from arch/x86/Kconfig:
config AMD_NUMA
def_bool y
prompt "Old style AMD Opteron NUMA detection"
depends on X86_64 && NUMA && PCI
---help---
Enable AMD NUMA node topology detection. You should say Y here if
you have a multi processor AMD system. This uses an old method to
read the NUMA configuration directly from the builtin Northbridge
of Opteron. It is recommended to use X86_64_ACPI_NUMA instead,
which also takes priority if both are compiled in.
config X86_64_ACPI_NUMA
def_bool y
prompt "ACPI NUMA detection"
depends on X86_64 && NUMA && ACPI && PCI
select ACPI_NUMA
---help---
Enable ACPI SRAT based node topology detection.
from the wording above, it's unclear whether someone on x86_64 would
want to select AMD_NUMA if X86_64_ACPI_NUMA is supported. obviously,
if ACPI is not selected, then the first option makes sense. but the
help for AMD_NUMA clearly encourages the user to select that option,
even while recommending the second option if it's available.
and a followup question -- in arch/x86/mm/numa.c, we read:
/**
* x86_numa_init - Initialize NUMA
*
* Try each configured NUMA initialization method until one succeeds. The
* last fallback is dummy single node config encomapssing whole memory and
* never fails.
*/
void __init x86_numa_init(void)
{
if (!numa_off) {
#ifdef CONFIG_X86_NUMAQ
if (!numa_init(numaq_numa_init))
return;
#endif
#ifdef CONFIG_ACPI_NUMA
if (!numa_init(x86_acpi_numa_init))
return;
#endif
#ifdef CONFIG_AMD_NUMA
if (!numa_init(amd_numa_init))
return;
#endif
}
numa_init(dummy_numa_init);
}
if both of those earlier options are properly selected, is there any
way that the CONFIG_ACPI_NUMA test could fail, while the
CONFIG_AMD_NUMA test would subsequently succeed? without digging into
the code, it's not clear from the help or comments what the safest
approach is here; as in, even if you select ACPI_NUMA, should you
still select the older AMD_NUMA just to play it safe?
rday
--
========================================================================
Robert P. J. Day Ottawa, Ontario, CANADA
http://crashcourse.ca
Twitter: http://twitter.com/rpjday
LinkedIn: http://ca.linkedin.com/in/rpjday
========================================================================
--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
