Re: [RFC PATCH 1/3] mm: enable MADV_DONTNEED for hugetlb mappings

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

 



On 1/26/22 18:58, Naoya Horiguchi wrote:
> On Thu, Jan 13, 2022 at 10:03:06AM -0800, Mike Kravetz wrote:
>> MADV_DONTNEED is currently disabled for hugetlb mappings.  This
>> certainly makes sense in shared file mappings as the pagecache maintains
>> a reference to the page and it will never be freed.  However, it could
>> be useful to unmap and free pages in private mappings.
>>
>> The only thing preventing MADV_DONTNEED (and MADV_FREE) from working on
>> hugetlb mappings is a check in can_madv_lru_vma().  To allow support for
>> hugetlb mappings create and use a new routine madvise_dontneed_valid_vma()
>> that will allow hugetlb mappings.
>>
>> Signed-off-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
> 
> I briefly tested the patch and it seems that when calling madvise(MADV_DONTNEED)
> with the range unaligned to hugepage size (like 4kB) triggered the following crash.
> Could you double check around the address range issue?

Thanks Naoya!  My bad for not considering this and doing more testing.
-- 
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