From mboxrd@z Thu Jan 1 00:00:00 1970 From: Shawn Guo Subject: Re: [PATCH] mmc: mxs-mmc: add support for pre_req and post_req Date: Wed, 20 Apr 2011 22:01:21 +0800 Message-ID: <20110420140120.GF1965@S2100-06.ap.freescale.net> References: <1302116833-24540-1-git-send-email-per.forlin@linaro.org> <1303058010-30256-1-git-send-email-shawn.guo@linaro.org> <20110417164830.GE17935@S2100-06.ap.freescale.net> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Received: from va3ehsobe003.messaging.microsoft.com ([216.32.180.13]:25095 "EHLO VA3EHSOBE003.bigfish.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755083Ab1DTN51 convert rfc822-to-8bit (ORCPT ); Wed, 20 Apr 2011 09:57:27 -0400 Content-Disposition: inline In-Reply-To: Sender: linux-mmc-owner@vger.kernel.org List-Id: linux-mmc@vger.kernel.org To: Per Forlin Cc: Shawn Guo , linaro-kernel@lists.linaro.org, linux-mmc@vger.kernel.org, cjb@laptop.org, linux-arm-kernel@lists.infradead.org, patches@linaro.org On Wed, Apr 20, 2011 at 10:01:22AM +0200, Per Forlin wrote: > On 17 April 2011 18:48, Shawn Guo wrote: > > On Mon, Apr 18, 2011 at 12:33:30AM +0800, Shawn Guo wrote: > >> pre_req() runs dma_map_sg() post_req() runs dma_unmap_sg. > >> If not calling pre_req() before mxs_mmc_request(), request() > >> will prepare the cache just like it did it before. > >> It is optional to use pre_req() and post_req(). > >> > >> Signed-off-by: Shawn Guo > >> --- > >> =A0drivers/mmc/host/mxs-mmc.c | =A0 75 +++++++++++++++++++++++++++= +++++++++++++++-- > >> =A01 files changed, 72 insertions(+), 3 deletions(-) > >> > > > > Here is the result of mmc_test case 37 ~ 40, which are designed to = see > > the performance improvement introduced by non-blocking changes. > > > > Honestly, the improvement is not so impressive. =A0Not sure if the = patch > > for mxs-mmc pre_req and post_req support was correctly produced. =A0= So > > please help review ... > My guess is that dma_unmap is not run in parallel with transfer. > Please look at my patch reply. >=20 Got it fixed in v2 posted just now. Please take another look. Unfortunately, I do not see noticeable difference than v1 in terms of mmc_test result. Do you have omap_hsmmc and mmci mmc_test result data to share? --=20 Regards, Shawn