selftests/mm: add check_after_split_folio_orders() helper

The helper gathers a 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.

The helper will be used the upcoming commit.

Link: https://lkml.kernel.org/r/20250818184622.1521620-5-ziy@nvidia.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Tested-by: 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>
Cc: wang lian <lianux.mm@gmail.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

tools/testing/selftests/mm/split_huge_page_test.c

@@ -98,6 +98,158 @@ fail:
 	return false;
 }
 
+static int vaddr_pageflags_get(char *vaddr, int pagemap_fd, int kpageflags_fd,
+		uint64_t *flags)
+{
+	unsigned long pfn;
+
+	pfn = pagemap_get_pfn(pagemap_fd, vaddr);
+
+	/* non-present PFN */
+	if (pfn == -1UL)
+		return 1;
+
+	if (pageflags_get(pfn, kpageflags_fd, flags))
+		return -1;
+
+	return 0;
+}
+
+/*
+ * gather_after_split_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_after_split_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.
+ *
+ * NOTE: the function is used to check folio orders after a split is performed,
+ * so it assumes [vaddr_start, len) fully maps to after-split folios within that
+ * range.
+ *
+ * Return: 0 - no error, -1 - unhandled cases
+ */
+static int gather_after_split_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 == -1 || kpageflags_fd == -1)
+		return -1;
+	if (!orders)
+		return -1;
+	if (nr_orders <= 0)
+		return -1;
+
+	for (vaddr = vaddr_start; vaddr < vaddr_start + len;) {
+		char *next_folio_vaddr;
+		int status;
+
+		status = vaddr_pageflags_get(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 {
+			vaddr += psize();
+			continue;
+		}
+
+		next_folio_vaddr = vaddr + (1UL << (cur_order + pshift()));
+
+		if (next_folio_vaddr >= vaddr_start + len)
+			break;
+
+		while ((status = vaddr_pageflags_get(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;
+			}
+
+			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;
+}
+
+static int check_after_split_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_after_split_folio_orders(vaddr_start, len, pagemap_fd,
+				     kpageflags_fd, vaddr_orders, nr_orders);
+	if (status)
+		ksft_exit_fail_msg("gather folio info failed\n");
+
+	for (i = 0; i < nr_orders; i++)
+		if (vaddr_orders[i] != orders[i]) {
+			ksft_print_msg("order %d: expected: %d got %d\n", i,
+				       orders[i], vaddr_orders[i]);
+			status = -1;
+		}
+
+	free(vaddr_orders);
+	return status;
+}
+
 static void write_file(const char *path, const char *buf, size_t buflen)
 {
 	int fd;