From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tom Herbert Subject: Re: [PATCH v3] xmit_compl_seq: information to reclaim vmsplice buffers Date: Mon, 27 Sep 2010 11:38:36 -0700 Message-ID: References: <20100927172315.GA8387@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Cc: netdev@vger.kernel.org, davem@davemloft.net, sridharr@google.com To: "Michael S. Tsirkin" Return-path: Received: from smtp-out.google.com ([74.125.121.35]:52052 "EHLO smtp-out.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933309Ab0I0Sij (ORCPT ); Mon, 27 Sep 2010 14:38:39 -0400 Received: from kpbe14.cbf.corp.google.com (kpbe14.cbf.corp.google.com [172.25.105.78]) by smtp-out.google.com with ESMTP id o8RIcb0v024065 for ; Mon, 27 Sep 2010 11:38:38 -0700 Received: from pvg16 (pvg16.prod.google.com [10.241.210.144]) by kpbe14.cbf.corp.google.com with ESMTP id o8RIcAWS010779 for ; Mon, 27 Sep 2010 11:38:36 -0700 Received: by pvg16 with SMTP id 16so1497489pvg.12 for ; Mon, 27 Sep 2010 11:38:36 -0700 (PDT) In-Reply-To: <20100927172315.GA8387@redhat.com> Sender: netdev-owner@vger.kernel.org List-ID: > > Can not packets referencing this memory > still be outstanding at the NIC device, if retransmit happens > before the ack but after the packet was passed to a device? > > It's true that the reftransmit will likely get discarded > by the remote end, but this might be a security issue > if an application puts sensitive data in the buffer > and that gets inadvertently sent on the wire, can it not? > Yes, this hole probably does exist. I don't know how to fix it other than more API that specifically reports when all references to a buffer are released. In the case of TCP that probably means we'd need a destructor. > -- > MST >