Merge pull request #14214 from github/cklin/pick-js-fix-2.14.5

Cherry pick "fix out of bounds string access in isUsingDecl" into 2.14.5

.bazelrc

@@ -1,3 +1,9 @@
-build --repo_env=CC=clang --repo_env=CXX=clang++ --cxxopt="-std=c++17"
+common --enable_platform_specific_config
+
+build --repo_env=CC=clang --repo_env=CXX=clang++
+
+build:linux --cxxopt=-std=c++20
+build:macos --cxxopt=-std=c++20 --cpu=darwin_x86_64
+build:windows --cxxopt=/std:c++20 --cxxopt=/Zc:preprocessor
 
 try-import %workspace%/local.bazelrc

.bazelversion

@@ -1 +1 @@
-5.0.0
+6.3.1

.devcontainer/devcontainer.json

@@ -1,6 +1,6 @@
 {
   "extensions": [
-    "rust-lang.rust",
+    "rust-lang.rust-analyzer",
     "bungcip.better-toml",
     "github.vscode-codeql",
     "hbenl.vscode-test-explorer",

.git-blame-ignore-revs

@@ -0,0 +1,21 @@
+# .git-blame-ignore-revs
+# Auto-formatted Java
+730eae952139209fe9fdf598541d608f4c0c0c84
+# Auto-formatted C#
+5ad7ed49dd3de03ec6dcfcb6848758a6a987e11c
+# Auto-formatted C/C++
+ef97e539ec1971494d4bba5cafe82e00bc8217ac
+# Auto-formatted Python
+21d5fa836b3a7d020ba45e8b8168b145a9772131
+# Auto-formatted JavaScript
+8d97fe9ed327a9546ff2eaf515cf0f5214deddd9
+# Auto-formatted Ruby
+a5d229903d2f12d45f2c2c38822f1d0e7504ae7f
+# Auto-formatted Go
+08c658e66bf867090033ea096e244a93d46c0aa7
+# Auto-formatted Swift
+711d7057f79fb7d72fc3b35e010bd018f9009169
+# Auto-formatted shared ql packs
+3640b6d3a8ce9edf8e1d3ed106fe8526cf255bc0
+# Auto-formatted taint tracking files
+159d8e978c51959b380838c080d891b66e763b19

.github/actions/cache-query-compilation/action.yml

@@ -9,7 +9,7 @@ inputs:
 outputs:
   cache-dir:
     description: "The directory where the cache was stored"
-    value: ${{ steps.fill-compilation-dir.outputs.compdir }}
+    value: ${{ steps.output-compilation-dir.outputs.compdir }}
 
 runs:
   using: composite
@@ -27,7 +27,9 @@ runs:
       if: ${{ github.event_name == 'pull_request' }}
       uses: actions/cache/restore@v3
       with:
-        path: '**/.cache'
+        path: |
+          **/.cache
+          ~/.codeql/compile-cache
         key: codeql-compile-${{ inputs.key }}-pr-${{ github.sha }}
         restore-keys: |
           codeql-compile-${{ inputs.key }}-${{ github.base_ref }}-${{ env.merge_base }}
@@ -37,18 +39,111 @@ runs:
       if: ${{ github.event_name != 'pull_request' }}
       uses: actions/cache@v3
       with:
-        path: '**/.cache'
+        path: |
+          **/.cache
+          ~/.codeql/compile-cache
         key: codeql-compile-${{ inputs.key }}-${{ github.ref_name }}-${{ github.sha }} # just fill on main
         restore-keys: | # restore the latest cache if the exact cache is unavailable, to speed up compilation.
           codeql-compile-${{ inputs.key }}-${{ github.ref_name }}-
           codeql-compile-${{ inputs.key }}-main-
-    - name: Fill compilation cache directory
-      id: fill-compilation-dir
+    - name: Output-compilationdir
+      id: output-compilation-dir
       shell: bash
       run: |
-        # Move all the existing cache into another folder, so we only preserve the cache for the current queries.
-        node $GITHUB_WORKSPACE/.github/actions/cache-query-compilation/move-caches.js ${COMBINED_CACHE_DIR}
-
         echo "compdir=${COMBINED_CACHE_DIR}" >> $GITHUB_OUTPUT
       env:
         COMBINED_CACHE_DIR: ${{ runner.temp }}/compilation-dir
+    - name: Fill compilation cache directory
+      id: fill-compilation-dir
+      uses: actions/github-script@v6
+      env: 
+        COMBINED_CACHE_DIR: ${{ runner.temp }}/compilation-dir
+      with:
+        script: |
+          // # Move all the existing cache into another folder, so we only preserve the cache for the current queries.
+          // mkdir -p ${COMBINED_CACHE_DIR}
+          // rm -f **/.cache/{lock,size} # -f to avoid errors if the cache is empty.
+          // # copy the contents of the .cache folders into the combined cache folder.
+          // cp -r **/.cache/* ${COMBINED_CACHE_DIR}/ || : # ignore missing files
+          // # clean up the .cache folders
+          // rm -rf **/.cache/*
+
+          const fs = require("fs");
+          const path = require("path");
+          const os = require("os");
+
+          // the first argv is the cache folder to create.
+          const COMBINED_CACHE_DIR = process.env.COMBINED_CACHE_DIR;
+
+          function* walkCaches(dir) {
+            const files = fs.readdirSync(dir, { withFileTypes: true });
+            for (const file of files) {
+              if (file.isDirectory()) {
+                const filePath = path.join(dir, file.name);
+                yield* walkCaches(filePath);
+                if (file.name === ".cache") {
+                  yield filePath;
+                }
+              }
+            }
+          }
+
+          async function copyDir(src, dest) {
+            for await (const file of await fs.promises.readdir(src, { withFileTypes: true })) {
+              const srcPath = path.join(src, file.name);
+              const destPath = path.join(dest, file.name);
+              if (file.isDirectory()) {
+                if (!fs.existsSync(destPath)) {
+                  fs.mkdirSync(destPath);
+                }
+                await copyDir(srcPath, destPath);
+              } else {
+                await fs.promises.copyFile(srcPath, destPath);
+              }
+            }
+          }
+
+          async function main() {
+            const cacheDirs = [...walkCaches(".")];
+
+            for (const dir of cacheDirs) {
+              console.log(`Found .cache dir at ${dir}`);
+            }
+
+            const globalCacheDir = path.join(os.homedir(), ".codeql", "compile-cache");
+            if (fs.existsSync(globalCacheDir)) {
+              console.log("Found global home dir: " + globalCacheDir);
+              cacheDirs.push(globalCacheDir);
+            }
+
+            if (cacheDirs.length === 0) {
+              console.log("No cache dirs found");
+              return;
+            }
+
+            // mkdir -p ${COMBINED_CACHE_DIR}
+            fs.mkdirSync(COMBINED_CACHE_DIR, { recursive: true });
+
+            // rm -f **/.cache/{lock,size} # -f to avoid errors if the cache is empty.
+            await Promise.all(
+              cacheDirs.map((cacheDir) =>
+                (async function () {
+                  await fs.promises.rm(path.join(cacheDir, "lock"), { force: true });
+                  await fs.promises.rm(path.join(cacheDir, "size"), { force: true });
+                })()
+              )
+            );
+
+            // # copy the contents of the .cache folders into the combined cache folder.
+            // cp -r **/.cache/* ${COMBINED_CACHE_DIR}/ || : # ignore missing files
+            await Promise.all(
+              cacheDirs.map((cacheDir) => copyDir(cacheDir, COMBINED_CACHE_DIR))
+            );
+
+            // # clean up the .cache folders
+            // rm -rf **/.cache/*
+            await Promise.all(
+              cacheDirs.map((cacheDir) => fs.promises.rm(cacheDir, { recursive: true }))
+            );
+          }
+          main();

.github/actions/cache-query-compilation/move-caches.js

@@ -1,75 +0,0 @@
-// # Move all the existing cache into another folder, so we only preserve the cache for the current queries.
-// mkdir -p ${COMBINED_CACHE_DIR}
-// rm -f **/.cache/{lock,size} # -f to avoid errors if the cache is empty.
-// # copy the contents of the .cache folders into the combined cache folder.
-// cp -r **/.cache/* ${COMBINED_CACHE_DIR}/ || : # ignore missing files
-// # clean up the .cache folders
-// rm -rf **/.cache/*
-
-const fs = require("fs");
-const path = require("path");
-
-// the first argv is the cache folder to create.
-const COMBINED_CACHE_DIR = process.argv[2];
-
-function* walkCaches(dir) {
-  const files = fs.readdirSync(dir, { withFileTypes: true });
-  for (const file of files) {
-    if (file.isDirectory()) {
-      const filePath = path.join(dir, file.name);
-      yield* walkCaches(filePath);
-      if (file.name === ".cache") {
-        yield filePath;
-      }
-    }
-  }
-}
-
-async function copyDir(src, dest) {
-  for await (const file of await fs.promises.readdir(src, { withFileTypes: true })) {
-    const srcPath = path.join(src, file.name);
-    const destPath = path.join(dest, file.name);
-    if (file.isDirectory()) {
-      if (!fs.existsSync(destPath)) {
-        fs.mkdirSync(destPath);
-      }
-      await copyDir(srcPath, destPath);
-    } else {
-      await fs.promises.copyFile(srcPath, destPath);
-    }
-  }
-}
-
-async function main() {
-  const cacheDirs = [...walkCaches(".")];
-
-  for (const dir of cacheDirs) {
-    console.log(`Found .cache dir at ${dir}`);
-  }
-
-  // mkdir -p ${COMBINED_CACHE_DIR}
-  fs.mkdirSync(COMBINED_CACHE_DIR, { recursive: true });
-
-  // rm -f **/.cache/{lock,size} # -f to avoid errors if the cache is empty.
-  await Promise.all(
-    cacheDirs.map((cacheDir) =>
-      (async function () {
-        await fs.promises.rm(path.join(cacheDir, "lock"), { force: true });
-        await fs.promises.rm(path.join(cacheDir, "size"), { force: true });
-      })()
-    )
-  );
-
-  // # copy the contents of the .cache folders into the combined cache folder.
-  // cp -r **/.cache/* ${COMBINED_CACHE_DIR}/ || : # ignore missing files
-  await Promise.all(
-    cacheDirs.map((cacheDir) => copyDir(cacheDir, COMBINED_CACHE_DIR))
-  );
-
-  // # clean up the .cache folders
-  // rm -rf **/.cache/*
-  await Promise.all(
-    cacheDirs.map((cacheDir) => fs.promises.rm(cacheDir, { recursive: true }))
-  );
-}
-main();

.github/labeler.yml

@@ -11,7 +11,7 @@ Go:
   - change-notes/**/*go.*
 
 Java:
-  - any: [ 'java/**/*', '!java/kotlin-extractor/**/*', '!java/kotlin-explorer/**/*', '!java/ql/test/kotlin/**/*' ]
+  - any: [ 'java/**/*', '!java/kotlin-extractor/**/*', '!java/ql/test/kotlin/**/*' ]
   - change-notes/**/*java.*
 
 JS:
@@ -20,7 +20,6 @@ JS:
 
 Kotlin:
   - java/kotlin-extractor/**/*
-  - java/kotlin-explorer/**/*
   - java/ql/test/kotlin/**/*
 
 Python:

.github/workflows/atm-check-query-suite.yml

@@ -1,102 +0,0 @@
-name: "ATM - Check query suite"
-
-env:
-  QUERY_PACK: javascript/ql/experimental/adaptivethreatmodeling/src
-  QUERY_SUITE: codeql-suites/javascript-atm-code-scanning.qls
-
-on:
-  pull_request:
-    paths:
-      - ".github/workflows/atm-check-query-suite.yml"
-      - "javascript/ql/experimental/adaptivethreatmodeling/**"
-  workflow_dispatch:
-
-jobs:
-  atm-check-query-suite:
-    runs-on: ubuntu-latest-xl
-
-    steps:
-      - uses: actions/checkout@v3
-
-      - name: Setup CodeQL
-        uses: ./.github/actions/fetch-codeql
-        with:
-          channel: release
-
-      - name: Cache compilation cache
-        id: query-cache
-        uses: ./.github/actions/cache-query-compilation
-        with: 
-          key: atm-suite
-
-      - name: Install ATM model
-        run: |
-          set -exu
-
-          # Install dependencies of ATM query pack, i.e. the ATM model
-          codeql pack install "${QUERY_PACK}"
-
-          # Retrieve model checksum
-          model_checksum=$(codeql resolve extensions "${QUERY_PACK}/${QUERY_SUITE}" | jq -r '.models[0].checksum')
-
-          # Trust the model so that we can use it in the ATM boosted queries
-          mkdir -p "$HOME/.config/codeql"
-          echo "--insecurely-execute-ml-model-checksums ${model_checksum}" >> "$HOME/.config/codeql/config"
-
-      - name: Create test DB
-        run: |
-          DB_PATH="${RUNNER_TEMP}/db"
-          echo "DB_PATH=${DB_PATH}" >> "${GITHUB_ENV}"
-
-          codeql database create "${DB_PATH}" --source-root config/atm --language javascript 
-
-      - name: Run ATM query suite
-        run: |
-          SARIF_PATH="${RUNNER_TEMP}/sarif.json"
-          echo "SARIF_PATH=${SARIF_PATH}" >> "${GITHUB_ENV}"
-
-          codeql database analyze \
-            --threads=0 \
-            --ram 50000 \
-            --format sarif-latest \
-            --output "${SARIF_PATH}" \
-            --sarif-group-rules-by-pack \
-            -vv \
-            --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}" \
-            -- \
-            "${DB_PATH}" \
-            "${QUERY_PACK}/${QUERY_SUITE}"
-
-      - name: Upload SARIF
-        uses: actions/upload-artifact@v3
-        with:
-          name: javascript-ml-powered-queries.sarif
-          path: "${{ env.SARIF_PATH }}"
-          retention-days: 5
-
-      - name: Check results
-        run: |
-          # We should run at least the ML-powered queries in `expected_rules`.
-          expected_rules="js/ml-powered/nosql-injection js/ml-powered/path-injection js/ml-powered/sql-injection js/ml-powered/xss"
-
-          for rule in ${expected_rules}; do
-            found_rule=$(jq --arg rule "${rule}" '[.runs[0].tool.extensions[].rules | select(. != null) |
-              flatten | .[].id] | any(. == $rule)' "${SARIF_PATH}")
-            if [[ "${found_rule}" != "true" ]]; then
-              echo "Expected SARIF output to contain rule '${rule}', but found no such rule."
-              exit 1
-            else
-              echo "Found rule '${rule}'."
-            fi
-          done
-
-          # We should have at least one alert from an ML-powered query.
-          num_alerts=$(jq '[.runs[0].results[] |
-            select(.properties.score != null and (.rule.id | startswith("js/ml-powered/")))] | length' \
-            "${SARIF_PATH}")
-          if [[ "${num_alerts}" -eq 0 ]]; then
-            echo "Expected to find at least one alert from an ML-powered query but found ${num_alerts}."
-            exit 1
-          else
-            echo "Found ${num_alerts} alerts from ML-powered queries.";
-          fi

.github/workflows/atm-model-integration-tests.yml

@@ -1,12 +0,0 @@
-name: ATM Model Integration Tests
-
-on:
-  workflow_dispatch:
-
-jobs:
-  hello-world:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: foo
-        run: echo "Hello world"

.github/workflows/check-change-note.yml

@@ -8,9 +8,9 @@ on:
       - "*/ql/src/**/*.qll"
       - "*/ql/lib/**/*.ql"
       - "*/ql/lib/**/*.qll"
+      - "*/ql/lib/**/*.yml"
       - "!**/experimental/**"
       - "!ql/**"
-      - "!swift/**"
       - ".github/workflows/check-change-note.yml"
 
 jobs:
@@ -26,9 +26,9 @@ jobs:
         run: |
           gh api 'repos/${{github.repository}}/pulls/${{github.event.number}}/files' --paginate --jq 'any(.[].filename ; test("/change-notes/.*[.]md$"))' |
           grep true -c
-      - name: Fail if the change note filename doesn't match the expected format. The file name must be of the form 'YYYY-MM-DD.md' or 'YYYY-MM-DD-{title}.md', where '{title}' is arbitrary text.
+      - name: Fail if the change note filename doesn't match the expected format. The file name must be of the form 'YYYY-MM-DD.md', 'YYYY-MM-DD-{title}.md', where '{title}' is arbitrary text, or released/x.y.z.md for released change-notes
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         run: |
-          gh api 'repos/${{github.repository}}/pulls/${{github.event.number}}/files' --paginate --jq '[.[].filename | select(test("/change-notes/.*[.]md$"))] | all(test("/change-notes/[0-9]{4}-[0-9]{2}-[0-9]{2}.*[.]md$"))' |
+          gh api 'repos/${{github.repository}}/pulls/${{github.event.number}}/files' --paginate --jq '[.[].filename | select(test("/change-notes/.*[.]md$"))] | all(test("/change-notes/[0-9]{4}-[0-9]{2}-[0-9]{2}.*[.]md$") or test("/change-notes/released/[0-9]*[.][0-9]*[.][0-9]*[.]md$"))' |
           grep true -c

.github/workflows/check-implicit-this.yml

@@ -0,0 +1,29 @@
+name: "Check implicit this warnings"
+
+on:
+  workflow_dispatch:
+  pull_request:
+    paths:
+      - "**qlpack.yml"
+    branches:
+      - main
+      - "rc/*"
+
+jobs:
+  check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Check that implicit this warnings is enabled for all packs
+        shell: bash
+        run: |
+          EXIT_CODE=0
+          packs="$(find . -iname 'qlpack.yml')"
+          for pack_file in ${packs}; do
+            option="$(yq '.warnOnImplicitThis' ${pack_file})"
+            if [ "${option}" != "true" ]; then
+              echo "::error file=${pack_file}::warnOnImplicitThis property must be set to 'true' for pack ${pack_file}"
+              EXIT_CODE=1
+            fi
+          done
+          exit "${EXIT_CODE}"

.github/workflows/check-qldoc.yml

@@ -26,9 +26,8 @@ jobs:
         shell: bash
         run: |
           EXIT_CODE=0
-          # TODO: remove the swift exception from the regex when we fix generated QLdoc
           # TODO: remove the shared exception from the regex when coverage of qlpacks without dbschemes is supported
-          changed_lib_packs="$(git diff --name-only --diff-filter=ACMRT HEAD^ HEAD | { grep -Po '^(?!(swift|shared))[a-z]*/ql/lib' || true; } | sort -u)"
+          changed_lib_packs="$(git diff --name-only --diff-filter=ACMRT HEAD^ HEAD | { grep -Po '^(?!(shared))[a-z]*/ql/lib' || true; } | sort -u)"
           for pack_dir in ${changed_lib_packs}; do
             lang="${pack_dir%/ql/lib}"
             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@v7
+    - uses: actions/stale@v8
       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/compile-queries.yml

@@ -24,14 +24,14 @@ jobs:
         with: 
           key: all-queries
       - name: check formatting
-        run: find */ql -type f \( -name "*.qll" -o -name "*.ql" \) -print0 | xargs -0 codeql query format --check-only
+        run: find */ql -type f \( -name "*.qll" -o -name "*.ql" \) -print0 | xargs -0 -n 3000 -P 10 codeql query format -q --check-only
       - name: compile queries - check-only
         # run with --check-only if running in a PR (github.sha != main)
         if : ${{ github.event_name == 'pull_request' }}
         shell: bash
-        run: codeql query compile -j0 */ql/{src,examples} --keep-going --warnings=error --check-only --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"
+        run: codeql query compile -q -j0 */ql/{src,examples} --keep-going --warnings=error --check-only --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"
       - name: compile queries - full
         # do full compile if running on main - this populates the cache
         if : ${{ github.event_name != 'pull_request' }}
         shell: bash
-        run: codeql query compile -j0 */ql/{src,examples} --keep-going --warnings=error --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"
+        run: codeql query compile -q -j0 */ql/{src,examples} --keep-going --warnings=error --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"

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

@@ -10,6 +10,7 @@ on:
       - "*/ql/src/**/*.qll"
       - "*/ql/lib/**/*.ql"
       - "*/ql/lib/**/*.qll"
+      - "*/ql/lib/ext/**/*.yml"
       - "misc/scripts/library-coverage/*.py"
       # input data files
       - "*/documentation/library-coverage/cwe-sink.csv"

.github/workflows/fast-forward.yml

@@ -0,0 +1,50 @@
+# Fast-forwards the branch specified in BRANCH_NAME
+# to the github.ref/sha that this workflow is run on.
+# Used as part of the release process, to ensure
+# external query writers can always access a branch of github/codeql
+# that is compatible with the latest stable release.
+name: Fast-forward tracking branch for selected CodeQL version
+on:
+  workflow_dispatch:
+
+jobs:
+  fast-forward:
+    name: Fast-forward tracking branch for selected CodeQL version
+    runs-on: ubuntu-latest
+    if: github.repository == 'github/codeql'
+    permissions:
+      contents: write
+    env:
+      BRANCH_NAME: 'lgtm.com'
+    steps:
+      - name: Validate chosen branch
+        if: ${{ !startsWith(github.ref_name, 'codeql-cli-') }}
+        shell: bash
+        run: |
+          echo "::error ::The $BRANCH_NAME tracking branch should only be fast-forwarded to the tip of a codeql-cli-* branch, got $GITHUB_REF_NAME instead."
+          exit 1
+
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Git config
+        shell: bash
+        run: |
+          git config user.name "github-actions[bot]"
+          git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
+
+      - name: Fetch
+        shell: bash
+        run: |
+          set -x
+          echo "Fetching $BRANCH_NAME"
+          # Explicitly unshallow and fetch to ensure the remote ref is available.
+          git fetch --unshallow origin "$BRANCH_NAME"
+          git checkout -b "$BRANCH_NAME" "origin/$BRANCH_NAME"
+
+      - name: Fast-forward
+        shell: bash
+        run: |
+          echo "Fast-forwarding $BRANCH_NAME to ${GITHUB_REF}@${GITHUB_SHA}"
+          git merge --ff-only "$GITHUB_SHA"
+          git push origin "$BRANCH_NAME"

.github/workflows/go-tests-other-os.yml

@@ -7,15 +7,17 @@ on:
       - .github/workflows/go-tests-other-os.yml
       - .github/actions/**
       - codeql-workspace.yml
+env:
+  GO_VERSION: '~1.21.0'
 jobs:
   test-mac:
     name: Test MacOS
     runs-on: macos-latest
     steps:
-      - name: Set up Go 1.20
-        uses: actions/setup-go@v3
+      - name: Set up Go ${{ env.GO_VERSION }}
+        uses: actions/setup-go@v4
         with:
-          go-version: 1.20.0
+          go-version: ${{ env.GO_VERSION }}
         id: go
 
       - name: Check out code
@@ -47,10 +49,10 @@ jobs:
     name: Test Windows
     runs-on: windows-latest-xl
     steps:
-      - name: Set up Go 1.20
-        uses: actions/setup-go@v3
+      - name: Set up Go ${{ env.GO_VERSION }}
+        uses: actions/setup-go@v4
         with:
-          go-version: 1.20.0
+          go-version: ${{ env.GO_VERSION }}
         id: go
 
       - name: Check out code

.github/workflows/go-tests.yml

@@ -15,15 +15,17 @@ on:
       - .github/workflows/go-tests.yml
       - .github/actions/**
       - codeql-workspace.yml
+env:
+  GO_VERSION: '~1.21.0'
 jobs:
   test-linux:
     name: Test Linux (Ubuntu)
     runs-on: ubuntu-latest-xl
     steps:
-      - name: Set up Go 1.20
-        uses: actions/setup-go@v3
+      - name: Set up Go ${{ env.GO_VERSION }}
+        uses: actions/setup-go@v4
         with:
-          go-version: 1.20.0
+          go-version: ${{ env.GO_VERSION }}
         id: go
 
       - name: Check out code

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

@@ -5,13 +5,6 @@ on:
     branches: [main]
   pull_request:
     branches: [main]
-    paths:
-      - "ql/**"
-      - "**.qll"
-      - "**.ql"
-      - "**.dbscheme"
-      - "**/qlpack.yml"
-      - ".github/workflows/ql-for-ql-build.yml"
 
 env:
   CARGO_TERM_COLOR: always
@@ -22,6 +15,8 @@ jobs:
     steps:
       ### Build the queries ###
       - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
       - name: Find codeql
         id: find-codeql
         uses: github/codeql-action/init@v2
@@ -34,8 +29,10 @@ jobs:
         id: cache-extractor
         uses: actions/cache@v3
         with:
-          path: ql/extractor-pack/
-          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-extractor-${{ hashFiles('ql/**/Cargo.lock') }}-${{ hashFiles('ql/**/*.rs') }}
+          path: |
+            ql/extractor-pack/
+            ql/target/release/buramu
+          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-extractor-${{ hashFiles('ql/**/Cargo.lock') }}-${{ hashFiles('shared/tree-sitter-extractor') }}-${{ hashFiles('ql/**/*.rs') }}
       - name: Cache cargo
         if: steps.cache-extractor.outputs.cache-hit != 'true'
         uses: actions/cache@v3
@@ -57,6 +54,7 @@ jobs:
           key: run-ql-for-ql
       - name: Make database and analyze
         run: |
+          ./ql/target/release/buramu | tee deprecated.blame # Add a blame file for the extractor to parse.
           ${CODEQL} database create -l=ql --search-path ql/extractor-pack ${DB}
           ${CODEQL} database analyze -j0 --format=sarif-latest --output=ql-for-ql.sarif ${DB} ql/ql/src/codeql-suites/ql-code-scanning.qls  --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"
         env: 
@@ -65,6 +63,7 @@ jobs:
           LGTM_INDEX_FILTERS: |
             exclude:ql/ql/test
             exclude:*/ql/lib/upgrades/
+            exclude:java/ql/integration-tests
       - name: Upload sarif to code-scanning
         uses: github/codeql-action/upload-sarif@v2
         with:

.github/workflows/ruby-build.yml

@@ -48,6 +48,9 @@ jobs:
         run: |
           brew install gnu-tar
           echo "/usr/local/opt/gnu-tar/libexec/gnubin" >> $GITHUB_PATH
+      - name: Install cargo-cross
+        if: runner.os == 'Linux'
+        run: cargo install cross --version 0.2.5
       - uses: ./.github/actions/os-version
         id: os_version
       - name: Cache entire extractor
@@ -55,12 +58,10 @@ jobs:
         id: cache-extractor
         with:
           path: |
-            ruby/target/release/ruby-autobuilder
-            ruby/target/release/ruby-autobuilder.exe
-            ruby/target/release/ruby-extractor
-            ruby/target/release/ruby-extractor.exe
-            ruby/ql/lib/codeql/ruby/ast/internal/TreeSitter.qll
-          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-ruby-extractor-${{ hashFiles('ruby/rust-toolchain.toml', 'ruby/**/Cargo.lock') }}--${{ hashFiles('ruby/**/*.rs') }}
+            ruby/extractor/target/release/codeql-extractor-ruby
+            ruby/extractor/target/release/codeql-extractor-ruby.exe
+            ruby/extractor/ql/lib/codeql/ruby/ast/internal/TreeSitter.qll
+          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-ruby-extractor-${{ hashFiles('ruby/extractor/rust-toolchain.toml', 'ruby/extractor/Cargo.lock') }}-${{ hashFiles('shared/tree-sitter-extractor') }}-${{ hashFiles('ruby/extractor/**/*.rs') }}
       - uses: actions/cache@v3
         if: steps.cache-extractor.outputs.cache-hit != 'true'
         with:
@@ -68,22 +69,30 @@ jobs:
             ~/.cargo/registry
             ~/.cargo/git
             ruby/target
-          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-ruby-rust-cargo-${{ hashFiles('ruby/rust-toolchain.toml', 'ruby/**/Cargo.lock') }}
+          key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-ruby-rust-cargo-${{ hashFiles('ruby/extractor/rust-toolchain.toml', 'ruby/extractor/**/Cargo.lock') }}
       - name: Check formatting
         if: steps.cache-extractor.outputs.cache-hit != 'true'
-        run: cargo fmt --all -- --check
+        run: cd extractor && cargo fmt --all -- --check
       - name: Build
         if: steps.cache-extractor.outputs.cache-hit != 'true'
-        run: cargo build --verbose
+        run: cd extractor && cargo build --verbose
       - name: Run tests
         if: steps.cache-extractor.outputs.cache-hit != 'true'
-        run: cargo test --verbose
-      - name: Release build
-        if: steps.cache-extractor.outputs.cache-hit != 'true'
-        run: cargo build --release
+        run: cd extractor && cargo test --verbose
+      # On linux, build the extractor via cross in a centos7 container.
+      # This ensures we don't depend on glibc > 2.17.
+      - name: Release build (linux)
+        if: steps.cache-extractor.outputs.cache-hit != 'true' && runner.os == 'Linux'
+        run: |
+          cd extractor
+          cross build --release
+          mv target/x86_64-unknown-linux-gnu/release/codeql-extractor-ruby target/release/
+      - name: Release build (windows and macos)
+        if: steps.cache-extractor.outputs.cache-hit != 'true' && runner.os != 'Linux'
+        run: cd extractor && cargo build --release
       - name: Generate dbscheme
         if: ${{ matrix.os == 'ubuntu-latest' && steps.cache-extractor.outputs.cache-hit != 'true'}}
-        run: target/release/ruby-generator --dbscheme ql/lib/ruby.dbscheme --library ql/lib/codeql/ruby/ast/internal/TreeSitter.qll
+        run: extractor/target/release/codeql-extractor-ruby generate --dbscheme ql/lib/ruby.dbscheme --library ql/lib/codeql/ruby/ast/internal/TreeSitter.qll
       - uses: actions/upload-artifact@v3
         if: ${{ matrix.os == 'ubuntu-latest' }}
         with:
@@ -98,10 +107,8 @@ jobs:
         with:
           name: extractor-${{ matrix.os }}
           path: |
-            ruby/target/release/ruby-autobuilder
-            ruby/target/release/ruby-autobuilder.exe
-            ruby/target/release/ruby-extractor
-            ruby/target/release/ruby-extractor.exe
+            ruby/extractor/target/release/codeql-extractor-ruby
+            ruby/extractor/target/release/codeql-extractor-ruby.exe
           retention-days: 1
   compile-queries:
     runs-on: ubuntu-latest-xl
@@ -116,21 +123,22 @@ jobs:
           key: ruby-build
       - name: Build Query Pack
         run: |
-          rm -rf target/packs
-          codeql pack create ../misc/suite-helpers --output target/packs
-          codeql pack create ../shared/regex --output target/packs
-          codeql pack create ../shared/ssa --output target/packs
-          codeql pack create ../shared/tutorial --output target/packs
-          codeql pack create ql/lib --output target/packs
-          codeql pack create -j0 ql/src --output target/packs --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"
-          PACK_FOLDER=$(readlink -f target/packs/codeql/ruby-queries/*)
+          PACKS=${{ runner.temp }}/query-packs
+          rm -rf $PACKS
+          codeql pack create ../misc/suite-helpers --output "$PACKS"
+          codeql pack create ../shared/regex --output "$PACKS"
+          codeql pack create ../shared/ssa --output "$PACKS"
+          codeql pack create ../shared/tutorial --output "$PACKS"
+          codeql pack create ql/lib --output "$PACKS"
+          codeql pack create -j0 ql/src --output "$PACKS" --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"
+          PACK_FOLDER=$(readlink -f "$PACKS"/codeql/ruby-queries/*)
           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@v3
         with:
           name: codeql-ruby-queries
           path: |
-            ruby/target/packs/*
+            ${{ runner.temp }}/query-packs/*
           retention-days: 1
 
   package:
@@ -158,13 +166,10 @@ jobs:
           mkdir -p ruby
           cp -r codeql-extractor.yml tools ql/lib/ruby.dbscheme.stats ruby/
           mkdir -p ruby/tools/{linux64,osx64,win64}
-          cp linux64/ruby-autobuilder ruby/tools/linux64/autobuilder
-          cp osx64/ruby-autobuilder ruby/tools/osx64/autobuilder
-          cp win64/ruby-autobuilder.exe ruby/tools/win64/autobuilder.exe
-          cp linux64/ruby-extractor ruby/tools/linux64/extractor
-          cp osx64/ruby-extractor ruby/tools/osx64/extractor
-          cp win64/ruby-extractor.exe ruby/tools/win64/extractor.exe
-          chmod +x ruby/tools/{linux64,osx64}/{autobuilder,extractor}
+          cp linux64/codeql-extractor-ruby ruby/tools/linux64/extractor
+          cp osx64/codeql-extractor-ruby ruby/tools/osx64/extractor
+          cp win64/codeql-extractor-ruby.exe ruby/tools/win64/extractor.exe
+          chmod +x ruby/tools/{linux64,osx64}/extractor
           zip -rq codeql-ruby.zip ruby
       - uses: actions/upload-artifact@v3
         with:
@@ -226,3 +231,54 @@ jobs:
         shell: bash
         run: |
           codeql database analyze --search-path "${{ runner.temp }}/ruby-bundle" --format=sarifv2.1.0 --output=out.sarif ../database ruby-code-scanning.qls
+
+  # This is a copy of the 'test' job that runs in a centos7 container.
+  # This tests that the extractor works correctly on systems with an old glibc.
+  test-centos7:
+    defaults:
+      run:
+        working-directory: ${{ github.workspace }}
+    strategy:
+      fail-fast: false
+    runs-on: ubuntu-latest
+    container:
+      image: centos:centos7
+      env:
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+    needs: [package]
+    steps:
+      - name: Install gh cli
+        run: |
+          yum-config-manager --add-repo https://cli.github.com/packages/rpm/gh-cli.repo
+          # fetch-codeql requires unzip and jq
+          # jq is available in epel-release (https://docs.fedoraproject.org/en-US/epel/)
+          yum install -y gh unzip epel-release
+          yum install -y jq
+      - uses: actions/checkout@v3
+      - name: Fetch CodeQL
+        uses: ./.github/actions/fetch-codeql
+
+      # Due to a bug in Actions, we can't use runner.temp in the run blocks here.
+      # https://github.com/actions/runner/issues/2185
+
+      - name: Download Ruby bundle
+        uses: actions/download-artifact@v3
+        with:
+          name: codeql-ruby-bundle
+          path: ${{ runner.temp }}
+      - name: Unzip Ruby bundle
+        shell: bash
+        run: unzip -q -d "$RUNNER_TEMP"/ruby-bundle "$RUNNER_TEMP"/codeql-ruby-bundle.zip
+
+      - name: Run QL test
+        shell: bash
+        run: |
+          codeql test run --search-path "$RUNNER_TEMP"/ruby-bundle --additional-packs "$RUNNER_TEMP"/ruby-bundle ruby/ql/test/library-tests/ast/constants/
+      - name: Create database
+        shell: bash
+        run: |
+          codeql database create --search-path "$RUNNER_TEMP"/ruby-bundle --language ruby --source-root ruby/ql/test/library-tests/ast/constants/ ../database
+      - name: Analyze database
+        shell: bash
+        run: |
+          codeql database analyze --search-path "$RUNNER_TEMP"/ruby-bundle --format=sarifv2.1.0 --output=out.sarif ../database ruby-code-scanning.qls

.github/workflows/ruby-qltest.yml

@@ -4,6 +4,7 @@ on:
   push:
     paths:
       - "ruby/**"
+      - "shared/**"
       - .github/workflows/ruby-build.yml
       - .github/actions/fetch-codeql/action.yml
       - codeql-workspace.yml
@@ -13,6 +14,7 @@ on:
   pull_request:
     paths:
       - "ruby/**"
+      - "shared/**"
       - .github/workflows/ruby-qltest.yml
       - .github/actions/fetch-codeql/action.yml
       - codeql-workspace.yml

.github/workflows/swift.yml

@@ -5,6 +5,7 @@ on:
     paths:
       - "swift/**"
       - "misc/bazel/**"
+      - "misc/codegen/**"
       - "*.bazel*"
       - .github/workflows/swift.yml
       - .github/actions/**
@@ -15,10 +16,12 @@ on:
     branches:
       - main
       - rc/*
+      - codeql-cli-*
   push:
     paths:
       - "swift/**"
       - "misc/bazel/**"
+      - "misc/codegen/**"
       - "*.bazel*"
       - .github/workflows/swift.yml
       - .github/actions/**
@@ -28,6 +31,7 @@ on:
     branches:
       - main
       - rc/*
+      - codeql-cli-*
 
 jobs:
   # not using a matrix as you cannot depend on a specific job in a matrix, and we want to start linux checks

.github/workflows/sync-files.yml

@@ -17,4 +17,6 @@ jobs:
       - uses: actions/checkout@v3
       - name: Check synchronized files
         run: python config/sync-files.py
+      - name: Check dbscheme fragments
+        run: python config/sync-dbscheme-fragments.py
 

.github/workflows/tree-sitter-extractor-test.yml

@@ -0,0 +1,46 @@
+name: Test tree-sitter-extractor
+
+on:
+  push:
+    paths:
+      - "shared/tree-sitter-extractor/**"
+      - .github/workflows/tree-sitter-extractor-test.yml
+    branches:
+      - main
+      - "rc/*"
+  pull_request:
+    paths:
+      - "shared/tree-sitter-extractor/**"
+      - .github/workflows/tree-sitter-extractor-test.yml
+    branches:
+      - main
+      - "rc/*"
+
+env:
+  CARGO_TERM_COLOR: always
+
+defaults:
+  run:
+    working-directory: shared/tree-sitter-extractor
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Check formatting
+        run: cargo fmt --all -- --check
+      - name: Run tests
+        run: cargo test --verbose
+  fmt:
+    runs-on: ubuntu-latest  
+    steps:
+      - uses: actions/checkout@v3
+      - name: Check formatting
+        run: cargo fmt --check
+  clippy:
+    runs-on: ubuntu-latest  
+    steps:
+      - uses: actions/checkout@v3
+      - name: Run clippy
+        run: cargo clippy -- --no-deps -D warnings -A clippy::new_without_default -A clippy::too_many_arguments

.pre-commit-config.yaml

@@ -5,9 +5,9 @@ repos:
     rev: v3.2.0
     hooks:
       - id: trailing-whitespace
-        exclude: /test/.*$(?<!\.ql)(?<!\.qll)(?<!\.qlref)
+        exclude: /test/.*$(?<!\.ql)(?<!\.qll)(?<!\.qlref)|.*\.patch
       - id: end-of-file-fixer
-        exclude: /test/.*$(?<!\.ql)(?<!\.qll)(?<!\.qlref)
+        exclude: /test/.*$(?<!\.ql)(?<!\.qll)(?<!\.qlref)|.*\.patch
 
   - repo: https://github.com/pre-commit/mirrors-clang-format
     rev: v13.0.1
@@ -19,7 +19,12 @@ repos:
     rev: v1.6.0
     hooks:
       - id: autopep8
-        files: ^swift/.*\.py
+        files: ^misc/codegen/.*\.py
+
+  - repo: https://github.com/warchant/pre-commit-buildifier
+    rev: 0.0.2
+    hooks:
+      - id: buildifier
 
   - repo: local
     hooks:
@@ -53,5 +58,5 @@ repos:
         name: Run Swift code generation unit tests
         files: ^swift/codegen/.*\.py$
         language: system
-        entry: bazel test //swift/codegen/test
+        entry: bazel test //misc/codegen/test
         pass_filenames: false

.vscode/tasks.json

@@ -22,6 +22,22 @@
                 "command": "${config:python.pythonPath}",
             },
             "problemMatcher": []
+        },
+        {
+            "label": "Accept .expected changes from CI",
+            "type": "process",
+            // Non-Windows OS will usually have Python 3 already installed at /usr/bin/python3.
+            "command": "python3",
+            "args": [
+                "misc/scripts/accept-expected-changes-from-ci.py"
+            ],
+            "group": "build",
+            "windows": {
+                // On Windows, use whatever Python interpreter is configured for this workspace. The default is
+                // just `python`, so if Python is already on the path, this will find it.
+                "command": "${config:python.pythonPath}",
+            },
+            "problemMatcher": []
         }
     ]
-}
+}

CODEOWNERS

@@ -6,8 +6,8 @@
 /python/ @github/codeql-python
 /ruby/ @github/codeql-ruby
 /swift/ @github/codeql-swift
+/misc/codegen/ @github/codeql-swift
 /java/kotlin-extractor/ @github/codeql-kotlin
-/java/kotlin-explorer/ @github/codeql-kotlin
 
 # ML-powered queries
 /javascript/ql/experimental/adaptivethreatmodeling/ @github/codeql-ml-powered-queries-reviewers
@@ -39,3 +39,6 @@ WORKSPACE.bazel @github/codeql-ci-reviewers
 /.github/workflows/ql-for-ql-* @github/codeql-ql-for-ql-reviewers
 /.github/workflows/ruby-* @github/codeql-ruby
 /.github/workflows/swift.yml @github/codeql-swift
+
+# Misc
+/misc/scripts/accept-expected-changes-from-ci.py @RasmusWL

CONTRIBUTING.md

@@ -14,14 +14,16 @@ If you have an idea for a query that you would like to share with other CodeQL u
 
 1. **Directory structure**
 
-    There are six language-specific query directories in this repository:
+    There are eight language-specific query directories in this repository:
 
       * C/C++: `cpp/ql/src`
       * C#: `csharp/ql/src`
-      * Java: `java/ql/src`
+      * Go: `go/ql/src`
+      * Java/Kotlin: `java/ql/src`
       * JavaScript: `javascript/ql/src`
       * Python: `python/ql/src`
       * Ruby: `ruby/ql/src`
+      * Swift: `swift/ql/src`
 
     Each language-specific directory contains further subdirectories that group queries based on their `@tags` or purpose.
     - Experimental queries and libraries are stored in the `experimental` subdirectory within each language-specific directory in the [CodeQL repository](https://github.com/github/codeql). For example, experimental Java queries and libraries are stored in `java/ql/src/experimental` and any corresponding tests in `java/ql/test/experimental`.

codeql-workspace.yml

@@ -4,6 +4,8 @@ provide:
   - "*/ql/test/qlpack.yml"
   - "*/ql/examples/qlpack.yml"
   - "*/ql/consistency-queries/qlpack.yml"
+  - "*/ql/automodel/src/qlpack.yml"
+  - "*/ql/automodel/test/qlpack.yml"
   - "shared/*/qlpack.yml"
   - "cpp/ql/test/query-tests/Security/CWE/CWE-190/semmle/tainted/qlpack.yml"
   - "go/ql/config/legacy-support/qlpack.yml"

config/dbscheme-fragments.json

@@ -0,0 +1,33 @@
+{
+  "files": [
+    "javascript/ql/lib/semmlecode.javascript.dbscheme",
+    "python/ql/lib/semmlecode.python.dbscheme",
+    "ruby/ql/lib/ruby.dbscheme",
+    "ql/ql/src/ql.dbscheme"
+  ],
+  "fragments": [
+    "/*- External data -*/",
+    "/*- Files and folders -*/",
+    "/*- Diagnostic messages -*/",
+    "/*- Diagnostic messages: severity -*/",
+    "/*- Source location prefix -*/",
+    "/*- Lines of code -*/",
+    "/*- Configuration files with key value pairs -*/",
+    "/*- YAML -*/",
+    "/*- XML Files -*/",
+    "/*- XML: sourceline -*/",
+    "/*- DEPRECATED: External defects and metrics -*/",
+    "/*- DEPRECATED: Snapshot date -*/",
+    "/*- DEPRECATED: Duplicate code -*/",
+    "/*- DEPRECATED: Version control data -*/",
+    "/*- JavaScript-specific part -*/",
+    "/*- Ruby dbscheme -*/",
+    "/*- Erb dbscheme -*/",
+    "/*- QL dbscheme -*/",
+    "/*- Dbscheme dbscheme -*/",
+    "/*- Yaml dbscheme -*/",
+    "/*- Blame dbscheme -*/",
+    "/*- JSON dbscheme -*/",
+    "/*- Python dbscheme -*/"
+  ]
+}

config/identical-files.json

@@ -1,66 +1,43 @@
 {
-  "DataFlow Java/C++/C#/Go/Python/Ruby/Swift": [
-    "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl.qll",
+  "DataFlow Java/C++/C#/Go/Python/Ruby/Swift Legacy Configuration": [
+    "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl1.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl2.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl3.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl4.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl5.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl6.qll",
-    "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplForSerializability.qll",
-    "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplForOnActivityResult.qll",
-    "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl.qll",
+    "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl1.qll",
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl2.qll",
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl3.qll",
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl4.qll",
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImplLocal.qll",
-    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl.qll",
+    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl1.qll",
     "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl2.qll",
     "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl3.qll",
     "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl4.qll",
-    "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl.qll",
-    "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl2.qll",
-    "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl3.qll",
-    "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl4.qll",
-    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl.qll",
+    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl1.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl2.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl3.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl4.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl5.qll",
-    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImplForContentDataFlow.qll",
-    "go/ql/lib/semmle/go/dataflow/internal/DataFlowImpl.qll",
+    "go/ql/lib/semmle/go/dataflow/internal/DataFlowImpl1.qll",
     "go/ql/lib/semmle/go/dataflow/internal/DataFlowImpl2.qll",
-    "go/ql/lib/semmle/go/dataflow/internal/DataFlowImplForStringsNewReplacer.qll",
-    "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl.qll",
+    "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl1.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl2.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl3.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl4.qll",
-    "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImplForRegExp.qll",
-    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImpl.qll",
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImpl1.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImpl2.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplForHttpClientLibraries.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplForPathname.qll",
-    "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImpl.qll"
+    "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImpl1.qll"
   ],
-  "DataFlow Java/C++/C#/Go/Python/Ruby/Swift Common": [
-    "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplCommon.qll",
-    "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImplCommon.qll",
-    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImplCommon.qll",
-    "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImplCommon.qll",
-    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImplCommon.qll",
-    "go/ql/lib/semmle/go/dataflow/internal/DataFlowImplCommon.qll",
-    "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImplCommon.qll",
-    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplCommon.qll",
-    "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImplCommon.qll"
-  ],
-  "TaintTracking::Configuration Java/C++/C#/Go/Python/Ruby/Swift": [
+  "TaintTracking Legacy Configuration Java/C++/C#/Go/Python/Ruby/Swift": [
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking2/TaintTrackingImpl.qll",
     "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
     "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/tainttracking2/TaintTrackingImpl.qll",
     "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/tainttracking3/TaintTrackingImpl.qll",
-    "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
-    "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/tainttracking2/TaintTrackingImpl.qll",
-    "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/tainttracking3/TaintTrackingImpl.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/tainttracking2/TaintTrackingImpl.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/tainttracking3/TaintTrackingImpl.qll",
@@ -78,16 +55,6 @@
     "ruby/ql/lib/codeql/ruby/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
     "swift/ql/lib/codeql/swift/dataflow/internal/tainttracking1/TaintTrackingImpl.qll"
   ],
-  "DataFlow Java/C++/C#/Python/Ruby/Swift Consistency checks": [
-    "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplConsistency.qll",
-    "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImplConsistency.qll",
-    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImplConsistency.qll",
-    "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImplConsistency.qll",
-    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImplConsistency.qll",
-    "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImplConsistency.qll",
-    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplConsistency.qll",
-    "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImplConsistency.qll"
-  ],
   "DataFlow Java/C#/Go/Ruby/Python/Swift Flow Summaries": [
     "java/ql/lib/semmle/code/java/dataflow/internal/FlowSummaryImpl.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/FlowSummaryImpl.qll",
@@ -104,6 +71,10 @@
     "java/ql/src/utils/modelgenerator/internal/CaptureModels.qll",
     "csharp/ql/src/utils/modelgenerator/internal/CaptureModels.qll"
   ],
+  "Model as Data Generation Java/C# - CaptureModelsPrinting": [
+    "java/ql/src/utils/modelgenerator/internal/CaptureModelsPrinting.qll",
+    "csharp/ql/src/utils/modelgenerator/internal/CaptureModelsPrinting.qll"
+  ],
   "Sign Java/C#": [
     "java/ql/lib/semmle/code/java/dataflow/internal/rangeanalysis/Sign.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/rangeanalysis/Sign.qll"
@@ -260,6 +231,11 @@
     "cpp/ql/lib/semmle/code/cpp/ir/implementation/unaliased_ssa/internal/IRBlockImports.qll",
     "cpp/ql/lib/semmle/code/cpp/ir/implementation/aliased_ssa/internal/IRBlockImports.qll"
   ],
+  "C++ IR IRConsistencyImports": [
+    "cpp/ql/lib/semmle/code/cpp/ir/implementation/raw/internal/IRConsistencyImports.qll",
+    "cpp/ql/lib/semmle/code/cpp/ir/implementation/unaliased_ssa/internal/IRConsistencyImports.qll",
+    "cpp/ql/lib/semmle/code/cpp/ir/implementation/aliased_ssa/internal/IRConsistencyImports.qll"
+  ],
   "C++ IR IRFunctionImports": [
     "cpp/ql/lib/semmle/code/cpp/ir/implementation/raw/internal/IRFunctionImports.qll",
     "cpp/ql/lib/semmle/code/cpp/ir/implementation/unaliased_ssa/internal/IRFunctionImports.qll",
@@ -485,17 +461,17 @@
   "SensitiveDataHeuristics Python/JS": [
     "javascript/ql/lib/semmle/javascript/security/internal/SensitiveDataHeuristics.qll",
     "python/ql/lib/semmle/python/security/internal/SensitiveDataHeuristics.qll",
-    "ruby/ql/lib/codeql/ruby/security/internal/SensitiveDataHeuristics.qll"
-  ],
-  "CFG": [
-    "csharp/ql/lib/semmle/code/csharp/controlflow/internal/ControlFlowGraphImplShared.qll",
-    "ruby/ql/lib/codeql/ruby/controlflow/internal/ControlFlowGraphImplShared.qll",
-    "swift/ql/lib/codeql/swift/controlflow/internal/ControlFlowGraphImplShared.qll"
+    "ruby/ql/lib/codeql/ruby/security/internal/SensitiveDataHeuristics.qll",
+    "swift/ql/lib/codeql/swift/security/internal/SensitiveDataHeuristics.qll"
   ],
   "TypeTracker": [
     "python/ql/lib/semmle/python/dataflow/new/internal/TypeTracker.qll",
     "ruby/ql/lib/codeql/ruby/typetracking/TypeTracker.qll"
   ],
+  "SummaryTypeTracker": [
+    "python/ql/lib/semmle/python/dataflow/new/internal/SummaryTypeTracker.qll",
+    "ruby/ql/lib/codeql/ruby/typetracking/internal/SummaryTypeTracker.qll"
+  ],
   "AccessPathSyntax": [
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/AccessPathSyntax.qll",
     "go/ql/lib/semmle/go/dataflow/internal/AccessPathSyntax.qll",
@@ -571,5 +547,9 @@
   "EncryptionKeySizes Python/Java": [
     "python/ql/lib/semmle/python/security/internal/EncryptionKeySizes.qll",
     "java/ql/lib/semmle/code/java/security/internal/EncryptionKeySizes.qll"
+  ],
+  "Python model summaries test extension": [
+    "python/ql/test/experimental/dataflow/model-summaries/InlineTaintTest.ext.yml",
+    "python/ql/test/experimental/dataflow/model-summaries/NormalDataflowTest.ext.yml"
   ]
-}
+}

config/sync-dbscheme-fragments.py

@@ -0,0 +1,86 @@
+#!/usr/bin/env python3
+
+import argparse
+import json
+import os
+import pathlib
+import re
+
+
+def make_groups(blocks):
+    groups = {}
+    for block in blocks:
+        groups.setdefault("".join(block["lines"]), []).append(block)
+    return list(groups.values())
+
+
+def validate_fragments(fragments):
+    ok = True
+    for header, blocks in fragments.items():
+        groups = make_groups(blocks)
+        if len(groups) > 1:
+            ok = False
+            print("Warning: dbscheme fragments with header '{}' are different for {}".format(header, ["{}:{}:{}".format(
+                group[0]["file"], group[0]["start"], group[0]["end"]) for group in groups]))
+    return ok
+
+
+def main():
+    script_path = os.path.realpath(__file__)
+    script_dir = os.path.dirname(script_path)
+    parser = argparse.ArgumentParser(
+        prog=os.path.basename(script_path),
+        description='Sync dbscheme fragments across files.'
+    )
+    parser.add_argument('files', metavar='dbscheme_file', type=pathlib.Path, nargs='*', default=[],
+                        help='dbscheme files to check')
+    args = parser.parse_args()
+
+    with open(os.path.join(script_dir, "dbscheme-fragments.json"), "r") as f:
+        config = json.load(f)
+
+    fragment_headers = set(config["fragments"])
+    fragments = {}
+    ok = True
+    for file in args.files + config["files"]:
+        with open(os.path.join(os.path.dirname(script_dir), file), "r") as dbscheme:
+            header = None
+            line_number = 1
+            block = {"file": file, "start": line_number,
+                     "end": None, "lines": []}
+
+            def end_block():
+                block["end"] = line_number - 1
+                if len(block["lines"]) > 0:
+                    if header is None:
+                        if re.match(r'(?m)\A(\s|//.*$|/\*(\**[^\*])*\*+/)*\Z', "".join(block["lines"])):
+                            # Ignore comments at the beginning of the file
+                            pass
+                        else:
+                            ok = False
+                            print("Warning: dbscheme fragment without header: {}:{}:{}".format(
+                                block["file"], block["start"], block["end"]))
+                    else:
+                        fragments.setdefault(header, []).append(block)
+            for line in dbscheme:
+                m = re.match(r"^\/\*-.*-\*\/$", line)
+                if m:
+                    end_block()
+                    header = line.strip()
+                    if header not in fragment_headers:
+                        ok = False
+                        print("Warning: unknown header for dbscheme fragment: '{}': {}:{}".format(
+                            header, file, line_number))
+                    block = {"file": file, "start": line_number,
+                             "end": None, "lines": []}
+                block["lines"].append(line)
+                line_number += 1
+            block["lines"].append('\n')
+            line_number += 1
+            end_block()
+    if not ok or not validate_fragments(fragments):
+        exit(1)
+
+
+if __name__ == "__main__":
+    main()

cpp/autobuilder/Semmle.Autobuild.Cpp.Tests/BuildScripts.cs

@@ -1,5 +1,6 @@
 using Xunit;
 using Semmle.Autobuild.Shared;
+using Semmle.Util;
 using System.Collections.Generic;
 using System;
 using System.Linq;
@@ -75,6 +76,15 @@ namespace Semmle.Autobuild.Cpp.Tests
             throw new ArgumentException("Missing RunProcess " + pattern);
         }
 
+        int IBuildActions.RunProcess(string cmd, string args, string? workingDirectory, IDictionary<string, string>? env, BuildOutputHandler onOutput, BuildOutputHandler onError)
+        {
+            var ret = (this as IBuildActions).RunProcess(cmd, args, workingDirectory, env, out var stdout);
+
+            stdout.ForEach(line => onOutput(line));
+
+            return ret;
+        }
+
         public IList<string> DirectoryDeleteIn = new List<string>();
 
         void IBuildActions.DirectoryDelete(string dir, bool recursive)
@@ -131,6 +141,14 @@ namespace Semmle.Autobuild.Cpp.Tests
 
         bool IBuildActions.IsWindows() => IsWindows;
 
+        public bool IsMacOs { get; set; }
+
+        bool IBuildActions.IsMacOs() => IsMacOs;
+
+        public bool IsArm { get; set; }
+
+        bool IBuildActions.IsArm() => IsArm;
+
         string IBuildActions.PathCombine(params string[] parts)
         {
             return string.Join(IsWindows ? '\\' : '/', parts.Where(p => !string.IsNullOrWhiteSpace(p)));
@@ -176,6 +194,15 @@ namespace Semmle.Autobuild.Cpp.Tests
             if (!DownloadFiles.Contains((address, fileName)))
                 throw new ArgumentException($"Missing DownloadFile, {address}, {fileName}");
         }
+
+        public IDiagnosticsWriter CreateDiagnosticsWriter(string filename) => new TestDiagnosticWriter();
+    }
+
+    internal class TestDiagnosticWriter : IDiagnosticsWriter
+    {
+        public IList<DiagnosticMessage> Diagnostics { get; } = new List<DiagnosticMessage>();
+
+        public void AddEntry(DiagnosticMessage message) => this.Diagnostics.Add(message);
     }
 
     /// <summary>
@@ -235,6 +262,7 @@ namespace Semmle.Autobuild.Cpp.Tests
             Actions.GetEnvironmentVariable[$"CODEQL_EXTRACTOR_{codeqlUpperLanguage}_TRAP_DIR"] = "";
             Actions.GetEnvironmentVariable[$"CODEQL_EXTRACTOR_{codeqlUpperLanguage}_SOURCE_ARCHIVE_DIR"] = "";
             Actions.GetEnvironmentVariable[$"CODEQL_EXTRACTOR_{codeqlUpperLanguage}_ROOT"] = $@"C:\codeql\{codeqlUpperLanguage.ToLowerInvariant()}";
+            Actions.GetEnvironmentVariable[$"CODEQL_EXTRACTOR_{codeqlUpperLanguage}_DIAGNOSTIC_DIR"] = "";
             Actions.GetEnvironmentVariable["CODEQL_JAVA_HOME"] = @"C:\codeql\tools\java";
             Actions.GetEnvironmentVariable["CODEQL_PLATFORM"] = "win64";
             Actions.GetEnvironmentVariable["SEMMLE_DIST"] = @"C:\odasa";
@@ -299,7 +327,7 @@ namespace Semmle.Autobuild.Cpp.Tests
         {
             Actions.RunProcess[@"cmd.exe /C nuget restore C:\Project\test.sln -DisableParallelProcessing"] = 1;
             Actions.RunProcess[@"cmd.exe /C C:\Project\.nuget\nuget.exe restore C:\Project\test.sln -DisableParallelProcessing"] = 0;
-            Actions.RunProcess[@"cmd.exe /C CALL ^""C:\Program Files ^(x86^)\Microsoft Visual Studio 14.0\VC\vcvarsall.bat^"" && set Platform=&& type NUL && msbuild C:\Project\test.sln /t:rebuild /p:Platform=""x86"" /p:Configuration=""Release"""] = 0;
+            Actions.RunProcess[@"cmd.exe /C CALL ^""C:\Program^ Files^ ^(x86^)\Microsoft^ Visual^ Studio^ 14.0\VC\vcvarsall.bat^"" && set Platform=&& type NUL && msbuild C:\Project\test.sln /t:rebuild /p:Platform=""x86"" /p:Configuration=""Release"""] = 0;
             Actions.RunProcessOut[@"C:\Program Files (x86)\Microsoft Visual Studio\Installer\vswhere.exe -prerelease -legacy -property installationPath"] = "";
             Actions.RunProcess[@"C:\Program Files (x86)\Microsoft Visual Studio\Installer\vswhere.exe -prerelease -legacy -property installationPath"] = 1;
             Actions.RunProcess[@"C:\Program Files (x86)\Microsoft Visual Studio\Installer\vswhere.exe -prerelease -legacy -property installationVersion"] = 0;

cpp/autobuilder/Semmle.Autobuild.Cpp/CppAutobuilder.cs

@@ -1,4 +1,5 @@
 using Semmle.Autobuild.Shared;
+using Semmle.Util;
 
 namespace Semmle.Autobuild.Cpp
 {
@@ -21,7 +22,7 @@ namespace Semmle.Autobuild.Cpp
 
     public class CppAutobuilder : Autobuilder<CppAutobuildOptions>
     {
-        public CppAutobuilder(IBuildActions actions, CppAutobuildOptions options) : base(actions, options) { }
+        public CppAutobuilder(IBuildActions actions, CppAutobuildOptions options) : base(actions, options, new DiagnosticClassifier()) { }
 
         public override BuildScript GetBuildScript()
         {

cpp/downgrades/19887dbd33327fb07d54251786e0cb2578539775/upgrade.properties

@@ -0,0 +1,4 @@
+description: Revert support for repeated initializers, which are allowed in C with designated initializers.
+compatibility: full
+aggregate_field_init.rel: reorder aggregate_field_init.rel (int aggregate, int initializer, int field, int position) aggregate initializer field
+aggregate_array_init.rel: reorder aggregate_array_init.rel (int aggregate, int initializer, int element_index, int position) aggregate initializer element_index

cpp/downgrades/d77c09d8bdc172c9201dec293de1e14c931d3f05/upgrade.properties

@@ -0,0 +1,2 @@
+description: Remove _Float128 type
+compatibility: full

cpp/downgrades/qlpack.yml

@@ -2,3 +2,4 @@ name: codeql/cpp-downgrades
 groups: cpp
 downgrades: .
 library: true
+warnOnImplicitThis: true

cpp/ql/examples/qlpack.yml

@@ -4,3 +4,4 @@ groups:
   - examples
 dependencies:
   codeql/cpp-all: ${workspace}
+warnOnImplicitThis: true

cpp/ql/examples/queries.xml

@@ -1 +0,0 @@
-<queries language="cpp"/>

cpp/ql/lib/CHANGELOG.md

@@ -1,3 +1,176 @@
+## 0.9.2
+
+### Deprecated APIs
+
+* `getAllocatorCall` on `DeleteExpr` and `DeleteArrayExpr` has been deprecated. `getDeallocatorCall` should be used instead.
+
+### New Features
+
+* Added `DeleteOrDeleteArrayExpr` as a super type of `DeleteExpr` and `DeleteArrayExpr`
+
+### Minor Analysis Improvements
+
+* `delete` and `delete[]` are now modeled as calls to the relevant `operator delete` in the IR. In the case of a dynamic delete call a new instruction `VirtualDeleteFunctionAddress` is used to represent a function that dispatches to the correct delete implementation.
+* Only the 2 level indirection of `argv` (corresponding to `**argv`) is consided for `FlowSource`.
+
+## 0.9.1
+
+No user-facing changes.
+
+## 0.9.0
+
+### Breaking Changes
+
+* The `shouldPrintFunction` predicate from `PrintAstConfiguration` has been replaced by `shouldPrintDeclaration`. Users should now override `shouldPrintDeclaration` if they want to limit the declarations that should be printed.
+* The `shouldPrintFunction` predicate from `PrintIRConfiguration` has been replaced by `shouldPrintDeclaration`. Users should now override `shouldPrintDeclaration` if they want to limit the declarations that should be printed.
+
+### Major Analysis Improvements
+
+* The `PrintAST` library now also prints global and namespace variables and their initializers.
+
+### Minor Analysis Improvements
+
+* The `_Float128x` type is no longer exposed as a builtin type. As this type could not occur any code base, this should only affect queries that explicitly looked at the builtin types.
+
+## 0.8.1
+
+### Deprecated APIs
+
+* The library `semmle.code.cpp.dataflow.DataFlow` has been deprecated. Please use `semmle.code.cpp.dataflow.new.DataFlow` instead.
+
+### New Features
+
+* The `DataFlow::StateConfigSig` signature module has gained default implementations for `isBarrier/2` and `isAdditionalFlowStep/4`. 
+  Hence it is no longer needed to provide `none()` implementations of these predicates if they are not needed.
+
+### Minor Analysis Improvements
+
+* Data flow configurations can now include a predicate `neverSkip(Node node)`
+  in order to ensure inclusion of certain nodes in the path explanations. The
+  predicate defaults to the end-points of the additional flow steps provided in
+  the configuration, which means that such steps now always are visible by
+  default in path explanations.
+* The `IRGuards` library has improved handling of pointer addition and subtraction operations.
+
+## 0.8.0
+
+### New Features
+
+* The `ProductFlow::StateConfigSig` signature now includes default predicates for `isBarrier1`, `isBarrier2`, `isAdditionalFlowStep1`, and `isAdditionalFlowStep1`. Hence, it is no longer needed to provide `none()` implementations of these predicates if they are not needed.
+
+### Minor Analysis Improvements
+
+* Deleted the deprecated `getURL` predicate from the `Container`, `Folder`, and `File` classes. Use the `getLocation` predicate instead.
+
+## 0.7.4
+
+No user-facing changes.
+
+## 0.7.3
+
+### Minor Analysis Improvements
+
+* Deleted the deprecated `hasCopyConstructor` predicate from the `Class` class in `Class.qll`.
+* Deleted many deprecated predicates and classes with uppercase `AST`, `SSA`, `CFG`, `API`, etc. in their names. Use the PascalCased versions instead.
+* Deleted the deprecated `CodeDuplication.qll` file.
+
+## 0.7.2
+
+### New Features
+
+* Added an AST-based interface (`semmle.code.cpp.rangeanalysis.new.RangeAnalysis`) for the relative range analysis library.
+* A new predicate `BarrierGuard::getAnIndirectBarrierNode` has been added to the new dataflow library (`semmle.code.cpp.dataflow.new.DataFlow`) to mark indirect expressions as barrier nodes using the `BarrierGuard` API.
+
+### Major Analysis Improvements
+
+* In the intermediate representation, handling of control flow after non-returning calls has been improved. This should remove false positives in queries that use the intermedite representation or libraries based on it, including the new data flow library.
+
+### Minor Analysis Improvements
+
+* The `StdNamespace` class now also includes all inline namespaces that are children of `std` namespace.
+* The new dataflow (`semmle.code.cpp.dataflow.new.DataFlow`) and taint-tracking libraries (`semmle.code.cpp.dataflow.new.TaintTracking`) now support tracking flow through static local variables.
+
+## 0.7.1
+
+No user-facing changes.
+
+## 0.7.0
+
+### Breaking Changes
+
+* The internal `SsaConsistency` module has been moved from `SSAConstruction` to `SSAConsitency`, and the deprecated `SSAConsistency` module has been removed.
+
+### Deprecated APIs
+
+* The single-parameter predicates `ArrayOrVectorAggregateLiteral.getElementExpr` and `ClassAggregateLiteral.getFieldExpr` have been deprecated in favor of `ArrayOrVectorAggregateLiteral.getAnElementExpr` and `ClassAggregateLiteral.getAFieldExpr`.
+* The recently introduced new data flow and taint tracking APIs have had a
+  number of module and predicate renamings. The old APIs remain in place for
+  now.
+* The `SslContextCallAbstractConfig`, `SslContextCallConfig`, `SslContextCallBannedProtocolConfig`, `SslContextCallTls12ProtocolConfig`, `SslContextCallTls13ProtocolConfig`, `SslContextCallTlsProtocolConfig`, `SslContextFlowsToSetOptionConfig`, `SslOptionConfig` dataflow configurations from `BoostorgAsio` have been deprecated. Please use `SslContextCallConfigSig`, `SslContextCallGlobal`, `SslContextCallFlow`, `SslContextCallBannedProtocolFlow`, `SslContextCallTls12ProtocolFlow`, `SslContextCallTls13ProtocolFlow`, `SslContextCallTlsProtocolFlow`, `SslContextFlowsToSetOptionFlow`.
+
+### New Features
+
+* Added overridable predicates `getSizeExpr` and `getSizeMult` to the `BufferAccess` class (`semmle.code.cpp.security.BufferAccess.qll`). This makes it possible to model a larger class of buffer reads and writes using the library.
+
+### Minor Analysis Improvements
+
+* The `BufferAccess` library (`semmle.code.cpp.security.BufferAccess`) no longer matches buffer accesses inside unevaluated contexts (such as inside `sizeof` or `decltype` expressions). As a result, queries using this library may see fewer false positives.
+
+### Bug Fixes
+
+* Fixed some accidental predicate visibility in the backwards-compatible wrapper for data flow configurations. In particular `DataFlow::hasFlowPath`, `DataFlow::hasFlow`, `DataFlow::hasFlowTo`, and `DataFlow::hasFlowToExpr` were accidentally exposed in a single version.
+
+## 0.6.1
+
+No user-facing changes.
+
+## 0.6.0
+
+### Breaking Changes
+
+* The `semmle.code.cpp.commons.Buffer` and `semmle.code.cpp.commons.NullTermination` libraries no longer expose `semmle.code.cpp.dataflow.DataFlow`. Please import `semmle.code.cpp.dataflow.DataFlow` directly.
+
+### Deprecated APIs
+
+* The `WriteConfig` taint tracking configuration has been deprecated. Please use `WriteFlow`.
+
+### New Features
+
+* Added support for merging two `PathGraph`s via disjoint union to allow results from multiple data flow computations in a single `path-problem` query.
+
+### Major Analysis Improvements
+
+* A new C/C++ dataflow library (`semmle.code.cpp.dataflow.new.DataFlow`) has been added.
+  The new library behaves much more like the dataflow library of other CodeQL supported
+  languages by following use-use dataflow paths instead of def-use dataflow paths.
+  The new library also better supports dataflow through indirections, and new predicates
+  such as `Node::asIndirectExpr` have been added to facilitate working with indirections.
+
+  The `semmle.code.cpp.ir.dataflow.DataFlow` library is now identical to the new
+  `semmle.code.cpp.dataflow.new.DataFlow` library.
+* The main data flow and taint tracking APIs have been changed. The old APIs
+  remain in place for now and translate to the new through a
+  backwards-compatible wrapper. If multiple configurations are in scope
+  simultaneously, then this may affect results slightly. The new API is quite
+  similar to the old, but makes use of a configuration module instead of a
+  configuration class.
+
+### Minor Analysis Improvements
+
+* Deleted the deprecated `hasGeneratedCopyConstructor` and `hasGeneratedCopyAssignmentOperator` predicates from the `Folder` class.
+* Deleted the deprecated `getPath` and `getFolder` predicates from the `XmlFile` class.
+* Deleted the deprecated `getMustlockFunction`, `getTrylockFunction`, `getLockFunction`, and `getUnlockFunction` predicates from the `MutexType` class.
+* Deleted the deprecated `getPosInBasicBlock` predicate from the `SubBasicBlock` class.
+* Deleted the deprecated `getExpr` predicate from the `PointerDereferenceExpr` class.
+* Deleted the deprecated `getUseInstruction` and `getDefinitionInstruction` predicates from the `Operand` class.
+* Deleted the deprecated `isInParameter`, `isInParameterPointer`, and `isInQualifier` predicates from the `FunctionInput` class.
+* Deleted the deprecated `isOutParameterPointer`, `isOutQualifier`, `isOutReturnValue`, and `isOutReturnPointer` predicate from the `FunctionOutput` class.
+* Deleted the deprecated 3-argument `isGuardPhi` predicate from the `RangeSsaDefinition` class.
+
+## 0.5.4
+
+No user-facing changes.
+
 ## 0.5.3
 
 No user-facing changes.

cpp/ql/lib/change-notes/released/0.5.4.md

@@ -0,0 +1,3 @@
+## 0.5.4
+
+No user-facing changes.

cpp/ql/lib/change-notes/released/0.6.0.md

@@ -0,0 +1,42 @@
+## 0.6.0
+
+### Breaking Changes
+
+* The `semmle.code.cpp.commons.Buffer` and `semmle.code.cpp.commons.NullTermination` libraries no longer expose `semmle.code.cpp.dataflow.DataFlow`. Please import `semmle.code.cpp.dataflow.DataFlow` directly.
+
+### Deprecated APIs
+
+* The `WriteConfig` taint tracking configuration has been deprecated. Please use `WriteFlow`.
+
+### New Features
+
+* Added support for merging two `PathGraph`s via disjoint union to allow results from multiple data flow computations in a single `path-problem` query.
+
+### Major Analysis Improvements
+
+* A new C/C++ dataflow library (`semmle.code.cpp.dataflow.new.DataFlow`) has been added.
+  The new library behaves much more like the dataflow library of other CodeQL supported
+  languages by following use-use dataflow paths instead of def-use dataflow paths.
+  The new library also better supports dataflow through indirections, and new predicates
+  such as `Node::asIndirectExpr` have been added to facilitate working with indirections.
+
+  The `semmle.code.cpp.ir.dataflow.DataFlow` library is now identical to the new
+  `semmle.code.cpp.dataflow.new.DataFlow` library.
+* The main data flow and taint tracking APIs have been changed. The old APIs
+  remain in place for now and translate to the new through a
+  backwards-compatible wrapper. If multiple configurations are in scope
+  simultaneously, then this may affect results slightly. The new API is quite
+  similar to the old, but makes use of a configuration module instead of a
+  configuration class.
+
+### Minor Analysis Improvements
+
+* Deleted the deprecated `hasGeneratedCopyConstructor` and `hasGeneratedCopyAssignmentOperator` predicates from the `Folder` class.
+* Deleted the deprecated `getPath` and `getFolder` predicates from the `XmlFile` class.
+* Deleted the deprecated `getMustlockFunction`, `getTrylockFunction`, `getLockFunction`, and `getUnlockFunction` predicates from the `MutexType` class.
+* Deleted the deprecated `getPosInBasicBlock` predicate from the `SubBasicBlock` class.
+* Deleted the deprecated `getExpr` predicate from the `PointerDereferenceExpr` class.
+* Deleted the deprecated `getUseInstruction` and `getDefinitionInstruction` predicates from the `Operand` class.
+* Deleted the deprecated `isInParameter`, `isInParameterPointer`, and `isInQualifier` predicates from the `FunctionInput` class.
+* Deleted the deprecated `isOutParameterPointer`, `isOutQualifier`, `isOutReturnValue`, and `isOutReturnPointer` predicate from the `FunctionOutput` class.
+* Deleted the deprecated 3-argument `isGuardPhi` predicate from the `RangeSsaDefinition` class.

cpp/ql/lib/change-notes/released/0.6.1.md

@@ -0,0 +1,3 @@
+## 0.6.1
+
+No user-facing changes.

cpp/ql/lib/change-notes/released/0.7.0.md

@@ -0,0 +1,25 @@
+## 0.7.0
+
+### Breaking Changes
+
+* The internal `SsaConsistency` module has been moved from `SSAConstruction` to `SSAConsitency`, and the deprecated `SSAConsistency` module has been removed.
+
+### Deprecated APIs
+
+* The single-parameter predicates `ArrayOrVectorAggregateLiteral.getElementExpr` and `ClassAggregateLiteral.getFieldExpr` have been deprecated in favor of `ArrayOrVectorAggregateLiteral.getAnElementExpr` and `ClassAggregateLiteral.getAFieldExpr`.
+* The recently introduced new data flow and taint tracking APIs have had a
+  number of module and predicate renamings. The old APIs remain in place for
+  now.
+* The `SslContextCallAbstractConfig`, `SslContextCallConfig`, `SslContextCallBannedProtocolConfig`, `SslContextCallTls12ProtocolConfig`, `SslContextCallTls13ProtocolConfig`, `SslContextCallTlsProtocolConfig`, `SslContextFlowsToSetOptionConfig`, `SslOptionConfig` dataflow configurations from `BoostorgAsio` have been deprecated. Please use `SslContextCallConfigSig`, `SslContextCallGlobal`, `SslContextCallFlow`, `SslContextCallBannedProtocolFlow`, `SslContextCallTls12ProtocolFlow`, `SslContextCallTls13ProtocolFlow`, `SslContextCallTlsProtocolFlow`, `SslContextFlowsToSetOptionFlow`.
+
+### New Features
+
+* Added overridable predicates `getSizeExpr` and `getSizeMult` to the `BufferAccess` class (`semmle.code.cpp.security.BufferAccess.qll`). This makes it possible to model a larger class of buffer reads and writes using the library.
+
+### Minor Analysis Improvements
+
+* The `BufferAccess` library (`semmle.code.cpp.security.BufferAccess`) no longer matches buffer accesses inside unevaluated contexts (such as inside `sizeof` or `decltype` expressions). As a result, queries using this library may see fewer false positives.
+
+### Bug Fixes
+
+* Fixed some accidental predicate visibility in the backwards-compatible wrapper for data flow configurations. In particular `DataFlow::hasFlowPath`, `DataFlow::hasFlow`, `DataFlow::hasFlowTo`, and `DataFlow::hasFlowToExpr` were accidentally exposed in a single version.

cpp/ql/lib/change-notes/released/0.7.1.md

@@ -0,0 +1,3 @@
+## 0.7.1
+
+No user-facing changes.

cpp/ql/lib/change-notes/released/0.7.2.md

@@ -0,0 +1,15 @@
+## 0.7.2
+
+### New Features
+
+* Added an AST-based interface (`semmle.code.cpp.rangeanalysis.new.RangeAnalysis`) for the relative range analysis library.
+* A new predicate `BarrierGuard::getAnIndirectBarrierNode` has been added to the new dataflow library (`semmle.code.cpp.dataflow.new.DataFlow`) to mark indirect expressions as barrier nodes using the `BarrierGuard` API.
+
+### Major Analysis Improvements
+
+* In the intermediate representation, handling of control flow after non-returning calls has been improved. This should remove false positives in queries that use the intermedite representation or libraries based on it, including the new data flow library.
+
+### Minor Analysis Improvements
+
+* The `StdNamespace` class now also includes all inline namespaces that are children of `std` namespace.
+* The new dataflow (`semmle.code.cpp.dataflow.new.DataFlow`) and taint-tracking libraries (`semmle.code.cpp.dataflow.new.TaintTracking`) now support tracking flow through static local variables.

cpp/ql/lib/change-notes/released/0.7.3.md

@@ -0,0 +1,7 @@
+## 0.7.3
+
+### Minor Analysis Improvements
+
+* Deleted the deprecated `hasCopyConstructor` predicate from the `Class` class in `Class.qll`.
+* Deleted many deprecated predicates and classes with uppercase `AST`, `SSA`, `CFG`, `API`, etc. in their names. Use the PascalCased versions instead.
+* Deleted the deprecated `CodeDuplication.qll` file.

cpp/ql/lib/change-notes/released/0.7.4.md

@@ -0,0 +1,3 @@
+## 0.7.4
+
+No user-facing changes.

cpp/ql/lib/change-notes/released/0.8.0.md

@@ -0,0 +1,9 @@
+## 0.8.0
+
+### New Features
+
+* The `ProductFlow::StateConfigSig` signature now includes default predicates for `isBarrier1`, `isBarrier2`, `isAdditionalFlowStep1`, and `isAdditionalFlowStep1`. Hence, it is no longer needed to provide `none()` implementations of these predicates if they are not needed.
+
+### Minor Analysis Improvements
+
+* Deleted the deprecated `getURL` predicate from the `Container`, `Folder`, and `File` classes. Use the `getLocation` predicate instead.

cpp/ql/lib/change-notes/released/0.8.1.md

@@ -0,0 +1,19 @@
+## 0.8.1
+
+### Deprecated APIs
+
+* The library `semmle.code.cpp.dataflow.DataFlow` has been deprecated. Please use `semmle.code.cpp.dataflow.new.DataFlow` instead.
+
+### New Features
+
+* The `DataFlow::StateConfigSig` signature module has gained default implementations for `isBarrier/2` and `isAdditionalFlowStep/4`. 
+  Hence it is no longer needed to provide `none()` implementations of these predicates if they are not needed.
+
+### Minor Analysis Improvements
+
+* Data flow configurations can now include a predicate `neverSkip(Node node)`
+  in order to ensure inclusion of certain nodes in the path explanations. The
+  predicate defaults to the end-points of the additional flow steps provided in
+  the configuration, which means that such steps now always are visible by
+  default in path explanations.
+* The `IRGuards` library has improved handling of pointer addition and subtraction operations.

cpp/ql/lib/change-notes/released/0.9.0.md

@@ -0,0 +1,14 @@
+## 0.9.0
+
+### Breaking Changes
+
+* The `shouldPrintFunction` predicate from `PrintAstConfiguration` has been replaced by `shouldPrintDeclaration`. Users should now override `shouldPrintDeclaration` if they want to limit the declarations that should be printed.
+* The `shouldPrintFunction` predicate from `PrintIRConfiguration` has been replaced by `shouldPrintDeclaration`. Users should now override `shouldPrintDeclaration` if they want to limit the declarations that should be printed.
+
+### Major Analysis Improvements
+
+* The `PrintAST` library now also prints global and namespace variables and their initializers.
+
+### Minor Analysis Improvements
+
+* The `_Float128x` type is no longer exposed as a builtin type. As this type could not occur any code base, this should only affect queries that explicitly looked at the builtin types.

cpp/ql/lib/change-notes/released/0.9.1.md

@@ -0,0 +1,3 @@
+## 0.9.1
+
+No user-facing changes.

cpp/ql/lib/change-notes/released/0.9.2.md

@@ -0,0 +1,14 @@
+## 0.9.2
+
+### Deprecated APIs
+
+* `getAllocatorCall` on `DeleteExpr` and `DeleteArrayExpr` has been deprecated. `getDeallocatorCall` should be used instead.
+
+### New Features
+
+* Added `DeleteOrDeleteArrayExpr` as a super type of `DeleteExpr` and `DeleteArrayExpr`
+
+### Minor Analysis Improvements
+
+* `delete` and `delete[]` are now modeled as calls to the relevant `operator delete` in the IR. In the case of a dynamic delete call a new instruction `VirtualDeleteFunctionAddress` is used to represent a function that dispatches to the correct delete implementation.
+* Only the 2 level indirection of `argv` (corresponding to `**argv`) is consided for `FlowSource`.

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

@@ -1,2 +1,2 @@
 ---
-lastReleaseVersion: 0.5.3
+lastReleaseVersion: 0.9.2

cpp/ql/lib/experimental/semmle/code/cpp/dataflow/ProductFlow.qll

@@ -1,301 +0,0 @@
-import experimental.semmle.code.cpp.ir.dataflow.DataFlow
-import experimental.semmle.code.cpp.ir.dataflow.DataFlow2
-
-module ProductFlow {
-  abstract class Configuration extends string {
-    bindingset[this]
-    Configuration() { any() }
-
-    /**
-     * Holds if `(source1, source2)` is a relevant data flow source.
-     *
-     * `source1` and `source2` must belong to the same callable.
-     */
-    predicate isSourcePair(DataFlow::Node source1, DataFlow::Node source2) { none() }
-
-    /**
-     * Holds if `(source1, source2)` is a relevant data flow source with initial states `state1`
-     * and `state2`, respectively.
-     *
-     * `source1` and `source2` must belong to the same callable.
-     */
-    predicate isSourcePair(
-      DataFlow::Node source1, DataFlow::FlowState state1, DataFlow::Node source2,
-      DataFlow::FlowState state2
-    ) {
-      state1 = "" and
-      state2 = "" and
-      this.isSourcePair(source1, source2)
-    }
-
-    /**
-     * Holds if `(sink1, sink2)` is a relevant data flow sink.
-     *
-     * `sink1` and `sink2` must belong to the same callable.
-     */
-    predicate isSinkPair(DataFlow::Node sink1, DataFlow::Node sink2) { none() }
-
-    /**
-     * Holds if `(sink1, sink2)` is a relevant data flow sink with final states `state1`
-     * and `state2`, respectively.
-     *
-     * `sink1` and `sink2` must belong to the same callable.
-     */
-    predicate isSinkPair(
-      DataFlow::Node sink1, DataFlow::FlowState state1, DataFlow::Node sink2,
-      DataFlow::FlowState state2
-    ) {
-      state1 = "" and
-      state2 = "" and
-      this.isSinkPair(sink1, sink2)
-    }
-
-    /**
-     * Holds if data flow through `node` is prohibited through the first projection of the product
-     * dataflow graph when the flow state is `state`.
-     */
-    predicate isBarrier1(DataFlow::Node node, DataFlow::FlowState state) {
-      this.isBarrier1(node) and state = ""
-    }
-
-    /**
-     * Holds if data flow through `node` is prohibited through the second projection of the product
-     * dataflow graph when the flow state is `state`.
-     */
-    predicate isBarrier2(DataFlow::Node node, DataFlow::FlowState state) {
-      this.isBarrier2(node) and state = ""
-    }
-
-    /**
-     * Holds if data flow through `node` is prohibited through the first projection of the product
-     * dataflow graph.
-     */
-    predicate isBarrier1(DataFlow::Node node) { none() }
-
-    /**
-     * Holds if data flow through `node` is prohibited through the second projection of the product
-     * dataflow graph.
-     */
-    predicate isBarrier2(DataFlow::Node node) { none() }
-
-    /**
-     * Holds if data flow out of `node` is prohibited in the first projection of the product
-     * dataflow graph.
-     */
-    predicate isBarrierOut1(DataFlow::Node node) { none() }
-
-    /**
-     * Holds if data flow out of `node` is prohibited in the second projection of the product
-     * dataflow graph.
-     */
-    predicate isBarrierOut2(DataFlow::Node node) { none() }
-
-    /*
-     * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps in
-     * the first projection of the product dataflow graph.
-     */
-
-    predicate isAdditionalFlowStep1(DataFlow::Node node1, DataFlow::Node node2) { none() }
-
-    /**
-     * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps in
-     * the first projection of the product dataflow graph.
-     *
-     * This step is only applicable in `state1` and updates the flow state to `state2`.
-     */
-    predicate isAdditionalFlowStep1(
-      DataFlow::Node node1, DataFlow::FlowState state1, DataFlow::Node node2,
-      DataFlow::FlowState state2
-    ) {
-      state1 instanceof DataFlow::FlowStateEmpty and
-      state2 instanceof DataFlow::FlowStateEmpty and
-      this.isAdditionalFlowStep1(node1, node2)
-    }
-
-    /**
-     * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps in
-     * the second projection of the product dataflow graph.
-     */
-    predicate isAdditionalFlowStep2(DataFlow::Node node1, DataFlow::Node node2) { none() }
-
-    /**
-     * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps in
-     * the second projection of the product dataflow graph.
-     *
-     * This step is only applicable in `state1` and updates the flow state to `state2`.
-     */
-    predicate isAdditionalFlowStep2(
-      DataFlow::Node node1, DataFlow::FlowState state1, DataFlow::Node node2,
-      DataFlow::FlowState state2
-    ) {
-      state1 instanceof DataFlow::FlowStateEmpty and
-      state2 instanceof DataFlow::FlowStateEmpty and
-      this.isAdditionalFlowStep2(node1, node2)
-    }
-
-    /**
-     * Holds if data flow into `node` is prohibited in the first projection of the product
-     * dataflow graph.
-     */
-    predicate isBarrierIn1(DataFlow::Node node) { none() }
-
-    /**
-     * Holds if data flow into `node` is prohibited in the second projection of the product
-     * dataflow graph.
-     */
-    predicate isBarrierIn2(DataFlow::Node node) { none() }
-
-    predicate hasFlowPath(
-      DataFlow::PathNode source1, DataFlow2::PathNode source2, DataFlow::PathNode sink1,
-      DataFlow2::PathNode sink2
-    ) {
-      reachable(this, source1, source2, sink1, sink2)
-    }
-  }
-
-  private import Internal
-
-  module Internal {
-    class Conf1 extends DataFlow::Configuration {
-      Conf1() { this = "Conf1" }
-
-      override predicate isSource(DataFlow::Node source, DataFlow::FlowState state) {
-        exists(Configuration conf | conf.isSourcePair(source, state, _, _))
-      }
-
-      override predicate isSink(DataFlow::Node sink, DataFlow::FlowState state) {
-        exists(Configuration conf | conf.isSinkPair(sink, state, _, _))
-      }
-
-      override predicate isBarrier(DataFlow::Node node, DataFlow::FlowState state) {
-        exists(Configuration conf | conf.isBarrier1(node, state))
-      }
-
-      override predicate isBarrierOut(DataFlow::Node node) {
-        exists(Configuration conf | conf.isBarrierOut1(node))
-      }
-
-      override predicate isAdditionalFlowStep(
-        DataFlow::Node node1, DataFlow::FlowState state1, DataFlow::Node node2,
-        DataFlow::FlowState state2
-      ) {
-        exists(Configuration conf | conf.isAdditionalFlowStep1(node1, state1, node2, state2))
-      }
-
-      override predicate isBarrierIn(DataFlow::Node node) {
-        exists(Configuration conf | conf.isBarrierIn1(node))
-      }
-    }
-
-    class Conf2 extends DataFlow2::Configuration {
-      Conf2() { this = "Conf2" }
-
-      override predicate isSource(DataFlow::Node source, DataFlow::FlowState state) {
-        exists(Configuration conf, DataFlow::PathNode source1 |
-          conf.isSourcePair(source1.getNode(), source1.getState(), source, state) and
-          any(Conf1 c).hasFlowPath(source1, _)
-        )
-      }
-
-      override predicate isSink(DataFlow::Node sink, DataFlow::FlowState state) {
-        exists(Configuration conf, DataFlow::PathNode sink1 |
-          conf.isSinkPair(sink1.getNode(), sink1.getState(), sink, state) and
-          any(Conf1 c).hasFlowPath(_, sink1)
-        )
-      }
-
-      override predicate isBarrier(DataFlow::Node node, DataFlow::FlowState state) {
-        exists(Configuration conf | conf.isBarrier2(node, state))
-      }
-
-      override predicate isBarrierOut(DataFlow::Node node) {
-        exists(Configuration conf | conf.isBarrierOut2(node))
-      }
-
-      override predicate isAdditionalFlowStep(
-        DataFlow::Node node1, DataFlow::FlowState state1, DataFlow::Node node2,
-        DataFlow::FlowState state2
-      ) {
-        exists(Configuration conf | conf.isAdditionalFlowStep2(node1, state1, node2, state2))
-      }
-
-      override predicate isBarrierIn(DataFlow::Node node) {
-        exists(Configuration conf | conf.isBarrierIn2(node))
-      }
-    }
-  }
-
-  pragma[nomagic]
-  private predicate reachableInterprocEntry(
-    Configuration conf, DataFlow::PathNode source1, DataFlow2::PathNode source2,
-    DataFlow::PathNode node1, DataFlow2::PathNode node2
-  ) {
-    conf.isSourcePair(node1.getNode(), node1.getState(), node2.getNode(), node2.getState()) and
-    node1 = source1 and
-    node2 = source2
-    or
-    exists(
-      DataFlow::PathNode midEntry1, DataFlow2::PathNode midEntry2, DataFlow::PathNode midExit1,
-      DataFlow2::PathNode midExit2
-    |
-      reachableInterprocEntry(conf, source1, source2, midEntry1, midEntry2) and
-      interprocEdgePair(midExit1, midExit2, node1, node2) and
-      localPathStep1*(midEntry1, midExit1) and
-      localPathStep2*(midEntry2, midExit2)
-    )
-  }
-
-  private predicate localPathStep1(DataFlow::PathNode pred, DataFlow::PathNode succ) {
-    DataFlow::PathGraph::edges(pred, succ) and
-    pragma[only_bind_out](pred.getNode().getEnclosingCallable()) =
-      pragma[only_bind_out](succ.getNode().getEnclosingCallable())
-  }
-
-  private predicate localPathStep2(DataFlow2::PathNode pred, DataFlow2::PathNode succ) {
-    DataFlow2::PathGraph::edges(pred, succ) and
-    pragma[only_bind_out](pred.getNode().getEnclosingCallable()) =
-      pragma[only_bind_out](succ.getNode().getEnclosingCallable())
-  }
-
-  pragma[nomagic]
-  private predicate interprocEdge1(
-    Declaration predDecl, Declaration succDecl, DataFlow::PathNode pred1, DataFlow::PathNode succ1
-  ) {
-    DataFlow::PathGraph::edges(pred1, succ1) and
-    predDecl != succDecl and
-    pred1.getNode().getEnclosingCallable() = predDecl and
-    succ1.getNode().getEnclosingCallable() = succDecl
-  }
-
-  pragma[nomagic]
-  private predicate interprocEdge2(
-    Declaration predDecl, Declaration succDecl, DataFlow2::PathNode pred2, DataFlow2::PathNode succ2
-  ) {
-    DataFlow2::PathGraph::edges(pred2, succ2) and
-    predDecl != succDecl and
-    pred2.getNode().getEnclosingCallable() = predDecl and
-    succ2.getNode().getEnclosingCallable() = succDecl
-  }
-
-  private predicate interprocEdgePair(
-    DataFlow::PathNode pred1, DataFlow2::PathNode pred2, DataFlow::PathNode succ1,
-    DataFlow2::PathNode succ2
-  ) {
-    exists(Declaration predDecl, Declaration succDecl |
-      interprocEdge1(predDecl, succDecl, pred1, succ1) and
-      interprocEdge2(predDecl, succDecl, pred2, succ2)
-    )
-  }
-
-  private predicate reachable(
-    Configuration conf, DataFlow::PathNode source1, DataFlow2::PathNode source2,
-    DataFlow::PathNode sink1, DataFlow2::PathNode sink2
-  ) {
-    exists(DataFlow::PathNode mid1, DataFlow2::PathNode mid2 |
-      reachableInterprocEntry(conf, source1, source2, mid1, mid2) and
-      conf.isSinkPair(sink1.getNode(), sink1.getState(), sink2.getNode(), sink2.getState()) and
-      localPathStep1*(mid1, sink1) and
-      localPathStep2*(mid2, sink2)
-    )
-  }
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/DataFlow.qll

@@ -1,26 +0,0 @@
-/**
- * Provides a library for local (intra-procedural) and global (inter-procedural)
- * data flow analysis: deciding whether data can flow from a _source_ to a
- * _sink_. This library differs from the one in `semmle.code.cpp.dataflow` in that
- * this library uses the IR (Intermediate Representation) library, which provides
- * a more precise semantic representation of the program, whereas the other dataflow
- * library uses the more syntax-oriented ASTs. This library should provide more accurate
- * results than the AST-based library in most scenarios.
- *
- * Unless configured otherwise, _flow_ means that the exact value of
- * the source may reach the sink. We do not track flow across pointer
- * dereferences or array indexing.
- *
- * To use global (interprocedural) data flow, extend the class
- * `DataFlow::Configuration` as documented on that class. To use local
- * (intraprocedural) data flow between expressions, call
- * `DataFlow::localExprFlow`. For more general cases of local data flow, call
- * `DataFlow::localFlow` or `DataFlow::localFlowStep` with arguments of type
- * `DataFlow::Node`.
- */
-
-import cpp
-
-module DataFlow {
-  import experimental.semmle.code.cpp.ir.dataflow.internal.DataFlowImpl
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/DataFlow2.qll

@@ -1,16 +0,0 @@
-/**
- * Provides a `DataFlow2` module, which is a copy of the `DataFlow` module. Use
- * this class when data-flow configurations must depend on each other. Two
- * classes extending `DataFlow::Configuration` should never depend on each
- * other, but one of them should instead depend on a
- * `DataFlow2::Configuration`, a `DataFlow3::Configuration`, or a
- * `DataFlow4::Configuration`.
- *
- * See `semmle.code.cpp.ir.dataflow.DataFlow` for the full documentation.
- */
-
-import cpp
-
-module DataFlow2 {
-  import experimental.semmle.code.cpp.ir.dataflow.internal.DataFlowImpl2
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/DataFlow3.qll

@@ -1,16 +0,0 @@
-/**
- * Provides a `DataFlow3` module, which is a copy of the `DataFlow` module. Use
- * this class when data-flow configurations must depend on each other. Two
- * classes extending `DataFlow::Configuration` should never depend on each
- * other, but one of them should instead depend on a
- * `DataFlow2::Configuration`, a `DataFlow3::Configuration`, or a
- * `DataFlow4::Configuration`.
- *
- * See `semmle.code.cpp.ir.dataflow.DataFlow` for the full documentation.
- */
-
-import cpp
-
-module DataFlow3 {
-  import experimental.semmle.code.cpp.ir.dataflow.internal.DataFlowImpl3
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/DataFlow4.qll

@@ -1,16 +0,0 @@
-/**
- * Provides a `DataFlow4` module, which is a copy of the `DataFlow` module. Use
- * this class when data-flow configurations must depend on each other. Two
- * classes extending `DataFlow::Configuration` should never depend on each
- * other, but one of them should instead depend on a
- * `DataFlow2::Configuration`, a `DataFlow3::Configuration`, or a
- * `DataFlow4::Configuration`.
- *
- * See `semmle.code.cpp.ir.dataflow.DataFlow` for the full documentation.
- */
-
-import cpp
-
-module DataFlow4 {
-  import experimental.semmle.code.cpp.ir.dataflow.internal.DataFlowImpl4
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/ResolveCall.qll

@@ -1,23 +0,0 @@
-/**
- * Provides a predicate for non-contextual virtual dispatch and function
- * pointer resolution.
- */
-
-import cpp
-private import semmle.code.cpp.ir.ValueNumbering
-private import internal.DataFlowDispatch
-private import semmle.code.cpp.ir.IR
-
-/**
- * Resolve potential target function(s) for `call`.
- *
- * If `call` is a call through a function pointer (`ExprCall`) or its target is
- * a virtual member function, simple data flow analysis is performed in order
- * to identify the possible target(s).
- */
-Function resolveCall(Call call) {
-  exists(CallInstruction callInstruction |
-    callInstruction.getAst() = call and
-    result = viableCallable(callInstruction)
-  )
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/TaintTracking.qll

@@ -1,23 +0,0 @@
-/**
- * Provides classes for performing local (intra-procedural) and
- * global (inter-procedural) taint-tracking analyses.
- *
- * We define _taint propagation_ informally to mean that a substantial part of
- * the information from the source is preserved at the sink. For example, taint
- * propagates from `x` to `x + 100`, but it does not propagate from `x` to `x >
- * 100` since we consider a single bit of information to be too little.
- *
- * To use global (interprocedural) taint tracking, extend the class
- * `TaintTracking::Configuration` as documented on that class. To use local
- * (intraprocedural) taint tracking between expressions, call
- * `TaintTracking::localExprTaint`. For more general cases of local taint
- * tracking, call `TaintTracking::localTaint` or
- * `TaintTracking::localTaintStep` with arguments of type `DataFlow::Node`.
- */
-
-import semmle.code.cpp.ir.dataflow.DataFlow
-import semmle.code.cpp.ir.dataflow.DataFlow2
-
-module TaintTracking {
-  import experimental.semmle.code.cpp.ir.dataflow.internal.tainttracking1.TaintTrackingImpl
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/TaintTracking2.qll

@@ -1,15 +0,0 @@
-/**
- * Provides a `TaintTracking2` module, which is a copy of the `TaintTracking`
- * module. Use this class when data-flow configurations or taint-tracking
- * configurations must depend on each other. Two classes extending
- * `DataFlow::Configuration` should never depend on each other, but one of them
- * should instead depend on a `DataFlow2::Configuration`, a
- * `DataFlow3::Configuration`, or a `DataFlow4::Configuration`. The
- * `TaintTracking::Configuration` class extends `DataFlow::Configuration`, and
- * `TaintTracking2::Configuration` extends `DataFlow2::Configuration`.
- *
- * See `semmle.code.cpp.ir.dataflow.TaintTracking` for the full documentation.
- */
-module TaintTracking2 {
-  import experimental.semmle.code.cpp.ir.dataflow.internal.tainttracking2.TaintTrackingImpl
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/TaintTracking3.qll

@@ -1,15 +0,0 @@
-/**
- * Provides a `TaintTracking3` module, which is a copy of the `TaintTracking`
- * module. Use this class when data-flow configurations or taint-tracking
- * configurations must depend on each other. Two classes extending
- * `DataFlow::Configuration` should never depend on each other, but one of them
- * should instead depend on a `DataFlow2::Configuration`, a
- * `DataFlow3::Configuration`, or a `DataFlow4::Configuration`. The
- * `TaintTracking::Configuration` class extends `DataFlow::Configuration`, and
- * `TaintTracking2::Configuration` extends `DataFlow2::Configuration`.
- *
- * See `semmle.code.cpp.ir.dataflow.TaintTracking` for the full documentation.
- */
-module TaintTracking3 {
-  import experimental.semmle.code.cpp.ir.dataflow.internal.tainttracking3.TaintTrackingImpl
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowDispatch.qll

@@ -1,273 +0,0 @@
-private import cpp
-private import semmle.code.cpp.ir.IR
-private import experimental.semmle.code.cpp.ir.dataflow.DataFlow
-private import experimental.semmle.code.cpp.ir.dataflow.internal.DataFlowPrivate
-private import experimental.semmle.code.cpp.ir.dataflow.internal.DataFlowUtil
-private import DataFlowImplCommon as DataFlowImplCommon
-
-/**
- * Gets a function that might be called by `call`.
- */
-cached
-Function viableCallable(CallInstruction call) {
-  DataFlowImplCommon::forceCachingInSameStage() and
-  result = call.getStaticCallTarget()
-  or
-  // If the target of the call does not have a body in the snapshot, it might
-  // be because the target is just a header declaration, and the real target
-  // will be determined at run time when the caller and callee are linked
-  // together by the operating system's dynamic linker. In case a _unique_
-  // function with the right signature is present in the database, we return
-  // that as a potential callee.
-  exists(string qualifiedName, int nparams |
-    callSignatureWithoutBody(qualifiedName, nparams, call) and
-    functionSignatureWithBody(qualifiedName, nparams, result) and
-    strictcount(Function other | functionSignatureWithBody(qualifiedName, nparams, other)) = 1
-  )
-  or
-  // Virtual dispatch
-  result = call.(VirtualDispatch::DataSensitiveCall).resolve()
-}
-
-/**
- * Provides virtual dispatch support compatible with the original
- * implementation of `semmle.code.cpp.security.TaintTracking`.
- */
-private module VirtualDispatch {
-  /** A call that may dispatch differently depending on the qualifier value. */
-  abstract class DataSensitiveCall extends DataFlowCall {
-    /**
-     * Gets the node whose value determines the target of this call. This node
-     * could be the qualifier of a virtual dispatch or the function-pointer
-     * expression in a call to a function pointer. What they have in common is
-     * that we need to find out which data flows there, and then it's up to the
-     * `resolve` predicate to stitch that information together and resolve the
-     * call.
-     */
-    abstract DataFlow::Node getDispatchValue();
-
-    /** Gets a candidate target for this call. */
-    abstract Function resolve();
-
-    /**
-     * Whether `src` can flow to this call.
-     *
-     * Searches backwards from `getDispatchValue()` to `src`. The `allowFromArg`
-     * parameter is true when the search is allowed to continue backwards into
-     * a parameter; non-recursive callers should pass `_` for `allowFromArg`.
-     */
-    predicate flowsFrom(DataFlow::Node src, boolean allowFromArg) {
-      src = this.getDispatchValue() and allowFromArg = true
-      or
-      exists(DataFlow::Node other, boolean allowOtherFromArg |
-        this.flowsFrom(other, allowOtherFromArg)
-      |
-        // Call argument
-        exists(DataFlowCall call, Position i |
-          other
-              .(DataFlow::ParameterNode)
-              .isParameterOf(pragma[only_bind_into](call).getStaticCallTarget(), i) and
-          src.(ArgumentNode).argumentOf(call, pragma[only_bind_into](pragma[only_bind_out](i)))
-        ) and
-        allowOtherFromArg = true and
-        allowFromArg = true
-        or
-        // Call return
-        exists(DataFlowCall call, ReturnKind returnKind |
-          other = getAnOutNode(call, returnKind) and
-          returnNodeWithKindAndEnclosingCallable(src, returnKind, call.getStaticCallTarget())
-        ) and
-        allowFromArg = false
-        or
-        // Local flow
-        DataFlow::localFlowStep(src, other) and
-        allowFromArg = allowOtherFromArg
-        or
-        // Flow from global variable to load.
-        exists(LoadInstruction load, GlobalOrNamespaceVariable var |
-          var = src.asVariable() and
-          other.asInstruction() = load and
-          addressOfGlobal(load.getSourceAddress(), var) and
-          // The `allowFromArg` concept doesn't play a role when `src` is a
-          // global variable, so we just set it to a single arbitrary value for
-          // performance.
-          allowFromArg = true
-        )
-        or
-        // Flow from store to global variable.
-        exists(StoreInstruction store, GlobalOrNamespaceVariable var |
-          var = other.asVariable() and
-          store = src.asInstruction() and
-          storeIntoGlobal(store, var) and
-          // Setting `allowFromArg` to `true` like in the base case means we
-          // treat a store to a global variable like the dispatch itself: flow
-          // may come from anywhere.
-          allowFromArg = true
-        )
-      )
-    }
-  }
-
-  pragma[noinline]
-  private predicate storeIntoGlobal(StoreInstruction store, GlobalOrNamespaceVariable var) {
-    addressOfGlobal(store.getDestinationAddress(), var)
-  }
-
-  /** Holds if `addressInstr` is an instruction that produces the address of `var`. */
-  private predicate addressOfGlobal(Instruction addressInstr, GlobalOrNamespaceVariable var) {
-    // Access directly to the global variable
-    addressInstr.(VariableAddressInstruction).getAstVariable() = var
-    or
-    // Access to a field on a global union
-    exists(FieldAddressInstruction fa |
-      fa = addressInstr and
-      fa.getObjectAddress().(VariableAddressInstruction).getAstVariable() = var and
-      fa.getField().getDeclaringType() instanceof Union
-    )
-  }
-
-  /**
-   * A ReturnNode with its ReturnKind and its enclosing callable.
-   *
-   * Used to fix a join ordering issue in flowsFrom.
-   */
-  pragma[noinline]
-  private predicate returnNodeWithKindAndEnclosingCallable(
-    ReturnNode node, ReturnKind kind, DataFlowCallable callable
-  ) {
-    node.getKind() = kind and
-    node.getEnclosingCallable() = callable
-  }
-
-  /** Call through a function pointer. */
-  private class DataSensitiveExprCall extends DataSensitiveCall {
-    DataSensitiveExprCall() { not exists(this.getStaticCallTarget()) }
-
-    override DataFlow::Node getDispatchValue() { result.asInstruction() = this.getCallTarget() }
-
-    override Function resolve() {
-      exists(FunctionInstruction fi |
-        this.flowsFrom(DataFlow::instructionNode(fi), _) and
-        result = fi.getFunctionSymbol()
-      ) and
-      (
-        this.getNumberOfArguments() <= result.getEffectiveNumberOfParameters() and
-        this.getNumberOfArguments() >= result.getEffectiveNumberOfParameters()
-        or
-        result.isVarargs()
-      )
-    }
-  }
-
-  /** Call to a virtual function. */
-  private class DataSensitiveOverriddenFunctionCall extends DataSensitiveCall {
-    DataSensitiveOverriddenFunctionCall() {
-      exists(this.getStaticCallTarget().(VirtualFunction).getAnOverridingFunction())
-    }
-
-    override DataFlow::Node getDispatchValue() { result.asInstruction() = this.getThisArgument() }
-
-    override MemberFunction resolve() {
-      exists(Class overridingClass |
-        this.overrideMayAffectCall(overridingClass, result) and
-        this.hasFlowFromCastFrom(overridingClass)
-      )
-    }
-
-    /**
-     * Holds if `this` is a virtual function call whose static target is
-     * overridden by `overridingFunction` in `overridingClass`.
-     */
-    pragma[noinline]
-    private predicate overrideMayAffectCall(Class overridingClass, MemberFunction overridingFunction) {
-      overridingFunction.getAnOverriddenFunction+() = this.getStaticCallTarget().(VirtualFunction) and
-      overridingFunction.getDeclaringType() = overridingClass
-    }
-
-    /**
-     * Holds if the qualifier of `this` has flow from an upcast from
-     * `derivedClass`.
-     */
-    pragma[noinline]
-    private predicate hasFlowFromCastFrom(Class derivedClass) {
-      exists(ConvertToBaseInstruction toBase |
-        this.flowsFrom(DataFlow::instructionNode(toBase), _) and
-        derivedClass = toBase.getDerivedClass()
-      )
-    }
-  }
-}
-
-/**
- * Holds if `f` is a function with a body that has name `qualifiedName` and
- * `nparams` parameter count. See `functionSignature`.
- */
-private predicate functionSignatureWithBody(string qualifiedName, int nparams, Function f) {
-  functionSignature(f, qualifiedName, nparams) and
-  exists(f.getBlock())
-}
-
-/**
- * Holds if the target of `call` is a function _with no definition_ that has
- * name `qualifiedName` and `nparams` parameter count. See `functionSignature`.
- */
-pragma[noinline]
-private predicate callSignatureWithoutBody(string qualifiedName, int nparams, CallInstruction call) {
-  exists(Function target |
-    target = call.getStaticCallTarget() and
-    not exists(target.getBlock()) and
-    functionSignature(target, qualifiedName, nparams)
-  )
-}
-
-/**
- * Holds if `f` has name `qualifiedName` and `nparams` parameter count. This is
- * an approximation of its signature for the purpose of matching functions that
- * might be the same across link targets.
- */
-private predicate functionSignature(Function f, string qualifiedName, int nparams) {
-  qualifiedName = f.getQualifiedName() and
-  nparams = f.getNumberOfParameters() and
-  not f.isStatic()
-}
-
-/**
- * Holds if the set of viable implementations that can be called by `call`
- * might be improved by knowing the call context.
- */
-predicate mayBenefitFromCallContext(CallInstruction call, Function f) {
-  mayBenefitFromCallContext(call, f, _)
-}
-
-/**
- * Holds if `call` is a call through a function pointer, and the pointer
- * value is given as the `arg`'th argument to `f`.
- */
-private predicate mayBenefitFromCallContext(
-  VirtualDispatch::DataSensitiveCall call, Function f, int arg
-) {
-  f = pragma[only_bind_out](call).getEnclosingCallable() and
-  exists(InitializeParameterInstruction init |
-    not exists(call.getStaticCallTarget()) and
-    init.getEnclosingFunction() = f and
-    call.flowsFrom(DataFlow::instructionNode(init), _) and
-    init.getParameter().getIndex() = arg
-  )
-}
-
-/**
- * Gets a viable dispatch target of `call` in the context `ctx`. This is
- * restricted to those `call`s for which a context might make a difference.
- */
-Function viableImplInCallContext(CallInstruction call, CallInstruction ctx) {
-  result = viableCallable(call) and
-  exists(int i, Function f |
-    mayBenefitFromCallContext(pragma[only_bind_into](call), f, i) and
-    f = ctx.getStaticCallTarget() and
-    result = ctx.getArgument(i).getUnconvertedResultExpression().(FunctionAccess).getTarget()
-  )
-}
-
-/** Holds if arguments at position `apos` match parameters at position `ppos`. */
-pragma[inline]
-predicate parameterMatch(ParameterPosition ppos, ArgumentPosition apos) { ppos = apos }

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImplConsistency.qll

@@ -1,278 +0,0 @@
-/**
- * Provides consistency queries for checking invariants in the language-specific
- * data-flow classes and predicates.
- */
-
-private import DataFlowImplSpecific::Private
-private import DataFlowImplSpecific::Public
-private import tainttracking1.TaintTrackingParameter::Private
-private import tainttracking1.TaintTrackingParameter::Public
-
-module Consistency {
-  private newtype TConsistencyConfiguration = MkConsistencyConfiguration()
-
-  /** A class for configuring the consistency queries. */
-  class ConsistencyConfiguration extends TConsistencyConfiguration {
-    string toString() { none() }
-
-    /** Holds if `n` should be excluded from the consistency test `uniqueEnclosingCallable`. */
-    predicate uniqueEnclosingCallableExclude(Node n) { none() }
-
-    /** Holds if `n` should be excluded from the consistency test `uniqueNodeLocation`. */
-    predicate uniqueNodeLocationExclude(Node n) { none() }
-
-    /** Holds if `n` should be excluded from the consistency test `missingLocation`. */
-    predicate missingLocationExclude(Node n) { none() }
-
-    /** Holds if `n` should be excluded from the consistency test `postWithInFlow`. */
-    predicate postWithInFlowExclude(Node n) { none() }
-
-    /** Holds if `n` should be excluded from the consistency test `argHasPostUpdate`. */
-    predicate argHasPostUpdateExclude(ArgumentNode n) { none() }
-
-    /** Holds if `n` should be excluded from the consistency test `reverseRead`. */
-    predicate reverseReadExclude(Node n) { none() }
-
-    /** Holds if `n` should be excluded from the consistency test `postHasUniquePre`. */
-    predicate postHasUniquePreExclude(PostUpdateNode n) { none() }
-
-    /** Holds if `n` should be excluded from the consistency test `uniquePostUpdate`. */
-    predicate uniquePostUpdateExclude(Node n) { none() }
-
-    /** Holds if `(call, ctx)` should be excluded from the consistency test `viableImplInCallContextTooLargeExclude`. */
-    predicate viableImplInCallContextTooLargeExclude(
-      DataFlowCall call, DataFlowCall ctx, DataFlowCallable callable
-    ) {
-      none()
-    }
-
-    /** Holds if `(c, pos, p)` should be excluded from the consistency test `uniqueParameterNodeAtPosition`. */
-    predicate uniqueParameterNodeAtPositionExclude(DataFlowCallable c, ParameterPosition pos, Node p) {
-      none()
-    }
-
-    /** Holds if `(c, pos, p)` should be excluded from the consistency test `uniqueParameterNodePosition`. */
-    predicate uniqueParameterNodePositionExclude(DataFlowCallable c, ParameterPosition pos, Node p) {
-      none()
-    }
-  }
-
-  private class RelevantNode extends Node {
-    RelevantNode() {
-      this instanceof ArgumentNode or
-      this instanceof ParameterNode or
-      this instanceof ReturnNode or
-      this = getAnOutNode(_, _) or
-      simpleLocalFlowStep(this, _) or
-      simpleLocalFlowStep(_, this) or
-      jumpStep(this, _) or
-      jumpStep(_, this) or
-      storeStep(this, _, _) or
-      storeStep(_, _, this) or
-      readStep(this, _, _) or
-      readStep(_, _, this) or
-      defaultAdditionalTaintStep(this, _) or
-      defaultAdditionalTaintStep(_, this)
-    }
-  }
-
-  query predicate uniqueEnclosingCallable(Node n, string msg) {
-    exists(int c |
-      n instanceof RelevantNode and
-      c = count(nodeGetEnclosingCallable(n)) and
-      c != 1 and
-      not any(ConsistencyConfiguration conf).uniqueEnclosingCallableExclude(n) and
-      msg = "Node should have one enclosing callable but has " + c + "."
-    )
-  }
-
-  query predicate uniqueType(Node n, string msg) {
-    exists(int c |
-      n instanceof RelevantNode and
-      c = count(getNodeType(n)) and
-      c != 1 and
-      msg = "Node should have one type but has " + c + "."
-    )
-  }
-
-  query predicate uniqueNodeLocation(Node n, string msg) {
-    exists(int c |
-      c =
-        count(string filepath, int startline, int startcolumn, int endline, int endcolumn |
-          n.hasLocationInfo(filepath, startline, startcolumn, endline, endcolumn)
-        ) and
-      c != 1 and
-      not any(ConsistencyConfiguration conf).uniqueNodeLocationExclude(n) and
-      msg = "Node should have one location but has " + c + "."
-    )
-  }
-
-  query predicate missingLocation(string msg) {
-    exists(int c |
-      c =
-        strictcount(Node n |
-          not n.hasLocationInfo(_, _, _, _, _) and
-          not any(ConsistencyConfiguration conf).missingLocationExclude(n)
-        ) and
-      msg = "Nodes without location: " + c
-    )
-  }
-
-  query predicate uniqueNodeToString(Node n, string msg) {
-    exists(int c |
-      c = count(n.toString()) and
-      c != 1 and
-      msg = "Node should have one toString but has " + c + "."
-    )
-  }
-
-  query predicate missingToString(string msg) {
-    exists(int c |
-      c = strictcount(Node n | not exists(n.toString())) and
-      msg = "Nodes without toString: " + c
-    )
-  }
-
-  query predicate parameterCallable(ParameterNode p, string msg) {
-    exists(DataFlowCallable c | isParameterNode(p, c, _) and c != nodeGetEnclosingCallable(p)) and
-    msg = "Callable mismatch for parameter."
-  }
-
-  query predicate localFlowIsLocal(Node n1, Node n2, string msg) {
-    simpleLocalFlowStep(n1, n2) and
-    nodeGetEnclosingCallable(n1) != nodeGetEnclosingCallable(n2) and
-    msg = "Local flow step does not preserve enclosing callable."
-  }
-
-  query predicate readStepIsLocal(Node n1, Node n2, string msg) {
-    readStep(n1, _, n2) and
-    nodeGetEnclosingCallable(n1) != nodeGetEnclosingCallable(n2) and
-    msg = "Read step does not preserve enclosing callable."
-  }
-
-  query predicate storeStepIsLocal(Node n1, Node n2, string msg) {
-    storeStep(n1, _, n2) and
-    nodeGetEnclosingCallable(n1) != nodeGetEnclosingCallable(n2) and
-    msg = "Store step does not preserve enclosing callable."
-  }
-
-  private DataFlowType typeRepr() { result = getNodeType(_) }
-
-  query predicate compatibleTypesReflexive(DataFlowType t, string msg) {
-    t = typeRepr() and
-    not compatibleTypes(t, t) and
-    msg = "Type compatibility predicate is not reflexive."
-  }
-
-  query predicate unreachableNodeCCtx(Node n, DataFlowCall call, string msg) {
-    isUnreachableInCall(n, call) and
-    exists(DataFlowCallable c |
-      c = nodeGetEnclosingCallable(n) and
-      not viableCallable(call) = c
-    ) and
-    msg = "Call context for isUnreachableInCall is inconsistent with call graph."
-  }
-
-  query predicate localCallNodes(DataFlowCall call, Node n, string msg) {
-    (
-      n = getAnOutNode(call, _) and
-      msg = "OutNode and call does not share enclosing callable."
-      or
-      n.(ArgumentNode).argumentOf(call, _) and
-      msg = "ArgumentNode and call does not share enclosing callable."
-    ) and
-    nodeGetEnclosingCallable(n) != call.getEnclosingCallable()
-  }
-
-  // This predicate helps the compiler forget that in some languages
-  // it is impossible for a result of `getPreUpdateNode` to be an
-  // instance of `PostUpdateNode`.
-  private Node getPre(PostUpdateNode n) {
-    result = n.getPreUpdateNode()
-    or
-    none()
-  }
-
-  query predicate postIsNotPre(PostUpdateNode n, string msg) {
-    getPre(n) = n and
-    msg = "PostUpdateNode should not equal its pre-update node."
-  }
-
-  query predicate postHasUniquePre(PostUpdateNode n, string msg) {
-    not any(ConsistencyConfiguration conf).postHasUniquePreExclude(n) and
-    exists(int c |
-      c = count(n.getPreUpdateNode()) and
-      c != 1 and
-      msg = "PostUpdateNode should have one pre-update node but has " + c + "."
-    )
-  }
-
-  query predicate uniquePostUpdate(Node n, string msg) {
-    not any(ConsistencyConfiguration conf).uniquePostUpdateExclude(n) and
-    1 < strictcount(PostUpdateNode post | post.getPreUpdateNode() = n) and
-    msg = "Node has multiple PostUpdateNodes."
-  }
-
-  query predicate postIsInSameCallable(PostUpdateNode n, string msg) {
-    nodeGetEnclosingCallable(n) != nodeGetEnclosingCallable(n.getPreUpdateNode()) and
-    msg = "PostUpdateNode does not share callable with its pre-update node."
-  }
-
-  private predicate hasPost(Node n) { exists(PostUpdateNode post | post.getPreUpdateNode() = n) }
-
-  query predicate reverseRead(Node n, string msg) {
-    exists(Node n2 | readStep(n, _, n2) and hasPost(n2) and not hasPost(n)) and
-    not any(ConsistencyConfiguration conf).reverseReadExclude(n) and
-    msg = "Origin of readStep is missing a PostUpdateNode."
-  }
-
-  query predicate argHasPostUpdate(ArgumentNode n, string msg) {
-    not hasPost(n) and
-    not any(ConsistencyConfiguration c).argHasPostUpdateExclude(n) and
-    msg = "ArgumentNode is missing PostUpdateNode."
-  }
-
-  // This predicate helps the compiler forget that in some languages
-  // it is impossible for a `PostUpdateNode` to be the target of
-  // `simpleLocalFlowStep`.
-  private predicate isPostUpdateNode(Node n) { n instanceof PostUpdateNode or none() }
-
-  query predicate postWithInFlow(Node n, string msg) {
-    isPostUpdateNode(n) and
-    not clearsContent(n, _) and
-    simpleLocalFlowStep(_, n) and
-    not any(ConsistencyConfiguration c).postWithInFlowExclude(n) and
-    msg = "PostUpdateNode should not be the target of local flow."
-  }
-
-  query predicate viableImplInCallContextTooLarge(
-    DataFlowCall call, DataFlowCall ctx, DataFlowCallable callable
-  ) {
-    callable = viableImplInCallContext(call, ctx) and
-    not callable = viableCallable(call) and
-    not any(ConsistencyConfiguration c).viableImplInCallContextTooLargeExclude(call, ctx, callable)
-  }
-
-  query predicate uniqueParameterNodeAtPosition(
-    DataFlowCallable c, ParameterPosition pos, Node p, string msg
-  ) {
-    not any(ConsistencyConfiguration conf).uniqueParameterNodeAtPositionExclude(c, pos, p) and
-    isParameterNode(p, c, pos) and
-    not exists(unique(Node p0 | isParameterNode(p0, c, pos))) and
-    msg = "Parameters with overlapping positions."
-  }
-
-  query predicate uniqueParameterNodePosition(
-    DataFlowCallable c, ParameterPosition pos, Node p, string msg
-  ) {
-    not any(ConsistencyConfiguration conf).uniqueParameterNodePositionExclude(c, pos, p) and
-    isParameterNode(p, c, pos) and
-    not exists(unique(ParameterPosition pos0 | isParameterNode(p, c, pos0))) and
-    msg = "Parameter node with multiple positions."
-  }
-
-  query predicate uniqueContentApprox(Content c, string msg) {
-    not exists(unique(ContentApprox approx | approx = getContentApprox(c))) and
-    msg = "Non-unique content approximation."
-  }
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImplSpecific.qll

@@ -1,11 +0,0 @@
-/**
- * Provides IR-specific definitions for use in the data flow library.
- */
-module Private {
-  import DataFlowPrivate
-  import DataFlowDispatch
-}
-
-module Public {
-  import DataFlowUtil
-}

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

@@ -1,567 +0,0 @@
-private import cpp as Cpp
-private import DataFlowUtil
-private import semmle.code.cpp.ir.IR
-private import DataFlowDispatch
-private import DataFlowImplConsistency
-private import semmle.code.cpp.ir.internal.IRCppLanguage
-private import SsaInternals as Ssa
-
-/** Gets the callable in which this node occurs. */
-DataFlowCallable nodeGetEnclosingCallable(Node n) { result = n.getEnclosingCallable() }
-
-/** Holds if `p` is a `ParameterNode` of `c` with position `pos`. */
-predicate isParameterNode(ParameterNode p, DataFlowCallable c, ParameterPosition pos) {
-  p.isParameterOf(c, pos)
-}
-
-/** Holds if `arg` is an `ArgumentNode` of `c` with position `pos`. */
-predicate isArgumentNode(ArgumentNode arg, DataFlowCall c, ArgumentPosition pos) {
-  arg.argumentOf(c, pos)
-}
-
-/**
- * A data flow node that occurs as the argument of a call and is passed as-is
- * to the callable. Instance arguments (`this` pointer) and read side effects
- * on parameters are also included.
- */
-abstract class ArgumentNode extends Node {
-  /**
-   * Holds if this argument occurs at the given position in the given call.
-   * The instance argument is considered to have index `-1`.
-   */
-  abstract predicate argumentOf(DataFlowCall call, ArgumentPosition pos);
-
-  /** Gets the call in which this node is an argument. */
-  DataFlowCall getCall() { this.argumentOf(result, _) }
-}
-
-/**
- * A data flow node that occurs as the argument to a call, or an
- * implicit `this` pointer argument.
- */
-private class PrimaryArgumentNode extends ArgumentNode, OperandNode {
-  override ArgumentOperand op;
-
-  PrimaryArgumentNode() { exists(CallInstruction call | op = call.getAnArgumentOperand()) }
-
-  override predicate argumentOf(DataFlowCall call, ArgumentPosition pos) {
-    op = call.getArgumentOperand(pos.(DirectPosition).getIndex())
-  }
-
-  override string toStringImpl() { result = argumentOperandToString(op) }
-}
-
-private string argumentOperandToString(ArgumentOperand op) {
-  exists(Expr unconverted |
-    unconverted = op.getDef().getUnconvertedResultExpression() and
-    result = unconverted.toString()
-  )
-  or
-  // Certain instructions don't map to an unconverted result expression. For these cases
-  // we fall back to a simpler naming scheme. This can happen in IR-generated constructors.
-  not exists(op.getDef().getUnconvertedResultExpression()) and
-  (
-    result = "Argument " + op.(PositionalArgumentOperand).getIndex()
-    or
-    op instanceof ThisArgumentOperand and result = "Argument this"
-  )
-}
-
-private class SideEffectArgumentNode extends ArgumentNode, SideEffectOperandNode {
-  override predicate argumentOf(DataFlowCall dfCall, ArgumentPosition pos) {
-    this.getCallInstruction() = dfCall and
-    pos.(IndirectionPosition).getArgumentIndex() = this.getArgumentIndex() and
-    pos.(IndirectionPosition).getIndirectionIndex() = super.getIndirectionIndex()
-  }
-
-  override string toStringImpl() {
-    result = argumentOperandToString(this.getAddressOperand()) + " indirection"
-  }
-}
-
-/** A parameter position represented by an integer. */
-class ParameterPosition = Position;
-
-/** An argument position represented by an integer. */
-class ArgumentPosition = Position;
-
-class Position extends TPosition {
-  abstract string toString();
-}
-
-class DirectPosition extends Position, TDirectPosition {
-  int index;
-
-  DirectPosition() { this = TDirectPosition(index) }
-
-  override string toString() { if index = -1 then result = "this" else result = index.toString() }
-
-  int getIndex() { result = index }
-}
-
-class IndirectionPosition extends Position, TIndirectionPosition {
-  int argumentIndex;
-  int indirectionIndex;
-
-  IndirectionPosition() { this = TIndirectionPosition(argumentIndex, indirectionIndex) }
-
-  override string toString() {
-    if argumentIndex = -1
-    then if indirectionIndex > 0 then result = "this indirection" else result = "this"
-    else
-      if indirectionIndex > 0
-      then result = argumentIndex.toString() + " indirection"
-      else result = argumentIndex.toString()
-  }
-
-  int getArgumentIndex() { result = argumentIndex }
-
-  int getIndirectionIndex() { result = indirectionIndex }
-}
-
-newtype TPosition =
-  TDirectPosition(int index) { exists(any(CallInstruction c).getArgument(index)) } or
-  TIndirectionPosition(int argumentIndex, int indirectionIndex) {
-    hasOperandAndIndex(_, any(CallInstruction call).getArgumentOperand(argumentIndex),
-      indirectionIndex)
-  }
-
-private newtype TReturnKind =
-  TNormalReturnKind(int index) {
-    exists(IndirectReturnNode return |
-      return.getAddressOperand() = any(ReturnValueInstruction r).getReturnAddressOperand() and
-      index = return.getIndirectionIndex() - 1 // We subtract one because the return loads the value.
-    )
-  } or
-  TIndirectReturnKind(int argumentIndex, int indirectionIndex) {
-    exists(IndirectReturnNode return, ReturnIndirectionInstruction returnInd |
-      returnInd.hasIndex(argumentIndex) and
-      return.getAddressOperand() = returnInd.getSourceAddressOperand() and
-      indirectionIndex = return.getIndirectionIndex()
-    )
-  }
-
-/**
- * A return kind. A return kind describes how a value can be returned
- * from a callable. For C++, this is simply a function return.
- */
-class ReturnKind extends TReturnKind {
-  /** Gets a textual representation of this return kind. */
-  abstract string toString();
-}
-
-private class NormalReturnKind extends ReturnKind, TNormalReturnKind {
-  int index;
-
-  NormalReturnKind() { this = TNormalReturnKind(index) }
-
-  override string toString() { result = "indirect return" }
-}
-
-private class IndirectReturnKind extends ReturnKind, TIndirectReturnKind {
-  int argumentIndex;
-  int indirectionIndex;
-
-  IndirectReturnKind() { this = TIndirectReturnKind(argumentIndex, indirectionIndex) }
-
-  override string toString() { result = "indirect outparam[" + argumentIndex.toString() + "]" }
-}
-
-/** A data flow node that occurs as the result of a `ReturnStmt`. */
-class ReturnNode extends Node instanceof IndirectReturnNode {
-  /** Gets the kind of this returned value. */
-  abstract ReturnKind getKind();
-}
-
-/**
- * This predicate represents an annoying hack that we have to do. We use the
- * `ReturnIndirectionInstruction` to determine which variables need flow back
- * out of a function. However, the IR will unconditionally create those for a
- * variable passed to a function even though the variable was never updated by
- * the function. And if a function has too many `ReturnNode`s the dataflow
- * library lowers its precision for that function by disabling field flow.
- *
- * So we those eliminate `ReturnNode`s that would have otherwise been created
- * by this unconditional `ReturnIndirectionInstruction` by requiring that there
- * must exist an SSA definition of the IR variable in the function.
- */
-private predicate hasNonInitializeParameterDef(IRVariable v) {
-  exists(Ssa::Def def |
-    not def.getDefiningInstruction() instanceof InitializeParameterInstruction and
-    v = def.getSourceVariable().getBaseVariable().(Ssa::BaseIRVariable).getIRVariable()
-  )
-}
-
-class ReturnIndirectionNode extends IndirectReturnNode, ReturnNode {
-  override ReturnKind getKind() {
-    exists(int argumentIndex, ReturnIndirectionInstruction returnInd |
-      returnInd.hasIndex(argumentIndex) and
-      this.getAddressOperand() = returnInd.getSourceAddressOperand() and
-      result = TIndirectReturnKind(argumentIndex, this.getIndirectionIndex()) and
-      hasNonInitializeParameterDef(returnInd.getIRVariable())
-    )
-    or
-    this.getAddressOperand() = any(ReturnValueInstruction r).getReturnAddressOperand() and
-    result = TNormalReturnKind(this.getIndirectionIndex() - 1)
-  }
-}
-
-private Operand fullyConvertedCallStep(Operand op) {
-  not exists(getANonConversionUse(op)) and
-  exists(Instruction instr |
-    conversionFlow(op, instr, _) and
-    result = getAUse(instr)
-  )
-}
-
-/**
- * Gets the instruction that uses this operand, if the instruction is not
- * ignored for dataflow purposes.
- */
-private Instruction getUse(Operand op) {
-  result = op.getUse() and
-  not Ssa::ignoreOperand(op)
-}
-
-/** Gets a use of the instruction `instr` that is not ignored for dataflow purposes. */
-Operand getAUse(Instruction instr) {
-  result = instr.getAUse() and
-  not Ssa::ignoreOperand(result)
-}
-
-/**
- * Gets a use of `operand` that is:
- * - not ignored for dataflow purposes, and
- * - not a conversion-like instruction.
- */
-private Instruction getANonConversionUse(Operand operand) {
-  result = getUse(operand) and
-  not conversionFlow(_, result, _)
-}
-
-/**
- * Gets the operand that represents the first use of the value of `call` following
- * a sequence of conversion-like instructions.
- */
-predicate operandForfullyConvertedCall(Operand operand, CallInstruction call) {
-  exists(getANonConversionUse(operand)) and
-  (
-    operand = getAUse(call)
-    or
-    operand = fullyConvertedCallStep*(getAUse(call))
-  )
-}
-
-/**
- * Gets the instruction that represents the first use of the value of `call` following
- * a sequence of conversion-like instructions.
- *
- * This predicate only holds if there is no suitable operand (i.e., no operand of a non-
- * conversion instruction) to use to represent the value of `call` after conversions.
- */
-predicate instructionForfullyConvertedCall(Instruction instr, CallInstruction call) {
-  not operandForfullyConvertedCall(_, call) and
-  (
-    // If there is no use of the call then we pick the call instruction
-    not exists(getAUse(call)) and
-    instr = call
-    or
-    // Otherwise, flow to the first non-conversion use.
-    exists(Operand operand | operand = fullyConvertedCallStep*(getAUse(call)) |
-      instr = getANonConversionUse(operand)
-    )
-  )
-}
-
-/** Holds if `node` represents the output node for `call`. */
-private predicate simpleOutNode(Node node, CallInstruction call) {
-  operandForfullyConvertedCall(node.asOperand(), call)
-  or
-  instructionForfullyConvertedCall(node.asInstruction(), call)
-}
-
-/** A data flow node that represents the output of a call. */
-class OutNode extends Node {
-  OutNode() {
-    // Return values not hidden behind indirections
-    simpleOutNode(this, _)
-    or
-    // Return values hidden behind indirections
-    this instanceof IndirectReturnOutNode
-    or
-    // Modified arguments hidden behind indirections
-    this instanceof IndirectArgumentOutNode
-  }
-
-  /** Gets the underlying call. */
-  abstract DataFlowCall getCall();
-
-  abstract ReturnKind getReturnKind();
-}
-
-private class DirectCallOutNode extends OutNode {
-  CallInstruction call;
-
-  DirectCallOutNode() { simpleOutNode(this, call) }
-
-  override DataFlowCall getCall() { result = call }
-
-  override ReturnKind getReturnKind() { result = TNormalReturnKind(0) }
-}
-
-private class IndirectCallOutNode extends OutNode, IndirectReturnOutNode {
-  override DataFlowCall getCall() { result = this.getCallInstruction() }
-
-  override ReturnKind getReturnKind() { result = TNormalReturnKind(this.getIndirectionIndex()) }
-}
-
-private class SideEffectOutNode extends OutNode, IndirectArgumentOutNode {
-  override DataFlowCall getCall() { result = this.getCallInstruction() }
-
-  override ReturnKind getReturnKind() {
-    result = TIndirectReturnKind(this.getArgumentIndex(), this.getIndirectionIndex())
-  }
-}
-
-/**
- * Gets a node that can read the value returned from `call` with return kind
- * `kind`.
- */
-OutNode getAnOutNode(DataFlowCall call, ReturnKind kind) {
-  result.getCall() = call and
-  result.getReturnKind() = kind
-}
-
-/**
- * Holds if data can flow from `node1` to `node2` in a way that loses the
- * calling context. For example, this would happen with flow through a
- * global or static variable.
- */
-predicate jumpStep(Node n1, Node n2) {
-  exists(Cpp::GlobalOrNamespaceVariable v |
-    v =
-      n1.asInstruction()
-          .(StoreInstruction)
-          .getResultAddress()
-          .(VariableAddressInstruction)
-          .getAstVariable() and
-    v = n2.asVariable()
-    or
-    v =
-      n2.asInstruction()
-          .(LoadInstruction)
-          .getSourceAddress()
-          .(VariableAddressInstruction)
-          .getAstVariable() and
-    v = n1.asVariable()
-  )
-}
-
-/**
- * Holds if data can flow from `node1` to `node2` via an assignment to `f`.
- * Thus, `node2` references an object with a field `f` that contains the
- * value of `node1`.
- */
-predicate storeStep(Node node1, Content c, PostFieldUpdateNode node2) {
-  exists(int indirectionIndex1, int numberOfLoads, StoreInstruction store |
-    nodeHasInstruction(node1, store, pragma[only_bind_into](indirectionIndex1)) and
-    node2.getIndirectionIndex() = 1 and
-    numberOfLoadsFromOperand(node2.getFieldAddress(), store.getDestinationAddressOperand(),
-      numberOfLoads)
-  |
-    exists(FieldContent fc | fc = c |
-      fc.getField() = node2.getUpdatedField() and
-      fc.getIndirectionIndex() = 1 + indirectionIndex1 + numberOfLoads
-    )
-    or
-    exists(UnionContent uc | uc = c |
-      uc.getAField() = node2.getUpdatedField() and
-      uc.getIndirectionIndex() = 1 + indirectionIndex1 + numberOfLoads
-    )
-  )
-}
-
-/**
- * Holds if `operandFrom` flows to `operandTo` using a sequence of conversion-like
- * operations and exactly `n` `LoadInstruction` operations.
- */
-private predicate numberOfLoadsFromOperandRec(Operand operandFrom, Operand operandTo, int ind) {
-  exists(LoadInstruction load | load.getSourceAddressOperand() = operandFrom |
-    operandTo = operandFrom and ind = 0
-    or
-    numberOfLoadsFromOperand(load.getAUse(), operandTo, ind - 1)
-  )
-  or
-  exists(Operand op, Instruction instr |
-    instr = op.getDef() and
-    conversionFlow(operandFrom, instr, _) and
-    numberOfLoadsFromOperand(op, operandTo, ind)
-  )
-}
-
-/**
- * Holds if `operandFrom` flows to `operandTo` using a sequence of conversion-like
- * operations and exactly `n` `LoadInstruction` operations.
- */
-private predicate numberOfLoadsFromOperand(Operand operandFrom, Operand operandTo, int n) {
-  numberOfLoadsFromOperandRec(operandFrom, operandTo, n)
-  or
-  not any(LoadInstruction load).getSourceAddressOperand() = operandFrom and
-  not conversionFlow(operandFrom, _, _) and
-  operandFrom = operandTo and
-  n = 0
-}
-
-// Needed to join on both an operand and an index at the same time.
-pragma[noinline]
-predicate nodeHasOperand(Node node, Operand operand, int indirectionIndex) {
-  node.asOperand() = operand and indirectionIndex = 0
-  or
-  hasOperandAndIndex(node, operand, indirectionIndex)
-}
-
-// Needed to join on both an instruction and an index at the same time.
-pragma[noinline]
-predicate nodeHasInstruction(Node node, Instruction instr, int indirectionIndex) {
-  node.asInstruction() = instr and indirectionIndex = 0
-  or
-  hasInstructionAndIndex(node, instr, indirectionIndex)
-}
-
-/**
- * Holds if data can flow from `node1` to `node2` via a read of `f`.
- * Thus, `node1` references an object with a field `f` whose value ends up in
- * `node2`.
- */
-predicate readStep(Node node1, Content c, Node node2) {
-  exists(FieldAddress fa1, Operand operand, int numberOfLoads, int indirectionIndex2 |
-    nodeHasOperand(node2, operand, indirectionIndex2) and
-    nodeHasOperand(node1, fa1.getObjectAddressOperand(), _) and
-    numberOfLoadsFromOperand(fa1, operand, numberOfLoads)
-  |
-    exists(FieldContent fc | fc = c |
-      fc.getField() = fa1.getField() and
-      fc.getIndirectionIndex() = indirectionIndex2 + numberOfLoads
-    )
-    or
-    exists(UnionContent uc | uc = c |
-      uc.getAField() = fa1.getField() and
-      uc.getIndirectionIndex() = indirectionIndex2 + numberOfLoads
-    )
-  )
-}
-
-/**
- * Holds if values stored inside content `c` are cleared at node `n`.
- */
-predicate clearsContent(Node n, Content c) {
-  none() // stub implementation
-}
-
-/**
- * Holds if the value that is being tracked is expected to be stored inside content `c`
- * at node `n`.
- */
-predicate expectsContent(Node n, ContentSet c) { none() }
-
-/** Gets the type of `n` used for type pruning. */
-DataFlowType getNodeType(Node n) {
-  suppressUnusedNode(n) and
-  result instanceof VoidType // stub implementation
-}
-
-/** Gets a string representation of a type returned by `getNodeType`. */
-string ppReprType(DataFlowType t) { none() } // stub implementation
-
-/**
- * Holds if `t1` and `t2` are compatible, that is, whether data can flow from
- * a node of type `t1` to a node of type `t2`.
- */
-pragma[inline]
-predicate compatibleTypes(DataFlowType t1, DataFlowType t2) {
-  any() // stub implementation
-}
-
-private predicate suppressUnusedNode(Node n) { any() }
-
-//////////////////////////////////////////////////////////////////////////////
-// Java QL library compatibility wrappers
-//////////////////////////////////////////////////////////////////////////////
-/** A node that performs a type cast. */
-class CastNode extends Node {
-  CastNode() { none() } // stub implementation
-}
-
-/**
- * A function that may contain code or a variable that may contain itself. When
- * flow crosses from one _enclosing callable_ to another, the interprocedural
- * data-flow library discards call contexts and inserts a node in the big-step
- * relation used for human-readable path explanations.
- */
-class DataFlowCallable = Cpp::Declaration;
-
-class DataFlowExpr = Expr;
-
-class DataFlowType = Type;
-
-/** A function call relevant for data flow. */
-class DataFlowCall extends CallInstruction {
-  Function getEnclosingCallable() { result = this.getEnclosingFunction() }
-}
-
-predicate isUnreachableInCall(Node n, DataFlowCall call) { none() } // stub implementation
-
-int accessPathLimit() { result = 5 }
-
-/**
- * Holds if access paths with `c` at their head always should be tracked at high
- * precision. This disables adaptive access path precision for such access paths.
- */
-predicate forceHighPrecision(Content c) { none() }
-
-/** The unit type. */
-private newtype TUnit = TMkUnit()
-
-/** The trivial type with a single element. */
-class Unit extends TUnit {
-  /** Gets a textual representation of this element. */
-  string toString() { result = "unit" }
-}
-
-/** Holds if `n` should be hidden from path explanations. */
-predicate nodeIsHidden(Node n) { n instanceof OperandNode and not n instanceof ArgumentNode }
-
-class LambdaCallKind = Unit;
-
-/** Holds if `creation` is an expression that creates a lambda of kind `kind` for `c`. */
-predicate lambdaCreation(Node creation, LambdaCallKind kind, DataFlowCallable c) { none() }
-
-/** Holds if `call` is a lambda call of kind `kind` where `receiver` is the lambda expression. */
-predicate lambdaCall(DataFlowCall call, LambdaCallKind kind, Node receiver) { none() }
-
-/** Extra data-flow steps needed for lambda flow analysis. */
-predicate additionalLambdaFlowStep(Node nodeFrom, Node nodeTo, boolean preservesValue) { none() }
-
-/**
- * Holds if flow is allowed to pass from parameter `p` and back to itself as a
- * side-effect, resulting in a summary from `p` to itself.
- *
- * One example would be to allow flow like `p.foo = p.bar;`, which is disallowed
- * by default as a heuristic.
- */
-predicate allowParameterReturnInSelf(ParameterNode p) { none() }
-
-/** An approximated `Content`. */
-class ContentApprox = Unit;
-
-/** Gets an approximated value for content `c`. */
-pragma[inline]
-ContentApprox getContentApprox(Content c) { any() }
-
-private class MyConsistencyConfiguration extends Consistency::ConsistencyConfiguration {
-  override predicate argHasPostUpdateExclude(ArgumentNode n) {
-    // The rules for whether an IR argument gets a post-update node are too
-    // complex to model here.
-    any()
-  }
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/ModelUtil.qll

@@ -1,93 +0,0 @@
-/**
- * Provides predicates for mapping the `FunctionInput` and `FunctionOutput`
- * classes used in function models to the corresponding instructions.
- */
-
-private import semmle.code.cpp.ir.IR
-private import experimental.semmle.code.cpp.ir.dataflow.DataFlow
-private import experimental.semmle.code.cpp.ir.dataflow.internal.DataFlowUtil
-private import SsaInternals as Ssa
-
-/**
- * Gets the instruction that goes into `input` for `call`.
- */
-DataFlow::Node callInput(CallInstruction call, FunctionInput input) {
-  // An argument or qualifier
-  exists(int index |
-    result.asOperand() = call.getArgumentOperand(index) and
-    input.isParameterOrQualifierAddress(index)
-  )
-  or
-  // A value pointed to by an argument or qualifier
-  exists(int index, int indirectionIndex |
-    hasOperandAndIndex(result, call.getArgumentOperand(index), indirectionIndex) and
-    input.isParameterDerefOrQualifierObject(index, indirectionIndex)
-  )
-  or
-  exists(int ind |
-    result = getIndirectReturnOutNode(call, ind) and
-    input.isReturnValueDeref(ind)
-  )
-}
-
-/**
- * Gets the instruction that holds the `output` for `call`.
- */
-Node callOutput(CallInstruction call, FunctionOutput output) {
-  // The return value
-  result.asInstruction() = call and
-  output.isReturnValue()
-  or
-  // The side effect of a call on the value pointed to by an argument or qualifier
-  exists(int index, int indirectionIndex |
-    result.(IndirectArgumentOutNode).getArgumentIndex() = index and
-    result.(IndirectArgumentOutNode).getIndirectionIndex() = indirectionIndex and
-    result.(IndirectArgumentOutNode).getCallInstruction() = call and
-    output.isParameterDerefOrQualifierObject(index, indirectionIndex)
-  )
-  or
-  exists(int ind |
-    result = getIndirectReturnOutNode(call, ind) and
-    output.isReturnValueDeref(ind)
-  )
-}
-
-DataFlow::Node callInput(CallInstruction call, FunctionInput input, int d) {
-  exists(DataFlow::Node n | n = callInput(call, input) and d > 0 |
-    // An argument or qualifier
-    hasOperandAndIndex(result, n.asOperand(), d)
-    or
-    exists(Operand operand, int indirectionIndex |
-      // A value pointed to by an argument or qualifier
-      hasOperandAndIndex(n, operand, indirectionIndex) and
-      hasOperandAndIndex(result, operand, indirectionIndex + d)
-    )
-  )
-}
-
-private IndirectReturnOutNode getIndirectReturnOutNode(CallInstruction call, int d) {
-  result.getCallInstruction() = call and
-  result.getIndirectionIndex() = d
-}
-
-/**
- * Gets the instruction that holds the `output` for `call`.
- */
-bindingset[d]
-Node callOutput(CallInstruction call, FunctionOutput output, int d) {
-  exists(DataFlow::Node n | n = callOutput(call, output) and d > 0 |
-    // The return value
-    result = getIndirectReturnOutNode(n.asInstruction(), d)
-    or
-    // If there isn't an indirect out node for the call with indirection `d` then
-    // we conflate this with the underlying `CallInstruction`.
-    not exists(getIndirectReturnOutNode(call, d)) and
-    n.asInstruction() = result.asInstruction()
-    or
-    // The side effect of a call on the value pointed to by an argument or qualifier
-    exists(Operand operand, int indirectionIndex |
-      Ssa::outNodeHasAddressAndIndex(n, operand, indirectionIndex) and
-      Ssa::outNodeHasAddressAndIndex(result, operand, indirectionIndex + d)
-    )
-  )
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/PrintIRLocalFlow.qll

@@ -1,136 +0,0 @@
-private import cpp
-// The `ValueNumbering` library has to be imported right after `cpp` to ensure
-// that the cached IR gets the same checksum here as it does in queries that use
-// `ValueNumbering` without `DataFlow`.
-private import semmle.code.cpp.ir.ValueNumbering
-private import semmle.code.cpp.ir.IR
-private import semmle.code.cpp.ir.dataflow.DataFlow
-private import semmle.code.cpp.ir.dataflow.internal.DataFlowUtil
-private import PrintIRUtilities
-
-/**
- * Gets the local dataflow from other nodes in the same function to this node.
- */
-private string getFromFlow(DataFlow::Node useNode, int order1, int order2) {
-  exists(DataFlow::Node defNode, string prefix |
-    (
-      simpleLocalFlowStep(defNode, useNode) and prefix = ""
-      or
-      any(DataFlow::Configuration cfg).isAdditionalFlowStep(defNode, useNode) and
-      defNode.getEnclosingCallable() = useNode.getEnclosingCallable() and
-      prefix = "+"
-    ) and
-    if defNode.asInstruction() = useNode.asOperand().getAnyDef()
-    then
-      // Shorthand for flow from the def of this operand.
-      result = prefix + "def" and
-      order1 = -1 and
-      order2 = 0
-    else
-      if defNode.asOperand().getUse() = useNode.asInstruction()
-      then
-        // Shorthand for flow from an operand of this instruction
-        result = prefix + defNode.asOperand().getDumpId() and
-        order1 = -1 and
-        order2 = defNode.asOperand().getDumpSortOrder()
-      else result = prefix + nodeId(defNode, order1, order2)
-  )
-}
-
-/**
- * Gets the local dataflow from this node to other nodes in the same function.
- */
-private string getToFlow(DataFlow::Node defNode, int order1, int order2) {
-  exists(DataFlow::Node useNode, string prefix |
-    (
-      simpleLocalFlowStep(defNode, useNode) and prefix = ""
-      or
-      any(DataFlow::Configuration cfg).isAdditionalFlowStep(defNode, useNode) and
-      defNode.getEnclosingCallable() = useNode.getEnclosingCallable() and
-      prefix = "+"
-    ) and
-    if useNode.asInstruction() = defNode.asOperand().getUse()
-    then
-      // Shorthand for flow to this operand's instruction.
-      result = prefix + "result" and
-      order1 = -1 and
-      order2 = 0
-    else result = prefix + nodeId(useNode, order1, order2)
-  )
-}
-
-/**
- * Gets the properties of the dataflow node `node`.
- */
-private string getNodeProperty(DataFlow::Node node, string key) {
-  // List dataflow into and out of this node. Flow into this node is printed as `src->@`, and flow
-  // out of this node is printed as `@->dest`.
-  key = "flow" and
-  result =
-    strictconcat(string flow, boolean to, int order1, int order2 |
-      flow = getFromFlow(node, order1, order2) + "->@" and to = false
-      or
-      flow = "@->" + getToFlow(node, order1, order2) and to = true
-    |
-      flow, ", " order by to, order1, order2, flow
-    )
-  or
-  // Is this node a dataflow sink?
-  key = "sink" and
-  any(DataFlow::Configuration cfg).isSink(node) and
-  result = "true"
-  or
-  // Is this node a dataflow source?
-  key = "source" and
-  any(DataFlow::Configuration cfg).isSource(node) and
-  result = "true"
-  or
-  // Is this node a dataflow barrier, and if so, what kind?
-  key = "barrier" and
-  result =
-    strictconcat(string kind |
-      any(DataFlow::Configuration cfg).isBarrier(node) and kind = "full"
-      or
-      any(DataFlow::Configuration cfg).isBarrierIn(node) and kind = "in"
-      or
-      any(DataFlow::Configuration cfg).isBarrierOut(node) and kind = "out"
-    |
-      kind, ", "
-    )
-  or
-  // Is there partial flow from a source to this node?
-  // This property will only be emitted if partial flow is enabled by overriding
-  // `DataFlow::Configuration::explorationLimit()`.
-  key = "pflow" and
-  result =
-    strictconcat(DataFlow::PartialPathNode sourceNode, DataFlow::PartialPathNode destNode, int dist,
-      int order1, int order2 |
-      any(DataFlow::Configuration cfg).hasPartialFlow(sourceNode, destNode, dist) and
-      destNode.getNode() = node and
-      // Only print flow from a source in the same function.
-      sourceNode.getNode().getEnclosingCallable() = node.getEnclosingCallable()
-    |
-      nodeId(sourceNode.getNode(), order1, order2) + "+" + dist.toString(), ", "
-      order by
-        order1, order2, dist desc
-    )
-}
-
-/**
- * Property provider for local IR dataflow.
- */
-class LocalFlowPropertyProvider extends IRPropertyProvider {
-  override string getOperandProperty(Operand operand, string key) {
-    exists(DataFlow::Node node |
-      operand = node.asOperand() and
-      result = getNodeProperty(node, key)
-    )
-  }
-
-  override string getInstructionProperty(Instruction instruction, string key) {
-    exists(DataFlow::Node node |
-      instruction = node.asInstruction() and
-      result = getNodeProperty(node, key)
-    )
-  }
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/PrintIRStoreSteps.qll

@@ -1,33 +0,0 @@
-/**
- * Print the dataflow local store steps in IR dumps.
- */
-
-private import cpp
-// The `ValueNumbering` library has to be imported right after `cpp` to ensure
-// that the cached IR gets the same checksum here as it does in queries that use
-// `ValueNumbering` without `DataFlow`.
-private import semmle.code.cpp.ir.ValueNumbering
-private import semmle.code.cpp.ir.IR
-private import semmle.code.cpp.ir.dataflow.DataFlow
-private import semmle.code.cpp.ir.dataflow.internal.DataFlowUtil
-private import semmle.code.cpp.ir.dataflow.internal.DataFlowPrivate
-private import PrintIRUtilities
-
-/**
- * Property provider for local IR dataflow store steps.
- */
-class LocalFlowPropertyProvider extends IRPropertyProvider {
-  override string getInstructionProperty(Instruction instruction, string key) {
-    exists(DataFlow::Node objectNode, Content content |
-      key = "content[" + content.toString() + "]" and
-      instruction = objectNode.asInstruction() and
-      result =
-        strictconcat(string element, DataFlow::Node fieldNode |
-          storeStep(fieldNode, content, objectNode) and
-          element = nodeId(fieldNode, _, _)
-        |
-          element, ", "
-        )
-    )
-  }
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/PrintIRUtilities.qll

@@ -1,39 +0,0 @@
-/**
- * Shared utilities used when printing dataflow annotations in IR dumps.
- */
-
-private import cpp
-// The `ValueNumbering` library has to be imported right after `cpp` to ensure
-// that the cached IR gets the same checksum here as it does in queries that use
-// `ValueNumbering` without `DataFlow`.
-private import semmle.code.cpp.ir.ValueNumbering
-private import semmle.code.cpp.ir.IR
-private import semmle.code.cpp.ir.dataflow.DataFlow
-
-/**
- * Gets a short ID for an IR dataflow node.
- * - For `Instruction`s, this is just the result ID of the instruction (e.g. `m128`).
- * - For `Operand`s, this is the label of the operand, prefixed with the result ID of the
- *   instruction and a dot (e.g. `m128.left`).
- * - For `Variable`s, this is the qualified name of the variable.
- */
-string nodeId(DataFlow::Node node, int order1, int order2) {
-  exists(Instruction instruction | instruction = node.asInstruction() |
-    result = instruction.getResultId() and
-    order1 = instruction.getBlock().getDisplayIndex() and
-    order2 = instruction.getDisplayIndexInBlock()
-  )
-  or
-  exists(Operand operand, Instruction instruction |
-    operand = node.asOperand() and
-    instruction = operand.getUse()
-  |
-    result = instruction.getResultId() + "." + operand.getDumpId() and
-    order1 = instruction.getBlock().getDisplayIndex() and
-    order2 = instruction.getDisplayIndexInBlock()
-  )
-  or
-  result = "var(" + node.asVariable().getQualifiedName() + ")" and
-  order1 = 1000000 and
-  order2 = 0
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/SsaInternals.qll

@@ -1,552 +0,0 @@
-private import codeql.ssa.Ssa as SsaImplCommon
-private import semmle.code.cpp.ir.IR
-private import DataFlowUtil
-private import DataFlowImplCommon as DataFlowImplCommon
-private import semmle.code.cpp.models.interfaces.Allocation as Alloc
-private import semmle.code.cpp.models.interfaces.DataFlow as DataFlow
-private import semmle.code.cpp.ir.internal.IRCppLanguage
-private import DataFlowPrivate
-private import ssa0.SsaInternals as SsaInternals0
-import SsaInternalsCommon
-
-private module SourceVariables {
-  int getMaxIndirectionForIRVariable(IRVariable var) {
-    exists(Type type, boolean isGLValue |
-      var.getLanguageType().hasType(type, isGLValue) and
-      if isGLValue = true
-      then result = 1 + getMaxIndirectionsForType(type)
-      else result = getMaxIndirectionsForType(type)
-    )
-  }
-
-  class BaseSourceVariable = SsaInternals0::BaseSourceVariable;
-
-  class BaseIRVariable = SsaInternals0::BaseIRVariable;
-
-  class BaseCallVariable = SsaInternals0::BaseCallVariable;
-
-  cached
-  private newtype TSourceVariable =
-    TSourceIRVariable(BaseIRVariable baseVar, int ind) {
-      ind = [0 .. getMaxIndirectionForIRVariable(baseVar.getIRVariable())]
-    } or
-    TCallVariable(AllocationInstruction call, int ind) {
-      ind = [0 .. countIndirectionsForCppType(getResultLanguageType(call))]
-    }
-
-  abstract class SourceVariable extends TSourceVariable {
-    int ind;
-
-    bindingset[ind]
-    SourceVariable() { any() }
-
-    abstract string toString();
-
-    int getIndirection() { result = ind }
-
-    abstract BaseSourceVariable getBaseVariable();
-  }
-
-  class SourceIRVariable extends SourceVariable, TSourceIRVariable {
-    BaseIRVariable var;
-
-    SourceIRVariable() { this = TSourceIRVariable(var, ind) }
-
-    IRVariable getIRVariable() { result = var.getIRVariable() }
-
-    override BaseIRVariable getBaseVariable() { result.getIRVariable() = this.getIRVariable() }
-
-    override string toString() {
-      ind = 0 and
-      result = this.getIRVariable().toString()
-      or
-      ind > 0 and
-      result = this.getIRVariable().toString() + " indirection"
-    }
-  }
-
-  class CallVariable extends SourceVariable, TCallVariable {
-    AllocationInstruction call;
-
-    CallVariable() { this = TCallVariable(call, ind) }
-
-    AllocationInstruction getCall() { result = call }
-
-    override BaseCallVariable getBaseVariable() { result.getCallInstruction() = call }
-
-    override string toString() {
-      ind = 0 and
-      result = "Call"
-      or
-      ind > 0 and
-      result = "Call indirection"
-    }
-  }
-}
-
-import SourceVariables
-
-predicate hasIndirectOperand(Operand op, int indirectionIndex) {
-  exists(CppType type, int m |
-    not ignoreOperand(op) and
-    type = getLanguageType(op) and
-    m = countIndirectionsForCppType(type) and
-    indirectionIndex = [1 .. m]
-  )
-}
-
-predicate hasIndirectInstruction(Instruction instr, int indirectionIndex) {
-  exists(CppType type, int m |
-    not ignoreInstruction(instr) and
-    type = getResultLanguageType(instr) and
-    m = countIndirectionsForCppType(type) and
-    indirectionIndex = [1 .. m]
-  )
-}
-
-cached
-private newtype TDefOrUseImpl =
-  TDefImpl(Operand address, int indirectionIndex) {
-    isDef(_, _, address, _, _, indirectionIndex) and
-    // We only include the definition if the SSA pruning stage
-    // concluded that the definition is live after the write.
-    any(SsaInternals0::Def def).getAddressOperand() = address
-  } or
-  TUseImpl(Operand operand, int indirectionIndex) {
-    isUse(_, operand, _, _, indirectionIndex) and
-    not isDef(_, _, operand, _, _, _)
-  }
-
-abstract private class DefOrUseImpl extends TDefOrUseImpl {
-  /** Gets a textual representation of this element. */
-  abstract string toString();
-
-  /** Gets the block of this definition or use. */
-  abstract IRBlock getBlock();
-
-  /** Holds if this definition or use has index `index` in block `block`. */
-  abstract predicate hasIndexInBlock(IRBlock block, int index);
-
-  final predicate hasIndexInBlock(IRBlock block, int index, SourceVariable sv) {
-    this.hasIndexInBlock(block, index) and
-    sv = this.getSourceVariable()
-  }
-
-  /** Gets the location of this element. */
-  abstract Cpp::Location getLocation();
-
-  /**
-   * Gets the index (i.e., the number of loads required) of this
-   * definition or use.
-   *
-   * Note that this is _not_ the definition's (or use's) index in
-   * the enclosing basic block. To obtain this index, use
-   * `DefOrUseImpl::hasIndexInBlock/2` or `DefOrUseImpl::hasIndexInBlock/3`.
-   */
-  abstract int getIndirectionIndex();
-
-  /**
-   * Gets the instruction that computes the base of this definition or use.
-   * This is always a `VariableAddressInstruction` or an `AllocationInstruction`.
-   */
-  abstract Instruction getBase();
-
-  final BaseSourceVariable getBaseSourceVariable() {
-    exists(IRVariable var |
-      result.(BaseIRVariable).getIRVariable() = var and
-      instructionHasIRVariable(this.getBase(), var)
-    )
-    or
-    result.(BaseCallVariable).getCallInstruction() = this.getBase()
-  }
-
-  /** Gets the variable that is defined or used. */
-  final SourceVariable getSourceVariable() {
-    exists(BaseSourceVariable v, int ind |
-      sourceVariableHasBaseAndIndex(result, v, ind) and
-      defOrUseHasSourceVariable(this, v, ind)
-    )
-  }
-}
-
-pragma[noinline]
-private predicate instructionHasIRVariable(VariableAddressInstruction vai, IRVariable var) {
-  vai.getIRVariable() = var
-}
-
-private predicate defOrUseHasSourceVariable(DefOrUseImpl defOrUse, BaseSourceVariable bv, int ind) {
-  defHasSourceVariable(defOrUse, bv, ind)
-  or
-  useHasSourceVariable(defOrUse, bv, ind)
-}
-
-pragma[noinline]
-private predicate defHasSourceVariable(DefImpl def, BaseSourceVariable bv, int ind) {
-  bv = def.getBaseSourceVariable() and
-  ind = def.getIndirection()
-}
-
-pragma[noinline]
-private predicate useHasSourceVariable(UseImpl use, BaseSourceVariable bv, int ind) {
-  bv = use.getBaseSourceVariable() and
-  ind = use.getIndirection()
-}
-
-pragma[noinline]
-private predicate sourceVariableHasBaseAndIndex(SourceVariable v, BaseSourceVariable bv, int ind) {
-  v.getBaseVariable() = bv and
-  v.getIndirection() = ind
-}
-
-class DefImpl extends DefOrUseImpl, TDefImpl {
-  Operand address;
-  int ind;
-
-  DefImpl() { this = TDefImpl(address, ind) }
-
-  override Instruction getBase() { isDef(_, _, address, result, _, _) }
-
-  Operand getAddressOperand() { result = address }
-
-  int getIndirection() { isDef(_, _, address, _, result, ind) }
-
-  override int getIndirectionIndex() { result = ind }
-
-  Instruction getDefiningInstruction() { isDef(_, result, address, _, _, _) }
-
-  override string toString() { result = "DefImpl" }
-
-  override IRBlock getBlock() { result = this.getDefiningInstruction().getBlock() }
-
-  override Cpp::Location getLocation() { result = this.getDefiningInstruction().getLocation() }
-
-  final override predicate hasIndexInBlock(IRBlock block, int index) {
-    this.getDefiningInstruction() = block.getInstruction(index)
-  }
-
-  predicate isCertain() { isDef(true, _, address, _, _, ind) }
-}
-
-class UseImpl extends DefOrUseImpl, TUseImpl {
-  Operand operand;
-  int ind;
-
-  UseImpl() { this = TUseImpl(operand, ind) }
-
-  Operand getOperand() { result = operand }
-
-  override string toString() { result = "UseImpl" }
-
-  final override predicate hasIndexInBlock(IRBlock block, int index) {
-    operand.getUse() = block.getInstruction(index)
-  }
-
-  final override IRBlock getBlock() { result = operand.getUse().getBlock() }
-
-  final override Cpp::Location getLocation() { result = operand.getLocation() }
-
-  final int getIndirection() { isUse(_, operand, _, result, ind) }
-
-  override int getIndirectionIndex() { result = ind }
-
-  override Instruction getBase() { isUse(_, operand, result, _, ind) }
-
-  predicate isCertain() { isUse(true, operand, _, _, ind) }
-}
-
-/**
- * Holds if `defOrUse1` is a definition which is first read by `use`,
- * or if `defOrUse1` is a use and `use` is a next subsequent use.
- *
- * In both cases, `use` can either be an explicit use written in the
- * source file, or it can be a phi node as computed by the SSA library.
- */
-predicate adjacentDefRead(DefOrUse defOrUse1, UseOrPhi use) {
-  exists(IRBlock bb1, int i1, SourceVariable v |
-    defOrUse1.asDefOrUse().hasIndexInBlock(bb1, i1, v)
-  |
-    exists(IRBlock bb2, int i2 |
-      adjacentDefRead(_, pragma[only_bind_into](bb1), pragma[only_bind_into](i1),
-        pragma[only_bind_into](bb2), pragma[only_bind_into](i2))
-    |
-      use.asDefOrUse().(UseImpl).hasIndexInBlock(bb2, i2, v)
-    )
-    or
-    exists(PhiNode phi |
-      lastRefRedef(_, bb1, i1, phi) and
-      use.asPhi() = phi and
-      phi.getSourceVariable() = pragma[only_bind_into](v)
-    )
-  )
-}
-
-private predicate useToNode(UseOrPhi use, Node nodeTo) {
-  exists(UseImpl useImpl |
-    useImpl = use.asDefOrUse() and
-    nodeHasOperand(nodeTo, useImpl.getOperand(), useImpl.getIndirectionIndex())
-  )
-  or
-  nodeTo.(SsaPhiNode).getPhiNode() = use.asPhi()
-}
-
-pragma[noinline]
-predicate outNodeHasAddressAndIndex(
-  IndirectArgumentOutNode out, Operand address, int indirectionIndex
-) {
-  out.getAddressOperand() = address and
-  out.getIndirectionIndex() = indirectionIndex
-}
-
-private predicate defToNode(Node nodeFrom, Def def) {
-  nodeHasInstruction(nodeFrom, def.getDefiningInstruction(), def.getIndirectionIndex())
-}
-
-/**
- * INTERNAL: Do not use.
- *
- * Holds if `nodeFrom` is the node that correspond to the definition or use `defOrUse`.
- */
-predicate nodeToDefOrUse(Node nodeFrom, SsaDefOrUse defOrUse) {
-  // Node -> Def
-  defToNode(nodeFrom, defOrUse)
-  or
-  // Node -> Use
-  useToNode(defOrUse, nodeFrom)
-}
-
-/**
- * Perform a single conversion-like step from `nFrom` to `nTo`. This relation
- * only holds when there is no use-use relation out of `nTo`.
- */
-private predicate indirectConversionFlowStep(Node nFrom, Node nTo) {
-  not exists(UseOrPhi defOrUse |
-    nodeToDefOrUse(nTo, defOrUse) and
-    adjacentDefRead(defOrUse, _)
-  ) and
-  exists(Operand op1, Operand op2, int indirectionIndex, Instruction instr |
-    hasOperandAndIndex(nFrom, op1, pragma[only_bind_into](indirectionIndex)) and
-    hasOperandAndIndex(nTo, op2, pragma[only_bind_into](indirectionIndex)) and
-    instr = op2.getDef() and
-    conversionFlow(op1, instr, _)
-  )
-}
-
-/**
- * The reason for this predicate is a bit annoying:
- * We cannot mark a `PointerArithmeticInstruction` that computes an offset based on some SSA
- * variable `x` as a use of `x` since this creates taint-flow in the following example:
- * ```c
- * int x = array[source]
- * sink(*array)
- * ```
- * This is because `source` would flow from the operand of `PointerArithmeticInstruction` to the
- * result of the instruction, and into the `IndirectOperand` that represents the value of `*array`.
- * Then, via use-use flow, flow will arrive at `*array` in `sink(*array)`.
- *
- * So this predicate recurses back along conversions and `PointerArithmeticInstruction`s to find the
- * first use that has provides use-use flow, and uses that target as the target of the `nodeFrom`.
- */
-private predicate adjustForPointerArith(Node nodeFrom, UseOrPhi use) {
-  nodeFrom = any(PostUpdateNode pun).getPreUpdateNode() and
-  exists(DefOrUse defOrUse, Node adjusted |
-    indirectConversionFlowStep*(adjusted, nodeFrom) and
-    nodeToDefOrUse(adjusted, defOrUse) and
-    adjacentDefRead(defOrUse, use)
-  )
-}
-
-/** Holds if there is def-use or use-use flow from `nodeFrom` to `nodeTo`. */
-predicate ssaFlow(Node nodeFrom, Node nodeTo) {
-  // `nodeFrom = any(PostUpdateNode pun).getPreUpdateNode()` is implied by adjustedForPointerArith.
-  exists(UseOrPhi use |
-    adjustForPointerArith(nodeFrom, use) and
-    useToNode(use, nodeTo)
-  )
-  or
-  not nodeFrom = any(PostUpdateNode pun).getPreUpdateNode() and
-  exists(DefOrUse defOrUse1, UseOrPhi use |
-    nodeToDefOrUse(nodeFrom, defOrUse1) and
-    adjacentDefRead(defOrUse1, use) and
-    useToNode(use, nodeTo)
-  )
-}
-
-/** Holds if `nodeTo` receives flow from the phi node `nodeFrom`. */
-predicate fromPhiNode(SsaPhiNode nodeFrom, Node nodeTo) {
-  exists(PhiNode phi, SourceVariable sv, IRBlock bb1, int i1, UseOrPhi use |
-    phi = nodeFrom.getPhiNode() and
-    phi.definesAt(sv, bb1, i1) and
-    useToNode(use, nodeTo)
-  |
-    exists(IRBlock bb2, int i2 |
-      use.asDefOrUse().hasIndexInBlock(bb2, i2, sv) and
-      adjacentDefRead(phi, bb1, i1, bb2, i2)
-    )
-    or
-    exists(PhiNode phiTo |
-      lastRefRedef(phi, _, _, phiTo) and
-      nodeTo.(SsaPhiNode).getPhiNode() = phiTo
-    )
-  )
-}
-
-private SsaInternals0::SourceVariable getOldSourceVariable(SourceVariable v) {
-  v.getBaseVariable().(BaseIRVariable).getIRVariable() =
-    result.getBaseVariable().(SsaInternals0::BaseIRVariable).getIRVariable()
-  or
-  v.getBaseVariable().(BaseCallVariable).getCallInstruction() =
-    result.getBaseVariable().(SsaInternals0::BaseCallVariable).getCallInstruction()
-}
-
-/**
- * Holds if there is a write at index `i` in basic block `bb` to variable `v` that's
- * subsequently read (as determined by the SSA pruning stage).
- */
-private predicate variableWriteCand(IRBlock bb, int i, SourceVariable v) {
-  exists(SsaInternals0::Def def, SsaInternals0::SourceVariable v0 |
-    def.asDefOrUse().hasIndexInBlock(bb, i, v0) and
-    v0 = getOldSourceVariable(v)
-  )
-}
-
-private module SsaInput implements SsaImplCommon::InputSig {
-  import InputSigCommon
-  import SourceVariables
-
-  /**
-   * Holds if the `i`'th write in block `bb` writes to the variable `v`.
-   * `certain` is `true` if the write is guaranteed to overwrite the entire variable.
-   */
-  predicate variableWrite(IRBlock bb, int i, SourceVariable v, boolean certain) {
-    DataFlowImplCommon::forceCachingInSameStage() and
-    variableWriteCand(bb, i, v) and
-    exists(DefImpl def | def.hasIndexInBlock(bb, i, v) |
-      if def.isCertain() then certain = true else certain = false
-    )
-  }
-
-  /**
-   * Holds if the `i`'th read in block `bb` reads to the variable `v`.
-   * `certain` is `true` if the read is guaranteed. For C++, this is always the case.
-   */
-  predicate variableRead(IRBlock bb, int i, SourceVariable v, boolean certain) {
-    exists(UseImpl use | use.hasIndexInBlock(bb, i, v) |
-      if use.isCertain() then certain = true else certain = false
-    )
-  }
-}
-
-/**
- * The final SSA predicates used for dataflow purposes.
- */
-cached
-module SsaCached {
-  /**
-   * Holds if `def` is accessed at index `i1` in basic block `bb1` (either a read
-   * or a write), `def` is read at index `i2` in basic block `bb2`, and there is a
-   * path between them without any read of `def`.
-   */
-  cached
-  predicate adjacentDefRead(Definition def, IRBlock bb1, int i1, IRBlock bb2, int i2) {
-    SsaImpl::adjacentDefRead(def, bb1, i1, bb2, i2)
-  }
-
-  /**
-   * Holds if the node at index `i` in `bb` is a last reference to SSA definition
-   * `def`. The reference is last because it can reach another write `next`,
-   * without passing through another read or write.
-   */
-  cached
-  predicate lastRefRedef(Definition def, IRBlock bb, int i, Definition next) {
-    SsaImpl::lastRefRedef(def, bb, i, next)
-  }
-}
-
-cached
-private newtype TSsaDefOrUse =
-  TDefOrUse(DefOrUseImpl defOrUse) {
-    defOrUse instanceof UseImpl
-    or
-    // Like in the pruning stage, we only include definition that's live after the
-    // write as the final definitions computed by SSA.
-    exists(Definition def, SourceVariable sv, IRBlock bb, int i |
-      def.definesAt(sv, bb, i) and
-      defOrUse.(DefImpl).hasIndexInBlock(bb, i, sv)
-    )
-  } or
-  TPhi(PhiNode phi)
-
-abstract private class SsaDefOrUse extends TSsaDefOrUse {
-  string toString() { none() }
-
-  DefOrUseImpl asDefOrUse() { none() }
-
-  PhiNode asPhi() { none() }
-
-  abstract Location getLocation();
-}
-
-class DefOrUse extends TDefOrUse, SsaDefOrUse {
-  DefOrUseImpl defOrUse;
-
-  DefOrUse() { this = TDefOrUse(defOrUse) }
-
-  final override DefOrUseImpl asDefOrUse() { result = defOrUse }
-
-  final override Location getLocation() { result = defOrUse.getLocation() }
-
-  final SourceVariable getSourceVariable() { result = defOrUse.getSourceVariable() }
-
-  override string toString() { result = defOrUse.toString() }
-}
-
-class Phi extends TPhi, SsaDefOrUse {
-  PhiNode phi;
-
-  Phi() { this = TPhi(phi) }
-
-  final override PhiNode asPhi() { result = phi }
-
-  final override Location getLocation() { result = phi.getBasicBlock().getLocation() }
-
-  override string toString() { result = "Phi" }
-}
-
-class UseOrPhi extends SsaDefOrUse {
-  UseOrPhi() {
-    this.asDefOrUse() instanceof UseImpl
-    or
-    this instanceof Phi
-  }
-
-  final override Location getLocation() {
-    result = this.asDefOrUse().getLocation() or result = this.(Phi).getLocation()
-  }
-}
-
-class Def extends DefOrUse {
-  override DefImpl defOrUse;
-
-  Operand getAddressOperand() { result = defOrUse.getAddressOperand() }
-
-  Instruction getAddress() { result = this.getAddressOperand().getDef() }
-
-  /**
-   * This predicate ensures that joins go from `defOrUse` to the result
-   * instead of the other way around.
-   */
-  pragma[inline]
-  int getIndirectionIndex() {
-    pragma[only_bind_into](result) = pragma[only_bind_out](defOrUse).getIndirectionIndex()
-  }
-
-  Instruction getDefiningInstruction() { result = defOrUse.getDefiningInstruction() }
-}
-
-private module SsaImpl = SsaImplCommon::Make<SsaInput>;
-
-class PhiNode = SsaImpl::PhiNode;
-
-class Definition = SsaImpl::Definition;
-
-import SsaCached

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/SsaInternalsCommon.qll

@@ -1,270 +0,0 @@
-import cpp as Cpp
-import semmle.code.cpp.ir.IR
-import semmle.code.cpp.ir.internal.IRCppLanguage
-private import semmle.code.cpp.ir.implementation.raw.internal.SideEffects as SideEffects
-private import DataFlowImplCommon as DataFlowImplCommon
-private import DataFlowUtil
-
-/**
- * Holds if `operand` is an operand that is not used by the dataflow library.
- * Ignored operands are not recognizd as uses by SSA, and they don't have a
- * corresponding `(Indirect)OperandNode`.
- */
-predicate ignoreOperand(Operand operand) {
-  operand = any(Instruction instr | ignoreInstruction(instr)).getAnOperand() or
-  operand = any(Instruction instr | ignoreInstruction(instr)).getAUse() or
-  operand instanceof MemoryOperand
-}
-
-/**
- * Holds if `instr` is an instruction that is not used by the dataflow library.
- * Ignored instructions are not recognized as reads/writes by SSA, and they
- * don't have a corresponding `(Indirect)InstructionNode`.
- */
-predicate ignoreInstruction(Instruction instr) {
-  DataFlowImplCommon::forceCachingInSameStage() and
-  (
-    instr instanceof WriteSideEffectInstruction or
-    instr instanceof PhiInstruction or
-    instr instanceof ReadSideEffectInstruction or
-    instr instanceof ChiInstruction or
-    instr instanceof InitializeIndirectionInstruction
-  )
-}
-
-/**
- * Gets the C++ type of `this` in the member function `f`.
- * The result is a glvalue if `isGLValue` is true, and
- * a prvalue if `isGLValue` is false.
- */
-bindingset[isGLValue]
-private CppType getThisType(Cpp::MemberFunction f, boolean isGLValue) {
-  result.hasType(f.getTypeOfThis(), isGLValue)
-}
-
-/**
- * Gets the C++ type of the instruction `i`.
- *
- * This is equivalent to `i.getResultLanguageType()` with the exception
- * of instructions that directly references a `this` IRVariable. In this
- * case, `i.getResultLanguageType()` gives an unknown type, whereas the
- * predicate gives the expected type (i.e., a potentially cv-qualified
- * type `A*` where `A` is the declaring type of the member function that
- * contains `i`).
- */
-cached
-CppType getResultLanguageType(Instruction i) {
-  if i.(VariableAddressInstruction).getIRVariable() instanceof IRThisVariable
-  then
-    if i.isGLValue()
-    then result = getThisType(i.getEnclosingFunction(), true)
-    else result = getThisType(i.getEnclosingFunction(), false)
-  else result = i.getResultLanguageType()
-}
-
-/**
- * Gets the C++ type of the operand `operand`.
- * This is equivalent to the type of the operand's defining instruction.
- *
- * See `getResultLanguageType` for a description of this behavior.
- */
-CppType getLanguageType(Operand operand) { result = getResultLanguageType(operand.getDef()) }
-
-/**
- * Gets the maximum number of indirections a glvalue of type `type` can have.
- * For example:
- * - If `type = int`, the result is 1
- * - If `type = MyStruct`, the result is 1
- * - If `type = char*`, the result is 2
- */
-int getMaxIndirectionsForType(Type type) {
-  result = countIndirectionsForCppType(getTypeForGLValue(type))
-}
-
-/**
- * Gets the maximum number of indirections a value of type `type` can have.
- *
- * Note that this predicate is intended to be called on unspecified types
- * (i.e., `countIndirections(e.getUnspecifiedType())`).
- */
-private int countIndirections(Type t) {
-  result =
-    1 +
-      countIndirections([t.(Cpp::PointerType).getBaseType(), t.(Cpp::ReferenceType).getBaseType()])
-  or
-  not t instanceof Cpp::PointerType and
-  not t instanceof Cpp::ReferenceType and
-  result = 0
-}
-
-/**
- * Gets the maximum number of indirections a value of C++
- * type `langType` can have.
- */
-int countIndirectionsForCppType(LanguageType langType) {
-  exists(Type type | langType.hasType(type, true) |
-    result = 1 + countIndirections(type.getUnspecifiedType())
-  )
-  or
-  exists(Type type | langType.hasType(type, false) |
-    result = countIndirections(type.getUnspecifiedType())
-  )
-}
-
-/**
- * A `CallInstruction` that calls an allocation function such
- * as `malloc` or `operator new`.
- */
-class AllocationInstruction extends CallInstruction {
-  AllocationInstruction() { this.getStaticCallTarget() instanceof Cpp::AllocationFunction }
-}
-
-/**
- * Holds if `i` is a base instruction that starts a sequence of uses
- * of some variable that SSA can handle.
- *
- * This is either when `i` is a `VariableAddressInstruction` or when
- * `i` is a fresh allocation produced by an `AllocationInstruction`.
- */
-private predicate isSourceVariableBase(Instruction i) {
-  i instanceof VariableAddressInstruction or i instanceof AllocationInstruction
-}
-
-/**
- * Holds if the value pointed to by `operand` can potentially be
- * modified be the caller.
- */
-predicate isModifiableByCall(ArgumentOperand operand) {
-  exists(CallInstruction call, int index, CppType type |
-    type = getLanguageType(operand) and
-    call.getArgumentOperand(index) = operand and
-    if index = -1
-    then not call.getStaticCallTarget() instanceof Cpp::ConstMemberFunction
-    else not SideEffects::isConstPointerLike(any(Type t | type.hasType(t, _)))
-  )
-}
-
-cached
-private module Cached {
-  /**
-   * Holds if `op` is a use of an SSA variable rooted at `base` with `ind` number
-   * of indirections.
-   *
-   * `certain` is `true` if the operand is guaranteed to read the variable, and
-   * `indirectionIndex` specifies the number of loads required to read the variable.
-   */
-  cached
-  predicate isUse(boolean certain, Operand op, Instruction base, int ind, int indirectionIndex) {
-    not ignoreOperand(op) and
-    certain = true and
-    exists(LanguageType type, int m, int ind0 |
-      type = getLanguageType(op) and
-      m = countIndirectionsForCppType(type) and
-      isUseImpl(op, base, ind0) and
-      ind = ind0 + [0 .. m] and
-      indirectionIndex = ind - ind0
-    )
-  }
-
-  /**
-   * Holds if `operand` is a use of an SSA variable rooted at `base`, and the
-   * path from `base` to `operand` passes through `ind` load-like instructions.
-   */
-  private predicate isUseImpl(Operand operand, Instruction base, int ind) {
-    DataFlowImplCommon::forceCachingInSameStage() and
-    ind = 0 and
-    operand.getDef() = base and
-    isSourceVariableBase(base)
-    or
-    exists(Operand mid, Instruction instr |
-      isUseImpl(mid, base, ind) and
-      instr = operand.getDef() and
-      conversionFlow(mid, instr, false)
-    )
-    or
-    exists(int ind0 |
-      isUseImpl(operand.getDef().(LoadInstruction).getSourceAddressOperand(), base, ind0)
-      or
-      isUseImpl(operand.getDef().(InitializeParameterInstruction).getAnOperand(), base, ind0)
-    |
-      ind0 = ind - 1
-    )
-  }
-
-  /**
-   * Holds if `address` is an address of an SSA variable rooted at `base`,
-   * and `instr` is a definition of the SSA variable with `ind` number of indirections.
-   *
-   * `certain` is `true` if `instr` is guaranteed to write to the variable, and
-   * `indirectionIndex` specifies the number of loads required to read the variable
-   * after the write operation.
-   */
-  cached
-  predicate isDef(
-    boolean certain, Instruction instr, Operand address, Instruction base, int ind,
-    int indirectionIndex
-  ) {
-    certain = true and
-    exists(int ind0, CppType type, int m |
-      address =
-        [
-          instr.(StoreInstruction).getDestinationAddressOperand(),
-          instr.(InitializeParameterInstruction).getAnOperand(),
-          instr.(InitializeDynamicAllocationInstruction).getAllocationAddressOperand(),
-          instr.(UninitializedInstruction).getAnOperand()
-        ]
-    |
-      isDefImpl(address, base, ind0) and
-      type = getLanguageType(address) and
-      m = countIndirectionsForCppType(type) and
-      ind = ind0 + [1 .. m] and
-      indirectionIndex = ind - (ind0 + 1)
-    )
-  }
-
-  /**
-   * Holds if `address` is a use of an SSA variable rooted at `base`, and the
-   * path from `base` to `address` passes through `ind` load-like instructions.
-   *
-   * Note: Unlike `isUseImpl`, this predicate recurses through pointer-arithmetic
-   * instructions.
-   */
-  private predicate isDefImpl(Operand address, Instruction base, int ind) {
-    DataFlowImplCommon::forceCachingInSameStage() and
-    ind = 0 and
-    address.getDef() = base and
-    isSourceVariableBase(base)
-    or
-    exists(Operand mid, Instruction instr |
-      isDefImpl(mid, base, ind) and
-      instr = address.getDef() and
-      conversionFlow(mid, instr, _)
-    )
-    or
-    exists(int ind0 |
-      isDefImpl(address.getDef().(LoadInstruction).getSourceAddressOperand(), base, ind0)
-      or
-      isDefImpl(address.getDef().(InitializeParameterInstruction).getAnOperand(), base, ind0)
-    |
-      ind0 = ind - 1
-    )
-  }
-}
-
-import Cached
-
-/**
- * Inputs to the shared SSA library's parameterized module that is shared
- * between the SSA pruning stage, and the final SSA stage.
- */
-module InputSigCommon {
-  class BasicBlock = IRBlock;
-
-  BasicBlock getImmediateBasicBlockDominator(BasicBlock bb) { result.immediatelyDominates(bb) }
-
-  BasicBlock getABasicBlockSuccessor(BasicBlock bb) { result = bb.getASuccessor() }
-
-  class ExitBasicBlock extends IRBlock {
-    ExitBasicBlock() { this.getLastInstruction() instanceof ExitFunctionInstruction }
-  }
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/TaintTrackingUtil.qll

@@ -1,208 +0,0 @@
-private import semmle.code.cpp.ir.IR
-private import experimental.semmle.code.cpp.ir.dataflow.DataFlow
-private import ModelUtil
-private import semmle.code.cpp.models.interfaces.DataFlow
-private import semmle.code.cpp.models.interfaces.SideEffect
-private import DataFlowUtil
-private import DataFlowPrivate
-private import semmle.code.cpp.models.Models
-
-/**
- * Holds if taint propagates from `nodeFrom` to `nodeTo` in exactly one local
- * (intra-procedural) step.
- */
-predicate localTaintStep(DataFlow::Node nodeFrom, DataFlow::Node nodeTo) {
-  DataFlow::localFlowStep(nodeFrom, nodeTo)
-  or
-  localAdditionalTaintStep(nodeFrom, nodeTo)
-}
-
-/**
- * Holds if taint can flow in one local step from `nodeFrom` to `nodeTo` excluding
- * local data flow steps. That is, `nodeFrom` and `nodeTo` are likely to represent
- * different objects.
- */
-cached
-predicate localAdditionalTaintStep(DataFlow::Node nodeFrom, DataFlow::Node nodeTo) {
-  operandToInstructionTaintStep(nodeFrom.asOperand(), nodeTo.asInstruction())
-  or
-  modeledTaintStep(nodeFrom, nodeTo)
-  or
-  // Flow from `op` to `*op`.
-  exists(Operand operand, int indirectionIndex |
-    nodeHasOperand(nodeFrom, operand, indirectionIndex) and
-    nodeHasOperand(nodeTo, operand, indirectionIndex - 1)
-  )
-  or
-  // Flow from `instr` to `*instr`.
-  exists(Instruction instr, int indirectionIndex |
-    nodeHasInstruction(nodeFrom, instr, indirectionIndex) and
-    nodeHasInstruction(nodeTo, instr, indirectionIndex - 1)
-  )
-  or
-  // Flow from (the indirection of) an operand of a pointer arithmetic instruction to the
-  // indirection of the pointer arithmetic instruction. This provides flow from `source`
-  // in `x[source]` to the result of the associated load instruction.
-  exists(PointerArithmeticInstruction pai, int indirectionIndex |
-    nodeHasOperand(nodeFrom, pai.getAnOperand(), pragma[only_bind_into](indirectionIndex)) and
-    hasInstructionAndIndex(nodeTo, pai, indirectionIndex + 1)
-  )
-}
-
-/**
- * Holds if taint propagates from `nodeFrom` to `nodeTo` in exactly one local
- * (intra-procedural) step.
- */
-private predicate operandToInstructionTaintStep(Operand opFrom, Instruction instrTo) {
-  // Taint can flow through expressions that alter the value but preserve
-  // more than one bit of it _or_ expressions that follow data through
-  // pointer indirections.
-  instrTo.getAnOperand() = opFrom and
-  (
-    instrTo instanceof ArithmeticInstruction
-    or
-    instrTo instanceof BitwiseInstruction
-    or
-    instrTo instanceof PointerArithmeticInstruction
-  )
-  or
-  // The `CopyInstruction` case is also present in non-taint data flow, but
-  // that uses `getDef` rather than `getAnyDef`. For taint, we want flow
-  // from a definition of `myStruct` to a `myStruct.myField` expression.
-  instrTo.(LoadInstruction).getSourceAddressOperand() = opFrom
-  or
-  // Unary instructions tend to preserve enough information in practice that we
-  // want taint to flow through.
-  // The exception is `FieldAddressInstruction`. Together with the rules below for
-  // `LoadInstruction`s and `ChiInstruction`s, flow through `FieldAddressInstruction`
-  // could cause flow into one field to come out an unrelated field.
-  // This would happen across function boundaries, where the IR would not be able to
-  // match loads to stores.
-  instrTo.(UnaryInstruction).getUnaryOperand() = opFrom and
-  (
-    not instrTo instanceof FieldAddressInstruction
-    or
-    instrTo.(FieldAddressInstruction).getField().getDeclaringType() instanceof Union
-  )
-}
-
-/**
- * Holds if taint may propagate from `source` to `sink` in zero or more local
- * (intra-procedural) steps.
- */
-pragma[inline]
-predicate localTaint(DataFlow::Node source, DataFlow::Node sink) { localTaintStep*(source, sink) }
-
-/**
- * Holds if taint can flow from `i1` to `i2` in zero or more
- * local (intra-procedural) steps.
- */
-pragma[inline]
-predicate localInstructionTaint(Instruction i1, Instruction i2) {
-  localTaint(DataFlow::instructionNode(i1), DataFlow::instructionNode(i2))
-}
-
-/**
- * Holds if taint can flow from `e1` to `e2` in zero or more
- * local (intra-procedural) steps.
- */
-pragma[inline]
-predicate localExprTaint(Expr e1, Expr e2) {
-  localTaint(DataFlow::exprNode(e1), DataFlow::exprNode(e2))
-}
-
-/**
- * Holds if the additional step from `src` to `sink` should be included in all
- * global taint flow configurations.
- */
-predicate defaultAdditionalTaintStep(DataFlow::Node src, DataFlow::Node sink) {
-  localAdditionalTaintStep(src, sink)
-}
-
-/**
- * Holds if default `TaintTracking::Configuration`s should allow implicit reads
- * of `c` at sinks and inputs to additional taint steps.
- */
-bindingset[node]
-predicate defaultImplicitTaintRead(DataFlow::Node node, DataFlow::Content c) { none() }
-
-/**
- * Holds if `node` should be a sanitizer in all global taint flow configurations
- * but not in local taint.
- */
-predicate defaultTaintSanitizer(DataFlow::Node node) { none() }
-
-/**
- * Holds if taint can flow from `instrIn` to `instrOut` through a call to a
- * modeled function.
- */
-predicate modeledTaintStep(DataFlow::Node nodeIn, DataFlow::Node nodeOut) {
-  // Normal taint steps
-  exists(CallInstruction call, TaintFunction func, FunctionInput modelIn, FunctionOutput modelOut |
-    call.getStaticCallTarget() = func and
-    func.hasTaintFlow(modelIn, modelOut)
-  |
-    (
-      nodeIn = callInput(call, modelIn)
-      or
-      exists(int n |
-        modelIn.isParameterDerefOrQualifierObject(n) and
-        if n = -1
-        then nodeIn = callInput(call, any(InQualifierAddress inQualifier))
-        else nodeIn = callInput(call, any(InParameter inParam | inParam.getIndex() = n))
-      )
-    ) and
-    nodeOut = callOutput(call, modelOut)
-    or
-    exists(int d |
-      nodeIn = callInput(call, modelIn, d)
-      or
-      exists(int n |
-        d = 1 and
-        modelIn.isParameterDerefOrQualifierObject(n) and
-        if n = -1
-        then nodeIn = callInput(call, any(InQualifierAddress inQualifier))
-        else nodeIn = callInput(call, any(InParameter inParam | inParam.getIndex() = n))
-      )
-    |
-      call.getStaticCallTarget() = func and
-      func.hasTaintFlow(modelIn, modelOut) and
-      nodeOut = callOutput(call, modelOut, d)
-    )
-  )
-  or
-  // Taint flow from one argument to another and data flow from an argument to a
-  // return value. This happens in functions like `strcat` and `memcpy`. We
-  // could model this flow in two separate steps, but that would add reverse
-  // flow from the write side-effect to the call instruction, which may not be
-  // desirable.
-  exists(
-    CallInstruction call, Function func, FunctionInput modelIn, OutParameterDeref modelMidOut,
-    int indexMid, InParameter modelMidIn, OutReturnValue modelOut
-  |
-    nodeIn = callInput(call, modelIn) and
-    nodeOut = callOutput(call, modelOut) and
-    call.getStaticCallTarget() = func and
-    func.(TaintFunction).hasTaintFlow(modelIn, modelMidOut) and
-    func.(DataFlowFunction).hasDataFlow(modelMidIn, modelOut) and
-    modelMidOut.isParameterDeref(indexMid) and
-    modelMidIn.isParameter(indexMid)
-  )
-  or
-  // Taint flow from a pointer argument to an output, when the model specifies flow from the deref
-  // to that output, but the deref is not modeled in the IR for the caller.
-  exists(
-    CallInstruction call, DataFlow::SideEffectOperandNode indirectArgument, Function func,
-    FunctionInput modelIn, FunctionOutput modelOut
-  |
-    indirectArgument = callInput(call, modelIn) and
-    indirectArgument.getAddressOperand() = nodeIn.asOperand() and
-    call.getStaticCallTarget() = func and
-    (
-      func.(DataFlowFunction).hasDataFlow(modelIn, modelOut)
-      or
-      func.(TaintFunction).hasTaintFlow(modelIn, modelOut)
-    ) and
-    nodeOut = callOutput(call, modelOut)
-  )
-}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/ssa0/SsaInternals.qll

@@ -1,314 +0,0 @@
-/**
- * This module defines an initial SSA pruning stage that doesn't take
- * indirections into account.
- */
-
-private import codeql.ssa.Ssa as SsaImplCommon
-private import semmle.code.cpp.ir.IR
-private import experimental.semmle.code.cpp.ir.dataflow.internal.DataFlowImplCommon as DataFlowImplCommon
-private import semmle.code.cpp.models.interfaces.Allocation as Alloc
-private import semmle.code.cpp.models.interfaces.DataFlow as DataFlow
-private import semmle.code.cpp.ir.implementation.raw.internal.SideEffects as SideEffects
-private import semmle.code.cpp.ir.internal.IRCppLanguage
-private import experimental.semmle.code.cpp.ir.dataflow.internal.DataFlowPrivate
-private import experimental.semmle.code.cpp.ir.dataflow.internal.DataFlowUtil
-private import experimental.semmle.code.cpp.ir.dataflow.internal.SsaInternalsCommon
-
-private module SourceVariables {
-  newtype TBaseSourceVariable =
-    // Each IR variable gets its own source variable
-    TBaseIRVariable(IRVariable var) or
-    // Each allocation gets its own source variable
-    TBaseCallVariable(AllocationInstruction call)
-
-  abstract class BaseSourceVariable extends TBaseSourceVariable {
-    abstract string toString();
-
-    abstract DataFlowType getType();
-  }
-
-  class BaseIRVariable extends BaseSourceVariable, TBaseIRVariable {
-    IRVariable var;
-
-    IRVariable getIRVariable() { result = var }
-
-    BaseIRVariable() { this = TBaseIRVariable(var) }
-
-    override string toString() { result = var.toString() }
-
-    override DataFlowType getType() { result = var.getType() }
-  }
-
-  class BaseCallVariable extends BaseSourceVariable, TBaseCallVariable {
-    AllocationInstruction call;
-
-    BaseCallVariable() { this = TBaseCallVariable(call) }
-
-    AllocationInstruction getCallInstruction() { result = call }
-
-    override string toString() { result = call.toString() }
-
-    override DataFlowType getType() { result = call.getResultType() }
-  }
-
-  private newtype TSourceVariable =
-    TSourceIRVariable(BaseIRVariable baseVar) or
-    TCallVariable(AllocationInstruction call)
-
-  abstract class SourceVariable extends TSourceVariable {
-    abstract string toString();
-
-    abstract BaseSourceVariable getBaseVariable();
-  }
-
-  class SourceIRVariable extends SourceVariable, TSourceIRVariable {
-    BaseIRVariable var;
-
-    SourceIRVariable() { this = TSourceIRVariable(var) }
-
-    IRVariable getIRVariable() { result = var.getIRVariable() }
-
-    override BaseIRVariable getBaseVariable() { result.getIRVariable() = this.getIRVariable() }
-
-    override string toString() { result = this.getIRVariable().toString() }
-  }
-
-  class CallVariable extends SourceVariable, TCallVariable {
-    AllocationInstruction call;
-
-    CallVariable() { this = TCallVariable(call) }
-
-    AllocationInstruction getCall() { result = call }
-
-    override BaseCallVariable getBaseVariable() { result.getCallInstruction() = call }
-
-    override string toString() { result = "Call" }
-  }
-}
-
-import SourceVariables
-
-private newtype TDefOrUseImpl =
-  TDefImpl(Operand address) { isDef(_, _, address, _, _, _) } or
-  TUseImpl(Operand operand) {
-    isUse(_, operand, _, _, _) and
-    not isDef(_, _, operand, _, _, _)
-  }
-
-abstract private class DefOrUseImpl extends TDefOrUseImpl {
-  /** Gets a textual representation of this element. */
-  abstract string toString();
-
-  /** Gets the block of this definition or use. */
-  abstract IRBlock getBlock();
-
-  /** Holds if this definition or use has index `index` in block `block`. */
-  abstract predicate hasIndexInBlock(IRBlock block, int index);
-
-  final predicate hasIndexInBlock(IRBlock block, int index, SourceVariable sv) {
-    this.hasIndexInBlock(block, index) and
-    sv = this.getSourceVariable()
-  }
-
-  /** Gets the location of this element. */
-  abstract Cpp::Location getLocation();
-
-  abstract Instruction getBase();
-
-  final BaseSourceVariable getBaseSourceVariable() {
-    exists(IRVariable var |
-      result.(BaseIRVariable).getIRVariable() = var and
-      instructionHasIRVariable(this.getBase(), var)
-    )
-    or
-    result.(BaseCallVariable).getCallInstruction() = this.getBase()
-  }
-
-  /** Gets the variable that is defined or used. */
-  final SourceVariable getSourceVariable() {
-    exists(BaseSourceVariable v |
-      sourceVariableHasBaseAndIndex(result, v) and
-      defOrUseHasSourceVariable(this, v)
-    )
-  }
-}
-
-pragma[noinline]
-private predicate instructionHasIRVariable(VariableAddressInstruction vai, IRVariable var) {
-  vai.getIRVariable() = var
-}
-
-private predicate defOrUseHasSourceVariable(DefOrUseImpl defOrUse, BaseSourceVariable bv) {
-  defHasSourceVariable(defOrUse, bv)
-  or
-  useHasSourceVariable(defOrUse, bv)
-}
-
-pragma[noinline]
-private predicate defHasSourceVariable(DefImpl def, BaseSourceVariable bv) {
-  bv = def.getBaseSourceVariable()
-}
-
-pragma[noinline]
-private predicate useHasSourceVariable(UseImpl use, BaseSourceVariable bv) {
-  bv = use.getBaseSourceVariable()
-}
-
-pragma[noinline]
-private predicate sourceVariableHasBaseAndIndex(SourceVariable v, BaseSourceVariable bv) {
-  v.getBaseVariable() = bv
-}
-
-class DefImpl extends DefOrUseImpl, TDefImpl {
-  Operand address;
-
-  DefImpl() { this = TDefImpl(address) }
-
-  override Instruction getBase() { isDef(_, _, address, result, _, _) }
-
-  Operand getAddressOperand() { result = address }
-
-  Instruction getDefiningInstruction() { isDef(_, result, address, _, _, _) }
-
-  override string toString() { result = address.toString() }
-
-  override IRBlock getBlock() { result = this.getDefiningInstruction().getBlock() }
-
-  override Cpp::Location getLocation() { result = this.getDefiningInstruction().getLocation() }
-
-  final override predicate hasIndexInBlock(IRBlock block, int index) {
-    this.getDefiningInstruction() = block.getInstruction(index)
-  }
-
-  predicate isCertain() { isDef(true, _, address, _, _, _) }
-}
-
-class UseImpl extends DefOrUseImpl, TUseImpl {
-  Operand operand;
-
-  UseImpl() { this = TUseImpl(operand) }
-
-  Operand getOperand() { result = operand }
-
-  override string toString() { result = operand.toString() }
-
-  final override predicate hasIndexInBlock(IRBlock block, int index) {
-    operand.getUse() = block.getInstruction(index)
-  }
-
-  final override IRBlock getBlock() { result = operand.getUse().getBlock() }
-
-  final override Cpp::Location getLocation() { result = operand.getLocation() }
-
-  override Instruction getBase() { isUse(_, operand, result, _, _) }
-
-  predicate isCertain() { isUse(true, operand, _, _, _) }
-}
-
-private module SsaInput implements SsaImplCommon::InputSig {
-  import InputSigCommon
-  import SourceVariables
-
-  /**
-   * Holds if the `i`'th write in block `bb` writes to the variable `v`.
-   * `certain` is `true` if the write is guaranteed to overwrite the entire variable.
-   */
-  predicate variableWrite(IRBlock bb, int i, SourceVariable v, boolean certain) {
-    DataFlowImplCommon::forceCachingInSameStage() and
-    exists(DefImpl def | def.hasIndexInBlock(bb, i, v) |
-      if def.isCertain() then certain = true else certain = false
-    )
-  }
-
-  /**
-   * Holds if the `i`'th read in block `bb` reads to the variable `v`.
-   * `certain` is `true` if the read is guaranteed.
-   */
-  predicate variableRead(IRBlock bb, int i, SourceVariable v, boolean certain) {
-    exists(UseImpl use | use.hasIndexInBlock(bb, i, v) |
-      if use.isCertain() then certain = true else certain = false
-    )
-  }
-}
-
-private newtype TSsaDefOrUse =
-  TDefOrUse(DefOrUseImpl defOrUse) {
-    defOrUse instanceof UseImpl
-    or
-    // If `defOrUse` is a definition we only include it if the
-    // SSA library concludes that it's live after the write.
-    exists(Definition def, SourceVariable sv, IRBlock bb, int i |
-      def.definesAt(sv, bb, i) and
-      defOrUse.(DefImpl).hasIndexInBlock(bb, i, sv)
-    )
-  } or
-  TPhi(PhiNode phi)
-
-abstract private class SsaDefOrUse extends TSsaDefOrUse {
-  string toString() { result = "SsaDefOrUse" }
-
-  DefOrUseImpl asDefOrUse() { none() }
-
-  PhiNode asPhi() { none() }
-
-  abstract Location getLocation();
-}
-
-class DefOrUse extends TDefOrUse, SsaDefOrUse {
-  DefOrUseImpl defOrUse;
-
-  DefOrUse() { this = TDefOrUse(defOrUse) }
-
-  final override DefOrUseImpl asDefOrUse() { result = defOrUse }
-
-  final override Location getLocation() { result = defOrUse.getLocation() }
-
-  final SourceVariable getSourceVariable() { result = defOrUse.getSourceVariable() }
-}
-
-class Phi extends TPhi, SsaDefOrUse {
-  PhiNode phi;
-
-  Phi() { this = TPhi(phi) }
-
-  final override PhiNode asPhi() { result = phi }
-
-  final override Location getLocation() { result = phi.getBasicBlock().getLocation() }
-}
-
-class UseOrPhi extends SsaDefOrUse {
-  UseOrPhi() {
-    this.asDefOrUse() instanceof UseImpl
-    or
-    this instanceof Phi
-  }
-
-  final override Location getLocation() {
-    result = this.asDefOrUse().getLocation() or result = this.(Phi).getLocation()
-  }
-
-  override string toString() {
-    result = this.asDefOrUse().toString()
-    or
-    this instanceof Phi and
-    result = "Phi"
-  }
-}
-
-class Def extends DefOrUse {
-  override DefImpl defOrUse;
-
-  Operand getAddressOperand() { result = defOrUse.getAddressOperand() }
-
-  Instruction getAddress() { result = this.getAddressOperand().getDef() }
-
-  Instruction getDefiningInstruction() { result = defOrUse.getDefiningInstruction() }
-
-  override string toString() { result = this.asDefOrUse().toString() + " (def)" }
-}
-
-private module SsaImpl = SsaImplCommon::Make<SsaInput>;
-
-class PhiNode = SsaImpl::PhiNode;
-
-class Definition = SsaImpl::Definition;

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

@@ -1,191 +0,0 @@
-/**
- * Provides an implementation of global (interprocedural) taint tracking.
- * This file re-exports the local (intraprocedural) taint-tracking analysis
- * from `TaintTrackingParameter::Public` and adds a global analysis, mainly
- * exposed through the `Configuration` class. For some languages, this file
- * exists in several identical copies, allowing queries to use multiple
- * `Configuration` classes that depend on each other without introducing
- * mutual recursion among those configurations.
- */
-
-import TaintTrackingParameter::Public
-private import TaintTrackingParameter::Private
-
-/**
- * A configuration of interprocedural taint tracking analysis. This defines
- * sources, sinks, and any other configurable aspect of the analysis. Each
- * use of the taint tracking library must define its own unique extension of
- * this abstract class.
- *
- * A taint-tracking configuration is a special data flow configuration
- * (`DataFlow::Configuration`) that allows for flow through nodes that do not
- * necessarily preserve values but are still relevant from a taint tracking
- * perspective. (For example, string concatenation, where one of the operands
- * is tainted.)
- *
- * To create a configuration, extend this class with a subclass whose
- * characteristic predicate is a unique singleton string. For example, write
- *
- * ```ql
- * class MyAnalysisConfiguration extends TaintTracking::Configuration {
- *   MyAnalysisConfiguration() { this = "MyAnalysisConfiguration" }
- *   // Override `isSource` and `isSink`.
- *   // Optionally override `isSanitizer`.
- *   // Optionally override `isSanitizerIn`.
- *   // Optionally override `isSanitizerOut`.
- *   // Optionally override `isSanitizerGuard`.
- *   // Optionally override `isAdditionalTaintStep`.
- * }
- * ```
- *
- * Then, to query whether there is flow between some `source` and `sink`,
- * write
- *
- * ```ql
- * exists(MyAnalysisConfiguration cfg | cfg.hasFlow(source, sink))
- * ```
- *
- * Multiple configurations can coexist, but it is unsupported to depend on
- * another `TaintTracking::Configuration` or a `DataFlow::Configuration` in the
- * overridden predicates that define sources, sinks, or additional steps.
- * Instead, the dependency should go to a `TaintTracking2::Configuration` or a
- * `DataFlow2::Configuration`, `DataFlow3::Configuration`, etc.
- */
-abstract class Configuration extends DataFlow::Configuration {
-  bindingset[this]
-  Configuration() { any() }
-
-  /**
-   * Holds if `source` is a relevant taint source.
-   *
-   * The smaller this predicate is, the faster `hasFlow()` will converge.
-   */
-  // overridden to provide taint-tracking specific qldoc
-  override predicate isSource(DataFlow::Node source) { none() }
-
-  /**
-   * Holds if `source` is a relevant taint source with the given initial
-   * `state`.
-   *
-   * The smaller this predicate is, the faster `hasFlow()` will converge.
-   */
-  // overridden to provide taint-tracking specific qldoc
-  override predicate isSource(DataFlow::Node source, DataFlow::FlowState state) { none() }
-
-  /**
-   * Holds if `sink` is a relevant taint sink
-   *
-   * The smaller this predicate is, the faster `hasFlow()` will converge.
-   */
-  // overridden to provide taint-tracking specific qldoc
-  override predicate isSink(DataFlow::Node sink) { none() }
-
-  /**
-   * Holds if `sink` is a relevant taint sink accepting `state`.
-   *
-   * The smaller this predicate is, the faster `hasFlow()` will converge.
-   */
-  // overridden to provide taint-tracking specific qldoc
-  override predicate isSink(DataFlow::Node sink, DataFlow::FlowState state) { none() }
-
-  /** Holds if the node `node` is a taint sanitizer. */
-  predicate isSanitizer(DataFlow::Node node) { none() }
-
-  final override predicate isBarrier(DataFlow::Node node) {
-    this.isSanitizer(node) or
-    defaultTaintSanitizer(node)
-  }
-
-  /**
-   * Holds if the node `node` is a taint sanitizer when the flow state is
-   * `state`.
-   */
-  predicate isSanitizer(DataFlow::Node node, DataFlow::FlowState state) { none() }
-
-  final override predicate isBarrier(DataFlow::Node node, DataFlow::FlowState state) {
-    this.isSanitizer(node, state)
-  }
-
-  /** Holds if taint propagation into `node` is prohibited. */
-  predicate isSanitizerIn(DataFlow::Node node) { none() }
-
-  final override predicate isBarrierIn(DataFlow::Node node) { this.isSanitizerIn(node) }
-
-  /** Holds if taint propagation out of `node` is prohibited. */
-  predicate isSanitizerOut(DataFlow::Node node) { none() }
-
-  final override predicate isBarrierOut(DataFlow::Node node) { this.isSanitizerOut(node) }
-
-  /**
-   * DEPRECATED: Use `isSanitizer` and `BarrierGuard` module instead.
-   *
-   * Holds if taint propagation through nodes guarded by `guard` is prohibited.
-   */
-  deprecated predicate isSanitizerGuard(DataFlow::BarrierGuard guard) { none() }
-
-  deprecated final override predicate isBarrierGuard(DataFlow::BarrierGuard guard) {
-    this.isSanitizerGuard(guard)
-  }
-
-  /**
-   * DEPRECATED: Use `isSanitizer` and `BarrierGuard` module instead.
-   *
-   * Holds if taint propagation through nodes guarded by `guard` is prohibited
-   * when the flow state is `state`.
-   */
-  deprecated predicate isSanitizerGuard(DataFlow::BarrierGuard guard, DataFlow::FlowState state) {
-    none()
-  }
-
-  deprecated final override predicate isBarrierGuard(
-    DataFlow::BarrierGuard guard, DataFlow::FlowState state
-  ) {
-    this.isSanitizerGuard(guard, state)
-  }
-
-  /**
-   * Holds if taint may propagate from `node1` to `node2` in addition to the normal data-flow and taint steps.
-   */
-  predicate isAdditionalTaintStep(DataFlow::Node node1, DataFlow::Node node2) { none() }
-
-  final override predicate isAdditionalFlowStep(DataFlow::Node node1, DataFlow::Node node2) {
-    this.isAdditionalTaintStep(node1, node2) or
-    defaultAdditionalTaintStep(node1, node2)
-  }
-
-  /**
-   * Holds if taint may propagate from `node1` to `node2` in addition to the normal data-flow and taint steps.
-   * This step is only applicable in `state1` and updates the flow state to `state2`.
-   */
-  predicate isAdditionalTaintStep(
-    DataFlow::Node node1, DataFlow::FlowState state1, DataFlow::Node node2,
-    DataFlow::FlowState state2
-  ) {
-    none()
-  }
-
-  final override predicate isAdditionalFlowStep(
-    DataFlow::Node node1, DataFlow::FlowState state1, DataFlow::Node node2,
-    DataFlow::FlowState state2
-  ) {
-    this.isAdditionalTaintStep(node1, state1, node2, state2)
-  }
-
-  override predicate allowImplicitRead(DataFlow::Node node, DataFlow::ContentSet c) {
-    (
-      this.isSink(node) or
-      this.isSink(node, _) or
-      this.isAdditionalTaintStep(node, _) or
-      this.isAdditionalTaintStep(node, _, _, _)
-    ) and
-    defaultImplicitTaintRead(node, c)
-  }
-
-  /**
-   * Holds if taint may flow from `source` to `sink` for this configuration.
-   */
-  // overridden to provide taint-tracking specific qldoc
-  override predicate hasFlow(DataFlow::Node source, DataFlow::Node sink) {
-    super.hasFlow(source, sink)
-  }
-}

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

@@ -1,5 +0,0 @@
-import experimental.semmle.code.cpp.ir.dataflow.internal.TaintTrackingUtil as Public
-
-module Private {
-  import experimental.semmle.code.cpp.ir.dataflow.DataFlow::DataFlow as DataFlow
-}

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

@@ -1,191 +0,0 @@
-/**
- * Provides an implementation of global (interprocedural) taint tracking.
- * This file re-exports the local (intraprocedural) taint-tracking analysis
- * from `TaintTrackingParameter::Public` and adds a global analysis, mainly
- * exposed through the `Configuration` class. For some languages, this file
- * exists in several identical copies, allowing queries to use multiple
- * `Configuration` classes that depend on each other without introducing
- * mutual recursion among those configurations.
- */
-
-import TaintTrackingParameter::Public
-private import TaintTrackingParameter::Private
-
-/**
- * A configuration of interprocedural taint tracking analysis. This defines
- * sources, sinks, and any other configurable aspect of the analysis. Each
- * use of the taint tracking library must define its own unique extension of
- * this abstract class.
- *
- * A taint-tracking configuration is a special data flow configuration
- * (`DataFlow::Configuration`) that allows for flow through nodes that do not
- * necessarily preserve values but are still relevant from a taint tracking
- * perspective. (For example, string concatenation, where one of the operands
- * is tainted.)
- *
- * To create a configuration, extend this class with a subclass whose
- * characteristic predicate is a unique singleton string. For example, write
- *
- * ```ql
- * class MyAnalysisConfiguration extends TaintTracking::Configuration {
- *   MyAnalysisConfiguration() { this = "MyAnalysisConfiguration" }
- *   // Override `isSource` and `isSink`.
- *   // Optionally override `isSanitizer`.
- *   // Optionally override `isSanitizerIn`.
- *   // Optionally override `isSanitizerOut`.
- *   // Optionally override `isSanitizerGuard`.
- *   // Optionally override `isAdditionalTaintStep`.
- * }
- * ```
- *
- * Then, to query whether there is flow between some `source` and `sink`,
- * write
- *
- * ```ql
- * exists(MyAnalysisConfiguration cfg | cfg.hasFlow(source, sink))
- * ```
- *
- * Multiple configurations can coexist, but it is unsupported to depend on
- * another `TaintTracking::Configuration` or a `DataFlow::Configuration` in the
- * overridden predicates that define sources, sinks, or additional steps.
- * Instead, the dependency should go to a `TaintTracking2::Configuration` or a
- * `DataFlow2::Configuration`, `DataFlow3::Configuration`, etc.
- */
-abstract class Configuration extends DataFlow::Configuration {
-  bindingset[this]
-  Configuration() { any() }
-
-  /**
-   * Holds if `source` is a relevant taint source.
-   *
-   * The smaller this predicate is, the faster `hasFlow()` will converge.
-   */
-  // overridden to provide taint-tracking specific qldoc
-  override predicate isSource(DataFlow::Node source) { none() }
-
-  /**
-   * Holds if `source` is a relevant taint source with the given initial
-   * `state`.
-   *
-   * The smaller this predicate is, the faster `hasFlow()` will converge.
-   */
-  // overridden to provide taint-tracking specific qldoc
-  override predicate isSource(DataFlow::Node source, DataFlow::FlowState state) { none() }
-
-  /**
-   * Holds if `sink` is a relevant taint sink
-   *
-   * The smaller this predicate is, the faster `hasFlow()` will converge.
-   */
-  // overridden to provide taint-tracking specific qldoc
-  override predicate isSink(DataFlow::Node sink) { none() }
-
-  /**
-   * Holds if `sink` is a relevant taint sink accepting `state`.
-   *
-   * The smaller this predicate is, the faster `hasFlow()` will converge.
-   */
-  // overridden to provide taint-tracking specific qldoc
-  override predicate isSink(DataFlow::Node sink, DataFlow::FlowState state) { none() }
-
-  /** Holds if the node `node` is a taint sanitizer. */
-  predicate isSanitizer(DataFlow::Node node) { none() }
-
-  final override predicate isBarrier(DataFlow::Node node) {
-    this.isSanitizer(node) or
-    defaultTaintSanitizer(node)
-  }
-
-  /**
-   * Holds if the node `node` is a taint sanitizer when the flow state is
-   * `state`.
-   */
-  predicate isSanitizer(DataFlow::Node node, DataFlow::FlowState state) { none() }
-
-  final override predicate isBarrier(DataFlow::Node node, DataFlow::FlowState state) {
-    this.isSanitizer(node, state)
-  }
-
-  /** Holds if taint propagation into `node` is prohibited. */
-  predicate isSanitizerIn(DataFlow::Node node) { none() }
-
-  final override predicate isBarrierIn(DataFlow::Node node) { this.isSanitizerIn(node) }
-
-  /** Holds if taint propagation out of `node` is prohibited. */
-  predicate isSanitizerOut(DataFlow::Node node) { none() }
-
-  final override predicate isBarrierOut(DataFlow::Node node) { this.isSanitizerOut(node) }
-
-  /**
-   * DEPRECATED: Use `isSanitizer` and `BarrierGuard` module instead.
-   *
-   * Holds if taint propagation through nodes guarded by `guard` is prohibited.
-   */
-  deprecated predicate isSanitizerGuard(DataFlow::BarrierGuard guard) { none() }
-
-  deprecated final override predicate isBarrierGuard(DataFlow::BarrierGuard guard) {
-    this.isSanitizerGuard(guard)
-  }
-
-  /**
-   * DEPRECATED: Use `isSanitizer` and `BarrierGuard` module instead.
-   *
-   * Holds if taint propagation through nodes guarded by `guard` is prohibited
-   * when the flow state is `state`.
-   */
-  deprecated predicate isSanitizerGuard(DataFlow::BarrierGuard guard, DataFlow::FlowState state) {
-    none()
-  }
-
-  deprecated final override predicate isBarrierGuard(
-    DataFlow::BarrierGuard guard, DataFlow::FlowState state
-  ) {
-    this.isSanitizerGuard(guard, state)
-  }
-
-  /**
-   * Holds if taint may propagate from `node1` to `node2` in addition to the normal data-flow and taint steps.
-   */
-  predicate isAdditionalTaintStep(DataFlow::Node node1, DataFlow::Node node2) { none() }
-
-  final override predicate isAdditionalFlowStep(DataFlow::Node node1, DataFlow::Node node2) {
-    this.isAdditionalTaintStep(node1, node2) or
-    defaultAdditionalTaintStep(node1, node2)
-  }
-
-  /**
-   * Holds if taint may propagate from `node1` to `node2` in addition to the normal data-flow and taint steps.
-   * This step is only applicable in `state1` and updates the flow state to `state2`.
-   */
-  predicate isAdditionalTaintStep(
-    DataFlow::Node node1, DataFlow::FlowState state1, DataFlow::Node node2,
-    DataFlow::FlowState state2
-  ) {
-    none()
-  }
-
-  final override predicate isAdditionalFlowStep(
-    DataFlow::Node node1, DataFlow::FlowState state1, DataFlow::Node node2,
-    DataFlow::FlowState state2
-  ) {
-    this.isAdditionalTaintStep(node1, state1, node2, state2)
-  }
-
-  override predicate allowImplicitRead(DataFlow::Node node, DataFlow::ContentSet c) {
-    (
-      this.isSink(node) or
-      this.isSink(node, _) or
-      this.isAdditionalTaintStep(node, _) or
-      this.isAdditionalTaintStep(node, _, _, _)
-    ) and
-    defaultImplicitTaintRead(node, c)
-  }
-
-  /**
-   * Holds if taint may flow from `source` to `sink` for this configuration.
-   */
-  // overridden to provide taint-tracking specific qldoc
-  override predicate hasFlow(DataFlow::Node source, DataFlow::Node sink) {
-    super.hasFlow(source, sink)
-  }
-}

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

@@ -1,5 +0,0 @@
-import experimental.semmle.code.cpp.ir.dataflow.internal.TaintTrackingUtil as Public
-
-module Private {
-  import experimental.semmle.code.cpp.ir.dataflow.DataFlow2::DataFlow2 as DataFlow
-}

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

@@ -1,191 +0,0 @@
-/**
- * Provides an implementation of global (interprocedural) taint tracking.
- * This file re-exports the local (intraprocedural) taint-tracking analysis
- * from `TaintTrackingParameter::Public` and adds a global analysis, mainly
- * exposed through the `Configuration` class. For some languages, this file
- * exists in several identical copies, allowing queries to use multiple
- * `Configuration` classes that depend on each other without introducing
- * mutual recursion among those configurations.
- */
-
-import TaintTrackingParameter::Public
-private import TaintTrackingParameter::Private
-
-/**
- * A configuration of interprocedural taint tracking analysis. This defines
- * sources, sinks, and any other configurable aspect of the analysis. Each
- * use of the taint tracking library must define its own unique extension of
- * this abstract class.
- *
- * A taint-tracking configuration is a special data flow configuration
- * (`DataFlow::Configuration`) that allows for flow through nodes that do not
- * necessarily preserve values but are still relevant from a taint tracking
- * perspective. (For example, string concatenation, where one of the operands
- * is tainted.)
- *
- * To create a configuration, extend this class with a subclass whose
- * characteristic predicate is a unique singleton string. For example, write
- *
- * ```ql
- * class MyAnalysisConfiguration extends TaintTracking::Configuration {
- *   MyAnalysisConfiguration() { this = "MyAnalysisConfiguration" }
- *   // Override `isSource` and `isSink`.
- *   // Optionally override `isSanitizer`.
- *   // Optionally override `isSanitizerIn`.
- *   // Optionally override `isSanitizerOut`.
- *   // Optionally override `isSanitizerGuard`.
- *   // Optionally override `isAdditionalTaintStep`.
- * }
- * ```
- *
- * Then, to query whether there is flow between some `source` and `sink`,
- * write
- *
- * ```ql
- * exists(MyAnalysisConfiguration cfg | cfg.hasFlow(source, sink))
- * ```
- *
- * Multiple configurations can coexist, but it is unsupported to depend on
- * another `TaintTracking::Configuration` or a `DataFlow::Configuration` in the
- * overridden predicates that define sources, sinks, or additional steps.
- * Instead, the dependency should go to a `TaintTracking2::Configuration` or a
- * `DataFlow2::Configuration`, `DataFlow3::Configuration`, etc.
- */
-abstract class Configuration extends DataFlow::Configuration {
-  bindingset[this]
-  Configuration() { any() }
-
-  /**
-   * Holds if `source` is a relevant taint source.
-   *
-   * The smaller this predicate is, the faster `hasFlow()` will converge.
-   */
-  // overridden to provide taint-tracking specific qldoc
-  override predicate isSource(DataFlow::Node source) { none() }
-
-  /**
-   * Holds if `source` is a relevant taint source with the given initial
-   * `state`.
-   *
-   * The smaller this predicate is, the faster `hasFlow()` will converge.
-   */
-  // overridden to provide taint-tracking specific qldoc
-  override predicate isSource(DataFlow::Node source, DataFlow::FlowState state) { none() }
-
-  /**
-   * Holds if `sink` is a relevant taint sink
-   *
-   * The smaller this predicate is, the faster `hasFlow()` will converge.
-   */
-  // overridden to provide taint-tracking specific qldoc
-  override predicate isSink(DataFlow::Node sink) { none() }
-
-  /**
-   * Holds if `sink` is a relevant taint sink accepting `state`.
-   *
-   * The smaller this predicate is, the faster `hasFlow()` will converge.
-   */
-  // overridden to provide taint-tracking specific qldoc
-  override predicate isSink(DataFlow::Node sink, DataFlow::FlowState state) { none() }
-
-  /** Holds if the node `node` is a taint sanitizer. */
-  predicate isSanitizer(DataFlow::Node node) { none() }
-
-  final override predicate isBarrier(DataFlow::Node node) {
-    this.isSanitizer(node) or
-    defaultTaintSanitizer(node)
-  }
-
-  /**
-   * Holds if the node `node` is a taint sanitizer when the flow state is
-   * `state`.
-   */
-  predicate isSanitizer(DataFlow::Node node, DataFlow::FlowState state) { none() }
-
-  final override predicate isBarrier(DataFlow::Node node, DataFlow::FlowState state) {
-    this.isSanitizer(node, state)
-  }
-
-  /** Holds if taint propagation into `node` is prohibited. */
-  predicate isSanitizerIn(DataFlow::Node node) { none() }
-
-  final override predicate isBarrierIn(DataFlow::Node node) { this.isSanitizerIn(node) }
-
-  /** Holds if taint propagation out of `node` is prohibited. */
-  predicate isSanitizerOut(DataFlow::Node node) { none() }
-
-  final override predicate isBarrierOut(DataFlow::Node node) { this.isSanitizerOut(node) }
-
-  /**
-   * DEPRECATED: Use `isSanitizer` and `BarrierGuard` module instead.
-   *
-   * Holds if taint propagation through nodes guarded by `guard` is prohibited.
-   */
-  deprecated predicate isSanitizerGuard(DataFlow::BarrierGuard guard) { none() }
-
-  deprecated final override predicate isBarrierGuard(DataFlow::BarrierGuard guard) {
-    this.isSanitizerGuard(guard)
-  }
-
-  /**
-   * DEPRECATED: Use `isSanitizer` and `BarrierGuard` module instead.
-   *
-   * Holds if taint propagation through nodes guarded by `guard` is prohibited
-   * when the flow state is `state`.
-   */
-  deprecated predicate isSanitizerGuard(DataFlow::BarrierGuard guard, DataFlow::FlowState state) {
-    none()
-  }
-
-  deprecated final override predicate isBarrierGuard(
-    DataFlow::BarrierGuard guard, DataFlow::FlowState state
-  ) {
-    this.isSanitizerGuard(guard, state)
-  }
-
-  /**
-   * Holds if taint may propagate from `node1` to `node2` in addition to the normal data-flow and taint steps.
-   */
-  predicate isAdditionalTaintStep(DataFlow::Node node1, DataFlow::Node node2) { none() }
-
-  final override predicate isAdditionalFlowStep(DataFlow::Node node1, DataFlow::Node node2) {
-    this.isAdditionalTaintStep(node1, node2) or
-    defaultAdditionalTaintStep(node1, node2)
-  }
-
-  /**
-   * Holds if taint may propagate from `node1` to `node2` in addition to the normal data-flow and taint steps.
-   * This step is only applicable in `state1` and updates the flow state to `state2`.
-   */
-  predicate isAdditionalTaintStep(
-    DataFlow::Node node1, DataFlow::FlowState state1, DataFlow::Node node2,
-    DataFlow::FlowState state2
-  ) {
-    none()
-  }
-
-  final override predicate isAdditionalFlowStep(
-    DataFlow::Node node1, DataFlow::FlowState state1, DataFlow::Node node2,
-    DataFlow::FlowState state2
-  ) {
-    this.isAdditionalTaintStep(node1, state1, node2, state2)
-  }
-
-  override predicate allowImplicitRead(DataFlow::Node node, DataFlow::ContentSet c) {
-    (
-      this.isSink(node) or
-      this.isSink(node, _) or
-      this.isAdditionalTaintStep(node, _) or
-      this.isAdditionalTaintStep(node, _, _, _)
-    ) and
-    defaultImplicitTaintRead(node, c)
-  }
-
-  /**
-   * Holds if taint may flow from `source` to `sink` for this configuration.
-   */
-  // overridden to provide taint-tracking specific qldoc
-  override predicate hasFlow(DataFlow::Node source, DataFlow::Node sink) {
-    super.hasFlow(source, sink)
-  }
-}

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

@@ -1,5 +0,0 @@
-import experimental.semmle.code.cpp.ir.dataflow.internal.TaintTrackingUtil as Public
-
-module Private {
-  import experimental.semmle.code.cpp.ir.dataflow.DataFlow3::DataFlow3 as DataFlow
-}

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/Bound.qll

@@ -1,86 +1 @@
-import cpp
-private import semmle.code.cpp.ir.IR
-private import semmle.code.cpp.ir.ValueNumbering
-
-private newtype TBound =
-  TBoundZero() or
-  TBoundValueNumber(ValueNumber vn) {
-    exists(Instruction i |
-      vn.getAnInstruction() = i and
-      (
-        i.getResultIRType() instanceof IRIntegerType or
-        i.getResultIRType() instanceof IRAddressType
-      ) and
-      not vn.getAnInstruction() instanceof ConstantInstruction
-    |
-      i instanceof PhiInstruction
-      or
-      i instanceof InitializeParameterInstruction
-      or
-      i instanceof CallInstruction
-      or
-      i instanceof VariableAddressInstruction
-      or
-      i instanceof FieldAddressInstruction
-      or
-      i.(LoadInstruction).getSourceAddress() instanceof VariableAddressInstruction
-      or
-      i.(LoadInstruction).getSourceAddress() instanceof FieldAddressInstruction
-      or
-      i.getAUse() instanceof ArgumentOperand
-      or
-      i instanceof PointerArithmeticInstruction
-      or
-      i.getAUse() instanceof AddressOperand
-    )
-  }
-
-/**
- * A bound that may be inferred for an expression plus/minus an integer delta.
- */
-abstract class Bound extends TBound {
-  abstract string toString();
-
-  /** Gets an expression that equals this bound plus `delta`. */
-  abstract Instruction getInstruction(int delta);
-
-  /** Gets an expression that equals this bound. */
-  Instruction getInstruction() { result = getInstruction(0) }
-
-  abstract Location getLocation();
-}
-
-/**
- * The bound that corresponds to the integer 0. This is used to represent all
- * integer bounds as bounds are always accompanied by an added integer delta.
- */
-class ZeroBound extends Bound, TBoundZero {
-  override string toString() { result = "0" }
-
-  override Instruction getInstruction(int delta) {
-    result.(ConstantValueInstruction).getValue().toInt() = delta
-  }
-
-  override Location getLocation() { result instanceof UnknownDefaultLocation }
-}
-
-/**
- * A bound corresponding to the value of an `Instruction`.
- */
-class ValueNumberBound extends Bound, TBoundValueNumber {
-  ValueNumber vn;
-
-  ValueNumberBound() { this = TBoundValueNumber(vn) }
-
-  /** Gets an `Instruction` that equals this bound. */
-  override Instruction getInstruction(int delta) {
-    this = TBoundValueNumber(valueNumber(result)) and delta = 0
-  }
-
-  override string toString() { result = "ValueNumberBound" }
-
-  override Location getLocation() { result = vn.getLocation() }
-
-  /** Gets the value number that equals this bound. */
-  ValueNumber getValueNumber() { result = vn }
-}
+import semmle.code.cpp.rangeanalysis.new.internal.semantic.analysis.Bound

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/ExtendedRangeAnalysis.qll

@@ -3,3 +3,4 @@ import semmle.code.cpp.rangeanalysis.SimpleRangeAnalysis
 // Import each extension we want to enable
 import extensions.SubtractSelf
 import extensions.ConstantBitwiseAndExprRange
+import extensions.StrlenLiteralRangeExpr

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/RangeAnalysis.qll

@@ -238,7 +238,7 @@ class NoReason extends Reason, TNoReason {
 class CondReason extends Reason, TCondReason {
   IRGuardCondition getCond() { this = TCondReason(result) }
 
-  override string toString() { result = getCond().toString() }
+  override string toString() { result = this.getCond().toString() }
 }
 
 /**
@@ -260,14 +260,14 @@ private predicate typeBound(IRIntegerType typ, int lowerbound, int upperbound) {
 private class NarrowingCastInstruction extends ConvertInstruction {
   NarrowingCastInstruction() {
     not this instanceof SafeCastInstruction and
-    typeBound(getResultIRType(), _, _)
+    typeBound(this.getResultIRType(), _, _)
   }
 
   /** Gets the lower bound of the resulting type. */
-  int getLowerBound() { typeBound(getResultIRType(), result, _) }
+  int getLowerBound() { typeBound(this.getResultIRType(), result, _) }
 
   /** Gets the upper bound of the resulting type. */
-  int getUpperBound() { typeBound(getResultIRType(), _, result) }
+  int getUpperBound() { typeBound(this.getResultIRType(), _, result) }
 }
 
 /**

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/RangeUtils.qll

@@ -109,8 +109,8 @@ private predicate safeCast(IRIntegerType fromtyp, IRIntegerType totyp) {
  */
 class PtrToPtrCastInstruction extends ConvertInstruction {
   PtrToPtrCastInstruction() {
-    getResultIRType() instanceof IRAddressType and
-    getUnary().getResultIRType() instanceof IRAddressType
+    this.getResultIRType() instanceof IRAddressType and
+    this.getUnary().getResultIRType() instanceof IRAddressType
   }
 }
 
@@ -119,7 +119,7 @@ class PtrToPtrCastInstruction extends ConvertInstruction {
  * that cannot overflow or underflow.
  */
 class SafeIntCastInstruction extends ConvertInstruction {
-  SafeIntCastInstruction() { safeCast(getUnary().getResultIRType(), getResultIRType()) }
+  SafeIntCastInstruction() { safeCast(this.getUnary().getResultIRType(), this.getResultIRType()) }
 }
 
 /**

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/extensions/ConstantBitwiseAndExprRange.qll

@@ -50,8 +50,8 @@ private class ConstantBitwiseAndExprRange extends SimpleRangeAnalysisExpr {
     // If an operand can have negative values, the lower bound is unconstrained.
     // Otherwise, the lower bound is zero.
     exists(float lLower, float rLower |
-      lLower = getFullyConvertedLowerBounds(getLeftOperand()) and
-      rLower = getFullyConvertedLowerBounds(getRightOperand()) and
+      lLower = getFullyConvertedLowerBounds(this.getLeftOperand()) and
+      rLower = getFullyConvertedLowerBounds(this.getRightOperand()) and
       (
         (lLower < 0 or rLower < 0) and
         result = exprMinVal(this)
@@ -68,10 +68,10 @@ private class ConstantBitwiseAndExprRange extends SimpleRangeAnalysisExpr {
     // If an operand can have negative values, the upper bound is unconstrained.
     // Otherwise, the upper bound is the minimum of the upper bounds of the operands
     exists(float lLower, float lUpper, float rLower, float rUpper |
-      lLower = getFullyConvertedLowerBounds(getLeftOperand()) and
-      lUpper = getFullyConvertedUpperBounds(getLeftOperand()) and
-      rLower = getFullyConvertedLowerBounds(getRightOperand()) and
-      rUpper = getFullyConvertedUpperBounds(getRightOperand()) and
+      lLower = getFullyConvertedLowerBounds(this.getLeftOperand()) and
+      lUpper = getFullyConvertedUpperBounds(this.getLeftOperand()) and
+      rLower = getFullyConvertedLowerBounds(this.getRightOperand()) and
+      rUpper = getFullyConvertedUpperBounds(this.getRightOperand()) and
       (
         (lLower < 0 or rLower < 0) and
         result = exprMaxVal(this)
@@ -85,6 +85,6 @@ private class ConstantBitwiseAndExprRange extends SimpleRangeAnalysisExpr {
   }
 
   override predicate dependsOnChild(Expr child) {
-    child = getLeftOperand() or child = getRightOperand()
+    child = this.getLeftOperand() or child = this.getRightOperand()
   }
 }

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/extensions/ConstantShiftExprRange.qll

@@ -50,7 +50,7 @@ class ConstantRShiftExprRange extends SimpleRangeAnalysisExpr {
    * We don't handle the case where `a` and `b` are both non-constant values.
    */
   ConstantRShiftExprRange() {
-    getUnspecifiedType() instanceof IntegralType and
+    this.getUnspecifiedType() instanceof IntegralType and
     exists(Expr l, Expr r |
       l = this.(RShiftExpr).getLeftOperand() and
       r = this.(RShiftExpr).getRightOperand()
@@ -84,10 +84,10 @@ class ConstantRShiftExprRange extends SimpleRangeAnalysisExpr {
 
   override float getLowerBounds() {
     exists(int lLower, int lUpper, int rLower, int rUpper |
-      lLower = getFullyConvertedLowerBounds(getLeftOperand()) and
-      lUpper = getFullyConvertedUpperBounds(getLeftOperand()) and
-      rLower = getFullyConvertedLowerBounds(getRightOperand()) and
-      rUpper = getFullyConvertedUpperBounds(getRightOperand()) and
+      lLower = getFullyConvertedLowerBounds(this.getLeftOperand()) and
+      lUpper = getFullyConvertedUpperBounds(this.getLeftOperand()) and
+      rLower = getFullyConvertedLowerBounds(this.getRightOperand()) and
+      rUpper = getFullyConvertedUpperBounds(this.getRightOperand()) and
       lLower <= lUpper and
       rLower <= rUpper
     |
@@ -95,8 +95,8 @@ class ConstantRShiftExprRange extends SimpleRangeAnalysisExpr {
         lLower < 0
         or
         not (
-          isValidShiftExprShift(rLower, getLeftOperand()) and
-          isValidShiftExprShift(rUpper, getLeftOperand())
+          isValidShiftExprShift(rLower, this.getLeftOperand()) and
+          isValidShiftExprShift(rUpper, this.getLeftOperand())
         )
       then
         // We don't want to deal with shifting negative numbers at the moment,
@@ -111,10 +111,10 @@ class ConstantRShiftExprRange extends SimpleRangeAnalysisExpr {
 
   override float getUpperBounds() {
     exists(int lLower, int lUpper, int rLower, int rUpper |
-      lLower = getFullyConvertedLowerBounds(getLeftOperand()) and
-      lUpper = getFullyConvertedUpperBounds(getLeftOperand()) and
-      rLower = getFullyConvertedLowerBounds(getRightOperand()) and
-      rUpper = getFullyConvertedUpperBounds(getRightOperand()) and
+      lLower = getFullyConvertedLowerBounds(this.getLeftOperand()) and
+      lUpper = getFullyConvertedUpperBounds(this.getLeftOperand()) and
+      rLower = getFullyConvertedLowerBounds(this.getRightOperand()) and
+      rUpper = getFullyConvertedUpperBounds(this.getRightOperand()) and
       lLower <= lUpper and
       rLower <= rUpper
     |
@@ -122,8 +122,8 @@ class ConstantRShiftExprRange extends SimpleRangeAnalysisExpr {
         lLower < 0
         or
         not (
-          isValidShiftExprShift(rLower, getLeftOperand()) and
-          isValidShiftExprShift(rUpper, getLeftOperand())
+          isValidShiftExprShift(rLower, this.getLeftOperand()) and
+          isValidShiftExprShift(rUpper, this.getLeftOperand())
         )
       then
         // We don't want to deal with shifting negative numbers at the moment,
@@ -137,7 +137,7 @@ class ConstantRShiftExprRange extends SimpleRangeAnalysisExpr {
   }
 
   override predicate dependsOnChild(Expr child) {
-    child = getLeftOperand() or child = getRightOperand()
+    child = this.getLeftOperand() or child = this.getRightOperand()
   }
 }
 
@@ -163,7 +163,7 @@ class ConstantLShiftExprRange extends SimpleRangeAnalysisExpr {
    * We don't handle the case where `a` and `b` are both non-constant values.
    */
   ConstantLShiftExprRange() {
-    getUnspecifiedType() instanceof IntegralType and
+    this.getUnspecifiedType() instanceof IntegralType and
     exists(Expr l, Expr r |
       l = this.(LShiftExpr).getLeftOperand() and
       r = this.(LShiftExpr).getRightOperand()
@@ -197,10 +197,10 @@ class ConstantLShiftExprRange extends SimpleRangeAnalysisExpr {
 
   override float getLowerBounds() {
     exists(int lLower, int lUpper, int rLower, int rUpper |
-      lLower = getFullyConvertedLowerBounds(getLeftOperand()) and
-      lUpper = getFullyConvertedUpperBounds(getLeftOperand()) and
-      rLower = getFullyConvertedLowerBounds(getRightOperand()) and
-      rUpper = getFullyConvertedUpperBounds(getRightOperand()) and
+      lLower = getFullyConvertedLowerBounds(this.getLeftOperand()) and
+      lUpper = getFullyConvertedUpperBounds(this.getLeftOperand()) and
+      rLower = getFullyConvertedLowerBounds(this.getRightOperand()) and
+      rUpper = getFullyConvertedUpperBounds(this.getRightOperand()) and
       lLower <= lUpper and
       rLower <= rUpper
     |
@@ -208,8 +208,8 @@ class ConstantLShiftExprRange extends SimpleRangeAnalysisExpr {
         lLower < 0
         or
         not (
-          isValidShiftExprShift(rLower, getLeftOperand()) and
-          isValidShiftExprShift(rUpper, getLeftOperand())
+          isValidShiftExprShift(rLower, this.getLeftOperand()) and
+          isValidShiftExprShift(rUpper, this.getLeftOperand())
         )
       then
         // We don't want to deal with shifting negative numbers at the moment,
@@ -228,10 +228,10 @@ class ConstantLShiftExprRange extends SimpleRangeAnalysisExpr {
 
   override float getUpperBounds() {
     exists(int lLower, int lUpper, int rLower, int rUpper |
-      lLower = getFullyConvertedLowerBounds(getLeftOperand()) and
-      lUpper = getFullyConvertedUpperBounds(getLeftOperand()) and
-      rLower = getFullyConvertedLowerBounds(getRightOperand()) and
-      rUpper = getFullyConvertedUpperBounds(getRightOperand()) and
+      lLower = getFullyConvertedLowerBounds(this.getLeftOperand()) and
+      lUpper = getFullyConvertedUpperBounds(this.getLeftOperand()) and
+      rLower = getFullyConvertedLowerBounds(this.getRightOperand()) and
+      rUpper = getFullyConvertedUpperBounds(this.getRightOperand()) and
       lLower <= lUpper and
       rLower <= rUpper
     |
@@ -239,8 +239,8 @@ class ConstantLShiftExprRange extends SimpleRangeAnalysisExpr {
         lLower < 0
         or
         not (
-          isValidShiftExprShift(rLower, getLeftOperand()) and
-          isValidShiftExprShift(rUpper, getLeftOperand())
+          isValidShiftExprShift(rLower, this.getLeftOperand()) and
+          isValidShiftExprShift(rUpper, this.getLeftOperand())
         )
       then
         // We don't want to deal with shifting negative numbers at the moment,
@@ -258,6 +258,6 @@ class ConstantLShiftExprRange extends SimpleRangeAnalysisExpr {
   }
 
   override predicate dependsOnChild(Expr child) {
-    child = getLeftOperand() or child = getRightOperand()
+    child = this.getLeftOperand() or child = this.getRightOperand()
   }
 }

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/extensions/RangeNode.qll

@@ -0,0 +1,118 @@
+/**
+ * This module implements subclasses for various DataFlow nodes that extends
+ * their `toString()` predicates with range information, if applicable. By
+ * including this module in a `path-problem` query, this range information
+ * will be displayed at each step in the query results.
+ *
+ * This is currently implemented for `DataFlow::ExprNode` and `DataFlow::DefinitionByReferenceNode`,
+ * but it is not yet implemented for `DataFlow::ParameterNode`.
+ */
+
+private import cpp
+private import semmle.code.cpp.dataflow.DataFlow
+private import semmle.code.cpp.rangeanalysis.SimpleRangeAnalysis
+
+string getExprBoundAsString(Expr e) {
+  if exists(lowerBound(e)) and exists(upperBound(e))
+  then result = "[" + lowerBound(e) + ", " + upperBound(e) + "]"
+  else result = "[unknown range]"
+}
+
+/**
+ * Holds for any integer type after resolving typedefs and stripping `const`
+ * specifiers, such as for `const size_t`
+ */
+predicate isIntegralType(Type t) {
+  // We use `getUnspecifiedType` here because without it things like
+  // `const size_t` aren't considered to be integral
+  t.getUnspecifiedType() instanceof IntegralType
+}
+
+/**
+ * Holds for any reference to an integer type after resolving typedefs and
+ * stripping `const` specifiers, such as for `const size_t&`
+ */
+predicate isIntegralReferenceType(Type t) { isIntegralType(t.(ReferenceType).stripType()) }
+
+/**
+ * Holds for any pointer to an integer type after resolving typedefs and
+ * stripping `const` specifiers, such as for `const size_t*`. This predicate
+ * holds for any pointer depth, such as for `const size_t**`.
+ */
+predicate isIntegralPointerType(Type t) { isIntegralType(t.(PointerType).stripType()) }
+
+predicate hasIntegralOrReferenceIntegralType(Locatable e) {
+  exists(Type t |
+    (
+      t = e.(Expr).getUnspecifiedType()
+      or
+      // This will cover variables, parameters, type declarations, etc.
+      t = e.(DeclarationEntry).getUnspecifiedType()
+    ) and
+    (isIntegralType(t) or isIntegralReferenceType(t))
+  )
+}
+
+Expr getLOp(Operation o) {
+  result = o.(BinaryOperation).getLeftOperand() or
+  result = o.(Assignment).getLValue()
+}
+
+Expr getROp(Operation o) {
+  result = o.(BinaryOperation).getRightOperand() or
+  result = o.(Assignment).getRValue()
+}
+
+/**
+ * Display the ranges of expressions in the path view
+ */
+private class ExprRangeNode extends DataFlow::ExprNode {
+  pragma[inline]
+  private string getIntegralBounds(Expr arg) {
+    if hasIntegralOrReferenceIntegralType(arg)
+    then result = getExprBoundAsString(arg)
+    else result = ""
+  }
+
+  private string getOperationBounds(Operation e) {
+    result =
+      getExprBoundAsString(e) + " = " + getExprBoundAsString(getLOp(e)) + e.getOperator() +
+        getExprBoundAsString(getROp(e))
+  }
+
+  private string getCallBounds(Call e) {
+    result =
+      getExprBoundAsString(e) + "(" +
+        concat(Expr arg, int i |
+          arg = e.getArgument(i)
+        |
+          this.getIntegralBounds(arg), "," order by i
+        ) + ")"
+  }
+
+  override string toString() {
+    exists(Expr e | e = this.getExpr() |
+      if hasIntegralOrReferenceIntegralType(e)
+      then
+        result = super.toString() + ": " + this.getOperationBounds(e)
+        or
+        result = super.toString() + ": " + this.getCallBounds(e)
+        or
+        not exists(this.getOperationBounds(e)) and
+        not exists(this.getCallBounds(e)) and
+        result = super.toString() + ": " + getExprBoundAsString(e)
+      else result = super.toString()
+    )
+  }
+}
+
+/**
+ * Display the ranges of expressions in the path view
+ */
+private class ReferenceArgumentRangeNode extends DataFlow::DefinitionByReferenceNode {
+  override string toString() {
+    if hasIntegralOrReferenceIntegralType(this.asDefiningArgument())
+    then result = super.toString() + ": " + getExprBoundAsString(this.getArgument())
+    else result = super.toString()
+  }
+}

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/extensions/StrlenLiteralRangeExpr.qll

@@ -0,0 +1,18 @@
+private import cpp
+private import experimental.semmle.code.cpp.models.interfaces.SimpleRangeAnalysisExpr
+
+/**
+ * Provides range analysis information for calls to `strlen` on literal strings.
+ * For example, the range of `strlen("literal")` will be 7.
+ */
+class StrlenLiteralRangeExpr extends SimpleRangeAnalysisExpr, FunctionCall {
+  StrlenLiteralRangeExpr() {
+    this.getTarget().hasGlobalOrStdName("strlen") and this.getArgument(0).isConstant()
+  }
+
+  override int getLowerBounds() { result = this.getArgument(0).getValue().length() }
+
+  override int getUpperBounds() { result = this.getArgument(0).getValue().length() }
+
+  override predicate dependsOnChild(Expr e) { none() }
+}

cpp/ql/lib/experimental/semmle/code/cpp/rangeanalysis/extensions/SubtractSelf.qll

@@ -3,8 +3,8 @@ import experimental.semmle.code.cpp.models.interfaces.SimpleRangeAnalysisExpr
 private class SelfSub extends SimpleRangeAnalysisExpr, SubExpr {
   SelfSub() {
     // Match `x - x` but not `myInt - (unsigned char)myInt`.
-    getLeftOperand().getExplicitlyConverted().(VariableAccess).getTarget() =
-      getRightOperand().getExplicitlyConverted().(VariableAccess).getTarget()
+    this.getLeftOperand().getExplicitlyConverted().(VariableAccess).getTarget() =
+      this.getRightOperand().getExplicitlyConverted().(VariableAccess).getTarget()
   }
 
   override float getLowerBounds() { result = 0 }