MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Message-ID: <18996.60235.178618.531664@cargo.ozlabs.ibm.com>
Date: Sun, 14 Jun 2009 22:21:31 +1000
From: Paul Mackerras <paulus@samba.org>
To: Avi Kivity <avi@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>, benh@kernel.crashing.org,
       akpm@linux-foundation.org, linuxppc-dev@ozlabs.org,
       linux-kernel@vger.kernel.org
Subject: Re: [PATCH 1/2] lib: Provide generic atomic64_t implementation
In-Reply-To: <4A34E4A5.3040306@redhat.com>
References: <18995.20685.227683.561827@cargo.ozlabs.ibm.com>
	<alpine.LFD.2.01.0906131312470.3237@localhost.localdomain>
	<alpine.LFD.2.01.0906131323270.3237@localhost.localdomain>
	<4A34E4A5.3040306@redhat.com>
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 825
Lines: 21

Avi Kivity writes:

> An alternative implementation using 64-bit cmpxchg will recover most of 
> the costs of hashed spinlocks.  I assume most serious 32-bit 
> architectures have them?

Have a 64-bit cmpxchg, you mean?  x86 is the only one I know of, and
it already has an atomic64_t implementation using cmpxchg8b (or
whatever it's called).

My thinking is that the 32-bit non-x86 architectures will be mostly
UP, so the overhead is just an interrupt enable/restore.  Those that
are SMP I would expect to be small SMP -- mostly just 2 cpus and maybe
a few 4-way systems.

Paul.
--
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/