On Thu, Aug 11, 2005 at 03:30:46PM -0700, Roland Dreier wrote:
> Do you have any theory as to why the drivers worked in 64-bit mode and
> failed in 32-bit mode?  I don't see any reason why the parameters
> passed to INIT_IB would be any different.

[EMAIL PROTECTED]:/usr/src/openib_gen2/src/linux-kernel/infiniband/hw/mthca$ 
fgrep writeq *
...
mthca_doorbell.h:       __raw_writeq((__force u64) val, dest);
mthca_doorbell.h:       __raw_writeq(*(u64 *) val, dest);

The only theory I can think of is 64-bit MMIO writes on a 32-bit
OS will come out as two seperate writes. But since others
are using this without a problem, this isn't likely a generic
issue. Maybe there is some timing issue here...ie slower/faster CPU
or chipset is exposing a problem.

grant
_______________________________________________
openib-general mailing list
[email protected]
http://openib.org/mailman/listinfo/openib-general

To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general

Reply via email to