Re: (*(unsigned long *)&jiffies)++;

From: Tigran Aivazian (tigran@sco.COM)
Date: Mon Jan 10 2000 - 04:08:56 EST


On Fri, 7 Jan 2000, Petko Manolov wrote:
> accessed
> address not the whole memory. And this should be true for everything
> newer
> than 386. So is possible CPU1 to access one _real_ address and CPU2
> access
> other _real_ adress at the same time.

Wrong. On i486 and Pentium LOCK means bus lock. Period.
On P6 it is more complex than that. If the location you are locking is
cached in the processor performing the lock the processor may not assert
the LOCK on the bus. It will modify its internal view of it and let the
cache coherency mechanism handle the "problems".

> But i'll not bet on this until i read the manuals ;-))
yes, good idea. They are all on developer.intel.com, btw.

Regards,
Tigran.

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Sat Jan 15 2000 - 21:00:15 EST