From owner-freebsd-smp Sun Dec 1 15:52:47 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 3829C37B401 for ; Sun, 1 Dec 2002 15:52:46 -0800 (PST) Received: from mail.interchange.ca (ns.interchange.ca [216.126.79.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id DCCE543E9C for ; Sun, 1 Dec 2002 15:52:45 -0800 (PST) (envelope-from michael@fastmail.ca) Received: by mail.interchange.ca (Fastmailer, from userid 555) id 894C32250; Sun, 1 Dec 2002 18:54:58 -0500 (EST) Received: from 24.43.130.241 by www.fastmail.ca with HTTP; Sun, 1 Dec 2002 23:54:58 +0000 (UTC) MIME-Version: 1.0 Message-Id: <3DEAA152.000003.36383@ns.interchange.ca> Content-Type: Multipart/Mixed; boundary="------------Boundary-00=_M3TGULUXFQQMYJ0CCJD0" To: smp@FreeBSD.ORG Subject: Intel SE7500CW2 Date: Sun, 1 Dec 2002 18:54:58 -0500 (EST) From: "Michael Richards" X-Fastmail-IP: [24.43.130.241] Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org --------------Boundary-00=_M3TGULUXFQQMYJ0CCJD0 Content-Type: Text/Plain Content-Transfer-Encoding: 7bit Hi. I tried updating the BIOS on this board to 1.18 but it didn't make any difference in being able to boot SMP. The board appears to work fine as a single processor board. Now that I've got serial support hooked up, any suggestions on getting further? FreeBSD 4.7-STABLE #1: Sun Dec 1 23:00:01 GMT 2002 root@test.interchange.ca:/usr/obj/usr/src/sys/TEST Timecounter "i8254" frequency 1193182 Hz CPU: Pentium 4 (1993.54-MHz 686-class CPU) Origin = "GenuineIntel" Id = 0xf24 Stepping = 4 Features=0x3febfbff,ACC> real memory = 2146959360 (2096640K bytes) avail memory = 2088095744 (2039156K bytes) Programming 24 pins in IOAPIC #0 IOAPIC #0 intpin 2 -> irq 0 Programming 24 pins in IOAPIC #1 Programming 24 pins in IOAPIC #2 AP #1 (PHY# 6) failed! panic y/n? [y] -Michael _________________________________________________________________ http://fastmail.ca/ - Fast Secure Web Email for Canadians --------------Boundary-00=_M3TGULUXFQQMYJ0CCJD0-- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sun Dec 1 16:53: 0 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B4EAE37B401 for ; Sun, 1 Dec 2002 16:52:58 -0800 (PST) Received: from mail.interchange.ca (ns.interchange.ca [216.126.79.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id 18EED43EBE for ; Sun, 1 Dec 2002 16:52:58 -0800 (PST) (envelope-from michael@fastmail.ca) Received: by mail.interchange.ca (Fastmailer, from userid 555) id DB98C22E2; Sun, 1 Dec 2002 19:55:10 -0500 (EST) Received: from 24.43.130.241 by www.fastmail.ca with HTTP; Mon, 2 Dec 2002 00:55:10 +0000 (UTC) MIME-Version: 1.0 Message-Id: <3DEAAF6E.000005.36395@ns.interchange.ca> Content-Type: Multipart/Mixed; boundary="------------Boundary-00=_YVVGK72XFQQMYJ0CCJD0" To: jwd@bsdwins.com Subject: Re: Intel SE7500CW2 Cc: freebsd-smp@freebsd.org Date: Sun, 1 Dec 2002 19:55:10 -0500 (EST) From: "Michael Richards" X-Fastmail-IP: [24.43.130.241] Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org --------------Boundary-00=_YVVGK72XFQQMYJ0CCJD0 Content-Type: Text/Plain Content-Transfer-Encoding: 7bit >> Now that I've got serial support hooked up, any suggestions on >> getting further? >> >> FreeBSD 4.7-STABLE #1: Sun Dec 1 23:00:01 GMT >> 2002 >> >> root@test.interchange.ca:/usr/obj/usr/src/sys/TEST >> >> Timecounter "i8254" frequency 1193182 Hz >> CPU: Pentium 4 (1993.54-MHz 686-class CPU) >> Origin = "GenuineIntel" Id = 0xf24 Stepping = 4 > > I seem to remember something about disabling onboard > scsi in the BIOS... Have you given this a try? The board doesn't have SCSI. It's got this funky Promise IDE RAID feature but it is disabled. I'm trying to figure out where it's actually barfing. I don't understand how SMP works so I may be getting in a little above my head. All the same, if I can find out what the decision is for this panic I may understand it a little better. Perhaps it's related to the apic id of the AP being 6 instead of 1... Here is some more boot info I forgot to include before... Programming 24 pins in IOAPIC #0 IOAPIC #0 intpin 2 -> irq 0 Programming 24 pins in IOAPIC #1 Programming 24 pins in IOAPIC #2 AP #1 (PHY# 6) failed! panic y/n? [y] FreeBSD/SMP: Multiprocessor motherboard cpu0 (BSP): apic id: 0, version: 0x00050014, at 0xfee00000 cpu1 (AP): apic id: 6, version: 0x00000000, at 0xfee00000 io0 (APIC): apic id: 2, version: 0x00178020, at 0xfec00000 io1 (APIC): apic id: 3, version: 0x00178020, at 0xfec80000 io2 (APIC): apic id: 4, version: 0x00178020, at 0xfec80400 Preloaded elf kernel "kernel" at 0xc0315000. -Michael _________________________________________________________________ http://fastmail.ca/ - Fast Secure Web Email for Canadians --------------Boundary-00=_YVVGK72XFQQMYJ0CCJD0-- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sun Dec 1 18:23:10 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 9D8F437B401 for ; Sun, 1 Dec 2002 18:23:08 -0800 (PST) Received: from mail.interchange.ca (ns.interchange.ca [216.126.79.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4566343EBE for ; Sun, 1 Dec 2002 18:23:08 -0800 (PST) (envelope-from michael@fastmail.ca) Received: by mail.interchange.ca (Fastmailer, from userid 555) id 914BE39D9; Sun, 1 Dec 2002 21:23:05 -0500 (EST) Received: from 24.43.130.241 by www.fastmail.ca with HTTP; Mon, 2 Dec 2002 02:23:05 +0000 (UTC) MIME-Version: 1.0 Message-Id: <3DEAC409.000009.36383@ns.interchange.ca> Content-Type: Multipart/Mixed; boundary="------------Boundary-00=_HYZG0DJXFQQMYJ0CCJD0" To: freebsd-smp@freebsd.org Subject: Intel SE7500CW2 narrowed down... Date: Sun, 1 Dec 2002 21:23:05 -0500 (EST) From: "Michael Richards" X-Fastmail-IP: [24.43.130.241] Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org --------------Boundary-00=_HYZG0DJXFQQMYJ0CCJD0 Content-Type: Text/Plain Content-Transfer-Encoding: 7bit Ok, I've been hacking up /usr/src/sys/i386/i386/mp_machdep.c to spit out some more debugging stuff. Here is what I have now. Programming 24 pins in IOAPIC #0 IOAPIC #0 intpin 2 -> irq 0 Programming 24 pins in IOAPIC #1 Programming 24 pins in IOAPIC #2 Starting application processors...Initializing APIC...Done. Installing AP 1st level boot code...Done. Setting up P->V mapping...Done. Starting AP 1 of 1 calling start_ap(1,9a000) This is physical CPU 6 at 0x9a Timed out waiting for processor to start! fake processor starting y/n? [n] Done. FreeBSD/SMP: Multiprocessor motherboard cpu0 (BSP): apic id: 0, version: 0x00050014, at 0xfee00000 cpu1 (AP): apic id: 6, version: 0x00000000, at 0xfee00000 io0 (APIC): apic id: 2, version: 0x00178020, at 0xfec00000 io1 (APIC): apic id: 3, version: 0x00178020, at 0xfec80000 io2 (APIC): apic id: 4, version: 0x00178020, at 0xfec80400 Interesting notes: a) the version for the AP CPU seems bogus and the address shows up in the list the same as cpu0. This happens both in the original kernel and my hacked up one. b) The failure happens in start_ap and it happens at the end of the function where mp_ncpus doesn't get incremented. For kicks I tried hacking it up to give you the option of returning a 1 so the system would continue. Had no effect. Since I'm getting in over my head here I'm assuming that the start_ap function sends the CPU off to increment the mp_ncpus and fill in the entry giving its version and address. This is a very broad assumption. If I'm remotely correct then our second CPU isn't doing anything and as a result even trying to trick it the SMP never comes on. If anyone can direct me or take over, or provide any other debugging type patch it would be greatly appreciated. I've been looking around for technical docs don't really know what I'm looking for. Any ideas? -Michael _________________________________________________________________ http://fastmail.ca/ - Fast Secure Web Email for Canadians --------------Boundary-00=_HYZG0DJXFQQMYJ0CCJD0-- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Dec 3 14:41:49 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id C35A937B401 for ; Tue, 3 Dec 2002 14:41:48 -0800 (PST) Received: from mailhub.cns.ksu.edu (grunt.ksu.ksu.edu [129.130.12.17]) by mx1.FreeBSD.org (Postfix) with ESMTP id C9E6343ECD for ; Tue, 3 Dec 2002 14:41:47 -0800 (PST) (envelope-from beemern@ksu.edu) Received: from unix2.cc.ksu.edu (daemon@unix2.cc.ksu.edu [129.130.12.4]) by mailhub.cns.ksu.edu (8.9.1/8.9.1/mailhub+tar) with ESMTP id QAA15040 for ; Tue, 3 Dec 2002 16:41:41 -0600 (CST) Received: from localhost (beemern@localhost) by unix2.cc.ksu.edu (8.11.6+Sun/8.11.6) with ESMTP id gB3MfdK28906 for ; Tue, 3 Dec 2002 16:41:39 -0600 (CST) X-Authentication-Warning: unix2.cc.ksu.edu: beemern owned process doing -bs Date: Tue, 3 Dec 2002 16:41:39 -0600 (CST) From: beemern X-X-Sender: To: Subject: Re: Intel SE7500CW2 narrowed down... Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org > Ok, I've been hacking up /usr/src/sys/i386/i386/mp_machdep.c to spit > out some more debugging stuff. Here is what I have now. You're covering already covered ground if you'll check the last few months archives, you'll see this issue with the SE7500CW2 addressed and re-addressed time and again i *was* waiting on a fix, and then thought perhaps fbsd 5.0 with its SMPng would be the answer... however, after comparing mach_dep.c etc from the 4.x tree and the current tree, i doubt thats an answer the good news? linux works great (windows too for that matter), and having converted, i'm now fully smp functional nathan To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Dec 3 15:57:54 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 83AC137B401 for ; Tue, 3 Dec 2002 15:57:53 -0800 (PST) Received: from paja.kn.vutbr.cz (paja.kn.vutbr.cz [147.229.191.135]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3C62043EB2 for ; Tue, 3 Dec 2002 15:57:52 -0800 (PST) (envelope-from ra@kn.vutbr.cz) Received: from kn.vutbr.cz (p2-204a.kn.vutbr.cz [147.229.204.30]) by paja.kn.vutbr.cz (8.11.6/8.11.6) with ESMTP id gB3NvnE08474 for ; Wed, 4 Dec 2002 00:57:50 +0100 (CET) (envelope-from ra@kn.vutbr.cz) Message-ID: <3DED44FD.1090407@kn.vutbr.cz> Date: Wed, 04 Dec 2002 00:57:49 +0100 From: Vaclav Musil User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.0.0) Gecko/20020623 Debian/1.0.0-0.woody.1 X-Accept-Language: cs, en MIME-Version: 1.0 To: smp@FreeBSD.ORG Subject: Re: Intel SE7500CW2 narrowed down... References: Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org I tried 5.0-DP2, unfortunately the same result. :( V. beemern wrote: >>Ok, I've been hacking up /usr/src/sys/i386/i386/mp_machdep.c to spit >>out some more debugging stuff. Here is what I have now. > > > You're covering already covered ground > if you'll check the last few months archives, you'll see this issue with > the SE7500CW2 addressed and re-addressed time and again > > i *was* waiting on a fix, and then thought perhaps fbsd 5.0 with its SMPng > would be the answer... however, after comparing mach_dep.c etc from the > 4.x tree and the current tree, i doubt thats an answer > > the good news? linux works great (windows too for that matter), and > having converted, i'm now fully smp functional > > nathan > > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-smp" in the body of the message To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Dec 3 17:44:39 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D793F37B401 for ; Tue, 3 Dec 2002 17:44:36 -0800 (PST) Received: from mail.interchange.ca (ns.interchange.ca [216.126.79.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7CD0B43EAF for ; Tue, 3 Dec 2002 17:44:36 -0800 (PST) (envelope-from michael@fastmail.ca) Received: by mail.interchange.ca (Fastmailer, from userid 555) id 4FBE825A8; Tue, 3 Dec 2002 20:44:38 -0500 (EST) Received: from 24.43.130.241 by www.fastmail.ca with HTTP; Wed, 4 Dec 2002 01:44:38 +0000 (UTC) MIME-Version: 1.0 Message-Id: <3DED5E06.00000D.37680@ns.interchange.ca> Content-Type: Multipart/Mixed; boundary="------------Boundary-00=_EINKGJZXFQQMYJ0CCJD0" To: beemern@ksu.edu Subject: Re: Intel SE7500CW2 narrowed down... Cc: freebsd-smp@freebsd.org Date: Tue, 3 Dec 2002 20:44:38 -0500 (EST) From: "Michael Richards" X-Fastmail-IP: [24.43.130.241] Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org --------------Boundary-00=_EINKGJZXFQQMYJ0CCJD0 Content-Type: Text/Plain Content-Transfer-Encoding: 7bit > You're covering already covered ground > if you'll check the last few months archives, you'll see this > issue with the SE7500CW2 addressed and re-addressed time and again I actually did a lot of searching and wasn't able to find any machdep code with debugging added. > i *was* waiting on a fix, and then thought perhaps fbsd 5.0 with > its SMPng would be the answer... however, after comparing > mach_dep.c etc from the 4.x tree and the current tree, i doubt > thats an answer It's been confirmed that DP2 doesn't fix the problem. Instead of waiting for someone to fix this I'm putting time into it myself. John is feeding me some patches and we're trying to get it fixed. > the good news? linux works great (windows too for that matter), > and having converted, i'm now fully smp functional That's good news for me. I can look at the linux code and see if they're initialising the AP any differently. Unfortunately linux's verion 2.0.43-patchlevel-4-subpatch-344-build-82 just ends up being too much of a headache to admin. -Michael _________________________________________________________________ http://fastmail.ca/ - Fast Secure Web Email for Canadians --------------Boundary-00=_EINKGJZXFQQMYJ0CCJD0-- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Tue Dec 3 20:38:31 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 701F837B401 for ; Tue, 3 Dec 2002 20:38:30 -0800 (PST) Received: from speedy.insekure.com (gotroot.insekure.com [207.254.222.218]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6EC0343EAF for ; Tue, 3 Dec 2002 20:38:26 -0800 (PST) (envelope-from james@JamesSchmidt.Com) Received: from localhost (james@localhost.insekure.com [127.0.0.1]) by speedy.insekure.com (8.12.5/8.12.3) with ESMTP id gB44bYXK086648; Tue, 3 Dec 2002 22:37:34 -0600 (CST) (envelope-from james@JamesSchmidt.Com) Date: Tue, 3 Dec 2002 22:37:34 -0600 (CST) From: James Schmidt X-X-Sender: james@speedy.insekure.com To: Michael Richards Cc: beemern@ksu.edu, Subject: Re: Intel SE7500CW2 narrowed down... In-Reply-To: <3DED5E06.00000D.37680@ns.interchange.ca> Message-ID: <20021203223549.R86634-100000@speedy.insekure.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org I'm glad that there is still someone working on this issue. As I am stuck with this system board, no kernel programming expertise, and unable to migrate to any other OS, this effort is greatly appreciated. Don't give up :) -James Schmidt On Tue, 3 Dec 2002, Michael Richards wrote: > > You're covering already covered ground > > if you'll check the last few months archives, you'll see this > > issue with the SE7500CW2 addressed and re-addressed time and again > > I actually did a lot of searching and wasn't able to find any machdep > code with debugging added. > > > i *was* waiting on a fix, and then thought perhaps fbsd 5.0 with > > its SMPng would be the answer... however, after comparing > > mach_dep.c etc from the 4.x tree and the current tree, i doubt > > thats an answer > > It's been confirmed that DP2 doesn't fix the problem. Instead of > waiting for someone to fix this I'm putting time into it myself. John > is feeding me some patches and we're trying to get it fixed. > > > the good news? linux works great (windows too for that matter), > > and having converted, i'm now fully smp functional > > That's good news for me. I can look at the linux code and see if > they're initialising the AP any differently. Unfortunately linux's > verion 2.0.43-patchlevel-4-subpatch-344-build-82 just ends up being > too much of a headache to admin. > > -Michael > _________________________________________________________________ > http://fastmail.ca/ - Fast Secure Web Email for Canadians To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 6:26:41 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id BDD7037B401 for ; Wed, 4 Dec 2002 06:26:40 -0800 (PST) Received: from mailhub.cns.ksu.edu (grunt.ksu.ksu.edu [129.130.12.17]) by mx1.FreeBSD.org (Postfix) with ESMTP id 152F443ED4 for ; Wed, 4 Dec 2002 06:26:39 -0800 (PST) (envelope-from beemern@ksu.edu) Received: from unix2.cc.ksu.edu (daemon@unix2.cc.ksu.edu [129.130.12.4]) by mailhub.cns.ksu.edu (8.9.1/8.9.1/mailhub+tar) with ESMTP id IAA08099 for ; Wed, 4 Dec 2002 08:26:38 -0600 (CST) Received: from localhost (beemern@localhost) by unix2.cc.ksu.edu (8.11.6+Sun/8.11.6) with ESMTP id gB4EQZZ09688 for ; Wed, 4 Dec 2002 08:26:35 -0600 (CST) X-Authentication-Warning: unix2.cc.ksu.edu: beemern owned process doing -bs Date: Wed, 4 Dec 2002 08:26:34 -0600 (CST) From: beemern X-X-Sender: To: Subject: Re: Intel SE7500CW2 narrowed down... Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Lanny Baron wrote: > > "having converted" ? Are you saying you dumped FreeBSD to use another > OS due to a Server Board? you better believe it the archives show that i (with a friend) spent a good deal of time testing and debugging the kernel on this mobo with the smp folks, but to no avail i just dont have the time to solve this myself.. and if i could, i'd be a damn committer i love fbsd, but i need *results* even more, and if that means i gotta use linux so that i can make this system work and perform as needed, well, my affections must give way to prudence To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 7:26:12 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id AA70A37B401 for ; Wed, 4 Dec 2002 07:26:11 -0800 (PST) Received: from alpha.de.tiscali.com (alpha.de.tiscali.com [62.27.91.200]) by mx1.FreeBSD.org (Postfix) with ESMTP id C255843EBE for ; Wed, 4 Dec 2002 07:26:09 -0800 (PST) (envelope-from Oliver.Blasnik@de.tiscali.com) Received: from de-ex-01.de.tiscali.com (de-ex-01.de.tiscali.com [10.49.8.74]) by alpha.de.tiscali.com (Postfix) with ESMTP id 8BFA764C28; Wed, 4 Dec 2002 16:26:02 +0100 (CET) Received: from de-ex-02.de.tiscali.com ([10.49.8.76]) by de-ex-01.de.tiscali.com with Microsoft SMTPSVC(5.0.2195.5329); Wed, 4 Dec 2002 16:26:01 +0100 Received: from TECHNIK47 ([10.49.10.29]) by de-ex-02.de.tiscali.com with Microsoft SMTPSVC(5.0.2195.5329); Wed, 4 Dec 2002 16:26:00 +0100 Message-ID: <015301c29ba9$737e98d0$1d0a310a@de.tiscali.com> From: "Oliver Blasnik" To: "beemern" , References: Subject: Re: Intel SE7500CW2 narrowed down... Date: Wed, 4 Dec 2002 16:26:00 +0100 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2800.1106 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1106 X-OriginalArrivalTime: 04 Dec 2002 15:26:00.0993 (UTC) FILETIME=[7388F910:01C29BA9] Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Hi there, > Lanny Baron wrote: > > > > "having converted" ? Are you saying you dumped FreeBSD to use another > > OS due to a Server Board? > you better believe it > i love fbsd, but i need *results* even more, and if that means i gotta > use linux so that i can make this system work and perform as needed, > well, my affections must give way to prudence I fully agree to Nathan, I had the same problem and the same solution: use another OS. I really can't spend that much time to deploy which server board / manufacturer FreeBSD likes and which not. SMP is a thing that doesn't work atm, so I don't use FreeBSD for SMP anymore 'till it gets stable and compatible again. I sometimes can't believe that all the boards at least work _somehow_ with other operating systems, but not with FreeBSD. Even went back using sparc/solaris again... My personal conclusion: SMP is for non-productional environment only, as every cvsup/upgrade/hardware change possibly breaks the whole system. Oliver To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 9:21:41 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 52E0E37B401 for ; Wed, 4 Dec 2002 09:21:40 -0800 (PST) Received: from mail.speakeasy.net (mail17.speakeasy.net [216.254.0.217]) by mx1.FreeBSD.org (Postfix) with ESMTP id D17E243EB2 for ; Wed, 4 Dec 2002 09:21:39 -0800 (PST) (envelope-from jhb@FreeBSD.org) Received: (qmail 8149 invoked from network); 4 Dec 2002 17:21:42 -0000 Received: from unknown (HELO server.baldwin.cx) ([216.27.160.63]) (envelope-sender ) by mail17.speakeasy.net (qmail-ldap-1.03) with DES-CBC3-SHA encrypted SMTP for ; 4 Dec 2002 17:21:42 -0000 Received: from laptop.baldwin.cx (gw1.twc.weather.com [216.133.140.1]) by server.baldwin.cx (8.12.6/8.12.6) with ESMTP id gB4HLauH041373; Wed, 4 Dec 2002 12:21:37 -0500 (EST) (envelope-from jhb@FreeBSD.org) Message-ID: X-Mailer: XFMail 1.5.2 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <015301c29ba9$737e98d0$1d0a310a@de.tiscali.com> Date: Wed, 04 Dec 2002 12:21:44 -0500 (EST) From: John Baldwin To: Oliver Blasnik Subject: Re: Intel SE7500CW2 narrowed down... Cc: smp@FreeBSD.ORG, beemern Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 04-Dec-2002 Oliver Blasnik wrote: > Hi there, > >> Lanny Baron wrote: >> > >> > "having converted" ? Are you saying you dumped FreeBSD to use another >> > OS due to a Server Board? >> you better believe it > >> i love fbsd, but i need *results* even more, and if that means i gotta >> use linux so that i can make this system work and perform as needed, >> well, my affections must give way to prudence > > I fully agree to Nathan, I had the same problem and the same solution: > use another OS. I really can't spend that much time to deploy which > server board / manufacturer FreeBSD likes and which not. SMP is a thing > that doesn't work atm, so I don't use FreeBSD for SMP anymore 'till > it gets stable and compatible again. I sometimes can't believe that > all the boards at least work _somehow_ with other operating systems, > but not with FreeBSD. Even went back using sparc/solaris again... > > My personal conclusion: SMP is for non-productional environment only, > as every cvsup/upgrade/hardware change possibly breaks the whole system. SMP is only broken on i386 for P4's on this one motherboard. It works perfectly fine on other motherboards. As yet we haven't figured out what exactly about this motherboard is broken. I can tell you that the way in which we startup CPU's is quite within the IA-32 spec and that it's probably about 90% that this motherboard has some h0rked BIOS. For example, we already know that it needed a BIOS update for SMP to work with Netware. The problem with this motherboard is likely not a FreeBSD problem and the best we can do is try to workaround it once we figure out what it's problem is. -- John Baldwin <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 9:23:40 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 3818237B401 for ; Wed, 4 Dec 2002 09:23:39 -0800 (PST) Received: from alpha.de.tiscali.com (alpha.de.tiscali.com [62.27.91.200]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0D7DE43E9C for ; Wed, 4 Dec 2002 09:23:37 -0800 (PST) (envelope-from Oliver.Blasnik@de.tiscali.com) Received: from de-ex-01.de.tiscali.com (de-ex-01.de.tiscali.com [10.49.8.74]) by alpha.de.tiscali.com (Postfix) with ESMTP id 1DFC864C6D; Wed, 4 Dec 2002 18:23:22 +0100 (CET) Received: from de-ex-02.de.tiscali.com ([10.49.8.76]) by de-ex-01.de.tiscali.com with Microsoft SMTPSVC(5.0.2195.5329); Wed, 4 Dec 2002 18:23:21 +0100 Received: from TECHNIK47 ([10.49.10.29]) by de-ex-02.de.tiscali.com with Microsoft SMTPSVC(5.0.2195.5329); Wed, 4 Dec 2002 18:23:21 +0100 Message-ID: <01ed01c29bb9$d8027550$1d0a310a@de.tiscali.com> From: "Oliver Blasnik" To: "Lanny Baron" , "beemern" , References: <015301c29ba9$737e98d0$1d0a310a@de.tiscali.com> <001801c29bb5$f09a5ff0$0200a8c0@noemie> Subject: Re: Intel SE7500CW2 narrowed down... Date: Wed, 4 Dec 2002 18:23:21 +0100 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 8bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2800.1106 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1106 X-OriginalArrivalTime: 04 Dec 2002 17:23:21.0613 (UTC) FILETIME=[D81253D0:01C29BB9] Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Hi Lanny, From: "Lanny Baron" ["Our Servers do work with FreeBSD"] > So in short, and yes this is repetitive, if you or the other fellow had > chosen us to build you a Server, you and the other fellow would not have > encountered the SMP problem and, you would still be running FreeBSD. Even worse, multiple times... "FreeBSD SMP for Lannys servers"? ;) And, no, why should we buy (a) from the US and (b) from a "small" OEM? Working in a european-wide company has some side effects - for example a policy to buy only specific servers from specific vendors (which have to be available in all that countrys). So, there are only the "Big Players", f.ex. HP, SUN, ...´ Back to track: this is no solution; buying hardware by OS needs and not by system needs/policy/[insert-any-other-reason]. If the OS doesn't work with a standard hardware it's simply of no use. Don't get me wrong, I WANT to use FreeBSD - but this isn't my choice anymore if it does not run on our typical hardware. I hate to use Linux and I definately hate to use Solaris (and even pay for that crap). > Regards, > Lanny Oliver To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 9:32:46 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id C949137B401; Wed, 4 Dec 2002 09:32:45 -0800 (PST) Received: from alpha.de.tiscali.com (alpha.de.tiscali.com [62.27.91.200]) by mx1.FreeBSD.org (Postfix) with ESMTP id EEAB843ECD; Wed, 4 Dec 2002 09:32:44 -0800 (PST) (envelope-from Oliver.Blasnik@de.tiscali.com) Received: from de-ex-01.de.tiscali.com (de-ex-01.de.tiscali.com [10.49.8.74]) by alpha.de.tiscali.com (Postfix) with ESMTP id 41BF664C6D; Wed, 4 Dec 2002 18:32:44 +0100 (CET) Received: from de-ex-02.de.tiscali.com ([10.49.8.76]) by de-ex-01.de.tiscali.com with Microsoft SMTPSVC(5.0.2195.5329); Wed, 4 Dec 2002 18:32:43 +0100 Received: from TECHNIK47 ([10.49.10.29]) by de-ex-02.de.tiscali.com with Microsoft SMTPSVC(5.0.2195.5329); Wed, 4 Dec 2002 18:32:43 +0100 Message-ID: <01fb01c29bbb$26d729e0$1d0a310a@de.tiscali.com> From: "Oliver Blasnik" To: "John Baldwin" Cc: , "beemern" References: Subject: Re: Intel SE7500CW2 narrowed down... Date: Wed, 4 Dec 2002 18:32:43 +0100 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2800.1106 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2800.1106 X-OriginalArrivalTime: 04 Dec 2002 17:32:43.0358 (UTC) FILETIME=[26E5CFE0:01C29BBB] Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Hello John, > SMP is only broken on i386 for P4's on this one motherboard. > It works perfectly fine on other motherboards. This isn't my perception after reading PRs every day and also trying out FreeBSD/SMP-STABLE+CURRENT sometimes on some of our labs hardware. > I can tell you that the way in which we startup CPU's is quite within > the IA-32 spec and that it's probably about 90% that this motherboard > has some h0rked BIOS. I know of this BIOS / tables problem. But why is f. ex. Linux able to boot up without any glitch and works as fast as expected (not knowing it from exactly this board, but from others I tested)? Yes, I know, i shouldn't compare those two OS. But in fact, there are many hardware related things working very, very well with Linux and don't do with FreeBSD. And - I do compare those two OS every- time if I try to get some people over to the FreeBSD side, so comparing them has it's good sides, too ;-) Oliver To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 9:46:48 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id C50E737B401 for ; Wed, 4 Dec 2002 09:46:46 -0800 (PST) Received: from mail.interchange.ca (ns.interchange.ca [216.126.79.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6B4F143ECF for ; Wed, 4 Dec 2002 09:46:46 -0800 (PST) (envelope-from michael@fastmail.ca) Received: by mail.interchange.ca (Fastmailer, from userid 555) id 8AA31275B; Wed, 4 Dec 2002 12:46:57 -0500 (EST) Received: from 24.43.130.241 by www.fastmail.ca with HTTP; Wed, 4 Dec 2002 17:46:57 +0000 (UTC) MIME-Version: 1.0 Message-Id: <3DEE3F91.000019.37680@ns.interchange.ca> Content-Type: Multipart/Mixed; boundary="------------Boundary-00=_92WLS3CYA1UMYJ0CCJD0" To: oliver.blasnik@de.tiscali.com Subject: Re: Intel SE7500CW2 narrowed down... Cc: freebsd-smp@freebsd.org Date: Wed, 4 Dec 2002 12:46:57 -0500 (EST) From: "Michael Richards" X-Fastmail-IP: [24.43.130.241] Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org --------------Boundary-00=_92WLS3CYA1UMYJ0CCJD0 Content-Type: Text/Plain Content-Transfer-Encoding: 7bit > Hello John, > >> SMP is only broken on i386 for P4's on this one motherboard. >> It works perfectly fine on other motherboards. > > This isn't my perception after reading PRs every day and also > trying out FreeBSD/SMP-STABLE+CURRENT sometimes on some of our > labs hardware. We've been running FreeBSD-SMP for 3 years now under some very heavily loaded servers without a problem. Ok, the SMP isn't the fastest implementation but I've found the 5.0-DP2 on our alpha runs pretty fast even compared to a similar Tru64 machine. >> I can tell you that the way in which we startup CPU's is quite >> within the IA-32 spec and that it's probably about 90% that this >> motherboard has some h0rked BIOS. > > I know of this BIOS / tables problem. But why is f. ex. Linux able > to boot up without any glitch and works as fast as expected (not > knowing it from exactly this board, but from others I tested)? I'm not convinced it's a tables problem as I read the spec and verified the CPU entries in this table byte for byte. It appears valid. Besides, Linux works and so do a host of other OSes. More than likely we're just doing something slightly different that happens to work find with all the other boards out there. My next step is to start looking at how linux works and compare it to how FreeBSD doesn't work. -Michael _________________________________________________________________ http://fastmail.ca/ - Fast Secure Web Email for Canadians --------------Boundary-00=_92WLS3CYA1UMYJ0CCJD0-- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 10:11:47 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id E782137B401 for ; Wed, 4 Dec 2002 10:11:45 -0800 (PST) Received: from mail.speakeasy.net (mail15.speakeasy.net [216.254.0.215]) by mx1.FreeBSD.org (Postfix) with ESMTP id 2752043EC2 for ; Wed, 4 Dec 2002 10:11:45 -0800 (PST) (envelope-from jhb@FreeBSD.org) Received: (qmail 13719 invoked from network); 4 Dec 2002 18:11:49 -0000 Received: from unknown (HELO server.baldwin.cx) ([216.27.160.63]) (envelope-sender ) by mail15.speakeasy.net (qmail-ldap-1.03) with DES-CBC3-SHA encrypted SMTP for ; 4 Dec 2002 18:11:49 -0000 Received: from laptop.baldwin.cx (gw1.twc.weather.com [216.133.140.1]) by server.baldwin.cx (8.12.6/8.12.6) with ESMTP id gB4IBhuH041562; Wed, 4 Dec 2002 13:11:43 -0500 (EST) (envelope-from jhb@FreeBSD.org) Message-ID: X-Mailer: XFMail 1.5.2 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <01ed01c29bb9$d8027550$1d0a310a@de.tiscali.com> Date: Wed, 04 Dec 2002 13:11:50 -0500 (EST) From: John Baldwin To: Oliver Blasnik Subject: Re: Intel SE7500CW2 narrowed down... Cc: smp@FreeBSD.ORG, beemern , Lanny Baron Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 04-Dec-2002 Oliver Blasnik wrote: > Hi Lanny, > > From: "Lanny Baron" > > ["Our Servers do work with FreeBSD"] >> So in short, and yes this is repetitive, if you or the other fellow had >> chosen us to build you a Server, you and the other fellow would not have >> encountered the SMP problem and, you would still be running FreeBSD. > > Even worse, multiple times... "FreeBSD SMP for Lannys servers"? ;) > > And, no, why should we buy (a) from the US and (b) from a "small" OEM? > Working in a european-wide company has some side effects - for example > a policy to buy only specific servers from specific vendors (which have > to be available in all that countrys). So, there are only the "Big > Players", f.ex. HP, SUN, ...´ > > Back to track: this is no solution; buying hardware by OS needs and not > by system needs/policy/[insert-any-other-reason]. If the OS doesn't work > with a standard hardware it's simply of no use. Don't get me wrong, I > WANT to use FreeBSD - but this isn't my choice anymore if it does not run > on our typical hardware. I hate to use Linux and I definately hate to > use Solaris (and even pay for that crap). The problem here (which people don't seem to realize) is that this ServerWorks mobo BIOS is exhibiting NON-STANDARD behavior. Go complain to SW about their BIOS or get them to tell us what in the world they have changed so we can work around it. -- John Baldwin <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 10:11:54 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 9409C37B401 for ; Wed, 4 Dec 2002 10:11:52 -0800 (PST) Received: from mail.speakeasy.net (mail16.speakeasy.net [216.254.0.216]) by mx1.FreeBSD.org (Postfix) with ESMTP id AAC0443EAF for ; Wed, 4 Dec 2002 10:11:51 -0800 (PST) (envelope-from jhb@FreeBSD.org) Received: (qmail 7077 invoked from network); 4 Dec 2002 18:11:56 -0000 Received: from unknown (HELO server.baldwin.cx) ([216.27.160.63]) (envelope-sender ) by mail16.speakeasy.net (qmail-ldap-1.03) with DES-CBC3-SHA encrypted SMTP for ; 4 Dec 2002 18:11:56 -0000 Received: from laptop.baldwin.cx (gw1.twc.weather.com [216.133.140.1]) by server.baldwin.cx (8.12.6/8.12.6) with ESMTP id gB4IBnuH041571; Wed, 4 Dec 2002 13:11:50 -0500 (EST) (envelope-from jhb@FreeBSD.org) Message-ID: X-Mailer: XFMail 1.5.2 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <01fb01c29bbb$26d729e0$1d0a310a@de.tiscali.com> Date: Wed, 04 Dec 2002 13:11:57 -0500 (EST) From: John Baldwin To: Oliver Blasnik Subject: Re: Intel SE7500CW2 narrowed down... Cc: beemern , smp@FreeBSD.ORG Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 04-Dec-2002 Oliver Blasnik wrote: > Hello John, > >> SMP is only broken on i386 for P4's on this one motherboard. >> It works perfectly fine on other motherboards. > > This isn't my perception after reading PRs every day and also trying > out FreeBSD/SMP-STABLE+CURRENT sometimes on some of our labs hardware. The only other reported/known problems are on older Pentium and possibly PPro machines. Do you have any other SMP i386 arch machines that do not work? >> I can tell you that the way in which we startup CPU's is quite within >> the IA-32 spec and that it's probably about 90% that this motherboard >> has some h0rked BIOS. > > I know of this BIOS / tables problem. But why is f. ex. Linux able to > boot up without any glitch and works as fast as expected (not knowing > it from exactly this board, but from others I tested)? > > Yes, I know, i shouldn't compare those two OS. But in fact, there > are many hardware related things working very, very well with Linux > and don't do with FreeBSD. And - I do compare those two OS every- > time if I try to get some people over to the FreeBSD side, so > comparing them has it's good sides, too ;-) Apparently both Linux and Windows use a different algorithm for starting up AP's on i386 in that (I think) they send broadcast IPI's instead of IPI'ing each CPU individually. Both methods are valid methods as far as the IA-32 arch are concerned. However, BIOS writers are known to write buggy non-standard code that they only test on Windows. For a classic example of this, go read up on the El Tortito CD-ROM boot standard and the no-emulation booting method which _clearly_ allows for a CD to specify the number of blocks to load up to 640k to allow for arbitrary sized bootstrap programs. However, since NT just used a single sector (4k) bootstrap program, all BIOS's I have run into blatantly ignore this length field and only read in one sector regardless. Whoever wrote the BIOS for these motherboards may suffer from similar malady of either 1) not being able to read, or 2) not knowing how to test. -- John Baldwin <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 11:29:43 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 5EBD837B401 for ; Wed, 4 Dec 2002 11:29:42 -0800 (PST) Received: from swan.mail.pas.earthlink.net (swan.mail.pas.earthlink.net [207.217.120.123]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0E87C43E88 for ; Wed, 4 Dec 2002 11:29:42 -0800 (PST) (envelope-from tlambert2@mindspring.com) Received: from pool0345.cvx40-bradley.dialup.earthlink.net ([216.244.43.90] helo=mindspring.com) by swan.mail.pas.earthlink.net with esmtp (Exim 3.33 #1) id 18JfDB-0004uf-00; Wed, 04 Dec 2002 11:29:34 -0800 Message-ID: <3DEE4970.5C2DACAA@mindspring.com> Date: Wed, 04 Dec 2002 10:29:04 -0800 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: Oliver Blasnik Cc: beemern , smp@FreeBSD.ORG Subject: Re: Intel SE7500CW2 narrowed down... References: <015301c29ba9$737e98d0$1d0a310a@de.tiscali.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Oliver Blasnik wrote: > > Lanny Baron wrote: > > i love fbsd, but i need *results* even more, and if that means i gotta > > use linux so that i can make this system work and perform as needed, > > well, my affections must give way to prudence > > I fully agree to Nathan, I had the same problem and the same solution: > use another OS. I really can't spend that much time to deploy which > server board / manufacturer FreeBSD likes and which not. SMP is a thing > that doesn't work atm, so I don't use FreeBSD for SMP anymore 'till > it gets stable and compatible again. I sometimes can't believe that > all the boards at least work _somehow_ with other operating systems, > but not with FreeBSD. Even went back using sparc/solaris again... > > My personal conclusion: SMP is for non-productional environment only, > as every cvsup/upgrade/hardware change possibly breaks the whole system. This is really unfair. The problem is that the board is not compliant with the Intel MP Spec. 1.4, with regard to APIC I/O. The workaround is to not use APIC I/O, which you can't do in SMP in FreeBSD, and which you can do in SMP in other OS's, but shouldn't do. If you look at the interrupt routing code differences between FreeBSD and Linux, you will find where they differ. FreeBSD interrupt routing follows Giant. An alternative is to correct the SMP Table information, and reflash your BIOS with a hacked version, rather than one from Intel. But that's a lot of work you have to do on your own. -- Terry To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 11:29:45 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 36B8F37B404 for ; Wed, 4 Dec 2002 11:29:43 -0800 (PST) Received: from swan.mail.pas.earthlink.net (swan.mail.pas.earthlink.net [207.217.120.123]) by mx1.FreeBSD.org (Postfix) with ESMTP id D482D43E88 for ; Wed, 4 Dec 2002 11:29:42 -0800 (PST) (envelope-from tlambert2@mindspring.com) Received: from pool0345.cvx40-bradley.dialup.earthlink.net ([216.244.43.90] helo=mindspring.com) by swan.mail.pas.earthlink.net with esmtp (Exim 3.33 #1) id 18JfDF-00050Q-00; Wed, 04 Dec 2002 11:29:37 -0800 Message-ID: <3DEE4B88.4781DFF1@mindspring.com> Date: Wed, 04 Dec 2002 10:38:00 -0800 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: Oliver Blasnik Cc: Lanny Baron , beemern , smp@FreeBSD.ORG Subject: Re: Intel SE7500CW2 narrowed down... References: <015301c29ba9$737e98d0$1d0a310a@de.tiscali.com> <001801c29bb5$f09a5ff0$0200a8c0@noemie> <01ed01c29bb9$d8027550$1d0a310a@de.tiscali.com> Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Oliver Blasnik wrote: > And, no, why should we buy (a) from the US and (b) from a "small" OEM? To get working hardware? 8-) 8-). > Working in a european-wide company has some side effects - for example > a policy to buy only specific servers from specific vendors (which have= > to be available in all that countrys). So, there are only the "Big > Players", f.ex. HP, SUN, ...=B4 > = > Back to track: this is no solution; buying hardware by OS needs and not= > by system needs/policy/[insert-any-other-reason]. If the OS doesn't wor= k > with a standard hardware it's simply of no use. Don't get me wrong, I > WANT to use FreeBSD - but this isn't my choice anymore if it does not r= un > on our typical hardware. I hate to use Linux and I definately hate to > use Solaris (and even pay for that crap). May I suggest that you buy MP Intel motherboards from the Intel Server Products division of Intel, rather than from the division of Intel that decided not to stair-step PCI IRQ's by slot, until two years after everyone else did it so that everything would not end up on "INT A"? -- Terry To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 11:29:48 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 39EB037B41A; Wed, 4 Dec 2002 11:29:45 -0800 (PST) Received: from swan.mail.pas.earthlink.net (swan.mail.pas.earthlink.net [207.217.120.123]) by mx1.FreeBSD.org (Postfix) with ESMTP id 84B7243EBE; Wed, 4 Dec 2002 11:29:45 -0800 (PST) (envelope-from tlambert2@mindspring.com) Received: from pool0345.cvx40-bradley.dialup.earthlink.net ([216.244.43.90] helo=mindspring.com) by swan.mail.pas.earthlink.net with esmtp (Exim 3.33 #1) id 18JfDM-0005Cm-00; Wed, 04 Dec 2002 11:29:45 -0800 Message-ID: <3DEE51A6.90BE5C12@mindspring.com> Date: Wed, 04 Dec 2002 11:04:06 -0800 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: John Baldwin Cc: Oliver Blasnik , beemern , smp@FreeBSD.ORG Subject: Re: Intel SE7500CW2 narrowed down... References: Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org John Baldwin wrote: > The only other reported/known problems are on older Pentium and possibly > PPro machines. Do you have any other SMP i386 arch machines that do not > work? [ ... ] > Apparently both Linux and Windows use a different algorithm for starting > up AP's on i386 in that (I think) they send broadcast IPI's instead of > IPI'ing each CPU individually. This is why they work on old ASUS Pentium 90 boxes, and FreeBSD does not. It's not related to the P4 SE7500CW2-type problems, which are incorrect APIC description and chipset programming. -- Terry To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 11:29:53 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id A472F37B40D for ; Wed, 4 Dec 2002 11:29:51 -0800 (PST) Received: from swan.mail.pas.earthlink.net (swan.mail.pas.earthlink.net [207.217.120.123]) by mx1.FreeBSD.org (Postfix) with ESMTP id D937A43EB2 for ; Wed, 4 Dec 2002 11:29:50 -0800 (PST) (envelope-from tlambert2@mindspring.com) Received: from pool0345.cvx40-bradley.dialup.earthlink.net ([216.244.43.90] helo=mindspring.com) by swan.mail.pas.earthlink.net with esmtp (Exim 3.33 #1) id 18JfDQ-0005J0-00; Wed, 04 Dec 2002 11:29:48 -0800 Message-ID: <3DEE523C.D7984CD8@mindspring.com> Date: Wed, 04 Dec 2002 11:06:36 -0800 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: Michael Richards Cc: oliver.blasnik@de.tiscali.com, freebsd-smp@freebsd.org Subject: Re: Intel SE7500CW2 narrowed down... References: <3DEE3F91.000019.37680@ns.interchange.ca> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Michael Richards wrote: > >> I can tell you that the way in which we startup CPU's is quite > >> within the IA-32 spec and that it's probably about 90% that this > >> motherboard has some h0rked BIOS. > > > > I know of this BIOS / tables problem. But why is f. ex. Linux able > > to boot up without any glitch and works as fast as expected (not > > knowing it from exactly this board, but from others I tested)? > > I'm not convinced it's a tables problem as I read the spec and > verified the CPU entries in this table byte for byte. It appears > valid. Besides, Linux works and so do a host of other OSes. More than > likely we're just doing something slightly different that happens to > work find with all the other boards out there. > > My next step is to start looking at how linux works and compare it to > how FreeBSD doesn't work. You will find it in the APIC I/O code and the interrupt routing code, with a tiny part in the shipset initialization. You could fix it in FreeBSD by disregarding what the BIOS says, and manually initializing the ServerWorks chipset the way FreeBSD wants it (i.e. MPSpec v1.4, mode 2 interrupt processing compliant). FreeBSD doesn't run in real "virtual wire mode", it makes the interrupts follow Giant. -- Terry To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 12: 1:50 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id A61BF37B401; Wed, 4 Dec 2002 12:01:48 -0800 (PST) Received: from mail.interchange.ca (ns.interchange.ca [216.126.79.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id 4B4BE43E4A; Wed, 4 Dec 2002 12:01:48 -0800 (PST) (envelope-from michael@fastmail.ca) Received: by mail.interchange.ca (Fastmailer, from userid 555) id D53E3243D; Wed, 4 Dec 2002 15:01:59 -0500 (EST) Received: from 24.43.130.241 by www.fastmail.ca with HTTP; Wed, 4 Dec 2002 20:01:59 +0000 (UTC) MIME-Version: 1.0 Message-Id: <3DEE5F37.000003.43942@ns.interchange.ca> Content-Type: Multipart/Mixed; boundary="------------Boundary-00=_BB2MULUXFQQMYJ0CCJD0" To: tlambert2@mindspring.com Subject: Re: Intel SE7500CW2 narrowed down... Cc: jhb@FreeBSD.org, freebsd-smp@freebsd.org Date: Wed, 4 Dec 2002 15:01:59 -0500 (EST) From: "Michael Richards" X-Fastmail-IP: [24.43.130.241] Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org --------------Boundary-00=_BB2MULUXFQQMYJ0CCJD0 Content-Type: Text/Plain Content-Transfer-Encoding: 7bit >> I'm not convinced it's a tables problem as I read the spec and >> verified the CPU entries in this table byte for byte. It appears >> valid. Besides, Linux works and so do a host of other OSes. More >> than likely we're just doing something slightly different that >> happens to work find with all the other boards out there. >> >> My next step is to start looking at how linux works and compare >> it to how FreeBSD doesn't work. > > You will find it in the APIC I/O code and the interrupt routing > code, with a tiny part in the shipset initialization. > > You could fix it in FreeBSD by disregarding what the BIOS says, > and manually initializing the ServerWorks chipset the way FreeBSD > wants it (i.e. MPSpec v1.4, mode 2 interrupt processing > compliant). FreeBSD doesn't run in real "virtual wire mode", it > makes the interrupts follow Giant. Wow, looks like someone who really knows what they're talking about stepped up here. So I know we could look at the BIOS to find if the user actually has this buggy board. This being the case we could then decide to hardcode whatever is wrong in the APIC tables so we can talk to the hardware. I didn't look at the APIC I/O code and it may take a while for me to actually understand it. Would you be interested in or able to write something describing the problem so it can be submitted to Intel in the unlikely event that they would actually fix it? -Michael _________________________________________________________________ http://fastmail.ca/ - Fast Secure Web Email for Canadians --------------Boundary-00=_BB2MULUXFQQMYJ0CCJD0-- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 12:24:34 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 72A6937B401 for ; Wed, 4 Dec 2002 12:24:33 -0800 (PST) Received: from mail.speakeasy.net (mail15.speakeasy.net [216.254.0.215]) by mx1.FreeBSD.org (Postfix) with ESMTP id CADA943ED4 for ; Wed, 4 Dec 2002 12:24:32 -0800 (PST) (envelope-from jhb@FreeBSD.org) Received: (qmail 22955 invoked from network); 4 Dec 2002 20:24:38 -0000 Received: from unknown (HELO server.baldwin.cx) ([216.27.160.63]) (envelope-sender ) by mail15.speakeasy.net (qmail-ldap-1.03) with DES-CBC3-SHA encrypted SMTP for ; 4 Dec 2002 20:24:38 -0000 Received: from laptop.baldwin.cx (gw1.twc.weather.com [216.133.140.1]) by server.baldwin.cx (8.12.6/8.12.6) with ESMTP id gB4KOUuH042029; Wed, 4 Dec 2002 15:24:30 -0500 (EST) (envelope-from jhb@FreeBSD.org) Message-ID: X-Mailer: XFMail 1.5.2 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <3DEE51A6.90BE5C12@mindspring.com> Date: Wed, 04 Dec 2002 15:24:37 -0500 (EST) From: John Baldwin To: Terry Lambert Subject: Re: Intel SE7500CW2 narrowed down... Cc: smp@FreeBSD.ORG, beemern , Oliver Blasnik Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 04-Dec-2002 Terry Lambert wrote: > John Baldwin wrote: >> The only other reported/known problems are on older Pentium and possibly >> PPro machines. Do you have any other SMP i386 arch machines that do not >> work? > > [ ... ] > >> Apparently both Linux and Windows use a different algorithm for starting >> up AP's on i386 in that (I think) they send broadcast IPI's instead of >> IPI'ing each CPU individually. > > This is why they work on old ASUS Pentium 90 boxes, and FreeBSD > does not. Well, considering FreeBSD started out working on Pentium 90 machines and has used the same algorithm since it first got SMP support, I am kind of skeptical that this is the source of the recent breakage of support for dual Pentiums. > It's not related to the P4 SE7500CW2-type problems, which are > incorrect APIC description and chipset programming. In which way exactly? -- John Baldwin <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 12:24:36 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id F2C1737B401 for ; Wed, 4 Dec 2002 12:24:34 -0800 (PST) Received: from mail.speakeasy.net (mail13.speakeasy.net [216.254.0.213]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7E3E643EB2 for ; Wed, 4 Dec 2002 12:24:34 -0800 (PST) (envelope-from jhb@FreeBSD.org) Received: (qmail 7071 invoked from network); 4 Dec 2002 20:24:40 -0000 Received: from unknown (HELO server.baldwin.cx) ([216.27.160.63]) (envelope-sender ) by mail13.speakeasy.net (qmail-ldap-1.03) with DES-CBC3-SHA encrypted SMTP for ; 4 Dec 2002 20:24:40 -0000 Received: from laptop.baldwin.cx (gw1.twc.weather.com [216.133.140.1]) by server.baldwin.cx (8.12.6/8.12.6) with ESMTP id gB4KOWuH042034; Wed, 4 Dec 2002 15:24:32 -0500 (EST) (envelope-from jhb@FreeBSD.org) Message-ID: X-Mailer: XFMail 1.5.2 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <3DEE5F37.000003.43942@ns.interchange.ca> Date: Wed, 04 Dec 2002 15:24:39 -0500 (EST) From: John Baldwin To: tlambert2@mindspring.com Subject: Re: Intel SE7500CW2 narrowed down... Cc: freebsd-smp@freebsd.org, Michael Richards Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 04-Dec-2002 Michael Richards wrote: >>> I'm not convinced it's a tables problem as I read the spec and >>> verified the CPU entries in this table byte for byte. It appears >>> valid. Besides, Linux works and so do a host of other OSes. More >>> than likely we're just doing something slightly different that >>> happens to work find with all the other boards out there. >>> >>> My next step is to start looking at how linux works and compare >>> it to how FreeBSD doesn't work. >> >> You will find it in the APIC I/O code and the interrupt routing >> code, with a tiny part in the shipset initialization. >> >> You could fix it in FreeBSD by disregarding what the BIOS says, >> and manually initializing the ServerWorks chipset the way FreeBSD >> wants it (i.e. MPSpec v1.4, mode 2 interrupt processing >> compliant). FreeBSD doesn't run in real "virtual wire mode", it >> makes the interrupts follow Giant. Terry. We are having problems sending _interprocess_interrupts_. IPI's do _not_ go through the IO APIC. They are sent from one local APIC over to another local APIC. The problems we are seeing have nothing to do with I/O interrupts. The box runs fine with one processor and using the I/O APIC if you ignore the failure of the AP to respond to the startup IPI. -- John Baldwin <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 17:20:55 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 65AFC37B401; Wed, 4 Dec 2002 17:20:54 -0800 (PST) Received: from albatross.prod.itd.earthlink.net (albatross.mail.pas.earthlink.net [207.217.120.120]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0269943EA9; Wed, 4 Dec 2002 17:20:54 -0800 (PST) (envelope-from tlambert2@mindspring.com) Received: from pool0353.cvx40-bradley.dialup.earthlink.net ([216.244.43.98] helo=mindspring.com) by albatross.prod.itd.earthlink.net with esmtp (Exim 3.33 #1) id 18Jkh9-0001h0-00; Wed, 04 Dec 2002 17:20:52 -0800 Message-ID: <3DEEA9A5.98315710@mindspring.com> Date: Wed, 04 Dec 2002 17:19:33 -0800 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: Michael Richards Cc: jhb@FreeBSD.org, freebsd-smp@freebsd.org Subject: Re: Intel SE7500CW2 narrowed down... References: <3DEE5F37.000003.43942@ns.interchange.ca> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Michael Richards wrote: > Wow, looks like someone who really knows what they're talking about > stepped up here. Peter Wemm knows it too, and so do other people (PHK, Steve Passe, Bruce Evans, etc.). Mostly, though, we just avoid that hardware, so it keeps it from being our problem. > So I know we could look at the BIOS to find if the > user actually has this buggy board. This being the case we could then > decide to hardcode whatever is wrong in the APIC tables so we can > talk to the hardware. No. The BIOS does not initialize the chipset for the way interrupt routing is done in FreeBSD. Basically, the BIOS will support virtual wire, or it will support all interrupts sent to the BP. FreeBSD uses whatever CPU is in the kernel, and allows in only one at a time (in the older code). In any case, interrupts are vectored to a single CPU at a time, which may be the AP. > I didn't look at the APIC I/O code and it may take a while for me to > actually understand it. Would you be interested in or able to write > something describing the problem so it can be submitted to Intel in > the unlikely event that they would actually fix it? If they knew enough to fix NetWare, then they are aware of the problem (NetWare runs non-preemptive multitasking, with threads run to copletion, with NLM's and *not* the main server code running on the AP's). The real question is whether the ServerWorks chipset can even *be* programmed to do the right thing, or whether it sucks, like the CMD640B IDE controller just sucked, with no way to fix it with software. The problem with solving it the Linux way is that you can't send the interrupt to the BP, if an AP is holding Giant. It would take a lot of work to keep all the AP's out of the kernel; it might not be that possible. Going the other direction works, but, again, you are up against the global lock. It's probably going to be a lot of work, and whoever does it is going to have to have one of the damaged boxes in hand to hack on. -- Terry To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 17:24: 2 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 837BE37B401; Wed, 4 Dec 2002 17:24:01 -0800 (PST) Received: from pintail.mail.pas.earthlink.net (pintail.mail.pas.earthlink.net [207.217.120.122]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3C1FF43EA9; Wed, 4 Dec 2002 17:24:01 -0800 (PST) (envelope-from tlambert2@mindspring.com) Received: from pool0353.cvx40-bradley.dialup.earthlink.net ([216.244.43.98] helo=mindspring.com) by pintail.mail.pas.earthlink.net with esmtp (Exim 3.33 #1) id 18JkkC-0002qC-00; Wed, 04 Dec 2002 17:24:00 -0800 Message-ID: <3DEEAA5F.DDC9536F@mindspring.com> Date: Wed, 04 Dec 2002 17:22:39 -0800 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: John Baldwin Cc: smp@FreeBSD.ORG, beemern , Oliver Blasnik Subject: Re: Intel SE7500CW2 narrowed down... References: Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org John Baldwin wrote: > >> Apparently both Linux and Windows use a different algorithm for starting > >> up AP's on i386 in that (I think) they send broadcast IPI's instead of > >> IPI'ing each CPU individually. > > > > This is why they work on old ASUS Pentium 90 boxes, and FreeBSD > > does not. > > Well, considering FreeBSD started out working on Pentium 90 machines > and has used the same algorithm since it first got SMP support, I > am kind of skeptical that this is the source of the recent breakage > of support for dual Pentiums. I own an ASUS Dual P90 box that was broken by the mpinit changes. > > It's not related to the P4 SE7500CW2-type problems, which are > > incorrect APIC description and chipset programming. > > In which way exactly? The chip isn't programmed to be able to direct interrupts to other than the BP, unless it's in virtual wire mode. You can deduce this, just by knowning the difference between the OS's that do work on the board, and FReeBSD. -- Terry To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 17:30:53 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 42EB637B401; Wed, 4 Dec 2002 17:30:52 -0800 (PST) Received: from pintail.mail.pas.earthlink.net (pintail.mail.pas.earthlink.net [207.217.120.122]) by mx1.FreeBSD.org (Postfix) with ESMTP id D72FE43E4A; Wed, 4 Dec 2002 17:30:51 -0800 (PST) (envelope-from tlambert2@mindspring.com) Received: from pool0353.cvx40-bradley.dialup.earthlink.net ([216.244.43.98] helo=mindspring.com) by pintail.mail.pas.earthlink.net with esmtp (Exim 3.33 #1) id 18Jkqp-0004M7-00; Wed, 04 Dec 2002 17:30:51 -0800 Message-ID: <3DEEABFD.A40A735E@mindspring.com> Date: Wed, 04 Dec 2002 17:29:33 -0800 From: Terry Lambert X-Mailer: Mozilla 4.79 [en] (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: John Baldwin Cc: freebsd-smp@freebsd.org, Michael Richards Subject: Re: Intel SE7500CW2 narrowed down... References: Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org John Baldwin wrote: > Terry. We are having problems sending _interprocess_interrupts_. > IPI's do _not_ go through the IO APIC. They are sent from one > local APIC over to another local APIC. The problems we are seeing > have nothing to do with I/O interrupts. The box runs fine with one > processor and using the I/O APIC if you ignore the failure of the > AP to respond to the startup IPI. This is the "ServerwWorks related lockup", not the "Second processor does not start, and so does not grab Giant, so system does not lock up" thing, right? The easy way to prove your thesis is to send a broadcast IPI. You only have 2 CPUs in that box, anyway. If it starts working then you are right. I think the serverworks chipset can only run in 2 of the 4 modes, at least as programmed by the BIOS, and goes off in the weeds, otherwise (the first thing an AP does is grab giant, which means it tries to grab the interrupts, as a side effect). It may be that the chipset is plain busted. Note that one of the OS's that works doesn't run in APIC I/O mode at all, and the other OS that works runs in virtual wire mode. Other than tonight, I won't be able to engage in a deep discussion on this for about a week, I think, so get your shots in now. 8-). -- Terry To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed Dec 4 20: 3:31 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 61AFA37B401; Wed, 4 Dec 2002 20:03:29 -0800 (PST) Received: from mail.interchange.ca (ns.interchange.ca [216.126.79.2]) by mx1.FreeBSD.org (Postfix) with ESMTP id BA64B43EB2; Wed, 4 Dec 2002 20:03:28 -0800 (PST) (envelope-from michael@fastmail.ca) Received: by mail.interchange.ca (Fastmailer, from userid 555) id 7A6EF3DE3; Wed, 4 Dec 2002 23:01:41 -0500 (EST) Received: from 24.43.130.241 by www.fastmail.ca with HTTP; Thu, 5 Dec 2002 04:01:41 +0000 (UTC) MIME-Version: 1.0 Message-Id: <3DEECFA5.000013.43946@ns.interchange.ca> Content-Type: Multipart/Mixed; boundary="------------Boundary-00=_TIOMMBOYA1UMYJ0CCJD0" To: tlambert2@mindspring.com Subject: Re: Intel SE7500CW2 narrowed down... Cc: freebsd-smp@freebsd.org, jhb@FreeBSD.org Date: Wed, 4 Dec 2002 23:01:41 -0500 (EST) From: "Michael Richards" X-Fastmail-IP: [24.43.130.241] Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org --------------Boundary-00=_TIOMMBOYA1UMYJ0CCJD0 Content-Type: Text/Plain Content-Transfer-Encoding: 7bit > John Baldwin wrote: >> Terry. We are having problems sending _interprocess_interrupts_. >> IPI's do _not_ go through the IO APIC. They are sent from one >> local APIC over to another local APIC. The problems we are >> seeing have nothing to do with I/O interrupts. The box runs fine >> with one processor and using the I/O APIC if you ignore the >> failure of the AP to respond to the startup IPI. > > This is the "ServerwWorks related lockup", not the "Second > processor does not start, and so does not grab Giant, so system > does not lock up" thing, right? Looks to me like the AP doesn't start and therefore never signals the main thread. As a result it times out and offers to panic. If you tell it not to it starts just fine in uniprocessor mode. > The easy way to prove your thesis is to send a broadcast IPI. You > only have 2 CPUs in that box, anyway. If it starts working then > you are right. If you send a broadcast init IPI and then sit in the loop waiting for all the different APs to increment the CPU number wouldn't this be not only compatable with FreeBSD's way of doing things, but also a tad cleaner. > I think the serverworks chipset can only run in 2 of the 4 modes, > at least as programmed by the BIOS, and goes off in the weeds, > otherwise (the first thing an AP does is grab giant, which means > it tries to grab the interrupts, as a side effect). It may be > that the chipset is plain busted. Note that one of the OS's that > works doesn't run in APIC I/O mode at all, and the other OS that > works runs in virtual wire mode. Is this a well known detail of the chipset? If so, where has it been documented? Although I've played around a lot with micros and other embedded designs I'm not totally up to speed on this. I've done a lot of searching for writeups on this board and chipset but not really found anything. Unless you happen to work for Intel or something and have access to something I don't I'd love to have a read and see what I can learn. -Michael _________________________________________________________________ http://fastmail.ca/ - Fast Secure Web Email for Canadians --------------Boundary-00=_TIOMMBOYA1UMYJ0CCJD0-- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Dec 5 1:22:36 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 29D5A37B401 for ; Thu, 5 Dec 2002 01:22:36 -0800 (PST) Received: from mx0.estimese.net (finom.estimese.net [195.168.3.50]) by mx1.FreeBSD.org (Postfix) with SMTP id 618DC43E9C for ; Thu, 5 Dec 2002 01:22:27 -0800 (PST) (envelope-from zero@estimese.net) Received: (qmail 7191 invoked by uid 69); 5 Dec 2002 09:21:58 -0000 Date: Thu, 5 Dec 2002 10:21:58 +0100 From: Robert Bopko To: Terry Lambert Cc: smp@freebsd.org Subject: Re: Intel SE7500CW2 narrowed down... Message-ID: <20021205092158.GB7065@finom.estimese.net> References: <3DEEABFD.A40A735E@mindspring.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <3DEEABFD.A40A735E@mindspring.com> Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org just a note. the intel E7500 chipset we are using here is in other dual xeon motherboards too e.g.(tyan,msi,supermicro) and these don't have problems with freebsd-smp. On Wed, Dec 04, 2002 at 05:29:33PM -0800, Terry Lambert wrote: > I think the serverworks chipset can only run in 2 of the 4 modes, > at least as programmed by the BIOS, and goes off in the weeds, > otherwise (the first thing an AP does is grab giant, which means > it tries to grab the interrupts, as a side effect). It may be > that the chipset is plain busted. Note that one of the OS's that > works doesn't run in APIC I/O mode at all, and the other OS that > works runs in virtual wire mode. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Dec 5 7:39:21 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id CEF9837B401 for ; Thu, 5 Dec 2002 07:39:19 -0800 (PST) Received: from mail.speakeasy.net (mail11.speakeasy.net [216.254.0.211]) by mx1.FreeBSD.org (Postfix) with ESMTP id 59DEE43E9C for ; Thu, 5 Dec 2002 07:39:19 -0800 (PST) (envelope-from jhb@FreeBSD.org) Received: (qmail 30451 invoked from network); 5 Dec 2002 15:39:22 -0000 Received: from unknown (HELO server.baldwin.cx) ([216.27.160.63]) (envelope-sender ) by mail11.speakeasy.net (qmail-ldap-1.03) with DES-CBC3-SHA encrypted SMTP for ; 5 Dec 2002 15:39:22 -0000 Received: from laptop.baldwin.cx (gw1.twc.weather.com [216.133.140.1]) by server.baldwin.cx (8.12.6/8.12.6) with ESMTP id gB5FdHuH044880; Thu, 5 Dec 2002 10:39:17 -0500 (EST) (envelope-from jhb@FreeBSD.org) Message-ID: X-Mailer: XFMail 1.5.2 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <3DEEAA5F.DDC9536F@mindspring.com> Date: Thu, 05 Dec 2002 10:39:25 -0500 (EST) From: John Baldwin To: Terry Lambert Subject: Re: Intel SE7500CW2 narrowed down... Cc: Oliver Blasnik , beemern , smp@FreeBSD.ORG Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 05-Dec-2002 Terry Lambert wrote: > John Baldwin wrote: >> >> Apparently both Linux and Windows use a different algorithm for starting >> >> up AP's on i386 in that (I think) they send broadcast IPI's instead of >> >> IPI'ing each CPU individually. >> > >> > This is why they work on old ASUS Pentium 90 boxes, and FreeBSD >> > does not. >> >> Well, considering FreeBSD started out working on Pentium 90 machines >> and has used the same algorithm since it first got SMP support, I >> am kind of skeptical that this is the source of the recent breakage >> of support for dual Pentiums. > > I own an ASUS Dual P90 box that was broken by the mpinit changes. > > >> > It's not related to the P4 SE7500CW2-type problems, which are >> > incorrect APIC description and chipset programming. >> >> In which way exactly? > > The chip isn't programmed to be able to direct interrupts to > other than the BP, unless it's in virtual wire mode. You can > deduce this, just by knowning the difference between the OS's > that do work on the board, and FReeBSD. Terry. Please be quiet until you know what is going on. IO interrupts work JUST FINE. It is ONLY the startup IPIs that are failing. This has NOTHING to do with IO APICs or virtual wire mode. Also, for your information, FreeBSD does NOT program the APIC to send all interrupts to one CPU. Rather, in 4.x, if an interrupt comes to a CPU when another CPU is in the kernel we use an IPI to "bounce" that interrupt over to the CPU already in the kernel manually. It is NOT done by programming the IO APIC. -- John Baldwin <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Dec 5 7:39:24 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B87DB37B401 for ; Thu, 5 Dec 2002 07:39:22 -0800 (PST) Received: from mail.speakeasy.net (mail16.speakeasy.net [216.254.0.216]) by mx1.FreeBSD.org (Postfix) with ESMTP id A209643EB2 for ; Thu, 5 Dec 2002 07:39:21 -0800 (PST) (envelope-from jhb@FreeBSD.org) Received: (qmail 20149 invoked from network); 5 Dec 2002 15:39:24 -0000 Received: from unknown (HELO server.baldwin.cx) ([216.27.160.63]) (envelope-sender ) by mail16.speakeasy.net (qmail-ldap-1.03) with DES-CBC3-SHA encrypted SMTP for ; 5 Dec 2002 15:39:24 -0000 Received: from laptop.baldwin.cx (gw1.twc.weather.com [216.133.140.1]) by server.baldwin.cx (8.12.6/8.12.6) with ESMTP id gB5FdJuH044883; Thu, 5 Dec 2002 10:39:19 -0500 (EST) (envelope-from jhb@FreeBSD.org) Message-ID: X-Mailer: XFMail 1.5.2 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 In-Reply-To: <3DEEABFD.A40A735E@mindspring.com> Date: Thu, 05 Dec 2002 10:39:27 -0500 (EST) From: John Baldwin To: Terry Lambert Subject: Re: Intel SE7500CW2 narrowed down... Cc: Michael Richards , freebsd-smp@freebsd.org Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On 05-Dec-2002 Terry Lambert wrote: > John Baldwin wrote: >> Terry. We are having problems sending _interprocess_interrupts_. >> IPI's do _not_ go through the IO APIC. They are sent from one >> local APIC over to another local APIC. The problems we are seeing >> have nothing to do with I/O interrupts. The box runs fine with one >> processor and using the I/O APIC if you ignore the failure of the >> AP to respond to the startup IPI. > > This is the "ServerwWorks related lockup", not the "Second processor > does not start, and so does not grab Giant, so system does not lock > up" thing, right? No, this is the second CPU fails to startup period. Giant isn't even a factor at this early stage. > The easy way to prove your thesis is to send a broadcast IPI. You > only have 2 CPUs in that box, anyway. If it starts working then > you are right. It didn't, it reset the box. At the moment I am getting an error after sending either the level-deassert INIT IPI or the first STARTUP IPI (if I disable the level-deassert INIT which is ignored by P4's anyways) of the type "Received Illegal Vector". I'm getting this error on the CPU that is sending the IPI however. :-/ [ irrelevant stuff removed ] -- John Baldwin <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Dec 5 13:17:39 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 7C0CA37B401 for ; Thu, 5 Dec 2002 13:17:38 -0800 (PST) Received: from mail.speakeasy.net (mail11.speakeasy.net [216.254.0.211]) by mx1.FreeBSD.org (Postfix) with ESMTP id B2B0F43E9C for ; Thu, 5 Dec 2002 13:17:37 -0800 (PST) (envelope-from jhb@FreeBSD.org) Received: (qmail 10628 invoked from network); 5 Dec 2002 21:17:45 -0000 Received: from unknown (HELO server.baldwin.cx) ([216.27.160.63]) (envelope-sender ) by mail11.speakeasy.net (qmail-ldap-1.03) with DES-CBC3-SHA encrypted SMTP for ; 5 Dec 2002 21:17:45 -0000 Received: from laptop.baldwin.cx (gw1.twc.weather.com [216.133.140.1]) by server.baldwin.cx (8.12.6/8.12.6) with ESMTP id gB5LHZuH045896; Thu, 5 Dec 2002 16:17:36 -0500 (EST) (envelope-from jhb@FreeBSD.org) Message-ID: X-Mailer: XFMail 1.5.2 on FreeBSD X-Priority: 3 (Normal) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 8bit MIME-Version: 1.0 Date: Thu, 05 Dec 2002 16:17:43 -0500 (EST) From: John Baldwin To: smp@FreeBSD.org Subject: Update on SE7500 P4 SMP.. Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org I've had the opportunity to tinker with one of these machines for a day or so now (as well as do some more peaking at how Linnex does this). So far I've had no luck in figuring it out. I can tell you that Linux does _not_ use broadcast startup IPI's as I had thought/heard, but targets them at each AP individually just as we do. In fact, both of us are (bascially, both Linux and FreeBSD add an extra level de-assert INIT IPI) following the algorithm outlined in the MP v1.4 spec except that Linux has some extra code to support external APICs for things like SMP on 486 which FreeBSD just doesn't support. I turned on the CHECK_PORTS stuff and am convinced that the AP just is not getting the INIT or STARTUP IPIs. The IPI's claim to succeed as far as being sent ok, but the AP never starts to execute the trampoline code. I do wonder if the APIC bus is a bit out of wack as the ESR (error status register) of the BSP's local APIC reports that it has "Received an Illegal Vector", but it has this reported at the before we even start sending startup IPI's (INIT or STARTUP) to the AP. I've tried all sorts of various things including tweaking some of the delivery modes on the INIT IPI's (which we didn't have quite right but which don't really matter) and nothing has made any difference. This has absolutely nothing to do with I/O interrupts, the I/O APIC, virtual wire mode, etc. It does have to do with interprocessor interrupts. For the time being I'm going to concenctrate on other more pressing 5.0 things, but if anyone has any ideas I'm all ears. :-/ -- John Baldwin <>< http://www.FreeBSD.org/~jhb/ "Power Users Use the Power to Serve!" - http://www.FreeBSD.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Dec 5 15:42:53 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 10BAC37B401; Thu, 5 Dec 2002 15:42:53 -0800 (PST) Received: from tp.databus.com (p70-227.acedsl.com [66.114.70.227]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5739943EA9; Thu, 5 Dec 2002 15:42:52 -0800 (PST) (envelope-from barney@tp.databus.com) Received: from tp.databus.com (localhost.databus.com [127.0.0.1]) by tp.databus.com (8.12.6/8.12.6) with ESMTP id gB5NgkMG019192; Thu, 5 Dec 2002 18:42:46 -0500 (EST) (envelope-from barney@tp.databus.com) Received: (from barney@localhost) by tp.databus.com (8.12.6/8.12.6/Submit) id gB5Ngk4C019191; Thu, 5 Dec 2002 18:42:46 -0500 (EST) (envelope-from barney) Date: Thu, 5 Dec 2002 18:42:46 -0500 From: Barney Wolff To: John Baldwin Cc: smp@FreeBSD.ORG Subject: Re: Update on SE7500 P4 SMP.. Message-ID: <20021205234246.GA18669@tp.databus.com> References: Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.4i X-Scanned-By: MIMEDefang 2.26 (www . roaringpenguin . com / mimedefang) Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org Here's a simpleminded idea: Can it be that the "extra stuff" that Linux does slows things down just enough to let some signal settle? Radically underclocking the board might work, then, and disclose the problem. Or just a bunch of NOPs. On Thu, Dec 05, 2002 at 04:17:43PM -0500, John Baldwin wrote: > ... but if anyone > has any ideas I'm all ears. :-/ -- Barney Wolff http://www.databus.com/bwresume.pdf I'm available by contract or FT, in the NYC metro area or via the 'Net. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu Dec 5 18:10:26 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4540237B401 for ; Thu, 5 Dec 2002 18:10:24 -0800 (PST) Received: from fledge.watson.org (fledge.watson.org [204.156.12.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6CFC443E4A for ; Thu, 5 Dec 2002 18:10:23 -0800 (PST) (envelope-from robert@fledge.watson.org) Received: from fledge.watson.org (fledge.pr.watson.org [192.0.2.3]) by fledge.watson.org (8.12.6/8.12.5) with SMTP id gB62AIBF009959 for ; Thu, 5 Dec 2002 21:10:18 -0500 (EST) (envelope-from robert@fledge.watson.org) Date: Thu, 5 Dec 2002 21:10:18 -0500 (EST) From: Robert Watson X-Sender: robert@fledge.watson.org To: smp@FreeBSD.org Subject: Tweaks to smp(4) Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org With the release of FreeBSD 5.0, support for SMP has changed substantially. Not least is the move to a new set of synchronization primitives, and the addition of SMP support on several new hardware platforms. I'd like comments on the attached patch to smp.4, and suggestions about other material to add or cross-reference. I realized I neglected to xref witness, but there's probably a lot more to this. I'd like to commit the changes prior to 5.0-RC2. Robert N M Watson FreeBSD Core Team, TrustedBSD Projects robert@fledge.watson.org Network Associates Laboratories Index: smp.4 =================================================================== RCS file: /home/ncvs/src/share/man/man4/smp.4,v retrieving revision 1.12 diff -u -r1.12 smp.4 --- smp.4 14 Jul 2001 19:40:47 -0000 1.12 +++ smp.4 6 Dec 2002 02:02:39 -0000 @@ -23,7 +23,7 @@ .\" .\" $FreeBSD: src/share/man/man4/smp.4,v 1.12 2001/07/14 19:40:47 schweikh Exp $ .\" -.Dd August 4, 1997 +.Dd December 5, 2002 .Dt SMP 4 .Os .Sh NAME @@ -36,15 +36,25 @@ .Nm kernel implements symmetric multiprocessor support. .Sh COMPATIBILITY -The +Support for multi-processor systems is present for all supported +architectures on FreeBSD. +Currently, this includes alpha, i386, ia64, and sparc64. +.Pp +For i386 systems, the .Nm kernel supports motherboards that follow the Intel MP specification, version 1.4. -.Sh BUGS -That would be a good guess... +On i386 systems, the +.Xr mptable 1 +command may be used to view the status of multi-processor support. .Sh SEE ALSO .Xr mptable 1 , -.Xr dmesg 8 +.Xr condvar 9 , +.Xr msleep 9 , +.Xr mtx_pool 9 , +.Xr mutex 9 , +.Xr sema 9 , +.Xr sx 9 .Sh HISTORY The .Nm @@ -52,5 +62,13 @@ in a separate CVS branch until April 26, 1997, at which point it was merged into 3.0-current. By this date 3.0-current had already been merged with Lite2 kernel code. +.Pp +.Fx 5.0 +introduced support for a host of new synchronization primitives, and +a move towards fine-grained kernel locking rather than reliance on +a Giant kernel lock. +The SMPng Project relied heavily on the support of BSDi, who provided +reference source code from the fine-grained SMP implementation found +in BSD/OS. .Sh AUTHORS .An Steve Passe Aq fsmp@FreeBSD.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Fri Dec 6 6:56:53 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 8734337B401 for ; Fri, 6 Dec 2002 06:56:46 -0800 (PST) Received: from mx0.estimese.net (finom.estimese.net [195.168.3.50]) by mx1.FreeBSD.org (Postfix) with SMTP id 08F2843EA9 for ; Fri, 6 Dec 2002 06:56:41 -0800 (PST) (envelope-from zero@estimese.net) Received: (qmail 11172 invoked by uid 69); 6 Dec 2002 14:56:05 -0000 Date: Fri, 6 Dec 2002 15:56:05 +0100 From: Robert Bopko To: John Baldwin Cc: smp@freebsd.org Subject: Re: Update on SE7500 P4 SMP.. Message-ID: <20021206145605.GA11128@finom.estimese.net> References: Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="x+6KMIRAuhnl3hBn" Content-Disposition: inline In-Reply-To: Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org --x+6KMIRAuhnl3hBn Content-Type: text/plain; charset=us-ascii Content-Disposition: inline On Thu, Dec 05, 2002 at 04:17:43PM -0500, John Baldwin wrote: > has any ideas I'm all ears. :-/ hi, i have successfully tested netbsd-current on it. smp-kernel is running without problems. my idea is to compare smp code from netbsd with freebsd and find any differences which may cause our problems. i'm sending dmesg output from kernel with debug-smp options enabled. --x+6KMIRAuhnl3hBn Content-Type: text/plain; charset=us-ascii Content-Disposition: attachment; filename="dmesg.txt" NetBSD 1.5ZC (GENERIC.MPDEBUG) #52: Sat May 18 18:03:01 EDT 2002 sommerfeld@snoop:/usr/smpsys/arch/i386/compile/GENERIC.MPDEBUG total memory = 1023 MB avail memory = 932 MB using 6144 buffers containing 52480 KB of memory BIOS32 rev. 0 found at 0xfd7f0 mainbus0 (root) mainbus0: scanning 0x9b800 to 0x9bbf0 for MP signature mainbus0: scanning 0x9b400 to 0x9b7f0 for MP signature mainbus0: scanning 0xf0000 to 0xffff0 for MP signature mainbus0: MP floating pointer found in bios at 0xf6a20 mainbus0: MP config table at 0x9bfa0, 332 bytes long mainbus0: Intel MP Specification (Version 1.4) ( SE7500CW2) cpu0 at mainbus0: apid 0 (boot processor) cpu0: Intel Pentium 4 (686-class), 2392.33 MHz cpu0: features 3febfbff cpu0: features 3febfbff cpu0: features 3febfbff cpu0: I-cache 12K uOp cache 8-way8-way, D-cache 8 KB 64b/line 4-way cpu0: L2 cache 512 KB 64b/line 8-way cpu0: ITLB 4K/4M: 64 entries cpu0: DTLB 4K/4M: 64 entries cpu0: calibrating local timer cpu0: apic clock running at 99 MHz cpu0: 16 page colors cpu0: kstack at 0xe40a4000 for 8192 bytes cpu0: idle pcb at 0xe40a4000, idle sp at 0xe40a5f98 cpu1 at mainbus0: apid 6 (application processor) cpu1: starting cpu1: Intel Pentium 4 (686-class), 2392.25 MHz cpu1: features 3febfbff cpu1: features 3febfbff cpu1: features 3febfbff cpu1: I-cache 12K uOp cache 8-way8-way, D-cache 8 KB 64b/line 4-way cpu1: L2 cache 512 KB 64b/line 8-way cpu1: ITLB 4K/4M: 64 entries cpu1: DTLB 4K/4M: 64 entries cpu1: kstack at 0xe40b6000 for 8192 bytes cpu1: idle pcb at 0xe40b6000, idle sp at 0xe40b7f98 mpbios: bus 0 is type PCI mpbios: bus 1 is type PCI mpbios: bus 2 is type PCI mpbios: bus 3 is type PCI mpbios: bus 4 is type PCI mpbios: bus 5 is type ISA ioapic0 at mainbus0 apid 2 (I/O APIC) ioapic0: pa 0xfec00000, virtual wire mode, version 20, 24 pins ioapic1 at mainbus0 apid 3 (I/O APIC) ioapic1: pa 0xfec80000, virtual wire mode, version 20, 24 pins ioapic2 at mainbus0 apid 4 (I/O APIC) ioapic2: pa 0xfec80400, virtual wire mode, version 20, 24 pins ioapic0: int0 attached to ExtINT (type 3 flags 5) ioapic0: int1 attached to isa0 irq 1 (type 0 flags 5) ioapic0: int2 attached to isa0 irq 0 (type 0 flags 5) ioapic0: int3 attached to isa0 irq 3 (type 0 flags 5) ioapic0: int4 attached to isa0 irq 4 (type 0 flags 5) ioapic0: int19 attached to pci0 device 29 INT_B (type 0 flags f) ioapic0: int6 attached to isa0 irq 6 (type 0 flags 5) ioapic0: int7 attached to isa0 irq 7 (type 0 flags 5) ioapic0: int8 attached to isa0 irq 8 (type 0 flags 5) ioapic0: int9 attached to isa0 irq 9 (type 0 flags 5) ioapic0: int16 attached to pci0 device 29 INT_A (type 0 flags f) ioapic0: int17 attached to pci0 device 31 INT_B (type 0 flags f) ioapic0: int12 attached to isa0 irq 12 (type 0 flags 5) ioapic0: int13 attached to isa0 irq 13 (type 0 flags 5) ioapic0: int14 attached to isa0 irq 14 (type 0 flags 5) ioapic0: int15 attached to isa0 irq 15 (type 0 flags 5) ioapic0: int21 attached to pci4 device 3 INT_A (type 0 flags f) ioapic0: int20 attached to pci4 device 4 INT_A (type 0 flags f) ioapic0: int23 attached to pci4 device 5 INT_A (type 0 flags f) ioapic0: int22 attached to pci4 device 6 INT_A (type 0 flags f) local apic: int0 attached to ExtINT (type 3 flags 5) local apic: int1 attached to NMI (type 1 flags 5) mainbus0: MP WARNING: 144 bytes of extended entries not examined pci0 at mainbus0 bus 0: configuration mode 1 pci0: i/o space, memory space enabled, rd/line, rd/mult, wr/inv ok pchb0 at pci0 dev 0 function 0 pchb0: Intel product 0x2540 (rev. 0x03) Intel product 0x2541 (undefined subclass 0x00, revision 0x03) at pci0 dev 0 function 1 not configured ppb0 at pci0 dev 2 function 0: Intel product 0x2543 (rev. 0x03) pci1 at ppb0 bus 1 pci1: i/o space, memory space enabled Intel product 0x1461 (8259 PIC system, interface 0x20, revision 0x03) at pci1 dev 28 function 0 not configured ppb1 at pci1 dev 29 function 0: Intel product 0x1460 (rev. 0x03) pci2 at ppb1 bus 2 pci2: i/o space, memory space enabled Intel product 0x1461 (8259 PIC system, interface 0x20, revision 0x03) at pci1 dev 30 function 0 not configured ppb2 at pci1 dev 31 function 0: Intel product 0x1460 (rev. 0x03) pci3 at ppb2 bus 3 pci3: i/o space, memory space enabled uhci0 at pci0 dev 29 function 0: Intel 82801CA/CAM USB Controller (rev. 0x02) uhci0: interrupting at apic 2 int 16 (irq 10) usb0 at uhci0: USB revision 1.0 uhub0 at usb0 uhub0: Intel UHCI root hub, class 9/0, rev 1.00/1.00, addr 1 uhub0: 2 ports with 2 removable, self powered uhci1 at pci0 dev 29 function 1: Intel 82801CA/CAM USB Controller (rev. 0x02) uhci1: interrupting at apic 2 int 19 (irq 5) usb1 at uhci1: USB revision 1.0 uhub1 at usb1 uhub1: Intel UHCI root hub, class 9/0, rev 1.00/1.00, addr 1 uhub1: 2 ports with 2 removable, self powered ppb3 at pci0 dev 30 function 0: Intel 82801BA Hub-to-PCI Bridge (rev. 0x42) pci4 at ppb3 bus 4 pci4: i/o space, memory space enabled vga1 at pci4 dev 3 function 0: ATI Technologies Rage XL (rev. 0x27) wsdisplay0 at vga1 kbdmux 1: console (80x25, vt100 emulation) wsmux1: connecting to wsdisplay0 fxp0 at pci4 dev 4 function 0: i82550 Ethernet, rev 13 fxp0: interrupting at apic 2 int 20 (irq 11) fxp0: detected 64 word EEPROM fxp0: Ethernet address 00:02:b3:b0:37:22 inphy0 at fxp0 phy 1: i82555 10/100 media interface, rev. 4 inphy0: 10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, auto fxp1 at pci4 dev 5 function 0: i82550 Ethernet, rev 13 fxp1: interrupting at apic 2 int 23 (irq 11) fxp1: detected 64 word EEPROM fxp1: Ethernet address 00:02:b3:b0:35:60 inphy1 at fxp1 phy 1: i82555 10/100 media interface, rev. 4 inphy1: 10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, auto pciide0 at pci4 dev 6 function 0: Promise Ultra100/ATA Bus Master IDE Accelerator (rev. 0x02) pciide0: bus-master DMA support present pciide0: primary channel configured to native-PCI mode pciide0: using apic 2 int 22 (irq 11) for native-PCI interrupt pciide0: disabling primary channel (no drives) pciide0: secondary channel configured to native-PCI mode pciide0: disabling secondary channel (no drives) pcib0 at pci0 dev 31 function 0 pcib0: Intel 82801CA LPC Interface (rev. 0x02) pciide1 at pci0 dev 31 function 1: Intel 82201CA IDE Controller (rev. 0x02) pciide1: bus-master DMA support present pciide1: primary channel wired to compatibility mode atapibus0 at pciide1 channel 0: 2 targets cd0 at atapibus0 drive 1: type 5 cdrom removable cd0: 32-bit data port cd0: drive supports PIO mode 4, DMA mode 2, Ultra-DMA mode 2 (Ultra/33) wd0 at pciide1 channel 0 drive 0: wd0: drive supports 16-sector PIO transfers, LBA addressing wd0: 19092 MB, 16383 cyl, 16 head, 63 sec, 512 bytes/sect x 39102336 sectors wd0: 32-bit data port wd0: drive supports PIO mode 4, DMA mode 2, Ultra-DMA mode 5 (Ultra/100) pciide1: primary channel interrupting at irq 14 wd0(pciide1:0:0): using PIO mode 4, Ultra-DMA mode 2 (Ultra/33) (using DMA data transfers) cd0(pciide1:0:1): using PIO mode 4, Ultra-DMA mode 2 (Ultra/33) (using DMA data transfers) pciide1: secondary channel wired to compatibility mode pciide1: disabling secondary channel (no drives) Intel 82801CA/CAM SMBus Controller (SMBus serial bus, revision 0x02) at pci0 dev 31 function 3 not configured isa0 at pcib0 com0 at isa0 port 0x3f8-0x3ff irq 4: ns16550a, working fifo com1 at isa0 port 0x2f8-0x2ff irq 3: ns16550a, working fifo pckbc0 at isa0 port 0x60-0x64 pckbd0 at pckbc0 (kbd slot) pckbc0: using irq 1 for kbd slot wskbd0 at pckbd0: console keyboard, using wsdisplay0 pms0 at pckbc0 (aux slot) pckbc0: using irq 12 for aux slot wsmouse0 at pms0 mux 0 lpt0 at isa0 port 0x378-0x37b irq 7 lptprobe: mask ff data 55 failed lptprobe: mask ff data 55 failed seaprobe: board type unknown at address 0xc0761000 pcppi0 at isa0 port 0x61 midi0 at pcppi0: PC speaker sysbeep0 at pcppi0 isapnp0 at isa0 port 0x279: ISA Plug 'n Play device support npx0 at isa0 port 0xf0-0xff: using exception 16 fdc0 at isa0 port 0x3f0-0x3f7 irq 6 drq 2 fd0 at fdc0 drive 0: 1.44MB, 80 cyl, 2 head, 18 sec isapnp0: no ISA Plug 'n Play devices found biomask 0 netmask 0 ttymask 0 cpu0: prelint0 700 0 cpu0: prelint1 400 0 cpu0: timer0 300d0 0 cpu0: pcint0 10000 0 cpu0: lint0 10700 0 cpu0: lint1 400 0 cpu0: err0 10000 0 ioapic2: enabling ioapic2: int0 10000 0 ioapic2: int1 10000 0 ioapic2: int2 10000 0 ioapic2: int3 10000 0 ioapic2: int4 10000 0 ioapic2: int5 10000 0 ioapic2: int6 10000 0 ioapic2: int7 10000 0 ioapic2: int8 10000 0 ioapic2: int9 10000 0 ioapic2: int10 10000 0 ioapic2: int11 10000 0 ioapic2: int12 10000 0 ioapic2: int13 10000 0 ioapic2: int14 10000 0 ioapic2: int15 10000 0 ioapic2: int16 10000 0 ioapic2: int17 10000 0 ioapic2: int18 10000 0 ioapic2: int19 10000 0 ioapic2: int20 10000 0 ioapic2: int21 10000 0 ioapic2: int22 10000 0 ioapic2: int23 10000 0 ioapic1: enabling ioapic1: int0 10000 0 ioapic1: int1 10000 0 ioapic1: int2 10000 0 ioapic1: int3 10000 0 ioapic1: int4 10000 0 ioapic1: int5 10000 0 ioapic1: int6 10000 0 ioapic1: int7 10000 0 ioapic1: int8 10000 0 ioapic1: int9 10000 0 ioapic1: int10 10000 0 ioapic1: int11 10000 0 ioapic1: int12 10000 0 ioapic1: int13 10000 0 ioapic1: int14 10000 0 ioapic1: int15 10000 0 ioapic1: int16 10000 0 ioapic1: int17 10000 0 ioapic1: int18 10000 0 ioapic1: int19 10000 0 ioapic1: int20 10000 0 ioapic1: int21 10000 0 ioapic1: int22 10000 0 ioapic1: int23 10000 0 ioapic0: enabling ioapic0: int0 10700 0 ioapic0: int1 1a0 0 ioapic0: int2 10100 0 ioapic0: int3 1e1 0 ioapic0: int4 1e2 0 ioapic0: int5 10000 0 ioapic0: int6 170 0 ioapic0: int7 1a1 0 ioapic0: int8 10100 0 ioapic0: int9 10100 0 ioapic0: int10 10000 0 ioapic0: int11 10000 0 ioapic0: int12 1a2 0 ioapic0: int13 10100 0 ioapic0: int14 171 0 ioapic0: int15 10100 0 ioapic0: int16 a172 0 ioapic0: int17 1a100 0 ioapic0: int18 10000 0 ioapic0: int19 a173 0 ioapic0: int20 a181 0 ioapic0: int21 1a100 0 ioapic0: int22 a174 0 ioapic0: int23 a182 0 boot device: wd0 root on wd0a dumps on wd0b mountroot: trying coda... mountroot: trying msdos... mountroot: trying cd9660... mountroot: trying ntfs... mountroot: trying nfs... mountroot: trying lfs... mountroot: trying ext2fs... mountroot: trying ffs... root file system type: ffs cpu1: prelint0 10000 0 cpu1: prelint1 10000 0 cpu1: timer0 200d0 0 cpu1: pcint0 10000 0 cpu1: lint0 10700 0 cpu1: lint1 400 0 cpu1: err0 10000 0 cpu1: CPU 6 running init: copying out path `/sbin/init' 11 wsdisplay0: screen 1 added (80x25, vt100 emulation) wsdisplay0: screen 2 added (80x25, vt100 emulation) wsdisplay0: screen 3 added (80x25, vt100 emulation) wsdisplay0: screen 4 added (80x25, vt100 emulation) --x+6KMIRAuhnl3hBn-- To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Fri Dec 6 7:17:49 2002 Delivered-To: freebsd-smp@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 51C8537B401 for ; Fri, 6 Dec 2002 07:17:36 -0800 (PST) Received: from mgate3.rrzn.uni-hannover.de (mgate3.rrzn.uni-hannover.de [130.75.2.31]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7DA6043EC5 for ; Fri, 6 Dec 2002 07:17:34 -0800 (PST) (envelope-from gerrit@pmp.uni-hannover.de) Received: from www.pmp.uni-hannover.de (www.pmp.uni-hannover.de [130.75.117.2]) by mgate3.rrzn.uni-hannover.de (8.12.6/8.12.6) with ESMTP id gB6FHTau028648 for ; Fri, 6 Dec 2002 16:17:30 +0100 (MET) Received: by www.pmp.uni-hannover.de (Postfix, from userid 846) id 33D9630B; Fri, 6 Dec 2002 16:17:24 +0100 (CET) Date: Fri, 6 Dec 2002 16:17:24 +0100 From: Gerrit =?iso-8859-1?Q?K=FChn?= To: freebsd-smp@freebsd.org Subject: USB on a MSI 694DPro-AIR with DP2 Message-ID: <20021206151723.GA3905@pmp.uni-hannover.de> Mail-Followup-To: Gerrit =?iso-8859-1?Q?K=FChn?= , freebsd-smp@freebsd.org References: <20021127172548.GF27502@pmp.uni-hannover.de> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <20021127172548.GF27502@pmp.uni-hannover.de> User-Agent: Mutt/1.4i X-Operating-System: FreeBSD X-Scanned-By: MIMEDefang 2.24 (www . roaringpenguin . com / mimedefang) Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.org On Wed, Nov 27, 2002 at 06:25:48PM +0100, Gerrit Kühn wrote: > BTW: apart from the things mentioned abvove, DP2 seems to be stable > running on my server at home for 18h now. I've got no response on my first mail so far, but I can add that the system is still running stable up to now. However, meanwhile I noticed that the USB-ports don't work. They're detected, but when I switch on a device connected to them, I get something like: uhub0: device problem, disabling port 1 When turning the device off again, I get: uhub0: port error, restarting port 1 Here is a verbose boot of the DP2-system with a GENERIC kernel with only SMP turned on additionally. Any help would be greatly appreciated: Copyright (c) 1992-2002 The FreeBSD Project. Copyright (c) 1979, 1980, 1983, 1986, 1988, 1989, 1991, 1992, 1993, 1994 The Regents of the University of California. All rights reserved. FreeBSD 5.0-DP2 #1: Mon Nov 25 22:41:52 CET 2002 root@stardust.terra.ger:/usr/obj/usr/src/sys/GENERIC2 Preloaded elf kernel "/boot/kernel/kernel" at 0xc0692000. Preloaded elf module "/boot/kernel/acpi.ko" at 0xc06920b4. Calibrating clock(s) ... TSC clock: 935444634 Hz, i8254 clock: 1193169 Hz CLK_USE_I8254_CALIBRATION not specified - using default frequency Timecounter "i8254" frequency 1193182 Hz CLK_USE_TSC_CALIBRATION not specified - using old calibration method CPU: Pentium III/Pentium III Xeon/Celeron (935.46-MHz 686-class CPU) Origin = "GenuineIntel" Id = 0x68a Stepping = 10 Features=0x387fbff real memory = 1610547200 (1535 MB) Physical memory chunk(s): 0x00001000 - 0x0009efff, 647168 bytes (158 pages) 0x006bc000 - 0x5ffe7fff, 1603452928 bytes (391468 pages) avail memory = 1559879680 (1487 MB) Programming 24 pins in IOAPIC #0 IOAPIC #0 intpin 2 -> irq 0 FreeBSD/SMP: Multiprocessor System Detected: 2 CPUs cpu0 (BSP): apic id: 0, version: 0x00040011, at 0xfee00000 cpu1 (AP): apic id: 1, version: 0x00040011, at 0xfee00000 io0 (APIC): apic id: 2, version: 0x00178011, at 0xfec00000 bios32: Found BIOS32 Service Directory header at 0xc00fae20 bios32: Entry = 0xfb290 (c00fb290) Rev = 0 Len = 1 pcibios: PCI BIOS entry at 0xf0000+0xb2c0 pnpbios: Found PnP BIOS data at 0xc00fbcc0 pnpbios: Entry = f0000:bcf0 Rev = 1.0 Other BIOS signatures found: Initializing GEOMetry subsystem random: mem: Pentium Pro MTRR support enabled null: SMP: CPU0 bsp_apic_configure(): lint0: 0x00010700 lint1: 0x00000400 TPR: 0x00000010 SVR: 0x000001ff npx0: on motherboard npx0: INT 16 interface acpi0: on motherboard pci_open(1): mode 1 addr port (0x0cf8) is 0x80000060 pci_open(1a): mode1res=0x80000000 (0x80000000) pci_cfgcheck: device 0 [class=060000] [hdr=00] is there (id=06911106) Using $PIR table, 9 entries at 0xc00fdc40 PCI-Only Interrupts: 5 9 10 11 Location Bus Device Pin Link IRQs slot 1 0 18 A 0x02 3 4 5 7 9 10 11 12 14 15 slot 1 0 18 B 0x03 3 4 5 7 9 10 11 12 14 15 slot 1 0 18 C 0x05 3 4 5 7 9 10 11 12 14 15 slot 1 0 18 D 0x01 3 4 5 7 9 10 11 12 14 15 slot 2 0 14 A 0x01 3 4 5 7 9 10 11 12 14 15 slot 2 0 14 B 0x02 3 4 5 7 9 10 11 12 14 15 slot 2 0 14 C 0x03 3 4 5 7 9 10 11 12 14 15 slot 2 0 14 D 0x05 3 4 5 7 9 10 11 12 14 15 slot 3 0 15 A 0x02 3 4 5 7 9 10 11 12 14 15 slot 3 0 15 B 0x03 3 4 5 7 9 10 11 12 14 15 slot 3 0 15 C 0x05 3 4 5 7 9 10 11 12 14 15 slot 3 0 15 D 0x01 3 4 5 7 9 10 11 12 14 15 slot 4 0 16 A 0x03 3 4 5 7 9 10 11 12 14 15 slot 4 0 16 B 0x05 3 4 5 7 9 10 11 12 14 15 slot 4 0 16 C 0x01 3 4 5 7 9 10 11 12 14 15 slot 4 0 16 D 0x02 3 4 5 7 9 10 11 12 14 15 slot 5 0 17 A 0x05 3 4 5 7 9 10 11 12 14 15 slot 5 0 17 B 0x01 3 4 5 7 9 10 11 12 14 15 slot 5 0 17 C 0x02 3 4 5 7 9 10 11 12 14 15 slot 5 0 17 D 0x03 3 4 5 7 9 10 11 12 14 15 slot 6 0 12 A 0x03 3 4 5 7 9 10 11 12 14 15 slot 6 0 12 B 0x05 3 4 5 7 9 10 11 12 14 15 slot 6 0 12 C 0x01 3 4 5 7 9 10 11 12 14 15 slot 6 0 12 D 0x02 3 4 5 7 9 10 11 12 14 15 slot 7 0 13 A 0x05 3 4 5 7 9 10 11 12 14 15 slot 7 0 13 B 0x01 3 4 5 7 9 10 11 12 14 15 slot 7 0 13 C 0x02 3 4 5 7 9 10 11 12 14 15 slot 7 0 13 D 0x03 3 4 5 7 9 10 11 12 14 15 embedded 0 1 A 0x01 3 4 5 7 9 10 11 12 14 15 embedded 0 1 B 0x02 3 4 5 7 9 10 11 12 14 15 embedded 0 1 C 0x03 3 4 5 7 9 10 11 12 14 15 embedded 0 1 D 0x05 3 4 5 7 9 10 11 12 14 15 embedded 0 7 C 0x03 3 4 5 7 9 10 11 12 14 15 embedded 0 7 D 0x05 3 4 5 7 9 10 11 12 14 15 acpi0: power button is handled as a fixed feature programming model. ACPI timer looks GOOD min = 1, max = 2, width = 2 ACPI timer looks GOOD min = 1, max = 2, width = 2 ACPI timer looks BAD min = 1, max = 5, width = 5 ACPI timer looks BAD min = 1, max = 5, width = 5 ACPI timer looks BAD min = 1, max = 6, width = 6 ACPI timer looks BAD min = 1, max = 6, width = 6 ACPI timer looks BAD min = 1, max = 5, width = 5 ACPI timer looks BAD min = 1, max = 6, width = 6 ACPI timer looks BAD min = 1, max = 5, width = 5 ACPI timer looks BAD min = 1, max = 6, width = 6 Timecounter "ACPI-safe" frequency 3579545 Hz acpi_timer0: <24-bit timer at 3.579545MHz> port 0x4008-0x400b on acpi0 acpi_cpu0: on acpi0 acpi_cpu1: on acpi0 acpi_button0: on acpi0 acpi_button1: on acpi0 pcib0: port 0x6000-0x607f,0x5000-0x500f,0x4080-0x40ff,0x4000-0x407f,0xcf8-0xcff on acpi0 ---- initial configuration ------------------------ \\_SB_.PCI0.LNKA irq 5: [ 1 3 4 5 6 7 10 11 12 14 15] low,level,sharable 0.7.0 \\_SB_.PCI0.LNKB irq 11: [ 1 3 4 5 6 7 10 11 12 14 15] low,level,sharable 0.7.1 \\_SB_.PCI0.LNKC irq 10: [ 1 3 4 5 6 7 10 11 12 14 15] low,level,sharable 0.7.2 \\_SB_.PCI0.LNKD irq 9: [ 1 3 4 5 6 7 10 11 12 14 15] low,level,sharable 0.7.3 ---- before setting priority for links ------------ ---- before fixup boot-disabled links ------------- ---- after fixup boot-disabled links -------------- ---- arbitrated configuration --------------------- \\_SB_.PCI0.LNKA irq 5: [ 1 3 4 5 6 7 10 11 12 14 15] low,level,sharable 0.7.0 \\_SB_.PCI0.LNKB irq 11: [ 1 3 4 5 6 7 10 11 12 14 15] low,level,sharable 0.7.1 \\_SB_.PCI0.LNKC irq 10: [ 1 3 4 5 6 7 10 11 12 14 15] low,level,sharable 0.7.2 \\_SB_.PCI0.LNKD irq 9: [ 1 3 4 5 6 7 10 11 12 14 15] low,level,sharable 0.7.3 pci0: on pcib0 pci0: physical bus=0 map[10]: type 3, range 32, base d0000000, size 26, enabled found-> vendor=0x1106, dev=0x0691, revid=0xc4 bus=0, slot=0, func=0 class=06-00-00, hdrtype=0x00, mfdev=0 cmdreg=0x0006, statreg=0x2210, cachelnsz=0 (dwords) lattimer=0x00 (0 ns), mingnt=0x00 (0 ns), maxlat=0x00 (0 ns) powerspec 2 supports D0 D3 current D0 found-> vendor=0x1106, dev=0x8598, revid=0x00 bus=0, slot=1, func=0 class=06-04-00, hdrtype=0x01, mfdev=0 cmdreg=0x0007, statreg=0x2230, cachelnsz=0 (dwords) lattimer=0x00 (0 ns), mingnt=0x0c (3000 ns), maxlat=0x00 (0 ns) found-> vendor=0x1106, dev=0x0686, revid=0x40 bus=0, slot=7, func=0 class=06-01-00, hdrtype=0x00, mfdev=1 cmdreg=0x0087, statreg=0x0210, cachelnsz=0 (dwords) lattimer=0x00 (0 ns), mingnt=0x00 (0 ns), maxlat=0x00 (0 ns) powerspec 2 supports D0 D3 current D0 map[20]: type 4, range 32, base 0000a000, size 4, enabled found-> vendor=0x1106, dev=0x0571, revid=0x06 bus=0, slot=7, func=1 class=01-01-8a, hdrtype=0x00, mfdev=0 cmdreg=0x0007, statreg=0x0290, cachelnsz=0 (dwords) lattimer=0x20 (960 ns), mingnt=0x00 (0 ns), maxlat=0x00 (0 ns) powerspec 2 supports D0 D3 current D0 IOAPIC #0 intpin 19 -> irq 2 Freeing (NOT implemented) redirected PCI irq 9. map[20]: type 4, range 32, base 0000a400, size 5, enabled found-> vendor=0x1106, dev=0x3038, revid=0x16 bus=0, slot=7, func=2 class=0c-03-00, hdrtype=0x00, mfdev=0 cmdreg=0x0007, statreg=0x0210, cachelnsz=8 (dwords) lattimer=0x20 (960 ns), mingnt=0x00 (0 ns), maxlat=0x00 (0 ns) intpin=d, irq=2 powerspec 2 supports D0 D3 current D0 Freeing (NOT implemented) redirected PCI irq 9. map[20]: type 4, range 32, base 0000a800, size 5, enabled found-> vendor=0x1106, dev=0x3038, revid=0x16 bus=0, slot=7, func=3 class=0c-03-00, hdrtype=0x00, mfdev=0 cmdreg=0x0007, statreg=0x0210, cachelnsz=8 (dwords) lattimer=0x20 (960 ns), mingnt=0x00 (0 ns), maxlat=0x00 (0 ns) intpin=d, irq=2 powerspec 2 supports D0 D3 current D0 found-> vendor=0x1106, dev=0x3057, revid=0x40 bus=0, slot=7, func=4 class=06-00-00, hdrtype=0x00, mfdev=0 cmdreg=0x0000, statreg=0x0290, cachelnsz=0 (dwords) lattimer=0x00 (0 ns), mingnt=0x00 (0 ns), maxlat=0x00 (0 ns) powerspec 2 supports D0 D3 current D0 IOAPIC #0 intpin 18 -> irq 5 Freeing (NOT implemented) redirected PCI irq 10. map[10]: type 4, range 32, base 0000ac00, size 8, enabled map[14]: type 4, range 32, base 0000b000, size 2, enabled map[18]: type 4, range 32, base 0000b400, size 2, enabled found-> vendor=0x1106, dev=0x3058, revid=0x50 bus=0, slot=7, func=5 class=04-01-00, hdrtype=0x00, mfdev=0 cmdreg=0x0001, statreg=0x0210, cachelnsz=0 (dwords) lattimer=0x00 (0 ns), mingnt=0x00 (0 ns), maxlat=0x00 (0 ns) intpin=c, irq=5 powerspec 2 supports D0 D3 current D0 Freeing (NOT implemented) redirected PCI irq 10. map[10]: type 4, range 32, base 0000b800, size 3, enabled map[14]: type 4, range 32, base 0000bc00, size 2, enabled map[18]: type 4, range 32, base 0000c000, size 3, enabled map[1c]: type 4, range 32, base 0000c400, size 2, enabled map[20]: type 4, range 32, base 0000c800, size 6, enabled map[24]: type 1, range 32, base db000000, size 17, enabled found-> vendor=0x105a, dev=0x0d30, revid=0x02 bus=0, slot=12, func=0 class=01-04-00, hdrtype=0x00, mfdev=0 cmdreg=0x0007, statreg=0x0210, cachelnsz=0 (dwords) lattimer=0x20 (960 ns), mingnt=0x00 (0 ns), maxlat=0x00 (0 ns) intpin=a, irq=5 powerspec 1 supports D0 D3 current D0 Freeing (NOT implemented) redirected PCI irq 9. map[10]: type 1, range 32, base db024000, size 11, enabled map[14]: type 1, range 32, base db020000, size 14, enabled found-> vendor=0x104c, dev=0x8020, revid=0x00 bus=0, slot=13, func=0 class=0c-00-10, hdrtype=0x00, mfdev=0 cmdreg=0x0006, statreg=0x0210, cachelnsz=8 (dwords) lattimer=0x20 (960 ns), mingnt=0x03 (750 ns), maxlat=0x04 (1000 ns) intpin=a, irq=2 powerspec 1 supports D0 D2 D3 current D0 IOAPIC #0 intpin 16 -> irq 9 Freeing (NOT implemented) redirected PCI irq 5. map[10]: type 4, range 32, base 0000cc00, size 8, enabled map[14]: type 1, range 32, base db025000, size 8, enabled found-> vendor=0x1106, dev=0x3065, revid=0x43 bus=0, slot=14, func=0 class=02-00-00, hdrtype=0x00, mfdev=0 cmdreg=0x0007, statreg=0x0210, cachelnsz=8 (dwords) lattimer=0x20 (960 ns), mingnt=0x03 (750 ns), maxlat=0x08 (2000 ns) intpin=a, irq=9 powerspec 2 supports D0 D3 current D0 IOAPIC #0 intpin 17 -> irq 10 Freeing (NOT implemented) redirected PCI irq 11. map[10]: type 4, range 32, base 0000d000, size 3, enabled map[14]: type 4, range 32, base 0000d400, size 3, enabled map[18]: type 4, range 32, base 0000d800, size 3, enabled map[1c]: type 4, range 32, base 0000dc00, size 3, enabled map[20]: type 4, range 32, base 0000e000, size 3, enabled map[24]: type 4, range 32, base 0000e400, size 4, enabled found-> vendor=0x9710, dev=0x9815, revid=0x01 bus=0, slot=15, func=0 class=07-80-00, hdrtype=0x00, mfdev=0 cmdreg=0x0003, statreg=0x0280, cachelnsz=8 (dwords) lattimer=0x20 (960 ns), mingnt=0x00 (0 ns), maxlat=0x00 (0 ns) intpin=a, irq=10 Freeing (NOT implemented) redirected PCI irq 10. map[10]: type 4, range 32, base 0000e800, size 8, enabled map[14]: type 1, range 32, base db026000, size 8, enabled found-> vendor=0x10cd, dev=0x1300, revid=0x03 bus=0, slot=16, func=0 class=01-00-00, hdrtype=0x00, mfdev=0 cmdreg=0x0007, statreg=0x0280, cachelnsz=8 (dwords) lattimer=0x20 (960 ns), mingnt=0x04 (1000 ns), maxlat=0x04 (1000 ns) intpin=a, irq=5 Freeing (NOT implemented) redirected PCI irq 11. map[10]: type 4, range 32, base 0000ec00, size 8, enabled map[14]: type 1, range 32, base db027000, size 8, enabled map[18]: type 1, range 32, base db028000, size 12, enabled found-> vendor=0x1000, dev=0x000f, revid=0x26 bus=0, slot=18, func=0 class=01-00-00, hdrtype=0x00, mfdev=0 cmdreg=0x0007, statreg=0x0210, cachelnsz=8 (dwords) lattimer=0x86 (4020 ns), mingnt=0x11 (4250 ns), maxlat=0x40 (16000 ns) intpin=a, irq=10 powerspec 1 supports D0 D3 current D0 agp0: mem 0xd0000000-0xd3ffffff at device 0.0 on pci0 agp0: allocating GATT for aperture of size 256M pcib1: at device 1.0 on pci0 pcib1: secondary bus 1 pcib1: subordinate bus 1 pcib1: I/O decode 0x9000-0x9fff pcib1: memory decode 0xd8000000-0xd9ffffff pcib1: prefetched decode 0xd4000000-0xd7ffffff pci1: on pcib1 pci1: physical bus=1 Freeing (NOT implemented) redirected PCI irq 5. map[10]: type 3, range 32, base d4000000, size 26, enabled map[14]: type 4, range 32, base 00009000, size 8, enabled map[18]: type 1, range 32, base d9000000, size 14, enabled found-> vendor=0x1002, dev=0x524c, revid=0x00 bus=1, slot=0, func=0 class=03-00-00, hdrtype=0x00, mfdev=0 cmdreg=0x0087, statreg=0x02b0, cachelnsz=8 (dwords) lattimer=0x20 (960 ns), mingnt=0x08 (2000 ns), maxlat=0x00 (0 ns) intpin=a, irq=9 powerspec 1 supports D0 D1 D3 current D0 pci1: at device 0.0 (no driver attached) isab0: at device 7.0 on pci0 isa0: on isab0 atapci0: port 0xa000-0xa00f at device 7.1 on pci0 ata0: iobase=0x01f0 altiobase=0x03f6 bmaddr=0xa000 ata0: mask=03 ostat0=50 ostat2=00 ata0-master: ATAPI 00 00 ata0-slave: ATAPI 00 00 ata0: mask=03 stat0=50 stat1=00 ata0-master: ATA 01 a5 ata0: devices=01 ata0: at 0x1f0 irq 14 on atapci0 ata1: iobase=0x0170 altiobase=0x0376 bmaddr=0xa008 ata1: mask=03 ostat0=50 ostat2=00 ata1-master: ATAPI 00 00 ata1-slave: ATAPI 00 00 ata1: mask=03 stat0=50 stat1=00 ata1-master: ATA 01 a5 ata1: devices=01 ata1: at 0x170 irq 15 on atapci0 uhci0: port 0xa400-0xa41f irq 2 at device 7.2 on pci0 usb0: on uhci0 usb0: USB revision 1.0 uhub0: VIA UHCI root hub, class 9/0, rev 1.00/1.00, addr 1 uhub0: 2 ports with 2 removable, self powered uhci1: port 0xa800-0xa81f irq 2 at device 7.3 on pci0 usb1: on uhci1 usb1: USB revision 1.0 uhub1: VIA UHCI root hub, class 9/0, rev 1.00/1.00, addr 1 uhub1: 2 ports with 2 removable, self powered pci0: at device 7.5 (no driver attached) atapci1: port 0xc800-0xc83f,0xc400-0xc403,0xc000-0xc007,0xbc00-0xbc03,0xb800-0xb807 mem 0xdb000000-0xdb01ffff irq 5 at device 12.0 on pci0 ata2: iobase=0xb800 altiobase=0xbc02 bmaddr=0xc800 ata2: mask=03 ostat0=00 ostat2=00 ata2-master: ATAPI 00 00 ata2-slave: ATAPI 00 00 ata2: mask=03 stat0=00 stat1=00 ata2: devices=00 ata2: at 0xb800 on atapci1 ata3: iobase=0xc000 altiobase=0xc402 bmaddr=0xc808 ata3: mask=03 ostat0=00 ostat2=00 ata3-master: ATAPI 14 eb ata3-slave: ATAPI 10 10 ata3: mask=03 stat0=00 stat1=00 ata3: devices=04 ata3: at 0xc000 on atapci1 pci0: at device 13.0 (no driver attached) vr0: port 0xcc00-0xccff mem 0xdb025000-0xdb0250ff irq 9 at device 14.0 on pci0 vr0: Ethernet address: 00:50:ba:21:d7:c7 miibus0: on vr0 ukphy0: on miibus0 ukphy0: OUI 0x000580, model 0x0000, rev. 0 ukphy0: 10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, auto vr0: bpf attached pci0: at device 15.0 (no driver attached) adv0: port 0xe800-0xe8ff mem 0xdb026000-0xdb0260ff irq 5 at device 16.0 on pci0 adv0: Warning EEPROM Checksum mismatch. Using default device parameters adv0: AdvanSys SCSI Host Adapter, SCSI ID 7, queue depth 16 sym0: <875> port 0xec00-0xecff mem 0xdb028000-0xdb028fff,0xdb027000-0xdb0270ff irq 10 at device 18.0 on pci0 sym0: No NVRAM, ID 7, Fast-20, SE, parity checking sym0: open drain IRQ line driver, using on-chip SRAM sym0: using LOAD/STORE-based firmware. fdc0: port 0x3f7,0x3f0-0x3f5 irq 6 drq 2 on acpi0 fdc0: FIFO enabled, 8 bytes threshold fd0: <1440-KB 3.5" drive> on fdc0 drive 0 sio0: irq maps: 0x1 0x11 0x1 0x1 sio0 port 0x3f8-0x3ff irq 4 on acpi0 sio0: type 16550A unknown: not probed (disabled) sio1: irq maps: 0x1 0x9 0x1 0x1 sio1 port 0x2f8-0x2ff irq 3 on acpi0 sio1: type 16550A unknown: not probed (disabled) ppc0: using extended I/O port range ppc0: ECP SPP ECP+EPP SPP ppc0 port 0x778-0x77b,0x378-0x37f irq 7 drq 3 on acpi0 ppc0: SMC-like chipset (ECP/EPP/PS2/NIBBLE) in COMPATIBLE mode ppc0: FIFO with 16/16/8 bytes threshold plip0: on ppbus0 lp0: bpf attached lpt0: on ppbus0 lpt0: Interrupt-driven port ppi0: on ppbus0 psmcpnp0 irq 12 on acpi0 atkbdc0: port 0x64,0x60 irq 1 on acpi0 atkbd0: flags 0x1 irq 1 on atkbdc0 atkbd: the current kbd controller command byte 0047 atkbd: keyboard ID 0x41ab (2) kbd0 at atkbd0 kbd0: atkbd0, AT 101/102 (2), config:0x1, flags:0x3d0000 psm0: current command byte:0047 psm0: irq 12 on atkbdc0 psm0: model Generic PS/2 mouse, device ID 0-00, 3 buttons psm0: config:00000000, flags:00000000, packet size:3 psm0: syncmask:c0, syncbits:00 unknown: not probed (disabled) unknown: not probed (disabled) adv: adv0 already exists; skipping it ata: ata0 already exists; skipping it ata: ata1 already exists; skipping it atkbdc: atkbdc0 already exists; skipping it fdc: fdc0 already exists; skipping it ppc: ppc0 already exists; skipping it sio: sio0 already exists; skipping it sio: sio1 already exists; skipping it Trying Read_Port at 203 Trying Read_Port at 243 Trying Read_Port at 283 Trying Read_Port at 2c3 Trying Read_Port at 303 Trying Read_Port at 343 Trying Read_Port at 383 Trying Read_Port at 3c3 ex_isa_identify() sc: sc0 already exists; skipping it vga: vga0 already exists; skipping it isa_probe_children: disabling PnP devices isa_probe_children: probing non-PnP devices orm0: