Warp/server/internal/syncapi/todevice.go

package syncapi

import (
	"context"
	"encoding/json"

	"github.com/dariuszjaniak/warp/server/internal/storage"
)

// To-device messaging: a message from one device to another, which the
// server stores and forwards without reading.
//
// It exists for end-to-end encryption — a device sending another one a
// Megolm session key is a to-device message — and the server deliberately
// cannot tell what is in one. Phase 7 builds the keyserver on top of this;
// the transport itself belongs here, because the only way a device ever
// receives one is in a /sync response.

// wildcardDevice is the device ID that means "every device of this user".
const wildcardDevice = "*"

// SendToDeviceRequest is PUT /sendToDevice/{eventType}/{txnID}.
type SendToDeviceRequest struct {
	// Sender is the full user ID sending, which is the caller.
	Sender string

	EventType string

	// Messages is user ID -> device ID -> content, as the request body
	// nests it. A device ID of "*" addresses every device of that user.
	Messages map[string]map[string]json.RawMessage
}

// SendToDevice queues messages for delivery.
//
// A message to a user of another server goes to the federation queue. With
// federation off it is dropped rather than refused. That is deliberate: a
// client encrypting for a room with remote members sends one message per
// device in one request, and failing the request because federation is
// off would stop it from delivering to the local devices as well. The
// dropped recipients simply never see the key and their client reports an
// undecryptable message, which is what they would see anyway.
func (s *API) SendToDevice(ctx context.Context, req SendToDeviceRequest) error {
	if req.EventType == "" {
		return errInvalidParamf("an event type is required")
	}

	var (
		queued []storage.NewToDeviceMessage
		woken  []string
		remote = map[string]map[string]json.RawMessage{}
		sentAt = s.nowMS()
	)
	for userID, byDevice := range req.Messages {
		localpart, ok := s.localpartOf(userID)
		if !ok {
			// A remote recipient goes to the federation queue when there
			// is one and the sender is ours; a remote sender's message to
			// a remote user is not this server's to forward.
			if s.outbound != nil && s.isLocal(req.Sender) {
				remote[userID] = byDevice
				continue
			}
			s.log.Debug("dropping a to-device message for a remote user",
				"sender", req.Sender, "recipient", userID)
			continue
		}

		for deviceID, content := range byDevice {
			if deviceID != wildcardDevice {
				queued = append(queued, storage.NewToDeviceMessage{
					Localpart: localpart,
					DeviceID:  deviceID,
					Sender:    req.Sender,
					Type:      req.EventType,
					Content:   contentOrEmpty(content),
					SentAtMS:  sentAt,
				})
				continue
			}

			// A wildcard is expanded here rather than stored as one: the
			// set of a user's devices changes, and a message addressed to
			// "every device" means the ones that existed when it was sent.
			// Storing the wildcard would deliver it to a device that was
			// created afterwards, which for a key share is both useless
			// and a leak.
			devices, err := s.accounts.Devices(ctx, localpart)
			if err != nil {
				return err
			}
			for _, device := range devices {
				queued = append(queued, storage.NewToDeviceMessage{
					Localpart: localpart,
					DeviceID:  device.ID,
					Sender:    req.Sender,
					Type:      req.EventType,
					Content:   contentOrEmpty(content),
					SentAtMS:  sentAt,
				})
			}
		}
		woken = append(woken, userID)
	}

	if len(remote) > 0 {
		s.outbound.ToDevice(ctx, req.Sender, req.EventType, remote)
	}
	if len(queued) == 0 {
		return nil
	}
	if _, err := s.store.SendToDevice(ctx, queued); err != nil {
		return err
	}
	s.notifier.NotifyUsers(woken)
	return nil
}

// contentOrEmpty keeps a null or absent content out of the store: the
// to-device content is passed through untouched, and "untouched" has to
// still be valid JSON on the way out.
func contentOrEmpty(content json.RawMessage) []byte {
	if len(content) == 0 {
		return []byte("{}")
	}
	return content
}

// toDeviceEvent is one message in the shape a sync reports it.
type toDeviceEvent struct {
	Sender  string          `json:"sender"`
	Type    string          `json:"type"`
	Content json.RawMessage `json:"content"`
}

// toDeviceMessages reads a device's queue between two positions and returns
// the events plus the position of the last one.
//
// The returned position is what the next token carries, and it is the
// position of the last message *delivered* rather than the top of the
// stream: a queue longer than one batch is drained over several syncs, and
// a token naming the top would skip the rest.
func (s *API) toDeviceMessages(ctx context.Context, localpart, deviceID string, from, to int64, limit int) ([]toDeviceEvent, int64, error) {
	if deviceID == "" {
		// An access token always names a device, so this cannot happen
		// through the API; a guest session later might.
		return nil, from, nil
	}

	msgs, err := s.store.ToDeviceMessages(ctx, localpart, deviceID, from, to, limit)
	if err != nil {
		return nil, 0, err
	}
	if len(msgs) == 0 {
		return nil, from, nil
	}

	out := make([]toDeviceEvent, 0, len(msgs))
	for _, m := range msgs {
		out = append(out, toDeviceEvent{
			Sender:  m.Sender,
			Type:    m.Type,
			Content: m.Content,
		})
	}
	return out, msgs[len(msgs)-1].StreamPos, nil
}

// ackToDevice deletes the messages a device has acknowledged by syncing
// past them.
//
// A device acknowledges a batch by sending back the token that batch came
// with, so the deletion happens on the *next* sync rather than when the
// batch is sent. A client that crashes between the two gets the batch
// again, which is the right way round: a lost key share leaves a message
// permanently undecryptable, and a duplicate one is ignored.
func (s *API) ackToDevice(ctx context.Context, localpart, deviceID string, through int64) {
	if deviceID == "" || through <= 0 {
		return
	}
	if err := s.store.DeleteToDeviceMessages(ctx, localpart, deviceID, through); err != nil {
		// Failing the sync over this would be worse than leaving the rows:
		// the client has the messages, and the next sync will try again.
		s.log.Warn("could not drop acknowledged to-device messages",
			"localpart", localpart, "device_id", deviceID, "through", through, "error", err)
	}
}