On Mon, Jul 06, 2009 at 12:53:54PM -0700, Warren Turkal wrote: > On Mon, Jul 6, 2009 at 12:22, Matthew Wilcox<matthew@xxxxxx> wrote: > > Do you want us to start working on an 8-byte atomic access method inside > > the kernel? ??As I said before, it won't be available on all systems. > > > > Or should we stand firm against this bad habit of putting a 64-bit > > register in config space? > > I'm not sure there is much we can do about it. At least Intel already > has hardware with 64-bit registers in config space on the market. I > imagine there will be others. Interesting! Which device, out of interest? > Having said that, my current case doesn't require it, but I am sure it > would be nice. Actually, we're safe, it can't be done. Refer to PCI Express 2.1, section 2.2.7 where it mandates that the data part of a config packet must contain exactly one DWORD. Maybe they'll change that for PCIe 3, but there's no need for a major firedrill yet. -- Matthew Wilcox Intel Open Source Technology Centre "Bill, look, we understand that you're interested in selling us this operating system, but compare it to ours. We can't possibly take such a retrograde step." -- To unsubscribe from this list: send the line "unsubscribe linux-pci" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
