From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S933931AbcI3TFs (ORCPT <rfc822;w@1wt.eu>);
        Fri, 30 Sep 2016 15:05:48 -0400
Received: from merlin.infradead.org ([205.233.59.134]:51848 "EHLO
        merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S933810AbcI3TFm (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Fri, 30 Sep 2016 15:05:42 -0400
Date: Fri, 30 Sep 2016 21:05:35 +0200
From: Peter Zijlstra <peterz@infradead.org>
To: Brent DeGraaf <bdegraaf@codeaurora.org>
Cc: Ingo Molnar <mingo@redhat.com>,
        Catalin Marinas <catalin.marinas@arm.com>,
        Will Deacon <will.deacon@arm.com>,
        Christopher Covington <cov@codeaurora.org>,
        Timur Tabi <timur@codeaurora.org>,
        Nathan Lynch <nathan_lynch@mentor.com>,
        linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org
Subject: Re: [RFC] arm64: Enforce observed order for spinlock and data
Message-ID: <20160930190535.GB3142@twins.programming.kicks-ass.net>
References: <1475257257-23072-1-git-send-email-bdegraaf@codeaurora.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <1475257257-23072-1-git-send-email-bdegraaf@codeaurora.org>
User-Agent: Mutt/1.5.23.1 (2014-03-12)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Fri, Sep 30, 2016 at 01:40:57PM -0400, Brent DeGraaf wrote:
> Prior spinlock code solely used load-acquire and store-release
> semantics to ensure ordering of the spinlock lock and the area it
> protects. However, store-release semantics and ordinary stores do
> not protect against accesses to the protected area being observed
> prior to the access that locks the lock itself.
> 
> While the load-acquire and store-release ordering is sufficient
> when the spinlock routines themselves are strictly used, other
> kernel code that references the lock values directly (e.g. lockrefs)

Isn't the problem with lockref the fact that arch_spin_value_unlocked()
isn't a load-acquire, and therefore the CPU in question doesn't need to
observe the contents of the critical section etc..?

That is, wouldn't fixing arch_spin_value_unlocked() by making that an
smp_load_acquire() fix things much better?

> could observe changes to the area protected by the spinlock prior
> to observance of the lock itself being in a locked state, despite
> the fact that the spinlock logic itself is correct.