Date: Mon, 7 Feb 2011 11:17:25 -0600 (CST)
From: Christoph Lameter <cl@linux.com>
To: Jan Beulich <JBeulich@novell.com>
cc: tj@kernel.org, mingo@elte.hu, tglx@linutronix.de,
        linux-kernel@vger.kernel.org, hpa@zytor.com
Subject: Re: x86: mis-named percpu_xchg_op() after switch to cmpxchg?
In-Reply-To: <4D4FDF050200007800030883@vpn.id2.novell.com>
Message-ID: <alpine.DEB.2.00.1102071115070.3911@router.home>
References: <4D4FDF050200007800030883@vpn.id2.novell.com>
User-Agent: Alpine 2.00 (DEB 1167 2008-08-23)
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 803
Lines: 17

On Mon, 7 Feb 2011, Jan Beulich wrote:

> Other than its name implies, with the switch to use cmpxchg instead of
> xchg (commit 8270137a0d50507a5b40f880db636527045b8466) this
> macro is no longer suitable for accessing anything that may be written
> by other than the local CPU (i.e. anything but the various this_cpu
> accessors). Shouldn't it therefore get renamed to eg this_cpu_xchg_op()?

No. The intend of the percpu_xchg_op was also to provide local cpu only
semantics. percpu_xx operations in general have the same semantics as
this_cpu operations.

--
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/