From mboxrd@z Thu Jan 1 00:00:00 1970 From: Bryan O'Donoghue Subject: Re: [PATCH 2/2] x86/quark: Add Quark embedded SRAM self-test Date: Wed, 06 May 2015 07:27:06 -0700 Message-ID: <554A24BA.80605@nexus-software.ie> References: <1430705875-6990-1-git-send-email-pure.logic@nexus-software.ie> <1430705875-6990-3-git-send-email-pure.logic@nexus-software.ie> <20150506100211.GB16458@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit Return-path: Received: from outbound-smtp06.blacknight.com ([81.17.249.39]:55621 "EHLO outbound-smtp06.blacknight.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751116AbbEFO1P (ORCPT ); Wed, 6 May 2015 10:27:15 -0400 Received: from mail.blacknight.com (pemlinmail04.blacknight.ie [81.17.254.17]) by outbound-smtp06.blacknight.com (Postfix) with ESMTPS id 4959898A0D for ; Wed, 6 May 2015 14:27:14 +0000 (UTC) In-Reply-To: <20150506100211.GB16458@gmail.com> Sender: platform-driver-x86-owner@vger.kernel.org List-ID: To: Ingo Molnar Cc: tglx@linutronix.de, mingo@redhat.com, hpa@zytor.com, x86@kernel.org, dvhart@infradead.org, andy.schevchenko@gmail.com, boon.leong.ong@intel.com, linux-kernel@vger.kernel.org, platform-driver-x86@vger.kernel.org, derek.browne@intel.com, josef.ahmad@intel.com, erik.nyquist@intel.com On 06/05/15 03:02, Ingo Molnar wrote: >> + * This function is carefully constructed to measure and verify the >> + * performance boost provided by eSRAM. We invalidate the cache with a >> + * wbinvd() and then perform a series of reads - each of which will cause a >> + * cacheline miss. We measure the aggregate time it takes to complete the >> + * series of reads and return the delta in cycles. The calling function will >> + * pass either a pointer to DRAM or a pointer to eSRAM. >> + * >> + * @param walker: Pointer to RAM area to test. >> + * @return: Number of cycles to complete test. >> + */ > > So I don't see the wbinvd() that the description mentions. wbinvd(); isn't required to make the test do it's job. Missed scrubbing from the description - damn :( > >> + * esram_self_test_init - entry point for IMR driver. >> + * esram_self_test_exit - exit point for IMR code. > > Stale 'IMR' references left over from copy & paste? Yep