From owner-freebsd-hackers  Mon Oct  7 14:17:38 1996
Return-Path: owner-hackers
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.5/8.7.3) id OAA29493
          for hackers-outgoing; Mon, 7 Oct 1996 14:17:38 -0700 (PDT)
Received: from mail13.digital.com (mail13.digital.com [192.208.46.30])
          by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id OAA29483
          for <hackers@freebsd.org>; Mon, 7 Oct 1996 14:17:35 -0700 (PDT)
Received: from muggsy.lkg.dec.com by mail13.digital.com (5.65v3.2/1.0/WV)
	id AA13308; Mon, 7 Oct 1996 17:06:22 -0400
Received:  from whydos.lkg.dec.com by muggsy.lkg.dec.com (5.65/DEC-Ultrix/4.3) with SMTP
	id AA05433; Mon, 7 Oct 1996 17:06:21 -0400
Received: from localhost.lkg.dec.com (localhost.lkg.dec.com [127.0.0.1]) by whydos.lkg.dec.com (8.6.12/8.6.12) with SMTP id RAA20621; Mon, 7 Oct 1996 17:08:00 GMT
Message-Id: <199610071708.RAA20621@whydos.lkg.dec.com>
X-Authentication-Warning: whydos.lkg.dec.com: Host localhost.lkg.dec.com didn't use HELO protocol
X-Mailer: exmh version 1.6.5 12/11/95
To: hackers@freebsd.org
Cc: Mikael Karpberg <karpen@ocean.campus.luth.se>
Subject: Re: Optimizing bzero() 
In-Reply-To: Your message of "Mon, 30 Sep 1996 10:33:14 +0200."
             <199609300833.KAA18915@ocean.campus.luth.se> 
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Date: Mon, 07 Oct 1996 17:07:59 +0000
From: Matt Thomas <matt@lkg.dec.com>
Sender: owner-hackers@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk


> According to Poul-Henning Kamp:
> > In message <199609250343.AA109333032@fakir.india.hp.com>, A JOSEPH KOSHY writes
> > :
> > >>>>> "phk" == "Poul-Henning Kamp" <phk@critter.tfs.com> writes
> > >
> > >phk> The next thing you could start to consider is when people realloc a
> > >phk> multipage allocation to something bigger, it would be nice to be able
> > >phk> to ask the kernel to "move these pages to this address" and then extend
> > >phk> It there instead of copying the contents.
> > >
> > >Makes sense; can this be done without major surgery though? How costly 
> > >would it be for malloc(3) to invoke a system call to re-arrange the
> > >address space compared to an memory allocation followed by a bcopy()? 
> > cheap(er).
> Can't you just make realloc do that? Is there a problem with doing it?
> If not, is there a way to tell the system to rearrange your address space?

I've always wanted to be able to use procfs for doing that.  Alas, procfs
doesn't support mmap operations.

#include <limits.h>
#include <unistd.h>
#include <fcntl.h>
#include <errno.h>
#include <sys/mman.h>

static int x;
int
main(
    void)
{
    char fname[50];
    int fd;
    caddr_t ptr;

    sprintf(fname, "/proc/%05d", getpid());
    fd = open(fname, O_RDONLY);
    if (fd < 0) {
	perror(fname);
	exit(1);
    }

    errno = 0;
    ptr = mmap(NULL, getpagesize(),
	       PROT_READ, MAP_FILE|MAP_SHARED, fd,
	       ((off_t) &x) & ~getpagesize());
    if (ptr == (caddr_t) -1) {
	perror("mmap");
	exit(1);
    }
    printf("OK\n");
}

-- 
Matt Thomas               Internet:   matt@3am-software.com
3am Software Foundry      WWW URL:    http://www.3am-software.com/bio/matt.html
Westford, MA              Disclaimer: I disavow all knowledge of this message