Messages in this thread | ![/](/images/icornerl.gif) | | Date | Thu, 6 Jan 2011 11:57:43 -0800 | Subject | Re: [GIT PULL] x86/apic changes for v2.6.38 | From | Tony Luck <> |
| |
On Thu, Jan 6, 2011 at 11:22 AM, H. Peter Anvin <hpa@zytor.com> wrote: > I don't know if this is applicable on IA64.
I think that ia64 might need something like this too. If I understand the change correctly, it makes sure that we read all entries for cpus from the SRAT table, so that we can figure out the topology for any cpus that we decide to use (which may be at arbitrary positions in the SRAT table as there is no guarantee that SRAT entries are in the same order as MADT entries ... we might try to boot the first four cpus we find in MADT, but those might be the last four entries in SRAT.)
It looks like this could be more simply achieved in an architecture neutral way by just passing "0" as the last argument to acpi_table_parse_srat() ... which will look at every entry in SRAT (this is not exactly the same ... but it seems unlikely that SRAT will have more than 32768 processor entries ... which you are apparently willing to allow for with the MAX_LOCAL_APIC value.)
-Tony -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| ![\](/images/icornerr.gif) |