Date: Thu, 19 Sep 1996 12:32:25 +0200 (MET DST)
From: Mark Habersack <grendel AT ananke DOT amu DOT edu DOT pl>
Reply-To: grendel AT ananke DOT amu DOT edu DOT pl
To: "Alaric B. Williams" <alaric AT abwillms DOT demon DOT co DOT uk>
cc: djgpp AT delorie DOT com
Subject: Re: Physical Memory Addresses
In-Reply-To: <843077144.28180.2@abwillms.demon.co.uk>
Message-ID: <Pine.NEB.3.95.960919122741.3071G-100000@ananke.amu.edu.pl>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII

On Wed, 18 Sep 1996, Alaric B. Williams wrote:

>Derek Smith <dsmith AT cybernet DOT com> wrote:
>
>>I am trying to get the physical address of a block of memory returned by
>>doing a malloc (or some other memory allocation function) to pass to the
>>DMA controller.  I cannot figure how to obtain this physical address. 
>>Can anyone provide some insight for me.
>
>Don't try - it is theoretically possible to do some DMA transfers
>between 1Mb and 16Mb (I think?) of physical RAM, but far safer to
>stick to the first meg.
It's practically possible to do it, provided you have a memory manager that
supports VDS service. But still, the VDS is just compying data between pmode
buffer in extmem and rmode buffer in conmem. It's reeeally slow...
OTOH, PCI BIOSes support DMA transfers in a whole range of virtual memory. The
question is whether you can count on all computers having such a BIOS? Even if
the computer has it, then if any ISA card plugged into the PCI motherboard
exists - everything goes nuts...

Bye, Mark

**********************************************************************
So if you ask me how do I feel inside, I could honestly tell you we've
been taken on a very long ride. And if my owners let me have free time
some day, with all good intention I would probably run away!
Clutching the short straw...
******************* http://ananke.amu.edu.pl/~grendel ****************