From owner-freebsd-current  Sat Feb 23 17:55: 5 2002
Delivered-To: freebsd-current@freebsd.org
Received: from apollo.backplane.com (apollo.backplane.com [216.240.41.2])
	by hub.freebsd.org (Postfix) with ESMTP
	id C4CBE37B402; Sat, 23 Feb 2002 17:54:58 -0800 (PST)
Received: (from dillon@localhost)
	by apollo.backplane.com (8.11.6/8.9.1) id g1O1suv36741;
	Sat, 23 Feb 2002 17:54:56 -0800 (PST)
	(envelope-from dillon)
Date: Sat, 23 Feb 2002 17:54:56 -0800 (PST)
From: Matthew Dillon <dillon@apollo.backplane.com>
Message-Id: <200202240154.g1O1suv36741@apollo.backplane.com>
To: Bruce Evans <bde@zeta.org.au>
Cc: Terry Lambert <tlambert2@mindspring.com>,
	Alfred Perlstein <alfred@FreeBSD.ORG>,
	Bosko Milekic <bmilekic@unixdaemons.com>,
	Seigo Tanimura <tanimura@r.dl.itc.u-tokyo.ac.jp>,
	<current@FreeBSD.ORG>, John Baldwin <jhb@FreeBSD.ORG>
Subject: Re: malloc_bucket() idea (was Re: How to fix malloc.)
References:  <20020224111043.W30980-100000@gamplex.bde.org>
Sender: owner-freebsd-current@FreeBSD.ORG
Precedence: bulk
List-ID: <freebsd-current.FreeBSD.ORG>
List-Archive: <http://docs.freebsd.org/mail/> (Web Archive)
List-Help: <mailto:majordomo@FreeBSD.ORG?subject=help> (List Instructions)
List-Subscribe: <mailto:majordomo@FreeBSD.ORG?subject=subscribe%20freebsd-current>
List-Unsubscribe: <mailto:majordomo@FreeBSD.ORG?subject=unsubscribe%20freebsd-current>
X-Loop: FreeBSD.ORG

:It's too messy and unfinished (doesn't work right for SMP or irqs >= 16),
:and dificult to untangle from my other patches.  I posted these partial
:ones to attempt to inhibit() recomplication of the current critical*
:functions in directions that I don't want to go :-).
:...
:
:ipending here works much as in RELENG_4.  It is ORed into by sched_ithd()
:if curthread->td_critnest != 0.  Nothing special is needed for pci
:(the ICU masks pending interrupts).
:
:Bruce

    Ok, I have most of it coded up.  Could you explain what 'spending'
    was for?

    I am doing it slightly different then you.  To avoid having to use
    locked instructions I have placed ipending in the thread structure:

void
critical_enter(void)
{
        struct thread *td = curthread;
        ++td->td_critnest;
}

void
critical_exit(void)
{
        struct thread *td = curthread;
        KASSERT(td->td_critnest > 0, ("bad td_critnest value!"));
        if (--td->td_critnest == 0) {
                if (td->td_ipending)
                        unpend();
        }
}

    The apic and icu vector code will do a simple td_critnest test and
    OR the irq bit into td->td_ipending (it conveniently already has 
    the struct thread in %ebx).  And the vector code will also check and
    handle any non-zero td_ipending if critnest is 0, handling the 
    1->0 transition/preemption race.

    I'll post the patch when it gets a little further along.

    How should I deal with fast interrupts?

					-Matt
					Matthew Dillon 
					<dillon@backplane.com>

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