On 12 Aug 2025, at 23:38, wang lian wrote:
>> On Aug 12, 2025, at 23:55, Zi Yan <z...@nvidia.com> wrote:
>>
>> The helper gathers an folio order statistics of folios within a virtual
>> address range and checks it against a given order list. It aims to provide
>> a more precise folio order check instead of just checking the existence of
>> PMD folios.
>>
>> Signed-off-by: Zi Yan <z...@nvidia.com>
>> ---
>> .../selftests/mm/split_huge_page_test.c | 4 +-
>> tools/testing/selftests/mm/vm_util.c | 173 ++++++++++++++++++
>> tools/testing/selftests/mm/vm_util.h | 7 +
>> 3 files changed, 181 insertions(+), 3 deletions(-)
>>
>> diff --git a/tools/testing/selftests/mm/split_huge_page_test.c
>> b/tools/testing/selftests/mm/split_huge_page_test.c
>> index 5d07b0b89226..63ac82f0b9e0 100644
>> --- a/tools/testing/selftests/mm/split_huge_page_test.c
>> +++ b/tools/testing/selftests/mm/split_huge_page_test.c
>> @@ -34,8 +34,6 @@ uint64_t pmd_pagesize;
>> #define PID_FMT_OFFSET "%d,0x%lx,0x%lx,%d,%d"
>> #define PATH_FMT "%s,0x%lx,0x%lx,%d"
>>
>> -#define PFN_MASK ((1UL<<55)-1)
>> -#define KPF_THP (1UL<<22)
>> #define GET_ORDER(nr_pages) (31 - __builtin_clz(nr_pages))
>>
>> int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file)
>> @@ -49,7 +47,7 @@ int is_backed_by_thp(char *vaddr, int pagemap_file, int
>> kpageflags_file)
>>
>> if (kpageflags_file) {
>> pread(kpageflags_file, &page_flags, sizeof(page_flags),
>> - (paddr & PFN_MASK) * sizeof(page_flags));
>> + PAGEMAP_PFN(paddr) * sizeof(page_flags));
>>
>> return !!(page_flags & KPF_THP);
>> }
>> diff --git a/tools/testing/selftests/mm/vm_util.c
>> b/tools/testing/selftests/mm/vm_util.c
>> index 6a239aa413e2..4d952d1bc96d 100644
>> --- a/tools/testing/selftests/mm/vm_util.c
>> +++ b/tools/testing/selftests/mm/vm_util.c
>> @@ -338,6 +338,179 @@ int detect_hugetlb_page_sizes(size_t sizes[], int max)
>> return count;
>> }
>>
>> +static int get_pfn_flags(unsigned long pfn, int kpageflags_fd, uint64_t
>> *flags)
>> +{
>> + size_t count;
>> +
>> + count = pread(kpageflags_fd, flags, sizeof(*flags),
>> + pfn * sizeof(*flags));
>> +
>> + if (count != sizeof(*flags))
>> + return -1;
>> +
>> + return 0;
>> +}
>> +
>> +static int get_page_flags(char *vaddr, int pagemap_fd, int kpageflags_fd,
>> + uint64_t *flags)
>> +{
>> + unsigned long pfn;
>> +
>> + pfn = pagemap_get_pfn(pagemap_fd, vaddr);
>> + /*
>> + * Treat non-present page as a page without any flag, so that
>> + * gather_folio_orders() just record the current folio order.
>> + */
>> + if (pfn == -1UL) {
>> + *flags = 0;
>> + return 1;
>> + }
>> +
>> + if (get_pfn_flags(pfn, kpageflags_fd, flags))
>> + return -1;
>> +
>> + return 0;
>> +}
>> +
>> +/*
>> + * gather_folio_orders - scan through [vaddr_start, len) and record folio
>> orders
>> + * @vaddr_start: start vaddr
>> + * @len: range length
>> + * @pagemap_fd: file descriptor to /proc/<pid>/pagemap
>> + * @kpageflags_fd: file descriptor to /proc/kpageflags
>> + * @orders: output folio order array
>> + * @nr_orders: folio order array size
>> + *
>> + * gather_folio_orders() scan through [vaddr_start, len) and check all
>> folios
>> + * within the range and record their orders. All order-0 pages will be
>> recorded.
>> + * Non-present vaddr is skipped.
>> + *
>> + *
>> + * Return: 0 - no error, -1 - unhandled cases
>> + */
>> +static int gather_folio_orders(char *vaddr_start, size_t len,
>> + int pagemap_fd, int kpageflags_fd,
>> + int orders[], int nr_orders)
>> +{
>> + uint64_t page_flags = 0;
>> + int cur_order = -1;
>> + char *vaddr;
>> +
>> + if (!pagemap_fd || !kpageflags_fd)
>> + return -1;
>> + if (nr_orders <= 0)
>> + return -1;
>> +
>> + for (vaddr = vaddr_start; vaddr < vaddr_start + len;) {
>> + char *next_folio_vaddr;
>> + int status;
>> +
>> + status = get_page_flags(vaddr, pagemap_fd, kpageflags_fd,
>> + &page_flags);
>> + if (status < 0)
>> + return -1;
>> +
>> + /* skip non present vaddr */
>> + if (status == 1) {
>> + vaddr += psize();
>> + continue;
>> + }
>> +
>> + /* all order-0 pages with possible false postive (non folio) */
>> + if (!(page_flags & (KPF_COMPOUND_HEAD | KPF_COMPOUND_TAIL))) {
>> + orders[0]++;
>> + vaddr += psize();
>> + continue;
>> + }
>> +
>> + /* skip non thp compound pages */
>> + if (!(page_flags & KPF_THP)) {
>> + vaddr += psize();
>> + continue;
>> + }
>> +
>> + /* vpn points to part of a THP at this point */
>> + if (page_flags & KPF_COMPOUND_HEAD)
>> + cur_order = 1;
>> + else {
>> + /* not a head nor a tail in a THP? */
>> + if (!(page_flags & KPF_COMPOUND_TAIL))
>> + return -1;
>> +
>> + vaddr += psize();
>> + continue;
>> + }
>> +
>> + next_folio_vaddr = vaddr + (1UL << (cur_order + pshift()));
>> +
>> + if (next_folio_vaddr >= vaddr_start + len)
>> + break;
>> +
>> + while ((status = get_page_flags(next_folio_vaddr, pagemap_fd,
>> + kpageflags_fd,
>> + &page_flags)) >= 0) {
>> + /*
>> + * non present vaddr, next compound head page, or
>> + * order-0 page
>> + */
>> + if (status == 1 ||
>> + (page_flags & KPF_COMPOUND_HEAD) ||
>> + !(page_flags & (KPF_COMPOUND_HEAD |
>> KPF_COMPOUND_TAIL))) {
>> + if (cur_order < nr_orders) {
>> + orders[cur_order]++;
>> + cur_order = -1;
>> + vaddr = next_folio_vaddr;
>> + }
>> + break;
>> + }
>> +
>> + /* not a head nor a tail in a THP? */
>> + if (!(page_flags & KPF_COMPOUND_TAIL))
>> + return -1;
>> +
>> + cur_order++;
>> + next_folio_vaddr = vaddr + (1UL << (cur_order +
>> pshift()));
>> + }
>> +
>> + if (status < 0)
>> + return status;
>> + }
>> + if (cur_order > 0 && cur_order < nr_orders)
>> + orders[cur_order]++;
>> + return 0;
>> +}
>> +
>> +int check_folio_orders(char *vaddr_start, size_t len, int pagemap_fd,
>> + int kpageflags_fd, int orders[], int nr_orders)
>> +{
>> + int *vaddr_orders;
>> + int status;
>> + int i;
>> +
>> + vaddr_orders = (int *)malloc(sizeof(int) * nr_orders);
>> +
>> + if (!vaddr_orders)
>> + ksft_exit_fail_msg("Cannot allocate memory for vaddr_orders");
>> +
>> + memset(vaddr_orders, 0, sizeof(int) * nr_orders);
>> + status = gather_folio_orders(vaddr_start, len, pagemap_fd,
>> + kpageflags_fd, vaddr_orders, nr_orders);
>> + if (status)
>> + goto out;
>> +
>> + status = 0;
>
> Nit.
> It seems redundant.
> Would you consider removing it for a bit more conciseness?
> This doesn't block my approval, of course.
> Reviewed-by: wang lian <lianux...@gmail.com>
Sure. Thanks.
Best Regards,
Yan, Zi
