From owner-freebsd-current  Fri Apr 19 12:30:53 1996
Return-Path: owner-current
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.3/8.7.3) id MAA26518
          for current-outgoing; Fri, 19 Apr 1996 12:30:53 -0700 (PDT)
Received: from phaeton.artisoft.com (phaeton.Artisoft.COM [198.17.250.211])
          by freefall.freebsd.org (8.7.3/8.7.3) with SMTP id MAA26512
          for <freebsd-current@freefall.freebsd.org>; Fri, 19 Apr 1996 12:30:48 -0700 (PDT)
Received: (from terry@localhost) by phaeton.artisoft.com (8.6.11/8.6.9) id MAA08783; Fri, 19 Apr 1996 12:27:10 -0700
From: Terry Lambert <terry@lambert.org>
Message-Id: <199604191927.MAA08783@phaeton.artisoft.com>
Subject: Re: gzipped executables
To: kuku@gilberto.physik.rwth-aachen.de (Christoph P. Kukulies)
Date: Fri, 19 Apr 1996 12:27:10 -0700 (MST)
Cc: freebsd-current@freefall.freebsd.org
In-Reply-To: <199604190816.KAA12947@gilberto.physik.rwth-aachen.de> from "Christoph P. Kukulies" at Apr 19, 96 10:16:55 am
X-Mailer: ELM [version 2.4 PL24]
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Sender: owner-current@FreeBSD.ORG
X-Loop: FreeBSD.org
Precedence: bulk

> Is anyone working on fixing the broken gzip executable feature in
> -current?

It's a cache interaction.  Pentium caches are written back inside
the cache queue depth, whereas pre-Pentium processors have
immutable cache queues.

It can be fixed by incorporating 32 NOP's (until the next processor
revision, anyway), in part of the code.

This is a kludge, but, of course, it works... of such ugly working
things are permanent warts grown.

Alternately, it can be caused by faulty writeback/invalidate hardware
on an external L2 cache.  Needless to say, I don't have any hardware
with broken L2 cache interaction, so I couldn't test even a kludge
if that's where it's falling down on you.  Typically, binvd'ing
the cache line range impacted immediately following a load and
again immediately following a buffer decompression would *probably*
fix the problem.


					Terry Lambert
					terry@lambert.org
---
Any opinions in this posting are my own and not those of my present
or previous employers.