From owner-freebsd-net  Tue Dec 12 18:50:34 2000
From owner-freebsd-net@FreeBSD.ORG  Tue Dec 12 18:50:31 2000
Return-Path: <owner-freebsd-net@FreeBSD.ORG>
Delivered-To: freebsd-net@freebsd.org
Received: from khavrinen.lcs.mit.edu (khavrinen.lcs.mit.edu [18.24.4.193])
	by hub.freebsd.org (Postfix) with ESMTP id 1838B37B400
	for <net@FreeBSD.ORG>; Tue, 12 Dec 2000 18:50:31 -0800 (PST)
Received: (from wollman@localhost)
	by khavrinen.lcs.mit.edu (8.9.3/8.9.3) id VAA55319;
	Tue, 12 Dec 2000 21:50:19 -0500 (EST)
	(envelope-from wollman)
Date: Tue, 12 Dec 2000 21:50:19 -0500 (EST)
From: Garrett Wollman <wollman@khavrinen.lcs.mit.edu>
Message-Id: <200012130250.VAA55319@khavrinen.lcs.mit.edu>
To: Alfred Perlstein <bright@wintelcom.net>
Cc: net@FreeBSD.ORG
Subject: Re: MEXT_IS_REF broken.
In-Reply-To: <20001212175937.M16205@fw.wintelcom.net>
References: <20001211014837.W16205@fw.wintelcom.net>
	<Pine.BSF.4.21.0012111223350.21769-100000@jehovah.technokratis.com>
	<20001212014429.Y16205@fw.wintelcom.net>
	<20001212015059.Z16205@fw.wintelcom.net>
	<20001212143214.H2312@canonware.com>
	<20001212175937.M16205@fw.wintelcom.net>
Sender: owner-freebsd-net@FreeBSD.ORG
Precedence: bulk
X-Loop: FreeBSD.org

<<On Tue, 12 Dec 2000 17:59:37 -0800, Alfred Perlstein <bright@wintelcom.net> said:

> Actually, in truth I think you can get the code right like so:

> long x = _mmm->m_ext.ref_cnt->refcnt;
> while (!atomic_cmpset_long(&_mmm->m_ext.ref_cnt->refcnt, x - 1, x))
> 	;

Cool!  You've just (almost) reinvented non-blocking parallel
reference-counts.  Of course, what you really need is:

long
atomic_decrement_long(long *where)
{
	long oldval;

	do {
		oldval = *where;
	} while (compare_exchange(where, &oldval, oldval - 1) != FAILURE);

	return (oldval);
	/*
	 * Five instructions in-line on i486.
	 * 1:	movl (%ebx), %eax
	 *	movl %eax, %edx
	 *	subl $1, %edx
	 *	cmpxchg (%ebx), %eax, %edx	; IIRC -- might be backwards
	 *	jc 1
	 */
}

...except that on some architectures, the right way to write it would
be:

long
atomic_decrement_long(long *where)
{
	long oldval;

	do {
		oldval = load_linked_long(where);
	} while (store_conditional(where, oldval - 1) != FAILURE);

	return (oldval);
	/*
	 * Compiles to four or five instructions on an Alpha.
	 */
}

In this particular instance, you know that you just deleted the last
reference if atomic_decrement_long returns an `old value' of 

> But that's just gross, expensive and shouldn't be needed.

Nothing gross about it -- just ask any parallel algorithms geek.  (Of
which I am emphatically not one, I should point out.)

-GAWollman



To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-net" in the body of the message