Re: [PATCH] sparc64: Fix numa node distance initialization

[Nitin Gupta <nitin.m.gupta@oracle.com>]

On 1/6/16 2:32 AM, Khalid Aziz wrote:
> On 01/05/2016 02:40 AM, Nitin Gupta wrote:
>> Orabug: 22495713
>>
>> Currently, NUMA node distance matrix is initialized only
>> when a machine descriptor (MD) exists. However, sun4u
>> machines (e.g. Sun Blade 2500) do not have an MD and thus
>> distance values were left uninitialized. The initialization
>> is now moved such that it happens on both sun4u and sun4v.
>>
>> Signed-off-by: Nitin Gupta <nitin.m.gupta@oracle.com>
>> Tested-by: Mikael Pettersson <mikpelinux@gmail.com>
>> ---
>>   arch/sparc/mm/init_64.c | 15 ++++++++-------
>>   1 file changed, 8 insertions(+), 7 deletions(-)
>>
>> diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
>> index 3025bd5..ff63db5 100644
>> --- a/arch/sparc/mm/init_64.c
>> +++ b/arch/sparc/mm/init_64.c
>> @@ -1267,13 +1267,6 @@ static int __init numa_parse_mdesc(void)
>>       int i, j, err, count;
>>       u64 node;
>>
>> -    /* Some sane defaults for numa latency values */
>> -    for (i = 0; i < MAX_NUMNODES; i++) {
>> -        for (j = 0; j < MAX_NUMNODES; j++)
>> -            numa_latency[i][j] = (i = j) ?
>> -                LOCAL_DISTANCE : REMOTE_DISTANCE;
>> -    }
>> -
>>       node = mdesc_node_by_name(md, MDESC_NODE_NULL, "latency-groups");
>>       if (node = MDESC_NODE_NULL) {
>>           mdesc_release(md);
>> @@ -1374,6 +1367,14 @@ static int __init bootmem_init_numa(void)
>>       numadbg("bootmem_init_numa()\n");
>>
>>       if (numa_enabled) {
>> +        int i, j;
>> +        /* Some sane defaults for numa latency values */
>> +        for (i = 0; i < MAX_NUMNODES; i++) {
>> +            for (j = 0; j < MAX_NUMNODES; j++)
>> +                numa_latency[i][j] = (i = j) ?
>> +                    LOCAL_DISTANCE : REMOTE_DISTANCE;
>> +        }
>> +
>>           if (tlb_type = hypervisor)
>>               err = numa_parse_mdesc();
>>           else
>>
> 
> If one were to boot up with "numa=off" kernel option, numa_latency array wouldn't be initialized by this code which will cause node_distance() to return 0 for any two nodes. Would it make more sense to do this initialization outside of "if (numa_enabled)" or is a value of 0, instead of LOCAL_DISTANCE when numa is not enabled, for node_distance() not a problem?
> 

I see that in places in page_alloc, numa_distance() is used based just on
compile time CONFIG_NUMA. So, yes the initialization should be moved outside
of dynamic config 'numa_enabled'. I will correct this in next patch v2.

Thanks,
Nitin