Date: Thu, 1 Dec 2005 04:25:43 +0100
From: Pavel Machek <pavel@ucw.cz>
To: "Zhang, Yanmin" <yanmin.zhang@intel.com>
Cc: linux-kernel@vger.kernel.org,
       "Pallipadi, Venkatesh" <venkatesh.pallipadi@intel.com>,
       "Shah, Rajesh" <rajesh.shah@intel.com>
Subject: Re: [BUG] Variable stopmachine_state should be volatile
Message-ID: <20051201032543.GA2387@elf.ucw.cz>
References: <8126E4F969BA254AB43EA03C59F44E84040B3C8C@pdsmsx404>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <8126E4F969BA254AB43EA03C59F44E84040B3C8C@pdsmsx404>
User-Agent: Mutt/1.5.9i
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1110
Lines: 30

Hi!

> >>Hi!
> >>
> >>> The model to access variable stopmachine_state is that a main thread
> >>> writes it and other threads read it. Its declaration has no sign
> >>> volatile. In the while loop in function stopmachine, this variable is
> >>> read, and compiler might optimize it by reading it once before the loop
> >>> and not reading it again in the loop, so the thread might enter dead
> >>> loop.
> >>
> >>No. volatile may look like a solution, but it usually is not. You may
> >>need some barriers, atomic_t or locking.
> >>								Pavel
> The original functions already use smp_mb/smp_wmb. My patch just
>tells compiler not to optimize by bringing the reading of
>stopmachine_state out of the while loop.

Those barriers should already prevent compiler optimalization, no? If
they do not, just use some barriers that do.
								Pavel


-- 
Thanks, Sharp!
-
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/