egress-proxies-operator/internal/provider/kvm/seed.go

package kvm

import (
	"bytes"
	"fmt"
	"reflect"
	"strings"

	"github.com/kdomanski/iso9660"
	"sigs.k8s.io/yaml"
)

// seedLabel is the volume label cloud-init's NoCloud datasource looks for.
const seedLabel = "cidata"

const (
	cloudConfigHeader = "#cloud-config"
	guestAgentPackage = "qemu-guest-agent"
)

// guestAgentEnable is the runcmd entry that starts the agent once it is
// installed, so the provider can read the VM's IP before ARP sees traffic.
var guestAgentEnable = []any{"systemctl", "enable", "--now", guestAgentPackage}

// guestAgentVendorData is the same bootstrap as a standalone cloud-config.
// It is only used as vendor-data when the Proxy's user-data is not a
// cloud-config document (a shell script, a MIME archive, an #include), i.e.
// when there are no top-level keys for it to collide with.
const guestAgentVendorData = cloudConfigHeader + `
packages:
  - qemu-guest-agent
runcmd:
  - [systemctl, enable, --now, qemu-guest-agent]
`

// withGuestAgent decides where the guest-agent bootstrap goes and returns
// the user-data and vendor-data to put on the seed.
//
// It cannot simply ride along as vendor-data: cloud-init merges vendor-data
// under user-data with its default mergers, which keep the user-data's
// value for any key both define and never append lists. A Proxy whose
// cloud-config has its own `packages:` (most do) would silently lose the
// agent and sit in Provisioning forever. So for a cloud-config user-data
// the bootstrap is merged into the document itself: `qemu-guest-agent`
// appended to `packages`, the enable command to `runcmd`, both skipped
// when already present. Anything the operator cannot parse as a
// cloud-config mapping is an error — cloud-init would reject it too, and a
// VM that boots without its config is harder to diagnose than a Proxy that
// fails fast.
func withGuestAgent(userData, vendorData string) (string, string, error) {
	if !isCloudConfig(userData) {
		if vendorData == "" {
			vendorData = guestAgentVendorData
		}
		return userData, vendorData, nil
	}
	var cfg map[string]any
	if err := yaml.Unmarshal([]byte(userData), &cfg); err != nil {
		return "", "", fmt.Errorf("parsing cloud-config user-data: %w", err)
	}
	if cfg == nil {
		cfg = map[string]any{}
	}
	pkgs, err := appendUnique(cfg, "packages", guestAgentPackage)
	if err != nil {
		return "", "", err
	}
	cfg["packages"] = pkgs
	cmds, err := appendUnique(cfg, "runcmd", guestAgentEnable)
	if err != nil {
		return "", "", err
	}
	cfg["runcmd"] = cmds
	out, err := yaml.Marshal(cfg)
	if err != nil {
		return "", "", fmt.Errorf("rendering cloud-config user-data: %w", err)
	}
	return cloudConfigHeader + "\n" + string(out), vendorData, nil
}

// isCloudConfig reports whether userData is a cloud-config document by
// cloud-init's own rule: the first line is the #cloud-config header. Empty
// user-data counts, so a Proxy without cloud-init still gets the agent.
func isCloudConfig(userData string) bool {
	if strings.TrimSpace(userData) == "" {
		return true
	}
	first, _, _ := strings.Cut(userData, "\n")
	return strings.TrimSpace(first) == cloudConfigHeader
}

// appendUnique returns cfg[key] with item appended unless an equal entry
// is already there. A missing key is an empty list; anything but a list is
// an error, since cloud-init expects one there as well.
func appendUnique(cfg map[string]any, key string, item any) ([]any, error) {
	var items []any
	switch v := cfg[key].(type) {
	case nil:
	case []any:
		items = v
	default:
		return nil, fmt.Errorf("cloud-config %s: want a list, got %T", key, v)
	}
	for _, it := range items {
		if reflect.DeepEqual(it, item) {
			return items, nil
		}
	}
	return append(items, item), nil
}

// buildSeedISO renders a NoCloud seed: user-data and vendor-data verbatim,
// and a meta-data whose instance-id is the deterministic VM name, so
// cloud-init never mistakes a reboot for a new instance. The ISO's volume
// descriptor carries the build time, so two builds differ in a few
// timestamp bytes; the files and label are identical.
func buildSeedISO(name, userData, vendorData string) ([]byte, error) {
	w, err := iso9660.NewWriter()
	if err != nil {
		return nil, fmt.Errorf("creating iso writer: %w", err)
	}
	defer w.Cleanup() //nolint:errcheck // temp-dir cleanup; nothing to do on failure

	files := []struct{ name, body string }{
		{"user-data", userData},
		{"meta-data", fmt.Sprintf("instance-id: %s\nlocal-hostname: %s\n", name, name)},
		{"vendor-data", vendorData},
	}
	for _, f := range files {
		if err := w.AddFile(strings.NewReader(f.body), f.name); err != nil {
			return nil, fmt.Errorf("adding %s to seed iso: %w", f.name, err)
		}
	}
	var buf bytes.Buffer
	if err := w.WriteTo(&buf, seedLabel); err != nil {
		return nil, fmt.Errorf("writing seed iso: %w", err)
	}
	return buf.Bytes(), nil
}