[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20171115180540.GQ19071@arm.com>
Date: Wed, 15 Nov 2017 18:05:41 +0000
From: Will Deacon <will.deacon@....com>
To: Alan Stern <stern@...land.harvard.edu>
Cc: Peter Zijlstra <peterz@...radead.org>,
"Reshetova, Elena" <elena.reshetova@...el.com>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"gregkh@...uxfoundation.org" <gregkh@...uxfoundation.org>,
"keescook@...omium.org" <keescook@...omium.org>,
"tglx@...utronix.de" <tglx@...utronix.de>,
"mingo@...hat.com" <mingo@...hat.com>,
"ishkamiel@...il.com" <ishkamiel@...il.com>,
Paul McKenney <paulmck@...ux.vnet.ibm.com>,
parri.andrea@...il.com, boqun.feng@...il.com, dhowells@...hat.com,
david@...morbit.com
Subject: Re: [PATCH] refcount: provide same memory ordering guarantees as in
atomic_t
On Thu, Nov 02, 2017 at 04:21:56PM -0400, Alan Stern wrote:
> I was trying to think of something completely different. If you have a
> release/acquire to the same address, it creates a happens-before
> ordering:
>
> Access x
> Release a
> Acquire a
> Access y
>
> Here is the access to x happens-before the access to y. This is true
> even on x86, even in the presence of forwarding -- the CPU still has to
> execute the instructions in order. But if the release and acquire are
> to different addresses:
>
> Access x
> Release a
> Acquire b
> Access y
>
> then there is no happens-before ordering for x and y -- the CPU can
> execute the last two instructions before the first two. x86 and
> PowerPC won't do this, but I believe ARMv8 can. (Please correct me if
> it can't.)
Release/Acquire are RCsc on ARMv8, so they are ordered irrespective of
address.
Will
Powered by blists - more mailing lists