From mboxrd@z Thu Jan  1 00:00:00 1970
From: torvalds@linux-foundation.org (Linus Torvalds)
Date: Thu, 12 Feb 2009 13:15:08 -0800 (PST)
Subject: [ltt-dev] [RFC git tree] Userspace RCU (urcu) for Linux (repost)
In-Reply-To: <20090212203924.GK6759@linux.vnet.ibm.com>
References: <20090211214258.GA32407@Krystal>
	<20090212003549.GU6694@linux.vnet.ibm.com>
	<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>
Message-ID: <alpine.LFD.2.00.0902121247040.3099@localhost.localdomain>



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.

			Linus