fix QL match-string pattern

Java: fix syntax error in path-injection example fix

.github/ISSUE_TEMPLATE/lgtm-com---false-positive.md

@@ -1,24 +0,0 @@
----
-name: LGTM.com - false positive
-about: Tell us about an alert that shouldn't be reported
-title: LGTM.com - false positive
-labels: false-positive
-assignees: ''
-
----
-
-**Description of the false positive**
-
-<!-- Please explain briefly why you think it shouldn't be included. -->
-
-**URL to the alert on the project page on LGTM.com**
-
-<!--
-1. Open the project on LGTM.com.
-For example, https://lgtm.com/projects/g/pallets/click/.
-2. Switch to the `Alerts` tab. For example, https://lgtm.com/projects/g/pallets/click/alerts/.
-3. Scroll to the alert that you would like to report.
-4. Click on the right most icon `View this alert within the complete file`.
-5. A new browser tab opens. Copy and paste the page URL here.
-For example, https://lgtm.com/projects/g/pallets/click/snapshot/719fb7d8322b0767cdd1e5903ba3eb3233ba8dd5/files/click/_winconsole.py#xa08d213ab3289f87:1.
--->

.github/ISSUE_TEMPLATE/ql---general.md

@@ -10,5 +10,5 @@ assignees: ''
 **Description of the issue**
 
 <!-- Please explain briefly what is the problem.
-If it is about an LGTM project, please include its URL.-->
+If it is about a GitHub project, please include its URL. -->
 

.github/ISSUE_TEMPLATE/ql--false-positive.md

@@ -0,0 +1,36 @@
+---
+name: CodeQL false positive
+about: Report CodeQL alerts that you think should not have been detected (not applicable, not exploitable, etc.)
+title: False positive
+labels: false-positive
+assignees: ''
+
+---
+
+**Description of the false positive**
+
+<!-- Please explain briefly why you think it shouldn't be included. -->
+
+**Code samples or links to source code**
+
+<!--
+For open source code: file links with line numbers on GitHub, for example:
+https://github.com/github/codeql/blob/dc440aaee6695deb0d9676b87e06ea984e1b4ae5/javascript/ql/test/query-tests/Security/CWE-078/CommandInjection/exec-sh2.js#L10
+
+For closed source code: (redacted) code samples that illustrate the problem, for example:
+
+```
+function execSh(command, options) {
+    return cp.spawn(getShell(), ["-c", command], options) // <- command line injection
+};
+```
+-->
+
+**URL to the alert on GitHub code scanning (optional)**
+
+<!--
+1. Open the project on GitHub.com.
+2. Switch to the `Security` tab.
+3. Browse to the alert that you would like to report.
+4. Copy and paste the page URL here.
+-->

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

@@ -0,0 +1,55 @@
+name: Cache query compilation
+description: Caches CodeQL compilation caches - should be run both on PRs and pushes to main.
+
+inputs:
+  key:
+    description: 'The cache key to use - should be unique to the workflow'
+    required: true
+
+outputs:
+  cache-dir:
+    description: "The directory where the cache was stored"
+    value: ${{ steps.fill-compilation-dir.outputs.compdir }}
+
+runs:
+  using: composite
+  steps:
+    # calculate the merge-base with main, in a way that works both on PRs and pushes to main.
+    - name: Calculate merge-base
+      shell: bash
+      if: ${{ github.event_name == 'pull_request' }}
+      env:
+        BASE_BRANCH: ${{ github.base_ref }}
+      run: |
+        MERGE_BASE=$(git cat-file commit $GITHUB_SHA | grep '^parent ' | head -1 | cut -f 2 -d " ")
+        echo "merge_base=$MERGE_BASE" >> $GITHUB_ENV
+    - name: Restore read-only cache (PR)
+      if: ${{ github.event_name == 'pull_request' }}
+      uses: erik-krogh/actions-cache@a88d0603fe5fb5606db9f002dfcadeb32b5f84c6
+      with:
+        path: '**/.cache'
+        read-only: true
+        key: codeql-compile-${{ inputs.key }}-pr-${{ github.sha }}
+        restore-keys: |
+          codeql-compile-${{ inputs.key }}-${{ github.base_ref }}-${{ env.merge_base }}
+          codeql-compile-${{ inputs.key }}-${{ github.base_ref }}-
+          codeql-compile-${{ inputs.key }}-main-
+    - name: Fill cache (push)
+      if: ${{ github.event_name != 'pull_request' }}
+      uses: erik-krogh/actions-cache@a88d0603fe5fb5606db9f002dfcadeb32b5f84c6
+      with:
+        path: '**/.cache'
+        key: codeql-compile-${{ 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
+      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

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

@@ -0,0 +1,75 @@
+// # 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/actions/fetch-codeql/action.yml

@@ -1,14 +1,22 @@
 name: Fetch CodeQL
 description: Fetches the latest version of CodeQL
+
+inputs:
+  channel:
+    description: 'The CodeQL channel to use'
+    required: false
+    default: 'nightly'
+
 runs:
   using: composite
   steps:
     - name: Fetch CodeQL
       shell: bash
-      run: |
-        gh extension install github/gh-codeql
-        gh codeql set-channel nightly
-        gh codeql version
-        gh codeql version --format=json | jq -r .unpackedLocation >> "${GITHUB_PATH}"
       env:
         GITHUB_TOKEN: ${{ github.token }}
+        CHANNEL: ${{ inputs.channel }}
+      run: |
+        gh extension install github/gh-codeql
+        gh codeql set-channel "$CHANNEL"
+        gh codeql version
+        gh codeql version --format=json | jq -r .unpackedLocation >> "${GITHUB_PATH}"

.github/labeler.yml

@@ -43,3 +43,14 @@ documentation:
 "QL-for-QL":
   - ql/**/*
   - .github/workflows/ql-for-ql*
+
+# Since these are all shared files that need to be synced, just pick _one_ copy of each.
+"DataFlow Library":
+  - "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl.qll"
+  - "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplCommon.qll"
+  - "java/ql/lib/semmle/code/java/dataflow/internal/tainttracking1/TaintTrackingImpl.qll"
+  - "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplConsistency.qll"
+  - "java/ql/lib/semmle/code/java/dataflow/internal/FlowSummaryImpl.qll"
+
+"ATM":
+  - javascript/ql/experimental/adaptivethreatmodeling/**/*

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

@@ -0,0 +1,93 @@
+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
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Setup CodeQL
+        uses: ./.github/actions/fetch-codeql
+        with:
+          channel: release
+
+      - 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}" >> "${GITHUB_ENV}"
+
+          codeql database analyze \
+            --format sarif-latest \
+            --output "${SARIF_PATH}" \
+            --sarif-group-rules-by-pack \
+            -vv \
+            -- \
+            "${DB_PATH}" \
+            "${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

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

.github/workflows/compile-queries.yml

@@ -0,0 +1,37 @@
+name: "Compile all queries using the latest stable CodeQL CLI"
+
+on:
+  push:
+    branches:  # makes sure the cache gets populated - running on the branches people tend to merge into.
+      - main
+      - "rc/*"
+      - "codeql-cli-*"
+  pull_request:
+
+jobs:
+  compile-queries:
+    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: all-queries
+      - name: check formatting
+        run: find */ql -type f \( -name "*.qll" -o -name "*.ql" \) -print0 | xargs -0 codeql query format --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 }}"
+      - 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 }}"

.github/workflows/csharp-qltest.yml

@@ -0,0 +1,86 @@
+name: "C#: Run QL Tests"
+
+on:
+  push:
+    paths:
+      - "csharp/**"
+      - "shared/**"
+      - .github/actions/fetch-codeql/action.yml
+      - codeql-workspace.yml
+    branches:
+      - main
+      - "rc/*"
+  pull_request:
+    paths:
+      - "csharp/**"
+      - "shared/**"
+      - .github/workflows/csharp-qltest.yml
+      - .github/actions/fetch-codeql/action.yml
+      - codeql-workspace.yml
+    branches:
+      - main
+      - "rc/*"
+
+defaults:
+  run:
+    working-directory: csharp
+
+jobs:
+  qlupgrade:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./.github/actions/fetch-codeql
+      - name: Check DB upgrade scripts
+        run: |
+          echo >empty.trap
+          codeql dataset import -S ql/lib/upgrades/initial/semmlecode.csharp.dbscheme testdb empty.trap
+          codeql dataset upgrade testdb --additional-packs ql/lib
+          diff -q testdb/semmlecode.csharp.dbscheme ql/lib/semmlecode.csharp.dbscheme
+      - name: Check DB downgrade scripts
+        run: |
+          echo >empty.trap
+          rm -rf testdb; codeql dataset import -S ql/lib/semmlecode.csharp.dbscheme testdb empty.trap
+          codeql resolve upgrades --format=lines --allow-downgrades --additional-packs downgrades \
+           --dbscheme=ql/lib/semmlecode.csharp.dbscheme --target-dbscheme=downgrades/initial/semmlecode.csharp.dbscheme |
+           xargs codeql execute upgrades testdb
+          diff -q testdb/semmlecode.csharp.dbscheme downgrades/initial/semmlecode.csharp.dbscheme
+  qltest:
+    runs-on: ubuntu-latest-xl
+    strategy:
+      fail-fast: false
+      matrix:
+        slice: ["1/2", "2/2"]
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./.github/actions/fetch-codeql
+      - uses: ./csharp/actions/create-extractor-pack
+      - name: Cache compilation cache
+        id: query-cache
+        uses: ./.github/actions/cache-query-compilation
+        with:
+          key: csharp-qltest-${{ matrix.slice }}
+      - name: Run QL tests
+        run: |
+          CODEQL_PATH=$(gh codeql version --format=json | jq -r .unpackedLocation)
+          # The legacy ASP extractor is not in this repo, so take the one from the nightly build
+          mv "$CODEQL_PATH/csharp/tools/extractor-asp.jar" "${{ github.workspace }}/csharp/extractor-pack/tools"
+          # Safe guard against using the bundled extractor
+          rm -rf "$CODEQL_PATH/csharp"
+          codeql test run --threads=0 --ram 52000 --slice ${{ matrix.slice }} --search-path "${{ github.workspace }}/csharp/extractor-pack" --check-databases --check-undefined-labels --check-repeated-labels --check-redefined-labels --consistency-queries ql/consistency-queries ql/test --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+  unit-tests:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Setup dotnet
+        uses: actions/setup-dotnet@v3
+        with:
+          dotnet-version: 6.0.202
+      - name: Extractor unit tests
+        run: |
+          dotnet test -p:RuntimeFrameworkVersion=6.0.4 "${{ github.workspace }}/csharp/extractor/Semmle.Util.Tests"
+          dotnet test -p:RuntimeFrameworkVersion=6.0.4 "${{ github.workspace }}/csharp/extractor/Semmle.Extraction.Tests"
+          dotnet test -p:RuntimeFrameworkVersion=6.0.4 "${{ github.workspace }}/csharp/autobuilder/Semmle.Autobuild.CSharp.Tests"
+          dotnet test -p:RuntimeFrameworkVersion=6.0.4 "${{ github.workspace }}/cpp/autobuilder/Semmle.Autobuild.Cpp.Tests"

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

@@ -0,0 +1,80 @@
+name: "Go: Run Tests - Other OS"
+on:
+  pull_request:
+    paths:
+      - "go/**"
+      - "!go/ql/**" # don't run other-os if only ql/ files changed
+      - .github/workflows/go-tests-other-os.yml
+      - .github/actions/**
+      - codeql-workspace.yml
+jobs:
+  test-mac:
+    name: Test MacOS
+    runs-on: macos-latest
+    steps:
+      - name: Set up Go 1.19
+        uses: actions/setup-go@v3
+        with:
+          go-version: 1.19
+        id: go
+
+      - name: Check out code
+        uses: actions/checkout@v2
+
+      - name: Set up CodeQL CLI
+        uses: ./.github/actions/fetch-codeql
+
+      - name: Enable problem matchers in repository
+        shell: bash
+        run: 'find .github/problem-matchers -name \*.json -exec echo "::add-matcher::{}" \;'
+
+      - name: Build
+        run: |
+          cd go
+          make
+
+      - name: Cache compilation cache
+        id: query-cache
+        uses: ./.github/actions/cache-query-compilation
+        with:
+          key: go-qltest
+      - name: Test
+        run: |
+          cd go
+          make test cache="${{ steps.query-cache.outputs.cache-dir }}"
+
+  test-win:
+    name: Test Windows
+    runs-on: windows-latest-xl
+    steps:
+      - name: Set up Go 1.19
+        uses: actions/setup-go@v3
+        with:
+          go-version: 1.19
+        id: go
+
+      - name: Check out code
+        uses: actions/checkout@v2
+
+      - name: Set up CodeQL CLI
+        uses: ./.github/actions/fetch-codeql
+
+      - name: Enable problem matchers in repository
+        shell: bash
+        run: 'find .github/problem-matchers -name \*.json -exec echo "::add-matcher::{}" \;'
+
+      - name: Build
+        run: |
+          cd go
+          make
+
+      - name: Cache compilation cache
+        id: query-cache
+        uses: ./.github/actions/cache-query-compilation
+        with:
+          key: go-qltest
+
+      - name: Test
+        run: |
+          cd go
+          make test cache="${{ steps.query-cache.outputs.cache-dir }}"

.github/workflows/go-tests.yml

@@ -1,15 +1,24 @@
 name: "Go: Run Tests"
 on:
+  push:
+    paths:
+      - "go/**"
+      - .github/workflows/go-tests.yml
+      - .github/actions/**
+      - codeql-workspace.yml
+    branches:
+      - main
+      - "rc/*"
   pull_request:
     paths:
       - "go/**"
       - .github/workflows/go-tests.yml
-      - .github/actions/fetch-codeql/action.yml
+      - .github/actions/**
       - codeql-workspace.yml
 jobs:
   test-linux:
     name: Test Linux (Ubuntu)
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-latest-xl
     steps:
       - name: Set up Go 1.19
         uses: actions/setup-go@v3
@@ -32,7 +41,7 @@ jobs:
           cd go
           make
 
-      - name: Check that all QL and Go code is autoformatted
+      - name: Check that all Go code is autoformatted
         run: |
           cd go
           make check-formatting
@@ -48,67 +57,13 @@ jobs:
           name: qhelp-markdown
           path: go/qhelp-out/**/*.md
 
-      - name: Test
-        run: |
-          cd go
-          make test
-
-  test-mac:
-    name: Test MacOS
-    runs-on: macos-latest
-    steps:
-      - name: Set up Go 1.19
-        uses: actions/setup-go@v3
+      - name: Cache compilation cache
+        id: query-cache
+        uses: ./.github/actions/cache-query-compilation
         with:
-          go-version: 1.19
-        id: go
-
-      - name: Check out code
-        uses: actions/checkout@v2
-
-      - name: Set up CodeQL CLI
-        uses: ./.github/actions/fetch-codeql
-
-      - name: Enable problem matchers in repository
-        shell: bash
-        run: 'find .github/problem-matchers -name \*.json -exec echo "::add-matcher::{}" \;'
-
-      - name: Build
-        run: |
-          cd go
-          make
+          key: go-qltest
 
       - name: Test
         run: |
           cd go
-          make test
-
-  test-win:
-    name: Test Windows
-    runs-on: windows-2019
-    steps:
-      - name: Set up Go 1.19
-        uses: actions/setup-go@v3
-        with:
-          go-version: 1.19
-        id: go
-
-      - name: Check out code
-        uses: actions/checkout@v2
-
-      - name: Set up CodeQL CLI
-        uses: ./.github/actions/fetch-codeql
-
-      - name: Enable problem matchers in repository
-        shell: bash
-        run: 'find .github/problem-matchers -name \*.json -exec echo "::add-matcher::{}" \;'
-
-      - name: Build
-        run: |
-          cd go
-          make
-
-      - name: Test
-        run: |
-          cd go
-          make test
+          make test cache="${{ steps.query-cache.outputs.cache-dir }}"

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

@@ -23,22 +23,9 @@ defaults:
     working-directory: javascript/ql/experimental/adaptivethreatmodeling
 
 jobs:
-  qlformat:
-    name: Check QL formatting
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-
-      - uses: ./.github/actions/fetch-codeql
-
-      - name: Check QL formatting
-        run: |
-          find . "(" -name "*.ql" -or -name "*.qll" ")" -print0 | \
-            xargs -0 codeql query format --check-only
-
-  qlcompile:
-    name: Check QL compilation
-    runs-on: ubuntu-latest
+  qltest:
+    name: Test QL
+    runs-on: ubuntu-latest-xl
     steps:
       - uses: actions/checkout@v3
 
@@ -46,36 +33,33 @@ jobs:
 
       - name: Install pack dependencies
         run: |
-          for pack in modelbuilding src; do
+          for pack in modelbuilding src test; do
             codeql pack install --mode verify -- "${pack}"
           done
+      
+      - name: Cache compilation cache
+        id: query-cache
+        uses: ./.github/actions/cache-query-compilation
+        with: 
+          key: js-ml-test
 
       - name: Check QL compilation
         run: |
           codeql query compile \
             --check-only \
-            --ram 5120 \
+            --ram 52000 \
             --additional-packs "${{ github.workspace }}" \
             --threads=0 \
+            --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}" \
             -- \
             lib modelbuilding src
 
-  qltest:
-    name: Run QL tests
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-
-      - uses: ./.github/actions/fetch-codeql
-
-      - name: Install pack dependencies
-        run: codeql pack install -- test
-
       - name: Run QL tests
         run: |
           codeql test run \
             --threads=0 \
-            --ram 5120 \
+            --ram 52000 \
             --additional-packs "${{ github.workspace }}" \
+            --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}" \
             -- \
-            test
+            test

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

@@ -27,7 +27,7 @@ on:
       - main
       - "rc/*"
     paths:
-      - "ruby/**/*.qhelp"
+      - "**/*.qhelp"
 
 jobs:
   qhelp:
@@ -52,7 +52,7 @@ jobs:
         id: changes
         run: |
           (git diff -z --name-only --diff-filter=ACMRT HEAD~1 HEAD | grep -z '.qhelp$' | grep -z -v '.inc.qhelp';
-           git diff -z --name-only --diff-filter=ACMRT HEAD~1 HEAD | grep -z '.inc.qhelp$' | xargs --null -rn1 basename | xargs --null -rn1 git grep -z -l) |
+           git diff -z --name-only --diff-filter=ACMRT HEAD~1 HEAD | grep -z '.inc.qhelp$' | xargs --null -rn1 basename -z | xargs --null -rn1 git grep -z -l) |
            grep -z '.qhelp$' | grep -z -v '^-' | sort -z -u > "${RUNNER_TEMP}/paths.txt"
 
       - name: QHelp preview

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

@@ -24,13 +24,13 @@ jobs:
       - uses: actions/checkout@v3
       - name: Find codeql
         id: find-codeql
-        uses: github/codeql-action/init@71a8b35ff4c80fcfcd05bc1cd932fe3c08f943ca
+        uses: github/codeql-action/init@77a8d2d10c0b403a8b4aadbd223dc489ecd22683
         with:
           languages: javascript # does not matter
       - name: Get CodeQL version
         id: get-codeql-version
         run: |
-          echo "::set-output name=version::$("${CODEQL}" --version | head -n 1 | rev | cut -d " " -f 1 | rev)"
+          echo "version=$("${CODEQL}" --version | head -n 1 | rev | cut -d " " -f 1 | rev)" >> $GITHUB_OUTPUT
         shell: bash
         env:
           CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
@@ -133,7 +133,7 @@ jobs:
         env:
           CONF: ./ql-for-ql-config.yml
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@71a8b35ff4c80fcfcd05bc1cd932fe3c08f943ca
+        uses: github/codeql-action/init@77a8d2d10c0b403a8b4aadbd223dc489ecd22683
         with:
           languages: ql
           db-location: ${{ runner.temp }}/db
@@ -145,7 +145,7 @@ jobs:
           PACK: ${{ runner.temp }}/pack
 
       - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@71a8b35ff4c80fcfcd05bc1cd932fe3c08f943ca
+        uses: github/codeql-action/analyze@77a8d2d10c0b403a8b4aadbd223dc489ecd22683
         with:
           category: "ql-for-ql"
       - name: Copy sarif file to CWD

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

@@ -25,7 +25,7 @@ jobs:
 
       - name: Find codeql
         id: find-codeql
-        uses: github/codeql-action/init@71a8b35ff4c80fcfcd05bc1cd932fe3c08f943ca
+        uses: github/codeql-action/init@77a8d2d10c0b403a8b4aadbd223dc489ecd22683
         with:
           languages: javascript # does not matter
       - uses: actions/cache@v3

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

@@ -22,7 +22,7 @@ jobs:
       - uses: actions/checkout@v3
       - name: Find codeql
         id: find-codeql
-        uses: github/codeql-action/init@71a8b35ff4c80fcfcd05bc1cd932fe3c08f943ca
+        uses: github/codeql-action/init@77a8d2d10c0b403a8b4aadbd223dc489ecd22683
         with:
           languages: javascript # does not matter
       - uses: actions/cache@v3
@@ -47,8 +47,3 @@ jobs:
           find ql/ql/src "(" -name "*.ql" -or -name "*.qll" ")" -print0 | xargs -0 "${CODEQL}" query format --check-only
         env:
           CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
-      - name: Check QL compilation
-        run: |
-          "${CODEQL}" query compile --check-only --threads=4 --warnings=error --search-path "${{ github.workspace }}/ql/extractor-pack" "ql/ql/src" "ql/ql/examples"
-        env:
-          CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}

.github/workflows/ruby-build.yml

@@ -48,7 +48,19 @@ jobs:
         run: |
           brew install gnu-tar
           echo "/usr/local/opt/gnu-tar/libexec/gnubin" >> $GITHUB_PATH
+      - name: Cache entire extractor
+        uses: actions/cache@v3
+        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: ${{ runner.os }}-ruby-extractor-${{ hashFiles('ruby/rust-toolchain.toml', 'ruby/**/Cargo.lock') }}--${{ hashFiles('ruby/**/*.rs') }}
       - uses: actions/cache@v3
+        if: steps.cache-extractor.outputs.cache-hit != 'true'
         with:
           path: |
             ~/.cargo/registry
@@ -56,15 +68,19 @@ jobs:
             ruby/target
           key: ${{ runner.os }}-ruby-rust-cargo-${{ hashFiles('ruby/rust-toolchain.toml', 'ruby/**/Cargo.lock') }}
       - name: Check formatting
+        if: steps.cache-extractor.outputs.cache-hit != 'true'
         run: cargo fmt --all -- --check
       - name: Build
+        if: steps.cache-extractor.outputs.cache-hit != 'true'
         run: 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
       - name: Generate dbscheme
-        if: ${{ matrix.os == 'ubuntu-latest' }}
+        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
       - uses: actions/upload-artifact@v3
         if: ${{ matrix.os == 'ubuntu-latest' }}
@@ -86,19 +102,24 @@ jobs:
             ruby/target/release/ruby-extractor.exe
           retention-days: 1
   compile-queries:
-    runs-on: ubuntu-latest
-    env:
-      CODEQL_THREADS: 4 # TODO: remove this once it's set by the CLI
+    runs-on: ubuntu-latest-xl
     steps:
       - uses: actions/checkout@v3
       - name: Fetch CodeQL
         uses: ./.github/actions/fetch-codeql
+      - name: Cache compilation cache
+        id: query-cache
+        uses: ./.github/actions/cache-query-compilation
+        with: 
+          key: ruby-build
       - name: Build Query Pack
         run: |
+          rm -rf target/packs
           codeql pack create ../shared/ssa --output target/packs
+          codeql pack create ../misc/suite-helpers --output target/packs
+          codeql pack create ../shared/regex --output target/packs
           codeql pack create ql/lib --output target/packs
-          codeql pack install ql/src
-          codeql pack create ql/src --output target/packs
+          codeql pack create -j0 ql/src --output target/packs --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"
           PACK_FOLDER=$(readlink -f target/packs/codeql/ruby-queries/*)
           codeql generate query-help --format=sarifv2.1.0 --output="${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}/{}" \;)
@@ -202,7 +223,7 @@ jobs:
           echo 'name: sample-tests
           version: 0.0.0
           dependencies:
-            codeql/ruby-all: 0.0.1
+            codeql/ruby-all: "*"
           extractor: ruby
           tests: .
           ' > qlpack.yml

.github/workflows/ruby-qltest.yml

@@ -4,7 +4,7 @@ on:
   push:
     paths:
       - "ruby/**"
-      - .github/workflows/ruby-qltest.yml
+      - .github/workflows/ruby-build.yml
       - .github/actions/fetch-codeql/action.yml
       - codeql-workspace.yml
     branches:
@@ -28,23 +28,6 @@ defaults:
     working-directory: ruby
 
 jobs:
-  qlformat:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - uses: ./.github/actions/fetch-codeql
-      - name: Check QL formatting
-        run: find ql "(" -name "*.ql" -or -name "*.qll" ")" -print0 | xargs -0 codeql query format --check-only
-  qlcompile:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - uses: ./.github/actions/fetch-codeql
-      - name: Check QL compilation
-        run: |
-          codeql query compile --check-only --threads=0 --ram 5000 --warnings=error "ql/src" "ql/examples"
-        env:
-          GITHUB_TOKEN: ${{ github.token }}
   qlupgrade:
     runs-on: ubuntu-latest
     steps:
@@ -65,17 +48,20 @@ jobs:
            xargs codeql execute upgrades testdb
           diff -q testdb/ruby.dbscheme downgrades/initial/ruby.dbscheme
   qltest:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-latest-xl
     strategy:
       fail-fast: false
-      matrix:
-        slice: ["1/2", "2/2"]
     steps:
       - uses: actions/checkout@v3
       - uses: ./.github/actions/fetch-codeql
       - uses: ./ruby/actions/create-extractor-pack
+      - name: Cache compilation cache
+        id: query-cache
+        uses: ./.github/actions/cache-query-compilation
+        with: 
+          key: ruby-qltest
       - name: Run QL tests
         run: |
-          codeql test run --threads=0 --ram 5000 --slice ${{ matrix.slice }} --search-path "${{ github.workspace }}/ruby/extractor-pack" --check-databases --check-unused-labels --check-repeated-labels --check-redefined-labels --check-use-before-definition --consistency-queries ql/consistency-queries ql/test
+          codeql test run --threads=0 --ram 52000 --search-path "${{ github.workspace }}/ruby/extractor-pack" --check-databases --check-undefined-labels --check-unused-labels --check-repeated-labels --check-redefined-labels --check-use-before-definition --consistency-queries ql/consistency-queries ql/test --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"
         env:
           GITHUB_TOKEN: ${{ github.token }}

.github/workflows/swift-codegen.yml

@@ -1,39 +0,0 @@
-name: "Swift: Check code generation"
-
-on:
-  pull_request:
-    paths:
-      - "swift/**"
-      - "misc/bazel/**"
-      - "*.bazel*"
-      - .github/workflows/swift-codegen.yml
-      - .github/actions/fetch-codeql/action.yml
-    branches:
-      - main
-
-jobs:
-  codegen:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - uses: ./.github/actions/fetch-codeql
-      - uses: bazelbuild/setup-bazelisk@v2
-      - uses: actions/setup-python@v3
-      - uses: pre-commit/action@v3.0.0
-        name: Check that python code is properly formatted
-        with:
-          extra_args: autopep8 --all-files
-      - name: Run unit tests
-        run: |
-          bazel test //swift/codegen/test --test_output=errors
-      - uses: pre-commit/action@v3.0.0
-        name: Check that QL generated code was checked in
-        with:
-          extra_args: swift-codegen --all-files
-      - name: Generate C++ files
-        run: |
-          bazel run //swift/codegen:codegen -- --generate=trap,cpp --cpp-output=$PWD/swift-generated-cpp-files
-      - uses: actions/upload-artifact@v3
-        with:
-          name: swift-generated-cpp-files
-          path: swift-generated-cpp-files/**

.github/workflows/swift-integration-tests.yml

@@ -1,45 +0,0 @@
-name: "Swift: Run Integration Tests"
-
-on:
-  pull_request:
-    paths:
-      - "swift/**"
-      - "misc/bazel/**"
-      - "*.bazel*"
-      - .github/workflows/swift-integration-tests.yml
-      - .github/actions/fetch-codeql/action.yml
-      - codeql-workspace.yml
-    branches:
-      - main
-defaults:
-  run:
-    working-directory: swift
-
-jobs:
-  integration-tests:
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os:
-          - ubuntu-20.04
-#          - macos-latest  TODO
-    steps:
-      - uses: actions/checkout@v3
-      - uses: ./.github/actions/fetch-codeql
-      - uses: bazelbuild/setup-bazelisk@v2
-      - uses: actions/setup-python@v3
-      - name: Build Swift extractor
-        run: |
-          bazel run //swift:create-extractor-pack
-      - name: Get Swift version
-        id: get_swift_version
-        run: |
-          VERSION=$(bazel run //swift/extractor -- --version | sed -ne 's/.*version \(\S*\).*/\1/p')
-          echo "::set-output name=version::$VERSION"
-      - uses: swift-actions/setup-swift@v1
-        with:
-          swift-version: "${{steps.get_swift_version.outputs.version}}"
-      - name: Run integration tests
-        run: |
-          python integration-tests/runner.py

.github/workflows/swift-qltest.yml

@@ -1,43 +0,0 @@
-name: "Swift: Run QL Tests"
-
-on:
-  pull_request:
-    paths:
-      - "swift/**"
-      - "misc/bazel/**"
-      - "*.bazel*"
-      - .github/workflows/swift-qltest.yml
-      - .github/actions/fetch-codeql/action.yml
-      - codeql-workspace.yml
-    branches:
-      - main
-defaults:
-  run:
-    working-directory: swift
-
-jobs:
-  qlformat:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-      - uses: ./.github/actions/fetch-codeql
-      - name: Check QL formatting
-        run: find ql "(" -name "*.ql" -or -name "*.qll" ")" -print0 | xargs -0 codeql query format --check-only
-  qltest:
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os : [ubuntu-20.04, macos-latest]
-    steps:
-      - uses: actions/checkout@v3
-      - uses: ./.github/actions/fetch-codeql
-      - uses: bazelbuild/setup-bazelisk@v2
-      - name: Build Swift extractor
-        run: |
-          bazel run //swift:create-extractor-pack
-      - name: Run QL tests
-        run: |
-          codeql test run --threads=0 --ram 5000 --search-path "${{ github.workspace }}/swift/extractor-pack" --check-databases --check-unused-labels --check-repeated-labels --check-redefined-labels --check-use-before-definition ql/test
-        env:
-          GITHUB_TOKEN: ${{ github.token }}

.github/workflows/swift.yml

@@ -0,0 +1,102 @@
+name: "Swift"
+
+on:
+  pull_request:
+    paths:
+      - "swift/**"
+      - "misc/bazel/**"
+      - "*.bazel*"
+      - .github/workflows/swift.yml
+      - .github/actions/**
+      - codeql-workspace.yml
+      - .pre-commit-config.yaml
+      - "!**/*.md"
+      - "!**/*.qhelp"
+    branches:
+      - main
+      - rc/*
+  push:
+    paths:
+      - "swift/**"
+      - "misc/bazel/**"
+      - "*.bazel*"
+      - .github/workflows/swift.yml
+      - .github/actions/**
+      - codeql-workspace.yml
+      - "!**/*.md"
+      - "!**/*.qhelp"
+    branches:
+      - main
+      - rc/*
+
+jobs:
+  # not using a matrix as you cannot depend on a specific job in a matrix, and we want to start linux checks
+  # without waiting for the macOS build
+  build-and-test-macos:
+    runs-on: macos-12-xl
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./swift/actions/build-and-test
+  build-and-test-linux:
+    runs-on: ubuntu-latest-xl
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./swift/actions/build-and-test
+  qltests-linux:
+    needs: build-and-test-linux
+    runs-on: ubuntu-latest-xl
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./swift/actions/run-ql-tests
+  qltests-macos:
+    if : ${{ github.event_name == 'pull_request' }}
+    needs: build-and-test-macos
+    runs-on: macos-12-xl
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./swift/actions/run-ql-tests
+  integration-tests-linux:
+    needs: build-and-test-linux
+    runs-on: ubuntu-latest-xl
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./swift/actions/run-integration-tests
+  integration-tests-macos:
+    if : ${{ github.event_name == 'pull_request' }}
+    needs: build-and-test-macos
+    runs-on: macos-12-xl
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./swift/actions/run-integration-tests
+  codegen:
+    if : ${{ github.event_name == 'pull_request' }}
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: bazelbuild/setup-bazelisk@v2
+      - uses: actions/setup-python@v4
+        with:
+          python-version-file: 'swift/.python-version'
+      - uses: pre-commit/action@v3.0.0
+        name: Check that python code is properly formatted
+        with:
+          extra_args: autopep8 --all-files
+      - uses: ./.github/actions/fetch-codeql
+      - uses: pre-commit/action@v3.0.0
+        name: Check that QL generated code was checked in
+        with:
+          extra_args: swift-codegen --all-files
+      - name: Generate C++ files
+        run: |
+          bazel run //swift/codegen:codegen -- --generate=trap,cpp --cpp-output=$PWD/generated-cpp-files
+      - uses: actions/upload-artifact@v3
+        with:
+          name: swift-generated-cpp-files
+          path: generated-cpp-files/**
+  database-upgrade-scripts:
+    if : ${{ github.event_name == 'pull_request' }}
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./.github/actions/fetch-codeql
+      - uses: ./swift/actions/database-upgrade-scripts

.gitignore

@@ -27,8 +27,6 @@
 # It's useful (though not required) to be able to unpack codeql in the ql checkout itself
 /codeql/
 
-csharp/extractor/Semmle.Extraction.CSharp.Driver/Properties/launchSettings.json
-
 # Avoid committing cached package components
 .codeql
 

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ repos:
     rev: v1.6.0
     hooks:
       - id: autopep8
-        files: ^swift/codegen/.*\.py
+        files: ^swift/.*\.py
 
   - repo: local
     hooks:
@@ -31,7 +31,7 @@ repos:
 
       - id: sync-files
         name: Fix files required to be identical
-        files: \.(qll?|qhelp|swift)$
+        files: \.(qll?|qhelp|swift)$|^config/identical-files\.json$
         language: system
         entry: python3 config/sync-files.py --latest
         pass_filenames: false
@@ -44,7 +44,7 @@ repos:
 
       - id: swift-codegen
         name: Run Swift checked in code generation
-        files: ^swift/(codegen/|.*/generated/|ql/lib/(swift\.dbscheme$|codeql/swift/elements))
+        files: ^swift/(schema.py$|codegen/|.*/generated/|ql/lib/(swift\.dbscheme$|codeql/swift/elements)|ql/\.generated.list)
         language: system
         entry: bazel run //swift/codegen -- --quiet
         pass_filenames: false

.vscode/settings.json

@@ -1,3 +1,5 @@
 {
-    "omnisharp.autoStart": false
+  "omnisharp.autoStart": false,
+  "cmake.sourceDirectory": "${workspaceFolder}/swift",
+  "cmake.buildDirectory": "${workspaceFolder}/bazel-cmake-build"
 }

CODEOWNERS

@@ -5,24 +5,17 @@
 /javascript/ @github/codeql-javascript
 /python/ @github/codeql-python
 /ruby/ @github/codeql-ruby
-/swift/ @github/codeql-c
+/swift/ @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
 
-# Notify members of codeql-go about PRs to the shared data-flow library files
-/java/ql/src/semmle/code/java/dataflow/internal/DataFlowImpl.qll @github/codeql-java @github/codeql-go
-/java/ql/src/semmle/code/java/dataflow/internal/DataFlowImpl2.qll @github/codeql-java @github/codeql-go
-/java/ql/src/semmle/code/java/dataflow/internal/DataFlowImplCommon.qll @github/codeql-java @github/codeql-go
-/java/ql/src/semmle/code/java/dataflow/internal/tainttracking1/TaintTrackingImpl.qll @github/codeql-java @github/codeql-go
-/java/ql/src/semmle/code/java/dataflow/internal/tainttracking2/TaintTrackingImpl.qll @github/codeql-java @github/codeql-go
-
 # CodeQL tools and associated docs
-/docs/codeql-cli/ @github/codeql-cli-reviewers
-/docs/codeql-for-visual-studio-code/ @github/codeql-vscode-reviewers
-/docs/ql-language-reference/ @github/codeql-frontend-reviewers
+/docs/codeql/codeql-cli/ @github/codeql-cli-reviewers
+/docs/codeql/codeql-for-visual-studio-code/ @github/codeql-vscode-reviewers
+/docs/codeql/ql-language-reference/ @github/codeql-frontend-reviewers
 /docs/query-*-style-guide.md @github/codeql-analysis-reviewers
 
 # QL for QL reviewers
@@ -40,8 +33,9 @@ WORKSPACE.bazel @github/codeql-ci-reviewers
 
 # Workflows
 /.github/workflows/ @github/codeql-ci-reviewers
+/.github/workflows/atm-* @github/codeql-ml-powered-queries-reviewers
 /.github/workflows/go-* @github/codeql-go
 /.github/workflows/js-ml-tests.yml @github/codeql-ml-powered-queries-reviewers
 /.github/workflows/ql-for-ql-* @github/codeql-ql-for-ql-reviewers
 /.github/workflows/ruby-* @github/codeql-ruby
-/.github/workflows/swift-* @github/codeql-c
+/.github/workflows/swift.yml @github/codeql-swift

README.md

@@ -4,8 +4,7 @@ This open source repository contains the standard CodeQL libraries and queries t
 
 ## How do I learn CodeQL and run queries?
 
-There is [extensive documentation](https://codeql.github.com/docs/) on getting started with writing CodeQL.
-You can use the [CodeQL for Visual Studio Code](https://codeql.github.com/docs/codeql-for-visual-studio-code/) extension or the [interactive query console](https://lgtm.com/help/lgtm/using-query-console) on LGTM.com (Semmle Legacy product) to try out your queries on any open source project that's currently being analyzed.
+There is [extensive documentation](https://codeql.github.com/docs/) on getting started with writing CodeQL using the [CodeQL extension for Visual Studio Code](https://codeql.github.com/docs/codeql-for-visual-studio-code/) and the [CodeQL CLI](https://codeql.github.com/docs/codeql-cli/).
 
 ## Contributing
 

change-notes/1.20/analysis-javascript.md

@@ -52,7 +52,7 @@
 | Unneeded defensive code | More true positive and fewer false positive results | This query now recognizes additional defensive code patterns. |
 | Unsafe dynamic method access              | Fewer false positive results | This query no longer flags concatenated strings as unsafe method names. |
 | Unused parameter                           | Fewer false positive results | This query no longer flags parameters with leading underscore. |
-| Unused variable, import, function or class | Fewer false positive results | This query now flags fewer variables that are implictly used by JSX elements. It no longer flags variables with a leading underscore and variables in dead code. |
+| Unused variable, import, function or class | Fewer false positive results | This query now flags fewer variables that are implicitly used by JSX elements. It no longer flags variables with a leading underscore and variables in dead code. |
 | Unvalidated dynamic method call           | More true positive results | This query now flags concatenated strings as unvalidated method names in more cases. |
 | Useless assignment to property. | Fewer false positive results | This query now treats assignments with complex right-hand sides correctly. |
 | Useless conditional | Fewer results | Additional defensive coding patterns are now ignored. |

change-notes/1.23/analysis-cpp.md

@@ -19,7 +19,7 @@ The following changes in version 1.23 affect C/C++ analysis in all applications.
 | Hard-coded Japanese era start date in call (`cpp/japanese-era/constructor-or-method-with-exact-era-date`) | Deprecated | This query has been deprecated.  Use the new combined query Hard-coded Japanese era start date (`cpp/japanese-era/exact-era-date`) instead. |
 | Hard-coded Japanese era start date in struct (`cpp/japanese-era/struct-with-exact-era-date`) | Deprecated | This query has been deprecated.  Use the new combined query Hard-coded Japanese era start date (`cpp/japanese-era/exact-era-date`) instead. |
 | Hard-coded Japanese era start date (`cpp/japanese-era/exact-era-date`) | More correct results | This query now checks for the beginning date of the Reiwa era (1st May 2019). |
-| Non-constant format string (`cpp/non-constant-format`) | Fewer false positive results | Fixed false positive results triggrered by mismatching declarations of a formatting function. |
+| Non-constant format string (`cpp/non-constant-format`) | Fewer false positive results | Fixed false positive results triggered by mismatching declarations of a formatting function. |
 | Sign check of bitwise operation (`cpp/bitwise-sign-check`) | Fewer false positive results | Results involving `>=` or `<=` are no longer reported. |
 | Too few arguments to formatting function (`cpp/wrong-number-format-arguments`) | Fewer false positive results | Fixed false positive results triggered by mismatching declarations of a formatting function. |
 | Too many arguments to formatting function (`cpp/too-many-format-arguments`) | Fewer false positive results | Fixed false positive results triggered by mismatching declarations of a formatting function. |

change-notes/1.24/analysis-javascript.md

@@ -91,7 +91,7 @@
 
 ## Changes to libraries
 
-* The predicates `RegExpTerm.getSuccessor` and `RegExpTerm.getPredecessor` have been changed to reflect textual, not operational, matching order. This only makes a difference in lookbehind assertions, which are operationally matched backwards. Previously, `getSuccessor` would mimick this, so in an assertion `(?<=ab)` the term `b` would be considered the predecessor, not the successor, of `a`. Textually, however, `a` is still matched before `b`, and this is the order we now follow.
+* The predicates `RegExpTerm.getSuccessor` and `RegExpTerm.getPredecessor` have been changed to reflect textual, not operational, matching order. This only makes a difference in lookbehind assertions, which are operationally matched backwards. Previously, `getSuccessor` would mimic this, so in an assertion `(?<=ab)` the term `b` would be considered the predecessor, not the successor, of `a`. Textually, however, `a` is still matched before `b`, and this is the order we now follow.
 * An extensible model of the `EventEmitter` pattern has been implemented.
 * Taint-tracking configurations now interact differently with the `data` flow label, which may affect queries
   that combine taint-tracking and flow labels.

codeql-workspace.yml

@@ -17,6 +17,7 @@ provide:
   # - "javascript/ql/experimental/adaptivethreatmodeling/model/qlpack.yml"
   - "javascript/ql/experimental/adaptivethreatmodeling/modelbuilding/qlpack.yml"
   - "javascript/ql/experimental/adaptivethreatmodeling/src/qlpack.yml"
+  - "javascript/ql/experimental/adaptivethreatmodeling/test/qlpack.yml"
   - "csharp/ql/campaigns/Solorigate/lib/qlpack.yml"
   - "csharp/ql/campaigns/Solorigate/src/qlpack.yml"
   - "csharp/ql/campaigns/Solorigate/test/qlpack.yml"
@@ -24,7 +25,8 @@ provide:
   - "misc/suite-helpers/qlpack.yml"
   - "ruby/extractor-pack/codeql-extractor.yml"
   - "swift/extractor-pack/codeql-extractor.yml"
-  - "ql/extractor-pack/codeql-extractor.ym"
+  - "swift/integration-tests/qlpack.yml"
+  - "ql/extractor-pack/codeql-extractor.yml"
 
 versionPolicies:
   default:

config/atm/ml-powered-queries-repo/add-note.js

@@ -0,0 +1,21 @@
+const mongoose = require('mongoose');
+
+Logger = require('./logger').Logger;
+Note = require('./models/note').Note;
+
+(async () => {
+  if (process.argv.length != 5) {
+    Logger.log("Creates a private note.  Usage: node add-note.js <token> <title> <body>")
+    return;
+  }
+
+  // Open the default mongoose connection
+  await mongoose.connect('mongodb://localhost:27017/notes', { useFindAndModify: false });
+
+  const [userToken, title, body] = process.argv.slice(2);
+  await Note.create({ title, body, userToken });
+
+  Logger.log(`Created private note with title ${title} and body ${body} belonging to user with token ${userToken}.`);
+
+  await mongoose.connection.close();
+})();

config/atm/ml-powered-queries-repo/app.js

@@ -0,0 +1,68 @@
+const bodyParser = require('body-parser');
+const express = require('express');
+const mongoose = require('mongoose');
+
+const notesApi = require('./notes-api');
+const usersApi = require('./users-api');
+
+const addSampleData = module.exports.addSampleData = async () => {
+  const [userA, userB] = await User.create([
+    {
+      name: "A",
+      token: "tokenA"
+    },
+    {
+      name: "B",
+      token: "tokenB"
+    }
+  ]);
+
+  await Note.create([
+    {
+      title: "Public note belonging to A",
+      body: "This is a public note belonging to A",
+      isPublic: true,
+      ownerToken: userA.token
+    },
+    {
+      title: "Public note belonging to B",
+      body: "This is a public note belonging to B",
+      isPublic: true,
+      ownerToken: userB.token
+    },
+    {
+      title: "Private note belonging to A",
+      body: "This is a private note belonging to A",
+      ownerToken: userA.token
+    },
+    {
+      title: "Private note belonging to B",
+      body: "This is a private note belonging to B",
+      ownerToken: userB.token
+    }
+  ]);
+}
+
+module.exports.startApp = async () => {
+  // Open the default mongoose connection
+  await mongoose.connect('mongodb://mongo:27017/notes', { useFindAndModify: false });
+  // Drop contents of DB
+  mongoose.connection.dropDatabase();
+  // Add some sample data
+  await addSampleData();
+
+  const app = express();
+
+  app.use(bodyParser.json());
+  app.use(bodyParser.urlencoded());
+
+  app.get('/', async (_req, res) => {
+    res.send('Hello World');
+  });
+
+  app.use('/api/notes', notesApi.router);
+  app.use('/api/users', usersApi.router);
+
+  app.listen(3000);
+  Logger.log('Express started on port 3000');
+};

config/atm/ml-powered-queries-repo/index.js

@@ -0,0 +1,7 @@
+const startApp = require('./app').startApp;
+
+Logger = require('./logger').Logger;
+Note = require('./models/note').Note;
+User = require('./models/user').User;
+
+startApp();

config/atm/ml-powered-queries-repo/logger.js

@@ -0,0 +1,5 @@
+module.exports.Logger = class {
+  log(message, ...objs) {
+    console.log(message, objs);
+  }
+};

config/atm/ml-powered-queries-repo/models/note.js

@@ -0,0 +1,8 @@
+const mongoose = require('mongoose');
+
+module.exports.Note = mongoose.model('Note', new mongoose.Schema({
+  title: String,
+  body: String,
+  ownerToken: String,
+  isPublic: Boolean
+}));

config/atm/ml-powered-queries-repo/models/user.js

@@ -0,0 +1,6 @@
+const mongoose = require('mongoose');
+
+module.exports.User = mongoose.model('User', new mongoose.Schema({
+  name: String,
+  token: String
+}));

config/atm/ml-powered-queries-repo/notes-api.js

@@ -0,0 +1,44 @@
+const express = require('express')
+
+const router = module.exports.router = express.Router();
+
+function serializeNote(note) {
+  return {
+    title: note.title,
+    body: note.body
+  };
+}
+
+router.post('/find', async (req, res) => {
+  const notes = await Note.find({
+    ownerToken: req.body.token
+  }).exec();
+  res.json({
+    notes: notes.map(serializeNote)
+  });
+});
+
+router.get('/findPublic', async (_req, res) => {
+  const notes = await Note.find({
+    isPublic: true
+  }).exec();
+  res.json({
+    notes: notes.map(serializeNote)
+  });
+});
+
+router.post('/findVisible', async (req, res) => {
+  const notes = await Note.find({
+    $or: [
+      {
+        isPublic: true
+      },
+      {
+        ownerToken: req.body.token
+      }
+    ]
+  }).exec();
+  res.json({
+    notes: notes.map(serializeNote)
+  });
+});

config/atm/ml-powered-queries-repo/read-notes.js

@@ -0,0 +1,37 @@
+const mongoose = require('mongoose');
+
+Logger = require('./logger').Logger;
+Note = require('./models/note').Note;
+User = require('./models/user').User;
+
+(async () => {
+  if (process.argv.length != 3) {
+    Logger.log("Outputs all notes visible to a user.  Usage: node read-notes.js <token>")
+    return;
+  }
+
+  // Open the default mongoose connection
+  await mongoose.connect('mongodb://localhost:27017/notes', { useFindAndModify: false });
+
+  const ownerToken = process.argv[2];
+
+  const user = await User.findOne({
+    token: ownerToken
+  }).exec();
+
+  const notes = await Note.find({
+    $or: [
+      { isPublic: true },
+      { ownerToken }
+    ]
+  }).exec();
+
+  notes.map(note => {
+    Logger.log("Title:" + note.title);
+    Logger.log("By:" + user.name);
+    Logger.log("Body:" + note.body);
+    Logger.log();
+  });
+
+  await mongoose.connection.close();
+})();

config/atm/ml-powered-queries-repo/users-api.js

@@ -0,0 +1,25 @@
+const express = require('express')
+
+Logger = require('./logger').Logger;
+const router = module.exports.router = express.Router();
+
+router.post('/updateName', async (req, res) => {
+  Logger.log("/updateName called with new name", req.body.name);
+  await User.findOneAndUpdate({
+    token: req.body.token
+  }, {
+    name: req.body.name
+  }).exec();
+  res.json({
+    name: req.body.name
+  });
+});
+
+router.post('/getName', async (req, res) => {
+  const user = await User.findOne({
+    token: req.body.token
+  }).exec();
+  res.json({
+    name: user.name
+  });
+});

config/identical-files.json

@@ -1,5 +1,5 @@
 {
-  "DataFlow Java/C++/C#/Python": [
+  "DataFlow Java/C++/C#/Go/Python/Ruby/Swift": [
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl2.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl3.qll",
@@ -27,27 +27,31 @@
     "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/DataFlowImpl2.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl2.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl3.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl4.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImpl.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImpl2.qll",
-    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplForLibraries.qll",
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplForRegExp.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"
   ],
-  "DataFlow Java/C++/C#/Python Common": [
+  "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#/Python": [
+  "TaintTracking::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",
@@ -61,6 +65,8 @@
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/tainttracking3/TaintTrackingImpl.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/tainttracking4/TaintTrackingImpl.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/tainttracking5/TaintTrackingImpl.qll",
+    "go/ql/lib/semmle/go/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
+    "go/ql/lib/semmle/go/dataflow/internal/tainttracking2/TaintTrackingImpl.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/tainttracking2/TaintTrackingImpl.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/tainttracking3/TaintTrackingImpl.qll",
@@ -69,10 +75,9 @@
     "python/ql/lib/semmle/python/dataflow/new/internal/tainttracking3/TaintTrackingImpl.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/tainttracking4/TaintTrackingImpl.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
-    "ruby/ql/lib/codeql/ruby/dataflow/internal/tainttrackingforlibraries/TaintTrackingImpl.qll",
     "swift/ql/lib/codeql/swift/dataflow/internal/tainttracking1/TaintTrackingImpl.qll"
   ],
-  "DataFlow Java/C++/C#/Python Consistency checks": [
+  "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",
@@ -82,9 +87,10 @@
     "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplConsistency.qll",
     "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImplConsistency.qll"
   ],
-  "DataFlow Java/C#/Ruby/Python/Swift Flow Summaries": [
+  "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",
+    "go/ql/lib/semmle/go/dataflow/internal/FlowSummaryImpl.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/FlowSummaryImpl.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/FlowSummaryImpl.qll",
     "swift/ql/lib/codeql/swift/dataflow/internal/FlowSummaryImpl.qll"
@@ -94,8 +100,8 @@
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/rangeanalysis/SsaReadPositionCommon.qll"
   ],
   "Model as Data Generation Java/C# - CaptureModels": [
-    "java/ql/src/utils/model-generator/internal/CaptureModels.qll",
-    "csharp/ql/src/utils/model-generator/internal/CaptureModels.qll"
+    "java/ql/src/utils/modelgenerator/internal/CaptureModels.qll",
+    "csharp/ql/src/utils/modelgenerator/internal/CaptureModels.qll"
   ],
   "Sign Java/C#": [
     "java/ql/lib/semmle/code/java/dataflow/internal/rangeanalysis/Sign.qll",
@@ -486,40 +492,6 @@
     "python/ql/lib/semmle/python/security/internal/SensitiveDataHeuristics.qll",
     "ruby/ql/lib/codeql/ruby/security/internal/SensitiveDataHeuristics.qll"
   ],
-  "ReDoS Util Python/JS/Ruby/Java": [
-    "javascript/ql/lib/semmle/javascript/security/regexp/NfaUtils.qll",
-    "python/ql/lib/semmle/python/security/regexp/NfaUtils.qll",
-    "ruby/ql/lib/codeql/ruby/security/regexp/NfaUtils.qll",
-    "java/ql/lib/semmle/code/java/security/regexp/NfaUtils.qll"
-  ],
-  "ReDoS Exponential Python/JS/Ruby/Java": [
-    "javascript/ql/lib/semmle/javascript/security/regexp/ExponentialBackTracking.qll",
-    "python/ql/lib/semmle/python/security/regexp/ExponentialBackTracking.qll",
-    "ruby/ql/lib/codeql/ruby/security/regexp/ExponentialBackTracking.qll",
-    "java/ql/lib/semmle/code/java/security/regexp/ExponentialBackTracking.qll"
-  ],
-  "ReDoS Polynomial Python/JS/Ruby/Java": [
-    "javascript/ql/lib/semmle/javascript/security/regexp/SuperlinearBackTracking.qll",
-    "python/ql/lib/semmle/python/security/regexp/SuperlinearBackTracking.qll",
-    "ruby/ql/lib/codeql/ruby/security/regexp/SuperlinearBackTracking.qll",
-    "java/ql/lib/semmle/code/java/security/regexp/SuperlinearBackTracking.qll"
-  ],
-  "RegexpMatching Python/JS/Ruby": [
-    "javascript/ql/lib/semmle/javascript/security/regexp/RegexpMatching.qll",
-    "python/ql/lib/semmle/python/security/regexp/RegexpMatching.qll",
-    "ruby/ql/lib/codeql/ruby/security/regexp/RegexpMatching.qll"
-  ],
-  "BadTagFilterQuery Python/JS/Ruby": [
-    "javascript/ql/lib/semmle/javascript/security/BadTagFilterQuery.qll",
-    "python/ql/lib/semmle/python/security/BadTagFilterQuery.qll",
-    "ruby/ql/lib/codeql/ruby/security/BadTagFilterQuery.qll"
-  ],
-  "OverlyLargeRange Python/JS/Ruby/Java": [
-    "javascript/ql/lib/semmle/javascript/security/OverlyLargeRangeQuery.qll",
-    "python/ql/lib/semmle/python/security/OverlyLargeRangeQuery.qll",
-    "ruby/ql/lib/codeql/ruby/security/OverlyLargeRangeQuery.qll",
-    "java/ql/lib/semmle/code/java/security/OverlyLargeRangeQuery.qll"
-  ],
   "CFG": [
     "csharp/ql/lib/semmle/code/csharp/controlflow/internal/ControlFlowGraphImplShared.qll",
     "ruby/ql/lib/codeql/ruby/controlflow/internal/ControlFlowGraphImplShared.qll",
@@ -539,6 +511,7 @@
   ],
   "AccessPathSyntax": [
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/AccessPathSyntax.qll",
+    "go/ql/lib/semmle/go/dataflow/internal/AccessPathSyntax.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/AccessPathSyntax.qll",
     "javascript/ql/lib/semmle/javascript/frameworks/data/internal/AccessPathSyntax.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/AccessPathSyntax.qll",
@@ -600,8 +573,12 @@
     "swift/ql/test/extractor-tests/patterns/patterns.swift",
     "swift/ql/test/library-tests/ast/patterns.swift"
   ],
+  "Swift control flow test file": [
+    "swift/ql/test/library-tests/controlflow/graph/cfg.swift",
+    "swift/ql/test/library-tests/ast/cfg.swift"
+  ],
   "IncompleteMultiCharacterSanitization JS/Ruby": [
     "javascript/ql/lib/semmle/javascript/security/IncompleteMultiCharacterSanitizationQuery.qll",
     "ruby/ql/lib/codeql/ruby/security/IncompleteMultiCharacterSanitizationQuery.qll"
   ]
-}
+}

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

@@ -257,11 +257,11 @@ namespace Semmle.Autobuild.Cpp.Tests
             Actions.GetCurrentDirectory = cwd;
             Actions.IsWindows = isWindows;
 
-            var options = new AutobuildOptions(Actions, Language.Cpp);
+            var options = new CppAutobuildOptions(Actions);
             return new CppAutobuilder(Actions, options);
         }
 
-        void TestAutobuilderScript(Autobuilder autobuilder, int expectedOutput, int commandsRun)
+        void TestAutobuilderScript(CppAutobuilder autobuilder, int expectedOutput, int commandsRun)
         {
             Assert.Equal(expectedOutput, autobuilder.GetBuildScript().Run(Actions, StartCallback, EndCallback));
 
@@ -299,7 +299,7 @@ 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 && C:\odasa\tools\odasa index --auto msbuild C:\Project\test.sln /t:rebuild /p:Platform=""x86"" /p:Configuration=""Release"" /p:MvcBuildViews=true"] = 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.Tests/Semmle.Autobuild.Cpp.Tests.csproj

@@ -11,11 +11,12 @@
   <ItemGroup>
     <PackageReference Include="System.IO.FileSystem" Version="4.3.0" />
     <PackageReference Include="System.IO.FileSystem.Primitives" Version="4.3.0" />
-    <PackageReference Include="xunit" Version="2.4.1" />
-    <PackageReference Include="xunit.runner.visualstudio" Version="2.4.1">
+    <PackageReference Include="xunit" Version="2.4.2" />
+    <PackageReference Include="xunit.runner.visualstudio" Version="2.4.5">
       <PrivateAssets>all</PrivateAssets>
       <IncludeAssets>runtime; build; native; contentfiles; analyzers</IncludeAssets>
     </PackageReference>
+    <PackageReference Include="Microsoft.NET.Test.Sdk" Version="17.4.0" />
   </ItemGroup>
 
   <ItemGroup>

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

@@ -2,9 +2,26 @@
 
 namespace Semmle.Autobuild.Cpp
 {
-    public class CppAutobuilder : Autobuilder
+    /// <summary>
+    /// Encapsulates C++ build options.
+    /// </summary>
+    public class CppAutobuildOptions : AutobuildOptionsShared
     {
-        public CppAutobuilder(IBuildActions actions, AutobuildOptions options) : base(actions, options) { }
+        public override Language Language => Language.Cpp;
+
+
+        /// <summary>
+        /// Reads options from environment variables.
+        /// Throws ArgumentOutOfRangeException for invalid arguments.
+        /// </summary>
+        public CppAutobuildOptions(IBuildActions actions) : base(actions)
+        {
+        }
+    }
+
+    public class CppAutobuilder : Autobuilder<CppAutobuildOptions>
+    {
+        public CppAutobuilder(IBuildActions actions, CppAutobuildOptions options) : base(actions, options) { }
 
         public override BuildScript GetBuildScript()
         {

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

@@ -11,14 +11,14 @@ namespace Semmle.Autobuild.Cpp
             try
             {
                 var actions = SystemBuildActions.Instance;
-                var options = new AutobuildOptions(actions, Language.Cpp);
+                var options = new CppAutobuildOptions(actions);
                 try
                 {
                     Console.WriteLine("CodeQL C++ autobuilder");
                     var builder = new CppAutobuilder(actions, options);
                     return builder.AttemptBuild();
                 }
-                catch(InvalidEnvironmentException ex)
+                catch (InvalidEnvironmentException ex)
                 {
                     Console.WriteLine("The environment is invalid: {0}", ex.Message);
                 }

cpp/autobuilder/Semmle.Autobuild.Cpp/Semmle.Autobuild.Cpp.csproj

@@ -17,7 +17,7 @@
   </ItemGroup>
 
   <ItemGroup>
-    <PackageReference Include="Microsoft.Build" Version="16.11.0" />
+    <PackageReference Include="Microsoft.Build" Version="17.3.2" />
   </ItemGroup>
 
   <ItemGroup>

cpp/ql/examples/qlpack.yml

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

cpp/ql/lib/CHANGELOG.md

@@ -1,3 +1,21 @@
+## 0.4.4
+
+No user-facing changes.
+
+## 0.4.3
+
+### Minor Analysis Improvements
+
+* Fixed bugs in the `FormatLiteral` class that were causing `getMaxConvertedLength` and related predicates to return no results when the format literal was `%e`, `%f` or `%g` and an explicit precision was specified.
+
+## 0.4.2
+
+No user-facing changes.
+
+## 0.4.1
+
+No user-facing changes.
+
 ## 0.4.0
 
 ### Deprecated APIs

cpp/ql/lib/change-notes/2022-11-14-deprecate-ast-gvn.md

@@ -0,0 +1,6 @@
+---
+category: deprecated
+---
+
+
+* Deprecated `semmle.code.cpp.valuenumbering.GlobalValueNumberingImpl`. Use `semmle.code.cpp.valuenumbering.GlobalValueNumbering`, which exposes the same API.

cpp/ql/lib/change-notes/2022-11-16-must-flow.md

@@ -0,0 +1,4 @@
+---
+category: breaking
+---
+The predicates in the `MustFlow::Configuration` class used by the `MustFlow` library (`semmle.code.cpp.ir.dataflow.MustFlow`) have changed to be defined directly in terms of the C++ IR instead of IR dataflow nodes.

cpp/ql/lib/change-notes/2022-11-17-deleted-deps.md

@@ -0,0 +1,4 @@
+---
+category: minorAnalysis
+---
+* Deleted the deprecated `getName` and `getShortName` predicates from the `Folder` class.

cpp/ql/lib/change-notes/released/0.4.1.md

@@ -0,0 +1,3 @@
+## 0.4.1
+
+No user-facing changes.

cpp/ql/lib/change-notes/released/0.4.2.md

@@ -0,0 +1,3 @@
+## 0.4.2
+
+No user-facing changes.

cpp/ql/lib/change-notes/released/0.4.3.md

@@ -0,0 +1,5 @@
+## 0.4.3
+
+### Minor Analysis Improvements
+
+* Fixed bugs in the `FormatLiteral` class that were causing `getMaxConvertedLength` and related predicates to return no results when the format literal was `%e`, `%f` or `%g` and an explicit precision was specified.

cpp/ql/lib/change-notes/released/0.4.4.md

@@ -0,0 +1,3 @@
+## 0.4.4
+
+No user-facing changes.

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

@@ -1,2 +1,2 @@
 ---
-lastReleaseVersion: 0.4.0
+lastReleaseVersion: 0.4.4

cpp/ql/lib/definitions.qll

@@ -12,8 +12,8 @@ import IDEContextual
  *
  * In some cases it is preferable to modify locations (the
  * `hasLocationInfo()` predicate) so that they are short, and
- * non-overlapping with other locations that might be highlighted in
- * the LGTM interface.
+ * non-overlapping with other locations that might be reported as
+ * code scanning alerts on GitHub.
  *
  * We need to give locations that may not be in the database, so
  * we use `hasLocationInfo()` rather than `getLocation()`.

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

@@ -20,7 +20,8 @@ module ProductFlow {
      * `source1` and `source2` must belong to the same callable.
      */
     predicate isSourcePair(
-      DataFlow::Node source1, string state1, DataFlow::Node source2, string state2
+      DataFlow::Node source1, DataFlow::FlowState state1, DataFlow::Node source2,
+      DataFlow::FlowState state2
     ) {
       state1 = "" and
       state2 = "" and
@@ -89,6 +90,61 @@ module ProductFlow {
      */
     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
@@ -103,54 +159,78 @@ module ProductFlow {
     class Conf1 extends DataFlow::Configuration {
       Conf1() { this = "Conf1" }
 
-      override predicate isSource(DataFlow::Node source, string state) {
+      override predicate isSource(DataFlow::Node source, DataFlow::FlowState state) {
         exists(Configuration conf | conf.isSourcePair(source, state, _, _))
       }
 
-      override predicate isSink(DataFlow::Node sink, string state) {
+      override predicate isSink(DataFlow::Node sink, DataFlow::FlowState state) {
         exists(Configuration conf | conf.isSinkPair(sink, state, _, _))
       }
 
-      override predicate isBarrier(DataFlow::Node node, string 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, string state) {
-        exists(Configuration conf, DataFlow::Node source1 |
-          conf.isSourcePair(source1, _, source, state) and
-          any(Conf1 c).hasFlow(source1, _)
+      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, string state) {
-        exists(Configuration conf, DataFlow::Node sink1 |
-          conf.isSinkPair(sink1, _, sink, state) and any(Conf1 c).hasFlow(_, sink1)
+      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, string state) {
+      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(), _, node2.getNode(), _) and
+    conf.isSourcePair(node1.getNode(), node1.getState(), node2.getNode(), node2.getState()) and
     node1 = source1 and
     node2 = source2
     or
@@ -213,7 +293,7 @@ module ProductFlow {
   ) {
     exists(DataFlow::PathNode mid1, DataFlow2::PathNode mid2 |
       reachableInterprocEntry(conf, source1, source2, mid1, mid2) and
-      conf.isSinkPair(sink1.getNode(), _, sink2.getNode(), _) 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/internal/DataFlowImplCommon.qll

@@ -915,6 +915,17 @@ private module Cached {
     TDataFlowCallNone() or
     TDataFlowCallSome(DataFlowCall call)
 
+  cached
+  newtype TParameterPositionOption =
+    TParameterPositionNone() or
+    TParameterPositionSome(ParameterPosition pos)
+
+  cached
+  newtype TReturnCtx =
+    TReturnCtxNone() or
+    TReturnCtxNoFlowThrough() or
+    TReturnCtxMaybeFlowThrough(ReturnKindExt kind)
+
   cached
   newtype TTypedContent = MkTypedContent(Content c, DataFlowType t) { store(_, c, _, _, t) }
 
@@ -1304,6 +1315,44 @@ class DataFlowCallOption extends TDataFlowCallOption {
   }
 }
 
+/** An optional `ParameterPosition`. */
+class ParameterPositionOption extends TParameterPositionOption {
+  string toString() {
+    this = TParameterPositionNone() and
+    result = "(none)"
+    or
+    exists(ParameterPosition pos |
+      this = TParameterPositionSome(pos) and
+      result = pos.toString()
+    )
+  }
+}
+
+/**
+ * A return context used to calculate flow summaries in reverse flow.
+ *
+ * The possible values are:
+ *
+ * - `TReturnCtxNone()`: no return flow.
+ * - `TReturnCtxNoFlowThrough()`: return flow, but flow through is not possible.
+ * - `TReturnCtxMaybeFlowThrough(ReturnKindExt kind)`: return flow, of kind `kind`, and
+ *    flow through may be possible.
+ */
+class ReturnCtx extends TReturnCtx {
+  string toString() {
+    this = TReturnCtxNone() and
+    result = "(none)"
+    or
+    this = TReturnCtxNoFlowThrough() and
+    result = "(no flow through)"
+    or
+    exists(ReturnKindExt kind |
+      this = TReturnCtxMaybeFlowThrough(kind) and
+      result = kind.toString()
+    )
+  }
+}
+
 /** A `Content` tagged with the type of a containing object. */
 class TypedContent extends MkTypedContent {
   private Content c;

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

@@ -136,6 +136,18 @@ module Consistency {
     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) {

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

@@ -137,7 +137,7 @@ private newtype TReturnKind =
     exists(IndirectReturnNode return, ReturnIndirectionInstruction returnInd |
       returnInd.hasIndex(argumentIndex) and
       return.getAddressOperand() = returnInd.getSourceAddressOperand() and
-      indirectionIndex = return.getIndirectionIndex() - 1 // We subtract one because the return loads the value.
+      indirectionIndex = return.getIndirectionIndex()
     )
   }
 
@@ -197,7 +197,7 @@ class ReturnIndirectionNode extends IndirectReturnNode, ReturnNode {
     exists(int argumentIndex, ReturnIndirectionInstruction returnInd |
       returnInd.hasIndex(argumentIndex) and
       this.getAddressOperand() = returnInd.getSourceAddressOperand() and
-      result = TIndirectReturnKind(argumentIndex, this.getIndirectionIndex() - 1) and
+      result = TIndirectReturnKind(argumentIndex, this.getIndirectionIndex()) and
       hasNonInitializeParameterDef(returnInd.getIRVariable())
     )
     or
@@ -241,7 +241,7 @@ private Instruction getANonConversionUse(Operand operand) {
 
 /**
  * Gets the operand that represents the first use of the value of `call` following
- * a sequnce of conversion-like instructions.
+ * a sequence of conversion-like instructions.
  */
 predicate operandForfullyConvertedCall(Operand operand, CallInstruction call) {
   exists(getANonConversionUse(operand)) and
@@ -254,7 +254,7 @@ predicate operandForfullyConvertedCall(Operand operand, CallInstruction call) {
 
 /**
  * Gets the instruction that represents the first use of the value of `call` following
- * a sequnce of conversion-like instructions.
+ * 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.
@@ -365,7 +365,7 @@ predicate jumpStep(Node n1, Node n2) {
 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() = 0 and
+    node2.getIndirectionIndex() = 1 and
     numberOfLoadsFromOperand(node2.getFieldAddress(), store.getDestinationAddressOperand(),
       numberOfLoads)
   |
@@ -465,20 +465,20 @@ predicate clearsContent(Node n, Content c) {
 predicate expectsContent(Node n, ContentSet c) { none() }
 
 /** Gets the type of `n` used for type pruning. */
-IRType getNodeType(Node n) {
+DataFlowType getNodeType(Node n) {
   suppressUnusedNode(n) and
-  result instanceof IRVoidType // stub implementation
+  result instanceof VoidType // stub implementation
 }
 
 /** Gets a string representation of a type returned by `getNodeType`. */
-string ppReprType(IRType t) { none() } // stub implementation
+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(IRType t1, IRType t2) {
+predicate compatibleTypes(DataFlowType t1, DataFlowType t2) {
   any() // stub implementation
 }
 
@@ -502,7 +502,7 @@ class DataFlowCallable = Cpp::Declaration;
 
 class DataFlowExpr = Expr;
 
-class DataFlowType = IRType;
+class DataFlowType = Type;
 
 /** A function call relevant for data flow. */
 class DataFlowCall extends CallInstruction {

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

@@ -38,13 +38,12 @@ private module Cached {
     TVariableNode(Variable var) or
     TPostFieldUpdateNode(FieldAddress operand, int indirectionIndex) {
       indirectionIndex =
-        [0 .. Ssa::countIndirectionsForCppType(operand.getObjectAddress().getResultLanguageType()) -
-            1]
+        [1 .. Ssa::countIndirectionsForCppType(operand.getObjectAddress().getResultLanguageType())]
     } or
     TSsaPhiNode(Ssa::PhiNode phi) or
     TIndirectArgumentOutNode(ArgumentOperand operand, int indirectionIndex) {
       Ssa::isModifiableByCall(operand) and
-      indirectionIndex = [0 .. Ssa::countIndirectionsForCppType(operand.getLanguageType()) - 1]
+      indirectionIndex = [1 .. Ssa::countIndirectionsForCppType(operand.getLanguageType())]
     } or
     TIndirectOperand(Operand op, int indirectionIndex) {
       Ssa::hasIndirectOperand(op, indirectionIndex)
@@ -113,7 +112,7 @@ class Node extends TIRDataFlowNode {
   Declaration getFunction() { none() } // overridden in subclasses
 
   /** Gets the type of this node. */
-  IRType getType() { none() } // overridden in subclasses
+  DataFlowType getType() { none() } // overridden in subclasses
 
   /** Gets the instruction corresponding to this node, if any. */
   Instruction asInstruction() { result = this.(InstructionNode).getInstruction() }
@@ -230,7 +229,13 @@ class Node extends TIRDataFlowNode {
   Expr asIndirectArgument() { result = this.asIndirectArgument(_) }
 
   /** Gets the positional parameter corresponding to this node, if any. */
-  Parameter asParameter() { result = asParameter(0) }
+  Parameter asParameter() { result = this.asParameter(0) }
+
+  /**
+   * Gets the uninitialized local variable corresponding to this node, if
+   * any.
+   */
+  LocalVariable asUninitialized() { result = this.(UninitializedNode).getLocalVariable() }
 
   /**
    * Gets the positional parameter corresponding to the node that represents
@@ -273,7 +278,7 @@ class Node extends TIRDataFlowNode {
   /**
    * Gets an upper bound on the type of this node.
    */
-  IRType getTypeBound() { result = this.getType() }
+  DataFlowType getTypeBound() { result = this.getType() }
 
   /** Gets the location of this element. */
   cached
@@ -322,7 +327,7 @@ class InstructionNode extends Node, TInstructionNode {
 
   override Declaration getFunction() { result = instr.getEnclosingFunction() }
 
-  override IRType getType() { result = instr.getResultIRType() }
+  override DataFlowType getType() { result = instr.getResultType() }
 
   final override Location getLocationImpl() { result = instr.getLocation() }
 
@@ -348,13 +353,32 @@ class OperandNode extends Node, TOperandNode {
 
   override Declaration getFunction() { result = op.getUse().getEnclosingFunction() }
 
-  override IRType getType() { result = op.getIRType() }
+  override DataFlowType getType() { result = op.getType() }
 
   final override Location getLocationImpl() { result = op.getLocation() }
 
   override string toStringImpl() { result = this.getOperand().toString() }
 }
 
+/**
+ * Returns `t`, but stripped of the `n` outermost pointers, references, etc.
+ *
+ * For example, `stripPointers(int*&, 2)` is `int` and `stripPointers(int*, 0)` is `int*`.
+ */
+private Type stripPointers(Type t, int n) {
+  result = t and n = 0
+  or
+  result = stripPointers(t.(PointerType).getBaseType(), n - 1)
+  or
+  result = stripPointers(t.(ArrayType).getBaseType(), n - 1)
+  or
+  result = stripPointers(t.(ReferenceType).getBaseType(), n - 1)
+  or
+  result = stripPointers(t.(PointerToMemberType).getBaseType(), n - 1)
+  or
+  result = stripPointers(t.(FunctionPointerIshType).getBaseType(), n - 1)
+}
+
 /**
  * INTERNAL: do not use.
  *
@@ -370,8 +394,6 @@ class PostFieldUpdateNode extends TPostFieldUpdateNode, PartialDefinitionNode {
 
   override Declaration getEnclosingCallable() { result = this.getFunction() }
 
-  override IRType getType() { result = fieldAddress.getIRType() }
-
   FieldAddress getFieldAddress() { result = fieldAddress }
 
   Field getUpdatedField() { result = fieldAddress.getField() }
@@ -379,10 +401,8 @@ class PostFieldUpdateNode extends TPostFieldUpdateNode, PartialDefinitionNode {
   int getIndirectionIndex() { result = indirectionIndex }
 
   override Node getPreUpdateNode() {
-    // + 1 because we're storing into an lvalue, and the original node should be the rvalue of
-    // the same address.
     hasOperandAndIndex(result, pragma[only_bind_into](fieldAddress).getObjectAddressOperand(),
-      indirectionIndex + 1)
+      indirectionIndex)
   }
 
   override Expr getDefinedExpr() {
@@ -411,7 +431,7 @@ class SsaPhiNode extends Node, TSsaPhiNode {
 
   override Declaration getFunction() { result = phi.getBasicBlock().getEnclosingFunction() }
 
-  override IRType getType() { result instanceof IRVoidType }
+  override DataFlowType getType() { result = this.getAnInput().getType() }
 
   final override Location getLocationImpl() { result = phi.getBasicBlock().getLocation() }
 
@@ -454,8 +474,6 @@ class SideEffectOperandNode extends Node, IndirectOperand {
 
   override Function getFunction() { result = call.getEnclosingFunction() }
 
-  override IRType getType() { result instanceof IRVoidType }
-
   Expr getArgument() { result = call.getArgument(argumentIndex).getUnconvertedResultExpression() }
 }
 
@@ -478,8 +496,6 @@ class IndirectParameterNode extends Node, IndirectInstruction {
 
   override Function getFunction() { result = this.getInstruction().getEnclosingFunction() }
 
-  override IRType getType() { result instanceof IRVoidType }
-
   override string toStringImpl() {
     result = this.getParameter().toString() + " indirection"
     or
@@ -504,8 +520,6 @@ class IndirectReturnNode extends IndirectOperand {
   Operand getAddressOperand() { result = operand }
 
   override Declaration getEnclosingCallable() { result = this.getFunction() }
-
-  override IRType getType() { result instanceof IRVoidType }
 }
 
 /**
@@ -536,9 +550,7 @@ class IndirectArgumentOutNode extends Node, TIndirectArgumentOutNode, PostUpdate
 
   override Function getFunction() { result = this.getCallInstruction().getEnclosingFunction() }
 
-  override IRType getType() { result instanceof IRVoidType }
-
-  override Node getPreUpdateNode() { hasOperandAndIndex(result, operand, indirectionIndex + 1) }
+  override Node getPreUpdateNode() { hasOperandAndIndex(result, operand, indirectionIndex) }
 
   override string toStringImpl() {
     // This string should be unique enough to be helpful but common enough to
@@ -594,6 +606,38 @@ class IndirectReturnOutNode extends Node {
   int getIndirectionIndex() { result = indirectionIndex }
 }
 
+private PointerType getGLValueType(Type t, int indirectionIndex) {
+  result.getBaseType() = stripPointers(t, indirectionIndex - 1)
+}
+
+bindingset[isGLValue]
+private DataFlowType getTypeImpl(Type t, int indirectionIndex, boolean isGLValue) {
+  if isGLValue = true
+  then
+    result = getGLValueType(t, indirectionIndex)
+    or
+    // Ideally, the above case would cover all glvalue cases. However, consider the case where
+    // the database consists only of:
+    // ```
+    // void test() {
+    //   int* x;
+    //   x = nullptr;
+    // }
+    // ```
+    // and we want to compute the type of `*x` in the assignment `x = nullptr`. Here, `x` is an lvalue
+    // of type int* (which morally is an int**). So when we call `getTypeImpl` it will be with the
+    // parameters:
+    // - t = int*
+    // - indirectionIndex = 1 (when we want to model the dataflow node corresponding to *x)
+    // - isGLValue = true
+    // In this case, `getTypeImpl(t, indirectionIndex, isGLValue)` should give back `int**`. In this
+    // case, however, `int**` does not exist in the database. So instead we return int* (which is
+    // wrong, but at least we have a type).
+    not exists(getGLValueType(t, indirectionIndex)) and
+    result = stripPointers(t, indirectionIndex - 1)
+  else result = stripPointers(t, indirectionIndex)
+}
+
 /**
  * INTERNAL: Do not use.
  *
@@ -615,7 +659,11 @@ class IndirectOperand extends Node, TIndirectOperand {
 
   override Declaration getEnclosingCallable() { result = this.getFunction() }
 
-  override IRType getType() { result = this.getOperand().getIRType() }
+  override DataFlowType getType() {
+    exists(boolean isGLValue | if operand.isGLValue() then isGLValue = true else isGLValue = false |
+      result = getTypeImpl(operand.getType().getUnspecifiedType(), indirectionIndex, isGLValue)
+    )
+  }
 
   final override Location getLocationImpl() { result = this.getOperand().getLocation() }
 
@@ -624,6 +672,25 @@ class IndirectOperand extends Node, TIndirectOperand {
   }
 }
 
+/**
+ * The value of an uninitialized local variable, viewed as a node in a data
+ * flow graph.
+ */
+class UninitializedNode extends Node {
+  LocalVariable v;
+
+  UninitializedNode() {
+    exists(Ssa::Def def |
+      def.getDefiningInstruction() instanceof UninitializedInstruction and
+      Ssa::nodeToDefOrUse(this, def) and
+      v = def.getSourceVariable().getBaseVariable().(Ssa::BaseIRVariable).getIRVariable().getAst()
+    )
+  }
+
+  /** Gets the uninitialized local variable corresponding to this node. */
+  LocalVariable getLocalVariable() { result = v }
+}
+
 /**
  * INTERNAL: Do not use.
  *
@@ -645,7 +712,11 @@ class IndirectInstruction extends Node, TIndirectInstruction {
 
   override Declaration getEnclosingCallable() { result = this.getFunction() }
 
-  override IRType getType() { result = this.getInstruction().getResultIRType() }
+  override DataFlowType getType() {
+    exists(boolean isGLValue | if instr.isGLValue() then isGLValue = true else isGLValue = false |
+      result = getTypeImpl(instr.getResultType().getUnspecifiedType(), indirectionIndex, isGLValue)
+    )
+  }
 
   final override Location getLocationImpl() { result = this.getInstruction().getLocation() }
 
@@ -675,7 +746,7 @@ predicate exprNodeShouldBeOperand(Node node, Expr e) {
 
 /**
  * Holds if `load` is a `LoadInstruction` that is the result of evaluating `e`
- * and `node` is an `IndirctOperandNode` that should map `node.asExpr()` to `e`.
+ * and `node` is an `IndirectOperandNode` that should map `node.asExpr()` to `e`.
  *
  * We map `e` to `node.asExpr()` when `node` semantically represents the
  * same value as `load`. A subsequent flow step will flow `node` to
@@ -859,6 +930,8 @@ abstract class PostUpdateNode extends Node {
    * Gets the node before the state update.
    */
   abstract Node getPreUpdateNode();
+
+  final override DataFlowType getType() { result = this.getPreUpdateNode().getType() }
 }
 
 /**
@@ -922,7 +995,7 @@ class VariableNode extends Node, TVariableNode {
     result = v
   }
 
-  override IRType getType() { result.getCanonicalLanguageType().hasUnspecifiedType(v.getType(), _) }
+  override DataFlowType getType() { result = v.getType() }
 
   final override Location getLocationImpl() { result = v.getLocation() }
 
@@ -1075,7 +1148,7 @@ predicate simpleLocalFlowStep(Node nodeFrom, Node nodeTo) {
       store.getDestinationAddressOperand() = address
     )
     or
-    Ssa::outNodeHasAddressAndIndex(nodeFrom, address, indirectionIndex - 1)
+    Ssa::outNodeHasAddressAndIndex(nodeFrom, address, indirectionIndex)
   )
 }
 

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

@@ -41,7 +41,7 @@ Node callOutput(CallInstruction call, FunctionOutput output) {
   // 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() + 1 = indirectionIndex and
+    result.(IndirectArgumentOutNode).getIndirectionIndex() = indirectionIndex and
     result.(IndirectArgumentOutNode).getCallInstruction() = call and
     output.isParameterDerefOrQualifierObject(index, indirectionIndex)
   )

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

@@ -100,7 +100,7 @@ private string getNodeProperty(DataFlow::Node node, string key) {
   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::Configration::explorationLimit()`.
+  // `DataFlow::Configuration::explorationLimit()`.
   key = "pflow" and
   result =
     strictconcat(DataFlow::PartialPathNode sourceNode, DataFlow::PartialPathNode destNode, int dist,

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

@@ -11,7 +11,9 @@ private import DataFlowUtil
  * corresponding `(Indirect)OperandNode`.
  */
 predicate ignoreOperand(Operand operand) {
-  operand = any(Instruction instr | ignoreInstruction(instr)).getAnOperand()
+  operand = any(Instruction instr | ignoreInstruction(instr)).getAnOperand() or
+  operand = any(Instruction instr | ignoreInstruction(instr)).getAUse() or
+  operand instanceof MemoryOperand
 }
 
 /**

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

@@ -36,7 +36,7 @@ private module SourceVariables {
 
     override string toString() { result = var.toString() }
 
-    override DataFlowType getType() { result = var.getIRType() }
+    override DataFlowType getType() { result = var.getType() }
   }
 
   class BaseCallVariable extends BaseSourceVariable, TBaseCallVariable {
@@ -48,7 +48,7 @@ private module SourceVariables {
 
     override string toString() { result = call.toString() }
 
-    override DataFlowType getType() { result = call.getResultIRType() }
+    override DataFlowType getType() { result = call.getResultType() }
   }
 
   private newtype TSourceVariable =

cpp/ql/lib/experimental/semmle/code/cpp/semantic/analysis/ModulusAnalysis.qll

@@ -4,6 +4,12 @@
  * variable), and `v` is an integer in the range `[0 .. m-1]`.
  */
 
+/*
+ * The main recursion has base cases in both `ssaModulus` (for guarded reads) and `semExprModulus`
+ * (for constant values). The most interesting recursive case is `phiModulusRankStep`, which
+ * handles phi inputs.
+ */
+
 private import ModulusAnalysisSpecific::Private
 private import experimental.semmle.code.cpp.semantic.Semantic
 private import ConstantAnalysis
@@ -162,6 +168,11 @@ private predicate phiModulusInit(SemSsaPhiNode phi, SemBound b, int val, int mod
  */
 pragma[nomagic]
 private predicate phiModulusRankStep(SemSsaPhiNode phi, SemBound b, int val, int mod, int rix) {
+  /*
+   * base case. If any phi input is equal to `b + val` modulo `mod`, that's a potential congruence
+   * class for the phi node.
+   */
+
   rix = 0 and
   phiModulusInit(phi, b, val, mod)
   or
@@ -169,6 +180,12 @@ private predicate phiModulusRankStep(SemSsaPhiNode phi, SemBound b, int val, int
     mod != 1 and
     val = remainder(v1, mod)
   |
+    /*
+     * Recursive case. If `inp` = `b + v2` mod `m2`, we combine that with the preceding potential
+     * congruence class `b + v1` mod `m1`. The result will be the congruence class of `v1` modulo
+     * the greatest common denominator of `m1`, `m2`, and `v1 - v2`.
+     */
+
     exists(int v2, int m2 |
       rankedPhiInput(pragma[only_bind_out](phi), inp, edge, rix) and
       phiModulusRankStep(phi, b, v1, m1, rix - 1) and
@@ -176,6 +193,12 @@ private predicate phiModulusRankStep(SemSsaPhiNode phi, SemBound b, int val, int
       mod = m1.gcd(m2).gcd(v1 - v2)
     )
     or
+    /*
+     * Recursive case. If `inp` = `phi` mod `m2`, we combine that with the preceding potential
+     * congruence class `b + v1` mod `m1`. The result will be a congruence class modulo the greatest
+     * common denominator of `m1` and `m2`.
+     */
+
     exists(int m2 |
       rankedPhiInput(phi, inp, edge, rix) and
       phiModulusRankStep(phi, b, v1, m1, rix - 1) and

cpp/ql/lib/experimental/semmle/code/cpp/semantic/analysis/SignAnalysisCommon.qll

@@ -71,7 +71,7 @@ abstract class CustomSignDef extends SignDef {
  * Concrete implementations extend one of the following subclasses:
  * - `ConstantSignExpr`, for expressions with a compile-time constant value.
  * - `FlowSignExpr`, for expressions whose sign can be computed from the signs of their operands.
- * - `CustomsignExpr`, for expressions shose sign can be computed by a language-specific
+ * - `CustomsignExpr`, for expressions whose sign can be computed by a language-specific
  *   implementation.
  *
  * If the same expression matches more than one of the above subclasses, the sign is computed as

cpp/ql/lib/experimental/semmle/code/cpp/semantic/analysis/SignAnalysisSpecific.qll

@@ -11,7 +11,7 @@ private import experimental.semmle.code.cpp.semantic.Semantic
 predicate ignoreTypeRestrictions(SemExpr e) { none() }
 
 /**
- * Workaround to track the sign of cetain expressions even if the type of the expression is not
+ * Workaround to track the sign of certain expressions even if the type of the expression is not
  * numeric.
  */
 predicate trackUnknownNonNumericExpr(SemExpr e) { none() }

cpp/ql/lib/qlpack.yml

@@ -1,9 +1,9 @@
 name: codeql/cpp-all
-version: 0.4.1-dev
+version: 0.4.5-dev
 groups: cpp
 dbscheme: semmlecode.cpp.dbscheme
 extractor: cpp
 library: true
 upgrades: upgrades
 dependencies:
-  codeql/ssa: 0.0.1
+  codeql/ssa: ${workspace}

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

@@ -189,18 +189,6 @@ class Folder extends Container, @folder {
    * Gets the URL of this folder.
    */
   deprecated override string getURL() { result = "file://" + this.getAbsolutePath() + ":0:0:0:0" }
-
-  /**
-   * DEPRECATED: use `getAbsolutePath` instead.
-   * Gets the name of this folder.
-   */
-  deprecated string getName() { folders(underlyingElement(this), result) }
-
-  /**
-   * DEPRECATED: use `getBaseName` instead.
-   * Gets the last part of the folder name.
-   */
-  deprecated string getShortName() { result = this.getBaseName() }
 }
 
 /**

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

@@ -1,5 +1,5 @@
 /**
- * Proivdes the `LinkTarget` class representing linker invocations during the build process.
+ * Provides the `LinkTarget` class representing linker invocations during the build process.
  */
 
 import semmle.code.cpp.Class

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

@@ -144,7 +144,7 @@ class Variable extends Declaration, @variable {
    * `Variable.getInitializer()` to get the variable's initializer,
    * or use `Variable.getAnAssignedValue()` to get an expression that
    * is the right-hand side of an assignment or an initialization of
-   * the varible.
+   * the variable.
    */
   Assignment getAnAssignment() { result.getLValue() = this.getAnAccess() }
 
@@ -173,7 +173,7 @@ class Variable extends Declaration, @variable {
   }
 
   /**
-   * Holds if this variable is declated as part of a structured binding
+   * Holds if this variable is declared as part of a structured binding
    * declaration. For example, `x` in `auto [x, y] = ...`.
    */
   predicate isStructuredBinding() { is_structured_binding(underlyingElement(this)) }

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

@@ -76,7 +76,7 @@ class TypeBoundsAnalysis extends BufferWriteEstimationReason, TTypeBoundsAnalysi
 
 /**
  * The estimation comes from non trivial bounds found via actual flow analysis,
- * but a widening aproximation might have been used for variables in loops.
+ * but a widening approximation might have been used for variables in loops.
  * For example
  * ```
  * for (int i = 0; i < 10; ++i) {
@@ -141,7 +141,7 @@ class AttributeFormattingFunction extends FormattingFunction {
  *  - `""` is a `vprintf` variant, `outputParamIndex` is `-1`.
  *  - `"f"` is a `vfprintf` variant, `outputParamIndex` indicates the output stream parameter.
  *  - `"s"` is a `vsprintf` variant, `outputParamIndex` indicates the output buffer parameter.
- *  - `"?"` if the type cannot be deteremined.  `outputParamIndex` is `-1`.
+ *  - `"?"` if the type cannot be determined.  `outputParamIndex` is `-1`.
  */
 predicate primitiveVariadicFormatter(
   TopLevelFunction f, string type, int formatParamIndex, int outputParamIndex
@@ -198,7 +198,7 @@ private predicate callsVariadicFormatter(
  *  - `""` is a `vprintf` variant, `outputParamIndex` is `-1`.
  *  - `"f"` is a `vfprintf` variant, `outputParamIndex` indicates the output stream parameter.
  *  - `"s"` is a `vsprintf` variant, `outputParamIndex` indicates the output buffer parameter.
- *  - `"?"` if the type cannot be deteremined.  `outputParamIndex` is `-1`.
+ *  - `"?"` if the type cannot be determined.  `outputParamIndex` is `-1`.
  */
 predicate variadicFormatter(Function f, string type, int formatParamIndex, int outputParamIndex) {
   primitiveVariadicFormatter(f, type, formatParamIndex, outputParamIndex)
@@ -1125,12 +1125,12 @@ class FormatLiteral extends Literal {
         exists(int dot, int afterdot |
           (if this.getPrecision(n) = 0 then dot = 0 else dot = 1) and
           (
-            (
-              if this.hasExplicitPrecision(n)
-              then afterdot = this.getPrecision(n)
-              else not this.hasImplicitPrecision(n)
-            ) and
-            afterdot = 6
+            if this.hasExplicitPrecision(n)
+            then afterdot = this.getPrecision(n)
+            else (
+              not this.hasImplicitPrecision(n) and
+              afterdot = 6
+            )
           ) and
           len = 1 + 309 + dot + afterdot
         ) and
@@ -1140,12 +1140,12 @@ class FormatLiteral extends Literal {
         exists(int dot, int afterdot |
           (if this.getPrecision(n) = 0 then dot = 0 else dot = 1) and
           (
-            (
-              if this.hasExplicitPrecision(n)
-              then afterdot = this.getPrecision(n)
-              else not this.hasImplicitPrecision(n)
-            ) and
-            afterdot = 6
+            if this.hasExplicitPrecision(n)
+            then afterdot = this.getPrecision(n)
+            else (
+              not this.hasImplicitPrecision(n) and
+              afterdot = 6
+            )
           ) and
           len = 1 + 1 + dot + afterdot + 1 + 1 + 3
         ) and
@@ -1155,12 +1155,12 @@ class FormatLiteral extends Literal {
         exists(int dot, int afterdot |
           (if this.getPrecision(n) = 0 then dot = 0 else dot = 1) and
           (
-            (
-              if this.hasExplicitPrecision(n)
-              then afterdot = this.getPrecision(n)
-              else not this.hasImplicitPrecision(n)
-            ) and
-            afterdot = 6
+            if this.hasExplicitPrecision(n)
+            then afterdot = this.getPrecision(n)
+            else (
+              not this.hasImplicitPrecision(n) and
+              afterdot = 6
+            )
           ) and
           // note: this could be displayed in the style %e or %f;
           //       however %f is only used when 'P > X >= -4'

cpp/ql/lib/semmle/code/cpp/controlflow/BasicBlocks.qll

@@ -12,7 +12,7 @@ private import internal.ConstantExprs
  * relation). The refinement manifests itself in two changes:
  *
  * - The successor relation on `BasicBlock`s uses `successors_adapted`
- * (instead of `successors_extended` used by `PrimtiveBasicBlock`s). Consequently,
+ * (instead of `successors_extended` used by `PrimitiveBasicBlock`s). Consequently,
  * some edges between `BasicBlock`s may be removed. Example:
  * ```
  * x = 1;      // s1

cpp/ql/lib/semmle/code/cpp/controlflow/StackVariableReachability.qll

@@ -149,7 +149,7 @@ private predicate bbLoopEntryConditionAlwaysTrueAt(BasicBlock bb, int i, Control
 /**
  * Basic block `pred` contains all or part of the condition belonging to a loop,
  * and there is an edge from `pred` to `succ` that concludes the condition.
- * If the edge corrseponds with the loop condition being found to be `true`, then
+ * If the edge corresponds with the loop condition being found to be `true`, then
  * `skipsLoop` is `false`.  Otherwise the edge corresponds with the loop condition
  * being found to be `false` and `skipsLoop` is `true`.  Non-concluding edges
  * within a complex loop condition are not matched by this predicate.

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

@@ -915,6 +915,17 @@ private module Cached {
     TDataFlowCallNone() or
     TDataFlowCallSome(DataFlowCall call)
 
+  cached
+  newtype TParameterPositionOption =
+    TParameterPositionNone() or
+    TParameterPositionSome(ParameterPosition pos)
+
+  cached
+  newtype TReturnCtx =
+    TReturnCtxNone() or
+    TReturnCtxNoFlowThrough() or
+    TReturnCtxMaybeFlowThrough(ReturnKindExt kind)
+
   cached
   newtype TTypedContent = MkTypedContent(Content c, DataFlowType t) { store(_, c, _, _, t) }
 
@@ -1304,6 +1315,44 @@ class DataFlowCallOption extends TDataFlowCallOption {
   }
 }
 
+/** An optional `ParameterPosition`. */
+class ParameterPositionOption extends TParameterPositionOption {
+  string toString() {
+    this = TParameterPositionNone() and
+    result = "(none)"
+    or
+    exists(ParameterPosition pos |
+      this = TParameterPositionSome(pos) and
+      result = pos.toString()
+    )
+  }
+}
+
+/**
+ * A return context used to calculate flow summaries in reverse flow.
+ *
+ * The possible values are:
+ *
+ * - `TReturnCtxNone()`: no return flow.
+ * - `TReturnCtxNoFlowThrough()`: return flow, but flow through is not possible.
+ * - `TReturnCtxMaybeFlowThrough(ReturnKindExt kind)`: return flow, of kind `kind`, and
+ *    flow through may be possible.
+ */
+class ReturnCtx extends TReturnCtx {
+  string toString() {
+    this = TReturnCtxNone() and
+    result = "(none)"
+    or
+    this = TReturnCtxNoFlowThrough() and
+    result = "(no flow through)"
+    or
+    exists(ReturnKindExt kind |
+      this = TReturnCtxMaybeFlowThrough(kind) and
+      result = kind.toString()
+    )
+  }
+}
+
 /** A `Content` tagged with the type of a containing object. */
 class TypedContent extends MkTypedContent {
   private Content c;

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

@@ -136,6 +136,18 @@ module Consistency {
     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) {

cpp/ql/lib/semmle/code/cpp/exprs/BuiltInOperations.qll

@@ -1137,7 +1137,7 @@ class BuiltInOperationIsArray extends BuiltInOperation, @isarray {
  * A C++ `__array_rank` built-in operation (used by some implementations of the
  * `<type_traits>` header).
  *
- * If known, returns the number of dimentsions of an arrary type.
+ * If known, returns the number of dimensions of an arrary type.
  * ```
  * template<typename _Tp>
  *   struct rank

cpp/ql/lib/semmle/code/cpp/exprs/Call.qll

@@ -494,7 +494,7 @@ class VacuousDestructorCall extends Expr, @vacuous_destructor_call {
  * An initialization of a base class or member variable performed as part
  * of a constructor's explicit initializer list or implicit actions.
  *
- * This is a QL root class for reprenting various types of constructor
+ * This is a QL root class for representing various types of constructor
  * initializations.
  */
 class ConstructorInit extends Expr, @ctorinit {

cpp/ql/lib/semmle/code/cpp/exprs/Cast.qll

@@ -779,7 +779,7 @@ class AlignofExprOperator extends AlignofOperator {
 /**
  * A C++11 `alignof` expression whose operand is a type name.
  * ```
- * bool proper_alignment = (alingof(T) == alignof(T[0]);
+ * bool proper_alignment = (alignof(T) == alignof(T[0]);
  * ```
  */
 class AlignofTypeOperator extends AlignofOperator {

cpp/ql/lib/semmle/code/cpp/exprs/Expr.qll

@@ -451,7 +451,7 @@ class Expr extends StmtParent, @expr {
     // For performance, we avoid a full transitive closure over `getConversion`.
     // Since there can be several implicit conversions before and after an
     // explicit conversion, use `getImplicitlyConverted` to step over them
-    // cheaply. Then, if there is an explicit conversion following the implict
+    // cheaply. Then, if there is an explicit conversion following the implicit
     // conversion sequence, recurse to handle multiple explicit conversions.
     if this.getImplicitlyConverted().hasExplicitConversion()
     then result = this.getImplicitlyConverted().getConversion().getExplicitlyConverted()

cpp/ql/lib/semmle/code/cpp/ir/dataflow/MustFlow.qll

@@ -5,7 +5,6 @@
  */
 
 private import cpp
-import semmle.code.cpp.ir.dataflow.DataFlow
 private import semmle.code.cpp.ir.IR
 
 /**
@@ -25,18 +24,18 @@ abstract class MustFlowConfiguration extends string {
   /**
    * Holds if `source` is a relevant data flow source.
    */
-  abstract predicate isSource(DataFlow::Node source);
+  abstract predicate isSource(Instruction source);
 
   /**
    * Holds if `sink` is a relevant data flow sink.
    */
-  abstract predicate isSink(DataFlow::Node sink);
+  abstract predicate isSink(Operand sink);
 
   /**
    * Holds if the additional flow step from `node1` to `node2` must be taken
    * into account in the analysis.
    */
-  predicate isAdditionalFlowStep(DataFlow::Node node1, DataFlow::Node node2) { none() }
+  predicate isAdditionalFlowStep(Operand node1, Instruction node2) { none() }
 
   /** Holds if this configuration allows flow from arguments to parameters. */
   predicate allowInterproceduralFlow() { any() }
@@ -48,17 +47,17 @@ abstract class MustFlowConfiguration extends string {
    * included in the module `PathGraph`.
    */
   final predicate hasFlowPath(MustFlowPathNode source, MustFlowPathSink sink) {
-    this.isSource(source.getNode()) and
+    this.isSource(source.getInstruction()) and
     source.getASuccessor+() = sink
   }
 }
 
 /** Holds if `node` flows from a source. */
 pragma[nomagic]
-private predicate flowsFromSource(DataFlow::Node node, MustFlowConfiguration config) {
+private predicate flowsFromSource(Instruction node, MustFlowConfiguration config) {
   config.isSource(node)
   or
-  exists(DataFlow::Node mid |
+  exists(Instruction mid |
     step(mid, node, config) and
     flowsFromSource(mid, pragma[only_bind_into](config))
   )
@@ -66,12 +65,12 @@ private predicate flowsFromSource(DataFlow::Node node, MustFlowConfiguration con
 
 /** Holds if `node` flows to a sink. */
 pragma[nomagic]
-private predicate flowsToSink(DataFlow::Node node, MustFlowConfiguration config) {
+private predicate flowsToSink(Instruction node, MustFlowConfiguration config) {
   flowsFromSource(node, pragma[only_bind_into](config)) and
   (
-    config.isSink(node)
+    config.isSink(node.getAUse())
     or
-    exists(DataFlow::Node mid |
+    exists(Instruction mid |
       step(node, mid, config) and
       flowsToSink(mid, pragma[only_bind_into](config))
     )
@@ -198,12 +197,13 @@ private module Cached {
   }
 
   cached
-  predicate step(DataFlow::Node nodeFrom, DataFlow::Node nodeTo) {
-    instructionToOperandStep(nodeFrom.asInstruction(), nodeTo.asOperand())
+  predicate step(Instruction nodeFrom, Instruction nodeTo) {
+    exists(Operand mid |
+      instructionToOperandStep(nodeFrom, mid) and
+      operandToInstructionStep(mid, nodeTo)
+    )
     or
-    flowThroughCallable(nodeFrom.asInstruction(), nodeTo.asInstruction())
-    or
-    operandToInstructionStep(nodeFrom.asOperand(), nodeTo.asInstruction())
+    flowThroughCallable(nodeFrom, nodeTo)
   }
 }
 
@@ -213,12 +213,12 @@ private module Cached {
  * way around.
  */
 pragma[inline]
-private Declaration getEnclosingCallable(DataFlow::Node n) {
-  pragma[only_bind_into](result) = pragma[only_bind_out](n).getEnclosingCallable()
+private IRFunction getEnclosingCallable(Instruction n) {
+  pragma[only_bind_into](result) = pragma[only_bind_out](n).getEnclosingIRFunction()
 }
 
 /** Holds if `nodeFrom` flows to `nodeTo`. */
-private predicate step(DataFlow::Node nodeFrom, DataFlow::Node nodeTo, MustFlowConfiguration config) {
+private predicate step(Instruction nodeFrom, Instruction nodeTo, MustFlowConfiguration config) {
   exists(config) and
   Cached::step(pragma[only_bind_into](nodeFrom), pragma[only_bind_into](nodeTo)) and
   (
@@ -227,37 +227,37 @@ private predicate step(DataFlow::Node nodeFrom, DataFlow::Node nodeTo, MustFlowC
     getEnclosingCallable(nodeFrom) = getEnclosingCallable(nodeTo)
   )
   or
-  config.isAdditionalFlowStep(nodeFrom, nodeTo)
+  config.isAdditionalFlowStep(nodeFrom.getAUse(), nodeTo)
 }
 
 private newtype TLocalPathNode =
-  MkLocalPathNode(DataFlow::Node n, MustFlowConfiguration config) {
+  MkLocalPathNode(Instruction n, MustFlowConfiguration config) {
     flowsToSink(n, config) and
     (
       config.isSource(n)
       or
-      exists(MustFlowPathNode mid | step(mid.getNode(), n, config))
+      exists(MustFlowPathNode mid | step(mid.getInstruction(), n, config))
     )
   }
 
 /** A `Node` that is in a path from a source to a sink. */
 class MustFlowPathNode extends TLocalPathNode {
-  DataFlow::Node n;
+  Instruction n;
 
   MustFlowPathNode() { this = MkLocalPathNode(n, _) }
 
   /** Gets the underlying node. */
-  DataFlow::Node getNode() { result = n }
+  Instruction getInstruction() { result = n }
 
   /** Gets a textual representation of this node. */
-  string toString() { result = n.toString() }
+  string toString() { result = n.getAst().toString() }
 
   /** Gets the location of this element. */
   Location getLocation() { result = n.getLocation() }
 
   /** Gets a successor node, if any. */
   MustFlowPathNode getASuccessor() {
-    step(this.getNode(), result.getNode(), this.getConfiguration())
+    step(this.getInstruction(), result.getInstruction(), this.getConfiguration())
   }
 
   /** Gets the associated configuration. */
@@ -265,7 +265,7 @@ class MustFlowPathNode extends TLocalPathNode {
 }
 
 private class MustFlowPathSink extends MustFlowPathNode {
-  MustFlowPathSink() { this.getConfiguration().isSink(this.getNode()) }
+  MustFlowPathSink() { this.getConfiguration().isSink(this.getInstruction().getAUse()) }
 }
 
 /**

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

@@ -915,6 +915,17 @@ private module Cached {
     TDataFlowCallNone() or
     TDataFlowCallSome(DataFlowCall call)
 
+  cached
+  newtype TParameterPositionOption =
+    TParameterPositionNone() or
+    TParameterPositionSome(ParameterPosition pos)
+
+  cached
+  newtype TReturnCtx =
+    TReturnCtxNone() or
+    TReturnCtxNoFlowThrough() or
+    TReturnCtxMaybeFlowThrough(ReturnKindExt kind)
+
   cached
   newtype TTypedContent = MkTypedContent(Content c, DataFlowType t) { store(_, c, _, _, t) }
 
@@ -1304,6 +1315,44 @@ class DataFlowCallOption extends TDataFlowCallOption {
   }
 }
 
+/** An optional `ParameterPosition`. */
+class ParameterPositionOption extends TParameterPositionOption {
+  string toString() {
+    this = TParameterPositionNone() and
+    result = "(none)"
+    or
+    exists(ParameterPosition pos |
+      this = TParameterPositionSome(pos) and
+      result = pos.toString()
+    )
+  }
+}
+
+/**
+ * A return context used to calculate flow summaries in reverse flow.
+ *
+ * The possible values are:
+ *
+ * - `TReturnCtxNone()`: no return flow.
+ * - `TReturnCtxNoFlowThrough()`: return flow, but flow through is not possible.
+ * - `TReturnCtxMaybeFlowThrough(ReturnKindExt kind)`: return flow, of kind `kind`, and
+ *    flow through may be possible.
+ */
+class ReturnCtx extends TReturnCtx {
+  string toString() {
+    this = TReturnCtxNone() and
+    result = "(none)"
+    or
+    this = TReturnCtxNoFlowThrough() and
+    result = "(no flow through)"
+    or
+    exists(ReturnKindExt kind |
+      this = TReturnCtxMaybeFlowThrough(kind) and
+      result = kind.toString()
+    )
+  }
+}
+
 /** A `Content` tagged with the type of a containing object. */
 class TypedContent extends MkTypedContent {
   private Content c;

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

@@ -136,6 +136,18 @@ module Consistency {
     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) {