Re: PCI MMIO flushing and stuff (was Re: 2.2.15 with eepro100: eth0:

From: Alan Cox (alan@lxorguk.ukuu.org.uk)
Date: Sun May 21 2000 - 07:50:55 EST


> > > What happens when PCI DMA writes to an address which is currently clean
> > > within a CPU cache?
> >
> > It goes dirty
>
> Are you sure? It should be invalidated shouldn't it?

It depends how smart the CPU/Bus is and if the line is clean but exclusive.
I dont know if x86 supports it but in this case the CPU can steal the
transaction and write it to cache taking the line dirty but still exclusive

-
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 : Tue May 23 2000 - 21:00:19 EST