Merge branch 'main' into jty/python/emailInjection

.bazelrc

@@ -1,3 +1,3 @@
-build --copt="-std=c++17"
+build --repo_env=CC=clang --repo_env=CXX=clang++ --copt="-std=c++17"
 
 try-import %workspace%/local.bazelrc

.codeqlmanifest.json

@@ -1,27 +0,0 @@
-{
-    "provide": [
-        "*/ql/src/qlpack.yml",
-        "*/ql/lib/qlpack.yml",
-        "*/ql/test/qlpack.yml",
-        "*/ql/examples/qlpack.yml",
-        "*/ql/consistency-queries/qlpack.yml",
-        "cpp/ql/test/query-tests/Security/CWE/CWE-190/semmle/tainted/qlpack.yml",
-        "javascript/ql/experimental/adaptivethreatmodeling/lib/qlpack.yml",
-        "javascript/ql/experimental/adaptivethreatmodeling/modelbuilding/qlpack.yml",
-        "javascript/ql/experimental/adaptivethreatmodeling/src/qlpack.yml",
-        "csharp/ql/campaigns/Solorigate/lib/qlpack.yml",
-        "csharp/ql/campaigns/Solorigate/src/qlpack.yml",
-        "csharp/ql/campaigns/Solorigate/test/qlpack.yml",
-        "misc/legacy-support/*/qlpack.yml",
-        "misc/suite-helpers/qlpack.yml",
-        "ruby/extractor-pack/codeql-extractor.yml",
-        "ql/extractor-pack/codeql-extractor.yml"
-    ],
-    "versionPolicies": {
-      "default": {
-        "requireChangeNotes": true,
-        "committedPrereleaseSuffix": "dev",
-        "committedVersion": "nextPatchRelease"
-      }
-    }
-}

.devcontainer/devcontainer.json

@@ -3,6 +3,8 @@
     "rust-lang.rust",
     "bungcip.better-toml",
     "github.vscode-codeql",
+    "hbenl.vscode-test-explorer",
+    "ms-vscode.test-adapter-converter",
     "slevesque.vscode-zipexplorer"
   ],
   "settings": {

.gitattributes

@@ -39,6 +39,7 @@
 *.py text
 *.lua text
 *.expected text
+*.go text
 
 # Explicitly set a bunch of known extensions to binary, because Git < 2.10 will treat
 # `* text=auto eol=lf` as `* text eol=lf`
@@ -52,6 +53,14 @@
 java/ql/test/stubs/**/*.java linguist-generated=true
 java/ql/test/experimental/stubs/**/*.java linguist-generated=true
 
+# Force git not to modify line endings for go or html files under the go/ql directory
+go/ql/**/*.go -text
+go/ql/**/*.html -text
+# Force git not to modify line endings for go dbschemes
+go/*.dbscheme -text
+# Preserve unusual line ending from codeql-go merge
+go/extractor/opencsv/CSVReader.java -text
+
 # For some languages, upgrade script testing references really old dbscheme
 # files from legacy upgrades that have CRLF line endings. Since upgrade
 # resolution relies on object hashes, we must suppress line ending conversion

.github/dependabot.yml

@@ -16,3 +16,11 @@ updates:
     directory: "ruby/autobuilder"
     schedule:
       interval: "daily"
+
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "daily"
+    ignore:
+      - dependency-name: '*'
+        update-types: ['version-update:semver-patch', 'version-update:semver-minor']

.github/labeler.yml

@@ -11,7 +11,7 @@ Java:
   - change-notes/**/*java.*
 
 JS:
-  - javascript/**/*
+  - any: [ 'javascript/**/*', '!javascript/ql/experimental/adaptivethreatmodeling/**/*' ]
   - change-notes/**/*javascript*
 
 Python:
@@ -21,6 +21,10 @@ Python:
 Ruby:
   - ruby/**/*
   - change-notes/**/*ruby*
+  
+Swift:
+  - swift/**/*
+  - change-notes/**/*swift*
 
 documentation:
   - "**/*.qhelp"
@@ -28,4 +32,4 @@ documentation:
   - docs/**/*
 
 "QL-for-QL": 
-  - ql/**/*
+  - ql/**/*

.github/problem-matchers/codeql-query-format.json

@@ -0,0 +1,14 @@
+{
+    "problemMatcher": [
+        {
+            "owner": "codeql-query-format",
+            "pattern": [
+                {
+                    "regexp": "^((.*) would change by autoformatting\\.)$",
+                    "file": 2,
+                    "message": 1
+                }
+            ]
+        }
+    ]
+}

.github/problem-matchers/codeql-syntax-check.json

@@ -0,0 +1,17 @@
+{
+    "problemMatcher": [
+        {
+            "owner": "codeql-syntax-check",
+            "pattern": [
+                {
+                    "regexp": "^((ERROR|WARNING): .* \\((.*):(\\d+),(\\d+)-\\d+\\))$",
+                    "message": 1,
+                    "file": 3,
+                    "line": 4,
+                    "col": 5,
+                    "severity": 2
+                }
+            ]
+        }
+    ]
+}

.github/problem-matchers/codeql-test-run.json

@@ -0,0 +1,14 @@
+{
+    "problemMatcher": [
+        {
+            "owner": "codeql-test-run",
+            "pattern": [
+                {
+                    "regexp": "(\\[.*\\] FAILED\\((RESULT|COMPILATION)\\) (.*))$",
+                    "file": 3,
+                    "message": 1
+                }
+            ]
+        }
+    ]
+}

.github/problem-matchers/make.json

@@ -0,0 +1,13 @@
+{
+    "problemMatcher": [
+        {
+            "owner": "make",
+            "pattern": [
+                {
+                    "regexp": "^(make: \\*\\*\\* .*)$",
+                    "message": 1
+                }
+            ]
+        }
+    ]
+}

.github/workflows/check-qldoc.yml

@@ -22,7 +22,7 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ github.token }}
 
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
         with:
           fetch-depth: 2
 
@@ -30,7 +30,8 @@ jobs:
         shell: bash
         run: |
           EXIT_CODE=0
-          changed_lib_packs="$(git diff --name-only --diff-filter=ACMRT HEAD^ HEAD | { grep -o '^[a-z]*/ql/lib' || true; } | sort -u)"
+          # TODO: remove the swift exception from the regex when we fix generated QLdoc
+          changed_lib_packs="$(git diff --name-only --diff-filter=ACMRT HEAD^ HEAD | { grep -Po '^(?!swift)[a-z]*/ql/lib' || true; } | sort -u)"
           for pack_dir in ${changed_lib_packs}; do
             lang="${pack_dir%/ql/lib}"
             gh codeql generate library-doc-coverage --output="${RUNNER_TEMP}/${lang}-current.txt" --dir="${pack_dir}"

.github/workflows/close-stale.yml

@@ -12,7 +12,7 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/stale@v3
+    - uses: actions/stale@v5
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
         stale-issue-message: 'This issue is stale because it has been open 14 days with no activity. Comment or remove the `Stale` label in order to avoid having this issue closed in 7 days.'

.github/workflows/codeql-analysis.yml

@@ -28,12 +28,12 @@ jobs:
 
     steps:
     - name: Setup dotnet
-      uses: actions/setup-dotnet@v1
+      uses: actions/setup-dotnet@v2
       with:
-        dotnet-version: 6.0.101
+        dotnet-version: 6.0.202
 
     - name: Checkout repository
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
@@ -49,7 +49,7 @@ jobs:
     #  uses: github/codeql-action/autobuild@main
 
     # ℹ️ Command-line programs to run using the OS shell.
-    # 📚 https://git.io/JvXDl
+    # 📚 https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
 
     # ✏️ If the Autobuild fails above, remove it and uncomment the following three lines
     #    and modify them (or add more) to build your code if your project

.github/workflows/csv-coverage-metrics.yml

@@ -14,11 +14,11 @@ on:
       - ".github/workflows/csv-coverage-metrics.yml"
 
 jobs:
-  publish:
+  publish-java:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
       - name: Setup CodeQL
         uses: ./.github/actions/fetch-codeql
       - name: Create empty database
@@ -31,13 +31,40 @@ jobs:
       - name: Capture coverage information
         run: |
           DATABASE="${{ runner.temp }}/java-database"
-          codeql database analyze --format=sarif-latest --output=metrics.sarif -- "$DATABASE" ./java/ql/src/Metrics/Summaries/FrameworkCoverage.ql
+          codeql database analyze --format=sarif-latest --output=metrics-java.sarif -- "$DATABASE" ./java/ql/src/Metrics/Summaries/FrameworkCoverage.ql
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         with:
-          name: metrics.sarif
+          name: metrics-java.sarif
-          path: metrics.sarif
+          path: metrics-java.sarif
           retention-days: 20
       - name: Upload SARIF file
-        uses: github/codeql-action/upload-sarif@v1
+        uses: github/codeql-action/upload-sarif@main
         with:
-          sarif_file: metrics.sarif
+          sarif_file: metrics-java.sarif
+  
+  publish-csharp:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+      - name: Setup CodeQL
+        uses: ./.github/actions/fetch-codeql
+      - name: Create empty database
+        run: |
+          DATABASE="${{ runner.temp }}/csharp-database"
+          PROJECT="${{ runner.temp }}/csharp-project"
+          dotnet new classlib --language=C# --output="$PROJECT"
+          codeql database create "$DATABASE" --language=csharp --source-root="$PROJECT" --command 'dotnet build /t:rebuild csharp-project.csproj /p:UseSharedCompilation=false'
+      - name: Capture coverage information
+        run: |
+          DATABASE="${{ runner.temp }}/csharp-database"
+          codeql database analyze --format=sarif-latest --output=metrics-csharp.sarif -- "$DATABASE" ./csharp/ql/src/Metrics/Summaries/FrameworkCoverage.ql
+      - uses: actions/upload-artifact@v3
+        with:
+          name: metrics-csharp.sarif
+          path: metrics-csharp.sarif
+          retention-days: 20
+      - name: Upload SARIF file
+        uses: github/codeql-action/upload-sarif@main
+        with:
+          sarif_file: metrics-csharp.sarif

.github/workflows/csv-coverage-pr-artifacts.yml

@@ -28,11 +28,11 @@ jobs:
         GITHUB_CONTEXT: ${{ toJSON(github.event) }}
       run: echo "$GITHUB_CONTEXT"
     - name: Clone self (github/codeql) - MERGE
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
       with:
         path: merge
     - name: Clone self (github/codeql) - BASE
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
       with:
         fetch-depth: 2
         path: base
@@ -41,7 +41,7 @@ jobs:
         git log -1 --format='%H'
       working-directory: base
     - name: Set up Python 3.8
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v3
       with:
         python-version: 3.8
     - name: Download CodeQL CLI
@@ -69,21 +69,21 @@ jobs:
       run: |
         python base/misc/scripts/library-coverage/compare-folders.py out_base out_merge comparison.md
     - name: Upload CSV package list
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v3
       with:
         name: csv-framework-coverage-merge
         path: |
           out_merge/framework-coverage-*.csv
           out_merge/framework-coverage-*.rst
     - name: Upload CSV package list
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v3
       with:
         name: csv-framework-coverage-base
         path: |
           out_base/framework-coverage-*.csv
           out_base/framework-coverage-*.rst
     - name: Upload comparison results
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v3
       with:
         name: comparison
         path: |
@@ -93,7 +93,7 @@ jobs:
         mkdir -p pr
         echo ${{ github.event.pull_request.number }} > pr/NR
     - name: Upload PR number
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v3
       with:
         name: pr
         path: pr/

.github/workflows/csv-coverage-pr-comment.yml

@@ -20,9 +20,9 @@ jobs:
         GITHUB_CONTEXT: ${{ toJSON(github.event) }}
       run: echo "$GITHUB_CONTEXT"
     - name: Clone self (github/codeql)
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
     - name: Set up Python 3.8
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v3
       with:
         python-version: 3.8
 

.github/workflows/csv-coverage-timeseries.yml

@@ -10,16 +10,16 @@ jobs:
 
     steps:
     - name: Clone self (github/codeql)
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
       with:
         path: script
     - name: Clone self (github/codeql) for analysis
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
       with:
         path: codeqlModels
         fetch-depth: 0
     - name: Set up Python 3.8
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v3
       with:
         python-version: 3.8
     - name: Download CodeQL CLI
@@ -35,7 +35,7 @@ jobs:
         echo $CLI
         PATH="$PATH:$CLI" python script/misc/scripts/library-coverage/generate-timeseries.py codeqlModels
     - name: Upload timeseries CSV
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v3
       with:
         name: framework-coverage-timeseries
         path: framework-coverage-timeseries-*.csv

.github/workflows/csv-coverage-update.yml

@@ -17,12 +17,12 @@ jobs:
         GITHUB_CONTEXT: ${{ toJSON(github.event) }}
       run: echo "$GITHUB_CONTEXT"
     - name: Clone self (github/codeql)
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
       with:
         path: ql
         fetch-depth: 0
     - name: Set up Python 3.8
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v3
       with:
         python-version: 3.8
     - name: Download CodeQL CLI

.github/workflows/csv-coverage.yml

@@ -14,16 +14,16 @@ jobs:
 
     steps:
     - name: Clone self (github/codeql)
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
       with:
         path: script
     - name: Clone self (github/codeql) for analysis
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
       with:
         path: codeqlModels
         ref: ${{ github.event.inputs.qlModelShaOverride || github.ref }}
     - name: Set up Python 3.8
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v3
       with:
         python-version: 3.8
     - name: Download CodeQL CLI
@@ -37,12 +37,12 @@ jobs:
       run: |
         PATH="$PATH:codeql-cli/codeql" python script/misc/scripts/library-coverage/generate-report.py ci codeqlModels script
     - name: Upload CSV package list
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v3
       with:
         name: framework-coverage-csv
         path: framework-coverage-*.csv
     - name: Upload RST package list
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v3
       with:
         name: framework-coverage-rst
         path: framework-coverage-*.rst

.github/workflows/go-tests.yml

@@ -0,0 +1,161 @@
+name: "Go: Run Tests"
+on:
+  pull_request:
+    paths:
+      - "go/**"
+      - .github/workflows/go-tests.yml
+jobs:
+
+  test-linux:
+    name: Test Linux (Ubuntu)
+    runs-on: ubuntu-latest
+    steps:
+
+    - name: Set up Go 1.18.1
+      uses: actions/setup-go@v3
+      with:
+        go-version: 1.18.1
+      id: go
+
+    - name: Set up CodeQL CLI
+      run: |
+        echo "Removing old CodeQL Directory..."
+        rm -rf $HOME/codeql
+        echo "Done"
+        cd $HOME
+        echo "Downloading CodeQL CLI..."
+        LATEST=$(gh release list --repo https://github.com/github/codeql-cli-binaries | cut -f 1 | sort --version-sort | grep -v beta | tail -1)
+        gh release download --repo https://github.com/github/codeql-cli-binaries --pattern codeql-linux64.zip "$LATEST"
+        echo "Done"
+        echo "Unpacking CodeQL CLI..."
+        unzip -q codeql-linux64.zip
+        rm -f codeql-linux64.zip
+        echo "Done"
+      env:
+        GITHUB_TOKEN: ${{ github.token }}
+
+    - name: Check out code
+      uses: actions/checkout@v2
+
+    - name: Enable problem matchers in repository
+      shell: bash
+      run: 'find .github/problem-matchers -name \*.json -exec echo "::add-matcher::{}" \;'
+
+    - name: Build
+      run: |
+        cd go
+        env PATH=$PATH:$HOME/codeql make
+
+    - name: Check that all QL and Go code is autoformatted
+      run: |
+        cd go
+        env PATH=$PATH:$HOME/codeql make check-formatting
+
+    - name: Compile qhelp files to markdown
+      run: |
+        cd go
+        env PATH=$PATH:$HOME/codeql QHELP_OUT_DIR=qhelp-out make qhelp-to-markdown
+
+    - name: Upload qhelp markdown
+      uses: actions/upload-artifact@v2
+      with:
+        name: qhelp-markdown
+        path: go/qhelp-out/**/*.md
+
+    - name: Test
+      run: |
+        cd go
+        env PATH=$PATH:$HOME/codeql make test
+
+  test-mac:
+    name: Test MacOS
+    runs-on: macOS-latest
+    steps:
+    - name: Set up Go 1.18.1
+      uses: actions/setup-go@v3
+      with:
+        go-version: 1.18.1
+      id: go
+
+    - name: Set up CodeQL CLI
+      run: |
+        echo "Removing old CodeQL Directory..."
+        rm -rf $HOME/codeql
+        echo "Done"
+        cd $HOME
+        echo "Downloading CodeQL CLI..."
+        LATEST=$(gh release list --repo https://github.com/github/codeql-cli-binaries | cut -f 1 | sort --version-sort | grep -v beta | tail -1)
+        gh release download --repo https://github.com/github/codeql-cli-binaries --pattern codeql-osx64.zip "$LATEST"
+        echo "Done"
+        echo "Unpacking CodeQL CLI..."
+        unzip -q codeql-osx64.zip
+        rm -f codeql-osx64.zip
+        echo "Done"
+      env:
+        GITHUB_TOKEN: ${{ github.token }}
+
+    - name: Check out code
+      uses: actions/checkout@v2
+
+    - name: Enable problem matchers in repository
+      shell: bash
+      run: 'find .github/problem-matchers -name \*.json -exec echo "::add-matcher::{}" \;'
+
+    - name: Build
+      run: |
+        cd go
+        env PATH=$PATH:$HOME/codeql make
+
+    - name: Test
+      run: |
+        cd go
+        env PATH=$PATH:$HOME/codeql make test
+
+  test-win:
+    name: Test Windows
+    runs-on: windows-2019
+    steps:
+    - name: Set up Go 1.18.1
+      uses: actions/setup-go@v3
+      with:
+        go-version: 1.18.1
+      id: go
+
+    - name: Set up CodeQL CLI
+      run: |
+        echo "Removing old CodeQL Directory..."
+        rm -rf $HOME/codeql
+        echo "Done"
+        cd "$HOME"
+        echo "Downloading CodeQL CLI..."
+        LATEST=$(gh release list --repo https://github.com/github/codeql-cli-binaries | cut -f 1 | sort --version-sort | grep -v beta | tail -1)
+        gh release download --repo https://github.com/github/codeql-cli-binaries --pattern codeql-win64.zip "$LATEST"
+        echo "Done"
+        echo "Unpacking CodeQL CLI..."
+        unzip -q -o codeql-win64.zip
+        unzip -q -o codeql-win64.zip codeql/codeql.exe
+        rm -f codeql-win64.zip
+        echo "Done"
+      env:
+        GITHUB_TOKEN: ${{ github.token }}
+      shell:
+        bash
+
+    - name: Check out code
+      uses: actions/checkout@v2
+
+    - name: Enable problem matchers in repository
+      shell: bash
+      run: 'find .github/problem-matchers -name \*.json -exec echo "::add-matcher::{}" \;'
+
+    - name: Build
+      run: |
+        $Env:Path += ";$HOME\codeql"
+        cd go
+        make
+
+    - name: Test
+      run: |
+        $Env:Path += ";$HOME\codeql"
+        cd go
+        make test

.github/workflows/js-ml-tests.yml

@@ -12,6 +12,7 @@ on:
     paths:
       - "javascript/ql/experimental/adaptivethreatmodeling/**"
       - .github/workflows/js-ml-tests.yml
+  workflow_dispatch:
 
 defaults:
   run:
@@ -22,7 +23,7 @@ jobs:
     name: Check QL formatting
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
 
       - uses: ./.github/actions/fetch-codeql
 
@@ -35,7 +36,7 @@ jobs:
     name: Check QL compilation
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
 
       - uses: ./.github/actions/fetch-codeql
 
@@ -59,7 +60,7 @@ jobs:
     name: Run QL tests
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
 
       - uses: ./.github/actions/fetch-codeql
 

.github/workflows/labeler.yml

@@ -6,6 +6,6 @@ jobs:
   triage:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/labeler@v2
+    - uses: actions/labeler@v4
       with:
         repo-token: "${{ secrets.GITHUB_TOKEN }}"

.github/workflows/mad_modelDiff.yml

@@ -27,12 +27,12 @@ jobs:
         slug: ${{fromJson(github.event.inputs.projects || '["apache/commons-codec", "apache/commons-io", "apache/commons-beanutils", "apache/commons-logging", "apache/commons-fileupload", "apache/commons-lang", "apache/commons-validator", "apache/commons-csv", "apache/dubbo"]' )}}
     steps:
       - name: Clone github/codeql from PR
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         if: github.event.pull_request
         with:
           path: codeql-pr
       - name: Clone github/codeql from main
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           path: codeql-main
           ref: main
@@ -91,12 +91,12 @@ jobs:
             name="diff_${basename/_main.qll/""}"
             (diff -w -u $m $t | diff2html -i stdin -F $MODELS/$name.html) || true
           done
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         with:
           name: models
           path: tmp-models/*.qll
           retention-days: 20
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         with:
           name: diffs
           path: tmp-models/*.html

.github/workflows/mad_regenerate-models.yml

@@ -26,11 +26,11 @@ jobs:
             ref: "placeholder"
     steps:
       - name: Clone self (github/codeql)
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
       - name: Setup CodeQL binaries
         uses: ./.github/actions/fetch-codeql
       - name: Clone repositories
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           path: repos/${{ matrix.ref }}
           ref: ${{ matrix.ref }}
@@ -55,7 +55,7 @@ jobs:
           find java -name "*.qll" -print0 | xargs -0 git add
           git status
           git diff --cached > models.patch
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         with:
           name: patch
           path: models.patch

.github/workflows/post-pr-comment.yml

@@ -1,12 +1,17 @@
-name: Post pull-request comment
+# This workflow is the second part of the process described in
+# .github/workflows/qhelp-pr-preview.yml
+# See that file for more info.
+
+name: Post PR comment
 on:
   workflow_run:
-    workflows: ["Query help preview"]
+    workflows: [Render QHelp changes]
     types:
       - completed
 
 permissions:
   pull-requests: write
+  actions: read
 
 jobs:
   post_comment:
@@ -17,15 +22,53 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ github.token }}
           WORKFLOW_RUN_ID: ${{ github.event.workflow_run.id }}
-      - run: |
+
-          PR="$(grep -o '^[0-9]\+$' pr.txt)"
+      - name: Check that PR SHA matches workflow SHA
+        run: |
+          PR="$(grep -o '^[0-9]\+$' pr_number.txt)"
           PR_HEAD_SHA="$(gh api "/repos/${GITHUB_REPOSITORY}/pulls/${PR}" --jq .head.sha)"
           # Check that the pull-request head SHA matches the head SHA of the workflow run
           if [ "${WORKFLOW_RUN_HEAD_SHA}" != "${PR_HEAD_SHA}" ]; then
             echo "PR head SHA ${PR_HEAD_SHA} does not match workflow_run event SHA ${WORKFLOW_RUN_HEAD_SHA}. Stopping." 1>&2
             exit 1
           fi
-          gh pr comment "${PR}" --repo "${GITHUB_REPOSITORY}" -F comment.txt
         env:
           GITHUB_TOKEN: ${{ github.token }}
           WORKFLOW_RUN_HEAD_SHA: ${{ github.event.workflow_run.head_commit.id }}
+
+      - name: Create or update comment
+        run: |
+          COMMENT_PREFIX="QHelp previews"
+          COMMENT_AUTHOR="github-actions[bot]"
+          PR_NUMBER="$(grep -o '^[0-9]\+$' pr_number.txt)"
+
+          # If there is no existing comment, comment_id.txt will contain just a
+          # newline (due to jq & gh behaviour). This will cause grep to fail, so
+          # we catch that.
+          RAW_COMMENT_ID=$(grep -o '^[0-9]\+$' comment_id.txt || true)
+
+          if [ $RAW_COMMENT_ID ]
+          then
+            # Fetch existing comment, and validate:
+            # - comment belongs to the PR with number $PR_NUMBER
+            # - comment starts with the expected prefix ("QHelp previews")
+            # - comment author is github-actions[bot]
+            FILTER='select(.issue_url | endswith($repo+"/issues/"+$pr))
+                  | select(.body | startswith($prefix))
+                  | select(.user.login == $author)
+                  | .id'
+            COMMENT_ID=$(gh api "repos/${GITHUB_REPOSITORY}/issues/comments/${RAW_COMMENT_ID}" | jq --arg repo "${GITHUB_REPOSITORY}" --arg pr "${PR_NUMBER}" --arg prefix "${COMMENT_PREFIX}" --arg author "${COMMENT_AUTHOR}" "${FILTER}")
+            if [ $COMMENT_ID ]
+            then
+              # Update existing comment
+              jq --rawfile body comment_body.txt '{"body":$body}' -n | gh api "repos/${GITHUB_REPOSITORY}/issues/comments/${COMMENT_ID}" -X PATCH --input -
+            else
+              echo "Comment ${RAW_COMMENT_ID} did not pass validations: not editing." >&2
+              exit 1
+            fi
+          else
+            # Create new comment
+            jq --rawfile body comment_body.txt '{"body":$body}' -n | gh api "repos/${GITHUB_REPOSITORY}/issues/${PR_NUMBER}/comments" -X POST --input -
+          fi
+        env:
+          GITHUB_TOKEN: ${{ github.token }}

.github/workflows/qhelp-pr-preview.yml

@@ -1,7 +1,25 @@
-name: Query help preview
+# This workflow checks for any changes in .qhelp files in pull requests.
+# For any changed files, it renders them to markdown in a file called `comment_body.txt`.
+# It then checks if there's an existing comment on the pull request generated by
+# this workflow, and writes the comment ID to `comment_id.txt`.
+# It also writes the PR number to `pr_number.txt`.
+# These three files are uploaded as an artifact.
+
+# When this workflow completes, the workflow "Post PR comment" runs.
+# It downloads the artifact and adds a comment to the PR with the rendered
+# QHelp.
+
+# The task is split like this because creating PR comments requires extra
+# permissions that we don't want to expose to PRs from external forks.
+
+# For more info see:
+# https://docs.github.com/en/actions/using-workflows/events-that-trigger-workflows#workflow_run
+# https://docs.github.com/en/actions/security-guides/automatic-token-authentication#permissions-for-the-github_token
+name: Render QHelp changes
 
 permissions:
   contents: read
+  pull-requests: read
 
 on:
   pull_request:
@@ -15,13 +33,17 @@ jobs:
   qhelp:
     runs-on: ubuntu-latest
     steps:
-      - run: echo "${{  github.event.number }}" > pr.txt
+      - run: echo "${PR_NUMBER}" > pr_number.txt
-      - uses: actions/upload-artifact@v2
+        env:
+          PR_NUMBER: ${{ github.event.number }}
+      - uses: actions/upload-artifact@v3
         with:
           name: comment
-          path: pr.txt
+          path: pr_number.txt
+          if-no-files-found: error
           retention-days: 1
-      - uses: actions/checkout@v2
+
+      - uses: actions/checkout@v3
         with:
           fetch-depth: 2
           persist-credentials: false
@@ -36,7 +58,7 @@ jobs:
       - name: QHelp preview
         run: |
           EXIT_CODE=0
-          echo "QHelp previews:" > comment.txt
+          echo "QHelp previews:" > comment_body.txt
           while read -r -d $'\0' path; do
             if [ ! -f "${path}" ]; then
                exit 1
@@ -52,12 +74,29 @@ jobs:
                echo '```'
             fi
             echo "</details>"
-          done < "${RUNNER_TEMP}/paths.txt" >> comment.txt
+          done < "${RUNNER_TEMP}/paths.txt" >> comment_body.txt
           exit "${EXIT_CODE}"
 
       - if: always()
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: comment
-          path: comment.txt
+          path: comment_body.txt
+          if-no-files-found: error
+          retention-days: 1
+
+      - name: Save ID of existing QHelp comment (if it exists)
+        run: |
+          # Find the latest comment starting with "QHelp previews"
+          COMMENT_PREFIX="QHelp previews"
+          gh api "repos/${GITHUB_REPOSITORY}/issues/${PR_NUMBER}/comments" --paginate | jq --arg prefix "${COMMENT_PREFIX}" '[.[] | select(.body|startswith($prefix)) | .id] | max' > comment_id.txt
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+          PR_NUMBER: ${{ github.event.number }}
+
+      - uses: actions/upload-artifact@v3
+        with:
+          name: comment
+          path: comment_id.txt
+          if-no-files-found: error
           retention-days: 1

.github/workflows/ql-for-ql-build.yml

@@ -13,7 +13,7 @@ jobs:
   queries:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - name: Find codeql
         id: find-codeql
         uses: github/codeql-action/init@aa93aea877e5fb8841bcb1193f672abf6e9f2980
@@ -29,7 +29,7 @@ jobs:
           CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
       - name: Cache queries
         id: cache-queries
-        uses: actions/cache@v2
+        uses: actions/cache@v3
         with:
           path: ${{ runner.temp }}/query-pack.zip
           key: queries-${{ hashFiles('ql/**/*.ql*') }}-${{ hashFiles('ql/**/qlpack.yml') }}-${{ hashFiles('ql/ql/src/ql.dbscheme*') }}-${{ steps.get-codeql-version.outputs.version }}
@@ -44,7 +44,7 @@ jobs:
           CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
           PACKZIP: ${{ runner.temp }}/query-pack.zip
       - name: Upload query pack
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: query-pack-zip
           path: ${{ runner.temp }}/query-pack.zip
@@ -56,10 +56,10 @@ jobs:
     runs-on: ubuntu-latest
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - name: Cache entire extractor
         id: cache-extractor
-        uses: actions/cache@v2
+        uses: actions/cache@v3
         with:
           path: |
             ql/target/release/ql-autobuilder
@@ -69,7 +69,7 @@ jobs:
           key: ${{ runner.os }}-extractor-${{ hashFiles('ql/**/Cargo.lock') }}-${{ hashFiles('ql/**/*.rs') }}
       - name: Cache cargo
         if: steps.cache-extractor.outputs.cache-hit != 'true'
-        uses: actions/cache@v2
+        uses: actions/cache@v3
         with:
           path: |
             ~/.cargo/registry
@@ -91,7 +91,7 @@ jobs:
       - name: Generate dbscheme
         if: steps.cache-extractor.outputs.cache-hit != 'true'
         run: ql/target/release/ql-generator --dbscheme ql/ql/src/ql.dbscheme --library ql/ql/src/codeql_ql/ast/internal/TreeSitter.qll
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         with:
           name: extractor-ubuntu-latest
           path: |
@@ -108,12 +108,12 @@ jobs:
       - queries
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
-      - uses: actions/download-artifact@v2
+      - uses: actions/download-artifact@v3
         with:
           name: query-pack-zip
           path: query-pack-zip
-      - uses: actions/download-artifact@v2
+      - uses: actions/download-artifact@v3
         with:
           name: extractor-ubuntu-latest
           path: linux64
@@ -131,7 +131,7 @@ jobs:
           fi
           cd pack
           zip -rq ../codeql-ql.zip .
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         with:
           name: codeql-ql-pack
           path: codeql-ql.zip
@@ -140,14 +140,14 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        folder: [cpp, csharp, java, javascript, python, ql, ruby]
+        folder: [cpp, csharp, java, javascript, python, ql, ruby, swift, go]
 
     needs:
       - package
 
     steps:
       - name: Download pack
-        uses: actions/download-artifact@v2
+        uses: actions/download-artifact@v3
         with:
           name: codeql-ql-pack
           path: ${{ runner.temp }}/codeql-ql-pack-artifact
@@ -166,7 +166,7 @@ jobs:
           PACK: ${{ runner.temp }}/pack
 
       - name: Checkout repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
       - name: Create CodeQL config file
         run: |
           echo "paths:" > ${CONF}
@@ -196,7 +196,7 @@ jobs:
       - name: Copy sarif file to CWD
         run: cp ../results/ql.sarif ./${{ matrix.folder }}.sarif
       - name: Sarif as artifact
-        uses: actions/upload-artifact@v2
+        uses: actions/upload-artifact@v3
         with:
           name: ${{ matrix.folder }}.sarif
           path: ${{ matrix.folder }}.sarif

.github/workflows/ql-for-ql-dataset_measure.yml

@@ -19,17 +19,16 @@ jobs:
       matrix:
         repo:
           - github/codeql
-          - github/codeql-go
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
 
       - name: Find codeql
         id: find-codeql
         uses: github/codeql-action/init@aa93aea877e5fb8841bcb1193f672abf6e9f2980
         with:
           languages: javascript # does not matter
-      - uses: actions/cache@v2
+      - uses: actions/cache@v3
         with:
           path: |
             ~/.cargo/registry
@@ -41,7 +40,7 @@ jobs:
         env:
           CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
       - name: Checkout ${{ matrix.repo }}
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           repository: ${{ matrix.repo }}
           path: ${{ github.workspace }}/repo
@@ -60,7 +59,7 @@ jobs:
           "${CODEQL}" dataset measure --threads 4 --output "stats/${{ matrix.repo }}/stats.xml" "${{ runner.temp }}/database/db-ql"
         env:
           CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         with:
           name: measurements
           path: stats
@@ -70,15 +69,15 @@ jobs:
     runs-on: ubuntu-latest
     needs: measure
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
-      - uses: actions/download-artifact@v2
+      - uses: actions/download-artifact@v3
         with:
           name: measurements
           path: stats
       - run: |
           python -m pip install --user lxml
-          find stats -name 'stats.xml' -print0 | sort -z | xargs -0 python ql/scripts/merge_stats.py --output ql/ql/src/ql.dbscheme.stats --normalise ql_tokeninfo
+          find stats -name 'stats.xml' -print0 | sort -z | xargs -0 python ruby/scripts/merge_stats.py --output ql/ql/src/ql.dbscheme.stats --normalise ql_tokeninfo
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         with:
           name: ql.dbscheme.stats
           path: ql/ql/src/ql.dbscheme.stats

.github/workflows/ql-for-ql-tests.yml

@@ -17,13 +17,13 @@ jobs:
   qltest:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - name: Find codeql
         id: find-codeql
         uses: github/codeql-action/init@aa93aea877e5fb8841bcb1193f672abf6e9f2980
         with:
           languages: javascript # does not matter
-      - uses: actions/cache@v2
+      - uses: actions/cache@v3
         with:
           path: |
             ~/.cargo/registry

.github/workflows/query-list.yml

@@ -17,33 +17,23 @@ jobs:
 
     steps:
     - name: Clone self (github/codeql)
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
       with:
         path: codeql 
-    - name: Clone github/codeql-go
-      uses: actions/checkout@v2
-      with:
-        repository: 'github/codeql-go'
-        path: codeql-go
     - name: Set up Python 3.8
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v3
       with:
         python-version: 3.8
     - name: Download CodeQL CLI
-      uses: dsaltares/fetch-gh-release-asset@aa37ae5c44d3c9820bc12fe675e8670ecd93bd1c
+      # Look under the `codeql` directory, as this is where we checked out the `github/codeql` repo
-      with:
+      uses: ./codeql/.github/actions/fetch-codeql
-        repo: "github/codeql-cli-binaries"
-        version: "latest"
-        file: "codeql-linux64.zip"
-        token: ${{ secrets.GITHUB_TOKEN }}
     - name: Unzip CodeQL CLI
       run: unzip -d codeql-cli codeql-linux64.zip
     - name: Build code scanning query list
       run: |
-        PATH="$PATH:codeql-cli/codeql" python codeql/misc/scripts/generate-code-scanning-query-list.py > code-scanning-query-list.csv
+        python codeql/misc/scripts/generate-code-scanning-query-list.py > code-scanning-query-list.csv
     - name: Upload code scanning query list
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v3
       with:
         name: code-scanning-query-list
         path: code-scanning-query-list.csv
-    

.github/workflows/ruby-build.yml

@@ -38,13 +38,13 @@ jobs:
     runs-on: ${{ matrix.os }}
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - name: Install GNU tar
         if: runner.os == 'macOS'
         run: |
           brew install gnu-tar
           echo "/usr/local/opt/gnu-tar/libexec/gnubin" >> $GITHUB_PATH
-      - uses: actions/cache@v2
+      - uses: actions/cache@v3
         with:
           path: |
             ~/.cargo/registry
@@ -62,17 +62,17 @@ jobs:
       - name: Generate dbscheme
         if: ${{ matrix.os == 'ubuntu-latest' }}
         run: target/release/ruby-generator --dbscheme ql/lib/ruby.dbscheme --library ql/lib/codeql/ruby/ast/internal/TreeSitter.qll
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         if: ${{ matrix.os == 'ubuntu-latest' }}
         with:
           name: ruby.dbscheme
           path: ruby/ql/lib/ruby.dbscheme
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         if: ${{ matrix.os == 'ubuntu-latest' }}
         with:
           name: TreeSitter.qll
           path: ruby/ql/lib/codeql/ruby/ast/internal/TreeSitter.qll
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         with:
           name: extractor-${{ matrix.os }}
           path: |
@@ -86,7 +86,7 @@ jobs:
     env:
       CODEQL_THREADS: 4 # TODO: remove this once it's set by the CLI
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - name: Fetch CodeQL
         run: |
           LATEST=$(gh release list --repo https://github.com/github/codeql-cli-binaries | cut -f 1 | grep -v beta | sort --version-sort | tail -1)
@@ -102,7 +102,7 @@ jobs:
           PACK_FOLDER=$(readlink -f target/packs/codeql/ruby-queries/*)
           codeql/codeql generate query-help --format=sarifv2.1.0 --output="${PACK_FOLDER}/rules.sarif" ql/src
           (cd ql/src; find queries \( -name '*.qhelp' -o -name '*.rb' -o -name '*.erb' \) -exec bash -c 'mkdir -p "'"${PACK_FOLDER}"'/$(dirname "{}")"' \; -exec cp "{}" "${PACK_FOLDER}/{}" \;)
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         with:
           name: codeql-ruby-queries
           path: |
@@ -113,20 +113,20 @@ jobs:
     runs-on: ubuntu-latest
     needs: [build, compile-queries]
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
-      - uses: actions/download-artifact@v2
+      - uses: actions/download-artifact@v3
         with:
           name: ruby.dbscheme
           path: ruby/ruby
-      - uses: actions/download-artifact@v2
+      - uses: actions/download-artifact@v3
         with:
           name: extractor-ubuntu-latest
           path: ruby/linux64
-      - uses: actions/download-artifact@v2
+      - uses: actions/download-artifact@v3
         with:
           name: extractor-windows-latest
           path: ruby/win64
-      - uses: actions/download-artifact@v2
+      - uses: actions/download-artifact@v3
         with:
           name: extractor-macos-latest
           path: ruby/osx64
@@ -142,12 +142,12 @@ jobs:
           cp win64/ruby-extractor.exe ruby/tools/win64/extractor.exe
           chmod +x ruby/tools/{linux64,osx64}/{autobuilder,extractor}
           zip -rq codeql-ruby.zip ruby
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         with:
           name: codeql-ruby-pack
           path: ruby/codeql-ruby.zip
           retention-days: 1
-      - uses: actions/download-artifact@v2
+      - uses: actions/download-artifact@v3
         with:
           name: codeql-ruby-queries
           path: ruby/qlpacks
@@ -159,7 +159,7 @@ jobs:
             ]
           }' > .codeqlmanifest.json
           zip -rq codeql-ruby-bundle.zip .codeqlmanifest.json ruby qlpacks
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         with:
           name: codeql-ruby-bundle
           path: ruby/codeql-ruby-bundle.zip
@@ -177,7 +177,7 @@ jobs:
     runs-on: ${{ matrix.os }}
     needs: [package]
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
         with:
           repository: Shopify/example-ruby-app
           ref: 67a0decc5eb550f3a9228eda53925c3afd40dfe9
@@ -191,7 +191,7 @@ jobs:
           GITHUB_TOKEN: ${{ github.token }}
         working-directory: ${{ runner.temp }}
       - name: Download Ruby bundle
-        uses: actions/download-artifact@v2
+        uses: actions/download-artifact@v3
         with:
           name: codeql-ruby-bundle
           path: ${{ runner.temp }}

.github/workflows/ruby-dataset-measure.yml

@@ -27,14 +27,14 @@ jobs:
         repo: [rails/rails, discourse/discourse, spree/spree, ruby/ruby]
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
 
       - uses: ./.github/actions/fetch-codeql
 
       - uses: ./ruby/actions/create-extractor-pack
 
       - name: Checkout ${{ matrix.repo }}
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           repository: ${{ matrix.repo }}
           path: ${{ github.workspace }}/repo
@@ -49,7 +49,7 @@ jobs:
         run: |
           mkdir -p "stats/${{ matrix.repo }}"
           codeql dataset measure --threads 4 --output "stats/${{ matrix.repo }}/stats.xml" "${{ runner.temp }}/database/db-ruby"
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         with:
           name: measurements
           path: stats
@@ -59,15 +59,15 @@ jobs:
     runs-on: ubuntu-latest
     needs: measure
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
-      - uses: actions/download-artifact@v2
+      - uses: actions/download-artifact@v3
         with:
           name: measurements
           path: stats
       - run: |
           python -m pip install --user lxml
           find stats -name 'stats.xml' | sort | xargs python ruby/scripts/merge_stats.py --output ruby/ql/lib/ruby.dbscheme.stats --normalise ruby_tokeninfo
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         with:
           name: ruby.dbscheme.stats
           path: ruby/ql/lib/ruby.dbscheme.stats

.github/workflows/ruby-qltest.yml

@@ -27,14 +27,14 @@ jobs:
   qlformat:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - uses: ./.github/actions/fetch-codeql
       - name: Check QL formatting
         run: find ql "(" -name "*.ql" -or -name "*.qll" ")" -print0 | xargs -0 codeql query format --check-only
   qlcompile:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - uses: ./.github/actions/fetch-codeql
       - name: Check QL compilation
         run: |
@@ -44,7 +44,7 @@ jobs:
   qlupgrade:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - uses: ./.github/actions/fetch-codeql
       - name: Check DB upgrade scripts
         run: |
@@ -67,7 +67,7 @@ jobs:
       matrix:
         slice: ["1/2", "2/2"]
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - uses: ./.github/actions/fetch-codeql
       - uses: ./ruby/actions/create-extractor-pack
       - name: Run QL tests

.github/workflows/swift-codegen.yml

@@ -0,0 +1,32 @@
+name: "Swift: Check code generation"
+
+on:
+  pull_request:
+    paths:
+      - "swift/**"
+      - .github/workflows/swift-codegen.yml
+    branches:
+      - main
+
+jobs:
+  codegen:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./.github/actions/fetch-codeql
+      - uses: bazelbuild/setup-bazelisk@v2
+      - name: Run unit tests
+        run: |
+          bazel test //swift/codegen/test --test_output=errors
+      - name: Check that QL generated code was checked in
+        run: |
+          bazel run //swift/codegen
+          git add swift
+          git diff --exit-code --stat HEAD
+      - name: Generate C++ files
+        run: |
+          bazel run //swift/codegen:cppcodegen -- --cpp-output=$PWD/swift-generated-headers
+      - uses: actions/upload-artifact@v3
+        with:
+          name: swift-generated-headers
+          path: swift-generated-headers/*.h

.github/workflows/swift-qltest.yml

@@ -15,7 +15,7 @@ jobs:
   qlformat:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - uses: ./.github/actions/fetch-codeql
       - name: Check QL formatting
         run: find ql "(" -name "*.ql" -or -name "*.qll" ")" -print0 | xargs -0 codeql query format --check-only
@@ -26,20 +26,9 @@ jobs:
       matrix:
         os : [ubuntu-20.04, macos-latest]
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - uses: ./.github/actions/fetch-codeql
-      - name: Install bazelisk - Linux
+      - uses: bazelbuild/setup-bazelisk@v2
-        if: runner.os == 'Linux'
-        run: |
-          sudo apt-get update
-          sudo apt-get install -y wget
-          wget https://github.com/bazelbuild/bazelisk/releases/download/v1.11.0/bazelisk-linux-amd64
-          mv bazelisk-linux-amd64 /usr/local/bin/bazel
-          chmod +x /usr/local/bin/bazel
-      - name: Install bazelisk - macOS
-        if: runner.os == 'MacOS'
-        run: |
-          brew install bazelisk
       - name: Build Swift extractor
         run: |
           bazel run //swift:create-extractor-pack
@@ -48,4 +37,3 @@ jobs:
           codeql test run --threads=0 --ram 5000 --search-path "${{ github.workspace }}/swift/extractor-pack" --check-databases --check-unused-labels --check-repeated-labels --check-redefined-labels --check-use-before-definition ql/test
         env:
           GITHUB_TOKEN: ${{ github.token }}
-

.github/workflows/sync-files.yml

@@ -14,7 +14,7 @@ jobs:
   sync:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
       - name: Check synchronized files
         run: python config/sync-files.py
 

.github/workflows/validate-change-notes.yml

@@ -18,7 +18,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
 
       - name: Setup CodeQL
         uses: ./.github/actions/fetch-codeql

.gitignore

@@ -9,6 +9,7 @@
 # qltest projects and artifacts
 */ql/test/**/*.testproj
 */ql/test/**/*.actual
+*/ql/test/**/go.sum
 
 # Visual studio temporaries, except a file used by QL4VS
 .vs/*
@@ -20,6 +21,9 @@
 # python virtual environment folder
 .venv/
 
+# binary files created by pytest-cov
+.coverage
+
 # It's useful (though not required) to be able to unpack codeql in the ql checkout itself
 /codeql/
 
@@ -34,5 +38,20 @@ csharp/extractor/Semmle.Extraction.CSharp.Driver/Properties/launchSettings.json
 # links created by bazel
 /bazel-*
 
+# local bazel options
+/local.bazelrc
+
 # CLion project files
 /.clwb
+
+# Go build artifacts
+go/build/*
+
+# Go binaries
+go/tools/bin
+go/tools/linux64
+go/tools/osx64
+go/tools/win64
+go/tools/tokenizer.jar
+go/main
+

.lgtm.yml

@@ -6,6 +6,7 @@ path_classifiers:
   test:
   - csharp/ql/src
   - csharp/ql/test
+  - go/ql/test
   - javascript/extractor/parser-tests
   - javascript/extractor/tests
   - javascript/ql/src
@@ -13,6 +14,9 @@ path_classifiers:
   - python/ql/src
   - python/ql/test
 
+  example:
+  - go/ql/src
+
 queries:
   - include: "*"
 

.pre-commit-config.yaml

@@ -1,29 +1,51 @@
 # See https://pre-commit.com for more information
 # See https://pre-commit.com/hooks.html for more hooks
-exclude: /test/.*$(?<!\.ql)(?<!\.qll)(?<!\.qlref)
 repos:
--   repo: https://github.com/pre-commit/pre-commit-hooks
+  - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v3.2.0
     hooks:
-    -   id: trailing-whitespace
+      - id: trailing-whitespace
-    -   id: end-of-file-fixer
+        exclude: /test/.*$(?<!\.ql)(?<!\.qll)(?<!\.qlref)
+      - id: end-of-file-fixer
+        exclude: /test/.*$(?<!\.ql)(?<!\.qll)(?<!\.qlref)
 
--   repo: local
+  - repo: https://github.com/pre-commit/mirrors-clang-format
+    rev: v13.0.1
     hooks:
-    -   id: codeql-format
+      - id: clang-format
+        files: ^swift/.*\.(h|c|cpp)$
+
+  - repo: local
+    hooks:
+      - id: codeql-format
         name: Fix QL file formatting
         files: \.qll?$
         language: system
         entry: codeql query format --in-place
 
-    -   id: sync-files
+      - id: sync-files
         name: Fix files required to be identical
+        files: \.(qll?|qhelp)$
         language: system
         entry: python3 config/sync-files.py --latest
         pass_filenames: false
 
-    -   id: qhelp
+      - id: qhelp
         name: Check query help generation
         files: \.qhelp$
         language: system
         entry: python3 misc/scripts/check-qhelp.py
+
+      - id: swift-codegen
+        name: Run Swift checked in code generation
+        files: ^swift/(codegen/|.*/generated/|ql/lib/(swift\.dbscheme$|codeql/swift/elements))
+        language: system
+        entry: bazel run //swift/codegen
+        pass_filenames: false
+
+      - id: swift-codegen-unit-tests
+        name: Run Swift code generation unit tests
+        files: ^swift/codegen/.*\.py$
+        language: system
+        entry: bazel test //swift/codegen/test
+        pass_filenames: false

CODEOWNERS

@@ -1,9 +1,13 @@
 /cpp/ @github/codeql-c-analysis
 /csharp/ @github/codeql-csharp
+/go/ @github/codeql-go
 /java/ @github/codeql-java
 /javascript/ @github/codeql-javascript
 /python/ @github/codeql-python
 /ruby/ @github/codeql-ruby
+/swift/ @github/codeql-c
+/java/kotlin-extractor/ @github/codeql-kotlin
+/java/kotlin-explorer/ @github/codeql-kotlin
 
 # ML-powered queries
 /javascript/ql/experimental/adaptivethreatmodeling/ @github/codeql-ml-powered-queries-reviewers
@@ -27,3 +31,14 @@
 # Bazel
 **/*.bazel @github/codeql-ci-reviewers
 **/*.bzl @github/codeql-ci-reviewers
+
+# Documentation etc
+/*.md @github/code-scanning-product
+/LICENSE @github/code-scanning-product
+
+# Workflows
+/.github/workflows/ @github/codeql-ci-reviewers
+/.github/workflows/go-* @github/codeql-go
+/.github/workflows/js-ml-tests.yml @github/codeql-ml-powered-queries-reviewers
+/.github/workflows/ql-for-ql-* @github/codeql-ql-for-ql-reviewers
+/.github/workflows/ruby-* @github/codeql-ruby

CONTRIBUTING.md

@@ -2,7 +2,7 @@
 
 We welcome contributions to our CodeQL libraries and queries. Got an idea for a new check, or how to improve an existing query? Then please go ahead and open a pull request! Contributions to this project are [released](https://help.github.com/articles/github-terms-of-service/#6-contributions-under-repository-license) to the public under the [project's open source license](LICENSE).
 
-There is lots of useful documentation to help you write queries, ranging from information about query file structure to tutorials for specific target languages. For more information on the documentation available, see [CodeQL queries](https://help.semmle.com/QL/learn-ql/writing-queries/writing-queries.html) on [help.semmle.com](https://help.semmle.com).
+There is lots of useful documentation to help you write queries, ranging from information about query file structure to tutorials for specific target languages. For more information on the documentation available, see [CodeQL queries](https://codeql.github.com/docs/writing-codeql-queries/codeql-queries) on [codeql.github.com](https://codeql.github.com).
 
 ## Change notes
 
@@ -40,7 +40,7 @@ If you have an idea for a query that you would like to share with other CodeQL u
 
 3. **Formatting**
 
-    - The queries and libraries must be autoformatted, for example using the "Format Document" command in [CodeQL for Visual Studio Code](https://help.semmle.com/codeql/codeql-for-vscode/procedures/about-codeql-for-vscode.html).
+    - The queries and libraries must be autoformatted, for example using the "Format Document" command in [CodeQL for Visual Studio Code](https://codeql.github.com/docs/codeql-for-visual-studio-code/about-codeql-for-visual-studio-code).
 
     If you prefer, you can either:
     1. install the [pre-commit framework](https://pre-commit.com/) and install the configured hooks on this repo via `pre-commit install`, or

README.md

@@ -1,6 +1,6 @@
 # CodeQL
 
-This open source repository contains the standard CodeQL libraries and queries that power [GitHub Advanced Security](https://github.com/features/security/code) and the other application security products that [GitHub](https://github.com/features/security/) makes available to its customers worldwide. For the queries, libraries, and extractor that power Go analysis, visit the [CodeQL for Go repository](https://github.com/github/codeql-go).
+This open source repository contains the standard CodeQL libraries and queries that power [GitHub Advanced Security](https://github.com/features/security/code) and the other application security products that [GitHub](https://github.com/features/security/) makes available to its customers worldwide.
 
 ## How do I learn CodeQL and run queries?
 
@@ -13,7 +13,9 @@ We welcome contributions to our standard library and standard checks. Do you hav
 
 ## License
 
-The code in this repository is licensed under the [MIT License](LICENSE) by [GitHub](https://github.com). The use of CodeQL on open source code is licensed under specific [Terms & Conditions](https://securitylab.github.com/tools/codeql/license/) UNLESS you have a commercial license in place. If you'd like to use CodeQL with a commercial codebase, please [contact us](https://github.com/enterprise/contact) for further help.
+The code in this repository is licensed under the [MIT License](LICENSE) by [GitHub](https://github.com).
+
+The CodeQL CLI (including the CodeQL engine) is hosted in a [different repository](https://github.com/github/codeql-cli-binaries) and is [licensed separately](https://github.com/github/codeql-cli-binaries/blob/main/LICENSE.md). If you'd like to use the CodeQL CLI to analyze closed-source code, you will need a separate commercial license; please [contact us](https://github.com/enterprise/contact) for further help.
 
 ## Visual Studio Code integration
 

codeql-workspace.yml

@@ -0,0 +1,32 @@
+provide:
+  - "*/ql/src/qlpack.yml"
+  - "*/ql/lib/qlpack.yml"
+  - "*/ql/test/qlpack.yml"
+  - "*/ql/examples/qlpack.yml"
+  - "*/ql/consistency-queries/qlpack.yml"
+  - "cpp/ql/test/query-tests/Security/CWE/CWE-190/semmle/tainted/qlpack.yml"
+  - "go/ql/config/legacy-support/qlpack.yml"
+  - "go/build/codeql-extractor-go/codeql-extractor.yml"
+  - "javascript/ql/experimental/adaptivethreatmodeling/lib/qlpack.yml"
+  # This pack is explicitly excluded from the workspace since most users
+  # will want to use a version of this pack from the package cache. Internal
+  # users can uncomment the following line and place a custom ML model
+  # in the corresponding pack to test a custom ML model within their local
+  # checkout.
+  # - "javascript/ql/experimental/adaptivethreatmodeling/model/qlpack.yml"
+  - "javascript/ql/experimental/adaptivethreatmodeling/modelbuilding/qlpack.yml"
+  - "javascript/ql/experimental/adaptivethreatmodeling/src/qlpack.yml"
+  - "csharp/ql/campaigns/Solorigate/lib/qlpack.yml"
+  - "csharp/ql/campaigns/Solorigate/src/qlpack.yml"
+  - "csharp/ql/campaigns/Solorigate/test/qlpack.yml"
+  - "misc/legacy-support/*/qlpack.yml"
+  - "misc/suite-helpers/qlpack.yml"
+  - "ruby/extractor-pack/codeql-extractor.yml"
+  - "swift/extractor-pack/codeql-extractor.yml"
+  - "ql/extractor-pack/codeql-extractor.ym"
+
+versionPolicies:
+  default:
+    requireChangeNotes: true
+    committedPrereleaseSuffix: dev
+    committedVersion: nextPatchRelease

config/identical-files.json

@@ -22,13 +22,15 @@
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl3.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl4.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl5.qll",
+    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImplForContentDataFlow.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl2.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl3.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl4.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImpl.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImpl2.qll",
-    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplForLibraries.qll"
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplForLibraries.qll",
+    "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImpl.qll"
   ],
   "DataFlow Java/C++/C#/Python Common": [
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplCommon.qll",
@@ -36,7 +38,8 @@
     "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImplCommon.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImplCommon.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImplCommon.qll",
-    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplCommon.qll"
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplCommon.qll",
+    "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImplCommon.qll"
   ],
   "TaintTracking::Configuration Java/C++/C#/Python": [
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
@@ -51,12 +54,14 @@
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/tainttracking5/TaintTrackingImpl.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/tainttracking2/TaintTrackingImpl.qll",
+    "java/ql/lib/semmle/code/java/dataflow/internal/tainttracking3/TaintTrackingImpl.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/tainttracking1/TaintTrackingImpl.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/tainttracking2/TaintTrackingImpl.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/tainttracking3/TaintTrackingImpl.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/tainttracking4/TaintTrackingImpl.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
-    "ruby/ql/lib/codeql/ruby/dataflow/internal/tainttrackingforlibraries/TaintTrackingImpl.qll"
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/tainttrackingforlibraries/TaintTrackingImpl.qll",
+    "swift/ql/lib/codeql/swift/dataflow/internal/tainttracking1/TaintTrackingImpl.qll"
   ],
   "DataFlow Java/C++/C#/Python Consistency checks": [
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplConsistency.qll",
@@ -64,7 +69,8 @@
     "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImplConsistency.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImplConsistency.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImplConsistency.qll",
-    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplConsistency.qll"
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplConsistency.qll",
+    "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImplConsistency.qll"
   ],
   "DataFlow Java/C# Flow Summaries": [
     "java/ql/lib/semmle/code/java/dataflow/internal/FlowSummaryImpl.qll",
@@ -457,7 +463,8 @@
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/basessa/SsaImplCommon.qll",
     "csharp/ql/lib/semmle/code/cil/internal/SsaImplCommon.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/SsaImplCommon.qll",
-    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/SsaImplCommon.qll"
+    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/SsaImplCommon.qll",
+    "swift/ql/lib/codeql/swift/dataflow/internal/SsaImplCommon.qll"
   ],
   "CryptoAlgorithms Python/JS/Ruby": [
     "javascript/ql/lib/semmle/javascript/security/CryptoAlgorithms.qll",
@@ -474,20 +481,23 @@
     "python/ql/lib/semmle/python/security/internal/SensitiveDataHeuristics.qll",
     "ruby/ql/lib/codeql/ruby/security/internal/SensitiveDataHeuristics.qll"
   ],
-  "ReDoS Util Python/JS/Ruby": [
+  "ReDoS Util Python/JS/Ruby/Java": [
     "javascript/ql/lib/semmle/javascript/security/performance/ReDoSUtil.qll",
     "python/ql/lib/semmle/python/security/performance/ReDoSUtil.qll",
-    "ruby/ql/lib/codeql/ruby/security/performance/ReDoSUtil.qll"
+    "ruby/ql/lib/codeql/ruby/security/performance/ReDoSUtil.qll",
+    "java/ql/lib/semmle/code/java/security/performance/ReDoSUtil.qll"
   ],
-  "ReDoS Exponential Python/JS/Ruby": [
+  "ReDoS Exponential Python/JS/Ruby/Java": [
     "javascript/ql/lib/semmle/javascript/security/performance/ExponentialBackTracking.qll",
     "python/ql/lib/semmle/python/security/performance/ExponentialBackTracking.qll",
-    "ruby/ql/lib/codeql/ruby/security/performance/ExponentialBackTracking.qll"
+    "ruby/ql/lib/codeql/ruby/security/performance/ExponentialBackTracking.qll",
+    "java/ql/lib/semmle/code/java/security/performance/ExponentialBackTracking.qll"
   ],
-  "ReDoS Polynomial Python/JS/Ruby": [
+  "ReDoS Polynomial Python/JS/Ruby/Java": [
     "javascript/ql/lib/semmle/javascript/security/performance/SuperlinearBackTracking.qll",
     "python/ql/lib/semmle/python/security/performance/SuperlinearBackTracking.qll",
-    "ruby/ql/lib/codeql/ruby/security/performance/SuperlinearBackTracking.qll"
+    "ruby/ql/lib/codeql/ruby/security/performance/SuperlinearBackTracking.qll",
+    "java/ql/lib/semmle/code/java/security/performance/SuperlinearBackTracking.qll"
   ],
   "BadTagFilterQuery Python/JS/Ruby": [
     "javascript/ql/lib/semmle/javascript/security/BadTagFilterQuery.qll",
@@ -496,7 +506,8 @@
   ],
   "CFG": [
     "csharp/ql/lib/semmle/code/csharp/controlflow/internal/ControlFlowGraphImplShared.qll",
-    "ruby/ql/lib/codeql/ruby/controlflow/internal/ControlFlowGraphImplShared.qll"
+    "ruby/ql/lib/codeql/ruby/controlflow/internal/ControlFlowGraphImplShared.qll",
+    "swift/ql/lib/codeql/swift/controlflow/internal/ControlFlowGraphImplShared.qll"
   ],
   "TypeTracker": [
     "python/ql/lib/semmle/python/dataflow/new/internal/TypeTracker.qll",
@@ -549,5 +560,9 @@
   "HttpToFileAccessCustomizations JS/Ruby": [
     "javascript/ql/lib/semmle/javascript/security/dataflow/HttpToFileAccessCustomizations.qll",
     "ruby/ql/lib/codeql/ruby/security/HttpToFileAccessCustomizations.qll"
+  ],
+  "Typo database": [
+    "javascript/ql/src/Expressions/TypoDatabase.qll",
+    "ql/ql/src/codeql_ql/style/TypoDatabase.qll"
   ]
 }

conftest.py

@@ -0,0 +1 @@
+# this empty file adds the repo root to PYTHON_PATH when running pytest

cpp/downgrades/cf72c8898d19eb1b3374432cf79d8276cb07ad43/exprparents.ql

@@ -0,0 +1,21 @@
+class Element extends @element {
+  string toString() { none() }
+}
+
+class Expr extends @expr {
+  string toString() { none() }
+}
+
+class Stmt extends @stmt {
+  string toString() { none() }
+}
+
+predicate isStmtWithInitializer(Stmt stmt) {
+  exists(int kind | stmts(stmt, kind, _) | kind = 2 or kind = 11 or kind = 35)
+}
+
+from Expr child, int index, int index_new, Element parent
+where
+  exprparents(child, index, parent) and
+  if isStmtWithInitializer(parent) then index_new = index - 1 else index_new = index
+select child, index_new, parent

cpp/downgrades/cf72c8898d19eb1b3374432cf79d8276cb07ad43/stmtparents.ql

@@ -0,0 +1,22 @@
+class Element extends @element {
+  string toString() { none() }
+}
+
+class Stmt extends @stmt {
+  string toString() { none() }
+}
+
+predicate isStmtWithInitializer(Stmt stmt) {
+  exists(int kind | stmts(stmt, kind, _) | kind = 2 or kind = 11 or kind = 35)
+}
+
+from Stmt child, int index, int index_new, Element parent
+where
+  stmtparents(child, index, parent) and
+  (
+    not isStmtWithInitializer(parent)
+    or
+    index > 0
+  ) and
+  if isStmtWithInitializer(parent) then index_new = index - 1 else index_new = index
+select child, index_new, parent

cpp/downgrades/cf72c8898d19eb1b3374432cf79d8276cb07ad43/upgrade.properties

@@ -0,0 +1,6 @@
+description: Support C++17 if and switch initializers
+compatibility: partial
+if_initialization.rel: delete
+switch_initialization.rel: delete
+exprparents.rel: run exprparents.qlo
+stmtparents.rel: run stmtparents.qlo

cpp/ql/lib/CHANGELOG.md

@@ -1,3 +1,30 @@
+## 0.2.1
+
+## 0.2.0
+
+### Breaking Changes
+
+* The signature of `allowImplicitRead` on `DataFlow::Configuration` and `TaintTracking::Configuration` has changed from `allowImplicitRead(DataFlow::Node node, DataFlow::Content c)` to `allowImplicitRead(DataFlow::Node node, DataFlow::ContentSet c)`.
+
+### Minor Analysis Improvements
+
+* More Windows pool allocation functions are now detected as `AllocationFunction`s.
+* The `semmle.code.cpp.commons.Buffer` library has been enhanced to handle array members of classes that do not specify a size.
+
+## 0.1.0
+
+### Breaking Changes
+
+* The recently added flow-state versions of `isBarrierIn`, `isBarrierOut`, `isSanitizerIn`, and `isSanitizerOut` in the data flow and taint tracking libraries have been removed.
+
+### New Features
+
+* A new library `semmle.code.cpp.security.PrivateData` has been added. The new library heuristically detects variables and functions dealing with sensitive private data, such as e-mail addresses and credit card numbers.
+
+### Minor Analysis Improvements
+
+* The `semmle.code.cpp.security.SensitiveExprs` library has been enhanced with some additional rules for detecting credentials.
+
 ## 0.0.13
 
 ## 0.0.12

cpp/ql/lib/change-notes/2022-03-28-private-data.md

@@ -1,4 +0,0 @@
----
-category: feature
----
-* A new library `semmle.code.cpp.security.PrivateData` has been added. The new library heuristically detects variables and functions dealing with sensitive private data, such as e-mail addresses and credit card numbers.

cpp/ql/lib/change-notes/2022-03-31-sensitive-exprs.md

@@ -1,4 +0,0 @@
----
-category: minorAnalysis
----
-* The `semmle.code.cpp.security.SensitiveExprs` library has been enhanced with some additional rules for detecting credentials.

cpp/ql/lib/change-notes/2022-04-08-flow-state-barriers.md

@@ -1,4 +0,0 @@
----
-category: breaking
----
-The recently added flow-state versions of `isBarrierIn`, `isBarrierOut`, `isSanitizerIn`, and `isSanitizerOut` in the data flow and taint tracking libraries have been removed.

cpp/ql/lib/change-notes/2022-04-12-if-and-switch-initializers.md

@@ -0,0 +1,4 @@
+---
+category: feature
+---
+* A `getInitialization` predicate was added to the `ConstexprIfStmt`, `IfStmt`, and `SwitchStmt` classes that yields the C++17-style initializer of the `if` or `switch` statement when it exists.

cpp/ql/lib/change-notes/2022-05-11-deprecated-analysed-string.md

@@ -0,0 +1,4 @@
+---
+ category: deprecated
+---
+ * The `AnalysedString` class in the `StringAnalysis` module has been replaced with `AnalyzedString`, to follow our style guide. The old name still exists as a deprecated alias.

cpp/ql/lib/change-notes/released/0.1.0.md

@@ -0,0 +1,13 @@
+## 0.1.0
+
+### Breaking Changes
+
+* The recently added flow-state versions of `isBarrierIn`, `isBarrierOut`, `isSanitizerIn`, and `isSanitizerOut` in the data flow and taint tracking libraries have been removed.
+
+### New Features
+
+* A new library `semmle.code.cpp.security.PrivateData` has been added. The new library heuristically detects variables and functions dealing with sensitive private data, such as e-mail addresses and credit card numbers.
+
+### Minor Analysis Improvements
+
+* The `semmle.code.cpp.security.SensitiveExprs` library has been enhanced with some additional rules for detecting credentials.

cpp/ql/lib/change-notes/released/0.2.0.md

@@ -0,0 +1,10 @@
+## 0.2.0
+
+### Breaking Changes
+
+* The signature of `allowImplicitRead` on `DataFlow::Configuration` and `TaintTracking::Configuration` has changed from `allowImplicitRead(DataFlow::Node node, DataFlow::Content c)` to `allowImplicitRead(DataFlow::Node node, DataFlow::ContentSet c)`.
+
+### Minor Analysis Improvements
+
+* More Windows pool allocation functions are now detected as `AllocationFunction`s.
+* The `semmle.code.cpp.commons.Buffer` library has been enhanced to handle array members of classes that do not specify a size.

cpp/ql/lib/change-notes/released/0.2.1.md

@@ -0,0 +1 @@
+## 0.2.1

cpp/ql/lib/codeql-pack.release.yml

@@ -1,2 +1,2 @@
 ---
-lastReleaseVersion: 0.0.13
+lastReleaseVersion: 0.2.1

cpp/ql/lib/qlpack.yml

@@ -1,5 +1,5 @@
 name: codeql/cpp-all
-version: 0.1.0-dev
+version: 0.2.2-dev
 groups: cpp
 dbscheme: semmlecode.cpp.dbscheme
 extractor: cpp

cpp/ql/lib/semmle/code/cpp/Element.qll

@@ -109,10 +109,7 @@ class Element extends ElementBase {
     then
       exists(MacroInvocation mi |
         this = mi.getAGeneratedElement() and
-        not exists(MacroInvocation closer |
+        not hasCloserMacroInvocation(this, mi) and
-          this = closer.getAGeneratedElement() and
-          mi = closer.getParentInvocation+()
-        ) and
         result = mi.getMacro()
       )
     else result = this
@@ -236,6 +233,14 @@ class Element extends ElementBase {
   }
 }
 
+pragma[noinline]
+private predicate hasCloserMacroInvocation(Element elem, MacroInvocation mi) {
+  exists(MacroInvocation closer |
+    elem = closer.getAGeneratedElement() and
+    mi = closer.getParentInvocation()
+  )
+}
+
 private predicate isFromTemplateInstantiationRec(Element e, Element instantiation) {
   instantiation.(Function).isConstructedFrom(_) and
   e = instantiation

cpp/ql/lib/semmle/code/cpp/Field.qll

@@ -4,7 +4,6 @@
 
 import semmle.code.cpp.Variable
 import semmle.code.cpp.Enum
-import semmle.code.cpp.exprs.Access
 
 /**
  * A C structure member or C++ non-static member variable. For example the
@@ -32,7 +31,7 @@ class Field extends MemberVariable {
   int getByteOffset() { fieldoffsets(underlyingElement(this), result, _) }
 
   /**
-   * Gets the byte offset within `mostDerivedClass` of each occurence of this
+   * Gets the byte offset within `mostDerivedClass` of each occurrence of this
    * field within `mostDerivedClass` itself or a base class subobject of
    * `mostDerivedClass`.
    * Note that for fields of virtual base classes, and non-virtual base classes

cpp/ql/lib/semmle/code/cpp/Function.qll

@@ -38,8 +38,8 @@ class Function extends Declaration, ControlFlowNode, AccessHolder, @function {
    * int z = min(5, 7);
    * ```
    * The full signature of the function called on the last line would be
-   * "min<int>(int, int) -> int", and the full signature of the uninstantiated
+   * `min<int>(int, int) -> int`, and the full signature of the uninstantiated
-   * template on the first line would be "min<T>(T, T) -> T".
+   * template on the first line would be `min<T>(T, T) -> T`.
    */
   string getFullSignature() {
     exists(string name, string templateArgs, string args |

cpp/ql/lib/semmle/code/cpp/PrintAST.qll

@@ -663,18 +663,24 @@ private predicate namedStmtChildPredicates(Locatable s, Element e, string pred)
     or
     s.(ComputedGotoStmt).getExpr() = e and pred = "getExpr()"
     or
+    s.(ConstexprIfStmt).getInitialization() = e and pred = "getInitialization()"
+    or
     s.(ConstexprIfStmt).getCondition() = e and pred = "getCondition()"
     or
     s.(ConstexprIfStmt).getThen() = e and pred = "getThen()"
     or
     s.(ConstexprIfStmt).getElse() = e and pred = "getElse()"
     or
+    s.(IfStmt).getInitialization() = e and pred = "getInitialization()"
+    or
     s.(IfStmt).getCondition() = e and pred = "getCondition()"
     or
     s.(IfStmt).getThen() = e and pred = "getThen()"
     or
     s.(IfStmt).getElse() = e and pred = "getElse()"
     or
+    s.(SwitchStmt).getInitialization() = e and pred = "getInitialization()"
+    or
     s.(SwitchStmt).getExpr() = e and pred = "getExpr()"
     or
     s.(SwitchStmt).getStmt() = e and pred = "getStmt()"

cpp/ql/lib/semmle/code/cpp/commons/Buffer.qll

@@ -10,11 +10,18 @@ import semmle.code.cpp.dataflow.DataFlow
  *   char data[1]; // v
  * };
  * ```
- * This requires that `v` is an array of size 0 or 1.
+ * or
+ * ```
+ * struct myStruct { // c
+ *   int amount;
+ *   char data[]; // v
+ * };
+ * ```
+ * This requires that `v` is an array of size 0 or 1, or that the array has no size.
  */
 predicate memberMayBeVarSize(Class c, MemberVariable v) {
   c = v.getDeclaringType() and
-  v.getUnspecifiedType().(ArrayType).getArraySize() <= 1
+  exists(ArrayType t | t = v.getUnspecifiedType() | not t.getArraySize() > 1)
 }
 
 /**
@@ -27,11 +34,11 @@ int getBufferSize(Expr bufferExpr, Element why) {
     result = bufferVar.getUnspecifiedType().(ArrayType).getSize() and
     why = bufferVar and
     not memberMayBeVarSize(_, bufferVar) and
-    not result = 0 // zero sized arrays are likely to have special usage, for example
+    // zero sized arrays are likely to have special usage, for example
-    or
     // behaving a bit like a 'union' overlapping other fields.
-    // buffer is an initialized array
+    not result = 0
-    //  e.g. int buffer[] = {1, 2, 3};
+    or
+    // buffer is an initialized array, e.g., int buffer[] = {1, 2, 3};
     why = bufferVar.getInitializer().getExpr() and
     (
       why instanceof AggregateLiteral or
@@ -40,13 +47,18 @@ int getBufferSize(Expr bufferExpr, Element why) {
     result = why.(Expr).getType().(ArrayType).getSize() and
     not exists(bufferVar.getUnspecifiedType().(ArrayType).getSize())
     or
-    exists(Class parentClass, VariableAccess parentPtr |
+    exists(Class parentClass, VariableAccess parentPtr, int bufferSize |
       // buffer is the parentPtr->bufferVar of a 'variable size struct'
       memberMayBeVarSize(parentClass, bufferVar) and
       why = bufferVar and
       parentPtr = bufferExpr.(VariableAccess).getQualifier() and
       parentPtr.getTarget().getUnspecifiedType().(PointerType).getBaseType() = parentClass and
-      result = getBufferSize(parentPtr, _) + bufferVar.getType().getSize() - parentClass.getSize()
+      (
+        if exists(bufferVar.getType().getSize())
+        then bufferSize = bufferVar.getType().getSize()
+        else bufferSize = 0
+      ) and
+      result = getBufferSize(parentPtr, _) + bufferSize - parentClass.getSize()
     )
   )
   or

cpp/ql/lib/semmle/code/cpp/commons/Printf.qll

@@ -872,7 +872,7 @@ class FormatLiteral extends Literal {
 
   private Type getConversionType1(int n) {
     exists(string cnv | cnv = this.getConversionChar(n) |
-      cnv.regexpMatch("d|i") and
+      cnv = ["d", "i"] and
       result = this.getIntegralConversion(n) and
       not result.getUnderlyingType().(IntegralType).isExplicitlySigned() and
       not result.getUnderlyingType().(IntegralType).isExplicitlyUnsigned()
@@ -912,7 +912,7 @@ class FormatLiteral extends Literal {
 
   private Type getConversionType2(int n) {
     exists(string cnv | cnv = this.getConversionChar(n) |
-      cnv.regexpMatch("o|u|x|X") and
+      cnv = ["o", "u", "x", "X"] and
       result = this.getIntegralConversion(n) and
       result.getUnderlyingType().(IntegralType).isUnsigned()
     )
@@ -920,7 +920,7 @@ class FormatLiteral extends Literal {
 
   private Type getConversionType3(int n) {
     exists(string cnv | cnv = this.getConversionChar(n) |
-      cnv.regexpMatch("a|A|e|E|f|F|g|G") and result = this.getFloatingPointConversion(n)
+      cnv = ["a", "A", "e", "E", "f", "F", "g", "G"] and result = this.getFloatingPointConversion(n)
     )
   }
 
@@ -1312,7 +1312,7 @@ class FormatLiteral extends Literal {
         len =
           min(int v |
             v = this.getPrecision(n) or
-            v = this.getUse().getFormatArgument(n).(AnalysedString).getMaxLength() - 1 // (don't count null terminator)
+            v = this.getUse().getFormatArgument(n).(AnalyzedString).getMaxLength() - 1 // (don't count null terminator)
           ) and
         reason = TValueFlowAnalysis()
       )

cpp/ql/lib/semmle/code/cpp/commons/StringAnalysis.qll

@@ -27,11 +27,14 @@ predicate canValueFlow(Expr fromExpr, Expr toExpr) {
   fromExpr = toExpr.(ConditionalExpr).getElse()
 }
 
+/** DEPRECATED: Alias for AnalyzedString */
+deprecated class AnalysedString = AnalyzedString;
+
 /**
- * An analysed null terminated string.
+ * An analyzed null terminated string.
  */
-class AnalysedString extends Expr {
+class AnalyzedString extends Expr {
-  AnalysedString() {
+  AnalyzedString() {
     this.getUnspecifiedType() instanceof ArrayType or
     this.getUnspecifiedType() instanceof PointerType
   }
@@ -41,15 +44,15 @@ class AnalysedString extends Expr {
    * can be calculated.
    */
   int getMaxLength() {
-    // take the longest AnalysedString it's value could 'flow' from; however if even one doesn't
+    // take the longest AnalyzedString its value could 'flow' from; however if even one doesn't
     // return a value (this essentially means 'infinity') we can't return a value either.
     result =
-      max(AnalysedString expr, int toMax |
+      max(AnalyzedString expr, int toMax |
         canValueFlow*(expr, this) and toMax = expr.(StringLiteral).getOriginalLength()
       |
         toMax
       ) and // maximum length
-    forall(AnalysedString expr | canValueFlow(expr, this) | exists(expr.getMaxLength())) // all sources return a value (recursive)
+    forall(AnalyzedString expr | canValueFlow(expr, this) | exists(expr.getMaxLength())) // all sources return a value (recursive)
   }
 }
 

cpp/ql/lib/semmle/code/cpp/controlflow/internal/CFG.qll

@@ -708,30 +708,33 @@ private predicate straightLineSparse(Node scope, int i, Node ni, Spec spec) {
   or
   scope =
     any(SwitchStmt s |
+      // SwitchStmt [-> init] -> expr
       i = -1 and ni = s and spec.isAt()
       or
-      i = 0 and ni = s.getExpr() and spec.isAround()
+      i = 0 and ni = s.getInitialization() and spec.isAround()
+      or
+      i = 1 and ni = s.getExpr() and spec.isAround()
       or
       // If the switch body is not a block then this step is skipped, and the
       // expression jumps directly to the cases.
-      i = 1 and ni = s.getStmt().(BlockStmt) and spec.isAt()
+      i = 2 and ni = s.getStmt().(BlockStmt) and spec.isAt()
       or
-      i = 2 and ni = s.getASwitchCase() and spec.isBefore()
+      i = 3 and ni = s.getASwitchCase() and spec.isBefore()
       or
       // If there is no default case, we can jump to after the block. Note: `i`
       // is same value as above.
       not s.getASwitchCase() instanceof DefaultCase and
-      i = 2 and
+      i = 3 and
       ni = s.getStmt() and
       spec.isAfter()
       or
-      i = 3 and /* BARRIER */ ni = s and spec.isBarrier()
+      i = 4 and /* BARRIER */ ni = s and spec.isBarrier()
       or
-      i = 4 and ni = s.getStmt() and spec.isAfter()
+      i = 5 and ni = s.getStmt() and spec.isAfter()
       or
-      i = 5 and ni = s and spec.isAroundDestructors()
+      i = 6 and ni = s and spec.isAroundDestructors()
       or
-      i = 6 and ni = s and spec.isAfter()
+      i = 7 and ni = s and spec.isAfter()
     )
   or
   scope =
@@ -836,8 +839,15 @@ private predicate subEdge(Pos p1, Node n1, Node n2, Pos p2) {
     p2.nodeAt(n2, f)
   )
   or
-  // IfStmt -> condition ; { then, else } ->
+  // IfStmt -> [ init -> ] condition ; { then, else } ->
   exists(IfStmt s |
+    p1.nodeAt(n1, s) and
+    p2.nodeBefore(n2, s.getInitialization())
+    or
+    p1.nodeAfter(n1, s.getInitialization()) and
+    p2.nodeBefore(n2, s.getCondition())
+    or
+    not exists(s.getInitialization()) and
     p1.nodeAt(n1, s) and
     p2.nodeBefore(n2, s.getCondition())
     or
@@ -851,8 +861,15 @@ private predicate subEdge(Pos p1, Node n1, Node n2, Pos p2) {
     p2.nodeAfter(n2, s)
   )
   or
-  // ConstexprIfStmt -> condition ; { then, else } -> // same as IfStmt
+  // ConstexprIfStmt -> [ init -> ] condition ; { then, else } -> // same as IfStmt
   exists(ConstexprIfStmt s |
+    p1.nodeAt(n1, s) and
+    p2.nodeBefore(n2, s.getInitialization())
+    or
+    p1.nodeAfter(n1, s.getInitialization()) and
+    p2.nodeBefore(n2, s.getCondition())
+    or
+    not exists(s.getInitialization()) and
     p1.nodeAt(n1, s) and
     p2.nodeBefore(n2, s.getCondition())
     or
@@ -953,7 +970,7 @@ private predicate subEdge(Pos p1, Node n1, Node n2, Pos p2) {
 private predicate subEdgeIncludingDestructors(Pos p1, Node n1, Node n2, Pos p2) {
   subEdge(p1, n1, n2, p2)
   or
-  // If `n1` has sub-nodes to accomodate destructors, but there are none to be
+  // If `n1` has sub-nodes to accommodate destructors, but there are none to be
   // called, connect the "before destructors" node directly to the "after
   // destructors" node. For performance, only do this when the nodes exist.
   exists(Pos afterDtors | afterDtors.isAfterDestructors() | subEdge(afterDtors, n1, _, _)) and

cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl.qll

@@ -116,7 +116,7 @@ abstract class Configuration extends string {
    * Holds if an arbitrary number of implicit read steps of content `c` may be
    * taken at `node`.
    */
-  predicate allowImplicitRead(Node node, Content c) { none() }
+  predicate allowImplicitRead(Node node, ContentSet c) { none() }
 
   /**
    * Gets the virtual dispatch branching limit when calculating field flow.
@@ -170,6 +170,14 @@ abstract class Configuration extends string {
    */
   int explorationLimit() { none() }
 
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (for example in a `path-problem` query).
+   */
+  predicate includeHiddenNodes() { none() }
+
   /**
    * Holds if there is a partial data flow path from `source` to `node`. The
    * approximate distance between `node` and the closest source is `dist` and
@@ -485,8 +493,9 @@ private predicate additionalJumpStateStep(
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+pragma[nomagic]
-  read(node1.asNode(), c, node2.asNode()) and
+private predicate readSet(NodeEx node1, ContentSet c, NodeEx node2, Configuration config) {
+  readSet(node1.asNode(), c, node2.asNode()) and
   stepFilter(node1, node2, config)
   or
   exists(Node n |
@@ -496,6 +505,37 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate expectsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    expectsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+pragma[nomagic]
+private predicate notExpectsContent(NodeEx n) { not expectsContentCached(n.asNode(), _) }
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -573,9 +613,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
+    exists(ContentSet c |
-      fwdFlowRead(c, node, cc, config) and
+      fwdFlowReadSet(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -599,10 +639,10 @@ private module Stage1 {
   private predicate fwdFlow(NodeEx node, Configuration config) { fwdFlow(node, _, config) }
 
   pragma[nomagic]
-  private predicate fwdFlowRead(Content c, NodeEx node, Cc cc, Configuration config) {
+  private predicate fwdFlowReadSet(ContentSet c, NodeEx node, Cc cc, Configuration config) {
     exists(NodeEx mid |
       fwdFlow(mid, cc, config) and
-      read(mid, c, node, config)
+      readSet(mid, c, node, config)
     )
   }
 
@@ -620,6 +660,16 @@ private module Stage1 {
     )
   }
 
+  /**
+   * Holds if `cs` may be interpreted in a read as the target of some store
+   * into `c`, in the flow covered by `fwdFlow`.
+   */
+  pragma[nomagic]
+  private predicate fwdFlowConsCandSet(ContentSet cs, Content c, Configuration config) {
+    fwdFlowConsCand(c, config) and
+    c = cs.getAReadContent()
+  }
+
   pragma[nomagic]
   private predicate fwdFlowReturnPosition(ReturnPosition pos, Cc cc, Configuration config) {
     exists(RetNodeEx ret |
@@ -712,9 +762,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
+    exists(NodeEx mid, ContentSet c |
-      read(node, c, mid, config) and
+      readSet(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -740,10 +790,10 @@ private module Stage1 {
    */
   pragma[nomagic]
   private predicate revFlowConsCand(Content c, Configuration config) {
-    exists(NodeEx mid, NodeEx node |
+    exists(NodeEx mid, NodeEx node, ContentSet cs |
       fwdFlow(node, pragma[only_bind_into](config)) and
-      read(node, c, mid, config) and
+      readSet(node, cs, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -762,7 +812,8 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
-  private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
+  pragma[nomagic]
+  predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
   }
@@ -861,8 +912,8 @@ private module Stage1 {
   pragma[nomagic]
   predicate readStepCand(NodeEx n1, Content c, NodeEx n2, Configuration config) {
     revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
-    revFlow(n2, pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
-    read(n1, c, n2, pragma[only_bind_into](config))
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -872,7 +923,10 @@ private module Stage1 {
   predicate revFlow(
     NodeEx node, FlowState state, boolean toReturn, ApOption returnAp, Ap ap, Configuration config
   ) {
-    revFlow(node, toReturn, config) and exists(state) and exists(returnAp) and exists(ap)
+    revFlow(node, toReturn, pragma[only_bind_into](config)) and
+    exists(state) and
+    exists(returnAp) and
+    exists(ap)
   }
 
   private predicate throughFlowNodeCand(NodeEx node, Configuration config) {
@@ -1147,11 +1201,26 @@ private module Stage2 {
 
   private predicate flowIntoCall = flowIntoCallNodeCand1/5;
 
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c)
+    )
+  }
+
   bindingset[node, state, ap, config]
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
-    PrevStage::revFlowState(state, config) and
+    PrevStage::revFlowState(state, pragma[only_bind_into](config)) and
     exists(ap) and
-    not stateBarrier(node, state, config)
+    not stateBarrier(node, state, config) and
+    (
+      notExpectsContent(node)
+      or
+      ap = true and
+      expectsContentCand(node, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -1574,7 +1643,7 @@ private module Stage2 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -1612,10 +1681,24 @@ private module Stage2 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -1706,7 +1789,8 @@ private module LocalFlowBigStep {
   private class FlowCheckNode extends NodeEx {
     FlowCheckNode() {
       castNode(this.asNode()) or
-      clearsContentCached(this.asNode(), _)
+      clearsContentCached(this.asNode(), _) or
+      expectsContentCached(this.asNode(), _)
     }
   }
 
@@ -1729,9 +1813,9 @@ private module LocalFlowBigStep {
       or
       node.asNode() instanceof OutNodeExt
       or
-      store(_, _, node, _, config)
+      Stage2::storeStepCand(_, _, _, node, _, config)
       or
-      read(_, _, node, config)
+      Stage2::readStepCand(_, _, node, config)
       or
       node instanceof FlowCheckNode
       or
@@ -1752,8 +1836,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
+      Stage2::storeStepCand(node, _, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1926,7 +2010,34 @@ private module Stage3 {
   private predicate flowIntoCall = flowIntoCallNodeCand2/5;
 
   pragma[nomagic]
-  private predicate clear(NodeEx node, Ap ap) { ap.isClearedAt(node.asNode()) }
+  private predicate clearSet(NodeEx node, ContentSet c, Configuration config) {
+    PrevStage::revFlow(node, config) and
+    clearsContentCached(node.asNode(), c)
+  }
+
+  pragma[nomagic]
+  private predicate clearContent(NodeEx node, Content c, Configuration config) {
+    exists(ContentSet cs |
+      PrevStage::readStepCand(_, pragma[only_bind_into](c), _, pragma[only_bind_into](config)) and
+      c = cs.getAReadContent() and
+      clearSet(node, cs, pragma[only_bind_into](config))
+    )
+  }
+
+  pragma[nomagic]
+  private predicate clear(NodeEx node, Ap ap, Configuration config) {
+    clearContent(node, ap.getHead().getContent(), config)
+  }
+
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Ap ap, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::readStepCand(_, c, _, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c) and
+      c = ap.getHead().getContent()
+    )
+  }
 
   pragma[nomagic]
   private predicate castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1935,8 +2046,13 @@ private module Stage3 {
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
     exists(state) and
     exists(config) and
-    not clear(node, ap) and
+    not clear(node, ap, config) and
-    if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()
+    (if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()) and
+    (
+      notExpectsContent(node)
+      or
+      expectsContentCand(node, ap, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -2363,7 +2479,7 @@ private module Stage3 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -2401,10 +2517,24 @@ private module Stage3 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3190,7 +3320,7 @@ private module Stage4 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -3228,10 +3358,24 @@ private module Stage4 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3300,17 +3444,28 @@ private Configuration unbindConf(Configuration conf) {
   exists(Configuration c | result = pragma[only_bind_into](c) and conf = pragma[only_bind_into](c))
 }
 
-private predicate nodeMayUseSummary(
+pragma[nomagic]
-  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+private predicate nodeMayUseSummary0(
+  NodeEx n, DataFlowCallable c, FlowState state, AccessPathApprox apa, Configuration config
 ) {
-  exists(DataFlowCallable c, AccessPathApprox apa0 |
+  exists(AccessPathApprox apa0 |
-    Stage4::parameterMayFlowThrough(_, c, apa, _) and
+    Stage4::parameterMayFlowThrough(_, c, _, _) and
     Stage4::revFlow(n, state, true, _, apa0, config) and
     Stage4::fwdFlow(n, state, any(CallContextCall ccc), TAccessPathApproxSome(apa), apa0, config) and
     n.getEnclosingCallable() = c
   )
 }
 
+pragma[nomagic]
+private predicate nodeMayUseSummary(
+  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+) {
+  exists(DataFlowCallable c |
+    Stage4::parameterMayFlowThrough(_, c, apa, config) and
+    nodeMayUseSummary0(n, c, state, apa, config)
+  )
+}
+
 private newtype TSummaryCtx =
   TSummaryCtxNone() or
   TSummaryCtxSome(ParamNodeEx p, FlowState state, AccessPath ap) {
@@ -3506,7 +3661,7 @@ private newtype TPathNode =
  * of dereference operations needed to get from the value in the node to the
  * tracked object. The final type indicates the type of the tracked object.
  */
-abstract private class AccessPath extends TAccessPath {
+private class AccessPath extends TAccessPath {
   /** Gets the head of this access path, if any. */
   abstract TypedContent getHead();
 
@@ -3721,11 +3876,14 @@ abstract private class PathNodeImpl extends PathNode {
   abstract NodeEx getNodeEx();
 
   predicate isHidden() {
-    hiddenNode(this.getNodeEx().asNode()) and
+    not this.getConfiguration().includeHiddenNodes() and
-    not this.isSource() and
+    (
-    not this instanceof PathNodeSink
+      hiddenNode(this.getNodeEx().asNode()) and
-    or
+      not this.isSource() and
-    this.getNodeEx() instanceof TNodeImplicitRead
+      not this instanceof PathNodeSink
+      or
+      this.getNodeEx() instanceof TNodeImplicitRead
+    )
   }
 
   private string ppAp() {
@@ -4202,10 +4360,16 @@ private module Subpaths {
     exists(NodeEx n1, NodeEx n2 | n1 = n.getNodeEx() and n2 = result.getNodeEx() |
       localFlowBigStep(n1, _, n2, _, _, _, _, _) or
       store(n1, _, n2, _, _) or
-      read(n1, _, n2, _)
+      readSet(n1, _, n2, _)
     )
   }
 
+  pragma[nomagic]
+  private predicate hasSuccessor(PathNode pred, PathNodeMid succ, NodeEx succNode) {
+    succ = pred.getASuccessor() and
+    succNode = succ.getNodeEx()
+  }
+
   /**
    * Holds if `(arg, par, ret, out)` forms a subpath-tuple, that is, flow through
    * a subpath between `par` and `ret` with the connecting edges `arg -> par` and
@@ -4213,15 +4377,13 @@ private module Subpaths {
    */
   predicate subpaths(PathNode arg, PathNodeImpl par, PathNodeImpl ret, PathNode out) {
     exists(ParamNodeEx p, NodeEx o, FlowState sout, AccessPath apout, PathNodeMid out0 |
-      pragma[only_bind_into](arg).getASuccessor() = par and
+      pragma[only_bind_into](arg).getASuccessor() = pragma[only_bind_into](out0) and
-      pragma[only_bind_into](arg).getASuccessor() = out0 and
+      subpaths03(pragma[only_bind_into](arg), p, localStepToHidden*(ret), o, sout, apout) and
-      subpaths03(arg, p, localStepToHidden*(ret), o, sout, apout) and
+      hasSuccessor(pragma[only_bind_into](arg), par, p) and
       not ret.isHidden() and
-      par.getNodeEx() = p and
+      pathNode(out0, o, sout, _, _, apout, _, _)
-      out0.getNodeEx() = o and
+    |
-      out0.getState() = sout and
+      out = out0 or out = out0.projectToSink()
-      out0.getAp() = apout and
-      (out = out0 or out = out0.projectToSink())
     )
   }
 
@@ -4557,7 +4719,11 @@ private module FlowExploration {
       or
       exists(PartialPathNodeRev mid |
         revPartialPathStep(mid, node, state, sc1, sc2, sc3, ap, config) and
-        not clearsContentCached(node.asNode(), ap.getHead()) and
+        not clearsContentEx(node, ap.getHead()) and
+        (
+          notExpectsContent(node) or
+          expectsContentEx(node, ap.getHead())
+        ) and
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4573,7 +4739,11 @@ private module FlowExploration {
       partialPathStep(mid, node, state, cc, sc1, sc2, sc3, ap, config) and
       not fullBarrier(node, config) and
       not stateBarrier(node, state, config) and
-      not clearsContentCached(node.asNode(), ap.getHead().getContent()) and
+      not clearsContentEx(node, ap.getHead().getContent()) and
+      (
+        notExpectsContent(node) or
+        expectsContentEx(node, ap.getHead().getContent())
+      ) and
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()

cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl2.qll

@@ -116,7 +116,7 @@ abstract class Configuration extends string {
    * Holds if an arbitrary number of implicit read steps of content `c` may be
    * taken at `node`.
    */
-  predicate allowImplicitRead(Node node, Content c) { none() }
+  predicate allowImplicitRead(Node node, ContentSet c) { none() }
 
   /**
    * Gets the virtual dispatch branching limit when calculating field flow.
@@ -170,6 +170,14 @@ abstract class Configuration extends string {
    */
   int explorationLimit() { none() }
 
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (for example in a `path-problem` query).
+   */
+  predicate includeHiddenNodes() { none() }
+
   /**
    * Holds if there is a partial data flow path from `source` to `node`. The
    * approximate distance between `node` and the closest source is `dist` and
@@ -485,8 +493,9 @@ private predicate additionalJumpStateStep(
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+pragma[nomagic]
-  read(node1.asNode(), c, node2.asNode()) and
+private predicate readSet(NodeEx node1, ContentSet c, NodeEx node2, Configuration config) {
+  readSet(node1.asNode(), c, node2.asNode()) and
   stepFilter(node1, node2, config)
   or
   exists(Node n |
@@ -496,6 +505,37 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate expectsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    expectsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+pragma[nomagic]
+private predicate notExpectsContent(NodeEx n) { not expectsContentCached(n.asNode(), _) }
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -573,9 +613,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
+    exists(ContentSet c |
-      fwdFlowRead(c, node, cc, config) and
+      fwdFlowReadSet(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -599,10 +639,10 @@ private module Stage1 {
   private predicate fwdFlow(NodeEx node, Configuration config) { fwdFlow(node, _, config) }
 
   pragma[nomagic]
-  private predicate fwdFlowRead(Content c, NodeEx node, Cc cc, Configuration config) {
+  private predicate fwdFlowReadSet(ContentSet c, NodeEx node, Cc cc, Configuration config) {
     exists(NodeEx mid |
       fwdFlow(mid, cc, config) and
-      read(mid, c, node, config)
+      readSet(mid, c, node, config)
     )
   }
 
@@ -620,6 +660,16 @@ private module Stage1 {
     )
   }
 
+  /**
+   * Holds if `cs` may be interpreted in a read as the target of some store
+   * into `c`, in the flow covered by `fwdFlow`.
+   */
+  pragma[nomagic]
+  private predicate fwdFlowConsCandSet(ContentSet cs, Content c, Configuration config) {
+    fwdFlowConsCand(c, config) and
+    c = cs.getAReadContent()
+  }
+
   pragma[nomagic]
   private predicate fwdFlowReturnPosition(ReturnPosition pos, Cc cc, Configuration config) {
     exists(RetNodeEx ret |
@@ -712,9 +762,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
+    exists(NodeEx mid, ContentSet c |
-      read(node, c, mid, config) and
+      readSet(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -740,10 +790,10 @@ private module Stage1 {
    */
   pragma[nomagic]
   private predicate revFlowConsCand(Content c, Configuration config) {
-    exists(NodeEx mid, NodeEx node |
+    exists(NodeEx mid, NodeEx node, ContentSet cs |
       fwdFlow(node, pragma[only_bind_into](config)) and
-      read(node, c, mid, config) and
+      readSet(node, cs, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -762,7 +812,8 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
-  private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
+  pragma[nomagic]
+  predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
   }
@@ -861,8 +912,8 @@ private module Stage1 {
   pragma[nomagic]
   predicate readStepCand(NodeEx n1, Content c, NodeEx n2, Configuration config) {
     revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
-    revFlow(n2, pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
-    read(n1, c, n2, pragma[only_bind_into](config))
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -872,7 +923,10 @@ private module Stage1 {
   predicate revFlow(
     NodeEx node, FlowState state, boolean toReturn, ApOption returnAp, Ap ap, Configuration config
   ) {
-    revFlow(node, toReturn, config) and exists(state) and exists(returnAp) and exists(ap)
+    revFlow(node, toReturn, pragma[only_bind_into](config)) and
+    exists(state) and
+    exists(returnAp) and
+    exists(ap)
   }
 
   private predicate throughFlowNodeCand(NodeEx node, Configuration config) {
@@ -1147,11 +1201,26 @@ private module Stage2 {
 
   private predicate flowIntoCall = flowIntoCallNodeCand1/5;
 
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c)
+    )
+  }
+
   bindingset[node, state, ap, config]
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
-    PrevStage::revFlowState(state, config) and
+    PrevStage::revFlowState(state, pragma[only_bind_into](config)) and
     exists(ap) and
-    not stateBarrier(node, state, config)
+    not stateBarrier(node, state, config) and
+    (
+      notExpectsContent(node)
+      or
+      ap = true and
+      expectsContentCand(node, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -1574,7 +1643,7 @@ private module Stage2 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -1612,10 +1681,24 @@ private module Stage2 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -1706,7 +1789,8 @@ private module LocalFlowBigStep {
   private class FlowCheckNode extends NodeEx {
     FlowCheckNode() {
       castNode(this.asNode()) or
-      clearsContentCached(this.asNode(), _)
+      clearsContentCached(this.asNode(), _) or
+      expectsContentCached(this.asNode(), _)
     }
   }
 
@@ -1729,9 +1813,9 @@ private module LocalFlowBigStep {
       or
       node.asNode() instanceof OutNodeExt
       or
-      store(_, _, node, _, config)
+      Stage2::storeStepCand(_, _, _, node, _, config)
       or
-      read(_, _, node, config)
+      Stage2::readStepCand(_, _, node, config)
       or
       node instanceof FlowCheckNode
       or
@@ -1752,8 +1836,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
+      Stage2::storeStepCand(node, _, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1926,7 +2010,34 @@ private module Stage3 {
   private predicate flowIntoCall = flowIntoCallNodeCand2/5;
 
   pragma[nomagic]
-  private predicate clear(NodeEx node, Ap ap) { ap.isClearedAt(node.asNode()) }
+  private predicate clearSet(NodeEx node, ContentSet c, Configuration config) {
+    PrevStage::revFlow(node, config) and
+    clearsContentCached(node.asNode(), c)
+  }
+
+  pragma[nomagic]
+  private predicate clearContent(NodeEx node, Content c, Configuration config) {
+    exists(ContentSet cs |
+      PrevStage::readStepCand(_, pragma[only_bind_into](c), _, pragma[only_bind_into](config)) and
+      c = cs.getAReadContent() and
+      clearSet(node, cs, pragma[only_bind_into](config))
+    )
+  }
+
+  pragma[nomagic]
+  private predicate clear(NodeEx node, Ap ap, Configuration config) {
+    clearContent(node, ap.getHead().getContent(), config)
+  }
+
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Ap ap, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::readStepCand(_, c, _, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c) and
+      c = ap.getHead().getContent()
+    )
+  }
 
   pragma[nomagic]
   private predicate castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1935,8 +2046,13 @@ private module Stage3 {
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
     exists(state) and
     exists(config) and
-    not clear(node, ap) and
+    not clear(node, ap, config) and
-    if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()
+    (if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()) and
+    (
+      notExpectsContent(node)
+      or
+      expectsContentCand(node, ap, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -2363,7 +2479,7 @@ private module Stage3 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -2401,10 +2517,24 @@ private module Stage3 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3190,7 +3320,7 @@ private module Stage4 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -3228,10 +3358,24 @@ private module Stage4 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3300,17 +3444,28 @@ private Configuration unbindConf(Configuration conf) {
   exists(Configuration c | result = pragma[only_bind_into](c) and conf = pragma[only_bind_into](c))
 }
 
-private predicate nodeMayUseSummary(
+pragma[nomagic]
-  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+private predicate nodeMayUseSummary0(
+  NodeEx n, DataFlowCallable c, FlowState state, AccessPathApprox apa, Configuration config
 ) {
-  exists(DataFlowCallable c, AccessPathApprox apa0 |
+  exists(AccessPathApprox apa0 |
-    Stage4::parameterMayFlowThrough(_, c, apa, _) and
+    Stage4::parameterMayFlowThrough(_, c, _, _) and
     Stage4::revFlow(n, state, true, _, apa0, config) and
     Stage4::fwdFlow(n, state, any(CallContextCall ccc), TAccessPathApproxSome(apa), apa0, config) and
     n.getEnclosingCallable() = c
   )
 }
 
+pragma[nomagic]
+private predicate nodeMayUseSummary(
+  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+) {
+  exists(DataFlowCallable c |
+    Stage4::parameterMayFlowThrough(_, c, apa, config) and
+    nodeMayUseSummary0(n, c, state, apa, config)
+  )
+}
+
 private newtype TSummaryCtx =
   TSummaryCtxNone() or
   TSummaryCtxSome(ParamNodeEx p, FlowState state, AccessPath ap) {
@@ -3506,7 +3661,7 @@ private newtype TPathNode =
  * of dereference operations needed to get from the value in the node to the
  * tracked object. The final type indicates the type of the tracked object.
  */
-abstract private class AccessPath extends TAccessPath {
+private class AccessPath extends TAccessPath {
   /** Gets the head of this access path, if any. */
   abstract TypedContent getHead();
 
@@ -3721,11 +3876,14 @@ abstract private class PathNodeImpl extends PathNode {
   abstract NodeEx getNodeEx();
 
   predicate isHidden() {
-    hiddenNode(this.getNodeEx().asNode()) and
+    not this.getConfiguration().includeHiddenNodes() and
-    not this.isSource() and
+    (
-    not this instanceof PathNodeSink
+      hiddenNode(this.getNodeEx().asNode()) and
-    or
+      not this.isSource() and
-    this.getNodeEx() instanceof TNodeImplicitRead
+      not this instanceof PathNodeSink
+      or
+      this.getNodeEx() instanceof TNodeImplicitRead
+    )
   }
 
   private string ppAp() {
@@ -4202,10 +4360,16 @@ private module Subpaths {
     exists(NodeEx n1, NodeEx n2 | n1 = n.getNodeEx() and n2 = result.getNodeEx() |
       localFlowBigStep(n1, _, n2, _, _, _, _, _) or
       store(n1, _, n2, _, _) or
-      read(n1, _, n2, _)
+      readSet(n1, _, n2, _)
     )
   }
 
+  pragma[nomagic]
+  private predicate hasSuccessor(PathNode pred, PathNodeMid succ, NodeEx succNode) {
+    succ = pred.getASuccessor() and
+    succNode = succ.getNodeEx()
+  }
+
   /**
    * Holds if `(arg, par, ret, out)` forms a subpath-tuple, that is, flow through
    * a subpath between `par` and `ret` with the connecting edges `arg -> par` and
@@ -4213,15 +4377,13 @@ private module Subpaths {
    */
   predicate subpaths(PathNode arg, PathNodeImpl par, PathNodeImpl ret, PathNode out) {
     exists(ParamNodeEx p, NodeEx o, FlowState sout, AccessPath apout, PathNodeMid out0 |
-      pragma[only_bind_into](arg).getASuccessor() = par and
+      pragma[only_bind_into](arg).getASuccessor() = pragma[only_bind_into](out0) and
-      pragma[only_bind_into](arg).getASuccessor() = out0 and
+      subpaths03(pragma[only_bind_into](arg), p, localStepToHidden*(ret), o, sout, apout) and
-      subpaths03(arg, p, localStepToHidden*(ret), o, sout, apout) and
+      hasSuccessor(pragma[only_bind_into](arg), par, p) and
       not ret.isHidden() and
-      par.getNodeEx() = p and
+      pathNode(out0, o, sout, _, _, apout, _, _)
-      out0.getNodeEx() = o and
+    |
-      out0.getState() = sout and
+      out = out0 or out = out0.projectToSink()
-      out0.getAp() = apout and
-      (out = out0 or out = out0.projectToSink())
     )
   }
 
@@ -4557,7 +4719,11 @@ private module FlowExploration {
       or
       exists(PartialPathNodeRev mid |
         revPartialPathStep(mid, node, state, sc1, sc2, sc3, ap, config) and
-        not clearsContentCached(node.asNode(), ap.getHead()) and
+        not clearsContentEx(node, ap.getHead()) and
+        (
+          notExpectsContent(node) or
+          expectsContentEx(node, ap.getHead())
+        ) and
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4573,7 +4739,11 @@ private module FlowExploration {
       partialPathStep(mid, node, state, cc, sc1, sc2, sc3, ap, config) and
       not fullBarrier(node, config) and
       not stateBarrier(node, state, config) and
-      not clearsContentCached(node.asNode(), ap.getHead().getContent()) and
+      not clearsContentEx(node, ap.getHead().getContent()) and
+      (
+        notExpectsContent(node) or
+        expectsContentEx(node, ap.getHead().getContent())
+      ) and
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()

cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl3.qll

@@ -116,7 +116,7 @@ abstract class Configuration extends string {
    * Holds if an arbitrary number of implicit read steps of content `c` may be
    * taken at `node`.
    */
-  predicate allowImplicitRead(Node node, Content c) { none() }
+  predicate allowImplicitRead(Node node, ContentSet c) { none() }
 
   /**
    * Gets the virtual dispatch branching limit when calculating field flow.
@@ -170,6 +170,14 @@ abstract class Configuration extends string {
    */
   int explorationLimit() { none() }
 
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (for example in a `path-problem` query).
+   */
+  predicate includeHiddenNodes() { none() }
+
   /**
    * Holds if there is a partial data flow path from `source` to `node`. The
    * approximate distance between `node` and the closest source is `dist` and
@@ -485,8 +493,9 @@ private predicate additionalJumpStateStep(
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+pragma[nomagic]
-  read(node1.asNode(), c, node2.asNode()) and
+private predicate readSet(NodeEx node1, ContentSet c, NodeEx node2, Configuration config) {
+  readSet(node1.asNode(), c, node2.asNode()) and
   stepFilter(node1, node2, config)
   or
   exists(Node n |
@@ -496,6 +505,37 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate expectsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    expectsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+pragma[nomagic]
+private predicate notExpectsContent(NodeEx n) { not expectsContentCached(n.asNode(), _) }
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -573,9 +613,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
+    exists(ContentSet c |
-      fwdFlowRead(c, node, cc, config) and
+      fwdFlowReadSet(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -599,10 +639,10 @@ private module Stage1 {
   private predicate fwdFlow(NodeEx node, Configuration config) { fwdFlow(node, _, config) }
 
   pragma[nomagic]
-  private predicate fwdFlowRead(Content c, NodeEx node, Cc cc, Configuration config) {
+  private predicate fwdFlowReadSet(ContentSet c, NodeEx node, Cc cc, Configuration config) {
     exists(NodeEx mid |
       fwdFlow(mid, cc, config) and
-      read(mid, c, node, config)
+      readSet(mid, c, node, config)
     )
   }
 
@@ -620,6 +660,16 @@ private module Stage1 {
     )
   }
 
+  /**
+   * Holds if `cs` may be interpreted in a read as the target of some store
+   * into `c`, in the flow covered by `fwdFlow`.
+   */
+  pragma[nomagic]
+  private predicate fwdFlowConsCandSet(ContentSet cs, Content c, Configuration config) {
+    fwdFlowConsCand(c, config) and
+    c = cs.getAReadContent()
+  }
+
   pragma[nomagic]
   private predicate fwdFlowReturnPosition(ReturnPosition pos, Cc cc, Configuration config) {
     exists(RetNodeEx ret |
@@ -712,9 +762,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
+    exists(NodeEx mid, ContentSet c |
-      read(node, c, mid, config) and
+      readSet(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -740,10 +790,10 @@ private module Stage1 {
    */
   pragma[nomagic]
   private predicate revFlowConsCand(Content c, Configuration config) {
-    exists(NodeEx mid, NodeEx node |
+    exists(NodeEx mid, NodeEx node, ContentSet cs |
       fwdFlow(node, pragma[only_bind_into](config)) and
-      read(node, c, mid, config) and
+      readSet(node, cs, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -762,7 +812,8 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
-  private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
+  pragma[nomagic]
+  predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
   }
@@ -861,8 +912,8 @@ private module Stage1 {
   pragma[nomagic]
   predicate readStepCand(NodeEx n1, Content c, NodeEx n2, Configuration config) {
     revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
-    revFlow(n2, pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
-    read(n1, c, n2, pragma[only_bind_into](config))
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -872,7 +923,10 @@ private module Stage1 {
   predicate revFlow(
     NodeEx node, FlowState state, boolean toReturn, ApOption returnAp, Ap ap, Configuration config
   ) {
-    revFlow(node, toReturn, config) and exists(state) and exists(returnAp) and exists(ap)
+    revFlow(node, toReturn, pragma[only_bind_into](config)) and
+    exists(state) and
+    exists(returnAp) and
+    exists(ap)
   }
 
   private predicate throughFlowNodeCand(NodeEx node, Configuration config) {
@@ -1147,11 +1201,26 @@ private module Stage2 {
 
   private predicate flowIntoCall = flowIntoCallNodeCand1/5;
 
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c)
+    )
+  }
+
   bindingset[node, state, ap, config]
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
-    PrevStage::revFlowState(state, config) and
+    PrevStage::revFlowState(state, pragma[only_bind_into](config)) and
     exists(ap) and
-    not stateBarrier(node, state, config)
+    not stateBarrier(node, state, config) and
+    (
+      notExpectsContent(node)
+      or
+      ap = true and
+      expectsContentCand(node, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -1574,7 +1643,7 @@ private module Stage2 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -1612,10 +1681,24 @@ private module Stage2 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -1706,7 +1789,8 @@ private module LocalFlowBigStep {
   private class FlowCheckNode extends NodeEx {
     FlowCheckNode() {
       castNode(this.asNode()) or
-      clearsContentCached(this.asNode(), _)
+      clearsContentCached(this.asNode(), _) or
+      expectsContentCached(this.asNode(), _)
     }
   }
 
@@ -1729,9 +1813,9 @@ private module LocalFlowBigStep {
       or
       node.asNode() instanceof OutNodeExt
       or
-      store(_, _, node, _, config)
+      Stage2::storeStepCand(_, _, _, node, _, config)
       or
-      read(_, _, node, config)
+      Stage2::readStepCand(_, _, node, config)
       or
       node instanceof FlowCheckNode
       or
@@ -1752,8 +1836,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
+      Stage2::storeStepCand(node, _, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1926,7 +2010,34 @@ private module Stage3 {
   private predicate flowIntoCall = flowIntoCallNodeCand2/5;
 
   pragma[nomagic]
-  private predicate clear(NodeEx node, Ap ap) { ap.isClearedAt(node.asNode()) }
+  private predicate clearSet(NodeEx node, ContentSet c, Configuration config) {
+    PrevStage::revFlow(node, config) and
+    clearsContentCached(node.asNode(), c)
+  }
+
+  pragma[nomagic]
+  private predicate clearContent(NodeEx node, Content c, Configuration config) {
+    exists(ContentSet cs |
+      PrevStage::readStepCand(_, pragma[only_bind_into](c), _, pragma[only_bind_into](config)) and
+      c = cs.getAReadContent() and
+      clearSet(node, cs, pragma[only_bind_into](config))
+    )
+  }
+
+  pragma[nomagic]
+  private predicate clear(NodeEx node, Ap ap, Configuration config) {
+    clearContent(node, ap.getHead().getContent(), config)
+  }
+
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Ap ap, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::readStepCand(_, c, _, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c) and
+      c = ap.getHead().getContent()
+    )
+  }
 
   pragma[nomagic]
   private predicate castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1935,8 +2046,13 @@ private module Stage3 {
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
     exists(state) and
     exists(config) and
-    not clear(node, ap) and
+    not clear(node, ap, config) and
-    if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()
+    (if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()) and
+    (
+      notExpectsContent(node)
+      or
+      expectsContentCand(node, ap, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -2363,7 +2479,7 @@ private module Stage3 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -2401,10 +2517,24 @@ private module Stage3 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3190,7 +3320,7 @@ private module Stage4 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -3228,10 +3358,24 @@ private module Stage4 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3300,17 +3444,28 @@ private Configuration unbindConf(Configuration conf) {
   exists(Configuration c | result = pragma[only_bind_into](c) and conf = pragma[only_bind_into](c))
 }
 
-private predicate nodeMayUseSummary(
+pragma[nomagic]
-  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+private predicate nodeMayUseSummary0(
+  NodeEx n, DataFlowCallable c, FlowState state, AccessPathApprox apa, Configuration config
 ) {
-  exists(DataFlowCallable c, AccessPathApprox apa0 |
+  exists(AccessPathApprox apa0 |
-    Stage4::parameterMayFlowThrough(_, c, apa, _) and
+    Stage4::parameterMayFlowThrough(_, c, _, _) and
     Stage4::revFlow(n, state, true, _, apa0, config) and
     Stage4::fwdFlow(n, state, any(CallContextCall ccc), TAccessPathApproxSome(apa), apa0, config) and
     n.getEnclosingCallable() = c
   )
 }
 
+pragma[nomagic]
+private predicate nodeMayUseSummary(
+  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+) {
+  exists(DataFlowCallable c |
+    Stage4::parameterMayFlowThrough(_, c, apa, config) and
+    nodeMayUseSummary0(n, c, state, apa, config)
+  )
+}
+
 private newtype TSummaryCtx =
   TSummaryCtxNone() or
   TSummaryCtxSome(ParamNodeEx p, FlowState state, AccessPath ap) {
@@ -3506,7 +3661,7 @@ private newtype TPathNode =
  * of dereference operations needed to get from the value in the node to the
  * tracked object. The final type indicates the type of the tracked object.
  */
-abstract private class AccessPath extends TAccessPath {
+private class AccessPath extends TAccessPath {
   /** Gets the head of this access path, if any. */
   abstract TypedContent getHead();
 
@@ -3721,11 +3876,14 @@ abstract private class PathNodeImpl extends PathNode {
   abstract NodeEx getNodeEx();
 
   predicate isHidden() {
-    hiddenNode(this.getNodeEx().asNode()) and
+    not this.getConfiguration().includeHiddenNodes() and
-    not this.isSource() and
+    (
-    not this instanceof PathNodeSink
+      hiddenNode(this.getNodeEx().asNode()) and
-    or
+      not this.isSource() and
-    this.getNodeEx() instanceof TNodeImplicitRead
+      not this instanceof PathNodeSink
+      or
+      this.getNodeEx() instanceof TNodeImplicitRead
+    )
   }
 
   private string ppAp() {
@@ -4202,10 +4360,16 @@ private module Subpaths {
     exists(NodeEx n1, NodeEx n2 | n1 = n.getNodeEx() and n2 = result.getNodeEx() |
       localFlowBigStep(n1, _, n2, _, _, _, _, _) or
       store(n1, _, n2, _, _) or
-      read(n1, _, n2, _)
+      readSet(n1, _, n2, _)
     )
   }
 
+  pragma[nomagic]
+  private predicate hasSuccessor(PathNode pred, PathNodeMid succ, NodeEx succNode) {
+    succ = pred.getASuccessor() and
+    succNode = succ.getNodeEx()
+  }
+
   /**
    * Holds if `(arg, par, ret, out)` forms a subpath-tuple, that is, flow through
    * a subpath between `par` and `ret` with the connecting edges `arg -> par` and
@@ -4213,15 +4377,13 @@ private module Subpaths {
    */
   predicate subpaths(PathNode arg, PathNodeImpl par, PathNodeImpl ret, PathNode out) {
     exists(ParamNodeEx p, NodeEx o, FlowState sout, AccessPath apout, PathNodeMid out0 |
-      pragma[only_bind_into](arg).getASuccessor() = par and
+      pragma[only_bind_into](arg).getASuccessor() = pragma[only_bind_into](out0) and
-      pragma[only_bind_into](arg).getASuccessor() = out0 and
+      subpaths03(pragma[only_bind_into](arg), p, localStepToHidden*(ret), o, sout, apout) and
-      subpaths03(arg, p, localStepToHidden*(ret), o, sout, apout) and
+      hasSuccessor(pragma[only_bind_into](arg), par, p) and
       not ret.isHidden() and
-      par.getNodeEx() = p and
+      pathNode(out0, o, sout, _, _, apout, _, _)
-      out0.getNodeEx() = o and
+    |
-      out0.getState() = sout and
+      out = out0 or out = out0.projectToSink()
-      out0.getAp() = apout and
-      (out = out0 or out = out0.projectToSink())
     )
   }
 
@@ -4557,7 +4719,11 @@ private module FlowExploration {
       or
       exists(PartialPathNodeRev mid |
         revPartialPathStep(mid, node, state, sc1, sc2, sc3, ap, config) and
-        not clearsContentCached(node.asNode(), ap.getHead()) and
+        not clearsContentEx(node, ap.getHead()) and
+        (
+          notExpectsContent(node) or
+          expectsContentEx(node, ap.getHead())
+        ) and
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4573,7 +4739,11 @@ private module FlowExploration {
       partialPathStep(mid, node, state, cc, sc1, sc2, sc3, ap, config) and
       not fullBarrier(node, config) and
       not stateBarrier(node, state, config) and
-      not clearsContentCached(node.asNode(), ap.getHead().getContent()) and
+      not clearsContentEx(node, ap.getHead().getContent()) and
+      (
+        notExpectsContent(node) or
+        expectsContentEx(node, ap.getHead().getContent())
+      ) and
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()

cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl4.qll

@@ -116,7 +116,7 @@ abstract class Configuration extends string {
    * Holds if an arbitrary number of implicit read steps of content `c` may be
    * taken at `node`.
    */
-  predicate allowImplicitRead(Node node, Content c) { none() }
+  predicate allowImplicitRead(Node node, ContentSet c) { none() }
 
   /**
    * Gets the virtual dispatch branching limit when calculating field flow.
@@ -170,6 +170,14 @@ abstract class Configuration extends string {
    */
   int explorationLimit() { none() }
 
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (for example in a `path-problem` query).
+   */
+  predicate includeHiddenNodes() { none() }
+
   /**
    * Holds if there is a partial data flow path from `source` to `node`. The
    * approximate distance between `node` and the closest source is `dist` and
@@ -485,8 +493,9 @@ private predicate additionalJumpStateStep(
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+pragma[nomagic]
-  read(node1.asNode(), c, node2.asNode()) and
+private predicate readSet(NodeEx node1, ContentSet c, NodeEx node2, Configuration config) {
+  readSet(node1.asNode(), c, node2.asNode()) and
   stepFilter(node1, node2, config)
   or
   exists(Node n |
@@ -496,6 +505,37 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate expectsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    expectsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+pragma[nomagic]
+private predicate notExpectsContent(NodeEx n) { not expectsContentCached(n.asNode(), _) }
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -573,9 +613,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
+    exists(ContentSet c |
-      fwdFlowRead(c, node, cc, config) and
+      fwdFlowReadSet(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -599,10 +639,10 @@ private module Stage1 {
   private predicate fwdFlow(NodeEx node, Configuration config) { fwdFlow(node, _, config) }
 
   pragma[nomagic]
-  private predicate fwdFlowRead(Content c, NodeEx node, Cc cc, Configuration config) {
+  private predicate fwdFlowReadSet(ContentSet c, NodeEx node, Cc cc, Configuration config) {
     exists(NodeEx mid |
       fwdFlow(mid, cc, config) and
-      read(mid, c, node, config)
+      readSet(mid, c, node, config)
     )
   }
 
@@ -620,6 +660,16 @@ private module Stage1 {
     )
   }
 
+  /**
+   * Holds if `cs` may be interpreted in a read as the target of some store
+   * into `c`, in the flow covered by `fwdFlow`.
+   */
+  pragma[nomagic]
+  private predicate fwdFlowConsCandSet(ContentSet cs, Content c, Configuration config) {
+    fwdFlowConsCand(c, config) and
+    c = cs.getAReadContent()
+  }
+
   pragma[nomagic]
   private predicate fwdFlowReturnPosition(ReturnPosition pos, Cc cc, Configuration config) {
     exists(RetNodeEx ret |
@@ -712,9 +762,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
+    exists(NodeEx mid, ContentSet c |
-      read(node, c, mid, config) and
+      readSet(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -740,10 +790,10 @@ private module Stage1 {
    */
   pragma[nomagic]
   private predicate revFlowConsCand(Content c, Configuration config) {
-    exists(NodeEx mid, NodeEx node |
+    exists(NodeEx mid, NodeEx node, ContentSet cs |
       fwdFlow(node, pragma[only_bind_into](config)) and
-      read(node, c, mid, config) and
+      readSet(node, cs, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -762,7 +812,8 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
-  private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
+  pragma[nomagic]
+  predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
   }
@@ -861,8 +912,8 @@ private module Stage1 {
   pragma[nomagic]
   predicate readStepCand(NodeEx n1, Content c, NodeEx n2, Configuration config) {
     revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
-    revFlow(n2, pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
-    read(n1, c, n2, pragma[only_bind_into](config))
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -872,7 +923,10 @@ private module Stage1 {
   predicate revFlow(
     NodeEx node, FlowState state, boolean toReturn, ApOption returnAp, Ap ap, Configuration config
   ) {
-    revFlow(node, toReturn, config) and exists(state) and exists(returnAp) and exists(ap)
+    revFlow(node, toReturn, pragma[only_bind_into](config)) and
+    exists(state) and
+    exists(returnAp) and
+    exists(ap)
   }
 
   private predicate throughFlowNodeCand(NodeEx node, Configuration config) {
@@ -1147,11 +1201,26 @@ private module Stage2 {
 
   private predicate flowIntoCall = flowIntoCallNodeCand1/5;
 
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c)
+    )
+  }
+
   bindingset[node, state, ap, config]
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
-    PrevStage::revFlowState(state, config) and
+    PrevStage::revFlowState(state, pragma[only_bind_into](config)) and
     exists(ap) and
-    not stateBarrier(node, state, config)
+    not stateBarrier(node, state, config) and
+    (
+      notExpectsContent(node)
+      or
+      ap = true and
+      expectsContentCand(node, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -1574,7 +1643,7 @@ private module Stage2 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -1612,10 +1681,24 @@ private module Stage2 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -1706,7 +1789,8 @@ private module LocalFlowBigStep {
   private class FlowCheckNode extends NodeEx {
     FlowCheckNode() {
       castNode(this.asNode()) or
-      clearsContentCached(this.asNode(), _)
+      clearsContentCached(this.asNode(), _) or
+      expectsContentCached(this.asNode(), _)
     }
   }
 
@@ -1729,9 +1813,9 @@ private module LocalFlowBigStep {
       or
       node.asNode() instanceof OutNodeExt
       or
-      store(_, _, node, _, config)
+      Stage2::storeStepCand(_, _, _, node, _, config)
       or
-      read(_, _, node, config)
+      Stage2::readStepCand(_, _, node, config)
       or
       node instanceof FlowCheckNode
       or
@@ -1752,8 +1836,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
+      Stage2::storeStepCand(node, _, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1926,7 +2010,34 @@ private module Stage3 {
   private predicate flowIntoCall = flowIntoCallNodeCand2/5;
 
   pragma[nomagic]
-  private predicate clear(NodeEx node, Ap ap) { ap.isClearedAt(node.asNode()) }
+  private predicate clearSet(NodeEx node, ContentSet c, Configuration config) {
+    PrevStage::revFlow(node, config) and
+    clearsContentCached(node.asNode(), c)
+  }
+
+  pragma[nomagic]
+  private predicate clearContent(NodeEx node, Content c, Configuration config) {
+    exists(ContentSet cs |
+      PrevStage::readStepCand(_, pragma[only_bind_into](c), _, pragma[only_bind_into](config)) and
+      c = cs.getAReadContent() and
+      clearSet(node, cs, pragma[only_bind_into](config))
+    )
+  }
+
+  pragma[nomagic]
+  private predicate clear(NodeEx node, Ap ap, Configuration config) {
+    clearContent(node, ap.getHead().getContent(), config)
+  }
+
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Ap ap, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::readStepCand(_, c, _, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c) and
+      c = ap.getHead().getContent()
+    )
+  }
 
   pragma[nomagic]
   private predicate castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1935,8 +2046,13 @@ private module Stage3 {
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
     exists(state) and
     exists(config) and
-    not clear(node, ap) and
+    not clear(node, ap, config) and
-    if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()
+    (if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()) and
+    (
+      notExpectsContent(node)
+      or
+      expectsContentCand(node, ap, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -2363,7 +2479,7 @@ private module Stage3 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -2401,10 +2517,24 @@ private module Stage3 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3190,7 +3320,7 @@ private module Stage4 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -3228,10 +3358,24 @@ private module Stage4 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3300,17 +3444,28 @@ private Configuration unbindConf(Configuration conf) {
   exists(Configuration c | result = pragma[only_bind_into](c) and conf = pragma[only_bind_into](c))
 }
 
-private predicate nodeMayUseSummary(
+pragma[nomagic]
-  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+private predicate nodeMayUseSummary0(
+  NodeEx n, DataFlowCallable c, FlowState state, AccessPathApprox apa, Configuration config
 ) {
-  exists(DataFlowCallable c, AccessPathApprox apa0 |
+  exists(AccessPathApprox apa0 |
-    Stage4::parameterMayFlowThrough(_, c, apa, _) and
+    Stage4::parameterMayFlowThrough(_, c, _, _) and
     Stage4::revFlow(n, state, true, _, apa0, config) and
     Stage4::fwdFlow(n, state, any(CallContextCall ccc), TAccessPathApproxSome(apa), apa0, config) and
     n.getEnclosingCallable() = c
   )
 }
 
+pragma[nomagic]
+private predicate nodeMayUseSummary(
+  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+) {
+  exists(DataFlowCallable c |
+    Stage4::parameterMayFlowThrough(_, c, apa, config) and
+    nodeMayUseSummary0(n, c, state, apa, config)
+  )
+}
+
 private newtype TSummaryCtx =
   TSummaryCtxNone() or
   TSummaryCtxSome(ParamNodeEx p, FlowState state, AccessPath ap) {
@@ -3506,7 +3661,7 @@ private newtype TPathNode =
  * of dereference operations needed to get from the value in the node to the
  * tracked object. The final type indicates the type of the tracked object.
  */
-abstract private class AccessPath extends TAccessPath {
+private class AccessPath extends TAccessPath {
   /** Gets the head of this access path, if any. */
   abstract TypedContent getHead();
 
@@ -3721,11 +3876,14 @@ abstract private class PathNodeImpl extends PathNode {
   abstract NodeEx getNodeEx();
 
   predicate isHidden() {
-    hiddenNode(this.getNodeEx().asNode()) and
+    not this.getConfiguration().includeHiddenNodes() and
-    not this.isSource() and
+    (
-    not this instanceof PathNodeSink
+      hiddenNode(this.getNodeEx().asNode()) and
-    or
+      not this.isSource() and
-    this.getNodeEx() instanceof TNodeImplicitRead
+      not this instanceof PathNodeSink
+      or
+      this.getNodeEx() instanceof TNodeImplicitRead
+    )
   }
 
   private string ppAp() {
@@ -4202,10 +4360,16 @@ private module Subpaths {
     exists(NodeEx n1, NodeEx n2 | n1 = n.getNodeEx() and n2 = result.getNodeEx() |
       localFlowBigStep(n1, _, n2, _, _, _, _, _) or
       store(n1, _, n2, _, _) or
-      read(n1, _, n2, _)
+      readSet(n1, _, n2, _)
     )
   }
 
+  pragma[nomagic]
+  private predicate hasSuccessor(PathNode pred, PathNodeMid succ, NodeEx succNode) {
+    succ = pred.getASuccessor() and
+    succNode = succ.getNodeEx()
+  }
+
   /**
    * Holds if `(arg, par, ret, out)` forms a subpath-tuple, that is, flow through
    * a subpath between `par` and `ret` with the connecting edges `arg -> par` and
@@ -4213,15 +4377,13 @@ private module Subpaths {
    */
   predicate subpaths(PathNode arg, PathNodeImpl par, PathNodeImpl ret, PathNode out) {
     exists(ParamNodeEx p, NodeEx o, FlowState sout, AccessPath apout, PathNodeMid out0 |
-      pragma[only_bind_into](arg).getASuccessor() = par and
+      pragma[only_bind_into](arg).getASuccessor() = pragma[only_bind_into](out0) and
-      pragma[only_bind_into](arg).getASuccessor() = out0 and
+      subpaths03(pragma[only_bind_into](arg), p, localStepToHidden*(ret), o, sout, apout) and
-      subpaths03(arg, p, localStepToHidden*(ret), o, sout, apout) and
+      hasSuccessor(pragma[only_bind_into](arg), par, p) and
       not ret.isHidden() and
-      par.getNodeEx() = p and
+      pathNode(out0, o, sout, _, _, apout, _, _)
-      out0.getNodeEx() = o and
+    |
-      out0.getState() = sout and
+      out = out0 or out = out0.projectToSink()
-      out0.getAp() = apout and
-      (out = out0 or out = out0.projectToSink())
     )
   }
 
@@ -4557,7 +4719,11 @@ private module FlowExploration {
       or
       exists(PartialPathNodeRev mid |
         revPartialPathStep(mid, node, state, sc1, sc2, sc3, ap, config) and
-        not clearsContentCached(node.asNode(), ap.getHead()) and
+        not clearsContentEx(node, ap.getHead()) and
+        (
+          notExpectsContent(node) or
+          expectsContentEx(node, ap.getHead())
+        ) and
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4573,7 +4739,11 @@ private module FlowExploration {
       partialPathStep(mid, node, state, cc, sc1, sc2, sc3, ap, config) and
       not fullBarrier(node, config) and
       not stateBarrier(node, state, config) and
-      not clearsContentCached(node.asNode(), ap.getHead().getContent()) and
+      not clearsContentEx(node, ap.getHead().getContent()) and
+      (
+        notExpectsContent(node) or
+        expectsContentEx(node, ap.getHead().getContent())
+      ) and
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()

cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImplCommon.qll

@@ -216,10 +216,9 @@ private module LambdaFlow {
     or
     // jump step
     exists(Node mid, DataFlowType t0 |
-      revLambdaFlow(lambdaCall, kind, mid, t0, _, _, _) and
+      revLambdaFlow(lambdaCall, kind, mid, t0, _, _, lastCall) and
       toReturn = false and
-      toJump = true and
+      toJump = true
-      lastCall = TDataFlowCallNone()
     |
       jumpStepCached(node, mid) and
       t = t0
@@ -305,7 +304,7 @@ cached
 private module Cached {
   /**
    * If needed, call this predicate from `DataFlowImplSpecific.qll` in order to
-   * force a stage-dependency on the `DataFlowImplCommon.qll` stage and therby
+   * force a stage-dependency on the `DataFlowImplCommon.qll` stage and thereby
    * collapsing the two stages.
    */
   cached
@@ -326,7 +325,10 @@ private module Cached {
   predicate jumpStepCached(Node node1, Node node2) { jumpStep(node1, node2) }
 
   cached
-  predicate clearsContentCached(Node n, Content c) { clearsContent(n, c) }
+  predicate clearsContentCached(Node n, ContentSet c) { clearsContent(n, c) }
+
+  cached
+  predicate expectsContentCached(Node n, ContentSet c) { expectsContent(n, c) }
 
   cached
   predicate isUnreachableInCallCached(Node n, DataFlowCall call) { isUnreachableInCall(n, call) }
@@ -373,7 +375,7 @@ private module Cached {
     // For reads, `x.f`, we want to check that the tracked type after the read (which
     // is obtained by popping the head of the access path stack) is compatible with
     // the type of `x.f`.
-    read(_, _, n)
+    readSet(_, _, n)
   }
 
   cached
@@ -469,7 +471,7 @@ private module Cached {
         // read
         exists(Node mid |
           parameterValueFlowCand(p, mid, false) and
-          read(mid, _, node) and
+          readSet(mid, _, node) and
           read = true
         )
         or
@@ -657,8 +659,10 @@ private module Cached {
        * Holds if `arg` flows to `out` through a call using only
        * value-preserving steps and a single read step, not taking call
        * contexts into account, thus representing a getter-step.
+       *
+       * This predicate is exposed for testing only.
        */
-      predicate getterStep(ArgNode arg, Content c, Node out) {
+      predicate getterStep(ArgNode arg, ContentSet c, Node out) {
         argumentValueFlowsThrough(arg, TReadStepTypesSome(_, c, _), out)
       }
 
@@ -781,8 +785,12 @@ private module Cached {
     parameterValueFlow(p, n.getPreUpdateNode(), TReadStepTypesNone())
   }
 
-  private predicate store(
+  cached
-    Node node1, Content c, Node node2, DataFlowType contentType, DataFlowType containerType
+  predicate readSet(Node node1, ContentSet c, Node node2) { readStep(node1, c, node2) }
+
+  cached
+  predicate storeSet(
+    Node node1, ContentSet c, Node node2, DataFlowType contentType, DataFlowType containerType
   ) {
     storeStep(node1, c, node2) and
     contentType = getNodeDataFlowType(node1) and
@@ -794,14 +802,19 @@ private module Cached {
     |
       argumentValueFlowsThrough(n2, TReadStepTypesSome(containerType, c, contentType), n1)
       or
-      read(n2, c, n1) and
+      readSet(n2, c, n1) and
       contentType = getNodeDataFlowType(n1) and
       containerType = getNodeDataFlowType(n2)
     )
   }
 
-  cached
+  private predicate store(
-  predicate read(Node node1, Content c, Node node2) { readStep(node1, c, node2) }
+    Node node1, Content c, Node node2, DataFlowType contentType, DataFlowType containerType
+  ) {
+    exists(ContentSet cs |
+      c = cs.getAStoreContent() and storeSet(node1, cs, node2, contentType, containerType)
+    )
+  }
 
   /**
    * Holds if data can flow from `node1` to `node2` via a direct assignment to
@@ -932,16 +945,16 @@ class CastingNode extends Node {
 }
 
 private predicate readStepWithTypes(
-  Node n1, DataFlowType container, Content c, Node n2, DataFlowType content
+  Node n1, DataFlowType container, ContentSet c, Node n2, DataFlowType content
 ) {
-  read(n1, c, n2) and
+  readSet(n1, c, n2) and
   container = getNodeDataFlowType(n1) and
   content = getNodeDataFlowType(n2)
 }
 
 private newtype TReadStepTypesOption =
   TReadStepTypesNone() or
-  TReadStepTypesSome(DataFlowType container, Content c, DataFlowType content) {
+  TReadStepTypesSome(DataFlowType container, ContentSet c, DataFlowType content) {
     readStepWithTypes(_, container, c, _, content)
   }
 
@@ -950,7 +963,7 @@ private class ReadStepTypesOption extends TReadStepTypesOption {
 
   DataFlowType getContainerType() { this = TReadStepTypesSome(result, _, _) }
 
-  Content getContent() { this = TReadStepTypesSome(_, result, _) }
+  ContentSet getContent() { this = TReadStepTypesSome(_, result, _) }
 
   DataFlowType getContentType() { this = TReadStepTypesSome(_, _, result) }
 
@@ -1325,8 +1338,6 @@ abstract class AccessPathFront extends TAccessPathFront {
   abstract boolean toBoolNonEmpty();
 
   TypedContent getHead() { this = TFrontHead(result) }
-
-  predicate isClearedAt(Node n) { clearsContentCached(n, this.getHead().getContent()) }
 }
 
 class AccessPathFrontNil extends AccessPathFront, TFrontNil {

cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImplLocal.qll

@@ -116,7 +116,7 @@ abstract class Configuration extends string {
    * Holds if an arbitrary number of implicit read steps of content `c` may be
    * taken at `node`.
    */
-  predicate allowImplicitRead(Node node, Content c) { none() }
+  predicate allowImplicitRead(Node node, ContentSet c) { none() }
 
   /**
    * Gets the virtual dispatch branching limit when calculating field flow.
@@ -170,6 +170,14 @@ abstract class Configuration extends string {
    */
   int explorationLimit() { none() }
 
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (for example in a `path-problem` query).
+   */
+  predicate includeHiddenNodes() { none() }
+
   /**
    * Holds if there is a partial data flow path from `source` to `node`. The
    * approximate distance between `node` and the closest source is `dist` and
@@ -485,8 +493,9 @@ private predicate additionalJumpStateStep(
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+pragma[nomagic]
-  read(node1.asNode(), c, node2.asNode()) and
+private predicate readSet(NodeEx node1, ContentSet c, NodeEx node2, Configuration config) {
+  readSet(node1.asNode(), c, node2.asNode()) and
   stepFilter(node1, node2, config)
   or
   exists(Node n |
@@ -496,6 +505,37 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate expectsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    expectsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+pragma[nomagic]
+private predicate notExpectsContent(NodeEx n) { not expectsContentCached(n.asNode(), _) }
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -573,9 +613,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
+    exists(ContentSet c |
-      fwdFlowRead(c, node, cc, config) and
+      fwdFlowReadSet(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -599,10 +639,10 @@ private module Stage1 {
   private predicate fwdFlow(NodeEx node, Configuration config) { fwdFlow(node, _, config) }
 
   pragma[nomagic]
-  private predicate fwdFlowRead(Content c, NodeEx node, Cc cc, Configuration config) {
+  private predicate fwdFlowReadSet(ContentSet c, NodeEx node, Cc cc, Configuration config) {
     exists(NodeEx mid |
       fwdFlow(mid, cc, config) and
-      read(mid, c, node, config)
+      readSet(mid, c, node, config)
     )
   }
 
@@ -620,6 +660,16 @@ private module Stage1 {
     )
   }
 
+  /**
+   * Holds if `cs` may be interpreted in a read as the target of some store
+   * into `c`, in the flow covered by `fwdFlow`.
+   */
+  pragma[nomagic]
+  private predicate fwdFlowConsCandSet(ContentSet cs, Content c, Configuration config) {
+    fwdFlowConsCand(c, config) and
+    c = cs.getAReadContent()
+  }
+
   pragma[nomagic]
   private predicate fwdFlowReturnPosition(ReturnPosition pos, Cc cc, Configuration config) {
     exists(RetNodeEx ret |
@@ -712,9 +762,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
+    exists(NodeEx mid, ContentSet c |
-      read(node, c, mid, config) and
+      readSet(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -740,10 +790,10 @@ private module Stage1 {
    */
   pragma[nomagic]
   private predicate revFlowConsCand(Content c, Configuration config) {
-    exists(NodeEx mid, NodeEx node |
+    exists(NodeEx mid, NodeEx node, ContentSet cs |
       fwdFlow(node, pragma[only_bind_into](config)) and
-      read(node, c, mid, config) and
+      readSet(node, cs, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -762,7 +812,8 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
-  private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
+  pragma[nomagic]
+  predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
   }
@@ -861,8 +912,8 @@ private module Stage1 {
   pragma[nomagic]
   predicate readStepCand(NodeEx n1, Content c, NodeEx n2, Configuration config) {
     revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
-    revFlow(n2, pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
-    read(n1, c, n2, pragma[only_bind_into](config))
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -872,7 +923,10 @@ private module Stage1 {
   predicate revFlow(
     NodeEx node, FlowState state, boolean toReturn, ApOption returnAp, Ap ap, Configuration config
   ) {
-    revFlow(node, toReturn, config) and exists(state) and exists(returnAp) and exists(ap)
+    revFlow(node, toReturn, pragma[only_bind_into](config)) and
+    exists(state) and
+    exists(returnAp) and
+    exists(ap)
   }
 
   private predicate throughFlowNodeCand(NodeEx node, Configuration config) {
@@ -1147,11 +1201,26 @@ private module Stage2 {
 
   private predicate flowIntoCall = flowIntoCallNodeCand1/5;
 
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c)
+    )
+  }
+
   bindingset[node, state, ap, config]
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
-    PrevStage::revFlowState(state, config) and
+    PrevStage::revFlowState(state, pragma[only_bind_into](config)) and
     exists(ap) and
-    not stateBarrier(node, state, config)
+    not stateBarrier(node, state, config) and
+    (
+      notExpectsContent(node)
+      or
+      ap = true and
+      expectsContentCand(node, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -1574,7 +1643,7 @@ private module Stage2 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -1612,10 +1681,24 @@ private module Stage2 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -1706,7 +1789,8 @@ private module LocalFlowBigStep {
   private class FlowCheckNode extends NodeEx {
     FlowCheckNode() {
       castNode(this.asNode()) or
-      clearsContentCached(this.asNode(), _)
+      clearsContentCached(this.asNode(), _) or
+      expectsContentCached(this.asNode(), _)
     }
   }
 
@@ -1729,9 +1813,9 @@ private module LocalFlowBigStep {
       or
       node.asNode() instanceof OutNodeExt
       or
-      store(_, _, node, _, config)
+      Stage2::storeStepCand(_, _, _, node, _, config)
       or
-      read(_, _, node, config)
+      Stage2::readStepCand(_, _, node, config)
       or
       node instanceof FlowCheckNode
       or
@@ -1752,8 +1836,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
+      Stage2::storeStepCand(node, _, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1926,7 +2010,34 @@ private module Stage3 {
   private predicate flowIntoCall = flowIntoCallNodeCand2/5;
 
   pragma[nomagic]
-  private predicate clear(NodeEx node, Ap ap) { ap.isClearedAt(node.asNode()) }
+  private predicate clearSet(NodeEx node, ContentSet c, Configuration config) {
+    PrevStage::revFlow(node, config) and
+    clearsContentCached(node.asNode(), c)
+  }
+
+  pragma[nomagic]
+  private predicate clearContent(NodeEx node, Content c, Configuration config) {
+    exists(ContentSet cs |
+      PrevStage::readStepCand(_, pragma[only_bind_into](c), _, pragma[only_bind_into](config)) and
+      c = cs.getAReadContent() and
+      clearSet(node, cs, pragma[only_bind_into](config))
+    )
+  }
+
+  pragma[nomagic]
+  private predicate clear(NodeEx node, Ap ap, Configuration config) {
+    clearContent(node, ap.getHead().getContent(), config)
+  }
+
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Ap ap, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::readStepCand(_, c, _, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c) and
+      c = ap.getHead().getContent()
+    )
+  }
 
   pragma[nomagic]
   private predicate castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1935,8 +2046,13 @@ private module Stage3 {
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
     exists(state) and
     exists(config) and
-    not clear(node, ap) and
+    not clear(node, ap, config) and
-    if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()
+    (if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()) and
+    (
+      notExpectsContent(node)
+      or
+      expectsContentCand(node, ap, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -2363,7 +2479,7 @@ private module Stage3 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -2401,10 +2517,24 @@ private module Stage3 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3190,7 +3320,7 @@ private module Stage4 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -3228,10 +3358,24 @@ private module Stage4 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3300,17 +3444,28 @@ private Configuration unbindConf(Configuration conf) {
   exists(Configuration c | result = pragma[only_bind_into](c) and conf = pragma[only_bind_into](c))
 }
 
-private predicate nodeMayUseSummary(
+pragma[nomagic]
-  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+private predicate nodeMayUseSummary0(
+  NodeEx n, DataFlowCallable c, FlowState state, AccessPathApprox apa, Configuration config
 ) {
-  exists(DataFlowCallable c, AccessPathApprox apa0 |
+  exists(AccessPathApprox apa0 |
-    Stage4::parameterMayFlowThrough(_, c, apa, _) and
+    Stage4::parameterMayFlowThrough(_, c, _, _) and
     Stage4::revFlow(n, state, true, _, apa0, config) and
     Stage4::fwdFlow(n, state, any(CallContextCall ccc), TAccessPathApproxSome(apa), apa0, config) and
     n.getEnclosingCallable() = c
   )
 }
 
+pragma[nomagic]
+private predicate nodeMayUseSummary(
+  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+) {
+  exists(DataFlowCallable c |
+    Stage4::parameterMayFlowThrough(_, c, apa, config) and
+    nodeMayUseSummary0(n, c, state, apa, config)
+  )
+}
+
 private newtype TSummaryCtx =
   TSummaryCtxNone() or
   TSummaryCtxSome(ParamNodeEx p, FlowState state, AccessPath ap) {
@@ -3506,7 +3661,7 @@ private newtype TPathNode =
  * of dereference operations needed to get from the value in the node to the
  * tracked object. The final type indicates the type of the tracked object.
  */
-abstract private class AccessPath extends TAccessPath {
+private class AccessPath extends TAccessPath {
   /** Gets the head of this access path, if any. */
   abstract TypedContent getHead();
 
@@ -3721,11 +3876,14 @@ abstract private class PathNodeImpl extends PathNode {
   abstract NodeEx getNodeEx();
 
   predicate isHidden() {
-    hiddenNode(this.getNodeEx().asNode()) and
+    not this.getConfiguration().includeHiddenNodes() and
-    not this.isSource() and
+    (
-    not this instanceof PathNodeSink
+      hiddenNode(this.getNodeEx().asNode()) and
-    or
+      not this.isSource() and
-    this.getNodeEx() instanceof TNodeImplicitRead
+      not this instanceof PathNodeSink
+      or
+      this.getNodeEx() instanceof TNodeImplicitRead
+    )
   }
 
   private string ppAp() {
@@ -4202,10 +4360,16 @@ private module Subpaths {
     exists(NodeEx n1, NodeEx n2 | n1 = n.getNodeEx() and n2 = result.getNodeEx() |
       localFlowBigStep(n1, _, n2, _, _, _, _, _) or
       store(n1, _, n2, _, _) or
-      read(n1, _, n2, _)
+      readSet(n1, _, n2, _)
     )
   }
 
+  pragma[nomagic]
+  private predicate hasSuccessor(PathNode pred, PathNodeMid succ, NodeEx succNode) {
+    succ = pred.getASuccessor() and
+    succNode = succ.getNodeEx()
+  }
+
   /**
    * Holds if `(arg, par, ret, out)` forms a subpath-tuple, that is, flow through
    * a subpath between `par` and `ret` with the connecting edges `arg -> par` and
@@ -4213,15 +4377,13 @@ private module Subpaths {
    */
   predicate subpaths(PathNode arg, PathNodeImpl par, PathNodeImpl ret, PathNode out) {
     exists(ParamNodeEx p, NodeEx o, FlowState sout, AccessPath apout, PathNodeMid out0 |
-      pragma[only_bind_into](arg).getASuccessor() = par and
+      pragma[only_bind_into](arg).getASuccessor() = pragma[only_bind_into](out0) and
-      pragma[only_bind_into](arg).getASuccessor() = out0 and
+      subpaths03(pragma[only_bind_into](arg), p, localStepToHidden*(ret), o, sout, apout) and
-      subpaths03(arg, p, localStepToHidden*(ret), o, sout, apout) and
+      hasSuccessor(pragma[only_bind_into](arg), par, p) and
       not ret.isHidden() and
-      par.getNodeEx() = p and
+      pathNode(out0, o, sout, _, _, apout, _, _)
-      out0.getNodeEx() = o and
+    |
-      out0.getState() = sout and
+      out = out0 or out = out0.projectToSink()
-      out0.getAp() = apout and
-      (out = out0 or out = out0.projectToSink())
     )
   }
 
@@ -4557,7 +4719,11 @@ private module FlowExploration {
       or
       exists(PartialPathNodeRev mid |
         revPartialPathStep(mid, node, state, sc1, sc2, sc3, ap, config) and
-        not clearsContentCached(node.asNode(), ap.getHead()) and
+        not clearsContentEx(node, ap.getHead()) and
+        (
+          notExpectsContent(node) or
+          expectsContentEx(node, ap.getHead())
+        ) and
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4573,7 +4739,11 @@ private module FlowExploration {
       partialPathStep(mid, node, state, cc, sc1, sc2, sc3, ap, config) and
       not fullBarrier(node, config) and
       not stateBarrier(node, state, config) and
-      not clearsContentCached(node.asNode(), ap.getHead().getContent()) and
+      not clearsContentEx(node, ap.getHead().getContent()) and
+      (
+        notExpectsContent(node) or
+        expectsContentEx(node, ap.getHead().getContent())
+      ) and
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()

cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowPrivate.qll

@@ -198,6 +198,12 @@ predicate clearsContent(Node n, Content c) {
   none() // stub implementation
 }
 
+/**
+ * Holds if the value that is being tracked is expected to be stored inside content `c`
+ * at node `n`.
+ */
+predicate expectsContent(Node n, ContentSet c) { none() }
+
 /** Gets the type of `n` used for type pruning. */
 Type getNodeType(Node n) {
   suppressUnusedNode(n) and

cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowUtil.qll

@@ -821,6 +821,34 @@ private class CollectionContent extends Content, TCollectionContent {
   override string toString() { result = "<element>" }
 }
 
+/**
+ * An entity that represents a set of `Content`s.
+ *
+ * The set may be interpreted differently depending on whether it is
+ * stored into (`getAStoreContent`) or read from (`getAReadContent`).
+ */
+class ContentSet instanceof Content {
+  /** Gets a content that may be stored into when storing into this set. */
+  Content getAStoreContent() { result = this }
+
+  /** Gets a content that may be read from when reading from this set. */
+  Content getAReadContent() { result = this }
+
+  /** Gets a textual representation of this content set. */
+  string toString() { result = super.toString() }
+
+  /**
+   * Holds if this element is at the specified location.
+   * The location spans column `startcolumn` of line `startline` to
+   * column `endcolumn` of line `endline` in file `filepath`.
+   * For more information, see
+   * [Locations](https://codeql.github.com/docs/writing-codeql-queries/providing-locations-in-codeql-queries/).
+   */
+  predicate hasLocationInfo(string path, int sl, int sc, int el, int ec) {
+    super.hasLocationInfo(path, sl, sc, el, ec)
+  }
+}
+
 /**
  * A guard that validates some expression.
  *

cpp/ql/lib/semmle/code/cpp/dataflow/internal/FlowVar.qll

@@ -549,7 +549,7 @@ module FlowVar_internal {
         bb = this.(Loop).getStmt() and
         v = this.getARelevantVariable()
         or
-        this.reachesWithoutAssignment(bb.getAPredecessor(), v) and
+        this.reachesWithoutAssignment(pragma[only_bind_out](bb.getAPredecessor()), v) and
         this.bbInLoop(bb)
       ) and
       not assignsToVar(bb, v)

cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking1/TaintTrackingImpl.qll

@@ -161,7 +161,7 @@ abstract class Configuration extends DataFlow::Configuration {
     this.isAdditionalTaintStep(node1, state1, node2, state2)
   }
 
-  override predicate allowImplicitRead(DataFlow::Node node, DataFlow::Content c) {
+  override predicate allowImplicitRead(DataFlow::Node node, DataFlow::ContentSet c) {
     (this.isSink(node) or this.isAdditionalTaintStep(node, _)) and
     defaultImplicitTaintRead(node, c)
   }

cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking2/TaintTrackingImpl.qll

@@ -161,7 +161,7 @@ abstract class Configuration extends DataFlow::Configuration {
     this.isAdditionalTaintStep(node1, state1, node2, state2)
   }
 
-  override predicate allowImplicitRead(DataFlow::Node node, DataFlow::Content c) {
+  override predicate allowImplicitRead(DataFlow::Node node, DataFlow::ContentSet c) {
     (this.isSink(node) or this.isAdditionalTaintStep(node, _)) and
     defaultImplicitTaintRead(node, c)
   }

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl.qll

@@ -116,7 +116,7 @@ abstract class Configuration extends string {
    * Holds if an arbitrary number of implicit read steps of content `c` may be
    * taken at `node`.
    */
-  predicate allowImplicitRead(Node node, Content c) { none() }
+  predicate allowImplicitRead(Node node, ContentSet c) { none() }
 
   /**
    * Gets the virtual dispatch branching limit when calculating field flow.
@@ -170,6 +170,14 @@ abstract class Configuration extends string {
    */
   int explorationLimit() { none() }
 
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (for example in a `path-problem` query).
+   */
+  predicate includeHiddenNodes() { none() }
+
   /**
    * Holds if there is a partial data flow path from `source` to `node`. The
    * approximate distance between `node` and the closest source is `dist` and
@@ -485,8 +493,9 @@ private predicate additionalJumpStateStep(
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+pragma[nomagic]
-  read(node1.asNode(), c, node2.asNode()) and
+private predicate readSet(NodeEx node1, ContentSet c, NodeEx node2, Configuration config) {
+  readSet(node1.asNode(), c, node2.asNode()) and
   stepFilter(node1, node2, config)
   or
   exists(Node n |
@@ -496,6 +505,37 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate expectsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    expectsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+pragma[nomagic]
+private predicate notExpectsContent(NodeEx n) { not expectsContentCached(n.asNode(), _) }
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -573,9 +613,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
+    exists(ContentSet c |
-      fwdFlowRead(c, node, cc, config) and
+      fwdFlowReadSet(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -599,10 +639,10 @@ private module Stage1 {
   private predicate fwdFlow(NodeEx node, Configuration config) { fwdFlow(node, _, config) }
 
   pragma[nomagic]
-  private predicate fwdFlowRead(Content c, NodeEx node, Cc cc, Configuration config) {
+  private predicate fwdFlowReadSet(ContentSet c, NodeEx node, Cc cc, Configuration config) {
     exists(NodeEx mid |
       fwdFlow(mid, cc, config) and
-      read(mid, c, node, config)
+      readSet(mid, c, node, config)
     )
   }
 
@@ -620,6 +660,16 @@ private module Stage1 {
     )
   }
 
+  /**
+   * Holds if `cs` may be interpreted in a read as the target of some store
+   * into `c`, in the flow covered by `fwdFlow`.
+   */
+  pragma[nomagic]
+  private predicate fwdFlowConsCandSet(ContentSet cs, Content c, Configuration config) {
+    fwdFlowConsCand(c, config) and
+    c = cs.getAReadContent()
+  }
+
   pragma[nomagic]
   private predicate fwdFlowReturnPosition(ReturnPosition pos, Cc cc, Configuration config) {
     exists(RetNodeEx ret |
@@ -712,9 +762,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
+    exists(NodeEx mid, ContentSet c |
-      read(node, c, mid, config) and
+      readSet(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -740,10 +790,10 @@ private module Stage1 {
    */
   pragma[nomagic]
   private predicate revFlowConsCand(Content c, Configuration config) {
-    exists(NodeEx mid, NodeEx node |
+    exists(NodeEx mid, NodeEx node, ContentSet cs |
       fwdFlow(node, pragma[only_bind_into](config)) and
-      read(node, c, mid, config) and
+      readSet(node, cs, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -762,7 +812,8 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
-  private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
+  pragma[nomagic]
+  predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
   }
@@ -861,8 +912,8 @@ private module Stage1 {
   pragma[nomagic]
   predicate readStepCand(NodeEx n1, Content c, NodeEx n2, Configuration config) {
     revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
-    revFlow(n2, pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
-    read(n1, c, n2, pragma[only_bind_into](config))
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -872,7 +923,10 @@ private module Stage1 {
   predicate revFlow(
     NodeEx node, FlowState state, boolean toReturn, ApOption returnAp, Ap ap, Configuration config
   ) {
-    revFlow(node, toReturn, config) and exists(state) and exists(returnAp) and exists(ap)
+    revFlow(node, toReturn, pragma[only_bind_into](config)) and
+    exists(state) and
+    exists(returnAp) and
+    exists(ap)
   }
 
   private predicate throughFlowNodeCand(NodeEx node, Configuration config) {
@@ -1147,11 +1201,26 @@ private module Stage2 {
 
   private predicate flowIntoCall = flowIntoCallNodeCand1/5;
 
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c)
+    )
+  }
+
   bindingset[node, state, ap, config]
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
-    PrevStage::revFlowState(state, config) and
+    PrevStage::revFlowState(state, pragma[only_bind_into](config)) and
     exists(ap) and
-    not stateBarrier(node, state, config)
+    not stateBarrier(node, state, config) and
+    (
+      notExpectsContent(node)
+      or
+      ap = true and
+      expectsContentCand(node, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -1574,7 +1643,7 @@ private module Stage2 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -1612,10 +1681,24 @@ private module Stage2 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -1706,7 +1789,8 @@ private module LocalFlowBigStep {
   private class FlowCheckNode extends NodeEx {
     FlowCheckNode() {
       castNode(this.asNode()) or
-      clearsContentCached(this.asNode(), _)
+      clearsContentCached(this.asNode(), _) or
+      expectsContentCached(this.asNode(), _)
     }
   }
 
@@ -1729,9 +1813,9 @@ private module LocalFlowBigStep {
       or
       node.asNode() instanceof OutNodeExt
       or
-      store(_, _, node, _, config)
+      Stage2::storeStepCand(_, _, _, node, _, config)
       or
-      read(_, _, node, config)
+      Stage2::readStepCand(_, _, node, config)
       or
       node instanceof FlowCheckNode
       or
@@ -1752,8 +1836,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
+      Stage2::storeStepCand(node, _, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1926,7 +2010,34 @@ private module Stage3 {
   private predicate flowIntoCall = flowIntoCallNodeCand2/5;
 
   pragma[nomagic]
-  private predicate clear(NodeEx node, Ap ap) { ap.isClearedAt(node.asNode()) }
+  private predicate clearSet(NodeEx node, ContentSet c, Configuration config) {
+    PrevStage::revFlow(node, config) and
+    clearsContentCached(node.asNode(), c)
+  }
+
+  pragma[nomagic]
+  private predicate clearContent(NodeEx node, Content c, Configuration config) {
+    exists(ContentSet cs |
+      PrevStage::readStepCand(_, pragma[only_bind_into](c), _, pragma[only_bind_into](config)) and
+      c = cs.getAReadContent() and
+      clearSet(node, cs, pragma[only_bind_into](config))
+    )
+  }
+
+  pragma[nomagic]
+  private predicate clear(NodeEx node, Ap ap, Configuration config) {
+    clearContent(node, ap.getHead().getContent(), config)
+  }
+
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Ap ap, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::readStepCand(_, c, _, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c) and
+      c = ap.getHead().getContent()
+    )
+  }
 
   pragma[nomagic]
   private predicate castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1935,8 +2046,13 @@ private module Stage3 {
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
     exists(state) and
     exists(config) and
-    not clear(node, ap) and
+    not clear(node, ap, config) and
-    if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()
+    (if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()) and
+    (
+      notExpectsContent(node)
+      or
+      expectsContentCand(node, ap, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -2363,7 +2479,7 @@ private module Stage3 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -2401,10 +2517,24 @@ private module Stage3 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3190,7 +3320,7 @@ private module Stage4 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -3228,10 +3358,24 @@ private module Stage4 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3300,17 +3444,28 @@ private Configuration unbindConf(Configuration conf) {
   exists(Configuration c | result = pragma[only_bind_into](c) and conf = pragma[only_bind_into](c))
 }
 
-private predicate nodeMayUseSummary(
+pragma[nomagic]
-  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+private predicate nodeMayUseSummary0(
+  NodeEx n, DataFlowCallable c, FlowState state, AccessPathApprox apa, Configuration config
 ) {
-  exists(DataFlowCallable c, AccessPathApprox apa0 |
+  exists(AccessPathApprox apa0 |
-    Stage4::parameterMayFlowThrough(_, c, apa, _) and
+    Stage4::parameterMayFlowThrough(_, c, _, _) and
     Stage4::revFlow(n, state, true, _, apa0, config) and
     Stage4::fwdFlow(n, state, any(CallContextCall ccc), TAccessPathApproxSome(apa), apa0, config) and
     n.getEnclosingCallable() = c
   )
 }
 
+pragma[nomagic]
+private predicate nodeMayUseSummary(
+  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+) {
+  exists(DataFlowCallable c |
+    Stage4::parameterMayFlowThrough(_, c, apa, config) and
+    nodeMayUseSummary0(n, c, state, apa, config)
+  )
+}
+
 private newtype TSummaryCtx =
   TSummaryCtxNone() or
   TSummaryCtxSome(ParamNodeEx p, FlowState state, AccessPath ap) {
@@ -3506,7 +3661,7 @@ private newtype TPathNode =
  * of dereference operations needed to get from the value in the node to the
  * tracked object. The final type indicates the type of the tracked object.
  */
-abstract private class AccessPath extends TAccessPath {
+private class AccessPath extends TAccessPath {
   /** Gets the head of this access path, if any. */
   abstract TypedContent getHead();
 
@@ -3721,11 +3876,14 @@ abstract private class PathNodeImpl extends PathNode {
   abstract NodeEx getNodeEx();
 
   predicate isHidden() {
-    hiddenNode(this.getNodeEx().asNode()) and
+    not this.getConfiguration().includeHiddenNodes() and
-    not this.isSource() and
+    (
-    not this instanceof PathNodeSink
+      hiddenNode(this.getNodeEx().asNode()) and
-    or
+      not this.isSource() and
-    this.getNodeEx() instanceof TNodeImplicitRead
+      not this instanceof PathNodeSink
+      or
+      this.getNodeEx() instanceof TNodeImplicitRead
+    )
   }
 
   private string ppAp() {
@@ -4202,10 +4360,16 @@ private module Subpaths {
     exists(NodeEx n1, NodeEx n2 | n1 = n.getNodeEx() and n2 = result.getNodeEx() |
       localFlowBigStep(n1, _, n2, _, _, _, _, _) or
       store(n1, _, n2, _, _) or
-      read(n1, _, n2, _)
+      readSet(n1, _, n2, _)
     )
   }
 
+  pragma[nomagic]
+  private predicate hasSuccessor(PathNode pred, PathNodeMid succ, NodeEx succNode) {
+    succ = pred.getASuccessor() and
+    succNode = succ.getNodeEx()
+  }
+
   /**
    * Holds if `(arg, par, ret, out)` forms a subpath-tuple, that is, flow through
    * a subpath between `par` and `ret` with the connecting edges `arg -> par` and
@@ -4213,15 +4377,13 @@ private module Subpaths {
    */
   predicate subpaths(PathNode arg, PathNodeImpl par, PathNodeImpl ret, PathNode out) {
     exists(ParamNodeEx p, NodeEx o, FlowState sout, AccessPath apout, PathNodeMid out0 |
-      pragma[only_bind_into](arg).getASuccessor() = par and
+      pragma[only_bind_into](arg).getASuccessor() = pragma[only_bind_into](out0) and
-      pragma[only_bind_into](arg).getASuccessor() = out0 and
+      subpaths03(pragma[only_bind_into](arg), p, localStepToHidden*(ret), o, sout, apout) and
-      subpaths03(arg, p, localStepToHidden*(ret), o, sout, apout) and
+      hasSuccessor(pragma[only_bind_into](arg), par, p) and
       not ret.isHidden() and
-      par.getNodeEx() = p and
+      pathNode(out0, o, sout, _, _, apout, _, _)
-      out0.getNodeEx() = o and
+    |
-      out0.getState() = sout and
+      out = out0 or out = out0.projectToSink()
-      out0.getAp() = apout and
-      (out = out0 or out = out0.projectToSink())
     )
   }
 
@@ -4557,7 +4719,11 @@ private module FlowExploration {
       or
       exists(PartialPathNodeRev mid |
         revPartialPathStep(mid, node, state, sc1, sc2, sc3, ap, config) and
-        not clearsContentCached(node.asNode(), ap.getHead()) and
+        not clearsContentEx(node, ap.getHead()) and
+        (
+          notExpectsContent(node) or
+          expectsContentEx(node, ap.getHead())
+        ) and
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4573,7 +4739,11 @@ private module FlowExploration {
       partialPathStep(mid, node, state, cc, sc1, sc2, sc3, ap, config) and
       not fullBarrier(node, config) and
       not stateBarrier(node, state, config) and
-      not clearsContentCached(node.asNode(), ap.getHead().getContent()) and
+      not clearsContentEx(node, ap.getHead().getContent()) and
+      (
+        notExpectsContent(node) or
+        expectsContentEx(node, ap.getHead().getContent())
+      ) and
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl2.qll

@@ -116,7 +116,7 @@ abstract class Configuration extends string {
    * Holds if an arbitrary number of implicit read steps of content `c` may be
    * taken at `node`.
    */
-  predicate allowImplicitRead(Node node, Content c) { none() }
+  predicate allowImplicitRead(Node node, ContentSet c) { none() }
 
   /**
    * Gets the virtual dispatch branching limit when calculating field flow.
@@ -170,6 +170,14 @@ abstract class Configuration extends string {
    */
   int explorationLimit() { none() }
 
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (for example in a `path-problem` query).
+   */
+  predicate includeHiddenNodes() { none() }
+
   /**
    * Holds if there is a partial data flow path from `source` to `node`. The
    * approximate distance between `node` and the closest source is `dist` and
@@ -485,8 +493,9 @@ private predicate additionalJumpStateStep(
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+pragma[nomagic]
-  read(node1.asNode(), c, node2.asNode()) and
+private predicate readSet(NodeEx node1, ContentSet c, NodeEx node2, Configuration config) {
+  readSet(node1.asNode(), c, node2.asNode()) and
   stepFilter(node1, node2, config)
   or
   exists(Node n |
@@ -496,6 +505,37 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate expectsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    expectsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+pragma[nomagic]
+private predicate notExpectsContent(NodeEx n) { not expectsContentCached(n.asNode(), _) }
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -573,9 +613,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
+    exists(ContentSet c |
-      fwdFlowRead(c, node, cc, config) and
+      fwdFlowReadSet(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -599,10 +639,10 @@ private module Stage1 {
   private predicate fwdFlow(NodeEx node, Configuration config) { fwdFlow(node, _, config) }
 
   pragma[nomagic]
-  private predicate fwdFlowRead(Content c, NodeEx node, Cc cc, Configuration config) {
+  private predicate fwdFlowReadSet(ContentSet c, NodeEx node, Cc cc, Configuration config) {
     exists(NodeEx mid |
       fwdFlow(mid, cc, config) and
-      read(mid, c, node, config)
+      readSet(mid, c, node, config)
     )
   }
 
@@ -620,6 +660,16 @@ private module Stage1 {
     )
   }
 
+  /**
+   * Holds if `cs` may be interpreted in a read as the target of some store
+   * into `c`, in the flow covered by `fwdFlow`.
+   */
+  pragma[nomagic]
+  private predicate fwdFlowConsCandSet(ContentSet cs, Content c, Configuration config) {
+    fwdFlowConsCand(c, config) and
+    c = cs.getAReadContent()
+  }
+
   pragma[nomagic]
   private predicate fwdFlowReturnPosition(ReturnPosition pos, Cc cc, Configuration config) {
     exists(RetNodeEx ret |
@@ -712,9 +762,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
+    exists(NodeEx mid, ContentSet c |
-      read(node, c, mid, config) and
+      readSet(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -740,10 +790,10 @@ private module Stage1 {
    */
   pragma[nomagic]
   private predicate revFlowConsCand(Content c, Configuration config) {
-    exists(NodeEx mid, NodeEx node |
+    exists(NodeEx mid, NodeEx node, ContentSet cs |
       fwdFlow(node, pragma[only_bind_into](config)) and
-      read(node, c, mid, config) and
+      readSet(node, cs, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -762,7 +812,8 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
-  private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
+  pragma[nomagic]
+  predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
   }
@@ -861,8 +912,8 @@ private module Stage1 {
   pragma[nomagic]
   predicate readStepCand(NodeEx n1, Content c, NodeEx n2, Configuration config) {
     revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
-    revFlow(n2, pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
-    read(n1, c, n2, pragma[only_bind_into](config))
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -872,7 +923,10 @@ private module Stage1 {
   predicate revFlow(
     NodeEx node, FlowState state, boolean toReturn, ApOption returnAp, Ap ap, Configuration config
   ) {
-    revFlow(node, toReturn, config) and exists(state) and exists(returnAp) and exists(ap)
+    revFlow(node, toReturn, pragma[only_bind_into](config)) and
+    exists(state) and
+    exists(returnAp) and
+    exists(ap)
   }
 
   private predicate throughFlowNodeCand(NodeEx node, Configuration config) {
@@ -1147,11 +1201,26 @@ private module Stage2 {
 
   private predicate flowIntoCall = flowIntoCallNodeCand1/5;
 
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c)
+    )
+  }
+
   bindingset[node, state, ap, config]
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
-    PrevStage::revFlowState(state, config) and
+    PrevStage::revFlowState(state, pragma[only_bind_into](config)) and
     exists(ap) and
-    not stateBarrier(node, state, config)
+    not stateBarrier(node, state, config) and
+    (
+      notExpectsContent(node)
+      or
+      ap = true and
+      expectsContentCand(node, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -1574,7 +1643,7 @@ private module Stage2 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -1612,10 +1681,24 @@ private module Stage2 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -1706,7 +1789,8 @@ private module LocalFlowBigStep {
   private class FlowCheckNode extends NodeEx {
     FlowCheckNode() {
       castNode(this.asNode()) or
-      clearsContentCached(this.asNode(), _)
+      clearsContentCached(this.asNode(), _) or
+      expectsContentCached(this.asNode(), _)
     }
   }
 
@@ -1729,9 +1813,9 @@ private module LocalFlowBigStep {
       or
       node.asNode() instanceof OutNodeExt
       or
-      store(_, _, node, _, config)
+      Stage2::storeStepCand(_, _, _, node, _, config)
       or
-      read(_, _, node, config)
+      Stage2::readStepCand(_, _, node, config)
       or
       node instanceof FlowCheckNode
       or
@@ -1752,8 +1836,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
+      Stage2::storeStepCand(node, _, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1926,7 +2010,34 @@ private module Stage3 {
   private predicate flowIntoCall = flowIntoCallNodeCand2/5;
 
   pragma[nomagic]
-  private predicate clear(NodeEx node, Ap ap) { ap.isClearedAt(node.asNode()) }
+  private predicate clearSet(NodeEx node, ContentSet c, Configuration config) {
+    PrevStage::revFlow(node, config) and
+    clearsContentCached(node.asNode(), c)
+  }
+
+  pragma[nomagic]
+  private predicate clearContent(NodeEx node, Content c, Configuration config) {
+    exists(ContentSet cs |
+      PrevStage::readStepCand(_, pragma[only_bind_into](c), _, pragma[only_bind_into](config)) and
+      c = cs.getAReadContent() and
+      clearSet(node, cs, pragma[only_bind_into](config))
+    )
+  }
+
+  pragma[nomagic]
+  private predicate clear(NodeEx node, Ap ap, Configuration config) {
+    clearContent(node, ap.getHead().getContent(), config)
+  }
+
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Ap ap, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::readStepCand(_, c, _, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c) and
+      c = ap.getHead().getContent()
+    )
+  }
 
   pragma[nomagic]
   private predicate castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1935,8 +2046,13 @@ private module Stage3 {
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
     exists(state) and
     exists(config) and
-    not clear(node, ap) and
+    not clear(node, ap, config) and
-    if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()
+    (if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()) and
+    (
+      notExpectsContent(node)
+      or
+      expectsContentCand(node, ap, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -2363,7 +2479,7 @@ private module Stage3 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -2401,10 +2517,24 @@ private module Stage3 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3190,7 +3320,7 @@ private module Stage4 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -3228,10 +3358,24 @@ private module Stage4 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3300,17 +3444,28 @@ private Configuration unbindConf(Configuration conf) {
   exists(Configuration c | result = pragma[only_bind_into](c) and conf = pragma[only_bind_into](c))
 }
 
-private predicate nodeMayUseSummary(
+pragma[nomagic]
-  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+private predicate nodeMayUseSummary0(
+  NodeEx n, DataFlowCallable c, FlowState state, AccessPathApprox apa, Configuration config
 ) {
-  exists(DataFlowCallable c, AccessPathApprox apa0 |
+  exists(AccessPathApprox apa0 |
-    Stage4::parameterMayFlowThrough(_, c, apa, _) and
+    Stage4::parameterMayFlowThrough(_, c, _, _) and
     Stage4::revFlow(n, state, true, _, apa0, config) and
     Stage4::fwdFlow(n, state, any(CallContextCall ccc), TAccessPathApproxSome(apa), apa0, config) and
     n.getEnclosingCallable() = c
   )
 }
 
+pragma[nomagic]
+private predicate nodeMayUseSummary(
+  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+) {
+  exists(DataFlowCallable c |
+    Stage4::parameterMayFlowThrough(_, c, apa, config) and
+    nodeMayUseSummary0(n, c, state, apa, config)
+  )
+}
+
 private newtype TSummaryCtx =
   TSummaryCtxNone() or
   TSummaryCtxSome(ParamNodeEx p, FlowState state, AccessPath ap) {
@@ -3506,7 +3661,7 @@ private newtype TPathNode =
  * of dereference operations needed to get from the value in the node to the
  * tracked object. The final type indicates the type of the tracked object.
  */
-abstract private class AccessPath extends TAccessPath {
+private class AccessPath extends TAccessPath {
   /** Gets the head of this access path, if any. */
   abstract TypedContent getHead();
 
@@ -3721,11 +3876,14 @@ abstract private class PathNodeImpl extends PathNode {
   abstract NodeEx getNodeEx();
 
   predicate isHidden() {
-    hiddenNode(this.getNodeEx().asNode()) and
+    not this.getConfiguration().includeHiddenNodes() and
-    not this.isSource() and
+    (
-    not this instanceof PathNodeSink
+      hiddenNode(this.getNodeEx().asNode()) and
-    or
+      not this.isSource() and
-    this.getNodeEx() instanceof TNodeImplicitRead
+      not this instanceof PathNodeSink
+      or
+      this.getNodeEx() instanceof TNodeImplicitRead
+    )
   }
 
   private string ppAp() {
@@ -4202,10 +4360,16 @@ private module Subpaths {
     exists(NodeEx n1, NodeEx n2 | n1 = n.getNodeEx() and n2 = result.getNodeEx() |
       localFlowBigStep(n1, _, n2, _, _, _, _, _) or
       store(n1, _, n2, _, _) or
-      read(n1, _, n2, _)
+      readSet(n1, _, n2, _)
     )
   }
 
+  pragma[nomagic]
+  private predicate hasSuccessor(PathNode pred, PathNodeMid succ, NodeEx succNode) {
+    succ = pred.getASuccessor() and
+    succNode = succ.getNodeEx()
+  }
+
   /**
    * Holds if `(arg, par, ret, out)` forms a subpath-tuple, that is, flow through
    * a subpath between `par` and `ret` with the connecting edges `arg -> par` and
@@ -4213,15 +4377,13 @@ private module Subpaths {
    */
   predicate subpaths(PathNode arg, PathNodeImpl par, PathNodeImpl ret, PathNode out) {
     exists(ParamNodeEx p, NodeEx o, FlowState sout, AccessPath apout, PathNodeMid out0 |
-      pragma[only_bind_into](arg).getASuccessor() = par and
+      pragma[only_bind_into](arg).getASuccessor() = pragma[only_bind_into](out0) and
-      pragma[only_bind_into](arg).getASuccessor() = out0 and
+      subpaths03(pragma[only_bind_into](arg), p, localStepToHidden*(ret), o, sout, apout) and
-      subpaths03(arg, p, localStepToHidden*(ret), o, sout, apout) and
+      hasSuccessor(pragma[only_bind_into](arg), par, p) and
       not ret.isHidden() and
-      par.getNodeEx() = p and
+      pathNode(out0, o, sout, _, _, apout, _, _)
-      out0.getNodeEx() = o and
+    |
-      out0.getState() = sout and
+      out = out0 or out = out0.projectToSink()
-      out0.getAp() = apout and
-      (out = out0 or out = out0.projectToSink())
     )
   }
 
@@ -4557,7 +4719,11 @@ private module FlowExploration {
       or
       exists(PartialPathNodeRev mid |
         revPartialPathStep(mid, node, state, sc1, sc2, sc3, ap, config) and
-        not clearsContentCached(node.asNode(), ap.getHead()) and
+        not clearsContentEx(node, ap.getHead()) and
+        (
+          notExpectsContent(node) or
+          expectsContentEx(node, ap.getHead())
+        ) and
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4573,7 +4739,11 @@ private module FlowExploration {
       partialPathStep(mid, node, state, cc, sc1, sc2, sc3, ap, config) and
       not fullBarrier(node, config) and
       not stateBarrier(node, state, config) and
-      not clearsContentCached(node.asNode(), ap.getHead().getContent()) and
+      not clearsContentEx(node, ap.getHead().getContent()) and
+      (
+        notExpectsContent(node) or
+        expectsContentEx(node, ap.getHead().getContent())
+      ) and
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl3.qll

@@ -116,7 +116,7 @@ abstract class Configuration extends string {
    * Holds if an arbitrary number of implicit read steps of content `c` may be
    * taken at `node`.
    */
-  predicate allowImplicitRead(Node node, Content c) { none() }
+  predicate allowImplicitRead(Node node, ContentSet c) { none() }
 
   /**
    * Gets the virtual dispatch branching limit when calculating field flow.
@@ -170,6 +170,14 @@ abstract class Configuration extends string {
    */
   int explorationLimit() { none() }
 
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (for example in a `path-problem` query).
+   */
+  predicate includeHiddenNodes() { none() }
+
   /**
    * Holds if there is a partial data flow path from `source` to `node`. The
    * approximate distance between `node` and the closest source is `dist` and
@@ -485,8 +493,9 @@ private predicate additionalJumpStateStep(
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+pragma[nomagic]
-  read(node1.asNode(), c, node2.asNode()) and
+private predicate readSet(NodeEx node1, ContentSet c, NodeEx node2, Configuration config) {
+  readSet(node1.asNode(), c, node2.asNode()) and
   stepFilter(node1, node2, config)
   or
   exists(Node n |
@@ -496,6 +505,37 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate expectsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    expectsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+pragma[nomagic]
+private predicate notExpectsContent(NodeEx n) { not expectsContentCached(n.asNode(), _) }
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -573,9 +613,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
+    exists(ContentSet c |
-      fwdFlowRead(c, node, cc, config) and
+      fwdFlowReadSet(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -599,10 +639,10 @@ private module Stage1 {
   private predicate fwdFlow(NodeEx node, Configuration config) { fwdFlow(node, _, config) }
 
   pragma[nomagic]
-  private predicate fwdFlowRead(Content c, NodeEx node, Cc cc, Configuration config) {
+  private predicate fwdFlowReadSet(ContentSet c, NodeEx node, Cc cc, Configuration config) {
     exists(NodeEx mid |
       fwdFlow(mid, cc, config) and
-      read(mid, c, node, config)
+      readSet(mid, c, node, config)
     )
   }
 
@@ -620,6 +660,16 @@ private module Stage1 {
     )
   }
 
+  /**
+   * Holds if `cs` may be interpreted in a read as the target of some store
+   * into `c`, in the flow covered by `fwdFlow`.
+   */
+  pragma[nomagic]
+  private predicate fwdFlowConsCandSet(ContentSet cs, Content c, Configuration config) {
+    fwdFlowConsCand(c, config) and
+    c = cs.getAReadContent()
+  }
+
   pragma[nomagic]
   private predicate fwdFlowReturnPosition(ReturnPosition pos, Cc cc, Configuration config) {
     exists(RetNodeEx ret |
@@ -712,9 +762,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
+    exists(NodeEx mid, ContentSet c |
-      read(node, c, mid, config) and
+      readSet(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -740,10 +790,10 @@ private module Stage1 {
    */
   pragma[nomagic]
   private predicate revFlowConsCand(Content c, Configuration config) {
-    exists(NodeEx mid, NodeEx node |
+    exists(NodeEx mid, NodeEx node, ContentSet cs |
       fwdFlow(node, pragma[only_bind_into](config)) and
-      read(node, c, mid, config) and
+      readSet(node, cs, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -762,7 +812,8 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
-  private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
+  pragma[nomagic]
+  predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
   }
@@ -861,8 +912,8 @@ private module Stage1 {
   pragma[nomagic]
   predicate readStepCand(NodeEx n1, Content c, NodeEx n2, Configuration config) {
     revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
-    revFlow(n2, pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
-    read(n1, c, n2, pragma[only_bind_into](config))
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -872,7 +923,10 @@ private module Stage1 {
   predicate revFlow(
     NodeEx node, FlowState state, boolean toReturn, ApOption returnAp, Ap ap, Configuration config
   ) {
-    revFlow(node, toReturn, config) and exists(state) and exists(returnAp) and exists(ap)
+    revFlow(node, toReturn, pragma[only_bind_into](config)) and
+    exists(state) and
+    exists(returnAp) and
+    exists(ap)
   }
 
   private predicate throughFlowNodeCand(NodeEx node, Configuration config) {
@@ -1147,11 +1201,26 @@ private module Stage2 {
 
   private predicate flowIntoCall = flowIntoCallNodeCand1/5;
 
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c)
+    )
+  }
+
   bindingset[node, state, ap, config]
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
-    PrevStage::revFlowState(state, config) and
+    PrevStage::revFlowState(state, pragma[only_bind_into](config)) and
     exists(ap) and
-    not stateBarrier(node, state, config)
+    not stateBarrier(node, state, config) and
+    (
+      notExpectsContent(node)
+      or
+      ap = true and
+      expectsContentCand(node, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -1574,7 +1643,7 @@ private module Stage2 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -1612,10 +1681,24 @@ private module Stage2 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -1706,7 +1789,8 @@ private module LocalFlowBigStep {
   private class FlowCheckNode extends NodeEx {
     FlowCheckNode() {
       castNode(this.asNode()) or
-      clearsContentCached(this.asNode(), _)
+      clearsContentCached(this.asNode(), _) or
+      expectsContentCached(this.asNode(), _)
     }
   }
 
@@ -1729,9 +1813,9 @@ private module LocalFlowBigStep {
       or
       node.asNode() instanceof OutNodeExt
       or
-      store(_, _, node, _, config)
+      Stage2::storeStepCand(_, _, _, node, _, config)
       or
-      read(_, _, node, config)
+      Stage2::readStepCand(_, _, node, config)
       or
       node instanceof FlowCheckNode
       or
@@ -1752,8 +1836,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
+      Stage2::storeStepCand(node, _, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1926,7 +2010,34 @@ private module Stage3 {
   private predicate flowIntoCall = flowIntoCallNodeCand2/5;
 
   pragma[nomagic]
-  private predicate clear(NodeEx node, Ap ap) { ap.isClearedAt(node.asNode()) }
+  private predicate clearSet(NodeEx node, ContentSet c, Configuration config) {
+    PrevStage::revFlow(node, config) and
+    clearsContentCached(node.asNode(), c)
+  }
+
+  pragma[nomagic]
+  private predicate clearContent(NodeEx node, Content c, Configuration config) {
+    exists(ContentSet cs |
+      PrevStage::readStepCand(_, pragma[only_bind_into](c), _, pragma[only_bind_into](config)) and
+      c = cs.getAReadContent() and
+      clearSet(node, cs, pragma[only_bind_into](config))
+    )
+  }
+
+  pragma[nomagic]
+  private predicate clear(NodeEx node, Ap ap, Configuration config) {
+    clearContent(node, ap.getHead().getContent(), config)
+  }
+
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Ap ap, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::readStepCand(_, c, _, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c) and
+      c = ap.getHead().getContent()
+    )
+  }
 
   pragma[nomagic]
   private predicate castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1935,8 +2046,13 @@ private module Stage3 {
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
     exists(state) and
     exists(config) and
-    not clear(node, ap) and
+    not clear(node, ap, config) and
-    if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()
+    (if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()) and
+    (
+      notExpectsContent(node)
+      or
+      expectsContentCand(node, ap, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -2363,7 +2479,7 @@ private module Stage3 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -2401,10 +2517,24 @@ private module Stage3 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3190,7 +3320,7 @@ private module Stage4 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -3228,10 +3358,24 @@ private module Stage4 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3300,17 +3444,28 @@ private Configuration unbindConf(Configuration conf) {
   exists(Configuration c | result = pragma[only_bind_into](c) and conf = pragma[only_bind_into](c))
 }
 
-private predicate nodeMayUseSummary(
+pragma[nomagic]
-  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+private predicate nodeMayUseSummary0(
+  NodeEx n, DataFlowCallable c, FlowState state, AccessPathApprox apa, Configuration config
 ) {
-  exists(DataFlowCallable c, AccessPathApprox apa0 |
+  exists(AccessPathApprox apa0 |
-    Stage4::parameterMayFlowThrough(_, c, apa, _) and
+    Stage4::parameterMayFlowThrough(_, c, _, _) and
     Stage4::revFlow(n, state, true, _, apa0, config) and
     Stage4::fwdFlow(n, state, any(CallContextCall ccc), TAccessPathApproxSome(apa), apa0, config) and
     n.getEnclosingCallable() = c
   )
 }
 
+pragma[nomagic]
+private predicate nodeMayUseSummary(
+  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+) {
+  exists(DataFlowCallable c |
+    Stage4::parameterMayFlowThrough(_, c, apa, config) and
+    nodeMayUseSummary0(n, c, state, apa, config)
+  )
+}
+
 private newtype TSummaryCtx =
   TSummaryCtxNone() or
   TSummaryCtxSome(ParamNodeEx p, FlowState state, AccessPath ap) {
@@ -3506,7 +3661,7 @@ private newtype TPathNode =
  * of dereference operations needed to get from the value in the node to the
  * tracked object. The final type indicates the type of the tracked object.
  */
-abstract private class AccessPath extends TAccessPath {
+private class AccessPath extends TAccessPath {
   /** Gets the head of this access path, if any. */
   abstract TypedContent getHead();
 
@@ -3721,11 +3876,14 @@ abstract private class PathNodeImpl extends PathNode {
   abstract NodeEx getNodeEx();
 
   predicate isHidden() {
-    hiddenNode(this.getNodeEx().asNode()) and
+    not this.getConfiguration().includeHiddenNodes() and
-    not this.isSource() and
+    (
-    not this instanceof PathNodeSink
+      hiddenNode(this.getNodeEx().asNode()) and
-    or
+      not this.isSource() and
-    this.getNodeEx() instanceof TNodeImplicitRead
+      not this instanceof PathNodeSink
+      or
+      this.getNodeEx() instanceof TNodeImplicitRead
+    )
   }
 
   private string ppAp() {
@@ -4202,10 +4360,16 @@ private module Subpaths {
     exists(NodeEx n1, NodeEx n2 | n1 = n.getNodeEx() and n2 = result.getNodeEx() |
       localFlowBigStep(n1, _, n2, _, _, _, _, _) or
       store(n1, _, n2, _, _) or
-      read(n1, _, n2, _)
+      readSet(n1, _, n2, _)
     )
   }
 
+  pragma[nomagic]
+  private predicate hasSuccessor(PathNode pred, PathNodeMid succ, NodeEx succNode) {
+    succ = pred.getASuccessor() and
+    succNode = succ.getNodeEx()
+  }
+
   /**
    * Holds if `(arg, par, ret, out)` forms a subpath-tuple, that is, flow through
    * a subpath between `par` and `ret` with the connecting edges `arg -> par` and
@@ -4213,15 +4377,13 @@ private module Subpaths {
    */
   predicate subpaths(PathNode arg, PathNodeImpl par, PathNodeImpl ret, PathNode out) {
     exists(ParamNodeEx p, NodeEx o, FlowState sout, AccessPath apout, PathNodeMid out0 |
-      pragma[only_bind_into](arg).getASuccessor() = par and
+      pragma[only_bind_into](arg).getASuccessor() = pragma[only_bind_into](out0) and
-      pragma[only_bind_into](arg).getASuccessor() = out0 and
+      subpaths03(pragma[only_bind_into](arg), p, localStepToHidden*(ret), o, sout, apout) and
-      subpaths03(arg, p, localStepToHidden*(ret), o, sout, apout) and
+      hasSuccessor(pragma[only_bind_into](arg), par, p) and
       not ret.isHidden() and
-      par.getNodeEx() = p and
+      pathNode(out0, o, sout, _, _, apout, _, _)
-      out0.getNodeEx() = o and
+    |
-      out0.getState() = sout and
+      out = out0 or out = out0.projectToSink()
-      out0.getAp() = apout and
-      (out = out0 or out = out0.projectToSink())
     )
   }
 
@@ -4557,7 +4719,11 @@ private module FlowExploration {
       or
       exists(PartialPathNodeRev mid |
         revPartialPathStep(mid, node, state, sc1, sc2, sc3, ap, config) and
-        not clearsContentCached(node.asNode(), ap.getHead()) and
+        not clearsContentEx(node, ap.getHead()) and
+        (
+          notExpectsContent(node) or
+          expectsContentEx(node, ap.getHead())
+        ) and
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4573,7 +4739,11 @@ private module FlowExploration {
       partialPathStep(mid, node, state, cc, sc1, sc2, sc3, ap, config) and
       not fullBarrier(node, config) and
       not stateBarrier(node, state, config) and
-      not clearsContentCached(node.asNode(), ap.getHead().getContent()) and
+      not clearsContentEx(node, ap.getHead().getContent()) and
+      (
+        notExpectsContent(node) or
+        expectsContentEx(node, ap.getHead().getContent())
+      ) and
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl4.qll

@@ -116,7 +116,7 @@ abstract class Configuration extends string {
    * Holds if an arbitrary number of implicit read steps of content `c` may be
    * taken at `node`.
    */
-  predicate allowImplicitRead(Node node, Content c) { none() }
+  predicate allowImplicitRead(Node node, ContentSet c) { none() }
 
   /**
    * Gets the virtual dispatch branching limit when calculating field flow.
@@ -170,6 +170,14 @@ abstract class Configuration extends string {
    */
   int explorationLimit() { none() }
 
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (for example in a `path-problem` query).
+   */
+  predicate includeHiddenNodes() { none() }
+
   /**
    * Holds if there is a partial data flow path from `source` to `node`. The
    * approximate distance between `node` and the closest source is `dist` and
@@ -485,8 +493,9 @@ private predicate additionalJumpStateStep(
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+pragma[nomagic]
-  read(node1.asNode(), c, node2.asNode()) and
+private predicate readSet(NodeEx node1, ContentSet c, NodeEx node2, Configuration config) {
+  readSet(node1.asNode(), c, node2.asNode()) and
   stepFilter(node1, node2, config)
   or
   exists(Node n |
@@ -496,6 +505,37 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+bindingset[c]
+private predicate expectsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    expectsContentCached(n.asNode(), cs) and
+    pragma[only_bind_out](c) = pragma[only_bind_into](cs).getAReadContent()
+  )
+}
+
+pragma[nomagic]
+private predicate notExpectsContent(NodeEx n) { not expectsContentCached(n.asNode(), _) }
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -573,9 +613,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
+    exists(ContentSet c |
-      fwdFlowRead(c, node, cc, config) and
+      fwdFlowReadSet(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -599,10 +639,10 @@ private module Stage1 {
   private predicate fwdFlow(NodeEx node, Configuration config) { fwdFlow(node, _, config) }
 
   pragma[nomagic]
-  private predicate fwdFlowRead(Content c, NodeEx node, Cc cc, Configuration config) {
+  private predicate fwdFlowReadSet(ContentSet c, NodeEx node, Cc cc, Configuration config) {
     exists(NodeEx mid |
       fwdFlow(mid, cc, config) and
-      read(mid, c, node, config)
+      readSet(mid, c, node, config)
     )
   }
 
@@ -620,6 +660,16 @@ private module Stage1 {
     )
   }
 
+  /**
+   * Holds if `cs` may be interpreted in a read as the target of some store
+   * into `c`, in the flow covered by `fwdFlow`.
+   */
+  pragma[nomagic]
+  private predicate fwdFlowConsCandSet(ContentSet cs, Content c, Configuration config) {
+    fwdFlowConsCand(c, config) and
+    c = cs.getAReadContent()
+  }
+
   pragma[nomagic]
   private predicate fwdFlowReturnPosition(ReturnPosition pos, Cc cc, Configuration config) {
     exists(RetNodeEx ret |
@@ -712,9 +762,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
+    exists(NodeEx mid, ContentSet c |
-      read(node, c, mid, config) and
+      readSet(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -740,10 +790,10 @@ private module Stage1 {
    */
   pragma[nomagic]
   private predicate revFlowConsCand(Content c, Configuration config) {
-    exists(NodeEx mid, NodeEx node |
+    exists(NodeEx mid, NodeEx node, ContentSet cs |
       fwdFlow(node, pragma[only_bind_into](config)) and
-      read(node, c, mid, config) and
+      readSet(node, cs, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -762,7 +812,8 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
-  private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
+  pragma[nomagic]
+  predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
   }
@@ -861,8 +912,8 @@ private module Stage1 {
   pragma[nomagic]
   predicate readStepCand(NodeEx n1, Content c, NodeEx n2, Configuration config) {
     revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
-    revFlow(n2, pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
-    read(n1, c, n2, pragma[only_bind_into](config))
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -872,7 +923,10 @@ private module Stage1 {
   predicate revFlow(
     NodeEx node, FlowState state, boolean toReturn, ApOption returnAp, Ap ap, Configuration config
   ) {
-    revFlow(node, toReturn, config) and exists(state) and exists(returnAp) and exists(ap)
+    revFlow(node, toReturn, pragma[only_bind_into](config)) and
+    exists(state) and
+    exists(returnAp) and
+    exists(ap)
   }
 
   private predicate throughFlowNodeCand(NodeEx node, Configuration config) {
@@ -1147,11 +1201,26 @@ private module Stage2 {
 
   private predicate flowIntoCall = flowIntoCallNodeCand1/5;
 
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::revFlowIsReadAndStored(c, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c)
+    )
+  }
+
   bindingset[node, state, ap, config]
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
-    PrevStage::revFlowState(state, config) and
+    PrevStage::revFlowState(state, pragma[only_bind_into](config)) and
     exists(ap) and
-    not stateBarrier(node, state, config)
+    not stateBarrier(node, state, config) and
+    (
+      notExpectsContent(node)
+      or
+      ap = true and
+      expectsContentCand(node, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -1574,7 +1643,7 @@ private module Stage2 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -1612,10 +1681,24 @@ private module Stage2 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -1706,7 +1789,8 @@ private module LocalFlowBigStep {
   private class FlowCheckNode extends NodeEx {
     FlowCheckNode() {
       castNode(this.asNode()) or
-      clearsContentCached(this.asNode(), _)
+      clearsContentCached(this.asNode(), _) or
+      expectsContentCached(this.asNode(), _)
     }
   }
 
@@ -1729,9 +1813,9 @@ private module LocalFlowBigStep {
       or
       node.asNode() instanceof OutNodeExt
       or
-      store(_, _, node, _, config)
+      Stage2::storeStepCand(_, _, _, node, _, config)
       or
-      read(_, _, node, config)
+      Stage2::readStepCand(_, _, node, config)
       or
       node instanceof FlowCheckNode
       or
@@ -1752,8 +1836,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
+      Stage2::storeStepCand(node, _, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1926,7 +2010,34 @@ private module Stage3 {
   private predicate flowIntoCall = flowIntoCallNodeCand2/5;
 
   pragma[nomagic]
-  private predicate clear(NodeEx node, Ap ap) { ap.isClearedAt(node.asNode()) }
+  private predicate clearSet(NodeEx node, ContentSet c, Configuration config) {
+    PrevStage::revFlow(node, config) and
+    clearsContentCached(node.asNode(), c)
+  }
+
+  pragma[nomagic]
+  private predicate clearContent(NodeEx node, Content c, Configuration config) {
+    exists(ContentSet cs |
+      PrevStage::readStepCand(_, pragma[only_bind_into](c), _, pragma[only_bind_into](config)) and
+      c = cs.getAReadContent() and
+      clearSet(node, cs, pragma[only_bind_into](config))
+    )
+  }
+
+  pragma[nomagic]
+  private predicate clear(NodeEx node, Ap ap, Configuration config) {
+    clearContent(node, ap.getHead().getContent(), config)
+  }
+
+  pragma[nomagic]
+  private predicate expectsContentCand(NodeEx node, Ap ap, Configuration config) {
+    exists(Content c |
+      PrevStage::revFlow(node, pragma[only_bind_into](config)) and
+      PrevStage::readStepCand(_, c, _, pragma[only_bind_into](config)) and
+      expectsContentEx(node, c) and
+      c = ap.getHead().getContent()
+    )
+  }
 
   pragma[nomagic]
   private predicate castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1935,8 +2046,13 @@ private module Stage3 {
   private predicate filter(NodeEx node, FlowState state, Ap ap, Configuration config) {
     exists(state) and
     exists(config) and
-    not clear(node, ap) and
+    not clear(node, ap, config) and
-    if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()
+    (if castingNodeEx(node) then compatibleTypes(node.getDataFlowType(), ap.getType()) else any()) and
+    (
+      notExpectsContent(node)
+      or
+      expectsContentCand(node, ap, config)
+    )
   }
 
   bindingset[ap, contentType]
@@ -2363,7 +2479,7 @@ private module Stage3 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -2401,10 +2517,24 @@ private module Stage3 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3190,7 +3320,7 @@ private module Stage4 {
     Configuration config
   ) {
     exists(Ap ap2, Content c |
-      store(node1, tc, node2, contentType, config) and
+      PrevStage::storeStepCand(node1, _, tc, node2, contentType, config) and
       revFlowStore(ap2, c, ap1, node1, _, tc, node2, _, _, config) and
       revFlowConsCand(ap2, c, ap1, config)
     )
@@ -3228,10 +3358,24 @@ private module Stage4 {
     storeStepFwd(_, ap, tc, _, _, config)
   }
 
-  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+  private predicate revConsCand(TypedContent tc, Ap ap, Configuration config) {
     storeStepCand(_, ap, tc, _, _, config)
   }
 
+  private predicate validAp(Ap ap, Configuration config) {
+    revFlow(_, _, _, _, ap, config) and ap instanceof ApNil
+    or
+    exists(TypedContent head, Ap tail |
+      consCand(head, tail, config) and
+      ap = apCons(head, tail)
+    )
+  }
+
+  predicate consCand(TypedContent tc, Ap ap, Configuration config) {
+    revConsCand(tc, ap, config) and
+    validAp(ap, config)
+  }
+
   pragma[noinline]
   private predicate parameterFlow(
     ParamNodeEx p, Ap ap, Ap ap0, DataFlowCallable c, Configuration config
@@ -3300,17 +3444,28 @@ private Configuration unbindConf(Configuration conf) {
   exists(Configuration c | result = pragma[only_bind_into](c) and conf = pragma[only_bind_into](c))
 }
 
-private predicate nodeMayUseSummary(
+pragma[nomagic]
-  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+private predicate nodeMayUseSummary0(
+  NodeEx n, DataFlowCallable c, FlowState state, AccessPathApprox apa, Configuration config
 ) {
-  exists(DataFlowCallable c, AccessPathApprox apa0 |
+  exists(AccessPathApprox apa0 |
-    Stage4::parameterMayFlowThrough(_, c, apa, _) and
+    Stage4::parameterMayFlowThrough(_, c, _, _) and
     Stage4::revFlow(n, state, true, _, apa0, config) and
     Stage4::fwdFlow(n, state, any(CallContextCall ccc), TAccessPathApproxSome(apa), apa0, config) and
     n.getEnclosingCallable() = c
   )
 }
 
+pragma[nomagic]
+private predicate nodeMayUseSummary(
+  NodeEx n, FlowState state, AccessPathApprox apa, Configuration config
+) {
+  exists(DataFlowCallable c |
+    Stage4::parameterMayFlowThrough(_, c, apa, config) and
+    nodeMayUseSummary0(n, c, state, apa, config)
+  )
+}
+
 private newtype TSummaryCtx =
   TSummaryCtxNone() or
   TSummaryCtxSome(ParamNodeEx p, FlowState state, AccessPath ap) {
@@ -3506,7 +3661,7 @@ private newtype TPathNode =
  * of dereference operations needed to get from the value in the node to the
  * tracked object. The final type indicates the type of the tracked object.
  */
-abstract private class AccessPath extends TAccessPath {
+private class AccessPath extends TAccessPath {
   /** Gets the head of this access path, if any. */
   abstract TypedContent getHead();
 
@@ -3721,11 +3876,14 @@ abstract private class PathNodeImpl extends PathNode {
   abstract NodeEx getNodeEx();
 
   predicate isHidden() {
-    hiddenNode(this.getNodeEx().asNode()) and
+    not this.getConfiguration().includeHiddenNodes() and
-    not this.isSource() and
+    (
-    not this instanceof PathNodeSink
+      hiddenNode(this.getNodeEx().asNode()) and
-    or
+      not this.isSource() and
-    this.getNodeEx() instanceof TNodeImplicitRead
+      not this instanceof PathNodeSink
+      or
+      this.getNodeEx() instanceof TNodeImplicitRead
+    )
   }
 
   private string ppAp() {
@@ -4202,10 +4360,16 @@ private module Subpaths {
     exists(NodeEx n1, NodeEx n2 | n1 = n.getNodeEx() and n2 = result.getNodeEx() |
       localFlowBigStep(n1, _, n2, _, _, _, _, _) or
       store(n1, _, n2, _, _) or
-      read(n1, _, n2, _)
+      readSet(n1, _, n2, _)
     )
   }
 
+  pragma[nomagic]
+  private predicate hasSuccessor(PathNode pred, PathNodeMid succ, NodeEx succNode) {
+    succ = pred.getASuccessor() and
+    succNode = succ.getNodeEx()
+  }
+
   /**
    * Holds if `(arg, par, ret, out)` forms a subpath-tuple, that is, flow through
    * a subpath between `par` and `ret` with the connecting edges `arg -> par` and
@@ -4213,15 +4377,13 @@ private module Subpaths {
    */
   predicate subpaths(PathNode arg, PathNodeImpl par, PathNodeImpl ret, PathNode out) {
     exists(ParamNodeEx p, NodeEx o, FlowState sout, AccessPath apout, PathNodeMid out0 |
-      pragma[only_bind_into](arg).getASuccessor() = par and
+      pragma[only_bind_into](arg).getASuccessor() = pragma[only_bind_into](out0) and
-      pragma[only_bind_into](arg).getASuccessor() = out0 and
+      subpaths03(pragma[only_bind_into](arg), p, localStepToHidden*(ret), o, sout, apout) and
-      subpaths03(arg, p, localStepToHidden*(ret), o, sout, apout) and
+      hasSuccessor(pragma[only_bind_into](arg), par, p) and
       not ret.isHidden() and
-      par.getNodeEx() = p and
+      pathNode(out0, o, sout, _, _, apout, _, _)
-      out0.getNodeEx() = o and
+    |
-      out0.getState() = sout and
+      out = out0 or out = out0.projectToSink()
-      out0.getAp() = apout and
-      (out = out0 or out = out0.projectToSink())
     )
   }
 
@@ -4557,7 +4719,11 @@ private module FlowExploration {
       or
       exists(PartialPathNodeRev mid |
         revPartialPathStep(mid, node, state, sc1, sc2, sc3, ap, config) and
-        not clearsContentCached(node.asNode(), ap.getHead()) and
+        not clearsContentEx(node, ap.getHead()) and
+        (
+          notExpectsContent(node) or
+          expectsContentEx(node, ap.getHead())
+        ) and
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4573,7 +4739,11 @@ private module FlowExploration {
       partialPathStep(mid, node, state, cc, sc1, sc2, sc3, ap, config) and
       not fullBarrier(node, config) and
       not stateBarrier(node, state, config) and
-      not clearsContentCached(node.asNode(), ap.getHead().getContent()) and
+      not clearsContentEx(node, ap.getHead().getContent()) and
+      (
+        notExpectsContent(node) or
+        expectsContentEx(node, ap.getHead().getContent())
+      ) and
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImplCommon.qll

@@ -216,10 +216,9 @@ private module LambdaFlow {
     or
     // jump step
     exists(Node mid, DataFlowType t0 |
-      revLambdaFlow(lambdaCall, kind, mid, t0, _, _, _) and
+      revLambdaFlow(lambdaCall, kind, mid, t0, _, _, lastCall) and
       toReturn = false and
-      toJump = true and
+      toJump = true
-      lastCall = TDataFlowCallNone()
     |
       jumpStepCached(node, mid) and
       t = t0
@@ -305,7 +304,7 @@ cached
 private module Cached {
   /**
    * If needed, call this predicate from `DataFlowImplSpecific.qll` in order to
-   * force a stage-dependency on the `DataFlowImplCommon.qll` stage and therby
+   * force a stage-dependency on the `DataFlowImplCommon.qll` stage and thereby
    * collapsing the two stages.
    */
   cached
@@ -326,7 +325,10 @@ private module Cached {
   predicate jumpStepCached(Node node1, Node node2) { jumpStep(node1, node2) }
 
   cached
-  predicate clearsContentCached(Node n, Content c) { clearsContent(n, c) }
+  predicate clearsContentCached(Node n, ContentSet c) { clearsContent(n, c) }
+
+  cached
+  predicate expectsContentCached(Node n, ContentSet c) { expectsContent(n, c) }
 
   cached
   predicate isUnreachableInCallCached(Node n, DataFlowCall call) { isUnreachableInCall(n, call) }
@@ -373,7 +375,7 @@ private module Cached {
     // For reads, `x.f`, we want to check that the tracked type after the read (which
     // is obtained by popping the head of the access path stack) is compatible with
     // the type of `x.f`.
-    read(_, _, n)
+    readSet(_, _, n)
   }
 
   cached
@@ -469,7 +471,7 @@ private module Cached {
         // read
         exists(Node mid |
           parameterValueFlowCand(p, mid, false) and
-          read(mid, _, node) and
+          readSet(mid, _, node) and
           read = true
         )
         or
@@ -657,8 +659,10 @@ private module Cached {
        * Holds if `arg` flows to `out` through a call using only
        * value-preserving steps and a single read step, not taking call
        * contexts into account, thus representing a getter-step.
+       *
+       * This predicate is exposed for testing only.
        */
-      predicate getterStep(ArgNode arg, Content c, Node out) {
+      predicate getterStep(ArgNode arg, ContentSet c, Node out) {
         argumentValueFlowsThrough(arg, TReadStepTypesSome(_, c, _), out)
       }
 
@@ -781,8 +785,12 @@ private module Cached {
     parameterValueFlow(p, n.getPreUpdateNode(), TReadStepTypesNone())
   }
 
-  private predicate store(
+  cached
-    Node node1, Content c, Node node2, DataFlowType contentType, DataFlowType containerType
+  predicate readSet(Node node1, ContentSet c, Node node2) { readStep(node1, c, node2) }
+
+  cached
+  predicate storeSet(
+    Node node1, ContentSet c, Node node2, DataFlowType contentType, DataFlowType containerType
   ) {
     storeStep(node1, c, node2) and
     contentType = getNodeDataFlowType(node1) and
@@ -794,14 +802,19 @@ private module Cached {
     |
       argumentValueFlowsThrough(n2, TReadStepTypesSome(containerType, c, contentType), n1)
       or
-      read(n2, c, n1) and
+      readSet(n2, c, n1) and
       contentType = getNodeDataFlowType(n1) and
       containerType = getNodeDataFlowType(n2)
     )
   }
 
-  cached
+  private predicate store(
-  predicate read(Node node1, Content c, Node node2) { readStep(node1, c, node2) }
+    Node node1, Content c, Node node2, DataFlowType contentType, DataFlowType containerType
+  ) {
+    exists(ContentSet cs |
+      c = cs.getAStoreContent() and storeSet(node1, cs, node2, contentType, containerType)
+    )
+  }
 
   /**
    * Holds if data can flow from `node1` to `node2` via a direct assignment to
@@ -932,16 +945,16 @@ class CastingNode extends Node {
 }
 
 private predicate readStepWithTypes(
-  Node n1, DataFlowType container, Content c, Node n2, DataFlowType content
+  Node n1, DataFlowType container, ContentSet c, Node n2, DataFlowType content
 ) {
-  read(n1, c, n2) and
+  readSet(n1, c, n2) and
   container = getNodeDataFlowType(n1) and
   content = getNodeDataFlowType(n2)
 }
 
 private newtype TReadStepTypesOption =
   TReadStepTypesNone() or
-  TReadStepTypesSome(DataFlowType container, Content c, DataFlowType content) {
+  TReadStepTypesSome(DataFlowType container, ContentSet c, DataFlowType content) {
     readStepWithTypes(_, container, c, _, content)
   }
 
@@ -950,7 +963,7 @@ private class ReadStepTypesOption extends TReadStepTypesOption {
 
   DataFlowType getContainerType() { this = TReadStepTypesSome(result, _, _) }
 
-  Content getContent() { this = TReadStepTypesSome(_, result, _) }
+  ContentSet getContent() { this = TReadStepTypesSome(_, result, _) }
 
   DataFlowType getContentType() { this = TReadStepTypesSome(_, _, result) }
 
@@ -1325,8 +1338,6 @@ abstract class AccessPathFront extends TAccessPathFront {
   abstract boolean toBoolNonEmpty();
 
   TypedContent getHead() { this = TFrontHead(result) }
-
-  predicate isClearedAt(Node n) { clearsContentCached(n, this.getHead().getContent()) }
 }
 
 class AccessPathFrontNil extends AccessPathFront, TFrontNil {

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowPrivate.qll

@@ -279,6 +279,12 @@ predicate clearsContent(Node n, Content c) {
   none() // stub implementation
 }
 
+/**
+ * Holds if the value that is being tracked is expected to be stored inside content `c`
+ * at node `n`.
+ */
+predicate expectsContent(Node n, ContentSet c) { none() }
+
 /** Gets the type of `n` used for type pruning. */
 IRType getNodeType(Node n) {
   suppressUnusedNode(n) and

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowUtil.qll

@@ -37,7 +37,7 @@ private module Cached {
    *      along the chain of addresses computed by `StoreNodeInstr.getInner` to identify field writes
    *      and call `storeStep` accordingly (i.e., for an expression like `a.b.c = x`, we visit `c`, then
    *      `b`, then `a`).
-   *   2. Flow is transfered from a `WriteSideEffectInstruction` to a `StoreNodeOperand` after flow
+   *   2. Flow is transferred from a `WriteSideEffectInstruction` to a `StoreNodeOperand` after flow
    *      returns to a caller. Flow will then proceed to the defining instruction of the operand (because
    *      the `StoreNodeInstr` computed by `StoreNodeOperand.getInner()` is the `StoreNode` containing
    *      the defining instruction), and then along the chain computed by `StoreNodeInstr.getInner` like
@@ -1063,6 +1063,34 @@ private class CollectionContent extends Content, TCollectionContent {
   override string toString() { result = "<element>" }
 }
 
+/**
+ * An entity that represents a set of `Content`s.
+ *
+ * The set may be interpreted differently depending on whether it is
+ * stored into (`getAStoreContent`) or read from (`getAReadContent`).
+ */
+class ContentSet instanceof Content {
+  /** Gets a content that may be stored into when storing into this set. */
+  Content getAStoreContent() { result = this }
+
+  /** Gets a content that may be read from when reading from this set. */
+  Content getAReadContent() { result = this }
+
+  /** Gets a textual representation of this content set. */
+  string toString() { result = super.toString() }
+
+  /**
+   * Holds if this element is at the specified location.
+   * The location spans column `startcolumn` of line `startline` to
+   * column `endcolumn` of line `endline` in file `filepath`.
+   * For more information, see
+   * [Locations](https://codeql.github.com/docs/writing-codeql-queries/providing-locations-in-codeql-queries/).
+   */
+  predicate hasLocationInfo(string path, int sl, int sc, int el, int ec) {
+    super.hasLocationInfo(path, sl, sc, el, ec)
+  }
+}
+
 /**
  * A guard that validates some instruction.
  *

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/tainttracking1/TaintTrackingImpl.qll

@@ -161,7 +161,7 @@ abstract class Configuration extends DataFlow::Configuration {
     this.isAdditionalTaintStep(node1, state1, node2, state2)
   }
 
-  override predicate allowImplicitRead(DataFlow::Node node, DataFlow::Content c) {
+  override predicate allowImplicitRead(DataFlow::Node node, DataFlow::ContentSet c) {
     (this.isSink(node) or this.isAdditionalTaintStep(node, _)) and
     defaultImplicitTaintRead(node, c)
   }

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/tainttracking2/TaintTrackingImpl.qll

@@ -161,7 +161,7 @@ abstract class Configuration extends DataFlow::Configuration {
     this.isAdditionalTaintStep(node1, state1, node2, state2)
   }
 
-  override predicate allowImplicitRead(DataFlow::Node node, DataFlow::Content c) {
+  override predicate allowImplicitRead(DataFlow::Node node, DataFlow::ContentSet c) {
     (this.isSink(node) or this.isAdditionalTaintStep(node, _)) and
     defaultImplicitTaintRead(node, c)
   }

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/tainttracking3/TaintTrackingImpl.qll

@@ -161,7 +161,7 @@ abstract class Configuration extends DataFlow::Configuration {
     this.isAdditionalTaintStep(node1, state1, node2, state2)
   }
 
-  override predicate allowImplicitRead(DataFlow::Node node, DataFlow::Content c) {
+  override predicate allowImplicitRead(DataFlow::Node node, DataFlow::ContentSet c) {
     (this.isSink(node) or this.isAdditionalTaintStep(node, _)) and
     defaultImplicitTaintRead(node, c)
   }

cpp/ql/lib/semmle/code/cpp/ir/implementation/EdgeKind.qll

@@ -67,7 +67,7 @@ class DefaultEdge extends EdgeKind, TDefaultEdge {
 
 /**
  * A "case" edge, representing the successor of a `Switch` instruction when the
- * the condition value matches a correponding `case` label.
+ * the condition value matches a corresponding `case` label.
  */
 class CaseEdge extends EdgeKind, TCaseEdge {
   string minValue;

cpp/ql/lib/semmle/code/cpp/ir/implementation/aliased_ssa/gvn/ValueNumbering.qll

@@ -34,7 +34,7 @@ class ValueNumber extends TValueNumber {
   final Instruction getAnInstruction() { this = valueNumber(result) }
 
   /**
-   * Gets one of the instructions that was assigned this value number. The chosen instuction is
+   * Gets one of the instructions that was assigned this value number. The chosen instruction is
    * deterministic but arbitrary. Intended for use only in debugging.
    */
   final Instruction getExampleInstruction() {

cpp/ql/lib/semmle/code/cpp/ir/implementation/aliased_ssa/internal/SSAConstruction.qll

@@ -1005,7 +1005,7 @@ predicate canReuseSsaForMemoryResult(Instruction instruction) {
 deprecated predicate canReuseSSAForMemoryResult = canReuseSsaForMemoryResult/1;
 
 /**
- * Expose some of the internal predicates to PrintSSA.qll. We do this by publically importing those modules in the
+ * Expose some of the internal predicates to PrintSSA.qll. We do this by publicly importing those modules in the
  * `DebugSSA` module, which is then imported by PrintSSA.
  */
 module DebugSsa {

cpp/ql/lib/semmle/code/cpp/ir/implementation/raw/gvn/ValueNumbering.qll

@@ -34,7 +34,7 @@ class ValueNumber extends TValueNumber {
   final Instruction getAnInstruction() { this = valueNumber(result) }
 
   /**
-   * Gets one of the instructions that was assigned this value number. The chosen instuction is
+   * Gets one of the instructions that was assigned this value number. The chosen instruction is
    * deterministic but arbitrary. Intended for use only in debugging.
    */
   final Instruction getExampleInstruction() {

cpp/ql/lib/semmle/code/cpp/ir/implementation/raw/internal/TranslatedExpr.qll

@@ -11,7 +11,6 @@ private import TranslatedDeclarationEntry
 private import TranslatedElement
 private import TranslatedFunction
 private import TranslatedInitialization
-private import TranslatedFunction
 private import TranslatedStmt
 import TranslatedCall
 

cpp/ql/lib/semmle/code/cpp/ir/implementation/raw/internal/TranslatedStmt.qll

@@ -421,20 +421,36 @@ class TranslatedCatchAnyHandler extends TranslatedHandler {
 class TranslatedIfStmt extends TranslatedStmt, ConditionContext {
   override IfStmt stmt;
 
-  override Instruction getFirstInstruction() { result = getCondition().getFirstInstruction() }
+  override Instruction getFirstInstruction() {
+    if hasInitialization()
+    then result = getInitialization().getFirstInstruction()
+    else result = getFirstConditionInstruction()
+  }
 
   override TranslatedElement getChild(int id) {
-    id = 0 and result = getCondition()
+    id = 0 and result = getInitialization()
     or
-    id = 1 and result = getThen()
+    id = 1 and result = getCondition()
     or
-    id = 2 and result = getElse()
+    id = 2 and result = getThen()
+    or
+    id = 3 and result = getElse()
+  }
+
+  private predicate hasInitialization() { exists(stmt.getInitialization()) }
+
+  private TranslatedStmt getInitialization() {
+    result = getTranslatedStmt(stmt.getInitialization())
   }
 
   private TranslatedCondition getCondition() {
     result = getTranslatedCondition(stmt.getCondition().getFullyConverted())
   }
 
+  private Instruction getFirstConditionInstruction() {
+    result = getCondition().getFirstInstruction()
+  }
+
   private TranslatedStmt getThen() { result = getTranslatedStmt(stmt.getThen()) }
 
   private TranslatedStmt getElse() { result = getTranslatedStmt(stmt.getElse()) }
@@ -456,6 +472,9 @@ class TranslatedIfStmt extends TranslatedStmt, ConditionContext {
   }
 
   override Instruction getChildSuccessor(TranslatedElement child) {
+    child = getInitialization() and
+    result = getFirstConditionInstruction()
+    or
     (child = getThen() or child = getElse()) and
     result = getParent().getChildSuccessor(this)
   }
@@ -698,14 +717,28 @@ class TranslatedSwitchStmt extends TranslatedStmt {
     result = getTranslatedExpr(stmt.getExpr().getFullyConverted())
   }
 
+  private Instruction getFirstExprInstruction() { result = getExpr().getFirstInstruction() }
+
   private TranslatedStmt getBody() { result = getTranslatedStmt(stmt.getStmt()) }
 
-  override Instruction getFirstInstruction() { result = getExpr().getFirstInstruction() }
+  override Instruction getFirstInstruction() {
+    if hasInitialization()
+    then result = getInitialization().getFirstInstruction()
+    else result = getFirstExprInstruction()
+  }
 
   override TranslatedElement getChild(int id) {
-    id = 0 and result = getExpr()
+    id = 0 and result = getInitialization()
     or
-    id = 1 and result = getBody()
+    id = 1 and result = getExpr()
+    or
+    id = 2 and result = getBody()
+  }
+
+  private predicate hasInitialization() { exists(stmt.getInitialization()) }
+
+  private TranslatedStmt getInitialization() {
+    result = getTranslatedStmt(stmt.getInitialization())
   }
 
   override predicate hasInstruction(Opcode opcode, InstructionTag tag, CppType resultType) {
@@ -735,6 +768,8 @@ class TranslatedSwitchStmt extends TranslatedStmt {
   }
 
   override Instruction getChildSuccessor(TranslatedElement child) {
+    child = getInitialization() and result = getFirstExprInstruction()
+    or
     child = getExpr() and result = getInstruction(SwitchBranchTag())
     or
     child = getBody() and result = getParent().getChildSuccessor(this)

cpp/ql/lib/semmle/code/cpp/ir/implementation/unaliased_ssa/gvn/ValueNumbering.qll

@@ -34,7 +34,7 @@ class ValueNumber extends TValueNumber {
   final Instruction getAnInstruction() { this = valueNumber(result) }
 
   /**
-   * Gets one of the instructions that was assigned this value number. The chosen instuction is
+   * Gets one of the instructions that was assigned this value number. The chosen instruction is
    * deterministic but arbitrary. Intended for use only in debugging.
    */
   final Instruction getExampleInstruction() {

cpp/ql/lib/semmle/code/cpp/ir/implementation/unaliased_ssa/internal/SSAConstruction.qll

@@ -1005,7 +1005,7 @@ predicate canReuseSsaForMemoryResult(Instruction instruction) {
 deprecated predicate canReuseSSAForMemoryResult = canReuseSsaForMemoryResult/1;
 
 /**
- * Expose some of the internal predicates to PrintSSA.qll. We do this by publically importing those modules in the
+ * Expose some of the internal predicates to PrintSSA.qll. We do this by publicly importing those modules in the
  * `DebugSSA` module, which is then imported by PrintSSA.
  */
 module DebugSsa {

cpp/ql/lib/semmle/code/cpp/ir/internal/CppType.qll

@@ -141,7 +141,7 @@ private predicate isOpaqueType(Type type) {
  * Holds if an `IROpaqueType` with the specified `tag` and `byteSize` should exist.
  */
 predicate hasOpaqueType(Type tag, int byteSize) {
-  isOpaqueType(tag) and byteSize = getTypeSize(tag)
+  isOpaqueType(tag) and byteSize = getTypeSize(tag.getUnspecifiedType())
   or
   tag instanceof UnknownType and Raw::needsUnknownOpaqueType(byteSize)
 }
@@ -153,17 +153,18 @@ private IRType getIRTypeForPRValue(Type type) {
   exists(Type unspecifiedType | unspecifiedType = type.getUnspecifiedType() |
     isOpaqueType(unspecifiedType) and
     exists(IROpaqueType opaqueType | opaqueType = result |
-      opaqueType.getByteSize() = getTypeSize(type) and
+      opaqueType.getByteSize() = getTypeSize(unspecifiedType) and
       opaqueType.getTag() = unspecifiedType
     )
     or
-    unspecifiedType instanceof BoolType and result.(IRBooleanType).getByteSize() = type.getSize()
+    unspecifiedType instanceof BoolType and
+    result.(IRBooleanType).getByteSize() = unspecifiedType.getSize()
     or
     isSignedIntegerType(unspecifiedType) and
-    result.(IRSignedIntegerType).getByteSize() = type.getSize()
+    result.(IRSignedIntegerType).getByteSize() = unspecifiedType.getSize()
     or
     isUnsignedIntegerType(unspecifiedType) and
-    result.(IRUnsignedIntegerType).getByteSize() = type.getSize()
+    result.(IRUnsignedIntegerType).getByteSize() = unspecifiedType.getSize()
     or
     exists(FloatingPointType floatType, IRFloatingPointType irFloatType |
       floatType = unspecifiedType and
@@ -173,7 +174,8 @@ private IRType getIRTypeForPRValue(Type type) {
       irFloatType.getDomain() = floatType.getDomain()
     )
     or
-    isPointerIshType(unspecifiedType) and result.(IRAddressType).getByteSize() = getTypeSize(type)
+    isPointerIshType(unspecifiedType) and
+    result.(IRAddressType).getByteSize() = getTypeSize(unspecifiedType)
     or
     unspecifiedType instanceof FunctionPointerIshType and
     result.(IRFunctionAddressType).getByteSize() = getTypeSize(type)