fix(transport): various tcp transport races (#1095)

Co-authored-by: diegomrsantos <[email protected]>

libp2p/dialer.nim

@@ -81,16 +81,18 @@ proc dialAndUpgrade(
           if dialed.dir != dir:
             dialed.dir = dir
           await transport.upgrade(dialed, peerId)
+        except CancelledError as exc:
+          await dialed.close()
+          raise exc
         except CatchableError as exc:
           # If we failed to establish the connection through one transport,
           # we won't succeeded through another - no use in trying again
           await dialed.close()
           debug "Connection upgrade failed", err = exc.msg, peerId = peerId.get(default(PeerId))
-          if exc isnot CancelledError:
-            if dialed.dir == Direction.Out:
-              libp2p_failed_upgrades_outgoing.inc()
-            else:
-              libp2p_failed_upgrades_incoming.inc()
+          if dialed.dir == Direction.Out:
+            libp2p_failed_upgrades_outgoing.inc()
+          else:
+            libp2p_failed_upgrades_incoming.inc()
 
           # Try other address
           return nil

libp2p/errors.nim

@@ -44,12 +44,3 @@ macro checkFutures*[F](futs: seq[F], exclude: untyped = []): untyped =
             # We still don't abort but warn
             debug "A future has failed, enable trace logging for details", error=exc.name
             trace "Exception details", msg=exc.msg
-
-template tryAndWarn*(message: static[string]; body: untyped): untyped =
-  try:
-    body
-  except CancelledError as exc:
-    raise exc
-  except CatchableError as exc:
-    debug "An exception has ocurred, enable trace logging for details", name = exc.name, msg = message
-    trace "Exception details", exc = exc.msg

libp2p/switch.nim

@@ -273,6 +273,7 @@ proc accept(s: Switch, transport: Transport) {.async.} = # noraises
     except CancelledError as exc:
       trace "releasing semaphore on cancellation"
       upgrades.release() # always release the slot
+      return
     except CatchableError as exc:
       error "Exception in accept loop, exiting", exc = exc.msg
       upgrades.release() # always release the slot
@@ -288,6 +289,12 @@ proc stop*(s: Switch) {.async, public.} =
 
   s.started = false
 
+  try:
+    # Stop accepting incoming connections
+    await allFutures(s.acceptFuts.mapIt(it.cancelAndWait())).wait(1.seconds)
+  except CatchableError as exc:
+    debug "Cannot cancel accepts", error = exc.msg
+
   for service in s.services:
     discard await service.stop(s)
 
@@ -302,18 +309,6 @@ proc stop*(s: Switch) {.async, public.} =
     except CatchableError as exc:
       warn "error cleaning up transports", msg = exc.msg
 
-  try:
-    await allFutures(s.acceptFuts)
-      .wait(1.seconds)
-  except CatchableError as exc:
-    trace "Exception while stopping accept loops", exc = exc.msg
-
-  # check that all futures were properly
-  # stopped and otherwise cancel them
-  for a in s.acceptFuts:
-    if not a.finished:
-      a.cancel()
-
   for service in s.services:
     discard await service.stop(s)