From owner-freebsd-bugs@FreeBSD.ORG Wed Aug 25 05:00:24 2010 Return-Path: Delivered-To: freebsd-bugs@hub.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 4A233106572D for ; Wed, 25 Aug 2010 05:00:24 +0000 (UTC) (envelope-from gnats@FreeBSD.org) Received: from freefall.freebsd.org (freefall.freebsd.org [IPv6:2001:4f8:fff6::28]) by mx1.freebsd.org (Postfix) with ESMTP id 4D6378FC3A for ; Wed, 25 Aug 2010 05:00:17 +0000 (UTC) Received: from freefall.freebsd.org (localhost [127.0.0.1]) by freefall.freebsd.org (8.14.4/8.14.4) with ESMTP id o7P50HAq090110 for ; Wed, 25 Aug 2010 05:00:17 GMT (envelope-from gnats@freefall.freebsd.org) Received: (from gnats@localhost) by freefall.freebsd.org (8.14.4/8.14.4/Submit) id o7P50Hcx090103; Wed, 25 Aug 2010 05:00:17 GMT (envelope-from gnats) Date: Wed, 25 Aug 2010 05:00:17 GMT Message-Id: <201008250500.o7P50Hcx090103@freefall.freebsd.org> To: freebsd-bugs@FreeBSD.org From: Garrett Cooper Cc: Subject: Re: kern/145385: [cpu] Logical processor cannot be disabled for some SMT-enabled Intel procs X-BeenThere: freebsd-bugs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Garrett Cooper List-Id: Bug reports List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 25 Aug 2010 05:00:24 -0000 The following reply was made to PR kern/145385; it has been noted by GNATS. From: Garrett Cooper To: Garrett Cooper Cc: Jeff Roberson , bug-followup@freebsd.org, jkim@freebsd.org, Attilio Rao , jeff@freebsd.org Subject: Re: kern/145385: [cpu] Logical processor cannot be disabled for some SMT-enabled Intel procs Date: Tue, 24 Aug 2010 21:50:20 -0700 On Tue, Aug 24, 2010 at 3:45 PM, Garrett Cooper wrote= : > On Tue, Aug 24, 2010 at 2:51 PM, Garrett Cooper wrot= e: >> On Aug 24, 2010, at 2:03 PM, Jeff Roberson wrote: >> >> >> On Tue, 24 Aug 2010, Garrett Cooper wrote: >> >> On Tue, Aug 24, 2010 at 12:22 PM, Jeff Roberson >> wrote: >> >> On Tue, 24 Aug 2010, Garrett Cooper wrote: >> >> On Mon, Aug 23, 2010 at 6:33 AM, John Baldwin wrote: >> >> On Sunday, August 22, 2010 4:17:37 am Garrett Cooper wrote: >> >> =A0 =A0 =A0 The following trivial patch fixes the issue on my W3520 proc= essor; >> >> AFAICS >> >> it's what should be done after reading several of the specs because the >> >> logical count that's tracked with ebx is exactly what is needed for >> >> logical_cpus (it's an absolute quantity). I need to verify it with a >> >> multi-cpu >> >> topology at work (the two r710s I was testing with E-series Xeons on >> >> aren't >> >> available remotely right now). >> >> Thanks! >> >> -Garrett >> >> Jung-uk Kim and Attilio Rao have both been looking at this code recently >> >> and >> >> are in a better position to review the patch in the PR. >> >> (Moving jhb@ to BCC, adding jeff@ for possible input on ULE) >> >> The patch works as expected (it now properly detects the SMIT CPUs as >> >> logical CPUs), but setting machdep.hlt_logical_cpus=3D1 causes other >> >> problems with scheduling tasks because certain kernel threads get >> >> stuck at boot when netbooting (in particular I've seen problems with >> >> usbhub* and a few others bits), so in order for >> >> machdep.hlt_logical_cpus to be fixed on SMT processors, it might >> >> require some changes to the ULE scheduler to shuffle around the >> >> threads to available cores/processors? >> >> >> hlt_logical_cpus should be rewritten to use cpusets to change the defaul= t >> >> system set rather than specifically halting those cpus. =A0There are a n= umber >> >> of loops in the kernel that iterate over all cpus and attempt to bind an= d >> >> perform some task. =A0I think there are a number of other reasons to pre= fer a >> >> less aggressive approach to avoiding the logical cpus as well. Simply >> >> preventing user thread schedule will achieve the intent of the sysctl in= any >> >> event. >> >> =A0=A0Ok... in that event then the bug is ok, but maybe I should add >> >> some code to the patch to warn the user about functional issues >> >> associated with halting logical CPUs? >> >> I don't think the bug is ok. =A0We probably shouldn't have sysctls which >> readily break the kernel. =A0As I said we should instead have the sysctl >> backend to cpuset. =A0It shouldn't take more than an hour to code and te= st. > > =A0 =A0Ok.. I'll look at this once I have my other system back online so > I can actively break something until I get it to work. BTW... there's a lot of code in machdep.c that does the same thing to idle the CPU, for instance, cpu_idle_hlt, cpu_idle_acpi, cpu_idle_amdc1e (on amd64). What should be done about those cases (same thing, or different)? Thanks, -Garrett