From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752072AbcAFPjU (ORCPT ); Wed, 6 Jan 2016 10:39:20 -0500 Received: from iolanthe.rowland.org ([192.131.102.54]:53126 "HELO iolanthe.rowland.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1751755AbcAFPjQ (ORCPT ); Wed, 6 Jan 2016 10:39:16 -0500 Date: Wed, 6 Jan 2016 10:39:15 -0500 (EST) From: Alan Stern X-X-Sender: stern@iolanthe.rowland.org To: Peter Stuge cc: "Steinar H. Gunderson" , Christoph Hellwig , Greg Kroah-Hartman , , Subject: Re: [PATCH] Add support for usbfs zerocopy. In-Reply-To: <20160106152212.15218.qmail@stuge.se> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 6 Jan 2016, Peter Stuge wrote: > Steinar H. Gunderson wrote: > > > Our interface for zero copy reads/writes is O_DIRECT, and that requires > > > not special memory allocation, just proper alignment. > > > > But that assumes you are using I/O using read()/write(). There's no way you > > can shoehorn USB isochronous reads into the read() interface, O_DIRECT or not. > > How about aio? aio is not zerocopy. And it also doesn't solve the memory allocation problem that originally affected both Steiner and Markus. (Were you thinking of "asynchronous" instead of "isochronous"?) Alan Stern