> On 9/29/26 12:01, Yeoreum Yun wrote:
> > On Tue, Sep 29, 2026 at 10:07:37AM +0200, David Hildenbrand (Arm) wrote:
> >> On 9/24/26 21:11, Yeoreum Yun wrote:
> >>> check_large_folios() only checks for large folios without distinguishing
> >>> between anonymous and file-backed huge pages.
> >>>
> >>> To add huge page type checking, integrate the huge page checks into
> >>> __check_huge():
> >>>
> >>> 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 huge page type.
> >>>
> >>> Suggested-by: David Hildenbrand (Arm) <[email protected]>
> >>> Suggested-by: Zi Yan <[email protected]>
> >>> Signed-off-by: Yeoreum Yun <[email protected]>
> >>> ---
> >>
> >> Instead of merging both things (detecting mapping vs. detecting anon vs.
> >> file),
> >> could we simply perform the anon vs. file change separately?
> >>
> >> Doing another pagemap walk that focuses on that should end up with
> >> something
> >> that is easier to read.
> >
> > Okay. I'll change like below in next-spin:
> >
> > -------&<-------
> >
> > @@ -411,57 +400,78 @@ static bool check_huge_type(uint64_t categories, enum
> > check_huge_type type)
> > return false;
> > }
> >
> > -static bool __check_pmd_huge(void *addr, size_t len, int nr_hpages,
> > - uint64_t hpage_size, enum check_huge_type type)
> > +static bool __check_huge(void *addr, size_t len, int nr_hpages,
> > + uint64_t hpage_size, enum check_huge_type type)
> > {
> > {
> > - int pagemap_fd;
> > + bool ret = false;
> > + int pagemap_fd, kpageflags_fd;
> > int nr_pmd_mappings = 0;
> > + uint64_t pmd_pagesize, scan_mapping_size;
> > uint64_t categories;
> > + 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");
> > +
> > + 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;
> > +
> > pagemap_fd = open(PAGEMAP_PATH, O_RDONLY);
> > if (pagemap_fd < 0)
> > ksft_exit_fail_perror("open pagemap");
> >
> > - for (; start < end; start += hpage_size) {
> > + kpageflags_fd = open(KPAGEFLAGS_PATH, O_RDONLY);
> > + if (kpageflags_fd < 0)
> > + ksft_exit_fail_perror("open kpageflags");
> > +
> > + for (; start < end; start += scan_mapping_size) {
> > categories = pagemap_scan_get_categories(pagemap_fd, start);
> > - if (!(categories & PAGE_IS_HUGE))
> > + pfn = pagemap_get_pfn(pagemap_fd, start);
> > + if (pfn == -1UL) {
> > + if (!allow_nonpresent)
> > + goto out;
> > continue;
> > - if (check_huge_type(categories, type))
> > + }
> > + if (!check_huge_type(categories, type))
> > + goto out;
> > + }
> > +
> > + if (!check_pmd_mapping) {
> > + ret = check_large_folios(pagemap_fd, kpageflags_fd,
> > + addr, len, nr_hpages, hpage_size);
> > + goto out;
> > + }
> > +
> > + for (start = addr; start < end; start += scan_mapping_size) {
> > + categories = pagemap_scan_get_categories(pagemap_fd, start);
> > + if (categories & PAGE_IS_HUGE)
> > nr_pmd_mappings++;
> > }
> > - close(pagemap_fd);
> >
> > - return nr_hpages == nr_pmd_mappings;
> > + if (nr_pmd_mappings != nr_hpages)
> > + goto out;
> > + ret = true;
> > +
> > +out:
> > + close(pagemap_fd);
> > + close(kpageflags_fd);
> > + return ret;
> > }
> >
>
> I'd leave existing __check_huge() mostly alone, and instead have an additional
> function that checks the type.
>
> Essentially a __check_type() or sth that we run after the large folio / pmd
> check.
So, You mean like this?
-------&<-------
-enum check_huge_type {
- CHECK_HUGE_ANON,
- CHECK_HUGE_FILE,
+enum check_type {
+ CHECK_TYPE_ANON,
+ CHECK_TYPE_FILE,
};
-static bool check_huge_type(uint64_t categories, enum check_huge_type type)
+static bool __check_type(void *addr, size_t len, uint64_t page_size,
+ bool allow_nonpresent, enum check_type type)
{
- const bool file = categories & PAGE_IS_FILE;
+ bool ret = false;
+ int pagemap_fd, kpageflags_fd;
+ char *start = addr;
+ char *end = start + len;
+ uint64_t categories;
+ unsigned long pfn;
+
+ pagemap_fd = open(PAGEMAP_PATH, O_RDONLY);
+ if (pagemap_fd < 0)
+ ksft_exit_fail_perror("open pagemap");
+
+ kpageflags_fd = open(KPAGEFLAGS_PATH, O_RDONLY);
+ if (kpageflags_fd < 0)
+ ksft_exit_fail_perror("open kpageflags");
- switch (type) {
- case CHECK_HUGE_ANON:
- return !file;
- case CHECK_HUGE_FILE:
- return file;
+ for (; start < end; start += page_size) {
+ categories = pagemap_scan_get_categories(pagemap_fd, start);
+ pfn = pagemap_get_pfn(pagemap_fd, start);
+ if (pfn == -1UL) {
+ if (!allow_nonpresent)
+ goto out;
+ continue;
+ }
+
+ if ((type == CHECK_TYPE_FILE) != !!(categories & PAGE_IS_FILE))
+ goto out;
}
- return false;
+ ret = true;
+
+out:
+ close(kpageflags_fd);
+ close(pagemap_fd);
+ return ret;
}
-static bool __check_pmd_huge(void *addr, size_t len, int nr_hpages,
- uint64_t hpage_size, enum check_huge_type type)
+static bool __check_huge(void *addr, size_t len, int nr_hpages,
+ uint64_t hpage_size)
{
+ bool ret = false;
int pagemap_fd;
int nr_pmd_mappings = 0;
+ uint64_t pmd_pagesize;
uint64_t categories;
char *start = addr;
char *end = start + len;
+ pmd_pagesize = read_pmd_pagesize();
+ 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_perror("open pagemap");
- for (; start < end; start += hpage_size) {
+ if (hpage_size != pmd_pagesize) {
+ ret = check_large_folios(addr, len, nr_hpages, hpage_size);
+ goto out;
+ }
+
+ for (start = addr; start < end; start += hpage_size) {
categories = pagemap_scan_get_categories(pagemap_fd, start);
- if (!(categories & PAGE_IS_HUGE))
- continue;
- if (check_huge_type(categories, type))
+ if (categories & PAGE_IS_HUGE)
nr_pmd_mappings++;
}
- close(pagemap_fd);
- return nr_hpages == nr_pmd_mappings;
+ if (nr_pmd_mappings != nr_hpages)
+ goto out;
+
+ ret = true;
+
+out:
+ close(pagemap_fd);
+ return ret;
}
bool check_huge_anon(void *addr, size_t len, int nr_hpages, uint64_t
hpage_size)
{
- uint64_t pmd_pagesize = read_pmd_pagesize();
-
- if (!pmd_pagesize)
- ksft_exit_fail_msg("reading PMD pagesize failed\n");
+ /* Some mTHP tests check a partially populated PMD-sized range. */
+ const bool allow_nonpresent = (uint64_t)nr_hpages * hpage_size < len;
+ const uint64_t scan_mapping_size = (nr_hpages > 0) ? hpage_size :
psize();
- if (hpage_size == pmd_pagesize)
- return __check_pmd_huge(addr, len, nr_hpages, hpage_size,
- CHECK_HUGE_ANON);
+ if (! __check_huge(addr, len, nr_hpages, hpage_size))
+ return false;
- return check_large_folios(addr, len, nr_hpages, hpage_size);
+ return __check_type(addr, len, scan_mapping_size, allow_nonpresent,
+ CHECK_TYPE_ANON);
}
bool check_huge_file(void *addr, size_t len, int nr_hpages, uint64_t
hpage_size)
{
- uint64_t pmd_pagesize = read_pmd_pagesize();
+ /* Some mTHP tests check a partially populated PMD-sized range. */
+ const bool allow_nonpresent = (uint64_t)nr_hpages * hpage_size < len;
+ const uint64_t scan_mapping_size = (nr_hpages > 0) ? hpage_size :
psize();
- if (!pmd_pagesize)
- ksft_exit_fail_msg("reading PMD pagesize failed\n");
-
- if (hpage_size == pmd_pagesize)
- return __check_pmd_huge(addr, len, nr_hpages, hpage_size,
- CHECK_HUGE_FILE);
+ if (! __check_huge(addr, len, nr_hpages, hpage_size))
+ return false;
- return check_large_folios(addr, len, nr_hpages, hpage_size);
+ return __check_type(addr, len, scan_mapping_size, allow_nonpresent,
+ CHECK_TYPE_FILE);
}
--
Sincerely,
Yeoreum Yun
