selftests/mm: transhuge-stress: check duration inside page loop

transhuge-stress.c currently scans memory equal to RAM by default, in
jumps of hugepage size, trying to allocate and split a THP at each step. 
After the entire range is covered, it checks whether elapsed time is
greater than the duration.  But it is possible that the THP work it does
takes time more than the duration itself, causing the test to exceed the
CI timeout.

Check the elapsed time after each THP operation.  If the duration has
elapsed, break and end the test.  Adjust the statistics calculations to
accommodate partially completed passes.  Also, reject sizes which are
smaller than a huge page.

Link: https://lore.kernel.org/20260720103105.169955-1-sarthak.sharma@arm.com
Signed-off-by: Sarthak Sharma <sarthak.sharma@arm.com>
Reported-by: Aishwarya TCV <aishwarya.tcv@arm.com>
Suggested-by: Dev Jain <dev.jain@arm.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: David Hildenbrand <david@kernel.org>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Mark Brown <broonie@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nico Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 23 insertions, 7 deletions

diff --git a/tools/testing/selftests/mm/transhuge-stress.c b/tools/testing/selftests/mm/transhuge-stress.c
index 8eb0c5630e7e..a0f9fc900360 100644
--- a/tools/testing/selftests/mm/transhuge-stress.c
+++ b/tools/testing/selftests/mm/transhuge-stress.c
@@ -35,6 +35,7 @@ int main(int argc, char **argv)
 	size_t map_len;
 	int pagemap_fd;
 	int duration = 0;
+	double elapsed = 0;
 
 	ksft_print_header();
 
@@ -60,8 +61,6 @@ int main(int argc, char **argv)
 			len = atoll(argv[i]) << 20;
 	}
 
-	ksft_set_plan(1);
-
 	if (name) {
 		backing_fd = open(name, O_RDWR);
 		if (backing_fd == -1)
@@ -78,6 +77,10 @@ int main(int argc, char **argv)
 		ksft_exit_fail_msg("open pagemap\n");
 
 	len -= len % HPAGE_SIZE;
+	if (len == 0)
+		ksft_exit_fail_msg("len must be at least %d MiB\n",
+			HPAGE_SIZE >> 20);
+
 	ptr = mmap(NULL, len + HPAGE_SIZE, PROT_RW, mmap_flags, backing_fd, 0);
 	if (ptr == MAP_FAILED)
 		ksft_exit_fail_msg("initial mmap");
@@ -91,6 +94,7 @@ int main(int argc, char **argv)
 	if (!map)
 		ksft_exit_fail_msg("map malloc\n");
 
+	ksft_set_plan(1);
 	clock_gettime(CLOCK_MONOTONIC, &start);
 
 	while (1) {
@@ -125,16 +129,28 @@ int main(int argc, char **argv)
 			/* split transhuge page, keep last page */
 			if (madvise(p, HPAGE_SIZE - psize(), MADV_DONTNEED))
 				ksft_exit_fail_msg("MADV_DONTNEED");
+
+			if (duration > 0) {
+				clock_gettime(CLOCK_MONOTONIC, &b);
+				elapsed = b.tv_sec - start.tv_sec +
+					(b.tv_nsec - start.tv_nsec) / 1000000000.;
+				if (elapsed >= duration)
+					break;
+			}
 		}
 		clock_gettime(CLOCK_MONOTONIC, &b);
 		s = b.tv_sec - a.tv_sec + (b.tv_nsec - a.tv_nsec) / 1000000000.;
 
 		ksft_print_msg("%.3f s/loop, %.3f ms/page, %10.3f MiB/s\t"
-			       "%4d succeed, %4d failed, %4d different pages\n",
-			       s, s * 1000 / (len >> HPAGE_SHIFT), len / s / (1 << 20),
-			       nr_succeed, nr_failed, nr_pages);
-
-		if (duration > 0 && b.tv_sec - start.tv_sec >= duration) {
+				"%4d succeed, %4d failed, %4d different pages\n",
+				s, s * 1000 / (nr_failed + nr_succeed),
+				s > 0 ?
+					(double)(nr_failed + nr_succeed) *
+					(HPAGE_SIZE >> 20) / s :
+					0.0,
+				nr_succeed, nr_failed, nr_pages);
+
+		if (duration > 0 && elapsed >= duration) {
 			ksft_test_result_pass("Completed\n");
 			ksft_finished();
 		}