From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932873Ab3FFKJM (ORCPT ); Thu, 6 Jun 2013 06:09:12 -0400 Received: from arroyo.ext.ti.com ([192.94.94.40]:42398 "EHLO arroyo.ext.ti.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932628Ab3FFKJI (ORCPT ); Thu, 6 Jun 2013 06:09:08 -0400 Message-ID: <51B05FAE.60508@ti.com> Date: Thu, 6 Jun 2013 13:08:46 +0300 From: Illia Smyrnov User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:17.0) Gecko/20130330 Thunderbird/17.0.5 MIME-Version: 1.0 To: Mark Brown CC: Illia Smyrnov , Grant Likely , Rob Herring , Rob Landley , Daniel Mack , Matthias Brugger , Tony Lindgren , Greg Kroah-Hartman , , , , Subject: Re: [PATCH 1/2] spi: spi-omap2-mcspi.c: Add dts for slave device configuration. References: <1370432398-7796-1-git-send-email-illia.smyrnov@ti.com> <1370432398-7796-2-git-send-email-illia.smyrnov@ti.com> <20130605115734.GY31367@sirena.org.uk> In-Reply-To: <20130605115734.GY31367@sirena.org.uk> Content-Type: text/plain; charset="ISO-8859-1"; format=flowed Content-Transfer-Encoding: 7bit X-Originating-IP: [10.167.145.193] X-EXCLAIMER-MD-CONFIG: f9c360f5-3d1e-4c3c-8703-f45bf52eff6b Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 06/05/2013 02:57 PM, Mark Brown wrote: > On Wed, Jun 05, 2013 at 02:39:57PM +0300, Illia Smyrnov wrote: > >> +SPI Controller specific data in SPI slave nodes: >> +- The spi slave nodes can provide the following information which is used >> + by the spi controller: >> + - ti,spi-turbo-mode: Set turbo mode for this device. >> + > > What is turb mode and According to OMAP TRM [1] MCSPI turbo mode improves the throughput of the SPI interface when a single channel is enabled by allowing transfers until the shift register and the MCSPI_RXx register are full. I tested turbo mode using KS8851 SPI Ethernet controller on Blaze with OMAP4460 and nuttcp tool with -r for RX throughput measuring. Enabling turbo mode was increased throughput form 7.5538 Mbps to 8.3848 Mbps > why would we not want to just enable it all the > time? Turbo mode gives the expected results not for all cases. There are some limitations: - works only if a single channel is enabled (no effect when several channels are enable); - improves the throughput on RX direction only; - effective only when a transfer exceeds two words. For single SPI word transfers OMAP TRM [1] recommends deactivate turbo mode. So it is useful to have the property in DT, that allow us to switch turbo mode off/on for certain slave. > Based on this documentation it's not really possible to tell... > I will add turbo mode description to documentation in the next patch version [1]: http://www.ti.com/lit/ug/swpu235z/swpu235z.pdf