swung0x48/MobileGL
1
0
Fork 0
mirror of https://github.com/MobileGL-Dev/MobileGL synced 2026-11-07 10:03:23 +09:00
Code Issues Packages Projects Releases Wiki Activity

Compare commits

base: swung0x48/MobileGL:feat/disaggregated-container-gbm
Branches Tags
swung0x48/MobileGL:dev swung0x48/MobileGL:feat/disaggregated swung0x48/MobileGL:cleanup swung0x48/MobileGL:nv_mesh_shader swung0x48/MobileGL:ci/arch-wsl-gpu-runner swung0x48/MobileGL:feat/disaggregated-fix-d1100-mali swung0x48/MobileGL:feat/disaggregated-container-gbm swung0x48/MobileGL:codex/frame-stats-20260926 swung0x48/MobileGL:Feat/Diligent-Vulkan-Backend swung0x48/MobileGL:fix/memory-audit-2026-08-16 swung0x48/MobileGL:libfork-async-compile swung0x48/MobileGL:feat/magma-relaxed-fragment-precision swung0x48/MobileGL:piglit-gl33 swung0x48/MobileGL:itrp swung0x48/MobileGL:codex/fix-unsized-packed-bgra swung0x48/MobileGL:Perf/Improvement1 swung0x48/MobileGL:Feat/Backend-Direct-Vulkan-TMP swung0x48/MobileGL:Deprecated/Feat/Diligent swung0x48/MobileGL:Deprecated/dev swung0x48/MobileGL:Deprecated/Feat/dev-es-shittily-draw swung0x48/MobileGL:Deprecated/Feat/dev-es-renaming
..
compare: swung0x48/MobileGL:nv_mesh_shader
Branches Tags
swung0x48/MobileGL:dev swung0x48/MobileGL:feat/disaggregated swung0x48/MobileGL:cleanup swung0x48/MobileGL:nv_mesh_shader swung0x48/MobileGL:ci/arch-wsl-gpu-runner swung0x48/MobileGL:feat/disaggregated-fix-d1100-mali swung0x48/MobileGL:feat/disaggregated-container-gbm swung0x48/MobileGL:codex/frame-stats-20260926 swung0x48/MobileGL:Feat/Diligent-Vulkan-Backend swung0x48/MobileGL:fix/memory-audit-2026-08-16 swung0x48/MobileGL:libfork-async-compile swung0x48/MobileGL:feat/magma-relaxed-fragment-precision swung0x48/MobileGL:piglit-gl33 swung0x48/MobileGL:itrp swung0x48/MobileGL:codex/fix-unsized-packed-bgra swung0x48/MobileGL:Perf/Improvement1 swung0x48/MobileGL:Feat/Backend-Direct-Vulkan-TMP swung0x48/MobileGL:Deprecated/Feat/Diligent swung0x48/MobileGL:Deprecated/dev swung0x48/MobileGL:Deprecated/Feat/dev-es-shittily-draw swung0x48/MobileGL:Deprecated/Feat/dev-es-renaming
3 Commits
feat/disaggregated-container-gbm .. nv_mesh_shader
Author SHA1 Message Date
HH45137 e3fac5e9fa [Fix]: Add Task/Mesh shader enum mapping 
Map the Task and Mesh shader stages to their NV OpenGL enum values in ProgramEnumConverter so shader stage conversion handles task and mesh pipelines correctly.
 2026-10-12 00:41:40 +08:00
HH45137 3823fe528c [Feat, Test]: Add NV mesh shader support 
Advertise GL_NV_mesh_shader in the DirectVulkan backend and expose the new task/mesh shader stages in the GL-to-MG and glslang conversion layers. This also wires the mesh task drawing entry points and adds a focused MeshShader test covering extension discovery and task shader compilation.
 2026-10-12 00:20:53 +08:00
swung0x48 08124c99f1 [Test] (trace): replace the create-indirect fixture with minecraft-1.21.1-neoforge-create-indirect-in-world-align1024, a derived trace and not the original capture - the desktop capture bound Flywheel's scatter lists at 16-byte SSBO offsets that Adreno 830 and Mali's Vulkan driver (64) reject, and fixture_tools/realign_buffer_ranges.cpp moves the 1,270 binds off a 1024-byte boundary onto 1024-aligned slots (3,812 calls inserted, target call 504631 -> 508443, host SSIM unchanged to 9 digits on both backends) 2026-09-30 10:00:26 -04:00
1611 changed files with 3723 additions and 734981 deletions
Expand all files Collapse all files
.github/scripts/validate-plugin-apks.sh
+2 -27
View File
@@ -61,40 +61,15 @@ if ! grep -Eq '^lib/[^/]+/libMobileGL\.so$' <<<"$plugin_contents"; then
exit 1
fi
# The render server is not trace-only: both flavors carry the control screen, the offscreen
# service, the on-screen display activity, and (split native builds) the supervisor executable.
# The plugin APK ships to users, so its build keeps the three components private (manifest
# placeholder serverComponentsExported=false); only the debuggable trace APK exports them for adb.
for component in ServerControlActivity MobileGLServerService MobileGLDisplayActivity; do
require "$component" "$plugin_manifest" "plugin render server component ($component)"
require "$component" "$trace_manifest" "trace render server component ($component)"
done
if [[ "${MOBILEGL_CI_DISAGGREGATED:-OFF}" == "ON" ]]; then
trace_contents=$(unzip -Z1 "$trace_apk")
for entry in "plugin:${plugin_contents}" "trace:${trace_contents}"; do
if ! grep -Eq '^lib/[^/]+/libMobileGLServer\.so$' <<<"${entry#*:}"; then
echo "::error::${entry%%:*} APK does not contain libMobileGLServer.so (both flavors ship the render server)" >&2
exit 1
fi
done
fi
require 'top.mobilegl.plugin.trace' "$trace_manifest" 'trace package name'
require 'top.mobilegl.plugin.TRACE_REPLAY' "$trace_manifest" 'trace replay action'
if grep -Fq 'fclPlugin' <<<"$trace_manifest"; then
echo '::error::Trace APK must not advertise renderer-plugin metadata' >&2
exit 1
fi
# The trace APK IS a launchable app now: PostActivity (the POST self-test screen) is its
# entry icon and the bottom navigation bar switches to the render server screen. What is
# left of the old "no launcher" contract is the count - exactly ONE MAIN activity, so a
# screen that accidentally grows a launcher entry (ServerControlActivity was one for a day)
# reds here instead of shipping two icons.
main_count=$(grep -Fc 'android.intent.action.MAIN' <<<"$trace_manifest")
if [[ "$main_count" -ne 1 ]]; then
echo "::error::Trace APK must expose exactly one launcher activity (PostActivity); found ${main_count} android.intent.action.MAIN" >&2
if grep -Fq 'android.intent.action.MAIN' <<<"$trace_manifest"; then
echo '::error::Trace APK must not expose a launcher activity' >&2
exit 1
fi
require 'PostActivity' "$trace_manifest" 'trace launcher activity (PostActivity)'
echo 'Validated unified MobileGL plugin APK and isolated trace APK.'
.github/workflows/apk.yml
+27 -157
View File
@@ -6,24 +6,8 @@ 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
@@ -37,7 +21,6 @@ jobs:
CCACHE_MAXSIZE: 4G
CCACHE_NOHASHDIR: "true"
MOBILEGL_CMAKE_COMPILER_LAUNCHER: ccache
MOBILEGL_CI_DISAGGREGATED: ${{ (github.ref_name == 'feat/disaggregated' || github.ref_name == 'codex/fix-github-ci') && 'ON' || 'OFF' }}
steps:
- name: Checkout repo
@@ -55,9 +38,6 @@ jobs:
distribution: zulu
java-version: '17'
- name: Android replay lifecycle regression
run: python3 tools/trace_replay/test_android_lifecycle.py
- name: Setup Gradle
uses: gradle/actions/setup-gradle@v6
with:
@@ -81,8 +61,6 @@ jobs:
uses: android-actions/setup-android@v4
with:
accept-android-sdk-licenses: false
packages: platform-tools
cmdline-tools-version: 13114758
- name: Accept Android SDK licenses
run: yes | sdkmanager --licenses >/dev/null
@@ -97,13 +75,7 @@ jobs:
run: python update_glslang_sources.py
- name: Build plugin APK
run: >-
gradle --no-daemon -p android-plugin :app:assemblePluginRelease
-Pmobilegl.apkSuffix="${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: ${{ secrets.SIGNING_KEY_ALIAS }}
@@ -145,14 +117,7 @@ jobs:
66fdc867e552192d553d59095ea2e3cef4829de65c356f1fd826027b1905972e
- name: Build retrace APK
run: >-
gradle --no-daemon -p android-plugin :app:assembleTraceRelease
-Pmobilegl.apkSuffix="${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 }}
@@ -234,8 +199,6 @@ 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: ${{ steps.trace-cases.outputs.names }}
@@ -246,12 +209,7 @@ jobs:
- name: Load trace cases
id: trace-cases
run: |
python3 tools/trace_replay/trace_cases.py --self-test-transport-matrices
matrix_format=github-apk-matrix
if [ "${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-matrix)" >> "$GITHUB_OUTPUT"
echo "names=$(python3 tools/trace_replay/trace_cases.py --ci --format names)" >> "$GITHUB_OUTPUT"
trace-fixtures:
@@ -335,8 +293,6 @@ jobs:
uses: android-actions/setup-android@v4
with:
accept-android-sdk-licenses: false
packages: platform-tools
cmdline-tools-version: 13114758
- name: Accept Android SDK licenses
run: yes | sdkmanager --licenses >/dev/null
@@ -364,7 +320,7 @@ jobs:
--avd-name "${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 +330,6 @@ 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
@@ -385,7 +339,7 @@ jobs:
max-parallel: 4
matrix: ${{ fromJSON(needs.trace-cases.outputs.android) }}
steps:
- name: Set swap space
- name: Set Swap Space
uses: pierotofy/set-swap-space@v1.0
with:
swap-size-gb: 8
@@ -414,8 +368,6 @@ jobs:
uses: android-actions/setup-android@v4
with:
accept-android-sdk-licenses: false
packages: platform-tools
cmdline-tools-version: 13114758
- name: Accept Android SDK licenses
run: yes | sdkmanager --licenses >/dev/null
@@ -454,7 +406,7 @@ jobs:
--profile pixel_6 \
--avd-name "${AVD_NAME}"
- name: Launch emulator
- name: Launch Emulator
run: |
sh android-plugin/run-avd-ci.sh start \
--avd-name "${AVD_NAME}" \
@@ -475,31 +427,6 @@ jobs:
apk_file="android-retrace-apks/MobileGL-plugin-trace-release-${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" ] && [ "${{ matrix.case.name }}" = "minecraft-1.21.4-fabric-iris-bliss-in-world" ]; then
@@ -581,12 +508,6 @@ jobs:
safe_case="$(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
@@ -611,7 +532,7 @@ jobs:
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 +544,7 @@ 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 +553,6 @@ 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 +567,25 @@ 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
@@ -730,19 +601,15 @@ 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):"
@@ -785,6 +652,9 @@ jobs:
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)."
.github/workflows/test.yml
+39 -2998
View File
File diff suppressed because it is too large Load Diff
.gitignore
-1
View File
@@ -28,4 +28,3 @@ tools/trace_replay/work/
__pycache__/
*.py[cod]
/.gradle
/.trace-work/
.gitmodules
-3
View File
@@ -34,6 +34,3 @@
[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
3rdparty/flatbuffers
Vendored
-1
Submodule 3rdparty/flatbuffers deleted from 7e163021e5
3rdparty/gbm/include/gbm.h
Vendored
-538
View File
@@ -1,538 +0,0 @@
/*
* Copyright © 2011 Intel Corporation
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice (including the next
* paragraph) shall be included in all copies or substantial portions of the
* Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
* HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
* WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Authors:
* Benjamin Franzke <benjaminfranzke@googlemail.com>
*/
#ifndef _GBM_H_
#define _GBM_H_
#define __GBM__ 1
#include <stddef.h>
#include <stdint.h>
#ifdef __cplusplus
extern "C" {
#endif
/**
* \file gbm.h
* \brief Generic Buffer Manager
*/
struct gbm_device;
struct gbm_bo;
struct gbm_surface;
/**
* \mainpage The Generic Buffer Manager
*
* This module provides an abstraction that the caller can use to request a
* buffer from the underlying memory management system for the platform.
*
* This allows the creation of portable code whilst still allowing access to
* the underlying memory manager.
*/
/**
* Abstraction representing the handle to a buffer allocated by the
* manager
*/
union gbm_bo_handle {
void *ptr;
int32_t s32;
uint32_t u32;
int64_t s64;
uint64_t u64;
};
/** Format of the allocated buffer */
enum gbm_bo_format {
/** RGB with 8 bits per channel in a 32 bit value */
GBM_BO_FORMAT_XRGB8888,
/** ARGB with 8 bits per channel in a 32 bit value */
GBM_BO_FORMAT_ARGB8888
};
/**
* The FourCC format codes are taken from the drm_fourcc.h definition, and
* re-namespaced. New GBM formats must not be added, unless they are
* identical ports from drm_fourcc.
*/
#define __gbm_fourcc_code(a,b,c,d) ((uint32_t)(a) | ((uint32_t)(b) << 8) | \
((uint32_t)(c) << 16) | ((uint32_t)(d) << 24))
#define GBM_FORMAT_BIG_ENDIAN (1<<31) /* format is big endian instead of little endian */
/* color index */
#define GBM_FORMAT_C8 __gbm_fourcc_code('C', '8', ' ', ' ') /* [7:0] C */
/* 8 bpp Red */
#define GBM_FORMAT_R8 __gbm_fourcc_code('R', '8', ' ', ' ') /* [7:0] R */
/* 16 bpp Red */
#define GBM_FORMAT_R16 __gbm_fourcc_code('R', '1', '6', ' ') /* [15:0] R little endian */
/* 16 bpp RG */
#define GBM_FORMAT_GR88 __gbm_fourcc_code('G', 'R', '8', '8') /* [15:0] G:R 8:8 little endian */
/* 32 bpp RG */
#define GBM_FORMAT_RG1616 __gbm_fourcc_code('R', 'G', '3', '2') /* [31:0] R:G 16:16 little endian */
#define GBM_FORMAT_GR1616 __gbm_fourcc_code('G', 'R', '3', '2') /* [31:0] G:R 16:16 little endian */
/* 8 bpp RGB */
#define GBM_FORMAT_RGB332 __gbm_fourcc_code('R', 'G', 'B', '8') /* [7:0] R:G:B 3:3:2 */
#define GBM_FORMAT_BGR233 __gbm_fourcc_code('B', 'G', 'R', '8') /* [7:0] B:G:R 2:3:3 */
/* 16 bpp RGB */
#define GBM_FORMAT_XRGB4444 __gbm_fourcc_code('X', 'R', '1', '2') /* [15:0] x:R:G:B 4:4:4:4 little endian */
#define GBM_FORMAT_XBGR4444 __gbm_fourcc_code('X', 'B', '1', '2') /* [15:0] x:B:G:R 4:4:4:4 little endian */
#define GBM_FORMAT_RGBX4444 __gbm_fourcc_code('R', 'X', '1', '2') /* [15:0] R:G:B:x 4:4:4:4 little endian */
#define GBM_FORMAT_BGRX4444 __gbm_fourcc_code('B', 'X', '1', '2') /* [15:0] B:G:R:x 4:4:4:4 little endian */
#define GBM_FORMAT_ARGB4444 __gbm_fourcc_code('A', 'R', '1', '2') /* [15:0] A:R:G:B 4:4:4:4 little endian */
#define GBM_FORMAT_ABGR4444 __gbm_fourcc_code('A', 'B', '1', '2') /* [15:0] A:B:G:R 4:4:4:4 little endian */
#define GBM_FORMAT_RGBA4444 __gbm_fourcc_code('R', 'A', '1', '2') /* [15:0] R:G:B:A 4:4:4:4 little endian */
#define GBM_FORMAT_BGRA4444 __gbm_fourcc_code('B', 'A', '1', '2') /* [15:0] B:G:R:A 4:4:4:4 little endian */
#define GBM_FORMAT_XRGB1555 __gbm_fourcc_code('X', 'R', '1', '5') /* [15:0] x:R:G:B 1:5:5:5 little endian */
#define GBM_FORMAT_XBGR1555 __gbm_fourcc_code('X', 'B', '1', '5') /* [15:0] x:B:G:R 1:5:5:5 little endian */
#define GBM_FORMAT_RGBX5551 __gbm_fourcc_code('R', 'X', '1', '5') /* [15:0] R:G:B:x 5:5:5:1 little endian */
#define GBM_FORMAT_BGRX5551 __gbm_fourcc_code('B', 'X', '1', '5') /* [15:0] B:G:R:x 5:5:5:1 little endian */
#define GBM_FORMAT_ARGB1555 __gbm_fourcc_code('A', 'R', '1', '5') /* [15:0] A:R:G:B 1:5:5:5 little endian */
#define GBM_FORMAT_ABGR1555 __gbm_fourcc_code('A', 'B', '1', '5') /* [15:0] A:B:G:R 1:5:5:5 little endian */
#define GBM_FORMAT_RGBA5551 __gbm_fourcc_code('R', 'A', '1', '5') /* [15:0] R:G:B:A 5:5:5:1 little endian */
#define GBM_FORMAT_BGRA5551 __gbm_fourcc_code('B', 'A', '1', '5') /* [15:0] B:G:R:A 5:5:5:1 little endian */
#define GBM_FORMAT_RGB565 __gbm_fourcc_code('R', 'G', '1', '6') /* [15:0] R:G:B 5:6:5 little endian */
#define GBM_FORMAT_BGR565 __gbm_fourcc_code('B', 'G', '1', '6') /* [15:0] B:G:R 5:6:5 little endian */
/* 24 bpp RGB */
#define GBM_FORMAT_RGB888 __gbm_fourcc_code('R', 'G', '2', '4') /* [23:0] R:G:B little endian */
#define GBM_FORMAT_BGR888 __gbm_fourcc_code('B', 'G', '2', '4') /* [23:0] B:G:R little endian */
/* 32 bpp RGB */
#define GBM_FORMAT_XRGB8888 __gbm_fourcc_code('X', 'R', '2', '4') /* [31:0] x:R:G:B 8:8:8:8 little endian */
#define GBM_FORMAT_XBGR8888 __gbm_fourcc_code('X', 'B', '2', '4') /* [31:0] x:B:G:R 8:8:8:8 little endian */
#define GBM_FORMAT_RGBX8888 __gbm_fourcc_code('R', 'X', '2', '4') /* [31:0] R:G:B:x 8:8:8:8 little endian */
#define GBM_FORMAT_BGRX8888 __gbm_fourcc_code('B', 'X', '2', '4') /* [31:0] B:G:R:x 8:8:8:8 little endian */
#define GBM_FORMAT_ARGB8888 __gbm_fourcc_code('A', 'R', '2', '4') /* [31:0] A:R:G:B 8:8:8:8 little endian */
#define GBM_FORMAT_ABGR8888 __gbm_fourcc_code('A', 'B', '2', '4') /* [31:0] A:B:G:R 8:8:8:8 little endian */
#define GBM_FORMAT_RGBA8888 __gbm_fourcc_code('R', 'A', '2', '4') /* [31:0] R:G:B:A 8:8:8:8 little endian */
#define GBM_FORMAT_BGRA8888 __gbm_fourcc_code('B', 'A', '2', '4') /* [31:0] B:G:R:A 8:8:8:8 little endian */
#define GBM_FORMAT_XRGB2101010 __gbm_fourcc_code('X', 'R', '3', '0') /* [31:0] x:R:G:B 2:10:10:10 little endian */
#define GBM_FORMAT_XBGR2101010 __gbm_fourcc_code('X', 'B', '3', '0') /* [31:0] x:B:G:R 2:10:10:10 little endian */
#define GBM_FORMAT_RGBX1010102 __gbm_fourcc_code('R', 'X', '3', '0') /* [31:0] R:G:B:x 10:10:10:2 little endian */
#define GBM_FORMAT_BGRX1010102 __gbm_fourcc_code('B', 'X', '3', '0') /* [31:0] B:G:R:x 10:10:10:2 little endian */
#define GBM_FORMAT_ARGB2101010 __gbm_fourcc_code('A', 'R', '3', '0') /* [31:0] A:R:G:B 2:10:10:10 little endian */
#define GBM_FORMAT_ABGR2101010 __gbm_fourcc_code('A', 'B', '3', '0') /* [31:0] A:B:G:R 2:10:10:10 little endian */
#define GBM_FORMAT_RGBA1010102 __gbm_fourcc_code('R', 'A', '3', '0') /* [31:0] R:G:B:A 10:10:10:2 little endian */
#define GBM_FORMAT_BGRA1010102 __gbm_fourcc_code('B', 'A', '3', '0') /* [31:0] B:G:R:A 10:10:10:2 little endian */
/* 64 bpp RGB */
#define GBM_FORMAT_XBGR16161616 __gbm_fourcc_code('X', 'B', '4', '8') /* [63:0] x:B:G:R 16:16:16:16 little endian */
#define GBM_FORMAT_ABGR16161616 __gbm_fourcc_code('A', 'B', '4', '8') /* [63:0] A:B:G:R 16:16:16:16 little endian */
/*
* Floating point 64bpp RGB
* IEEE 754-2008 binary16 half-precision float
* [15:0] sign:exponent:mantissa 1:5:10
*/
#define GBM_FORMAT_XBGR16161616F __gbm_fourcc_code('X', 'B', '4', 'H') /* [63:0] x:B:G:R 16:16:16:16 little endian */
#define GBM_FORMAT_ABGR16161616F __gbm_fourcc_code('A', 'B', '4', 'H') /* [63:0] A:B:G:R 16:16:16:16 little endian */
/* packed YCbCr */
#define GBM_FORMAT_YUYV __gbm_fourcc_code('Y', 'U', 'Y', 'V') /* [31:0] Cr0:Y1:Cb0:Y0 8:8:8:8 little endian */
#define GBM_FORMAT_YVYU __gbm_fourcc_code('Y', 'V', 'Y', 'U') /* [31:0] Cb0:Y1:Cr0:Y0 8:8:8:8 little endian */
#define GBM_FORMAT_UYVY __gbm_fourcc_code('U', 'Y', 'V', 'Y') /* [31:0] Y1:Cr0:Y0:Cb0 8:8:8:8 little endian */
#define GBM_FORMAT_VYUY __gbm_fourcc_code('V', 'Y', 'U', 'Y') /* [31:0] Y1:Cb0:Y0:Cr0 8:8:8:8 little endian */
#define GBM_FORMAT_AYUV __gbm_fourcc_code('A', 'Y', 'U', 'V') /* [31:0] A:Y:Cb:Cr 8:8:8:8 little endian */
/*
* 2 plane YCbCr
* index 0 = Y plane, [7:0] Y
* index 1 = Cr:Cb plane, [15:0] Cr:Cb little endian
* or
* index 1 = Cb:Cr plane, [15:0] Cb:Cr little endian
*/
#define GBM_FORMAT_NV12 __gbm_fourcc_code('N', 'V', '1', '2') /* 2x2 subsampled Cr:Cb plane */
#define GBM_FORMAT_NV21 __gbm_fourcc_code('N', 'V', '2', '1') /* 2x2 subsampled Cb:Cr plane */
#define GBM_FORMAT_NV16 __gbm_fourcc_code('N', 'V', '1', '6') /* 2x1 subsampled Cr:Cb plane */
#define GBM_FORMAT_NV61 __gbm_fourcc_code('N', 'V', '6', '1') /* 2x1 subsampled Cb:Cr plane */
/*
* 3 plane YCbCr
* index 0: Y plane, [7:0] Y
* index 1: Cb plane, [7:0] Cb
* index 2: Cr plane, [7:0] Cr
* or
* index 1: Cr plane, [7:0] Cr
* index 2: Cb plane, [7:0] Cb
*/
#define GBM_FORMAT_YUV410 __gbm_fourcc_code('Y', 'U', 'V', '9') /* 4x4 subsampled Cb (1) and Cr (2) planes */
#define GBM_FORMAT_YVU410 __gbm_fourcc_code('Y', 'V', 'U', '9') /* 4x4 subsampled Cr (1) and Cb (2) planes */
#define GBM_FORMAT_YUV411 __gbm_fourcc_code('Y', 'U', '1', '1') /* 4x1 subsampled Cb (1) and Cr (2) planes */
#define GBM_FORMAT_YVU411 __gbm_fourcc_code('Y', 'V', '1', '1') /* 4x1 subsampled Cr (1) and Cb (2) planes */
#define GBM_FORMAT_YUV420 __gbm_fourcc_code('Y', 'U', '1', '2') /* 2x2 subsampled Cb (1) and Cr (2) planes */
#define GBM_FORMAT_YVU420 __gbm_fourcc_code('Y', 'V', '1', '2') /* 2x2 subsampled Cr (1) and Cb (2) planes */
#define GBM_FORMAT_YUV422 __gbm_fourcc_code('Y', 'U', '1', '6') /* 2x1 subsampled Cb (1) and Cr (2) planes */
#define GBM_FORMAT_YVU422 __gbm_fourcc_code('Y', 'V', '1', '6') /* 2x1 subsampled Cr (1) and Cb (2) planes */
#define GBM_FORMAT_YUV444 __gbm_fourcc_code('Y', 'U', '2', '4') /* non-subsampled Cb (1) and Cr (2) planes */
#define GBM_FORMAT_YVU444 __gbm_fourcc_code('Y', 'V', '2', '4') /* non-subsampled Cr (1) and Cb (2) planes */
struct gbm_format_name_desc {
char name[5];
};
/**
* Flags to indicate the intended use for the buffer - these are passed into
* gbm_bo_create(). The caller must set the union of all the flags that are
* appropriate
*
* \sa Use gbm_device_is_format_supported() to check if the combination of format
* and use flags are supported
*/
enum gbm_bo_flags {
/**
* Buffer is going to be presented to the screen using an API such as KMS
*/
GBM_BO_USE_SCANOUT = (1 << 0),
/**
* Buffer is going to be used as cursor
*/
GBM_BO_USE_CURSOR = (1 << 1),
/**
* Deprecated
*/
GBM_BO_USE_CURSOR_64X64 = GBM_BO_USE_CURSOR,
/**
* Buffer is to be used for rendering - for example it is going to be used
* as the storage for a color buffer
*/
GBM_BO_USE_RENDERING = (1 << 2),
/**
* Buffer can be used for gbm_bo_write. This is guaranteed to work
* with GBM_BO_USE_CURSOR, but may not work for other combinations.
*/
GBM_BO_USE_WRITE = (1 << 3),
/**
* Buffer is linear, i.e. not tiled.
*/
GBM_BO_USE_LINEAR = (1 << 4),
/**
* Buffer is protected, i.e. encrypted and not readable by CPU or any
* other non-secure / non-trusted components nor by non-trusted OpenGL,
* OpenCL, and Vulkan applications.
*/
GBM_BO_USE_PROTECTED = (1 << 5),
/**
* The buffer will be used for front buffer rendering. On some
* platforms this may (for example) disable framebuffer compression
* to avoid problems with compression flags data being out of sync
* with pixel data.
*/
GBM_BO_USE_FRONT_RENDERING = (1 << 6),
/**
* Allow the driver to select fixed-rate compression parameters.
*/
GBM_BO_FIXED_COMPRESSION_DEFAULT = (1 << 7),
/**
* Fixed-rate compression: at least 1bpc, less than 2bpc
*/
GBM_BO_FIXED_COMPRESSION_1BPC = (2 << 7),
/**
* Fixed-rate compression: at least 2bpc, less than 3bpc
*/
GBM_BO_FIXED_COMPRESSION_2BPC = (3 << 7),
/**
* Fixed-rate compression: at least 3bpc, less than 4bpc
*/
GBM_BO_FIXED_COMPRESSION_3BPC = (4 << 7),
/**
* Fixed-rate compression: at least 4bpc, less than 5bpc
*/
GBM_BO_FIXED_COMPRESSION_4BPC = (5 << 7),
/**
* Fixed-rate compression: at least 5bpc, less than 6bpc
*/
GBM_BO_FIXED_COMPRESSION_5BPC = (6 << 7),
/**
* Fixed-rate compression: at least 6bpc, less than 7bpc
*/
GBM_BO_FIXED_COMPRESSION_6BPC = (7 << 7),
/**
* Fixed-rate compression: at least 7bpc, less than 8bpc
*/
GBM_BO_FIXED_COMPRESSION_7BPC = (8 << 7),
/**
* Fixed-rate compression: at least 8bpc, less than 9bpc
*/
GBM_BO_FIXED_COMPRESSION_8BPC = (9 << 7),
/**
* Fixed-rate compression: at least 9bpc, less than 10bpc
*/
GBM_BO_FIXED_COMPRESSION_9BPC = (10 << 7),
/**
* Fixed-rate compression: at least 10bpc, less than 11bpc
*/
GBM_BO_FIXED_COMPRESSION_10BPC = (11 << 7),
/**
* Fixed-rate compression: at least 11bpc, less than 12bpc
*/
GBM_BO_FIXED_COMPRESSION_11BPC = (12 << 7),
/**
* Fixed-rate compression: at least 12bpc, no maximum rate
*/
GBM_BO_FIXED_COMPRESSION_12BPC = (13 << 7),
/* next available value is (1 << 11) */
};
#define GBM_BO_FIXED_COMPRESSION_MASK (((1 << 11) - 1) & ~((1 << 7) - 1))
int
gbm_device_get_fd(struct gbm_device *gbm);
const char *
gbm_device_get_backend_name(struct gbm_device *gbm);
int
gbm_device_is_format_supported(struct gbm_device *gbm,
uint32_t format, uint32_t flags);
int
gbm_device_get_format_modifier_plane_count(struct gbm_device *gbm,
uint32_t format,
uint64_t modifier);
void
gbm_device_destroy(struct gbm_device *gbm);
struct gbm_device *
gbm_create_device(int fd);
struct gbm_bo *
gbm_bo_create(struct gbm_device *gbm,
uint32_t width, uint32_t height,
uint32_t format, uint32_t flags);
struct gbm_bo *
gbm_bo_create_with_modifiers(struct gbm_device *gbm,
uint32_t width, uint32_t height,
uint32_t format,
const uint64_t *modifiers,
const unsigned int count);
struct gbm_bo *
gbm_bo_create_with_modifiers2(struct gbm_device *gbm,
uint32_t width, uint32_t height,
uint32_t format,
const uint64_t *modifiers,
const unsigned int count,
uint32_t flags);
#define GBM_BO_IMPORT_WL_BUFFER 0x5501
#define GBM_BO_IMPORT_EGL_IMAGE 0x5502
#define GBM_BO_IMPORT_FD 0x5503
#define GBM_BO_IMPORT_FD_MODIFIER 0x5504
struct gbm_import_fd_data {
int fd;
uint32_t width;
uint32_t height;
uint32_t stride;
uint32_t format;
};
#define GBM_MAX_PLANES 4
struct gbm_import_fd_modifier_data {
uint32_t width;
uint32_t height;
uint32_t format;
uint32_t num_fds;
int fds[GBM_MAX_PLANES];
int strides[GBM_MAX_PLANES];
int offsets[GBM_MAX_PLANES];
uint64_t modifier;
};
struct gbm_bo *
gbm_bo_import(struct gbm_device *gbm, uint32_t type,
void *buffer, uint32_t flags);
/**
* Flags to indicate the type of mapping for the buffer - these are
* passed into gbm_bo_map(). The caller must set the union of all the
* flags that are appropriate.
*
* These flags are independent of the GBM_BO_USE_* creation flags. However,
* mapping the buffer may require copying to/from a staging buffer.
*
* See also: pipe_map_flags
*/
enum gbm_bo_transfer_flags {
/**
* Buffer contents read back (or accessed directly) at transfer
* create time.
*/
GBM_BO_TRANSFER_READ = (1 << 0),
/**
* Buffer contents will be written back at unmap time
* (or modified as a result of being accessed directly).
*/
GBM_BO_TRANSFER_WRITE = (1 << 1),
/**
* Read/modify/write
*/
GBM_BO_TRANSFER_READ_WRITE = (GBM_BO_TRANSFER_READ | GBM_BO_TRANSFER_WRITE),
};
void *
gbm_bo_map(struct gbm_bo *bo,
uint32_t x, uint32_t y, uint32_t width, uint32_t height,
uint32_t flags, uint32_t *stride, void **map_data);
void
gbm_bo_unmap(struct gbm_bo *bo, void *map_data);
uint32_t
gbm_bo_get_width(struct gbm_bo *bo);
uint32_t
gbm_bo_get_height(struct gbm_bo *bo);
uint32_t
gbm_bo_get_stride(struct gbm_bo *bo);
uint32_t
gbm_bo_get_stride_for_plane(struct gbm_bo *bo, int plane);
uint32_t
gbm_bo_get_format(struct gbm_bo *bo);
uint32_t
gbm_bo_get_bpp(struct gbm_bo *bo);
uint32_t
gbm_bo_get_offset(struct gbm_bo *bo, int plane);
struct gbm_device *
gbm_bo_get_device(struct gbm_bo *bo);
union gbm_bo_handle
gbm_bo_get_handle(struct gbm_bo *bo);
int
gbm_bo_get_fd(struct gbm_bo *bo);
uint64_t
gbm_bo_get_modifier(struct gbm_bo *bo);
int
gbm_bo_get_plane_count(struct gbm_bo *bo);
union gbm_bo_handle
gbm_bo_get_handle_for_plane(struct gbm_bo *bo, int plane);
int
gbm_bo_get_fd_for_plane(struct gbm_bo *bo, int plane);
int
gbm_bo_write(struct gbm_bo *bo, const void *buf, size_t count);
void
gbm_bo_set_user_data(struct gbm_bo *bo, void *data,
void (*destroy_user_data)(struct gbm_bo *, void *));
void *
gbm_bo_get_user_data(struct gbm_bo *bo);
void
gbm_bo_destroy(struct gbm_bo *bo);
struct gbm_surface *
gbm_surface_create(struct gbm_device *gbm,
uint32_t width, uint32_t height,
uint32_t format, uint32_t flags);
struct gbm_surface *
gbm_surface_create_with_modifiers(struct gbm_device *gbm,
uint32_t width, uint32_t height,
uint32_t format,
const uint64_t *modifiers,
const unsigned int count);
struct gbm_surface *
gbm_surface_create_with_modifiers2(struct gbm_device *gbm,
uint32_t width, uint32_t height,
uint32_t format,
const uint64_t *modifiers,
const unsigned int count,
uint32_t flags);
struct gbm_bo *
gbm_surface_lock_front_buffer(struct gbm_surface *surface);
void
gbm_surface_release_buffer(struct gbm_surface *surface, struct gbm_bo *bo);
int
gbm_surface_has_free_buffers(struct gbm_surface *surface);
void
gbm_surface_destroy(struct gbm_surface *surface);
char *
gbm_format_get_name(uint32_t gbm_format, struct gbm_format_name_desc *desc);
#ifdef __cplusplus
}
#endif
#endif
3rdparty/glvnd/README.md
Vendored
-11
View File
@@ -1,11 +0,0 @@
# glvnd vendor ABI headers
'libeglabi.h' and 'GLdispatchABI.h' from libglvnd (MIT), copied verbatim with their own licence
headers intact.
They are here because MobileGL implements the *vendor* half of glvnd's EGL ABI - the side a library
exposes so the system's 'libEGL.so.1', which IS glvnd, can dispatch to it. The distribution ships
the runtime but not these headers in the base image, and a vendored copy of two MIT headers is a
smaller dependency than a build-time download of a source tree.
Upstream ABI version implemented: 'EGL_VENDOR_ABI_MAJOR_VERSION' 0 (the header pins it).
3rdparty/glvnd/include/glvnd/GLdispatchABI.h
Vendored
-141
View File
@@ -1,141 +0,0 @@
/*
* Copyright (c) 2013, NVIDIA CORPORATION.
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and/or associated documentation files (the
* "Materials"), to deal in the Materials without restriction, including
* without limitation the rights to use, copy, modify, merge, publish,
* distribute, sublicense, and/or sell copies of the Materials, and to
* permit persons to whom the Materials are furnished to do so, subject to
* the following conditions:
*
* The above copyright notice and this permission notice shall be included
* unaltered in all copies or substantial portions of the Materials.
* Any additions, deletions, or changes to the original source files
* must be clearly indicated in accompanying documentation.
*
* THE MATERIALS ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
* IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
* CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
* TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
* MATERIALS OR THE USE OR OTHER DEALINGS IN THE MATERIALS.
*/
#include <GL/gl.h>
#if !defined(__GL_DISPATCH_ABI_H)
#define __GL_DISPATCH_ABI_H
#if defined(__cplusplus)
extern "C" {
#endif
/*!
* \defgroup gldispatchabi GL dispatching ABI
*
* This is not a complete ABI, but rather a fragment common to the libEGL and
* libGLX ABIs. Changes to this file should be accompanied by a version bump to
* these client ABIs.
*/
/*!
* Thread-local implementation used by libglvnd. This is passed into the patch
* function callback via the type parameter.
*
* For most architectures, the vendor library can ignore this parameter, since
* it will always be the same value. It's used for systems like ARM, where the
* stubs might be use the ARM or Thumb instruction sets.
*
* The stub type does not make any distinction between TLS and TSD stubs. The
* entire purpose of entrypoint rewriting is to skip the dispatch table in
* libGLdispatch.so, so it doesn't matter how that dispatch table is stored.
*/
enum {
/*!
* Indicates that the stubs aren't defined in assembly. For example, if the
* dispatch stubs are written in C. Vendor libraries generally won't see
* this value.
*/
__GLDISPATCH_STUB_UNKNOWN,
/*!
* Used for stubs on x86 systems.
*/
__GLDISPATCH_STUB_X86,
/*!
* Used for stubs on x86-64 systems.
*/
__GLDISPATCH_STUB_X86_64,
/*!
* Used for stubs on ARMv7, using the Thumb instruction set.
*/
__GLDISPATCH_STUB_ARMV7_THUMB,
/*!
* Used for stubs on ARMv7, using the normal ARM instruction set.
*/
__GLDISPATCH_STUB_ARMV7_ARM,
/*!
* Used for stubs on ARMv8/aarch64.
*/
__GLDISPATCH_STUB_AARCH64,
/*!
* Used for stubs on x32 builds (x86-64 with 32-bit pointers).
*/
__GLDISPATCH_STUB_X32,
/*!
* Used for stubs on PPC64 systems.
*/
__GLDISPATCH_STUB_PPC64,
/*!
* Used for stubs on PPC64LE systems. Same as PPC64, for compatibility.
*/
__GLDISPATCH_STUB_PPC64LE = __GLDISPATCH_STUB_PPC64,
/*!
* Used for stubs on LOONGARCH/loongarch64.
*/
__GLDISPATCH_STUB_LOONGARCH64,
};
/*!
* A callback function called by the vendor library to fetch the address of an
* entrypoint.
*
* The function returns two pointers, one writable and one executable. The two
* pointers may or may not be the same virtual address, but they will both be
* mappings of the same physical memory.
*
* The vendor library should write its entrypoint to the address returned by
* \p writePtr, but should use the address from \p execPtr for things like
* calculating PC-relative offsets.
*
* Note that if this function fails, then the vendor library can still try to
* patch other entrypoints.
*
* Note that on ARM, the low-order bit of both \c execPtr and \p writePtr will
* be zero, even if the stub uses the thumb instruction set. The vendor library
* should use the \c type parameter of \c initiatePatch to determine which
* instruction set to use.
*
* \param funcName The function name.
* \param[out] writePtr The pointer that the vendor library can write to.
* \param[out] execPtr The pointer to the executable code.
* \return GL_TRUE if the entrypoint exists, or GL_FALSE if it doesn't.
*/
typedef GLboolean (*DispatchPatchLookupStubOffset)(const char *funcName,
void **writePtr, const void **execPtr);
#if defined(__cplusplus)
}
#endif
#endif // __GL_DISPATCH_ABI_H
3rdparty/glvnd/include/glvnd/libeglabi.h
Vendored
-464
View File
@@ -1,464 +0,0 @@
/*
* Copyright (c) 2013, NVIDIA CORPORATION.
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and/or associated documentation files (the
* "Materials"), to deal in the Materials without restriction, including
* without limitation the rights to use, copy, modify, merge, publish,
* distribute, sublicense, and/or sell copies of the Materials, and to
* permit persons to whom the Materials are furnished to do so, subject to
* the following conditions:
*
* The above copyright notice and this permission notice shall be included
* unaltered in all copies or substantial portions of the Materials.
* Any additions, deletions, or changes to the original source files
* must be clearly indicated in accompanying documentation.
*
* THE MATERIALS ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
* IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
* CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
* TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
* MATERIALS OR THE USE OR OTHER DEALINGS IN THE MATERIALS.
*/
#if !defined(__LIB_EGL_ABI_H)
#define __LIB_EGL_ABI_H
#include <stdint.h>
#include <EGL/egl.h>
#include <EGL/eglext.h>
#include "glvnd/GLdispatchABI.h"
#if defined(__cplusplus)
extern "C" {
#endif
/*!
* \defgroup eglvendorabi EGL Vendor ABI
*
* Definition of ABI exported by libEGL.so to libEGL_VENDOR.so libraries.
*
* Each vendor is associated with three distinct dispatch table types:
*
* - static EGL dispatch table: this is the fixed list of EGL 1.5 entrypoints
* provided by the vendor at load time during the initial handshake.
* - dynamic EGL dispatch table: this is a structure allocated by the API
* library at runtime used to manage EGL extension functions which are not
* present in the static table.
* - core GL dispatch table: this is a structure maintained by the API library
* which contains both GL core (static) and GL extension (dynamic) functions.
*
* @{
*/
/*
* Rendering API handling:
*
* libEGL only supports OpenGL and OpenGL ES, not OpenVG. If OpenVG or any
* other API is added, then the major version number will be incremented.
*
* When the application calls eglBindAPI, libEGL will forward the call to every
* vendor library. In addition, a vendor library can query the current API from
* libEGL using the getCurrentApi callback.
*
* Vendor libraries are not required to support both GL and GLES, but they must
* be able to deal with either one as the current rendering API. If a vendor
* doesn't support the current API, then it should return an error from
* eglCreateContext.
*/
/*!
* Current version of the ABI.
*
* This version number contains a major number in the high-order 16 bits, and
* a minor version number in the low-order 16 bits.
*
* The major version number is incremented when an interface change will break
* backwards compatibility with existing vendor libraries. The minor version
* number is incremented when there's a change but existing vendor libraries
* will still work.
*/
#define EGL_VENDOR_ABI_MAJOR_VERSION ((uint32_t) 0)
#define EGL_VENDOR_ABI_MINOR_VERSION ((uint32_t) 2)
#define EGL_VENDOR_ABI_VERSION ((EGL_VENDOR_ABI_MAJOR_VERSION << 16) | EGL_VENDOR_ABI_MINOR_VERSION)
static inline uint32_t EGL_VENDOR_ABI_GET_MAJOR_VERSION(uint32_t version)
{
return version >> 16;
}
static inline uint32_t EGL_VENDOR_ABI_GET_MINOR_VERSION(uint32_t version)
{
return version & 0xFFFF;
}
/*!
* This opaque structure stores function pointers for EGL extension functions.
* It is allocated at runtime by the API library. Vendor-provided dispatch
* functions retrieve and operate on this structure using the API below.
*/
typedef struct __EGLvendorInfoRec __EGLvendorInfo;
/****************************************************************************
* API library exports *
****************************************************************************/
typedef struct __EGLapiExportsRec {
/************************************************************************
* The following routines are used by vendor-implemented EGL dispatch
* functions to lookup and call into the right vendor.
************************************************************************/
/*!
* This function must be called at the start of every EGL dispatch stub. It
* performs any necessary per-call bookkeeping.
*/
void (* threadInit) (void);
EGLenum (* getCurrentApi)(void);
/*!
* This function retrieves the appropriate current dynamic dispatch table,
* if a GL context is current. Otherwise, this returns NULL.
*/
__EGLvendorInfo *(*getCurrentVendor)(void);
/*!
* This retrieves the current context for this thread.
*/
EGLContext (*getCurrentContext)(void);
/*!
* Returns the current display for this thread.
*/
EGLDisplay (*getCurrentDisplay)(void);
/*!
* Returns the current drawable for this thread.
*/
EGLSurface (*getCurrentSurface)(EGLint readDraw);
/*!
* This function retrieves an entry point from the dynamic dispatch table
* given an index into the table.
*/
__eglMustCastToProperFunctionPointerType (*fetchDispatchEntry) (__EGLvendorInfo *dynDispatch, int index);
/*!
* Sets the last error for the current thread. The error will be returned
* the next time the app calls eglGetError().
*
* This function will override a call to \c setLastVendor, and vice-versa.
*/
void (* setEGLError) (EGLint errorCode);
/*!
* Notifies libEGL about the vendor library that an EGL function is
* dispatched to. This is used to look up the last EGL error code from a
* vendor.
*
* A vendor library may generate an EGL error asynchronously, if it
* offloads some EGL functions onto a worker thread. In that case, calling
* \c setEGLError to set the last error would not work.
*
* When an EGL dispatch stubs finds the vendor library, it must call this
* function before it dispatches the function call.
*
* This function will override a call to \c setEGLError, and vice-versa.
*
* \param vendor The vendor library of the current EGL function call.
* \return EGL_TRUE on success, or EGL_FALSE on failure.
*/
EGLBoolean (* setLastVendor) (__EGLvendorInfo *vendor);
/************************************************************************
* These routines are used by vendor dispatch functions to look up
* and add mappings between various objects and vendors.
************************************************************************/
// As far as I can tell, all EGL functions that take a context or drawable
// also take an EGLDisplay. So, we don't need any extra functions for
// mapping a context/surface/whatever to a EGLDisplay or vendor.
/*!
* Returns the EGL vendor for an EGLDisplay handle.
*/
__EGLvendorInfo *(*getVendorFromDisplay)(EGLDisplay dpy);
/*!
* Returns the EGL vendor for an EGLDeviceEXT handle.
*/
__EGLvendorInfo *(*getVendorFromDevice)(EGLDeviceEXT dev);
/**
* Sets the EGL vendor for an EGLDeviceEXT handle. The dispatch stub for
* any function that returns an EGLDeviceEXT handle should call this.
*
* Supported since ABI version 1.2.
*/
EGLBoolean (* setVendorForDevice)(EGLDeviceEXT dev, __EGLvendorInfo *vendor);
} __EGLapiExports;
/*****************************************************************************
* API library imports *
*****************************************************************************/
/*!
* The enum values accepted by \c __EGLapiImports::getVendorString.
*/
enum
{
/*!
* The set of platform extensions that the vendor supports.
*
* Platform extensions typically just add enums to the existing
* eglGetPlatformDisplay function, so we don't need any additional logic
* or special handling from libEGL itself.
*
* As a result, vendor libraries can add these extensions without having
* to modify libEGL to match.
*/
__EGL_VENDOR_STRING_PLATFORM_EXTENSIONS,
};
/*!
* This structure stores required and optional vendor library callbacks.
*/
typedef struct __EGLapiImportsRec {
/**
* Creates an EGLDisplay. This function is used to handle both
* \c eglGetDisplay and \c eglGetPlatformDisplay.
*
* For some platform types, libEGL may be able to identify a specific
* vendor to use.
*
* If libEGL can't figure out which vendor to use on its own, then it will
* go through the list of available vendor libraries and call this function
* until one succeeds.
*
* If the application calls eglGetPlatformDisplay, then the parameters are
* passed through from the application.
*
* If the application calls eglGetDisplay, and the native display handle is
* not \c EGL_DEFAULT_DISPLAY, then libEGL will try to guess a platform
* type, and will pass that platform to the vendor library.
*
* Lastly, if eglGetDisplay is called with \c EGL_DEFAULT_DISPLAY, then
* libEGL will call into each vendor library with \p platform set to
* \c EGL_NONE. The vendor library can then select a default display to
* return.
*
* In all cases, if the vendor library can't find a matching EGLDisplay,
* then it should return \c EGL_NO_DISPLAY. Any errors should be reported
* through the vendor's \c eglGetError function.
*/
EGLDisplay (* getPlatformDisplay) (EGLenum platform, void *nativeDisplay,
const EGLAttrib *attrib_list);
/*!
* Checks if the vendor library supports a given client API (that is, the
* API value passed to \c eglBindAPI).
*/
EGLBoolean (* getSupportsAPI) (EGLenum api);
/*!
* (OPTIONAL) Returns a string from the vendor library. This is used for
* anything that isn't available from eglQueryString.
*/
const char * (* getVendorString) (int name);
/*
* NOTE: libEGL will load all of the vendor libraries up front, so it
* handles extension functions slightly differently than EGL.
*/
/*!
* This retrieves the pointer to the real EGL or core GL function.
*
* \param procName The name of the function.
* \return A pointer to a function, or \c NULL if the vendor does not
* support the function.
*/
void * (* getProcAddress) (const char *procName);
/*!
* This retrieves vendor-neutral functions which use the
* __EGLdispatchTableDynamic API above to dispatch to the correct vendor.
*
* A vendor library must provide a dispatch function for all EGL display
* extension functions that it supports.
*
* Client extension functions cannot be dispatched based on an EGDisplay,
* so they must be handled in libEGL itself.
*
* \param procName The name of the function.
* \return A pointer to a function, or \c NULL if the vendor does not
* support the function or \p procName is not a EGL display function.
*/
void * (*getDispatchAddress) (const char *procName);
/*!
* This notifies the vendor library which dispatch table index is
* assigned to a particular EGL extension function.
*/
void (*setDispatchIndex) (const char *procName, int index);
/*
* The vendor library may use the isPatchSupported, initiatePatch,
* releasePatch, and patchThreadAttach callbacks to re-write libglvnd's
* entrypoints at make current time, provided no other contexts are current
* and the TLS model supports this functionality. This is a performance
* optimization that may not be available at runtime; the vendor library
* must not depend on this functionality for correctness.
*
* To use this optimization, the vendor library must provide at least the
* isPatchSupported and initiatePatch entrypoints.
*
* Note that these functions are identical to the ones used in GLX.
*/
/*!
* (OPTIONAL) Checks to see if the vendor library supports patching the
* given stub type and size.
*
* \param type The type of entrypoints. This will be a one of the
* __GLDISPATCH_STUB_* values.
* \param stubSize The maximum size of the stub that the vendor library can
* write, in bytes.
* \param lookupStubOffset A callback into libglvnd to look up the address
* of each entrypoint.
*/
GLboolean (* isPatchSupported)(int type, int stubSize);
/*!
* (OPTIONAL) Called by libglvnd to request that a vendor library patch its
* top-level entrypoints.
*
* The vendor library should use the \p lookupStubOffset callback to find
* the addresses of each entrypoint.
*
* This function may be called more than once to patch multiple sets of
* entrypoints. For example, depending on how they're built, libOpenGL.so
* or libGL.so may have their own entrypoints that are separate functions
* from the ones in libGLdispatch.
*
* Note that during this call is the only time that the entrypoints can be
* modified. After the call to \c initiatePatch returns, the vendor library
* should treat the entrypoints as read-only.
*
* \param type The type of entrypoints. This will be a one of the
* __GLDISPATCH_STUB_* values.
* \param stubSize The maximum size of the stub that the vendor library can
* write, in bytes.
* \param lookupStubOffset A callback into libglvnd to look up the address
* of each entrypoint.
*
* \return GL_TRUE if the vendor library supports patching with this type
* and size.
*/
GLboolean (*initiatePatch)(int type,
int stubSize,
DispatchPatchLookupStubOffset lookupStubOffset);
/*!
* (OPTIONAL) Called by libglvnd to notify the current vendor that it no
* longer owns the top-level entrypoints.
*
* Libglvnd will take care of the restoring the entrypoints back to their
* original state. The vendor library must not try to modify them.
*/
void (*releasePatch)(void);
/*!
* (OPTIONAL) Called at the start of window-system functions (GLX and EGL).
* This callback allows vendor libraries to perform any per-thread
* initialization.
*
* This is basically a workaround for broken applications. A lot of apps
* will make one or more invalid GLX/EGL calls on a thread (often including
* a MakeCurrent with invalid parameters), and then will try to call an
* OpenGL function.
*
* A non-libglvnd-based driver would be able to initialize any thread state
* even on a bogus GLX call, but with libglvnd, those calls wouldn't get
* past libGLX.
*
* This function is optional. If it's \c NULL, then libGLdispatch will
* simply ignore it.
*
* \note This function may be called concurrently from multiple threads.
*/
void (*patchThreadAttach)(void);
/*!
* (OPTIONAL) Tries to determine the platform type for a native display.
*
* If the vendor library provides this function, then libglvnd will call it
* to determine which platform to use for a native display handle in
* eglGetDisplay.
*
* If no vendor library identifies the platform, then libglvnd will fall
* back to its own platform detection logic.
*
* Libglvnd can call this function for any native display handle except
* \c EGL_DEFAULT_DISPLAY.
*
* No matter what the value of \p native_display, the vendor library must
* not crash, and must not return a false match. If the vendor library
* can't identify the display, then it must return \c EGL_NONE.
*
* In particular, that means that a vendor library must not return any sort
* of default or fallback platform.
*
* \param native_display The native display handle passed to eglGetDisplay.
* \return Either a platform type enum or EGL_NONE.
*/
EGLenum (* findNativeDisplayPlatform) (void *native_display);
} __EGLapiImports;
/*****************************************************************************/
#define __EGL_MAIN_PROTO_NAME "__egl_Main"
typedef EGLBoolean (* __PFNEGLMAINPROC) (uint32_t version, const __EGLapiExports *exports,
__EGLvendorInfo *vendor, __EGLapiImports *imports);
/*!
* Vendor libraries must export a function called __egl_Main() with the
* following prototype.
*
* This function also performs a handshake based on the ABI version number.
* Vendor libraries can optionally use the version number to support older
* versions of the ABI.
*
* \param[in] version The ABI version. The upper 16 bits contains the major version
* number, and the lower 16 bits contains the minor version number.
*
* \param[in] exports The table of functions provided by libEGL. This pointer will
* remain valid for as long as the vendor is loaded.
*
* \param[in] vendor The opaque pointer used to identify this vendor library. This
* may be used in future versions to provide additional per-vendor information.
*
* \param[out] imports The function table that the vendor library should fill
* in. The vendor library must assign every non-optional function in the
* struct.
*
* \return True on success. If the vendor library does not support the
* requested ABI version or if some other error occurs, then it should return
* False.
*/
EGLBoolean __egl_Main(uint32_t version, const __EGLapiExports *exports,
__EGLvendorInfo *vendor, __EGLapiImports *imports);
/*!
* @}
*/
#if defined(__cplusplus)
}
#endif
#endif /* __LIB_EGL_ABI_H */
CMakeLists.txt
-561
View File
@@ -14,35 +14,6 @@ option(MOBILEGL_ENABLE_TRACY "Enable tracy for profiling"
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)
option(MOBILEGL_BUILD_EXTMEM_PROBE "Package tools/spikes/extmem_probe as libMobileGLExtmemProbe.so for the trace APK's exec hook (P11 A3, Android only)" OFF)
option(MOBILEGL_EXTMEM_PROBE_AS_SERVER "Spike only (P11 B2 step 1): also package the probe as libMobileGLServer.so, the real server as libMobileGLServerReal.so" 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")
@@ -187,61 +158,15 @@ 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
@@ -313,8 +238,6 @@ set(SOURCE_FILES
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
@@ -403,10 +326,7 @@ set(SOURCE_FILES
MobileGL/MG_Impl/GLXImpl/LookUp/LookUp.cpp
MobileGL/MG_Impl/EGLImpl/Exporting/Definitions.cpp
MobileGL/MG_Impl/EGLImpl/Exporting/GlvndVendor.cpp
MobileGL/MG_Impl/EGLImpl/EGLImpl.cpp
MobileGL/MG_Impl/EGLImpl/WaylandWindow.cpp
# @INSERTION_POINT:SOURCE_FILE_GLIMPL@ #
MobileGL/MG_Impl/GLImpl/Sampler/Validators.cpp
@@ -437,14 +357,10 @@ set(SOURCE_FILES
MobileGL/MG_Backend/Init.cpp
MobileGL/MG_Backend/BackendObject.cpp
MobileGL/MG_Backend/HostFrameBridge.cpp
MobileGL/MG_Backend/GbmFrameChannel.cpp
MobileGL/MG_Backend/DirectGLES/DirectGLES.cpp
MobileGL/MG_Backend/DirectGLES/BackendObject_DirectGLES.cpp
MobileGL/MG_Backend/DirectGLES/Utils.cpp
MobileGL/MG_Backend/DirectGLES/Managers.cpp
MobileGL/MG_Backend/DirectGLES/HostFrameTarget.cpp
MobileGL/MG_Backend/DirectGLES/MultiDraw.cpp
MobileGL/MG_Backend/DirectVulkan/DirectVulkan.cpp
@@ -502,194 +418,6 @@ 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
# P9 W3: the server's log forward - a queue and a sender thread, graded by severity
# (<= WARN lossy, >= ERROR lossless and paced), so no logging thread writes the socket.
MobileGL/MG_Remote/Transport/LogForward.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
# P11 A1: the adopt tier settled at the handshake from the knob and the data plane, by
# both roles (so SERVER-partition code in the link ratchet, not the client's tracker).
MobileGL/MG_Remote/Transport/AdoptTier.cpp
# P11 B2: T0 - the client's AHardwareBuffer store and its hop descriptor (both roles).
MobileGL/MG_Remote/Transport/AdoptT0.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/DmaBufImport.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
# P11 PAIR: a socket client's control and aux connections paired by the nonce each
# presents first (PairBind), not by arrival order - both unix supervisors take pairs here.
MobileGL/MG_Remote/Server/PairAcceptor.cpp
# P11 B2: T0's Offers on the aux socket, matched to their map_persistent records by seq.
MobileGL/MG_Remote/Server/AdoptInbox.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
@@ -704,14 +432,6 @@ if (ANDROID)
MobileGL/MG_Util/SelfTest/DriverPostJni.cpp
MobileGL/MG_Util/SelfTest/DriverBenchJni.cpp
)
if (MOBILEGL_BUILD_DISAGGREGATED)
# P12 (on-screen server window): the 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)
@@ -748,29 +468,11 @@ set(MOBILEGL_COMPILE_DEF
-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}
@@ -781,16 +483,6 @@ set(MOBILEGL_INCLUDE_DIR
${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)
# The vendored glvnd vendor-ABI headers (3rdparty/glvnd): the entry point a vendor library
# exposes so the system libEGL - which IS glvnd - can dispatch to it.
list(APPEND MOBILEGL_INCLUDE_DIR ${CMAKE_SOURCE_DIR}/3rdparty/glvnd/include)
endif()
add_library(${CMAKE_PROJECT_NAME} SHARED
${SOURCE_FILES}
)
@@ -826,17 +518,6 @@ target_link_libraries(${CMAKE_PROJECT_NAME}
${MOBILEGL_LINK_LIBRARIES}
)
# A LINUX BUILD COMPILES THE DirectVulkan BACKEND BUT HAS NO VULKAN LOADER TO LINK AGAINST, so the
# resulting shared library carries undefined vk* symbols - and that is not theoretical: glvnd dlopens
# this file as the EGL vendor with RTLD_NOW, so the load fails outright with "undefined symbol:
# vkGetQueryPoolResults" (measured on the phone's container). Android links the loader already; on
# Linux the caller passes the runtime's own libvulkan.so.1, and leaving the variable empty keeps the
# previous behaviour for every build that has no Vulkan runtime to point at.
set(MOBILEGL_VULKAN_LOADER "" CACHE FILEPATH "Vulkan loader (libvulkan.so.1) to link into the GL library")
if (UNIX AND NOT ANDROID AND MOBILEGL_VULKAN_LOADER)
target_link_libraries(${CMAKE_PROJECT_NAME} PRIVATE ${MOBILEGL_VULKAN_LOADER})
endif()
target_compile_definitions(${CMAKE_PROJECT_NAME}
PUBLIC
${MOBILEGL_COMPILE_DEF}
@@ -903,68 +584,6 @@ if(NOT ANDROID)
)
endif()
# ---------------------------------------------------------------------------
# MobileGLGbm: the GBM drop-in the container's compositor loads.
#
# kwin - the Wayland compositor in the container half of the split - allocates the
# buffers it renders into and scans out through libgbm, and the dma-buf fds it gets
# back are what the Anland display producer ships to the phone. Mesa's libgbm cannot
# serve that: its buffers belong to the host GPU, and the phone would receive a copy
# through a path that was never designed to carry one. This target is the library
# that is loaded in its place, under the name a loader looks for.
#
# It is deliberately NOT part of libMobileGL.so. The compositor needs one file named
# libgbm.so that it loads instead of Mesa's, and folding this code into the GL
# library would put a second GL frontend, a second Vulkan instance and a second
# glslang in the compositor's address space to serve an API that shares none of them.
#
# The include paths below are borrowed rather than linked. Includes.h - which this
# library includes for the MobileGL types and the MGLOG macros - pulls in the GL,
# EGL, Vulkan, glslang, SPIRV-Cross and xxHash HEADERS transitively, and headers are
# all this library wants from them: linking any of those static libraries into a
# libgbm would embed a copy of each in a process that already has one.
#
# -Bsymbolic-functions, for the same reason the main target carries it: the point of
# this library is to REPLACE a libgbm that may already be loaded in the process, so
# every internal reference has to bind to this file's own definitions rather than to
# whatever else the process has under the same names.
# ---------------------------------------------------------------------------
add_library(MobileGLGbm SHARED
MobileGL/MG_Gbm/GbmDevice.cpp
# The display host's socket protocol, kept in its own translation unit so that the
# allocation paths never have to know how a frame arrives - only that one did.
MobileGL/MG_Gbm/GbmHostChannel.cpp
MobileGL/MG_Gbm/GbmApi.cpp
# MGLOG_I/W/E expand to a call to MobileGL::MG_Util::Debug::Log, and this is the
# one translation unit that defines it. It is compiled in rather than linked from
# libMobileGL.so because this library has to load into a compositor that has no
# libMobileGL in it at all - and because a libgbm with an undefined symbol is a
# library that fails on the first diagnostic rather than at a link step somebody
# could have read.
MobileGL/MG_Util/Debug/Log.cpp
)
# The vendored gbm.h first: this library implements THAT declaration set, and a
# system <gbm.h> from another Mesa version on the include path ahead of it would
# change the ABI under the implementations in GbmApi.cpp.
target_include_directories(MobileGLGbm PRIVATE
${CMAKE_SOURCE_DIR}/3rdparty/gbm/include
${MOBILEGL_INCLUDE_DIR}
${CMAKE_SOURCE_DIR}/3rdparty/glslang
${CMAKE_SOURCE_DIR}/3rdparty/SPIRV-Cross
${CMAKE_SOURCE_DIR}/3rdparty/xxHash
${CMAKE_SOURCE_DIR}/3rdparty/Vulkan-Headers/include
)
set_target_properties(MobileGLGbm PROPERTIES
OUTPUT_NAME gbm
POSITION_INDEPENDENT_CODE ON
)
if (UNIX AND NOT APPLE)
target_link_options(MobileGLGbm PRIVATE "LINKER:-Bsymbolic-functions")
endif()
if (TRACY_ENABLE)
target_link_libraries(${CMAKE_PROJECT_NAME} PUBLIC Tracy::TracyClient)
target_link_libraries(${CMAKE_PROJECT_NAME}_s PUBLIC Tracy::TracyClient)
@@ -972,19 +591,6 @@ if (TRACY_ENABLE)
target_compile_definitions(${CMAKE_PROJECT_NAME}_s PUBLIC -DTRACY_ENABLE)
endif ()
# GLVND, AND WHY THIS IS A LINKER FLAG RATHER THAN A VISIBILITY ONE.
#
# MobileGL can serve as a glvnd EGL vendor - the library the system's libEGL.so.1 dispatches to -
# and a vendor must hand glvnd ITS OWN entry points: glvnd calls whatever address it is given, so
# an address that resolves to another libEGL in the process is a call back into the dispatcher.
# With default visibility every reference inside this library resolves against the whole process,
# and a process that loaded the system libEGL first wins. Marking the entry points protected says
# the same thing in the source, except the platform's own GL/EGL headers declare them default and
# the two visibilities do not mix; this flag is that promise made by the linker instead.
if (UNIX AND NOT APPLE)
target_link_options(${CMAKE_PROJECT_NAME} PRIVATE "LINKER:-Bsymbolic-functions")
endif()
if (ANDROID)
target_link_libraries(${CMAKE_PROJECT_NAME} PUBLIC
android
@@ -1093,170 +699,3 @@ endif()
if (ANDROID AND MOBILEGL_BUILD_INTEGRATION_TEST)
add_subdirectory(MobileGL/MG_IntegrationTest)
endif()
# The replay runner also builds for Android: an adb-shell executable that can
# dial a render server on the device (unix or TCP) without any Activity.
if (ANDROID AND MOBILEGL_BUILD_TRACE_REPLAY)
add_subdirectory(tools/trace_replay)
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()
if (ANDROID AND MOBILEGL_BUILD_EXTMEM_PROBE)
# P11 A3 (open question 3): the spike-B external-memory probe, exec'd from the trace
# app's own process by the spike hook (`--es mobilegl_spike_spawn
# libMobileGLExtmemProbe.so`), so its rows answer for the untrusted_app domain. The
# same PIE-executable-named-like-a-library shape as MobileGLServerSpike above; it
# links nothing from MobileGL.
add_executable(MobileGLExtmemProbe
${CMAKE_CURRENT_SOURCE_DIR}/tools/spikes/extmem_probe/extmem_probe.cpp)
set_target_properties(MobileGLExtmemProbe PROPERTIES
PREFIX "lib"
SUFFIX ".so"
OUTPUT_NAME "MobileGLExtmemProbe"
POSITION_INDEPENDENT_CODE ON)
target_compile_options(MobileGLExtmemProbe PRIVATE -fPIE)
target_link_options(MobileGLExtmemProbe PRIVATE -pie)
target_link_libraries(MobileGLExtmemProbe PRIVATE vulkan EGL GLESv3 android log)
if (CMAKE_LIBRARY_OUTPUT_DIRECTORY)
set_target_properties(MobileGLExtmemProbe PROPERTIES
RUNTIME_OUTPUT_DIRECTORY "${CMAKE_LIBRARY_OUTPUT_DIRECTORY}")
endif()
if (MOBILEGL_EXTMEM_PROBE_AS_SERVER)
# P11 B2 step 1, spike APKs only: MobileGLServerService execs `libMobileGLServer.so
# <endpoint> --serve` and B1's broker connects to whatever that listens on, so the probe
# takes the server's file name and answers "does a client's AHardwareBuffer cross this
# route into the server app" on the real route (tools/spikes/extmem_probe, route mode).
if (TARGET MobileGLServer)
set_target_properties(MobileGLServer PROPERTIES OUTPUT_NAME "MobileGLServerReal")
endif()
add_executable(MobileGLExtmemProbeAsServer
${CMAKE_CURRENT_SOURCE_DIR}/tools/spikes/extmem_probe/extmem_probe.cpp)
set_target_properties(MobileGLExtmemProbeAsServer PROPERTIES
PREFIX "lib"
SUFFIX ".so"
OUTPUT_NAME "MobileGLServer"
POSITION_INDEPENDENT_CODE ON)
target_compile_options(MobileGLExtmemProbeAsServer PRIVATE -fPIE)
target_link_options(MobileGLExtmemProbeAsServer PRIVATE -pie)
target_link_libraries(MobileGLExtmemProbeAsServer PRIVATE vulkan EGL GLESv3 android log)
if (CMAKE_LIBRARY_OUTPUT_DIRECTORY)
set_target_properties(MobileGLExtmemProbeAsServer PROPERTIES
RUNTIME_OUTPUT_DIRECTORY "${CMAKE_LIBRARY_OUTPUT_DIRECTORY}")
endif()
endif()
endif()
# The GBM library carries the tree's logger, which reaches Android's own log. The main target gets
# these libraries in its own Android block; a library built from the same sources needs them for the
# same reason, and without them it is the LINK that fails rather than anything in the code.
if (ANDROID)
target_link_libraries(MobileGLGbm PRIVATE log android)
endif()
MobileGL/Config.h
+4 -419
View File
@@ -14,7 +14,7 @@ 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, 8, 0, "-dev", VersionType::Development};
inline const VersionStringFormatAttrib DefaultVersionStringFormatAttrib = {2, 2, 0, true, true};
inline const Uint64 CacheVersion = 0;
@@ -214,12 +214,9 @@ namespace MobileGL::MG_Config {
// 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 lands GPU-ordered through the backend's resident-subdata op
// (BufferObject::LandBytesIntoResidentStore, since 0ee3384b: an in-place write
// tore the frames still reading the old bytes) - still no driver-mediated write
// into the busy mutable store, which on this class of Mali driver stalls the
// thread or ghost-copies the whole arena, and the arena stops costing its size
// again in RAM.
// 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
@@ -331,418 +328,6 @@ namespace MobileGL::MG_Config {
// 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
Host = 2, // a window surface draws into frames the DISPLAY HOST owns; the host presents
};
// IpcTable::AdoptTier when MOBILEGL_IPC_ADOPT_TIER is unset (or unparseable): T0 by default,
// with QUIET fallbacks. Not a tier a user can type - the knob admits 0..2.
inline constexpr Uint32 kAdoptTierUnset = 3;
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_PBO_READBACK_SYNC (P9 W1, MG_Remote/CONTRACT-P9.md §1): 1 = a glReadPixels
// or glGetTexImage into a bound GL_PIXEL_PACK_BUFFER takes the reply-slot form again -
// the client waits for the pixels and uploads them into the buffer itself, as before P9.
// 0 (default) sends read_pixels_to_buffer / get_texture_image_to_buffer, waits for
// nothing, and marks the buffer GPU-written. The 1 arm is the A/B control and the
// red-once of the wait-count gate (PackBufferReadbackScenario): it must show a reply
// wait per read.
Uint32 PboReadbackSync = 0;
// MOBILEGL_IPC_POLL_ESCALATE (P10, MG_Remote/CONTRACT-P10.md §1): a glClientWaitSync with a
// zero timeout or a glGetSynciv(GL_SYNC_STATUS) is answered by the client from what the
// server reported (kEventFenceSignaled) - "signaled" when it has been, "not yet" otherwise
// - and only the Nth "not yet" in a row on one fence crosses as a real round trip, so a
// poll loop cannot outlive a late report. 0 = every poll crosses, as before P10: the A/B
// arm and the red-once of the no-reply gate (FencePollScenario).
Uint32 PollEscalate = 64;
// MOBILEGL_IPC_ADOPT_TIER, THE ZERO-COPY SWITCH (ruling ID-P11-14, CONTRACT-P11 B2):
// UNSET (kAdoptTierUnset, the default since 2026-09-29, the user's decision) = T0 where the
// session can run it, T2 QUIETLY where it cannot (MGLOG_D only, still counted);
// 0 = T0 asked by name - a T0 this session cannot use (a stream plane, the server's allow
// switch, no AHardwareBuffer, a failed server POST) is T2 plus one named line;
// 1 = T1, closed - refused by name, then T2; 2 = emulate (T2: the client keeps the shadow
// and pushes). Never a Fatal (MG_Remote/Transport/AdoptTier.h).
Uint32 AdoptTier = kAdoptTierUnset;
// MOBILEGL_IPC_ALLOW_ADOPT_T0 (server): 1 (default) = grant a client's T0 ask when this
// platform and the backend's POST self-test allow it; 0 = never grant it (the session
// runs T2 and says so). Read by the server role only; kept through ServerSpawn.
Uint32 AllowAdoptT0 = 1;
// 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;
}
// P12: the other on-screen shape, and the mirror image of the one above. The display host
// (the Android side that owns the screen) allocates the frames, offers each one over the
// host frame bridge, and puts it on the glass when this side says it is drawn - so a
// client that asks for this has no window of its own either, and the server takes the
// frames rather than making a window.
inline Bool HostFrameWindowSurfaces() {
return Transport == TransportMode::Spawn && Ipc.Surface == IpcSurface::Host;
}
#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
-342
View File
@@ -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 {
@@ -180,38 +159,6 @@ 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");
@@ -263,40 +210,6 @@ namespace MobileGL::MG_ConfigLoader {
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() {
@@ -315,267 +228,12 @@ 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);
// P9 W1: the pack-buffer readback's A/B and red-once control (Config.h says both).
ipc.PboReadbackSync = QueryEnvUint32("MOBILEGL_IPC_PBO_READBACK_SYNC", 0, 0, 1);
// P10: fence polls answered locally; 0 is the A/B arm (Config.h).
ipc.PollEscalate = QueryEnvUint32("MOBILEGL_IPC_POLL_ESCALATE", 64, 0, 1000000);
// 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;
// UNSET is T0 with quiet fallbacks (the default since 2026-09-29); 0 asks for T0 by name, 1 is
// refused by name, 2 is T2 - settled at the handshake from the data plane (P11 A1/B2,
// MG_Remote/Transport/AdoptTier.h). An unparseable value is warned about and reads as unset.
ipc.AdoptTier = QueryEnvUint32("MOBILEGL_IPC_ADOPT_TIER", MG_Config::kAdoptTierUnset, 0, 2);
// P11 B2: the server's own T0 allow switch (Config.h).
ipc.AllowAdoptT0 = QueryEnvUint32("MOBILEGL_IPC_ALLOW_ADOPT_T0", 1, 0, 1);
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): MOBILEGL_IPC_SURFACE = offscreen | server | host (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 if (surface == "host") {
ipc.Surface = MG_Config::IpcSurface::Host;
} else {
MGLOG_W("Config: Ignoring invalid env variable MOBILEGL_IPC_SURFACE='%s'; expected "
"offscreen|server|host, 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::Offscreen && !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=%s is IGNORED - it asks for an on-screen "
"surface (the server's own window, or the frames the display host owns) and "
"this run has no remote server to provide one: MOBILEGL_TRANSPORT is not "
"spawn. Window surfaces stay the client's own",
ipc.Surface == MG_Config::IpcSurface::Server ? "server" : "host");
}
}
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 pbo-readback-sync=%u poll-escalate=%u "
"adopt-tier=%s allow-t0=%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.PboReadbackSync, ipc.PollEscalate,
ipc.AdoptTier == 0 ? "0" : ipc.AdoptTier == 1 ? "1" : ipc.AdoptTier == 2 ? "2" : "unset(T0)",
ipc.AllowAdoptT0,
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
+2 -9
View File
@@ -8,8 +8,6 @@
#pragma once
#include <cstdio>
// ============== 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
@@ -36,11 +34,6 @@
#ifdef _WIN32
#define MOBILEGL_EXPORT extern "C" __declspec(dllexport)
#else
// Default visibility, which is what the platform's own GL and EGL headers declare their entry
// points with. The one place where that is not enough - a vendor library handing glvnd its own
// entry points, where a reference resolving against the process instead of this library would be a
// call back into the dispatcher - is answered at link time with -Bsymbolic-functions rather than
// here, because a second visibility on the same declaration does not compile.
#define MOBILEGL_EXPORT extern "C" __attribute__((visibility("default")))
#endif
@@ -112,8 +105,8 @@
#define MOBILEGL_ASSERT(condition, ...) \
do { \
if (!(condition)) { \
fprintf(stderr, "Assertion failed" __VA_OPT__(": ") "%s", "" __VA_ARGS__); \
fprintf(stderr, " at %s:%d (%s)\n", __FILE__, __LINE__, __func__); \
MGLOG_F("Assertion failed" __VA_OPT__(": ") __VA_ARGS__); \
MGLOG_F(" at %s:%d (%s)", __FILE__, __LINE__, __func__); \
TRAP; \
} \
} while (0)
MobileGL/Init.cpp
+1 -72
View File
@@ -17,13 +17,9 @@
#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>
@@ -46,20 +42,6 @@ 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,
@@ -102,14 +84,6 @@ namespace MobileGL {
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();
}
@@ -128,54 +102,9 @@ 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");
MobileGL/MG_Backend/BackendObject.cpp
+5 -86
View File
@@ -172,15 +172,11 @@ namespace MobileGL::MG_Backend {
return false;
}
// A DISPLAY IS A CONNECTION, NOT A RESOURCE THIS BACKEND OWNS, and refusing the second one
// refused a caller for a reason that is not there: the surface and context tables are keyed
// by the display each was created on, every operation carries its own display handle, and
// this field has no reader anywhere - it was the whole of the rule.
//
// What the rule cost was a compositor. One asks for the display it will draw into AFTER
// probing another, so the second eglInitialize is the one that matters, and a refusal there
// is reported one layer up as "no usable DRM render device" - the probe having succeeded
// and the real display having failed, with nothing in between that says which was refused.
if (m_eglDisplayInitialized && m_eglDisplay != dpy) {
MGLOG_E("InitializeEGLDisplay failed: backend already bound to a different EGLDisplay");
return false;
}
m_eglDisplay = dpy;
m_eglDisplayInitialized = true;
if (major) {
@@ -213,28 +209,6 @@ namespace MobileGL::MG_Backend {
return true;
}
// The frame itself is the backend's business (InitHostFrameSurface); what happens here is
// the registration every surface kind shares, so the swap path and the state mirrors see
// a host-framed surface exactly like any other.
Bool BackendObject::CreateEGLHostFrameSurface(EGLSurface surface, Uint32 width, Uint32 height) {
const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
if (!m_eglDisplayInitialized) {
MGLOG_E("CreateEGLHostFrameSurface failed: EGL display is not initialized");
return false;
}
if (surface == EGL_NO_SURFACE) {
MGLOG_E("CreateEGLHostFrameSurface failed: invalid EGLSurface");
return false;
}
auto& state = m_eglSurfaces[surface];
state = EGLSurfaceState{
.Kind = SurfaceKind::HostFrame,
.Width = static_cast<EGLint>(std::max<Uint32>(width, 1)),
.Height = static_cast<EGLint>(std::max<Uint32>(height, 1)),
};
return ActivateEGLSurface(surface);
}
Bool BackendObject::CreateEGLPbufferSurface(EGLSurface surface, EGLint width, EGLint height) {
const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
return RegisterEGLPbufferSurface(surface, width, height) && ActivateEGLSurface(surface);
@@ -316,11 +290,6 @@ namespace MobileGL::MG_Backend {
MGLOG_E("ActivateEGLSurface failed: backend InitPbufferSurface failed");
return false;
}
} else if (surfaceState->Kind == SurfaceKind::HostFrame) {
if (!InitHostFrameSurface(surfaceState->Width, surfaceState->Height)) {
MGLOG_E("ActivateEGLSurface failed: backend InitHostFrameSurface failed");
return false;
}
} else {
MGLOG_E("ActivateEGLSurface failed: unsupported surface kind");
return false;
@@ -346,29 +315,6 @@ namespace MobileGL::MG_Backend {
MGLOG_E("MakeEGLCurrent failed: EGL display mismatch or not initialized");
return false;
}
// EGL_KHR_surfaceless_context. A context whose draw and read surfaces are both absent has
// no framebuffer of its own to be bound to: the caller draws into framebuffers it binds
// itself, and this side only has to have its own GL context current on this thread for the
// records that follow. Everything below this point describes a surface, so none of it
// applies - and what is recorded is exactly what was asked for, so a later swap on a
// surface that does not exist is never made to look like one that does.
if (draw == EGL_NO_SURFACE && read == EGL_NO_SURFACE && ctx != EGL_NO_CONTEXT) {
if (!m_backendCapabilitiesInitialized) {
if (!InitCapabilities()) {
MGLOG_E("MakeEGLCurrent failed: InitCapabilities failed");
return false;
}
m_backendCapabilitiesInitialized = true;
}
ReleaseEGLCurrentThread(threadKey);
m_eglCurrentThreads[threadKey] = EGLCurrentState{
.Display = dpy,
.DrawSurface = EGL_NO_SURFACE,
.ReadSurface = EGL_NO_SURFACE,
.Context = ctx,
};
return true;
}
if (!m_eglSurfaceInitialized) {
if (draw != read || !ActivateEGLSurface(draw)) {
MGLOG_E("MakeEGLCurrent failed: EGL surface is not initialized");
@@ -441,12 +387,6 @@ namespace MobileGL::MG_Backend {
return false;
}
// A host-framed surface has no swapchain: presenting it means telling the host the frame
// is drawn, because the host is what puts it on the glass.
if (m_eglSurfaceKind == SurfaceKind::HostFrame) {
return PresentHostFrame();
}
const auto& backendFunctions = GetBackendFunctions();
if (!backendFunctions.Present) {
MGLOG_E("SwapEGLBuffers failed: backend Present function is null");
@@ -464,27 +404,6 @@ namespace MobileGL::MG_Backend {
}
}
// A backend that has no host-framed surfaces says so by name: the server may ask for one
// (MOBILEGL_IPC_SURFACE=host) against a build that cannot serve it, and that has to be a
// refusal with a reason rather than a surface that draws nowhere.
Bool BackendObject::InitHostFrameSurface(EGLint width, EGLint height) {
(void)width;
(void)height;
MGLOG_E("InitHostFrameSurface: this backend has no host-framed surfaces");
return false;
}
Bool BackendObject::PresentHostFrame() {
MGLOG_E("PresentHostFrame: this backend has no host-framed surfaces");
return false;
}
Bool BackendObject::PresentHostFrameIfCurrent() {
const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
if (!m_eglSurfaceInitialized || m_eglSurfaceKind != SurfaceKind::HostFrame) return true;
return PresentHostFrame();
}
Bool BackendObject::IsEGLSurfaceCurrent(EGLSurface surface) const {
if (surface == EGL_NO_SURFACE) {
return false;
MobileGL/MG_Backend/BackendObject.h
+10 -71
View File
@@ -9,9 +9,6 @@
#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 {
@@ -36,24 +33,9 @@ namespace MobileGL {
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;
}
Bool IsRenderbuffer() const { return Renderbuffer != nullptr; }
Bool Exists() const { return Texture != nullptr || Renderbuffer != nullptr; }
};
enum class FormatCapability : Uint64 {
@@ -210,23 +192,9 @@ 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.
void (*GetInteger64i_v)(GLenum target, GLuint index, GLint64* data);
void (*GetProgramiv)(GLuint program, GLenum pname, GLint* params);
// 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
@@ -332,13 +300,13 @@ namespace MobileGL {
};
struct DynamicBackendParameters {
Uint64 UniformBufferOffsetAlignment = 256;
SizeT 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 ShaderStorageBufferOffsetAlignment = 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;
@@ -396,19 +364,6 @@ namespace MobileGL {
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.
@@ -460,8 +415,8 @@ namespace MobileGL {
// 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;
GLenum LayerProvokingVertex = GL_UNDEFINED_VERTEX;
GLenum ViewportIndexProvokingVertex = GL_UNDEFINED_VERTEX;
Int MaxViewportWidth = 16384;
Int MaxViewportHeight = 16384;
Float ViewportBoundsRangeMin = 0.0f;
@@ -558,7 +513,7 @@ namespace MobileGL {
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;
@@ -595,18 +550,6 @@ namespace MobileGL {
virtual Bool CreateEGLWindowSurface(EGLSurface surface, const WindowHandle& handle);
virtual Bool ResizeEGLWindowSurface(EGLSurface surface, Uint32 width, Uint32 height);
virtual Bool CreateEGLPbufferSurface(EGLSurface surface, EGLint width, EGLint height);
// The host owns the screen: this side never gets a window of the client's to draw
// into, so the surface it draws into is a frame the host allocated and offered over
// the host frame bridge. Each swap tells the host the frame is done and takes the
// next; presentation is the host's, not a swapchain's.
virtual Bool CreateEGLHostFrameSurface(EGLSurface surface, Uint32 width, Uint32 height);
virtual Bool InitHostFrameSurface(EGLint width, EGLint height);
virtual Bool PresentHostFrame();
// The present RECORD's half of a host-framed swap. A split client's swap reaches the
// server as a present record (ServerVerbSink::OnPresent), never as SwapEGLBuffers, so
// without this the host was never told a frame was drawn. True when the current
// surface is not host-framed: there is nothing to present then.
Bool PresentHostFrameIfCurrent();
virtual Bool MakeEGLCurrent(EGLDisplay dpy, EGLSurface draw, EGLSurface read, EGLContext ctx);
virtual Bool SwapEGLBuffers(EGLDisplay dpy, EGLSurface draw);
// Forwards the app-requested eglSwapInterval to the backend's native
@@ -628,11 +571,7 @@ namespace MobileGL {
enum class SurfaceKind {
None,
Window,
Pbuffer,
// A surface whose drawing target is a frame the display host owns. There is no
// swapchain behind it: the host puts the frame on the glass when this side says
// it is drawn, which is why presenting one is its own call and not a Present.
HostFrame
Pbuffer
};
struct EGLCurrentState {
MobileGL/MG_Backend/BackendObjects.h
-41
View File
@@ -15,45 +15,4 @@
namespace MobileGL::MG_Backend {
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.cpp
+10 -474
View File
@@ -6,12 +6,6 @@
// SPDX-License-Identifier: LGPL-3.0-only
// End of Source File Header
#if MOBILEGL_BUILD_DISAGGREGATED && defined(__ANDROID__)
// The role's own backend is resolved the way Utils.cpp (C6 / ID-52) resolves it; that needs this
// header, and it has to be included at file scope - a header included inside this file's namespace
// would nest its own namespace under it.
#include <MG_Remote/Server/ServerLoop.h>
#endif
#include "BackendObject_DirectGLES.h"
#include "MG_Backend/BackendObject.h"
#include "MG_Backend/BackendObjects.h"
@@ -38,54 +32,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
return draw == EGL_NO_SURFACE && read == EGL_NO_SURFACE && ctx == EGL_NO_CONTEXT;
}
#if MOBILEGL_BUILD_DISAGGREGATED
// ID-54 / ID-67 (v1, under ID-52/ID-59's grant for this file). Which VIRTUAL (dpy, draw,
// read, ctx) the process's one native ES context is currently bound FOR, on the apply
// thread. DirectGLES has one native context and one native surface (g_Context, g_Surface)
// whatever virtual handles the client uses, so "is a native eglMakeCurrent needed" is never
// "is the native triple different" - it is "did the VIRTUAL context change":
// DirectGLES::MakeCurrent is also where the seven caches that describe the frontend context
// are invalidated, and a different virtual context needs them invalidated even though the
// driver binds the same triple. ID-67: a make-current with a DIFFERENT tuple is a real
// native bind (and a caps republish, ServerLoop's half); an IDENTICAL one is neither.
//
// Three states. NotBound: the next bind is native. FreshFromSurfaceCreation: the surface's
// own creation (InitPbufferSurface / InitWindowSurface) bound natively and invalidated, and
// no virtual tuple has claimed that bind yet - the first tuple adopts it, which is the
// "2 -> 1 native binds per process" of round 3. BoundForTuple: bound and invalidated for
// the recorded tuple; only that exact tuple may skip. Process-wide like the native state it
// mirrors; under split exactly one DirectGLES object exists (the server's), and only the
// apply thread reaches these.
enum class NativeBindState : Uint8 { NotBound, FreshFromSurfaceCreation, BoundForTuple };
NativeBindState g_nativeBindState = NativeBindState::NotBound;
EGLDisplay g_nativeBoundDpy = EGL_NO_DISPLAY;
EGLSurface g_nativeBoundDraw = EGL_NO_SURFACE;
EGLSurface g_nativeBoundRead = EGL_NO_SURFACE;
EGLContext g_nativeBoundCtx = EGL_NO_CONTEXT;
void NoteNativeContextGone() { g_nativeBindState = NativeBindState::NotBound; }
void NoteNativeContextFreshFromSurfaceCreation() {
g_nativeBindState = NativeBindState::FreshFromSurfaceCreation;
}
void NoteNativeBoundFor(EGLDisplay dpy, EGLSurface draw, EGLSurface read, EGLContext ctx) {
g_nativeBindState = NativeBindState::BoundForTuple;
g_nativeBoundDpy = dpy;
g_nativeBoundDraw = draw;
g_nativeBoundRead = read;
g_nativeBoundCtx = ctx;
}
Bool NativeBindCanBeSkippedFor(EGLDisplay dpy, EGLSurface draw, EGLSurface read, EGLContext ctx) {
switch (g_nativeBindState) {
case NativeBindState::NotBound: return false;
case NativeBindState::FreshFromSurfaceCreation: return true;
case NativeBindState::BoundForTuple:
return g_nativeBoundDpy == dpy && g_nativeBoundDraw == draw && g_nativeBoundRead == read &&
g_nativeBoundCtx == ctx;
}
return false;
}
#endif
void ClearGLErrors(const MG_External::GLESFunctionsTable& gl) {
if (!gl.glGetError) return;
while (gl.glGetError() != GL_NO_ERROR) {}
@@ -866,19 +812,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
Int maxSamples = 0;
const SizeT formatIndex = static_cast<SizeT>(logicalFormat);
#if MOBILEGL_BUILD_DISAGGREGATED
// C6 / ID-52: read the ROLE's own cache. Under split that is the server's private backend
// (ActiveBackendFormatCaps), not pActiveBackendObject, which holds the client's mirror.
const FormatCapabilityCache* activeCaps = ActiveBackendFormatCaps();
if (activeCaps != nullptr && targetIndex < kFormatCapabilityTargetCount &&
formatIndex < kFormatCapabilityFormatCount) {
// Descending, so the head is the largest count this device actually allocated.
const Vector<Int>& probedCounts = activeCaps->SampleCounts[targetIndex][formatIndex];
if (!probedCounts.empty()) {
maxSamples = probedCounts.front();
}
}
#else
if (pActiveBackendObject && targetIndex < kFormatCapabilityTargetCount &&
formatIndex < kFormatCapabilityFormatCount) {
// Descending, so the head is the largest count this device actually allocated.
@@ -888,7 +821,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
maxSamples = probedCounts.front();
}
}
#endif
if (maxSamples <= 0) {
maxSamples = GetGLESFormatMaxSamples(g_GLESCapabilities, logicalFormat, imageFormat);
}
@@ -897,19 +829,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
BackendObject_DirectGLES::~BackendObject_DirectGLES() {
DestroyEGLContext();
#if MOBILEGL_BUILD_DISAGGREGATED
NoteNativeContextGone();
// P12: under a transport this object is the SERVER's backend and its destruction is the
// end of a session (ServerLoop's apply thread, after the final drain). The in-process
// display server runs the next session in this same process, so the twins this one built
// - naming ids of the context just destroyed - must not answer for the next client's
// handles (Managers.h, DropEveryTwinForEndedServerSession). Monolith keeps its twins.
if (MG_Config::Transport != MG_Config::TransportMode::Monolith) {
DropEveryTwinForEndedServerSession();
// Review fix: and the swap interval it asked for (DirectGLES.h).
ForgetRequestedSwapInterval();
}
#endif
}
Bool BackendObject_DirectGLES::InitWindowSurface() {
@@ -987,20 +906,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
ResetEGLRuntimeState();
}
#if MOBILEGL_BUILD_DISAGGREGATED
// ID-54 / ID-67: the surface's creation bound natively (InitWindowSurface -> MakeCurrent);
// the first virtual tuple adopts that bind. On failure nothing is known to be bound. The
// pull arm below is the original statement, byte for byte (G1).
const Bool created = BackendObject::CreateEGLWindowSurface(surface, handle);
if (created) {
NoteNativeContextFreshFromSurfaceCreation();
} else {
NoteNativeContextGone();
}
return created;
#else
return BackendObject::CreateEGLWindowSurface(surface, handle);
#endif
}
Bool BackendObject_DirectGLES::CreateEGLPbufferSurface(EGLSurface surface, EGLint width, EGLint height) {
@@ -1019,256 +925,9 @@ namespace MobileGL::MG_Backend::DirectGLES {
ResetEGLRuntimeState();
}
#if MOBILEGL_BUILD_DISAGGREGATED
// ID-54 / ID-67: as for the window surface - InitPbufferSurface bound natively. The pull
// arm below is the original statement, byte for byte (G1).
const Bool created = BackendObject::CreateEGLPbufferSurface(surface, width, height);
if (created) {
NoteNativeContextFreshFromSurfaceCreation();
} else {
NoteNativeContextGone();
}
return created;
#else
return BackendObject::CreateEGLPbufferSurface(surface, width, height);
#endif
}
#if MOBILEGL_BUILD_DISAGGREGATED && defined(__ANDROID__)
namespace {
// The host may still be starting when the client asks for its surface: it is a separate
// app that has to come up and allocate its pool. Waiting is better than refusing a
// surface a client is entitled to, and the wait is answered by name if it expires.
constexpr Int kHostFrameWaitMs = 30000;
}
Bool TakeHostFrameForExternalTexture(Uint width, Uint height) {
// THIS ROLE'S OWN BACKEND, resolved exactly the way ActiveBackendFormatCaps (Utils.cpp,
// C6 / ID-52) resolves it: under a live split session the SERVER's private backend owns the
// context on the apply thread, and pActiveBackendObject is the CLIENT's mirror there.
MG_Backend::BackendObject* backend = nullptr;
if (MG_Config::Transport != MG_Config::TransportMode::Monolith) {
backend = MG_Remote::Server::ServerLoopInstance().Backend();
} else {
backend = MG_Backend::pActiveBackendObject.get();
}
if (backend == nullptr) return false;
return backend->InitHostFrameSurface(static_cast<EGLint>(width), static_cast<EGLint>(height));
}
Bool BackendObject_DirectGLES::InitHostFrameSurface(EGLint width, EGLint height) {
// The EGL context comes from the same place a pbuffer session's does. What changes is not
// how this side draws but what it draws INTO: a frame the display host allocated, bound as
// this context's framebuffer. The pbuffer stays as the draw target for the moment before
// the first frame arrives, which is the only moment it is used.
if (!DirectGLES::InitPbufferSurface(width, height)) {
MGLOG_E("InitHostFrameSurface: the context the host frames are drawn in did not come up");
return false;
}
if (!m_hostFrameBridgeOpen) {
String why;
if (!m_hostFrameBridge.Open(MG_Backend::kHostFrameSocket, kHostFrameWaitMs, why)) {
MGLOG_E("InitHostFrameSurface: no display host: %s", why.c_str());
return false;
}
m_hostFrameBridgeOpen = true;
}
return TakeHostFrame();
}
Bool BackendObject_DirectGLES::TakeHostFrame() {
String why;
struct AHardwareBuffer* frame = nullptr;
MG_Backend::HostFrameOffer offer{};
if (!m_hostFrameBridge.Acquire(&frame, offer, why)) {
MGLOG_E("TakeHostFrame: %s", why.c_str());
return false;
}
HostFrameTarget target;
if (!HostFrameTargetCreate(frame, target, why)) {
MGLOG_E("TakeHostFrame: the host frame %ux%u did not become a draw target: %s", offer.Width,
offer.Height, why.c_str());
AHardwareBuffer_release(frame);
return false;
}
DestroyHostFrame();
m_hostFrameTarget = target;
m_hostFrameBuffer = frame;
m_hostFrameOffer = offer;
// The canvas is made at the first frame's size and kept; a failure leaves the frame itself
// as the draw target, which is how this path behaved before the canvas existed.
if (!EnsureHostFrameCanvas(target.Width, target.Height))
MGLOG_E_ONCE("TakeHostFrame: no canvas in front of the host frames; drawing into the frame itself");
const HostFrameTarget& drawTarget = HostFrameDrawTarget();
// BEFORE the bind: every default-framebuffer bind the engine makes from here on has to
// resolve to this target, and that resolution is what this global is.
g_hostFrameFramebufferId = drawTarget.Framebuffer;
// Published together with the framebuffer, because they describe the same target: the STORAGE
// an attachment is bound to when the client's texture has none of its own, and the SIZE that
// decides whether binding it is right at all.
g_hostFrameRenderbuffer = drawTarget.Renderbuffer;
g_hostFrameWidth = drawTarget.Width;
g_hostFrameHeight = drawTarget.Height;
FramebufferImpl::InvalidateFramebufferBindingCache();
HostFrameTargetBind(drawTarget);
// AND ON TO THE CONTAINER, as the dma-buf descriptor behind it. The Wayland compositor
// over there renders into THESE frames - it runs this project's own GBM, whose
// gbm_bo_create answers with the phone's frame instead of an allocation of its own - so
// every frame taken here is useless to it until its descriptor has crossed. Open() binds
// the listening socket a container dials, and the IsUp() test keeps the ordinary frame
// down to an integer compare: the socket outlives every container and every connection,
// while OfferFrame accepts whoever dialled since the last frame and opens the socket
// itself when the first frame arrives before any container has.
//
// NEITHER ANSWER IS EXAMINED, and that is the channel's contract rather than an
// oversight: no container running, a container that has died, or one that has taken the
// descriptor and stopped reading must all leave this frame drawn and presented exactly as
// it would have been without a channel - the descriptor is a copy of the pixels' route,
// not a step in producing them.
if (!m_gbmFrameChannel.IsUp()) m_gbmFrameChannel.Open();
(void)m_gbmFrameChannel.OfferFrame(frame, offer);
MGLOG_I("host frame %u is the draw target: %ux%u", offer.Index, target.Width, target.Height);
return true;
}
void BackendObject_DirectGLES::DestroyHostFrame() {
// The canvas outlives the frame, so with one the globals keep naming it: the attachments
// made over it stay valid between this frame being handed back and the next one arriving.
g_hostFrameFramebufferId = m_hostFrameCanvas.Framebuffer;
g_hostFrameRenderbuffer = m_hostFrameCanvas.Renderbuffer;
g_hostFrameWidth = m_hostFrameCanvas.Width;
g_hostFrameHeight = m_hostFrameCanvas.Height;
HostFrameTargetDestroy(m_hostFrameTarget);
if (m_hostFrameBuffer != nullptr) {
AHardwareBuffer_release(m_hostFrameBuffer);
m_hostFrameBuffer = nullptr;
}
// AND NOTHING IS SAID TO THE CHANNEL HERE, which is the fix rather than an omission. This
// runs once per presented frame: it used to Close() the channel (unlinking the container's
// socket node and dropping its connection sixty times a second - measured: connect()
// answered EAGAIN(11) on every attempt) and it used to tell the channel to forget the frame,
// which left the ONE window a compositor's first allocations arrive in - between this frame
// being presented and the host handing the next one over, i.e. inside Complete() above -
// with nothing to answer a dialer with. A compositor allocates its swapchain ONCE and keeps
// those buffers for the life of the process, so a dialer that finds nothing here renders
// its whole life into buffers nobody displays. The frame the channel remembers is the last
// one the host handed over: the next offer replaces it and Close() releases it.
}
Bool BackendObject_DirectGLES::PresentHostFrame() {
// When this returns, the pixels are complete: glFinish is the fence the host is told
// about, and the host's own readback - which Complete reads - is what proves the drawing
// landed where the screen will look.
BlitHostFrameCanvas();
if (g_GLESFuncs.glFinish != nullptr) g_GLESFuncs.glFinish();
// WHAT THE CONTAINER SAID WHILE THIS FRAME WAS BEING DRAWN. This is the one place the
// server's apply loop passes through the host channel - the swap it runs lands here for a
// host-framed surface - and a release is the container's compositor saying it is done
// reading a frame this side handed over. Poll() is a bare recvmsg on a non-blocking
// socket: with no container connected it returns on its first test, and a container that
// is between frames answers EAGAIN, so a pass costs nothing when there is nothing to
// read. Nothing here is waited for and nothing is required to arrive; the count of
// frames offered and not released is a number the channel keeps for the log, never a
// frame the render path waits on.
m_gbmFrameChannel.Poll();
String why;
if (!m_hostFrameBridge.Complete(m_hostFrameOffer, /*imported=*/true, /*drawn=*/true, /*fenceOk=*/true, why)) {
MGLOG_E("PresentHostFrame: %s", why.c_str());
return false;
}
// The answer has been read, so the host has already put this frame on the glass: it is
// this side's to drop, and the next one becomes the drawing target.
DestroyHostFrame();
return TakeHostFrame();
}
Bool BackendObject_DirectGLES::EnsureHostFrameCanvas(Uint width, Uint height) {
if (m_hostFrameCanvas.Framebuffer != 0) return true;
if (width == 0 || height == 0 || !g_GLESFuncs.glRenderbufferStorage || !g_GLESFuncs.glBlitFramebuffer ||
!g_GLESFuncs.glGenRenderbuffers || !g_GLESFuncs.glGenFramebuffers || !g_GLESFuncs.glCheckFramebufferStatus)
return false;
// RAW binds, as HostFrameTargetCreate makes them: the caller invalidates the engine's
// framebuffer shadow and binds through it right after.
GLuint renderbuffer = 0;
g_GLESFuncs.glGenRenderbuffers(1, &renderbuffer);
g_GLESFuncs.glBindRenderbuffer(GL_RENDERBUFFER, renderbuffer);
// The frames are R8G8B8A8_UNORM (the display host allocates them so), and so is this.
g_GLESFuncs.glRenderbufferStorage(GL_RENDERBUFFER, GL_RGBA8, static_cast<GLsizei>(width),
static_cast<GLsizei>(height));
GLuint framebuffer = 0;
g_GLESFuncs.glGenFramebuffers(1, &framebuffer);
g_GLESFuncs.glBindFramebuffer(GL_FRAMEBUFFER, framebuffer);
g_GLESFuncs.glFramebufferRenderbuffer(GL_FRAMEBUFFER, GL_COLOR_ATTACHMENT0, GL_RENDERBUFFER, renderbuffer);
const GLenum status = g_GLESFuncs.glCheckFramebufferStatus(GL_FRAMEBUFFER);
if (status != GL_FRAMEBUFFER_COMPLETE) {
MGLOG_E("host frame canvas %ux%u: framebuffer status 0x%04x", width, height, status);
g_GLESFuncs.glDeleteFramebuffers(1, &framebuffer);
g_GLESFuncs.glDeleteRenderbuffers(1, &renderbuffer);
return false;
}
m_hostFrameCanvas.Renderbuffer = renderbuffer;
m_hostFrameCanvas.Framebuffer = framebuffer;
m_hostFrameCanvas.Width = width;
m_hostFrameCanvas.Height = height;
MGLOG_I("host frame canvas: %ux%u as framebuffer %u (renderbuffer %u), copied into each frame at present",
width, height, framebuffer, renderbuffer);
return true;
}
void BackendObject_DirectGLES::BlitHostFrameCanvas() {
if (m_hostFrameCanvas.Framebuffer == 0 || m_hostFrameTarget.Framebuffer == 0) return;
// Whatever the compositor had bound is put back as it was, raw for raw, so the engine's
// shadow (which never saw this) is still right afterwards. The scissor test and
// rasterizer discard both apply to a blit, so they are lifted for it.
GLint readBinding = 0;
GLint drawBinding = 0;
g_GLESFuncs.glGetIntegerv(GL_READ_FRAMEBUFFER_BINDING, &readBinding);
g_GLESFuncs.glGetIntegerv(GL_DRAW_FRAMEBUFFER_BINDING, &drawBinding);
const GLboolean scissor = g_GLESFuncs.glIsEnabled(GL_SCISSOR_TEST);
const GLboolean discard = g_GLESFuncs.glIsEnabled(GL_RASTERIZER_DISCARD);
if (scissor) g_GLESFuncs.glDisable(GL_SCISSOR_TEST);
if (discard) g_GLESFuncs.glDisable(GL_RASTERIZER_DISCARD);
g_GLESFuncs.glBindFramebuffer(GL_READ_FRAMEBUFFER, m_hostFrameCanvas.Framebuffer);
g_GLESFuncs.glBindFramebuffer(GL_DRAW_FRAMEBUFFER, m_hostFrameTarget.Framebuffer);
const Bool sameSize = m_hostFrameCanvas.Width == m_hostFrameTarget.Width &&
m_hostFrameCanvas.Height == m_hostFrameTarget.Height;
g_GLESFuncs.glBlitFramebuffer(0, 0, static_cast<GLint>(m_hostFrameCanvas.Width),
static_cast<GLint>(m_hostFrameCanvas.Height), 0, 0,
static_cast<GLint>(m_hostFrameTarget.Width),
static_cast<GLint>(m_hostFrameTarget.Height), GL_COLOR_BUFFER_BIT,
sameSize ? GL_NEAREST : GL_LINEAR);
g_GLESFuncs.glBindFramebuffer(GL_READ_FRAMEBUFFER, static_cast<GLuint>(readBinding));
g_GLESFuncs.glBindFramebuffer(GL_DRAW_FRAMEBUFFER, static_cast<GLuint>(drawBinding));
if (scissor) g_GLESFuncs.glEnable(GL_SCISSOR_TEST);
if (discard) g_GLESFuncs.glEnable(GL_RASTERIZER_DISCARD);
}
#else // !(MOBILEGL_BUILD_DISAGGREGATED && __ANDROID__)
// The other arm's half: on a build with no host frames there is no frame to take, and the
// attach site's ordinary path (a storage-less external texture, exactly as before) is the honest
// behaviour there rather than a link error.
Bool TakeHostFrameForExternalTexture(Uint, Uint) { return false; }
Bool BackendObject_DirectGLES::InitHostFrameSurface(EGLint width, EGLint height) {
(void)width;
(void)height;
MGLOG_E("InitHostFrameSurface: host frames are a disaggregated Android path");
return false;
}
Bool BackendObject_DirectGLES::TakeHostFrame() { return false; }
void BackendObject_DirectGLES::DestroyHostFrame() {}
Bool BackendObject_DirectGLES::EnsureHostFrameCanvas(Uint, Uint) { return false; }
void BackendObject_DirectGLES::BlitHostFrameCanvas() {}
Bool BackendObject_DirectGLES::PresentHostFrame() {
MGLOG_E("PresentHostFrame: host frames are a disaggregated Android path");
return false;
}
#endif
Bool BackendObject_DirectGLES::InitPbufferSurface(EGLint width, EGLint height) {
return DirectGLES::InitPbufferSurface(width, height);
}
@@ -1279,9 +938,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
if (!DirectGLES::ReleaseCurrent()) {
return false;
}
#if MOBILEGL_BUILD_DISAGGREGATED
NoteNativeContextGone();
#endif
return BackendObject::MakeEGLCurrent(dpy, draw, read, ctx);
}
@@ -1293,99 +949,23 @@ namespace MobileGL::MG_Backend::DirectGLES {
MGLOG_E("MakeEGLCurrent failed: EGL display mismatch or not initialized");
return false;
}
// EGL_KHR_surfaceless_context, WHICH IS THE SHAPE A COMPOSITOR ASKS FOR. Its context has no
// draw surface of its own - every frame goes into a framebuffer it binds itself, and under
// this project that framebuffer is one of the display host's frames - so the surface checks
// below describe a surface that legitimately does not exist. What the server still needs is
// its own GL context current on this thread for the records that follow, and that is what
// the native bind underneath them does.
const Bool surfaceless = draw == EGL_NO_SURFACE && read == EGL_NO_SURFACE && ctx != EGL_NO_CONTEXT;
if (surfaceless && !m_eglSurfaceInitialized) {
// A DRAWABLE OF THIS SIDE'S OWN, WHICH IS WHAT A SURFACELESS CLIENT LEAVES TO US. The
// backend's native context has to be current on a surface of some kind before a single
// record of the client's can run - that is what the Init*Surface calls establish - and a
// client that makes its context current with no surface at all supplies none of its own.
// A pbuffer is the one that costs nothing to keep: it is never scanned out and never
// read, because every frame the client draws goes into a framebuffer it binds itself.
// The client is NOT told it has a surface - m_eglSurface stays EGL_NO_SURFACE - so a
// swap on one is still the refusal it was.
if (!InitPbufferSurface(1, 1)) {
MGLOG_E("MakeEGLCurrent failed: the backend's own drawable for a surfaceless context could not "
"be created");
return false;
}
m_eglSurface = EGL_NO_SURFACE;
m_eglSurfaceInitialized = true;
m_eglSurfaceKind = SurfaceKind::Pbuffer;
m_eglCurrentThreads.clear();
m_backendCapabilitiesInitialized = false;
}
if (!surfaceless) {
if (!m_eglSurfaceInitialized) {
MGLOG_E("MakeEGLCurrent failed: EGL surface is not initialized");
return false;
}
if (draw == EGL_NO_SURFACE || read == EGL_NO_SURFACE || ctx == EGL_NO_CONTEXT) {
MGLOG_E("MakeEGLCurrent failed: draw/read/context is invalid");
return false;
}
}
#if MOBILEGL_BUILD_DISAGGREGATED
// ID-54 / C7, the native half of "bind once per tuple" (v1, under ID-52/ID-59's grant for
// this file; #if-guarded so the pull build is byte-identical). Under an active transport
// this runs on the apply thread, which is the ONLY thread that ever binds the server's
// context, and the surface it is asked for was made natively current on this very thread
// by its own creation (InitPbufferSurface / InitWindowSurface -> DirectGLES::MakeCurrent).
// A second native eglMakeCurrent for the same surface is then a repeat: it rewrites the
// owner with the same thread, re-registers the same op table and invalidates seven caches
// that describe a context that did not change - the per-client-make-current storm the
// v2 review measured as "2 native binds per process, unchanged". So when the requested
// draw surface IS the active one and EGL itself says this thread holds the context
// (IsBackendContextCurrentOnThisThread re-verifies against eglGetCurrentContext), the
// native call is skipped and only the base class's bookkeeping below runs - which is
// still required: it is what InitCapabilities and SwapEGLBuffers' current-thread record
// hang off. Monolith transport in this build, and the pull build, bind exactly as before.
//
// AND ONLY FOR THE SAME VIRTUAL TUPLE (ID-67). The skip is keyed on NativeBindCanBeSkippedFor:
// the surface's own creation bind is adopted by the FIRST tuple, an identical tuple skips,
// and a DIFFERENT tuple - a second MobileGL context onto the same surface - runs the native
// call again even though the driver's triple is the same, because MakeCurrent's seven
// invalidations describe the frontend context that is changing. Red once, two ways:
// make this arm unconditional (ServerLoopTest's C7 control reads 2 native binds at the EGL
// function table instead of 1), or make NativeBindCanBeSkippedFor answer true for any tuple
// (the ID-67 control's different tuple stays at 1 native bind where 2 are required).
const Bool nativelyCurrentAlready = MG_Config::Transport != MG_Config::TransportMode::Monolith &&
DirectGLES::IsBackendContextCurrentOnThisThread() &&
(surfaceless || (m_eglSurfaceInitialized && m_eglSurface == draw &&
NativeBindCanBeSkippedFor(dpy, draw, read, ctx)));
if (!nativelyCurrentAlready && !DirectGLES::MakeCurrent()) {
NoteNativeContextGone();
if (!m_eglSurfaceInitialized) {
MGLOG_E("MakeEGLCurrent failed: EGL surface is not initialized");
return false;
}
NoteNativeBoundFor(dpy, draw, read, ctx);
#else
if (draw == EGL_NO_SURFACE || read == EGL_NO_SURFACE || ctx == EGL_NO_CONTEXT) {
MGLOG_E("MakeEGLCurrent failed: draw/read/context is invalid");
return false;
}
if (!DirectGLES::MakeCurrent()) {
return false;
}
#endif
if (!BackendObject::MakeEGLCurrent(dpy, draw, read, ctx)) {
(void)DirectGLES::ReleaseCurrent();
#if MOBILEGL_BUILD_DISAGGREGATED
NoteNativeContextGone();
#endif
return false;
}
// A HOST-FRAMED SURFACE HAS TO BE PUT BACK AFTER EVERY MAKE-CURRENT. The native call
// binds the surface's own default framebuffer - the pbuffer this path makes its context
// with - and that is not where these pixels go. Both the driver and the engine's binding
// shadow have to be told again, or the next default-framebuffer bind is deduped away and
// every draw lands in a pbuffer nobody sees.
if (m_eglSurfaceKind == SurfaceKind::HostFrame && m_hostFrameTarget.Framebuffer != 0) {
FramebufferImpl::InvalidateFramebufferBindingCache();
HostFrameTargetBind(HostFrameDrawTarget());
}
return true;
}
@@ -1401,18 +981,12 @@ namespace MobileGL::MG_Backend::DirectGLES {
void BackendObject_DirectGLES::ReleaseEGLResources() {
const std::lock_guard<std::recursive_mutex> lock(m_eglStateMutex);
DestroyEGLContext();
#if MOBILEGL_BUILD_DISAGGREGATED
NoteNativeContextGone();
#endif
BackendObject::ReleaseEGLResources();
}
void BackendObject_DirectGLES::OnEGLSurfaceReleased(EGLSurface surface) {
(void)surface;
DestroyEGLContext();
#if MOBILEGL_BUILD_DISAGGREGATED
NoteNativeContextGone();
#endif
}
const RendererInfo& BackendObject_DirectGLES::GetRendererInfo() const {
@@ -1542,40 +1116,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
// 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,
// kwin_wayland 6.7.3 will not use a context it cannot drive, and it asks for these
// three names first: EglContext::checkSupported() (src/opengl/eglcontext.cpp) takes the
// DESKTOP-OpenGL branch for every context whose GL_VERSION is not an "OpenGL ES"
// string, and that branch requires GL_ARB_shader_objects, GL_ARB_fragment_shader and
// GL_ARB_vertex_shader. GL_VERSION here is "4.6.0 MobileGL ...", so with the names
// missing checkSupported() answered false, EglContext::create() returned nullptr,
// EglBackend::createContext() returned false, and kwin printed "Could not initialize
// rendering context" and quit before drawing a frame.
//
// The three are true statements about this backend now rather than a test unlock: every
// procedure they define is implemented in MG_Impl/GLImpl/Exporting/Definitions.cpp over
// the same shader and program objects the core entry points drive - the 39 of
// ARB_shader_objects, ARB_vertex_shader's three attrib-location entry points, and none
// at all for ARB_fragment_shader ("New Procedures and Functions: None" - it is the
// capability half, and the reason kwin's conjunction names it).
E_GL_ARB_shader_objects, E_GL_ARB_vertex_shader, E_GL_ARB_fragment_shader,
// NPOT textures: core since GL 2.0, and every host this backend can run on provides
// them. Full non-power-of-two support - mipmapping and every wrap mode, not ES 2.0's
// CLAMP_TO_EDGE-only exception - is required from ES 3.0 on, and the entries this list
// already advertises without any gate (compute shaders, shader storage buffers,
// indirect draws) need an ES 3.1 host. Nothing in the texture path rejects or pads a
// non-power-of-two size - storage and sampling are forwarded to that host - so the
// string describes what an application actually gets.
E_GL_ARB_texture_non_power_of_two,
// GL_OES_EGL_image: the entry points are real (MG_Impl/GLImpl/Exporting/Definitions.cpp)
// and this name is what makes them reachable - libepoxy in kwin resolves
// glEGLImageTargetTexture2DOES BY NAME and refuses the import path without it, printing
// "No provider of glEGLImageTargetTexture2DOES found. Requires one of: GL_OES_EGL_image".
// That import path is how the compositor's scene reaches the display daemon's dma-bufs.
// The render-server half of the import (fd over the GBM socket, then the server-side
// EGLImage) is the next change; until it lands an imported texture has no storage behind
// it, which is logged once at the entry point rather than left to look like a black frame.
E_GL_OES_EGL_image};
E_GL_ARB_get_program_binary};
// Minecraft 26.3 checks this prerequisite before it even considers
// GL_ARB_multi_draw_indirect. ES 3.1 supplies both single-draw entry points; the loader
// folds the version and pointer checks into SupportsDrawIndirect.
@@ -1714,6 +1255,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
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.ShaderStorageBlockBinding = ShaderStorageBlockBinding;
funcsTable.GL.Clear = Clear;
funcsTable.GL.ClearBufferfi = ClearBufferfi;
@@ -1874,13 +1417,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
clampStageStorageBlocks(m_GLESCapabilities.MaxFragmentShaderStorageBlocks);
m_dynamicParameters.MaxComputeUniformBlocks = m_GLESCapabilities.MaxComputeUniformBlocks;
m_dynamicParameters.MaxComputeWorkGroupInvocations = m_GLESCapabilities.MaxComputeWorkGroupInvocations;
// The six per-axis compute limits: the driver's raw glGetIntegeri_v answers, the same
// numbers GLFunctionsTable::GetIntegeri_v forwards live. Carried here so that MGPCaps has
// them once the table entry retires (plan B section 4.4.1); GL_Getter floors them.
for (SizeT axis = 0; axis < 3; ++axis) {
m_dynamicParameters.MaxComputeWorkGroupCount[axis] = m_GLESCapabilities.MaxComputeWorkGroupCount[axis];
m_dynamicParameters.MaxComputeWorkGroupSize[axis] = m_GLESCapabilities.MaxComputeWorkGroupSize[axis];
}
// (MaxShaderStorageBufferBindings is assigned above, before the per-stage clamp reads it.)
// This is the number glGetIntegerv(GL_MAX_TEXTURE_BUFFER_SIZE) hands the application, and
// on a host without buffer textures it is knowingly a floor MobileGL cannot honour rather
MobileGL/MG_Backend/DirectGLES/BackendObject_DirectGLES.h
-41
View File
@@ -8,9 +8,6 @@
#pragma once
#include <Includes.h>
#include "HostFrameTarget.h"
#include "MG_Backend/HostFrameBridge.h"
#include "MG_Backend/GbmFrameChannel.h"
#include "../BackendObject.h"
#include <MG_Util/BackendLoaders/OpenGL/Loader.h>
@@ -59,46 +56,8 @@ namespace MobileGL::MG_Backend::DirectGLES {
private:
void UpdateDynamicBackendParameters();
Bool InitPbufferSurface(EGLint width, EGLint height) override;
// A host-framed surface draws into a frame the display host owns; presenting one
// tells the host the frame is drawn, because the host is what puts it on the glass.
// NOT CreateEGLHostFrameSurface: the base class registers the surface and activates it,
// and activation is what reaches InitHostFrameSurface below. There is nothing about the
// EGL side of a host-framed surface this backend needs to do its own way.
Bool InitHostFrameSurface(EGLint width, EGLint height) override;
Bool PresentHostFrame() override;
// Takes the next frame from the host and makes it this context's framebuffer.
Bool TakeHostFrame();
void DestroyHostFrame();
// The canvas the compositor draws into, made once at the first frame's size.
Bool EnsureHostFrameCanvas(Uint width, Uint height);
// Copies the canvas into the frame about to be presented.
void BlitHostFrameCanvas();
// What draws resolve to: the canvas when there is one, the frame itself otherwise.
const HostFrameTarget& HostFrameDrawTarget() const {
return m_hostFrameCanvas.Framebuffer != 0 ? m_hostFrameCanvas : m_hostFrameTarget;
}
void OnEGLSurfaceReleased(EGLSurface surface) override;
// MOBILEGL_IPC_SURFACE=host: the frames the display host owns, one at a time, which
// is what the host offers - it hands one over and waits for the answer before it
// presents it and offers the next.
MG_Backend::HostFrameBridge m_hostFrameBridge;
// The frames the bridge just took, on to the container: the Wayland compositor over there
// renders into this same memory, and the only route to it that end has is the dma-buf
// descriptor this channel offers per frame and reads a release back from.
MG_Backend::GbmFrameChannel m_gbmFrameChannel;
HostFrameTarget m_hostFrameTarget;
// A STABLE TARGET IN FRONT OF THE FRAMES. Every present hands the frame back and takes
// a different one, and its renderbuffer is deleted with it - but a compositor attaches
// its framebuffers ONCE (kwin: one per daemon buffer, for the life of the process), so
// attachments bound to a frame's own renderbuffer named a deleted object from the second
// frame on. The attachments name this instead, and each present copies it into the
// frame. No EGLImage behind it (Image stays null).
HostFrameTarget m_hostFrameCanvas;
struct AHardwareBuffer* m_hostFrameBuffer = nullptr;
MG_Backend::HostFrameOffer m_hostFrameOffer{};
Bool m_hostFrameBridgeOpen = false;
Bool m_initialized = false;
MG_External::EGLFunctionsTable m_EGLFunctions;
MG_External::GLESFunctionsTable m_GLESFunctions;
MobileGL/MG_Backend/DirectGLES/ContextEpoch.h
-23
View File
@@ -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.cpp
+511 -7164
View File
File diff suppressed because it is too large Load Diff
MobileGL/MG_Backend/DirectGLES/DirectGLES.h
+2 -36
View File
@@ -30,15 +30,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
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 MOBILEGL_BUILD_DISAGGREGATED
Bool ReadTextureImageWire(const MG_Pipe::MGPReadbackInfo& info, Vector<Uint8>& bytes);
// Whether the NATIVE texture currently holds `level` of `uploadTarget` at `logicalExtent`
// (glGetTexLevelParameteriv). False for a level the driver never allocated - one defined after
// the texture's last sync - so a re-mint does not read what is not there. A query the driver
// refuses answers true, keeping the caller on its readback path.
Bool NativeTextureLevelHasExtent(GLuint texture, TextureTarget target, TextureUploadTarget uploadTarget,
GLint level, const IntVec3& logicalExtent);
#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);
@@ -108,6 +99,8 @@ 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 GetInteger64i_v(GLenum target, GLuint index, GLint64* data);
void GetProgramiv(GLuint program, GLenum pname, GLint* params);
void ShaderStorageBlockBinding(GLuint program, const GLchar* storageBlockName, GLuint storageBlockBinding);
Bool InitWindowSurface(NativeWindowType window);
Bool InitPbufferSurface(EGLint width, EGLint height);
@@ -194,13 +187,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
// 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);
@@ -249,26 +235,6 @@ namespace MobileGL::MG_Backend::DirectGLES {
void InvalidateSyncedRenderState();
} // namespace RenderStateImpl
// MOBILEGL_IPC_SURFACE=host: what the client's DEFAULT framebuffer means while a host-framed
// surface is current. Zero everywhere else, because the driver's own 0 IS the EGL surface
// then - but on a host-framed surface the pixels belong to a frame the display host owns,
// and drawing into the driver's 0 would draw into a pbuffer nobody ever sees.
extern Uint g_hostFrameFramebufferId;
// WHAT THE HOST FRAME'S STORAGE IS, for the one caller that has to bind it in place of a
// storage-less attachment: an imported dma-buf is the display host's frame (same memory, same
// size), and the frame's storage is a RENDERBUFFER (HostFrameTarget.cpp binds it with
// glFramebufferRenderbuffer). A texture argument cannot name it, which is why these exist and
// why g_hostFrameFramebufferId alone was not enough. Zero whenever no frame is held.
extern Uint g_hostFrameRenderbuffer;
extern Uint g_hostFrameWidth;
extern Uint g_hostFrameHeight;
// TAKE THE FRAME WHEN NOTHING ELSE WILL. On the anland route the container's compositor never
// creates a window surface, so ActivateEGLSurface never runs and InitHostFrameSurface is never
// reached: the FIRST proof that the display host's frame is wanted is an ATTACHMENT of an
// imported external texture (Managers.cpp's 0x8D65 arm), and that is where the frame has to be
// taken. The host's own offer carries the width/height, so the numbers passed here are only
// what the bridge logs. Answers false (and changes nothing) whenever no backend is up.
Bool TakeHostFrameForExternalTexture(Uint width, Uint height);
extern MG_External::EGLFunctionsTable g_EGLFuncs;
extern MG_External::GLESFunctionsTable g_GLESFuncs;
extern MG_External::GLESCapabilities g_GLESCapabilities;
MobileGL/MG_Backend/DirectGLES/HostFrameTarget.cpp
-208
View File
@@ -1,208 +0,0 @@
// MobileGL - MobileGL/MG_Backend/DirectGLES/HostFrameTarget.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
#include "HostFrameTarget.h"
#include "DirectGLES.h"
#include "Managers.h"
#if MOBILEGL_BUILD_DISAGGREGATED && defined(__ANDROID__)
#include <android/hardware_buffer.h>
#include <cstring>
#include <format>
namespace MobileGL::MG_Backend::DirectGLES {
namespace {
// The four entry points this is spelled in are optional everywhere: the loader's own
// tables do not carry them (a missing EGL function there is MGLOG_F), so the extension
// strings decide first and the pointers are taken only once they have.
using GetNativeClientBufferFn = EGLClientBuffer (*)(const struct AHardwareBuffer*);
using CreateImageFn = EGLImageKHR (*)(EGLDisplay, EGLContext, EGLenum, EGLClientBuffer, const EGLint*);
using DestroyImageFn = EGLBoolean (*)(EGLDisplay, EGLImageKHR);
using ImageTargetRenderbufferFn = void (*)(GLenum, GLeglImageOES);
Bool HasExtensionWord(const char* list, const char* word) {
if (list == nullptr) return false;
const SizeT n = std::strlen(word);
for (const char* at = std::strstr(list, word); at != nullptr; at = std::strstr(at + 1, word)) {
const Bool startOk = at == list || at[-1] == ' ';
const Bool endOk = !at[n] || at[n] == ' ';
if (startOk && endOk) return true;
}
return false;
}
struct EntryPoints {
GetNativeClientBufferFn GetNativeClientBuffer = nullptr;
CreateImageFn CreateImage = nullptr;
DestroyImageFn DestroyImage = nullptr;
ImageTargetRenderbufferFn TargetRenderbuffer = nullptr;
};
// Resolved once per process and cached together with the refusal: a driver that lacks one
// of these does not grow it later, and the answer names what is missing.
const EntryPoints& Resolved(String& why) {
static EntryPoints points;
static Bool resolved = false;
static String refusal;
if (!resolved) {
resolved = true;
if (!g_EGLFuncs.eglGetProcAddress || !g_EGLFuncs.eglQueryString || !g_EGLFuncs.eglGetCurrentDisplay ||
!g_GLESFuncs.glGetString) {
refusal = "the loader has no eglGetProcAddress/eglQueryString/eglGetCurrentDisplay/glGetString";
} else {
const char* egl = g_EGLFuncs.eglQueryString(g_EGLFuncs.eglGetCurrentDisplay(), EGL_EXTENSIONS);
const char* gl = reinterpret_cast<const char*>(g_GLESFuncs.glGetString(GL_EXTENSIONS));
if (!HasExtensionWord(egl, "EGL_ANDROID_get_native_client_buffer")) {
refusal = "EGL_ANDROID_get_native_client_buffer is not advertised";
} else if (!HasExtensionWord(egl, "EGL_KHR_image_base")) {
refusal = "EGL_KHR_image_base is not advertised";
} else if (!HasExtensionWord(gl, "GL_OES_EGL_image")) {
refusal = "GL_OES_EGL_image is not advertised";
} else {
points.GetNativeClientBuffer = reinterpret_cast<GetNativeClientBufferFn>(
g_EGLFuncs.eglGetProcAddress("eglGetNativeClientBufferANDROID"));
points.CreateImage =
reinterpret_cast<CreateImageFn>(g_EGLFuncs.eglGetProcAddress("eglCreateImageKHR"));
points.DestroyImage =
reinterpret_cast<DestroyImageFn>(g_EGLFuncs.eglGetProcAddress("eglDestroyImageKHR"));
points.TargetRenderbuffer = reinterpret_cast<ImageTargetRenderbufferFn>(
g_EGLFuncs.eglGetProcAddress("glEGLImageTargetRenderbufferStorageOES"));
if (points.GetNativeClientBuffer == nullptr || points.CreateImage == nullptr ||
points.DestroyImage == nullptr || points.TargetRenderbuffer == nullptr) {
refusal = "eglGetProcAddress gave no eglGetNativeClientBufferANDROID / eglCreateImageKHR / "
"eglDestroyImageKHR / glEGLImageTargetRenderbufferStorageOES";
points = EntryPoints{};
}
}
}
}
why = refusal;
return points;
}
void DrainGLErrors() {
if (!g_GLESFuncs.glGetError) return;
for (Uint guard = 0; guard < 16 && g_GLESFuncs.glGetError() != GL_NO_ERROR; ++guard) {
}
}
}
Bool HostFrameTargetSupported(String& why) {
const EntryPoints& points = Resolved(why);
return points.GetNativeClientBuffer != nullptr;
}
Bool HostFrameTargetCreate(const struct AHardwareBuffer* buffer, HostFrameTarget& target, String& why) {
target = HostFrameTarget{};
if (buffer == nullptr) {
why = "no buffer";
return false;
}
const EntryPoints& points = Resolved(why);
if (points.GetNativeClientBuffer == nullptr) return false;
if (!g_GLESFuncs.glGenRenderbuffers || !g_GLESFuncs.glBindRenderbuffer || !g_GLESFuncs.glGenFramebuffers ||
!g_GLESFuncs.glBindFramebuffer || !g_GLESFuncs.glFramebufferRenderbuffer ||
!g_GLESFuncs.glCheckFramebufferStatus) {
why = "the loader has no glGenRenderbuffers/glBindRenderbuffer/glGenFramebuffers/glBindFramebuffer/"
"glFramebufferRenderbuffer/glCheckFramebufferStatus";
return false;
}
AHardwareBuffer_Desc desc{};
AHardwareBuffer_describe(buffer, &desc);
DrainGLErrors();
const EGLClientBuffer clientBuffer = points.GetNativeClientBuffer(buffer);
if (clientBuffer == nullptr) {
why = "eglGetNativeClientBufferANDROID returned null";
return false;
}
const EGLint imageAttribs[] = {EGL_IMAGE_PRESERVED_KHR, EGL_TRUE, EGL_NONE};
const EGLImageKHR image =
points.CreateImage(g_EGLFuncs.eglGetCurrentDisplay(), EGL_NO_CONTEXT, EGL_NATIVE_BUFFER_ANDROID,
clientBuffer, imageAttribs);
if (image == EGL_NO_IMAGE_KHR) {
why = "eglCreateImageKHR(EGL_NATIVE_BUFFER_ANDROID) refused the host frame";
return false;
}
GLuint renderbuffer = 0;
g_GLESFuncs.glGenRenderbuffers(1, &renderbuffer);
g_GLESFuncs.glBindRenderbuffer(GL_RENDERBUFFER, renderbuffer);
points.TargetRenderbuffer(GL_RENDERBUFFER, reinterpret_cast<GLeglImageOES>(image));
const GLenum renderbufferError = g_GLESFuncs.glGetError ? g_GLESFuncs.glGetError() : GL_NO_ERROR;
if (renderbufferError != GL_NO_ERROR) {
why = std::format("glEGLImageTargetRenderbufferStorageOES -> 0x{:04x}", renderbufferError);
g_GLESFuncs.glDeleteRenderbuffers(1, &renderbuffer);
points.DestroyImage(g_EGLFuncs.eglGetCurrentDisplay(), image);
return false;
}
GLuint framebuffer = 0;
g_GLESFuncs.glGenFramebuffers(1, &framebuffer);
g_GLESFuncs.glBindFramebuffer(GL_FRAMEBUFFER, framebuffer);
g_GLESFuncs.glFramebufferRenderbuffer(GL_FRAMEBUFFER, GL_COLOR_ATTACHMENT0, GL_RENDERBUFFER, renderbuffer);
const GLenum status = g_GLESFuncs.glCheckFramebufferStatus(GL_FRAMEBUFFER);
if (status != GL_FRAMEBUFFER_COMPLETE) {
why = std::format("the host frame as a color attachment -> framebuffer status 0x{:04x}", status);
g_GLESFuncs.glDeleteFramebuffers(1, &framebuffer);
g_GLESFuncs.glDeleteRenderbuffers(1, &renderbuffer);
points.DestroyImage(g_EGLFuncs.eglGetCurrentDisplay(), image);
return false;
}
target.Image = image;
target.Renderbuffer = renderbuffer;
target.Framebuffer = framebuffer;
target.Width = desc.width;
target.Height = desc.height;
MGLOG_I("host frame target: %ux%d as framebuffer %u (stride %u, format 0x%x)", desc.width, desc.height,
framebuffer, desc.stride, desc.format);
return true;
}
void HostFrameTargetBind(const HostFrameTarget& target) {
if (target.Framebuffer == 0) return;
// THROUGH THE ENGINE'S SHADOW, never raw: a raw bind would leave the shadow claiming
// the previous framebuffer and false-skip the next re-bind (FramebufferImpl, Managers.h).
FramebufferImpl::BindFramebufferId(GL_FRAMEBUFFER, target.Framebuffer);
}
void HostFrameTargetDestroy(HostFrameTarget& target) {
if (target.Framebuffer != 0 && g_GLESFuncs.glDeleteFramebuffers)
g_GLESFuncs.glDeleteFramebuffers(1, &target.Framebuffer);
if (target.Renderbuffer != 0 && g_GLESFuncs.glDeleteRenderbuffers)
g_GLESFuncs.glDeleteRenderbuffers(1, &target.Renderbuffer);
if (target.Image != nullptr) {
String why;
const EntryPoints& points = Resolved(why);
if (points.DestroyImage != nullptr && g_EGLFuncs.eglGetCurrentDisplay)
points.DestroyImage(g_EGLFuncs.eglGetCurrentDisplay(), static_cast<EGLImageKHR>(target.Image));
}
target = HostFrameTarget{};
}
}
#else // !(MOBILEGL_BUILD_DISAGGREGATED && __ANDROID__)
namespace MobileGL::MG_Backend::DirectGLES {
Bool HostFrameTargetSupported(String& why) {
why = "host frames are a disaggregated Android path";
return false;
}
Bool HostFrameTargetCreate(const struct AHardwareBuffer*, HostFrameTarget&, String& why) {
why = "host frames are a disaggregated Android path";
return false;
}
void HostFrameTargetBind(const HostFrameTarget&) {}
void HostFrameTargetDestroy(HostFrameTarget& target) { target = HostFrameTarget{}; }
}
#endif
MobileGL/MG_Backend/DirectGLES/HostFrameTarget.h
-52
View File
@@ -1,52 +0,0 @@
// MobileGL - MobileGL/MG_Backend/DirectGLES/HostFrameTarget.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 <EGL/egl.h>
#include <EGL/eglext.h>
struct AHardwareBuffer;
namespace MobileGL::MG_Backend::DirectGLES {
// THE FRAME THE DISPLAY HOST IS ABOUT TO SCAN OUT, AS A DRAW TARGET.
//
// The display host (the Android side that owns the screen) allocates its frames itself and
// offers each one over a socket as an AHardwareBuffer. That is not a convenience: measured
// on the device, AHardwareBuffer_createFromHandle accepts an AHardwareBuffer this side
// allocated and refuses one the display queue handed over (gralloc BAD_VALUE), so the frames
// a render server can draw into are the ones the host made for it.
//
// What this makes of such a frame: an EGLImage the driver accepts as a renderbuffer, and a
// framebuffer that is the drawing target while that frame is the current one. None of
// Android's window machinery is involved - no ANativeWindow, no SurfaceFlinger - which is
// the point: the host puts the frame on the glass when this side says it is drawn.
struct HostFrameTarget {
void* Image = nullptr; // EGLImageKHR; opaque here so this header stays free of EGL types
Uint Renderbuffer = 0;
Uint Framebuffer = 0;
Uint Width = 0;
Uint Height = 0;
};
// Whether the driver advertises what this is spelled in. False is answered with the missing
// name in `why`, never an abort: a server that cannot take host frames has to be able to
// say so.
Bool HostFrameTargetSupported(String& why);
// Imports `buffer` as a render target. On failure `target` is left empty and `why` says
// which call refused; no GL name is leaked.
Bool HostFrameTargetCreate(const struct AHardwareBuffer* buffer, HostFrameTarget& target, String& why);
// Binds the target as the current draw framebuffer, called when its frame becomes current.
void HostFrameTargetBind(const HostFrameTarget& target);
// Drops the GL names and the EGLImage. The AHardwareBuffer belongs to the bridge, which
// releases it; this never touches it.
void HostFrameTargetDestroy(HostFrameTarget& target);
}
MobileGL/MG_Backend/DirectGLES/Managers.cpp
+250 -8115
View File
File diff suppressed because it is too large Load Diff
MobileGL/MG_Backend/DirectGLES/Managers.h
+32 -1896
View File
File diff suppressed because it is too large Load Diff
MobileGL/MG_Backend/DirectGLES/MultiDraw.cpp
+52 -275
View File
@@ -9,9 +9,6 @@
#include "MultiDraw.h"
#include "Managers.h"
#include <MG_State/GLState/Core.h>
#include <MG_Pipe/PipeInputsSwitch.h>
#include <MG_Util/Metrics/PipeStats.h>
#include <cstdlib>
#include <cstring>
#include <limits>
@@ -44,14 +41,14 @@ namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
// verbatim is already "this batch restarts nowhere".
Uint32 RestartSentinelFor(GLenum type) {
if (ResolveRestartSubstitution(type) != RestartSubstitutionKind::None) {
return MGB_CTX->GetPrimitiveRestartIndex();
return MG_State::pGLContext->GetPrimitiveRestartIndex();
}
return MG_Util::FixedRestartIndexForGLType(type);
}
Bool RestartActive() {
return MGB_CTX->IsCapabilityEnabled(CapabilityInput::PrimitiveRestart) ||
MGB_CTX->IsCapabilityEnabled(CapabilityInput::PrimitiveRestartFixedIndex);
return MG_State::pGLContext->IsCapabilityEnabled(CapabilityInput::PrimitiveRestart) ||
MG_State::pGLContext->IsCapabilityEnabled(CapabilityInput::PrimitiveRestartFixedIndex);
}
// Vertices per primitive for the modes whose sub-draws may be concatenated into a
@@ -84,173 +81,19 @@ namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
constexpr SizeT kMaxComputeWorkGroups = 65535;
constexpr SizeT kMaxComputeFlattenedIndices = kMaxComputeWorkGroups * kComputeWorkGroupSize;
// BoundDrawIndirectBufferId MOVED (P5e ra2, ID-136) to sit beside BoundIndexBufferId,
// which is the same question about the other target and now has the same two arms.
// ---------------------------------------------------------------------------
// The bound index buffer, and WHICH SIDE ANSWERS FOR IT
//
// P5e (mv), CONTRACT-P5E §5.1 + §5.8 (ruling ID-81): this file asks the bound element
// array buffer exactly three questions - "is one bound at all", "what GL name did
// PrepareForDraw leave on GL_ELEMENT_ARRAY_BUFFER (and how big is its store)", and
// "give me its bytes on the CPU" - and until now it asked all three of the FRONTEND
// VAO, on the apply thread, once per indexed multi-draw. That was the last unguarded
// `MGB_CTX->GetBoundVertexArray()` in the backend: package vi retired the ordinary
// draw path's copy (DirectGLES.cpp's SyncCurrentVertexAttributeValues / PrepareForDraw)
// and this one survived only because these batches used to die earlier, on the
// framebuffer row fb has since retired.
//
// THE ARM IS STATED, NEVER INFERRED. BufferImpl::VertexInputReadsRecords() is the
// family's own selector and reduces to `Transport != Monolith && the vertex-input bit`;
// it is the same conjunction RefuseElementArrayBufferFromTheFrontend guards the
// single-draw path with. Nothing below decides an arm by noticing that a handle or a
// pointer happens to be null - conflating "a handle was noted" with "the record arm is
// selected" is what ID-107 cost this phase 137 scenarios.
// ---------------------------------------------------------------------------
// How much of the index buffer a caller needs. DELIBERATELY not nested levels: each
// value is exactly the work its original call site did, in its original order, so the
// monolith arm makes the same calls in the same sequence it made before this package.
enum class IndexBufferQuestion {
Presence, // is an element array buffer bound at all
DriverName, // + the GL name currently bound to GL_ELEMENT_ARRAY_BUFFER
DriverNameAndSize,// + the store's size in bytes (the compute tier's source)
HostBytes, // a CPU-readable copy of the whole store, and its size
};
struct BoundIndexBufferView {
Bool Present = false;
Uint Id = 0; // DriverName*: 0 when there is no backend store yet
SizeT Size = 0; // DriverNameAndSize / HostBytes
const Uint8* HostBytes = nullptr; // HostBytes: null when there is no CPU copy
};
#if MOBILEGL_BUILD_DISAGGREGATED
// A missing record on the handle arm is a NAMED refusal and never a quiet fall-back to
// the frontend (TASK-mv requirement 2; the shape is Managers.cpp's
// RefuseNullFrontendTextureOffTheHandleArm). The frontend element slot is not a second
// opinion on this side: it answers for whatever the CLIENT has bound NOW, which is a
// later draw than the one being applied. Drawing a batch from it would be a silently
// wrong picture, which is precisely what MultiDrawScenario's batch-matches-unrolled
// assertions exist to catch and what a fall-back would hide from them.
[[noreturn]] void RefuseMissingIndexBufferRecord(const char* entry, MG_Pipe::MGPipeHandle res,
const char* missing) {
MGLOG_F("MGPipe: Fatal{RoleViolation, \"multidraw-index-buffer-arm\"} - %s found no %s for "
"the index buffer {%u, %u} this batch's record named. The index buffer of this "
"family is MGPipeApplier().IndexBuffer.Res (CONTRACT-P5E §5.1) and the arm is "
"selected by Transport != Monolith AND the vertex-input subsystem bit (§5.8, "
"ID-81); falling back to the frontend VAO's element slot here would draw this "
"multi-draw from whatever the CLIENT has bound now",
entry, missing, res.Slot, res.Gen);
std::abort();
Uint BoundDrawIndirectBufferId() {
const auto& indirect =
MG_State::pGLContext->GetBufferBindingSlot(BufferTarget::DrawIndirect).GetBoundObject();
if (!indirect) return 0;
const auto* resource = BufferImpl::EnsureBufferResource(indirect);
return resource ? resource->id : 0;
}
// ---- P5e (ra2), ID-136: THE SAME REFUSAL FOR THE INDIRECT TARGET -------------------
//
// A sibling of mv's rather than a second idiom, because it is the same sentence about
// the other buffer target: a missing record on the handle arm aborts by name and never
// falls back to the frontend binding slot, which answers for whatever the CLIENT has
// bound NOW - a later verb than the one being applied.
[[noreturn]] void RefuseMissingIndirectBufferRecord(const char* entry,
MG_Pipe::MGPipeHandle res) {
MGLOG_F("MGPipe: Fatal{RoleViolation, \"multidraw-indirect-buffer-arm\"} - %s found no "
"backend resource for the indirect buffer {%u, %u} this verb's record named. "
"The indirect buffer of this family is MGPipeApplier().VerbIndirectBuffer "
"(CONTRACT-P5E §2.1) and the arm is selected by Transport != Monolith "
"(ID-81); falling back to the frontend GL_DRAW_INDIRECT_BUFFER slot here "
"would restore whatever the CLIENT has bound now",
entry, res.Slot, res.Gen);
std::abort();
}
// Does the applier's record say the application SUPPLIED this store's content? The M-3
// rule ScopedRestartIndexSubstitution spells: for a supplied store a coverage gap in the
// server shadow is a missing record and Fatal by name; for one the application ORPHANED
// the gap is its own undefined content, and reading the shadow's zero-fill is exactly
// what the monolith arm's MappedData() hands back.
Bool IndexBufferRecordHasDefinedContent(const MG_Pipe::MGPipeApplierState& st,
MG_Pipe::MGPipeHandle res) {
if (res.Slot >= st.Resources.size()) return false;
const auto& candidate = st.Resources[res.Slot];
if (!candidate.Live || candidate.Gen != res.Gen) return false;
return candidate.Desc.HasDefinedContent != 0;
}
#endif
BoundIndexBufferView ResolveBoundIndexBuffer(IndexBufferQuestion question, const char* entry) {
BoundIndexBufferView view;
#if MOBILEGL_BUILD_DISAGGREGATED
if (BufferImpl::VertexInputReadsRecords()) {
const auto& st = MG_Pipe::MGPipeApplier();
const MG_Pipe::MGPipeHandle res = BufferImpl::ResolveDrawIndexBufferFromRecord(st).Res;
// A null Res is "no element array buffer bound", exactly as a null frontend slot
// is on the arm below - the batch's indices are a client array, and every caller
// already has an arm for that. It is NOT the arm test; the arm was decided above.
if (MG_Pipe::MGPipeHandleIsNull(res)) return view;
view.Present = true;
if (question == IndexBufferQuestion::Presence) return view;
if (question == IndexBufferQuestion::HostBytes) {
// The applier has already consumed the persistent-map blocks for this
// resource before the draw verb replayed; the one Sync* this arm owes is the
// monolith's SyncGpuWrites, and (P8-C) SplitHostBytesForCpuRead is it: a store
// a shader wrote on this side is read back from this server's own GL buffer,
// because no writeback ever reaches the server's staged copy. That is also why
// this arm cannot be expressed as "find the object and run the monolith body".
auto* resource = BufferImpl::FindBufferResourceForHandle(res);
if (resource == nullptr) RefuseMissingIndexBufferRecord(entry, res, "backend resource");
view.Size = BufferImpl::ResourceWidthForHandle(res);
view.HostBytes = BufferImpl::SplitHostBytesForCpuRead(*resource, res, "multidraw_index_rebase");
if (view.HostBytes != nullptr && IndexBufferRecordHasDefinedContent(st, res)) {
BufferImpl::RequireStagedCoverage(*resource, view.HostBytes, 0, view.Size,
"multidraw_index_rebase");
}
// A null HostBytes is not a refusal: MappedData() on the monolith arm is
// equally allowed to be null (an adopted coherent map keeps its bytes
// elsewhere), and the one caller that asks declines the tier for it.
return view;
}
auto* resource = BufferImpl::EnsureBufferResourceForHandle(nullptr, res);
if (resource == nullptr) RefuseMissingIndexBufferRecord(entry, res, "backend resource");
view.Id = resource->id;
if (question == IndexBufferQuestion::DriverNameAndSize) {
view.Size = BufferImpl::ResourceWidthForHandle(res);
}
return view;
}
#endif
// MONOLITH GLUE from here down, token for token what each call site did before.
const auto& vao = MGB_CTX->GetBoundVertexArray();
if (!vao) return view;
const auto& ibo = vao->GetIndexBufferBindingSlot().GetBoundObject();
if (!ibo) return view;
view.Present = true;
switch (question) {
case IndexBufferQuestion::Presence:
break;
case IndexBufferQuestion::DriverName: {
const auto* resource = BufferImpl::EnsureBufferResource(ibo);
view.Id = resource ? resource->id : 0;
break;
}
case IndexBufferQuestion::DriverNameAndSize: {
const auto* resource = BufferImpl::EnsureBufferResource(ibo);
view.Id = resource ? resource->id : 0;
view.Size = ibo->GetSize();
break;
}
case IndexBufferQuestion::HostBytes:
// The shadow is the source of truth for CPU reads, but a persistent map or
// a shader write may have moved past it since the last sync.
ibo->SyncPersistentMappedRange();
ibo->SyncGpuWrites();
view.HostBytes = ibo->MappedData();
view.Size = ibo->GetSize();
break;
}
(void)entry;
return view;
const SharedPtr<MG_State::GLState::BufferObject>& BoundIndexBuffer() {
static const SharedPtr<MG_State::GLState::BufferObject> none;
const auto& vao = MG_State::pGLContext->GetBoundVertexArray();
if (!vao) return none;
return vao->GetIndexBufferBindingSlot().GetBoundObject();
}
// The GL name PrepareForDraw left on GL_ELEMENT_ARRAY_BUFFER, i.e. what a tier
@@ -258,57 +101,9 @@ namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
// matters beyond tidiness: the VAO twin memoises that it already synced this
// index binding and will not re-issue it on the next draw.
Uint BoundIndexBufferId() {
return ResolveBoundIndexBuffer(IndexBufferQuestion::DriverName, "BoundIndexBufferId").Id;
}
// The GL name on GL_DRAW_INDIRECT_BUFFER, i.e. what a tier that swaps in its own scratch
// COMMAND buffer has to put back - the exact twin of BoundIndexBufferId above, and now
// with the same two arms.
//
// ---- P5e (ra2), ID-136: THE SEAT THIS FILE'S OWN RULE HAD MISSED -------------------
//
// This was the LAST unguarded frontend read on the multi-draw apply path, and it sat
// twenty lines above the function that retired its neighbour. It asked
// `MGB_CTX->GetBufferBindingSlot(BufferTarget::DrawIndirect)` and then
// `EnsureBufferResource(<frontend object>)` - a registry lookup keyed by the client's
// identity, which is §4.4's rule and not only the allocator's. Under run-ahead that is
// `Fatal{UnmigratedPipeInput, "GetBufferBindingSlot@DrawArrays"}` on every batch the
// indirect tiers execute: 18 lane entries, and the only thing standing between the flip
// and a green lane once the fill race was fixed.
//
// WHAT IT IS NOT: a data dependency. The tier does not want the client's indirect
// buffer - it never reads a byte of it. It binds its OWN scratch command buffer
// (g_indirectCommands) and wants to put back the name that was there. So the answer is
// not "migrate the value" (which is what P8 owes for the ordinary indirect draw path);
// it is "ask the side that did the binding". ID-133's escalation (iii) legalised the
// pull instead, at the price of a rendezvous on every plain glMultiDraw* on the DEFAULT
// tier - a real cost on the shipping arm, paid to make a lane green. ID-136 withdraws
// that escalation and retires the read, in the commit that adds this arm.
//
// WHY MGPipeApplier().VerbIndirectBuffer IS THE WHOLE ANSWER ON THIS ARM: with a
// transport, the ONLY writer of this process's GL_DRAW_INDIRECT_BUFFER outside this
// function is DirectGLES.cpp's DrawSyncBit::IndirectBuffer arm, which binds from exactly
// that handle and nothing else. So "what was bound" IS "what the verb's record named",
// and a null handle is "this verb bound none" - the same 0 the monolith arm returns for
// an empty slot, and not the arm test (ID-110: the arm was decided by the transport
// above, never inferred from a null).
Uint BoundDrawIndirectBufferId() {
#if MOBILEGL_BUILD_DISAGGREGATED
if (MG_Config::Transport != MG_Config::TransportMode::Monolith) {
const MG_Pipe::MGPipeHandle res = MG_Pipe::MGPipeApplier().VerbIndirectBuffer;
if (MG_Pipe::MGPipeHandleIsNull(res)) return 0;
auto* resource = BufferImpl::EnsureBufferResourceForHandle(nullptr, res);
if (resource == nullptr) {
RefuseMissingIndirectBufferRecord("BoundDrawIndirectBufferId", res);
}
return resource->id;
}
#endif
// MONOLITH GLUE from here down, token for token what this function did before.
const auto& indirect =
MGB_CTX->GetBufferBindingSlot(BufferTarget::DrawIndirect).GetBoundObject();
if (!indirect) return 0;
const auto* resource = BufferImpl::EnsureBufferResource(indirect);
const auto& ibo = BoundIndexBuffer();
if (!ibo) return 0;
const auto* resource = BufferImpl::EnsureBufferResource(ibo);
return resource ? resource->id : 0;
}
@@ -361,10 +156,7 @@ namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
// are bound as storage blocks. Respecifies rather than sub-updates: glBufferData
// orphans the previous store, so the upload never waits on a dispatch still reading
// the old contents out of the same name.
// statsClass: which MGPipe byte population these bytes belong to. Counted here
// rather than at the four call sites so a new tier cannot forget it.
Bool UploadScratch(ScratchBuffer& buffer, SizeT bytes, const void* data,
MG_Util::PipeStats::ByteClass statsClass) {
Bool UploadScratch(ScratchBuffer& buffer, SizeT bytes, const void* data) {
if (bytes == 0) return true;
if (!EnsureScratchName(buffer)) return false;
BufferImpl::BindBufferId(BufferImpl::TempBufferTarget, buffer.id);
@@ -377,9 +169,6 @@ namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
buffer.cursor = 0;
if (data) {
g_GLESFuncs.glBufferSubData(BufferImpl::TempBufferTarget, 0, static_cast<GLsizeiptr>(bytes), data);
if (MG_Util::PipeStats::Enabled()) {
MG_Util::PipeStats::AddBytes(statsClass, static_cast<Uint64>(bytes));
}
}
return true;
}
@@ -394,8 +183,7 @@ namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
constexpr SizeT kRingAlignment = 16; // >= 4, so both command and uint32-index offsets stay legal
constexpr SizeT kMinRingBytes = 1u << 16;
Bool UploadScratchRing(ScratchBuffer& buffer, SizeT bytes, const void* data,
MG_Util::PipeStats::ByteClass statsClass, SizeT& outOffset) {
Bool UploadScratchRing(ScratchBuffer& buffer, SizeT bytes, const void* data, SizeT& outOffset) {
outOffset = 0;
if (bytes == 0) return true;
if (!EnsureScratchName(buffer)) return false;
@@ -419,9 +207,6 @@ namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
if (data) {
g_GLESFuncs.glBufferSubData(BufferImpl::TempBufferTarget, static_cast<GLintptr>(outOffset),
static_cast<GLsizeiptr>(bytes), data);
if (MG_Util::PipeStats::Enabled()) {
MG_Util::PipeStats::AddBytes(statsClass, static_cast<Uint64>(bytes));
}
}
buffer.cursor += aligned;
return true;
@@ -564,18 +349,13 @@ namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
}
}
// CPU-readable bytes of one sub-draw's indices, from the CPU copy of the bound index
// buffer (the frontend shadow on the monolith arm, the server's staged shadow on the
// record arm) or straight from the client array. Null when the sub-draw would read
// outside the buffer.
//
// P5e (mv): `hasIndexBuffer` is a Bool and not the frontend object it used to be,
// because presence is the only thing this function ever asked of it - and on the record
// arm there is no such object on this side to hand it.
const Uint8* ResolveSubDrawIndices(Bool hasIndexBuffer, const Uint8* indexBufferBytes,
SizeT indexBufferSize, const void* indices, SizeT indexCount,
SizeT indexSize) {
if (!hasIndexBuffer) {
// CPU-readable bytes of one sub-draw's indices, from the frontend shadow of the
// bound index buffer or straight from the client array. Null when the sub-draw
// would read outside the buffer.
const Uint8* ResolveSubDrawIndices(const SharedPtr<MG_State::GLState::BufferObject>& indexBuffer,
const Uint8* indexBufferBytes, SizeT indexBufferSize, const void* indices,
SizeT indexCount, SizeT indexSize) {
if (!indexBuffer) {
return static_cast<const Uint8*>(indices);
}
if (!indexBufferBytes) return nullptr;
@@ -618,7 +398,8 @@ namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
if (indexSize == 0) return false;
// Indirect commands address indices as an element offset into the bound element
// array buffer, and an indirect draw is not defined without one.
if (!ResolveBoundIndexBuffer(IndexBufferQuestion::Presence, "RunIndirect").Present) return false;
const auto& indexBuffer = BoundIndexBuffer();
if (!indexBuffer) return false;
g_commandStaging.resize(static_cast<SizeT>(drawcount));
for (GLsizei i = 0; i < drawcount; ++i) {
@@ -636,8 +417,7 @@ namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
const SizeT commandBytes = g_commandStaging.size() * sizeof(DrawElementsIndirectCommand);
SizeT commandBase = 0;
if (!UploadScratchRing(g_indirectCommands, commandBytes, g_commandStaging.data(),
MG_Util::PipeStats::ByteClass::StageIndirectCmd, commandBase)) {
if (!UploadScratchRing(g_indirectCommands, commandBytes, g_commandStaging.data(), commandBase)) {
return false;
}
@@ -709,10 +489,17 @@ namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
if (total == 0) return true;
if (total > kMaxFlattenedIndices) return false;
const BoundIndexBufferView indexBuffer =
ResolveBoundIndexBuffer(IndexBufferQuestion::HostBytes, "RunRebasedDrawElements");
const Uint8* const indexBufferBytes = indexBuffer.HostBytes;
const SizeT indexBufferSize = indexBuffer.Size;
const auto& indexBuffer = BoundIndexBuffer();
const Uint8* indexBufferBytes = nullptr;
SizeT indexBufferSize = 0;
if (indexBuffer) {
// The shadow is the source of truth for CPU reads, but a persistent map or
// a shader write may have moved past it since the last sync.
indexBuffer->SyncPersistentMappedRange();
indexBuffer->SyncGpuWrites();
indexBufferBytes = indexBuffer->MappedData();
indexBufferSize = indexBuffer->GetSize();
}
const Bool restartActive = RestartActive();
const Uint32 restartSentinel = RestartSentinelFor(type);
@@ -731,8 +518,8 @@ namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
for (GLsizei i = 0; i < drawcount; ++i) {
if (count[i] <= 0) continue;
const SizeT subDrawCount = static_cast<SizeT>(count[i]);
const Uint8* source = ResolveSubDrawIndices(indexBuffer.Present, indexBufferBytes, indexBufferSize,
indices[i], subDrawCount, indexSize);
const Uint8* source = ResolveSubDrawIndices(indexBuffer, indexBufferBytes, indexBufferSize, indices[i],
subDrawCount, indexSize);
if (!source) {
MGLOG_E_ONCE("DirectGLES multi-draw (drawelements tier): sub-draw %d reads outside the bound index "
"buffer; skipping the batch",
@@ -745,8 +532,7 @@ namespace MobileGL::MG_Backend::DirectGLES::MultiDrawImpl {
}
SizeT indexBase = 0;
if (!UploadScratchRing(g_rebasedIndices, total * sizeof(Uint32), g_indexStaging.data(),
MG_Util::PipeStats::ByteClass::StageIndexClient, indexBase)) {
if (!UploadScratchRing(g_rebasedIndices, total * sizeof(Uint32), g_indexStaging.data(), indexBase)) {
return false;
}
@@ -914,18 +700,16 @@ void main() {
// The shader reads the source indices as a storage buffer, so there has to be
// a real buffer to read - a client-memory index array has none.
if (!ResolveBoundIndexBuffer(IndexBufferQuestion::Presence, "FlattenWithCompute").Present) return;
const auto& indexBuffer = BoundIndexBuffer();
if (!indexBuffer) return;
// A dispatch inside an open capture span is not legal, and the span would also
// observe one merged draw rather than the batch it asked for.
if (XfbImpl::IsCaptureSpanOpen()) return;
// Asked a second time, and one question later: the ensure below may do GL work, so
// it stays BEHIND the capture-span check exactly as it was before P5e (mv).
const BoundIndexBufferView source =
ResolveBoundIndexBuffer(IndexBufferQuestion::DriverNameAndSize, "FlattenWithCompute");
if (source.Id == 0) return;
const SizeT sourceSize = source.Size;
auto* sourceResource = BufferImpl::EnsureBufferResource(indexBuffer);
if (!sourceResource || sourceResource->id == 0) return;
const SizeT sourceSize = indexBuffer->GetSize();
// std430 addresses the source as uint[]; a tail shorter than a word is not
// reachable, so a narrow index type needs a word-multiple buffer.
if (indexSize < 4 && (sourceSize % 4) != 0) return;
@@ -953,18 +737,12 @@ void main() {
if (total == 0) return; // nothing to draw; the ordinary tiers no-op just as well
if (!EnsureComputeProgram()) return;
if (!UploadScratch(g_drawInfo, g_drawInfoStaging.size() * sizeof(Uint32), g_drawInfoStaging.data(),
MG_Util::PipeStats::ByteClass::StageIndirectCmd)) {
return;
}
// data == nullptr: pure respecify, the compute pass writes the contents, so no
// host bytes cross here and nothing is counted.
if (!UploadScratch(g_flattenedIndices, total * sizeof(Uint32), nullptr,
MG_Util::PipeStats::ByteClass::StageIndexClient)) {
if (!UploadScratch(g_drawInfo, g_drawInfoStaging.size() * sizeof(Uint32), g_drawInfoStaging.data())) {
return;
}
if (!UploadScratch(g_flattenedIndices, total * sizeof(Uint32), nullptr)) return;
BufferImpl::BindBufferBaseCached(GL_SHADER_STORAGE_BUFFER, 0, source.Id);
BufferImpl::BindBufferBaseCached(GL_SHADER_STORAGE_BUFFER, 0, sourceResource->id);
BufferImpl::BindBufferBaseCached(GL_SHADER_STORAGE_BUFFER, 1, g_drawInfo.id);
BufferImpl::BindBufferBaseCached(GL_SHADER_STORAGE_BUFFER, 2, g_flattenedIndices.id);
@@ -1108,8 +886,7 @@ void main() {
const Bool arbitraryRestart = restartKind == RestartSubstitutionKind::RewriteIndices;
const ScopedSuppressedPrimitiveRestart restartCapOverride(restartKind);
const Bool hasIndexBuffer =
ResolveBoundIndexBuffer(IndexBufferQuestion::Presence, "DrawElementsBatch").Present;
const Bool hasIndexBuffer = BoundIndexBuffer() != nullptr;
// The compute tier dispatches BEFORE the draw state is established: doing it
// afterwards would mean unpicking the program, SSBO and index bindings
MobileGL/MG_Backend/DirectGLES/SlotTables.h
-785
View File
@@ -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.cpp
+2 -71
View File
@@ -10,9 +10,6 @@
#include "Utils.h"
#include "Managers.h"
#include "MG_Backend/BackendObjects.h"
#if MOBILEGL_BUILD_DISAGGREGATED
#include <MG_Remote/Server/ServerLoop.h>
#endif
#include "MG_Util/Converters/GLToMG/FramebufferEnumConverter.h"
#include "MG_Util/SelfTest/DriverBugProbes.h"
#include "MG_Util/Texture/TextureFormatProcessor.h"
@@ -20,7 +17,6 @@
#include <Config.h>
#include <MG_State/GLState/Core.h>
#include <MG_Pipe/PipeInputsSwitch.h>
#include <MG_Util/BackendLoaders/OpenGL/Loader.h>
#include <MG_Util/Converters/GLToStr/GLEnumConverter.h>
#include <MG_Util/Converters/MGToGL/TextureEnumConverter.h>
@@ -31,45 +27,11 @@
#include <algorithm>
#include <cmath>
#include <cctype>
#include <cstdlib>
#include <cstring>
#include <format>
#include <regex>
namespace MobileGL::MG_Backend::DirectGLES {
#if MOBILEGL_BUILD_DISAGGREGATED
// read_pixels writes server reply scratch. The client refuses PACK_BUFFER before
// emission, so no frontend pack binding can affect this destination.
static const SharedPtr<MG_State::GLState::BufferObject>& SplitReadbackPackBuffer() {
static const SharedPtr<MG_State::GLState::BufferObject> none;
return none;
}
#endif
#if MOBILEGL_BUILD_DISAGGREGATED
const FormatCapabilityCache* ActiveBackendFormatCaps() {
// Under a live split session the SERVER's private backend is what owns the context on the
// apply thread (and these reads all run there), so its cache is the authoritative one.
// Before the session lands, or under monolith transport in a disaggregated build, fall
// back to the process global exactly as the monolith path always has.
if (MG_Config::Transport != MG_Config::TransportMode::Monolith) {
if (MG_Backend::BackendObject* server = MG_Remote::Server::ServerLoopInstance().Backend()) {
return &server->GetFormatCapabilities();
}
// P5c (hd, CONTRACT-P5C §3.7): the mirror fallback is REFUSED with an active
// transport. The server's backend exists whenever the session does, so reaching
// here is a bring-up ordering defect, and a silent read of the client caps mirror
// (pActiveBackendObject is client memory, rule E) would hide it.
MGLOG_F("MGPipe: Fatal{RoleViolation, \"caps-mirror\"} - the format-capability "
"fallback to the client caps mirror was reached with an active transport "
"but no server backend; the server's own backend is the only legal source "
"on the apply thread");
std::abort();
}
return pActiveBackendObject ? &pActiveBackendObject->GetFormatCapabilities() : nullptr;
}
#endif
namespace {
Flags<PixelFormatNormalizeOptionBit> GetForcedPixelFormatNormalizeOptions() {
Flags<PixelFormatNormalizeOptionBit> options;
@@ -108,26 +70,15 @@ namespace MobileGL::MG_Backend::DirectGLES {
SizeT targetIndex,
Bool caveat,
FormatCapability capability) {
#if MOBILEGL_BUILD_DISAGGREGATED
const FormatCapabilityCache* activeCaps = ActiveBackendFormatCaps();
if (activeCaps == nullptr || targetIndex >= kFormatCapabilityTargetCount) {
return false;
}
#else
if (!pActiveBackendObject || targetIndex >= kFormatCapabilityTargetCount) {
return false;
}
#endif
const SizeT formatIndex = static_cast<SizeT>(internalFormat);
if (formatIndex >= kFormatCapabilityFormatCount) {
return false;
}
#if MOBILEGL_BUILD_DISAGGREGATED
const FormatCapabilityCache& cache = *activeCaps;
#else
const FormatCapabilityCache& cache = pActiveBackendObject->GetFormatCapabilities();
#endif
const FormatCapabilityFlags caps =
caveat ? cache.CaveatCaps[targetIndex][formatIndex] : cache.FullCaps[targetIndex][formatIndex];
return HasFormatCapability(caps, capability);
@@ -171,11 +122,7 @@ namespace MobileGL::MG_Backend::DirectGLES {
using namespace MobileGL::MG_Util::TextureFormatProcessor;
const GLenum requestedInternalFormat = MG_Util::ConvertTextureInternalFormatToGLEnum(internalFormat);
Flags<PixelFormatNormalizeOptionBit> options;
#if MOBILEGL_BUILD_DISAGGREGATED
if (ActiveBackendFormatCaps() == nullptr || ShouldUseCaveatFormat(internalFormat, targetIndex)) {
#else
if (!pActiveBackendObject || ShouldUseCaveatFormat(internalFormat, targetIndex)) {
#endif
options = GetRuntimeFallbackNormalizeOptions(
requestedInternalFormat,
TextureImpl::GetRenderTargetNormalizeOptions(g_GLESCapabilities, targetIndex));
@@ -269,15 +216,9 @@ namespace MobileGL::MG_Backend::DirectGLES {
// not be resolved yet - a probe run then would latch "cannot tell" as "clean"
// forever. Once the backend exists, the first narrow-format image this process
// creates runs the probe on a live context.
#if MOBILEGL_BUILD_DISAGGREGATED
if (ActiveBackendFormatCaps() == nullptr) {
return false;
}
#else
if (pActiveBackendObject == nullptr) {
return false;
}
#endif
return MG_Util::SelfTest::CopyImageMirrorsPacked16FieldOrder(g_GLESFuncs);
}
@@ -315,15 +256,9 @@ namespace MobileGL::MG_Backend::DirectGLES {
if (!TargetRequiresRenderableFormat(targetIndex)) {
return false;
}
#if MOBILEGL_BUILD_DISAGGREGATED
if (ActiveBackendFormatCaps() != nullptr && !ShouldUseCaveatFormat(internalFormat, targetIndex)) {
return false;
}
#else
if (pActiveBackendObject && !ShouldUseCaveatFormat(internalFormat, targetIndex)) {
return false;
}
#endif
const GLenum requestedInternalFormat = MG_Util::ConvertTextureInternalFormatToGLEnum(internalFormat);
const Flags<PixelFormatNormalizeOptionBit> options = GetRuntimeFallbackNormalizeOptions(
requestedInternalFormat, GetRenderTargetNormalizeOptions(g_GLESCapabilities, targetIndex));
@@ -2359,15 +2294,11 @@ namespace MobileGL::MG_Backend::DirectGLES {
static Bool StoreClientRows(SizeT dstPixelBytes, SizeT swapGroupSize, GLsizei width, GLsizei sliceHeight,
GLsizei sliceCount, void* pixels, Bool applyPackImageParams, FillRow&& fillRow) {
const auto& pixelPackBufferObject =
#if MOBILEGL_BUILD_DISAGGREGATED
MG_Config::Transport != MG_Config::TransportMode::Monolith
? SplitReadbackPackBuffer() :
#endif
MGB_CTX->GetBufferBindingSlot(BufferTarget::PixelPack).GetBoundObject();
MG_State::pGLContext->GetBufferBindingSlot(BufferTarget::PixelPack).GetBoundObject();
// Destination layout is computed from the client-side PACK parameters; only the actual pixel
// rows are written so skip regions of the destination stay untouched.
const auto packParams = MGB_CTX->GetPixelStoreParameters(false);
const auto packParams = MG_State::pGLContext->GetPixelStoreParameters(false);
const SizeT rowPixels = static_cast<SizeT>(packParams.RowLength > 0 ? packParams.RowLength : width);
const SizeT dstRowStride = AlignReadbackRow(rowPixels * dstPixelBytes, packParams.Alignment);
const SizeT imageRows =
MobileGL/MG_Backend/DirectGLES/Utils.h
-13
View File
@@ -13,19 +13,6 @@
#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:
MobileGL/MG_Backend/DirectGLES/WireTextureReadback.inc
-181
View File
@@ -280,184 +280,3 @@
bytes = Move(result);
return true;
}
#if MOBILEGL_BUILD_DISAGGREGATED
// P9 W2-a. The store's Defined-ness follows the client's respecifies; the driver's follows the
// twin's last sync. A re-mint asks this before reading a level back, because a level defined
// after that sync (null data, or null data plus a partial upload) is not on the driver yet and
// its FBO attachment is incomplete - which used to end the session at
// Fatal{ResourceUnavailable, "image-promotion-readback"} on legal GL.
Bool NativeTextureLevelHasExtent(GLuint texture, TextureTarget target, TextureUploadTarget uploadTarget,
GLint level, const IntVec3& logicalExtent) {
if (!texture || level < 0 || !g_GLESFuncs.glGetTexLevelParameteriv) return true;
const IntVec3 extent = TextureImpl::GetBackendUploadSize(target, logicalExtent);
const GLenum nativeTarget = TextureImpl::ConvertTextureTargetToBackendGLEnum(target);
GLenum binding = GL_NONE;
switch (nativeTarget) {
case GL_TEXTURE_2D: binding = GL_TEXTURE_BINDING_2D; break;
case GL_TEXTURE_3D: binding = GL_TEXTURE_BINDING_3D; break;
case GL_TEXTURE_2D_ARRAY: binding = GL_TEXTURE_BINDING_2D_ARRAY; break;
case GL_TEXTURE_CUBE_MAP: binding = GL_TEXTURE_BINDING_CUBE_MAP; break;
case GL_TEXTURE_CUBE_MAP_ARRAY: binding = GL_TEXTURE_BINDING_CUBE_MAP_ARRAY; break;
default: return true;
}
// A cube's levels are per face; every other target answers for the whole level.
const GLenum queryTarget = nativeTarget == GL_TEXTURE_CUBE_MAP
? TextureImpl::ConvertTextureUploadTargetToBackendGLEnum(uploadTarget) : nativeTarget;
DrainESErrors();
GLint previous = 0;
g_GLESFuncs.glGetIntegerv(binding, &previous);
g_GLESFuncs.glBindTexture(nativeTarget, texture);
GLint width = 0, height = 0, depth = 0;
g_GLESFuncs.glGetTexLevelParameteriv(queryTarget, level, GL_TEXTURE_WIDTH, &width);
g_GLESFuncs.glGetTexLevelParameteriv(queryTarget, level, GL_TEXTURE_HEIGHT, &height);
g_GLESFuncs.glGetTexLevelParameteriv(queryTarget, level, GL_TEXTURE_DEPTH, &depth);
const Bool answered = g_GLESFuncs.glGetError() == GL_NO_ERROR;
g_GLESFuncs.glBindTexture(nativeTarget, static_cast<GLuint>(previous));
if (!answered) return true;
const Bool layered = nativeTarget == GL_TEXTURE_3D || nativeTarget == GL_TEXTURE_2D_ARRAY ||
nativeTarget == GL_TEXTURE_CUBE_MAP_ARRAY;
return width == extent.x() && height == extent.y() && (!layered || depth == extent.z());
}
// P8-E (notes/p8/E.md). MGITEST_ESPRYT_REFUSE_TEXTURE_READBACK_EXTENT=<w>x<h>, READ BY THE SERVER:
// a colour level of exactly that extent is treated as one the driver refused to attach - what an
// Adreno does for RGB16 and the 16-bit SNORM formats, and what no host driver can be made to do.
// Scoped by the extent so the tcp lane's shared supervisor can carry it for the whole lane: only
// the scenario that builds that extent (CopyImageStoreReadbackScenario) ever meets it.
static Bool WireTextureReadbackRefusedForTesting(const IntVec3& extent) {
static const IntVec3 s_refused = [] {
const char* value = std::getenv("MGITEST_ESPRYT_REFUSE_TEXTURE_READBACK_EXTENT");
if (value == nullptr) return IntVec3{0, 0, 0};
char* end = nullptr;
const long width = std::strtol(value, &end, 10);
if (end == value || *end != 'x') return IntVec3{0, 0, 0};
const long height = std::strtol(end + 1, nullptr, 10);
if (width <= 0 || height <= 0) return IntVec3{0, 0, 0};
return IntVec3{static_cast<Int>(width), static_cast<Int>(height), 1};
}();
return s_refused.x() > 0 && extent == s_refused;
}
// P8-E: THE STORE ROUTE, for a level the driver refused to read back. The server's staged store
// is the only CPU copy of the level on this side, and it answers only while its bytes ARE the
// level: every byte crossed (IsCovered), at the extent asked for, and the texture was never
// written by the driver except by copies the store followed (!IsDriverWritten - see
// StagedTextureStore's P8-E block and FollowCopyImageInStagedStore). The conversion is
// GetTexImageViaShadowConversion's, into tight rows: a packed format read with its own type
// takes the stored words verbatim, everything else decodes to wide RGBA and converts row by row.
// Anything else DECLINES BY NAME: the reply is an error, and the client's
// Fatal{ReplyError, "ReadPixels"} ends the session instead of handing back bytes the driver has
// since overwritten.
static Bool ReadWireLevelFromStagedStore(MG_Pipe::MGPipeHandle res, TextureInternalFormat logicalFormat,
TextureUploadTarget uploadTarget, GLint level, const IntVec3& extent,
GLenum format, GLenum type, Vector<Uint8>& bytes) {
auto& store = MG_Remote::Server::ServerStagedTexture();
const Uint64 key = MG_Remote::Server::StagedTextureStore::KeyForHandle(res);
const auto target = static_cast<Uint16>(uploadTarget);
const auto mip = static_cast<Uint16>(level);
ReadbackChannelMapping mapping{};
const SizeT pixelBytes = GetReadbackChannelMapping(format, mapping) ? GetReadbackDstPixelSize(mapping, type) : 0;
const SizeT texels = static_cast<SizeT>(std::max(extent.x(), 0)) * static_cast<SizeT>(std::max(extent.y(), 0)) *
static_cast<SizeT>(std::max(extent.z(), 0));
const char* declined = nullptr;
if (!store.CopiesIntoServerStorage()) {
declined = "this arm keeps no staged store";
} else if (store.IsDriverWritten(key)) {
declined = "the driver has written the texture since its bytes crossed";
} else if (!store.IsCovered(key, target, mip)) {
declined = "not every byte of the level crossed";
} else if (store.LevelExtentOrUndefined(key, target, mip) != extent) {
declined = "the staged level is not the extent asked for";
} else if (pixelBytes == 0 || texels == 0) {
declined = "the format/type pair has no readback mapping";
}
Vector<Uint8> out;
if (declined == nullptr) {
const Uint8* staged = store.RequireLevelBytes(key, target, mip, "texture-readback-from-store");
if (MG_Util::PixelStoreProcessor::IsRawPackedPixelTransfer(
logicalFormat, MG_Util::ConvertGLEnumToTextureInputFormat(format),
MG_Util::ConvertGLEnumToTexturePixelDataType(type))) {
if (store.LevelByteSize(key, target, mip) != texels * pixelBytes) {
declined = "the staged words are not the client's word size";
} else {
out.assign(staged, staged + texels * pixelBytes);
}
} else {
Vector<Uint8> wide;
Bool isInteger = false;
Bool isSigned = false;
if (!MG_Util::PixelStoreProcessor::DecodeShadowDataToWideRGBA(logicalFormat, staged, texels, wide,
isInteger, isSigned)) {
declined = "the staged format has no wide decoding";
} else if (mapping.isInteger != isInteger) {
declined = "an integer read of a normalized level, or the reverse";
} else {
const GLenum wideType = isInteger ? (isSigned ? GL_INT : GL_UNSIGNED_INT) : GL_FLOAT;
const SizeT rowTexels = static_cast<SizeT>(extent.x());
const SizeT rows = texels / rowTexels;
const SizeT wideRowBytes = rowTexels * 4 * GetReadbackComponentSize(wideType);
out.resize(texels * pixelBytes);
for (SizeT row = 0; row < rows; ++row) {
ReadbackImpl::ConvertWideReadbackRow(wide.data() + row * wideRowBytes,
out.data() + row * rowTexels * pixelBytes, rowTexels,
wideType, mapping, type);
}
}
}
}
if (declined != nullptr) {
MGLOG_E_ONCE("MGPipe: texture {%u,%u} level %d: the driver refused the readback and the staged store "
"cannot answer it (%s) - DECLINED (texture-readback-store-declined)",
res.Slot, res.Gen, level, declined);
return false;
}
MGLOG_W_ONCE("MGPipe: texture {%u,%u} level %d: the driver refused the readback (internal format %u); "
"answered from the server's staged store (texture-readback-from-store)",
res.Slot, res.Gen, level, static_cast<unsigned>(logicalFormat));
bytes = Move(out);
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)};
const auto logicalFormat = static_cast<TextureInternalFormat>(record->Desc.InternalFormat);
// The R32UI word leg never goes through a framebuffer, so the knob leaves it alone (it is
// ReadTextureLevelTight's first choice for exactly these reads).
const Bool packedWordRead =
!twin->RequiresImageBindableStorage() &&
MG_Util::PixelStoreProcessor::IsRawPackedPixelTransfer(
logicalFormat, MG_Util::ConvertGLEnumToTextureInputFormat(info.Format),
MG_Util::ConvertGLEnumToTexturePixelDataType(info.Type)) &&
MG_Util::GetInputBytesPerPixel(MG_Util::ConvertGLEnumToTextureInputFormat(info.Format),
MG_Util::ConvertGLEnumToTexturePixelDataType(info.Type)) == sizeof(Uint32);
const Bool refusedForTesting = !packedWordRead && WireTextureReadbackRefusedForTesting(extent);
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 (refusedForTesting ||
!ReadTextureLevelTight(twin->GetBackendTextureId(), target, uploadTarget, logicalFormat, info.Level,
extent, twin->RequiresImageBindableStorage(), info.Format, info.Type, slice)) {
if (!ReadWireLevelFromStagedStore(info.Res, logicalFormat, uploadTarget, info.Level, extent,
info.Format, info.Type, slice)) return false;
}
result.insert(result.end(), slice.begin(), slice.end());
}
bytes = Move(result);
return true;
}
#endif // MOBILEGL_BUILD_DISAGGREGATED
MobileGL/MG_Backend/DirectVulkan/BackendObject_DirectVulkan.cpp
+14 -81
View File
@@ -12,7 +12,6 @@
#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"
@@ -330,29 +329,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
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();
}
// And the swap interval it asked for (DirectVulkan.h).
if (MG_Config::Transport != MG_Config::TransportMode::Monolith) {
ForgetRequestedSwapInterval();
}
}
#else
BackendObject_DirectVulkan::~BackendObject_DirectVulkan() = default;
#endif
BackendObject_DirectVulkan::BackendObject_DirectVulkan() : m_rendererInfo{GetRendererIdentity()} {}
@@ -389,18 +366,6 @@ 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;
}
@@ -422,8 +387,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
UpdateDynamicBackendParameters();
UpdateAdvertisedExtensions();
if (MGB_CTX_LIVE) {
MGB_CTX->InvalidateCompileEnv();
if (MG_State::pGLContext) {
MG_State::pGLContext->InvalidateCompileEnv();
}
PopulateFormatCapabilities(physicalDevice.handle, vkGetPhysicalDeviceFormatProperties, m_vulkanCaps,
MutableFormatCapabilities());
@@ -556,7 +521,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Vector<GLExtension> BuildAdvertisedExtensions(Bool shaderSubgroupSupported, Bool timerQueriesSupported,
Bool anisotropicFilteringSupported,
Bool nonZeroIndirectBaseInstanceSupported,
Bool cubeMapArraySupported) {
Bool cubeMapArraySupported,
Bool nvMeshShader) {
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
@@ -659,38 +625,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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,
// kwin_wayland 6.7.3 will not use a context it cannot drive, and it asks for these
// three names first: EglContext::checkSupported() (src/opengl/eglcontext.cpp) takes the
// DESKTOP-OpenGL branch for every context whose GL_VERSION is not an "OpenGL ES"
// string, and that branch requires GL_ARB_shader_objects, GL_ARB_fragment_shader and
// GL_ARB_vertex_shader. GL_VERSION here is "4.6.0 MobileGL ...", so with the names
// missing checkSupported() answered false, EglContext::create() returned nullptr,
// EglBackend::createContext() returned false, and kwin printed "Could not initialize
// rendering context" and quit before drawing a frame.
//
// The three are true statements about this backend too, and the entry points behind
// them are the same ones the DirectGLES half of this list is advertised with: the
// frontend implements all 39 ARB_shader_objects procedures, ARB_vertex_shader's three
// attrib-location entry points, and nothing for ARB_fragment_shader, whose "New
// Procedures and Functions" section reads "None". The shader and program objects live in
// MG_Impl/MG_State, above the backend that draws with them, so a name that is true on
// one backend is true on the other.
E_GL_ARB_shader_objects, E_GL_ARB_vertex_shader, E_GL_ARB_fragment_shader,
// NPOT textures: Vulkan puts no power-of-two restriction on an image, its mip chain or
// its samplers, so this is the strongest form of the promise the string makes. Kept
// identical to the DirectGLES group so the two backends do not disagree about what
// MobileGL is.
E_GL_ARB_texture_non_power_of_two,
// GL_OES_EGL_image: the entry points are real (MG_Impl/GLImpl/Exporting/Definitions.cpp)
// and this name is what makes them reachable - libepoxy in kwin resolves
// glEGLImageTargetTexture2DOES BY NAME and refuses the import path without it, printing
// "No provider of glEGLImageTargetTexture2DOES found. Requires one of: GL_OES_EGL_image".
// That import path is how the compositor's scene reaches the display daemon's dma-bufs.
// The render-server half of the import (fd over the GBM socket, then the server-side
// EGLImage) is the next change; until it lands an imported texture has no storage behind
// it, which is logged once at the entry point rather than left to look like a black frame.
E_GL_OES_EGL_image};
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
@@ -751,6 +686,11 @@ namespace MobileGL::MG_Backend::DirectVulkan {
if (cubeMapArraySupported) {
extensions.push_back(E_GL_ARB_texture_cube_map_array);
}
if (nvMeshShader) {
extensions.push_back(E_GL_NV_mesh_shader);
}
return extensions;
}
@@ -815,6 +755,8 @@ 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.ShaderStorageBlockBinding = ShaderStorageBlockBinding;
funcsTable.GL.FenceSync = FenceSync;
funcsTable.GL.ClientWaitSync = ClientWaitSync;
@@ -858,8 +800,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_vulkanCaps = capabilities;
UpdateDynamicBackendParameters();
UpdateAdvertisedExtensions();
if (MGB_CTX_LIVE) {
MGB_CTX->InvalidateCompileEnv();
if (MG_State::pGLContext) {
MG_State::pGLContext->InvalidateCompileEnv();
}
MutableFormatCapabilities().Clear();
}
@@ -1012,15 +954,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
clampLimit("GL_MAX_COMPUTE_UNIFORM_BLOCKS", m_vulkanCaps.MaxComputeUniformBlocks,
kMaxAdvertisedBufferBlocks);
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);
MobileGL/MG_Backend/DirectVulkan/BackendObject_DirectVulkan.h
+2 -1
View File
@@ -77,7 +77,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Vector<GLExtension> BuildAdvertisedExtensions(Bool shaderSubgroupSupported, Bool timerQueriesSupported,
Bool anisotropicFilteringSupported,
Bool nonZeroIndirectBaseInstanceSupported,
Bool cubeMapArraySupported);
Bool cubeMapArraySupported,
Bool nvMeshShader = true);
// 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.cpp
+175 -526
View File
File diff suppressed because it is too large Load Diff
MobileGL/MG_Backend/DirectVulkan/DirectVulkan.h
+2 -18
View File
@@ -23,18 +23,6 @@ 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
@@ -107,6 +95,8 @@ 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 GetInteger64i_v(GLenum target, GLuint index, GLint64* data);
void GetProgramiv(GLuint program, GLenum pname, GLint* params);
void ShaderStorageBlockBinding(GLuint program, const GLchar* storageBlockName, 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);
@@ -151,10 +141,4 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// starts from the app's last request (GetRequestedSwapInterval) instead of the default.
void SetSwapInterval(Int interval);
Optional<Int> GetRequestedSwapInterval();
#if MOBILEGL_BUILD_DISAGGREGATED
// The swap interval an ended server session asked for is not the next one's, the same rule as
// DirectGLES::ForgetRequestedSwapInterval: under a transport ~BackendObject_DirectVulkan forgets
// it, so the next session starts at the default until it asks.
void ForgetRequestedSwapInterval();
#endif
} // namespace MobileGL::MG_Backend::DirectVulkan
MobileGL/MG_Backend/DirectVulkan/Renderer/BufferArena.cpp
-11
View File
@@ -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) {
@@ -128,14 +125,6 @@ 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
+3 -22
View File
@@ -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) {
@@ -220,13 +217,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
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;
@@ -238,14 +228,7 @@ 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) {
@@ -307,10 +290,8 @@ 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,
MobileGL/MG_Backend/DirectVulkan/Renderer/MagmaPipeArms.h
-611
View File
@@ -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
-224
View File
@@ -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
+2 -19
View File
@@ -198,17 +198,7 @@ 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)));
@@ -285,14 +275,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
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_cache.emplace(hash, PipelineCacheEntry{pipeline, payload.programHash, payload.renderPass,
m_frameCounter});
return pipeline;
}
MobileGL/MG_Backend/DirectVulkan/Renderer/PipelineFactory.h
-5
View File
@@ -35,11 +35,6 @@ 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
MobileGL/MG_Backend/DirectVulkan/Renderer/ProgramFactory.cpp
+6 -18
View File
@@ -1891,7 +1891,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
Bool TransformSpirvForXfbCapture(const Vector<Uint>& input, Vector<Uint>& output,
const MagmaProgramSource& program) {
const MG_State::GLState::ProgramObject& program) {
if (input.empty()) {
output.clear();
return true;
@@ -2466,7 +2466,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
}
ProgramFactory::HashType ProgramFactory::ComputeHash(const MagmaProgramSource& program,
ProgramFactory::HashType ProgramFactory::ComputeHash(const MG_State::GLState::ProgramObject& program,
CompileOptionFlags flags) const {
XXHASH_VERIFY(XXH64_reset(m_hashState, m_config.CacheVersion));
// We expect shader stages in program object are sorted
@@ -2832,7 +2832,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// key and every element of an array of arrays seeds texture unit 0. Resolving those elements
// would then paint silently-wrong pixels with no diagnostic at all - strictly worse than
// declining. The decline goes away together with the seeding fix, not before it.
static Uint32 DescriptorCountForOpaqueUniformArray(const MagmaProgramSource& program,
static Uint32 DescriptorCountForOpaqueUniformArray(const MG_State::GLState::ProgramObject& program,
const String& uniformName, Uint32 binding, Int baseLocation,
Uint32 reflectedCount, Uint32 maxBindings,
const char* kindLabel, Bool& outDeclined) {
@@ -2868,7 +2868,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
return count;
}
void ProgramFactory::ReflectLayout(const MagmaProgramSource& program,
void ProgramFactory::ReflectLayout(const MG_State::GLState::ProgramObject& program,
const Vector<Vector<Uint>>& spirv, VkProgramObject& entry) const {
// Initialize layout vectors
entry.bindingKinds.assign(m_maxBindings, DescriptorBindingKind::None);
@@ -3068,12 +3068,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
entry.bindingKinds[binding] = descriptorKind;
if (descriptorKind == DescriptorBindingKind::StorageBuffer) {
const GLuint blockIndex =
#if MOBILEGL_BUILD_DISAGGREGATED
program.GetShaderStorageBlockIndex(uniformName);
#else
GetShaderStorageBlockIndex(program, uniformName);
#endif
const GLuint blockIndex = GetShaderStorageBlockIndex(program, uniformName);
if (blockIndex == GL_INVALID_INDEX) {
MGLOG_D("ProgramFactory::ReflectLayout: skipping inactive SSBO '%s' at binding %u",
uniformName.c_str(), binding);
@@ -3365,13 +3360,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
updateAfterBindSampledImages + updateAfterBindStorageImages;
const auto& uab = m_updateAfterBindLimits;
entry.usesUpdateAfterBind =
#if MOBILEGL_BUILD_DISAGGREGATED
// Vulkan forbids ANY update-after-bind binding in a set layout that
// contains a dynamic buffer descriptor (VUID 03001/03011). Wire draws
// retain UniformManager's per-frame, content-versioned descriptor sets;
// this selects the legal ordinary pool, not in-place mutation of a live set.
(!program.IsWire() || entry.dynamicBindings.empty()) &&
#endif
uab.enabled && updateAfterBindSamplers <= uab.maxPerStageSamplers &&
updateAfterBindUniformBuffers <= uab.maxPerStageUniformBuffers &&
updateAfterBindStorageBuffers <= uab.maxPerStageStorageBuffers &&
@@ -3438,7 +3426,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
const ProgramFactory::VkProgramObject& ProgramFactory::GetOrCreateProgram(
const MagmaProgramSource& program, CompileOptionFlags flags) {
const MG_State::GLState::ProgramObject& program, CompileOptionFlags flags) {
// Hashing the full SPIR-V of every stage is far too expensive to repeat per draw;
// reuse the program's memoized hash while its backend state version is unchanged.
// The memo keys on the flags word, which ComputeHash is no longer a pure function of:
MobileGL/MG_Backend/DirectVulkan/Renderer/ProgramFactory.h
+4 -4
View File
@@ -10,7 +10,7 @@
#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"
@@ -471,9 +471,9 @@ namespace MobileGL::MG_Backend::DirectVulkan {
~ProgramFactory();
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);
const MG_State::GLState::ProgramObject& 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
@@ -600,7 +600,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
void ReflectFragmentOutputs(const Vector<ShaderStage>& stages,
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
MobileGL/MG_Backend/DirectVulkan/Renderer/SubmitFencePrefix.h
-41
View File
@@ -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
+15 -43
View File
@@ -13,11 +13,6 @@
#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>
@@ -307,6 +302,11 @@ 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:
@@ -322,6 +322,11 @@ 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
@@ -341,44 +346,11 @@ 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
}
MobileGL/MG_Backend/DirectVulkan/Renderer/UniformManager.cpp
+46 -824
View File
File diff suppressed because it is too large Load Diff
MobileGL/MG_Backend/DirectVulkan/Renderer/UniformManager.h
+16 -140
View File
@@ -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 "../DescriptorPoolCensus.h"
#include "../VkIncludes.h"
#include <Includes.h>
@@ -56,25 +54,6 @@ 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; }
@@ -102,7 +81,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
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);
@@ -111,25 +90,18 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// (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,
Bool SampledBindingsUnchanged(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj,
const Vector<SampledBindingRecord>& previousRecords) const;
Bool CollectStorageImageTextures(const MagmaProgramSource& program,
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 MG_State::GLState::ProgramObject& 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
@@ -137,7 +109,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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,
@@ -158,7 +130,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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,
static Bool ProgramSamplesOnlySingleLevelTextures(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj);
// ---- per-frame descriptor pools ----------------------------------------------------
@@ -215,66 +187,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
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
// descriptorSetCacheByLayout is the per-frame set cache: BeginFrame rewinds every cursor, so
// a slot re-writes the sets it allocated in earlier frames instead of allocating new ones, and
// the cache only ever grows - except through TrimFrameDescriptorPools, which gives a slot's
@@ -283,12 +195,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
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;
@@ -298,7 +204,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Uint32 quietEpochs = 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
@@ -307,7 +213,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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,
Bool ResolveSampledBinding(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj, Uint32 binding, Uint32 element,
MG_State::GLState::ITextureObject*& outTexture,
const MG_State::GLState::SamplerObject*& outSampler) const;
@@ -315,7 +221,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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 MG_State::GLState::ProgramObject& 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.
@@ -362,27 +268,13 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// (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,
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
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,
@@ -390,19 +282,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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,
Bool ResolveStorageTexelBufferDescriptor(const MG_State::GLState::ProgramObject& 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.
Bool ResolveStorageImageDescriptor(VkCommandBuffer commandBuffer,
const MagmaProgramSource& program,
const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
Uint32 element, VkDescriptorImageInfo& outImageInfo) const;
// Result of resolving a UBO binding: either a zero-copy direct bind to the app's resident
@@ -415,18 +307,14 @@ 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,
Bool ResolveDynamicUboDescriptor(const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj, Uint32 binding,
Uint32 arrayElement, Uint32 frameIndex, VkBuffer& outBuffer,
VkDeviceSize& outRange, Uint32& outDynamicOffset);
@@ -545,15 +433,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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;
@@ -563,9 +442,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkBuffer uboBuffer = VK_NULL_HANDLE;
VkDeviceSize uboRange = 0;
VkDescriptorSet set = VK_NULL_HANDLE;
#if MOBILEGL_BUILD_DISAGGREGATED
Uint64 wireStoreDestroyEpoch = 0;
#endif
};
FastRebindMemo m_fastRebindMemo;
MobileGL/MG_Backend/DirectVulkan/Renderer/VertexInputStateFactory.cpp
+3 -310
View File
@@ -7,13 +7,8 @@
// 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 {
@@ -50,149 +45,25 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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 Uint64 bufferKey = attr.Buffer ? attr.Buffer->GetLifetimeId() : 0;
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.
@@ -212,7 +83,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
vao.SetBackendAuxMemo(entry.layoutHash,
PackVertexInputAuxMasks(entry.unsupportedAttribMask, entry.attributeLocationMask));
return entry;
#endif // MOBILEGL_PIPE_LEGACY_MEMOS
}
const VertexInputStateFactory::BackendVertexInputState& VertexInputStateFactory::GetOrCreateVertexInputState(
@@ -250,16 +120,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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) {
@@ -435,146 +295,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
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;
@@ -596,14 +316,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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
// instances (see the member comment).
m_evictionEpoch = ++s_evictionEpochSource;
#else
++m_evictionEpoch;
#endif
} else {
++it;
}
@@ -653,17 +367,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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 ||
if (MG_Backend::pActiveBackendObject == nullptr ||
!MG_Backend::pActiveBackendObject->GetDynamicParameters().SupportsFloat64VertexAttributes) {
return VK_FORMAT_UNDEFINED;
}
@@ -847,17 +551,6 @@ 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
+1 -84
View File
@@ -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>
@@ -77,18 +70,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
};
};
#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;
@@ -103,13 +86,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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);
@@ -128,13 +104,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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,
@@ -143,51 +112,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
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
@@ -204,24 +130,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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
// memos outlive this factory (they live on pGLContext'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
static inline XXH64_state_t* m_hashState = XXH64_createState();
};
} // namespace MobileGL::MG_Backend::DirectVulkan
MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferManager.cpp
+4 -1093
View File
File diff suppressed because it is too large Load Diff
MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferManager.h
+1 -207
View File
@@ -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 {
@@ -103,56 +99,6 @@ 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);
// P8-D: whether a shader write was marked on this store since the last indirect draw
// read it natively, clearing the mark. The caller records the INDIRECT_COMMAND_READ
// barrier before the draw when this answers true. Transfer writes need no mark: their own
// after-barriers already make them visible to MEMORY_READ at ALL_COMMANDS.
Bool TakeWireIndirectReadBarrier(MG_Pipe::MGPipeHandle res);
// P8-D: every WaitForWireBufferHostAccess that actually waited, over this manager's life -
// the attribution base a caller reads before and after its own ReadWireBuffer.
Uint64 GetWireHostWaitCount() const { return m_wireHostWaits; }
// 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);
// P11 B2 (T0): make the client's AHardwareBuffer `ahb` (a BLOB of `size` bytes) buffer
// `res`'s store - a VkBuffer on memory imported through
// VK_ANDROID_external_memory_android_hardware_buffer, host-visible and mapped like every
// wire store, so every wire path (draw binds, WriteWireBuffer's ordered copy, CPU readers)
// applies unchanged. The T2 store it replaces goes through DeferWireRelease. False = not
// imported (the T2 store is untouched and the client is DECLINED).
Bool ImportWireBuffer(MG_Pipe::MGPipeHandle res, void* ahb, Uint64 size);
// The POST self-test of the sustained-lock pattern on this device (see the definition).
static Bool SelfTestWireImport(char* why, Uint64 whyBytes);
#endif
// Recreate all per-frame transient arenas
Bool RecreateTransientArenas(Uint32 frameCount);
void BeginFrame(Uint32 frameIndex);
@@ -225,13 +171,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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.
@@ -239,131 +178,8 @@ 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;
// P11 B2 (T0): `buffer` is the client's imported AHardwareBuffer. Its readback posts
// no bytes (the client reads its own pages once the wait below it is done).
Bool imported = false;
// P8-D: a shader write was marked (MarkWireBufferGpuWritten) and no indirect draw has
// recorded its INDIRECT_COMMAND_READ barrier since (TakeWireIndirectReadBarrier).
Bool indirectReadBarrierPending = false;
};
// P8-D: see GetWireHostWaitCount.
Uint64 m_wireHostWaits = 0;
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);
// P11 B2: the serial a T0 store's release waits behind (never "destroy at once").
Uint64 T0ReleaseSerial(Uint64 lastUseSerial) const;
// 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);
@@ -376,9 +192,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// in-flight and already-recorded GPU work.
Bool StagedRangeCopy(VkBufferResource& resource, const void* data,
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);
@@ -397,26 +211,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
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;
MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferObject.cpp
-77
View File
@@ -8,45 +8,13 @@
#include "VkBufferObject.h"
#if MOBILEGL_BUILD_DISAGGREGATED
#include <MG_Remote/Transport/AdoptT0.h>
#endif
namespace MobileGL::MG_Backend::DirectVulkan {
#if MOBILEGL_BUILD_DISAGGREGATED
void VkBufferObject::MoveExternalFrom(VkBufferObject& other) {
m_device = other.m_device;
m_externalMemory = other.m_externalMemory;
m_externalAhb = other.m_externalAhb;
m_externalCoherent = other.m_externalCoherent;
other.m_device = VK_NULL_HANDLE;
other.m_externalMemory = VK_NULL_HANDLE;
other.m_externalAhb = nullptr;
other.m_externalCoherent = true;
}
void VkBufferObject::AdoptExternal(VkDevice device, VkBuffer buffer, VkDeviceMemory memory, VkDeviceSize size,
void* mapped, Bool coherent, void* ahb) {
Destroy();
m_device = device;
m_buffer = buffer;
m_externalMemory = memory;
m_mappedData = mapped;
m_size = size;
m_externalCoherent = coherent;
m_externalAhb = ahb;
}
#endif
VkBufferObject::VkBufferObject(VkBufferObject&& other) noexcept {
m_allocator = other.m_allocator;
m_buffer = other.m_buffer;
m_allocation = other.m_allocation;
m_mappedData = other.m_mappedData;
m_size = other.m_size;
#if MOBILEGL_BUILD_DISAGGREGATED
MoveExternalFrom(other);
#endif
other.m_allocator = nullptr;
other.m_buffer = VK_NULL_HANDLE;
@@ -67,9 +35,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
m_allocation = other.m_allocation;
m_mappedData = other.m_mappedData;
m_size = other.m_size;
#if MOBILEGL_BUILD_DISAGGREGATED
MoveExternalFrom(other);
#endif
other.m_allocator = nullptr;
other.m_buffer = VK_NULL_HANDLE;
@@ -124,24 +89,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
void VkBufferObject::Destroy() {
#if MOBILEGL_BUILD_DISAGGREGATED
if (m_externalMemory != VK_NULL_HANDLE) {
// P11 B2 (T0): an imported AHardwareBuffer store. Reached through the wire arm's
// deferred release, i.e. once no submission can still name it.
if (m_mappedData != nullptr) vkUnmapMemory(m_device, m_externalMemory);
if (m_buffer != VK_NULL_HANDLE) vkDestroyBuffer(m_device, m_buffer, nullptr);
vkFreeMemory(m_device, m_externalMemory, nullptr);
MG_Remote::Transport::AdoptT0::ReleaseImported(m_externalAhb);
m_mappedData = nullptr;
m_buffer = VK_NULL_HANDLE;
m_externalMemory = VK_NULL_HANDLE;
m_externalAhb = nullptr;
m_device = VK_NULL_HANDLE;
m_externalCoherent = true;
m_size = 0;
return;
}
#endif
Unmap();
if (m_allocator != nullptr && m_buffer != VK_NULL_HANDLE && m_allocation != nullptr) {
vmaDestroyBuffer(m_allocator, m_buffer, m_allocation);
@@ -170,10 +117,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
void VkBufferObject::Unmap() {
#if MOBILEGL_BUILD_DISAGGREGATED
// An imported store stays mapped for its life (Destroy unmaps it).
if (m_externalMemory != VK_NULL_HANDLE) return;
#endif
if (!IsValid() || m_mappedData == nullptr) {
m_mappedData = nullptr;
return;
@@ -200,16 +143,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
Memcpy(static_cast<Uint8*>(mapped) + offset, data, static_cast<SizeT>(size));
#if MOBILEGL_BUILD_DISAGGREGATED
if (m_externalMemory != VK_NULL_HANDLE) {
if (m_externalCoherent) return true;
VkMappedMemoryRange range{VK_STRUCTURE_TYPE_MAPPED_MEMORY_RANGE};
range.memory = m_externalMemory;
range.offset = 0;
range.size = VK_WHOLE_SIZE;
return vkFlushMappedMemoryRanges(m_device, 1, &range) == VK_SUCCESS;
}
#endif
const VkResult flushResult = vmaFlushAllocation(m_allocator, m_allocation, offset, size);
if (flushResult != VK_SUCCESS) {
MGLOG_E_ONCE("VkBufferObject::Upload failed: vmaFlushAllocation returned %d", flushResult);
@@ -234,16 +167,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
if (resolvedSize == 0) {
return true;
}
#if MOBILEGL_BUILD_DISAGGREGATED
if (m_externalMemory != VK_NULL_HANDLE) {
if (m_externalCoherent) return true;
VkMappedMemoryRange range{VK_STRUCTURE_TYPE_MAPPED_MEMORY_RANGE};
range.memory = m_externalMemory;
range.offset = 0;
range.size = VK_WHOLE_SIZE;
return vkInvalidateMappedMemoryRanges(m_device, 1, &range) == VK_SUCCESS;
}
#endif
const VkResult result = vmaInvalidateAllocation(m_allocator, m_allocation, offset, resolvedSize);
if (result != VK_SUCCESS) {
MobileGL/MG_Backend/DirectVulkan/Renderer/VkBufferObject.h
+1 -26
View File
@@ -64,25 +64,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
void* GetMappedData() const { return m_mappedData; }
Bool IsMapped() const { return m_mappedData != nullptr; }
Bool IsValid() const {
#if MOBILEGL_BUILD_DISAGGREGATED
if (m_externalMemory != VK_NULL_HANDLE) return m_buffer != VK_NULL_HANDLE;
#endif
return m_allocator != nullptr && m_buffer != VK_NULL_HANDLE && m_allocation != nullptr;
}
#if MOBILEGL_BUILD_DISAGGREGATED
// P11 B2 (T0): a store whose memory is NOT this allocator's - a client's AHardwareBuffer
// imported with VK_ANDROID_external_memory_android_hardware_buffer into `memory` (a
// dedicated allocation bound to `buffer`, mapped persistently at `mapped`). It behaves
// like any mapped store (GetSlice, Upload, Invalidate), and Destroy frees the buffer and
// the memory and drops `ahb` - which is why the store goes through the wire arm's
// serial-gated deferred release like every other: the AHardwareBuffer is let go only once
// no submission can still name it. `coherent` = the memory type is HOST_COHERENT.
void AdoptExternal(VkDevice device, VkBuffer buffer, VkDeviceMemory memory, VkDeviceSize size,
void* mapped, Bool coherent, void* ahb);
Bool IsExternal() const { return m_externalMemory != VK_NULL_HANDLE; }
#endif
Bool IsValid() const { return m_allocator != nullptr && m_buffer != VK_NULL_HANDLE && m_allocation != nullptr; }
private:
VmaAllocator m_allocator = nullptr;
@@ -90,12 +72,5 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VmaAllocation m_allocation = nullptr;
void* m_mappedData = nullptr;
VkDeviceSize m_size = 0;
#if MOBILEGL_BUILD_DISAGGREGATED
VkDevice m_device = VK_NULL_HANDLE;
VkDeviceMemory m_externalMemory = VK_NULL_HANDLE;
void* m_externalAhb = nullptr;
Bool m_externalCoherent = true;
void MoveExternalFrom(VkBufferObject& other);
#endif
};
} // namespace MobileGL::MG_Backend::DirectVulkan
MobileGL/MG_Backend/DirectVulkan/Renderer/VkClearManager.cpp
+1 -2
View File
@@ -13,7 +13,6 @@
#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"
@@ -55,7 +54,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
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 (MG_State::pGLContext->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
MobileGL/MG_Backend/DirectVulkan/Renderer/VkRenderPassManager.cpp
+3 -4
View File
@@ -13,7 +13,6 @@
#include "MG_Util/Converters/MGToStr/FramebufferEnumConverter.h"
#include "MG_Util/Converters/MGToVk/TextureEnumConverter.h"
#include "MG_Util/Metrics/TextureMetrics.h"
#include <MG_Pipe/PipeInputsSwitch.h>
namespace MobileGL::MG_Backend::DirectVulkan {
static Bool TryResolveSampleCountFlagBits(Int requestedSamples, VkSampleCountFlagBits& outSampleCount) {
@@ -611,7 +610,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// sRGB attachments switch between their sRGB and UNORM-twin views with this
// capability (ResolveSrgbAttachmentWriteFormat), changing the render pass formats.
const Bool framebufferSrgbEnabled =
MGB_CTX->IsCapabilityEnabled(MobileGL::CapabilityInput::FramebufferSrgb);
MG_State::pGLContext->IsCapabilityEnabled(MobileGL::CapabilityInput::FramebufferSrgb);
XXHASH_VERIFY(XXH64_update(m_hashState, &framebufferSrgbEnabled, sizeof(framebufferSrgbEnabled)));
auto& drawBuffers = fbo.GetDrawBuffers();
XXHASH_VERIFY(XXH64_update(m_hashState, drawBuffers.data(), drawBuffers.size() * sizeof(drawBuffers[0])));
@@ -963,7 +962,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
const VkImageLayout trackedRbLayout = rbResource->layout;
const Bool rbFramebufferSrgb =
MGB_CTX->IsCapabilityEnabled(MobileGL::CapabilityInput::FramebufferSrgb);
MG_State::pGLContext->IsCapabilityEnabled(MobileGL::CapabilityInput::FramebufferSrgb);
const VkFormat rbAttachmentFormat =
ResolveSrgbAttachmentWriteFormat(rbResource->format, rbFramebufferSrgb);
rbDesc.flags = 0;
@@ -1109,7 +1108,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
textureResources.emplace_back(textureResource);
desc.format = ResolveSrgbAttachmentWriteFormat(
textureResource->format,
MGB_CTX->IsCapabilityEnabled(MobileGL::CapabilityInput::FramebufferSrgb));
MG_State::pGLContext->IsCapabilityEnabled(MobileGL::CapabilityInput::FramebufferSrgb));
attachmentSampleCount = textureResource->sampleCount;
trackedColorLayout = textureResource->layout;
trackedAttachmentLayouts.emplace_back(TrackedAttachmentLayoutInfo {
MobileGL/MG_Backend/DirectVulkan/Renderer/VkSamplerManager.cpp
-87
View File
@@ -15,37 +15,7 @@
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;
@@ -221,24 +191,14 @@ 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);
}
@@ -249,12 +209,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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;
}
@@ -275,12 +230,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
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;
@@ -339,12 +289,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
}
}
#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 {
MOBILEGL_ASSERT(m_config != nullptr, "VkSamplerManager::BuildSamplerKey: m_config is null");
@@ -390,14 +335,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
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 -
@@ -409,11 +348,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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);
auto it = m_samplers.find(key);
if (it != m_samplers.end()) {
@@ -473,20 +408,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
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;
}
@@ -542,14 +463,8 @@ 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{};
if (!UsesBorderColor(sampler)) {
return resolved; // FLOAT_TRANSPARENT_BLACK, never sampled
@@ -557,9 +472,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// 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;
MobileGL/MG_Backend/DirectVulkan/Renderer/VkSamplerManager.h
-24
View File
@@ -46,12 +46,6 @@ public:
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
@@ -92,37 +86,19 @@ private:
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;
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
// 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;
MobileGL/MG_Backend/DirectVulkan/Renderer/VkTextureManager.cpp
+4 -1272
View File
File diff suppressed because it is too large Load Diff
MobileGL/MG_Backend/DirectVulkan/Renderer/VkTextureManager.h
-88
View File
@@ -17,21 +17,9 @@
#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;
@@ -350,13 +338,6 @@ public:
// 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;
@@ -390,9 +371,6 @@ public:
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() {
@@ -457,9 +435,6 @@ public:
syncedContentVersion = 0;
syncedMipLevelCount = 0;
syncedShapeVersion = 0;
#if MOBILEGL_BUILD_DISAGGREGATED
syncedWireSerial = 0;
#endif
}
~TextureResource() {
@@ -486,12 +461,6 @@ public:
// 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.
@@ -551,47 +520,6 @@ public:
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,
@@ -768,22 +696,6 @@ private:
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;
MobileGL/MG_Backend/DirectVulkan/Renderer/VulkanRenderer.cpp
+394 -2220
View File
File diff suppressed because it is too large Load Diff
MobileGL/MG_Backend/DirectVulkan/Renderer/VulkanRenderer.h
+16 -542
View File
@@ -9,7 +9,6 @@
#pragma once
#include "Config.h"
#include "FrameContext.h"
#include "MagmaPipeArms.h"
#include "PipelineFactory.h"
#include "ProgramFactory.h"
#include "SwapchainObject.h"
@@ -22,19 +21,10 @@
#include "VkSamplerManager.h"
#include "VkTextureManager.h"
#include "VkTimerQueryManager.h"
#if MOBILEGL_BUILD_DISAGGREGATED
#include "WireRenderPassCompatibility.h"
#endif
#include "MG_Util/Math/VectorTypes.h"
#include <Includes.h>
#include <MG_Backend/BackendObject.h>
#include <MG_Pipe/MGPipeHandles.h>
#include <MG_Util/SelfTest/PrimitivesGeneratedNoXfbProbe.h>
#if MOBILEGL_PIPE_PUSH
// The applier's CSO store: MGPipeApplier().BoundRenderStateCso is what the pipeline memo
// keys on after P2 (D12.1). Push-only, so the pull build's include graph is unchanged.
#include <MG_Pipe/PipeApply.h>
#endif
#include <vk_mem_alloc.h>
#include "../VkIncludes.h"
@@ -144,42 +134,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// IBufferCopyCommandProvider: recording command buffer, outside any
// render pass, for immediate staged buffer copies.
VkCommandBuffer AcquireBufferCopyCommandBuffer() override;
#if MOBILEGL_BUILD_DISAGGREGATED
VkBufferManager& GetWireBufferManager() { return m_bufferManager; }
Bool FlushWirePendingCommandsForTextureUpdate() {
// A new texture upload must not race graphics work that samples
// the old texels. No current recording does not imply no in-flight
// submission: finish the recorded work, then wait its whole prefix.
if (HasPendingRecordedWork() && !FlushPendingCommands()) return false;
return WaitForSubmitsUpTo(m_submitCounter, UINT64_MAX);
}
// P7 wave 2 package B3: the submission that will carry whatever is recorded NEXT.
// RetireWireObjects (WireDraw.inc) already tags future objects with exactly this, and
// for the same reason: a draw being set up now is not in any submission yet, so the
// index that names it is one past the counter. Deliberately NOT
// GetSyncPointSubmitIndex(), which answers m_submitCounter when nothing is recorded -
// true for a fence taken at that instant, wrong for work about to be recorded.
Uint64 GetWireNextSubmitIndex() const { return m_submitCounter + 1; }
// P8-D: the wire arm's indirect draw families, issued as vkCmdDraw[Indexed]Indirect[Count]
// from the wire stores MGPipeApplier().VerbIndirectBuffer / VerbIndirectParameterBuffer
// name. `offset` / `countOffset` are byte offsets into those stores; `stride` 0 means
// tightly packed. FALSE = this device cannot issue the COUNT form natively (the monolith
// arm's own condition, see the definition in WireDraw.inc) and the caller must read the
// words on the CPU; TRUE = issued, or declined by name.
Bool DrawWireIndirectNative(GLenum mode, GLenum type, Uint64 offset, GLsizei drawcount, GLsizei stride,
Bool indexed, Bool counted, Uint64 countOffset);
// P11 B2 (T0): what importing a client's AHardwareBuffer as a wire buffer store needs from
// this device. False when the device did not take VK_ANDROID_external_memory_android_
// hardware_buffer at creation (not Android, not advertised, or a monolith device).
struct WireAhbImport {
VkDevice device = VK_NULL_HANDLE;
VkQueue queue = VK_NULL_HANDLE;
Uint32 queueFamily = 0;
VkPhysicalDeviceMemoryProperties memory{};
void* getAhbProperties = nullptr; // PFN_vkGetAndroidHardwareBufferPropertiesANDROID
};
Bool GetWireAhbImport(WireAhbImport& out) const;
#endif
// FrameContext::IRecordingObserver: prepares the frame's timer-query
// pool (harvest + reset) right after the frame command buffer begins
@@ -252,11 +206,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
GLsizei srcWidth, GLsizei srcHeight, GLsizei srcDepth);
void GenerateMipmap(GLenum target);
void ReadPixels(GLint x, GLint y, GLsizei width, GLsizei height, GLenum format, GLenum type, void* pixels);
#if MOBILEGL_BUILD_DISAGGREGATED
// Server resource handle in, tightly packed owned bytes out. No frontend
// texture, pixel-pack state or PBO is consulted by this readback.
Bool ReadTextureImageWire(const MG_Pipe::MGPReadbackInfo& info, Vector<Uint8>& ownedBytes);
#endif
// GL_DEPTH_COMPONENT / GL_DEPTH_STENCIL / GL_STENCIL_INDEX readback from the
// read framebuffer's depth/stencil attachment (per-aspect buffer copies with
// CPU repacking into the requested client layout).
@@ -286,16 +235,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Uint32 dstMipLevel, Uint32 dstBaseArrayLayer, GLint srcX, GLint srcY, GLint dstX,
GLint dstY, GLint width, GLint height, VkImageLayout srcRestoreLayout,
VkImageLayout dstRestoreLayout, Bool stencilAspect);
// One depth/stencil copy whose source and destination are the same format and whose region
// is a same-size, same-layer rectangle: the aspect named by `aspect` is staged through a
// device-local buffer so the destination's other aspect cannot be overwritten by the
// packed native word a whole-image copy moves.
Bool CopyDepthStencilAspectThroughBuffer(FrameContext::FrameData& frame, VkImage srcImage,
VkImage dstImage, VkFormat format, Uint32 srcMipLevel,
Uint32 srcBaseArrayLayer, Uint32 dstMipLevel,
Uint32 dstBaseArrayLayer, GLint srcX, GLint srcY, GLint dstX,
GLint dstY, GLsizei width, GLsizei height,
VkImageAspectFlagBits aspect);
static SizeT GetReadbackTexelSize(VkFormat sourceFormat);
// Map a GL bottom-left-origin rectangle into the display-oriented swapchain image.
// Quarter-turn surface transforms swap the copy extent's axes.
@@ -445,20 +384,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Int padding[3] = {0, 0, 0};
};
// P7 wave 2-B2, CONTRACT-P7 §5.2 (B'): THE FRONTEND MEMBERS ARE PULL-BUILD ONLY. In a
// disaggregated build the monolith arm blits and generates depth mips with the baked
// modules (WireColorBlit.inc, WireDepthMipmap.inc), so no DirectVulkan object holds a
// ProgramObject, a ShaderObject or a SamplerObject any more - which is what takes
// ProgramObject::{AllocateLifetimeId, AttachShader, Link, ~ProgramObject},
// ShaderObject::{SetShaderSource, Compile, JoinPendingCompile, ReleaseCompileNode,
// DropCompileNode} and SamplerObject::{SetWrapS, SetWrapT, SetWrapR, SetLodRange} out
// of the link ratchet's `p7-magma` bucket (§4.2). The destructor of a SharedPtr member
// is a reference too, so the MEMBER has to go and not only its construction.
//
// The structs stay, empty, so ShutdownBlitResources and the two `= {}` assignments read
// the same on both builds.
struct BlitResources {
#if !MOBILEGL_BUILD_DISAGGREGATED
SharedPtr<MG_State::GLState::ProgramObject> program;
SharedPtr<MG_State::GLState::SamplerObject> nearestSampler;
SharedPtr<MG_State::GLState::SamplerObject> linearSampler;
@@ -466,18 +392,15 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Int dstRectLocation = -1;
Int surfaceTransformLocation = -1;
Uint32 samplerBinding = 0;
#endif
};
struct DepthMipmapResources {
#if !MOBILEGL_BUILD_DISAGGREGATED
SharedPtr<MG_State::GLState::ProgramObject> program;
Int srcRectLocation = -1;
Int dstRectLocation = -1;
Int surfaceTransformLocation = -1;
Int srcTexelSizeLocation = -1;
Uint32 samplerBinding = 0;
#endif
};
// A single-sample staging image for multisample-resolve blits that also have to change
@@ -513,200 +436,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
};
void QueueClearBufferPayload(GLenum buffer, GLint drawbuffer, const ClearAttachmentPayload& clearPayload);
#if MOBILEGL_BUILD_DISAGGREGATED
struct WireImage {
VkImage image = VK_NULL_HANDLE;
VkFormat format = VK_FORMAT_UNDEFINED;
VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
VkExtent2D extent{};
VkImageLayout layout = VK_IMAGE_LAYOUT_UNDEFINED;
VkImageLayout* trackedLayout = nullptr;
VkSampleCountFlagBits samples = VK_SAMPLE_COUNT_1_BIT;
VkImageAspectFlags aspect = 0;
// Zero for the default framebuffer, which no arm that reads this ever reaches.
VkImageUsageFlags usageFlags = 0;
Uint32 level = 0, layer = 0, layers = 1, levels = 1;
Bool isDefault = false;
// Set when isDefault: the swapchain image index this role resolved to.
Uint32 swapchainImageIndex = 0;
Bool is3D = false;
MG_Pipe::MGPipeHandle storage = MG_Pipe::kMGPipeNullHandle;
};
// `isWriteTarget` selects which side of the default framebuffer this resolves: a write
// re-points it at the image Present() acquired, a read keeps the current one (see
// m_defaultFramebufferImageIndex). Reads must pass false.
WireImage ResolveWireImage(const MG_Pipe::MGPFramebufferState& fbo,
const MG_Pipe::MGPSurface& surface, VkImageAspectFlags aspect,
Bool isWriteTarget = false);
void TransitionWireImage(WireImage& image, VkImageLayout layout);
void ClearWireFramebuffer(const MG_Pipe::MGPFramebufferState& fbo,
const ClearAttachmentPayload& payload, GLint drawbuffer = -1);
void BlitWireFramebuffers(GLint sx0, GLint sy0, GLint sx1, GLint sy1,
GLint dx0, GLint dy0, GLint dx1, GLint dy1, GLbitfield mask, GLenum filter);
void ResolveWireDepthStencil(WireImage source, WireImage destination,
GLint sx0, GLint sy0, GLint sx1, GLint sy1,
GLint dx0, GLint dy0, GLint dx1, GLint dy1);
// One aspect of a depth/stencil image through a buffer (source in TRANSFER_SRC_OPTIMAL,
// destination in TRANSFER_DST_OPTIMAL, one format). The returned buffer is named by the
// recorded commands and must be retired with them.
UniquePtr<VkBufferObject> CopyWireAspectThroughBuffer(VkImage srcImage, Uint32 srcLevel, Uint32 srcLayer,
GLint sx, GLint sy, const WireImage& destination,
GLint dx, GLint dy, Uint32 width, Uint32 height,
VkImageAspectFlags aspect, VkFormat format,
Bool mirrorY, const char* fatalDetail);
// A single-sample depth/stencil blit whose rectangles make it a plain copy, performed
// without vkCmdBlitImage (P7 gate 5). False when the shape is not a plain copy.
Bool CopyWireDepthStencilBlit(WireImage& source, WireImage& destination,
GLint sx0, GLint sy0, GLint sx1, GLint sy1,
GLint dx0, GLint dy0, GLint dx1, GLint dy1, VkImageAspectFlags aspect);
// True when the rectangles give a multisample depth/stencil resolve a shape it declines
// (a scale, an X mirror, a Y mirror across two formats); the decline has then been
// logged and its INVALID_OPERATION recorded. BlitWireFramebuffers asks it BEFORE any
// aspect runs, so a call the SHAPE declines leaves every attachment alone - the user
// and the default draw framebuffer alike. The CAPABILITY decline inside
// ResolveWireDepthStencil (a stencil-only resolve without VK_EXT_shader_stencil_export
// on a device without VK_KHR_depth_stencil_resolve) is still decided per aspect, after
// colour ran; rule I (a) accepts that (notes/p7/magma-b2.md §2.10).
Bool DeclineWireDepthStencilResolveShape(const WireImage& source, const WireImage& destination,
GLint sx0, GLint sy0, GLint sx1, GLint sy1,
GLint dx0, GLint dy0, GLint dx1, GLint dy1);
PFN_vkCreateRenderPass2 m_wireCreateRenderPass2 = nullptr;
VkResolveModeFlags m_wireDepthResolveModes = 0;
VkResolveModeFlags m_wireStencilResolveModes = 0;
// P7 wave 2-B2, CONTRACT-P7 §3.2 (`multisample-blit-aspect`): the SECOND arm of the
// multisample depth/stencil resolve, for the device that does not carry
// VK_KHR_depth_stencil_resolve. One baked pass per aspect, sample zero, no frontend
// object - see WireMultisampleResolve.inc. `resolved` must be a single-sample image of
// the source's format and extent; the rect is expressed by the scissor.
Bool ResolveWireDepthStencilWithShader(WireImage source, WireImage resolved,
VkImageAspectFlags aspect, GLint sx0, GLint sy0,
Uint32 width, Uint32 height);
struct WireMultisampleResolveResources;
WireMultisampleResolveResources* m_wireMultisampleResolveResources = nullptr;
void DestroyWireMultisampleResolveResources();
Bool m_wireShaderStencilExport = false;
// VK_EXT_robustness2 (or its KHR promotion) with ONLY nullDescriptor enabled, wire arms
// only: an invalid image unit binds a null storage descriptor (codex closeout finding 2).
Bool m_wireNullDescriptor = false;
// The resolve probe's verdict for this device (WireDepthResolveArm.h,
// WireDepthResolveProbe.h): true when the no-draw render pass was measured leaving its
// target unwritten while the shader control resolved - the shader arm then resolves
// first and the render-pass arm is the fallback (P7 gate 5, g5-msprobe).
Bool m_wirePreferShaderDepthResolve = false;
// P11 B2 (T0): the device took the AHardwareBuffer import extensions at creation, and the
// one entry point the import needs (PFN_vkGetAndroidHardwareBufferPropertiesANDROID).
Bool m_wireAhbImport = false;
void* m_wireGetAhbProperties = nullptr;
// Runs the probe (memoized per device identity) and sets the member above. Called at the end of
// device creation, after ArmPrimGenReroute: it records on m_graphicsQueue.
void ArmWireDepthResolveOrder();
Bool BlitWireColorToDefault(WireImage source, WireImage destination,
GLint sx0, GLint sy0, GLint sx1, GLint sy1,
GLint dx0, GLint dy0, GLint dx1, GLint dy1, GLenum filter);
Bool 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);
// P7 wave 2-B, CONTRACT-P7 §3.2 (`default-color-blit-shape`): the rotated arm. Moves the
// source region into an owned single-sample 2D image of a sampled-float format in the
// same size-compatibility class, then shader-blits THAT to the rotated default
// framebuffer - the shapes BlitWireColorImage itself cannot sample (an integer format, a
// 3D or array source) become shapes it can.
Bool BlitWireColorToDefaultThroughScratch(WireImage source, WireImage destination,
GLint sx0, GLint sy0, GLint sx1, GLint sy1,
GLint dx0, GLint dy0, GLint dx1, GLint dy1,
GLenum filter);
struct WireColorBlitResources;
WireColorBlitResources* m_wireColorBlitResources = nullptr;
void DestroyWireColorBlitResources();
// P7 wave 2-B, CONTRACT-P7 §5.1 (A): the baked depth-mip program (WireDepthMipmap.inc).
// One level of a depth chain, source and destination being two depth subresources of
// the same image; the caller loops. It owns no frontend object, which is what the
// monolith arm's GenerateDepthMipmapWithShader cannot say.
Bool GenerateWireDepthMipLevel(WireImage source, WireImage destination);
struct WireDepthMipmapResources;
WireDepthMipmapResources* m_wireDepthMipmapResources = nullptr;
void DestroyWireDepthMipmapResources();
// P7 wave 2-B (exit gate 3): the readback's own write-visibility barrier, recorded before
// the copy instead of inferred from the image's tracked layout. See WireFramebuffer.inc.
void RecordWireReadbackWriteBarrier();
void ReadWirePixels(GLint x, GLint y, GLsizei width, GLsizei height,
GLenum format, GLenum type, void* pixels);
void GenerateWireMipmap();
Bool SetupWireDraw(FrameContext::FrameData& frame, GLenum mode, Flags<DrawSetupAspect> aspects,
const DrawCmdParam& drawParams, const IndexBufferView* indices);
void DestroyWireDrawPass();
void RetireWireDrawPass();
struct WireDrawAttachmentKey {
MG_Pipe::MGPipeHandle storage = MG_Pipe::kMGPipeNullHandle;
Uint32 resourceKind = 0;
VkImage image = VK_NULL_HANDLE;
VkImageViewType viewType = VK_IMAGE_VIEW_TYPE_2D;
VkFormat format = VK_FORMAT_UNDEFINED;
VkImageAspectFlags aspect = 0, requestedAspect = 0;
Uint32 level = 0, layer = 0, layers = 1, imageLevels = 1;
Uint32 width = 0, height = 0;
VkSampleCountFlagBits samples = VK_SAMPLE_COUNT_1_BIT;
Bool operator==(const WireDrawAttachmentKey&) const = default;
};
struct WireDrawPassKey {
Vector<WireDrawAttachmentKey> attachments;
Vector<Uint32> colorReferences;
Uint32 depthReference = VK_ATTACHMENT_UNUSED;
Uint32 width = 0, height = 0, layers = 1;
Uint64 textureImageEpoch = 0, resourceEraseEpoch = 0;
VkSwapchainKHR swapchain = VK_NULL_HANDLE;
Uint32 swapchainImageIndex = 0;
Bool isDefault = false, framebufferSrgb = false;
Bool operator==(const WireDrawPassKey&) const = default;
};
struct WireDrawPassCacheEntry {
WireDrawPassKey key;
UniquePtr<RenderPassEntry> pass;
Vector<VkImageView> views;
};
// Objects only: every draw still ends/begins its pass and records the
// existing memory dependencies. Each slot is cleared after its fence.
Bool AcquireCachedWireDrawPass(const WireDrawPassKey& key);
void ClearWireDrawPassCache(Uint32 frameIndex);
void ClearAllWireDrawPassCaches();
Vector<Vector<WireDrawPassCacheEntry>> m_wireDrawPassCaches;
WireDrawPassKey m_wireDrawPassKey;
WireRenderPassCompatibilityTable m_wireRenderPassCompatibility;
struct WireRetiredObjects {
Uint64 submitIndex = 0;
UniquePtr<RenderPassEntry> drawPass;
Vector<VkFramebuffer> framebuffers;
Vector<VkRenderPass> renderPasses;
Vector<VkImageView> imageViews;
Vector<VkDescriptorPool> descriptorPools;
// Transfer/resolve scratch storage belongs to the submission that
// consumes it, just like the views and framebuffer above.
Vector<UniquePtr<VkTextureManager::TextureResource>> textures;
Vector<UniquePtr<VkBufferObject>> buffers;
};
void RetireWireObjects(WireRetiredObjects objects);
void CollectWireObjects(Uint64 completedSubmit, Bool all = false);
Vector<WireRetiredObjects> m_wireRetiredObjects;
Uint32 m_wirePreparationDepth = 0;
// P8-D: set only while DrawWireIndirectNative is inside SetupDraw, so SetupWireDraw can
// tell the wire arm's own indirect draw from a monolith indirect entry point reached under
// a transport (still the `buffer-legacy-arm` role violation).
Bool m_wireNativeIndirectDraw = false;
void DispatchWireCompute(GLuint x, GLuint y, GLuint z);
// P8-SV: glDispatchComputeIndirect on the wire arm - vkCmdDispatchIndirect from the
// dispatch-indirect store, as the monolith arm issues it (WireDraw.inc).
void DispatchWireComputeIndirect(GLintptr offset);
void RewindWireDescriptorSetsIfDue();
UniquePtr<RenderPassEntry> m_wireDrawPass;
Vector<VkImageView> m_wireDrawViews;
VkPipeline GetOrCreatePipelineWithInput(GLenum mode, const MagmaProgramSource& program,
const ProgramFactory::VkProgramObject& programObj, ProgramFactory::CompileOptionFlags transformFlags,
const VertexInputStateFactory::BackendVertexInputState& vis, const RenderPassEntry& renderPassEntry,
Bool primitiveRestartEnable, Uint64 wireRenderPassCompatibilityId = 0);
void CopyWireFramebufferToTexture(GLenum target, GLint level, GLint xoffset, GLint yoffset,
GLint x, GLint y, GLsizei width, GLsizei height);
#endif
void QueueClearBufferPayloadForFramebuffer(const MG_State::GLState::FramebufferObject& framebuffer,
GLenum buffer, GLint drawbuffer,
const ClearAttachmentPayload& clearPayload);
@@ -753,11 +482,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// was waited or the device was idled); drops their records and
// recycles pooled fences.
void OnSubmitsCompletedUpTo(Uint64 submitIndex);
#if MOBILEGL_BUILD_DISAGGREGATED
// A later fence alone cannot retire earlier submissions. Wait for the
// whole still-live prefix before advancing the completed submit floor.
Bool WaitForSubmitsUpTo(Uint64 submitIndex, Uint64 timeoutNs);
#endif
VkFence AcquirePooledSubmitFence();
void DestroySubmitFencePool();
Bool HasPendingRecordedWork() const;
@@ -936,12 +660,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkDeviceSize countBufferOffset, Uint32 maxDrawCount,
Uint32 stride);
static inline PFNDrawIndexedIndirectCountFunc s_vkCmdDrawIndexedIndirectCount = nullptr;
#if MOBILEGL_BUILD_DISAGGREGATED
// P8-D: vkCmdDrawIndirectCount (same signature, same extension), for the wire arm's
// glMultiDrawArraysIndirectCount. The monolith arm never loads it: it reads that count on
// the CPU (DirectVulkan.cpp's MultiDrawArraysIndirectCount).
static inline PFNDrawIndexedIndirectCountFunc s_vkCmdWireDrawIndirectCount = nullptr;
#endif
// VK_EXT_multi_draw entry points, loaded at device creation when the extension
// (and its multiDraw feature) is enabled; null otherwise.
static inline PFN_vkCmdDrawMultiEXT s_vkCmdDrawMultiEXT = nullptr;
@@ -985,18 +703,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// per object: one group of four slots each, handed out on first use.
static constexpr SizeT kXfbCounterObjectSlots = 16;
VkBufferObject m_xfbCounterBuffer;
// Which transform feedback object owns each slot group, by the frontend's never-reused
// lifetime id (0 = the slot is free). This used to be an UnorderedMap keyed on the GL
// NAME, which is recycled by glGenTransformFeedbacks: a deleted-and-recreated object
// inherited the dead one's slot, and since nothing ever removed an entry the map also
// grew for the life of the context. A fixed table cannot do either: a group is taken over
// only from an owner with no OPEN span (see CurrentXfbCounterSlot), so an object whose
// counters can still be resumed never loses them, and a dead object's group comes back.
Array<Uint64, kXfbCounterObjectSlots> m_xfbCounterSlotOwner{};
// Tie-break among reclaimable groups only; never on its own, because the paused span the
// groups exist for is by construction the least recently used one.
Array<Uint64, kXfbCounterObjectSlots> m_xfbCounterSlotLastUse{};
Uint64 m_xfbCounterSlotUseSerial = 0;
UnorderedMap<Uint, Uint32> m_xfbCounterSlotByObject;
Uint32 m_xfbNextCounterSlot = 0;
// Set for a slot once a captured draw has been recorded into its span; selects
// counter-buffer resume on the next captured draw of the same span.
Array<Bool, kXfbCounterObjectSlots> m_xfbCountersValid{};
@@ -1006,14 +714,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// Wraps a recorded draw with BeginTransformFeedbackEXT/EndTransformFeedbackEXT
// when GL transform feedback is active; binds capture buffers on demand.
Bool BeginXfbCaptureForDraw(FrameContext::FrameData& frame);
Bool BeginXfbCaptureWithBuffers(FrameContext::FrameData& frame, Uint32 count,
const VkBuffer* buffers, const VkDeviceSize* offsets,
const VkDeviceSize* sizes);
#if MOBILEGL_BUILD_DISAGGREGATED
Bool BeginWireXfbCaptureForDraw(FrameContext::FrameData& frame);
#endif
Uint32 m_currentDrawXfbBufferCount = 0;
Uint32 m_currentDrawXfbBufferMask = 0;
void EndXfbCaptureForDraw(FrameContext::FrameData& frame, Bool began);
// Makes the captured bytes visible to whatever reads them next. Deferred rather than
// recorded next to the capture, because the capturing draw runs inside a render pass
@@ -1121,29 +821,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkBufferManager m_bufferManager;
Uint m_imageIndexAcquired = 0;
// The swapchain image GL addresses as the default framebuffer: the one a readback, a
// blit source or a copy out of it resolves, and the one the app last rendered into.
// Present() runs ahead - it presents the frame and acquires the next image without
// waiting for the apply that would render into it (kWaitPresent) - so this must NOT
// follow m_imageIndexAcquired. Before it existed a readback resolved the freshly
// acquired image, which nothing had written yet: the pure-black sundial-lite frame.
Uint m_defaultFramebufferImageIndex = 0;
FrameContext m_frameContext;
// Resolves the swapchain image index a READ of the default framebuffer must use. A
// non-default framebuffer ignores the index; it keeps the acquired one, which still
// keys its render-pass cache.
Uint32 DefaultFramebufferReadIndex(Bool isDefaultFramebuffer) const {
return isDefaultFramebuffer ? m_defaultFramebufferImageIndex : m_imageIndexAcquired;
}
// Same for a WRITE: the default framebuffer starts addressing the image Present()
// acquired only once something renders into it again.
Uint32 DefaultFramebufferWriteIndex(Bool isDefaultFramebuffer) {
if (isDefaultFramebuffer) m_defaultFramebufferImageIndex = m_imageIndexAcquired;
return DefaultFramebufferReadIndex(isDefaultFramebuffer);
}
UniquePtr<PipelineFactory> m_pipelineFactory;
// Single-slot "last pipeline" memo: skip the per-draw GetOrCreatePipeline work (state
// gather + synthetic vertex-input rebuild + payload hash + lookup) when the full pipeline
@@ -1159,34 +838,12 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Uint64 programHash = 0;
Uint64 vertexInputHash = 0;
Uint64 renderPassHash = 0;
#if MOBILEGL_BUILD_DISAGGREGATED
Uint64 wireRenderPassCompatibilityId = 0;
#endif
// The PRE-HANDLE arm's key component (P2 brief D12.1), and 0 in every entry the
// handle arm mints. VALUE hash of the pipeline-relevant fixed-function state (see
// ComputePipelineStateHash), not the monotonic pipeline-state version: the version
// never repeats, so a per-draw GL_BLEND toggle would miss all entries forever even
// though the state alternates between two values the memo already holds.
// VALUE hash of the pipeline-relevant fixed-function state (see
// ComputePipelineStateHash), not the monotonic pipeline-state version:
// the version never repeats, so a per-draw GL_BLEND toggle would miss
// all entries forever even though the state alternates between two
// values the memo already holds.
Uint64 pipelineStateHash = 0;
#if MOBILEGL_PIPE_PUSH
// The HANDLE arm's key component, and the whole of D12.1: the CLIENT already
// hashed the pipeline subset of RenderStateParameters and minted a content-
// addressed CSO for it (MG_Pipe/MGPipeRenderStateSpans.h, MG_Impl/Pipe/CsoCache),
// so re-hashing the same 396 bytes here was work the boundary had already done.
// Two draws share a CSO handle exactly when their pipeline bytes are equal, and
// the client's subset is a strict SUPERSET of what ComputePipelineStateHash read,
// so the handle discriminates at least as finely as the hash it replaces.
//
// renderPassHash STAYS beside it and is what keeps this key complete: the CSO
// carries GL state only, while colorAttachmentCount and the rasterization sample
// count - which ComputePipelineStateHash folded in through its signature and
// through ResolveEffectiveSampleMask - are render-pass facts that the render-pass
// hash already separates.
//
// Null in an entry minted by the legacy arm, so entries of the two arms can never
// match each other: the compare below tests BOTH components.
MG_Pipe::MGPipeHandle renderStateCso = MG_Pipe::kMGPipeNullHandle;
#endif
ProgramFactory::CompileOptionFlags transformFlags = {};
// Baked into the pipeline (PipelineFactory::ComputeHash mixes it), and NOT derivable
// from anything else in this key: it depends on whether the draw is indexed and on the
@@ -1200,142 +857,19 @@ namespace MobileGL::MG_Backend::DirectVulkan {
PipelineMemoEntry m_pipelineMemo[kPipelineMemoSize];
Uint32 m_pipelineMemoCount = 0;
Uint32 m_pipelineMemoNext = 0;
#if MOBILEGL_PIPE_PUSH
// P2 D12.1's arm selector, and the whole of the pipeline memo's re-key. Returns the
// render-state CSO this draw is keyed on, or the null handle when the pre-handle arm
// is the one that runs.
//
// Under the handle arm the memo's state key IS this handle. The client hashed those
// 396 pipeline bytes when it minted the CSO (MGPipeComputePipelineSubsetHash), so
// recomputing an overlapping hash here was work the boundary had already done; the
// client's pipeline subset is a strict SUPERSET of what ComputePipelineStateHash read,
// so the handle discriminates at least as finely as the hash it replaces. What the
// handle does NOT carry is the render-pass side - colorAttachmentCount and the
// rasterization sample count, which ComputePipelineStateHash folded in through its
// signature and through ResolveEffectiveSampleMask - and that is exactly why
// entry.renderPassHash stays in the key beside it.
//
// The arm is live only when the render-state subsystem is migrated in this run AND the
// client has actually bound a CSO. The second half is not belt and braces: a tree whose
// tracker does not emit create/bind_render_state yet has no handle to key on, and
// delete_render_state clears the binding (MG_Pipe/PipeApply.cpp), so the null handle is
// reachable on any tree. Keying every draw on it would alias every render state onto
// one memo entry, so a null handle means "fall back to a state hash" - never an abort,
// and never a per-draw consultation of the legacy-memo lever: bit 0 is not a Track-H
// subsystem (D14 labels only bits 5 and 6 that), and the lever's Fatal is a STARTUP
// one, in MagmaPipeValidateSubsystemConfiguration.
//
// The fallback is warned ONCE rather than logged at debug, and that is deliberate: a
// silent fallback is what makes "the CSO arm never ran" easy to miss. W is compiled in
// at every shipped log level.
//
// The latch is a plain member bool, NOT MGLOG_W_ONCE. MOBILEGL_LOG_ONCE_INTERNAL
// (MG_Util/Debug/Log.h) is an UNCONDITIONAL std::atomic_flag::test_and_set - a locked
// xchg, executed on every evaluation, not "one static bool test" as an earlier round of
// this comment claimed - and this site is on the per-draw pipeline path in the very
// configuration that reaches it (no tracker: every draw). ROADMAP.md:7 forbids leaving
// instrumentation on a hot path, so the once-ness is one non-atomic, always-predicted
// load of a member that is false exactly once. Single-threaded like the rest of the
// renderer, and per renderer rather than per process, which is also the right scope: a
// second context that never binds a CSO deserves to say so.
//
// What the absence of this warning from a run's log proves, EXACTLY: that no draw took
// the fallback WHILE bit 0 was set. With kMGPipeSubsystemRenderState clear the function
// returns before the latch, so absence proves nothing at all - and no draw is keyed on a
// handle either. Grep the mask out of the log beside it (review v2 minor 3).
//
// Push-only by construction: the pull build does not compile this function at all, so
// its two callers are statement-for-statement what they were (G1).
//
// [routed to the integrator, review v2 minor 11] MG_Pipe::MGPipeApplier() is ONE
// process-global applier (MG_Pipe/PipeApply.cpp), not the per-context CSO store D2
// specifies. In a multi-context process this reads whatever CSO another context last
// bound. The defect is package A's and the fix belongs there; Magma is its only P2
// consumer, so it is named here rather than left for both reviews to assume the other
// caught it.
MG_Pipe::MGPipeHandle ResolveBoundRenderStateCso() const {
if (!MagmaPipeSubsystemOn(MG_Pipe::kMGPipeSubsystemRenderState)) {
return MG_Pipe::kMGPipeNullHandle;
}
const MG_Pipe::MGPipeHandle boundCso = MG_Pipe::MGPipeApplier().BoundRenderStateCso;
if (MG_Pipe::MGPipeHandleIsNull(boundCso) && !m_pipelineCsoFallbackWarned) {
m_pipelineCsoFallbackWarned = true;
MGLOG_W("MGPipe: kMGPipeSubsystemRenderState is on but no render-state CSO is "
"bound; the pipeline memo is running on a state hash, not on the CSO "
"handle (no tracker on this build, or a draw between "
"delete_render_state and the next bind)");
}
return boundCso;
}
// Latch for the warning above. Mutable because the resolve is const and the latch is
// not part of the renderer's observable state.
mutable Bool m_pipelineCsoFallbackWarned = false;
// The memo key's STATE-HASH half, for a draw that has no CSO handle to key on: the
// pre-handle arm, and the fallback of D12.1's handle arm. Cached on the pipeline-state
// version plus the two render-pass facts the hash's inputs depend on, so an unchanged
// (version, colorAttachmentCount, sampleCount) proves the bytes are unchanged.
//
// [deviation from D12.1] The brief deletes this gate and its cached fields outright.
// They cannot go while a no-CSO draw is reachable - and it is, on any tree: a draw
// between delete_render_state and the next bind has no handle. On a tree whose tracker
// binds a CSO these five words are written once and never read again; they retire for
// real when the pull path does, at P13.
Uint64 ResolveFallbackPipelineStateHash(Uint renderStateVersion, Uint32 colorAttachmentCount,
VkSampleCountFlagBits rasterizationSamples) {
if (!m_pipelineStateHashValid || m_pipelineStateHashVersion != renderStateVersion ||
m_pipelineStateHashColorCount != colorAttachmentCount ||
m_pipelineStateHashSampleCount != rasterizationSamples) {
#if MOBILEGL_PIPE_LEGACY_MEMOS
m_pipelineStateHash =
ComputePipelineStateHash(colorAttachmentCount, rasterizationSamples);
#else
m_pipelineStateHash = ComputePipelineSubsetStateHashFallback();
#endif
m_pipelineStateHashVersion = renderStateVersion;
m_pipelineStateHashColorCount = colorAttachmentCount;
m_pipelineStateHashSampleCount = rasterizationSamples;
m_pipelineStateHashValid = true;
}
return m_pipelineStateHash;
}
#endif // MOBILEGL_PIPE_PUSH
#if MOBILEGL_PIPE_PUSH && !MOBILEGL_PIPE_LEGACY_MEMOS
// The same answer as ComputePipelineStateHash, computed from the P2 chunk table
// instead of from a hand-written field list, for the build that compiles no
// pre-handle arm (cmake -DMOBILEGL_PIPE_LEGACY_MEMOS=OFF). It is the CLIENT's own
// hash function - MGPipeComputePipelineSubsetHash over the 396 pipeline bytes - so a
// draw keyed on it and a draw keyed on a CSO handle are keyed on the same equivalence
// class of state, and the render-pass facts stay separated by renderPassHash either
// way. This is what makes the no-legacy build RUNNABLE rather than a configuration
// that aborts on the first draw that arrives without a CSO.
Uint64 ComputePipelineSubsetStateHashFallback() const;
#endif
#if MOBILEGL_PIPE_LEGACY_MEMOS
// THE PRE-HANDLE ARM (P2 brief D12.1 / D14). Hash of every fixed-function GL state the
// pipeline payload reads that the memo key's other fields (mode / program / vertex
// input / render pass / transform flags) do not already pin down. Equal hash under an
// equal rest of key => byte-identical PipelineCreatePayload. Cached per pipeline-state
// Hash of every fixed-function GL state the pipeline payload reads that the
// memo key's other fields (mode / program / vertex input / render pass /
// transform flags) do not already pin down. Equal hash under an equal rest
// of key => byte-identical PipelineCreatePayload. Cached per pipeline-state
// version: the version is monotonic and bumps on every pipeline-state
// change, so an unchanged (version, colorAttachmentCount) proves the state
// bytes are unchanged and the hash can be reused without re-reading them.
//
// The handle arm computes none of this: the client hashed the same bytes when it
// minted the CSO, so all five cached-hash members below exist only to avoid a
// re-hash the handle arm never performs.
Uint64 ComputePipelineStateHash(Uint32 colorAttachmentCount,
VkSampleCountFlagBits rasterizationSamples) const;
#endif
// The effective GL_SAMPLE_MASK word for a draw at this rasterization sample count; see
// the definition for the GL-vs-Vulkan rule it reconciles. Shared by the pipeline payload
// and the pipeline-state memo word so the two cannot disagree. NOT part of the legacy
// arm: it is a PAYLOAD computation that depends on rasterizationSamples, so it survives
// the re-key and keeps reading Multisample / SampleMask / SampleMaskValue out of the
// working block.
// and the pipeline-state memo word so the two cannot disagree.
Uint32 ResolveEffectiveSampleMask(VkSampleCountFlagBits rasterizationSamples) const;
// ResolveFallbackPipelineStateHash's cache. Written once and never read again on a
// build whose client binds a render-state CSO; see that function for why it survives
// the re-key at all.
Uint m_pipelineStateHashVersion = 0;
Uint32 m_pipelineStateHashColorCount = 0;
// The sample count the cached hash was computed at. A pipeline-state input now depends on
@@ -1361,8 +895,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// Drops every memoized pipeline handle. Required at command-buffer
// boundaries and whenever any pipeline may have been destroyed. Also drops
// the cached pipeline-state hash: the same boundaries can retire the GL
// context whose monotonic version the cache is keyed on. The handle arm has no
// such cache to drop - a CSO handle is not derived from a monotonic version.
// context whose monotonic version the cache is keyed on.
void InvalidatePipelineMemo() {
m_pipelineMemoCount = 0;
m_pipelineMemoNext = 0;
@@ -1453,13 +986,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// common shape), and "the VAO did not move" would then skip the layout
// re-resolve for a different VAO.
Uint64 vaoLifetimeId = 0;
#if MOBILEGL_PIPE_PUSH
// P2 D12.4: the handle arm's answer to the same question, and one compare rather
// than the pair above. Kept BESIDE them rather than replacing them because the
// pre-handle arm is still compiled (MOBILEGL_PIPE_LEGACY_MEMOS) and this snapshot
// is a value struct, not a wire type.
MG_Pipe::MGPipeHandle vaoHandle = MG_Pipe::kMGPipeNullHandle;
#endif
Uint32 vaoConfigVersion = 0;
const void* drawFbo = nullptr;
// Never-reused lifetime id beside the raw pointer + Uint16 version: a
@@ -1734,13 +1260,6 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// - bindings revalidates per draw exactly as before (frame serial, content
// hash, per-binding live buffer pointers and slice epochs).
struct alignas(64) VaoDrawMemo {
#if MOBILEGL_PIPE_PUSH
// P2 D12.4: the handle arm's key, and the ONLY key it needs. {slot, gen} is an
// identity, so the pointer-plus-lifetime-id pair below stops being a key here;
// the slot also picks the table entry, so the address hash and the two-way probe
// go with it. Null in an entry that has never been claimed.
MG_Pipe::MGPipeHandle vaoHandle = MG_Pipe::kMGPipeNullHandle;
#endif
const MG_State::GLState::VertexArrayObject* vaoKey = nullptr;
// The VAO's never-reused lifetime id, checked alongside vaoKey. The pointer
// ALONE is not an identity: a deleted VAO's heap address is handed straight
@@ -1767,48 +1286,8 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// fixed table also makes every VaoDrawMemo/ResolvedVertexBindings pointer
// stable for the duration of a draw, which the EBO memo handoff
// (m_currentDrawResolvedEntry) relies on.
//
// [deviation from D12.4, deliberate and narrow] The brief asks for a grow-on-demand
// Vector. This one stays FIXED at exactly the capacity and exactly the 2-way victim
// rule it has on the base ref, and only its KEY changes (a {slot, gen} handle instead
// of a hashed heap address plus a lifetime id). Two reasons, and the second is the
// whole of review v2's MAJOR 1:
// * a VaoDrawMemo is ~450 B (ResolvedVertexBindings dominates), so growing this
// table with the live VAO set is megabytes on a platform with an LMK, where the
// other two memos are 48 B and can afford it;
// * this is the ONLY one of the three memos that had a capacity before this package.
// Losing an entry here costs a vertex-binding re-resolve, exactly what losing it
// cost on the base ref, so at any working-set size this table is no worse than what
// it replaces - and strictly better below capacity, where the handle is a bijection
// with the slot and the two-way probe never collides at all. The other two memos
// (VertexInputStateFactory::m_vaoMemos) had NO capacity, so they keep having none.
static constexpr Uint32 kVaoDrawMemoSlotCount = 2048; // power of two
Vector<VaoDrawMemo> m_vaoDrawMemoTable;
#if MOBILEGL_PIPE_PUSH
// The renderer's {slot, gen} mint, shared with its VertexInputStateFactory so both
// derive the same handle for the same VAO. Per renderer, never a process-global: a
// global would share one table and one reclamation clock across two live contexts and
// outlive every one of them (review v2 minor 4).
MagmaPipeIdentityTables m_pipeIdentity;
// The VAO's {slot, gen}. A one-entry memo hit for every acquisition after a draw's
// first, so there is no second memo in front of it here.
MG_Pipe::MGPipeHandle ResolveVaoHandle(const MG_State::GLState::VertexArrayObject& vao) {
return m_pipeIdentity.HandleOf(MG_Pipe::MGPipeKind::VertexElementsCso,
vao.GetLifetimeId());
}
#endif
// "Is this VAO's content hash already memoized?", asked of whichever side owns the
// memo (P2 D12.5). Force-inlined and defined in the class body so that the PULL
// build's three readers keep compiling to the very same two loads they always did -
// G1 admits no resize, and an out-of-line call here would be one.
[[gnu::always_inline]] inline Bool VaoContentHashIfKnown(
const MG_State::GLState::VertexArrayObject& vao, Uint64& outHash) const {
#if MOBILEGL_PIPE_PUSH
return m_vertexInputStateFactory->TryGetMemoizedHash(vao, outHash);
#else
return vao.GetBackendHashMemo(outHash);
#endif
}
// Finds the slot holding `vao`, or recycles the older of its two candidate
// slots into an empty memo keyed on `vao`. Never returns null.
VaoDrawMemo* LookupVaoDrawMemo(const MG_State::GLState::VertexArrayObject* vao);
@@ -1843,7 +1322,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
VkPipeline GetOrCreatePipeline(
GLenum mode,
const MagmaProgramSource& program,
const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj,
ProgramFactory::CompileOptionFlags transformFlags,
const MG_State::GLState::VertexArrayObject& vao,
@@ -1855,14 +1334,14 @@ namespace MobileGL::MG_Backend::DirectVulkan {
// flush the pending recording (see the body), which retires the current command buffer.
Bool PrepareStorageImageTextures(
FrameContext::FrameData& frame,
const MagmaProgramSource& program,
const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj);
// Vulkan forbids a sampled descriptor and writable storage descriptor from naming the
// same image subresource in one shader operation. Snapshot only the sampler side; the
// storage descriptor continues to name the application texture.
Bool PrepareSamplerImageFeedbackSnapshots(
FrameContext::FrameData& frame,
const MagmaProgramSource& program,
const MG_State::GLState::ProgramObject& program,
const ProgramFactory::VkProgramObject& programObj,
VkPipelineStageFlags consumerShaderStageMask);
@@ -1969,12 +1448,7 @@ namespace MobileGL::MG_Backend::DirectVulkan {
Bool MaterializePendingDepthStencilClearForDefaultFramebuffer(
VkCommandBuffer commandBuffer, const MG_State::GLState::FramebufferAttachmentObject& attachment,
const ClearAttachmentPayload& payload);
#if !MOBILEGL_BUILD_DISAGGREGATED
// P7 wave 2-B2 (CONTRACT-P7 §5.2, (B')): the hidden blit program's pipeline. A
// disaggregated build has no hidden program on either arm, so this has neither a body
// nor a caller there.
VkPipeline GetOrCreateBlitPipeline(const RenderPassEntry& renderPassEntry);
#endif
Bool GenerateDepthMipmapWithShader(FrameContext::FrameData& frame,
MG_State::GLState::ITextureObject& texture,
VkTextureManager::TextureResource& resource,
MobileGL/MG_Backend/DirectVulkan/Renderer/WireColorBlit.frag
-13
View File
@@ -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
-407
View File
@@ -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
-25
View File
@@ -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
-66
View File
@@ -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
-132
View File
@@ -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
-172
View File
@@ -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
-128
View File
@@ -1,128 +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 (and DispatchWireComputeIndirect, P8-SV) -------------------------
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)
// ---- VulkanRenderer::GenerateWireMipmap (P8-F) -----------------------------------------
// `mipmap-shader-format-or-shape` was a Fatal on this arm and a decline on the monolith arm; it
// is the monolith's decline now. Counted once per refused glGenerateMipmap, whose chain is left
// as it was.
MGL_WIRE_DECLINE(MipmapShaderFormatOrShape)
// ---- VulkanRenderer::DrawWireIndirectNative (P8-D), in statement order -----------------------
MGL_WIRE_DECLINE(IndirectBufferUnbound)
MGL_WIRE_DECLINE(IndirectCommandRange)
MGL_WIRE_DECLINE(IndirectCountRange)
MGL_WIRE_DECLINE(IndirectIndexStore)
// ---- P8-SV -------------------------------------------------------------------------------
// VulkanRenderer::GenerateWireMipmap: a combined depth/stencil (or stencil-only) chain, which no
// arm generates (CONTRACT-P7 §3.2). It logged but was never counted, so MGWIRE-DECLINES could
// not see it. Counted once per refused glGenerateMipmap, whose chain is left as it was.
MGL_WIRE_DECLINE(MipmapDepthStencilAspect)
// VulkanRenderer::DispatchWireComputeIndirect, in statement order: the dispatch-indirect store
// is missing, or the three group-count words lie outside it or are misaligned.
MGL_WIRE_DECLINE(DispatchIndirectBufferUnbound)
MGL_WIRE_DECLINE(DispatchIndirectRange)
MobileGL/MG_Backend/DirectVulkan/Renderer/WireDepthMipmap.frag
-28
View File
@@ -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
-328
View File
@@ -1,328 +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;
// P8-SV: THE PASS MAKES 2D VIEWS (makeView below), which a 1D, 1D-array or 3D image does
// not admit. A caller that fills viewType from the image gets a refusal here, and the
// wire arm's GenerateWireMipmap asks the same question before it grows the chain.
for (const VkImageViewType viewType : {source.viewType, destination.viewType}) {
if (viewType == VK_IMAGE_VIEW_TYPE_1D || viewType == VK_IMAGE_VIEW_TYPE_1D_ARRAY ||
viewType == VK_IMAGE_VIEW_TYPE_3D)
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
-33
View File
@@ -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
-174
View File
@@ -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
-329
View File
@@ -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
-992
View File
@@ -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
-121
View File
@@ -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
-849
View File
@@ -1,849 +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;
}
// P8-D: the wire arm's own indirect draw (DrawWireIndirectNative) is the one caller that
// may pass this aspect; a monolith indirect entry point reached here is still the role
// violation.
if ((aspects & DrawSetupAspect::IndirectDrawBuffer) && !m_wireNativeIndirectDraw)
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];
// P8-F: A RECORD INVARIANT, NOT AN UNMIGRATED VERB (it carried a P8 phase tag).
// The client turns every enabled client-memory array into an owned buffer before the
// draw record is built, or refuses the draw itself (MG_Impl/Pipe/OwnedDrawInputs.h),
// so an attribute the program reads with no buffer handle is a foreign peer's record.
if (MG_Pipe::MGPipeHandleIsNull(resource.Res))
MG_Pipe::MGPipeSessionFail(MG_Pipe::MGPipeFatalFamily::ProtocolCorruption,
"MGPipe: Fatal{ProtocolCorruption, \"Magma:client-vertex-array\"} location=%u: an "
"attribute the program reads carries no buffer handle", location);
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. So may an
// indirect draw (P8-D): its vertex range is in GPU words nobody read.
if (stride && !(aspects & DrawSetupAspect::IndexBuffer) &&
!(aspects & DrawSetupAspect::IndirectDrawBuffer) && !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;
}
// ---- P8-D: THE WIRE ARM'S INDIRECT DRAWS READ THEIR WORDS ON THE GPU ----------------------
//
// The shape the monolith arm records (VulkanRenderer.cpp's MultiDraw{Elements,Arrays}Indirect
// and MultiDrawElementsIndirectCount), with the wire store's own VkBuffer in place of the
// frontend buffer's resident slice. Before this, every wire indirect draw read its commands
// through ReadWireBuffer and expanded them on the CPU, and a store a shader had written made
// that read a whole-GPU wait (WaitForWireBufferHostAccess) per draw.
//
// THE ONE FALSE: a COUNT form this device cannot issue - the monolith arm's own condition for
// vkCmdDrawIndexedIndirectCount (MultiDrawElementsIndirectCount), extended to the non-indexed
// twin the monolith never loads. Everything else is issued here or declined by name.
Bool VulkanRenderer::DrawWireIndirectNative(GLenum mode, GLenum type, Uint64 offset, GLsizei drawcount,
GLsizei stride, Bool indexed, Bool counted, Uint64 countOffset) {
if (drawcount <= 0) return true;
if (counted) {
const auto countEntry = indexed ? s_vkCmdDrawIndexedIndirectCount : s_vkCmdWireDrawIndirectCount;
if (!m_drawIndirectCountExtensionEnabled || countEntry == nullptr ||
(!m_multiDrawIndirectFeatureEnabled && drawcount != 1))
return false;
}
const auto& state = MG_Pipe::MGPipeApplier();
// GL's command sizes (GL 4.6 10.3.10), which are also Vulkan's.
const Uint64 commandSize = indexed ? 5 * sizeof(Uint32) : 4 * sizeof(Uint32);
if (stride == 0) stride = static_cast<GLsizei>(commandSize);
BufferSlice commands{};
if (MG_Pipe::MGPipeHandleIsNull(state.VerbIndirectBuffer) ||
!m_bufferManager.AcquireWireSlice(BufferKind::Indirect, state.VerbIndirectBuffer, commands)) {
MGL_WIRE_DECLINE_AT(IndirectBufferUnbound, "an indirect draw names no live indirect buffer store");
return true;
}
const Uint64 span = static_cast<Uint64>(stride) * static_cast<Uint64>(drawcount - 1) + commandSize;
// GL refuses a stride that is not a multiple of four (INVALID_VALUE), and Vulkan requires
// it for drawCount > 1; a peer's record that breaks either is declined, not issued.
if (stride < static_cast<GLsizei>(commandSize) || (stride & 3) != 0 || (offset & 3u) != 0 ||
offset > commands.size || span > commands.size - offset) {
MGL_WIRE_DECLINE_AT(IndirectCommandRange, "the indirect commands lie outside their store or are misaligned");
return true;
}
BufferSlice parameters{};
if (counted) {
if (MG_Pipe::MGPipeHandleIsNull(state.VerbIndirectParameterBuffer) ||
!m_bufferManager.AcquireWireSlice(BufferKind::Indirect, state.VerbIndirectParameterBuffer, parameters) ||
(countOffset & 3u) != 0 || countOffset > parameters.size || parameters.size - countOffset < sizeof(Uint32)) {
MGL_WIRE_DECLINE_AT(IndirectCountRange, "the indirect draw count lies outside its parameter store");
return true;
}
}
// The index view is the WHOLE bound element store past its binding offset, as the monolith
// arm binds it: the commands name their own firstIndex, which only the GPU reads.
IndexBufferView indices{};
DrawCmdParam vertexRange{};
vertexRange.instanceCount = 1;
Flags<DrawSetupAspect> aspects = DrawSetupAspect::IndirectDrawBuffer;
if (indexed) {
const SizeT width = MG_Util::GetGLTypeSize(type);
BufferSlice elements{};
if (width == 0 || MG_Pipe::MGPipeHandleIsNull(state.IndexBuffer.Res) ||
!m_bufferManager.AcquireWireSlice(BufferKind::Index, state.IndexBuffer.Res, elements) ||
state.IndexBuffer.Offset > elements.size) {
MGL_WIRE_DECLINE_AT(IndirectIndexStore, "an indexed indirect draw names no usable element store");
return true;
}
indices.indexType = type;
indices.indexByteOffset = 0;
indices.indexByteSize = static_cast<SizeT>(elements.size - state.IndexBuffer.Offset);
vertexRange.vertexCount = static_cast<Uint32>(indices.indexByteSize / width);
aspects |= DrawSetupAspect::IndexBuffer;
}
// A shader write the store was marked with (MarkWireBufferGpuWritten) is made visible to
// the indirect read here, once per write, so a program that omits GL_COMMAND_BARRIER_BIT
// is not left racing a read the old CPU path used to take after a whole-GPU wait. The
// application's own glMemoryBarrier is BuildMemoryBarrierForGlBarriers, as on the monolith
// arm; transfer writes carry their own MEMORY_READ after-barrier (VkBufferManager.cpp).
const Bool commandsWritten = m_bufferManager.TakeWireIndirectReadBarrier(state.VerbIndirectBuffer);
const Bool countWritten = counted && m_bufferManager.TakeWireIndirectReadBarrier(state.VerbIndirectParameterBuffer);
if (commandsWritten || countWritten) {
RetireWireDrawPass();
auto& barrierFrame = m_frameContext.GetCurrent();
if (!barrierFrame.isCommandRecording) m_frameContext.BeginCommandRecording();
if (VkRenderPassManager::GetActiveRenderPass() != nullptr)
VkRenderPassManager::EndRenderPass(barrierFrame.commandBuffer);
VkMemoryBarrier barrier{VK_STRUCTURE_TYPE_MEMORY_BARRIER};
barrier.srcAccessMask = VK_ACCESS_MEMORY_WRITE_BIT;
barrier.dstAccessMask = VK_ACCESS_INDIRECT_COMMAND_READ_BIT;
vkCmdPipelineBarrier(barrierFrame.commandBuffer, VK_PIPELINE_STAGE_ALL_COMMANDS_BIT,
VK_PIPELINE_STAGE_DRAW_INDIRECT_BIT, 0, 1, &barrier, 0, nullptr, 0, nullptr);
if (MG_Util::PipeStats::Enabled())
MG_Util::PipeStats::AddCalls(MG_Util::PipeStats::CallClass::WireIndirectBarriers, 1);
}
auto& frame = m_frameContext.GetCurrent();
m_wireNativeIndirectDraw = true;
const Bool ready = SetupDraw(frame, mode, aspects, vertexRange, indexed ? &indices : nullptr);
m_wireNativeIndirectDraw = false;
if (!ready) return true;
MOBILEGL_ASSERT(frame.isCommandRecording, "%s: frame recording was not started", __func__);
const VkCommandBuffer commandBuffer = frame.commandBuffer;
const VkDeviceSize first = commands.offset + offset;
const Uint32 count = static_cast<Uint32>(drawcount);
const Uint32 byteStride = static_cast<Uint32>(stride);
if (counted) {
const auto countEntry = indexed ? s_vkCmdDrawIndexedIndirectCount : s_vkCmdWireDrawIndirectCount;
countEntry(commandBuffer, commands.buffer, first, parameters.buffer, parameters.offset + countOffset,
count, byteStride);
} else if (count == 1 || (!m_multiDrawForceUnrollIndirect && m_multiDrawIndirectFeatureEnabled)) {
// maxDrawIndirectCount bounds one call; GL's drawcount does not.
const Uint32 limit = std::max<Uint32>(1u, m_physicalDevice.properties.limits.maxDrawIndirectCount);
for (Uint32 base = 0; base < count; base += limit) {
const Uint32 chunk = std::min(count - base, limit);
const VkDeviceSize at = first + static_cast<VkDeviceSize>(base) * byteStride;
if (indexed) vkCmdDrawIndexedIndirect(commandBuffer, commands.buffer, at, chunk, byteStride);
else vkCmdDrawIndirect(commandBuffer, commands.buffer, at, chunk, byteStride);
}
} else {
// No multiDrawIndirect: one indirect draw per command, still read by the GPU
// (the monolith arm's own fallback).
for (Uint32 i = 0; i < count; ++i) {
const VkDeviceSize at = first + static_cast<VkDeviceSize>(i) * byteStride;
if (indexed) vkCmdDrawIndexedIndirect(commandBuffer, commands.buffer, at, 1, 0);
else vkCmdDrawIndirect(commandBuffer, commands.buffer, at, 1, 0);
}
}
if (MG_Util::PipeStats::Enabled())
MG_Util::PipeStats::AddCalls(MG_Util::PipeStats::CallClass::WireIndirectNativeDraws, 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);
}
// ---- P8-SV: THE WIRE ARM'S INDIRECT DISPATCH READS ITS GROUP COUNTS ON THE GPU ----------
//
// The monolith arm's shape (VulkanRenderer.cpp's DispatchComputeIndirect) with the wire
// store's own VkBuffer in place of the frontend buffer's resident slice. Before this the wire
// arm read the three words through ReadWireBuffer and dispatched them from the CPU, and a store
// a shader had written made that read a whole-GPU wait (WaitForWireBufferHostAccess) per call.
// There is no shape the device cannot issue, so there is no CPU path left: a record whose
// store or words are unusable is declined by name.
//
// The barrier is P8-D's draw rule (DrawWireIndirectNative): a store marked shader-written gets
// one MEMORY_WRITE -> INDIRECT_COMMAND_READ barrier before its next indirect read, whether or
// not the application issued GL_COMMAND_BARRIER_BIT; DRAW_INDIRECT is the stage that consumes
// VkDispatchIndirectCommand too. It is TAKEN before the bindings below, because binding this
// dispatch's own storage buffers marks them written, and a store that is both this dispatch's
// parameters and one of its outputs must keep that mark for the next reader.
void VulkanRenderer::DispatchWireComputeIndirect(GLintptr offset) {
RetireWireDrawPass();
const auto& state = MG_Pipe::MGPipeApplier();
constexpr Uint64 kCommandSize = 3 * sizeof(Uint32); // GL 4.6 10.3.10 / VkDispatchIndirectCommand
BufferSlice parameters{};
if (MG_Pipe::MGPipeHandleIsNull(state.VerbDispatchIndirectBuffer) ||
!m_bufferManager.AcquireWireSlice(BufferKind::Indirect, state.VerbDispatchIndirectBuffer, parameters)) {
MGL_WIRE_DECLINE_AT(DispatchIndirectBufferUnbound, "an indirect dispatch names no live dispatch-indirect store");
return;
}
// GL refuses an offset that is negative or not a multiple of four (INVALID_VALUE) and a
// command past the end of the buffer (INVALID_OPERATION); a peer's record that breaks
// either is declined, not issued.
if (offset < 0 || (static_cast<Uint64>(offset) & 3u) != 0 || static_cast<Uint64>(offset) > parameters.size ||
parameters.size - static_cast<Uint64>(offset) < kCommandSize) {
MGL_WIRE_DECLINE_AT(DispatchIndirectRange, "the dispatch group counts lie outside their store or are misaligned");
return;
}
auto& frame = m_frameContext.GetCurrent();
if (m_bufferManager.TakeWireIndirectReadBarrier(state.VerbDispatchIndirectBuffer)) {
if (!frame.isCommandRecording) m_frameContext.BeginCommandRecording();
if (VkRenderPassManager::GetActiveRenderPass() != nullptr)
VkRenderPassManager::EndRenderPass(frame.commandBuffer);
VkMemoryBarrier barrier{VK_STRUCTURE_TYPE_MEMORY_BARRIER};
barrier.srcAccessMask = VK_ACCESS_MEMORY_WRITE_BIT;
barrier.dstAccessMask = VK_ACCESS_INDIRECT_COMMAND_READ_BIT;
vkCmdPipelineBarrier(frame.commandBuffer, VK_PIPELINE_STAGE_ALL_COMMANDS_BIT,
VK_PIPELINE_STAGE_DRAW_INDIRECT_BIT, 0, 1, &barrier, 0, nullptr, 0, nullptr);
if (MG_Util::PipeStats::Enabled())
MG_Util::PipeStats::AddCalls(MG_Util::PipeStats::CallClass::WireIndirectBarriers, 1);
}
const auto program = WireProgramSource(state.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;
}
// PrepareWireTextureResources may have flushed and begun a new recording.
auto& dispatchFrame = m_frameContext.GetCurrent();
if (!dispatchFrame.isCommandRecording) m_frameContext.BeginCommandRecording();
if (!m_uniformManager->BindProgramUniformBuffers(dispatchFrame.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(dispatchFrame.commandBuffer, VK_PIPELINE_BIND_POINT_COMPUTE, pipeline);
vkCmdDispatchIndirect(dispatchFrame.commandBuffer, parameters.buffer,
parameters.offset + static_cast<VkDeviceSize>(offset));
if (MG_Util::PipeStats::Enabled())
MG_Util::PipeStats::AddCalls(MG_Util::PipeStats::CallClass::WireIndirectNativeDispatches, 1);
}
#endif
MobileGL/MG_Backend/DirectVulkan/Renderer/WireFramebuffer.inc
-1684
View File
File diff suppressed because it is too large Load Diff
MobileGL/MG_Backend/DirectVulkan/Renderer/WireMultisampleDepthResolve.frag
-16
View File
@@ -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
-167
View File
@@ -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
-18
View File
@@ -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
-103
View File
@@ -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
-19
View File
@@ -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
-245
View File
@@ -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
-62
View File
@@ -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
-49
View File
@@ -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
-214
View File
@@ -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/GbmFrameChannel.cpp
-737
View File
@@ -1,737 +0,0 @@
// MobileGL - MobileGL/MG_Backend/GbmFrameChannel.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
#include "GbmFrameChannel.h"
#if MOBILEGL_BUILD_DISAGGREGATED && defined(__ANDROID__)
#include <android/hardware_buffer.h>
#include <cerrno>
#include <cstring>
#include <poll.h>
#include <sys/socket.h>
#include <sys/stat.h>
#include <sys/un.h>
#include <unistd.h>
// WHAT THIS FILE IS WRITTEN AGAINST, AND WHAT HAS NOT BEEN RUN.
//
// The other end exists and is tested on this machine: MobileGL/MG_Gbm/GbmHostChannel.cpp dials
// this socket with SOCK_SEQPACKET, reads one message per frame, computes that message's expected
// length from the handle's own two counts, and refuses any other length. Every byte below is
// written to that parser. There is no phone attached to the machine this was written on, so the
// file is compile-verified for aarch64 Android and nothing more: the first run on a device is what
// will say whether the relay in RelayHandle() reads back the handle's bytes exactly as
// AHardwareBuffer_sendHandleToUnixSocket writes them, which is why that path is written to
// survive both layouts the platform's serializer could have (see the note there).
namespace MobileGL::MG_Backend {
namespace {
// THE LAYOUT IS A PROTOCOL, SO ITS SIZES ARE ASSERTED AND NOT ASSUMED. The container
// derives the length of a frame message from these three sizes plus the handle's counts,
// so a field added here, or the packing attribute dropped, would not be a compile error
// over there - it would be every frame skipped with a message about its length.
static_assert(sizeof(GbmFrameOffer) == 10 * sizeof(Uint32), "the offer is ten 32 bit fields on the wire");
static_assert(sizeof(GbmFrameRelease) == 3 * sizeof(Uint32), "the release is three 32 bit fields on the wire");
static_assert(sizeof(GbmNativeHandleHeader) == 3 * sizeof(Int32),
"a native handle begins with a version and two counts, on every Android ABI");
// The container reads one message per frame into a 4 KiB buffer and skips a message that
// does not fit in it (GbmHostMessageMax, GbmHostChannel.cpp), so a message larger than this
// is refused here rather than built and dropped there.
constexpr SizeT kMessageMax = 4096;
// The descriptors one handle may carry, which is the container's own cap (GbmHostMaxFds).
// Every AHardwareBuffer handle this project has seen carries one - the dma-buf - and both
// ends refuse a frame whose handle names more than they can take rather than forward a
// truncated list into a buffer of unknown memory.
constexpr Int kMaxHandleFds = 8;
// How many release messages one call reads before it returns to the frame. A cap and not a
// loop to exhaustion: the messages left behind stay in the socket, whose buffer the kernel
// bounds, and the next frame drains them.
constexpr Int kDrainMax = 64;
// HOW MANY DIALERS THE KERNEL MAY HOLD FOR THIS LISTENER. One container is the protocol,
// but the queue is not the connection: every compositor that was restarted dials once more,
// and a listener that only ever has one slot leaves its queue full for the next one. With
// listen(fd, 1) that is exactly what was measured - connect() from the container answered
// EAGAIN(11) on four attempts out of four after two restarts, and no dialer reached this
// side again for as long as the server lived.
constexpr Int kDialerBacklog = 16;
// The acceptor's poll timeout. It is a wake-up and not a schedule, so it only has to be
// short enough that a container dialling into a socket nothing else touches is taken
// promptly; a dialer that arrives while the thread is waiting wakes it at once.
constexpr Int kAcceptPollMs = 100;
// How long the relay read waits for bytes the send one statement earlier has already put in
// the socket. It exists only so that an invariant broken somewhere else cannot park the
// apply thread; on a local socketpair the wait is zero.
constexpr Int kRelayWaitMs = 2;
// close() may overwrite the errno a caller is in the middle of reporting, and every caller
// here is reporting a failure errno describes.
void CloseQuietly(Int fd) {
if (fd < 0) return;
const Int savedErrno = errno;
::close(fd);
errno = savedErrno;
}
}
GbmFrameChannel::~GbmFrameChannel() { Close(); }
Bool GbmFrameChannel::Open() {
const std::lock_guard<std::mutex> lock(m_mutex);
if (m_listen >= 0) return true;
const char* configured = ::getenv(kGbmFrameSocketEnv);
const char* path = (configured != nullptr && configured[0] != 0) ? configured : kGbmFrameSocketPath;
constexpr SizeT pathMax = sizeof(((struct sockaddr_un*)nullptr)->sun_path);
if (std::strlen(path) >= pathMax) {
MGLOG_E_ONCE("gbm frame channel: the container socket path %s does not fit in sun_path (%zu bytes); no "
"container can be served",
path, pathMax);
return false;
}
// SOCK_SEQPACKET because that is what the container dials with (GbmHostChannel::EnsureOpen
// asks for exactly this), and a stream listener answers it EPROTOTYPE - the container
// prints that as "a socket of a different type". SOCK_NONBLOCK because the accept below
// runs on the apply thread and may not wait for a container that is not there; SOCK_CLOEXEC
// because every process this server starts would otherwise inherit a socket that receives
// the phone's frames.
const Int fd = ::socket(AF_UNIX, SOCK_SEQPACKET | SOCK_NONBLOCK | SOCK_CLOEXEC, 0);
if (fd < 0) {
MGLOG_E_ONCE("gbm frame channel: socket(AF_UNIX, SOCK_SEQPACKET): %s; the frames are drawn and presented "
"without a container",
std::strerror(errno));
return false;
}
// A node left behind by a server that died is not a reason to refuse a container: bind
// would answer EADDRINUSE for a socket nobody is listening on.
::unlink(path);
struct sockaddr_un address = {};
address.sun_family = AF_UNIX;
// The terminator travels with the name: sun_path is a C string for a pathname socket, and a
// name without one is a name the kernel reads past the end of.
std::memcpy(address.sun_path, path, std::strlen(path) + 1);
if (::bind(fd, reinterpret_cast<struct sockaddr*>(&address), sizeof(address)) != 0) {
MGLOG_E_ONCE("gbm frame channel: bind(%s): %s; the frames are drawn and presented without a container",
path, std::strerror(errno));
CloseQuietly(fd);
return false;
}
// connect() to a pathname socket needs write permission on the node, and the container is
// not this process's user, so the umask's usual 0755 would leave it refused for a reason it
// could not see. 0666 is what makes the node reachable by the other half of a split run; a
// chmod that fails is not fatal, because a peer running as this uid still dials it.
if (::chmod(path, 0666) != 0) {
MGLOG_W_ONCE("gbm frame channel: chmod(%s, 0666): %s; a container running as another user cannot dial "
"this socket",
path, std::strerror(errno));
}
if (::listen(fd, kDialerBacklog) != 0) {
MGLOG_E_ONCE("gbm frame channel: listen(%s): %s; the frames are drawn and presented without a container",
path, std::strerror(errno));
::unlink(path);
CloseQuietly(fd);
return false;
}
m_listen = fd;
m_path = path;
// THE ACCEPTOR IS STARTED WITH THE SOCKET AND NOT WITH THE FIRST FRAME. A compositor dials
// at its device creation and keeps the connection, so the dial a frame would have answered
// has already happened by the time that frame is offered: an accept on the offer path is an
// accept that runs after the thing it exists for. The descriptor is copied into the thread
// as an argument - it is the one piece of this object the thread reads without the lock,
// which is what lets Close() join it before closing that descriptor.
m_accepting.store(true, std::memory_order_release);
try {
m_acceptor = std::thread(&GbmFrameChannel::AcceptLoop, this, fd);
} catch (...) {
// A thread that cannot be made is a phone that is out of them, not a reason to refuse
// the frames the container can still be given one at a time.
m_accepting.store(false, std::memory_order_release);
MGLOG_W_ONCE("gbm frame channel: the acceptor thread could not be started; a container is only taken in "
"when a frame is offered, and one that dials between frames waits for the next one");
}
MGLOG_I("gbm frame channel: listening on %s for one container (SOCK_SEQPACKET, one message per frame)", path);
return true;
}
Bool GbmFrameChannel::EnsureRelay() {
if (m_relay[0] >= 0 && m_relay[1] >= 0) return true;
// Both ends are dropped before a new pair is made: half a socketpair is a socket with bytes
// in it that nothing will ever read, and the next handle read from it would be the tail of
// the last one.
DropRelay();
Int pair[2] = {-1, -1};
if (::socketpair(AF_UNIX, SOCK_STREAM | SOCK_NONBLOCK | SOCK_CLOEXEC, 0, pair) != 0) {
MGLOG_E_ONCE("gbm frame channel: socketpair for the handle relay: %s; no frame can be offered until one "
"can be made",
std::strerror(errno));
return false;
}
m_relay[0] = pair[0];
m_relay[1] = pair[1];
return true;
}
void GbmFrameChannel::DropRelay() {
CloseQuietly(m_relay[0]);
CloseQuietly(m_relay[1]);
m_relay[0] = -1;
m_relay[1] = -1;
}
Bool GbmFrameChannel::RelayHandle(struct AHardwareBuffer* buffer, Uint8* payload, SizeT capacity, SizeT& payloadBytes,
Int* fds, Int& fdCount) {
payloadBytes = 0;
fdCount = 0;
if (!EnsureRelay()) return false;
// WHY A FRAME'S HANDLE GOES THROUGH A SOCKETPAIR OF THIS CHANNEL'S OWN.
//
// The container takes ONE message per frame - the offer, then the handle's counts, then the
// arrays those counts describe, with the descriptors in that same message's SCM_RIGHTS
// control data - and it refuses a message of any other length. Two sends cannot be one
// message on a message-oriented socket, so AHardwareBuffer_sendHandleToUnixSocket, which
// sends a handle as a message of its own, is pointed at a socketpair this channel owns, and
// what comes out of the other end is both halves of what the container wants: the handle's
// own bytes, read here, and its descriptors, as SCM_RIGHTS.
//
// The alternative does not exist: the NDK's <android/hardware_buffer.h> declares no way to
// ask a buffer for its descriptors. AHardwareBuffer_getNativeHandle is a platform API and
// is absent from the NDK's copy of that header (checked against NDK 27.3.13750724 in this
// tree's build-termux toolchain), so this is the one route from an AHardwareBuffer to a
// dma-buf descriptor that an app can take.
const Int code = AHardwareBuffer_sendHandleToUnixSocket(buffer, m_relay[0]);
if (code != 0) {
MGLOG_W_ONCE("gbm frame channel: the frame's handle did not cross the relay socket (rc %d, errno %d); the "
"frame is not offered to the container",
code, errno);
// The relay is dropped rather than kept: a send that failed part way through would
// leave bytes that the next handle's read would take for its own header.
DropRelay();
return false;
}
struct iovec vector = {};
vector.iov_base = payload;
vector.iov_len = capacity;
Uint8 control[CMSG_SPACE(sizeof(Int) * (SizeT)kMaxHandleFds)] = {};
struct msghdr message = {};
message.msg_iov = &vector;
message.msg_iovlen = 1;
message.msg_control = control;
message.msg_controllen = sizeof(control);
// MSG_DONTWAIT for the promise at the top of this file, and MSG_CMSG_CLOEXEC so a descriptor
// read out of the relay does not survive into a child of this process, which would then hold
// the phone's frame until it died.
ssize_t got = ::recvmsg(m_relay[1], &message, MSG_DONTWAIT | MSG_CMSG_CLOEXEC);
if (got < 0 && (errno == EAGAIN || errno == EWOULDBLOCK)) {
struct pollfd waiting = {};
waiting.fd = m_relay[1];
waiting.events = POLLIN;
if (::poll(&waiting, 1, kRelayWaitMs) > 0) {
// The kernel rewrites these on every call, so a retry starts from the same state as
// the first attempt.
message.msg_controllen = sizeof(control);
message.msg_flags = 0;
got = ::recvmsg(m_relay[1], &message, MSG_DONTWAIT | MSG_CMSG_CLOEXEC);
}
}
if (got < 0) {
MGLOG_W_ONCE("gbm frame channel: a relayed handle could not be read back (%d: %s); the frame is not "
"offered to the container",
errno, std::strerror(errno));
DropRelay();
return false;
}
if (got == 0) {
// Zero bytes on a connected socket is the end of it. Only this process holds either end
// of this socketpair, so this is a bug being reported rather than a peer going away.
MGLOG_W_ONCE("gbm frame channel: the handle relay is closed; the frame is not offered to the container");
DropRelay();
return false;
}
// The descriptors come out of the control data before anything is decided about the
// message, because they belong to this process from the moment they were received: a path
// that returns without closing them leaks a descriptor per frame.
Int collected = 0;
for (struct cmsghdr* header = CMSG_FIRSTHDR(&message); header != nullptr;
header = CMSG_NXTHDR(&message, header)) {
if (header->cmsg_level != SOL_SOCKET || header->cmsg_type != SCM_RIGHTS) continue;
const SizeT bytes = (SizeT)header->cmsg_len - CMSG_LEN(0);
const Int count = (Int)(bytes / sizeof(Int));
const Int* descriptors = reinterpret_cast<const Int*>(CMSG_DATA(header));
for (Int i = 0; i < count; ++i) {
if (collected < kMaxHandleFds) {
fds[collected++] = descriptors[i];
} else {
// More descriptors than a frame can carry: they are this process's now, so they
// are closed here rather than leaked.
CloseQuietly(descriptors[i]);
}
}
}
if ((message.msg_flags & MSG_CTRUNC) != 0) {
MGLOG_W_ONCE("gbm frame channel: a frame's control data did not fit in %zu bytes; the frame is not "
"offered because its descriptor list is incomplete",
sizeof(control));
for (Int i = 0; i < collected; ++i) CloseQuietly(fds[i]);
DropRelay();
return false;
}
if ((message.msg_flags & MSG_TRUNC) != 0 || (SizeT)got < sizeof(GbmNativeHandleHeader)) {
// A message longer than a handle can be, or shorter than the three counts every handle
// begins with. Either way it cannot describe a frame, and a relay that has been read
// past the end of one message must not carry the next frame's header: it is recreated.
MGLOG_W_ONCE("gbm frame channel: a relayed handle is %zd bytes and %s; the frame is not offered", got,
((message.msg_flags & MSG_TRUNC) != 0) ? "longer than a handle can be"
: "too short to hold its own counts");
for (Int i = 0; i < collected; ++i) CloseQuietly(fds[i]);
DropRelay();
return false;
}
// THE BYTES THAT COME BACK ARE THE HANDLE'S INTEGER ARRAY, NOT A handle AND ITS COUNTS.
// Measured on the phone: parsing the front of this payload as {version, numFds, numInts}
// produced a NumFds taken from the buffer's own integer data, and every frame was refused
// with "its handle carries more descriptors than either end takes" - which is what the
// container saw as a connection that was accepted and then closed without a frame. The two
// counts are known HERE and are not in those bytes: the descriptors came out of the control
// data (collected of them) and the payload is their integer array. So the header is BUILT
// rather than copied, and what leaves this process is a real native_handle_t layout -
// version, numFds, numInts, then the ints - which is exactly what the container's parser
// reads (GbmInternal.h's AHBNativeHandleHeader).
if (payloadBytes + sizeof(GbmNativeHandleHeader) > capacity) {
MGLOG_W_ONCE("gbm frame channel: a handle's integer array does not fit in a frame message with its "
"header; the frame is not offered to the container");
for (Int i = 0; i < collected; ++i) CloseQuietly(fds[i]);
DropRelay();
return false;
}
std::memmove(payload + sizeof(GbmNativeHandleHeader), payload, payloadBytes);
GbmNativeHandleHeader header = {};
header.Version = (Int32)sizeof(GbmNativeHandleHeader);
header.NumFds = (Int32)collected;
header.NumInts = (Int32)(payloadBytes / sizeof(Int32));
std::memcpy(payload, &header, sizeof(header));
payloadBytes += sizeof(header);
fdCount = collected;
return true;
}
// The acceptor. It touches the listener - its own copy of the descriptor, which nothing else
// closes while this loop runs - and, once per dialer, the channel under its lock.
void GbmFrameChannel::AcceptLoop(Int listen) {
while (m_accepting.load(std::memory_order_acquire)) {
struct pollfd waiting = {};
waiting.fd = listen;
waiting.events = POLLIN;
const Int ready = ::poll(&waiting, 1, kAcceptPollMs);
if (ready < 0) {
if (errno == EINTR) continue;
MGLOG_W_ONCE("gbm frame channel: poll on the listening socket failed (%d: %s); no container can be "
"taken in until the socket is opened again",
errno, std::strerror(errno));
return;
}
if (ready == 0) continue;
// accept4, so the connection is close-on-exec and non-blocking from the moment it
// exists: a container that stops reading must not be able to park a send on either
// thread.
const Int fd = ::accept4(listen, nullptr, nullptr, SOCK_CLOEXEC | SOCK_NONBLOCK);
if (fd < 0) {
if (errno == EINTR || errno == EAGAIN || errno == EWOULDBLOCK || errno == ECONNABORTED) continue;
MGLOG_W_ONCE("gbm frame channel: accept failed (%d: %s); no container can be taken in until the "
"socket is opened again",
errno, std::strerror(errno));
return;
}
const std::lock_guard<std::mutex> lock(m_mutex);
AdoptLocked(fd);
}
}
void GbmFrameChannel::AdoptLocked(Int fd) {
if (ClientAliveLocked()) {
// ONE CLIENT, which is what the protocol is written for, and a dialer that arrives while
// a live one is connected is closed rather than left connected - it learns it is not the
// one being served instead of holding a connection whose frames nobody reads.
CloseQuietly(fd);
MGLOG_W_ONCE("gbm frame channel: a second peer dialled %s while a container is connected; it is closed "
"and the frames stay with the connected one",
m_path.c_str());
return;
}
m_client = fd;
MGLOG_I("gbm frame channel: a container is connected on %s; every frame the host offers is sent to it as "
"the dma-buf descriptor behind it",
m_path.c_str());
// AND THE FRAME IT DIALED FOR GOES OUT FROM HERE. A compositor creates its GBM device before
// it asks for a surface, so the frame that is the draw target right now was offered before
// this connection existed; a container that is not told about it allocates every buffer of
// its new swapchain locally, and keeps them for the life of the process.
ReofferFrameLocked();
}
Bool GbmFrameChannel::ClientAliveLocked() {
if (m_client < 0) return false;
Uint8 peek = 0;
// MSG_PEEK, because a release waiting in the socket belongs to the render path: this test
// only asks whether the peer is still there, and a release it consumed would be a frame the
// channel believed was still outstanding.
const ssize_t got = ::recv(m_client, &peek, sizeof(peek), MSG_DONTWAIT | MSG_PEEK);
if (got > 0) return true;
if (got == 0) {
// Zero bytes on a connected socket is the end of it, whether the container exited or
// the kernel gave up on it. A compositor that crashed and is being restarted is
// exactly this, and its successor is the dialer standing right here.
MarkDown("the container closed the connection", 0);
return false;
}
if (errno == EAGAIN || errno == EWOULDBLOCK || errno == EINTR) return true;
MarkDown("recv", errno);
return false;
}
void GbmFrameChannel::MarkDown(const char* what, Int error) {
if (m_client < 0) return;
CloseQuietly(m_client);
m_client = -1;
if (error != 0) {
MGLOG_W("gbm frame channel: the container connection is down: %s failed (%d: %s); the frames are still "
"drawn and presented, and the container stops receiving them until it dials again",
what, error, std::strerror(error));
} else {
MGLOG_W("gbm frame channel: the container connection is down: %s; the frames are still drawn and "
"presented, and the container stops receiving them until it dials again",
what);
}
}
Bool GbmFrameChannel::OfferFrame(struct AHardwareBuffer* buffer, const HostFrameOffer& offer) {
if (buffer == nullptr) return false;
// Open() does nothing once the socket exists, so this is an integer test in the common case.
Open();
const std::lock_guard<std::mutex> lock(m_mutex);
// The releases the container has sent since the last frame, which is also how a container
// that died is noticed. Whoever replaced it was taken by the acceptor's own thread the
// moment it dialled: that thread is what makes a container's connect() succeed at all.
PollLocked();
// AND THE FRAME IS REMEMBERED BEFORE IT IS SENT. A container that dials while this call is
// running is one the acceptor hands the frame it finds here to, so the two threads must not
// be able to disagree about which frame is the one being drawn into.
const Uint32 seq = m_nextSeq;
RememberFrameLocked(buffer, offer, seq);
if (m_client < 0) return false;
return SendFrameLocked(buffer, offer, seq, /*counting=*/true);
}
void GbmFrameChannel::RememberFrameLocked(struct AHardwareBuffer* buffer, const HostFrameOffer& offer, Uint32 seq) {
if (m_frame == buffer) {
// The host redrawing into the buffer it already handed over: the same frame under a new
// sequence number. Acquiring it again would be a reference this channel takes and never
// gives back.
m_frameOffer = offer;
m_frameSeq = seq;
return;
}
// The reference is this channel's own, and it is what makes the frame a container that dials
// late is owed safe to hold: the backend drops its handle the moment the frame is presented,
// and a frame owed to a dialer arriving in the same millisecond may not be memory that has
// already gone back to the host's pool.
AHardwareBuffer_acquire(buffer);
ReleaseFrameLocked();
m_frame = buffer;
m_frameOffer = offer;
m_frameSeq = seq;
}
void GbmFrameChannel::ReleaseFrameLocked() {
if (m_frame == nullptr) return;
AHardwareBuffer_release(m_frame);
m_frame = nullptr;
m_frameOffer = {};
m_frameSeq = 0;
}
void GbmFrameChannel::DropFrame() {
const std::lock_guard<std::mutex> lock(m_mutex);
ReleaseFrameLocked();
}
void GbmFrameChannel::ReofferFrameLocked() {
if (m_frame == nullptr) return;
// The same frame, under the sequence number it was offered with: it IS the frame that is the
// draw target now, and a second number for it would be this channel claiming the host had
// handed over a frame it never handed over.
MGLOG_I("gbm frame channel: a container dialled after frame %u was offered; it is sent that frame, which is "
"still the draw target",
m_frameSeq);
SendFrameLocked(m_frame, m_frameOffer, m_frameSeq, /*counting=*/false);
}
Bool GbmFrameChannel::SendFrameLocked(struct AHardwareBuffer* buffer, const HostFrameOffer& offer, Uint32 seq,
Bool counting) {
if (m_client < 0) return false;
Uint8 payload[kMessageMax];
SizeT payloadBytes = 0;
Int fds[kMaxHandleFds];
for (Int i = 0; i < kMaxHandleFds; ++i) fds[i] = -1;
Int fdCount = 0;
if (!RelayHandle(buffer, payload, sizeof(payload), payloadBytes, fds, fdCount)) return false;
GbmNativeHandleHeader handle = {};
std::memcpy(&handle, payload, sizeof(handle));
const SizeT tail = ((SizeT)handle.NumFds + (SizeT)handle.NumInts) * sizeof(Int32);
const SizeT messageBytes = sizeof(GbmFrameOffer) + sizeof(GbmNativeHandleHeader) + tail;
// EVERY REASON THIS CHANNEL REFUSES A FRAME, IN ONE PLACE. Each of them is a frame the
// container would refuse anyway - it checks the same counts and the same geometry - and a
// frame that is refused here costs nothing: no message, no sequence number, and no entry in
// the count of frames waiting to be released.
const char* refusal = nullptr;
if (offer.Width == 0 || offer.Height == 0 || offer.StrideBytes == 0) {
refusal = "the host described it with a width, height or stride of zero, and a buffer with no size is "
"not one a compositor can render into";
} else if (handle.NumFds < 1) {
refusal = "its handle carries no descriptor, and a frame without a dma-buf is not one the container "
"can render into";
} else if (handle.NumFds > kMaxHandleFds) {
refusal = "its handle carries more descriptors than either end takes";
} else if (handle.NumInts < 0) {
refusal = "its handle claims a negative number of integers";
} else if ((SizeT)handle.NumInts > kMessageMax / sizeof(Int32)) {
// This is what keeps the message's length arithmetic from wrapping on a 32 bit ABI: a
// handle whose integer array alone is longer than a whole message cannot be carried by
// this protocol whatever the rest of it says, and the check below would otherwise be
// reading a number that had already turned into a small and plausible one.
refusal = "its handle names more integers than a whole message could carry";
} else if (fdCount < handle.NumFds) {
refusal = "fewer descriptors arrived with it than its handle names";
} else if (messageBytes > kMessageMax) {
refusal = "the message it makes is longer than the container reads";
}
Bool offered = false;
if (refusal != nullptr) {
// ONCE, not per frame: a host that describes every frame the same broken way must not
// turn this into a line per frame on the apply thread.
MGLOG_W_ONCE("gbm frame channel: frame %u (%ux%u) is not offered to the container: %s", offer.Index,
offer.Width, offer.Height, refusal);
} else {
// One message, built whole: the offer, then the handle's own three counts, then the two
// arrays the counts describe. What came back from the relay is copied in as far as it
// goes and the remainder is left zero, because the container checks the LENGTH it
// derives from those counts and never reads the arrays themselves - it takes the
// descriptors from the control data and hands the first one to GBM. So a handle whose
// bytes are shorter than its own counts imply is padded rather than refused, and one
// longer than they imply is cut to what the counts say; either way the length the
// container computes is the length it receives.
Uint8 message[kMessageMax] = {};
GbmFrameOffer out = {};
out.Magic = kGbmFrameOfferMagic;
out.Version = kGbmFrameVersion;
out.Seq = seq;
out.Index = offer.Index;
out.Width = offer.Width;
out.Height = offer.Height;
out.StrideBytes = offer.StrideBytes;
out.Format = offer.Format;
out.UsageLo = offer.UsageLo;
out.UsageHi = offer.UsageHi;
std::memcpy(message, &out, sizeof(out));
const SizeT handleBytes = (payloadBytes < sizeof(GbmNativeHandleHeader) + tail)
? payloadBytes
: (sizeof(GbmNativeHandleHeader) + tail);
std::memcpy(message + sizeof(out), payload, handleBytes);
struct iovec vector = {};
vector.iov_base = message;
vector.iov_len = messageBytes;
Uint8 control[CMSG_SPACE(sizeof(Int) * (SizeT)kMaxHandleFds)] = {};
struct msghdr outgoing = {};
outgoing.msg_iov = &vector;
outgoing.msg_iovlen = 1;
outgoing.msg_control = control;
outgoing.msg_controllen = CMSG_SPACE(sizeof(Int) * (SizeT)handle.NumFds);
struct cmsghdr* rights = CMSG_FIRSTHDR(&outgoing);
rights->cmsg_level = SOL_SOCKET;
rights->cmsg_type = SCM_RIGHTS;
rights->cmsg_len = CMSG_LEN(sizeof(Int) * (SizeT)handle.NumFds);
std::memcpy(CMSG_DATA(rights), fds, sizeof(Int) * (SizeT)handle.NumFds);
// MSG_DONTWAIT for the promise at the top of this file, and MSG_NOSIGNAL because a
// server killed by SIGPIPE when the container goes away takes the frames it was drawing
// with it. A full socket, a reset peer and a broken pipe all say the same thing here:
// this connection can no longer be trusted with a frame, so it is closed and the next
// container to dial is served.
const ssize_t sent = ::sendmsg(m_client, &outgoing, MSG_DONTWAIT | MSG_NOSIGNAL);
if (sent != (ssize_t)messageBytes) {
MarkDown("sendmsg", (sent < 0) ? errno : 0);
} else {
// A frame offered for the first time is the next sequence number and one more frame
// outstanding. The same frame sent again to a container that has just dialled is
// neither: the host handed over nothing new, and a count of frames waiting to be
// released may not be moved by a message that describes one already in it.
if (counting) {
m_nextSeq = seq + 1;
++m_offered;
++m_outstanding;
}
offered = true;
// The first offer is the one worth a line, and it carries the host's own numbers:
// the format in particular is the field the two ends could disagree about without
// either failing, so the value the host actually sends is put where a run on a
// device can be read afterwards.
MGLOG_I_ONCE("gbm frame channel: the first frame is offered to the container (seq %u index %u %ux%u "
"stride %u format 0x%08x)",
out.Seq, out.Index, out.Width, out.Height, out.StrideBytes, out.Format);
MGLOG_D("gbm frame channel: frame seq=%u index=%u offered (%zu bytes, %d descriptor(s), %llu "
"outstanding)",
out.Seq, out.Index, messageBytes, handle.NumFds, (unsigned long long)m_outstanding);
}
}
// The kernel took its own copies of these when the message was sent, and one that was not
// sent is not the container's to hold: every path closes what the relay handed over.
for (Int i = 0; i < fdCount; ++i) CloseQuietly(fds[i]);
return offered;
}
void GbmFrameChannel::Poll() {
const std::lock_guard<std::mutex> lock(m_mutex);
PollLocked();
}
void GbmFrameChannel::PollLocked() {
if (m_client < 0) return;
for (Int drained = 0; drained < kDrainMax; ++drained) {
GbmFrameRelease release = {};
struct iovec vector = {};
vector.iov_base = &release;
vector.iov_len = sizeof(release);
struct msghdr message = {};
message.msg_iov = &vector;
message.msg_iovlen = 1;
// recvmsg and not recv, for MSG_TRUNC: a message longer than a release can only be a
// peer speaking something else, and a release read out of the first twelve bytes of it
// would name a frame nobody released.
const ssize_t got = ::recvmsg(m_client, &message, MSG_DONTWAIT);
if (got < 0) {
if (errno == EINTR) continue;
// Nothing said, which is what a container that is between frames looks like.
if (errno == EAGAIN || errno == EWOULDBLOCK) return;
MarkDown("recvmsg", errno);
return;
}
if (got == 0) {
// Zero bytes on a connected socket is the end of it, whether the container exited or
// the kernel gave up on it. Its replacement is taken by the next frame.
MarkDown("the container closed the connection", 0);
return;
}
if ((message.msg_flags & MSG_TRUNC) != 0 || got != (ssize_t)sizeof(release)) {
// The message is skipped, not the connection: on a message-oriented socket a
// message too long for the buffer is consumed whole, so the next one is still a
// message rather than the tail of this one.
MGLOG_W_ONCE("gbm frame channel: the container sent a message that is not a %zu byte release; it is "
"skipped",
sizeof(release));
continue;
}
if (release.Magic != kGbmFrameReleaseMagic) {
MGLOG_W_ONCE("gbm frame channel: a message from the container begins with 0x%08x rather than 'MGGR'; "
"it is skipped",
release.Magic);
continue;
}
if (release.Version != kGbmFrameVersion) {
// Refused rather than acted on: the version is what says how the rest of the message
// is laid out, and a release read with the wrong layout names a frame the container
// did not mean.
MGLOG_E_ONCE("gbm frame channel: the container speaks protocol version %u where this server speaks "
"version %u; its releases are refused until the two agree",
release.Version, (Uint32)kGbmFrameVersion);
continue;
}
++m_released;
if (m_outstanding > 0) --m_outstanding;
// The first release is the only one worth a line: it is the proof that the container
// took the descriptor and its compositor retired the frame, where every later one says
// the same thing sixty times a second.
MGLOG_I_ONCE("gbm frame channel: the container is releasing frames (first: seq %u)", release.Seq);
}
// Anything past this cap stays in the socket, whose buffer the kernel bounds, and goes out
// with the next frame: a peer that says nothing but releases may not spend the apply thread
// here.
}
void GbmFrameChannel::Close() {
// THE ACCEPTOR IS STOPPED AND JOINED FIRST, and outside the lock. It may be inside that
// lock when this is called - a teardown that waited for it while holding it would wait for
// ever - and it polls the listening descriptor, which may not be closed under it: the next
// open() in this process hands out the descriptor number a moment later, and the thread
// would then be polling somebody else's socket.
m_accepting.store(false, std::memory_order_release);
if (m_acceptor.joinable()) m_acceptor.join();
const std::lock_guard<std::mutex> lock(m_mutex);
// The frame is this channel's reference and is released with it: the backend has already
// dropped its own by the time a teardown here is a teardown of the frame as well.
ReleaseFrameLocked();
// The connection is closed quietly rather than marked down: this is a teardown, not a
// failure, and a warning about it would be noise in a log read for the failures.
CloseQuietly(m_client);
m_client = -1;
DropRelay();
if (m_listen >= 0) {
// The node is this channel's to remove only while it still IS this channel's socket: a
// server that was restarted has bound the same path with a socket of its own, and a
// teardown that unlinked it would take the successor's node away with it. st_dev and
// st_ino against the listening descriptor is the cheapest way to ask, and a check that
// fails only leaves a name behind that the next Open() unlinks anyway.
struct stat node = {};
struct stat socket = {};
if (!m_path.empty() && ::stat(m_path.c_str(), &node) == 0 && ::fstat(m_listen, &socket) == 0 &&
node.st_dev == socket.st_dev && node.st_ino == socket.st_ino) {
::unlink(m_path.c_str());
}
CloseQuietly(m_listen);
m_listen = -1;
}
m_path.clear();
// The counters are history and stay: a caller that logs Outstanding() after a teardown is
// asking what happened, and IsUp() is what answers what is connected now.
}
}
#else // !(MOBILEGL_BUILD_DISAGGREGATED && __ANDROID__)
namespace MobileGL::MG_Backend {
// A build that is not the Android render server has no AHardwareBuffer to offer and no
// container beside it. The class exists so that callers do not have to be compiled
// differently, and every entry point answers the way an absent container does.
GbmFrameChannel::~GbmFrameChannel() = default;
Bool GbmFrameChannel::Open() { return false; }
Bool GbmFrameChannel::OfferFrame(struct AHardwareBuffer*, const HostFrameOffer&) { return false; }
void GbmFrameChannel::Poll() {}
void GbmFrameChannel::Close() {}
}
#endif
// End of Source File Header
MobileGL/MG_Backend/GbmFrameChannel.h
-281
View File
@@ -1,281 +0,0 @@
// MobileGL - MobileGL/MG_Backend/GbmFrameChannel.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 "HostFrameBridge.h"
struct AHardwareBuffer;
namespace MobileGL::MG_Backend {
// THE FRAME THE HOST HANDED OVER, HANDED ON TO THE CONTAINER AS A dma-buf.
//
// The display host owns a pool of AHardwareBuffers: it allocates them, this side imports the
// one it offers as a draw target (HostFrameBridge, DirectGLES::HostFrameTarget), and the host
// puts it on the glass when this side answers that it is drawn. The Wayland compositor in the
// Linux container has to render into THOSE SAME frames - it runs this project's own GBM, and a
// gbm_bo_create there answers with the phone's frame instead of a dma-heap allocation of its
// own - so every frame this side takes has to reach the container as that frame's dma-buf
// descriptor. That, and the release that comes back, is all this channel carries.
//
// The container's end is MobileGL/MG_Gbm/GbmHostChannel.cpp. It reads exactly the bytes
// declared below and answers with a release once its compositor no longer reads the frame.
// The three shapes ARE that file's GbmFrameOffer/GbmFrameRelease and GbmInternal.h's
// AHBNativeHandleHeader, field for field and packing included. They are restated here rather
// than shared because the two ends are built into different libraries from different build
// configurations: MG_Backend is the Android render server and never sees libgbm's headers,
// while MG_Gbm is built for the container and never sees Android's. A change on either side
// is a protocol change, and the magic is what makes a mismatched pair fail loudly instead of
// being read as plausible numbers.
//
// ONE MESSAGE PER FRAME, on SOCK_SEQPACKET, and that is part of the protocol rather than an
// implementation detail: an offer and its handle only mean anything together, and the message
// boundary is what lets the reader take the two as one thing. The container derives the
// length of the message it expects from the handle's own two counts and refuses any other
// length, so this end sends the offer immediately followed by the handle's counts and its two
// arrays, with the descriptors in the SCM_RIGHTS control data of that same sendmsg.
//
// The channel is OPTIONAL, and that is the rule the implementation is built around: a
// container that is not running, has died, or has stopped reading may cost the render path a
// syscall or two, and may never block it, fail it, or grow without bound. Every entry point
// below is non-blocking and answers silence with silence.
inline constexpr Uint32 kGbmFrameOfferMagic = 0x4647474Du; // 'M','G','G','F' in memory order
inline constexpr Uint32 kGbmFrameReleaseMagic = 0x5247474Du; // 'M','G','G','R' in memory order
inline constexpr Uint32 kGbmFrameVersion = 1u;
// WHERE THE CONTAINER DIALS. /data/local/tmp is the one directory both halves of a split run
// can be pointed at on a device, and the default lives on this end because this end is the
// server. The container's compiled-in default is /run/mobilegl-gbm.sock - the same protocol
// with the path each side can reach unaided - so a deployment that puts the two in different
// mount namespaces sets MOBILEGL_GBM_SOCKET on both; it is read here and in
// GbmHostChannelCreate, from the same variable, for that reason.
inline constexpr const char* kGbmFrameSocketPath = "/data/local/tmp/mobilegl-gbm.sock";
inline constexpr const char* kGbmFrameSocketEnv = "MOBILEGL_GBM_SOCKET";
// One frame the host offered, described for the container. Width, Height, StrideBytes and
// Format are the host's own numbers for the frame (HostFrameOffer), carried through
// unchanged: they describe the memory the descriptor points at, and this end is not the place
// where a number the other two ends agreed on gets rewritten.
struct GbmFrameOffer {
Uint32 Magic;
Uint32 Version;
Uint32 Seq; // this channel's, one per frame offered
Uint32 Index; // the host's own buffer index, echoed so the phone can match a frame
Uint32 Width;
Uint32 Height;
Uint32 StrideBytes;
Uint32 Format;
Uint32 UsageLo;
Uint32 UsageHi;
} __attribute__((packed));
// What the container says once it is done with a frame. It may arrive late, it may never
// arrive, and both are cheap here: the channel keeps a count and no per-frame record (see
// Outstanding below), so nothing is leaked and nothing grows when one is missed.
struct GbmFrameRelease {
Uint32 Magic;
Uint32 Version;
Uint32 Seq;
} __attribute__((packed));
// THE OTHER DIRECTION: A dma-buf THE CONTAINER WANTS THIS SIDE TO BACK A TEXTURE WITH.
//
// The compositor's scene reaches the display daemon's dma-bufs through glEGLImageTargetTexture2DOES
// (MG_Impl/GLImpl/Exporting/Definitions.cpp, MG_Backend/DirectGLES/BackendObject_DirectGLES.cpp both
// name this half as the next change). eglCreateImageKHR has already held a dup() of every plane's
// descriptor since the image was made; what was missing is the render server's half - telling THIS
// side which texture that dma-buf backs, over the one channel that can carry a descriptor across the
// container boundary. This message is that half: the client names the texture target and the
// texture's own name, describes the buffer exactly as drmModeAddFB2 would, and the plane descriptors
// ride in the SCM_RIGHTS control data of the same sendmsg. One message per import, as SEQPACKET
// requires, so a descriptor and its description are never read apart.
//
// The reply is what the client waits for before a framebuffer is allowed to be complete over the
// texture: Ok=0 means this side could not make the import real, and the client keeps treating the
// texture as having no storage rather than letting it render into nothing.
inline constexpr Uint32 kGbmImportRequestMagic = 0x4947474Du; // 'M','G','G','I' in memory order
inline constexpr Uint32 kGbmImportReplyMagic = 0x52474749u; // 'I','G','G','R' in memory order
inline constexpr Uint32 kGbmImportVersion = 1u;
inline constexpr Uint32 kGbmImportMaxPlanes = 4u;
struct GbmImportRequest {
Uint32 Magic;
Uint32 Version;
Uint32 Target; // the GL texture target the image was bound to (0x8D65 = GL_TEXTURE_EXTERNAL_OES)
Uint32 TexName; // the CLIENT's texture name; this side resolves its twin
Uint32 Width;
Uint32 Height;
Uint32 FourCC;
Uint32 PlaneCount; // 1..kGbmImportMaxPlanes; the descriptors are the message's control data
Int32 Stride[kGbmImportMaxPlanes];
Int32 Offset[kGbmImportMaxPlanes];
Uint64 Modifier[kGbmImportMaxPlanes];
Uint32 HasModifier[kGbmImportMaxPlanes];
} __attribute__((packed));
struct GbmImportReply {
Uint32 Magic;
Uint32 Version;
Uint32 Ok;
Uint32 Reserved;
} __attribute__((packed));
// An AHardwareBuffer native handle as it appears on the wire: the platform's native_handle_t
// (version, then the two counts, then the descriptor array followed by the integer array),
// written by AHardwareBuffer_sendHandleToUnixSocket and read by the container's
// AHBNativeHandleHeader. The counts are 32 bit on every Android ABI, which is why they are
// spelled out here rather than taken from a platform header this library cannot include.
struct GbmNativeHandleHeader {
Int32 Version;
Int32 NumFds;
Int32 NumInts;
} __attribute__((packed));
// ONE CONTAINER, ONE LISTENING SOCKET, TWO THREADS: the render path's, and an acceptor's.
//
// A compositor dials ONCE - when it creates its GBM device - and keeps that connection for the
// life of the process, while this side offers a frame per drawn frame. An accept that only ran
// inside OfferFrame therefore ran after the dial it was supposed to answer, and a dialer that
// nobody took kept the listener's queue full for every later one. That is measured on the
// phone rather than argued: with accept() only on the offer path, connect() from the container
// answered EAGAIN(11) on four attempts out of four while the node sat there listening.
//
// So the accept has a thread of its own, started by Open() and stopped by Close(), and it
// adopts what it takes on the spot - including sending it the frame the host last handed over,
// because a compositor's first allocation is the one its swapchain is built from. The
// connected socket, the frame that is remembered, the relay and the counters are shared between
// the two threads and guarded by the one mutex below; both entry points are non-blocking, so
// neither thread can park the other for longer than a syscall.
class GbmFrameChannel {
public:
GbmFrameChannel() = default;
GbmFrameChannel(const GbmFrameChannel&) = delete;
GbmFrameChannel& operator=(const GbmFrameChannel&) = delete;
~GbmFrameChannel();
// Creates the listening socket if it is not there yet and starts the acceptor, and does
// nothing otherwise. It never waits for a container: the socket is bound, a backlog is
// given to listen(), and the acceptor takes whoever dials from then on - whether or not a
// frame is being drawn. A caller that wants the container to find the socket before the
// first frame - the container dials once at its own device creation and retries about once
// a second - can call this when the host-framed surface is initialized, beside
// HostFrameBridge::Open.
Bool Open();
// Offers one frame the host just handed over, as the dma-buf descriptor behind it.
// False means the frame did not go out, for any of the reasons this channel treats as
// ordinary: no container is connected, the container just died, or the frame could not be
// described. None of them is the caller's problem and none of them is fatal - the frame
// is drawn and presented exactly as it would have been without a channel at all.
Bool OfferFrame(struct AHardwareBuffer* buffer, const HostFrameOffer& offer);
// Reads whatever the container has said since the last call and marks the channel down if
// the connection has ended. OfferFrame already does this once per frame, so a caller only
// needs it if it wants releases drained on a path that has no new frame in it.
void Poll();
// The frame the host handed over is gone - it was presented, or it was replaced - and this
// channel may no longer hold it or offer it to anybody. THE CHANNEL ITSELF STAYS OPEN, and
// that is the point of the call: the listening socket, its node and the container's
// connection outlive every frame, and a channel that was closed and reopened per frame took
// the node away sixty times a second - a container dialling at the wrong moment got ENOENT
// for a socket that was there a millisecond earlier and would be there a millisecond later.
void DropFrame();
// True while a container is connected and the frames are being offered to it.
Bool IsUp() const {
const std::lock_guard<std::mutex> lock(m_mutex);
return m_client >= 0;
}
// How many frames have been offered and not released, as a count of messages and not a
// record of them. It is here to be logged, and it is deliberately the only per-frame state
// the channel keeps: a release that never arrives costs a number that is too high, and
// nothing else, which is what makes a container that stops reading harmless.
Uint64 Outstanding() const {
const std::lock_guard<std::mutex> lock(m_mutex);
return m_outstanding;
}
// Closes the connection, the listening socket and the node it created. Idempotent, safe
// from a destructor, and safe to call while a container is connected: the container sees
// the connection end and goes back to allocating its frames locally, which is the state it
// starts in.
void Close();
private:
// The socketpair a frame's handle is handed to and read back from. Recreated on demand,
// because the one call the NDK offers for a buffer's descriptors sends them as a message
// of its own and the container takes one message per frame - see the note in the .cpp.
Bool EnsureRelay();
void DropRelay();
Bool RelayHandle(struct AHardwareBuffer* buffer, Uint8* payload, SizeT capacity, SizeT& payloadBytes,
Int* fds, Int& fdCount);
// Takes the one container the protocol allows, and closes anyone else who dials while a
// LIVE one is connected rather than leaving them to believe they are being served. A
// connection whose peer has exited is not a live one: it is closed here and its dialer's
// replacement is taken, which is what a compositor that crashed and was restarted is.
void AdoptLocked(Int fd);
// True while the connected container is still there. recvmsg with MSG_PEEK is what asks:
// zero bytes is the peer's close, EAGAIN is a peer that is between frames, and a release
// waiting in the socket is a peer that is alive - peeked at rather than read, because the
// render path is the one that spends releases.
Bool ClientAliveLocked();
// Takes the one container the protocol allows out of whoever dialled.
void AcceptLoop(Int listen);
// Sends the frame that is the draw target to a container that has just connected.
void ReofferFrameLocked();
// Remembers the frame the host last handed over, holding a reference to it so that a
// container which dials after the offer can still be given it. The previous one is
// released here; nothing else in the channel holds a frame.
void RememberFrameLocked(struct AHardwareBuffer* buffer, const HostFrameOffer& offer, Uint32 seq);
void ReleaseFrameLocked();
// The offer itself: the handle relayed out of the buffer, the message built, one sendmsg.
// A frame that has already been offered once is sent again with the sequence number it was
// offered under and does not move the counters, because it is the same frame and not a new
// one.
Bool SendFrameLocked(struct AHardwareBuffer* buffer, const HostFrameOffer& offer, Uint32 seq, Bool counting);
// The body of Poll(), for a caller that is already holding the lock.
void PollLocked();
// Closes the connection and says why, once. The channel stays open for the next container.
void MarkDown(const char* what, Int error);
Int m_listen = -1;
Int m_client = -1;
Int m_relay[2] = {-1, -1};
String m_path;
// Bumped only for a frame that actually went out, so a sequence number is never reused and
// a release can never be read as belonging to a frame of an earlier connection.
Uint32 m_nextSeq = 0;
Uint64 m_offered = 0;
Uint64 m_released = 0;
Uint64 m_outstanding = 0;
// The frame the host handed over most recently, held by this channel's own reference for as
// long as it is the draw target: it is what a container that dials late is sent.
struct AHardwareBuffer* m_frame = nullptr;
HostFrameOffer m_frameOffer = {};
Uint32 m_frameSeq = 0;
// The acceptor, and the flag that ends it. The listening descriptor is handed to the thread
// as its own copy, so it is the only thing in here that thread reads without the lock - and
// Close() joins the thread before it closes that descriptor.
std::thread m_acceptor;
std::atomic<Bool> m_accepting{false};
// Guards every member above, from both threads. Mutable because the two const questions a
// caller asks about the channel - is a container connected, how many frames are outstanding
// - are answers that have to be read under it.
mutable std::mutex m_mutex;
};
}
MobileGL/MG_Backend/HostFrameBridge.cpp
-189
View File
@@ -1,189 +0,0 @@
// MobileGL - MobileGL/MG_Backend/HostFrameBridge.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
#include "HostFrameBridge.h"
#if MOBILEGL_BUILD_DISAGGREGATED && defined(__ANDROID__)
#include <android/hardware_buffer.h>
#include <cerrno>
#include <cstring>
#include <poll.h>
#include <sys/socket.h>
#include <sys/un.h>
#include <unistd.h>
namespace MobileGL::MG_Backend {
namespace {
Bool ReadExactly(Int fd, void* out, SizeT n) {
Uint8* at = static_cast<Uint8*>(out);
while (n > 0) {
const ssize_t got = ::read(fd, at, n);
if (got <= 0) {
if (got < 0 && errno == EINTR) continue;
return false;
}
at += got;
n -= static_cast<SizeT>(got);
}
return true;
}
Bool WriteExactly(Int fd, const void* in, SizeT n) {
const Uint8* at = static_cast<const Uint8*>(in);
while (n > 0) {
const ssize_t put = ::write(fd, at, n);
if (put <= 0) {
if (put < 0 && errno == EINTR) continue;
return false;
}
at += put;
n -= static_cast<SizeT>(put);
}
return true;
}
}
HostFrameBridge::~HostFrameBridge() { Close(); }
Bool HostFrameBridge::Open(const char* path, Int acceptTimeoutMs, String& why) {
Close();
const char* name = (path != nullptr && path[0] != 0) ? path : kHostFrameSocket;
m_listen = ::socket(AF_UNIX, SOCK_STREAM, 0);
if (m_listen < 0) {
why = std::format("socket(AF_UNIX): {}", std::strerror(errno));
return false;
}
sockaddr_un address{};
address.sun_family = AF_UNIX;
if (std::strlen(name) >= sizeof(address.sun_path)) {
why = std::format("the socket name is longer than the kernel takes: {}", name);
Close();
return false;
}
// "@name" is the abstract namespace: sun_path[0] is NUL and the name follows it.
// Nothing is created on disk, so nothing is left behind and no file permission stands
// between two apps that may not write each other's directories.
if (name[0] == '@') {
address.sun_path[0] = 0;
std::strncpy(address.sun_path + 1, name + 1, sizeof(address.sun_path) - 2);
} else {
std::strncpy(address.sun_path, name, sizeof(address.sun_path) - 1);
// A leftover socket file from a server that died is not a reason to refuse the host.
::unlink(name);
}
if (::bind(m_listen, reinterpret_cast<sockaddr*>(&address), sizeof(address)) != 0) {
why = std::format("bind({}): {}", name, std::strerror(errno));
Close();
return false;
}
if (::listen(m_listen, 1) != 0) {
why = std::format("listen({}): {}", name, std::strerror(errno));
Close();
return false;
}
pollfd waiting{};
waiting.fd = m_listen;
waiting.events = POLLIN;
const Int ready = ::poll(&waiting, 1, acceptTimeoutMs);
if (ready <= 0) {
why = (ready == 0) ? std::format("no display host dialled {} within {} ms", name, acceptTimeoutMs)
: std::format("poll({}): {}", name, std::strerror(errno));
Close();
return false;
}
m_fd = ::accept(m_listen, nullptr, nullptr);
if (m_fd < 0) {
why = std::format("accept({}): {}", name, std::strerror(errno));
Close();
return false;
}
MGLOG_I("host frame bridge: a display host is on %s", name);
return true;
}
Bool HostFrameBridge::Acquire(struct AHardwareBuffer** buffer, HostFrameOffer& offer, String& why) {
*buffer = nullptr;
offer = HostFrameOffer{};
if (m_fd < 0) {
why = "the bridge is not open";
return false;
}
AHardwareBuffer* received = nullptr;
if (AHardwareBuffer_recvHandleFromUnixSocket(m_fd, &received) != 0 || received == nullptr) {
why = "the host stopped offering frames, or the handle did not cross";
return false;
}
if (!ReadExactly(m_fd, &offer, sizeof(offer)) || offer.Magic != kHostFrameMagic) {
// The handle is already this side's by the time this fails, so it goes back before
// the failure does: a reference held past the connection starves the host's pool.
AHardwareBuffer_release(received);
why = std::format("the frame's description did not follow its handle (magic 0x{:08x})", offer.Magic);
return false;
}
*buffer = received;
return true;
}
Bool HostFrameBridge::Complete(const HostFrameOffer& offer, Bool imported, Bool drawn, Bool fenceOk, String& why) {
if (m_fd < 0) {
why = "the bridge is not open";
return false;
}
HostFrameAck ack{};
ack.Magic = kHostFrameMagic;
ack.Version = kHostFrameVersion;
ack.Index = offer.Index;
ack.Imported = imported ? 1u : 0u;
ack.Drawn = drawn ? 1u : 0u;
ack.FenceOk = fenceOk ? 1u : 0u;
if (!WriteExactly(m_fd, &ack, sizeof(ack))) {
why = std::format("the answer to frame {} did not go out: {}", offer.Index, std::strerror(errno));
return false;
}
// The host answers with its own view of the pixels. It is what closes the round trip, so
// it is read here and kept rather than left in the socket for the next frame to trip over.
m_lastSeen = HostFrameSeen{};
if (!ReadExactly(m_fd, &m_lastSeen, sizeof(m_lastSeen)) || m_lastSeen.Magic != kHostFrameMagic) {
why = std::format("frame {} was answered but the host's readback did not arrive", offer.Index);
m_lastSeen = HostFrameSeen{};
return false;
}
return true;
}
void HostFrameBridge::Close() {
if (m_fd >= 0) ::close(m_fd);
if (m_listen >= 0) ::close(m_listen);
m_fd = -1;
m_listen = -1;
}
}
#else // !(MOBILEGL_BUILD_DISAGGREGATED && __ANDROID__)
namespace MobileGL::MG_Backend {
HostFrameBridge::~HostFrameBridge() = default;
Bool HostFrameBridge::Open(const char*, Int, String& why) {
why = "host frames are a disaggregated Android path";
return false;
}
Bool HostFrameBridge::Acquire(struct AHardwareBuffer**, HostFrameOffer&, String& why) {
why = "host frames are a disaggregated Android path";
return false;
}
Bool HostFrameBridge::Complete(const HostFrameOffer&, Bool, Bool, Bool, String& why) {
why = "host frames are a disaggregated Android path";
return false;
}
void HostFrameBridge::Close() {}
}
#endif
MobileGL/MG_Backend/HostFrameBridge.h
-103
View File
@@ -1,103 +0,0 @@
// MobileGL - MobileGL/MG_Backend/HostFrameBridge.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>
struct AHardwareBuffer;
namespace MobileGL::MG_Backend {
// THE DISPLAY HOST'S FRAMES, AS THEY ARRIVE.
//
// The Android side that owns the screen allocates its frames itself and offers each one over
// an AF_UNIX socket: the handle travels ahead of a fixed-size description on the same
// connection, and the host then waits for this side to say the frame is drawn before it puts
// it on the glass. Why the host allocates rather than this side asking for the display's own
// buffers is measured, not chosen: AHardwareBuffer_createFromHandle accepts an
// AHardwareBuffer this process allocated and refuses one the display queue handed over
// (gralloc BAD_VALUE), so the only frames a render server can draw into are the ones the host
// made for it.
//
// The three message shapes below ARE the host's (its ahb_bridge.h), field for field and
// packing included. They are restated here rather than shared because the two ends are built
// by different projects; a change on either side is a protocol change, and the magic is what
// makes a mismatched pair fail loudly instead of being read as plausible numbers.
inline constexpr Uint32 kHostFrameMagic = 0x4D474C41u; // the host spells it "ALGM" in memory
inline constexpr Uint32 kHostFrameVersion = 1u;
// AN ABSTRACT NAME, not a path: the two ends are separate apps, and neither may create a
// socket file in /data/local/tmp (its directory grants others traverse only). An abstract
// name lives in the kernel namespace instead of the filesystem, so there is no file
// permission to get wrong - the same reason this project names its own endpoints @mgl-*.
inline constexpr const char* kHostFrameSocket = "@mobilegl-host-frame";
struct HostFrameOffer {
Uint32 Magic;
Uint32 Version;
Uint32 Index;
Uint32 Width;
Uint32 Height;
Uint32 StrideBytes;
Uint32 Format;
Uint32 UsageLo;
Uint32 UsageHi;
char Note[64];
} __attribute__((packed));
struct HostFrameAck {
Uint32 Magic;
Uint32 Version;
Uint32 Index;
Uint32 Imported;
Uint32 Drawn;
Uint32 FenceOk;
Uint8 Color[4];
char Note[64];
} __attribute__((packed));
struct HostFrameSeen {
Uint32 Magic;
Uint32 Version;
Uint32 Index;
Uint32 Locked;
Uint8 Observed[4];
Uint8 ObservedCorner[4];
char Note[64];
} __attribute__((packed));
// One host connection at a time, which is what the host offers: it dials, hands over a frame,
// waits for the answer, and hands over the next.
class HostFrameBridge {
public:
HostFrameBridge() = default;
HostFrameBridge(const HostFrameBridge&) = delete;
HostFrameBridge& operator=(const HostFrameBridge&) = delete;
~HostFrameBridge();
// Listens on `path` (the well-known name by default) and waits for the host. A host that
// never dials is answered with false and a reason, never an abort.
Bool Open(const char* path, Int acceptTimeoutMs, String& why);
// Takes the next frame. Ownership of the returned AHardwareBuffer is the caller's, who
// must hand it back through ReleaseOwned() once the frame is off the glass.
Bool Acquire(struct AHardwareBuffer** buffer, HostFrameOffer& offer, String& why);
// Tells the host what became of the frame it offered, and reads back what the host's own
// view of the pixels holds. `drawn` is what the host waits for before it presents.
Bool Complete(const HostFrameOffer& offer, Bool imported, Bool drawn, Bool fenceOk, String& why);
// The readback the host returned for the last completed frame, as the host reported it.
const HostFrameSeen& LastSeen() const { return m_lastSeen; }
void Close();
private:
Int m_fd = -1;
Int m_listen = -1;
HostFrameSeen m_lastSeen{};
};
}
MobileGL/MG_Backend/Init.cpp
-390
View File
@@ -11,29 +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_Pipe/PipeMutation.h> // MGPipeForgetAllPublications, at the end of ShutdownSplitRoles
#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) {
@@ -68,376 +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 its wire resource op table off monolith only
// (VkBufferManager::RegisterWireResourceOps, VkBufferManager.cpp): under a transport it
// owns buffer stores and claims bit 7 (the P4a mask, see ConsumedSubsystemsFor below);
// under monolith it registers none and its buffers keep the legacy BufferBackendOps path.
// 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, kCapNeedsHostUboBytes and kCapViewportArray are RESERVED
// (P8-F) and never set here: the first two are the only things that ask for an
// MGHostSpan, and 0 keeps every one of them off the wire (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();
// The server's twins died with the session; the frontend objects that are destroyed after
// this (the GL context's) have nothing left on the other side to delete.
MG_Pipe::MGPipeForgetAllPublications();
}
#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
-715
View File
@@ -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
MobileGL/MG_Backend/MGPipe/PipeInputs.h
-1068
View File
File diff suppressed because it is too large Load Diff
MobileGL/MG_Backend/ServerRole.h
-45
View File
@@ -1,45 +0,0 @@
// MobileGL - MobileGL/MG_Backend/ServerRole.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
// The server role's bring-up, as one entry point two shapes share.
//
// Steps 1 and 2 of Init.cpp's split bring-up - the server's private
// BackendObject, and the two CallMask halves computed from THAT backend's own
// function table. Under `inproc` InitSplitRoles calls it and then starts the
// client in the same process; under `spawn` the child's ServerMain calls it and
// then accepts a connection instead.
//
// ONE ENTRY POINT, not two, because the capability bits are a statement about
// the server's backend and only the server can compute them. A second copy in
// ServerMain would be a second answer to "does this backend own the XFB
// capture", diverging silently the first time a backend registers a slot.
#pragma once
#include <Includes.h>
// DECLARED ONLY IN A DISAGGREGATED BUILD. G1 requires the pull build's symbol
// set and .text to be byte-identical, and a definition guarded only on the
// inside still emits a symbol - measured, not assumed.
#if MOBILEGL_BUILD_DISAGGREGATED
namespace MobileGL::MG_Backend {
// Creates the server's BackendObject and publishes the consumed-subsystem
// mask and the capability bits onto ServerSessionInstance(). Does NOT create
// an EGL context: that happens later, on the apply thread, when the client's
// first eglMakeCurrent crosses as a blocking control request.
//
// Returns false when the backend could not be created, and the caller must
// then REFUSE TO CONTINUE rather than fall back - a server process that came
// up without a backend would accept a session it can never apply.
Bool InitServerRoleForSpawn();
} // namespace MobileGL::MG_Backend
#endif // MOBILEGL_BUILD_DISAGGREGATED
MobileGL/MG_Benchmark/Driver/CMakeLists.txt
+1 -47
View File
@@ -11,51 +11,5 @@ endif()
add_executable(DriverBench DriverBench.c)
target_link_libraries(DriverBench PRIVATE dl)
# WHY EVERY ENTRY HERE CARRIES A PASS_REGULAR_EXPRESSION.
#
# DriverBench prints one CSV row per case it ran and exits 0 whatever it ran. Before this, a ctest
# entry naming a case therefore could not answer the only question it exists to ask: an argument
# matching nothing in kBenchCases selected no case, printed only the header row, and still exited
# 0. DriverBench.c now refuses an unknown case name (exit 2), which closes it at the source - but
# the entry must be able to go red for the reason it exists WITHOUT depending on that check
# staying in the binary, so each entry also requires the case's own output row to appear.
#
# The regex is what a healthy run of that case prints and nothing else does: the case name at the
# start of a line, then the frames / ops-per-frame / median-ms / ns-per-op / fps columns
# (run_case()). A rename, a drop from kBenchCases, a boot_egl() failure or
# a crash part-way through the case all remove that row and turn the entry red.
#
# Note that a PASS_REGULAR_EXPRESSION makes ctest ignore the process exit code (cmCTestRunTest:
# success is `retVal == 0 || !RequiredRegularExpressions.empty()`), which is why the row itself
# has to be the evidence rather than a companion to the rc.
add_test(NAME DriverBench COMMAND DriverBench draw_tiny)
# draw_tiny's a/ops scale with $DRIVERBENCH_DRAWS (main()), so only the shape of
# the row is pinned here, not the column values.
set_tests_properties(DriverBench PROPERTIES
LABELS benchmark
PASS_REGULAR_EXPRESSION "(^|\n)draw_tiny,[0-9]+,[0-9]+,[0-9.]+,[0-9.]+,[0-9.]+")
# The Blaze3D blend toggle, as its own entry.
#
# mc_state_toggle is glEnable(GL_BLEND) / glBlendFuncSeparate / glDrawElements /
# glDisable(GL_BLEND) / glDrawElements, 46 times - the measured vanilla-frame rate, and the exact
# shape ROADMAP.md writes down as the microbenchmark P2 owes the GO/NO-GO. It is the workload the
# whole "push at validate, not in the setter" decision was made for: a per-setter design pays for
# every toggle, and a CSO that is minted twice and then reused pays for none of them.
#
# The case has existed in kBenchCases since P0 and nothing ran it, so nothing noticed if it broke.
# Exposing it costs about 1.2 s inside an existing three-minute job, and it means the number the
# P2 report quotes comes from a case CI has been executing all along rather than from a code path
# whose first run is the day it is measured.
#
# Like the entry above, this runs against whatever $DRIVERBENCH_EGL_LIB names (the system driver
# when unset) - the ctest entry is a "does this case still run" gate, not the measurement. The
# measurement is run_driver_bench.sh against each of {native, espryt, magma}.
add_test(NAME DriverBenchStateToggle COMMAND DriverBench mc_state_toggle)
# The ops-per-frame column is pinned to 46 here, unlike the entry above: the mc_* cases are
# excluded from the $DRIVERBENCH_DRAWS scaling on purpose ("the mc_* rates are measured and must
# not move, or the numbers stop being comparable", main()), so 46 toggles per frame
# is part of what "this case still runs" means. Change the workload and this entry says so.
set_tests_properties(DriverBenchStateToggle PROPERTIES
LABELS benchmark
PASS_REGULAR_EXPRESSION "(^|\n)mc_state_toggle,[0-9]+,46,[0-9.]+,[0-9.]+,[0-9.]+")
set_tests_properties(DriverBench PROPERTIES LABELS benchmark)
MobileGL/MG_Benchmark/Driver/DriverBench.c
-22
View File
@@ -476,28 +476,6 @@ int main(int argc, char** argv) {
if (getenv("DRIVERBENCH_FRAMES")) g_frames = atoi(getenv("DRIVERBENCH_FRAMES"));
if (getenv("DRIVERBENCH_SPRITES")) g_mixSprites = atol(getenv("DRIVERBENCH_SPRITES"));
/* A requested case name that matches nothing used to select nothing, print the header row and
* exit 0 - so a caller that names a case (run_driver_bench.sh, and the two ctest entries in
* CMakeLists.txt) could not tell "the case ran" from "the case has been renamed or deleted".
* Refuse it here, before any GL work, so the refusal reaches a caller that has no display
* either, and name what does exist so the fix is obvious. */
int unknownCases = 0;
for (int j = 1; j < argc; ++j) {
int known = 0;
for (int i = 0; i < kBenchCaseCount; ++i)
if (strcmp(argv[j], kBenchCases[i].name) == 0) known = 1;
if (!known) {
fprintf(stderr, "DriverBench: no case named '%s'\n", argv[j]);
unknownCases = 1;
}
}
if (unknownCases) {
fprintf(stderr, "DriverBench: the %d cases in kBenchCases are:\n", kBenchCaseCount);
for (int i = 0; i < kBenchCaseCount; ++i)
fprintf(stderr, " %s\n", kBenchCases[i].name);
return 2;
}
if (boot_egl()) return 1;
build_resources();
MobileGL/MG_Client/generated_trampoline_coverage.txt
-1355
View File
File diff suppressed because it is too large Load Diff
MobileGL/MG_Client/generated_wire_client.h
-10894
View File
File diff suppressed because it is too large Load Diff
MobileGL/MG_Client/generated_wire_trampoline.cpp
-12497
View File
File diff suppressed because it is too large Load Diff

Some files were not shown because too many files have changed in this diff Show More