Message-ID: <57B82533.9010507@huawei.com>
Date:   Sat, 20 Aug 2016 17:38:59 +0800
From:   zhong jiang <zhongjiang@...wei.com>
To:     Ganapatrao Kulkarni <gpkulkarni@...il.com>
CC:     Catalin Marinas <catalin.marinas@....com>,
        Mark Rutland <mark.rutland@....com>,
        Will Deacon <will.deacon@....com>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
        Rob Herring <robh+dt@...nel.org>,
        Ganapatrao Kulkarni <gkulkarni@...iumnetworks.com>,
        "linux-arm-kernel@...ts.infradead.org" 
        <linux-arm-kernel@...ts.infradead.org>
Subject: Re: [PATCH] mm, numa: boot cpu should bound to the node0 when node_off
 enable

On 2016/8/19 12:11, Ganapatrao Kulkarni wrote:
> On Fri, Aug 19, 2016 at 9:30 AM, Ganapatrao Kulkarni
> <gpkulkarni@...il.com> wrote:
>> On Fri, Aug 19, 2016 at 7:28 AM, zhong jiang <zhongjiang@...wei.com> wrote:
>>> On 2016/8/19 1:45, Ganapatrao Kulkarni wrote:
>>>> On Thu, Aug 18, 2016 at 9:34 PM, Catalin Marinas
>>>> <catalin.marinas@....com> 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@...wei.com>
>>>>>> ---
>>>>>>  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.
>> boot cpu is default mapped to node0
>> are you running with any other patches?
> if you added any patch to change this code
>   /* init boot processor */
>         cpu_to_node_map[0] = 0;
>         map_cpu_to_node(0, 0);
>
> then adding code to take-care numa_off here might solve your issue.
 but in of_smp_init_cpus, boot cpu will call early_map_cpu_to_node[] to get
 the relation node. and the node is from devicetree.

 you points to the code will be covered with another node. therefore, it is
 possible that cpu_to_node[cpu] will leads to the incorrect results. therefore,
 The crash will come up.
>>> __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.
>> when numa_off, all cpus are mapped to node0( refer
>> numa_store_cpu_info) and device tree mapping is ignored.
>>> 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@...ts.infradead.org
>>>>> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
>>>> .
>>>>
>>>
> .
>

Powered by blists - more mailing lists