Re: bus_space_physload(9)

[David Young <dyoung%pobox.com@localhost>]

On Thu, Mar 25, 2010 at 02:39:18PM +0900, Masao Uebayashi wrote:
> Another question is, do we want to register device memory as part of usual
> memory?

I don't think that we should register device memory as part of "usual"
memory, if that means putting the device memory into the same pool as
the rest.  The device memory may have different properties than the
rest.

Properties of the "usual" memory, if by that you mean the system RAM,
can vary from physical address to physical address.  Think of NUMA.

> For example OpenBSD seems to be trying to use framebuffer's memory
> for mbufs.

Why is OpenBSD doing that?  Doesn't the framebuffer memory go into an
mbuf-only pool?

> It's possible if we prepare the relevant interface and call 
> uvm_page_physload(9)
> instead of uvm_page_physload_device(9).  Maybe worth preparing the API.  It'd
> internally allocate struct vm_page array.  Let UVM use those pages keeping
> reference counts so that we can safely detach device.  This is kind of NUMA.

It's interesting that you mention device detachment.  I don't think that
we have any way to ask for the kernel to vacate physical pages, or to
wait for it to vacate physical pages.  Do we?

Dave

-- 
David Young             OJC Technologies
dyoung%ojctech.com@localhost      Urbana, IL * (217) 278-3933