There is room for improvement, so let's clean up a bit:

(1) Define "4" as a constant.

(2) SKIP if we fail to allocate all THPs (e.g., fragmented) and add
    recovery code for all other failure cases: no need to exit the test.

(3) Rename "len" to thp_area_size, and "one_page" to "thp_area".

(4) Allocate a new area "page_area" into which we will mremap the
    pages; add "page_area_size". Now we can easily merge the two
    mremap instances into a single one.

(5) Iterate THPs instead of bytes when checking for missed THPs after
    mremap.

(6) Rename "pte_mapped2" to "tmp", used to verify mremap(MAP_FIXED)
    result.

(7) Split the corruption test from the failed-split test, so we can just
    iterate bytes vs. thps naturally.

(8) Extend comments and clarify why we are using mremap in the first
    place.

Reviewed-by: Zi Yan <ziy@nvidia.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 .../selftests/mm/split_huge_page_test.c       | 123 +++++++++++-------
 1 file changed, 74 insertions(+), 49 deletions(-)

diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c
index 72d6d8bb329ed..7731191cc8e9b 100644
--- a/tools/testing/selftests/mm/split_huge_page_test.c
+++ b/tools/testing/selftests/mm/split_huge_page_test.c
@@ -389,67 +389,92 @@ static void split_pmd_thp_to_order(int order)
 
 static void split_pte_mapped_thp(void)
 {
-	char *one_page, *pte_mapped, *pte_mapped2;
-	size_t len = 4 * pmd_pagesize;
-	uint64_t thp_size;
+	const size_t nr_thps = 4;
+	const size_t thp_area_size = nr_thps * pmd_pagesize;
+	const size_t page_area_size = nr_thps * pagesize;
+	char *thp_area, *tmp, *page_area = MAP_FAILED;
 	size_t i;
 
-	one_page = mmap((void *)(1UL << 30), len, PROT_READ | PROT_WRITE,
+	thp_area = mmap((void *)(1UL << 30), thp_area_size, PROT_READ | PROT_WRITE,
 			MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
-	if (one_page == MAP_FAILED)
-		ksft_exit_fail_msg("Fail to allocate memory: %s\n", strerror(errno));
+	if (thp_area == MAP_FAILED) {
+		ksft_test_result_fail("Fail to allocate memory: %s\n", strerror(errno));
+		return;
+	}
 
-	madvise(one_page, len, MADV_HUGEPAGE);
+	madvise(thp_area, thp_area_size, MADV_HUGEPAGE);
 
-	for (i = 0; i < len; i++)
-		one_page[i] = (char)i;
+	for (i = 0; i < thp_area_size; i++)
+		thp_area[i] = (char)i;
 
-	if (!check_huge_anon(one_page, 4, pmd_pagesize))
-		ksft_exit_fail_msg("No THP is allocated\n");
+	if (!check_huge_anon(thp_area, nr_thps, pmd_pagesize)) {
+		ksft_test_result_skip("Not all THPs allocated\n");
+		goto out;
+	}
 
-	/* remap the first pagesize of first THP */
-	pte_mapped = mremap(one_page, pagesize, pagesize, MREMAP_MAYMOVE);
-
-	/* remap the Nth pagesize of Nth THP */
-	for (i = 1; i < 4; i++) {
-		pte_mapped2 = mremap(one_page + pmd_pagesize * i + pagesize * i,
-				     pagesize, pagesize,
-				     MREMAP_MAYMOVE|MREMAP_FIXED,
-				     pte_mapped + pagesize * i);
-		if (pte_mapped2 == MAP_FAILED)
-			ksft_exit_fail_msg("mremap failed: %s\n", strerror(errno));
-	}
-
-	/* smap does not show THPs after mremap, use kpageflags instead */
-	thp_size = 0;
-	for (i = 0; i < pagesize * 4; i++)
-		if (i % pagesize == 0 &&
-		    is_backed_by_folio(&pte_mapped[i], pmd_order, pagemap_fd, kpageflags_fd))
-			thp_size++;
-
-	if (thp_size != 4)
-		ksft_exit_fail_msg("Some THPs are missing during mremap\n");
-
-	/* split all remapped THPs */
-	write_debugfs(PID_FMT, getpid(), (uint64_t)pte_mapped,
-		      (uint64_t)pte_mapped + pagesize * 4, 0);
-
-	/* smap does not show THPs after mremap, use kpageflags instead */
-	thp_size = 0;
-	for (i = 0; i < pagesize * 4; i++) {
-		if (pte_mapped[i] != (char)i)
-			ksft_exit_fail_msg("%ld byte corrupted\n", i);
+	/*
+	 * To challenge spitting code, we will mremap a single page of each
+	 * THP (page[i] of thp[i]) in the thp_area into page_area. This will
+	 * replace the PMD mappings in the thp_area by PTE mappings first,
+	 * but leaving the THP unsplit, to then create a page-sized hole in
+	 * the thp_area.
+	 * We will then manually trigger splitting of all THPs through the
+	 * single mremap'ed pages of each THP in the page_area.
+	 */
+	page_area = mmap(NULL, page_area_size, PROT_READ | PROT_WRITE,
+			MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	if (page_area == MAP_FAILED) {
+		ksft_test_result_fail("Fail to allocate memory: %s\n", strerror(errno));
+		goto out;
+	}
 
-		if (i % pagesize == 0 &&
-		    !is_backed_by_folio(&pte_mapped[i], 0, pagemap_fd, kpageflags_fd))
-			thp_size++;
+	for (i = 0; i < nr_thps; i++) {
+		tmp = mremap(thp_area + pmd_pagesize * i + pagesize * i,
+			     pagesize, pagesize, MREMAP_MAYMOVE|MREMAP_FIXED,
+			     page_area + pagesize * i);
+		if (tmp != MAP_FAILED)
+			continue;
+		ksft_test_result_fail("mremap failed: %s\n", strerror(errno));
+		goto out;
+	}
+
+	/*
+	 * Verify that our THPs were not split yet. Note that
+	 * check_huge_anon() cannot be used as it checks for PMD mappings.
+	 */
+	for (i = 0; i < nr_thps; i++) {
+		if (is_backed_by_folio(page_area + i * pagesize, pmd_order,
+				       pagemap_fd, kpageflags_fd))
+			continue;
+		ksft_test_result_fail("THP %zu missing after mremap\n", i);
+		goto out;
 	}
 
-	if (thp_size)
-		ksft_exit_fail_msg("Still %ld THPs not split\n", thp_size);
+	/* Split all THPs through the remapped pages. */
+	write_debugfs(PID_FMT, getpid(), (uint64_t)page_area,
+		      (uint64_t)page_area + page_area_size, 0);
+
+	/* Corruption during mremap or split? */
+	for (i = 0; i < page_area_size; i++) {
+		if (page_area[i] == (char)i)
+			continue;
+		ksft_test_result_fail("%zu byte corrupted\n", i);
+		goto out;
+	}
+
+	/* Split failed? */
+	for (i = 0; i < nr_thps; i++) {
+		if (is_backed_by_folio(page_area + i * pagesize, 0,
+				       pagemap_fd, kpageflags_fd))
+			continue;
+		ksft_test_result_fail("THP %zu not split\n", i);
+	}
 
 	ksft_test_result_pass("Split PTE-mapped huge pages successful\n");
-	munmap(one_page, len);
+out:
+	munmap(thp_area, thp_area_size);
+	if (page_area != MAP_FAILED)
+		munmap(page_area, page_area_size);
 }
 
 static void split_file_backed_thp(int order)
-- 
2.50.1

On Tue, Sep 02, 2025 at 06:25:36PM +0200, David Hildenbrand wrote:
>There is room for improvement, so let's clean up a bit:
>
>(1) Define "4" as a constant.
>
>(2) SKIP if we fail to allocate all THPs (e.g., fragmented) and add
>    recovery code for all other failure cases: no need to exit the test.
>
>(3) Rename "len" to thp_area_size, and "one_page" to "thp_area".
>
>(4) Allocate a new area "page_area" into which we will mremap the
>    pages; add "page_area_size". Now we can easily merge the two
>    mremap instances into a single one.
>
>(5) Iterate THPs instead of bytes when checking for missed THPs after
>    mremap.
>
>(6) Rename "pte_mapped2" to "tmp", used to verify mremap(MAP_FIXED)
>    result.
>
>(7) Split the corruption test from the failed-split test, so we can just
>    iterate bytes vs. thps naturally.
>
>(8) Extend comments and clarify why we are using mremap in the first
>    place.
>
>Reviewed-by: Zi Yan <ziy@nvidia.com>
>Signed-off-by: David Hildenbrand <david@redhat.com>

Reviewed-by: Wei Yang <richard.weiyang@gmail.com>

-- 
Wei Yang
Help you, Help me