xenbus/xenbus_backend: Disallow pending watch messages

'xenbus_backend' watches 'state' of devices, which is writable by
guests.  Hence, if guests intensively updates it, dom0 will have lots of
pending events that exhausting memory of dom0.  In other words, guests
can trigger dom0 memory pressure.  This is known as XSA-349.  However,
the watch callback of it, 'frontend_changed()', reads only 'state', so
doesn't need to have the pending events.

To avoid the problem, this commit disallows pending watch messages for
'xenbus_backend' using the 'will_handle()' watch callback.

This is part of XSA-349

Cc: [email protected]
Signed-off-by: SeongJae Park <[email protected]>
Reported-by: Michael Kurth <[email protected]>
Reported-by: Pawel Wieczorkiewicz <[email protected]>
Reviewed-by: Juergen Gross <[email protected]>
Signed-off-by: Juergen Gross <[email protected]>

Author: sj-aws

drivers/xen/xenbus/xenbus_probe_backend.c

@@ -180,6 +180,12 @@ static int xenbus_probe_backend(struct xen_bus_type *bus, const char *type,
 	return err;
 }
 
+static bool frontend_will_handle(struct xenbus_watch *watch,
+				 const char *path, const char *token)
+{
+	return watch->nr_pending == 0;
+}
+
 static void frontend_changed(struct xenbus_watch *watch,
 			     const char *path, const char *token)
 {
@@ -191,6 +197,7 @@ static struct xen_bus_type xenbus_backend = {
 	.levels = 3,		/* backend/type/<frontend>/<id> */
 	.get_bus_id = backend_bus_id,
 	.probe = xenbus_probe_backend,
+	.otherend_will_handle = frontend_will_handle,
 	.otherend_changed = frontend_changed,
 	.bus = {
 		.name		= "xen-backend",