fix: arm64: collapse per-core CPU info lists to a single line

built from commit 44ba3790d9 dated 2026-06-02 19:11:45 +0200 by Stéphane Lesimple (speed47_github@speed47.net) Store the per-core implementer/part/arch/variant/revision lists space-separated (no embedded newlines, which also cleans up JSON and prometheus output) and dedup them for the human-readable display, so homogeneous systems show e.g. "0x41" instead of repeating it per core.
add scripts/update_mcedb.sh to be used in cron github workflow
2026-06-05 22:23:04 +02:00 · 2026-06-02 17:16:47 +00:00 · 2026-06-01 20:22:11 +00:00 · 2026-04-21 06:56:29 +00:00 · 2026-04-20 20:44:06 +00:00 · 2026-04-20 16:05:45 +00:00
4 changed files with 22 additions and 273 deletions
@@ -1,41 +0,0 @@
-name: autoupdate
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron: '42 9 * * *'
-
-permissions:
-  pull-requests: write
-  contents: write
-
-jobs:
-  autoupdate:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v5
-        with:
-          ref: source
-      - name: Install prerequisites
-        run: sudo apt-get update && sudo apt-get install -y --no-install-recommends iucode-tool sqlite3 unzip shfmt
-      - name: Update microcode versions
-        run: ./scripts/update_mcedb.sh
-      - name: Update Intel models
-        run: ./scripts/update_intel_models.sh
-      - name: Check git diff
-        id: diff
-        run: |
-          echo change="$(git diff | awk '/MCEDB/ { if(V) { print V" to "$4; exit } else { V=$4 } }')" >> "$GITHUB_OUTPUT"
-          echo nbdiff="$(git diff | grep -cE -- '^\+# [AI],')" >> "$GITHUB_OUTPUT"
-          git diff
-          cat "$GITHUB_OUTPUT"
-      - name: Create Pull Request if needed
-        if: steps.diff.outputs.nbdiff != '0'
-        uses: peter-evans/create-pull-request@v7
-        with:
-          branch: autoupdate-fwdb
-          commit-message: "update: fwdb from ${{ steps.diff.outputs.change }}, ${{ steps.diff.outputs.nbdiff }} microcode changes"
-          title: "[Auto] Update fwdb from ${{ steps.diff.outputs.change }}"
-          body: |
-            Automated PR to update fwdb from ${{ steps.diff.outputs.change }}
-            Detected ${{ steps.diff.outputs.nbdiff }} microcode changes
@@ -1,33 +0,0 @@
-name: 'Manage stale issues and PRs'
-
-on:
-  schedule:
-    - cron: '37 7 * * *'
-  workflow_dispatch:
-    inputs:
-      action:
-        description: "dry-run"
-        required: true
-        default: "dryrun"
-        type: choice
-        options:
-          - dryrun
-          - apply
-
-permissions:
-  issues: write
-  pull-requests: write
-
-jobs:
-  stale:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/stale@v10
-        with:
-          any-of-labels: 'needs-more-info,answered'
-          labels-to-remove-when-unstale: 'needs-more-info,answered'
-          days-before-stale: 30
-          days-before-close: 7
-          stale-issue-label: stale
-          remove-stale-when-updated: true
-          debug-only: ${{ case(inputs.action == 'dryrun', true, false) }}
@@ -1,190 +0,0 @@
-name: Online search for vulns
-
-on:
-  schedule:
-    - cron: '42 8 * * *'
-  workflow_dispatch:
-    inputs:
-      model:
-        description: 'Claude model to use (cron runs default to Sonnet)'
-        required: false
-        type: choice
-        default: claude-sonnet-4-6
-        options:
-          - claude-sonnet-4-6
-          - claude-opus-4-7
-          - claude-haiku-4-5-20251001
-      window_hours:
-        description: 'Lookback window in hours (cron runs use 25)'
-        required: false
-        type: string
-        default: '25'
-      reconsider_age_days:
-        description: 'Only reconsider backlog entries last reviewed ≥ N days ago (0 = all, default 7)'
-        required: false
-        type: string
-        default: '7'
-
-permissions:
-  contents: read
-  actions: read           # needed to list/download previous run artifacts
-  id-token: write         # needed by claude-code-action for OIDC auth
-
-concurrency:
-  group: vuln-watch
-  cancel-in-progress: true
-
-jobs:
-  watch:
-    runs-on: ubuntu-latest
-    timeout-minutes: 20
-
-    steps:
-      # The scripts driving this workflow live on the `vuln-watch` branch so
-      # they don't clutter master (which is what ships to production). The
-      # workflow file itself MUST stay on the default branch, as GitHub only
-      # honors `schedule:` triggers on the default branch.
-      - name: Checkout vuln-watch branch (scripts + prompt)
-        uses: actions/checkout@v5
-        with:
-          ref: vuln-watch
-          fetch-depth: 1
-          persist-credentials: false
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: '3.12'
-
-      - name: Install Python dependencies
-        run: python -m pip install --quiet feedparser
-
-      # ---- Load previous state ---------------------------------------------
-      # Find the most recent successful run of THIS workflow (other than the
-      # current one) and pull its `vuln-watch-state` artifact. On the very
-      # first run there will be none — that's fine, we start empty.
-      - name: Find previous successful run id
-        id: prev
-        env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: |
-          set -e
-          run_id=$(gh run list \
-            --workflow="${{ github.workflow }}" \
-            --status=success \
-            --limit 1 \
-            --json databaseId \
-            --jq '.[0].databaseId // empty')
-          echo "run_id=${run_id}" >> "$GITHUB_OUTPUT"
-          if [ -n "$run_id" ]; then
-            echo "Found previous successful run: $run_id"
-          else
-            echo "No previous successful run — starting from empty state."
-          fi
-
-      - name: Download previous state artifact
-        if: steps.prev.outputs.run_id != ''
-        uses: actions/download-artifact@v5
-        continue-on-error: true   # tolerate retention expiry
-        with:
-          name: vuln-watch-state
-          path: state/
-          run-id: ${{ steps.prev.outputs.run_id }}
-          github-token: ${{ secrets.GITHUB_TOKEN }}
-
-      # ---- Fetch + diff (token-free; runs every time) ---------------------
-      # Performs conditional GETs (ETag / If-Modified-Since) against every
-      # source, parses RSS/Atom/HTML, dedups against state.seen + state.aliases,
-      # applies the time-window filter, and emits new_items.json.
-      # Updates state.sources (HTTP cache metadata + per-source high-water
-      # marks) in place so the cache survives even when Claude doesn't run.
-      - name: Fetch + diff all sources
-        id: diff
-        env:
-          SCAN_DATE: ${{ github.run_started_at }}
-          # Cron runs have no `inputs` context, so the fallback kicks in.
-          WINDOW_HOURS:         ${{ inputs.window_hours || '25' }}
-          RECONSIDER_AGE_DAYS:  ${{ inputs.reconsider_age_days || '7' }}
-        run: python -m scripts.vuln_watch.fetch_and_diff
-
-      # ---- Fetch checker code so Claude can grep it for coverage ---------
-      # The orphan vuln-watch branch has none of the actual checker code,
-      # so we pull the `test` branch (the dev branch where coded-but-
-      # unreleased CVE checks live) into ./checker/. The prompt tells
-      # Claude this is the canonical source of truth for "is CVE-X already
-      # implemented?". Only fetched on days with something to classify.
-      - name: Checkout checker code (test branch) for coverage grep
-        if: steps.diff.outputs.new_count != '0' || steps.diff.outputs.reconsider_count != '0'
-        uses: actions/checkout@v5
-        with:
-          ref: test
-          path: checker
-          fetch-depth: 1
-          persist-credentials: false
-
-      # ---- Classify new items with Claude (skipped when nothing is new) ---
-      # Model selection: a manual workflow_dispatch run picks from a dropdown
-      # (defaulting to Sonnet). Scheduled cron runs have no `inputs` context,
-      # so the `|| 'claude-sonnet-4-6'` fallback kicks in — cron always uses
-      # Sonnet to keep the daily cost floor low.
-      - name: Run classifier with Claude
-        id: classify
-        if: steps.diff.outputs.new_count != '0' || steps.diff.outputs.reconsider_count != '0'
-        uses: anthropics/claude-code-action@v1
-        env:
-          SCAN_DATE: ${{ github.run_started_at }}
-        with:
-          prompt: |
-            Read the full task instructions from scripts/daily_vuln_watch_prompt.md
-            and execute them end-to-end. Your input is new_items.json (already
-            deduped, windowed, and pre-filtered — do NOT re-fetch sources).
-            Write the three watch_${TODAY}_*.md files and classifications.json.
-            Use $SCAN_DATE as the canonical timestamp.
-          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
-          # model + tool allowlist pass through claude_args (v1 dropped the
-          # dedicated `model:` and `allowed_tools:` inputs). Job-level
-          # `timeout-minutes: 20` above bounds total runtime.
-          claude_args: |
-            --model ${{ inputs.model || 'claude-sonnet-4-6' }}
-            --allowedTools "Read,Write,Edit,Bash,Grep,Glob,WebFetch"
-
-      - name: Upload Claude execution log
-        if: ${{ always() && steps.classify.outputs.execution_file != '' }}
-        uses: actions/upload-artifact@v5
-        with:
-          name: claude-execution-log-${{ github.run_id }}
-          path: ${{ steps.classify.outputs.execution_file }}
-          retention-days: 30
-          if-no-files-found: warn
-
-      # ---- Merge classifications back into state --------------------------
-      # Also writes stub watch_*.md files if the classify step was skipped, so
-      # the report artifact is consistent across runs.
-      - name: Merge classifications into state
-        if: always()
-        env:
-          SCAN_DATE: ${{ github.run_started_at }}
-        run: python -m scripts.vuln_watch.merge_state
-
-      - name: Upload new state artifact
-        if: always()
-        uses: actions/upload-artifact@v5
-        with:
-          name: vuln-watch-state
-          path: state/seen.json
-          retention-days: 90
-          if-no-files-found: error
-
-      - name: Upload daily report
-        if: always()
-        uses: actions/upload-artifact@v5
-        with:
-          name: vuln-watch-report-${{ github.run_id }}
-          path: |
-            watch_*.md
-            current_toimplement.md
-            current_tocheck.md
-            new_items.json
-            classifications.json
-          retention-days: 90
-          if-no-files-found: warn
@@ -13,7 +13,7 @@
 #
 # Stephane Lesimple
 #
-VERSION='26.36.0601873'
+VERSION='26.36.0602719'

 # --- Common paths and basedirs ---
 readonly VULN_SYSFS_BASE="/sys/devices/system/cpu/vulnerabilities"
@@ -3936,11 +3936,18 @@ parse_cpu_details() {
        # cpu_variant_list and cpu_revision_list are consumed by ARM64 errata affection checks
        # that need to match a specific revision range.
        if grep -q 'CPU implementer' "$g_procfs/cpuinfo"; then
-            cpu_impl_list=$(awk '/CPU implementer/ {print $4}' "$g_procfs/cpuinfo")
-            cpu_part_list=$(awk '/CPU part/         {print $4}' "$g_procfs/cpuinfo")
-            cpu_arch_list=$(awk '/CPU architecture/ {print $3}' "$g_procfs/cpuinfo")
-            cpu_variant_list=$(awk '/CPU variant/   {print $4}' "$g_procfs/cpuinfo")
-            cpu_revision_list=$(awk '/CPU revision/ {print $4}' "$g_procfs/cpuinfo")
+            # keep these single-line (space-separated) so consumers and outputs (JSON, prometheus)
+            # don't end up with embedded newlines; per-core order is preserved for the errata checks
+            cpu_impl_list=$(awk '/CPU implementer/ {print $4}' "$g_procfs/cpuinfo" | tr '\n' ' ')
+            cpu_impl_list=${cpu_impl_list% }
+            cpu_part_list=$(awk '/CPU part/         {print $4}' "$g_procfs/cpuinfo" | tr '\n' ' ')
+            cpu_part_list=${cpu_part_list% }
+            cpu_arch_list=$(awk '/CPU architecture/ {print $3}' "$g_procfs/cpuinfo" | tr '\n' ' ')
+            cpu_arch_list=${cpu_arch_list% }
+            cpu_variant_list=$(awk '/CPU variant/   {print $4}' "$g_procfs/cpuinfo" | tr '\n' ' ')
+            cpu_variant_list=${cpu_variant_list% }
+            cpu_revision_list=$(awk '/CPU revision/ {print $4}' "$g_procfs/cpuinfo" | tr '\n' ' ')
+            cpu_revision_list=${cpu_revision_list% }
        fi
        # Map first-seen implementer to cpu_vendor; note that heterogeneous systems
        # (e.g. DynamIQ with ARM+Kryo cores) would all map to one vendor here, but
@@ -5051,6 +5058,12 @@ check_kernel_info() {
    fi
 }

+# Collapse a whitespace-separated list to its unique values, preserving first-seen order.
+# Used to prettify the per-core ARM lists for display (e.g. "0x41 0x41 0x41 0x41" -> "0x41").
+_uniq_list() {
+    echo "$1" | awk '{ for (i = 1; i <= NF; i++) if (!seen[$i]++) printf "%s%s", (n++ ? " " : ""), $i }'
+}
+
 # Display hardware-level CPU mitigation support (microcode features, ARCH_CAPABILITIES, etc.)
 check_cpu() {
    local capabilities ret spec_ctrl_msr codename ucode_str
@@ -5060,13 +5073,13 @@ check_cpu() {
        pr_info "  * Vendor: $cpu_vendor"
        pr_info "  * Model name: $cpu_friendly_name"
        if [ -n "${cpu_impl_list:-}" ]; then
-            pr_info "  * Implementer(s): $cpu_impl_list"
+            pr_info "  * Implementer(s): $(_uniq_list "$cpu_impl_list")"
        fi
        if [ -n "${cpu_part_list:-}" ]; then
-            pr_info "  * Part(s): $cpu_part_list"
+            pr_info "  * Part(s): $(_uniq_list "$cpu_part_list")"
        fi
        if [ -n "${cpu_arch_list:-}" ]; then
-            pr_info "  * Architecture(s): $cpu_arch_list"
+            pr_info "  * Architecture(s): $(_uniq_list "$cpu_arch_list")"
        fi
        if has_runtime; then
            pr_info_nol "  * Running as VM guest: "