Messages in this thread | | | Date | Mon, 26 Jul 1999 09:49:34 +0930 (CST) | From | Alan Modra <> | Subject | Re: New kernel/resource.c |
| |
On Sun, 25 Jul 1999, Linus Torvalds wrote: > > On Sun, 25 Jul 1999, Richard Henderson wrote: > > > > Hmm, actually we have more than 65536 generically on PCI. It's > > just the x86 that limits to 64k. I actually ran into trouble > > here the other day -- > > Yeehaa.. > > I wonder how many devices decode all 32 bits of an IO address. Maybe they > all do, but it sure hasn't gotten any testing by anybody. Considering that
They aren't PCI compliant if they don't decode all 32 bits. Extract from PCI v2.1 spec:
"The I/O Read command is used to read data from an agent mapped in I/O Address Space. AD[31::00] provide a byte address. All 32 bits must be decoded."
Ditto for I/O write. The area where PCI devices are likely to cheat on address decoding is in the IO/mem base address regs, where some bits may be hardwired to zeros.
- 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/
| |