+ selftests-mm-reimplement-is_backed_by_thp-with-more-precise-check.patch added to mm-new branch

[Andrew Morton <akpm@linux-foundation.org>]

The patch titled
     Subject: selftests/mm: reimplement is_backed_by_thp() with more precise check
has been added to the -mm mm-new branch.  Its filename is
     selftests-mm-reimplement-is_backed_by_thp-with-more-precise-check.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/selftests-mm-reimplement-is_backed_by_thp-with-more-precise-check.patch

This patch will later appear in the mm-new branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Note, mm-new is a provisional staging ground for work-in-progress
patches, and acceptance into mm-new is a notification for others take
notice and to finish up reviews.  Please do not hesitate to respond to
review feedback and post updated versions to replace or incrementally
fixup patches in mm-new.

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: Zi Yan <ziy@nvidia.com>
Subject: selftests/mm: reimplement is_backed_by_thp() with more precise check
Date: Mon, 18 Aug 2025 14:46:20 -0400

and rename it to is_backed_by_folio().

is_backed_by_folio() checks if the given vaddr is backed a folio with
a given order. It does so by:
1. getting the pfn of the vaddr;
2. checking kpageflags of the pfn;

if order is greater than 0:
3. checking kpageflags of the head pfn;
4. checking kpageflags of all tail pfns.

pmd_order is added to split_huge_page_test.c and replaces max_order.

Link: https://lkml.kernel.org/r/20250818184622.1521620-4-ziy@nvidia.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Wei Yang <richard.weiyang@gmail.com>
Reviewed-by: wang lian <lianux.mm@gmail.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Donet Tom <donettom@linux.ibm.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Mariano Pache <npache@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 tools/testing/selftests/mm/split_huge_page_test.c |   88 ++++++++----
 tools/testing/selftests/mm/vm_util.c              |   13 +
 tools/testing/selftests/mm/vm_util.h              |    4 
 3 files changed, 81 insertions(+), 24 deletions(-)

--- a/tools/testing/selftests/mm/split_huge_page_test.c~selftests-mm-reimplement-is_backed_by_thp-with-more-precise-check
+++ a/tools/testing/selftests/mm/split_huge_page_test.c
@@ -25,6 +25,7 @@
 uint64_t pagesize;
 unsigned int pageshift;
 uint64_t pmd_pagesize;
+unsigned int pmd_order;
 
 #define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages"
 #define SMAP_PATH "/proc/self/smaps"
@@ -34,26 +35,66 @@ 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)
-
-static int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file)
+static bool is_backed_by_folio(char *vaddr, int order, int pagemap_fd,
+		int kpageflags_fd)
 {
-	uint64_t paddr;
-	uint64_t page_flags;
+	unsigned long pfn_head;
+	uint64_t pfn_flags;
+	unsigned long pfn;
+	unsigned long i;
+
+	pfn = pagemap_get_pfn(pagemap_fd, vaddr);
 
-	if (pagemap_file) {
-		pread(pagemap_file, &paddr, sizeof(paddr),
-			((long)vaddr >> pageshift) * sizeof(paddr));
+	/* non present page */
+	if (pfn == -1UL)
+		return false;
 
-		if (kpageflags_file) {
-			pread(kpageflags_file, &page_flags, sizeof(page_flags),
-				(paddr & PFN_MASK) * sizeof(page_flags));
+	if (pageflags_get(pfn, kpageflags_fd, &pfn_flags))
+		goto fail;
 
-			return !!(page_flags & KPF_THP);
-		}
+	/* check for order-0 pages */
+	if (!order) {
+		if (pfn_flags & (KPF_THP | KPF_COMPOUND_HEAD | KPF_COMPOUND_TAIL))
+			return false;
+		return true;
 	}
-	return 0;
+
+	/* non THP folio */
+	if (!(pfn_flags & KPF_THP))
+		return false;
+
+	pfn_head = pfn & ~((1 << order) - 1);
+
+	if (pageflags_get(pfn_head, kpageflags_fd, &pfn_flags))
+		goto fail;
+
+	/* head PFN has no compound_head flag set */
+	if (!(pfn_flags & (KPF_THP | KPF_COMPOUND_HEAD)))
+		return false;
+
+	/* check all tail PFN flags */
+	for (i = 1; i < 1UL << order; i++) {
+		if (pageflags_get(pfn_head + i, kpageflags_fd, &pfn_flags))
+			goto fail;
+		if (!(pfn_flags & (KPF_THP | KPF_COMPOUND_TAIL)))
+			return false;
+	}
+
+	/*
+	 * check the PFN after this folio, but if its flags cannot be obtained,
+	 * assume this folio has the expected order
+	 */
+	if (pageflags_get(pfn_head + (1UL << order), kpageflags_fd, &pfn_flags))
+		return true;
+
+	/* this folio is bigger than the given order */
+	if (pfn_flags & (KPF_THP | KPF_COMPOUND_TAIL))
+		return false;
+
+	return true;
+fail:
+	ksft_exit_fail_msg("Failed to get folio info\n");
+	return false;
 }
 
 static void write_file(const char *path, const char *buf, size_t buflen)
@@ -234,7 +275,7 @@ static void split_pte_mapped_thp(void)
 	thp_size = 0;
 	for (i = 0; i < pagesize * 4; i++)
 		if (i % pagesize == 0 &&
-		    is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd))
+		    is_backed_by_folio(&pte_mapped[i], pmd_order, pagemap_fd, kpageflags_fd))
 			thp_size++;
 
 	if (thp_size != 4)
@@ -251,7 +292,7 @@ static void split_pte_mapped_thp(void)
 			ksft_exit_fail_msg("%ld byte corrupted\n", i);
 
 		if (i % pagesize == 0 &&
-		    is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd))
+		    !is_backed_by_folio(&pte_mapped[i], 0, pagemap_fd, kpageflags_fd))
 			thp_size++;
 	}
 
@@ -523,7 +564,6 @@ int main(int argc, char **argv)
 	const char *fs_loc;
 	bool created_tmp;
 	int offset;
-	unsigned int max_order;
 	unsigned int nr_pages;
 	unsigned int tests;
 
@@ -544,28 +584,28 @@ int main(int argc, char **argv)
 		ksft_exit_fail_msg("Reading PMD pagesize failed\n");
 
 	nr_pages = pmd_pagesize / pagesize;
-	max_order =  sz2ord(pmd_pagesize, pagesize);
-	tests = 2 + (max_order - 1) + (2 * max_order) + (max_order - 1) * 4 + 2;
+	pmd_order = sz2ord(pmd_pagesize, pagesize);
+	tests = 2 + (pmd_order - 1) + (2 * pmd_order) + (pmd_order - 1) * 4 + 2;
 	ksft_set_plan(tests);
 
 	fd_size = 2 * pmd_pagesize;
 
 	split_pmd_zero_pages();
 
-	for (i = 0; i < max_order; i++)
+	for (i = 0; i < pmd_order; i++)
 		if (i != 1)
 			split_pmd_thp_to_order(i);
 
 	split_pte_mapped_thp();
-	for (i = 0; i < max_order; i++)
+	for (i = 0; i < pmd_order; i++)
 		split_file_backed_thp(i);
 
 	created_tmp = prepare_thp_fs(optional_xfs_path, fs_loc_template,
 			&fs_loc);
-	for (i = max_order - 1; i >= 0; i--)
+	for (i = pmd_order - 1; i >= 0; i--)
 		split_thp_in_pagecache_to_order_at(fd_size, fs_loc, i, -1);
 
-	for (i = 0; i < max_order; i++)
+	for (i = 0; i < pmd_order; i++)
 		for (offset = 0;
 		     offset < nr_pages;
 		     offset += MAX(nr_pages / 4, 1 << i))
--- a/tools/testing/selftests/mm/vm_util.c~selftests-mm-reimplement-is_backed_by_thp-with-more-precise-check
+++ a/tools/testing/selftests/mm/vm_util.c
@@ -338,6 +338,19 @@ int detect_hugetlb_page_sizes(size_t siz
 	return count;
 }
 
+int pageflags_get(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;
+}
+
 /* If `ioctls' non-NULL, the allowed ioctls will be returned into the var */
 int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len,
 			      bool miss, bool wp, bool minor, uint64_t *ioctls)
--- a/tools/testing/selftests/mm/vm_util.h~selftests-mm-reimplement-is_backed_by_thp-with-more-precise-check
+++ a/tools/testing/selftests/mm/vm_util.h
@@ -18,6 +18,9 @@
 #define PM_SWAP                       BIT_ULL(62)
 #define PM_PRESENT                    BIT_ULL(63)
 
+#define KPF_COMPOUND_HEAD             BIT_ULL(15)
+#define KPF_COMPOUND_TAIL             BIT_ULL(16)
+#define KPF_THP                       BIT_ULL(22)
 /*
  * Ignore the checkpatch warning, we must read from x but don't want to do
  * anything with it in order to trigger a read page fault. We therefore must use
@@ -85,6 +88,7 @@ bool check_huge_shmem(void *addr, int nr
 int64_t allocate_transhuge(void *ptr, int pagemap_fd);
 unsigned long default_huge_page_size(void);
 int detect_hugetlb_page_sizes(size_t sizes[], int max);
+int pageflags_get(unsigned long pfn, int kpageflags_fd, uint64_t *flags);
 
 int uffd_register(int uffd, void *addr, uint64_t len,
 		  bool miss, bool wp, bool minor);
_

Patches currently in -mm which might be from ziy@nvidia.com are

selftests-mm-fix-force_read-to-read-input-value-correctly.patch
mm-huge_memory-add-new_order-and-offset-to-split_huge_pages-pr_debug.patch
selftests-mm-mark-all-functions-static-in-split_huge_page_testc.patch
selftests-mm-reimplement-is_backed_by_thp-with-more-precise-check.patch
selftests-mm-add-check_after_split_folio_orders-helper.patch
selftests-mm-check-after-split-folio-orders-in-split_huge_page_test.patch