linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: Rabeeh Khoury <rabeeh@galileo.co.il>
To: "Karaaslan, Utku" <UKaraasl@drs.ca>
Cc: "'linuxppc-embedded@lists.linuxppc.org'"
	<linuxppc-embedded@lists.linuxppc.org>
Subject: Re: A Question on Physical Memory Access from Applications
Date: Thu, 09 Aug 2001 00:24:50 +0300	[thread overview]
Message-ID: <3B71AE22.2050901@galileo.co.il> (raw)
In-Reply-To: 47EE8DCFB8C6D311A23700508B8BAD5903DAF7@THEBRAIN2


Hi,

We had such a problem few months ago ; what we've done is allocating
contigious physical memory using kmalloc in kernel space.
 From the pointer that you get from kmalloc remove the 4 MSB bits
(usually 0xc) and pass it (some how) to the user space application.
The user space application map the address that was passed from the
kernel, and it will get another virtual contigious memory space.

Now the memory area that you have in user space is contigious AND the
physical memory that the page tables points to is contigious (because it
was allocated in kernel space using kmalloc), therfore it is enough that
your ADA applications just refer to the allocated memory using a pointer
to the virtual memory.

Regards,
Rabeeh


Karaaslan, Utku wrote:

>I have ported the Linux bootloader/kernel to our home-made boards
>(Motorola 860) and they have been running well up to now. However,
>I have a problem: we've got a number of ADA applications which are
>using direct memory access to certain hardware registers. Under
>VxWorks, this is not a problem as it lacks kernelspace/userspace
>separation. Under Linux, I know I can do direct memory access (through
>/dev/mem), but in this case I want to use the applications as they are,
>with no change to the ADA code. Is there any way to do physical memory
>access transparently wrt the application? Many thanks in advance.

** Sent via the linuxppc-embedded mail list. See http://lists.linuxppc.org/

  parent reply	other threads:[~2001-08-08 21:24 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2001-08-08 13:38 A Question on Physical Memory Access from Applications Karaaslan, Utku
2001-08-08 14:32 ` Andrew Johnson
2001-08-08 21:24 ` Rabeeh Khoury [this message]
  -- strict thread matches above, loose matches on Subject: below --
2001-08-09  5:55 eejape

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=3B71AE22.2050901@galileo.co.il \
    --to=rabeeh@galileo.co.il \
    --cc=UKaraasl@drs.ca \
    --cc=linuxppc-embedded@lists.linuxppc.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).