Roomserver/federation input refactor (#2104)

* Put federation client functions into their own file

* Look for missing auth events in RS input

* Remove retrieveMissingAuthEvents from federation API

* Logging

* Sorta transplanted the code over

* Use event origin failing all else

* Don't get stuck on mutexes:

* Add verifier

* Don't mark state events with zero snapshot NID as not existing

* Check missing state if not an outlier before storing the event

* Reject instead of soft-fail, don't copy roominfo so much

* Use synchronous contexts, limit time to fetch missing events

* Clean up some commented out bits

* Simplify `/send` endpoint significantly

* Submit async

* Report errors on sending to RS input

* Set max payload in NATS to 16MB

* Tweak metrics

* Add `workerForRoom` for tidiness

* Try skipping unmarshalling errors for RespMissingEvents

* Track missing prev events separately to avoid calculating state when not possible

* Tweak logic around checking missing state

* Care about state when checking missing prev events

* Don't check missing state for create events

* Try that again

* Handle create events better

* Send create room events as new

* Use given event kind when sending auth/state events

* Revert "Use given event kind when sending auth/state events"

This reverts commit 089d64d271b5fca8c104e1554711187420dbebca.

* Only search for missing prev events or state for new events

* Tweaks

* We only have missing prev if we don't supply state

* Room version tweaks

* Allow async inputs again

* Apply backpressure to consumers/synchronous requests to hopefully stop things being overwhelmed

* Set timeouts on roomserver input tasks (need to decide what timeout makes sense)

* Use work queue policy, deliver all on restart

* Reduce chance of duplicates being sent by NATS

* Limit the number of servers we attempt to reduce backpressure

* Some review comment fixes

* Tidy up a couple things

* Don't limit servers, randomise order using map

* Some context refactoring

* Update gmsl

* Don't resend create events

* Set stateIDs length correctly or else the roomserver thinks there are missing events when there aren't

* Exclude our own servername

* Try backing off servers

* Make excluding self behaviour optional

* Exclude self from g_m_e

* Update sytest-whitelist

* Update consumers for the roomserver output stream

* Remember to send outliers for state returned from /gme

* Make full HTTP tests less upsetti

* Remove 'If a device list update goes missing, the server resyncs on the next one' from the sytest blacklist

* Remove debugging test

* Fix blacklist again, remove unnecessary duplicate context

* Clearer contexts, don't use background in case there's something happening there

* Don't queue up events more than once in memory

* Correctly identify create events when checking for state

* Fill in gaps again in /gme code

* Remove `AuthEventIDs` from `InputRoomEvent`

* Remove stray field

Co-authored-by: Kegan Dougal <kegan@matrix.org>

federationapi/inthttp/client.go

@@ -26,16 +26,18 @@ const (
 	FederationAPIPerformServersAlivePath           = "/federationapi/performServersAlive"
 	FederationAPIPerformBroadcastEDUPath           = "/federationapi/performBroadcastEDU"
 
-	FederationAPIGetUserDevicesPath     = "/federationapi/client/getUserDevices"
-	FederationAPIClaimKeysPath          = "/federationapi/client/claimKeys"
-	FederationAPIQueryKeysPath          = "/federationapi/client/queryKeys"
-	FederationAPIBackfillPath           = "/federationapi/client/backfill"
-	FederationAPILookupStatePath        = "/federationapi/client/lookupState"
-	FederationAPILookupStateIDsPath     = "/federationapi/client/lookupStateIDs"
-	FederationAPIGetEventPath           = "/federationapi/client/getEvent"
-	FederationAPILookupServerKeysPath   = "/federationapi/client/lookupServerKeys"
-	FederationAPIEventRelationshipsPath = "/federationapi/client/msc2836eventRelationships"
-	FederationAPISpacesSummaryPath      = "/federationapi/client/msc2946spacesSummary"
+	FederationAPIGetUserDevicesPath      = "/federationapi/client/getUserDevices"
+	FederationAPIClaimKeysPath           = "/federationapi/client/claimKeys"
+	FederationAPIQueryKeysPath           = "/federationapi/client/queryKeys"
+	FederationAPIBackfillPath            = "/federationapi/client/backfill"
+	FederationAPILookupStatePath         = "/federationapi/client/lookupState"
+	FederationAPILookupStateIDsPath      = "/federationapi/client/lookupStateIDs"
+	FederationAPILookupMissingEventsPath = "/federationapi/client/lookupMissingEvents"
+	FederationAPIGetEventPath            = "/federationapi/client/getEvent"
+	FederationAPILookupServerKeysPath    = "/federationapi/client/lookupServerKeys"
+	FederationAPIEventRelationshipsPath  = "/federationapi/client/msc2836eventRelationships"
+	FederationAPISpacesSummaryPath       = "/federationapi/client/msc2946spacesSummary"
+	FederationAPIGetEventAuthPath        = "/federationapi/client/getEventAuth"
 
 	FederationAPIInputPublicKeyPath = "/federationapi/inputPublicKey"
 	FederationAPIQueryPublicKeyPath = "/federationapi/queryPublicKey"
@@ -353,6 +355,49 @@ func (h *httpFederationInternalAPI) LookupStateIDs(
 	return *response.Res, nil
 }
 
+type lookupMissingEvents struct {
+	S           gomatrixserverlib.ServerName
+	RoomID      string
+	Missing     gomatrixserverlib.MissingEvents
+	RoomVersion gomatrixserverlib.RoomVersion
+	Res         struct {
+		Events []gomatrixserverlib.RawJSON `json:"events"`
+	}
+	Err *api.FederationClientError
+}
+
+func (h *httpFederationInternalAPI) LookupMissingEvents(
+	ctx context.Context, s gomatrixserverlib.ServerName, roomID string,
+	missing gomatrixserverlib.MissingEvents, roomVersion gomatrixserverlib.RoomVersion,
+) (res gomatrixserverlib.RespMissingEvents, err error) {
+	span, ctx := opentracing.StartSpanFromContext(ctx, "LookupMissingEvents")
+	defer span.Finish()
+
+	request := lookupMissingEvents{
+		S:           s,
+		RoomID:      roomID,
+		Missing:     missing,
+		RoomVersion: roomVersion,
+	}
+	apiURL := h.federationAPIURL + FederationAPILookupMissingEventsPath
+	err = httputil.PostJSON(ctx, span, h.httpClient, apiURL, &request, &request)
+	if err != nil {
+		return res, err
+	}
+	if request.Err != nil {
+		return res, request.Err
+	}
+	res.Events = make([]*gomatrixserverlib.Event, 0, len(request.Res.Events))
+	for _, js := range request.Res.Events {
+		ev, err := gomatrixserverlib.NewEventFromUntrustedJSON(js, roomVersion)
+		if err != nil {
+			return res, err
+		}
+		res.Events = append(res.Events, ev)
+	}
+	return res, nil
+}
+
 type getEvent struct {
 	S       gomatrixserverlib.ServerName
 	EventID string
@@ -382,6 +427,40 @@ func (h *httpFederationInternalAPI) GetEvent(
 	return *response.Res, nil
 }
 
+type getEventAuth struct {
+	S           gomatrixserverlib.ServerName
+	RoomVersion gomatrixserverlib.RoomVersion
+	RoomID      string
+	EventID     string
+	Res         *gomatrixserverlib.RespEventAuth
+	Err         *api.FederationClientError
+}
+
+func (h *httpFederationInternalAPI) GetEventAuth(
+	ctx context.Context, s gomatrixserverlib.ServerName,
+	roomVersion gomatrixserverlib.RoomVersion, roomID, eventID string,
+) (gomatrixserverlib.RespEventAuth, error) {
+	span, ctx := opentracing.StartSpanFromContext(ctx, "GetEventAuth")
+	defer span.Finish()
+
+	request := getEventAuth{
+		S:           s,
+		RoomVersion: roomVersion,
+		RoomID:      roomID,
+		EventID:     eventID,
+	}
+	var response getEventAuth
+	apiURL := h.federationAPIURL + FederationAPIGetEventAuthPath
+	err := httputil.PostJSON(ctx, span, h.httpClient, apiURL, &request, &response)
+	if err != nil {
+		return gomatrixserverlib.RespEventAuth{}, err
+	}
+	if response.Err != nil {
+		return gomatrixserverlib.RespEventAuth{}, response.Err
+	}
+	return *response.Res, nil
+}
+
 func (h *httpFederationInternalAPI) QueryServerKeys(
 	ctx context.Context, req *api.QueryServerKeysRequest, res *api.QueryServerKeysResponse,
 ) error {