On Mon, Sep 01, 2025 at 09:22:44AM +0200, David Hildenbrand wrote:
>On 31.08.25 04:27, Wei Yang wrote:
>
>Subject: "selftests/mm: verify page content after remapping PMD through PTEs"
>
>> After mremap(), add a check on content to see whether mremap corrupt
>> data.
>>
>> Signed-off-by: Wei Yang <richard.weiy...@gmail.com>
>>
>> ---
>> v2: add check on content instead of just test backed folio
>
>I'm confused, don't we have that exact check later in the function?
>
>Your v1 might have been better, unless I am missing something.
>
Maybe I should insist a little.
>> ---
>> tools/testing/selftests/mm/split_huge_page_test.c | 6 +++++-
>> 1 file changed, 5 insertions(+), 1 deletion(-)
>>
>> diff --git a/tools/testing/selftests/mm/split_huge_page_test.c
>> b/tools/testing/selftests/mm/split_huge_page_test.c
>> index 10ae65ea032f..229b6dcabece 100644
>> --- a/tools/testing/selftests/mm/split_huge_page_test.c
>> +++ b/tools/testing/selftests/mm/split_huge_page_test.c
>> @@ -423,10 +423,14 @@ static void split_pte_mapped_thp(void)
>> /* smap does not show THPs after mremap, use kpageflags instead */
>> thp_size = 0;
>> - for (i = 0; i < pagesize * 4; i++)
>> + for (i = 0; i < pagesize * 4; i++) {
>> + if (pte_mapped[i] != (char)i)
>> + ksft_exit_fail_msg("%ld byte corrupted\n", i);
>> +
>> if (i % pagesize == 0 &&
>> is_backed_by_folio(&pte_mapped[i], pmd_order, pagemap_fd,
>> kpageflags_fd))
>> thp_size++;
>> + }
>> if (thp_size != 4)
>> ksft_exit_fail_msg("Some THPs are missing during mremap\n");
>
>I'm a bit confused with this test in general.
>
>We do a
>
>pte_mapped = mremap(one_page, pagesize, pagesize, MREMAP_MAYMOVE);
>
>which I read as a "NOP".
>
>Questions
>
>(a) Will this actually do anything? Also, maybe it does now, but can't the
>kernel just optimize that out in the future?
>
>(b) Is it even guaranteed that we can access > pagesize afterwards? I mean,
>we specify MREMAP_MAYMOVE.
>
To be honest, I am not fully understand the operations here.
>
>I would suggest to just use mprotect/madvise to pte-map a PMD-THP.
>
>This is, of course, independent of this patch.
>
>--
>Cheers
>
>David / dhildenb
--
Wei Yang
Help you, Help me
