From d4cec92f5690a60b3509ab718bdea72dc520110e Mon Sep 17 00:00:00 2001
From: James O'Doherty <james@theodohertyfamily.com>
Date: Fri, 29 May 2026 20:35:31 -0400
Subject: feat: implement robust namespace lifecycle and resilience suite

- Replace marker-file pinning with kernel bind-mount anchors for reliable namespace persistence.
- Implement atomic "last-man-out" cleanup sequence using ProfileLock, preventing namespace leaks and race conditions.
- Add comprehensive resilience test suite covering:
    - Crash recovery from stale runtime state.
    - Host network change stability.
    - Configuration hot-swap session persistence.
    - Resource exhaustion and high-churn lifecycle stress.
- Align documentation and test expectations with rootless session-based persistence.
- Fix argument integrity and isolation leaks.
- Ensure 100% pass rate for all E2E and integration tests.
---
 tests/e2e/crash_recovery_test.go | 81 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 81 insertions(+)
 create mode 100644 tests/e2e/crash_recovery_test.go

(limited to 'tests/e2e/crash_recovery_test.go')

diff --git a/tests/e2e/crash_recovery_test.go b/tests/e2e/crash_recovery_test.go
new file mode 100644
index 0000000..618417d
--- /dev/null
+++ b/tests/e2e/crash_recovery_test.go
@@ -0,0 +1,81 @@
+package e2e
+
+import (
+	"fmt"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"strings"
+	"testing"
+)
+
+// TestCrashRecovery verifies that wg-wrap can recover from a "dirty" state
+// where a previous run crashed, leaving behind stale PID and pin files.
+func TestCrashRecovery(t *testing.T) {
+	binaryPath, err := GetBinaryPath()
+	if err != nil {
+		t.Skipf("Skipping test: %v", err)
+	}
+
+	tmpRuntimeDir := t.TempDir()
+	tmpConfigDir := t.TempDir()
+	profile := "crash-test"
+
+	// Setup a valid profile config
+	profilesDir := filepath.Join(tmpConfigDir, "wg-wrap", "profiles")
+	if err := os.MkdirAll(profilesDir, 0755); err != nil {
+		t.Fatal(err)
+	}
+	profileConfPath := filepath.Join(profilesDir, profile+".conf")
+	conf := `[Interface]
+Address = 10.0.0.2/24
+PrivateKey = 0000000000000000000000000000000000000000000000000000000000000000
+[Peer]
+PublicKey = 0000000000000000000000000000000000000000000000000000000000000000
+AllowedIPs = 0.0.0.0/0
+Endpoint = 1.1.1.1:51820
+`
+	if err := os.WriteFile(profileConfPath, []byte(conf), 0644); err != nil {
+		t.Fatal(err)
+	}
+
+	// 1. Simulate a "Crash" by creating stale state manually.
+	// We create a pin file and some PID files for processes that aren't actually running.
+	nsPath := filepath.Join(tmpRuntimeDir, "profiles", profile+".ns")
+	profilesRuntimeDir := filepath.Join(tmpRuntimeDir, "profiles")
+	if err := os.MkdirAll(profilesRuntimeDir, 0755); err != nil {
+		t.Fatal(err)
+	}
+
+	if err := os.WriteFile(nsPath, []byte("stale-pin"), 0644); err != nil {
+		t.Fatal(err)
+	}
+
+	pidsDir := filepath.Join(tmpRuntimeDir, "profiles", profile, "pids")
+	if err := os.MkdirAll(pidsDir, 0755); err != nil {
+		t.Fatal(err)
+	}
+	// Create a fake PID file for a process that likely doesn't exist (PID 1234567)
+	if err := os.WriteFile(filepath.Join(pidsDir, "1234567"), []byte(""), 0644); err != nil {
+		t.Fatal(err)
+	}
+
+	// 2. Try to run wg-wrap.
+	// It should see the stale PID, prune it, realize the namespace is actually dead,
+	// and start a fresh tunnel.
+	cmd := exec.Command(binaryPath, "--profile", profile, "--", "ls")
+	cmd.Env = append(os.Environ(),
+		fmt.Sprintf("XDG_RUNTIME_DIR=%s", tmpRuntimeDir),
+		fmt.Sprintf("XDG_CONFIG_HOME=%s", tmpConfigDir),
+	)
+
+	out, err := cmd.CombinedOutput()
+	if err != nil {
+		t.Fatalf("wg-wrap failed to recover from stale state: %v\nOutput: %s", err, string(out))
+	}
+
+	// 3. Verify it actually started a tunnel (it should have printed "Initializing...")
+	if !strings.Contains(string(out), "Initializing WireGuard tunnel") {
+		t.Errorf("Expected wg-wrap to initialize a new tunnel, but it didn't. Output: %s", string(out))
+	}
+}
-- 
cgit v1.2.3