On Fri, 18 Sep 2009, Yinghai Lu wrote:
>
> exposed by Jesse's patch too.
>
> please check
>
> ---
> arch/x86/include/asm/pci.h | 9 ++++++++-
> 1 file changed, 8 insertions(+), 1 deletion(-)
>
> Index: linux-2.6/arch/x86/include/asm/pci.h
> ===================================================================
> --- linux-2.6.orig/arch/x86/include/asm/pci.h
> +++ linux-2.6/arch/x86/include/asm/pci.h
> @@ -143,7 +143,14 @@ static inline int __pcibus_to_node(const
> static inline const struct cpumask *
> cpumask_of_pcibus(const struct pci_bus *bus)
> {
> - return cpumask_of_node(__pcibus_to_node(bus));
> + int node;
> +
> + node = __pcibus_to_node(bus);
> +
> + if (node == -1)
> + node = numa_node_id();
> +
> + return cpumask_of_node(node);
This looks like the wrong fix. Why would the pcibus cpumask depend on the
node we happen to run on right now? All the other code says "no node means
all online cpus", which makes much more sense.
Linus
--
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
