Files
usb-server/internal/relay/hub.go
T
duffyduckandClaude Opus 5 9ed473a965 Fix HID transfers, harden the tunnel, add E2E crypto and direct peers
The HID failure came down to the endpoint type map being indexed by
endpoint number without the direction bit. A composite device can have
endpoint 1 as both interrupt IN (0x81) and bulk OUT (0x01); the last one
read won, so interrupt URBs were submitted as bulk and the kernel rejected
them. The device attached and stayed silent.

Endpoint data now comes from the raw descriptors read from /dev/bus/usb
rather than sysfs, which only ever exposes the active alternate setting —
a webcam's isochronous endpoints are invisible there because they only
exist after SET_INTERFACE. Two sysfs parsing bugs fell out of that too:
the numeric endpoint attributes are hex without a prefix (wMaxPacketSize
"0040" was read as 40, not 64), and bInterval was never read at all.

Reliability: three places could freeze the whole process. The share path
fed io.Pipe from the WebSocket read loop, so one slow USB transfer stalled
every tunnel and the keepalives with them. The relay wrote to client
sockets while holding the hub lock, so one peer that stopped reading
blocked routing and registration for everyone. Control transfers ran
inline in the protocol loop behind a 5s timeout. Also fixed: a use-after-
free where a discarded URB's memory could be collected while the kernel
still owned it, a reap loop that spun at 100% CPU on ioctl errors, a
missing attach timeout, a double close(done) panic, and Hash[:8] in the
relay's log line, which let a client with a short hash take the server
down.

Adds mode "both", so one client can offer and consume devices at once.
The tunnel and client-left callbacks became multicast for it: as plain
fields the second manager to register silently unhooked the first.

Tunnel traffic is now AES-256-GCM end to end, on the relay path as well
as directly. The key is derived from the three tokens, not from the group
hash — the relay is told the hash, so a key derived from it would protect
nothing from the one party in the middle. Group IDs are unchanged, so
existing setups keep working; only clients configured without the tokens
drop to unencrypted, relay-only operation.

Peers now try to connect directly, with the relay supplying the public
address neither side can determine for itself. Candidates are raced
because an unreachable address hangs until timeout rather than refusing.
Falling back to the relay is not an error.

Platform reach: cross-compiled targets for ARM, MIPS and RISC-V (the
Linux client needed no code changes — usbdevfs is not architecture
specific), multi-arch Docker images, an Android bridge that accepts
devices over SCM_RIGHTS because apps cannot open /dev/bus/usb, and macOS
builds via system_profiler enumeration.

Adds a Windows KMDF filter driver under driver/windows with its Go side.
UNTESTED: it has never been compiled or run, needs the WDK to build and
an EV certificate to distribute. Treat it as a starting point.

Adds "usb-client diag": says per machine whether sharing and using are
possible, what stands in the way, and what fixes it. Reports can be
uploaded to a relay to get them off machines that are awkward to copy
from.

96 tests, all green under -race. Builds for linux, windows and darwin on
amd64 and arm64.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-11 22:02:04 +02:00

480 lines
13 KiB
Go

package relay
import (
"encoding/json"
"log"
"net"
"strconv"
"sync"
"github.com/duffy/usb-server/internal/protocol"
"github.com/gorilla/websocket"
)
// sendQueueDepth bounds per-client outgoing backlog. A client that falls this
// far behind is not going to catch up, and buffering more would let one stuck
// peer consume the relay's memory.
const sendQueueDepth = 256
// outMsg is one queued WebSocket frame.
type outMsg struct {
typ int // websocket.TextMessage or websocket.BinaryMessage
data []byte
}
// Client represents a connected WebSocket client
type Client struct {
ID string
Hash string
Mode string // "share", "use" or "both"
Name string
Conn *websocket.Conn
// DirectPort is the port this client accepts direct tunnel connections on,
// 0 if it accepts none.
DirectPort int
// PublicIP is the source address the relay sees this client connect from.
// Peers cannot determine their own public address, so the relay supplies
// it when passing on a grant — that is the whole reason it is involved in
// setting up connections that then bypass it.
PublicIP string
// Send carries outgoing frames to this client's write pump. All writes go
// through it: writing to the socket directly from another client's read
// loop would block that peer — and, because the hub held its lock across
// the write, every other client with it.
Send chan outMsg
closeOnce sync.Once
dead chan struct{}
}
// newClient creates a client with its outgoing queue ready.
func newClient(id, hash, mode, name string, conn *websocket.Conn) *Client {
return &Client{
ID: id,
Hash: hash,
Mode: mode,
Name: name,
Conn: conn,
Send: make(chan outMsg, sendQueueDepth),
dead: make(chan struct{}),
}
}
// enqueue queues a frame without blocking.
// It reports false when the client's queue is full or it is already gone; the
// caller should treat that as a disconnect rather than retrying.
func (c *Client) enqueue(typ int, data []byte) bool {
select {
case <-c.dead:
return false
default:
}
select {
case c.Send <- outMsg{typ: typ, data: data}:
return true
case <-c.dead:
return false
default:
log.Printf("[hub] send queue full for %s (%s), dropping client",
protocol.ShortID(c.ID), c.Name)
c.kill()
return false
}
}
// kill marks the client dead and wakes its write pump. Idempotent.
func (c *Client) kill() {
c.closeOnce.Do(func() { close(c.dead) })
}
// enqueueJSON marshals and queues a JSON control message.
func (c *Client) enqueueJSON(v interface{}) bool {
data, err := json.Marshal(v)
if err != nil {
return false
}
return c.enqueue(websocket.TextMessage, data)
}
// Hub manages all connected clients and routes messages between them
type Hub struct {
mu sync.RWMutex
groups map[string]map[string]*Client // hash -> client_id -> client
tunnels map[string]*Tunnel // tunnel_id -> tunnel info
}
// Tunnel tracks an active USB/IP tunnel between two clients
type Tunnel struct {
ID string
ShareClient string
UseClient string
BusID string
}
// NewHub creates a new Hub
func NewHub() *Hub {
return &Hub{
groups: make(map[string]map[string]*Client),
tunnels: make(map[string]*Tunnel),
}
}
// peers returns a snapshot of the clients in a hash group, excluding one ID.
//
// Taking a snapshot and releasing the lock before doing anything with the
// clients is deliberate: holding the hub lock across a send is what let a
// single slow peer stall registration and routing for everyone.
func (h *Hub) peers(hash, excludeID string) []*Client {
h.mu.RLock()
defer h.mu.RUnlock()
group := h.groups[hash]
result := make([]*Client, 0, len(group))
for _, c := range group {
if c.ID != excludeID {
result = append(result, c)
}
}
return result
}
// peer looks up a single client in a hash group.
func (h *Hub) peer(hash, clientID string) *Client {
h.mu.RLock()
defer h.mu.RUnlock()
group := h.groups[hash]
if group == nil {
return nil
}
return group[clientID]
}
// Register adds a client to its hash group
func (h *Hub) Register(client *Client) {
h.mu.Lock()
if h.groups[client.Hash] == nil {
h.groups[client.Hash] = make(map[string]*Client)
}
// A reconnecting client reuses its ID; drop the stale entry so its
// write pump exits instead of lingering with a dead socket.
if old, exists := h.groups[client.Hash][client.ID]; exists && old != client {
old.kill()
}
h.groups[client.Hash][client.ID] = client
h.mu.Unlock()
log.Printf("[hub] client registered: id=%s hash=%s mode=%s name=%s",
protocol.ShortID(client.ID), protocol.ShortID(client.Hash), client.Mode, client.Name)
// Notify other clients in the group
joined := &protocol.ClientJoined{
Type: protocol.MsgClientJoined,
ClientID: client.ID,
Mode: client.Mode,
Name: client.Name,
}
for _, peer := range h.peers(client.Hash, client.ID) {
peer.enqueueJSON(joined)
}
}
// Unregister removes a client and cleans up its tunnels
func (h *Hub) Unregister(client *Client) {
h.mu.Lock()
group := h.groups[client.Hash]
if group == nil {
h.mu.Unlock()
return
}
// Only remove this exact client: a reconnect may already have installed a
// newer connection under the same ID.
if group[client.ID] == client {
delete(group, client.ID)
}
if len(group) == 0 {
delete(h.groups, client.Hash)
}
// Clean up tunnels involving this client
for tid, tunnel := range h.tunnels {
if tunnel.ShareClient == client.ID || tunnel.UseClient == client.ID {
delete(h.tunnels, tid)
}
}
h.mu.Unlock()
client.kill()
log.Printf("[hub] client unregistered: id=%s name=%s", protocol.ShortID(client.ID), client.Name)
left := &protocol.ClientLeft{
Type: protocol.MsgClientLeft,
ClientID: client.ID,
}
for _, peer := range h.peers(client.Hash, client.ID) {
peer.enqueueJSON(left)
}
}
// HandleTextMessage processes a JSON control message
func (h *Hub) HandleTextMessage(sender *Client, data []byte) {
var env protocol.Envelope
if err := json.Unmarshal(data, &env); err != nil {
log.Printf("[hub] invalid message from %s: %v", protocol.ShortID(sender.ID), err)
return
}
switch env.Type {
case protocol.MsgDeviceList:
h.handleDeviceList(sender, data)
case protocol.MsgRequestDevice:
h.handleRequestDevice(sender, data)
case protocol.MsgDeviceGranted:
h.handleDeviceGranted(sender, data)
case protocol.MsgDeviceDenied:
h.handleDeviceDenied(sender, data)
case protocol.MsgForceRelease:
h.handleForceRelease(sender, data)
case protocol.MsgReleaseDevice:
h.handleReleaseDevice(sender, data)
case protocol.MsgDeviceReleased:
h.handleDeviceReleased(sender, data)
case protocol.MsgPing:
sender.enqueueJSON(&protocol.Pong{Type: protocol.MsgPong})
default:
log.Printf("[hub] unknown message type from %s: %s", protocol.ShortID(sender.ID), env.Type)
}
}
// HandleBinaryMessage forwards tunnel data to the other end
func (h *Hub) HandleBinaryMessage(sender *Client, data []byte) {
if len(data) < protocol.TunnelHeaderSize {
return
}
tunnelID := string(data[:protocol.TunnelHeaderSize])
h.mu.RLock()
tunnel := h.tunnels[tunnelID]
h.mu.RUnlock()
if tunnel == nil {
return
}
// Forward to the other end of the tunnel
var targetID string
switch sender.ID {
case tunnel.ShareClient:
targetID = tunnel.UseClient
case tunnel.UseClient:
targetID = tunnel.ShareClient
default:
return
}
if target := h.peer(sender.Hash, targetID); target != nil {
target.enqueue(websocket.BinaryMessage, data)
}
}
// handleDeviceList broadcasts a device list to every client in the group that
// can consume devices.
func (h *Hub) handleDeviceList(sender *Client, data []byte) {
if !protocol.CanShare(sender.Mode) {
return
}
for _, client := range h.peers(sender.Hash, sender.ID) {
if protocol.CanUse(client.Mode) {
client.enqueue(websocket.TextMessage, data)
}
}
}
// handleRequestDevice forwards a device request to the target share client
func (h *Hub) handleRequestDevice(sender *Client, data []byte) {
var msg protocol.RequestDevice
if err := json.Unmarshal(data, &msg); err != nil {
return
}
target := h.peer(sender.Hash, msg.TargetClient)
if target == nil || !protocol.CanShare(target.Mode) {
return
}
// Add the sender's ID so the share client knows who's requesting
target.enqueueJSON(map[string]interface{}{
"type": protocol.MsgRequestDevice,
"target_client": msg.TargetClient,
"bus_id": msg.BusID,
"request_id": msg.RequestID,
"from_client": sender.ID,
})
}
// handleDeviceGranted registers the tunnel and forwards to the requesting client
func (h *Hub) handleDeviceGranted(sender *Client, data []byte) {
var granted struct {
protocol.DeviceGranted
TargetClient string `json:"target_client"`
}
if err := json.Unmarshal(data, &granted); err != nil {
return
}
if granted.TunnelID == "" {
return
}
h.mu.Lock()
h.tunnels[granted.TunnelID] = &Tunnel{
ID: granted.TunnelID,
ShareClient: sender.ID,
UseClient: granted.TargetClient,
BusID: granted.BusID,
}
h.mu.Unlock()
log.Printf("[hub] tunnel created: %s (share=%s, use=%s, device=%s)",
granted.TunnelID, protocol.ShortID(sender.ID), protocol.ShortID(granted.TargetClient), granted.BusID)
target := h.peer(sender.Hash, granted.TargetClient)
if target == nil {
return
}
// Add the address we see the granting client at. It cannot know its own
// public address, and this is what lets the two peers connect directly
// across NAT and take their USB traffic off this relay entirely.
out := data
if extra := publicEndpoint(sender); extra != "" {
granted.Endpoints = appendUnique(granted.Endpoints, extra)
if reencoded, err := json.Marshal(granted); err == nil {
out = reencoded
}
}
target.enqueue(websocket.TextMessage, out)
}
// publicEndpoint builds the host:port at which a client's direct listener
// should be reachable from outside, or "" if it accepts no direct connections.
func publicEndpoint(c *Client) string {
if c.DirectPort == 0 || c.PublicIP == "" {
return ""
}
return net.JoinHostPort(c.PublicIP, strconv.Itoa(c.DirectPort))
}
// appendUnique adds an entry unless it is already present.
func appendUnique(list []string, item string) []string {
for _, existing := range list {
if existing == item {
return list
}
}
return append(list, item)
}
// handleDeviceDenied forwards denial to the requesting client
func (h *Hub) handleDeviceDenied(sender *Client, data []byte) {
var denied struct {
protocol.DeviceDenied
TargetClient string `json:"target_client"`
}
if err := json.Unmarshal(data, &denied); err != nil {
return
}
if target := h.peer(sender.Hash, denied.TargetClient); target != nil {
target.enqueue(websocket.TextMessage, data)
}
}
// handleReleaseDevice forwards a release to the share client
func (h *Hub) handleReleaseDevice(sender *Client, data []byte) {
var msg protocol.ReleaseDevice
if err := json.Unmarshal(data, &msg); err != nil {
return
}
// Clean up tunnel
h.mu.Lock()
for tid, tunnel := range h.tunnels {
if tunnel.UseClient == sender.ID && tunnel.BusID == msg.BusID {
delete(h.tunnels, tid)
log.Printf("[hub] tunnel closed: %s", tid)
break
}
}
h.mu.Unlock()
if target := h.peer(sender.Hash, msg.TargetClient); target != nil {
target.enqueueJSON(map[string]interface{}{
"type": protocol.MsgReleaseDevice,
"target_client": msg.TargetClient,
"bus_id": msg.BusID,
"from_client": sender.ID,
})
}
}
// handleForceRelease forwards a force-release request to the target share client
func (h *Hub) handleForceRelease(sender *Client, data []byte) {
var msg protocol.ForceRelease
if err := json.Unmarshal(data, &msg); err != nil {
return
}
// Clean up tunnel for this device (by BusID, regardless of who owns it)
h.mu.Lock()
for tid, tunnel := range h.tunnels {
if tunnel.BusID == msg.BusID && tunnel.ShareClient == msg.TargetClient {
delete(h.tunnels, tid)
log.Printf("[hub] tunnel force-closed: %s", tid)
break
}
}
h.mu.Unlock()
target := h.peer(sender.Hash, msg.TargetClient)
if target == nil || !protocol.CanShare(target.Mode) {
return
}
target.enqueueJSON(map[string]interface{}{
"type": protocol.MsgForceRelease,
"target_client": msg.TargetClient,
"bus_id": msg.BusID,
"from_client": sender.ID,
})
}
// handleDeviceReleased broadcasts device released notification
func (h *Hub) handleDeviceReleased(sender *Client, data []byte) {
for _, client := range h.peers(sender.Hash, sender.ID) {
if protocol.CanUse(client.Mode) {
client.enqueue(websocket.TextMessage, data)
}
}
}
// GroupStats reports the number of clients per hash group, for diagnostics.
func (h *Hub) GroupStats() map[string]int {
h.mu.RLock()
defer h.mu.RUnlock()
stats := make(map[string]int, len(h.groups))
for hash, group := range h.groups {
stats[protocol.ShortID(hash)] = len(group)
}
return stats
}