health: begin work to use structured health warnings instead of strings, pipe changes into ipn.Notify (#12406)

Updates tailscale/tailscale#4136

This PR is the first round of work to move from encoding health warnings as strings and use structured data instead. The current health package revolves around the idea of Subsystems. Each subsystem can have (or not have) a Go error associated with it. The overall health of the backend is given by the concatenation of all these errors.

This PR polishes the concept of Warnable introduced by @bradfitz a few weeks ago. Each Warnable is a component of the backend (for instance, things like 'dns' or 'magicsock' are Warnables). Each Warnable has a unique identifying code. A Warnable is an entity we can warn the user about, by setting (or unsetting) a WarningState for it. Warnables have:

- an identifying Code, so that the GUI can track them as their WarningStates come and go
- a Title, which the GUIs can use to tell the user what component of the backend is broken
- a Text, which is a function that is called with a set of Args to generate a more detailed error message to explain the unhappy state

Additionally, this PR also begins to send Warnables and their WarningStates through LocalAPI to the clients, using ipn.Notify messages. An ipn.Notify is only issued when a warning is added or removed from the Tracker.

In a next PR, we'll get rid of subsystems entirely, and we'll start using structured warnings for all errors affecting the backend functionality.

Signed-off-by: Andrea Gottardo <andrea@gottardo.me>

wgengine/router/ifconfig_windows.go

@@ -14,17 +14,18 @@ import (
 	"sort"
 	"time"
 
-	ole "github.com/go-ole/go-ole"
-	"github.com/tailscale/wireguard-go/tun"
-	"go4.org/netipx"
-	"golang.org/x/sys/windows"
-	"golang.zx2c4.com/wireguard/windows/tunnel/winipcfg"
 	"tailscale.com/health"
 	"tailscale.com/net/netmon"
 	"tailscale.com/net/tsaddr"
 	"tailscale.com/net/tstun"
 	"tailscale.com/util/multierr"
 	"tailscale.com/wgengine/winnet"
+
+	ole "github.com/go-ole/go-ole"
+	"github.com/tailscale/wireguard-go/tun"
+	"go4.org/netipx"
+	"golang.org/x/sys/windows"
+	"golang.zx2c4.com/wireguard/windows/tunnel/winipcfg"
 )
 
 // monitorDefaultRoutes subscribes to route change events and updates
@@ -235,9 +236,17 @@ func interfaceFromLUID(luid winipcfg.LUID, flags winipcfg.GAAFlags) (*winipcfg.I
 	return nil, fmt.Errorf("interfaceFromLUID: interface with LUID %v not found", luid)
 }
 
-var networkCategoryWarning = health.NewWarnable(health.WithMapDebugFlag("warn-network-category-unhealthy"))
+var networkCategoryWarnable = health.Register(&health.Warnable{
+	Code:     "set-network-category-failed",
+	Severity: health.SeverityMedium,
+	Title:    "Windows network configuration failed",
+	Text: func(args health.Args) string {
+		return fmt.Sprintf("Failed to set the network category to private on the Tailscale adapter. This may prevent Tailscale from working correctly. Error: %s", args[health.ArgError])
+	},
+	MapDebugFlag: "warn-network-category-unhealthy",
+})
 
-func configureInterface(cfg *Config, tun *tun.NativeTun, health *health.Tracker) (retErr error) {
+func configureInterface(cfg *Config, tun *tun.NativeTun, ht *health.Tracker) (retErr error) {
 	var mtu = tstun.DefaultTUNMTU()
 	luid := winipcfg.LUID(tun.LUID())
 	iface, err := interfaceFromLUID(luid,
@@ -268,10 +277,10 @@ func configureInterface(cfg *Config, tun *tun.NativeTun, health *health.Tracker)
 		for i := range tries {
 			found, err := setPrivateNetwork(luid)
 			if err != nil {
-				health.SetWarnable(networkCategoryWarning, fmt.Errorf("set-network-category: %w", err))
+				ht.SetUnhealthy(networkCategoryWarnable, health.Args{health.ArgError: err.Error()})
 				log.Printf("setPrivateNetwork(try=%d): %v", i, err)
 			} else {
-				health.SetWarnable(networkCategoryWarning, nil)
+				ht.SetHealthy(networkCategoryWarnable)
 				if found {
 					if i > 0 {
 						log.Printf("setPrivateNetwork(try=%d): success", i)

wgengine/router/router_linux.go

@@ -445,12 +445,17 @@ func (r *linuxRouter) Set(cfg *Config) error {
 	return multierr.New(errs...)
 }
 
-var warnStatefulFilteringWithDocker = health.NewWarnable()
+var dockerStatefulFilteringWarnable = health.Register(&health.Warnable{
+	Code:     "docker-stateful-filtering",
+	Title:    "Docker with stateful filtering",
+	Severity: health.SeverityMedium,
+	Text:     health.StaticMessage("Stateful filtering is enabled and Docker was detected; this may prevent Docker containers on this host from resolving DNS and connecting to Tailscale nodes. See https://tailscale.com/s/stateful-docker"),
+})
 
 func (r *linuxRouter) updateStatefulFilteringWithDockerWarning(cfg *Config) {
 	// If stateful filtering is disabled, clear the warning.
 	if !r.statefulFiltering {
-		r.health.SetWarnable(warnStatefulFilteringWithDocker, nil)
+		r.health.SetHealthy(dockerStatefulFilteringWarnable)
 		return
 	}
 
@@ -479,17 +484,13 @@ func (r *linuxRouter) updateStatefulFilteringWithDockerWarning(cfg *Config) {
 		// socket/daemon/etc.
 		ifstate := r.netMon.InterfaceState()
 		if _, found := ifstate.Interface["docker0"]; found {
-			r.health.SetWarnable(warnStatefulFilteringWithDocker, fmt.Errorf(""+
-				"Stateful filtering is enabled and Docker was detected; this may prevent Docker containers "+
-				"on this host from resolving DNS and connecting to Tailscale nodes. "+
-				"See https://tailscale.com/s/stateful-docker",
-			))
+			r.health.SetUnhealthy(dockerStatefulFilteringWarnable, nil)
 			return
 		}
 	}
 
 	// If we get here, then we have no warnings; clear anything existing.
-	r.health.SetWarnable(warnStatefulFilteringWithDocker, nil)
+	r.health.SetHealthy(dockerStatefulFilteringWarnable)
 }
 
 // UpdateMagicsockPort implements the Router interface.