[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]
On Tue, Apr 6, 2010 at 10:41 AM, David Young <dyoung%pobox.com@localhost> wrote:
> 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
> Properties of the "usual" memory, if by that you mean the system RAM,
> can vary from physical address to physical address. Think of NUMA.
I think of NUMA, yes. :)
>> 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?
Ah, that makes more sense.
>> It's possible if we prepare the relevant interface and call
>> 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?
I don't think so.
I think we'll need kind of physical page migration to support memory
hot-plug detachment. NUMA may benefit from page migration too.
Main Index |
Thread Index |