From mboxrd@z Thu Jan  1 00:00:00 1970
From: paulmck@linux.vnet.ibm.com (Paul E. McKenney)
Date: Thu, 12 Feb 2009 13:59:59 -0800
Subject: [ltt-dev] [RFC git tree] Userspace RCU (urcu) for Linux	(repost)
In-Reply-To: <alpine.LFD.2.00.0902121247040.3099@localhost.localdomain>
References: <20090212023308.GA21157@linux.vnet.ibm.com>
	<20090212040824.GA12346@Krystal>
	<20090212050120.GA8317@linux.vnet.ibm.com>
	<20090212070539.GA15896@Krystal>
	<20090212164621.GC6759@linux.vnet.ibm.com>
	<20090212192941.GC2047@Krystal>
	<20090212200249.GG6759@linux.vnet.ibm.com>
	<alpine.LFD.2.00.0902121210120.3099@localhost.localdomain>
	<20090212203924.GK6759@linux.vnet.ibm.com>
	<alpine.LFD.2.00.0902121247040.3099@localhost.localdomain>
Message-ID: <20090212215959.GN6759@linux.vnet.ibm.com>

On Thu, Feb 12, 2009 at 01:15:08PM -0800, Linus Torvalds wrote:
> 
> 
> On Thu, 12 Feb 2009, Paul E. McKenney wrote:
> > 
> > In other words, you are arguing for using ACCESS_ONCE() in the loops,
> > but keeping the old ACCESS_ONCE() definition, and declaring BF hardware
> > broken?
> 
> Well, I _also_ argue that if you have a busy loop, you'd better have a 
> cpu_relax() in there somewhere anyway. If you don't, you have a bug.
> 
> So I think the BF approach is "borderline broken", but I think it should 
> work, if BF just has whatever appropriate cache flush in its cpu_relax.

OK, got it.  Keep ACCESS_ONCE() as is, make sure any busy-wait
loops contain a cpu_relax().  A given busy loop might or might not
need ACCESS_ONCE(), but that decision is independent of hardware
considerations.

Ah, and blackfin's cpu_relax() does seem to have migrated from barrier()
to smp_mb() recently, so sounds good to me!!!

							Thanx, Paul