage records.
-        copy.srcSubresource = {VK_IMAGE_ASPECT_COLOR_BIT, source.level, source.is3D ? 0u : source.layer, 1};
-        copy.srcOffset = {std::min(sx0, sx1), std::min(sy0, sy1),
-                          source.is3D ? static_cast<Int32>(source.layer) : 0};
-        copy.dstSubresource = {VK_IMAGE_ASPECT_COLOR_BIT, 0, 0, 1};
-        copy.dstOffset = {0, 0, 0};
-        copy.extent = {static_cast<Uint32>(width), static_cast<Uint32>(height), 1};
-        vkCmdCopyImage(m_frameContext.GetCurrent().commandBuffer, source.image,
-                       VK_IMAGE_LAYOUT_TRANSFER_SRC_OPTIMAL, staged.image,
-                       VK_IMAGE_LAYOUT_TRANSFER_DST_OPTIMAL, 1, &copy);
-        staged.layout = scratch->layout;
-        // The scratch holds the region at its own origin, so a reversed source rectangle
-        // becomes a reversed rectangle OVER THE SCRATCH - the multisample resolve arm's shape.
-        const GLint rx0 = sx1 > sx0 ? 0 : static_cast<GLint>(width);
-        const GLint rx1 = sx1 > sx0 ? static_cast<GLint>(width) : 0;
-        const GLint ry0 = sy1 > sy0 ? 0 : static_cast<GLint>(height);
-        const GLint ry1 = sy1 > sy0 ? static_cast<GLint>(height) : 0;
-        const Bool blitted = BlitWireColorImage(staged, destination, rx0, ry0, rx1, ry1,
-                                                dx0, dy0, dx1, dy1, filter, false);
-        // Retired whether or not the blit took: the copy above is already recorded against this
-        // image, so the submission that consumes it owns the storage either way.
-        WireRetiredObjects retired{};
-        retired.textures.push_back(Move(scratch));
-        RetireWireObjects(Move(retired));
-        return blitted;
-    }
-
-    Bool VulkanRenderer::BlitWireColorImage(WireImage source, WireImage destination,
-        GLint sx0, GLint sy0, GLint sx1, GLint sy1,
-        GLint dx0, GLint dy0, GLint dx1, GLint dy1, GLenum filter, Bool mipmap) {
-        const Bool sameImage = source.image == destination.image;
-        if (source.isDefault || (sameImage && source.level == destination.level && source.layer == destination.layer) ||
-            source.samples != VK_SAMPLE_COUNT_1_BIT || destination.samples != VK_SAMPLE_COUNT_1_BIT ||
-            source.is3D || destination.is3D || (source.viewType != VK_IMAGE_VIEW_TYPE_2D &&
-                            source.viewType != VK_IMAGE_VIEW_TYPE_2D_ARRAY) ||
-            (destination.viewType != VK_IMAGE_VIEW_TYPE_2D && destination.viewType != VK_IMAGE_VIEW_TYPE_2D_ARRAY) ||
-            !vkuFormatIsSampledFloat(source.format)) return false;
-        if (sx0 == sx1 || sy0 == sy1 || dx0 == dx1 || dy0 == dy1) return true;
-        if (!source.extent.width || !source.extent.height ||
-            !destination.extent.width || !destination.extent.height) return false;
-        const auto transform = destination.isDefault ? m_swapchainObject.GetPreTransform() :
-                                                       VK_SURFACE_TRANSFORM_IDENTITY_BIT_KHR;
-        if (transform != VK_SURFACE_TRANSFORM_IDENTITY_BIT_KHR &&
-            transform != VK_SURFACE_TRANSFORM_ROTATE_90_BIT_KHR &&
-            transform != VK_SURFACE_TRANSFORM_ROTATE_180_BIT_KHR &&
-            transform != VK_SURFACE_TRANSFORM_ROTATE_270_BIT_KHR) return false;
-        VkFormatProperties sourceProperties{};
-        vkGetPhysicalDeviceFormatProperties(m_physicalDevice.handle, source.format, &sourceProperties);
-        const VkFormatFeatureFlags required = VK_FORMAT_FEATURE_SAMPLED_IMAGE_BIT |
-            (filter == GL_LINEAR ? VK_FORMAT_FEATURE_SAMPLED_IMAGE_FILTER_LINEAR_BIT : 0);
-        if ((sourceProperties.optimalTilingFeatures & required) != required) return false;
-        // Mip generation samples and writes the texture's own color space;
-        // GL_FRAMEBUFFER_SRGB only controls framebuffer operations.
-        if (!mipmap) destination.format = ResolveSrgbAttachmentWriteFormat(destination.format,
-            MGB_CTX->IsCapabilityEnabled(CapabilityInput::FramebufferSrgb));
-        VkFormatProperties destinationProperties{};
-        vkGetPhysicalDeviceFormatProperties(m_physicalDevice.handle, destination.format, &destinationProperties);
-        if (!(destinationProperties.optimalTilingFeatures & VK_FORMAT_FEATURE_COLOR_ATTACHMENT_BIT)) return false;
-        const VkImageLayout sourceLayout = sameImage ? VK_IMAGE_LAYOUT_GENERAL : VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL;
-        const VkImageLayout destinationLayout = sameImage ? VK_IMAGE_LAYOUT_GENERAL : VK_IMAGE_LAYOUT_COLOR_ATTACHMENT_OPTIMAL;
-
-        struct Constants {
-            float srcRect[4];
-            float dstRect[4];
-            Int32 surfaceTransform;
-        };
-        static_assert(sizeof(Constants) == 36);
-        if (!m_wireColorBlitResources) {
-            m_wireColorBlitResources = new WireColorBlitResources;
-            auto& cache = *m_wireColorBlitResources;
-            const auto shader = [&](const Uint32* code, SizeT bytes, VkShaderModule& module) {
-                VkShaderModuleCreateInfo info{VK_STRUCTURE_TYPE_SHADER_MODULE_CREATE_INFO};
-                info.codeSize = bytes;
-                info.pCode = code;
-                VK_VERIFY(vkCreateShaderModule(m_device, &info, nullptr, &module));
-            };
-            shader(kWireColorBlitVertexSpirv, sizeof(kWireColorBlitVertexSpirv), cache.vertex);
-            shader(kWireColorBlitFragmentSpirv, sizeof(kWireColorBlitFragmentSpirv), cache.fragment);
-            const VkDescriptorSetLayoutBinding binding{0, VK_DESCRIPTOR_TYPE_COMBINED_IMAGE_SAMPLER,
-                                                       1, VK_SHADER_STAGE_FRAGMENT_BIT, nullptr};
-            VkDescriptorSetLayoutCreateInfo layout{VK_STRUCTURE_TYPE_DESCRIPTOR_SET_LAYOUT_CREATE_INFO};
-            layout.bindingCount = 1;
-            layout.pBindings = &binding;
-            VK_VERIFY(vkCreateDescriptorSetLayout(m_device, &layout, nullptr, &cache.descriptorLayout));
-            const VkPushConstantRange push{VK_SHADER_STAGE_VERTEX_BIT, 0, sizeof(Constants)};
-            VkPipelineLayoutCreateInfo pipelineLayout{VK_STRUCTURE_TYPE_PIPELINE_LAYOUT_CREATE_INFO};
-            pipelineLayout.setLayoutCount = 1;
-            pipelineLayout.pSetLayouts = &cache.descriptorLayout;
-            pipelineLayout.pushConstantRangeCount = 1;
-            pipelineLayout.pPushConstantRanges = &push;
-            VK_VERIFY(vkCreatePipelineLayout(m_device, &pipelineLayout, nullptr, &cache.pipelineLayout));
-            VkSamplerCreateInfo sampler{VK_STRUCTURE_TYPE_SAMPLER_CREATE_INFO};
-            sampler.mipmapMode = VK_SAMPLER_MIPMAP_MODE_NEAREST;
-            sampler.addressModeU = sampler.addressModeV = sampler.addressModeW = VK_SAMPLER_ADDRESS_MODE_CLAMP_TO_EDGE;
-            sampler.magFilter = sampler.minFilter = VK_FILTER_NEAREST;
-            sampler.maxLod = 0.0f;
-            VK_VERIFY(vkCreateSampler(m_device, &sampler, nullptr, &cache.nearest));
-            sampler.magFilter = sampler.minFilter = VK_FILTER_LINEAR;
-            VK_VERIFY(vkCreateSampler(m_device, &sampler, nullptr, &cache.linear));
-        }
-        auto& cache = *m_wireColorBlitResources;
-        WireColorBlitResources::Target* target = nullptr;
-        for (auto& entry : cache.targets) {
-            if (entry.format == destination.format && entry.layout == destinationLayout) { target = &entry; break; }
-        }
-        if (!target) {
-            cache.targets.emplace_back();
-            target = &cache.targets.back();
-            target->format = destination.format;
-            target->layout = destinationLayout;
-            VkAttachmentDescription attachment{};
-            attachment.format = destination.format;
-            attachment.samples = VK_SAMPLE_COUNT_1_BIT;
-            attachment.loadOp = VK_ATTACHMENT_LOAD_OP_LOAD;
-            attachment.storeOp = VK_ATTACHMENT_STORE_OP_STORE;
-            attachment.stencilLoadOp = VK_ATTACHMENT_LOAD_OP_DONT_CARE;
-            attachment.stencilStoreOp = VK_ATTACHMENT_STORE_OP_DONT_CARE;
-            attachment.initialLayout = attachment.finalLayout = destinationLayout;
-            const VkAttachmentReference color{0, destinationLayout};
-            VkSubpassDescription subpass{};
-            subpass.pipelineBindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS;
-            subpass.colorAttachmentCount = 1;
-            subpass.pColorAttachments = &color;
-            VkRenderPassCreateInfo pass{VK_STRUCTURE_TYPE_RENDER_PASS_CREATE_INFO};
-            pass.attachmentCount = 1;
-            pass.pAttachments = &attachment;
-            pass.subpassCount = 1;
-            pass.pSubpasses = &subpass;
-            VK_VERIFY(vkCreateRenderPass(m_device, &pass, nullptr, &target->renderPass));
-            VkPipelineShaderStageCreateInfo stages[2]{};
-            for (auto& stage : stages) {
-                stage.sType = VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_CREATE_INFO;
-                stage.pName = "main";
-            }
-            stages[0].stage = VK_SHADER_STAGE_VERTEX_BIT;
-            stages[0].module = cache.vertex;
-            stages[1].stage = VK_SHADER_STAGE_FRAGMENT_BIT;
-            stages[1].module = cache.fragment;
-            const VkPipelineVertexInputStateCreateInfo vertex{VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_STATE_CREATE_INFO};
-            VkPipelineInputAssemblyStateCreateInfo assembly{VK_STRUCTURE_TYPE_PIPELINE_INPUT_ASSEMBLY_STATE_CREATE_INFO};
-            assembly.topology = VK_PRIMITIVE_TOPOLOGY_TRIANGLE_LIST;
-            VkPipelineViewportStateCreateInfo viewport{VK_STRUCTURE_TYPE_PIPELINE_VIEWPORT_STATE_CREATE_INFO};
-            viewport.viewportCount = viewport.scissorCount = 1;
-            VkPipelineRasterizationStateCreateInfo raster{VK_STRUCTURE_TYPE_PIPELINE_RASTERIZATION_STATE_CREATE_INFO};
-            raster.polygonMode = VK_POLYGON_MODE_FILL;
-            raster.cullMode = VK_CULL_MODE_NONE;
-            raster.frontFace = VK_FRONT_FACE_COUNTER_CLOCKWISE;
-            raster.lineWidth = 1.0f;
-            VkPipelineMultisampleStateCreateInfo samples{VK_STRUCTURE_TYPE_PIPELINE_MULTISAMPLE_STATE_CREATE_INFO};
-            samples.rasterizationSamples = VK_SAMPLE_COUNT_1_BIT;
-            VkPipelineColorBlendAttachmentState colorMask{};
-            colorMask.colorWriteMask = VK_COLOR_COMPONENT_R_BIT | VK_COLOR_COMPONENT_G_BIT |
-                                       VK_COLOR_COMPONENT_B_BIT | VK_COLOR_COMPONENT_A_BIT;
-            VkPipelineColorBlendStateCreateInfo blend{VK_STRUCTURE_TYPE_PIPELINE_COLOR_BLEND_STATE_CREATE_INFO};
-            blend.attachmentCount = 1;
-            blend.pAttachments = &colorMask;
-            const VkDynamicState dynamicStates[]{VK_DYNAMIC_STATE_VIEWPORT, VK_DYNAMIC_STATE_SCISSOR};
-            VkPipelineDynamicStateCreateInfo dynamic{VK_STRUCTURE_TYPE_PIPELINE_DYNAMIC_STATE_CREATE_INFO};
-            dynamic.dynamicStateCount = 2;
-            dynamic.pDynamicStates = dynamicStates;
-            VkGraphicsPipelineCreateInfo pipeline{VK_STRUCTURE_TYPE_GRAPHICS_PIPELINE_CREATE_INFO};
-            pipeline.stageCount = 2;
-            pipeline.pStages = stages;
-            pipeline.pVertexInputState = &vertex;
-            pipeline.pInputAssemblyState = &assembly;
-            pipeline.pViewportState = &viewport;
-            pipeline.pRasterizationState = &raster;
-            pipeline.pMultisampleState = &samples;
-            pipeline.pColorBlendState = &blend;
-            pipeline.pDynamicState = &dynamic;
-            pipeline.layout = cache.pipelineLayout;
-            pipeline.renderPass = target->renderPass;
-            VK_VERIFY(vkCreateGraphicsPipelines(m_device, VK_NULL_HANDLE, 1, &pipeline, nullptr, &target->pipeline));
-        }
-
-        m_textureManager->FlushPendingUploads();
-        // Distinct mip/layer views of the same image are legal shader input and
-        // output. GENERAL keeps the whole-image layout tracker truthful; the
-        // transition also orders the previous mip's attachment write.
-        TransitionWireImage(source, sourceLayout);
-        if (sameImage) destination.layout = source.layout;
-        else TransitionWireImage(destination, destinationLayout);
-        const auto makeView = [&](const WireImage& image) {
-            VkImageViewCreateInfo view{VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO};
-            view.image = image.image;
-            view.viewType = VK_IMAGE_VIEW_TYPE_2D;
-            view.format = image.format;
-            // A layered framebuffer blit reads its first layer, as the native path does.
-            view.subresourceRange = {VK_IMAGE_ASPECT_COLOR_BIT, image.level, 1, image.layer, 1};
-            VkImageView handle = VK_NULL_HANDLE;
-            VK_VERIFY(vkCreateImageView(m_device, &view, nullptr, &handle));
-            return handle;
-        };
-        const VkImageView sourceView = makeView(source), destinationView = makeView(destination);
-        VkFramebufferCreateInfo framebufferInfo{VK_STRUCTURE_TYPE_FRAMEBUFFER_CREATE_INFO};
-        framebufferInfo.renderPass = target->renderPass;
-        framebufferInfo.attachmentCount = 1;
-        framebufferInfo.pAttachments = &destinationView;
-        framebufferInfo.width = destination.extent.width;
-        framebufferInfo.height = destination.extent.height;
-        framebufferInfo.layers = 1;
-        VkFramebuffer framebuffer = VK_NULL_HANDLE;
-        VK_VERIFY(vkCreateFramebuffer(m_device, &framebufferInfo, nullptr, &framebuffer));
-        // Each in-flight blit owns its descriptor set. Updating a cached set
-        // would rewrite the source view of an older queued blit.
-        VkDescriptorPool descriptorPool = VK_NULL_HANDLE;
-        VkDescriptorSet descriptorSet = VK_NULL_HANDLE;
-        const VkDescriptorPoolSize poolSize{VK_DESCRIPTOR_TYPE_COMBINED_IMAGE_SAMPLER, 1};
-        VkDescriptorPoolCreateInfo pool{VK_STRUCTURE_TYPE_DESCRIPTOR_POOL_CREATE_INFO};
-        pool.maxSets = 1;
-        pool.poolSizeCount = 1;
-        pool.pPoolSizes = &poolSize;
-        VK_VERIFY(vkCreateDescriptorPool(m_device, &pool, nullptr, &descriptorPool));
-        VkDescriptorSetAllocateInfo alloc{VK_STRUCTURE_TYPE_DESCRIPTOR_SET_ALLOCATE_INFO};
-        alloc.descriptorPool = descriptorPool;
-        alloc.descriptorSetCount = 1;
-        alloc.pSetLayouts = &cache.descriptorLayout;
-        VK_VERIFY(vkAllocateDescriptorSets(m_device, &alloc, &descriptorSet));
-        // GL_LINEAR filters only a STRETCHED blit; an unscaled one (mirrored or not, on any of the
-        // four transforms) is a copy and samples NEAREST, which is exact where linear filtering
-        // at a quantised coordinate is not (WireColorBlitFilter.h). The format check above still
-        // asks for SAMPLED_IMAGE_FILTER_LINEAR whenever GL said GL_LINEAR, so which blits reach
-        // this pass is unchanged.
-        const VkFilter samplerFilter = WireColorBlitFilterFor({sx0, sy0, sx1, sy1}, {dx0, dy0, dx1, dy1},
-                                                              filter, transform);
-        const VkDescriptorImageInfo sampled{samplerFilter == VK_FILTER_LINEAR ? cache.linear : cache.nearest,
-                                           sourceView, sourceLayout};
-        VkWriteDescriptorSet write{VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET};
-        write.dstSet = descriptorSet;
-        write.dstBinding = 0;
-        write.descriptorCount = 1;
-        write.descriptorType = VK_DESCRIPTOR_TYPE_COMBINED_IMAGE_SAMPLER;
-        write.pImageInfo = &sampled;
-        vkUpdateDescriptorSets(m_device, 1, &write, 0, nullptr);
-
-        const float sw = static_cast<float>(source.extent.width), sh = static_cast<float>(source.extent.height);
-        const Bool quarterTurn = transform == VK_SURFACE_TRANSFORM_ROTATE_90_BIT_KHR ||
-                                 transform == VK_SURFACE_TRANSFORM_ROTATE_270_BIT_KHR;
-        const float dw = static_cast<float>(quarterTurn ? destination.extent.height : destination.extent.width);
-        const float dh = static_cast<float>(quarterTurn ? destination.extent.width : destination.extent.height);
-        // The shared vertex shader flips window Y. Offscreen images keep the
-        // source row order, so undo that flip in the destination rectangle.
-        if (!destination.isDefault) {
-            dy0 = static_cast<GLint>(destination.extent.height) - dy0;
-            dy1 = static_cast<GLint>(destination.extent.height) - dy1;
-        }
-        const Constants constants{{sx0 / sw, sy0 / sh, (static_cast<float>(sx1) - sx0) / sw,
-                                    (static_cast<float>(sy1) - sy0) / sh},
-                                  {dx0 / dw, dy0 / dh, (static_cast<float>(dx1) - dx0) / dw,
-                                    (static_cast<float>(dy1) - dy0) / dh},
-                                  static_cast<Int32>(ToBlitSurfaceTransform(transform))};
-        auto& frame = m_frameContext.GetCurrent();
-        VkRenderPassBeginInfo begin{VK_STRUCTURE_TYPE_RENDER_PASS_BEGIN_INFO};
-        begin.renderPass = target->renderPass;
-        begin.framebuffer = framebuffer;
-        begin.renderArea = {{0, 0}, destination.extent};
-        vkCmdBeginRenderPass(frame.commandBuffer, &begin, VK_SUBPASS_CONTENTS_INLINE);
-        vkCmdBindPipeline(frame.commandBuffer, VK_PIPELINE_BIND_POINT_GRAPHICS, target->pipeline);
-        const VkViewport viewport{0.0f, 0.0f, static_cast<float>(destination.extent.width),
-                                  static_cast<float>(destination.extent.height), 0.0f, 1.0f};
-        const VkRect2D scissor{{0, 0}, destination.extent};
-        vkCmdSetViewport(frame.commandBuffer, 0, 1, &viewport);
-        vkCmdSetScissor(frame.commandBuffer, 0, 1, &scissor);
-        vkCmdBindDescriptorSets(frame.commandBuffer, VK_PIPELINE_BIND_POINT_GRAPHICS,
-                                cache.pipelineLayout, 0, 1, &descriptorSet, 0, nullptr);
-        vkCmdPushConstants(frame.commandBuffer, cache.pipelineLayout, VK_SHADER_STAGE_VERTEX_BIT,
-                           0, sizeof(constants), &constants);
-        vkCmdDraw(frame.commandBuffer, 6, 1, 0, 0);
-        vkCmdEndRenderPass(frame.commandBuffer);
-        ResetDynamicStateShadow();
-        InvalidatePipelineMemo();
-        // This native pass binds its own set/layout without going through the
-        // application's descriptor binder. Its next fast path must rebind.
-        if (m_uniformManager) m_uniformManager->OnCommandBufferBoundary();
-        WireRetiredObjects retired{};
-        retired.framebuffers.push_back(framebuffer);
-        retired.imageViews = {sourceView, destinationView};
-        retired.descriptorPools.push_back(descriptorPool);
-        RetireWireObjects(Move(retired));
-        if (destination.isDefault) m_swapchainObject.SetImageContentDefined(destination.swapchainImageIndex, true);
-        return true;
-    }
-#endif

MobileGL/MG_Backend/DirectVulkan/Renderer/WireColorBlit.vert

@@ -1,25 +0,0 @@
-#version 450
-// Native Vulkan blit: no GL program, registry entry, or runtime transpilation.
-layout(push_constant) uniform BlitRect {
-    vec4 srcRect;
-    vec4 dstRect;
-    int surfaceTransform;
-} rect;
-layout(location = 0) out vec2 texCoord;
-
-void main() {
-    // A quad, rather than an oversized triangle, also clips partial blits to
-    // their destination rectangle. The Vulkan viewport covers the native image.
-    const vec2 corners[6] = vec2[](
-        vec2(0.0, 0.0), vec2(1.0, 0.0), vec2(0.0, 1.0),
-        vec2(0.0, 1.0), vec2(1.0, 0.0), vec2(1.0, 1.0));
-    vec2 uv = corners[gl_VertexIndex];
-    vec2 p = (rect.dstRect.xy + uv * rect.dstRect.zw) * 2.0 - 1.0;
-    // Same GL-bottom-left to native-image mapping as the monolithic blit.
-    p.y = -p.y;
-    if (rect.surfaceTransform == 1) p = vec2(-p.y, p.x);
-    else if (rect.surfaceTransform == 2) p = -p;
-    else if (rect.surfaceTransform == 3) p = vec2(p.y, -p.x);
-    gl_Position = vec4(p, 0.0, 1.0);
-    texCoord = rect.srcRect.xy + uv * rect.srcRect.zw;
-}

MobileGL/MG_Backend/DirectVulkan/Renderer/WireColorBlitFilter.h

@@ -1,66 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/WireColorBlitFilter.h
-// Copyright (c) 2025-2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-#pragma once
-
-#include <Includes.h>
-#include "../VkIncludes.h"
-
-// P7 g3-blit (g3det, gate 3): WHICH SAMPLER THE WIRE ARM'S SHADER COLOUR BLIT READS ITS SOURCE
-// THROUGH.
-//
-// GL applies a blit's `filter` only where the image is STRETCHED (GL 4.6 core 18.3.1). A blit whose
-// source and destination rectangles are the same size is a copy, whatever `filter` says, and so is
-// a mirrored one. The wire arm's shader blit (WireColorBlit.inc, BlitWireColorImage) draws a quad
-// and samples `textureLod(sourceImage, texCoord, 0)` at interpolated coordinates, and it used the
-// LINEAR sampler for every GL_LINEAR blit. At 1:1 every fragment centre maps to a texel centre, so
-// in exact arithmetic linear filtering reads the same single texel. Adreno 830 quantises the
-// coordinate to sub-texel precision: a fragment that lands a fraction off the centre blends in a
-// small weight of a neighbour. minecraft-1.21.1-neoforge-create-instancing-in-world ends with a
-// 1:1 GL_LINEAR glBlitFramebuffer into FB 0, and on the wire arm 712 high-contrast pixels moved by
-// 1 LSB toward a neighbour. The monolith's vkCmdBlitImage copied them exactly
-// (~/w7/logs/g3det/VERDICT.md section 3). NEAREST within half a texel of the centre is exact, so an
-// unscaled blit takes NEAREST. Lavapipe samples texel centres exactly, so no host picture can see
-// the difference; this pure half is what the unit test pins
-// (MG_Test/Pipeline/PipelineQuirkTest.cpp, WireColorBlitSamples*).
-//
-// THE SURFACE TRANSFORM DOES NOT TURN A COPY INTO A STRETCH. BlitWireColorImage applies the
-// quarter and half turns in NDC, over a viewport of the native image, and for a quarter turn it
-// takes the logical extent as the native extent swapped. A native pixel then has exactly the pitch
-// of a logical one, and the rotation maps pixel centres onto pixel centres. So the scale test is on
-// GL's own (logical) rectangles for identity and all three rotations. BlitWireColorImage declines
-// any other transform before it chooses a sampler; for one, this answers with the filter's own
-// mapping, as before this package.
-#if MOBILEGL_BUILD_DISAGGREGATED
-namespace MobileGL::MG_Backend::DirectVulkan {
-    // A glBlitFramebuffer rectangle as GL names it: two corners, either order.
-    struct WireBlitRect {
-        GLint x0 = 0, y0 = 0, x1 = 0, y1 = 0;
-    };
-
-    // Same extent on both axes, orientation aside. The extents are taken in 64 bits: GL accepts any
-    // GLint corner, and INT_MAX - INT_MIN does not fit in one.
-    inline Bool WireBlitIsUnscaled(const WireBlitRect& source, const WireBlitRect& destination) {
-        const auto extent = [](GLint a, GLint b) {
-            return std::abs(static_cast<Int64>(b) - static_cast<Int64>(a));
-        };
-        return extent(source.x0, source.x1) == extent(destination.x0, destination.x1) &&
-               extent(source.y0, source.y1) == extent(destination.y0, destination.y1);
-    }
-
-    inline VkFilter WireColorBlitFilterFor(const WireBlitRect& source, const WireBlitRect& destination,
-                                           GLenum filter, VkSurfaceTransformFlagBitsKHR transform) {
-        if (filter != GL_LINEAR) return VK_FILTER_NEAREST;
-        const Bool expressed = transform == VK_SURFACE_TRANSFORM_IDENTITY_BIT_KHR ||
-                               transform == VK_SURFACE_TRANSFORM_ROTATE_90_BIT_KHR ||
-                               transform == VK_SURFACE_TRANSFORM_ROTATE_180_BIT_KHR ||
-                               transform == VK_SURFACE_TRANSFORM_ROTATE_270_BIT_KHR;
-        if (expressed && WireBlitIsUnscaled(source, destination)) return VK_FILTER_NEAREST;
-        return VK_FILTER_LINEAR;
-    }
-} // namespace MobileGL::MG_Backend::DirectVulkan
-#endif

MobileGL/MG_Backend/DirectVulkan/Renderer/WireColorBlitSpirv.h

@@ -1,132 +0,0 @@
-// Generated from WireColorBlit.vert / WireColorBlit.frag (Vulkan 1.0 / SPIR-V 1.0) by
-// scripts/bake_internal_shaders.py, which runs MG_Test's BakedInternalShadersTest with the
-// IN-TREE glslang and splices the words it emits into the arrays below. Do not edit the words
-// by hand: MOBILEGL_BAKED_INTERNAL_SHADERS (the same test, run as a gate) recompiles every
-// source in its table and reds on the first word that disagrees.
-//
-// These words were hand-run through glslangValidator before that gate existed, and the gate
-// reproduces them exactly - which is the one thing nobody could have known beforehand.
-#pragma once
-
-static constexpr Uint32 kWireColorBlitVertexSpirv[] = {
-    0x07230203u, 0x00010000u, 0x0008000bu, 0x00000070u, 0x00000000u, 0x00020011u, 0x00000001u, 0x0006000bu,
-    0x00000001u, 0x4c534c47u, 0x6474732eu, 0x3035342eu, 0x00000000u, 0x0003000eu, 0x00000000u, 0x00000001u,
-    0x0008000fu, 0x00000000u, 0x00000004u, 0x6e69616du, 0x00000000u, 0x00000016u, 0x0000005du, 0x00000066u,
-    0x00030003u, 0x00000002u, 0x000001c2u, 0x00040005u, 0x00000004u, 0x6e69616du, 0x00000000u, 0x00030005u,
-    0x00000009u, 0x00007675u, 0x00060005u, 0x00000016u, 0x565f6c67u, 0x65747265u, 0x646e4978u, 0x00007865u,
-    0x00050005u, 0x00000019u, 0x65646e69u, 0x6c626178u, 0x00000065u, 0x00030005u, 0x0000001cu, 0x00000070u,
-    0x00050005u, 0x0000001eu, 0x74696c42u, 0x74636552u, 0x00000000u, 0x00050006u, 0x0000001eu, 0x00000000u,
-    0x52637273u, 0x00746365u, 0x00050006u, 0x0000001eu, 0x00000001u, 0x52747364u, 0x00746365u, 0x00080006u,
-    0x0000001eu, 0x00000002u, 0x66727573u, 0x54656361u, 0x736e6172u, 0x6d726f66u, 0x00000000u, 0x00040005u,
-    0x00000020u, 0x74636572u, 0x00000000u, 0x00060005u, 0x0000005bu, 0x505f6c67u, 0x65567265u, 0x78657472u,
-    0x00000000u, 0x00060006u, 0x0000005bu, 0x00000000u, 0x505f6c67u, 0x7469736fu, 0x006e6f69u, 0x00070006u,
-    0x0000005bu, 0x00000001u, 0x505f6c67u, 0x746e696fu, 0x657a6953u, 0x00000000u, 0x00070006u, 0x0000005bu,
-    0x00000002u, 0x435f6c67u, 0x4470696cu, 0x61747369u, 0x0065636eu, 0x00070006u, 0x0000005bu, 0x00000003u,
-    0x435f6c67u, 0x446c6c75u, 0x61747369u, 0x0065636eu, 0x00030005u, 0x0000005du, 0x00000000u, 0x00050005u,
-    0x00000066u, 0x43786574u, 0x64726f6fu, 0x00000000u, 0x00040047u, 0x00000016u, 0x0000000bu, 0x0000002au,
-    0x00030047u, 0x0000001eu, 0x00000002u, 0x00050048u, 0x0000001eu, 0x00000000u, 0x00000023u, 0x00000000u,
-    0x00050048u, 0x0000001eu, 0x00000001u, 0x00000023u, 0x00000010u, 0x00050048u, 0x0000001eu, 0x00000002u,
-    0x00000023u, 0x00000020u, 0x00030047u, 0x0000005bu, 0x00000002u, 0x00050048u, 0x0000005bu, 0x00000000u,
-    0x0000000bu, 0x00000000u, 0x00050048u, 0x0000005bu, 0x00000001u, 0x0000000bu, 0x00000001u, 0x00050048u,
-    0x0000005bu, 0x00000002u, 0x0000000bu, 0x00000003u, 0x00050048u, 0x0000005bu, 0x00000003u, 0x0000000bu,
-    0x00000004u, 0x00040047u, 0x00000066u, 0x0000001eu, 0x00000000u, 0x00020013u, 0x00000002u, 0x00030021u,
-    0x00000003u, 0x00000002u, 0x00030016u, 0x00000006u, 0x00000020u, 0x00040017u, 0x00000007u, 0x00000006u,
-    0x00000002u, 0x00040020u, 0x00000008u, 0x00000007u, 0x00000007u, 0x00040015u, 0x0000000au, 0x00000020u,
-    0x00000000u, 0x0004002bu, 0x0000000au, 0x0000000bu, 0x00000006u, 0x0004001cu, 0x0000000cu, 0x00000007u,
-    0x0000000bu, 0x0004002bu, 0x00000006u, 0x0000000du, 0x00000000u, 0x0005002cu, 0x00000007u, 0x0000000eu,
-    0x0000000du, 0x0000000du, 0x0004002bu, 0x00000006u, 0x0000000fu, 0x3f800000u, 0x0005002cu, 0x00000007u,
-    0x00000010u, 0x0000000fu, 0x0000000du, 0x0005002cu, 0x00000007u, 0x00000011u, 0x0000000du, 0x0000000fu,
-    0x0005002cu, 0x00000007u, 0x00000012u, 0x0000000fu, 0x0000000fu, 0x0009002cu, 0x0000000cu, 0x00000013u,
-    0x0000000eu, 0x00000010u, 0x00000011u, 0x00000011u, 0x00000010u, 0x00000012u, 0x00040015u, 0x00000014u,
-    0x00000020u, 0x00000001u, 0x00040020u, 0x00000015u, 0x00000001u, 0x00000014u, 0x0004003bu, 0x00000015u,
-    0x00000016u, 0x00000001u, 0x00040020u, 0x00000018u, 0x00000007u, 0x0000000cu, 0x00040017u, 0x0000001du,
-    0x00000006u, 0x00000004u, 0x0005001eu, 0x0000001eu, 0x0000001du, 0x0000001du, 0x00000014u, 0x00040020u,
-    0x0000001fu, 0x00000009u, 0x0000001eu, 0x0004003bu, 0x0000001fu, 0x00000020u, 0x00000009u, 0x0004002bu,
-    0x00000014u, 0x00000021u, 0x00000001u, 0x00040020u, 0x00000022u, 0x00000009u, 0x0000001du, 0x0004002bu,
-    0x00000006u, 0x0000002cu, 0x40000000u, 0x0004002bu, 0x0000000au, 0x00000030u, 0x00000001u, 0x00040020u,
-    0x00000031u, 0x00000007u, 0x00000006u, 0x0004002bu, 0x00000014u, 0x00000036u, 0x00000002u, 0x00040020u,
-    0x00000037u, 0x00000009u, 0x00000014u, 0x00020014u, 0x0000003au, 0x0004002bu, 0x0000000au, 0x00000041u,
-    0x00000000u, 0x0004002bu, 0x00000014u, 0x00000050u, 0x00000003u, 0x0004001cu, 0x0000005au, 0x00000006u,
-    0x00000030u, 0x0006001eu, 0x0000005bu, 0x0000001du, 0x00000006u, 0x0000005au, 0x0000005au, 0x00040020u,
-    0x0000005cu, 0x00000003u, 0x0000005bu, 0x0004003bu, 0x0000005cu, 0x0000005du, 0x00000003u, 0x0004002bu,
-    0x00000014u, 0x0000005eu, 0x00000000u, 0x00040020u, 0x00000063u, 0x00000003u, 0x0000001du, 0x00040020u,
-    0x00000065u, 0x00000003u, 0x00000007u, 0x0004003bu, 0x00000065u, 0x00000066u, 0x00000003u, 0x00050036u,
-    0x00000002u, 0x00000004u, 0x00000000u, 0x00000003u, 0x000200f8u, 0x00000005u, 0x0004003bu, 0x00000008u,
-    0x00000009u, 0x00000007u, 0x0004003bu, 0x00000018u, 0x00000019u, 0x00000007u, 0x0004003bu, 0x00000008u,
-    0x0000001cu, 0x00000007u, 0x0004003du, 0x00000014u, 0x00000017u, 0x00000016u, 0x0003003eu, 0x00000019u,
-    0x00000013u, 0x00050041u, 0x00000008u, 0x0000001au, 0x00000019u, 0x00000017u, 0x0004003du, 0x00000007u,
-    0x0000001bu, 0x0000001au, 0x0003003eu, 0x00000009u, 0x0000001bu, 0x00050041u, 0x00000022u, 0x00000023u,
-    0x00000020u, 0x00000021u, 0x0004003du, 0x0000001du, 0x00000024u, 0x00000023u, 0x0007004fu, 0x00000007u,
-    0x00000025u, 0x00000024u, 0x00000024u, 0x00000000u, 0x00000001u, 0x0004003du, 0x00000007u, 0x00000026u,
-    0x00000009u, 0x00050041u, 0x00000022u, 0x00000027u, 0x00000020u, 0x00000021u, 0x0004003du, 0x0000001du,
-    0x00000028u, 0x00000027u, 0x0007004fu, 0x00000007u, 0x00000029u, 0x00000028u, 0x00000028u, 0x00000002u,
-    0x00000003u, 0x00050085u, 0x00000007u, 0x0000002au, 0x00000026u, 0x00000029u, 0x00050081u, 0x00000007u,
-    0x0000002bu, 0x00000025u, 0x0000002au, 0x0005008eu, 0x00000007u, 0x0000002du, 0x0000002bu, 0x0000002cu,
-    0x00050050u, 0x00000007u, 0x0000002eu, 0x0000000fu, 0x0000000fu, 0x00050083u, 0x00000007u, 0x0000002fu,
-    0x0000002du, 0x0000002eu, 0x0003003eu, 0x0000001cu, 0x0000002fu, 0x00050041u, 0x00000031u, 0x00000032u,
-    0x0000001cu, 0x00000030u, 0x0004003du, 0x00000006u, 0x00000033u, 0x00000032u, 0x0004007fu, 0x00000006u,
-    0x00000034u, 0x00000033u, 0x00050041u, 0x00000031u, 0x00000035u, 0x0000001cu, 0x00000030u, 0x0003003eu,
-    0x00000035u, 0x00000034u, 0x00050041u, 0x00000037u, 0x00000038u, 0x00000020u, 0x00000036u, 0x0004003du,
-    0x00000014u, 0x00000039u, 0x00000038u, 0x000500aau, 0x0000003au, 0x0000003bu, 0x00000039u, 0x00000021u,
-    0x000300f7u, 0x0000003du, 0x00000000u, 0x000400fau, 0x0000003bu, 0x0000003cu, 0x00000045u, 0x000200f8u,
-    0x0000003cu, 0x00050041u, 0x00000031u, 0x0000003eu, 0x0000001cu, 0x00000030u, 0x0004003du, 0x00000006u,
-    0x0000003fu, 0x0000003eu, 0x0004007fu, 0x00000006u, 0x00000040u, 0x0000003fu, 0x00050041u, 0x00000031u,
-    0x00000042u, 0x0000001cu, 0x00000041u, 0x0004003du, 0x00000006u, 0x00000043u, 0x00000042u, 0x00050050u,
-    0x00000007u, 0x00000044u, 0x00000040u, 0x00000043u, 0x0003003eu, 0x0000001cu, 0x00000044u, 0x000200f9u,
-    0x0000003du, 0x000200f8u, 0x00000045u, 0x00050041u, 0x00000037u, 0x00000046u, 0x00000020u, 0x00000036u,
-    0x0004003du, 0x00000014u, 0x00000047u, 0x00000046u, 0x000500aau, 0x0000003au, 0x00000048u, 0x00000047u,
-    0x00000036u, 0x000300f7u, 0x0000004au, 0x00000000u, 0x000400fau, 0x00000048u, 0x00000049u, 0x0000004du,
-    0x000200f8u, 0x00000049u, 0x0004003du, 0x00000007u, 0x0000004bu, 0x0000001cu, 0x0004007fu, 0x00000007u,
-    0x0000004cu, 0x0000004bu, 0x0003003eu, 0x0000001cu, 0x0000004cu, 0x000200f9u, 0x0000004au, 0x000200f8u,
-    0x0000004du, 0x00050041u, 0x00000037u, 0x0000004eu, 0x00000020u, 0x00000036u, 0x0004003du, 0x00000014u,
-    0x0000004fu, 0x0000004eu, 0x000500aau, 0x0000003au, 0x00000051u, 0x0000004fu, 0x00000050u, 0x000300f7u,
-    0x00000053u, 0x00000000u, 0x000400fau, 0x00000051u, 0x00000052u, 0x00000053u, 0x000200f8u, 0x00000052u,
-    0x00050041u, 0x00000031u, 0x00000054u, 0x0000001cu, 0x00000030u, 0x0004003du, 0x00000006u, 0x00000055u,
-    0x00000054u, 0x00050041u, 0x00000031u, 0x00000056u, 0x0000001cu, 0x00000041u, 0x0004003du, 0x00000006u,
-    0x00000057u, 0x00000056u, 0x0004007fu, 0x00000006u, 0x00000058u, 0x00000057u, 0x00050050u, 0x00000007u,
-    0x00000059u, 0x00000055u, 0x00000058u, 0x0003003eu, 0x0000001cu, 0x00000059u, 0x000200f9u, 0x00000053u,
-    0x000200f8u, 0x00000053u, 0x000200f9u, 0x0000004au, 0x000200f8u, 0x0000004au, 0x000200f9u, 0x0000003du,
-    0x000200f8u, 0x0000003du, 0x0004003du, 0x00000007u, 0x0000005fu, 0x0000001cu, 0x00050051u, 0x00000006u,
-    0x00000060u, 0x0000005fu, 0x00000000u, 0x00050051u, 0x00000006u, 0x00000061u, 0x0000005fu, 0x00000001u,
-    0x00070050u, 0x0000001du, 0x00000062u, 0x00000060u, 0x00000061u, 0x0000000du, 0x0000000fu, 0x00050041u,
-    0x00000063u, 0x00000064u, 0x0000005du, 0x0000005eu, 0x0003003eu, 0x00000064u, 0x00000062u, 0x00050041u,
-    0x00000022u, 0x00000067u, 0x00000020u, 0x0000005eu, 0x0004003du, 0x0000001du, 0x00000068u, 0x00000067u,
-    0x0007004fu, 0x00000007u, 0x00000069u, 0x00000068u, 0x00000068u, 0x00000000u, 0x00000001u, 0x0004003du,
-    0x00000007u, 0x0000006au, 0x00000009u, 0x00050041u, 0x00000022u, 0x0000006bu, 0x00000020u, 0x0000005eu,
-    0x0004003du, 0x0000001du, 0x0000006cu, 0x0000006bu, 0x0007004fu, 0x00000007u, 0x0000006du, 0x0000006cu,
-    0x0000006cu, 0x00000002u, 0x00000003u, 0x00050085u, 0x00000007u, 0x0000006eu, 0x0000006au, 0x0000006du,
-    0x00050081u, 0x00000007u, 0x0000006fu, 0x00000069u, 0x0000006eu, 0x0003003eu, 0x00000066u, 0x0000006fu,
-    0x000100fdu, 0x00010038u,
-};
-
-static constexpr Uint32 kWireColorBlitFragmentSpirv[] = {
-    0x07230203u, 0x00010000u, 0x0008000bu, 0x00000027u, 0x00000000u, 0x00020011u, 0x00000001u, 0x0006000bu,
-    0x00000001u, 0x4c534c47u, 0x6474732eu, 0x3035342eu, 0x00000000u, 0x0003000eu, 0x00000000u, 0x00000001u,
-    0x0007000fu, 0x00000004u, 0x00000004u, 0x6e69616du, 0x00000000u, 0x0000000au, 0x0000001fu, 0x00030010u,
-    0x00000004u, 0x00000007u, 0x00030003u, 0x00000002u, 0x000001c2u, 0x00040005u, 0x00000004u, 0x6e69616du,
-    0x00000000u, 0x00050005u, 0x0000000au, 0x43786574u, 0x64726f6fu, 0x00000000u, 0x00050005u, 0x0000001fu,
-    0x4374756fu, 0x726f6c6fu, 0x00000000u, 0x00050005u, 0x00000023u, 0x72756f73u, 0x6d496563u, 0x00656761u,
-    0x00040047u, 0x0000000au, 0x0000001eu, 0x00000000u, 0x00040047u, 0x0000001fu, 0x0000001eu, 0x00000000u,
-    0x00040047u, 0x00000023u, 0x00000021u, 0x00000000u, 0x00040047u, 0x00000023u, 0x00000022u, 0x00000000u,
-    0x00020013u, 0x00000002u, 0x00030021u, 0x00000003u, 0x00000002u, 0x00020014u, 0x00000006u, 0x00030016u,
-    0x00000007u, 0x00000020u, 0x00040017u, 0x00000008u, 0x00000007u, 0x00000002u, 0x00040020u, 0x00000009u,
-    0x00000001u, 0x00000008u, 0x0004003bu, 0x00000009u, 0x0000000au, 0x00000001u, 0x0004002bu, 0x00000007u,
-    0x0000000cu, 0x00000000u, 0x0005002cu, 0x00000008u, 0x0000000du, 0x0000000cu, 0x0000000cu, 0x00040017u,
-    0x0000000eu, 0x00000006u, 0x00000002u, 0x0004002bu, 0x00000007u, 0x00000015u, 0x3f800000u, 0x0005002cu,
-    0x00000008u, 0x00000016u, 0x00000015u, 0x00000015u, 0x00040017u, 0x0000001du, 0x00000007u, 0x00000004u,
-    0x00040020u, 0x0000001eu, 0x00000003u, 0x0000001du, 0x0004003bu, 0x0000001eu, 0x0000001fu, 0x00000003u,
-    0x00090019u, 0x00000020u, 0x00000007u, 0x00000001u, 0x00000000u, 0x00000000u, 0x00000000u, 0x00000001u,
-    0x00000000u, 0x0003001bu, 0x00000021u, 0x00000020u, 0x00040020u, 0x00000022u, 0x00000000u, 0x00000021u,
-    0x0004003bu, 0x00000022u, 0x00000023u, 0x00000000u, 0x00050036u, 0x00000002u, 0x00000004u, 0x00000000u,
-    0x00000003u, 0x000200f8u, 0x00000005u, 0x0004003du, 0x00000008u, 0x0000000bu, 0x0000000au, 0x000500b8u,
-    0x0000000eu, 0x0000000fu, 0x0000000bu, 0x0000000du, 0x0004009au, 0x00000006u, 0x00000010u, 0x0000000fu,
-    0x000400a8u, 0x00000006u, 0x00000011u, 0x00000010u, 0x000300f7u, 0x00000013u, 0x00000000u, 0x000400fau,
-    0x00000011u, 0x00000012u, 0x00000013u, 0x000200f8u, 0x00000012u, 0x0004003du, 0x00000008u, 0x00000014u,
-    0x0000000au, 0x000500bau, 0x0000000eu, 0x00000017u, 0x00000014u, 0x00000016u, 0x0004009au, 0x00000006u,
-    0x00000018u, 0x00000017u, 0x000200f9u, 0x00000013u, 0x000200f8u, 0x00000013u, 0x000700f5u, 0x00000006u,
-    0x00000019u, 0x00000010u, 0x00000005u, 0x00000018u, 0x00000012u, 0x000300f7u, 0x0000001bu, 0x00000000u,
-    0x000400fau, 0x00000019u, 0x0000001au, 0x0000001bu, 0x000200f8u, 0x0000001au, 0x000100fcu, 0x000200f8u,
-    0x0000001bu, 0x0004003du, 0x00000021u, 0x00000024u, 0x00000023u, 0x0004003du, 0x00000008u, 0x00000025u,
-    0x0000000au, 0x00070058u, 0x0000001du, 0x00000026u, 0x00000024u, 0x00000025u, 0x00000002u, 0x0000000cu,
-    0x0003003eu, 0x0000001fu, 0x00000026u, 0x000100fdu, 0x00010038u,
-};

MobileGL/MG_Backend/DirectVulkan/Renderer/WireDeclineTally.h

@@ -1,172 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/WireDeclineTally.h
-// Copyright (c) 2025-2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-
-#pragma once
-
-#include <Config.h>
-#if MOBILEGL_BUILD_DISAGGREGATED
-
-#include <Includes.h>
-#include <MG_Util/Debug/Log.h>
-
-#include <atomic>
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-
-// P7 wave 2 package B3: the per-site tally behind CONTRACT-P7 §0 rule I.
-//
-// Shape is PipeApplier.h's ServerVerbSink tallies, and for the same reason (R-16: a probe may
-// not arm against a stub). "The retrace passed" and "the retrace silently dropped nine draws"
-// produce the same exit code and the same log, so the lane has to assert the number that only
-// this path can move.
-//
-// Counters are process-wide and monotone. On the spawn arm they live in the SERVER process,
-// which is where the draw path runs - a client-side reader would always see zero, so the
-// two-process case asserts pixels and reads these from the server's own dump.
-enum class WireDeclineSite : Uint32 {
-#define MGL_WIRE_DECLINE(name) name,
-#include "WireDeclines.def"
-#undef MGL_WIRE_DECLINE
-    Count
-};
-
-inline const char* WireDeclineSiteName(WireDeclineSite site) {
-    switch (site) {
-#define MGL_WIRE_DECLINE(name)                                                                                         \
-    case WireDeclineSite::name:                                                                                        \
-        return #name;
-#include "WireDeclines.def"
-#undef MGL_WIRE_DECLINE
-    case WireDeclineSite::Count:
-        break;
-    }
-    return "Unnamed";
-}
-
-class WireDeclineTally {
-public:
-    static constexpr SizeT kSiteCount = static_cast<SizeT>(WireDeclineSite::Count);
-
-    static void Count(WireDeclineSite site) {
-        Slots()[static_cast<SizeT>(site)].fetch_add(1, std::memory_order_relaxed);
-        Total().fetch_add(1, std::memory_order_relaxed);
-    }
-
-    static Uint64 Get(WireDeclineSite site) {
-        return Slots()[static_cast<SizeT>(site)].load(std::memory_order_relaxed);
-    }
-
-    static Uint64 TotalDeclines() { return Total().load(std::memory_order_relaxed); }
-
-    // The memory half (package M1's thread): a refused upload does not consume its
-    // PendingUpload entry, so the entry and the level shadow behind it stay alive. These are
-    // GAUGES, not counters - the last observed live depth, sampled where the refusal happens -
-    // so a monotone climb across frames is the signature that a refusal is also a leak.
-    static void SetPendingGauge(Uint64 entries, Uint64 bytes) {
-        PendingEntries().store(entries, std::memory_order_relaxed);
-        PendingBytes().store(bytes, std::memory_order_relaxed);
-        Uint64 peak = PeakPendingBytes().load(std::memory_order_relaxed);
-        while (bytes > peak && !PeakPendingBytes().compare_exchange_weak(peak, bytes, std::memory_order_relaxed)) {
-        }
-    }
-    // The frame-serial floor's own counter. An "unsound serial complete" is an advance of
-    // VkBufferManager's completed-frame-serial floor to a serial that ANOTHER submission still
-    // in flight also carries - i.e. the renderer telling the buffer manager "frame N-1 is done"
-    // while the submission holding frame N-1's buffer copies is still executing. It is what
-    // lets a streamed glBufferSubData take the unordered host path and tear one draw's vertex
-    // range. With a provable floor it is unreachable, so this counter is the red-once's reading:
-    // non-zero on the wire arms before the fix, zero after, zero on monolith either way.
-    static void CountUnsoundSerialComplete() {
-        UnsoundSerial().fetch_add(1, std::memory_order_relaxed);
-    }
-    static Uint64 UnsoundSerialCompleteEvents() { return UnsoundSerial().load(std::memory_order_relaxed); }
-
-    static Uint64 PendingUploadEntries() { return PendingEntries().load(std::memory_order_relaxed); }
-    static Uint64 PendingUploadBytes() { return PendingBytes().load(std::memory_order_relaxed); }
-    static Uint64 PeakPendingUploadBytes() { return PeakPendingBytes().load(std::memory_order_relaxed); }
-
-    static void Reset() {
-        for (SizeT i = 0; i < kSiteCount; ++i) Slots()[i].store(0, std::memory_order_relaxed);
-        Total().store(0, std::memory_order_relaxed);
-        UnsoundSerial().store(0, std::memory_order_relaxed);
-        PendingEntries().store(0, std::memory_order_relaxed);
-        PendingBytes().store(0, std::memory_order_relaxed);
-        PeakPendingBytes().store(0, std::memory_order_relaxed);
-    }
-
-    // One line per site that moved, plus the pending gauges. Called at session teardown and
-    // from the forced-condition harness; silent when nothing declined, so a green lane stays
-    // quiet and a lane that dropped a draw cannot.
-    static void Dump(const char* tag) {
-        // The floor counter prints unconditionally: "zero unsound advances" is the reading the
-        // red-once needs, and an absent line cannot be told from a lane that never ran.
-        MGLOG_I("MGWIRE-FLOOR[%s] unsoundSerialComplete=%llu", tag,
-                static_cast<unsigned long long>(UnsoundSerialCompleteEvents()));
-        if (TotalDeclines() == 0 && PeakPendingUploadBytes() == 0) return;
-        MGLOG_I("MGWIRE-DECLINES[%s] total=%llu pendingEntries=%llu pendingBytes=%llu peakPendingBytes=%llu", tag,
-                static_cast<unsigned long long>(TotalDeclines()),
-                static_cast<unsigned long long>(PendingUploadEntries()),
-                static_cast<unsigned long long>(PendingUploadBytes()),
-                static_cast<unsigned long long>(PeakPendingUploadBytes()));
-        for (SizeT i = 0; i < kSiteCount; ++i) {
-            const Uint64 value = Slots()[i].load(std::memory_order_relaxed);
-            if (!value) continue;
-            MGLOG_I("MGWIRE-DECLINES[%s]   %s=%llu", tag, WireDeclineSiteName(static_cast<WireDeclineSite>(i)),
-                    static_cast<unsigned long long>(value));
-        }
-    }
-
-private:
-    static std::atomic<Uint64>* Slots() {
-        static std::atomic<Uint64> slots[kSiteCount]{};
-        return slots;
-    }
-    static std::atomic<Uint64>& Total() {
-        static std::atomic<Uint64> total{0};
-        return total;
-    }
-    static std::atomic<Uint64>& PendingEntries() {
-        static std::atomic<Uint64> value{0};
-        return value;
-    }
-    static std::atomic<Uint64>& PendingBytes() {
-        static std::atomic<Uint64> value{0};
-        return value;
-    }
-    static std::atomic<Uint64>& PeakPendingBytes() {
-        static std::atomic<Uint64> value{0};
-        return value;
-    }
-    static std::atomic<Uint64>& UnsoundSerial() {
-        static std::atomic<Uint64> value{0};
-        return value;
-    }
-};
-
-// Every decline goes through this: the tally moves ALWAYS, the log line is once per site.
-// `MGL_WIRE_DECLINE_AT(Site, "why", ...); return false;` is the statement pair that replaces
-// a bare `return false;` (the few sites that call WireDeclineTally::Count directly stand
-// under an MGLOG_W/E of their own; scripts/ci/wire_declines_audit.py holds them to that).
-//
-// A DECLINE IS NOT ALWAYS A SKIPPED DRAW, so the line does not say "draw". The Tex*, Shape* and
-// Upload* rows are counted per texture SYNC: SyncTextureResourceByHandle is reached from the
-// draw/dispatch texture preparation, but also from the descriptor resolver, framebuffer
-// attachments, CopyTexSubImage, mipmap generation and CopyImageSubData - each of which Fatals
-// right after a failed sync - and from texture readback, which falls back to the unbacked
-// shadow. A draw that samples three unsyncable textures counts three; a failed attachment
-// sync counts once and is then a Fatal, not a skipped draw.
-#define MGL_WIRE_DECLINE_AT(site, fmt, ...)                                                                            \
-    do {                                                                                                               \
-        ::MobileGL::MG_Backend::DirectVulkan::WireDeclineTally::Count(                                                  \
-            ::MobileGL::MG_Backend::DirectVulkan::WireDeclineSite::site);                                              \
-        MGLOG_E_ONCE("Magma wire decline [" #site "]: " fmt, ##__VA_ARGS__);                                           \
-    } while (0)
-
-} // namespace MobileGL::MG_Backend::DirectVulkan
-
-#endif // MOBILEGL_BUILD_DISAGGREGATED

MobileGL/MG_Backend/DirectVulkan/Renderer/WireDeclines.def

@@ -1,106 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/WireDeclines.def
-// Copyright (c) 2025-2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-
-// P7 wave 2 package B3. THE NAMES OF EVERY WAY THE MAGMA WIRE ARM CAN DECLINE.
-//
-// A DECLINE IS NOT ALWAYS A SKIPPED DRAW. The SetupWireDraw / DispatchWireCompute rows are one
-// per refused draw or dispatch; the Tex* / Shape* / Upload* rows are counted per texture SYNC,
-// which the draw path reaches once per sampled texture and the descriptor resolver, framebuffer
-// attachments, CopyTexSubImage, mipmap generation, CopyImageSubData and texture readback reach
-// on their own (WireDeclineTally.h, above MGL_WIRE_DECLINE_AT).
-//
-// CONTRACT-P7 §0 rule I says a refusal on the wire arm is either a named decline or a named
-// Fatal. Before B3 the draw path had a third shape the rule does not admit: a bare
-// `return false` with no log, no counter and no census entry - roughly twenty of them in
-// SetupWireDraw alone, plus the texture-sync chain behind PrepareWireTextureResources. A draw
-// that took one of those exits left NO trace anywhere, which is precisely why the OpenRA
-// device divergence survived four device windows with client and server logs that were
-// LINE-IDENTICAL between a passing and a failing run.
-//
-// Each row below is one such exit. The name is what the decline logs and what the tally
-// counts, so "which exit did this frame take" is answerable from a counter dump instead of
-// from a bisect. Rows are append-only: the integration lane asserts specific counters moved.
-//
-// EVERY ROW HAS A SITE AND EVERY SITE HAS A LINE. A row with no site is a name that can never
-// be counted - it reads as "this cannot happen here" when it only means "nobody wired it up" -
-// and a site with no line puts the reader back on a bisect. Sites reached through a macro
-// (MGL_WIRE_DECLINE_AT) get both at once; the few that use WireDeclineTally::Count directly do
-// so ONLY because the statement above them already carries the same reason as an _ONCE log.
-// scripts/ci/wire_declines_audit.py holds both halves.
-//
-// MGL_WIRE_DECLINE(Name)
-
-// ---- SetupWireDraw, in statement order -------------------------------------------------
-MGL_WIRE_DECLINE(ProgramLinkOrSpirv)
-MGL_WIRE_DECLINE(PointSizeCapability)
-MGL_WIRE_DECLINE(TextureResourcesUnprepared)
-MGL_WIRE_DECLINE(VertexFormatUnsupported)
-MGL_WIRE_DECLINE(VertexAttributeWindow)
-MGL_WIRE_DECLINE(VertexStreamCountZero)
-MGL_WIRE_DECLINE(VertexStreamRead)
-MGL_WIRE_DECLINE(VertexStreamConverter)
-MGL_WIRE_DECLINE(VertexTransientUpload)
-MGL_WIRE_DECLINE(IndexViewMissing)
-MGL_WIRE_DECLINE(IndexTypeWidth)
-MGL_WIRE_DECLINE(IndexWindow)
-MGL_WIRE_DECLINE(IndexStreamRead)
-MGL_WIRE_DECLINE(IndexTransientUpload)
-MGL_WIRE_DECLINE(IndexSliceInvalid)
-MGL_WIRE_DECLINE(UniformBufferBinding)
-MGL_WIRE_DECLINE(NoAttachments)
-MGL_WIRE_DECLINE(PipelineUnavailable)
-MGL_WIRE_DECLINE(CurrentAttributePayload)
-MGL_WIRE_DECLINE(CurrentAttributeUpload)
-MGL_WIRE_DECLINE(BeginRenderPass)
-
-// ---- DispatchWireCompute ----------------------------------------------------------------
-MGL_WIRE_DECLINE(ComputeProgramLinkOrSpirv)
-MGL_WIRE_DECLINE(ComputeTextureResourcesUnprepared)
-MGL_WIRE_DECLINE(ComputePipelineUnavailable)
-MGL_WIRE_DECLINE(ComputeUniformBufferBinding)
-
-// ---- UniformManager::PrepareWireTextureResources ----------------------------------------
-MGL_WIRE_DECLINE(DescriptorDeclined)
-MGL_WIRE_DECLINE(SamplerLocationAlias)
-MGL_WIRE_DECLINE(SamplerUnitRange)
-
-// ---- VkTextureManager::SyncTextureResourceByHandle --------------------------------------
-MGL_WIRE_DECLINE(TexResolveStorage)
-MGL_WIRE_DECLINE(TexViewFormat)
-MGL_WIRE_DECLINE(TexNoApplierRecord)
-MGL_WIRE_DECLINE(TexRecordDeadOrStale)
-MGL_WIRE_DECLINE(TexShapeSync)
-MGL_WIRE_DECLINE(TexUploadPendingLevels)
-MGL_WIRE_DECLINE(TexStorageUsage)
-
-// ---- VkTextureManager::UploadPendingWireLevels ------------------------------------------
-// The five `incomplete`/false exits the investigation named, plus the two that leave an
-// entry pending WITHOUT failing (a `continue`) - those are the ones that can starve a draw
-// of its texels while still reporting success, so they are counted separately.
-MGL_WIRE_DECLINE(UploadLevelBeyondChain)
-MGL_WIRE_DECLINE(UploadLevelExtentMismatch)
-MGL_WIRE_DECLINE(UploadEmptyLevel)
-MGL_WIRE_DECLINE(UploadConversion)
-MGL_WIRE_DECLINE(UploadTexelArithmetic)
-MGL_WIRE_DECLINE(UploadRegionOutOfBounds)
-MGL_WIRE_DECLINE(UploadIncomplete)
-MGL_WIRE_DECLINE(UploadFlushFailed)
-
-// ---- VkTextureManager::SyncWireTextureShape ---------------------------------------------
-MGL_WIRE_DECLINE(ShapeBufferBacked)
-MGL_WIRE_DECLINE(ShapeViewOfStorage)
-MGL_WIRE_DECLINE(ShapeNoLevels)
-MGL_WIRE_DECLINE(ShapeNoVulkanShape)
-MGL_WIRE_DECLINE(ShapeNoVkFormat)
-MGL_WIRE_DECLINE(ShapeSampleCount)
-MGL_WIRE_DECLINE(ShapePreserveFlushFailed)
-MGL_WIRE_DECLINE(ShapeImageFlagsUnsupported)
-MGL_WIRE_DECLINE(ShapeCreateImageFailed)
-// Appended by the B3 review round: the preserve-copy arm of a reallocation was the one exit in
-// SyncWireTextureShape still leaving no trace at all.
-MGL_WIRE_DECLINE(ShapePreserveCopyFailed)

MobileGL/MG_Backend/DirectVulkan/Renderer/WireDepthMipmap.frag

@@ -1,28 +0,0 @@
-#version 450
-// The monolith arm's kDepthMipmapFragmentShaderSource (VulkanRenderer.cpp), ported to the
-// baked pipeline: the same 2x2 box of texelFetches, the same clamp, the same average, the
-// same gl_FragDepth. It is a PORT and not a rewrite on purpose - CONTRACT-P7 §3.2 retires a
-// refusal by making the wire arm observably the monolith's, so the two arms have to agree
-// texel for texel, including where they read.
-//
-// uSrcTexelSize arrives on the push constant rather than in a uniform block: the wire arm
-// owns no GL program, so there is no default-block uniform to write and no global UBO to
-// bind. That is the whole of OQ-13's narrow half for this program.
-layout(push_constant) uniform DepthMipmapRect {
-    vec4 srcRect;
-    vec4 dstRect;
-    int surfaceTransform;
-    ivec2 srcTexelSize;
-} rect;
-layout(set = 0, binding = 0) uniform sampler2D sourceImage;
-layout(location = 0) in vec2 texCoord;
-
-void main() {
-    ivec2 srcBase = ivec2(texCoord * vec2(rect.srcTexelSize));
-    ivec2 srcMax = rect.srcTexelSize - ivec2(1);
-    float depth0 = texelFetch(sourceImage, clamp(srcBase, ivec2(0), srcMax), 0).r;
-    float depth1 = texelFetch(sourceImage, clamp(srcBase + ivec2(1, 0), ivec2(0), srcMax), 0).r;
-    float depth2 = texelFetch(sourceImage, clamp(srcBase + ivec2(0, 1), ivec2(0), srcMax), 0).r;
-    float depth3 = texelFetch(sourceImage, clamp(srcBase + ivec2(1, 1), ivec2(0), srcMax), 0).r;
-    gl_FragDepth = 0.25 * (depth0 + depth1 + depth2 + depth3);
-}

MobileGL/MG_Backend/DirectVulkan/Renderer/WireDepthMipmap.inc

@@ -1,320 +0,0 @@
-// Included by VulkanRenderer.cpp inside the backend namespace, after WireColorBlit.inc.
-// The native depth mip owns no frontend object and never invokes the GL shader compiler.
-//
-// WHY THIS FILE EXISTS AT ALL. vkCmdBlitImage is the ordinary way to halve a mip, and for a
-// depth format it is often not available: VK_FORMAT_FEATURE_BLIT_DST is optional for depth,
-// and the monolith arm has carried a shader fallback for exactly that case since before the
-// split (VulkanRenderer.cpp's GenerateDepthMipmapWithShader). The wire arm had no such
-// fallback, so every depth mip the device could not blit died as
-// `Magma:mipmap-shader-format-or-shape`, and a DEPTH|STENCIL texture died one guard earlier
-// as `Magma:depth-stencil-mipmap@P7` whether or not it could be blitted.
-//
-// The monolith fallback is not reusable here and that is the whole of CONTRACT-P7 §5.1 (A):
-// it builds a GL ProgramObject, two GL ShaderObjects and a GL sampler, binds through the
-// uniform manager's global UBO, and writes uSrcTexelSize as a default-block uniform - four
-// frontend objects and a GL compiler on the server's apply thread. The baked program below is
-// the same shader with the same arithmetic, driven by a push constant and its own descriptor
-// set, which is what lets the server generate a depth mip while owning nothing of the client.
-#if MOBILEGL_BUILD_DISAGGREGATED
-#include "WireDepthMipmapSpirv.h"
-
-    struct VulkanRenderer::WireDepthMipmapResources {
-        struct Target {
-            VkFormat format = VK_FORMAT_UNDEFINED;
-            VkImageLayout layout = VK_IMAGE_LAYOUT_UNDEFINED;
-            VkRenderPass renderPass = VK_NULL_HANDLE;
-            VkPipeline pipeline = VK_NULL_HANDLE;
-        };
-        VkShaderModule vertex = VK_NULL_HANDLE, fragment = VK_NULL_HANDLE;
-        VkDescriptorSetLayout descriptorLayout = VK_NULL_HANDLE;
-        VkPipelineLayout pipelineLayout = VK_NULL_HANDLE;
-        VkSampler nearest = VK_NULL_HANDLE;
-        Vector<Target> targets;
-    };
-
-    void VulkanRenderer::DestroyWireDepthMipmapResources() {
-        if (!m_wireDepthMipmapResources) return;
-        // Shutdown calls this after vkDeviceWaitIdle and after all per-submit
-        // descriptor pools/framebuffers/views have been collected.
-        auto& cache = *m_wireDepthMipmapResources;
-        for (const auto& target : cache.targets) {
-            vkDestroyPipeline(m_device, target.pipeline, nullptr);
-            vkDestroyRenderPass(m_device, target.renderPass, nullptr);
-        }
-        vkDestroySampler(m_device, cache.nearest, nullptr);
-        vkDestroyPipelineLayout(m_device, cache.pipelineLayout, nullptr);
-        vkDestroyDescriptorSetLayout(m_device, cache.descriptorLayout, nullptr);
-        vkDestroyShaderModule(m_device, cache.vertex, nullptr);
-        vkDestroyShaderModule(m_device, cache.fragment, nullptr);
-        delete m_wireDepthMipmapResources;
-        m_wireDepthMipmapResources = nullptr;
-    }
-
-    // ONE LEVEL, source -> destination, both depth subresources of the same image. The shape
-    // mirrors BlitWireColorImage deliberately: the same lazily built module pair, the same
-    // per-format render pass/pipeline cache, the same per-submit descriptor pool, and the
-    // same GENERAL-on-both-sides layout rule for a same-image pass, so the two native passes
-    // cannot disagree about how an image is handed between them.
-    Bool VulkanRenderer::GenerateWireDepthMipLevel(WireImage source, WireImage destination) {
-        const Bool sameImage = source.image == destination.image;
-        if (!source.image || !destination.image) return false;
-        if (sameImage && source.level == destination.level && source.layer == destination.layer)
-            return false;
-        if (source.isDefault || destination.isDefault) return false;
-        if (source.samples != VK_SAMPLE_COUNT_1_BIT || destination.samples != VK_SAMPLE_COUNT_1_BIT)
-            return false;
-        if (source.is3D || destination.is3D) return false;
-        if (source.format != destination.format) return false;
-        // DEPTH ONLY. A combined depth/stencil image can be sampled for its depth and
-        // rendered as a depth attachment, but this pass writes gl_FragDepth and NOTHING
-        // else - the stencil aspect would come out of the render pass undefined, which is
-        // not what GL's glGenerateMipmap promises for the level it just produced. The
-        // caller declines that shape rather than producing half a level.
-        if (source.aspect != VK_IMAGE_ASPECT_DEPTH_BIT ||
-            destination.aspect != VK_IMAGE_ASPECT_DEPTH_BIT) return false;
-        if (!source.extent.width || !source.extent.height ||
-            !destination.extent.width || !destination.extent.height) return false;
-        VkFormatProperties properties{};
-        vkGetPhysicalDeviceFormatProperties(m_physicalDevice.handle, source.format, &properties);
-        const VkFormatFeatureFlags required = VK_FORMAT_FEATURE_SAMPLED_IMAGE_BIT |
-                                              VK_FORMAT_FEATURE_DEPTH_STENCIL_ATTACHMENT_BIT;
-        if ((properties.optimalTilingFeatures & required) != required) return false;
-
-        // The baked block's layout, and the offsets are not a guess: the generated header
-        // decorates its members at 0 / 16 / 32 / 40, which is where a vec4, a vec4, an int
-        // and an 8-byte-aligned ivec2 land. The pad is what makes the C++ agree.
-        struct Constants {
-            float srcRect[4];
-            float dstRect[4];
-            Int32 surfaceTransform;
-            Int32 reservedForIvec2Alignment;
-            Int32 srcTexelSize[2];
-        };
-        static_assert(sizeof(Constants) == 48);
-        static_assert(offsetof(Constants, srcTexelSize) == 40);
-
-        if (!m_wireDepthMipmapResources) {
-            m_wireDepthMipmapResources = new WireDepthMipmapResources;
-            auto& cache = *m_wireDepthMipmapResources;
-            const auto shader = [&](const Uint32* code, SizeT bytes, VkShaderModule& module) {
-                VkShaderModuleCreateInfo info{VK_STRUCTURE_TYPE_SHADER_MODULE_CREATE_INFO};
-                info.codeSize = bytes;
-                info.pCode = code;
-                VK_VERIFY(vkCreateShaderModule(m_device, &info, nullptr, &module));
-            };
-            shader(kWireDepthMipmapVertexSpirv, sizeof(kWireDepthMipmapVertexSpirv), cache.vertex);
-            shader(kWireDepthMipmapFragmentSpirv, sizeof(kWireDepthMipmapFragmentSpirv), cache.fragment);
-            const VkDescriptorSetLayoutBinding binding{0, VK_DESCRIPTOR_TYPE_COMBINED_IMAGE_SAMPLER,
-                                                       1, VK_SHADER_STAGE_FRAGMENT_BIT, nullptr};
-            VkDescriptorSetLayoutCreateInfo layout{VK_STRUCTURE_TYPE_DESCRIPTOR_SET_LAYOUT_CREATE_INFO};
-            layout.bindingCount = 1;
-            layout.pBindings = &binding;
-            VK_VERIFY(vkCreateDescriptorSetLayout(m_device, &layout, nullptr, &cache.descriptorLayout));
-            // BOTH STAGES ON ONE RANGE: the block is declared identically in the vertex and
-            // fragment sources (a push-constant block must be), the vertex stage reads the
-            // rects and the fragment stage reads srcTexelSize.
-            const VkPushConstantRange push{VK_SHADER_STAGE_VERTEX_BIT | VK_SHADER_STAGE_FRAGMENT_BIT,
-                                           0, sizeof(Constants)};
-            VkPipelineLayoutCreateInfo pipelineLayout{VK_STRUCTURE_TYPE_PIPELINE_LAYOUT_CREATE_INFO};
-            pipelineLayout.setLayoutCount = 1;
-            pipelineLayout.pSetLayouts = &cache.descriptorLayout;
-            pipelineLayout.pushConstantRangeCount = 1;
-            pipelineLayout.pPushConstantRanges = &push;
-            VK_VERIFY(vkCreatePipelineLayout(m_device, &pipelineLayout, nullptr, &cache.pipelineLayout));
-            // NEAREST, and it is not a default: the fragment shader does its own 2x2 box with
-            // texelFetch, so any filtering the sampler added would be applied twice. It also
-            // keeps the sampler legal on a device that does not advertise linear filtering for
-            // depth formats, which is most of them.
-            VkSamplerCreateInfo sampler{VK_STRUCTURE_TYPE_SAMPLER_CREATE_INFO};
-            sampler.mipmapMode = VK_SAMPLER_MIPMAP_MODE_NEAREST;
-            sampler.addressModeU = sampler.addressModeV = sampler.addressModeW =
-                VK_SAMPLER_ADDRESS_MODE_CLAMP_TO_EDGE;
-            sampler.magFilter = sampler.minFilter = VK_FILTER_NEAREST;
-            sampler.maxLod = 0.0f;
-            VK_VERIFY(vkCreateSampler(m_device, &sampler, nullptr, &cache.nearest));
-        }
-        auto& cache = *m_wireDepthMipmapResources;
-
-        const VkImageLayout sourceLayout = sameImage ? VK_IMAGE_LAYOUT_GENERAL
-                                                     : VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL;
-        const VkImageLayout destinationLayout = sameImage ? VK_IMAGE_LAYOUT_GENERAL
-                                                          : VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL;
-        WireDepthMipmapResources::Target* target = nullptr;
-        for (auto& entry : cache.targets) {
-            if (entry.format == destination.format && entry.layout == destinationLayout) {
-                target = &entry;
-                break;
-            }
-        }
-        if (!target) {
-            cache.targets.emplace_back();
-            target = &cache.targets.back();
-            target->format = destination.format;
-            target->layout = destinationLayout;
-            VkAttachmentDescription attachment{};
-            attachment.format = destination.format;
-            attachment.samples = VK_SAMPLE_COUNT_1_BIT;
-            // DONT_CARE, not LOAD: the pass writes gl_FragDepth at every texel of the level
-            // it is producing, so there is nothing in the destination worth loading, and a
-            // level that has just been grown has no defined contents to load anyway.
-            attachment.loadOp = VK_ATTACHMENT_LOAD_OP_DONT_CARE;
-            attachment.storeOp = VK_ATTACHMENT_STORE_OP_STORE;
-            attachment.stencilLoadOp = VK_ATTACHMENT_LOAD_OP_DONT_CARE;
-            attachment.stencilStoreOp = VK_ATTACHMENT_STORE_OP_DONT_CARE;
-            attachment.initialLayout = attachment.finalLayout = destinationLayout;
-            const VkAttachmentReference depth{0, destinationLayout};
-            VkSubpassDescription subpass{};
-            subpass.pipelineBindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS;
-            subpass.pDepthStencilAttachment = &depth;
-            VkRenderPassCreateInfo pass{VK_STRUCTURE_TYPE_RENDER_PASS_CREATE_INFO};
-            pass.attachmentCount = 1;
-            pass.pAttachments = &attachment;
-            pass.subpassCount = 1;
-            pass.pSubpasses = &subpass;
-            VK_VERIFY(vkCreateRenderPass(m_device, &pass, nullptr, &target->renderPass));
-            VkPipelineShaderStageCreateInfo stages[2]{};
-            for (auto& stage : stages) {
-                stage.sType = VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_CREATE_INFO;
-                stage.pName = "main";
-            }
-            stages[0].stage = VK_SHADER_STAGE_VERTEX_BIT;
-            stages[0].module = cache.vertex;
-            stages[1].stage = VK_SHADER_STAGE_FRAGMENT_BIT;
-            stages[1].module = cache.fragment;
-            const VkPipelineVertexInputStateCreateInfo vertex{VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_STATE_CREATE_INFO};
-            VkPipelineInputAssemblyStateCreateInfo assembly{VK_STRUCTURE_TYPE_PIPELINE_INPUT_ASSEMBLY_STATE_CREATE_INFO};
-            assembly.topology = VK_PRIMITIVE_TOPOLOGY_TRIANGLE_LIST;
-            VkPipelineViewportStateCreateInfo viewport{VK_STRUCTURE_TYPE_PIPELINE_VIEWPORT_STATE_CREATE_INFO};
-            viewport.viewportCount = viewport.scissorCount = 1;
-            VkPipelineRasterizationStateCreateInfo raster{VK_STRUCTURE_TYPE_PIPELINE_RASTERIZATION_STATE_CREATE_INFO};
-            raster.polygonMode = VK_POLYGON_MODE_FILL;
-            raster.cullMode = VK_CULL_MODE_NONE;
-            raster.frontFace = VK_FRONT_FACE_COUNTER_CLOCKWISE;
-            raster.lineWidth = 1.0f;
-            VkPipelineMultisampleStateCreateInfo samples{VK_STRUCTURE_TYPE_PIPELINE_MULTISAMPLE_STATE_CREATE_INFO};
-            samples.rasterizationSamples = VK_SAMPLE_COUNT_1_BIT;
-            // ALWAYS + write enabled: the fragment shader's gl_FragDepth is the answer, and a
-            // comparison against whatever DONT_CARE left behind would discard some of it.
-            VkPipelineDepthStencilStateCreateInfo depthStencil{VK_STRUCTURE_TYPE_PIPELINE_DEPTH_STENCIL_STATE_CREATE_INFO};
-            depthStencil.depthTestEnable = VK_TRUE;
-            depthStencil.depthWriteEnable = VK_TRUE;
-            depthStencil.depthCompareOp = VK_COMPARE_OP_ALWAYS;
-            depthStencil.minDepthBounds = 0.0f;
-            depthStencil.maxDepthBounds = 1.0f;
-            // No colour attachment in this render pass, so no attachment states either.
-            VkPipelineColorBlendStateCreateInfo blend{VK_STRUCTURE_TYPE_PIPELINE_COLOR_BLEND_STATE_CREATE_INFO};
-            const VkDynamicState dynamicStates[]{VK_DYNAMIC_STATE_VIEWPORT, VK_DYNAMIC_STATE_SCISSOR};
-            VkPipelineDynamicStateCreateInfo dynamic{VK_STRUCTURE_TYPE_PIPELINE_DYNAMIC_STATE_CREATE_INFO};
-            dynamic.dynamicStateCount = 2;
-            dynamic.pDynamicStates = dynamicStates;
-            VkGraphicsPipelineCreateInfo pipeline{VK_STRUCTURE_TYPE_GRAPHICS_PIPELINE_CREATE_INFO};
-            pipeline.stageCount = 2;
-            pipeline.pStages = stages;
-            pipeline.pVertexInputState = &vertex;
-            pipeline.pInputAssemblyState = &assembly;
-            pipeline.pViewportState = &viewport;
-            pipeline.pRasterizationState = &raster;
-            pipeline.pMultisampleState = &samples;
-            pipeline.pDepthStencilState = &depthStencil;
-            pipeline.pColorBlendState = &blend;
-            pipeline.pDynamicState = &dynamic;
-            pipeline.layout = cache.pipelineLayout;
-            pipeline.renderPass = target->renderPass;
-            VK_VERIFY(vkCreateGraphicsPipelines(m_device, VK_NULL_HANDLE, 1, &pipeline, nullptr, &target->pipeline));
-        }
-
-        m_textureManager->FlushPendingUploads();
-        // Distinct mip views of the same image are legal shader input and output at once.
-        // GENERAL keeps the whole-image layout tracker truthful; the transition also orders
-        // the previous level's attachment write against this level's sample of it.
-        TransitionWireImage(source, sourceLayout);
-        if (sameImage) destination.layout = source.layout;
-        else TransitionWireImage(destination, destinationLayout);
-        const auto makeView = [&](const WireImage& image) {
-            VkImageViewCreateInfo view{VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO};
-            view.image = image.image;
-            view.viewType = VK_IMAGE_VIEW_TYPE_2D;
-            view.format = image.format;
-            view.subresourceRange = {VK_IMAGE_ASPECT_DEPTH_BIT, image.level, 1, image.layer, 1};
-            VkImageView handle = VK_NULL_HANDLE;
-            VK_VERIFY(vkCreateImageView(m_device, &view, nullptr, &handle));
-            return handle;
-        };
-        const VkImageView sourceView = makeView(source), destinationView = makeView(destination);
-        VkFramebufferCreateInfo framebufferInfo{VK_STRUCTURE_TYPE_FRAMEBUFFER_CREATE_INFO};
-        framebufferInfo.renderPass = target->renderPass;
-        framebufferInfo.attachmentCount = 1;
-        framebufferInfo.pAttachments = &destinationView;
-        framebufferInfo.width = destination.extent.width;
-        framebufferInfo.height = destination.extent.height;
-        framebufferInfo.layers = 1;
-        VkFramebuffer framebuffer = VK_NULL_HANDLE;
-        VK_VERIFY(vkCreateFramebuffer(m_device, &framebufferInfo, nullptr, &framebuffer));
-        // Each in-flight pass owns its descriptor set, for the colour blit's reason: updating
-        // a cached set would rewrite the source view of an older queued pass.
-        VkDescriptorPool descriptorPool = VK_NULL_HANDLE;
-        VkDescriptorSet descriptorSet = VK_NULL_HANDLE;
-        const VkDescriptorPoolSize poolSize{VK_DESCRIPTOR_TYPE_COMBINED_IMAGE_SAMPLER, 1};
-        VkDescriptorPoolCreateInfo pool{VK_STRUCTURE_TYPE_DESCRIPTOR_POOL_CREATE_INFO};
-        pool.maxSets = 1;
-        pool.poolSizeCount = 1;
-        pool.pPoolSizes = &poolSize;
-        VK_VERIFY(vkCreateDescriptorPool(m_device, &pool, nullptr, &descriptorPool));
-        VkDescriptorSetAllocateInfo alloc{VK_STRUCTURE_TYPE_DESCRIPTOR_SET_ALLOCATE_INFO};
-        alloc.descriptorPool = descriptorPool;
-        alloc.descriptorSetCount = 1;
-        alloc.pSetLayouts = &cache.descriptorLayout;
-        VK_VERIFY(vkAllocateDescriptorSets(m_device, &alloc, &descriptorSet));
-        const VkDescriptorImageInfo sampled{cache.nearest, sourceView, sourceLayout};
-        VkWriteDescriptorSet write{VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET};
-        write.dstSet = descriptorSet;
-        write.dstBinding = 0;
-        write.descriptorCount = 1;
-        write.descriptorType = VK_DESCRIPTOR_TYPE_COMBINED_IMAGE_SAMPLER;
-        write.pImageInfo = &sampled;
-        vkUpdateDescriptorSets(m_device, 1, &write, 0, nullptr);
-
-        // The destination rectangle is flipped exactly as BlitWireColorImage flips it for an
-        // offscreen target, because it shares that file's vertex shader and therefore its
-        // window-Y flip. With the flip undone, destination row r samples texCoord.y
-        // (r + 0.5) / dstHeight, and the fragment's ivec2(texCoord * srcTexelSize) lands on
-        // the same source texels the monolith arm's fullscreen triangle lands on - which is
-        // the point: §3.2 retires a refusal by making the wire arm observably the monolith's,
-        // half-texel offset included.
-        const Constants constants{
-            {0.0f, 0.0f, 1.0f, 1.0f},
-            {0.0f, 1.0f, 1.0f, -1.0f},
-            0, 0,
-            {static_cast<Int32>(source.extent.width), static_cast<Int32>(source.extent.height)}};
-        auto& frame = m_frameContext.GetCurrent();
-        VkRenderPassBeginInfo begin{VK_STRUCTURE_TYPE_RENDER_PASS_BEGIN_INFO};
-        begin.renderPass = target->renderPass;
-        begin.framebuffer = framebuffer;
-        begin.renderArea = {{0, 0}, destination.extent};
-        vkCmdBeginRenderPass(frame.commandBuffer, &begin, VK_SUBPASS_CONTENTS_INLINE);
-        vkCmdBindPipeline(frame.commandBuffer, VK_PIPELINE_BIND_POINT_GRAPHICS, target->pipeline);
-        const VkViewport viewport{0.0f, 0.0f, static_cast<float>(destination.extent.width),
-                                  static_cast<float>(destination.extent.height), 0.0f, 1.0f};
-        const VkRect2D scissor{{0, 0}, destination.extent};
-        vkCmdSetViewport(frame.commandBuffer, 0, 1, &viewport);
-        vkCmdSetScissor(frame.commandBuffer, 0, 1, &scissor);
-        vkCmdBindDescriptorSets(frame.commandBuffer, VK_PIPELINE_BIND_POINT_GRAPHICS,
-                                cache.pipelineLayout, 0, 1, &descriptorSet, 0, nullptr);
-        vkCmdPushConstants(frame.commandBuffer, cache.pipelineLayout,
-                           VK_SHADER_STAGE_VERTEX_BIT | VK_SHADER_STAGE_FRAGMENT_BIT,
-                           0, sizeof(constants), &constants);
-        vkCmdDraw(frame.commandBuffer, 6, 1, 0, 0);
-        vkCmdEndRenderPass(frame.commandBuffer);
-        ResetDynamicStateShadow();
-        InvalidatePipelineMemo();
-        // This native pass binds its own set/layout without going through the application's
-        // descriptor binder. Its next fast path must rebind.
-        if (m_uniformManager) m_uniformManager->OnCommandBufferBoundary();
-        WireRetiredObjects retired{};
-        retired.framebuffers.push_back(framebuffer);
-        retired.imageViews = {sourceView, destinationView};
-        retired.descriptorPools.push_back(descriptorPool);
-        RetireWireObjects(Move(retired));
-        return true;
-    }
-#endif

MobileGL/MG_Backend/DirectVulkan/Renderer/WireDepthMipmap.vert

@@ -1,33 +0,0 @@
-#version 450
-// Native Vulkan depth mip generation: no GL program, registry entry, or runtime transpilation.
-//
-// The geometry is WireColorBlit.vert's, unchanged - the same quad, the same push-constant
-// rect, the same GL-bottom-left to native-image mapping - so a depth mip and a colour blit
-// place their fragments identically and only the fragment stage differs. The block carries
-// one member more than the colour blit's, and the fragment stage is the member's only
-// reader: a push-constant block must be declared identically in every stage of one pipeline,
-// so it is declared here too rather than split into a second range.
-layout(push_constant) uniform DepthMipmapRect {
-    vec4 srcRect;
-    vec4 dstRect;
-    int surfaceTransform;
-    ivec2 srcTexelSize;
-} rect;
-layout(location = 0) out vec2 texCoord;
-
-void main() {
-    // A quad, rather than an oversized triangle, also clips partial blits to
-    // their destination rectangle. The Vulkan viewport covers the native image.
-    const vec2 corners[6] = vec2[](
-        vec2(0.0, 0.0), vec2(1.0, 0.0), vec2(0.0, 1.0),
-        vec2(0.0, 1.0), vec2(1.0, 0.0), vec2(1.0, 1.0));
-    vec2 uv = corners[gl_VertexIndex];
-    vec2 p = (rect.dstRect.xy + uv * rect.dstRect.zw) * 2.0 - 1.0;
-    // Same GL-bottom-left to native-image mapping as the monolithic blit.
-    p.y = -p.y;
-    if (rect.surfaceTransform == 1) p = vec2(-p.y, p.x);
-    else if (rect.surfaceTransform == 2) p = -p;
-    else if (rect.surfaceTransform == 3) p = vec2(p.y, -p.x);
-    gl_Position = vec4(p, 0.0, 1.0);
-    texCoord = rect.srcRect.xy + uv * rect.srcRect.zw;
-}

MobileGL/MG_Backend/DirectVulkan/Renderer/WireDepthMipmapSpirv.h

@@ -1,174 +0,0 @@
-// Generated from WireDepthMipmap.vert / WireDepthMipmap.frag by
-// scripts/bake_internal_shaders.py, which runs MG_Test's BakedInternalShadersTest with the
-// IN-TREE glslang and splices the words it emits into the arrays below. Do not edit the
-// words by hand: MOBILEGL_BAKED_INTERNAL_SHADERS (the same test, run as a gate) recompiles
-// every source in its table and reds on the first word that disagrees.
-#pragma once
-
-static constexpr Uint32 kWireDepthMipmapVertexSpirv[] = {
-    0x07230203u, 0x00010000u, 0x0008000bu, 0x00000071u, 0x00000000u, 0x00020011u, 0x00000001u, 0x0006000bu,
-    0x00000001u, 0x4c534c47u, 0x6474732eu, 0x3035342eu, 0x00000000u, 0x0003000eu, 0x00000000u, 0x00000001u,
-    0x0008000fu, 0x00000000u, 0x00000004u, 0x6e69616du, 0x00000000u, 0x00000016u, 0x0000005eu, 0x00000067u,
-    0x00030003u, 0x00000002u, 0x000001c2u, 0x00040005u, 0x00000004u, 0x6e69616du, 0x00000000u, 0x00030005u,
-    0x00000009u, 0x00007675u, 0x00060005u, 0x00000016u, 0x565f6c67u, 0x65747265u, 0x646e4978u, 0x00007865u,
-    0x00050005u, 0x00000019u, 0x65646e69u, 0x6c626178u, 0x00000065u, 0x00030005u, 0x0000001cu, 0x00000070u,
-    0x00060005u, 0x0000001fu, 0x74706544u, 0x70694d68u, 0x5270616du, 0x00746365u, 0x00050006u, 0x0000001fu,
-    0x00000000u, 0x52637273u, 0x00746365u, 0x00050006u, 0x0000001fu, 0x00000001u, 0x52747364u, 0x00746365u,
-    0x00080006u, 0x0000001fu, 0x00000002u, 0x66727573u, 0x54656361u, 0x736e6172u, 0x6d726f66u, 0x00000000u,
-    0x00070006u, 0x0000001fu, 0x00000003u, 0x54637273u, 0x6c657865u, 0x657a6953u, 0x00000000u, 0x00040005u,
-    0x00000021u, 0x74636572u, 0x00000000u, 0x00060005u, 0x0000005cu, 0x505f6c67u, 0x65567265u, 0x78657472u,
-    0x00000000u, 0x00060006u, 0x0000005cu, 0x00000000u, 0x505f6c67u, 0x7469736fu, 0x006e6f69u, 0x00070006u,
-    0x0000005cu, 0x00000001u, 0x505f6c67u, 0x746e696fu, 0x657a6953u, 0x00000000u, 0x00070006u, 0x0000005cu,
-    0x00000002u, 0x435f6c67u, 0x4470696cu, 0x61747369u, 0x0065636eu, 0x00070006u, 0x0000005cu, 0x00000003u,
-    0x435f6c67u, 0x446c6c75u, 0x61747369u, 0x0065636eu, 0x00030005u, 0x0000005eu, 0x00000000u, 0x00050005u,
-    0x00000067u, 0x43786574u, 0x64726f6fu, 0x00000000u, 0x00040047u, 0x00000016u, 0x0000000bu, 0x0000002au,
-    0x00030047u, 0x0000001fu, 0x00000002u, 0x00050048u, 0x0000001fu, 0x00000000u, 0x00000023u, 0x00000000u,
-    0x00050048u, 0x0000001fu, 0x00000001u, 0x00000023u, 0x00000010u, 0x00050048u, 0x0000001fu, 0x00000002u,
-    0x00000023u, 0x00000020u, 0x00050048u, 0x0000001fu, 0x00000003u, 0x00000023u, 0x00000028u, 0x00030047u,
-    0x0000005cu, 0x00000002u, 0x00050048u, 0x0000005cu, 0x00000000u, 0x0000000bu, 0x00000000u, 0x00050048u,
-    0x0000005cu, 0x00000001u, 0x0000000bu, 0x00000001u, 0x00050048u, 0x0000005cu, 0x00000002u, 0x0000000bu,
-    0x00000003u, 0x00050048u, 0x0000005cu, 0x00000003u, 0x0000000bu, 0x00000004u, 0x00040047u, 0x00000067u,
-    0x0000001eu, 0x00000000u, 0x00020013u, 0x00000002u, 0x00030021u, 0x00000003u, 0x00000002u, 0x00030016u,
-    0x00000006u, 0x00000020u, 0x00040017u, 0x00000007u, 0x00000006u, 0x00000002u, 0x00040020u, 0x00000008u,
-    0x00000007u, 0x00000007u, 0x00040015u, 0x0000000au, 0x00000020u, 0x00000000u, 0x0004002bu, 0x0000000au,
-    0x0000000bu, 0x00000006u, 0x0004001cu, 0x0000000cu, 0x00000007u, 0x0000000bu, 0x0004002bu, 0x00000006u,
-    0x0000000du, 0x00000000u, 0x0005002cu, 0x00000007u, 0x0000000eu, 0x0000000du, 0x0000000du, 0x0004002bu,
-    0x00000006u, 0x0000000fu, 0x3f800000u, 0x0005002cu, 0x00000007u, 0x00000010u, 0x0000000fu, 0x0000000du,
-    0x0005002cu, 0x00000007u, 0x00000011u, 0x0000000du, 0x0000000fu, 0x0005002cu, 0x00000007u, 0x00000012u,
-    0x0000000fu, 0x0000000fu, 0x0009002cu, 0x0000000cu, 0x00000013u, 0x0000000eu, 0x00000010u, 0x00000011u,
-    0x00000011u, 0x00000010u, 0x00000012u, 0x00040015u, 0x00000014u, 0x00000020u, 0x00000001u, 0x00040020u,
-    0x00000015u, 0x00000001u, 0x00000014u, 0x0004003bu, 0x00000015u, 0x00000016u, 0x00000001u, 0x00040020u,
-    0x00000018u, 0x00000007u, 0x0000000cu, 0x00040017u, 0x0000001du, 0x00000006u, 0x00000004u, 0x00040017u,
-    0x0000001eu, 0x00000014u, 0x00000002u, 0x0006001eu, 0x0000001fu, 0x0000001du, 0x0000001du, 0x00000014u,
-    0x0000001eu, 0x00040020u, 0x00000020u, 0x00000009u, 0x0000001fu, 0x0004003bu, 0x00000020u, 0x00000021u,
-    0x00000009u, 0x0004002bu, 0x00000014u, 0x00000022u, 0x00000001u, 0x00040020u, 0x00000023u, 0x00000009u,
-    0x0000001du, 0x0004002bu, 0x00000006u, 0x0000002du, 0x40000000u, 0x0004002bu, 0x0000000au, 0x00000031u,
-    0x00000001u, 0x00040020u, 0x00000032u, 0x00000007u, 0x00000006u, 0x0004002bu, 0x00000014u, 0x00000037u,
-    0x00000002u, 0x00040020u, 0x00000038u, 0x00000009u, 0x00000014u, 0x00020014u, 0x0000003bu, 0x0004002bu,
-    0x0000000au, 0x00000042u, 0x00000000u, 0x0004002bu, 0x00000014u, 0x00000051u, 0x00000003u, 0x0004001cu,
-    0x0000005bu, 0x00000006u, 0x00000031u, 0x0006001eu, 0x0000005cu, 0x0000001du, 0x00000006u, 0x0000005bu,
-    0x0000005bu, 0x00040020u, 0x0000005du, 0x00000003u, 0x0000005cu, 0x0004003bu, 0x0000005du, 0x0000005eu,
-    0x00000003u, 0x0004002bu, 0x00000014u, 0x0000005fu, 0x00000000u, 0x00040020u, 0x00000064u, 0x00000003u,
-    0x0000001du, 0x00040020u, 0x00000066u, 0x00000003u, 0x00000007u, 0x0004003bu, 0x00000066u, 0x00000067u,
-    0x00000003u, 0x00050036u, 0x00000002u, 0x00000004u, 0x00000000u, 0x00000003u, 0x000200f8u, 0x00000005u,
-    0x0004003bu, 0x00000008u, 0x00000009u, 0x00000007u, 0x0004003bu, 0x00000018u, 0x00000019u, 0x00000007u,
-    0x0004003bu, 0x00000008u, 0x0000001cu, 0x00000007u, 0x0004003du, 0x00000014u, 0x00000017u, 0x00000016u,
-    0x0003003eu, 0x00000019u, 0x00000013u, 0x00050041u, 0x00000008u, 0x0000001au, 0x00000019u, 0x00000017u,
-    0x0004003du, 0x00000007u, 0x0000001bu, 0x0000001au, 0x0003003eu, 0x00000009u, 0x0000001bu, 0x00050041u,
-    0x00000023u, 0x00000024u, 0x00000021u, 0x00000022u, 0x0004003du, 0x0000001du, 0x00000025u, 0x00000024u,
-    0x0007004fu, 0x00000007u, 0x00000026u, 0x00000025u, 0x00000025u, 0x00000000u, 0x00000001u, 0x0004003du,
-    0x00000007u, 0x00000027u, 0x00000009u, 0x00050041u, 0x00000023u, 0x00000028u, 0x00000021u, 0x00000022u,
-    0x0004003du, 0x0000001du, 0x00000029u, 0x00000028u, 0x0007004fu, 0x00000007u, 0x0000002au, 0x00000029u,
-    0x00000029u, 0x00000002u, 0x00000003u, 0x00050085u, 0x00000007u, 0x0000002bu, 0x00000027u, 0x0000002au,
-    0x00050081u, 0x00000007u, 0x0000002cu, 0x00000026u, 0x0000002bu, 0x0005008eu, 0x00000007u, 0x0000002eu,
-    0x0000002cu, 0x0000002du, 0x00050050u, 0x00000007u, 0x0000002fu, 0x0000000fu, 0x0000000fu, 0x00050083u,
-    0x00000007u, 0x00000030u, 0x0000002eu, 0x0000002fu, 0x0003003eu, 0x0000001cu, 0x00000030u, 0x00050041u,
-    0x00000032u, 0x00000033u, 0x0000001cu, 0x00000031u, 0x0004003du, 0x00000006u, 0x00000034u, 0x00000033u,
-    0x0004007fu, 0x00000006u, 0x00000035u, 0x00000034u, 0x00050041u, 0x00000032u, 0x00000036u, 0x0000001cu,
-    0x00000031u, 0x0003003eu, 0x00000036u, 0x00000035u, 0x00050041u, 0x00000038u, 0x00000039u, 0x00000021u,
-    0x00000037u, 0x0004003du, 0x00000014u, 0x0000003au, 0x00000039u, 0x000500aau, 0x0000003bu, 0x0000003cu,
-    0x0000003au, 0x00000022u, 0x000300f7u, 0x0000003eu, 0x00000000u, 0x000400fau, 0x0000003cu, 0x0000003du,
-    0x00000046u, 0x000200f8u, 0x0000003du, 0x00050041u, 0x00000032u, 0x0000003fu, 0x0000001cu, 0x00000031u,
-    0x0004003du, 0x00000006u, 0x00000040u, 0x0000003fu, 0x0004007fu, 0x00000006u, 0x00000041u, 0x00000040u,
-    0x00050041u, 0x00000032u, 0x00000043u, 0x0000001cu, 0x00000042u, 0x0004003du, 0x00000006u, 0x00000044u,
-    0x00000043u, 0x00050050u, 0x00000007u, 0x00000045u, 0x00000041u, 0x00000044u, 0x0003003eu, 0x0000001cu,
-    0x00000045u, 0x000200f9u, 0x0000003eu, 0x000200f8u, 0x00000046u, 0x00050041u, 0x00000038u, 0x00000047u,
-    0x00000021u, 0x00000037u, 0x0004003du, 0x00000014u, 0x00000048u, 0x00000047u, 0x000500aau, 0x0000003bu,
-    0x00000049u, 0x00000048u, 0x00000037u, 0x000300f7u, 0x0000004bu, 0x00000000u, 0x000400fau, 0x00000049u,
-    0x0000004au, 0x0000004eu, 0x000200f8u, 0x0000004au, 0x0004003du, 0x00000007u, 0x0000004cu, 0x0000001cu,
-    0x0004007fu, 0x00000007u, 0x0000004du, 0x0000004cu, 0x0003003eu, 0x0000001cu, 0x0000004du, 0x000200f9u,
-    0x0000004bu, 0x000200f8u, 0x0000004eu, 0x00050041u, 0x00000038u, 0x0000004fu, 0x00000021u, 0x00000037u,
-    0x0004003du, 0x00000014u, 0x00000050u, 0x0000004fu, 0x000500aau, 0x0000003bu, 0x00000052u, 0x00000050u,
-    0x00000051u, 0x000300f7u, 0x00000054u, 0x00000000u, 0x000400fau, 0x00000052u, 0x00000053u, 0x00000054u,
-    0x000200f8u, 0x00000053u, 0x00050041u, 0x00000032u, 0x00000055u, 0x0000001cu, 0x00000031u, 0x0004003du,
-    0x00000006u, 0x00000056u, 0x00000055u, 0x00050041u, 0x00000032u, 0x00000057u, 0x0000001cu, 0x00000042u,
-    0x0004003du, 0x00000006u, 0x00000058u, 0x00000057u, 0x0004007fu, 0x00000006u, 0x00000059u, 0x00000058u,
-    0x00050050u, 0x00000007u, 0x0000005au, 0x00000056u, 0x00000059u, 0x0003003eu, 0x0000001cu, 0x0000005au,
-    0x000200f9u, 0x00000054u, 0x000200f8u, 0x00000054u, 0x000200f9u, 0x0000004bu, 0x000200f8u, 0x0000004bu,
-    0x000200f9u, 0x0000003eu, 0x000200f8u, 0x0000003eu, 0x0004003du, 0x00000007u, 0x00000060u, 0x0000001cu,
-    0x00050051u, 0x00000006u, 0x00000061u, 0x00000060u, 0x00000000u, 0x00050051u, 0x00000006u, 0x00000062u,
-    0x00000060u, 0x00000001u, 0x00070050u, 0x0000001du, 0x00000063u, 0x00000061u, 0x00000062u, 0x0000000du,
-    0x0000000fu, 0x00050041u, 0x00000064u, 0x00000065u, 0x0000005eu, 0x0000005fu, 0x0003003eu, 0x00000065u,
-    0x00000063u, 0x00050041u, 0x00000023u, 0x00000068u, 0x00000021u, 0x0000005fu, 0x0004003du, 0x0000001du,
-    0x00000069u, 0x00000068u, 0x0007004fu, 0x00000007u, 0x0000006au, 0x00000069u, 0x00000069u, 0x00000000u,
-    0x00000001u, 0x0004003du, 0x00000007u, 0x0000006bu, 0x00000009u, 0x00050041u, 0x00000023u, 0x0000006cu,
-    0x00000021u, 0x0000005fu, 0x0004003du, 0x0000001du, 0x0000006du, 0x0000006cu, 0x0007004fu, 0x00000007u,
-    0x0000006eu, 0x0000006du, 0x0000006du, 0x00000002u, 0x00000003u, 0x00050085u, 0x00000007u, 0x0000006fu,
-    0x0000006bu, 0x0000006eu, 0x00050081u, 0x00000007u, 0x00000070u, 0x0000006au, 0x0000006fu, 0x0003003eu,
-    0x00000067u, 0x00000070u, 0x000100fdu, 0x00010038u,
-};
-
-static constexpr Uint32 kWireDepthMipmapFragmentSpirv[] = {
-    0x07230203u, 0x00010000u, 0x0008000bu, 0x00000059u, 0x00000000u, 0x00020011u, 0x00000001u, 0x0006000bu,
-    0x00000001u, 0x4c534c47u, 0x6474732eu, 0x3035342eu, 0x00000000u, 0x0003000eu, 0x00000000u, 0x00000001u,
-    0x0007000fu, 0x00000004u, 0x00000004u, 0x6e69616du, 0x00000000u, 0x0000000du, 0x0000004fu, 0x00030010u,
-    0x00000004u, 0x00000007u, 0x00030010u, 0x00000004u, 0x0000000cu, 0x00030003u, 0x00000002u, 0x000001c2u,
-    0x00040005u, 0x00000004u, 0x6e69616du, 0x00000000u, 0x00040005u, 0x00000009u, 0x42637273u, 0x00657361u,
-    0x00050005u, 0x0000000du, 0x43786574u, 0x64726f6fu, 0x00000000u, 0x00060005u, 0x00000010u, 0x74706544u,
-    0x70694d68u, 0x5270616du, 0x00746365u, 0x00050006u, 0x00000010u, 0x00000000u, 0x52637273u, 0x00746365u,
-    0x00050006u, 0x00000010u, 0x00000001u, 0x52747364u, 0x00746365u, 0x00080006u, 0x00000010u, 0x00000002u,
-    0x66727573u, 0x54656361u, 0x736e6172u, 0x6d726f66u, 0x00000000u, 0x00070006u, 0x00000010u, 0x00000003u,
-    0x54637273u, 0x6c657865u, 0x657a6953u, 0x00000000u, 0x00040005u, 0x00000012u, 0x74636572u, 0x00000000u,
-    0x00040005u, 0x0000001au, 0x4d637273u, 0x00007861u, 0x00040005u, 0x00000021u, 0x74706564u, 0x00003068u,
-    0x00050005u, 0x00000025u, 0x72756f73u, 0x6d496563u, 0x00656761u, 0x00040005u, 0x00000031u, 0x74706564u,
-    0x00003168u, 0x00040005u, 0x0000003bu, 0x74706564u, 0x00003268u, 0x00040005u, 0x00000045u, 0x74706564u,
-    0x00003368u, 0x00060005u, 0x0000004fu, 0x465f6c67u, 0x44676172u, 0x68747065u, 0x00000000u, 0x00040047u,
-    0x0000000du, 0x0000001eu, 0x00000000u, 0x00030047u, 0x00000010u, 0x00000002u, 0x00050048u, 0x00000010u,
-    0x00000000u, 0x00000023u, 0x00000000u, 0x00050048u, 0x00000010u, 0x00000001u, 0x00000023u, 0x00000010u,
-    0x00050048u, 0x00000010u, 0x00000002u, 0x00000023u, 0x00000020u, 0x00050048u, 0x00000010u, 0x00000003u,
-    0x00000023u, 0x00000028u, 0x00040047u, 0x00000025u, 0x00000021u, 0x00000000u, 0x00040047u, 0x00000025u,
-    0x00000022u, 0x00000000u, 0x00040047u, 0x0000004fu, 0x0000000bu, 0x00000016u, 0x00020013u, 0x00000002u,
-    0x00030021u, 0x00000003u, 0x00000002u, 0x00040015u, 0x00000006u, 0x00000020u, 0x00000001u, 0x00040017u,
-    0x00000007u, 0x00000006u, 0x00000002u, 0x00040020u, 0x00000008u, 0x00000007u, 0x00000007u, 0x00030016u,
-    0x0000000au, 0x00000020u, 0x00040017u, 0x0000000bu, 0x0000000au, 0x00000002u, 0x00040020u, 0x0000000cu,
-    0x00000001u, 0x0000000bu, 0x0004003bu, 0x0000000cu, 0x0000000du, 0x00000001u, 0x00040017u, 0x0000000fu,
-    0x0000000au, 0x00000004u, 0x0006001eu, 0x00000010u, 0x0000000fu, 0x0000000fu, 0x00000006u, 0x00000007u,
-    0x00040020u, 0x00000011u, 0x00000009u, 0x00000010u, 0x0004003bu, 0x00000011u, 0x00000012u, 0x00000009u,
-    0x0004002bu, 0x00000006u, 0x00000013u, 0x00000003u, 0x00040020u, 0x00000014u, 0x00000009u, 0x00000007u,
-    0x0004002bu, 0x00000006u, 0x0000001du, 0x00000001u, 0x0005002cu, 0x00000007u, 0x0000001eu, 0x0000001du,
-    0x0000001du, 0x00040020u, 0x00000020u, 0x00000007u, 0x0000000au, 0x00090019u, 0x00000022u, 0x0000000au,
-    0x00000001u, 0x00000000u, 0x00000000u, 0x00000000u, 0x00000001u, 0x00000000u, 0x0003001bu, 0x00000023u,
-    0x00000022u, 0x00040020u, 0x00000024u, 0x00000000u, 0x00000023u, 0x0004003bu, 0x00000024u, 0x00000025u,
-    0x00000000u, 0x0004002bu, 0x00000006u, 0x00000028u, 0x00000000u, 0x0005002cu, 0x00000007u, 0x00000029u,
-    0x00000028u, 0x00000028u, 0x00040015u, 0x0000002eu, 0x00000020u, 0x00000000u, 0x0004002bu, 0x0000002eu,
-    0x0000002fu, 0x00000000u, 0x0005002cu, 0x00000007u, 0x00000034u, 0x0000001du, 0x00000028u, 0x0005002cu,
-    0x00000007u, 0x0000003eu, 0x00000028u, 0x0000001du, 0x00040020u, 0x0000004eu, 0x00000003u, 0x0000000au,
-    0x0004003bu, 0x0000004eu, 0x0000004fu, 0x00000003u, 0x0004002bu, 0x0000000au, 0x00000050u, 0x3e800000u,
-    0x00050036u, 0x00000002u, 0x00000004u, 0x00000000u, 0x00000003u, 0x000200f8u, 0x00000005u, 0x0004003bu,
-    0x00000008u, 0x00000009u, 0x00000007u, 0x0004003bu, 0x00000008u, 0x0000001au, 0x00000007u, 0x0004003bu,
-    0x00000020u, 0x00000021u, 0x00000007u, 0x0004003bu, 0x00000020u, 0x00000031u, 0x00000007u, 0x0004003bu,
-    0x00000020u, 0x0000003bu, 0x00000007u, 0x0004003bu, 0x00000020u, 0x00000045u, 0x00000007u, 0x0004003du,
-    0x0000000bu, 0x0000000eu, 0x0000000du, 0x00050041u, 0x00000014u, 0x00000015u, 0x00000012u, 0x00000013u,
-    0x0004003du, 0x00000007u, 0x00000016u, 0x00000015u, 0x0004006fu, 0x0000000bu, 0x00000017u, 0x00000016u,
-    0x00050085u, 0x0000000bu, 0x00000018u, 0x0000000eu, 0x00000017u, 0x0004006eu, 0x00000007u, 0x00000019u,
-    0x00000018u, 0x0003003eu, 0x00000009u, 0x00000019u, 0x00050041u, 0x00000014u, 0x0000001bu, 0x00000012u,
-    0x00000013u, 0x0004003du, 0x00000007u, 0x0000001cu, 0x0000001bu, 0x00050082u, 0x00000007u, 0x0000001fu,
-    0x0000001cu, 0x0000001eu, 0x0003003eu, 0x0000001au, 0x0000001fu, 0x0004003du, 0x00000023u, 0x00000026u,
-    0x00000025u, 0x0004003du, 0x00000007u, 0x00000027u, 0x00000009u, 0x0004003du, 0x00000007u, 0x0000002au,
-    0x0000001au, 0x0008000cu, 0x00000007u, 0x0000002bu, 0x00000001u, 0x0000002du, 0x00000027u, 0x00000029u,
-    0x0000002au, 0x00040064u, 0x00000022u, 0x0000002cu, 0x00000026u, 0x0007005fu, 0x0000000fu, 0x0000002du,
-    0x0000002cu, 0x0000002bu, 0x00000002u, 0x00000028u, 0x00050051u, 0x0000000au, 0x00000030u, 0x0000002du,
-    0x00000000u, 0x0003003eu, 0x00000021u, 0x00000030u, 0x0004003du, 0x00000023u, 0x00000032u, 0x00000025u,
-    0x0004003du, 0x00000007u, 0x00000033u, 0x00000009u, 0x00050080u, 0x00000007u, 0x00000035u, 0x00000033u,
-    0x00000034u, 0x0004003du, 0x00000007u, 0x00000036u, 0x0000001au, 0x0008000cu, 0x00000007u, 0x00000037u,
-    0x00000001u, 0x0000002du, 0x00000035u, 0x00000029u, 0x00000036u, 0x00040064u, 0x00000022u, 0x00000038u,
-    0x00000032u, 0x0007005fu, 0x0000000fu, 0x00000039u, 0x00000038u, 0x00000037u, 0x00000002u, 0x00000028u,
-    0x00050051u, 0x0000000au, 0x0000003au, 0x00000039u, 0x00000000u, 0x0003003eu, 0x00000031u, 0x0000003au,
-    0x0004003du, 0x00000023u, 0x0000003cu, 0x00000025u, 0x0004003du, 0x00000007u, 0x0000003du, 0x00000009u,
-    0x00050080u, 0x00000007u, 0x0000003fu, 0x0000003du, 0x0000003eu, 0x0004003du, 0x00000007u, 0x00000040u,
-    0x0000001au, 0x0008000cu, 0x00000007u, 0x00000041u, 0x00000001u, 0x0000002du, 0x0000003fu, 0x00000029u,
-    0x00000040u, 0x00040064u, 0x00000022u, 0x00000042u, 0x0000003cu, 0x0007005fu, 0x0000000fu, 0x00000043u,
-    0x00000042u, 0x00000041u, 0x00000002u, 0x00000028u, 0x00050051u, 0x0000000au, 0x00000044u, 0x00000043u,
-    0x00000000u, 0x0003003eu, 0x0000003bu, 0x00000044u, 0x0004003du, 0x00000023u, 0x00000046u, 0x00000025u,
-    0x0004003du, 0x00000007u, 0x00000047u, 0x00000009u, 0x00050080u, 0x00000007u, 0x00000048u, 0x00000047u,
-    0x0000001eu, 0x0004003du, 0x00000007u, 0x00000049u, 0x0000001au, 0x0008000cu, 0x00000007u, 0x0000004au,
-    0x00000001u, 0x0000002du, 0x00000048u, 0x00000029u, 0x00000049u, 0x00040064u, 0x00000022u, 0x0000004bu,
-    0x00000046u, 0x0007005fu, 0x0000000fu, 0x0000004cu, 0x0000004bu, 0x0000004au, 0x00000002u, 0x00000028u,
-    0x00050051u, 0x0000000au, 0x0000004du, 0x0000004cu, 0x00000000u, 0x0003003eu, 0x00000045u, 0x0000004du,
-    0x0004003du, 0x0000000au, 0x00000051u, 0x00000021u, 0x0004003du, 0x0000000au, 0x00000052u, 0x00000031u,
-    0x00050081u, 0x0000000au, 0x00000053u, 0x00000051u, 0x00000052u, 0x0004003du, 0x0000000au, 0x00000054u,
-    0x0000003bu, 0x00050081u, 0x0000000au, 0x00000055u, 0x00000053u, 0x00000054u, 0x0004003du, 0x0000000au,
-    0x00000056u, 0x00000045u, 0x00050081u, 0x0000000au, 0x00000057u, 0x00000055u, 0x00000056u, 0x00050085u,
-    0x0000000au, 0x00000058u, 0x00000050u, 0x00000057u, 0x0003003eu, 0x0000004fu, 0x00000058u, 0x000100fdu,
-    0x00010038u,
-};

MobileGL/MG_Backend/DirectVulkan/Renderer/WireDepthResolveArm.h

@@ -1,329 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/WireDepthResolveArm.h
-// Copyright (c) 2025-2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-#pragma once
-
-#include <Includes.h>
-
-#include <cstring>
-#include <mutex>
-#include <utility>
-
-// P7 gate 5 (g5-msrbo, g5-msprobe): WHICH ARM RESOLVES A MULTISAMPLE DEPTH/STENCIL ASPECT FIRST.
-//
-// The wire arm has two (WireFramebuffer.inc, ResolveWireDepthStencil): a render pass that carries
-// a VK_KHR_depth_stencil_resolve attachment and no draw, and the baked shader pass of
-// WireMultisampleResolve.inc, which draws. P7 wave 2-B2 took the render pass wherever the
-// extension exists. On the Redmi (Adreno 830, Vulkan 1.3.284, driver 512.800.71) that pass left
-// its resolve target unwritten - KHR-GL46.direct_state_access.renderbuffers_storage_multisample
-// read every resolved depth and stencil value back as 0 on the inproc arm while the monolith arm
-// passed, and the same case passed on the device with the shader arm forced
-// (MGITEST_MAGMA_FORCE_SHADER_DEPTH_RESOLVE=1).
-//
-// A DRIVER THAT CLAIMS WHAT IT CANNOT DO IS A POST PROBE, NOT A VENDOR QUIRK (standing rule,
-// 2026-08-22). The first fix keyed the order on Qualcomm's vendor id; it is replaced by a probe
-// that reproduces the production resolve on the actual VkDevice (WireDepthResolveProbe.cpp) and
-// asks the one question the order depends on: does the no-draw render pass write the resolve
-// target? A driver that fixes the defect gets the fast arm back, and a driver of any vendor that
-// has it gets the shader arm - neither needs a table edit.
-//
-// EVERY BUG PROBE CARRIES A CONTROL (MG_Util/SelfTest/DriverBugProbes.h). The control is the
-// production SHADER arm fed the same inputs: when it does not resolve them either, the probe has
-// measured its own setup (or a device that cannot resolve depth at all) rather than the render
-// pass, the verdict is INCONCLUSIVE, and the default order stands.
-//
-// This header is the pure half - the measurement, the verdict, the test knob and the choice - so
-// a unit test pins every mapping with a fake result source (MG_Test/Pipeline/PipelineQuirkTest.cpp).
-// The Vulkan half that fills the measurement is WireDepthResolveProbe.{h,cpp}.
-namespace MobileGL::MG_Backend::DirectVulkan {
-    // One aspect of one probed format, both arms. Values are the RAW aspect words the
-    // buffer copy returns (D16: 16 bits; D24: the low 24 bits of the 32-bit word; D32F: the float's
-    // bits; stencil: 8 bits), compared within `tolerance` (1 LSB for a UNORM depth, 0 otherwise).
-    struct WireDepthResolveAspectReading {
-        // The format has this aspect and the render-pass arm's copy of it was read back.
-        Bool measured = false;
-        Uint32 texels = 0;
-        Uint32 expected = 0;  // the multisample source's cleared value
-        Uint32 sentinel = 0;  // what the resolve target was pre-filled with
-        Uint32 tolerance = 0;
-        // THE SUBJECT: VK_KHR_depth_stencil_resolve render pass, no draw.
-        Uint32 renderPassMatches = 0;   // texels within tolerance of `expected`
-        Uint32 renderPassSentinels = 0; // texels still holding the sentinel
-        Uint32 renderPassFirst = 0;     // texel (0,0)
-        // THE CONTROL: the production shader pass, same inputs. False where it cannot run for this
-        // aspect (a stencil aspect without VK_EXT_shader_stencil_export, a failed pipeline).
-        Bool shaderRan = false;
-        Uint32 shaderMatches = 0;
-        Uint32 shaderFirst = 0;
-    };
-
-    struct WireDepthResolveFormatReading {
-        String name;          // e.g. "D24_UNORM_S8_UINT"
-        Int32 format = 0;     // the VkFormat
-        Uint32 samples = 0;
-        // False when the format was not probed; `skipReason` says why (unsupported, the render-pass
-        // arm would not be taken for it, an object the probe needed could not be created).
-        Bool ran = false;
-        String skipReason;
-        WireDepthResolveAspectReading depth, stencil;
-    };
-
-    struct WireDepthResolveProbeMeasurement {
-        // At least one format was recorded, submitted and read back.
-        Bool ran = false;
-        // The bounded fence wait expired: every object the probe created was deliberately leaked
-        // (the queue may still be executing it), and nothing was read back.
-        Bool fenceWaitTimedOut = false;
-        String failureReason;
-        // Came from MGITEST_MAGMA_DEPTH_RESOLVE_PROBE=bug|clean, not from the device.
-        Bool fromKnob = false;
-        // Measured on the device, but with MGITEST_MAGMA_DEPTH_RESOLVE_PROBE=elide-subject: the probe
-        // recorded no render-pass resolve at all, so the subject's target kept its sentinel.
-        Bool subjectElided = false;
-        Vector<WireDepthResolveFormatReading> formats;
-    };
-
-    enum class WireDepthResolveProbeVerdict : Uint8 {
-        // Nothing was measured: the render-pass arm is not available (nothing to choose between),
-        // or the probe could not set itself up. The default order stands.
-        NotRun,
-        // Measured, but no format's CONTROL resolved: the probe cannot tell the render pass's
-        // defect from its own. The default order stands, and the report must never call it a bug.
-        Inconclusive,
-        // Every format whose control resolved was resolved by the render pass too.
-        Clean,
-        // The defect: on at least one format the shader control resolved the inputs and the
-        // render pass did not (wrote nothing - the sentinel survived - or wrote wrong values).
-        RenderPassResolveBroken,
-    };
-
-    inline const char* WireDepthResolveProbeVerdictName(WireDepthResolveProbeVerdict verdict) {
-        switch (verdict) {
-            case WireDepthResolveProbeVerdict::NotRun: return "not-run";
-            case WireDepthResolveProbeVerdict::Inconclusive: return "inconclusive";
-            case WireDepthResolveProbeVerdict::Clean: return "clean";
-            case WireDepthResolveProbeVerdict::RenderPassResolveBroken: return "render-pass-resolve-broken";
-        }
-        return "?";
-    }
-
-    inline Bool WireDepthResolveControlHolds(const WireDepthResolveAspectReading& aspect) {
-        return aspect.measured && aspect.shaderRan && aspect.texels > 0 && aspect.shaderMatches == aspect.texels;
-    }
-
-    inline Bool WireDepthResolveSubjectHolds(const WireDepthResolveAspectReading& aspect) {
-        return aspect.texels > 0 && aspect.renderPassMatches == aspect.texels;
-    }
-
-    // An aspect only counts where its control holds; a format is conclusive when any of its
-    // aspects is. The render pass resolves every aspect of the format in one pass, so one aspect
-    // it fails is the defect for the whole arm.
-    inline WireDepthResolveProbeVerdict EvaluateWireDepthResolveProbe(const WireDepthResolveProbeMeasurement& measurement) {
-        if (!measurement.ran || measurement.fenceWaitTimedOut) return WireDepthResolveProbeVerdict::NotRun;
-        Bool conclusive = false, broken = false;
-        for (const WireDepthResolveFormatReading& reading : measurement.formats) {
-            if (!reading.ran) continue;
-            for (const WireDepthResolveAspectReading* aspect : {&reading.depth, &reading.stencil}) {
-                if (!WireDepthResolveControlHolds(*aspect)) continue;
-                conclusive = true;
-                if (!WireDepthResolveSubjectHolds(*aspect)) broken = true;
-            }
-        }
-        if (broken) return WireDepthResolveProbeVerdict::RenderPassResolveBroken;
-        return conclusive ? WireDepthResolveProbeVerdict::Clean : WireDepthResolveProbeVerdict::Inconclusive;
-    }
-
-    // THE TEST KNOB, read by the SERVER (split and spawn arms only; the tcp server is a lane fixture
-    // whose environment no entry reaches - spawn_lane_parity.py's MAGMA_SERVER_ENV_KNOB_NO_TCP).
-    // Lavapipe resolves correctly through both arms, so no host lane can reach the verdict that
-    // matters on the Redmi. MGITEST_MAGMA_DEPTH_RESOLVE_PROBE=bug|clean replaces the MEASUREMENT
-    // with a canned one that says exactly that, and nothing else: the canned measurement still goes
-    // through EvaluateWireDepthResolveProbe and the same member, so an entry that forces `bug` is red
-    // when the evaluation stops detecting the defect.
-    //
-    // A canned measurement cannot see the REAL probe - its recording, readback and tally - stop
-    // detecting the defect, and on lavapipe the real subject is clean, so nothing would. The third
-    // value, MGITEST_MAGMA_DEPTH_RESOLVE_PROBE=elide-subject, is that negative control: the REAL
-    // probe runs (ChooseWireDepthResolveArm treats it as Measure) and the caller passes it on as
-    // WireDepthResolveProbeContext::elideSubject, so the probe records no render-pass resolve and
-    // the real readback keeps the sentinel while the shader control still runs. The
-    // DirectVulkan.{Split,Spawn}.MsResolveElide. entries then require the defect verdict from the
-    // measurement itself.
-    enum class WireDepthResolveProbeKnob : Uint8 { Measure, ForceBug, ForceClean, ElideSubject, Unrecognised };
-
-    inline WireDepthResolveProbeKnob ParseWireDepthResolveProbeKnob(const char* value) {
-        if (value == nullptr || *value == '\0') return WireDepthResolveProbeKnob::Measure;
-        if (std::strcmp(value, "bug") == 0) return WireDepthResolveProbeKnob::ForceBug;
-        if (std::strcmp(value, "clean") == 0) return WireDepthResolveProbeKnob::ForceClean;
-        if (std::strcmp(value, "elide-subject") == 0) return WireDepthResolveProbeKnob::ElideSubject;
-        return WireDepthResolveProbeKnob::Unrecognised;
-    }
-
-    // One packed format's worth of readings: the control resolved both aspects; the render pass
-    // either did too (`renderPassWrites`) or left the sentinel everywhere.
-    inline WireDepthResolveProbeMeasurement CannedWireDepthResolveProbeMeasurement(Bool renderPassWrites) {
-        WireDepthResolveProbeMeasurement measurement;
-        measurement.ran = true;
-        measurement.fromKnob = true;
-        WireDepthResolveFormatReading reading;
-        reading.name = "MGITEST_MAGMA_DEPTH_RESOLVE_PROBE";
-        reading.samples = 4;
-        reading.ran = true;
-        const auto fill = [&](WireDepthResolveAspectReading& aspect, Uint32 expected, Uint32 sentinel) {
-            aspect.measured = true;
-            aspect.texels = 16;
-            aspect.expected = expected;
-            aspect.sentinel = sentinel;
-            aspect.renderPassMatches = renderPassWrites ? 16 : 0;
-            aspect.renderPassSentinels = renderPassWrites ? 0 : 16;
-            aspect.renderPassFirst = renderPassWrites ? expected : sentinel;
-            aspect.shaderRan = true;
-            aspect.shaderMatches = 16;
-            aspect.shaderFirst = expected;
-        };
-        fill(reading.depth, 0x400000u, 0xBFFFFFu);
-        fill(reading.stencil, 0x5Au, 0xA5u);
-        measurement.formats.push_back(Move(reading));
-        return measurement;
-    }
-
-    struct WireDepthResolveArmChoice {
-        WireDepthResolveProbeMeasurement measurement;
-        WireDepthResolveProbeVerdict verdict = WireDepthResolveProbeVerdict::NotRun;
-        // m_wirePreferShaderDepthResolve: the shader pass goes first, the render pass is the
-        // fallback for what the shader cannot write.
-        Bool preferShader = false;
-    };
-
-    // The whole decision, with the Vulkan half behind `measure` (called at most once, and only when
-    // the knob does not decide and the render-pass arm exists at all: without it the shader pass
-    // is the only arm and there is no order to choose). ElideSubject does not decide: it is
-    // measured like Measure, and the elision is the measuring callable's to apply.
-    template <typename MeasureFn>
-    WireDepthResolveArmChoice ChooseWireDepthResolveArm(WireDepthResolveProbeKnob knob, Bool renderPassArmAvailable,
-                                                        MeasureFn&& measure) {
-        WireDepthResolveArmChoice choice;
-        if (knob == WireDepthResolveProbeKnob::ForceBug || knob == WireDepthResolveProbeKnob::ForceClean) {
-            choice.measurement = CannedWireDepthResolveProbeMeasurement(knob == WireDepthResolveProbeKnob::ForceClean);
-        } else if (renderPassArmAvailable) {
-            choice.measurement = measure();
-        }
-        choice.verdict = EvaluateWireDepthResolveProbe(choice.measurement);
-        choice.preferShader = choice.verdict == WireDepthResolveProbeVerdict::RenderPassResolveBroken;
-        return choice;
-    }
-
-    // WHOSE VERDICT IT IS (codex closeout finding 7). The verdict is a property of ONE device and
-    // driver, and a process can hold more than one: inproc tears a renderer down and initializes
-    // another, possibly on a different physical device or under a different driver. The choice was
-    // a function-static - the first renderer's answer for every renderer after it - so a second
-    // device skipped its own probe and took an order measured elsewhere. It is now memoized per
-    // IDENTITY: the device (vendor, device, driver version, pipeline-cache UUID - the last changes
-    // with the driver build even where the version number does not) plus the two inputs the choice
-    // itself depends on (whether a render-pass arm exists to judge, and the test knob). The same
-    // identity is still probed once per process; a different one is probed for itself.
-    struct WireDepthResolveDeviceIdentity {
-        Uint32 vendorID = 0;
-        Uint32 deviceID = 0;
-        Uint32 driverVersion = 0;
-        Uint8 pipelineCacheUUID[16] = {};
-        Bool renderPassArmAvailable = false;
-        WireDepthResolveProbeKnob knob = WireDepthResolveProbeKnob::Measure;
-
-        Bool operator==(const WireDepthResolveDeviceIdentity& other) const {
-            return vendorID == other.vendorID && deviceID == other.deviceID && driverVersion == other.driverVersion &&
-                   std::memcmp(pipelineCacheUUID, other.pipelineCacheUUID, sizeof(pipelineCacheUUID)) == 0 &&
-                   renderPassArmAvailable == other.renderPassArmAvailable && knob == other.knob;
-        }
-    };
-
-    // The renderer's identity from its device's VkPhysicalDeviceProperties - the ONE place the fields
-    // are filled (VulkanRenderer::ArmWireDepthResolveOrder calls it), so the unit test proves that each
-    // property reaches the key: with only the cache tested, a field left out here stayed green.
-    inline WireDepthResolveDeviceIdentity MakeWireDepthResolveDeviceIdentity(const VkPhysicalDeviceProperties& properties,
-                                                                             Bool renderPassArmAvailable,
-                                                                             WireDepthResolveProbeKnob knob) {
-        WireDepthResolveDeviceIdentity identity;
-        identity.vendorID = properties.vendorID;
-        identity.deviceID = properties.deviceID;
-        identity.driverVersion = properties.driverVersion;
-        static_assert(sizeof(identity.pipelineCacheUUID) == sizeof(properties.pipelineCacheUUID));
-        std::memcpy(identity.pipelineCacheUUID, properties.pipelineCacheUUID, sizeof(identity.pipelineCacheUUID));
-        identity.renderPassArmAvailable = renderPassArmAvailable;
-        identity.knob = knob;
-        return identity;
-    }
-
-    class WireDepthResolveArmCache {
-    public:
-        // The identity's memoized choice, or `decide()`'s - called at most once per identity, under
-        // the cache's lock (a probe records on the device's queue; two renderers of one identity
-        // must not both run it). `decided`, when given, says whether this call ran `decide`.
-        template <typename DecideFn>
-        WireDepthResolveArmChoice Resolve(const WireDepthResolveDeviceIdentity& identity, DecideFn&& decide,
-                                          Bool* decided = nullptr) {
-            std::lock_guard<std::mutex> lock(m_mutex);
-            for (const auto& entry : m_entries) {
-                if (entry.first == identity) {
-                    if (decided) *decided = false;
-                    return entry.second;
-                }
-            }
-            WireDepthResolveArmChoice choice = decide();
-            m_entries.emplace_back(identity, choice);
-            if (decided) *decided = true;
-            return choice;
-        }
-
-        SizeT Size() const {
-            std::lock_guard<std::mutex> lock(m_mutex);
-            return m_entries.size();
-        }
-
-    private:
-        mutable std::mutex m_mutex;
-        Vector<std::pair<WireDepthResolveDeviceIdentity, WireDepthResolveArmChoice>> m_entries;
-    };
-
-    // One format's readings, both arms: "D24_UNORM_S8_UINT x4: depth expected 0x400000 sentinel
-    // 0xbfffff: render pass 0/16 (first 0xbfffff, sentinel 16), shader control 16/16 (first
-    // 0x400000) / stencil ...".
-    inline String DescribeWireDepthResolveFormat(const WireDepthResolveFormatReading& reading) {
-        const auto aspectText = [](const char* name, const WireDepthResolveAspectReading& aspect) {
-            String text = format("{} expected 0x{:x} sentinel 0x{:x}: render pass {}/{} (first 0x{:x}, sentinel {}), ",
-                                 name, aspect.expected, aspect.sentinel, aspect.renderPassMatches, aspect.texels,
-                                 aspect.renderPassFirst, aspect.renderPassSentinels);
-            if (aspect.shaderRan) {
-                text += format("shader control {}/{} (first 0x{:x})", aspect.shaderMatches, aspect.texels,
-                               aspect.shaderFirst);
-            } else {
-                text += "no shader control";
-            }
-            return text;
-        };
-        String out = reading.name;
-        if (!reading.ran) return out + " skipped (" + reading.skipReason + ")";
-        out += format(" x{}: ", reading.samples);
-        if (reading.depth.measured) out += aspectText("depth", reading.depth);
-        if (reading.depth.measured && reading.stencil.measured) out += " / ";
-        if (reading.stencil.measured) out += aspectText("stencil", reading.stencil);
-        return out;
-    }
-
-    // Every format, "; "-separated, for the POST row.
-    inline String DescribeWireDepthResolveProbe(const WireDepthResolveProbeMeasurement& measurement) {
-        if (!measurement.ran) {
-            return measurement.failureReason.empty() ? String("not run") : "not run (" + measurement.failureReason + ")";
-        }
-        String out;
-        for (const WireDepthResolveFormatReading& reading : measurement.formats) {
-            if (!out.empty()) out += "; ";
-            out += DescribeWireDepthResolveFormat(reading);
-        }
-        return out;
-    }
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/Renderer/WireDepthResolveProbe.cpp

@@ -1,992 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/WireDepthResolveProbe.cpp
-// Copyright (c) 2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-//
-// See WireDepthResolveProbe.h for the arms and the probe's shape, WireDepthResolveArm.h for the
-// verdict. The plumbing is the PRIMITIVES_GENERATED probe's (MG_Util/SelfTest/
-// PrimitivesGeneratedNoXfbProbe.cpp): one throwaway command buffer, a bounded fence wait that
-// leaks rather than idle-waits a hung GPU, teardown on every other path.
-
-#include "WireDepthResolveProbe.h"
-
-#include <MG_Util/Debug/Log.h>
-
-#include <bit>
-#include <cmath>
-#include <cstring>
-#include <vulkan/vulkan_core.h>
-
-#if MOBILEGL_BUILD_DISAGGREGATED
-namespace MobileGL::MG_Backend::DirectVulkan {
-#include "WireMultisampleResolveSpirv.h"
-
-    VkImageAspectFlags WireDepthStencilFormatAspects(VkFormat format) {
-        if (format == VK_FORMAT_S8_UINT) return VK_IMAGE_ASPECT_STENCIL_BIT;
-        if (format == VK_FORMAT_D16_UNORM_S8_UINT || format == VK_FORMAT_D24_UNORM_S8_UINT ||
-            format == VK_FORMAT_D32_SFLOAT_S8_UINT)
-            return VK_IMAGE_ASPECT_DEPTH_BIT | VK_IMAGE_ASPECT_STENCIL_BIT;
-        return VK_IMAGE_ASPECT_DEPTH_BIT;
-    }
-
-    VkImageViewCreateInfo WireDepthStencilViewInfo(VkImage image, VkFormat format, VkImageAspectFlags aspects,
-                                                   Uint32 level, Uint32 layer) {
-        VkImageViewCreateInfo info{VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO};
-        info.image = image;
-        info.viewType = VK_IMAGE_VIEW_TYPE_2D;
-        info.format = format;
-        info.subresourceRange = {aspects, level, 1, layer, 1};
-        return info;
-    }
-
-    VkResult CreateWireDepthStencilResolvePass(PFN_vkCreateRenderPass2 createRenderPass2, VkDevice device,
-                                               VkFormat format, VkSampleCountFlagBits samples, VkRenderPass* pass) {
-        const VkImageAspectFlags formatAspects = WireDepthStencilFormatAspects(format);
-        VkAttachmentDescription2 attachments[2]{};
-        for (Uint32 i = 0; i < 2; ++i) {
-            auto& attachment = attachments[i];
-            attachment.sType = VK_STRUCTURE_TYPE_ATTACHMENT_DESCRIPTION_2;
-            attachment.format = format;
-            attachment.samples = i == 0 ? samples : VK_SAMPLE_COUNT_1_BIT;
-            attachment.loadOp = attachment.stencilLoadOp =
-                i == 0 ? VK_ATTACHMENT_LOAD_OP_LOAD : VK_ATTACHMENT_LOAD_OP_DONT_CARE;
-            attachment.storeOp = attachment.stencilStoreOp = VK_ATTACHMENT_STORE_OP_STORE;
-            attachment.initialLayout = attachment.finalLayout = VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL;
-        }
-        VkAttachmentReference2 sourceReference{VK_STRUCTURE_TYPE_ATTACHMENT_REFERENCE_2};
-        sourceReference.attachment = 0;
-        sourceReference.layout = VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL;
-        sourceReference.aspectMask = formatAspects;
-        VkAttachmentReference2 resolveReference = sourceReference;
-        resolveReference.attachment = 1;
-        VkSubpassDescriptionDepthStencilResolve resolve{VK_STRUCTURE_TYPE_SUBPASS_DESCRIPTION_DEPTH_STENCIL_RESOLVE};
-        resolve.depthResolveMode =
-            (formatAspects & VK_IMAGE_ASPECT_DEPTH_BIT) ? VK_RESOLVE_MODE_SAMPLE_ZERO_BIT : VK_RESOLVE_MODE_NONE;
-        resolve.stencilResolveMode =
-            (formatAspects & VK_IMAGE_ASPECT_STENCIL_BIT) ? VK_RESOLVE_MODE_SAMPLE_ZERO_BIT : VK_RESOLVE_MODE_NONE;
-        resolve.pDepthStencilResolveAttachment = &resolveReference;
-        VkSubpassDescription2 subpass{VK_STRUCTURE_TYPE_SUBPASS_DESCRIPTION_2};
-        subpass.pNext = &resolve;
-        subpass.pipelineBindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS;
-        subpass.pDepthStencilAttachment = &sourceReference;
-        VkRenderPassCreateInfo2 passInfo{VK_STRUCTURE_TYPE_RENDER_PASS_CREATE_INFO_2};
-        passInfo.attachmentCount = 2;
-        passInfo.pAttachments = attachments;
-        passInfo.subpassCount = 1;
-        passInfo.pSubpasses = &subpass;
-        return createRenderPass2(device, &passInfo, nullptr, pass);
-    }
-
-    VkResult CreateWireShaderResolveKit(VkDevice device, Bool shaderStencilExport, WireShaderResolveKit& kit) {
-        const auto shader = [&](const Uint32* code, SizeT bytes, VkShaderModule& module) {
-            VkShaderModuleCreateInfo info{VK_STRUCTURE_TYPE_SHADER_MODULE_CREATE_INFO};
-            info.codeSize = bytes;
-            info.pCode = code;
-            return vkCreateShaderModule(device, &info, nullptr, &module);
-        };
-        VkResult result =
-            shader(kWireMultisampleResolveVertexSpirv, sizeof(kWireMultisampleResolveVertexSpirv), kit.vertex);
-        if (result != VK_SUCCESS) return result;
-        result = shader(kWireMultisampleDepthResolveFragmentSpirv, sizeof(kWireMultisampleDepthResolveFragmentSpirv),
-                        kit.depthFragment);
-        if (result != VK_SUCCESS) return result;
-        // THE STENCIL MODULE IS ONLY CREATED WHERE IT CAN RUN: its SPIR-V declares the
-        // StencilExportEXT capability, and handing a module with an unsupported capability to
-        // vkCreateShaderModule is undefined behaviour - not an error this could catch.
-        if (shaderStencilExport) {
-            result = shader(kWireMultisampleStencilResolveFragmentSpirv,
-                            sizeof(kWireMultisampleStencilResolveFragmentSpirv), kit.stencilFragment);
-            if (result != VK_SUCCESS) return result;
-        }
-        const VkDescriptorSetLayoutBinding binding{0, VK_DESCRIPTOR_TYPE_COMBINED_IMAGE_SAMPLER, 1,
-                                                   VK_SHADER_STAGE_FRAGMENT_BIT, nullptr};
-        VkDescriptorSetLayoutCreateInfo layout{VK_STRUCTURE_TYPE_DESCRIPTOR_SET_LAYOUT_CREATE_INFO};
-        layout.bindingCount = 1;
-        layout.pBindings = &binding;
-        result = vkCreateDescriptorSetLayout(device, &layout, nullptr, &kit.descriptorLayout);
-        if (result != VK_SUCCESS) return result;
-        // NO PUSH CONSTANT RANGE AT ALL: the pass reads its coordinate from gl_FragCoord and its
-        // rectangle from the scissor, so neither stage takes an input.
-        VkPipelineLayoutCreateInfo pipelineLayout{VK_STRUCTURE_TYPE_PIPELINE_LAYOUT_CREATE_INFO};
-        pipelineLayout.setLayoutCount = 1;
-        pipelineLayout.pSetLayouts = &kit.descriptorLayout;
-        result = vkCreatePipelineLayout(device, &pipelineLayout, nullptr, &kit.pipelineLayout);
-        if (result != VK_SUCCESS) return result;
-        // NEAREST: texelFetch ignores the sampler's filter, and most devices do not advertise
-        // linear filtering for a depth format anyway. The sampler exists only because GLSL's
-        // sampler2DMS is a COMBINED image sampler.
-        VkSamplerCreateInfo sampler{VK_STRUCTURE_TYPE_SAMPLER_CREATE_INFO};
-        sampler.mipmapMode = VK_SAMPLER_MIPMAP_MODE_NEAREST;
-        sampler.addressModeU = sampler.addressModeV = sampler.addressModeW = VK_SAMPLER_ADDRESS_MODE_CLAMP_TO_EDGE;
-        sampler.magFilter = sampler.minFilter = VK_FILTER_NEAREST;
-        sampler.maxLod = 0.0f;
-        return vkCreateSampler(device, &sampler, nullptr, &kit.nearest);
-    }
-
-    void DestroyWireShaderResolveKit(VkDevice device, WireShaderResolveKit& kit) {
-        vkDestroySampler(device, kit.nearest, nullptr);
-        vkDestroyPipelineLayout(device, kit.pipelineLayout, nullptr);
-        vkDestroyDescriptorSetLayout(device, kit.descriptorLayout, nullptr);
-        vkDestroyShaderModule(device, kit.vertex, nullptr);
-        vkDestroyShaderModule(device, kit.depthFragment, nullptr);
-        vkDestroyShaderModule(device, kit.stencilFragment, nullptr);
-        kit = {};
-    }
-
-    VkResult CreateWireShaderResolveRenderPass(VkDevice device, VkFormat format, VkRenderPass* pass) {
-        VkAttachmentDescription attachment{};
-        attachment.format = format;
-        attachment.samples = VK_SAMPLE_COUNT_1_BIT;
-        // DONT_CARE on BOTH aspects: the pass writes every texel of the scissored rect for the
-        // aspect it owns, and the caller copies only that aspect out. The other aspect of a packed
-        // format is left undefined on purpose - it is never read, and LOADing it would order this
-        // pass behind a write nobody is waiting for.
-        attachment.loadOp = attachment.stencilLoadOp = VK_ATTACHMENT_LOAD_OP_DONT_CARE;
-        attachment.storeOp = attachment.stencilStoreOp = VK_ATTACHMENT_STORE_OP_STORE;
-        attachment.initialLayout = attachment.finalLayout = VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL;
-        const VkAttachmentReference depthStencil{0, VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL};
-        VkSubpassDescription subpass{};
-        subpass.pipelineBindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS;
-        subpass.pDepthStencilAttachment = &depthStencil;
-        VkRenderPassCreateInfo info{VK_STRUCTURE_TYPE_RENDER_PASS_CREATE_INFO};
-        info.attachmentCount = 1;
-        info.pAttachments = &attachment;
-        info.subpassCount = 1;
-        info.pSubpasses = &subpass;
-        return vkCreateRenderPass(device, &info, nullptr, pass);
-    }
-
-    VkResult CreateWireShaderResolvePipeline(VkDevice device, const WireShaderResolveKit& kit, VkRenderPass pass,
-                                             VkImageAspectFlags aspect, VkPipeline* pipeline) {
-        const VkShaderModule fragment =
-            aspect == VK_IMAGE_ASPECT_STENCIL_BIT ? kit.stencilFragment : kit.depthFragment;
-        if (fragment == VK_NULL_HANDLE || kit.vertex == VK_NULL_HANDLE) return VK_ERROR_FEATURE_NOT_PRESENT;
-        VkPipelineShaderStageCreateInfo stages[2]{};
-        for (auto& stage : stages) {
-            stage.sType = VK_STRUCTURE_TYPE_PIPELINE_SHADER_STAGE_CREATE_INFO;
-            stage.pName = "main";
-        }
-        stages[0].stage = VK_SHADER_STAGE_VERTEX_BIT;
-        stages[0].module = kit.vertex;
-        stages[1].stage = VK_SHADER_STAGE_FRAGMENT_BIT;
-        stages[1].module = fragment;
-        const VkPipelineVertexInputStateCreateInfo vertex{VK_STRUCTURE_TYPE_PIPELINE_VERTEX_INPUT_STATE_CREATE_INFO};
-        VkPipelineInputAssemblyStateCreateInfo assembly{VK_STRUCTURE_TYPE_PIPELINE_INPUT_ASSEMBLY_STATE_CREATE_INFO};
-        assembly.topology = VK_PRIMITIVE_TOPOLOGY_TRIANGLE_LIST;
-        VkPipelineViewportStateCreateInfo viewport{VK_STRUCTURE_TYPE_PIPELINE_VIEWPORT_STATE_CREATE_INFO};
-        viewport.viewportCount = viewport.scissorCount = 1;
-        VkPipelineRasterizationStateCreateInfo raster{VK_STRUCTURE_TYPE_PIPELINE_RASTERIZATION_STATE_CREATE_INFO};
-        raster.polygonMode = VK_POLYGON_MODE_FILL;
-        raster.cullMode = VK_CULL_MODE_NONE;
-        raster.frontFace = VK_FRONT_FACE_COUNTER_CLOCKWISE;
-        raster.lineWidth = 1.0f;
-        VkPipelineMultisampleStateCreateInfo samples{VK_STRUCTURE_TYPE_PIPELINE_MULTISAMPLE_STATE_CREATE_INFO};
-        samples.rasterizationSamples = VK_SAMPLE_COUNT_1_BIT;
-        VkPipelineDepthStencilStateCreateInfo depthStencilState{VK_STRUCTURE_TYPE_PIPELINE_DEPTH_STENCIL_STATE_CREATE_INFO};
-        depthStencilState.minDepthBounds = 0.0f;
-        depthStencilState.maxDepthBounds = 1.0f;
-        if (aspect == VK_IMAGE_ASPECT_DEPTH_BIT) {
-            // ALWAYS + write: gl_FragDepth is the answer, and a comparison against whatever
-            // DONT_CARE left behind would discard some of it.
-            depthStencilState.depthTestEnable = VK_TRUE;
-            depthStencilState.depthWriteEnable = VK_TRUE;
-            depthStencilState.depthCompareOp = VK_COMPARE_OP_ALWAYS;
-        } else {
-            // REPLACE on every outcome, compare ALWAYS, full write mask: that is what makes the
-            // shader-exported reference the value that lands. The static `reference` is overridden
-            // by gl_FragStencilRefARB, which is the whole point of the extension.
-            depthStencilState.stencilTestEnable = VK_TRUE;
-            VkStencilOpState op{};
-            op.failOp = op.passOp = op.depthFailOp = VK_STENCIL_OP_REPLACE;
-            op.compareOp = VK_COMPARE_OP_ALWAYS;
-            op.compareMask = op.writeMask = 0xFFu;
-            op.reference = 0;
-            depthStencilState.front = depthStencilState.back = op;
-        }
-        // No colour attachment in this render pass, so no attachment states either.
-        VkPipelineColorBlendStateCreateInfo blend{VK_STRUCTURE_TYPE_PIPELINE_COLOR_BLEND_STATE_CREATE_INFO};
-        const VkDynamicState dynamicStates[]{VK_DYNAMIC_STATE_VIEWPORT, VK_DYNAMIC_STATE_SCISSOR};
-        VkPipelineDynamicStateCreateInfo dynamic{VK_STRUCTURE_TYPE_PIPELINE_DYNAMIC_STATE_CREATE_INFO};
-        dynamic.dynamicStateCount = 2;
-        dynamic.pDynamicStates = dynamicStates;
-        VkGraphicsPipelineCreateInfo info{VK_STRUCTURE_TYPE_GRAPHICS_PIPELINE_CREATE_INFO};
-        info.stageCount = 2;
-        info.pStages = stages;
-        info.pVertexInputState = &vertex;
-        info.pInputAssemblyState = &assembly;
-        info.pViewportState = &viewport;
-        info.pRasterizationState = &raster;
-        info.pMultisampleState = &samples;
-        info.pDepthStencilState = &depthStencilState;
-        info.pColorBlendState = &blend;
-        info.pDynamicState = &dynamic;
-        info.layout = kit.pipelineLayout;
-        info.renderPass = pass;
-        return vkCreateGraphicsPipelines(device, VK_NULL_HANDLE, 1, &info, nullptr, pipeline);
-    }
-
-    void RecordWireShaderResolveDraw(VkCommandBuffer commandBuffer, const WireShaderResolveKit& kit,
-                                     VkRenderPass pass, VkPipeline pipeline, VkFramebuffer framebuffer,
-                                     VkDescriptorSet descriptorSet, VkExtent2D attachmentExtent, VkRect2D rect) {
-        VkRenderPassBeginInfo begin{VK_STRUCTURE_TYPE_RENDER_PASS_BEGIN_INFO};
-        begin.renderPass = pass;
-        begin.framebuffer = framebuffer;
-        // The RECTANGLE is the render area, exactly as the render-pass arm's renderArea is - the
-        // scratch outside it is never read.
-        begin.renderArea = rect;
-        vkCmdBeginRenderPass(commandBuffer, &begin, VK_SUBPASS_CONTENTS_INLINE);
-        vkCmdBindPipeline(commandBuffer, VK_PIPELINE_BIND_POINT_GRAPHICS, pipeline);
-        // THE VIEWPORT IS THE WHOLE ATTACHMENT AND THE SCISSOR IS THE RECT, and the two are not
-        // interchangeable here: gl_FragCoord is what the fragment shader fetches by, so the
-        // clip-space-to-attachment mapping has to be the identity for every rectangle. A viewport
-        // shrunk onto the rect would slide the whole image instead of moving a window over it.
-        const VkViewport viewport{0.0f, 0.0f, static_cast<float>(attachmentExtent.width),
-                                  static_cast<float>(attachmentExtent.height), 0.0f, 1.0f};
-        vkCmdSetViewport(commandBuffer, 0, 1, &viewport);
-        vkCmdSetScissor(commandBuffer, 0, 1, &rect);
-        vkCmdBindDescriptorSets(commandBuffer, VK_PIPELINE_BIND_POINT_GRAPHICS, kit.pipelineLayout, 0, 1,
-                                &descriptorSet, 0, nullptr);
-        vkCmdDraw(commandBuffer, 3, 1, 0, 0);
-        vkCmdEndRenderPass(commandBuffer);
-    }
-
-    namespace {
-        constexpr Uint32 kProbeExtent = 4;
-        constexpr Uint32 kProbeTexels = kProbeExtent * kProbeExtent;
-        // Every Vulkan device must support 4 samples on a depth/stencil attachment
-        // (framebufferDepthSampleCounts), and the CTS case the probe stands for fails at 2 and 4.
-        constexpr VkSampleCountFlagBits kProbeSamples = VK_SAMPLE_COUNT_4_BIT;
-        constexpr Float kClearDepth = 0.25f;
-        constexpr Float kSentinelDepth = 0.75f;
-        constexpr Uint32 kClearStencil = 0x5Au;
-        constexpr Uint32 kSentinelStencil = 0xA5u;
-        constexpr Uint64 kFenceTimeoutNs = 5ull * 1000ull * 1000ull * 1000ull;
-
-        // The formats the wire maps GL's depth/stencil internal formats onto (VkTextureManager),
-        // packed first: the case that set all this off failed on every one of them.
-        struct ProbeFormat {
-            VkFormat format;
-            const char* name;
-        };
-        constexpr ProbeFormat kProbeFormats[] = {
-            {VK_FORMAT_D24_UNORM_S8_UINT, "D24_UNORM_S8_UINT"},
-            {VK_FORMAT_D32_SFLOAT_S8_UINT, "D32_SFLOAT_S8_UINT"},
-            {VK_FORMAT_D16_UNORM, "D16_UNORM"},
-            {VK_FORMAT_X8_D24_UNORM_PACK32, "X8_D24_UNORM_PACK32"},
-            {VK_FORMAT_D32_SFLOAT, "D32_SFLOAT"},
-            {VK_FORMAT_S8_UINT, "S8_UINT"},
-        };
-
-        // The usages production gives the two images: a wire multisample depth/stencil attachment
-        // (VkTextureManager: SAMPLED | DEPTH_STENCIL_ATTACHMENT | TRANSFER_SRC | TRANSFER_DST) and
-        // ResolveWireDepthStencil's resolve scratch (DEPTH_STENCIL_ATTACHMENT | TRANSFER_SRC).
-        constexpr VkImageUsageFlags kSourceUsage = VK_IMAGE_USAGE_SAMPLED_BIT |
-                                                   VK_IMAGE_USAGE_DEPTH_STENCIL_ATTACHMENT_BIT |
-                                                   VK_IMAGE_USAGE_TRANSFER_SRC_BIT | VK_IMAGE_USAGE_TRANSFER_DST_BIT;
-        constexpr VkImageUsageFlags kScratchUsage =
-            VK_IMAGE_USAGE_DEPTH_STENCIL_ATTACHMENT_BIT | VK_IMAGE_USAGE_TRANSFER_SRC_BIT;
-
-        Bool IsFloatDepth(VkFormat format) {
-            return format == VK_FORMAT_D32_SFLOAT || format == VK_FORMAT_D32_SFLOAT_S8_UINT;
-        }
-
-        Uint32 DepthCopyBytes(VkFormat format) { return format == VK_FORMAT_D16_UNORM ? 2u : 4u; }
-
-        Uint32 EncodeDepth(VkFormat format, Float depth) {
-            if (IsFloatDepth(format)) return std::bit_cast<Uint32>(depth);
-            const double scale = format == VK_FORMAT_D16_UNORM ? 65535.0 : 16777215.0;
-            return static_cast<Uint32>(std::lround(static_cast<double>(depth) * scale));
-        }
-
-        Uint32 ReadDepthWord(VkFormat format, const Uint8* texel) {
-            if (format == VK_FORMAT_D16_UNORM) {
-                Uint16 word = 0;
-                std::memcpy(&word, texel, sizeof(word));
-                return word;
-            }
-            Uint32 word = 0;
-            std::memcpy(&word, texel, sizeof(word));
-            // A D24 aspect copies out as a 32-bit word whose top byte is undefined.
-            return IsFloatDepth(format) ? word : (word & 0x00FFFFFFu);
-        }
-
-        Uint32 WordDistance(Uint32 a, Uint32 b) { return a > b ? a - b : b - a; }
-
-        struct ProbeImage {
-            VkImage image = VK_NULL_HANDLE;
-            VkDeviceMemory memory = VK_NULL_HANDLE;
-        };
-
-        struct ControlPass {
-            Bool ready = false;
-            ProbeImage target;
-            VkRenderPass pass = VK_NULL_HANDLE;
-            VkPipeline pipeline = VK_NULL_HANDLE;
-            VkImageView sampledView = VK_NULL_HANDLE;
-            VkImageView targetView = VK_NULL_HANDLE;
-            VkFramebuffer framebuffer = VK_NULL_HANDLE;
-            VkDescriptorSet set = VK_NULL_HANDLE;
-            VkDeviceSize offset = 0;
-        };
-
-        struct FormatWork {
-            SizeT reading = 0;
-            VkFormat format = VK_FORMAT_UNDEFINED;
-            VkImageAspectFlags aspects = 0;
-            ProbeImage subjectSource, controlSource, subjectTarget;
-            VkRenderPass resolvePass = VK_NULL_HANDLE;
-            VkImageView resolveViews[2]{};
-            VkFramebuffer resolveFramebuffer = VK_NULL_HANDLE;
-            VkDeviceSize subjectDepthOffset = 0, subjectStencilOffset = 0;
-            ControlPass depthControl, stencilControl;
-        };
-
-        // Everything the probe creates, destroyed together (or leaked together on a timeout).
-        struct ProbeObjects {
-            VkDevice device = VK_NULL_HANDLE;
-            Vector<VkImage> images;
-            Vector<VkDeviceMemory> memories;
-            Vector<VkImageView> views;
-            Vector<VkRenderPass> passes;
-            Vector<VkFramebuffer> framebuffers;
-            Vector<VkPipeline> pipelines;
-            VkBuffer buffer = VK_NULL_HANDLE;
-            VkDescriptorPool descriptorPool = VK_NULL_HANDLE;
-            VkCommandPool commandPool = VK_NULL_HANDLE;
-            VkFence fence = VK_NULL_HANDLE;
-            WireShaderResolveKit kit;
-
-            void Destroy() {
-                for (VkPipeline pipeline : pipelines) vkDestroyPipeline(device, pipeline, nullptr);
-                for (VkFramebuffer framebuffer : framebuffers) vkDestroyFramebuffer(device, framebuffer, nullptr);
-                for (VkRenderPass pass : passes) vkDestroyRenderPass(device, pass, nullptr);
-                for (VkImageView view : views) vkDestroyImageView(device, view, nullptr);
-                for (VkImage image : images) vkDestroyImage(device, image, nullptr);
-                vkDestroyBuffer(device, buffer, nullptr);
-                for (VkDeviceMemory memory : memories) vkFreeMemory(device, memory, nullptr);
-                vkDestroyDescriptorPool(device, descriptorPool, nullptr);
-                vkDestroyCommandPool(device, commandPool, nullptr);
-                vkDestroyFence(device, fence, nullptr);
-                DestroyWireShaderResolveKit(device, kit);
-            }
-        };
-
-        Optional<Uint32> PickMemoryType(const VkPhysicalDeviceMemoryProperties& properties, Uint32 allowed,
-                                        VkMemoryPropertyFlags wanted, VkMemoryPropertyFlags required) {
-            Optional<Uint32> fallback;
-            for (Uint32 i = 0; i < properties.memoryTypeCount; ++i) {
-                if (!(allowed & (1u << i))) continue;
-                const VkMemoryPropertyFlags flags = properties.memoryTypes[i].propertyFlags;
-                if (flags & VK_MEMORY_PROPERTY_LAZILY_ALLOCATED_BIT) continue;
-                if ((flags & required) != required) continue;
-                if ((flags & wanted) == wanted) return i;
-                if (!fallback) fallback = i;
-            }
-            return fallback;
-        }
-
-        void ImageBarrier(VkCommandBuffer commandBuffer, VkImage image, VkImageAspectFlags aspects,
-                          VkImageLayout oldLayout, VkImageLayout newLayout, VkPipelineStageFlags srcStage,
-                          VkAccessFlags srcAccess, VkPipelineStageFlags dstStage, VkAccessFlags dstAccess) {
-            VkImageMemoryBarrier barrier{VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER};
-            barrier.srcAccessMask = srcAccess;
-            barrier.dstAccessMask = dstAccess;
-            barrier.oldLayout = oldLayout;
-            barrier.newLayout = newLayout;
-            barrier.srcQueueFamilyIndex = barrier.dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
-            barrier.image = image;
-            barrier.subresourceRange = {aspects, 0, 1, 0, VK_REMAINING_ARRAY_LAYERS};
-            vkCmdPipelineBarrier(commandBuffer, srcStage, dstStage, 0, 0, nullptr, 0, nullptr, 1, &barrier);
-        }
-    } // namespace
-
-    WireDepthResolveProbeMeasurement RunWireDepthResolveProbe(const WireDepthResolveProbeContext& context) {
-        WireDepthResolveProbeMeasurement measurement;
-        measurement.subjectElided = context.elideSubject;
-        const VkDevice device = context.device;
-        if (device == VK_NULL_HANDLE || context.queue == VK_NULL_HANDLE || context.createRenderPass2 == nullptr) {
-            measurement.failureReason = "no device, queue or vkCreateRenderPass2";
-            return measurement;
-        }
-        ProbeObjects objects;
-        objects.device = device;
-        Bool leak = false;
-        struct Teardown {
-            ProbeObjects& objects;
-            Bool& leak;
-            ~Teardown() {
-                if (!leak) objects.Destroy();
-            }
-        } teardown{objects, leak};
-        const auto fail = [&](String reason) {
-            measurement.ran = false;
-            measurement.failureReason = Move(reason);
-            return measurement;
-        };
-
-        VkPhysicalDeviceMemoryProperties memoryProperties{};
-        vkGetPhysicalDeviceMemoryProperties(context.physicalDevice, &memoryProperties);
-        const auto makeImage = [&](VkFormat format, VkSampleCountFlagBits samples, VkImageUsageFlags usage,
-                                   ProbeImage& out) -> Bool {
-            VkImageCreateInfo info{VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO};
-            info.imageType = VK_IMAGE_TYPE_2D;
-            info.format = format;
-            info.extent = {kProbeExtent, kProbeExtent, 1};
-            info.mipLevels = info.arrayLayers = 1;
-            info.samples = samples;
-            info.tiling = VK_IMAGE_TILING_OPTIMAL;
-            info.usage = usage;
-            info.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
-            info.initialLayout = VK_IMAGE_LAYOUT_UNDEFINED;
-            if (vkCreateImage(device, &info, nullptr, &out.image) != VK_SUCCESS) return false;
-            objects.images.push_back(out.image);
-            VkMemoryRequirements requirements{};
-            vkGetImageMemoryRequirements(device, out.image, &requirements);
-            const Optional<Uint32> type = PickMemoryType(memoryProperties, requirements.memoryTypeBits,
-                                                         VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT, 0);
-            if (!type) return false;
-            VkMemoryAllocateInfo allocate{VK_STRUCTURE_TYPE_MEMORY_ALLOCATE_INFO};
-            allocate.allocationSize = requirements.size;
-            allocate.memoryTypeIndex = *type;
-            if (vkAllocateMemory(device, &allocate, nullptr, &out.memory) != VK_SUCCESS) return false;
-            objects.memories.push_back(out.memory);
-            return vkBindImageMemory(device, out.image, out.memory, 0) == VK_SUCCESS;
-        };
-        const auto makeView = [&](const VkImageViewCreateInfo& info, VkImageView& out) -> Bool {
-            if (vkCreateImageView(device, &info, nullptr, &out) != VK_SUCCESS) return false;
-            objects.views.push_back(out);
-            return true;
-        };
-        const auto makeFramebuffer = [&](VkRenderPass pass, const VkImageView* views, Uint32 count,
-                                         VkFramebuffer& out) -> Bool {
-            VkFramebufferCreateInfo info{VK_STRUCTURE_TYPE_FRAMEBUFFER_CREATE_INFO};
-            info.renderPass = pass;
-            info.attachmentCount = count;
-            info.pAttachments = views;
-            info.width = info.height = kProbeExtent;
-            info.layers = 1;
-            if (vkCreateFramebuffer(device, &info, nullptr, &out) != VK_SUCCESS) return false;
-            objects.framebuffers.push_back(out);
-            return true;
-        };
-        // The wire's clear (WireFramebuffer.inc, ClearWireFramebuffer): a LOAD/STORE pass over every
-        // aspect of the format with vkCmdClearAttachments inside it. Recorded later; built now.
-        struct ClearPass {
-            VkRenderPass pass = VK_NULL_HANDLE;
-            VkFramebuffer framebuffer = VK_NULL_HANDLE;
-            VkImageAspectFlags aspects = 0;
-            Float depth = 0.0f;
-            Uint32 stencil = 0;
-        };
-        Vector<ClearPass> clears;
-        const auto makeClear = [&](const ProbeImage& image, VkFormat format, VkSampleCountFlagBits samples,
-                                   Float depth, Uint32 stencil) -> Bool {
-            const VkImageAspectFlags aspects = WireDepthStencilFormatAspects(format);
-            VkImageView view = VK_NULL_HANDLE;
-            if (!makeView(WireDepthStencilViewInfo(image.image, format, aspects, 0, 0), view)) return false;
-            VkAttachmentDescription attachment{};
-            attachment.format = format;
-            attachment.samples = samples;
-            attachment.loadOp = attachment.stencilLoadOp = VK_ATTACHMENT_LOAD_OP_LOAD;
-            attachment.storeOp = attachment.stencilStoreOp = VK_ATTACHMENT_STORE_OP_STORE;
-            attachment.initialLayout = attachment.finalLayout = VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL;
-            const VkAttachmentReference reference{0, VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL};
-            VkSubpassDescription subpass{};
-            subpass.pipelineBindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS;
-            subpass.pDepthStencilAttachment = &reference;
-            VkRenderPassCreateInfo info{VK_STRUCTURE_TYPE_RENDER_PASS_CREATE_INFO};
-            info.attachmentCount = 1;
-            info.pAttachments = &attachment;
-            info.subpassCount = 1;
-            info.pSubpasses = &subpass;
-            ClearPass clear;
-            if (vkCreateRenderPass(device, &info, nullptr, &clear.pass) != VK_SUCCESS) return false;
-            objects.passes.push_back(clear.pass);
-            if (!makeFramebuffer(clear.pass, &view, 1, clear.framebuffer)) return false;
-            clear.aspects = aspects;
-            clear.depth = depth;
-            clear.stencil = stencil;
-            clears.push_back(clear);
-            return true;
-        };
-
-        // THE CONTROL'S FORMAT-INDEPENDENT HALF. A kit that cannot be made leaves every control
-        // un-run, which the verdict reads as INCONCLUSIVE - never as the bug.
-        String kitFailure;
-        if (const VkResult result = CreateWireShaderResolveKit(device, context.shaderStencilExport, objects.kit);
-            result != VK_SUCCESS)
-            kitFailure = format("shader resolve kit creation failed (VkResult {})", static_cast<Int>(result));
-
-        // Readback layout: every region on a 16-byte boundary (a depth/stencil buffer copy wants a
-        // multiple of 4).
-        VkDeviceSize bufferBytes = 0;
-        const auto reserve = [&](VkDeviceSize bytes) {
-            const VkDeviceSize offset = bufferBytes;
-            bufferBytes += (bytes + 15u) & ~VkDeviceSize{15u};
-            return offset;
-        };
-
-        Vector<FormatWork> work;
-        for (const ProbeFormat& probeFormat : kProbeFormats) {
-            WireDepthResolveFormatReading reading;
-            reading.name = probeFormat.name;
-            reading.format = static_cast<Int32>(probeFormat.format);
-            reading.samples = static_cast<Uint32>(kProbeSamples);
-            const SizeT readingIndex = measurement.formats.size();
-            measurement.formats.push_back(reading);
-            auto& slot = measurement.formats.back();
-            // A skipped format records nothing: the clears it had already built are dropped with it
-            // (their images stay in `objects` and are only destroyed).
-            const SizeT clearsBefore = clears.size();
-            const auto skip = [&](String reason) {
-                slot.skipReason = Move(reason);
-                clears.resize(clearsBefore);
-            };
-
-            const VkFormat format = probeFormat.format;
-            const VkImageAspectFlags aspects = WireDepthStencilFormatAspects(format);
-            VkFormatProperties formatProperties{};
-            vkGetPhysicalDeviceFormatProperties(context.physicalDevice, format, &formatProperties);
-            constexpr VkFormatFeatureFlags kRequired =
-                VK_FORMAT_FEATURE_DEPTH_STENCIL_ATTACHMENT_BIT | VK_FORMAT_FEATURE_SAMPLED_IMAGE_BIT;
-            if ((formatProperties.optimalTilingFeatures & kRequired) != kRequired) {
-                skip("not a sampled depth/stencil attachment format here");
-                continue;
-            }
-            VkImageFormatProperties imageProperties{};
-            if (vkGetPhysicalDeviceImageFormatProperties(context.physicalDevice, format, VK_IMAGE_TYPE_2D,
-                                                         VK_IMAGE_TILING_OPTIMAL, kSourceUsage, 0,
-                                                         &imageProperties) != VK_SUCCESS ||
-                !(imageProperties.sampleCounts & kProbeSamples)) {
-                skip("no 4x multisample image with the wire's attachment usage");
-                continue;
-            }
-            if (vkGetPhysicalDeviceImageFormatProperties(context.physicalDevice, format, VK_IMAGE_TYPE_2D,
-                                                         VK_IMAGE_TILING_OPTIMAL, kScratchUsage, 0,
-                                                         &imageProperties) != VK_SUCCESS) {
-                skip("no single-sample image with the resolve scratch's usage");
-                continue;
-            }
-            // ResolveWireDepthStencil's own test for the render-pass arm, per format.
-            if (((aspects & VK_IMAGE_ASPECT_DEPTH_BIT) &&
-                 !(context.depthResolveModes & VK_RESOLVE_MODE_SAMPLE_ZERO_BIT)) ||
-                ((aspects & VK_IMAGE_ASPECT_STENCIL_BIT) &&
-                 !(context.stencilResolveModes & VK_RESOLVE_MODE_SAMPLE_ZERO_BIT))) {
-                skip("the render-pass arm is not taken for this format (no SAMPLE_ZERO resolve mode)");
-                continue;
-            }
-
-            FormatWork item;
-            item.reading = readingIndex;
-            item.format = format;
-            item.aspects = aspects;
-            if (!makeImage(format, kProbeSamples, kSourceUsage, item.subjectSource) ||
-                !makeImage(format, kProbeSamples, kSourceUsage, item.controlSource) ||
-                !makeImage(format, VK_SAMPLE_COUNT_1_BIT, kScratchUsage, item.subjectTarget)) {
-                skip("image creation failed");
-                continue;
-            }
-            if (CreateWireDepthStencilResolvePass(context.createRenderPass2, device, format, kProbeSamples,
-                                                  &item.resolvePass) != VK_SUCCESS) {
-                skip("the render-pass arm's vkCreateRenderPass2 failed");
-                continue;
-            }
-            objects.passes.push_back(item.resolvePass);
-            if (!makeView(WireDepthStencilViewInfo(item.subjectSource.image, format, aspects, 0, 0),
-                          item.resolveViews[0]) ||
-                !makeView(WireDepthStencilViewInfo(item.subjectTarget.image, format, aspects, 0, 0),
-                          item.resolveViews[1]) ||
-                !makeFramebuffer(item.resolvePass, item.resolveViews, 2, item.resolveFramebuffer)) {
-                skip("the render-pass arm's views or framebuffer could not be created");
-                continue;
-            }
-            if (!makeClear(item.subjectSource, format, kProbeSamples, kClearDepth, kClearStencil) ||
-                !makeClear(item.controlSource, format, kProbeSamples, kClearDepth, kClearStencil) ||
-                !makeClear(item.subjectTarget, format, VK_SAMPLE_COUNT_1_BIT, kSentinelDepth, kSentinelStencil)) {
-                skip("the clear passes could not be created");
-                continue;
-            }
-            // The control, one target per aspect: the shader pass's attachment is DONT_CARE on both
-            // aspects, so a second aspect's pass into the same target would discard the first.
-            const auto makeControl = [&](VkImageAspectFlags aspect, ControlPass& control) {
-                if (!kitFailure.empty()) return;
-                if (aspect == VK_IMAGE_ASPECT_STENCIL_BIT && objects.kit.stencilFragment == VK_NULL_HANDLE) return;
-                if (!makeImage(format, VK_SAMPLE_COUNT_1_BIT, kScratchUsage, control.target)) return;
-                if (CreateWireShaderResolveRenderPass(device, format, &control.pass) != VK_SUCCESS) return;
-                objects.passes.push_back(control.pass);
-                if (CreateWireShaderResolvePipeline(device, objects.kit, control.pass, aspect, &control.pipeline) !=
-                    VK_SUCCESS)
-                    return;
-                objects.pipelines.push_back(control.pipeline);
-                if (!makeView(WireDepthStencilViewInfo(item.controlSource.image, format, aspect, 0, 0),
-                              control.sampledView) ||
-                    !makeView(WireDepthStencilViewInfo(control.target.image, format, aspects, 0, 0),
-                              control.targetView) ||
-                    !makeFramebuffer(control.pass, &control.targetView, 1, control.framebuffer))
-                    return;
-                if (!makeClear(control.target, format, VK_SAMPLE_COUNT_1_BIT, kSentinelDepth, kSentinelStencil))
-                    return;
-                control.ready = true;
-            };
-            if (aspects & VK_IMAGE_ASPECT_DEPTH_BIT) makeControl(VK_IMAGE_ASPECT_DEPTH_BIT, item.depthControl);
-            if (aspects & VK_IMAGE_ASPECT_STENCIL_BIT) makeControl(VK_IMAGE_ASPECT_STENCIL_BIT, item.stencilControl);
-
-            if (aspects & VK_IMAGE_ASPECT_DEPTH_BIT) {
-                item.subjectDepthOffset = reserve(kProbeTexels * DepthCopyBytes(format));
-                if (item.depthControl.ready) item.depthControl.offset = reserve(kProbeTexels * DepthCopyBytes(format));
-            }
-            if (aspects & VK_IMAGE_ASPECT_STENCIL_BIT) {
-                item.subjectStencilOffset = reserve(kProbeTexels);
-                if (item.stencilControl.ready) item.stencilControl.offset = reserve(kProbeTexels);
-            }
-            slot.ran = true;
-            work.push_back(item);
-        }
-        if (work.empty()) return fail("no format could be probed");
-
-        // Descriptor sets for the controls, one per draw (the production shader arm's own rule).
-        Uint32 controlDraws = 0;
-        for (const FormatWork& item : work)
-            controlDraws += (item.depthControl.ready ? 1u : 0u) + (item.stencilControl.ready ? 1u : 0u);
-        if (controlDraws > 0) {
-            const VkDescriptorPoolSize poolSize{VK_DESCRIPTOR_TYPE_COMBINED_IMAGE_SAMPLER, controlDraws};
-            VkDescriptorPoolCreateInfo pool{VK_STRUCTURE_TYPE_DESCRIPTOR_POOL_CREATE_INFO};
-            pool.maxSets = controlDraws;
-            pool.poolSizeCount = 1;
-            pool.pPoolSizes = &poolSize;
-            if (vkCreateDescriptorPool(device, &pool, nullptr, &objects.descriptorPool) != VK_SUCCESS)
-                return fail("vkCreateDescriptorPool failed");
-            for (FormatWork& item : work) {
-                for (ControlPass* control : {&item.depthControl, &item.stencilControl}) {
-                    if (!control->ready) continue;
-                    VkDescriptorSetAllocateInfo alloc{VK_STRUCTURE_TYPE_DESCRIPTOR_SET_ALLOCATE_INFO};
-                    alloc.descriptorPool = objects.descriptorPool;
-                    alloc.descriptorSetCount = 1;
-                    alloc.pSetLayouts = &objects.kit.descriptorLayout;
-                    if (vkAllocateDescriptorSets(device, &alloc, &control->set) != VK_SUCCESS)
-                        return fail("vkAllocateDescriptorSets failed");
-                    const VkDescriptorImageInfo sampled{objects.kit.nearest, control->sampledView,
-                                                        VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL};
-                    VkWriteDescriptorSet write{VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET};
-                    write.dstSet = control->set;
-                    write.dstBinding = 0;
-                    write.descriptorCount = 1;
-                    write.descriptorType = VK_DESCRIPTOR_TYPE_COMBINED_IMAGE_SAMPLER;
-                    write.pImageInfo = &sampled;
-                    vkUpdateDescriptorSets(device, 1, &write, 0, nullptr);
-                }
-            }
-        }
-
-        // The host-visible readback buffer.
-        VkDeviceMemory bufferMemory = VK_NULL_HANDLE;
-        Bool bufferCoherent = false;
-        {
-            VkBufferCreateInfo info{VK_STRUCTURE_TYPE_BUFFER_CREATE_INFO};
-            info.size = bufferBytes;
-            info.usage = VK_BUFFER_USAGE_TRANSFER_DST_BIT;
-            info.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
-            if (vkCreateBuffer(device, &info, nullptr, &objects.buffer) != VK_SUCCESS)
-                return fail("vkCreateBuffer failed");
-            VkMemoryRequirements requirements{};
-            vkGetBufferMemoryRequirements(device, objects.buffer, &requirements);
-            const Optional<Uint32> type =
-                PickMemoryType(memoryProperties, requirements.memoryTypeBits, VK_MEMORY_PROPERTY_HOST_COHERENT_BIT,
-                               VK_MEMORY_PROPERTY_HOST_VISIBLE_BIT);
-            if (!type) return fail("no host-visible memory type for the readback buffer");
-            bufferCoherent = (memoryProperties.memoryTypes[*type].propertyFlags &
-                              VK_MEMORY_PROPERTY_HOST_COHERENT_BIT) != 0;
-            VkMemoryAllocateInfo allocate{VK_STRUCTURE_TYPE_MEMORY_ALLOCATE_INFO};
-            allocate.allocationSize = requirements.size;
-            allocate.memoryTypeIndex = *type;
-            if (vkAllocateMemory(device, &allocate, nullptr, &bufferMemory) != VK_SUCCESS)
-                return fail("vkAllocateMemory (readback) failed");
-            objects.memories.push_back(bufferMemory);
-            if (vkBindBufferMemory(device, objects.buffer, bufferMemory, 0) != VK_SUCCESS)
-                return fail("vkBindBufferMemory failed");
-        }
-
-        VkCommandPoolCreateInfo poolInfo{VK_STRUCTURE_TYPE_COMMAND_POOL_CREATE_INFO};
-        poolInfo.flags = VK_COMMAND_POOL_CREATE_TRANSIENT_BIT;
-        poolInfo.queueFamilyIndex = context.queueFamilyIndex;
-        if (vkCreateCommandPool(device, &poolInfo, nullptr, &objects.commandPool) != VK_SUCCESS)
-            return fail("vkCreateCommandPool failed");
-        VkCommandBufferAllocateInfo commandInfo{VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO};
-        commandInfo.commandPool = objects.commandPool;
-        commandInfo.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY;
-        commandInfo.commandBufferCount = 1;
-        VkCommandBuffer cmd = VK_NULL_HANDLE;
-        if (vkAllocateCommandBuffers(device, &commandInfo, &cmd) != VK_SUCCESS)
-            return fail("vkAllocateCommandBuffers failed");
-        VkCommandBufferBeginInfo beginInfo{VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO};
-        beginInfo.flags = VK_COMMAND_BUFFER_USAGE_ONE_TIME_SUBMIT_BIT;
-        if (vkBeginCommandBuffer(cmd, &beginInfo) != VK_SUCCESS) return fail("vkBeginCommandBuffer failed");
-
-        const VkRect2D fullRect{{0, 0}, {kProbeExtent, kProbeExtent}};
-        // (1) Every image UNDEFINED -> DEPTH_STENCIL_ATTACHMENT_OPTIMAL, the way TransitionWireImage
-        // moves a fresh image (source state from UNDEFINED, destination ALL_COMMANDS).
-        for (const FormatWork& item : work) {
-            const VkImage images[] = {item.subjectSource.image, item.controlSource.image, item.subjectTarget.image,
-                                      item.depthControl.ready ? item.depthControl.target.image : VK_NULL_HANDLE,
-                                      item.stencilControl.ready ? item.stencilControl.target.image : VK_NULL_HANDLE};
-            for (const VkImage image : images) {
-                if (image == VK_NULL_HANDLE) continue;
-                ImageBarrier(cmd, image, item.aspects, VK_IMAGE_LAYOUT_UNDEFINED,
-                             VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT, 0,
-                             VK_PIPELINE_STAGE_ALL_COMMANDS_BIT,
-                             VK_ACCESS_MEMORY_READ_BIT | VK_ACCESS_MEMORY_WRITE_BIT);
-            }
-        }
-        // (2) The inputs and the sentinels, cleared the wire's way.
-        for (const ClearPass& clear : clears) {
-            VkRenderPassBeginInfo begin{VK_STRUCTURE_TYPE_RENDER_PASS_BEGIN_INFO};
-            begin.renderPass = clear.pass;
-            begin.framebuffer = clear.framebuffer;
-            begin.renderArea = fullRect;
-            vkCmdBeginRenderPass(cmd, &begin, VK_SUBPASS_CONTENTS_INLINE);
-            VkClearAttachment attachment{};
-            attachment.aspectMask = clear.aspects;
-            attachment.clearValue.depthStencil = {clear.depth, clear.stencil};
-            const VkClearRect rect{fullRect, 0, 1};
-            vkCmdClearAttachments(cmd, 1, &attachment, 1, &rect);
-            vkCmdEndRenderPass(cmd);
-        }
-        // (3) What TransitionWireImage records when the layout already matches - the case of a
-        // source the application cleared and then resolves.
-        {
-            VkMemoryBarrier memory{VK_STRUCTURE_TYPE_MEMORY_BARRIER};
-            memory.srcAccessMask = VK_ACCESS_MEMORY_WRITE_BIT;
-            memory.dstAccessMask = VK_ACCESS_MEMORY_READ_BIT | VK_ACCESS_MEMORY_WRITE_BIT;
-            vkCmdPipelineBarrier(cmd, VK_PIPELINE_STAGE_ALL_COMMANDS_BIT, VK_PIPELINE_STAGE_ALL_COMMANDS_BIT, 0, 1,
-                                 &memory, 0, nullptr, 0, nullptr);
-        }
-        // (4) THE SUBJECT: the render-pass arm, begun and ended with no draw. Under the test-only
-        // elideSubject it is not recorded at all: its target keeps the sentinel cleared in (2) and
-        // the layout it was left in, which is what (6) expects either way.
-        if (!context.elideSubject) {
-            for (const FormatWork& item : work) {
-                VkRenderPassBeginInfo begin{VK_STRUCTURE_TYPE_RENDER_PASS_BEGIN_INFO};
-                begin.renderPass = item.resolvePass;
-                begin.framebuffer = item.resolveFramebuffer;
-                begin.renderArea = fullRect;
-                vkCmdBeginRenderPass(cmd, &begin, VK_SUBPASS_CONTENTS_INLINE);
-                vkCmdEndRenderPass(cmd);
-            }
-        }
-        // (5) THE CONTROL: the shader arm on the twin source, which TransitionWireImage moves to
-        // SHADER_READ_ONLY_OPTIMAL first (both aspects of a packed format).
-        for (const FormatWork& item : work) {
-            if (!item.depthControl.ready && !item.stencilControl.ready) continue;
-            ImageBarrier(cmd, item.controlSource.image, item.aspects, VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL,
-                         VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL,
-                         VK_PIPELINE_STAGE_EARLY_FRAGMENT_TESTS_BIT | VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT,
-                         VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_READ_BIT | VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE_BIT,
-                         VK_PIPELINE_STAGE_ALL_COMMANDS_BIT, VK_ACCESS_MEMORY_READ_BIT | VK_ACCESS_MEMORY_WRITE_BIT);
-            for (const ControlPass* control : {&item.depthControl, &item.stencilControl}) {
-                if (!control->ready) continue;
-                RecordWireShaderResolveDraw(cmd, objects.kit, control->pass, control->pipeline, control->framebuffer,
-                                            control->set, {kProbeExtent, kProbeExtent}, fullRect);
-            }
-        }
-        // (6) Every target to TRANSFER_SRC with the barrier ResolveWireDepthStencil puts after its
-        // resolve (a depth/stencil resolve writes in COLOR_ATTACHMENT_OUTPUT), then one copy per aspect.
-        const auto copyOut = [&](VkImage image, VkImageAspectFlags aspect, VkDeviceSize offset) {
-            VkBufferImageCopy copy{};
-            copy.bufferOffset = offset;
-            copy.imageSubresource = {aspect, 0, 0, 1};
-            copy.imageExtent = {kProbeExtent, kProbeExtent, 1};
-            vkCmdCopyImageToBuffer(cmd, image, VK_IMAGE_LAYOUT_TRANSFER_SRC_OPTIMAL, objects.buffer, 1, &copy);
-        };
-        const auto toTransfer = [&](VkImage image, VkImageAspectFlags aspects) {
-            ImageBarrier(cmd, image, aspects, VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL,
-                         VK_IMAGE_LAYOUT_TRANSFER_SRC_OPTIMAL,
-                         VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT | VK_PIPELINE_STAGE_EARLY_FRAGMENT_TESTS_BIT |
-                             VK_PIPELINE_STAGE_LATE_FRAGMENT_TESTS_BIT,
-                         VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT | VK_ACCESS_DEPTH_STENCIL_ATTACHMENT_WRITE_BIT,
-                         VK_PIPELINE_STAGE_TRANSFER_BIT, VK_ACCESS_TRANSFER_READ_BIT);
-        };
-        for (const FormatWork& item : work) {
-            toTransfer(item.subjectTarget.image, item.aspects);
-            if (item.aspects & VK_IMAGE_ASPECT_DEPTH_BIT)
-                copyOut(item.subjectTarget.image, VK_IMAGE_ASPECT_DEPTH_BIT, item.subjectDepthOffset);
-            if (item.aspects & VK_IMAGE_ASPECT_STENCIL_BIT)
-                copyOut(item.subjectTarget.image, VK_IMAGE_ASPECT_STENCIL_BIT, item.subjectStencilOffset);
-            if (item.depthControl.ready) {
-                toTransfer(item.depthControl.target.image, item.aspects);
-                copyOut(item.depthControl.target.image, VK_IMAGE_ASPECT_DEPTH_BIT, item.depthControl.offset);
-            }
-            if (item.stencilControl.ready) {
-                toTransfer(item.stencilControl.target.image, item.aspects);
-                copyOut(item.stencilControl.target.image, VK_IMAGE_ASPECT_STENCIL_BIT, item.stencilControl.offset);
-            }
-        }
-        {
-            VkBufferMemoryBarrier barrier{VK_STRUCTURE_TYPE_BUFFER_MEMORY_BARRIER};
-            barrier.srcAccessMask = VK_ACCESS_TRANSFER_WRITE_BIT;
-            barrier.dstAccessMask = VK_ACCESS_HOST_READ_BIT;
-            barrier.srcQueueFamilyIndex = barrier.dstQueueFamilyIndex = VK_QUEUE_FAMILY_IGNORED;
-            barrier.buffer = objects.buffer;
-            barrier.size = VK_WHOLE_SIZE;
-            vkCmdPipelineBarrier(cmd, VK_PIPELINE_STAGE_TRANSFER_BIT, VK_PIPELINE_STAGE_HOST_BIT, 0, 0, nullptr, 1,
-                                 &barrier, 0, nullptr);
-        }
-        if (vkEndCommandBuffer(cmd) != VK_SUCCESS) return fail("vkEndCommandBuffer failed");
-
-        VkFenceCreateInfo fenceInfo{VK_STRUCTURE_TYPE_FENCE_CREATE_INFO};
-        if (vkCreateFence(device, &fenceInfo, nullptr, &objects.fence) != VK_SUCCESS)
-            return fail("vkCreateFence failed");
-        VkSubmitInfo submit{VK_STRUCTURE_TYPE_SUBMIT_INFO};
-        submit.commandBufferCount = 1;
-        submit.pCommandBuffers = &cmd;
-        if (const VkResult result = vkQueueSubmit(context.queue, 1, &submit, objects.fence); result != VK_SUCCESS)
-            return fail(format("vkQueueSubmit failed (VkResult {})", static_cast<Int>(result)));
-        const VkResult waited = vkWaitForFences(device, 1, &objects.fence, VK_TRUE, kFenceTimeoutNs);
-        if (waited == VK_TIMEOUT) {
-            // The submission may still be executing: destroying anything it names, or idle-waiting
-            // the device, is the hang the bound exists to prevent. Everything leaks.
-            leak = true;
-            measurement.fenceWaitTimedOut = true;
-            return fail("the probe's fence did not signal within 5 s");
-        }
-        if (waited != VK_SUCCESS) return fail(format("vkWaitForFences failed (VkResult {})", static_cast<Int>(waited)));
-
-        void* mapped = nullptr;
-        if (vkMapMemory(device, bufferMemory, 0, VK_WHOLE_SIZE, 0, &mapped) != VK_SUCCESS || mapped == nullptr)
-            return fail("vkMapMemory failed");
-        if (!bufferCoherent) {
-            VkMappedMemoryRange range{VK_STRUCTURE_TYPE_MAPPED_MEMORY_RANGE};
-            range.memory = bufferMemory;
-            range.size = VK_WHOLE_SIZE;
-            vkInvalidateMappedMemoryRanges(device, 1, &range);
-        }
-        const Uint8* bytes = static_cast<const Uint8*>(mapped);
-        const auto tally = [&](WireDepthResolveAspectReading& aspect, VkDeviceSize offset, Uint32 texelBytes,
-                               Bool depth, VkFormat format, Bool subject) {
-            Uint32 matches = 0, sentinels = 0, first = 0;
-            for (Uint32 i = 0; i < kProbeTexels; ++i) {
-                const Uint8* texel = bytes + offset + static_cast<VkDeviceSize>(i) * texelBytes;
-                const Uint32 word = depth ? ReadDepthWord(format, texel) : static_cast<Uint32>(*texel);
-                if (i == 0) first = word;
-                if (WordDistance(word, aspect.expected) <= aspect.tolerance) ++matches;
-                if (WordDistance(word, aspect.sentinel) <= aspect.tolerance) ++sentinels;
-            }
-            if (subject) {
-                aspect.renderPassMatches = matches;
-                aspect.renderPassSentinels = sentinels;
-                aspect.renderPassFirst = first;
-            } else {
-                aspect.shaderRan = true;
-                aspect.shaderMatches = matches;
-                aspect.shaderFirst = first;
-            }
-        };
-        for (const FormatWork& item : work) {
-            WireDepthResolveFormatReading& reading = measurement.formats[item.reading];
-            if (item.aspects & VK_IMAGE_ASPECT_DEPTH_BIT) {
-                auto& aspect = reading.depth;
-                aspect.measured = true;
-                aspect.texels = kProbeTexels;
-                aspect.expected = EncodeDepth(item.format, kClearDepth);
-                aspect.sentinel = EncodeDepth(item.format, kSentinelDepth);
-                aspect.tolerance = IsFloatDepth(item.format) ? 0u : 1u;
-                tally(aspect, item.subjectDepthOffset, DepthCopyBytes(item.format), true, item.format, true);
-                if (item.depthControl.ready)
-                    tally(aspect, item.depthControl.offset, DepthCopyBytes(item.format), true, item.format, false);
-            }
-            if (item.aspects & VK_IMAGE_ASPECT_STENCIL_BIT) {
-                auto& aspect = reading.stencil;
-                aspect.measured = true;
-                aspect.texels = kProbeTexels;
-                aspect.expected = kClearStencil;
-                aspect.sentinel = kSentinelStencil;
-                aspect.tolerance = 0;
-                tally(aspect, item.subjectStencilOffset, 1, false, item.format, true);
-                if (item.stencilControl.ready)
-                    tally(aspect, item.stencilControl.offset, 1, false, item.format, false);
-            }
-        }
-        vkUnmapMemory(device, bufferMemory);
-        measurement.ran = true;
-        if (!kitFailure.empty()) measurement.failureReason = kitFailure;
-        return measurement;
-    }
-
-    WireDepthResolveProbeMeasurement RunWireDepthResolveProbeOnThrowawayDevice(
-        PFN_vkGetInstanceProcAddr getInstanceProcAddr, VkInstance instance, VkPhysicalDevice physicalDevice,
-        Uint32 graphicsQueueFamilyIndex, const Vector<VkExtensionProperties>& deviceExtensions,
-        Bool& renderPassArmAvailable, Bool& shaderStencilExport) {
-        WireDepthResolveProbeMeasurement measurement;
-        const auto has = [&](const char* name) {
-            for (const VkExtensionProperties& extension : deviceExtensions)
-                if (std::strcmp(extension.extensionName, name) == 0) return true;
-            return false;
-        };
-        renderPassArmAvailable = has(VK_KHR_CREATE_RENDERPASS_2_EXTENSION_NAME) &&
-                                 has(VK_KHR_DEPTH_STENCIL_RESOLVE_EXTENSION_NAME);
-        shaderStencilExport = has(VK_EXT_SHADER_STENCIL_EXPORT_EXTENSION_NAME);
-        if (!renderPassArmAvailable) {
-            measurement.failureReason = "no VK_KHR_create_renderpass2 + VK_KHR_depth_stencil_resolve";
-            return measurement;
-        }
-        VkPhysicalDeviceProperties properties{};
-        vkGetPhysicalDeviceProperties(physicalDevice, &properties);
-        auto getProperties2 = reinterpret_cast<PFN_vkGetPhysicalDeviceProperties2>(
-            getInstanceProcAddr(instance, "vkGetPhysicalDeviceProperties2"));
-        if (getProperties2 == nullptr)
-            getProperties2 = reinterpret_cast<PFN_vkGetPhysicalDeviceProperties2>(
-                getInstanceProcAddr(instance, "vkGetPhysicalDeviceProperties2KHR"));
-        const auto createDevice =
-            reinterpret_cast<PFN_vkCreateDevice>(getInstanceProcAddr(instance, "vkCreateDevice"));
-        if (properties.apiVersion < VK_API_VERSION_1_1 || getProperties2 == nullptr || createDevice == nullptr) {
-            renderPassArmAvailable = false;
-            measurement.failureReason = "a pre-1.1 device, or no vkGetPhysicalDeviceProperties2 / vkCreateDevice";
-            return measurement;
-        }
-        VkPhysicalDeviceDepthStencilResolveProperties resolveProperties{
-            VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_DEPTH_STENCIL_RESOLVE_PROPERTIES};
-        VkPhysicalDeviceProperties2 properties2{VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_PROPERTIES_2};
-        properties2.pNext = &resolveProperties;
-        getProperties2(physicalDevice, &properties2);
-
-        // The renderer's own extension set for the two arms (VulkanRenderer.cpp,
-        // CreateLogicalDeviceAndQueues), nothing more.
-        const Float priority = 1.0f;
-        VkDeviceQueueCreateInfo queueInfo{VK_STRUCTURE_TYPE_DEVICE_QUEUE_CREATE_INFO};
-        queueInfo.queueFamilyIndex = graphicsQueueFamilyIndex;
-        queueInfo.queueCount = 1;
-        queueInfo.pQueuePriorities = &priority;
-        Vector<const char*> extensions{VK_KHR_CREATE_RENDERPASS_2_EXTENSION_NAME,
-                                       VK_KHR_DEPTH_STENCIL_RESOLVE_EXTENSION_NAME};
-        if (shaderStencilExport) extensions.push_back(VK_EXT_SHADER_STENCIL_EXPORT_EXTENSION_NAME);
-        VkDeviceCreateInfo deviceInfo{VK_STRUCTURE_TYPE_DEVICE_CREATE_INFO};
-        deviceInfo.queueCreateInfoCount = 1;
-        deviceInfo.pQueueCreateInfos = &queueInfo;
-        deviceInfo.enabledExtensionCount = static_cast<Uint32>(extensions.size());
-        deviceInfo.ppEnabledExtensionNames = extensions.data();
-        VkDevice device = VK_NULL_HANDLE;
-        if (const VkResult result = createDevice(physicalDevice, &deviceInfo, nullptr, &device);
-            result != VK_SUCCESS || device == VK_NULL_HANDLE) {
-            measurement.failureReason = format("vkCreateDevice failed (VkResult {})", static_cast<Int>(result));
-            return measurement;
-        }
-        WireDepthResolveProbeContext context;
-        context.physicalDevice = physicalDevice;
-        context.device = device;
-        vkGetDeviceQueue(device, graphicsQueueFamilyIndex, 0, &context.queue);
-        context.queueFamilyIndex = graphicsQueueFamilyIndex;
-        context.createRenderPass2 =
-            reinterpret_cast<PFN_vkCreateRenderPass2>(vkGetDeviceProcAddr(device, "vkCreateRenderPass2KHR"));
-        context.depthResolveModes = resolveProperties.supportedDepthResolveModes;
-        context.stencilResolveModes = resolveProperties.supportedStencilResolveModes;
-        context.shaderStencilExport = shaderStencilExport;
-        measurement = RunWireDepthResolveProbe(context);
-        // A timed-out probe leaked its children on purpose; destroying their device would block
-        // exactly where the bound says not to.
-        if (!measurement.fenceWaitTimedOut) vkDestroyDevice(device, nullptr);
-        return measurement;
-    }
-} // namespace MobileGL::MG_Backend::DirectVulkan
-#endif

MobileGL/MG_Backend/DirectVulkan/Renderer/WireDepthResolveProbe.h

@@ -1,121 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/WireDepthResolveProbe.h
-// Copyright (c) 2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-#pragma once
-
-#include "WireDepthResolveArm.h"
-
-#include <Config.h>
-#include <Includes.h>
-
-// P7 gate 5 (g5-msprobe): the Vulkan half of the multisample depth/stencil resolve probe, and the
-// two resolve arms it measures.
-//
-// THE ARMS LIVE HERE, NOT ONLY IN THE RENDERER. A probe that rebuilt "something like" the wire's
-// render pass would measure its own copy; the render-pass description, the shader pass's modules,
-// pipeline and draw, and the view shapes both arms attach are defined once below and called by
-// ResolveWireDepthStencil (WireFramebuffer.inc), ResolveWireDepthStencilWithShader
-// (WireMultisampleResolve.inc) and the probe alike.
-//
-// Two callers: the Magma renderer at device bring-up (server side, once per process, only where
-// the render-pass arm exists at all - VulkanRenderer::ArmWireDepthResolveOrder) and the POST's
-// "Known Driver Bugs" section (MG_Util/SelfTest/DriverBugProbes.cpp) on a throwaway device.
-//
-// Disaggregated builds only: the monolith never records either arm, and the pull build's image
-// must not change (P7 gate G1).
-#if MOBILEGL_BUILD_DISAGGREGATED
-namespace MobileGL::MG_Backend::DirectVulkan {
-    // Every aspect a wire depth/stencil format has.
-    VkImageAspectFlags WireDepthStencilFormatAspects(VkFormat format);
-
-    // A 2D view of one level/layer of a depth/stencil image naming `aspects`. The render-pass arm
-    // attaches both images with every aspect of the format; the shader arm SAMPLES its source
-    // through a view of exactly one aspect (a depth/stencil image can only be sampled that way) and
-    // attaches its target with every aspect.
-    VkImageViewCreateInfo WireDepthStencilViewInfo(VkImage image, VkFormat format, VkImageAspectFlags aspects,
-                                                   Uint32 level, Uint32 layer);
-
-    // THE RENDER-PASS ARM: attachment 0 the multisample source (LOAD/STORE), attachment 1 the
-    // single-sample resolve target (DONT_CARE/STORE), both in DEPTH_STENCIL_ATTACHMENT_OPTIMAL, one
-    // subpass whose VkSubpassDescriptionDepthStencilResolve resolves every aspect of the format
-    // with VK_RESOLVE_MODE_SAMPLE_ZERO_BIT. The caller begins and ends it with NO draw.
-    VkResult CreateWireDepthStencilResolvePass(PFN_vkCreateRenderPass2 createRenderPass2, VkDevice device,
-                                               VkFormat format, VkSampleCountFlagBits samples, VkRenderPass* pass);
-
-    // THE SHADER ARM's device objects that do not depend on the format.
-    struct WireShaderResolveKit {
-        VkShaderModule vertex = VK_NULL_HANDLE;
-        VkShaderModule depthFragment = VK_NULL_HANDLE;
-        // Only where VK_EXT_shader_stencil_export is enabled: its SPIR-V declares StencilExportEXT.
-        VkShaderModule stencilFragment = VK_NULL_HANDLE;
-        VkDescriptorSetLayout descriptorLayout = VK_NULL_HANDLE;
-        VkPipelineLayout pipelineLayout = VK_NULL_HANDLE;
-        VkSampler nearest = VK_NULL_HANDLE;
-    };
-    // Creates every member; the first failure is returned and the members made so far stay set,
-    // for DestroyWireShaderResolveKit.
-    VkResult CreateWireShaderResolveKit(VkDevice device, Bool shaderStencilExport, WireShaderResolveKit& kit);
-    void DestroyWireShaderResolveKit(VkDevice device, WireShaderResolveKit& kit);
-    // One (format, aspect)'s single-attachment render pass: DONT_CARE/STORE on both aspects,
-    // DEPTH_STENCIL_ATTACHMENT_OPTIMAL throughout.
-    VkResult CreateWireShaderResolveRenderPass(VkDevice device, VkFormat format, VkRenderPass* pass);
-    // Its pipeline: full-screen triangle, gl_FragDepth (ALWAYS + write) or gl_FragStencilRefARB
-    // (REPLACE everywhere), viewport and scissor dynamic. VK_ERROR_FEATURE_NOT_PRESENT when the kit
-    // has no fragment module for `aspect`.
-    VkResult CreateWireShaderResolvePipeline(VkDevice device, const WireShaderResolveKit& kit, VkRenderPass pass,
-                                             VkImageAspectFlags aspect, VkPipeline* pipeline);
-    // Records the draw: the render area and the scissor are `rect`, the viewport is the WHOLE
-    // attachment (gl_FragCoord is what the fragment stage fetches by), one triangle.
-    void RecordWireShaderResolveDraw(VkCommandBuffer commandBuffer, const WireShaderResolveKit& kit,
-                                     VkRenderPass pass, VkPipeline pipeline, VkFramebuffer framebuffer,
-                                     VkDescriptorSet descriptorSet, VkExtent2D attachmentExtent, VkRect2D rect);
-
-    // What the probe runs on. The device must have been created with VK_KHR_create_renderpass2 and
-    // VK_KHR_depth_stencil_resolve (or Vulkan 1.2 core), and with VK_EXT_shader_stencil_export where
-    // `shaderStencilExport` says so. The queue must be otherwise idle for the probe's duration.
-    struct WireDepthResolveProbeContext {
-        VkPhysicalDevice physicalDevice = VK_NULL_HANDLE;
-        VkDevice device = VK_NULL_HANDLE;
-        VkQueue queue = VK_NULL_HANDLE;
-        Uint32 queueFamilyIndex = 0;
-        PFN_vkCreateRenderPass2 createRenderPass2 = nullptr;
-        VkResolveModeFlags depthResolveModes = 0;
-        VkResolveModeFlags stencilResolveModes = 0;
-        Bool shaderStencilExport = false;
-        // TEST ONLY (MGITEST_MAGMA_DEPTH_RESOLVE_PROBE=elide-subject, WireDepthResolveArm.h): record
-        // NO render-pass resolve, so every subject target keeps its sentinel - the Adreno 830's
-        // reading - while the shader control runs as always. Everything else is the real probe.
-        Bool elideSubject = false;
-    };
-
-    // Per format the device can host as a 4x multisample depth/stencil attachment AND for which
-    // ResolveWireDepthStencil would take the render-pass arm (D16, X8_D24, D32F, D24S8, D32FS8, S8):
-    //   - two identical 4x4 4x multisample sources (production usage), each cleared to depth 0.25 /
-    //     stencil 0x5A the way the wire clears (a LOAD pass with vkCmdClearAttachments);
-    //   - single-sample resolve targets (the production scratch usage) pre-filled with the sentinel
-    //     depth 0.75 / stencil 0xA5;
-    //   - SUBJECT: the render-pass arm's exact pass, begun and ended with no draw;
-    //   - CONTROL: the shader arm's exact pass on the other source, one target per aspect (stencil
-    //     only with VK_EXT_shader_stencil_export);
-    //   - every target copied aspect by aspect into a host-visible buffer and compared texel by texel.
-    // One submission, a bounded fence wait (on timeout every object is leaked and the measurement
-    // says so - the caller must then not destroy or idle-wait the device), teardown on every other
-    // path. Never touches renderer state.
-    WireDepthResolveProbeMeasurement RunWireDepthResolveProbe(const WireDepthResolveProbeContext& context);
-
-    // The POST's entry: creates a throwaway device on `physicalDevice` with exactly the extensions
-    // the renderer enables for the two arms, runs the probe on its graphics queue and destroys the
-    // device (leaks it on a fence timeout). `renderPassArmAvailable` is false - and nothing is run -
-    // when the device lacks VK_KHR_create_renderpass2 / VK_KHR_depth_stencil_resolve; the shader
-    // pass is then the only arm and the probe has nothing to choose between.
-    // `shaderStencilExport` reports whether VK_EXT_shader_stencil_export was available.
-    WireDepthResolveProbeMeasurement RunWireDepthResolveProbeOnThrowawayDevice(
-        PFN_vkGetInstanceProcAddr getInstanceProcAddr, VkInstance instance, VkPhysicalDevice physicalDevice,
-        Uint32 graphicsQueueFamilyIndex, const Vector<VkExtensionProperties>& deviceExtensions,
-        Bool& renderPassArmAvailable, Bool& shaderStencilExport);
-} // namespace MobileGL::MG_Backend::DirectVulkan
-#endif

MobileGL/MG_Backend/DirectVulkan/Renderer/WireDraw.inc

@@ -1,631 +0,0 @@
-// Server-owned draw/dispatch setup. The legacy setup remains the monolith implementation.
-#if MOBILEGL_BUILD_DISAGGREGATED
-    static MagmaProgramSource WireProgramSource(MG_Pipe::MGPipeHandle handle) {
-        auto& state = MG_Pipe::MGPipeApplier();
-        const Bool composite = handle.Slot >= MG_Pipe::kMGPipeShaderCsoCompositeSlotBase;
-        const auto& records = composite ? state.CompositeShaderCsos : state.ShaderCsos;
-        const SizeT index = composite ? handle.Slot - MG_Pipe::kMGPipeShaderCsoCompositeSlotBase : handle.Slot;
-        if (MG_Pipe::MGPipeHandleIsNull(handle) || index >= records.size() ||
-            !records[index].Live || records[index].Gen != handle.Gen || !records[index].Archive)
-            MagmaWireFatal("program-record");
-        return MagmaProgramSource(handle, records[index]);
-    }
-
-    // Through the same seam as MagmaWireFatal, and for the same reason (P7 wave 0). The family
-    // stays RoleViolation: reaching the legacy buffer arm inside a Magma server is a role
-    // invariant the two halves must hold, not a verb the wire failed to migrate.
-    [[noreturn]] static void WireBufferLegacyFatal() {
-        MG_Pipe::MGPipeSessionFail(
-            MG_Pipe::MGPipeFatalFamily::RoleViolation,
-            "MGPipe: Fatal{RoleViolation, \"buffer-legacy-arm\"} (Magma P7 buffer consumer)");
-    }
-
-    static const MG_Pipe::MGPStreamOutputBegin& WireXfbSpan() {
-        const auto& state = MG_Pipe::MGPipeApplier();
-        const auto found = state.StreamOutputSpans.find(state.BoundStreamOutputLifetimeId);
-        if (found == state.StreamOutputSpans.end()) MagmaWireFatal("xfb-span-record");
-        return found->second;
-    }
-
-    Bool VulkanRenderer::BeginWireXfbCaptureForDraw(FrameContext::FrameData& frame) {
-        const auto& span = WireXfbSpan();
-        const auto program = WireProgramSource(span.CaptureProgram);
-        const Uint32 count = static_cast<Uint32>(std::min<SizeT>(program.GetTransformFeedbackBufferCount(), 4));
-        if (!count || !program.GetTransformFeedbackVaryingCount()) return false;
-        VkBuffer buffers[4]{};
-        VkDeviceSize offsets[4]{};
-        VkDeviceSize sizes[4]{};
-        Bool hasTarget = false;
-        for (Uint32 i = 0; i < count; ++i) {
-            // A leading gl_NextBuffer leaves a hole in the binding indices. No
-            // output names that zero-stride target, and GL need not bind a buffer.
-            if (!program.GetTransformFeedbackStride(i)) continue;
-            const auto& target = span.Targets[i];
-            BufferSlice slice{};
-            if (MG_Pipe::MGPipeHandleIsNull(target.Res) ||
-                !m_bufferManager.AcquireWireSlice(BufferKind::Vertex, target.Res, slice))
-                MagmaWireFatal("xfb-buffer-resource");
-            if (target.Offset >= slice.size) return false;
-            const Uint64 size = target.Size == 0 || target.Size == MG_Pipe::kMGPipeWholeBuffer
-                ? slice.size - target.Offset : target.Size;
-            if (!size || size > slice.size - target.Offset) return false;
-            buffers[i] = slice.buffer;
-            offsets[i] = slice.offset + target.Offset;
-            sizes[i] = size;
-            hasTarget = true;
-            // The server owns the storage. Publish dirtiness through the existing
-            // reverse channel so CPU readback does not reuse the client's old shadow.
-            m_bufferManager.MarkWireBufferGpuWritten(target.Res, target.Offset, size);
-        }
-        if (!hasTarget) return false;
-        return BeginXfbCaptureWithBuffers(frame, count, buffers, offsets, sizes);
-    }
-
-    static Bool ConvertWireVertexStream(const MGPVertexAttribWire& attr,
-            VertexInputStateFactory::VertexStreamConversion conversion, const Uint8* source,
-            SizeT stride, SizeT count, Vector<Uint8>& output) {
-        using Conversion = VertexInputStateFactory::VertexStreamConversion;
-        const auto type = static_cast<DataType>(attr.Type);
-        const SizeT elementBytes = VertexInputStateFactory::GetAttributeByteSize(type, attr.Size, attr.IsBgra);
-        if (conversion == Conversion::Repack) {
-            output.resize(count * elementBytes);
-            for (SizeT i = 0; i < count; ++i)
-                Memcpy(output.data() + i * elementBytes, source + i * stride, elementBytes);
-            return true;
-        }
-        output.resize(count * attr.Size * sizeof(Float));
-        const auto convert = [&]<typename T>() {
-            for (SizeT i = 0; i < count; ++i) {
-                for (SizeT component = 0; component < attr.Size; ++component) {
-                    T value{};
-                    Memcpy(&value, source + i * stride + component * sizeof(T), sizeof(T));
-                    const Float converted = static_cast<Float>(value);
-                    Memcpy(output.data() + (i * attr.Size + component) * sizeof(Float), &converted, sizeof(Float));
-                }
-            }
-            return true;
-        };
-        switch (type) {
-        case DataType::Float64: return convert.template operator()<Double>();
-        case DataType::Int8: return convert.template operator()<Int8>();
-        case DataType::Uint8: return convert.template operator()<Uint8>();
-        case DataType::Int16: return convert.template operator()<Int16>();
-        case DataType::Uint16: return convert.template operator()<Uint16>();
-        case DataType::Int32: return convert.template operator()<Int32>();
-        case DataType::Uint32: return convert.template operator()<Uint32>();
-        default: return false;
-        }
-    }
-
-    void VulkanRenderer::DestroyWireDrawPass() {
-        // Only shutdown/swapchain replacement calls this, after device idle.
-        if (m_wireDrawPass && m_frameContext.GetFrameCount() != 0) {
-            auto& frame = m_frameContext.GetCurrent();
-            if (frame.isCommandRecording && VkRenderPassManager::GetActiveRenderPass())
-                VkRenderPassManager::EndRenderPass(frame.commandBuffer);
-        }
-        m_wireDrawPass.reset();
-        for (const auto view : m_wireDrawViews) vkDestroyImageView(m_device, view, nullptr);
-        m_wireDrawViews.clear();
-        m_wireDrawPassKey = {};
-    }
-
-    void VulkanRenderer::RetireWireObjects(WireRetiredObjects objects) {
-        // The current recording is the next graphics submission. Do not use a
-        // frame number: mid-frame flushes and readbacks can split one frame.
-        objects.submitIndex = m_submitCounter + 1;
-        m_wireRetiredObjects.push_back(Move(objects));
-    }
-
-    void VulkanRenderer::RetireWireDrawPass() {
-        if (!m_wireDrawPass) return;
-        auto& frame = m_frameContext.GetCurrent();
-        if (frame.isCommandRecording && VkRenderPassManager::GetActiveRenderPass())
-            VkRenderPassManager::EndRenderPass(frame.commandBuffer);
-        const Uint32 frameIndex = m_frameContext.GetCurrentFrameIndex();
-        if (m_wireDrawPassCaches.size() < m_frameContext.GetFrameCount())
-            m_wireDrawPassCaches.resize(m_frameContext.GetFrameCount());
-        auto& cache = m_wireDrawPassCaches[frameIndex];
-        // Bound a present-less stream of distinct framebuffer configurations.
-        // Overflow retains the original submit-index retirement path.
-        constexpr SizeT kMaxCachedWirePassesPerFrame = 32;
-        if (cache.size() < kMaxCachedWirePassesPerFrame) {
-            cache.push_back({Move(m_wireDrawPassKey), Move(m_wireDrawPass), Move(m_wireDrawViews)});
-            return;
-        }
-        WireRetiredObjects retired{};
-        retired.drawPass = Move(m_wireDrawPass);
-        retired.imageViews = Move(m_wireDrawViews);
-        RetireWireObjects(Move(retired));
-        m_wireDrawPassKey = {};
-    }
-
-    Bool VulkanRenderer::AcquireCachedWireDrawPass(const WireDrawPassKey& key) {
-        const Uint32 frameIndex = m_frameContext.GetCurrentFrameIndex();
-        if (frameIndex >= m_wireDrawPassCaches.size()) return false;
-        auto& cache = m_wireDrawPassCaches[frameIndex];
-        for (auto it = cache.begin(); it != cache.end(); ++it) {
-            // Exact values, not a compatibility hash: two FBOs with the same
-            // formats can name different images, windows or draw-buffer slots.
-            if (!(it->key == key)) continue;
-            m_wireDrawPassKey = Move(it->key);
-            m_wireDrawPass = Move(it->pass);
-            m_wireDrawViews = Move(it->views);
-            cache.erase(it);
-            return true;
-        }
-        return false;
-    }
-
-    void VulkanRenderer::ClearWireDrawPassCache(Uint32 frameIndex) {
-        if (frameIndex >= m_wireDrawPassCaches.size()) return;
-        auto& cache = m_wireDrawPassCaches[frameIndex];
-        for (auto& entry : cache) {
-            entry.pass.reset();
-            for (const auto view : entry.views) vkDestroyImageView(m_device, view, nullptr);
-        }
-        cache.clear();
-    }
-
-    void VulkanRenderer::ClearAllWireDrawPassCaches() {
-        for (Uint32 frameIndex = 0; frameIndex < m_wireDrawPassCaches.size(); ++frameIndex)
-            ClearWireDrawPassCache(frameIndex);
-    }
-
-    void VulkanRenderer::CollectWireObjects(Uint64 completedSubmit, Bool all) {
-        SizeT retained = 0;
-        for (SizeT index = 0; index < m_wireRetiredObjects.size(); ++index) {
-            auto& entry = m_wireRetiredObjects[index];
-            if (!all && entry.submitIndex > completedSubmit) {
-                if (retained != index) m_wireRetiredObjects[retained] = Move(entry);
-                ++retained;
-                continue;
-            }
-            // Framebuffers/descriptor sets stop naming their views first.
-            entry.drawPass.reset();
-            for (const auto pool : entry.descriptorPools) vkDestroyDescriptorPool(m_device, pool, nullptr);
-            for (const auto framebuffer : entry.framebuffers) vkDestroyFramebuffer(m_device, framebuffer, nullptr);
-            for (const auto pass : entry.renderPasses) vkDestroyRenderPass(m_device, pass, nullptr);
-            for (const auto view : entry.imageViews) vkDestroyImageView(m_device, view, nullptr);
-        }
-        // Erase once: repeated front erases move the whole remaining cohort for
-        // every draw retired by a fence, turning a batch retirement quadratic.
-        m_wireRetiredObjects.resize(retained);
-    }
-
-    struct WirePreparationScope {
-        Uint32& depth;
-        explicit WirePreparationScope(Uint32& value) : depth(value) { ++depth; }
-        ~WirePreparationScope() { --depth; }
-    };
-
-    Bool VulkanRenderer::SetupWireDraw(FrameContext::FrameData& frame, GLenum mode,
-            Flags<DrawSetupAspect> aspects, const DrawCmdParam& drawParams, const IndexBufferView* indices) {
-        auto& state = MG_Pipe::MGPipeApplier();
-        const auto program = WireProgramSource(state.BoundShaderCso);
-        if (!program.GetLinkStatus() || !program.GetSpirvStatus()) {
-            MGL_WIRE_DECLINE_AT(ProgramLinkOrSpirv, "program is not linked or carries no SPIR-V");
-            return false;
-        }
-        if (aspects & DrawSetupAspect::IndirectDrawBuffer)
-            WireBufferLegacyFatal();
-        MakeXfbWritesVisible();
-        const auto* fbo = state.DrawFramebuffer();
-        if (!fbo) MagmaWireFatal("draw-framebuffer-record");
-        RetireWireDrawPass();
-        // CPU preparation may synchronize GPU-produced vertex/index bytes. Do
-        // not rewind an arena while this draw owns as-yet-unrecorded slices.
-        WirePreparationScope preparing(m_wirePreparationDepth);
-
-        ProgramFactory::CompileOptionFlags flags =
-            ProgramFactory::CompileOptionFlags(GetBaseTransformFlagsRaw(fbo->IsDefault));
-        if (m_transformFeedbackFeatureEnabled && MGB_CTX->IsTransformFeedbackActive() &&
-            program.GetTransformFeedbackVaryingCount() > 0)
-            flags |= ProgramFactory::CompileOptionBit::XfbCapture;
-        const auto* programObject = &m_programFactory->GetOrCreateProgram(program, flags);
-        if (!(aspects & DrawSetupAspect::IndexBuffer) && programObject->readsBaseVertexBuiltin) {
-            flags |= ProgramFactory::CompileOptionBit::ZeroBaseVertex;
-            programObject = &m_programFactory->GetOrCreateProgram(program, flags);
-        }
-        if (programObject->pointSizeCapabilityUnsupported) {
-            MGL_WIRE_DECLINE_AT(PointSizeCapability, "the program writes gl_PointSize and the device cannot express it");
-            return false;
-        }
-        const auto& programObj = *programObject;
-        m_currentDrawXfbCaptureDeclined = programObj.xfbCaptureDeclined;
-        if (!m_uniformManager->PrepareWireTextureResources(program, programObj)) {
-            MGL_WIRE_DECLINE_AT(TextureResourcesUnprepared, "a sampled/storage image could not be made ready; see the Tex* tally");
-            return false;
-        }
-        // Lazy image uploads/promotions can submit the old recording. Resolve
-        // ALL attachments before descriptor binding captures the current cmd.
-        for (Uint32 i = 0; i < MG_Pipe::kMGPipeMaxColorAttachments; ++i) {
-            const Int32 slot = fbo->DrawBuffers[i];
-            if (slot >= 0) (void)ResolveWireImage(*fbo, fbo->Color[slot], VK_IMAGE_ASPECT_COLOR_BIT);
-        }
-        if (fbo->IsDefault || fbo->Depth.Kind != MG_Pipe::kMGPipeSurfaceKindNone)
-            (void)ResolveWireImage(*fbo, fbo->Depth, VK_IMAGE_ASPECT_DEPTH_BIT);
-        else if (fbo->Stencil.Kind != MG_Pipe::kMGPipeSurfaceKindNone)
-            (void)ResolveWireImage(*fbo, fbo->Stencil, VK_IMAGE_ASPECT_STENCIL_BIT);
-        m_textureManager->FlushPendingUploads();
-        const auto vaoHandle = state.BoundVertexElements;
-        if (MG_Pipe::MGPipeHandleIsNull(vaoHandle)) MagmaWireFatal("vertex-elements-record");
-        if (vaoHandle.Slot >= state.VertexElementsCsos.size()) MagmaWireFatal("vertex-elements-record");
-        const auto& vao = state.VertexElementsCsos[vaoHandle.Slot];
-        if (!vao.Live || vao.Gen != vaoHandle.Gen) MagmaWireFatal("vertex-elements-generation");
-        VertexInputStateFactory::BackendVertexInputState input{};
-        // P7 wave 2 package C, CONTRACT-P7 §3.2: THE `vertex-layout` ROW IS RETIRED AND SPLIT.
-        //
-        // A false is now ONE reason and only one - `buffer-window`, an enabled attribute the
-        // program reads whose slot lies outside the window set_vertex_buffers published. That
-        // is a disagreement about what crossed, not about what this device can express, so it
-        // keeps a named Fatal through the hook (MGPipeSessionFail -> Session::Fail, which is
-        // what rule I asks of a refusal that must stay a refusal). It is the check that caught
-        // the Redmi VAO hash collision fixed in 376c04be, which is why it is not softened.
-        // The P7 marker is gone from the detail string with the abort: this is a permanent
-        // protocol error, not a shape the split path has yet to migrate, so it must not keep
-        // counting against the census of unmigrated refusals (scripts/ci/fatal_census.py
-        // counts the marker literally, which is also why no comment in this package spells it).
-        if (!m_vertexInputStateFactory->BuildWireVertexInput(vao, state,
-                programObj.activeVertexInputLocationMask, input))
-            MagmaWireFatal("vertex-layout-buffer-window");
-        // The seven device/format reasons are now MASKED OUT of the vertex input state, and
-        // this is the monolith arm's pre-flight for them, statement for statement
-        // (VulkanRenderer.cpp's SetupDraw: "Fail loudly rather than render wrong pixels"). An
-        // enabled array with no usable VkFormat never reaches the vertex input state, which
-        // makes it indistinguishable from a DISABLED one - and a disabled one is answered
-        // below by uploading the current attribute value, so without this check the draw would
-        // quietly feed the shader a constant in place of the application's vertex data.
-        //
-        // A DECLINE, NOT A FATAL (rule I (a)): the draw is skipped, the reason is named once,
-        // and the observable is the monolith lane's for the same VAO on the same device.
-        // BuildWireVertexInput only considers attributes the program reads, so a masked bit is
-        // always an active one and this predicate is the whole of the difference.
-        if ((input.unsupportedAttribMask & programObj.activeVertexInputLocationMask) != 0) {
-            MGLOG_E_ONCE("Magma wire draw skipped: program=%u reads vertex attribute location "
-                         "mask 0x%x whose enabled array has no supported vertex format",
-                         program.GetExternalIndex(),
-                         input.unsupportedAttribMask & programObj.activeVertexInputLocationMask);
-            WireDeclineTally::Count(WireDeclineSite::VertexFormatUnsupported);
-            return false;
-        }
-        Vector<BufferSlice> vertexSlices(input.bindings.size());
-        for (SizeT binding = 0; binding < input.bindings.size(); ++binding) {
-            const Uint32 location = input.bindingAttributeLocations[binding];
-            const auto& attr = vao.Attributes[location];
-            const auto& resource = state.VertexBuffers[location];
-            if (MG_Pipe::MGPipeHandleIsNull(resource.Res)) MagmaWireFatal("client-vertex-array@P8");
-            BufferSlice slice{};
-            if (!m_bufferManager.AcquireWireSlice(BufferKind::Vertex, resource.Res, slice))
-                MagmaWireFatal("vertex-buffer-resource");
-            const VkDeviceSize offset = input.bindingBaseOffsets[binding];
-            const auto type = static_cast<DataType>(attr.Type);
-            const SizeT elementSize = VertexInputStateFactory::GetAttributeByteSize(type, attr.Size, attr.IsBgra);
-            if (offset > slice.size || elementSize > slice.size - offset) {
-                MGL_WIRE_DECLINE_AT(VertexAttributeWindow, "an enabled attribute's first element lies outside its buffer");
-                return false;
-            }
-            const auto conversion = input.bindingConversions[binding];
-            if (conversion != VertexInputStateFactory::VertexStreamConversion::None) {
-                const SizeT stride = static_cast<SizeT>(attr.Stride);
-                SizeT count = stride ? 1 + (static_cast<SizeT>(slice.size - offset) - elementSize) / stride : 1;
-                // Direct non-indexed draws bound the conversion; indexed/multi-draw may
-                // name arbitrary vertices, so preserve the entire valid source stream.
-                if (stride && !(aspects & DrawSetupAspect::IndexBuffer) && !resource.Divisor)
-                    count = std::min<SizeT>(count, static_cast<SizeT>(drawParams.firstVertex) + drawParams.vertexCount);
-                if (!count) {
-                    MGL_WIRE_DECLINE_AT(VertexStreamCountZero, "the converted vertex stream would hold no elements");
-                    return false;
-                }
-                Vector<Uint8> source((count - 1) * stride + elementSize);
-                if (!m_bufferManager.ReadWireBuffer(resource.Res, offset, source.size(), source.data())) {
-                    MGL_WIRE_DECLINE_AT(VertexStreamRead, "the vertex bytes to convert could not be read back");
-                    return false;
-                }
-                Vector<Uint8> converted;
-                // P7 wave 2 package C, CONTRACT-P7 §3.2 `vertex-format-conversion`: DECLINE.
-                // The converter is asked only for a conversion BuildWireVertexInput already
-                // chose, so a refusal here means the two disagree about what is convertible -
-                // a MobileGL-internal defect, not a peer's malformed record and not a verb the
-                // split path has yet to migrate. Killing the session for it told the peer
-                // "protocol corruption" about a bug on this side; skipping the draw and naming
-                // it once is the honest answer and is what the row asks for. The packed
-                // converter that would make the refusal unreachable is the row's optional half
-                // and is not taken here.
-                if (!ConvertWireVertexStream(attr, conversion, source.data(), stride, count, converted)) {
-                    MGLOG_E_ONCE("Magma wire draw skipped: no vertex stream converter for "
-                                 "location=%u type=%u size=%u conversion=%d",
-                                 location, attr.Type, static_cast<Uint32>(attr.Size),
-                                 static_cast<Int>(conversion));
-                    WireDeclineTally::Count(WireDeclineSite::VertexStreamConverter);
-                    return false;
-                }
-                if (!m_bufferManager.UploadTransient(BufferKind::Vertex, m_frameContext.GetCurrentFrameIndex(),
-                        converted.data(), converted.size(), 16, vertexSlices[binding])) {
-                    MGL_WIRE_DECLINE_AT(VertexTransientUpload, "the converted vertex stream did not fit the transient arena");
-                    return false;
-                }
-            } else {
-                slice.offset += offset;
-                slice.size -= offset;
-                vertexSlices[binding] = slice;
-            }
-        }
-
-        BufferSlice indexSlice{};
-        VkIndexType indexType = VK_INDEX_TYPE_MAX_ENUM;
-        if (aspects & DrawSetupAspect::IndexBuffer) {
-            if (!indices) {
-                MGL_WIRE_DECLINE_AT(IndexViewMissing, "an indexed draw arrived with no index view");
-                return false;
-            }
-            const SizeT width = MG_Util::GetGLTypeSize(indices->indexType);
-            if (width != 1 && width != 2 && width != 4) {
-                MGL_WIRE_DECLINE_AT(IndexTypeWidth, "the index type is not 1, 2 or 4 bytes wide");
-                return false;
-            }
-            indexType = width == 4 ? VK_INDEX_TYPE_UINT32 : width == 2 ? VK_INDEX_TYPE_UINT16 : VK_INDEX_TYPE_UINT8;
-            const auto& restart = MGB_CTX->GetRenderStateParameters();
-            const Uint32 fixed = MG_Util::FixedRestartIndexForGLType(indices->indexType);
-            const Bool replaceRestart = restart.PrimitiveRestartEnabled && !restart.PrimitiveRestartFixedIndexEnabled &&
-                restart.PrimitiveRestartIndex < fixed;
-            const Bool expandByte = width == 1 && !m_indexTypeUint8ExtensionEnabled;
-            const Bool cpuIndices = indices->forceClientMemory || MG_Pipe::MGPipeHandleIsNull(state.IndexBuffer.Res);
-            Vector<Uint8> copied;
-            const void* bytes = nullptr;
-            if (cpuIndices) bytes = reinterpret_cast<const void*>(indices->indexByteOffset);
-            else {
-                if (!m_bufferManager.AcquireWireSlice(BufferKind::Index, state.IndexBuffer.Res, indexSlice))
-                    MagmaWireFatal("index-buffer-resource");
-                const Uint64 offset = state.IndexBuffer.Offset + indices->indexByteOffset;
-                if (offset < state.IndexBuffer.Offset || offset > indexSlice.size ||
-                    indices->indexByteSize > indexSlice.size - offset) {
-                    MGL_WIRE_DECLINE_AT(IndexWindow, "the index range lies outside its buffer");
-                    return false;
-                }
-                if (replaceRestart || expandByte || offset % width) {
-                    copied.resize(indices->indexByteSize);
-                    if (!m_bufferManager.ReadWireBuffer(state.IndexBuffer.Res, offset, copied.size(), copied.data())) {
-                        MGL_WIRE_DECLINE_AT(IndexStreamRead, "the indices to rewrite could not be read back");
-                        return false;
-                    }
-                    bytes = copied.data();
-                }
-                indexSlice.offset += offset;
-                indexSlice.size = indices->indexByteSize;
-            }
-            if (bytes) {
-                Vector<Uint8> rewritten;
-                SizeT uploadSize = indices->indexByteSize;
-                if (replaceRestart || expandByte) {
-                    const SizeT outWidth = expandByte ? 2 : width;
-                    rewritten.resize(uploadSize / width * outWidth);
-                    for (SizeT i = 0; i < uploadSize / width; ++i) {
-                        Uint32 value = 0;
-                        Memcpy(&value, static_cast<const Uint8*>(bytes) + i * width, width);
-                        if (replaceRestart && value == restart.PrimitiveRestartIndex) value = fixed;
-                        if (expandByte && ResolvePrimitiveRestartEnable(aspects, indices) && value == fixed) value = 0xffffu;
-                        Memcpy(rewritten.data() + i * outWidth, &value, outWidth);
-                    }
-                    bytes = rewritten.data();
-                    uploadSize = rewritten.size();
-                    if (expandByte) indexType = VK_INDEX_TYPE_UINT16;
-                }
-                if (!m_bufferManager.UploadTransient(BufferKind::Index, m_frameContext.GetCurrentFrameIndex(),
-                        bytes, uploadSize, 16, indexSlice)) {
-                    MGL_WIRE_DECLINE_AT(IndexTransientUpload, "the rewritten indices did not fit the transient arena");
-                    return false;
-                }
-            }
-            if (!indexSlice.IsValid()) {
-                MGL_WIRE_DECLINE_AT(IndexSliceInvalid, "no usable index slice was resolved");
-                return false;
-            }
-        }
-
-        if (!frame.isCommandRecording) m_frameContext.BeginCommandRecording();
-        // Descriptor resolution can upgrade a view's root image to STORAGE usage.
-        // Resolve it before constructing framebuffer views so both roles of that image
-        // name the same allocation even on its first storage-image use.
-        if (!m_uniformManager->BindProgramUniformBuffers(frame.commandBuffer, program, programObj,
-                m_frameContext.GetCurrentFrameIndex(), VK_PIPELINE_BIND_POINT_GRAPHICS)) {
-            MGL_WIRE_DECLINE_AT(UniformBufferBinding, "the program's uniform/storage bindings could not be bound");
-            return false;
-        }
-
-        Vector<VkAttachmentDescription> attachments;
-        Vector<VkImageViewCreateInfo> viewInfos;
-        Vector<VkAttachmentReference> colors;
-        VkAttachmentReference depth{VK_ATTACHMENT_UNUSED, VK_IMAGE_LAYOUT_GENERAL};
-        VkExtent2D extent{~0u, ~0u};
-        Uint32 layers = ~0u;
-        VkSampleCountFlagBits samples = VK_SAMPLE_COUNT_1_BIT;
-        Uint64 passHash = 0;
-        WireDrawPassKey passKey{};
-        passKey.isDefault = fbo->IsDefault;
-        passKey.framebufferSrgb = MGB_CTX->IsCapabilityEnabled(CapabilityInput::FramebufferSrgb);
-        if (fbo->IsDefault) {
-            passKey.swapchain = m_swapchainObject.GetHandle();
-            // A drawing pass on the default framebuffer is what makes the freshly acquired
-            // swapchain image the one GL addresses (see m_defaultFramebufferImageIndex); the
-            // attachments below resolve the same index, so this key has to be taken after it.
-            passKey.swapchainImageIndex = DefaultFramebufferWriteIndex(true);
-        }
-        const auto add = [&](const MG_Pipe::MGPSurface& surface, VkImageAspectFlags aspect) -> Uint32 {
-            WireImage image = ResolveWireImage(*fbo, surface, aspect, /*isWriteTarget=*/true);
-            if (!image.image) return VK_ATTACHMENT_UNUSED;
-            m_textureManager->FlushPendingUploads();
-            if (aspect == VK_IMAGE_ASPECT_COLOR_BIT)
-                image.format = ResolveSrgbAttachmentWriteFormat(image.format,
-                    MGB_CTX->IsCapabilityEnabled(CapabilityInput::FramebufferSrgb));
-            const VkImageLayout layout = aspect == VK_IMAGE_ASPECT_COLOR_BIT ?
-                VK_IMAGE_LAYOUT_GENERAL : VK_IMAGE_LAYOUT_GENERAL;
-            TransitionWireImage(image, layout);
-            VkImageViewCreateInfo info{VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO};
-            info.image = image.image;
-            info.viewType = image.viewType;
-            info.format = image.format;
-            info.subresourceRange = {aspect, image.level, 1, image.layer, image.layers};
-            if (image.format == VK_FORMAT_D24_UNORM_S8_UINT || image.format == VK_FORMAT_D32_SFLOAT_S8_UINT)
-                info.subresourceRange.aspectMask = VK_IMAGE_ASPECT_DEPTH_BIT | VK_IMAGE_ASPECT_STENCIL_BIT;
-            viewInfos.push_back(info);
-            passKey.attachments.push_back({image.storage, static_cast<Uint32>(surface.Kind), image.image,
-                image.viewType, image.format, info.subresourceRange.aspectMask, aspect,
-                image.level, image.layer, image.layers, image.levels, image.extent.width, image.extent.height,
-                image.samples});
-            VkAttachmentDescription description{};
-            description.format = image.format;
-            description.samples = image.samples;
-            description.loadOp = description.stencilLoadOp = VK_ATTACHMENT_LOAD_OP_LOAD;
-            description.storeOp = description.stencilStoreOp = VK_ATTACHMENT_STORE_OP_STORE;
-            description.initialLayout = description.finalLayout = layout;
-            attachments.push_back(description);
-            extent.width = std::min(extent.width, image.extent.width);
-            extent.height = std::min(extent.height, image.extent.height);
-            layers = std::min(layers, image.layers);
-            samples = image.samples;
-            passHash = XXH64(&description, sizeof(description), passHash);
-            if (!image.isDefault && surface.Kind == MG_Pipe::kMGPipeSurfaceKindTexture)
-                m_textureManager->MarkWireTextureGpuWritten(image.storage, image.level, image.layer, image.layers);
-            if (image.isDefault) {
-                if (aspect == VK_IMAGE_ASPECT_COLOR_BIT) m_swapchainObject.SetImageContentDefined(image.swapchainImageIndex, true);
-                else m_swapchainObject.SetDepthStencilContentDefined(image.swapchainImageIndex, true);
-            }
-            return static_cast<Uint32>(attachments.size() - 1);
-        };
-        for (Uint32 i = 0; i < MG_Pipe::kMGPipeMaxColorAttachments; ++i) {
-            const Int32 slot = fbo->DrawBuffers[i];
-            const Uint32 index = slot < 0 ? VK_ATTACHMENT_UNUSED : add(fbo->Color[slot], VK_IMAGE_ASPECT_COLOR_BIT);
-            colors.push_back({index, VK_IMAGE_LAYOUT_GENERAL});
-        }
-        while (!colors.empty() && colors.back().attachment == VK_ATTACHMENT_UNUSED) colors.pop_back();
-        if (fbo->IsDefault || fbo->Depth.Kind != MG_Pipe::kMGPipeSurfaceKindNone)
-            depth.attachment = add(fbo->Depth, VK_IMAGE_ASPECT_DEPTH_BIT);
-        else if (fbo->Stencil.Kind != MG_Pipe::kMGPipeSurfaceKindNone)
-            depth.attachment = add(fbo->Stencil, VK_IMAGE_ASPECT_STENCIL_BIT);
-        if (attachments.empty()) {
-            MGL_WIRE_DECLINE_AT(NoAttachments, "the draw framebuffer resolved to no attachments");
-            return false;
-        }
-        passKey.width = extent.width;
-        passKey.height = extent.height;
-        passKey.layers = layers;
-        passKey.depthReference = depth.attachment;
-        for (const auto& color : colors) passKey.colorReferences.push_back(color.attachment);
-        // A native handle can be recycled after image replacement or death.
-        // Sample epochs after every lazy resolve, then compare them with the key.
-        passKey.textureImageEpoch = m_textureManager->GetTextureImageEpoch();
-        passKey.resourceEraseEpoch = m_textureManager->GetResourceEraseEpoch();
-        VkSubpassDescription subpass{};
-        subpass.pipelineBindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS;
-        subpass.colorAttachmentCount = static_cast<Uint32>(colors.size());
-        subpass.pColorAttachments = colors.data();
-        subpass.pDepthStencilAttachment = depth.attachment != VK_ATTACHMENT_UNUSED ? &depth : nullptr;
-        VkRenderPassCreateInfo passInfo{VK_STRUCTURE_TYPE_RENDER_PASS_CREATE_INFO};
-        passInfo.attachmentCount = static_cast<Uint32>(attachments.size());
-        passInfo.pAttachments = attachments.data();
-        passInfo.subpassCount = 1;
-        passInfo.pSubpasses = &subpass;
-        if (!AcquireCachedWireDrawPass(passKey)) {
-            m_wireDrawPassKey = Move(passKey);
-            Vector<VkImageView> views;
-            views.reserve(viewInfos.size());
-            for (const auto& info : viewInfos) {
-                VkImageView view = VK_NULL_HANDLE;
-                VK_VERIFY(vkCreateImageView(m_device, &info, nullptr, &view));
-                m_wireDrawViews.push_back(view);
-                views.push_back(view);
-            }
-            m_wireDrawPass = MakeUnique<RenderPassEntry>();
-            auto& created = *m_wireDrawPass;
-            VK_VERIFY(vkCreateRenderPass(m_device, &passInfo, nullptr, &created.renderPass));
-            VkFramebufferCreateInfo fbInfo{VK_STRUCTURE_TYPE_FRAMEBUFFER_CREATE_INFO};
-            fbInfo.renderPass = created.renderPass;
-            fbInfo.attachmentCount = static_cast<Uint32>(views.size());
-            fbInfo.pAttachments = views.data();
-            fbInfo.width = extent.width; fbInfo.height = extent.height; fbInfo.layers = layers;
-            VK_VERIFY(vkCreateFramebuffer(m_device, &fbInfo, nullptr, &created.framebuffer));
-            created.attachmentCount = static_cast<Uint32>(attachments.size());
-            created.colorAttachmentCount = static_cast<Uint32>(colors.size());
-            created.hasDepthStencilAttachment = depth.attachment != VK_ATTACHMENT_UNUSED;
-            created.sampleCount = samples;
-            created.extent = {static_cast<Int>(extent.width), static_cast<Int>(extent.height)};
-            created.layers = layers;
-            created.hash = created.compatibilityHash = XXH64(colors.data(), colors.size() * sizeof(colors[0]), passHash);
-        }
-        auto& pass = *m_wireDrawPass;
-        WireRenderPassCompatibilityKey pipelinePassKey{};
-        for (const auto& attachment : attachments)
-            pipelinePassKey.attachmentFormatsAndSamples.push_back(
-                (static_cast<Uint64>(attachment.format) << 32) | static_cast<Uint32>(attachment.samples));
-        for (const auto& color : colors) pipelinePassKey.colorReferences.push_back(color.attachment);
-        pipelinePassKey.depthReference = depth.attachment;
-        const Uint64 compatibilityId = m_wireRenderPassCompatibility.Intern(pipelinePassKey);
-        const auto pipeline = GetOrCreatePipelineWithInput(mode, program, programObj, flags, input, pass,
-            ResolvePrimitiveRestartEnable(aspects, indices), compatibilityId);
-        if (pipeline == VK_NULL_HANDLE) {
-            MGL_WIRE_DECLINE_AT(PipelineUnavailable, "no graphics pipeline could be created for this draw");
-            return false;
-        }
-        for (Uint32 i = 0; i < vertexSlices.size(); ++i)
-            vkCmdBindVertexBuffers(frame.commandBuffer, i, 1, &vertexSlices[i].buffer, &vertexSlices[i].offset);
-        Uint32 binding = static_cast<Uint32>(vertexSlices.size());
-        for (Uint32 location = 0; location < kMaxVertexAttribs; ++location) {
-            if (!(programObj.activeVertexInputLocationMask & (1u << location)) ||
-                (input.attributeLocationMask & (1u << location))) continue;
-            VkFormat format = VK_FORMAT_UNDEFINED;
-            const void* data = nullptr;
-            VkDeviceSize size = 0;
-            if (!TryGetCurrentVertexAttributeUploadPayload(MGB_CTX->GetCurrentVertexAttribute(location),
-                    programObj.vertexInputTypes[location], format, data, size)) {
-                MGL_WIRE_DECLINE_AT(CurrentAttributePayload, "a disabled array's current attribute value has no upload payload");
-                return false;
-            }
-            BufferSlice slice{};
-            if (!m_bufferManager.UploadTransient(BufferKind::Vertex, m_frameContext.GetCurrentFrameIndex(),
-                    data, size, 16, slice)) {
-                MGL_WIRE_DECLINE_AT(CurrentAttributeUpload, "the current attribute value did not fit the transient arena");
-                return false;
-            }
-            vkCmdBindVertexBuffers(frame.commandBuffer, binding++, 1, &slice.buffer, &slice.offset);
-        }
-        if (indexSlice.IsValid()) vkCmdBindIndexBuffer(frame.commandBuffer, indexSlice.buffer, indexSlice.offset, indexType);
-        if (!VkRenderPassManager::BeginRenderPass(frame.commandBuffer, pass)) {
-            MGL_WIRE_DECLINE_AT(BeginRenderPass, "the render pass for this draw could not be begun");
-            return false;
-        }
-        vkCmdBindPipeline(frame.commandBuffer, VK_PIPELINE_BIND_POINT_GRAPHICS, pipeline);
-        ApplyDynamicDrawStateTail(frame, pass.extent, fbo->IsDefault,
-                                 ResolveDrawViewportCount(programObj.writesViewportIndexBuiltin));
-        if (MG_Util::PipeStats::Enabled()) MG_Util::PipeStats::AddCalls(MG_Util::PipeStats::CallClass::Draws, 1);
-        return true;
-    }
-
-    void VulkanRenderer::DispatchWireCompute(GLuint x, GLuint y, GLuint z) {
-        RetireWireDrawPass();
-        auto& frame = m_frameContext.GetCurrent();
-        const auto program = WireProgramSource(MG_Pipe::MGPipeApplier().DispatchProgram);
-        if (!program.GetLinkStatus() || !program.GetSpirvStatus()) {
-            MGL_WIRE_DECLINE_AT(ComputeProgramLinkOrSpirv, "the compute program is not linked or carries no SPIR-V");
-            return;
-        }
-        const auto& programObj = m_programFactory->GetOrCreateProgram(program, {});
-        if (!m_uniformManager->PrepareWireTextureResources(program, programObj)) {
-            MGL_WIRE_DECLINE_AT(ComputeTextureResourcesUnprepared, "a sampled/storage image could not be made ready for the dispatch");
-            return;
-        }
-        const auto pipeline = GetOrCreateComputePipeline(programObj);
-        if (!pipeline) {
-            MGL_WIRE_DECLINE_AT(ComputePipelineUnavailable, "no compute pipeline could be created for this dispatch");
-            return;
-        }
-        if (!frame.isCommandRecording) m_frameContext.BeginCommandRecording();
-        if (!m_uniformManager->BindProgramUniformBuffers(frame.commandBuffer, program, programObj,
-                m_frameContext.GetCurrentFrameIndex(), VK_PIPELINE_BIND_POINT_COMPUTE)) {
-            MGL_WIRE_DECLINE_AT(ComputeUniformBufferBinding, "the dispatch's uniform/storage bindings could not be bound");
-            return;
-        }
-        vkCmdBindPipeline(frame.commandBuffer, VK_PIPELINE_BIND_POINT_COMPUTE, pipeline);
-        vkCmdDispatch(frame.commandBuffer, x, y, z);
-    }
-#endif

MobileGL/MG_Backend/DirectVulkan/Renderer/WireMultisampleDepthResolve.frag

@@ -1,16 +0,0 @@
-#version 450
-// SAMPLE ZERO, and it is not an approximation: VK_RESOLVE_MODE_SAMPLE_ZERO_BIT is the mode the
-// VK_KHR_depth_stencil_resolve arm asks for, and GL 4.6 core 18.3.1 says a depth resolve picks
-// a value "in an implementation-dependent manner where the result will be between the minimum
-// and maximum depth values in the pixel" - sample 0 is one of the samples, so it qualifies, and
-// taking the same sample as the extension arm is what makes the two arms interchangeable on one
-// device.
-//
-// AVERAGING WOULD NOT BE: a mean of four depths is a surface that exists nowhere, and GL's
-// bound is on the per-pixel min/max, which a mean satisfies but a shadow comparison against it
-// does not survive.
-layout(set = 0, binding = 0) uniform sampler2DMS sourceImage;
-
-void main() {
-    gl_FragDepth = texelFetch(sourceImage, ivec2(gl_FragCoord.xy), 0).r;
-}

MobileGL/MG_Backend/DirectVulkan/Renderer/WireMultisampleResolve.inc

@@ -1,167 +0,0 @@
-// Included by VulkanRenderer.cpp inside the backend namespace, after WireDepthMipmap.inc.
-// The native multisample depth/stencil resolve owns no frontend object and never invokes the
-// GL shader compiler.
-//
-// WHY THIS FILE EXISTS. vkCmdResolveImage is COLOUR ONLY. The one way Vulkan resolves a depth
-// or stencil aspect without a shader is a render pass with a depth/stencil resolve attachment,
-// which needs VK_KHR_create_renderpass2 and VK_KHR_depth_stencil_resolve - and until this
-// package a device without either killed the session at
-// `Magma:multisample-depth-resolve-capability` the first time an application resolved a
-// multisample depth buffer, which is what glBlitFramebuffer(GL_DEPTH_BUFFER_BIT) from a
-// multisampled read framebuffer IS. CONTRACT-P7 §3.2's `multisample-blit-aspect` row names both
-// arms; this is the second one.
-//
-// SAMPLE ZERO IN BOTH ARMS. The extension arm asks for VK_RESOLVE_MODE_SAMPLE_ZERO_BIT, so the
-// shader arm fetches sample 0 - not an average. Two arms that answer differently on two devices
-// would make "the wire arm is observably the monolith's" untestable, and GL 4.6 core 18.3.1
-// requires a SELECTED sample for stencil anyway.
-#if MOBILEGL_BUILD_DISAGGREGATED
-    // The pass's modules, layouts, render passes and pipeline, and the draw it records, are
-    // WireDepthResolveProbe.cpp's (g5-msprobe): the multisample depth/stencil resolve probe runs
-    // this exact arm as its CONTROL, so it is defined once for both.
-    struct VulkanRenderer::WireMultisampleResolveResources {
-        struct Target {
-            VkFormat format = VK_FORMAT_UNDEFINED;
-            VkImageAspectFlags aspect = 0; // the ONE aspect this pipeline writes
-            VkRenderPass renderPass = VK_NULL_HANDLE;
-            VkPipeline pipeline = VK_NULL_HANDLE;
-        };
-        WireShaderResolveKit kit;
-        Vector<Target> targets;
-    };
-
-    void VulkanRenderer::DestroyWireMultisampleResolveResources() {
-        if (!m_wireMultisampleResolveResources) return;
-        // Shutdown calls this after vkDeviceWaitIdle and after all per-submit descriptor
-        // pools/framebuffers/views have been collected.
-        auto& cache = *m_wireMultisampleResolveResources;
-        for (const auto& target : cache.targets) {
-            vkDestroyPipeline(m_device, target.pipeline, nullptr);
-            vkDestroyRenderPass(m_device, target.renderPass, nullptr);
-        }
-        DestroyWireShaderResolveKit(m_device, cache.kit);
-        delete m_wireMultisampleResolveResources;
-        m_wireMultisampleResolveResources = nullptr;
-    }
-
-    // ONE ASPECT, source -> resolved, both 2D images of the same format and extent, the source
-    // multisampled and the destination not. Returns false for every shape it cannot express,
-    // which the caller turns into a decline; it never ends the session.
-    Bool VulkanRenderer::ResolveWireDepthStencilWithShader(WireImage source, WireImage resolved,
-        VkImageAspectFlags aspect, GLint sx0, GLint sy0, Uint32 width, Uint32 height) {
-        if (!source.image || !resolved.image || !width || !height) return false;
-        if (aspect != VK_IMAGE_ASPECT_DEPTH_BIT && aspect != VK_IMAGE_ASPECT_STENCIL_BIT) return false;
-        // A fragment shader cannot write the stencil aspect at all without
-        // VK_EXT_shader_stencil_export. §3.2: decline stencil-only rather than produce a level
-        // whose stencil is whatever the DONT_CARE left there.
-        if (aspect == VK_IMAGE_ASPECT_STENCIL_BIT && !m_wireShaderStencilExport) return false;
-        if (source.samples == VK_SAMPLE_COUNT_1_BIT) return false;
-        if (source.format != resolved.format) return false;
-        // SAMPLED is asked for by every attachment VkTextureManager creates; a device that
-        // declined it would make the descriptor write below undefined, not failed.
-        if (!(source.usageFlags & VK_IMAGE_USAGE_SAMPLED_BIT)) return false;
-        VkFormatProperties properties{};
-        vkGetPhysicalDeviceFormatProperties(m_physicalDevice.handle, source.format, &properties);
-        const VkFormatFeatureFlags required = VK_FORMAT_FEATURE_SAMPLED_IMAGE_BIT |
-                                              VK_FORMAT_FEATURE_DEPTH_STENCIL_ATTACHMENT_BIT;
-        if ((properties.optimalTilingFeatures & required) != required) return false;
-
-        const VkImageAspectFlags formatAspects = WireDepthStencilFormatAspects(source.format);
-        if (!(formatAspects & aspect)) return false;
-
-        if (!m_wireMultisampleResolveResources) {
-            m_wireMultisampleResolveResources = new WireMultisampleResolveResources;
-            VK_VERIFY(CreateWireShaderResolveKit(m_device, m_wireShaderStencilExport,
-                                                 m_wireMultisampleResolveResources->kit));
-        }
-        auto& cache = *m_wireMultisampleResolveResources;
-        const VkShaderModule fragment = aspect == VK_IMAGE_ASPECT_STENCIL_BIT ? cache.kit.stencilFragment
-                                                                              : cache.kit.depthFragment;
-        if (fragment == VK_NULL_HANDLE) return false;
-
-        WireMultisampleResolveResources::Target* target = nullptr;
-        for (auto& entry : cache.targets)
-            if (entry.format == resolved.format && entry.aspect == aspect) { target = &entry; break; }
-        if (!target) {
-            cache.targets.emplace_back();
-            target = &cache.targets.back();
-            target->format = resolved.format;
-            target->aspect = aspect;
-            VK_VERIFY(CreateWireShaderResolveRenderPass(m_device, resolved.format, &target->renderPass));
-            if (CreateWireShaderResolvePipeline(m_device, cache.kit, target->renderPass, aspect,
-                                                &target->pipeline) != VK_SUCCESS) {
-                vkDestroyRenderPass(m_device, target->renderPass, nullptr);
-                cache.targets.pop_back();
-                return false;
-            }
-        }
-
-        m_textureManager->FlushPendingUploads();
-        TransitionWireImage(source, VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL);
-        TransitionWireImage(resolved, VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL);
-
-        // ONE ASPECT on the sampled view: a depth/stencil image can only be SAMPLED through a
-        // view that names exactly one of its aspects, which is also what makes the stencil half
-        // a usampler2DMS and the depth half a sampler2DMS.
-        const VkImageViewCreateInfo sourceViewInfo =
-            WireDepthStencilViewInfo(source.image, source.format, aspect, source.level, source.layer);
-        VkImageView sourceView = VK_NULL_HANDLE;
-        VK_VERIFY(vkCreateImageView(m_device, &sourceViewInfo, nullptr, &sourceView));
-        // BOTH aspects on the attachment view: a depth/stencil ATTACHMENT names every aspect
-        // its format has, whichever one the pipeline writes.
-        const VkImageViewCreateInfo targetViewInfo =
-            WireDepthStencilViewInfo(resolved.image, resolved.format, formatAspects, 0, 0);
-        VkImageView targetView = VK_NULL_HANDLE;
-        VK_VERIFY(vkCreateImageView(m_device, &targetViewInfo, nullptr, &targetView));
-
-        VkFramebufferCreateInfo framebufferInfo{VK_STRUCTURE_TYPE_FRAMEBUFFER_CREATE_INFO};
-        framebufferInfo.renderPass = target->renderPass;
-        framebufferInfo.attachmentCount = 1;
-        framebufferInfo.pAttachments = &targetView;
-        framebufferInfo.width = resolved.extent.width;
-        framebufferInfo.height = resolved.extent.height;
-        framebufferInfo.layers = 1;
-        VkFramebuffer framebuffer = VK_NULL_HANDLE;
-        VK_VERIFY(vkCreateFramebuffer(m_device, &framebufferInfo, nullptr, &framebuffer));
-
-        // Each in-flight pass owns its descriptor set, for the colour blit's reason: updating a
-        // cached set would rewrite the source view of an older queued pass.
-        VkDescriptorPool descriptorPool = VK_NULL_HANDLE;
-        VkDescriptorSet descriptorSet = VK_NULL_HANDLE;
-        const VkDescriptorPoolSize poolSize{VK_DESCRIPTOR_TYPE_COMBINED_IMAGE_SAMPLER, 1};
-        VkDescriptorPoolCreateInfo pool{VK_STRUCTURE_TYPE_DESCRIPTOR_POOL_CREATE_INFO};
-        pool.maxSets = 1;
-        pool.poolSizeCount = 1;
-        pool.pPoolSizes = &poolSize;
-        VK_VERIFY(vkCreateDescriptorPool(m_device, &pool, nullptr, &descriptorPool));
-        VkDescriptorSetAllocateInfo alloc{VK_STRUCTURE_TYPE_DESCRIPTOR_SET_ALLOCATE_INFO};
-        alloc.descriptorPool = descriptorPool;
-        alloc.descriptorSetCount = 1;
-        alloc.pSetLayouts = &cache.kit.descriptorLayout;
-        VK_VERIFY(vkAllocateDescriptorSets(m_device, &alloc, &descriptorSet));
-        const VkDescriptorImageInfo sampled{cache.kit.nearest, sourceView,
-                                            VK_IMAGE_LAYOUT_SHADER_READ_ONLY_OPTIMAL};
-        VkWriteDescriptorSet write{VK_STRUCTURE_TYPE_WRITE_DESCRIPTOR_SET};
-        write.dstSet = descriptorSet;
-        write.dstBinding = 0;
-        write.descriptorCount = 1;
-        write.descriptorType = VK_DESCRIPTOR_TYPE_COMBINED_IMAGE_SAMPLER;
-        write.pImageInfo = &sampled;
-        vkUpdateDescriptorSets(m_device, 1, &write, 0, nullptr);
-
-        auto& frame = m_frameContext.GetCurrent();
-        RecordWireShaderResolveDraw(frame.commandBuffer, cache.kit, target->renderPass, target->pipeline, framebuffer,
-                                    descriptorSet, resolved.extent, {{sx0, sy0}, {width, height}});
-        ResetDynamicStateShadow();
-        InvalidatePipelineMemo();
-        // This native pass binds its own set/layout without going through the application's
-        // descriptor binder. Its next fast path must rebind.
-        if (m_uniformManager) m_uniformManager->OnCommandBufferBoundary();
-        WireRetiredObjects retired{};
-        retired.framebuffers.push_back(framebuffer);
-        retired.imageViews = {sourceView, targetView};
-        retired.descriptorPools.push_back(descriptorPool);
-        RetireWireObjects(Move(retired));
-        return true;
-    }
-#endif

MobileGL/MG_Backend/DirectVulkan/Renderer/WireMultisampleResolve.vert

@@ -1,18 +0,0 @@
-#version 450
-// Native Vulkan multisample depth/stencil resolve: no GL program, registry entry, or runtime
-// transpilation.
-//
-// THIS STAGE CARRIES NOTHING, and that is the whole design. The scratch this pass writes has
-// the SAME extent and the SAME coordinate space as the multisample source it reads - both are
-// native images, neither is flipped against the other - so the fragment stage can take its
-// coordinate straight out of gl_FragCoord and needs no varying, no push constant and no rect.
-// The requested rectangle is expressed by the scissor instead, which is also what the
-// VK_KHR_depth_stencil_resolve arm next door expresses with its renderArea.
-//
-// An oversized triangle rather than WireDepthMipmap.vert's quad: there is no destination
-// rectangle to clip to here, only the scissor, and a triangle rasterizes the same area with
-// one fewer primitive and no shared edge.
-void main() {
-    const vec2 corners[3] = vec2[](vec2(-1.0, -1.0), vec2(3.0, -1.0), vec2(-1.0, 3.0));
-    gl_Position = vec4(corners[gl_VertexIndex], 0.0, 1.0);
-}

MobileGL/MG_Backend/DirectVulkan/Renderer/WireMultisampleResolveSpirv.h

@@ -1,103 +0,0 @@
-// Generated from WireMultisampleResolve.vert / WireMultisampleDepthResolve.frag /
-// WireMultisampleStencilResolve.frag by scripts/bake_internal_shaders.py, which runs MG_Test's
-// BakedInternalShadersTest with the IN-TREE glslang and splices the words it emits into the
-// arrays below. Do not edit the words by hand: MOBILEGL_BAKED_INTERNAL_SHADERS (the same test,
-// run as a gate) recompiles every source in its table and reds on the first word that
-// disagrees.
-#pragma once
-
-static constexpr Uint32 kWireMultisampleResolveVertexSpirv[] = {
-    0x07230203u, 0x00010000u, 0x0008000bu, 0x00000028u, 0x00000000u, 0x00020011u, 0x00000001u, 0x0006000bu,
-    0x00000001u, 0x4c534c47u, 0x6474732eu, 0x3035342eu, 0x00000000u, 0x0003000eu, 0x00000000u, 0x00000001u,
-    0x0007000fu, 0x00000000u, 0x00000004u, 0x6e69616du, 0x00000000u, 0x0000000du, 0x0000001au, 0x00030003u,
-    0x00000002u, 0x000001c2u, 0x00040005u, 0x00000004u, 0x6e69616du, 0x00000000u, 0x00060005u, 0x0000000bu,
-    0x505f6c67u, 0x65567265u, 0x78657472u, 0x00000000u, 0x00060006u, 0x0000000bu, 0x00000000u, 0x505f6c67u,
-    0x7469736fu, 0x006e6f69u, 0x00070006u, 0x0000000bu, 0x00000001u, 0x505f6c67u, 0x746e696fu, 0x657a6953u,
-    0x00000000u, 0x00070006u, 0x0000000bu, 0x00000002u, 0x435f6c67u, 0x4470696cu, 0x61747369u, 0x0065636eu,
-    0x00070006u, 0x0000000bu, 0x00000003u, 0x435f6c67u, 0x446c6c75u, 0x61747369u, 0x0065636eu, 0x00030005u,
-    0x0000000du, 0x00000000u, 0x00060005u, 0x0000001au, 0x565f6c67u, 0x65747265u, 0x646e4978u, 0x00007865u,
-    0x00050005u, 0x0000001du, 0x65646e69u, 0x6c626178u, 0x00000065u, 0x00030047u, 0x0000000bu, 0x00000002u,
-    0x00050048u, 0x0000000bu, 0x00000000u, 0x0000000bu, 0x00000000u, 0x00050048u, 0x0000000bu, 0x00000001u,
-    0x0000000bu, 0x00000001u, 0x00050048u, 0x0000000bu, 0x00000002u, 0x0000000bu, 0x00000003u, 0x00050048u,
-    0x0000000bu, 0x00000003u, 0x0000000bu, 0x00000004u, 0x00040047u, 0x0000001au, 0x0000000bu, 0x0000002au,
-    0x00020013u, 0x00000002u, 0x00030021u, 0x00000003u, 0x00000002u, 0x00030016u, 0x00000006u, 0x00000020u,
-    0x00040017u, 0x00000007u, 0x00000006u, 0x00000004u, 0x00040015u, 0x00000008u, 0x00000020u, 0x00000000u,
-    0x0004002bu, 0x00000008u, 0x00000009u, 0x00000001u, 0x0004001cu, 0x0000000au, 0x00000006u, 0x00000009u,
-    0x0006001eu, 0x0000000bu, 0x00000007u, 0x00000006u, 0x0000000au, 0x0000000au, 0x00040020u, 0x0000000cu,
-    0x00000003u, 0x0000000bu, 0x0004003bu, 0x0000000cu, 0x0000000du, 0x00000003u, 0x00040015u, 0x0000000eu,
-    0x00000020u, 0x00000001u, 0x0004002bu, 0x0000000eu, 0x0000000fu, 0x00000000u, 0x00040017u, 0x00000010u,
-    0x00000006u, 0x00000002u, 0x0004002bu, 0x00000008u, 0x00000011u, 0x00000003u, 0x0004001cu, 0x00000012u,
-    0x00000010u, 0x00000011u, 0x0004002bu, 0x00000006u, 0x00000013u, 0xbf800000u, 0x0005002cu, 0x00000010u,
-    0x00000014u, 0x00000013u, 0x00000013u, 0x0004002bu, 0x00000006u, 0x00000015u, 0x40400000u, 0x0005002cu,
-    0x00000010u, 0x00000016u, 0x00000015u, 0x00000013u, 0x0005002cu, 0x00000010u, 0x00000017u, 0x00000013u,
-    0x00000015u, 0x0006002cu, 0x00000012u, 0x00000018u, 0x00000014u, 0x00000016u, 0x00000017u, 0x00040020u,
-    0x00000019u, 0x00000001u, 0x0000000eu, 0x0004003bu, 0x00000019u, 0x0000001au, 0x00000001u, 0x00040020u,
-    0x0000001cu, 0x00000007u, 0x00000012u, 0x00040020u, 0x0000001eu, 0x00000007u, 0x00000010u, 0x0004002bu,
-    0x00000006u, 0x00000021u, 0x00000000u, 0x0004002bu, 0x00000006u, 0x00000022u, 0x3f800000u, 0x00040020u,
-    0x00000026u, 0x00000003u, 0x00000007u, 0x00050036u, 0x00000002u, 0x00000004u, 0x00000000u, 0x00000003u,
-    0x000200f8u, 0x00000005u, 0x0004003bu, 0x0000001cu, 0x0000001du, 0x00000007u, 0x0004003du, 0x0000000eu,
-    0x0000001bu, 0x0000001au, 0x0003003eu, 0x0000001du, 0x00000018u, 0x00050041u, 0x0000001eu, 0x0000001fu,
-    0x0000001du, 0x0000001bu, 0x0004003du, 0x00000010u, 0x00000020u, 0x0000001fu, 0x00050051u, 0x00000006u,
-    0x00000023u, 0x00000020u, 0x00000000u, 0x00050051u, 0x00000006u, 0x00000024u, 0x00000020u, 0x00000001u,
-    0x00070050u, 0x00000007u, 0x00000025u, 0x00000023u, 0x00000024u, 0x00000021u, 0x00000022u, 0x00050041u,
-    0x00000026u, 0x00000027u, 0x0000000du, 0x0000000fu, 0x0003003eu, 0x00000027u, 0x00000025u, 0x000100fdu,
-    0x00010038u,
-};
-
-static constexpr Uint32 kWireMultisampleDepthResolveFragmentSpirv[] = {
-    0x07230203u, 0x00010000u, 0x0008000bu, 0x0000001du, 0x00000000u, 0x00020011u, 0x00000001u, 0x0006000bu,
-    0x00000001u, 0x4c534c47u, 0x6474732eu, 0x3035342eu, 0x00000000u, 0x0003000eu, 0x00000000u, 0x00000001u,
-    0x0007000fu, 0x00000004u, 0x00000004u, 0x6e69616du, 0x00000000u, 0x00000008u, 0x00000010u, 0x00030010u,
-    0x00000004u, 0x00000007u, 0x00030010u, 0x00000004u, 0x0000000cu, 0x00030003u, 0x00000002u, 0x000001c2u,
-    0x00040005u, 0x00000004u, 0x6e69616du, 0x00000000u, 0x00060005u, 0x00000008u, 0x465f6c67u, 0x44676172u,
-    0x68747065u, 0x00000000u, 0x00050005u, 0x0000000cu, 0x72756f73u, 0x6d496563u, 0x00656761u, 0x00060005u,
-    0x00000010u, 0x465f6c67u, 0x43676172u, 0x64726f6fu, 0x00000000u, 0x00040047u, 0x00000008u, 0x0000000bu,
-    0x00000016u, 0x00040047u, 0x0000000cu, 0x00000021u, 0x00000000u, 0x00040047u, 0x0000000cu, 0x00000022u,
-    0x00000000u, 0x00040047u, 0x00000010u, 0x0000000bu, 0x0000000fu, 0x00020013u, 0x00000002u, 0x00030021u,
-    0x00000003u, 0x00000002u, 0x00030016u, 0x00000006u, 0x00000020u, 0x00040020u, 0x00000007u, 0x00000003u,
-    0x00000006u, 0x0004003bu, 0x00000007u, 0x00000008u, 0x00000003u, 0x00090019u, 0x00000009u, 0x00000006u,
-    0x00000001u, 0x00000000u, 0x00000000u, 0x00000001u, 0x00000001u, 0x00000000u, 0x0003001bu, 0x0000000au,
-    0x00000009u, 0x00040020u, 0x0000000bu, 0x00000000u, 0x0000000au, 0x0004003bu, 0x0000000bu, 0x0000000cu,
-    0x00000000u, 0x00040017u, 0x0000000eu, 0x00000006u, 0x00000004u, 0x00040020u, 0x0000000fu, 0x00000001u,
-    0x0000000eu, 0x0004003bu, 0x0000000fu, 0x00000010u, 0x00000001u, 0x00040017u, 0x00000011u, 0x00000006u,
-    0x00000002u, 0x00040015u, 0x00000014u, 0x00000020u, 0x00000001u, 0x00040017u, 0x00000015u, 0x00000014u,
-    0x00000002u, 0x0004002bu, 0x00000014u, 0x00000017u, 0x00000000u, 0x00040015u, 0x0000001au, 0x00000020u,
-    0x00000000u, 0x0004002bu, 0x0000001au, 0x0000001bu, 0x00000000u, 0x00050036u, 0x00000002u, 0x00000004u,
-    0x00000000u, 0x00000003u, 0x000200f8u, 0x00000005u, 0x0004003du, 0x0000000au, 0x0000000du, 0x0000000cu,
-    0x0004003du, 0x0000000eu, 0x00000012u, 0x00000010u, 0x0007004fu, 0x00000011u, 0x00000013u, 0x00000012u,
-    0x00000012u, 0x00000000u, 0x00000001u, 0x0004006eu, 0x00000015u, 0x00000016u, 0x00000013u, 0x00040064u,
-    0x00000009u, 0x00000018u, 0x0000000du, 0x0007005fu, 0x0000000eu, 0x00000019u, 0x00000018u, 0x00000016u,
-    0x00000040u, 0x00000017u, 0x00050051u, 0x00000006u, 0x0000001cu, 0x00000019u, 0x00000000u, 0x0003003eu,
-    0x00000008u, 0x0000001cu, 0x000100fdu, 0x00010038u,
-};
-
-static constexpr Uint32 kWireMultisampleStencilResolveFragmentSpirv[] = {
-    0x07230203u, 0x00010000u, 0x0008000bu, 0x0000001fu, 0x00000000u, 0x00020011u, 0x00000001u, 0x00020011u,
-    0x00001395u, 0x0009000au, 0x5f565053u, 0x5f545845u, 0x64616873u, 0x735f7265u, 0x636e6574u, 0x655f6c69u,
-    0x726f7078u, 0x00000074u, 0x0006000bu, 0x00000001u, 0x4c534c47u, 0x6474732eu, 0x3035342eu, 0x00000000u,
-    0x0003000eu, 0x00000000u, 0x00000001u, 0x0007000fu, 0x00000004u, 0x00000004u, 0x6e69616du, 0x00000000u,
-    0x00000008u, 0x00000012u, 0x00030010u, 0x00000004u, 0x00000007u, 0x00030010u, 0x00000004u, 0x000013a3u,
-    0x00030003u, 0x00000002u, 0x000001c2u, 0x00090004u, 0x415f4c47u, 0x735f4252u, 0x65646168u, 0x74735f72u,
-    0x69636e65u, 0x78655f6cu, 0x74726f70u, 0x00000000u, 0x00040005u, 0x00000004u, 0x6e69616du, 0x00000000u,
-    0x00080005u, 0x00000008u, 0x465f6c67u, 0x53676172u, 0x636e6574u, 0x65526c69u, 0x42524166u, 0x00000000u,
-    0x00050005u, 0x0000000du, 0x72756f73u, 0x6d496563u, 0x00656761u, 0x00060005u, 0x00000012u, 0x465f6c67u,
-    0x43676172u, 0x64726f6fu, 0x00000000u, 0x00040047u, 0x00000008u, 0x0000000bu, 0x00001396u, 0x00040047u,
-    0x0000000du, 0x00000021u, 0x00000000u, 0x00040047u, 0x0000000du, 0x00000022u, 0x00000000u, 0x00040047u,
-    0x00000012u, 0x0000000bu, 0x0000000fu, 0x00020013u, 0x00000002u, 0x00030021u, 0x00000003u, 0x00000002u,
-    0x00040015u, 0x00000006u, 0x00000020u, 0x00000001u, 0x00040020u, 0x00000007u, 0x00000003u, 0x00000006u,
-    0x0004003bu, 0x00000007u, 0x00000008u, 0x00000003u, 0x00040015u, 0x00000009u, 0x00000020u, 0x00000000u,
-    0x00090019u, 0x0000000au, 0x00000009u, 0x00000001u, 0x00000000u, 0x00000000u, 0x00000001u, 0x00000001u,
-    0x00000000u, 0x0003001bu, 0x0000000bu, 0x0000000au, 0x00040020u, 0x0000000cu, 0x00000000u, 0x0000000bu,
-    0x0004003bu, 0x0000000cu, 0x0000000du, 0x00000000u, 0x00030016u, 0x0000000fu, 0x00000020u, 0x00040017u,
-    0x00000010u, 0x0000000fu, 0x00000004u, 0x00040020u, 0x00000011u, 0x00000001u, 0x00000010u, 0x0004003bu,
-    0x00000011u, 0x00000012u, 0x00000001u, 0x00040017u, 0x00000013u, 0x0000000fu, 0x00000002u, 0x00040017u,
-    0x00000016u, 0x00000006u, 0x00000002u, 0x0004002bu, 0x00000006u, 0x00000018u, 0x00000000u, 0x00040017u,
-    0x0000001au, 0x00000009u, 0x00000004u, 0x0004002bu, 0x00000009u, 0x0000001cu, 0x00000000u, 0x00050036u,
-    0x00000002u, 0x00000004u, 0x00000000u, 0x00000003u, 0x000200f8u, 0x00000005u, 0x0004003du, 0x0000000bu,
-    0x0000000eu, 0x0000000du, 0x0004003du, 0x00000010u, 0x00000014u, 0x00000012u, 0x0007004fu, 0x00000013u,
-    0x00000015u, 0x00000014u, 0x00000014u, 0x00000000u, 0x00000001u, 0x0004006eu, 0x00000016u, 0x00000017u,
-    0x00000015u, 0x00040064u, 0x0000000au, 0x00000019u, 0x0000000eu, 0x0007005fu, 0x0000001au, 0x0000001bu,
-    0x00000019u, 0x00000017u, 0x00000040u, 0x00000018u, 0x00050051u, 0x00000009u, 0x0000001du, 0x0000001bu,
-    0x00000000u, 0x0004007cu, 0x00000006u, 0x0000001eu, 0x0000001du, 0x0003003eu, 0x00000008u, 0x0000001eu,
-    0x000100fdu, 0x00010038u,
-};

MobileGL/MG_Backend/DirectVulkan/Renderer/WireMultisampleStencilResolve.frag

@@ -1,19 +0,0 @@
-#version 450
-// The stencil half, and it needs an extension to exist at all: a fragment shader cannot write
-// the stencil aspect without VK_EXT_shader_stencil_export (SPV_EXT_shader_stencil_export, which
-// this `#extension` line is how glslang is asked for). CONTRACT-P7 §3.2 says so and says what
-// happens otherwise - a stencil-only resolve DECLINES on a device without it, because there is
-// no second way to put a value in the stencil aspect from a pass.
-//
-// usampler2DMS and not sampler2DMS: the stencil aspect of a depth/stencil image is an unsigned
-// integer, and a float view of it would round the index.
-//
-// Sample zero, for WireMultisampleDepthResolve.frag's reason, and GL is stricter here: 18.3.1
-// says integer and stencil resolves SELECT one sample rather than combining them, so sample 0
-// is the answer and not merely an acceptable one.
-#extension GL_ARB_shader_stencil_export : require
-layout(set = 0, binding = 0) uniform usampler2DMS sourceImage;
-
-void main() {
-    gl_FragStencilRefARB = int(texelFetch(sourceImage, ivec2(gl_FragCoord.xy), 0).r);
-}

MobileGL/MG_Backend/DirectVulkan/Renderer/WirePlaceholderImages.inc

@@ -1,245 +0,0 @@
-// UniformManager-owned native descriptors for wire bindings with no image.
-// No GL object is constructed or inserted into the client's resource namespace.
-#if MOBILEGL_BUILD_DISAGGREGATED
-    void UniformManager::DestroyWirePlaceholderImage(WirePlaceholderImage& image) const {
-        if (m_device != VK_NULL_HANDLE) {
-            if (image.clearFramebuffer) vkDestroyFramebuffer(m_device, image.clearFramebuffer, nullptr);
-            if (image.clearPass) vkDestroyRenderPass(m_device, image.clearPass, nullptr);
-            if (image.sampler) vkDestroySampler(m_device, image.sampler, nullptr);
-            if (image.view) vkDestroyImageView(m_device, image.view, nullptr);
-            if (image.image) vkDestroyImage(m_device, image.image, nullptr);
-            if (image.memory) vkFreeMemory(m_device, image.memory, nullptr);
-        }
-        image = {};
-    }
-
-    void UniformManager::SetWireInvalidStorageImageArm(Bool deviceNullDescriptor) {
-        const char* forced = std::getenv("MGITEST_MAGMA_FORCE_PRIVATE_IMAGE_PLACEHOLDER");
-        const Bool forcePrivate = forced != nullptr && std::strcmp(forced, "1") == 0;
-        m_wireInvalidStorageImagesBindNull = deviceNullDescriptor && !forcePrivate;
-        MGLOG_I("Magma wire: an invalid or unbound image unit binds %s (VK_EXT_robustness2 nullDescriptor %s%s)",
-                m_wireInvalidStorageImagesBindNull ? "a NULL storage descriptor"
-                                                   : "a placeholder private to its unit",
-                deviceNullDescriptor ? "enabled" : "unavailable",
-                deviceNullDescriptor && forcePrivate ? "; MGITEST_MAGMA_FORCE_PRIVATE_IMAGE_PLACEHOLDER=1" : "");
-    }
-
-    Bool UniformManager::ResolveWirePlaceholderImage(VkCommandBuffer commands, const MagmaProgramSource& program,
-            const ProgramFactory::VkProgramObject& programObj, Uint32 binding, Bool storage,
-            VkDescriptorImageInfo& out, VkFormat boundStorageFormat, Uint32 unit) const {
-        // GL 4.6 core 8.26, codex closeout finding 2: every access through an invalid image unit
-        // is invalid - a load returns zero, a store and an atomic are discarded. A NULL storage
-        // descriptor (VK_EXT_robustness2 nullDescriptor) is exactly that, for any target, format
-        // and sample count, so nothing below is needed.
-        if (storage && m_wireInvalidStorageImagesBindNull) {
-            out = {VK_NULL_HANDLE, VK_NULL_HANDLE, VK_IMAGE_LAYOUT_GENERAL};
-            return true;
-        }
-        if (binding >= programObj.samplerTextureTargetByBinding.size() ||
-            binding >= programObj.samplerNumericDomainByBinding.size()) return false;
-        const auto target = programObj.samplerTextureTargetByBinding[binding];
-        const auto domain = programObj.samplerNumericDomainByBinding[binding];
-        const Bool multisample = target == TextureTarget::Texture2DMultisample ||
-                                target == TextureTarget::Texture2DMultisampleArray;
-        Bool shadow = false;
-        if (!storage) {
-            const Int location = programObj.samplerUniformLocationByBinding[binding];
-            switch (program.GetUniformType(static_cast<Uint>(location))) {
-            case GL_SAMPLER_1D_SHADOW: case GL_SAMPLER_2D_SHADOW: case GL_SAMPLER_CUBE_SHADOW:
-            case GL_SAMPLER_1D_ARRAY_SHADOW: case GL_SAMPLER_2D_ARRAY_SHADOW:
-            case GL_SAMPLER_CUBE_MAP_ARRAY_SHADOW: case GL_SAMPLER_2D_RECT_SHADOW: shadow = true; break;
-            default: break;
-            }
-        }
-        VkFormat format = VK_FORMAT_UNDEFINED;
-        if (storage) {
-            if (binding >= programObj.storageImageFormatByBinding.size()) return false;
-            format = programObj.storageImageFormatByBinding[binding];
-            // A formatless declaration of an INVALID binding (a unit whose texture lacks the
-            // named level or layer) takes the format the application bound, where the device can
-            // store to it and it is in the shader's numeric class. The R32 default expands a load
-            // to (0, 0, 0, 1); a four-channel carrier cleared to zero reads (0, 0, 0, 0), which
-            // is what KHR-GL46.shader_image_load_store.incomplete_textures compares against.
-            if (format == VK_FORMAT_UNDEFINED && boundStorageFormat != VK_FORMAT_UNDEFINED) {
-                const Bool classMatches = domain == SamplerNumericDomain::Float
-                    ? !vkuFormatIsUINT(boundStorageFormat) && !vkuFormatIsSINT(boundStorageFormat)
-                    : domain == SamplerNumericDomain::SignedInteger ? vkuFormatIsSINT(boundStorageFormat)
-                    : domain == SamplerNumericDomain::UnsignedInteger && vkuFormatIsUINT(boundStorageFormat);
-                VkFormatProperties properties{};
-                if (classMatches) vkGetPhysicalDeviceFormatProperties(m_physicalDevice, boundStorageFormat, &properties);
-                if (properties.optimalTilingFeatures & VK_FORMAT_FEATURE_STORAGE_IMAGE_BIT) format = boundStorageFormat;
-            }
-            if (format == VK_FORMAT_UNDEFINED) format = PlaceholderFormatForNumericDomain(domain);
-        } else if (shadow) format = VK_FORMAT_D16_UNORM;
-        else if (domain == SamplerNumericDomain::Float) format = VK_FORMAT_R8G8B8A8_UNORM;
-        else if (domain == SamplerNumericDomain::SignedInteger) format = VK_FORMAT_R8G8B8A8_SINT;
-        else if (domain == SamplerNumericDomain::UnsignedInteger) format = VK_FORMAT_R8G8B8A8_UINT;
-        if (format == VK_FORMAT_UNDEFINED) return false;
-        VkImageType imageType = VK_IMAGE_TYPE_2D;
-        VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
-        VkImageCreateFlags flags = 0;
-        Uint32 layers = 1;
-        switch (target) {
-        case TextureTarget::Texture1D: imageType = VK_IMAGE_TYPE_1D; viewType = VK_IMAGE_VIEW_TYPE_1D; break;
-        case TextureTarget::Texture1DArray: imageType = VK_IMAGE_TYPE_1D; viewType = VK_IMAGE_VIEW_TYPE_1D_ARRAY; break;
-        case TextureTarget::Texture2D: case TextureTarget::TextureRectangle:
-        case TextureTarget::Texture2DMultisample: break;
-        case TextureTarget::Texture2DArray: case TextureTarget::Texture2DMultisampleArray:
-            viewType = VK_IMAGE_VIEW_TYPE_2D_ARRAY; break;
-        case TextureTarget::Texture3D: imageType = VK_IMAGE_TYPE_3D; viewType = VK_IMAGE_VIEW_TYPE_3D; break;
-        case TextureTarget::TextureCubeMap: case TextureTarget::TextureCubeMapArray:
-            flags = VK_IMAGE_CREATE_CUBE_COMPATIBLE_BIT; layers = 6;
-            viewType = target == TextureTarget::TextureCubeMap ? VK_IMAGE_VIEW_TYPE_CUBE : VK_IMAGE_VIEW_TYPE_CUBE_ARRAY;
-            break;
-        default: return false;
-        }
-        // A STORAGE placeholder is private to its unit (per shape). Shared by shape alone, a store
-        // through invalid unit A was visible, after a barrier, to a load through invalid unit B of
-        // the same shape - one Vulkan image behind both (codex closeout finding 2). The clear
-        // below still runs before each use; what a private image cannot hide is the SAME unit's
-        // own store to its own later load inside one pass (CONTRACT-P7 §12). Not per binding: GL
-        // aliases per unit, and a (binding, unit) key only multiplied allocations. Past
-        // kWirePrivateStoragePlaceholderCap a new (shape, unit) shares its shape's (WirePlaceholderKey.h).
-        const Uint64 shape = static_cast<Uint32>(format) | (static_cast<Uint64>(target) << 32) |
-                             (static_cast<Uint64>(storage) << 48) | (static_cast<Uint64>(shadow) << 49);
-        const WirePlaceholderKey key = ChooseWirePlaceholderKey(shape, storage, unit, m_wirePrivateStoragePlaceholders,
-            [this](const WirePlaceholderKey& candidate) { return m_wirePlaceholderImages.count(candidate) != 0; });
-        if (storage && unit != WirePlaceholderKey::kShared && key.unit == WirePlaceholderKey::kShared) {
-            MGLOG_W_ONCE("Magma wire: %zu image-unit-private placeholders exist (the cap); a further invalid or "
-                         "unbound unit shares its shape's placeholder, so two such units of one shape can alias",
-                         static_cast<size_t>(m_wirePrivateStoragePlaceholders));
-        }
-        auto found = m_wirePlaceholderImages.find(key);
-        if (found == m_wirePlaceholderImages.end()) {
-            WirePlaceholderImage image{};
-            image.format = format; image.layers = layers;
-            image.aspect = shadow ? VK_IMAGE_ASPECT_DEPTH_BIT : VK_IMAGE_ASPECT_COLOR_BIT;
-            const auto fail = [&] {
-                MGLOG_E_ONCE("Magma wire placeholder allocation failed: target=%d format=%d storage=%d multisample=%d",
-                    static_cast<Int>(target), static_cast<Int>(format), static_cast<Int>(storage), static_cast<Int>(multisample));
-                DestroyWirePlaceholderImage(image);
-                return false;
-            };
-            const VkImageUsageFlags usage = (storage ? VK_IMAGE_USAGE_STORAGE_BIT : VK_IMAGE_USAGE_SAMPLED_BIT) |
-                (multisample ? VK_IMAGE_USAGE_COLOR_ATTACHMENT_BIT : VK_IMAGE_USAGE_TRANSFER_DST_BIT);
-            VkImageFormatProperties properties{};
-            if (vkGetPhysicalDeviceImageFormatProperties(m_physicalDevice, format, imageType,
-                    VK_IMAGE_TILING_OPTIMAL, usage, flags, &properties) != VK_SUCCESS) return fail();
-            if (multisample) {
-                // MS=1 in SPIR-V cannot name a single-sampled image, even when
-                // the shader's runtime branch does not fetch that descriptor.
-                image.samples = VK_SAMPLE_COUNT_FLAG_BITS_MAX_ENUM;
-                for (const auto sample : {VK_SAMPLE_COUNT_2_BIT, VK_SAMPLE_COUNT_4_BIT, VK_SAMPLE_COUNT_8_BIT,
-                                          VK_SAMPLE_COUNT_16_BIT, VK_SAMPLE_COUNT_32_BIT, VK_SAMPLE_COUNT_64_BIT}) {
-                    if (properties.sampleCounts & sample) { image.samples = sample; break; }
-                }
-                if (image.samples == VK_SAMPLE_COUNT_FLAG_BITS_MAX_ENUM) return fail();
-            }
-            VkImageCreateInfo create{VK_STRUCTURE_TYPE_IMAGE_CREATE_INFO};
-            create.flags = flags; create.imageType = imageType; create.format = format;
-            create.extent = {1, 1, 1}; create.mipLevels = 1; create.arrayLayers = layers;
-            create.samples = image.samples; create.tiling = VK_IMAGE_TILING_OPTIMAL;
-            create.usage = usage; create.sharingMode = VK_SHARING_MODE_EXCLUSIVE;
-            if (vkCreateImage(m_device, &create, nullptr, &image.image) != VK_SUCCESS) return fail();
-            VkMemoryRequirements requirements{};
-            vkGetImageMemoryRequirements(m_device, image.image, &requirements);
-            VkPhysicalDeviceMemoryProperties memoryProperties{};
-            vkGetPhysicalDeviceMemoryProperties(m_physicalDevice, &memoryProperties);
-            Uint32 memoryType = ~0u;
-            for (Uint32 i = 0; i < memoryProperties.memoryTypeCount; ++i) {
-                if (!(requirements.memoryTypeBits & (1u << i))) continue;
-                if (memoryType == ~0u) memoryType = i;
-                if (memoryProperties.memoryTypes[i].propertyFlags & VK_MEMORY_PROPERTY_DEVICE_LOCAL_BIT) {
-                    memoryType = i; break;
-                }
-            }
-            if (memoryType == ~0u) return fail();
-            VkMemoryAllocateInfo allocate{VK_STRUCTURE_TYPE_MEMORY_ALLOCATE_INFO};
-            allocate.allocationSize = requirements.size; allocate.memoryTypeIndex = memoryType;
-            if (vkAllocateMemory(m_device, &allocate, nullptr, &image.memory) != VK_SUCCESS ||
-                vkBindImageMemory(m_device, image.image, image.memory, 0) != VK_SUCCESS) return fail();
-            VkImageViewCreateInfo view{VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO};
-            view.image = image.image; view.viewType = viewType; view.format = format;
-            view.subresourceRange = {image.aspect, 0, 1, 0, layers};
-            if (vkCreateImageView(m_device, &view, nullptr, &image.view) != VK_SUCCESS) return fail();
-            if (!storage) {
-                VkSamplerCreateInfo sampler{VK_STRUCTURE_TYPE_SAMPLER_CREATE_INFO};
-                sampler.magFilter = sampler.minFilter = VK_FILTER_NEAREST;
-                sampler.mipmapMode = VK_SAMPLER_MIPMAP_MODE_NEAREST;
-                sampler.addressModeU = sampler.addressModeV = sampler.addressModeW = VK_SAMPLER_ADDRESS_MODE_CLAMP_TO_EDGE;
-                sampler.compareEnable = shadow; sampler.compareOp = VK_COMPARE_OP_LESS_OR_EQUAL;
-                sampler.maxLod = 0.0f;
-                if (vkCreateSampler(m_device, &sampler, nullptr, &image.sampler) != VK_SUCCESS) return fail();
-            }
-            if (multisample) {
-                VkAttachmentDescription attachment{};
-                attachment.format = format; attachment.samples = image.samples;
-                attachment.loadOp = VK_ATTACHMENT_LOAD_OP_CLEAR; attachment.storeOp = VK_ATTACHMENT_STORE_OP_STORE;
-                attachment.initialLayout = VK_IMAGE_LAYOUT_UNDEFINED; attachment.finalLayout = VK_IMAGE_LAYOUT_GENERAL;
-                VkAttachmentReference color{0, VK_IMAGE_LAYOUT_COLOR_ATTACHMENT_OPTIMAL};
-                VkSubpassDescription subpass{};
-                subpass.pipelineBindPoint = VK_PIPELINE_BIND_POINT_GRAPHICS;
-                subpass.colorAttachmentCount = 1; subpass.pColorAttachments = &color;
-                VkRenderPassCreateInfo pass{VK_STRUCTURE_TYPE_RENDER_PASS_CREATE_INFO};
-                pass.attachmentCount = 1; pass.pAttachments = &attachment;
-                pass.subpassCount = 1; pass.pSubpasses = &subpass;
-                VkSubpassDependency dependencies[2]{};
-                dependencies[0] = {VK_SUBPASS_EXTERNAL, 0, VK_PIPELINE_STAGE_ALL_COMMANDS_BIT,
-                    VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT,
-                    VK_ACCESS_MEMORY_READ_BIT | VK_ACCESS_MEMORY_WRITE_BIT, VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT, 0};
-                dependencies[1] = {0, VK_SUBPASS_EXTERNAL, VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT,
-                    VK_PIPELINE_STAGE_ALL_COMMANDS_BIT, VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT,
-                    VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT, 0};
-                pass.dependencyCount = 2; pass.pDependencies = dependencies;
-                if (vkCreateRenderPass(m_device, &pass, nullptr, &image.clearPass) != VK_SUCCESS) return fail();
-                VkFramebufferCreateInfo framebuffer{VK_STRUCTURE_TYPE_FRAMEBUFFER_CREATE_INFO};
-                framebuffer.renderPass = image.clearPass; framebuffer.attachmentCount = 1;
-                framebuffer.pAttachments = &image.view; framebuffer.width = framebuffer.height = 1; framebuffer.layers = layers;
-                if (vkCreateFramebuffer(m_device, &framebuffer, nullptr, &image.clearFramebuffer) != VK_SUCCESS) return fail();
-            }
-            found = m_wirePlaceholderImages.emplace(key, image).first;
-            if (key.unit != WirePlaceholderKey::kShared) ++m_wirePrivateStoragePlaceholders;
-        }
-        auto& image = found->second;
-        // Sampled incomplete textures remain immutable opaque black. A storage
-        // placeholder is reset before each use, so a prior discarded store cannot
-        // leak into a later pass's loads through the same unit.
-        if (storage || image.layout == VK_IMAGE_LAYOUT_UNDEFINED) {
-            VkClearValue clear{};
-            if (!storage) {
-                if (domain == SamplerNumericDomain::SignedInteger) clear.color.int32[3] = 1;
-                else if (domain == SamplerNumericDomain::UnsignedInteger) clear.color.uint32[3] = 1;
-                else clear.color.float32[3] = 1.0f;
-            }
-            if (multisample) {
-                VkRenderPassBeginInfo begin{VK_STRUCTURE_TYPE_RENDER_PASS_BEGIN_INFO};
-                begin.renderPass = image.clearPass; begin.framebuffer = image.clearFramebuffer;
-                begin.renderArea.extent = {1, 1}; begin.clearValueCount = 1; begin.pClearValues = &clear;
-                vkCmdBeginRenderPass(commands, &begin, VK_SUBPASS_CONTENTS_INLINE);
-                vkCmdEndRenderPass(commands);
-                image.layout = VK_IMAGE_LAYOUT_GENERAL;
-            } else {
-                if (!VkTextureManager::TransitionImageLayout(commands, image.image, image.layout,
-                        VK_IMAGE_LAYOUT_TRANSFER_DST_OPTIMAL, VK_PIPELINE_STAGE_ALL_COMMANDS_BIT,
-                        VK_PIPELINE_STAGE_TRANSFER_BIT, VK_ACCESS_MEMORY_WRITE_BIT | VK_ACCESS_MEMORY_READ_BIT,
-                        VK_ACCESS_TRANSFER_WRITE_BIT, image.aspect)) return false;
-                const VkImageSubresourceRange range{image.aspect, 0, 1, 0, image.layers};
-                if (shadow) {
-                    const VkClearDepthStencilValue depth{0.0f, 0};
-                    vkCmdClearDepthStencilImage(commands, image.image, image.layout, &depth, 1, &range);
-                } else vkCmdClearColorImage(commands, image.image, image.layout, &clear.color, 1, &range);
-                if (!VkTextureManager::TransitionImageLayout(commands, image.image, image.layout,
-                        VK_IMAGE_LAYOUT_GENERAL, VK_PIPELINE_STAGE_TRANSFER_BIT, VK_PIPELINE_STAGE_ALL_COMMANDS_BIT,
-                        VK_ACCESS_TRANSFER_WRITE_BIT, VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT,
-                        image.aspect)) return false;
-            }
-            VkMemoryBarrier visible{VK_STRUCTURE_TYPE_MEMORY_BARRIER};
-            visible.srcAccessMask = multisample ? VK_ACCESS_COLOR_ATTACHMENT_WRITE_BIT : VK_ACCESS_TRANSFER_WRITE_BIT;
-            visible.dstAccessMask = VK_ACCESS_SHADER_READ_BIT | VK_ACCESS_SHADER_WRITE_BIT;
-            vkCmdPipelineBarrier(commands, multisample ? VK_PIPELINE_STAGE_COLOR_ATTACHMENT_OUTPUT_BIT : VK_PIPELINE_STAGE_TRANSFER_BIT,
-                VK_PIPELINE_STAGE_ALL_COMMANDS_BIT, 0, 1, &visible, 0, nullptr, 0, nullptr);
-        }
-        out = {image.sampler, image.view, VK_IMAGE_LAYOUT_GENERAL};
-        return true;
-    }
-#endif

MobileGL/MG_Backend/DirectVulkan/Renderer/WirePlaceholderKey.h

@@ -1,62 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/Renderer/WirePlaceholderKey.h
-// Copyright (c) 2025-2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-#pragma once
-
-#include <Includes.h>
-
-// The pure half of UniformManager's wire placeholder cache (WirePlaceholderImages.inc): WHICH
-// placeholder a binding with no usable image takes. A unit test pins it
-// (MG_Test/Pipeline/PipelineQuirkTest.cpp); the Vulkan half that makes the image stays in the .inc.
-#if MOBILEGL_BUILD_DISAGGREGATED
-#include <MG_Pipe/MGPipeTypes.h>
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    // The placeholder's SHAPE (format, target, storage, shadow) and, for a STORAGE placeholder on
-    // the arm without a null descriptor, the image UNIT it is private to. GL aliases per UNIT, so the
-    // unit is the whole of the no-alias guarantee (codex closeout finding 2): two bindings that name
-    // one unit are one GL image, and keying them apart as well only multiplied allocations (cf-magma
-    // critic). A sampled placeholder is never written, so it stays shared: its unit is kShared.
-    struct WirePlaceholderKey {
-        static constexpr Uint32 kShared = ~0u;
-        Uint64 shape = 0;
-        Uint32 unit = kShared;
-        Bool operator==(const WirePlaceholderKey& other) const { return shape == other.shape && unit == other.unit; }
-    };
-
-    struct WirePlaceholderKeyHash {
-        SizeT operator()(const WirePlaceholderKey& key) const {
-            Uint64 h = key.shape * 0x9E3779B97F4A7C15ull;
-            h ^= static_cast<Uint64>(key.unit) + 0x9E3779B97F4A7C15ull + (h << 6) + (h >> 2);
-            return static_cast<SizeT>(h);
-        }
-    };
-
-    // Every private placeholder is its own vkCreateImage + vkAllocateMemory, freed only at Shutdown.
-    // (shape, unit) bounds them by shapes x kMGPipeMaxImageUnits, and a peer rotating formats and
-    // targets across the units could still walk that towards maxMemoryAllocationCount (4096 is the
-    // spec minimum). So past this many, a NEW (shape, unit) takes its shape's SHARED placeholder - the
-    // pre-fix aliasing, logged once by the caller - instead of another allocation; a unit that already
-    // has its private placeholder keeps it. Two per unit is far past any real program.
-    inline constexpr SizeT kWirePrivateStoragePlaceholderCap = 2 * static_cast<SizeT>(MG_Pipe::kMGPipeMaxImageUnits);
-
-    // The key a placeholder of `shape` is found or made under. `privateStorage` = a storage binding on
-    // the arm without a null descriptor (with one, the caller never gets here); `unit` = its image
-    // unit; `privateCount` = how many private placeholders exist; `known(key)` = the cache holds `key`.
-    template <typename KnownFn>
-    WirePlaceholderKey ChooseWirePlaceholderKey(Uint64 shape, Bool privateStorage, Uint32 unit, SizeT privateCount,
-                                                KnownFn&& known) {
-        WirePlaceholderKey key;
-        key.shape = shape;
-        if (!privateStorage || unit == WirePlaceholderKey::kShared) return key;
-        key.unit = unit;
-        if (privateCount < kWirePrivateStoragePlaceholderCap || known(key)) return key;
-        key.unit = WirePlaceholderKey::kShared;
-        return key;
-    }
-} // namespace MobileGL::MG_Backend::DirectVulkan
-#endif

MobileGL/MG_Backend/DirectVulkan/Renderer/WireRenderPassCompatibility.h

@@ -1,49 +0,0 @@
-#pragma once
-#include <Includes.h>
-#include "../VkIncludes.h"
-
-#if MOBILEGL_BUILD_DISAGGREGATED
-namespace MobileGL::MG_Backend::DirectVulkan {
-    // The wire draw pass has one graphics subpass, no input attachments,
-    // multiview or extensions. Its Vulkan pipeline compatibility is formats,
-    // sample counts and the ordered attachment references, not native handles,
-    // image identity, dimensions, load/store operations or image layouts.
-    struct WireRenderPassCompatibilityKey {
-        Vector<Uint64> attachmentFormatsAndSamples;
-        Vector<Uint32> colorReferences;
-        Uint32 depthReference = VK_ATTACHMENT_UNUSED;
-        Bool operator==(const WireRenderPassCompatibilityKey&) const = default;
-    };
-
-    struct WireRenderPassCompatibilityHash {
-        SizeT operator()(const WireRenderPassCompatibilityKey& key) const {
-            SizeT hash = 0;
-            const auto mix = [&](Uint64 value) {
-                hash ^= static_cast<SizeT>(value) + 0x9e3779b97f4a7c15ull + (hash << 6) + (hash >> 2);
-            };
-            mix(key.attachmentFormatsAndSamples.size());
-            for (const auto value : key.attachmentFormatsAndSamples) mix(value);
-            mix(key.colorReferences.size());
-            for (const auto value : key.colorReferences) mix(value);
-            mix(key.depthReference);
-            return hash;
-        }
-    };
-
-    class WireRenderPassCompatibilityTable {
-    public:
-        Uint64 Intern(const WireRenderPassCompatibilityKey& key) {
-            if (const auto found = m_ids.find(key); found != m_ids.end()) return found->second;
-            // No reset/eviction: an ID cannot be reused while a pipeline factory
-            // or a renderer memo can still hold its previous meaning.
-            MOBILEGL_ASSERT(m_nextId != 0, "wire render-pass compatibility ID exhausted");
-            const Uint64 id = m_nextId++;
-            m_ids.emplace(key, id);
-            return id;
-        }
-    private:
-        UnorderedMap<WireRenderPassCompatibilityKey, Uint64, WireRenderPassCompatibilityHash> m_ids;
-        Uint64 m_nextId = 1; // zero selects the native-handle pipeline domain
-    };
-}
-#endif

MobileGL/MG_Backend/DirectVulkan/Renderer/WireTextureReadback.inc

@@ -1,214 +0,0 @@
-// Server-owned texture readback. Included after WireFramebuffer.inc so image
-// layout tracking and frame retirement are the same as every other wire verb.
-#if MOBILEGL_BUILD_DISAGGREGATED
-    static Bool PackWireColorTight(const Uint8* source, SizeT sourceBytes, VkFormat format,
-                                   TextureInternalFormat logicalFormat, const MG_Pipe::MGPReadbackInfo& info,
-                                   Vector<Uint8>& result) {
-        using namespace DirectGLES::ReadbackImpl;
-        ReadbackChannelMapping mapping{};
-        if (!GetReadbackChannelMapping(info.Format, mapping)) return false;
-        const SizeT sourcePixelSize = VulkanRenderer::GetReadbackTexelSize(format);
-        const SizeT pixelBytes = GetReadbackDstPixelSize(mapping, info.Type);
-        const Uint64 rows64 = Uint64(info.Box.H) * info.Box.D;
-        if (!info.Box.W || !rows64 || rows64 > std::numeric_limits<GLsizei>::max() ||
-            rows64 > std::numeric_limits<SizeT>::max() / 16 / info.Box.W) return false;
-        const SizeT pixels = static_cast<SizeT>(info.Box.W) * static_cast<SizeT>(rows64);
-        if (!sourcePixelSize || !pixelBytes || sourceBytes != pixels * sourcePixelSize ||
-            info.DstSize != pixels * pixelBytes) return false;
-        if (MG_Util::PixelStoreProcessor::IsRawPackedPixelTransfer(GetPackedReadbackInternalFormat(format),
-                MG_Util::ConvertGLEnumToTextureInputFormat(info.Format),
-                MG_Util::ConvertGLEnumToTexturePixelDataType(info.Type))) {
-            if (pixelBytes != sourcePixelSize) return false;
-            result.assign(source, source + sourceBytes);
-            return true;
-        }
-        Vector<Uint8> wide;
-        GLenum wideType = GL_NONE;
-        const GLsizei rows = static_cast<GLsizei>(Uint64(info.Box.H) * info.Box.D);
-        if (!DecodeReadbackRowsToWide(source, format, info.Box.W, rows, wide, wideType) ||
-            mapping.isInteger != (wideType == GL_INT || wideType == GL_UNSIGNED_INT)) return false;
-        if (ResolveTextureFormatInfo(logicalFormat).expandRgbToRgba) {
-            const Float floatOne = 1.0f;
-            const Uint32 integerOne = 1;
-            const void* alpha = wideType == GL_FLOAT ? static_cast<const void*>(&floatOne) : &integerOne;
-            for (SizeT i = 0; i < pixels; ++i)
-                Memcpy(wide.data() + (i * 4 + 3) * sizeof(Uint32), alpha, sizeof(Uint32));
-        }
-        result.resize(info.DstSize);
-        for (GLsizei row = 0; row < rows; ++row)
-            ConvertWideReadbackRow(wide.data() + row * static_cast<SizeT>(info.Box.W) * 16,
-                result.data() + row * static_cast<SizeT>(info.Box.W) * pixelBytes,
-                info.Box.W, wideType, mapping, info.Type);
-        return true;
-    }
-
-    Bool VulkanRenderer::ReadTextureImageWire(const MG_Pipe::MGPReadbackInfo& info,
-                                               Vector<Uint8>& ownedBytes) {
-        ownedBytes.clear();
-        const auto& box = info.Box;
-        if (box.X || box.Y || box.Z || !box.W || !box.H || !box.D ||
-            box.W > static_cast<Uint32>(std::numeric_limits<GLsizei>::max()) ||
-            Uint64(box.H) * box.D > static_cast<Uint64>(std::numeric_limits<GLsizei>::max())) return false;
-        const auto& state = MG_Pipe::MGPipeApplier();
-        if (MG_Pipe::MGPipeHandleIsNull(info.Res) || info.Res.Slot >= state.TextureResources.size()) return false;
-        const auto& record = state.TextureResources[info.Res.Slot];
-        if (!record.Live || record.Gen != info.Res.Gen) return false;
-
-        using Target = MG_Pipe::MGPipeResourceTarget;
-        const auto target = static_cast<Target>(record.Desc.Target);
-        const Bool oneDArray = target == Target::Tex1DArray;
-        const Bool volume = target == Target::Tex3D;
-        Uint32 level = info.Level, layer = 0, layerCount = 1, availableLayers = 1;
-        VkExtent3D extent{box.W, box.H, 1};
-        if (oneDArray) {
-            if (info.Target != GL_TEXTURE_1D_ARRAY || box.D != 1) return false;
-            layerCount = box.H; extent.height = 1;
-        } else if (volume) {
-            if (info.Target != GL_TEXTURE_3D) return false;
-            extent.depth = box.D;
-        } else if (target == Target::Tex2DArray || target == Target::TexCubeArray) {
-            if (info.Target != (target == Target::Tex2DArray ? GL_TEXTURE_2D_ARRAY : GL_TEXTURE_CUBE_MAP_ARRAY)) return false;
-            layerCount = box.D;
-        } else if (target == Target::TexCube) {
-            if (info.Target == GL_TEXTURE_CUBE_MAP) {
-                if (box.D != 6) return false;
-                layerCount = 6;
-            } else if (info.Target >= GL_TEXTURE_CUBE_MAP_POSITIVE_X && info.Target <= GL_TEXTURE_CUBE_MAP_NEGATIVE_Z) {
-                if (box.D != 1) return false;
-                layer = info.Target - GL_TEXTURE_CUBE_MAP_POSITIVE_X;
-            } else return false;
-        } else {
-            if (box.D != 1) return false;
-            const GLenum expected = target == Target::Tex1D ? GL_TEXTURE_1D :
-                                    target == Target::Tex2D ? GL_TEXTURE_2D :
-                                    target == Target::TexRect ? GL_TEXTURE_RECTANGLE : GL_NONE;
-            if (!expected || info.Target != expected || (target == Target::Tex1D && box.H != 1)) return false;
-        }
-        VkFormat viewFormat = VK_FORMAT_UNDEFINED;
-        const auto storage = m_textureManager->ResolveWireTextureStorage(info.Res, level, layer, &viewFormat, &availableLayers);
-        if (MG_Pipe::MGPipeHandleIsNull(storage)) return false;
-        const Uint64 pixels64 = Uint64(box.W) * box.H * box.D;
-        if (pixels64 > std::numeric_limits<SizeT>::max() / 16) return false;
-        const auto readUnbacked = [&]() {
-            // Only a level the VkImage cannot represent may use its owned,
-            // non-GPU-dirty staging bytes. A failed GPU read never falls back.
-            if (storage != info.Res || info.Target == GL_TEXTURE_CUBE_MAP) return false;
-            Vector<Uint8> raw;
-            VkFormat nativeFormat = VK_FORMAT_UNDEFINED;
-            if (!m_textureManager->ReadUnbackedWireLevel(storage,
-                    MG_Util::ConvertGLEnumToTextureUploadTarget(info.Target), info.Level,
-                    IntVec3{static_cast<Int>(box.W), static_cast<Int>(box.H), static_cast<Int>(box.D)},
-                    nativeFormat, raw)) return false;
-            return PackWireColorTight(raw.data(), raw.size(), nativeFormat,
-                static_cast<TextureInternalFormat>(record.Desc.InternalFormat), info, ownedBytes);
-        };
-        RetireWireDrawPass();
-        MakeXfbWritesVisible();
-        auto* resource = m_textureManager->SyncTextureResourceByHandle(storage);
-        if (!resource || !resource->image || level >= resource->mipLevels) return readUnbacked();
-        if (resource->sampleCount != VK_SAMPLE_COUNT_1_BIT) return false;
-        m_textureManager->FlushPendingUploads();
-        const Bool nativeVolume = resource->viewType == VK_IMAGE_VIEW_TYPE_3D;
-        const Uint32 nativeDepth = nativeVolume ? std::max(resource->depth >> level, 1u) : resource->arrayLayers;
-        if (extent.width != std::max(resource->extent.width >> level, 1u) ||
-            extent.height != std::max(resource->extent.height >> level, 1u) ||
-            layer >= nativeDepth || (nativeVolume ? extent.depth : layerCount) > nativeDepth - layer ||
-            (!nativeVolume && layerCount > availableLayers)) return readUnbacked();
-        // A view can reinterpret the same native words. Decode using the outer
-        // view format, while Vulkan copies the storage allocation's bytes.
-        const VkFormat format = viewFormat == VK_FORMAT_UNDEFINED ? resource->format : viewFormat;
-        const Bool depth = info.Format == GL_DEPTH_COMPONENT || info.Format == GL_DEPTH_STENCIL;
-        const Bool stencil = info.Format == GL_STENCIL_INDEX || info.Format == GL_DEPTH_STENCIL;
-        const Bool depthStencil = depth || stencil;
-        const VkImageAspectFlags aspects = depthStencil ?
-            ((depth ? VK_IMAGE_ASPECT_DEPTH_BIT : 0) | (stencil ? VK_IMAGE_ASPECT_STENCIL_BIT : 0)) : VK_IMAGE_ASPECT_COLOR_BIT;
-        if ((resource->aspect & aspects) != aspects) return false;
-        const SizeT pixels = static_cast<SizeT>(pixels64);
-        const SizeT destinationPixelSize = MG_Util::GetInputBytesPerPixel(
-            MG_Util::ConvertGLEnumToTextureInputFormat(info.Format), MG_Util::ConvertGLEnumToTexturePixelDataType(info.Type));
-        if (!destinationPixelSize || pixels64 * destinationPixelSize != info.DstSize) return false;
-        SizeT sourcePixelSize = GetReadbackTexelSize(resource->format);
-        if (depthStencil) {
-            switch (resource->format) {
-            case VK_FORMAT_D16_UNORM: sourcePixelSize = 2; break;
-            case VK_FORMAT_D24_UNORM_S8_UINT: case VK_FORMAT_X8_D24_UNORM_PACK32:
-            case VK_FORMAT_D32_SFLOAT: case VK_FORMAT_D32_SFLOAT_S8_UINT: sourcePixelSize = 4; break;
-            case VK_FORMAT_S8_UINT: sourcePixelSize = 0; break;
-            default: return false;
-            }
-        } else if (!sourcePixelSize || sourcePixelSize != GetReadbackTexelSize(format)) return false;
-        const VkDeviceSize firstBytes = pixels * (depthStencil ? (depth ? sourcePixelSize : 0) : sourcePixelSize);
-        const VkDeviceSize stencilOffset = (firstBytes + 3) & ~VkDeviceSize{3};
-        const VkDeviceSize copyBytes = depthStencil ? stencilOffset + (stencil ? pixels : 0) : firstBytes;
-        if (!copyBytes) return false;
-        VkBufferObject readback;
-        if (!readback.Create({.allocator = m_allocator, .size = copyBytes, .usage = VK_BUFFER_USAGE_TRANSFER_DST_BIT,
-                .memoryUsage = VMA_MEMORY_USAGE_AUTO, .allocationFlags = VMA_ALLOCATION_CREATE_HOST_ACCESS_RANDOM_BIT})) return false;
-        WireImage image{};
-        image.image = resource->image; image.format = resource->format; image.aspect = resource->aspect;
-        image.layout = resource->layout; image.trackedLayout = &resource->layout; image.levels = resource->mipLevels;
-        const auto restore = image.layout == VK_IMAGE_LAYOUT_UNDEFINED ? VK_IMAGE_LAYOUT_GENERAL : image.layout;
-        TransitionWireImage(image, VK_IMAGE_LAYOUT_TRANSFER_SRC_OPTIMAL);
-        VkBufferImageCopy regions[2]{};
-        Uint32 regionCount = 0;
-        const auto addCopy = [&](VkImageAspectFlags aspect, VkDeviceSize offset) {
-            auto& copy = regions[regionCount++];
-            copy.bufferOffset = offset;
-            copy.imageSubresource = {aspect, level, nativeVolume ? 0u : layer, nativeVolume ? 1u : layerCount};
-            copy.imageOffset = {0, 0, nativeVolume ? static_cast<Int32>(layer) : 0};
-            copy.imageExtent = extent;
-        };
-        if (!depthStencil) addCopy(VK_IMAGE_ASPECT_COLOR_BIT, 0);
-        if (depth) addCopy(VK_IMAGE_ASPECT_DEPTH_BIT, 0);
-        if (stencil) addCopy(VK_IMAGE_ASPECT_STENCIL_BIT, stencilOffset);
-        auto& frame = m_frameContext.GetCurrent();
-        vkCmdCopyImageToBuffer(frame.commandBuffer, image.image, VK_IMAGE_LAYOUT_TRANSFER_SRC_OPTIMAL,
-                              readback.GetHandle(), regionCount, regions);
-        TransitionWireImage(image, restore);
-        VkMemoryBarrier host{VK_STRUCTURE_TYPE_MEMORY_BARRIER};
-        host.srcAccessMask = VK_ACCESS_TRANSFER_WRITE_BIT; host.dstAccessMask = VK_ACCESS_HOST_READ_BIT;
-        vkCmdPipelineBarrier(frame.commandBuffer, VK_PIPELINE_STAGE_TRANSFER_BIT, VK_PIPELINE_STAGE_HOST_BIT,
-                             0, 1, &host, 0, nullptr, 0, nullptr);
-        if (!SubmitReadbackCommandsAndWait(frame)) return false;
-        const auto* mapped = static_cast<const Uint8*>(readback.Map());
-        if (!mapped || !readback.Invalidate(copyBytes)) return false;
-        Vector<Uint8> result;
-        if (depthStencil) {
-            if (!PackDepthStencilTight(depth ? mapped : nullptr, stencil ? mapped + stencilOffset : nullptr,
-                                       resource->format, pixels, info.Format, info.Type, result)) return false;
-        } else {
-            using namespace DirectGLES::ReadbackImpl;
-            ReadbackChannelMapping mapping{};
-            if (!GetReadbackChannelMapping(info.Format, mapping) ||
-                GetReadbackDstPixelSize(mapping, info.Type) != destinationPixelSize) return false;
-            if (MG_Util::PixelStoreProcessor::IsRawPackedPixelTransfer(GetPackedReadbackInternalFormat(format),
-                    MG_Util::ConvertGLEnumToTextureInputFormat(info.Format),
-                    MG_Util::ConvertGLEnumToTexturePixelDataType(info.Type))) {
-                if (destinationPixelSize != sourcePixelSize) return false;
-                result.assign(mapped, mapped + firstBytes);
-            } else {
-                Vector<Uint8> wide;
-                GLenum wideType = GL_NONE;
-                const GLsizei rows = static_cast<GLsizei>(Uint64(box.H) * box.D);
-                if (!DecodeReadbackRowsToWide(mapped, format, box.W, rows, wide, wideType) ||
-                    mapping.isInteger != (wideType == GL_INT || wideType == GL_UNSIGNED_INT)) return false;
-                if (ResolveTextureFormatInfo(static_cast<TextureInternalFormat>(record.Desc.InternalFormat)).expandRgbToRgba) {
-                    const Float floatOne = 1.0f;
-                    const Uint32 integerOne = 1;
-                    const void* alpha = wideType == GL_FLOAT ? static_cast<const void*>(&floatOne) : &integerOne;
-                    for (SizeT i = 0; i < pixels; ++i)
-                        Memcpy(wide.data() + (i * 4 + 3) * sizeof(Uint32), alpha, sizeof(Uint32));
-                }
-                result.resize(pixels * destinationPixelSize);
-                const SizeT srcRow = static_cast<SizeT>(box.W) * 4 * sizeof(Uint32);
-                const SizeT dstRow = static_cast<SizeT>(box.W) * destinationPixelSize;
-                for (GLsizei row = 0; row < rows; ++row)
-                    ConvertWideReadbackRow(wide.data() + row * srcRow, result.data() + row * dstRow,
-                                           box.W, wideType, mapping, info.Type);
-            }
-        }
-        if (result.size() != info.DstSize) return false;
-        ownedBytes = Move(result);
-        return true;
-    }
-#endif

MobileGL/MG_Backend/DirectVulkan/SubgroupSupportPolicy.h

@@ -1,63 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/DirectVulkan/SubgroupSupportPolicy.h
-// Copyright (c) 2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-
-#pragma once
-
-#include <Config.h>
-#include <Includes.h>
-
-namespace MobileGL::MG_Backend::DirectVulkan {
-    // The single decision point for how DirectVulkan implements GL_KHR_shader_subgroup,
-    // shared by capability advertisement (BackendObject) and module lowering
-    // (VulkanRenderer / ProgramFactory) so the two can never disagree.
-    //
-    // Native subgroups are the implementation whenever the device has them, whatever
-    // their width - subgroup operations execute on the hardware paths they were made
-    // for. Module-level repairs keep the GL contract intact around them:
-    //   - FixIterationRPSubgroupScratchPass patches the one known pack bug: iterationRP's
-    //     prefixSumCache[32], under-declared for sub-16-lane devices (8-lane lavapipe);
-    //   - FixIterationRPBarrierPass repairs Program 203's race between two reductions
-    //     reusing that scratch, when explicitly enabled;
-    //   - DeriveNumSubgroupsPass replaces the one builtin drivers get wrong
-    //     (gl_NumSubgroups) with the value the rest of the topology implies.
-    // The 32-lane shared-memory emulation (EmulateSubgroupsPass) is a LAST RESORT for
-    // devices with no subgroup support at all, and only when the user opts in with
-    // MOBILEGL_MAGMA_EMULATE_SUBGROUP=1; it never replaces available native operations.
-
-    inline constexpr Uint32 kEmulatedSubgroupSize = 32u;
-    inline constexpr Uint32 kEmulatedSubgroupStages = GL_COMPUTE_SHADER_BIT;
-    inline constexpr Uint32 kEmulatedSubgroupFeatures =
-        GL_SUBGROUP_FEATURE_BASIC_BIT_KHR | GL_SUBGROUP_FEATURE_VOTE_BIT_KHR |
-        GL_SUBGROUP_FEATURE_ARITHMETIC_BIT_KHR | GL_SUBGROUP_FEATURE_BALLOT_BIT_KHR |
-        GL_SUBGROUP_FEATURE_SHUFFLE_BIT_KHR | GL_SUBGROUP_FEATURE_SHUFFLE_RELATIVE_BIT_KHR |
-        GL_SUBGROUP_FEATURE_CLUSTERED_BIT_KHR | GL_SUBGROUP_FEATURE_QUAD_BIT_KHR;
-
-    inline Bool ShouldEmulateSubgroups(const Bool nativeSubgroupSupported) {
-        return MG_Config::Features.MagmaEmulateSubgroup && !nativeSubgroupSupported &&
-               !MG_Config::Features.MagmaDisableSubgroup;
-    }
-
-    inline Bool ShouldFixIterationRPSubgroupScratch() {
-        // Auto is ON: the patch is fingerprint-gated to iterationRP's reduction and
-        // grows one under-declared array; every other module passes through untouched.
-        return MG_Config::Features.MagmaFixIterationRPSubgroupScratch !=
-               MG_Config::QuirkOverride::ForceOff;
-    }
-
-    inline Bool ShouldFixIterationRPBarrier() {
-        return MG_Config::Features.MagmaIterationRPFixBarrier;
-    }
-
-    inline Bool ShouldDeriveNumSubgroups() {
-        // Auto is ON: gl_NumSubgroups must agree with the gl_SubgroupID range for the GL
-        // contract to hold, and the derived ceil() value is the one the renderer can pin
-        // with REQUIRE_FULL_SUBGROUPS - the driver builtin is the value with no
-        // cross-driver guarantee (Adreno returns 1 for an 8-subgroup dispatch).
-        return MG_Config::Features.MagmaDeriveNumSubgroups != MG_Config::QuirkOverride::ForceOff;
-    }
-} // namespace MobileGL::MG_Backend::DirectVulkan

MobileGL/MG_Backend/DirectVulkan/VkIncludes.h

@@ -52,60 +52,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
     }
 } // namespace MobileGL::MG_Backend::DirectVulkan
 
-namespace MobileGL::MG_Backend::DirectVulkan {
-    // GL renders into sRGB color attachments RAW while GL_FRAMEBUFFER_SRGB is disabled
-    // (the core-profile default); Vulkan sRGB attachments always encode on write. The
-    // attachment view (and render pass format) therefore drops to the UNORM twin
-    // whenever the capability is off. Sampled views keep the sRGB format (decode on
-    // sample is unconditional in GL).
-    inline VkFormat ResolveSrgbAttachmentWriteFormat(VkFormat format, bool framebufferSrgbEnabled) {
-        if (framebufferSrgbEnabled) return format;
-        switch (format) {
-        case VK_FORMAT_R8G8B8A8_SRGB:
-            return VK_FORMAT_R8G8B8A8_UNORM;
-        case VK_FORMAT_B8G8R8A8_SRGB:
-            return VK_FORMAT_B8G8R8A8_UNORM;
-        default:
-            return format;
-        }
-    }
-} // namespace MobileGL::MG_Backend::DirectVulkan
-
-// The context line (__VA_ARGS__ = its own format string + args) must be a SEPARATE log
-// call: appending its format to the base format while its arguments precede the base
-// arguments makes every conversion read the wrong slot (a %s pulling an int crashes).
-//
-// MGLOG_F and deliberately NOT latched. VK_VERIFY is the invariant-check macro: a Vulkan call
-// MobileGL believes it has already made legal came back non-success, which is a
-// should-never-happen state, not an expected failure mode a user hits. Those fast-fail loudly
-// and keep saying so - the log-quietness rules that latch W/E cover expected failures (driver
-// capability gaps, app misuse), not broken internal invariants. MOBILEGL_ASSERT below traps in
-// a DEBUG build; MGLOG_F is what makes the same condition visible in an INFO test run, where
-// the assert is compiled out by contract.
-//
-// A soft, recoverable failure must therefore NOT be routed through VK_VERIFY. Check the
-// VkResult directly and report it with MGLOG_E_ONCE - see VkTextureManager::SyncTextureResource,
-// where a driver legitimately refuses an image the format pre-check accepted.
 #define VK_VERIFY(expr, ...)                                                                                           \
     do {                                                                                                               \
         VkResult _vk_verify_result = (expr);                                                                           \
         if (_vk_verify_result != VK_SUCCESS) {                                                                         \
-            __VA_OPT__(MGLOG_F(__VA_ARGS__);)                                                                          \
-            MGLOG_F("Vulkan error %s (%d) at %s:%d",                                                                   \
+            MGLOG_F("Vulkan error %s (%d) at %s:%d" __VA_OPT__(" - ") __VA_ARGS__,                                  \
                     MobileGL::MG_Backend::DirectVulkan::VkResultToString(_vk_verify_result),                          \
                     _vk_verify_result, __FILE__, __LINE__);                                                            \
         }                                                                                                              \
-        MOBILEGL_ASSERT(_vk_verify_result == VK_SUCCESS, "Vulkan error %s (%d) at %s:%d",                              \
-                        MobileGL::MG_Backend::DirectVulkan::VkResultToString(_vk_verify_result),                       \
-                        _vk_verify_result, __FILE__, __LINE__);                                                        \
+        MOBILEGL_ASSERT(_vk_verify_result == VK_SUCCESS, "Vulkan error %s (%d) at %s:%d" __VA_OPT__(" - ") __VA_ARGS__, MobileGL::MG_Backend::DirectVulkan::VkResultToString(_vk_verify_result), _vk_verify_result, __FILE__, __LINE__);  \
     } while (0)
 
 #define XXHASH_VERIFY(expr, ...)                                                                                       \
     do {                                                                                                               \
         XXH_errorcode _xxh_verify_result = (expr);                                                                     \
-        if (_xxh_verify_result != XXH_OK) {                                                                            \
-            __VA_OPT__(MGLOG_F(__VA_ARGS__);)                                                                          \
-        }                                                                                                              \
-        MOBILEGL_ASSERT(_xxh_verify_result == XXH_OK, "XXHash error %d at %s:%d", _xxh_verify_result, __FILE__,        \
-                        __LINE__);                                                                                     \
+        MOBILEGL_ASSERT(_xxh_verify_result == XXH_OK, "XXHash error %d at %s:%d" __VA_OPT__(" - ") __VA_ARGS__, _xxh_verify_result, __FILE__, __LINE__);  \
     } while (0)

MobileGL/MG_Backend/Init.cpp

@@ -11,28 +11,6 @@
 #include <MG_Util/BackendLoaders/OpenGL/Loader.h>
 #include <MG_Util/Converters/MGToStr/GLExtensionConverter.h>
 
-#if MOBILEGL_BUILD_DISAGGREGATED
-#include <MG_Pipe/MGPipe.h>
-#include <MG_Pipe/PipeApply.h>
-#include <MG_Remote/Client/ClientSession.h>
-#include <MG_Remote/FatalFunnel.h> // InstallPipeSessionFailHook, installed at step 0 below
-#include <MG_Remote/Server/ServerLoop.h>
-#include <MG_Remote/Server/ServerSession.h>
-#endif
-
-#if MOBILEGL_BUILD_DISAGGREGATED
-// [p5/v1-joint PREVIEW EDIT - the merge-time form of v1's hook, c1-v1 8.2's exact order.] The
-// weak CreateRemoteBackendObject placeholder v1 shipped for a c1-less tree is DELETED at the
-// merge: the integration test links the STATIC MobileGL_s archive, and an archive member is
-// only pulled to satisfy an UNDEFINED reference - the weak definition in ServerLoop.cpp.o
-// already satisfied it, so BackendObject_Remote.cpp.o was never linked at all and the joint
-// build aborted in the placeholder (~/w7/p5-v1-joint-preflight.log). Direct construction
-// needs no factory and no weak symbol.
-#include <MG_Remote/Client/BackendObject_Remote.h>
-#endif
-
-#include "ServerRole.h"
-
 namespace MobileGL::MG_Backend {
     void LogBackendInfo() {
         if (!pActiveBackendObject) {
@@ -67,372 +45,9 @@ namespace MobileGL::MG_Backend {
         return true;
     }
 
-#if MOBILEGL_BUILD_DISAGGREGATED
-    namespace {
-        // WHICH MGPipe SUBSYSTEMS THIS SERVER HAS A CONSUMER FOR - CallMask bits 32..47 (R-8 /
-        // C-4). It is stated from what the server's own backend IS, and NOT derived from
-        // MGPipeGetResourceOps(): that is a PROCESS-WIDE global, so under inproc a derivation
-        // would answer with whatever the client half of the same process registered and under
-        // spawn it would collapse to P2's 0x7f. Either way CapsMirror::ServerConsumes would
-        // then answer a client-side liveness gate with a guess, the client would stop emitting
-        // whole record families, clear its dirty flags on acceptance anyway, and the lane would
-        // go green with the uploads lost - ID-39's 66 lost uploads, reflected (ServerSession.h).
-        //
-        // DirectGLES consumes all thirteen migrated families (P2's 0..6, P3a's 7..8, P4a's
-        // 9..12): it registers the resource op table in Initialize()
-        // (BackendObject_DirectGLES.cpp:849) and reads every other family out of gPipeInputs.
-        // DirectVulkan registers NO resource ops - MGPipeSetResourceOps has exactly one caller
-        // in the whole tree and it is Managers.cpp:2594 - so bit 7 is CLEAR for it, which is
-        // the same fact ObjectSubsystemControlScenario already pins from the client side.
-        // P5e (MG_Remote/CONTRACT-P5E.md §6.2). THE ONE CONSTANT THE WHOLE PHASE HANGS ON.
-        //
-        // kCapRunAheadApply says "this server applies an unbarriered record without reading
-        // client memory". That is only true once EVERY per-draw family reads records instead
-        // of the frontend - vi, sb, pg, tx2 and fb all land before it is - so the caps arm
-        // below is gated on this constant, which the P5e INTEGRATION COMMIT flips to true
-        // after the last of them. Until then every P5e package lands with the wait rule, the
-        // static WaitClass column and the barriered predicate compiled and INERT: the client
-        // never latches RunAheadArmed, so it runs today's lockstep path byte for byte.
-        //
-        // It is a constant and not a knob on purpose. An operator cannot turn a half-migrated
-        // server into a run-ahead one, because the failure mode is not a slow frame - it is
-        // the apply thread reading client memory that has already moved, which renders wrong
-        // rather than aborting.
-        constexpr Bool kMGPipeP5eRunAheadReady = true;
-        constexpr Bool kMGPipeMagmaRunAheadReady = true;
-
-        // The Magma transport now owns buffer stores and consumes their vertex,
-        // index and shader binding records. Both backends publish the resource
-        // family only alongside a real op table (checked below). This does not
-        // itself establish run-ahead readiness: that has its separate gate below.
-        Uint64 ConsumedSubsystemsFor(BackendType type) {
-            switch (type) {
-            case BackendType::DirectGLES: return MG_Pipe::kMGPipeSubsystemsMigratedAtP5e;
-            case BackendType::DirectVulkan:
-                return MG_Pipe::kMGPipeSubsystemsMigratedAtP4a | MG_Pipe::kMGPipeSubsystemBufferBindings;
-            default: return 0;
-            }
-        }
-
-        // THE CROSS-CHECK THAT MAKES A WRONG ANSWER LOUD. Claiming bit 7 while no resource op
-        // table is registered is the exact failure the mask exists to prevent, one level down:
-        // the client would keep emitting the resource family and the server would drop every
-        // record of it. The check runs AFTER Initialize(), which is where DirectGLES registers
-        // the table, so it can see the real answer rather than a promise.
-        void AssertConsumerMaskIsHonest(Uint64 mask) {
-            const Bool claimsResources = (mask & MG_Pipe::kMGPipeSubsystemResources) != 0;
-            const Bool hasResourceOps = MG_Pipe::MGPipeGetResourceOps() != nullptr;
-            if (claimsResources && !hasResourceOps) {
-                MGLOG_F("MGPipe: Fatal{ConsumerMaskLie, \"kMGPipeSubsystemResources\"} - the "
-                        "server published a consumer bit for the resource family while "
-                        "MGPipeGetResourceOps() is null. The client's R-8 liveness gate would "
-                        "keep emitting resource_create / resource_subdata records that this "
-                        "server drops on the floor, and the client clears its dirty flags on "
-                        "acceptance anyway (ID-39). A mask is a statement about this backend, "
-                        "not a hope");
-                std::abort();
-            }
-            if (!claimsResources && hasResourceOps) {
-                // The safe direction: the legacy pull path keeps running. Said out loud anyway,
-                // because it silently costs the whole P3a family its migration.
-                MGLOG_W("MG_Remote server: a resource op table is registered but the consumer "
-                        "mask withholds kMGPipeSubsystemResources; the buffer family will fall "
-                        "back to the legacy path for this session");
-            }
-        }
-
-        // The resource op table the SERVER's backend registered at step 1 (BackendObject_DirectGLES::
-        // Initialize -> RegisterBufferBackendOps), as step 2 saw it. Step 5 compares against it
-        // (review v2 N-8): a client object that registered a table of its own would have made
-        // AssertConsumerMaskIsHonest's "is a table registered" answer TRUE, so re-asking that
-        // question could never notice the swap - only the pointer can.
-        const MG_Pipe::MGPipeResourceOps* g_resourceOpsAtStep2 = nullptr;
-
-        // The single hook (ARCHITECTURE.md:29). Returns false when the split could not be
-        // brought up, and the caller then REFUSES TO CONTINUE rather than falling back to the
-        // switch below - a fallback here is "the split lane ran monolith and went green".
-        // Steps 1 and 2 of the split bring-up: the server role's private backend
-        // object and the two CallMask halves. EXTRACTED so the spawn server
-        // process runs the SAME code the inproc server role runs - a second copy
-        // is how the two roles end up disagreeing about a capability bit that
-        // only one of them ever computes. ServerMain calls this and then does
-        // its own Accept; InitSplitRoles calls it and then starts the client.
-        Bool InitServerRoleCommon() {
-            using namespace MobileGL::MG_Remote;
-
-            // 0. the Magma wire funnels' route to Session::Fail (P7 wave 0). FIRST, before
-            //    CreateBackend can reach a wire arm: a hook installed after the first death it
-            //    was meant to catch is a hook that does nothing on the only run that mattered.
-            //    Here rather than in ServerMain because BOTH server roles pass through this
-            //    function - the inproc role and the spawn/TCP session child - and a per-transport
-            //    install is how one of the two ends up without it.
-            InstallPipeSessionFailHook();
-
-            // 1. the SERVER role's private backend object, on the app thread, with no GL and no
-            //    EGL. The context is created and made current later, on mgl-srv-apply, when the
-            //    client's first eglMakeCurrent crosses as a blocking control request.
-            Server::ServerLoop& loop = Server::ServerLoopInstance();
-            const MobileGLResult created = loop.CreateBackend(MG_Config::ActiveBackendType);
-            if (created != MOBILEGL_OK) return false;
-
-            // 2. the two CallMask halves. NEITHER HAS A DEFAULT and CallMask() is a named Fatal
-            //    on an unset one (s1's BLOCKER fix), so this is the "somebody" that block names.
-            Server::ServerSession& session = Server::ServerSessionInstance();
-            const Uint64 consumed = ConsumedSubsystemsFor(MG_Config::ActiveBackendType);
-            AssertConsumerMaskIsHonest(consumed);
-            g_resourceOpsAtStep2 = MG_Pipe::MGPipeGetResourceOps();
-            session.SetConsumedSubsystems(consumed);
-            // ZERO IS THE EXPLICIT ANSWER FOR P5, not an omission (ServerSession.h's block):
-            // every optional capability bit belongs to the package that owns its question, and
-            // withholding one leaves the legacy path running, which is the safe direction.
-            // kCapNeedsHostIndexBytes and kCapNeedsHostUboBytes must be 0 for the whole of P5
-            // by ruling - they are the only two things that ask for an MGHostSpan, and 0 is
-            // what keeps every one of them out of the first IPC frame (contract table 0).
-            //
-            // P5b t2 (CONTRACT-P5B.md §6.5) PUBLISHES THE ONE BIT P5b ADDS, and this is the
-            // only place that can: the question kCapBackendOwnsXfbCapture answers is "does the
-            // SERVER's backend own the transform-feedback capture", and the server's table is
-            // visible here and nowhere on the client. It is read straight off the table
-            // ServerLoop::CreateBackend just built - Espryt registers XfbImpl::EndTransformFeedback
-            // (BackendObject_DirectGLES.cpp:1458) and Magma registers no XFB slot at all - so the
-            // bit is a statement about THIS backend rather than about a build option, which is
-            // what makes it survive a backend switch. The client reads it through
-            // MGL_BACKEND_SLOT_CAP at GL_Drawing.cpp's FixupGsStripCaptureOrder.
-            Uint64 capBits = 0;
-            if (const MG_Backend::BackendObject* serverBackend = loop.Backend();
-                serverBackend != nullptr &&
-                serverBackend->GetBackendFunctions().GL.EndTransformFeedback != nullptr) {
-                capBits |= MG_Pipe::kCapBackendOwnsXfbCapture;
-            }
-            if (const auto* backend = loop.Backend()) {
-                const auto& gl = backend->GetBackendFunctions().GL;
-                // The query owner publishes only complete native query/reply paths.
-                // Timer hardware support is refreshed when caps are published after
-                // make-current; no CPU primitive-accounting preference is advertised.
-                if (gl.IsQueryResultAvailable && gl.GetQueryResult64 && gl.DeleteBackendQuery &&
-                    gl.FenceSync && gl.ClientWaitSync && gl.DeleteSync) {
-                    if (gl.BeginXfbPrimitivesQuery && gl.EndXfbPrimitivesQuery)
-                        capBits |= MG_Pipe::kCapXfbPrimitivesQuery;
-                    if (gl.BeginOcclusionQuery && gl.EndOcclusionQuery)
-                        capBits |= MG_Pipe::kCapOcclusionQuery;
-                    if (gl.IsTimerQuerySupported && gl.BeginTimeElapsedQuery &&
-                        gl.EndTimeElapsedQuery && gl.QueryCounterTimestamp)
-                        capBits |= MG_Pipe::kCapTimerQuery;
-                }
-            }
-            // P7 wave 2 package C, OQ-10 (CONTRACT-P7 §5.4): kCapResidentSubData, PUBLISHED
-            // OFF THE SERVER'S OWN WIRE RESOURCE TABLE AND NOTHING ELSE.
-            //
-            // The question the bit answers is the one BufferObject::LandBytesIntoResidentStore
-            // asks before it chooses between emitting `buffer_subdata_resident` (opcode 49) and
-            // falling back to the ordered in-place host memcpy: "does the side that will APPLY
-            // this record implement the resident arm at all?" Under a transport the client has
-            // no op table to probe - MGPipeResourceOpsHaveSubDataResident says so in as many
-            // words (MG_Impl/Pipe/PipeFill.cpp) and reads this bit instead - and until now
-            // nothing ever set it, so the answer was permanently "no" and BOTH backends fell
-            // back to the memcpy while both of them in fact register a SubDataResident arm
-            // (DirectGLES Managers.cpp's g_glesResourceOps, Magma VkBufferManager.cpp's
-            // g_vulkanWireResourceOps). Magma's implementation was dead code on the wire.
-            //
-            // BY THE TABLE, NEVER BY THE BACKEND ENUM, and that is ID-39's lesson rather than a
-            // style preference: a mask is a statement about THIS backend's registered table, so
-            // a bit derived from `ActiveBackendType == ...` would keep claiming the capability
-            // for a build, a flavour or a future backend whose table does not carry the arm -
-            // which is exactly how 66 uploads were lost to a consumer bit that nobody could
-            // have honoured. `g_resourceOpsAtStep2` is the pointer this function just pinned,
-            // and step 5 already refuses a run where that pointer was swapped underneath us, so
-            // reading the arm off it means the published bit and the table that has to answer
-            // for it cannot come apart.
-            if (g_resourceOpsAtStep2 != nullptr && g_resourceOpsAtStep2->SubDataResident != nullptr) {
-                capBits |= MG_Pipe::kCapResidentSubData;
-            }
-            // Each backend has an independent implementation-readiness gate.
-            // The runtime RunAhead knob can decline the feature, never create it.
-            const Bool runAheadReady = MG_Config::ActiveBackendType == BackendType::DirectVulkan
-                ? kMGPipeMagmaRunAheadReady : kMGPipeP5eRunAheadReady;
-            capBits |= MG_Pipe::MGPipeRunAheadCapBitsFor(MG_Config::ActiveBackendType, runAheadReady);
-            session.SetCapabilityBits(capBits);
-            session.SetBackend(loop.Backend());
-            return true;
-        }
-
-        // The single hook (ARCHITECTURE.md:29) for the INPROC shape: both roles in
-        // this process. The spawn shape runs InitServerRoleCommon in the child and
-        // the client half here.
-        Bool InitSplitRoles() {
-            using namespace MobileGL::MG_Remote;
-
-            // SPAWN: THE SERVER ROLE IS NOT IN THIS PROCESS. Steps 1 and 2 -
-            // the backend and the two CallMask halves - happen in the server,
-            // which ran InitServerRoleForSpawn before it accepted us. Running
-            // them here as well would build a second BackendObject in the one
-            // process that must not have one, and would publish a capability
-            // mask computed from the WRONG backend's function table.
-            if (MG_Config::Transport == MG_Config::TransportMode::Spawn) {
-                const MobileGLResult started = Client::ClientSessionInstance().StartSpawned();
-                if (started != MOBILEGL_OK) {
-                    MGLOG_E("MG_Remote: the spawn session failed to start (rc=%d); MobileGL will "
-                            "NOT fall back to monolith - a lane named split that ran monolith is "
-                            "the one failure this phase is built to make impossible",
-                            static_cast<int>(started));
-                    return false;
-                }
-                pActiveBackendObject = MakeUnique<MG_Remote::Client::BackendObject_Remote>();
-                return true;
-            }
-
-            if (!InitServerRoleCommon()) {
-                return false;
-            }
-
-            // 3. the handshake, the four segments, and - at its end - the apply thread.
-            const MobileGLResult started =
-                Client::ClientSessionInstance().Start(MG_Config::Transport, MG_Config::TransportEndpoint);
-            if (started != MOBILEGL_OK) {
-                MGLOG_E("MG_Remote: the split session failed to start (rc=%d); MobileGL will not "
-                        "fall back to monolith - a lane named split that ran monolith is the one "
-                        "failure this phase is built to make impossible",
-                        static_cast<int>(started));
-                return false;
-            }
-
-            // 4. and only now the CLIENT's backend object in the one global that holds it.
-            //    Table 3: pActiveBackendObject holds BackendObject_Remote and the server's
-            //    BackendObject_DirectGLES stays private to ServerLoop.
-            pActiveBackendObject = MakeUnique<MG_Remote::Client::BackendObject_Remote>();
-            return true;
-        }
-
-        // F1 (P7 wave 2). THE WHOLE SPLIT ARM OF Init(), AS ONE BODY, so it can run from
-        // either of the two places that may reach it - MobileGL::Initialize's early hook,
-        // before MG_State::Init(), and Init() itself for a direct caller such as a unit
-        // fixture - without a second copy. Two copies of a bring-up order is how the two
-        // orders come to differ on the day one of them is wrong.
-        Bool g_splitBackendBroughtUp = false;
-
-        void InitSplitBackend() {
-            g_splitBackendBroughtUp = true;
-            if (!InitSplitRoles()) {
-                // NOT a fallback to the switch. pActiveBackendObject stays null and the next GL
-                // call fails loudly, which is the only honest outcome: the operator asked for a
-                // transport this process could not bring up.
-                pActiveBackendObject = nullptr;
-                return;
-            }
-            Bool remoteResult = InitSpecificBackendLibs();
-            if (!remoteResult) {
-                MGLOG_W("Failed to initialize MobileGL backend libraries for the remote object");
-                return;
-            }
-            // P6: BOTH CHECKS BELOW ARE STATEMENTS ABOUT THE SERVER'S PROCESS, and under
-            // spawn that is not this one. Their own wording says so - "a mask is a
-            // statement about THIS BACKEND", "the table the SERVER'S BACKEND registered at
-            // step 1" - and in a spawn client there is no backend and never was a table, so
-            // MGPipeGetResourceOps() is null by construction and the first check fires on a
-            // correct session. It did, on the first spawn retrace ever run.
-            //
-            // The checks are NOT weakened: the server runs the step-2 one itself, inside
-            // InitServerRoleForSpawn, against its own freshly registered table - which is the
-            // process where the question has an answer. What is lost under spawn is the
-            // step-5 re-run's ability to catch a table REPLACED between accept and here, and
-            // that is a question about one address space; it cannot be asked across two.
-            if (MG_Config::Transport != MG_Config::TransportMode::Spawn) {
-            // m-6, re-worded per review v2 N-8. The honesty cross-check runs a SECOND time, now
-            // that step 4's pActiveBackendObject (the client's BackendObject_Remote) exists and
-            // its Initialize() has run inside InitSpecificBackendLibs. What the re-run CAN catch
-            // is a table that was REMOVED between step 2 and here (the claim would then be a lie
-            // again). What it cannot catch - and its first comment claimed it could - is a client
-            // object that REGISTERED a table of its own: that leaves "is a table registered"
-            // true. Only the pointer tells those apart, so the table is compared against the one
-            // step 2 saw and a swap is refused by name: the applier would otherwise dispatch the
-            // server's resource records into the CLIENT object's table under its feet.
-            AssertConsumerMaskIsHonest(ConsumedSubsystemsFor(MG_Config::ActiveBackendType));
-            if (MG_Pipe::MGPipeGetResourceOps() != g_resourceOpsAtStep2) {
-                MGLOG_F("MGPipe: Fatal{ConsumerMaskLie, \"resource ops table replaced\"} - the "
-                        "resource op table MGPipeGetResourceOps() answers with is not the one the "
-                        "server's backend registered at step 1 (%p now, %p then). Something between "
-                        "ServerSession::Accept and the client object's Initialize() registered its "
-                        "own table, and the applier would dispatch every resource record into it. A "
-                        "mask is a statement about the server's backend, and so is the table",
-                        static_cast<const void*>(MG_Pipe::MGPipeGetResourceOps()),
-                        static_cast<const void*>(g_resourceOpsAtStep2));
-                std::abort();
-            }
-            }
-            LogBackendInfo();
-        }
-    } // namespace
-#endif
-
-#if MOBILEGL_BUILD_DISAGGREGATED
-    // F1 (P7 wave 2). See BackendObjects.h for why this exists and MobileGL/Init.cpp for the
-    // defect the order closes.
-    Bool InitSplitRolesBeforeState() {
-        if (MG_Config::Transport == MG_Config::TransportMode::Monolith) return false;
-        InitSplitBackend();
-        return true;
-    }
-#endif
-
-#if MOBILEGL_BUILD_DISAGGREGATED
-    void ShutdownSplitRoles() {
-        g_splitBackendBroughtUp = false;
-        if (MG_Config::Transport == MG_Config::TransportMode::Monolith) return;
-        // ClientSession::Stop IS table 3's whole order and it is idempotent: publish and wait
-        // for the server to drain (bounded - a lost record must be a red lane, not a hung
-        // exit), Doorbell::Kill through the transport's Shutdown, ServerLoop::Stop's bounded
-        // join - which also destroys the server's private BackendObject ON the apply thread
-        // while it still owns the context - the transport, and only THEN anything an emitter
-        // owns. A var-tail still named by an unapplied record is a use-after-free the join is
-        // what prevents, which is why the order is not a preference.
-        MG_Remote::Client::ClientSessionInstance().Stop();
-        // M-6: ClientSession::Stop's !m_started arm (a Start that FAILED after
-        // ServerSession::Accept - a refused Accept, an invalid cmd/reply ring) tears down only
-        // the client half and never stops the apply thread or drops the server's private backend,
-        // which ServerLoop::CreateBackend already built and which holds the process-wide
-        // g_resourceOps. So call ServerLoop::Stop() here unconditionally. It is idempotent: on the
-        // started path ClientSession::Stop already joined the thread, so this hits Stop's
-        // !joinable arm, which resets a backend that never ran a thread and is otherwise a no-op.
-        // Without this an early Start failure leaves BackendObject_DirectGLES permanently alive
-        // and every later split bring-up in the process fails at CreateBackend's m_backend!=null
-        // guard.
-        MG_Remote::Server::ServerLoopInstance().Stop();
-    }
-#endif
-
-#if MOBILEGL_BUILD_DISAGGREGATED
-    // The spawn server's entry into the SAME bring-up the inproc server role
-    // runs (ServerRole.h). A thin forwarder on purpose: the body stays in the
-    // anonymous namespace beside InitSplitRoles so the two cannot drift.
-    //
-    // THE WHOLE FUNCTION IS INSIDE THE GUARD, not just its body. A version with
-    // the guard inside still DEFINES the symbol in a pull build, and G1 caught
-    // it: 2 symbols added, 1 removed, .text +16 bytes. The pull build's identity
-    // is byte-for-byte, and "it returns false there" is not the same as "it is
-    // not there".
-    Bool InitServerRoleForSpawn() { return InitServerRoleCommon(); }
-#endif
-
     void Init() {
         MGLOG_D("Initializing MobileGL Backend...");
 
-#if MOBILEGL_BUILD_DISAGGREGATED
-        // THE SINGLE HOOK. In a build without MOBILEGL_BUILD_DISAGGREGATED, MG_Config::Transport
-        // is a `constexpr Monolith` (Config.h) and this whole statement is discarded, so the
-        // pull build gains no symbol, no branch and no byte - which is what G1 measures.
-        if (MG_Config::Transport != MG_Config::TransportMode::Monolith) {
-            // F1: MobileGL::Initialize now brings the split roles up BEFORE MG_State::Init(),
-            // through InitSplitRolesBeforeState() below, so by the time Init() is reached on
-            // that path the work is done. A DIRECT caller - a unit fixture that calls
-            // MG_Backend::Init() itself - still gets the whole bring-up here. The flag rather
-            // than `pActiveBackendObject == nullptr`, because a bring-up that FAILED leaves
-            // that pointer null too and retrying it would refuse at CreateBackend's
-            // m_backend != nullptr guard with a second, misleading line.
-            if (!g_splitBackendBroughtUp) InitSplitBackend();
-            return;
-        }
-#endif
-
         switch (MG_Config::ActiveBackendType) {
         case BackendType::DirectGLES:
             pActiveBackendObject = MakeUnique<DirectGLES::BackendObject_DirectGLES>();

MobileGL/MG_Backend/MGPipe/PipeInputs.cpp

@@ -1,715 +0,0 @@
-// MobileGL - MobileGL/MG_Backend/MGPipe/PipeInputs.cpp
-// Copyright (c) 2025-2026 MobileGL-Dev
-// Licensed under the GNU Lesser General Public License v3.0:
-//   https://www.gnu.org/licenses/gpl-3.0.txt
-//   https://www.gnu.org/licenses/lgpl-3.0.txt
-// SPDX-License-Identifier: LGPL-3.0-only
-// End of Source File Header
-
-// The backend-side half of the PipeInputs block: the poison Fatal with its verb name, the
-// name lookups the runtime knobs need, and - in a verify build - the per-field equality,
-// the entry comparator and the corruption injector. Compiled only under MOBILEGL_PIPE_PUSH
-// (CMakeLists.txt appends it to SOURCE_FILES there), so the pull build never sees it. Spells
-// no MG_State global: everything that reads the live context lives in MG_Impl/Pipe/PipeFill.cpp.
-#include <MG_Backend/MGPipe/PipeInputs.h>
-
-#include <cstdint>
-#include <cstring>
-
-#if MOBILEGL_BUILD_DISAGGREGATED
-#include <Config.h>
-#include <MG_Util/Metrics/PipeStats.h>
-#endif
-
-namespace MobileGL::MG_Pipe {
-    const char* MGPipeVerbName(MGPipeVerb verb) {
-        const auto index = static_cast<SizeT>(verb);
-        return index < kMGPipeVerbCount ? kMGPipeVerbNames[index] : "<none>";
-    }
-
-    [[noreturn]] void MGPipeInputPoisonFatalForVerb(MGPipeInputField field, MGPipeVerb verb) {
-        MGPipeInputPoisonFatal(field, MGPipeVerbName(verb));
-    }
-
-    Optional<MGPipeInputField> MGPipeFindInputField(const char* name) {
-        if (name == nullptr) return std::nullopt;
-        for (SizeT i = 0; i < kMGPipeInputFieldCount; ++i) {
-            if (std::strcmp(kMGPipeInputFieldNames[i], name) == 0) return static_cast<MGPipeInputField>(i);
-        }
-        return std::nullopt;
-    }
-
-    Optional<MGPipeVerb> MGPipeFindVerb(const char* name) {
-        if (name == nullptr) return std::nullopt;
-        for (SizeT i = 0; i < kMGPipeVerbCount; ++i) {
-            if (std::strcmp(kMGPipeVerbNames[i], name) == 0) return static_cast<MGPipeVerb>(i);
-        }
-        return std::nullopt;
-    }
-
-#if MOBILEGL_BUILD_DISAGGREGATED
-    // ================================================================================
-    // P5: the server's verb stamp, the residual-pull counter, and the four-way read verdict
-    // ================================================================================
-    namespace {
-        Uint64 g_residualPulls = 0;
-
-#if MOBILEGL_PIPE_VERIFY
-        // ---- P7 wave 3 (V1): negative control B's SERVER half ----------------------------
-        //
-        // MOBILEGL_PIPE_POISON_OMIT withholds the STAMP of one (verb, field) pair, and until a
-        // verify build first ran on the split arm it was only ever read by the client's filler
-        // (MG_Impl/Pipe/PipeFill.cpp's ParsePoisonOmissionKnob). On the split arm that is not
-        // where the stamp the backend reads comes from: the stamp below re-stamps every field
-        // the verb's class can answer out of applied records, so it restamped the very field
-        // the client had withheld and the control went GREEN - measured, both backends, the
-        // child's glGenerateMipmap returned and the process exited 0 with
-        // GenerateMipmap:GetActiveTextureUnit omitted. The knob means "this verb's stamp of this
-        // field was never written", and under a transport the stamp that answers the backend is
-        // this one, so this one honours it too.
-        //
-        // PARSED HERE, NOT SHARED WITH THE CLIENT'S PARSER, because this file is in the server
-        // library and MG_Impl is not. A malformed value is the client's Fatal{PipeVerifyBadKnob}
-        // (it parses first, at the first fill of the process); this side simply does not arm.
-        // VERIFY BUILDS ONLY: the knob belongs to the verify harness, and a push build's stamp
-        // stays the branch-free fill the P5d profile asked for.
-        struct ServerPoisonOmission {
-            Bool Parsed = false;
-            String Value;
-            Bool Armed = false;
-            MGPipeVerb Verb = MGPipeVerb::kVerbCount;
-            MGPipeInputField Field = MGPipeInputField::kFieldCount;
-        };
-        ServerPoisonOmission g_serverOmission;
-
-        const ServerPoisonOmission& ServerOmission() {
-            const String& knob = MG_Config::Features.PipePoisonOmit;
-            if (g_serverOmission.Parsed && knob.size() == g_serverOmission.Value.size() &&
-                (knob.empty() || knob == g_serverOmission.Value)) {
-                return g_serverOmission;
-            }
-            g_serverOmission = ServerPoisonOmission{};
-            g_serverOmission.Parsed = true;
-            g_serverOmission.Value = knob;
-            const auto colon = knob.find(':');
-            if (colon == String::npos || colon == 0 || colon + 1 >= knob.size()) return g_serverOmission;
-            const auto verb = MGPipeFindVerb(knob.substr(0, colon).c_str());
-            const auto field = MGPipeFindInputField(knob.substr(colon + 1).c_str());
-            if (!verb || !field) return g_serverOmission;
-            g_serverOmission.Armed = true;
-            g_serverOmission.Verb = *verb;
-            g_serverOmission.Field = *field;
-            return g_serverOmission;
-        }
-
-        Bool ServerOmitsStamp(MGPipeVerb verb, MGPipeInputField field) {
-            const ServerPoisonOmission& omission = ServerOmission();
-            return omission.Armed && omission.Verb == verb && omission.Field == field;
-        }
-#endif // MOBILEGL_PIPE_VERIFY
-
-        // The strict arm of R-7.3. Same first line as the ordinary poison Fatal, so every
-        // existing filter on Fatal{UnmigratedPipeInput still matches, plus the class and the
-        // phase that retires it - a strict abort that did not say which phase owes the answer
-        // would leave the reader exactly where the gate found them.
-        // P5e (ra): `why` is the second half of the marker, because the lane's allowlist step
-        // reads this line and the two reasons mean different things to it. "MOBILEGL_IPC_
-        // STRICT_ERRORS=1" is the operator asking for a real, ordered value to be loud;
-        // "UNBARRIERED" is the value not existing (§3.3). The `<field>@<verb>` prefix and the
-        // Fatal{UnmigratedPipeInput tag are unchanged, so every filter written since P5c still
-        // matches.
-        [[noreturn]] void StrictBarrierPullFatal(MGPipeInputField field, MGPipeVerb verb,
-                                                 const char* why) {
-            const SizeT index = static_cast<SizeT>(field);
-            MGLOG_F("MGPipe: Fatal{UnmigratedPipeInput, \"%s@%s\"} [BARRIER-PULLED, %s, "
-                    "retires in %s]",
-                    kMGPipeInputFieldNames[index], MGPipeVerbName(verb), why,
-                    kMGPipeFieldRetiringPhase[index]);
-            std::abort();
-        }
-
-        // P5e (gl), ID-117: THE ADMITTED MARKER, AND WHY IT IS ONLY THE TAG THAT CHANGED.
-        //
-        // `<field>@<verb>` and the `[BARRIER-PULLED, …, retires in <phase>]` tail are IDENTICAL
-        // to the Fatal above; the leading tag is `Admitted{` instead of `Fatal{`. Every filter
-        // written since P5c matches `Fatal{UnmigratedPipeInput`, so all of them keep meaning
-        // exactly "red" and none of them has to learn a new grammar to keep meaning it. A reader
-        // grepping for the pair still finds it, and the lane can ratchet on both sets with one
-        // regex per tag (ID-119's two-sided ratchet).
-        //
-        // THE DEDUPE IS NOT TIDINESS. An 852-draw Minecraft frame reaches an admitted readback
-        // row once per draw; without this, one frame writes 852 identical lines, the log file is
-        // the size of the run and the marker census cannot be read at all. So it is once per
-        // (field, verb) per process, which is the granularity the allowlist is written in.
-        //
-        // A PLAIN ARRAY, NOT AN ATOMIC, and that is the file's existing rule rather than a
-        // shortcut: CountBarrierPull is reachable only after the server stamped a verb boundary,
-        // which happens on the apply thread inside PipeApplier::ApplyOne, and g_residualPulls
-        // beside it is a plain Uint64 for the same reason. A racing writer here would at worst
-        // log a duplicate line, never lose one.
-        void AdmittedBarrierPullOnce(MGPipeInputField field, MGPipeVerb verb, Bool escalated) {
-            const SizeT fieldIndex = static_cast<SizeT>(field);
-            const SizeT verbIndex = static_cast<SizeT>(verb);
-            if (fieldIndex >= kMGPipeInputFieldCount || verbIndex >= kMGPipeVerbCount) return;
-            static Uint64 seen[(kMGPipeVerbCount * kMGPipeInputFieldCount + 63) / 64] = {};
-            const SizeT bit = verbIndex * kMGPipeInputFieldCount + fieldIndex;
-            const Uint64 mask = Uint64{1} << (bit % 64);
-            if ((seen[bit / 64] & mask) != 0) return;
-            seen[bit / 64] |= mask;
-            // P5e (gl), ID-128: WHICH DISJUNCT ADMITTED IT, in the slot the grammar already has
-            // for the reason. `ADMITTED` means the generated table said so, and the lane can
-            // check that against `--print-admitted`. `ADMITTED-ESCALATED` means the table did
-            // NOT and the record was barriered by an escalation the table cannot see, which is a
-            // RUNTIME fact about that record's payload - so the lane must not look for it in a
-            // static list. Saying which is what keeps the lane's comparison exact instead of
-            // widening the list with every pair that could ever escalate.
-            MGLOG_W("MGPipe: Admitted{UnmigratedPipeInput, \"%s@%s\"} [BARRIER-PULLED, %s, "
-                    "retires in %s]",
-                    kMGPipeInputFieldNames[fieldIndex], MGPipeVerbName(verb),
-                    escalated ? "ADMITTED-ESCALATED" : "ADMITTED",
-                    kMGPipeFieldRetiringPhase[fieldIndex]);
-        }
-
-        // One place decides what a BARRIER-PULLED read does, so the field accessors and the
-        // seven sticky forwards cannot drift apart on it.
-        //
-        // ---- P5e (ra), CONTRACT-P5E §3.3: THE DETECTOR IS UNCONDITIONAL UNDER AN UNBARRIERED
-        // RECORD, AND THAT IS WHAT MAKES THE STRICT LANE A GATE -------------------------------
-        //
-        // The knob exists because under LOCKSTEP a pulled row is a real, ordered, fresh value:
-        // the client filled it and then parked, so "count it and carry on" is an honest
-        // measurement of remaining debt and MOBILEGL_IPC_STRICT_ERRORS is the operator asking
-        // for the debt to be loud instead. None of that survives run-ahead. With the client
-        // running ahead of this apply, the row was either never filled for this verb (§3.1
-        // skips the fill) or is being overwritten by a verb two frames later - so the value is
-        // torn or stale BY CONSTRUCTION and there is nothing for a counter to count. A
-        // "count it" arm here would be a wrong picture with a number beside it.
-        //
-        // P5e (gl), ID-119: THE OLD PIN HERE - "rsp is 0 on unbarriered records" - WAS VACUOUS
-        // AND HAS BEEN WITHDRAWN. The unbarriered arm below is [[noreturn]] and runs BEFORE
-        // ++g_residualPulls, so an unbarriered pull can never reach the counter whatever this
-        // function is written to do; the sentence was true of every possible implementation and
-        // therefore checked nothing. What rsp actually counts is BARRIERED pulls, and under the
-        // strict knob it counts exactly the ADMITTED ones, because every other barriered pull
-        // aborts two lines down. That is the form CONTRACT-P5E §7 now states and the lane checks.
-        //
-        // ---- P5e (gl), ID-117: AN ADMITTED PULL IS LOUD, NOT FATAL ---------------------------
-        //
-        // Before this, strict aborted on EVERY barrier-pulled read, admitted or not - which made
-        // the CI's allowlist comparison unreachable code (the run's rc != 0 exits first) and made
-        // "hard green" impossible with the knob as written. So there is a third state, and the
-        // two existing ones are untouched:
-        //
-        //   unbarriered            -> Fatal, no knob. The value is torn by construction.
-        //   barriered, unadmitted  -> Fatal under strict. A debt no phase has taken.
-        //   barriered, admitted    -> ONE MGLOG_W per (field, verb), and the entry completes.
-        //
-        // "Admitted" has three disjuncts and the third is a runtime one (ID-128): the generated
-        // table answers the first two, and the record's own escalation flag answers the third.
-        //
-        // An admitted pull is a debt this phase deliberately leaves standing: the field's row is
-        // BARRIER_PULLED, the verb's op is statically barriered so the client really is parked
-        // behind the record, and the field is inside the verb's own may-read mask - so the value
-        // is real, ordered and fresh, exactly ruling 4's "barriered records keep P5C semantics".
-        // MGPipeBarrierPullAdmitted is generated from those three tables (ID-116); there is no
-        // list here to drift.
-        void CountBarrierPull(MGPipeInputField field, MGPipeVerb verb) {
-            // P5f (f1), P5F-WIRE-COMPLETENESS.md §4: UNDER THE DUAL-BLOCK REHEARSAL EVERY
-            // BARRIER-PULLED READ IS A NAMED FATAL, unconditionally - ahead of the barriered
-            // question, ahead of the strict knob, ahead of the counter. The server block has no
-            // residual fill to answer from, so the value the read would return is not "torn"
-            // or "stale" but ABSENT: the field's stamp was withdrawn by the server's own verb
-            // boundary and nothing on this side of the role split ever writes it. Letting the
-            // read proceed would hand the backend default storage - or, for the O-class rows
-            // with no null check, an empty SharedPtr to dereference - which is an UNNAMED
-            // crash exactly where the rehearsal exists to produce a named one. The red is the
-            // census (Harness/dualblock-expected-fatals.txt), so the marker keeps the strict
-            // grammar with the knob's own name as the reason.
-            // D10: rides MGPipeBlocksAreDistinct() - under spawn the two blocks are distinct
-            // whatever the rehearsal knob says, and a barrier pull across a real process
-            // boundary is exactly the thing this Fatal exists to name.
-            if (MGPipeBlocksAreDistinct()) {
-                StrictBarrierPullFatal(field, verb, "MOBILEGL_IPC_ROLE_SPLIT_STATE=1");
-            }
-            if (!MGPipeApplierCurrentRecordIsBarriered()) {
-                StrictBarrierPullFatal(field, verb, "UNBARRIERED, the client did not fill it");
-            }
-            ++g_residualPulls;
-            if (MG_Util::PipeStats::Enabled()) {
-                MG_Util::PipeStats::AddCalls(MG_Util::PipeStats::CallClass::ResidualPulls, 1);
-            }
-            if (MG_Config::Ipc.StrictErrors) {
-                // THE THIRD DISJUNCT (P5e gl, ID-128), and it has to be asked at RUNTIME because
-                // it is a fact about this record's payload rather than about its opcode. The
-                // static table admits a pair when the verb's op waits (disjunct 1) or when the
-                // field's retiring phase is not this phase (disjunct 2); an escalated record is
-                // one the client parks behind for a reason only the payload knows - an open
-                // transform-feedback span, or a draw carrying client vertex arrays. Both are
-                // outside this phase by ruling (§5.7, ID-82), and the client-array read site
-                // aborts by its own name if it is ever applied unbarriered, so the pull is legal
-                // and P5e is not the phase that owes it.
-                const Bool statically = MGPipeBarrierPullAdmitted(field, verb);
-                const Bool escalated = MGPipeApplierCurrentRecordIsBarrieredByEscalation();
-                if (!statically && !escalated) {
-                    StrictBarrierPullFatal(field, verb, "MOBILEGL_IPC_STRICT_ERRORS=1");
-                }
-                AdmittedBarrierPullOnce(field, verb, !statically);
-            }
-        }
-
-        // The verb's OWN may-read table (FillPoints.def, kMGPipeClassFieldMask). The stamp
-        // respects it for the same reason the client's residual fill does: a field outside the
-        // verb's class is one the fill never copied, so answering it out of gPipeInputs would
-        // hand the server the PREVIOUS verb's value - the exact staleness the generation poison
-        // exists to catch, re-introduced by the very mechanism meant to instrument it.
-        Bool FieldIsInVerbClass(MGPipeInputField field, MGPipeVerb verb) {
-            const SizeT verbIndex = static_cast<SizeT>(verb);
-            if (verbIndex >= kMGPipeVerbCount) return false;
-            const MGPipeVerbClass verbClass = kMGPipeVerbClass[verbIndex];
-            return MGPipeFieldMaskHas(kMGPipeClassFieldMask[static_cast<SizeT>(verbClass)], field);
-        }
-
-        // ---- the same verdict, per verb CLASS, as a constant (P5d round 3, package C) ----
-        //
-        // THE STAMP's ANSWER IS A CONSTANT OF THE VERB CLASS AND OF NOTHING ELSE. Both halves of
-        // `answerable` below read constexpr tables only - kMGPipeFieldOwnership, kMGPipeVerbClass
-        // and kMGPipeClassFieldMask - so the 63-field loop was recomputing, at every verb on the
-        // apply thread, a table the compiler can build once. The 2026-09-17 inproc profile put
-        // MGPipeServerStampVerbBoundary at 1.1% self of the apply thread (Minecraft 26.3-rc-3,
-        // ~852 draws/frame), and every cycle taken there is a cycle the lockstep client waits for.
-        //
-        // IT IS A MASK, NOT A BOOL ARRAY, so the stamp loop's body stays a shift and a store with
-        // no branch: FilledGen[i] = serial & -bit, which is `serial` for an answerable field and
-        // the WITHDRAWAL 0 for every other. The verdict itself is unchanged, and it is still
-        // computed by the one expression argued at the stamp - it just runs at compile time.
-        constexpr MGPipeFieldMask AnswerableMaskForClass(MGPipeVerbClass verbClass) {
-            MGPipeFieldMask mask{};
-            for (SizeT i = 0; i < kMGPipeInputFieldCount; ++i) {
-                const auto field = static_cast<MGPipeInputField>(i);
-                const MGPipeFieldOwnership ownership = kMGPipeFieldOwnership[i];
-                const Bool answerable = (ownership == MGPipeFieldOwnership::kRecordSupplied ||
-                                         ownership == MGPipeFieldOwnership::kApplierDerived) &&
-                                        MGPipeFieldMaskHas(
-                                            kMGPipeClassFieldMask[static_cast<SizeT>(verbClass)], field);
-                if (answerable) mask.Words[i / 64] |= (Uint64{1} << (i % 64));
-            }
-            return mask;
-        }
-
-        struct AnswerableMaskTable {
-            MGPipeFieldMask ByClass[kMGPipeVerbClassCount];
-        };
-
-        constexpr AnswerableMaskTable MakeAnswerableMaskTable() {
-            AnswerableMaskTable table{};
-            for (SizeT i = 0; i < kMGPipeVerbClassCount; ++i) {
-                table.ByClass[i] = AnswerableMaskForClass(static_cast<MGPipeVerbClass>(i));
-            }
-            return table;
-        }
-
-        constexpr AnswerableMaskTable kAnswerableByClass = MakeAnswerableMaskTable();
-
-        // A verb id outside the table answers NOTHING, which is exactly what FieldIsInVerbClass
-        // said for it (`verbIndex >= kMGPipeVerbCount` -> false for every field) and therefore
-        // what the stamp said: all 63 withdrawn, every read the poison Fatal.
-        constexpr MGPipeFieldMask kNoFieldIsAnswerable{};
-
-        const MGPipeFieldMask& AnswerableMaskForVerb(MGPipeVerb verb) {
-            const SizeT verbIndex = static_cast<SizeT>(verb);
-            if (verbIndex >= kMGPipeVerbCount) return kNoFieldIsAnswerable;
-            return kAnswerableByClass.ByClass[static_cast<SizeT>(kMGPipeVerbClass[verbIndex])];
-        }
-    } // namespace
-
-    // The third door into the storage (see PipeInputs.h). It exists because neither of the
-    // other two can be the one that stamps: MGPipeApplyAccess deliberately does not, and
-    // MGPipeFillAccess lives in MG_Impl, the role a server does not have.
-    struct MGPipeStampAccess {
-        static MGPipeFilledState& Filled(PipeInputs& inputs) { return inputs.m_filled; }
-        static void SetVerb(PipeInputs& inputs, MGPipeVerb verb) { inputs.m_currentVerb = verb; }
-        static void SetServerStamped(PipeInputs& inputs, Bool stamped) {
-            inputs.m_serverStampedVerb = stamped;
-        }
-        // P5f (f1): the server block's identity half of the stamp door (CONTRACT-P5E §3.2).
-        // The client's SetIdentity lives in MG_Impl's MGPipeFillAccess and writes the CLIENT
-        // block now; this one is how the server block learns which served context it describes
-        // without MG_Impl being in the process at all.
-        static void SetIdentity(PipeInputs& inputs, Bool live, const void* identity) {
-            inputs.m_live = live;
-            inputs.m_contextIdentity = identity;
-        }
-    };
-
-    // ---- P5f (f1): the dual-block rehearsal's selection functions (PipeInputs.h) -----------
-    //
-    // MGPipeRoleSplitRehearsalActive is deliberately NOT latched: it is two global loads, asked once per
-    // verb on the fill side and once per verb boundary on the stamp side, and a latch is a
-    // second thing a test that flips the knob mid-process would have to know about.
-    Bool MGPipeRoleSplitRehearsalActive() {
-        return MG_Config::Ipc.RoleSplitState &&
-               MG_Config::Transport != MG_Config::TransportMode::Monolith;
-    }
-
-#if MOBILEGL_BUILD_DISAGGREGATED
-    // ---- D1c's predicates (CONTRACT-P6 3.2) -------------------------------------------------
-    namespace {
-        // Set once by ServerMain, before any GL work. A spawn server is the server for the whole
-        // life of the process; there is no thread in it that is not.
-        Bool g_serverProcessRole = false;
-        // MG_Remote's "is the calling thread inside the applier". Null until a session installs
-        // it, which is the honest answer for a process that has no applier.
-        Bool (*g_applyThreadProbe)() = nullptr;
-        Bool g_sessionLive = false;
-    } // namespace
-
-    void MGPipeSetServerProcessRole(Bool isServerProcess) { g_serverProcessRole = isServerProcess; }
-    void MGPipeSetApplyThreadProbe(Bool (*probe)()) { g_applyThreadProbe = probe; }
-    void MGPipeSetSessionLive(Bool live) { g_sessionLive = live; }
-
-    Bool MGPipeServerArm() {
-        // THE PROCESS FACT FIRST, and it short-circuits: in a spawn server every thread is a
-        // server thread, and asking the probe would be asking MG_Remote a question it answers
-        // only about the applier.
-        if (g_serverProcessRole) return true;
-        return g_applyThreadProbe != nullptr && g_applyThreadProbe();
-    }
-
-    Bool MGPipeSessionLive() { return g_sessionLive; }
-
-    Bool MGPipeBlocksAreDistinct() {
-        // TWO DIFFERENT REASONS, ONE ANSWER. The rehearsal makes two blocks in one process;
-        // spawn makes them two blocks in two ADDRESS SPACES, where no knob is involved and the
-        // distinctness is a fact about the machine. The guards that used to ask only the first
-        // question were therefore disarmed in the one shape where the answer matters most - a
-        // spawn server's block is never the client's, whatever MOBILEGL_IPC_ROLE_SPLIT_STATE
-        // says.
-        return MGPipeRoleSplitRehearsalActive() ||
-               MG_Config::Transport == MG_Config::TransportMode::Spawn;
-    }
-#endif // MOBILEGL_BUILD_DISAGGREGATED
-
-    PipeInputs& MGPipeClientInputs() {
-        return MGPipeRoleSplitRehearsalActive() ? gPipeInputsClientBlock : gPipeInputs;
-    }
-
-    void MGPipeClientClearVerbBoundary() {
-        MGPipeStampAccess::SetServerStamped(MGPipeClientInputs(), false);
-    }
-
-    namespace { Bool g_serverContextLive = false; }
-
-    void MGPipeServerSetContextLive(Bool live) {
-        g_serverContextLive = live;
-        MGPipeServerBlockNoteIdentity();
-    }
-
-    Bool MGPipeServerContextIsLive() { return g_serverContextLive; }
-
-#if MOBILEGL_BUILD_DISAGGREGATED
-    namespace { const void* g_serverOwnedWindow = nullptr; }
-
-    void MGPipeServerSetOwnedWindow(const void* window) { g_serverOwnedWindow = window; }
-
-    const void* MGPipeServerOwnedWindow() { return g_serverOwnedWindow; }
-#endif
-
-    void MGPipeServerBlockNoteIdentity() {
-        // D10: THE WIDER PREDICATE, and the narrow one was a latent crash rather than a missing
-        // optimisation. Gated on the REHEARSAL, this early-returned for the whole life of a
-        // spawn server - because that knob is off by default and nothing in the spawn shape
-        // turns it on - so the server's gPipeInputs.ContextIdentity() stayed nullptr forever.
-        // DirectGLES' fb-slot memo compares that identity FIRST and with no generation, so a
-        // nullptr against its own nullptr initialiser reads as a CACHE HIT and hands out a slot
-        // that was never filled. `st` lands the named Fatal at that site; this is the gate that
-        // stops it being reachable in the first place.
-        if (!MGPipeBlocksAreDistinct()) return;
-        // The server cannot name the client's GLContext - under a real transport it is in
-        // another process - so the identity the server block carries is the server's OWN
-        // served-context clock: MGPipeApplierContextSerial moves exactly when the served
-        // context does (MGPipeApplierReset), which is all the backends' per-context memo keys
-        // ask of an identity. The odd-encoding keeps the token non-null at serial 0: a null
-        // identity reads as a hit against DirectGLES' zero-initialised fb-slot memo cache and
-        // hands out a null slot - an unnamed crash where the rehearsal exists to produce a
-        // named one.
-        const Uint64 serial = MGPipeApplierContextSerial();
-        MGPipeStampAccess::SetIdentity(gPipeInputs, g_serverContextLive,
-                                       reinterpret_cast<const void*>(static_cast<std::uintptr_t>(
-                                           (serial << 1) | Uint64{1})));
-    }
-
-    void MGPipeServerStampVerbBoundary(MGPipeVerb verb) {
-        PipeInputs& inputs = gPipeInputs;
-        // P5e (gl), ID-115: THE POSITIVE CONTROL'S ONLY HONEST SIGNAL, and it belongs HERE
-        // because this is the line the whole strict mechanism hangs off. The poison, rsp and
-        // the BARRIER-PULLED verdict are all reachable only after this stamp, and the monolith
-        // arm never stamps at all - so "the strict lane is green" and "strict was never armed"
-        // were observationally identical, which is how a lane whose seven passing entries
-        // included no record-carrying split GL scenario read as rigour. Behind Enabled(), which
-        // is the file's rule for counters (`rsp` beside it does the same) and keeps the stamp a
-        // table lookup and a branch-free fill when stats are off.
-        if (MG_Util::PipeStats::Enabled()) {
-            MG_Util::PipeStats::AddCalls(MG_Util::PipeStats::CallClass::ServerVerbBoundaries, 1);
-        }
-        MGPipeFilledState& filled = MGPipeStampAccess::Filled(inputs);
-        MGPipeStampAccess::SetVerb(inputs, verb);
-        // Starts at 1 for MGPipeValidateForVerb's reason: FilledGen == 0 is "never filled" on
-        // BOTH branches of MGPipeInputFieldIsFresh, so the zeroing below is a real withdrawal
-        // rather than a stamp that happens to be old.
-        ++filled.CurrentVerbSerial;
-        // STAMPED: in this verb's class AND answerable out of the records the applier has
-        // already applied. WITHDRAWN (0): everything else - which is BARRIER-PULLED, FATAL,
-        // and anything the verb's own may-read table says this verb does not read.
-        //
-        // The withdrawal is the load-bearing half of the rule: the client's residual fill
-        // stamped all 63 fields at its own verb boundary, so without it every field would
-        // read fresh on the server, `rsp` would be identically 0 and the exit gate would be
-        // decoration. It also cancels the sticky exemption for free - generated/
-        // PipeFilled.inc tests "never filled" BEFORE it tests sticky, so 0 wins over
-        // kMGPipeInputFieldSticky without a line of the generated file changing.
-        //
-        // THE VERDICT IS THE SAME EXPRESSION; it is just precomputed per verb class
-        // (AnswerableMaskForClass above) instead of re-derived 63 times per verb, so what is
-        // left here is a table lookup and a branch-free fill.
-        const MGPipeFieldMask& answerable = AnswerableMaskForVerb(verb);
-        const Uint64 serial = filled.CurrentVerbSerial;
-        for (SizeT i = 0; i < kMGPipeInputFieldCount; ++i) {
-            const Uint64 bit = (answerable.Words[i / 64] >> (i % 64)) & Uint64{1};
-            filled.FilledGen[i] = serial & (Uint64{0} - bit);
-        }
-#if MOBILEGL_PIPE_VERIFY
-        // Negative control B's server half (ServerPoisonOmission above): the one withheld pair.
-        {
-            const ServerPoisonOmission& omission = ServerOmission();
-            if (omission.Armed && omission.Verb == verb) {
-                filled.FilledGen[static_cast<SizeT>(omission.Field)] = 0;
-            }
-        }
-#endif
-        MGPipeStampAccess::SetServerStamped(inputs, true);
-        // P5f (f1): the server block's identity rides the stamp (CONTRACT-P5E §3.2's
-        // "SetIdentity moves to ApplyOne" - the stamp is the per-verb half of ApplyOne, and
-        // refreshing here rather than once at Attach keeps the token in step with
-        // MGPipeApplierContextSerial across a context switch). A no-op with the rehearsal off.
-        MGPipeServerBlockNoteIdentity();
-    }
-
-    void MGPipeServerClearVerbBoundary() { MGPipeStampAccess::SetServerStamped(gPipeInputs, false); }
-
-    Uint64 MGPipeResidualPullCount() { return g_residualPulls; }
-    void MGPipeResetResidualPullCountForTesting() { g_residualPulls = 0; }
-
-    void MGPipeInputUnfreshRead(MGPipeInputField field, MGPipeVerb verb, Bool serverStamped) {
-        // OUTSIDE A SERVER-STAMPED VERB THIS IS THE MONOLITH ANSWER, UNCHANGED. A split BUILD
-        // running MOBILEGL_TRANSPORT=monolith - every unit and integration-gpu lane of
-        // build-split - has a client that stamped all 63 fields, so a stale read there is the
-        // same defect it is in a verify build. Softening it on the build rather than on the
-        // stamp would take 1842 unit cases' ability to go red away with it.
-        //
-        // AND A READ OUTSIDE THE VERB'S OWN CLASS IS STILL FATAL even for a BARRIER-PULLED
-        // field: the value it would be answered with was never copied for this verb, so
-        // counting it would trade a loud staleness for a quiet one.
-#if MOBILEGL_PIPE_VERIFY
-        // An injected omission is reported as what it models - a stamp nobody wrote, the
-        // client filler's own Fatal{UnmigratedPipeInput, "<Field>@<Verb>"} - and never as the
-        // RoleViolation below, which would blame the wire for a withdrawal the control made.
-        if (serverStamped && ServerOmitsStamp(verb, field)) MGPipeInputPoisonFatalForVerb(field, verb);
-#endif
-        if (!serverStamped ||
-            kMGPipeFieldOwnership[static_cast<SizeT>(field)] != MGPipeFieldOwnership::kBarrierPulled ||
-            !FieldIsInVerbClass(field, verb)) {
-            // P5c (gt, CONTRACT-P5C §6 layer 1): under a server stamp, a stale read of a field
-            // whose row is RECORD-SUPPLIED or APPLIER-DERIVED - i.e. a value a pushed record
-            // DOES carry, read where this verb's stamp does not cover it - is a role violation
-            // named by its surface, not a generic unmigrated read: the wire already owns the
-            // answer, so reaching past it into the residual fill is rule E's shape. A
-            // BARRIER-PULLED field outside the verb's class and a FATAL field keep the poison
-            // Fatal - those are the stamp table's own verdicts, not a role's overreach.
-            const MGPipeFieldOwnership ownership = kMGPipeFieldOwnership[static_cast<SizeT>(field)];
-            if (serverStamped && (ownership == MGPipeFieldOwnership::kRecordSupplied ||
-                                  ownership == MGPipeFieldOwnership::kApplierDerived)) {
-                MGLOG_F("MGPipe: Fatal{RoleViolation, \"%s\"} - the server read this field stale "
-                        "at %s, but a pushed record carries it (the row is %s): the read reached "
-                        "the client's residual fill for a value the wire already owns",
-                        kMGPipeInputFieldNames[static_cast<SizeT>(field)], MGPipeVerbName(verb),
-                        MGPipeFieldOwnershipName(ownership));
-                std::abort();
-            }
-            MGPipeInputPoisonFatalForVerb(field, verb);
-        }
-        CountBarrierPull(field, verb);
-    }
-
-    Bool MGPipeInputArgumentRead(MGPipeInputField field, Uint32 arg0, MGPipeVerb verb, Bool serverStamped) {
-        if (!serverStamped) return false;
-        const MGPipeFieldOwnership narrowed = MGPipeFieldOwnershipOf(field, arg0);
-        if (narrowed == MGPipeFieldOwnershipOf(field)) return false; // the argument narrows nothing
-        if (narrowed == MGPipeFieldOwnership::kFatal) {
-            // The field's own stamp says fresh - the applier really did write the half that has
-            // a carrier - so only the argument can say that THIS read is unserved. THE MESSAGE
-            // NAMES THE ARGUMENT, because without it this line is byte-identical to what a
-            // genuinely stale read of the OTHER half would print, and the whole case for
-            // narrowing by argument rather than by a second field id is that the reader is told
-            // which half they asked for.
-            MGLOG_F("MGPipe: Fatal{UnmigratedPipeInput, \"%s@%s\"} [argument 0 = %u is %s while the "
-                    "field is %s]",
-                    kMGPipeInputFieldNames[static_cast<SizeT>(field)], MGPipeVerbName(verb), arg0,
-                    MGPipeFieldOwnershipName(narrowed),
-                    MGPipeFieldOwnershipName(MGPipeFieldOwnershipOf(field)));
-            std::abort();
-        }
-        if (narrowed == MGPipeFieldOwnership::kBarrierPulled) {
-            CountBarrierPull(field, verb);
-            return true; // decided here; the field-level check must not count it again
-        }
-        return true;
-    }
-
-    void MGPipeStickyForwardPull(MGPipeInputField field) {
-        // The seven carry no MGP_INPUT_CHECK at all (the declared exception argued at
-        // PipeInputs.h's F-class block), so freshness can never reach them and neither can the
-        // stamp's withdrawal. This is the only thing that puts them in `rsp`.
-        if (!gPipeInputs.ServerStampedVerb()) return;
-        const auto ownership = MGPipeFieldOwnershipOf(field);
-        if (ownership == MGPipeFieldOwnership::kFatal)
-            MGPipeInputPoisonFatalForVerb(field, gPipeInputs.CurrentVerb());
-        if (ownership == MGPipeFieldOwnership::kBarrierPulled)
-            CountBarrierPull(field, gPipeInputs.CurrentVerb());
-    }
-#endif // MOBILEGL_BUILD_DISAGGREGATED
-
-#if MOBILEGL_PIPE_VERIFY
-    namespace {
-        using CurrentVertexAttributeValue = PipeInputs::CurrentVertexAttributeValue;
-
-        // Every overload is declared up front: the array overloads recurse into their element
-        // type, and a call inside a template only sees what was declared before the template.
-        template <class T>
-        Bool StorageEqual(const T& a, const T& b);
-        template <class T>
-        Bool StorageEqual(T* const& a, T* const& b);
-        template <class T>
-        Bool StorageEqual(const SharedPtr<T>& a, const SharedPtr<T>& b);
-        template <class T, SizeT N>
-        Bool StorageEqual(const T (&a)[N], const T (&b)[N]);
-        Bool StorageEqual(const PipeInputs::IndexedCapabilities& a, const PipeInputs::IndexedCapabilities& b);
-        Bool StorageEqual(const CurrentVertexAttributeValue& a, const CurrentVertexAttributeValue& b);
-        template <class T>
-        void CorruptStorage(T& v);
-        template <class T>
-        void CorruptStorage(T*& p);
-        template <class T>
-        void CorruptStorage(SharedPtr<T>& p);
-        template <class T, SizeT N>
-        void CorruptStorage(T (&a)[N]);
-        void CorruptStorage(PipeInputs::IndexedCapabilities& c);
-        void CorruptStorage(CurrentVertexAttributeValue& v);
-
-        // ---- equality over one field's storage ----
-        // O-class storage compares by identity: a raw pointer into the context, or the object a
-        // SharedPtr owns. Everything else goes through G4's MGPipeFieldEqual, recursing through
-        // C arrays element-wise.
-        template <class T>
-        Bool StorageEqual(T* const& a, T* const& b) {
-            return a == b;
-        }
-        template <class T>
-        Bool StorageEqual(const SharedPtr<T>& a, const SharedPtr<T>& b) {
-            return a.get() == b.get();
-        }
-        template <class T, SizeT N>
-        Bool StorageEqual(const T (&a)[N], const T (&b)[N]) {
-            for (SizeT i = 0; i < N; ++i) {
-                if (!StorageEqual(a[i], b[i])) return false;
-            }
-            return true;
-        }
-        Bool StorageEqual(const PipeInputs::IndexedCapabilities& a, const PipeInputs::IndexedCapabilities& b) {
-            return StorageEqual(a.Blend, b.Blend) && StorageEqual(a.ScissorTest, b.ScissorTest);
-        }
-        // Three scalar arrays and nothing else (Core.h), so a bitwise compare has no padding to
-        // false-differ on and keeps a NaN float attribute equal to itself. The size assertion is
-        // what turns a fourth member into a build break rather than a blind spot.
-        Bool StorageEqual(const CurrentVertexAttributeValue& a, const CurrentVertexAttributeValue& b) {
-            static_assert(sizeof(CurrentVertexAttributeValue) == 3 * 4 * 4,
-                          "CurrentVertexAttributeValue grew a member; update the comparator");
-            return std::memcmp(&a, &b, sizeof(CurrentVertexAttributeValue)) == 0;
-        }
-        template <class T>
-        Bool StorageEqual(const T& a, const T& b) {
-            return MGPipeFieldEqual(a, b);
-        }
-
-        // ---- corruption of one field's storage ----
-        // Every shape is perturbed in a way the comparator above must see: a Bool flips, a
-        // scalar or enum moves by one, a pointer's low bits are flipped (never dereferenced:
-        // the snapshot is only ever compared), a SharedPtr becomes an aliasing pointer to a
-        // flipped address with no control block, an array corrupts its first element, and any
-        // other struct has its first byte XOR'ed with 0x5A.
-        template <class T>
-        T* FlipPointer(T* p) {
-            return reinterpret_cast<T*>(reinterpret_cast<std::uintptr_t>(p) ^ 0x5A);
-        }
-        template <class T>
-        void CorruptStorage(T*& p) {
-            p = FlipPointer(p);
-        }
-        template <class T>
-        void CorruptStorage(SharedPtr<T>& p) {
-            p = SharedPtr<T>(SharedPtr<T>(), FlipPointer(p.get()));
-        }
-        template <class T, SizeT N>
-        void CorruptStorage(T (&a)[N]) {
-            CorruptStorage(a[0]);
-        }
-        void CorruptStorage(PipeInputs::IndexedCapabilities& c) {
-            CorruptStorage(c.Blend);
-        }
-        void CorruptStorage(CurrentVertexAttributeValue& v) {
-            v.floatValue[0] += 1.f;
-        }
-        template <class T>
-        void CorruptStorage(T& v) {
-            if constexpr (std::is_same_v<T, Bool>) {
-                v = !v;
-            } else if constexpr (std::is_enum_v<T>) {
-                v = static_cast<T>(static_cast<std::underlying_type_t<T>>(v) + 1);
-            } else if constexpr (std::is_arithmetic_v<T>) {
-                v = static_cast<T>(v + 1);
-            } else {
-                static_assert(std::is_trivially_copyable_v<T>, "PipeInputs storage must be trivially copyable");
-                unsigned char first = 0;
-                std::memcpy(&first, &v, 1);
-                first ^= 0x5A;
-                std::memcpy(&v, &first, 1);
-            }
-        }
-    } // namespace
-
-    Bool MGPipeInputsFieldEqual(MGPipeInputField field, const PipeInputs& a, const PipeInputs& b) {
-        // A forwarded field has no storage and is equal by definition; VisitStorage answers
-        // false for it, hence the explicit sticky test first.
-        if (kMGPipeInputFieldSticky[static_cast<SizeT>(field)]) return true;
-        return PipeInputs::VisitStorage(field, a, b, [](const auto& x, const auto& y) { return StorageEqual(x, y); });
-    }
-
-    Bool MGPipeVerifyInputs(const PipeInputs& pushed, const PipeInputs& snapshot, const MGPipeFieldMask& mask,
-                            MGPipeInputField* outField) {
-        for (SizeT i = 0; i < kMGPipeInputFieldCount; ++i) {
-            const auto field = static_cast<MGPipeInputField>(i);
-            if (!MGPipeFieldMaskHas(mask, field)) continue;
-            if (MGPipeInputsFieldEqual(field, pushed, snapshot)) continue;
-            if (outField != nullptr) *outField = field;
-            return false;
-        }
-        return true;
-    }
-
-    Bool MGPipeApplyVerifyCorruption(PipeInputs& snapshot, MGPipeInputField field) {
-        return PipeInputs::VisitStorage(field, snapshot, snapshot, [](auto& x, auto&) {
-            CorruptStorage(x);
-            return true;
-        });
-    }
-#endif // MOBILEGL_PIPE_VERIFY
-} // namespace MobileGL::MG_Pipe