![]() | |||||||||||||
Messages in this thread |
On 7/22/07, David Rientjes <rientjes@google.com> wrote:
> On Sat, 21 Jul 2007, Yinghai Lu wrote:
>
> > [PATCH 3/3] x86_64: offset apicid_to_node before use it before
> > init_cpu_to_node
> >
>
> Does this preserve the correct fake apicid_to_node mapping for the
> emulated case such as numa=fake=32?
>
+void __init update_apicid_to_node(void)
+{
+ /*
+ * let modify apicid_to_node array when boot_cpu_id !=0
+ * apicid_to_node[0] != NUMA_NODE
+ */
+
+ int i;
+
+ /* there is no apic id offset */
+ if (!boot_cpu_id)
+ return;
+
+ /* check if it is already updated */
+ if (apicid_to_node[0] == NUMA_NO_NODE)
+ return;
boot_cpu_id (bsp apic id ) is 0 under fake numa case?
or need to add some exit for fake numa mode.
YH
-
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/
| ||||||||||||
| Last update: 2007-07-22 08:19 [from the cache] ©2003-2008 | |||||||||||||