From owner-freebsd-smp Sun May 7 1:16: 2 2000 Delivered-To: freebsd-smp@freebsd.org Received: from mailman.zeta.org.au (mailman.zeta.org.au [203.26.10.16]) by hub.freebsd.org (Postfix) with ESMTP id B740937BA49 for ; Sun, 7 May 2000 01:15:57 -0700 (PDT) (envelope-from bde@zeta.org.au) Received: from bde.zeta.org.au (bde.zeta.org.au [203.2.228.102]) by mailman.zeta.org.au (8.8.7/8.8.7) with ESMTP id SAA32016; Sun, 7 May 2000 18:15:24 +1000 Date: Sun, 7 May 2000 18:15:22 +1000 (EST) From: Bruce Evans X-Sender: bde@besplex.bde.org To: Steve Passe Cc: djb@ifa.au.dk, smp@FreeBSD.ORG Subject: Re: hlt instructions and temperature issues In-Reply-To: <200005070131.TAA79722@Ilsa.StevesCafe.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Sat, 6 May 2000, Steve Passe wrote: > I need to clarify, I can't think of any way the hlt could cause a stray irq7, > but in this business you can never say never... A "stray irq7" is what occurs Perhaps it does so by changing the timing. > when some piece of hardware causes an INT cycle on the PIC (in our case APIC) > to begin, but when the PIC gets to the INTACK cycle the hardware is no longer > asserting the INT. Thus the PIC has no way to build a vector to return on the > bus, so it arbitrarily uses the irq7 vector (intel design decision). Usually > the offending INT wasn't even asserted on the INT7 pin, but the hardware has > no > way of telling this... I believe its perfectly feasable that the stray irq7s > are causing printer related hangs, as a stray irq7 happening in a race with > real irq7s from the printer port could well cause problems. Authors of parallel port drivers and/or spl's should be aware of this :-). I think the ICU (and APIC?) mask for irq7 doesn't mask stray irq7's. Perhaps this causes more problems with the lazy interrupt masking and/or level triggering used in the SMP case (is irq7 ever level triggered?). The parallel port driver is sloppy about setting the bits in the ipl masks. Perhaps this causes more problems for stray irq7's than for normal ones. Bruce To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sun May 7 4:36: 8 2000 Delivered-To: freebsd-smp@freebsd.org Received: from relativity.student.utwente.nl (wit389306.student.utwente.nl [130.89.234.166]) by hub.freebsd.org (Postfix) with ESMTP id 6A50637BB0E for ; Sun, 7 May 2000 04:35:57 -0700 (PDT) (envelope-from djb@wit389306.student.utwente.nl) Received: by relativity.student.utwente.nl (Postfix, from userid 1000) id CFB275DF0; Sun, 7 May 2000 13:35:57 +0200 (CEST) Date: Sun, 7 May 2000 13:35:57 +0200 From: Dave Boers To: Steve Passe Cc: smp@FreeBSD.ORG Subject: Re: hlt instructions and temperature issues Message-ID: <20000507133557.A3051@relativity.student.utwente.nl> Reply-To: djb@ifa.au.dk References: <20000507013850.A1023@relativity.student.utwente.nl> <200005070131.TAA79722@Ilsa.StevesCafe.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 1.0.1i In-Reply-To: <200005070131.TAA79722@Ilsa.StevesCafe.com>; from smp@csn.net on Sat, May 06, 2000 at 07:31:09PM -0600 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Sat, May 06, 2000 at 07:31:09PM -0600, Steve Passe wrote: > So in summary: > > I can't see how hlt could cause stray irq7s (but it might...) > > stray irq7s could well cause a hang if occurring during printing. Just curious. Could the stray irq7's possibly indicate a hardware problem which somehow only triggers stray irq7's when the hlt instruction is there, but which can trigger a system hang in both cases? Might such a problem be caused by the UDMA66 hardware (which was the last remaining variable and which I removed from the system yesterday). BTW, thanks for the explanation of the stray irq concept. Regards, Dave. -- djb@ifa.au.dk d.j.boers@tn.utwente.nl In the land of the blind, the one-eyed man is murdered for heresy To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sun May 7 9:29:38 2000 Delivered-To: freebsd-smp@freebsd.org Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [206.168.13.65]) by hub.freebsd.org (Postfix) with ESMTP id B1E8437B6EE for ; Sun, 7 May 2000 09:29:30 -0700 (PDT) (envelope-from smp@Ilsa.StevesCafe.com) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.9.3/8.9.3) with ESMTP id KAA83403; Sun, 7 May 2000 10:29:18 -0600 (MDT) (envelope-from smp@Ilsa.StevesCafe.com) Message-Id: <200005071629.KAA83403@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0.2 2/24/98 From: Steve Passe To: Bruce Evans Cc: djb@ifa.au.dk, smp@FreeBSD.ORG Subject: Re: hlt instructions and temperature issues In-reply-to: Your message of "Sun, 07 May 2000 18:15:22 +1000." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sun, 07 May 2000 10:29:18 -0600 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Hi, > Authors of parallel port drivers and/or spl's should be aware of this :-). > I think the ICU (and APIC?) mask for irq7 doesn't mask stray irq7's. > Perhaps this causes more problems with the lazy interrupt masking and/or > level triggering used in the SMP case (is irq7 ever level triggered?). > The parallel port driver is sloppy about setting the bits in the ipl masks. > Perhaps this causes more problems for stray irq7's than for normal ones. > > Bruce --- Quoting from "Intel 82371AB PCI ISA IDE Xcelerator (PIIX4) Datasheet" In both the edge and level triggered modes, the IRQ inputs must remain active until after the falling edge of the first INTA#. If the IRQ input goes inactive before this time, a default IRQ7 occurs when the CPU acknowledges the interrupt. This can be a useful safeguard for detecting interrupts caused by spurious noise glitches on the IRQ inputs. To implement this feature, the IRQ7 routine is used for "clean up" simply executing a return instruction, thus ignoring the interrupt. If IRQ7 is needed for other purposes, a default IRQ7 can still be detected by reading the ISR. A normal IRQ7 interrupt sets the corresponding ISR bit; a default IRQ7 does not set this bit. However, If a default IRQ7 routine occurs during a normal IRQ7 routine, the ISR remains set. In this case, it is necessary to keep track of whether or not the IRQ7 routine was previously entered. If another IRQ7 occurs, its a default. --- I need to chew on your comments some more, but the bottom line is that there should never be any "spurious noise glitches" on the irq lines. At this point, we are talking about hardware bus cycles, and spl/ipl should have no causal effect (although they might HIDE and/or ENHANCE the symptoms). I have noticed stray irq7s on my desktop when removing a compactflash card from the card reader. This hardware generates an INT when a pair of pins are shorted by the act of inserting the card. I can imagine this causing glitches as the (cheap) hardware probably doesn't buffer that pin well. Another reason that stray irq7s sometimes occur is a misconfigured setup with "dueling INTs". --- I just ran dmesg on my asus p2b-ds, FreeBSD 4.0-CURRENT #0: Mon Feb 14, 2000 and saw this: stray irq 7 stray irq 7 stray irq 7 stray irq 7 stray irq 7 too many stray irq 7's; not logging any more Perhaps we've added a problem that's gone unnoticed? This system does NOT have the hlt patch. This code is from i386/isa/intr_machdep.c: /* * XXX TODO print a different message for #7 if it is for a * glitch. Glitches can be distinguished from real #7's by * testing that the in-service bit is _not_ set. The test * must be done before sending an EOI so it can't be done if * we are using AUTO_EOI_1. */ if (intrcnt[1 + intr] <= 5) log(LOG_ERR, "stray irq %d\n", intr); So evidently we do not yet determine if an INT7 is "stray" or "real". I don't think irq7 would be level mapped, unless the MPtable was hosed..., it should say either conforms or edge. But mpapic.c should deal with that: if ((bustype == ISA) && (pin < IOAPIC_ISA_INTS) && (irq == pin) && (apic_polarity(apic, pin) == 0x1) && (apic_trigger(apic, pin) == 0x3)) { /* * A broken BIOS might describe some ISA * interrupts as active-high level-triggered. * Use default ISA flags for those interrupts. */ flags = DEFAULT_ISA_FLAGS; } else { /* * Program polarity and trigger mode according to * interrupt entry. */ -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sun May 7 10: 2: 7 2000 Delivered-To: freebsd-smp@freebsd.org Received: from relativity.student.utwente.nl (wit389306.student.utwente.nl [130.89.234.166]) by hub.freebsd.org (Postfix) with ESMTP id 159A437B6EE for ; Sun, 7 May 2000 10:02:05 -0700 (PDT) (envelope-from djb@wit389306.student.utwente.nl) Received: by relativity.student.utwente.nl (Postfix, from userid 1000) id 6821E5DF0; Sun, 7 May 2000 19:02:05 +0200 (CEST) Date: Sun, 7 May 2000 19:02:05 +0200 From: Dave Boers To: Steve Passe Cc: Bruce Evans , djb@ifa.au.dk, smp@FreeBSD.ORG Subject: Re: hlt instructions and temperature issues Message-ID: <20000507190205.B3619@relativity.student.utwente.nl> Reply-To: djb@ifa.au.dk References: <200005071629.KAA83403@Ilsa.StevesCafe.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 1.0.1i In-Reply-To: <200005071629.KAA83403@Ilsa.StevesCafe.com>; from smp@csn.net on Sun, May 07, 2000 at 10:29:18AM -0600 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Sun, May 07, 2000 at 10:29:18AM -0600, Steve Passe wrote: > I just ran dmesg on my asus p2b-ds, FreeBSD 4.0-CURRENT #0: Mon Feb 14, 2000 > and saw this: > > stray irq 7 > stray irq 7 > stray irq 7 > stray irq 7 > stray irq 7 > too many stray irq 7's; not logging any more That's exactly the same as what occurred here. They didn't occur until I added the hlt instruction; but now I've physically removed the UDMA66 drive, I disabled the (Highpoint) interface and PIIX4 in the bios, and I removed the ata driver from my kernel and guess what? The stray irq7's are gone! Not a single one in dmesg, and uptime is 17 hours. The hlt instruction is still there. Regards, Dave. -- djb@ifa.au.dk d.j.boers@tn.utwente.nl In the land of the blind, the one-eyed man is murdered for heresy To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sun May 7 11:41:59 2000 Delivered-To: freebsd-smp@freebsd.org Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [206.168.13.65]) by hub.freebsd.org (Postfix) with ESMTP id 3F9FD37BA8A for ; Sun, 7 May 2000 11:41:53 -0700 (PDT) (envelope-from fbsd@Ilsa.StevesCafe.com) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.9.3/8.9.3) with ESMTP id MAA83955; Sun, 7 May 2000 12:41:39 -0600 (MDT) (envelope-from fbsd@Ilsa.StevesCafe.com) Message-Id: <200005071841.MAA83955@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0.2 2/24/98 From: Steve Passe To: djb@ifa.au.dk Cc: Bruce Evans , smp@FreeBSD.ORG Subject: Re: hlt instructions and temperature issues In-reply-to: Your message of "Sun, 07 May 2000 19:02:05 +0200." <20000507190205.B3619@relativity.student.utwente.nl> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sun, 07 May 2000 12:41:39 -0600 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Hi, > On Sun, May 07, 2000 at 10:29:18AM -0600, Steve Passe wrote: > > I just ran dmesg on my asus p2b-ds, FreeBSD 4.0-CURRENT #0: Mon Feb 14, 2000 > > and saw this: > > > > stray irq 7 > > stray irq 7 > > stray irq 7 > > stray irq 7 > > stray irq 7 > > too many stray irq 7's; not logging any more > > That's exactly the same as what occurred here. They didn't occur until I > added the hlt instruction; but now I've physically removed the UDMA66 > drive, I disabled the (Highpoint) interface and PIIX4 in the bios, and I ^^^^^ not sure what this means? > removed the ata driver from my kernel and guess what? The stray irq7's are > gone! Not a single one in dmesg, and uptime is 17 hours. The hlt > instruction is still there. It would be interesting to with: no physical disk, BIOS/ata driver active. no physical disk, BIOS ata disabled, ata driver active. The question now is whether the hardware is funky, or our setup of the hardware causes it to act funky, or if we artifically manufacture the stray irq7s. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sun May 7 12: 6:41 2000 Delivered-To: freebsd-smp@freebsd.org Received: from relativity.student.utwente.nl (wit389306.student.utwente.nl [130.89.234.166]) by hub.freebsd.org (Postfix) with ESMTP id 1961237B80E for ; Sun, 7 May 2000 12:06:34 -0700 (PDT) (envelope-from djb@wit389306.student.utwente.nl) Received: by relativity.student.utwente.nl (Postfix, from userid 1000) id 14EE25DF0; Sun, 7 May 2000 21:06:35 +0200 (CEST) Date: Sun, 7 May 2000 21:06:35 +0200 From: Dave Boers To: Steve Passe Cc: djb@ifa.au.dk, Bruce Evans , smp@FreeBSD.ORG Subject: Re: hlt instructions and temperature issues Message-ID: <20000507210634.A3886@relativity.student.utwente.nl> Reply-To: djb@ifa.au.dk References: <20000507190205.B3619@relativity.student.utwente.nl> <200005071841.MAA83955@Ilsa.StevesCafe.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 1.0.1i In-Reply-To: <200005071841.MAA83955@Ilsa.StevesCafe.com>; from smp@csn.net on Sun, May 07, 2000 at 12:41:39PM -0600 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Sun, May 07, 2000 at 12:41:39PM -0600, Steve Passe wrote: > > > [ stray irq7's in dmesg ] > > That's exactly the same as what occurred here. They didn't occur until I > > added the hlt instruction; but now I've physically removed the UDMA66 > > drive, I disabled the (Highpoint) interface and PIIX4 in the bios, and I > ^^^^^ > not sure what this means? I'm sorry. I meant the ordinary IDE interface only. The Abit BP6 (dual celeron) mainboard has two dual channel IDE controllers: the PIIX4 one (max UDMA33) and the Highpoint one (max UDMA66). > > removed the ata driver from my kernel and guess what? The stray irq7's are > > gone! Not a single one in dmesg, and uptime is 17 hours. The hlt > > instruction is still there. > > It would be interesting to with: > > no physical disk, BIOS/ata driver active. > > no physical disk, BIOS ata disabled, ata driver active. > > The question now is whether the hardware is funky, or our setup of the > hardware causes it to act funky, or if we artifically manufacture the > stray irq7s. I'll do the testing but (tomorrow) I first have to get a nasty wisdom tooth removed at the dental surgeon's. I don't know how long I need to recover but I'll do the testing afterwards. Regards, Dave. -- djb@ifa.au.dk d.j.boers@tn.utwente.nl In the land of the blind, the one-eyed man is murdered for heresy To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sun May 7 12:21:30 2000 Delivered-To: freebsd-smp@freebsd.org Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [206.168.13.65]) by hub.freebsd.org (Postfix) with ESMTP id 49CC837B80E for ; Sun, 7 May 2000 12:21:26 -0700 (PDT) (envelope-from fbsd@Ilsa.StevesCafe.com) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.9.3/8.9.3) with ESMTP id NAA84109; Sun, 7 May 2000 13:21:11 -0600 (MDT) (envelope-from fbsd@Ilsa.StevesCafe.com) Message-Id: <200005071921.NAA84109@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0.2 2/24/98 From: Steve Passe To: djb@ifa.au.dk Cc: Bruce Evans , smp@FreeBSD.ORG Subject: Re: hlt instructions and temperature issues In-reply-to: Your message of "Sun, 07 May 2000 21:06:35 +0200." <20000507210634.A3886@relativity.student.utwente.nl> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sun, 07 May 2000 13:21:11 -0600 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Hi, > On Sun, May 07, 2000 at 12:41:39PM -0600, Steve Passe wrote: > > > > [ stray irq7's in dmesg ] > > > That's exactly the same as what occurred here. They didn't occur until I > > > added the hlt instruction; but now I've physically removed the UDMA66 > > > drive, I disabled the (Highpoint) interface and PIIX4 in the bios, and I > > ^^^^^ > > not sure what this means? > > I'm sorry. I meant the ordinary IDE interface only. The Abit BP6 (dual > celeron) mainboard has two dual channel IDE controllers: the PIIX4 one (max > UDMA33) and the Highpoint one (max UDMA66). So when both controllers were enabled, did the BIOS properly assign one to irq14, and the second to irq15? The PIIX4 chip itself contains 2 IDE channels (ie 2 busses x 2 drives). Can you disable individual channels, or does enabling the UDMA33 force both to be active? If both UDMA33 channels were active, as well as the UDMA66, this moight cause the irq7 problem... Did fbsd also assign them to 14 and 15? Were there any drives on the UDAM33 bus? -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sun May 7 13:53:33 2000 Delivered-To: freebsd-smp@freebsd.org Received: from relativity.student.utwente.nl (wit389306.student.utwente.nl [130.89.234.166]) by hub.freebsd.org (Postfix) with ESMTP id 4D8E337BDE5 for ; Sun, 7 May 2000 13:53:24 -0700 (PDT) (envelope-from djb@wit389306.student.utwente.nl) Received: by relativity.student.utwente.nl (Postfix, from userid 1000) id B01645DF0; Sun, 7 May 2000 22:53:25 +0200 (CEST) Date: Sun, 7 May 2000 22:53:25 +0200 From: Dave Boers To: Steve Passe Cc: djb@ifa.au.dk, Bruce Evans , smp@FreeBSD.ORG Subject: Re: hlt instructions and temperature issues Message-ID: <20000507225325.A4343@relativity.student.utwente.nl> Reply-To: djb@ifa.au.dk References: <20000507210634.A3886@relativity.student.utwente.nl> <200005071921.NAA84109@Ilsa.StevesCafe.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 1.0.1i In-Reply-To: <200005071921.NAA84109@Ilsa.StevesCafe.com>; from smp@csn.net on Sun, May 07, 2000 at 01:21:11PM -0600 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Sun, May 07, 2000 at 01:21:11PM -0600, Steve Passe wrote: > So when both controllers were enabled, did the BIOS properly assign > one to irq14, and the second to irq15? Both controllers were never enabled at the same time. Since I only got one IDE drive in the system and that one's connected to the Highpoint controller. I always disabled the PIIX4 IDE controller. > The PIIX4 chip itself contains 2 IDE channels (ie 2 busses x 2 drives). And so does the Highpoint controller. You can hook up to eight IDE drives onto an Abit BP6 mainboard. > Can you disable individual channels, or does enabling the UDMA33 force > both to be active? On the UDMA33 I can enable/disable individual channels, on the Highpoint everything is "automatic" and the Highpoint BIOS autodetects the drives on it's controller. I believe in later revisions of the BP6 BIOS you can enter a separate menu to tune the Highpoint controller, but I never did a bios upgrade. > If both UDMA33 channels were active, as well as the UDMA66, this > might cause the irq7 problem... They weren't. > Did fbsd also assign them to 14 and 15? No. I've attached two dmesg's (from /var/log/messages). One including the ata driver in the kernel and with the Highpoint IDE controller enabled and the other with all IDE disabled (the current configuration). Please pay no attention to the unconfigured USB hardware about which the kernel complains. I didn't get around to configuring that yet. The USB has it's irq disabled in the BIOS. I don't think it's causing the stray irq7's however, because it's configuration hasn't changed between the dmesgs and the stray irq7's went away anyway. Also, no usb devices are attached. Regards, Dave. -- djb@ifa.au.dk d.j.boers@tn.utwente.nl Copyright (C) 2000 by Dave J. Boers All rights reserved In the land of the blind, the one-eyed man is murdered for heresy -----> BOOT MESSAGES WITH HIGHPOINT IDE ENABLED: May 6 22:39:38 relativity /kernel: Copyright (c) 1992-2000 The FreeBSD Project. May 6 22:39:38 relativity /kernel: Copyright (c) 1982, 1986, 1989, 1991, 1993 May 6 22:39:38 relativity /kernel: The Regents of the University of California. All rights reserved. May 6 22:39:38 relativity /kernel: FreeBSD 4.0-STABLE #0: Wed May 3 21:45:36 CEST 2000 May 6 22:39:38 relativity /kernel: root@relativity.student.utwente.nl:/usr/src/sys/compile/STABLE01 May 6 22:39:38 relativity /kernel: Timecounter "i8254" frequency 1193182 Hz May 6 22:39:38 relativity /kernel: CPU: Pentium II/Pentium II Xeon/Celeron (400.91-MHz 686-class CPU) May 6 22:39:38 relativity /kernel: Origin = "GenuineIntel" Id = 0x665 Stepping = 5 May 6 22:39:38 relativity /kernel: Features=0x183fbff May 6 22:39:38 relativity /kernel: real memory = 268435456 (262144K bytes) May 6 22:39:39 relativity /kernel: avail memory = 257224704 (251196K bytes) May 6 22:39:39 relativity /kernel: Programming 24 pins in IOAPIC #0 May 6 22:39:39 relativity /kernel: IOAPIC #0 intpin 2 -> irq 0 May 6 22:39:39 relativity /kernel: FreeBSD/SMP: Multiprocessor motherboard May 6 22:39:39 relativity /kernel: cpu0 (BSP): apic id: 0, version: 0x00040011, at 0xfee00000 May 6 22:39:39 relativity /kernel: cpu1 (AP): apic id: 1, version: 0x00040011, at 0xfee00000 May 6 22:39:39 relativity /kernel: io0 (APIC): apic id: 2, version: 0x00170011, at 0xfec00000 May 6 22:39:39 relativity /kernel: Preloaded elf kernel "kernel" at 0xc03c1000. May 6 22:39:39 relativity /kernel: Pentium Pro MTRR support enabled May 6 22:39:39 relativity /kernel: npx0: on motherboard May 6 22:39:39 relativity /kernel: npx0: INT 16 interface May 6 22:39:39 relativity /kernel: pcib0: on motherboard May 6 22:39:39 relativity /kernel: pci0: on pcib0 May 6 22:39:39 relativity /kernel: pcib1: at device 1.0 on pci0 May 6 22:39:39 relativity /kernel: pci1: on pcib1 May 6 22:39:39 relativity /kernel: pci1: at 0.0 irq 16 May 6 22:39:39 relativity /kernel: isab0: at device 7.0 on pci0 May 6 22:39:39 relativity /kernel: isa0: on isab0 May 6 22:39:39 relativity /kernel: atapci0: port 0xf000-0xf00f at device 7.1 on pci0 May 6 22:39:39 relativity /kernel: uhci0: port 0xa000-0xa01f at device 7.2 on pci0 May 6 22:39:39 relativity /kernel: uhci0: Invalid irq 255 May 6 22:39:39 relativity /kernel: uhci0: Please switch on USB support and switch PNP-OS to 'No' in BIOS May 6 22:39:39 relativity /kernel: device_probe_and_attach: uhci0 attach returned 6 May 6 22:39:39 relativity /kernel: Timecounter "PIIX" frequency 3579545 Hz May 6 22:39:39 relativity /kernel: chip1: port 0x5000-0x500f at device 7.3 on pci0 May 6 22:39:39 relativity /kernel: fxp0: port 0xa400-0xa41f mem 0xeb000000-0xeb0fffff,0xeb203000-0xeb203fff irq 19 at device 9.0 on pci0 May 6 22:39:39 relativity /kernel: fxp0: Ethernet address 00:a0:c9:9f:a6:59 May 6 22:39:39 relativity /kernel: fxp0: supplying EUI64: 00:a0:c9:ff:fe:9f:a6:59 May 6 22:39:39 relativity /kernel: sym0: <895> port 0xa800-0xa8ff mem 0xeb202000-0xeb202fff,0xeb200000-0xeb2000ff irq 18 at device 11.0 on pci0 May 6 22:39:39 relativity /kernel: sym0: Tekram NVRAM, ID 7, Fast-40, LVD, parity checking May 6 22:39:39 relativity /kernel: xl0: <3Com 3c905B-TX Fast Etherlink XL> port 0xac00-0xac7f mem 0xeb204000-0xeb20407f irq 17 at device 13.0 on pci0 May 6 22:39:39 relativity /kernel: xl0: Ethernet address: 00:10:5a:65:33:80 May 6 22:39:39 relativity /kernel: miibus0: on xl0 May 6 22:39:39 relativity /kernel: xlphy0: <3Com internal media interface> on miibus0 May 6 22:39:39 relativity /kernel: xlphy0: 10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, auto May 6 22:39:39 relativity /kernel: fxp1: port 0xb000-0xb01f mem 0xeb100000-0xeb1fffff,0xeb201000-0xeb201fff irq 16 at device 15.0 on pci0 May 6 22:39:39 relativity /kernel: fxp1: Ethernet address 00:a0:c9:9f:a6:ae May 6 22:39:39 relativity /kernel: atapci1: port 0xbc00-0xbcff,0xb800-0xb803,0xb400-0xb407 irq 18 at device 19.0 on pci0 May 6 22:39:39 relativity /kernel: ata2: at 0xb400 on atapci1 May 6 22:39:40 relativity /kernel: atapci2: port 0xc800-0xc8ff,0xc400-0xc403,0xc000-0xc007 irq 18 at device 19.1 on pci0 May 6 22:39:40 relativity /kernel: fdc0: at port 0x3f0-0x3f5,0x3f7 irq 6 drq 2 on isa0 May 6 22:39:40 relativity /kernel: fdc0: FIFO enabled, 8 bytes threshold May 6 22:39:40 relativity /kernel: fd0: <1440-KB 3.5" drive> on fdc0 drive 0 May 6 22:39:40 relativity /kernel: atkbdc0: at port 0x60,0x64 on isa0 May 6 22:39:40 relativity /kernel: atkbd0: irq 1 on atkbdc0 May 6 22:39:40 relativity /kernel: psm0: irq 12 on atkbdc0 May 6 22:39:40 relativity /kernel: psm0: model Generic PS/2 mouse, device ID 0 May 6 22:39:40 relativity /kernel: vga0: at port 0x3c0-0x3df iomem 0xa0000-0xbffff on isa0 May 6 22:39:40 relativity /kernel: sc0: on isa0 May 6 22:39:40 relativity /kernel: sc0: VGA <16 virtual consoles, flags=0x200> May 6 22:39:40 relativity /kernel: sio0 at port 0x3f8-0x3ff irq 4 flags 0x10 on isa0 May 6 22:39:40 relativity /kernel: sio0: type 16550A May 6 22:39:40 relativity /kernel: sio1: configured irq 3 not in bitmap of probed irqs 0 May 6 22:39:40 relativity /kernel: ppc0: at port 0x378-0x37f irq 7 on isa0 May 6 22:39:40 relativity /kernel: ppc0: Generic chipset (NIBBLE-only) in COMPATIBLE mode May 6 22:39:40 relativity /kernel: ppi0: on ppbus0 May 6 22:39:40 relativity /kernel: lpt0: on ppbus0 May 6 22:39:40 relativity /kernel: lpt0: Interrupt-driven port May 6 22:39:40 relativity /kernel: plip0: on ppbus0 May 6 22:39:40 relativity /kernel: sbc0: at port 0x220-0x22f,0x330-0x331,0x388-0x38b irq 5 drq 1,5 on isa0 May 6 22:39:40 relativity /kernel: sbc0: setting card to irq 5, drq 1, 5 May 6 22:39:40 relativity /kernel: pcm0: on sbc0 May 6 22:39:40 relativity /kernel: unknown0: at port 0x168-0x16f,0x36e-0x36f irq 10 on isa0 May 6 22:39:40 relativity /kernel: unknown1: at port 0x100 on isa0 May 6 22:39:40 relativity /kernel: unknown2: at port 0x200-0x207 on isa0 May 6 22:39:40 relativity /kernel: APIC_IO: Testing 8254 interrupt delivery May 6 22:39:40 relativity /kernel: APIC_IO: routing 8254 via IOAPIC #0 intpin 2 May 6 22:39:40 relativity /kernel: IP packet filtering initialized, divert enabled, rule-based forwarding disabled, default to deny, unlimited logging May 6 22:39:40 relativity /kernel: DUMMYNET initialized (000106) May 6 22:39:40 relativity /kernel: IPsec: Initialized Security Association Processing. May 6 22:39:40 relativity /kernel: SMP: AP CPU #1 Launched! May 6 22:39:40 relativity /kernel: ad4: 17206MB [34960/16/63] at ata2-master using UDMA66 May 6 22:39:40 relativity /kernel: Waiting 2 seconds for SCSI devices to settle May 6 22:39:40 relativity /kernel: da0 at sym0 bus 0 target 4 lun 0 May 6 22:39:40 relativity /kernel: da0: Fixed Direct Access SCSI-3 device May 6 22:39:40 relativity /kernel: da0: 80.000MB/s transfers (40.000MHz, offset 31, 16bit), Tagged Queueing Enabled May 6 22:39:40 relativity /kernel: da0: 17522MB (35885168 512 byte sectors: 255H 63S/T 2233C) May 6 22:39:40 relativity /kernel: cd0 at sym0 bus 0 target 1 lun 0 May 6 22:39:40 relativity /kernel: cd0: Removable CD-ROM SCSI-2 device May 6 22:39:40 relativity /kernel: cd0: 10.000MB/s transfers (10.000MHz, offset 8) May 6 22:39:40 relativity /kernel: cd0: cd present [309750 x 2048 byte records] May 6 22:39:40 relativity /kernel: Mounting root from ufs:/dev/da0s1a May 6 22:39:40 relativity /kernel: cd1 at sym0 bus 0 target 2 lun 0 May 6 22:39:40 relativity /kernel: cd1: Removable CD-ROM SCSI-2 device May 6 22:39:40 relativity /kernel: cd1: 10.000MB/s transfers (10.000MHz, offset 8) May 6 22:39:40 relativity /kernel: cd1: Attempt to query device size failed: NOT READY, Medium not present . . . Here's the first stray irq 7 May 6 22:39:52 relativity /kernel: stray irq 7 . . . And now with Highpoint disabled and ide hardware disconnected May 7 01:57:59 relativity /kernel: Copyright (c) 1992-2000 The FreeBSD Project. May 7 01:57:59 relativity /kernel: Copyright (c) 1982, 1986, 1989, 1991, 1993 May 7 01:57:59 relativity /kernel: The Regents of the University of California. All rights reserved. May 7 01:57:59 relativity /kernel: FreeBSD 4.0-STABLE #0: Sun May 7 01:47:18 CEST 2000 May 7 01:57:59 relativity /kernel: djb@relativity.student.utwente.nl:/usr/src/sys/compile/SCSIONLY01 May 7 01:57:59 relativity /kernel: Timecounter "i8254" frequency 1193182 Hz May 7 01:57:59 relativity /kernel: CPU: Pentium II/Pentium II Xeon/Celeron (400.91-MHz 686-class CPU) May 7 01:57:59 relativity /kernel: Origin = "GenuineIntel" Id = 0x665 Stepping = 5 May 7 01:57:59 relativity /kernel: Features=0x183fbff May 7 01:57:59 relativity /kernel: real memory = 268435456 (262144K bytes) May 7 01:58:00 relativity /kernel: avail memory = 257257472 (251228K bytes) May 7 01:58:00 relativity /kernel: Programming 24 pins in IOAPIC #0 May 7 01:58:00 relativity /kernel: IOAPIC #0 intpin 2 -> irq 0 May 7 01:58:00 relativity /kernel: FreeBSD/SMP: Multiprocessor motherboard May 7 01:58:00 relativity /kernel: cpu0 (BSP): apic id: 0, version: 0x00040011, at 0xfee00000 May 7 01:58:00 relativity /kernel: cpu1 (AP): apic id: 1, version: 0x00040011, at 0xfee00000 May 7 01:58:00 relativity /kernel: io0 (APIC): apic id: 2, version: 0x00170011, at 0xfec00000 May 7 01:58:00 relativity /kernel: Preloaded elf kernel "kernel" at 0xc03b9000. May 7 01:58:00 relativity /kernel: Pentium Pro MTRR support enabled May 7 01:58:00 relativity /kernel: npx0: on motherboard May 7 01:58:00 relativity /kernel: npx0: INT 16 interface May 7 01:58:00 relativity /kernel: pcib0: on motherboard May 7 01:58:00 relativity /kernel: pci0: on pcib0 May 7 01:58:00 relativity /kernel: pcib1: at device 1.0 on pci0 May 7 01:58:00 relativity /kernel: pci1: on pcib1 May 7 01:58:00 relativity /kernel: pci1: at 0.0 irq 16 May 7 01:58:00 relativity /kernel: isab0: at device 7.0 on pci0 May 7 01:58:00 relativity /kernel: isa0: on isab0 May 7 01:58:00 relativity /kernel: pci0: at 7.1 May 7 01:58:00 relativity /kernel: uhci0: port 0xa000-0xa01f at device 7.2 on pci0 May 7 01:58:00 relativity /kernel: uhci0: Invalid irq 255 May 7 01:58:00 relativity /kernel: uhci0: Please switch on USB support and switch PNP-OS to 'No' in BIOS May 7 01:58:00 relativity /kernel: device_probe_and_attach: uhci0 attach returned 6 May 7 01:58:00 relativity /kernel: Timecounter "PIIX" frequency 3579545 Hz May 7 01:58:00 relativity /kernel: chip1: port 0x5000-0x500f at device 7.3 on pci0 May 7 01:58:00 relativity /kernel: fxp0: port 0xa400-0xa41f mem 0xeb000000-0xeb0fffff,0xeb203000-0xeb203fff irq 19 at device 9.0 on pci0 May 7 01:58:00 relativity /kernel: fxp0: Ethernet address 00:a0:c9:9f:a6:59 May 7 01:58:00 relativity /kernel: fxp0: supplying EUI64: 00:a0:c9:ff:fe:9f:a6:59 May 7 01:58:00 relativity /kernel: sym0: <895> port 0xa800-0xa8ff mem 0xeb202000-0xeb202fff,0xeb200000-0xeb2000ff irq 18 at device 11.0 on pci0 May 7 01:58:00 relativity /kernel: sym0: Tekram NVRAM, ID 7, Fast-40, LVD, parity checking May 7 01:58:00 relativity /kernel: xl0: <3Com 3c905B-TX Fast Etherlink XL> port 0xac00-0xac7f mem 0xeb204000-0xeb20407f irq 17 at device 13.0 on pci0 May 7 01:58:00 relativity /kernel: xl0: Ethernet address: 00:10:5a:65:33:80 May 7 01:58:00 relativity /kernel: miibus0: on xl0 May 7 01:58:00 relativity /kernel: xlphy0: <3Com internal media interface> on miibus0 May 7 01:58:00 relativity /kernel: xlphy0: 10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, auto May 7 01:58:00 relativity /kernel: fxp1: port 0xb000-0xb01f mem 0xeb100000-0xeb1fffff,0xeb201000-0xeb201fff irq 16 at device 15.0 on pci0 May 7 01:58:00 relativity /kernel: fxp1: Ethernet address 00:a0:c9:9f:a6:ae May 7 01:58:00 relativity /kernel: pci0: at 19.0 irq 18 May 7 01:58:00 relativity /kernel: pci0: at 19.1 irq 18 May 7 01:58:00 relativity /kernel: fdc0: at port 0x3f0-0x3f5,0x3f7 irq 6 drq 2 on isa0 May 7 01:58:00 relativity /kernel: fdc0: FIFO enabled, 8 bytes threshold May 7 01:58:00 relativity /kernel: fd0: <1440-KB 3.5" drive> on fdc0 drive 0 May 7 01:58:00 relativity /kernel: atkbdc0: at port 0x60,0x64 on isa0 May 7 01:58:00 relativity /kernel: atkbd0: irq 1 on atkbdc0 May 7 01:58:00 relativity /kernel: psm0: irq 12 on atkbdc0 May 7 01:58:00 relativity /kernel: psm0: model Generic PS/2 mouse, device ID 0 May 7 01:58:00 relativity /kernel: vga0: at port 0x3c0-0x3df iomem 0xa0000-0xbffff on isa0 May 7 01:58:00 relativity /kernel: sc0: on isa0 May 7 01:58:00 relativity /kernel: sc0: VGA <16 virtual consoles, flags=0x200> May 7 01:58:00 relativity /kernel: sio0 at port 0x3f8-0x3ff irq 4 flags 0x10 on isa0 May 7 01:58:00 relativity /kernel: sio0: type 16550A May 7 01:58:00 relativity /kernel: sio1: configured irq 3 not in bitmap of probed irqs 0 May 7 01:58:00 relativity /kernel: ppc0: at port 0x378-0x37f irq 7 on isa0 May 7 01:58:00 relativity /kernel: ppc0: SMC-like chipset (ECP/EPP/PS2/NIBBLE) in COMPATIBLE mode May 7 01:58:00 relativity /kernel: ppc0: FIFO with 16/16/16 bytes threshold May 7 01:58:00 relativity /kernel: ppi0: on ppbus0 May 7 01:58:00 relativity /kernel: lpt0: on ppbus0 May 7 01:58:00 relativity /kernel: lpt0: Interrupt-driven port May 7 01:58:00 relativity /kernel: plip0: on ppbus0 May 7 01:58:00 relativity /kernel: sbc0: at port 0x220-0x22f,0x330-0x331,0x388-0x38b irq 5 drq 1,5 on isa0 May 7 01:58:00 relativity /kernel: sbc0: setting card to irq 5, drq 1, 5 May 7 01:58:00 relativity /kernel: pcm0: on sbc0 May 7 01:58:00 relativity /kernel: unknown0: at port 0x168-0x16f,0x36e-0x36f irq 10 on isa0 May 7 01:58:00 relativity /kernel: unknown1: at port 0x100 on isa0 May 7 01:58:00 relativity /kernel: unknown2: at port 0x200-0x207 on isa0 May 7 01:58:00 relativity /kernel: APIC_IO: Testing 8254 interrupt delivery May 7 01:58:00 relativity /kernel: APIC_IO: routing 8254 via IOAPIC #0 intpin 2 May 7 01:58:00 relativity /kernel: IP packet filtering initialized, divert enabled, rule-based forwarding disabled, default to deny, unlimited logging May 7 01:58:00 relativity /kernel: DUMMYNET initialized (000106) May 7 01:58:00 relativity /kernel: IPsec: Initialized Security Association Processing. May 7 01:58:00 relativity /kernel: Waiting 2 seconds for SCSI devices to settle May 7 01:58:00 relativity /kernel: SMP: AP CPU #1 Launched! May 7 01:58:00 relativity /kernel: da0 at sym0 bus 0 target 4 lun 0 May 7 01:58:00 relativity /kernel: da0: Fixed Direct Access SCSI-3 device May 7 01:58:00 relativity /kernel: da0: 80.000MB/s transfers (40.000MHz, offset 31, 16bit), Tagged Queueing Enabled May 7 01:58:00 relativity /kernel: da0: 17522MB (35885168 512 byte sectors: 255H 63S/T 2233C) May 7 01:58:00 relativity /kernel: cd0 at sym0 bus 0 target 1 lun 0 May 7 01:58:00 relativity /kernel: cd0: Removable CD-ROM SCSI-2 device May 7 01:58:00 relativity /kernel: cd0: 10.000MB/s transfers (10.000MHz, offset 8) May 7 01:58:00 relativity /kernel: cd0: cd present [309750 x 2048 byte records] May 7 01:58:00 relativity /kernel: Mounting root from ufs:/dev/da0s1a May 7 01:58:00 relativity /kernel: cd1 at sym0 bus 0 target 2 lun 0 May 7 01:58:00 relativity /kernel: cd1: Removable CD-ROM SCSI-2 device May 7 01:58:00 relativity /kernel: cd1: 10.000MB/s transfers (10.000MHz, offset 8) May 7 01:58:00 relativity /kernel: cd1: Attempt to query device size failed: NOT READY, Medium not present ... no more stray irq7's ... To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sun May 7 14: 9:45 2000 Delivered-To: freebsd-smp@freebsd.org Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [206.168.13.65]) by hub.freebsd.org (Postfix) with ESMTP id D08E837B757 for ; Sun, 7 May 2000 14:09:38 -0700 (PDT) (envelope-from fbsd@Ilsa.StevesCafe.com) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.9.3/8.9.3) with ESMTP id PAA84796; Sun, 7 May 2000 15:04:50 -0600 (MDT) (envelope-from fbsd@Ilsa.StevesCafe.com) Message-Id: <200005072104.PAA84796@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0.2 2/24/98 From: Steve Passe To: djb@ifa.au.dk Cc: Bruce Evans , smp@FreeBSD.ORG Subject: Re: hlt instructions and temperature issues In-reply-to: Your message of "Sun, 07 May 2000 22:53:25 +0200." <20000507225325.A4343@relativity.student.utwente.nl> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sun, 07 May 2000 15:04:50 -0600 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Hi, from the " One including the ata driver in the kernel and with the Highpoint IDE controller enabled": > May 6 22:39:40 relativity /kernel: unknown0: at port 0x168-0x16f,0x36e-0x36f irq 10 on isa0 was the UDMA33 controller enabled in the BIOS for this one? -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sun May 7 14:43:15 2000 Delivered-To: freebsd-smp@freebsd.org Received: from relativity.student.utwente.nl (wit389306.student.utwente.nl [130.89.234.166]) by hub.freebsd.org (Postfix) with ESMTP id D9ADF37BA67 for ; Sun, 7 May 2000 14:43:12 -0700 (PDT) (envelope-from djb@wit389306.student.utwente.nl) Received: by relativity.student.utwente.nl (Postfix, from userid 1000) id F26285DF0; Sun, 7 May 2000 23:43:10 +0200 (CEST) Date: Sun, 7 May 2000 23:43:10 +0200 From: Dave Boers To: Steve Passe Cc: djb@ifa.au.dk, Bruce Evans , smp@FreeBSD.ORG Subject: Re: hlt instructions and temperature issues Message-ID: <20000507234310.A4505@relativity.student.utwente.nl> Reply-To: djb@ifa.au.dk References: <20000507225325.A4343@relativity.student.utwente.nl> <200005072104.PAA84796@Ilsa.StevesCafe.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 1.0.1i In-Reply-To: <200005072104.PAA84796@Ilsa.StevesCafe.com>; from smp@csn.net on Sun, May 07, 2000 at 03:04:50PM -0600 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org On Sun, May 07, 2000 at 03:04:50PM -0600, Steve Passe wrote: > from the " One including the ata driver in the kernel and with the > Highpoint IDE controller enabled": > > > May 6 22:39:40 relativity /kernel: unknown0: at port 0x168-0x16f,0x36e-0x36f irq 10 on isa0 > > was the UDMA33 controller enabled in the BIOS for this one? No it wasn't. What you're seeing is a message for the IDE interface on the SB16 sound card. Regards, Dave. -- djb@ifa.au.dk d.j.boers@tn.utwente.nl In the land of the blind, the one-eyed man is murdered for heresy To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Sun May 7 15:22: 2 2000 Delivered-To: freebsd-smp@freebsd.org Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [206.168.13.65]) by hub.freebsd.org (Postfix) with ESMTP id 7C88937C111 for ; Sun, 7 May 2000 15:21:58 -0700 (PDT) (envelope-from fbsd@Ilsa.StevesCafe.com) Received: from Ilsa.StevesCafe.com (localhost [127.0.0.1]) by Ilsa.StevesCafe.com (8.9.3/8.9.3) with ESMTP id QAA00636; Sun, 7 May 2000 16:17:10 -0600 (MDT) (envelope-from fbsd@Ilsa.StevesCafe.com) Message-Id: <200005072217.QAA00636@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0.2 2/24/98 From: Steve Passe To: djb@ifa.au.dk Cc: Bruce Evans , smp@FreeBSD.ORG Subject: Re: hlt instructions and temperature issues In-reply-to: Your message of "Sun, 07 May 2000 23:43:10 +0200." <20000507234310.A4505@relativity.student.utwente.nl> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sun, 07 May 2000 16:17:10 -0600 Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Hi, > On Sun, May 07, 2000 at 03:04:50PM -0600, Steve Passe wrote: > > from the " One including the ata driver in the kernel and with the > > Highpoint IDE controller enabled": > > > > > May 6 22:39:40 relativity /kernel: unknown0: at port 0x168-0x16f,0x36e-0x36f irq 10 on isa0 > > > > was the UDMA33 controller enabled in the BIOS for this one? > > No it wasn't. What you're seeing is a message for the IDE interface on the > SB16 sound card. Another good experiment would be: both channels UDMA33 disabled in BIOS UDMA66 enabled, hard drive attached sound card driver removed sound card removed -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Mon May 8 12: 8:54 2000 Delivered-To: freebsd-smp@freebsd.org Received: from thehousleys.net (frenchknot.ne.mediaone.net [24.147.224.201]) by hub.freebsd.org (Postfix) with ESMTP id 3C46337B923 for ; Mon, 8 May 2000 12:08:51 -0700 (PDT) (envelope-from jim@thehousleys.net) Received: from thehousleys.net (baby.int.thehousleys.net [192.168.0.24]) by thehousleys.net (8.9.3/8.9.3) with ESMTP id PAA50455; Mon, 8 May 2000 15:08:28 -0400 (EDT) Message-ID: <391710AB.B6C680AC@thehousleys.net> Date: Mon, 08 May 2000 15:08:27 -0400 From: James Housley Organization: The Housleys dot Net X-Mailer: Mozilla 4.72 [en] (X11; U; FreeBSD 3.4-STABLE i386) X-Accept-Language: en MIME-Version: 1.0 To: Matthew Dillon Cc: Terry Lambert , Jeremiah Gowdy , Steve Passe , freebsd-smp@FreeBSD.ORG Subject: Re: hlt instructions and temperature issues References: <200004282108.OAA01313@usr08.primenet.com> <200004282240.PAA14200@apollo.backplane.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Matthew Dillon wrote: > I like the HLT + IPI idea, but none of the patches to date really cover > the bases and switching performance is not going to be as good as when you > don't have the HLT due to the overhead of sending the IPIs and having to > keep track of which cpu's are in a HLT'd state and which are not (so you > don't send IPI's to all cpu's gratuitously). > > This is not a trivial problem because we cannot afford to have N cpu's > all trying to do locked bitset instructions on the same memory location > in order to go idle -- that alone will create big latencies. Just a thought after reading this thread. Might it make sense to implement a simple form of this or a similar scheme for the dual-processor system? There would only be 1 processor accessing the lock-memory location. Dual processor systems are leaving the server only areana and entering user/power-user areana. Then work on a more elegant solution the 4-way and above, I know i skipped the 3-way. Jim -- "...there's no idea that's so good you can't ruin it with a few well-placed idiots." -- Charles Spickman To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed May 10 10:25:15 2000 Delivered-To: freebsd-smp@freebsd.org Received: from lucy.ssg.gunter.af.mil (LUCY.SSG.gunter.af.mil [143.158.254.15]) by hub.freebsd.org (Postfix) with ESMTP id 39E7B37B73D for ; Wed, 10 May 2000 10:25:02 -0700 (PDT) (envelope-from John.Hubbard@Gunter.AF.mil) Received: from mfil.terminal (mfil@localhost) by lucy.ssg.gunter.af.mil with SMTP id MAA06303 for ; Wed, 10 May 2000 12:23:14 -0500 (CDT) From: John.Hubbard@Gunter.AF.mil Received: from fsjubj01.ssg.gunter.af.mil (fsjubj01.gunter.af.mil [143.158.17.101]) by lucy.ssg.gunter.af.mil with ESMTP id MAA06257 for ; Wed, 10 May 2000 12:22:41 -0500 (CDT) Received: by fsjubj01.gunter.af.mil with Internet Mail Service (5.5.2650.21) id ; Wed, 10 May 2000 12:22:30 -0500 Message-ID: To: freebsd-smp@freebsd.org Subject: Compaq ProLiant 6500 (again) Date: Wed, 10 May 2000 12:22:36 -0500 X-MS-TNEF-Correlator: X-Mailer: Internet Mail Service (5.5.2650.21) Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Awhile back I had tried installing 3.4-R onto a ProLiant 6500R (2x Xeon 500Mhz, 256MB of RAM, SmartArray 3200 RAID) and ran into a rather strange problem. This machine has a dual-port EtherExpress (fxp) in it. When I run the machine with a uni-processor kernel, everything works fine. When I run it with a dual processor kernel, the fxp gets detected fine, but I get "device timeout : fxp0" all of the time and the network interface doesn't work. Now I have 4.0-R on the machine, and while the ida support is much better, the problem is the same. The machine runs fine uni-processor but I cannot get the NIC to work with an SMP kernel. What sort of data do I need to get to the developers to help figure out what's going on here? Also, an unrelated issue. When I try to run ps or top I get this: "proc size mismatch (29344 total, 1044 free)" Oh, and I just CVSup'd the source tree this morning, rebuilt and restarted. Help! I need network service, but I also need that second processor. TIA. Thatcher Hubbard begin 600 winmail.dat M>)\^(A\1`0:0"``$```````!``$``0>0!@`(````Y`0```````#H``$(@`<` M&````$E032Y-:6-R;W-O9G0@36%I;"Y.;W1E`#$(`06``P`.````T`<%``H` M#``6`"0``P`O`0$@@`,`#@```-`'!0`*``P`%@`;``,`)@$!"8`!`"$````S M,4,V1$(T,C/Z]O```#``"`""`&``````#`````````1@````!2A0`` M)VH!`!X``8`((`8``````,````````!&`````%2%```!````!````#DN,``+ M``*`""`&``````#`````````1@`````&A0````````,``X`((`8``````,`` M``````!&``````&%````````"P`$@`@@!@``````P````````$8``````X4` M```````+``6`""`&``````#`````````1@`````.A0````````,`!H`((`8` M`````,````````!&`````!"%`````````P`'@`@@!@``````P````````$8` M````$84````````#``B`""`&``````#`````````1@`````8A0```````!X` M"8`((`8``````,````````!&`````#:%```!`````0`````````>``J`""`& M``````#`````````1@`````WA0```0````$`````````'@`+@`@@!@`````` MP````````$8`````.(4```$````!``````````(!"1`!````J@,``*8#``!6 M!0``3%I&==6+4HP#``H`(R`T-T97@%00$#`??_"H`"I`/D!Q," M@`_S`%`$5C\(50>R$24.40,!`@!C:.$*P'-E=#(&``;#$27V,P1&$[V.Q@?#C`U$2(,8&,`4+,+"0%D,S864`NF(!S@B$%W:`,092!B`-`0 M:R!)(!/@9"!TEPB!'A`+@',!D&QL"X``9R`S+C0M4B!!`B%O(&$@4`-@3(,' M,`(P(#8U,#`?@$`H,G@@6&4"("!!(+%-:'HL(`XP-I1-0A^09@?P04TA\(Y3 M`,``(`<00!"`H9BD`)##K"X`>@'0FH5:LE8!\"=P6P:P0@9B=A_RHL M*@`KMB@")B(LK2L"*8&Z("8`=`0@`0`.L&,.L.<>$"ZB(?!B=05`'=`R4;0@ M(@$`=@W@'6!T!W'+"&`%0#HR`C`B'^`>X+\B8BL"-+(D0RL")W!T+D*;),($ MD&8`T!U@9&\'D.QN)R_1+E$N"J(*@!S@'$YO!^`=TBV@(#0N?C`?(!_0-V,KQ`.@^%--4"T%*B,E4"6@ M*&+_(G$\H`&0.$$=P2=P'F$?P9]#`Q_0*P(T02U0;W`$D+<_(1_0)7!L,C`N MH&<(<"\=8#3R'2`E4"<$(&=O)Q\"(6$E<64_.29!;/\LT#N2+"$8(`M@,O($ M`0I0WRHH'C`C@!_!*L)P!"`%L<\?P#(P,]0MX7,Z.20Y).8B,+(EH&EZ*R$$ M``#`AG0]H2$`.3,T-$.Q ML!(@5E,\X"`'```0```!T` M``!#;VUP87$@4')O3&EA;G0@-C4P,"`H86=A:6XI``````L``@`!`````P#] M/^0$``!``#D`0,?#5:2ZOP$#`/$_"00``!X`,4`!````"0```$A50D)!4D1* M``````,`&D``````'@`P0`$````)````2%5"0D%21$H``````P`90``````# M`"8```````,`-@```````P"`$/____\"`4<``0```"H```!C/553.V$]1$U3 M.VP]1E-*54)*,# M`/@_`0```",```!(=6)B87)D("!*;VAN("!4("`@03%#("!(42!34T`#A``0````D```!(54)"05)$2@`````"`?L_`0```%8`````````W*=` MR,!"$!JTN0@`*R_A@@$`````````+T\]3U)'04Y)6D%424].+T]5/4=53E1% M4BU!3DY%6"]#3CU214-)4$E%3E13+T-./4A50D)!4D1*````'@#Z/P$````C M````2'5B8F%R9"`@2F]H;B`@5"`@($$Q0R`@2%$@4U-'+U!)30``'@`Y0`$` M```)````2%5"0D%21$H`````0``',&YXP56DNK\!0``(,`(+C%"DNK\!'@`] M``$````!`````````!X`'0X!````'0```$-O;7!A<2!0``@0`0```&4```!!5TA)3$5"04-+24A!1%12245$24Y35$%,3$E. M1S,T+5)/3E1/05!23TQ)04Y4-C4P,%(H,EA814].-3`P34A:+#(U-DU"3T92 M04TL4TU!4E1!4E)!63,R,#!204E$*4%.1%)!``````(!?P`!````1````#Q! M04(T-T4X-D,W,C%$-#$Q0CDV0C`P.3`R-T(Q,44T1C0P0S0Q0D!F; Wed, 10 May 2000 11:32:55 -0700 (PDT) (envelope-from marketing@infotechsys.net) Received: from infotechsys.net (2K-SERVER [192.168.0.100]) by mail.sullivan-reportlibrary.com with SMTP (Microsoft Exchange Internet Mail Service Version 5.5.2650.21) id KTQY5PLP; Wed, 10 May 2000 14:29:34 -0400 MIME-Version: 1.0 From: marketing@infotechsys.net Reply-To: marketing@infotechsys.net To: smp@freebsd.org Subject: ITS Brochure Mime-Version: 1.0 Content-Type: text/html; charset="us-ascii" Message-Id: <20000510183255.EF83A37B927@hub.freebsd.org> Date: Wed, 10 May 2000 11:32:55 -0700 (PDT) Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org ITS Internet Site

P.O. Box 70671

Charleston, SC 29415-0671

843.566.1397


To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Wed May 10 13: 5:51 2000 Delivered-To: freebsd-smp@freebsd.org Received: from lucy.ssg.gunter.af.mil (LUCY.SSG.gunter.af.mil [143.158.254.15]) by hub.freebsd.org (Postfix) with ESMTP id 18E5137B787 for ; Wed, 10 May 2000 13:05:38 -0700 (PDT) (envelope-from John.Hubbard@Gunter.AF.mil) Received: from mfil.terminal (mfil@localhost) by lucy.ssg.gunter.af.mil with SMTP id OAA21771 for ; Wed, 10 May 2000 14:57:39 -0500 (CDT) From: John.Hubbard@Gunter.AF.mil Received: from fsjubj01.ssg.gunter.af.mil (fsjubj01.gunter.af.mil [143.158.17.101]) by lucy.ssg.gunter.af.mil with ESMTP id OAA21537 for ; Wed, 10 May 2000 14:56:01 -0500 (CDT) Received: by fsjubj01.gunter.af.mil with Internet Mail Service (5.5.2650.21) id ; Wed, 10 May 2000 14:55:50 -0500 Message-ID: To: bart@ixori.demon.nl, freebsd-smp@freebsd.org Subject: RE: Compaq ProLiant 6500 (again) Date: Wed, 10 May 2000 14:55:56 -0500 X-MS-TNEF-Correlator: X-Mailer: Internet Mail Service (5.5.2650.21) Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Cheers on the second suggestion, upon the completion of a 'make world' top and ps functioned as expected. As for the first problem, I'm considering trying to put a single port NIC in there and see what happens, it might by some difficulty with having two different PCI devices in a single slot. I appears that IRQ's are being mapped correctly, but who knows. For right now, I just have two kernels that I can choose from at boot time depending on what I'm intending to do (I ran it for an hour in MP to do a 'make world', went back to UP). Is there anyone out there who can take a look at my dmesg output and maybe tell me what's going wrong here? -----Original Message----- From: Bart van Leeuwen [mailto:bart@ixori.demon.nl] Sent: Wednesday, May 10, 2000 1:50 PM To: John.Hubbard@gunter.af.mil Subject: Re: Compaq ProLiant 6500 (again) Not knowing how experienced you are with rebuilding/reinstalling/upgrading from source.. Just 2 quick suggestions: - The fxp problem sounds like some IRQ related issue. Note that IRQ handling with SMP is somewhat different from UP. I have never tested this driver but I can imagine that the problem somehow has to do with IRQ settings and IRQ delivery to the driver. - The proc size mismatch sounds to me like your kernel and userland are not built from exactly the same sources, ie, the kernel is built from sources of a later date then the userland (for example because you did a cvsup before rebuilding the kernel) If this is the case, or if you are not entirely sure, I suggest you build a new 'world' in /usr/src and a new kernel (based on your current config file, however, it is a good idea to do a config -r before rebuilding the kernel. Also read the /usr/src/UPDATING file for details on upgrading/rebuilding/reinstalling from source. Bart van Leeuwen ----------------------------------------------------------- mailto:bart@ixori.demon.nl - http://www.ixori.demon.nl/ ----------------------------------------------------------- On Wed, 10 May 2000 John.Hubbard@Gunter.AF.mil wrote: > Awhile back I had tried installing 3.4-R onto a ProLiant 6500R (2x Xeon > 500Mhz, 256MB of RAM, SmartArray 3200 RAID) and ran into a rather strange > problem. This machine has a dual-port EtherExpress (fxp) in it. When I run > the machine with a uni-processor kernel, everything works fine. When I run > it with a dual processor kernel, the fxp gets detected fine, but I get > "device timeout : fxp0" all of the time and the network interface doesn't > work. > Now I have 4.0-R on the machine, and while the ida support is much better, > the problem is the same. The machine runs fine uni-processor but I cannot > get the NIC to work with an SMP kernel. What sort of data do I need to get > to the developers to help figure out what's going on here? > Also, an unrelated issue. When I try to run ps or top I get this: > > "proc size mismatch (29344 total, 1044 free)" > > Oh, and I just CVSup'd the source tree this morning, rebuilt and > restarted. Help! I need network service, but I also need that second > processor. TIA. > > Thatcher Hubbard > > begin 600 winmail.dat > M>)\^(A\1`0:0"``$```````!``$``0>0!@`(````Y`0```````#H``$(@`<` > M&````$E032Y-:6-R;W-O9G0@36%I;"Y.;W1E`#$(`06``P`.````T`<%``H` > M#``6`"0``P`O`0$@@`,`#@```-`'!0`*``P`%@`;``,`)@$!"8`!`"$````S > M,4,V1$(T,C M;7!A<2!0 M!@!@"0``,`````,`"5D!`````@%Q``$````6`````;^ZI%:7 MW@#`3QES00```P#>/Z]O```#``"`""`&``````#`````````1@````!2A0`` > M)VH!`!X``8`((`8``````,````````!&`````%2%```!````!````#DN,``+ > M``*`""`&``````#`````````1@`````&A0````````,``X`((`8``````,`` > M``````!&``````&%````````"P`$@`@@!@``````P````````$8``````X4` > M```````+``6`""`&``````#`````````1@`````.A0````````,`!H`((`8` > M`````,````````!&`````!"%`````````P`'@`@@!@``````P````````$8` > M````$84````````#``B`""`&``````#`````````1@`````8A0```````!X` > M"8`((`8``````,````````!&`````#:%```!`````0`````````>``J`""`& > M``````#`````````1@`````WA0```0````$`````````'@`+@`@@!@`````` > MP````````$8`````.(4```$````!``````````(!"1`!````J@,``*8#``!6 > M!0``3%I&==6+4HP#``H`(R`T-T97@%00$#`??_"H`"I`/D!Q," > M@`_S`%`$5C\(50>R$24.40,!`@!C:.$*P'-E=#(&``;#$27V,P1&$[ M,PCO"?>V.Q@?#C`U$2(,8&,`4+,+"0%D,S864`NF(!S@B$%W:`,092!B`-`0 > M:R!)(!/@9"!TEPB!'A`+@',!D&QL"X``9R`S+C0M4B!!`B%O(&$@4`-@3(,' > M,`(P(#8U,#`?@$`H,G@@6&4"("!!(+%-:'HL(`XP-I1-0A^09@?P04TA\(Y3 > M`,``(`<0 MD6<=8'`#8`)@Z&5M+AS@5!TP!"``P3T=,&X=8!/@!"`?\&1U20=`+7`7P2!% > M)6)%SG@F,`>0!"`H9BD`)##K"X`>@'0FH5 M'^%M*M!I*$`#8&,I,06Q:TD$D65L(?!E=@20>:LE8!\"=P6P:P0@9B=A_RHL > M*@`KMB@")B(LK2L"*8&Z("8`=`0@`0`.L&,.L.<>$"ZB(?!B=05`'=`R4;0@ > M(@$`=@W@'6!T!W'+"&`%0#HR`C`B'^`>X+\B8BL"-+(D0RL")W!T+D*;),($ > MD&8`T!U@9&\'D.QN)R_1+E$N"J(*@!S@'$YO!^`=TBV@(#0N?C`? M4ATD*P)IXF0?\'-U<"A3)O(:T/TK\&(4(#?1,;0F-3U"*P+\ MP2Z$+"WE,Y1C`'!N;P5`,_(K`OA.24,>(!_0-V,KQ`.@^%--4"T%*B,E4"6@ > M*&+_(G$\H`&0.$$=P2=P'F$?P9]#`Q_0*P(T02U0;W`$D+<_(1_0)7!L,C`N > MH&<(<"\=8#3R'2`E4"<$(&=O)Q\"(6$E<64_.29!;/\LT#N2+"$8(`M@,O($ > M`0I0WRHH'C`C@!_!*L)P!"`%L<\?P#(P,]0MX7,Z.20Y).8B,+(EH&EZ*R$$ > M``#`AG0]H2$`.3,T-$.Q > ML!(@5E,\X" M`9``(`F`)J%(22$A'.#W1N4W-A00 M_SD54`4!D0,P7L]?VB;04;)Q$H%(=6(=@`LB.4)]`6)0```>`'```0```!T` > M``!#;VUP87$@4')O3&EA;G0@-C4P,"`H86=A:6XI``````L``@`!`````P#] > M/^0$``!``#D`0,?#5:2ZOP$#`/$_"00``!X`,4`!````"0```$A50D)!4D1* > M``````,`&D``````'@`P0`$````)````2%5"0D%21$H``````P`90``````# > M`"8```````,`-@```````P"`$/____\"`4<``0```"H```!C/553.V$]1$U3 > M.VP]1E-*54)*,# M``````# M3U4]1U5.5$52+4%.3D58+T-./5)%0TE0245.5%,O0TX]2%5"0D%21$H````> > M`/@_`0```",```!(=6)B87)D("!*;VAN("!4("`@03%#("!(42!34T M```>`#A``0````D```!(54)"05)$2@`````"`?L_`0```%8`````````W*=` > MR,!"$!JTN0@`*R_A@@$`````````+T\]3U)'04Y)6D%424].+T]5/4=53E1% > M4BU!3DY%6"]#3CU214-)4$E%3E13+T-./4A50D)!4D1*````'@#Z/P$````C > M````2'5B8F%R9"`@2F]H;B`@5"`@($$Q0R`@2%$@4U-'+U!)30``'@`Y0`$` > M```)````2%5"0D%21$H`````0``',&YXP56DNK\!0``(,`(+C%"DNK\!'@`] > M``$````!`````````!X`'0X!````'0```$-O;7!A<2!0 M("AA9V%I;BD`````'@`U$`$```!$````/$%!0C0W13@V0S M,#`Y,#(W0C$Q131&-#!#-#%"0&9S:G5B:C`W+G-S9RYG=6YT97(N868N;6EL > M/@`+`"D```````L`(P```````P`&$-S([;H#``<0)P,```,`$!```````P`1 > M$``````>``@0`0```&4```!!5TA)3$5"04-+24A!1%12245$24Y35$%,3$E. > M1S,T+5)/3E1/05!23TQ)04Y4-C4P,%(H,EA814].-3`P34A:+#(U-DU"3T92 > M04TL4TU!4E1!4E)!63,R,#!204E$*4%.1%)!``````(!?P`!````1````#Q! > M04(T-T4X-D,W,C%$-#$Q0CDV0C`P.3`R-T(Q,44T1C0P0S0Q0D!F 7-RYS ` > end > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-smp" in the body of the message > begin 600 winmail.dat M>)\^(C,3`0:0"``$```````!``$``0>0!@`(````Y`0```````#H``$(@`<` M&````$E032Y-:6-R;W-O9G0@36%I;"Y.;W1E`#$(`06``P`.````T`<%``H` M#@`W`#@``P!F`0$@@`,`#@```-`'!0`*``X`-P`P``,`7@$!"8`!`"$````Y M,#8R-#9!1$$Q,C9$-#$Q0CDV0C`P.3`R-T(Q,44T1@#\!@$$@`$`(0```%)% M.B!#;VUP87$@4')O3&EA;G0@-C4P,"`H86=A:6XI`/<)`0V`!``"`````@`" M``$#D`8`'!L``#(````#``"`""`&``````#`````````1@````!2A0``)VH! M`!X``8`((`8``````,````````!&`````%2%```!````!````#DN,``+``*` M""`&``````#`````````1@`````&A0````````,``X`((`8``````,`````` M``!&``````&%````````"P`$@`@@!@``````P````````$8``````X4````` M```+``6`""`&``````#`````````1@`````.A0````````,`!H`((`8````` M`,````````!&`````!"%`````````P`'@`@@!@``````P````````$8````` M$84````````#``B`""`&``````#`````````1@`````8A0```````!X`"8`( M(`8``````,````````!&`````#:%```!`````0`````````>``J`""`&```` M``#`````````1@`````WA0```0````$`````````'@`+@`@@!@``````P``` M`````$8`````.(4```$````!``````````(!"1`!````!14```$5```P'P`` M3%I&=>).N*P#``H`(R`T-T97@%00$#`??_"H`"I`/D!Q,"@`_S M`%`$5C\(50>R$24.40,!`@!C:.$*P'-E=#(&``;#$27V,P1&$[V.Q@?#C`U$2(,8&,`4+,+"0%D,S864`NF(!S@+$-H">`4`"`"("!T31T@ M(!00!:!N9!W@=21G9P>0=&D"("P@['5P'84%H&T+4!0@'M%!'7!F(&$@)P#` M:T4=T'<%L&QD)QV@;Q9P((`>,7`$(&9U;KYC'L()@""`!"`.P'`%D'D.L&0N M'.`*H@J`'.!!9R(1!;$=LF9I%``%0'#3`V`"8&5M'P!)(+`?H9<`@02!"X!G M':!R>2:C^F\A\'4%0""0`)`FL!_PQR'P%\$'L$E#(`N`':)_&"`ALQ00(/$3 MX`5`$^!P%R,P`(`?`&D%0&UI9W)H!4!B>1W@`W`=T&3#!I`D\&-U;'0K<`/P M^QVP*C%V)J,A$"O3*3$",%`@4$-)*]!E+0!CUP>1*.$GQW,7L'0CD2Y0#RI2 M$_$=H2H125)1)^<$(`K`'=!B92:B`,`J84\>0`6A&"`B8&QY'P!B!R>1*?`G M8&MN;W=S?2.11@6Q!1`K(C/!)<$@_&IU)2$LX1W0+5(@X`2@/&5L,*8?H`.1 M$]!O;_\4$"(@`V$@@"M!-W`%0![`_2NR92IQ*^`FL1V!*?,EXJ\+@`ZP.20G M460G8"@N4/YR`Y$JT21R`Y$S@`AP*-)<35`ZU2"<'P!W+?)BQ0#0:R="55`I M+_(PHOTI-'DBD1UP)Y$I%#-R-Q)O`9`@X2"0%[!O/N`J$6W]*W!D!X$Y82>0 M)X,>,0#`_GDQL!V@-F`#("NQ*?(Q071G;R:B=P-@)K$I(C_K(\0CQ"U'`D\T M<0N`!T!S!=`'D'-A'I!'`R/$1K$#83H@0@K`!4!V`Y'*3`G@=3YA(%L`P`,0 MC2&`.CZP`"!`:7@%L`QI+@$`!&!N+FYLWETCQ`9@`C!)0%<)@"*@+'-D0_`? M`$U#\"`QGC`?``'03C!-T#HU%E`44$TCQ%1*T"!*;R)H2^!(=6)*\61`!FL`=`;%@R'R`)P&$_.3(CQ#?#*Y`(<"ZP+B[M1DI*-5(4 M0'%7\#[1'FCD,%CR+(13/-'_!``K@RGS+9@WPS\P(Y`N4/\U MDR*@-;`DD1ZA(K$=L`0`_2/$9`409D(S,C;T!W!((/\+@&&E';)>N`>`5?(3 MX#"A_SKS+)-B%Q01'L`FL#%1'C'_8$(!`%CP9D$K<"=1';)GE-=:^UX4)5%C M)]%Z'=`K`/IS`,!T$]!?)B=1*[%?H_]6\07`-B0ALS50!)`+8!XQ_S%Q(\0S MP"M!5_%E!0[``-"[,N$=I&$KL5J$*J)E'P#_';)R=6/!=(AKU794(%1@HK\% MP$U089-*01VRH([42)`J28=LK2V+)/[()`B0&FUT&_A1_$%L38DNQ\`9C)Y9O%%8@6P M:R(1_VCAM[^I8BK1N<6UDF_#NKSW)+->@1Z0=`0@DO$C0[R3[S,4+E#`P:DF M(BYT.(-`DO-)0%YQ,"(@@$1A(&$=LG\XDR'"';(BH"U1O&`Z,W*69@#0*\%O M!Y!N)\*'/[Q"6O6I@E4P!^!EM30N_C"L([CZ'P`APJG4';(F8/\GP1\@*%.T M@AK0+,`QL`)`_XKAN(I>MH#E=?*T,[DHN%'_O(2Z+6@'=$&I)L#!':,HHO\G M4<9#N<0#H&."C^:]`2H1_[K1!4`@87HAM7$G8"Y0(J#_9L(G8,)I;=9F,1>P M5E%JT_T=(&PAH(FA@W%`@T3+'8'_1?FI@Y!QRP*Z(6"-O08FX?\G0KA1(?(D M@B&1PD-FXUU%'XX0PI=OWRS`K;`Y,S1^-"%Q6,&ETN-A`U`)X"EF(N#N'.!/ M:,L$-25#\E91@'`GD.1:A";1*<'_@),$8`2@)J$?`)240X.I)J^VL0&0`"`C M!4T!.056AG1)+D!,J$*DF33Y4`%Q>*$)!]V`Q M8#`ZQ&!@+&`D^##X8R'X,S`^H#`A0&`H^&)9]^`I^&4C2/@Q*/EP/&!%]KP-0U* M`%`"\/YA,U0]+#PF6%:@2;%7\=P07"8,,56PT%,@*S=@-PI0"/`E%0@V*253 MG4[`1@$@^4'X($@Y"K%0*2,C2TLA/DJ@,*!&2#4\1?L`+DJ@8T,`]V`\1S3Z M@`WP0=@I43Q=<0WP0/:W4]#()4TJ#.!)*OA0"R`%1F!)2#`V43I41,HD5G`U M3^`_(4+P4X`Q^3`Z3$58L%YA/5`8-E`Z4.!)T$(]09Q?4D_0]K=3<&!+KV"! M#2`I0BA,2S)+$/D[8"9:"B`#$%,@_1#Y\0PN3$9@99`N/#XDG"):9#!A$&*@ M,#4!H/%3(%(T._T0]K?ZT/A0$V%`$4`G-DH`(5@F`Q!HH%5) MT#,@"%PG1$603BE27P`Q*T4D3B)**(-3<$>A)R193R%IP"`]5$)60$WP,$Y" M/P7@/SQ22V30/PU5R322`&M04"E)6$Q&,%DA0M!5/`HP,\8I3%!@@"]42UDQ M.2`Q3?`_,2QG,#VP,U5%4V!0:@$\5B0I`")`.D,J4D!*-X@R!%HD1L!712Q9 M,2,%X`&P3CM09L`L7UHH5;!/\!!!T"P^,"'V7\G@0[!+#J!=,%]0G%"!3Q!4 M)2I"+$5/$*(V7J@J)BMV@$=KL+I<^I`F##`',&(0,F(02"=&)%#0.5T``%&' M=U!"L`2P,#)5,/RP4?A`1"L\=H`Q=U`I'0BP3`301V#VMT@F/`XH<<#W8%:@ M(S-2)[0R8'BA//K`/-!/7B"I7F$H-OP`/$=`7W;@"#DA.Z"07$Q4([Q.,D;` M(4#YD$"@+$Q0(VNX]^!),%=BX$@G!07@0PT`7R$J3"EQ5^(E3#SW8%#00Q!0 MA"Q=KM!8-RQ:=N`P,%DI+FI`1K`H17E]X$5:=&`',!E9``!!L?T`74@R^%`& M$"P^<.(D19`\45M/8&_P!H`4)2GXT%4"L%@B1:-'@/W@*B[D->((/!`1%? M?X%40&_P/8%`(\G0>U!I$3J0,R%<62(("$M0"V)&`K!*UB6ML(=008F`(_W` MB>"G_,`4P`D00S%X@%=5((?$8!&P1*`!V:"Q"B.XO04#@W3($G<@`2,X7`03O]`2U#--^$8%NA M1S!BL`E@6#^@^&.OC3`.<#&5$A!=]K84:` M^P#Y\S]A^+&P0R\U-:OP<_!=!)`655%XJ'!0J*!%+2KIE!`I*DXP/*_@``!0 M('0S)(1@,V^@!-`$<#;(0E11!A!`4U!@.C1Z7E%P7`XC7I`=CZI02>>`T$W0 M^L`P)F1@CM#X,'!+*UXF^"`R")D@4S>+X*``BA`SDR#X`#4Q6BE80%@("'-@ M-*B@59@U+C5!(($`-"4&$&F4`#@K/G`NJ#!:\#!K2A![T#2RD26!D+/P6,Y= MHMV*>#^P0%^G=`URST]@//!D()BP*41/,6M@N%9!3D\QK,`+P`N!*5$YE07ET8%]!`/`UZ+-P]V!=U7-@*0>0-(4@ M-A`0N8"ELE`NLW!=-;"0/:A0+$4Q6CA+X%6PT5DE)#8B>S`S0UEP,334+2FZ M`27"L3.S$"4!P$NP_<"KT+T%P%.K(4(`!0`\H"(&$)=)X`/(``!9 M3C`H5P60_P5PCJ!#X`50"Q`%4,]`KM`Y/>`Z1\@P=$`U("M'I"U32V!91SSP M63Z1E"A.1S`X=B`V16,(_TG`(N'/4/AEC3!-T"AW0_#AVY`H6SM(``%2<(.` M_PUR`2`"X"AW1'CX53*AN/#G^?-/`/BB(351$+%002!+`%#$D"M!T$$APM`Q M?Y!0M$!!P5%@LK"T@*K015'P)TTQ4X>@*[/`+]W"L2]FL!2@6$!1EH#!@-_$ MD)G"D#!.H)E0.,2`PA"W">*YL)I@*T,0RF!$0JS#:0%F`_^KP0J"S`<+0B*$Z)5#0[]]#Z4E&32)40!+`& M4#3^6.E@D9`$T,H@!5\&9DNP+U#@$;#O\`L`1G/@2557R%`],#O6-_R06=>P M5F`\3CE7-0F05T!2JBM2H$;T$%7]8",5\(^4X%,0.];[%V5N9#O6`?9>5&\@ M56YS=0!BIH[JR`.)I\1 MU)CF`)`GRQ/;``(UIP```P`N```````+``(``0````,`"5D!````'@!"$`$` M``!!````/%!I;F4N0E-&+C0N,C$N,#`P-3$P,C`T,3,S,"XS-S@M,3`P,#`P M0&ES96YG87)D+FEX;W)I+F1E;6]N+FYL/@`````#`-X_KV\``$``.0"PEYW! MN;J_`0,`\3\)!```'@`Q0`$````)````2%5"0D%21$H``````P`:0``````> M`#!``0````D```!(54)"05)$2@`````#`!E```````,`_3_D!````P`F```` M```#`#8```````,`@!#_____`@%'``$````J````8SU54SMA/41-4SML/493 M2E5"2C`W+3`P,#4Q,#$Y-34U-EHM,C$P.3,````"`?D_`0```%8````````` MW*=`R,!"$!JTN0@`*R_A@@$`````````+T\]3U)'04Y)6D%424].+T]5/4=5 M3E1%4BU!3DY%6"]#3CU214-)4$E%3E13+T-./4A50D)!4D1*````'@#X/P$` M```C````2'5B8F%R9"`@2F]H;B`@5"`@($$Q0R`@2%$@4U-'+U!)30``'@`X M0`$````)````2%5"0D%21$H``````@'[/P$```!6`````````-RG0,C`0A`: MM+D(`"LOX8(!`````````"]//4]21T%.25I!5$E/3B]/53U'54Y415(M04Y. M15@O0TX]4D5#25!)14Y44R]#3CU(54)"05)$2@```!X`^C\!````(P```$AU M8F)A`#40`0```$0````\04%"-#=%.#9#-S(Q1#0Q,4(Y-D(P M,#DP,C=",3%%-$8T,$,T,4-`9G-J=6)J,#; Wed, 10 May 2000 18:15:48 -0700 (PDT) (envelope-from msmith@mass.cdrom.com) Received: from mass.cdrom.com (localhost [127.0.0.1]) by mass.cdrom.com (8.9.3/8.9.3) with ESMTP id SAA01727; Wed, 10 May 2000 18:15:57 -0700 (PDT) (envelope-from msmith@mass.cdrom.com) Message-Id: <200005110115.SAA01727@mass.cdrom.com> X-Mailer: exmh version 2.1.1 10/15/1999 To: Drew Eckhardt Cc: freebsd-smp@freebsd.org Subject: Re: T_RESERVED prevention kludge In-reply-to: Your message of "Fri, 05 May 2000 14:07:33 MDT." <200005052007.OAA28764@chopper.Poohsticks.ORG> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Wed, 10 May 2000 18:15:57 -0700 From: Mike Smith Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org I've committed this to -current, and will do so to -stable in a day or so. I'm also now happily trolling along here with this patch on a Dell PowerEdge 2450 loaned to us by Dell; if someone wants to play detective and needs access to the box, let me know - they don't want it back for another couple of weeks yet. > The following is against 4.0 stable, and includes Tor.Egge@fast.no's > mask unused APIC pins patch. > > Before, half the time I couldn't build a kernel before I paniced. Now, > I can survive five make buildworld -j 5s. > > Index: mpapic.c > =================================================================== > RCS file: /usr/local/cvs/src/sys/i386/i386/mpapic.c,v > retrieving revision 1.37 > diff -u -r1.37 mpapic.c > --- mpapic.c 1999/12/15 19:17:08 1.37 > +++ mpapic.c 2000/05/05 19:08:45 > @@ -168,6 +168,27 @@ > for (pin = 0; pin < maxpin; ++pin) { > int bus, bustype, irq; > > + select = pin * 2 + IOAPIC_REDTBL0; /* register */ > + /* > + * Always disable interrupts, and by default map > + * pin X to IRQX because the disable doesn't stick > + * and the uninitialize vector will get translated > + * into a panic. > + * > + * This is correct for IRQs 1 and 3-15. In the other cases, > + * any robust driver will handle the spurious interrupt, and > + * the effective NOP beats a panic. > + * > + * A dedicated "bogus interrupt" entry in the IDT would > + * be a nicer hack, although some one should find out > + * why some systems are generating interrupts when they > + * shouldn't and stop the carnage. > + */ > + vector = NRSVIDT + pin; /* IDT vec */ > + io_apic_write(apic, select, > + (io_apic_read(apic, select) & ~IOART_INTMASK > + & ~0xff)|IOART_INTMSET|vector); > + > /* we only deal with vectored INTs here */ > if (apic_int_type(apic, pin) != 0) > continue; > @@ -209,7 +230,6 @@ > if (apic != 0 || pin != irq) > printf("IOAPIC #%d intpin %d -> irq %d\n", > apic, pin, irq); > - select = pin * 2 + IOAPIC_REDTBL0; /* register */ > vector = NRSVIDT + irq; /* IDT vec */ > io_apic_write(apic, select, flags | vector); > io_apic_write(apic, select + 1, target); > > -- > Home Page > For those who do, no explanation is necessary. > For those who don't, no explanation is possible. > > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-smp" in the body of the message > -- \\ Give a man a fish, and you feed him for a day. \\ Mike Smith \\ Tell him he should learn how to fish himself, \\ msmith@freebsd.org \\ and he'll hate you for a lifetime. \\ msmith@cdrom.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message From owner-freebsd-smp Thu May 11 7:52:13 2000 Delivered-To: freebsd-smp@freebsd.org Received: from lucy.ssg.gunter.af.mil (LUCY.SSG.gunter.af.mil [143.158.254.15]) by hub.freebsd.org (Postfix) with ESMTP id 37A4B37B8BD for ; Thu, 11 May 2000 07:52:03 -0700 (PDT) (envelope-from John.Hubbard@Gunter.AF.mil) Received: from mfil.terminal (mfil@localhost) by lucy.ssg.gunter.af.mil with SMTP id JAA11151 for ; Thu, 11 May 2000 09:45:50 -0500 (CDT) From: John.Hubbard@Gunter.AF.mil Received: from fsjubj01.ssg.gunter.af.mil (fsjubj01.gunter.af.mil [143.158.17.101]) by lucy.ssg.gunter.af.mil with ESMTP id JAA10982 for ; Thu, 11 May 2000 09:44:43 -0500 (CDT) Received: by fsjubj01.gunter.af.mil with Internet Mail Service (5.5.2650.21) id ; Thu, 11 May 2000 09:44:33 -0500 Message-ID: To: freebsd-smp@freebsd.org Subject: Compaq ProLiant 6500 Date: Thu, 11 May 2000 09:44:41 -0500 X-MS-TNEF-Correlator: X-Mailer: Internet Mail Service (5.5.2650.21) Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org In case this help someone who actually knows a little about the code: In reference to an earlier message, I could not get SMP to work without problems with the NIC (a dual port Intel fxp). On a hunch, I threw a 3Com 3c905c in (single port), reconfigured and recompiled, and it works fine. This leads me to believe that there is a problem (but only with SMP enabled) with having two PCI devices in one slot (is this a PCI-PCI bridge?). begin 600 winmail.dat M>)\^(B(.`0:0"``$```````!``$``0>0!@`(````Y`0```````#H``$(@`<` M&````$E032Y-:6-R;W-O9G0@36%I;"Y.;W1E`#$(`06``P`.````T`<%``L` M"0`L`"D`!`!)`0$@@`,`#@```-`'!0`+``D`+``?``0`/P$!"8`!`"$```!$ M-$4S04,Q,3,X,C=$-#$Q0CDV0C`P.3`R-T(Q,44T1@`,!P$$@`$`%0```$-O M;7!A<2!0``&` M""`&``````#`````````1@````!4A0```0````0````Y+C``"P`"@`@@!@`` M````P````````$8`````!H4````````#``.`""`&``````#`````````1@`` M```!A0````````L`!(`((`8``````,````````!&``````.%````````"P`% M@`@@!@``````P````````$8`````#H4````````#``:`""`&``````#````` M````1@`````0A0````````,`!X`((`8``````,````````!&`````!&%```` M`````P`(@`@@!@``````P````````$8`````&(4````````>``F`""`&```` M``#`````````1@`````VA0```0````$`````````'@`*@`@@!@``````P``` M`````$8`````-X4```$````!`````````!X`"X`((`8``````,````````!& M`````#B%```!`````0`````````"`0D0`0```!4"```1`@``R`(``$Q:1G4N MHIGY`P`*`')C<&L0.@90\*P!_@$H$'@7-A M9V6&+!S@(.%U;&0@'W!'!4`D(`5`4TU0(N)WO06P:QZ`'_`>H""!<`-@.0)@ M96T$("8B(*-.2>A#("@?P&0?`2:0%\$''.$.L`,@9GAP*2Y-(@!/`Z`?P&AU M(K!H7R1"'7`8(`?@'\`S"%!M@2KP8SDP-6,@"X"S)_``D&YG("$H@BDD0,,8 M(`6@;F9I9PAP"8#G(Q$DP"SB;7`#$`F`)$!_+;(?\"7#!"`M,!Y@*7%44G,7L`5`7B@= MD1US'\`UP2TUPF*U!1!D)"`_*6`A1'TY<````!X`<``!````%0```$-O;7!A M<2!0[ MOP$#`/$_"00``!X`,4`!````"0```$A50D)!4D1*``````,`&D``````'@`P M0`$````)````2%5"0D%21$H``````P`90``````#`"8```````,`-@`````` M`P"`$/____\"`4<``0```"H```!C/553.V$]1$U3.VP]1E-*54)*,#`/@_`0```",```!(=6)B M87)D("!*;VAN("!4("`@03%#("!(42!34T`#A``0````D```!( M54)"05)$2@`````"`?L_`0```%8`````````W*=`R,!"$!JTN0@`*R_A@@$` M````````+T\]3U)'04Y)6D%424].+T]5/4=53E1%4BU!3DY%6"]#3CU214-) M4$E%3E13+T-./4A50D)!4D1*````'@#Z/P$````C````2'5B8F%R9"`@2F]H M;B`@5"`@($$Q0R`@2%$@4U-'+U!)30``'@`Y0`$````)````2%5"0D%21$H` M````0``',));1G!7N[\!0``(,-[SE&I7N[\!'@`]``$````!`````````!X` M'0X!````%0```$-O;7!A<2!0