From owner-freebsd-current@FreeBSD.ORG Wed Nov 5 01:40:32 2003 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id A234316A4CE for ; Wed, 5 Nov 2003 01:40:32 -0800 (PST) Received: from mail.chesapeake.net (chesapeake.net [208.142.252.6]) by mx1.FreeBSD.org (Postfix) with ESMTP id A9EB843FAF for ; Wed, 5 Nov 2003 01:40:31 -0800 (PST) (envelope-from jroberson@chesapeake.net) Received: from localhost (jroberson@localhost) by mail.chesapeake.net (8.11.6/8.11.6) with ESMTP id hA59eNR74975; Wed, 5 Nov 2003 04:40:23 -0500 (EST) (envelope-from jroberson@chesapeake.net) Date: Wed, 5 Nov 2003 04:40:23 -0500 (EST) From: Jeff Roberson To: David Xu In-Reply-To: <3FA8BD16.2080705@viatech.com.cn> Message-ID: <20031105043821.A10222-100000@mail.chesapeake.net> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII cc: Jun Su cc: current@freebsd.org Subject: Re: SYSENTER in FreeBSD X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 05 Nov 2003 09:40:32 -0000 On Wed, 5 Nov 2003, David Xu wrote: > Jun Su wrote: > > >I noticed that Jeff Roberson implement this already. Is whi will be commit? > >http://kerneltrap.org/node/view/1531 > > > >I google this because I found this feature is listed in the list of Kernel Improvement of WindowsXP. :-) > > > >Thanks, > >Jun Su > > > > > > > I have almost done this experiment about 10 months ago. > http://people.freebsd.org/~davidxu/fastsyscall/ > The patch is out of date and still not complete. > Also it can give you some performance improve, but I think too many > things need to be changed, > and this really makes user ret code very dirty, some syscalls, for > example, pipe() can not use > this fast syscall, becaues pipe() seems using two registers to return > file handle, the performance gain > is immediately lost when the assemble code becomes more complex. I don't > think this hack is worth > to do on IA32, I heard AMD has different way to support fast syscall, > that may already in FreeBSD > AMD 64 branch. This works with every syscall. I have a patch in perforce that doesn't require any changes to userret(). The performance gain is not so substantial for most things but I feel that it is worth it. Mini is probably going to finish this up over the next week or so. Cheers, Jeff > > David Xu > > > _______________________________________________ > freebsd-current@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-current > To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org" >