Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 20 Jan 2000 08:44:57 -0800
From:      Arun Sharma <adsharma@sharmas.dhs.org>
To:        Zhihui Zhang <zzhang@cs.binghamton.edu>
Cc:        hackers@freebsd.org
Subject:   Re: Accessing user data from kernel
Message-ID:  <20000120084457.A19569@sharmas.dhs.org>
In-Reply-To: <Pine.GSO.3.96.1000120095742.24022A-100000@sol.cs.binghamton.edu>; from Zhihui Zhang on Thu, Jan 20, 2000 at 10:04:16AM -0500
References:  <200001200214.SAA17214@c62443-a.frmt1.sfba.home.com> <Pine.GSO.3.96.1000120095742.24022A-100000@sol.cs.binghamton.edu>

next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, Jan 20, 2000 at 10:04:16AM -0500, Zhihui Zhang wrote:
> Point 2 seems to be saying that we would rather sacrifice some performance
> to gain a cleaner interface (people are talking about eliminating kernel
> copying for a long time). Consider the physical I/O on a raw device, where
> we map the user data again in the KVA without copying the data. Why do we
> do this double mapping, when we can access the user data directly?
> 

Direct I/O to user space should be treated as an optimization. Such I/O
requires wiring down all the user pages before I/O can happen. Hence
it requires special previleges.

Why does it get mapped to KVA ? Because of point 1.

	-Arun


To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20000120084457.A19569>