Date: Tue, 2 Jul 2002 14:45:01 +0200 From: Erik Trulsson <ertr1013@student.uu.se> To: Paulo Roberto <nirv199@yahoo.com> Cc: Aaron Burke <aburke@nullplusone.com>, FreeBSD-Questions <freebsd-questions@freebsd.org> Subject: Re: kernel - pentium FDIV bug corrected? Message-ID: <20020702124501.GA35222@falcon.midgard.homeip.net> In-Reply-To: <20020702123343.23356.qmail@web14911.mail.yahoo.com> References: <20020702061857.GA29547@falcon.midgard.homeip.net> <20020702123343.23356.qmail@web14911.mail.yahoo.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, Jul 02, 2002 at 05:33:43AM -0700, Paulo Roberto wrote: > --- Erik Trulsson <ertr1013@student.uu.se> wrote: > > On Mon, Jul 01, 2002 at 10:52:53PM -0700, Aaron Burke wrote: > > > There is a kernel config option that takes care of it. Also, the > > > problem affected more than just the pentium. > > > > > > But check out /sys/i386/conf/LINT for the "NO_F00F_HACK" option. > > > > The F00F bug is not the same as the FDIV bug. Also the FDIV bug > > affected only the earliest Pentiums (I think it was only the 60 and > > 66 > > MHz versions) while the F00F bug affected all Pentiums and > > Pentium/MMX. > > Wow. So there is one more bug I was not aware of? Is it also related to > math operations? Not math related. It is a certain instruction (whose opcode starts with f00f, hence the name) that can lock up the machine if it is executed. This instruction should never be generated by any compiler so if you ever encounter it, it is due to a buggy or malicious program. > > I got a few boxes and I am planning in compiling one kernel for all of > them (same sort of hardware). Can I enable this "NO_FOOF_HACK" and use > this kernel with a machine that has a cpu that possibly do not have > this bug? The "NO_F00F_HACK" (zeroes, not "o"'s) option actually disables the workaround which is turned on by default. It is recommended but not necessary that this option be used to *turn off* the workaround on machines that do *not* suffer from this bug. (AFAIK it is Pentiums and only Pentiums that have the bug.) > > > One possible workaround could be to use the emulator instead of the > > hardware FPU. Check the [GPL_]MATH_EMULATE option and the npx device > > in LINT. Note that this will cause all floating point operations to > > go > > slower so it might not be an acceptable solution. > > I will try that. > > > If you really have a machine with the FDIV bug, I would actually > > suggest you replace the machine, or at least the CPU. It can't be > > that > > expensive. > > The problem is that it would have to change the cpu in seven machines, > and probably the motherboards as well. That might be a bit more trouble and money than it is worth, yes. -- <Insert your favourite quote here.> Erik Trulsson ertr1013@student.uu.se To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20020702124501.GA35222>