Retry pinned BusyBox fetches (#554)

qemu/lib.sh

@@ -22,15 +22,34 @@ qemu_get_busybox() {
     echo "FATAL: no pinned sha256 for busybox (expected $sha_file): refusing to build from an unverified binary" >&2
     exit 1
   }
-  if [ ! -f "$BB" ]; then
-    qemu_log "downloading $BB_URL"
-    curl --retry 3 --retry-delay 5 --retry-connrefused -fSL "$BB_URL" -o "$BB"
-  fi
   local want got
   want="$(cat "$sha_file")"
-  got="$(sha256sum "$BB" | awk '{print $1}')"
-  [ "$want" = "$got" ] || { echo "busybox sha256 mismatch: want $want got $got" >&2; exit 1; }
-  qemu_log "busybox sha256 verified"
+  if [ -f "$BB" ]; then
+    got="$(sha256sum "$BB" | awk '{print $1}')"
+    if [ "$want" = "$got" ]; then
+      qemu_log "busybox sha256 verified"
+      return
+    fi
+    qemu_log "cached busybox failed verification; fetching a clean copy"
+  fi
+
+  local attempt tmp="${BB}.download.$$"
+  rm -f "$tmp"
+  for attempt in 1 2 3; do
+    qemu_log "downloading $BB_URL (attempt $attempt/3)"
+    if curl --retry 3 --retry-delay 5 --retry-connrefused -fSL "$BB_URL" -o "$tmp"; then
+      got="$(sha256sum "$tmp" | awk '{print $1}')"
+      if [ "$want" = "$got" ]; then
+        mv -f "$tmp" "$BB"
+        qemu_log "busybox sha256 verified"
+        return
+      fi
+      echo "busybox sha256 mismatch on attempt $attempt: want $want got $got" >&2
+    fi
+    rm -f "$tmp"
+  done
+  echo "FATAL: could not fetch pinned busybox after 3 verified attempts" >&2
+  exit 1
 }
 
 # Stage the shared rootfs skeleton (qemu/rootfs/ + busybox) into $1.

qemu/tests/busybox-fetch.sh

@@ -0,0 +1,72 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+TEST_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+QEMU_DIR="$(cd "$TEST_DIR/.." && pwd)"
+SCRATCH="$(mktemp -d "${TMPDIR:-/tmp}/busybox-fetch.XXXXXX")"
+trap 'rm -rf "$SCRATCH"' EXIT
+
+FAKE_BIN="$SCRATCH/bin"
+FAKE_CURL_COUNT="$SCRATCH/curl-count"
+mkdir -p "$FAKE_BIN" "$SCRATCH/qemu"
+printf 'good payload' > "$SCRATCH/good"
+sha256sum "$SCRATCH/good" | awk '{print $1}' > "$SCRATCH/qemu/busybox.sha256"
+
+FAKE_CURL="$FAKE_BIN/curl"
+apply_fake_curl() {
+  chmod 0755 "$FAKE_CURL"
+  export PATH="$FAKE_BIN:$PATH"
+  export FAKE_CURL_COUNT FAKE_CURL_MODE
+}
+
+# The path is resolved at runtime from this file's location.
+# shellcheck disable=SC1091
+source "$QEMU_DIR/lib.sh"
+QEMU_DIR="$SCRATCH/qemu"
+# Read by qemu_get_busybox from the sourced helper.
+# shellcheck disable=SC2034
+BB_URL="https://invalid.example/busybox"
+
+# These single-quoted lines are the literal source of the fake curl program.
+# shellcheck disable=SC2016
+printf '%s\n' '#!/bin/sh' \
+  'count=0' \
+  '[ ! -f "$FAKE_CURL_COUNT" ] || count=$(cat "$FAKE_CURL_COUNT")' \
+  'count=$((count + 1))' \
+  'printf "%s\n" "$count" > "$FAKE_CURL_COUNT"' \
+  'out=' \
+  'while [ "$#" -gt 0 ]; do' \
+  '  if [ "$1" = "-o" ]; then shift; out="$1"; fi' \
+  '  shift' \
+  'done' \
+  '[ -n "$out" ] || exit 2' \
+  'if [ "$FAKE_CURL_MODE" = "flaky" ] && [ "$count" -gt 1 ]; then' \
+  '  printf "good payload" > "$out"' \
+  'else' \
+  '  printf "bad payload" > "$out"' \
+  'fi' > "$FAKE_CURL"
+
+FAKE_CURL_MODE=flaky
+apply_fake_curl
+OUT="$SCRATCH/flaky" qemu_get_busybox
+test "$(cat "$FAKE_CURL_COUNT")" = 2
+test "$(sha256sum "$BB" | awk '{print $1}')" = "$(cat "$QEMU_DIR/busybox.sha256")"
+
+printf '0\n' > "$FAKE_CURL_COUNT"
+FAKE_CURL_MODE=bad
+apply_fake_curl
+if (OUT="$SCRATCH/always-bad" qemu_get_busybox) >"$SCRATCH/failure.log" 2>&1; then
+  echo "FAIL: an unverified download was accepted" >&2
+  exit 1
+fi
+test "$(cat "$FAKE_CURL_COUNT")" = 3
+test ! -e "$SCRATCH/always-bad/busybox-armv7l"
+grep -q 'after 3 verified attempts' "$SCRATCH/failure.log"
+
+printf '0\n' > "$FAKE_CURL_COUNT"
+mkdir -p "$SCRATCH/cached"
+cp "$SCRATCH/good" "$SCRATCH/cached/busybox-armv7l"
+OUT="$SCRATCH/cached" qemu_get_busybox
+test "$(cat "$FAKE_CURL_COUNT")" = 0
+
+echo "busybox fetch tests passed"