lkml.org 
[lkml]   [2022]   [May]   [12]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
Subject[PATCH] arch_topology: support parsing cluster_id from DT
Date

>> 
>>>> From: Wang Qing <wangqing@vivo.com>
>
>[...]
>
>>> Would have to be cluster_id = -1. 0 is a valid 2. level cluster.
>>> Otherwise you're not removing the CLS data from CPU4 to CPU7 in the
>>> `Armv9 with L2 complexes` cpu-map example I used for testing:
>>>
>>>                 cpu-map {
>>>                         cluster0 {
>>>                                 cluster0 {
>>>                                         core0 {
>>>                                                 cpu = <&cpu0>;
>>>                                         };
>>>                                         core1 {
>>>                                                 cpu = <&cpu1>;
>>>                                         };
>>>                                 };
>>>                                 cluster1 {
>>>                                         core0 {
>>>                                                 cpu = <&cpu2>;
>>>                                         };
>>>                                         core1 {
>>>                                                 cpu = <&cpu3>;
>>>                                         };
>>>                                 };
>>>                         };
>>>                         cluster1 {
>>>                                 core0 {
>>>                                         cpu = <&cpu4>;
>>>                                 };
>>>                                 core1 {
>>>                                         cpu = <&cpu5>;
>>>                                 };
>>>                                 core2 {
>>>                                         cpu = <&cpu6>;
>>>                                 };
>>>                         };
>>>                         cluster2 {
>>>                                 core0 {
>>>                                         cpu = <&cpu7>;
>>>                                 };
>>>                         };
>>>                 };
>
>[...]
>
>>> Looks like you also need to adapt update_siblings_masks() to only set
>>> cpu in &cpu_topo->thread_sibling and &cpuid_topo->thread_sibling when
>>> `cpu_topo->thread_id != -1`.
>>>
>>> @@ -723,11 +723,11 @@ void update_siblings_masks(unsigned int cpuid)
>>>                 cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
>>>                 cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
>>>
>>> -               if (cpuid_topo->core_id != cpu_topo->core_id)
>>> -                       continue;
>>> -
>>> -               cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
>>> -               cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
>>> +               if (cpu_topo->thread_id != -1 &&
>>> +                   cpuid_topo->core_id == cpu_topo->core_id) {
>>> +                       cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
>>> +                       cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
>>> +
>>
>> This seems like another problem?
>
>I don't think so. If you run a system with the cpu-map mentioned above

Here is not enough, cpu0,1,4,5 will make up SMT below:
cluster0 {
        cluster0 {
                core0 {
                        thread0 {
                                 cpu = <&CPU0>;
                                };
                        thread1 {
                                 cpu = <&CPU1>;
                                };
                      };
                };
                core1 {
                        thread0 {
                                 cpu = <&CPU2>;
                                };
                        thread1 {
                                 cpu = <&CPU3>;
                                };
                      };
                };
        cluster1 {
                core0 {
                        thread0 {
                                 cpu = <&CPU4>;
                                };
                        thread1 {
                                 cpu = <&CPU5>;
                                };
                      };
                };
                core1 {
                        thread0 {
                                 cpu = <&CPU6>;
                                };
                        thread1 {
                                 cpu = <&CPU7>;
                                };
                      };
                };
...
I will handle this.

Thanks,
Qing

>you get:
>
># cat /sys/kernel/debug/sched/domains/cpu0/domain*/name
>SMT        <-- !!!
>CLS
>MC
>
>root@e125579:~# cat /proc/schedstat | awk '{print $1 " " $2 }' | grep
>^[cd] | head -5
>cpu0 0
>domain0 05 <-- !!!
>domain1 07 <-- !!!
>domain2 0f
>domain3 ff
>
>So you get an unwanted SMT level for CPU0-3 and messed-up cpumasks
>without this change.
\
 
 \ /
  Last update: 2022-05-12 14:52    [W:0.128 / U:0.136 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site