Update TaintedPathConfig after rebase on main

This filter currently has some overlap with `CreatePathSinkCharacteristic`. We add a flag to `erroneousEndpoints` such that these known modeling errors can optionally be ignored.

We turn the flag off when extracting prompt examples, to ensure the prompt contains only examples we're highly certain about.

If there are errors even with this flag turned on, we return an error message in the query that extracts positive examples, to prevent us from accidentally running it when there's a codex-generated data extension file in `java/ql/lib/ext`.

.git-blame-ignore-revs

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

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

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

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

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

.github/workflows/check-qldoc.yml

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

.github/workflows/compile-queries.yml

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

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

@@ -5,13 +5,6 @@ on:
     branches: [main]
   pull_request:
     branches: [main]
-    paths:
-      - "ql/**"
-      - "**.qll"
-      - "**.ql"
-      - "**.dbscheme"
-      - "**/qlpack.yml"
-      - ".github/workflows/ql-for-ql-build.yml"
 
 env:
   CARGO_TERM_COLOR: always
@@ -22,6 +15,8 @@ jobs:
     steps:
       ### Build the queries ###
       - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
       - name: Find codeql
         id: find-codeql
         uses: github/codeql-action/init@v2
@@ -34,7 +29,9 @@ jobs:
         id: cache-extractor
         uses: actions/cache@v3
         with:
-          path: ql/extractor-pack/
+          path: |
+            ql/extractor-pack/
+            ql/target/release/buramu
           key: ${{ runner.os }}-${{ steps.os_version.outputs.version }}-extractor-${{ hashFiles('ql/**/Cargo.lock') }}-${{ hashFiles('ql/**/*.rs') }}
       - name: Cache cargo
         if: steps.cache-extractor.outputs.cache-hit != 'true'
@@ -57,6 +54,7 @@ jobs:
           key: run-ql-for-ql
       - name: Make database and analyze
         run: |
+          ./ql/target/release/buramu | tee deprecated.blame # Add a blame file for the extractor to parse.
           ${CODEQL} database create -l=ql --search-path ql/extractor-pack ${DB}
           ${CODEQL} database analyze -j0 --format=sarif-latest --output=ql-for-ql.sarif ${DB} ql/ql/src/codeql-suites/ql-code-scanning.qls  --compilation-cache "${{ steps.query-cache.outputs.cache-dir }}"
         env: 
@@ -65,6 +63,7 @@ jobs:
           LGTM_INDEX_FILTERS: |
             exclude:ql/ql/test
             exclude:*/ql/lib/upgrades/
+            exclude:java/ql/integration-tests
       - name: Upload sarif to code-scanning
         uses: github/codeql-action/upload-sarif@v2
         with:

.github/workflows/swift.yml

@@ -5,6 +5,7 @@ on:
     paths:
       - "swift/**"
       - "misc/bazel/**"
+      - "misc/codegen/**"
       - "*.bazel*"
       - .github/workflows/swift.yml
       - .github/actions/**
@@ -19,6 +20,7 @@ on:
     paths:
       - "swift/**"
       - "misc/bazel/**"
+      - "misc/codegen/**"
       - "*.bazel*"
       - .github/workflows/swift.yml
       - .github/actions/**

.pre-commit-config.yaml

@@ -53,5 +53,5 @@ repos:
         name: Run Swift code generation unit tests
         files: ^swift/codegen/.*\.py$
         language: system
-        entry: bazel test //swift/codegen/test
+        entry: bazel test //misc/codegen/test
         pass_filenames: false

CODEOWNERS

@@ -6,6 +6,7 @@
 /python/ @github/codeql-python
 /ruby/ @github/codeql-ruby
 /swift/ @github/codeql-swift
+/misc/codegen/ @github/codeql-swift
 /java/kotlin-extractor/ @github/codeql-kotlin
 /java/kotlin-explorer/ @github/codeql-kotlin
 

codeql-workspace.yml

@@ -8,16 +8,16 @@ provide:
   - "cpp/ql/test/query-tests/Security/CWE/CWE-190/semmle/tainted/qlpack.yml"
   - "go/ql/config/legacy-support/qlpack.yml"
   - "go/build/codeql-extractor-go/codeql-extractor.yml"
-  - "javascript/ql/experimental/adaptivethreatmodeling/lib/qlpack.yml"
+  - "*/ql/experimental/adaptivethreatmodeling/lib/qlpack.yml"
   # This pack is explicitly excluded from the workspace since most users
   # will want to use a version of this pack from the package cache. Internal
   # users can uncomment the following line and place a custom ML model
   # in the corresponding pack to test a custom ML model within their local
   # checkout.
-  # - "javascript/ql/experimental/adaptivethreatmodeling/model/qlpack.yml"
-  - "javascript/ql/experimental/adaptivethreatmodeling/modelbuilding/qlpack.yml"
-  - "javascript/ql/experimental/adaptivethreatmodeling/src/qlpack.yml"
-  - "javascript/ql/experimental/adaptivethreatmodeling/test/qlpack.yml"
+  # - "*/ql/experimental/adaptivethreatmodeling/model/qlpack.yml"
+  - "*/ql/experimental/adaptivethreatmodeling/modelbuilding/qlpack.yml"
+  - "*/ql/experimental/adaptivethreatmodeling/src/qlpack.yml"
+  - "*/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"

config/identical-files.json

@@ -1,6 +1,28 @@
 {
   "DataFlow Java/C++/C#/Go/Python/Ruby/Swift": [
+    "java/ql/lib/semmle/code/java/dataflow/internal/DataFlow.qll",
+    "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlow.qll",
+    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlow.qll",
+    "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlow.qll",
+    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlow.qll",
+    "go/ql/lib/semmle/go/dataflow/internal/DataFlow.qll",
+    "python/ql/lib/semmle/python/dataflow/new/internal/DataFlow.qll",
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlow.qll",
+    "swift/ql/lib/codeql/swift/dataflow/internal/DataFlow.qll"
+  ],
+  "DataFlowImpl Java/C++/C#/Go/Python/Ruby/Swift": [
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl.qll",
+    "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl.qll",
+    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl.qll",
+    "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl.qll",
+    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl.qll",
+    "go/ql/lib/semmle/go/dataflow/internal/DataFlowImpl.qll",
+    "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl.qll",
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImpl.qll",
+    "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImpl.qll"
+  ],
+  "DataFlow Java/C++/C#/Go/Python/Ruby/Swift Legacy Configuration": [
+    "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl1.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl2.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl3.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl4.qll",
@@ -8,38 +30,38 @@
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl6.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplForSerializability.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplForOnActivityResult.qll",
-    "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl.qll",
+    "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl1.qll",
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl2.qll",
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl3.qll",
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl4.qll",
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImplLocal.qll",
-    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl.qll",
+    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl1.qll",
     "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl2.qll",
     "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl3.qll",
     "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl4.qll",
-    "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl.qll",
+    "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl1.qll",
     "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl2.qll",
     "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl3.qll",
     "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl4.qll",
-    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl.qll",
+    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl1.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl2.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl3.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl4.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImpl5.qll",
     "csharp/ql/lib/semmle/code/csharp/dataflow/internal/DataFlowImplForContentDataFlow.qll",
-    "go/ql/lib/semmle/go/dataflow/internal/DataFlowImpl.qll",
+    "go/ql/lib/semmle/go/dataflow/internal/DataFlowImpl1.qll",
     "go/ql/lib/semmle/go/dataflow/internal/DataFlowImpl2.qll",
     "go/ql/lib/semmle/go/dataflow/internal/DataFlowImplForStringsNewReplacer.qll",
-    "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl.qll",
+    "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl1.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl2.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl3.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImpl4.qll",
     "python/ql/lib/semmle/python/dataflow/new/internal/DataFlowImplForRegExp.qll",
-    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImpl.qll",
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImpl1.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImpl2.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplForHttpClientLibraries.qll",
     "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplForPathname.qll",
-    "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImpl.qll"
+    "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImpl1.qll"
   ],
   "DataFlow Java/C++/C#/Go/Python/Ruby/Swift Common": [
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplCommon.qll",
@@ -52,7 +74,18 @@
     "ruby/ql/lib/codeql/ruby/dataflow/internal/DataFlowImplCommon.qll",
     "swift/ql/lib/codeql/swift/dataflow/internal/DataFlowImplCommon.qll"
   ],
-  "TaintTracking::Configuration Java/C++/C#/Go/Python/Ruby/Swift": [
+  "TaintTracking Java/C++/C#/Go/Python/Ruby/Swift": [
+    "cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking1/TaintTracking.qll",
+    "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/tainttracking1/TaintTracking.qll",
+    "cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/tainttracking1/TaintTracking.qll",
+    "csharp/ql/lib/semmle/code/csharp/dataflow/internal/tainttracking1/TaintTracking.qll",
+    "go/ql/lib/semmle/go/dataflow/internal/tainttracking1/TaintTracking.qll",
+    "java/ql/lib/semmle/code/java/dataflow/internal/tainttracking1/TaintTracking.qll",
+    "python/ql/lib/semmle/python/dataflow/new/internal/tainttracking1/TaintTracking.qll",
+    "ruby/ql/lib/codeql/ruby/dataflow/internal/tainttracking1/TaintTracking.qll",
+    "swift/ql/lib/codeql/swift/dataflow/internal/tainttracking1/TaintTracking.qll"
+  ],
+  "TaintTracking Legacy Configuration Java/C++/C#/Go/Python/Ruby/Swift": [
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/tainttracking2/TaintTrackingImpl.qll",
     "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/tainttracking1/TaintTrackingImpl.qll",

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

@@ -1,5 +1,6 @@
 using Xunit;
 using Semmle.Autobuild.Shared;
+using Semmle.Util;
 using System.Collections.Generic;
 using System;
 using System.Linq;
@@ -75,6 +76,15 @@ namespace Semmle.Autobuild.Cpp.Tests
             throw new ArgumentException("Missing RunProcess " + pattern);
         }
 
+        int IBuildActions.RunProcess(string cmd, string args, string? workingDirectory, IDictionary<string, string>? env, BuildOutputHandler onOutput, BuildOutputHandler onError)
+        {
+            var ret = (this as IBuildActions).RunProcess(cmd, args, workingDirectory, env, out var stdout);
+
+            stdout.ForEach(line => onOutput(line));
+
+            return ret;
+        }
+
         public IList<string> DirectoryDeleteIn = new List<string>();
 
         void IBuildActions.DirectoryDelete(string dir, bool recursive)
@@ -131,6 +141,14 @@ namespace Semmle.Autobuild.Cpp.Tests
 
         bool IBuildActions.IsWindows() => IsWindows;
 
+        public bool IsMacOs { get; set; }
+
+        bool IBuildActions.IsMacOs() => IsMacOs;
+
+        public bool IsArm { get; set; }
+
+        bool IBuildActions.IsArm() => IsArm;
+
         string IBuildActions.PathCombine(params string[] parts)
         {
             return string.Join(IsWindows ? '\\' : '/', parts.Where(p => !string.IsNullOrWhiteSpace(p)));
@@ -176,6 +194,15 @@ namespace Semmle.Autobuild.Cpp.Tests
             if (!DownloadFiles.Contains((address, fileName)))
                 throw new ArgumentException($"Missing DownloadFile, {address}, {fileName}");
         }
+
+        public IDiagnosticsWriter CreateDiagnosticsWriter(string filename) => new TestDiagnosticWriter();
+    }
+
+    internal class TestDiagnosticWriter : IDiagnosticsWriter
+    {
+        public IList<DiagnosticMessage> Diagnostics { get; } = new List<DiagnosticMessage>();
+
+        public void AddEntry(DiagnosticMessage message) => this.Diagnostics.Add(message);
     }
 
     /// <summary>
@@ -235,6 +262,7 @@ namespace Semmle.Autobuild.Cpp.Tests
             Actions.GetEnvironmentVariable[$"CODEQL_EXTRACTOR_{codeqlUpperLanguage}_TRAP_DIR"] = "";
             Actions.GetEnvironmentVariable[$"CODEQL_EXTRACTOR_{codeqlUpperLanguage}_SOURCE_ARCHIVE_DIR"] = "";
             Actions.GetEnvironmentVariable[$"CODEQL_EXTRACTOR_{codeqlUpperLanguage}_ROOT"] = $@"C:\codeql\{codeqlUpperLanguage.ToLowerInvariant()}";
+            Actions.GetEnvironmentVariable[$"CODEQL_EXTRACTOR_{codeqlUpperLanguage}_DIAGNOSTIC_DIR"] = "";
             Actions.GetEnvironmentVariable["CODEQL_JAVA_HOME"] = @"C:\codeql\tools\java";
             Actions.GetEnvironmentVariable["CODEQL_PLATFORM"] = "win64";
             Actions.GetEnvironmentVariable["SEMMLE_DIST"] = @"C:\odasa";

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

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

cpp/ql/lib/CHANGELOG.md

@@ -1,3 +1,7 @@
+## 0.5.4
+
+No user-facing changes.
+
 ## 0.5.3
 
 No user-facing changes.

cpp/ql/lib/change-notes/2023-03-02-dataflow-conf-module.md

@@ -0,0 +1,9 @@
+---
+category: majorAnalysis
+---
+* The main data flow and taint tracking APIs have been changed. The old APIs
+  remain in place for now and translate to the new through a
+  backwards-compatible wrapper. If multiple configurations are in scope
+  simultaneously, then this may affect results slightly. The new API is quite
+  similar to the old, but makes use of a configuration module instead of a
+  configuration class.

cpp/ql/lib/change-notes/2023-03-03-delete-deps.md

@@ -0,0 +1,12 @@
+---
+category: minorAnalysis
+---
+* Deleted the deprecated `hasGeneratedCopyConstructor` and `hasGeneratedCopyAssignmentOperator` predicates from the `Folder` class.
+* Deleted the deprecated `getPath` and `getFolder` predicates from the `XmlFile` class.
+* Deleted the deprecated `getMustlockFunction`, `getTrylockFunction`, `getLockFunction`, and `getUnlockFunction` predicates from the `MutexType` class.
+* Deleted the deprecated `getPosInBasicBlock` predicate from the `SubBasicBlock` class.
+* Deleted the deprecated `getExpr` predicate from the `PointerDereferenceExpr` class.
+* Deleted the deprecated `getUseInstruction` and `getDefinitionInstruction` predicates from the `Operand` class.
+* Deleted the deprecated `isInParameter`, `isInParameterPointer`, and `isInQualifier` predicates from the `FunctionInput` class.
+* Deleted the deprecated `isOutParameterPointer`, `isOutQualifier`, `isOutReturnValue`, and `isOutReturnPointer` predicate from the `FunctionOutput` class.
+* Deleted the deprecated 3-argument `isGuardPhi` predicate from the `RangeSsaDefinition` class.

cpp/ql/lib/change-notes/2023-03-13-mergepathgraph.md

@@ -0,0 +1,4 @@
+---
+category: feature
+---
+* Added support for merging two `PathGraph`s via disjoint union to allow results from multiple data flow computations in a single `path-problem` query.

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

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

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

@@ -1,2 +1,2 @@
 ---
-lastReleaseVersion: 0.5.3
+lastReleaseVersion: 0.5.4

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

@@ -22,5 +22,6 @@
 import cpp
 
 module DataFlow {
-  import experimental.semmle.code.cpp.ir.dataflow.internal.DataFlowImpl
+  import experimental.semmle.code.cpp.ir.dataflow.internal.DataFlow
+  import experimental.semmle.code.cpp.ir.dataflow.internal.DataFlowImpl1
 }

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

@@ -19,5 +19,6 @@ import semmle.code.cpp.ir.dataflow.DataFlow
 import semmle.code.cpp.ir.dataflow.DataFlow2
 
 module TaintTracking {
+  import experimental.semmle.code.cpp.ir.dataflow.internal.tainttracking1.TaintTracking
   import experimental.semmle.code.cpp.ir.dataflow.internal.tainttracking1.TaintTrackingImpl
 }

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

@@ -0,0 +1,353 @@
+/**
+ * Provides an implementation of global (interprocedural) data flow. This file
+ * re-exports the local (intraprocedural) data flow analysis from
+ * `DataFlowImplSpecific::Public` and adds a global analysis, mainly exposed
+ * through the `Make` and `MakeWithState` modules.
+ */
+
+private import DataFlowImplCommon
+private import DataFlowImplSpecific::Private
+import DataFlowImplSpecific::Public
+import DataFlowImplCommonPublic
+private import DataFlowImpl
+
+/** An input configuration for data flow. */
+signature module ConfigSig {
+  /**
+   * Holds if `source` is a relevant data flow source.
+   */
+  predicate isSource(Node source);
+
+  /**
+   * Holds if `sink` is a relevant data flow sink.
+   */
+  predicate isSink(Node sink);
+
+  /**
+   * Holds if data flow through `node` is prohibited. This completely removes
+   * `node` from the data flow graph.
+   */
+  default predicate isBarrier(Node node) { none() }
+
+  /** Holds if data flow into `node` is prohibited. */
+  default predicate isBarrierIn(Node node) { none() }
+
+  /** Holds if data flow out of `node` is prohibited. */
+  default predicate isBarrierOut(Node node) { none() }
+
+  /**
+   * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps.
+   */
+  default predicate isAdditionalFlowStep(Node node1, Node node2) { none() }
+
+  /**
+   * Holds if an arbitrary number of implicit read steps of content `c` may be
+   * taken at `node`.
+   */
+  default predicate allowImplicitRead(Node node, ContentSet c) { none() }
+
+  /**
+   * Gets the virtual dispatch branching limit when calculating field flow.
+   * This can be overridden to a smaller value to improve performance (a
+   * value of 0 disables field flow), or a larger value to get more results.
+   */
+  default int fieldFlowBranchLimit() { result = 2 }
+
+  /**
+   * Gets a data flow configuration feature to add restrictions to the set of
+   * valid flow paths.
+   *
+   * - `FeatureHasSourceCallContext`:
+   *    Assume that sources have some existing call context to disallow
+   *    conflicting return-flow directly following the source.
+   * - `FeatureHasSinkCallContext`:
+   *    Assume that sinks have some existing call context to disallow
+   *    conflicting argument-to-parameter flow directly preceding the sink.
+   * - `FeatureEqualSourceSinkCallContext`:
+   *    Implies both of the above and additionally ensures that the entire flow
+   *    path preserves the call context.
+   *
+   * These features are generally not relevant for typical end-to-end data flow
+   * queries, but should only be used for constructing paths that need to
+   * somehow be pluggable in another path context.
+   */
+  default FlowFeature getAFeature() { none() }
+
+  /** Holds if sources should be grouped in the result of `hasFlowPath`. */
+  default predicate sourceGrouping(Node source, string sourceGroup) { none() }
+
+  /** Holds if sinks should be grouped in the result of `hasFlowPath`. */
+  default predicate sinkGrouping(Node sink, string sinkGroup) { none() }
+
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (as it is in a `path-problem` query).
+   */
+  default predicate includeHiddenNodes() { none() }
+}
+
+/** An input configuration for data flow using flow state. */
+signature module StateConfigSig {
+  bindingset[this]
+  class FlowState;
+
+  /**
+   * Holds if `source` is a relevant data flow source with the given initial
+   * `state`.
+   */
+  predicate isSource(Node source, FlowState state);
+
+  /**
+   * Holds if `sink` is a relevant data flow sink accepting `state`.
+   */
+  predicate isSink(Node sink, FlowState state);
+
+  /**
+   * Holds if data flow through `node` is prohibited. This completely removes
+   * `node` from the data flow graph.
+   */
+  default predicate isBarrier(Node node) { none() }
+
+  /**
+   * Holds if data flow through `node` is prohibited when the flow state is
+   * `state`.
+   */
+  predicate isBarrier(Node node, FlowState state);
+
+  /** Holds if data flow into `node` is prohibited. */
+  default predicate isBarrierIn(Node node) { none() }
+
+  /** Holds if data flow out of `node` is prohibited. */
+  default predicate isBarrierOut(Node node) { none() }
+
+  /**
+   * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps.
+   */
+  default predicate isAdditionalFlowStep(Node node1, Node node2) { none() }
+
+  /**
+   * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps.
+   * This step is only applicable in `state1` and updates the flow state to `state2`.
+   */
+  predicate isAdditionalFlowStep(Node node1, FlowState state1, Node node2, FlowState state2);
+
+  /**
+   * Holds if an arbitrary number of implicit read steps of content `c` may be
+   * taken at `node`.
+   */
+  default predicate allowImplicitRead(Node node, ContentSet c) { none() }
+
+  /**
+   * Gets the virtual dispatch branching limit when calculating field flow.
+   * This can be overridden to a smaller value to improve performance (a
+   * value of 0 disables field flow), or a larger value to get more results.
+   */
+  default int fieldFlowBranchLimit() { result = 2 }
+
+  /**
+   * Gets a data flow configuration feature to add restrictions to the set of
+   * valid flow paths.
+   *
+   * - `FeatureHasSourceCallContext`:
+   *    Assume that sources have some existing call context to disallow
+   *    conflicting return-flow directly following the source.
+   * - `FeatureHasSinkCallContext`:
+   *    Assume that sinks have some existing call context to disallow
+   *    conflicting argument-to-parameter flow directly preceding the sink.
+   * - `FeatureEqualSourceSinkCallContext`:
+   *    Implies both of the above and additionally ensures that the entire flow
+   *    path preserves the call context.
+   *
+   * These features are generally not relevant for typical end-to-end data flow
+   * queries, but should only be used for constructing paths that need to
+   * somehow be pluggable in another path context.
+   */
+  default FlowFeature getAFeature() { none() }
+
+  /** Holds if sources should be grouped in the result of `hasFlowPath`. */
+  default predicate sourceGrouping(Node source, string sourceGroup) { none() }
+
+  /** Holds if sinks should be grouped in the result of `hasFlowPath`. */
+  default predicate sinkGrouping(Node sink, string sinkGroup) { none() }
+
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (as it is in a `path-problem` query).
+   */
+  default predicate includeHiddenNodes() { none() }
+}
+
+/**
+ * Gets the exploration limit for `hasPartialFlow` and `hasPartialFlowRev`
+ * measured in approximate number of interprocedural steps.
+ */
+signature int explorationLimitSig();
+
+/**
+ * The output of a data flow computation.
+ */
+signature module DataFlowSig {
+  /**
+   * A `Node` augmented with a call context (except for sinks) and an access path.
+   * Only those `PathNode`s that are reachable from a source, and which can reach a sink, are generated.
+   */
+  class PathNode;
+
+  /**
+   * Holds if data can flow from `source` to `sink`.
+   *
+   * The corresponding paths are generated from the end-points and the graph
+   * included in the module `PathGraph`.
+   */
+  predicate hasFlowPath(PathNode source, PathNode sink);
+
+  /**
+   * Holds if data can flow from `source` to `sink`.
+   */
+  predicate hasFlow(Node source, Node sink);
+
+  /**
+   * Holds if data can flow from some source to `sink`.
+   */
+  predicate hasFlowTo(Node sink);
+
+  /**
+   * Holds if data can flow from some source to `sink`.
+   */
+  predicate hasFlowToExpr(DataFlowExpr sink);
+}
+
+/**
+ * Constructs a standard data flow computation.
+ */
+module Make<ConfigSig Config> implements DataFlowSig {
+  private module C implements FullStateConfigSig {
+    import DefaultState<Config>
+    import Config
+  }
+
+  import Impl<C>
+}
+
+/**
+ * Constructs a data flow computation using flow state.
+ */
+module MakeWithState<StateConfigSig Config> implements DataFlowSig {
+  private module C implements FullStateConfigSig {
+    import Config
+  }
+
+  import Impl<C>
+}
+
+signature class PathNodeSig {
+  /** Gets a textual representation of this element. */
+  string toString();
+
+  /**
+   * Holds if this element is at the specified location.
+   * The location spans column `startcolumn` of line `startline` to
+   * column `endcolumn` of line `endline` in file `filepath`.
+   * For more information, see
+   * [Locations](https://codeql.github.com/docs/writing-codeql-queries/providing-locations-in-codeql-queries/).
+   */
+  predicate hasLocationInfo(
+    string filepath, int startline, int startcolumn, int endline, int endcolumn
+  );
+
+  /** Gets the underlying `Node`. */
+  Node getNode();
+}
+
+signature module PathGraphSig<PathNodeSig PathNode> {
+  /** Holds if `(a,b)` is an edge in the graph of data flow path explanations. */
+  predicate edges(PathNode a, PathNode b);
+
+  /** Holds if `n` is a node in the graph of data flow path explanations. */
+  predicate nodes(PathNode n, string key, string val);
+
+  /**
+   * Holds if `(arg, par, ret, out)` forms a subpath-tuple, that is, flow through
+   * a subpath between `par` and `ret` with the connecting edges `arg -> par` and
+   * `ret -> out` is summarized as the edge `arg -> out`.
+   */
+  predicate subpaths(PathNode arg, PathNode par, PathNode ret, PathNode out);
+}
+
+/**
+ * Constructs a `PathGraph` from two `PathGraph`s by disjoint union.
+ */
+module MergePathGraph<
+  PathNodeSig PathNode1, PathNodeSig PathNode2, PathGraphSig<PathNode1> Graph1,
+  PathGraphSig<PathNode2> Graph2>
+{
+  private newtype TPathNode =
+    TPathNode1(PathNode1 p) or
+    TPathNode2(PathNode2 p)
+
+  /** A node in a graph of path explanations that is formed by disjoint union of the two given graphs. */
+  class PathNode extends TPathNode {
+    /** Gets this as a projection on the first given `PathGraph`. */
+    PathNode1 asPathNode1() { this = TPathNode1(result) }
+
+    /** Gets this as a projection on the second given `PathGraph`. */
+    PathNode2 asPathNode2() { this = TPathNode2(result) }
+
+    /** Gets a textual representation of this element. */
+    string toString() {
+      result = this.asPathNode1().toString() or
+      result = this.asPathNode2().toString()
+    }
+
+    /**
+     * Holds if this element is at the specified location.
+     * The location spans column `startcolumn` of line `startline` to
+     * column `endcolumn` of line `endline` in file `filepath`.
+     * For more information, see
+     * [Locations](https://codeql.github.com/docs/writing-codeql-queries/providing-locations-in-codeql-queries/).
+     */
+    predicate hasLocationInfo(
+      string filepath, int startline, int startcolumn, int endline, int endcolumn
+    ) {
+      this.asPathNode1().hasLocationInfo(filepath, startline, startcolumn, endline, endcolumn) or
+      this.asPathNode2().hasLocationInfo(filepath, startline, startcolumn, endline, endcolumn)
+    }
+
+    /** Gets the underlying `Node`. */
+    Node getNode() {
+      result = this.asPathNode1().getNode() or
+      result = this.asPathNode2().getNode()
+    }
+  }
+
+  /**
+   * Provides the query predicates needed to include a graph in a path-problem query.
+   */
+  module PathGraph implements PathGraphSig<PathNode> {
+    /** Holds if `(a,b)` is an edge in the graph of data flow path explanations. */
+    query predicate edges(PathNode a, PathNode b) {
+      Graph1::edges(a.asPathNode1(), b.asPathNode1()) or
+      Graph2::edges(a.asPathNode2(), b.asPathNode2())
+    }
+
+    /** Holds if `n` is a node in the graph of data flow path explanations. */
+    query predicate nodes(PathNode n, string key, string val) {
+      Graph1::nodes(n.asPathNode1(), key, val) or
+      Graph2::nodes(n.asPathNode2(), key, val)
+    }
+
+    /**
+     * Holds if `(arg, par, ret, out)` forms a subpath-tuple, that is, flow through
+     * a subpath between `par` and `ret` with the connecting edges `arg -> par` and
+     * `ret -> out` is summarized as the edge `arg -> out`.
+     */
+    query predicate subpaths(PathNode arg, PathNode par, PathNode ret, PathNode out) {
+      Graph1::subpaths(arg.asPathNode1(), par.asPathNode1(), ret.asPathNode1(), out.asPathNode1()) or
+      Graph2::subpaths(arg.asPathNode2(), par.asPathNode2(), ret.asPathNode2(), out.asPathNode2())
+    }
+  }
+}

cpp/ql/lib/experimental/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl1.qll

@@ -0,0 +1,396 @@
+/**
+ * DEPRECATED: Use `Make` and `MakeWithState` instead.
+ *
+ * Provides a `Configuration` class backwards-compatible interface to the data
+ * flow library.
+ */
+
+private import DataFlowImplCommon
+private import DataFlowImplSpecific::Private
+import DataFlowImplSpecific::Public
+private import DataFlowImpl
+import DataFlowImplCommonPublic
+import FlowStateString
+
+/**
+ * A configuration of interprocedural data flow analysis. This defines
+ * sources, sinks, and any other configurable aspect of the analysis. Each
+ * use of the global data flow library must define its own unique extension
+ * of this abstract class. To create a configuration, extend this class with
+ * a subclass whose characteristic predicate is a unique singleton string.
+ * For example, write
+ *
+ * ```ql
+ * class MyAnalysisConfiguration extends DataFlow::Configuration {
+ *   MyAnalysisConfiguration() { this = "MyAnalysisConfiguration" }
+ *   // Override `isSource` and `isSink`.
+ *   // Optionally override `isBarrier`.
+ *   // Optionally override `isAdditionalFlowStep`.
+ * }
+ * ```
+ * Conceptually, this defines a graph where the nodes are `DataFlow::Node`s and
+ * the edges are those data-flow steps that preserve the value of the node
+ * along with any additional edges defined by `isAdditionalFlowStep`.
+ * Specifying nodes in `isBarrier` will remove those nodes from the graph, and
+ * specifying nodes in `isBarrierIn` and/or `isBarrierOut` will remove in-going
+ * and/or out-going edges from those nodes, respectively.
+ *
+ * Then, to query whether there is flow between some `source` and `sink`,
+ * write
+ *
+ * ```ql
+ * exists(MyAnalysisConfiguration cfg | cfg.hasFlow(source, sink))
+ * ```
+ *
+ * Multiple configurations can coexist, but two classes extending
+ * `DataFlow::Configuration` should never depend on each other. One of them
+ * should instead depend on a `DataFlow2::Configuration`, a
+ * `DataFlow3::Configuration`, or a `DataFlow4::Configuration`.
+ */
+abstract class Configuration extends string {
+  bindingset[this]
+  Configuration() { any() }
+
+  /**
+   * Holds if `source` is a relevant data flow source.
+   */
+  predicate isSource(Node source) { none() }
+
+  /**
+   * Holds if `source` is a relevant data flow source with the given initial
+   * `state`.
+   */
+  predicate isSource(Node source, FlowState state) { none() }
+
+  /**
+   * Holds if `sink` is a relevant data flow sink.
+   */
+  predicate isSink(Node sink) { none() }
+
+  /**
+   * Holds if `sink` is a relevant data flow sink accepting `state`.
+   */
+  predicate isSink(Node sink, FlowState state) { none() }
+
+  /**
+   * Holds if data flow through `node` is prohibited. This completely removes
+   * `node` from the data flow graph.
+   */
+  predicate isBarrier(Node node) { none() }
+
+  /**
+   * Holds if data flow through `node` is prohibited when the flow state is
+   * `state`.
+   */
+  predicate isBarrier(Node node, FlowState state) { none() }
+
+  /** Holds if data flow into `node` is prohibited. */
+  predicate isBarrierIn(Node node) { none() }
+
+  /** Holds if data flow out of `node` is prohibited. */
+  predicate isBarrierOut(Node node) { none() }
+
+  /**
+   * DEPRECATED: Use `isBarrier` and `BarrierGuard` module instead.
+   *
+   * Holds if data flow through nodes guarded by `guard` is prohibited.
+   */
+  deprecated predicate isBarrierGuard(BarrierGuard guard) { none() }
+
+  /**
+   * DEPRECATED: Use `isBarrier` and `BarrierGuard` module instead.
+   *
+   * Holds if data flow through nodes guarded by `guard` is prohibited when
+   * the flow state is `state`
+   */
+  deprecated predicate isBarrierGuard(BarrierGuard guard, FlowState state) { none() }
+
+  /**
+   * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps.
+   */
+  predicate isAdditionalFlowStep(Node node1, Node node2) { none() }
+
+  /**
+   * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps.
+   * This step is only applicable in `state1` and updates the flow state to `state2`.
+   */
+  predicate isAdditionalFlowStep(Node node1, FlowState state1, Node node2, FlowState state2) {
+    none()
+  }
+
+  /**
+   * Holds if an arbitrary number of implicit read steps of content `c` may be
+   * taken at `node`.
+   */
+  predicate allowImplicitRead(Node node, ContentSet c) { none() }
+
+  /**
+   * Gets the virtual dispatch branching limit when calculating field flow.
+   * This can be overridden to a smaller value to improve performance (a
+   * value of 0 disables field flow), or a larger value to get more results.
+   */
+  int fieldFlowBranchLimit() { result = 2 }
+
+  /**
+   * Gets a data flow configuration feature to add restrictions to the set of
+   * valid flow paths.
+   *
+   * - `FeatureHasSourceCallContext`:
+   *    Assume that sources have some existing call context to disallow
+   *    conflicting return-flow directly following the source.
+   * - `FeatureHasSinkCallContext`:
+   *    Assume that sinks have some existing call context to disallow
+   *    conflicting argument-to-parameter flow directly preceding the sink.
+   * - `FeatureEqualSourceSinkCallContext`:
+   *    Implies both of the above and additionally ensures that the entire flow
+   *    path preserves the call context.
+   *
+   * These features are generally not relevant for typical end-to-end data flow
+   * queries, but should only be used for constructing paths that need to
+   * somehow be pluggable in another path context.
+   */
+  FlowFeature getAFeature() { none() }
+
+  /** Holds if sources should be grouped in the result of `hasFlowPath`. */
+  predicate sourceGrouping(Node source, string sourceGroup) { none() }
+
+  /** Holds if sinks should be grouped in the result of `hasFlowPath`. */
+  predicate sinkGrouping(Node sink, string sinkGroup) { none() }
+
+  /**
+   * Holds if data may flow from `source` to `sink` for this configuration.
+   */
+  predicate hasFlow(Node source, Node sink) { hasFlow(source, sink, this) }
+
+  /**
+   * Holds if data may flow from `source` to `sink` for this configuration.
+   *
+   * The corresponding paths are generated from the end-points and the graph
+   * included in the module `PathGraph`.
+   */
+  predicate hasFlowPath(PathNode source, PathNode sink) { hasFlowPath(source, sink, this) }
+
+  /**
+   * Holds if data may flow from some source to `sink` for this configuration.
+   */
+  predicate hasFlowTo(Node sink) { hasFlowTo(sink, this) }
+
+  /**
+   * Holds if data may flow from some source to `sink` for this configuration.
+   */
+  predicate hasFlowToExpr(DataFlowExpr sink) { this.hasFlowTo(exprNode(sink)) }
+
+  /**
+   * DEPRECATED: Use `FlowExploration<explorationLimit>` instead.
+   *
+   * Gets the exploration limit for `hasPartialFlow` and `hasPartialFlowRev`
+   * measured in approximate number of interprocedural steps.
+   */
+  deprecated int explorationLimit() { none() }
+
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (for example in a `path-problem` query).
+   */
+  predicate includeHiddenNodes() { none() }
+}
+
+/**
+ * This class exists to prevent mutual recursion between the user-overridden
+ * member predicates of `Configuration` and the rest of the data-flow library.
+ * Good performance cannot be guaranteed in the presence of such recursion, so
+ * it should be replaced by using more than one copy of the data flow library.
+ */
+abstract private class ConfigurationRecursionPrevention extends Configuration {
+  bindingset[this]
+  ConfigurationRecursionPrevention() { any() }
+
+  override predicate hasFlow(Node source, Node sink) {
+    strictcount(Node n | this.isSource(n)) < 0
+    or
+    strictcount(Node n | this.isSource(n, _)) < 0
+    or
+    strictcount(Node n | this.isSink(n)) < 0
+    or
+    strictcount(Node n | this.isSink(n, _)) < 0
+    or
+    strictcount(Node n1, Node n2 | this.isAdditionalFlowStep(n1, n2)) < 0
+    or
+    strictcount(Node n1, Node n2 | this.isAdditionalFlowStep(n1, _, n2, _)) < 0
+    or
+    super.hasFlow(source, sink)
+  }
+}
+
+/** A bridge class to access the deprecated `isBarrierGuard`. */
+private class BarrierGuardGuardedNodeBridge extends Unit {
+  abstract predicate guardedNode(Node n, Configuration config);
+
+  abstract predicate guardedNode(Node n, FlowState state, Configuration config);
+}
+
+private class BarrierGuardGuardedNode extends BarrierGuardGuardedNodeBridge {
+  deprecated override predicate guardedNode(Node n, Configuration config) {
+    exists(BarrierGuard g |
+      config.isBarrierGuard(g) and
+      n = g.getAGuardedNode()
+    )
+  }
+
+  deprecated override predicate guardedNode(Node n, FlowState state, Configuration config) {
+    exists(BarrierGuard g |
+      config.isBarrierGuard(g, state) and
+      n = g.getAGuardedNode()
+    )
+  }
+}
+
+private FlowState relevantState(Configuration config) {
+  config.isSource(_, result) or
+  config.isSink(_, result) or
+  config.isBarrier(_, result) or
+  config.isAdditionalFlowStep(_, result, _, _) or
+  config.isAdditionalFlowStep(_, _, _, result)
+}
+
+private newtype TConfigState =
+  TMkConfigState(Configuration config, FlowState state) {
+    state = relevantState(config) or state instanceof FlowStateEmpty
+  }
+
+private Configuration getConfig(TConfigState state) { state = TMkConfigState(result, _) }
+
+private FlowState getState(TConfigState state) { state = TMkConfigState(_, result) }
+
+private predicate singleConfiguration() { 1 = strictcount(Configuration c) }
+
+private module Config implements FullStateConfigSig {
+  class FlowState = TConfigState;
+
+  predicate isSource(Node source, FlowState state) {
+    getConfig(state).isSource(source, getState(state))
+    or
+    getConfig(state).isSource(source) and getState(state) instanceof FlowStateEmpty
+  }
+
+  predicate isSink(Node sink, FlowState state) {
+    getConfig(state).isSink(sink, getState(state))
+    or
+    getConfig(state).isSink(sink) and getState(state) instanceof FlowStateEmpty
+  }
+
+  predicate isBarrier(Node node) { none() }
+
+  predicate isBarrier(Node node, FlowState state) {
+    getConfig(state).isBarrier(node, getState(state)) or
+    getConfig(state).isBarrier(node) or
+    any(BarrierGuardGuardedNodeBridge b).guardedNode(node, getState(state), getConfig(state)) or
+    any(BarrierGuardGuardedNodeBridge b).guardedNode(node, getConfig(state))
+  }
+
+  predicate isBarrierIn(Node node) { any(Configuration config).isBarrierIn(node) }
+
+  predicate isBarrierOut(Node node) { any(Configuration config).isBarrierOut(node) }
+
+  predicate isAdditionalFlowStep(Node node1, Node node2) {
+    singleConfiguration() and
+    any(Configuration config).isAdditionalFlowStep(node1, node2)
+  }
+
+  predicate isAdditionalFlowStep(Node node1, FlowState state1, Node node2, FlowState state2) {
+    getConfig(state1).isAdditionalFlowStep(node1, getState(state1), node2, getState(state2)) and
+    getConfig(state2) = getConfig(state1)
+    or
+    not singleConfiguration() and
+    getConfig(state1).isAdditionalFlowStep(node1, node2) and
+    state2 = state1
+  }
+
+  predicate allowImplicitRead(Node node, ContentSet c) {
+    any(Configuration config).allowImplicitRead(node, c)
+  }
+
+  int fieldFlowBranchLimit() { result = min(any(Configuration config).fieldFlowBranchLimit()) }
+
+  FlowFeature getAFeature() { result = any(Configuration config).getAFeature() }
+
+  predicate sourceGrouping(Node source, string sourceGroup) {
+    any(Configuration config).sourceGrouping(source, sourceGroup)
+  }
+
+  predicate sinkGrouping(Node sink, string sinkGroup) {
+    any(Configuration config).sinkGrouping(sink, sinkGroup)
+  }
+
+  predicate includeHiddenNodes() { any(Configuration config).includeHiddenNodes() }
+}
+
+private import Impl<Config> as I
+import I
+
+/**
+ * A `Node` augmented with a call context (except for sinks), an access path, and a configuration.
+ * Only those `PathNode`s that are reachable from a source, and which can reach a sink, are generated.
+ */
+class PathNode instanceof I::PathNode {
+  /** Gets a textual representation of this element. */
+  final string toString() { result = super.toString() }
+
+  /**
+   * Gets a textual representation of this element, including a textual
+   * representation of the call context.
+   */
+  final string toStringWithContext() { result = super.toStringWithContext() }
+
+  /**
+   * Holds if this element is at the specified location.
+   * The location spans column `startcolumn` of line `startline` to
+   * column `endcolumn` of line `endline` in file `filepath`.
+   * For more information, see
+   * [Locations](https://codeql.github.com/docs/writing-codeql-queries/providing-locations-in-codeql-queries/).
+   */
+  final predicate hasLocationInfo(
+    string filepath, int startline, int startcolumn, int endline, int endcolumn
+  ) {
+    super.hasLocationInfo(filepath, startline, startcolumn, endline, endcolumn)
+  }
+
+  /** Gets the underlying `Node`. */
+  final Node getNode() { result = super.getNode() }
+
+  /** Gets the `FlowState` of this node. */
+  final FlowState getState() { result = getState(super.getState()) }
+
+  /** Gets the associated configuration. */
+  final Configuration getConfiguration() { result = getConfig(super.getState()) }
+
+  /** Gets a successor of this node, if any. */
+  final PathNode getASuccessor() { result = super.getASuccessor() }
+
+  /** Holds if this node is a source. */
+  final predicate isSource() { super.isSource() }
+
+  /** Holds if this node is a grouping of source nodes. */
+  final predicate isSourceGroup(string group) { super.isSourceGroup(group) }
+
+  /** Holds if this node is a grouping of sink nodes. */
+  final predicate isSinkGroup(string group) { super.isSinkGroup(group) }
+}
+
+private predicate hasFlow(Node source, Node sink, Configuration config) {
+  exists(PathNode source0, PathNode sink0 |
+    hasFlowPath(source0, sink0, config) and
+    source0.getNode() = source and
+    sink0.getNode() = sink
+  )
+}
+
+private predicate hasFlowPath(PathNode source, PathNode sink, Configuration config) {
+  hasFlowPath(source, sink) and source.getConfiguration() = config
+}
+
+private predicate hasFlowTo(Node sink, Configuration config) { hasFlow(_, sink, config) }
+
+predicate flowsTo = hasFlow/3;

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

@@ -3,15 +3,18 @@ private import DataFlowImplSpecific::Public
 import Cached
 
 module DataFlowImplCommonPublic {
-  /** A state value to track during data flow. */
-  class FlowState = string;
+  /** Provides `FlowState = string`. */
+  module FlowStateString {
+    /** A state value to track during data flow. */
+    class FlowState = string;
 
-  /**
-   * The default state, which is used when the state is unspecified for a source
-   * or a sink.
-   */
-  class FlowStateEmpty extends FlowState {
-    FlowStateEmpty() { this = "" }
+    /**
+     * The default state, which is used when the state is unspecified for a source
+     * or a sink.
+     */
+    class FlowStateEmpty extends FlowState {
+      FlowStateEmpty() { this = "" }
+    }
   }
 
   private newtype TFlowFeature =
@@ -179,6 +182,7 @@ private module LambdaFlow {
     boolean toJump, DataFlowCallOption lastCall
   ) {
     revLambdaFlow0(lambdaCall, kind, node, t, toReturn, toJump, lastCall) and
+    not expectsContent(node, _) and
     if castNode(node) or node instanceof ArgNode or node instanceof ReturnNode
     then compatibleTypes(t, getNodeDataFlowType(node))
     else any()

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

@@ -565,3 +565,12 @@ private class MyConsistencyConfiguration extends Consistency::ConsistencyConfigu
     any()
   }
 }
+
+/**
+ * Gets an additional term that is added to the `join` and `branch` computations to reflect
+ * an additional forward or backwards branching factor that is not taken into account
+ * when calculating the (virtual) dispatch cost.
+ *
+ * Argument `arg` is part of a path from a source to a sink, and `p` is the target parameter.
+ */
+int getAdditionalFlowIntoCallNodeTerm(ArgumentNode arg, ParameterNode p) { none() }

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

@@ -97,23 +97,23 @@ private string getNodeProperty(DataFlow::Node node, string key) {
     |
       kind, ", "
     )
-  or
-  // Is there partial flow from a source to this node?
-  // This property will only be emitted if partial flow is enabled by overriding
-  // `DataFlow::Configuration::explorationLimit()`.
-  key = "pflow" and
-  result =
-    strictconcat(DataFlow::PartialPathNode sourceNode, DataFlow::PartialPathNode destNode, int dist,
-      int order1, int order2 |
-      any(DataFlow::Configuration cfg).hasPartialFlow(sourceNode, destNode, dist) and
-      destNode.getNode() = node and
-      // Only print flow from a source in the same function.
-      sourceNode.getNode().getEnclosingCallable() = node.getEnclosingCallable()
-    |
-      nodeId(sourceNode.getNode(), order1, order2) + "+" + dist.toString(), ", "
-      order by
-        order1, order2, dist desc
-    )
+  // or
+  // // Is there partial flow from a source to this node?
+  // // This property will only be emitted if partial flow is enabled by overriding
+  // // `DataFlow::Configuration::explorationLimit()`.
+  // key = "pflow" and
+  // result =
+  //   strictconcat(DataFlow::PartialPathNode sourceNode, DataFlow::PartialPathNode destNode, int dist,
+  //     int order1, int order2 |
+  //     any(DataFlow::Configuration cfg).hasPartialFlow(sourceNode, destNode, dist) and
+  //     destNode.getNode() = node and
+  //     // Only print flow from a source in the same function.
+  //     sourceNode.getNode().getEnclosingCallable() = node.getEnclosingCallable()
+  //   |
+  //     nodeId(sourceNode.getNode(), order1, order2) + "+" + dist.toString(), ", "
+  //     order by
+  //       order1, order2, dist desc
+  //   )
 }
 
 /**

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

@@ -0,0 +1,64 @@
+/**
+ * Provides classes for performing local (intra-procedural) and
+ * global (inter-procedural) taint-tracking analyses.
+ */
+
+import TaintTrackingParameter::Public
+private import TaintTrackingParameter::Private
+
+private module AddTaintDefaults<DataFlowInternal::FullStateConfigSig Config> implements
+  DataFlowInternal::FullStateConfigSig
+{
+  import Config
+
+  predicate isBarrier(DataFlow::Node node) {
+    Config::isBarrier(node) or defaultTaintSanitizer(node)
+  }
+
+  predicate isAdditionalFlowStep(DataFlow::Node node1, DataFlow::Node node2) {
+    Config::isAdditionalFlowStep(node1, node2) or
+    defaultAdditionalTaintStep(node1, node2)
+  }
+
+  predicate allowImplicitRead(DataFlow::Node node, DataFlow::ContentSet c) {
+    Config::allowImplicitRead(node, c)
+    or
+    (
+      Config::isSink(node, _) or
+      Config::isAdditionalFlowStep(node, _) or
+      Config::isAdditionalFlowStep(node, _, _, _)
+    ) and
+    defaultImplicitTaintRead(node, c)
+  }
+}
+
+/**
+ * Constructs a standard taint tracking computation.
+ */
+module Make<DataFlow::ConfigSig Config> implements DataFlow::DataFlowSig {
+  private module Config0 implements DataFlowInternal::FullStateConfigSig {
+    import DataFlowInternal::DefaultState<Config>
+    import Config
+  }
+
+  private module C implements DataFlowInternal::FullStateConfigSig {
+    import AddTaintDefaults<Config0>
+  }
+
+  import DataFlowInternal::Impl<C>
+}
+
+/**
+ * Constructs a taint tracking computation using flow state.
+ */
+module MakeWithState<DataFlow::StateConfigSig Config> implements DataFlow::DataFlowSig {
+  private module Config0 implements DataFlowInternal::FullStateConfigSig {
+    import Config
+  }
+
+  private module C implements DataFlowInternal::FullStateConfigSig {
+    import AddTaintDefaults<Config0>
+  }
+
+  import DataFlowInternal::Impl<C>
+}

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

@@ -2,4 +2,5 @@ import experimental.semmle.code.cpp.ir.dataflow.internal.TaintTrackingUtil as Pu
 
 module Private {
   import experimental.semmle.code.cpp.ir.dataflow.DataFlow::DataFlow as DataFlow
+  import experimental.semmle.code.cpp.ir.dataflow.internal.DataFlowImpl as DataFlowInternal
 }

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

@@ -936,6 +936,15 @@ module RangeStage<DeltaSig D, BoundSig<D> Bounds, LangSig<D> LangParam, UtilSig<
     bounded(cast.getOperand(), b, delta, upper, fromBackEdge, origdelta, reason)
   }
 
+  /**
+   * Computes a normal form of `x` where -0.0 has changed to +0.0. This can be
+   * needed on the lesser side of a floating-point comparison or on both sides of
+   * a floating point equality because QL does not follow IEEE in floating-point
+   * comparisons but instead defines -0.0 to be less than and distinct from 0.0.
+   */
+  bindingset[x]
+  private float normalizeFloatUp(float x) { result = x + 0.0 }
+
   /**
    * Holds if `b + delta` is a valid bound for `e`.
    * - `upper = true`  : `e <= b + delta`
@@ -1020,6 +1029,15 @@ module RangeStage<DeltaSig D, BoundSig<D> Bounds, LangSig<D> LangParam, UtilSig<
         or
         upper = false and delta = D::fromFloat(D::toFloat(d1).minimum(D::toFloat(d2)))
       )
+      or
+      exists(SemExpr mid, D::Delta d, float f |
+        e.(SemNegateExpr).getOperand() = mid and
+        b instanceof SemZeroBound and
+        bounded(mid, b, d, upper.booleanNot(), fromBackEdge, origdelta, reason) and
+        f = normalizeFloatUp(-D::toFloat(d)) and
+        delta = D::fromFloat(f) and
+        if semPositive(e) then f >= 0 else any()
+      )
     )
   }
 

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

@@ -0,0 +1,132 @@
+/**
+ * Wrapper for the semantic range analysis library that mimics the
+ * interface of the simple range analysis library.
+ */
+
+private import cpp
+private import semmle.code.cpp.ir.IR
+private import experimental.semmle.code.cpp.semantic.SemanticBound
+private import experimental.semmle.code.cpp.semantic.SemanticExprSpecific
+private import RangeAnalysis
+
+/**
+ * Gets the lower bound of the expression.
+ *
+ * Note: expressions in C/C++ are often implicitly or explicitly cast to a
+ * different result type. Such casts can cause the value of the expression
+ * to overflow or to be truncated. This predicate computes the lower bound
+ * of the expression without including the effect of the casts. To compute
+ * the lower bound of the expression after all the casts have been applied,
+ * call `lowerBound` like this:
+ *
+ *    `lowerBound(expr.getFullyConverted())`
+ */
+float lowerBound(Expr expr) {
+  exists(Instruction i, SemBound b | i.getAst() = expr and b instanceof SemZeroBound |
+    semBounded(getSemanticExpr(i), b, result, false, _)
+  )
+}
+
+/**
+ * Gets the upper bound of the expression.
+ *
+ * Note: expressions in C/C++ are often implicitly or explicitly cast to a
+ * different result type. Such casts can cause the value of the expression
+ * to overflow or to be truncated. This predicate computes the upper bound
+ * of the expression without including the effect of the casts. To compute
+ * the upper bound of the expression after all the casts have been applied,
+ * call `upperBound` like this:
+ *
+ *    `upperBound(expr.getFullyConverted())`
+ */
+float upperBound(Expr expr) {
+  exists(Instruction i, SemBound b | i.getAst() = expr and b instanceof SemZeroBound |
+    semBounded(getSemanticExpr(i), b, result, true, _)
+  )
+}
+
+/**
+ * Holds if the upper bound of `expr` may have been widened. This means the
+ * upper bound is in practice likely to be overly wide.
+ */
+predicate upperBoundMayBeWidened(Expr e) { none() }
+
+/**
+ * Holds if `expr` has a provably empty range. For example:
+ *
+ *   10 < expr and expr < 5
+ *
+ * The range of an expression can only be empty if it can never be
+ * executed. For example:
+ *
+ * ```cpp
+ * if (10 < x) {
+ *   if (x < 5) {
+ *     // Unreachable code
+ *     return x; // x has an empty range: 10 < x && x < 5
+ *   }
+ * }
+ * ```
+ */
+predicate exprWithEmptyRange(Expr expr) { lowerBound(expr) > upperBound(expr) }
+
+/** Holds if the definition might overflow negatively. */
+predicate defMightOverflowNegatively(RangeSsaDefinition def, StackVariable v) { none() }
+
+/** Holds if the definition might overflow positively. */
+predicate defMightOverflowPositively(RangeSsaDefinition def, StackVariable v) { none() }
+
+/**
+ * Holds if the definition might overflow (either positively or
+ * negatively).
+ */
+predicate defMightOverflow(RangeSsaDefinition def, StackVariable v) {
+  defMightOverflowNegatively(def, v) or
+  defMightOverflowPositively(def, v)
+}
+
+/**
+ * Holds if the expression might overflow negatively. This predicate
+ * does not consider the possibility that the expression might overflow
+ * due to a conversion.
+ */
+predicate exprMightOverflowNegatively(Expr expr) { none() }
+
+/**
+ * Holds if the expression might overflow negatively. Conversions
+ * are also taken into account. For example the expression
+ * `(int16)(x+y)` might overflow due to the `(int16)` cast, rather than
+ * due to the addition.
+ */
+predicate convertedExprMightOverflowNegatively(Expr expr) {
+  exprMightOverflowNegatively(expr) or
+  convertedExprMightOverflowNegatively(expr.getConversion())
+}
+
+/**
+ * Holds if the expression might overflow positively. This predicate
+ * does not consider the possibility that the expression might overflow
+ * due to a conversion.
+ */
+predicate exprMightOverflowPositively(Expr expr) { none() }
+
+/**
+ * Holds if the expression might overflow positively. Conversions
+ * are also taken into account. For example the expression
+ * `(int16)(x+y)` might overflow due to the `(int16)` cast, rather than
+ * due to the addition.
+ */
+predicate convertedExprMightOverflowPositively(Expr expr) {
+  exprMightOverflowPositively(expr) or
+  convertedExprMightOverflowPositively(expr.getConversion())
+}
+
+/**
+ * Holds if the expression might overflow (either positively or
+ * negatively). The possibility that the expression might overflow
+ * due to an implicit or explicit cast is also considered.
+ */
+predicate convertedExprMightOverflow(Expr expr) {
+  convertedExprMightOverflowNegatively(expr) or
+  convertedExprMightOverflowPositively(expr)
+}

cpp/ql/lib/qlpack.yml

@@ -1,5 +1,5 @@
 name: codeql/cpp-all
-version: 0.5.3
+version: 0.5.5-dev
 groups: cpp
 dbscheme: semmlecode.cpp.dbscheme
 extractor: cpp

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

@@ -227,18 +227,6 @@ class Class extends UserType {
     result = this.accessOfBaseMember(member.getDeclaringType(), member.getASpecifier())
   }
 
-  /**
-   * DEPRECATED: name changed to `hasImplicitCopyConstructor` to reflect that
-   * `= default` members are no longer included.
-   */
-  deprecated predicate hasGeneratedCopyConstructor() { this.hasImplicitCopyConstructor() }
-
-  /**
-   * DEPRECATED: name changed to `hasImplicitCopyAssignmentOperator` to
-   * reflect that `= default` members are no longer included.
-   */
-  deprecated predicate hasGeneratedCopyAssignmentOperator() { this.hasImplicitCopyConstructor() }
-
   /**
    * Holds if this class, struct or union has an implicitly-declared copy
    * constructor that is not _deleted_. This predicate is more accurate than

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

@@ -68,7 +68,9 @@ class Declaration extends Locatable, @declaration {
    * Holds if this declaration has the fully-qualified name `qualifiedName`.
    * See `getQualifiedName`.
    */
-  predicate hasQualifiedName(string qualifiedName) { this.getQualifiedName() = qualifiedName }
+  deprecated predicate hasQualifiedName(string qualifiedName) {
+    this.getQualifiedName() = qualifiedName
+  }
 
   /**
    * Holds if this declaration has a fully-qualified name with a name-space
@@ -184,7 +186,7 @@ class Declaration extends Locatable, @declaration {
   predicate hasDefinition() { exists(this.getDefinition()) }
 
   /** DEPRECATED: Use `hasDefinition` instead. */
-  predicate isDefined() { this.hasDefinition() }
+  deprecated predicate isDefined() { this.hasDefinition() }
 
   /** Gets the preferred location of this declaration, if any. */
   override Location getLocation() { none() }
@@ -617,11 +619,10 @@ private class DirectAccessHolder extends Element {
   /**
    * Like `couldAccessMember` but only contains derivations in which either
    * (5.2), (5.3) or (5.4) must be invoked. In other words, the `this`
-   * parameter is not ignored. This restriction makes it feasible to fully
-   * enumerate this predicate even on large code bases. We check for 11.4 as
-   * part of (5.3), since this further limits the number of tuples produced by
-   * this predicate.
+   * parameter is not ignored. We check for 11.4 as part of (5.3), since
+   * this further limits the number of tuples produced by this predicate.
    */
+  pragma[inline]
   predicate thisCouldAccessMember(Class memberClass, AccessSpecifier memberAccess, Class derived) {
     // Only (5.4) is recursive, and chains of invocations of (5.4) can always
     // be collapsed to one invocation by the transitivity of 11.2/4.
@@ -663,7 +664,9 @@ private class DirectAccessHolder extends Element {
     //    bypasses `p`. Then that path must be public, or we are in case 2.
     exists(AccessSpecifier public | public.hasName("public") |
       exists(Class between, Class p |
-        between.accessOfBaseMember(memberClass, memberAccess).hasName("protected") and
+        between
+            .accessOfBaseMember(pragma[only_bind_into](memberClass), memberAccess)
+            .hasName("protected") and
         this.isFriendOfOrEqualTo(p) and
         (
           // This is case 1 from above. If `p` derives privately from `between`

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

@@ -41,7 +41,7 @@ class Function extends Declaration, ControlFlowNode, AccessHolder, @function {
    * `min<int>(int, int) -> int`, and the full signature of the uninstantiated
    * template on the first line would be `min<T>(T, T) -> T`.
    */
-  string getFullSignature() {
+  deprecated string getFullSignature() {
     exists(string name, string templateArgs, string args |
       result = name + templateArgs + args + " -> " + this.getType().toString() and
       name = this.getQualifiedName() and

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

@@ -65,6 +65,7 @@ class Location extends @location {
    * For more information, see
    * [Locations](https://codeql.github.com/docs/writing-codeql-queries/providing-locations-in-codeql-queries/).
    */
+  pragma[inline]
   predicate hasLocationInfo(
     string filepath, int startline, int startcolumn, int endline, int endcolumn
   ) {

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

@@ -159,7 +159,8 @@ class NameQualifyingElement extends Element, @namequalifyingelement {
  * A special name-qualifying element. For example: `__super`.
  */
 library class SpecialNameQualifyingElement extends NameQualifyingElement,
-  @specialnamequalifyingelement {
+  @specialnamequalifyingelement
+{
   /** Gets the name of this special qualifying element. */
   override string getName() { specialnamequalifyingelements(underlyingElement(this), result) }
 

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

@@ -108,20 +108,6 @@ class XmlFile extends XmlParent, File {
   /** Gets the name of this XML file. */
   override string getName() { result = File.super.getAbsolutePath() }
 
-  /**
-   * DEPRECATED: Use `getAbsolutePath()` instead.
-   *
-   * Gets the path of this XML file.
-   */
-  deprecated string getPath() { result = this.getAbsolutePath() }
-
-  /**
-   * DEPRECATED: Use `getParentContainer().getAbsolutePath()` instead.
-   *
-   * Gets the path of the folder that contains this XML file.
-   */
-  deprecated string getFolder() { result = this.getParentContainer().getAbsolutePath() }
-
   /** Gets the encoding of this XML file. */
   string getEncoding() { xmlEncoding(this, result) }
 

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

@@ -12,7 +12,9 @@ predicate freeFunction(Function f, int argNum) { argNum = f.(DeallocationFunctio
  *
  * DEPRECATED: Use `DeallocationExpr` instead (this also includes `delete` expressions).
  */
-predicate freeCall(FunctionCall fc, Expr arg) { arg = fc.(DeallocationExpr).getFreedExpr() }
+deprecated predicate freeCall(FunctionCall fc, Expr arg) {
+  arg = fc.(DeallocationExpr).getFreedExpr()
+}
 
 /**
  * Is e some kind of allocation or deallocation (`new`, `alloc`, `realloc`, `delete`, `free` etc)?

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

@@ -59,26 +59,6 @@ abstract class MutexType extends Type {
    * Gets a call that unlocks any mutex of this type.
    */
   FunctionCall getUnlockAccess() { this.unlockAccess(result, _) }
-
-  /**
-   * DEPRECATED: use mustlockAccess(fc, arg) instead.
-   */
-  deprecated Function getMustlockFunction() { result = this.getMustlockAccess().getTarget() }
-
-  /**
-   * DEPRECATED: use trylockAccess(fc, arg) instead.
-   */
-  deprecated Function getTrylockFunction() { result = this.getTrylockAccess().getTarget() }
-
-  /**
-   * DEPRECATED: use lockAccess(fc, arg) instead.
-   */
-  deprecated Function getLockFunction() { result = this.getLockAccess().getTarget() }
-
-  /**
-   * DEPRECATED: use unlockAccess(fc, arg) instead.
-   */
-  deprecated Function getUnlockFunction() { result = this.getUnlockAccess().getTarget() }
 }
 
 /**

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

@@ -75,13 +75,6 @@ class SubBasicBlock extends ControlFlowNodeBase {
     )
   }
 
-  /**
-   * DEPRECATED: use `getRankInBasicBlock` instead. Note that this predicate
-   * returns a 0-based position, while `getRankInBasicBlock` returns a 1-based
-   * position.
-   */
-  deprecated int getPosInBasicBlock(BasicBlock bb) { result = this.getRankInBasicBlock(bb) - 1 }
-
   pragma[noinline]
   private int getIndexInBasicBlock(BasicBlock bb) { this = bb.getNode(result) }
 

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

@@ -20,5 +20,6 @@
 import cpp
 
 module DataFlow {
-  import semmle.code.cpp.dataflow.internal.DataFlowImpl
+  import semmle.code.cpp.dataflow.internal.DataFlow
+  import semmle.code.cpp.dataflow.internal.DataFlowImpl1
 }

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

@@ -19,5 +19,6 @@ import semmle.code.cpp.dataflow.DataFlow
 import semmle.code.cpp.dataflow.DataFlow2
 
 module TaintTracking {
+  import semmle.code.cpp.dataflow.internal.tainttracking1.TaintTracking
   import semmle.code.cpp.dataflow.internal.tainttracking1.TaintTrackingImpl
 }

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

@@ -0,0 +1,353 @@
+/**
+ * Provides an implementation of global (interprocedural) data flow. This file
+ * re-exports the local (intraprocedural) data flow analysis from
+ * `DataFlowImplSpecific::Public` and adds a global analysis, mainly exposed
+ * through the `Make` and `MakeWithState` modules.
+ */
+
+private import DataFlowImplCommon
+private import DataFlowImplSpecific::Private
+import DataFlowImplSpecific::Public
+import DataFlowImplCommonPublic
+private import DataFlowImpl
+
+/** An input configuration for data flow. */
+signature module ConfigSig {
+  /**
+   * Holds if `source` is a relevant data flow source.
+   */
+  predicate isSource(Node source);
+
+  /**
+   * Holds if `sink` is a relevant data flow sink.
+   */
+  predicate isSink(Node sink);
+
+  /**
+   * Holds if data flow through `node` is prohibited. This completely removes
+   * `node` from the data flow graph.
+   */
+  default predicate isBarrier(Node node) { none() }
+
+  /** Holds if data flow into `node` is prohibited. */
+  default predicate isBarrierIn(Node node) { none() }
+
+  /** Holds if data flow out of `node` is prohibited. */
+  default predicate isBarrierOut(Node node) { none() }
+
+  /**
+   * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps.
+   */
+  default predicate isAdditionalFlowStep(Node node1, Node node2) { none() }
+
+  /**
+   * Holds if an arbitrary number of implicit read steps of content `c` may be
+   * taken at `node`.
+   */
+  default predicate allowImplicitRead(Node node, ContentSet c) { none() }
+
+  /**
+   * Gets the virtual dispatch branching limit when calculating field flow.
+   * This can be overridden to a smaller value to improve performance (a
+   * value of 0 disables field flow), or a larger value to get more results.
+   */
+  default int fieldFlowBranchLimit() { result = 2 }
+
+  /**
+   * Gets a data flow configuration feature to add restrictions to the set of
+   * valid flow paths.
+   *
+   * - `FeatureHasSourceCallContext`:
+   *    Assume that sources have some existing call context to disallow
+   *    conflicting return-flow directly following the source.
+   * - `FeatureHasSinkCallContext`:
+   *    Assume that sinks have some existing call context to disallow
+   *    conflicting argument-to-parameter flow directly preceding the sink.
+   * - `FeatureEqualSourceSinkCallContext`:
+   *    Implies both of the above and additionally ensures that the entire flow
+   *    path preserves the call context.
+   *
+   * These features are generally not relevant for typical end-to-end data flow
+   * queries, but should only be used for constructing paths that need to
+   * somehow be pluggable in another path context.
+   */
+  default FlowFeature getAFeature() { none() }
+
+  /** Holds if sources should be grouped in the result of `hasFlowPath`. */
+  default predicate sourceGrouping(Node source, string sourceGroup) { none() }
+
+  /** Holds if sinks should be grouped in the result of `hasFlowPath`. */
+  default predicate sinkGrouping(Node sink, string sinkGroup) { none() }
+
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (as it is in a `path-problem` query).
+   */
+  default predicate includeHiddenNodes() { none() }
+}
+
+/** An input configuration for data flow using flow state. */
+signature module StateConfigSig {
+  bindingset[this]
+  class FlowState;
+
+  /**
+   * Holds if `source` is a relevant data flow source with the given initial
+   * `state`.
+   */
+  predicate isSource(Node source, FlowState state);
+
+  /**
+   * Holds if `sink` is a relevant data flow sink accepting `state`.
+   */
+  predicate isSink(Node sink, FlowState state);
+
+  /**
+   * Holds if data flow through `node` is prohibited. This completely removes
+   * `node` from the data flow graph.
+   */
+  default predicate isBarrier(Node node) { none() }
+
+  /**
+   * Holds if data flow through `node` is prohibited when the flow state is
+   * `state`.
+   */
+  predicate isBarrier(Node node, FlowState state);
+
+  /** Holds if data flow into `node` is prohibited. */
+  default predicate isBarrierIn(Node node) { none() }
+
+  /** Holds if data flow out of `node` is prohibited. */
+  default predicate isBarrierOut(Node node) { none() }
+
+  /**
+   * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps.
+   */
+  default predicate isAdditionalFlowStep(Node node1, Node node2) { none() }
+
+  /**
+   * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps.
+   * This step is only applicable in `state1` and updates the flow state to `state2`.
+   */
+  predicate isAdditionalFlowStep(Node node1, FlowState state1, Node node2, FlowState state2);
+
+  /**
+   * Holds if an arbitrary number of implicit read steps of content `c` may be
+   * taken at `node`.
+   */
+  default predicate allowImplicitRead(Node node, ContentSet c) { none() }
+
+  /**
+   * Gets the virtual dispatch branching limit when calculating field flow.
+   * This can be overridden to a smaller value to improve performance (a
+   * value of 0 disables field flow), or a larger value to get more results.
+   */
+  default int fieldFlowBranchLimit() { result = 2 }
+
+  /**
+   * Gets a data flow configuration feature to add restrictions to the set of
+   * valid flow paths.
+   *
+   * - `FeatureHasSourceCallContext`:
+   *    Assume that sources have some existing call context to disallow
+   *    conflicting return-flow directly following the source.
+   * - `FeatureHasSinkCallContext`:
+   *    Assume that sinks have some existing call context to disallow
+   *    conflicting argument-to-parameter flow directly preceding the sink.
+   * - `FeatureEqualSourceSinkCallContext`:
+   *    Implies both of the above and additionally ensures that the entire flow
+   *    path preserves the call context.
+   *
+   * These features are generally not relevant for typical end-to-end data flow
+   * queries, but should only be used for constructing paths that need to
+   * somehow be pluggable in another path context.
+   */
+  default FlowFeature getAFeature() { none() }
+
+  /** Holds if sources should be grouped in the result of `hasFlowPath`. */
+  default predicate sourceGrouping(Node source, string sourceGroup) { none() }
+
+  /** Holds if sinks should be grouped in the result of `hasFlowPath`. */
+  default predicate sinkGrouping(Node sink, string sinkGroup) { none() }
+
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (as it is in a `path-problem` query).
+   */
+  default predicate includeHiddenNodes() { none() }
+}
+
+/**
+ * Gets the exploration limit for `hasPartialFlow` and `hasPartialFlowRev`
+ * measured in approximate number of interprocedural steps.
+ */
+signature int explorationLimitSig();
+
+/**
+ * The output of a data flow computation.
+ */
+signature module DataFlowSig {
+  /**
+   * A `Node` augmented with a call context (except for sinks) and an access path.
+   * Only those `PathNode`s that are reachable from a source, and which can reach a sink, are generated.
+   */
+  class PathNode;
+
+  /**
+   * Holds if data can flow from `source` to `sink`.
+   *
+   * The corresponding paths are generated from the end-points and the graph
+   * included in the module `PathGraph`.
+   */
+  predicate hasFlowPath(PathNode source, PathNode sink);
+
+  /**
+   * Holds if data can flow from `source` to `sink`.
+   */
+  predicate hasFlow(Node source, Node sink);
+
+  /**
+   * Holds if data can flow from some source to `sink`.
+   */
+  predicate hasFlowTo(Node sink);
+
+  /**
+   * Holds if data can flow from some source to `sink`.
+   */
+  predicate hasFlowToExpr(DataFlowExpr sink);
+}
+
+/**
+ * Constructs a standard data flow computation.
+ */
+module Make<ConfigSig Config> implements DataFlowSig {
+  private module C implements FullStateConfigSig {
+    import DefaultState<Config>
+    import Config
+  }
+
+  import Impl<C>
+}
+
+/**
+ * Constructs a data flow computation using flow state.
+ */
+module MakeWithState<StateConfigSig Config> implements DataFlowSig {
+  private module C implements FullStateConfigSig {
+    import Config
+  }
+
+  import Impl<C>
+}
+
+signature class PathNodeSig {
+  /** Gets a textual representation of this element. */
+  string toString();
+
+  /**
+   * Holds if this element is at the specified location.
+   * The location spans column `startcolumn` of line `startline` to
+   * column `endcolumn` of line `endline` in file `filepath`.
+   * For more information, see
+   * [Locations](https://codeql.github.com/docs/writing-codeql-queries/providing-locations-in-codeql-queries/).
+   */
+  predicate hasLocationInfo(
+    string filepath, int startline, int startcolumn, int endline, int endcolumn
+  );
+
+  /** Gets the underlying `Node`. */
+  Node getNode();
+}
+
+signature module PathGraphSig<PathNodeSig PathNode> {
+  /** Holds if `(a,b)` is an edge in the graph of data flow path explanations. */
+  predicate edges(PathNode a, PathNode b);
+
+  /** Holds if `n` is a node in the graph of data flow path explanations. */
+  predicate nodes(PathNode n, string key, string val);
+
+  /**
+   * Holds if `(arg, par, ret, out)` forms a subpath-tuple, that is, flow through
+   * a subpath between `par` and `ret` with the connecting edges `arg -> par` and
+   * `ret -> out` is summarized as the edge `arg -> out`.
+   */
+  predicate subpaths(PathNode arg, PathNode par, PathNode ret, PathNode out);
+}
+
+/**
+ * Constructs a `PathGraph` from two `PathGraph`s by disjoint union.
+ */
+module MergePathGraph<
+  PathNodeSig PathNode1, PathNodeSig PathNode2, PathGraphSig<PathNode1> Graph1,
+  PathGraphSig<PathNode2> Graph2>
+{
+  private newtype TPathNode =
+    TPathNode1(PathNode1 p) or
+    TPathNode2(PathNode2 p)
+
+  /** A node in a graph of path explanations that is formed by disjoint union of the two given graphs. */
+  class PathNode extends TPathNode {
+    /** Gets this as a projection on the first given `PathGraph`. */
+    PathNode1 asPathNode1() { this = TPathNode1(result) }
+
+    /** Gets this as a projection on the second given `PathGraph`. */
+    PathNode2 asPathNode2() { this = TPathNode2(result) }
+
+    /** Gets a textual representation of this element. */
+    string toString() {
+      result = this.asPathNode1().toString() or
+      result = this.asPathNode2().toString()
+    }
+
+    /**
+     * Holds if this element is at the specified location.
+     * The location spans column `startcolumn` of line `startline` to
+     * column `endcolumn` of line `endline` in file `filepath`.
+     * For more information, see
+     * [Locations](https://codeql.github.com/docs/writing-codeql-queries/providing-locations-in-codeql-queries/).
+     */
+    predicate hasLocationInfo(
+      string filepath, int startline, int startcolumn, int endline, int endcolumn
+    ) {
+      this.asPathNode1().hasLocationInfo(filepath, startline, startcolumn, endline, endcolumn) or
+      this.asPathNode2().hasLocationInfo(filepath, startline, startcolumn, endline, endcolumn)
+    }
+
+    /** Gets the underlying `Node`. */
+    Node getNode() {
+      result = this.asPathNode1().getNode() or
+      result = this.asPathNode2().getNode()
+    }
+  }
+
+  /**
+   * Provides the query predicates needed to include a graph in a path-problem query.
+   */
+  module PathGraph implements PathGraphSig<PathNode> {
+    /** Holds if `(a,b)` is an edge in the graph of data flow path explanations. */
+    query predicate edges(PathNode a, PathNode b) {
+      Graph1::edges(a.asPathNode1(), b.asPathNode1()) or
+      Graph2::edges(a.asPathNode2(), b.asPathNode2())
+    }
+
+    /** Holds if `n` is a node in the graph of data flow path explanations. */
+    query predicate nodes(PathNode n, string key, string val) {
+      Graph1::nodes(n.asPathNode1(), key, val) or
+      Graph2::nodes(n.asPathNode2(), key, val)
+    }
+
+    /**
+     * Holds if `(arg, par, ret, out)` forms a subpath-tuple, that is, flow through
+     * a subpath between `par` and `ret` with the connecting edges `arg -> par` and
+     * `ret -> out` is summarized as the edge `arg -> out`.
+     */
+    query predicate subpaths(PathNode arg, PathNode par, PathNode ret, PathNode out) {
+      Graph1::subpaths(arg.asPathNode1(), par.asPathNode1(), ret.asPathNode1(), out.asPathNode1()) or
+      Graph2::subpaths(arg.asPathNode2(), par.asPathNode2(), ret.asPathNode2(), out.asPathNode2())
+    }
+  }
+}

cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl1.qll

@@ -0,0 +1,396 @@
+/**
+ * DEPRECATED: Use `Make` and `MakeWithState` instead.
+ *
+ * Provides a `Configuration` class backwards-compatible interface to the data
+ * flow library.
+ */
+
+private import DataFlowImplCommon
+private import DataFlowImplSpecific::Private
+import DataFlowImplSpecific::Public
+private import DataFlowImpl
+import DataFlowImplCommonPublic
+import FlowStateString
+
+/**
+ * A configuration of interprocedural data flow analysis. This defines
+ * sources, sinks, and any other configurable aspect of the analysis. Each
+ * use of the global data flow library must define its own unique extension
+ * of this abstract class. To create a configuration, extend this class with
+ * a subclass whose characteristic predicate is a unique singleton string.
+ * For example, write
+ *
+ * ```ql
+ * class MyAnalysisConfiguration extends DataFlow::Configuration {
+ *   MyAnalysisConfiguration() { this = "MyAnalysisConfiguration" }
+ *   // Override `isSource` and `isSink`.
+ *   // Optionally override `isBarrier`.
+ *   // Optionally override `isAdditionalFlowStep`.
+ * }
+ * ```
+ * Conceptually, this defines a graph where the nodes are `DataFlow::Node`s and
+ * the edges are those data-flow steps that preserve the value of the node
+ * along with any additional edges defined by `isAdditionalFlowStep`.
+ * Specifying nodes in `isBarrier` will remove those nodes from the graph, and
+ * specifying nodes in `isBarrierIn` and/or `isBarrierOut` will remove in-going
+ * and/or out-going edges from those nodes, respectively.
+ *
+ * Then, to query whether there is flow between some `source` and `sink`,
+ * write
+ *
+ * ```ql
+ * exists(MyAnalysisConfiguration cfg | cfg.hasFlow(source, sink))
+ * ```
+ *
+ * Multiple configurations can coexist, but two classes extending
+ * `DataFlow::Configuration` should never depend on each other. One of them
+ * should instead depend on a `DataFlow2::Configuration`, a
+ * `DataFlow3::Configuration`, or a `DataFlow4::Configuration`.
+ */
+abstract class Configuration extends string {
+  bindingset[this]
+  Configuration() { any() }
+
+  /**
+   * Holds if `source` is a relevant data flow source.
+   */
+  predicate isSource(Node source) { none() }
+
+  /**
+   * Holds if `source` is a relevant data flow source with the given initial
+   * `state`.
+   */
+  predicate isSource(Node source, FlowState state) { none() }
+
+  /**
+   * Holds if `sink` is a relevant data flow sink.
+   */
+  predicate isSink(Node sink) { none() }
+
+  /**
+   * Holds if `sink` is a relevant data flow sink accepting `state`.
+   */
+  predicate isSink(Node sink, FlowState state) { none() }
+
+  /**
+   * Holds if data flow through `node` is prohibited. This completely removes
+   * `node` from the data flow graph.
+   */
+  predicate isBarrier(Node node) { none() }
+
+  /**
+   * Holds if data flow through `node` is prohibited when the flow state is
+   * `state`.
+   */
+  predicate isBarrier(Node node, FlowState state) { none() }
+
+  /** Holds if data flow into `node` is prohibited. */
+  predicate isBarrierIn(Node node) { none() }
+
+  /** Holds if data flow out of `node` is prohibited. */
+  predicate isBarrierOut(Node node) { none() }
+
+  /**
+   * DEPRECATED: Use `isBarrier` and `BarrierGuard` module instead.
+   *
+   * Holds if data flow through nodes guarded by `guard` is prohibited.
+   */
+  deprecated predicate isBarrierGuard(BarrierGuard guard) { none() }
+
+  /**
+   * DEPRECATED: Use `isBarrier` and `BarrierGuard` module instead.
+   *
+   * Holds if data flow through nodes guarded by `guard` is prohibited when
+   * the flow state is `state`
+   */
+  deprecated predicate isBarrierGuard(BarrierGuard guard, FlowState state) { none() }
+
+  /**
+   * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps.
+   */
+  predicate isAdditionalFlowStep(Node node1, Node node2) { none() }
+
+  /**
+   * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps.
+   * This step is only applicable in `state1` and updates the flow state to `state2`.
+   */
+  predicate isAdditionalFlowStep(Node node1, FlowState state1, Node node2, FlowState state2) {
+    none()
+  }
+
+  /**
+   * Holds if an arbitrary number of implicit read steps of content `c` may be
+   * taken at `node`.
+   */
+  predicate allowImplicitRead(Node node, ContentSet c) { none() }
+
+  /**
+   * Gets the virtual dispatch branching limit when calculating field flow.
+   * This can be overridden to a smaller value to improve performance (a
+   * value of 0 disables field flow), or a larger value to get more results.
+   */
+  int fieldFlowBranchLimit() { result = 2 }
+
+  /**
+   * Gets a data flow configuration feature to add restrictions to the set of
+   * valid flow paths.
+   *
+   * - `FeatureHasSourceCallContext`:
+   *    Assume that sources have some existing call context to disallow
+   *    conflicting return-flow directly following the source.
+   * - `FeatureHasSinkCallContext`:
+   *    Assume that sinks have some existing call context to disallow
+   *    conflicting argument-to-parameter flow directly preceding the sink.
+   * - `FeatureEqualSourceSinkCallContext`:
+   *    Implies both of the above and additionally ensures that the entire flow
+   *    path preserves the call context.
+   *
+   * These features are generally not relevant for typical end-to-end data flow
+   * queries, but should only be used for constructing paths that need to
+   * somehow be pluggable in another path context.
+   */
+  FlowFeature getAFeature() { none() }
+
+  /** Holds if sources should be grouped in the result of `hasFlowPath`. */
+  predicate sourceGrouping(Node source, string sourceGroup) { none() }
+
+  /** Holds if sinks should be grouped in the result of `hasFlowPath`. */
+  predicate sinkGrouping(Node sink, string sinkGroup) { none() }
+
+  /**
+   * Holds if data may flow from `source` to `sink` for this configuration.
+   */
+  predicate hasFlow(Node source, Node sink) { hasFlow(source, sink, this) }
+
+  /**
+   * Holds if data may flow from `source` to `sink` for this configuration.
+   *
+   * The corresponding paths are generated from the end-points and the graph
+   * included in the module `PathGraph`.
+   */
+  predicate hasFlowPath(PathNode source, PathNode sink) { hasFlowPath(source, sink, this) }
+
+  /**
+   * Holds if data may flow from some source to `sink` for this configuration.
+   */
+  predicate hasFlowTo(Node sink) { hasFlowTo(sink, this) }
+
+  /**
+   * Holds if data may flow from some source to `sink` for this configuration.
+   */
+  predicate hasFlowToExpr(DataFlowExpr sink) { this.hasFlowTo(exprNode(sink)) }
+
+  /**
+   * DEPRECATED: Use `FlowExploration<explorationLimit>` instead.
+   *
+   * Gets the exploration limit for `hasPartialFlow` and `hasPartialFlowRev`
+   * measured in approximate number of interprocedural steps.
+   */
+  deprecated int explorationLimit() { none() }
+
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (for example in a `path-problem` query).
+   */
+  predicate includeHiddenNodes() { none() }
+}
+
+/**
+ * This class exists to prevent mutual recursion between the user-overridden
+ * member predicates of `Configuration` and the rest of the data-flow library.
+ * Good performance cannot be guaranteed in the presence of such recursion, so
+ * it should be replaced by using more than one copy of the data flow library.
+ */
+abstract private class ConfigurationRecursionPrevention extends Configuration {
+  bindingset[this]
+  ConfigurationRecursionPrevention() { any() }
+
+  override predicate hasFlow(Node source, Node sink) {
+    strictcount(Node n | this.isSource(n)) < 0
+    or
+    strictcount(Node n | this.isSource(n, _)) < 0
+    or
+    strictcount(Node n | this.isSink(n)) < 0
+    or
+    strictcount(Node n | this.isSink(n, _)) < 0
+    or
+    strictcount(Node n1, Node n2 | this.isAdditionalFlowStep(n1, n2)) < 0
+    or
+    strictcount(Node n1, Node n2 | this.isAdditionalFlowStep(n1, _, n2, _)) < 0
+    or
+    super.hasFlow(source, sink)
+  }
+}
+
+/** A bridge class to access the deprecated `isBarrierGuard`. */
+private class BarrierGuardGuardedNodeBridge extends Unit {
+  abstract predicate guardedNode(Node n, Configuration config);
+
+  abstract predicate guardedNode(Node n, FlowState state, Configuration config);
+}
+
+private class BarrierGuardGuardedNode extends BarrierGuardGuardedNodeBridge {
+  deprecated override predicate guardedNode(Node n, Configuration config) {
+    exists(BarrierGuard g |
+      config.isBarrierGuard(g) and
+      n = g.getAGuardedNode()
+    )
+  }
+
+  deprecated override predicate guardedNode(Node n, FlowState state, Configuration config) {
+    exists(BarrierGuard g |
+      config.isBarrierGuard(g, state) and
+      n = g.getAGuardedNode()
+    )
+  }
+}
+
+private FlowState relevantState(Configuration config) {
+  config.isSource(_, result) or
+  config.isSink(_, result) or
+  config.isBarrier(_, result) or
+  config.isAdditionalFlowStep(_, result, _, _) or
+  config.isAdditionalFlowStep(_, _, _, result)
+}
+
+private newtype TConfigState =
+  TMkConfigState(Configuration config, FlowState state) {
+    state = relevantState(config) or state instanceof FlowStateEmpty
+  }
+
+private Configuration getConfig(TConfigState state) { state = TMkConfigState(result, _) }
+
+private FlowState getState(TConfigState state) { state = TMkConfigState(_, result) }
+
+private predicate singleConfiguration() { 1 = strictcount(Configuration c) }
+
+private module Config implements FullStateConfigSig {
+  class FlowState = TConfigState;
+
+  predicate isSource(Node source, FlowState state) {
+    getConfig(state).isSource(source, getState(state))
+    or
+    getConfig(state).isSource(source) and getState(state) instanceof FlowStateEmpty
+  }
+
+  predicate isSink(Node sink, FlowState state) {
+    getConfig(state).isSink(sink, getState(state))
+    or
+    getConfig(state).isSink(sink) and getState(state) instanceof FlowStateEmpty
+  }
+
+  predicate isBarrier(Node node) { none() }
+
+  predicate isBarrier(Node node, FlowState state) {
+    getConfig(state).isBarrier(node, getState(state)) or
+    getConfig(state).isBarrier(node) or
+    any(BarrierGuardGuardedNodeBridge b).guardedNode(node, getState(state), getConfig(state)) or
+    any(BarrierGuardGuardedNodeBridge b).guardedNode(node, getConfig(state))
+  }
+
+  predicate isBarrierIn(Node node) { any(Configuration config).isBarrierIn(node) }
+
+  predicate isBarrierOut(Node node) { any(Configuration config).isBarrierOut(node) }
+
+  predicate isAdditionalFlowStep(Node node1, Node node2) {
+    singleConfiguration() and
+    any(Configuration config).isAdditionalFlowStep(node1, node2)
+  }
+
+  predicate isAdditionalFlowStep(Node node1, FlowState state1, Node node2, FlowState state2) {
+    getConfig(state1).isAdditionalFlowStep(node1, getState(state1), node2, getState(state2)) and
+    getConfig(state2) = getConfig(state1)
+    or
+    not singleConfiguration() and
+    getConfig(state1).isAdditionalFlowStep(node1, node2) and
+    state2 = state1
+  }
+
+  predicate allowImplicitRead(Node node, ContentSet c) {
+    any(Configuration config).allowImplicitRead(node, c)
+  }
+
+  int fieldFlowBranchLimit() { result = min(any(Configuration config).fieldFlowBranchLimit()) }
+
+  FlowFeature getAFeature() { result = any(Configuration config).getAFeature() }
+
+  predicate sourceGrouping(Node source, string sourceGroup) {
+    any(Configuration config).sourceGrouping(source, sourceGroup)
+  }
+
+  predicate sinkGrouping(Node sink, string sinkGroup) {
+    any(Configuration config).sinkGrouping(sink, sinkGroup)
+  }
+
+  predicate includeHiddenNodes() { any(Configuration config).includeHiddenNodes() }
+}
+
+private import Impl<Config> as I
+import I
+
+/**
+ * A `Node` augmented with a call context (except for sinks), an access path, and a configuration.
+ * Only those `PathNode`s that are reachable from a source, and which can reach a sink, are generated.
+ */
+class PathNode instanceof I::PathNode {
+  /** Gets a textual representation of this element. */
+  final string toString() { result = super.toString() }
+
+  /**
+   * Gets a textual representation of this element, including a textual
+   * representation of the call context.
+   */
+  final string toStringWithContext() { result = super.toStringWithContext() }
+
+  /**
+   * Holds if this element is at the specified location.
+   * The location spans column `startcolumn` of line `startline` to
+   * column `endcolumn` of line `endline` in file `filepath`.
+   * For more information, see
+   * [Locations](https://codeql.github.com/docs/writing-codeql-queries/providing-locations-in-codeql-queries/).
+   */
+  final predicate hasLocationInfo(
+    string filepath, int startline, int startcolumn, int endline, int endcolumn
+  ) {
+    super.hasLocationInfo(filepath, startline, startcolumn, endline, endcolumn)
+  }
+
+  /** Gets the underlying `Node`. */
+  final Node getNode() { result = super.getNode() }
+
+  /** Gets the `FlowState` of this node. */
+  final FlowState getState() { result = getState(super.getState()) }
+
+  /** Gets the associated configuration. */
+  final Configuration getConfiguration() { result = getConfig(super.getState()) }
+
+  /** Gets a successor of this node, if any. */
+  final PathNode getASuccessor() { result = super.getASuccessor() }
+
+  /** Holds if this node is a source. */
+  final predicate isSource() { super.isSource() }
+
+  /** Holds if this node is a grouping of source nodes. */
+  final predicate isSourceGroup(string group) { super.isSourceGroup(group) }
+
+  /** Holds if this node is a grouping of sink nodes. */
+  final predicate isSinkGroup(string group) { super.isSinkGroup(group) }
+}
+
+private predicate hasFlow(Node source, Node sink, Configuration config) {
+  exists(PathNode source0, PathNode sink0 |
+    hasFlowPath(source0, sink0, config) and
+    source0.getNode() = source and
+    sink0.getNode() = sink
+  )
+}
+
+private predicate hasFlowPath(PathNode source, PathNode sink, Configuration config) {
+  hasFlowPath(source, sink) and source.getConfiguration() = config
+}
+
+private predicate hasFlowTo(Node sink, Configuration config) { hasFlow(_, sink, config) }
+
+predicate flowsTo = hasFlow/3;

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

@@ -3,15 +3,18 @@ private import DataFlowImplSpecific::Public
 import Cached
 
 module DataFlowImplCommonPublic {
-  /** A state value to track during data flow. */
-  class FlowState = string;
+  /** Provides `FlowState = string`. */
+  module FlowStateString {
+    /** A state value to track during data flow. */
+    class FlowState = string;
 
-  /**
-   * The default state, which is used when the state is unspecified for a source
-   * or a sink.
-   */
-  class FlowStateEmpty extends FlowState {
-    FlowStateEmpty() { this = "" }
+    /**
+     * The default state, which is used when the state is unspecified for a source
+     * or a sink.
+     */
+    class FlowStateEmpty extends FlowState {
+      FlowStateEmpty() { this = "" }
+    }
   }
 
   private newtype TFlowFeature =
@@ -179,6 +182,7 @@ private module LambdaFlow {
     boolean toJump, DataFlowCallOption lastCall
   ) {
     revLambdaFlow0(lambdaCall, kind, node, t, toReturn, toJump, lastCall) and
+    not expectsContent(node, _) and
     if castNode(node) or node instanceof ArgNode or node instanceof ReturnNode
     then compatibleTypes(t, getNodeDataFlowType(node))
     else any()

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

@@ -318,3 +318,12 @@ private class MyConsistencyConfiguration extends Consistency::ConsistencyConfigu
     // consistency alerts enough that most of them are interesting.
   }
 }
+
+/**
+ * Gets an additional term that is added to the `join` and `branch` computations to reflect
+ * an additional forward or backwards branching factor that is not taken into account
+ * when calculating the (virtual) dispatch cost.
+ *
+ * Argument `arg` is part of a path from a source to a sink, and `p` is the target parameter.
+ */
+int getAdditionalFlowIntoCallNodeTerm(ArgumentNode arg, ParameterNode p) { none() }

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

@@ -75,13 +75,6 @@ class SubBasicBlock extends ControlFlowNodeBase {
     )
   }
 
-  /**
-   * DEPRECATED: use `getRankInBasicBlock` instead. Note that this predicate
-   * returns a 0-based position, while `getRankInBasicBlock` returns a 1-based
-   * position.
-   */
-  deprecated int getPosInBasicBlock(BasicBlock bb) { result = this.getRankInBasicBlock(bb) - 1 }
-
   pragma[noinline]
   private int getIndexInBasicBlock(BasicBlock bb) { this = bb.getNode(result) }
 

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

@@ -0,0 +1,64 @@
+/**
+ * Provides classes for performing local (intra-procedural) and
+ * global (inter-procedural) taint-tracking analyses.
+ */
+
+import TaintTrackingParameter::Public
+private import TaintTrackingParameter::Private
+
+private module AddTaintDefaults<DataFlowInternal::FullStateConfigSig Config> implements
+  DataFlowInternal::FullStateConfigSig
+{
+  import Config
+
+  predicate isBarrier(DataFlow::Node node) {
+    Config::isBarrier(node) or defaultTaintSanitizer(node)
+  }
+
+  predicate isAdditionalFlowStep(DataFlow::Node node1, DataFlow::Node node2) {
+    Config::isAdditionalFlowStep(node1, node2) or
+    defaultAdditionalTaintStep(node1, node2)
+  }
+
+  predicate allowImplicitRead(DataFlow::Node node, DataFlow::ContentSet c) {
+    Config::allowImplicitRead(node, c)
+    or
+    (
+      Config::isSink(node, _) or
+      Config::isAdditionalFlowStep(node, _) or
+      Config::isAdditionalFlowStep(node, _, _, _)
+    ) and
+    defaultImplicitTaintRead(node, c)
+  }
+}
+
+/**
+ * Constructs a standard taint tracking computation.
+ */
+module Make<DataFlow::ConfigSig Config> implements DataFlow::DataFlowSig {
+  private module Config0 implements DataFlowInternal::FullStateConfigSig {
+    import DataFlowInternal::DefaultState<Config>
+    import Config
+  }
+
+  private module C implements DataFlowInternal::FullStateConfigSig {
+    import AddTaintDefaults<Config0>
+  }
+
+  import DataFlowInternal::Impl<C>
+}
+
+/**
+ * Constructs a taint tracking computation using flow state.
+ */
+module MakeWithState<DataFlow::StateConfigSig Config> implements DataFlow::DataFlowSig {
+  private module Config0 implements DataFlowInternal::FullStateConfigSig {
+    import Config
+  }
+
+  private module C implements DataFlowInternal::FullStateConfigSig {
+    import AddTaintDefaults<Config0>
+  }
+
+  import DataFlowInternal::Impl<C>
+}

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

@@ -2,4 +2,5 @@ import semmle.code.cpp.dataflow.internal.TaintTrackingUtil as Public
 
 module Private {
   import semmle.code.cpp.dataflow.DataFlow::DataFlow as DataFlow
+  import semmle.code.cpp.dataflow.internal.DataFlowImpl as DataFlowInternal
 }

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

@@ -569,7 +569,8 @@ class BuiltInOperationBuiltInAddressOf extends UnaryOperation, BuiltInOperation,
  * ```
  */
 class BuiltInOperationIsTriviallyConstructible extends BuiltInOperation,
-  @istriviallyconstructibleexpr {
+  @istriviallyconstructibleexpr
+{
   override string toString() { result = "__is_trivially_constructible" }
 
   override string getAPrimaryQlClass() { result = "BuiltInOperationIsTriviallyConstructible" }
@@ -619,7 +620,8 @@ class BuiltInOperationIsNothrowDestructible extends BuiltInOperation, @isnothrow
  * bool v = __is_trivially_destructible(MyType);
  * ```
  */
-class BuiltInOperationIsTriviallyDestructible extends BuiltInOperation, @istriviallydestructibleexpr {
+class BuiltInOperationIsTriviallyDestructible extends BuiltInOperation, @istriviallydestructibleexpr
+{
   override string toString() { result = "__is_trivially_destructible" }
 
   override string getAPrimaryQlClass() { result = "BuiltInOperationIsTriviallyDestructible" }
@@ -738,7 +740,8 @@ class BuiltInOperationIsLiteralType extends BuiltInOperation, @isliteraltypeexpr
  * ```
  */
 class BuiltInOperationHasTrivialMoveConstructor extends BuiltInOperation,
-  @hastrivialmoveconstructorexpr {
+  @hastrivialmoveconstructorexpr
+{
   override string toString() { result = "__has_trivial_move_constructor" }
 
   override string getAPrimaryQlClass() { result = "BuiltInOperationHasTrivialMoveConstructor" }
@@ -1034,7 +1037,8 @@ class BuiltInOperationIsAggregate extends BuiltInOperation, @isaggregate {
  * ```
  */
 class BuiltInOperationHasUniqueObjectRepresentations extends BuiltInOperation,
-  @hasuniqueobjectrepresentations {
+  @hasuniqueobjectrepresentations
+{
   override string toString() { result = "__has_unique_object_representations" }
 
   override string getAPrimaryQlClass() { result = "BuiltInOperationHasUniqueObjectRepresentations" }
@@ -1107,7 +1111,8 @@ class BuiltInOperationIsLayoutCompatible extends BuiltInOperation, @islayoutcomp
  * ```
  */
 class BuiltInOperationIsPointerInterconvertibleBaseOf extends BuiltInOperation,
-  @ispointerinterconvertiblebaseof {
+  @ispointerinterconvertiblebaseof
+{
   override string toString() { result = "__is_pointer_interconvertible_base_of" }
 
   override string getAPrimaryQlClass() {

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

@@ -719,13 +719,6 @@ class ReferenceToExpr extends Conversion, @reference_to {
 class PointerDereferenceExpr extends UnaryOperation, @indirect {
   override string getAPrimaryQlClass() { result = "PointerDereferenceExpr" }
 
-  /**
-   * DEPRECATED: Use getOperand() instead.
-   *
-   * Gets the expression that is being dereferenced.
-   */
-  deprecated Expr getExpr() { result = this.getOperand() }
-
   override string getOperator() { result = "*" }
 
   override int getPrecedence() { result = 16 }

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

@@ -22,5 +22,6 @@
 import cpp
 
 module DataFlow {
-  import semmle.code.cpp.ir.dataflow.internal.DataFlowImpl
+  import semmle.code.cpp.ir.dataflow.internal.DataFlow
+  import semmle.code.cpp.ir.dataflow.internal.DataFlowImpl1
 }

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

@@ -19,5 +19,6 @@ import semmle.code.cpp.ir.dataflow.DataFlow
 import semmle.code.cpp.ir.dataflow.DataFlow2
 
 module TaintTracking {
+  import semmle.code.cpp.ir.dataflow.internal.tainttracking1.TaintTracking
   import semmle.code.cpp.ir.dataflow.internal.tainttracking1.TaintTrackingImpl
 }

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

@@ -0,0 +1,353 @@
+/**
+ * Provides an implementation of global (interprocedural) data flow. This file
+ * re-exports the local (intraprocedural) data flow analysis from
+ * `DataFlowImplSpecific::Public` and adds a global analysis, mainly exposed
+ * through the `Make` and `MakeWithState` modules.
+ */
+
+private import DataFlowImplCommon
+private import DataFlowImplSpecific::Private
+import DataFlowImplSpecific::Public
+import DataFlowImplCommonPublic
+private import DataFlowImpl
+
+/** An input configuration for data flow. */
+signature module ConfigSig {
+  /**
+   * Holds if `source` is a relevant data flow source.
+   */
+  predicate isSource(Node source);
+
+  /**
+   * Holds if `sink` is a relevant data flow sink.
+   */
+  predicate isSink(Node sink);
+
+  /**
+   * Holds if data flow through `node` is prohibited. This completely removes
+   * `node` from the data flow graph.
+   */
+  default predicate isBarrier(Node node) { none() }
+
+  /** Holds if data flow into `node` is prohibited. */
+  default predicate isBarrierIn(Node node) { none() }
+
+  /** Holds if data flow out of `node` is prohibited. */
+  default predicate isBarrierOut(Node node) { none() }
+
+  /**
+   * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps.
+   */
+  default predicate isAdditionalFlowStep(Node node1, Node node2) { none() }
+
+  /**
+   * Holds if an arbitrary number of implicit read steps of content `c` may be
+   * taken at `node`.
+   */
+  default predicate allowImplicitRead(Node node, ContentSet c) { none() }
+
+  /**
+   * Gets the virtual dispatch branching limit when calculating field flow.
+   * This can be overridden to a smaller value to improve performance (a
+   * value of 0 disables field flow), or a larger value to get more results.
+   */
+  default int fieldFlowBranchLimit() { result = 2 }
+
+  /**
+   * Gets a data flow configuration feature to add restrictions to the set of
+   * valid flow paths.
+   *
+   * - `FeatureHasSourceCallContext`:
+   *    Assume that sources have some existing call context to disallow
+   *    conflicting return-flow directly following the source.
+   * - `FeatureHasSinkCallContext`:
+   *    Assume that sinks have some existing call context to disallow
+   *    conflicting argument-to-parameter flow directly preceding the sink.
+   * - `FeatureEqualSourceSinkCallContext`:
+   *    Implies both of the above and additionally ensures that the entire flow
+   *    path preserves the call context.
+   *
+   * These features are generally not relevant for typical end-to-end data flow
+   * queries, but should only be used for constructing paths that need to
+   * somehow be pluggable in another path context.
+   */
+  default FlowFeature getAFeature() { none() }
+
+  /** Holds if sources should be grouped in the result of `hasFlowPath`. */
+  default predicate sourceGrouping(Node source, string sourceGroup) { none() }
+
+  /** Holds if sinks should be grouped in the result of `hasFlowPath`. */
+  default predicate sinkGrouping(Node sink, string sinkGroup) { none() }
+
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (as it is in a `path-problem` query).
+   */
+  default predicate includeHiddenNodes() { none() }
+}
+
+/** An input configuration for data flow using flow state. */
+signature module StateConfigSig {
+  bindingset[this]
+  class FlowState;
+
+  /**
+   * Holds if `source` is a relevant data flow source with the given initial
+   * `state`.
+   */
+  predicate isSource(Node source, FlowState state);
+
+  /**
+   * Holds if `sink` is a relevant data flow sink accepting `state`.
+   */
+  predicate isSink(Node sink, FlowState state);
+
+  /**
+   * Holds if data flow through `node` is prohibited. This completely removes
+   * `node` from the data flow graph.
+   */
+  default predicate isBarrier(Node node) { none() }
+
+  /**
+   * Holds if data flow through `node` is prohibited when the flow state is
+   * `state`.
+   */
+  predicate isBarrier(Node node, FlowState state);
+
+  /** Holds if data flow into `node` is prohibited. */
+  default predicate isBarrierIn(Node node) { none() }
+
+  /** Holds if data flow out of `node` is prohibited. */
+  default predicate isBarrierOut(Node node) { none() }
+
+  /**
+   * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps.
+   */
+  default predicate isAdditionalFlowStep(Node node1, Node node2) { none() }
+
+  /**
+   * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps.
+   * This step is only applicable in `state1` and updates the flow state to `state2`.
+   */
+  predicate isAdditionalFlowStep(Node node1, FlowState state1, Node node2, FlowState state2);
+
+  /**
+   * Holds if an arbitrary number of implicit read steps of content `c` may be
+   * taken at `node`.
+   */
+  default predicate allowImplicitRead(Node node, ContentSet c) { none() }
+
+  /**
+   * Gets the virtual dispatch branching limit when calculating field flow.
+   * This can be overridden to a smaller value to improve performance (a
+   * value of 0 disables field flow), or a larger value to get more results.
+   */
+  default int fieldFlowBranchLimit() { result = 2 }
+
+  /**
+   * Gets a data flow configuration feature to add restrictions to the set of
+   * valid flow paths.
+   *
+   * - `FeatureHasSourceCallContext`:
+   *    Assume that sources have some existing call context to disallow
+   *    conflicting return-flow directly following the source.
+   * - `FeatureHasSinkCallContext`:
+   *    Assume that sinks have some existing call context to disallow
+   *    conflicting argument-to-parameter flow directly preceding the sink.
+   * - `FeatureEqualSourceSinkCallContext`:
+   *    Implies both of the above and additionally ensures that the entire flow
+   *    path preserves the call context.
+   *
+   * These features are generally not relevant for typical end-to-end data flow
+   * queries, but should only be used for constructing paths that need to
+   * somehow be pluggable in another path context.
+   */
+  default FlowFeature getAFeature() { none() }
+
+  /** Holds if sources should be grouped in the result of `hasFlowPath`. */
+  default predicate sourceGrouping(Node source, string sourceGroup) { none() }
+
+  /** Holds if sinks should be grouped in the result of `hasFlowPath`. */
+  default predicate sinkGrouping(Node sink, string sinkGroup) { none() }
+
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (as it is in a `path-problem` query).
+   */
+  default predicate includeHiddenNodes() { none() }
+}
+
+/**
+ * Gets the exploration limit for `hasPartialFlow` and `hasPartialFlowRev`
+ * measured in approximate number of interprocedural steps.
+ */
+signature int explorationLimitSig();
+
+/**
+ * The output of a data flow computation.
+ */
+signature module DataFlowSig {
+  /**
+   * A `Node` augmented with a call context (except for sinks) and an access path.
+   * Only those `PathNode`s that are reachable from a source, and which can reach a sink, are generated.
+   */
+  class PathNode;
+
+  /**
+   * Holds if data can flow from `source` to `sink`.
+   *
+   * The corresponding paths are generated from the end-points and the graph
+   * included in the module `PathGraph`.
+   */
+  predicate hasFlowPath(PathNode source, PathNode sink);
+
+  /**
+   * Holds if data can flow from `source` to `sink`.
+   */
+  predicate hasFlow(Node source, Node sink);
+
+  /**
+   * Holds if data can flow from some source to `sink`.
+   */
+  predicate hasFlowTo(Node sink);
+
+  /**
+   * Holds if data can flow from some source to `sink`.
+   */
+  predicate hasFlowToExpr(DataFlowExpr sink);
+}
+
+/**
+ * Constructs a standard data flow computation.
+ */
+module Make<ConfigSig Config> implements DataFlowSig {
+  private module C implements FullStateConfigSig {
+    import DefaultState<Config>
+    import Config
+  }
+
+  import Impl<C>
+}
+
+/**
+ * Constructs a data flow computation using flow state.
+ */
+module MakeWithState<StateConfigSig Config> implements DataFlowSig {
+  private module C implements FullStateConfigSig {
+    import Config
+  }
+
+  import Impl<C>
+}
+
+signature class PathNodeSig {
+  /** Gets a textual representation of this element. */
+  string toString();
+
+  /**
+   * Holds if this element is at the specified location.
+   * The location spans column `startcolumn` of line `startline` to
+   * column `endcolumn` of line `endline` in file `filepath`.
+   * For more information, see
+   * [Locations](https://codeql.github.com/docs/writing-codeql-queries/providing-locations-in-codeql-queries/).
+   */
+  predicate hasLocationInfo(
+    string filepath, int startline, int startcolumn, int endline, int endcolumn
+  );
+
+  /** Gets the underlying `Node`. */
+  Node getNode();
+}
+
+signature module PathGraphSig<PathNodeSig PathNode> {
+  /** Holds if `(a,b)` is an edge in the graph of data flow path explanations. */
+  predicate edges(PathNode a, PathNode b);
+
+  /** Holds if `n` is a node in the graph of data flow path explanations. */
+  predicate nodes(PathNode n, string key, string val);
+
+  /**
+   * Holds if `(arg, par, ret, out)` forms a subpath-tuple, that is, flow through
+   * a subpath between `par` and `ret` with the connecting edges `arg -> par` and
+   * `ret -> out` is summarized as the edge `arg -> out`.
+   */
+  predicate subpaths(PathNode arg, PathNode par, PathNode ret, PathNode out);
+}
+
+/**
+ * Constructs a `PathGraph` from two `PathGraph`s by disjoint union.
+ */
+module MergePathGraph<
+  PathNodeSig PathNode1, PathNodeSig PathNode2, PathGraphSig<PathNode1> Graph1,
+  PathGraphSig<PathNode2> Graph2>
+{
+  private newtype TPathNode =
+    TPathNode1(PathNode1 p) or
+    TPathNode2(PathNode2 p)
+
+  /** A node in a graph of path explanations that is formed by disjoint union of the two given graphs. */
+  class PathNode extends TPathNode {
+    /** Gets this as a projection on the first given `PathGraph`. */
+    PathNode1 asPathNode1() { this = TPathNode1(result) }
+
+    /** Gets this as a projection on the second given `PathGraph`. */
+    PathNode2 asPathNode2() { this = TPathNode2(result) }
+
+    /** Gets a textual representation of this element. */
+    string toString() {
+      result = this.asPathNode1().toString() or
+      result = this.asPathNode2().toString()
+    }
+
+    /**
+     * Holds if this element is at the specified location.
+     * The location spans column `startcolumn` of line `startline` to
+     * column `endcolumn` of line `endline` in file `filepath`.
+     * For more information, see
+     * [Locations](https://codeql.github.com/docs/writing-codeql-queries/providing-locations-in-codeql-queries/).
+     */
+    predicate hasLocationInfo(
+      string filepath, int startline, int startcolumn, int endline, int endcolumn
+    ) {
+      this.asPathNode1().hasLocationInfo(filepath, startline, startcolumn, endline, endcolumn) or
+      this.asPathNode2().hasLocationInfo(filepath, startline, startcolumn, endline, endcolumn)
+    }
+
+    /** Gets the underlying `Node`. */
+    Node getNode() {
+      result = this.asPathNode1().getNode() or
+      result = this.asPathNode2().getNode()
+    }
+  }
+
+  /**
+   * Provides the query predicates needed to include a graph in a path-problem query.
+   */
+  module PathGraph implements PathGraphSig<PathNode> {
+    /** Holds if `(a,b)` is an edge in the graph of data flow path explanations. */
+    query predicate edges(PathNode a, PathNode b) {
+      Graph1::edges(a.asPathNode1(), b.asPathNode1()) or
+      Graph2::edges(a.asPathNode2(), b.asPathNode2())
+    }
+
+    /** Holds if `n` is a node in the graph of data flow path explanations. */
+    query predicate nodes(PathNode n, string key, string val) {
+      Graph1::nodes(n.asPathNode1(), key, val) or
+      Graph2::nodes(n.asPathNode2(), key, val)
+    }
+
+    /**
+     * Holds if `(arg, par, ret, out)` forms a subpath-tuple, that is, flow through
+     * a subpath between `par` and `ret` with the connecting edges `arg -> par` and
+     * `ret -> out` is summarized as the edge `arg -> out`.
+     */
+    query predicate subpaths(PathNode arg, PathNode par, PathNode ret, PathNode out) {
+      Graph1::subpaths(arg.asPathNode1(), par.asPathNode1(), ret.asPathNode1(), out.asPathNode1()) or
+      Graph2::subpaths(arg.asPathNode2(), par.asPathNode2(), ret.asPathNode2(), out.asPathNode2())
+    }
+  }
+}

cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/DataFlowImpl1.qll

@@ -0,0 +1,396 @@
+/**
+ * DEPRECATED: Use `Make` and `MakeWithState` instead.
+ *
+ * Provides a `Configuration` class backwards-compatible interface to the data
+ * flow library.
+ */
+
+private import DataFlowImplCommon
+private import DataFlowImplSpecific::Private
+import DataFlowImplSpecific::Public
+private import DataFlowImpl
+import DataFlowImplCommonPublic
+import FlowStateString
+
+/**
+ * A configuration of interprocedural data flow analysis. This defines
+ * sources, sinks, and any other configurable aspect of the analysis. Each
+ * use of the global data flow library must define its own unique extension
+ * of this abstract class. To create a configuration, extend this class with
+ * a subclass whose characteristic predicate is a unique singleton string.
+ * For example, write
+ *
+ * ```ql
+ * class MyAnalysisConfiguration extends DataFlow::Configuration {
+ *   MyAnalysisConfiguration() { this = "MyAnalysisConfiguration" }
+ *   // Override `isSource` and `isSink`.
+ *   // Optionally override `isBarrier`.
+ *   // Optionally override `isAdditionalFlowStep`.
+ * }
+ * ```
+ * Conceptually, this defines a graph where the nodes are `DataFlow::Node`s and
+ * the edges are those data-flow steps that preserve the value of the node
+ * along with any additional edges defined by `isAdditionalFlowStep`.
+ * Specifying nodes in `isBarrier` will remove those nodes from the graph, and
+ * specifying nodes in `isBarrierIn` and/or `isBarrierOut` will remove in-going
+ * and/or out-going edges from those nodes, respectively.
+ *
+ * Then, to query whether there is flow between some `source` and `sink`,
+ * write
+ *
+ * ```ql
+ * exists(MyAnalysisConfiguration cfg | cfg.hasFlow(source, sink))
+ * ```
+ *
+ * Multiple configurations can coexist, but two classes extending
+ * `DataFlow::Configuration` should never depend on each other. One of them
+ * should instead depend on a `DataFlow2::Configuration`, a
+ * `DataFlow3::Configuration`, or a `DataFlow4::Configuration`.
+ */
+abstract class Configuration extends string {
+  bindingset[this]
+  Configuration() { any() }
+
+  /**
+   * Holds if `source` is a relevant data flow source.
+   */
+  predicate isSource(Node source) { none() }
+
+  /**
+   * Holds if `source` is a relevant data flow source with the given initial
+   * `state`.
+   */
+  predicate isSource(Node source, FlowState state) { none() }
+
+  /**
+   * Holds if `sink` is a relevant data flow sink.
+   */
+  predicate isSink(Node sink) { none() }
+
+  /**
+   * Holds if `sink` is a relevant data flow sink accepting `state`.
+   */
+  predicate isSink(Node sink, FlowState state) { none() }
+
+  /**
+   * Holds if data flow through `node` is prohibited. This completely removes
+   * `node` from the data flow graph.
+   */
+  predicate isBarrier(Node node) { none() }
+
+  /**
+   * Holds if data flow through `node` is prohibited when the flow state is
+   * `state`.
+   */
+  predicate isBarrier(Node node, FlowState state) { none() }
+
+  /** Holds if data flow into `node` is prohibited. */
+  predicate isBarrierIn(Node node) { none() }
+
+  /** Holds if data flow out of `node` is prohibited. */
+  predicate isBarrierOut(Node node) { none() }
+
+  /**
+   * DEPRECATED: Use `isBarrier` and `BarrierGuard` module instead.
+   *
+   * Holds if data flow through nodes guarded by `guard` is prohibited.
+   */
+  deprecated predicate isBarrierGuard(BarrierGuard guard) { none() }
+
+  /**
+   * DEPRECATED: Use `isBarrier` and `BarrierGuard` module instead.
+   *
+   * Holds if data flow through nodes guarded by `guard` is prohibited when
+   * the flow state is `state`
+   */
+  deprecated predicate isBarrierGuard(BarrierGuard guard, FlowState state) { none() }
+
+  /**
+   * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps.
+   */
+  predicate isAdditionalFlowStep(Node node1, Node node2) { none() }
+
+  /**
+   * Holds if data may flow from `node1` to `node2` in addition to the normal data-flow steps.
+   * This step is only applicable in `state1` and updates the flow state to `state2`.
+   */
+  predicate isAdditionalFlowStep(Node node1, FlowState state1, Node node2, FlowState state2) {
+    none()
+  }
+
+  /**
+   * Holds if an arbitrary number of implicit read steps of content `c` may be
+   * taken at `node`.
+   */
+  predicate allowImplicitRead(Node node, ContentSet c) { none() }
+
+  /**
+   * Gets the virtual dispatch branching limit when calculating field flow.
+   * This can be overridden to a smaller value to improve performance (a
+   * value of 0 disables field flow), or a larger value to get more results.
+   */
+  int fieldFlowBranchLimit() { result = 2 }
+
+  /**
+   * Gets a data flow configuration feature to add restrictions to the set of
+   * valid flow paths.
+   *
+   * - `FeatureHasSourceCallContext`:
+   *    Assume that sources have some existing call context to disallow
+   *    conflicting return-flow directly following the source.
+   * - `FeatureHasSinkCallContext`:
+   *    Assume that sinks have some existing call context to disallow
+   *    conflicting argument-to-parameter flow directly preceding the sink.
+   * - `FeatureEqualSourceSinkCallContext`:
+   *    Implies both of the above and additionally ensures that the entire flow
+   *    path preserves the call context.
+   *
+   * These features are generally not relevant for typical end-to-end data flow
+   * queries, but should only be used for constructing paths that need to
+   * somehow be pluggable in another path context.
+   */
+  FlowFeature getAFeature() { none() }
+
+  /** Holds if sources should be grouped in the result of `hasFlowPath`. */
+  predicate sourceGrouping(Node source, string sourceGroup) { none() }
+
+  /** Holds if sinks should be grouped in the result of `hasFlowPath`. */
+  predicate sinkGrouping(Node sink, string sinkGroup) { none() }
+
+  /**
+   * Holds if data may flow from `source` to `sink` for this configuration.
+   */
+  predicate hasFlow(Node source, Node sink) { hasFlow(source, sink, this) }
+
+  /**
+   * Holds if data may flow from `source` to `sink` for this configuration.
+   *
+   * The corresponding paths are generated from the end-points and the graph
+   * included in the module `PathGraph`.
+   */
+  predicate hasFlowPath(PathNode source, PathNode sink) { hasFlowPath(source, sink, this) }
+
+  /**
+   * Holds if data may flow from some source to `sink` for this configuration.
+   */
+  predicate hasFlowTo(Node sink) { hasFlowTo(sink, this) }
+
+  /**
+   * Holds if data may flow from some source to `sink` for this configuration.
+   */
+  predicate hasFlowToExpr(DataFlowExpr sink) { this.hasFlowTo(exprNode(sink)) }
+
+  /**
+   * DEPRECATED: Use `FlowExploration<explorationLimit>` instead.
+   *
+   * Gets the exploration limit for `hasPartialFlow` and `hasPartialFlowRev`
+   * measured in approximate number of interprocedural steps.
+   */
+  deprecated int explorationLimit() { none() }
+
+  /**
+   * Holds if hidden nodes should be included in the data flow graph.
+   *
+   * This feature should only be used for debugging or when the data flow graph
+   * is not visualized (for example in a `path-problem` query).
+   */
+  predicate includeHiddenNodes() { none() }
+}
+
+/**
+ * This class exists to prevent mutual recursion between the user-overridden
+ * member predicates of `Configuration` and the rest of the data-flow library.
+ * Good performance cannot be guaranteed in the presence of such recursion, so
+ * it should be replaced by using more than one copy of the data flow library.
+ */
+abstract private class ConfigurationRecursionPrevention extends Configuration {
+  bindingset[this]
+  ConfigurationRecursionPrevention() { any() }
+
+  override predicate hasFlow(Node source, Node sink) {
+    strictcount(Node n | this.isSource(n)) < 0
+    or
+    strictcount(Node n | this.isSource(n, _)) < 0
+    or
+    strictcount(Node n | this.isSink(n)) < 0
+    or
+    strictcount(Node n | this.isSink(n, _)) < 0
+    or
+    strictcount(Node n1, Node n2 | this.isAdditionalFlowStep(n1, n2)) < 0
+    or
+    strictcount(Node n1, Node n2 | this.isAdditionalFlowStep(n1, _, n2, _)) < 0
+    or
+    super.hasFlow(source, sink)
+  }
+}
+
+/** A bridge class to access the deprecated `isBarrierGuard`. */
+private class BarrierGuardGuardedNodeBridge extends Unit {
+  abstract predicate guardedNode(Node n, Configuration config);
+
+  abstract predicate guardedNode(Node n, FlowState state, Configuration config);
+}
+
+private class BarrierGuardGuardedNode extends BarrierGuardGuardedNodeBridge {
+  deprecated override predicate guardedNode(Node n, Configuration config) {
+    exists(BarrierGuard g |
+      config.isBarrierGuard(g) and
+      n = g.getAGuardedNode()
+    )
+  }
+
+  deprecated override predicate guardedNode(Node n, FlowState state, Configuration config) {
+    exists(BarrierGuard g |
+      config.isBarrierGuard(g, state) and
+      n = g.getAGuardedNode()
+    )
+  }
+}
+
+private FlowState relevantState(Configuration config) {
+  config.isSource(_, result) or
+  config.isSink(_, result) or
+  config.isBarrier(_, result) or
+  config.isAdditionalFlowStep(_, result, _, _) or
+  config.isAdditionalFlowStep(_, _, _, result)
+}
+
+private newtype TConfigState =
+  TMkConfigState(Configuration config, FlowState state) {
+    state = relevantState(config) or state instanceof FlowStateEmpty
+  }
+
+private Configuration getConfig(TConfigState state) { state = TMkConfigState(result, _) }
+
+private FlowState getState(TConfigState state) { state = TMkConfigState(_, result) }
+
+private predicate singleConfiguration() { 1 = strictcount(Configuration c) }
+
+private module Config implements FullStateConfigSig {
+  class FlowState = TConfigState;
+
+  predicate isSource(Node source, FlowState state) {
+    getConfig(state).isSource(source, getState(state))
+    or
+    getConfig(state).isSource(source) and getState(state) instanceof FlowStateEmpty
+  }
+
+  predicate isSink(Node sink, FlowState state) {
+    getConfig(state).isSink(sink, getState(state))
+    or
+    getConfig(state).isSink(sink) and getState(state) instanceof FlowStateEmpty
+  }
+
+  predicate isBarrier(Node node) { none() }
+
+  predicate isBarrier(Node node, FlowState state) {
+    getConfig(state).isBarrier(node, getState(state)) or
+    getConfig(state).isBarrier(node) or
+    any(BarrierGuardGuardedNodeBridge b).guardedNode(node, getState(state), getConfig(state)) or
+    any(BarrierGuardGuardedNodeBridge b).guardedNode(node, getConfig(state))
+  }
+
+  predicate isBarrierIn(Node node) { any(Configuration config).isBarrierIn(node) }
+
+  predicate isBarrierOut(Node node) { any(Configuration config).isBarrierOut(node) }
+
+  predicate isAdditionalFlowStep(Node node1, Node node2) {
+    singleConfiguration() and
+    any(Configuration config).isAdditionalFlowStep(node1, node2)
+  }
+
+  predicate isAdditionalFlowStep(Node node1, FlowState state1, Node node2, FlowState state2) {
+    getConfig(state1).isAdditionalFlowStep(node1, getState(state1), node2, getState(state2)) and
+    getConfig(state2) = getConfig(state1)
+    or
+    not singleConfiguration() and
+    getConfig(state1).isAdditionalFlowStep(node1, node2) and
+    state2 = state1
+  }
+
+  predicate allowImplicitRead(Node node, ContentSet c) {
+    any(Configuration config).allowImplicitRead(node, c)
+  }
+
+  int fieldFlowBranchLimit() { result = min(any(Configuration config).fieldFlowBranchLimit()) }
+
+  FlowFeature getAFeature() { result = any(Configuration config).getAFeature() }
+
+  predicate sourceGrouping(Node source, string sourceGroup) {
+    any(Configuration config).sourceGrouping(source, sourceGroup)
+  }
+
+  predicate sinkGrouping(Node sink, string sinkGroup) {
+    any(Configuration config).sinkGrouping(sink, sinkGroup)
+  }
+
+  predicate includeHiddenNodes() { any(Configuration config).includeHiddenNodes() }
+}
+
+private import Impl<Config> as I
+import I
+
+/**
+ * A `Node` augmented with a call context (except for sinks), an access path, and a configuration.
+ * Only those `PathNode`s that are reachable from a source, and which can reach a sink, are generated.
+ */
+class PathNode instanceof I::PathNode {
+  /** Gets a textual representation of this element. */
+  final string toString() { result = super.toString() }
+
+  /**
+   * Gets a textual representation of this element, including a textual
+   * representation of the call context.
+   */
+  final string toStringWithContext() { result = super.toStringWithContext() }
+
+  /**
+   * Holds if this element is at the specified location.
+   * The location spans column `startcolumn` of line `startline` to
+   * column `endcolumn` of line `endline` in file `filepath`.
+   * For more information, see
+   * [Locations](https://codeql.github.com/docs/writing-codeql-queries/providing-locations-in-codeql-queries/).
+   */
+  final predicate hasLocationInfo(
+    string filepath, int startline, int startcolumn, int endline, int endcolumn
+  ) {
+    super.hasLocationInfo(filepath, startline, startcolumn, endline, endcolumn)
+  }
+
+  /** Gets the underlying `Node`. */
+  final Node getNode() { result = super.getNode() }
+
+  /** Gets the `FlowState` of this node. */
+  final FlowState getState() { result = getState(super.getState()) }
+
+  /** Gets the associated configuration. */
+  final Configuration getConfiguration() { result = getConfig(super.getState()) }
+
+  /** Gets a successor of this node, if any. */
+  final PathNode getASuccessor() { result = super.getASuccessor() }
+
+  /** Holds if this node is a source. */
+  final predicate isSource() { super.isSource() }
+
+  /** Holds if this node is a grouping of source nodes. */
+  final predicate isSourceGroup(string group) { super.isSourceGroup(group) }
+
+  /** Holds if this node is a grouping of sink nodes. */
+  final predicate isSinkGroup(string group) { super.isSinkGroup(group) }
+}
+
+private predicate hasFlow(Node source, Node sink, Configuration config) {
+  exists(PathNode source0, PathNode sink0 |
+    hasFlowPath(source0, sink0, config) and
+    source0.getNode() = source and
+    sink0.getNode() = sink
+  )
+}
+
+private predicate hasFlowPath(PathNode source, PathNode sink, Configuration config) {
+  hasFlowPath(source, sink) and source.getConfiguration() = config
+}
+
+private predicate hasFlowTo(Node sink, Configuration config) { hasFlow(_, sink, config) }
+
+predicate flowsTo = hasFlow/3;

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

@@ -3,15 +3,18 @@ private import DataFlowImplSpecific::Public
 import Cached
 
 module DataFlowImplCommonPublic {
-  /** A state value to track during data flow. */
-  class FlowState = string;
+  /** Provides `FlowState = string`. */
+  module FlowStateString {
+    /** A state value to track during data flow. */
+    class FlowState = string;
 
-  /**
-   * The default state, which is used when the state is unspecified for a source
-   * or a sink.
-   */
-  class FlowStateEmpty extends FlowState {
-    FlowStateEmpty() { this = "" }
+    /**
+     * The default state, which is used when the state is unspecified for a source
+     * or a sink.
+     */
+    class FlowStateEmpty extends FlowState {
+      FlowStateEmpty() { this = "" }
+    }
   }
 
   private newtype TFlowFeature =
@@ -179,6 +182,7 @@ private module LambdaFlow {
     boolean toJump, DataFlowCallOption lastCall
   ) {
     revLambdaFlow0(lambdaCall, kind, node, t, toReturn, toJump, lastCall) and
+    not expectsContent(node, _) and
     if castNode(node) or node instanceof ArgNode or node instanceof ReturnNode
     then compatibleTypes(t, getNodeDataFlowType(node))
     else any()

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

@@ -414,3 +414,12 @@ private class MyConsistencyConfiguration extends Consistency::ConsistencyConfigu
     any()
   }
 }
+
+/**
+ * Gets an additional term that is added to the `join` and `branch` computations to reflect
+ * an additional forward or backwards branching factor that is not taken into account
+ * when calculating the (virtual) dispatch cost.
+ *
+ * Argument `arg` is part of a path from a source to a sink, and `p` is the target parameter.
+ */
+int getAdditionalFlowIntoCallNodeTerm(ArgumentNode arg, ParameterNode p) { none() }

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

@@ -97,23 +97,23 @@ private string getNodeProperty(DataFlow::Node node, string key) {
     |
       kind, ", "
     )
-  or
-  // Is there partial flow from a source to this node?
-  // This property will only be emitted if partial flow is enabled by overriding
-  // `DataFlow::Configuration::explorationLimit()`.
-  key = "pflow" and
-  result =
-    strictconcat(DataFlow::PartialPathNode sourceNode, DataFlow::PartialPathNode destNode, int dist,
-      int order1, int order2 |
-      any(DataFlow::Configuration cfg).hasPartialFlow(sourceNode, destNode, dist) and
-      destNode.getNode() = node and
-      // Only print flow from a source in the same function.
-      sourceNode.getNode().getEnclosingCallable() = node.getEnclosingCallable()
-    |
-      nodeId(sourceNode.getNode(), order1, order2) + "+" + dist.toString(), ", "
-      order by
-        order1, order2, dist desc
-    )
+  // or
+  // // Is there partial flow from a source to this node?
+  // // This property will only be emitted if partial flow is enabled by overriding
+  // // `DataFlow::Configuration::explorationLimit()`.
+  // key = "pflow" and
+  // result =
+  //   strictconcat(DataFlow::PartialPathNode sourceNode, DataFlow::PartialPathNode destNode, int dist,
+  //     int order1, int order2 |
+  //     any(DataFlow::Configuration cfg).hasPartialFlow(sourceNode, destNode, dist) and
+  //     destNode.getNode() = node and
+  //     // Only print flow from a source in the same function.
+  //     sourceNode.getNode().getEnclosingCallable() = node.getEnclosingCallable()
+  //   |
+  //     nodeId(sourceNode.getNode(), order1, order2) + "+" + dist.toString(), ", "
+  //     order by
+  //       order1, order2, dist desc
+  //   )
 }
 
 /**

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

@@ -0,0 +1,64 @@
+/**
+ * Provides classes for performing local (intra-procedural) and
+ * global (inter-procedural) taint-tracking analyses.
+ */
+
+import TaintTrackingParameter::Public
+private import TaintTrackingParameter::Private
+
+private module AddTaintDefaults<DataFlowInternal::FullStateConfigSig Config> implements
+  DataFlowInternal::FullStateConfigSig
+{
+  import Config
+
+  predicate isBarrier(DataFlow::Node node) {
+    Config::isBarrier(node) or defaultTaintSanitizer(node)
+  }
+
+  predicate isAdditionalFlowStep(DataFlow::Node node1, DataFlow::Node node2) {
+    Config::isAdditionalFlowStep(node1, node2) or
+    defaultAdditionalTaintStep(node1, node2)
+  }
+
+  predicate allowImplicitRead(DataFlow::Node node, DataFlow::ContentSet c) {
+    Config::allowImplicitRead(node, c)
+    or
+    (
+      Config::isSink(node, _) or
+      Config::isAdditionalFlowStep(node, _) or
+      Config::isAdditionalFlowStep(node, _, _, _)
+    ) and
+    defaultImplicitTaintRead(node, c)
+  }
+}
+
+/**
+ * Constructs a standard taint tracking computation.
+ */
+module Make<DataFlow::ConfigSig Config> implements DataFlow::DataFlowSig {
+  private module Config0 implements DataFlowInternal::FullStateConfigSig {
+    import DataFlowInternal::DefaultState<Config>
+    import Config
+  }
+
+  private module C implements DataFlowInternal::FullStateConfigSig {
+    import AddTaintDefaults<Config0>
+  }
+
+  import DataFlowInternal::Impl<C>
+}
+
+/**
+ * Constructs a taint tracking computation using flow state.
+ */
+module MakeWithState<DataFlow::StateConfigSig Config> implements DataFlow::DataFlowSig {
+  private module Config0 implements DataFlowInternal::FullStateConfigSig {
+    import Config
+  }
+
+  private module C implements DataFlowInternal::FullStateConfigSig {
+    import AddTaintDefaults<Config0>
+  }
+
+  import DataFlowInternal::Impl<C>
+}

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

@@ -2,4 +2,5 @@ import semmle.code.cpp.ir.dataflow.internal.TaintTrackingUtil as Public
 
 module Private {
   import semmle.code.cpp.ir.dataflow.DataFlow::DataFlow as DataFlow
+  import semmle.code.cpp.ir.dataflow.internal.DataFlowImpl as DataFlowInternal
 }

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

@@ -1082,7 +1082,8 @@ module Opcode {
    * See the `CallSideEffectInstruction` documentation for more details.
    */
   class CallSideEffect extends WriteSideEffectOpcode, EscapedWriteOpcode, MayWriteOpcode,
-    ReadSideEffectOpcode, EscapedReadOpcode, MayReadOpcode, TCallSideEffect {
+    ReadSideEffectOpcode, EscapedReadOpcode, MayReadOpcode, TCallSideEffect
+  {
     final override string toString() { result = "CallSideEffect" }
   }
 
@@ -1092,7 +1093,8 @@ module Opcode {
    * See the `CallReadSideEffectInstruction` documentation for more details.
    */
   class CallReadSideEffect extends ReadSideEffectOpcode, EscapedReadOpcode, MayReadOpcode,
-    TCallReadSideEffect {
+    TCallReadSideEffect
+  {
     final override string toString() { result = "CallReadSideEffect" }
   }
 
@@ -1102,7 +1104,8 @@ module Opcode {
    * See the `IndirectReadSideEffectInstruction` documentation for more details.
    */
   class IndirectReadSideEffect extends ReadSideEffectOpcode, IndirectReadOpcode,
-    TIndirectReadSideEffect {
+    TIndirectReadSideEffect
+  {
     final override string toString() { result = "IndirectReadSideEffect" }
   }
 
@@ -1112,7 +1115,8 @@ module Opcode {
    * See the `IndirectMustWriteSideEffectInstruction` documentation for more details.
    */
   class IndirectMustWriteSideEffect extends WriteSideEffectOpcode, IndirectWriteOpcode,
-    TIndirectMustWriteSideEffect {
+    TIndirectMustWriteSideEffect
+  {
     final override string toString() { result = "IndirectMustWriteSideEffect" }
   }
 
@@ -1122,7 +1126,8 @@ module Opcode {
    * See the `IndirectMayWriteSideEffectInstruction` documentation for more details.
    */
   class IndirectMayWriteSideEffect extends WriteSideEffectOpcode, IndirectWriteOpcode,
-    MayWriteOpcode, TIndirectMayWriteSideEffect {
+    MayWriteOpcode, TIndirectMayWriteSideEffect
+  {
     final override string toString() { result = "IndirectMayWriteSideEffect" }
   }
 
@@ -1132,7 +1137,8 @@ module Opcode {
    * See the `BufferReadSideEffectInstruction` documentation for more details.
    */
   class BufferReadSideEffect extends ReadSideEffectOpcode, UnsizedBufferReadOpcode,
-    TBufferReadSideEffect {
+    TBufferReadSideEffect
+  {
     final override string toString() { result = "BufferReadSideEffect" }
   }
 
@@ -1142,7 +1148,8 @@ module Opcode {
    * See the `BufferMustWriteSideEffectInstruction` documentation for more details.
    */
   class BufferMustWriteSideEffect extends WriteSideEffectOpcode, UnsizedBufferWriteOpcode,
-    TBufferMustWriteSideEffect {
+    TBufferMustWriteSideEffect
+  {
     final override string toString() { result = "BufferMustWriteSideEffect" }
   }
 
@@ -1152,7 +1159,8 @@ module Opcode {
    * See the `BufferMayWriteSideEffectInstruction` documentation for more details.
    */
   class BufferMayWriteSideEffect extends WriteSideEffectOpcode, UnsizedBufferWriteOpcode,
-    MayWriteOpcode, TBufferMayWriteSideEffect {
+    MayWriteOpcode, TBufferMayWriteSideEffect
+  {
     final override string toString() { result = "BufferMayWriteSideEffect" }
   }
 
@@ -1162,7 +1170,8 @@ module Opcode {
    * See the `SizedBufferReadSideEffectInstruction` documentation for more details.
    */
   class SizedBufferReadSideEffect extends ReadSideEffectOpcode, SizedBufferReadOpcode,
-    TSizedBufferReadSideEffect {
+    TSizedBufferReadSideEffect
+  {
     final override string toString() { result = "SizedBufferReadSideEffect" }
   }
 
@@ -1172,7 +1181,8 @@ module Opcode {
    * See the `SizedBufferMustWriteSideEffectInstruction` documentation for more details.
    */
   class SizedBufferMustWriteSideEffect extends WriteSideEffectOpcode, SizedBufferWriteOpcode,
-    TSizedBufferMustWriteSideEffect {
+    TSizedBufferMustWriteSideEffect
+  {
     final override string toString() { result = "SizedBufferMustWriteSideEffect" }
   }
 
@@ -1182,7 +1192,8 @@ module Opcode {
    * See the `SizedBufferMayWriteSideEffectInstruction` documentation for more details.
    */
   class SizedBufferMayWriteSideEffect extends WriteSideEffectOpcode, SizedBufferWriteOpcode,
-    MayWriteOpcode, TSizedBufferMayWriteSideEffect {
+    MayWriteOpcode, TSizedBufferMayWriteSideEffect
+  {
     final override string toString() { result = "SizedBufferMayWriteSideEffect" }
   }
 
@@ -1192,7 +1203,8 @@ module Opcode {
    * See the `InitializeDynamicAllocationInstruction` documentation for more details.
    */
   class InitializeDynamicAllocation extends SideEffectOpcode, EntireAllocationWriteOpcode,
-    TInitializeDynamicAllocation {
+    TInitializeDynamicAllocation
+  {
     final override string toString() { result = "InitializeDynamicAllocation" }
   }
 
@@ -1221,7 +1233,8 @@ module Opcode {
    * See the `InlineAsmInstruction` documentation for more details.
    */
   class InlineAsm extends Opcode, EscapedWriteOpcode, MayWriteOpcode, EscapedReadOpcode,
-    MayReadOpcode, TInlineAsm {
+    MayReadOpcode, TInlineAsm
+  {
     final override string toString() { result = "InlineAsm" }
 
     final override predicate hasOperandInternal(OperandTag tag) {

cpp/ql/lib/semmle/code/cpp/ir/implementation/aliased_ssa/Operand.qll

@@ -87,22 +87,6 @@ class Operand extends TStageOperand {
     this.getDefinitionOverlap() instanceof MustExactlyOverlap
   }
 
-  /**
-   * DEPRECATED: renamed to `getUse`.
-   *
-   * Gets the `Instruction` that consumes this operand.
-   */
-  deprecated final Instruction getUseInstruction() { result = this.getUse() }
-
-  /**
-   * DEPRECATED: use `getAnyDef` or `getDef`. The exact replacement for this
-   * predicate is `getAnyDef`, but most uses of this predicate should probably
-   * be replaced with `getDef`.
-   *
-   * Gets the `Instruction` whose result is the value of the operand.
-   */
-  deprecated final Instruction getDefinitionInstruction() { result = this.getAnyDef() }
-
   /**
    * Gets the overlap relationship between the operand's definition and its use.
    */

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

@@ -246,7 +246,8 @@ class VariableMemoryLocation extends TVariableMemoryLocation, AllocationMemoryLo
 }
 
 class EntireAllocationMemoryLocation extends TEntireAllocationMemoryLocation,
-  AllocationMemoryLocation {
+  AllocationMemoryLocation
+{
   EntireAllocationMemoryLocation() { this = TEntireAllocationMemoryLocation(var, isMayAccess) }
 
   final override string toStringInternal() { result = var.toString() }

cpp/ql/lib/semmle/code/cpp/ir/implementation/raw/Operand.qll

@@ -87,22 +87,6 @@ class Operand extends TStageOperand {
     this.getDefinitionOverlap() instanceof MustExactlyOverlap
   }
 
-  /**
-   * DEPRECATED: renamed to `getUse`.
-   *
-   * Gets the `Instruction` that consumes this operand.
-   */
-  deprecated final Instruction getUseInstruction() { result = this.getUse() }
-
-  /**
-   * DEPRECATED: use `getAnyDef` or `getDef`. The exact replacement for this
-   * predicate is `getAnyDef`, but most uses of this predicate should probably
-   * be replaced with `getDef`.
-   *
-   * Gets the `Instruction` whose result is the value of the operand.
-   */
-  deprecated final Instruction getDefinitionInstruction() { result = this.getAnyDef() }
-
   /**
    * Gets the overlap relationship between the operand's definition and its use.
    */

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

@@ -511,7 +511,8 @@ abstract class TranslatedArgumentSideEffect extends TranslatedSideEffect {
  * calls other than constructor calls.
  */
 class TranslatedArgumentExprSideEffect extends TranslatedArgumentSideEffect,
-  TTranslatedArgumentExprSideEffect {
+  TTranslatedArgumentExprSideEffect
+{
   Expr arg;
 
   TranslatedArgumentExprSideEffect() {
@@ -546,7 +547,8 @@ class TranslatedArgumentExprSideEffect extends TranslatedArgumentSideEffect,
  * calls to non-static member functions.
  */
 class TranslatedStructorQualifierSideEffect extends TranslatedArgumentSideEffect,
-  TTranslatedStructorQualifierSideEffect {
+  TTranslatedStructorQualifierSideEffect
+{
   TranslatedStructorQualifierSideEffect() {
     this = TTranslatedStructorQualifierSideEffect(call, sideEffectOpcode) and
     index = -1

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

@@ -34,7 +34,8 @@ abstract class TranslatedCondition extends TranslatedElement {
 }
 
 abstract class TranslatedFlexibleCondition extends TranslatedCondition, ConditionContext,
-  TTranslatedFlexibleCondition {
+  TTranslatedFlexibleCondition
+{
   TranslatedFlexibleCondition() { this = TTranslatedFlexibleCondition(expr) }
 
   final override TranslatedElement getChild(int id) { id = 0 and result = getOperand() }

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

@@ -75,7 +75,8 @@ abstract class TranslatedLocalVariableDeclaration extends TranslatedVariableInit
  * The IR translation of a local variable declaration within a declaration statement.
  */
 class TranslatedAutoVariableDeclarationEntry extends TranslatedLocalVariableDeclaration,
-  TranslatedDeclarationEntry {
+  TranslatedDeclarationEntry
+{
   StackVariable var;
 
   TranslatedAutoVariableDeclarationEntry() { var = entry.getDeclaration() }
@@ -217,7 +218,8 @@ class TranslatedStaticLocalVariableDeclarationEntry extends TranslatedDeclaratio
  * with a dynamic initializer.
  */
 class TranslatedStaticLocalVariableInitialization extends TranslatedElement,
-  TranslatedLocalVariableDeclaration, TTranslatedStaticLocalVariableInitialization {
+  TranslatedLocalVariableDeclaration, TTranslatedStaticLocalVariableInitialization
+{
   IRVariableDeclarationEntry entry;
   StaticLocalVariable var;
 

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

@@ -131,7 +131,8 @@ abstract class TranslatedCoreExpr extends TranslatedExpr {
 }
 
 class TranslatedConditionValue extends TranslatedCoreExpr, ConditionContext,
-  TTranslatedConditionValue {
+  TTranslatedConditionValue
+{
   TranslatedConditionValue() { this = TTranslatedConditionValue(expr) }
 
   override TranslatedElement getChild(int id) { id = 0 and result = this.getCondition() }
@@ -326,7 +327,8 @@ class TranslatedLoad extends TranslatedValueCategoryAdjustment, TTranslatedLoad
  * from the AST.
  */
 class TranslatedSyntheticTemporaryObject extends TranslatedValueCategoryAdjustment,
-  TTranslatedSyntheticTemporaryObject {
+  TTranslatedSyntheticTemporaryObject
+{
   TranslatedSyntheticTemporaryObject() { this = TTranslatedSyntheticTemporaryObject(expr) }
 
   override string toString() { result = "Temporary materialization of " + expr.toString() }
@@ -2302,7 +2304,8 @@ class TranslatedBinaryConditionalExpr extends TranslatedConditionalExpr {
  * its initializer.
  */
 class TranslatedTemporaryObjectExpr extends TranslatedNonConstantExpr,
-  TranslatedVariableInitialization {
+  TranslatedVariableInitialization
+{
   override TemporaryObjectExpr expr;
 
   final override predicate hasTempVariable(TempVariableTag tag, CppType type) {

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

@@ -566,7 +566,8 @@ private TranslatedConstructorInitList getTranslatedConstructorInitList(Function
  * instances for constructors can actually contain initializers.
  */
 class TranslatedConstructorInitList extends TranslatedElement, InitializationContext,
-  TTranslatedConstructorInitList {
+  TTranslatedConstructorInitList
+{
   Function func;
 
   TranslatedConstructorInitList() { this = TTranslatedConstructorInitList(func) }
@@ -637,7 +638,8 @@ private TranslatedDestructorDestructionList getTranslatedDestructorDestructionLi
  * destructions.
  */
 class TranslatedDestructorDestructionList extends TranslatedElement,
-  TTranslatedDestructorDestructionList {
+  TTranslatedDestructorDestructionList
+{
   Function func;
 
   TranslatedDestructorDestructionList() { this = TTranslatedDestructorDestructionList(func) }

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

@@ -9,7 +9,8 @@ private import InstructionTag
 private import semmle.code.cpp.ir.internal.IRUtilities
 
 class TranslatedGlobalOrNamespaceVarInit extends TranslatedRootElement,
-  TTranslatedGlobalOrNamespaceVarInit, InitializationContext {
+  TTranslatedGlobalOrNamespaceVarInit, InitializationContext
+{
   GlobalOrNamespaceVariable var;
 
   TranslatedGlobalOrNamespaceVarInit() { this = TTranslatedGlobalOrNamespaceVarInit(var) }

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

@@ -440,7 +440,8 @@ class TranslatedStringLiteralInitialization extends TranslatedDirectInitializati
 }
 
 class TranslatedConstructorInitialization extends TranslatedDirectInitialization,
-  StructorCallContext {
+  StructorCallContext
+{
   override ConstructorCall expr;
 
   override predicate hasInstruction(Opcode opcode, InstructionTag tag, CppType resultType) {
@@ -528,7 +529,8 @@ abstract class TranslatedFieldInitialization extends TranslatedElement {
  * explicit element in an initializer list.
  */
 class TranslatedExplicitFieldInitialization extends TranslatedFieldInitialization,
-  InitializationContext, TTranslatedExplicitFieldInitialization {
+  InitializationContext, TTranslatedExplicitFieldInitialization
+{
   Expr expr;
 
   TranslatedExplicitFieldInitialization() {
@@ -565,7 +567,8 @@ private string getZeroValue(Type type) {
  * corresponding element in the initializer list.
  */
 class TranslatedFieldValueInitialization extends TranslatedFieldInitialization,
-  TTranslatedFieldValueInitialization {
+  TTranslatedFieldValueInitialization
+{
   TranslatedFieldValueInitialization() { this = TTranslatedFieldValueInitialization(ast, field) }
 
   override predicate hasInstruction(Opcode opcode, InstructionTag tag, CppType resultType) {
@@ -700,7 +703,8 @@ abstract class TranslatedElementInitialization extends TranslatedElement {
  * an explicit element in an initializer list.
  */
 class TranslatedExplicitElementInitialization extends TranslatedElementInitialization,
-  TTranslatedExplicitElementInitialization, InitializationContext {
+  TTranslatedExplicitElementInitialization, InitializationContext
+{
   int elementIndex;
 
   TranslatedExplicitElementInitialization() {
@@ -737,7 +741,8 @@ class TranslatedExplicitElementInitialization extends TranslatedElementInitializ
  * elements without corresponding elements in the initializer list.
  */
 class TranslatedElementValueInitialization extends TranslatedElementInitialization,
-  TTranslatedElementValueInitialization {
+  TTranslatedElementValueInitialization
+{
   int elementIndex;
   int elementCount;
 
@@ -881,7 +886,8 @@ abstract class TranslatedBaseStructorCall extends TranslatedStructorCallFromStru
  * Represents a call to a delegating or base class constructor from within a constructor.
  */
 abstract class TranslatedConstructorCallFromConstructor extends TranslatedStructorCallFromStructor,
-  TTranslatedConstructorBaseInit {
+  TTranslatedConstructorBaseInit
+{
   TranslatedConstructorCallFromConstructor() { this = TTranslatedConstructorBaseInit(call) }
 }
 
@@ -917,7 +923,8 @@ class TranslatedConstructorDelegationInit extends TranslatedConstructorCallFromC
  * derived class constructor
  */
 class TranslatedConstructorBaseInit extends TranslatedConstructorCallFromConstructor,
-  TranslatedBaseStructorCall {
+  TranslatedBaseStructorCall
+{
   TranslatedConstructorBaseInit() { not call instanceof ConstructorDelegationInit }
 
   final override string toString() { result = "construct base: " + call.toString() }
@@ -934,7 +941,8 @@ TranslatedDestructorBaseDestruction getTranslatedDestructorBaseDestruction(
  * derived class destructor.
  */
 class TranslatedDestructorBaseDestruction extends TranslatedBaseStructorCall,
-  TTranslatedDestructorBaseDestruction {
+  TTranslatedDestructorBaseDestruction
+{
   TranslatedDestructorBaseDestruction() { this = TTranslatedDestructorBaseDestruction(call) }
 
   final override string toString() { result = "destroy base: " + call.toString() }

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

@@ -20,7 +20,8 @@ TranslatedMicrosoftTryExceptHandler getTranslatedMicrosoftTryExceptHandler(
 }
 
 class TranslatedMicrosoftTryExceptHandler extends TranslatedElement,
-  TTranslatedMicrosoftTryExceptHandler {
+  TTranslatedMicrosoftTryExceptHandler
+{
   MicrosoftTryExceptStmt tryExcept;
 
   TranslatedMicrosoftTryExceptHandler() { this = TTranslatedMicrosoftTryExceptHandler(tryExcept) }

cpp/ql/lib/semmle/code/cpp/ir/implementation/unaliased_ssa/Operand.qll

@@ -87,22 +87,6 @@ class Operand extends TStageOperand {
     this.getDefinitionOverlap() instanceof MustExactlyOverlap
   }
 
-  /**
-   * DEPRECATED: renamed to `getUse`.
-   *
-   * Gets the `Instruction` that consumes this operand.
-   */
-  deprecated final Instruction getUseInstruction() { result = this.getUse() }
-
-  /**
-   * DEPRECATED: use `getAnyDef` or `getDef`. The exact replacement for this
-   * predicate is `getAnyDef`, but most uses of this predicate should probably
-   * be replaced with `getDef`.
-   *
-   * Gets the `Instruction` whose result is the value of the operand.
-   */
-  deprecated final Instruction getDefinitionInstruction() { result = this.getAnyDef() }
-
   /**
    * Gets the overlap relationship between the operand's definition and its use.
    */

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

@@ -389,7 +389,8 @@ private class NewArrayAllocationExpr extends AllocationExpr, NewArrayExpr {
 
 private module HeuristicAllocation {
   /** A class that maps an `AllocationExpr` to an `HeuristicAllocationExpr`. */
-  private class HeuristicAllocationModeled extends HeuristicAllocationExpr instanceof AllocationExpr {
+  private class HeuristicAllocationModeled extends HeuristicAllocationExpr instanceof AllocationExpr
+  {
     override Expr getSizeExpr() { result = AllocationExpr.super.getSizeExpr() }
 
     override int getSizeMult() { result = AllocationExpr.super.getSizeMult() }
@@ -406,7 +407,8 @@ private module HeuristicAllocation {
   }
 
   /** A class that maps an `AllocationFunction` to an `HeuristicAllocationFunction`. */
-  private class HeuristicAllocationFunctionModeled extends HeuristicAllocationFunction instanceof AllocationFunction {
+  private class HeuristicAllocationFunctionModeled extends HeuristicAllocationFunction instanceof AllocationFunction
+  {
     override int getSizeArg() { result = AllocationFunction.super.getSizeArg() }
 
     override int getSizeMult() { result = AllocationFunction.super.getSizeMult() }
@@ -430,7 +432,8 @@ private module HeuristicAllocation {
    * 2. The function must return a pointer type
    * 3. There must be a unique parameter of unsigned integral type.
    */
-  private class HeuristicAllocationFunctionByName extends HeuristicAllocationFunction instanceof Function {
+  private class HeuristicAllocationFunctionByName extends HeuristicAllocationFunction instanceof Function
+  {
     int sizeArg;
 
     HeuristicAllocationFunctionByName() {

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

@@ -7,7 +7,8 @@ import semmle.code.cpp.models.interfaces.FlowSource
  * The standard functions `getdelim`, `getwdelim` and the glibc variant `__getdelim`.
  */
 private class GetDelimFunction extends TaintFunction, AliasFunction, SideEffectFunction,
-  RemoteFlowSourceFunction {
+  RemoteFlowSourceFunction
+{
   GetDelimFunction() { this.hasGlobalName(["getdelim", "getwdelim", "__getdelim"]) }
 
   override predicate hasTaintFlow(FunctionInput i, FunctionOutput o) {

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

@@ -14,7 +14,8 @@ import semmle.code.cpp.models.interfaces.FlowSource
  * The standard functions `fgets` and `fgetws`.
  */
 private class FgetsFunction extends DataFlowFunction, TaintFunction, ArrayFunction, AliasFunction,
-  SideEffectFunction, RemoteFlowSourceFunction {
+  SideEffectFunction, RemoteFlowSourceFunction
+{
   FgetsFunction() {
     // fgets(str, num, stream)
     // fgetws(wstr, num, stream)
@@ -69,7 +70,8 @@ private class FgetsFunction extends DataFlowFunction, TaintFunction, ArrayFuncti
  * The standard functions `gets`.
  */
 private class GetsFunction extends DataFlowFunction, ArrayFunction, AliasFunction,
-  SideEffectFunction, LocalFlowSourceFunction {
+  SideEffectFunction, LocalFlowSourceFunction
+{
   GetsFunction() {
     // gets(str)
     this.hasGlobalOrStdOrBslName("gets")

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

@@ -7,7 +7,8 @@ import semmle.code.cpp.models.interfaces.SideEffect
  * The standard function templates `std::move` and `std::forward`.
  */
 private class IdentityFunction extends DataFlowFunction, SideEffectFunction, AliasFunction,
-  FunctionTemplateInstantiation {
+  FunctionTemplateInstantiation
+{
   IdentityFunction() { this.hasQualifiedName("std", ["move", "forward"]) }
 
   override predicate hasOnlySpecificReadSideEffects() { any() }

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

@@ -121,7 +121,8 @@ class IteratorCrementNonMemberOperator extends Operator {
 }
 
 private class IteratorCrementNonMemberOperatorModel extends IteratorCrementNonMemberOperator,
-  DataFlowFunction {
+  DataFlowFunction
+{
   override predicate hasDataFlow(FunctionInput input, FunctionOutput output) {
     input = getIteratorArgumentInput(this, 0) and
     output.isReturnValue()
@@ -143,7 +144,8 @@ class IteratorCrementMemberOperator extends MemberFunction {
 }
 
 private class IteratorCrementMemberOperatorModel extends IteratorCrementMemberOperator,
-  DataFlowFunction, TaintFunction {
+  DataFlowFunction, TaintFunction
+{
   override predicate hasDataFlow(FunctionInput input, FunctionOutput output) {
     input.isQualifierAddress() and
     output.isReturnValue()
@@ -204,7 +206,8 @@ class IteratorBinaryArithmeticMemberOperator extends MemberFunction {
 }
 
 private class IteratorBinaryArithmeticMemberOperatorModel extends IteratorBinaryArithmeticMemberOperator,
-  TaintFunction {
+  TaintFunction
+{
   override predicate hasTaintFlow(FunctionInput input, FunctionOutput output) {
     input.isQualifierObject() and
     output.isReturnValue()
@@ -258,7 +261,8 @@ class IteratorAssignArithmeticNonMemberOperator extends Operator {
 }
 
 private class IteratorAssignArithmeticNonMemberOperatorModel extends IteratorAssignArithmeticNonMemberOperator,
-  DataFlowFunction, TaintFunction {
+  DataFlowFunction, TaintFunction
+{
   override predicate hasDataFlow(FunctionInput input, FunctionOutput output) {
     input.isParameter(0) and
     output.isReturnValue()
@@ -289,7 +293,8 @@ class IteratorAssignArithmeticMemberOperator extends MemberFunction {
 }
 
 private class IteratorAssignArithmeticMemberOperatorModel extends IteratorAssignArithmeticMemberOperator,
-  DataFlowFunction, TaintFunction {
+  DataFlowFunction, TaintFunction
+{
   override predicate hasDataFlow(FunctionInput input, FunctionOutput output) {
     input.isQualifierAddress() and
     output.isReturnValue()
@@ -325,7 +330,8 @@ class IteratorAssignArithmeticOperator extends Function {
  * non-member and member versions, use `IteratorPointerDereferenceOperator`.
  */
 class IteratorPointerDereferenceMemberOperator extends MemberFunction, TaintFunction,
-  IteratorReferenceFunction {
+  IteratorReferenceFunction
+{
   IteratorPointerDereferenceMemberOperator() {
     this.getClassAndName("operator*") instanceof Iterator
   }
@@ -353,7 +359,8 @@ class IteratorPointerDereferenceNonMemberOperator extends Operator, IteratorRefe
 }
 
 private class IteratorPointerDereferenceNonMemberOperatorModel extends IteratorPointerDereferenceNonMemberOperator,
-  TaintFunction {
+  TaintFunction
+{
   override predicate hasTaintFlow(FunctionInput input, FunctionOutput output) {
     input = getIteratorArgumentInput(this, 0) and
     output.isReturnValue()
@@ -389,7 +396,8 @@ private class IteratorFieldMemberOperator extends Operator, TaintFunction {
  * An `operator[]` member function of an iterator class.
  */
 private class IteratorArrayMemberOperator extends MemberFunction, TaintFunction,
-  IteratorReferenceFunction {
+  IteratorReferenceFunction
+{
   IteratorArrayMemberOperator() { this.getClassAndName("operator[]") instanceof Iterator }
 
   override predicate hasTaintFlow(FunctionInput input, FunctionOutput output) {
@@ -418,7 +426,8 @@ class IteratorAssignmentMemberOperator extends MemberFunction {
  * `operator*` and use their own `operator=` to assign to the container.
  */
 private class IteratorAssignmentMemberOperatorModel extends IteratorAssignmentMemberOperator,
-  TaintFunction {
+  TaintFunction
+{
   override predicate hasTaintFlow(FunctionInput input, FunctionOutput output) {
     input.isParameterDeref(0) and
     output.isQualifierObject()

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

@@ -15,7 +15,8 @@ import semmle.code.cpp.models.interfaces.Taint
  * `__builtin___memcpy_chk`.
  */
 private class MemcpyFunction extends ArrayFunction, DataFlowFunction, SideEffectFunction,
-  AliasFunction {
+  AliasFunction
+{
   MemcpyFunction() {
     // memcpy(dest, src, num)
     // memmove(dest, src, num)

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

@@ -13,7 +13,8 @@ import semmle.code.cpp.models.interfaces.SideEffect
  * The standard function `memset` and its assorted variants
  */
 private class MemsetFunction extends ArrayFunction, DataFlowFunction, AliasFunction,
-  SideEffectFunction {
+  SideEffectFunction
+{
   MemsetFunction() {
     this.hasGlobalOrStdOrBslName("memset")
     or

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

@@ -8,7 +8,8 @@ import semmle.code.cpp.models.interfaces.SideEffect
  * guaranteed to be side-effect free.
  */
 private class PureStrFunction extends AliasFunction, ArrayFunction, TaintFunction,
-  SideEffectFunction {
+  SideEffectFunction
+{
   PureStrFunction() {
     this.hasGlobalOrStdOrBslName([
         atoi(), "strcasestr", "strchnul", "strchr", "strchrnul", "strstr", "strpbrk", "strrchr",
@@ -153,7 +154,8 @@ private class PureFunction extends TaintFunction, SideEffectFunction {
  * evaluation is guaranteed to be side-effect free.
  */
 private class PureMemFunction extends AliasFunction, ArrayFunction, TaintFunction,
-  SideEffectFunction {
+  SideEffectFunction
+{
   PureMemFunction() {
     this.hasGlobalOrStdOrBslName([
         "memchr", "__builtin_memchr", "memrchr", "rawmemchr", "memcmp", "__builtin_memcmp", "memmem"

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

@@ -11,7 +11,8 @@ import semmle.code.cpp.models.interfaces.SideEffect
 
 /** The function `recv` and its assorted variants */
 private class Recv extends AliasFunction, ArrayFunction, SideEffectFunction,
-  RemoteFlowSourceFunction {
+  RemoteFlowSourceFunction
+{
   Recv() {
     this.hasGlobalName([
         "recv", // recv(socket, dest, len, flags)

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

@@ -15,7 +15,8 @@ import semmle.code.cpp.models.interfaces.FlowSource
  * The `scanf` family of functions.
  */
 abstract private class ScanfFunctionModel extends ArrayFunction, TaintFunction, AliasFunction,
-  SideEffectFunction {
+  SideEffectFunction
+{
   override predicate hasArrayWithNullTerminator(int bufParam) {
     bufParam = this.(ScanfFunction).getFormatParameterIndex()
   }

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

@@ -29,7 +29,8 @@ private class SmartPtr extends Class, PointerWrapper {
  * - `std::weak_ptr<T>::operator*()`
  */
 private class PointerUnwrapperFunction extends MemberFunction, TaintFunction, DataFlowFunction,
-  SideEffectFunction, AliasFunction {
+  SideEffectFunction, AliasFunction
+{
   PointerUnwrapperFunction() {
     exists(PointerWrapper wrapper | wrapper.getAnUnwrapperFunction() = this)
   }

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

@@ -13,7 +13,8 @@ import semmle.code.cpp.models.interfaces.SideEffect
  * The standard function `strset` and its assorted variants
  */
 private class StrsetFunction extends ArrayFunction, DataFlowFunction, AliasFunction,
-  SideEffectFunction {
+  SideEffectFunction
+{
   StrsetFunction() {
     hasGlobalName([
         "strset", "_strset", "_strset_l", "_wcsset", "_wcsset_l", "_mbsset", "_mbsset_l",

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

@@ -7,7 +7,8 @@ import semmle.code.cpp.models.interfaces.CommandExecution
  * A function for running a command using a command interpreter.
  */
 private class SystemFunction extends CommandExecutionFunction, ArrayFunction, AliasFunction,
-  SideEffectFunction {
+  SideEffectFunction
+{
   SystemFunction() {
     hasGlobalOrStdName("system") or // system(command)
     hasGlobalName("popen") or // popen(command, mode)

cpp/ql/lib/semmle/code/cpp/models/interfaces/FunctionInputsAndOutputs.qll

@@ -40,12 +40,6 @@ class FunctionInput extends TFunctionInput {
    */
   predicate isParameter(ParameterIndex index) { none() }
 
-  /**
-   * Holds if this is the input value of the parameter with index `index`.
-   * DEPRECATED: Use `isParameter(index)` instead.
-   */
-  deprecated final predicate isInParameter(ParameterIndex index) { this.isParameter(index) }
-
   /**
    * Holds if this is the input value pointed to (through `ind` number of indirections) by a
    * pointer parameter to a function, or the input value referred to by a reference parameter
@@ -84,16 +78,6 @@ class FunctionInput extends TFunctionInput {
    */
   predicate isParameterDeref(ParameterIndex index) { this.isParameterDeref(index, 1) }
 
-  /**
-   * Holds if this is the input value pointed to by a pointer parameter to a function, or the input
-   * value referred to by a reference parameter to a function, where the parameter has index
-   * `index`.
-   * DEPRECATED: Use `isParameterDeref(index)` instead.
-   */
-  deprecated final predicate isInParameterPointer(ParameterIndex index) {
-    this.isParameterDeref(index)
-  }
-
   /**
    * Holds if this is the input value pointed to by the `this` pointer of an instance member
    * function.
@@ -124,13 +108,6 @@ class FunctionInput extends TFunctionInput {
    */
   predicate isQualifierObject() { this.isQualifierObject(1) }
 
-  /**
-   * Holds if this is the input value pointed to by the `this` pointer of an instance member
-   * function.
-   * DEPRECATED: Use `isQualifierObject()` instead.
-   */
-  deprecated final predicate isInQualifier() { this.isQualifierObject() }
-
   /**
    * Holds if this is the input value of the `this` pointer of an instance member function.
    *
@@ -396,16 +373,6 @@ class FunctionOutput extends TFunctionOutput {
    */
   predicate isParameterDeref(ParameterIndex i, int ind) { ind = 1 and this.isParameterDeref(i) }
 
-  /**
-   * Holds if this is the output value pointed to by a pointer parameter to a function, or the
-   * output value referred to by a reference parameter to a function, where the parameter has
-   * index `index`.
-   * DEPRECATED: Use `isParameterDeref(index)` instead.
-   */
-  deprecated final predicate isOutParameterPointer(ParameterIndex index) {
-    this.isParameterDeref(index)
-  }
-
   /**
    * Holds if this is the output value pointed to by the `this` pointer of an instance member
    *   function.
@@ -436,13 +403,6 @@ class FunctionOutput extends TFunctionOutput {
    */
   predicate isQualifierObject(int ind) { ind = 1 and this.isQualifierObject() }
 
-  /**
-   * Holds if this is the output value pointed to by the `this` pointer of an instance member
-   * function.
-   * DEPRECATED: Use `isQualifierObject()` instead.
-   */
-  deprecated final predicate isOutQualifier() { this.isQualifierObject() }
-
   /**
    * Holds if this is the value returned by a function.
    *
@@ -462,12 +422,6 @@ class FunctionOutput extends TFunctionOutput {
    */
   predicate isReturnValue() { none() }
 
-  /**
-   * Holds if this is the value returned by a function.
-   * DEPRECATED: Use `isReturnValue()` instead.
-   */
-  deprecated final predicate isOutReturnValue() { this.isReturnValue() }
-
   /**
    * Holds if this is the output value pointed to by the return value of a function, if the function
    * returns a pointer, or the output value referred to by the return value of a function, if the
@@ -508,14 +462,6 @@ class FunctionOutput extends TFunctionOutput {
    */
   predicate isReturnValueDeref(int ind) { ind = 1 and this.isReturnValueDeref() }
 
-  /**
-   * Holds if this is the output value pointed to by the return value of a function, if the function
-   * returns a pointer, or the output value referred to by the return value of a function, if the
-   * function returns a reference.
-   * DEPRECATED: Use `isReturnValueDeref()` instead.
-   */
-  deprecated final predicate isOutReturnPointer() { this.isReturnValueDeref() }
-
   /**
    * Holds if `i >= 0` and `isParameterDeref(i, ind)` holds for this is the value, or
    * if `i = -1` and `isQualifierObject(ind)` holds for this value.