Merge pull request #7948 from github/release-prep/2.8.1

Release preparation for version 2.8.1

.codeqlmanifest.json

@@ -4,14 +4,18 @@
         "*/ql/lib/qlpack.yml",
         "*/ql/test/qlpack.yml",
         "*/ql/examples/qlpack.yml",
-        "*/upgrades/qlpack.yml",
+        "*/ql/consistency-queries/qlpack.yml",
         "cpp/ql/test/query-tests/Security/CWE/CWE-190/semmle/tainted/qlpack.yml",
         "javascript/ql/experimental/adaptivethreatmodeling/lib/qlpack.yml",
+        "javascript/ql/experimental/adaptivethreatmodeling/modelbuilding/qlpack.yml",
         "javascript/ql/experimental/adaptivethreatmodeling/src/qlpack.yml",
+        "csharp/ql/campaigns/Solorigate/lib/qlpack.yml",
+        "csharp/ql/campaigns/Solorigate/src/qlpack.yml",
+        "csharp/ql/campaigns/Solorigate/test/qlpack.yml",
         "misc/legacy-support/*/qlpack.yml",
         "misc/suite-helpers/qlpack.yml",
         "ruby/extractor-pack/codeql-extractor.yml",
-        "ruby/ql/consistency-queries/qlpack.yml"
+        "ql/extractor-pack/codeql-extractor.yml"
     ],
     "versionPolicies": {
       "default": {

.gitattributes

@@ -50,4 +50,9 @@
 *.pdb -text
 
 java/ql/test/stubs/**/*.java linguist-generated=true
-java/ql/test/experimental/stubs/**/*.java linguist-generated=true
+java/ql/test/experimental/stubs/**/*.java linguist-generated=true
+
+# Generated test files - these are synced from the standard JavaScript libraries using
+# `javascript/ql/experimental/adaptivethreatmodeling/test/update_endpoint_test_files.py`.
+javascript/ql/experimental/adaptivethreatmodeling/test/endpoint_large_scale/autogenerated/**/*.js linguist-generated=true -merge
+javascript/ql/experimental/adaptivethreatmodeling/test/endpoint_large_scale/autogenerated/**/*.ts linguist-generated=true -merge

.github/labeler.yml

@@ -26,3 +26,6 @@ documentation:
   - "**/*.qhelp"
   - "**/*.md"
   - docs/**/*
+
+"QL-for-QL": 
+  - ql/**/*

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

@@ -7,6 +7,7 @@ on:
       - "*/ql/src/**/*.ql"
       - "*/ql/src/**/*.qll"
       - "!**/experimental/**"
+      - "!ql/**"
 
 jobs:
   check-change-note:

.github/workflows/codeql-analysis.yml

@@ -27,6 +27,11 @@ jobs:
       pull-requests: read
 
     steps:
+    - name: Setup dotnet
+      uses: actions/setup-dotnet@v1
+      with:
+        dotnet-version: 6.0.101
+
     - name: Checkout repository
       uses: actions/checkout@v2
 
@@ -51,7 +56,7 @@ jobs:
     #    uses a compiled language
 
     - run: |
-       dotnet build csharp
+       dotnet build csharp /p:UseSharedCompilation=false
 
     - name: Perform CodeQL Analysis
       uses: github/codeql-action/analyze@main

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

@@ -0,0 +1,43 @@
+name: "Publish framework coverage as metrics"
+
+on:
+  schedule:
+    - cron: '5 0 * * *'
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+  pull_request:
+    branches:
+      - main
+    paths:
+      - ".github/workflows/csv-coverage-metrics.yml"
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v2
+      - name: Setup CodeQL
+        uses: ./.github/actions/fetch-codeql
+      - name: Create empty database
+        run: |
+          DATABASE="${{ runner.temp }}/java-database"
+          PROJECT="${{ runner.temp }}/java-project"
+          mkdir -p "$PROJECT/src/tmp/empty"
+          echo "class Empty {}" >> "$PROJECT/src/tmp/empty/Empty.java"
+          codeql database create "$DATABASE" --language=java --source-root="$PROJECT" --command 'javac src/tmp/empty/Empty.java'
+      - name: Capture coverage information
+        run: |
+          DATABASE="${{ runner.temp }}/java-database"
+          codeql database analyze --format=sarif-latest --output=metrics.sarif -- "$DATABASE" ./java/ql/src/Metrics/Summaries/FrameworkCoverage.ql
+      - uses: actions/upload-artifact@v2
+        with:
+          name: metrics.sarif
+          path: metrics.sarif
+          retention-days: 20
+      - name: Upload SARIF file
+        uses: github/codeql-action/upload-sarif@v1
+        with:
+          sarif_file: metrics.sarif

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

@@ -0,0 +1,67 @@
+name: JS ML-powered queries tests
+
+on:
+  push:
+    paths:
+      - "javascript/ql/experimental/adaptivethreatmodeling/**"
+      - .github/workflows/js-ml-tests.yml
+    branches:
+      - main
+      - "rc/*"
+  pull_request:
+    paths:
+      - "javascript/ql/experimental/adaptivethreatmodeling/**"
+      - .github/workflows/js-ml-tests.yml
+
+defaults:
+  run:
+    working-directory: javascript/ql/experimental/adaptivethreatmodeling
+
+jobs:
+  qlformat:
+    name: Check QL formatting
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+
+      - uses: ./.github/actions/fetch-codeql
+
+      - name: Check QL formatting
+        run: |
+          find . "(" -name "*.ql" -or -name "*.qll" ")" -print0 | \
+            xargs -0 codeql query format --check-only
+
+  qlcompile:
+    name: Check QL compilation
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+
+      - uses: ./.github/actions/fetch-codeql
+
+      - name: Check QL compilation
+        run: |
+          codeql query compile \
+            --check-only \
+            --ram 5120 \
+            --additional-packs "${{ github.workspace }}" \
+            --threads=0 \
+            -- \
+            lib modelbuilding src
+
+  qltest:
+    name: Run QL tests
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+
+      - uses: ./.github/actions/fetch-codeql
+
+      - name: Run QL tests
+        run: |
+          codeql test run \
+            --threads=0 \
+            --ram 5120 \
+            --additional-packs "${{ github.workspace }}" \
+            -- \
+            test

.github/workflows/mad_modelDiff.yml

@@ -0,0 +1,103 @@
+name: Models as Data - Diff
+
+on:
+  workflow_dispatch:
+    inputs:
+      projects:
+        description: "The projects to generate models for"
+        required: true
+        default: '["netty/netty"]'
+  pull_request:
+    branches:
+      - main
+    paths:
+      - "java/ql/src/utils/model-generator/**/*.*"
+      - ".github/workflows/mad_modelDiff.yml"
+
+permissions:
+  contents: read
+
+jobs:
+  model-diff:
+    name: Model Difference
+    runs-on: ubuntu-latest
+    if: github.repository == 'github/codeql'
+    strategy:
+      matrix:
+        slug: ${{fromJson(github.event.inputs.projects || '["apache/commons-codec", "apache/commons-io", "apache/commons-beanutils", "apache/commons-logging", "apache/commons-fileupload", "apache/commons-lang", "apache/commons-validator", "apache/commons-csv", "apache/dubbo"]' )}}
+    steps:
+      - name: Clone github/codeql from PR
+        uses: actions/checkout@v2
+        if: github.event.pull_request
+        with:
+          path: codeql-pr
+      - name: Clone github/codeql from main
+        uses: actions/checkout@v2
+        with:
+          path: codeql-main
+          ref: main
+      - uses: ./codeql-main/.github/actions/fetch-codeql
+      - name: Download database
+        env:
+          SLUG: ${{ matrix.slug }}
+        run: |
+          set -x
+          mkdir lib-dbs
+          SHORTNAME=${SLUG//[^a-zA-Z0-9_]/}
+          projectId=`curl -s https://lgtm.com/api/v1.0/projects/g/${SLUG} | jq .id`
+          curl -L "https://lgtm.com/api/v1.0/snapshots/$projectId/java" -o "$SHORTNAME.zip"
+          unzip -q -d "${SHORTNAME}-db" "${SHORTNAME}.zip"
+          mkdir "lib-dbs/$SHORTNAME/"
+          mv "${SHORTNAME}-db/"$(ls -1 "${SHORTNAME}"-db)/* "lib-dbs/${SHORTNAME}/"
+      - name: Generate Models (PR and main)
+        run: |
+          set -x
+          mkdir tmp-models
+          MODELS=`pwd`/tmp-models
+          DATABASES=`pwd`/lib-dbs
+
+          analyzeDatabaseWithCheckout() {
+            QL_VARIANT=$1
+            DATABASE=$2
+            cd codeql-$QL_VARIANT
+            SHORTNAME=`basename $DATABASE`
+            python java/ql/src/utils/model-generator/GenerateFlowModel.py $DATABASE $MODELS/${SHORTNAME}.qll
+            mv $MODELS/${SHORTNAME}.qll $MODELS/${SHORTNAME}Generated_${QL_VARIANT}.qll
+            cd ..
+          }
+
+          for d in $DATABASES/*/ ; do
+            ls -1 "$d"
+
+            analyzeDatabaseWithCheckout "main" $d
+            if [[ "$GITHUB_EVENT_NAME" == "pull_request" ]]
+            then
+              analyzeDatabaseWithCheckout "pr" $d
+            fi
+          done
+      - name: Install diff2html
+        if: github.event.pull_request
+        run: |
+          npm install -g diff2html-cli
+      - name: Generate Model Diff
+        if: github.event.pull_request
+        run: |
+          set -x
+          MODELS=`pwd`/tmp-models
+          ls -1 tmp-models/
+          for m in $MODELS/*_main.qll ; do
+            t="${m/main/"pr"}"
+            basename=`basename $m`
+            name="diff_${basename/_main.qll/""}"
+            (diff -w -u $m $t | diff2html -i stdin -F $MODELS/$name.html) || true
+          done
+      - uses: actions/upload-artifact@v2
+        with:
+          name: models
+          path: tmp-models/*.qll
+          retention-days: 20
+      - uses: actions/upload-artifact@v2
+        with:
+          name: diffs
+          path: tmp-models/*.html
+          retention-days: 20

.github/workflows/mad_regenerate-models.yml

@@ -0,0 +1,62 @@
+name: Regenerate framework models
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: "30 2 * * *"
+  pull_request:
+    branches:
+      - main
+    paths:
+      - ".github/workflows/mad_regenerate-models.yml"
+
+jobs:
+  regenerate-models:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        # placeholder required for each axis, excluded below, replaced by the actual combinations (see include)
+        slug: ["placeholder"]
+        ref: ["placeholder"]
+        include:
+          - slug: "apache/commons-io"
+            ref: "8985de8fe74f6622a419b37a6eed0dbc484dc128"
+        exclude:
+          - slug: "placeholder"
+            ref: "placeholder"
+    steps:
+      - name: Clone self (github/codeql)
+        uses: actions/checkout@v2
+      - name: Setup CodeQL binaries
+        uses: ./.github/actions/fetch-codeql
+      - name: Clone repositories
+        uses: actions/checkout@v2
+        with:
+          path: repos/${{ matrix.ref }}
+          ref: ${{ matrix.ref }}
+          repository: ${{ matrix.slug }}
+      - name: Build database
+        env:
+          SLUG: ${{ matrix.slug }}
+          REF: ${{ matrix.ref }}
+        run: |
+          mkdir dbs
+          cd repos/${REF}
+          SHORTNAME=${SLUG//[^a-zA-Z0-9_]/}
+          codeql database create --language=java ../../dbs/${SHORTNAME}
+      - name: Regenerate models in-place
+        env:
+          SLUG: ${{ matrix.slug }}
+        run: |
+          SHORTNAME=${SLUG//[^a-zA-Z0-9_]/}
+          java/ql/src/utils/model-generator/RegenerateModels.py "${SLUG}" dbs/${SHORTNAME}
+      - name: Stage changes
+        run: |
+          find java -name "*.qll" -print0 | xargs -0 git add
+          git status
+          git diff --cached > models.patch
+      - uses: actions/upload-artifact@v2
+        with:
+          name: patch
+          path: models.patch
+          retention-days: 7

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

@@ -0,0 +1,199 @@
+name: Run QL for QL
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  queries:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: Find codeql
+        id: find-codeql
+        uses: github/codeql-action/init@erik-krogh/ql
+        with:
+          languages: javascript # does not matter
+      - name: Get CodeQL version
+        id: get-codeql-version
+        run: |
+          echo "::set-output name=version::$("${CODEQL}" --version | head -n 1 | rev | cut -d " " -f 1 | rev)"
+        shell: bash
+        env:
+          CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
+      - name: Cache queries
+        id: cache-queries
+        uses: actions/cache@v2
+        with:
+          path: ${{ runner.temp }}/query-pack.zip
+          key: queries-${{ hashFiles('ql/**/*.ql*') }}-${{ hashFiles('ql/ql/src/ql.dbscheme*') }}-${{ steps.get-codeql-version.outputs.version }}
+      - name: Build query pack
+        if: steps.cache-queries.outputs.cache-hit != 'true'
+        run: |
+          cd ql/ql/src
+          "${CODEQL}" pack create
+          cd .codeql/pack/codeql/ql-all/0.0.0
+          zip "${PACKZIP}" -r .
+        env:
+          CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
+          PACKZIP: ${{ runner.temp }}/query-pack.zip
+      - name: Upload query pack
+        uses: actions/upload-artifact@v2
+        with:
+          name: query-pack-zip
+          path: ${{ runner.temp }}/query-pack.zip
+
+  extractors:
+    strategy:
+      fail-fast: false
+
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Cache entire extractor
+        id: cache-extractor
+        uses: actions/cache@v2
+        with:
+          path: |
+            ql/target/release/ql-autobuilder
+            ql/target/release/ql-autobuilder.exe
+            ql/target/release/ql-extractor
+            ql/target/release/ql-extractor.exe
+          key: ${{ runner.os }}-extractor-${{ hashFiles('ql/**/Cargo.lock') }}-${{ hashFiles('ql/**/*.rs') }}
+      - name: Cache cargo
+        if: steps.cache-extractor.outputs.cache-hit != 'true'
+        uses: actions/cache@v2
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            ql/target
+          key: ${{ runner.os }}-rust-cargo-${{ hashFiles('ql/**/Cargo.lock') }}
+      - name: Check formatting
+        if: steps.cache-extractor.outputs.cache-hit != 'true'
+        run: cd ql; cargo fmt --all -- --check
+      - name: Build
+        if: steps.cache-extractor.outputs.cache-hit != 'true'
+        run: cd ql; cargo build --verbose
+      - name: Run tests
+        if: steps.cache-extractor.outputs.cache-hit != 'true'
+        run: cd ql; cargo test --verbose
+      - name: Release build
+        if: steps.cache-extractor.outputs.cache-hit != 'true'
+        run: cd ql; cargo build --release
+      - name: Generate dbscheme
+        if: steps.cache-extractor.outputs.cache-hit != 'true'
+        run: ql/target/release/ql-generator --dbscheme ql/ql/src/ql.dbscheme --library ql/ql/src/codeql_ql/ast/internal/TreeSitter.qll
+      - uses: actions/upload-artifact@v2
+        with:
+          name: extractor-ubuntu-latest
+          path: |
+            ql/target/release/ql-autobuilder
+            ql/target/release/ql-autobuilder.exe
+            ql/target/release/ql-extractor
+            ql/target/release/ql-extractor.exe
+          retention-days: 1
+  package:
+    runs-on: ubuntu-latest
+
+    needs:
+      - extractors
+      - queries
+
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions/download-artifact@v2
+        with:
+          name: query-pack-zip
+          path: query-pack-zip
+      - uses: actions/download-artifact@v2
+        with:
+          name: extractor-ubuntu-latest
+          path: linux64
+      - run: |
+          unzip query-pack-zip/*.zip -d pack
+          cp -r ql/codeql-extractor.yml ql/tools ql/ql/src/ql.dbscheme.stats pack/
+          mkdir -p pack/tools/linux64
+          if [[ -f linux64/ql-autobuilder ]]; then
+            cp linux64/ql-autobuilder pack/tools/linux64/autobuilder
+            chmod +x pack/tools/linux64/autobuilder
+          fi
+          if [[ -f linux64/ql-extractor ]]; then
+            cp linux64/ql-extractor pack/tools/linux64/extractor
+            chmod +x pack/tools/linux64/extractor
+          fi
+          cd pack
+          zip -rq ../codeql-ql.zip .
+      - uses: actions/upload-artifact@v2
+        with:
+          name: codeql-ql-pack
+          path: codeql-ql.zip
+          retention-days: 1
+  analyze:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        folder: [cpp, csharp, java, javascript, python, ql, ruby]
+
+    needs:
+      - package
+
+    steps:
+      - name: Download pack
+        uses: actions/download-artifact@v2
+        with:
+          name: codeql-ql-pack
+          path: ${{ runner.temp }}/codeql-ql-pack-artifact
+
+      - name: Prepare pack
+        run: |
+          unzip "${PACK_ARTIFACT}/*.zip" -d "${PACK}"
+        env:
+          PACK_ARTIFACT: ${{ runner.temp }}/codeql-ql-pack-artifact
+          PACK: ${{ runner.temp }}/pack
+      - name: Hack codeql-action options
+        run: |
+          JSON=$(jq -nc --arg pack "${PACK}" '.resolve.queries=["--search-path", $pack] | .resolve.extractor=["--search-path", $pack] | .database.init=["--search-path", $pack]')
+          echo "CODEQL_ACTION_EXTRA_OPTIONS=${JSON}" >> ${GITHUB_ENV}
+        env:
+          PACK: ${{ runner.temp }}/pack
+
+      - name: Checkout repository
+        uses: actions/checkout@v2
+      - name: Create CodeQL config file
+        run: |
+          echo "paths:" > ${CONF}
+          echo "  - ${FOLDER}" >> ${CONF}
+          echo "paths-ignore:" >> ${CONF}
+          echo "  - ql/ql/test" >> ${CONF}
+          echo "Config file: "
+          cat ${CONF}
+        env: 
+          CONF: ./ql-for-ql-config.yml
+          FOLDER: ${{ matrix.folder }}
+
+      - name: Initialize CodeQL
+        uses: github/codeql-action/init@erik-krogh/ql
+        with:
+          languages: ql
+          db-location: ${{ runner.temp }}/db
+          config-file: ./ql-for-ql-config.yml
+
+      - name: Perform CodeQL Analysis
+        uses: github/codeql-action/analyze@erik-krogh/ql
+        with: 
+          category: "ql-for-ql-${{ matrix.folder }}"
+      - name: Copy sarif file to CWD
+        run: cp ../results/ql.sarif ./${{ matrix.folder }}.sarif
+      - name: Sarif as artifact
+        uses: actions/upload-artifact@v2
+        with:
+          name: ${{ matrix.folder }}.sarif
+          path: ${{ matrix.folder }}.sarif
+

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

@@ -0,0 +1,84 @@
+name: Collect database stats for QL for QL
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - ql/ql/src/ql.dbscheme
+  pull_request:
+    branches: [main]
+    paths:
+      - ql/ql/src/ql.dbscheme
+  workflow_dispatch:
+
+jobs:
+  measure:
+    env:
+      CODEQL_THREADS: 4 # TODO: remove this once it's set by the CLI
+    strategy:
+      matrix:
+        repo:
+          - github/codeql
+          - github/codeql-go
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+
+      - name: Find codeql
+        id: find-codeql
+        uses: github/codeql-action/init@erik-krogh/ql
+        with:
+          languages: javascript # does not matter
+      - uses: actions/cache@v2
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            ql/target
+          key: ${{ runner.os }}-qltest-cargo-${{ hashFiles('ql/**/Cargo.lock') }}
+      - name: Build Extractor
+        run: cd ql; env "PATH=$PATH:`dirname ${CODEQL}`" ./create-extractor-pack.sh
+        env:
+          CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
+      - name: Checkout ${{ matrix.repo }}
+        uses: actions/checkout@v2
+        with:
+          repository: ${{ matrix.repo }}
+          path: ${{ github.workspace }}/repo
+      - name: Create database
+        run: |
+          "${CODEQL}" database create \
+            --search-path "ql/extractor-pack" \
+            --threads 4 \
+            --language ql --source-root "${{ github.workspace }}/repo" \
+            "${{ runner.temp }}/database"
+        env:
+          CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
+      - name: Measure database
+        run: |
+          mkdir -p "stats/${{ matrix.repo }}"
+          "${CODEQL}" dataset measure --threads 4 --output "stats/${{ matrix.repo }}/stats.xml" "${{ runner.temp }}/database/db-ql"
+        env:
+          CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
+      - uses: actions/upload-artifact@v2
+        with:
+          name: measurements
+          path: stats
+          retention-days: 1
+
+  merge:
+    runs-on: ubuntu-latest
+    needs: measure
+    steps:
+      - uses: actions/checkout@v2
+      - uses: actions/download-artifact@v2
+        with:
+          name: measurements
+          path: stats
+      - run: |
+          python -m pip install --user lxml
+          find stats -name 'stats.xml' -print0 | sort -z | xargs -0 python ql/scripts/merge_stats.py --output ql/ql/src/ql.dbscheme.stats --normalise ql_tokeninfo
+      - uses: actions/upload-artifact@v2
+        with:
+          name: ql.dbscheme.stats
+          path: ql/ql/src/ql.dbscheme.stats

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

@@ -0,0 +1,52 @@
+name: Run QL for QL Tests
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - "ql/**"
+  pull_request:
+    branches: [main]
+    paths:
+      - "ql/**"
+
+env:
+  CARGO_TERM_COLOR: always
+
+jobs:
+  qltest:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: Find codeql
+        id: find-codeql
+        uses: github/codeql-action/init@erik-krogh/ql
+        with:
+          languages: javascript # does not matter
+      - uses: actions/cache@v2
+        with:
+          path: |
+            ~/.cargo/registry
+            ~/.cargo/git
+            ql/target
+          key: ${{ runner.os }}-qltest-cargo-${{ hashFiles('ql/**/Cargo.lock') }}
+      - name: Build extractor
+        run: |
+          cd ql;
+          codeqlpath=$(dirname ${{ steps.find-codeql.outputs.codeql-path }});
+          env "PATH=$PATH:$codeqlpath" ./create-extractor-pack.sh
+      - name: Run QL tests
+        run: |
+          "${CODEQL}" test run --check-databases --check-unused-labels --check-repeated-labels --check-redefined-labels --check-use-before-definition --search-path "${{ github.workspace }}/ql/extractor-pack" --consistency-queries ql/ql/consistency-queries ql/ql/test
+        env:
+          CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
+      - name: Check QL formatting
+        run: |
+          find ql/ql "(" -name "*.ql" -or -name "*.qll" ")" -print0 | xargs -0 "${CODEQL}" query format --check-only
+        env:
+          CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}
+      - name: Check QL compilation
+        run: |
+          "${CODEQL}" query compile --check-only --threads=4 --warnings=error --search-path "${{ github.workspace }}/ql/extractor-pack" "ql/ql/src" "ql/ql/examples"
+        env:
+          CODEQL: ${{ steps.find-codeql.outputs.codeql-path }}

.github/workflows/ruby-build.yml

@@ -50,7 +50,7 @@ jobs:
             ~/.cargo/registry
             ~/.cargo/git
             ruby/target
-          key: ${{ runner.os }}-rust-cargo-${{ hashFiles('**/Cargo.lock') }}
+          key: ${{ runner.os }}-ruby-rust-cargo-${{ hashFiles('ruby/rust-toolchain.toml', 'ruby/**/Cargo.lock') }}
       - name: Check formatting
         run: cargo fmt --all -- --check
       - name: Build

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

@@ -24,7 +24,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        repo: [rails/rails, discourse/discourse, spree/spree]
+        repo: [rails/rails, discourse/discourse, spree/spree, ruby/ruby]
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v2

.github/workflows/ruby-qltest.yml

@@ -24,27 +24,53 @@ defaults:
     working-directory: ruby
 
 jobs:
-  qltest:
+  qlformat:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v2
       - uses: ./.github/actions/fetch-codeql
-      - uses: ./ruby/actions/create-extractor-pack
-      - name: Run QL tests
-        run: |
-          codeql test run --search-path "${{ github.workspace }}/ruby/extractor-pack" --check-databases --check-unused-labels --check-repeated-labels --check-redefined-labels --check-use-before-definition --consistency-queries ql/consistency-queries ql/test
-        env:
-          GITHUB_TOKEN: ${{ github.token }}
       - name: Check QL formatting
         run: find ql "(" -name "*.ql" -or -name "*.qll" ")" -print0 | xargs -0 codeql query format --check-only
+  qlcompile:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: ./.github/actions/fetch-codeql
       - name: Check QL compilation
         run: |
-          codeql query compile --check-only --threads=4 --warnings=error "ql/src" "ql/examples"
+          codeql query compile --check-only --threads=0 --ram 5000 --warnings=error "ql/src" "ql/examples"
         env:
           GITHUB_TOKEN: ${{ github.token }}
+  qlupgrade:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: ./.github/actions/fetch-codeql
       - name: Check DB upgrade scripts
         run: |
           echo >empty.trap
           codeql dataset import -S ql/lib/upgrades/initial/ruby.dbscheme testdb empty.trap
           codeql dataset upgrade testdb --additional-packs ql/lib
           diff -q testdb/ruby.dbscheme ql/lib/ruby.dbscheme
+      - name: Check DB downgrade scripts
+        run: |
+          echo >empty.trap
+          rm -rf testdb; codeql dataset import -S ql/lib/ruby.dbscheme testdb empty.trap
+          codeql resolve upgrades --format=lines --allow-downgrades --additional-packs downgrades \
+           --dbscheme=ql/lib/ruby.dbscheme --target-dbscheme=downgrades/initial/ruby.dbscheme |
+           xargs codeql execute upgrades testdb
+          diff -q testdb/ruby.dbscheme downgrades/initial/ruby.dbscheme
+  qltest:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        slice: ["1/2", "2/2"]
+    steps:
+      - uses: actions/checkout@v2
+      - uses: ./.github/actions/fetch-codeql
+      - uses: ./ruby/actions/create-extractor-pack
+      - name: Run QL tests
+        run: |
+          codeql test run --threads=0 --ram 5000 --slice ${{ matrix.slice }} --search-path "${{ github.workspace }}/ruby/extractor-pack" --check-databases --check-unused-labels --check-repeated-labels --check-redefined-labels --check-use-before-definition --consistency-queries ql/consistency-queries ql/test
+        env:
+          GITHUB_TOKEN: ${{ github.token }}

CODEOWNERS

@@ -13,6 +13,9 @@
 /python/**/experimental/**/* @github/codeql-python @xcorail
 /ruby/**/experimental/**/* @github/codeql-ruby @xcorail
 
+# ML-powered queries
+/javascript/ql/experimental/adaptivethreatmodeling/ @github/codeql-ml-powered-queries-reviewers
+
 # Notify members of codeql-go about PRs to the shared data-flow library files
 /java/ql/src/semmle/code/java/dataflow/internal/DataFlowImpl.qll @github/codeql-java @github/codeql-go
 /java/ql/src/semmle/code/java/dataflow/internal/DataFlowImpl2.qll @github/codeql-java @github/codeql-go
@@ -25,3 +28,6 @@
 /docs/codeql-for-visual-studio-code/ @github/codeql-vscode-reviewers
 /docs/ql-language-reference/ @github/codeql-frontend-reviewers
 /docs/query-*-style-guide.md @github/codeql-analysis-reviewers
+
+# QL for QL reviewers
+/ql/ @github/codeql-ql-for-ql-reviewers

CONTRIBUTING.md

@@ -4,6 +4,9 @@ We welcome contributions to our CodeQL libraries and queries. Got an idea for a
 
 There is lots of useful documentation to help you write queries, ranging from information about query file structure to tutorials for specific target languages. For more information on the documentation available, see [CodeQL queries](https://help.semmle.com/QL/learn-ql/writing-queries/writing-queries.html) on [help.semmle.com](https://help.semmle.com).
 
+## Change notes
+
+Any nontrivial user-visible change to a query pack or library pack should have a change note. For details on how to add a change note for your change, see [this guide](docs/change-notes.md).
 
 ## Submitting a new experimental query
 

README.md

@@ -1,11 +1,11 @@
 # CodeQL
 
-This open source repository contains the standard CodeQL libraries and queries that power [LGTM](https://lgtm.com) and the other CodeQL products that [GitHub](https://github.com) makes available to its customers worldwide. For the queries, libraries, and extractor that power Go analysis, visit the [CodeQL for Go repository](https://github.com/github/codeql-go).
+This open source repository contains the standard CodeQL libraries and queries that power [GitHub Advanced Security](https://github.com/features/security/code) and the other application security products that [GitHub](https://github.com/features/security/) makes available to its customers worldwide. For the queries, libraries, and extractor that power Go analysis, visit the [CodeQL for Go repository](https://github.com/github/codeql-go).
 
 ## How do I learn CodeQL and run queries?
 
 There is [extensive documentation](https://codeql.github.com/docs/) on getting started with writing CodeQL.
-You can use the [interactive query console](https://lgtm.com/help/lgtm/using-query-console) on LGTM.com or the [CodeQL for Visual Studio Code](https://codeql.github.com/docs/codeql-for-visual-studio-code/) extension to try out your queries on any open source project that's currently being analyzed.
+You can use the [CodeQL for Visual Studio Code](https://codeql.github.com/docs/codeql-for-visual-studio-code/) extension or the [interactive query console](https://lgtm.com/help/lgtm/using-query-console) on LGTM.com (Semmle Legacy product) to try out your queries on any open source project that's currently being analyzed.
 
 ## Contributing
 
@@ -13,7 +13,7 @@ We welcome contributions to our standard library and standard checks. Do you hav
 
 ## License
 
-The code in this repository is licensed under the [MIT License](LICENSE) by [GitHub](https://github.com).
+The code in this repository is licensed under the [MIT License](LICENSE) by [GitHub](https://github.com). The use of CodeQL on open source code is licensed under specific [Terms & Conditions](https://securitylab.github.com/tools/codeql/license/) UNLESS you have a commercial license in place. If you'd like to use CodeQL with a commercial codebase, please [contact us](https://github.com/enterprise/contact) for further help.
 
 ## Visual Studio Code integration
 

config/identical-files.json

@@ -7,6 +7,7 @@
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl5.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImpl6.qll",
     "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplForSerializability.qll",
+    "java/ql/lib/semmle/code/java/dataflow/internal/DataFlowImplForOnActivityResult.qll",
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl.qll",
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl2.qll",
     "cpp/ql/lib/semmle/code/cpp/dataflow/internal/DataFlowImpl3.qll",
@@ -452,9 +453,15 @@
     "ruby/ql/lib/codeql/ruby/dataflow/internal/SsaImplCommon.qll",
     "cpp/ql/lib/semmle/code/cpp/ir/dataflow/internal/SsaImplCommon.qll"
   ],
-  "CryptoAlgorithms Python/JS": [
+  "CryptoAlgorithms Python/JS/Ruby": [
     "javascript/ql/lib/semmle/javascript/security/CryptoAlgorithms.qll",
-    "python/ql/lib/semmle/python/concepts/CryptoAlgorithms.qll"
+    "python/ql/lib/semmle/python/concepts/CryptoAlgorithms.qll",
+    "ruby/ql/lib/codeql/ruby/security/CryptoAlgorithms.qll"
+  ],
+  "CryptoAlgorithmNames Python/JS/Ruby": [
+    "javascript/ql/lib/semmle/javascript/security/internal/CryptoAlgorithmNames.qll",
+    "python/ql/lib/semmle/python/concepts/internal/CryptoAlgorithmNames.qll",
+    "ruby/ql/lib/codeql/ruby/security/internal/CryptoAlgorithmNames.qll"
   ],
   "SensitiveDataHeuristics Python/JS": [
     "javascript/ql/lib/semmle/javascript/security/internal/SensitiveDataHeuristics.qll",

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

@@ -2,7 +2,7 @@
 
   <PropertyGroup>
     <OutputType>Exe</OutputType>
-    <TargetFramework>net5.0</TargetFramework>
+    <TargetFramework>net6.0</TargetFramework>
     <GenerateAssemblyInfo>false</GenerateAssemblyInfo>
     <RuntimeIdentifiers>win-x64;linux-x64;osx-x64</RuntimeIdentifiers>
     <Nullable>enable</Nullable>

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

@@ -1,7 +1,7 @@
 <Project Sdk="Microsoft.NET.Sdk">
 
   <PropertyGroup>
-    <TargetFramework>net5.0</TargetFramework>
+    <TargetFramework>net6.0</TargetFramework>
     <AssemblyName>Semmle.Autobuild.Cpp</AssemblyName>
     <RootNamespace>Semmle.Autobuild.Cpp</RootNamespace>
     <ApplicationIcon />
@@ -17,7 +17,7 @@
   </ItemGroup>
 
   <ItemGroup>
-    <PackageReference Include="Microsoft.Build" Version="16.9.0" />
+    <PackageReference Include="Microsoft.Build" Version="16.11.0" />
   </ItemGroup>
 
   <ItemGroup>

cpp/change-notes/2021-11-01-isFromSystemMacroDefinition.md

@@ -1,4 +0,0 @@
-lgtm,codescanning
-* The QL library `semmle.code.cpp.commons.Exclusions` now contains a predicate
-  `isFromSystemMacroDefinition` for identifying code that originates from a
-  macro outside the project being analyzed.

cpp/change-notes/2021-11-09-use-of-http.md

@@ -1,2 +0,0 @@
-lgtm,codescanning
-* A new query `cpp/non-https-url` has been added for C/C++. The query flags uses of `http` URLs that might be better replaced with `https`.

cpp/config/suites/security/cwe-120

@@ -5,9 +5,11 @@
   @name Badly bounded write (CWE-120)
 + semmlecode-cpp-queries/Security/CWE/CWE-120/OverrunWrite.ql: /CWE/CWE-120
   @name Potentially overrunning write (CWE-120)
++ semmlecode-cpp-queries/Security/CWE/CWE-120/VeryLikelyOverrunWrite.ql: /CWE/CWE-120
+  @name Likely overrunning write
 + semmlecode-cpp-queries/Security/CWE/CWE-120/OverrunWriteFloat.ql: /CWE/CWE-120
   @name Potentially overrunning write with float to string conversion (CWE-120)
 + semmlecode-cpp-queries/Best Practices/Likely Errors/OffsetUseBeforeRangeCheck.ql: /CWE/CWE-120
   @name Array offset used before range check (CWE-120)
 + semmlecode-cpp-queries/Likely Bugs/Memory Management/UnsafeUseOfStrcat.ql: /CWE/CWE-120
-    @name Potentially unsafe use of strcat (CWE-120)
+  @name Potentially unsafe use of strcat (CWE-120)

cpp/old-change-notes/2021-10-07-cleartext-transmission.md

@@ -0,0 +1,2 @@
+lgtm,codescanning
+* The "Cleartext transmission of sensitive information" (`cpp/cleartext-transmission`) query has been improved, reducing the number of false positive results when encryption is present.

cpp/ql/examples/qlpack.yml

@@ -1,4 +1,6 @@
 name: codeql/cpp-examples
-version: 0.0.2
+groups: 
+  - cpp
+  - examples
 dependencies:
   codeql/cpp-all: "*"

cpp/ql/lib/CHANGELOG.md

@@ -1,3 +1,22 @@
+## 0.0.9
+
+## 0.0.8
+
+### Deprecated APIs
+
+* The `codeql/cpp-upgrades` CodeQL pack has been removed. All upgrades scripts have been merged into the `codeql/cpp-all` CodeQL pack.
+
+### Minor Analysis Improvements
+
+* `FormatLiteral::getMaxConvertedLength` now uses range analysis to provide a
+  more accurate length for integers formatted with `%x`
+
+## 0.0.7
+
+## 0.0.6
+
+## 0.0.5
+
 ## 0.0.4
 
 ### New Features

cpp/ql/lib/DefaultOptions.qll

@@ -73,7 +73,7 @@ class Options extends string {
    *   __assume(0);
    * ```
    * (note that in this case if the hint is wrong and the expression is reached at
-   * runtime, the program's behaviour is undefined)
+   * runtime, the program's behavior is undefined)
    */
   predicate exprExits(Expr e) {
     e.(AssumeExpr).getChild(0).(CompileTimeConstantInt).getIntValue() = 0 or

cpp/ql/lib/Options.qll

@@ -50,7 +50,7 @@ class CustomOptions extends Options {
    *   __assume(0);
    * ```
    * (note that in this case if the hint is wrong and the expression is reached at
-   * runtime, the program's behaviour is undefined)
+   * runtime, the program's behavior is undefined)
    */
   override predicate exprExits(Expr e) { Options.super.exprExits(e) }
 

cpp/ql/lib/change-notes/released/0.0.6.md

@@ -0,0 +1 @@
+## 0.0.6

cpp/ql/lib/change-notes/released/0.0.7.md

@@ -0,0 +1 @@
+## 0.0.7

cpp/ql/lib/change-notes/released/0.0.8.md

@@ -0,0 +1,10 @@
+## 0.0.8
+
+### Deprecated APIs
+
+* The `codeql/cpp-upgrades` CodeQL pack has been removed. All upgrades scripts have been merged into the `codeql/cpp-all` CodeQL pack.
+
+### Minor Analysis Improvements
+
+* `FormatLiteral::getMaxConvertedLength` now uses range analysis to provide a
+  more accurate length for integers formatted with `%x`

cpp/ql/lib/change-notes/released/0.0.9.md

@@ -0,0 +1,2 @@
+## 0.0.9
+

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

@@ -1,2 +1,2 @@
 ---
-lastReleaseVersion: 0.0.4
+lastReleaseVersion: 0.0.9

cpp/ql/lib/experimental/semmle/code/cpp/models/interfaces/SimpleRangeAnalysisDefinition.qll

@@ -37,7 +37,7 @@ abstract class SimpleRangeAnalysisDefinition extends RangeSsaDefinition {
    * dependencies. Without this information, range analysis might work for
    * simple cases but will go into infinite loops on complex code.
    *
-   * For example, when modelling the definition by reference in a call to an
+   * For example, when modeling the definition by reference in a call to an
    * overloaded `operator=`, written as `v = e`, the definition of `(this, v)`
    * depends on `e`.
    */

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

@@ -5,7 +5,7 @@
  * `Instruction` level), and then using the array length analysis and the range
  * analysis together to prove that some of these pointer dereferences are safe.
  *
- * The analysis is soundy, i.e. it is sound if no undefined behaviour is present
+ * The analysis is soundy, i.e. it is sound if no undefined behavior is present
  * in the program.
  * Furthermore, it crucially depends on the soundiness of the range analysis and
  * the array length analysis.

cpp/ql/lib/qlpack.yml

@@ -1,8 +1,7 @@
 name: codeql/cpp-all
-version: 0.0.4
+version: 0.0.9
 groups: cpp
 dbscheme: semmlecode.cpp.dbscheme
 extractor: cpp
 library: true
-dependencies:
-  codeql/cpp-upgrades: 0.0.3
+upgrades: upgrades

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

@@ -206,9 +206,7 @@ class Class extends UserType {
    * it is callable by a particular caller. For C++11, there's also a question
    * of whether to include members that are defaulted or deleted.
    */
-  deprecated predicate hasCopyConstructor() {
-    exists(CopyConstructor cc | cc = this.getAMemberFunction())
-  }
+  deprecated predicate hasCopyConstructor() { this.getAMemberFunction() instanceof CopyConstructor }
 
   /**
    * Holds if this class has a copy assignment operator that is either
@@ -224,7 +222,7 @@ class Class extends UserType {
    * or deleted.
    */
   deprecated predicate hasCopyAssignmentOperator() {
-    exists(CopyAssignmentOperator coa | coa = this.getAMemberFunction())
+    this.getAMemberFunction() instanceof CopyAssignmentOperator
   }
 
   /**
@@ -887,7 +885,7 @@ class NestedClass extends Class {
  * pure virtual function.
  */
 class AbstractClass extends Class {
-  AbstractClass() { exists(PureVirtualFunction f | this.getAMemberFunction() = f) }
+  AbstractClass() { this.getAMemberFunction() instanceof PureVirtualFunction }
 
   override string getAPrimaryQlClass() { result = "AbstractClass" }
 }

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

@@ -286,13 +286,13 @@ class AttributeArgument extends Element, @attribute_arg {
   override Location getLocation() { attribute_args(underlyingElement(this), _, _, _, result) }
 
   override string toString() {
-    if exists(@attribute_arg_empty self | self = underlyingElement(this))
+    if underlyingElement(this) instanceof @attribute_arg_empty
     then result = "empty argument"
     else
       exists(string prefix, string tail |
         (if exists(this.getName()) then prefix = this.getName() + "=" else prefix = "") and
         (
-          if exists(@attribute_arg_type self | self = underlyingElement(this))
+          if underlyingElement(this) instanceof @attribute_arg_type
           then tail = this.getValueType().getName()
           else tail = this.getValueText()
         ) and

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

@@ -233,7 +233,7 @@ class XMLElement extends @xmlelement, XMLParent, XMLLocatable {
   XMLAttribute getAttribute(string name) { result.getElement() = this and result.getName() = name }
 
   /** Holds if this XML element has an attribute with the specified `name`. */
-  predicate hasAttribute(string name) { exists(XMLAttribute a | a = this.getAttribute(name)) }
+  predicate hasAttribute(string name) { exists(this.getAttribute(name)) }
 
   /** Gets the value of the attribute with the specified `name`, if any. */
   string getAttributeValue(string name) { result = this.getAttribute(name).getValue() }

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

@@ -101,6 +101,21 @@ predicate functionArgumentMustBeNullTerminated(Function f, int i) {
   f instanceof StrcatFunction and i = 0
 }
 
+/**
+ * Holds if `arg` is a string format argument to a formatting function call
+ * `ffc`.
+ */
+predicate formatArgumentMustBeNullTerminated(FormattingFunctionCall ffc, Expr arg) {
+  // String argument to a formatting function (such as `printf`)
+  exists(int n, FormatLiteral fl |
+    ffc.getConversionArgument(n) = arg and
+    fl = ffc.getFormat() and
+    fl.getConversionType(n) instanceof PointerType and // `%s`, `%ws` etc
+    not fl.getConversionType(n) instanceof VoidPointerType and // exclude: `%p`
+    not fl.hasPrecision(n) // exclude: `%.*s`
+  )
+}
+
 /**
  * Holds if `va` is a variable access where the contents must be null terminated.
  */
@@ -113,13 +128,7 @@ predicate variableMustBeNullTerminated(VariableAccess va) {
     )
     or
     // String argument to a formatting function (such as `printf`)
-    exists(int n, FormatLiteral fl |
-      fc.(FormattingFunctionCall).getConversionArgument(n) = va and
-      fl = fc.(FormattingFunctionCall).getFormat() and
-      fl.getConversionType(n) instanceof PointerType and // `%s`, `%ws` etc
-      not fl.getConversionType(n) instanceof VoidPointerType and // exclude: `%p`
-      not fl.hasPrecision(n) // exclude: `%.*s`
-    )
+    formatArgumentMustBeNullTerminated(fc, va)
     or
     // Call to a wrapper function that requires null termination
     // (not itself adding a null terminator)

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

@@ -9,6 +9,106 @@ import semmle.code.cpp.models.interfaces.FormattingFunction
 private import semmle.code.cpp.rangeanalysis.SimpleRangeAnalysis
 private import semmle.code.cpp.rangeanalysis.RangeAnalysisUtils
 
+private newtype TBufferWriteEstimationReason =
+  TUnspecifiedEstimateReason() or
+  TTypeBoundsAnalysis() or
+  TWidenedValueFlowAnalysis() or
+  TValueFlowAnalysis()
+
+private predicate gradeToReason(int grade, TBufferWriteEstimationReason reason) {
+  // when combining reasons, lower grade takes precedence
+  grade = 0 and reason = TUnspecifiedEstimateReason()
+  or
+  grade = 1 and reason = TTypeBoundsAnalysis()
+  or
+  grade = 2 and reason = TWidenedValueFlowAnalysis()
+  or
+  grade = 3 and reason = TValueFlowAnalysis()
+}
+
+/**
+ * A reason for a specific buffer write size estimate.
+ */
+abstract class BufferWriteEstimationReason extends TBufferWriteEstimationReason {
+  /**
+   * Returns the name of the concrete class.
+   */
+  abstract string toString();
+
+  /**
+   * Returns a human readable representation of this reason.
+   */
+  abstract string getDescription();
+
+  /**
+   * Combine estimate reasons. Used to give a reason for the size of a format string
+   * conversion given reasons coming from its individual specifiers.
+   */
+  BufferWriteEstimationReason combineWith(BufferWriteEstimationReason other) {
+    exists(int grade, int otherGrade |
+      gradeToReason(grade, this) and gradeToReason(otherGrade, other)
+    |
+      if otherGrade < grade then result = other else result = this
+    )
+  }
+}
+
+/**
+ * No particular reason given. This is currently used for backward compatibility so that
+ * classes derived from BufferWrite and overriding `getMaxData/0` still work with the
+ * queries as intended.
+ */
+class UnspecifiedEstimateReason extends BufferWriteEstimationReason, TUnspecifiedEstimateReason {
+  override string toString() { result = "UnspecifiedEstimateReason" }
+
+  override string getDescription() { result = "no reason specified" }
+}
+
+/**
+ * The estimation comes from rough bounds just based on the type (e.g.
+ * `0 <= x < 2^32` for an unsigned 32 bit integer).
+ */
+class TypeBoundsAnalysis extends BufferWriteEstimationReason, TTypeBoundsAnalysis {
+  override string toString() { result = "TypeBoundsAnalysis" }
+
+  override string getDescription() { result = "based on type bounds" }
+}
+
+/**
+ * The estimation comes from non trivial bounds found via actual flow analysis,
+ * but a widening aproximation might have been used for variables in loops.
+ * For example
+ * ```
+ * for (int i = 0; i < 10; ++i) {
+ *    int j = i + i;
+ *    //...  <- estimation done here based on j
+ * }
+ * ```
+ */
+class WidenedValueFlowAnalysis extends BufferWriteEstimationReason, TWidenedValueFlowAnalysis {
+  override string toString() { result = "WidenedValueFlowAnalysis" }
+
+  override string getDescription() {
+    result = "based on flow analysis of value bounds with a widening approximation"
+  }
+}
+
+/**
+ * The estimation comes from non trivial bounds found via actual flow analysis.
+ * For example
+ * ```
+ * unsigned u = x;
+ * if (u < 1000) {
+ *    //...  <- estimation done here based on u
+ * }
+ * ```
+ */
+class ValueFlowAnalysis extends BufferWriteEstimationReason, TValueFlowAnalysis {
+  override string toString() { result = "ValueFlowAnalysis" }
+
+  override string getDescription() { result = "based on flow analysis of value bounds" }
+}
+
 class PrintfFormatAttribute extends FormatAttribute {
   PrintfFormatAttribute() { this.getArchetype() = ["printf", "__printf__"] }
 }
@@ -282,6 +382,38 @@ private int lengthInBase10(float f) {
   result = f.log10().floor() + 1
 }
 
+pragma[nomagic]
+private predicate isPointerTypeWithBase(Type base, PointerType pt) { base = pt.getBaseType() }
+
+bindingset[expr]
+private BufferWriteEstimationReason getEstimationReasonForIntegralExpression(Expr expr) {
+  // we consider the range analysis non trivial if it
+  // * constrained non-trivially both sides of a signed value, or
+  // * constrained non-trivially the positive side of an unsigned value
+  // expr should already be given as getFullyConverted
+  if
+    upperBound(expr) < exprMaxVal(expr) and
+    (exprMinVal(expr) >= 0 or lowerBound(expr) > exprMinVal(expr))
+  then
+    // next we check whether the estimate may have been widened
+    if upperBoundMayBeWidened(expr)
+    then result = TWidenedValueFlowAnalysis()
+    else result = TValueFlowAnalysis()
+  else result = TTypeBoundsAnalysis()
+}
+
+/**
+ * Gets the number of hex digits required to represent the integer represented by `f`.
+ *
+ * `f` is assumed to be nonnegative.
+ */
+bindingset[f]
+private int lengthInBase16(float f) {
+  f = 0 and result = 1
+  or
+  result = (f.log2() / 4.0).floor() + 1
+}
+
 /**
  * A class to represent format strings that occur as arguments to invocations of formatting functions.
  */
@@ -833,19 +965,19 @@ class FormatLiteral extends Literal {
       (
         conv = ["s", "S"] and
         len = "h" and
-        result.(PointerType).getBaseType() instanceof PlainCharType
+        isPointerTypeWithBase(any(PlainCharType plainCharType), result)
         or
         conv = ["s", "S"] and
         len = ["l", "w"] and
-        result.(PointerType).getBaseType() = this.getWideCharType()
+        isPointerTypeWithBase(this.getWideCharType(), result)
         or
         conv = "s" and
         (len != "l" and len != "w" and len != "h") and
-        result.(PointerType).getBaseType() = this.getDefaultCharType()
+        isPointerTypeWithBase(this.getDefaultCharType(), result)
         or
         conv = "S" and
         (len != "l" and len != "w" and len != "h") and
-        result.(PointerType).getBaseType() = this.getNonDefaultCharType()
+        isPointerTypeWithBase(this.getNonDefaultCharType(), result)
       )
     )
   }
@@ -990,7 +1122,14 @@ class FormatLiteral extends Literal {
    * conversion specifier of this format string; has no result if this cannot
    * be determined.
    */
-  int getMaxConvertedLength(int n) {
+  int getMaxConvertedLength(int n) { result = max(this.getMaxConvertedLength(n, _)) }
+
+  /**
+   * Gets the maximum length of the string that can be produced by the nth
+   * conversion specifier of this format string, specifying the estimation reason;
+   * has no result if this cannot be determined.
+   */
+  int getMaxConvertedLength(int n, BufferWriteEstimationReason reason) {
     exists(int len |
       (
         (
@@ -1002,10 +1141,12 @@ class FormatLiteral extends Literal {
       ) and
       (
         this.getConversionChar(n) = "%" and
-        len = 1
+        len = 1 and
+        reason = TValueFlowAnalysis()
         or
         this.getConversionChar(n).toLowerCase() = "c" and
-        len = 1 // e.g. 'a'
+        len = 1 and
+        reason = TValueFlowAnalysis() // e.g. 'a'
         or
         this.getConversionChar(n).toLowerCase() = "f" and
         exists(int dot, int afterdot |
@@ -1019,7 +1160,8 @@ class FormatLiteral extends Literal {
             afterdot = 6
           ) and
           len = 1 + 309 + dot + afterdot
-        ) // e.g. -1e308="-100000"...
+        ) and
+        reason = TTypeBoundsAnalysis() // e.g. -1e308="-100000"...
         or
         this.getConversionChar(n).toLowerCase() = "e" and
         exists(int dot, int afterdot |
@@ -1033,7 +1175,8 @@ class FormatLiteral extends Literal {
             afterdot = 6
           ) and
           len = 1 + 1 + dot + afterdot + 1 + 1 + 3
-        ) // -1e308="-1.000000e+308"
+        ) and
+        reason = TTypeBoundsAnalysis() // -1e308="-1.000000e+308"
         or
         this.getConversionChar(n).toLowerCase() = "g" and
         exists(int dot, int afterdot |
@@ -1056,85 +1199,110 @@ class FormatLiteral extends Literal {
           //       (e.g. 123456, 0.000123456 are just OK)
           //       so case %f can be at most P characters + 4 zeroes, sign, dot = P + 6
           len = (afterdot.maximum(1) + 6).maximum(1 + 1 + dot + afterdot + 1 + 1 + 3)
-        ) // (e.g. "-1.59203e-319")
+        ) and
+        reason = TTypeBoundsAnalysis() // (e.g. "-1.59203e-319")
         or
         this.getConversionChar(n).toLowerCase() = ["d", "i"] and
         // e.g. -2^31 = "-2147483648"
-        len =
-          min(float cand |
-            // The first case handles length sub-specifiers
-            // Subtract one in the exponent because one bit is for the sign.
-            // Add 1 to account for the possible sign in the output.
-            cand = 1 + lengthInBase10(2.pow(this.getIntegralDisplayType(n).getSize() * 8 - 1))
-            or
-            // The second case uses range analysis to deduce a length that's shorter than the length
-            // of the number -2^31.
-            exists(Expr arg, float lower, float upper |
-              arg = this.getUse().getConversionArgument(n) and
-              lower = lowerBound(arg.getFullyConverted()) and
-              upper = upperBound(arg.getFullyConverted())
-            |
-              cand =
-                max(int cand0 |
-                  // Include the sign bit in the length if it can be negative
-                  (
-                    if lower < 0
-                    then cand0 = 1 + lengthInBase10(lower.abs())
-                    else cand0 = lengthInBase10(lower)
-                  )
-                  or
-                  (
-                    if upper < 0
-                    then cand0 = 1 + lengthInBase10(upper.abs())
-                    else cand0 = lengthInBase10(upper)
-                  )
+        exists(float typeBasedBound, float valueBasedBound |
+          // The first case handles length sub-specifiers
+          // Subtract one in the exponent because one bit is for the sign.
+          // Add 1 to account for the possible sign in the output.
+          typeBasedBound =
+            1 + lengthInBase10(2.pow(this.getIntegralDisplayType(n).getSize() * 8 - 1)) and
+          // The second case uses range analysis to deduce a length that's shorter than the length
+          // of the number -2^31.
+          exists(Expr arg, float lower, float upper |
+            arg = this.getUse().getConversionArgument(n) and
+            lower = lowerBound(arg.getFullyConverted()) and
+            upper = upperBound(arg.getFullyConverted())
+          |
+            valueBasedBound =
+              max(int cand |
+                // Include the sign bit in the length if it can be negative
+                (
+                  if lower < 0
+                  then cand = 1 + lengthInBase10(lower.abs())
+                  else cand = lengthInBase10(lower)
                 )
-            )
-          )
+                or
+                (
+                  if upper < 0
+                  then cand = 1 + lengthInBase10(upper.abs())
+                  else cand = lengthInBase10(upper)
+                )
+              ) and
+            // we don't want to call this on `arg.getFullyConverted()` as we want
+            // to detect non-trivial range analysis without taking into account up-casting
+            reason = getEstimationReasonForIntegralExpression(arg)
+          ) and
+          len = valueBasedBound.minimum(typeBasedBound)
+        )
         or
         this.getConversionChar(n).toLowerCase() = "u" and
         // e.g. 2^32 - 1 = "4294967295"
-        len =
-          min(float cand |
-            // The first case handles length sub-specifiers
-            cand = 2.pow(this.getIntegralDisplayType(n).getSize() * 8)
-            or
-            // The second case uses range analysis to deduce a length that's shorter than
-            // the length of the number 2^31 - 1.
-            exists(Expr arg, float lower |
-              arg = this.getUse().getConversionArgument(n) and
-              lower = lowerBound(arg.getFullyConverted())
-            |
-              cand =
-                max(float cand0 |
+        exists(float typeBasedBound, float valueBasedBound |
+          // The first case handles length sub-specifiers
+          typeBasedBound = lengthInBase10(2.pow(this.getIntegralDisplayType(n).getSize() * 8) - 1) and
+          // The second case uses range analysis to deduce a length that's shorter than
+          // the length of the number 2^31 - 1.
+          exists(Expr arg, float lower, float upper |
+            arg = this.getUse().getConversionArgument(n) and
+            lower = lowerBound(arg.getFullyConverted()) and
+            upper = upperBound(arg.getFullyConverted())
+          |
+            valueBasedBound =
+              lengthInBase10(max(float cand |
                   // If lower can be negative we use `(unsigned)-1` as the candidate value.
                   lower < 0 and
-                  cand0 = 2.pow(any(IntType t | t.isUnsigned()).getSize() * 8)
+                  cand = 2.pow(any(IntType t | t.isUnsigned()).getSize() * 8)
                   or
-                  cand0 = upperBound(arg.getFullyConverted())
-                )
-            )
-          |
-            lengthInBase10(cand)
-          )
+                  cand = upper
+                )) and
+            // we don't want to call this on `arg.getFullyConverted()` as we want
+            // to detect non-trivial range analysis without taking into account up-casting
+            reason = getEstimationReasonForIntegralExpression(arg)
+          ) and
+          len = valueBasedBound.minimum(typeBasedBound)
+        )
         or
         this.getConversionChar(n).toLowerCase() = "x" and
         // e.g. "12345678"
-        exists(int sizeBytes, int baseLen |
-          sizeBytes =
-            min(int bytes |
-              bytes = this.getIntegralDisplayType(n).getSize()
+        exists(int baseLen, int typeBasedBound, int valueBasedBound |
+          typeBasedBound =
+            min(int digits |
+              digits = 2 * this.getIntegralDisplayType(n).getSize()
               or
               exists(IntegralType t |
                 t = this.getUse().getConversionArgument(n).getType().getUnderlyingType()
               |
-                t.isUnsigned() and bytes = t.getSize()
+                t.isUnsigned() and
+                digits = 2 * t.getSize()
               )
             ) and
-          baseLen = sizeBytes * 2 and
-          (
-            if this.hasAlternateFlag(n) then len = 2 + baseLen else len = baseLen // "0x"
-          )
+          exists(Expr arg, float lower, float upper, float typeLower, float typeUpper |
+            arg = this.getUse().getConversionArgument(n) and
+            lower = lowerBound(arg.getFullyConverted()) and
+            upper = upperBound(arg.getFullyConverted()) and
+            typeLower = exprMinVal(arg.getFullyConverted()) and
+            typeUpper = exprMaxVal(arg.getFullyConverted())
+          |
+            valueBasedBound =
+              lengthInBase16(max(float cand |
+                  // If lower can be negative we use `(unsigned)-1` as the candidate value.
+                  lower < 0 and
+                  cand = 2.pow(any(IntType t | t.isUnsigned()).getSize() * 8)
+                  or
+                  cand = upper
+                )) and
+            (
+              if lower > typeLower or upper < typeUpper
+              then reason = TValueFlowAnalysis()
+              else reason = TTypeBoundsAnalysis()
+            )
+          ) and
+          baseLen = valueBasedBound.minimum(typeBasedBound) and
+          if this.hasAlternateFlag(n) then len = 2 + baseLen else len = baseLen // "0x"
         )
         or
         this.getConversionChar(n).toLowerCase() = "p" and
@@ -1144,7 +1312,8 @@ class FormatLiteral extends Literal {
           (
             if this.hasAlternateFlag(n) then len = 2 + baseLen else len = baseLen // "0x"
           )
-        )
+        ) and
+        reason = TValueFlowAnalysis()
         or
         this.getConversionChar(n).toLowerCase() = "o" and
         // e.g. 2^32 - 1 = "37777777777"
@@ -1163,14 +1332,16 @@ class FormatLiteral extends Literal {
           (
             if this.hasAlternateFlag(n) then len = 1 + baseLen else len = baseLen // "0"
           )
-        )
+        ) and
+        reason = TTypeBoundsAnalysis()
         or
         this.getConversionChar(n).toLowerCase() = "s" and
         len =
           min(int v |
             v = this.getPrecision(n) or
             v = this.getUse().getFormatArgument(n).(AnalysedString).getMaxLength() - 1 // (don't count null terminator)
-          )
+          ) and
+        reason = TValueFlowAnalysis()
       )
     )
   }
@@ -1182,10 +1353,19 @@ class FormatLiteral extends Literal {
    * determining whether a buffer overflow is caused by long float to string
    * conversions.
    */
-  int getMaxConvertedLengthLimited(int n) {
+  int getMaxConvertedLengthLimited(int n) { result = max(this.getMaxConvertedLengthLimited(n, _)) }
+
+  /**
+   * Gets the maximum length of the string that can be produced by the nth
+   * conversion specifier of this format string, specifying the reason for the
+   * estimation, except that float to string conversions are assumed to be 8
+   * characters.  This is helpful for determining whether a buffer overflow is
+   * caused by long float to string conversions.
+   */
+  int getMaxConvertedLengthLimited(int n, BufferWriteEstimationReason reason) {
     if this.getConversionChar(n).toLowerCase() = "f"
-    then result = this.getMaxConvertedLength(n).minimum(8)
-    else result = this.getMaxConvertedLength(n)
+    then result = this.getMaxConvertedLength(n, reason).minimum(8)
+    else result = this.getMaxConvertedLength(n, reason)
   }
 
   /**
@@ -1225,29 +1405,35 @@ class FormatLiteral extends Literal {
     )
   }
 
-  private int getMaxConvertedLengthAfter(int n) {
+  private int getMaxConvertedLengthAfter(int n, BufferWriteEstimationReason reason) {
     if n = this.getNumConvSpec()
-    then result = this.getConstantSuffix().length() + 1
+    then result = this.getConstantSuffix().length() + 1 and reason = TValueFlowAnalysis()
     else
-      result =
-        this.getConstantPart(n).length() + this.getMaxConvertedLength(n) +
-          this.getMaxConvertedLengthAfter(n + 1)
+      exists(BufferWriteEstimationReason headReason, BufferWriteEstimationReason tailReason |
+        result =
+          this.getConstantPart(n).length() + this.getMaxConvertedLength(n, headReason) +
+            this.getMaxConvertedLengthAfter(n + 1, tailReason) and
+        reason = headReason.combineWith(tailReason)
+      )
   }
 
-  private int getMaxConvertedLengthAfterLimited(int n) {
+  private int getMaxConvertedLengthAfterLimited(int n, BufferWriteEstimationReason reason) {
     if n = this.getNumConvSpec()
-    then result = this.getConstantSuffix().length() + 1
+    then result = this.getConstantSuffix().length() + 1 and reason = TValueFlowAnalysis()
     else
-      result =
-        this.getConstantPart(n).length() + this.getMaxConvertedLengthLimited(n) +
-          this.getMaxConvertedLengthAfterLimited(n + 1)
+      exists(BufferWriteEstimationReason headReason, BufferWriteEstimationReason tailReason |
+        result =
+          this.getConstantPart(n).length() + this.getMaxConvertedLengthLimited(n, headReason) +
+            this.getMaxConvertedLengthAfterLimited(n + 1, tailReason) and
+        reason = headReason.combineWith(tailReason)
+      )
   }
 
   /**
    * Gets the maximum length of the string that can be produced by this format
    * string.  Has no result if this cannot be determined.
    */
-  int getMaxConvertedLength() { result = this.getMaxConvertedLengthAfter(0) }
+  int getMaxConvertedLength() { result = this.getMaxConvertedLengthAfter(0, _) }
 
   /**
    * Gets the maximum length of the string that can be produced by this format
@@ -1255,5 +1441,24 @@ class FormatLiteral extends Literal {
    * characters.  This is helpful for determining whether a buffer overflow
    * is caused by long float to string conversions.
    */
-  int getMaxConvertedLengthLimited() { result = this.getMaxConvertedLengthAfterLimited(0) }
+  int getMaxConvertedLengthLimited() { result = this.getMaxConvertedLengthAfterLimited(0, _) }
+
+  /**
+   * Gets the maximum length of the string that can be produced by this format
+   * string, specifying the reason for the estimate. Has no result if no estimate
+   * can be found.
+   */
+  int getMaxConvertedLengthWithReason(BufferWriteEstimationReason reason) {
+    result = this.getMaxConvertedLengthAfter(0, reason)
+  }
+
+  /**
+   * Gets the maximum length of the string that can be produced by this format
+   * string, specifying the reason for the estimate, except that float to string
+   * conversions are assumed to be 8 characters.  This is helpful for determining
+   * whether a buffer overflow is caused by long float to string conversions.
+   */
+  int getMaxConvertedLengthLimitedWithReason(BufferWriteEstimationReason reason) {
+    result = this.getMaxConvertedLengthAfterLimited(0, reason)
+  }
 }

cpp/ql/lib/semmle/code/cpp/commons/unix/Constants.qll

@@ -11,10 +11,10 @@ import cpp
  */
 bindingset[input]
 int parseOctal(string input) {
-  input.charAt(0) = "0" and
+  input.regexpMatch("0[0-7]+") and
   result =
     strictsum(int ix |
-      ix in [0 .. input.length()]
+      ix in [1 .. input.length()]
     |
       8.pow(input.length() - (ix + 1)) * input.charAt(ix).toInt()
     )

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

@@ -29,7 +29,7 @@ class GuardCondition extends Expr {
     exists(IRGuardCondition ir | this = ir.getUnconvertedResultExpression())
     or
     // no binary operators in the IR
-    exists(GuardCondition gc | this.(BinaryLogicalOperation).getAnOperand() = gc)
+    this.(BinaryLogicalOperation).getAnOperand() instanceof GuardCondition
     or
     // the IR short-circuits if(!x)
     // don't produce a guard condition for `y = !x` and other non-short-circuited cases
@@ -98,7 +98,7 @@ class GuardCondition extends Expr {
  */
 private class GuardConditionFromBinaryLogicalOperator extends GuardCondition {
   GuardConditionFromBinaryLogicalOperator() {
-    exists(GuardCondition gc | this.(BinaryLogicalOperation).getAnOperand() = gc)
+    this.(BinaryLogicalOperation).getAnOperand() instanceof GuardCondition
   }
 
   override predicate controls(BasicBlock controlled, boolean testIsTrue) {

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

@@ -153,9 +153,11 @@ library class SSAHelper extends int {
    * Modern Compiler Implementation by Andrew Appel.
    */
   private predicate frontier_phi_node(StackVariable v, BasicBlock b) {
-    exists(BasicBlock x | dominanceFrontier(x, b) and ssa_defn_rec(v, x)) and
+    exists(BasicBlock x |
+      dominanceFrontier(x, b) and ssa_defn_rec(pragma[only_bind_into](v), pragma[only_bind_into](x))
+    ) and
     /* We can also eliminate those nodes where the variable is not live on any incoming edge */
-    live_at_start_of_bb(v, b)
+    live_at_start_of_bb(pragma[only_bind_into](v), b)
   }
 
   private predicate ssa_defn_rec(StackVariable v, BasicBlock b) {

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

@@ -626,9 +626,9 @@ library class ExprEvaluator extends int {
       // All assignments must have the same int value
       result =
         unique(Expr value |
-          value = v.getAnAssignedValue() and not ignoreVariableAssignment(e, v, value)
+          value = v.getAnAssignedValue() and not this.ignoreVariableAssignment(e, v, value)
         |
-          getValueInternalNonSubExpr(value)
+          this.getValueInternalNonSubExpr(value)
         )
     )
   }

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

@@ -1,4 +1,6 @@
 private import cpp
+private import semmle.code.cpp.dataflow.internal.DataFlowPrivate
+private import semmle.code.cpp.dataflow.internal.DataFlowUtil
 
 /**
  * Gets a function that might be called by `call`.
@@ -63,3 +65,17 @@ predicate mayBenefitFromCallContext(Call call, Function f) { none() }
  * restricted to those `call`s for which a context might make a difference.
  */
 Function viableImplInCallContext(Call call, Call ctx) { none() }
+
+/** A parameter position represented by an integer. */
+class ParameterPosition extends int {
+  ParameterPosition() { any(ParameterNode p).isParameterOf(_, this) }
+}
+
+/** An argument position represented by an integer. */
+class ArgumentPosition extends int {
+  ArgumentPosition() { any(ArgumentNode a).argumentOf(_, this) }
+}
+
+/** Holds if arguments at position `apos` match parameters at position `ppos`. */
+pragma[inline]
+predicate parameterMatch(ParameterPosition ppos, ArgumentPosition apos) { ppos = apos }