From owner-freebsd-arm@FreeBSD.ORG Mon Mar 17 10:16:17 2014 Return-Path: Delivered-To: freebsd-arm@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 595A6C0F for ; Mon, 17 Mar 2014 10:16:17 +0000 (UTC) Received: from mail-ve0-f180.google.com (mail-ve0-f180.google.com [209.85.128.180]) (using TLSv1 with cipher ECDHE-RSA-RC4-SHA (128/128 bits)) (No client certificate requested) by mx1.freebsd.org (Postfix) with ESMTPS id 13BA6DB4 for ; Mon, 17 Mar 2014 10:16:16 +0000 (UTC) Received: by mail-ve0-f180.google.com with SMTP id jz11so5330257veb.39 for ; Mon, 17 Mar 2014 03:16:09 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:mime-version:in-reply-to:references:date :message-id:subject:from:to:content-type; bh=HHJXEuaOk5zKBW3LT1+NZXA2LfPc7/JNi0Sbi1IO9qU=; b=Opp0v3U/t3mYGlLjXU9UxWnpQ/K3EIlnfUQJ1BM1lLkQEC+HB1ytIRJoWwfkGO5VDm 3hSU6eI+IIIAYBOZlT4CYpFZS7f5v+AKs+vzMXJPIqoqCVs7U6xF3OrMV8Z6uhJbuNEm yn5aT+ctssUEr6j1X5tHH27lO39vEql3bLaquy2LUL7HpaLGgoXdefRvoU+tVQ+ou2f/ XY0D/IiAuY0hUVBgmjPnF98M0J/fY3iAK2WRXQOwERIR/wPSbfB8nSf3fnUjrJo9oOnQ K+vMNC9bHFYvwKU29yd/Q9dB285Og/m5zPoci2sUJDO81oEDCBZG7Js51S/VnEiEDAAn zU7w== X-Gm-Message-State: ALoCoQmpnLAA0o172T7ZN35y0AT336qNm0UgKlL6IOS79o16erS6U4PwvIZyPAgQAB7Unshx/I8o MIME-Version: 1.0 X-Received: by 10.52.165.105 with SMTP id yx9mr15810421vdb.22.1395044952185; Mon, 17 Mar 2014 01:29:12 -0700 (PDT) Received: by 10.220.209.135 with HTTP; Mon, 17 Mar 2014 01:29:12 -0700 (PDT) In-Reply-To: <20131222123636.GA61193@ci0.org> References: <20131220125638.GA5132@mail.bsdpad.com> <20131222092913.GA89153@mail.bsdpad.com> <20131222123636.GA61193@ci0.org> Date: Mon, 17 Mar 2014 09:29:12 +0100 Message-ID: Subject: Re: arm SMP on Cortex-A15 From: Wojciech Macek To: freebsd-arm@freebsd.org Content-Type: text/plain; charset=ISO-8859-1 X-Content-Filtered-By: Mailman/MimeDel 2.1.17 X-BeenThere: freebsd-arm@freebsd.org X-Mailman-Version: 2.1.17 Precedence: list List-Id: "Porting FreeBSD to ARM processors." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 17 Mar 2014 10:16:17 -0000 Hi, Finally I've found some time to continue SMP hacking. It seems that I isolated the tlb/pmam failures and developed two simple patches that help. There are still some pmap changes and TEX remap left, but I don't want to use them now. https://drive.google.com/folderview?id=0B-7yTLrPxaWtSzZPUGgtM3pnUjg&usp=sharing * 01 - ensure that TTB is set before TLB invalidation and flush BTB to comply the specs * 02 - add missing TLB invalidations to pmap and fix invalidation order I chose buildworld -j4 as a stresstest, and run it on Arndale (USB rootfs) and a different 4-core a15 chip (SATA rootfs). On both setups test passed and was significantly faster than the one with previous patchset. I'd like to submit these changes to FreeBSD tree (with some help from our local committers), so any comments and testing are really appreciated. Best regards, Wojtek 2013-12-22 13:36 GMT+01:00 Olivier Houchard : > On Sun, Dec 22, 2013 at 11:53:47AM +0100, Wojciech Macek wrote: > > Thanks, so it seems that there is still something wrong... > > From what I observed, the place where you got the panic was the most > likely > > to fail if there are issues with TLB cache. I guess your case can also > have > > the same root case. Nevertheless, I'll try to reproduce your setup and > > debug it futher. > > > > Regards, > > Wojtek > > I'm quite sure Ruslan's panic happens because the VFP code isn't completely > smp-safe, and I have patches that hopefully fixes this. > > Regards, > > Olivier > > >