Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757551AbbEWHgM (ORCPT ); Sat, 23 May 2015 03:36:12 -0400 Received: from mail-ie0-f178.google.com ([209.85.223.178]:34176 "EHLO mail-ie0-f178.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755713AbbEWHgF (ORCPT ); Sat, 23 May 2015 03:36:05 -0400 MIME-Version: 1.0 X-Originating-IP: [85.250.95.98] In-Reply-To: <20150518150302.GA23206@linaro.org> References: <1430500026-47990-1-git-send-email-lina.iyer@linaro.org> <20150511144608.GB16124@linaro.org> <20150518150302.GA23206@linaro.org> From: Ohad Ben-Cohen Date: Sat, 23 May 2015 10:35:44 +0300 Message-ID: Subject: Re: [PATCH RFC] hwspinlock: Don't take software spinlock before hwspinlock To: Lina Iyer Cc: "Anna, Suman" , Bjorn Andersson , Andy Gross , "linux-arm-msm@vger.kernel.org" , "linux-kernel@vger.kernel.org" , Kumar Gala , Jeffrey Hugo Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3094 Lines: 59 Hi Lina, On Mon, May 18, 2015 at 6:03 PM, Lina Iyer wrote: > The lock in question is used differently than traditional locks across > processors. This lock helps synchronizes context transition from > non-secure to secure on the same processor. > > The usecase, goes like this. In cpuidle, any core can be the last core > to power down. The last man also holds the responsibility of shutting > down shared resources like caches etc. The way the power down of a core > works is, there are some high level decisions made in Linux and these > decisions (like to flush and invalidate caches) etc gets transferred > over to the the secure layer. The secure layer executes the ARM WFI that > powers down the cpu, but uses these decisions passed into to determine > if the cache needs to be invalidated upon wakeup etc. > > There is a possible race condition between what Linux thinks is the last > core, vs what secure layer thinks is the last core. Lets say, two cores > c0, c1 are going down. c1 is the second last core to go down from Linux > as such, will not carry information about shared resources when making > the SCM call. c1 made the SCM call, but is stuck handling some FIQs. In > the meanwhile c0, goes idle and since its the last core in Linux, > figures out the state of the shared resources. c0 calls into SCM, and > ends up powering down earlier than c1. Per secure layer, the last core > to go down is c1 and the votes of the shared resources are considered > from that core. Things like cache invalidation without flush may happen > as a result of this inconsistency of last man view point. > > The way we have solved it, Linux acquires a hw spinlock for each core, > when calling into SCM and the secure monitor releases the spinlock. At > any given time, only one core can switch the context from Linux to > secure for power down operations. This guarantees the last man is > synchronized between both Linux and secure. Another core may be spinning > waiting for hw mutex, but they all happen serialized. This mutex is held > in an irq disable context in cpuidle. > > There may be another processor spining to wait on hw mutex, but there > isnt much to do otherwise, because the only operation at this time while > holding the lock is to call into SCM and that would unlock the mutex. Just to make sure I understand, is this how your scenario is solved? - c1 goes down - c0 goes down, carries information about shared resources - c1 takes HWLOCK and calls into SCM, stuck handling FIQs - c0 wants to call into SCM but is waiting spinning on HWLOCK - c1 completes handling FIQs, goes idle, HWLOCK is released by secure monitor - c0 takes HWLOCK, calls into SCM, shared resources handled correctly, HWLOCK in this example is a single shared hwspinlock accessible by c0, c1 and secure monitor. Thanks, Ohad. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/