From bd212a7dbdb151e9bacb02857a222e25b28c229d Mon Sep 17 00:00:00 2001 From: Yeoreum Yun Date: Tue, 29 Sep 2026 11:33:18 +0100 Subject: [PATCH] kselftest: mm: return fail when child test result is fail in khugepaged Patch series "kselftest: mm: fix intermittent failure khugepaged test", v4. There are intermittent failures in collapse_max_ptes_swap() and collapse_max_ptes_shared() when using the khugepaged_context: # Run test: collapse_max_ptes_shared (khugepaged:anon) # Allocate huge page... OK # Share huge page over fork()... OK # Trigger CoW on page 1023 of 2048... OK # Maybe collapse with max_ptes_shared exceeded.... OK # Trigger CoW on page 1024 of 2048... Fail Bail out! Unexpected huge page # Planned tests != run tests (26 != 23) # Totals: pass:23 fail:0 xfail:0 xpass:0 skip:0 error:0 # Run test: collapse_max_ptes_swap (khugepaged:anon) # Swapout 257 of 2048 pages... OK # Maybe collapse with max_ptes_swap exceeded.... OK # Swapout 256 of 2048 pages... OK Bail out! Unexpected huge page # Planned tests != run tests (26 != 17) # Totals: pass:17 fail:0 xfail:0 xpass:0 skip:0 error:0 This happens because khugepaged may collapse the pages before wait_for_scan() is called, causing a sanity check that expects uncollapsed pages to fail. For example, in collapse_max_ptes_swap(), after faulting the pages back in and paging out up to max_ptes_swap pages, khugepaged may collapse them again before c->collapse() is called. To prevent this, mark the VMA with MADV_NOHUGEPAGE after it has been collapsed by wait_for_scan() for anon. This prevents khugepaged from collapsing it again before c->collapse() is called. Also, fix false-positive results when a child process fails in tests such as collapse_fork*() or collapse_max_ptes_shared(): # ------------------------- # running ./khugepaged -s 2 # ------------------------- # # Run test: collapse_max_ptes_shared (khugepaged:anon) # Allocate huge page... OK # Share huge page over fork()... OK # Trigger CoW on page 1023 of 2048... OK # Maybe collapse with max_ptes_shared exceeded.... OK # Trigger CoW on page 1024 of 2048... Fail Bail out! Unexpected huge page # Planned tests != run tests (26 != 23) # Totals: pass:23 fail:0 xfail:0 xpass:0 skip:0 error:0 // child failed. # Check if parent still has huge page... OK // parent hpage success ok 24 collapse_max_ptes_shared // considered as success ... # Totals: pass:26 fail:0 xfail:0 xpass:0 skip:0 error:0 This failure was observed on NVIDIA Spark with 16KB page. This patch (of 2): Although the child process in collapse_fork*() or collapse_max_ptes_shared() reports `KSFT_FAIL`, the result is ignored because the test only checks whether the parent's page was collapsed into a huge page. As a result, the test is considered successful whenever the parent's page is a huge page, even if the child test fails, as shown below: # # Run test: collapse_max_ptes_shared (khugepaged:anon) # Allocate huge page... OK # Share huge page over fork()... OK # Trigger CoW on page 1023 of 2048... OK # Maybe collapse with max_ptes_shared exceeded.... OK # Trigger CoW on page 1024 of 2048... Fail Bail out! Unexpected huge page # Planned tests != run tests (26 != 23) # Totals: pass:23 fail:0 xfail:0 xpass:0 skip:0 error:0 // child failed. # Check if parent still has huge page... OK // parent hpage success ok 24 collapse_max_ptes_shared // considered as success ... # Totals: pass:26 fail:0 xfail:0 xpass:0 skip:0 error:0 To address this, propagate the child's failure and skip the subsequent check in the parent. Link: https://lore.kernel.org/20260929-fix_khugepagd_fail-v4-0-2169c18f2576@arm.com Link: https://lore.kernel.org/20260929-fix_khugepagd_fail-v4-1-2169c18f2576@arm.com Signed-off-by: Yeoreum Yun Signed-off-by: Andrew Morton Reviewed-by: Baolin Wang Reviewed-by: Gregory Price (Meta) Reviewed-by: Lorenzo Stoakes (ARM) Acked-by: David Hildenbrand (Arm) Acked-by: Zi Yan Cc: Liam R. Howlett Cc: Nico Pache Cc: Ryan Roberts Cc: Dev Jain Cc: Barry Song Cc: Lance Yang Cc: Usama Arif Cc: Kiryl Shutsemau Cc: Vlastimil Babka Cc: Mike Rapoport Cc: Suren Baghdasaryan Cc: Michal Hocko Cc: Shuah Khan --- tools/testing/selftests/mm/khugepaged.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/tools/testing/selftests/mm/khugepaged.c b/tools/testing/selftests/mm/khugepaged.c index a2ac3b3ca5de..2aa7c9197158 100644 --- a/tools/testing/selftests/mm/khugepaged.c +++ b/tools/testing/selftests/mm/khugepaged.c @@ -1053,6 +1053,8 @@ static void collapse_fork(struct collapse_context *c, struct mem_ops *ops) wait(&wstatus); exit_status = WEXITSTATUS(wstatus); + if (exit_status == KSFT_FAIL) + goto out; ksft_print_msg("Check if parent still has small page..."); if (ops->check_huge(p, hpage_pmd_size, 0, hpage_pmd_size)) @@ -1060,6 +1062,7 @@ static void collapse_fork(struct collapse_context *c, struct mem_ops *ops) else fail("Fail"); validate_memory(p, 0, page_size); +out: ops->cleanup_area(p, hpage_pmd_size); ksft_test_result_report(exit_status, "%s\n", __func__); } @@ -1100,6 +1103,8 @@ static void collapse_fork_compound(struct collapse_context *c, struct mem_ops *o wait(&wstatus); exit_status = WEXITSTATUS(wstatus); + if (exit_status == KSFT_FAIL) + goto out; ksft_print_msg("Check if parent still has huge page..."); if (ops->check_huge(p, hpage_pmd_size, 1, hpage_pmd_size)) @@ -1107,6 +1112,7 @@ static void collapse_fork_compound(struct collapse_context *c, struct mem_ops *o else fail("Fail"); validate_memory(p, 0, hpage_pmd_size); +out: ops->cleanup_area(p, hpage_pmd_size); ksft_test_result_report(exit_status, "%s\n", __func__); } @@ -1158,6 +1164,8 @@ static void collapse_max_ptes_shared(struct collapse_context *c, struct mem_ops wait(&wstatus); exit_status = WEXITSTATUS(wstatus); + if (exit_status == KSFT_FAIL) + goto out; ksft_print_msg("Check if parent still has huge page..."); if (ops->check_huge(p, hpage_pmd_size, 1, hpage_pmd_size)) @@ -1165,6 +1173,7 @@ static void collapse_max_ptes_shared(struct collapse_context *c, struct mem_ops else fail("Fail"); validate_memory(p, 0, hpage_pmd_size); +out: ops->cleanup_area(p, hpage_pmd_size); ksft_test_result_report(exit_status, "%s\n", __func__); }