From owner-svn-src-all@FreeBSD.ORG Wed Aug 11 14:29:23 2010 Return-Path: Delivered-To: svn-src-all@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 3DD891065673; Wed, 11 Aug 2010 14:29:23 +0000 (UTC) (envelope-from asmrookie@gmail.com) Received: from mail-gy0-f182.google.com (mail-gy0-f182.google.com [209.85.160.182]) by mx1.freebsd.org (Postfix) with ESMTP id 97B2C8FC21; Wed, 11 Aug 2010 14:29:22 +0000 (UTC) Received: by gyg4 with SMTP id 4so52651gyg.13 for ; Wed, 11 Aug 2010 07:29:21 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:sender:received :in-reply-to:references:date:x-google-sender-auth:message-id:subject :from:to:cc:content-type:content-transfer-encoding; bh=M8l88OOL7BDHVi3Sa5upYQ/zQ/+xJtmYdh8B0ITVI6I=; b=LimvdgklPZ9/l6LADaAEYHmzh5Yt2/fWo1euyotJzBwYLFJ/fzqb1txEd4BKXqaE6a s5mU9+MbvQDMO46YOJt0fYol17x6mlE1kGiS79dI2Sa7feqsOcgV35ZaOCsobEM0s2Xg TAsk9c+Y0ULXrayQ+T3hldJkCwbpT4+NKeMyk= DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; b=Xt13IXyaHT+wl69cjNHdkYMyKYA/NjOlKe9DZZwx3H5eKGT9W3jRQkfDjVBLMcN+2Q myAhjgm81BJ/ofiVLJvJksqYzHQEBZx9lyijopmoKlFcGdp5JMTkpHsSEkbsVliN6Hqw ALLJ4BTyqSTuH2elCXgBpvuGfAiCJTSl3OBmY= MIME-Version: 1.0 Received: by 10.151.79.13 with SMTP id g13mr4231899ybl.286.1281536961398; Wed, 11 Aug 2010 07:29:21 -0700 (PDT) Sender: asmrookie@gmail.com Received: by 10.151.116.3 with HTTP; Wed, 11 Aug 2010 07:29:21 -0700 (PDT) In-Reply-To: <20100811123430.GK2396@deviant.kiev.zoral.com.ua> References: <201008111051.o7BApRp4028538@svn.freebsd.org> <20100811105739.GJ2396@deviant.kiev.zoral.com.ua> <20100811123430.GK2396@deviant.kiev.zoral.com.ua> Date: Wed, 11 Aug 2010 16:29:21 +0200 X-Google-Sender-Auth: GHWvjNc5TJ9g0DojmGciWnBPGRA Message-ID: From: Attilio Rao To: Kostik Belousov Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Cc: svn-src-head@freebsd.org, svn-src-all@freebsd.org, src-committers@freebsd.org, Jeff Roberson , John Baldwin Subject: Re: svn commit: r211176 - in head/sys: amd64/amd64 i386/i386 X-BeenThere: svn-src-all@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: "SVN commit messages for the entire src tree \(except for " user" and " projects" \)" List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 11 Aug 2010 14:29:23 -0000 2010/8/11 Kostik Belousov : > On Wed, Aug 11, 2010 at 01:21:46PM +0200, Attilio Rao wrote: >> 2010/8/11 Kostik Belousov : >> > On Wed, Aug 11, 2010 at 10:51:27AM +0000, Attilio Rao wrote: >> >> Author: attilio >> >> Date: Wed Aug 11 10:51:27 2010 >> >> New Revision: 211176 >> >> URL: http://svn.freebsd.org/changeset/base/211176 >> >> >> >> Log: >> >> =C2=A0 IPI handlers may run generally with interrupts disabled becaus= e they >> >> =C2=A0 are served via an interrupt gate. >> >> >> >> =C2=A0 However, that doesn't explicitly prevent preemption and thread >> >> =C2=A0 migration thus scheduler pinning may be necessary in some hand= lers. >> >> =C2=A0 Fix that. >> > >> > How the preemption is supposed to happen ? Aside from the explicit >> > calls to mi_switch() from e.g. critical_exit(). >> >> IIRC it should be hardclock() willing to schedule the softclock(). It >> is the critical_exit() in the thread_unlock() that may trigger it >> (sorry for not digging more, it was a while back that I hacked this >> part, but I guess you can verify on your own). >> We already have other points within the kernel that take care of >> dealing with preemption/migration like lapic_handle_timer(), for >> example. > > Right, and if the interrupts are indeed disabled, I do not see how > the preemption may be triggered in the fragments like > =C2=A0 =C2=A0 =C2=A0 =C2=A0cpu =3D PCPU_GET(cpuid); > =C2=A0 =C2=A0 =C2=A0 =C2=A0cpumask =3D PCPU_GET(cpumask); I don't recall all the details and I have no time to dig now. However, also spinlock_enter() does disable explicitly preemption via critical_enter() after have disabled the interrupts. Let me CC jhb as he implemented spinlock_enter() and may have a clue about how preemption can happen with interrupts disabled. Thanks, Attilio --=20 Peace can only be achieved by understanding - A. Einstein