On Wed, 27 Sep 2000, Arjan van de Ven wrote:
> "This means that your CPU indicates that it is defective"
An MCE might also mean an external error. For example, the
Mercury/Neptune chipsets used to report MB memory and PCI parity errors
via the BUSCHK# CPU input, which in turn triggers an MCE in Pentia.
BTW, this is a better way of reporting such errors, than using NMI, in my
opinion, especially as triggering an MCE latches the address and data
buses of the affected cycle (chipset could possibly drive appropriate data
if a parity error happens on a posted write, for example) so they can be
examined directly later.
--
+ Maciej W. Rozycki, Technical University of Gdansk, Poland +
+--------------------------------------------------------------+
+ e-mail: [EMAIL PROTECTED], PGP key available +
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
Please read the FAQ at http://www.tux.org/lkml/