Re: [PATCH v3] mm/hugetlb: split hugetlb_cma in nodes with memory

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On 7/15/20 4:14 AM, Song Bao Hua (Barry Song) wrote:
>> From: Mike Kravetz [mailto:mike.kravetz@xxxxxxxxxx]
>>  					huge_page_size(h)/1024);
>>
>> +	if (order >= MAX_ORDER && hugetlb_cma_size)
>> +		hugetlb_cma_reserve(order);
> 
> Hello, Mike,
> I am not sure if it is necessarily correct as the order for gigantic pages is arch-dependent:
> https://lkml.org/lkml/2020/7/1/14
> 

See my reply to Wil.

The code to allocate gigantic pages from CMA depends on the arch independent
definition of gigantic page which is 'order >= MAX_ORDER'.

-- 
Mike Kravetz




[Index of Archives]     [Linux ARM Kernel]     [Linux ARM]     [Linux Omap]     [Fedora ARM]     [IETF Annouce]     [Bugtraq]     [Linux OMAP]     [Linux MIPS]     [eCos]     [Asterisk Internet PBX]     [Linux API]

  Powered by Linux