mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* [Q] mmap/munmap of physical address
@ 2001-06-29  1:08 Christophe Beaumont
  0 siblings, 0 replies; only message in thread
From: Christophe Beaumont @ 2001-06-29  1:08 UTC (permalink / raw)
  To: Linux-Kernel

Hi,

I am fighting with a little problem here.
I have reserved a chunk of physical memory for my personnal
use and out of the kernel scope (linux mem=1024M).
I have now to handle this reserved memory by myself with
a simple scheme (I need BIG contiguous memory chunks (over
64Megs, and only few of them).
My idea was to create a driver for that memory & mmap()
in it. So far so good, I can mmap() from user side, driver
works fine as far as remap_page_range() is concerned.
Now comes the freeing/unmapping of those regions. I have
implemented my personnal vm_operations_struct to take care
of house keeping....
BUT
the close(struct vm_area_struct *vma) only gives me back
a virtual address, and a call to virt_to_phys(vma->start)
doesn't point back to the physical address I gave when mmaping.
As I have multiple processes, I cannot associate (virt addr,
phys addr) [2 processes could have the same virt addr pointing
to 2 different physical areas].

I am wondering if there is something totally obvious I am
missing there in the process (i.e., is there unmap_page_range
taking the virtual address as input... ;)  )

Thanks in advance...


Christophe Beaumont

Sr Software Engineer                     Phone: 626-744-2078
Paracel, Inc.                              Fax: 626-744-2001
1055 East Colorado Blvd,   email: chris.beaumont@paracel.com
Pasadena, CA 91106-2341                 www: www.paracel.com




^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2001-06-29  1:07 UTC | newest]

Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2001-06-29  1:08 [Q] mmap/munmap of physical address Christophe Beaumont

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®