From mboxrd@z Thu Jan  1 00:00:00 1970
From: Nikita Danilov <nikita@clusterfs.com>
Subject: Re: Writing out a (file) mmapped page
Date: Tue, 14 Jun 2005 20:37:45 +0400
Message-ID: <17071.2009.722920.324990@gargle.gargle.HOWL>
References: <8e70aacf050612094916d32276@mail.gmail.com>
	<1118763383.16269.61.camel@imp.csi.cam.ac.uk>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Cc: linux-fsdevel@vger.kernel.org
Return-path: <linux-fsdevel-owner@vger.kernel.org>
Received: from [80.71.243.242] ([80.71.243.242]:12502 "EHLO tau.rusteko.ru")
	by vger.kernel.org with ESMTP id S261238AbVFNQhp (ORCPT
	<rfc822;linux-fsdevel@vger.kernel.org>);
	Tue, 14 Jun 2005 12:37:45 -0400
To: Anton Altaparmakov <aia21@cam.ac.uk>
In-Reply-To: <1118763383.16269.61.camel@imp.csi.cam.ac.uk>
Sender: linux-fsdevel-owner@vger.kernel.org
List-Id: linux-fsdevel.vger.kernel.org

Anton Altaparmakov writes:

[...]

 > 
 > That is a little trickier than one might expect because it is partially
 > done in hardware (heavily arch dependent though).
 > 
 > When a write to a writable mmapped page happens the CPU sets the page
 > dirty flag in hardware.  So there is no code where you can see this
 > happen.  Later on, at msync() time or munmap() time, this hardware dirty
 > bit results in a set_page_dirty() being called which for buffer based

This also happens when page migrates to the cold end of "VM LRU list"
(tail of the inactive list, technically).

Nikita.