From mboxrd@z Thu Jan 1 00:00:00 1970 From: Peter Ujfalusi Subject: Re: Patch to parameterize DMA_MIN_BYTES for omap2-mcspi Date: Fri, 20 Mar 2015 15:10:04 +0200 Message-ID: <550C1C2C.5080204@ti.com> References: <1426741501.10003.6.camel@midgaarde> <550AC256.4070509@ti.com> <550AF7F6.7080200@ti.com> <1426786080.13824.23.camel@symus-gk-mint> <20150319185129.GZ2869@sirena.org.uk> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Received: from bear.ext.ti.com ([192.94.94.41]:43916 "EHLO bear.ext.ti.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750871AbbCTNKM (ORCPT ); Fri, 20 Mar 2015 09:10:12 -0400 In-Reply-To: <20150319185129.GZ2869@sirena.org.uk> Sender: linux-omap-owner@vger.kernel.org List-Id: linux-omap@vger.kernel.org To: Mark Brown , Greg Knight Cc: linux-spi@vger.kernel.org, "linux-omap@vger.kernel.org" On 03/19/2015 08:51 PM, Mark Brown wrote: > On Thu, Mar 19, 2015 at 01:28:00PM -0400, Greg Knight wrote: >=20 >> Changing DMA_MIN_BYTES to, say, "dma_min_time_ms" sounds reasonable = to >> me. I don't know how to compute it completely accurately as some SPI >=20 > You probably need both - there's often a hard limit where the FIFO si= ze > in the hardware becomes a limit for DMA as well as a soft limit on to= p > of that for performance reasons. The FIFO is only going to be enabled when the DMA is used for transfer = so we should have some lower limit for the PIO/DMA threshold. The FIFO in McS= PI is a tricky one anyways, since it has only one FIFO but several channels and= the =46IFO can be enabled for only one channel, if it is enabled for more c= hannels it is not going to be used by either channel. --=20 P=E9ter -- To unsubscribe from this list: send the line "unsubscribe linux-omap" i= n the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html