Panama/tests/setup/hardware-contract

#!/usr/bin/env bash

# What install-hardware does, and — more importantly — what it does not.
#
# This stage cannot be verified the way the rest of Panama is. It installs a
# proprietary driver, rewrites kernel arguments and queues a Secure Boot
# enrolment, and the machine it was written on is an AMD desktop with no NVIDIA
# card in it. Running it to see what happens is not available.
#
# So every privileged command it can reach is stood in on PATH, and the contract
# asserts what was called with what. That verifies the decisions — which answer
# leads to which command — which is the part that can be wrong. It does not
# verify that akmod-nvidia builds, and nothing here should be read as claiming it
# does.
#
# The properties worth pinning:
#
#   1. Absent answers do nothing at all. Every stage in this repository is
#      independently re-runnable while repairing one piece of a machine, and a
#      hardware stage that acted on its own defaults would be the one that
#      installed a driver nobody asked for.
#   2. The MOK password never appears in a command line or an environment. It is
#      hashed in the interview and reaches mokutil through a file, which is what
#      --generate-hash and --hash-file exist for.
#   3. Nothing opens an editor. sunhat stopped in the middle of a run so grub
#      could be hand-corrected, and that single step is why walking away from an
#      install did not work.
#   4. Removal is offered only for packages that are actually installed, and the
#      list has exactly one home.

set -uo pipefail

repo_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
stage="$repo_dir/setup/scripts/install-hardware"
interview="$repo_dir/setup/scripts/interview"

findings=()
note() { findings+=("$1"); }

[[ -x "$stage" ]] || { printf 'hardware contract: %s is not executable\n' "$stage" >&2; exit 1; }

work="$(mktemp -d)"
trap 'rm -rf "$work"' EXIT

# ── The stand-ins ────────────────────────────────────────────────────────────
#
# Each records its own name and arguments and succeeds. `sudo` records the
# command it was asked to run and then runs it through the same stubs, so a
# privileged call is visible whether or not it went through sudo.

stub_dir="$work/bin"
mkdir -p "$stub_dir"
calls="$work/calls"

for command in dnf grubby systemctl mokutil fwupdmgr rpm; do
    cat >"$stub_dir/$command" <<STUB
#!/usr/bin/env bash
printf '%s %s\n' "$command" "\$*" >>"\$PANAMA_CALLS"
exit \${STUB_${command^^}_STATUS:-0}
STUB
    chmod +x "$stub_dir/$command"
done

cat >"$stub_dir/sudo" <<'STUB'
#!/usr/bin/env bash
printf 'sudo %s\n' "$*" >>"$PANAMA_CALLS"
exec "$@"
STUB
chmod +x "$stub_dir/sudo"

# `rpm -q` decides what debloat has to work with, so it answers for exactly one
# package. Overrides the recording stub for that one query.
cat >"$stub_dir/rpm" <<'STUB'
#!/usr/bin/env bash
printf 'rpm %s\n' "$*" >>"$PANAMA_CALLS"
if [[ "${1:-}" == "-q" ]]; then
    [[ "${2:-}" == "${STUB_INSTALLED:-}" ]] && exit 0
    exit 1
fi
exit 0
STUB
chmod +x "$stub_dir/rpm"

# Runs the stage with the given answers and returns everything it invoked.
run_stage() {
    : >"$calls"
    env -i HOME="$HOME" PATH="$stub_dir:/usr/bin:/bin" PANAMA_CALLS="$calls" \
        STUB_INSTALLED="${STUB_INSTALLED:-}" STUB_DNF_STATUS="${STUB_DNF_STATUS:-0}" \
        "$@" bash "$stage" >/dev/null 2>&1
    cat "$calls"
}

called() { grep -q -- "$2" <<<"$1"; }

# ── 1. Nothing asked for, nothing done ───────────────────────────────────────

quiet="$(run_stage)"
if [[ -n "$quiet" ]]; then
    note "with no answers the stage still ran: $(head -1 <<<"$quiet")"
fi

# ── The NVIDIA path ──────────────────────────────────────────────────────────

nvidia="$(run_stage PANAMA_NVIDIA=yes)"

called "$nvidia" 'dnf install -y akmod-nvidia' \
    || note 'answering yes to NVIDIA does not install akmod-nvidia'
called "$nvidia" 'xorg-x11-drv-nvidia-cuda' \
    || note 'the CUDA driver is not installed alongside the kernel module'
called "$nvidia" 'grubby --update-kernel=ALL' \
    || note 'the kernel arguments are never set'
called "$nvidia" 'modprobe.blacklist=nouveau' \
    || note 'nouveau is not blacklisted, so it can bind the card before nvidia does'
called "$nvidia" 'nvidia-drm.modeset=1' \
    || note 'nvidia-drm.modeset is not set, which a Wayland session needs'
called "$nvidia" 'systemctl enable nvidia-hibernate.service' \
    || note 'the suspend and resume services are never enabled'

# A driver that failed to install must not be followed by arguments and services
# for a driver that is not there.
failed="$(STUB_DNF_STATUS=1 run_stage PANAMA_NVIDIA=yes)"
if called "$failed" 'grubby --update-kernel'; then
    note 'kernel arguments are set even when the driver failed to install'
fi

# ── 2. The MOK password stays out of sight ───────────────────────────────────

cert="$work/public_key.der"
printf 'not a real certificate\n' >"$cert"
hash='$6$notarealsalt$notarealhashvalue'

mok="$(run_stage PANAMA_MOK_HASH="$hash" PANAMA_MOK_CERT="$cert")"

called "$mok" 'mokutil --import' \
    || note 'a recorded MOK hash does not queue an enrolment'
called "$mok" -- '--hash-file' \
    || note 'the enrolment does not pass a hash file, so mokutil would prompt for a password'
if grep -qF -- "$hash" <<<"$mok"; then
    note 'the MOK hash is passed on a command line where any process can read it'
fi

# No certificate means akmods never generated a key. Requesting enrolment of a
# key that does not exist is worse than skipping: it queues a prompt at the next
# boot for nothing.
without_cert="$(run_stage PANAMA_MOK_HASH="$hash" PANAMA_MOK_CERT="$work/absent.der")"
if called "$without_cert" 'mokutil --import'; then
    note 'enrolment is requested even with no akmods certificate to enrol'
fi

# ── 4. Removal is honest about what it removes ───────────────────────────────

removable="$("$stage" --debloat-list)"
[[ -n "$removable" ]] || note '--debloat-list prints nothing, so the interview cannot name what it removes'

# Exactly one of them is installed, so exactly one may be passed to dnf.
present="$(head -1 <<<"$removable")"
absent="$(tail -1 <<<"$removable")"
debloat="$(STUB_INSTALLED="$present" run_stage PANAMA_DEBLOAT=yes)"

called "$debloat" "dnf remove -y $present" \
    || note "an installed package ($present) is not removed"
removal="$(grep 'dnf remove' <<<"$debloat")"
if grep -q -- "$absent" <<<"$removal"; then
    note "a package that is not installed ($absent) is still passed to dnf remove"
fi

# ── Firmware ─────────────────────────────────────────────────────────────────

firmware="$(run_stage PANAMA_FIRMWARE=yes)"
called "$firmware" 'fwupdmgr refresh' \
    || note 'firmware metadata is never refreshed'
called "$firmware" 'fwupdmgr update' \
    || note 'firmware updates are never applied'
called "$firmware" -- '--no-reboot-check' \
    || note 'the firmware update may reboot the machine in the middle of an install'

# ── 3. Nothing stops for a human ─────────────────────────────────────────────

if grep -qE 'sudoedit|EDITOR=|\bnvim\b|kitty .*-e|read -r? *-?p' "$stage"; then
    note 'the stage opens an editor or waits for input, which is the failure the interview exists to prevent'
fi

# The interview must ask for every answer this stage reads. The interview
# contract checks that in general; what it cannot check is that the two agree on
# the list itself, which is the coupling that breaks when a question is renamed.
for key in PANAMA_NVIDIA PANAMA_MOK_HASH PANAMA_DEBLOAT PANAMA_FIRMWARE; do
    grep -q "record $key " "$interview" \
        || note "install-hardware reads $key, but the interview never records it"
done

# ── Report ───────────────────────────────────────────────────────────────────

if (( ${#findings[@]} > 0 )); then
    printf 'hardware contract: %d finding(s)\n' "${#findings[@]}" >&2
    printf '  - %s\n' "${findings[@]}" >&2
    exit 1
fi

printf 'hardware contract: PASS\n'