From owner-freebsd-mips@FreeBSD.ORG Sun Oct 23 17:10:44 2011 Return-Path: Delivered-To: freebsd-mips@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id ABDDE1065675; Sun, 23 Oct 2011 17:10:44 +0000 (UTC) (envelope-from mipsjunkie@gmail.com) Received: from mail-gx0-f182.google.com (mail-gx0-f182.google.com [209.85.161.182]) by mx1.freebsd.org (Postfix) with ESMTP id 1EDD28FC12; Sun, 23 Oct 2011 17:10:44 +0000 (UTC) Received: by ggnq2 with SMTP id q2so4973493ggn.13 for ; Sun, 23 Oct 2011 10:10:43 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; bh=Qk8ECCYWoxQ7ifFC36AJUIVf9+gOr83wamXUroYlRKQ=; b=g7rXZBRqMl2PUb06Dc7saabQVddQlDMq0xtBjAOGzyaz9SDuZ9gYrCipbE8WD2GD0S d+LA7Uz2anoeCZz6q+byu81vGJcjeq/cnXX8VGuLsyA6+T9YXyPEDY08bS3IZ66dOuje 6y/FRFnHWxtkOq45TmTg9tMSwzqF/wL/x0WRY= MIME-Version: 1.0 Received: by 10.182.77.196 with SMTP id u4mr2589046obw.19.1319389843426; Sun, 23 Oct 2011 10:10:43 -0700 (PDT) Received: by 10.182.42.40 with HTTP; Sun, 23 Oct 2011 10:10:43 -0700 (PDT) In-Reply-To: <072342B7-4DED-4F0B-ADAE-BCCA8A4A63D4@bluezbox.com> References: <072342B7-4DED-4F0B-ADAE-BCCA8A4A63D4@bluezbox.com> Date: Sun, 23 Oct 2011 22:40:43 +0530 Message-ID: From: Rohit J To: Oleksandr Tymoshenko Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Cc: freebsd-mips Subject: Re: Assembler complains about use of $at after ".set noat" on sd instr X-BeenThere: freebsd-mips@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Porting FreeBSD to MIPS List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 23 Oct 2011 17:10:44 -0000 Thanks a ton Juli and Oleksandr. :) I shall try the patch and let you know how it goes. rohit On Sun, Oct 23, 2011 at 10:17 PM, Oleksandr Tymoshenko wrote: > > On 2011-10-21, at 3:27 PM, Juli Mallett wrote: > >> On Fri, Oct 21, 2011 at 14:56, Rohit J wrote: >>> the big picture story is that >>> as a partial fix to using octeon specific very large mult instructions >>> in our freebsd kernel >>> (for crypto related ops), we had initially disabled >>> interrupts=3D>context switches >> >> Assuming you're using the stuff in-tree, that's my fault :) >> >>> Need to see if there is a better way to do it. >>> am now trying to see if it makes sense to save those registers and >>> remove the disable interrupt constraint for running these large multipl= ication >>> instructions. >>> will be adapting the (multiplication context save/restore) >>> in the octeon HRM and will revert if i have any further questions. >> >> gonzo@ has incomplete patches, you may want to ask him. =A0Alternately, >> look at how FPU context is lazily switched on other architectures. >> > > Here is the latest version of my patch: > http://people.freebsd.org/~gonzo/patches/cop2.diff > > context is saved for kernel threads only, usage of crypto stuff from user= land is not supported.