Re: [PATCH] mm, numa: boot cpu should bound to the node0 when node_off enable

[zhong jiang]

On 2016/8/19 1:45, Ganapatrao Kulkarni wrote:
> On Thu, Aug 18, 2016 at 9:34 PM, Catalin Marinas
> <catalin.marinas@xxxxxxx> wrote:
>> On Thu, Aug 18, 2016 at 09:09:26PM +0800, zhongjiang wrote:
>>> At present, boot cpu will bound to a node from device tree when node_off enable.
>>> if the node is not initialization, it will lead to a following problem.
>>>
>>>  next_zones_zonelist+0x18/0x80
>>>  __build_all_zonelists+0x1e0/0x288
>>>  build_all_zonelists_init+0x10/0x1c
>>>  build_all_zonelists+0x114/0x128
>>>  start_kernel+0x1a0/0x414
>> I think this "problem" is missing a lot of information. Is this supposed
>> to be a kernel panic?
>>
>>> The patch fix it by fallback to node 0. therefore, the cpu will bound to the node
>>> correctly.
>>>
>>> Signed-off-by: zhongjiang <zhongjiang@xxxxxxxxxx>
>>> ---
>>>  arch/arm64/mm/numa.c | 2 +-
>>>  1 file changed, 1 insertion(+), 1 deletion(-)
>>>
>>> diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
>>> index 4dcd7d6..1f8f5da 100644
>>> --- a/arch/arm64/mm/numa.c
>>> +++ b/arch/arm64/mm/numa.c
>>> @@ -119,7 +119,7 @@ void numa_store_cpu_info(unsigned int cpu)
>>>  void __init early_map_cpu_to_node(unsigned int cpu, int nid)
>>>  {
>>>       /* fallback to node 0 */
>>> -     if (nid < 0 || nid >= MAX_NUMNODES)
>>> +     if (nid < 0 || nid >= MAX_NUMNODES || numa_off)
> i  did not understood how this line change fixes the issue that you
> have mentioned (i too not understood fully the issue description)
> this array used while mapping node id when secondary cores comes up
> when numa_off is set the cpu_to_node_map[cpu] is not used and set to
> node0 always( refer function numa_store_cpu_info)..
> please provide more details to understand the issue you are facing.
> /*
>  *  Set the cpu to node and mem mapping
>  */
> void numa_store_cpu_info(unsigned int cpu)
> {
>         map_cpu_to_node(cpu, numa_off ? 0 : cpu_to_node_map[cpu]);
> }
>
> thanks
> Ganapat
The issue comes up when we test the kdump. it will leads to kernel crash.
when I debug the issue, I find boot cpu actually bound to the node1. while
node1 is not real existence when numa_off enable.

__build_all_zonelists will call the cpu_to_node[cpu], but orresponding relation
will be obtained from the devicetree. therefore, the issue will come up.
The corresponding message is as follows when kdump start. it is obvious that mem
range points to the node1 in the devicetree.

Early memory node ranges
node   0: [mem 0x0000005fe0000000-0x0000005fffffffff]
Initmem setup node 0 [mem 0x0000005fe0000000-0x0000005fffffffff]

Unable to handle kernel paging request at virtual address 00001690
pgd = ffff800001226000
[00001690] *pgd=0000000000000000
Internal error: Oops: 96000004 [#1] SMP
 Modules linked in:
CPU: 0 PID: 0 Comm: swapper Not tainted 4.1.27-vhulk3.6.5.aarch64 #1
Hardware name: Hisilicon Hi1612 Development Board (DT)
 task: ffff80000102b730 ti: ffff800001018000 task.ti: ffff800001018000
PC is at next_zones_zonelist+0x18/0x80
 LR is at __build_all_zonelists+0x1e0/0x288
next_zones_zonelist+0x18/0x80
 __build_all_zonelists+0x1e0/0x288
build_all_zonelists_init+0x10/0x1c
 build_all_zonelists+0x114/0x128
 start_kernel+0x1a0/0x414
>>>               nid = 0;
>>>
>>>       cpu_to_node_map[cpu] = nid;
>> The patch looks fine (slight inconsistence from the map_cpu_to_node()
>> callers but I guess we don't want to expose numa_off outside this file).
>> I would however like to see an Ack from Ganapat (cc'ed).
>>
>> --
>> Catalin
>>
>> _______________________________________________
>> linux-arm-kernel mailing list
>> linux-arm-kernel@xxxxxxxxxxxxxxxxxxx
>> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
> .
>