Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Wed, 27 Oct 2021 14:34:29 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     Paul =?iso-8859-1?Q?Heidekr=FCger?= <paul.heidekrueger@in.tum.de>
Cc:     paulmck@kernel.org, will@kernel.org, boqun.feng@gmail.com,
        stern@rowland.harvard.edu, parri.andrea@gmail.com,
        linux-kernel@vger.kernel.org, llvm@lists.linux.dev,
        elver@google.com, charalampos.mainas@gmail.com,
        pramod.bhatotia@in.tum.de
Subject: Re: Potentially Broken Address Dependency via test_bit() When
 Compiling With Clang
Message-ID: <20211027123429.GE174730@worktop.programming.kicks-ass.net>
References: <YXknxGFjvaB46d/p@Pauls-MacBook-Pro>
 <20211027121747.GI174703@worktop.programming.kicks-ass.net>
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <20211027121747.GI174703@worktop.programming.kicks-ass.net>
Precedence: bulk

On Wed, Oct 27, 2021 at 02:17:48PM +0200, Peter Zijlstra wrote:
> On Wed, Oct 27, 2021 at 12:19:48PM +0200, Paul Heidekr?ger wrote:
> I would personally not consider this a dependend load. The result
> depends on two loads, but there is no actual ordering between them.
> 
>   r1 = *x
>   r2 = *y
>   b = 1 & (r1 >> r2);
> 
> (more or less)

melver pointed out on IRC that I missed the whole BIT_WORD(nr) thing.
And with that restored this should indeed be an address dependency.

Still, I wasn't actually expecting test_bit() to be one. Nice find.