Date: Wed, 10 May 2006 12:40:03 -0700 (PDT)
Message-Id: <20060510.124003.04457042.davem@davemloft.net>
To: rth@twiddle.net
Cc: paulus@samba.org, linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org,
       linuxppc-dev@ozlabs.org
Subject: Re: [RFC/PATCH] Make powerpc64 use __thread for per-cpu variables
From: "David S. Miller" <davem@davemloft.net>
In-Reply-To: <20060510154702.GA28938@twiddle.net>
References: <17505.26159.807484.477212@cargo.ozlabs.ibm.com>
	<20060510154702.GA28938@twiddle.net>
Mime-Version: 1.0
Content-Type: Text/Plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1035
Lines: 37

From: Richard Henderson <rth@twiddle.net>
Date: Wed, 10 May 2006 08:47:13 -0700

> How do you plan to address the compiler optimizing
 ...
> Across the schedule, we may have changed cpus, making the cached
> address invalid.

Per-cpu variables need to be accessed only with preemption
disabled.  And the preemption enable/disable operations
provide a compiler memory barrier.

#define preempt_disable() \
do { \
	inc_preempt_count(); \
	barrier(); \
} while (0)

 ...

#define preempt_enable() \
do { \
	preempt_enable_no_resched(); \
	barrier(); \
	preempt_check_resched(); \
} while (0)

The scheduler itself need to take care to not cause the situation
you mention either.

Therefore this is an issue we had already, not some new thing
introduced by using __thread for per-cpu variables.
-
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/