From: "Kiryl Shutsemau (Meta)" <[email protected]> A khugepaged test has to tell "not collapsed" from "not scanned yet", and nothing in the selftests can. wait_for_scan() in khugepaged.c comes closest: it polls full_scans until the counter has advanced by two, since the pass in progress may already have passed the test's mm. But it only returns in time if scan_sleep_millisecs happens to be short, and it is private to that one test.
Add khugepaged_full_pass() to hugepage_settings, built on the same advance-by-two wait but driven through sysfs: a store to scan_sleep_millisecs wakes the daemon, so the barrier completes whatever the scan cadence. A store made while the daemon is scanning rather than sleeping is lost, so the helper keeps storing until the pass lands. One wake completes one pass only if pages_to_scan covers every mm on the list, so callers need it large. Settings pushes must not start passes of their own. A store to either sleep knob wakes the daemon, so thp_write_settings() now writes a khugepaged knob only when its value changes. Assisted-by: LLM Tested-by: Muhammad Usama Anjum <[email protected]> Signed-off-by: Kiryl Shutsemau (Meta) <[email protected]> --- .../testing/selftests/mm/hugepage_settings.c | 60 ++++++++++++++++--- .../testing/selftests/mm/hugepage_settings.h | 2 + 2 files changed, 53 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/mm/hugepage_settings.c b/tools/testing/selftests/mm/hugepage_settings.c index d7917dce3aba..ca73f9ac8e9b 100644 --- a/tools/testing/selftests/mm/hugepage_settings.c +++ b/tools/testing/selftests/mm/hugepage_settings.c @@ -183,6 +183,13 @@ void thp_read_settings(struct thp_settings *settings) } } +/* A store to either sleep knob wakes khugepaged, so write only on change */ +static void thp_update_num(const char *name, unsigned long num) +{ + if (thp_read_num(name) != num) + thp_write_num(name, num); +} + void thp_write_settings(struct thp_settings *settings) { struct khugepaged_settings *khugepaged = &settings->khugepaged; @@ -198,15 +205,15 @@ void thp_write_settings(struct thp_settings *settings) shmem_enabled_strings[settings->shmem_enabled]); thp_write_num("use_zero_page", settings->use_zero_page); - thp_write_num("khugepaged/defrag", khugepaged->defrag); - thp_write_num("khugepaged/alloc_sleep_millisecs", - khugepaged->alloc_sleep_millisecs); - thp_write_num("khugepaged/scan_sleep_millisecs", - khugepaged->scan_sleep_millisecs); - thp_write_num("khugepaged/max_ptes_none", khugepaged->max_ptes_none); - thp_write_num("khugepaged/max_ptes_swap", khugepaged->max_ptes_swap); - thp_write_num("khugepaged/max_ptes_shared", khugepaged->max_ptes_shared); - thp_write_num("khugepaged/pages_to_scan", khugepaged->pages_to_scan); + thp_update_num("khugepaged/defrag", khugepaged->defrag); + thp_update_num("khugepaged/alloc_sleep_millisecs", + khugepaged->alloc_sleep_millisecs); + thp_update_num("khugepaged/scan_sleep_millisecs", + khugepaged->scan_sleep_millisecs); + thp_update_num("khugepaged/max_ptes_none", khugepaged->max_ptes_none); + thp_update_num("khugepaged/max_ptes_swap", khugepaged->max_ptes_swap); + thp_update_num("khugepaged/max_ptes_shared", khugepaged->max_ptes_shared); + thp_update_num("khugepaged/pages_to_scan", khugepaged->pages_to_scan); if (dev_queue_read_ahead_path[0]) write_num(dev_queue_read_ahead_path, settings->read_ahead_kb); @@ -230,6 +237,41 @@ void thp_write_settings(struct thp_settings *settings) } } +/* + * Wait for a full khugepaged scan pass that started after this call: the + * pass in progress may already have passed this mm, so full_scans has to + * advance twice. + * + * A store to scan_sleep_millisecs wakes the daemon, but one made while it + * is scanning rather than sleeping is lost, so keep storing until the pass + * lands. + * + * One wake is one pass only if pages_to_scan covers every mm on the list. + */ +bool khugepaged_full_pass(unsigned int timeout_s) +{ + unsigned long deadline_ms = timeout_s * 1000UL; + unsigned long elapsed_ms = 0, poll_ms = 10; + unsigned long sleep_ms; + int pass; + + sleep_ms = thp_read_num("khugepaged/scan_sleep_millisecs"); + for (pass = 0; pass < 2; pass++) { + unsigned long target = + thp_read_num("khugepaged/full_scans") + 1; + + while (thp_read_num("khugepaged/full_scans") < target) { + if (elapsed_ms >= deadline_ms) + return false; + thp_write_num("khugepaged/scan_sleep_millisecs", + sleep_ms); + usleep(poll_ms * 1000); + elapsed_ms += poll_ms; + } + } + return true; +} + struct thp_settings *thp_current_settings(void) { if (!settings_index) { diff --git a/tools/testing/selftests/mm/hugepage_settings.h b/tools/testing/selftests/mm/hugepage_settings.h index a1d12e2ffd62..2ea169d11796 100644 --- a/tools/testing/selftests/mm/hugepage_settings.h +++ b/tools/testing/selftests/mm/hugepage_settings.h @@ -83,6 +83,8 @@ static inline void thp_save_settings(void) hugepage_save_settings(/* thp = */ true, /* hugetlb = */ false); } +bool khugepaged_full_pass(unsigned int timeout_s); + void thp_set_read_ahead_path(char *path); unsigned long thp_supported_orders(void); unsigned long thp_shmem_supported_orders(void); -- 2.54.0
