From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Date: Fri, 14 Jan 2005 04:14:21 +0000 Subject: Re: page table lock patch V15 [0/7]: overview Message-Id: <20050114041421.GA41559@muc.de> List-Id: References: <41E4BCBE.2010001@yahoo.com.au> <20050112014235.7095dcf4.akpm@osdl.org> <20050112104326.69b99298.akpm@osdl.org> <41E73EE4.50200@linux-m68k.org> In-Reply-To: <41E73EE4.50200@linux-m68k.org> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Roman Zippel Cc: Christoph Lameter , Andrew Morton , nickpiggin@yahoo.com.au, torvalds@osdl.org, hugh@veritas.com, linux-mm@kvack.org, linux-ia64@vger.kernel.org, linux-kernel@vger.kernel.org, benh@kernel.crashing.org On Fri, Jan 14, 2005 at 04:39:16AM +0100, Roman Zippel wrote: > Hi, > > Christoph Lameter wrote: > > >Introduction of the cmpxchg is one atomic operations that replaces the two > >spinlock ops typically necessary in an unpatched kernel. Obtaining the > >spinlock requires an spinlock (which is an atomic operation) and then the > >release involves a barrier. So there is a net win for all SMP cases as far > >as I can see. > > But there might be a loss in the UP case. Spinlocks are optimized away, > but your cmpxchg emulation enables/disables interrupts with every access. Only for 386s and STI/CLI is quite cheap there. -Andi