Re: [PATCH RESEND 1/1] lib/Kconfig: remove DEBUG_PER_CPU_MAPS dependency for CPUMASK_OFFSTACK

[Randy Dunlap <rdunlap@infradead.org>]

Hi,

On 4/13/22 14:50, Libo Chen wrote:
> 
> 
> On 4/13/22 13:52, Arnd Bergmann wrote:
>> On Wed, Apr 13, 2022 at 9:28 PM Libo Chen <libo.chen@oracle.com> wrote:
>>> On 4/13/22 08:41, Randy Dunlap wrote:
>>>> On 4/12/22 23:56, Libo Chen wrote:
>>>>>> --- a/lib/Kconfig
>>>>>> +++ b/lib/Kconfig
>>>>>> @@ -511,7 +511,8 @@ config CHECK_SIGNATURE
>>>>>>         bool
>>>>>>       config CPUMASK_OFFSTACK
>>>>>> -    bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS
>>>>>> +    bool "Force CPU masks off stack"
>>>>>> +    depends on DEBUG_PER_CPU_MAPS
>>>>> This forces every arch to enable DEBUG_PER_CPU_MAPS if they want to enable CPUMASK_OFFSTACK, it's even stronger than "if". My whole argument is CPUMASK_OFFSTACK should be enable/disabled independent of DEBUG_PER_CPU_MASK
>>>>>>         help
>>>>>>           Use dynamic allocation for cpumask_var_t, instead of putting
>>>>>>           them on the stack.  This is a bit more expensive, but avoids
>>>>>>
>>>>>>
>>>>>> As I said earlier, the "if" on the "bool" line just controls the prompt message.
>>>>>> This patch make CPUMASK_OFFSTACK require DEBUG_PER_CPU_MAPS -- which might be overkill.
>>>>>>
>>>>> Okay I understand now "if" on the "boot" is not a dependency and it only controls the prompt message, then the question is why we cannot enable CPUMASK_OFFSTACK without DEBUG_PER_CPU_MAPS if it only controls prompt message? Is it not the behavior we expect?
>>>> Yes, it is. I don't know that the problem is...
>>> Masahiro explained that CPUMASK_OFFSTACK can only be configured by
>>> options not users if DEBUG_PER_CPU_MASK is not enabled. This doesn't
>>> seem to be what we want.
>> I think the correct way to do it is to follow x86 and powerpc, and tying
>> CPUMASK_OFFSTACK to "large" values of CONFIG_NR_CPUS.

Sure. Just FTR, I was just trying to see if an arch (arm64) would build OK or not
when CPUMASK_OFFSTACK was enabled. and it does.
My patch wasn't meant to have a very long life.

>> For smaller values of NR_CPUS, the onstack masks are obviously
>> cheaper, we just need to decide what the cut-off point is.
> I agree. It appears enabling CPUMASK_OFFSTACK breaks kernel builds on some architectures such as parisc and nios2 as reported by kernel test robot. Maybe it makes sense to use DEBUG_PER_CPU_MAPS as some kind of guard on CPUMASK_OFFSTACK.
>> In x86, the onstack masks can be selected for normal SMP builds with
>> up to 512 CPUs, while CONFIG_MAXSMP=y raises the limit to 8192
>> CPUs while selecting CPUMASK_OFFSTACK.
>> PowerPC does it the other way round, selecting CPUMASK_OFFSTACK
>> implicitly whenever NR_CPUS is set to 8192 or more.
>>
>> I think we can easily do the same as powerpc on arm64. With the
> I am leaning more towards x86's way because even NR_CPUS=160 is too expensive for 4-core arm64 VMs according to apachebench. I highly doubt that there is a good cut-off point to make everybody happy (or not unhappy).
>> ApacheBench test you cite in the patch description, what is the
>> value of NR_CPUS at which you start seeing a noticeable
>> benefit for offstack masks? Can you do the same test for
>> NR_CPUS=1024 or 2048?
> As mentioned above, a good cut-off point moves depends on the actual number of CPUs. But yeah I can do the same test for 1024 or even smaller NR_CPUs values on the same 64-core arm64 VM setup.


-- 
~Randy