Files
tomswall/internal/agent/agent.go
T
benvin e0f54ef320 Add tomswall agent (control-plane pull mode)
Add `tomswall agent`: it pulls this device's compiled config from tomswallapi,
differentially applies it, and reports the applied generation. It caches the
last known-good config and, when the control plane is unreachable, keeps
applying that cache — it never fails closed.

- internal/agent: rendered-config types, HTTP client (fetch + status report),
  on-disk cache, on-device DNS resolver for dns sets (honors the device's
  configured resolver, fail-safe on lookup failure), and the pull-apply-report
  loop behind a mockable Applier.
- Translate the interface-agnostic, address-matched rendered model into native
  tomswall config using the "all:<cidr>" any-interface source/dest form, reusing
  the existing differential engine. Named-set members are inlined as concrete
  addresses (native nft set references are a tracked follow-up).
- cmd/tomswall: wire the `agent` subcommand (flags + TOMSWALL_* env, --once).
- Unit tests: translation, cache, and the don't-fail-closed fallback loop.
- Add DESIGN.md documenting the control-plane architecture.
2026-07-20 20:05:49 +10:00

115 lines
3.1 KiB
Go

package agent
import (
"context"
"fmt"
"log/slog"
"time"
"git.unkin.net/unkin/tomswall/internal/config"
"git.unkin.net/unkin/tomswall/internal/nftables"
)
// Applier applies a translated config to the firewall. Abstracted so the run
// loop is testable without touching the kernel.
type Applier interface {
Apply(ctx context.Context, cfg *config.Config) error
}
// Agent runs the pull-apply-report loop for one device.
type Agent struct {
Client *Client
Cache Cache
Interval time.Duration
Applier Applier
// Resolver overrides the DNS resolver (tests); nil derives it per-config.
Resolver *Resolver
}
// Run loops until ctx is cancelled, applying one cycle per Interval (and once
// immediately). A failed cycle is logged and retried on the next tick — the loop
// never exits on transient errors.
func (a *Agent) Run(ctx context.Context) error {
if a.Interval <= 0 {
a.Interval = time.Minute
}
t := time.NewTicker(a.Interval)
defer t.Stop()
for {
if err := a.RunOnce(ctx); err != nil {
slog.Error("agent: apply cycle failed", "err", err)
}
select {
case <-ctx.Done():
return ctx.Err()
case <-t.C:
}
}
}
// RunOnce performs a single pull-apply-report cycle. On a fetch failure it falls
// back to the on-disk cache and re-applies it — it never fails closed.
func (a *Agent) RunOnce(ctx context.Context) error {
rc, raw, err := a.Client.FetchConfig(ctx)
if err != nil {
slog.Warn("agent: control plane unreachable, using cached config", "err", err)
cached, cerr := a.Cache.Read()
if cerr != nil {
return fmt.Errorf("read cache: %w", cerr)
}
if cached == nil {
return fmt.Errorf("control plane unreachable and no cached config: %w", err)
}
// Re-apply last known-good; do not report a generation we didn't fetch.
return a.applyConfig(ctx, cached, false)
}
if err := a.Cache.Write(raw); err != nil {
slog.Warn("agent: caching config failed", "err", err)
}
return a.applyConfig(ctx, rc, true)
}
func (a *Agent) applyConfig(ctx context.Context, rc *RenderedConfig, report bool) error {
resolver := a.Resolver
if resolver == nil {
resolver = NewResolver(rc.Resolver)
}
resolver.ExpandDNSSets(ctx, rc)
cfg, err := Translate(rc)
if err != nil {
return fmt.Errorf("translate: %w", err)
}
if err := a.Applier.Apply(ctx, cfg); err != nil {
return fmt.Errorf("apply: %w", err)
}
slog.Info("agent: applied config", "generation", rc.Generation, "rules", len(cfg.Rules))
if report {
if err := a.Client.ReportStatus(ctx, rc.Generation); err != nil {
slog.Warn("agent: reporting status failed", "err", err)
}
}
return nil
}
// EngineApplier applies via the real nftables differential engine.
type EngineApplier struct{}
// Apply computes and applies the differential change set for cfg.
func (EngineApplier) Apply(_ context.Context, cfg *config.Config) error {
engine, err := nftables.NewEngine(cfg)
if err != nil {
return fmt.Errorf("initializing nftables: %w", err)
}
changes, err := engine.Plan()
if err != nil {
return fmt.Errorf("computing changes: %w", err)
}
if changes.Empty() {
return nil
}
return engine.Apply(changes)
}