Re: [patch] srat, x86_64: Add support for nodes spanning other nodes

[Suresh Siddha <suresh.b.siddha@intel.com>]

On Tue, Mar 25, 2008 at 01:28:53PM -0400, Chris Snook wrote:
> Suresh Siddha wrote:
> >For example, If the physical address layout on a two node system with 8 GB
> >memory is something like:
> >node 0: 0-2GB, 4-6GB
> >node 1: 2-4GB, 6-8GB
> >
> >Current kernels fail to boot/detect this NUMA topology.
> >
> >ACPI SRAT tables can expose such a topology which needs to be supported.
> >
> >Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
> >---
> >
> >diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
> >index 227fdb0..99eb102 100644
> >--- a/arch/x86/Kconfig
> >+++ b/arch/x86/Kconfig
> >@@ -880,6 +880,15 @@ config X86_64_ACPI_NUMA
> > 	help
> > 	  Enable ACPI SRAT based node topology detection.
> > 
> >+# Some NUMA nodes have memory ranges that span
> >+# other nodes.  Even though a pfn is valid and
> >+# between a node's start and end pfns, it may not
> >+# reside on that node.  See memmap_init_zone()
> >+# for details.
> >+config NODES_SPAN_OTHER_NODES
> >+	def_bool y
> >+	depends on X86_64_ACPI_NUMA
> >+
> 
> Is this hunk a leftover from your testing?  You're not using the config 

No.

> option anywhere, and there isn't really anything in this patch that would 
> justify making this a separate config option in mainline.

Its the generic -mm code which needs this. Please refer to early_pfn_in_nid()
and its usage in memmap_init_zone()

thanks,
suresh