From mboxrd@z Thu Jan 1 00:00:00 1970 From: Paul Walmsley Subject: Re: [PATCH] OMAP: MMC: recover from transfer failures - Resend Date: Thu, 5 Feb 2009 13:32:03 -0700 (MST) Message-ID: References: <20081207213617.10456.43951.stgit@localhost> <200902020946.16508.jpihet@mvista.com> <20090202190503.GT7215@atomide.com> <200902031505.58697.jpihet@mvista.com> <20090205121045.4022c319.akpm@linux-foundation.org> Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Return-path: Received: from utopia.booyaka.com ([72.9.107.138]:58334 "EHLO utopia.booyaka.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752643AbZBEUcG (ORCPT ); Thu, 5 Feb 2009 15:32:06 -0500 In-Reply-To: <20090205121045.4022c319.akpm@linux-foundation.org> Sender: linux-omap-owner@vger.kernel.org List-Id: linux-omap@vger.kernel.org To: Andrew Morton Cc: Jean Pihet , tony@atomide.com, ext-adrian.hunter@nokia.com, linux-arm-kernel@lists.arm.linux.org.uk, linux-omap@vger.kernel.org, jarkko.lavinen@nokia.com, drzeus-mmc@drzeus.cx, linux-kernel@vger.kernel.org On Thu, 5 Feb 2009, Andrew Morton wrote: > On Tue, 3 Feb 2009 15:05:58 +0100 > Jean Pihet wrote: > > > + while (OMAP_HSMMC_READ(host->base, > > + SYSCTL) & SRD) > > + ; > > Is a __raw_readl() sufficient to prevent the cpu from burning up here, > or should we add cpu_relax()? The __raw_readl() should be sufficient. The MMC controller is located on the L4 CORE interconnect, so the round trip latency for the read from MMC is at least 90 ns, while the CPU cycle time is only about 1 to 2 ns. > An infinite loop which assumes the hardware is perfect is always a > worry. But I see the driver already does that, so we're no worse off.. - Paul