Hi,

> On 9/21/26 12:40, Yeoreum Yun wrote:
> > Since glibc commit 321e1fc73f (“malloc: Enable 2MB THP by default on 
> > AArch64”),
> > glibc may call madvise(MADV_HUGEPAGE) for sufficiently large allocations
> > made by memalign().
> > 
> > The underlying VMA may start at a different address from the aligned
> > address returned by memalign(). Furthermore, a subsequent
> > madvise(MADV_HUGEPAGE) call does not split the VMA because the flag is
> > already set.
> > 
> > This causes split_huge_page_test to fail because the check_huge_xxx()
> > helpers incorrectly require the address returned by memalign() to
> > match the VMA start address reported in /proc/self/smaps.
> > 
> > Instead of relying on /proc/self/smaps, use /proc/self/pagemap and
> > /proc/kpageflags to detect huge-page mappings and large folios:
> > 
> >   1. If hpage_size == pmd_pagesize, check PAGE_IS_HUGE instead of
> >      using check_large_folios(), since only the mapping type matters.
> >      This identifies PMD-mapped huge pages.
> >   2. Otherwise, use check_large_folios() to detect large folios. This
> >      covers mTHP cases.
> >   3. Check the folio flags according to the type of huge page.
> > 
> > Since shmem pages are also file-backed, simply check whether the page
> > is file-backed.
> > 
> > Suggested-by: David Hildenbrand (Arm) <[email protected]>
> > Suggested-by: Zi Yan <[email protected]>
> 
> Do we need a Fixes: tag?

Since this change is required for the chaning of behavior of glibc,
I don't think we don't need to add Fixes tag in here?

> 
> > Signed-off-by: Yeoreum Yun <[email protected]>
> > ---
> >  tools/testing/selftests/mm/vm_util.c | 137 
> > +++++++++++++++++++++--------------
> >  1 file changed, 84 insertions(+), 53 deletions(-)
> > 
> > diff --git a/tools/testing/selftests/mm/vm_util.c 
> > b/tools/testing/selftests/mm/vm_util.c
> > index 4821a35630363..a7c5caf6925e0 100644
> > --- a/tools/testing/selftests/mm/vm_util.c
> > +++ b/tools/testing/selftests/mm/vm_util.c
> > @@ -351,31 +351,13 @@ char *__get_smap_entry(void *addr, const char 
> > *pattern, char *buf, size_t len)
> >     return entry;
> >  }
> >  
> > -static bool __check_pmd_huge(void *addr, char *pattern, int nr_hpages,
> > -             uint64_t hpage_size)
> > -{
> > -   char buffer[MAX_LINE_LENGTH];
> > -   uint64_t thp = -1;
> > -   char *entry;
> > -
> > -   entry = __get_smap_entry(addr, pattern, buffer, sizeof(buffer));
> > -   if (!entry)
> > -           goto err_out;
> > -
> > -   if (sscanf(entry, "%9" SCNu64 " kB", &thp) != 1)
> > -           ksft_exit_fail_msg("Reading smap error\n");
> > -
> > -err_out:
> > -   return thp == (nr_hpages * (hpage_size >> 10));
> > -}
> > -
> > -static bool check_large_folios(void *addr, size_t len, int nr_hpages,
> > -           uint64_t hpage_size)
> > +static bool check_large_folios(int pagemap_fd, int kpageflags_fd,
> > +                          void *addr, size_t len, int nr_hpages,
> > +                          uint64_t hpage_size)
> 
> The function used two tab indent for a reason ;)
> 
> Use two tabs also in the functions you change below.

Okay.

> 
> >  
> > -bool check_huge_file(void *addr, size_t len, int nr_hpages, uint64_t 
> > hpage_size)
> > +static bool __check_huge(void *addr, size_t len, int nr_hpages,
> > +                    uint64_t hpage_size, enum check_huge_type type)
> 
> 
> >  {
> > -   uint64_t pmd_pagesize = read_pmd_pagesize();
> > +   bool ret = false;
> > +   int pagemap_fd, kpageflags_fd;
> > +   int nr_pmd_mappings = 0;
> > +   uint64_t pmd_pagesize, scan_mapping_size;
> > +   uint64_t categories, kpf;
> > +   unsigned long pfn;
> > +   bool check_pmd_mapping, allow_nonpresent;
> > +   char *start = addr;
> > +   char *end = start + len;
> >  
> > +   pmd_pagesize = read_pmd_pagesize();
> >     if (!pmd_pagesize)
> >             ksft_exit_fail_msg("reading PMD pagesize failed\n");
> >  
> > -   if (hpage_size == pmd_pagesize)
> > -           return __check_pmd_huge(addr, "FilePmdMapped:", nr_hpages, 
> > hpage_size);
> > +   check_pmd_mapping = (hpage_size == pmd_pagesize);
> 
> No need for ()

I see.

> 
> > +   scan_mapping_size = (nr_hpages > 0) ? hpage_size : psize();
> > +   /* Some mTHP tests check a partially populated PMD-sized range. */
> > +   allow_nonpresent = (uint64_t)nr_hpages * hpage_size < len;
> >  
> > -   return check_large_folios(addr, len, nr_hpages, hpage_size);
> > +   pagemap_fd = open(PAGEMAP_PATH, O_RDONLY);
> > +   if (pagemap_fd < 0)
> > +           ksft_exit_fail_msg("open pagemap fail\n");
> > +
> > +   kpageflags_fd = open(KPAGEFLAGS_PATH, O_RDONLY);
> > +   if (kpageflags_fd < 0)
> > +           ksft_exit_fail_msg("open kpageflags fail\n");
> > +
> > +   if (!check_pmd_mapping &&
> > +       !check_large_folios(pagemap_fd, kpageflags_fd,
> > +                           addr, len, nr_hpages, hpage_size))
> > +           goto out;
> > +
> > +   for (; start < end; start += scan_mapping_size) {
> > +           categories = pagemap_scan_get_categories(pagemap_fd, start);
> > +           pfn = pagemap_get_pfn(pagemap_fd, start);
> > +           if (pfn == -1UL) {
> > +                   if (!allow_nonpresent)
> > +                           goto out;
> > +                   else
> > +                           continue;
> > +           }
> > +           if (pageflags_get(pfn, kpageflags_fd, &kpf))
> > +                   ksft_exit_fail_msg("read kpageflags: %s\n", 
> > strerror(errno));
> > +           if (check_pmd_mapping && (categories & PAGE_IS_HUGE))
> > +                   nr_pmd_mappings++;
> > +           if (kpf & KPF_COMPOUND_TAIL)
> > +                   continue;
> > +           if (!check_huge_type(categories, kpf, type))
> > +                   goto out;
> > +   }
> > +
> > +   if (check_pmd_mapping && (nr_pmd_mappings != nr_hpages))
> > +           goto out;
> 
> 
> There is way too much happening here, which makes this rather hard to review.
> 
> Why can't we just focus on the smaps change for now?

Yeap. I think we can simplify as your suggestion with a little bit
change. I'll spin again.

Thanks.

> 
> I.e., something like the following (untested)
> 
> diff --git a/tools/testing/selftests/mm/vm_util.c 
> b/tools/testing/selftests/mm/vm_util.c
> index 4821a35630363..5d348d6985026 100644
> --- a/tools/testing/selftests/mm/vm_util.c
> +++ b/tools/testing/selftests/mm/vm_util.c
> @@ -351,24 +351,6 @@ char *__get_smap_entry(void *addr, const char *pattern, 
> char *buf, size_t len)
>       return entry;
>  }
>  
> -static bool __check_pmd_huge(void *addr, char *pattern, int nr_hpages,
> -               uint64_t hpage_size)
> -{
> -     char buffer[MAX_LINE_LENGTH];
> -     uint64_t thp = -1;
> -     char *entry;
> -
> -     entry = __get_smap_entry(addr, pattern, buffer, sizeof(buffer));
> -     if (!entry)
> -             goto err_out;
> -
> -     if (sscanf(entry, "%9" SCNu64 " kB", &thp) != 1)
> -             ksft_exit_fail_msg("Reading smap error\n");
> -
> -err_out:
> -     return thp == (nr_hpages * (hpage_size >> 10));
> -}
> -
>  static bool check_large_folios(void *addr, size_t len, int nr_hpages,
>               uint64_t hpage_size)
>  {
> @@ -410,20 +392,34 @@ static bool check_large_folios(void *addr, size_t len, 
> int nr_hpages,
>       return ret;
>  }
>  
> -bool check_huge_anon(void *addr, size_t len, int nr_hpages, uint64_t 
> hpage_size)
> +static bool __check_pmds(void *start, size_t len, int expected_file_pmds,
> +             int expected_anon_pmds, uint64_t pmd_pagesize)
>  {
> -     uint64_t pmd_pagesize = read_pmd_pagesize();
> +     int found_anon_pmds = 0, found_file_pmds = 0;
> +     int pagemap_fd;
> +     void *addr;
>  
> -     if (!pmd_pagesize)
> -             ksft_exit_fail_msg("reading PMD pagesize failed\n");
> +     pagemap_fd = open(PAGEMAP_PATH, O_RDONLY);
> +     if (pagemap_fd < 0)
> +             ksft_exit_fail_msg("open pagemap fail\n");
>  
> -     if (hpage_size == pmd_pagesize)
> -             return __check_pmd_huge(addr, "AnonHugePages: ", nr_hpages, 
> hpage_size);
> +     for (addr = start; addr < start + len; addr += pmd_pagesize) {
> +             const uint64_t categories = 
> pagemap_scan_get_categories(pagemap_fd, addr);
>  
> -     return check_large_folios(addr, len, nr_hpages, hpage_size);
> +             if (!(categories & PAGE_IS_HUGE))
> +                     continue;
> +             if (categories & PAGE_IS_FILE)
> +                     found_file_pmds++;
> +             else
> +                     found_anon_pmds++;
> +     }
> +
> +     close(pagemap_fd);
> +     return found_anon_pmds == expected_anon_pmds &&
> +            found_file_pmds == expected_file_pmds;
>  }
>  
> -bool check_huge_file(void *addr, size_t len, int nr_hpages, uint64_t 
> hpage_size)
> +bool check_huge_anon(void *addr, size_t len, int nr_hpages, uint64_t 
> hpage_size)
>  {
>       uint64_t pmd_pagesize = read_pmd_pagesize();
>  
> @@ -431,12 +427,12 @@ bool check_huge_file(void *addr, size_t len, int 
> nr_hpages, uint64_t hpage_size)
>               ksft_exit_fail_msg("reading PMD pagesize failed\n");
>  
>       if (hpage_size == pmd_pagesize)
> -             return __check_pmd_huge(addr, "FilePmdMapped:", nr_hpages, 
> hpage_size);
> +             return __check_pmds(addr, len, 0, nr_hpages, pmd_pagesize);
>  
>       return check_large_folios(addr, len, nr_hpages, hpage_size);
>  }
>  
> -bool check_huge_shmem(void *addr, size_t len, int nr_hpages, uint64_t 
> hpage_size)
> +bool check_huge_file(void *addr, size_t len, int nr_hpages, uint64_t 
> hpage_size)
>  {
>       uint64_t pmd_pagesize = read_pmd_pagesize();
>  
> @@ -444,11 +440,16 @@ bool check_huge_shmem(void *addr, size_t len, int 
> nr_hpages, uint64_t hpage_size
>               ksft_exit_fail_msg("reading PMD pagesize failed\n");
>  
>       if (hpage_size == pmd_pagesize)
> -             return __check_pmd_huge(addr, "ShmemPmdMapped:", nr_hpages, 
> hpage_size);
> +             return __check_pmds(addr, len, nr_hpages, 0, pmd_pagesize);
>  
>       return check_large_folios(addr, len, nr_hpages, hpage_size);
>  }
>  
> +bool check_huge_shmem(void *addr, size_t len, int nr_hpages, uint64_t 
> hpage_size)
> +{
> +     return check_huge_file(addr, len, nr_hpages, hpage_size);
> +}
> +
>  int64_t allocate_transhuge(void *ptr, int pagemap_fd)
>  {
>       uint64_t ent[2];
> -- 
> 2.43.0
> -- 
> Cheers,
> 
> David
> 

-- 
Sincerely,
Yeoreum Yun

Reply via email to