Subject: Re: Still Pyxis DMA trouble
To: Olaf Seibert <firstname.lastname@example.org>
From: Wilko Bulte <email@example.com>
Date: 01/19/2001 00:10:48
On Wed, Jan 17, 2001 at 11:57:01PM +0100, Olaf Seibert wrote:
> On Wed 17 Jan 2001 at 22:03:25 +0100, Wilko Bulte wrote:
> > On Wed, Jan 17, 2001 at 09:54:55PM +0100, Olaf Seibert wrote:
> > > It seems that even in 1.5 the Pyxis DMA workaround is not perfect yet.
> > > I was careful to try the netbsd.ram kernel, and it did not work properly
> > There are multiple ECO levels on the MX5 so you might have hardware that is
> > not up to the latest rev. Just a guess of course
You could send me your revision level of the MLB. I might be able to check
how 'old' as far as ECOs go, your board is.
> That is of course quite possible.
> When browsing through the source, I found the following comment a bit
> * Flush the scatter/gather TLB on broken Pyxis chips.
> * Now, read from PCI dense memory space at offset 128M (our
> * target window base), skipping 64k on each read. This forces
> * S/G TLB misses.
> * XXX Looks like the TLB entries are `not quite LRU'. We need
> * XXX to read more times than there are actual tags!
> in arch/alpha/pci/cia_dma.c. A thing like this sounds like it could differ
> between revisions - maybe my version needs still more forced TLB misses?
> Or am I talking nonsense here?
Sorry, I do not know enough of the intricacies involved here to really
comment with useful information.
| / o / / _ Arnhem, The Netherlands email: firstname.lastname@example.org
|/|/ / / /( (_) Bulte http://www.freebsd.org http://www.nlfug.nl