On 9/7/26 10:19, 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.
>
> Suggested-by: David Hildenbrand (Arm) <[email protected]>
> Suggested-by: Zi Yan <[email protected]>
> Reviewed-by: Zi Yan <[email protected]>
> Reviewed-by: Baolin Wang <[email protected]>
> Tested-by: Baolin Wang <[email protected]>
> Acked-by: Lorenzo Stoakes (ARM) <[email protected]>
> Signed-off-by: Yeoreum Yun <[email protected]>
> ---
> tools/testing/selftests/mm/vm_util.c | 145
> ++++++++++++++++++++++-------------
> tools/testing/selftests/mm/vm_util.h | 1 +
> 2 files changed, 92 insertions(+), 54 deletions(-)
>
> diff --git a/tools/testing/selftests/mm/vm_util.c
> b/tools/testing/selftests/mm/vm_util.c
> index 4821a3563036..dc62ce84e143 100644
[...]
>
> - if (hpage_size == pmd_pagesize)
> - return __check_pmd_huge(addr, "AnonHugePages: ", nr_hpages,
> hpage_size);
> +static bool check_huge_type(uint64_t categories, uint64_t kpageflags,
> + enum check_huge_type type)
> +{
> + const bool file = categories & PAGE_IS_FILE;
> + const bool swapbacked = kpageflags & KPF_SWAPBACKED;
> +
> + switch (type) {
> + case CHECK_HUGE_ANON:
> + return !file;
> + case CHECK_HUGE_FILE:
> + return file && !swapbacked;
> + case CHECK_HUGE_SHMEM:
> + return file & swapbacked;
> + }
Why do we even need CHECK_HUGE_SHMEM?
That's really just a legacy thing for using smaps to identify huge pages.
It's sufficient to identify CHECK_HUGE_FILE if you know that you have shmem
mapping.
You will not arbitrarily have non-shmem folios in a shmem mapping :)
>
> - return check_large_folios(addr, len, nr_hpages, hpage_size);
> + return false;
> }
>
> -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);
> + 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) {
> + close(pagemap_fd);
No need to cleanup when exiting.
> + 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;
> + ret = true;
> +
> +out:
> + close(pagemap_fd);
> + close(kpageflags_fd);
> + return ret;
> }
--
Cheers,
David
