Current-Users archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

Re: USB problems after memory upgrade

> Some devices, busses, and potentially device+bus combinations have
> limitations on the  memory range they can use for DMA. Where known
> these are handled in the tree by enforce allocation within an
> acceptable range or bounce-buffering where needed.


If the limitations are come from a fundamental device like PCI
it might be worth to try, but in most case such limitations are
for cost reduction or by simply bugs. memcpy() between bounce buffer
is fast enough on modern machines so I doubt we can see visible
performance improvements and I'm afraid such restrictions on
allocation could cause bad side effect on memory shortage.
We need certain benchmark in any case.

> What I was proposing was akin to a test case - a kernel option which
> would not be expected to be used in normal use, but would provide
> memory to devices from the maximum permissible range.

Probably it might be trivial to prepare multiple physmem segments
passed to uvm_page_physload(9)? (as you've put into atari pmap ;-)
Izumi Tsutsui

Home | Main Index | Thread Index | Old Index