Revert "JS: Recognize DomSanitizer from @angular/core"

This reverts commit ff1d0cc4c7.

.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

.github/actions/fetch-codeql/action.yml

@@ -3,12 +3,22 @@ description: Fetches the latest version of CodeQL
 runs:
   using: composite
   steps:
+    - name: Select platform - Linux
+      if: runner.os == 'Linux'
+      shell: bash
+      run: echo "GA_CODEQL_CLI_PLATFORM=linux64" >> $GITHUB_ENV
+
+    - name: Select platform - MacOS
+      if: runner.os == 'MacOS'
+      shell: bash
+      run: echo "GA_CODEQL_CLI_PLATFORM=osx64" >> $GITHUB_ENV
+
     - name: Fetch CodeQL
       shell: bash
       run: |
         LATEST=$(gh release list --repo https://github.com/github/codeql-cli-binaries | cut -f 1 | grep -v beta | sort --version-sort | tail -1)
-        gh release download --repo https://github.com/github/codeql-cli-binaries --pattern codeql-linux64.zip "$LATEST"
-        unzip -q -d "${RUNNER_TEMP}" codeql-linux64.zip
+        gh release download --repo https://github.com/github/codeql-cli-binaries --pattern codeql-$GA_CODEQL_CLI_PLATFORM.zip "$LATEST"
+        unzip -q -d "${RUNNER_TEMP}" codeql-$GA_CODEQL_CLI_PLATFORM.zip
         echo "${RUNNER_TEMP}/codeql" >> "${GITHUB_PATH}"
       env:
         GITHUB_TOKEN: ${{ github.token }}

.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

@@ -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/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
 
     - 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
-      - uses: actions/upload-artifact@v2
+          codeql database analyze --format=sarif-latest --output=metrics-java.sarif -- "$DATABASE" ./java/ql/src/Metrics/Summaries/FrameworkCoverage.ql
+      - uses: actions/upload-artifact@v3
         with:
-          name: metrics.sarif
-          path: metrics.sarif
+          name: metrics-java.sarif
+          path: metrics-java.sarif
           retention-days: 20
       - name: Upload SARIF file
         uses: github/codeql-action/upload-sarif@v1
         with:
-          sarif_file: metrics.sarif
+          sarif_file: metrics-java.sarif
+  
+  publish-csharp:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+      - name: Setup CodeQL
+        uses: ./.github/actions/fetch-codeql
+      - name: Create empty database
+        run: |
+          DATABASE="${{ 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@v1
+        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/js-ml-tests.yml

@@ -22,7 +22,7 @@ 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 +35,7 @@ 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 +59,7 @@ 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 "${{  github.event.number }}" > pr.txt
-      - uses: actions/upload-artifact@v2
+      - run: echo "${PR_NUMBER}" > pr_number.txt
+        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/download-artifact@v2
+      - uses: actions/checkout@v3
+      - 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]
 
     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

@@ -22,14 +22,14 @@ jobs:
           - 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 +41,7 @@ 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: ${{ github.workspace }}/repo
@@ -60,7 +60,7 @@ jobs:
           "${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 +70,15 @@ jobs:
     runs-on: ubuntu-latest
     needs: measure
     steps:
-      - uses: actions/checkout@v2
-      - uses: actions/download-artifact@v2
+      - uses: actions/checkout@v3
+      - 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
-      - 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

@@ -17,16 +17,16 @@ 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
+      uses: actions/checkout@v3
       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
@@ -42,7 +42,7 @@ jobs:
       run: |
         PATH="$PATH:codeql-cli/codeql" 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/download-artifact@v2
+      - uses: actions/checkout@v3
+      - 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/download-artifact@v2
+      - uses: actions/checkout@v3
+      - 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
+      - uses: actions/setup-python@v3
+        with:
+          python-version: '~3.8'
+          cache: 'pip'
+      - name: Install python dependencies
+        run: |
+          pip install -r swift/codegen/requirements.txt
+      - name: Run unit tests
+        run: |
+          bazel test //swift/codegen/test --test_output=errors
+      - name: Check that code was generated
+        run: |
+          bazel run //swift/codegen
+          git add swift
+          git diff --exit-code --stat HEAD

.github/workflows/swift-qltest.yml

@@ -0,0 +1,46 @@
+name: "Swift: Run QL Tests"
+
+on:
+  pull_request:
+    paths:
+      - "swift/**"
+      - .github/workflows/swift-qltest.yml
+    branches:
+      - main
+defaults:
+  run:
+    working-directory: swift
+
+jobs:
+  qlformat:
+    runs-on: ubuntu-latest
+    steps:
+      - 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
+  qltest:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os : [ubuntu-20.04, macos-latest]
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./.github/actions/fetch-codeql
+      - uses: bazelbuild/setup-bazelisk@v2
+      - uses: actions/setup-python@v3
+        with:
+          python-version: '~3.8'
+          cache: 'pip'
+      - name: Install python dependencies
+        run: |
+          pip install -r codegen/requirements.txt
+      - name: Build Swift extractor
+        run: |
+          bazel run //swift:create-extractor-pack
+      - name: Run QL tests
+        run: |
+          codeql test run --threads=0 --ram 5000 --search-path "${{ 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

@@ -20,6 +20,9 @@
 # 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/
 

.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/.*$(?<!\.ql)(?<!\.qll)(?<!\.qlref)
 repos:
--   repo: https://github.com/pre-commit/pre-commit-hooks
+  - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v3.2.0
     hooks:
-    -   id: trailing-whitespace
-    -   id: end-of-file-fixer
+      - id: trailing-whitespace
+        exclude: /test/.*$(?<!\.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

@@ -27,3 +27,13 @@
 # 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/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

@@ -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
 

WORKSPACE.bazel

@@ -1,12 +1,12 @@
 # Please notice that any bazel targets and definitions in this repository are currently experimental
 # and for internal use only.
 
-workspace(name = "ql")
+workspace(name = "codeql")
 
-load("//misc/bazel:workspace.bzl", "ql_workspace")
+load("//misc/bazel:workspace.bzl", "codeql_workspace")
 
-ql_workspace()
+codeql_workspace()
 
-load("//misc/bazel:workspace_deps.bzl", "ql_workspace_deps")
+load("//misc/bazel:workspace_deps.bzl", "codeql_workspace_deps")
 
-ql_workspace_deps()
+codeql_workspace_deps()

config/identical-files.json

@@ -51,6 +51,7 @@
     "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",
@@ -383,7 +384,8 @@
     "csharp/ql/test/TestUtilities/InlineExpectationsTest.qll",
     "java/ql/test/TestUtilities/InlineExpectationsTest.qll",
     "python/ql/test/TestUtilities/InlineExpectationsTest.qll",
-    "ruby/ql/test/TestUtilities/InlineExpectationsTest.qll"
+    "ruby/ql/test/TestUtilities/InlineExpectationsTest.qll",
+    "ql/ql/test/TestUtilities/InlineExpectationsTest.qll"
   ],
   "C++ ExternalAPIs": [
     "cpp/ql/src/Security/CWE/CWE-020/ExternalAPIs.qll",
@@ -549,4 +551,4 @@
     "javascript/ql/lib/semmle/javascript/security/dataflow/HttpToFileAccessCustomizations.qll",
     "ruby/ql/lib/codeql/ruby/security/HttpToFileAccessCustomizations.qll"
   ]
-}
+}

conftest.py

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

cpp/ql/lib/CHANGELOG.md

@@ -1,3 +1,17 @@
+## 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/2022-04-22-no-size-array.md

@@ -0,0 +1,4 @@
+---
+category: minorAnalysis
+---
+* 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/2022-04-25-allow-implicit-read-signature.md

@@ -0,0 +1,4 @@
+---
+category: breaking
+---
+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)`.

cpp/ql/lib/change-notes/2022-04-25-windows-pool-allocation-functions.md

@@ -0,0 +1,4 @@
+---
+category: minorAnalysis
+---
+* More Windows pool allocation functions are now detected as `AllocationFunction`s.

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/codeql-pack.release.yml

@@ -1,2 +1,2 @@
 ---
-lastReleaseVersion: 0.0.13
+lastReleaseVersion: 0.1.0

cpp/ql/lib/qlpack.yml

@@ -1,5 +1,5 @@
 name: codeql/cpp-all
-version: 0.1.0-dev
+version: 0.1.1-dev
 groups: cpp
 dbscheme: semmlecode.cpp.dbscheme
 extractor: cpp

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

@@ -84,6 +84,7 @@ private int fileHeaderLimit(File f) {
     fc = fileFirstComment(f) and
     result =
       min(int line |
+        // code ending the initial comments
         exists(DeclarationEntry de, Location l |
           l = de.getLocation() and
           l.getFile() = f and
@@ -105,7 +106,13 @@ private int fileHeaderLimit(File f) {
           line > fc
         )
         or
+        // end of the file
         line = f.getMetrics().getNumberOfLines()
+        or
+        // rarely, we've seen extremely long sequences of initial comments
+        // (and/or limitations in the above constraints) cause an overflow of
+        // the maximum string length. So don't look past 1000 lines regardless.
+        line = 1000
       )
   )
 }

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 |
-          this = closer.getAGeneratedElement() and
-          mi = closer.getParentInvocation+()
-        ) and
+        not hasCloserMacroInvocation(this, mi) 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

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
-    or
+    // zero sized arrays are likely to have special usage, for example
     // behaving a bit like a 'union' overlapping other fields.
-    // buffer is an initialized array
-    //  e.g. int buffer[] = {1, 2, 3};
+    not result = 0
+    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/dataflow/internal/DataFlowImpl.qll

@@ -87,21 +87,9 @@ abstract class Configuration extends string {
   /** Holds if data flow into `node` is prohibited. */
   predicate isBarrierIn(Node node) { none() }
 
-  /**
-   * Holds if data flow into `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierIn(Node node, FlowState state) { none() }
-
   /** Holds if data flow out of `node` is prohibited. */
   predicate isBarrierOut(Node node) { none() }
 
-  /**
-   * Holds if data flow out of `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierOut(Node node, FlowState state) { none() }
-
   /** Holds if data flow through nodes guarded by `guard` is prohibited. */
   predicate isBarrierGuard(BarrierGuard guard) { none() }
 
@@ -128,7 +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.
@@ -321,7 +309,7 @@ private class RetNodeEx extends NodeEx {
   ReturnKindExt getKind() { result = this.asNode().(ReturnNodeExt).getKind() }
 }
 
-private predicate fullInBarrier(NodeEx node, Configuration config) {
+private predicate inBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierIn(n)
@@ -330,16 +318,7 @@ private predicate fullInBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateInBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierIn(n, state)
-  |
-    config.isSource(n, state)
-  )
-}
-
-private predicate fullOutBarrier(NodeEx node, Configuration config) {
+private predicate outBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierOut(n)
@@ -348,15 +327,6 @@ private predicate fullOutBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateOutBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierOut(n, state)
-  |
-    config.isSink(n, state)
-  )
-}
-
 pragma[nomagic]
 private predicate fullBarrier(NodeEx node, Configuration config) {
   exists(Node n | node.asNode() = n |
@@ -382,12 +352,6 @@ private predicate stateBarrier(NodeEx node, FlowState state, Configuration confi
   exists(Node n | node.asNode() = n |
     config.isBarrier(n, state)
     or
-    config.isBarrierIn(n, state) and
-    not config.isSource(n, state)
-    or
-    config.isBarrierOut(n, state) and
-    not config.isSink(n, state)
-    or
     exists(BarrierGuard g |
       config.isBarrierGuard(g, state) and
       n = g.getAGuardedNode()
@@ -420,8 +384,8 @@ private predicate sinkNode(NodeEx node, FlowState state, Configuration config) {
 /** Provides the relevant barriers for a step from `node1` to `node2`. */
 pragma[inline]
 private predicate stepFilter(NodeEx node1, NodeEx node2, Configuration config) {
-  not fullOutBarrier(node1, config) and
-  not fullInBarrier(node2, config) and
+  not outBarrier(node1, config) and
+  not inBarrier(node2, config) and
   not fullBarrier(node1, config) and
   not fullBarrier(node2, config)
 }
@@ -474,8 +438,6 @@ private predicate additionalLocalStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) = getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config)
   )
@@ -517,16 +479,15 @@ private predicate additionalJumpStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) != getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config) and
     not config.getAFeature() instanceof FeatureEqualSourceSinkCallContext
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
-  read(node1.asNode(), c, node2.asNode()) and
+pragma[nomagic]
+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 |
@@ -536,6 +497,25 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    c = cs.getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    c = cs.getAReadContent()
+  )
+}
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -613,9 +593,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
-      fwdFlowRead(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+    exists(ContentSet c |
+      fwdFlowReadSet(c, node, cc, config) and
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -639,10 +619,10 @@ 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)
     )
   }
 
@@ -660,6 +640,16 @@ 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 |
@@ -752,9 +742,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
-      read(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+    exists(NodeEx mid, ContentSet c |
+      readSet(node, c, mid, config) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -780,10 +770,10 @@ 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
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      readSet(node, cs, mid, config) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -802,6 +792,7 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
+  pragma[nomagic]
   private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
@@ -900,9 +891,9 @@ 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))
+    revFlowIsReadAndStored(pragma[only_bind_into](c), pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -912,14 +903,17 @@ 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) {
     revFlow(node, true, config) and
     fwdFlow(node, true, config) and
-    not fullInBarrier(node, config) and
-    not fullOutBarrier(node, config)
+    not inBarrier(node, config) and
+    not outBarrier(node, config)
   }
 
   /** Holds if flow may return from `callable`. */
@@ -1014,8 +1008,8 @@ private predicate flowOutOfCallNodeCand1(
 ) {
   viableReturnPosOutNodeCand1(call, ret.getReturnPosition(), out, config) and
   Stage1::revFlow(ret, config) and
-  not fullOutBarrier(ret, config) and
-  not fullInBarrier(out, config)
+  not outBarrier(ret, config) and
+  not inBarrier(out, config)
 }
 
 pragma[nomagic]
@@ -1036,8 +1030,8 @@ private predicate flowIntoCallNodeCand1(
 ) {
   viableParamArgNodeCand1(call, p, arg, config) and
   Stage1::revFlow(p, config) and
-  not fullOutBarrier(arg, config) and
-  not fullInBarrier(p, config)
+  not outBarrier(arg, config) and
+  not inBarrier(p, config)
 }
 
 /**
@@ -1189,7 +1183,7 @@ private module Stage2 {
 
   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)
   }
@@ -1614,7 +1608,7 @@ 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)
     )
@@ -1769,9 +1763,9 @@ 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
@@ -1792,8 +1786,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::storeStepCand(node, _, _, next, _, config) or
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1966,7 +1960,24 @@ 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 castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1975,7 +1986,7 @@ 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()
   }
 
@@ -2403,7 +2414,7 @@ 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)
     )
@@ -3230,7 +3241,7 @@ 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)
     )
@@ -4242,7 +4253,7 @@ 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, _)
     )
   }
 
@@ -4597,7 +4608,7 @@ 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
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4613,7 +4624,7 @@ 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
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()
@@ -5047,6 +5058,7 @@ private module FlowExploration {
     )
   }
 
+  pragma[nomagic]
   private predicate revPartialPathStep(
     PartialPathNodeRev mid, NodeEx node, FlowState state, TRevSummaryCtx1 sc1, TRevSummaryCtx2 sc2,
     TRevSummaryCtx3 sc3, RevPartialAccessPath ap, Configuration config

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

@@ -87,21 +87,9 @@ abstract class Configuration extends string {
   /** Holds if data flow into `node` is prohibited. */
   predicate isBarrierIn(Node node) { none() }
 
-  /**
-   * Holds if data flow into `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierIn(Node node, FlowState state) { none() }
-
   /** Holds if data flow out of `node` is prohibited. */
   predicate isBarrierOut(Node node) { none() }
 
-  /**
-   * Holds if data flow out of `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierOut(Node node, FlowState state) { none() }
-
   /** Holds if data flow through nodes guarded by `guard` is prohibited. */
   predicate isBarrierGuard(BarrierGuard guard) { none() }
 
@@ -128,7 +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.
@@ -321,7 +309,7 @@ private class RetNodeEx extends NodeEx {
   ReturnKindExt getKind() { result = this.asNode().(ReturnNodeExt).getKind() }
 }
 
-private predicate fullInBarrier(NodeEx node, Configuration config) {
+private predicate inBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierIn(n)
@@ -330,16 +318,7 @@ private predicate fullInBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateInBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierIn(n, state)
-  |
-    config.isSource(n, state)
-  )
-}
-
-private predicate fullOutBarrier(NodeEx node, Configuration config) {
+private predicate outBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierOut(n)
@@ -348,15 +327,6 @@ private predicate fullOutBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateOutBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierOut(n, state)
-  |
-    config.isSink(n, state)
-  )
-}
-
 pragma[nomagic]
 private predicate fullBarrier(NodeEx node, Configuration config) {
   exists(Node n | node.asNode() = n |
@@ -382,12 +352,6 @@ private predicate stateBarrier(NodeEx node, FlowState state, Configuration confi
   exists(Node n | node.asNode() = n |
     config.isBarrier(n, state)
     or
-    config.isBarrierIn(n, state) and
-    not config.isSource(n, state)
-    or
-    config.isBarrierOut(n, state) and
-    not config.isSink(n, state)
-    or
     exists(BarrierGuard g |
       config.isBarrierGuard(g, state) and
       n = g.getAGuardedNode()
@@ -420,8 +384,8 @@ private predicate sinkNode(NodeEx node, FlowState state, Configuration config) {
 /** Provides the relevant barriers for a step from `node1` to `node2`. */
 pragma[inline]
 private predicate stepFilter(NodeEx node1, NodeEx node2, Configuration config) {
-  not fullOutBarrier(node1, config) and
-  not fullInBarrier(node2, config) and
+  not outBarrier(node1, config) and
+  not inBarrier(node2, config) and
   not fullBarrier(node1, config) and
   not fullBarrier(node2, config)
 }
@@ -474,8 +438,6 @@ private predicate additionalLocalStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) = getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config)
   )
@@ -517,16 +479,15 @@ private predicate additionalJumpStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) != getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config) and
     not config.getAFeature() instanceof FeatureEqualSourceSinkCallContext
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
-  read(node1.asNode(), c, node2.asNode()) and
+pragma[nomagic]
+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 |
@@ -536,6 +497,25 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    c = cs.getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    c = cs.getAReadContent()
+  )
+}
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -613,9 +593,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
-      fwdFlowRead(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+    exists(ContentSet c |
+      fwdFlowReadSet(c, node, cc, config) and
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -639,10 +619,10 @@ 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)
     )
   }
 
@@ -660,6 +640,16 @@ 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 |
@@ -752,9 +742,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
-      read(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+    exists(NodeEx mid, ContentSet c |
+      readSet(node, c, mid, config) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -780,10 +770,10 @@ 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
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      readSet(node, cs, mid, config) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -802,6 +792,7 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
+  pragma[nomagic]
   private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
@@ -900,9 +891,9 @@ 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))
+    revFlowIsReadAndStored(pragma[only_bind_into](c), pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -912,14 +903,17 @@ 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) {
     revFlow(node, true, config) and
     fwdFlow(node, true, config) and
-    not fullInBarrier(node, config) and
-    not fullOutBarrier(node, config)
+    not inBarrier(node, config) and
+    not outBarrier(node, config)
   }
 
   /** Holds if flow may return from `callable`. */
@@ -1014,8 +1008,8 @@ private predicate flowOutOfCallNodeCand1(
 ) {
   viableReturnPosOutNodeCand1(call, ret.getReturnPosition(), out, config) and
   Stage1::revFlow(ret, config) and
-  not fullOutBarrier(ret, config) and
-  not fullInBarrier(out, config)
+  not outBarrier(ret, config) and
+  not inBarrier(out, config)
 }
 
 pragma[nomagic]
@@ -1036,8 +1030,8 @@ private predicate flowIntoCallNodeCand1(
 ) {
   viableParamArgNodeCand1(call, p, arg, config) and
   Stage1::revFlow(p, config) and
-  not fullOutBarrier(arg, config) and
-  not fullInBarrier(p, config)
+  not outBarrier(arg, config) and
+  not inBarrier(p, config)
 }
 
 /**
@@ -1189,7 +1183,7 @@ private module Stage2 {
 
   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)
   }
@@ -1614,7 +1608,7 @@ 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)
     )
@@ -1769,9 +1763,9 @@ 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
@@ -1792,8 +1786,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::storeStepCand(node, _, _, next, _, config) or
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1966,7 +1960,24 @@ 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 castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1975,7 +1986,7 @@ 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()
   }
 
@@ -2403,7 +2414,7 @@ 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)
     )
@@ -3230,7 +3241,7 @@ 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)
     )
@@ -4242,7 +4253,7 @@ 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, _)
     )
   }
 
@@ -4597,7 +4608,7 @@ 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
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4613,7 +4624,7 @@ 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
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()
@@ -5047,6 +5058,7 @@ private module FlowExploration {
     )
   }
 
+  pragma[nomagic]
   private predicate revPartialPathStep(
     PartialPathNodeRev mid, NodeEx node, FlowState state, TRevSummaryCtx1 sc1, TRevSummaryCtx2 sc2,
     TRevSummaryCtx3 sc3, RevPartialAccessPath ap, Configuration config

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

@@ -87,21 +87,9 @@ abstract class Configuration extends string {
   /** Holds if data flow into `node` is prohibited. */
   predicate isBarrierIn(Node node) { none() }
 
-  /**
-   * Holds if data flow into `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierIn(Node node, FlowState state) { none() }
-
   /** Holds if data flow out of `node` is prohibited. */
   predicate isBarrierOut(Node node) { none() }
 
-  /**
-   * Holds if data flow out of `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierOut(Node node, FlowState state) { none() }
-
   /** Holds if data flow through nodes guarded by `guard` is prohibited. */
   predicate isBarrierGuard(BarrierGuard guard) { none() }
 
@@ -128,7 +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.
@@ -321,7 +309,7 @@ private class RetNodeEx extends NodeEx {
   ReturnKindExt getKind() { result = this.asNode().(ReturnNodeExt).getKind() }
 }
 
-private predicate fullInBarrier(NodeEx node, Configuration config) {
+private predicate inBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierIn(n)
@@ -330,16 +318,7 @@ private predicate fullInBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateInBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierIn(n, state)
-  |
-    config.isSource(n, state)
-  )
-}
-
-private predicate fullOutBarrier(NodeEx node, Configuration config) {
+private predicate outBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierOut(n)
@@ -348,15 +327,6 @@ private predicate fullOutBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateOutBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierOut(n, state)
-  |
-    config.isSink(n, state)
-  )
-}
-
 pragma[nomagic]
 private predicate fullBarrier(NodeEx node, Configuration config) {
   exists(Node n | node.asNode() = n |
@@ -382,12 +352,6 @@ private predicate stateBarrier(NodeEx node, FlowState state, Configuration confi
   exists(Node n | node.asNode() = n |
     config.isBarrier(n, state)
     or
-    config.isBarrierIn(n, state) and
-    not config.isSource(n, state)
-    or
-    config.isBarrierOut(n, state) and
-    not config.isSink(n, state)
-    or
     exists(BarrierGuard g |
       config.isBarrierGuard(g, state) and
       n = g.getAGuardedNode()
@@ -420,8 +384,8 @@ private predicate sinkNode(NodeEx node, FlowState state, Configuration config) {
 /** Provides the relevant barriers for a step from `node1` to `node2`. */
 pragma[inline]
 private predicate stepFilter(NodeEx node1, NodeEx node2, Configuration config) {
-  not fullOutBarrier(node1, config) and
-  not fullInBarrier(node2, config) and
+  not outBarrier(node1, config) and
+  not inBarrier(node2, config) and
   not fullBarrier(node1, config) and
   not fullBarrier(node2, config)
 }
@@ -474,8 +438,6 @@ private predicate additionalLocalStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) = getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config)
   )
@@ -517,16 +479,15 @@ private predicate additionalJumpStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) != getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config) and
     not config.getAFeature() instanceof FeatureEqualSourceSinkCallContext
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
-  read(node1.asNode(), c, node2.asNode()) and
+pragma[nomagic]
+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 |
@@ -536,6 +497,25 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    c = cs.getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    c = cs.getAReadContent()
+  )
+}
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -613,9 +593,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
-      fwdFlowRead(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+    exists(ContentSet c |
+      fwdFlowReadSet(c, node, cc, config) and
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -639,10 +619,10 @@ 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)
     )
   }
 
@@ -660,6 +640,16 @@ 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 |
@@ -752,9 +742,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
-      read(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+    exists(NodeEx mid, ContentSet c |
+      readSet(node, c, mid, config) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -780,10 +770,10 @@ 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
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      readSet(node, cs, mid, config) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -802,6 +792,7 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
+  pragma[nomagic]
   private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
@@ -900,9 +891,9 @@ 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))
+    revFlowIsReadAndStored(pragma[only_bind_into](c), pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -912,14 +903,17 @@ 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) {
     revFlow(node, true, config) and
     fwdFlow(node, true, config) and
-    not fullInBarrier(node, config) and
-    not fullOutBarrier(node, config)
+    not inBarrier(node, config) and
+    not outBarrier(node, config)
   }
 
   /** Holds if flow may return from `callable`. */
@@ -1014,8 +1008,8 @@ private predicate flowOutOfCallNodeCand1(
 ) {
   viableReturnPosOutNodeCand1(call, ret.getReturnPosition(), out, config) and
   Stage1::revFlow(ret, config) and
-  not fullOutBarrier(ret, config) and
-  not fullInBarrier(out, config)
+  not outBarrier(ret, config) and
+  not inBarrier(out, config)
 }
 
 pragma[nomagic]
@@ -1036,8 +1030,8 @@ private predicate flowIntoCallNodeCand1(
 ) {
   viableParamArgNodeCand1(call, p, arg, config) and
   Stage1::revFlow(p, config) and
-  not fullOutBarrier(arg, config) and
-  not fullInBarrier(p, config)
+  not outBarrier(arg, config) and
+  not inBarrier(p, config)
 }
 
 /**
@@ -1189,7 +1183,7 @@ private module Stage2 {
 
   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)
   }
@@ -1614,7 +1608,7 @@ 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)
     )
@@ -1769,9 +1763,9 @@ 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
@@ -1792,8 +1786,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::storeStepCand(node, _, _, next, _, config) or
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1966,7 +1960,24 @@ 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 castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1975,7 +1986,7 @@ 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()
   }
 
@@ -2403,7 +2414,7 @@ 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)
     )
@@ -3230,7 +3241,7 @@ 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)
     )
@@ -4242,7 +4253,7 @@ 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, _)
     )
   }
 
@@ -4597,7 +4608,7 @@ 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
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4613,7 +4624,7 @@ 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
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()
@@ -5047,6 +5058,7 @@ private module FlowExploration {
     )
   }
 
+  pragma[nomagic]
   private predicate revPartialPathStep(
     PartialPathNodeRev mid, NodeEx node, FlowState state, TRevSummaryCtx1 sc1, TRevSummaryCtx2 sc2,
     TRevSummaryCtx3 sc3, RevPartialAccessPath ap, Configuration config

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

@@ -87,21 +87,9 @@ abstract class Configuration extends string {
   /** Holds if data flow into `node` is prohibited. */
   predicate isBarrierIn(Node node) { none() }
 
-  /**
-   * Holds if data flow into `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierIn(Node node, FlowState state) { none() }
-
   /** Holds if data flow out of `node` is prohibited. */
   predicate isBarrierOut(Node node) { none() }
 
-  /**
-   * Holds if data flow out of `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierOut(Node node, FlowState state) { none() }
-
   /** Holds if data flow through nodes guarded by `guard` is prohibited. */
   predicate isBarrierGuard(BarrierGuard guard) { none() }
 
@@ -128,7 +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.
@@ -321,7 +309,7 @@ private class RetNodeEx extends NodeEx {
   ReturnKindExt getKind() { result = this.asNode().(ReturnNodeExt).getKind() }
 }
 
-private predicate fullInBarrier(NodeEx node, Configuration config) {
+private predicate inBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierIn(n)
@@ -330,16 +318,7 @@ private predicate fullInBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateInBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierIn(n, state)
-  |
-    config.isSource(n, state)
-  )
-}
-
-private predicate fullOutBarrier(NodeEx node, Configuration config) {
+private predicate outBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierOut(n)
@@ -348,15 +327,6 @@ private predicate fullOutBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateOutBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierOut(n, state)
-  |
-    config.isSink(n, state)
-  )
-}
-
 pragma[nomagic]
 private predicate fullBarrier(NodeEx node, Configuration config) {
   exists(Node n | node.asNode() = n |
@@ -382,12 +352,6 @@ private predicate stateBarrier(NodeEx node, FlowState state, Configuration confi
   exists(Node n | node.asNode() = n |
     config.isBarrier(n, state)
     or
-    config.isBarrierIn(n, state) and
-    not config.isSource(n, state)
-    or
-    config.isBarrierOut(n, state) and
-    not config.isSink(n, state)
-    or
     exists(BarrierGuard g |
       config.isBarrierGuard(g, state) and
       n = g.getAGuardedNode()
@@ -420,8 +384,8 @@ private predicate sinkNode(NodeEx node, FlowState state, Configuration config) {
 /** Provides the relevant barriers for a step from `node1` to `node2`. */
 pragma[inline]
 private predicate stepFilter(NodeEx node1, NodeEx node2, Configuration config) {
-  not fullOutBarrier(node1, config) and
-  not fullInBarrier(node2, config) and
+  not outBarrier(node1, config) and
+  not inBarrier(node2, config) and
   not fullBarrier(node1, config) and
   not fullBarrier(node2, config)
 }
@@ -474,8 +438,6 @@ private predicate additionalLocalStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) = getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config)
   )
@@ -517,16 +479,15 @@ private predicate additionalJumpStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) != getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config) and
     not config.getAFeature() instanceof FeatureEqualSourceSinkCallContext
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
-  read(node1.asNode(), c, node2.asNode()) and
+pragma[nomagic]
+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 |
@@ -536,6 +497,25 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    c = cs.getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    c = cs.getAReadContent()
+  )
+}
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -613,9 +593,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
-      fwdFlowRead(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+    exists(ContentSet c |
+      fwdFlowReadSet(c, node, cc, config) and
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -639,10 +619,10 @@ 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)
     )
   }
 
@@ -660,6 +640,16 @@ 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 |
@@ -752,9 +742,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
-      read(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+    exists(NodeEx mid, ContentSet c |
+      readSet(node, c, mid, config) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -780,10 +770,10 @@ 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
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      readSet(node, cs, mid, config) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -802,6 +792,7 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
+  pragma[nomagic]
   private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
@@ -900,9 +891,9 @@ 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))
+    revFlowIsReadAndStored(pragma[only_bind_into](c), pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -912,14 +903,17 @@ 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) {
     revFlow(node, true, config) and
     fwdFlow(node, true, config) and
-    not fullInBarrier(node, config) and
-    not fullOutBarrier(node, config)
+    not inBarrier(node, config) and
+    not outBarrier(node, config)
   }
 
   /** Holds if flow may return from `callable`. */
@@ -1014,8 +1008,8 @@ private predicate flowOutOfCallNodeCand1(
 ) {
   viableReturnPosOutNodeCand1(call, ret.getReturnPosition(), out, config) and
   Stage1::revFlow(ret, config) and
-  not fullOutBarrier(ret, config) and
-  not fullInBarrier(out, config)
+  not outBarrier(ret, config) and
+  not inBarrier(out, config)
 }
 
 pragma[nomagic]
@@ -1036,8 +1030,8 @@ private predicate flowIntoCallNodeCand1(
 ) {
   viableParamArgNodeCand1(call, p, arg, config) and
   Stage1::revFlow(p, config) and
-  not fullOutBarrier(arg, config) and
-  not fullInBarrier(p, config)
+  not outBarrier(arg, config) and
+  not inBarrier(p, config)
 }
 
 /**
@@ -1189,7 +1183,7 @@ private module Stage2 {
 
   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)
   }
@@ -1614,7 +1608,7 @@ 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)
     )
@@ -1769,9 +1763,9 @@ 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
@@ -1792,8 +1786,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::storeStepCand(node, _, _, next, _, config) or
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1966,7 +1960,24 @@ 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 castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1975,7 +1986,7 @@ 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()
   }
 
@@ -2403,7 +2414,7 @@ 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)
     )
@@ -3230,7 +3241,7 @@ 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)
     )
@@ -4242,7 +4253,7 @@ 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, _)
     )
   }
 
@@ -4597,7 +4608,7 @@ 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
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4613,7 +4624,7 @@ 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
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()
@@ -5047,6 +5058,7 @@ private module FlowExploration {
     )
   }
 
+  pragma[nomagic]
   private predicate revPartialPathStep(
     PartialPathNodeRev mid, NodeEx node, FlowState state, TRevSummaryCtx1 sc1, TRevSummaryCtx2 sc2,
     TRevSummaryCtx3 sc3, RevPartialAccessPath ap, Configuration config

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

@@ -326,7 +326,7 @@ 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 isUnreachableInCallCached(Node n, DataFlowCall call) { isUnreachableInCall(n, call) }
@@ -373,7 +373,7 @@ 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 +469,7 @@ 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 +657,10 @@ 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)
       }
 
@@ -781,28 +783,30 @@ private module Cached {
     parameterValueFlow(p, n.getPreUpdateNode(), TReadStepTypesNone())
   }
 
+  cached
+  predicate readSet(Node node1, ContentSet c, Node node2) { readStep(node1, c, node2) }
+
   private predicate store(
     Node node1, Content c, Node node2, DataFlowType contentType, DataFlowType containerType
   ) {
-    storeStep(node1, c, node2) and
-    contentType = getNodeDataFlowType(node1) and
-    containerType = getNodeDataFlowType(node2)
-    or
-    exists(Node n1, Node n2 |
-      n1 = node1.(PostUpdateNode).getPreUpdateNode() and
-      n2 = node2.(PostUpdateNode).getPreUpdateNode()
-    |
-      argumentValueFlowsThrough(n2, TReadStepTypesSome(containerType, c, contentType), n1)
+    exists(ContentSet cs | c = cs.getAStoreContent() |
+      storeStep(node1, cs, node2) and
+      contentType = getNodeDataFlowType(node1) and
+      containerType = getNodeDataFlowType(node2)
       or
-      read(n2, c, n1) and
-      contentType = getNodeDataFlowType(n1) and
-      containerType = getNodeDataFlowType(n2)
+      exists(Node n1, Node n2 |
+        n1 = node1.(PostUpdateNode).getPreUpdateNode() and
+        n2 = node2.(PostUpdateNode).getPreUpdateNode()
+      |
+        argumentValueFlowsThrough(n2, TReadStepTypesSome(containerType, cs, contentType), n1)
+        or
+        readSet(n2, cs, n1) and
+        contentType = getNodeDataFlowType(n1) and
+        containerType = getNodeDataFlowType(n2)
+      )
     )
   }
 
-  cached
-  predicate read(Node node1, Content c, Node node2) { readStep(node1, c, node2) }
-
   /**
    * Holds if data can flow from `node1` to `node2` via a direct assignment to
    * `f`.
@@ -932,16 +936,16 @@ 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 +954,7 @@ 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 +1329,6 @@ 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

@@ -87,21 +87,9 @@ abstract class Configuration extends string {
   /** Holds if data flow into `node` is prohibited. */
   predicate isBarrierIn(Node node) { none() }
 
-  /**
-   * Holds if data flow into `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierIn(Node node, FlowState state) { none() }
-
   /** Holds if data flow out of `node` is prohibited. */
   predicate isBarrierOut(Node node) { none() }
 
-  /**
-   * Holds if data flow out of `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierOut(Node node, FlowState state) { none() }
-
   /** Holds if data flow through nodes guarded by `guard` is prohibited. */
   predicate isBarrierGuard(BarrierGuard guard) { none() }
 
@@ -128,7 +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.
@@ -321,7 +309,7 @@ private class RetNodeEx extends NodeEx {
   ReturnKindExt getKind() { result = this.asNode().(ReturnNodeExt).getKind() }
 }
 
-private predicate fullInBarrier(NodeEx node, Configuration config) {
+private predicate inBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierIn(n)
@@ -330,16 +318,7 @@ private predicate fullInBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateInBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierIn(n, state)
-  |
-    config.isSource(n, state)
-  )
-}
-
-private predicate fullOutBarrier(NodeEx node, Configuration config) {
+private predicate outBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierOut(n)
@@ -348,15 +327,6 @@ private predicate fullOutBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateOutBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierOut(n, state)
-  |
-    config.isSink(n, state)
-  )
-}
-
 pragma[nomagic]
 private predicate fullBarrier(NodeEx node, Configuration config) {
   exists(Node n | node.asNode() = n |
@@ -382,12 +352,6 @@ private predicate stateBarrier(NodeEx node, FlowState state, Configuration confi
   exists(Node n | node.asNode() = n |
     config.isBarrier(n, state)
     or
-    config.isBarrierIn(n, state) and
-    not config.isSource(n, state)
-    or
-    config.isBarrierOut(n, state) and
-    not config.isSink(n, state)
-    or
     exists(BarrierGuard g |
       config.isBarrierGuard(g, state) and
       n = g.getAGuardedNode()
@@ -420,8 +384,8 @@ private predicate sinkNode(NodeEx node, FlowState state, Configuration config) {
 /** Provides the relevant barriers for a step from `node1` to `node2`. */
 pragma[inline]
 private predicate stepFilter(NodeEx node1, NodeEx node2, Configuration config) {
-  not fullOutBarrier(node1, config) and
-  not fullInBarrier(node2, config) and
+  not outBarrier(node1, config) and
+  not inBarrier(node2, config) and
   not fullBarrier(node1, config) and
   not fullBarrier(node2, config)
 }
@@ -474,8 +438,6 @@ private predicate additionalLocalStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) = getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config)
   )
@@ -517,16 +479,15 @@ private predicate additionalJumpStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) != getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config) and
     not config.getAFeature() instanceof FeatureEqualSourceSinkCallContext
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
-  read(node1.asNode(), c, node2.asNode()) and
+pragma[nomagic]
+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 |
@@ -536,6 +497,25 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    c = cs.getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    c = cs.getAReadContent()
+  )
+}
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -613,9 +593,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
-      fwdFlowRead(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+    exists(ContentSet c |
+      fwdFlowReadSet(c, node, cc, config) and
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -639,10 +619,10 @@ 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)
     )
   }
 
@@ -660,6 +640,16 @@ 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 |
@@ -752,9 +742,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
-      read(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+    exists(NodeEx mid, ContentSet c |
+      readSet(node, c, mid, config) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -780,10 +770,10 @@ 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
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      readSet(node, cs, mid, config) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -802,6 +792,7 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
+  pragma[nomagic]
   private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
@@ -900,9 +891,9 @@ 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))
+    revFlowIsReadAndStored(pragma[only_bind_into](c), pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -912,14 +903,17 @@ 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) {
     revFlow(node, true, config) and
     fwdFlow(node, true, config) and
-    not fullInBarrier(node, config) and
-    not fullOutBarrier(node, config)
+    not inBarrier(node, config) and
+    not outBarrier(node, config)
   }
 
   /** Holds if flow may return from `callable`. */
@@ -1014,8 +1008,8 @@ private predicate flowOutOfCallNodeCand1(
 ) {
   viableReturnPosOutNodeCand1(call, ret.getReturnPosition(), out, config) and
   Stage1::revFlow(ret, config) and
-  not fullOutBarrier(ret, config) and
-  not fullInBarrier(out, config)
+  not outBarrier(ret, config) and
+  not inBarrier(out, config)
 }
 
 pragma[nomagic]
@@ -1036,8 +1030,8 @@ private predicate flowIntoCallNodeCand1(
 ) {
   viableParamArgNodeCand1(call, p, arg, config) and
   Stage1::revFlow(p, config) and
-  not fullOutBarrier(arg, config) and
-  not fullInBarrier(p, config)
+  not outBarrier(arg, config) and
+  not inBarrier(p, config)
 }
 
 /**
@@ -1189,7 +1183,7 @@ private module Stage2 {
 
   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)
   }
@@ -1614,7 +1608,7 @@ 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)
     )
@@ -1769,9 +1763,9 @@ 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
@@ -1792,8 +1786,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::storeStepCand(node, _, _, next, _, config) or
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1966,7 +1960,24 @@ 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 castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1975,7 +1986,7 @@ 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()
   }
 
@@ -2403,7 +2414,7 @@ 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)
     )
@@ -3230,7 +3241,7 @@ 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)
     )
@@ -4242,7 +4253,7 @@ 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, _)
     )
   }
 
@@ -4597,7 +4608,7 @@ 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
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4613,7 +4624,7 @@ 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
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()
@@ -5047,6 +5058,7 @@ private module FlowExploration {
     )
   }
 
+  pragma[nomagic]
   private predicate revPartialPathStep(
     PartialPathNodeRev mid, NodeEx node, FlowState state, TRevSummaryCtx1 sc1, TRevSummaryCtx2 sc2,
     TRevSummaryCtx3 sc3, RevPartialAccessPath ap, Configuration config

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/tainttracking1/TaintTrackingImpl.qll

@@ -109,16 +109,6 @@ abstract class Configuration extends DataFlow::Configuration {
   /** Holds if taint propagation into `node` is prohibited. */
   predicate isSanitizerIn(DataFlow::Node node) { none() }
 
-  /**
-   * Holds if taint propagation into `node` is prohibited when the flow state is
-   * `state`.
-   */
-  predicate isSanitizerIn(DataFlow::Node node, DataFlow::FlowState state) { none() }
-
-  final override predicate isBarrierIn(DataFlow::Node node, DataFlow::FlowState state) {
-    this.isSanitizerIn(node, state)
-  }
-
   final override predicate isBarrierIn(DataFlow::Node node) { this.isSanitizerIn(node) }
 
   /** Holds if taint propagation out of `node` is prohibited. */
@@ -126,16 +116,6 @@ abstract class Configuration extends DataFlow::Configuration {
 
   final override predicate isBarrierOut(DataFlow::Node node) { this.isSanitizerOut(node) }
 
-  /**
-   * Holds if taint propagation out of `node` is prohibited when the flow state is
-   * `state`.
-   */
-  predicate isSanitizerOut(DataFlow::Node node, DataFlow::FlowState state) { none() }
-
-  final override predicate isBarrierOut(DataFlow::Node node, DataFlow::FlowState state) {
-    this.isSanitizerOut(node, state)
-  }
-
   /** Holds if taint propagation through nodes guarded by `guard` is prohibited. */
   predicate isSanitizerGuard(DataFlow::BarrierGuard guard) { none() }
 
@@ -181,7 +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

@@ -109,16 +109,6 @@ abstract class Configuration extends DataFlow::Configuration {
   /** Holds if taint propagation into `node` is prohibited. */
   predicate isSanitizerIn(DataFlow::Node node) { none() }
 
-  /**
-   * Holds if taint propagation into `node` is prohibited when the flow state is
-   * `state`.
-   */
-  predicate isSanitizerIn(DataFlow::Node node, DataFlow::FlowState state) { none() }
-
-  final override predicate isBarrierIn(DataFlow::Node node, DataFlow::FlowState state) {
-    this.isSanitizerIn(node, state)
-  }
-
   final override predicate isBarrierIn(DataFlow::Node node) { this.isSanitizerIn(node) }
 
   /** Holds if taint propagation out of `node` is prohibited. */
@@ -126,16 +116,6 @@ abstract class Configuration extends DataFlow::Configuration {
 
   final override predicate isBarrierOut(DataFlow::Node node) { this.isSanitizerOut(node) }
 
-  /**
-   * Holds if taint propagation out of `node` is prohibited when the flow state is
-   * `state`.
-   */
-  predicate isSanitizerOut(DataFlow::Node node, DataFlow::FlowState state) { none() }
-
-  final override predicate isBarrierOut(DataFlow::Node node, DataFlow::FlowState state) {
-    this.isSanitizerOut(node, state)
-  }
-
   /** Holds if taint propagation through nodes guarded by `guard` is prohibited. */
   predicate isSanitizerGuard(DataFlow::BarrierGuard guard) { none() }
 
@@ -181,7 +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

@@ -87,21 +87,9 @@ abstract class Configuration extends string {
   /** Holds if data flow into `node` is prohibited. */
   predicate isBarrierIn(Node node) { none() }
 
-  /**
-   * Holds if data flow into `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierIn(Node node, FlowState state) { none() }
-
   /** Holds if data flow out of `node` is prohibited. */
   predicate isBarrierOut(Node node) { none() }
 
-  /**
-   * Holds if data flow out of `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierOut(Node node, FlowState state) { none() }
-
   /** Holds if data flow through nodes guarded by `guard` is prohibited. */
   predicate isBarrierGuard(BarrierGuard guard) { none() }
 
@@ -128,7 +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.
@@ -321,7 +309,7 @@ private class RetNodeEx extends NodeEx {
   ReturnKindExt getKind() { result = this.asNode().(ReturnNodeExt).getKind() }
 }
 
-private predicate fullInBarrier(NodeEx node, Configuration config) {
+private predicate inBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierIn(n)
@@ -330,16 +318,7 @@ private predicate fullInBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateInBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierIn(n, state)
-  |
-    config.isSource(n, state)
-  )
-}
-
-private predicate fullOutBarrier(NodeEx node, Configuration config) {
+private predicate outBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierOut(n)
@@ -348,15 +327,6 @@ private predicate fullOutBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateOutBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierOut(n, state)
-  |
-    config.isSink(n, state)
-  )
-}
-
 pragma[nomagic]
 private predicate fullBarrier(NodeEx node, Configuration config) {
   exists(Node n | node.asNode() = n |
@@ -382,12 +352,6 @@ private predicate stateBarrier(NodeEx node, FlowState state, Configuration confi
   exists(Node n | node.asNode() = n |
     config.isBarrier(n, state)
     or
-    config.isBarrierIn(n, state) and
-    not config.isSource(n, state)
-    or
-    config.isBarrierOut(n, state) and
-    not config.isSink(n, state)
-    or
     exists(BarrierGuard g |
       config.isBarrierGuard(g, state) and
       n = g.getAGuardedNode()
@@ -420,8 +384,8 @@ private predicate sinkNode(NodeEx node, FlowState state, Configuration config) {
 /** Provides the relevant barriers for a step from `node1` to `node2`. */
 pragma[inline]
 private predicate stepFilter(NodeEx node1, NodeEx node2, Configuration config) {
-  not fullOutBarrier(node1, config) and
-  not fullInBarrier(node2, config) and
+  not outBarrier(node1, config) and
+  not inBarrier(node2, config) and
   not fullBarrier(node1, config) and
   not fullBarrier(node2, config)
 }
@@ -474,8 +438,6 @@ private predicate additionalLocalStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) = getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config)
   )
@@ -517,16 +479,15 @@ private predicate additionalJumpStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) != getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config) and
     not config.getAFeature() instanceof FeatureEqualSourceSinkCallContext
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
-  read(node1.asNode(), c, node2.asNode()) and
+pragma[nomagic]
+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 |
@@ -536,6 +497,25 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    c = cs.getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    c = cs.getAReadContent()
+  )
+}
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -613,9 +593,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
-      fwdFlowRead(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+    exists(ContentSet c |
+      fwdFlowReadSet(c, node, cc, config) and
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -639,10 +619,10 @@ 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)
     )
   }
 
@@ -660,6 +640,16 @@ 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 |
@@ -752,9 +742,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
-      read(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+    exists(NodeEx mid, ContentSet c |
+      readSet(node, c, mid, config) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -780,10 +770,10 @@ 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
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      readSet(node, cs, mid, config) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -802,6 +792,7 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
+  pragma[nomagic]
   private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
@@ -900,9 +891,9 @@ 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))
+    revFlowIsReadAndStored(pragma[only_bind_into](c), pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -912,14 +903,17 @@ 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) {
     revFlow(node, true, config) and
     fwdFlow(node, true, config) and
-    not fullInBarrier(node, config) and
-    not fullOutBarrier(node, config)
+    not inBarrier(node, config) and
+    not outBarrier(node, config)
   }
 
   /** Holds if flow may return from `callable`. */
@@ -1014,8 +1008,8 @@ private predicate flowOutOfCallNodeCand1(
 ) {
   viableReturnPosOutNodeCand1(call, ret.getReturnPosition(), out, config) and
   Stage1::revFlow(ret, config) and
-  not fullOutBarrier(ret, config) and
-  not fullInBarrier(out, config)
+  not outBarrier(ret, config) and
+  not inBarrier(out, config)
 }
 
 pragma[nomagic]
@@ -1036,8 +1030,8 @@ private predicate flowIntoCallNodeCand1(
 ) {
   viableParamArgNodeCand1(call, p, arg, config) and
   Stage1::revFlow(p, config) and
-  not fullOutBarrier(arg, config) and
-  not fullInBarrier(p, config)
+  not outBarrier(arg, config) and
+  not inBarrier(p, config)
 }
 
 /**
@@ -1189,7 +1183,7 @@ private module Stage2 {
 
   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)
   }
@@ -1614,7 +1608,7 @@ 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)
     )
@@ -1769,9 +1763,9 @@ 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
@@ -1792,8 +1786,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::storeStepCand(node, _, _, next, _, config) or
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1966,7 +1960,24 @@ 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 castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1975,7 +1986,7 @@ 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()
   }
 
@@ -2403,7 +2414,7 @@ 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)
     )
@@ -3230,7 +3241,7 @@ 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)
     )
@@ -4242,7 +4253,7 @@ 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, _)
     )
   }
 
@@ -4597,7 +4608,7 @@ 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
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4613,7 +4624,7 @@ 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
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()
@@ -5047,6 +5058,7 @@ private module FlowExploration {
     )
   }
 
+  pragma[nomagic]
   private predicate revPartialPathStep(
     PartialPathNodeRev mid, NodeEx node, FlowState state, TRevSummaryCtx1 sc1, TRevSummaryCtx2 sc2,
     TRevSummaryCtx3 sc3, RevPartialAccessPath ap, Configuration config

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

@@ -87,21 +87,9 @@ abstract class Configuration extends string {
   /** Holds if data flow into `node` is prohibited. */
   predicate isBarrierIn(Node node) { none() }
 
-  /**
-   * Holds if data flow into `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierIn(Node node, FlowState state) { none() }
-
   /** Holds if data flow out of `node` is prohibited. */
   predicate isBarrierOut(Node node) { none() }
 
-  /**
-   * Holds if data flow out of `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierOut(Node node, FlowState state) { none() }
-
   /** Holds if data flow through nodes guarded by `guard` is prohibited. */
   predicate isBarrierGuard(BarrierGuard guard) { none() }
 
@@ -128,7 +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.
@@ -321,7 +309,7 @@ private class RetNodeEx extends NodeEx {
   ReturnKindExt getKind() { result = this.asNode().(ReturnNodeExt).getKind() }
 }
 
-private predicate fullInBarrier(NodeEx node, Configuration config) {
+private predicate inBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierIn(n)
@@ -330,16 +318,7 @@ private predicate fullInBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateInBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierIn(n, state)
-  |
-    config.isSource(n, state)
-  )
-}
-
-private predicate fullOutBarrier(NodeEx node, Configuration config) {
+private predicate outBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierOut(n)
@@ -348,15 +327,6 @@ private predicate fullOutBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateOutBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierOut(n, state)
-  |
-    config.isSink(n, state)
-  )
-}
-
 pragma[nomagic]
 private predicate fullBarrier(NodeEx node, Configuration config) {
   exists(Node n | node.asNode() = n |
@@ -382,12 +352,6 @@ private predicate stateBarrier(NodeEx node, FlowState state, Configuration confi
   exists(Node n | node.asNode() = n |
     config.isBarrier(n, state)
     or
-    config.isBarrierIn(n, state) and
-    not config.isSource(n, state)
-    or
-    config.isBarrierOut(n, state) and
-    not config.isSink(n, state)
-    or
     exists(BarrierGuard g |
       config.isBarrierGuard(g, state) and
       n = g.getAGuardedNode()
@@ -420,8 +384,8 @@ private predicate sinkNode(NodeEx node, FlowState state, Configuration config) {
 /** Provides the relevant barriers for a step from `node1` to `node2`. */
 pragma[inline]
 private predicate stepFilter(NodeEx node1, NodeEx node2, Configuration config) {
-  not fullOutBarrier(node1, config) and
-  not fullInBarrier(node2, config) and
+  not outBarrier(node1, config) and
+  not inBarrier(node2, config) and
   not fullBarrier(node1, config) and
   not fullBarrier(node2, config)
 }
@@ -474,8 +438,6 @@ private predicate additionalLocalStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) = getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config)
   )
@@ -517,16 +479,15 @@ private predicate additionalJumpStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) != getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config) and
     not config.getAFeature() instanceof FeatureEqualSourceSinkCallContext
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
-  read(node1.asNode(), c, node2.asNode()) and
+pragma[nomagic]
+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 |
@@ -536,6 +497,25 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    c = cs.getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    c = cs.getAReadContent()
+  )
+}
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -613,9 +593,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
-      fwdFlowRead(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+    exists(ContentSet c |
+      fwdFlowReadSet(c, node, cc, config) and
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -639,10 +619,10 @@ 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)
     )
   }
 
@@ -660,6 +640,16 @@ 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 |
@@ -752,9 +742,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
-      read(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+    exists(NodeEx mid, ContentSet c |
+      readSet(node, c, mid, config) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -780,10 +770,10 @@ 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
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      readSet(node, cs, mid, config) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -802,6 +792,7 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
+  pragma[nomagic]
   private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
@@ -900,9 +891,9 @@ 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))
+    revFlowIsReadAndStored(pragma[only_bind_into](c), pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -912,14 +903,17 @@ 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) {
     revFlow(node, true, config) and
     fwdFlow(node, true, config) and
-    not fullInBarrier(node, config) and
-    not fullOutBarrier(node, config)
+    not inBarrier(node, config) and
+    not outBarrier(node, config)
   }
 
   /** Holds if flow may return from `callable`. */
@@ -1014,8 +1008,8 @@ private predicate flowOutOfCallNodeCand1(
 ) {
   viableReturnPosOutNodeCand1(call, ret.getReturnPosition(), out, config) and
   Stage1::revFlow(ret, config) and
-  not fullOutBarrier(ret, config) and
-  not fullInBarrier(out, config)
+  not outBarrier(ret, config) and
+  not inBarrier(out, config)
 }
 
 pragma[nomagic]
@@ -1036,8 +1030,8 @@ private predicate flowIntoCallNodeCand1(
 ) {
   viableParamArgNodeCand1(call, p, arg, config) and
   Stage1::revFlow(p, config) and
-  not fullOutBarrier(arg, config) and
-  not fullInBarrier(p, config)
+  not outBarrier(arg, config) and
+  not inBarrier(p, config)
 }
 
 /**
@@ -1189,7 +1183,7 @@ private module Stage2 {
 
   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)
   }
@@ -1614,7 +1608,7 @@ 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)
     )
@@ -1769,9 +1763,9 @@ 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
@@ -1792,8 +1786,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::storeStepCand(node, _, _, next, _, config) or
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1966,7 +1960,24 @@ 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 castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1975,7 +1986,7 @@ 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()
   }
 
@@ -2403,7 +2414,7 @@ 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)
     )
@@ -3230,7 +3241,7 @@ 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)
     )
@@ -4242,7 +4253,7 @@ 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, _)
     )
   }
 
@@ -4597,7 +4608,7 @@ 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
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4613,7 +4624,7 @@ 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
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()
@@ -5047,6 +5058,7 @@ private module FlowExploration {
     )
   }
 
+  pragma[nomagic]
   private predicate revPartialPathStep(
     PartialPathNodeRev mid, NodeEx node, FlowState state, TRevSummaryCtx1 sc1, TRevSummaryCtx2 sc2,
     TRevSummaryCtx3 sc3, RevPartialAccessPath ap, Configuration config

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

@@ -87,21 +87,9 @@ abstract class Configuration extends string {
   /** Holds if data flow into `node` is prohibited. */
   predicate isBarrierIn(Node node) { none() }
 
-  /**
-   * Holds if data flow into `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierIn(Node node, FlowState state) { none() }
-
   /** Holds if data flow out of `node` is prohibited. */
   predicate isBarrierOut(Node node) { none() }
 
-  /**
-   * Holds if data flow out of `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierOut(Node node, FlowState state) { none() }
-
   /** Holds if data flow through nodes guarded by `guard` is prohibited. */
   predicate isBarrierGuard(BarrierGuard guard) { none() }
 
@@ -128,7 +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.
@@ -321,7 +309,7 @@ private class RetNodeEx extends NodeEx {
   ReturnKindExt getKind() { result = this.asNode().(ReturnNodeExt).getKind() }
 }
 
-private predicate fullInBarrier(NodeEx node, Configuration config) {
+private predicate inBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierIn(n)
@@ -330,16 +318,7 @@ private predicate fullInBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateInBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierIn(n, state)
-  |
-    config.isSource(n, state)
-  )
-}
-
-private predicate fullOutBarrier(NodeEx node, Configuration config) {
+private predicate outBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierOut(n)
@@ -348,15 +327,6 @@ private predicate fullOutBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateOutBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierOut(n, state)
-  |
-    config.isSink(n, state)
-  )
-}
-
 pragma[nomagic]
 private predicate fullBarrier(NodeEx node, Configuration config) {
   exists(Node n | node.asNode() = n |
@@ -382,12 +352,6 @@ private predicate stateBarrier(NodeEx node, FlowState state, Configuration confi
   exists(Node n | node.asNode() = n |
     config.isBarrier(n, state)
     or
-    config.isBarrierIn(n, state) and
-    not config.isSource(n, state)
-    or
-    config.isBarrierOut(n, state) and
-    not config.isSink(n, state)
-    or
     exists(BarrierGuard g |
       config.isBarrierGuard(g, state) and
       n = g.getAGuardedNode()
@@ -420,8 +384,8 @@ private predicate sinkNode(NodeEx node, FlowState state, Configuration config) {
 /** Provides the relevant barriers for a step from `node1` to `node2`. */
 pragma[inline]
 private predicate stepFilter(NodeEx node1, NodeEx node2, Configuration config) {
-  not fullOutBarrier(node1, config) and
-  not fullInBarrier(node2, config) and
+  not outBarrier(node1, config) and
+  not inBarrier(node2, config) and
   not fullBarrier(node1, config) and
   not fullBarrier(node2, config)
 }
@@ -474,8 +438,6 @@ private predicate additionalLocalStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) = getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config)
   )
@@ -517,16 +479,15 @@ private predicate additionalJumpStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) != getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config) and
     not config.getAFeature() instanceof FeatureEqualSourceSinkCallContext
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
-  read(node1.asNode(), c, node2.asNode()) and
+pragma[nomagic]
+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 |
@@ -536,6 +497,25 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    c = cs.getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    c = cs.getAReadContent()
+  )
+}
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -613,9 +593,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
-      fwdFlowRead(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+    exists(ContentSet c |
+      fwdFlowReadSet(c, node, cc, config) and
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -639,10 +619,10 @@ 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)
     )
   }
 
@@ -660,6 +640,16 @@ 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 |
@@ -752,9 +742,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
-      read(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+    exists(NodeEx mid, ContentSet c |
+      readSet(node, c, mid, config) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -780,10 +770,10 @@ 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
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      readSet(node, cs, mid, config) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -802,6 +792,7 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
+  pragma[nomagic]
   private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
@@ -900,9 +891,9 @@ 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))
+    revFlowIsReadAndStored(pragma[only_bind_into](c), pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -912,14 +903,17 @@ 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) {
     revFlow(node, true, config) and
     fwdFlow(node, true, config) and
-    not fullInBarrier(node, config) and
-    not fullOutBarrier(node, config)
+    not inBarrier(node, config) and
+    not outBarrier(node, config)
   }
 
   /** Holds if flow may return from `callable`. */
@@ -1014,8 +1008,8 @@ private predicate flowOutOfCallNodeCand1(
 ) {
   viableReturnPosOutNodeCand1(call, ret.getReturnPosition(), out, config) and
   Stage1::revFlow(ret, config) and
-  not fullOutBarrier(ret, config) and
-  not fullInBarrier(out, config)
+  not outBarrier(ret, config) and
+  not inBarrier(out, config)
 }
 
 pragma[nomagic]
@@ -1036,8 +1030,8 @@ private predicate flowIntoCallNodeCand1(
 ) {
   viableParamArgNodeCand1(call, p, arg, config) and
   Stage1::revFlow(p, config) and
-  not fullOutBarrier(arg, config) and
-  not fullInBarrier(p, config)
+  not outBarrier(arg, config) and
+  not inBarrier(p, config)
 }
 
 /**
@@ -1189,7 +1183,7 @@ private module Stage2 {
 
   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)
   }
@@ -1614,7 +1608,7 @@ 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)
     )
@@ -1769,9 +1763,9 @@ 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
@@ -1792,8 +1786,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::storeStepCand(node, _, _, next, _, config) or
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1966,7 +1960,24 @@ 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 castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1975,7 +1986,7 @@ 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()
   }
 
@@ -2403,7 +2414,7 @@ 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)
     )
@@ -3230,7 +3241,7 @@ 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)
     )
@@ -4242,7 +4253,7 @@ 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, _)
     )
   }
 
@@ -4597,7 +4608,7 @@ 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
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4613,7 +4624,7 @@ 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
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()
@@ -5047,6 +5058,7 @@ private module FlowExploration {
     )
   }
 
+  pragma[nomagic]
   private predicate revPartialPathStep(
     PartialPathNodeRev mid, NodeEx node, FlowState state, TRevSummaryCtx1 sc1, TRevSummaryCtx2 sc2,
     TRevSummaryCtx3 sc3, RevPartialAccessPath ap, Configuration config

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

@@ -87,21 +87,9 @@ abstract class Configuration extends string {
   /** Holds if data flow into `node` is prohibited. */
   predicate isBarrierIn(Node node) { none() }
 
-  /**
-   * Holds if data flow into `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierIn(Node node, FlowState state) { none() }
-
   /** Holds if data flow out of `node` is prohibited. */
   predicate isBarrierOut(Node node) { none() }
 
-  /**
-   * Holds if data flow out of `node` is prohibited when the flow state is
-   * `state`
-   */
-  predicate isBarrierOut(Node node, FlowState state) { none() }
-
   /** Holds if data flow through nodes guarded by `guard` is prohibited. */
   predicate isBarrierGuard(BarrierGuard guard) { none() }
 
@@ -128,7 +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.
@@ -321,7 +309,7 @@ private class RetNodeEx extends NodeEx {
   ReturnKindExt getKind() { result = this.asNode().(ReturnNodeExt).getKind() }
 }
 
-private predicate fullInBarrier(NodeEx node, Configuration config) {
+private predicate inBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierIn(n)
@@ -330,16 +318,7 @@ private predicate fullInBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateInBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierIn(n, state)
-  |
-    config.isSource(n, state)
-  )
-}
-
-private predicate fullOutBarrier(NodeEx node, Configuration config) {
+private predicate outBarrier(NodeEx node, Configuration config) {
   exists(Node n |
     node.asNode() = n and
     config.isBarrierOut(n)
@@ -348,15 +327,6 @@ private predicate fullOutBarrier(NodeEx node, Configuration config) {
   )
 }
 
-private predicate stateOutBarrier(NodeEx node, FlowState state, Configuration config) {
-  exists(Node n |
-    node.asNode() = n and
-    config.isBarrierOut(n, state)
-  |
-    config.isSink(n, state)
-  )
-}
-
 pragma[nomagic]
 private predicate fullBarrier(NodeEx node, Configuration config) {
   exists(Node n | node.asNode() = n |
@@ -382,12 +352,6 @@ private predicate stateBarrier(NodeEx node, FlowState state, Configuration confi
   exists(Node n | node.asNode() = n |
     config.isBarrier(n, state)
     or
-    config.isBarrierIn(n, state) and
-    not config.isSource(n, state)
-    or
-    config.isBarrierOut(n, state) and
-    not config.isSink(n, state)
-    or
     exists(BarrierGuard g |
       config.isBarrierGuard(g, state) and
       n = g.getAGuardedNode()
@@ -420,8 +384,8 @@ private predicate sinkNode(NodeEx node, FlowState state, Configuration config) {
 /** Provides the relevant barriers for a step from `node1` to `node2`. */
 pragma[inline]
 private predicate stepFilter(NodeEx node1, NodeEx node2, Configuration config) {
-  not fullOutBarrier(node1, config) and
-  not fullInBarrier(node2, config) and
+  not outBarrier(node1, config) and
+  not inBarrier(node2, config) and
   not fullBarrier(node1, config) and
   not fullBarrier(node2, config)
 }
@@ -474,8 +438,6 @@ private predicate additionalLocalStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) = getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config)
   )
@@ -517,16 +479,15 @@ private predicate additionalJumpStateStep(
     config.isAdditionalFlowStep(n1, s1, n2, s2) and
     getNodeEnclosingCallable(n1) != getNodeEnclosingCallable(n2) and
     stepFilter(node1, node2, config) and
-    not stateOutBarrier(node1, s1, config) and
-    not stateInBarrier(node2, s2, config) and
     not stateBarrier(node1, s1, config) and
     not stateBarrier(node2, s2, config) and
     not config.getAFeature() instanceof FeatureEqualSourceSinkCallContext
   )
 }
 
-private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
-  read(node1.asNode(), c, node2.asNode()) and
+pragma[nomagic]
+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 |
@@ -536,6 +497,25 @@ private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration conf
   )
 }
 
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate read(NodeEx node1, Content c, NodeEx node2, Configuration config) {
+  exists(ContentSet cs |
+    readSet(node1, cs, node2, config) and
+    c = cs.getAReadContent()
+  )
+}
+
+// inline to reduce fan-out via `getAReadContent`
+pragma[inline]
+private predicate clearsContentEx(NodeEx n, Content c) {
+  exists(ContentSet cs |
+    clearsContentCached(n.asNode(), cs) and
+    c = cs.getAReadContent()
+  )
+}
+
+pragma[nomagic]
 private predicate store(
   NodeEx node1, TypedContent tc, NodeEx node2, DataFlowType contentType, Configuration config
 ) {
@@ -613,9 +593,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(Content c |
-      fwdFlowRead(c, node, cc, config) and
-      fwdFlowConsCand(c, config)
+    exists(ContentSet c |
+      fwdFlowReadSet(c, node, cc, config) and
+      fwdFlowConsCandSet(c, _, config)
     )
     or
     // flow into a callable
@@ -639,10 +619,10 @@ 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)
     )
   }
 
@@ -660,6 +640,16 @@ 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 |
@@ -752,9 +742,9 @@ private module Stage1 {
     )
     or
     // read
-    exists(NodeEx mid, Content c |
-      read(node, c, mid, config) and
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+    exists(NodeEx mid, ContentSet c |
+      readSet(node, c, mid, config) and
+      fwdFlowConsCandSet(c, _, pragma[only_bind_into](config)) and
       revFlow(mid, toReturn, pragma[only_bind_into](config))
     )
     or
@@ -780,10 +770,10 @@ 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
-      fwdFlowConsCand(c, pragma[only_bind_into](config)) and
+      readSet(node, cs, mid, config) and
+      fwdFlowConsCandSet(cs, c, pragma[only_bind_into](config)) and
       revFlow(pragma[only_bind_into](mid), _, pragma[only_bind_into](config))
     )
   }
@@ -802,6 +792,7 @@ private module Stage1 {
    * Holds if `c` is the target of both a read and a store in the flow covered
    * by `revFlow`.
    */
+  pragma[nomagic]
   private predicate revFlowIsReadAndStored(Content c, Configuration conf) {
     revFlowConsCand(c, conf) and
     revFlowStore(c, _, _, conf)
@@ -900,9 +891,9 @@ 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))
+    revFlowIsReadAndStored(pragma[only_bind_into](c), pragma[only_bind_into](config)) and
+    read(n1, c, n2, pragma[only_bind_into](config)) and
+    revFlow(n2, pragma[only_bind_into](config))
   }
 
   pragma[nomagic]
@@ -912,14 +903,17 @@ 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) {
     revFlow(node, true, config) and
     fwdFlow(node, true, config) and
-    not fullInBarrier(node, config) and
-    not fullOutBarrier(node, config)
+    not inBarrier(node, config) and
+    not outBarrier(node, config)
   }
 
   /** Holds if flow may return from `callable`. */
@@ -1014,8 +1008,8 @@ private predicate flowOutOfCallNodeCand1(
 ) {
   viableReturnPosOutNodeCand1(call, ret.getReturnPosition(), out, config) and
   Stage1::revFlow(ret, config) and
-  not fullOutBarrier(ret, config) and
-  not fullInBarrier(out, config)
+  not outBarrier(ret, config) and
+  not inBarrier(out, config)
 }
 
 pragma[nomagic]
@@ -1036,8 +1030,8 @@ private predicate flowIntoCallNodeCand1(
 ) {
   viableParamArgNodeCand1(call, p, arg, config) and
   Stage1::revFlow(p, config) and
-  not fullOutBarrier(arg, config) and
-  not fullInBarrier(p, config)
+  not outBarrier(arg, config) and
+  not inBarrier(p, config)
 }
 
 /**
@@ -1189,7 +1183,7 @@ private module Stage2 {
 
   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)
   }
@@ -1614,7 +1608,7 @@ 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)
     )
@@ -1769,9 +1763,9 @@ 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
@@ -1792,8 +1786,8 @@ private module LocalFlowBigStep {
       additionalJumpStep(node, next, config) or
       flowIntoCallNodeCand1(_, node, next, config) or
       flowOutOfCallNodeCand1(_, node, next, config) or
-      store(node, _, next, _, config) or
-      read(node, _, next, config)
+      Stage2::storeStepCand(node, _, _, next, _, config) or
+      Stage2::readStepCand(node, _, next, config)
     )
     or
     exists(NodeEx next, FlowState s | Stage2::revFlow(next, s, config) |
@@ -1966,7 +1960,24 @@ 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 castingNodeEx(NodeEx node) { node.asNode() instanceof CastingNode }
@@ -1975,7 +1986,7 @@ 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()
   }
 
@@ -2403,7 +2414,7 @@ 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)
     )
@@ -3230,7 +3241,7 @@ 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)
     )
@@ -4242,7 +4253,7 @@ 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, _)
     )
   }
 
@@ -4597,7 +4608,7 @@ 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
         not fullBarrier(node, config) and
         not stateBarrier(node, state, config) and
         distSink(node.getEnclosingCallable(), config) <= config.explorationLimit()
@@ -4613,7 +4624,7 @@ 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
       if node.asNode() instanceof CastingNode
       then compatibleTypes(node.getDataFlowType(), ap.getType())
       else any()
@@ -5047,6 +5058,7 @@ private module FlowExploration {
     )
   }
 
+  pragma[nomagic]
   private predicate revPartialPathStep(
     PartialPathNodeRev mid, NodeEx node, FlowState state, TRevSummaryCtx1 sc1, TRevSummaryCtx2 sc2,
     TRevSummaryCtx3 sc3, RevPartialAccessPath ap, Configuration config

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

@@ -326,7 +326,7 @@ 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 isUnreachableInCallCached(Node n, DataFlowCall call) { isUnreachableInCall(n, call) }
@@ -373,7 +373,7 @@ 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 +469,7 @@ 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 +657,10 @@ 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)
       }
 
@@ -781,28 +783,30 @@ private module Cached {
     parameterValueFlow(p, n.getPreUpdateNode(), TReadStepTypesNone())
   }
 
+  cached
+  predicate readSet(Node node1, ContentSet c, Node node2) { readStep(node1, c, node2) }
+
   private predicate store(
     Node node1, Content c, Node node2, DataFlowType contentType, DataFlowType containerType
   ) {
-    storeStep(node1, c, node2) and
-    contentType = getNodeDataFlowType(node1) and
-    containerType = getNodeDataFlowType(node2)
-    or
-    exists(Node n1, Node n2 |
-      n1 = node1.(PostUpdateNode).getPreUpdateNode() and
-      n2 = node2.(PostUpdateNode).getPreUpdateNode()
-    |
-      argumentValueFlowsThrough(n2, TReadStepTypesSome(containerType, c, contentType), n1)
+    exists(ContentSet cs | c = cs.getAStoreContent() |
+      storeStep(node1, cs, node2) and
+      contentType = getNodeDataFlowType(node1) and
+      containerType = getNodeDataFlowType(node2)
       or
-      read(n2, c, n1) and
-      contentType = getNodeDataFlowType(n1) and
-      containerType = getNodeDataFlowType(n2)
+      exists(Node n1, Node n2 |
+        n1 = node1.(PostUpdateNode).getPreUpdateNode() and
+        n2 = node2.(PostUpdateNode).getPreUpdateNode()
+      |
+        argumentValueFlowsThrough(n2, TReadStepTypesSome(containerType, cs, contentType), n1)
+        or
+        readSet(n2, cs, n1) and
+        contentType = getNodeDataFlowType(n1) and
+        containerType = getNodeDataFlowType(n2)
+      )
     )
   }
 
-  cached
-  predicate read(Node node1, Content c, Node node2) { readStep(node1, c, node2) }
-
   /**
    * Holds if data can flow from `node1` to `node2` via a direct assignment to
    * `f`.
@@ -932,16 +936,16 @@ 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 +954,7 @@ 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 +1329,6 @@ 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/DataFlowUtil.qll

@@ -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

@@ -109,16 +109,6 @@ abstract class Configuration extends DataFlow::Configuration {
   /** Holds if taint propagation into `node` is prohibited. */
   predicate isSanitizerIn(DataFlow::Node node) { none() }
 
-  /**
-   * Holds if taint propagation into `node` is prohibited when the flow state is
-   * `state`.
-   */
-  predicate isSanitizerIn(DataFlow::Node node, DataFlow::FlowState state) { none() }
-
-  final override predicate isBarrierIn(DataFlow::Node node, DataFlow::FlowState state) {
-    this.isSanitizerIn(node, state)
-  }
-
   final override predicate isBarrierIn(DataFlow::Node node) { this.isSanitizerIn(node) }
 
   /** Holds if taint propagation out of `node` is prohibited. */
@@ -126,16 +116,6 @@ abstract class Configuration extends DataFlow::Configuration {
 
   final override predicate isBarrierOut(DataFlow::Node node) { this.isSanitizerOut(node) }
 
-  /**
-   * Holds if taint propagation out of `node` is prohibited when the flow state is
-   * `state`.
-   */
-  predicate isSanitizerOut(DataFlow::Node node, DataFlow::FlowState state) { none() }
-
-  final override predicate isBarrierOut(DataFlow::Node node, DataFlow::FlowState state) {
-    this.isSanitizerOut(node, state)
-  }
-
   /** Holds if taint propagation through nodes guarded by `guard` is prohibited. */
   predicate isSanitizerGuard(DataFlow::BarrierGuard guard) { none() }
 
@@ -181,7 +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

@@ -109,16 +109,6 @@ abstract class Configuration extends DataFlow::Configuration {
   /** Holds if taint propagation into `node` is prohibited. */
   predicate isSanitizerIn(DataFlow::Node node) { none() }
 
-  /**
-   * Holds if taint propagation into `node` is prohibited when the flow state is
-   * `state`.
-   */
-  predicate isSanitizerIn(DataFlow::Node node, DataFlow::FlowState state) { none() }
-
-  final override predicate isBarrierIn(DataFlow::Node node, DataFlow::FlowState state) {
-    this.isSanitizerIn(node, state)
-  }
-
   final override predicate isBarrierIn(DataFlow::Node node) { this.isSanitizerIn(node) }
 
   /** Holds if taint propagation out of `node` is prohibited. */
@@ -126,16 +116,6 @@ abstract class Configuration extends DataFlow::Configuration {
 
   final override predicate isBarrierOut(DataFlow::Node node) { this.isSanitizerOut(node) }
 
-  /**
-   * Holds if taint propagation out of `node` is prohibited when the flow state is
-   * `state`.
-   */
-  predicate isSanitizerOut(DataFlow::Node node, DataFlow::FlowState state) { none() }
-
-  final override predicate isBarrierOut(DataFlow::Node node, DataFlow::FlowState state) {
-    this.isSanitizerOut(node, state)
-  }
-
   /** Holds if taint propagation through nodes guarded by `guard` is prohibited. */
   predicate isSanitizerGuard(DataFlow::BarrierGuard guard) { none() }
 
@@ -181,7 +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

@@ -109,16 +109,6 @@ abstract class Configuration extends DataFlow::Configuration {
   /** Holds if taint propagation into `node` is prohibited. */
   predicate isSanitizerIn(DataFlow::Node node) { none() }
 
-  /**
-   * Holds if taint propagation into `node` is prohibited when the flow state is
-   * `state`.
-   */
-  predicate isSanitizerIn(DataFlow::Node node, DataFlow::FlowState state) { none() }
-
-  final override predicate isBarrierIn(DataFlow::Node node, DataFlow::FlowState state) {
-    this.isSanitizerIn(node, state)
-  }
-
   final override predicate isBarrierIn(DataFlow::Node node) { this.isSanitizerIn(node) }
 
   /** Holds if taint propagation out of `node` is prohibited. */
@@ -126,16 +116,6 @@ abstract class Configuration extends DataFlow::Configuration {
 
   final override predicate isBarrierOut(DataFlow::Node node) { this.isSanitizerOut(node) }
 
-  /**
-   * Holds if taint propagation out of `node` is prohibited when the flow state is
-   * `state`.
-   */
-  predicate isSanitizerOut(DataFlow::Node node, DataFlow::FlowState state) { none() }
-
-  final override predicate isBarrierOut(DataFlow::Node node, DataFlow::FlowState state) {
-    this.isSanitizerOut(node, state)
-  }
-
   /** Holds if taint propagation through nodes guarded by `guard` is prohibited. */
   predicate isSanitizerGuard(DataFlow::BarrierGuard guard) { none() }
 
@@ -181,7 +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/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/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)

cpp/ql/lib/semmle/code/cpp/models/implementations/Allocation.qll

@@ -42,10 +42,13 @@ private class MallocAllocationFunction extends AllocationFunction {
     this.hasGlobalName([
         // --- Windows Memory Management for Windows Drivers
         "ExAllocatePool", // ExAllocatePool(type, size)
+        "ExAllocatePool2", // ExAllocatePool2(flags, size, tag)
+        "ExAllocatePool3", // ExAllocatePool3(flags, size, tag, extparams, extparamscount)
         "ExAllocatePoolWithTag", // ExAllocatePool(type, size, tag)
         "ExAllocatePoolWithTagPriority", // ExAllocatePoolWithTagPriority(type, size, tag, priority)
         "ExAllocatePoolWithQuota", // ExAllocatePoolWithQuota(type, size)
         "ExAllocatePoolWithQuotaTag", // ExAllocatePoolWithQuotaTag(type, size, tag)
+        "ExAllocatePoolZero", // ExAllocatePoolZero(type, size, tag)
         "IoAllocateMdl", // IoAllocateMdl(address, size, flag, flag, irp)
         "IoAllocateErrorLogEntry", // IoAllocateErrorLogEntry(object, size)
         // --- Windows Global / Local legacy allocation

cpp/ql/lib/semmle/code/cpp/models/implementations/Strtok.qll

@@ -5,7 +5,6 @@
 
 import semmle.code.cpp.Function
 import semmle.code.cpp.models.interfaces.ArrayFunction
-import semmle.code.cpp.models.interfaces.ArrayFunction
 import semmle.code.cpp.models.interfaces.Alias
 import semmle.code.cpp.models.interfaces.SideEffect
 import semmle.code.cpp.models.interfaces.Taint

cpp/ql/lib/semmle/code/cpp/rangeanalysis/SimpleRangeAnalysis.qll

@@ -1802,5 +1802,3 @@ module SimpleRangeAnalysisInternal {
     defMightOverflowNegatively(def, v) and result = varMaxVal(v)
   }
 }
-
-private import SimpleRangeAnalysisInternal

cpp/ql/lib/semmle/code/cpp/security/BufferWrite.qll

@@ -6,7 +6,6 @@
  */
 
 import cpp
-import semmle.code.cpp.commons.Alloc
 import semmle.code.cpp.commons.Buffer
 import semmle.code.cpp.commons.Scanf
 import semmle.code.cpp.models.implementations.Strcat

cpp/ql/src/CHANGELOG.md

@@ -1,3 +1,12 @@
+## 0.1.0
+
+### Minor Analysis Improvements
+
+* The `cpp/cleartext-transmission` query now recognizes additional sources, for sensitive private data such as e-mail addresses and credit card numbers.
+* The `cpp/unused-local-variable` no longer ignores functions that include lambda expressions capturing trivially copyable objects.
+* The `cpp/command-line-injection` query now takes into account calling contexts across string concatenations. This removes false positives due to mismatched calling contexts before and after string concatenations.
+* A new query, "Potential exposure of sensitive system data to an unauthorized control sphere" (`cpp/potential-system-data-exposure`) has been added. This query is focused on exposure of information that is highly likely to be sensitive, whereas the similar query "Exposure of system data to an unauthorized control sphere" (`cpp/system-data-exposure`) is focused on exposure of information on a channel that is more likely to be intercepted by an attacker.
+
 ## 0.0.13
 
 ## 0.0.12

cpp/ql/src/Likely Bugs/Leap Year/Adding365DaysPerYear.ql

@@ -13,7 +13,6 @@
 
 import cpp
 import LeapYear
-import semmle.code.cpp.dataflow.DataFlow
 
 from Expr source, Expr sink, PossibleYearArithmeticOperationCheckConfiguration config
 where config.hasFlow(DataFlow::exprNode(source), DataFlow::exprNode(sink))

cpp/ql/src/Likely Bugs/Memory Management/NtohlArrayNoBound.ql

@@ -10,7 +10,6 @@
 
 import cpp
 import NtohlArrayNoBound
-import semmle.code.cpp.dataflow.DataFlow
 
 from NetworkToBufferSizeConfiguration bufConfig, DataFlow::Node source, DataFlow::Node sink
 where bufConfig.hasFlow(source, sink)

cpp/ql/src/Security/CWE/CWE-120/OverrunWrite.ql

@@ -15,7 +15,6 @@
  */
 
 import semmle.code.cpp.security.BufferWrite
-import semmle.code.cpp.commons.Alloc
 
 /*
  * See CWE-120/UnboundedWrite.ql for a summary of CWE-120 alert cases.

cpp/ql/src/Security/CWE/CWE-120/VeryLikelyOverrunWrite.ql

@@ -15,7 +15,6 @@
  */
 
 import semmle.code.cpp.security.BufferWrite
-import semmle.code.cpp.commons.Alloc
 
 /*
  * See CWE-120/UnboundedWrite.ql for a summary of CWE-120 alert cases.

cpp/ql/src/Security/CWE/CWE-611/XXE.qhelp

@@ -0,0 +1,57 @@
+<!DOCTYPE qhelp PUBLIC "-//Semmle//qhelp//EN" "qhelp.dtd">
+<qhelp>
+
+<overview>
+<p>
+Parsing untrusted XML files with a weakly configured XML parser may lead to an
+XML external entity (XXE) attack. This type of attack uses external entity references
+to access arbitrary files on a system, carry out denial-of-service (DoS) attacks, or server-side
+request forgery. Even when the result of parsing is not returned to the user, DoS attacks are still possible
+and out-of-band data retrieval techniques may allow attackers to steal sensitive data.
+</p>
+</overview>
+
+<recommendation>
+<p>
+The easiest way to prevent XXE attacks is to disable external entity handling when
+parsing untrusted data. How this is done depends on the library being used. Note that some
+libraries, such as recent versions of <code>libxml</code>, disable entity expansion by default,
+so unless you have explicitly enabled entity expansion, no further action needs to be taken.
+</p>
+</recommendation>
+
+<example>
+<p>
+The following example uses the <code>Xerces-C++</code> XML parser to parse a string <code>data</code>.
+If that string is from an untrusted source, this code may be vulnerable to an XXE attack, since
+the parser is constructed in its default state with <code>setDisableDefaultEntityResolution</code>
+set to <code>false</code>:
+</p>
+<sample src="XXEBad.cpp"/>
+
+<p>
+To guard against XXE attacks, the <code>setDisableDefaultEntityResolution</code> option should be
+set to <code>true</code>.
+</p>
+<sample src="XXEGood.cpp"/>
+</example>
+
+<references>
+<li>
+OWASP:
+<a href="https://www.owasp.org/index.php/XML_External_Entity_(XXE)_Processing">XML External Entity (XXE) Processing</a>.
+</li>
+<li>
+OWASP:
+<a href="https://cheatsheetseries.owasp.org/cheatsheets/XML_External_Entity_Prevention_Cheat_Sheet.html">XML External Entity Prevention Cheat Sheet</a>.
+</li>
+<li>
+Timothy Morgen:
+<a href="https://research.nccgroup.com/2014/05/19/xml-schema-dtd-and-entity-attacks-a-compendium-of-known-techniques/">XML Schema, DTD, and Entity Attacks</a>.
+</li>
+<li>
+Timur Yunusov, Alexey Osipov:
+<a href="https://www.slideshare.net/qqlan/bh-ready-v4">XML Out-Of-Band Data Retrieval</a>.
+</li>
+</references>
+</qhelp>

cpp/ql/src/Security/CWE/CWE-611/XXE.ql

@@ -0,0 +1,226 @@
+/**
+ * @name XML external entity expansion
+ * @description Parsing user-controlled XML documents and allowing expansion of
+ *              external entity references may lead to disclosure of
+ *              confidential data or denial of service.
+ * @kind path-problem
+ * @id cpp/external-entity-expansion
+ * @problem.severity warning
+ * @security-severity 9.1
+ * @precision medium
+ * @tags security
+ *       external/cwe/cwe-611
+ */
+
+import cpp
+import semmle.code.cpp.ir.dataflow.DataFlow
+import DataFlow::PathGraph
+import semmle.code.cpp.ir.IR
+
+/**
+ * A flow state representing a possible configuration of an XML object.
+ */
+abstract class XXEFlowState extends DataFlow::FlowState {
+  bindingset[this]
+  XXEFlowState() { any() } // required characteristic predicate
+}
+
+/**
+ * An `Expr` that changes the configuration of an XML object, transforming the
+ * `XXEFlowState` that flows through it.
+ */
+abstract class XXEFlowStateTranformer extends Expr {
+  /**
+   * Gets the flow state that `flowstate` is transformed into.
+   *
+   * Due to limitations of the implementation the transformation defined by this
+   * predicate must be idempotent, that is, for any input `x` it must be that:
+   * ```
+   * transform(tranform(x)) = tranform(x)
+   * ```
+   */
+  abstract XXEFlowState transform(XXEFlowState flowstate);
+}
+
+/**
+ * The `AbstractDOMParser` class.
+ */
+class AbstractDOMParserClass extends Class {
+  AbstractDOMParserClass() { this.hasName("AbstractDOMParser") }
+}
+
+/**
+ * The `XercesDOMParser` class.
+ */
+class XercesDOMParserClass extends Class {
+  XercesDOMParserClass() { this.hasName("XercesDOMParser") }
+}
+
+/**
+ * Gets a valid flow state for `XercesDOMParser` flow.
+ *
+ * These flow states take the form `XercesDOM-A-B`, where:
+ *  - A is 1 if `setDisableDefaultEntityResolution` is `true`, 0 otherwise.
+ *  - B is 1 if `setCreateEntityReferenceNodes` is `true`, 0 otherwise.
+ */
+predicate encodeXercesDOMFlowState(
+  string flowstate, int disabledDefaultEntityResolution, int createEntityReferenceNodes
+) {
+  flowstate = "XercesDOM-0-0" and
+  disabledDefaultEntityResolution = 0 and
+  createEntityReferenceNodes = 0
+  or
+  flowstate = "XercesDOM-0-1" and
+  disabledDefaultEntityResolution = 0 and
+  createEntityReferenceNodes = 1
+  or
+  flowstate = "XercesDOM-1-0" and
+  disabledDefaultEntityResolution = 1 and
+  createEntityReferenceNodes = 0
+  or
+  flowstate = "XercesDOM-1-1" and
+  disabledDefaultEntityResolution = 1 and
+  createEntityReferenceNodes = 1
+}
+
+/**
+ * A flow state representing the configuration of a `XercesDOMParser` object.
+ */
+class XercesDOMParserFlowState extends XXEFlowState {
+  XercesDOMParserFlowState() { encodeXercesDOMFlowState(this, _, _) }
+}
+
+/**
+ * A flow state transformer for a call to
+ * `AbstractDOMParser.setDisableDefaultEntityResolution`. Transforms the flow
+ * state through the qualifier according to the setting in the parameter.
+ */
+class DisableDefaultEntityResolutionTranformer extends XXEFlowStateTranformer {
+  Expr newValue;
+
+  DisableDefaultEntityResolutionTranformer() {
+    exists(Call call, Function f |
+      call.getTarget() = f and
+      f.getDeclaringType() instanceof AbstractDOMParserClass and
+      f.hasName("setDisableDefaultEntityResolution") and
+      this = call.getQualifier() and
+      newValue = call.getArgument(0)
+    )
+  }
+
+  final override XXEFlowState transform(XXEFlowState flowstate) {
+    exists(int createEntityReferenceNodes |
+      encodeXercesDOMFlowState(flowstate, _, createEntityReferenceNodes) and
+      (
+        newValue.getValue().toInt() = 1 and // true
+        encodeXercesDOMFlowState(result, 1, createEntityReferenceNodes)
+        or
+        not newValue.getValue().toInt() = 1 and // false or unknown
+        encodeXercesDOMFlowState(result, 0, createEntityReferenceNodes)
+      )
+    )
+  }
+}
+
+/**
+ * A flow state transformer for a call to
+ * `AbstractDOMParser.setCreateEntityReferenceNodes`. Transforms the flow
+ * state through the qualifier according to the setting in the parameter.
+ */
+class CreateEntityReferenceNodesTranformer extends XXEFlowStateTranformer {
+  Expr newValue;
+
+  CreateEntityReferenceNodesTranformer() {
+    exists(Call call, Function f |
+      call.getTarget() = f and
+      f.getDeclaringType() instanceof AbstractDOMParserClass and
+      f.hasName("setCreateEntityReferenceNodes") and
+      this = call.getQualifier() and
+      newValue = call.getArgument(0)
+    )
+  }
+
+  final override XXEFlowState transform(XXEFlowState flowstate) {
+    exists(int disabledDefaultEntityResolution |
+      encodeXercesDOMFlowState(flowstate, disabledDefaultEntityResolution, _) and
+      (
+        newValue.getValue().toInt() = 1 and // true
+        encodeXercesDOMFlowState(result, disabledDefaultEntityResolution, 1)
+        or
+        not newValue.getValue().toInt() = 1 and // false or unknown
+        encodeXercesDOMFlowState(result, disabledDefaultEntityResolution, 0)
+      )
+    )
+  }
+}
+
+/**
+ * The `AbstractDOMParser.parse` method.
+ */
+class ParseFunction extends Function {
+  ParseFunction() { this.getClassAndName("parse") instanceof AbstractDOMParserClass }
+}
+
+/**
+ * The `createLSParser` function that returns a newly created `LSParser` object.
+ */
+class CreateLSParser extends Function {
+  CreateLSParser() {
+    this.hasName("createLSParser") and
+    this.getUnspecifiedType().(PointerType).getBaseType().getName() = "DOMLSParser" // returns a `DOMLSParser *`.
+  }
+}
+
+/**
+ * A configuration for tracking XML objects and their states.
+ */
+class XXEConfiguration extends DataFlow::Configuration {
+  XXEConfiguration() { this = "XXEConfiguration" }
+
+  override predicate isSource(DataFlow::Node node, string flowstate) {
+    // source is the write on `this` of a call to the `XercesDOMParser`
+    // constructor.
+    exists(CallInstruction call |
+      call.getStaticCallTarget() = any(XercesDOMParserClass c).getAConstructor() and
+      node.asInstruction().(WriteSideEffectInstruction).getDestinationAddress() =
+        call.getThisArgument() and
+      encodeXercesDOMFlowState(flowstate, 0, 1) // default configuration
+    )
+    or
+    // source is the result of a call to `createLSParser`.
+    exists(Call call |
+      call.getTarget() instanceof CreateLSParser and
+      call = node.asExpr() and
+      encodeXercesDOMFlowState(flowstate, 0, 1) // default configuration
+    )
+  }
+
+  override predicate isSink(DataFlow::Node node, string flowstate) {
+    // sink is the read of the qualifier of a call to `parse`.
+    exists(Call call |
+      call.getTarget() instanceof ParseFunction and
+      call.getQualifier() = node.asConvertedExpr()
+    ) and
+    flowstate instanceof XercesDOMParserFlowState and
+    not encodeXercesDOMFlowState(flowstate, 1, 1) // safe configuration
+  }
+
+  override predicate isAdditionalFlowStep(
+    DataFlow::Node node1, string state1, DataFlow::Node node2, string state2
+  ) {
+    // create additional flow steps for `XXEFlowStateTranformer`s
+    state2 = node2.asConvertedExpr().(XXEFlowStateTranformer).transform(state1) and
+    DataFlow::simpleLocalFlowStep(node1, node2)
+  }
+
+  override predicate isBarrier(DataFlow::Node node, string flowstate) {
+    // when the flowstate is transformed at a call node, block the original
+    // flowstate value.
+    node.asConvertedExpr().(XXEFlowStateTranformer).transform(flowstate) != flowstate
+  }
+}
+
+from XXEConfiguration conf, DataFlow::PathNode source, DataFlow::PathNode sink
+where conf.hasFlowPath(source, sink)
+select sink, source, sink,
+  "This $@ is not configured to prevent an XML external entity (XXE) attack.", source, "XML parser"

cpp/ql/src/Security/CWE/CWE-611/XXEBad.cpp

@@ -0,0 +1,4 @@
+
+XercesDOMParser *parser = new XercesDOMParser();
+
+parser->parse(data); // BAD (parser is not correctly configured, may expand external entity references)

cpp/ql/src/Security/CWE/CWE-611/XXEGood.cpp

@@ -0,0 +1,5 @@
+
+XercesDOMParser *parser = new XercesDOMParser();
+
+parser->setDisableDefaultEntityResolution(true);
+parser->parse(data);

cpp/ql/src/change-notes/2022-03-03-potential-system-data-exposure.md

@@ -1,4 +0,0 @@
----
-category: minorAnalysis
----
-* A new query, "Potential exposure of sensitive system data to an unauthorized control sphere" (`cpp/potential-system-data-exposure`) has been added. This query is focused on exposure of information that is highly likely to be sensitive, whereas the similar query "Exposure of system data to an unauthorized control sphere" (`cpp/system-data-exposure`) is focused on exposure of information on a channel that is more likely to be intercepted by an attacker.

cpp/ql/src/change-notes/2022-03-21-command-line-injection-with-flow-states.md

@@ -1,4 +0,0 @@
----
-category: minorAnalysis
----
-* The `cpp/command-line-injection` query now takes into account calling contexts across string concatenations. This removes false positives due to mismatched calling contexts before and after string concatenations.

cpp/ql/src/change-notes/2022-03-25-unused-lambda-capture.md

@@ -1,4 +0,0 @@
----
-category: minorAnalysis
----
-* The `cpp/unused-local-variable` no longer ignores functions that include lambda expressions capturing trivially copyable objects.

cpp/ql/src/change-notes/2022-03-28-cleartext-transmission.md

@@ -1,4 +0,0 @@
----
-category: minorAnalysis
----
-* The `cpp/cleartext-transmission` query now recognizes additional sources, for sensitive private data such as e-mail addresses and credit card numbers.

cpp/ql/src/change-notes/2022-04-13-pexternal-entity-expansion.md

@@ -0,0 +1,4 @@
+---
+category: newQuery
+---
+* An new query `cpp/external-entity-expansion` has been added. The query detects XML objects that are vulnerable to external entity expansion (XXE) attacks.

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

@@ -0,0 +1,8 @@
+## 0.1.0
+
+### Minor Analysis Improvements
+
+* The `cpp/cleartext-transmission` query now recognizes additional sources, for sensitive private data such as e-mail addresses and credit card numbers.
+* The `cpp/unused-local-variable` no longer ignores functions that include lambda expressions capturing trivially copyable objects.
+* The `cpp/command-line-injection` query now takes into account calling contexts across string concatenations. This removes false positives due to mismatched calling contexts before and after string concatenations.
+* A new query, "Potential exposure of sensitive system data to an unauthorized control sphere" (`cpp/potential-system-data-exposure`) has been added. This query is focused on exposure of information that is highly likely to be sensitive, whereas the similar query "Exposure of system data to an unauthorized control sphere" (`cpp/system-data-exposure`) is focused on exposure of information on a channel that is more likely to be intercepted by an attacker.

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

@@ -1,2 +1,2 @@
 ---
-lastReleaseVersion: 0.0.13
+lastReleaseVersion: 0.1.0

cpp/ql/src/experimental/Security/CWE/CWE-266/IncorrectPrivilegeAssignment.ql

@@ -16,7 +16,6 @@
  */
 
 import cpp
-import semmle.code.cpp.exprs.BitwiseOperation
 import semmle.code.cpp.valuenumbering.GlobalValueNumbering
 
 /**

cpp/ql/src/qlpack.yml

@@ -1,5 +1,5 @@
 name: codeql/cpp-queries
-version: 0.1.0-dev
+version: 0.1.1-dev
 groups: 
   - cpp
   - queries

cpp/ql/test/library-tests/controlflow/dominance/bbIDominates.expected

@@ -31,4 +31,4 @@
 | test2 | 83 | if (...) ...  | 74 | test2 |
 | test2 | 83 | if (...) ...  | 84 | break; |
 | test2 | 83 | if (...) ...  | 85 | if (...) ...  |
-| test2 | 85 | if (...) ...  | 0 | { ... } |
+| test2 | 85 | if (...) ...  | 86 | { ... } |

cpp/ql/test/library-tests/controlflow/dominance/dominator.expected

@@ -118,7 +118,7 @@
 | test | 44 | ... = ... | 42 | j |
 | test | 44 | ExprStmt | 44 | 10 |
 | test | 44 | w | 44 | ... = ... |
-| test | 47 | ... += ... | 50 | for(...;...;...) ... |
+| test | 47 | ... += ... | 50 | { ... } |
 | test | 47 | ExprStmt | 47 | z |
 | test | 47 | w | 47 | ... += ... |
 | test | 47 | z | 47 | w |
@@ -133,6 +133,7 @@
 | test | 50 | j | 50 | ... ++ |
 | test | 50 | j | 50 | ... = ... |
 | test | 50 | label ...: | 50 | j |
+| test | 50 | { ... } | 50 | for(...;...;...) ... |
 | test | 50 | { ... } | 51 | ExprStmt |
 | test | 51 | 30 | 51 | y |
 | test | 51 | ... = ... | 52 | if (...) ...  |
@@ -181,10 +182,10 @@
 | test | 70 | ExprStmt | 70 | 40 |
 | test | 70 | w | 70 | ... = ... |
 | test | 71 | return ... | 71 | w |
-| test2 | 0 | { ... } | 86 | ExprStmt |
 | test2 | 74 | { ... } | 76 | declaration |
-| test2 | 76 | declaration | 77 | for(...;...;...) ... |
+| test2 | 76 | declaration | 77 | { ... } |
 | test2 | 77 | for(...;...;...) ... | 77 | { ... } |
+| test2 | 77 | { ... } | 77 | for(...;...;...) ... |
 | test2 | 77 | { ... } | 78 | ExprStmt |
 | test2 | 78 | 10 | 78 | b |
 | test2 | 78 | ... = ... | 79 | if (...) ...  |
@@ -211,11 +212,12 @@
 | test2 | 83 | if (...) ...  | 83 | a |
 | test2 | 84 | break; | 87 | label ...: |
 | test2 | 85 | 20 | 85 | ... == ... |
-| test2 | 85 | ... == ... | 0 | { ... } |
+| test2 | 85 | ... == ... | 86 | { ... } |
 | test2 | 85 | a | 85 | 20 |
 | test2 | 85 | if (...) ...  | 85 | a |
 | test2 | 86 | ExprStmt | 86 | c |
 | test2 | 86 | c | 86 | return ... |
+| test2 | 86 | { ... } | 86 | ExprStmt |
 | test2 | 87 | label ...: | 88 | ExprStmt |
 | test2 | 88 | ExprStmt | 88 | b |
 | test2 | 88 | b | 88 | return ... |

cpp/ql/test/library-tests/dataflow/dataflow-tests/dataflow-ir-consistency.expected

@@ -218,10 +218,10 @@ postWithInFlow
 | lambdas.cpp:20:11:20:11 | FieldAddress [post update] | PostUpdateNode should not be the target of local flow. |
 | lambdas.cpp:20:11:20:11 | FieldAddress [post update] | PostUpdateNode should not be the target of local flow. |
 | lambdas.cpp:20:11:20:11 | FieldAddress [post update] | PostUpdateNode should not be the target of local flow. |
-| lambdas.cpp:23:3:23:3 | (reference dereference) [post update] | PostUpdateNode should not be the target of local flow. |
 | lambdas.cpp:23:3:23:14 | FieldAddress [post update] | PostUpdateNode should not be the target of local flow. |
 | lambdas.cpp:23:3:23:14 | VariableAddress [post update] | PostUpdateNode should not be the target of local flow. |
 | lambdas.cpp:23:3:23:14 | v [post update] | PostUpdateNode should not be the target of local flow. |
+| lambdas.cpp:23:15:23:15 | (reference dereference) [post update] | PostUpdateNode should not be the target of local flow. |
 | lambdas.cpp:28:7:28:7 | VariableAddress [post update] | PostUpdateNode should not be the target of local flow. |
 | lambdas.cpp:28:10:31:2 | FieldAddress [post update] | PostUpdateNode should not be the target of local flow. |
 | lambdas.cpp:28:10:31:2 | FieldAddress [post update] | PostUpdateNode should not be the target of local flow. |

cpp/ql/test/library-tests/dataflow/fields/ir-path-flow.ql

@@ -4,7 +4,6 @@
 
 import semmle.code.cpp.ir.dataflow.DataFlow
 import IRConfiguration
-import cpp
 import DataFlow::PathGraph
 
 from DataFlow::PathNode src, DataFlow::PathNode sink, IRConf conf

cpp/ql/test/library-tests/dataflow/fields/path-flow.ql

@@ -4,7 +4,6 @@
 
 import semmle.code.cpp.dataflow.DataFlow
 import ASTConfiguration
-import cpp
 import DataFlow::PathGraph
 
 from DataFlow::PathNode src, DataFlow::PathNode sink, AstConf conf

cpp/ql/test/library-tests/depends_initializers/InitializerAccesses.expected

@@ -1,7 +1,7 @@
 | initializers.cpp:18:8:18:15 | initializer for y | initializers.cpp:18:9:18:9 | x |
 | initializers.cpp:19:8:19:21 | initializer for z | initializers.cpp:19:9:19:9 | x |
 | initializers.cpp:23:8:23:9 | initializer for j | initializers.cpp:23:9:23:9 | i |
-| initializers.cpp:27:8:27:10 | initializer for aax | initializers.cpp:27:9:27:10 | ax |
+| initializers.cpp:27:9:27:10 | initializer for aax | initializers.cpp:27:9:27:10 | ax |
 | initializers.cpp:30:20:30:35 | initializer for myIntArray | initializers.cpp:30:22:30:22 | i |
 | template_static.cpp:9:24:9:24 | initializer for static_c | template_static.cpp:9:24:9:24 | c |
 | template_static.cpp:10:22:10:24 | initializer for static_v | template_static.cpp:10:24:10:24 | v |

cpp/ql/test/library-tests/depends_initializers/InitializerCFG.expected

@@ -8,7 +8,7 @@
 | initializers.cpp:23:8:23:9 | initializer for j |  |
 | initializers.cpp:25:3:25:3 | initializer for a |  |
 | initializers.cpp:26:7:26:10 | initializer for ax |  |
-| initializers.cpp:27:8:27:10 | initializer for aax |  |
+| initializers.cpp:27:9:27:10 | initializer for aax |  |
 | initializers.cpp:30:20:30:35 | initializer for myIntArray |  |
 | initializers.cpp:31:3:31:15 | initializer for myObjectArray |  |
 | template_static.cpp:2:15:2:15 | initializer for c |  |