selftests/mm: reimplement is_backed_by_thp() with more precise check

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.

[ziy@nvidia.com: reduce code duplication, per David]
  Link: https://lkml.kernel.org/r/F54782D6-65A3-4D35-AE03-8ADE636EE258@nvidia.com
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>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
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>

3 files changed, 82 insertions, 24 deletions

diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c
index 001a6ff24bf7..7be06dae663e 100644
--- a/tools/testing/selftests/mm/split_huge_page_test.c
+++ b/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 +35,67 @@ 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;
+	const unsigned long nr_pages = 1UL << order;
+	unsigned long pfn_head;
+	uint64_t pfn_flags;
+	unsigned long pfn;
+	unsigned long i;
 
-	if (pagemap_file) {
-		pread(pagemap_file, &paddr, sizeof(paddr),
-			((long)vaddr >> pageshift) * sizeof(paddr));
+	pfn = pagemap_get_pfn(pagemap_fd, vaddr);
 
-		if (kpageflags_file) {
-			pread(kpageflags_file, &page_flags, sizeof(page_flags),
-				(paddr & PFN_MASK) * sizeof(page_flags));
+	/* non present page */
+	if (pfn == -1UL)
+		return false;
 
-			return !!(page_flags & KPF_THP);
-		}
+	if (pageflags_get(pfn, kpageflags_fd, &pfn_flags))
+		goto fail;
+
+	/* 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 & ~(nr_pages - 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 < nr_pages; 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 + nr_pages, 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 +276,7 @@ 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 +293,7 @@ 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++;
 	}
 
@@ -525,7 +567,6 @@ 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;
 
@@ -546,28 +587,28 @@ 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))
diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c
index 6a239aa413e2..741fc129313d 100644
--- a/tools/testing/selftests/mm/vm_util.c
+++ b/tools/testing/selftests/mm/vm_util.c
@@ -338,6 +338,19 @@ int detect_hugetlb_page_sizes(size_t sizes[], int max)
 	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)
diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h
index 3da56feeb944..ab8722f482ae 100644
--- a/tools/testing/selftests/mm/vm_util.h
+++ b/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_hpages, uint64_t hpage_size);
 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);