From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Message-ID: <18082.46270.713491.488496@cargo.ozlabs.ibm.com> Date: Sun, 22 Jul 2007 11:37:02 +1000 From: Paul Mackerras To: Andrew Morton Subject: Re: [PATCH 1/2] OProfile - Enable SPU switch notification to detect currently active SPU tasks - update In-Reply-To: <20070720130241.176c50a5.akpm@linux-foundation.org> References: <200707201424.07292.rrnelson@linux.vnet.ibm.com> <20070720130241.176c50a5.akpm@linux-foundation.org> Cc: Maynard Johnson , Philippe Elie , linuxppc , Bob Nelson , Arnd Bergmann , oprofile List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Andrew Morton writes: > I still wonder about that barrier. At the least it should be smp_mb(). > But aren't our set_bit() semantics _alone_ sufficient to make this barrier > unneeded? No, but our wake_up semantics certainly ought to be, if they aren't already. It's the wake_up which implies synchronization with other tasks, not the set_bit. Paul.