From owner-freebsd-smp  Wed Dec  4 07:29:46 1996
Return-Path: owner-smp
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.5/8.7.3) id HAA14619
          for smp-outgoing; Wed, 4 Dec 1996 07:29:46 -0800 (PST)
Received: from tfs.com (tfs.com [140.145.250.1])
          by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id HAA14605
          for <freebsd-smp@freebsd.org>; Wed, 4 Dec 1996 07:29:42 -0800 (PST)
Received: from critter.tfs.com by tfs.com (smail3.1.28.1) with SMTP
	id m0vVIYx-0003wHC; Wed, 4 Dec 96 06:44 PST
Received: from critter.tfs.com (localhost [127.0.0.1]) by critter.tfs.com (8.8.2/8.8.2) with ESMTP id JAA01938; Wed, 4 Dec 1996 09:33:34 +0100 (MET)
To: Chris Csanady <ccsanady@friley216.res.iastate.edu>
cc: freebsd-smp@freebsd.org
Subject: Re: Finished locks.. 
In-reply-to: Your message of "Tue, 03 Dec 1996 15:08:32 CST."
             <199612032108.PAA15610@friley216.res.iastate.edu> 
Date: Wed, 04 Dec 1996 09:33:34 +0100
Message-ID: <1936.849688414@critter.tfs.com>
From: Poul-Henning Kamp <phk@critter.tfs.com>
Sender: owner-smp@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk

In message <199612032108.PAA15610@friley216.res.iastate.edu>, Chris Csanady wri
tes:
>For what it's worth, I have completed a simple implementation of spin
>locks.  (However, I'm sure someone will tell me different.. :)  Either
>way, it was nice to learn a bit of assembly.
>
>If these are not sufficient, how can I improve upon them?  I'd like to
>move some of the locking around, and they would help.  In particular, I
>am planning to move the global lock out into the syscalls, and perhaps
>create a seperate lock for the run queues and such.  Then from there, we
>can we can reduce the graininess a bit. :)
>
>Anyway, I'd just like to thank all of you for helping me out.
>
>Chris
>
>
>
>        .text
>
>/***********************************************************************
> *  void LOCK()
> *  -----------------
> *  All registers preserved
> */
>
>        .align  2,0x90
>        .globl  _LOCK
>_LOCK:
>        pushl   %eax
>        pushl   %ecx
>        pushl   %edx
>        movl    $_smp_active, %eax
>        cmpl    $0, %eax
>        je      4f
>1:      movl    16(%esp), %edx
>        movl    $1, %ecx
>        movl    $0, %eax
>2:      lock
>        cmpxchg %ecx, (%edx)

->        jne     3f
->        jmp     4f
+	 je	4f

>3:      cmpl    %ecx, (%edx)
>        je      3b
I'm sure you don't mean the above  jump.

>        jmp     2b
>4:      popl    %edx
>        popl    %ecx
>        popl    %eax
>        ret

--
Poul-Henning Kamp           | phk@FreeBSD.ORG       FreeBSD Core-team.
http://www.freebsd.org/~phk | phk@login.dknet.dk    Private mailbox.
whois: [PHK]                | phk@tfs.com           TRW Financial Systems, Inc.
Power and ignorance is a disgusting cocktail.