port smoke to go

Makefile

@@ -25,7 +25,6 @@ SMOKE_DIR := $(BUILD_DIR)/smoke
 SMOKE_BIN_DIR := $(SMOKE_DIR)/bin
 SMOKE_COVER_DIR := $(SMOKE_DIR)/covdata
 SMOKE_XDG_DIR := $(SMOKE_DIR)/xdg
-SMOKE_SCRIPT := scripts/smoke.sh
 VERSION ?= $(shell git describe --tags --exact-match 2>/dev/null || echo dev)
 COMMIT ?= $(shell git rev-parse --verify HEAD 2>/dev/null || echo unknown)
 BUILT_AT ?= $(shell date -u +%Y-%m-%dT%H:%M:%SZ)
@@ -61,9 +60,9 @@ help:
 	  '  make tidy            Run go mod tidy' \
 	  '  make clean           Remove built Go binaries and coverage artefacts' \
 	  '  make smoke           Build instrumented binaries, run the supported systemd smoke suite, report coverage (needs KVM + sudo)' \
-	  '  make smoke JOBS=N    Override parallelism (default: nproc, capped at 8 by the script). JOBS=1 forces serial.' \
-	  '  make smoke-list      Print the list of smoke scenarios with descriptions (no build, no install)' \
-	  '  make smoke-one SCENARIO=NAME  Run a single smoke scenario (still does the install preamble)' \
+	  '  make smoke JOBS=N    Override parallelism (default: nproc, capped at 8). JOBS=1 forces serial.' \
+	  '  make smoke-list      Print the list of smoke scenarios (no build, no install)' \
+	  '  make smoke-one SCENARIO=NAME  Run a single smoke scenario (still does the install preamble; comma-separated for several)' \
 	  '  make smoke-fresh     smoke-clean + smoke — purges stale smoke-owned installs before a clean supported-path run' \
 	  '  make smoke-coverage-html  HTML coverage report from the last smoke run' \
 	  '  make smoke-clean     Remove the smoke build tree and purge any stale smoke-owned system install' \
@@ -164,17 +163,17 @@ clean:
 
 # Smoke test suite. Builds the three banger binaries with -cover
 # instrumentation under $(SMOKE_BIN_DIR), installs them as temporary
-# bangerd.service + bangerd-root.service, runs scripts/smoke.sh, copies
-# service covdata out of /var/lib/banger, then purges the smoke-owned
-# install on exit.
+# bangerd.service + bangerd-root.service, runs the Go scenarios under
+# internal/smoketest (built with -tags=smoke), copies service covdata
+# out of /var/lib/banger, then purges the smoke-owned install on exit.
 #
-# Unlike the old per-user daemon path, this touches global systemd
-# state. The smoke script refuses to overwrite a pre-existing non-smoke
-# install and uses a marker file so `make smoke-clean` can recover a
-# stale smoke-owned install after an interrupted run.
+# This touches global systemd state. The harness refuses to overwrite a
+# pre-existing non-smoke install and drops a marker file under
+# /etc/banger so `make smoke-clean` can recover a stale smoke-owned
+# install after an interrupted run.
 #
 # Requires a KVM-capable Linux host with sudo. This is a pre-release
-# gate, not CI — the Go test suite is what runs everywhere.
+# gate, not CI — the Go unit suite (`make test`) is what runs everywhere.
 smoke-build: $(SMOKE_BIN_DIR)/.built
 
 $(SMOKE_BIN_DIR)/.built: $(BUILD_INPUTS) go.mod go.sum
@@ -184,10 +183,11 @@ $(SMOKE_BIN_DIR)/.built: $(BUILD_INPUTS) go.mod go.sum
 	CGO_ENABLED=0 GOOS=linux GOARCH=amd64 $(GO) build -ldflags '$(GO_LDFLAGS)' -o "$(SMOKE_BIN_DIR)/banger-vsock-agent" ./cmd/banger-vsock-agent
 	touch "$@"
 
-# JOBS defaults to nproc (the script caps at 8). Override with
-# `make smoke JOBS=1` for a fully serial run, or any specific N for
-# tighter parallelism.
+# JOBS defaults to nproc; SMOKE_JOBS clamps it at 8. Each parallel slot
+# runs a smoke-tuned VM, and over-subscribing the host pushes
+# waitForSSH past its 60s deadline. Floored at 1 so JOBS=1 still works.
 JOBS ?= $(shell nproc 2>/dev/null || echo 1)
+SMOKE_JOBS := $(shell n=$(JOBS); [ $$n -lt 1 ] && n=1; [ $$n -gt 8 ] && n=8; echo $$n)
 
 smoke: smoke-build
 	rm -rf "$(SMOKE_COVER_DIR)"
@@ -195,27 +195,31 @@ smoke: smoke-build
 	BANGER_SMOKE_BIN_DIR="$(abspath $(SMOKE_BIN_DIR))" \
 	BANGER_SMOKE_COVER_DIR="$(abspath $(SMOKE_COVER_DIR))" \
 	BANGER_SMOKE_XDG_DIR="$(abspath $(SMOKE_XDG_DIR))" \
-	  bash "$(SMOKE_SCRIPT)" --jobs $(JOBS)
+	  $(GO) test -tags=smoke -count=1 -v -parallel $(SMOKE_JOBS) -timeout 30m ./internal/smoketest
 	@echo ''
 	@echo 'Smoke coverage:'
 	@$(GO) tool covdata percent -i="$(SMOKE_COVER_DIR)"
 
-# smoke-list is intentionally cheap: no smoke-build dep, no env vars.
-# The script's --list path short-circuits before any side-effect or
-# env validation, so this works on a fresh checkout.
+# smoke-list parses the test scaffold for scenario names. Cheap: no
+# smoke-build dep, no env vars, no test binary spawned.
 smoke-list:
-	@bash "$(SMOKE_SCRIPT)" --list
+	@grep -oE 't\.Run\("[a-z_]+", *test[A-Za-z]+\)' internal/smoketest/smoke_test.go \
+	  | sed -E 's/t\.Run\("([a-z_]+)".*/  \1/'
+
+# smoke-one runs one scenario (or a comma-separated list) with the
+# install preamble. Comma list becomes a regex alternation so multiple
+# scenarios can be selected without invoking go test by hand.
+SCENARIO_PATTERN := $(shell echo '$(SCENARIO)' | tr ',' '|')
 
-# smoke-one runs one scenario (or a comma-separated list) with the same
-# install preamble as the full suite. Useful when iterating on a specific
-# scenario — see `make smoke-list` for names.
 smoke-one: smoke-build
 	rm -rf "$(SMOKE_COVER_DIR)"
 	mkdir -p "$(SMOKE_COVER_DIR)" "$(SMOKE_XDG_DIR)"
 	BANGER_SMOKE_BIN_DIR="$(abspath $(SMOKE_BIN_DIR))" \
 	BANGER_SMOKE_COVER_DIR="$(abspath $(SMOKE_COVER_DIR))" \
 	BANGER_SMOKE_XDG_DIR="$(abspath $(SMOKE_XDG_DIR))" \
-	  bash "$(SMOKE_SCRIPT)" --scenario "$(SCENARIO)"
+	  $(GO) test -tags=smoke -count=1 -v -timeout 30m \
+	    -run "TestSmoke/.*/($(SCENARIO_PATTERN))$$" \
+	    ./internal/smoketest
 
 smoke-coverage-html: smoke
 	$(GO) tool covdata textfmt -i="$(SMOKE_COVER_DIR)" -o="$(SMOKE_DIR)/cover.out"