On Tue, Mar 15, 2005 at 10:10:57PM -0500, Brown, Len wrote: > >Interrupt Disable bit was added via an > >"Engineering Change Notice". At the same time, an "Interrupt Status" > >bit was defined for the Status register. > > I believe that this is for (new) devices that support MSI.
Hrm...that sounds like a good reason but I'm certain it didn't happen at the same time. MSI was clearly added first as an ECN to PCI 2.2 and part of PCI 2.3 release (AFAIK). > While I'm > certainly out on a limb in this area, the last time I inquired about > MSI, nobody could point me to an adapter and driver in the field that > actually worked -- so I think this bit is unlikely to help with the > problem at hand. We are starting to digress...but things look slightly better now. MSI and MSI-X seems to work for infiniband (Mellanox chips). I'm expecting 10GigE to support MSI-X properly (or perf will really stink). I've posted a patch to enable MSI for tg3 to linux-net mailing list. Even thought it worked for me, I was told bcm57xx chips have a bug in the MSI implementation that causes it to assert IRQ line anyway. I suppose that's a problem if the IRQ line is shared and the other device can't do either MSI or MSI-X. e1000 (Intel GigE) chips to date have disfunctional MSI. I haven't investigated LSI ultra 320 cards or qlogic 2312 chips though they both advertise the capability. thanks, grant ------------------------------------------------------- SF email is sponsored by - The IT Product Guide Read honest & candid reviews on hundreds of IT Products from real users. Discover which products truly live up to the hype. Start reading now. http://ads.osdn.com/?ad_id=6595&alloc_id=14396&op=click _______________________________________________ linux-usb-devel@lists.sourceforge.net To unsubscribe, use the last form field at: https://lists.sourceforge.net/lists/listinfo/linux-usb-devel
